Merge tag 'vfs-6.10.netfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull netfs updates from Christian Brauner:
 "This reworks the netfslib writeback implementation so that pages read
  from the cache are written to the cache through ->writepages(),
  thereby allowing the fscache page flag to be retired.

  The reworking also:

   - builds on top of the new writeback_iter() infrastructure

   - makes it possible to use vectored write RPCs as discontiguous
     streams of pages can be accommodated

   - makes it easier to do simultaneous content crypto and stream
     division

   - provides support for retrying writes and re-dividing a stream

   - replaces the ->launder_folio() op, so that ->writepages() is used
     instead

   - uses mempools to allocate the netfs_io_request and
     netfs_io_subrequest structs to avoid allocation failure in the
     writeback path

  Some code that uses the fscache page flag is retained for
  compatibility purposes with nfs and ceph. The code is switched to
  using the synonymous private_2 label instead and marked with
  deprecation comments.

  The merge commit contains additional details on the new algorithm that
  I've left out of here as it would probably be excessively detailed.

  On top of the netfslib infrastructure this contains the work to
  convert cifs over to netfslib"

* tag 'vfs-6.10.netfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (38 commits)
  cifs: Enable large folio support
  cifs: Remove some code that's no longer used, part 3
  cifs: Remove some code that's no longer used, part 2
  cifs: Remove some code that's no longer used, part 1
  cifs: Cut over to using netfslib
  cifs: Implement netfslib hooks
  cifs: Make add_credits_and_wake_if() clear deducted credits
  cifs: Add mempools for cifs_io_request and cifs_io_subrequest structs
  cifs: Set zero_point in the copy_file_range() and remap_file_range()
  cifs: Move cifs_loose_read_iter() and cifs_file_write_iter() to file.c
  cifs: Replace the writedata replay bool with a netfs sreq flag
  cifs: Make wait_mtu_credits take size_t args
  cifs: Use more fields from netfs_io_subrequest
  cifs: Replace cifs_writedata with a wrapper around netfs_io_subrequest
  cifs: Replace cifs_readdata with a wrapper around netfs_io_subrequest
  cifs: Use alternative invalidation to using launder_folio
  netfs, afs: Use writeback retry to deal with alternate keys
  netfs: Miscellaneous tidy ups
  netfs: Remove the old writeback code
  netfs: Cut over to using new writeback code
  ...

1 files changed, 39 insertions, 17 deletions

diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index bee047e20f5d..608ba6416919 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -34,6 +34,7 @@ static ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov
 	unsigned long long start = iocb->ki_pos;
 	unsigned long long end = start + iov_iter_count(iter);
 	ssize_t ret, n;
+	size_t len = iov_iter_count(iter);
 	bool async = !is_sync_kiocb(iocb);
 
 	_enter("");
@@ -46,13 +47,17 @@ static ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov
 
 	_debug("uw %llx-%llx", start, end);
 
-	wreq = netfs_alloc_request(iocb->ki_filp->f_mapping, iocb->ki_filp,
-				   start, end - start,
-				   iocb->ki_flags & IOCB_DIRECT ?
-				   NETFS_DIO_WRITE : NETFS_UNBUFFERED_WRITE);
+	wreq = netfs_create_write_req(iocb->ki_filp->f_mapping, iocb->ki_filp, start,
+				      iocb->ki_flags & IOCB_DIRECT ?
+				      NETFS_DIO_WRITE : NETFS_UNBUFFERED_WRITE);
 	if (IS_ERR(wreq))
 		return PTR_ERR(wreq);
 
+	wreq->io_streams[0].avail = true;
+	trace_netfs_write(wreq, (iocb->ki_flags & IOCB_DIRECT ?
+				 netfs_write_trace_dio_write :
+				 netfs_write_trace_unbuffered_write));
+
 	{
 		/* If this is an async op and we're not using a bounce buffer,
 		 * we have to save the source buffer as the iterator is only
@@ -63,7 +68,7 @@ static ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov
 		 * request.
 		 */
 		if (async || user_backed_iter(iter)) {
-			n = netfs_extract_user_iter(iter, wreq->len, &wreq->iter, 0);
+			n = netfs_extract_user_iter(iter, len, &wreq->iter, 0);
 			if (n < 0) {
 				ret = n;
 				goto out;
@@ -71,7 +76,6 @@ static ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov
 			wreq->direct_bv = (struct bio_vec *)wreq->iter.bvec;
 			wreq->direct_bv_count = n;
 			wreq->direct_bv_unpin = iov_iter_extract_will_pin(iter);
-			wreq->len = iov_iter_count(&wreq->iter);
 		} else {
 			wreq->iter = *iter;
 		}
@@ -79,6 +83,8 @@ static ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov
 		wreq->io_iter = wreq->iter;
 	}
 
+	__set_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags);
+
 	/* Copy the data into the bounce buffer and encrypt it. */
 	// TODO
 
@@ -87,10 +93,7 @@ static ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov
 	if (async)
 		wreq->iocb = iocb;
 	wreq->cleanup = netfs_cleanup_dio_write;
-	ret = netfs_begin_write(wreq, is_sync_kiocb(iocb),
-				iocb->ki_flags & IOCB_DIRECT ?
-				netfs_write_trace_dio_write :
-				netfs_write_trace_unbuffered_write);
+	ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), iov_iter_count(&wreq->io_iter));
 	if (ret < 0) {
 		_debug("begin = %zd", ret);
 		goto out;
@@ -100,9 +103,8 @@ static ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov
 		trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip);
 		wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS,
 			    TASK_UNINTERRUPTIBLE);
-
+		smp_rmb(); /* Read error/transferred after RIP flag */
 		ret = wreq->error;
-		_debug("waited = %zd", ret);
 		if (ret == 0) {
 			ret = wreq->transferred;
 			iocb->ki_pos += ret;
@@ -132,18 +134,20 @@ out:
 ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_mapping->host;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
 	struct netfs_inode *ictx = netfs_inode(inode);
-	unsigned long long end;
 	ssize_t ret;
+	loff_t pos = iocb->ki_pos;
+	unsigned long long end = pos + iov_iter_count(from) - 1;
 
-	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
+	_enter("%llx,%zx,%llx", pos, iov_iter_count(from), i_size_read(inode));
 
 	if (!iov_iter_count(from))
 		return 0;
 
 	trace_netfs_write_iter(iocb, from);
-	netfs_stat(&netfs_n_rh_dio_write);
+	netfs_stat(&netfs_n_wh_dio_write);
 
 	ret = netfs_start_io_direct(inode);
 	if (ret < 0)
@@ -157,7 +161,25 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ret = file_update_time(file);
 	if (ret < 0)
 		goto out;
-	ret = kiocb_invalidate_pages(iocb, iov_iter_count(from));
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		/* We could block if there are any pages in the range. */
+		ret = -EAGAIN;
+		if (filemap_range_has_page(mapping, pos, end))
+			if (filemap_invalidate_inode(inode, true, pos, end))
+				goto out;
+	} else {
+		ret = filemap_write_and_wait_range(mapping, pos, end);
+		if (ret < 0)
+			goto out;
+	}
+
+	/*
+	 * After a write we want buffered reads to be sure to go to disk to get
+	 * the new data.  We invalidate clean cached page from the region we're
+	 * about to write.  We do this *before* the write so that we can return
+	 * without clobbering -EIOCBQUEUED from ->direct_IO().
+	 */
+	ret = filemap_invalidate_inode(inode, true, pos, end);
 	if (ret < 0)
 		goto out;
 	end = iocb->ki_pos + iov_iter_count(from);