ceph: make page alignment explicit in osd interface
We used to infer alignment of IOs within a page based on the file offset,
which assumed they matched. This broke with direct IO that was not aligned
to pages (e.g., 512-byte aligned IO). We were also trusting the alignment
specified in the OSD reply, which could have been adjusted by the server.
Explicitly specify the page alignment when setting up OSD IO requests.
Signed-off-by: Sage Weil <sage@newdream.net>
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 7939199..6c09623 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -71,6 +71,7 @@
op->extent.length = objlen;
}
req->r_num_pages = calc_pages_for(off, *plen);
+ req->r_page_alignment = off & ~PAGE_MASK;
if (op->op == CEPH_OSD_OP_WRITE)
op->payload_len = *plen;
@@ -419,7 +420,8 @@
u32 truncate_seq,
u64 truncate_size,
struct timespec *mtime,
- bool use_mempool, int num_reply)
+ bool use_mempool, int num_reply,
+ int page_align)
{
struct ceph_osd_req_op ops[3];
struct ceph_osd_request *req;
@@ -447,6 +449,10 @@
calc_layout(osdc, vino, layout, off, plen, req, ops);
req->r_file_layout = *layout; /* keep a copy */
+ /* in case it differs from natural alignment that calc_layout
+ filled in for us */
+ req->r_page_alignment = page_align;
+
ceph_osdc_build_request(req, off, plen, ops,
snapc,
mtime,
@@ -1489,7 +1495,7 @@
struct ceph_vino vino, struct ceph_file_layout *layout,
u64 off, u64 *plen,
u32 truncate_seq, u64 truncate_size,
- struct page **pages, int num_pages)
+ struct page **pages, int num_pages, int page_align)
{
struct ceph_osd_request *req;
int rc = 0;
@@ -1499,15 +1505,15 @@
req = ceph_osdc_new_request(osdc, layout, vino, off, plen,
CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
NULL, 0, truncate_seq, truncate_size, NULL,
- false, 1);
+ false, 1, page_align);
if (!req)
return -ENOMEM;
/* it may be a short read due to an object boundary */
req->r_pages = pages;
- dout("readpages final extent is %llu~%llu (%d pages)\n",
- off, *plen, req->r_num_pages);
+ dout("readpages final extent is %llu~%llu (%d pages align %d)\n",
+ off, *plen, req->r_num_pages, page_align);
rc = ceph_osdc_start_request(osdc, req, false);
if (!rc)
@@ -1533,6 +1539,7 @@
{
struct ceph_osd_request *req;
int rc = 0;
+ int page_align = off & ~PAGE_MASK;
BUG_ON(vino.snap != CEPH_NOSNAP);
req = ceph_osdc_new_request(osdc, layout, vino, off, &len,
@@ -1541,7 +1548,7 @@
CEPH_OSD_FLAG_WRITE,
snapc, do_sync,
truncate_seq, truncate_size, mtime,
- nofail, 1);
+ nofail, 1, page_align);
if (!req)
return -ENOMEM;
@@ -1638,8 +1645,7 @@
m = ceph_msg_get(req->r_reply);
if (data_len > 0) {
- unsigned data_off = le16_to_cpu(hdr->data_off);
- int want = calc_pages_for(data_off & ~PAGE_MASK, data_len);
+ int want = calc_pages_for(req->r_page_alignment, data_len);
if (unlikely(req->r_num_pages < want)) {
pr_warning("tid %lld reply %d > expected %d pages\n",