aboutsummaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/Makefile2
-rw-r--r--fs/ext4/acl.c98
-rw-r--r--fs/ext4/acl.h4
-rw-r--r--fs/ext4/balloc.c393
-rw-r--r--fs/ext4/block_validity.c21
-rw-r--r--fs/ext4/ext4.h241
-rw-r--r--fs/ext4/ext4_extents.h2
-rw-r--r--fs/ext4/ext4_jbd2.c8
-rw-r--r--fs/ext4/ext4_jbd2.h4
-rw-r--r--fs/ext4/extents.c1291
-rw-r--r--fs/ext4/file.c53
-rw-r--r--fs/ext4/fsync.c36
-rw-r--r--fs/ext4/ialloc.c208
-rw-r--r--fs/ext4/indirect.c1503
-rw-r--r--fs/ext4/inode.c2141
-rw-r--r--fs/ext4/ioctl.c77
-rw-r--r--fs/ext4/mballoc.c551
-rw-r--r--fs/ext4/mballoc.h12
-rw-r--r--fs/ext4/migrate.c111
-rw-r--r--fs/ext4/mmp.c10
-rw-r--r--fs/ext4/move_extent.c1
-rw-r--r--fs/ext4/namei.c63
-rw-r--r--fs/ext4/page-io.c82
-rw-r--r--fs/ext4/resize.c209
-rw-r--r--fs/ext4/super.c352
-rw-r--r--fs/ext4/truncate.h43
-rw-r--r--fs/ext4/xattr.c12
-rw-r--r--fs/ext4/xattr_security.c36
28 files changed, 4427 insertions, 3137 deletions
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 04109460ba9e..56fd8f865930 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_EXT4_FS) += ext4.o
ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
- mmp.o
+ mmp.o indirect.o
ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o
ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 60d900fcc3db..a5c29bb3b835 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -131,7 +131,7 @@ fail:
*
* inode->i_mutex: don't care
*/
-static struct posix_acl *
+struct posix_acl *
ext4_get_acl(struct inode *inode, int type)
{
int name_index;
@@ -198,12 +198,10 @@ ext4_set_acl(handle_t *handle, struct inode *inode, int type,
case ACL_TYPE_ACCESS:
name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
if (acl) {
- mode_t mode = inode->i_mode;
- error = posix_acl_equiv_mode(acl, &mode);
+ error = posix_acl_equiv_mode(acl, &inode->i_mode);
if (error < 0)
return error;
else {
- inode->i_mode = mode;
inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
if (error == 0)
@@ -237,29 +235,6 @@ ext4_set_acl(handle_t *handle, struct inode *inode, int type,
return error;
}
-int
-ext4_check_acl(struct inode *inode, int mask)
-{
- struct posix_acl *acl;
-
- if (mask & MAY_NOT_BLOCK) {
- if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
- return -ECHILD;
- return -EAGAIN;
- }
-
- acl = ext4_get_acl(inode, ACL_TYPE_ACCESS);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- if (acl) {
- int error = posix_acl_permission(inode, acl, mask);
- posix_acl_release(acl);
- return error;
- }
-
- return -EAGAIN;
-}
-
/*
* Initialize the ACLs of a new inode. Called from ext4_new_inode.
*
@@ -282,31 +257,20 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
inode->i_mode &= ~current_umask();
}
if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
- struct posix_acl *clone;
- mode_t mode;
-
if (S_ISDIR(inode->i_mode)) {
error = ext4_set_acl(handle, inode,
ACL_TYPE_DEFAULT, acl);
if (error)
goto cleanup;
}
- clone = posix_acl_clone(acl, GFP_NOFS);
- error = -ENOMEM;
- if (!clone)
- goto cleanup;
-
- mode = inode->i_mode;
- error = posix_acl_create_masq(clone, &mode);
- if (error >= 0) {
- inode->i_mode = mode;
- if (error > 0) {
- /* This is an extended ACL */
- error = ext4_set_acl(handle, inode,
- ACL_TYPE_ACCESS, clone);
- }
+ error = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode);
+ if (error < 0)
+ return error;
+
+ if (error > 0) {
+ /* This is an extended ACL */
+ error = ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, acl);
}
- posix_acl_release(clone);
}
cleanup:
posix_acl_release(acl);
@@ -330,9 +294,12 @@ cleanup:
int
ext4_acl_chmod(struct inode *inode)
{
- struct posix_acl *acl, *clone;
+ struct posix_acl *acl;
+ handle_t *handle;
+ int retries = 0;
int error;
+
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
if (!test_opt(inode->i_sb, POSIX_ACL))
@@ -340,31 +307,24 @@ ext4_acl_chmod(struct inode *inode)
acl = ext4_get_acl(inode, ACL_TYPE_ACCESS);
if (IS_ERR(acl) || !acl)
return PTR_ERR(acl);
- clone = posix_acl_clone(acl, GFP_KERNEL);
- posix_acl_release(acl);
- if (!clone)
- return -ENOMEM;
- error = posix_acl_chmod_masq(clone, inode->i_mode);
- if (!error) {
- handle_t *handle;
- int retries = 0;
-
- retry:
- handle = ext4_journal_start(inode,
- EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
- if (IS_ERR(handle)) {
- error = PTR_ERR(handle);
- ext4_std_error(inode->i_sb, error);
- goto out;
- }
- error = ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, clone);
- ext4_journal_stop(handle);
- if (error == -ENOSPC &&
- ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
+ error = posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+ if (error)
+ return error;
+retry:
+ handle = ext4_journal_start(inode,
+ EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+ if (IS_ERR(handle)) {
+ error = PTR_ERR(handle);
+ ext4_std_error(inode->i_sb, error);
+ goto out;
}
+ error = ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, acl);
+ ext4_journal_stop(handle);
+ if (error == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
out:
- posix_acl_release(clone);
+ posix_acl_release(acl);
return error;
}
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h
index 9d843d5deac4..18cb39ed7c7b 100644
--- a/fs/ext4/acl.h
+++ b/fs/ext4/acl.h
@@ -54,13 +54,13 @@ static inline int ext4_acl_count(size_t size)
#ifdef CONFIG_EXT4_FS_POSIX_ACL
/* acl.c */
-extern int ext4_check_acl(struct inode *, int);
+struct posix_acl *ext4_get_acl(struct inode *inode, int type);
extern int ext4_acl_chmod(struct inode *);
extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
#else /* CONFIG_EXT4_FS_POSIX_ACL */
#include <linux/sched.h>
-#define ext4_check_acl NULL
+#define ext4_get_acl NULL
static inline int
ext4_acl_chmod(struct inode *inode)
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 264f6949511e..f6dba4505f1c 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -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)
@@ -55,130 +57,169 @@ 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,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp)
+/* 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)
{
- ext4_fsblk_t tmp;
+ 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);
- /* 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;
+ /* 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;
}
}
- return used_blocks;
-}
-/* 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;
+ 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;
}
- 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);
+ 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;
}
- } else { /* For META_BG_BLOCK_GROUPS */
- bit_max += ext4_bg_num_gdb(sb, block_group);
}
- if (block_group == ngroups - 1) {
+ 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 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
+ * 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.
*/
- group_blocks = ext4_blocks_count(sbi->s_es) -
- ext4_group_first_block_no(sb, ngroups - 1);
- } else {
- group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
- }
+ 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);
+}
- free_blocks = group_blocks - bit_max;
+/* 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);
- if (bh) {
- ext4_fsblk_t start, tmp;
- int flex_bg = 0;
+ bit_max = ext4_num_base_meta_clusters(sb, block_group);
+ for (bit = 0; bit < bit_max; bit++)
+ ext4_set_bit(bit, bh->b_data);
- for (bit = 0; bit < bit_max; bit++)
- ext4_set_bit(bit, bh->b_data);
+ start = ext4_group_first_block_no(sb, block_group);
- start = ext4_group_first_block_no(sb, block_group);
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+ flex_bg = 1;
- 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);
- /* 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(EXT4_B2C(sbi, tmp - start), bh->b_data);
- tmp = ext4_inode_bitmap(sb, gdp);
+ 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);
-
- 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);
+ ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
}
- return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp);
+
+ /*
+ * 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)
+{
+ return num_clusters_in_group(sb, block_group) -
+ ext4_num_overhead_clusters(sb, block_group, gdp);
+}
/*
* The free blocks are managed by bitmaps. A file system contains several
@@ -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;
-
- free_blocks = percpu_counter_read_positive(fbc);
- dirty_blocks = percpu_counter_read_positive(dbc);
- root_blocks = 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);
+ s64 free_clusters, dirty_clusters, root_clusters;
+ struct percpu_counter *fcc = &sbi->s_freeclusters_counter;
+ struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter;
+
+ 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_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;
@@ -620,3 +664,76 @@ 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
+ *
+ * Return the ideal location to start allocating blocks for a
+ * newly created inode.
+ */
+ext4_fsblk_t ext4_inode_to_goal_block(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ ext4_group_t block_group;
+ ext4_grpblk_t colour;
+ int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));
+ ext4_fsblk_t bg_start;
+ ext4_fsblk_t last_block;
+
+ block_group = ei->i_block_group;
+ if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
+ /*
+ * If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME
+ * block groups per flexgroup, reserve the first block
+ * group for directories and special files. Regular
+ * files will start at the second block group. This
+ * tends to speed up directory access and improves
+ * fsck times.
+ */
+ block_group &= ~(flex_size-1);
+ if (S_ISREG(inode->i_mode))
+ block_group++;
+ }
+ bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
+ last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+
+ /*
+ * If we are doing delayed allocation, we don't need take
+ * colour into account.
+ */
+ if (test_opt(inode->i_sb, DELALLOC))
+ return bg_start;
+
+ if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
+ colour = (current->pid % 16) *
+ (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+ else
+ colour = (current->pid % 16) * ((last_block - bg_start) / 16);
+ return bg_start + colour;
+}
+
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index fac90f3fba80..8efb2f0a3447 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -246,3 +246,24 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
return 1;
}
+int ext4_check_blockref(const char *function, unsigned int line,
+ struct inode *inode, __le32 *p, unsigned int max)
+{
+ struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+ __le32 *bref = p;
+ unsigned int blk;
+
+ while (bref < p+max) {
+ blk = le32_to_cpu(*bref++);
+ if (blk &&
+ unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
+ blk, 1))) {
+ es->s_last_error_block = cpu_to_le64(blk);
+ ext4_error_inode(inode, function, line, blk,
+ "invalid block");
+ return -EIO;
+ }
+ }
+ return 0;
+}
+
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index fa44df879711..5b0e26a1272d 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -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;
@@ -175,6 +183,7 @@ struct mpage_da_data {
*/
#define EXT4_IO_END_UNWRITTEN 0x0001
#define EXT4_IO_END_ERROR 0x0002
+#define EXT4_IO_END_QUEUED 0x0004
struct ext4_io_page {
struct page *p_page;
@@ -238,8 +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
@@ -257,6 +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
*/
@@ -288,7 +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;
};
@@ -305,6 +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)
@@ -357,8 +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)
@@ -519,6 +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
@@ -526,6 +548,14 @@ struct ext4_new_group_data {
#define EXT4_FREE_BLOCKS_METADATA 0x0001
#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
@@ -536,9 +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)
@@ -561,9 +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
@@ -835,6 +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;
@@ -884,7 +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 */
@@ -916,6 +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 |= \
@@ -939,6 +966,8 @@ struct ext4_inode_info {
#define ext4_find_next_zero_bit find_next_zero_bit_le
#define ext4_find_next_bit find_next_bit_le
+extern void ext4_set_bits(void *bm, int cur, int len);
+
/*
* Maximal mount counts between two filesystem checks
*/
@@ -964,9 +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 */
@@ -1062,7 +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)
@@ -1082,6 +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 */
@@ -1090,6 +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 */
@@ -1113,10 +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;
@@ -1126,15 +1161,12 @@ struct ext4_sb_info {
struct journal_s *s_journal;
struct list_head s_orphan;
struct mutex s_orphan_lock;
- struct mutex s_resize_lock;
+ unsigned long s_resize_flags; /* Flags indicating if there
+ is a resizer */
unsigned long s_commit_interval;
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 */
@@ -1214,6 +1246,9 @@ struct ext4_sb_info {
/* Kernel thread for multiple mount protection */
struct task_struct *s_mmp_tsk;
+
+ /* record the last minlen when FITRIM is called. */
+ atomic_t s_last_trim_minblks;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1240,6 +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
*/
@@ -1352,6 +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
@@ -1394,7 +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
@@ -1727,9 +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,
@@ -1737,12 +1783,19 @@ 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 */
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
@@ -1767,7 +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 *);
@@ -1793,7 +1847,7 @@ extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
unsigned long count, int flags);
extern int ext4_mb_add_groupinfo(struct super_block *sb,
ext4_group_t i, struct ext4_group_desc *desc);
-extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
ext4_fsblk_t block, unsigned long count);
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
@@ -1830,10 +1884,27 @@ 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,
int used, int quota_claim);
+
+/* indirect.c */
+extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
+ struct ext4_map_blocks *map, int flags);
+extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
+ const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs);
+extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
+extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk);
+extern void ext4_ind_truncate(struct inode *inode);
+
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
@@ -1855,40 +1926,43 @@ extern int ext4_group_extend(struct super_block *sb,
ext4_fsblk_t n_blocks_count);
/* super.c */
-extern void __ext4_error(struct super_block *, const char *, unsigned int,
- const char *, ...)
- __attribute__ ((format (printf, 4, 5)));
+extern void *ext4_kvmalloc(size_t size, gfp_t flags);
+extern void *ext4_kvzalloc(size_t size, gfp_t flags);
+extern void ext4_kvfree(void *ptr);
+extern __printf(4, 5)
+void __ext4_error(struct super_block *, const char *, unsigned int,
+ const char *, ...);
#define ext4_error(sb, message...) __ext4_error(sb, __func__, \
__LINE__, ## message)
-extern void ext4_error_inode(struct inode *, const char *, unsigned int,
- ext4_fsblk_t, const char *, ...)
- __attribute__ ((format (printf, 5, 6)));
-extern void ext4_error_file(struct file *, const char *, unsigned int,
- ext4_fsblk_t, const char *, ...)
- __attribute__ ((format (printf, 5, 6)));
+extern __printf(5, 6)
+void ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t,
+ const char *, ...);
+extern __printf(5, 6)
+void ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
+ const char *, ...);
extern void __ext4_std_error(struct super_block *, const char *,
unsigned int, int);
-extern void __ext4_abort(struct super_block *, const char *, unsigned int,
- const char *, ...)
- __attribute__ ((format (printf, 4, 5)));
+extern __printf(4, 5)
+void __ext4_abort(struct super_block *, const char *, unsigned int,
+ const char *, ...);
#define ext4_abort(sb, message...) __ext4_abort(sb, __func__, \
__LINE__, ## message)
-extern void __ext4_warning(struct super_block *, const char *, unsigned int,
- const char *, ...)
- __attribute__ ((format (printf, 4, 5)));
+extern __printf(4, 5)
+void __ext4_warning(struct super_block *, const char *, unsigned int,
+ const char *, ...);
#define ext4_warning(sb, message...) __ext4_warning(sb, __func__, \
__LINE__, ## message)
-extern void ext4_msg(struct super_block *, const char *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
+extern __printf(3, 4)
+void ext4_msg(struct super_block *, const char *, const char *, ...);
extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
const char *, unsigned int, const char *);
#define dump_mmp_msg(sb, mmp, msg) __dump_mmp_msg(sb, mmp, __func__, \
__LINE__, msg)
-extern void __ext4_grp_locked_error(const char *, unsigned int, \
- struct super_block *, ext4_group_t, \
- unsigned long, ext4_fsblk_t, \
- const char *, ...)
- __attribute__ ((format (printf, 7, 8)));
+extern __printf(7, 8)
+void __ext4_grp_locked_error(const char *, unsigned int,
+ struct super_block *, ext4_group_t,
+ unsigned long, ext4_fsblk_t,
+ const char *, ...);
#define ext4_grp_locked_error(sb, grp, message...) \
__ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message)
extern void ext4_update_dynamic_rev(struct super_block *sb);
@@ -1904,8 +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,
@@ -1918,8 +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,
@@ -2028,13 +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)
@@ -2067,11 +2142,19 @@ struct ext4_group_info {
* 5 free 8-block regions. */
};
-#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
+#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
+#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1
#define EXT4_MB_GRP_NEED_INIT(grp) \
(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_WAS_TRIMMED(grp) \
+ (test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_SET_TRIMMED(grp) \
+ (set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_CLEAR_TRIMMED(grp) \
+ (clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
+
#define EXT4_MAX_CONTENTION 8
#define EXT4_CONTENTION_THRESHOLD 2
@@ -2123,6 +2206,19 @@ static inline void ext4_mark_super_dirty(struct super_block *sb)
}
/*
+ * Block validity checking
+ */
+#define ext4_check_indirect_blockref(inode, bh) \
+ ext4_check_blockref(__func__, __LINE__, inode, \
+ (__le32 *)(bh)->b_data, \
+ EXT4_ADDR_PER_BLOCK((inode)->i_sb))
+
+#define ext4_ind_check_inode(inode) \
+ ext4_check_blockref(__func__, __LINE__, inode, \
+ EXT4_I(inode)->i_data, \
+ EXT4_NDIR_BLOCKS)
+
+/*
* Inodes and files operations
*/
@@ -2151,6 +2247,8 @@ extern void ext4_exit_system_zone(void);
extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
ext4_fsblk_t start_blk,
unsigned int count);
+extern int ext4_check_blockref(const char *, unsigned int,
+ struct inode *, __le32 *, unsigned int);
/* extents.c */
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
@@ -2197,10 +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
@@ -2230,6 +2337,12 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+#define EXT4_RESIZING 0
+extern int ext4_resize_begin(struct super_block *sb);
+extern void ext4_resize_end(struct super_block *sb);
+
#endif /* __KERNEL__ */
+#include "ext4_extents.h"
+
#endif /* _EXT4_H */
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 095c36f3b612..a52db3a69a30 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -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 */
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index f5240aa15601..aca179017582 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -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);
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index bb85757689b6..5802fa1dab18 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -289,10 +289,10 @@ static inline int ext4_should_order_data(struct inode *inode)
static inline int ext4_should_writeback_data(struct inode *inode)
{
- if (!S_ISREG(inode->i_mode))
- return 0;
if (EXT4_JOURNAL(inode) == NULL)
return 1;
+ if (!S_ISREG(inode->i_mode))
+ return 0;
if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
return 0;
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index f815cc81e7a2..61fa9e1614af 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -42,7 +42,6 @@
#include <asm/uaccess.h>
#include <linux/fiemap.h>
#include "ext4_jbd2.h"
-#include "ext4_extents.h"
#include <trace/events/ext4.h>
@@ -96,13 +95,17 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
* - ENOMEM
* - EIO
*/
-static int ext4_ext_dirty(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path)
+#define ext4_ext_dirty(handle, inode, path) \
+ __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
+static int __ext4_ext_dirty(const char *where, unsigned int line,
+ handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path)
{
int err;
if (path->p_bh) {
/* path points to block */
- err = ext4_handle_dirty_metadata(handle, inode, path->p_bh);
+ err = __ext4_handle_dirty_metadata(where, line, handle,
+ inode, path->p_bh);
} else {
/* path points to leaf/index in inode body */
err = ext4_mark_inode_dirty(handle, inode);
@@ -114,17 +117,9 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t block)
{
- struct ext4_inode_info *ei = EXT4_I(inode);
- ext4_fsblk_t bg_start;
- ext4_fsblk_t last_block;
- ext4_grpblk_t colour;
- ext4_group_t block_group;
- int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));
- int depth;
-
if (path) {
+ int depth = path->p_depth;
struct ext4_extent *ex;
- depth = path->p_depth;
/*
* Try to predict block placement assuming that we are
@@ -161,36 +156,7 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
}
/* OK. use inode's group */
- block_group = ei->i_block_group;
- if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
- /*
- * If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME
- * block groups per flexgroup, reserve the first block
- * group for directories and special files. Regular
- * files will start at the second block group. This
- * tends to speed up directory access and improves
- * fsck times.
- */
- block_group &= ~(flex_size-1);
- if (S_ISREG(inode->i_mode))
- block_group++;
- }
- bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
- last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
-
- /*
- * If we are doing delayed allocation, we don't need take
- * colour into account.
- */
- if (test_opt(inode->i_sb, DELALLOC))
- return bg_start;
-
- if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
- colour = (current->pid % 16) *
- (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
- else
- colour = (current->pid % 16) * ((last_block - bg_start) / 16);
- return bg_start + colour + block;
+ return ext4_inode_to_goal_block(inode);
}
/*
@@ -215,12 +181,10 @@ static inline int ext4_ext_space_block(struct inode *inode, int check)
size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
/ sizeof(struct ext4_extent);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 6)
- size = 6;
+ if (!check && size > 6)
+ size = 6;
#endif
- }
return size;
}
@@ -230,12 +194,10 @@ static inline int ext4_ext_space_block_idx(struct inode *inode, int check)
size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
/ sizeof(struct ext4_extent_idx);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 5)
- size = 5;
+ if (!check && size > 5)
+ size = 5;
#endif
- }
return size;
}
@@ -246,12 +208,10 @@ static inline int ext4_ext_space_root(struct inode *inode, int check)
size = sizeof(EXT4_I(inode)->i_data);
size -= sizeof(struct ext4_extent_header);
size /= sizeof(struct ext4_extent);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 3)
- size = 3;
+ if (!check && size > 3)
+ size = 3;
#endif
- }
return size;
}
@@ -262,12 +222,10 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
size = sizeof(EXT4_I(inode)->i_data);
size -= sizeof(struct ext4_extent_header);
size /= sizeof(struct ext4_extent_idx);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 4)
- size = 4;
+ if (!check && size > 4)
+ size = 4;
#endif
- }
return size;
}
@@ -279,7 +237,7 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
{
struct ext4_inode_info *ei = EXT4_I(inode);
- int idxs, num = 0;
+ int idxs;
idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
/ sizeof(struct ext4_extent_idx));
@@ -294,6 +252,8 @@ int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
*/
if (ei->i_da_metadata_calc_len &&
ei->i_da_metadata_calc_last_lblock+1 == lblock) {
+ int num = 0;
+
if ((ei->i_da_metadata_calc_len % idxs) == 0)
num++;
if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
@@ -356,8 +316,6 @@ static int ext4_valid_extent_entries(struct inode *inode,
struct ext4_extent_header *eh,
int depth)
{
- struct ext4_extent *ext;
- struct ext4_extent_idx *ext_idx;
unsigned short entries;
if (eh->eh_entries == 0)
return 1;
@@ -366,7 +324,7 @@ static int ext4_valid_extent_entries(struct inode *inode,
if (depth == 0) {
/* leaf entries */
- ext = EXT_FIRST_EXTENT(eh);
+ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
while (entries) {
if (!ext4_valid_extent(inode, ext))
return 0;
@@ -374,7 +332,7 @@ static int ext4_valid_extent_entries(struct inode *inode,
entries--;
}
} else {
- ext_idx = EXT_FIRST_INDEX(eh);
+ struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
while (entries) {
if (!ext4_valid_extent_idx(inode, ext_idx))
return 0;
@@ -776,42 +734,44 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
logical, le32_to_cpu(curp->p_idx->ei_block));
return -EIO;
}
- len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx;
+
+ if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries)
+ >= le16_to_cpu(curp->p_hdr->eh_max))) {
+ EXT4_ERROR_INODE(inode,
+ "eh_entries %d >= eh_max %d!",
+ le16_to_cpu(curp->p_hdr->eh_entries),
+ le16_to_cpu(curp->p_hdr->eh_max));
+ return -EIO;
+ }
+
if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
/* insert after */
- if (curp->p_idx != EXT_LAST_INDEX(curp->p_hdr)) {
- len = (len - 1) * sizeof(struct ext4_extent_idx);
- len = len < 0 ? 0 : len;
- ext_debug("insert new index %d after: %llu. "
- "move %d from 0x%p to 0x%p\n",
- logical, ptr, len,
- (curp->p_idx + 1), (curp->p_idx + 2));
- memmove(curp->p_idx + 2, curp->p_idx + 1, len);
- }
+ ext_debug("insert new index %d after: %llu\n", logical, ptr);
ix = curp->p_idx + 1;
} else {
/* insert before */
- len = len * sizeof(struct ext4_extent_idx);
- len = len < 0 ? 0 : len;
- ext_debug("insert new index %d before: %llu. "
- "move %d from 0x%p to 0x%p\n",
- logical, ptr, len,
- curp->p_idx, (curp->p_idx + 1));
- memmove(curp->p_idx + 1, curp->p_idx, len);
+ ext_debug("insert new index %d before: %llu\n", logical, ptr);
ix = curp->p_idx;
}
+ len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1;
+ BUG_ON(len < 0);
+ if (len > 0) {
+ ext_debug("insert new index %d: "
+ "move %d indices from 0x%p to 0x%p\n",
+ logical, len, ix, ix + 1);
+ memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx));
+ }
+
+ if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) {
+ EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!");
+ return -EIO;
+ }
+
ix->ei_block = cpu_to_le32(logical);
ext4_idx_store_pblock(ix, ptr);
le16_add_cpu(&curp->p_hdr->eh_entries, 1);
- if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries)
- > le16_to_cpu(curp->p_hdr->eh_max))) {
- EXT4_ERROR_INODE(inode,
- "logical %d == ei_block %d!",
- logical, le32_to_cpu(curp->p_idx->ei_block));
- return -EIO;
- }
if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) {
EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!");
return -EIO;
@@ -1074,16 +1034,14 @@ cleanup:
*/
static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
unsigned int flags,
- struct ext4_ext_path *path,
struct ext4_extent *newext)
{
- struct ext4_ext_path *curp = path;
struct ext4_extent_header *neh;
struct buffer_head *bh;
ext4_fsblk_t newblock;
int err = 0;
- newblock = ext4_ext_new_meta_block(handle, inode, path,
+ newblock = ext4_ext_new_meta_block(handle, inode, NULL,
newext, &err, flags);
if (newblock == 0)
return err;
@@ -1103,7 +1061,8 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
}
/* move top-level index/leaf into new block */
- memmove(bh->b_data, curp->p_hdr, sizeof(EXT4_I(inode)->i_data));
+ memmove(bh->b_data, EXT4_I(inode)->i_data,
+ sizeof(EXT4_I(inode)->i_data));
/* set size of new block */
neh = ext_block_hdr(bh);
@@ -1121,32 +1080,23 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
if (err)
goto out;
- /* create index in new top-level index: num,max,pointer */
- err = ext4_ext_get_access(handle, inode, curp);
- if (err)
- goto out;
-
- curp->p_hdr->eh_magic = EXT4_EXT_MAGIC;
- curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0));
- curp->p_hdr->eh_entries = cpu_to_le16(1);
- curp->p_idx = EXT_FIRST_INDEX(curp->p_hdr);
-
- if (path[0].p_hdr->eh_depth)
- curp->p_idx->ei_block =
- EXT_FIRST_INDEX(path[0].p_hdr)->ei_block;
- else
- curp->p_idx->ei_block =
- EXT_FIRST_EXTENT(path[0].p_hdr)->ee_block;
- ext4_idx_store_pblock(curp->p_idx, newblock);
-
+ /* Update top-level index: num,max,pointer */
neh = ext_inode_hdr(inode);
+ neh->eh_entries = cpu_to_le16(1);
+ ext4_idx_store_pblock(EXT_FIRST_INDEX(neh), newblock);
+ if (neh->eh_depth == 0) {
+ /* Root extent block becomes index block */
+ neh->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0));
+ EXT_FIRST_INDEX(neh)->ei_block =
+ EXT_FIRST_EXTENT(neh)->ee_block;
+ }
ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n",
le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max),
le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
- neh->eh_depth = cpu_to_le16(path->p_depth + 1);
- err = ext4_ext_dirty(handle, inode, curp);
+ neh->eh_depth = cpu_to_le16(neh->eh_depth + 1);
+ ext4_mark_inode_dirty(handle, inode);
out:
brelse(bh);
@@ -1194,8 +1144,7 @@ repeat:
err = PTR_ERR(path);
} else {
/* tree is full, time to grow in depth */
- err = ext4_ext_grow_indepth(handle, inode, flags,
- path, newext);
+ err = ext4_ext_grow_indepth(handle, inode, flags, newext);
if (err)
goto out;
@@ -1267,9 +1216,9 @@ static int ext4_ext_search_left(struct inode *inode,
if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
EXT4_ERROR_INODE(inode,
"ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!",
- ix != NULL ? ix->ei_block : 0,
+ ix != NULL ? le32_to_cpu(ix->ei_block) : 0,
EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ?
- EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block : 0,
+ le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block) : 0,
depth);
return -EIO;
}
@@ -1292,13 +1241,14 @@ static int ext4_ext_search_left(struct inode *inode,
/*
* search the closest allocated block to the right for *logical
* and returns it at @logical + it's physical address at @phys
- * if *logical is the smallest allocated block, the function
+ * if *logical is the largest allocated block, the function
* returns 0 at @phys
* return value contains 0 (success) or error code
*/
static int ext4_ext_search_right(struct inode *inode,
struct ext4_ext_path *path,
- ext4_lblk_t *logical, ext4_fsblk_t *phys)
+ ext4_lblk_t *logical, ext4_fsblk_t *phys,
+ struct ext4_extent **ret_ex)
{
struct buffer_head *bh = NULL;
struct ext4_extent_header *eh;
@@ -1340,9 +1290,7 @@ static int ext4_ext_search_right(struct inode *inode,
return -EIO;
}
}
- *logical = le32_to_cpu(ex->ee_block);
- *phys = ext4_ext_pblock(ex);
- return 0;
+ goto found_extent;
}
if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
@@ -1355,9 +1303,7 @@ static int ext4_ext_search_right(struct inode *inode,
if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
/* next allocated block in this leaf */
ex++;
- *logical = le32_to_cpu(ex->ee_block);
- *phys = ext4_ext_pblock(ex);
- return 0;
+ goto found_extent;
}
/* go up and search for index to the right */
@@ -1400,9 +1346,12 @@ got_index:
return -EIO;
}
ex = EXT_FIRST_EXTENT(eh);
+found_extent:
*logical = le32_to_cpu(ex->ee_block);
*phys = ext4_ext_pblock(ex);
- put_bh(bh);
+ *ret_ex = ex;
+ if (bh)
+ put_bh(bh);
return 0;
}
@@ -1427,7 +1376,8 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path)
while (depth >= 0) {
if (depth == path->p_depth) {
/* leaf */
- if (path[depth].p_ext !=
+ if (path[depth].p_ext &&
+ path[depth].p_ext !=
EXT_LAST_EXTENT(path[depth].p_hdr))
return le32_to_cpu(path[depth].p_ext[1].ee_block);
} else {
@@ -1446,8 +1396,7 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path)
* ext4_ext_next_leaf_block:
* returns first allocated block from next leaf or EXT_MAX_BLOCKS
*/
-static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode,
- struct ext4_ext_path *path)
+static ext4_lblk_t ext4_ext_next_leaf_block(struct ext4_ext_path *path)
{
int depth;
@@ -1656,7 +1605,8 @@ static int ext4_ext_try_to_merge(struct inode *inode,
* such that there will be no overlap, and then returns 1.
* If there is no overlap found, it returns 0.
*/
-static unsigned int ext4_ext_check_overlap(struct inode *inode,
+static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi,
+ struct inode *inode,
struct ext4_extent *newext,
struct ext4_ext_path *path)
{
@@ -1670,6 +1620,7 @@ static unsigned int ext4_ext_check_overlap(struct inode *inode,
if (!path[depth].p_ext)
goto out;
b2 = le32_to_cpu(path[depth].p_ext->ee_block);
+ b2 &= ~(sbi->s_cluster_ratio - 1);
/*
* get the next allocated block if the extent in the path
@@ -1679,6 +1630,7 @@ static unsigned int ext4_ext_check_overlap(struct inode *inode,
b2 = ext4_ext_next_allocated_block(path);
if (b2 == EXT_MAX_BLOCKS)
goto out;
+ b2 &= ~(sbi->s_cluster_ratio - 1);
}
/* check for wrap through zero on extent logical start block*/
@@ -1730,7 +1682,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
/* try to insert block into found extent and return */
if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)
&& ext4_can_extents_be_merged(inode, ex, newext)) {
- ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n",
+ ext_debug("append [%d]%d block to %u:[%d]%d (from %llu)\n",
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
@@ -1757,7 +1709,6 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
goto merge;
}
-repeat:
depth = ext_depth(inode);
eh = path[depth].p_hdr;
if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max))
@@ -1765,10 +1716,11 @@ repeat:
/* probably next leaf has space for us? */
fex = EXT_LAST_EXTENT(eh);
- next = ext4_ext_next_leaf_block(inode, path);
- if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)
- && next != EXT_MAX_BLOCKS) {
- ext_debug("next leaf block - %d\n", next);
+ next = EXT_MAX_BLOCKS;
+ if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block))
+ next = ext4_ext_next_leaf_block(path);
+ if (next != EXT_MAX_BLOCKS) {
+ ext_debug("next leaf block - %u\n", next);
BUG_ON(npath != NULL);
npath = ext4_ext_find_extent(inode, next, NULL);
if (IS_ERR(npath))
@@ -1779,7 +1731,7 @@ repeat:
ext_debug("next leaf isn't full(%d)\n",
le16_to_cpu(eh->eh_entries));
path = npath;
- goto repeat;
+ goto has_space;
}
ext_debug("next leaf has no free space(%d,%d)\n",
le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
@@ -1806,46 +1758,51 @@ has_space:
if (!nearex) {
/* there is no extent in this leaf, create first one */
- ext_debug("first extent in the leaf: %d:%llu:[%d]%d\n",
+ ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext));
- path[depth].p_ext = EXT_FIRST_EXTENT(eh);
- } else if (le32_to_cpu(newext->ee_block)
+ nearex = EXT_FIRST_EXTENT(eh);
+ } else {
+ if (le32_to_cpu(newext->ee_block)
> le32_to_cpu(nearex->ee_block)) {
-/* BUG_ON(newext->ee_block == nearex->ee_block); */
- if (nearex != EXT_LAST_EXTENT(eh)) {
- len = EXT_MAX_EXTENT(eh) - nearex;
- len = (len - 1) * sizeof(struct ext4_extent);
- len = len < 0 ? 0 : len;
- ext_debug("insert %d:%llu:[%d]%d after: nearest 0x%p, "
- "move %d from 0x%p to 0x%p\n",
+ /* Insert after */
+ ext_debug("insert %u:%llu:[%d]%d before: "
+ "nearest %p\n",
+ le32_to_cpu(newext->ee_block),
+ ext4_ext_pblock(newext),
+ ext4_ext_is_uninitialized(newext),
+ ext4_ext_get_actual_len(newext),
+ nearex);
+ nearex++;
+ } else {
+ /* Insert before */
+ BUG_ON(newext->ee_block == nearex->ee_block);
+ ext_debug("insert %u:%llu:[%d]%d after: "
+ "nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext),
- nearex, len, nearex + 1, nearex + 2);
- memmove(nearex + 2, nearex + 1, len);
+ nearex);
+ }
+ len = EXT_LAST_EXTENT(eh) - nearex + 1;
+ if (len > 0) {
+ ext_debug("insert %u:%llu:[%d]%d: "
+ "move %d extents from 0x%p to 0x%p\n",
+ le32_to_cpu(newext->ee_block),
+ ext4_ext_pblock(newext),
+ ext4_ext_is_uninitialized(newext),
+ ext4_ext_get_actual_len(newext),
+ len, nearex, nearex + 1);
+ memmove(nearex + 1, nearex,
+ len * sizeof(struct ext4_extent));
}
- path[depth].p_ext = nearex + 1;
- } else {
- BUG_ON(newext->ee_block == nearex->ee_block);
- len = (EXT_MAX_EXTENT(eh) - nearex) * sizeof(struct ext4_extent);
- len = len < 0 ? 0 : len;
- ext_debug("insert %d:%llu:[%d]%d before: nearest 0x%p, "
- "move %d from 0x%p to 0x%p\n",
- le32_to_cpu(newext->ee_block),
- ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
- ext4_ext_get_actual_len(newext),
- nearex, len, nearex + 1, nearex + 2);
- memmove(nearex + 1, nearex, len);
- path[depth].p_ext = nearex;
}
le16_add_cpu(&eh->eh_entries, 1);
- nearex = path[depth].p_ext;
+ path[depth].p_ext = nearex;
nearex->ee_block = newext->ee_block;
ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext));
nearex->ee_len = newext->ee_len;
@@ -1995,6 +1952,7 @@ ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
struct ext4_ext_cache *cex;
BUG_ON(len == 0);
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+ trace_ext4_ext_put_in_cache(inode, block, len, start);
cex = &EXT4_I(inode)->i_cached_extent;
cex->ec_block = block;
cex->ec_len = len;
@@ -2052,7 +2010,7 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
}
/*
- * ext4_ext_in_cache()
+ * ext4_ext_check_cache()
* Checks to see if the given block is in the cache.
* If it is, the cached extent is stored in the given
* cache extent pointer. If the cached extent is a hole,
@@ -2096,6 +2054,7 @@ errout:
sbi->extent_cache_misses++;
else
sbi->extent_cache_hits++;
+ trace_ext4_ext_in_cache(inode, block, ret);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
return ret;
}
@@ -2134,8 +2093,6 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
/*
* ext4_ext_rm_idx:
* removes index from the index block.
- * It's used in truncate case only, thus all requests are for
- * last index in the block only.
*/
static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
@@ -2153,11 +2110,20 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
err = ext4_ext_get_access(handle, inode, path);
if (err)
return err;
+
+ if (path->p_idx != EXT_LAST_INDEX(path->p_hdr)) {
+ int len = EXT_LAST_INDEX(path->p_hdr) - path->p_idx;
+ len *= sizeof(struct ext4_extent_idx);
+ memmove(path->p_idx, path->p_idx + 1, len);
+ }
+
le16_add_cpu(&path->p_hdr->eh_entries, -1);
err = ext4_ext_dirty(handle, inode, path);
if (err)
return err;
ext_debug("index is empty, remove it, free block %llu\n", leaf);
+ trace_ext4_ext_rm_idx(inode, leaf);
+
ext4_free_blocks(handle, inode, NULL, leaf, 1,
EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
return err;
@@ -2186,7 +2152,7 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks,
* need to account for leaf block credit
*
* bitmaps and block group descriptor blocks
- * and other metadat blocks still need to be
+ * and other metadata blocks still need to be
* accounted.
