iomap: add the new iomap_iter model

The iomap_iter struct provides a convenient way to package up and
maintain all the arguments to the various mapping and operation
functions.  It is operated on using the iomap_iter() function that
is called in loop until the whole range has been processed.  Compared
to the existing iomap_apply() function this avoid an indirect call
for each iteration.

For now iomap_iter() calls back into the existing ->iomap_begin and
->iomap_end methods, but in the future this could be further optimized
to avoid indirect calls entirely.

Based on an earlier patch from Matthew Wilcox <willy@infradead.org>.

Signed-off-by: Christoph Hellwig <hch@lst.de>
[djwong: add to apply.c to preserve git history of iomap loop control]
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>

2 files changed, 109 insertions, 2 deletions

diff --git a/fs/iomap/apply.c b/fs/iomap/apply.c
index 26ab6563181f..e82647aef7ea 100644
--- a/fs/iomap/apply.c
+++ b/fs/iomap/apply.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2010 Red Hat, Inc.
- * Copyright (c) 2016-2018 Christoph Hellwig.
+ * Copyright (c) 2016-2021 Christoph Hellwig.
  */
 #include <linux/module.h>
 #include <linux/compiler.h>
@@ -97,3 +97,75 @@ out:
 
 	return written ? written : ret;
 }
+
+static inline int iomap_iter_advance(struct iomap_iter *iter)
+{
+	/* handle the previous iteration (if any) */
+	if (iter->iomap.length) {
+		if (iter->processed <= 0)
+			return iter->processed;
+		if (WARN_ON_ONCE(iter->processed > iomap_length(iter)))
+			return -EIO;
+		iter->pos += iter->processed;
+		iter->len -= iter->processed;
+		if (!iter->len)
+			return 0;
+	}
+
+	/* clear the state for the next iteration */
+	iter->processed = 0;
+	memset(&iter->iomap, 0, sizeof(iter->iomap));
+	memset(&iter->srcmap, 0, sizeof(iter->srcmap));
+	return 1;
+}
+
+static inline void iomap_iter_done(struct iomap_iter *iter)
+{
+	WARN_ON_ONCE(iter->iomap.offset > iter->pos);
+	WARN_ON_ONCE(iter->iomap.length == 0);
+	WARN_ON_ONCE(iter->iomap.offset + iter->iomap.length <= iter->pos);
+
+	trace_iomap_iter_dstmap(iter->inode, &iter->iomap);
+	if (iter->srcmap.type != IOMAP_HOLE)
+		trace_iomap_iter_srcmap(iter->inode, &iter->srcmap);
+}
+
+/**
+ * iomap_iter - iterate over a ranges in a file
+ * @iter: iteration structue
+ * @ops: iomap ops provided by the file system
+ *
+ * Iterate over filesystem-provided space mappings for the provided file range.
+ *
+ * This function handles cleanup of resources acquired for iteration when the
+ * filesystem indicates there are no more space mappings, which means that this
+ * function must be called in a loop that continues as long it returns a
+ * positive value.  If 0 or a negative value is returned, the caller must not
+ * return to the loop body.  Within a loop body, there are two ways to break out
+ * of the loop body:  leave @iter.processed unchanged, or set it to a negative
+ * errno.
+ */
+int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops)
+{
+	int ret;
+
+	if (iter->iomap.length && ops->iomap_end) {
+		ret = ops->iomap_end(iter->inode, iter->pos, iomap_length(iter),
+				iter->processed > 0 ? iter->processed : 0,
+				iter->flags, &iter->iomap);
+		if (ret < 0 && !iter->processed)
+			return ret;
+	}
+
+	trace_iomap_iter(iter, ops, _RET_IP_);
+	ret = iomap_iter_advance(iter);
+	if (ret <= 0)
+		return ret;
+
+	ret = ops->iomap_begin(iter->inode, iter->pos, iter->len, iter->flags,
+			       &iter->iomap, &iter->srcmap);
+	if (ret < 0)
+		return ret;
+	iomap_iter_done(iter);
+	return 1;
+}
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index e9cd5cc0d6ba..1012d7af6b68 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Copyright (c) 2009-2019 Christoph Hellwig
+ * Copyright (c) 2009-2021 Christoph Hellwig
  *
  * NOTE: none of these tracepoints shall be considered a stable kernel ABI
  * as they can change at any time.
@@ -140,6 +140,8 @@ DEFINE_EVENT(iomap_class, name,	\
 	TP_ARGS(inode, iomap))
 DEFINE_IOMAP_EVENT(iomap_apply_dstmap);
 DEFINE_IOMAP_EVENT(iomap_apply_srcmap);
+DEFINE_IOMAP_EVENT(iomap_iter_dstmap);
+DEFINE_IOMAP_EVENT(iomap_iter_srcmap);
 
 TRACE_EVENT(iomap_apply,
 	TP_PROTO(struct inode *inode, loff_t pos, loff_t length,
@@ -179,6 +181,39 @@ TRACE_EVENT(iomap_apply,
 		   __entry->actor)
 );
 
+TRACE_EVENT(iomap_iter,
+	TP_PROTO(struct iomap_iter *iter, const void *ops,
+		 unsigned long caller),
+	TP_ARGS(iter, ops, caller),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(u64, ino)
+		__field(loff_t, pos)
+		__field(loff_t, length)
+		__field(unsigned int, flags)
+		__field(const void *, ops)
+		__field(unsigned long, caller)
+	),
+	TP_fast_assign(
+		__entry->dev = iter->inode->i_sb->s_dev;
+		__entry->ino = iter->inode->i_ino;
+		__entry->pos = iter->pos;
+		__entry->length = iomap_length(iter);
+		__entry->flags = iter->flags;
+		__entry->ops = ops;
+		__entry->caller = caller;
+	),
+	TP_printk("dev %d:%d ino 0x%llx pos %lld length %lld flags %s (0x%x) ops %ps caller %pS",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		   __entry->ino,
+		   __entry->pos,
+		   __entry->length,
+		   __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS),
+		   __entry->flags,
+		   __entry->ops,
+		   (void *)__entry->caller)
+);
+
 #endif /* _IOMAP_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH