aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/filesystems/ext4.txt8
-rw-r--r--fs/ext4/balloc.c63
-rw-r--r--fs/ext4/dir.c13
-rw-r--r--fs/ext4/ext4.h34
-rw-r--r--fs/ext4/ext4_extents.h4
-rw-r--r--fs/ext4/ext4_jbd2.h128
-rw-r--r--fs/ext4/extents.c330
-rw-r--r--fs/ext4/fsync.c2
-rw-r--r--fs/ext4/ialloc.c260
-rw-r--r--fs/ext4/inode.c95
-rw-r--r--fs/ext4/mballoc.c342
-rw-r--r--fs/ext4/mballoc.h20
-rw-r--r--fs/ext4/migrate.c2
-rw-r--r--fs/ext4/mmp.c4
-rw-r--r--fs/ext4/namei.c2
-rw-r--r--fs/ext4/page-io.c18
-rw-r--r--fs/ext4/resize.c37
-rw-r--r--fs/ext4/super.c1075
-rw-r--r--fs/ext4/xattr.c25
-rw-r--r--fs/jbd2/checkpoint.c140
-rw-r--r--fs/jbd2/commit.c47
-rw-r--r--fs/jbd2/journal.c361
-rw-r--r--fs/jbd2/recovery.c5
-rw-r--r--fs/jbd2/revoke.c12
-rw-r--r--fs/jbd2/transaction.c48
-rw-r--r--include/linux/fs.h13
-rw-r--r--include/linux/jbd2.h12
-rw-r--r--include/linux/journal-head.h2
-rw-r--r--include/trace/events/jbd2.h29
-rw-r--r--mm/page-writeback.c2
30 files changed, 1522 insertions, 1611 deletions
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 8c10bf375c7..1b7f9acbcbb 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -144,9 +144,6 @@ journal_async_commit Commit block can be written to disk without waiting
mount the device. This will enable 'journal_checksum'
internally.
-journal=update Update the ext4 file system's journal to the current
- format.
-
journal_dev=devnum When the external journal device's major/minor numbers
have changed, this option allows the user to specify
the new journal location. The journal device is
@@ -356,11 +353,6 @@ nouid32 Disables 32-bit UIDs and GIDs. This is for
interoperability with older kernels which only
store and expect 16-bit values.
-resize Allows to resize filesystem to the end of the last
- existing block group, further resize has to be done
- with resize2fs either online, or offline. It can be
- used only with conjunction with remount.
-
block_validity This options allows to enables/disables the in-kernel
noblock_validity facility for tracking filesystem metadata blocks
within internal data structures. This allows multi-
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index f9e2cd8cf71..4bbd07a6fa1 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -336,10 +336,10 @@ err_out:
* Return buffer_head on success or NULL in case of failure.
*/
struct buffer_head *
-ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
+ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
{
struct ext4_group_desc *desc;
- struct buffer_head *bh = NULL;
+ struct buffer_head *bh;
ext4_fsblk_t bitmap_blk;
desc = ext4_get_group_desc(sb, block_group, NULL);
@@ -348,9 +348,9 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
bitmap_blk = ext4_block_bitmap(sb, desc);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
- ext4_error(sb, "Cannot read block bitmap - "
- "block_group = %u, block_bitmap = %llu",
- block_group, bitmap_blk);
+ ext4_error(sb, "Cannot get buffer for block bitmap - "
+ "block_group = %u, block_bitmap = %llu",
+ block_group, bitmap_blk);
return NULL;
}
@@ -382,25 +382,50 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
return bh;
}
/*
- * submit the buffer_head for read. We can
- * safely mark the bitmap as uptodate now.
- * We do it here so the bitmap uptodate bit
- * get set with buffer lock held.