*/
/* 1 bitmap, 1 block group descriptor */
@@ -2223,14 +2189,40 @@ int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
}
static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
- struct ext4_extent *ex,
- ext4_lblk_t from, ext4_lblk_t to)
+ struct ext4_extent *ex,
+ ext4_fsblk_t *partial_cluster,
+ ext4_lblk_t from, ext4_lblk_t to)
{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned short ee_len = ext4_ext_get_actual_len(ex);
+ ext4_fsblk_t pblk;
int flags = EXT4_FREE_BLOCKS_FORGET;
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
flags |= EXT4_FREE_BLOCKS_METADATA;
+ /*
+ * For bigalloc file systems, we never free a partial cluster
+ * at the beginning of the extent. Instead, we make a note
+ * that we tried freeing the cluster, and check to see if we
+ * need to free it on a subsequent call to ext4_remove_blocks,
+ * or at the end of the ext4_truncate() operation.
+ */
+ flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER;
+
+ trace_ext4_remove_blocks(inode, ex, from, to, *partial_cluster);
+ /*
+ * If we have a partial cluster, and it's different from the
+ * cluster of the last block, we need to explicitly free the
+ * partial cluster here.
+ */
+ pblk = ext4_ext_pblock(ex) + ee_len - 1;
+ if (*partial_cluster && (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
+ ext4_free_blocks(handle, inode, NULL,
+ EXT4_C2B(sbi, *partial_cluster),
+ sbi->s_cluster_ratio, flags);
+ *partial_cluster = 0;
+ }
+
#ifdef EXTENTS_STATS
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -2250,12 +2242,24 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
&& to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
/* tail removal */
ext4_lblk_t num;
- ext4_fsblk_t start;
num = le32_to_cpu(ex->ee_block) + ee_len - from;
- start = ext4_ext_pblock(ex) + ee_len - num;
- ext_debug("free last %u blocks starting %llu\n", num, start);
- ext4_free_blocks(handle, inode, NULL, start, num, flags);
+ pblk = ext4_ext_pblock(ex) + ee_len - num;
+ ext_debug("free last %u blocks starting %llu\n", num, pblk);
+ ext4_free_blocks(handle, inode, NULL, pblk, num, flags);
+ /*
+ * If the block range to be freed didn't start at the
+ * beginning of a cluster, and we removed the entire
+ * extent, save the partial cluster here, since we
+ * might need to delete if we determine that the
+ * truncate operation has removed all of the blocks in
+ * the cluster.
+ */
+ if (pblk & (sbi->s_cluster_ratio - 1) &&
+ (ee_len == num))
+ *partial_cluster = EXT4_B2C(sbi, pblk);
+ else
+ *partial_cluster = 0;
} else if (from == le32_to_cpu(ex->ee_block)
&& to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
/* head removal */
@@ -2266,7 +2270,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
start = ext4_ext_pblock(ex);
ext_debug("free first %u blocks starting %llu\n", num, start);
- ext4_free_blocks(handle, inode, 0, start, num, flags);
+ ext4_free_blocks(handle, inode, NULL, start, num, flags);
} else {
printk(KERN_INFO "strange request: removal(2) "
@@ -2290,19 +2294,19 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
*/
static int
ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path, ext4_lblk_t start,
- ext4_lblk_t end)
+ struct ext4_ext_path *path, ext4_fsblk_t *partial_cluster,
+ ext4_lblk_t start, ext4_lblk_t end)
{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int err = 0, correct_index = 0;
int depth = ext_depth(inode), credits;
struct ext4_extent_header *eh;
- ext4_lblk_t a, b, block;
+ ext4_lblk_t a, b;
unsigned num;
ext4_lblk_t ex_ee_block;
unsigned short ex_ee_len;
unsigned uninitialized = 0;
struct ext4_extent *ex;
- struct ext4_map_blocks map;
/* the header must be checked already in ext4_ext_remove_space() */
ext_debug("truncate since %u in leaf\n", start);
@@ -2319,6 +2323,8 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
+ trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
+
while (ex >= EXT_FIRST_EXTENT(eh) &&
ex_ee_block + ex_ee_len > start) {
@@ -2343,86 +2349,18 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
continue;
- } else if (a != ex_ee_block &&
- b != ex_ee_block + ex_ee_len - 1) {
- /*
- * If this is a truncate, then this condition should
- * never happen because at least one of the end points
- * needs to be on the edge of the extent.
- */
- if (end == EXT_MAX_BLOCKS - 1) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- block = 0;
- num = 0;
- err = -EIO;
- goto out;
- }
- /*
- * else this is a hole punch, so the extent needs to
- * be split since neither edge of the hole is on the
- * extent edge
- */
- else{
- map.m_pblk = ext4_ext_pblock(ex);
- map.m_lblk = ex_ee_block;
- map.m_len = b - ex_ee_block;
-
- err = ext4_split_extent(handle,
- inode, path, &map, 0,
- EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
- EXT4_GET_BLOCKS_PRE_IO);
-
- if (err < 0)
- goto out;
-
- ex_ee_len = ext4_ext_get_actual_len(ex);
-
- b = ex_ee_block+ex_ee_len - 1 < end ?
- ex_ee_block+ex_ee_len - 1 : end;
-
- /* Then remove tail of this extent */
- block = ex_ee_block;
- num = a - block;
- }
+ } else if (b != ex_ee_block + ex_ee_len - 1) {
+ EXT4_ERROR_INODE(inode," bad truncate %u:%u\n",
+ start, end);
+ err = -EIO;
+ goto out;
} else if (a != ex_ee_block) {
/* remove tail of the extent */
- block = ex_ee_block;
- num = a - block;
- } else if (b != ex_ee_block + ex_ee_len - 1) {
- /* remove head of the extent */
- block = b;
- num = ex_ee_block + ex_ee_len - b;
-
- /*
- * If this is a truncate, this condition
- * should never happen
- */
- if (end == EXT_MAX_BLOCKS - 1) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- err = -EIO;
- goto out;
- }
+ num = a - ex_ee_block;
} else {
/* remove whole extent: excellent! */
- block = ex_ee_block;
num = 0;
- if (a != ex_ee_block) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- err = -EIO;
- goto out;
- }
-
- if (b != ex_ee_block + ex_ee_len - 1) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- err = -EIO;
- goto out;
- }
}
-
/*
* 3 for leaf, sb, and inode plus 2 (bmap and group
* descriptor) for each block group; assume two block
@@ -2444,23 +2382,15 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
if (err)
goto out;
- err = ext4_remove_blocks(handle, inode, ex, a, b);
+ err = ext4_remove_blocks(handle, inode, ex, partial_cluster,
+ a, b);
if (err)
goto out;
- if (num == 0) {
+ if (num == 0)
/* this extent is removed; mark slot entirely unused */
ext4_ext_store_pblock(ex, 0);
- } else if (block != ex_ee_block) {
- /*
- * If this was a head removal, then we need to update
- * the physical block since it is now at a different
- * location
- */
- ext4_ext_store_pblock(ex, ext4_ext_pblock(ex) + (b-a));
- }
- ex->ee_block = cpu_to_le32(block);
ex->ee_len = cpu_to_le16(num);
/*
* Do not mark uninitialized if all the blocks in the
@@ -2468,11 +2398,6 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
*/
if (uninitialized && num)
ext4_ext_mark_uninitialized(ex);
-
- err = ext4_ext_dirty(handle, inode, path + depth);
- if (err)
- goto out;
-
/*
* If the extent was completely released,
* we need to remove it from the leaf
@@ -2492,9 +2417,14 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
sizeof(struct ext4_extent));
}
le16_add_cpu(&eh->eh_entries, -1);
- }
+ } else
+ *partial_cluster = 0;
- ext_debug("new extent: %u:%u:%llu\n", block, num,
+ err = ext4_ext_dirty(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ ext_debug("new extent: %u:%u:%llu\n", ex_ee_block, num,
ext4_ext_pblock(ex));
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
@@ -2504,6 +2434,25 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
if (correct_index && eh->eh_entries)
err = ext4_ext_correct_indexes(handle, inode, path);
+ /*
+ * If there is still a entry in the leaf node, check to see if
+ * it references the partial cluster. This is the only place
+ * where it could; if it doesn't, we can free the cluster.
+ */
+ if (*partial_cluster && ex >= EXT_FIRST_EXTENT(eh) &&
+ (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
+ *partial_cluster)) {
+ int flags = EXT4_FREE_BLOCKS_FORGET;
+
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ flags |= EXT4_FREE_BLOCKS_METADATA;
+
+ ext4_free_blocks(handle, inode, NULL,
+ EXT4_C2B(sbi, *partial_cluster),
+ sbi->s_cluster_ratio, flags);
+ *partial_cluster = 0;
+ }
+
/* if this leaf is free, then we should
* remove it from index block above */
if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL)
@@ -2534,12 +2483,12 @@ ext4_ext_more_to_rm(struct ext4_ext_path *path)
return 1;
}
-static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
- ext4_lblk_t end)
+static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
{
struct super_block *sb = inode->i_sb;
int depth = ext_depth(inode);
struct ext4_ext_path *path;
+ ext4_fsblk_t partial_cluster = 0;
handle_t *handle;
int i, err;
@@ -2553,6 +2502,8 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
again:
ext4_ext_invalidate_cache(inode);
+ trace_ext4_ext_remove_space(inode, start, depth);
+
/*
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
@@ -2575,7 +2526,8 @@ again:
if (i == depth) {
/* this is leaf block */
err = ext4_ext_rm_leaf(handle, inode, path,
- start, end);
+ &partial_cluster, start,
+ EXT_MAX_BLOCKS - 1);
/* root level has p_bh == NULL, brelse() eats this */
brelse(path[i].p_bh);
path[i].p_bh = NULL;
@@ -2647,6 +2599,24 @@ again:
}
}
+ trace_ext4_ext_remove_space_done(inode, start, depth, partial_cluster,
+ path->p_hdr->eh_entries);
+
+ /* If we still have something in the partial cluster and we have removed
+ * even the first extent, then we should free the blocks in the partial
+ * cluster as well. */
+ if (partial_cluster && path->p_hdr->eh_entries == 0) {
+ int flags = EXT4_FREE_BLOCKS_FORGET;
+
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ flags |= EXT4_FREE_BLOCKS_METADATA;
+
+ ext4_free_blocks(handle, inode, NULL,
+ EXT4_C2B(EXT4_SB(sb), partial_cluster),
+ EXT4_SB(sb)->s_cluster_ratio, flags);
+ partial_cluster = 0;
+ }
+
/* TODO: flexible tree reduction should be here */
if (path->p_hdr->eh_entries == 0) {
/*
@@ -2938,17 +2908,29 @@ out:
* a> There is no split required: Entire extent should be initialized
* b> Splits in two extents: Write is happening at either end of the extent
* c> Splits in three extents: Somone is writing in middle of the extent
+ *
+ * Pre-conditions:
+ * - The extent pointed to by 'path' is uninitialized.
+ * - The extent pointed to by 'path' contains a superset
+ * of the logical span [map->m_lblk, map->m_lblk + map->m_len).
+ *
+ * Post-conditions on success:
+ * - the returned value is the number of blocks beyond map->l_lblk
+ * that are allocated and initialized.
+ * It is guaranteed to be >= map->m_len.
*/
static int ext4_ext_convert_to_initialized(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path *path)
{
+ struct ext4_extent_header *eh;
struct ext4_map_blocks split_map;
struct ext4_extent zero_ex;
struct ext4_extent *ex;
ext4_lblk_t ee_block, eof_block;
- unsigned int allocated, ee_len, depth;
+ unsigned int ee_len, depth;
+ int allocated;
int err = 0;
int split_flag = 0;
@@ -2962,11 +2944,93 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
eof_block = map->m_lblk + map->m_len;
depth = ext_depth(inode);
+ eh = path[depth].p_hdr;
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (map->m_lblk - ee_block);
+ trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
+
+ /* Pre-conditions */
+ BUG_ON(!ext4_ext_is_uninitialized(ex));
+ BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
+ BUG_ON(map->m_lblk + map->m_len > ee_block + ee_len);
+
+ /*
+ * Attempt to transfer newly initialized blocks from the currently
+ * uninitialized extent to its left neighbor. This is much cheaper
+ * than an insertion followed by a merge as those involve costly
+ * memmove() calls. This is the common case in steady state for
+ * workloads doing fallocate(FALLOC_FL_KEEP_SIZE) followed by append
+ * writes.
+ *
+ * Limitations of the current logic:
+ * - L1: we only deal with writes at the start of the extent.
+ * The approach could be extended to writes at the end
+ * of the extent but this scenario was deemed less common.
+ * - L2: we do not deal with writes covering the whole extent.
+ * This would require removing the extent if the transfer
+ * is possible.
+ * - L3: we only attempt to merge with an extent stored in the
+ * same extent tree node.
+ */
+ if ((map->m_lblk == ee_block) && /*L1*/
+ (map->m_len < ee_len) && /*L2*/
+ (ex > EXT_FIRST_EXTENT(eh))) { /*L3*/
+ struct ext4_extent *prev_ex;
+ ext4_lblk_t prev_lblk;
+ ext4_fsblk_t prev_pblk, ee_pblk;
+ unsigned int prev_len, write_len;
+
+ prev_ex = ex - 1;
+ prev_lblk = le32_to_cpu(prev_ex->ee_block);
+ prev_len = ext4_ext_get_actual_len(prev_ex);
+ prev_pblk = ext4_ext_pblock(prev_ex);
+ ee_pblk = ext4_ext_pblock(ex);
+ write_len = map->m_len;
+
+ /*
+ * A transfer of blocks from 'ex' to 'prev_ex' is allowed
+ * upon those conditions:
+ * - C1: prev_ex is initialized,
+ * - C2: prev_ex is logically abutting ex,
+ * - C3: prev_ex is physically abutting ex,
+ * - C4: prev_ex can receive the additional blocks without
+ * overflowing the (initialized) length limit.
+ */
+ if ((!ext4_ext_is_uninitialized(prev_ex)) && /*C1*/
+ ((prev_lblk + prev_len) == ee_block) && /*C2*/
+ ((prev_pblk + prev_len) == ee_pblk) && /*C3*/
+ (prev_len < (EXT_INIT_MAX_LEN - write_len))) { /*C4*/
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ trace_ext4_ext_convert_to_initialized_fastpath(inode,
+ map, ex, prev_ex);
+
+ /* Shift the start of ex by 'write_len' blocks */
+ ex->ee_block = cpu_to_le32(ee_block + write_len);
+ ext4_ext_store_pblock(ex, ee_pblk + write_len);
+ ex->ee_len = cpu_to_le16(ee_len - write_len);
+ ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+
+ /* Extend prev_ex by 'write_len' blocks */
+ prev_ex->ee_len = cpu_to_le16(prev_len + write_len);
+
+ /* Mark the block containing both extents as dirty */
+ ext4_ext_dirty(handle, inode, path + depth);
+
+ /* Update path to point to the right extent */
+ path[depth].p_ext = prev_ex;
+
+ /* Result: number of initialized blocks past m_lblk */
+ allocated = write_len;
+ goto out;
+ }
+ }
+
WARN_ON(map->m_lblk < ee_block);
/*
* It is safe to convert extent to initialized via explicit
@@ -3107,12 +3171,10 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
struct ext4_ext_path *path)
{
struct ext4_extent *ex;
- struct ext4_extent_header *eh;
int depth;
int err = 0;
depth = ext_depth(inode);
- eh = path[depth].p_hdr;
ex = path[depth].p_ext;
ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical"
@@ -3196,6 +3258,192 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
return ext4_mark_inode_dirty(handle, inode);
}
+/**
+ * ext4_find_delalloc_range: find delayed allocated block in the given range.
+ *
+ * Goes through the buffer heads in the range [lblk_start, lblk_end] and returns
+ * whether there are any buffers marked for delayed allocation. It returns '1'
+ * on the first delalloc'ed buffer head found. If no buffer head in the given
+ * range is marked for delalloc, it returns 0.
+ * lblk_start should always be <= lblk_end.
+ * search_hint_reverse is to indicate that searching in reverse from lblk_end to
+ * lblk_start might be more efficient (i.e., we will likely hit the delalloc'ed
+ * block sooner). This is useful when blocks are truncated sequentially from
+ * lblk_start towards lblk_end.
+ */
+static int ext4_find_delalloc_range(struct inode *inode,
+ ext4_lblk_t lblk_start,
+ ext4_lblk_t lblk_end,
+ int search_hint_reverse)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct buffer_head *head, *bh = NULL;
+ struct page *page;
+ ext4_lblk_t i, pg_lblk;
+ pgoff_t index;
+
+ /* reverse search wont work if fs block size is less than page size */
+ if (inode->i_blkbits < PAGE_CACHE_SHIFT)
+ search_hint_reverse = 0;
+
+ if (search_hint_reverse)
+ i = lblk_end;
+ else
+ i = lblk_start;
+
+ index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ while ((i >= lblk_start) && (i <= lblk_end)) {
+ page = find_get_page(mapping, index);
+ if (!page)
+ goto nextpage;
+
+ if (!page_has_buffers(page))
+ goto nextpage;
+
+ head = page_buffers(page);
+ if (!head)
+ goto nextpage;
+
+ bh = head;
+ pg_lblk = index << (PAGE_CACHE_SHIFT -
+ inode->i_blkbits);
+ do {
+ if (unlikely(pg_lblk < lblk_start)) {
+ /*
+ * This is possible when fs block size is less
+ * than page size and our cluster starts/ends in
+ * middle of the page. So we need to skip the
+ * initial few blocks till we reach the 'lblk'
+ */
+ pg_lblk++;
+ continue;
+ }
+
+ /* Check if the buffer is delayed allocated and that it
+ * is not yet mapped. (when da-buffers are mapped during
+ * their writeout, their da_mapped bit is set.)
+ */
+ if (buffer_delay(bh) && !buffer_da_mapped(bh)) {
+ page_cache_release(page);
+ trace_ext4_find_delalloc_range(inode,
+ lblk_start, lblk_end,
+ search_hint_reverse,
+ 1, i);
+ return 1;
+ }
+ if (search_hint_reverse)
+ i--;
+ else
+ i++;
+ } while ((i >= lblk_start) && (i <= lblk_end) &&
+ ((bh = bh->b_this_page) != head));
+nextpage:
+ if (page)
+ page_cache_release(page);
+ /*
+ * Move to next page. 'i' will be the first lblk in the next
+ * page.
+ */
+ if (search_hint_reverse)
+ index--;
+ else
+ index++;
+ i = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ }
+
+ trace_ext4_find_delalloc_range(inode, lblk_start, lblk_end,
+ search_hint_reverse, 0, 0);
+ return 0;
+}
+
+int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
+ int search_hint_reverse)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ ext4_lblk_t lblk_start, lblk_end;
+ lblk_start = lblk & (~(sbi->s_cluster_ratio - 1));
+ lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
+
+ return ext4_find_delalloc_range(inode, lblk_start, lblk_end,
+ search_hint_reverse);
+}
+
+/**
+ * Determines how many complete clusters (out of those specified by the 'map')
+ * are under delalloc and were reserved quota for.
+ * This function is called when we are writing out the blocks that were
+ * originally written with their allocation delayed, but then the space was
+ * allocated using fallocate() before the delayed allocation could be resolved.
+ * The cases to look for are:
+ * ('=' indicated delayed allocated blocks
+ * '-' indicates non-delayed allocated blocks)
+ * (a) partial clusters towards beginning and/or end outside of allocated range
+ * are not delalloc'ed.
+ * Ex:
+ * |----c---=|====c====|====c====|===-c----|
+ * |++++++ allocated ++++++|
+ * ==> 4 complete clusters in above example
+ *
+ * (b) partial cluster (outside of allocated range) towards either end is
+ * marked for delayed allocation. In this case, we will exclude that
+ * cluster.
+ * Ex:
+ * |----====c========|========c========|
+ * |++++++ allocated ++++++|
+ * ==> 1 complete clusters in above example
+ *
+ * Ex:
+ * |================c================|
+ * |++++++ allocated ++++++|
+ * ==> 0 complete clusters in above example
+ *
+ * The ext4_da_update_reserve_space will be called only if we
+ * determine here that there were some "entire" clusters that span
+ * this 'allocated' range.
+ * In the non-bigalloc case, this function will just end up returning num_blks
+ * without ever calling ext4_find_delalloc_range.
+ */
+static unsigned int
+get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
+ unsigned int num_blks)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ ext4_lblk_t alloc_cluster_start, alloc_cluster_end;
+ ext4_lblk_t lblk_from, lblk_to, c_offset;
+ unsigned int allocated_clusters = 0;
+
+ alloc_cluster_start = EXT4_B2C(sbi, lblk_start);
+ alloc_cluster_end = EXT4_B2C(sbi, lblk_start + num_blks - 1);
+
+ /* max possible clusters for this allocation */
+ allocated_clusters = alloc_cluster_end - alloc_cluster_start + 1;
+
+ trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks);
+
+ /* Check towards left side */
+ c_offset = lblk_start & (sbi->s_cluster_ratio - 1);
+ if (c_offset) {
+ lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1));
+ lblk_to = lblk_from + c_offset - 1;
+
+ if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+ allocated_clusters--;
+ }
+
+ /* Now check towards right. */
+ c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1);
+ if (allocated_clusters && c_offset) {
+ lblk_from = lblk_start + num_blks;
+ lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
+
+ if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+ allocated_clusters--;
+ }
+
+ return allocated_clusters;
+}
+
static int
ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
@@ -3212,6 +3460,9 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
flags, allocated);
ext4_ext_show_leaf(inode, path);
+ trace_ext4_ext_handle_uninitialized_extents(inode, map, allocated,
+ newblock);
+
/* get_block() before submit the IO, split the extent */
if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
ret = ext4_split_unwritten_extents(handle, inode, map,
@@ -3221,10 +3472,9 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
* that this IO needs to conversion to written when IO is
* completed
*/
- if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
- io->flag = EXT4_IO_END_UNWRITTEN;
- atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
- } else
+ if (io)
+ ext4_set_io_unwritten_flag(inode, io);
+ else
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
if (ext4_should_dioread_nolock(inode))
map->m_flags |= EXT4_MAP_UNINIT;
@@ -3265,14 +3515,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
/* buffered write, writepage time, convert*/
ret = ext4_ext_convert_to_initialized(handle, inode, map, path);
- if (ret >= 0) {
+ if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
- err = check_eofblocks_fl(handle, inode, map->m_lblk, path,
- map->m_len);
- if (err < 0)
- goto out2;
- }
-
out:
if (ret <= 0) {
err = ret;
@@ -3301,11 +3545,24 @@ out:
* But fallocate would have already updated quota and block
* count for this offset. So cancel these reservation
*/
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
- ext4_da_update_reserve_space(inode, allocated, 0);
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+ unsigned int reserved_clusters;
+ reserved_clusters = get_reserved_cluster_alloc(inode,
+ map->m_lblk, map->m_len);
+ if (reserved_clusters)
+ ext4_da_update_reserve_space(inode,
+ reserved_clusters,
+ 0);
+ }
map_out:
map->m_flags |= EXT4_MAP_MAPPED;
+ if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) {
+ err = check_eofblocks_fl(handle, inode, map->m_lblk, path,
+ map->m_len);
+ if (err < 0)
+ goto out2;
+ }
out1:
if (allocated > map->m_len)
allocated = map->m_len;
@@ -3321,6 +3578,111 @@ out2:
}
/*
+ * get_implied_cluster_alloc - check to see if the requested
+ * allocation (in the map structure) overlaps with a cluster already
+ * allocated in an extent.
+ * @sb The filesystem superblock structure
+ * @map The requested lblk->pblk mapping
+ * @ex The extent structure which might contain an implied
+ * cluster allocation
+ *
+ * This function is called by ext4_ext_map_blocks() after we failed to
+ * find blocks that were already in the inode's extent tree. Hence,
+ * we know that the beginning of the requested region cannot overlap
+ * the extent from the inode's extent tree. There are three cases we
+ * want to catch. The first is this case:
+ *
+ * |--- cluster # N--|
+ * |--- extent ---| |---- requested region ---|
+ * |==========|
+ *
+ * The second case that we need to test for is this one:
+ *
+ * |--------- cluster # N ----------------|
+ * |--- requested region --| |------- extent ----|
+ * |=======================|
+ *
+ * The third case is when the requested region lies between two extents
+ * within the same cluster:
+ * |------------- cluster # N-------------|
+ * |----- ex -----| |---- ex_right ----|
+ * |------ requested region ------|
+ * |================|
+ *
+ * In each of the above cases, we need to set the map->m_pblk and
+ * map->m_len so it corresponds to the return the extent labelled as
+ * "|====|" from cluster #N, since it is already in use for data in
+ * cluster EXT4_B2C(sbi, map->m_lblk). We will then return 1 to
+ * signal to ext4_ext_map_blocks() that map->m_pblk should be treated
+ * as a new "allocated" block region. Otherwise, we will return 0 and
+ * ext4_ext_map_blocks() will then allocate one or more new clusters
+ * by calling ext4_mb_new_blocks().
+ */
+static int get_implied_cluster_alloc(struct super_block *sb,
+ struct ext4_map_blocks *map,
+ struct ext4_extent *ex,
+ struct ext4_ext_path *path)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+ ext4_lblk_t ex_cluster_start, ex_cluster_end;
+ ext4_lblk_t rr_cluster_start, rr_cluster_end;
+ ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
+ ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
+ unsigned short ee_len = ext4_ext_get_actual_len(ex);
+
+ /* The extent passed in that we are trying to match */
+ ex_cluster_start = EXT4_B2C(sbi, ee_block);
+ ex_cluster_end = EXT4_B2C(sbi, ee_block + ee_len - 1);
+
+ /* The requested region passed into ext4_map_blocks() */
+ rr_cluster_start = EXT4_B2C(sbi, map->m_lblk);
+ rr_cluster_end = EXT4_B2C(sbi, map->m_lblk + map->m_len - 1);
+
+ if ((rr_cluster_start == ex_cluster_end) ||
+ (rr_cluster_start == ex_cluster_start)) {
+ if (rr_cluster_start == ex_cluster_end)
+ ee_start += ee_len - 1;
+ map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) +
+ c_offset;
+ map->m_len = min(map->m_len,
+ (unsigned) sbi->s_cluster_ratio - c_offset);
+ /*
+ * Check for and handle this case:
+ *
+ * |--------- cluster # N-------------|
+ * |------- extent ----|
+ * |--- requested region ---|
+ * |===========|
+ */
+
+ if (map->m_lblk < ee_block)
+ map->m_len = min(map->m_len, ee_block - map->m_lblk);
+
+ /*
+ * Check for the case where there is already another allocated
+ * block to the right of 'ex' but before the end of the cluster.
+ *
+ * |------------- cluster # N-------------|
+ * |----- ex -----| |---- ex_right ----|
+ * |------ requested region ------|
+ * |================|
+ */
+ if (map->m_lblk > ee_block) {
+ ext4_lblk_t next = ext4_ext_next_allocated_block(path);
+ map->m_len = min(map->m_len, next - map->m_lblk);
+ }
+
+ trace_ext4_get_implied_cluster_alloc_exit(sb, map, 1);
+ return 1;
+ }
+
+ trace_ext4_get_implied_cluster_alloc_exit(sb, map, 0);
+ return 0;
+}
+
+
+/*
* Block allocation/map/preallocation routine for extents based files
*
*
@@ -3342,24 +3704,30 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags)
{
struct ext4_ext_path *path = NULL;
- struct ext4_extent newex, *ex;
+ struct ext4_extent newex, *ex, *ex2;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_fsblk_t newblock = 0;
- int err = 0, depth, ret;
- unsigned int allocated = 0;
+ int free_on_err = 0, err = 0, depth, ret;
+ unsigned int allocated = 0, offset = 0;
+ unsigned int allocated_clusters = 0;
unsigned int punched_out = 0;
unsigned int result = 0;
struct ext4_allocation_request ar;
ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
- struct ext4_map_blocks punch_map;
+ ext4_lblk_t cluster_offset;
ext_debug("blocks %u/%u requested for inode %lu\n",
map->m_lblk, map->m_len, inode->i_ino);
trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
/* check in cache */
- if (ext4_ext_in_cache(inode, map->m_lblk, &newex) &&
- ((flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) == 0)) {
+ if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) &&
+ ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
if (!newex.ee_start_lo && !newex.ee_start_hi) {
+ if ((sbi->s_cluster_ratio > 1) &&
+ ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
/*
* block isn't allocated yet and
@@ -3370,6 +3738,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/* we should allocate requested block */
} else {
/* block is already allocated */
+ if (sbi->s_cluster_ratio > 1)
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
newblock = map->m_lblk
- le32_to_cpu(newex.ee_block)
+ ext4_ext_pblock(&newex);
@@ -3415,8 +3785,14 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* we split out initialized portions during a write.
*/
ee_len = ext4_ext_get_actual_len(ex);
+
+ trace_ext4_ext_show_extent(inode, ee_block, ee_start, ee_len);
+
/* if found extent covers block, simply return it */
if (in_range(map->m_lblk, ee_block, ee_len)) {
+ struct ext4_map_blocks punch_map;
+ ext4_fsblk_t partial_cluster = 0;
+
newblock = map->m_lblk - ee_block + ee_start;
/* number of remaining blocks in the extent */
allocated = ee_len - (map->m_lblk - ee_block);
@@ -3497,13 +3873,37 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ext4_ext_mark_uninitialized(ex);
- err = ext4_ext_remove_space(inode, map->m_lblk,
- map->m_lblk + punched_out);
+ ext4_ext_invalidate_cache(inode);
+
+ err = ext4_ext_rm_leaf(handle, inode, path,
+ &partial_cluster, map->m_lblk,
+ map->m_lblk + punched_out);
+
+ if (!err && path->p_hdr->eh_entries == 0) {
+ /*
+ * Punch hole freed all of this sub tree,
+ * so we need to correct eh_depth
+ */
+ err = ext4_ext_get_access(handle, inode, path);
+ if (err == 0) {
+ ext_inode_hdr(inode)->eh_depth = 0;
+ ext_inode_hdr(inode)->eh_max =
+ cpu_to_le16(ext4_ext_space_root(
+ inode, 0));
+
+ err = ext4_ext_dirty(
+ handle, inode, path);
+ }
+ }
goto out2;
}
}
+ if ((sbi->s_cluster_ratio > 1) &&
+ ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+
/*
* requested block isn't allocated yet;
* we couldn't try to create block if create flag is zero
@@ -3516,9 +3916,25 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
goto out2;
}
+
/*
* Okay, we need to do block allocation.
*/
+ map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
+ newex.ee_block = cpu_to_le32(map->m_lblk);
+ cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+
+ /*
+ * If we are doing bigalloc, check to see if the extent returned
+ * by ext4_ext_find_extent() implies a cluster we can use.
+ */
+ if (cluster_offset && ex &&
+ get_implied_cluster_alloc(inode->i_sb, map, ex, path)) {
+ ar.len = allocated = map->m_len;
+ newblock = map->m_pblk;
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+ goto got_allocated_blocks;
+ }
/* find neighbour allocated blocks */
ar.lleft = map->m_lblk;
@@ -3526,10 +3942,21 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
if (err)
goto out2;
ar.lright = map->m_lblk;
- err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright);
+ ex2 = NULL;
+ err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2);
if (err)
goto out2;
+ /* Check if the extent after searching to the right implies a
+ * cluster we can use. */
+ if ((sbi->s_cluster_ratio > 1) && ex2 &&
+ get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) {
+ ar.len = allocated = map->m_len;
+ newblock = map->m_pblk;
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+ goto got_allocated_blocks;
+ }
+
/*
* See if request is beyond maximum number of blocks we can have in
* a single extent. For an initialized extent this limit is
@@ -3544,9 +3971,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
map->m_len = EXT_UNINIT_MAX_LEN;
/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
- newex.ee_block = cpu_to_le32(map->m_lblk);
newex.ee_len = cpu_to_le16(map->m_len);
- err = ext4_ext_check_overlap(inode, &newex, path);
+ err = ext4_ext_check_overlap(sbi, inode, &newex, path);
if (err)
allocated = ext4_ext_get_actual_len(&newex);
else
@@ -3556,7 +3982,18 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ar.inode = inode;
ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk);
ar.logical = map->m_lblk;
- ar.len = allocated;
+ /*
+ * We calculate the offset from the beginning of the cluster
+ * for the logical block number, since when we allocate a
+ * physical cluster, the physical block should start at the
+ * same offset from the beginning of the cluster. This is
+ * needed so that future calls to get_implied_cluster_alloc()
+ * work correctly.
+ */
+ offset = map->m_lblk & (sbi->s_cluster_ratio - 1);
+ ar.len = EXT4_NUM_B2C(sbi, offset+allocated);
+ ar.goal -= offset;
+ ar.logical -= offset;
if (S_ISREG(inode->i_mode))
ar.flags = EXT4_MB_HINT_DATA;
else
@@ -3569,9 +4006,15 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
goto out2;
ext_debug("allocate new block: goal %llu, found %llu/%u\n",
ar.goal, newblock, allocated);
+ free_on_err = 1;
+ allocated_clusters = ar.len;
+ ar.len = EXT4_C2B(sbi, ar.len) - offset;
+ if (ar.len > allocated)
+ ar.len = allocated;
+got_allocated_blocks:
/* try to insert new extent into found leaf and return */
- ext4_ext_store_pblock(&newex, newblock);
+ ext4_ext_store_pblock(&newex, newblock + offset);
newex.ee_len = cpu_to_le16(ar.len);
/* Mark uninitialized */
if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
@@ -3584,10 +4027,9 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* that we need to perform conversion when IO is done.
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
- if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
- io->flag = EXT4_IO_END_UNWRITTEN;
- atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
- } else
+ if (io)
+ ext4_set_io_unwritten_flag(inode, io);
+ else
ext4_set_inode_state(inode,
EXT4_STATE_DIO_UNWRITTEN);
}
@@ -3595,18 +4037,22 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
map->m_flags |= EXT4_MAP_UNINIT;
}
- err = check_eofblocks_fl(handle, inode, map->m_lblk, path, ar.len);
- if (err)
- goto out2;
-
- err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
- if (err) {
+ err = 0;
+ if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0)
+ err = check_eofblocks_fl(handle, inode, map->m_lblk,
+ path, ar.len);
+ if (!err)
+ err = ext4_ext_insert_extent(handle, inode, path,
+ &newex, flags);
+ if (err && free_on_err) {
+ int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
+ EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;
/* free data blocks we just allocated */
/* not a good idea to call discard here directly,
* but otherwise we'd need to call it every free() */
ext4_discard_preallocations(inode);
ext4_free_blocks(handle, inode, NULL, ext4_ext_pblock(&newex),
- ext4_ext_get_actual_len(&newex), 0);
+ ext4_ext_get_actual_len(&newex), fb_flags);
goto out2;
}
@@ -3621,8 +4067,82 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* Update reserved blocks/metadata blocks after successful
* block allocation which had been deferred till now.
*/
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
- ext4_da_update_reserve_space(inode, allocated, 1);
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+ unsigned int reserved_clusters;
+ /*
+ * Check how many clusters we had reserved this allocated range
+ */
+ reserved_clusters = get_reserved_cluster_alloc(inode,
+ map->m_lblk, allocated);
+ if (map->m_flags & EXT4_MAP_FROM_CLUSTER) {
+ if (reserved_clusters) {
+ /*
+ * We have clusters reserved for this range.
+ * But since we are not doing actual allocation
+ * and are simply using blocks from previously
+ * allocated cluster, we should release the
+ * reservation and not claim quota.
+ */
+ ext4_da_update_reserve_space(inode,
+ reserved_clusters, 0);
+ }
+ } else {
+ BUG_ON(allocated_clusters < reserved_clusters);
+ /* We will claim quota for all newly allocated blocks.*/
+ ext4_da_update_reserve_space(inode, allocated_clusters,
+ 1);
+ if (reserved_clusters < allocated_clusters) {
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int reservation = allocated_clusters -
+ reserved_clusters;
+ /*
+ * It seems we claimed few clusters outside of
+ * the range of this allocation. We should give
+ * it back to the reservation pool. This can
+ * happen in the following case:
+ *
+ * * Suppose s_cluster_ratio is 4 (i.e., each
+ * cluster has 4 blocks. Thus, the clusters
+ * are [0-3],[4-7],[8-11]...
+ * * First comes delayed allocation write for
+ * logical blocks 10 & 11. Since there were no
+ * previous delayed allocated blocks in the
+ * range [8-11], we would reserve 1 cluster
+ * for this write.
+ * * Next comes write for logical blocks 3 to 8.
+ * In this case, we will reserve 2 clusters
+ * (for [0-3] and [4-7]; and not for [8-11] as
+ * that range has a delayed allocated blocks.
+ * Thus total reserved clusters now becomes 3.
+ * * Now, during the delayed allocation writeout
+ * time, we will first write blocks [3-8] and
+ * allocate 3 clusters for writing these
+ * blocks. Also, we would claim all these
+ * three clusters above.
+ * * Now when we come here to writeout the
+ * blocks [10-11], we would expect to claim
+ * the reservation of 1 cluster we had made
+ * (and we would claim it since there are no
+ * more delayed allocated blocks in the range
+ * [8-11]. But our reserved cluster count had
+ * already gone to 0.
+ *
+ * Thus, at the step 4 above when we determine
+ * that there are still some unwritten delayed
+ * allocated blocks outside of our current
+ * block range, we should increment the
+ * reserved clusters count so that when the
+ * remaining blocks finally gets written, we
+ * could claim them.
