#include <linux/namei.h>
#include <linux/uio.h>
#include <linux/bio.h>
+#include <linux/workqueue.h>
#include "ext4_jbd2.h"
#include "xattr.h"
}
/*
- * The ext4 forget function must perform a revoke if we are freeing data
- * which has been journaled. Metadata (eg. indirect blocks) must be
- * revoked in all cases.
- *
- * "bh" may be NULL: a metadata block may have been freed from memory
- * but there may still be a record of it in the journal, and that record
- * still needs to be revoked.
- *
- * If the handle isn't valid we're not journaling, but we still need to
- * call into ext4_journal_revoke() to put the buffer head.
- */
-int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
- struct buffer_head *bh, ext4_fsblk_t blocknr)
-{
- int err;
-
- might_sleep();
-
- BUFFER_TRACE(bh, "enter");
-
- jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
- "data mode %x\n",
- bh, is_metadata, inode->i_mode,
- test_opt(inode->i_sb, DATA_FLAGS));
-
- /* Never use the revoke function if we are doing full data
- * journaling: there is no need to, and a V1 superblock won't
- * support it. Otherwise, only skip the revoke on un-journaled
- * data blocks. */
-
- if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
- (!is_metadata && !ext4_should_journal_data(inode))) {
- if (bh) {
- BUFFER_TRACE(bh, "call jbd2_journal_forget");
- return ext4_journal_forget(handle, bh);
- }
- return 0;
- }
-
- /*
- * data!=journal && (is_metadata || should_journal_data(inode))
- */
- BUFFER_TRACE(bh, "call ext4_journal_revoke");
- err = ext4_journal_revoke(handle, blocknr, bh);
- if (err)
- ext4_abort(inode->i_sb, __func__,
- "error %d when attempting revoke", err);
- BUFFER_TRACE(bh, "exit");
- return err;
-}
-
-/*
* Work out how many blocks we need to proceed with the next chunk of a
* truncate transaction.
*/
* so before we call here everything must be consistently dirtied against
* this transaction.
*/
- int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
+int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
int nblocks)
{
int ret;
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);
+ ext4_discard_preallocations(inode);
return ret;
}
return ret;
failed_out:
for (i = 0; i < index; i++)
- ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
+ ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
return ret;
}
return err;
failed:
/* Allocation failed, free what we already allocated */
+ ext4_free_blocks(handle, inode, 0, new_blocks[0], 1, 0);
for (i = 1; i <= n ; i++) {
- BUFFER_TRACE(branch[i].bh, "call jbd2_journal_forget");
- ext4_journal_forget(handle, branch[i].bh);
+ /*
+ * 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_FORGET);
}
- for (i = 0; i < indirect_blks; i++)
- ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
+ for (i = n+1; i < indirect_blks; i++)
+ ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
- ext4_free_blocks(handle, inode, new_blocks[i], num, 0);
+ ext4_free_blocks(handle, inode, 0, new_blocks[i], num, 0);
return err;
}
err_out:
for (i = 1; i <= num; i++) {
- BUFFER_TRACE(where[i].bh, "call jbd2_journal_forget");
- ext4_journal_forget(handle, where[i].bh);
- ext4_free_blocks(handle, inode,
- le32_to_cpu(where[i-1].key), 1, 0);
+ /*
+ * branch[i].bh is newly allocated, so there is no
+ * need to revoke the block, which is why we don't
+ * need to set EXT4_FREE_BLOCKS_METADATA.
+ */
+ ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
+ EXT4_FREE_BLOCKS_FORGET);
}
- ext4_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks, 0);
+ ext4_free_blocks(handle, inode, 0, le32_to_cpu(where[num].key),
+ blks, 0);
return err;
}
if (!err)
err = ext4_splice_branch(handle, inode, iblock,
partial, indirect_blks, count);
- else
+ if (err)
goto cleanup;
set_buffer_new(bh_result);
+
+ ext4_update_inode_fsync_trans(handle, inode, 1);
got_it:
map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
if (count > blocks_to_boundary)
return err;
}
-qsize_t ext4_get_reserved_space(struct inode *inode)
+#ifdef CONFIG_QUOTA
+qsize_t *ext4_get_reserved_space(struct inode *inode)
{
- unsigned long long total;
-
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- total = EXT4_I(inode)->i_reserved_data_blocks +
- EXT4_I(inode)->i_reserved_meta_blocks;
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
-
- return total;
+ return &EXT4_I(inode)->i_reserved_quota;
}
+#endif
/*
* Calculate the number of metadata blocks need to reserve
* to allocate @blocks for non extent file based file
static void ext4_da_update_reserve_space(struct inode *inode, int used)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- int total, mdb, mdb_free;
+ int total, mdb, mdb_free, mdb_claim = 0;
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
/* recalculate the number of metablocks still need to be reserved */
if (mdb_free) {
/* Account for allocated meta_blocks */
- mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
+ mdb_claim = EXT4_I(inode)->i_allocated_meta_blocks;
+ BUG_ON(mdb_free < mdb_claim);
+ mdb_free -= mdb_claim;
/* update fs dirty blocks counter */
percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
/* update per-inode reservations */
BUG_ON(used > EXT4_I(inode)->i_reserved_data_blocks);
EXT4_I(inode)->i_reserved_data_blocks -= used;
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, used + mdb_claim);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ vfs_dq_claim_block(inode, used + mdb_claim);
+
/*
* free those over-booking quota for metadata blocks
*/
}
/*
+ * Return the number of contiguous dirty pages in a given inode
+ * starting at page frame idx.
+ */
+static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
+ unsigned int max_pages)
+{
+ struct address_space *mapping = inode->i_mapping;
+ pgoff_t index;
+ struct pagevec pvec;
+ pgoff_t num = 0;
+ int i, nr_pages, done = 0;
+
+ if (max_pages == 0)
+ return 0;
+ pagevec_init(&pvec, 0);
+ while (!done) {
+ index = idx;
+ nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+ PAGECACHE_TAG_DIRTY,
+ (pgoff_t)PAGEVEC_SIZE);
+ if (nr_pages == 0)
+ break;
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+ struct buffer_head *bh, *head;
+
+ lock_page(page);
+ if (unlikely(page->mapping != mapping) ||
+ !PageDirty(page) ||
+ PageWriteback(page) ||
+ page->index != idx) {
+ done = 1;
+ unlock_page(page);
+ break;
+ }
+ if (page_has_buffers(page)) {
+ bh = head = page_buffers(page);
+ do {
+ if (!buffer_delay(bh) &&
+ !buffer_unwritten(bh))
+ done = 1;
+ bh = bh->b_this_page;
+ } while (!done && (bh != head));
+ }
+ unlock_page(page);
+ if (done)
+ break;
+ idx++;
+ num++;
+ if (num >= max_pages)
+ break;
+ }
+ pagevec_release(&pvec);
+ }
+ return num;
+}
+
+/*
* The ext4_get_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
*
clear_buffer_mapped(bh);
clear_buffer_unwritten(bh);
+ ext_debug("ext4_get_blocks(): inode %lu, flag %d, max_blocks %u,"
+ "logical block %lu\n", inode->i_ino, flags, max_blocks,
+ (unsigned long)block);
/*
* Try to see if we can get the block without requesting a new
* file system block.
return ext4_journal_get_write_access(handle, bh);
}
+/*
+ * Truncate blocks that were not used by write. We have to truncate the
+ * pagecache as well so that corresponding buffers get properly unmapped.
+ */
+static void ext4_truncate_failed_write(struct inode *inode)
+{
+ truncate_inode_pages(inode->i_mapping, inode->i_size);
+ ext4_truncate(inode);
+}
+
static int ext4_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
ext4_journal_stop(handle);
if (pos + len > inode->i_size) {
- ext4_truncate(inode);
+ ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might
* still be on the orphan list; we need to
ret = ret2;
if (pos + len > inode->i_size) {
- ext4_truncate(inode);
+ ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
ret = ret2;
if (pos + len > inode->i_size) {
- ext4_truncate(inode);
+ ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
if (!ret)
ret = ret2;
if (pos + len > inode->i_size) {
- ext4_truncate(inode);
+ ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
total = md_needed + nrblocks;
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
/*
* Make quota reservation here to prevent quota overflow
* later. Real quota accounting is done at pages writeout
* time.
