spin_lock(&ei->i_block_reservation_lock);
trace_ext4_da_update_reserve_space(inode, used, quota_claim);
if (unlikely(used > ei->i_reserved_data_blocks)) {
- ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
+ ext4_warning(inode->i_sb, "%s: ino %lu, used %d "
"with only %d reserved data blocks",
__func__, inode->i_ino, used,
ei->i_reserved_data_blocks);
}
if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) {
- ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, allocated %d "
- "with only %d reserved metadata blocks\n", __func__,
- inode->i_ino, ei->i_allocated_meta_blocks,
- ei->i_reserved_meta_blocks);
+ ext4_warning(inode->i_sb, "ino %lu, allocated %d "
+ "with only %d reserved metadata blocks "
+ "(releasing %d blocks with reserved %d data blocks)",
+ inode->i_ino, ei->i_allocated_meta_blocks,
+ ei->i_reserved_meta_blocks, used,
+ ei->i_reserved_data_blocks);
WARN_ON(1);
ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks;
}
return num;
}
+#ifdef ES_AGGRESSIVE_TEST
+static void ext4_map_blocks_es_recheck(handle_t *handle,
+ struct inode *inode,
+ struct ext4_map_blocks *es_map,
+ struct ext4_map_blocks *map,
+ int flags)
+{
+ int retval;
+
+ map->m_flags = 0;
+ /*
+ * There is a race window that the result is not the same.
+ * e.g. xfstests #223 when dioread_nolock enables. The reason
+ * is that we lookup a block mapping in extent status tree with
+ * out taking i_data_sem. So at the time the unwritten extent
+ * could be converted.
+ */
+ if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
+ down_read((&EXT4_I(inode)->i_data_sem));
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+ retval = ext4_ext_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
+ } else {
+ retval = ext4_ind_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
+ }
+ if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
+ up_read((&EXT4_I(inode)->i_data_sem));
+ /*
+ * Clear EXT4_MAP_FROM_CLUSTER and EXT4_MAP_BOUNDARY flag
+ * because it shouldn't be marked in es_map->m_flags.
+ */
+ map->m_flags &= ~(EXT4_MAP_FROM_CLUSTER | EXT4_MAP_BOUNDARY);
+
+ /*
+ * We don't check m_len because extent will be collpased in status
+ * tree. So the m_len might not equal.
+ */
+ if (es_map->m_lblk != map->m_lblk ||
+ es_map->m_flags != map->m_flags ||
+ es_map->m_pblk != map->m_pblk) {
+ printk("ES cache assertation failed for inode: %lu "
+ "es_cached ex [%d/%d/%llu/%x] != "
+ "found ex [%d/%d/%llu/%x] retval %d flags %x\n",
+ inode->i_ino, es_map->m_lblk, es_map->m_len,
+ es_map->m_pblk, es_map->m_flags, map->m_lblk,
+ map->m_len, map->m_pblk, map->m_flags,
+ retval, flags);
+ }
+}
+#endif /* ES_AGGRESSIVE_TEST */
+
/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags)
{
+ struct extent_status es;
int retval;
+#ifdef ES_AGGRESSIVE_TEST
+ struct ext4_map_blocks orig_map;
+
+ memcpy(&orig_map, map, sizeof(*map));
+#endif
map->m_flags = 0;
ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
"logical block %lu\n", inode->i_ino, flags, map->m_len,
(unsigned long) map->m_lblk);
+
+ /* Lookup extent status tree firstly */
+ if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
+ if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
+ map->m_pblk = ext4_es_pblock(&es) +
+ map->m_lblk - es.es_lblk;
+ map->m_flags |= ext4_es_is_written(&es) ?