+ */
+ dquot_reserve_block(inode,
+ EXT4_C2B(sbi, reservation));
+ spin_lock(&ei->i_block_reservation_lock);
+ ei->i_reserved_data_blocks += reservation;
+ spin_unlock(&ei->i_block_reservation_lock);
+ }
+ }
+ }
/*
* Cache the extent and update transaction to commit on fdatasync only
@@ -3645,12 +4165,12 @@ out2:
ext4_ext_drop_refs(path);
kfree(path);
}
- trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
- newblock, map->m_len, err ? err : allocated);
-
result = (flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) ?
punched_out : allocated;
+ trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
+ newblock, map->m_len, err ? err : result);
+
return err ? err : result;
}
@@ -3660,6 +4180,7 @@ void ext4_ext_truncate(struct inode *inode)
struct super_block *sb = inode->i_sb;
ext4_lblk_t last_block;
handle_t *handle;
+ loff_t page_len;
int err = 0;
/*
@@ -3676,8 +4197,16 @@ void ext4_ext_truncate(struct inode *inode)
if (IS_ERR(handle))
return;
- if (inode->i_size & (sb->s_blocksize - 1))
- 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 (ext4_orphan_add(handle, inode))
goto out_stop;
@@ -3699,7 +4228,7 @@ void ext4_ext_truncate(struct inode *inode)
last_block = (inode->i_size + sb->s_blocksize - 1)
>> EXT4_BLOCK_SIZE_BITS(sb);
- err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
+ err = ext4_ext_remove_space(inode, last_block);
/* In a multi-transaction truncate, we only make the final
* transaction synchronous.
@@ -3771,6 +4300,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
int ret = 0;
int ret2 = 0;
int retries = 0;
+ int flags;
struct ext4_map_blocks map;
unsigned int credits, blkbits = inode->i_blkbits;
@@ -3807,6 +4337,16 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
return ret;
}
+ flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
+ if (mode & FALLOC_FL_KEEP_SIZE)
+ flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+ /*
+ * Don't normalize the request if it can fit in one extent so
+ * that it doesn't get unnecessarily split into multiple
+ * extents.
+ */
+ if (len <= EXT_UNINIT_MAX_LEN << blkbits)
+ flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
retry:
while (ret >= 0 && ret < max_blocks) {
map.m_lblk = map.m_lblk + ret;
@@ -3816,9 +4356,7 @@ retry:
ret = PTR_ERR(handle);
break;
}
- ret = ext4_map_blocks(handle, inode, &map,
- EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
- EXT4_GET_BLOCKS_NO_NORMALIZE);
+ ret = ext4_map_blocks(handle, inode, &map, flags);
if (ret <= 0) {
#ifdef EXT4FS_DEBUG
WARN_ON(ret <= 0);
@@ -3835,7 +4373,7 @@ retry:
blkbits) >> blkbits))
new_size = offset + len;
else
- new_size = (map.m_lblk + ret) << blkbits;
+ new_size = ((loff_t) map.m_lblk + ret) << blkbits;
ext4_falloc_update_inode(inode, mode, new_size,
(map.m_flags & EXT4_MAP_NEW));
@@ -4113,7 +4651,6 @@ found_delayed_extent:
return EXT_BREAK;
return EXT_CONTINUE;
}
-
/* fiemap flags we can handle specified here */
#define EXT4_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
@@ -4173,17 +4710,28 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
struct address_space *mapping = inode->i_mapping;
struct ext4_map_blocks map;
handle_t *handle;
- loff_t first_block_offset, last_block_offset, block_len;
- loff_t first_page, last_page, first_page_offset, last_page_offset;
+ loff_t first_page, last_page, page_len;
+ loff_t first_page_offset, last_page_offset;
int ret, credits, blocks_released, err = 0;
+ /* No need to punch hole beyond i_size */
+ if (offset >= inode->i_size)
+ return 0;
+
+ /*
+ * If the hole extends beyond i_size, set the hole
+ * to end after the page that contains i_size
+ */
+ if (offset + length > inode->i_size) {
+ length = inode->i_size +
+ PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
+ offset;
+ }
+
first_block = (offset + sb->s_blocksize - 1) >>
EXT4_BLOCK_SIZE_BITS(sb);
last_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
- first_block_offset = first_block << EXT4_BLOCK_SIZE_BITS(sb);
- last_block_offset = last_block << EXT4_BLOCK_SIZE_BITS(sb);
-
first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
last_page = (offset + length) >> PAGE_CACHE_SHIFT;
@@ -4196,11 +4744,10 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
*/
if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
err = filemap_write_and_wait_range(mapping,
- first_page_offset == 0 ? 0 : first_page_offset-1,
- last_page_offset);
+ offset, offset + length - 1);
- if (err)
- return err;
+ if (err)
+ return err;
}
/* Now release the pages */
@@ -4222,24 +4769,64 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
goto out;
/*
- * Now we need to zero out the un block aligned data.
- * If the file is smaller than a block, just
- * zero out the middle
+ * Now we need to zero out the non-page-aligned data in the
+ * pages at the start and tail of the hole, and unmap the buffer
+ * heads for the block aligned regions of the page that were
+ * completely zeroed.
+ */
+ if (first_page > last_page) {
+ /*
+ * If the file space being truncated is contained within a page
+ * just zero out and unmap the middle of that page
+ */
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, offset, length, 0);
+
+ if (err)
+ goto out;
+ } else {
+ /*
+ * zero out and unmap the partial page that contains
+ * the start of the hole
+ */
+ page_len = first_page_offset - offset;
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle, mapping,
+ offset, page_len, 0);
+ if (err)
+ goto out;
+ }
+
+ /*
+ * zero out and unmap the partial page that contains
+ * the end of the hole
+ */
+ page_len = offset + length - last_page_offset;
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle, mapping,
+ last_page_offset, page_len, 0);
+ if (err)
+ goto out;
+ }
+ }
+
+
+ /*
+ * If i_size is contained in the last page, we need to
+ * unmap and zero the partial page after i_size
*/
- if (first_block > last_block)
- ext4_block_zero_page_range(handle, mapping, offset, length);
- else {
- /* zero out the head of the hole before the first block */
- block_len = first_block_offset - offset;
- if (block_len > 0)
- ext4_block_zero_page_range(handle, mapping,
- offset, block_len);
-
- /* zero out the tail of the hole after the last block */
- block_len = offset + length - last_block_offset;
- if (block_len > 0) {
- ext4_block_zero_page_range(handle, mapping,
- last_block_offset, block_len);
+ if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
+ inode->i_size % PAGE_CACHE_SIZE != 0) {
+
+ page_len = PAGE_CACHE_SIZE -
+ (inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, inode->i_size, page_len, 0);
+
+ if (err)
+ goto out;
}
}
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index ce766f974b1d..cb70f1812a70 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -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);
}
}
@@ -224,53 +224,8 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
else
maxbytes = inode->i_sb->s_maxbytes;
- mutex_lock(&inode->i_mutex);
- switch (origin) {
- case SEEK_END:
- offset += inode->i_size;
- break;
- case SEEK_CUR:
- if (offset == 0) {
- mutex_unlock(&inode->i_mutex);
- return file->f_pos;
- }
- offset += file->f_pos;
- break;
- case SEEK_DATA:
- /*
- * In the generic case the entire file is data, so as long as
- * offset isn't at the end of the file then the offset is data.
- */
- if (offset >= inode->i_size) {
- mutex_unlock(&inode->i_mutex);
- return -ENXIO;
- }
- break;
- case SEEK_HOLE:
- /*
- * There is a virtual hole at the end of the file, so as long as
- * offset isn't i_size or larger, return i_size.
- */
- if (offset >= inode->i_size) {
- mutex_unlock(&inode->i_mutex);
- return -ENXIO;
- }
- offset = inode->i_size;
- break;
- }
-
- if (offset < 0 || offset > maxbytes) {
- mutex_unlock(&inode->i_mutex);
- return -EINVAL;
- }
-
- if (offset != file->f_pos) {
- file->f_pos = offset;
- file->f_version = 0;
- }
- mutex_unlock(&inode->i_mutex);
- return offset;
+ return generic_file_llseek_size(file, offset, origin, maxbytes);
}
const struct file_operations ext4_file_operations = {
@@ -301,7 +256,7 @@ const struct inode_operations ext4_file_inode_operations = {
.listxattr = ext4_listxattr,
.removexattr = generic_removexattr,
#endif
- .check_acl = ext4_check_acl,
+ .get_acl = ext4_get_acl,
.fiemap = ext4_fiemap,
};
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index da3bed3e0c29..00a2cb753efd 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -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;
@@ -129,15 +125,30 @@ static int ext4_sync_parent(struct inode *inode)
{
struct writeback_control wbc;
struct dentry *dentry = NULL;
+ struct inode *next;
int ret = 0;
- while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
+ if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
+ return 0;
+ inode = igrab(inode);
+ while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
- dentry = list_entry(inode->i_dentry.next,
- struct dentry, d_alias);
- if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode)
+ dentry = NULL;
+ spin_lock(&inode->i_lock);
+ if (!list_empty(&inode->i_dentry)) {
+ dentry = list_first_entry(&inode->i_dentry,
+ struct dentry, d_alias);
+ dget(dentry);
+ }
+ spin_unlock(&inode->i_lock);
+ if (!dentry)
+ break;
+ next = igrab(dentry->d_parent->d_inode);
+ dput(dentry);
+ if (!next)
break;
- inode = dentry->d_parent->d_inode;
+ iput(inode);
+ inode = next;
ret = sync_mapping_buffers(inode->i_mapping);
if (ret)
break;
@@ -148,6 +159,7 @@ static int ext4_sync_parent(struct inode *inode)
if (ret)
break;
}
+ iput(inode);
return ret;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 21bb2f61e502..00beb4f9cc4f 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -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;
@@ -1084,7 +948,7 @@ fail_free_drop:
fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
- inode->i_nlink = 0;
+ clear_nlink(inode);
unlock_new_inode(inode);
iput(inode);
brelse(inode_bitmap_bh);
@@ -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);
@@ -1287,7 +1151,7 @@ extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
group, used_blks,
ext4_itable_unused_count(sb, gdp));
ret = 1;
- goto out;
+ goto err_out;
}
blk = ext4_inode_table(sb, gdp) + used_blks;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
new file mode 100644
index 000000000000..3cfc73fbca8e
--- /dev/null
+++ b/fs/ext4/indirect.c
@@ -0,0 +1,1503 @@
+/*
+ * linux/fs/ext4/indirect.c
+ *
+ * from
+ *
+ * linux/fs/ext4/inode.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card ([email protected])
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * from
+ *
+ * linux/fs/minix/inode.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * Goal-directed block allocation by Stephen Tweedie
+ * ([email protected]), 1993, 1998
+ */
+
+#include <linux/module.h>
+#include "ext4_jbd2.h"
+#include "truncate.h"
+
+#include <trace/events/ext4.h>
+
+typedef struct {
+ __le32 *p;
+ __le32 key;
+ struct buffer_head *bh;
+} Indirect;
+
+static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
+{
+ p->key = *(p->p = v);
+ p->bh = bh;
+}
+
+/**
+ * ext4_block_to_path - parse the block number into array of offsets
+ * @inode: inode in question (we are only interested in its superblock)
+ * @i_block: block number to be parsed
+ * @offsets: array to store the offsets in
+ * @boundary: set this non-zero if the referred-to block is likely to be
+ * followed (on disk) by an indirect block.
+ *
+ * To store the locations of file's data ext4 uses a data structure common
+ * for UNIX filesystems - tree of pointers anchored in the inode, with
+ * data blocks at leaves and indirect blocks in intermediate nodes.
+ * This function translates the block number into path in that tree -
+ * return value is the path length and @offsets[n] is the offset of
+ * pointer to (n+1)th node in the nth one. If @block is out of range
+ * (negative or too large) warning is printed and zero returned.
+ *
+ * Note: function doesn't find node addresses, so no IO is needed. All
+ * we need to know is the capacity of indirect blocks (taken from the
+ * inode->i_sb).
+ */
+
+/*
+ * Portability note: the last comparison (check that we fit into triple
+ * indirect block) is spelled differently, because otherwise on an
+ * architecture with 32-bit longs and 8Kb pages we might get into trouble
+ * if our filesystem had 8Kb blocks. We might use long long, but that would
+ * kill us on x86. Oh, well, at least the sign propagation does not matter -
+ * i_block would have to be negative in the very beginning, so we would not
+ * get there at all.
+ */
+
+static int ext4_block_to_path(struct inode *inode,
+ ext4_lblk_t i_block,
+ ext4_lblk_t offsets[4], int *boundary)
+{
+ int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+ int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb);
+ const long direct_blocks = EXT4_NDIR_BLOCKS,
+ indirect_blocks = ptrs,
+ double_blocks = (1 << (ptrs_bits * 2));
+ int n = 0;
+ int final = 0;
+
+ if (i_block < direct_blocks) {
+ offsets[n++] = i_block;
+ final = direct_blocks;
+ } else if ((i_block -= direct_blocks) < indirect_blocks) {
+ offsets[n++] = EXT4_IND_BLOCK;
+ offsets[n++] = i_block;
+ final = ptrs;
+ } else if ((i_block -= indirect_blocks) < double_blocks) {
+ offsets[n++] = EXT4_DIND_BLOCK;
+ offsets[n++] = i_block >> ptrs_bits;
+ offsets[n++] = i_block & (ptrs - 1);
+ final = ptrs;
+ } else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) {
+ offsets[n++] = EXT4_TIND_BLOCK;
+ offsets[n++] = i_block >> (ptrs_bits * 2);
+ offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1);
+ offsets[n++] = i_block & (ptrs - 1);
+ final = ptrs;
+ } else {
+ ext4_warning(inode->i_sb, "block %lu > max in inode %lu",
+ i_block + direct_blocks +
+ indirect_blocks + double_blocks, inode->i_ino);
+ }
+ if (boundary)
+ *boundary = final - 1 - (i_block & (ptrs - 1));
+ return n;
+}
+
+/**
+ * ext4_get_branch - read the chain of indirect blocks leading to data
+ * @inode: inode in question
+ * @depth: depth of the chain (1 - direct pointer, etc.)
+ * @offsets: offsets of pointers in inode/indirect blocks
+ * @chain: place to store the result
+ * @err: here we store the error value
+ *
+ * Function fills the array of triples <key, p, bh> and returns %NULL
+ * if everything went OK or the pointer to the last filled triple
+ * (incomplete one) otherwise. Upon the return chain[i].key contains
+ * the number of (i+1)-th block in the chain (as it is stored in memory,
+ * i.e. little-endian 32-bit), chain[i].p contains the address of that
+ * number (it points into struct inode for i==0 and into the bh->b_data
+ * for i>0) and chain[i].bh points to the buffer_head of i-th indirect
+ * block for i>0 and NULL for i==0. In other words, it holds the block
+ * numbers of the chain, addresses they were taken from (and where we can
+ * verify that chain did not change) and buffer_heads hosting these
+ * numbers.
+ *
+ * Function stops when it stumbles upon zero pointer (absent block)
+ * (pointer to last triple returned, *@err == 0)
+ * or when it gets an IO error reading an indirect block
+ * (ditto, *@err == -EIO)
+ * or when it reads all @depth-1 indirect blocks successfully and finds
+ * the whole chain, all way to the data (returns %NULL, *err == 0).
+ *
+ * Need to be called with
+ * down_read(&EXT4_I(inode)->i_data_sem)
+ */
+static Indirect *ext4_get_branch(struct inode *inode, int depth,
+ ext4_lblk_t *offsets,
+ Indirect chain[4], int *err)
+{
+ struct super_block *sb = inode->i_sb;
+ Indirect *p = chain;
+ struct buffer_head *bh;
+
+ *err = 0;
+ /* i_data is not going away, no lock needed */
+ add_chain(chain, NULL, EXT4_I(inode)->i_data + *offsets);
+ if (!p->key)
+ goto no_block;
+ while (--depth) {
+ bh = sb_getblk(sb, le32_to_cpu(p->key));
+ if (unlikely(!bh))
+ goto failure;
+
+ if (!bh_uptodate_or_lock(bh)) {
+ if (bh_submit_read(bh) < 0) {
+ put_bh(bh);
+ goto failure;
+ }
+ /* validate block references */
+ if (ext4_check_indirect_blockref(inode, bh)) {
+ put_bh(bh);
+ goto failure;
+ }
+ }
+
+ add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
+ /* Reader: end */
+ if (!p->key)
+ goto no_block;
+ }
+ return NULL;
+
+failure:
+ *err = -EIO;
+no_block:
+ return p;
+}
+
+/**
+ * ext4_find_near - find a place for allocation with sufficient locality
+ * @inode: owner
+ * @ind: descriptor of indirect block.
+ *
+ * This function returns the preferred place for block allocation.
+ * It is used when heuristic for sequential allocation fails.
+ * Rules are:
+ * + if there is a block to the left of our position - allocate near it.
+ * + if pointer will live in indirect block - allocate near that block.
+ * + if pointer will live in inode - allocate in the same
+ * cylinder group.
+ *
+ * In the latter case we colour the starting block by the callers PID to
+ * prevent it from clashing with concurrent allocations for a different inode
+ * in the same block group. The PID is used here so that functionally related
+ * files will be close-by on-disk.
+ *
+ * Caller must make sure that @ind is valid and will stay that way.
+ */
+static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ __le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
+ __le32 *p;
+
+ /* Try to find previous block */
+ for (p = ind->p - 1; p >= start; p--) {
+ if (*p)
+ return le32_to_cpu(*p);
+ }
+
+ /* No such thing, so let's try location of indirect block */
+ if (ind->bh)
+ return ind->bh->b_blocknr;
+
+ /*
+ * It is going to be referred to from the inode itself? OK, just put it
+ * into the same cylinder group then.
+ */
+ return ext4_inode_to_goal_block(inode);
+}
+
+/**
+ * ext4_find_goal - find a preferred place for allocation.
+ * @inode: owner
+ * @block: block we want
+ * @partial: pointer to the last triple within a chain
+ *
+ * Normally this function find the preferred place for block allocation,
+ * returns it.
+ * Because this is only used for non-extent files, we limit the block nr
+ * to 32 bits.
+ */
+static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
+ Indirect *partial)
+{
+ ext4_fsblk_t goal;
+
+ /*
+ * XXX need to get goal block from mballoc's data structures
+ */
+
+ goal = ext4_find_near(inode, partial);
+ goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
+ return goal;
+}
+
+/**
+ * ext4_blks_to_allocate - Look up the block map and count the number
+ * of direct blocks need to be allocated for the given branch.
+ *
+ * @branch: chain of indirect blocks
+ * @k: number of blocks need for indirect blocks
+ * @blks: number of data blocks to be mapped.
+ * @blocks_to_boundary: the offset in the indirect block
+ *
+ * return the total number of blocks to be allocate, including the
+ * direct and indirect blocks.
+ */
+static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
+ int blocks_to_boundary)
+{
+ unsigned int count = 0;
+
+ /*
+ * Simple case, [t,d]Indirect block(s) has not allocated yet
+ * then it's clear blocks on that path have not allocated
+ */
+ if (k > 0) {
+ /* right now we don't handle cross boundary allocation */
+ if (blks < blocks_to_boundary + 1)
+ count += blks;
+ else
+ count += blocks_to_boundary + 1;
+ return count;
+ }
+
+ count++;
+ while (count < blks && count <= blocks_to_boundary &&
+ le32_to_cpu(*(branch[0].p + count)) == 0) {
+ count++;
+ }
+ return count;
+}
+
+/**
+ * ext4_alloc_blocks: multiple allocate blocks needed for a branch
+ * @handle: handle for this transaction
+ * @inode: inode which needs allocated blocks
+ * @iblock: the logical block to start allocated at
+ * @goal: preferred physical block of allocation
+ * @indirect_blks: the number of blocks need to allocate for indirect
+ * blocks
+ * @blks: number of desired blocks
+ * @new_blocks: on return it will store the new block numbers for
+ * the indirect blocks(if needed) and the first direct block,
+ * @err: on return it will store the error code
+ *
+ * This function will return the number of blocks allocated as
+ * requested by the passed-in parameters.
+ */
+static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
+ ext4_lblk_t iblock, ext4_fsblk_t goal,
+ int indirect_blks, int blks,
+ ext4_fsblk_t new_blocks[4], int *err)
+{
+ struct ext4_allocation_request ar;
+ int target, i;
+ unsigned long count = 0, blk_allocated = 0;
+ int index = 0;
+ ext4_fsblk_t current_block = 0;
+ int ret = 0;
+
+ /*
+ * Here we try to allocate the requested multiple blocks at once,
+ * on a best-effort basis.
+ * To build a branch, we should allocate blocks for
+ * the indirect blocks(if not allocated yet), and at least
+ * the first direct block of this branch. That's the
+ * minimum number of blocks need to allocate(required)
+ */
+ /* first we try to allocate the indirect blocks */
+ target = indirect_blks;
+ while (target > 0) {
+ count = target;
+ /* allocating blocks for indirect blocks and direct blocks */
+ current_block = ext4_new_meta_blocks(handle, inode, goal,
+ 0, &count, err);
+ if (*err)
+ goto failed_out;
+
+ if (unlikely(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS)) {
+ EXT4_ERROR_INODE(inode,
+ "current_block %llu + count %lu > %d!",
+ current_block, count,
+ EXT4_MAX_BLOCK_FILE_PHYS);
+ *err = -EIO;
+ goto failed_out;
+ }
+
+ target -= count;
+ /* allocate blocks for indirect blocks */
+ while (index < indirect_blks && count) {
+ new_blocks[index++] = current_block++;
+ count--;
+ }
+ if (count > 0) {
+ /*
+ * save the new block number
+ * for the first direct block
+ */
+ new_blocks[index] = current_block;
+ printk(KERN_INFO "%s returned more blocks than "
+ "requested\n", __func__);
+ WARN_ON(1);
+ break;
+ }
+ }
+
+ target = blks - count ;
+ blk_allocated = count;
+ if (!target)
+ goto allocated;
+ /* Now allocate data blocks */
+ memset(&ar, 0, sizeof(ar));
+ ar.inode = inode;
+ ar.goal = goal;
+ ar.len = target;
+ ar.logical = iblock;
+ if (S_ISREG(inode->i_mode))
+ /* enable in-core preallocation only for regular files */
+ ar.flags = EXT4_MB_HINT_DATA;
+
+ current_block = ext4_mb_new_blocks(handle, &ar, err);
+ if (unlikely(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS)) {
+ EXT4_ERROR_INODE(inode,
+ "current_block %llu + ar.len %d > %d!",
+ current_block, ar.len,
+ EXT4_MAX_BLOCK_FILE_PHYS);
+ *err = -EIO;
+ goto failed_out;
+ }
+
+ if (*err && (target == blks)) {
+ /*
+ * if the allocation failed and we didn't allocate
+ * any blocks before
+ */
+ goto failed_out;
+ }
+ if (!*err) {
+ if (target == blks) {
+ /*
+ * save the new block number
+ * for the first direct block
+ */
+ new_blocks[index] = current_block;
+ }
+ blk_allocated += ar.len;
+ }
+allocated:
+ /* total number of blocks allocated for direct blocks */
+ ret = blk_allocated;
+ *err = 0;
+ return ret;
+failed_out:
+ for (i = 0; i < index; i++)
+ ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
+ return ret;
+}
+
+/**
+ * ext4_alloc_branch - allocate and set up a chain of blocks.
+ * @handle: handle for this transaction
+ * @inode: owner
+ * @indirect_blks: number of allocated indirect blocks
+ * @blks: number of allocated direct blocks
+ * @goal: preferred place for allocation
+ * @offsets: offsets (in the blocks) to store the pointers to next.
+ * @branch: place to store the chain in.
+ *
+ * This function allocates blocks, zeroes out all but the last one,
+ * links them into chain and (if we are synchronous) writes them to disk.
+ * In other words, it prepares a branch that can be spliced onto the
+ * inode. It stores the information about that chain in the branch[], in
+ * the same format as ext4_get_branch() would do. We are calling it after
+ * we had read the existing part of chain and partial points to the last
+ * triple of that (one with zero ->key). Upon the exit we have the same
+ * picture as after the successful ext4_get_block(), except that in one
+ * place chain is disconnected - *branch->p is still zero (we did not
+ * set the last link), but branch->key contains the number that should
+ * be placed into *branch->p to fill that gap.
+ *
+ * If allocation fails we free all blocks we've allocated (and forget
+ * their buffer_heads) and return the error value the from failed
+ * ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain
+ * as described above and return 0.
+ */
+static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
+ ext4_lblk_t iblock, int indirect_blks,
+ int *blks, ext4_fsblk_t goal,
+ ext4_lblk_t *offsets, Indirect *branch)
+{
+ int blocksize = inode->i_sb->s_blocksize;
+ int i, n = 0;
+ int err = 0;
+ struct buffer_head *bh;
+ int num;
+ ext4_fsblk_t new_blocks[4];
+ ext4_fsblk_t current_block;
+
+ num = ext4_alloc_blocks(handle, inode, iblock, goal, indirect_blks,
+ *blks, new_blocks, &err);
+ if (err)
+ return err;
+
+ branch[0].key = cpu_to_le32(new_blocks[0]);
+ /*
+ * metadata blocks and data blocks are allocated.
+ */
+ for (n = 1; n <= indirect_blks; n++) {
+ /*
+ * Get buffer_head for parent block, zero it out
+ * and set the pointer to new one, then send
+ * parent to disk.
+ */
+ bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
+ if (unlikely(!bh)) {
+ err = -EIO;
+ goto failed;
+ }
+
+ branch[n].bh = bh;
+ lock_buffer(bh);
+ BUFFER_TRACE(bh, "call get_create_access");
+ err = ext4_journal_get_create_access(handle, bh);
+ if (err) {
+ /* Don't brelse(bh) here; it's done in
+ * ext4_journal_forget() below */
+ unlock_buffer(bh);
+ goto failed;
+ }
+
+ memset(bh->b_data, 0, blocksize);
+ branch[n].p = (__le32 *) bh->b_data + offsets[n];
+ branch[n].key = cpu_to_le32(new_blocks[n]);
+ *branch[n].p = branch[n].key;
+ if (n == indirect_blks) {
+ current_block = new_blocks[n];
+ /*
+ * End of chain, update the last new metablock of
+ * the chain to point to the new allocated
+ * data blocks numbers
+ */
+ for (i = 1; i < num; i++)
+ *(branch[n].p + i) = cpu_to_le32(++current_block);
+ }
+ BUFFER_TRACE(bh, "marking uptodate");
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
+ if (err)
+ goto failed;
+ }
+ *blks = num;
+ return err;
+failed:
+ /* Allocation failed, free what we already allocated */
+ ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0);
+ for (i = 1; i <= n ; i++) {
+ /*
+ * branch[i].bh is newly allocated, so there is no
+ * need to revoke the block, which is why we don't
+ * need to set EXT4_FREE_BLOCKS_METADATA.
+ */
+ ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1,
+ EXT4_FREE_BLOCKS_FORGET);
+ }
+ for (i = n+1; i < indirect_blks; i++)
+ ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
+
+ ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0);
+
+ return err;
+}
+
+/**
+ * ext4_splice_branch - splice the allocated branch onto inode.
+ * @handle: handle for this transaction
+ * @inode: owner
+ * @block: (logical) number of block we are adding
+ * @chain: chain of indirect blocks (with a missing link - see
+ * ext4_alloc_branch)
+ * @where: location of missing link
+ * @num: number of indirect blocks we are adding
+ * @blks: number of direct blocks we are adding
+ *
+ * This function fills the missing link and does all housekeeping needed in
+ * inode (->i_blocks, etc.). In case of success we end up with the full
+ * chain to new block and return 0.
+ */
+static int ext4_splice_branch(handle_t *handle, struct inode *inode,
+ ext4_lblk_t block, Indirect *where, int num,
+ int blks)
+{
+ int i;
+ int err = 0;
+ ext4_fsblk_t current_block;
+
+ /*
+ * If we're splicing into a [td]indirect block (as opposed to the
+ * inode) then we need to get write access to the [td]indirect block
+ * before the splice.
+ */
+ if (where->bh) {
+ BUFFER_TRACE(where->bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, where->bh);
+ if (err)
+ goto err_out;
+ }
+ /* That's it */
+
+ *where->p = where->key;
+
+ /*
+ * Update the host buffer_head or inode to point to more just allocated
+ * direct blocks blocks
+ */
+ if (num == 0 && blks > 1) {
+ current_block = le32_to_cpu(where->key) + 1;
+ for (i = 1; i < blks; i++)
+ *(where->p + i) = cpu_to_le32(current_block++);
+ }
+
+ /* We are done with atomic stuff, now do the rest of housekeeping */
+ /* had we spliced it onto indirect block? */
+ if (where->bh) {
+ /*
+ * If we spliced it onto an indirect block, we haven't
+ * altered the inode. Note however that if it is being spliced
+ * onto an indirect block at the very end of the file (the
+ * file is growing) then we *will* alter the inode to reflect
+ * the new i_size. But that is not done here - it is done in
+ * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode.
+ */
+ jbd_debug(5, "splicing indirect only\n");
+ BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, where->bh);
+ if (err)
+ goto err_out;
+ } else {
+ /*
+ * OK, we spliced it into the inode itself on a direct block.
+ */
+ ext4_mark_inode_dirty(handle, inode);
+ jbd_debug(5, "splicing direct\n");
+ }
+ return err;
+
+err_out:
+ for (i = 1; i <= num; i++) {
+ /*
+ * branch[i].bh is newly allocated, so there is no
+ * need to revoke the block, which is why we don't
+ * need to set EXT4_FREE_BLOCKS_METADATA.
+ */
+ ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
+ EXT4_FREE_BLOCKS_FORGET);
+ }
+ ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key),
+ blks, 0);
+
+ return err;
+}
+
+/*
+ * The ext4_ind_map_blocks() function handles non-extents inodes
+ * (i.e., using the traditional indirect/double-indirect i_blocks
+ * scheme) for ext4_map_blocks().
+ *
+ * Allocation strategy is simple: if we have to allocate something, we will
+ * have to go the whole way to leaf. So let's do it before attaching anything
+ * to tree, set linkage between the newborn blocks, write them if sync is
+ * required, recheck the path, free and repeat if check fails, otherwise
+ * set the last missing link (that will protect us from any truncate-generated
+ * removals - all blocks on the path are immune now) and possibly force the
+ * write on the parent block.
+ * That has a nice additional property: no special recovery from the failed
+ * allocations is needed - we simply release blocks and do not touch anything
+ * reachable from inode.
+ *
+ * `handle' can be NULL if create == 0.
+ *
+ * return > 0, # of blocks mapped or allocated.
+ * return = 0, if plain lookup failed.
+ * return < 0, error case.
+ *
+ * The ext4_ind_get_blocks() function should be called with
+ * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem
+ * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or
+ * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system
+ * blocks.
+ */
+int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
+ struct ext4_map_blocks *map,
+ int flags)
+{
+ int err = -EIO;
+ ext4_lblk_t offsets[4];
+ Indirect chain[4];
+ Indirect *partial;
+ ext4_fsblk_t goal;
+ int indirect_blks;
+ int blocks_to_boundary = 0;
+ int depth;
+ int count = 0;
+ ext4_fsblk_t first_block = 0;
+
+ trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
+ J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
+ J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
+ depth = ext4_block_to_path(inode, map->m_lblk, offsets,
+ &blocks_to_boundary);
+
+ if (depth == 0)
+ goto out;
+
+ partial = ext4_get_branch(inode, depth, offsets, chain, &err);
+
+ /* Simplest case - block found, no allocation needed */
+ if (!partial) {
+ first_block = le32_to_cpu(chain[depth - 1].key);
+ count++;
+ /*map more blocks*/
+ while (count < map->m_len && count <= blocks_to_boundary) {
+ ext4_fsblk_t blk;
+
+ blk = le32_to_cpu(*(chain[depth-1].p + count));
+
+ if (blk == first_block + count)
+ count++;
+ else
+ break;
+ }
+ goto got_it;
+ }
+
+ /* Next simple case - plain lookup or failed read of indirect block */
+ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO)
+ goto cleanup;
+
+ /*
+ * 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 */
+ indirect_blks = (chain + depth) - partial - 1;
+
+ /*
+ * Next look up the indirect map to count the totoal number of
+ * direct blocks to allocate for this branch.
+ */
+ count = ext4_blks_to_allocate(partial, indirect_blks,
+ map->m_len, blocks_to_boundary);
+ /*
+ * Block out ext4_truncate while we alter the tree
+ */
+ err = ext4_alloc_branch(handle, inode, map->m_lblk, indirect_blks,
+ &count, goal,
+ offsets + (partial - chain), partial);
+
+ /*
+ * The ext4_splice_branch call will free and forget any buffers
+ * on the new chain if there is a failure, but that risks using
+ * up transaction credits, especially for bitmaps where the
+ * credits cannot be returned. Can we handle this somehow? We
+ * may need to return -EAGAIN upwards in the worst case. --sct
+ */
+ if (!err)
+ err = ext4_splice_branch(handle, inode, map->m_lblk,
+ partial, indirect_blks, count);
+ if (err)
+ goto cleanup;
+
+ map->m_flags |= EXT4_MAP_NEW;
+
+ ext4_update_inode_fsync_trans(handle, inode, 1);
+got_it:
+ map->m_flags |= EXT4_MAP_MAPPED;
+ map->m_pblk = le32_to_cpu(chain[depth-1].key);
+ map->m_len = count;
+ if (count > blocks_to_boundary)
+ map->m_flags |= EXT4_MAP_BOUNDARY;
+ err = count;
+ /* Clean up and exit */
+ partial = chain + depth - 1; /* the whole chain */
+cleanup:
+ while (partial > chain) {
+ BUFFER_TRACE(partial->bh, "call brelse");
+ brelse(partial->bh);
+ partial--;
+ }
+out:
+ trace_ext4_ind_map_blocks_exit(inode, map->m_lblk,
+ map->m_pblk, map->m_len, err);
+ return err;
+}
+
+/*
+ * O_DIRECT for ext3 (or indirect map) based files
+ *
+ * If the O_DIRECT write will extend the file then add this inode to the
+ * orphan list. So recovery will truncate it back to the original size
+ * if the machine crashes during the write.
+ *
+ * If the O_DIRECT write is intantiating holes inside i_size and the machine
+ * crashes then stale disk data _may_ be exposed inside the file. But current
+ * VFS code falls back into buffered path in that case so we are safe.
+ */
+ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
+ const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ handle_t *handle;
+ ssize_t ret;
+ int orphan = 0;
+ size_t count = iov_length(iov, nr_segs);
+ int retries = 0;
+
+ if (rw == WRITE) {
+ loff_t final_size = offset + count;
+
+ if (final_size > inode->i_size) {
+ /* Credits for sb + inode write */
+ handle = ext4_journal_start(inode, 2);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+ ret = ext4_orphan_add(handle, inode);
+ if (ret) {
+ ext4_journal_stop(handle);
+ goto out;
+ }
+ orphan = 1;
+ ei->i_disksize = inode->i_size;
+ ext4_journal_stop(handle);
+ }
+ }
+
+retry:
+ if (rw == READ && ext4_should_dioread_nolock(inode)) {
+ if (unlikely(!list_empty(&ei->i_completed_io_list))) {
+ mutex_lock(&inode->i_mutex);
+ ext4_flush_completed_IO(inode);
+ mutex_unlock(&inode->i_mutex);
+ }
+ ret = __blockdev_direct_IO(rw, iocb, inode,
+ inode->i_sb->s_bdev, iov,
+ offset, nr_segs,
+ ext4_get_block, NULL, NULL, 0);
+ } else {
+ ret = blockdev_direct_IO(rw, iocb, inode, iov,
+ offset, nr_segs, ext4_get_block);
+
+ if (unlikely((rw & WRITE) && ret < 0)) {
+ loff_t isize = i_size_read(inode);
+ loff_t end = offset + iov_length(iov, nr_segs);
+
+ if (end > isize)
+ ext4_truncate_failed_write(inode);
+ }
+ }
+ if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+
+ if (orphan) {
+ int err;
+
+ /* Credits for sb + inode write */
+ handle = ext4_journal_start(inode, 2);
+ if (IS_ERR(handle)) {
+ /* This is really bad luck. We've written the data
+ * but cannot extend i_size. Bail out and pretend
+ * the write failed... */
+ ret = PTR_ERR(handle);
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+
+ goto out;
+ }
+ if (inode->i_nlink)
+ ext4_orphan_del(handle, inode);
+ if (ret > 0) {
+ loff_t end = offset + ret;
+ if (end > inode->i_size) {
+ ei->i_disksize = end;
+ i_size_write(inode, end);
+ /*
+ * We're going to return a positive `ret'
+ * here due to non-zero-length I/O, so there's
+ * no way of reporting error returns from
+ * ext4_mark_inode_dirty() to userspace. So
+ * ignore it.
+ */
+ ext4_mark_inode_dirty(handle, inode);
+ }
+ }
+ err = ext4_journal_stop(handle);
+ if (ret == 0)
+ ret = err;
+ }
+out:
+ return ret;
+}
+
+/*
+ * Calculate the number of metadata blocks need to reserve
+ * to allocate a new block at @lblocks for non extent file based file
+ */
+int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1);
+ int blk_bits;
+
+ if (lblock < EXT4_NDIR_BLOCKS)
+ return 0;
+
+ lblock -= EXT4_NDIR_BLOCKS;
+
+ if (ei->i_da_metadata_calc_len &&
+ (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) {
+ ei->i_da_metadata_calc_len++;
+ return 0;
+ }
+ ei->i_da_metadata_calc_last_lblock = lblock & dind_mask;
+ ei->i_da_metadata_calc_len = 1;
+ blk_bits = order_base_2(lblock);
+ return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
+}
+
+int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+{
+ int indirects;
+
+ /* if nrblocks are contiguous */
+ if (chunk) {
+ /*
+ * With N contiguous data blocks, we need at most
+ * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks,
+ * 2 dindirect blocks, and 1 tindirect block
+ */
+ return DIV_ROUND_UP(nrblocks,
+ EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
+ }
+ /*
+ * if nrblocks are not contiguous, worse case, each block touch
+ * a indirect block, and each indirect block touch a double indirect
+ * block, plus a triple indirect block
+ */
+ indirects = nrblocks * 2 + 1;
+ return indirects;
+}
+
+/*
+ * Truncate transactions can be complex and absolutely huge. So we need to
+ * be able to restart the transaction at a conventient checkpoint to make
+ * sure we don't overflow the journal.
+ *
+ * start_transaction gets us a new handle for a truncate transaction,
+ * and extend_transaction tries to extend the existing one a bit. If
+ * extend fails, we need to propagate the failure up and restart the
+ * transaction in the top-level truncate loop. --sct
+ */
+static handle_t *start_transaction(struct inode *inode)
+{
+ handle_t *result;
+
+ result = ext4_journal_start(inode, ext4_blocks_for_truncate(inode));
+ if (!IS_ERR(result))
+ return result;
+
+ ext4_std_error(inode->i_sb, PTR_ERR(result));
+ return result;
+}
+
+/*
+ * Try to extend this transaction for the purposes of truncation.
+ *
+ * Returns 0 if we managed to create more room. If we can't create more
+ * room, and the transaction must be restarted we return 1.
+ */
+static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
+{
+ if (!ext4_handle_valid(handle))
+ return 0;
+ if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
+ return 0;
+ if (!ext4_journal_extend(handle, ext4_blocks_for_truncate(inode)))
+ return 0;
+ return 1;
+}
+
+/*
+ * Probably it should be a library function... search for first non-zero word
+ * or memcmp with zero_page, whatever is better for particular architecture.
+ * Linus?
+ */
+static inline int all_zeroes(__le32 *p, __le32 *q)
+{
+ while (p < q)
+ if (*p++)
+ return 0;
+ return 1;
+}
+
+/**
+ * ext4_find_shared - find the indirect blocks for partial truncation.
+ * @inode: inode in question
+ * @depth: depth of the affected branch
+ * @offsets: offsets of pointers in that branch (see ext4_block_to_path)
+ * @chain: place to store the pointers to partial indirect blocks
+ * @top: place to the (detached) top of branch
+ *
+ * This is a helper function used by ext4_truncate().
+ *
+ * When we do truncate() we may have to clean the ends of several
+ * indirect blocks but leave the blocks themselves alive. Block is
+ * partially truncated if some data below the new i_size is referred
+ * from it (and it is on the path to the first completely truncated
+ * data block, indeed). We have to free the top of that path along
+ * with everything to the right of the path. Since no allocation
+ * past the truncation point is possible until ext4_truncate()
+ * finishes, we may safely do the latter, but top of branch may
+ * require special attention - pageout below the truncation point
+ * might try to populate it.
+ *
+ * We atomically detach the top of branch from the tree, store the
+ * block number of its root in *@top, pointers to buffer_heads of
+ * partially truncated blocks - in @chain[].bh and pointers to
+ * their last elements that should not be removed - in
+ * @chain[].p. Return value is the pointer to last filled element
+ * of @chain.
+ *
+ * The work left to caller to do the actual freeing of subtrees:
+ * a) free the subtree starting from *@top
+ * b) free the subtrees whose roots are stored in
+ * (@chain[i].p+1 .. end of @chain[i].bh->b_data)
+ * c) free the subtrees growing from the inode past the @chain[0].
+ * (no partially truncated stuff there). */
+
+static Indirect *ext4_find_shared(struct inode *inode, int depth,
+ ext4_lblk_t offsets[4], Indirect chain[4],
+ __le32 *top)
+{
+ Indirect *partial, *p;
+ int k, err;
+
+ *top = 0;
+ /* Make k index the deepest non-null offset + 1 */
+ for (k = depth; k > 1 && !offsets[k-1]; k--)
+ ;
+ partial = ext4_get_branch(inode, k, offsets, chain, &err);
+ /* Writer: pointers */
+ if (!partial)
+ partial = chain + k-1;
+ /*
+ * If the branch acquired continuation since we've looked at it -
+ * fine, it should all survive and (new) top doesn't belong to us.
+ */
+ if (!partial->key && *partial->p)
+ /* Writer: end */
+ goto no_top;
+ for (p = partial; (p > chain) && all_zeroes((__le32 *) p->bh->b_data, p->p); p--)
+ ;
+ /*
+ * OK, we've found the last block that must survive. The rest of our
+ * branch should be detached before unlocking. However, if that rest
+ * of branch is all ours and does not grow immediately from the inode
+ * it's easier to cheat and just decrement partial->p.
+ */
+ if (p == chain + k - 1 && p > chain) {
+ p->p--;
+ } else {
+ *top = *p->p;
+ /* Nope, don't do this in ext4. Must leave the tree intact */
+#if 0
+ *p->p = 0;
+#endif
+ }
+ /* Writer: end */
+
+ while (partial > p) {
+ brelse(partial->bh);
+ partial--;
+ }
+no_top:
+ return partial;
+}
+
+/*
+ * Zero a number of block pointers in either an inode or an indirect block.
+ * If we restart the transaction we must again get write access to the
+ * indirect block for further modification.
+ *
+ * We release `count' blocks on disk, but (last - first) may be greater
+ * than `count' because there can be holes in there.
+ *
+ * Return 0 on success, 1 on invalid block range
+ * and < 0 on fatal error.
+ */
+static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh,
+ ext4_fsblk_t block_to_free,
+ unsigned long count, __le32 *first,
+ __le32 *last)
+{
+ __le32 *p;
+ int flags = EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_VALIDATED;
+ int err;
+
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ flags |= EXT4_FREE_BLOCKS_METADATA;
+
+ if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
+ count)) {
+ EXT4_ERROR_INODE(inode, "attempt to clear invalid "
+ "blocks %llu len %lu",
+ (unsigned long long) block_to_free, count);
+ return 1;
+ }
+
+ if (try_to_extend_transaction(handle, inode)) {
+ if (bh) {
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
+ if (unlikely(err))
+ goto out_err;
+ }
+ err = ext4_mark_inode_dirty(handle, inode);
+ if (unlikely(err))
+ goto out_err;
+ err = ext4_truncate_restart_trans(handle, inode,
+ ext4_blocks_for_truncate(inode));
+ if (unlikely(err))
+ goto out_err;
+ if (bh) {
+ BUFFER_TRACE(bh, "retaking write access");
+ err = ext4_journal_get_write_access(handle, bh);
+ if (unlikely(err))
+ goto out_err;
+ }
+ }
+
+ for (p = first; p < last; p++)
+ *p = 0;
+
+ ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags);
+ return 0;
+out_err:
+ ext4_std_error(inode->i_sb, err);
+ return err;
+}
+
+/**
+ * ext4_free_data - free a list of data blocks
+ * @handle: handle for this transaction
+ * @inode: inode we are dealing with
+ * @this_bh: indirect buffer_head which contains *@first and *@last
+ * @first: array of block numbers
+ * @last: points immediately past the end of array
+ *
+ * We are freeing all blocks referred from that array (numbers are stored as
+ * little-endian 32-bit) and updating @inode->i_blocks appropriately.
+ *
+ * We accumulate contiguous runs of blocks to free. Conveniently, if these
+ * blocks are contiguous then releasing them at one time will only affect one
+ * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't
+ * actually use a lot of journal space.
+ *
+ * @this_bh will be %NULL if @first and @last point into the inode's direct
+ * block pointers.
+ */
+static void ext4_free_data(handle_t *handle, struct inode *inode,
+ struct buffer_head *this_bh,
+ __le32 *first, __le32 *last)
+{
+ ext4_fsblk_t block_to_free = 0; /* Starting block # of a run */
+ unsigned long count = 0; /* Number of blocks in the run */
+ __le32 *block_to_free_p = NULL; /* Pointer into inode/ind
+ corresponding to
+ block_to_free */
+ ext4_fsblk_t nr; /* Current block # */
+ __le32 *p; /* Pointer into inode/ind
+ for current block */
+ int err = 0;
+
+ if (this_bh) { /* For indirect block */
+ BUFFER_TRACE(this_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, this_bh);
+ /* Important: if we can't update the indirect pointers
+ * to the blocks, we can't free them. */
+ if (err)
+ return;
+ }
+
+ for (p = first; p < last; p++) {
+ nr = le32_to_cpu(*p);
+ if (nr) {
+ /* accumulate blocks to free if they're contiguous */
+ if (count == 0) {
+ block_to_free = nr;
+ block_to_free_p = p;
+ count = 1;
+ } else if (nr == block_to_free + count) {
+ count++;
+ } else {
+ err = ext4_clear_blocks(handle, inode, this_bh,
+ block_to_free, count,
+ block_to_free_p, p);
+ if (err)
+ break;
+ block_to_free = nr;
+ block_to_free_p = p;
+ count = 1;
+ }
+ }
+ }
+
+ if (!err && count > 0)
+ err = ext4_clear_blocks(handle, inode, this_bh, block_to_free,
+ count, block_to_free_p, p);
+ if (err < 0)
+ /* fatal error */
+ return;
+
+ if (this_bh) {
+ BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata");
+
+ /*
+ * The buffer head should have an attached journal head at this
+ * point. However, if the data is corrupted and an indirect
+ * block pointed to itself, it would have been detached when
+ * the block was cleared. Check for this instead of OOPSing.
+ */
+ if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh))
+ ext4_handle_dirty_metadata(handle, inode, this_bh);
+ else
+ EXT4_ERROR_INODE(inode,
+ "circular indirect block detected at "
+ "block %llu",
+ (unsigned long long) this_bh->b_blocknr);
+ }
+}
+
+/**
+ * ext4_free_branches - free an array of branches
+ * @handle: JBD handle for this transaction
+ * @inode: inode we are dealing with
+ * @parent_bh: the buffer_head which contains *@first and *@last
+ * @first: array of block numbers
+ * @last: pointer immediately past the end of array
+ * @depth: depth of the branches to free
+ *
+ * We are freeing all blocks referred from these branches (numbers are
+ * stored as little-endian 32-bit) and updating @inode->i_blocks
+ * appropriately.
+ */
+static void ext4_free_branches(handle_t *handle, struct inode *inode,
+ struct buffer_head *parent_bh,
+ __le32 *first, __le32 *last, int depth)
+{
+ ext4_fsblk_t nr;
+ __le32 *p;
+
+ if (ext4_handle_is_aborted(handle))
+ return;
+
+ if (depth--) {
+ struct buffer_head *bh;
+ int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+ p = last;
+ while (--p >= first) {
+ nr = le32_to_cpu(*p);
+ if (!nr)
+ continue; /* A hole */
+
+ if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
+ nr, 1)) {
+ EXT4_ERROR_INODE(inode,
+ "invalid indirect mapped "
+ "block %lu (level %d)",
+ (unsigned long) nr, depth);
+ break;
+ }
+
+ /* Go read the buffer for the next level down */
+ bh = sb_bread(inode->i_sb, nr);
+
+ /*
+ * A read failure? Report error and clear slot
+ * (should be rare).
+ */
+ if (!bh) {
+ EXT4_ERROR_INODE_BLOCK(inode, nr,
+ "Read failure");
+ continue;
+ }
+
+ /* This zaps the entire block. Bottom up. */
+ BUFFER_TRACE(bh, "free child branches");
+ ext4_free_branches(handle, inode, bh,
+ (__le32 *) bh->b_data,
+ (__le32 *) bh->b_data + addr_per_block,
+ depth);
+ brelse(bh);
+
+ /*
+ * Everything below this this pointer has been
+ * released. Now let this top-of-subtree go.
+ *
+ * We want the freeing of this indirect block to be
+ * atomic in the journal with the updating of the
+ * bitmap block which owns it. So make some room in
+ * the journal.
+ *
+ * We zero the parent pointer *after* freeing its
+ * pointee in the bitmaps, so if extend_transaction()
+ * for some reason fails to put the bitmap changes and
+ * the release into the same transaction, recovery
+ * will merely complain about releasing a free block,
+ * rather than leaking blocks.
+ */
+ if (ext4_handle_is_aborted(handle))
+ return;
+ if (try_to_extend_transaction(handle, inode)) {
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_truncate_restart_trans(handle, inode,
+ ext4_blocks_for_truncate(inode));
+ }
+
+ /*
+ * The forget flag here is critical because if
+ * we are journaling (and not doing data
+ * journaling), we have to make sure a revoke
+ * record is written to prevent the journal
+ * replay from overwriting the (former)
+ * indirect block if it gets reallocated as a
+ * data block. This must happen in the same
+ * transaction where the data blocks are
+ * actually freed.
+ */
+ ext4_free_blocks(handle, inode, NULL, nr, 1,
+ EXT4_FREE_BLOCKS_METADATA|
+ EXT4_FREE_BLOCKS_FORGET);
+
+ if (parent_bh) {
+ /*
+ * The block which we have just freed is
+ * pointed to by an indirect block: journal it
+ */
+ BUFFER_TRACE(parent_bh, "get_write_access");
+ if (!ext4_journal_get_write_access(handle,
+ parent_bh)){
+ *p = 0;
+ BUFFER_TRACE(parent_bh,
+ "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle,
+ inode,
+ parent_bh);
+ }
+ }
+ }
+ } else {
+ /* We have reached the bottom of the tree. */
+ BUFFER_TRACE(parent_bh, "free data blocks");
+ ext4_free_data(handle, inode, parent_bh, first, last);
+ }
+}
+
+void ext4_ind_truncate(struct inode *inode)
+{
+ handle_t *handle;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ __le32 *i_data = ei->i_data;
+ int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+ struct address_space *mapping = inode->i_mapping;
+ ext4_lblk_t offsets[4];
+ Indirect chain[4];
+ Indirect *partial;
+ __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))
+ return; /* AKPM: return what? */
+
+ last_block = (inode->i_size + blocksize-1)
+ >> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
+ max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
+ >> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
+
+ 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);
+ if (n == 0)
+ goto out_stop; /* error */
+ }
+
+ /*
+ * OK. This truncate is going to happen. We add the inode to the
+ * orphan list, so that if this truncate spans multiple transactions,
+ * and we crash, we will resume the truncate when the filesystem
+ * recovers. It also marks the inode dirty, to catch the new size.
+ *
+ * Implication: the file must always be in a sane, consistent
+ * truncatable state while each transaction commits.
+ */
+ if (ext4_orphan_add(handle, inode))
+ goto out_stop;
+
+ /*
+ * From here we block out all ext4_get_block() callers who want to
+ * modify the block allocation tree.
+ */
+ down_write(&ei->i_data_sem);
+
+ ext4_discard_preallocations(inode);
+
+ /*
+ * The orphan list entry will now protect us from any crash which
+ * occurs before the truncate completes, so it is now safe to propagate
+ * the new, shorter inode size (held for now in i_size) into the
+ * on-disk inode. We do this via i_disksize, which is the value which
+ * ext4 *really* writes onto the disk inode.
+ */
+ ei->i_disksize = inode->i_size;
+
+ if (last_block == max_block) {
+ /*
+ * It is unnecessary to free any data blocks if last_block is
+ * equal to the indirect block limit.
+ */
+ goto out_unlock;
+ } else if (n == 1) { /* direct blocks */
+ ext4_free_data(handle, inode, NULL, i_data+offsets[0],
+ i_data + EXT4_NDIR_BLOCKS);
+ goto do_indirects;
+ }
+
+ partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+ /* Kill the top of shared branch (not detached) */
+ if (nr) {
+ if (partial == chain) {
+ /* Shared branch grows from the inode */
+ ext4_free_branches(handle, inode, NULL,
+ &nr, &nr+1, (chain+n-1) - partial);
+ *partial->p = 0;
+ /*
+ * We mark the inode dirty prior to restart,
+ * and prior to stop. No need for it here.
+ */
+ } else {
+ /* Shared branch grows from an indirect block */
+ BUFFER_TRACE(partial->bh, "get_write_access");
+ ext4_free_branches(handle, inode, partial->bh,
+ partial->p,
+ partial->p+1, (chain+n-1) - partial);
+ }
+ }
+ /* Clear the ends of indirect blocks on the shared branch */
+ while (partial > chain) {
+ ext4_free_branches(handle, inode, partial->bh, partial->p + 1,
+ (__le32*)partial->bh->b_data+addr_per_block,
+ (chain+n-1) - partial);
+ BUFFER_TRACE(partial->bh, "call brelse");
+ brelse(partial->bh);
+ partial--;
+ }
+do_indirects:
+ /* Kill the remaining (whole) subtrees */
+ switch (offsets[0]) {
+ default:
+ nr = i_data[EXT4_IND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
+ i_data[EXT4_IND_BLOCK] = 0;
+ }
+ case EXT4_IND_BLOCK:
+ nr = i_data[EXT4_DIND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
+ i_data[EXT4_DIND_BLOCK] = 0;
+ }
+ case EXT4_DIND_BLOCK:
+ nr = i_data[EXT4_TIND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
+ i_data[EXT4_TIND_BLOCK] = 0;
+ }
+ case EXT4_TIND_BLOCK:
+ ;
+ }
+
+out_unlock:
+ up_write(&ei->i_data_sem);
+ inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+ ext4_mark_inode_dirty(handle, inode);
+
+ /*
+ * In a multi-transaction truncate, we only make the final transaction
+ * synchronous
+ */
+ if (IS_SYNC(inode))
+ ext4_handle_sync(handle);
+out_stop:
+ /*
+ * If this was a simple ftruncate(), and the file will remain alive
+ * then we need to clear up the orphan record which we created above.
+ * However, if this was a real unlink then we were called by
+ * ext4_delete_inode(), and we allow that function to clean up the
+ * orphan info for us.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(handle, inode);
+
+ ext4_journal_stop(handle);
+ trace_ext4_truncate_exit(inode);
+}
+
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 678cde834f19..240f6e2dc7ee 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -12,10 +12,6 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
- * Goal-directed block allocation by Stephen Tweedie
- * ([email protected]), 1993, 1998
- * Big-endian to little-endian byte-swapping/bitmaps by
- * David S. Miller ([email protected]), 1995
* 64-bit file support on 64-bit platforms by Jakub Jelinek
* ([email protected])
*
@@ -46,7 +42,7 @@
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
-#include "ext4_extents.h"
+#include "truncate.h"
#include <trace/events/ext4.h>
@@ -89,72 +85,6 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
}
/*
- * Work out how many blocks we need to proceed with the next chunk of a
- * truncate transaction.
- */
-static unsigned long blocks_for_truncate(struct inode *inode)
-{
- ext4_lblk_t needed;
-
- needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9);
-
- /* Give ourselves just enough room to cope with inodes in which
- * i_blocks is corrupt: we've seen disk corruptions in the past
- * which resulted in random data in an inode which looked enough
- * like a regular file for ext4 to try to delete it. Things
- * will go a bit crazy if that happens, but at least we should
- * try not to panic the whole kernel. */
- if (needed < 2)
- needed = 2;
-
- /* But we need to bound the transaction so we don't overflow the
- * journal. */
- if (needed > EXT4_MAX_TRANS_DATA)
- needed = EXT4_MAX_TRANS_DATA;
-
- return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed;
-}
-
-/*
- * Truncate transactions can be complex and absolutely huge. So we need to
- * be able to restart the transaction at a conventient checkpoint to make
- * sure we don't overflow the journal.
- *
- * start_transaction gets us a new handle for a truncate transaction,
- * and extend_transaction tries to extend the existing one a bit. If
- * extend fails, we need to propagate the failure up and restart the
- * transaction in the top-level truncate loop. --sct
- */
-static handle_t *start_transaction(struct inode *inode)
-{
- handle_t *result;
-
- result = ext4_journal_start(inode, blocks_for_truncate(inode));
- if (!IS_ERR(result))
- return result;
-
- ext4_std_error(inode->i_sb, PTR_ERR(result));
- return result;
-}
-
-/*
- * Try to extend this transaction for the purposes of truncation.
- *
- * Returns 0 if we managed to create more room. If we can't create more
- * room, and the transaction must be restarted we return 1.
- */
-static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
-{
- if (!ext4_handle_valid(handle))
- return 0;
- if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
- return 0;
- if (!ext4_journal_extend(handle, blocks_for_truncate(inode)))
- return 0;
- return 1;
-}
-
-/*
* Restart the transaction associated with *handle. This does a commit,
* so before we call here everything must be consistently dirtied against
* this transaction.
@@ -189,7 +119,37 @@ void ext4_evict_inode(struct inode *inode)
int err;
trace_ext4_evict_inode(inode);
+
+ ext4_ioend_wait(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 (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_log_start_commit(journal, commit_tid);
+ jbd2_log_wait_commit(journal, commit_tid);
+ filemap_write_and_wait(&inode->i_data);
+ }
truncate_inode_pages(&inode->i_data, 0);
goto no_delete;
}
@@ -204,7 +164,7 @@ void ext4_evict_inode(struct inode *inode)
if (is_bad_inode(inode))
goto no_delete;
- handle = ext4_journal_start(inode, blocks_for_truncate(inode)+3);
+ handle = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)+3);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
@@ -277,793 +237,6 @@ no_delete:
ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
}
-typedef struct {
- __le32 *p;
- __le32 key;
- struct buffer_head *bh;
-} Indirect;
-
-static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
-{
- p->key = *(p->p = v);
- p->bh = bh;
-}
-
-/**
- * ext4_block_to_path - parse the block number into array of offsets
- * @inode: inode in question (we are only interested in its superblock)
- * @i_block: block number to be parsed
- * @offsets: array to store the offsets in
- * @boundary: set this non-zero if the referred-to block is likely to be
- * followed (on disk) by an indirect block.
- *
- * To store the locations of file's data ext4 uses a data structure common
- * for UNIX filesystems - tree of pointers anchored in the inode, with
- * data blocks at leaves and indirect blocks in intermediate nodes.
- * This function translates the block number into path in that tree -
- * return value is the path length and @offsets[n] is the offset of
- * pointer to (n+1)th node in the nth one. If @block is out of range
- * (negative or too large) warning is printed and zero returned.
- *
- * Note: function doesn't find node addresses, so no IO is needed. All
- * we need to know is the capacity of indirect blocks (taken from the
- * inode->i_sb).
- */
-
-/*
- * Portability note: the last comparison (check that we fit into triple
- * indirect block) is spelled differently, because otherwise on an
- * architecture with 32-bit longs and 8Kb pages we might get into trouble
- * if our filesystem had 8Kb blocks. We might use long long, but that would
- * kill us on x86. Oh, well, at least the sign propagation does not matter -
- * i_block would have to be negative in the very beginning, so we would not
- * get there at all.
- */
-
-static int ext4_block_to_path(struct inode *inode,
- ext4_lblk_t i_block,
- ext4_lblk_t offsets[4], int *boundary)
-{
- int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb);
- const long direct_blocks = EXT4_NDIR_BLOCKS,
- indirect_blocks = ptrs,
- double_blocks = (1 << (ptrs_bits * 2));
- int n = 0;
- int final = 0;
-
- if (i_block < direct_blocks) {
- offsets[n++] = i_block;
- final = direct_blocks;
- } else if ((i_block -= direct_blocks) < indirect_blocks) {
- offsets[n++] = EXT4_IND_BLOCK;
- offsets[n++] = i_block;
- final = ptrs;
- } else if ((i_block -= indirect_blocks) < double_blocks) {
- offsets[n++] = EXT4_DIND_BLOCK;
- offsets[n++] = i_block >> ptrs_bits;
- offsets[n++] = i_block & (ptrs - 1);
- final = ptrs;
- } else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) {
- offsets[n++] = EXT4_TIND_BLOCK;
- offsets[n++] = i_block >> (ptrs_bits * 2);
- offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1);
- offsets[n++] = i_block & (ptrs - 1);
- final = ptrs;
- } else {
- ext4_warning(inode->i_sb, "block %lu > max in inode %lu",
- i_block + direct_blocks +
- indirect_blocks + double_blocks, inode->i_ino);
- }
- if (boundary)
- *boundary = final - 1 - (i_block & (ptrs - 1));
- return n;
-}
-
-static int __ext4_check_blockref(const char *function, unsigned int line,
- struct inode *inode,
- __le32 *p, unsigned int max)
-{
- struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
- __le32 *bref = p;
- unsigned int blk;
-
- while (bref < p+max) {
- blk = le32_to_cpu(*bref++);
- if (blk &&
- unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
- blk, 1))) {
- es->s_last_error_block = cpu_to_le64(blk);
- ext4_error_inode(inode, function, line, blk,
- "invalid block");
- return -EIO;
- }
- }
- return 0;
-}
-
-
-#define ext4_check_indirect_blockref(inode, bh) \
- __ext4_check_blockref(__func__, __LINE__, inode, \
- (__le32 *)(bh)->b_data, \
- EXT4_ADDR_PER_BLOCK((inode)->i_sb))
-
-#define ext4_check_inode_blockref(inode) \
- __ext4_check_blockref(__func__, __LINE__, inode, \
- EXT4_I(inode)->i_data, \
- EXT4_NDIR_BLOCKS)
-
-/**
- * ext4_get_branch - read the chain of indirect blocks leading to data
- * @inode: inode in question
- * @depth: depth of the chain (1 - direct pointer, etc.)
- * @offsets: offsets of pointers in inode/indirect blocks
- * @chain: place to store the result
- * @err: here we store the error value
- *
- * Function fills the array of triples <key, p, bh> and returns %NULL
- * if everything went OK or the pointer to the last filled triple
- * (incomplete one) otherwise. Upon the return chain[i].key contains
- * the number of (i+1)-th block in the chain (as it is stored in memory,
- * i.e. little-endian 32-bit), chain[i].p contains the address of that
- * number (it points into struct inode for i==0 and into the bh->b_data
- * for i>0) and chain[i].bh points to the buffer_head of i-th indirect
- * block for i>0 and NULL for i==0. In other words, it holds the block
- * numbers of the chain, addresses they were taken from (and where we can
- * verify that chain did not change) and buffer_heads hosting these
- * numbers.
- *
- * Function stops when it stumbles upon zero pointer (absent block)
- * (pointer to last triple returned, *@err == 0)
- * or when it gets an IO error reading an indirect block
- * (ditto, *@err == -EIO)
- * or when it reads all @depth-1 indirect blocks successfully and finds
- * the whole chain, all way to the data (returns %NULL, *err == 0).
- *
- * Need to be called with
- * down_read(&EXT4_I(inode)->i_data_sem)
- */
-static Indirect *ext4_get_branch(struct inode *inode, int depth,
- ext4_lblk_t *offsets,
- Indirect chain[4], int *err)
-{
- struct super_block *sb = inode->i_sb;
- Indirect *p = chain;
- struct buffer_head *bh;
-
- *err = 0;
- /* i_data is not going away, no lock needed */
- add_chain(chain, NULL, EXT4_I(inode)->i_data + *offsets);
- if (!p->key)
- goto no_block;
- while (--depth) {
- bh = sb_getblk(sb, le32_to_cpu(p->key));
- if (unlikely(!bh))
- goto failure;
-
- if (!bh_uptodate_or_lock(bh)) {
- if (bh_submit_read(bh) < 0) {
- put_bh(bh);
- goto failure;
- }
- /* validate block references */
- if (ext4_check_indirect_blockref(inode, bh)) {
- put_bh(bh);
- goto failure;
- }
- }
-
- add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
- /* Reader: end */
- if (!p->key)
- goto no_block;
- }
- return NULL;
-
-failure:
- *err = -EIO;
-no_block:
- return p;
-}
-
-/**
- * ext4_find_near - find a place for allocation with sufficient locality
- * @inode: owner
- * @ind: descriptor of indirect block.
- *
- * This function returns the preferred place for block allocation.
- * It is used when heuristic for sequential allocation fails.
- * Rules are:
- * + if there is a block to the left of our position - allocate near it.
- * + if pointer will live in indirect block - allocate near that block.
- * + if pointer will live in inode - allocate in the same
- * cylinder group.
- *
- * In the latter case we colour the starting block by the callers PID to
- * prevent it from clashing with concurrent allocations for a different inode
- * in the same block group. The PID is used here so that functionally related
- * files will be close-by on-disk.
- *
- * Caller must make sure that @ind is valid and will stay that way.
- */
-static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
-{
- struct ext4_inode_info *ei = EXT4_I(inode);
- __le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
- __le32 *p;
- ext4_fsblk_t bg_start;
- ext4_fsblk_t last_block;
- ext4_grpblk_t colour;
- ext4_group_t block_group;
- int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));
-
- /* Try to find previous block */
- for (p = ind->p - 1; p >= start; p--) {
- if (*p)
- return le32_to_cpu(*p);
- }
-
- /* No such thing, so let's try location of indirect block */
- if (ind->bh)
- return ind->bh->b_blocknr;
-
- /*
- * It is going to be referred to from the inode itself? OK, just put it
- * into the same cylinder group then.
- */
- block_group = ei->i_block_group;
- if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
- block_group &= ~(flex_size-1);
- if (S_ISREG(inode->i_mode))
- block_group++;
- }
- bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
- last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
-
- /*
- * If we are doing delayed allocation, we don't need take
- * colour into account.
- */
- if (test_opt(inode->i_sb, DELALLOC))
- return bg_start;
-
- if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
- colour = (current->pid % 16) *
- (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
- else
- colour = (current->pid % 16) * ((last_block - bg_start) / 16);
- return bg_start + colour;
-}
-
-/**
- * ext4_find_goal - find a preferred place for allocation.
- * @inode: owner
- * @block: block we want
- * @partial: pointer to the last triple within a chain
- *
- * Normally this function find the preferred place for block allocation,
- * returns it.
- * Because this is only used for non-extent files, we limit the block nr
- * to 32 bits.
- */
-static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
- Indirect *partial)
-{
- ext4_fsblk_t goal;
-
- /*
- * XXX need to get goal block from mballoc's data structures
- */
-
- goal = ext4_find_near(inode, partial);
- goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
- return goal;
-}
-
-/**
- * ext4_blks_to_allocate - Look up the block map and count the number
- * of direct blocks need to be allocated for the given branch.
- *
- * @branch: chain of indirect blocks
- * @k: number of blocks need for indirect blocks
- * @blks: number of data blocks to be mapped.
- * @blocks_to_boundary: the offset in the indirect block
- *
- * return the total number of blocks to be allocate, including the
- * direct and indirect blocks.
- */
-static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
- int blocks_to_boundary)
-{
- unsigned int count = 0;
-
- /*
- * Simple case, [t,d]Indirect block(s) has not allocated yet
- * then it's clear blocks on that path have not allocated
- */
- if (k > 0) {
- /* right now we don't handle cross boundary allocation */
- if (blks < blocks_to_boundary + 1)
- count += blks;
- else
- count += blocks_to_boundary + 1;
- return count;
- }
-
- count++;
- while (count < blks && count <= blocks_to_boundary &&
- le32_to_cpu(*(branch[0].p + count)) == 0) {
- count++;
- }
- return count;
-}
-
-/**
- * ext4_alloc_blocks: multiple allocate blocks needed for a branch
- * @handle: handle for this transaction
- * @inode: inode which needs allocated blocks
- * @iblock: the logical block to start allocated at
- * @goal: preferred physical block of allocation
- * @indirect_blks: the number of blocks need to allocate for indirect
- * blocks
- * @blks: number of desired blocks
- * @new_blocks: on return it will store the new block numbers for
- * the indirect blocks(if needed) and the first direct block,
- * @err: on return it will store the error code
- *
- * This function will return the number of blocks allocated as
- * requested by the passed-in parameters.
- */
-static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, ext4_fsblk_t goal,
- int indirect_blks, int blks,
- ext4_fsblk_t new_blocks[4], int *err)
-{
- struct ext4_allocation_request ar;
- int target, i;
- unsigned long count = 0, blk_allocated = 0;
- int index = 0;
- ext4_fsblk_t current_block = 0;
- int ret = 0;
-
- /*
- * Here we try to allocate the requested multiple blocks at once,
- * on a best-effort basis.
- * To build a branch, we should allocate blocks for
- * the indirect blocks(if not allocated yet), and at least
- * the first direct block of this branch. That's the
- * minimum number of blocks need to allocate(required)
- */
- /* first we try to allocate the indirect blocks */
- target = indirect_blks;
- while (target > 0) {
- count = target;
- /* allocating blocks for indirect blocks and direct blocks */
- current_block = ext4_new_meta_blocks(handle, inode, goal,
- 0, &count, err);
- if (*err)
- goto failed_out;
-
- if (unlikely(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS)) {
- EXT4_ERROR_INODE(inode,
- "current_block %llu + count %lu > %d!",
- current_block, count,
- EXT4_MAX_BLOCK_FILE_PHYS);
- *err = -EIO;
- goto failed_out;
- }
-
- target -= count;
- /* allocate blocks for indirect blocks */
- while (index < indirect_blks && count) {
- new_blocks[index++] = current_block++;
- count--;
- }
- if (count > 0) {
- /*
- * save the new block number
- * for the first direct block
- */
- new_blocks[index] = current_block;
- printk(KERN_INFO "%s returned more blocks than "
- "requested\n", __func__);
- WARN_ON(1);
- break;
- }
- }
-
- target = blks - count ;
- blk_allocated = count;
- if (!target)
- goto allocated;
- /* Now allocate data blocks */
- memset(&ar, 0, sizeof(ar));
- ar.inode = inode;
- ar.goal = goal;
- ar.len = target;
- ar.logical = iblock;
- if (S_ISREG(inode->i_mode))
- /* enable in-core preallocation only for regular files */
- ar.flags = EXT4_MB_HINT_DATA;
-
- current_block = ext4_mb_new_blocks(handle, &ar, err);
- if (unlikely(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS)) {
- EXT4_ERROR_INODE(inode,
- "current_block %llu + ar.len %d > %d!",
- current_block, ar.len,
- EXT4_MAX_BLOCK_FILE_PHYS);
- *err = -EIO;
- goto failed_out;
- }
-
- if (*err && (target == blks)) {
- /*
- * if the allocation failed and we didn't allocate
- * any blocks before
- */
- goto failed_out;
- }
- if (!*err) {
- if (target == blks) {
- /*
- * save the new block number
- * for the first direct block
- */
- new_blocks[index] = current_block;
- }
- blk_allocated += ar.len;
- }
-allocated:
- /* total number of blocks allocated for direct blocks */
- ret = blk_allocated;
- *err = 0;
- return ret;
-failed_out:
- for (i = 0; i < index; i++)
- ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
- return ret;
-}
-
-/**
- * ext4_alloc_branch - allocate and set up a chain of blocks.
- * @handle: handle for this transaction
- * @inode: owner
- * @indirect_blks: number of allocated indirect blocks
- * @blks: number of allocated direct blocks
- * @goal: preferred place for allocation
- * @offsets: offsets (in the blocks) to store the pointers to next.
- * @branch: place to store the chain in.
- *
- * This function allocates blocks, zeroes out all but the last one,
- * links them into chain and (if we are synchronous) writes them to disk.
- * In other words, it prepares a branch that can be spliced onto the
- * inode. It stores the information about that chain in the branch[], in
- * the same format as ext4_get_branch() would do. We are calling it after
- * we had read the existing part of chain and partial points to the last
- * triple of that (one with zero ->key). Upon the exit we have the same
- * picture as after the successful ext4_get_block(), except that in one
- * place chain is disconnected - *branch->p is still zero (we did not
- * set the last link), but branch->key contains the number that should
- * be placed into *branch->p to fill that gap.
- *
- * If allocation fails we free all blocks we've allocated (and forget
- * their buffer_heads) and return the error value the from failed
- * ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain
- * as described above and return 0.
- */
-static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, int indirect_blks,
- int *blks, ext4_fsblk_t goal,
- ext4_lblk_t *offsets, Indirect *branch)
-{
- int blocksize = inode->i_sb->s_blocksize;
- int i, n = 0;
- int err = 0;
- struct buffer_head *bh;
- int num;
- ext4_fsblk_t new_blocks[4];
- ext4_fsblk_t current_block;
-
- num = ext4_alloc_blocks(handle, inode, iblock, goal, indirect_blks,
- *blks, new_blocks, &err);
- if (err)
- return err;
-
- branch[0].key = cpu_to_le32(new_blocks[0]);
- /*
- * metadata blocks and data blocks are allocated.
- */
- for (n = 1; n <= indirect_blks; n++) {
- /*
- * Get buffer_head for parent block, zero it out
- * and set the pointer to new one, then send
- * parent to disk.
- */
- bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
- if (unlikely(!bh)) {
- err = -EIO;
- goto failed;
- }
-
- branch[n].bh = bh;
- lock_buffer(bh);
- BUFFER_TRACE(bh, "call get_create_access");
- err = ext4_journal_get_create_access(handle, bh);
- if (err) {
- /* Don't brelse(bh) here; it's done in
- * ext4_journal_forget() below */
- unlock_buffer(bh);
- goto failed;
- }
-
- memset(bh->b_data, 0, blocksize);
- branch[n].p = (__le32 *) bh->b_data + offsets[n];
- branch[n].key = cpu_to_le32(new_blocks[n]);
- *branch[n].p = branch[n].key;
- if (n == indirect_blks) {
- current_block = new_blocks[n];
- /*
- * End of chain, update the last new metablock of
- * the chain to point to the new allocated
- * data blocks numbers
- */
- for (i = 1; i < num; i++)
- *(branch[n].p + i) = cpu_to_le32(++current_block);
- }
- BUFFER_TRACE(bh, "marking uptodate");
- set_buffer_uptodate(bh);
- unlock_buffer(bh);
-
- BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, inode, bh);
- if (err)
- goto failed;
- }
- *blks = num;
- return err;
-failed:
- /* Allocation failed, free what we already allocated */
- ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0);
- for (i = 1; i <= n ; i++) {
- /*
- * branch[i].bh is newly allocated, so there is no
- * need to revoke the block, which is why we don't
- * need to set EXT4_FREE_BLOCKS_METADATA.
- */
- ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1,
- EXT4_FREE_BLOCKS_FORGET);
- }
- for (i = n+1; i < indirect_blks; i++)
- ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
-
- ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0);
-
- return err;
-}
-
-/**
- * ext4_splice_branch - splice the allocated branch onto inode.
- * @handle: handle for this transaction
- * @inode: owner
- * @block: (logical) number of block we are adding
- * @chain: chain of indirect blocks (with a missing link - see
- * ext4_alloc_branch)
- * @where: location of missing link
- * @num: number of indirect blocks we are adding
- * @blks: number of direct blocks we are adding
- *
- * This function fills the missing link and does all housekeeping needed in
- * inode (->i_blocks, etc.). In case of success we end up with the full
- * chain to new block and return 0.