*/
- if (vfs_dq_reserve_block(inode, total)) {
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ if (vfs_dq_reserve_block(inode, total))
return -EDQUOT;
- }
if (ext4_claim_free_blocks(sbi, total)) {
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ vfs_dq_release_reservation_block(inode, total);
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
}
- vfs_dq_release_reservation_block(inode, total);
return -ENOSPC;
}
+ spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
- EXT4_I(inode)->i_reserved_meta_blocks = mdblocks;
-
+ EXT4_I(inode)->i_reserved_meta_blocks += md_needed;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+
return 0; /* success */
}
static void ext4_print_free_blocks(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- printk(KERN_EMERG "Total free blocks count %lld\n",
- ext4_count_free_blocks(inode->i_sb));
- printk(KERN_EMERG "Free/Dirty block details\n");
- printk(KERN_EMERG "free_blocks=%lld\n",
- (long long)percpu_counter_sum(&sbi->s_freeblocks_counter));
- printk(KERN_EMERG "dirty_blocks=%lld\n",
- (long long)percpu_counter_sum(&sbi->s_dirtyblocks_counter));
- printk(KERN_EMERG "Block reservation details\n");
- printk(KERN_EMERG "i_reserved_data_blocks=%u\n",
- EXT4_I(inode)->i_reserved_data_blocks);
- printk(KERN_EMERG "i_reserved_meta_blocks=%u\n",
- EXT4_I(inode)->i_reserved_meta_blocks);
+ printk(KERN_CRIT "Total free blocks count %lld\n",
+ ext4_count_free_blocks(inode->i_sb));
+ printk(KERN_CRIT "Free/Dirty block details\n");
+ printk(KERN_CRIT "free_blocks=%lld\n",
+ (long long) percpu_counter_sum(&sbi->s_freeblocks_counter));
+ printk(KERN_CRIT "dirty_blocks=%lld\n",
+ (long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ printk(KERN_CRIT "Block reservation details\n");
+ printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
+ EXT4_I(inode)->i_reserved_data_blocks);
+ printk(KERN_CRIT "i_reserved_meta_blocks=%u\n",
+ EXT4_I(inode)->i_reserved_meta_blocks);
return;
}
* writepage and writepages will again try to write
* the same.
*/
- printk(KERN_EMERG "%s block allocation failed for inode %lu "
- "at logical offset %llu with max blocks "
- "%zd with error %d\n",
- __func__, mpd->inode->i_ino,
- (unsigned long long)next,
- mpd->b_size >> mpd->inode->i_blkbits, err);
- printk(KERN_EMERG "This should not happen.!! "
- "Data will be lost\n");
+ ext4_msg(mpd->inode->i_sb, KERN_CRIT,
+ "delayed block allocation failed for inode %lu at "
+ "logical offset %llu with max blocks %zd with "
+ "error %d\n", mpd->inode->i_ino,
+ (unsigned long long) next,
+ mpd->b_size >> mpd->inode->i_blkbits, err);
+ printk(KERN_CRIT "This should not happen!! "
+ "Data will be lost\n");
if (err == -ENOSPC) {
ext4_print_free_blocks(mpd->inode);
}
/*
* Rest of the page in the page_vec
* redirty then and skip then. We will
- * try to to write them again after
+ * try to write them again after
* starting a new transaction
*/
redirty_page_for_writepage(wbc, page);
}
static int __ext4_journalled_writepage(struct page *page,
- struct writeback_control *wbc,
unsigned int len)
{
struct address_space *mapping = page->mapping;
* doesn't seem much point in redirtying the page here.
*/
ClearPageChecked(page);
- return __ext4_journalled_writepage(page, wbc, len);
+ return __ext4_journalled_writepage(page, len);
}
if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
* number of contiguous block. So we will limit
* number of contiguous block to a sane value
*/
- if (!(inode->i_flags & EXT4_EXTENTS_FL) &&
+ if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) &&
(max_blocks > EXT4_MAX_TRANS_DATA))
max_blocks = EXT4_MAX_TRANS_DATA;
int no_nrwrite_index_update;
int pages_written = 0;
long pages_skipped;
+ unsigned int max_pages;
int range_cyclic, cycled = 1, io_done = 0;
- int needed_blocks, ret = 0, nr_to_writebump = 0;
+ int needed_blocks, ret = 0;
+ long desired_nr_to_write, nr_to_writebump = 0;
loff_t range_start = wbc->range_start;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED))
return -EROFS;
- /*
- * Make sure nr_to_write is >= sbi->s_mb_stream_request
- * This make sure small files blocks are allocated in
- * single attempt. This ensure that small files
- * get less fragmented.
- */
- if (wbc->nr_to_write < sbi->s_mb_stream_request) {
- nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write;
- wbc->nr_to_write = sbi->s_mb_stream_request;
- }
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
} else
index = wbc->range_start >> PAGE_CACHE_SHIFT;
+ /*
+ * This works around two forms of stupidity. The first is in
+ * the writeback code, which caps the maximum number of pages
+ * written to be 1024 pages. This is wrong on multiple
+ * levels; different architectues have a different page size,
+ * which changes the maximum amount of data which gets
+ * written. Secondly, 4 megabytes is way too small. XFS
+ * forces this value to be 16 megabytes by multiplying
+ * nr_to_write parameter by four, and then relies on its
+ * allocator to allocate larger extents to make them
+ * contiguous. Unfortunately this brings us to the second
+ * stupidity, which is that ext4's mballoc code only allocates
+ * at most 2048 blocks. So we force contiguous writes up to
+ * the number of dirty blocks in the inode, or
+ * sbi->max_writeback_mb_bump whichever is smaller.
