summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/acl.c2
-rw-r--r--fs/ext4/balloc.c5
-rw-r--r--fs/ext4/ext4.h12
-rw-r--r--fs/ext4/ext4_jbd2.h11
-rw-r--r--fs/ext4/extents.c223
-rw-r--r--fs/ext4/fsync.c33
-rw-r--r--fs/ext4/ialloc.c8
-rw-r--r--fs/ext4/inode.c467
-rw-r--r--fs/ext4/ioctl.c15
-rw-r--r--fs/ext4/mballoc.c36
-rw-r--r--fs/ext4/mballoc.h2
-rw-r--r--fs/ext4/migrate.c12
-rw-r--r--fs/ext4/namei.c13
-rw-r--r--fs/ext4/page-io.c16
-rw-r--r--fs/ext4/resize.c12
-rw-r--r--fs/ext4/super.c126
-rw-r--r--fs/ext4/xattr.c4
17 files changed, 579 insertions, 418 deletions
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index e0270d1f8d82..21eacd7b7d79 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -433,7 +433,7 @@ ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
return -EINVAL;
if (!test_opt(inode->i_sb, POSIX_ACL))
return -EOPNOTSUPP;
- if (!is_owner_or_cap(inode))
+ if (!inode_owner_or_capable(inode))
return -EPERM;
if (value) {
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index adf96b822781..1c67139ad4b4 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -21,6 +21,8 @@
#include "ext4_jbd2.h"
#include "mballoc.h"
+#include <trace/events/ext4.h>
+
/*
* balloc.c contains the blocks allocation and deallocation routines
*/
@@ -342,6 +344,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
* We do it here so the bitmap uptodate bit
* get set with buffer lock held.
*/
+ trace_ext4_read_block_bitmap_load(sb, block_group);
set_bitmap_uptodate(bh);
if (bh_submit_read(bh) < 0) {
put_bh(bh);
@@ -544,7 +547,7 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
*
* ext4_should_retry_alloc() is called when ENOSPC is returned, and if
* it is profitable to retry the operation, this function will wait
- * for the current or commiting transaction to complete, and then
+ * for the current or committing transaction to complete, and then
* return TRUE.
*
* if the total number of retries exceed three times, return FALSE.
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 3aa0b72b3b94..4daaf2b753f4 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -923,14 +923,14 @@ struct ext4_inode_info {
#define test_opt2(sb, opt) (EXT4_SB(sb)->s_mount_opt2 & \
EXT4_MOUNT2_##opt)
-#define ext4_set_bit ext2_set_bit
+#define ext4_set_bit __test_and_set_bit_le
#define ext4_set_bit_atomic ext2_set_bit_atomic
-#define ext4_clear_bit ext2_clear_bit
+#define ext4_clear_bit __test_and_clear_bit_le
#define ext4_clear_bit_atomic ext2_clear_bit_atomic
-#define ext4_test_bit ext2_test_bit
-#define ext4_find_first_zero_bit ext2_find_first_zero_bit
-#define ext4_find_next_zero_bit ext2_find_next_zero_bit
-#define ext4_find_next_bit ext2_find_next_bit
+#define ext4_test_bit test_bit_le
+#define ext4_find_first_zero_bit find_first_zero_bit_le
+#define ext4_find_next_zero_bit find_next_zero_bit_le
+#define ext4_find_next_bit find_next_bit_le
/*
* Maximal mount counts between two filesystem checks
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index d8b992e658c1..d0f53538a57f 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -86,8 +86,8 @@
#ifdef CONFIG_QUOTA
/* Amount of blocks needed for quota update - we know that the structure was
- * allocated so we need to update only inode+data */
-#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0)
+ * allocated so we need to update only data block */
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 1 : 0)
/* Amount of blocks needed for quota insert/delete - we do some block writes
* but inode, sb and group updates are done only once */
#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
@@ -202,13 +202,6 @@ static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
return 1;
}
-static inline void ext4_journal_release_buffer(handle_t *handle,
- struct buffer_head *bh)
-{
- if (ext4_handle_valid(handle))
- jbd2_journal_release_buffer(handle, bh);
-}
-
static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
{
return ext4_journal_start_sb(inode->i_sb, nblocks);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 7516fb9c0bd5..4890d6f3ad15 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -44,6 +44,8 @@
#include "ext4_jbd2.h"
#include "ext4_extents.h"
+#include <trace/events/ext4.h>
+
static int ext4_ext_truncate_extend_restart(handle_t *handle,
struct inode *inode,
int needed)
@@ -664,6 +666,8 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
if (unlikely(!bh))
goto err;
if (!bh_uptodate_or_lock(bh)) {
+ trace_ext4_ext_load_extent(inode, block,
+ path[ppos].p_block);
if (bh_submit_read(bh) < 0) {
put_bh(bh);
goto err;
@@ -1034,7 +1038,7 @@ cleanup:
for (i = 0; i < depth; i++) {
if (!ablocks[i])
continue;
- ext4_free_blocks(handle, inode, 0, ablocks[i], 1,
+ ext4_free_blocks(handle, inode, NULL, ablocks[i], 1,
EXT4_FREE_BLOCKS_METADATA);
}
}
@@ -1725,7 +1729,7 @@ repeat:
BUG_ON(npath->p_depth != path->p_depth);
eh = npath[depth].p_hdr;
if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) {
- ext_debug("next leaf isnt full(%d)\n",
+ ext_debug("next leaf isn't full(%d)\n",
le16_to_cpu(eh->eh_entries));
path = npath;
goto repeat;
@@ -2059,7 +2063,7 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
if (err)
return err;
ext_debug("index is empty, remove it, free block %llu\n", leaf);
- ext4_free_blocks(handle, inode, 0, leaf, 1,
+ ext4_free_blocks(handle, inode, NULL, leaf, 1,
EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
return err;
}
@@ -2156,7 +2160,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
num = le32_to_cpu(ex->ee_block) + ee_len - from;
start = ext4_ext_pblock(ex) + ee_len - num;
ext_debug("free last %u blocks starting %llu\n", num, start);
- ext4_free_blocks(handle, inode, 0, start, num, flags);
+ ext4_free_blocks(handle, inode, NULL, start, num, flags);
} else if (from == le32_to_cpu(ex->ee_block)
&& to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
printk(KERN_INFO "strange request: removal %u-%u from %u:%u\n",
@@ -2529,7 +2533,7 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
/*
* This function is called by ext4_ext_map_blocks() if someone tries to write
* to an uninitialized extent. It may result in splitting the uninitialized
- * extent into multiple extents (upto three - one initialized and two
+ * extent into multiple extents (up to three - one initialized and two
* uninitialized).
* There are three possibilities:
* a> There is no split required: Entire extent should be initialized
@@ -3108,14 +3112,13 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
{
int i, depth;
struct ext4_extent_header *eh;
- struct ext4_extent *ex, *last_ex;
+ struct ext4_extent *last_ex;
if (!ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))
return 0;
depth = ext_depth(inode);
eh = path[depth].p_hdr;
- ex = path[depth].p_ext;
if (unlikely(!eh->eh_entries)) {
EXT4_ERROR_INODE(inode, "eh->eh_entries == 0 and "
@@ -3171,7 +3174,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
path, flags);
/*
* Flag the inode(non aio case) or end_io struct (aio case)
- * that this IO needs to convertion to written when IO is
+ * that this IO needs to conversion to written when IO is
* completed
*/
if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
@@ -3295,9 +3298,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags)
{
struct ext4_ext_path *path = NULL;
- struct ext4_extent_header *eh;
struct ext4_extent newex, *ex;
- ext4_fsblk_t newblock;
+ ext4_fsblk_t newblock = 0;
int err = 0, depth, ret;
unsigned int allocated = 0;
struct ext4_allocation_request ar;
@@ -3305,6 +3307,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ext_debug("blocks %u/%u requested for inode %lu\n",
map->m_lblk, map->m_len, inode->i_ino);
+ trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
/* check in cache */
if (ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
@@ -3352,7 +3355,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
err = -EIO;
goto out2;
}
- eh = path[depth].p_hdr;
ex = path[depth].p_ext;
if (ex) {
@@ -3458,10 +3460,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ext4_ext_mark_uninitialized(&newex);
/*
* io_end structure was created for every IO write to an
- * uninitialized extent. To avoid unecessary conversion,
+ * uninitialized extent. To avoid unnecessary conversion,
* here we flag the IO that really needs the conversion.
* For non asycn direct IO case, flag the inode state
- * that we need to perform convertion when IO is done.
+ * that we need to perform conversion when IO is done.
