aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext4/file.c
diff options
context:
space:
mode:
authorPatrick McHardy <kaber@trash.net>2013-03-31 18:10:34 +0200
committerPatrick McHardy <kaber@trash.net>2013-03-31 18:10:34 +0200
commit70711d223510ba1773cfe1d7770a56141c815ff8 (patch)
tree4a71f38a3a554ddecaa31b7d8c6bc49b7d1705b4 /fs/ext4/file.c
parentd53b4ed072d9779cdf53582c46436dec06d0961f (diff)
parent19f949f52599ba7c3f67a5897ac6be14bfcb1200 (diff)
Merge tag 'v3.8' of /home/kaber/src/repos/linux
Linux 3.8 Signed-off-by: Patrick McHardy <kaber@trash.net> Conflicts: include/linux/Kbuild include/linux/netlink.h
Diffstat (limited to 'fs/ext4/file.c')
-rw-r--r--fs/ext4/file.c462
1 files changed, 429 insertions, 33 deletions
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8c7642a0005..405565a6227 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -24,6 +24,7 @@
#include <linux/mount.h>
#include <linux/path.h>
#include <linux/quotaops.h>
+#include <linux/pagevec.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -55,11 +56,11 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
return 0;
}
-static void ext4_aiodio_wait(struct inode *inode)
+void ext4_unwritten_wait(struct inode *inode)
{
wait_queue_head_t *wq = ext4_ioend_wq(inode);
- wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0));
+ wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
}
/*
@@ -90,11 +91,83 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
}
static ssize_t
+ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+ struct blk_plug plug;
+ int unaligned_aio = 0;
+ ssize_t ret;
+ int overwrite = 0;
+ size_t length = iov_length(iov, nr_segs);
+
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+ !is_sync_kiocb(iocb))
+ unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
+
+ /* Unaligned direct AIO must be serialized; see comment above */
+ if (unaligned_aio) {
+ mutex_lock(ext4_aio_mutex(inode));
+ ext4_unwritten_wait(inode);
+ }
+
+ BUG_ON(iocb->ki_pos != pos);
+
+ mutex_lock(&inode->i_mutex);
+ blk_start_plug(&plug);
+
+ iocb->private = &overwrite;
+
+ /* check whether we do a DIO overwrite or not */
+ if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
+ !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
+ struct ext4_map_blocks map;
+ unsigned int blkbits = inode->i_blkbits;
+ int err, len;
+
+ map.m_lblk = pos >> blkbits;
+ map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
+ - map.m_lblk;
+ len = map.m_len;
+
+ err = ext4_map_blocks(NULL, inode, &map, 0);
+ /*
+ * 'err==len' means that all of blocks has been preallocated no
+ * matter they are initialized or not. For excluding
+ * uninitialized extents, we need to check m_flags. There are
+ * two conditions that indicate for initialized extents.
+ * 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned;
+ * 2) If we do a real lookup, non-flags are returned.
+ * So we should check these two conditions.
+ */
+ if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
+ overwrite = 1;
+ }
+
+ ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+ mutex_unlock(&inode->i_mutex);
+
+ if (ret > 0 || ret == -EIOCBQUEUED) {
+ ssize_t err;
+
+ err = generic_write_sync(file, pos, ret);
+ if (err < 0 && ret > 0)
+ ret = err;
+ }
+ blk_finish_plug(&plug);
+
+ if (unaligned_aio)
+ mutex_unlock(ext4_aio_mutex(inode));
+
+ return ret;
+}
+
+static ssize_t
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
- int unaligned_aio = 0;
ssize_t ret;
/*
@@ -114,29 +187,12 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
sbi->s_bitmap_maxbytes - pos);
}
- } else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
- !is_sync_kiocb(iocb))) {
- unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
- }
-
- /* Unaligned direct AIO must be serialized; see comment above */
- if (unaligned_aio) {
- static unsigned long unaligned_warn_time;
-
- /* Warn about this once per day */
- if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
- ext4_msg(inode->i_sb, KERN_WARNING,
- "Unaligned AIO/DIO on inode %ld by %s; "
- "performance will be poor.",
- inode->i_ino, current->comm);
- mutex_lock(ext4_aio_mutex(inode));
- ext4_aiodio_wait(inode);
}
- ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
-
- if (unaligned_aio)
- mutex_unlock(ext4_aio_mutex(inode));
+ if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
+ ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
+ else
+ ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
return ret;
}
@@ -144,6 +200,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
static const struct vm_operations_struct ext4_file_vm_ops = {
.fault = filemap_fault,
.page_mkwrite = ext4_page_mkwrite,
+ .remap_pages = generic_file_remap_pages,
};
static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
@@ -154,7 +211,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
return -ENOEXEC;
file_accessed(file);
vma->vm_ops = &ext4_file_vm_ops;
- vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
@@ -181,9 +237,21 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
if (!IS_ERR(cp)) {
+ handle_t *handle;
+ int err;
+
+ handle = ext4_journal_start_sb(sb, 1);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ err = ext4_journal_get_write_access(handle, sbi->s_sbh);
+ if (err) {
+ ext4_journal_stop(handle);
+ return err;
+ }
strlcpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
- ext4_mark_super_dirty(sb);
+ ext4_handle_dirty_super(handle, sb);
+ ext4_journal_stop(handle);
}
}
/*
@@ -211,11 +279,329 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
}
/*
- * ext4_llseek() copied from generic_file_llseek() to handle both
- * block-mapped and extent-mapped maxbytes values. This should
- * otherwise be identical with generic_file_llseek().