+ */
+ max_pages = sbi->s_max_writeback_mb_bump << (20 - PAGE_CACHE_SHIFT);
+ if (!range_cyclic && range_whole)
+ desired_nr_to_write = wbc->nr_to_write * 8;
+ else
+ desired_nr_to_write = ext4_num_dirty_pages(inode, index,
+ max_pages);
+ if (desired_nr_to_write > max_pages)
+ desired_nr_to_write = max_pages;
+
+ if (wbc->nr_to_write < desired_nr_to_write) {
+ nr_to_writebump = desired_nr_to_write - wbc->nr_to_write;
+ wbc->nr_to_write = desired_nr_to_write;
+ }
+
mpd.wbc = wbc;
mpd.inode = mapping->host;
handle = ext4_journal_start(inode, needed_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
- printk(KERN_CRIT "%s: jbd2_start: "
+ ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
"%ld pages, ino %lu; err %d\n", __func__,
wbc->nr_to_write, inode->i_ino, ret);
- dump_stack();
goto out_writepages;
}
ret = write_cache_pages(mapping, wbc, __mpage_da_writepage,
&mpd);
/*
- * If we have a contigous extent of pages and we
+ * If we have a contiguous extent of pages and we
* haven't done the I/O yet, map the blocks and submit
* them for I/O.
*/
goto retry;
}
if (pages_skipped != wbc->pages_skipped)
- printk(KERN_EMERG "This should not happen leaving %s "
- "with nr_to_write = %ld ret = %d\n",
- __func__, wbc->nr_to_write, ret);
+ ext4_msg(inode->i_sb, KERN_CRIT,
+ "This should not happen leaving %s "
+ "with nr_to_write = %ld ret = %d\n",
+ __func__, wbc->nr_to_write, ret);
/* Update index */
index += pages_written;
if (2 * free_blocks < 3 * dirty_blocks ||
free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
/*
- * free block count is less that 150% of dirty blocks
- * or free blocks is less that watermark
+ * free block count is less than 150% of dirty blocks
+ * or free blocks is less than watermark
*/
return 1;
}
+ /*
+ * Even if we don't switch but are nearing capacity,
+ * start pushing delalloc when 1/2 of free blocks are dirty.
+ */
+ if (free_blocks < 2 * dirty_blocks)
+ writeback_inodes_sb_if_idle(sb);
+
return 0;
}
* i_size_read because we hold i_mutex.
*/
if (pos + len > inode->i_size)
- ext4_truncate(inode);
+ ext4_truncate_failed_write(inode);
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
}
/*
+ * O_DIRECT for ext3 (or indirect map) based files
+ *
* If the O_DIRECT write will extend the file then add this inode to the
* orphan list. So recovery will truncate it back to the original size
* if the machine crashes during the write.
* crashes then stale disk data _may_ be exposed inside the file. But current
* VFS code falls back into buffered path in that case so we are safe.
*/
-static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
+static ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
ssize_t ret;
int orphan = 0;
size_t count = iov_length(iov, nr_segs);
+ int retries = 0;
if (rw == WRITE) {
loff_t final_size = offset + count;
}
}
+retry:
ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs,
ext4_get_block, NULL);
+ if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
if (orphan) {
int err;
return ret;
}
+static int ext4_get_block_dio_write(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ handle_t *handle = NULL;
+ int ret = 0;
+ unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+ int dio_credits;
+
+ ext4_debug("ext4_get_block_dio_write: inode %lu, create flag %d\n",
+ inode->i_ino, create);
+ /*
+ * DIO VFS code passes create = 0 flag for write to
+ * the middle of file. It does this to avoid block
+ * allocation for holes, to prevent expose stale data
+ * out when there is parallel buffered read (which does
+ * not hold the i_mutex lock) while direct IO write has
+ * not completed. DIO request on holes finally falls back
+ * to buffered IO for this reason.
+ *
+ * For ext4 extent based file, since we support fallocate,
+ * new allocated extent as uninitialized, for holes, we
+ * could fallocate blocks for holes, thus parallel
+ * buffered IO read will zero out the page when read on
+ * a hole while parallel DIO write to the hole has not completed.
+ *
+ * when we come here, we know it's a direct IO write to
+ * to the middle of file (<i_size)
+ * so it's safe to override the create flag from VFS.
+ */
+ create = EXT4_GET_BLOCKS_DIO_CREATE_EXT;
+
+ if (max_blocks > DIO_MAX_BLOCKS)
+ max_blocks = DIO_MAX_BLOCKS;
+ dio_credits = ext4_chunk_trans_blocks(inode, max_blocks);
+ handle = ext4_journal_start(inode, dio_credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+ ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result,
+ create);
+ if (ret > 0) {
+ bh_result->b_size = (ret << inode->i_blkbits);
+ ret = 0;
+ }
+ ext4_journal_stop(handle);
+out:
+ return ret;
+}
+
+static void ext4_free_io_end(ext4_io_end_t *io)
+{
+ BUG_ON(!io);
+ iput(io->inode);
+ kfree(io);
+}
+static void dump_aio_dio_list(struct inode * inode)
+{
+#ifdef EXT4_DEBUG
+ struct list_head *cur, *before, *after;
+ ext4_io_end_t *io, *io0, *io1;
+
+ if (list_empty(&EXT4_I(inode)->i_aio_dio_complete_list)){
+ ext4_debug("inode %lu aio dio list is empty\n", inode->i_ino);
+ return;
+ }
+
+ ext4_debug("Dump inode %lu aio_dio_completed_IO list \n", inode->i_ino);
+ list_for_each_entry(io, &EXT4_I(inode)->i_aio_dio_complete_list, list){
+ cur = &io->list;
+ before = cur->prev;
+ io0 = container_of(before, ext4_io_end_t, list);
+ after = cur->next;
+ io1 = container_of(after, ext4_io_end_t, list);
+
+ ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
+ io, inode->i_ino, io0, io1);
+ }
+#endif
+}
+
+/*
+ * check a range of space and convert unwritten extents to written.
+ */
+static int ext4_end_aio_dio_nolock(ext4_io_end_t *io)
+{
+ struct inode *inode = io->inode;
+ loff_t offset = io->offset;
+ size_t size = io->size;
+ int ret = 0;
+
+ ext4_debug("end_aio_dio_onlock: io 0x%p from inode %lu,list->next 0x%p,"
+ "list->prev 0x%p\n",
+ io, inode->i_ino, io->list.next, io->list.prev);
+
+ if (list_empty(&io->list))
+ return ret;
+
+ if (io->flag != DIO_AIO_UNWRITTEN)
+ return ret;
+
+ if (offset + size <= i_size_read(inode))
+ ret = ext4_convert_unwritten_extents(inode, offset, size);
+
+ if (ret < 0) {
+ printk(KERN_EMERG "%s: failed to convert unwritten"
+ "extents to written extents, error is %d"
+ " io is still on inode %lu aio dio list\n",
+ __func__, ret, inode->i_ino);
+ return ret;
+ }
+
+ /* clear the DIO AIO unwritten flag */
+ io->flag = 0;
+ return ret;
+}
+/*
+ * work on completed aio dio IO, to convert unwritten extents to extents
+ */
+static void ext4_end_aio_dio_work(struct work_struct *work)
+{
+ ext4_io_end_t *io = container_of(work, ext4_io_end_t, work);
+ struct inode *inode = io->inode;
+ int ret = 0;
+
+ mutex_lock(&inode->i_mutex);
+ ret = ext4_end_aio_dio_nolock(io);
+ if (ret >= 0) {
+ if (!list_empty(&io->list))
+ list_del_init(&io->list);
+ ext4_free_io_end(io);
+ }
+ mutex_unlock(&inode->i_mutex);
+}
+/*
+ * This function is called from ext4_sync_file().
+ *
+ * When AIO DIO IO is completed, the work to convert unwritten
+ * extents to written is queued on workqueue but may not get immediately
+ * scheduled. When fsync is called, we need to ensure the
+ * conversion is complete before fsync returns.
+ * The inode keeps track of a list of completed AIO from DIO path
+ * that might needs to do the conversion. This function walks through
+ * the list and convert the related unwritten extents to written.
+ */
+int flush_aio_dio_completed_IO(struct inode *inode)
+{
+ ext4_io_end_t *io;
+ int ret = 0;
+ int ret2 = 0;
+
+ if (list_empty(&EXT4_I(inode)->i_aio_dio_complete_list))
+ return ret;
+
+ dump_aio_dio_list(inode);
+ while (!list_empty(&EXT4_I(inode)->i_aio_dio_complete_list)){
+ io = list_entry(EXT4_I(inode)->i_aio_dio_complete_list.next,
+ ext4_io_end_t, list);
+ /*
+ * Calling ext4_end_aio_dio_nolock() to convert completed
+ * IO to written.
+ *
+ * When ext4_sync_file() is called, run_queue() may already
+ * about to flush the work corresponding to this io structure.
+ * It will be upset if it founds the io structure related
+ * 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
+ * avoid double converting from both fsync and background work
+ * queue work.
