CEPH-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: Jeff Layton <jlayton@kernel.org>
To: dhowells@redhat.com, idryomov@gmail.com
Cc: xiubli@redhat.com, ceph-devel@vger.kernel.org,
	linux-cachefs@redhat.com, linux-fsdevel@vger.kernel.org
Subject: [PATCH v2 5/6] ceph: plug write_begin into read helper
Date: Wed, 17 Feb 2021 07:58:44 -0500
Message-ID: <20210217125845.10319-6-jlayton@kernel.org> (raw)
In-Reply-To: <20210217125845.10319-1-jlayton@kernel.org>

Convert ceph_write_begin to use the netfs_write_begin helper. Most of
the ops we need for it are already in place from the readpage conversion
but we do add a new check_write_begin op since ceph needs to be able to
vet whether there is an incompatible writeback already in flight before
reading in the page.

With this, we can also remove the old ceph_do_readpage helper.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Cc: ceph-devel@vger.kernel.org
Cc: linux-cachefs@redhat.com
Cc: linux-fsdevel@vger.kernel.org
---
 fs/ceph/addr.c | 188 ++++++++++++++++---------------------------------
 1 file changed, 62 insertions(+), 126 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 6d4de969f761..774fd4efffd7 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -340,76 +340,6 @@ static int ceph_readpage(struct file *file, struct page *page)
 	return netfs_readpage(file, page, &ceph_readpage_netfs_ops, NULL);
 }
 
-/* read a single page, without unlocking it. */
-static int ceph_do_readpage(struct file *filp, struct page *page)
-{
-	struct inode *inode = file_inode(filp);
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	struct ceph_osd_client *osdc = &fsc->client->osdc;
-	struct ceph_osd_request *req;
-	struct ceph_vino vino = ceph_vino(inode);
-	int err = 0;
-	u64 off = page_offset(page);
-	u64 len = PAGE_SIZE;
-
-	if (off >= i_size_read(inode)) {
-		zero_user_segment(page, 0, PAGE_SIZE);
-		SetPageUptodate(page);
-		return 0;
-	}
-
-	if (ci->i_inline_version != CEPH_INLINE_NONE) {
-		/*
-		 * Uptodate inline data should have been added
-		 * into page cache while getting Fcr caps.
-		 */
-		if (off == 0)
-			return -EINVAL;
-		zero_user_segment(page, 0, PAGE_SIZE);
-		SetPageUptodate(page);
-		return 0;
-	}
-
-	dout("readpage ino %llx.%llx file %p off %llu len %llu page %p index %lu\n",
-	     vino.ino, vino.snap, filp, off, len, page, page->index);
-	req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len, 0, 1,
-				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, NULL,
-				    ci->i_truncate_seq, ci->i_truncate_size,
-				    false);
-	if (IS_ERR(req))
-		return PTR_ERR(req);
-
-	osd_req_op_extent_osd_data_pages(req, 0, &page, len, 0, false, false);
-
-	err = ceph_osdc_start_request(osdc, req, false);
-	if (!err)
-		err = ceph_osdc_wait_request(osdc, req);
-
-	ceph_update_read_latency(&fsc->mdsc->metric, req->r_start_latency,
-				 req->r_end_latency, err);
-
-	ceph_osdc_put_request(req);
-	dout("readpage result %d\n", err);
-
-	if (err == -ENOENT)
-		err = 0;
-	if (err < 0) {
-		if (err == -EBLOCKLISTED)
-			fsc->blocklisted = true;
-		goto out;
-	}
-	if (err < PAGE_SIZE)
-		/* zero fill remainder of page */
-		zero_user_segment(page, err, PAGE_SIZE);
-	else
-		flush_dcache_page(page);
-
-	SetPageUptodate(page);
-out:
-	return err < 0 ? err : 0;
-}
-
 /*
  * Finish an async read(ahead) op.
  */
@@ -1429,6 +1359,41 @@ ceph_find_incompatible(struct page *page)
 	return NULL;
 }
 
