summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/ocfs2/alloc.c105
-rw-r--r--fs/ocfs2/aops.c1146
-rw-r--r--fs/ocfs2/aops.h19
-rw-r--r--fs/ocfs2/cluster/heartbeat.c4
-rw-r--r--fs/ocfs2/dlm/dlmconvert.c30
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c1
-rw-r--r--fs/ocfs2/file.c165
-rw-r--r--fs/ocfs2/inode.c3
-rw-r--r--fs/ocfs2/inode.h6
-rw-r--r--fs/ocfs2/journal.c8
-rw-r--r--fs/ocfs2/localalloc.c4
-rw-r--r--fs/ocfs2/mmap.c4
-rw-r--r--fs/ocfs2/ocfs2.h8
-rw-r--r--fs/ocfs2/ocfs2_trace.h16
-rw-r--r--fs/ocfs2/quota_global.c2
-rw-r--r--fs/ocfs2/resize.c2
-rw-r--r--fs/ocfs2/super.c39
-rw-r--r--fs/ocfs2/super.h2
18 files changed, 723 insertions, 841 deletions
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index d002579c6f2b..70907d638b60 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -2516,21 +2516,6 @@ static int ocfs2_update_edge_lengths(handle_t *handle,
struct ocfs2_extent_block *eb;
u32 range;
- /*
- * In normal tree rotation process, we will never touch the
- * tree branch above subtree_index and ocfs2_extend_rotate_transaction
- * doesn't reserve the credits for them either.
- *
- * But we do have a special case here which will update the rightmost
- * records for all the bh in the path.
- * So we have to allocate extra credits and access them.
- */
- ret = ocfs2_extend_trans(handle, subtree_index);
- if (ret) {
- mlog_errno(ret);
- goto out;
- }
-
ret = ocfs2_journal_access_path(et->et_ci, handle, path);
if (ret) {
mlog_errno(ret);
@@ -2956,7 +2941,7 @@ static int __ocfs2_rotate_tree_left(handle_t *handle,
right_path->p_node[subtree_root].bh->b_blocknr,
right_path->p_tree_depth);
- ret = ocfs2_extend_rotate_transaction(handle, subtree_root,
+ ret = ocfs2_extend_rotate_transaction(handle, 0,
orig_credits, left_path);
if (ret) {
mlog_errno(ret);
@@ -3029,21 +3014,9 @@ static int ocfs2_remove_rightmost_path(handle_t *handle,
struct ocfs2_extent_block *eb;
struct ocfs2_extent_list *el;
-
ret = ocfs2_et_sanity_check(et);
if (ret)
goto out;
- /*
- * There's two ways we handle this depending on
- * whether path is the only existing one.
- */
- ret = ocfs2_extend_rotate_transaction(handle, 0,
- handle->h_buffer_credits,
- path);
- if (ret) {
- mlog_errno(ret);
- goto out;
- }
ret = ocfs2_journal_access_path(et->et_ci, handle, path);
if (ret) {
@@ -3641,6 +3614,14 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path,
*/
if (le16_to_cpu(right_rec->e_leaf_clusters) == 0 &&
le16_to_cpu(el->l_next_free_rec) == 1) {
+ /* extend credit for ocfs2_remove_rightmost_path */
+ ret = ocfs2_extend_rotate_transaction(handle, 0,
+ handle->h_buffer_credits,
+ right_path);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
ret = ocfs2_remove_rightmost_path(handle, et,
right_path,
@@ -3679,6 +3660,14 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
BUG_ON(ctxt->c_contig_type == CONTIG_NONE);
if (ctxt->c_split_covers_rec && ctxt->c_has_empty_extent) {
+ /* extend credit for ocfs2_remove_rightmost_path */
+ ret = ocfs2_extend_rotate_transaction(handle, 0,
+ handle->h_buffer_credits,
+ path);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
/*
* The merge code will need to create an empty
* extent to take the place of the newly
@@ -3727,6 +3716,15 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
*/
BUG_ON(!ocfs2_is_empty_extent(&el->l_recs[0]));
+ /* extend credit for ocfs2_remove_rightmost_path */
+ ret = ocfs2_extend_rotate_transaction(handle, 0,
+ handle->h_buffer_credits,
+ path);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
/* The merge left us with an empty extent, remove it. */
ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
if (ret) {
@@ -3748,6 +3746,15 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
goto out;
}
+ /* extend credit for ocfs2_remove_rightmost_path */
+ ret = ocfs2_extend_rotate_transaction(handle, 0,
+ handle->h_buffer_credits,
+ path);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
/*
* Error from this last rotate is not critical, so
@@ -3783,6 +3790,16 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
}
if (ctxt->c_split_covers_rec) {
+ /* extend credit for ocfs2_remove_rightmost_path */
+ ret = ocfs2_extend_rotate_transaction(handle, 0,
+ handle->h_buffer_credits,
+ path);
+ if (ret) {
+ mlog_errno(ret);
+ ret = 0;
+ goto out;
+ }
+
/*
* The merge may have left an empty extent in
* our leaf. Try to rotate it away.
@@ -5342,6 +5359,15 @@ static int ocfs2_truncate_rec(handle_t *handle,
struct ocfs2_extent_block *eb;
if (ocfs2_is_empty_extent(&el->l_recs[0]) && index > 0) {
+ /* extend credit for ocfs2_remove_rightmost_path */
+ ret = ocfs2_extend_rotate_transaction(handle, 0,
+ handle->h_buffer_credits,
+ path);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
if (ret) {
mlog_errno(ret);
@@ -5928,16 +5954,6 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
ocfs2_journal_dirty(handle, tl_bh);
- /* TODO: Perhaps we can calculate the bulk of the
- * credits up front rather than extending like
- * this. */
- status = ocfs2_extend_trans(handle,
- OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
- if (status < 0) {
- mlog_errno(status);
- goto bail;
- }
-
rec = tl->tl_recs[i];
start_blk = ocfs2_clusters_to_blocks(data_alloc_inode->i_sb,
le32_to_cpu(rec.t_start));
@@ -5958,6 +5974,13 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
goto bail;
}
}
+
+ status = ocfs2_extend_trans(handle,
+ OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
+ if (status < 0) {
+ mlog_errno(status);
+ goto bail;
+ }
i--;
}
@@ -6016,7 +6039,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
goto out_mutex;
}
- handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_UPDATE);
+ handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
mlog_errno(status);
@@ -6079,7 +6102,7 @@ void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb,
if (cancel)
cancel_delayed_work(&osb->osb_truncate_log_wq);
- queue_delayed_work(ocfs2_wq, &osb->osb_truncate_log_wq,
+ queue_delayed_work(osb->ocfs2_wq, &osb->osb_truncate_log_wq,
OCFS2_TRUNCATE_LOG_FLUSH_INTERVAL);
}
}
@@ -6253,7 +6276,7 @@ void ocfs2_truncate_log_shutdown(struct ocfs2_super *osb)
if (tl_inode) {
cancel_delayed_work(&osb->osb_truncate_log_wq);
- flush_workqueue(ocfs2_wq);
+ flush_workqueue(osb->ocfs2_wq);
status = ocfs2_flush_truncate_log(osb);
if (status < 0)
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 043110e5212d..1581240a7ca0 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -499,158 +499,6 @@ bail:
return status;
}
-/*
- * TODO: Make this into a generic get_blocks function.
- *
- * From do_direct_io in direct-io.c:
- * "So what we do is to permit the ->get_blocks function to populate
- * bh.b_size with the size of IO which is permitted at this offset and
- * this i_blkbits."
- *
- * This function is called directly from get_more_blocks in direct-io.c.
- *
- * called like this: dio->get_blocks(dio->inode, fs_startblk,
- * fs_count, map_bh, dio->rw == WRITE);
- */
-static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- int ret;
- u32 cpos = 0;
- int alloc_locked = 0;
- u64 p_blkno, inode_blocks, contig_blocks;
- unsigned int ext_flags;
- unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
- unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
- unsigned long len = bh_result->b_size;
- unsigned int clusters_to_alloc = 0, contig_clusters = 0;
-
- cpos = ocfs2_blocks_to_clusters(inode->i_sb, iblock);
-
- /* This function won't even be called if the request isn't all
- * nicely aligned and of the right size, so there's no need
- * for us to check any of that. */
-
- inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
-
- down_read(&OCFS2_I(inode)->ip_alloc_sem);
-
- /* This figures out the size of the next contiguous block, and
- * our logical offset */
- ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
- &contig_blocks, &ext_flags);
- up_read(&OCFS2_I(inode)->ip_alloc_sem);
-
- if (ret) {
- mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
- (unsigned long long)iblock);
- ret = -EIO;
- goto bail;
- }
-
- /* We should already CoW the refcounted extent in case of create. */
- BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
-
- /* allocate blocks if no p_blkno is found, and create == 1 */
- if (!p_blkno && create) {
- ret = ocfs2_inode_lock(inode, NULL, 1);
- if (ret < 0) {
- mlog_errno(ret);
- goto bail;
- }
-
- alloc_locked = 1;
-
- down_write(&OCFS2_I(inode)->ip_alloc_sem);
-
- /* fill hole, allocate blocks can't be larger than the size
- * of the hole */
- clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len);
- contig_clusters = ocfs2_clusters_for_blocks(inode->i_sb,
- contig_blocks);
- if (clusters_to_alloc > contig_clusters)
- clusters_to_alloc = contig_clusters;
-
- /* allocate extent and insert them into the extent tree */
- ret = ocfs2_extend_allocation(inode, cpos,
- clusters_to_alloc, 0);
- if (ret < 0) {
- up_write(&OCFS2_I(inode)->ip_alloc_sem);
- mlog_errno(ret);
- goto bail;
- }
-
- ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
- &contig_blocks, &ext_flags);
- if (ret < 0) {
- up_write(&OCFS2_I(inode)->ip_alloc_sem);
- mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
- (unsigned long long)iblock);
- ret = -EIO;
- goto bail;
- }
- set_buffer_new(bh_result);
- up_write(&OCFS2_I(inode)->ip_alloc_sem);
- }
-
- /*
- * get_more_blocks() expects us to describe a hole by clearing
- * the mapped bit on bh_result().
- *
- * Consider an unwritten extent as a hole.
- */
- if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
- map_bh(bh_result, inode->i_sb, p_blkno);
- else
- clear_buffer_mapped(bh_result);
-
- /* make sure we don't map more than max_blocks blocks here as
- that's all the kernel will handle at this point. */
- if (max_blocks < contig_blocks)
- contig_blocks = max_blocks;
- bh_result->b_size = contig_blocks << blocksize_bits;
-bail:
- if (alloc_locked)
- ocfs2_inode_unlock(inode, 1);
- return ret;
-}
-
-/*
- * ocfs2_dio_end_io is called by the dio core when a dio is finished. We're
- * particularly interested in the aio/dio case. We use the rw_lock DLM lock
- * to protect io on one node from truncation on another.
- */
-static int ocfs2_dio_end_io(struct kiocb *iocb,
- loff_t offset,
- ssize_t bytes,
- void *private)
-{
- struct inode *inode = file_inode(iocb->ki_filp);
- int level;
-
- if (bytes <= 0)
- return 0;
-
- /* this io's submitter should not have unlocked this before we could */
- BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
-
- if (ocfs2_iocb_is_unaligned_aio(iocb)) {
- ocfs2_iocb_clear_unaligned_aio(iocb);
-
- mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
- }
-
- /* Let rw unlock to be done later to protect append direct io write */
- if (offset + bytes <= i_size_read(inode)) {
- ocfs2_iocb_clear_rw_locked(iocb);
-
- level = ocfs2_iocb_rw_locked_level(iocb);
- ocfs2_rw_unlock(inode, level);
- }
-
- return 0;
-}
-
static int ocfs2_releasepage(struct page *page, gfp_t wait)
{
if (!page_has_buffers(page))
@@ -658,363 +506,6 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
return try_to_free_buffers(page);
}
-static int ocfs2_is_overwrite(struct ocfs2_super *osb,
- struct inode *inode, loff_t offset)
-{
- int ret = 0;
- u32 v_cpos = 0;
- u32 p_cpos = 0;
- unsigned int num_clusters = 0;
- unsigned int ext_flags = 0;
-
- v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
- ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
- &num_clusters, &ext_flags);
- if (ret < 0) {
- mlog_errno(ret);
- return ret;
- }
-
- if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN))
- return 1;
-
- return 0;
-}
-
-static int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb,
- struct inode *inode, loff_t offset,
- u64 zero_len, int cluster_align)
-{
- u32 p_cpos = 0;
- u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
- unsigned int num_clusters = 0;
- unsigned int ext_flags = 0;
- int ret = 0;
-
- if (offset <= i_size_read(inode) || cluster_align)
- return 0;
-
- ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters,
- &ext_flags);
- if (ret < 0) {
- mlog_errno(ret);
- return ret;
- }
-
- if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
- u64 s = i_size_read(inode);
- sector_t sector = ((u64)p_cpos << (osb->s_clustersize_bits - 9)) +
- (do_div(s, osb->s_clustersize) >> 9);
-
- ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector,
- zero_len >> 9, GFP_NOFS, false);
- if (ret < 0)
- mlog_errno(ret);
- }
-
- return ret;
-}
-
-static int ocfs2_direct_IO_extend_no_holes(struct ocfs2_super *osb,
- struct inode *inode, loff_t offset)
-{
- u64 zero_start, zero_len, total_zero_len;
- u32 p_cpos = 0, clusters_to_add;
- u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
- unsigned int num_clusters = 0;
- unsigned int ext_flags = 0;
- u32 size_div, offset_div;
- int ret = 0;
-
- {
- u64 o = offset;
- u64 s = i_size_read(inode);
-
- offset_div = do_div(o, osb->s_clustersize);
- size_div = do_div(s, osb->s_clustersize);
- }
-
- if (offset <= i_size_read(inode))
- return 0;
-
- clusters_to_add = ocfs2_bytes_to_clusters(inode->i_sb, offset) -
- ocfs2_bytes_to_clusters(inode->i_sb, i_size_read(inode));
- total_zero_len = offset - i_size_read(inode);
- if (clusters_to_add)
- total_zero_len -= offset_div;
-
- /* Allocate clusters to fill out holes, and this is only needed
- * when we add more than one clusters. Otherwise the cluster will
- * be allocated during direct IO */
- if (clusters_to_add > 1) {
- ret = ocfs2_extend_allocation(inode,
- OCFS2_I(inode)->ip_clusters,
- clusters_to_add - 1, 0);
- if (ret) {
- mlog_errno(ret);
- goto out;
- }
- }
-
- while (total_zero_len) {
- ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters,
- &ext_flags);
- if (ret < 0) {
- mlog_errno(ret);
- goto out;
- }
-
- zero_start = ocfs2_clusters_to_bytes(osb->sb, p_cpos) +
- size_div;
- zero_len = ocfs2_clusters_to_bytes(osb->sb, num_clusters) -
- size_div;
- zero_len = min(total_zero_len, zero_len);
-
- if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
- ret = blkdev_issue_zeroout(osb->sb->s_bdev,
- zero_start >> 9, zero_len >> 9,
- GFP_NOFS, false);
- if (ret < 0) {
- mlog_errno(ret);
- goto out;
- }
- }
-
- total_zero_len -= zero_len;
- v_cpos += ocfs2_bytes_to_clusters(osb->sb, zero_len + size_div);
-
- /* Only at first iteration can be cluster not aligned.
- * So set size_div to 0 for the rest */
- size_div = 0;
- }
-
-out:
- return ret;
-}
-
-static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
- struct iov_iter *iter,
- loff_t offset)
-{
- ssize_t ret = 0;
- ssize_t written = 0;
- bool orphaned = false;
- int is_overwrite = 0;
- struct file *file = iocb->ki_filp;
- struct inode *inode = file_inode(file)->i_mapping->host;
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- struct buffer_head *di_bh = NULL;
- size_t count = iter->count;
- journal_t *journal = osb->journal->j_journal;
- u64 zero_len_head, zero_len_tail;
- int cluster_align_head, cluster_align_tail;
- loff_t final_size = offset + count;
- int append_write = offset >= i_size_read(inode) ? 1 : 0;
- unsigned int num_clusters = 0;
- unsigned int ext_flags = 0;
-
- {
- u64 o = offset;
- u64 s = i_size_read(inode);
-
- zero_len_head = do_div(o, 1 << osb->s_clustersize_bits);
- cluster_align_head = !zero_len_head;
-
- zero_len_tail = osb->s_clustersize -
- do_div(s, osb->s_clustersize);
- if ((offset - i_size_read(inode)) < zero_len_tail)
- zero_len_tail = offset - i_size_read(inode);
- cluster_align_tail = !zero_len_tail;
- }
-
- /*
- * when final_size > inode->i_size, inode->i_size will be
- * updated after direct write, so add the inode to orphan
- * dir first.