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
@@ -3485,7 +3487,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/* not a good idea to call discard here directly,
* but otherwise we'd need to call it every free() */
ext4_discard_preallocations(inode);
- ext4_free_blocks(handle, inode, 0, ext4_ext_pblock(&newex),
+ ext4_free_blocks(handle, inode, NULL, ext4_ext_pblock(&newex),
ext4_ext_get_actual_len(&newex), 0);
goto out2;
}
@@ -3525,6 +3527,8 @@ out2:
ext4_ext_drop_refs(path);
kfree(path);
}
+ trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
+ newblock, map->m_len, err ? err : allocated);
return err ? err : allocated;
}
@@ -3658,6 +3662,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EOPNOTSUPP;
+ trace_ext4_fallocate_enter(inode, offset, len, mode);
map.m_lblk = offset >> blkbits;
/*
* We can't just convert len to max_blocks because
@@ -3673,6 +3678,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
ret = inode_newsize_ok(inode, (len + offset));
if (ret) {
mutex_unlock(&inode->i_mutex);
+ trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
return ret;
}
retry:
@@ -3717,6 +3723,8 @@ retry:
goto retry;
}
mutex_unlock(&inode->i_mutex);
+ trace_ext4_fallocate_exit(inode, offset, max_blocks,
+ ret > 0 ? ret2 : ret);
return ret > 0 ? ret2 : ret;
}
@@ -3775,6 +3783,7 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
}
return ret > 0 ? ret2 : ret;
}
+
/*
* Callback function called for each extent to gather FIEMAP information.
*/
@@ -3782,38 +3791,162 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
struct ext4_ext_cache *newex, struct ext4_extent *ex,
void *data)
{
- struct fiemap_extent_info *fieinfo = data;
- unsigned char blksize_bits = inode->i_sb->s_blocksize_bits;
__u64 logical;
__u64 physical;
__u64 length;
+ loff_t size;
__u32 flags = 0;
- int error;
+ int ret = 0;
+ struct fiemap_extent_info *fieinfo = data;
+ unsigned char blksize_bits;
- logical = (__u64)newex->ec_block << blksize_bits;
+ blksize_bits = inode->i_sb->s_blocksize_bits;
+ logical = (__u64)newex->ec_block << blksize_bits;
if (newex->ec_start == 0) {
- pgoff_t offset;
- struct page *page;
+ /*
+ * No extent in extent-tree contains block @newex->ec_start,
+ * then the block may stay in 1)a hole or 2)delayed-extent.
+ *
+ * Holes or delayed-extents are processed as follows.
+ * 1. lookup dirty pages with specified range in pagecache.
+ * If no page is got, then there is no delayed-extent and
+ * return with EXT_CONTINUE.
+ * 2. find the 1st mapped buffer,
+ * 3. check if the mapped buffer is both in the request range
+ * and a delayed buffer. If not, there is no delayed-extent,
+ * then return.
+ * 4. a delayed-extent is found, the extent will be collected.
+ */
+ ext4_lblk_t end = 0;
+ pgoff_t last_offset;
+ pgoff_t offset;
+ pgoff_t index;
+ struct page **pages = NULL;
struct buffer_head *bh = NULL;
+ struct buffer_head *head = NULL;
+ unsigned int nr_pages = PAGE_SIZE / sizeof(struct page *);
+
+ pages = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (pages == NULL)
+ return -ENOMEM;
offset = logical >> PAGE_SHIFT;
- page = find_get_page(inode->i_mapping, offset);
- if (!page || !page_has_buffers(page))
- return EXT_CONTINUE;
+repeat:
+ last_offset = offset;
+ head = NULL;
+ ret = find_get_pages_tag(inode->i_mapping, &offset,
+ PAGECACHE_TAG_DIRTY, nr_pages, pages);
+
+ if (!(flags & FIEMAP_EXTENT_DELALLOC)) {
+ /* First time, try to find a mapped buffer. */
+ if (ret == 0) {
+out:
+ for (index = 0; index < ret; index++)
+ page_cache_release(pages[index]);
+ /* just a hole. */
+ kfree(pages);
+ return EXT_CONTINUE;
+ }
- bh = page_buffers(page);
+ /* Try to find the 1st mapped buffer. */
+ end = ((__u64)pages[0]->index << PAGE_SHIFT) >>
+ blksize_bits;
+ if (!page_has_buffers(pages[0]))
+ goto out;
+ head = page_buffers(pages[0]);
+ if (!head)
+ goto out;
- if (!bh)
- return EXT_CONTINUE;
+ bh = head;
+ do {
+ if (buffer_mapped(bh)) {
+ /* get the 1st mapped buffer. */
+ if (end > newex->ec_block +
+ newex->ec_len)
+ /* The buffer is out of
+ * the request range.
+ */
+ goto out;
+ goto found_mapped_buffer;
+ }
+ bh = bh->b_this_page;
+ end++;
+ } while (bh != head);
- if (buffer_delay(bh)) {
- flags |= FIEMAP_EXTENT_DELALLOC;
- page_cache_release(page);
+ /* No mapped buffer found. */
+ goto out;
} else {
- page_cache_release(page);
- return EXT_CONTINUE;
+ /*Find contiguous delayed buffers. */
+ if (ret > 0 && pages[0]->index == last_offset)
+ head = page_buffers(pages[0]);
+ bh = head;
}
+
+found_mapped_buffer:
+ if (bh != NULL && buffer_delay(bh)) {
+ /* 1st or contiguous delayed buffer found. */
+ if (!(flags & FIEMAP_EXTENT_DELALLOC)) {
+ /*
+ * 1st delayed buffer found, record
+ * the start of extent.
+ */
+ flags |= FIEMAP_EXTENT_DELALLOC;
+ newex->ec_block = end;
+ logical = (__u64)end << blksize_bits;
+ }
+ /* Find contiguous delayed buffers. */
+ do {
+ if (!buffer_delay(bh))
+ goto found_delayed_extent;
+ bh = bh->b_this_page;
+ end++;
+ } while (bh != head);
+
+ for (index = 1; index < ret; index++) {
+ if (!page_has_buffers(pages[index])) {
+ bh = NULL;
+ break;
+ }
+ head = page_buffers(pages[index]);
+ if (!head) {
+ bh = NULL;
+ break;
+ }
+ if (pages[index]->index !=
+ pages[0]->index + index) {
+ /* Blocks are not contiguous. */
+ bh = NULL;
+ break;
+ }
+ bh = head;
+ do {
+ if (!buffer_delay(bh))
+ /* Delayed-extent ends. */
+ goto found_delayed_extent;
+ bh = bh->b_this_page;
+ end++;
+ } while (bh != head);
+ }
+ } else if (!(flags & FIEMAP_EXTENT_DELALLOC))
+ /* a hole found. */
+ goto out;
+
+found_delayed_extent:
+ newex->ec_len = min(end - newex->ec_block,
+ (ext4_lblk_t)EXT_INIT_MAX_LEN);
+ if (ret == nr_pages && bh != NULL &&
+ newex->ec_len < EXT_INIT_MAX_LEN &&
+ buffer_delay(bh)) {
+ /* Have not collected an extent and continue. */
+ for (index = 0; index < ret; index++)
+ page_cache_release(pages[index]);
+ goto repeat;
+ }
+
+ for (index = 0; index < ret; index++)
+ page_cache_release(pages[index]);
+ kfree(pages);
}
physical = (__u64)newex->ec_start << blksize_bits;
@@ -3822,32 +3955,16 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
if (ex && ext4_ext_is_uninitialized(ex))
flags |= FIEMAP_EXTENT_UNWRITTEN;
- /*
- * If this extent reaches EXT_MAX_BLOCK, it must be last.
- *
- * Or if ext4_ext_next_allocated_block is EXT_MAX_BLOCK,
- * this also indicates no more allocated blocks.
- *
- * XXX this might miss a single-block extent at EXT_MAX_BLOCK
- */
- if (ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK ||
- newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) {
- loff_t size = i_size_read(inode);
- loff_t bs = EXT4_BLOCK_SIZE(inode->i_sb);
-
+ size = i_size_read(inode);
+ if (logical + length >= size)
flags |= FIEMAP_EXTENT_LAST;
- if ((flags & FIEMAP_EXTENT_DELALLOC) &&
- logical+length > size)
- length = (size - logical + bs - 1) & ~(bs-1);
- }
- error = fiemap_fill_next_extent(fieinfo, logical, physical,
+ ret = fiemap_fill_next_extent(fieinfo, logical, physical,
length, flags);
- if (error < 0)
- return error;
- if (error == 1)
+ if (ret < 0)
+ return ret;
+ if (ret == 1)
return EXT_BREAK;
-
return EXT_CONTINUE;
}
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 7829b287822a..e9473cbe80df 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -101,7 +101,7 @@ extern int ext4_flush_completed_IO(struct inode *inode)
* to the work-to-be schedule is freed.
*
* Thus we need to keep the io structure still valid here after
- * convertion finished. The io structure has a flag to
+ * conversion finished. The io structure has a flag to
* avoid double converting from both fsync and background work
* queue work.
*/
@@ -125,9 +125,11 @@ extern int ext4_flush_completed_IO(struct inode *inode)
* the parent directory's parent as well, and so on recursively, if
* they are also freshly created.
