summaryrefslogtreecommitdiffstats
path: root/fs/ext4/inode.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/inode.c')
-rw-r--r--fs/ext4/inode.c926
1 files changed, 304 insertions, 622 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1d880ae90c1f..28f28de0c1b6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -164,39 +164,18 @@ int ext4_inode_is_fast_symlink(struct inode *inode)
}
/*
- * Restart the transaction associated with *handle. This does a commit,
- * 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 nblocks)
-{
- int ret;
-
- /*
- * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
- * moment, get_block can be called only for blocks inside i_size since
- * page cache has been already dropped and writes are blocked by
- * i_mutex. So we can safely drop the i_data_sem here.
- */
- 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, nblocks);
- down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
-
- return ret;
-}
-
-/*
* Called at the last iput() if i_nlink is zero.
*/
void ext4_evict_inode(struct inode *inode)
{
handle_t *handle;
int err;
- int extra_credits = 3;
+ /*
+ * Credits for final inode cleanup and freeing:
+ * sb + inode (ext4_orphan_del()), block bitmap, group descriptor
+ * (xattr block freeing), bitmap, group descriptor (inode freeing)
+ */
+ int extra_credits = 6;
struct ext4_xattr_inode_array *ea_inode_array = NULL;
trace_ext4_evict_inode(inode);
@@ -252,8 +231,12 @@ void ext4_evict_inode(struct inode *inode)
if (!IS_NOQUOTA(inode))
extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb);
+ /*
+ * Block bitmap, group descriptor, and inode are accounted in both
+ * ext4_blocks_for_truncate() and extra_credits. So subtract 3.
+ */
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
- ext4_blocks_for_truncate(inode)+extra_credits);
+ ext4_blocks_for_truncate(inode) + extra_credits - 3);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
@@ -827,136 +810,6 @@ int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
#define DIO_MAX_BLOCKS 4096
/*
- * Get blocks function for the cases that need to start a transaction -
- * generally difference cases of direct IO and DAX IO. It also handles retries
- * in case of ENOSPC.
- */
-static int ext4_get_block_trans(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int flags)
-{
- int dio_credits;
- handle_t *handle;
- int retries = 0;
- int ret;
-
- /* Trim mapping request to maximum we can map at once for DIO */
- if (bh_result->b_size >> inode->i_blkbits > DIO_MAX_BLOCKS)
- bh_result->b_size = DIO_MAX_BLOCKS << inode->i_blkbits;
- dio_credits = ext4_chunk_trans_blocks(inode,
- bh_result->b_size >> inode->i_blkbits);
-retry:
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- ret = _ext4_get_block(inode, iblock, bh_result, flags);
- ext4_journal_stop(handle);
-
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
- return ret;
-}
-
-/* Get block function for DIO reads and writes to inodes without extents */
-int ext4_dio_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh, int create)
-{
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- if (!create)
- return _ext4_get_block(inode, iblock, bh, 0);
- return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE);
-}
-
-/*
- * Get block function for AIO DIO writes when we create unwritten extent if
- * blocks are not allocated yet. The extent will be converted to written
- * after IO is complete.
- */
-static int ext4_dio_get_block_unwritten_async(struct inode *inode,
- sector_t iblock, struct buffer_head *bh_result, int create)
-{
- int ret;
-
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- ret = ext4_get_block_trans(inode, iblock, bh_result,
- EXT4_GET_BLOCKS_IO_CREATE_EXT);
-
- /*
- * When doing DIO using unwritten extents, we need io_end to convert
- * unwritten extents to written on IO completion. We allocate io_end
- * once we spot unwritten extent and store it in b_private. Generic
- * DIO code keeps b_private set and furthermore passes the value to
- * our completion callback in 'private' argument.
- */
- if (!ret && buffer_unwritten(bh_result)) {
- if (!bh_result->b_private) {
- ext4_io_end_t *io_end;
-
- io_end = ext4_init_io_end(inode, GFP_KERNEL);
- if (!io_end)
- return -ENOMEM;
- bh_result->b_private = io_end;
- ext4_set_io_unwritten_flag(inode, io_end);
- }
- set_buffer_defer_completion(bh_result);
- }
-
- return ret;
-}
-
-/*
- * Get block function for non-AIO DIO writes when we create unwritten extent if
- * blocks are not allocated yet. The extent will be converted to written
- * after IO is complete by ext4_direct_IO_write().
- */
-static int ext4_dio_get_block_unwritten_sync(struct inode *inode,
- sector_t iblock, struct buffer_head *bh_result, int create)
-{
- int ret;
-
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- ret = ext4_get_block_trans(inode, iblock, bh_result,
- EXT4_GET_BLOCKS_IO_CREATE_EXT);
-
- /*
- * Mark inode as having pending DIO writes to unwritten extents.
- * ext4_direct_IO_write() checks this flag and converts extents to
- * written.
- */
- if (!ret && buffer_unwritten(bh_result))
- ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
-
- return ret;
-}
-
-static int ext4_dio_get_block_overwrite(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- int ret;
-
- ext4_debug("ext4_dio_get_block_overwrite: inode %lu, create flag %d\n",
- inode->i_ino, create);
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- ret = _ext4_get_block(inode, iblock, bh_result, 0);
- /*
- * Blocks should have been preallocated! ext4_file_write_iter() checks
- * that.
- */
- WARN_ON_ONCE(!buffer_mapped(bh_result) || buffer_unwritten(bh_result));
-
- return ret;
-}
-
-
-/*
* `handle' can be NULL if create is zero
*/
struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
@@ -2341,6 +2194,79 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
}
/*
+ * mpage_process_page - update page buffers corresponding to changed extent and
+ * may submit fully mapped page for IO
+ *
+ * @mpd - description of extent to map, on return next extent to map
+ * @m_lblk - logical block mapping.
+ * @m_pblk - corresponding physical mapping.
+ * @map_bh - determines on return whether this page requires any further
+ * mapping or not.
+ * Scan given page buffers corresponding to changed extent and update buffer
+ * state according to new extent state.
+ * We map delalloc buffers to their physical location, clear unwritten bits.
+ * If the given page is not fully mapped, we update @map to the next extent in
+ * the given page that needs mapping & return @map_bh as true.
+ */
+static int mpage_process_page(struct mpage_da_data *mpd, struct page *page,
+ ext4_lblk_t *m_lblk, ext4_fsblk_t *m_pblk,
+ bool *map_bh)
+{
+ struct buffer_head *head, *bh;
+ ext4_io_end_t *io_end = mpd->io_submit.io_end;
+ ext4_lblk_t lblk = *m_lblk;
+ ext4_fsblk_t pblock = *m_pblk;
+ int err = 0;
+ int blkbits = mpd->inode->i_blkbits;
+ ssize_t io_end_size = 0;
+ struct ext4_io_end_vec *io_end_vec = ext4_last_io_end_vec(io_end);
+
+ bh = head = page_buffers(page);
+ do {
+ if (lblk < mpd->map.m_lblk)
+ continue;
+ if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
+ /*
+ * Buffer after end of mapped extent.
+ * Find next buffer in the page to map.
+ */
+ mpd->map.m_len = 0;
+ mpd->map.m_flags = 0;
+ io_end_vec->size += io_end_size;
+ io_end_size = 0;
+
+ err = mpage_process_page_bufs(mpd, head, bh, lblk);
+ if (err > 0)
+ err = 0;
+ if (!err && mpd->map.m_len && mpd->map.m_lblk > lblk) {
+ io_end_vec = ext4_alloc_io_end_vec(io_end);
+ if (IS_ERR(io_end_vec)) {
+ err = PTR_ERR(io_end_vec);
+ goto out;
+ }
+ io_end_vec->offset = mpd->map.m_lblk << blkbits;
+ }
+ *map_bh = true;
+ goto out;
+ }
+ if (buffer_delay(bh)) {
+ clear_buffer_delay(bh);
+ bh->b_blocknr = pblock++;
+ }
+ clear_buffer_unwritten(bh);
+ io_end_size += (1 << blkbits);
+ } while (lblk++, (bh = bh->b_this_page) != head);
+
+ io_end_vec->size += io_end_size;
+ io_end_size = 0;
+ *map_bh = false;
+out:
+ *m_lblk = lblk;
+ *m_pblk = pblock;
+ return err;
+}
+
+/*
* mpage_map_buffers - update buffers corresponding to changed extent and
* submit fully mapped pages for IO
*
@@ -2359,12 +2285,12 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
struct pagevec pvec;
int nr_pages, i;
struct inode *inode = mpd->inode;
- struct buffer_head *head, *bh;
int bpp_bits = PAGE_SHIFT - inode->i_blkbits;
pgoff_t start, end;
ext4_lblk_t lblk;
- sector_t pblock;
+ ext4_fsblk_t pblock;
int err;
+ bool map_bh = false;
start = mpd->map.m_lblk >> bpp_bits;
end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits;
@@ -2380,50 +2306,19 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
- bh = head = page_buffers(page);
- do {
- if (lblk < mpd->map.m_lblk)
- continue;
- if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
- /*
- * Buffer after end of mapped extent.
- * Find next buffer in the page to map.
- */
- mpd->map.m_len = 0;
- mpd->map.m_flags = 0;
- /*
- * FIXME: If dioread_nolock supports
- * blocksize < pagesize, we need to make
- * sure we add size mapped so far to
- * io_end->size as the following call
- * can submit the page for IO.
- */
- err = mpage_process_page_bufs(mpd, head,
- bh, lblk);
- pagevec_release(&pvec);
- if (err > 0)
- err = 0;
- return err;
- }
- if (buffer_delay(bh)) {
- clear_buffer_delay(bh);
- bh->b_blocknr = pblock++;
- }
- clear_buffer_unwritten(bh);
- } while (lblk++, (bh = bh->b_this_page) != head);
-
+ err = mpage_process_page(mpd, page, &lblk, &pblock,
+ &map_bh);
/*
- * FIXME: This is going to break if dioread_nolock
- * supports blocksize < pagesize as we will try to
- * convert potentially unmapped parts of inode.
+ * If map_bh is true, means page may require further bh
+ * mapping, or maybe the page was submitted for IO.
+ * So we return to call further extent mapping.
*/
- mpd->io_submit.io_end->size += PAGE_SIZE;
+ if (err < 0 || map_bh == true)
+ goto out;
/* Page fully mapped - let IO run! */
err = mpage_submit_page(mpd, page);
- if (err < 0) {
- pagevec_release(&pvec);
- return err;
- }
+ if (err < 0)
+ goto out;
}
pagevec_release(&pvec);
}
@@ -2431,6 +2326,9 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
mpd->map.m_len = 0;
mpd->map.m_flags = 0;
return 0;
+out:
+ pagevec_release(&pvec);
+ return err;
}
static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
@@ -2510,9 +2408,13 @@ static int mpage_map_and_submit_extent(handle_t *handle,
int err;
loff_t disksize;
int progress = 0;
+ ext4_io_end_t *io_end = mpd->io_submit.io_end;
+ struct ext4_io_end_vec *io_end_vec;
- mpd->io_submit.io_end->offset =
- ((loff_t)map->m_lblk) << inode->i_blkbits;
+ io_end_vec = ext4_alloc_io_end_vec(io_end);
+ if (IS_ERR(io_end_vec))
+ return PTR_ERR(io_end_vec);
+ io_end_vec->offset = ((loff_t)map->m_lblk) << inode->i_blkbits;
do {
err = mpage_map_one_extent(handle, mpd);
if (err < 0) {
@@ -3406,473 +3308,235 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
return inode->i_state & I_DIRTY_DATASYNC;
}
-static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
- unsigned flags, struct iomap *iomap, struct iomap *srcmap)
+static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
+ struct ext4_map_blocks *map, loff_t offset,
+ loff_t length)
{
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- unsigned int blkbits = inode->i_blkbits;
- unsigned long first_block, last_block;
- struct ext4_map_blocks map;
- bool delalloc = false;
- int ret;
-
- if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
- return -EINVAL;
- first_block = offset >> blkbits;
- last_block = min_t(loff_t, (offset + length - 1) >> blkbits,
- EXT4_MAX_LOGICAL_BLOCK);
-
- if (flags & IOMAP_REPORT) {
- if (ext4_has_inline_data(inode)) {
- ret = ext4_inline_data_iomap(inode, iomap);
- if (ret != -EAGAIN) {
- if (ret == 0 && offset >= iomap->length)
- ret = -ENOENT;
- return ret;
- }
- }
- } else {
- if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
- return -ERANGE;
- }
-
- map.m_lblk = first_block;
- map.m_len = last_block - first_block + 1;
-
- if (flags & IOMAP_REPORT) {
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0)
- return ret;
-
- if (ret == 0) {
- ext4_lblk_t end = map.m_lblk + map.m_len - 1;
- struct extent_status es;
-
- ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
- map.m_lblk, end, &es);
-
- if (!es.es_len || es.es_lblk > end) {
- /* entire range is a hole */
- } else if (es.es_lblk > map.m_lblk) {
- /* range starts with a hole */
- map.m_len = es.es_lblk - map.m_lblk;
- } else {
- ext4_lblk_t offs = 0;
-
- if (es.es_lblk < map.m_lblk)
- offs = map.m_lblk - es.es_lblk;
- map.m_lblk = es.es_lblk + offs;
- map.m_len = es.es_len - offs;
- delalloc = true;
- }
- }
- } else if (flags & IOMAP_WRITE) {
- int dio_credits;
- handle_t *handle;
- int retries = 0;
-
- /* Trim mapping request to maximum we can map at once for DIO */
- if (map.m_len > DIO_MAX_BLOCKS)
- map.m_len = DIO_MAX_BLOCKS;
- dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
-retry:
- /*
- * Either we allocate blocks and then we don't get unwritten
- * extent so we have reserved enough credits, or the blocks
- * are already allocated and unwritten and in that case
- * extent conversion fits in the credits as well.