- */
-static int ext4_splice_branch(handle_t *handle, struct inode *inode,
- ext4_lblk_t block, Indirect *where, int num,
- int blks)
-{
- int i;
- int err = 0;
- ext4_fsblk_t current_block;
-
- /*
- * If we're splicing into a [td]indirect block (as opposed to the
- * inode) then we need to get write access to the [td]indirect block
- * before the splice.
- */
- if (where->bh) {
- BUFFER_TRACE(where->bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, where->bh);
- if (err)
- goto err_out;
- }
- /* That's it */
-
- *where->p = where->key;
-
- /*
- * Update the host buffer_head or inode to point to more just allocated
- * direct blocks blocks
- */
- if (num == 0 && blks > 1) {
- current_block = le32_to_cpu(where->key) + 1;
- for (i = 1; i < blks; i++)
- *(where->p + i) = cpu_to_le32(current_block++);
- }
-
- /* We are done with atomic stuff, now do the rest of housekeeping */
- /* had we spliced it onto indirect block? */
- if (where->bh) {
- /*
- * If we spliced it onto an indirect block, we haven't
- * altered the inode. Note however that if it is being spliced
- * onto an indirect block at the very end of the file (the
- * file is growing) then we *will* alter the inode to reflect
- * the new i_size. But that is not done here - it is done in
- * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode.
- */
- jbd_debug(5, "splicing indirect only\n");
- BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, inode, where->bh);
- if (err)
- goto err_out;
- } else {
- /*
- * OK, we spliced it into the inode itself on a direct block.
- */
- ext4_mark_inode_dirty(handle, inode);
- jbd_debug(5, "splicing direct\n");
- }
- return err;
-
-err_out:
- for (i = 1; i <= num; i++) {
- /*
- * branch[i].bh is newly allocated, so there is no
- * need to revoke the block, which is why we don't
- * need to set EXT4_FREE_BLOCKS_METADATA.
- */
- ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
- EXT4_FREE_BLOCKS_FORGET);
- }
- ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key),
- blks, 0);
-
- return err;
-}
-
-/*
- * The ext4_ind_map_blocks() function handles non-extents inodes
- * (i.e., using the traditional indirect/double-indirect i_blocks
- * scheme) for ext4_map_blocks().
- *
- * Allocation strategy is simple: if we have to allocate something, we will
- * have to go the whole way to leaf. So let's do it before attaching anything
- * to tree, set linkage between the newborn blocks, write them if sync is
- * required, recheck the path, free and repeat if check fails, otherwise
- * set the last missing link (that will protect us from any truncate-generated
- * removals - all blocks on the path are immune now) and possibly force the
- * write on the parent block.
- * That has a nice additional property: no special recovery from the failed
- * allocations is needed - we simply release blocks and do not touch anything
- * reachable from inode.
- *
- * `handle' can be NULL if create == 0.
- *
- * return > 0, # of blocks mapped or allocated.
- * return = 0, if plain lookup failed.
- * return < 0, error case.
- *
- * The ext4_ind_get_blocks() function should be called with
- * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem
- * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or
- * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system
- * blocks.
- */
-static int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
- struct ext4_map_blocks *map,
- int flags)
-{
- int err = -EIO;
- ext4_lblk_t offsets[4];
- Indirect chain[4];
- Indirect *partial;
- ext4_fsblk_t goal;
- int indirect_blks;
- int blocks_to_boundary = 0;
- int depth;
- int count = 0;
- ext4_fsblk_t first_block = 0;
-
- trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
- J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
- J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
- depth = ext4_block_to_path(inode, map->m_lblk, offsets,
- &blocks_to_boundary);
-
- if (depth == 0)
- goto out;
-
- partial = ext4_get_branch(inode, depth, offsets, chain, &err);
-
- /* Simplest case - block found, no allocation needed */
- if (!partial) {
- first_block = le32_to_cpu(chain[depth - 1].key);
- count++;
- /*map more blocks*/
- while (count < map->m_len && count <= blocks_to_boundary) {
- ext4_fsblk_t blk;
-
- blk = le32_to_cpu(*(chain[depth-1].p + count));
-
- if (blk == first_block + count)
- count++;
- else
- break;
- }
- goto got_it;
- }
-
- /* Next simple case - plain lookup or failed read of indirect block */
- if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO)
- goto cleanup;
-
- /*
- * Okay, we need to do block allocation.
- */
- goal = ext4_find_goal(inode, map->m_lblk, partial);
-
- /* the number of blocks need to allocate for [d,t]indirect blocks */
- indirect_blks = (chain + depth) - partial - 1;
-
- /*
- * Next look up the indirect map to count the totoal number of
- * direct blocks to allocate for this branch.
- */
- count = ext4_blks_to_allocate(partial, indirect_blks,
- map->m_len, blocks_to_boundary);
- /*
- * Block out ext4_truncate while we alter the tree
- */
- err = ext4_alloc_branch(handle, inode, map->m_lblk, indirect_blks,
- &count, goal,
- offsets + (partial - chain), partial);
-
- /*
- * The ext4_splice_branch call will free and forget any buffers
- * on the new chain if there is a failure, but that risks using
- * up transaction credits, especially for bitmaps where the
- * credits cannot be returned. Can we handle this somehow? We
- * may need to return -EAGAIN upwards in the worst case. --sct
- */
- if (!err)
- err = ext4_splice_branch(handle, inode, map->m_lblk,
- partial, indirect_blks, count);
- if (err)
- goto cleanup;
-
- map->m_flags |= EXT4_MAP_NEW;
-
- ext4_update_inode_fsync_trans(handle, inode, 1);
-got_it:
- map->m_flags |= EXT4_MAP_MAPPED;
- map->m_pblk = le32_to_cpu(chain[depth-1].key);
- map->m_len = count;
- if (count > blocks_to_boundary)
- map->m_flags |= EXT4_MAP_BOUNDARY;
- err = count;
- /* Clean up and exit */
- partial = chain + depth - 1; /* the whole chain */
-cleanup:
- while (partial > chain) {
- BUFFER_TRACE(partial->bh, "call brelse");
- brelse(partial->bh);
- partial--;
- }
-out:
- trace_ext4_ind_map_blocks_exit(inode, map->m_lblk,
- map->m_pblk, map->m_len, err);
- return err;
-}
-
#ifdef CONFIG_QUOTA
qsize_t *ext4_get_reserved_space(struct inode *inode)
{
@@ -1073,33 +246,6 @@ qsize_t *ext4_get_reserved_space(struct inode *inode)
/*
* Calculate the number of metadata blocks need to reserve
- * to allocate a new block at @lblocks for non extent file based file
- */
-static int ext4_indirect_calc_metadata_amount(struct inode *inode,
- sector_t lblock)
-{
- struct ext4_inode_info *ei = EXT4_I(inode);
- sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1);
- int blk_bits;
-
- if (lblock < EXT4_NDIR_BLOCKS)
- return 0;
-
- lblock -= EXT4_NDIR_BLOCKS;
-
- if (ei->i_da_metadata_calc_len &&
- (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) {
- ei->i_da_metadata_calc_len++;
- return 0;
- }
- ei->i_da_metadata_calc_last_lblock = lblock & dind_mask;
- ei->i_da_metadata_calc_len = 1;
- blk_bits = order_base_2(lblock);
- return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
-}
-
-/*
- * Calculate the number of metadata blocks need to reserve
* to allocate a block located at @lblock
*/
static int ext4_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
@@ -1107,7 +253,7 @@ static int ext4_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return ext4_ext_calc_metadata_amount(inode, lblock);
- return ext4_indirect_calc_metadata_amount(inode, lblock);
+ return ext4_ind_calc_metadata_amount(inode, lblock);
}
/*
@@ -1121,7 +267,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
struct ext4_inode_info *ei = EXT4_I(inode);
spin_lock(&ei->i_block_reservation_lock);
- trace_ext4_da_update_reserve_space(inode, used);
+ trace_ext4_da_update_reserve_space(inode, used, quota_claim);
if (unlikely(used > ei->i_reserved_data_blocks)) {
ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
"with only %d reserved data blocks\n",
@@ -1134,7 +280,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
/* Update per-inode reservations */
ei->i_reserved_data_blocks -= used;
ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
used + ei->i_allocated_meta_blocks);
ei->i_allocated_meta_blocks = 0;
@@ -1144,7 +290,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
* only when we have written all of the delayed
* allocation blocks.
*/
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
@@ -1153,14 +299,14 @@ void ext4_da_update_reserve_space(struct inode *inode,
/* Update quota subsystem for data blocks */
if (quota_claim)
- dquot_claim_block(inode, used);
+ 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, used);
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, used));
}
/*
@@ -1252,6 +398,49 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
}
/*
+ * Sets the BH_Da_Mapped bit on the buffer heads corresponding to the given map.
+ */
+static void set_buffers_da_mapped(struct inode *inode,
+ struct ext4_map_blocks *map)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct pagevec pvec;
+ int i, nr_pages;
+ pgoff_t index, end;
+
+ index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ end = (map->m_lblk + map->m_len - 1) >>
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ pagevec_init(&pvec, 0);
+ while (index <= end) {
+ nr_pages = pagevec_lookup(&pvec, mapping, index,
+ min(end - index + 1,
+ (pgoff_t)PAGEVEC_SIZE));
+ if (nr_pages == 0)
+ break;
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+ struct buffer_head *bh, *head;
+
+ if (unlikely(page->mapping != mapping) ||
+ !PageDirty(page))
+ break;
+
+ if (page_has_buffers(page)) {
+ bh = head = page_buffers(page);
+ do {
+ set_buffer_da_mapped(bh);
+ bh = bh->b_this_page;
+ } while (bh != head);
+ }
+ index++;
+ }
+ pagevec_release(&pvec);
+ }
+}
+
+/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
*
@@ -1269,7 +458,7 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
* the buffer head is mapped.
*
* It returns 0 if plain look up failed (blocks have not been allocated), in
- * that casem, buffer head is unmapped
+ * that case, buffer head is unmapped
*
* It returns the error in case of allocation failure.
*/
@@ -1288,9 +477,11 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
*/
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, 0);
+ retval = ext4_ext_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
} else {
- retval = ext4_ind_map_blocks(handle, inode, map, 0);
+ retval = ext4_ind_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
}
up_read((&EXT4_I(inode)->i_data_sem));
@@ -1308,7 +499,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
* Returns if the blocks have already allocated
*
* Note that if blocks have been preallocated
- * ext4_ext_get_block() returns th create = 0
+ * ext4_ext_get_block() returns the create = 0
* with buffer head unmapped.
*/
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
@@ -1370,9 +561,17 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
ext4_da_update_reserve_space(inode, retval, 1);
}
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
+ /* If we have successfully mapped the delayed allocated blocks,
+ * set the BH_Da_Mapped bit on them. Its important to do this
+ * under the protection of i_data_sem.
+ */
+ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
+ set_buffers_da_mapped(inode, map);
+ }
+
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
int ret = check_block_validity(inode, map);
@@ -1500,7 +699,7 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
return bh;
if (buffer_uptodate(bh))
return bh;
- ll_rw_block(READ_META, 1, &bh);
+ ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
@@ -1589,16 +788,6 @@ static int do_journal_get_write_access(handle_t *handle,
return ret;
}
-/*
- * Truncate blocks that were not used by write. We have to truncate the
- * pagecache as well so that corresponding buffers get properly unmapped.
- */
-static void ext4_truncate_failed_write(struct inode *inode)
-{
- truncate_inode_pages(inode->i_mapping, inode->i_size);
- ext4_truncate(inode);
-}
-
static int ext4_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
static int ext4_write_begin(struct file *file, struct address_space *mapping,
@@ -1772,7 +961,11 @@ static int ext4_ordered_write_end(struct file *file,
ext4_orphan_add(handle, inode);
if (ret2 < 0)
ret = ret2;
+ } else {
+ unlock_page(page);
+ page_cache_release(page);
}
+
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
@@ -1849,6 +1042,8 @@ static int ext4_journalled_write_end(struct file *file,
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
+ BUG_ON(!ext4_handle_valid(handle));
+
if (copied < len) {
if (!PageUptodate(page))
copied = 0;
@@ -1863,6 +1058,7 @@ static int ext4_journalled_write_end(struct file *file,
if (new_i_size > inode->i_size)
i_size_write(inode, pos+copied);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
+ EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
if (new_i_size > EXT4_I(inode)->i_disksize) {
ext4_update_i_disksize(inode, new_i_size);
ret2 = ext4_mark_inode_dirty(handle, inode);
@@ -1897,14 +1093,14 @@ static int ext4_journalled_write_end(struct file *file,
}
/*
- * Reserve a single block located at lblock
+ * Reserve a single cluster located at lblock
*/
static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
{
int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
- unsigned long md_needed;
+ unsigned int md_needed;
int ret;
/*
@@ -1914,7 +1110,8 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
*/
repeat:
spin_lock(&ei->i_block_reservation_lock);
- md_needed = ext4_calc_metadata_amount(inode, lblock);
+ md_needed = EXT4_NUM_B2C(sbi,
+ ext4_calc_metadata_amount(inode, lblock));
trace_ext4_da_reserve_space(inode, md_needed);
spin_unlock(&ei->i_block_reservation_lock);
@@ -1923,15 +1120,15 @@ repeat:
* us from metadata over-estimation, though we may go over by
* a small amount in the end. Here we just reserve for data.
*/
- ret = dquot_reserve_block(inode, 1);
+ ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
if (ret)
return ret;
/*
* We do still charge estimated metadata to the sb though;
* we cannot afford to run out of free blocks.
*/
- if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) {
- dquot_release_reservation_block(inode, 1);
+ if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) {
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
@@ -1978,19 +1175,21 @@ static void ext4_da_release_space(struct inode *inode, int to_free)
* We can release all of the reserved metadata blocks
* only when we have written all of the delayed
* allocation blocks.
+ * Note that in case of bigalloc, i_reserved_meta_blocks,
+ * i_reserved_data_blocks, etc. refer to number of clusters.
*/
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
}
/* update fs dirty data blocks counter */
- percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- dquot_release_reservation_block(inode, to_free);
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free));
}
static void ext4_da_page_release_reservation(struct page *page,
@@ -1999,6 +1198,9 @@ static void ext4_da_page_release_reservation(struct page *page,
int to_release = 0;
struct buffer_head *head, *bh;
unsigned int curr_off = 0;
+ struct inode *inode = page->mapping->host;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ int num_clusters;
head = page_buffers(page);
bh = head;
@@ -2008,10 +1210,24 @@ static void ext4_da_page_release_reservation(struct page *page,
if ((offset <= curr_off) && (buffer_delay(bh))) {
to_release++;
clear_buffer_delay(bh);
+ clear_buffer_da_mapped(bh);
}
curr_off = next_off;
} while ((bh = bh->b_this_page) != head);
- ext4_da_release_space(page->mapping->host, to_release);
+
+ /* If we have released all the blocks belonging to a cluster, then we
+ * need to release the reserved space for that cluster. */
+ num_clusters = EXT4_NUM_B2C(sbi, to_release);
+ while (num_clusters > 0) {
+ ext4_fsblk_t lblk;
+ lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) +
+ ((num_clusters - 1) << sbi->s_cluster_bits);
+ if (sbi->s_cluster_ratio == 1 ||
+ !ext4_find_delalloc_cluster(inode, lblk, 1))
+ ext4_da_release_space(inode, 1);
+
+ num_clusters--;
+ }
}
/*
@@ -2113,6 +1329,8 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
clear_buffer_delay(bh);
bh->b_blocknr = pblock;
}
+ if (buffer_da_mapped(bh))
+ clear_buffer_da_mapped(bh);
if (buffer_unwritten(bh) ||
buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
@@ -2148,7 +1366,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
err = ext4_bio_write_page(&io_submit, page,
len, mpd->wbc);
- else
+ else if (buffer_uninit(page_bufs)) {
+ ext4_set_bh_endio(page_bufs, inode);
+ err = block_write_full_page_endio(page,
+ noalloc_get_block_write,
+ mpd->wbc, ext4_end_io_buffer_write);
+ } else
err = block_write_full_page(page,
noalloc_get_block_write, mpd->wbc);
@@ -2201,12 +1424,15 @@ static void ext4_print_free_blocks(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
printk(KERN_CRIT "Total free blocks count %lld\n",
- ext4_count_free_blocks(inode->i_sb));
+ EXT4_C2B(EXT4_SB(inode->i_sb),
+ ext4_count_free_clusters(inode->i_sb)));
printk(KERN_CRIT "Free/Dirty block details\n");
printk(KERN_CRIT "free_blocks=%lld\n",
- (long long) percpu_counter_sum(&sbi->s_freeblocks_counter));
+ (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+ percpu_counter_sum(&sbi->s_freeclusters_counter)));
printk(KERN_CRIT "dirty_blocks=%lld\n",
- (long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+ percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
printk(KERN_CRIT "Block reservation details\n");
printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
EXT4_I(inode)->i_reserved_data_blocks);
@@ -2285,8 +1511,7 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
if (err == -EAGAIN)
goto submit_io;
- if (err == -ENOSPC &&
- ext4_count_free_blocks(sb)) {
+ if (err == -ENOSPC && ext4_count_free_clusters(sb)) {
mpd->retval = err;
goto submit_io;
}
@@ -2326,13 +1551,15 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
for (i = 0; i < map.m_len; i++)
unmap_underlying_metadata(bdev, map.m_pblk + i);
- }
- if (ext4_should_order_data(mpd->inode)) {
- err = ext4_jbd2_file_inode(handle, mpd->inode);
- if (err)
- /* This only happens if the journal is aborted */
- return;
+ if (ext4_should_order_data(mpd->inode)) {
+ err = ext4_jbd2_file_inode(handle, mpd->inode);
+ if (err) {
+ /* Only if the journal is aborted */
+ mpd->retval = err;
+ goto submit_io;
+ }
+ }
}
/*
@@ -2439,6 +1666,66 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
}
/*
+ * This function is grabs code from the very beginning of
+ * ext4_map_blocks, but assumes that the caller is from delayed write
+ * time. This function looks up the requested blocks and sets the
+ * buffer delay bit under the protection of i_data_sem.
+ */
+static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
+ struct ext4_map_blocks *map,
+ struct buffer_head *bh)
+{
+ int retval;
+ sector_t invalid_block = ~((sector_t) 0xffff);
+
+ if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
+ invalid_block = ~0;
+
+ map->m_flags = 0;
+ ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
+ "logical block %lu\n", inode->i_ino, map->m_len,
+ (unsigned long) map->m_lblk);
+ /*
+ * 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(NULL, inode, map, 0);
+ else
+ retval = ext4_ind_map_blocks(NULL, inode, map, 0);
+
+ if (retval == 0) {
+ /*
+ * XXX: __block_prepare_write() unmaps passed block,
+ * is it OK?
+ */
+ /* If the block was allocated from previously allocated cluster,
+ * then we dont need to reserve it again. */
+ if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) {
+ retval = ext4_da_reserve_space(inode, iblock);
+ if (retval)
+ /* not enough space to reserve */
+ goto out_unlock;
+ }
+
+ /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served
+ * and it should not appear on the bh->b_state.
+ */
+ map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
+
+ map_bh(bh, inode->i_sb, invalid_block);
+ set_buffer_new(bh);
+ set_buffer_delay(bh);
+ }
+
+out_unlock:
+ up_read((&EXT4_I(inode)->i_data_sem));
+
+ return retval;
+}
+
+/*
* This is a special get_blocks_t callback which is used by
* ext4_da_write_begin(). It will either return mapped block or
* reserve space for a single block.
@@ -2455,10 +1742,6 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
{
struct ext4_map_blocks map;
int ret = 0;
- sector_t invalid_block = ~((sector_t) 0xffff);
-
- if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
- invalid_block = ~0;
BUG_ON(create == 0);
BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
@@ -2471,25 +1754,9 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
* preallocated blocks are unmapped but should treated
* the same as allocated blocks.
*/
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0)
+ ret = ext4_da_map_blocks(inode, iblock, &map, bh);
+ if (ret <= 0)
return ret;
- if (ret == 0) {
- if (buffer_delay(bh))
- return 0; /* Not sure this could or should happen */
- /*
- * XXX: __block_write_begin() unmaps passed block, is it OK?
- */
- ret = ext4_da_reserve_space(inode, iblock);
- if (ret)
- /* not enough space to reserve */
- return ret;
-
- map_bh(bh, inode->i_sb, invalid_block);
- set_buffer_new(bh);
- set_buffer_delay(bh);
- return 0;
- }
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
@@ -2564,6 +1831,8 @@ static int __ext4_journalled_writepage(struct page *page,
goto out;
}
+ BUG_ON(!ext4_handle_valid(handle));
+
ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
do_journal_get_write_access);
@@ -2571,6 +1840,7 @@ static int __ext4_journalled_writepage(struct page *page,
write_end_fn);
if (ret == 0)
ret = err;
+ EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
@@ -2663,8 +1933,12 @@ static int ext4_writepage(struct page *page,
* We don't want to do block allocation, so redirty
* the page and return. We may reach here when we do
* a journal commit via journal_submit_inode_data_buffers.
- * We can also reach here via shrink_page_list
+ * We can also reach here via shrink_page_list but it
+ * should never be for direct reclaim so warn if that
+ * happens
*/
+ WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
+ PF_MEMALLOC);
goto redirty_page;
}
if (commit_write)
@@ -2741,7 +2015,7 @@ static int write_cache_pages_da(struct address_space *mapping,
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
@@ -2898,6 +2172,7 @@ static int ext4_da_writepages(struct address_space *mapping,
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
pgoff_t done_index = 0;
pgoff_t end;
+ struct blk_plug plug;
trace_ext4_da_writepages(inode, wbc);
@@ -2973,9 +2248,10 @@ static int ext4_da_writepages(struct address_space *mapping,
}
retry:
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
+ blk_start_plug(&plug);
while (!ret && wbc->nr_to_write > 0) {
/*
@@ -3026,11 +2302,12 @@ retry:
ret = 0;
} else if (ret == MPAGE_DA_EXTENT_TAIL) {
/*
- * got one extent now try with
- * rest of the pages
+ * Got one extent now try with rest of the pages.
+ * If mpd.retval is set -EIO, journal is aborted.
+ * So we don't need to write any more.
*/
pages_written += mpd.pages_written;
- ret = 0;
+ ret = mpd.retval;
io_done = 1;
} else if (wbc->nr_to_write)
/*
@@ -3040,6 +2317,7 @@ retry:
*/
break;
}
+ blk_finish_plug(&plug);
if (!io_done && !cycled) {
cycled = 1;
index = 0;
@@ -3078,10 +2356,11 @@ static int ext4_nonda_switch(struct super_block *sb)
* Delalloc need an accurate free block accounting. So switch
* to non delalloc when we are near to error range.
*/
- free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
- dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter);
+ free_blocks = EXT4_C2B(sbi,
+ percpu_counter_read_positive(&sbi->s_freeclusters_counter));
+ dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
if (2 * free_blocks < 3 * dirty_blocks ||
- free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
+ free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
/*
* free block count is less than 150% of dirty blocks
* or free blocks is less than watermark
@@ -3093,7 +2372,7 @@ static int ext4_nonda_switch(struct super_block *sb)
* start pushing delalloc when 1/2 of free blocks are dirty.
*/
if (free_blocks < 2 * dirty_blocks)
- writeback_inodes_sb_if_idle(sb);
+ writeback_inodes_sb_if_idle(sb, WB_REASON_FS_FREE_SPACE);
return 0;
}
@@ -3107,6 +2386,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
pgoff_t index;
struct inode *inode = mapping->host;
handle_t *handle;
+ loff_t page_len;
index = pos >> PAGE_CACHE_SHIFT;
@@ -3153,6 +2433,13 @@ retry:
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
+ } else {
+ page_len = pos & (PAGE_CACHE_SIZE - 1);
+ if (page_len > 0) {
+ ret = ext4_discard_partial_page_buffers_no_lock(handle,
+ inode, page, pos - page_len, page_len,
+ EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
+ }
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -3195,6 +2482,7 @@ static int ext4_da_write_end(struct file *file,
loff_t new_i_size;
unsigned long start, end;
int write_mode = (int)(unsigned long)fsdata;
+ loff_t page_len;
if (write_mode == FALL_BACK_TO_NONDELALLOC) {
if (ext4_should_order_data(inode)) {
@@ -3243,6 +2531,16 @@ static int ext4_da_write_end(struct file *file,
}
ret2 = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
+
+ page_len = PAGE_CACHE_SIZE -
+ ((pos + copied - 1) & (PAGE_CACHE_SIZE - 1));
+
+ if (page_len > 0) {
+ ret = ext4_discard_partial_page_buffers_no_lock(handle,
+ inode, page, pos + copied - 1, page_len,
+ EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
+ }
+
copied = ret2;
if (ret2 < 0)
ret = ret2;
@@ -3450,112 +2748,6 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
}
/*
- * O_DIRECT for ext3 (or indirect map) based files
- *
- * If the O_DIRECT write will extend the file then add this inode to the
- * orphan list. So recovery will truncate it back to the original size
- * if the machine crashes during the write.
- *
- * If the O_DIRECT write is intantiating holes inside i_size and the machine
- * crashes then stale disk data _may_ be exposed inside the file. But current
- * VFS code falls back into buffered path in that case so we are safe.
- */
-static ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
-{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct ext4_inode_info *ei = EXT4_I(inode);
- handle_t *handle;
- ssize_t ret;
- int orphan = 0;
- size_t count = iov_length(iov, nr_segs);
- int retries = 0;
-
- if (rw == WRITE) {
- loff_t final_size = offset + count;
-
- if (final_size > inode->i_size) {
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, 2);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
- ret = ext4_orphan_add(handle, inode);
- if (ret) {
- ext4_journal_stop(handle);
- goto out;
- }
- orphan = 1;
- ei->i_disksize = inode->i_size;
- ext4_journal_stop(handle);
- }
- }
-
-retry:
- if (rw == READ && ext4_should_dioread_nolock(inode))
- ret = __blockdev_direct_IO(rw, iocb, inode,
- inode->i_sb->s_bdev, iov,
- offset, nr_segs,
- ext4_get_block, NULL, NULL, 0);
- else {
- ret = blockdev_direct_IO(rw, iocb, inode, iov,
- offset, nr_segs, ext4_get_block);
-
- if (unlikely((rw & WRITE) && ret < 0)) {
- loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
-
- if (end > isize)
- ext4_truncate_failed_write(inode);
- }
- }
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
-
- if (orphan) {
- int err;
-
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, 2);
- if (IS_ERR(handle)) {
- /* This is really bad luck. We've written the data
- * but cannot extend i_size. Bail out and pretend
- * the write failed... */
- ret = PTR_ERR(handle);
- if (inode->i_nlink)
- ext4_orphan_del(NULL, inode);
-
- goto out;
- }
- if (inode->i_nlink)
- ext4_orphan_del(handle, inode);
- if (ret > 0) {
- loff_t end = offset + ret;
- if (end > inode->i_size) {
- ei->i_disksize = end;
- i_size_write(inode, end);
- /*
- * We're going to return a positive `ret'
- * here due to non-zero-length I/O, so there's
- * no way of reporting error returns from
- * ext4_mark_inode_dirty() to userspace. So
- * ignore it.
- */
- ext4_mark_inode_dirty(handle, inode);
- }
- }
- err = ext4_journal_stop(handle);
- if (ret == 0)
- ret = err;
- }
-out:
- return ret;
-}
-
-/*
* ext4_get_block used when preparing for a DIO write or buffer write.
* We allocate an uinitialized extent if blocks haven't been allocated.
* The extent will be converted to initialized after the IO is complete.
@@ -3638,8 +2830,12 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
goto out;
}
- io_end->flag = EXT4_IO_END_UNWRITTEN;
+ /*
+ * It may be over-defensive here to check EXT4_IO_END_UNWRITTEN now,
+ * but being more careful is always safe for the future change.
+ */
inode = io_end->inode;
+ ext4_set_io_unwritten_flag(inode, io_end);
/* Add the io_end to per-inode completed io list*/
spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
@@ -3805,6 +3001,12 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
struct inode *inode = file->f_mapping->host;
ssize_t ret;
+ /*
+ * If we are doing data journalling we don't support O_DIRECT
+ */
+ if (ext4_should_journal_data(inode))
+ return 0;
+
trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
@@ -3874,6 +3076,7 @@ static const struct address_space_operations ext4_journalled_aops = {
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
+ .direct_IO = ext4_direct_IO,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
@@ -3910,6 +3113,227 @@ void ext4_set_aops(struct inode *inode)
inode->i_mapping->a_ops = &ext4_journalled_aops;
}
+
+/*
+ * ext4_discard_partial_page_buffers()
+ * Wrapper function for ext4_discard_partial_page_buffers_no_lock.
+ * This function finds and locks the page containing the offset
+ * "from" and passes it to ext4_discard_partial_page_buffers_no_lock.
+ * Calling functions that already have the page locked should call
+ * ext4_discard_partial_page_buffers_no_lock directly.
+ */
+int ext4_discard_partial_page_buffers(handle_t *handle,
+ struct address_space *mapping, loff_t from,
+ loff_t length, int flags)
+{
+ struct inode *inode = mapping->host;
+ struct page *page;
+ int err = 0;
+
+ page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
+ mapping_gfp_mask(mapping) & ~__GFP_FS);
+ if (!page)
+ return -ENOMEM;
+
+ err = ext4_discard_partial_page_buffers_no_lock(handle, inode, page,
+ from, length, flags);
+
+ unlock_page(page);
+ page_cache_release(page);
+ return err;
+}
+
+/*
+ * ext4_discard_partial_page_buffers_no_lock()
+ * Zeros a page range of length 'length' starting from offset 'from'.
+ * Buffer heads that correspond to the block aligned regions of the
+ * zeroed range will be unmapped. Unblock aligned regions
+ * will have the corresponding buffer head mapped if needed so that
+ * that region of the page can be updated with the partial zero out.
+ *
+ * This function assumes that the page has already been locked. The
+ * The range to be discarded must be contained with in the given page.
+ * If the specified range exceeds the end of the page it will be shortened
+ * to the end of the page that corresponds to 'from'. This function is
+ * appropriate for updating a page and it buffer heads to be unmapped and
+ * zeroed for blocks that have been either released, or are going to be
+ * released.
+ *
+ * handle: The journal handle
+ * inode: The files inode
+ * page: A locked page that contains the offset "from"
+ * from: The starting byte offset (from the begining of the file)
+ * to begin discarding
+ * len: The length of bytes to discard
+ * flags: Optional flags that may be used:
+ *
+ * EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED
+ * Only zero the regions of the page whose buffer heads
+ * have already been unmapped. This flag is appropriate
+ * for updateing the contents of a page whose blocks may
+ * have already been released, and we only want to zero
+ * out the regions that correspond to those released blocks.
+ *
+ * Returns zero on sucess or negative on failure.
+ */
+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)
+{
+ ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
+ unsigned int offset = from & (PAGE_CACHE_SIZE-1);
+ unsigned int blocksize, max, pos;
+ ext4_lblk_t iblock;
+ struct buffer_head *bh;
+ int err = 0;
+
+ blocksize = inode->i_sb->s_blocksize;
+ max = PAGE_CACHE_SIZE - offset;
+
+ if (index != page->index)
+ return -EINVAL;
+
+ /*
+ * correct length if it does not fall between
+ * 'from' and the end of the page
+ */
+ if (length > max || length < 0)
+ length = max;
+
+ iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+
+ if (!page_has_buffers(page)) {
+ /*
+ * If the range to be discarded covers a partial block
+ * we need to get the page buffers. This is because
+ * partial blocks cannot be released and the page needs
+ * to be updated with the contents of the block before
+ * we write the zeros on top of it.
+ */
+ if ((from & (blocksize - 1)) ||
+ ((from + length) & (blocksize - 1))) {
+ create_empty_buffers(page, blocksize, 0);
+ } else {
+ /*
+ * If there are no partial blocks,
+ * there is nothing to update,
+ * so we can return now
+ */
+ return 0;
+ }
+ }
+
+ /* Find the buffer that contains "offset" */
+ bh = page_buffers(page);
+ pos = blocksize;
+ while (offset >= pos) {
+ bh = bh->b_this_page;
+ iblock++;
+ pos += blocksize;
+ }
+
+ pos = offset;
+ while (pos < offset + length) {
+ unsigned int end_of_block, range_to_discard;
+
+ err = 0;
+
+ /* The length of space left to zero and unmap */
+ range_to_discard = offset + length - pos;
+
+ /* The length of space until the end of the block */
+ end_of_block = blocksize - (pos & (blocksize-1));
+
+ /*
+ * Do not unmap or zero past end of block
+ * for this buffer head
+ */
+ if (range_to_discard > end_of_block)
+ range_to_discard = end_of_block;
+
+
+ /*
+ * Skip this buffer head if we are only zeroing unampped
+ * regions of the page
+ */
+ if (flags & EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED &&
+ buffer_mapped(bh))
+ goto next;
+
+ /* If the range is block aligned, unmap */
+ if (range_to_discard == blocksize) {
+ clear_buffer_dirty(bh);
+ bh->b_bdev = NULL;
+ clear_buffer_mapped(bh);
+ clear_buffer_req(bh);
+ clear_buffer_new(bh);
+ clear_buffer_delay(bh);
+ clear_buffer_unwritten(bh);
+ clear_buffer_uptodate(bh);
+ zero_user(page, pos, range_to_discard);
+ BUFFER_TRACE(bh, "Buffer discarded");
+ goto next;
+ }
+
+ /*
+ * If this block is not completely contained in the range
+ * to be discarded, then it is not going to be released. Because
+ * we need to keep this block, we need to make sure this part
+ * of the page is uptodate before we modify it by writeing
+ * partial zeros on it.
+ */
+ if (!buffer_mapped(bh)) {
+ /*
+ * Buffer head must be mapped before we can read
+ * from the block
+ */
+ BUFFER_TRACE(bh, "unmapped");
+ ext4_get_block(inode, iblock, bh, 0);
+ /* unmapped? It's a hole - nothing to do */
+ if (!buffer_mapped(bh)) {
+ BUFFER_TRACE(bh, "still unmapped");
+ goto next;
+ }
+ }
+
+ /* Ok, it's mapped. Make sure it's up-to-date */
+ if (PageUptodate(page))
+ set_buffer_uptodate(bh);
+
+ if (!buffer_uptodate(bh)) {
+ err = -EIO;
+ ll_rw_block(READ, 1, &bh);
+ wait_on_buffer(bh);
+ /* Uhhuh. Read error. Complain and punt.*/
+ if (!buffer_uptodate(bh))
+ goto next;
+ }
+
+ if (ext4_should_journal_data(inode)) {
+ BUFFER_TRACE(bh, "get write access");
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err)
+ goto next;
+ }
+
+ zero_user(page, pos, range_to_discard);
+
+ err = 0;
+ if (ext4_should_journal_data(inode)) {
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
+ } else
+ mark_buffer_dirty(bh);
+
+ BUFFER_TRACE(bh, "Partial buffer zeroed");
+next:
+ bh = bh->b_this_page;
+ iblock++;
+ pos += range_to_discard;
+ }
+
+ return err;
+}
+
/*
* ext4_block_truncate_page() zeroes out a mapping from file offset `from'
* up to the end of the block which corresponds to `from'.
@@ -3952,7 +3376,7 @@ int ext4_block_zero_page_range(handle_t *handle,
page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
mapping_gfp_mask(mapping) & ~__GFP_FS);
if (!page)
- return -EINVAL;
+ return -ENOMEM;
blocksize = inode->i_sb->s_blocksize;
max = blocksize - (offset & (blocksize - 1));
@@ -4021,11 +3445,8 @@ int ext4_block_zero_page_range(handle_t *handle,
err = 0;
if (ext4_should_journal_data(inode)) {
err = ext4_handle_dirty_metadata(handle, inode, bh);
- } else {
- if (ext4_should_order_data(inode) && EXT4_I(inode)->jinode)
- err = ext4_jbd2_file_inode(handle, inode);
+ } else
mark_buffer_dirty(bh);
- }
unlock:
unlock_page(page);
@@ -4033,383 +3454,6 @@ unlock:
return err;
}
-/*
- * Probably it should be a library function... search for first non-zero word
- * or memcmp with zero_page, whatever is better for particular architecture.
- * Linus?
- */
-static inline int all_zeroes(__le32 *p, __le32 *q)
-{
- while (p < q)
- if (*p++)
- return 0;
- return 1;
-}
-
-/**
- * ext4_find_shared - find the indirect blocks for partial truncation.
- * @inode: inode in question
- * @depth: depth of the affected branch
- * @offsets: offsets of pointers in that branch (see ext4_block_to_path)
- * @chain: place to store the pointers to partial indirect blocks
- * @top: place to the (detached) top of branch
- *
- * This is a helper function used by ext4_truncate().
- *
- * When we do truncate() we may have to clean the ends of several
- * indirect blocks but leave the blocks themselves alive. Block is
- * partially truncated if some data below the new i_size is referred
- * from it (and it is on the path to the first completely truncated
- * data block, indeed). We have to free the top of that path along
- * with everything to the right of the path. Since no allocation
- * past the truncation point is possible until ext4_truncate()
- * finishes, we may safely do the latter, but top of branch may
- * require special attention - pageout below the truncation point
- * might try to populate it.
- *
- * We atomically detach the top of branch from the tree, store the
- * block number of its root in *@top, pointers to buffer_heads of
- * partially truncated blocks - in @chain[].bh and pointers to
- * their last elements that should not be removed - in
- * @chain[].p. Return value is the pointer to last filled element
- * of @chain.
- *
- * The work left to caller to do the actual freeing of subtrees:
- * a) free the subtree starting from *@top
- * b) free the subtrees whose roots are stored in
- * (@chain[i].p+1 .. end of @chain[i].bh->b_data)
- * c) free the subtrees growing from the inode past the @chain[0].
