diff mbox series

[v3,2/3] ceph: Make ceph_netfs_issue_op() handle inlined data

Message ID 20220121141838.110954-3-jlayton@kernel.org (mailing list archive)
State New, archived
Headers show
Series ceph: uninline data on open instead of write | expand

Commit Message

Jeff Layton Jan. 21, 2022, 2:18 p.m. UTC 
From: David Howells <dhowells@redhat.com>

Make ceph_netfs_issue_op() handle inlined data on page 0.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/ceph/addr.c | 79 +++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 62 insertions(+), 17 deletions(-)

Comments

David Howells Jan. 21, 2022, 2:57 p.m. UTC | #1 
Jeff Layton <jlayton@kernel.org> wrote:

> +	len = iinfo->inline_len;
> +	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
> +	err = copy_to_iter(iinfo->inline_data, len, &iter);

I think this is probably wrong.  It will read the entirety of the inline data
into the buffer, even if it's bigger than the buffer and you need to offset
pointer into the buffer.

You need to limit it to subreq->len.  Maybe:

	len = min_t(size_t, iinfo->inline_len - subreq->start, subreq->len);
	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages,
			subreq->start, len);
	err = copy_to_iter(iinfo->inline_data + subreq->start, len, &iter);

David
Jeff Layton Jan. 21, 2022, 3:18 p.m. UTC | #2 
On Fri, 2022-01-21 at 14:57 +0000, David Howells wrote:
> Jeff Layton <jlayton@kernel.org> wrote:
> 
> > +	len = iinfo->inline_len;
> > +	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
> > +	err = copy_to_iter(iinfo->inline_data, len, &iter);
> 
> I think this is probably wrong.  It will read the entirety of the inline data
> into the buffer, even if it's bigger than the buffer and you need to offset
> pointer into the buffer.
> 
> You need to limit it to subreq->len.  Maybe:
> 
> 	len = min_t(size_t, iinfo->inline_len - subreq->start, subreq->len);
> 	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages,
> 			subreq->start, len);
> 	err = copy_to_iter(iinfo->inline_data + subreq->start, len, &iter);
> 
> David
> 

Good point. I'll make that change and re-test, but it makes sense.
diff mbox series

Patch

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index fcba36d2cc23..01d97ab56f71 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -239,6 +239,61 @@  static void finish_netfs_read(struct ceph_osd_request *req)
 	iput(req->r_inode);
 }
 
+static bool ceph_netfs_issue_op_inline(struct netfs_read_subrequest *subreq)
+{
+	struct netfs_read_request *rreq = subreq->rreq;
+	struct inode *inode = rreq->inode;
+	struct ceph_mds_reply_info_parsed *rinfo;
+	struct ceph_mds_reply_info_in *iinfo;
+	struct ceph_mds_request *req;
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct iov_iter iter;
+	ssize_t err = 0;
+	size_t len;
+
+	__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+	__clear_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags);
+
+	if (subreq->start >= inode->i_size)
+		goto out;
+
+	/* We need to fetch the inline data. */
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto out;
+	}
+	req->r_ino1 = ci->i_vino;
+	req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INLINE_DATA);
+	req->r_num_caps = 2;
+
+	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	if (err < 0)
+		goto out;
+
+	rinfo = &req->r_reply_info;
+	iinfo = &rinfo->targeti;
+	if (iinfo->inline_version == CEPH_INLINE_NONE) {
+		/* The data got uninlined */
+		ceph_mdsc_put_request(req);
+		return false;
+	}
+
+	len = iinfo->inline_len;
+	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
+
+	err = copy_to_iter(iinfo->inline_data, len, &iter);
+	if (err == 0)
+		err = -EFAULT;
+
+	ceph_mdsc_put_request(req);
+
+out:
+	netfs_subreq_terminated(subreq, err, false);
+	return true;
+}
+
 static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
 {
 	struct netfs_read_request *rreq = subreq->rreq;
@@ -253,6 +308,10 @@  static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
 	int err = 0;
 	u64 len = subreq->len;
 
+	if (ci->i_inline_version != CEPH_INLINE_NONE &&
+	    ceph_netfs_issue_op_inline(subreq))
+		return;
+
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
 			0, 1, CEPH_OSD_OP_READ,
 			CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
@@ -326,23 +385,9 @@  static int ceph_readpage(struct file *file, struct page *subpage)
 	size_t len = folio_size(folio);
 	u64 off = folio_file_pos(folio);
 
-	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) {
-			folio_unlock(folio);
-			return -EINVAL;
-		}
-		zero_user_segment(&folio->page, 0, folio_size(folio));
-		folio_mark_uptodate(folio);
-		folio_unlock(folio);
-		return 0;
-	}
-
-	dout("readpage ino %llx.%llx file %p off %llu len %zu folio %p index %lu\n",
-	     vino.ino, vino.snap, file, off, len, folio, folio_index(folio));
+	dout("readpage ino %llx.%llx file %p off %llu len %zu folio %p index %lu\n inline %d",
+	     vino.ino, vino.snap, file, off, len, folio, folio_index(folio),
+	     ci->i_inline_version != CEPH_INLINE_NONE);
 
 	return netfs_readpage(file, folio, &ceph_netfs_read_ops, NULL);
 }