Linux-Block Archive on lore.kernel.org
 help / color / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: linux-xfs@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org, linux-block@vger.kernel.org,
	linux-mm@kvack.org
Subject: [PATCH 11/33] iomap: add an iomap-based readpage and readpages implementation
Date: Wed,  9 May 2018 09:48:08 +0200
Message-ID: <20180509074830.16196-12-hch@lst.de> (raw)
In-Reply-To: <20180509074830.16196-1-hch@lst.de>

Simply use iomap_apply to iterate over the file and a submit a bio for
each non-uptodate but mapped region and zero everything else.  Note that
as-is this can not be used for file systems with a blocksize smaller than
the page size, but that support will be added later.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/iomap.c            | 195 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/iomap.h |   4 +
 2 files changed, 198 insertions(+), 1 deletion(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index 049e0c4aacac..967bd31540fe 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010 Red Hat, Inc.
- * Copyright (c) 2016 Christoph Hellwig.
+ * Copyright (c) 2016-2018 Christoph Hellwig.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -18,6 +18,7 @@
 #include <linux/uaccess.h>
 #include <linux/gfp.h>
 #include <linux/mm.h>
+#include <linux/mm_inline.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
@@ -102,6 +103,198 @@ iomap_sector(struct iomap *iomap, loff_t pos)
 	return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
 }
 
+static inline bool
+iomap_block_needs_zeroing(struct inode *inode, loff_t pos, struct iomap *iomap)
+{
+       return iomap->type != IOMAP_MAPPED || pos > i_size_read(inode);
+}
+
+static void
+iomap_read_end_io(struct bio *bio)
+{
+	int error = blk_status_to_errno(bio->bi_status);
+	struct bio_vec *bvec;
+	int i;
+
+	bio_for_each_segment_all(bvec, bio, i)
+		page_endio(bvec->bv_page, false, error);
+	bio_put(bio);
+}
+
+static struct bio *
+iomap_read_bio_alloc(struct iomap *iomap, sector_t sector, loff_t length)
+{
+	int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	struct bio *bio = bio_alloc(GFP_NOFS, min(BIO_MAX_PAGES, nr_vecs));
+
+	bio->bi_opf = REQ_OP_READ;
+	bio->bi_iter.bi_sector = sector;
+	bio_set_dev(bio, iomap->bdev);
+	bio->bi_end_io = iomap_read_end_io;
+	return bio;
+}
+
+struct iomap_readpage_ctx {
+	struct page		*cur_page;
+	bool			cur_page_in_bio;
+	struct bio		*bio;
+	struct list_head	*pages;
+};
+
+static loff_t
+iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
+		struct iomap *iomap)
+{
+	struct iomap_readpage_ctx *ctx = data;
+	struct page *page = ctx->cur_page;
+	unsigned poff = pos & (PAGE_SIZE - 1);
+	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length);
+	bool is_contig = false;
+	sector_t sector;
+
+	/* we don't support blocksize < PAGE_SIZE quite yet: */
+	WARN_ON_ONCE(pos != page_offset(page));
+	WARN_ON_ONCE(plen != PAGE_SIZE);
+
+	if (iomap_block_needs_zeroing(inode, pos, iomap)) {
+		zero_user(page, poff, plen);
+		SetPageUptodate(page);
+		goto done;
+	}
+
+	ctx->cur_page_in_bio = true;
+
+	/*
+	 * Try to merge into a previous segment if we can.
+	 */
+	sector = iomap_sector(iomap, pos);
+	if (ctx->bio && bio_end_sector(ctx->bio) == sector) {
