[PATCH 12/17] orangefs: implement writepage

[Martin Brandenburg <martin@omnibond.com>]

Now orangefs_inode_getattr fills from cache if an inode has dirty pages.

also if attr_valid and dirty pages and !flags, we spin on inode writeback
before returning if pages still dirty after: should it be other way

Signed-off-by: Martin Brandenburg <martin@omnibond.com>
---
 fs/orangefs/file.c           | 77 +++++++-----------------------------
 fs/orangefs/inode.c          | 59 ++++++++++++++++++++++++---
 fs/orangefs/orangefs-utils.c | 12 +++++-
 3 files changed, 78 insertions(+), 70 deletions(-)

diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index 4bc06c310e02..ba580a5c6fd2 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * (C) 2001 Clemson University and The University of Chicago
+ * Copyright 2018 Omnibond Systems, L.L.C.
  *
  * See COPYING in top-level directory.
  */
@@ -348,65 +349,11 @@ static ssize_t orangefs_file_read_iter(struct kiocb *iocb,
 	return generic_file_read_iter(iocb, iter);
 }
 
-static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
+static ssize_t orangefs_file_write_iter(struct kiocb *iocb,
+    struct iov_iter *iter)
 {
-	struct file *file = iocb->ki_filp;
-	loff_t pos;
-	ssize_t rc;
-
-	BUG_ON(iocb->private);
-
-	truncate_inode_pages(file->f_mapping, 0);
-
-	gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n");
-
-	inode_lock(file->f_mapping->host);
-
-	/* Make sure generic_write_checks sees an up to date inode size. */
-	if (file->f_flags & O_APPEND) {
-		rc = orangefs_inode_getattr(file->f_mapping->host,
-		    ORANGEFS_GETATTR_SIZE);
-		if (rc == -ESTALE)
-			rc = -EIO;
-		if (rc) {
-			gossip_err("%s: orangefs_inode_getattr failed, "
-			    "rc:%zd:.\n", __func__, rc);
-			goto out;
-		}
-	}
-
-	rc = generic_write_checks(iocb, iter);
-
-	if (rc <= 0) {
-		gossip_err("%s: generic_write_checks failed, rc:%zd:.\n",
-			   __func__, rc);
-		goto out;
-	}
-
-	/*
-	 * if we are appending, generic_write_checks would have updated
-	 * pos to the end of the file, so we will wait till now to set
-	 * pos...
-	 */
-	pos = iocb->ki_pos;
-
-	rc = do_readv_writev(ORANGEFS_IO_WRITE,
-			     file,
-			     &pos,
-			     iter);
-	if (rc < 0) {
-		gossip_err("%s: do_readv_writev failed, rc:%zd:.\n",
-			   __func__, rc);
-		goto out;
-	}
-
-	iocb->ki_pos = pos;
 	orangefs_stats.writes++;
-
-out:
-
-	inode_unlock(file->f_mapping->host);
-	return rc;
+	return generic_file_write_iter(iocb, iter);
 }
 
 /*
@@ -501,9 +448,6 @@ static int orangefs_file_mmap(struct file *file, struct vm_area_struct *vma)
 			(char *)file->f_path.dentry->d_name.name :
 			(char *)"Unknown"));
 
-	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
-		return -EINVAL;
-
 	/* set the sequential readahead hint */
 	vma->vm_flags |= VM_SEQ_READ;
 	vma->vm_flags &= ~VM_RAND_READ;
@@ -543,8 +487,6 @@ static int orangefs_file_release(struct inode *inode, struct file *file)
 			gossip_debug(GOSSIP_INODE_DEBUG,
 			    "flush_racache finished\n");
 		}
-		truncate_inode_pages(file_inode(file)->i_mapping,
-				     0);
 	}
 	return 0;
 }
@@ -562,6 +504,11 @@ static int orangefs_fsync(struct file *file,
 		ORANGEFS_I(file_inode(file));
 	struct orangefs_kernel_op_s *new_op = NULL;
 
+	ret = filemap_write_and_wait_range(file_inode(file)->i_mapping,
+	    start, end);
+	if (ret)
+		return ret;
+
 	new_op = op_alloc(ORANGEFS_VFS_OP_FSYNC);
 	if (!new_op)
 		return -ENOMEM;
@@ -643,6 +590,11 @@ static int orangefs_lock(struct file *filp, int cmd, struct file_lock *fl)
 	return rc;
 }
 
+int orangefs_flush(struct file *file, fl_owner_t id)
+{
+	return vfs_fsync(file, 0);
+}
+
 /** ORANGEFS implementation of VFS file operations */
 const struct file_operations orangefs_file_operations = {
 	.llseek		= orangefs_file_llseek,
@@ -652,6 +604,7 @@ const struct file_operations orangefs_file_operations = {
 	.unlocked_ioctl	= orangefs_ioctl,
 	.mmap		= orangefs_file_mmap,
 	.open		= generic_file_open,
+	.flush		= orangefs_flush,
 	.release	= orangefs_file_release,
 	.fsync		= orangefs_fsync,
 };
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 826054b979cc..5832104cab6a 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -15,6 +15,44 @@
 #include "orangefs-kernel.h"
 #include "orangefs-bufmap.h"
 
+static int orangefs_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct iov_iter iter;
+	struct bio_vec bv;
+	size_t len, wlen;
+	ssize_t ret;
+	loff_t off;
+
+	set_page_writeback(page);
+
+	off = page_offset(page);
+	len = i_size_read(inode);
+	if (off + PAGE_SIZE > len)
+		wlen = len - off;
+	else
+		wlen = PAGE_SIZE;
+
+	bv.bv_page = page;
+	bv.bv_len = wlen;
+	bv.bv_offset = 0;
+	if (wlen == 0)
+		dump_stack();
+	iov_iter_bvec(&iter, ITER_BVEC | WRITE, &bv, 1, wlen);
+
+	ret = wait_for_direct_io(ORANGEFS_IO_WRITE, inode, &off, &iter, wlen,
+	    len);
+	if (ret < 0) {
+		SetPageError(page);
+		mapping_set_error(page->mapping, ret);
+	} else {
+		ret = 0;
+	}
+	end_page_writeback(page);
+	unlock_page(page);
+	return ret;
+}
+
 static int orangefs_readpage(struct file *file, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
@@ -48,6 +86,15 @@ static int orangefs_readpage(struct file *file, struct page *page)
 	return ret;
 }
 
+int orangefs_write_end(struct file *file, struct address_space *mapping,
+    loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata)
+{
+	int r;
+	r = simple_write_end(file, mapping, pos, len, copied, page, fsdata);
+	mark_inode_dirty_sync(file_inode(file));
+	return r;
+}
+
 static void orangefs_invalidatepage(struct page *page,
 				 unsigned int offset,
 				 unsigned int length)
@@ -77,17 +124,17 @@ static ssize_t orangefs_direct_IO(struct kiocb *iocb,
 {
 	struct file *file = iocb->ki_filp;
 	loff_t pos = *(&iocb->ki_pos);
-	/*
-	 * This cannot happen until write_iter becomes
-	 * generic_file_write_iter.
-	 */
-	BUG_ON(iov_iter_rw(iter) != READ);
-	return do_readv_writev(ORANGEFS_IO_READ, file, &pos, iter);
+	return do_readv_writev(iov_iter_rw(iter) == WRITE ?
+	    ORANGEFS_IO_WRITE : ORANGEFS_IO_READ, file, &pos, iter);
 }
 
 /** ORANGEFS2 implementation of address space operations */
 static const struct address_space_operations orangefs_address_operations = {
+	.writepage = orangefs_writepage,
 	.readpage = orangefs_readpage,
+	.set_page_dirty = __set_page_dirty_nobuffers,
+	.write_begin = simple_write_begin,
+	.write_end = orangefs_write_end,
 	.invalidatepage = orangefs_invalidatepage,
 	.releasepage = orangefs_releasepage,
 	.direct_IO = orangefs_direct_IO,
diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c
index 9221c4a3398e..902ebd1599e1 100644
--- a/fs/orangefs/orangefs-utils.c
+++ b/fs/orangefs/orangefs-utils.c
@@ -247,12 +247,16 @@ int orangefs_inode_getattr(struct inode *inode, int flags)
 	spin_lock(&inode->i_lock);
 	/* Must have all the attributes in the mask and be within cache time. */
 	if ((!flags && time_before(jiffies, orangefs_inode->getattr_time)) ||
-	    orangefs_inode->attr_valid) {
+	    orangefs_inode->attr_valid || inode->i_state & I_DIRTY_PAGES) {
 		if (orangefs_inode->attr_valid) {
 			spin_unlock(&inode->i_lock);
 			write_inode_now(inode, 1);
 			goto again;
 		}
+		if (inode->i_state & I_DIRTY_PAGES) {
+			spin_unlock(&inode->i_lock);
+			return 0;
+		}
 		spin_unlock(&inode->i_lock);
 		return 0;
 	}
@@ -281,12 +285,16 @@ int orangefs_inode_getattr(struct inode *inode, int flags)
 	spin_lock(&inode->i_lock);
 	/* Must have all the attributes in the mask and be within cache time. */
 	if ((!flags && time_before(jiffies, orangefs_inode->getattr_time)) ||
-	    orangefs_inode->attr_valid) {
+	    orangefs_inode->attr_valid || inode->i_state & I_DIRTY_PAGES) {
 		if (orangefs_inode->attr_valid) {
 			spin_unlock(&inode->i_lock);
 			write_inode_now(inode, 1);
 			goto again2;
 		}
+		if (inode->i_state & I_DIRTY_PAGES) {
+			spin_unlock(&inode->i_lock);
+			return 0;
+		}
 		gossip_debug(GOSSIP_UTILS_DEBUG, "%s: in cache or dirty\n",
 		    __func__);
 		ret = 0;
-- 
2.19.0