+ * Here we use ext4_map_blocks() to get a block mapping for a extent-based
+ * file rather than ext4_ext_walk_space() because we can introduce
+ * SEEK_DATA/SEEK_HOLE for block-mapped and extent-mapped file at the same
+ * function. When extent status tree has been fully implemented, it will
+ * track all extent status for a file and we can directly use it to
+ * retrieve the offset for SEEK_DATA/SEEK_HOLE.
*/
-loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
+
+/*
+ * When we retrieve the offset for SEEK_DATA/SEEK_HOLE, we would need to
+ * lookup page cache to check whether or not there has some data between
+ * [startoff, endoff] because, if this range contains an unwritten extent,
+ * we determine this extent as a data or a hole according to whether the
+ * page cache has data or not.
+ */
+static int ext4_find_unwritten_pgoff(struct inode *inode,
+ int whence,
+ struct ext4_map_blocks *map,
+ loff_t *offset)
+{
+ struct pagevec pvec;
+ unsigned int blkbits;
+ pgoff_t index;
+ pgoff_t end;
+ loff_t endoff;
+ loff_t startoff;
+ loff_t lastoff;
+ int found = 0;
+
+ blkbits = inode->i_sb->s_blocksize_bits;
+ startoff = *offset;
+ lastoff = startoff;
+ endoff = (map->m_lblk + map->m_len) << blkbits;
+
+ index = startoff >> PAGE_CACHE_SHIFT;
+ end = endoff >> PAGE_CACHE_SHIFT;
+
+ pagevec_init(&pvec, 0);
+ do {
+ int i, num;
+ unsigned long nr_pages;
+
+ num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+ nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
+ (pgoff_t)num);
+ if (nr_pages == 0) {
+ if (whence == SEEK_DATA)
+ break;
+
+ BUG_ON(whence != SEEK_HOLE);
+ /*
+ * If this is the first time to go into the loop and
+ * offset is not beyond the end offset, it will be a
+ * hole at this offset
+ */
+ if (lastoff == startoff || lastoff < endoff)
+ found = 1;
+ break;
+ }
+
+ /*
+ * If this is the first time to go into the loop and
+ * offset is smaller than the first page offset, it will be a
+ * hole at this offset.
+ */
+ if (lastoff == startoff && whence == SEEK_HOLE &&
+ lastoff < page_offset(pvec.pages[0])) {
+ found = 1;
+ break;
+ }
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+ struct buffer_head *bh, *head;
+
+ /*
+ * If the current offset is not beyond the end of given
+ * range, it will be a hole.
+ */
+ if (lastoff < endoff && whence == SEEK_HOLE &&
+ page->index > end) {
+ found = 1;
+ *offset = lastoff;
+ goto out;
+ }
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != inode->i_mapping)) {
+ unlock_page(page);
+ continue;
+ }
+
+ if (!page_has_buffers(page)) {
+ unlock_page(page);
+ continue;
+ }
+
+ if (page_has_buffers(page)) {
+ lastoff = page_offset(page);
+ bh = head = page_buffers(page);
+ do {
+ if (buffer_uptodate(bh) ||
+ buffer_unwritten(bh)) {
+ if (whence == SEEK_DATA)
+ found = 1;
+ } else {
+ if (whence == SEEK_HOLE)
+ found = 1;
+ }
+ if (found) {
+ *offset = max_t(loff_t,
+ startoff, lastoff);
+ unlock_page(page);
+ goto out;
+ }
+ lastoff += bh->b_size;
+ bh = bh->b_this_page;
+ } while (bh != head);
+ }
+
+ lastoff = page_offset(page) + PAGE_SIZE;
+ unlock_page(page);
+ }
+
+ /*
+ * The no. of pages is less than our desired, that would be a
+ * hole in there.
+ */
+ if (nr_pages < num && whence == SEEK_HOLE) {
+ found = 1;
+ *offset = lastoff;
+ break;
+ }
+
+ index = pvec.pages[i - 1]->index + 1;
+ pagevec_release(&pvec);
+ } while (index <= end);
+
+out:
+ pagevec_release(&pvec);
+ return found;
+}
+
+/*
+ * ext4_seek_data() retrieves the offset for SEEK_DATA.