- * (no partially truncated stuff there). */
-
-static Indirect *ext4_find_shared(struct inode *inode, int depth,
- ext4_lblk_t offsets[4], Indirect chain[4],
- __le32 *top)
-{
- Indirect *partial, *p;
- int k, err;
-
- *top = 0;
- /* Make k index the deepest non-null offset + 1 */
- for (k = depth; k > 1 && !offsets[k-1]; k--)
- ;
- partial = ext4_get_branch(inode, k, offsets, chain, &err);
- /* Writer: pointers */
- if (!partial)
- partial = chain + k-1;
- /*
- * If the branch acquired continuation since we've looked at it -
- * fine, it should all survive and (new) top doesn't belong to us.
- */
- if (!partial->key && *partial->p)
- /* Writer: end */
- goto no_top;
- for (p = partial; (p > chain) && all_zeroes((__le32 *) p->bh->b_data, p->p); p--)
- ;
- /*
- * OK, we've found the last block that must survive. The rest of our
- * branch should be detached before unlocking. However, if that rest
- * of branch is all ours and does not grow immediately from the inode
- * it's easier to cheat and just decrement partial->p.
- */
- if (p == chain + k - 1 && p > chain) {
- p->p--;
- } else {
- *top = *p->p;
- /* Nope, don't do this in ext4. Must leave the tree intact */
-#if 0
- *p->p = 0;
-#endif
- }
- /* Writer: end */
-
- while (partial > p) {
- brelse(partial->bh);
- partial--;
- }
-no_top:
- return partial;
-}
-
-/*
- * Zero a number of block pointers in either an inode or an indirect block.
- * If we restart the transaction we must again get write access to the
- * indirect block for further modification.
- *
- * We release `count' blocks on disk, but (last - first) may be greater
- * than `count' because there can be holes in there.
- *
- * Return 0 on success, 1 on invalid block range
- * and < 0 on fatal error.
- */
-static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
- struct buffer_head *bh,
- ext4_fsblk_t block_to_free,
- unsigned long count, __le32 *first,
- __le32 *last)
-{
- __le32 *p;
- int flags = EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_VALIDATED;
- int err;
-
- if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
- flags |= EXT4_FREE_BLOCKS_METADATA;
-
- if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
- count)) {
- EXT4_ERROR_INODE(inode, "attempt to clear invalid "
- "blocks %llu len %lu",
- (unsigned long long) block_to_free, count);
- return 1;
- }
-
- if (try_to_extend_transaction(handle, inode)) {
- if (bh) {
- BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, inode, bh);
- if (unlikely(err))
- goto out_err;
- }
- err = ext4_mark_inode_dirty(handle, inode);
- if (unlikely(err))
- goto out_err;
- err = ext4_truncate_restart_trans(handle, inode,
- blocks_for_truncate(inode));
- if (unlikely(err))
- goto out_err;
- if (bh) {
- BUFFER_TRACE(bh, "retaking write access");
- err = ext4_journal_get_write_access(handle, bh);
- if (unlikely(err))
- goto out_err;
- }
- }
-
- for (p = first; p < last; p++)
- *p = 0;
-
- ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags);
- return 0;
-out_err:
- ext4_std_error(inode->i_sb, err);
- return err;
-}
-
-/**
- * ext4_free_data - free a list of data blocks
- * @handle: handle for this transaction
- * @inode: inode we are dealing with
- * @this_bh: indirect buffer_head which contains *@first and *@last
- * @first: array of block numbers
- * @last: points immediately past the end of array
- *
- * We are freeing all blocks referred from that array (numbers are stored as
- * little-endian 32-bit) and updating @inode->i_blocks appropriately.
- *
- * We accumulate contiguous runs of blocks to free. Conveniently, if these
- * blocks are contiguous then releasing them at one time will only affect one
- * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't
- * actually use a lot of journal space.
- *
- * @this_bh will be %NULL if @first and @last point into the inode's direct
- * block pointers.
- */
-static void ext4_free_data(handle_t *handle, struct inode *inode,
- struct buffer_head *this_bh,
- __le32 *first, __le32 *last)
-{
- ext4_fsblk_t block_to_free = 0; /* Starting block # of a run */
- unsigned long count = 0; /* Number of blocks in the run */
- __le32 *block_to_free_p = NULL; /* Pointer into inode/ind
- corresponding to
- block_to_free */
- ext4_fsblk_t nr; /* Current block # */
- __le32 *p; /* Pointer into inode/ind
- for current block */
- int err = 0;
-
- if (this_bh) { /* For indirect block */
- BUFFER_TRACE(this_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, this_bh);
- /* Important: if we can't update the indirect pointers
- * to the blocks, we can't free them. */
- if (err)
- return;
- }
-
- for (p = first; p < last; p++) {
- nr = le32_to_cpu(*p);
- if (nr) {
- /* accumulate blocks to free if they're contiguous */
- if (count == 0) {
- block_to_free = nr;
- block_to_free_p = p;
- count = 1;
- } else if (nr == block_to_free + count) {
- count++;
- } else {
- err = ext4_clear_blocks(handle, inode, this_bh,
- block_to_free, count,
- block_to_free_p, p);
- if (err)
- break;
- block_to_free = nr;
- block_to_free_p = p;
- count = 1;
- }
- }
- }
-
- if (!err && count > 0)
- err = ext4_clear_blocks(handle, inode, this_bh, block_to_free,
- count, block_to_free_p, p);
- if (err < 0)
- /* fatal error */
- return;
-
- if (this_bh) {
- BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata");
-
- /*
- * The buffer head should have an attached journal head at this
- * point. However, if the data is corrupted and an indirect
- * block pointed to itself, it would have been detached when
- * the block was cleared. Check for this instead of OOPSing.
- */
- if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh))
- ext4_handle_dirty_metadata(handle, inode, this_bh);
- else
- EXT4_ERROR_INODE(inode,
- "circular indirect block detected at "
- "block %llu",
- (unsigned long long) this_bh->b_blocknr);
- }
-}
-
-/**
- * ext4_free_branches - free an array of branches
- * @handle: JBD handle for this transaction
- * @inode: inode we are dealing with
- * @parent_bh: the buffer_head which contains *@first and *@last
- * @first: array of block numbers
- * @last: pointer immediately past the end of array
- * @depth: depth of the branches to free
- *
- * We are freeing all blocks referred from these branches (numbers are
- * stored as little-endian 32-bit) and updating @inode->i_blocks
- * appropriately.
- */
-static void ext4_free_branches(handle_t *handle, struct inode *inode,
- struct buffer_head *parent_bh,
- __le32 *first, __le32 *last, int depth)
-{
- ext4_fsblk_t nr;
- __le32 *p;
-
- if (ext4_handle_is_aborted(handle))
- return;
-
- if (depth--) {
- struct buffer_head *bh;
- int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- p = last;
- while (--p >= first) {
- nr = le32_to_cpu(*p);
- if (!nr)
- continue; /* A hole */
-
- if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
- nr, 1)) {
- EXT4_ERROR_INODE(inode,
- "invalid indirect mapped "
- "block %lu (level %d)",
- (unsigned long) nr, depth);
- break;
- }
-
- /* Go read the buffer for the next level down */
- bh = sb_bread(inode->i_sb, nr);
-
- /*
- * A read failure? Report error and clear slot
- * (should be rare).
- */
- if (!bh) {
- EXT4_ERROR_INODE_BLOCK(inode, nr,
- "Read failure");
- continue;
- }
-
- /* This zaps the entire block. Bottom up. */
- BUFFER_TRACE(bh, "free child branches");
- ext4_free_branches(handle, inode, bh,
- (__le32 *) bh->b_data,
- (__le32 *) bh->b_data + addr_per_block,
- depth);
- brelse(bh);
-
- /*
- * Everything below this this pointer has been
- * released. Now let this top-of-subtree go.
- *
- * We want the freeing of this indirect block to be
- * atomic in the journal with the updating of the
- * bitmap block which owns it. So make some room in
- * the journal.
- *
- * We zero the parent pointer *after* freeing its
- * pointee in the bitmaps, so if extend_transaction()
- * for some reason fails to put the bitmap changes and
- * the release into the same transaction, recovery
- * will merely complain about releasing a free block,
- * rather than leaking blocks.
- */
- if (ext4_handle_is_aborted(handle))
- return;
- if (try_to_extend_transaction(handle, inode)) {
- ext4_mark_inode_dirty(handle, inode);
- ext4_truncate_restart_trans(handle, inode,
- blocks_for_truncate(inode));
- }
-
- /*
- * The forget flag here is critical because if
- * we are journaling (and not doing data
- * journaling), we have to make sure a revoke
- * record is written to prevent the journal
- * replay from overwriting the (former)
- * indirect block if it gets reallocated as a
- * data block. This must happen in the same
- * transaction where the data blocks are
- * actually freed.
- */
- ext4_free_blocks(handle, inode, NULL, nr, 1,
- EXT4_FREE_BLOCKS_METADATA|
- EXT4_FREE_BLOCKS_FORGET);
-
- if (parent_bh) {
- /*
- * The block which we have just freed is
- * pointed to by an indirect block: journal it
- */
- BUFFER_TRACE(parent_bh, "get_write_access");
- if (!ext4_journal_get_write_access(handle,
- parent_bh)){
- *p = 0;
- BUFFER_TRACE(parent_bh,
- "call ext4_handle_dirty_metadata");
- ext4_handle_dirty_metadata(handle,
- inode,
- parent_bh);
- }
- }
- }
- } else {
- /* We have reached the bottom of the tree. */
- BUFFER_TRACE(parent_bh, "free data blocks");
- ext4_free_data(handle, inode, parent_bh, first, last);
- }
-}
-
int ext4_can_truncate(struct inode *inode)
{
if (S_ISREG(inode->i_mode))
@@ -4443,6 +3487,11 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
return -ENOTSUPP;
}
+ if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) {
+ /* TODO: Add support for bigalloc file systems */
+ return -ENOTSUPP;
+ }
+
return ext4_ext_punch_hole(file, offset, length);
}
@@ -4476,19 +3525,6 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
*/
void ext4_truncate(struct inode *inode)
{
- handle_t *handle;
- struct ext4_inode_info *ei = EXT4_I(inode);
- __le32 *i_data = ei->i_data;
- int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- struct address_space *mapping = inode->i_mapping;
- ext4_lblk_t offsets[4];
- Indirect chain[4];
- Indirect *partial;
- __le32 nr = 0;
- int n = 0;
- ext4_lblk_t last_block, max_block;
- unsigned blocksize = inode->i_sb->s_blocksize;
-
trace_ext4_truncate_enter(inode);
if (!ext4_can_truncate(inode))
@@ -4499,149 +3535,11 @@ void ext4_truncate(struct inode *inode)
if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ext4_ext_truncate(inode);
- trace_ext4_truncate_exit(inode);
- return;
- }
-
- handle = start_transaction(inode);
- if (IS_ERR(handle))
- return; /* AKPM: return what? */
-
- last_block = (inode->i_size + blocksize-1)
- >> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
- 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))
- goto out_stop;
-
- if (last_block != max_block) {
- n = ext4_block_to_path(inode, last_block, offsets, NULL);
- if (n == 0)
- goto out_stop; /* error */
- }
-
- /*
- * OK. This truncate is going to happen. We add the inode to the
- * orphan list, so that if this truncate spans multiple transactions,
- * and we crash, we will resume the truncate when the filesystem
- * recovers. It also marks the inode dirty, to catch the new size.
- *
- * Implication: the file must always be in a sane, consistent
- * truncatable state while each transaction commits.
- */
- if (ext4_orphan_add(handle, inode))
- goto out_stop;
-
- /*
- * From here we block out all ext4_get_block() callers who want to
- * modify the block allocation tree.
- */
- down_write(&ei->i_data_sem);
-
- ext4_discard_preallocations(inode);
-
- /*
- * The orphan list entry will now protect us from any crash which
- * occurs before the truncate completes, so it is now safe to propagate
- * the new, shorter inode size (held for now in i_size) into the
- * on-disk inode. We do this via i_disksize, which is the value which
- * ext4 *really* writes onto the disk inode.
- */
- ei->i_disksize = inode->i_size;
-
- if (last_block == max_block) {
- /*
- * It is unnecessary to free any data blocks if last_block is
- * equal to the indirect block limit.
- */
- goto out_unlock;
- } else if (n == 1) { /* direct blocks */
- ext4_free_data(handle, inode, NULL, i_data+offsets[0],
- i_data + EXT4_NDIR_BLOCKS);
- goto do_indirects;
- }
-
- partial = ext4_find_shared(inode, n, offsets, chain, &nr);
- /* Kill the top of shared branch (not detached) */
- if (nr) {
- if (partial == chain) {
- /* Shared branch grows from the inode */
- ext4_free_branches(handle, inode, NULL,
- &nr, &nr+1, (chain+n-1) - partial);
- *partial->p = 0;
- /*
- * We mark the inode dirty prior to restart,
- * and prior to stop. No need for it here.
- */
- } else {
- /* Shared branch grows from an indirect block */
- BUFFER_TRACE(partial->bh, "get_write_access");
- ext4_free_branches(handle, inode, partial->bh,
- partial->p,
- partial->p+1, (chain+n-1) - partial);
- }
- }
- /* Clear the ends of indirect blocks on the shared branch */
- while (partial > chain) {
- ext4_free_branches(handle, inode, partial->bh, partial->p + 1,
- (__le32*)partial->bh->b_data+addr_per_block,
- (chain+n-1) - partial);
- BUFFER_TRACE(partial->bh, "call brelse");
- brelse(partial->bh);
- partial--;
- }
-do_indirects:
- /* Kill the remaining (whole) subtrees */
- switch (offsets[0]) {
- default:
- nr = i_data[EXT4_IND_BLOCK];
- if (nr) {
- ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
- i_data[EXT4_IND_BLOCK] = 0;
- }
- case EXT4_IND_BLOCK:
- nr = i_data[EXT4_DIND_BLOCK];
- if (nr) {
- ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
- i_data[EXT4_DIND_BLOCK] = 0;
- }
- case EXT4_DIND_BLOCK:
- nr = i_data[EXT4_TIND_BLOCK];
- if (nr) {
- ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
- i_data[EXT4_TIND_BLOCK] = 0;
- }
- case EXT4_TIND_BLOCK:
- ;
- }
-
-out_unlock:
- up_write(&ei->i_data_sem);
- inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
- ext4_mark_inode_dirty(handle, inode);
-
- /*
- * In a multi-transaction truncate, we only make the final transaction
- * synchronous
- */
- if (IS_SYNC(inode))
- ext4_handle_sync(handle);
-out_stop:
- /*
- * If this was a simple ftruncate(), and the file will remain alive
- * then we need to clear up the orphan record which we created above.
- * However, if this was a real unlink then we were called by
- * ext4_delete_inode(), and we allow that function to clean up the
- * orphan info for us.
- */
- if (inode->i_nlink)
- ext4_orphan_del(handle, inode);
+ else
+ ext4_ind_truncate(inode);
- ext4_journal_stop(handle);
trace_ext4_truncate_exit(inode);
}
@@ -4777,7 +3675,7 @@ make_io:
trace_ext4_load_inode(inode);
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(READ_META, bh);
+ submit_bh(READ | REQ_META | REQ_PRIO, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
EXT4_ERROR_INODE_BLOCK(inode, block,
@@ -4893,7 +3791,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
- inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
+ set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
ei->i_dir_start_lookup = 0;
@@ -5012,7 +3910,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
(S_ISLNK(inode->i_mode) &&
!ext4_inode_is_fast_symlink(inode))) {
/* Validate block references which are part of inode */
- ret = ext4_check_inode_blockref(inode);
+ ret = ext4_ind_check_inode(inode);
}
if (ret)
goto bad_inode;
@@ -5459,34 +4357,10 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
return 0;
}
-static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks,
- int chunk)
-{
- int indirects;
-
- /* if nrblocks are contiguous */
- if (chunk) {
- /*
- * With N contiguous data blocks, we need at most
- * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks,
- * 2 dindirect blocks, and 1 tindirect block
- */
- return DIV_ROUND_UP(nrblocks,
- EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
- }
- /*
- * if nrblocks are not contiguous, worse case, each block touch
- * a indirect block, and each indirect block touch a double indirect
- * block, plus a triple indirect block
- */
- indirects = nrblocks * 2 + 1;
- return indirects;
-}
-
static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
{
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
- return ext4_indirect_trans_blocks(inode, nrblocks, chunk);
+ return ext4_ind_trans_blocks(inode, nrblocks, chunk);
return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
}
@@ -5919,6 +4793,7 @@ retry_alloc:
PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {
unlock_page(page);
ret = VM_FAULT_SIGBUS;
+ ext4_journal_stop(handle);
goto out;
}
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 808c554e773f..a56796814d6a 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -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;
@@ -173,41 +174,24 @@ 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;
- if (!capable(CAP_SYS_RESOURCE))
- return -EPERM;
+ err = ext4_resize_begin(sb);
+ if (err)
+ return err;
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;
@@ -221,6 +205,7 @@ setversion_out:
if (err == 0)
err = err2;
mnt_drop_write(filp->f_path.mnt);
+ ext4_resize_end(sb);
return err;
}
@@ -248,6 +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;
@@ -268,16 +260,23 @@ mext_out:
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
- struct super_block *sb = inode->i_sb;
int err, err2=0;
- if (!capable(CAP_SYS_RESOURCE))
- return -EPERM;
+ err = ext4_resize_begin(sb);
+ if (err)
+ return err;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
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;
@@ -291,6 +290,7 @@ mext_out:
if (err == 0)
err = err2;
mnt_drop_write(filp->f_path.mnt);
+ ext4_resize_end(sb);
return err;
}
@@ -333,7 +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;
@@ -344,7 +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;
@@ -354,7 +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;
@@ -392,11 +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;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 6ed859d56850..e2d8be8f28bf 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -70,13 +70,13 @@
*
* pa_lstart -> the logical start block for this prealloc space
* pa_pstart -> the physical start block for this prealloc space
- * pa_len -> length for this prealloc space
- * pa_free -> free space available in this prealloc space
+ * pa_len -> length for this prealloc space (in clusters)
+ * pa_free -> free space available in this prealloc space (in clusters)
*
* The inode preallocation space is used looking at the _logical_ start
* block. If only the logical file block falls within the range of prealloc
- * space we will consume the particular prealloc space. This make sure that
- * that the we have contiguous physical blocks representing the file blocks
+ * space we will consume the particular prealloc space. This makes sure that
+ * we have contiguous physical blocks representing the file blocks
*
* The important thing to be noted in case of inode prealloc space is that
* we don't modify the values associated to inode prealloc space except
@@ -84,7 +84,7 @@
*
* If we are not able to find blocks in the inode prealloc space and if we
* have the group allocation flag set then we look at the locality group
- * prealloc space. These are per CPU prealloc list repreasented as
+ * prealloc space. These are per CPU prealloc list represented as
*
* ext4_sb_info.s_locality_groups[smp_processor_id()]
*
@@ -126,14 +126,16 @@
* list. In case of inode preallocation we follow a list of heuristics
* based on file size. This can be found in ext4_mb_normalize_request. If
* we are doing a group prealloc we try to normalize the request to
- * sbi->s_mb_group_prealloc. Default value of s_mb_group_prealloc is
+ * sbi->s_mb_group_prealloc. The default value of s_mb_group_prealloc is
+ * dependent on the cluster size; for non-bigalloc file systems, it is
* 512 blocks. This can be tuned via
- * /sys/fs/ext4/<partition/mb_group_prealloc. The value is represented in
+ * /sys/fs/ext4/<partition>/mb_group_prealloc. The value is represented in
* terms of number of blocks. If we have mounted the file system with -O
* stripe=<value> option the group prealloc request is normalized to the
- * stripe value (sbi->s_stripe)
+ * the smallest multiple of the stripe value (sbi->s_stripe) which is
+ * greater than the default mb_group_prealloc.
*
- * The regular allocator(using the buddy cache) supports few tunables.
+ * The regular allocator (using the buddy cache) supports a few tunables.
*
* /sys/fs/ext4/<partition>/mb_min_to_scan
* /sys/fs/ext4/<partition>/mb_max_to_scan
@@ -152,7 +154,7 @@
* best extent in the found extents. Searching for the blocks starts with
* the group specified as the goal value in allocation context via
* ac_g_ex. Each group is first checked based on the criteria whether it
- * can used for allocation. ext4_mb_good_group explains how the groups are
+ * can be used for allocation. ext4_mb_good_group explains how the groups are
* checked.
*
* Both the prealloc space are getting populated as above. So for the first
@@ -458,7 +460,7 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
ext4_fsblk_t blocknr;
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
- blocknr += first + i;
+ blocknr += EXT4_C2B(EXT4_SB(sb), first + i);
ext4_grp_locked_error(sb, e4b->bd_group,
inode ? inode->i_ino : 0,
blocknr,
@@ -492,10 +494,11 @@ static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap)
b2 = (unsigned char *) bitmap;
for (i = 0; i < e4b->bd_sb->s_blocksize; i++) {
if (b1[i] != b2[i]) {
- printk(KERN_ERR "corruption in group %u "
- "at byte %u(%u): %x in copy != %x "
- "on disk/prealloc\n",
- e4b->bd_group, i, i * 8, b1[i], b2[i]);
+ ext4_msg(e4b->bd_sb, KERN_ERR,
+ "corruption in group %u "
+ "at byte %u(%u): %x in copy != %x "
+ "on disk/prealloc",
+ e4b->bd_group, i, i * 8, b1[i], b2[i]);
BUG();
}
}
@@ -578,7 +581,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
continue;
}
- /* both bits in buddy2 must be 0 */
+ /* both bits in buddy2 must be 1 */
MB_CHECK_ASSERT(mb_test_bit(i << 1, buddy2));
MB_CHECK_ASSERT(mb_test_bit((i << 1) + 1, buddy2));
@@ -651,7 +654,7 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
ext4_grpblk_t chunk;
unsigned short border;
- BUG_ON(len > EXT4_BLOCKS_PER_GROUP(sb));
+ BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb));
border = 2 << sb->s_blocksize_bits;
@@ -703,7 +706,7 @@ void ext4_mb_generate_buddy(struct super_block *sb,
void *buddy, void *bitmap, ext4_group_t group)
{
struct ext4_group_info *grp = ext4_get_group_info(sb, group);
- ext4_grpblk_t max = EXT4_BLOCKS_PER_GROUP(sb);
+ ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb);
ext4_grpblk_t i = 0;
ext4_grpblk_t first;
ext4_grpblk_t len;
@@ -732,7 +735,7 @@ void ext4_mb_generate_buddy(struct super_block *sb,
if (free != grp->bb_free) {
ext4_grp_locked_error(sb, group, 0, 0,
- "%u blocks in bitmap, %u in gd",
+ "%u clusters in bitmap, %u in gd",
free, grp->bb_free);
/*
* If we intent to continue, we consider group descritor
@@ -1125,7 +1128,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
grp = ext4_get_group_info(sb, group);
e4b->bd_blkbits = sb->s_blocksize_bits;
- e4b->bd_info = ext4_get_group_info(sb, group);
+ e4b->bd_info = grp;
e4b->bd_sb = sb;
e4b->bd_group = group;
e4b->bd_buddy_page = NULL;
@@ -1281,7 +1284,7 @@ static void mb_clear_bits(void *bm, int cur, int len)
}
}
-static void mb_set_bits(void *bm, int cur, int len)
+void ext4_set_bits(void *bm, int cur, int len)
{
__u32 *addr;
@@ -1337,7 +1340,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
ext4_fsblk_t blocknr;
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
- blocknr += block;
+ blocknr += EXT4_C2B(EXT4_SB(sb), block);
ext4_grp_locked_error(sb, e4b->bd_group,
inode ? inode->i_ino : 0,
blocknr,
@@ -1388,7 +1391,6 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
{
int next = block;
int max;
- int ord;
void *buddy;
assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
@@ -1430,9 +1432,8 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
if (mb_test_bit(next, EXT4_MB_BITMAP(e4b)))
break;
- ord = mb_find_order_for_block(e4b, next);
+ order = mb_find_order_for_block(e4b, next);
- order = ord;
block = next >> order;
ex->fe_len += 1 << order;
}
@@ -1510,7 +1511,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
}
mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);
- mb_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
+ ext4_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
mb_check_buddy(e4b);
return ret;
@@ -1622,8 +1623,8 @@ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac,
struct ext4_free_extent *gex = &ac->ac_g_ex;
BUG_ON(ex->fe_len <= 0);
- BUG_ON(ex->fe_len > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
- BUG_ON(ex->fe_start >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+ BUG_ON(ex->fe_len > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
+ BUG_ON(ex->fe_start >= EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
BUG_ON(ac->ac_status != AC_STATUS_CONTINUE);
ac->ac_found++;
@@ -1821,15 +1822,15 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
while (free && ac->ac_status == AC_STATUS_CONTINUE) {
i = mb_find_next_zero_bit(bitmap,
- EXT4_BLOCKS_PER_GROUP(sb), i);
- if (i >= EXT4_BLOCKS_PER_GROUP(sb)) {
+ EXT4_CLUSTERS_PER_GROUP(sb), i);
+ if (i >= EXT4_CLUSTERS_PER_GROUP(sb)) {
/*
* IF we have corrupt bitmap, we won't find any
* free blocks even though group info says we
* we have free blocks
*/
ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
- "%d free blocks as per "
+ "%d free clusters as per "
"group info. But bitmap says 0",
free);
break;
@@ -1839,7 +1840,7 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
BUG_ON(ex.fe_len <= 0);
if (free < ex.fe_len) {
ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
- "%d free blocks as per "
+ "%d free clusters as per "
"group info. But got %d blocks",
free, ex.fe_len);
/*
@@ -1885,7 +1886,7 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
do_div(a, sbi->s_stripe);
i = (a * sbi->s_stripe) - first_group_block;
- while (i < EXT4_BLOCKS_PER_GROUP(sb)) {
+ while (i < EXT4_CLUSTERS_PER_GROUP(sb)) {
if (!mb_test_bit(i, bitmap)) {
max = mb_find_extent(e4b, 0, i, sbi->s_stripe, &ex);
if (max >= sbi->s_stripe) {
@@ -2223,8 +2224,8 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
EXT4_DESC_PER_BLOCK_BITS(sb);
meta_group_info = kmalloc(metalen, GFP_KERNEL);
if (meta_group_info == NULL) {
- printk(KERN_ERR "EXT4-fs: can't allocate mem for a "
- "buddy group\n");
+ ext4_msg(sb, KERN_ERR, "EXT4-fs: can't allocate mem "
+ "for a buddy group");
goto exit_meta_group_info;
}
sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] =
@@ -2237,7 +2238,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL);
if (meta_group_info[i] == NULL) {
- printk(KERN_ERR "EXT4-fs: can't allocate buddy mem\n");
+ ext4_msg(sb, KERN_ERR, "EXT4-fs: can't allocate buddy mem");
goto exit_group_info;
}
memset(meta_group_info[i], 0, kmem_cache_size(cachep));
@@ -2250,10 +2251,10 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
*/
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
meta_group_info[i]->bb_free =
- ext4_free_blocks_after_init(sb, group, desc);
+ ext4_free_clusters_after_init(sb, group, desc);
} else {
meta_group_info[i]->bb_free =
- ext4_free_blks_count(sb, desc);
+ ext4_free_group_clusters(sb, desc);
}
INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
@@ -2279,8 +2280,10 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
exit_group_info:
/* If a meta_group_info table has been allocated, release it now */
- if (group % EXT4_DESC_PER_BLOCK(sb) == 0)
+ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) {
kfree(sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]);
+ sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = NULL;
+ }
exit_meta_group_info:
return -ENOMEM;
} /* ext4_mb_add_groupinfo */
@@ -2328,23 +2331,26 @@ static int ext4_mb_init_backend(struct super_block *sb)
/* An 8TB filesystem with 64-bit pointers requires a 4096 byte
* kmalloc. A 128kb malloc should suffice for a 256TB filesystem.
* So a two level scheme suffices for now. */
- sbi->s_group_info = kzalloc(array_size, GFP_KERNEL);
+ sbi->s_group_info = ext4_kvzalloc(array_size, GFP_KERNEL);
if (sbi->s_group_info == NULL) {
- printk(KERN_ERR "EXT4-fs: can't allocate buddy meta group\n");
+ ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group");
return -ENOMEM;
}
sbi->s_buddy_cache = new_inode(sb);
if (sbi->s_buddy_cache == NULL) {
- printk(KERN_ERR "EXT4-fs: can't get new inode\n");
+ ext4_msg(sb, KERN_ERR, "can't get new inode");
goto err_freesgi;
}
- sbi->s_buddy_cache->i_ino = get_next_ino();
+ /* To avoid potentially colliding with an valid on-disk inode number,
+ * use EXT4_BAD_INO for the buddy cache inode number. This inode is
+ * not in the inode hash, so it should never be found by iget(), but
+ * this will avoid confusion if it ever shows up during debugging. */
+ sbi->s_buddy_cache->i_ino = EXT4_BAD_INO;
EXT4_I(sbi->s_buddy_cache)->i_disksize = 0;
for (i = 0; i < ngroups; i++) {
desc = ext4_get_group_desc(sb, i, NULL);
if (desc == NULL) {
- printk(KERN_ERR
- "EXT4-fs: can't read descriptor %u\n", i);
+ ext4_msg(sb, KERN_ERR, "can't read descriptor %u", i);
goto err_freebuddy;
}
if (ext4_mb_add_groupinfo(sb, i, desc) != 0)
@@ -2362,7 +2368,7 @@ err_freebuddy:
kfree(sbi->s_group_info[i]);
iput(sbi->s_buddy_cache);
err_freesgi:
- kfree(sbi->s_group_info);
+ ext4_kvfree(sbi->s_group_info);
return -ENOMEM;
}
@@ -2404,14 +2410,15 @@ static int ext4_groupinfo_create_slab(size_t size)
slab_size, 0, SLAB_RECLAIM_ACCOUNT,
NULL);
+ ext4_groupinfo_caches[cache_index] = cachep;
+
mutex_unlock(&ext4_grpinfo_slab_create_mutex);
if (!cachep) {
- printk(KERN_EMERG "EXT4: no memory for groupinfo slab cache\n");
+ printk(KERN_EMERG
+ "EXT4-fs: no memory for groupinfo slab cache\n");
return -ENOMEM;
}
- ext4_groupinfo_caches[cache_index] = cachep;
-
return 0;
}
@@ -2457,12 +2464,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
i++;
} while (i <= sb->s_blocksize_bits + 1);
- /* init file for buddy data */
- ret = ext4_mb_init_backend(sb);
- if (ret != 0) {
- goto out;
- }
-
spin_lock_init(&sbi->s_md_lock);
spin_lock_init(&sbi->s_bal_lock);
@@ -2471,12 +2472,37 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
sbi->s_mb_stats = MB_DEFAULT_STATS;
sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD;
sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS;
- sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC;
+ /*
+ * The default group preallocation is 512, which for 4k block
+ * sizes translates to 2 megabytes. However for bigalloc file
+ * systems, this is probably too big (i.e, if the cluster size
+ * is 1 megabyte, then group preallocation size becomes half a
+ * gigabyte!). As a default, we will keep a two megabyte
+ * group pralloc size for cluster sizes up to 64k, and after
+ * that, we will force a minimum group preallocation size of
+ * 32 clusters. This translates to 8 megs when the cluster
+ * size is 256k, and 32 megs when the cluster size is 1 meg,
+ * which seems reasonable as a default.
+ */
+ sbi->s_mb_group_prealloc = max(MB_DEFAULT_GROUP_PREALLOC >>
+ sbi->s_cluster_bits, 32);
+ /*
+ * If there is a s_stripe > 1, then we set the s_mb_group_prealloc
+ * to the lowest multiple of s_stripe which is bigger than
+ * the s_mb_group_prealloc as determined above. We want
+ * the preallocation size to be an exact multiple of the
+ * RAID stripe size so that preallocations don't fragment
+ * the stripes.
+ */
+ if (sbi->s_stripe > 1) {
+ sbi->s_mb_group_prealloc = roundup(
+ sbi->s_mb_group_prealloc, sbi->s_stripe);
+ }
sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
if (sbi->s_locality_groups == NULL) {
ret = -ENOMEM;
- goto out;
+ goto out_free_groupinfo_slab;
}
for_each_possible_cpu(i) {
struct ext4_locality_group *lg;
@@ -2487,17 +2513,30 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
spin_lock_init(&lg->lg_prealloc_lock);
}
+ /* init file for buddy data */
+ ret = ext4_mb_init_backend(sb);
+ if (ret != 0)
+ goto out_free_locality_groups;
+
if (sbi->s_proc)
proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
&ext4_mb_seq_groups_fops, sb);
if (sbi->s_journal)
sbi->s_journal->j_commit_callback = release_blocks_on_commit;
+
+ return 0;
+
+out_free_locality_groups:
+ free_percpu(sbi->s_locality_groups);
+ sbi->s_locality_groups = NULL;
+out_free_groupinfo_slab:
+ ext4_groupinfo_destroy_slabs();
out:
- if (ret) {
- kfree(sbi->s_mb_offsets);
- kfree(sbi->s_mb_maxs);
- }
+ kfree(sbi->s_mb_offsets);
+ sbi->s_mb_offsets = NULL;
+ kfree(sbi->s_mb_maxs);
+ sbi->s_mb_maxs = NULL;
return ret;
}
@@ -2544,32 +2583,32 @@ int ext4_mb_release(struct super_block *sb)
EXT4_DESC_PER_BLOCK_BITS(sb);
for (i = 0; i < num_meta_group_infos; i++)
kfree(sbi->s_group_info[i]);
- kfree(sbi->s_group_info);
+ ext4_kvfree(sbi->s_group_info);
}
kfree(sbi->s_mb_offsets);
kfree(sbi->s_mb_maxs);
if (sbi->s_buddy_cache)
iput(sbi->s_buddy_cache);
if (sbi->s_mb_stats) {
- printk(KERN_INFO
- "EXT4-fs: mballoc: %u blocks %u reqs (%u success)\n",
+ ext4_msg(sb, KERN_INFO,
+ "mballoc: %u blocks %u reqs (%u success)",
atomic_read(&sbi->s_bal_allocated),
atomic_read(&sbi->s_bal_reqs),
atomic_read(&sbi->s_bal_success));
- printk(KERN_INFO
- "EXT4-fs: mballoc: %u extents scanned, %u goal hits, "
- "%u 2^N hits, %u breaks, %u lost\n",
+ ext4_msg(sb, KERN_INFO,
+ "mballoc: %u extents scanned, %u goal hits, "
+ "%u 2^N hits, %u breaks, %u lost",
atomic_read(&sbi->s_bal_ex_scanned),
atomic_read(&sbi->s_bal_goals),
atomic_read(&sbi->s_bal_2orders),
atomic_read(&sbi->s_bal_breaks),
atomic_read(&sbi->s_mb_lost_chunks));
- printk(KERN_INFO
- "EXT4-fs: mballoc: %lu generated and it took %Lu\n",
- sbi->s_mb_buddies_generated++,
+ ext4_msg(sb, KERN_INFO,
+ "mballoc: %lu generated and it took %Lu",
+ sbi->s_mb_buddies_generated,
sbi->s_mb_generation_time);
- printk(KERN_INFO
- "EXT4-fs: mballoc: %u preallocated, %u discarded\n",
+ ext4_msg(sb, KERN_INFO,
+ "mballoc: %u preallocated, %u discarded",
atomic_read(&sbi->s_mb_preallocated),
atomic_read(&sbi->s_mb_discarded));
}
@@ -2582,11 +2621,13 @@ int ext4_mb_release(struct super_block *sb)
}
static inline int ext4_issue_discard(struct super_block *sb,
- ext4_group_t block_group, ext4_grpblk_t block, int count)
+ ext4_group_t block_group, ext4_grpblk_t cluster, int count)
{
ext4_fsblk_t discard_block;
- discard_block = block + ext4_group_first_block_no(sb, block_group);
+ discard_block = (EXT4_C2B(EXT4_SB(sb), cluster) +
+ ext4_group_first_block_no(sb, block_group));
+ count = EXT4_C2B(EXT4_SB(sb), count);
trace_ext4_discard_blocks(sb,
(unsigned long long) discard_block, count);
return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
@@ -2613,7 +2654,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
if (test_opt(sb, DISCARD))
ext4_issue_discard(sb, entry->group,
- entry->start_blk, entry->count);
+ entry->start_cluster, entry->count);
err = ext4_mb_load_buddy(sb, entry->group, &e4b);
/* we expect to find existing buddy because it's pinned */
@@ -2626,7 +2667,16 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
ext4_lock_group(sb, entry->group);
/* Take it out of per group rb tree */
rb_erase(&entry->node, &(db->bb_free_root));
- mb_free_blocks(NULL, &e4b, entry->start_blk, entry->count);
+ mb_free_blocks(NULL, &e4b, entry->start_cluster, entry->count);
+
+ /*
+ * Clear the trimmed flag for the group so that the next
+ * ext4_trim_fs can trim it.
+ * If the volume is mounted with -o discard, online discard
+ * is supported and the free blocks will be trimmed online.
+ */
+ if (!test_opt(sb, DISCARD))
+ EXT4_MB_GRP_CLEAR_TRIMMED(db);
if (!db->bb_free_root.rb_node) {
/* No more items in the per group rb tree
@@ -2723,7 +2773,7 @@ void ext4_exit_mballoc(void)
*/
static noinline_for_stack int
ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
- handle_t *handle, unsigned int reserv_blks)
+ handle_t *handle, unsigned int reserv_clstrs)
{
struct buffer_head *bitmap_bh = NULL;
struct ext4_group_desc *gdp;
@@ -2754,7 +2804,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
goto out_err;
ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
- ext4_free_blks_count(sb, gdp));
+ ext4_free_group_clusters(sb, gdp));
err = ext4_journal_get_write_access(handle, gdp_bh);
if (err)
@@ -2762,7 +2812,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
- len = ac->ac_b_ex.fe_len;
+ len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
if (!ext4_data_block_valid(sbi, block, len)) {
ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
"fs metadata\n", block, block+len);
@@ -2771,8 +2821,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
* We leak some of the blocks here.
