summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/filesystems/ext4.txt24
-rw-r--r--fs/ext4/Kconfig11
-rw-r--r--fs/ext4/balloc.c2
-rw-r--r--fs/ext4/ext4.h91
-rw-r--r--fs/ext4/ext4_extents.h4
-rw-r--r--fs/ext4/ext4_jbd2.c9
-rw-r--r--fs/ext4/extents.c112
-rw-r--r--fs/ext4/fsync.c13
-rw-r--r--fs/ext4/ialloc.c2
-rw-r--r--fs/ext4/inode.c150
-rw-r--r--fs/ext4/ioctl.c7
-rw-r--r--fs/ext4/mballoc.c429
-rw-r--r--fs/ext4/mballoc.h22
-rw-r--r--fs/ext4/migrate.c22
-rw-r--r--fs/ext4/move_extent.c334
-rw-r--r--fs/ext4/namei.c22
-rw-r--r--fs/ext4/resize.c7
-rw-r--r--fs/ext4/super.c155
-rw-r--r--fs/ext4/xattr.c15
-rw-r--r--fs/jbd2/commit.c11
-rw-r--r--fs/jbd2/journal.c6
-rw-r--r--fs/jbd2/transaction.c7
-rw-r--r--include/linux/jbd2.h2
-rw-r--r--include/trace/events/ext4.h142
-rw-r--r--include/trace/events/jbd2.h2
25 files changed, 1000 insertions, 601 deletions
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 7be02ac5fa3..18b5ec8cea4 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -134,15 +134,9 @@ ro Mount filesystem read only. Note that ext4 will
mount options "ro,noload" can be used to prevent
writes to the filesystem.
-journal_checksum Enable checksumming of the journal transactions.
- This will allow the recovery code in e2fsck and the
- kernel to detect corruption in the kernel. It is a
- compatible change and will be ignored by older kernels.
-
journal_async_commit Commit block can be written to disk without waiting
for descriptor blocks. If enabled older kernels cannot
- mount the device. This will enable 'journal_checksum'
- internally.
+ mount the device.
journal=update Update the ext4 file system's journal to the current
format.
@@ -263,10 +257,18 @@ resuid=n The user ID which may use the reserved blocks.
sb=n Use alternate superblock at this location.
-quota
-noquota
-grpquota
-usrquota
+quota These options are ignored by the filesystem. They
+noquota are used only by quota tools to recognize volumes
+grpquota where quota should be turned on. See documentation
+usrquota in the quota-tools package for more details
+ (http://sourceforge.net/projects/linuxquota).
+
+jqfmt=<quota type> These options tell filesystem details about quota
+usrjquota=<file> so that quota information can be properly updated
+grpjquota=<file> during journal replay. They replace the above
+ quota options. See documentation in the quota-tools
+ package for more details
+ (http://sourceforge.net/projects/linuxquota).
bh (*) ext4 associates buffer heads to data pages to
nobh (a) cache disk block mapping information
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 418b6f3b0ae..d5c0ea2e8f2 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -37,7 +37,7 @@ config EXT4DEV_COMPAT
To enable backwards compatibility so that systems that are
still expecting to mount ext4 filesystems using ext4dev,
- chose Y here. This feature will go away by 2.6.31, so
+ choose Y here. This feature will go away by 2.6.31, so
please arrange to get your userspace programs fixed!
config EXT4_FS_XATTR
@@ -77,3 +77,12 @@ config EXT4_FS_SECURITY
If you are not using a security module that requires using
extended attributes for file security labels, say N.
+
+config EXT4_DEBUG
+ bool "EXT4 debugging support"
+ depends on EXT4_FS
+ help
+ Enables run-time debugging support for the ext4 filesystem.
+
+ If you select Y here, then you will be able to turn on debugging
+ with a command such as "echo 1 > /sys/kernel/debug/ext4/mballoc-debug"
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index e2126d70dff..1d0418980f8 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -478,7 +478,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
* new bitmap information
*/
set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
- ext4_mb_update_group_info(grp, blocks_freed);
+ grp->bb_free += blocks_freed;
up_write(&grp->alloc_sem);
/* We dirtied the bitmap block */
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 9714db393ef..e227eea23f0 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -67,27 +67,29 @@ typedef unsigned int ext4_group_t;
/* prefer goal again. length */
-#define EXT4_MB_HINT_MERGE 1
+#define EXT4_MB_HINT_MERGE 0x0001
/* blocks already reserved */
-#define EXT4_MB_HINT_RESERVED 2
+#define EXT4_MB_HINT_RESERVED 0x0002
/* metadata is being allocated */
-#define EXT4_MB_HINT_METADATA 4
+#define EXT4_MB_HINT_METADATA 0x0004
/* first blocks in the file */
-#define EXT4_MB_HINT_FIRST 8
+#define EXT4_MB_HINT_FIRST 0x0008
/* search for the best chunk */
-#define EXT4_MB_HINT_BEST 16
+#define EXT4_MB_HINT_BEST 0x0010
/* data is being allocated */
-#define EXT4_MB_HINT_DATA 32
+#define EXT4_MB_HINT_DATA 0x0020
/* don't preallocate (for tails) */
-#define EXT4_MB_HINT_NOPREALLOC 64
+#define EXT4_MB_HINT_NOPREALLOC 0x0040
/* allocate for locality group */
-#define EXT4_MB_HINT_GROUP_ALLOC 128
+#define EXT4_MB_HINT_GROUP_ALLOC 0x0080
/* allocate goal blocks or none */
-#define EXT4_MB_HINT_GOAL_ONLY 256
+#define EXT4_MB_HINT_GOAL_ONLY 0x0100
/* goal is meaningful */
-#define EXT4_MB_HINT_TRY_GOAL 512
+#define EXT4_MB_HINT_TRY_GOAL 0x0200
/* blocks already pre-reserved by delayed allocation */
-#define EXT4_MB_DELALLOC_RESERVED 1024
+#define EXT4_MB_DELALLOC_RESERVED 0x0400
+/* We are doing stream allocation */
+#define EXT4_MB_STREAM_ALLOC 0x0800
struct ext4_allocation_request {
@@ -112,6 +114,21 @@ struct ext4_allocation_request {
};
/*
+ * For delayed allocation tracking
+ */
+struct mpage_da_data {
+ struct inode *inode;
+ sector_t b_blocknr; /* start block number of extent */
+ size_t b_size; /* size of extent */
+ unsigned long b_state; /* state of the extent */
+ unsigned long first_page, next_page; /* extent of pages */
+ struct writeback_control *wbc;
+ int io_done;
+ int pages_written;
+ int retval;
+};
+
+/*
* Special inodes numbers
*/
#define EXT4_BAD_INO 1 /* Bad blocks inode */
@@ -251,7 +268,6 @@ struct flex_groups {
#define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
#define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */
#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */
-#define EXT4_EXT_MIGRATE 0x00100000 /* Inode is migrating */
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
#define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */
@@ -289,6 +305,7 @@ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
#define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */
#define EXT4_STATE_NO_EXPAND 0x00000008 /* No space for expansion */
#define EXT4_STATE_DA_ALLOC_CLOSE 0x00000010 /* Alloc DA blks on close */
+#define EXT4_STATE_EXT_MIGRATE 0x00000020 /* Inode is migrating */
/* Used to pass group descriptor data when online resize is done */
struct ext4_new_group_input {
@@ -386,6 +403,9 @@ struct ext4_mount_options {
#endif
};
+/* Max physical block we can addres w/o extents */
+#define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF
+
/*
* Structure of an inode on the disk
*/
@@ -456,7 +476,6 @@ struct move_extent {
__u64 len; /* block length to be moved */
__u64 moved_len; /* moved block length */
};
-#define MAX_DEFRAG_SIZE ((1UL<<31) - 1)
#define EXT4_EPOCH_BITS 2
#define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1)
@@ -694,7 +713,6 @@ struct ext4_inode_info {
#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
-#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_DELALLOC 0x8000000 /* Delalloc support */
@@ -841,6 +859,7 @@ struct ext4_sb_info {
unsigned long s_gdb_count; /* Number of group descriptor blocks */
unsigned long s_desc_per_block; /* Number of group descriptors per block */
ext4_group_t s_groups_count; /* Number of groups in the fs */
+ 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 */
loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
@@ -950,6 +969,7 @@ struct ext4_sb_info {
atomic_t s_mb_lost_chunks;
atomic_t s_mb_preallocated;
atomic_t s_mb_discarded;
+ atomic_t s_lock_busy;
/* locality groups */
struct ext4_locality_group *s_locality_groups;
@@ -1340,8 +1360,6 @@ extern void ext4_mb_free_blocks(handle_t *, struct inode *,
ext4_fsblk_t, unsigned long, int, unsigned long *);
extern int ext4_mb_add_groupinfo(struct super_block *sb,
ext4_group_t i, struct ext4_group_desc *desc);
-extern void ext4_mb_update_group_info(struct ext4_group_info *grp,
- ext4_grpblk_t add);
extern int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t);
extern void ext4_mb_put_buddy_cache_lock(struct super_block *,
ext4_group_t, int);
@@ -1367,6 +1385,7 @@ extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
extern int ext4_can_truncate(struct inode *inode);
extern void ext4_truncate(struct inode *);
+extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
extern void ext4_set_inode_flags(struct inode *);
extern void ext4_get_inode_flags(struct ext4_inode_info *);
extern int ext4_alloc_da_blocks(struct inode *inode);
@@ -1575,15 +1594,18 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
struct ext4_group_info {
unsigned long bb_state;
struct rb_root bb_free_root;
- unsigned short bb_first_free;
- unsigned short bb_free;
- unsigned short bb_fragments;
+ ext4_grpblk_t bb_first_free; /* first free block */
+ ext4_grpblk_t bb_free; /* total free blocks */
+ ext4_grpblk_t bb_fragments; /* nr of freespace fragments */
struct list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
void *bb_bitmap;
#endif
struct rw_semaphore alloc_sem;
- unsigned short bb_counters[];
+ ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block
+ * regions, index is order.
+ * bb_counters[3] = 5 means
+ * 5 free 8-block regions. */
};
#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
@@ -1591,15 +1613,42 @@ struct ext4_group_info {
#define EXT4_MB_GRP_NEED_INIT(grp) \
(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
+#define EXT4_MAX_CONTENTION 8
+#define EXT4_CONTENTION_THRESHOLD 2
+
static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
ext4_group_t group)
{
return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
+/*
+ * Returns true if the filesystem is busy enough that attempts to
+ * access the block group locks has run into contention.
+ */
+static inline int ext4_fs_is_busy(struct ext4_sb_info *sbi)
+{
+ return (atomic_read(&sbi->s_lock_busy) > EXT4_CONTENTION_THRESHOLD);
+}
+
static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
{
- spin_lock(ext4_group_lock_ptr(sb, group));
+ spinlock_t *lock = ext4_group_lock_ptr(sb, group);
+ if (spin_trylock(lock))
+ /*
+ * We're able to grab the lock right away, so drop the
+ * lock contention counter.
+ */
+ atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, -1, 0);
+ else {
+ /*
+ * The lock is busy, so bump the contention counter,
+ * and then wait on the spin lock.
+ */
+ atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, 1,
+ EXT4_MAX_CONTENTION);
+ spin_lock(lock);
+ }
}
static inline void ext4_unlock_group(struct super_block *sb,
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 20a84105a10..61652f1d15e 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -43,8 +43,7 @@
#define CHECK_BINSEARCH__
/*
- * If EXT_DEBUG is defined you can use the 'extdebug' mount option
- * to get lots of info about what's going on.
+ * Turn on EXT_DEBUG to get lots of info about extents operations.
*/
#define EXT_DEBUG__
#ifdef EXT_DEBUG
@@ -138,6 +137,7 @@ typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
#define EXT_BREAK 1
#define EXT_REPEAT 2
+/* Maximum logical block in a file; ext4_extent's ee_block is __le32 */
#define EXT_MAX_BLOCK 0xffffffff
/*
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index eb27fd0f2ee..6a9409920de 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -44,7 +44,7 @@ int __ext4_journal_forget(const char *where, handle_t *handle,
handle, err);
}
else
- brelse(bh);
+ bforget(bh);
return err;
}
@@ -60,7 +60,7 @@ int __ext4_journal_revoke(const char *where, handle_t *handle,
handle, err);
}
else
- brelse(bh);
+ bforget(bh);
return err;
}
@@ -89,7 +89,10 @@ int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
ext4_journal_abort_handle(where, __func__, bh,
handle, err);
} else {
- mark_buffer_dirty(bh);
+ if (inode && bh)
+ mark_buffer_dirty_inode(bh, inode);
+ else
+ mark_buffer_dirty(bh);
if (inode && inode_needs_sync(inode)) {
sync_dirty_buffer(bh);
if (buffer_req(bh) && !buffer_uptodate(bh)) {
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 73ebfb44ad7..7a383257792 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -93,7 +93,9 @@ static void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb)
ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
}
-static int ext4_ext_journal_restart(handle_t *handle, int needed)
+static int ext4_ext_truncate_extend_restart(handle_t *handle,
+ struct inode *inode,
+ int needed)
{
int err;
@@ -104,7 +106,14 @@ static int ext4_ext_journal_restart(handle_t *handle, int needed)
err = ext4_journal_extend(handle, needed);
if (err <= 0)
return err;
- return ext4_journal_restart(handle, needed);
+ err = ext4_truncate_restart_trans(handle, inode, needed);
+ /*
+ * We have dropped i_data_sem so someone might have cached again
+ * an extent we are going to truncate.
+ */
+ ext4_ext_invalidate_cache(inode);
+
+ return err;
}
/*
@@ -220,57 +229,65 @@ ext4_ext_new_meta_block(handle_t *handle, struct inode *inode,
return newblock;
}
-static int ext4_ext_space_block(struct inode *inode)
+static inline int ext4_ext_space_block(struct inode *inode, int check)
{
int size;
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 (size > 6)
+ size = 6;
#endif
+ }
return size;
}
-static int ext4_ext_space_block_idx(struct inode *inode)
+static inline int ext4_ext_space_block_idx(struct inode *inode, int check)
{
int size;
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 (size > 5)
+ size = 5;
#endif
+ }
return size;
}
-static int ext4_ext_space_root(struct inode *inode)
+static inline int ext4_ext_space_root(struct inode *inode, int check)
{
int size;
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 (size > 3)
+ size = 3;
#endif
+ }
return size;
}
-static int ext4_ext_space_root_idx(struct inode *inode)
+static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
{
int size;
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 (size > 4)
+ size = 4;
#endif
+ }
return size;
}
@@ -284,9 +301,9 @@ int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks)
int lcap, icap, rcap, leafs, idxs, num;
int newextents = blocks;
- rcap = ext4_ext_space_root_idx(inode);
- lcap = ext4_ext_space_block(inode);
- icap = ext4_ext_space_block_idx(inode);
+ rcap = ext4_ext_space_root_idx(inode, 0);
+ lcap = ext4_ext_space_block(inode, 0);
+ icap = ext4_ext_space_block_idx(inode, 0);
/* number of new leaf blocks needed */
num = leafs = (newextents + lcap - 1) / lcap;
@@ -311,14 +328,14 @@ ext4_ext_max_entries(struct inode *inode, int depth)
if (depth == ext_depth(inode)) {
if (depth == 0)
- max = ext4_ext_space_root(inode);
+ max = ext4_ext_space_root(inode, 1);
else
- max = ext4_ext_space_root_idx(inode);
+ max = ext4_ext_space_root_idx(inode, 1);
} else {
if (depth == 0)
- max = ext4_ext_space_block(inode);
+ max = ext4_ext_space_block(inode, 1);
else
- max = ext4_ext_space_block_idx(inode);
+ max = ext4_ext_space_block_idx(inode, 1);
}
return max;
@@ -437,8 +454,9 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
ext_debug(" %d->%llu", le32_to_cpu(path->p_idx->ei_block),
idx_pblock(path->p_idx));
} else if (path->p_ext) {
- ext_debug(" %d:%d:%llu ",
+ ext_debug(" %d:[%d]%d:%llu ",
le32_to_cpu(path->p_ext->ee_block),
+ ext4_ext_is_uninitialized(path->p_ext),
ext4_ext_get_actual_len(path->p_ext),
ext_pblock(path->p_ext));
} else
@@ -460,8 +478,11 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
eh = path[depth].p_hdr;
ex = EXT_FIRST_EXTENT(eh);
+ ext_debug("Displaying leaf extents for inode %lu\n", inode->i_ino);
+
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
- ext_debug("%d:%d:%llu ", le32_to_cpu(ex->ee_block),
+ ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block),
+ ext4_ext_is_uninitialized(ex),
ext4_ext_get_actual_len(ex), ext_pblock(ex));
}
ext_debug("\n");
@@ -580,9 +601,10 @@ ext4_ext_binsearch(struct inode *inode,
}
path->p_ext = l - 1;
- ext_debug(" -> %d:%llu:%d ",
+ ext_debug(" -> %d:%llu:[%d]%d ",
le32_to_cpu(path->p_ext->ee_block),
ext_pblock(path->p_ext),
+ ext4_ext_is_uninitialized(path->p_ext),
ext4_ext_get_actual_len(path->p_ext));
#ifdef CHECK_BINSEARCH
@@ -612,7 +634,7 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode)
eh->eh_depth = 0;
eh->eh_entries = 0;
eh->eh_magic = EXT4_EXT_MAGIC;
- eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode));
+ eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0));
ext4_mark_inode_dirty(handle, inode);
ext4_ext_invalidate_cache(inode);
return 0;
@@ -837,7 +859,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
neh = ext_block_hdr(bh);
neh->eh_entries = 0;
- neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode));
+ neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0));
neh->eh_magic = EXT4_EXT_MAGIC;
neh->eh_depth = 0;
ex = EXT_FIRST_EXTENT(neh);
@@ -850,9 +872,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
path[depth].p_ext++;
while (path[depth].p_ext <=
EXT_MAX_EXTENT(path[depth].p_hdr)) {
- ext_debug("move %d:%llu:%d in new leaf %llu\n",
+ ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n",
le32_to_cpu(path[depth].p_ext->ee_block),
ext_pblock(path[depth].p_ext),
+ ext4_ext_is_uninitialized(path[depth].p_ext),
ext4_ext_get_actual_len(path[depth].p_ext),
newblock);
/*memmove(ex++, path[depth].p_ext++,
@@ -912,7 +935,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
neh = ext_block_hdr(bh);
neh->eh_entries = cpu_to_le16(1);
neh->eh_magic = EXT4_EXT_MAGIC;
- neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode));
+ neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0));
neh->eh_depth = cpu_to_le16(depth - i);
fidx = EXT_FIRST_INDEX(neh);
fidx->ei_block = border;
@@ -1037,9 +1060,9 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
/* old root could have indexes or leaves
* so calculate e_max right way */
if (ext_depth(inode))
- neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode));
+ neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0));
else
- neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode));
+ neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0));
neh->eh_magic = EXT4_EXT_MAGIC;
set_buffer_uptodate(bh);
unlock_buffer(bh);
@@ -1054,7 +1077,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
goto out;
curp->p_hdr->eh_magic = EXT4_EXT_MAGIC;
- curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode));
+ 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);
@@ -1580,9 +1603,11 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
/* try to insert block into found extent and return */
if (ex && ext4_can_extents_be_merged(inode, ex, newext)) {
- ext_debug("append %d block to %d:%d (from %llu)\n",
+ ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n",
+ ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
+ ext4_ext_is_uninitialized(ex),
ext4_ext_get_actual_len(ex), ext_pblock(ex));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
@@ -1651,9 +1676,10 @@ has_space:
if (!nearex) {
/* there is no extent in this leaf, create first one */
- ext_debug("first extent in the leaf: %d:%llu:%d\n",
+ ext_debug("first extent in the leaf: %d:%llu:[%d]%d\n",
le32_to_cpu(newext->ee_block),
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)
@@ -1663,10 +1689,11 @@ has_space:
len = EXT_MAX_EXTENT(eh) - nearex;
len = (len - 1) * sizeof(struct ext4_extent);
len = len < 0 ? 0 : len;
- ext_debug("insert %d:%llu:%d after: nearest 0x%p, "
+ ext_debug("insert %d:%llu:[%d]%d after: nearest 0x%p, "
"move %d from 0x%p to 0x%p\n",
le32_to_cpu(newext->ee_block),
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);
@@ -1676,10 +1703,11 @@ has_space:
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 before: nearest 0x%p, "
+ 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),
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);
@@ -2094,7 +2122,8 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
else
uninitialized = 0;
- ext_debug("remove ext %lu:%u\n", ex_ee_block, ex_ee_len);
+ ext_debug("remove ext %u:[%d]%d\n", ex_ee_block,
+ uninitialized, ex_ee_len);
path[depth].p_ext = ex;
a = ex_ee_block > start ? ex_ee_block : start;
@@ -2138,7 +2167,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
}
credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
- err = ext4_ext_journal_restart(handle, credits);
+ err = ext4_ext_truncate_extend_restart(handle, inode, credits);
if (err)
goto out;
@@ -2327,7 +2356,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
if (err == 0) {
ext_inode_hdr(inode)->eh_depth = 0;
ext_inode_hdr(inode)->eh_max =
- cpu_to_le16(ext4_ext_space_root(inode));
+ cpu_to_le16(ext4_ext_space_root(inode, 0));
err = ext4_ext_dirty(handle, inode, path);
}
}
@@ -2743,6 +2772,7 @@ insert:
} else if (err)
goto fix_extent_len;
out:
+ ext4_ext_show_leaf(inode, path);
return err ? err : allocated;
fix_extent_len:
@@ -2786,7 +2816,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
struct ext4_allocation_request ar;
__clear_bit(BH_New, &bh_result->b_state);
- ext_debug("blocks %u/%u requested for inode %u\n",
+ ext_debug("blocks %u/%u requested for inode %lu\n",
iblock, max_blocks, inode->i_ino);
/* check in cache */
@@ -2849,7 +2879,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
newblock = iblock - ee_block + ee_start;
/* number of remaining blocks in the extent */
allocated = ee_len - (iblock - ee_block);
- ext_debug("%u fit into %lu:%d -> %llu\n", iblock,
+ ext_debug("%u fit into %u:%d -> %llu\n", iblock,
ee_block, ee_len, newblock);
/* Do not put uninitialized extent in the cache */
@@ -2950,7 +2980,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
newblock = ext4_mb_new_blocks(handle, &ar, &err);
if (!newblock)
goto out2;
- ext_debug("allocate new block: goal %llu, found %llu/%lu\n",
+ ext_debug("allocate new block: goal %llu, found %llu/%u\n",
ar.goal, newblock, allocated);
/* try to insert new extent into found leaf and return */
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 83cf6415f59..07475740b51 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -50,7 +50,7 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
- int ret = 0;
+ int err, ret = 0;
J_ASSERT(ext4_journal_current_handle() == NULL);
@@ -79,6 +79,9 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
goto out;
}
+ if (!journal)
+ ret = sync_mapping_buffers(inode->i_mapping);
+
if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
goto out;
@@ -91,10 +94,12 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 0, /* sys_fsync did this */
};
- ret = sync_inode(inode, &wbc);
- if (journal && (journal->j_flags & JBD2_BARRIER))
- blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
+ err = sync_inode(inode, &wbc);
+ if (ret == 0)
+ ret = err;
}
out:
+ if (journal && (journal->j_flags & JBD2_BARRIER))
+ blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
return ret;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 29e6dc7299b..f3624ead4f6 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1189,7 +1189,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
- i, ext4_free_inodes_count(sb, gdp), x);
+ (unsigned long) i, ext4_free_inodes_count(sb, gdp), x);
bitmap_count += x;
}
brelse(bitmap_bh);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f9c642b22ef..4abd683b963 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -192,11 +192,24 @@ static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
* so before we call here everything must be consistently dirtied against
* this transaction.
*/
-static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
+ int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
+ int nblocks)
{
+ int ret;
+
+ /*
+ * Drop i_data_sem to avoid deadlock with ext4_get_blocks At this
+ * moment, get_block can be called only for blocks inside i_size since
+ * page cache has been already dropped and writes are blocked by
+ * i_mutex. So we can safely drop the i_data_sem here.