+ */
+ ret = ext4_end_aio_dio_nolock(io);
+ if (ret < 0)
+ ret2 = ret;
+ else
+ list_del_init(&io->list);
+ }
+ return (ret2 < 0) ? ret2 : 0;
+}
+
+static ext4_io_end_t *ext4_init_io_end (struct inode *inode)
+{
+ ext4_io_end_t *io = NULL;
+
+ io = kmalloc(sizeof(*io), GFP_NOFS);
+
+ if (io) {
+ igrab(inode);
+ io->inode = inode;
+ io->flag = 0;
+ io->offset = 0;
+ io->size = 0;
+ io->error = 0;
+ INIT_WORK(&io->work, ext4_end_aio_dio_work);
+ INIT_LIST_HEAD(&io->list);
+ }
+
+ return io;
+}
+
+static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
+ ssize_t size, void *private)
+{
+ ext4_io_end_t *io_end = iocb->private;
+ struct workqueue_struct *wq;
+
+ /* if not async direct IO or dio with 0 bytes write, just return */
+ if (!io_end || !size)
+ return;
+
+ ext_debug("ext4_end_io_dio(): io_end 0x%p"
+ "for inode %lu, iocb 0x%p, offset %llu, size %llu\n",
+ iocb->private, io_end->inode->i_ino, iocb, offset,
+ size);
+
+ /* if not aio dio with unwritten extents, just free io and return */
+ if (io_end->flag != DIO_AIO_UNWRITTEN){
+ ext4_free_io_end(io_end);
+ iocb->private = NULL;
+ return;
+ }
+
+ io_end->offset = offset;
+ io_end->size = size;
+ wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
+
+ /* queue the work to convert unwritten extents to written */
+ queue_work(wq, &io_end->work);
+
+ /* Add the io_end to per-inode completed aio dio list*/
+ list_add_tail(&io_end->list,
+ &EXT4_I(io_end->inode)->i_aio_dio_complete_list);
+ iocb->private = NULL;
+}
+/*
+ * For ext4 extent files, ext4 will do direct-io write to holes,
+ * preallocated extents, and those write extend the file, no need to
+ * fall back to buffered IO.
+ *
+ * For holes, we fallocate those blocks, mark them as unintialized
+ * If those blocks were preallocated, we mark sure they are splited, but
+ * still keep the range to write as unintialized.
+ *
+ * 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
+ * when async direct IO completed.
+ *
+ * If the O_DIRECT write will extend the file then add this inode to the
+ * orphan list. So recovery will truncate it back to the original size
+ * if the machine crashes during the write.
+ *
+ */
+static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
+ const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+ ssize_t ret;
+ size_t count = iov_length(iov, nr_segs);
+
+ loff_t final_size = offset + count;
+ if (rw == WRITE && final_size <= inode->i_size) {
+ /*
+ * 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
+ * before DIO complete the data IO.
+ *
+ * As to previously fallocated extents, ext4 get_block
+ * will just simply mark the buffer mapped but still
+ * keep the extents uninitialized.
+ *
+ * for non AIO case, we will convert those unwritten extents
+ * to written after return back from blockdev_direct_IO.
+ *
+ * for async DIO, the conversion needs to be defered when
+ * the IO is completed. The ext4 end_io callback function
+ * will be called to take care of the conversion work.
+ * Here for async case, we allocate an io_end structure to
+ * hook to the iocb.
+ */
+ iocb->private = NULL;
+ EXT4_I(inode)->cur_aio_dio = NULL;
+ if (!is_sync_kiocb(iocb)) {
+ iocb->private = ext4_init_io_end(inode);
+ if (!iocb->private)
+ return -ENOMEM;
+ /*
+ * we save the io structure for current async
+ * direct IO, so that later ext4_get_blocks()
+ * could flag the io structure whether there
+ * is a unwritten extents needs to be converted
+ * when IO is completed.
+ */
+ EXT4_I(inode)->cur_aio_dio = iocb->private;
+ }
+
+ ret = blockdev_direct_IO(rw, iocb, inode,
+ inode->i_sb->s_bdev, iov,
+ offset, nr_segs,
+ ext4_get_block_dio_write,
+ ext4_end_io_dio);
+ if (iocb->private)
+ EXT4_I(inode)->cur_aio_dio = NULL;
+ /*
+ * The io_end structure takes a reference to the inode,
+ * that structure needs to be destroyed and the
+ * reference to the inode need to be dropped, when IO is
+ * complete, even with 0 byte write, or failed.
+ *
+ * In the successful AIO DIO case, the io_end structure will be
+ * desctroyed and the reference to the inode will be dropped
+ * after the end_io call back function is called.