*/
-static void ext4_sync_parent(struct inode *inode)
+static int ext4_sync_parent(struct inode *inode)
{
+ struct writeback_control wbc;
struct dentry *dentry = NULL;
+ int ret = 0;
while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
@@ -136,8 +138,17 @@ static void ext4_sync_parent(struct inode *inode)
if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode)
break;
inode = dentry->d_parent->d_inode;
- sync_mapping_buffers(inode->i_mapping);
+ ret = sync_mapping_buffers(inode->i_mapping);
+ if (ret)
+ break;
+ memset(&wbc, 0, sizeof(wbc));
+ wbc.sync_mode = WB_SYNC_ALL;
+ wbc.nr_to_write = 0; /* only write out the inode */
+ ret = sync_inode(inode, &wbc);
+ if (ret)
+ break;
}
+ return ret;
}
/*
@@ -164,20 +175,20 @@ int ext4_sync_file(struct file *file, int datasync)
J_ASSERT(ext4_journal_current_handle() == NULL);
- trace_ext4_sync_file(file, datasync);
+ trace_ext4_sync_file_enter(file, datasync);
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
ret = ext4_flush_completed_IO(inode);
if (ret < 0)
- return ret;
+ goto out;
if (!journal) {
ret = generic_file_fsync(file, datasync);
if (!ret && !list_empty(&inode->i_dentry))
- ext4_sync_parent(inode);
- return ret;
+ ret = ext4_sync_parent(inode);
+ goto out;
}
/*
@@ -194,8 +205,10 @@ int ext4_sync_file(struct file *file, int datasync)
* (they were dirtied by commit). But that's OK - the blocks are
* safe in-journal, which is all fsync() needs to ensure.
*/
- if (ext4_should_journal_data(inode))
- return ext4_force_commit(inode->i_sb);
+ if (ext4_should_journal_data(inode)) {
+ ret = ext4_force_commit(inode->i_sb);
+ goto out;
+ }
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
if (jbd2_log_start_commit(journal, commit_tid)) {
@@ -215,5 +228,7 @@ int ext4_sync_file(struct file *file, int datasync)
ret = jbd2_log_wait_commit(journal, commit_tid);
} else if (journal->j_flags & JBD2_BARRIER)
blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+ out:
+ trace_ext4_sync_file_exit(inode, ret);
return ret;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 78b79e1bd7ed..21bb2f61e502 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -152,6 +152,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
* We do it here so the bitmap uptodate bit
* get set with buffer lock held.
*/
+ trace_ext4_load_inode_bitmap(sb, block_group);
set_bitmap_uptodate(bh);
if (bh_submit_read(bh) < 0) {
put_bh(bh);
@@ -649,7 +650,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
*group = parent_group + flex_size;
if (*group > ngroups)
*group = 0;
- return find_group_orlov(sb, parent, group, mode, 0);
+ return find_group_orlov(sb, parent, group, mode, NULL);
}
/*
@@ -1054,6 +1055,11 @@ got:
}
}
+ if (ext4_handle_valid(handle)) {
+ ei->i_sync_tid = handle->h_transaction->t_tid;
+ ei->i_datasync_tid = handle->h_transaction->t_tid;
+ }
+
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
ext4_std_error(sb, err);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9f7f9e49914f..f2fa5e8a582c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -173,7 +173,7 @@ int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
BUG_ON(EXT4_JOURNAL(inode) == NULL);
jbd_debug(2, "restarting handle %p\n", handle);
up_write(&EXT4_I(inode)->i_data_sem);
- ret = ext4_journal_restart(handle, blocks_for_truncate(inode));
+ ret = ext4_journal_restart(handle, nblocks);
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode);
@@ -720,7 +720,7 @@ allocated:
return ret;
failed_out:
for (i = 0; i < index; i++)
- ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
+ ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
return ret;
}
@@ -823,20 +823,20 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
return err;
failed:
/* Allocation failed, free what we already allocated */
- ext4_free_blocks(handle, inode, 0, new_blocks[0], 1, 0);
+ ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0);
for (i = 1; i <= n ; i++) {
/*
* branch[i].bh is newly allocated, so there is no
* need to revoke the block, which is why we don't
* need to set EXT4_FREE_BLOCKS_METADATA.
*/
- ext4_free_blocks(handle, inode, 0, new_blocks[i], 1,
+ ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1,
EXT4_FREE_BLOCKS_FORGET);
}
for (i = n+1; i < indirect_blks; i++)
- ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
+ ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
- ext4_free_blocks(handle, inode, 0, new_blocks[i], num, 0);
+ ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0);
return err;
}
@@ -924,7 +924,7 @@ err_out:
ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
EXT4_FREE_BLOCKS_FORGET);
}
- ext4_free_blocks(handle, inode, 0, le32_to_cpu(where[num].key),
+ ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key),
blks, 0);
return err;
@@ -973,6 +973,7 @@ static int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
int count = 0;
ext4_fsblk_t first_block = 0;
+ trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
depth = ext4_block_to_path(inode, map->m_lblk, offsets,
@@ -1058,6 +1059,8 @@ cleanup:
partial--;
}
out:
+ trace_ext4_ind_map_blocks_exit(inode, map->m_lblk,
+ map->m_pblk, map->m_len, err);
return err;
}
@@ -2060,7 +2063,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
- int commit_write = 0, redirty_page = 0;
+ int commit_write = 0, skip_page = 0;
struct page *page = pvec.pages[i];
index = page->index;
@@ -2086,14 +2089,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
* If the page does not have buffers (for
* whatever reason), try to create them using
* __block_write_begin. If this fails,
- * redirty the page and move on.
+ * skip the page and move on.
*/
if (!page_has_buffers(page)) {
if (__block_write_begin(page, 0, len,
noalloc_get_block_write)) {
- redirty_page:
- redirty_page_for_writepage(mpd->wbc,
- page);
+ skip_page:
unlock_page(page);
continue;
}
@@ -2104,7 +2105,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
block_start = 0;
do {
if (!bh)
- goto redirty_page;
+ goto skip_page;
if (map && (cur_logical >= map->m_lblk) &&
(cur_logical <= (map->m_lblk +
(map->m_len - 1)))) {
@@ -2120,22 +2121,23 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
clear_buffer_unwritten(bh);
}
- /* redirty page if block allocation undone */
+ /* skip page if block allocation undone */
if (buffer_delay(bh) || buffer_unwritten(bh))
- redirty_page = 1;
+ skip_page = 1;
bh = bh->b_this_page;
block_start += bh->b_size;
cur_logical++;
pblock++;
} while (bh != page_bufs);
- if (redirty_page)
- goto redirty_page;
+ if (skip_page)
+ goto skip_page;
if (commit_write)
/* mark the buffer_heads as dirty & uptodate */
block_commit_write(page, 0, len);
+ clear_page_dirty_for_io(page);
/*
* Delalloc doesn't support data journalling,
* but eventually maybe we'll lift this
@@ -2165,8 +2167,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
return ret;
}
-static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
- sector_t logical, long blk_cnt)
+static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
{
int nr_pages, i;
pgoff_t index, end;
@@ -2174,9 +2175,8 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
- index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
- end = (logical + blk_cnt - 1) >>
- (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ index = mpd->first_page;
+ end = mpd->next_page - 1;
while (index <= end) {
nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
if (nr_pages == 0)
@@ -2279,9 +2279,8 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
err = blks;
/*
* If get block returns EAGAIN or ENOSPC and there
- * appears to be free blocks we will call
- * ext4_writepage() for all of the pages which will
- * just redirty the pages.
+ * appears to be free blocks we will just let
+ * mpage_da_submit_io() unlock all of the pages.
*/
if (err == -EAGAIN)
goto submit_io;
@@ -2312,8 +2311,10 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
ext4_print_free_blocks(mpd->inode);
}
/* invalidate all the pages */
- ext4_da_block_invalidatepages(mpd, next,
- mpd->b_size >> mpd->inode->i_blkbits);
+ ext4_da_block_invalidatepages(mpd);
+
+ /* Mark this page range as having been completed */
+ mpd->io_done = 1;
return;
}
BUG_ON(blks == 0);
@@ -2438,102 +2439,6 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
}
/*
- * __mpage_da_writepage - finds extent of pages and blocks
- *
- * @page: page to consider
- * @wbc: not used, we just follow rules
- * @data: context
- *
- * The function finds extents of pages and scan them for all blocks.
- */
-static int __mpage_da_writepage(struct page *page,
- struct writeback_control *wbc,
- struct mpage_da_data *mpd)
-{
- struct inode *inode = mpd->inode;
- struct buffer_head *bh, *head;
- sector_t logical;
-
- /*
- * Can we merge this page to current extent?
- */
- if (mpd->next_page != page->index) {
- /*
- * Nope, we can't. So, we map non-allocated blocks
- * and start IO on them
- */
- if (mpd->next_page != mpd->first_page) {
- mpage_da_map_and_submit(mpd);
- /*
- * skip rest of the page in the page_vec
- */
- redirty_page_for_writepage(wbc, page);
- unlock_page(page);
- return MPAGE_DA_EXTENT_TAIL;
- }
-
- /*
- * Start next extent of pages ...
- */
- mpd->first_page = page->index;
-
- /*
- * ... and blocks
- */
- mpd->b_size = 0;
- mpd->b_state = 0;
- mpd->b_blocknr = 0;
- }
-
- mpd->next_page = page->index + 1;
- logical = (sector_t) page->index <<
- (PAGE_CACHE_SHIFT - inode->i_blkbits);
-
- if (!page_has_buffers(page)) {
- mpage_add_bh_to_extent(mpd, logical, PAGE_CACHE_SIZE,
- (1 << BH_Dirty) | (1 << BH_Uptodate));
- if (mpd->io_done)
- return MPAGE_DA_EXTENT_TAIL;
- } else {
- /*
- * Page with regular buffer heads, just add all dirty ones
- */
- head = page_buffers(page);
- bh = head;
- do {
- BUG_ON(buffer_locked(bh));
- /*
- * We need to try to allocate
- * unmapped blocks in the same page.