+		if (__bio_try_merge_page(ctx->bio, page, plen, poff))
+			goto done;
+		is_contig = true;
+	}
+
+	if (!ctx->bio || !is_contig || bio_full(ctx->bio)) {
+		if (ctx->bio)
+			submit_bio(ctx->bio);
+		ctx->bio = iomap_read_bio_alloc(iomap, sector, length);
+	}
+
+	__bio_add_page(ctx->bio, page, plen, poff);
+done:
+	return plen;
+}
+
+int
+iomap_readpage(struct page *page, const struct iomap_ops *ops)
+{
+	struct iomap_readpage_ctx ctx = { .cur_page = page };
+	struct inode *inode = page->mapping->host;
+	unsigned poff;
+	loff_t ret;
+
+	WARN_ON_ONCE(page_has_buffers(page));
+
+	for (poff = 0; poff < PAGE_SIZE; poff += ret) {
+		ret = iomap_apply(inode, page_offset(page) + poff,
+				PAGE_SIZE - poff, 0, ops, &ctx,
+				iomap_readpage_actor);
+		if (ret <= 0) {
+			SetPageError(page);
+			break;
+		}
+	}
+
+	if (ctx.bio)
+		submit_bio(ctx.bio);
+	else
+		unlock_page(page);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_readpage);
+
+static struct page *
+iomap_next_page(struct inode *inode, struct list_head *pages, loff_t end,
+		loff_t *done)
+{
+	while (!list_empty(pages)) {
+		struct page *page = lru_to_page(pages);
+
+		if (page_offset(page) >= end)
+			break;
+
+		list_del(&page->lru);
+		if (!add_to_page_cache_lru(page, inode->i_mapping, page->index,
+				GFP_NOFS))
+			return page;
+
+		*done += PAGE_SIZE;
+		put_page(page);
+	}
+
+	return NULL;
+}
+
+static loff_t
+iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
+		void *data, struct iomap *iomap)
+{
+	struct iomap_readpage_ctx *ctx = data;
+	loff_t done, ret;
+
+	for (done = 0; done < length; done += ret) {
+		if (ctx->cur_page && ((pos + done) & (PAGE_SIZE - 1)) == 0) {
+			if (!ctx->cur_page_in_bio)
+				unlock_page(ctx->cur_page);
+			put_page(ctx->cur_page);
+			ctx->cur_page = NULL;
+		}
+		if (!ctx->cur_page) {
+			ctx->cur_page = iomap_next_page(inode, ctx->pages,
+					pos + length, &done);
+			if (!ctx->cur_page)
+				break;
+			ctx->cur_page_in_bio = false;
+		}
+		ret = iomap_readpage_actor(inode, pos + done, length - done,
+				ctx, iomap);
+	}
+
+	return done;
+}
+
+int
+iomap_readpages(struct address_space *mapping, struct list_head *pages,
+		unsigned nr_pages, const struct iomap_ops *ops)
+{
+	struct iomap_readpage_ctx ctx = { .pages = pages };
+	loff_t pos = page_offset(list_entry(pages->prev, struct page, lru));
+	loff_t last = page_offset(list_entry(pages->next, struct page, lru));
+	loff_t length = last - pos + PAGE_SIZE, ret = 0;
+
+	while (length > 0) {
+		ret = iomap_apply(mapping->host, pos, length, 0, ops,
+				&ctx, iomap_readpages_actor);
+		if (ret <= 0)
+			break;
+		pos += ret;
+		length -= ret;
+	}
+
+	ret = 0;
+
+	if (ctx.bio)
+		submit_bio(ctx.bio);
+	if (ctx.cur_page) {
+		if (!ctx.cur_page_in_bio)
+			unlock_page(ctx.cur_page);
+		put_page(ctx.cur_page);
+	}
+	WARN_ON_ONCE(ret && !list_empty(ctx.pages));
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iomap_readpages);
+
 static void
 iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 {
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 07f73224c38b..4710789620e7 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -9,6 +9,7 @@ struct fiemap_extent_info;
 struct inode;
 struct iov_iter;
 struct kiocb;
+struct page;
 struct vm_area_struct;
 struct vm_fault;
 