+ *
+ * In the case there is 0 byte write, or error case, since
+ * VFS direct IO won't invoke the end_io call back function,
+ * we need to free the end_io structure here.
+ */
+ if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
+ ext4_free_io_end(iocb->private);
+ iocb->private = NULL;
+ } else if (ret > 0 && (EXT4_I(inode)->i_state &
+ EXT4_STATE_DIO_UNWRITTEN)) {
+ int err;
+ /*
+ * for non AIO case, since the IO is already
+ * completed, we could do the convertion right here
+ */
+ err = ext4_convert_unwritten_extents(inode,
+ offset, ret);
+ if (err < 0)
+ ret = err;
+ EXT4_I(inode)->i_state &= ~EXT4_STATE_DIO_UNWRITTEN;
+ }
+ return ret;
+ }
+
+ /* for write the the end of file case, we fall back to old way */
+ return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
+}
+
+static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
+ const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+
+ if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+ return ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
+
+ return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
+}
+
/*
* Pages can be marked dirty completely asynchronously from ext4's journalling
* activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext4_writeback_aops = {
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext4_journalled_aops = {
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext4_da_aops = {
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
void ext4_set_aops(struct inode *inode)
int k, err;
*top = 0;
- /* Make k index the deepest non-null offest + 1 */
+ /* Make k index the deepest non-null offset + 1 */
for (k = depth; k > 1 && !offsets[k-1]; k--)
;
partial = ext4_get_branch(inode, k, offsets, chain, &err);
__le32 *last)
{
__le32 *p;
+ int flags = EXT4_FREE_BLOCKS_FORGET;
+
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ flags |= EXT4_FREE_BLOCKS_METADATA;
+
if (try_to_extend_transaction(handle, inode)) {
if (bh) {
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
}
}
- /*
- * Any buffers which are on the journal will be in memory. We
- * find them on the hash table so jbd2_journal_revoke() will
- * run jbd2_journal_forget() on them. We've already detached
- * each block from the file, so bforget() in
- * jbd2_journal_forget() should be safe.
- *
- * AKPM: turn on bforget in jbd2_journal_forget()!!!
- */
- for (p = first; p < last; p++) {
- u32 nr = le32_to_cpu(*p);
- if (nr) {
- struct buffer_head *tbh;
-
- *p = 0;
- tbh = sb_find_get_block(inode->i_sb, nr);
- ext4_forget(handle, 0, inode, tbh, nr);
- }
- }
+ for (p = first; p < last; p++)
+ *p = 0;
- ext4_free_blocks(handle, inode, block_to_free, count, 0);
+ ext4_free_blocks(handle, inode, 0, block_to_free, count, flags);
}
/**
blocks_for_truncate(inode));
}
- ext4_free_blocks(handle, inode, nr, 1, 1);
+ ext4_free_blocks(handle, inode, 0, nr, 1,
+ EXT4_FREE_BLOCKS_METADATA);
if (parent_bh) {
/*
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) {
struct ext4_iloc iloc;
struct ext4_inode *raw_inode;
struct ext4_inode_info *ei;
- struct buffer_head *bh;
struct inode *inode;
+ journal_t *journal = EXT4_SB(sb)->s_journal;
long ret;
int block;
return inode;
ei = EXT4_I(inode);
+ iloc.bh = 0;
ret = __ext4_get_inode_loc(inode, &iloc, 0);
if (ret < 0)
goto bad_inode;
- bh = iloc.bh;
raw_inode = ext4_raw_inode(&iloc);
inode->i_mode = le16_to_cpu(raw_inode->i_mode);
inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
if (inode->i_mode == 0 ||
!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
/* this inode is deleted */
- brelse(bh);
ret = -ESTALE;
goto bad_inode;
}
((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
inode->i_size = ext4_isize(raw_inode);
ei->i_disksize = inode->i_size;
+#ifdef CONFIG_QUOTA
+ ei->i_reserved_quota = 0;
+#endif
inode->i_generation = le32_to_cpu(raw_inode->i_generation);
ei->i_block_group = iloc.block_group;
ei->i_last_alloc_group = ~0;
ei->i_data[block] = raw_inode->i_block[block];
INIT_LIST_HEAD(&ei->i_orphan);
+ /*
+ * Set transaction id's of transactions that have to be committed
+ * to finish f[data]sync. We set them to currently running transaction
+ * as we cannot be sure that the inode or some of its metadata isn't
+ * part of the transaction - the inode could have been reclaimed and
+ * now it is reread from disk.