- * Otherwise we won't make progress
- * with the page in ext4_writepage
- */
- if (ext4_bh_delay_or_unwritten(NULL, bh)) {
- mpage_add_bh_to_extent(mpd, logical,
- bh->b_size,
- bh->b_state);
- if (mpd->io_done)
- return MPAGE_DA_EXTENT_TAIL;
- } else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
- /*
- * mapped dirty buffer. We need to update
- * the b_state because we look at
- * b_state in mpage_da_map_blocks. We don't
- * update b_size because if we find an
- * unmapped buffer_head later we need to
- * use the b_state flag of that buffer_head.
- */
- if (mpd->b_size == 0)
- mpd->b_state = bh->b_state & BH_FLAGS;
- }
- logical++;
- } while ((bh = bh->b_this_page) != head);
- }
-
- return 0;
-}
-
-/*
* This is a special get_blocks_t callback which is used by
* ext4_da_write_begin(). It will either return mapped block or
* reserve space for a single block.
@@ -2684,7 +2589,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
* because we should have holes filled from ext4_page_mkwrite(). We even don't
* need to file the inode to the transaction's list in ordered mode because if
* we are writing back data added by write(), the inode is already there and if
- * we are writing back data modified via mmap(), noone guarantees in which
+ * we are writing back data modified via mmap(), no one guarantees in which
* transaction the data will hit the disk. In case we are journaling data, we
* cannot start transaction directly because transaction start ranks above page
* lock so we have to do some magic.
@@ -2786,7 +2691,7 @@ static int ext4_writepage(struct page *page,
/*
* This is called via ext4_da_writepages() to
- * calulate the total number of credits to reserve to fit
+ * calculate the total number of credits to reserve to fit
* a single extent allocation into a single transaction,
* ext4_da_writpeages() will loop calling this before
* the block allocation.
@@ -2811,27 +2716,27 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode)
/*
* write_cache_pages_da - walk the list of dirty pages of the given
- * address space and call the callback function (which usually writes
- * the pages).
- *
- * This is a forked version of write_cache_pages(). Differences:
- * Range cyclic is ignored.
- * no_nrwrite_index_update is always presumed true
+ * address space and accumulate pages that need writing, and call
+ * mpage_da_map_and_submit to map a single contiguous memory region
+ * and then write them.
*/
static int write_cache_pages_da(struct address_space *mapping,
struct writeback_control *wbc,
struct mpage_da_data *mpd,
pgoff_t *done_index)
{
- int ret = 0;
- int done = 0;
- struct pagevec pvec;
- unsigned nr_pages;
- pgoff_t index;
- pgoff_t end; /* Inclusive */
- long nr_to_write = wbc->nr_to_write;
- int tag;
-
+ struct buffer_head *bh, *head;
+ struct inode *inode = mapping->host;
+ struct pagevec pvec;
+ unsigned int nr_pages;
+ sector_t logical;
+ pgoff_t index, end;
+ long nr_to_write = wbc->nr_to_write;
+ int i, tag, ret = 0;
+
+ memset(mpd, 0, sizeof(struct mpage_da_data));
+ mpd->wbc = wbc;
+ mpd->inode = inode;
pagevec_init(&pvec, 0);
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
@@ -2842,13 +2747,11 @@ static int write_cache_pages_da(struct address_space *mapping,
tag = PAGECACHE_TAG_DIRTY;
*done_index = index;
- while (!done && (index <= end)) {
- int i;
-
+ while (index <= end) {
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
- break;
+ return 0;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
@@ -2860,60 +2763,100 @@ static int write_cache_pages_da(struct address_space *mapping,
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
- if (page->index > end) {
- done = 1;
- break;
- }
+ if (page->index > end)
+ goto out;
*done_index = page->index + 1;
+ /*
+ * If we can't merge this page, and we have
+ * accumulated an contiguous region, write it
+ */
+ if ((mpd->next_page != page->index) &&
+ (mpd->next_page != mpd->first_page)) {
+ mpage_da_map_and_submit(mpd);
+ goto ret_extent_tail;
+ }
+
lock_page(page);
/*
- * Page truncated or invalidated. We can freely skip it
- * then, even for data integrity operations: the page
- * has disappeared concurrently, so there could be no
- * real expectation of this data interity operation
- * even if there is now a new, dirty page at the same
- * pagecache address.
+ * If the page is no longer dirty, or its
+ * mapping no longer corresponds to inode we
+ * are writing (which means it has been
+ * truncated or invalidated), or the page is
+ * already under writeback and we are not
+ * doing a data integrity writeback, skip the page
*/
- if (unlikely(page->mapping != mapping)) {
-continue_unlock:
+ if (!PageDirty(page) ||
+ (PageWriteback(page) &&
+ (wbc->sync_mode == WB_SYNC_NONE)) ||
+ unlikely(page->mapping != mapping)) {
unlock_page(page);
continue;
}
- if (!PageDirty(page)) {
- /* someone wrote it for us */
- goto continue_unlock;
- }
-
- if (PageWriteback(page)) {
- if (wbc->sync_mode != WB_SYNC_NONE)
- wait_on_page_writeback(page);
- else
- goto continue_unlock;
- }
+ if (PageWriteback(page))
+ wait_on_page_writeback(page);
BUG_ON(PageWriteback(page));
- if (!clear_page_dirty_for_io(page))
- goto continue_unlock;
- ret = __mpage_da_writepage(page, wbc, mpd);
- if (unlikely(ret)) {
- if (ret == AOP_WRITEPAGE_ACTIVATE) {
- unlock_page(page);
- ret = 0;
- } else {
- done = 1;
- break;
- }
+ if (mpd->next_page != page->index)
+ mpd->first_page = page->index;
+ mpd->next_page = page->index + 1;
+ logical = (sector_t) page->index <<
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ if (!page_has_buffers(page)) {
+ mpage_add_bh_to_extent(mpd, logical,
+ PAGE_CACHE_SIZE,
+ (1 << BH_Dirty) | (1 << BH_Uptodate));
+ if (mpd->io_done)
+ goto ret_extent_tail;
+ } else {
+ /*
+ * Page with regular buffer heads,
+ * just add all dirty ones
+ */
+ head = page_buffers(page);
+ bh = head;
+ do {
+ BUG_ON(buffer_locked(bh));
+ /*
+ * We need to try to allocate
+ * unmapped blocks in the same page.
+ * Otherwise we won't make progress
+ * with the page in ext4_writepage
+ */
+ if (ext4_bh_delay_or_unwritten(NULL, bh)) {
+ mpage_add_bh_to_extent(mpd, logical,
+ bh->b_size,
+ bh->b_state);
+ if (mpd->io_done)
+ goto ret_extent_tail;
+ } else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
+ /*
+ * mapped dirty buffer. We need
+ * to update the b_state
+ * because we look at b_state
+ * in mpage_da_map_blocks. We
+ * don't update b_size because
+ * if we find an unmapped
+ * buffer_head later we need to
+ * use the b_state flag of that
+ * buffer_head.
+ */
+ if (mpd->b_size == 0)
+ mpd->b_state = bh->b_state & BH_FLAGS;
+ }
+ logical++;
+ } while ((bh = bh->b_this_page) != head);
}
if (nr_to_write > 0) {
nr_to_write--;
if (nr_to_write == 0 &&
- wbc->sync_mode == WB_SYNC_NONE) {
+ wbc->sync_mode == WB_SYNC_NONE)
/*
* We stop writing back only if we are
* not doing integrity sync. In case of
@@ -2924,14 +2867,18 @@ continue_unlock:
* pages, but have not synced all of the
* old dirty pages.
*/
- done = 1;
- break;
- }
+ goto out;
}
}
pagevec_release(&pvec);
cond_resched();
}
+ return 0;
+ret_extent_tail:
+ ret = MPAGE_DA_EXTENT_TAIL;
+out:
+ pagevec_release(&pvec);
+ cond_resched();
return ret;
}
@@ -2945,7 +2892,6 @@ static int ext4_da_writepages(struct address_space *mapping,
struct mpage_da_data mpd;
struct inode *inode = mapping->host;
int pages_written = 0;
- long pages_skipped;
unsigned int max_pages;
int range_cyclic, cycled = 1, io_done = 0;
int needed_blocks, ret = 0;
@@ -3028,11 +2974,6 @@ static int ext4_da_writepages(struct address_space *mapping,
wbc->nr_to_write = desired_nr_to_write;
}
- mpd.wbc = wbc;
- mpd.inode = mapping->host;
-
- pages_skipped = wbc->pages_skipped;
-
retry:
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
@@ -3059,22 +3000,10 @@ retry:
}
/*
- * Now call __mpage_da_writepage to find the next
+ * Now call write_cache_pages_da() to find the next
* contiguous region of logical blocks that need
- * blocks to be allocated by ext4. We don't actually
- * submit the blocks for I/O here, even though
- * write_cache_pages thinks it will, and will set the
- * pages as clean for write before calling
- * __mpage_da_writepage().
+ * blocks to be allocated by ext4 and submit them.