*/
ext4_lock_group(sb, ac->ac_b_ex.fe_group);
- mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
- ac->ac_b_ex.fe_len);
+ ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+ ac->ac_b_ex.fe_len);
ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!err)
@@ -2790,31 +2840,33 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
}
}
#endif
- mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,ac->ac_b_ex.fe_len);
+ ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+ ac->ac_b_ex.fe_len);
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
- ext4_free_blks_set(sb, gdp,
- ext4_free_blocks_after_init(sb,
- ac->ac_b_ex.fe_group, gdp));
+ ext4_free_group_clusters_set(sb, gdp,
+ ext4_free_clusters_after_init(sb,
+ ac->ac_b_ex.fe_group, gdp));
}
- len = ext4_free_blks_count(sb, gdp) - ac->ac_b_ex.fe_len;
- ext4_free_blks_set(sb, gdp, len);
+ len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len;
+ ext4_free_group_clusters_set(sb, gdp, len);
gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
- percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
+ percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len);
/*
* Now reduce the dirty block count also. Should not go negative
*/
if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
/* release all the reserved blocks if non delalloc */
- percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
+ reserv_clstrs);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi,
ac->ac_b_ex.fe_group);
atomic_sub(ac->ac_b_ex.fe_len,
- &sbi->s_flex_groups[flex_group].free_blocks);
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -2830,8 +2882,9 @@ out_err:
/*
* here we normalize request for locality group
- * Group request are normalized to s_strip size if we set the same via mount
- * option. If not we set it to s_mb_group_prealloc which can be configured via
+ * Group request are normalized to s_mb_group_prealloc, which goes to
+ * s_strip if we set the same via mount option.
+ * s_mb_group_prealloc can be configured via
* /sys/fs/ext4/<partition>/mb_group_prealloc
*
* XXX: should we try to preallocate more than the group has now?
@@ -2842,10 +2895,7 @@ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac)
struct ext4_locality_group *lg = ac->ac_lg;
BUG_ON(lg == NULL);
- if (EXT4_SB(sb)->s_stripe)
- ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_stripe;
- else
- ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc;
+ ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc;
mb_debug(1, "#%u: goal %u blocks for locality group\n",
current->pid, ac->ac_g_ex.fe_len);
}
@@ -2858,6 +2908,7 @@ static noinline_for_stack void
ext4_mb_normalize_request(struct ext4_allocation_context *ac,
struct ext4_allocation_request *ar)
{
+ struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
int bsbits, max;
ext4_lblk_t end;
loff_t size, orig_size, start_off;
@@ -2888,7 +2939,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
/* first, let's learn actual file size
* given current request is allocated */
- size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len;
+ size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len);
size = size << bsbits;
if (size < i_size_read(ac->ac_inode))
size = i_size_read(ac->ac_inode);
@@ -2960,7 +3011,8 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
continue;
}
- pa_end = pa->pa_lstart + pa->pa_len;
+ pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb),
+ pa->pa_len);
/* PA must not overlap original request */
BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end ||
@@ -2990,9 +3042,11 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
rcu_read_lock();
list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
ext4_lblk_t pa_end;
+
spin_lock(&pa->pa_lock);
if (pa->pa_deleted == 0) {
- pa_end = pa->pa_lstart + pa->pa_len;
+ pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb),
+ pa->pa_len);
BUG_ON(!(start >= pa_end || end <= pa->pa_lstart));
}
spin_unlock(&pa->pa_lock);
@@ -3001,20 +3055,21 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
if (start + size <= ac->ac_o_ex.fe_logical &&
start > ac->ac_o_ex.fe_logical) {
- printk(KERN_ERR "start %lu, size %lu, fe_logical %lu\n",
- (unsigned long) start, (unsigned long) size,
- (unsigned long) ac->ac_o_ex.fe_logical);
+ ext4_msg(ac->ac_sb, KERN_ERR,
+ "start %lu, size %lu, fe_logical %lu",
+ (unsigned long) start, (unsigned long) size,
+ (unsigned long) ac->ac_o_ex.fe_logical);
}
BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
start > ac->ac_o_ex.fe_logical);
- BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+ BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
/* now prepare goal request */
/* XXX: is it better to align blocks WRT to logical
* placement or satisfy big request as is */
ac->ac_g_ex.fe_logical = start;
- ac->ac_g_ex.fe_len = size;
+ ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size);
/* define goal start in order to merge */
if (ar->pright && (ar->lright == (start + size))) {
@@ -3083,14 +3138,16 @@ static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
struct ext4_prealloc_space *pa)
{
+ struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
ext4_fsblk_t start;
ext4_fsblk_t end;
int len;
/* found preallocated blocks, use them */
start = pa->pa_pstart + (ac->ac_o_ex.fe_logical - pa->pa_lstart);
- end = min(pa->pa_pstart + pa->pa_len, start + ac->ac_o_ex.fe_len);
- len = end - start;
+ end = min(pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len),
+ start + EXT4_C2B(sbi, ac->ac_o_ex.fe_len));
+ len = EXT4_NUM_B2C(sbi, end - start);
ext4_get_group_no_and_offset(ac->ac_sb, start, &ac->ac_b_ex.fe_group,
&ac->ac_b_ex.fe_start);
ac->ac_b_ex.fe_len = len;
@@ -3098,7 +3155,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
ac->ac_pa = pa;
BUG_ON(start < pa->pa_pstart);
- BUG_ON(start + len > pa->pa_pstart + pa->pa_len);
+ BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len));
BUG_ON(pa->pa_free < len);
pa->pa_free -= len;
@@ -3164,6 +3221,7 @@ ext4_mb_check_group_pa(ext4_fsblk_t goal_block,
static noinline_for_stack int
ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
{
+ struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
int order, i;
struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
struct ext4_locality_group *lg;
@@ -3181,12 +3239,14 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
/* all fields in this condition don't change,
* so we can skip locking for them */
if (ac->ac_o_ex.fe_logical < pa->pa_lstart ||
- ac->ac_o_ex.fe_logical >= pa->pa_lstart + pa->pa_len)
+ ac->ac_o_ex.fe_logical >= (pa->pa_lstart +
+ EXT4_C2B(sbi, pa->pa_len)))
continue;
/* non-extent files can't have physical blocks past 2^32 */
if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
- pa->pa_pstart + pa->pa_len > EXT4_MAX_BLOCK_FILE_PHYS)
+ (pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len) >
+ EXT4_MAX_BLOCK_FILE_PHYS))
continue;
/* found preallocated blocks, use them */
@@ -3262,7 +3322,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
while (n) {
entry = rb_entry(n, struct ext4_free_data, node);
- mb_set_bits(bitmap, entry->start_blk, entry->count);
+ ext4_set_bits(bitmap, entry->start_cluster, entry->count);
n = rb_next(n);
}
return;
@@ -3283,7 +3343,6 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
ext4_group_t groupnr;
ext4_grpblk_t start;
int preallocated = 0;
- int count = 0;
int len;
/* all form of preallocation discards first load group,
@@ -3304,9 +3363,8 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
if (unlikely(len == 0))
continue;
BUG_ON(groupnr != group);
- mb_set_bits(bitmap, start, len);
+ ext4_set_bits(bitmap, start, len);
preallocated += len;
- count++;
}
mb_debug(1, "prellocated %u for group %u\n", preallocated, group);
}
@@ -3383,6 +3441,7 @@ static noinline_for_stack int
ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
{
struct super_block *sb = ac->ac_sb;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_prealloc_space *pa;
struct ext4_group_info *grp;
struct ext4_inode_info *ei;
@@ -3414,16 +3473,18 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical;
/* also, we should cover whole original request */
- wins = ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len;
+ wins = EXT4_C2B(sbi, ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len);
/* the smallest one defines real window */
win = min(winl, wins);
- offs = ac->ac_o_ex.fe_logical % ac->ac_b_ex.fe_len;
+ offs = ac->ac_o_ex.fe_logical %
+ EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
if (offs && offs < win)
win = offs;
- ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical - win;
+ ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical -
+ EXT4_B2C(sbi, win);
BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
}
@@ -3448,7 +3509,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
trace_ext4_mb_new_inode_pa(ac, pa);
ext4_mb_use_inode_pa(ac, pa);
- atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated);
+ atomic_add(pa->pa_free, &sbi->s_mb_preallocated);
ei = EXT4_I(ac->ac_inode);
grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group);
@@ -3563,7 +3624,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
BUG_ON(pa->pa_deleted == 0);
ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
- grp_blk_start = pa->pa_pstart - bit;
+ grp_blk_start = pa->pa_pstart - EXT4_C2B(sbi, bit);
BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
end = bit + pa->pa_len;
@@ -3578,16 +3639,18 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
free += next - bit;
trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit);
- trace_ext4_mb_release_inode_pa(pa, grp_blk_start + bit,
+ trace_ext4_mb_release_inode_pa(pa, (grp_blk_start +
+ EXT4_C2B(sbi, bit)),
next - bit);
mb_free_blocks(pa->pa_inode, e4b, bit, next - bit);
bit = next + 1;
}
if (free != pa->pa_free) {
- printk(KERN_CRIT "pa %p: logic %lu, phys. %lu, len %lu\n",
- pa, (unsigned long) pa->pa_lstart,
- (unsigned long) pa->pa_pstart,
- (unsigned long) pa->pa_len);
+ ext4_msg(e4b->bd_sb, KERN_CRIT,
+ "pa %p: logic %lu, phys. %lu, len %lu",
+ pa, (unsigned long) pa->pa_lstart,
+ (unsigned long) pa->pa_pstart,
+ (unsigned long) pa->pa_len);
ext4_grp_locked_error(sb, group, 0, 0, "free %u, pa_free %u",
free, pa->pa_free);
/*
@@ -3660,7 +3723,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
}
if (needed == 0)
- needed = EXT4_BLOCKS_PER_GROUP(sb) + 1;
+ needed = EXT4_CLUSTERS_PER_GROUP(sb) + 1;
INIT_LIST_HEAD(&list);
repeat:
@@ -3775,7 +3838,8 @@ repeat:
* use preallocation while we're discarding it */
spin_unlock(&pa->pa_lock);
spin_unlock(&ei->i_prealloc_lock);
- printk(KERN_ERR "uh-oh! used pa while discarding\n");
+ ext4_msg(sb, KERN_ERR,
+ "uh-oh! used pa while discarding");
WARN_ON(1);
schedule_timeout_uninterruptible(HZ);
goto repeat;
@@ -3852,12 +3916,13 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
(EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED))
return;
- printk(KERN_ERR "EXT4-fs: Can't allocate:"
- " Allocation context details:\n");
- printk(KERN_ERR "EXT4-fs: status %d flags %d\n",
+ ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: Can't allocate:"
+ " Allocation context details:");
+ ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: status %d flags %d",
ac->ac_status, ac->ac_flags);
- printk(KERN_ERR "EXT4-fs: orig %lu/%lu/%lu@%lu, goal %lu/%lu/%lu@%lu, "
- "best %lu/%lu/%lu@%lu cr %d\n",
+ ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: orig %lu/%lu/%lu@%lu, "
+ "goal %lu/%lu/%lu@%lu, "
+ "best %lu/%lu/%lu@%lu cr %d",
(unsigned long)ac->ac_o_ex.fe_group,
(unsigned long)ac->ac_o_ex.fe_start,
(unsigned long)ac->ac_o_ex.fe_len,
@@ -3871,9 +3936,9 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
(unsigned long)ac->ac_b_ex.fe_len,
(unsigned long)ac->ac_b_ex.fe_logical,
(int)ac->ac_criteria);
- printk(KERN_ERR "EXT4-fs: %lu scanned, %d found\n", ac->ac_ex_scanned,
- ac->ac_found);
- printk(KERN_ERR "EXT4-fs: groups: \n");
+ ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: %lu scanned, %d found",
+ ac->ac_ex_scanned, ac->ac_found);
+ ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: groups: ");
ngroups = ext4_get_groups_count(sb);
for (i = 0; i < ngroups; i++) {
struct ext4_group_info *grp = ext4_get_group_info(sb, i);
@@ -3926,7 +3991,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
return;
- size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len;
+ size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len);
isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1)
>> bsbits;
@@ -3937,6 +4002,11 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
return;
}
+ if (sbi->s_mb_group_prealloc <= 0) {
+ ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
+ return;
+ }
+
/* don't use group allocation for large files */
size = max(size, isize);
if (size > sbi->s_mb_stream_request) {
@@ -3975,8 +4045,8 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
len = ar->len;
/* just a dirty hack to filter too big requests */
- if (len >= EXT4_BLOCKS_PER_GROUP(sb) - 10)
- len = EXT4_BLOCKS_PER_GROUP(sb) - 10;
+ if (len >= EXT4_CLUSTERS_PER_GROUP(sb) - 10)
+ len = EXT4_CLUSTERS_PER_GROUP(sb) - 10;
/* start searching from the goal */
goal = ar->goal;
@@ -3987,18 +4057,15 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
/* set up allocation goals */
memset(ac, 0, sizeof(struct ext4_allocation_context));
- ac->ac_b_ex.fe_logical = ar->logical;
+ ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1);
ac->ac_status = AC_STATUS_CONTINUE;
ac->ac_sb = sb;
ac->ac_inode = ar->inode;
- ac->ac_o_ex.fe_logical = ar->logical;
+ ac->ac_o_ex.fe_logical = ac->ac_b_ex.fe_logical;
ac->ac_o_ex.fe_group = group;
ac->ac_o_ex.fe_start = block;
ac->ac_o_ex.fe_len = len;
- ac->ac_g_ex.fe_logical = ar->logical;
- ac->ac_g_ex.fe_group = group;
- ac->ac_g_ex.fe_start = block;
- ac->ac_g_ex.fe_len = len;
+ ac->ac_g_ex = ac->ac_o_ex;
ac->ac_flags = ar->flags;
/* we have to define context: we'll we work with a file or
@@ -4150,13 +4217,14 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
*/
static int ext4_mb_release_context(struct ext4_allocation_context *ac)
{
+ struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
struct ext4_prealloc_space *pa = ac->ac_pa;
if (pa) {
if (pa->pa_type == MB_GROUP_PA) {
/* see comment in ext4_mb_use_group_pa() */
spin_lock(&pa->pa_lock);
- pa->pa_pstart += ac->ac_b_ex.fe_len;
- pa->pa_lstart += ac->ac_b_ex.fe_len;
+ pa->pa_pstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
+ pa->pa_lstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
pa->pa_free -= ac->ac_b_ex.fe_len;
pa->pa_len -= ac->ac_b_ex.fe_len;
spin_unlock(&pa->pa_lock);
@@ -4217,13 +4285,17 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
struct super_block *sb;
ext4_fsblk_t block = 0;
unsigned int inquota = 0;
- unsigned int reserv_blks = 0;
+ unsigned int reserv_clstrs = 0;
sb = ar->inode->i_sb;
sbi = EXT4_SB(sb);
trace_ext4_request_blocks(ar);
+ /* Allow to use superuser reservation for quota file */
+ if (IS_NOQUOTA(ar->inode))
+ ar->flags |= EXT4_MB_USE_ROOT_BLOCKS;
+
/*
* For delayed allocation, we could skip the ENOSPC and
* EDQUOT check, as blocks and quotas have been already
@@ -4237,7 +4309,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
* and verify allocation doesn't exceed the quota limits.
*/
while (ar->len &&
- ext4_claim_free_blocks(sbi, ar->len, ar->flags)) {
+ ext4_claim_free_clusters(sbi, ar->len, ar->flags)) {
/* let others to free the space */
yield();
@@ -4247,12 +4319,14 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
*errp = -ENOSPC;
return 0;
}
- reserv_blks = ar->len;
+ reserv_clstrs = ar->len;
if (ar->flags & EXT4_MB_USE_ROOT_BLOCKS) {
- dquot_alloc_block_nofail(ar->inode, ar->len);
+ dquot_alloc_block_nofail(ar->inode,
+ EXT4_C2B(sbi, ar->len));
} else {
while (ar->len &&
- dquot_alloc_block(ar->inode, ar->len)) {
+ dquot_alloc_block(ar->inode,
+ EXT4_C2B(sbi, ar->len))) {
ar->flags |= EXT4_MB_HINT_NOPREALLOC;
ar->len--;
@@ -4296,7 +4370,7 @@ repeat:
ext4_mb_new_preallocation(ac);
}
if (likely(ac->ac_status == AC_STATUS_FOUND)) {
- *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_blks);
+ *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs);
if (*errp == -EAGAIN) {
/*
* drop the reference that we took
@@ -4332,13 +4406,13 @@ out:
if (ac)
kmem_cache_free(ext4_ac_cachep, ac);
if (inquota && ar->len < inquota)
- dquot_free_block(ar->inode, inquota - ar->len);
+ dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len));
if (!ar->len) {
if (!ext4_test_inode_state(ar->inode,
EXT4_STATE_DELALLOC_RESERVED))
/* release all the reserved blocks if non delalloc */
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
- reserv_blks);
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
+ reserv_clstrs);
}
trace_ext4_allocate_blocks(ar, (unsigned long long)block);
@@ -4356,7 +4430,7 @@ static int can_merge(struct ext4_free_data *entry1,
{
if ((entry1->t_tid == entry2->t_tid) &&
(entry1->group == entry2->group) &&
- ((entry1->start_blk + entry1->count) == entry2->start_blk))
+ ((entry1->start_cluster + entry1->count) == entry2->start_cluster))
return 1;
return 0;
}
@@ -4366,7 +4440,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
struct ext4_free_data *new_entry)
{
ext4_group_t group = e4b->bd_group;
- ext4_grpblk_t block;
+ ext4_grpblk_t cluster;
struct ext4_free_data *entry;
struct ext4_group_info *db = e4b->bd_info;
struct super_block *sb = e4b->bd_sb;
@@ -4379,7 +4453,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
BUG_ON(e4b->bd_buddy_page == NULL);
new_node = &new_entry->node;
- block = new_entry->start_blk;
+ cluster = new_entry->start_cluster;
if (!*n) {
/* first free block exent. We need to
@@ -4393,13 +4467,14 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
while (*n) {
parent = *n;
entry = rb_entry(parent, struct ext4_free_data, node);
- if (block < entry->start_blk)
+ if (cluster < entry->start_cluster)
n = &(*n)->rb_left;
- else if (block >= (entry->start_blk + entry->count))
+ else if (cluster >= (entry->start_cluster + entry->count))
n = &(*n)->rb_right;
else {
ext4_grp_locked_error(sb, group, 0,
- ext4_group_first_block_no(sb, group) + block,
+ ext4_group_first_block_no(sb, group) +
+ EXT4_C2B(sbi, cluster),
"Block already on to-be-freed list");
return 0;
}
@@ -4413,7 +4488,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
if (node) {
entry = rb_entry(node, struct ext4_free_data, node);
if (can_merge(entry, new_entry)) {
- new_entry->start_blk = entry->start_blk;
+ new_entry->start_cluster = entry->start_cluster;
new_entry->count += entry->count;
rb_erase(node, &(db->bb_free_root));
spin_lock(&sbi->s_md_lock);
@@ -4464,6 +4539,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
ext4_group_t block_group;
struct ext4_sb_info *sbi;
struct ext4_buddy e4b;
+ unsigned int count_clusters;
int err = 0;
int ret;
@@ -4512,6 +4588,38 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
if (!ext4_should_writeback_data(inode))
flags |= EXT4_FREE_BLOCKS_METADATA;
+ /*
+ * If the extent to be freed does not begin on a cluster
+ * boundary, we need to deal with partial clusters at the
+ * beginning and end of the extent. Normally we will free
+ * blocks at the beginning or the end unless we are explicitly
+ * requested to avoid doing so.
+ */
+ overflow = block & (sbi->s_cluster_ratio - 1);
+ if (overflow) {
+ if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
+ overflow = sbi->s_cluster_ratio - overflow;
+ block += overflow;
+ if (count > overflow)
+ count -= overflow;
+ else
+ return;
+ } else {
+ block -= overflow;
+ count += overflow;
+ }
+ }
+ overflow = count & (sbi->s_cluster_ratio - 1);
+ if (overflow) {
+ if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
+ if (count > overflow)
+ count -= overflow;
+ else
+ return;
+ } else
+ count += sbi->s_cluster_ratio - overflow;
+ }
+
do_more:
overflow = 0;
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
@@ -4520,10 +4628,12 @@ do_more:
* Check to see if we are freeing blocks across a group
* boundary.
*/
- if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
- overflow = bit + count - EXT4_BLOCKS_PER_GROUP(sb);
+ if (EXT4_C2B(sbi, bit) + count > EXT4_BLOCKS_PER_GROUP(sb)) {
+ overflow = EXT4_C2B(sbi, bit) + count -
+ EXT4_BLOCKS_PER_GROUP(sb);
count -= overflow;
}
+ count_clusters = EXT4_B2C(sbi, count);
bitmap_bh = ext4_read_block_bitmap(sb, block_group);
if (!bitmap_bh) {
err = -EIO;
@@ -4538,9 +4648,9 @@ do_more:
if (in_range(ext4_block_bitmap(sb, gdp), block, count) ||
in_range(ext4_inode_bitmap(sb, gdp), block, count) ||
in_range(block, ext4_inode_table(sb, gdp),
- EXT4_SB(sb)->s_itb_per_group) ||
+ EXT4_SB(sb)->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, gdp),
- EXT4_SB(sb)->s_itb_per_group)) {
+ EXT4_SB(sb)->s_itb_per_group)) {
ext4_error(sb, "Freeing blocks in system zone - "
"Block = %llu, count = %lu", block, count);
@@ -4565,11 +4675,11 @@ do_more:
#ifdef AGGRESSIVE_CHECK
{
int i;
- for (i = 0; i < count; i++)
+ for (i = 0; i < count_clusters; i++)
BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data));
}
#endif
- trace_ext4_mballoc_free(sb, inode, block_group, bit, count);
+ trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters);
err = ext4_mb_load_buddy(sb, block_group, &e4b);
if (err)
@@ -4586,13 +4696,13 @@ do_more:
err = -ENOMEM;
goto error_return;
}
- new_entry->start_blk = bit;
+ new_entry->start_cluster = bit;
new_entry->group = block_group;
- new_entry->count = count;
+ new_entry->count = count_clusters;
new_entry->t_tid = handle->h_transaction->t_tid;
ext4_lock_group(sb, block_group);
- mb_clear_bits(bitmap_bh->b_data, bit, count);
+ mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
ext4_mb_free_metadata(handle, &e4b, new_entry);
} else {
/* need to update group_info->bb_free and bitmap
@@ -4600,25 +4710,29 @@ do_more:
* them with group lock_held
*/
ext4_lock_group(sb, block_group);
- mb_clear_bits(bitmap_bh->b_data, bit, count);
- mb_free_blocks(inode, &e4b, bit, count);
+ mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
+ mb_free_blocks(inode, &e4b, bit, count_clusters);
}
- ret = ext4_free_blks_count(sb, gdp) + count;
- ext4_free_blks_set(sb, gdp, ret);
+ ret = ext4_free_group_clusters(sb, gdp) + count_clusters;
+ ext4_free_group_clusters_set(sb, gdp, ret);
gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
ext4_unlock_group(sb, block_group);
- percpu_counter_add(&sbi->s_freeblocks_counter, count);
+ percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
- atomic_add(count, &sbi->s_flex_groups[flex_group].free_blocks);
+ atomic_add(count_clusters,
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
ext4_mb_unload_buddy(&e4b);
freed += count;
+ if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
+ dquot_free_block(inode, EXT4_C2B(sbi, count_clusters));
+
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -4637,15 +4751,13 @@ do_more:
}
ext4_mark_super_dirty(sb);
error_return:
- if (freed)
- dquot_free_block(inode, freed);
brelse(bitmap_bh);
ext4_std_error(sb, err);
return;
}
/**
- * ext4_add_groupblocks() -- Add given blocks to an existing group
+ * ext4_group_add_blocks() -- Add given blocks to an existing group
* @handle: handle to this transaction
* @sb: super block
* @block: start physcial block to add to the block group
@@ -4653,7 +4765,7 @@ error_return:
*
* This marks the blocks as free in the bitmap and buddy.
*/
-void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
ext4_fsblk_t block, unsigned long count)
{
struct buffer_head *bitmap_bh = NULL;
@@ -4666,25 +4778,35 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
struct ext4_buddy e4b;
int err = 0, ret, blk_free_count;
ext4_grpblk_t blocks_freed;
- struct ext4_group_info *grp;
ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
+ if (count == 0)
+ return 0;
+
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
- grp = ext4_get_group_info(sb, block_group);
/*
* Check to see if we are freeing blocks across a group
* boundary.
*/
- if (bit + count > EXT4_BLOCKS_PER_GROUP(sb))
+ if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
+ ext4_warning(sb, "too much blocks added to group %u\n",
+ block_group);
+ err = -EINVAL;
goto error_return;
+ }
bitmap_bh = ext4_read_block_bitmap(sb, block_group);
- if (!bitmap_bh)
+ if (!bitmap_bh) {
+ err = -EIO;
goto error_return;
+ }
+
desc = ext4_get_group_desc(sb, block_group, &gd_bh);
- if (!desc)
+ if (!desc) {
+ err = -EIO;
goto error_return;
+ }
if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
in_range(ext4_inode_bitmap(sb, desc), block, count) ||
@@ -4694,6 +4816,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
ext4_error(sb, "Adding blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
+ err = -EINVAL;
goto error_return;
}
@@ -4735,16 +4858,17 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
ext4_lock_group(sb, block_group);
mb_clear_bits(bitmap_bh->b_data, bit, count);
mb_free_blocks(NULL, &e4b, bit, count);
- blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
- ext4_free_blks_set(sb, desc, blk_free_count);
+ blk_free_count = blocks_freed + ext4_free_group_clusters(sb, desc);
+ ext4_free_group_clusters_set(sb, desc, blk_free_count);
desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
ext4_unlock_group(sb, block_group);
- percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
+ percpu_counter_add(&sbi->s_freeclusters_counter,
+ EXT4_B2C(sbi, blocks_freed));
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
- atomic_add(blocks_freed,
- &sbi->s_flex_groups[flex_group].free_blocks);
+ atomic_add(EXT4_B2C(sbi, blocks_freed),
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
ext4_mb_unload_buddy(&e4b);
@@ -4762,7 +4886,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
error_return:
brelse(bitmap_bh);
ext4_std_error(sb, err);
- return;
+ return err;
}
/**
@@ -4782,6 +4906,8 @@ static void ext4_trim_extent(struct super_block *sb, int start, int count,
{
struct ext4_free_extent ex;
+ trace_ext4_trim_extent(sb, group, start, count);
+
assert_spin_locked(ext4_group_lock_ptr(sb, group));
ex.fe_start = start;
@@ -4802,7 +4928,7 @@ static void ext4_trim_extent(struct super_block *sb, int start, int count,
/**
* ext4_trim_all_free -- function to trim all free space in alloc. group
* @sb: super block for file system
- * @e4b: ext4 buddy
+ * @group: group to be trimmed
* @start: first group block to examine
* @max: last group block to examine
* @minblocks: minimum extent block count
@@ -4823,10 +4949,12 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ext4_grpblk_t minblocks)
{
void *bitmap;
- ext4_grpblk_t next, count = 0;
+ ext4_grpblk_t next, count = 0, free_count = 0;
struct ext4_buddy e4b;
int ret;
+ trace_ext4_trim_all_free(sb, group, start, max);
+
ret = ext4_mb_load_buddy(sb, group, &e4b);
if (ret) {
ext4_error(sb, "Error in loading buddy "
@@ -4836,6 +4964,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
bitmap = e4b.bd_bitmap;
ext4_lock_group(sb, group);
+ if (EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) &&
+ minblocks >= atomic_read(&EXT4_SB(sb)->s_last_trim_minblks))
+ goto out;
+
start = (e4b.bd_info->bb_first_free > start) ?
e4b.bd_info->bb_first_free : start;
@@ -4850,6 +4982,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
next - start, group, &e4b);
count += next - start;
}
+ free_count += next - start;
start = next + 1;
if (fatal_signal_pending(current)) {
@@ -4863,9 +4996,13 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ext4_lock_group(sb, group);
}
- if ((e4b.bd_info->bb_free - count) < minblocks)
+ if ((e4b.bd_info->bb_free - free_count) < minblocks)
break;
}
+
+ if (!ret)
+ EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info);
+out:
ext4_unlock_group(sb, group);
ext4_mb_unload_buddy(&e4b);
@@ -4892,7 +5029,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
struct ext4_group_info *grp;
ext4_group_t first_group, last_group;
ext4_group_t group, ngroups = ext4_get_groups_count(sb);
- ext4_grpblk_t cnt = 0, first_block, last_block;
+ ext4_grpblk_t cnt = 0, first_cluster, last_cluster;
uint64_t start, len, minlen, trimmed = 0;
ext4_fsblk_t first_data_blk =
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
@@ -4902,8 +5039,10 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
len = range->len >> sb->s_blocksize_bits;
minlen = range->minlen >> sb->s_blocksize_bits;
- if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
+ if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)))
return -EINVAL;
+ if (start + len <= first_data_blk)
+ goto out;
if (start < first_data_blk) {
len -= first_data_blk - start;
start = first_data_blk;
@@ -4911,11 +5050,11 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
/* Determine first and last group to examine based on start and len */
ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start,
- &first_group, &first_block);
+ &first_group, &first_cluster);
ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) (start + len),
- &last_group, &last_block);
+ &last_group, &last_cluster);
last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
- last_block = EXT4_BLOCKS_PER_GROUP(sb);
+ last_cluster = EXT4_CLUSTERS_PER_GROUP(sb);
if (first_group > last_group)
return -EINVAL;
@@ -4935,22 +5074,26 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
* change it for the last group in which case start +
* len < EXT4_BLOCKS_PER_GROUP(sb).
*/
- if (first_block + len < EXT4_BLOCKS_PER_GROUP(sb))
- last_block = first_block + len;
- len -= last_block - first_block;
+ if (first_cluster + len < EXT4_CLUSTERS_PER_GROUP(sb))
+ last_cluster = first_cluster + len;
+ len -= last_cluster - first_cluster;
if (grp->bb_free >= minlen) {
- cnt = ext4_trim_all_free(sb, group, first_block,
- last_block, minlen);
+ cnt = ext4_trim_all_free(sb, group, first_cluster,
+ last_cluster, minlen);
if (cnt < 0) {
ret = cnt;
break;
}
}
trimmed += cnt;
- first_block = 0;
+ first_cluster = 0;
}
range->len = trimmed * sb->s_blocksize;
+ if (!ret)
+ atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen);
+
+out:
return ret;
}
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 20b5e7bfebd1..47705f3285e3 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -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 */
@@ -187,7 +187,6 @@ struct ext4_allocation_context {
__u16 ac_flags; /* allocation hints */
__u8 ac_status;
__u8 ac_criteria;
- __u8 ac_repeats;
__u8 ac_2order; /* if request is to allocate 2^N blocks and
* N > 0, the field stores N, otherwise 0 */
__u8 ac_op; /* operation, for history only */
@@ -217,6 +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
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index b57b98fb44d1..16ac228dbec6 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -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;
}
@@ -507,7 +481,7 @@ int ext4_ext_migrate(struct inode *inode)
* Set the i_nlink to zero so it will be deleted later
* when we drop inode reference.
*/
- tmp_inode->i_nlink = 0;
+ clear_nlink(tmp_inode);
ext4_ext_tree_init(handle, tmp_inode);
ext4_orphan_add(handle, tmp_inode);
@@ -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;
}
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 9bdef3f537c5..7ea4ba4eff2a 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -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)
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index f57455a1b1b2..c5826c623e7a 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -17,7 +17,6 @@
#include <linux/quotaops.h>
#include <linux/slab.h>
#include "ext4_jbd2.h"
-#include "ext4_extents.h"
#include "ext4.h"
/**
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 707d605bf769..aa4c782c9dd7 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -289,7 +289,7 @@ static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_ent
while (len--) printk("%c", *name++);
ext4fs_dirhash(de->name, de->name_len, &h);
printk(":%x.%u ", h.hash,
- ((char *) de - base));
+ (unsigned) ((char *) de - base));
}
space += EXT4_DIR_REC_LEN(de->name_len);
names++;
@@ -922,7 +922,8 @@ restart:
bh = ext4_getblk(NULL, dir, b++, 0, &err);
bh_use[ra_max] = bh;
if (bh)
- ll_rw_block(READ_META, 1, &bh);
+ ll_rw_block(READ | REQ_META | REQ_PRIO,
+ 1, &bh);
}
}
if ((bh = bh_use[ra_ptr++]) == NULL)
@@ -1013,7 +1014,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q
*err = -ENOENT;
errout:
- dxtrace(printk(KERN_DEBUG "%s not found\n", name));
+ dxtrace(printk(KERN_DEBUG "%s not found\n", d_name->name));
dx_release (frames);
return NULL;
}
@@ -1585,7 +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);
@@ -1611,7 +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;
@@ -1693,7 +1694,7 @@ static void ext4_inc_count(handle_t *handle, struct inode *inode)
if (is_dx(inode) && inode->i_nlink > 1) {
/* limit is 16-bit i_links_count */
if (inode->i_nlink >= EXT4_LINK_MAX || inode->i_nlink == 2) {
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
EXT4_SET_RO_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_RO_COMPAT_DIR_NLINK);
}
@@ -1706,9 +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);
}
@@ -1755,7 +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;
@@ -1791,7 +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);
@@ -1831,7 +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;
@@ -1860,9 +1860,9 @@ retry:
de->name_len = 2;
strcpy(de->name, "..");
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
- inode->i_nlink = 2;
+ set_nlink(inode, 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);
@@ -1985,18 +1985,11 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
if (!list_empty(&EXT4_I(inode)->i_orphan))
goto out_unlock;
- /* Orphan handling is only valid for files with data blocks
- * being truncated, or files being unlinked. */
-
- /* @@@ FIXME: Observation from aviro:
- * I think I can trigger J_ASSERT in ext4_orphan_add(). We block
- * here (on s_orphan_lock), so race with ext4_link() which might bump
- * ->i_nlink. For, say it, character device. Not a regular file,
- * not a directory, not a symlink and ->i_nlink > 0.
- *
- * tytso, 4/25/2009: I'm not sure how that could happen;
- * shouldn't the fs core protect us from these sort of
- * unlink()/link() races?
+ /*
+ * Orphan handling is only valid for files with data blocks
+ * being truncated, or files being unlinked. Note that we either
+ * hold i_mutex, or the inode can not be referenced from outside,
+ * so i_nlink should not be bumped due to race
*/
J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
@@ -2220,7 +2213,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
ext4_warning(inode->i_sb,
"Deleting nonexistent file (%lu), %d",
inode->i_ino, inode->i_nlink);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
retval = ext4_delete_entry(handle, dir, de, bh);
if (retval)
@@ -2260,9 +2253,11 @@ static int ext4_symlink(struct inode *dir,
/*
* For non-fast symlinks, we just allocate inode and put it on
* orphan list in the first transaction => we need bitmap,
- * group descriptor, sb, inode block, quota blocks.
+ * group descriptor, sb, inode block, quota blocks, and
+ * possibly selinux xattr blocks.
*/
- credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
+ credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+ EXT4_XATTR_TRANS_BLOCKS;
} else {
/*
* Fast symlink. We have to add entry to directory
@@ -2283,7 +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;
@@ -2534,7 +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;
@@ -2543,7 +2538,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
if (new_inode) {
/* checked empty_dir above, can't have another parent,
* ext4_dec_count() won't work for many-linked dirs */
- new_inode->i_nlink = 0;
+ clear_nlink(new_inode);
} else {
ext4_inc_count(handle, new_dir);
ext4_update_dx_flag(new_dir);
@@ -2590,7 +2585,7 @@ const struct inode_operations ext4_dir_inode_operations = {
.listxattr = ext4_listxattr,
.removexattr = generic_removexattr,
#endif
- .check_acl = ext4_check_acl,
+ .get_acl = ext4_get_acl,
.fiemap = ext4_fiemap,
};
@@ -2602,5 +2597,5 @@ const struct inode_operations ext4_special_inode_operations = {
.listxattr = ext4_listxattr,
.removexattr = generic_removexattr,
#endif
- .check_acl = ext4_check_acl,
+ .get_acl = ext4_get_acl,
};
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 7bb8f76d470a..7ce1d0b19c94 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -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;
}
@@ -140,20 +126,36 @@ 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;
- mutex_lock(&inode->i_mutex);
- 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)) {
+ spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+ goto free;
}
- spin_lock_irqsave(&ei->i_completed_io_lock, flags);
- if (!list_empty(&io->list))
- list_del_init(&io->list);
+ 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.
+ */
+ queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
+ /*
+ * To prevent the ext4-dio-unwritten thread from keeping
+ * requeueing end_io requests and occupying cpu for too long,
+ * yield the cpu if it sees an end_io request that has already
+ * been requeued.
+ */
+ if (io->flag & EXT4_IO_END_QUEUED)
+ yield();
+ io->flag |= EXT4_IO_END_QUEUED;
+ return;
+ }
+ 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);
}
@@ -285,11 +287,7 @@ static int io_submit_init(struct ext4_io_submit *io,
io_end = ext4_init_io_end(inode, GFP_NOFS);
if (!io_end)
return -ENOMEM;
- do {
- bio = bio_alloc(GFP_NOIO, nvecs);
- nvecs >>= 1;
- } while (bio == NULL);
-
+ bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_bdev = bh->b_bdev;
bio->bi_private = io->io_end = io_end;
@@ -339,7 +337,7 @@ submit_and_retry:
(io_end->pages[io_end->num_io_pages-1] != io_page))
goto submit_and_retry;
if (buffer_uninit(bh))
- io->io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ 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));
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 80bbc9c60c24..996780ab4f4e 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -16,6 +16,35 @@
#include "ext4_jbd2.h"
+int ext4_resize_begin(struct super_block *sb)
+{
+ int ret = 0;
+
+ if (!capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+
+ /*
+ * We are not allowed to do online-resizing on a filesystem mounted
+ * with error, because it can destroy the filesystem easily.
