All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Howells <dhowells@redhat.com>
To: Trond Myklebust <trondmy@hammerspace.com>,
	Anna Schumaker <anna.schumaker@netapp.com>,
	Steve French <sfrench@samba.org>,
	Dominique Martinet <asmadeus@codewreck.org>
Cc: Jeff Layton <jlayton@kernel.org>,
	ceph-devel@vger.kernel.org, linux-cachefs@redhat.com,
	linux-fsdevel@vger.kernel.org, dhowells@redhat.com,
	Jeff Layton <jlayton@redhat.com>,
	David Wysochanski <dwysocha@redhat.com>,
	"Matthew Wilcox (Oracle)" <willy@infradead.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	linux-cachefs@redhat.com, linux-afs@lists.infradead.org,
	linux-nfs@vger.kernel.org, linux-cifs@vger.kernel.org,
	ceph-devel@vger.kernel.org, v9fs-developer@lists.sourceforge.net,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH 32/33] ceph: plug write_begin into read helper
Date: Mon, 15 Feb 2021 15:50:49 +0000	[thread overview]
Message-ID: <161340424973.1303470.6253467365270537258.stgit@warthog.procyon.org.uk> (raw)
In-Reply-To: <161340385320.1303470.2392622971006879777.stgit@warthog.procyon.org.uk>

From: Jeff Layton <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>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: ceph-devel@vger.kernel.org
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
---

 fs/ceph/addr.c |  187 ++++++++++++++++++--------------------------------------
 1 file changed, 61 insertions(+), 126 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 95f39ff9bb24..18f660611ba1 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -322,76 +322,6 @@ 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.
  */
@@ -1411,6 +1341,40 @@ 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,
+	.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.
@@ -1421,75 +1385,46 @@ 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;



  parent reply	other threads:[~2021-02-15 15:56 UTC|newest]

Thread overview: 81+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-15 15:44 [PATCH 00/33] Network fs helper library & fscache kiocb API [ver #3] David Howells
2021-02-15 15:44 ` [PATCH 01/33] iov_iter: Add ITER_XARRAY David Howells
2021-02-15 15:44 ` [PATCH 02/33] mm: Add an unlock function for PG_private_2/PG_fscache David Howells
2021-02-16 10:26   ` Christoph Hellwig
2021-02-15 15:44 ` [PATCH 03/33] mm: Implement readahead_control pageset expansion David Howells
2021-02-16 10:32   ` Christoph Hellwig
2021-02-16 13:22     ` Matthew Wilcox
2021-02-17 14:36       ` Mike Marshall
2021-02-17 14:36         ` Mike Marshall
2021-02-17 15:42       ` David Howells
2021-02-17 16:59         ` Mike Marshall
2021-02-17 16:59           ` Mike Marshall
2021-02-17 22:20         ` David Howells
2021-02-16 11:48   ` David Howells
2021-02-17 16:13   ` Matthew Wilcox
2021-02-17 22:34   ` David Howells
2021-02-17 22:49     ` Matthew Wilcox
2021-02-18 17:47   ` David Howells
2021-02-15 15:45 ` [PATCH 04/33] vfs: Export rw_verify_area() for use by cachefiles David Howells
2021-02-16 10:26   ` Christoph Hellwig
2021-02-16 11:55   ` David Howells
2021-02-15 15:45 ` [PATCH 05/33] netfs: Make a netfs helper module David Howells
2021-02-15 15:45 ` [PATCH 06/33] netfs, mm: Move PG_fscache helper funcs to linux/netfs.h David Howells
2021-02-15 15:45 ` [PATCH 07/33] netfs, mm: Add unlock_page_fscache() and wait_on_page_fscache() David Howells
2021-02-15 15:45 ` [PATCH 08/33] netfs: Provide readahead and readpage netfs helpers David Howells
2021-02-15 15:45 ` [PATCH 09/33] netfs: Add tracepoints David Howells
2021-02-15 15:46 ` [PATCH 10/33] netfs: Gather stats David Howells
2021-02-15 15:46 ` [PATCH 11/33] netfs: Add write_begin helper David Howells
2021-02-15 15:46 ` [PATCH 12/33] netfs: Define an interface to talk to a cache David Howells
2021-02-15 15:46 ` [PATCH 13/33] netfs: Hold a ref on a page when PG_private_2 is set David Howells
2021-02-15 15:47 ` [PATCH 14/33] fscache, cachefiles: Add alternate API to use kiocb for read/write to cache David Howells
2021-02-16 10:49   ` Christoph Hellwig
2021-02-16 15:08   ` David Howells
2021-02-15 15:47 ` [PATCH 15/33] afs: Disable use of the fscache I/O routines David Howells
2021-02-15 15:47 ` [PATCH 16/33] afs: Pass page into dirty region helpers to provide THP size David Howells
2021-02-15 15:47 ` [PATCH 17/33] afs: Print the operation debug_id when logging an unexpected data version David Howells
2021-02-15 15:47 ` [PATCH 18/33] afs: Move key to afs_read struct David Howells
2021-02-15 15:47 ` [PATCH 19/33] afs: Don't truncate iter during data fetch David Howells
2021-02-15 15:48 ` [PATCH 20/33] afs: Log remote unmarshalling errors David Howells
2021-02-15 15:48 ` [PATCH 21/33] afs: Set up the iov_iter before calling afs_extract_data() David Howells
2021-02-15 15:48 ` [PATCH 22/33] afs: Use ITER_XARRAY for writing David Howells
2021-02-15 15:48 ` [PATCH 23/33] afs: Wait on PG_fscache before modifying/releasing a page David Howells
2021-02-15 15:49 ` [PATCH 24/33] afs: Extract writeback extension into its own function David Howells
2021-02-15 15:49 ` [PATCH 25/33] afs: Prepare for use of THPs David Howells
2021-02-15 15:49 ` [PATCH 26/33] afs: Use the fs operation ops to handle FetchData completion David Howells
2021-02-15 15:49 ` [PATCH 27/33] afs: Use new fscache read helper API David Howells
2021-02-15 15:49 ` [PATCH 28/33] ceph: disable old fscache readpage handling David Howells
2021-02-15 15:50 ` [PATCH 29/33] ceph: rework PageFsCache handling David Howells
2021-02-15 15:50 ` [PATCH 30/33] ceph: fix fscache invalidation David Howells
2021-02-15 15:50 ` [PATCH 31/33] ceph: convert readpage to fscache read helper David Howells
2021-02-15 15:50 ` David Howells [this message]
2021-02-15 15:51 ` [PATCH 33/33] ceph: convert ceph_readpages to ceph_readahead David Howells
2021-02-15 18:05 ` [PATCH 00/33] Network fs helper library & fscache kiocb API [ver #3] Jeff Layton
2021-02-15 18:05   ` Jeff Layton
2021-02-16  0:40   ` Steve French
2021-02-16  0:40     ` Steve French
2021-02-16  2:10     ` Matthew Wilcox
2021-02-16  5:18       ` Steve French
2021-02-16  5:18         ` Steve French
2021-02-16  5:22       ` Steve French
2021-02-16  5:22         ` Steve French
2021-02-23 20:27         ` Matthew Wilcox
2021-02-23 20:27           ` [f2fs-dev] " Matthew Wilcox
2021-02-24  4:57           ` Steve French
2021-02-24  4:57             ` [f2fs-dev] " Steve French
2021-02-24  4:57             ` Steve French
2021-02-24 13:32       ` David Howells
2021-02-24 15:51         ` Matthew Wilcox
2021-02-16 11:01     ` Jeff Layton
2021-02-16 11:01       ` Jeff Layton
2021-02-15 22:46 ` [PATCH 34/33] netfs: Use in_interrupt() not in_softirq() David Howells
2021-02-16  8:42   ` Christoph Hellwig
2021-02-16  9:06     ` Sebastian Andrzej Siewior
2021-02-16  9:29   ` David Howells
2021-02-16  9:30     ` Christoph Hellwig
2021-02-18 14:02     ` [PATCH 34/33] netfs: Pass flag rather than use in_softirq() David Howells
2021-02-18 15:06       ` Marc Dionne
2021-02-18 15:06         ` Marc Dionne
2021-02-18 15:16       ` Marc Dionne
2021-02-18 15:16         ` Marc Dionne
2021-02-19  9:01       ` Sebastian Andrzej Siewior

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=161340424973.1303470.6253467365270537258.stgit@warthog.procyon.org.uk \
    --to=dhowells@redhat.com \
    --cc=anna.schumaker@netapp.com \
    --cc=asmadeus@codewreck.org \
    --cc=ceph-devel@vger.kernel.org \
    --cc=dwysocha@redhat.com \
    --cc=jlayton@kernel.org \
    --cc=jlayton@redhat.com \
    --cc=linux-afs@lists.infradead.org \
    --cc=linux-cachefs@redhat.com \
    --cc=linux-cifs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=sfrench@samba.org \
    --cc=trondmy@hammerspace.com \
    --cc=v9fs-developer@lists.sourceforge.net \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    --subject='Re: [PATCH 32/33] ceph: plug write_begin into read helper' \
    /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

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.