+static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len,
+					struct page *page, void **_fsdata)
+{
+	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_snap_context *snapc;
+
+	snapc = ceph_find_incompatible(page);
+	if (snapc) {
+		int r;
+
+		unlock_page(page);
+		put_page(page);
+		if (IS_ERR(snapc))
+			return PTR_ERR(snapc);
+
+		ceph_queue_writeback(inode);
+		r = wait_event_killable(ci->i_cap_wq,
+					context_is_writeable_or_written(inode, snapc));
+		ceph_put_snap_context(snapc);
+		return r == 0 ? -EAGAIN : r;
+	}
+	return 0;
+}
+
+const struct netfs_read_request_ops ceph_netfs_write_begin_ops = {
+	.init_rreq		= ceph_init_rreq,
+	.is_cache_enabled	= ceph_is_cache_enabled,
+	.begin_cache_operation	= ceph_begin_cache_operation,
+	.issue_op		= ceph_netfs_issue_op,
+	.expand_readahead	= ceph_netfs_expand_readahead,
+	.clamp_length		= ceph_netfs_clamp_length,
+	.check_write_begin	= ceph_netfs_check_write_begin,
+};
+
 /*
  * We are only allowed to write into/dirty the page if the page is
  * clean, or already dirty within the same snap context.
@@ -1439,75 +1404,46 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_snap_context *snapc;
 	struct page *page = NULL;
 	pgoff_t index = pos >> PAGE_SHIFT;
-	int pos_in_page = pos & ~PAGE_MASK;
-	int r = 0;
-
-	dout("write_begin file %p inode %p page %p %d~%d\n", file, inode, page, (int)pos, (int)len);
-
-	for (;;) {
-		page = grab_cache_page_write_begin(mapping, index, flags);
-		if (!page) {
-			r = -ENOMEM;
-			break;
-		}
-
-		snapc = ceph_find_incompatible(page);
-		if (snapc) {
-			if (IS_ERR(snapc)) {
-				r = PTR_ERR(snapc);
-				break;
-			}
-			unlock_page(page);
-			put_page(page);
-			page = NULL;
-			ceph_queue_writeback(inode);
-			r = wait_event_killable(ci->i_cap_wq,
-						context_is_writeable_or_written(inode, snapc));
-			ceph_put_snap_context(snapc);
-			if (r != 0)
-				break;
-			continue;
-		}
-
-		if (PageUptodate(page)) {
-			dout(" page %p already uptodate\n", page);
-			break;
-		}
+	int r;
 
+	if (ci->i_inline_version != CEPH_INLINE_NONE) {
 		/*
-		 * In some cases we don't need to read at all:
-		 * - full page write
-		 * - write that lies completely beyond EOF
-		 * - write that covers the the page from start to EOF or beyond it
+		 * In principle, we should never get here, as the inode should have been uninlined
+		 * before we're allowed to write to the page (in write_iter or page_mkwrite).
 		 */
-		if ((pos_in_page == 0 && len == PAGE_SIZE) ||
-		    (pos >= i_size_read(inode)) ||
-		    (pos_in_page == 0 && (pos + len) >= i_size_read(inode))) {
-			zero_user_segments(page, 0, pos_in_page,
-					   pos_in_page + len, PAGE_SIZE);
-			break;
-		}
+		WARN_ONCE(1, "ceph: write_begin called on still-inlined inode!\n");
 
 		/*
-		 * We need to read it. If we get back -EINPROGRESS, then the page was
-		 * handed off to fscache and it will be unlocked when the read completes.
-		 * Refind the page in that case so we can reacquire the page lock. Otherwise
-		 * we got a hard error or the read was completed synchronously.
+		 * Uptodate inline data should have been added
+		 * into page cache while getting Fcr caps.
 		 */
-		r = ceph_do_readpage(file, page);
-		if (r != -EINPROGRESS)
-			break;
+		if (index == 0) {
+			r = -EINVAL;
+			goto out;
+		}
+
+		page = grab_cache_page_write_begin(mapping, index, flags);
+		if (!page)
+			return -ENOMEM;
+
+		zero_user_segment(page, 0, PAGE_SIZE);
+		SetPageUptodate(page);
+		r = 0;
+		goto out;
 	}
 
+	r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &page, NULL,
+			      &ceph_netfs_write_begin_ops, NULL);
+out:
+	if (r == 0)
+		wait_on_page_fscache(page);
 	if (r < 0) {
-		if (page) {
-			unlock_page(page);
+		if (page)
 			put_page(page);
-		}
 	} else {
+		WARN_ON_ONCE(!PageLocked(page));
 		*pagep = page;
 	}
 	return r;
-- 
2.29.2


  parent reply index

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20210217125845.10319-1-jlayton@kernel.org>
2021-02-17 12:58 ` [PATCH v2 1/6] ceph: disable old fscache readpage handling Jeff Layton
2021-02-19  5:09   ` Xiubo Li
2021-02-22 14:47     ` Jeff Layton
2021-02-17 12:58 ` [PATCH v2 2/6] ceph: rework PageFsCache handling Jeff Layton
2021-02-17 14:38   ` Matthew Wilcox
2021-02-17 14:59     ` Jeff Layton
2021-02-17 12:58 ` [PATCH v2 3/6] ceph: fix fscache invalidation Jeff Layton
2021-02-17 12:58 ` [PATCH v2 4/6] ceph: convert readpage to fscache read helper Jeff Layton
2021-02-17 12:58 ` Jeff Layton [this message]
2021-02-17 12:58 ` [PATCH v2 6/6] ceph: convert ceph_readpages to ceph_readahead Jeff Layton
2021-02-17 15:15   ` Matthew Wilcox
2021-02-17 15:46     ` Jeff Layton

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=20210217125845.10319-6-jlayton@kernel.org \
    --to=jlayton@kernel.org \
    --cc=ceph-devel@vger.kernel.org \
    --cc=dhowells@redhat.com \
    --cc=idryomov@gmail.com \
    --cc=linux-cachefs@redhat.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=xiubli@redhat.com \
    /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

CEPH-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/ceph-devel/0 ceph-devel/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 ceph-devel ceph-devel/ https://lore.kernel.org/ceph-devel \
		ceph-devel@vger.kernel.org
	public-inbox-index ceph-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.ceph-devel


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