+ */
+ if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
+ ext4_warning(sb, "There are errors in the filesystem, "
+ "so online resizing is not allowed\n");
+ return -EPERM;
+ }
+
+ if (test_and_set_bit_lock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags))
+ ret = -EBUSY;
+
+ return ret;
+}
+
+void ext4_resize_end(struct super_block *sb)
+{
+ clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags);
+ smp_mb__after_clear_bit();
+}
+
#define outside(b, first, last) ((b) < (first) || (b) >= (last))
#define inside(b, first, last) ((b) >= (first) && (b) < (last))
@@ -118,10 +147,8 @@ static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
brelse(bh);
bh = ERR_PTR(err);
} else {
- lock_buffer(bh);
memset(bh->b_data, 0, sb->s_blocksize);
set_buffer_uptodate(bh);
- unlock_buffer(bh);
}
return bh;
@@ -132,8 +159,7 @@ static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
* If that fails, restart the transaction & regain write access for the
* buffer head which is used for block_bitmap modifications.
*/
-static int extend_or_restart_transaction(handle_t *handle, int thresh,
- struct buffer_head *bh)
+static int extend_or_restart_transaction(handle_t *handle, int thresh)
{
int err;
@@ -144,9 +170,8 @@ static int extend_or_restart_transaction(handle_t *handle, int thresh,
if (err < 0)
return err;
if (err) {
- if ((err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
- return err;
- if ((err = ext4_journal_get_write_access(handle, bh)))
+ err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA);
+ if (err)
return err;
}
@@ -181,21 +206,7 @@ static int setup_new_group_blocks(struct super_block *sb,
if (IS_ERR(handle))
return PTR_ERR(handle);
- mutex_lock(&sbi->s_resize_lock);
- if (input->group != sbi->s_groups_count) {
- err = -EBUSY;
- goto exit_journal;
- }
-
- if (IS_ERR(bh = bclean(handle, sb, input->block_bitmap))) {
- err = PTR_ERR(bh);
- goto exit_journal;
- }
-
- if (ext4_bg_has_super(sb, input->group)) {
- ext4_debug("mark backup superblock %#04llx (+0)\n", start);
- ext4_set_bit(0, bh->b_data);
- }
+ BUG_ON(input->group != sbi->s_groups_count);
/* Copy all of the GDT blocks into the backup in this group */
for (i = 0, bit = 1, block = start + 1;
@@ -203,29 +214,26 @@ static int setup_new_group_blocks(struct super_block *sb,
struct buffer_head *gdb;
ext4_debug("update backup group %#04llx (+%d)\n", block, bit);
-
- if ((err = extend_or_restart_transaction(handle, 1, bh)))
- goto exit_bh;
+ err = extend_or_restart_transaction(handle, 1);
+ if (err)
+ goto exit_journal;
gdb = sb_getblk(sb, block);
if (!gdb) {
err = -EIO;
- goto exit_bh;
+ goto exit_journal;
}
if ((err = ext4_journal_get_write_access(handle, gdb))) {
brelse(gdb);
- goto exit_bh;
+ goto exit_journal;
}
- lock_buffer(gdb);
memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size);
set_buffer_uptodate(gdb);
- unlock_buffer(gdb);
err = ext4_handle_dirty_metadata(handle, NULL, gdb);
if (unlikely(err)) {
brelse(gdb);
- goto exit_bh;
+ goto exit_journal;
}
- ext4_set_bit(bit, bh->b_data);
brelse(gdb);
}
@@ -235,9 +243,22 @@ static int setup_new_group_blocks(struct super_block *sb,
err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb,
GFP_NOFS);
if (err)
- goto exit_bh;
- for (i = 0, bit = gdblocks + 1; i < reserved_gdb; i++, bit++)
- ext4_set_bit(bit, bh->b_data);
+ goto exit_journal;
+
+ err = extend_or_restart_transaction(handle, 2);
+ if (err)
+ goto exit_journal;
+
+ bh = bclean(handle, sb, input->block_bitmap);
+ if (IS_ERR(bh)) {
+ err = PTR_ERR(bh);
+ goto exit_journal;
+ }
+
+ if (ext4_bg_has_super(sb, input->group)) {
+ ext4_debug("mark backup group tables %#04llx (+0)\n", start);
+ ext4_set_bits(bh->b_data, 0, gdblocks + reserved_gdb + 1);
+ }
ext4_debug("mark block bitmap %#04llx (+%llu)\n", input->block_bitmap,
input->block_bitmap - start);
@@ -253,12 +274,9 @@ static int setup_new_group_blocks(struct super_block *sb,
err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, GFP_NOFS);
if (err)
goto exit_bh;
- for (i = 0, bit = input->inode_table - start;
- i < sbi->s_itb_per_group; i++, bit++)
- ext4_set_bit(bit, bh->b_data);
+ ext4_set_bits(bh->b_data, input->inode_table - start,
+ sbi->s_itb_per_group);
- if ((err = extend_or_restart_transaction(handle, 2, bh)))
- goto exit_bh;
ext4_mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8,
bh->b_data);
@@ -285,7 +303,6 @@ exit_bh:
brelse(bh);
exit_journal:
- mutex_unlock(&sbi->s_resize_lock);
if ((err2 = ext4_journal_stop(handle)) && !err)
err = err2;
@@ -377,15 +394,15 @@ static int verify_reserved_gdb(struct super_block *sb,
* fail once we start modifying the data on disk, because JBD has no rollback.
*/
static int add_new_gdb(handle_t *handle, struct inode *inode,
- struct ext4_new_group_data *input,
- struct buffer_head **primary)
+ ext4_group_t group)
{
struct super_block *sb = inode->i_sb;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
- unsigned long gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
+ unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
ext4_fsblk_t gdblock = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num;
struct buffer_head **o_group_desc, **n_group_desc;
struct buffer_head *dind;
+ struct buffer_head *gdb_bh;
int gdbackups;
struct ext4_iloc iloc;
__le32 *data;
@@ -408,11 +425,12 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
return -EPERM;
}
- *primary = sb_bread(sb, gdblock);
- if (!*primary)
+ gdb_bh = sb_bread(sb, gdblock);
+ if (!gdb_bh)
return -EIO;
- if ((gdbackups = verify_reserved_gdb(sb, *primary)) < 0) {
+ gdbackups = verify_reserved_gdb(sb, gdb_bh);
+ if (gdbackups < 0) {
err = gdbackups;
goto exit_bh;
}
@@ -427,7 +445,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
data = (__le32 *)dind->b_data;
if (le32_to_cpu(data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)]) != gdblock) {
ext4_warning(sb, "new group %u GDT block %llu not reserved",
- input->group, gdblock);
+ group, gdblock);
err = -EINVAL;
goto exit_dind;
}
@@ -436,7 +454,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
if (unlikely(err))
goto exit_dind;
- err = ext4_journal_get_write_access(handle, *primary);
+ err = ext4_journal_get_write_access(handle, gdb_bh);
if (unlikely(err))
goto exit_sbh;
@@ -449,12 +467,13 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
if (unlikely(err))
goto exit_dindj;
- n_group_desc = kmalloc((gdb_num + 1) * sizeof(struct buffer_head *),
- GFP_NOFS);
+ n_group_desc = ext4_kvmalloc((gdb_num + 1) *
+ sizeof(struct buffer_head *),
+ GFP_NOFS);
if (!n_group_desc) {
err = -ENOMEM;
- ext4_warning(sb,
- "not enough memory for %lu groups", gdb_num + 1);
+ ext4_warning(sb, "not enough memory for %lu groups",
+ gdb_num + 1);
goto exit_inode;
}
@@ -475,8 +494,8 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
}
inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
ext4_mark_iloc_dirty(handle, inode, &iloc);
- memset((*primary)->b_data, 0, sb->s_blocksize);
- err = ext4_handle_dirty_metadata(handle, NULL, *primary);
+ memset(gdb_bh->b_data, 0, sb->s_blocksize);
+ err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
if (unlikely(err)) {
ext4_std_error(sb, err);
goto exit_inode;
@@ -486,10 +505,10 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
o_group_desc = EXT4_SB(sb)->s_group_desc;
memcpy(n_group_desc, o_group_desc,
EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
- n_group_desc[gdb_num] = *primary;
+ n_group_desc[gdb_num] = gdb_bh;
EXT4_SB(sb)->s_group_desc = n_group_desc;
EXT4_SB(sb)->s_gdb_count++;
- kfree(o_group_desc);
+ ext4_kvfree(o_group_desc);
le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
@@ -499,6 +518,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
return err;
exit_inode:
+ ext4_kvfree(n_group_desc);
/* ext4_handle_release_buffer(handle, iloc.bh); */
brelse(iloc.bh);
exit_dindj:
@@ -508,7 +528,7 @@ exit_sbh:
exit_dind:
brelse(dind);
exit_bh:
- brelse(*primary);
+ brelse(gdb_bh);
ext4_debug("leaving with error %d\n", err);
return err;
@@ -528,7 +548,7 @@ exit_bh:
* backup GDT blocks are stored in their reserved primary GDT block.
*/
static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
- struct ext4_new_group_data *input)
+ ext4_group_t group)
{
struct super_block *sb = inode->i_sb;
int reserved_gdb =le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks);
@@ -599,7 +619,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
* Finally we can add each of the reserved backup GDT blocks from
* the new group to its reserved primary GDT block.
*/
- blk = input->group * EXT4_BLOCKS_PER_GROUP(sb);
+ blk = group * EXT4_BLOCKS_PER_GROUP(sb);
for (i = 0; i < reserved_gdb; i++) {
int err2;
data = (__le32 *)primary[i]->b_data;
@@ -799,13 +819,6 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
goto exit_put;
}
- mutex_lock(&sbi->s_resize_lock);
- if (input->group != sbi->s_groups_count) {
- ext4_warning(sb, "multiple resizers run on filesystem!");
- err = -EBUSY;
- goto exit_journal;
- }
-
if ((err = ext4_journal_get_write_access(handle, sbi->s_sbh)))
goto exit_journal;
@@ -820,16 +833,25 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
if ((err = ext4_journal_get_write_access(handle, primary)))
goto exit_journal;
- if (reserved_gdb && ext4_bg_num_gdb(sb, input->group) &&
- (err = reserve_backup_gdb(handle, inode, input)))
+ if (reserved_gdb && ext4_bg_num_gdb(sb, input->group)) {
+ err = reserve_backup_gdb(handle, inode, input->group);
+ if (err)
+ goto exit_journal;
+ }
+ } else {
+ /*
+ * Note that we can access new group descriptor block safely
+ * only if add_new_gdb() succeeds.
+ */
+ err = add_new_gdb(handle, inode, input->group);
+ if (err)
goto exit_journal;
- } else if ((err = add_new_gdb(handle, inode, input, &primary)))
- goto exit_journal;
+ primary = sbi->s_group_desc[gdb_num];
+ }
/*
* OK, now we've set up the new group. Time to make it active.
*
- * We do not lock all allocations via s_resize_lock
* so we have to be safe wrt. concurrent accesses the group
* data. So we need to be careful to set all of the relevant
* group descriptor data etc. *before* we enable the group.
@@ -853,7 +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);
@@ -886,13 +908,9 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
*
* The precise rules we use are:
*
- * * Writers of s_groups_count *must* hold s_resize_lock
- * AND
* * Writers must perform a smp_wmb() after updating all dependent
* data and before modifying the groups count
*
- * * Readers must hold s_resize_lock over the access
- * OR
* * Readers must perform an smp_rmb() after reading the groups count
* and before reading any dependent data.
*
@@ -919,8 +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));
@@ -928,8 +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);
}
@@ -937,10 +955,9 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
ext4_handle_dirty_super(handle, sb);
exit_journal:
- mutex_unlock(&sbi->s_resize_lock);
if ((err2 = ext4_journal_stop(handle)) && !err)
err = err2;
- if (!err) {
+ if (!err && primary) {
update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
sizeof(struct ext4_super_block));
update_backups(sb, primary->b_blocknr, primary->b_data,
@@ -969,16 +986,13 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
ext4_grpblk_t add;
struct buffer_head *bh;
handle_t *handle;
- int err;
+ int err, err2;
ext4_group_t group;
- /* We don't need to worry about locking wrt other resizers just
- * yet: we're going to revalidate es->s_blocks_count after
- * taking the s_resize_lock below. */
o_blocks_count = ext4_blocks_count(es);
if (test_opt(sb, DEBUG))
- printk(KERN_DEBUG "EXT4-fs: extending last group from %llu uto %llu blocks\n",
+ printk(KERN_DEBUG "EXT4-fs: extending last group from %llu to %llu blocks\n",
o_blocks_count, n_blocks_count);
if (n_blocks_count == 0 || n_blocks_count == o_blocks_count)
@@ -995,7 +1009,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
if (n_blocks_count < o_blocks_count) {
ext4_warning(sb, "can't shrink FS - resize aborted");
- return -EBUSY;
+ return -EINVAL;
}
/* Handle the remaining blocks in the last group only. */
@@ -1038,32 +1052,25 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
goto exit_put;
}
- mutex_lock(&EXT4_SB(sb)->s_resize_lock);
- if (o_blocks_count != ext4_blocks_count(es)) {
- ext4_warning(sb, "multiple resizers run on filesystem!");
- mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
- ext4_journal_stop(handle);
- err = -EBUSY;
- goto exit_put;
- }
-
if ((err = ext4_journal_get_write_access(handle,
EXT4_SB(sb)->s_sbh))) {
ext4_warning(sb, "error %d on journal write access", err);
- mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
ext4_journal_stop(handle);
goto exit_put;
}
ext4_blocks_count_set(es, o_blocks_count + add);
- mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
/* We add the blocks to the bitmap and set the group need init bit */
- ext4_add_groupblocks(handle, sb, o_blocks_count, add);
+ err = ext4_group_add_blocks(handle, sb, o_blocks_count, add);
ext4_handle_dirty_super(handle, sb);
ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
- if ((err = ext4_journal_stop(handle)))
+ err2 = ext4_journal_stop(handle);
+ if (!err && err2)
+ err = err2;
+
+ if (err)
goto exit_put;
if (test_opt(sb, DEBUG))
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9ea71aa864b3..9953d80145ad 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -45,6 +45,7 @@
#include <linux/freezer.h>
#include "ext4.h"
+#include "ext4_extents.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
@@ -110,6 +111,35 @@ static struct file_system_type ext3_fs_type = {
#define IS_EXT3_SB(sb) (0)
#endif
+void *ext4_kvmalloc(size_t size, gfp_t flags)
+{
+ void *ret;
+
+ ret = kmalloc(size, flags);
+ if (!ret)
+ ret = __vmalloc(size, flags, PAGE_KERNEL);
+ return ret;
+}
+
+void *ext4_kvzalloc(size_t size, gfp_t flags)
+{
+ void *ret;
+
+ ret = kzalloc(size, flags);
+ if (!ret)
+ ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
+ return ret;
+}
+
+void ext4_kvfree(void *ptr)
+{
+ if (is_vmalloc_addr(ptr))
+ vfree(ptr);
+ else
+ kfree(ptr);
+
+}
+
ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
{
@@ -134,8 +164,8 @@ ext4_fsblk_t ext4_inode_table(struct super_block *sb,
(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
}
-__u32 ext4_free_blks_count(struct super_block *sb,
- struct ext4_group_desc *bg)
+__u32 ext4_free_group_clusters(struct super_block *sb,
+ struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_free_blocks_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
@@ -190,8 +220,8 @@ void ext4_inode_table_set(struct super_block *sb,
bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
}
-void ext4_free_blks_set(struct super_block *sb,
- struct ext4_group_desc *bg, __u32 count)
+void ext4_free_group_clusters_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count)
{
bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
@@ -269,6 +299,7 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
journal_t *journal;
handle_t *handle;
+ trace_ext4_journal_start(sb, nblocks, _RET_IP_);
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
@@ -384,6 +415,22 @@ static void save_error_info(struct super_block *sb, const char *func,
ext4_commit_super(sb, 1);
}
+/*
+ * The del_gendisk() function uninitializes the disk-specific data
+ * structures, including the bdi structure, without telling anyone
+ * else. Once this happens, any attempt to call mark_buffer_dirty()
+ * (for example, by ext4_commit_super), will cause a kernel OOPS.
+ * This is a kludge to prevent these oops until we can put in a proper
+ * hook in del_gendisk() to inform the VFS and file system layers.
+ */
+static int block_device_ejected(struct super_block *sb)
+{
+ struct inode *bd_inode = sb->s_bdev->bd_inode;
+ struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info;
+
+ return bdi->dev == NULL;
+}
+
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
@@ -789,15 +836,12 @@ static void ext4_put_super(struct super_block *sb)
for (i = 0; i < sbi->s_gdb_count; i++)
brelse(sbi->s_group_desc[i]);
- kfree(sbi->s_group_desc);
- if (is_vmalloc_addr(sbi->s_flex_groups))
- vfree(sbi->s_flex_groups);
- else
- kfree(sbi->s_flex_groups);
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ ext4_kvfree(sbi->s_group_desc);
+ ext4_kvfree(sbi->s_flex_groups);
+ percpu_counter_destroy(&sbi->s_freeclusters_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+ percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
@@ -892,7 +936,6 @@ static void ext4_i_callback(struct rcu_head *head)
static void ext4_destroy_inode(struct inode *inode)
{
- ext4_ioend_wait(inode);
if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
ext4_msg(inode->i_sb, KERN_ERR,
"Inode %lu (%p): orphan list check failed!",
@@ -1031,8 +1074,6 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
seq_puts(seq, ",nouid32");
if (test_opt(sb, DEBUG) && !(def_mount_opts & EXT4_DEFM_DEBUG))
seq_puts(seq, ",debug");
- if (test_opt(sb, OLDALLOC))
- seq_puts(seq, ",oldalloc");
#ifdef CONFIG_EXT4_FS_XATTR
if (test_opt(sb, XATTR_USER))
seq_puts(seq, ",user_xattr");
@@ -1541,10 +1582,12 @@ static int parse_options(char *options, struct super_block *sb,
set_opt(sb, DEBUG);
break;
case Opt_oldalloc:
- set_opt(sb, OLDALLOC);
+ ext4_msg(sb, KERN_WARNING,
+ "Ignoring deprecated oldalloc option");
break;
case Opt_orlov:
- clear_opt(sb, OLDALLOC);
+ ext4_msg(sb, KERN_WARNING,
+ "Ignoring deprecated orlov option");
break;
#ifdef CONFIG_EXT4_FS_XATTR
case Opt_user_xattr:
@@ -1775,6 +1818,7 @@ set_qf_format:
break;
case Opt_nodelalloc:
clear_opt(sb, DELALLOC);
+ clear_opt2(sb, EXPLICIT_DELALLOC);
break;
case Opt_mblk_io_submit:
set_opt(sb, MBLK_IO_SUBMIT);
@@ -1791,6 +1835,7 @@ set_qf_format:
break;
case Opt_delalloc:
set_opt(sb, DELALLOC);
+ set_opt2(sb, EXPLICIT_DELALLOC);
break;
case Opt_block_validity:
set_opt(sb, BLOCK_VALIDITY);
@@ -1909,7 +1954,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
res = MS_RDONLY;
}
if (read_only)
- return res;
+ goto done;
if (!(sbi->s_mount_state & EXT4_VALID_FS))
ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
"running e2fsck is recommended");
@@ -1940,6 +1985,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, 1);
+done:
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
"bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n",
@@ -1976,15 +2022,11 @@ static int ext4_fill_flex_info(struct super_block *sb)
((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
size = flex_group_count * sizeof(struct flex_groups);
- sbi->s_flex_groups = kzalloc(size, GFP_KERNEL);
+ sbi->s_flex_groups = ext4_kvzalloc(size, GFP_KERNEL);
if (sbi->s_flex_groups == NULL) {
- sbi->s_flex_groups = vzalloc(size);
- if (sbi->s_flex_groups == NULL) {
- ext4_msg(sb, KERN_ERR,
- "not enough memory for %u flex groups",
- flex_group_count);
- goto failed;
- }
+ ext4_msg(sb, KERN_ERR, "not enough memory for %u flex groups",
+ flex_group_count);
+ goto failed;
}
for (i = 0; i < sbi->s_groups_count; i++) {
@@ -1993,8 +2035,8 @@ static int ext4_fill_flex_info(struct super_block *sb)
flex_group = ext4_flex_group(sbi, i);
atomic_add(ext4_free_inodes_count(sb, gdp),
&sbi->s_flex_groups[flex_group].free_inodes);
- atomic_add(ext4_free_blks_count(sb, gdp),
- &sbi->s_flex_groups[flex_group].free_blocks);
+ atomic_add(ext4_free_group_clusters(sb, gdp),
+ &sbi->s_flex_groups[flex_group].free_clusters);
atomic_add(ext4_used_dirs_count(sb, gdp),
&sbi->s_flex_groups[flex_group].used_dirs);
}
@@ -2112,7 +2154,8 @@ static int ext4_check_descriptors(struct super_block *sb,
if (NULL != first_not_zeroed)
*first_not_zeroed = grp;
- ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
+ ext4_free_blocks_count_set(sbi->s_es,
+ EXT4_C2B(sbi, ext4_count_free_clusters(sb)));
sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
return 1;
}
@@ -2383,17 +2426,25 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride);
unsigned long stripe_width =
le32_to_cpu(sbi->s_es->s_raid_stripe_width);
+ int ret;
if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
- return sbi->s_stripe;
-
- if (stripe_width <= sbi->s_blocks_per_group)
- return stripe_width;
+ ret = sbi->s_stripe;
+ else if (stripe_width <= sbi->s_blocks_per_group)
+ ret = stripe_width;
+ else if (stride <= sbi->s_blocks_per_group)
+ ret = stride;
+ else
+ ret = 0;
- if (stride <= sbi->s_blocks_per_group)
- return stride;
+ /*
+ * If the stripe width is 1, this makes no sense and
+ * we set it to 0 to turn off stripe handling code.
+ */
+ if (ret <= 1)
+ ret = 0;
- return 0;
+ return ret;
}
/* sysfs supprt */
@@ -2424,7 +2475,8 @@ static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a,
char *buf)
{
return snprintf(buf, PAGE_SIZE, "%llu\n",
- (s64) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ (s64) EXT4_C2B(sbi,
+ percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
}
static ssize_t session_write_kbytes_show(struct ext4_attr *a,
@@ -2652,6 +2704,13 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
return 0;
}
}
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC) &&
+ !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+ ext4_msg(sb, KERN_ERR,
+ "Can't support bigalloc feature without "
+ "extents feature\n");
+ return 0;
+ }
return 1;
}
@@ -3057,10 +3116,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
char *cp;
const char *descr;
int ret = -ENOMEM;
- int blocksize;
+ int blocksize, clustersize;
unsigned int db_count;
unsigned int i;
- int needs_recovery, has_huge_files;
+ int needs_recovery, has_huge_files, has_bigalloc;
__u64 blocks_count;
int err;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
@@ -3194,6 +3253,33 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
&journal_ioprio, NULL, 0))
goto failed_mount;
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ printk_once(KERN_WARNING "EXT4-fs: Warning: mounting "
+ "with data=journal disables delayed "
+ "allocation and O_DIRECT support!\n");
+ if (test_opt2(sb, EXPLICIT_DELALLOC)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and delalloc");
+ goto failed_mount;
+ }
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and delalloc");
+ goto failed_mount;
+ }
+ if (test_opt(sb, DELALLOC))
+ clear_opt(sb, DELALLOC);
+ }
+
+ blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ if (blocksize < PAGE_SIZE) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "dioread_nolock if block size != PAGE_SIZE");
+ goto failed_mount;
+ }
+ }
+
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
@@ -3235,8 +3321,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY)))
goto failed_mount;
- blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
-
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
blocksize > EXT4_MAX_BLOCK_SIZE) {
ext4_msg(sb, KERN_ERR,
@@ -3339,12 +3423,53 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sb->s_dirt = 1;
}
- if (sbi->s_blocks_per_group > blocksize * 8) {
- ext4_msg(sb, KERN_ERR,
- "#blocks per group too big: %lu",
- sbi->s_blocks_per_group);
- goto failed_mount;
+ /* Handle clustersize */
+ clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size);
+ has_bigalloc = EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC);
+ if (has_bigalloc) {
+ if (clustersize < blocksize) {
+ ext4_msg(sb, KERN_ERR,
+ "cluster size (%d) smaller than "
+ "block size (%d)", clustersize, blocksize);
+ goto failed_mount;
+ }
+ sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
+ le32_to_cpu(es->s_log_block_size);
+ sbi->s_clusters_per_group =
+ le32_to_cpu(es->s_clusters_per_group);
+ if (sbi->s_clusters_per_group > blocksize * 8) {
+ ext4_msg(sb, KERN_ERR,
+ "#clusters per group too big: %lu",
+ sbi->s_clusters_per_group);
+ goto failed_mount;
+ }
+ if (sbi->s_blocks_per_group !=
+ (sbi->s_clusters_per_group * (clustersize / blocksize))) {
+ ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and "
+ "clusters per group (%lu) inconsistent",
+ sbi->s_blocks_per_group,
+ sbi->s_clusters_per_group);
+ goto failed_mount;
+ }
+ } else {
+ if (clustersize != blocksize) {
+ ext4_warning(sb, "fragment/cluster size (%d) != "
+ "block size (%d)", clustersize,
+ blocksize);
+ clustersize = blocksize;
+ }
+ if (sbi->s_blocks_per_group > blocksize * 8) {
+ ext4_msg(sb, KERN_ERR,
+ "#blocks per group too big: %lu",
+ sbi->s_blocks_per_group);
+ goto failed_mount;
+ }
+ sbi->s_clusters_per_group = sbi->s_blocks_per_group;
+ sbi->s_cluster_bits = 0;
}
+ sbi->s_cluster_ratio = clustersize / blocksize;
+
if (sbi->s_inodes_per_group > blocksize * 8) {
ext4_msg(sb, KERN_ERR,
"#inodes per group too big: %lu",
@@ -3408,17 +3533,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
EXT4_DESC_PER_BLOCK(sb);
- sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *),
- GFP_KERNEL);
+ sbi->s_group_desc = ext4_kvmalloc(db_count *
+ sizeof(struct buffer_head *),
+ GFP_KERNEL);
if (sbi->s_group_desc == NULL) {
ext4_msg(sb, KERN_ERR, "not enough memory");
goto failed_mount;
}
-#ifdef CONFIG_PROC_FS
if (ext4_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
-#endif
bgl_lock_init(sbi->s_blockgroup_lock);
@@ -3452,8 +3576,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_err_report.function = print_daily_error_info;
sbi->s_err_report.data = (unsigned long) sb;
- err = percpu_counter_init(&sbi->s_freeblocks_counter,
- ext4_count_free_blocks(sb));
+ err = percpu_counter_init(&sbi->s_freeclusters_counter,
+ ext4_count_free_clusters(sb));
if (!err) {
err = percpu_counter_init(&sbi->s_freeinodes_counter,
ext4_count_free_inodes(sb));
@@ -3463,7 +3587,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
ext4_count_dirs(sb));
}
if (!err) {
- err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+ err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
}
if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
@@ -3491,7 +3615,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
mutex_init(&sbi->s_orphan_lock);
- mutex_init(&sbi->s_resize_lock);
+ sbi->s_resize_flags = 0;
sb->s_root = NULL;
@@ -3578,13 +3702,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
* The journal may have updated the bg summary counts, so we
* need to update the global counters.
*/
- percpu_counter_set(&sbi->s_freeblocks_counter,
- ext4_count_free_blocks(sb));
+ percpu_counter_set(&sbi->s_freeclusters_counter,
+ ext4_count_free_clusters(sb));
percpu_counter_set(&sbi->s_freeinodes_counter,
ext4_count_free_inodes(sb));
percpu_counter_set(&sbi->s_dirs_counter,
ext4_count_dirs(sb));
- percpu_counter_set(&sbi->s_dirtyblocks_counter, 0);
+ percpu_counter_set(&sbi->s_dirtyclusters_counter, 0);
no_journal:
/*
@@ -3648,25 +3772,6 @@ no_journal:
"available");
}
- if (test_opt(sb, DELALLOC) &&
- (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) {
- ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - "
- "requested data journaling mode");
- clear_opt(sb, DELALLOC);
- }
- if (test_opt(sb, DIOREAD_NOLOCK)) {
- if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
- ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
- "option - requested data journaling mode");
- clear_opt(sb, DIOREAD_NOLOCK);
- }
- if (sb->s_blocksize < PAGE_SIZE) {
- ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
- "option - block size is too small");
- clear_opt(sb, DIOREAD_NOLOCK);
- }
- }
-
err = ext4_setup_system_zone(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize system "
@@ -3679,22 +3784,19 @@ no_journal:
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
err);
- goto failed_mount4;
+ goto failed_mount5;
}
err = ext4_register_li_request(sb, first_not_zeroed);
if (err)
- goto failed_mount4;
+ goto failed_mount6;
sbi->s_kobj.kset = ext4_kset;
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
"%s", sb->s_id);
- if (err) {
- ext4_mb_release(sb);
- ext4_ext_release(sb);
- goto failed_mount4;
- };
+ if (err)
+ goto failed_mount7;
EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
ext4_orphan_cleanup(sb, es);
@@ -3728,35 +3830,37 @@ cantfind_ext4:
ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
goto failed_mount;
+failed_mount7:
+ ext4_unregister_li_request(sb);
+failed_mount6:
+ ext4_ext_release(sb);
+failed_mount5:
+ ext4_mb_release(sb);
+ ext4_release_system_zone(sb);
failed_mount4:
iput(root);
sb->s_root = NULL;
ext4_msg(sb, KERN_ERR, "mount failed");
destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
failed_mount_wq:
- ext4_release_system_zone(sb);
if (sbi->s_journal) {
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
failed_mount3:
del_timer(&sbi->s_err_report);
- if (sbi->s_flex_groups) {
- if (is_vmalloc_addr(sbi->s_flex_groups))
- vfree(sbi->s_flex_groups);
- else
- kfree(sbi->s_flex_groups);
- }
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ if (sbi->s_flex_groups)
+ ext4_kvfree(sbi->s_flex_groups);
+ percpu_counter_destroy(&sbi->s_freeclusters_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+ percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
- kfree(sbi->s_group_desc);
+ ext4_kvfree(sbi->s_group_desc);
failed_mount:
if (sbi->s_proc) {
remove_proc_entry(sb->s_id, ext4_proc_root);
@@ -4037,7 +4141,7 @@ static int ext4_commit_super(struct super_block *sb, int sync)
struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
int error = 0;
- if (!sbh)
+ if (!sbh || block_device_ejected(sb))
return error;
if (buffer_write_io_error(sbh)) {
/*
@@ -4073,8 +4177,9 @@ static int ext4_commit_super(struct super_block *sb, int sync)
else
es->s_kbytes_written =
cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
- ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeblocks_counter));
+ ext4_free_blocks_count_set(es,
+ EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
+ &EXT4_SB(sb)->s_freeclusters_counter)));
es->s_free_inodes_count =
cpu_to_le32(percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeinodes_counter));
@@ -4479,16 +4584,34 @@ restore_opts:
return err;
}
+/*
+ * Note: calculating the overhead so we can be compatible with
+ * historical BSD practice is quite difficult in the face of
+ * clusters/bigalloc. This is because multiple metadata blocks from
+ * different block group can end up in the same allocation cluster.
+ * Calculating the exact overhead in the face of clustered allocation
+ * requires either O(all block bitmaps) in memory or O(number of block
+ * groups**2) in time. We will still calculate the superblock for
+ * older file systems --- and if we come across with a bigalloc file
+ * system with zero in s_overhead_clusters the estimate will be close to
+ * correct especially for very large cluster sizes --- but for newer
+ * file systems, it's better to calculate this figure once at mkfs
+ * time, and store it in the superblock. If the superblock value is
+ * present (even for non-bigalloc file systems), we will use it.
+ */
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
+ struct ext4_group_desc *gdp;
u64 fsid;
s64 bfree;
if (test_opt(sb, MINIX_DF)) {
sbi->s_overhead_last = 0;
+ } else if (es->s_overhead_clusters) {
+ sbi->s_overhead_last = le32_to_cpu(es->s_overhead_clusters);
} else if (sbi->s_blocks_last != ext4_blocks_count(es)) {
ext4_group_t i, ngroups = ext4_get_groups_count(sb);
ext4_fsblk_t overhead = 0;
@@ -4503,24 +4626,16 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
* All of the blocks before first_data_block are
* overhead
*/
- overhead = le32_to_cpu(es->s_first_data_block);
+ overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block));
/*
- * Add the overhead attributed to the superblock and
- * block group descriptors. If the sparse superblocks
- * feature is turned on, then not all groups have this.
+ * Add the overhead found in each block group
*/
for (i = 0; i < ngroups; i++) {
- overhead += ext4_bg_has_super(sb, i) +
- ext4_bg_num_gdb(sb, i);
+ gdp = ext4_get_group_desc(sb, i, NULL);
+ overhead += ext4_num_overhead_clusters(sb, i, gdp);
cond_resched();
}
-
- /*
- * Every block group has an inode bitmap, a block
- * bitmap, and an inode table.
- */
- overhead += ngroups * (2 + sbi->s_itb_per_group);
sbi->s_overhead_last = overhead;
smp_wmb();
sbi->s_blocks_last = ext4_blocks_count(es);
@@ -4528,11 +4643,12 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_type = EXT4_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
- buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
- bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
- percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
+ buf->f_blocks = (ext4_blocks_count(es) -
+ EXT4_C2B(sbi, sbi->s_overhead_last));
+ bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) -
+ percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter);
/* prevent underflow in case that few free space is available */
- buf->f_bfree = max_t(s64, bfree, 0);
+ buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0));
buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
if (buf->f_bfree < ext4_r_blocks_count(es))
buf->f_bavail = 0;
@@ -4953,13 +5069,11 @@ static int __init ext4_init_fs(void)
return err;
err = ext4_init_system_zone();
if (err)
- goto out7;
+ goto out6;
ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
if (!ext4_kset)
- goto out6;
- ext4_proc_root = proc_mkdir("fs/ext4", NULL);
- if (!ext4_proc_root)
goto out5;
+ ext4_proc_root = proc_mkdir("fs/ext4", NULL);
err = ext4_init_feat_adverts();
if (err)
@@ -4995,12 +5109,12 @@ out2:
out3:
ext4_exit_feat_adverts();
out4:
- remove_proc_entry("fs/ext4", NULL);
-out5:
+ if (ext4_proc_root)
+ remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
-out6:
+out5:
ext4_exit_system_zone();
-out7:
+out6:
ext4_exit_pageio();
return err;
}
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
new file mode 100644
index 000000000000..011ba6670d99
--- /dev/null
+++ b/fs/ext4/truncate.h
@@ -0,0 +1,43 @@
+/*
+ * linux/fs/ext4/truncate.h
+ *
+ * Common inline functions needed for truncate support
+ */
+
+/*
+ * Truncate blocks that were not used by write. We have to truncate the
+ * pagecache as well so that corresponding buffers get properly unmapped.
+ */
+static inline void ext4_truncate_failed_write(struct inode *inode)
+{
+ truncate_inode_pages(inode->i_mapping, inode->i_size);
+ ext4_truncate(inode);
+}
+
+/*
+ * Work out how many blocks we need to proceed with the next chunk of a
+ * truncate transaction.
+ */
+static inline unsigned long ext4_blocks_for_truncate(struct inode *inode)
+{
+ ext4_lblk_t needed;
+
+ needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9);
+
+ /* Give ourselves just enough room to cope with inodes in which
+ * i_blocks is corrupt: we've seen disk corruptions in the past
+ * which resulted in random data in an inode which looked enough
+ * like a regular file for ext4 to try to delete it. Things
+ * will go a bit crazy if that happens, but at least we should
+ * try not to panic the whole kernel. */
+ if (needed < 2)
+ needed = 2;
+
+ /* But we need to bound the transaction so we don't overflow the
+ * journal. */
+ if (needed > EXT4_MAX_TRANS_DATA)
+ needed = EXT4_MAX_TRANS_DATA;
+
+ return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed;
+}
+
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c757adc97250..93a00d89a220 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -820,8 +820,14 @@ inserted:
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
+ /*
+ * take i_data_sem because we will test
+ * i_delalloc_reserved_flag in ext4_mb_new_blocks
+ */
+ down_read((&EXT4_I(inode)->i_data_sem));
block = ext4_new_meta_blocks(handle, inode, goal, 0,
NULL, &error);
+ up_read((&EXT4_I(inode)->i_data_sem));
if (error)
goto cleanup;
@@ -985,11 +991,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
no_expand = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
- error = ext4_get_inode_loc(inode, &is.iloc);
- if (error)
- goto cleanup;
-
- error = ext4_journal_get_write_access(handle, is.iloc.bh);
+ error = ext4_reserve_inode_write(handle, inode, &is.iloc);
if (error)
goto cleanup;
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index 007c3bfbf094..34e4350dd4d9 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -48,28 +48,32 @@ ext4_xattr_security_set(struct dentry *dentry, const char *name,
name, value, size, flags);
}
-int
-ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir,
- const struct qstr *qstr)
+int ext4_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+ void *fs_info)
{
- int err;
- size_t len;
- void *value;
- char *name;
+ const struct xattr *xattr;
+ handle_t *handle = fs_info;
+ int err = 0;
- err = security_inode_init_security(inode, dir, qstr, &name, &value, &len);
- if (err) {
- if (err == -EOPNOTSUPP)
- return 0;
- return err;
+ for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+ err = ext4_xattr_set_handle(handle, inode,
+ EXT4_XATTR_INDEX_SECURITY,
+ xattr->name, xattr->value,
+ xattr->value_len, 0);
+ if (err < 0)
+ break;
}
- err = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_SECURITY,
- name, value, len, 0);
- kfree(name);
- kfree(value);
return err;
}
+int
+ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir,
+ const struct qstr *qstr)
+{
+ return security_inode_init_security(inode, dir, qstr,
+ &ext4_initxattrs, handle);
+}
+
const struct xattr_handler ext4_xattr_security_handler = {
.prefix = XATTR_SECURITY_PREFIX,
.list = ext4_xattr_security_list,
Powered by cgit, Gruvboxed by Blaster4385.