+ */
BUG_ON(EXT4_JOURNAL(inode) == NULL);
jbd_debug(2, "restarting handle %p\n", handle);
- return ext4_journal_restart(handle, blocks_for_truncate(inode));
+ up_write(&EXT4_I(inode)->i_data_sem);
+ ret = ext4_journal_restart(handle, blocks_for_truncate(inode));
+ down_write(&EXT4_I(inode)->i_data_sem);
+
+ return ret;
}
/*
@@ -341,9 +354,7 @@ static int ext4_block_to_path(struct inode *inode,
int n = 0;
int final = 0;
- if (i_block < 0) {
- ext4_warning(inode->i_sb, "ext4_block_to_path", "block < 0");
- } else if (i_block < direct_blocks) {
+ if (i_block < direct_blocks) {
offsets[n++] = i_block;
final = direct_blocks;
} else if ((i_block -= direct_blocks) < indirect_blocks) {
@@ -551,15 +562,21 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
*
* 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
*/
- return ext4_find_near(inode, partial);
+ goal = ext4_find_near(inode, partial);
+ goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
+ return goal;
}
/**
@@ -640,6 +657,8 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
if (*err)
goto failed_out;
+ BUG_ON(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS);
+
target -= count;
/* allocate blocks for indirect blocks */
while (index < indirect_blks && count) {
@@ -674,6 +693,7 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
ar.flags = EXT4_MB_HINT_DATA;
current_block = ext4_mb_new_blocks(handle, &ar, err);
+ BUG_ON(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS);
if (*err && (target == blks)) {
/*
@@ -762,8 +782,9 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
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);
- brelse(bh);
goto failed;
}
@@ -1109,16 +1130,15 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
ext4_discard_preallocations(inode);
}
-static int check_block_validity(struct inode *inode, sector_t logical,
- sector_t phys, int len)
+static int check_block_validity(struct inode *inode, const char *msg,
+ sector_t logical, sector_t phys, int len)
{
if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) {
- ext4_error(inode->i_sb, "check_block_validity",
+ ext4_error(inode->i_sb, msg,
"inode #%lu logical block %llu mapped to %llu "
"(size %d)", inode->i_ino,
(unsigned long long) logical,
(unsigned long long) phys, len);
- WARN_ON(1);
return -EIO;
}
return 0;
@@ -1170,8 +1190,8 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
up_read((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && buffer_mapped(bh)) {
- int ret = check_block_validity(inode, block,
- bh->b_blocknr, retval);
+ int ret = check_block_validity(inode, "file system corruption",
+ block, bh->b_blocknr, retval);
if (ret != 0)
return ret;
}
@@ -1235,8 +1255,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
* i_data's format changing. Force the migrate
* to fail by clearing migrate flags
*/
- EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags &
- ~EXT4_EXT_MIGRATE;
+ EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE;
}
}
@@ -1252,8 +1271,9 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && buffer_mapped(bh)) {
- int ret = check_block_validity(inode, block,
- bh->b_blocknr, retval);
+ int ret = check_block_validity(inode, "file system "
+ "corruption after allocation",
+ block, bh->b_blocknr, retval);
if (ret != 0)
return ret;
}
@@ -1863,18 +1883,6 @@ static void ext4_da_page_release_reservation(struct page *page,
* Delayed allocation stuff
*/
-struct mpage_da_data {
- struct inode *inode;
- sector_t b_blocknr; /* start block number of extent */
- size_t b_size; /* size of extent */
- unsigned long b_state; /* state of the extent */
- unsigned long first_page, next_page; /* extent of pages */
- struct writeback_control *wbc;
- int io_done;
- int pages_written;
- int retval;
-};
-
/*
* mpage_da_submit_io - walks through extent of pages and try to write
* them with writepage() call back
@@ -2737,6 +2745,7 @@ static int ext4_da_writepages(struct address_space *mapping,
long pages_skipped;
int range_cyclic, cycled = 1, io_done = 0;
int needed_blocks, ret = 0, nr_to_writebump = 0;
+ loff_t range_start = wbc->range_start;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
trace_ext4_da_writepages(inode, wbc);
@@ -2850,6 +2859,7 @@ retry:
mpd.io_done = 1;
ret = MPAGE_DA_EXTENT_TAIL;
}
+ trace_ext4_da_write_pages(inode, &mpd);
wbc->nr_to_write -= mpd.pages_written;
ext4_journal_stop(handle);
@@ -2905,6 +2915,7 @@ out_writepages:
if (!no_nrwrite_index_update)
wbc->no_nrwrite_index_update = 0;
wbc->nr_to_write -= nr_to_writebump;
+ wbc->range_start = range_start;
trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
return ret;
}
@@ -3117,6 +3128,8 @@ out:
*/
int ext4_alloc_da_blocks(struct inode *inode)
{
+ trace_ext4_alloc_da_blocks(inode);
+
if (!EXT4_I(inode)->i_reserved_data_blocks &&
!EXT4_I(inode)->i_reserved_meta_blocks)
return 0;
@@ -3659,7 +3672,8 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
ext4_handle_dirty_metadata(handle, inode, bh);
}
ext4_mark_inode_dirty(handle, inode);
- ext4_journal_test_restart(handle, inode);
+ ext4_truncate_restart_trans(handle, inode,
+ blocks_for_truncate(inode));
if (bh) {
BUFFER_TRACE(bh, "retaking write access");
ext4_journal_get_write_access(handle, bh);
@@ -3870,7 +3884,8 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
return;
if (try_to_extend_transaction(handle, inode)) {
ext4_mark_inode_dirty(handle, inode);
- ext4_journal_test_restart(handle, inode);
+ ext4_truncate_restart_trans(handle, inode,
+ blocks_for_truncate(inode));
}
ext4_free_blocks(handle, inode, nr, 1, 1);
@@ -3958,8 +3973,7 @@ void ext4_truncate(struct inode *inode)
if (!ext4_can_truncate(inode))
return;
- if (ei->i_disksize && inode->i_size == 0 &&
- !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
+ if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE;
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
@@ -4533,7 +4547,8 @@ static int ext4_inode_blocks_set(handle_t *handle,
*/
static int ext4_do_update_inode(handle_t *handle,
struct inode *inode,
- struct ext4_iloc *iloc)
+ struct ext4_iloc *iloc,
+ int do_sync)
{
struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -4581,8 +4596,7 @@ static int ext4_do_update_inode(handle_t *handle,
if (ext4_inode_blocks_set(handle, raw_inode, ei))
goto out_brelse;
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
- /* clear the migrate flag in the raw_inode */
- raw_inode->i_flags = cpu_to_le32(ei->i_flags & ~EXT4_EXT_MIGRATE);
+ raw_inode->i_flags = cpu_to_le32(ei->i_flags);
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_HURD))
raw_inode->i_file_acl_high =
@@ -4635,10 +4649,22 @@ static int ext4_do_update_inode(handle_t *handle,
raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
}
- BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- rc = ext4_handle_dirty_metadata(handle, inode, bh);
- if (!err)
- err = rc;
+ /*
+ * If we're not using a journal and we were called from
+ * ext4_write_inode() to sync the inode (making do_sync true),
+ * we can just use sync_dirty_buffer() directly to do our dirty
+ * work. Testing s_journal here is a bit redundant but it's
+ * worth it to avoid potential future trouble.
+ */
+ if (EXT4_SB(inode->i_sb)->s_journal == NULL && do_sync) {
+ BUFFER_TRACE(bh, "call sync_dirty_buffer");
+ sync_dirty_buffer(bh);
+ } else {
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ rc = ext4_handle_dirty_metadata(handle, inode, bh);
+ if (!err)
+ err = rc;
+ }
ei->i_state &= ~EXT4_STATE_NEW;
out_brelse:
@@ -4684,19 +4710,32 @@ out_brelse:
*/
int ext4_write_inode(struct inode *inode, int wait)
{
+ int err;
+
if (current->flags & PF_MEMALLOC)
return 0;
- if (ext4_journal_current_handle()) {
- jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n");
- dump_stack();
- return -EIO;
- }
+ if (EXT4_SB(inode->i_sb)->s_journal) {
+ if (ext4_journal_current_handle()) {
+ jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n");
+ dump_stack();
+ return -EIO;
+ }
- if (!wait)
- return 0;
+ if (!wait)
+ return 0;
+
+ err = ext4_force_commit(inode->i_sb);
+ } else {
+ struct ext4_iloc iloc;
- return ext4_force_commit(inode->i_sb);
+ err = ext4_get_inode_loc(inode, &iloc);
+ if (err)
+ return err;
+ err = ext4_do_update_inode(EXT4_NOJOURNAL_HANDLE,
+ inode, &iloc, wait);
+ }
+ return err;
}
/*
@@ -4990,7 +5029,7 @@ int ext4_mark_iloc_dirty(handle_t *handle,
get_bh(iloc->bh);
/* ext4_do_update_inode() does jbd2_journal_dirty_metadata */
- err = ext4_do_update_inode(handle, inode, iloc);
+ err = ext4_do_update_inode(handle, inode, iloc, 0);
put_bh(iloc->bh);
return err;
}
@@ -5281,12 +5320,21 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
else
len = PAGE_CACHE_SIZE;
+ lock_page(page);
+ /*
+ * return if we have all the buffers mapped. This avoid
+ * the need to call write_begin/write_end which does a
+ * journal_start/journal_stop which can block and take
+ * long time
+ */
if (page_has_buffers(page)) {
- /* return if we have all the buffers mapped */
if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
- ext4_bh_unmapped))
+ ext4_bh_unmapped)) {
+ unlock_page(page);
goto out_unlock;
+ }
}
+ unlock_page(page);
/*
* OK, we need to fill the hole... Do write_begin write_end
* to do block allocation/reservation.We are not holding
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 7050a9cd04a..c1cdf613e72 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -243,10 +243,9 @@ setversion_out:
me.donor_start, me.len, &me.moved_len);
fput(donor_filp);
- if (!err)
- if (copy_to_user((struct move_extent *)arg,
- &me, sizeof(me)))
- return -EFAULT;
+ if (copy_to_user((struct move_extent *)arg, &me, sizeof(me)))
+ return -EFAULT;
+
return err;
}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index cd258463e2a..e9c61896d60 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -22,6 +22,7 @@
*/
#include "mballoc.h"
+#include <linux/debugfs.h>
#include <trace/events/ext4.h>
/*
@@ -622,13 +623,13 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
/* FIXME!! need more doc */
static void ext4_mb_mark_free_simple(struct super_block *sb,
- void *buddy, unsigned first, int len,
+ void *buddy, ext4_grpblk_t first, ext4_grpblk_t len,
struct ext4_group_info *grp)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- unsigned short min;
- unsigned short max;
- unsigned short chunk;
+ ext4_grpblk_t min;
+ ext4_grpblk_t max;
+ ext4_grpblk_t chunk;
unsigned short border;
BUG_ON(len > EXT4_BLOCKS_PER_GROUP(sb));
@@ -662,10 +663,10 @@ 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);
- unsigned short max = EXT4_BLOCKS_PER_GROUP(sb);
- unsigned short i = 0;
- unsigned short first;
- unsigned short len;
+ ext4_grpblk_t max = EXT4_BLOCKS_PER_GROUP(sb);
+ ext4_grpblk_t i = 0;
+ ext4_grpblk_t first;
+ ext4_grpblk_t len;
unsigned free = 0;
unsigned fragments = 0;
unsigned long long period = get_cycles();
@@ -743,7 +744,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
char *data;
char *bitmap;
- mb_debug("init page %lu\n", page->index);
+ mb_debug(1, "init page %lu\n", page->index);
inode = page->mapping->host;
sb = inode->i_sb;
@@ -822,7 +823,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
set_bitmap_uptodate(bh[i]);
bh[i]->b_end_io = end_buffer_read_sync;
submit_bh(READ, bh[i]);
- mb_debug("read bitmap for group %u\n", first_group + i);
+ mb_debug(1, "read bitmap for group %u\n", first_group + i);
}
/* wait for I/O completion */
@@ -862,12 +863,13 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
if ((first_block + i) & 1) {
/* this is block of buddy */
BUG_ON(incore == NULL);
- mb_debug("put buddy for group %u in page %lu/%x\n",
+ mb_debug(1, "put buddy for group %u in page %lu/%x\n",
group, page->index, i * blocksize);
grinfo = ext4_get_group_info(sb, group);
grinfo->bb_fragments = 0;
memset(grinfo->bb_counters, 0,
- sizeof(unsigned short)*(sb->s_blocksize_bits+2));
+ sizeof(*grinfo->bb_counters) *
+ (sb->s_blocksize_bits+2));
/*
* incore got set to the group block bitmap below
*/
@@ -878,7 +880,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
} else {
/* this is block of bitmap */
BUG_ON(incore != NULL);
- mb_debug("put bitmap for group %u in page %lu/%x\n",
+ mb_debug(1, "put bitmap for group %u in page %lu/%x\n",
group, page->index, i * blocksize);
/* see comments in ext4_mb_put_pa() */
@@ -908,6 +910,100 @@ out:
return err;
}
+static noinline_for_stack
+int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
+{
+
+ int ret = 0;
+ void *bitmap;
+ int blocks_per_page;
+ int block, pnum, poff;
+ int num_grp_locked = 0;
+ struct ext4_group_info *this_grp;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct inode *inode = sbi->s_buddy_cache;
+ struct page *page = NULL, *bitmap_page = NULL;
+
+ mb_debug(1, "init group %u\n", group);
+ blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+ this_grp = ext4_get_group_info(sb, group);
+ /*
+ * This ensures that we don't reinit the buddy cache
+ * page which map to the group from which we are already
+ * allocating. If we are looking at the buddy cache we would
+ * have taken a reference using ext4_mb_load_buddy and that
+ * would have taken the alloc_sem lock.
+ */
+ num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, group);
+ if (!EXT4_MB_GRP_NEED_INIT(this_grp)) {
+ /*
+ * somebody initialized the group
+ * return without doing anything
+ */
+ ret = 0;
+ goto err;
+ }
+ /*
+ * the buddy cache inode stores the block bitmap
+ * and buddy information in consecutive blocks.
+ * So for each group we need two blocks.
+ */
+ block = group * 2;
+ pnum = block / blocks_per_page;
+ poff = block % blocks_per_page;
+ page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+ if (page) {
+ BUG_ON(page->mapping != inode->i_mapping);
+ ret = ext4_mb_init_cache(page, NULL);
+ if (ret) {
+ unlock_page(page);
+ goto err;
+ }
+ unlock_page(page);
+ }
+ if (page == NULL || !PageUptodate(page)) {
+ ret = -EIO;
+ goto err;
+ }
+ mark_page_accessed(page);
+ bitmap_page = page;
+ bitmap = page_address(page) + (poff * sb->s_blocksize);
+
+ /* init buddy cache */
+ block++;
+ pnum = block / blocks_per_page;
+ poff = block % blocks_per_page;
+ page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+ if (page == bitmap_page) {
+ /*
+ * If both the bitmap and buddy are in
+ * the same page we don't need to force
+ * init the buddy
+ */
+ unlock_page(page);
+ } else if (page) {
+ BUG_ON(page->mapping != inode->i_mapping);
+ ret = ext4_mb_init_cache(page, bitmap);
+ if (ret) {
+ unlock_page(page);
+ goto err;
+ }
+ unlock_page(page);
+ }
+ if (page == NULL || !PageUptodate(page)) {
+ ret = -EIO;
+ goto err;
+ }
+ mark_page_accessed(page);
+err:
+ ext4_mb_put_buddy_cache_lock(sb, group, num_grp_locked);
+ if (bitmap_page)
+ page_cache_release(bitmap_page);
+ if (page)
+ page_cache_release(page);
+ return ret;
+}
+
static noinline_for_stack int
ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
struct ext4_buddy *e4b)
@@ -922,7 +1018,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct inode *inode = sbi->s_buddy_cache;
- mb_debug("load group %u\n", group);
+ mb_debug(1, "load group %u\n", group);
blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
grp = ext4_get_group_info(sb, group);
@@ -941,8 +1037,26 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
* groups mapped by the page is blocked
* till we are done with allocation
*/
+repeat_load_buddy:
down_read(e4b->alloc_semp);
+ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
+ /* we need to check for group need init flag
+ * with alloc_semp held so that we can be sure
+ * that new blocks didn't get added to the group
+ * when we are loading the buddy cache
+ */
+ up_read(e4b->alloc_semp);
+ /*
+ * we need full data about the group
+ * to make a good selection
+ */
+ ret = ext4_mb_init_group(sb, group);
+ if (ret)
+ return ret;
+ goto repeat_load_buddy;
+ }
+
/*
* the buddy cache inode stores the block bitmap
* and buddy information in consecutive blocks.