+ * submit the buffer_head for reading
*/
+ set_buffer_new(bh);
trace_ext4_read_block_bitmap_load(sb, block_group);
- set_bitmap_uptodate(bh);
- if (bh_submit_read(bh) < 0) {
- put_bh(bh);
+ bh->b_end_io = ext4_end_bitmap_read;
+ get_bh(bh);
+ submit_bh(READ, bh);
+ return bh;
+}
+
+/* Returns 0 on success, 1 on error */
+int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
+ struct buffer_head *bh)
+{
+ struct ext4_group_desc *desc;
+
+ if (!buffer_new(bh))
+ return 0;
+ desc = ext4_get_group_desc(sb, block_group, NULL);
+ if (!desc)
+ return 1;
+ wait_on_buffer(bh);
+ if (!buffer_uptodate(bh)) {
ext4_error(sb, "Cannot read block bitmap - "
- "block_group = %u, block_bitmap = %llu",
- block_group, bitmap_blk);
- return NULL;
+ "block_group = %u, block_bitmap = %llu",
+ block_group, (unsigned long long) bh->b_blocknr);
+ return 1;
}
+ clear_buffer_new(bh);
+ /* Panic or remount fs read-only if block bitmap is invalid */
ext4_valid_block_bitmap(sb, desc, block_group, bh);
- /*
- * file system mounted not to panic on error,
- * continue with corrupt bitmap
- */
+ return 0;
+}
+
+struct buffer_head *
+ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
+{
+ struct buffer_head *bh;
+
+ bh = ext4_read_block_bitmap_nowait(sb, block_group);
+ if (ext4_wait_block_bitmap(sb, block_group, bh)) {
+ put_bh(bh);
+ return NULL;
+ }
return bh;
}
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 164c56092e5..ad56866d729 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -91,17 +91,17 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
return 0;
if (filp)
- ext4_error_file(filp, function, line, bh ? bh->b_blocknr : 0,
+ ext4_error_file(filp, function, line, bh->b_blocknr,
"bad entry in directory: %s - offset=%u(%u), "
"inode=%u, rec_len=%d, name_len=%d",
- error_msg, (unsigned) (offset%bh->b_size),
+ error_msg, (unsigned) (offset % bh->b_size),
offset, le32_to_cpu(de->inode),
rlen, de->name_len);
else
- ext4_error_inode(dir, function, line, bh ? bh->b_blocknr : 0,
+ ext4_error_inode(dir, function, line, bh->b_blocknr,
"bad entry in directory: %s - offset=%u(%u), "
"inode=%u, rec_len=%d, name_len=%d",
- error_msg, (unsigned) (offset%bh->b_size),
+ error_msg, (unsigned) (offset % bh->b_size),
offset, le32_to_cpu(de->inode),
rlen, de->name_len);
@@ -425,8 +425,9 @@ static int call_filldir(struct file *filp, void *dirent,
sb = inode->i_sb;
if (!fname) {
- printk(KERN_ERR "EXT4-fs: call_filldir: called with "
- "null fname?!?\n");
+ ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: comm %s: "
+ "called with null fname?!?", __func__, __LINE__,
+ inode->i_ino, current->comm);
return 0;
}
curr_pos = hash2pos(fname->hash, fname->minor_hash);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 513004fc3d8..ded731ac8a3 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -53,7 +53,7 @@
printk(KERN_DEBUG f, ## a); \
} while (0)
#else
-#define ext4_debug(f, a...) do {} while (0)
+#define ext4_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
#define EXT4_ERROR_INODE(inode, fmt, a...) \
@@ -184,6 +184,8 @@ struct mpage_da_data {
#define EXT4_IO_END_UNWRITTEN 0x0001
#define EXT4_IO_END_ERROR 0x0002
#define EXT4_IO_END_QUEUED 0x0004
+#define EXT4_IO_END_DIRECT 0x0008
+#define EXT4_IO_END_IN_FSYNC 0x0010
struct ext4_io_page {
struct page *p_page;
@@ -192,18 +194,25 @@ struct ext4_io_page {
#define MAX_IO_PAGES 128
+/*
+ * For converting uninitialized extents on a work queue.
+ *
+ * 'page' is only used from the writepage() path; 'pages' is only used for
+ * buffered writes; they are used to keep page references until conversion
+ * takes place. For AIO/DIO, neither field is filled in.