+ */
+ if (journal) {
+ transaction_t *transaction;
+ tid_t tid;
+
+ spin_lock(&journal->j_state_lock);
+ if (journal->j_running_transaction)
+ transaction = journal->j_running_transaction;
+ else
+ transaction = journal->j_committing_transaction;
+ if (transaction)
+ tid = transaction->t_tid;
+ else
+ tid = journal->j_commit_sequence;
+ spin_unlock(&journal->j_state_lock);
+ ei->i_sync_tid = tid;
+ ei->i_datasync_tid = tid;
+ }
+
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
EXT4_INODE_SIZE(inode->i_sb)) {
- brelse(bh);
ret = -EIO;
goto bad_inode;
}
ret = 0;
if (ei->i_file_acl &&
- ((ei->i_file_acl <
- (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
- EXT4_SB(sb)->s_gdb_count)) ||
- (ei->i_file_acl >= ext4_blocks_count(EXT4_SB(sb)->s_es)))) {
+ !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
ext4_error(sb, __func__,
"bad extended attribute block %llu in inode #%lu",
ei->i_file_acl, inode->i_ino);
/* Validate block references which are part of inode */
ret = ext4_check_inode_blockref(inode);
}
- if (ret) {
- brelse(bh);
+ if (ret)
goto bad_inode;
- }
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext4_file_inode_operations;
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
} else {
- brelse(bh);
ret = -EIO;
ext4_error(inode->i_sb, __func__,
"bogus i_mode (%o) for inode=%lu",
return inode;
bad_inode:
+ brelse(iloc.bh);
iget_failed(inode);
return ERR_PTR(ret);
}
*/
static int ext4_do_update_inode(handle_t *handle,
struct inode *inode,
- struct ext4_iloc *iloc,
- int do_sync)
+ struct ext4_iloc *iloc)
{
struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
struct ext4_inode_info *ei = EXT4_I(inode);
raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
}
- /*
- * 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;
- }
+ 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;
+ ext4_update_inode_fsync_trans(handle, inode, 0);
out_brelse:
brelse(bh);
ext4_std_error(inode->i_sb, err);
err = ext4_get_inode_loc(inode, &iloc);
if (err)
return err;
- err = ext4_do_update_inode(EXT4_NOJOURNAL_HANDLE,
- inode, &iloc, wait);
+ if (wait)
+ sync_dirty_buffer(iloc.bh);
+ if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
+ ext4_error(inode->i_sb, __func__,
+ "IO error syncing inode, "
+ "inode=%lu, block=%llu",
+ inode->i_ino,
+ (unsigned long long)iloc.bh->b_blocknr);
+ err = -EIO;
+ }
}
return err;
}
/* (user+group)*(old+new) structure, inode write (sb,
* inode block, ? - but truncate inode update has it) */
- handle = ext4_journal_start(inode, 2*(EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)+
- EXT4_QUOTA_DEL_BLOCKS(inode->i_sb))+3);
+ handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+
+ EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb))+3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;
* worse case, the indexs blocks spread over different block groups
*
* If datablocks are discontiguous, they are possible to spread over
- * different block groups too. If they are contiugous, with flexbg,
+ * different block groups too. If they are contiuguous, with flexbg,
* they could still across block group boundary.
*
* Also account for superblock, inode, quota and xattr blocks
* Calculate the journal credits for a chunk of data modification.
*
* This is called from DIO, fallocate or whoever calling
- * ext4_get_blocks() to map/allocate a chunk of contigous disk blocks.
+ * ext4_get_blocks() to map/allocate a chunk of contiguous disk blocks.
*
* journal buffers for data blocks are not included here, as DIO
* and fallocate do no need to journal data buffers.
get_bh(iloc->bh);
/* ext4_do_update_inode() does jbd2_journal_dirty_metadata */
- err = ext4_do_update_inode(handle, inode, iloc, 0);
+ err = ext4_do_update_inode(handle, inode, iloc);
put_bh(iloc->bh);
return err;
}
*/
void ext4_dirty_inode(struct inode *inode)
{
- handle_t *current_handle = ext4_journal_current_handle();
handle_t *handle;
- if (!ext4_handle_valid(current_handle)) {
- ext4_mark_inode_dirty(current_handle, inode);
- return;
- }
-
handle = ext4_journal_start(inode, 2);
if (IS_ERR(handle))
goto out;
- if (current_handle &&
- current_handle->h_transaction != handle->h_transaction) {
- /* This task has a transaction open against a different fs */
- printk(KERN_EMERG "%s: transactions do not match!\n",
- __func__);
- } else {
- jbd_debug(5, "marking dirty. outer handle=%p\n",
- current_handle);
- ext4_mark_inode_dirty(handle, inode);
- }
+
+ ext4_mark_inode_dirty(handle, inode);
+
ext4_journal_stop(handle);
out:
return;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff