Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/k…

…ernel/git/jlbec/ocfs2

* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2: (31 commits)
  ocfs2: avoid unaligned access to dqc_bitmap
  ocfs2: Use filemap_write_and_wait() instead of write_inode_now()
  ocfs2: honor O_(D)SYNC flag in fallocate
  ocfs2: Add a missing journal credit in ocfs2_link_credits() -v2
  ocfs2: send correct UUID to cleancache initialization
  ocfs2: Commit transactions in error cases -v2
  ocfs2: make direntry invalid when deleting it
  fs/ocfs2/dlm/dlmlock.c: free kmem_cache_zalloc'd data using kmem_cache_free
  ocfs2: Avoid livelock in ocfs2_readpage()
  ocfs2: serialize unaligned aio
  ocfs2: Implement llseek()
  ocfs2: Fix ocfs2_page_mkwrite()
  ocfs2: Add comment about orphan scanning
  ocfs2: Clean up messages in the fs
  ocfs2/cluster: Cluster up now includes network connections too
  ocfs2/cluster: Add new function o2net_fill_node_map()
  ocfs2/cluster: Fix output in file elapsed_time_in_ms
  ocfs2/dlm: dlmlock_remote() needs to account for remastery
  ocfs2/dlm: Take inflight reference count for remotely mastered resources too
  ocfs2/dlm: Cleanup dlm_wait_for_node_death() and dlm_wait_for_node_recovery()
  ...

fs/ocfs2/alloc.c

@@ -5699,7 +5699,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 					   OCFS2_JOURNAL_ACCESS_WRITE);
 	if (ret) {
 		mlog_errno(ret);
-		goto out;
+		goto out_commit;
 	}
 
 	dquot_free_space_nodirty(inode,

fs/ocfs2/aops.c

@@ -290,7 +290,15 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 	}
 
 	if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
+		/*
+		 * Unlock the page and cycle ip_alloc_sem so that we don't
+		 * busyloop waiting for ip_alloc_sem to unlock
+		 */
 		ret = AOP_TRUNCATED_PAGE;
+		unlock_page(page);
+		unlock = 0;
+		down_read(&oi->ip_alloc_sem);
+		up_read(&oi->ip_alloc_sem);
 		goto out_inode_unlock;
 	}
 
@@ -563,13 +571,23 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 {
 	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
 	int level;
+	wait_queue_head_t *wq = ocfs2_ioend_wq(inode);
 
 	/* this io's submitter should not have unlocked this before we could */
 	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
 
 	if (ocfs2_iocb_is_sem_locked(iocb))
 		ocfs2_iocb_clear_sem_locked(iocb);
 
+	if (ocfs2_iocb_is_unaligned_aio(iocb)) {
+		ocfs2_iocb_clear_unaligned_aio(iocb);
+
+		if (atomic_dec_and_test(&OCFS2_I(inode)->ip_unaligned_aio) &&
+		    waitqueue_active(wq)) {
+			wake_up_all(wq);
+		}
+	}
+
 	ocfs2_iocb_clear_rw_locked(iocb);
 
 	level = ocfs2_iocb_rw_locked_level(iocb);
@@ -862,6 +880,12 @@ struct ocfs2_write_ctxt {
 	struct page			*w_pages[OCFS2_MAX_CTXT_PAGES];
 	struct page			*w_target_page;
 
+	/*
+	 * w_target_locked is used for page_mkwrite path indicating no unlocking
+	 * against w_target_page in ocfs2_write_end_nolock.
+	 */
+	unsigned int			w_target_locked:1;
+
 	/*
 	 * ocfs2_write_end() uses this to know what the real range to
 	 * write in the target should be.
@@ -895,6 +919,24 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 
 static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 {
+	int i;
+
+	/*
+	 * w_target_locked is only set to true in the page_mkwrite() case.
+	 * The intent is to allow us to lock the target page from write_begin()
+	 * to write_end(). The caller must hold a ref on w_target_page.
+	 */
+	if (wc->w_target_locked) {
+		BUG_ON(!wc->w_target_page);
+		for (i = 0; i < wc->w_num_pages; i++) {
+			if (wc->w_target_page == wc->w_pages[i]) {
+				wc->w_pages[i] = NULL;
+				break;
+			}
+		}
+		mark_page_accessed(wc->w_target_page);
+		page_cache_release(wc->w_target_page);
+	}
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
 
 	brelse(wc->w_di_bh);
@@ -1132,20 +1174,17 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 			 */
 			lock_page(mmap_page);
 
+			/* Exit and let the caller retry */
 			if (mmap_page->mapping != mapping) {
+				WARN_ON(mmap_page->mapping);
 				unlock_page(mmap_page);
-				/*
-				 * Sanity check - the locking in
-				 * ocfs2_pagemkwrite() should ensure
-				 * that this code doesn't trigger.
-				 */
-				ret = -EINVAL;
-				mlog_errno(ret);
+				ret = -EAGAIN;
 				goto out;
 			}
 
 			page_cache_get(mmap_page);
 			wc->w_pages[i] = mmap_page;
+			wc->w_target_locked = true;
 		} else {
 			wc->w_pages[i] = find_or_create_page(mapping, index,
 							     GFP_NOFS);
@@ -1160,6 +1199,8 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 			wc->w_target_page = wc->w_pages[i];
 	}
 out:
+	if (ret)
+		wc->w_target_locked = false;
 	return ret;
 }
 
@@ -1817,11 +1858,23 @@ int ocfs2_write_begin_nolock(struct file *filp,
 	 */
 	ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, len,
 					 cluster_of_pages, mmap_page);
-	if (ret) {
+	if (ret && ret != -EAGAIN) {
 		mlog_errno(ret);
 		goto out_quota;
 	}
 
+	/*
+	 * ocfs2_grab_pages_for_write() returns -EAGAIN if it could not lock
+	 * the target page. In this case, we exit with no error and no target
+	 * page. This will trigger the caller, page_mkwrite(), to re-try
+	 * the operation.
+	 */
+	if (ret == -EAGAIN) {
+		BUG_ON(wc->w_target_page);
+		ret = 0;
+		goto out_quota;
+	}
+
 	ret = ocfs2_write_cluster_by_desc(mapping, data_ac, meta_ac, wc, pos,
 					  len);
 	if (ret) {

fs/ocfs2/aops.h

@@ -78,6 +78,7 @@ enum ocfs2_iocb_lock_bits {
 	OCFS2_IOCB_RW_LOCK = 0,
 	OCFS2_IOCB_RW_LOCK_LEVEL,
 	OCFS2_IOCB_SEM,
+	OCFS2_IOCB_UNALIGNED_IO,
 	OCFS2_IOCB_NUM_LOCKS
 };
 
@@ -91,4 +92,17 @@ enum ocfs2_iocb_lock_bits {
 	clear_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
 #define ocfs2_iocb_is_sem_locked(iocb) \
 	test_bit(OCFS2_IOCB_SEM, (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)
+
+#define OCFS2_IOEND_WQ_HASH_SZ	37
+#define ocfs2_ioend_wq(v)   (&ocfs2__ioend_wq[((unsigned long)(v)) %\
+					    OCFS2_IOEND_WQ_HASH_SZ])
+extern wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ];
+
 #endif /* OCFS2_FILE_H */