+ */
typedef struct ext4_io_end {
struct list_head list; /* per-file finished IO list */
struct inode *inode; /* file being written to */
unsigned int flag; /* unwritten or not */
- struct page *page; /* page struct for buffer write */
+ struct page *page; /* for writepage() path */
loff_t offset; /* offset in the file */
ssize_t size; /* size of the extent */
struct work_struct work; /* data work queue */
struct kiocb *iocb; /* iocb struct for AIO */
int result; /* error value for AIO */
- int num_io_pages;
- struct ext4_io_page *pages[MAX_IO_PAGES];
+ int num_io_pages; /* for writepages() */
+ struct ext4_io_page *pages[MAX_IO_PAGES]; /* for writepages() */
} ext4_io_end_t;
struct ext4_io_submit {
@@ -923,6 +932,7 @@ struct ext4_inode_info {
#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
#define EXT4_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */
#define EXT4_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */
+#define EXT4_MOUNT_ERRORS_MASK 0x00070
#define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */
#define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/
#define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */
@@ -941,7 +951,6 @@ struct ext4_inode_info {
#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
-#define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */
#define EXT4_MOUNT_MBLK_IO_SUBMIT 0x4000000 /* multi-block io submits */
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
@@ -1142,6 +1151,7 @@ struct ext4_sb_info {
unsigned int s_mount_opt;
unsigned int s_mount_opt2;
unsigned int s_mount_flags;
+ unsigned int s_def_mount_opt;
ext4_fsblk_t s_sb_block;
uid_t s_resuid;
gid_t s_resgid;
@@ -1420,8 +1430,9 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
#define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200
#define EXT4_FEATURE_INCOMPAT_EA_INODE 0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */
-#define EXT4_FEATURE_INCOMPAT_INLINEDATA 0x2000 /* data in inode */
+#define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM 0x2000 /* use crc32c for bg */
#define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */
+#define EXT4_FEATURE_INCOMPAT_INLINEDATA 0x8000 /* data in inode */
#define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR
#define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
@@ -1794,8 +1805,14 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
ext4_group_t block_group,
struct buffer_head ** bh);
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 struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
+ ext4_group_t block_group);
+extern int ext4_wait_block_bitmap(struct super_block *sb,
+ ext4_group_t block_group,
+ struct buffer_head *bh);
+extern struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
+ ext4_group_t block_group);
extern void ext4_init_block_bitmap(struct super_block *sb,
struct buffer_head *bh,
ext4_group_t group,
@@ -1841,6 +1858,7 @@ extern void ext4_check_inodes_bitmap(struct super_block *);
extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
extern int ext4_init_inode_table(struct super_block *sb,
ext4_group_t group, int barrier);
+extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
/* mballoc.c */
extern long ext4_mb_stats;
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index a52db3a69a3..0f58b86e3a0 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -47,9 +47,9 @@
*/
#define EXT_DEBUG__
#ifdef EXT_DEBUG
-#define ext_debug(a...) printk(a)
+#define ext_debug(fmt, ...) printk(fmt, ##__VA_ARGS__)
#else
-#define ext_debug(a...)
+#define ext_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
/*
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 5802fa1dab1..83b20fcf940 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -104,6 +104,78 @@
#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
+/**
+ * struct ext4_journal_cb_entry - Base structure for callback information.
+ *
+ * This struct is a 'seed' structure for a using with your own callback
+ * structs. If you are using callbacks you must allocate one of these
+ * or another struct of your own definition which has this struct
+ * as it's first element and pass it to ext4_journal_callback_add().
+ */
+struct ext4_journal_cb_entry {
+ /* list information for other callbacks attached to the same handle */
+ struct list_head jce_list;
+
+ /* Function to call with this callback structure */
+ void (*jce_func)(struct super_block *sb,
+ struct ext4_journal_cb_entry *jce, int error);
+
+ /* user data goes here */
+};
+
+/**
+ * ext4_journal_callback_add: add a function to call after transaction commit
+ * @handle: active journal transaction handle to register callback on
+ * @func: callback function to call after the transaction has committed:
+ * @sb: superblock of current filesystem for transaction
+ * @jce: returned journal callback data
+ * @rc: journal state at commit (0 = transaction committed properly)
+ * @jce: journal callback data (internal and function private data struct)
+ *
+ * The registered function will be called in the context of the journal thread
+ * after the transaction for which the handle was created has completed.
+ *
+ * No locks are held when the callback function is called, so it is safe to
+ * call blocking functions from within the callback, but the callback should
+ * not block or run for too long, or the filesystem will be blocked waiting for
+ * the next transaction to commit. No journaling functions can be used, or
+ * there is a risk of deadlock.
+ *
+ * There is no guaranteed calling order of multiple registered callbacks on
+ * the same transaction.