@@ -1360,7 +1474,7 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac,
ac->alloc_semp = e4b->alloc_semp;
e4b->alloc_semp = NULL;
/* store last allocated for subsequent stream allocation */
- if ((ac->ac_flags & EXT4_MB_HINT_DATA)) {
+ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) {
spin_lock(&sbi->s_md_lock);
sbi->s_mb_last_group = ac->ac_f_ex.fe_group;
sbi->s_mb_last_start = ac->ac_f_ex.fe_start;
@@ -1837,97 +1951,6 @@ void ext4_mb_put_buddy_cache_lock(struct super_block *sb,
}
-static noinline_for_stack
-int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
-{
-
- int ret;
- void *bitmap;
- int blocks_per_page;
- int block, pnum, poff;
- int num_grp_locked = 0;
- struct ext4_group_info *this_grp;
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct inode *inode = sbi->s_buddy_cache;
- struct page *page = NULL, *bitmap_page = NULL;
-
- mb_debug("init group %lu\n", group);
- blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
- this_grp = ext4_get_group_info(sb, group);
- /*
- * This ensures we don't add group
- * to this buddy cache via resize
- */
- num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, group);
- if (!EXT4_MB_GRP_NEED_INIT(this_grp)) {
- /*
- * somebody initialized the group
- * return without doing anything
- */
- ret = 0;
- goto err;
- }
- /*
- * the buddy cache inode stores the block bitmap
- * and buddy information in consecutive blocks.
- * So for each group we need two blocks.
- */
- block = group * 2;
- pnum = block / blocks_per_page;
- poff = block % blocks_per_page;
- page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
- if (page) {
- BUG_ON(page->mapping != inode->i_mapping);
- ret = ext4_mb_init_cache(page, NULL);
- if (ret) {
- unlock_page(page);
- goto err;
- }
- unlock_page(page);
- }
- if (page == NULL || !PageUptodate(page)) {
- ret = -EIO;
- goto err;
- }
- mark_page_accessed(page);
- bitmap_page = page;
- bitmap = page_address(page) + (poff * sb->s_blocksize);
-
- /* init buddy cache */
- block++;
- pnum = block / blocks_per_page;
- poff = block % blocks_per_page;
- page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
- if (page == bitmap_page) {
- /*
- * If both the bitmap and buddy are in
- * the same page we don't need to force
- * init the buddy
- */
- unlock_page(page);
- } else if (page) {
- BUG_ON(page->mapping != inode->i_mapping);
- ret = ext4_mb_init_cache(page, bitmap);
- if (ret) {
- unlock_page(page);
- goto err;
- }
- unlock_page(page);
- }
- if (page == NULL || !PageUptodate(page)) {
- ret = -EIO;
- goto err;
- }
- mark_page_accessed(page);
-err:
- ext4_mb_put_buddy_cache_lock(sb, group, num_grp_locked);
- if (bitmap_page)
- page_cache_release(bitmap_page);
- if (page)
- page_cache_release(page);
- return ret;
-}
-
static noinline_for_stack int
ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
{
@@ -1938,11 +1961,14 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
struct ext4_sb_info *sbi;
struct super_block *sb;
struct ext4_buddy e4b;
- loff_t size, isize;
sb = ac->ac_sb;
sbi = EXT4_SB(sb);
ngroups = ext4_get_groups_count(sb);
+ /* non-extent files are limited to low blocks/groups */
+ if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL))
+ ngroups = sbi->s_blockfile_groups;
+
BUG_ON(ac->ac_status == AC_STATUS_FOUND);
/* first, try the goal */
@@ -1974,20 +2000,16 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
}
bsbits = ac->ac_sb->s_blocksize_bits;
- /* if stream allocation is enabled, use global goal */
- size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len;
- isize = i_size_read(ac->ac_inode) >> bsbits;
- if (size < isize)
- size = isize;
- if (size < sbi->s_mb_stream_request &&
- (ac->ac_flags & EXT4_MB_HINT_DATA)) {
+ /* if stream allocation is enabled, use global goal */
+ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) {
/* TBD: may be hot point */
spin_lock(&sbi->s_md_lock);
ac->ac_g_ex.fe_group = sbi->s_mb_last_group;
ac->ac_g_ex.fe_start = sbi->s_mb_last_start;
spin_unlock(&sbi->s_md_lock);
}
+
/* Let's just scan groups to find more-less suitable blocks */
cr = ac->ac_2order ? 0 : 1;
/*
@@ -2015,27 +2037,6 @@ repeat:
if (grp->bb_free == 0)
continue;
- /*
- * if the group is already init we check whether it is
- * a good group and if not we don't load the buddy
- */
- if (EXT4_MB_GRP_NEED_INIT(grp)) {
- /*
- * we need full data about the group
- * to make a good selection
- */
- err = ext4_mb_init_group(sb, group);
- if (err)
- goto out;
- }
-
- /*
- * If the particular group doesn't satisfy our
- * criteria we continue with the next group
- */
- if (!ext4_mb_good_group(ac, group, cr))
- continue;
-
err = ext4_mb_load_buddy(sb, group, &e4b);
if (err)
goto out;
@@ -2156,7 +2157,7 @@ static int ext4_mb_seq_history_show(struct seq_file *seq, void *v)
if (v == SEQ_START_TOKEN) {
seq_printf(seq, "%-5s %-8s %-23s %-23s %-23s %-5s "
- "%-5s %-2s %-5s %-5s %-5s %-6s\n",
+ "%-5s %-2s %-6s %-5s %-5s %-6s\n",
"pid", "inode", "original", "goal", "result", "found",
"grps", "cr", "flags", "merge", "tail", "broken");
return 0;
@@ -2164,7 +2165,7 @@ static int ext4_mb_seq_history_show(struct seq_file *seq, void *v)
if (hs->op == EXT4_MB_HISTORY_ALLOC) {
fmt = "%-5u %-8u %-23s %-23s %-23s %-5u %-5u %-2u "
- "%-5u %-5s %-5u %-6u\n";
+ "0x%04x %-5s %-5u %-6u\n";
sprintf(buf2, "%u/%d/%u@%u", hs->result.fe_group,
hs->result.fe_start, hs->result.fe_len,
hs->result.fe_logical);
@@ -2205,7 +2206,7 @@ static void ext4_mb_seq_history_stop(struct seq_file *seq, void *v)
{
}
-static struct seq_operations ext4_mb_seq_history_ops = {
+static const struct seq_operations ext4_mb_seq_history_ops = {
.start = ext4_mb_seq_history_start,
.next = ext4_mb_seq_history_next,
.stop = ext4_mb_seq_history_stop,
@@ -2287,7 +2288,7 @@ static ssize_t ext4_mb_seq_history_write(struct file *file,
return count;
}
-static struct file_operations ext4_mb_seq_history_fops = {
+static const struct file_operations ext4_mb_seq_history_fops = {
.owner = THIS_MODULE,
.open = ext4_mb_seq_history_open,
.read = seq_read,
@@ -2328,7 +2329,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
struct ext4_buddy e4b;
struct sg {
struct ext4_group_info info;
- unsigned short counters[16];
+ ext4_grpblk_t counters[16];
} sg;
group--;
@@ -2366,7 +2367,7 @@ static void ext4_mb_seq_groups_stop(struct seq_file *seq, void *v)
{
}
-static struct seq_operations ext4_mb_seq_groups_ops = {
+static const struct seq_operations ext4_mb_seq_groups_ops = {
.start = ext4_mb_seq_groups_start,
.next = ext4_mb_seq_groups_next,
.stop = ext4_mb_seq_groups_stop,
@@ -2387,7 +2388,7 @@ static int ext4_mb_seq_groups_open(struct inode *inode, struct file *file)
}
-static struct file_operations ext4_mb_seq_groups_fops = {
+static const struct file_operations ext4_mb_seq_groups_fops = {
.owner = THIS_MODULE,
.open = ext4_mb_seq_groups_open,
.read = seq_read,
@@ -2532,7 +2533,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
init_rwsem(&meta_group_info[i]->alloc_sem);
- meta_group_info[i]->bb_free_root.rb_node = NULL;;
+ meta_group_info[i]->bb_free_root.rb_node = NULL;
#ifdef DOUBLE_CHECK
{
@@ -2558,26 +2559,15 @@ exit_meta_group_info:
return -ENOMEM;
} /* ext4_mb_add_groupinfo */
-/*
- * Update an existing group.
- * This function is used for online resize
- */
-void ext4_mb_update_group_info(struct ext4_group_info *grp, ext4_grpblk_t add)
-{
- grp->bb_free += add;
-}
-
static int ext4_mb_init_backend(struct super_block *sb)
{
ext4_group_t ngroups = ext4_get_groups_count(sb);
ext4_group_t i;
- int metalen;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
int num_meta_group_infos;
int num_meta_group_infos_max;
int array_size;
- struct ext4_group_info **meta_group_info;
struct ext4_group_desc *desc;
/* This is the number of blocks used by GDT */
@@ -2622,22 +2612,6 @@ static int ext4_mb_init_backend(struct super_block *sb)
goto err_freesgi;
}
EXT4_I(sbi->s_buddy_cache)->i_disksize = 0;
-
- metalen = sizeof(*meta_group_info) << EXT4_DESC_PER_BLOCK_BITS(sb);
- for (i = 0; i < num_meta_group_infos; i++) {
- if ((i + 1) == num_meta_group_infos)
- metalen = sizeof(*meta_group_info) *
- (ngroups -
- (i << 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");
- goto err_freemeta;
- }
- sbi->s_group_info[i] = meta_group_info;
- }
-
for (i = 0; i < ngroups; i++) {
desc = ext4_get_group_desc(sb, i, NULL);
if (desc == NULL) {
@@ -2655,7 +2629,6 @@ err_freebuddy:
while (i-- > 0)
kfree(ext4_get_group_info(sb, i));
i = num_meta_group_infos;
-err_freemeta:
while (i-- > 0)
kfree(sbi->s_group_info[i]);
iput(sbi->s_buddy_cache);
@@ -2672,14 +2645,14 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
unsigned max;
int ret;
- i = (sb->s_blocksize_bits + 2) * sizeof(unsigned short);
+ i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets);
sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL);
if (sbi->s_mb_offsets == NULL) {
return -ENOMEM;
}
- i = (sb->s_blocksize_bits + 2) * sizeof(unsigned int);
+ i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_maxs);
sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL);
if (sbi->s_mb_maxs == NULL) {
kfree(sbi->s_mb_offsets);
@@ -2758,7 +2731,7 @@ static void ext4_mb_cleanup_pa(struct ext4_group_info *grp)
kmem_cache_free(ext4_pspace_cachep, pa);
}
if (count)
- mb_debug("mballoc: %u PAs left\n", count);
+ mb_debug(1, "mballoc: %u PAs left\n", count);
}
@@ -2839,7 +2812,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
list_for_each_safe(l, ltmp, &txn->t_private_list) {
entry = list_entry(l, struct ext4_free_data, list);
- mb_debug("gonna free %u blocks in group %u (0x%p):",
+ mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
entry->count, entry->group, entry);
err = ext4_mb_load_buddy(sb, entry->group, &e4b);
@@ -2874,9 +2847,43 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
ext4_mb_release_desc(&e4b);
}
- mb_debug("freed %u blocks in %u structures\n", count, count2);
+ mb_debug(1, "freed %u blocks in %u structures\n", count, count2);
+}
+
+#ifdef CONFIG_EXT4_DEBUG
+u8 mb_enable_debug __read_mostly;
+
+static struct dentry *debugfs_dir;
+static struct dentry *debugfs_debug;
+
+static void __init ext4_create_debugfs_entry(void)
+{
+ debugfs_dir = debugfs_create_dir("ext4", NULL);
+ if (debugfs_dir)
+ debugfs_debug = debugfs_create_u8("mballoc-debug",
+ S_IRUGO | S_IWUSR,
+ debugfs_dir,
+ &mb_enable_debug);
+}
+
+static void ext4_remove_debugfs_entry(void)
+{
+ debugfs_remove(debugfs_debug);
+ debugfs_remove(debugfs_dir);
}
+#else
+
+static void __init ext4_create_debugfs_entry(void)
+{
+}
+
+static void ext4_remove_debugfs_entry(void)
+{
+}
+
+#endif
+
int __init init_ext4_mballoc(void)
{
ext4_pspace_cachep =
@@ -2904,6 +2911,7 @@ int __init init_ext4_mballoc(void)
kmem_cache_destroy(ext4_ac_cachep);
return -ENOMEM;
}
+ ext4_create_debugfs_entry();
return 0;
}
@@ -2917,6 +2925,7 @@ void exit_ext4_mballoc(void)
kmem_cache_destroy(ext4_pspace_cachep);
kmem_cache_destroy(ext4_ac_cachep);
kmem_cache_destroy(ext4_free_ext_cachep);
+ ext4_remove_debugfs_entry();
}
@@ -3061,7 +3070,7 @@ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac)
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;
- mb_debug("#%u: goal %u blocks for locality group\n",
+ mb_debug(1, "#%u: goal %u blocks for locality group\n",
current->pid, ac->ac_g_ex.fe_len);
}
@@ -3180,23 +3189,18 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end ||
ac->ac_o_ex.fe_logical < pa->pa_lstart));
- /* skip PA normalized request doesn't overlap with */
- if (pa->pa_lstart >= end) {
- spin_unlock(&pa->pa_lock);
- continue;
- }
- if (pa_end <= start) {
+ /* skip PAs this normalized request doesn't overlap with */
+ if (pa->pa_lstart >= end || pa_end <= start) {
spin_unlock(&pa->pa_lock);
continue;
}
BUG_ON(pa->pa_lstart <= start && pa_end >= end);
+ /* adjust start or end to be adjacent to this pa */
if (pa_end <= ac->ac_o_ex.fe_logical) {
BUG_ON(pa_end < start);
start = pa_end;
- }
-
- if (pa->pa_lstart > ac->ac_o_ex.fe_logical) {
+ } else if (pa->pa_lstart > ac->ac_o_ex.fe_logical) {
BUG_ON(pa->pa_lstart > end);
end = pa->pa_lstart;
}
@@ -3251,7 +3255,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL;
}
- mb_debug("goal: %u(was %u) blocks at %u\n", (unsigned) size,
+ mb_debug(1, "goal: %u(was %u) blocks at %u\n", (unsigned) size,
(unsigned) orig_size, (unsigned) start);
}
@@ -3300,7 +3304,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
BUG_ON(pa->pa_free < len);
pa->pa_free -= len;
- mb_debug("use %llu/%u from inode pa %p\n", start, len, pa);
+ mb_debug(1, "use %llu/%u from inode pa %p\n", start, len, pa);
}
/*
@@ -3324,7 +3328,7 @@ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac,
* in on-disk bitmap -- see ext4_mb_release_context()
* Other CPUs are prevented from allocating from this pa by lg_mutex
*/
- mb_debug("use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa);
+ mb_debug(1, "use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa);
}
/*
@@ -3382,6 +3386,11 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
ac->ac_o_ex.fe_logical >= pa->pa_lstart + pa->pa_len)
continue;
+ /* non-extent files can't have physical blocks past 2^32 */
+ if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL) &&
+ pa->pa_pstart + pa->pa_len > EXT4_MAX_BLOCK_FILE_PHYS)
+ continue;
+
/* found preallocated blocks, use them */
spin_lock(&pa->pa_lock);
if (pa->pa_deleted == 0 && pa->pa_free) {
@@ -3503,7 +3512,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
preallocated += len;
count++;
}
- mb_debug("prellocated %u for group %u\n", preallocated, group);
+ mb_debug(1, "prellocated %u for group %u\n", preallocated, group);
}
static void ext4_mb_pa_callback(struct rcu_head *head)
@@ -3638,7 +3647,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
pa->pa_deleted = 0;
pa->pa_type = MB_INODE_PA;
- mb_debug("new inode pa %p: %llu/%u for %u\n", pa,
+ mb_debug(1, "new inode pa %p: %llu/%u for %u\n", pa,
pa->pa_pstart, pa->pa_len, pa->pa_lstart);
trace_ext4_mb_new_inode_pa(ac, pa);
@@ -3698,7 +3707,7 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac)
pa->pa_deleted = 0;
pa->pa_type = MB_GROUP_PA;
- mb_debug("new group pa %p: %llu/%u for %u\n", pa,
+ mb_debug(1, "new group pa %p: %llu/%u for %u\n", pa,
pa->pa_pstart, pa->pa_len, pa->pa_lstart);
trace_ext4_mb_new_group_pa(ac, pa);
@@ -3777,7 +3786,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
next = mb_find_next_bit(bitmap_bh->b_data, end, bit);
start = group * EXT4_BLOCKS_PER_GROUP(sb) + bit +
le32_to_cpu(sbi->s_es->s_first_data_block);
- mb_debug(" free preallocated %u/%u in group %u\n",
+ mb_debug(1, " free preallocated %u/%u in group %u\n",
(unsigned) start, (unsigned) next - bit,
(unsigned) group);
free += next - bit;
@@ -3868,7 +3877,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
int busy = 0;
int free = 0;
- mb_debug("discard preallocation for group %u\n", group);
+ mb_debug(1, "discard preallocation for group %u\n", group);
if (list_empty(&grp->bb_prealloc_list))
return 0;
@@ -3992,7 +4001,7 @@ void ext4_discard_preallocations(struct inode *inode)
return;
}
- mb_debug("discard preallocation for inode %lu\n", inode->i_ino);
+ mb_debug(1, "discard preallocation for inode %lu\n", inode->i_ino);
trace_ext4_discard_preallocations(inode);
INIT_LIST_HEAD(&list);
@@ -4097,7 +4106,7 @@ static void ext4_mb_return_to_preallocation(struct inode *inode,
{
BUG_ON(!list_empty(&EXT4_I(inode)->i_prealloc_list));
}
-#ifdef MB_DEBUG
+#ifdef CONFIG_EXT4_DEBUG
static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
{
struct super_block *sb = ac->ac_sb;
@@ -4139,14 +4148,14 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
ext4_get_group_no_and_offset(sb, pa->pa_pstart,
NULL, &start);
spin_unlock(&pa->pa_lock);
- printk(KERN_ERR "PA:%lu:%d:%u \n", i,
- start, pa->pa_len);
+ printk(KERN_ERR "PA:%u:%d:%u \n", i,
+ start, pa->pa_len);
}
ext4_unlock_group(sb, i);
if (grp->bb_free == 0)
continue;
- printk(KERN_ERR "%lu: %d/%d \n",
+ printk(KERN_ERR "%u: %d/%d \n",
i, grp->bb_free, grp->bb_fragments);
}
printk(KERN_ERR "\n");
@@ -4174,16 +4183,26 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
if (!(ac->ac_flags & EXT4_MB_HINT_DATA))
return;
+ if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
+ return;
+
size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len;
- isize = i_size_read(ac->ac_inode) >> bsbits;
+ isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1)
+ >> bsbits;
size = max(size, isize);
- /* don't use group allocation for large files */
- if (size >= sbi->s_mb_stream_request)
+ if ((size == isize) &&
+ !ext4_fs_is_busy(sbi) &&
+ (atomic_read(&ac->ac_inode->i_writecount) == 0)) {
+ ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC;
return;
+ }
- if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
+ /* don't use group allocation for large files */
+ if (size >= sbi->s_mb_stream_request) {
+ ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
return;
+ }
BUG_ON(ac->ac_lg != NULL);
/*
@@ -4246,7 +4265,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
* locality group. this is a policy, actually */
ext4_mb_group_or_file(ac);
- mb_debug("init ac: %u blocks @ %u, goal %u, flags %x, 2^%d, "
+ mb_debug(1, "init ac: %u blocks @ %u, goal %u, flags %x, 2^%d, "
"left: %u/%u, right %u/%u to %swritable\n",
(unsigned) ar->len, (unsigned) ar->logical,
(unsigned) ar->goal, ac->ac_flags, ac->ac_2order,
@@ -4268,7 +4287,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
struct ext4_prealloc_space *pa, *tmp;
struct ext4_allocation_context *ac;
- mb_debug("discard locality group preallocation\n");
+ mb_debug(1, "discard locality group preallocation\n");
INIT_LIST_HEAD(&discard_list);
ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index c96bb19f58f..188d3d709b2 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -37,11 +37,19 @@
/*
*/
-#define MB_DEBUG__
-#ifdef MB_DEBUG
-#define mb_debug(fmt, a...) printk(fmt, ##a)
+#ifdef CONFIG_EXT4_DEBUG
+extern u8 mb_enable_debug;
+
+#define mb_debug(n, fmt, a...) \
+ do { \
+ if ((n) <= mb_enable_debug) { \
+ printk(KERN_DEBUG "(%s, %d): %s: ", \
+ __FILE__, __LINE__, __func__); \
+ printk(fmt, ## a); \
+ } \
+ } while (0)
#else
-#define mb_debug(fmt, a...)
+#define mb_debug(n, fmt, a...)
#endif
/*
@@ -128,8 +136,8 @@ struct ext4_prealloc_space {
unsigned pa_deleted;
ext4_fsblk_t pa_pstart; /* phys. block */
ext4_lblk_t pa_lstart; /* log. block */
- unsigned short pa_len; /* len of preallocated chunk */
- unsigned short pa_free; /* how many blocks are free */
+ ext4_grpblk_t pa_len; /* len of preallocated chunk */
+ ext4_grpblk_t pa_free; /* how many blocks are free */
unsigned short pa_type; /* pa type. inode or group */
spinlock_t *pa_obj_lock;
struct inode *pa_inode; /* hack, for history only */
@@ -144,7 +152,7 @@ struct ext4_free_extent {
ext4_lblk_t fe_logical;
ext4_grpblk_t fe_start;
ext4_group_t fe_group;
- int fe_len;
+ ext4_grpblk_t fe_len;
};
/*
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 313a50b3974..bf519f239ae 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -353,17 +353,16 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
down_write(&EXT4_I(inode)->i_data_sem);
/*
- * if EXT4_EXT_MIGRATE is cleared a block allocation
+ * if EXT4_STATE_EXT_MIGRATE is cleared a block allocation
* happened after we started the migrate. We need to
* fail the migrate
*/
- if (!(EXT4_I(inode)->i_flags & EXT4_EXT_MIGRATE)) {
+ if (!(EXT4_I(inode)->i_state & EXT4_STATE_EXT_MIGRATE)) {
retval = -EAGAIN;
up_write(&EXT4_I(inode)->i_data_sem);
goto err_out;
} else
- EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags &
- ~EXT4_EXT_MIGRATE;
+ EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE;
/*
* We have the extent map build with the tmp inode.
* Now copy the i_data across
@@ -517,14 +516,15 @@ int ext4_ext_migrate(struct inode *inode)
* when we add extents we extent the journal
*/
/*
- * Even though we take i_mutex we can still cause block allocation
- * via mmap write to holes. If we have allocated new blocks we fail
- * migrate. New block allocation will clear EXT4_EXT_MIGRATE flag.
- * The flag is updated with i_data_sem held to prevent racing with
- * block allocation.
+ * Even though we take i_mutex we can still cause block
+ * allocation via mmap write to holes. If we have allocated
+ * new blocks we fail migrate. New block allocation will
+ * clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated
+ * with i_data_sem held to prevent racing with block
+ * allocation.
*/
down_read((&EXT4_I(inode)->i_data_sem));
- EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags | EXT4_EXT_MIGRATE;
+ EXT4_I(inode)->i_state |= EXT4_STATE_EXT_MIGRATE;
up_read((&EXT4_I(inode)->i_data_sem));
handle = ext4_journal_start(inode, 1);
@@ -618,7 +618,7 @@ err_out:
tmp_inode->i_nlink = 0;
ext4_journal_stop(handle);
-
+ unlock_new_inode(tmp_inode);
iput(tmp_inode);
return retval;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index bbf2dd9404d..c07a2915e40 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -19,14 +19,31 @@
#include "ext4_extents.h"
#include "ext4.h"
-#define get_ext_path(path, inode, block, ret) \
- do { \
- path = ext4_ext_find_extent(inode, block, path); \
- if (IS_ERR(path)) { \
- ret = PTR_ERR(path); \
- path = NULL; \
- } \
- } while (0)
+/**
+ * get_ext_path - Find an extent path for designated logical block number.
+ *
+ * @inode: an inode which is searched
+ * @lblock: logical block number to find an extent path
+ * @path: pointer to an extent path pointer (for output)
+ *
+ * ext4_ext_find_extent wrapper. Return 0 on success, or a negative error value
+ * on failure.
+ */
+static inline int
+get_ext_path(struct inode *inode, ext4_lblk_t lblock,
+ struct ext4_ext_path **path)
+{
+ int ret = 0;
+
+ *path = ext4_ext_find_extent(inode, lblock, *path);
+ if (IS_ERR(*path)) {
+ ret = PTR_ERR(*path);
+ *path = NULL;
+ } else if ((*path)[ext_depth(inode)].p_ext == NULL)
+ ret = -ENODATA;
+
+ return ret;
+}
/**
* copy_extent_status - Copy the extent's initialization status
@@ -113,6 +130,31 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
}
/**
+ * mext_check_null_inode - NULL check for two inodes
+ *
+ * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
+ */
+static int
+mext_check_null_inode(struct inode *inode1, struct inode *inode2,
+ const char *function)
+{
+ int ret = 0;
+
+ if (inode1 == NULL) {
+ ext4_error(inode2->i_sb, function,
+ "Both inodes should not be NULL: "
+ "inode1 NULL inode2 %lu", inode2->i_ino);
+ ret = -EIO;
+ } else if (inode2 == NULL) {
+ ext4_error(inode1->i_sb, function,
+ "Both inodes should not be NULL: "
+ "inode1 %lu inode2 NULL", inode1->i_ino);
+ ret = -EIO;
+ }
+ return ret;
+}
+
+/**
* mext_double_down_read - Acquire two inodes' read semaphore
*
* @orig_inode: original inode structure
@@ -124,8 +166,6 @@ mext_double_down_read(struct inode *orig_inode, struct inode *donor_inode)
{
struct inode *first = orig_inode, *second = donor_inode;
- BUG_ON(orig_inode == NULL || donor_inode == NULL);
-
/*
* Use the inode number to provide the stable locking order instead
* of its address, because the C language doesn't guarantee you can
@@ -152,8 +192,6 @@ mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode)
{
struct inode *first = orig_inode, *second = donor_inode;
- BUG_ON(orig_inode == NULL || donor_inode == NULL);
-
/*
* Use the inode number to provide the stable locking order instead
* of its address, because the C language doesn't guarantee you can
@@ -178,8 +216,6 @@ mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode)
static void
mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode)
{
- BUG_ON(orig_inode == NULL || donor_inode == NULL);
-
up_read(&EXT4_I(orig_inode)->i_data_sem);
up_read(&EXT4_I(donor_inode)->i_data_sem);
}
@@ -194,8 +230,6 @@ mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode)
static void
mext_double_up_write(struct inode *orig_inode, struct inode *donor_inode)
{
- BUG_ON(orig_inode == NULL || donor_inode == NULL);
-
up_write(&EXT4_I(orig_inode)->i_data_sem);
up_write(&EXT4_I(donor_inode)->i_data_sem);
}
@@ -283,8 +317,8 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
}
if (new_flag) {
- get_ext_path(orig_path, orig_inode, eblock, err);
- if (orig_path == NULL)
+ err = get_ext_path(orig_inode, eblock, &orig_path);
+ if (err)
goto out;
if (ext4_ext_insert_extent(handle, orig_inode,
@@ -293,9 +327,9 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
}
if (end_flag) {
- get_ext_path(orig_path, orig_inode,
- le32_to_cpu(end_ext->ee_block) - 1, err);
- if (orig_path == NULL)
+ err = get_ext_path(orig_inode,
+ le32_to_cpu(end_ext->ee_block) - 1, &orig_path);
+ if (err)
goto out;
if (ext4_ext_insert_extent(handle, orig_inode,
@@ -519,7 +553,15 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
* oext |-----------|
* new_ext |-------|
*/
- BUG_ON(le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end);
+ if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) {
+ ext4_error(orig_inode->i_sb, __func__,
+ "new_ext_end(%u) should be less than or equal to "
+ "oext->ee_block(%u) + oext_alen(%d) - 1",
+ new_ext_end, le32_to_cpu(oext->ee_block),
+ oext_alen);
+ ret = -EIO;
+ goto out;
+ }
/*
* Case: new_ext is smaller than original extent
@@ -543,6 +585,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
ret = mext_insert_extents(handle, orig_inode, orig_path, o_start,
o_end, &start_ext, &new_ext, &end_ext);
+out:
return ret;
}
@@ -554,8 +597,10 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
* @orig_off: block offset of original inode
* @donor_off: block offset of donor inode
* @max_count: the maximun length of extents
+ *
+ * Return 0 on success, or a negative error value on failure.
*/
-static void
+static int
mext_calc_swap_extents(struct ext4_extent *tmp_dext,
struct ext4_extent *tmp_oext,
ext4_lblk_t orig_off, ext4_lblk_t donor_off,
@@ -564,6 +609,19 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
ext4_lblk_t diff, orig_diff;
struct ext4_extent dext_old, oext_old;
+ BUG_ON(orig_off != donor_off);
+
+ /* original and donor extents have to cover the same block offset */
+ if (orig_off < le32_to_cpu(tmp_oext->ee_block) ||
+ le32_to_cpu(tmp_oext->ee_block) +
+ ext4_ext_get_actual_len(tmp_oext) - 1 < orig_off)
+ return -ENODATA;
+
+ if (orig_off < le32_to_cpu(tmp_dext->ee_block) ||
+ le32_to_cpu(tmp_dext->ee_block) +
+ ext4_ext_get_actual_len(tmp_dext) - 1 < orig_off)
+ return -ENODATA;
+
dext_old = *tmp_dext;
oext_old = *tmp_oext;
@@ -591,6 +649,8 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
copy_extent_status(&oext_old, tmp_dext);
copy_extent_status(&dext_old, tmp_oext);
+
+ return 0;
}
/**
@@ -631,13 +691,13 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
mext_double_down_write(orig_inode, donor_inode);
/* Get the original extent for the block "orig_off" */
- get_ext_path(orig_path, orig_inode, orig_off, err);
- if (orig_path == NULL)
+ err = get_ext_path(orig_inode, orig_off, &orig_path);
+ if (err)
goto out;
/* Get the donor extent for the head */
- get_ext_path(donor_path, donor_inode, donor_off, err);
- if (donor_path == NULL)
+ err = get_ext_path(donor_inode, donor_off, &donor_path);
+ if (err)
goto out;
depth = ext_depth(orig_inode);
oext = orig_path[depth].p_ext;
@@ -647,13 +707,28 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
dext = donor_path[depth].p_ext;
tmp_dext = *dext;
- mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
+ err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
donor_off, count);
+ if (err)
+ goto out;
/* Loop for the donor extents */
while (1) {
/* The extent for donor must be found. */
- BUG_ON(!dext || donor_off != le32_to_cpu(tmp_dext.ee_block));
+ if (!dext) {
+ ext4_error(donor_inode->i_sb, __func__,
+ "The extent for donor must be found");
+ err = -EIO;
+ goto out;
+ } else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) {
+ ext4_error(donor_inode->i_sb, __func__,
+ "Donor offset(%u) and the first block of donor "
+ "extent(%u) should be equal",
+ donor_off,
+ le32_to_cpu(tmp_dext.ee_block));
+ err = -EIO;
+ goto out;
+ }
/* Set donor extent to orig extent */
err = mext_leaf_block(handle, orig_inode,
@@ -678,8 +753,8 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
if (orig_path)
ext4_ext_drop_refs(orig_path);
- get_ext_path(orig_path, orig_inode, orig_off, err);
- if (orig_path == NULL)
+ err = get_ext_path(orig_inode, orig_off, &orig_path);
+ if (err)
goto out;
depth = ext_depth(orig_inode);
oext = orig_path[depth].p_ext;
@@ -692,9 +767,8 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
if (donor_path)
ext4_ext_drop_refs(donor_path);
- get_ext_path(donor_path, donor_inode,
- donor_off, err);
- if (donor_path == NULL)
+ err = get_ext_path(donor_inode, donor_off, &donor_path);
+ if (err)
goto out;
depth = ext_depth(donor_inode);
dext = donor_path[depth].p_ext;
@@ -705,9 +779,10 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
}
tmp_dext = *dext;
- mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
- donor_off,
- count - replaced_count);
+ err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
+ donor_off, count - replaced_count);
+ if (err)
+ goto out;
}
out:
@@ -740,7 +815,7 @@ out:
* on success, or a negative error value on failure.
*/
static int
-move_extent_par_page(struct file *o_filp, struct inode *donor_inode,
+move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
pgoff_t orig_page_offset, int data_offset_in_page,
int block_len_in_page, int uninit)
{
@@ -871,6 +946,7 @@ out:
if (PageLocked(page))
unlock_page(page);
page_cache_release(page);
+ ext4_journal_stop(handle);
}
out2:
ext4_journal_stop(handle);
@@ -897,6 +973,10 @@ mext_check_arguments(struct inode *orig_inode,
struct inode *donor_inode, __u64 orig_start,
__u64 donor_start, __u64 *len, __u64 moved_len)
{
+ ext4_lblk_t orig_blocks, donor_blocks;
+ unsigned int blkbits = orig_inode->i_blkbits;
+ unsigned int blocksize = 1 << blkbits;
+
/* Regular file check */
if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
ext4_debug("ext4 move extent: The argument files should be "
@@ -960,54 +1040,58 @@ mext_check_arguments(struct inode *orig_inode,
return -EINVAL;
}
- if ((orig_start > MAX_DEFRAG_SIZE) ||
- (donor_start > MAX_DEFRAG_SIZE) ||
- (*len > MAX_DEFRAG_SIZE) ||
- (orig_start + *len > MAX_DEFRAG_SIZE)) {
- ext4_debug("ext4 move extent: Can't handle over [%lu] blocks "
- "[ino:orig %lu, donor %lu]\n", MAX_DEFRAG_SIZE,
+ if ((orig_start > EXT_MAX_BLOCK) ||
+ (donor_start > EXT_MAX_BLOCK) ||
+ (*len > EXT_MAX_BLOCK) ||
+ (orig_start + *len > EXT_MAX_BLOCK)) {
+ ext4_debug("ext4 move extent: Can't handle over [%u] blocks "
+ "[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCK,
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
if (orig_inode->i_size > donor_inode->i_size) {
- if (orig_start >= donor_inode->i_size) {
+ donor_blocks = (donor_inode->i_size + blocksize - 1) >> blkbits;
+ /* TODO: eliminate this artificial restriction */
+ if (orig_start >= donor_blocks) {
ext4_debug("ext4 move extent: orig start offset "
- "[%llu] should be less than donor file size "
- "[%lld] [ino:orig %lu, donor_inode %lu]\n",
- orig_start, donor_inode->i_size,
+ "[%llu] should be less than donor file blocks "
+ "[%u] [ino:orig %lu, donor %lu]\n",
+ orig_start, donor_blocks,
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
- if (orig_start + *len > donor_inode->i_size) {
+ /* TODO: eliminate this artificial restriction */
+ if (orig_start + *len > donor_blocks) {
ext4_debug("ext4 move extent: End offset [%llu] should "
- "be less than donor file size [%lld]."
- "So adjust length from %llu to %lld "
+ "be less than donor file blocks [%u]."
+ "So adjust length from %llu to %llu "
"[ino:orig %lu, donor %lu]\n",
- orig_start + *len, donor_inode->i_size,
- *len, donor_inode->i_size - orig_start,
+ orig_start + *len, donor_blocks,
+ *len, donor_blocks - orig_start,
orig_inode->i_ino, donor_inode->i_ino);
- *len = donor_inode->i_size - orig_start;
+ *len = donor_blocks - orig_start;
}
} else {
- if (orig_start >= orig_inode->i_size) {
+ orig_blocks = (orig_inode->i_size + blocksize - 1) >> blkbits;
+ if (orig_start >= orig_blocks) {
ext4_debug("ext4 move extent: start offset [%llu] "
- "should be less than original file size "
- "[%lld] [inode:orig %lu, donor %lu]\n",
- orig_start, orig_inode->i_size,
+ "should be less than original file blocks "
+ "[%u] [ino:orig %lu, donor %lu]\n",
+ orig_start, orig_blocks,
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
- if (orig_start + *len > orig_inode->i_size) {
+ if (orig_start + *len > orig_blocks) {
ext4_debug("ext4 move extent: Adjust length "
- "from %llu to %lld. Because it should be "
- "less than original file size "
+ "from %llu to %llu. Because it should be "
+ "less than original file blocks "
"[ino:orig %lu, donor %lu]\n",
- *len, orig_inode->i_size - orig_start,
+ *len, orig_blocks - orig_start,
orig_inode->i_ino, donor_inode->i_ino);
- *len = orig_inode->i_size - orig_start;
+ *len = orig_blocks - orig_start;
}
}
@@ -1027,18 +1111,23 @@ mext_check_arguments(struct inode *orig_inode,
* @inode1: the inode structure
* @inode2: the inode structure
*
- * Lock two inodes' i_mutex by i_ino order. This function is moved from
- * fs/inode.c.
+ * Lock two inodes' i_mutex by i_ino order.
+ * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
*/
-static void
+static int
mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
{
- if (inode1 == NULL || inode2 == NULL || inode1 == inode2) {
- if (inode1)
- mutex_lock(&inode1->i_mutex);
- else if (inode2)
- mutex_lock(&inode2->i_mutex);
- return;
+ int ret = 0;
+
+ BUG_ON(inode1 == NULL && inode2 == NULL);
+
+ ret = mext_check_null_inode(inode1, inode2, __func__);
+ if (ret < 0)
+ goto out;
+
+ if (inode1 == inode2) {
+ mutex_lock(&inode1->i_mutex);
+ goto out;
}
if (inode1->i_ino < inode2->i_ino) {
@@ -1048,6 +1137,9 @@ mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
}
+
+out:
+ return ret;
}
/**
@@ -1056,17 +1148,28 @@ mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
* @inode1: the inode that is released first
* @inode2: the inode that is released second
*
- * This function is moved from fs/inode.c.
+ * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
*/
-static void
+static int
mext_inode_double_unlock(struct inode *inode1, struct inode *inode2)
{
+ int ret = 0;
+
+ BUG_ON(inode1 == NULL && inode2 == NULL);
+
+ ret = mext_check_null_inode(inode1, inode2, __func__);
+ if (ret < 0)
+ goto out;
+
if (inode1)
mutex_unlock(&inode1->i_mutex);
if (inode2 && inode2 != inode1)
mutex_unlock(&inode2->i_mutex);
+
+out:
+ return ret;
}
/**
@@ -1123,70 +1226,76 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
ext4_lblk_t block_end, seq_start, add_blocks, file_end, seq_blocks = 0;
ext4_lblk_t rest_blocks;
pgoff_t orig_page_offset = 0, seq_end_page;
- int ret, depth, last_extent = 0;
+ int ret1, ret2, depth, last_extent = 0;
int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
int data_offset_in_page;
int block_len_in_page;
int uninit;
/* protect orig and donor against a truncate */
- mext_inode_double_lock(orig_inode, donor_inode);
+ ret1 = mext_inode_double_lock(orig_inode, donor_inode);
+ if (ret1 < 0)
+ return ret1;
mext_double_down_read(orig_inode, donor_inode);
/* Check the filesystem environment whether move_extent can be done */
- ret = mext_check_arguments(orig_inode, donor_inode, orig_start,
+ ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start,
donor_start, &len, *moved_len);
mext_double_up_read(orig_inode, donor_inode);
- if (ret)
- goto out2;
+ if (ret1)
+ goto out;
file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits;
block_end = block_start + len - 1;
if (file_end < block_end)
len -= block_end - file_end;
- get_ext_path(orig_path, orig_inode, block_start, ret);
- if (orig_path == NULL)
- goto out2;
+ ret1 = get_ext_path(orig_inode, block_start, &orig_path);
+ if (ret1)
+ goto out;
/* Get path structure to check the hole */
- get_ext_path(holecheck_path, orig_inode, block_start, ret);
- if (holecheck_path == NULL)
+ ret1 = get_ext_path(orig_inode, block_start, &holecheck_path);
+ if (ret1)
goto out;
depth = ext_depth(orig_inode);
ext_cur = holecheck_path[depth].p_ext;
- if (ext_cur == NULL) {
- ret = -EINVAL;
- goto out;
- }
/*
- * Get proper extent whose ee_block is beyond block_start
- * if block_start was within the hole.
+ * Get proper starting location of block replacement if block_start was
+ * within the hole.
*/
if (le32_to_cpu(ext_cur->ee_block) +
ext4_ext_get_actual_len(ext_cur) - 1 < block_start) {
+ /*
+ * The hole exists between extents or the tail of
+ * original file.