+ EXT4_MAP_MAPPED : EXT4_MAP_UNWRITTEN;
+ retval = es.es_len - (map->m_lblk - es.es_lblk);
+ if (retval > map->m_len)
+ retval = map->m_len;
+ map->m_len = retval;
+ } else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
+ retval = 0;
+ } else {
+ BUG_ON(1);
+ }
+#ifdef ES_AGGRESSIVE_TEST
+ ext4_map_blocks_es_recheck(handle, inode, map,
+ &orig_map, flags);
+#endif
+ goto found;
+ }
+
/*
* Try to see if we can get the block without requesting a new
* file system block.
retval = ext4_ind_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
}
+ if (retval > 0) {
+ int ret;
+ unsigned long long status;
+
+#ifdef ES_AGGRESSIVE_TEST
+ if (retval != map->m_len) {
+ printk("ES len assertation failed for inode: %lu "
+ "retval %d != map->m_len %d "
+ "in %s (lookup)\n", inode->i_ino, retval,
+ map->m_len, __func__);
+ }
+#endif
+
+ status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+ EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+ if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
+ ext4_find_delalloc_range(inode, map->m_lblk,
+ map->m_lblk + map->m_len - 1))
+ status |= EXTENT_STATUS_DELAYED;
+ ret = ext4_es_insert_extent(inode, map->m_lblk,
+ map->m_len, map->m_pblk, status);
+ if (ret < 0)
+ retval = ret;
+ }
if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
up_read((&EXT4_I(inode)->i_data_sem));
+found:
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
- int ret;
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
- /* delayed alloc may be allocated by fallocate and
- * coverted to initialized by directIO.
- * we need to handle delayed extent here.
- */
- down_write((&EXT4_I(inode)->i_data_sem));
- goto delayed_mapped;
- }
- ret = check_block_validity(inode, map);
+ int ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
return retval;
/*
- * When we call get_blocks without the create flag, the
- * BH_Unwritten flag could have gotten set if the blocks
- * requested were part of a uninitialized extent. We need to
- * clear this flag now that we are committed to convert all or
- * part of the uninitialized extent to be an initialized
- * extent. This is because we need to avoid the combination
- * of BH_Unwritten and BH_Mapped flags being simultaneously
- * set on the buffer_head.
+ * Here we clear m_flags because after allocating an new extent,
+ * it will be set again.
*/
- map->m_flags &= ~EXT4_MAP_UNWRITTEN;
+ map->m_flags &= ~EXT4_MAP_FLAGS;
/*
* New blocks allocate and/or writing to uninitialized extent
(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
ext4_da_update_reserve_space(inode, retval, 1);
}
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
- if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
- int ret;
-delayed_mapped:
- /* delayed allocation blocks has been allocated */
- ret = ext4_es_remove_extent(inode, map->m_lblk,
- map->m_len);
- if (ret < 0)
- retval = ret;
+ if (retval > 0) {
+ int ret;
+ unsigned long long status;
+
+#ifdef ES_AGGRESSIVE_TEST
+ if (retval != map->m_len) {
+ printk("ES len assertation failed for inode: %lu "
+ "retval %d != map->m_len %d "
+ "in %s (allocation)\n", inode->i_ino, retval,
+ map->m_len, __func__);
}
+#endif
+
+ status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+ EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+ if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
+ ext4_find_delalloc_range(inode, map->m_lblk,
+ map->m_lblk + map->m_len - 1))
+ status |= EXTENT_STATUS_DELAYED;
+ ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+ map->m_pblk, status);
+ if (ret < 0)
+ retval = ret;
}
up_write((&EXT4_I(inode)->i_data_sem));
/* ensure we send some value back into *errp */
*errp = 0;
+ if (create && err == 0)
+ err = -ENOSPC; /* should never happen */
if (err < 0)
*errp = err;
if (err <= 0)
ret = ext4_try_to_write_inline_data(mapping, inode, pos, len,
flags, pagep);
if (ret < 0)
- goto out;
- if (ret == 1) {
- ret = 0;
- goto out;
- }
+ return ret;
+ if (ret == 1)
+ return 0;
}
-retry:
+ /*
+ * grab_cache_page_write_begin() can take a long time if the
+ * system is thrashing due to memory pressure, or if the page
+ * is being written back. So grab it first before we start
+ * the transaction handle. This also allows us to allocate
+ * the page (if needed) without using GFP_NOFS.
+ */
+retry_grab:
+ page = grab_cache_page_write_begin(mapping, index, flags);
+ if (!page)
+ return -ENOMEM;
+ unlock_page(page);
+
+retry_journal:
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
+ page_cache_release(page);
+ return PTR_ERR(handle);
}
- /* We cannot recurse into the filesystem as the transaction is already
- * started */
- flags |= AOP_FLAG_NOFS;
-
- page = grab_cache_page_write_begin(mapping, index, flags);
- if (!page) {
+ lock_page(page);
+ if (page->mapping != mapping) {
+ /* The page got truncated from under us */
+ unlock_page(page);
+ page_cache_release(page);
ext4_journal_stop(handle);
- ret = -ENOMEM;
- goto out;
+ goto retry_grab;
}
-
- *pagep = page;
+ wait_on_page_writeback(page);
if (ext4_should_dioread_nolock(inode))
ret = __block_write_begin(page, pos, len, ext4_get_block_write);
if (ret) {
unlock_page(page);
- page_cache_release(page);
/*
* __block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
- }
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
-out:
+ if (ret == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry_journal;
+ page_cache_release(page);
+ return ret;
+ }
+ *pagep = page;
return ret;
}
* function is called from invalidate page, it's
* harmless to return without any action.
*/
- ext4_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
+ ext4_warning(inode->i_sb, "ext4_da_release_space: "
"ino %lu, to_free %d with only %d reserved "
"data blocks", inode->i_ino, to_free,
ei->i_reserved_data_blocks);
(unsigned long long) next,
mpd->b_size >> mpd->inode->i_blkbits, err);
ext4_msg(sb, KERN_CRIT,
- "This should not happen!! Data will be lost\n");
+ "This should not happen!! Data will be lost");
if (err == -ENOSPC)
ext4_print_free_blocks(mpd->inode);
}
struct ext4_map_blocks *map,
struct buffer_head *bh)
{
+ struct extent_status es;
int retval;
sector_t invalid_block = ~((sector_t) 0xffff);
+#ifdef ES_AGGRESSIVE_TEST
+ struct ext4_map_blocks orig_map;
+
+ memcpy(&orig_map, map, sizeof(*map));
+#endif
if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
invalid_block = ~0;
ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
"logical block %lu\n", inode->i_ino, map->m_len,
(unsigned long) map->m_lblk);
+
+ /* Lookup extent status tree firstly */
+ if (ext4_es_lookup_extent(inode, iblock, &es)) {
+
+ if (ext4_es_is_hole(&es)) {
+ retval = 0;
+ down_read((&EXT4_I(inode)->i_data_sem));
+ goto add_delayed;
+ }
+
+ /*
+ * Delayed extent could be allocated by fallocate.
+ * So we need to check it.
+ */
+ if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) {
+ map_bh(bh, inode->i_sb, invalid_block);
+ set_buffer_new(bh);
+ set_buffer_delay(bh);
+ return 0;
+ }
+
+ map->m_pblk = ext4_es_pblock(&es) + iblock - es.es_lblk;
+ retval = es.es_len - (iblock - es.es_lblk);
+ if (retval > map->m_len)
+ retval = map->m_len;
+ map->m_len = retval;
+ if (ext4_es_is_written(&es))
+ map->m_flags |= EXT4_MAP_MAPPED;
+ else if (ext4_es_is_unwritten(&es))
+ map->m_flags |= EXT4_MAP_UNWRITTEN;
+ else
+ BUG_ON(1);
+
+#ifdef ES_AGGRESSIVE_TEST
+ ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
+#endif
+ return retval;
+ }
+
/*
* Try to see if we can get the block without requesting a new
* file system block.
map->m_flags |= EXT4_MAP_FROM_CLUSTER;
retval = 0;
} else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- retval = ext4_ext_map_blocks(NULL, inode, map, 0);
+ retval = ext4_ext_map_blocks(NULL, inode, map,
+ EXT4_GET_BLOCKS_NO_PUT_HOLE);
else
- retval = ext4_ind_map_blocks(NULL, inode, map, 0);
+ retval = ext4_ind_map_blocks(NULL, inode, map,
+ EXT4_GET_BLOCKS_NO_PUT_HOLE);
+add_delayed:
if (retval == 0) {
+ int ret;
/*
* XXX: __block_prepare_write() unmaps passed block,
* is it OK?
/* If the block was allocated from previously allocated cluster,
* then we dont need to reserve it again. */
if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) {
- retval = ext4_da_reserve_space(inode, iblock);
- if (retval)
+ ret = ext4_da_reserve_space(inode, iblock);
+ if (ret) {
/* not enough space to reserve */
+ retval = ret;
goto out_unlock;
+ }
}
- retval = ext4_es_insert_extent(inode, map->m_lblk, map->m_len);
- if (retval)
+ ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+ ~0, EXTENT_STATUS_DELAYED);
+ if (ret) {
+ retval = ret;
goto out_unlock;
+ }
/* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served
* and it should not appear on the bh->b_state.
map_bh(bh, inode->i_sb, invalid_block);
set_buffer_new(bh);
set_buffer_delay(bh);
+ } else if (retval > 0) {
+ int ret;
+ unsigned long long status;
+
+#ifdef ES_AGGRESSIVE_TEST
+ if (retval != map->m_len) {
+ printk("ES len assertation failed for inode: %lu "
+ "retval %d != map->m_len %d "
+ "in %s (lookup)\n", inode->i_ino, retval,
+ map->m_len, __func__);
+ }
+#endif
+
+ status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+ EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+ ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+ map->m_pblk, status);
+ if (ret != 0)
+ retval = ret;
}
out_unlock:
pos, len, flags,
pagep, fsdata);
if (ret < 0)
- goto out;
- if (ret == 1) {
- ret = 0;
- goto out;
- }
+ return ret;
+ if (ret == 1)
+ return 0;
}
-retry:
+ /*
+ * grab_cache_page_write_begin() can take a long time if the
+ * system is thrashing due to memory pressure, or if the page
+ * is being written back. So grab it first before we start
+ * the transaction handle. This also allows us to allocate
+ * the page (if needed) without using GFP_NOFS.
+ */
+retry_grab:
+ page = grab_cache_page_write_begin(mapping, index, flags);
+ if (!page)
+ return -ENOMEM;
+ unlock_page(page);
+
/*
* With delayed allocation, we don't log the i_disksize update
* if there is delayed block allocation. But we still need
* to journalling the i_disksize update if writes to the end
* of file which has an already mapped buffer.
*/
+retry_journal:
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1);
if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
+ page_cache_release(page);
+ return PTR_ERR(handle);
}
- /* We cannot recurse into the filesystem as the transaction is already
- * started */
- flags |= AOP_FLAG_NOFS;
- page = grab_cache_page_write_begin(mapping, index, flags);
- if (!page) {
+ lock_page(page);
+ if (page->mapping != mapping) {
+ /* The page got truncated from under us */
+ unlock_page(page);
+ page_cache_release(page);
ext4_journal_stop(handle);
- ret = -ENOMEM;
- goto out;
+ goto retry_grab;
}
- *pagep = page;
+ /* In case writeback began while the page was unlocked */
+ wait_on_page_writeback(page);
ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep);
if (ret < 0) {
unlock_page(page);
ext4_journal_stop(handle);
- page_cache_release(page);
/*
* block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
+
+ if (ret == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry_journal;
+
+ page_cache_release(page);
+ return ret;
}
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
-out:
+ *pagep = page;
return ret;
}