+ */
+static inline void ext4_journal_callback_add(handle_t *handle,
+ void (*func)(struct super_block *sb,
+ struct ext4_journal_cb_entry *jce,
+ int rc),
+ struct ext4_journal_cb_entry *jce)
+{
+ struct ext4_sb_info *sbi =
+ EXT4_SB(handle->h_transaction->t_journal->j_private);
+
+ /* Add the jce to transaction's private list */
+ jce->jce_func = func;
+ spin_lock(&sbi->s_md_lock);
+ list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list);
+ spin_unlock(&sbi->s_md_lock);
+}
+
+/**
+ * ext4_journal_callback_del: delete a registered callback
+ * @handle: active journal transaction handle on which callback was registered
+ * @jce: registered journal callback entry to unregister
+ */
+static inline void ext4_journal_callback_del(handle_t *handle,
+ struct ext4_journal_cb_entry *jce)
+{
+ struct ext4_sb_info *sbi =
+ EXT4_SB(handle->h_transaction->t_journal->j_private);
+
+ spin_lock(&sbi->s_md_lock);
+ list_del_init(&jce->jce_list);
+ spin_unlock(&sbi->s_md_lock);
+}
+
int
ext4_mark_iloc_dirty(handle_t *handle,
struct inode *inode,
@@ -261,43 +333,45 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle,
/* super.c */
int ext4_force_commit(struct super_block *sb);
-static inline int ext4_should_journal_data(struct inode *inode)
+/*
+ * Ext4 inode journal modes
+ */
+#define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */
+#define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */
+#define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */
+
+static inline int ext4_inode_journal_mode(struct inode *inode)
{
if (EXT4_JOURNAL(inode) == NULL)
- return 0;
- if (!S_ISREG(inode->i_mode))
- return 1;
- if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
- return 1;
- if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
- return 1;
- return 0;
+ return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
+ /* We do not support data journalling with delayed allocation */
+ if (!S_ISREG(inode->i_mode) ||
+ test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+ return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
+ if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+ !test_opt(inode->i_sb, DELALLOC))
+ return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+ return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+ return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
+ else
+ BUG();
+}
+
+static inline int ext4_should_journal_data(struct inode *inode)
+{
+ return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE;
}
static inline int ext4_should_order_data(struct inode *inode)
{
- if (EXT4_JOURNAL(inode) == NULL)
- return 0;
- 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_ORDERED_DATA)
- return 1;
- return 0;
+ return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE;
}
static inline int ext4_should_writeback_data(struct inode *inode)
{
- 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)
- return 1;
- return 0;
+ return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
}
/*
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 74f23c292e1..1421938e679 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -44,6 +44,14 @@
#include <trace/events/ext4.h>
+/*
+ * used by extent splitting.
+ */
+#define EXT4_EXT_MAY_ZEROOUT 0x1 /* safe to zeroout if split fails \
+ due to ENOSPC */
+#define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */
+#define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */
+
static int ext4_split_extent(handle_t *handle,
struct inode *inode,
struct ext4_ext_path *path,
@@ -51,6 +59,13 @@ static int ext4_split_extent(handle_t *handle,
int split_flag,
int flags);
+static int ext4_split_extent_at(handle_t *handle,
+ struct inode *inode,
+ struct ext4_ext_path *path,
+ ext4_lblk_t split,
+ int split_flag,
+ int flags);
+
static int ext4_ext_truncate_extend_restart(handle_t *handle,
struct inode *inode,
int needed)
@@ -300,6 +315,8 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
ext4_fsblk_t block = ext4_ext_pblock(ext);
int len = ext4_ext_get_actual_len(ext);
+ if (len == 0)
+ return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
@@ -2308,7 +2325,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
struct ext4_extent *ex;
/* the header must be checked already in ext4_ext_remove_space() */
- ext_debug("truncate since %u in leaf\n", start);
+ ext_debug("truncate since %u in leaf to %u\n", start, end);
if (!path[depth].p_hdr)
path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
eh = path[depth].p_hdr;
@@ -2343,14 +2360,17 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
ext_debug(" border %u:%u\n", a, b);
/* If this extent is beyond the end of the hole, skip it */
- if (end <= ex_ee_block) {
+ if (end < ex_ee_block) {
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
continue;
} else if (b != ex_ee_block + ex_ee_len - 1) {
- EXT4_ERROR_INODE(inode," bad truncate %u:%u\n",
- start, end);
+ EXT4_ERROR_INODE(inode,
+ "can not handle truncate %u:%u "
+ "on extent %u:%u",
+ start, end, ex_ee_block,
+ ex_ee_block + ex_ee_len - 1);
err = -EIO;
goto out;
} else if (a != ex_ee_block) {
@@ -2482,7 +2502,8 @@ 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)
+static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
+ ext4_lblk_t end)
{
struct super_block *sb = inode->i_sb;
int depth = ext_depth(inode);
@@ -2491,7 +2512,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
handle_t *handle;
int i, err;
- ext_debug("truncate since %u\n", start);
+ ext_debug("truncate since %u to %u\n", start, end);
/* probably first extent we're gonna free will be last in block */
handle = ext4_journal_start(inode, depth + 1);
@@ -2504,6 +2525,61 @@ again:
trace_ext4_ext_remove_space(inode, start, depth);
/*
+ * Check if we are removing extents inside the extent tree. If that
+ * is the case, we are going to punch a hole inside the extent tree
+ * so we have to check whether we need to split the extent covering
+ * the last block to remove so we can easily remove the part of it
+ * in ext4_ext_rm_leaf().