- */
- if (final_size > i_size_read(inode)) {
- ret = ocfs2_add_inode_to_orphan(osb, inode);
- if (ret < 0) {
- mlog_errno(ret);
- goto out;
- }
- orphaned = true;
- }
-
- if (append_write) {
- ret = ocfs2_inode_lock(inode, NULL, 1);
- if (ret < 0) {
- mlog_errno(ret);
- goto clean_orphan;
- }
-
- /* zeroing out the previously allocated cluster tail
- * that but not zeroed */
- if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) {
- down_read(&OCFS2_I(inode)->ip_alloc_sem);
- ret = ocfs2_direct_IO_zero_extend(osb, inode, offset,
- zero_len_tail, cluster_align_tail);
- up_read(&OCFS2_I(inode)->ip_alloc_sem);
- } else {
- down_write(&OCFS2_I(inode)->ip_alloc_sem);
- ret = ocfs2_direct_IO_extend_no_holes(osb, inode,
- offset);
- up_write(&OCFS2_I(inode)->ip_alloc_sem);
- }
- if (ret < 0) {
- mlog_errno(ret);
- ocfs2_inode_unlock(inode, 1);
- goto clean_orphan;
- }
-
- is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
- if (is_overwrite < 0) {
- mlog_errno(is_overwrite);
- ret = is_overwrite;
- ocfs2_inode_unlock(inode, 1);
- goto clean_orphan;
- }
-
- ocfs2_inode_unlock(inode, 1);
- }
-
- written = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
- offset, ocfs2_direct_IO_get_blocks,
- ocfs2_dio_end_io, NULL, 0);
- /* overwrite aio may return -EIOCBQUEUED, and it is not an error */
- if ((written < 0) && (written != -EIOCBQUEUED)) {
- loff_t i_size = i_size_read(inode);
-
- if (offset + count > i_size) {
- ret = ocfs2_inode_lock(inode, &di_bh, 1);
- if (ret < 0) {
- mlog_errno(ret);
- goto clean_orphan;
- }
-
- if (i_size == i_size_read(inode)) {
- ret = ocfs2_truncate_file(inode, di_bh,
- i_size);
- if (ret < 0) {
- if (ret != -ENOSPC)
- mlog_errno(ret);
-
- ocfs2_inode_unlock(inode, 1);
- brelse(di_bh);
- di_bh = NULL;
- goto clean_orphan;
- }
- }
-
- ocfs2_inode_unlock(inode, 1);
- brelse(di_bh);
- di_bh = NULL;
-
- ret = jbd2_journal_force_commit(journal);
- if (ret < 0)
- mlog_errno(ret);
- }
- } else if (written > 0 && append_write && !is_overwrite &&
- !cluster_align_head) {
- /* zeroing out the allocated cluster head */
- u32 p_cpos = 0;
- u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
-
- ret = ocfs2_inode_lock(inode, NULL, 0);
- if (ret < 0) {
- mlog_errno(ret);
- goto clean_orphan;
- }
-
- ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
- &num_clusters, &ext_flags);
- if (ret < 0) {
- mlog_errno(ret);
- ocfs2_inode_unlock(inode, 0);
- goto clean_orphan;
- }
-
- BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
-
- ret = blkdev_issue_zeroout(osb->sb->s_bdev,
- (u64)p_cpos << (osb->s_clustersize_bits - 9),
- zero_len_head >> 9, GFP_NOFS, false);
- if (ret < 0)
- mlog_errno(ret);
-
- ocfs2_inode_unlock(inode, 0);
- }
-
-clean_orphan:
- if (orphaned) {
- int tmp_ret;
- int update_isize = written > 0 ? 1 : 0;
- loff_t end = update_isize ? offset + written : 0;
-
- tmp_ret = ocfs2_inode_lock(inode, &di_bh, 1);
- if (tmp_ret < 0) {
- ret = tmp_ret;
- mlog_errno(ret);
- goto out;
- }
-
- tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
- update_isize, end);
- if (tmp_ret < 0) {
- ocfs2_inode_unlock(inode, 1);
- ret = tmp_ret;
- mlog_errno(ret);
- brelse(di_bh);
- goto out;
- }
-
- ocfs2_inode_unlock(inode, 1);
- brelse(di_bh);
-
- tmp_ret = jbd2_journal_force_commit(journal);
- if (tmp_ret < 0) {
- ret = tmp_ret;
- mlog_errno(tmp_ret);
- }
- }
-
-out:
- if (ret >= 0)
- ret = written;
- return ret;
-}
-
-static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
-{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file_inode(file)->i_mapping->host;
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- int full_coherency = !(osb->s_mount_opt &
- OCFS2_MOUNT_COHERENCY_BUFFERED);
-
- /*
- * Fallback to buffered I/O if we see an inode without
- * extents.
- */
- if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
- return 0;
-
- /* Fallback to buffered I/O if we are appending and
- * concurrent O_DIRECT writes are allowed.
- */
- if (i_size_read(inode) <= offset && !full_coherency)
- return 0;
-
- if (iov_iter_rw(iter) == READ)
- return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
- iter, offset,
- ocfs2_direct_IO_get_blocks,
- ocfs2_dio_end_io, NULL, 0);
- else
- return ocfs2_direct_IO_write(iocb, iter, offset);
-}
-
static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
u32 cpos,
unsigned int *start,
@@ -1201,6 +692,13 @@ next_bh:
#define OCFS2_MAX_CLUSTERS_PER_PAGE (PAGE_CACHE_SIZE / OCFS2_MIN_CLUSTERSIZE)
+struct ocfs2_unwritten_extent {
+ struct list_head ue_node;
+ struct list_head ue_ip_node;
+ u32 ue_cpos;
+ u32 ue_phys;
+};
+
/*
* Describe the state of a single cluster to be written to.
*/
@@ -1212,7 +710,7 @@ struct ocfs2_write_cluster_desc {
* filled.
*/
unsigned c_new;
- unsigned c_unwritten;
+ unsigned c_clear_unwritten;
unsigned c_needs_zero;
};
@@ -1224,6 +722,9 @@ struct ocfs2_write_ctxt {
/* First cluster allocated in a nonsparse extend */
u32 w_first_new_cpos;
+ /* Type of caller. Must be one of buffer, mmap, direct. */
+ ocfs2_write_type_t w_type;
+
struct ocfs2_write_cluster_desc w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE];
/*
@@ -1272,6 +773,8 @@ struct ocfs2_write_ctxt {
struct buffer_head *w_di_bh;
struct ocfs2_cached_dealloc_ctxt w_dealloc;
+
+ struct list_head w_unwritten_list;
};
void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
@@ -1310,8 +813,25 @@ static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
}
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_free_unwritten_list(struct inode *inode,
+ struct list_head *head)
{
+ struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ struct ocfs2_unwritten_extent *ue = NULL, *tmp = NULL;
+
+ list_for_each_entry_safe(ue, tmp, head, ue_node) {
+ list_del(&ue->ue_node);
+ spin_lock(&oi->ip_lock);
+ list_del(&ue->ue_ip_node);
+ spin_unlock(&oi->ip_lock);
+ kfree(ue);
+ }
+}
+
+static void ocfs2_free_write_ctxt(struct inode *inode,
+ struct ocfs2_write_ctxt *wc)
+{
+ ocfs2_free_unwritten_list(inode, &wc->w_unwritten_list);
ocfs2_unlock_pages(wc);
brelse(wc->w_di_bh);
kfree(wc);
@@ -1319,7 +839,8 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
struct ocfs2_super *osb, loff_t pos,
- unsigned len, struct buffer_head *di_bh)
+ unsigned len, ocfs2_write_type_t type,
+ struct buffer_head *di_bh)
{
u32 cend;
struct ocfs2_write_ctxt *wc;
@@ -1334,6 +855,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
wc->w_clen = cend - wc->w_cpos + 1;
get_bh(di_bh);
wc->w_di_bh = di_bh;
+ wc->w_type = type;
if (unlikely(PAGE_CACHE_SHIFT > osb->s_clustersize_bits))
wc->w_large_pages = 1;
@@ -1341,6 +863,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
wc->w_large_pages = 0;
ocfs2_init_dealloc_ctxt(&wc->w_dealloc);
+ INIT_LIST_HEAD(&wc->w_unwritten_list);
*wcp = wc;
@@ -1401,12 +924,13 @@ static void ocfs2_write_failure(struct inode *inode,
to = user_pos + user_len;
struct page *tmppage;
- ocfs2_zero_new_buffers(wc->w_target_page, from, to);
+ if (wc->w_target_page)
+ ocfs2_zero_new_buffers(wc->w_target_page, from, to);
for(i = 0; i < wc->w_num_pages; i++) {
tmppage = wc->w_pages[i];
- if (page_has_buffers(tmppage)) {
+ if (tmppage && page_has_buffers(tmppage)) {
if (ocfs2_should_order_data(inode))
ocfs2_jbd2_file_inode(wc->w_handle, inode);
@@ -1536,11 +1060,13 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
wc->w_num_pages = 1;
start = target_index;
}
+ end_index = (user_pos + user_len - 1) >> PAGE_CACHE_SHIFT;
for(i = 0; i < wc->w_num_pages; i++) {
index = start + i;
- if (index == target_index && mmap_page) {
+ if (index >= target_index && index <= end_index &&
+ wc->w_type == OCFS2_WRITE_MMAP) {
/*
* ocfs2_pagemkwrite() is a little different
* and wants us to directly use the page
@@ -1559,6 +1085,11 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
page_cache_get(mmap_page);
wc->w_pages[i] = mmap_page;
wc->w_target_locked = true;
+ } else if (index >= target_index && index <= end_index &&
+ wc->w_type == OCFS2_WRITE_DIRECT) {
+ /* Direct write has no mapping page. */
+ wc->w_pages[i] = NULL;
+ continue;
} else {
wc->w_pages[i] = find_or_create_page(mapping, index,
GFP_NOFS);
@@ -1583,19 +1114,20 @@ out:
* Prepare a single cluster for write one cluster into the file.
*/
static int ocfs2_write_cluster(struct address_space *mapping,
- u32 phys, unsigned int unwritten,
+ u32 *phys, unsigned int new,
+ unsigned int clear_unwritten,
unsigned int should_zero,
struct ocfs2_alloc_context *data_ac,
struct ocfs2_alloc_context *meta_ac,
struct ocfs2_write_ctxt *wc, u32 cpos,
loff_t user_pos, unsigned user_len)
{
- int ret, i, new;
- u64 v_blkno, p_blkno;
+ int ret, i;
+ u64 p_blkno;
struct inode *inode = mapping->host;
struct ocfs2_extent_tree et;
+ int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
- new = phys == 0 ? 1 : 0;
if (new) {
u32 tmp_pos;
@@ -1605,9 +1137,9 @@ static int ocfs2_write_cluster(struct address_space *mapping,
*/
tmp_pos = cpos;
ret = ocfs2_add_inode_data(OCFS2_SB(inode->i_sb), inode,
- &tmp_pos, 1, 0, wc->w_di_bh,
- wc->w_handle, data_ac,
- meta_ac, NULL);
+ &tmp_pos, 1, !clear_unwritten,
+ wc->w_di_bh, wc->w_handle,
+ data_ac, meta_ac, NULL);
/*
* This shouldn't happen because we must have already
* calculated the correct meta data allocation required. The
@@ -1624,11 +1156,11 @@ static int ocfs2_write_cluster(struct address_space *mapping,
mlog_errno(ret);
goto out;
}
- } else if (unwritten) {
+ } else if (clear_unwritten) {
ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode),
wc->w_di_bh);
ret = ocfs2_mark_extent_written(inode, &et,
- wc->w_handle, cpos, 1, phys,
+ wc->w_handle, cpos, 1, *phys,
meta_ac, &wc->w_dealloc);
if (ret < 0) {
mlog_errno(ret);
@@ -1636,30 +1168,33 @@ static int ocfs2_write_cluster(struct address_space *mapping,
}
}
- if (should_zero)
- v_blkno = ocfs2_clusters_to_blocks(inode->i_sb, cpos);
- else
- v_blkno = user_pos >> inode->i_sb->s_blocksize_bits;
-
/*
* The only reason this should fail is due to an inability to
* find the extent added.
*/
- ret = ocfs2_extent_map_get_blocks(inode, v_blkno, &p_blkno, NULL,
- NULL);
+ ret = ocfs2_get_clusters(inode, cpos, phys, NULL, NULL);
if (ret < 0) {
mlog(ML_ERROR, "Get physical blkno failed for inode %llu, "
- "at logical block %llu",
- (unsigned long long)OCFS2_I(inode)->ip_blkno,
- (unsigned long long)v_blkno);
+ "at logical cluster %u",
+ (unsigned long long)OCFS2_I(inode)->ip_blkno, cpos);
goto out;
}
- BUG_ON(p_blkno == 0);
+ BUG_ON(*phys == 0);
+
+ p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *phys);
+ if (!should_zero)
+ p_blkno += (user_pos >> inode->i_sb->s_blocksize_bits) & (u64)(bpc - 1);
for(i = 0; i < wc->w_num_pages; i++) {
int tmpret;
+ /* This is the direct io target page. */
+ if (wc->w_pages[i] == NULL) {
+ p_blkno++;
+ continue;
+ }
+
tmpret = ocfs2_prepare_page_for_write(inode, &p_blkno, wc,
wc->w_pages[i], cpos,
user_pos, user_len,
@@ -1706,8 +1241,9 @@ static int ocfs2_write_cluster_by_desc(struct address_space *mapping,
if ((cluster_off + local_len) > osb->s_clustersize)
local_len = osb->s_clustersize - cluster_off;
- ret = ocfs2_write_cluster(mapping, desc->c_phys,
- desc->c_unwritten,
+ ret = ocfs2_write_cluster(mapping, &desc->c_phys,
+ desc->c_new,
+ desc->c_clear_unwritten,
desc->c_needs_zero,
data_ac, meta_ac,
wc, desc->c_cpos, pos, local_len);
@@ -1778,6 +1314,66 @@ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb,
}
/*
+ * Check if this extent is marked UNWRITTEN by direct io. If so, we need not to
+ * do the zero work. And should not to clear UNWRITTEN since it will be cleared
+ * by the direct io procedure.
+ * If this is a new extent that allocated by direct io, we should mark it in
+ * the ip_unwritten_list.
+ */
+static int ocfs2_unwritten_check(struct inode *inode,
+ struct ocfs2_write_ctxt *wc,
+ struct ocfs2_write_cluster_desc *desc)
+{
+ struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ struct ocfs2_unwritten_extent *ue = NULL, *new = NULL;
+ int ret = 0;
+
+ if (!desc->c_needs_zero)
+ return 0;
+
+retry:
+ spin_lock(&oi->ip_lock);
+ /* Needs not to zero no metter buffer or direct. The one who is zero
+ * the cluster is doing zero. And he will clear unwritten after all
+ * cluster io finished. */
+ list_for_each_entry(ue, &oi->ip_unwritten_list, ue_ip_node) {
+ if (desc->c_cpos == ue->ue_cpos) {
+ BUG_ON(desc->c_new);
+ desc->c_needs_zero = 0;
+ desc->c_clear_unwritten = 0;
+ goto unlock;
+ }
+ }
+
+ if (wc->w_type != OCFS2_WRITE_DIRECT)
+ goto unlock;
+
+ if (new == NULL) {
+ spin_unlock(&oi->ip_lock);
+ new = kmalloc(sizeof(struct ocfs2_unwritten_extent),
+ GFP_NOFS);
+ if (new == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ goto retry;
+ }
+ /* This direct write will doing zero. */
+ new->ue_cpos = desc->c_cpos;
+ new->ue_phys = desc->c_phys;
+ desc->c_clear_unwritten = 0;
+ list_add_tail(&new->ue_ip_node, &oi->ip_unwritten_list);
+ list_add_tail(&new->ue_node, &wc->w_unwritten_list);
+ new = NULL;
+unlock:
+ spin_unlock(&oi->ip_lock);
+out:
+ if (new)
+ kfree(new);
+ return ret;
+}
+
+/*
* Populate each single-cluster write descriptor in the write context
* with information about the i/o to be done.
*
@@ -1852,14 +1448,21 @@ static int ocfs2_populate_write_desc(struct inode *inode,
if (phys == 0) {
desc->c_new = 1;
desc->c_needs_zero = 1;
+ desc->c_clear_unwritten = 1;
*clusters_to_alloc = *clusters_to_alloc + 1;
}
if (ext_flags & OCFS2_EXT_UNWRITTEN) {
- desc->c_unwritten = 1;
+ desc->c_clear_unwritten = 1;
desc->c_needs_zero = 1;
}
+ ret = ocfs2_unwritten_check(inode, wc, desc);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
num_clusters--;
}
@@ -2022,8 +1625,10 @@ static int ocfs2_expand_nonsparse_inode(struct inode *inode,
if (ret)
mlog_errno(ret);
- wc->w_first_new_cpos =
- ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
+ /* There is no wc if this is call from direct. */
+ if (wc)
+ wc->w_first_new_cpos =
+ ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
return ret;
}
@@ -2077,9 +1682,8 @@ out:
return ret;
}
-int ocfs2_write_begin_nolock(struct file *filp,
- struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
+int ocfs2_write_begin_nolock(struct address_space *mapping,
+ loff_t pos, unsigned len, ocfs2_write_type_t type,
struct page **pagep, void **fsdata,
struct buffer_head *di_bh, struct page *mmap_page)
{
@@ -2096,7 +1700,7 @@ int ocfs2_write_begin_nolock(struct file *filp,
int try_free = 1, ret1;
try_again:
- ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, di_bh);
+ ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, type, di_bh);
if (ret) {
mlog_errno(ret);
return ret;
@@ -2115,14 +1719,17 @@ try_again:
}
}
- if (ocfs2_sparse_alloc(osb))
- ret = ocfs2_zero_tail(inode, di_bh, pos);
- else
- ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, len,
- wc);
- if (ret) {
- mlog_errno(ret);
- goto out;
+ /* Direct io change i_size late, should not zero tail here. */
+ if (type != OCFS2_WRITE_DIRECT) {
+ if (ocfs2_sparse_alloc(osb))
+ ret = ocfs2_zero_tail(inode, di_bh, pos);
+ else
+ ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
+ len, wc);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
}
ret = ocfs2_check_range_for_refcount(inode, pos, len);
@@ -2153,7 +1760,7 @@ try_again:
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(long long)i_size_read(inode),
le32_to_cpu(di->i_clusters),
- pos, len, flags, mmap_page,
+ pos, len, type, mmap_page,
clusters_to_alloc, extents_to_split);
/*
@@ -2183,17 +1790,17 @@ try_again:
credits = ocfs2_calc_extend_credits(inode->i_sb,
&di->id2.i_list);
-
- }
+ } else if (type == OCFS2_WRITE_DIRECT)
+ /* direct write needs not to start trans if no extents alloc. */
+ goto success;
/*
* We have to zero sparse allocated clusters, unwritten extent clusters,
* and non-sparse clusters we just extended. For non-sparse writes,
* we know zeros will only be needed in the first and/or last cluster.
*/
- if (clusters_to_alloc || extents_to_split ||
- (wc->w_clen && (wc->w_desc[0].c_needs_zero ||
- wc->w_desc[wc->w_clen - 1].c_needs_zero)))
+ if (wc->w_clen && (wc->w_desc[0].c_needs_zero ||
+ wc->w_desc[wc->w_clen - 1].c_needs_zero))
cluster_of_pages = 1;
else
cluster_of_pages = 0;
@@ -2260,7 +1867,8 @@ try_again:
ocfs2_free_alloc_context(meta_ac);
success:
- *pagep = wc->w_target_page;
+ if (pagep)
+ *pagep = wc->w_target_page;
*fsdata = wc;
return 0;
out_quota:
@@ -2271,7 +1879,7 @@ out_commit:
ocfs2_commit_trans(osb, handle);
out:
- ocfs2_free_write_ctxt(wc);
+ ocfs2_free_write_ctxt(inode, wc);
if (data_ac) {
ocfs2_free_alloc_context(data_ac);
@@ -2323,8 +1931,8 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
*/
down_write(&OCFS2_I(inode)->ip_alloc_sem);
- ret = ocfs2_write_begin_nolock(file, mapping, pos, len, flags, pagep,
- fsdata, di_bh, NULL);
+ ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_BUFFER,
+ pagep, fsdata, di_bh, NULL);
if (ret) {
mlog_errno(ret);
goto out_fail;
@@ -2381,12 +1989,16 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
handle_t *handle = wc->w_handle;
struct page *tmppage;
- ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
- if (ret) {
- copied = ret;
- mlog_errno(ret);
- goto out;
+ BUG_ON(!list_empty(&wc->w_unwritten_list));
+
+ if (handle) {
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
+ wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret) {
+ copied = ret;
+ mlog_errno(ret);
+ goto out;
+ }
}
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
@@ -2394,18 +2006,23 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
goto out_write_size;
}
- if (unlikely(copied < len)) {
+ if (unlikely(copied < len) && wc->w_target_page) {
if (!PageUptodate(wc->w_target_page))
copied = 0;
ocfs2_zero_new_buffers(wc->w_target_page, start+copied,
start+len);
}
- flush_dcache_page(wc->w_target_page);
+ if (wc->w_target_page)
+ flush_dcache_page(wc->w_target_page);
for(i = 0; i < wc->w_num_pages; i++) {
tmppage = wc->w_pages[i];
+ /* This is the direct io target page. */
+ if (tmppage == NULL)
+ continue;
+
if (tmppage == wc->w_target_page) {
from = wc->w_target_from;
to = wc->w_target_to;
@@ -2424,25 +2041,29 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
}
if (page_has_buffers(tmppage)) {
- if (ocfs2_should_order_data(inode))
- ocfs2_jbd2_file_inode(wc->w_handle, inode);
+ if (handle && ocfs2_should_order_data(inode))
+ ocfs2_jbd2_file_inode(handle, inode);
block_commit_write(tmppage, from, to);
}
}
out_write_size:
- pos += copied;
- if (pos > i_size_read(inode)) {
- i_size_write(inode, pos);
- mark_inode_dirty(inode);
- }
- inode->i_blocks = ocfs2_inode_sector_count(inode);
- di->i_size = cpu_to_le64((u64)i_size_read(inode));
- inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
- di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
- ocfs2_update_inode_fsync_trans(handle, inode, 1);
- ocfs2_journal_dirty(handle, wc->w_di_bh);
+ /* Direct io do not update i_size here. */
+ if (wc->w_type != OCFS2_WRITE_DIRECT) {
+ pos += copied;
+ if (pos > i_size_read(inode)) {
+ i_size_write(inode, pos);
+ mark_inode_dirty(inode);
+ }
+ inode->i_blocks = ocfs2_inode_sector_count(inode);
+ di->i_size = cpu_to_le64((u64)i_size_read(inode));
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+ di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+ ocfs2_update_inode_fsync_trans(handle, inode, 1);
+ }
+ if (handle)
+ ocfs2_journal_dirty(handle, wc->w_di_bh);
out:
/* unlock pages before dealloc since it needs acquiring j_trans_barrier
@@ -2452,7 +2073,8 @@ out:
*/
ocfs2_unlock_pages(wc);
- ocfs2_commit_trans(osb, handle);
+ if (handle)
+ ocfs2_commit_trans(osb, handle);
ocfs2_run_deallocs(osb, &wc->w_dealloc);
@@ -2477,6 +2099,360 @@ static int ocfs2_write_end(struct file *file, struct address_space *mapping,
return ret;
}
+struct ocfs2_dio_write_ctxt {
+ struct list_head dw_zero_list;
+ unsigned dw_zero_count;
+ int dw_orphaned;
+ pid_t dw_writer_pid;
+};
+
+static struct ocfs2_dio_write_ctxt *
+ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc)
+{
+ struct ocfs2_dio_write_ctxt *dwc = NULL;
+
+ if (bh->b_private)
+ return bh->b_private;
+
+ dwc = kmalloc(sizeof(struct ocfs2_dio_write_ctxt), GFP_NOFS);
+ if (dwc == NULL)
+ return NULL;
+ INIT_LIST_HEAD(&dwc->dw_zero_list);
+ dwc->dw_zero_count = 0;
+ dwc->dw_orphaned = 0;
+ dwc->dw_writer_pid = task_pid_nr(current);
+ bh->b_private = dwc;
+ *alloc = 1;
+
+ return dwc;
+}
+
+static void ocfs2_dio_free_write_ctx(struct inode *inode,
+ struct ocfs2_dio_write_ctxt *dwc)
+{
+ ocfs2_free_unwritten_list(inode, &dwc->dw_zero_list);
+ kfree(dwc);
+}
+
+/*
+ * TODO: Make this into a generic get_blocks function.
+ *
+ * From do_direct_io in direct-io.c:
+ * "So what we do is to permit the ->get_blocks function to populate
+ * bh.b_size with the size of IO which is permitted at this offset and
+ * this i_blkbits."
+ *
+ * This function is called directly from get_more_blocks in direct-io.c.
+ *
+ * called like this: dio->get_blocks(dio->inode, fs_startblk,
+ * fs_count, map_bh, dio->rw == WRITE);
+ */
+static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ struct ocfs2_write_ctxt *wc;
+ struct ocfs2_write_cluster_desc *desc = NULL;
+ struct ocfs2_dio_write_ctxt *dwc = NULL;
+ struct buffer_head *di_bh = NULL;
+ u64 p_blkno;
+ loff_t pos = iblock << inode->i_sb->s_blocksize_bits;
+ unsigned len, total_len = bh_result->b_size;
+ int ret = 0, first_get_block = 0;
+
+ len = osb->s_clustersize - (pos & (osb->s_clustersize - 1));
+ len = min(total_len, len);
+
+ mlog(0, "get block of %lu at %llu:%u req %u\n",
+ inode->i_ino, pos, len, total_len);
+
+ /*
+ * Because we need to change file size in ocfs2_dio_end_io_write(), or
+ * we may need to add it to orphan dir. So can not fall to fast path
+ * while file size will be changed.
+ */
+ if (pos + total_len <= i_size_read(inode)) {
+ down_read(&oi->ip_alloc_sem);
+ /* This is the fast path for re-write. */
+ ret = ocfs2_get_block(inode, iblock, bh_result, create);
+
+ up_read(&oi->ip_alloc_sem);
+
+ if (buffer_mapped(bh_result) &&
+ !buffer_new(bh_result) &&
+ ret == 0)
+ goto out;
+
+ /* Clear state set by ocfs2_get_block. */
+ bh_result->b_state = 0;
+ }
+
+ dwc = ocfs2_dio_alloc_write_ctx(bh_result, &first_get_block);
+ if (unlikely(dwc == NULL)) {
+ ret = -ENOMEM;
+ mlog_errno(ret);
+ goto out;
+ }
+
+ if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) >
+ ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) &&
+ !dwc->dw_orphaned) {
+ /*
+ * when we are going to alloc extents beyond file size, add the
+ * inode to orphan dir, so we can recall those spaces when
+ * system crashed during write.
+ */
+ ret = ocfs2_add_inode_to_orphan(osb, inode);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto out;
+ }
+ dwc->dw_orphaned = 1;
+ }
+
+ ret = ocfs2_inode_lock(inode, &di_bh, 1);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ down_write(&oi->ip_alloc_sem);
+
+ if (first_get_block) {
+ if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+ ret = ocfs2_zero_tail(inode, di_bh, pos);
+ else
+ ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
+ total_len, NULL);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto unlock;
+ }
+ }
+
+ ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len,
+ OCFS2_WRITE_DIRECT, NULL,
+ (void **)&wc, di_bh, NULL);
+ if (ret) {
+ mlog_errno(ret);
+ goto unlock;
+ }
+
+ desc = &wc->w_desc[0];
+
+ p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys);
+ BUG_ON(p_blkno == 0);
+ p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1);
+
+ map_bh(bh_result, inode->i_sb, p_blkno);
+ bh_result->b_size = len;
+ if (desc->c_needs_zero)
+ set_buffer_new(bh_result);
+
+ /* May sleep in end_io. It should not happen in a irq context. So defer
+ * it to dio work queue. */
+ set_buffer_defer_completion(bh_result);
+
+ if (!list_empty(&wc->w_unwritten_list)) {
+ struct ocfs2_unwritten_extent *ue = NULL;
+
+ ue = list_first_entry(&wc->w_unwritten_list,
+ struct ocfs2_unwritten_extent,
+ ue_node);
+ BUG_ON(ue->ue_cpos != desc->c_cpos);
+ /* The physical address may be 0, fill it. */
+ ue->ue_phys = desc->c_phys;
+
+ list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list);
+ dwc->dw_zero_count++;
+ }
+
+ ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, NULL, wc);
+ BUG_ON(ret != len);
+ ret = 0;
+unlock:
+ up_write(&oi->ip_alloc_sem);
+ ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
+out:
+ if (ret < 0)
+ ret = -EIO;
+ return ret;
+}
+
+static void ocfs2_dio_end_io_write(struct inode *inode,
+ struct ocfs2_dio_write_ctxt *dwc,
+ loff_t offset,
+ ssize_t bytes)
+{
+ struct ocfs2_cached_dealloc_ctxt dealloc;
+ struct ocfs2_extent_tree et;
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ struct ocfs2_unwritten_extent *ue = NULL;
+ struct buffer_head *di_bh = NULL;
+ struct ocfs2_dinode *di;
+ struct ocfs2_alloc_context *data_ac = NULL;
+ struct ocfs2_alloc_context *meta_ac = NULL;
+ handle_t *handle = NULL;
+ loff_t end = offset + bytes;
+ int ret = 0, credits = 0, locked = 0;
+
+ ocfs2_init_dealloc_ctxt(&dealloc);
+
+ /* We do clear unwritten, delete orphan, change i_size here. If neither
+ * of these happen, we can skip all this. */
+ if (list_empty(&dwc->dw_zero_list) &&
+ end <= i_size_read(inode) &&
+ !dwc->dw_orphaned)
+ goto out;
+
+ /* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
+ * are in that context. */
+ if (dwc->dw_writer_pid != task_pid_nr(current)) {
+ mutex_lock(&inode->i_mutex);
+ locked = 1;
+ }
+
+ ret = ocfs2_inode_lock(inode, &di_bh, 1);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ down_write(&oi->ip_alloc_sem);
+
+ /* Delete orphan before acquire i_mutex. */
+ if (dwc->dw_orphaned) {
+ BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));
+
+ end = end > i_size_read(inode) ? end : 0;
+
+ ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
+ !!end, end);
+ if (ret < 0)
+ mlog_errno(ret);
+ }
+
+ di = (struct ocfs2_dinode *)di_bh;
+
+ ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
+
+ ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2,
+ &data_ac, &meta_ac);
+ if (ret) {
+ mlog_errno(ret);
+ goto unlock;
+ }
+
+ credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list);
+
+ handle = ocfs2_start_trans(osb, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ mlog_errno(ret);
+ goto unlock;
+ }
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret) {
+ mlog_errno(ret);
+ goto commit;
+ }
+
+ list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) {
+ ret = ocfs2_mark_extent_written(inode, &et, handle,
+ ue->ue_cpos, 1,
+ ue->ue_phys,
+ meta_ac, &dealloc);
+ if (ret < 0) {
+ mlog_errno(ret);
+ break;
+ }
+ }
+
+ if (end > i_size_read(inode)) {
+ ret = ocfs2_set_inode_size(handle, inode, di_bh, end);
+ if (ret < 0)
+ mlog_errno(ret);
+ }
+commit:
+ ocfs2_commit_trans(osb, handle);
+unlock:
+ up_write(&oi->ip_alloc_sem);
+ ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
+out:
+ if (data_ac)
+ ocfs2_free_alloc_context(data_ac);
+ if (meta_ac)
+ ocfs2_free_alloc_context(meta_ac);
+ ocfs2_run_deallocs(osb, &dealloc);
+ if (locked)
+ mutex_unlock(&inode->i_mutex);
+ ocfs2_dio_free_write_ctx(inode, dwc);
+}
+
+/*
+ * ocfs2_dio_end_io is called by the dio core when a dio is finished. We're
+ * particularly interested in the aio/dio case. We use the rw_lock DLM lock
+ * to protect io on one node from truncation on another.
+ */
+static int ocfs2_dio_end_io(struct kiocb *iocb,
+ loff_t offset,
+ ssize_t bytes,
+ void *private)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+ int level;
+
+ if (bytes <= 0)
+ return 0;
+
+ /* this io's submitter should not have unlocked this before we could */
+ BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
+
+ if (private)
+ ocfs2_dio_end_io_write(inode, private, offset, bytes);
+
+ ocfs2_iocb_clear_rw_locked(iocb);
+
+ level = ocfs2_iocb_rw_locked_level(iocb);
+ ocfs2_rw_unlock(inode, level);
+ return 0;
+}
+
+static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+ loff_t offset)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file)->i_mapping->host;
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ loff_t end = offset + iter->count;
+ get_block_t *get_block;
+
+ /*
+ * Fallback to buffered I/O if we see an inode without
+ * extents.
+ */
+ if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+ return 0;
+
+ /* Fallback to buffered I/O if we do not support append dio. */
+ if (end > i_size_read(inode) && !ocfs2_supports_append_dio(osb))
+ return 0;
+
+ if (iov_iter_rw(iter) == READ)
+ get_block = ocfs2_get_block;
+ else
+ get_block = ocfs2_dio_get_block;
+
+ return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+ iter, offset, get_block,
+ ocfs2_dio_end_io, NULL, 0);
+}
+
const struct address_space_operations ocfs2_aops = {
.readpage = ocfs2_readpage,
.readpages = ocfs2_readpages,
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 24e496d6bdcd..b1c9f28a57b1 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -47,9 +47,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
-int ocfs2_write_begin_nolock(struct file *filp,
- struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
+typedef enum {
+ OCFS2_WRITE_BUFFER = 0,
+ OCFS2_WRITE_DIRECT,
+ OCFS2_WRITE_MMAP,
+} ocfs2_write_type_t;
+
+int ocfs2_write_begin_nolock(struct address_space *mapping,
+ loff_t pos, unsigned len, ocfs2_write_type_t type,
struct page **pagep, void **fsdata,
struct buffer_head *di_bh, struct page *mmap_page);
@@ -79,7 +84,6 @@ static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
enum ocfs2_iocb_lock_bits {
OCFS2_IOCB_RW_LOCK = 0,
OCFS2_IOCB_RW_LOCK_LEVEL,
- OCFS2_IOCB_UNALIGNED_IO,
OCFS2_IOCB_NUM_LOCKS
};
@@ -88,11 +92,4 @@ enum ocfs2_iocb_lock_bits {
#define ocfs2_iocb_rw_locked_level(iocb) \
test_bit(OCFS2_IOCB_RW_LOCK_LEVEL, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_set_unaligned_aio(iocb) \
- set_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_clear_unaligned_aio(iocb) \
- clear_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_is_unaligned_aio(iocb) \
- test_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
-
#endif /* OCFS2_FILE_H */
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index ef6a2ec494de..bd15929b5f92 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1444,8 +1444,8 @@ static void o2hb_region_release(struct config_item *item)
debugfs_remove(reg->hr_debug_dir);
kfree(reg->hr_db_livenodes);
kfree(reg->hr_db_regnum);
- kfree(reg->hr_debug_elapsed_time);
- kfree(reg->hr_debug_pinned);
+ kfree(reg->hr_db_elapsed_time);
+ kfree(reg->hr_db_pinned);
spin_lock(&o2hb_live_lock);
list_del(&reg->hr_all_item);
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index e36d63ff1783..cdeafb4e7ed6 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -212,6 +212,12 @@ grant:
if (lock->lksb->flags & DLM_LKSB_PUT_LVB)
memcpy(res->lvb, lock->lksb->lvb, DLM_LVB_LEN);
+ /*
+ * Move the lock to the tail because it may be the only lock which has
+ * an invalid lvb.
+ */
+ list_move_tail(&lock->list, &res->granted);
+
status = DLM_NORMAL;
*call_ast = 1;
goto unlock_exit;
@@ -262,6 +268,7 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
struct dlm_lock *lock, int flags, int type)
{
enum dlm_status status;
+ u8 old_owner = res->owner;
mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type,
lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS);
@@ -287,6 +294,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
status = DLM_DENIED;
goto bail;
}
+
+ if (lock->ml.type == type && lock->ml.convert_type == LKM_IVMODE) {
+ mlog(0, "last convert request returned DLM_RECOVERING, but "
+ "owner has already queued and sent ast to me. res %.*s, "
+ "(cookie=%u:%llu, type=%d, conv=%d)\n",
+ res->lockname.len, res->lockname.name,
+ dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
+ dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
+ lock->ml.type, lock->ml.convert_type);
+ status = DLM_NORMAL;
+ goto bail;
+ }
+
res->state |= DLM_LOCK_RES_IN_PROGRESS;
/* move lock to local convert queue */
/* do not alter lock refcount. switching lists. */
@@ -316,11 +336,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
spin_lock(&res->spinlock);
res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
lock->convert_pending = 0;
- /* if it failed, move it back to granted queue */
+ /* if it failed, move it back to granted queue.
+ * if master returns DLM_NORMAL and then down before sending ast,
+ * it may have already been moved to granted queue, reset to
+ * DLM_RECOVERING and retry convert */
if (status != DLM_NORMAL) {
if (status != DLM_NOTQUEUED)
dlm_error(status);
dlm_revert_pending_convert(res, lock);
+ } else if ((res->state & DLM_LOCK_RES_RECOVERING) ||
+ (old_owner != res->owner)) {
+ mlog(0, "res %.*s is in recovering or has been recovered.\n",
+ res->lockname.len, res->lockname.name);
+ status = DLM_RECOVERING;
}
bail:
spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index cd38488a10fc..f6b313898763 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2083,7 +2083,6 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm,
dlm_lock_get(lock);
if (lock->convert_pending) {
/* move converting lock back to granted */
- BUG_ON(i != DLM_CONVERTING_LIST);
mlog(0, "node died with convert pending "
"on %.*s. move back to granted list.\n",
res->lockname.len, res->lockname.name);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 7cb38fdca229..c18ab45f8d21 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1381,44 +1381,6 @@ out:
return ret;
}
-/*
- * Will look for holes and unwritten extents in the range starting at
- * pos for count bytes (inclusive).
- */
-static int ocfs2_check_range_for_holes(struct inode *inode, loff_t pos,
- size_t count)
-{
- int ret = 0;
- unsigned int extent_flags;
- u32 cpos, clusters, extent_len, phys_cpos;
- struct super_block *sb = inode->i_sb;
-
- cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits;
- clusters = ocfs2_clusters_for_bytes(sb, pos + count) - cpos;
-
- while (clusters) {
- ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &extent_len,
- &extent_flags);
- if (ret < 0) {
- mlog_errno(ret);
- goto out;
- }
-
- if (phys_cpos == 0 || (extent_flags & OCFS2_EXT_UNWRITTEN)) {
- ret = 1;
- break;
- }
-
- if (extent_len > clusters)
- extent_len = clusters;
-
- clusters -= extent_len;
- cpos += extent_len;
- }
-out:
- return ret;
-}
-
static int ocfs2_write_remove_suid(struct inode *inode)
{
int ret;
@@ -2129,18 +2091,12 @@ out:
static int ocfs2_prepare_inode_for_write(struct file *file,
loff_t pos,
- size_t count,
- int appending,
- int *direct_io,
- int *has_refcount)
+ size_t count)
{
int ret = 0, meta_level = 0;
struct dentry *dentry = file->f_path.dentry;
struct inode *inode = d_inode(dentry);
loff_t end;
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- int full_coherency = !(osb->s_mount_opt &
- OCFS2_MOUNT_COHERENCY_BUFFERED);
/*
* We start with a read level meta lock and only jump to an ex
@@ -2189,10 +2145,6 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
pos,
count,
&meta_level);
- if (has_refcount)
- *has_refcount = 1;
- if (direct_io)
- *direct_io = 0;
}
if (ret < 0) {
@@ -2200,67 +2152,12 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
goto out_unlock;
}
- /*
- * Skip the O_DIRECT checks if we don't need
- * them.
- */
- if (!direct_io || !(*direct_io))
- break;
-
- /*
- * There's no sane way to do direct writes to an inode
- * with inline data.
- */
- if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
- *direct_io = 0;
- break;
- }
-
- /*
- * Allowing concurrent direct writes means
- * i_size changes wouldn't be synchronized, so
- * one node could wind up truncating another
- * nodes writes.
- */
- if (end > i_size_read(inode) && !full_coherency) {
- *direct_io = 0;
- break;
- }
-
- /*
- * Fallback to old way if the feature bit is not set.
- */
- if (end > i_size_read(inode) &&
- !ocfs2_supports_append_dio(osb)) {
- *direct_io = 0;
- break;
- }
-
- /*
- * We don't fill holes during direct io, so
- * check for them here. If any are found, the
- * caller will have to retake some cluster
- * locks and initiate the io as buffered.
- */
- ret = ocfs2_check_range_for_holes(inode, pos, count);
- if (ret == 1) {
- /*
- * Fallback to old way if the feature bit is not set.
- * Otherwise try dio first and then complete the rest
- * request through buffer io.
- */
- if (!ocfs2_supports_append_dio(osb))
- *direct_io = 0;
- ret = 0;
- } else if (ret < 0)
- mlog_errno(ret);
break;
}
out_unlock:
trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno,
- pos, appending, count,
- direct_io, has_refcount);
+ pos, count);
if (meta_level >= 0)
ocfs2_inode_unlock(inode, meta_level);
@@ -2272,18 +2169,16 @@ out:
static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
struct iov_iter *from)
{
- int direct_io, appending, rw_level;
- int can_do_direct, has_refcount = 0;
+ int direct_io, rw_level;
ssize_t written = 0;
ssize_t ret;
- size_t count = iov_iter_count(from), orig_count;
+ size_t count = iov_iter_count(from);
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
int full_coherency = !(osb->s_mount_opt &
OCFS2_MOUNT_COHERENCY_BUFFERED);
- int unaligned_dio = 0;
- int dropped_dio = 0;
+ void *saved_ki_complete = NULL;
int append_write = ((iocb->ki_pos + count) >=
i_size_read(inode) ? 1 : 0);
@@ -2296,12 +2191,10 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
if (count == 0)
return 0;
- appending = iocb->ki_flags & IOCB_APPEND ? 1 : 0;
direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
inode_lock(inode);
-relock:
/*
* Concurrent O_DIRECT writes are allowed with
* mount_option "coherency=buffered".
@@ -2334,7 +2227,6 @@ relock:
ocfs2_inode_unlock(inode, 1);
}
- orig_count = iov_iter_count(from);
ret = generic_write_checks(iocb, from);
if (ret <= 0) {
if (ret)
@@ -2343,41 +2235,18 @@ relock:
}
count = ret;
- can_do_direct = direct_io;
- ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count, appending,
- &can_do_direct, &has_refcount);
+ ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count);
if (ret < 0) {
mlog_errno(ret);
goto out;
}
- if (direct_io && !is_sync_kiocb(iocb))
- unaligned_dio = ocfs2_is_io_unaligned(inode, count, iocb->ki_pos);
-
- /*
- * We can't complete the direct I/O as requested, fall back to
- * buffered I/O.
- */
- if (direct_io && !can_do_direct) {
- ocfs2_rw_unlock(inode, rw_level);
-
- rw_level = -1;
-
- direct_io = 0;
- iocb->ki_flags &= ~IOCB_DIRECT;
- iov_iter_reexpand(from, orig_count);
- dropped_dio = 1;
- goto relock;
- }
-
- if (unaligned_dio) {
+ if (direct_io && !is_sync_kiocb(iocb) &&
+ ocfs2_is_io_unaligned(inode, count, iocb->ki_pos)) {
/*
- * Wait on previous unaligned aio to complete before
- * proceeding.
+ * Make it a sync io if it's an unaligned aio.
*/
- mutex_lock(&OCFS2_I(inode)->ip_unaligned_aio);
- /* Mark the iocb as needing an unlock in ocfs2_dio_end_io */
- ocfs2_iocb_set_unaligned_aio(iocb);
+ saved_ki_complete = xchg(&iocb->ki_complete, NULL);
}
/* communicate with ocfs2_dio_end_io */
@@ -2398,14 +2267,13 @@ relock:
*/
if ((written == -EIOCBQUEUED) || (!ocfs2_iocb_is_rw_locked(iocb))) {
rw_level = -1;
- unaligned_dio = 0;
}
if (unlikely(written <= 0))
- goto no_sync;
+ goto out;
if (((file->f_flags & O_DSYNC) && !direct_io) ||
- IS_SYNC(inode) || dropped_dio) {
+ IS_SYNC(inode)) {
ret = filemap_fdatawrite_range(file->f_mapping,
iocb->ki_pos - written,
iocb->ki_pos - 1);
@@ -2424,13 +2292,10 @@ relock:
iocb->ki_pos - 1);
}
-no_sync:
- if (unaligned_dio && ocfs2_iocb_is_unaligned_aio(iocb)) {
- ocfs2_iocb_clear_unaligned_aio(iocb);
- mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
- }
-
out:
+ if (saved_ki_complete)
+ xchg(&iocb->ki_complete, saved_ki_complete);
+
if (rw_level != -1)
ocfs2_rw_unlock(inode, rw_level);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index ba495beff1c2..12f4a9e9800f 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1170,6 +1170,9 @@ static void ocfs2_clear_inode(struct inode *inode)
mlog_bug_on_msg(!list_empty(&oi->ip_io_markers),
"Clear inode of %llu, inode has io markers\n",
(unsigned long long)oi->ip_blkno);
+ mlog_bug_on_msg(!list_empty(&oi->ip_unwritten_list),
+ "Clear inode of %llu, inode has unwritten extents\n",
+ (unsigned long long)oi->ip_blkno);
ocfs2_extent_map_trunc(inode, 0);
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 01635e016b3e..d8f3fc8d2551 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -43,9 +43,6 @@ struct ocfs2_inode_info
/* protects extended attribute changes on this inode */
struct rw_semaphore ip_xattr_sem;
- /* Number of outstanding AIO's which are not page aligned */
- struct mutex ip_unaligned_aio;
-
/* These fields are protected by ip_lock */
spinlock_t ip_lock;
u32 ip_open_count;
@@ -57,6 +54,9 @@ struct ocfs2_inode_info
u32 ip_flags; /* see below */
u32 ip_attr; /* inode attributes */
+ /* Record unwritten extents during direct io. */
+ struct list_head ip_unwritten_list;
+
/* protected by recovery_lock. */
struct inode *ip_next_orphan;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 61b833b721d8..e607419cdfa4 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -231,7 +231,7 @@ void ocfs2_recovery_exit(struct ocfs2_super *osb)
/* At this point, we know that no more recovery threads can be
* launched, so wait for any recovery completion work to
* complete. */
- flush_workqueue(ocfs2_wq);
+ flush_workqueue(osb->ocfs2_wq);
/*
* Now that recovery is shut down, and the osb is about to be
@@ -1326,7 +1326,7 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
spin_lock(&journal->j_lock);
list_add_tail(&item->lri_list, &journal->j_la_cleanups);
- queue_work(ocfs2_wq, &journal->j_recovery_work);
+ queue_work(journal->j_osb->ocfs2_wq, &journal->j_recovery_work);
spin_unlock(&journal->j_lock);
}
@@ -1968,7 +1968,7 @@ static void ocfs2_orphan_scan_work(struct work_struct *work)
mutex_lock(&os->os_lock);
ocfs2_queue_orphan_scan(osb);
if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE)
- queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work,
+ queue_delayed_work(osb->ocfs2_wq, &os->os_orphan_scan_work,
ocfs2_orphan_scan_timeout());
mutex_unlock(&os->os_lock);
}
@@ -2008,7 +2008,7 @@ void ocfs2_orphan_scan_start(struct ocfs2_super *osb)
atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE);
else {
atomic_set(&os->os_state, ORPHAN_SCAN_ACTIVE);
- queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work,
+ queue_delayed_work(osb->ocfs2_wq, &os->os_orphan_scan_work,
ocfs2_orphan_scan_timeout());
}
}
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 7d62c43a2c3e..fe0d1f9571bb 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -386,7 +386,7 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
struct ocfs2_dinode *alloc = NULL;
cancel_delayed_work(&osb->la_enable_wq);
- flush_workqueue(ocfs2_wq);
+ flush_workqueue(osb->ocfs2_wq);
if (osb->local_alloc_state == OCFS2_LA_UNUSED)
goto out;
@@ -1085,7 +1085,7 @@ static int ocfs2_recalc_la_window(struct ocfs2_super *osb,
} else {
osb->local_alloc_state = OCFS2_LA_DISABLED;
}
- queue_delayed_work(ocfs2_wq, &osb->la_enable_wq,
+ queue_delayed_work(osb->ocfs2_wq, &osb->la_enable_wq,
OCFS2_LA_ENABLE_INTERVAL);
goto out_unlock;
}
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 77ebc2bc1cca..9ea081f4e6e4 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -104,8 +104,8 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh,
if (page->index == last_index)
len = ((size - 1) & ~PAGE_CACHE_MASK) + 1;
- ret = ocfs2_write_begin_nolock(file, mapping, pos, len, 0, &locked_page,
- &fsdata, di_bh, page);
+ ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP,
+ &locked_page, &fsdata, di_bh, page);
if (ret) {
if (ret != -ENOSPC)
mlog_errno(ret);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 7a0126267847..6cf6538a0651 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -464,6 +464,14 @@ struct ocfs2_super
struct ocfs2_refcount_tree *osb_ref_tree_lru;
struct mutex system_file_mutex;
+
+ /*
+ * OCFS2 needs to schedule several different types of work which
+ * require cluster locking, disk I/O, recovery waits, etc. Since these
+ * types of work tend to be heavy we avoid using the kernel events
+ * workqueue and schedule on our own.
+ */
+ struct workqueue_struct *ocfs2_wq;
};
#define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info)
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 24b7e7f591dc..f8f5fc5e6c05 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1450,28 +1450,20 @@ DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_remove_inode_range);
TRACE_EVENT(ocfs2_prepare_inode_for_write,
TP_PROTO(unsigned long long ino, unsigned long long saved_pos,
- int appending, unsigned long count,
- int *direct_io, int *has_refcount),
- TP_ARGS(ino, saved_pos, appending, count, direct_io, has_refcount),
+ unsigned long count),
+ TP_ARGS(ino, saved_pos, count),
TP_STRUCT__entry(
__field(unsigned long long, ino)
__field(unsigned long long, saved_pos)
- __field(int, appending)
__field(unsigned long, count)
- __field(int, direct_io)
- __field(int, has_refcount)
),
TP_fast_assign(
__entry->ino = ino;
__entry->saved_pos = saved_pos;
- __entry->appending = appending;
__entry->count = count;
- __entry->direct_io = direct_io ? *direct_io : -1;
- __entry->has_refcount = has_refcount ? *has_refcount : -1;
),
- TP_printk("%llu %llu %d %lu %d %d", __entry->ino,
- __entry->saved_pos, __entry->appending, __entry->count,
- __entry->direct_io, __entry->has_refcount)
+ TP_printk("%llu %llu %lu", __entry->ino,
+ __entry->saved_pos, __entry->count)
);
DEFINE_OCFS2_INT_EVENT(generic_file_aio_read_ret);
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 91bc674203ed..3892f3c079ca 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -726,7 +726,7 @@ static int ocfs2_release_dquot(struct dquot *dquot)
dqgrab(dquot);
/* First entry on list -> queue work */
if (llist_add(&OCFS2_DQUOT(dquot)->list, &osb->dquot_drop_list))
- queue_work(ocfs2_wq, &osb->dquot_drop_work);
+ queue_work(osb->ocfs2_wq, &osb->dquot_drop_work);
goto out;
}
status = ocfs2_lock_global_qf(oinfo, 1);
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index 576b9a04873f..18451e0fab81 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -196,7 +196,7 @@ static int update_backups(struct inode * inode, u32 clusters, char *data)
for (i = 0; i < OCFS2_MAX_BACKUP_SUPERBLOCKS; i++) {
blkno = ocfs2_backup_super_blkno(inode->i_sb, i);
cluster = ocfs2_blocks_to_clusters(inode->i_sb, blkno);
- if (cluster > clusters)
+ if (cluster >= clusters)
break;
ret = ocfs2_read_blocks_sync(osb, blkno, 1, &backup);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index ccc9386c42c5..7db631e1c8b0 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -80,12 +80,6 @@ static struct kmem_cache *ocfs2_inode_cachep;
struct kmem_cache *ocfs2_dquot_cachep;
struct kmem_cache *ocfs2_qf_chunk_cachep;
-/* OCFS2 needs to schedule several different types of work which
- * require cluster locking, disk I/O, recovery waits, etc. Since these
- * types of work tend to be heavy we avoid using the kernel events
- * workqueue and schedule on our own. */
-struct workqueue_struct *ocfs2_wq = NULL;
-
static struct dentry *ocfs2_debugfs_root;
MODULE_AUTHOR("Oracle");
@@ -1613,33 +1607,25 @@ static int __init ocfs2_init(void)
if (status < 0)
goto out2;
- ocfs2_wq = create_singlethread_workqueue("ocfs2_wq");
- if (!ocfs2_wq) {
- status = -ENOMEM;
- goto out3;
- }
-
ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
if (!ocfs2_debugfs_root) {
status = -ENOMEM;
mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n");
- goto out4;
+ goto out3;
}
ocfs2_set_locking_protocol();
status = register_quota_format(&ocfs2_quota_format);
if (status < 0)
- goto out4;
+ goto out3;
status = register_filesystem(&ocfs2_fs_type);
if (!status)
return 0;
unregister_quota_format(&ocfs2_quota_format);
-out4:
- destroy_workqueue(ocfs2_wq);
- debugfs_remove(ocfs2_debugfs_root);
out3:
+ debugfs_remove(ocfs2_debugfs_root);
ocfs2_free_mem_caches();
out2:
exit_ocfs2_uptodate_cache();
@@ -1650,11 +1636,6 @@ out1:
static void __exit ocfs2_exit(void)
{
- if (ocfs2_wq) {
- flush_workqueue(ocfs2_wq);
- destroy_workqueue(ocfs2_wq);
- }
-
unregister_quota_format(&ocfs2_quota_format);
debugfs_remove(ocfs2_debugfs_root);
@@ -1745,8 +1726,8 @@ static void ocfs2_inode_init_once(void *data)
spin_lock_init(&oi->ip_lock);
ocfs2_extent_map_init(&oi->vfs_inode);
INIT_LIST_HEAD(&oi->ip_io_markers);
+ INIT_LIST_HEAD(&oi->ip_unwritten_list);
oi->ip_dir_start_lookup = 0;
- mutex_init(&oi->ip_unaligned_aio);
init_rwsem(&oi->ip_alloc_sem);
init_rwsem(&oi->ip_xattr_sem);
mutex_init(&oi->ip_io_mutex);
@@ -2349,6 +2330,12 @@ static int ocfs2_initialize_super(struct super_block *sb,
}
cleancache_init_shared_fs(sb);
+ osb->ocfs2_wq = create_singlethread_workqueue("ocfs2_wq");
+ if (!osb->ocfs2_wq) {
+ status = -ENOMEM;
+ mlog_errno(status);
+ }
+
bail:
return status;
}
@@ -2536,6 +2523,12 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
{
/* This function assumes that the caller has the main osb resource */
+ /* ocfs2_initializer_super have already created this workqueue */
+ if (osb->ocfs2_wq) {
+ flush_workqueue(osb->ocfs2_wq);
+ destroy_workqueue(osb->ocfs2_wq);
+ }
+
ocfs2_free_slot_info(osb);
kfree(osb->osb_orphan_wipes);
diff --git a/fs/ocfs2/super.h b/fs/ocfs2/super.h
index b477d0b1c7b6..b023e4f3d740 100644
--- a/fs/ocfs2/super.h
+++ b/fs/ocfs2/super.h
@@ -26,8 +26,6 @@
#ifndef OCFS2_SUPER_H
#define OCFS2_SUPER_H
-extern struct workqueue_struct *ocfs2_wq;
-
int ocfs2_publish_get_mount_state(struct ocfs2_super *osb,
int node_num);