From: Matthew Wilcox <willy@infradead.org>
To: hch@infradead.org
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
linux-xfs@vger.kernel.org
Subject: [PATCH 1/2] iomap: Add iomap_iter API
Date: Wed, 1 Apr 2020 08:25:21 -0700 [thread overview]
Message-ID: <20200401152522.20737-2-willy@infradead.org> (raw)
In-Reply-To: <20200401152522.20737-1-willy@infradead.org>
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
To replace the apply API
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
fs/iomap/Makefile | 2 +-
fs/iomap/iter.c | 81 +++++++++++++++++++++++++++++++++++++++++++
include/linux/iomap.h | 24 +++++++++++++
3 files changed, 106 insertions(+), 1 deletion(-)
create mode 100644 fs/iomap/iter.c
diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile
index eef2722d93a1..477e5e79f874 100644
--- a/fs/iomap/Makefile
+++ b/fs/iomap/Makefile
@@ -9,7 +9,7 @@ ccflags-y += -I $(srctree)/$(src) # needed for trace events
obj-$(CONFIG_FS_IOMAP) += iomap.o
iomap-y += trace.o \
- apply.o \
+ apply.o iter.o \
buffered-io.o \
direct-io.o \
fiemap.o \
diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c
new file mode 100644
index 000000000000..1d668fdd928e
--- /dev/null
+++ b/fs/iomap/iter.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2010 Red Hat, Inc.
+ * Copyright (c) 2016-2018 Christoph Hellwig.
+ */
+#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/iomap.h>
+#include "trace.h"
+
+/*
+ * Execute a iomap write on a segment of the mapping that spans a
+ * contiguous range of pages that have identical block mapping state.
+ *
+ * This avoids the need to map pages individually, do individual allocations
+ * for each page and most importantly avoid the need for filesystem specific
+ * locking per page. Instead, all the operations are amortised over the entire
+ * range of pages. It is assumed that the filesystems will lock whatever
+ * resources they require in the iomap_begin call, and release them in the
+ * iomap_end call.
+ */
+loff_t iomap_iter(struct iomap_iter *iter, loff_t written)
+{
+ const struct iomap_ops *ops = iter->ops;
+ struct iomap *iomap = &iter->iomap;
+ struct iomap *srcmap = &iter->srcmap;
+ loff_t end, ret = 0;
+
+ trace_iomap_apply(iter->inode, iter->pos, iter->len, iter->flags,
+ iter->ops, NULL, _RET_IP_);
+
+ if (written != IOMAP_FIRST_CALL) {
+ if (ops->iomap_end)
+ ret = ops->iomap_end(iter->inode, iter->pos,
+ iter->len, written > 0 ? written : 0,
+ iter->flags, iomap);
+ if (written < 0)
+ return written;
+ if (ret < 0)
+ return ret;
+ iter->pos += written;
+ iter->len -= written;
+ }
+
+ /*
+ * Need to map a range from start position for length bytes. This can
+ * span multiple pages - it is only guaranteed to return a range of a
+ * single type of pages (e.g. all into a hole, all mapped or all
+ * unwritten). Failure at this point has nothing to undo.
+ *
+ * If allocation is required for this range, reserve the space now so
+ * that the allocation is guaranteed to succeed later on. Once we copy
+ * the data into the page cache pages, then we cannot fail otherwise we
+ * expose transient stale data. If the reserve fails, we can safely
+ * back out at this point as there is nothing to undo.
+ */
+ ret = ops->iomap_begin(iter->inode, iter->pos, iter->len,
+ iter->flags, iomap, srcmap);
+ if (ret)
+ return ret;
+ if (WARN_ON(iomap->offset > iter->pos))
+ return -EIO;
+ if (WARN_ON(iomap->offset + iomap->length <= iter->pos))
+ return -EIO;
+ if (WARN_ON(iomap->length == 0))
+ return -EIO;
+
+ trace_iomap_apply_dstmap(iter->inode, iomap);
+ if (srcmap->type != IOMAP_HOLE)
+ trace_iomap_apply_srcmap(iter->inode, srcmap);
+
+ /*
+ * Cut down the length to the one actually provided by the filesystem,
+ * as it might not be able to give us the whole size that we requested.
+ */
+ end = iomap->offset + iomap->length;
+ if (srcmap->type != IOMAP_HOLE)
+ end = min_t(loff_t, end, srcmap->offset + srcmap->length);
+ return min(iter->len, end - iter->pos);
+}
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 8b09463dae0d..ec00a2268f14 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -142,6 +142,30 @@ struct iomap_ops {
ssize_t written, unsigned flags, struct iomap *iomap);
};
+struct iomap_iter {
+ struct inode *inode;
+ const struct iomap_ops *ops;
+ loff_t pos;
+ loff_t len;
+ unsigned flags;
+ struct iomap iomap;
+ struct iomap srcmap;
+};
+
+#define DEFINE_IOMAP_ITER(name, _inode, _pos, _len, _flags, _ops) \
+ struct iomap_iter name = { \
+ .inode = _inode, \
+ .ops = _ops, \
+ .pos = _pos, \
+ .len = _len, \
+ .flags = _flags, \
+ }
+
+/* Magic value for first call to iterator */
+#define IOMAP_FIRST_CALL LLONG_MIN
+
+loff_t iomap_iter(struct iomap_iter *, loff_t written);
+
/*
* Main iomap iterator function.
*/
--
2.25.1
next prev parent reply other threads:[~2020-04-01 15:25 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-01 15:25 [RFC 0/2] Begin switching iomap from apply to iter Matthew Wilcox
2020-04-01 15:25 ` Matthew Wilcox [this message]
2020-04-01 15:42 ` [PATCH 1/2] iomap: Add iomap_iter API Christoph Hellwig
2020-04-01 18:42 ` Matthew Wilcox
2020-04-22 15:19 ` Jan Kara
2020-04-01 19:20 ` Matthew Wilcox
2020-04-02 7:48 ` Christoph Hellwig
2020-04-01 15:25 ` [PATCH 2/2] iomap: Convert page_mkwrite to iter API Matthew Wilcox
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200401152522.20737-2-willy@infradead.org \
--to=willy@infradead.org \
--cc=hch@infradead.org \
--cc=linux-xfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).