+ */
+ if (end < EXT_MAX_BLOCKS - 1) {
+ struct ext4_extent *ex;
+ ext4_lblk_t ee_block;
+
+ /* find extent for this block */
+ path = ext4_ext_find_extent(inode, end, NULL);
+ if (IS_ERR(path)) {
+ ext4_journal_stop(handle);
+ return PTR_ERR(path);
+ }
+ depth = ext_depth(inode);
+ ex = path[depth].p_ext;
+ if (!ex)
+ goto cont;
+
+ ee_block = le32_to_cpu(ex->ee_block);
+
+ /*
+ * See if the last block is inside the extent, if so split
+ * the extent at 'end' block so we can easily remove the
+ * tail of the first part of the split extent in
+ * ext4_ext_rm_leaf().
+ */
+ if (end >= ee_block &&
+ end < ee_block + ext4_ext_get_actual_len(ex) - 1) {
+ int split_flag = 0;
+
+ if (ext4_ext_is_uninitialized(ex))
+ split_flag = EXT4_EXT_MARK_UNINIT1 |
+ EXT4_EXT_MARK_UNINIT2;
+
+ /*
+ * Split the extent in two so that 'end' is the last
+ * block in the first new extent
+ */
+ err = ext4_split_extent_at(handle, inode, path,
+ end + 1, split_flag,
+ EXT4_GET_BLOCKS_PRE_IO |
+ EXT4_GET_BLOCKS_PUNCH_OUT_EXT);
+
+ if (err < 0)
+ goto out;
+ }
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ }
+cont:
+
+ /*
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
*/
@@ -2515,6 +2591,7 @@ again:
}
path[0].p_depth = depth;
path[0].p_hdr = ext_inode_hdr(inode);
+
if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
err = -EIO;
goto out;
@@ -2526,7 +2603,7 @@ again:
/* this is leaf block */
err = ext4_ext_rm_leaf(handle, inode, path,
&partial_cluster, start,
- EXT_MAX_BLOCKS - 1);
+ end);
/* root level has p_bh == NULL, brelse() eats this */
brelse(path[i].p_bh);
path[i].p_bh = NULL;
@@ -2651,17 +2728,17 @@ void ext4_ext_init(struct super_block *sb)
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
#if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS)
- printk(KERN_INFO "EXT4-fs: file extents enabled");
+ printk(KERN_INFO "EXT4-fs: file extents enabled"
#ifdef AGGRESSIVE_TEST
- printk(", aggressive tests");
+ ", aggressive tests"
#endif
#ifdef CHECK_BINSEARCH
- printk(", check binsearch");
+ ", check binsearch"
#endif
#ifdef EXTENTS_STATS
- printk(", stats");
+ ", stats"
#endif
- printk("\n");
+ "\n");
#endif
#ifdef EXTENTS_STATS
spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock);
@@ -2709,14 +2786,6 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
}
/*
- * used by extent splitting.
- */
-#define EXT4_EXT_MAY_ZEROOUT 0x1 /* safe to zeroout if split fails \
- due to ENOSPC */
-#define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */
-#define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */
-
-/*
* ext4_split_extent_at() splits an extent at given block.