*/
- mpd.b_size = 0;
- mpd.b_state = 0;
- mpd.b_blocknr = 0;
- mpd.first_page = 0;
- mpd.next_page = 0;
- mpd.io_done = 0;
- mpd.pages_written = 0;
- mpd.retval = 0;
ret = write_cache_pages_da(mapping, wbc, &mpd, &done_index);
/*
* If we have a contiguous extent of pages and we
@@ -3096,7 +3025,6 @@ retry:
* and try again
*/
jbd2_journal_force_commit_nested(sbi->s_journal);
- wbc->pages_skipped = pages_skipped;
ret = 0;
} else if (ret == MPAGE_DA_EXTENT_TAIL) {
/*
@@ -3104,7 +3032,6 @@ retry:
* rest of the pages
*/
pages_written += mpd.pages_written;
- wbc->pages_skipped = pages_skipped;
ret = 0;
io_done = 1;
} else if (wbc->nr_to_write)
@@ -3122,11 +3049,6 @@ retry:
wbc->range_end = mapping->writeback_index - 1;
goto retry;
}
- if (pages_skipped != wbc->pages_skipped)
- ext4_msg(inode->i_sb, KERN_CRIT,
- "This should not happen leaving %s "
- "with nr_to_write = %ld ret = %d",
- __func__, wbc->nr_to_write, ret);
/* Update index */
wbc->range_cyclic = range_cyclic;
@@ -3383,7 +3305,7 @@ int ext4_alloc_da_blocks(struct inode *inode)
* the pages by calling redirty_page_for_writepage() but that
* would be ugly in the extreme. So instead we would need to
* replicate parts of the code in the above functions,
- * simplifying them becuase we wouldn't actually intend to
+ * simplifying them because we wouldn't actually intend to
* write out the pages, but rather only collect contiguous
* logical block extents, call the multi-block allocator, and
* then update the buffer heads with the block allocations.
@@ -3460,6 +3382,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
static int ext4_readpage(struct file *file, struct page *page)
{
+ trace_ext4_readpage(page);
return mpage_readpage(page, ext4_get_block);
}
@@ -3494,6 +3417,8 @@ static void ext4_invalidatepage(struct page *page, unsigned long offset)
{
journal_t *journal = EXT4_JOURNAL(page->mapping->host);
+ trace_ext4_invalidatepage(page, offset);
+
/*
* free any io_end structure allocated for buffers to be discarded
*/
@@ -3515,6 +3440,8 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
{
journal_t *journal = EXT4_JOURNAL(page->mapping->host);
+ trace_ext4_releasepage(page);
+
WARN_ON(PageChecked(page));
if (!page_has_buffers(page))
return 0;
@@ -3768,7 +3695,7 @@ retry:
*
* The unwrritten extents will be converted to written when DIO is completed.
* For async direct IO, since the IO may still pending when return, we
- * set up an end_io call back function, which will do the convertion
+ * set up an end_io call back function, which will do the conversion
* when async direct IO completed.
*
* If the O_DIRECT write will extend the file then add this inode to the
@@ -3791,7 +3718,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
* We could direct write to holes and fallocate.
*
* Allocated blocks to fill the hole are marked as uninitialized
- * to prevent paralel buffered read to expose the stale data
+ * to prevent parallel buffered read to expose the stale data
* before DIO complete the data IO.
*
* As to previously fallocated extents, ext4 get_block
@@ -3852,7 +3779,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
int err;
/*
* for non AIO case, since the IO is already
- * completed, we could do the convertion right here
+ * completed, we could do the conversion right here
*/
err = ext4_convert_unwritten_extents(inode,
offset, ret);
@@ -3873,11 +3800,16 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ ssize_t ret;
+ trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- return ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
-
- return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
+ ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
+ else
+ ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
+ trace_ext4_direct_IO_exit(inode, offset,
+ iov_length(iov, nr_segs), rw, ret);
+ return ret;
}
/*
@@ -3903,7 +3835,6 @@ static const struct address_space_operations ext4_ordered_aops = {
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
- .sync_page = block_sync_page,
.write_begin = ext4_write_begin,
.write_end = ext4_ordered_write_end,
.bmap = ext4_bmap,
@@ -3919,7 +3850,6 @@ static const struct address_space_operations ext4_writeback_aops = {
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
- .sync_page = block_sync_page,
.write_begin = ext4_write_begin,
.write_end = ext4_writeback_write_end,
.bmap = ext4_bmap,
@@ -3935,7 +3865,6 @@ static const struct address_space_operations ext4_journalled_aops = {
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
- .sync_page = block_sync_page,
.write_begin = ext4_write_begin,
.write_end = ext4_journalled_write_end,
.set_page_dirty = ext4_journalled_set_page_dirty,
@@ -3951,7 +3880,6 @@ static const struct address_space_operations ext4_da_aops = {
.readpages = ext4_readpages,
.writepage = ext4_writepage,
.writepages = ext4_da_writepages,
- .sync_page = block_sync_page,
.write_begin = ext4_da_write_begin,
.write_end = ext4_da_write_end,
.bmap = ext4_bmap,
@@ -4098,7 +4026,7 @@ static inline int all_zeroes(__le32 *p, __le32 *q)
*
* When we do truncate() we may have to clean the ends of several
* indirect blocks but leave the blocks themselves alive. Block is
- * partially truncated if some data below the new i_size is refered
+ * partially truncated if some data below the new i_size is referred
* from it (and it is on the path to the first completely truncated
* data block, indeed). We have to free the top of that path along
* with everything to the right of the path. Since no allocation
@@ -4177,6 +4105,9 @@ no_top:
*
* We release `count' blocks on disk, but (last - first) may be greater
* than `count' because there can be holes in there.
+ *
+ * Return 0 on success, 1 on invalid block range
+ * and < 0 on fatal error.
*/
static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
struct buffer_head *bh,
@@ -4203,33 +4134,32 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
if (bh) {
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, inode, bh);
- if (unlikely(err)) {
- ext4_std_error(inode->i_sb, err);
- return 1;
- }
+ if (unlikely(err))
+ goto out_err;
}
err = ext4_mark_inode_dirty(handle, inode);
- if (unlikely(err)) {
- ext4_std_error(inode->i_sb, err);
- return 1;
- }
+ if (unlikely(err))
+ goto out_err;
err = ext4_truncate_restart_trans(handle, inode,
blocks_for_truncate(inode));
- if (unlikely(err)) {
- ext4_std_error(inode->i_sb, err);
- return 1;
- }
+ if (unlikely(err))
+ goto out_err;
if (bh) {
BUFFER_TRACE(bh, "retaking write access");
- ext4_journal_get_write_access(handle, bh);
+ err = ext4_journal_get_write_access(handle, bh);
+ if (unlikely(err))
+ goto out_err;
}
}
for (p = first; p < last; p++)
*p = 0;
- ext4_free_blocks(handle, inode, 0, block_to_free, count, flags);
+ ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags);
return 0;
+out_err:
+ ext4_std_error(inode->i_sb, err);
+ return err;
}
/**
@@ -4240,7 +4170,7 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
* @first: array of block numbers
* @last: points immediately past the end of array
*
- * We are freeing all blocks refered from that array (numbers are stored as
+ * We are freeing all blocks referred from that array (numbers are stored as
* little-endian 32-bit) and updating @inode->i_blocks appropriately.
*
* We accumulate contiguous runs of blocks to free. Conveniently, if these
@@ -4263,7 +4193,7 @@ static void ext4_free_data(handle_t *handle, struct inode *inode,
ext4_fsblk_t nr; /* Current block # */
__le32 *p; /* Pointer into inode/ind
for current block */
- int err;
+ int err = 0;
if (this_bh) { /* For indirect block */
BUFFER_TRACE(this_bh, "get_write_access");
@@ -4285,9 +4215,10 @@ static void ext4_free_data(handle_t *handle, struct inode *inode,
} else if (nr == block_to_free + count) {
count++;
} else {
- if (ext4_clear_blocks(handle, inode, this_bh,
- block_to_free, count,
- block_to_free_p, p))
+ err = ext4_clear_blocks(handle, inode, this_bh,
+ block_to_free, count,
+ block_to_free_p, p);
+ if (err)
break;
block_to_free = nr;
block_to_free_p = p;
@@ -4296,9 +4227,12 @@ static void ext4_free_data(handle_t *handle, struct inode *inode,
}
}
- if (count > 0)
- ext4_clear_blocks(handle, inode, this_bh, block_to_free,
- count, block_to_free_p, p);
+ if (!err && count > 0)
+ err = ext4_clear_blocks(handle, inode, this_bh, block_to_free,
+ count, block_to_free_p, p);
+ if (err < 0)
+ /* fatal error */
+ return;
if (this_bh) {
BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata");
@@ -4328,7 +4262,7 @@ static void ext4_free_data(handle_t *handle, struct inode *inode,
* @last: pointer immediately past the end of array
* @depth: depth of the branches to free
*
- * We are freeing all blocks refered from these branches (numbers are
+ * We are freeing all blocks referred from these branches (numbers are
* stored as little-endian 32-bit) and updating @inode->i_blocks
* appropriately.
*/
@@ -4416,7 +4350,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
* transaction where the data blocks are
* actually freed.
*/
- ext4_free_blocks(handle, inode, 0, nr, 1,
+ ext4_free_blocks(handle, inode, NULL, nr, 1,
EXT4_FREE_BLOCKS_METADATA|
EXT4_FREE_BLOCKS_FORGET);
@@ -4496,10 +4430,12 @@ void ext4_truncate(struct inode *inode)
Indirect chain[4];
Indirect *partial;
__le32 nr = 0;
- int n;
- ext4_lblk_t last_block;
+ int n = 0;
+ ext4_lblk_t last_block, max_block;
unsigned blocksize = inode->i_sb->s_blocksize;
+ trace_ext4_truncate_enter(inode);
+
if (!ext4_can_truncate(inode))
return;
@@ -4510,6 +4446,7 @@ void ext4_truncate(struct inode *inode)
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
ext4_ext_truncate(inode);
+ trace_ext4_truncate_exit(inode);
return;
}
@@ -4519,14 +4456,18 @@ void ext4_truncate(struct inode *inode)
last_block = (inode->i_size + blocksize-1)
>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
+ max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
+ >> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
if (inode->i_size & (blocksize - 1))
if (ext4_block_truncate_page(handle, mapping, inode->i_size))
goto out_stop;
- n = ext4_block_to_path(inode, last_block, offsets, NULL);
- if (n == 0)
- goto out_stop; /* error */
+ if (last_block != max_block) {
+ n = ext4_block_to_path(inode, last_block, offsets, NULL);
+ if (n == 0)
+ goto out_stop; /* error */
+ }
/*
* OK. This truncate is going to happen. We add the inode to the
@@ -4557,7 +4498,13 @@ void ext4_truncate(struct inode *inode)
*/
ei->i_disksize = inode->i_size;
- if (n == 1) { /* direct blocks */
+ if (last_block == max_block) {
+ /*
+ * It is unnecessary to free any data blocks if last_block is
+ * equal to the indirect block limit.
+ */
+ goto out_unlock;
+ } else if (n == 1) { /* direct blocks */
ext4_free_data(handle, inode, NULL, i_data+offsets[0],
i_data + EXT4_NDIR_BLOCKS);
goto do_indirects;
@@ -4617,6 +4564,7 @@ do_indirects:
;
}
+out_unlock:
up_write(&ei->i_data_sem);
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
@@ -4639,6 +4587,7 @@ out_stop:
ext4_orphan_del(handle, inode);
ext4_journal_stop(handle);
+ trace_ext4_truncate_exit(inode);
}
/*
@@ -4770,6 +4719,7 @@ make_io:
* has in-inode xattrs, or we don't have this inode in memory.
* Read the block from disk.
*/
+ trace_ext4_load_inode(inode);
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
submit_bh(READ_META, bh);
@@ -4875,7 +4825,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
return inode;
ei = EXT4_I(inode);
- iloc.bh = 0;
+ iloc.bh = NULL;
ret = __ext4_get_inode_loc(inode, &iloc, 0);
if (ret < 0)
@@ -5460,13 +5410,12 @@ static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks,
/* if nrblocks are contiguous */
if (chunk) {
/*
- * With N contiguous data blocks, it need at most
- * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) indirect blocks
- * 2 dindirect blocks
- * 1 tindirect block
+ * With N contiguous data blocks, we need at most
+ * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks,
+ * 2 dindirect blocks, and 1 tindirect block
*/
- indirects = nrblocks / EXT4_ADDR_PER_BLOCK(inode->i_sb);
- return indirects + 3;
+ return DIV_ROUND_UP(nrblocks,
+ EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
}
/*
* if nrblocks are not contiguous, worse case, each block touch
@@ -5540,7 +5489,7 @@ static int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk)
}
/*
- * Calulate the total number of credits to reserve to fit
+ * Calculate the total number of credits to reserve to fit
* the modification of a single pages into a single transaction,
* which may include multiple chunks of block allocations.
*
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index eb3bc2fe647e..808c554e773f 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -38,7 +38,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
unsigned int oldflags;
unsigned int jflag;
- if (!is_owner_or_cap(inode))
+ if (!inode_owner_or_capable(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
@@ -146,7 +146,7 @@ flags_out:
__u32 generation;
int err;
- if (!is_owner_or_cap(inode))
+ if (!inode_owner_or_capable(inode))
return -EPERM;
err = mnt_want_write(filp->f_path.mnt);
@@ -298,7 +298,7 @@ mext_out:
case EXT4_IOC_MIGRATE:
{
int err;
- if (!is_owner_or_cap(inode))
+ if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write(filp->f_path.mnt);
@@ -320,7 +320,7 @@ mext_out:
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
- if (!is_owner_or_cap(inode))
+ if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write(filp->f_path.mnt);
@@ -334,16 +334,22 @@ mext_out:
case FITRIM:
{
struct super_block *sb = inode->i_sb;
+ struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ if (!blk_queue_discard(q))
+ return -EOPNOTSUPP;
+
if (copy_from_user(&range, (struct fstrim_range *)arg,
sizeof(range)))
return -EFAULT;
+ range.minlen = max((unsigned int)range.minlen,
+ q->limits.discard_granularity);
ret = ext4_trim_fs(sb, &range);
if (ret < 0)
return ret;
@@ -421,6 +427,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return err;
}
case EXT4_IOC_MOVE_EXT:
+ case FITRIM:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index d1fe09aea73d..d8a16eecf1d5 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -92,7 +92,7 @@
* between CPUs. It is possible to get scheduled at this point.
*
* The locality group prealloc space is used looking at whether we have
- * enough free space (pa_free) withing the prealloc space.
+ * enough free space (pa_free) within the prealloc space.
*
* If we can't allocate blocks via inode prealloc or/and locality group
* prealloc then we look at the buddy cache. The buddy cache is represented
@@ -432,9 +432,10 @@ static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max)
}
/* at order 0 we see each particular block */
- *max = 1 << (e4b->bd_blkbits + 3);
- if (order == 0)
+ if (order == 0) {
+ *max = 1 << (e4b->bd_blkbits + 3);
return EXT4_MB_BITMAP(e4b);
+ }
bb = EXT4_MB_BUDDY(e4b) + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order];
*max = EXT4_SB(e4b->bd_sb)->s_mb_maxs[order];
@@ -616,7 +617,6 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments);
grp = ext4_get_group_info(sb, e4b->bd_group);
- buddy = mb_find_buddy(e4b, 0, &max);
list_for_each(cur, &grp->bb_prealloc_list) {
ext4_group_t groupnr;
struct ext4_prealloc_space *pa;
@@ -635,7 +635,12 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
#define mb_check_buddy(e4b)
#endif
-/* FIXME!! need more doc */
+/*
+ * Divide blocks started from @first with length @len into
+ * smaller chunks with power of 2 blocks.
+ * Clear the bits in bitmap which the blocks of the chunk(s) covered,
+ * then increase bb_counters[] for corresponded chunk size.
+ */
static void ext4_mb_mark_free_simple(struct super_block *sb,
void *buddy, ext4_grpblk_t first, ext4_grpblk_t len,
struct ext4_group_info *grp)
@@ -2381,7 +2386,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
/* An 8TB filesystem with 64-bit pointers requires a 4096 byte
* kmalloc. A 128kb malloc should suffice for a 256TB filesystem.
* So a two level scheme suffices for now. */
- sbi->s_group_info = kmalloc(array_size, GFP_KERNEL);
+ sbi->s_group_info = kzalloc(array_size, GFP_KERNEL);
if (sbi->s_group_info == NULL) {
printk(KERN_ERR "EXT4-fs: can't allocate buddy meta group\n");
return -ENOMEM;
@@ -3208,7 +3213,7 @@ ext4_mb_check_group_pa(ext4_fsblk_t goal_block,
cur_distance = abs(goal_block - cpa->pa_pstart);
new_distance = abs(goal_block - pa->pa_pstart);
- if (cur_distance < new_distance)
+ if (cur_distance <= new_distance)
return cpa;
/* drop the previous reference */
@@ -3907,7 +3912,8 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
struct super_block *sb = ac->ac_sb;
ext4_group_t ngroups, i;
- if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ if (!mb_enable_debug ||
+ (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED))
return;
printk(KERN_ERR "EXT4-fs: Can't allocate:"
@@ -4753,7 +4759,8 @@ static int ext4_trim_extent(struct super_block *sb, int start, int count,
* bitmap. Then issue a TRIM command on this extent and free the extent in
* the group buddy bitmap. This is done until whole group is scanned.
*/
-ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
+static ext4_grpblk_t
+ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks)
{
void *bitmap;
@@ -4863,10 +4870,15 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
break;
}
- if (len >= EXT4_BLOCKS_PER_GROUP(sb))
- len -= (EXT4_BLOCKS_PER_GROUP(sb) - first_block);
- else
+ /*
+ * For all the groups except the last one, last block will
+ * always be EXT4_BLOCKS_PER_GROUP(sb), so we only need to
+ * change it for the last group in which case start +
+ * len < EXT4_BLOCKS_PER_GROUP(sb).
+ */
+ if (first_block + len < EXT4_BLOCKS_PER_GROUP(sb))
last_block = first_block + len;
+ len -= last_block - first_block;
if (e4b.bd_info->bb_free >= minlen) {
cnt = ext4_trim_all_free(sb, &e4b, first_block,
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index b619322c76f0..22bd4d7f289b 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -169,7 +169,7 @@ struct ext4_allocation_context {
/* original request */
struct ext4_free_extent ac_o_ex;
- /* goal request (after normalization) */
+ /* goal request (normalized ac_o_ex) */
struct ext4_free_extent ac_g_ex;
/* the best found extent */
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index b0a126f23c20..92816b4e0f16 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -263,7 +263,7 @@ static int free_dind_blocks(handle_t *handle,
for (i = 0; i < max_entries; i++) {
if (tmp_idata[i]) {
extend_credit_for_blkdel(handle, inode);
- ext4_free_blocks(handle, inode, 0,
+ ext4_free_blocks(handle, inode, NULL,
le32_to_cpu(tmp_idata[i]), 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
@@ -271,7 +271,7 @@ static int free_dind_blocks(handle_t *handle,
}
put_bh(bh);
extend_credit_for_blkdel(handle, inode);
- ext4_free_blocks(handle, inode, 0, le32_to_cpu(i_data), 1,
+ ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
return 0;
@@ -302,7 +302,7 @@ static int free_tind_blocks(handle_t *handle,
}
put_bh(bh);
extend_credit_for_blkdel(handle, inode);
- ext4_free_blocks(handle, inode, 0, le32_to_cpu(i_data), 1,
+ ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
return 0;
@@ -315,7 +315,7 @@ static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data)
/* ei->i_data[EXT4_IND_BLOCK] */
if (i_data[0]) {
extend_credit_for_blkdel(handle, inode);
- ext4_free_blocks(handle, inode, 0,
+ ext4_free_blocks(handle, inode, NULL,
le32_to_cpu(i_data[0]), 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
@@ -428,7 +428,7 @@ static int free_ext_idx(handle_t *handle, struct inode *inode,
}
put_bh(bh);
extend_credit_for_blkdel(handle, inode);
- ext4_free_blocks(handle, inode, 0, block, 1,
+ ext4_free_blocks(handle, inode, NULL, block, 1,
EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
return retval;
}
@@ -517,7 +517,7 @@ int ext4_ext_migrate(struct inode *inode)
* start with one credit accounted for
* superblock modification.
*
- * For the tmp_inode we already have commited the
+ * For the tmp_inode we already have committed the
* trascation that created the inode. Later as and
* when we add extents we extent the journal
*/
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index e781b7ea5630..67fd0b025858 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -40,6 +40,7 @@
#include "xattr.h"
#include "acl.h"
+#include <trace/events/ext4.h>
/*
* define how far ahead to read directories while searching them.
*/
@@ -2183,6 +2184,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
struct ext4_dir_entry_2 *de;
handle_t *handle;
+ trace_ext4_unlink_enter(dir, dentry);
/* Initialize quotas before so that eventual writes go
* in separate transaction */
dquot_initialize(dir);
@@ -2228,6 +2230,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
end_unlink:
ext4_journal_stop(handle);
brelse(bh);
+ trace_ext4_unlink_exit(dentry, retval);
return retval;
}
@@ -2402,6 +2405,10 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
if (!new_inode && new_dir != old_dir &&
EXT4_DIR_LINK_MAX(new_dir))
goto end_rename;
+ BUFFER_TRACE(dir_bh, "get_write_access");
+ retval = ext4_journal_get_write_access(handle, dir_bh);
+ if (retval)
+ goto end_rename;
}
if (!new_bh) {
retval = ext4_add_entry(handle, new_dentry, old_inode);
@@ -2409,7 +2416,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
goto end_rename;
} else {
BUFFER_TRACE(new_bh, "get write access");
- ext4_journal_get_write_access(handle, new_bh);
+ retval = ext4_journal_get_write_access(handle, new_bh);
+ if (retval)
+ goto end_rename;
new_de->inode = cpu_to_le32(old_inode->i_ino);
if (EXT4_HAS_INCOMPAT_FEATURE(new_dir->i_sb,
EXT4_FEATURE_INCOMPAT_FILETYPE))
@@ -2470,8 +2479,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
old_dir->i_ctime = old_dir->i_mtime = ext4_current_time(old_dir);
ext4_update_dx_flag(old_dir);
if (dir_bh) {
- BUFFER_TRACE(dir_bh, "get_write_access");
- ext4_journal_get_write_access(handle, dir_bh);
PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
cpu_to_le32(new_dir->i_ino);
BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 955cc309142f..b6dbd056fcb1 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -259,6 +259,11 @@ static void ext4_end_bio(struct bio *bio, int error)
bi_sector >> (inode->i_blkbits - 9));
}
+ if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+ ext4_free_io_end(io_end);
+ return;
+ }
+
/* Add the io_end to per-inode completed io list*/
spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list);
@@ -279,9 +284,9 @@ void ext4_io_submit(struct ext4_io_submit *io)
BUG_ON(bio_flagged(io->io_bio, BIO_EOPNOTSUPP));
bio_put(io->io_bio);
}
- io->io_bio = 0;
+ io->io_bio = NULL;
io->io_op = 0;
- io->io_end = 0;
+ io->io_end = NULL;
}
static int io_submit_init(struct ext4_io_submit *io,
@@ -310,8 +315,7 @@ static int io_submit_init(struct ext4_io_submit *io,
io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh);
io->io_bio = bio;
- io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?
- WRITE_SYNC_PLUG : WRITE);
+ io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
io->io_next_block = bh->b_blocknr;
return 0;
}
@@ -381,8 +385,6 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
- set_page_writeback(page);
- ClearPageError(page);
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
@@ -393,6 +395,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
io_page->p_page = page;
atomic_set(&io_page->p_count, 1);
get_page(page);
+ set_page_writeback(page);
+ ClearPageError(page);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 3ecc6e45d2f9..80bbc9c60c24 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -230,7 +230,7 @@ static int setup_new_group_blocks(struct super_block *sb,
}
/* Zero out all of the reserved backup group descriptor table blocks */
- ext4_debug("clear inode table blocks %#04llx -> %#04llx\n",
+ ext4_debug("clear inode table blocks %#04llx -> %#04lx\n",
block, sbi->s_itb_per_group);
err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb,
GFP_NOFS);
@@ -248,7 +248,7 @@ static int setup_new_group_blocks(struct super_block *sb,
/* Zero out all of the inode table blocks */
block = input->inode_table;
- ext4_debug("clear inode table blocks %#04llx -> %#04llx\n",
+ ext4_debug("clear inode table blocks %#04llx -> %#04lx\n",
block, sbi->s_itb_per_group);
err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, GFP_NOFS);
if (err)
@@ -499,12 +499,12 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
return err;
exit_inode:
- /* ext4_journal_release_buffer(handle, iloc.bh); */
+ /* ext4_handle_release_buffer(handle, iloc.bh); */
brelse(iloc.bh);
exit_dindj:
- /* ext4_journal_release_buffer(handle, dind); */
+ /* ext4_handle_release_buffer(handle, dind); */
exit_sbh:
- /* ext4_journal_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
+ /* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
exit_dind:
brelse(dind);
exit_bh:
@@ -586,7 +586,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
/*
int j;
for (j = 0; j < i; j++)
- ext4_journal_release_buffer(handle, primary[j]);
+ ext4_handle_release_buffer(handle, primary[j]);
*/
goto exit_bh;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 203f9e4a70be..8553dfb310af 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -54,9 +54,9 @@
static struct proc_dir_entry *ext4_proc_root;
static struct kset *ext4_kset;
-struct ext4_lazy_init *ext4_li_info;
-struct mutex ext4_li_mtx;
-struct ext4_features *ext4_feat;
+static struct ext4_lazy_init *ext4_li_info;
+static struct mutex ext4_li_mtx;
+static struct ext4_features *ext4_feat;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
@@ -75,6 +75,7 @@ static void ext4_write_super(struct super_block *sb);
static int ext4_freeze(struct super_block *sb);
static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data);
+static int ext4_feature_set_ok(struct super_block *sb, int readonly);
static void ext4_destroy_lazyinit_thread(void);
static void ext4_unregister_li_request(struct super_block *sb);
static void ext4_clear_request_list(void);
@@ -241,27 +242,44 @@ static void ext4_put_nojournal(handle_t *handle)
* journal_end calls result in the superblock being marked dirty, so
* that sync() will call the filesystem's write_super callback if
* appropriate.
+ *
+ * To avoid j_barrier hold in userspace when a user calls freeze(),
+ * ext4 prevents a new handle from being started by s_frozen, which
+ * is in an upper layer.
*/
handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
{
journal_t *journal;
+ handle_t *handle;
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
- vfs_check_frozen(sb, SB_FREEZE_TRANS);
- /* Special case here: if the journal has aborted behind our
- * backs (eg. EIO in the commit thread), then we still need to
- * take the FS itself readonly cleanly. */
journal = EXT4_SB(sb)->s_journal;
- if (journal) {
- if (is_journal_aborted(journal)) {
- ext4_abort(sb, "Detected aborted journal");
- return ERR_PTR(-EROFS);
- }
- return jbd2_journal_start(journal, nblocks);
+ handle = ext4_journal_current_handle();
+
+ /*
+ * If a handle has been started, it should be allowed to
+ * finish, otherwise deadlock could happen between freeze
+ * and others(e.g. truncate) due to the restart of the
+ * journal handle if the filesystem is forzen and active
+ * handles are not stopped.
+ */
+ if (!handle)
+ vfs_check_frozen(sb, SB_FREEZE_TRANS);
+
+ if (!journal)
+ return ext4_get_nojournal();
+ /*
+ * Special case here: if the journal has aborted behind our
+ * backs (eg. EIO in the commit thread), then we still need to
+ * take the FS itself readonly cleanly.
+ */
+ if (is_journal_aborted(journal)) {
+ ext4_abort(sb, "Detected aborted journal");
+ return ERR_PTR(-EROFS);
}
- return ext4_get_nojournal();
+ return jbd2_journal_start(journal, nblocks);
}
/*
@@ -594,7 +612,7 @@ __acquires(bitlock)
vaf.fmt = fmt;
vaf.va = &args;
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u",
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ",
sb->s_id, function, line, grp);
if (ino)
printk(KERN_CONT "inode %lu: ", ino);
@@ -616,7 +634,7 @@ __acquires(bitlock)
* filesystem will have already been marked read/only and the
* journal has been aborted. We return 1 as a hint to callers
* who might what to use the return value from
- * ext4_grp_locked_error() to distinguish beween the
+ * ext4_grp_locked_error() to distinguish between the
* ERRORS_CONT and ERRORS_RO case, and perhaps return more
* aggressively from the ext4 function in question, with a
* more appropriate error code.
@@ -997,13 +1015,10 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
if (test_opt(sb, OLDALLOC))
seq_puts(seq, ",oldalloc");
#ifdef CONFIG_EXT4_FS_XATTR
- if (test_opt(sb, XATTR_USER) &&
- !(def_mount_opts & EXT4_DEFM_XATTR_USER))
+ if (test_opt(sb, XATTR_USER))
seq_puts(seq, ",user_xattr");
- if (!test_opt(sb, XATTR_USER) &&
- (def_mount_opts & EXT4_DEFM_XATTR_USER)) {
+ if (!test_opt(sb, XATTR_USER))
seq_puts(seq, ",nouser_xattr");
- }
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL))
@@ -1041,8 +1056,8 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
!(def_mount_opts & EXT4_DEFM_NODELALLOC))
seq_puts(seq, ",nodelalloc");
- if (test_opt(sb, MBLK_IO_SUBMIT))
- seq_puts(seq, ",mblk_io_submit");
+ if (!test_opt(sb, MBLK_IO_SUBMIT))
+ seq_puts(seq, ",nomblk_io_submit");
if (sbi->s_stripe)
seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
/*
@@ -1451,7 +1466,7 @@ static int parse_options(char *options, struct super_block *sb,
* Initialize args struct so we know whether arg was
* found; some options take optional arguments.
*/
- args[0].to = args[0].from = 0;
+ args[0].to = args[0].from = NULL;
token = match_token(p, tokens, args);
switch (token) {
case Opt_bsd_df:
@@ -1771,7 +1786,7 @@ set_qf_format:
return 0;
if (option < 0 || option > (1 << 30))
return 0;
- if (!is_power_of_2(option)) {
+ if (option && !is_power_of_2(option)) {
ext4_msg(sb, KERN_ERR,
"EXT4-fs: inode_readahead_blks"
" must be a power of 2");
@@ -2120,6 +2135,13 @@ static void ext4_orphan_cleanup(struct super_block *sb,
return;
}
+ /* Check if feature set would not allow a r/w mount */
+ if (!ext4_feature_set_ok(sb, 0)) {
+ ext4_msg(sb, KERN_INFO, "Skipping orphan cleanup due to "
+ "unknown ROCOMPAT features");
+ return;
+ }
+
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
if (es->s_last_orphan)
jbd_debug(1, "Errors on filesystem, "
@@ -2412,7 +2434,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
if (parse_strtoul(buf, 0x40000000, &t))
return -EINVAL;
- if (!is_power_of_2(t))
+ if (t && !is_power_of_2(t))
return -EINVAL;
sbi->s_inode_readahead_blks = t;
@@ -2970,6 +2992,12 @@ static int ext4_register_li_request(struct super_block *sb,
mutex_unlock(&ext4_li_info->li_list_mtx);
sbi->s_li_request = elr;
+ /*
+ * set elr to NULL here since it has been inserted to
+ * the request_list and the removal and free of it is
+ * handled by ext4_clear_request_list from now on.
+ */
+ elr = NULL;
if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
ret = ext4_run_lazyinit_thread();
@@ -3095,14 +3123,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
if (def_mount_opts & EXT4_DEFM_UID16)
set_opt(sb, NO_UID32);
+ /* xattr user namespace & acls are now defaulted on */
#ifdef CONFIG_EXT4_FS_XATTR
- if (def_mount_opts & EXT4_DEFM_XATTR_USER)
- set_opt(sb, XATTR_USER);
+ set_opt(sb, XATTR_USER);
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
- if (def_mount_opts & EXT4_DEFM_ACL)
- set_opt(sb, POSIX_ACL);
+ set_opt(sb, POSIX_ACL);
#endif
+ set_opt(sb, MBLK_IO_SUBMIT);
if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
set_opt(sb, JOURNAL_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
@@ -3380,6 +3408,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
+ init_timer(&sbi->s_err_report);
+ sbi->s_err_report.function = print_daily_error_info;
+ sbi->s_err_report.data = (unsigned long) sb;
+
err = percpu_counter_init(&sbi->s_freeblocks_counter,
ext4_count_free_blocks(sb));
if (!err) {
@@ -3516,7 +3548,7 @@ no_journal:
* concurrency isn't really necessary. Limit it to 1.
*/
EXT4_SB(sb)->dio_unwritten_wq =
- alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM, 1);
+ alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
if (!EXT4_SB(sb)->dio_unwritten_wq) {
printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
goto failed_mount_wq;
@@ -3531,17 +3563,16 @@ no_journal:
if (IS_ERR(root)) {
ext4_msg(sb, KERN_ERR, "get root inode failed");
ret = PTR_ERR(root);
+ root = NULL;
goto failed_mount4;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
- iput(root);
ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck");
goto failed_mount4;
}
sb->s_root = d_alloc_root(root);
if (!sb->s_root) {
ext4_msg(sb, KERN_ERR, "get root dentry failed");
- iput(root);
ret = -ENOMEM;
goto failed_mount4;
}
@@ -3642,9 +3673,6 @@ no_journal:
"Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
*sbi->s_es->s_mount_opts ? "; " : "", orig_data);
- init_timer(&sbi->s_err_report);
- sbi->s_err_report.function = print_daily_error_info;
- sbi->s_err_report.data = (unsigned long) sb;
if (es->s_error_count)
mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
@@ -3657,6 +3685,8 @@ cantfind_ext4:
goto failed_mount;
failed_mount4:
+ iput(root);
+ sb->s_root = NULL;
ext4_msg(sb, KERN_ERR, "mount failed");
destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
failed_mount_wq:
@@ -3666,6 +3696,7 @@ failed_mount_wq:
sbi->s_journal = NULL;
}
failed_mount3:
+ del_timer(&sbi->s_err_report);
if (sbi->s_flex_groups) {
if (is_vmalloc_addr(sbi->s_flex_groups))
vfree(sbi->s_flex_groups);
@@ -4132,6 +4163,11 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
/*
* LVM calls this function before a (read-only) snapshot is created. This
* gives us a chance to flush the journal completely and mark the fs clean.
+ *
+ * Note that only this function cannot bring a filesystem to be in a clean
+ * state independently, because ext4 prevents a new handle from being started
+ * by @sb->s_frozen, which stays in an upper layer. It thus needs help from
+ * the upper layer.
*/
static int ext4_freeze(struct super_block *sb)
{
@@ -4608,17 +4644,30 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
static int ext4_quota_off(struct super_block *sb, int type)
{
+ struct inode *inode = sb_dqopt(sb)->files[type];
+ handle_t *handle;
+
/* Force all delayed allocation blocks to be allocated.
* Caller already holds s_umount sem */
if (test_opt(sb, DELALLOC))
sync_filesystem(sb);
+ /* Update modification times of quota files when userspace can
+ * start looking at them */
+ handle = ext4_journal_start(inode, 1);
+ if (IS_ERR(handle))
+ goto out;
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
+
+out:
return dquot_quota_off(sb, type);
}
/* Read data from quotafile - avoid pagecache and such because we cannot afford
* acquiring the locks... As quota files are never truncated and quota code
- * itself serializes the operations (and noone else should touch the files)
+ * itself serializes the operations (and no one else should touch the files)
* we don't have to be afraid of races */
static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off)
@@ -4708,9 +4757,8 @@ out:
if (inode->i_size < off + len) {
i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
+ ext4_mark_inode_dirty(handle, inode);
}
- inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- ext4_mark_inode_dirty(handle, inode);
mutex_unlock(&inode->i_mutex);
return len;
}
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index fc32176eee39..b545ca1c459c 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -735,7 +735,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
int offset = (char *)s->here - bs->bh->b_data;
unlock_buffer(bs->bh);
- jbd2_journal_release_buffer(handle, bs->bh);
+ ext4_handle_release_buffer(handle, bs->bh);
if (ce) {
mb_cache_entry_release(ce);
ce = NULL;
@@ -833,7 +833,7 @@ inserted:
new_bh = sb_getblk(sb, block);
if (!new_bh) {
getblk_failed:
- ext4_free_blocks(handle, inode, 0, block, 1,
+ ext4_free_blocks(handle, inode, NULL, block, 1,
EXT4_FREE_BLOCKS_METADATA);
error = -EIO;
goto cleanup;
generated by cgit v1.2.3 (git 2.39.0) at 2024-08-01 12:57:55 +0300