+ */
+static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
+{
+ struct inode *inode = file->f_mapping->host;
+ struct ext4_map_blocks map;
+ struct extent_status es;
+ ext4_lblk_t start, last, end;
+ loff_t dataoff, isize;
+ int blkbits;
+ int ret = 0;
+
+ mutex_lock(&inode->i_mutex);
+
+ isize = i_size_read(inode);
+ if (offset >= isize) {
+ mutex_unlock(&inode->i_mutex);
+ return -ENXIO;
+ }
+
+ blkbits = inode->i_sb->s_blocksize_bits;
+ start = offset >> blkbits;
+ last = start;
+ end = isize >> blkbits;
+ dataoff = offset;
+
+ do {
+ map.m_lblk = last;
+ map.m_len = end - last + 1;
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+ if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
+ if (last != start)
+ dataoff = last << blkbits;
+ break;
+ }
+
+ /*
+ * If there is a delay extent at this offset,
+ * it will be as a data.
+ */
+ es.start = last;
+ (void)ext4_es_find_extent(inode, &es);
+ if (last >= es.start &&
+ last < es.start + es.len) {
+ if (last != start)
+ dataoff = last << blkbits;
+ break;
+ }
+
+ /*
+ * If there is a unwritten extent at this offset,
+ * it will be as a data or a hole according to page
+ * cache that has data or not.
+ */
+ if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+ int unwritten;
+ unwritten = ext4_find_unwritten_pgoff(inode, SEEK_DATA,
+ &map, &dataoff);
+ if (unwritten)
+ break;
+ }
+
+ last++;
+ dataoff = last << blkbits;
+ } while (last <= end);
+
+ mutex_unlock(&inode->i_mutex);
+
+ if (dataoff > isize)
+ return -ENXIO;
+
+ if (dataoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
+ return -EINVAL;
+ if (dataoff > maxsize)
+ return -EINVAL;
+
+ if (dataoff != file->f_pos) {
+ file->f_pos = dataoff;
+ file->f_version = 0;
+ }
+
+ return dataoff;
+}
+
+/*
+ * ext4_seek_hole() retrieves the offset for SEEK_HOLE.
+ */
+static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
+{
+ struct inode *inode = file->f_mapping->host;
+ struct ext4_map_blocks map;
+ struct extent_status es;
+ ext4_lblk_t start, last, end;
+ loff_t holeoff, isize;
+ int blkbits;
+ int ret = 0;
+
+ mutex_lock(&inode->i_mutex);
+
+ isize = i_size_read(inode);
+ if (offset >= isize) {
+ mutex_unlock(&inode->i_mutex);
+ return -ENXIO;
+ }
+
+ blkbits = inode->i_sb->s_blocksize_bits;
+ start = offset >> blkbits;
+ last = start;
+ end = isize >> blkbits;
+ holeoff = offset;
+
+ do {
+ map.m_lblk = last;
+ map.m_len = end - last + 1;
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+ if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
+ last += ret;
+ holeoff = last << blkbits;
+ continue;
+ }
+
+ /*
+ * If there is a delay extent at this offset,
+ * we will skip this extent.
+ */
+ es.start = last;
+ (void)ext4_es_find_extent(inode, &es);
+ if (last >= es.start &&
+ last < es.start + es.len) {
+ last = es.start + es.len;
+ holeoff = last << blkbits;
+ continue;
+ }
+
+ /*
+ * If there is a unwritten extent at this offset,
+ * it will be as a data or a hole according to page
+ * cache that has data or not.
+ */
+ if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+ int unwritten;
+ unwritten = ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
+ &map, &holeoff);
+ if (!unwritten) {
+ last += ret;
+ holeoff = last << blkbits;
+ continue;
+ }
+ }
+
+ /* find a hole */
+ break;
+ } while (last <= end);
+
+ mutex_unlock(&inode->i_mutex);
+
+ if (holeoff > isize)
+ holeoff = isize;
+
+ if (holeoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
+ return -EINVAL;
+ if (holeoff > maxsize)
+ return -EINVAL;
+
+ if (holeoff != file->f_pos) {
+ file->f_pos = holeoff;
+ file->f_version = 0;
+ }
+
+ return holeoff;
+}
+
+/*
+ * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
+ * by calling generic_file_llseek_size() with the appropriate maxbytes
+ * value for each.
+ */
+loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
loff_t maxbytes;
@@ -225,7 +611,19 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
else
maxbytes = inode->i_sb->s_maxbytes;
- return generic_file_llseek_size(file, offset, origin, maxbytes);
+ switch (whence) {
+ case SEEK_SET:
+ case SEEK_CUR:
+ case SEEK_END:
+ return generic_file_llseek_size(file, offset, whence,
+ maxbytes, i_size_read(inode));
+ case SEEK_DATA:
+ return ext4_seek_data(file, offset, maxbytes);
+ case SEEK_HOLE:
+ return ext4_seek_hole(file, offset, maxbytes);
+ }
+
+ return -EINVAL;
}
const struct file_operations ext4_file_operations = {
@@ -250,12 +648,10 @@ const struct file_operations ext4_file_operations = {
const struct inode_operations ext4_file_inode_operations = {
.setattr = ext4_setattr,
.getattr = ext4_getattr,
-#ifdef CONFIG_EXT4_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = ext4_listxattr,
.removexattr = generic_removexattr,
-#endif
.get_acl = ext4_get_acl,
.fiemap = ext4_fiemap,
};