+ */
last_extent = mext_next_extent(orig_inode,
holecheck_path, &ext_cur);
if (last_extent < 0) {
- ret = last_extent;
+ ret1 = last_extent;
goto out;
}
last_extent = mext_next_extent(orig_inode, orig_path,
&ext_dummy);
if (last_extent < 0) {
- ret = last_extent;
+ ret1 = last_extent;
goto out;
}
- }
- seq_start = block_start;
+ seq_start = le32_to_cpu(ext_cur->ee_block);
+ } else if (le32_to_cpu(ext_cur->ee_block) > block_start)
+ /* The hole exists at the beginning of original file. */
+ seq_start = le32_to_cpu(ext_cur->ee_block);
+ else
+ seq_start = block_start;
/* No blocks within the specified range. */
if (le32_to_cpu(ext_cur->ee_block) > block_end) {
ext4_debug("ext4 move extent: The specified range of file "
"may be the hole\n");
- ret = -EINVAL;
+ ret1 = -EINVAL;
goto out;
}
@@ -1206,7 +1315,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
last_extent = mext_next_extent(orig_inode, holecheck_path,
&ext_cur);
if (last_extent < 0) {
- ret = last_extent;
+ ret1 = last_extent;
break;
}
add_blocks = ext4_ext_get_actual_len(ext_cur);
@@ -1258,16 +1367,23 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
while (orig_page_offset <= seq_end_page) {
/* Swap original branches with new branches */
- ret = move_extent_par_page(o_filp, donor_inode,
+ ret1 = move_extent_per_page(o_filp, donor_inode,
orig_page_offset,
data_offset_in_page,
block_len_in_page, uninit);
- if (ret < 0)
+ if (ret1 < 0)
goto out;
orig_page_offset++;
/* Count how many blocks we have exchanged */
*moved_len += block_len_in_page;
- BUG_ON(*moved_len > len);
+ if (*moved_len > len) {
+ ext4_error(orig_inode->i_sb, __func__,
+ "We replaced blocks too much! "
+ "sum of replaced: %llu requested: %llu",
+ *moved_len, len);
+ ret1 = -EIO;
+ goto out;
+ }
data_offset_in_page = 0;
rest_blocks -= block_len_in_page;
@@ -1280,17 +1396,16 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
/* Decrease buffer counter */
if (holecheck_path)
ext4_ext_drop_refs(holecheck_path);
- get_ext_path(holecheck_path, orig_inode,
- seq_start, ret);
- if (holecheck_path == NULL)
+ ret1 = get_ext_path(orig_inode, seq_start, &holecheck_path);
+ if (ret1)
break;
depth = holecheck_path->p_depth;
/* Decrease buffer counter */
if (orig_path)
ext4_ext_drop_refs(orig_path);
- get_ext_path(orig_path, orig_inode, seq_start, ret);
- if (orig_path == NULL)
+ ret1 = get_ext_path(orig_inode, seq_start, &orig_path);
+ if (ret1)
break;
ext_cur = holecheck_path[depth].p_ext;
@@ -1307,14 +1422,13 @@ out:
ext4_ext_drop_refs(holecheck_path);
kfree(holecheck_path);
}
-out2:
- mext_inode_double_unlock(orig_inode, donor_inode);
- if (ret)
- return ret;
+ ret2 = mext_inode_double_unlock(orig_inode, donor_inode);
- /* All of the specified blocks must be exchanged in succeed */
- BUG_ON(*moved_len != len);
+ if (ret1)
+ return ret1;
+ else if (ret2)
+ return ret2;
return 0;
}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 114abe5d2c1..42f81d285cd 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1518,8 +1518,12 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
return retval;
if (blocks == 1 && !dx_fallback &&
- EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
- return make_indexed_dir(handle, dentry, inode, bh);
+ EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
+ retval = make_indexed_dir(handle, dentry, inode, bh);
+ if (retval == -ENOSPC)
+ brelse(bh);
+ return retval;
+ }
brelse(bh);
}
bh = ext4_append(handle, dir, &block, &retval);
@@ -1528,7 +1532,10 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
de = (struct ext4_dir_entry_2 *) bh->b_data;
de->inode = 0;
de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize);
- return add_dirent_to_buf(handle, dentry, inode, de, bh);
+ retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+ if (retval == -ENOSPC)
+ brelse(bh);
+ return retval;
}
/*
@@ -1590,9 +1597,9 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
goto cleanup;
node2 = (struct dx_node *)(bh2->b_data);
entries2 = node2->entries;
+ memset(&node2->fake, 0, sizeof(struct fake_dirent));
node2->fake.rec_len = ext4_rec_len_to_disk(sb->s_blocksize,
sb->s_blocksize);
- node2->fake.inode = 0;
BUFFER_TRACE(frame->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, frame->bh);
if (err)
@@ -1657,7 +1664,8 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
if (!de)
goto cleanup;
err = add_dirent_to_buf(handle, dentry, inode, de, bh);
- bh = NULL;
+ if (err != -ENOSPC)
+ bh = NULL;
goto cleanup;
journal_error:
@@ -2310,7 +2318,7 @@ static int ext4_link(struct dentry *old_dentry,
struct inode *inode = old_dentry->d_inode;
int err, retries = 0;
- if (EXT4_DIR_LINK_MAX(inode))
+ if (inode->i_nlink >= EXT4_LINK_MAX)
return -EMLINK;
/*
@@ -2413,7 +2421,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
goto end_rename;
retval = -EMLINK;
if (!new_inode && new_dir != old_dir &&
- new_dir->i_nlink >= EXT4_LINK_MAX)
+ EXT4_DIR_LINK_MAX(new_dir))
goto end_rename;
}
if (!new_bh) {
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 68b0351fc64..3cfc343c41b 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -746,7 +746,6 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
struct inode *inode = NULL;
handle_t *handle;
int gdb_off, gdb_num;
- int num_grp_locked = 0;
int err, err2;
gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
@@ -856,7 +855,6 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
* using the new disk blocks.
*/
- num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, input->group);
/* Update group descriptor block for new group */
gdp = (struct ext4_group_desc *)((char *)primary->b_data +
gdb_off * EXT4_DESC_SIZE(sb));
@@ -875,10 +873,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
* descriptor
*/
err = ext4_mb_add_groupinfo(sb, input->group, gdp);
- if (err) {
- ext4_mb_put_buddy_cache_lock(sb, input->group, num_grp_locked);
+ if (err)
goto exit_journal;
- }
/*
* Make the new blocks and inodes valid next. We do this before
@@ -920,7 +916,6 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
/* Update the global fs size fields */
sbi->s_groups_count++;
- ext4_mb_put_buddy_cache_lock(sb, input->group, num_grp_locked);
ext4_handle_dirty_metadata(handle, NULL, primary);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 8f4f079e6b9..a6b1ab73472 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -45,6 +45,7 @@
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
+#include "mballoc.h"
#define CREATE_TRACE_POINTS
#include <trace/events/ext4.h>
@@ -344,7 +345,8 @@ static const char *ext4_decode_error(struct super_block *sb, int errno,
errstr = "Out of memory";
break;
case -EROFS:
- if (!sb || EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT)
+ if (!sb || (EXT4_SB(sb)->s_journal &&
+ EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT))
errstr = "Journal has aborted";
else
errstr = "Readonly filesystem";
@@ -1279,11 +1281,9 @@ static int parse_options(char *options, struct super_block *sb,
*journal_devnum = option;
break;
case Opt_journal_checksum:
- set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
- break;
+ break; /* Kept for backwards compatibility */
case Opt_journal_async_commit:
set_opt(sbi->s_mount_opt, JOURNAL_ASYNC_COMMIT);
- set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
break;
case Opt_noload:
set_opt(sbi->s_mount_opt, NOLOAD);
@@ -1695,12 +1695,12 @@ static int ext4_fill_flex_info(struct super_block *sb)
gdp = ext4_get_group_desc(sb, i, NULL);
flex_group = ext4_flex_group(sbi, i);
- atomic_set(&sbi->s_flex_groups[flex_group].free_inodes,
- ext4_free_inodes_count(sb, gdp));
- atomic_set(&sbi->s_flex_groups[flex_group].free_blocks,
- ext4_free_blks_count(sb, gdp));
- atomic_set(&sbi->s_flex_groups[flex_group].used_dirs,
- ext4_used_dirs_count(sb, gdp));
+ 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_used_dirs_count(sb, gdp),
+ &sbi->s_flex_groups[flex_group].used_dirs);
}
return 1;
@@ -2253,6 +2253,49 @@ static struct kobj_type ext4_ktype = {
.release = ext4_sb_release,
};
+/*
+ * Check whether this filesystem can be mounted based on
+ * the features present and the RDONLY/RDWR mount requested.
+ * Returns 1 if this filesystem can be mounted as requested,
+ * 0 if it cannot be.
+ */
+static int ext4_feature_set_ok(struct super_block *sb, int readonly)
+{
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP)) {
+ ext4_msg(sb, KERN_ERR,
+ "Couldn't mount because of "
+ "unsupported optional features (%x)",
+ (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) &
+ ~EXT4_FEATURE_INCOMPAT_SUPP));
+ return 0;
+ }
+
+ if (readonly)
+ return 1;
+
+ /* Check that feature set is OK for a read-write mount */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP)) {
+ ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of "
+ "unsupported optional features (%x)",
+ (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
+ ~EXT4_FEATURE_RO_COMPAT_SUPP));
+ return 0;
+ }
+ /*
+ * Large file size enabled file system can only be mounted
+ * read-write on 32-bit systems if kernel is built with CONFIG_LBDAF
+ */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
+ if (sizeof(blkcnt_t) < sizeof(u64)) {
+ ext4_msg(sb, KERN_ERR, "Filesystem with huge files "
+ "cannot be mounted RDWR without "
+ "CONFIG_LBDAF");
+ return 0;
+ }
+ }
+ return 1;
+}
+
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
__releases(kernel_lock)
__acquires(kernel_lock)
@@ -2274,7 +2317,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
unsigned int db_count;
unsigned int i;
int needs_recovery, has_huge_files;
- int features;
__u64 blocks_count;
int err;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
@@ -2401,39 +2443,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
* previously didn't change the revision level when setting the flags,
* so there is a chance incompat flags are set on a rev 0 filesystem.
*/
- features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP);
- if (features) {
- ext4_msg(sb, KERN_ERR,
- "Couldn't mount because of "
- "unsupported optional features (%x)",
- (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) &
- ~EXT4_FEATURE_INCOMPAT_SUPP));
- goto failed_mount;
- }
- features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP);
- if (!(sb->s_flags & MS_RDONLY) && features) {
- ext4_msg(sb, KERN_ERR,
- "Couldn't mount RDWR because of "
- "unsupported optional features (%x)",
- (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
- ~EXT4_FEATURE_RO_COMPAT_SUPP));
+ if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY)))
goto failed_mount;
- }
- has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
- if (has_huge_files) {
- /*
- * Large file size enabled file system can only be
- * mount if kernel is build with CONFIG_LBDAF
- */
- if (sizeof(root->i_blocks) < sizeof(u64) &&
- !(sb->s_flags & MS_RDONLY)) {
- ext4_msg(sb, KERN_ERR, "Filesystem with huge "
- "files cannot be mounted read-write "
- "without CONFIG_LBDAF");
- goto failed_mount;
- }
- }
+
blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
@@ -2469,6 +2481,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
}
+ has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits,
has_huge_files);
sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files);
@@ -2549,12 +2563,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount;
}
- if (ext4_blocks_count(es) >
- (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
+ /*
+ * Test whether we have more sectors than will fit in sector_t,
+ * and whether the max offset is addressable by the page cache.
+ */
+ if ((ext4_blocks_count(es) >
+ (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) ||
+ (ext4_blocks_count(es) >
+ (pgoff_t)(~0ULL) >> (PAGE_CACHE_SHIFT - sb->s_blocksize_bits))) {
ext4_msg(sb, KERN_ERR, "filesystem"
- " too large to mount safely");
+ " too large to mount safely on this system");
if (sizeof(sector_t) < 8)
ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled");
+ ret = -EFBIG;
goto failed_mount;
}
@@ -2595,6 +2616,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount;
}
sbi->s_groups_count = blocks_count;
+ sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
+ (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 *),
@@ -2729,20 +2752,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount4;
}
- if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
- jbd2_journal_set_features(sbi->s_journal,
- JBD2_FEATURE_COMPAT_CHECKSUM, 0,
+ jbd2_journal_set_features(sbi->s_journal,
+ JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0);
+ if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
+ jbd2_journal_set_features(sbi->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
- } else if (test_opt(sb, JOURNAL_CHECKSUM)) {
- jbd2_journal_set_features(sbi->s_journal,
- JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0);
+ else
jbd2_journal_clear_features(sbi->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
- } else {
- jbd2_journal_clear_features(sbi->s_journal,
- JBD2_FEATURE_COMPAT_CHECKSUM, 0,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
- }
/* We have now updated the journal if required, so we can
* validate the data journaling mode. */
@@ -3208,7 +3225,18 @@ static int ext4_commit_super(struct super_block *sb, int sync)
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
- es->s_wtime = cpu_to_le32(get_seconds());
+ /*
+ * If the file system is mounted read-only, don't update the
+ * superblock write time. This avoids updating the superblock
+ * write time when we are mounting the root file system
+ * read/only but we need to replay the journal; at that point,
+ * for people who are east of GMT and who make their clock
+ * tick in localtime for Windows bug-for-bug compatibility,
+ * the clock is set in the future, and this will cause e2fsck
+ * to complain and force a full file system check.
+ */
+ if (!(sb->s_flags & MS_RDONLY))
+ es->s_wtime = cpu_to_le32(get_seconds());
es->s_kbytes_written =
cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
@@ -3477,18 +3505,11 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
if (sbi->s_journal)
ext4_mark_recovery_complete(sb, es);
} else {
- int ret;
- if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb,
- ~EXT4_FEATURE_RO_COMPAT_SUPP))) {
- ext4_msg(sb, KERN_WARNING, "couldn't "
- "remount RDWR because of unsupported "
- "optional features (%x)",
- (le32_to_cpu(sbi->s_es->s_feature_ro_compat) &
- ~EXT4_FEATURE_RO_COMPAT_SUPP));
+ /* Make sure we can mount this feature set readwrite */
+ if (!ext4_feature_set_ok(sb, 0)) {
err = -EROFS;
goto restore_opts;
}
-
/*
* Make sure the group descriptor checksums
* are sane. If they aren't, refuse to remount r/w.
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 62b31c24699..fed5b01d7a8 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -810,12 +810,23 @@ inserted:
get_bh(new_bh);
} else {
/* We need to allocate a new block */
- ext4_fsblk_t goal = ext4_group_first_block_no(sb,
+ ext4_fsblk_t goal, block;
+
+ goal = ext4_group_first_block_no(sb,
EXT4_I(inode)->i_block_group);
- ext4_fsblk_t block = ext4_new_meta_blocks(handle, inode,
+
+ /* non-extent files can't have physical blocks past 2^32 */
+ if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
+
+ block = ext4_new_meta_blocks(handle, inode,
goal, NULL, &error);
if (error)
goto cleanup;
+
+ if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);
+
ea_idebug(inode, "creating block %d", block);
new_bh = sb_getblk(sb, block);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 0df600e9162..26d991ddc1e 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -25,6 +25,7 @@
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
+#include <linux/blkdev.h>
#include <trace/events/jbd2.h>
/*
@@ -133,8 +134,8 @@ static int journal_submit_commit_record(journal_t *journal,
bh->b_end_io = journal_end_buffer_io_sync;
if (journal->j_flags & JBD2_BARRIER &&
- !JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
+ !JBD2_HAS_INCOMPAT_FEATURE(journal,
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
set_buffer_ordered(bh);
barrier_done = 1;
}
@@ -706,11 +707,13 @@ start_journal_io:
/* Done it all: now write the commit record asynchronously. */
if (JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
err = journal_submit_commit_record(journal, commit_transaction,
&cbh, crc32_sum);
if (err)
__jbd2_journal_abort_hard(journal);
+ if (journal->j_flags & JBD2_BARRIER)
+ blkdev_issue_flush(journal->j_dev, NULL);
}
/*
@@ -833,7 +836,7 @@ wait_for_iobuf:
jbd_debug(3, "JBD: commit phase 5\n");
if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
err = journal_submit_commit_record(journal, commit_transaction,
&cbh, crc32_sum);
if (err)
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index e378cb38397..a8a358bc0f2 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1187,6 +1187,12 @@ static int journal_reset(journal_t *journal)
first = be32_to_cpu(sb->s_first);
last = be32_to_cpu(sb->s_maxlen);
+ if (first + JBD2_MIN_JOURNAL_BLOCKS > last + 1) {
+ printk(KERN_ERR "JBD: Journal too short (blocks %llu-%llu).\n",
+ first, last);
+ journal_fail_superblock(journal);
+ return -EINVAL;
+ }
journal->j_first = first;
journal->j_last = last;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 6213ac728f3..a0512700542 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -57,7 +57,7 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
INIT_LIST_HEAD(&transaction->t_private_list);
/* Set up the commit timer for the new transaction. */
- journal->j_commit_timer.expires = round_jiffies(transaction->t_expires);
+ journal->j_commit_timer.expires = round_jiffies_up(transaction->t_expires);
add_timer(&journal->j_commit_timer);
J_ASSERT(journal->j_running_transaction == NULL);
@@ -238,6 +238,8 @@ repeat_locked:
__jbd2_log_space_left(journal));
spin_unlock(&transaction->t_handle_lock);
spin_unlock(&journal->j_state_lock);
+
+ lock_map_acquire(&handle->h_lockdep_map);
out:
if (unlikely(new_transaction)) /* It's usually NULL */
kfree(new_transaction);
@@ -303,8 +305,6 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
handle = ERR_PTR(err);
goto out;
}
-
- lock_map_acquire(&handle->h_lockdep_map);
out:
return handle;
}
@@ -426,6 +426,7 @@ int jbd2_journal_restart(handle_t *handle, int nblocks)
__jbd2_log_start_commit(journal, transaction->t_tid);
spin_unlock(&journal->j_state_lock);
+ lock_map_release(&handle->h_lockdep_map);
handle->h_buffer_credits = nblocks;
ret = start_this_handle(journal, handle);
return ret;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d97eb652d6c..52695d3dfd0 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -652,7 +652,7 @@ struct transaction_s
* This transaction is being forced and some process is
* waiting for it to finish.
*/
- int t_synchronous_commit:1;
+ unsigned int t_synchronous_commit:1;
/*
* For use by the filesystem to store fs-specific data
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 8d433c4e370..c1bd8f1e8b9 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -5,10 +5,15 @@
#define _TRACE_EXT4_H
#include <linux/writeback.h>
-#include "../../../fs/ext4/ext4.h"
-#include "../../../fs/ext4/mballoc.h"
#include <linux/tracepoint.h>
+struct ext4_allocation_context;
+struct ext4_allocation_request;
+struct ext4_prealloc_space;
+struct ext4_inode_info;
+
+#define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode))
+
TRACE_EVENT(ext4_free_inode,
TP_PROTO(struct inode *inode),
@@ -33,8 +38,8 @@ TRACE_EVENT(ext4_free_inode,
),
TP_printk("dev %s ino %lu mode %d uid %u gid %u blocks %llu",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->mode,
- __entry->uid, __entry->gid,
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->mode, __entry->uid, __entry->gid,
(unsigned long long) __entry->blocks)
);
@@ -56,7 +61,8 @@ TRACE_EVENT(ext4_request_inode,
),
TP_printk("dev %s dir %lu mode %d",
- jbd2_dev_to_name(__entry->dev), __entry->dir, __entry->mode)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->dir,
+ __entry->mode)
);
TRACE_EVENT(ext4_allocate_inode,
@@ -79,7 +85,8 @@ TRACE_EVENT(ext4_allocate_inode,
),
TP_printk("dev %s ino %lu dir %lu mode %d",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->dir, __entry->mode)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ (unsigned long) __entry->dir, __entry->mode)
);
TRACE_EVENT(ext4_write_begin,
@@ -106,8 +113,8 @@ TRACE_EVENT(ext4_write_begin,
),
TP_printk("dev %s ino %lu pos %llu len %u flags %u",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
- __entry->flags)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->pos, __entry->len, __entry->flags)
);
TRACE_EVENT(ext4_ordered_write_end,
@@ -133,8 +140,8 @@ TRACE_EVENT(ext4_ordered_write_end,
),
TP_printk("dev %s ino %lu pos %llu len %u copied %u",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
- __entry->copied)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->pos, __entry->len, __entry->copied)
);
TRACE_EVENT(ext4_writeback_write_end,
@@ -160,8 +167,8 @@ TRACE_EVENT(ext4_writeback_write_end,
),
TP_printk("dev %s ino %lu pos %llu len %u copied %u",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
- __entry->copied)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->pos, __entry->len, __entry->copied)
);
TRACE_EVENT(ext4_journalled_write_end,
@@ -186,8 +193,8 @@ TRACE_EVENT(ext4_journalled_write_end,
),
TP_printk("dev %s ino %lu pos %llu len %u copied %u",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
- __entry->copied)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->pos, __entry->len, __entry->copied)
);
TRACE_EVENT(ext4_writepage,
@@ -209,7 +216,8 @@ TRACE_EVENT(ext4_writepage,
),
TP_printk("dev %s ino %lu page_index %lu",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->index)
);
TRACE_EVENT(ext4_da_writepages,
@@ -243,14 +251,49 @@ TRACE_EVENT(ext4_da_writepages,
__entry->range_cyclic = wbc->range_cyclic;
),
- TP_printk("dev %s ino %lu nr_t_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->nr_to_write,
+ TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d",
+ jbd2_dev_to_name(__entry->dev),
+ (unsigned long) __entry->ino, __entry->nr_to_write,
__entry->pages_skipped, __entry->range_start,
__entry->range_end, __entry->nonblocking,
__entry->for_kupdate, __entry->for_reclaim,
__entry->range_cyclic)
);
+TRACE_EVENT(ext4_da_write_pages,
+ TP_PROTO(struct inode *inode, struct mpage_da_data *mpd),
+
+ TP_ARGS(inode, mpd),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( ino_t, ino )
+ __field( __u64, b_blocknr )
+ __field( __u32, b_size )
+ __field( __u32, b_state )
+ __field( unsigned long, first_page )
+ __field( int, io_done )
+ __field( int, pages_written )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->b_blocknr = mpd->b_blocknr;
+ __entry->b_size = mpd->b_size;
+ __entry->b_state = mpd->b_state;
+ __entry->first_page = mpd->first_page;
+ __entry->io_done = mpd->io_done;
+ __entry->pages_written = mpd->pages_written;
+ ),
+
+ TP_printk("dev %s ino %lu b_blocknr %llu b_size %u b_state 0x%04x first_page %lu io_done %d pages_written %d",
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->b_blocknr, __entry->b_size,
+ __entry->b_state, __entry->first_page,
+ __entry->io_done, __entry->pages_written)
+);
+
TRACE_EVENT(ext4_da_writepages_result,
TP_PROTO(struct inode *inode, struct writeback_control *wbc,
int ret, int pages_written),
@@ -280,7 +323,8 @@ TRACE_EVENT(ext4_da_writepages_result,
),
TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld congestion %d more_io %d no_nrwrite_index_update %d",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->ret,
+ jbd2_dev_to_name(__entry->dev),
+ (unsigned long) __entry->ino, __entry->ret,
__entry->pages_written, __entry->pages_skipped,
__entry->encountered_congestion, __entry->more_io,
__entry->no_nrwrite_index_update)
@@ -309,8 +353,8 @@ TRACE_EVENT(ext4_da_write_begin,
),
TP_printk("dev %s ino %lu pos %llu len %u flags %u",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
- __entry->flags)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->pos, __entry->len, __entry->flags)
);
TRACE_EVENT(ext4_da_write_end,
@@ -336,8 +380,8 @@ TRACE_EVENT(ext4_da_write_end,
),
TP_printk("dev %s ino %lu pos %llu len %u copied %u",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
- __entry->copied)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->pos, __entry->len, __entry->copied)
);
TRACE_EVENT(ext4_discard_blocks,
@@ -387,8 +431,8 @@ TRACE_EVENT(ext4_mb_new_inode_pa,
),
TP_printk("dev %s ino %lu pstart %llu len %u lstart %llu",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pa_pstart,
- __entry->pa_len, __entry->pa_lstart)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart)
);
TRACE_EVENT(ext4_mb_new_group_pa,
@@ -415,8 +459,8 @@ TRACE_EVENT(ext4_mb_new_group_pa,
),
TP_printk("dev %s ino %lu pstart %llu len %u lstart %llu",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pa_pstart,
- __entry->pa_len, __entry->pa_lstart)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart)
);
TRACE_EVENT(ext4_mb_release_inode_pa,
@@ -442,8 +486,8 @@ TRACE_EVENT(ext4_mb_release_inode_pa,
),
TP_printk("dev %s ino %lu block %llu count %u",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->block,
- __entry->count)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->block, __entry->count)
);
TRACE_EVENT(ext4_mb_release_group_pa,
@@ -488,7 +532,7 @@ TRACE_EVENT(ext4_discard_preallocations,
),
TP_printk("dev %s ino %lu",
- jbd2_dev_to_name(__entry->dev), __entry->ino)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino)
);
TRACE_EVENT(ext4_mb_discard_preallocations,
@@ -543,8 +587,8 @@ TRACE_EVENT(ext4_request_blocks,
),
TP_printk("dev %s ino %lu flags %u len %u lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->flags,
- __entry->len,
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->flags, __entry->len,
(unsigned long long) __entry->logical,
(unsigned long long) __entry->goal,
(unsigned long long) __entry->lleft,
@@ -587,8 +631,8 @@ TRACE_EVENT(ext4_allocate_blocks,
),
TP_printk("dev %s ino %lu flags %u len %u block %llu lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->flags,
- __entry->len, __entry->block,
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->flags, __entry->len, __entry->block,
(unsigned long long) __entry->logical,
(unsigned long long) __entry->goal,
(unsigned long long) __entry->lleft,
@@ -621,8 +665,8 @@ TRACE_EVENT(ext4_free_blocks,
),
TP_printk("dev %s ino %lu block %llu count %lu metadata %d",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->block,
- __entry->count, __entry->metadata)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->block, __entry->count, __entry->metadata)
);
TRACE_EVENT(ext4_sync_file,
@@ -645,8 +689,8 @@ TRACE_EVENT(ext4_sync_file,
),
TP_printk("dev %s ino %ld parent %ld datasync %d ",
- jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->parent,
- __entry->datasync)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ (unsigned long) __entry->parent, __entry->datasync)
);
TRACE_EVENT(ext4_sync_fs,
@@ -669,6 +713,30 @@ TRACE_EVENT(ext4_sync_fs,
__entry->wait)
);
+TRACE_EVENT(ext4_alloc_da_blocks,
+ TP_PROTO(struct inode *inode),
+
+ TP_ARGS(inode),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( ino_t, ino )
+ __field( unsigned int, data_blocks )
+ __field( unsigned int, meta_blocks )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
+ __entry->meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
+ ),
+
+ TP_printk("dev %s ino %lu data_blocks %u meta_blocks %u",
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+ __entry->data_blocks, __entry->meta_blocks)
+);
+
#endif /* _TRACE_EXT4_H */
/* This part must be outside protection */
diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h
index 10813fa0c8d..b851f0b4701 100644
--- a/include/trace/events/jbd2.h
+++ b/include/trace/events/jbd2.h
@@ -159,7 +159,7 @@ TRACE_EVENT(jbd2_submit_inode_data,
),
TP_printk("dev %s ino %lu",
- jbd2_dev_to_name(__entry->dev), __entry->ino)
+ jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino)
);
#endif /* _TRACE_JBD2_H */
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-25 21:29:03 +0000