*
* @handle: the journal handle
@@ -3224,11 +3293,13 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
depth = ext_depth(inode);
eh = path[depth].p_hdr;
- if (unlikely(!eh->eh_entries)) {
- EXT4_ERROR_INODE(inode, "eh->eh_entries == 0 and "
- "EOFBLOCKS_FL set");
- return -EIO;
- }
+ /*
+ * We're going to remove EOFBLOCKS_FL entirely in future so we
+ * do not care for this case anymore. Simply remove the flag
+ * if there are no extents.
+ */
+ if (unlikely(!eh->eh_entries))
+ goto out;
last_ex = EXT_LAST_EXTENT(eh);
/*
* We should clear the EOFBLOCKS_FL flag if we are writing the
@@ -3252,6 +3323,7 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
for (i = depth-1; i >= 0; i--)
if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr))
return 0;
+out:
ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
return ext4_mark_inode_dirty(handle, inode);
}
@@ -3710,8 +3782,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
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;
ext4_lblk_t cluster_offset;
@@ -3721,8 +3791,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
/* check in cache */
- if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) &&
- ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
+ if (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))
@@ -3790,113 +3859,25 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/* 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);
ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
ee_block, ee_len, newblock);
- if ((flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) == 0) {
- /*
- * Do not put uninitialized extent
- * in the cache
- */
- if (!ext4_ext_is_uninitialized(ex)) {
- ext4_ext_put_in_cache(inode, ee_block,
- ee_len, ee_start);
- goto out;
- }
- ret = ext4_ext_handle_uninitialized_extents(
- handle, inode, map, path, flags,
- allocated, newblock);
- return ret;
- }
-
- /*
- * Punch out the map length, but only to the
- * end of the extent
- */
- punched_out = allocated < map->m_len ?
- allocated : map->m_len;
-
/*
- * Sense extents need to be converted to
- * uninitialized, they must fit in an
- * uninitialized extent
+ * Do not put uninitialized extent
+ * in the cache
*/
- if (punched_out > EXT_UNINIT_MAX_LEN)
- punched_out = EXT_UNINIT_MAX_LEN;
-
- punch_map.m_lblk = map->m_lblk;
- punch_map.m_pblk = newblock;
- punch_map.m_len = punched_out;
- punch_map.m_flags = 0;
-
- /* Check to see if the extent needs to be split */
- if (punch_map.m_len != ee_len ||
- punch_map.m_lblk != ee_block) {
-
- ret = ext4_split_extent(handle, inode,
- path, &punch_map, 0,
- EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
- EXT4_GET_BLOCKS_PRE_IO);
-
- if (ret < 0) {
- err = ret;
- goto out2;
- }
- /*
- * find extent for the block at
- * the start of the hole
- */
- ext4_ext_drop_refs(path);
- kfree(path);
-
- path = ext4_ext_find_extent(inode,
- map->m_lblk, NULL);
- if (IS_ERR(path)) {
- err = PTR_ERR(path);
- path = NULL;
- goto out2;
- }
-
- depth = ext_depth(inode);
- ex = path[depth].p_ext;
- ee_len = ext4_ext_get_actual_len(ex);
- ee_block = le32_to_cpu(ex->ee_block);
- ee_start = ext4_ext_pblock(ex);
-
- }
-
- ext4_ext_mark_uninitialized(ex);
-
- 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);
- }
+ if (!ext4_ext_is_uninitialized(ex)) {
+ ext4_ext_put_in_cache(inode, ee_block,
+ ee_len, ee_start);
+ goto out;
}
-
- goto out2;
+ ret = ext4_ext_handle_uninitialized_extents(
+ handle, inode, map, path, flags,
+ allocated, newblock);
+ return ret;
}
}
@@ -4165,13 +4146,11 @@ out2:
ext4_ext_drop_refs(path);
kfree(path);
}
- 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);
+ newblock, map->m_len, err ? err : allocated);
- return err ? err : result;
+ return err ? err : allocated;
}
void ext4_ext_truncate(struct inode *inode)
@@ -4228,7 +4207,7 @@ 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);
+ err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
/* In a multi-transaction truncate, we only make the final
* transaction synchronous.
@@ -4436,10 +4415,11 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
EXT4_GET_BLOCKS_IO_CONVERT_EXT);