@@ -83,6 +84,9 @@ struct iomap_ops {
 
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops);
+int iomap_readpage(struct page *page, const struct iomap_ops *ops);
+int iomap_readpages(struct address_space *mapping, struct list_head *pages,
+		unsigned nr_pages, const struct iomap_ops *ops);
 int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
-- 
2.17.0

  parent reply index

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-09  7:47 stop using buffer heads in xfs and iomap Christoph Hellwig
2018-05-09  7:47 ` [PATCH 01/33] block: add a lower-level bio_add_page interface Christoph Hellwig
2018-05-09 15:12   ` Matthew Wilcox
2018-05-10  6:40     ` Christoph Hellwig
2018-05-10 21:49       ` Andreas Dilger
2018-05-11  6:29         ` Christoph Hellwig
2018-05-15 16:47           ` Jens Axboe
2018-05-10  8:52   ` Ming Lei
2018-05-11  6:24     ` Christoph Hellwig
2018-05-16  5:06   ` Ritesh Harjani
2018-05-16 18:05     ` Christoph Hellwig
2018-05-17  4:18       ` Ritesh Harjani
2018-05-09  7:47 ` [PATCH 02/33] fs: factor out a __generic_write_end helper Christoph Hellwig
2018-05-09 15:15   ` Matthew Wilcox
2018-05-10  6:40     ` Christoph Hellwig
2018-05-09  7:48 ` [PATCH 03/33] fs: move page_cache_seek_hole_data to iomap.c Christoph Hellwig
2018-05-09  7:48 ` [PATCH 04/33] fs: remove the buffer_unwritten check in page_seek_hole_data Christoph Hellwig
2018-05-17 11:33   ` Andreas Grünbacher
2018-05-09  7:48 ` [PATCH 05/33] fs: use ->is_partially_uptodate in page_cache_seek_hole_data Christoph Hellwig
2018-05-09  7:48 ` [PATCH 06/33] mm: give the 'ret' variable a better name __do_page_cache_readahead Christoph Hellwig
2018-05-09 15:45   ` Matthew Wilcox
2018-05-10  6:41     ` Christoph Hellwig
2018-05-09  7:48 ` [PATCH 07/33] mm: split ->readpages calls to avoid non-contiguous pages lists Christoph Hellwig
2018-05-09 15:46   ` Matthew Wilcox
2018-05-09  7:48 ` [PATCH 08/33] iomap: use __bio_add_page in iomap_dio_zero Christoph Hellwig
2018-05-09  7:48 ` [PATCH 09/33] iomap: add a iomap_sector helper Christoph Hellwig
2018-05-09  7:48 ` [PATCH 10/33] iomap: add an iomap-based bmap implementation Christoph Hellwig
2018-05-09 16:46   ` Darrick J. Wong
2018-05-10  6:42     ` Christoph Hellwig
2018-05-10 15:08       ` Darrick J. Wong
2018-05-11  6:25         ` Christoph Hellwig
2018-05-12  1:56           ` Darrick J. Wong
2018-05-09  7:48 ` Christoph Hellwig [this message]
2018-05-10  1:17   ` [PATCH 11/33] iomap: add an iomap-based readpage and readpages implementation Dave Chinner
2018-05-10  6:44     ` Christoph Hellwig
2018-05-09  7:48 ` [PATCH 12/33] xfs: use iomap_bmap Christoph Hellwig
2018-05-09  7:48 ` [PATCH 13/33] xfs: use iomap for blocksize == PAGE_SIZE readpage and readpages Christoph Hellwig
2018-05-09  7:48 ` [PATCH 14/33] xfs: simplify xfs_bmap_punch_delalloc_range Christoph Hellwig
2018-05-09  7:48 ` [PATCH 15/33] xfs: simplify xfs_aops_discard_page Christoph Hellwig
2018-05-09  7:48 ` [PATCH 16/33] xfs: move locking into xfs_bmap_punch_delalloc_range Christoph Hellwig
2018-05-09  7:48 ` [PATCH 17/33] xfs: make xfs_writepage_map extent map centric Christoph Hellwig
2018-05-09  7:48 ` [PATCH 18/33] xfs: remove the now unused XFS_BMAPI_IGSTATE flag Christoph Hellwig
2018-05-09  7:48 ` [PATCH 19/33] xfs: remove xfs_reflink_find_cow_mapping Christoph Hellwig
2018-05-09  7:48 ` [PATCH 20/33] xfs: remove xfs_reflink_trim_irec_to_next_cow Christoph Hellwig
2018-05-09  7:48 ` [PATCH 21/33] xfs: simplify xfs_map_blocks by using xfs_iext_lookup_extent directly Christoph Hellwig
2018-05-09  7:48 ` [PATCH 22/33] xfs: don't clear imap_valid for a non-uptodate buffers Christoph Hellwig
2018-05-09  7:48 ` [PATCH 23/33] xfs: remove the imap_valid flag Christoph Hellwig
2018-05-09  7:48 ` [PATCH 24/33] xfs: don't look at buffer heads in xfs_add_to_ioend Christoph Hellwig
2018-05-09  7:48 ` [PATCH 25/33] xfs: move all writeback buffer_head manipulation into xfs_map_at_offset Christoph Hellwig
2018-05-09  7:48 ` [PATCH 26/33] xfs: allow writeback on pages without buffer heads Christoph Hellwig
2018-05-09  7:48 ` [PATCH 27/33] xfs: remove xfs_start_page_writeback Christoph Hellwig
2018-05-09  7:48 ` [PATCH 28/33] xfs: refactor the tail of xfs_writepage_map Christoph Hellwig
2018-05-09  7:48 ` [PATCH 29/33] xfs: do not set the page uptodate in xfs_writepage_map Christoph Hellwig
2018-05-09  7:48 ` [PATCH 30/33] iomap: add initial support for writes without buffer heads Christoph Hellwig
2018-05-09  7:48 ` [PATCH 31/33] iomap: add support for sub-pagesize buffered I/O " Christoph Hellwig
2018-05-14 16:00   ` Goldwyn Rodrigues
2018-05-15  7:26     ` Christoph Hellwig
2018-05-15 13:47       ` Goldwyn Rodrigues
2018-05-16  5:46         ` Dave Chinner
2018-05-09  7:48 ` [PATCH 32/33] xfs: add support for sub-pagesize writeback without buffer_heads Christoph Hellwig
2018-05-09  7:48 ` [PATCH 33/33] fs: remove __block_write_begin and iomap_to_bh Christoph Hellwig
2018-05-10 15:13 ` stop using buffer heads in xfs and iomap Darrick J. Wong
2018-05-11  6:22   ` Christoph Hellwig
2018-05-11  6:39     ` Darrick J. Wong

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=20180509074830.16196-12-hch@lst.de \
    --to=hch@lst.de \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.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

Linux-Block Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-block/0 linux-block/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-block linux-block/ https://lore.kernel.org/linux-block \
		linux-block@vger.kernel.org
	public-inbox-index linux-block

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-block


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git