Commit b3aff3e3 authored by Zheng Liu's avatar Zheng Liu Committed by Theodore Ts'o

ext4: reimplement fiemap using extent status tree

Signed-off-by: default avatarYongqiang Yang <xiaoqiangnk@gmail.com>
Signed-off-by: default avatarAllison Henderson <achender@linux.vnet.ibm.com>
Signed-off-by: default avatarZheng Liu <wenqing.lz@taobao.com>
Signed-off-by: default avatar"Theodore Ts'o" <tytso@mit.edu>
parent 7d1b1fbc
...@@ -4499,193 +4499,51 @@ static int ext4_ext_fiemap_cb(struct inode *inode, ext4_lblk_t next, ...@@ -4499,193 +4499,51 @@ static int ext4_ext_fiemap_cb(struct inode *inode, ext4_lblk_t next,
struct ext4_ext_cache *newex, struct ext4_extent *ex, struct ext4_ext_cache *newex, struct ext4_extent *ex,
void *data) void *data)
{ {
struct extent_status es;
__u64 logical; __u64 logical;
__u64 physical; __u64 physical;
__u64 length; __u64 length;
__u32 flags = 0; __u32 flags = 0;
ext4_lblk_t next_del;
int ret = 0; int ret = 0;
struct fiemap_extent_info *fieinfo = data; struct fiemap_extent_info *fieinfo = data;
unsigned char blksize_bits; unsigned char blksize_bits;
blksize_bits = inode->i_sb->s_blocksize_bits; es.start = newex->ec_block;
logical = (__u64)newex->ec_block << blksize_bits; next_del = ext4_es_find_extent(inode, &es);
next = min(next_del, next);
if (newex->ec_start == 0) { if (newex->ec_start == 0) {
/* /*
* No extent in extent-tree contains block @newex->ec_start, * No extent in extent-tree contains block @newex->ec_start,
* then the block may stay in 1)a hole or 2)delayed-extent. * 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;
pgoff_t start_index = 0;
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;
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;
}
index = 0;
next_page:
/* Try to find the 1st mapped buffer. */
end = ((__u64)pages[index]->index << PAGE_SHIFT) >>
blksize_bits;
if (!page_has_buffers(pages[index]))
goto out;
head = page_buffers(pages[index]);
if (!head)
goto out;
index++;
bh = head;
do {
if (end >= newex->ec_block +
newex->ec_len)
/* The buffer is out of
* the request range.
*/ */
goto out; if (es.len == 0)
/* A hole found. */
return EXT_CONTINUE;
if (buffer_mapped(bh) && if (es.start > newex->ec_block) {
end >= newex->ec_block) { /* A hole found. */
start_index = index - 1; newex->ec_len = min(es.start - newex->ec_block,
/* get the 1st mapped buffer. */ newex->ec_len);
goto found_mapped_buffer; return EXT_CONTINUE;
} }
bh = bh->b_this_page;
end++;
} while (bh != head);
/* No mapped buffer in the range found in this page,
* We need to look up next page.
*/
if (index >= ret) {
/* There is no page left, but we need to limit
* newex->ec_len.
*/
newex->ec_len = end - newex->ec_block;
goto out;
}
goto next_page;
} else {
/*Find contiguous delayed buffers. */
if (ret > 0 && pages[0]->index == last_offset)
head = page_buffers(pages[0]);
bh = head;
index = 1;
start_index = 0;
}
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; flags |= FIEMAP_EXTENT_DELALLOC;
newex->ec_block = end; newex->ec_len = es.start + es.len - newex->ec_block;
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 < 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[start_index]->index + index
- start_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;
length = (__u64)newex->ec_len << blksize_bits;
if (ex && ext4_ext_is_uninitialized(ex)) if (ex && ext4_ext_is_uninitialized(ex))
flags |= FIEMAP_EXTENT_UNWRITTEN; flags |= FIEMAP_EXTENT_UNWRITTEN;
if (next == EXT_MAX_BLOCKS) if (next == EXT_MAX_BLOCKS)
flags |= FIEMAP_EXTENT_LAST; flags |= FIEMAP_EXTENT_LAST;
blksize_bits = inode->i_sb->s_blocksize_bits;
logical = (__u64)newex->ec_block << blksize_bits;
physical = (__u64)newex->ec_start << blksize_bits;
length = (__u64)newex->ec_len << blksize_bits;
ret = fiemap_fill_next_extent(fieinfo, logical, physical, ret = fiemap_fill_next_extent(fieinfo, logical, physical,
length, flags); length, flags);
if (ret < 0) if (ret < 0)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment