Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull ceph updates from Sage Weil:
 "The bulk of this pull is a series from Alex that refactors and cleans
  up the RBD code to lay the groundwork for supporting the new image
  format and evolving feature set.  There are also some cleanups in
  libceph, and for ceph there's fixed validation of file striping
  layouts and a bugfix in the code handling a shrinking MDS cluster."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (71 commits)
  ceph: avoid 32-bit page index overflow
  ceph: return EIO on invalid layout on GET_DATALOC ioctl
  rbd: BUG on invalid layout
  ceph: propagate layout error on osd request creation
  libceph: check for invalid mapping
  ceph: convert to use le32_add_cpu()
  ceph: Fix oops when handling mdsmap that decreases max_mds
  rbd: update remaining header fields for v2
  rbd: get snapshot name for a v2 image
  rbd: get the snapshot context for a v2 image
  rbd: get image features for a v2 image
  rbd: get the object prefix for a v2 rbd image
  rbd: add code to get the size of a v2 rbd image
  rbd: lay out header probe infrastructure
  rbd: encapsulate code that gets snapshot info
  rbd: add an rbd features field
  rbd: don't use index in __rbd_add_snap_dev()
  rbd: kill create_snap sysfs entry
  rbd: define rbd_dev_image_id()
  rbd: define some new format constants
  ...

4 files changed, 50 insertions, 27 deletions

diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 900ea0f043fc..812eb3b46c1f 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -637,7 +637,7 @@ bad:
 /*
  * Do a synchronous pool op.
  */
-int ceph_monc_do_poolop(struct ceph_mon_client *monc, u32 op,
+static int do_poolop(struct ceph_mon_client *monc, u32 op,
 			u32 pool, u64 snapid,
 			char *buf, int len)
 {
@@ -687,7 +687,7 @@ out:
 int ceph_monc_create_snapid(struct ceph_mon_client *monc,
 			    u32 pool, u64 *snapid)
 {
-	return ceph_monc_do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
+	return do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
 				   pool, 0, (char *)snapid, sizeof(*snapid));
 
 }
@@ -696,7 +696,7 @@ EXPORT_SYMBOL(ceph_monc_create_snapid);
 int ceph_monc_delete_snapid(struct ceph_mon_client *monc,
 			    u32 pool, u64 snapid)
 {
-	return ceph_monc_do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
+	return do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
 				   pool, snapid, 0, 0);
 
 }
@@ -769,7 +769,6 @@ static int build_initial_monmap(struct ceph_mon_client *monc)
 		monc->monmap->mon_inst[i].name.num = cpu_to_le64(i);
 	}
 	monc->monmap->num_mon = num_mon;
-	monc->have_fsid = false;
 	return 0;
 }
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 42119c05e82c..ccbdfbba9e53 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -52,7 +52,7 @@ static int op_has_extent(int op)
 		op == CEPH_OSD_OP_WRITE);
 }
 
-void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+int ceph_calc_raw_layout(struct ceph_osd_client *osdc,
 			struct ceph_file_layout *layout,
 			u64 snapid,
 			u64 off, u64 *plen, u64 *bno,
@@ -62,12 +62,15 @@ void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
 	struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
 	u64 orig_len = *plen;
 	u64 objoff, objlen;    /* extent in object */
+	int r;
 
 	reqhead->snapid = cpu_to_le64(snapid);
 
 	/* object extent? */
-	ceph_calc_file_object_mapping(layout, off, plen, bno,
-				      &objoff, &objlen);
+	r = ceph_calc_file_object_mapping(layout, off, plen, bno,
+					  &objoff, &objlen);
+	if (r < 0)
+		return r;
 	if (*plen < orig_len)
 		dout(" skipping last %llu, final file extent %llu~%llu\n",
 		     orig_len - *plen, off, *plen);
@@ -83,7 +86,7 @@ void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
 
 	dout("calc_layout bno=%llx %llu~%llu (%d pages)\n",
 	     *bno, objoff, objlen, req->r_num_pages);
-
+	return 0;
 }
 EXPORT_SYMBOL(ceph_calc_raw_layout);
 
@@ -112,20 +115,25 @@ EXPORT_SYMBOL(ceph_calc_raw_layout);
  *
  * fill osd op in request message.
  */
-static void calc_layout(struct ceph_osd_client *osdc,
-			struct ceph_vino vino,
-			struct ceph_file_layout *layout,
-			u64 off, u64 *plen,
-			struct ceph_osd_request *req,
-			struct ceph_osd_req_op *op)
+static int calc_layout(struct ceph_osd_client *osdc,
+		       struct ceph_vino vino,
+		       struct ceph_file_layout *layout,
+		       u64 off, u64 *plen,
+		       struct ceph_osd_request *req,
+		       struct ceph_osd_req_op *op)
 {
 	u64 bno;
+	int r;
 
-	ceph_calc_raw_layout(osdc, layout, vino.snap, off,
-			     plen, &bno, req, op);
+	r = ceph_calc_raw_layout(osdc, layout, vino.snap, off,
+				 plen, &bno, req, op);
+	if (r < 0)
+		return r;
 
 	snprintf(req->r_oid, sizeof(req->r_oid), "%llx.%08llx", vino.ino, bno);
 	req->r_oid_len = strlen(req->r_oid);
+
+	return r;
 }
 
 /*
@@ -456,6 +464,7 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 {
 	struct ceph_osd_req_op ops[3];
 	struct ceph_osd_request *req;
+	int r;
 
 	ops[0].op = opcode;
 	ops[0].extent.truncate_seq = truncate_seq;
@@ -474,10 +483,12 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 					 use_mempool,
 					 GFP_NOFS, NULL, NULL);
 	if (!req)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	/* calculate max write size */
-	calc_layout(osdc, vino, layout, off, plen, req, ops);
+	r = calc_layout(osdc, vino, layout, off, plen, req, ops);
+	if (r < 0)
+		return ERR_PTR(r);
 	req->r_file_layout = *layout;  /* keep a copy */
 
 	/* in case it differs from natural (file) alignment that
@@ -1920,8 +1931,8 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
 				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
 				    NULL, 0, truncate_seq, truncate_size, NULL,
 				    false, 1, page_align);
-	if (!req)
-		return -ENOMEM;
+	if (IS_ERR(req))
+		return PTR_ERR(req);
 
 	/* it may be a short read due to an object boundary */
 	req->r_pages = pages;
@@ -1963,8 +1974,8 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 				    snapc, do_sync,
 				    truncate_seq, truncate_size, mtime,
 				    nofail, 1, page_align);
-	if (!req)
-		return -ENOMEM;
+	if (IS_ERR(req))
+		return PTR_ERR(req);
 
 	/* it may be a short write due to an object boundary */
 	req->r_pages = pages;
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 3124b71a8883..5433fb0eb3c6 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -984,7 +984,7 @@ bad:
  * for now, we write only a single su, until we can
  * pass a stride back to the caller.
  */
-void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
+int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 				   u64 off, u64 *plen,
 				   u64 *ono,
 				   u64 *oxoff, u64 *oxlen)
@@ -998,11 +998,17 @@ void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 
 	dout("mapping %llu~%llu  osize %u fl_su %u\n", off, *plen,
 	     osize, su);
+	if (su == 0 || sc == 0)
+		goto invalid;
 	su_per_object = osize / su;
+	if (su_per_object == 0)
+		goto invalid;
 	dout("osize %u / su %u = su_per_object %u\n", osize, su,
 	     su_per_object);
 
-	BUG_ON((su & ~PAGE_MASK) != 0);
+	if ((su & ~PAGE_MASK) != 0)
+		goto invalid;
+
 	/* bl = *off / su; */
 	t = off;
 	do_div(t, su);
@@ -1030,6 +1036,14 @@ void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 	*plen = *oxlen;
 
 	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
+	return 0;
+
+invalid:
+	dout(" invalid layout\n");
+	*ono = 0;
+	*oxoff = 0;
+	*oxlen = 0;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(ceph_calc_file_object_mapping);
 
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
index 665cd23020ff..92866bebb65f 100644
--- a/net/ceph/pagelist.c
+++ b/net/ceph/pagelist.c
@@ -1,4 +1,3 @@
-
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/pagemap.h>
@@ -134,8 +133,8 @@ int ceph_pagelist_truncate(struct ceph_pagelist *pl,
 	ceph_pagelist_unmap_tail(pl);
 	while (pl->head.prev != c->page_lru) {
 		page = list_entry(pl->head.prev, struct page, lru);
-		list_del(&page->lru);                /* remove from pagelist */
-		list_add_tail(&page->lru, &pl->free_list); /* add to reserve */
+		/* move from pagelist to reserve */
+		list_move_tail(&page->lru, &pl->free_list);
 		++pl->num_pages_free;
 	}
 	pl->room = c->room;