ceph: convert ceph_readpage to netfs_readpage

Have the ceph KConfig select NETFS_SUPPORT. Add a new netfs ops
structure and the operations for it. Convert ceph_readpage to use
the new netfs_readpage helper.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

1 files changed, 158 insertions, 10 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 3936ae3e8dcd..c848e8a4e539 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -12,6 +12,7 @@
 #include <linux/signal.h>
 #include <linux/iversion.h>
 #include <linux/ktime.h>
+#include <linux/netfs.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -183,6 +184,163 @@ static int ceph_releasepage(struct page *page, gfp_t gfp)
 	return !PagePrivate(page);
 }
 
+static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq)
+{
+	struct inode *inode = rreq->mapping->host;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_file_layout *lo = &ci->i_layout;
+	u32 blockoff;
+	u64 blockno;
+
+	/* Expand the start downward */
+	blockno = div_u64_rem(rreq->start, lo->stripe_unit, &blockoff);
+	rreq->start = blockno * lo->stripe_unit;
+	rreq->len += blockoff;
+
+	/* Now, round up the length to the next block */
+	rreq->len = roundup(rreq->len, lo->stripe_unit);
+}
+
+static bool ceph_netfs_clamp_length(struct netfs_read_subrequest *subreq)
+{
+	struct inode *inode = subreq->rreq->mapping->host;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	u64 objno, objoff;
+	u32 xlen;
+
+	/* Truncate the extent at the end of the current block */
+	ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len,
+				      &objno, &objoff, &xlen);
+	subreq->len = min(xlen, fsc->mount_options->rsize);
+	return true;
+}
+
+static void finish_netfs_read(struct ceph_osd_request *req)
+{
+	struct ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode);
+	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
+	struct netfs_read_subrequest *subreq = req->r_priv;
+	int num_pages;
+	int err = req->r_result;
+
+	ceph_update_read_latency(&fsc->mdsc->metric, req->r_start_latency,
+				 req->r_end_latency, err);
+
+	dout("%s: result %d subreq->len=%zu i_size=%lld\n", __func__, req->r_result,
+	     subreq->len, i_size_read(req->r_inode));
+
+	/* no object means success but no data */
+	if (err == -ENOENT)
+		err = 0;
+	else if (err == -EBLOCKLISTED)
+		fsc->blocklisted = true;
+
+	if (err >= 0 && err < subreq->len)
+		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+
+	netfs_subreq_terminated(subreq, err, true);
+
+	num_pages = calc_pages_for(osd_data->alignment, osd_data->length);
+	ceph_put_page_vector(osd_data->pages, num_pages, false);
+	iput(req->r_inode);
+}
+
+static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
+{
+	struct netfs_read_request *rreq = subreq->rreq;
+	struct inode *inode = rreq->mapping->host;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_osd_request *req;
+	struct ceph_vino vino = ceph_vino(inode);
+	struct iov_iter iter;
+	struct page **pages;
+	size_t page_off;
+	int err = 0;
+	u64 len = subreq->len;
+
+	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,
+			NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		req = NULL;
+		goto out;
+	}
+
+	dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
+	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
+	err = iov_iter_get_pages_alloc(&iter, &pages, len, &page_off);
+	if (err < 0) {
+		dout("%s: iov_ter_get_pages_alloc returned %d\n", __func__, err);
+		goto out;
+	}
+
+	/* should always give us a page-aligned read */
+	WARN_ON_ONCE(page_off);
+	len = err;
+
+	osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false);
+	req->r_callback = finish_netfs_read;
+	req->r_priv = subreq;
+	req->r_inode = inode;
+	ihold(inode);
+
+	err = ceph_osdc_start_request(req->r_osdc, req, false);
+	if (err)
+		iput(inode);
+out:
+	ceph_osdc_put_request(req);
+	if (err)
+		netfs_subreq_terminated(subreq, err, false);
+	dout("%s: result %d\n", __func__, err);
+}
+
+static void ceph_init_rreq(struct netfs_read_request *rreq, struct file *file)
+{
+}
+
+const struct netfs_read_request_ops ceph_netfs_read_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,
+};
+
+/* read a single page, without unlocking it. */
+static int ceph_readpage(struct file *file, struct page *page)
+{
+	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_vino vino = ceph_vino(inode);
+	u64 off = page_offset(page);
+	u64 len = PAGE_SIZE;
+
+	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) {
+			unlock_page(page);
+			return -EINVAL;
+		}
+		zero_user_segment(page, 0, PAGE_SIZE);
+		SetPageUptodate(page);
+		unlock_page(page);
+		return 0;
+	}
+
+	dout("readpage ino %llx.%llx file %p off %llu len %llu page %p index %lu\n",
+	     vino.ino, vino.snap, file, off, len, page, page->index);
+
+	return netfs_readpage(file, page, &ceph_netfs_read_ops, NULL);
+}
+
 /* read a single page, without unlocking it. */
 static int ceph_do_readpage(struct file *filp, struct page *page)
 {
@@ -253,16 +411,6 @@ out:
 	return err < 0 ? err : 0;
 }
 
-static int ceph_readpage(struct file *filp, struct page *page)
-{
-	int r = ceph_do_readpage(filp, page);
-	if (r != -EINPROGRESS)
-		unlock_page(page);
-	else
-		r = 0;
-	return r;
-}
-
 /*
  * Finish an async read(ahead) op.
  */