- */
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
- dio_credits);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- ret = ext4_map_blocks(handle, inode, &map,
- EXT4_GET_BLOCKS_CREATE_ZERO);
- if (ret < 0) {
- ext4_journal_stop(handle);
- if (ret == -ENOSPC &&
- ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
- return ret;
- }
-
- /*
- * If we added blocks beyond i_size, we need to make sure they
- * will get truncated if we crash before updating i_size in
- * ext4_iomap_end(). For faults we don't need to do that (and
- * even cannot because for orphan list operations inode_lock is
- * required) - if we happen to instantiate block beyond i_size,
- * it is because we race with truncate which has already added
- * the inode to the orphan list.
- */
- if (!(flags & IOMAP_FAULT) && first_block + map.m_len >
- (i_size_read(inode) + (1 << blkbits) - 1) >> blkbits) {
- int err;
-
- err = ext4_orphan_add(handle, inode);
- if (err < 0) {
- ext4_journal_stop(handle);
- return err;
- }
- }
- ext4_journal_stop(handle);
- } else {
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0)
- return ret;
- }
+ u8 blkbits = inode->i_blkbits;
+ /*
+ * Writes that span EOF might trigger an I/O size update on completion,
+ * so consider them to be dirty for the purpose of O_DSYNC, even if
+ * there is no other metadata changes being made or are pending.
+ */
iomap->flags = 0;
- if (ext4_inode_datasync_dirty(inode))
+ if (ext4_inode_datasync_dirty(inode) ||
+ offset + length > i_size_read(inode))
iomap->flags |= IOMAP_F_DIRTY;
+
+ if (map->m_flags & EXT4_MAP_NEW)
+ iomap->flags |= IOMAP_F_NEW;
+
iomap->bdev = inode->i_sb->s_bdev;
- iomap->dax_dev = sbi->s_daxdev;
- iomap->offset = (u64)first_block << blkbits;
- iomap->length = (u64)map.m_len << blkbits;
+ iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+ iomap->offset = (u64) map->m_lblk << blkbits;
+ iomap->length = (u64) map->m_len << blkbits;
- if (ret == 0) {
- iomap->type = delalloc ? IOMAP_DELALLOC : IOMAP_HOLE;
- iomap->addr = IOMAP_NULL_ADDR;
+ /*
+ * Flags passed to ext4_map_blocks() for direct I/O writes can result
+ * in m_flags having both EXT4_MAP_MAPPED and EXT4_MAP_UNWRITTEN bits
+ * set. In order for any allocated unwritten extents to be converted
+ * into written extents correctly within the ->end_io() handler, we
+ * need to ensure that the iomap->type is set appropriately. Hence, the
+ * reason why we need to check whether the EXT4_MAP_UNWRITTEN bit has
+ * been set first.
+ */
+ if (map->m_flags & EXT4_MAP_UNWRITTEN) {
+ iomap->type = IOMAP_UNWRITTEN;
+ iomap->addr = (u64) map->m_pblk << blkbits;
+ } else if (map->m_flags & EXT4_MAP_MAPPED) {
+ iomap->type = IOMAP_MAPPED;
+ iomap->addr = (u64) map->m_pblk << blkbits;
} else {
- if (map.m_flags & EXT4_MAP_MAPPED) {
- iomap->type = IOMAP_MAPPED;
- } else if (map.m_flags & EXT4_MAP_UNWRITTEN) {
- iomap->type = IOMAP_UNWRITTEN;
- } else {
- WARN_ON_ONCE(1);
- return -EIO;
- }
- iomap->addr = (u64)map.m_pblk << blkbits;
+ iomap->type = IOMAP_HOLE;
+ iomap->addr = IOMAP_NULL_ADDR;
}
-
- if (map.m_flags & EXT4_MAP_NEW)
- iomap->flags |= IOMAP_F_NEW;
-
- return 0;
}
-static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
- ssize_t written, unsigned flags, struct iomap *iomap)
+static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map,
+ unsigned int flags)
{
- int ret = 0;
handle_t *handle;
- int blkbits = inode->i_blkbits;
- bool truncate = false;
+ u8 blkbits = inode->i_blkbits;
+ int ret, dio_credits, m_flags = 0, retries = 0;
- if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT))
- return 0;
-
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto orphan_del;
- }
- if (ext4_update_inode_size(inode, offset + written))
- ext4_mark_inode_dirty(handle, inode);
/*
- * We may need to truncate allocated but not written blocks beyond EOF.
+ * Trim the mapping request to the maximum value that we can map at
+ * once for direct I/O.
*/
- if (iomap->offset + iomap->length >
- ALIGN(inode->i_size, 1 << blkbits)) {
- ext4_lblk_t written_blk, end_blk;
+ if (map->m_len > DIO_MAX_BLOCKS)
+ map->m_len = DIO_MAX_BLOCKS;
+ dio_credits = ext4_chunk_trans_blocks(inode, map->m_len);
- written_blk = (offset + written) >> blkbits;
- end_blk = (offset + length) >> blkbits;
- if (written_blk < end_blk && ext4_can_truncate(inode))
- truncate = true;
- }
+retry:
/*
- * Remove inode from orphan list if we were extending a inode and
- * everything went fine.
+ * Either we allocate blocks and then don't get an unwritten extent, so
+ * in that case we have reserved enough credits. Or, the blocks are
+ * already allocated and unwritten. In that case, the extent conversion
+ * fits into the credits as well.
*/
- if (!truncate && inode->i_nlink &&
- !list_empty(&EXT4_I(inode)->i_orphan))
- ext4_orphan_del(handle, inode);
- ext4_journal_stop(handle);
- if (truncate) {
- ext4_truncate_failed_write(inode);
-orphan_del:
- /*
- * If truncate failed early the inode might still be on the
- * orphan list; we need to make sure the inode is removed from
- * the orphan list in that case.
- */
- if (inode->i_nlink)
- ext4_orphan_del(NULL, inode);
- }
- return ret;
-}
-
-const struct iomap_ops ext4_iomap_ops = {
- .iomap_begin = ext4_iomap_begin,
- .iomap_end = ext4_iomap_end,
-};
-
-static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
- ssize_t size, void *private)
-{
- ext4_io_end_t *io_end = private;
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
- /* if not async direct IO just return */
- if (!io_end)
- return 0;
+ /*
+ * DAX and direct I/O are the only two operations that are currently
+ * supported with IOMAP_WRITE.
+ */
+ WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT));
+ if (IS_DAX(inode))
+ m_flags = EXT4_GET_BLOCKS_CREATE_ZERO;
+ /*
+ * We use i_size instead of i_disksize here because delalloc writeback
+ * can complete at any point during the I/O and subsequently push the
+ * i_disksize out to i_size. This could be beyond where direct I/O is
+ * happening and thus expose allocated blocks to direct I/O reads.
+ */
+ else if ((map->m_lblk * (1 << blkbits)) >= i_size_read(inode))
+ m_flags = EXT4_GET_BLOCKS_CREATE;
+ else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT;
- ext_debug("ext4_end_io_dio(): io_end 0x%p "
- "for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
- io_end, io_end->inode->i_ino, iocb, offset, size);
+ ret = ext4_map_blocks(handle, inode, map, m_flags);
/*
- * Error during AIO DIO. We cannot convert unwritten extents as the
- * data was not written. Just clear the unwritten flag and drop io_end.
+ * We cannot fill holes in indirect tree based inodes as that could
+ * expose stale data in the case of a crash. Use the magic error code
+ * to fallback to buffered I/O.
*/
- if (size <= 0) {
- ext4_clear_io_unwritten_flag(io_end);
- size = 0;
- }
- io_end->offset = offset;
- io_end->size = size;
- ext4_put_io_end(io_end);
+ if (!m_flags && !ret)
+ ret = -ENOTBLK;
- return 0;
+ ext4_journal_stop(handle);
+ if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+
+ return ret;
}
-/*
- * Handling of direct IO writes.
- *
- * For ext4 extent files, ext4 will do direct-io write even 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 unwritten
- * If those blocks were preallocated, we mark sure they are split, but
- * still keep the range to write as unwritten.
- *
- * The unwritten 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 conversion
- * 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_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
+
+static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+ unsigned flags, struct iomap *iomap, struct iomap *srcmap)
{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct ext4_inode_info *ei = EXT4_I(inode);
- ssize_t ret;
- loff_t offset = iocb->ki_pos;
- size_t count = iov_iter_count(iter);
- int overwrite = 0;
- get_block_t *get_block_func = NULL;
- int dio_flags = 0;
- loff_t final_size = offset + count;
- int orphan = 0;
- handle_t *handle;
+ int ret;
+ struct ext4_map_blocks map;
+ u8 blkbits = inode->i_blkbits;
- if (final_size > inode->i_size || final_size > ei->i_disksize) {
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
- ret = ext4_orphan_add(handle, inode);
- if (ret) {
- ext4_journal_stop(handle);
- goto out;
- }
- orphan = 1;
- ext4_update_i_disksize(inode, inode->i_size);
- ext4_journal_stop(handle);
- }
+ if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
+ return -EINVAL;
- BUG_ON(iocb->private == NULL);
+ if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
+ return -ERANGE;
/*
- * Make all waiters for direct IO properly wait also for extent
- * conversion. This also disallows race between truncate() and
- * overwrite DIO as i_dio_count needs to be incremented under i_mutex.
+ * Calculate the first and last logical blocks respectively.
*/
- inode_dio_begin(inode);
+ map.m_lblk = offset >> blkbits;
+ map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
+ EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
- /* If we do a overwrite dio, i_mutex locking can be released */
- overwrite = *((int *)iocb->private);
+ if (flags & IOMAP_WRITE)
+ ret = ext4_iomap_alloc(inode, &map, flags);
+ else
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+
+ if (ret < 0)
+ return ret;
- if (overwrite)
- inode_unlock(inode);
+ ext4_set_iomap(inode, iomap, &map, offset, length);
+ return 0;
+}
+
+static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
+ ssize_t written, unsigned flags, struct iomap *iomap)
+{
/*
- * For extent mapped files we could direct write to holes and fallocate.
- *
- * Allocated blocks to fill the hole are marked as unwritten to prevent
- * parallel 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 unwritten.
- *
- * For non AIO case, we will convert those unwritten extents to written
- * after return back from blockdev_direct_IO. That way we save us from
- * allocating io_end structure and also the overhead of offloading
- * the extent convertion to a workqueue.
- *
- * For async DIO, the conversion needs to be deferred 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.
+ * Check to see whether an error occurred while writing out the data to
+ * the allocated blocks. If so, return the magic error code so that we
+ * fallback to buffered I/O and attempt to complete the remainder of
+ * the I/O. Any blocks that may have been allocated in preparation for
+ * the direct I/O will be reused during buffered I/O.
*/
- iocb->private = NULL;
- if (overwrite)
- get_block_func = ext4_dio_get_block_overwrite;
- else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
- round_down(offset, i_blocksize(inode)) >= inode->i_size) {
- get_block_func = ext4_dio_get_block;
- dio_flags = DIO_LOCKING | DIO_SKIP_HOLES;
- } else if (is_sync_kiocb(iocb)) {
- get_block_func = ext4_dio_get_block_unwritten_sync;
- dio_flags = DIO_LOCKING;
- } else {
- get_block_func = ext4_dio_get_block_unwritten_async;
- dio_flags = DIO_LOCKING;
- }
- ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
- get_block_func, ext4_end_io_dio, NULL,
- dio_flags);
+ if (flags & (IOMAP_WRITE | IOMAP_DIRECT) && written == 0)
+ return -ENOTBLK;
- if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
- EXT4_STATE_DIO_UNWRITTEN)) {
- int err;
- /*
- * for non AIO case, since the IO is already
- * completed, we could do the conversion right here
- */
- err = ext4_convert_unwritten_extents(NULL, inode,
- offset, ret);
- if (err < 0)
- ret = err;
- ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
- }
+ return 0;
+}
- inode_dio_end(inode);
- /* take i_mutex locking again if we do a ovewrite dio */
- if (overwrite)
- inode_lock(inode);
+const struct iomap_ops ext4_iomap_ops = {
+ .iomap_begin = ext4_iomap_begin,
+ .iomap_end = ext4_iomap_end,
+};
- if (ret < 0 && final_size > inode->i_size)
- ext4_truncate_failed_write(inode);
+static bool ext4_iomap_is_delalloc(struct inode *inode,
+ struct ext4_map_blocks *map)
+{
+ struct extent_status es;
+ ext4_lblk_t offset = 0, end = map->m_lblk + map->m_len - 1;
- /* Handle extending of i_size after direct IO write */
- if (orphan) {
- int err;
+ ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
+ map->m_lblk, end, &es);
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- /*
- * We wrote the data but cannot extend
- * i_size. Bail out. In async io case, we do
- * not return error here because we have
- * already submmitted the corresponding
- * bio. Returning error here makes the caller
- * think that this IO is done and failed
- * resulting in race with bio's completion
- * handler.
- */
- if (!ret)
- ret = PTR_ERR(handle);
- if (inode->i_nlink)
- ext4_orphan_del(NULL, inode);
+ if (!es.es_len || es.es_lblk > end)
+ return false;
- goto out;
- }
- if (inode->i_nlink)
- ext4_orphan_del(handle, inode);
- if (ret > 0) {
- loff_t end = offset + ret;
- if (end > inode->i_size || end > ei->i_disksize) {
- ext4_update_i_disksize(inode, end);
- if (end > inode->i_size)
- i_size_write(inode, end);
- /*
- * We're going to return a positive `ret'
- * here due to non-zero-length I/O, so there's
- * no way of reporting error returns from
- * ext4_mark_inode_dirty() to userspace. So
- * ignore it.
- */
- ext4_mark_inode_dirty(handle, inode);
- }
- }
- err = ext4_journal_stop(handle);
- if (ret == 0)
- ret = err;
+ if (es.es_lblk > map->m_lblk) {
+ map->m_len = es.es_lblk - map->m_lblk;
+ return false;
}
-out:
- return ret;
-}
-static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct address_space *mapping = iocb->ki_filp->f_mapping;
- struct inode *inode = mapping->host;
- size_t count = iov_iter_count(iter);
- ssize_t ret;
+ offset = map->m_lblk - es.es_lblk;
+ map->m_len = es.es_len - offset;
- /*
- * Shared inode_lock is enough for us - it protects against concurrent
- * writes & truncates and since we take care of writing back page cache,
- * we are protected against page writeback as well.
- */
- inode_lock_shared(inode);
- ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
- iocb->ki_pos + count - 1);
- if (ret)
- goto out_unlock;
- ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
- iter, ext4_dio_get_block, NULL, NULL, 0);
-out_unlock:
- inode_unlock_shared(inode);
- return ret;
+ return true;
}
-static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
+ loff_t length, unsigned int flags,
+ struct iomap *iomap, struct iomap *srcmap)
{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- size_t count = iov_iter_count(iter);
- loff_t offset = iocb->ki_pos;
- ssize_t ret;
+ int ret;
+ bool delalloc = false;
+ struct ext4_map_blocks map;
+ u8 blkbits = inode->i_blkbits;
-#ifdef CONFIG_FS_ENCRYPTION
- if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode))
- return 0;
-#endif
- if (fsverity_active(inode))
- return 0;
+ if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
+ return -EINVAL;
+
+ if (ext4_has_inline_data(inode)) {
+ ret = ext4_inline_data_iomap(inode, iomap);
+ if (ret != -EAGAIN) {
+ if (ret == 0 && offset >= iomap->length)
+ ret = -ENOENT;
+ return ret;
+ }
+ }
/*
- * If we are doing data journalling we don't support O_DIRECT
+ * Calculate the first and last logical block respectively.
*/
- if (ext4_should_journal_data(inode))
- return 0;
+ map.m_lblk = offset >> blkbits;
+ map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
+ EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
- /* Let buffer I/O handle the inline data case. */
- if (ext4_has_inline_data(inode))
- return 0;
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+ if (ret < 0)
+ return ret;
+ if (ret == 0)
+ delalloc = ext4_iomap_is_delalloc(inode, &map);
- trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
- if (iov_iter_rw(iter) == READ)
- ret = ext4_direct_IO_read(iocb, iter);
- else
- ret = ext4_direct_IO_write(iocb, iter);
- trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
- return ret;
+ ext4_set_iomap(inode, iomap, &map, offset, length);
+ if (delalloc && iomap->type == IOMAP_HOLE)
+ iomap->type = IOMAP_DELALLOC;
+
+ return 0;
}
+const struct iomap_ops ext4_iomap_report_ops = {
+ .iomap_begin = ext4_iomap_begin_report,
+};
+
/*
* Pages can be marked dirty completely asynchronously from ext4's journalling
* activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do
@@ -3910,7 +3574,7 @@ static const struct address_space_operations ext4_aops = {
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
+ .direct_IO = noop_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
@@ -3927,7 +3591,7 @@ static const struct address_space_operations ext4_journalled_aops = {
.bmap = ext4_bmap,
.invalidatepage = ext4_journalled_invalidatepage,
.releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
+ .direct_IO = noop_direct_IO,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
@@ -3943,7 +3607,7 @@ static const struct address_space_operations ext4_da_aops = {
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
+ .direct_IO = noop_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
@@ -5450,11 +5114,15 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
offset = inode->i_size & (PAGE_SIZE - 1);
/*
- * All buffers in the last page remain valid? Then there's nothing to
- * do. We do the check mainly to optimize the common PAGE_SIZE ==
- * blocksize case
+ * If the page is fully truncated, we don't need to wait for any commit
+ * (and we even should not as __ext4_journalled_invalidatepage() may
+ * strip all buffers from the page but keep the page dirty which can then
+ * confuse e.g. concurrent ext4_writepage() seeing dirty page without
+ * buffers). Also we don't need to wait for any commit if all buffers in
+ * the page remain valid. This is most beneficial for the common case of
+ * blocksize == PAGESIZE.
*/
- if (offset > PAGE_SIZE - i_blocksize(inode))
+ if (!offset || offset > (PAGE_SIZE - i_blocksize(inode)))
return;
while (1) {
page = find_lock_page(inode->i_mapping,
@@ -5915,8 +5583,23 @@ static int __ext4_expand_extra_isize(struct inode *inode,
{
struct ext4_inode *raw_inode;
struct ext4_xattr_ibody_header *header;
+ unsigned int inode_size = EXT4_INODE_SIZE(inode->i_sb);
+ struct ext4_inode_info *ei = EXT4_I(inode);
int error;
+ /* this was checked at iget time, but double check for good measure */
+ if ((EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > inode_size) ||
+ (ei->i_extra_isize & 3)) {
+ EXT4_ERROR_INODE(inode, "bad extra_isize %u (inode size %u)",
+ ei->i_extra_isize,
+ EXT4_INODE_SIZE(inode->i_sb));
+ return -EFSCORRUPTED;
+ }
+ if ((new_extra_isize < ei->i_extra_isize) ||
+ (new_extra_isize < 4) ||
+ (new_extra_isize > inode_size - EXT4_GOOD_OLD_INODE_SIZE))
+ return -EINVAL; /* Should never happen */
+
raw_inode = ext4_raw_inode(iloc);
header = IHDR(inode, raw_inode);
@@ -5968,9 +5651,8 @@ static int ext4_try_to_expand_extra_isize(struct inode *inode,
* If this is felt to be critical, then e2fsck should be run to
* force a large enough s_min_extra_isize.
*/
- if (ext4_handle_valid(handle) &&
- jbd2_journal_extend(handle,
- EXT4_DATA_TRANS_BLOCKS(inode->i_sb)) != 0)
+ if (ext4_journal_extend(handle,
+ EXT4_DATA_TRANS_BLOCKS(inode->i_sb), 0) != 0)
return -ENOSPC;
if (ext4_write_trylock_xattr(inode, &no_expand) == 0)