Merge branch 'testing' of github.com:ceph/ceph-client into into linux-3.8-ceph

7 files changed, 274 insertions, 286 deletions

diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index ee71ea2..c236c235 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -26,6 +26,22 @@
 #include "crypto.h"
 
 
+/*
+ * Module compatibility interface.  For now it doesn't do anything,
+ * but its existence signals a certain level of functionality.
+ *
+ * The data buffer is used to pass information both to and from
+ * libceph.  The return value indicates whether libceph determines
+ * it is compatible with the caller (from another kernel module),
+ * given the provided data.
+ *
+ * The data pointer can be null.
+ */
+bool libceph_compatible(void *data)
+{
+	return true;
+}
+EXPORT_SYMBOL(libceph_compatible);
 
 /*
  * find filename portion of a path (/foo/bar/baz -> baz)
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
index 3fbda04..1348df9 100644
--- a/net/ceph/ceph_strings.c
+++ b/net/ceph/ceph_strings.c
@@ -21,9 +21,15 @@ const char *ceph_osd_op_name(int op)
 	switch (op) {
 	case CEPH_OSD_OP_READ: return "read";
 	case CEPH_OSD_OP_STAT: return "stat";
+	case CEPH_OSD_OP_MAPEXT: return "mapext";
+	case CEPH_OSD_OP_SPARSE_READ: return "sparse-read";
+	case CEPH_OSD_OP_NOTIFY: return "notify";
+	case CEPH_OSD_OP_NOTIFY_ACK: return "notify-ack";
+	case CEPH_OSD_OP_ASSERT_VER: return "assert-version";
 
 	case CEPH_OSD_OP_MASKTRUNC: return "masktrunc";
 
+	case CEPH_OSD_OP_CREATE: return "create";
 	case CEPH_OSD_OP_WRITE: return "write";
 	case CEPH_OSD_OP_DELETE: return "delete";
 	case CEPH_OSD_OP_TRUNCATE: return "truncate";
@@ -39,6 +45,11 @@ const char *ceph_osd_op_name(int op)
 	case CEPH_OSD_OP_TMAPUP: return "tmapup";
 	case CEPH_OSD_OP_TMAPGET: return "tmapget";
 	case CEPH_OSD_OP_TMAPPUT: return "tmapput";
+	case CEPH_OSD_OP_WATCH: return "watch";
+
+	case CEPH_OSD_OP_CLONERANGE: return "clonerange";
+	case CEPH_OSD_OP_ASSERT_SRC_VERSION: return "assert-src-version";
+	case CEPH_OSD_OP_SRC_CMPXATTR: return "src-cmpxattr";
 
 	case CEPH_OSD_OP_GETXATTR: return "getxattr";
 	case CEPH_OSD_OP_GETXATTRS: return "getxattrs";
@@ -53,6 +64,10 @@ const char *ceph_osd_op_name(int op)
 	case CEPH_OSD_OP_BALANCEREADS: return "balance-reads";
 	case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads";
 	case CEPH_OSD_OP_SCRUB: return "scrub";
+	case CEPH_OSD_OP_SCRUB_RESERVE: return "scrub-reserve";
+	case CEPH_OSD_OP_SCRUB_UNRESERVE: return "scrub-unreserve";
+	case CEPH_OSD_OP_SCRUB_STOP: return "scrub-stop";
+	case CEPH_OSD_OP_SCRUB_MAP: return "scrub-map";
 
 	case CEPH_OSD_OP_WRLOCK: return "wrlock";
 	case CEPH_OSD_OP_WRUNLOCK: return "wrunlock";
@@ -64,10 +79,34 @@ const char *ceph_osd_op_name(int op)
 	case CEPH_OSD_OP_CALL: return "call";
 
 	case CEPH_OSD_OP_PGLS: return "pgls";
+	case CEPH_OSD_OP_PGLS_FILTER: return "pgls-filter";
+	case CEPH_OSD_OP_OMAPGETKEYS: return "omap-get-keys";
+	case CEPH_OSD_OP_OMAPGETVALS: return "omap-get-vals";
+	case CEPH_OSD_OP_OMAPGETHEADER: return "omap-get-header";
+	case CEPH_OSD_OP_OMAPGETVALSBYKEYS: return "omap-get-vals-by-keys";
+	case CEPH_OSD_OP_OMAPSETVALS: return "omap-set-vals";
+	case CEPH_OSD_OP_OMAPSETHEADER: return "omap-set-header";
+	case CEPH_OSD_OP_OMAPCLEAR: return "omap-clear";
+	case CEPH_OSD_OP_OMAPRMKEYS: return "omap-rm-keys";
 	}
 	return "???";
 }
 
+const char *ceph_osd_state_name(int s)
+{
+	switch (s) {
+	case CEPH_OSD_EXISTS:
+		return "exists";
+	case CEPH_OSD_UP:
+		return "up";
+	case CEPH_OSD_AUTOOUT:
+		return "autoout";
+	case CEPH_OSD_NEW:
+		return "new";
+	default:
+		return "???";
+	}
+}
 
 const char *ceph_pool_op_name(int op)
 {
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 35fce75..cbd06a9 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -287,6 +287,7 @@ static int is_out(const struct crush_map *map, const __u32 *weight, int item, in
  * @outpos: our position in that vector
  * @firstn: true if choosing "first n" items, false if choosing "indep"
  * @recurse_to_leaf: true if we want one device under each item of given type
+ * @descend_once: true if we should only try one descent before giving up
  * @out2: second output vector for leaf items (if @recurse_to_leaf)
  */
 static int crush_choose(const struct crush_map *map,
@@ -295,7 +296,7 @@ static int crush_choose(const struct crush_map *map,
 			int x, int numrep, int type,
 			int *out, int outpos,
 			int firstn, int recurse_to_leaf,
-			int *out2)
+			int descend_once, int *out2)
 {
 	int rep;
 	unsigned int ftotal, flocal;
@@ -391,7 +392,7 @@ static int crush_choose(const struct crush_map *map,
 				}
 
 				reject = 0;
-				if (recurse_to_leaf) {
+				if (!collide && recurse_to_leaf) {
 					if (item < 0) {
 						if (crush_choose(map,
 							 map->buckets[-1-item],
@@ -399,6 +400,7 @@ static int crush_choose(const struct crush_map *map,
 							 x, outpos+1, 0,
 							 out2, outpos,
 							 firstn, 0,
+							 map->chooseleaf_descend_once,
 							 NULL) <= outpos)
 							/* didn't get leaf */
 							reject = 1;
@@ -422,7 +424,10 @@ reject:
 					ftotal++;
 					flocal++;
 
-					if (collide && flocal <= map->choose_local_tries)
+					if (reject && descend_once)
+						/* let outer call try again */
+						skip_rep = 1;
+					else if (collide && flocal <= map->choose_local_tries)
 						/* retry locally a few times */
 						retry_bucket = 1;
 					else if (map->choose_local_fallback_tries > 0 &&
@@ -485,6 +490,7 @@ int crush_do_rule(const struct crush_map *map,
 	int i, j;
 	int numrep;
 	int firstn;
+	const int descend_once = 0;
 
 	if ((__u32)ruleno >= map->max_rules) {
 		dprintk(" bad ruleno %d\n", ruleno);
@@ -544,7 +550,8 @@ int crush_do_rule(const struct crush_map *map,
 						      curstep->arg2,
 						      o+osize, j,
 						      firstn,
-						      recurse_to_leaf, c+osize);
+						      recurse_to_leaf,
+						      descend_once, c+osize);
 			}
 
 			if (recurse_to_leaf)
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 5ccf87e..8a62a55 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -9,8 +9,9 @@
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/string.h>
+#ifdef	CONFIG_BLOCK
 #include <linux/bio.h>
-#include <linux/blkdev.h>
+#endif	/* CONFIG_BLOCK */
 #include <linux/dns_resolver.h>
 #include <net/tcp.h>
 
@@ -2651,9 +2652,11 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
 	m->page_alignment = 0;
 	m->pages = NULL;
 	m->pagelist = NULL;
+#ifdef	CONFIG_BLOCK
 	m->bio = NULL;
 	m->bio_iter = NULL;
 	m->bio_seg = 0;
+#endif	/* CONFIG_BLOCK */
 	m->trail = NULL;
 
 	/* front */
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index eb9a444..39629b6 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -23,7 +23,7 @@
 
 static const struct ceph_connection_operations osd_con_ops;
 
-static void send_queued(struct ceph_osd_client *osdc);
+static void __send_queued(struct ceph_osd_client *osdc);
 static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd);
 static void __register_request(struct ceph_osd_client *osdc,
 			       struct ceph_osd_request *req);
@@ -32,64 +32,12 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc,
 static void __send_request(struct ceph_osd_client *osdc,
 			   struct ceph_osd_request *req);
 
-static int op_needs_trail(int op)
-{
-	switch (op) {
-	case CEPH_OSD_OP_GETXATTR:
-	case CEPH_OSD_OP_SETXATTR:
-	case CEPH_OSD_OP_CMPXATTR:
-	case CEPH_OSD_OP_CALL:
-	case CEPH_OSD_OP_NOTIFY:
-		return 1;
-	default:
-		return 0;
-	}
-}
-
 static int op_has_extent(int op)
 {
 	return (op == CEPH_OSD_OP_READ ||
 		op == CEPH_OSD_OP_WRITE);
 }
 
-int ceph_calc_raw_layout(struct ceph_osd_client *osdc,
-			struct ceph_file_layout *layout,
-			u64 snapid,
-			u64 off, u64 *plen, u64 *bno,
-			struct ceph_osd_request *req,
-			struct ceph_osd_req_op *op)
-{
-	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? */
-	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);
-
-	if (op_has_extent(op->op)) {
-		op->extent.offset = objoff;
-		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;
-
-	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);
-
 /*
  * Implement client access to distributed object storage cluster.
  *
@@ -115,20 +63,48 @@ EXPORT_SYMBOL(ceph_calc_raw_layout);
  *
  * fill osd op in request message.
  */
-static int calc_layout(struct ceph_osd_client *osdc,
-		       struct ceph_vino vino,
+static int calc_layout(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;
+	u64 orig_len = *plen;
+	u64 bno = 0;
+	u64 objoff = 0;
+	u64 objlen = 0;
 	int r;
 
-	r = ceph_calc_raw_layout(osdc, layout, vino.snap, off,
-				 plen, &bno, req, op);
+	/* object extent? */
+	r = ceph_calc_file_object_mapping(layout, off, orig_len, &bno,
+					  &objoff, &objlen);
 	if (r < 0)
 		return r;
+	if (objlen < orig_len) {
+		*plen = objlen;
+		dout(" skipping last %llu, final file extent %llu~%llu\n",
+		     orig_len - *plen, off, *plen);
+	}
+
+	if (op_has_extent(op->op)) {
+		u32 osize = le32_to_cpu(layout->fl_object_size);
+		op->extent.offset = objoff;
+		op->extent.length = objlen;
+		if (op->extent.truncate_size <= off - objoff) {
+			op->extent.truncate_size = 0;
+		} else {
+			op->extent.truncate_size -= off - objoff;
+			if (op->extent.truncate_size > osize)
+				op->extent.truncate_size = osize;
+		}
+	}
+	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;
+
+	dout("calc_layout bno=%llx %llu~%llu (%d pages)\n",
+	     bno, objoff, objlen, req->r_num_pages);
 
 	snprintf(req->r_oid, sizeof(req->r_oid), "%llx.%08llx", vino.ino, bno);
 	req->r_oid_len = strlen(req->r_oid);
@@ -148,25 +124,19 @@ void ceph_osdc_release_request(struct kref *kref)
 	if (req->r_request)
 		ceph_msg_put(req->r_request);
 	if (req->r_con_filling_msg) {
-		dout("%s revoking pages %p from con %p\n", __func__,
-		     req->r_pages, req->r_con_filling_msg);
+		dout("%s revoking msg %p from con %p\n", __func__,
+		     req->r_reply, req->r_con_filling_msg);
 		ceph_msg_revoke_incoming(req->r_reply);
 		req->r_con_filling_msg->ops->put(req->r_con_filling_msg);
+		req->r_con_filling_msg = NULL;
 	}
 	if (req->r_reply)
 		ceph_msg_put(req->r_reply);
 	if (req->r_own_pages)
 		ceph_release_page_vector(req->r_pages,
 					 req->r_num_pages);
-#ifdef CONFIG_BLOCK
-	if (req->r_bio)
-		bio_put(req->r_bio);
-#endif
 	ceph_put_snap_context(req->r_snapc);
-	if (req->r_trail) {
-		ceph_pagelist_release(req->r_trail);
-		kfree(req->r_trail);
-	}
+	ceph_pagelist_release(&req->r_trail);
 	if (req->r_mempool)
 		mempool_free(req, req->r_osdc->req_mempool);
 	else
@@ -174,34 +144,14 @@ void ceph_osdc_release_request(struct kref *kref)
 }
 EXPORT_SYMBOL(ceph_osdc_release_request);
 
-static int get_num_ops(struct ceph_osd_req_op *ops, int *needs_trail)
-{
-	int i = 0;
-
-	if (needs_trail)
-		*needs_trail = 0;
-	while (ops[i].op) {
-		if (needs_trail && op_needs_trail(ops[i].op))
-			*needs_trail = 1;
-		i++;
-	}
-
-	return i;
-}
-
 struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
-					       int flags,
 					       struct ceph_snap_context *snapc,
-					       struct ceph_osd_req_op *ops,
+					       unsigned int num_op,
 					       bool use_mempool,
-					       gfp_t gfp_flags,
-					       struct page **pages,
-					       struct bio *bio)
+					       gfp_t gfp_flags)
 {
 	struct ceph_osd_request *req;
 	struct ceph_msg *msg;
-	int needs_trail;
-	int num_op = get_num_ops(ops, &needs_trail);
 	size_t msg_size = sizeof(struct ceph_osd_request_head);
 
 	msg_size += num_op*sizeof(struct ceph_osd_op);
@@ -228,10 +178,6 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 	INIT_LIST_HEAD(&req->r_req_lru_item);
 	INIT_LIST_HEAD(&req->r_osd_item);
 
-	req->r_flags = flags;
-
-	WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0);
-
 	/* create reply message */
 	if (use_mempool)
 		msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
@@ -244,15 +190,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 	}
 	req->r_reply = msg;
 
-	/* allocate space for the trailing data */
-	if (needs_trail) {
-		req->r_trail = kmalloc(sizeof(struct ceph_pagelist), gfp_flags);
-		if (!req->r_trail) {
-			ceph_osdc_put_request(req);
-			return NULL;
-		}
-		ceph_pagelist_init(req->r_trail);
-	}
+	ceph_pagelist_init(&req->r_trail);
 
 	/* create request message; allow space for oid */
 	msg_size += MAX_OBJ_NAME_SIZE;
@@ -270,13 +208,6 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 	memset(msg->front.iov_base, 0, msg->front.iov_len);
 
 	req->r_request = msg;
-	req->r_pages = pages;
-#ifdef CONFIG_BLOCK
-	if (bio) {
-		req->r_bio = bio;
-		bio_get(req->r_bio);
-	}
-#endif
 
 	return req;
 }
@@ -289,6 +220,8 @@ static void osd_req_encode_op(struct ceph_osd_request *req,
 	dst->op = cpu_to_le16(src->op);
 
 	switch (src->op) {
+	case CEPH_OSD_OP_STAT:
+		break;
 	case CEPH_OSD_OP_READ:
 	case CEPH_OSD_OP_WRITE:
 		dst->extent.offset =
@@ -300,52 +233,20 @@ static void osd_req_encode_op(struct ceph_osd_request *req,
 		dst->extent.truncate_seq =
 			cpu_to_le32(src->extent.truncate_seq);
 		break;
-
-	case CEPH_OSD_OP_GETXATTR:
-	case CEPH_OSD_OP_SETXATTR:
-	case CEPH_OSD_OP_CMPXATTR:
-		BUG_ON(!req->r_trail);
-
-		dst->xattr.name_len = cpu_to_le32(src->xattr.name_len);
-		dst->xattr.value_len = cpu_to_le32(src->xattr.value_len);
-		dst->xattr.cmp_op = src->xattr.cmp_op;
-		dst->xattr.cmp_mode = src->xattr.cmp_mode;
-		ceph_pagelist_append(req->r_trail, src->xattr.name,
-				     src->xattr.name_len);
-		ceph_pagelist_append(req->r_trail, src->xattr.val,
-				     src->xattr.value_len);
-		break;
 	case CEPH_OSD_OP_CALL:
-		BUG_ON(!req->r_trail);
-
 		dst->cls.class_len = src->cls.class_len;
 		dst->cls.method_len = src->cls.method_len;
 		dst->cls.indata_len = cpu_to_le32(src->cls.indata_len);
 
-		ceph_pagelist_append(req->r_trail, src->cls.class_name,
+		ceph_pagelist_append(&req->r_trail, src->cls.class_name,
 				     src->cls.class_len);
-		ceph_pagelist_append(req->r_trail, src->cls.method_name,
+		ceph_pagelist_append(&req->r_trail, src->cls.method_name,
 				     src->cls.method_len);
-		ceph_pagelist_append(req->r_trail, src->cls.indata,
+		ceph_pagelist_append(&req->r_trail, src->cls.indata,
 				     src->cls.indata_len);
 		break;
-	case CEPH_OSD_OP_ROLLBACK:
-		dst->snap.snapid = cpu_to_le64(src->snap.snapid);
-		break;
 	case CEPH_OSD_OP_STARTSYNC:
 		break;
-	case CEPH_OSD_OP_NOTIFY:
-		{
-			__le32 prot_ver = cpu_to_le32(src->watch.prot_ver);
-			__le32 timeout = cpu_to_le32(src->watch.timeout);
-
-			BUG_ON(!req->r_trail);
-
-			ceph_pagelist_append(req->r_trail,
-						&prot_ver, sizeof(prot_ver));
-			ceph_pagelist_append(req->r_trail,
-						&timeout, sizeof(timeout));
-		}
 	case CEPH_OSD_OP_NOTIFY_ACK:
 	case CEPH_OSD_OP_WATCH:
 		dst->watch.cookie = cpu_to_le64(src->watch.cookie);
@@ -356,6 +257,64 @@ static void osd_req_encode_op(struct ceph_osd_request *req,
 		pr_err("unrecognized osd opcode %d\n", dst->op);
 		WARN_ON(1);
 		break;
+	case CEPH_OSD_OP_MAPEXT:
+	case CEPH_OSD_OP_MASKTRUNC:
+	case CEPH_OSD_OP_SPARSE_READ:
+	case CEPH_OSD_OP_NOTIFY:
+	case CEPH_OSD_OP_ASSERT_VER:
+	case CEPH_OSD_OP_WRITEFULL:
+	case CEPH_OSD_OP_TRUNCATE:
+	case CEPH_OSD_OP_ZERO:
+	case CEPH_OSD_OP_DELETE:
+	case CEPH_OSD_OP_APPEND:
+	case CEPH_OSD_OP_SETTRUNC:
+	case CEPH_OSD_OP_TRIMTRUNC:
+	case CEPH_OSD_OP_TMAPUP:
+	case CEPH_OSD_OP_TMAPPUT:
+	case CEPH_OSD_OP_TMAPGET:
+	case CEPH_OSD_OP_CREATE:
+	case CEPH_OSD_OP_ROLLBACK:
+	case CEPH_OSD_OP_OMAPGETKEYS:
+	case CEPH_OSD_OP_OMAPGETVALS:
+	case CEPH_OSD_OP_OMAPGETHEADER:
+	case CEPH_OSD_OP_OMAPGETVALSBYKEYS:
+	case CEPH_OSD_OP_MODE_RD:
+	case CEPH_OSD_OP_OMAPSETVALS:
+	case CEPH_OSD_OP_OMAPSETHEADER:
+	case CEPH_OSD_OP_OMAPCLEAR:
+	case CEPH_OSD_OP_OMAPRMKEYS:
+	case CEPH_OSD_OP_OMAP_CMP:
+	case CEPH_OSD_OP_CLONERANGE:
+	case CEPH_OSD_OP_ASSERT_SRC_VERSION:
+	case CEPH_OSD_OP_SRC_CMPXATTR:
+	case CEPH_OSD_OP_GETXATTR:
+	case CEPH_OSD_OP_GETXATTRS:
+	case CEPH_OSD_OP_CMPXATTR:
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_SETXATTRS:
+	case CEPH_OSD_OP_RESETXATTRS:
+	case CEPH_OSD_OP_RMXATTR:
+	case CEPH_OSD_OP_PULL:
+	case CEPH_OSD_OP_PUSH:
+	case CEPH_OSD_OP_BALANCEREADS:
+	case CEPH_OSD_OP_UNBALANCEREADS:
+	case CEPH_OSD_OP_SCRUB:
+	case CEPH_OSD_OP_SCRUB_RESERVE:
+	case CEPH_OSD_OP_SCRUB_UNRESERVE:
+	case CEPH_OSD_OP_SCRUB_STOP:
+	case CEPH_OSD_OP_SCRUB_MAP:
+	case CEPH_OSD_OP_WRLOCK:
+	case CEPH_OSD_OP_WRUNLOCK:
+	case CEPH_OSD_OP_RDLOCK:
+	case CEPH_OSD_OP_RDUNLOCK:
+	case CEPH_OSD_OP_UPLOCK:
+	case CEPH_OSD_OP_DNLOCK:
+	case CEPH_OSD_OP_PGLS:
+	case CEPH_OSD_OP_PGLS_FILTER:
+		pr_err("unsupported osd opcode %s\n",
+			ceph_osd_op_name(dst->op));
+		WARN_ON(1);
+		break;
 	}
 	dst->payload_len = cpu_to_le32(src->payload_len);
 }
@@ -365,25 +324,25 @@ static void osd_req_encode_op(struct ceph_osd_request *req,
  *
  */
 void ceph_osdc_build_request(struct ceph_osd_request *req,
-			     u64 off, u64 *plen,
+			     u64 off, u64 len, unsigned int num_op,
 			     struct ceph_osd_req_op *src_ops,
-			     struct ceph_snap_context *snapc,
-			     struct timespec *mtime,
-			     const char *oid,
-			     int oid_len)
+			     struct ceph_snap_context *snapc, u64 snap_id,
+			     struct timespec *mtime)
 {
 	struct ceph_msg *msg = req->r_request;
 	struct ceph_osd_request_head *head;
 	struct ceph_osd_req_op *src_op;
 	struct ceph_osd_op *op;
 	void *p;
-	int num_op = get_num_ops(src_ops, NULL);
 	size_t msg_size = sizeof(*head) + num_op*sizeof(*op);
 	int flags = req->r_flags;
-	u64 data_len = 0;
+	u64 data_len;
 	int i;
 
+	WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0);
+
 	head = msg->front.iov_base;
+	head->snapid = cpu_to_le64(snap_id);
 	op = (void *)(head + 1);
 	p = (void *)(op + num_op);
 
@@ -393,23 +352,17 @@ void ceph_osdc_build_request(struct ceph_osd_request *req,
 	head->flags = cpu_to_le32(flags);
 	if (flags & CEPH_OSD_FLAG_WRITE)
 		ceph_encode_timespec(&head->mtime, mtime);
+	BUG_ON(num_op > (unsigned int) ((u16) -1));
 	head->num_ops = cpu_to_le16(num_op);
 
-
 	/* fill in oid */
-	head->object_len = cpu_to_le32(oid_len);
-	memcpy(p, oid, oid_len);
-	p += oid_len;
+	head->object_len = cpu_to_le32(req->r_oid_len);
+	memcpy(p, req->r_oid, req->r_oid_len);
+	p += req->r_oid_len;
 
 	src_op = src_ops;
-	while (src_op->op) {
-		osd_req_encode_op(req, op, src_op);
-		src_op++;
-		op++;
-	}
-
-	if (req->r_trail)
-		data_len += req->r_trail->length;
+	while (num_op--)
+		osd_req_encode_op(req, op++, src_op++);
 
 	if (snapc) {
 		head->snap_seq = cpu_to_le64(snapc->seq);
@@ -420,14 +373,12 @@ void ceph_osdc_build_request(struct ceph_osd_request *req,
 		}
 	}
 
+	data_len = req->r_trail.length;
 	if (flags & CEPH_OSD_FLAG_WRITE) {
 		req->r_request->hdr.data_off = cpu_to_le16(off);
-		req->r_request->hdr.data_len = cpu_to_le32(*plen + data_len);
-	} else if (data_len) {
-		req->r_request->hdr.data_off = 0;
-		req->r_request->hdr.data_len = cpu_to_le32(data_len);
+		data_len += len;
 	}
-
+	req->r_request->hdr.data_len = cpu_to_le32(data_len);
 	req->r_request->page_alignment = req->r_page_alignment;
 
 	BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
@@ -459,34 +410,33 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 					       u32 truncate_seq,
 					       u64 truncate_size,
 					       struct timespec *mtime,
-					       bool use_mempool, int num_reply,
+					       bool use_mempool,
 					       int page_align)
 {
-	struct ceph_osd_req_op ops[3];
+	struct ceph_osd_req_op ops[2];
 	struct ceph_osd_request *req;
+	unsigned int num_op = 1;
 	int r;
 
+	memset(&ops, 0, sizeof ops);
+
 	ops[0].op = opcode;
 	ops[0].extent.truncate_seq = truncate_seq;
 	ops[0].extent.truncate_size = truncate_size;
-	ops[0].payload_len = 0;
 
 	if (do_sync) {
 		ops[1].op = CEPH_OSD_OP_STARTSYNC;
-		ops[1].payload_len = 0;
-		ops[2].op = 0;
-	} else
-		ops[1].op = 0;
-
-	req = ceph_osdc_alloc_request(osdc, flags,
-					 snapc, ops,
-					 use_mempool,
-					 GFP_NOFS, NULL, NULL);
+		num_op++;
+	}
+
+	req = ceph_osdc_alloc_request(osdc, snapc, num_op, use_mempool,
+					GFP_NOFS);
 	if (!req)
 		return ERR_PTR(-ENOMEM);
+	req->r_flags = flags;
 
 	/* calculate max write size */
-	r = calc_layout(osdc, vino, layout, off, plen, req, ops);
+	r = calc_layout(vino, layout, off, plen, req, ops);
 	if (r < 0)
 		return ERR_PTR(r);
 	req->r_file_layout = *layout;  /* keep a copy */
@@ -496,10 +446,8 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	req->r_num_pages = calc_pages_for(page_align, *plen);
 	req->r_page_alignment = page_align;
 
-	ceph_osdc_build_request(req, off, plen, ops,
-				snapc,
-				mtime,
-				req->r_oid, req->r_oid_len);
+	ceph_osdc_build_request(req, off, *plen, num_op, ops,
+				snapc, vino.snap, mtime);
 
 	return req;
 }
@@ -623,8 +571,8 @@ static void osd_reset(struct ceph_connection *con)
 	down_read(&osdc->map_sem);
 	mutex_lock(&osdc->request_mutex);
 	__kick_osd_requests(osdc, osd);
+	__send_queued(osdc);
 	mutex_unlock(&osdc->request_mutex);
-	send_queued(osdc);
 	up_read(&osdc->map_sem);
 }
 
@@ -739,31 +687,35 @@ static void remove_old_osds(struct ceph_osd_client *osdc)
  */
 static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
 {
-	struct ceph_osd_request *req;
-	int ret = 0;
+	struct ceph_entity_addr *peer_addr;
 
 	dout("__reset_osd %p osd%d\n", osd, osd->o_osd);
 	if (list_empty(&osd->o_requests) &&
 	    list_empty(&osd->o_linger_requests)) {
 		__remove_osd(osdc, osd);
-		ret = -ENODEV;
-	} else if (memcmp(&osdc->osdmap->osd_addr[osd->o_osd],
-			  &osd->o_con.peer_addr,
-			  sizeof(osd->o_con.peer_addr)) == 0 &&
-		   !ceph_con_opened(&osd->o_con)) {
+
+		return -ENODEV;
+	}
+
+	peer_addr = &osdc->osdmap->osd_addr[osd->o_osd];
+	if (!memcmp(peer_addr, &osd->o_con.peer_addr, sizeof (*peer_addr)) &&
+			!ceph_con_opened(&osd->o_con)) {
+		struct ceph_osd_request *req;
+
 		dout(" osd addr hasn't changed and connection never opened,"
 		     " letting msgr retry");
 		/* touch each r_stamp for handle_timeout()'s benfit */
 		list_for_each_entry(req, &osd->o_requests, r_osd_item)
 			req->r_stamp = jiffies;
-		ret = -EAGAIN;
-	} else {
-		ceph_con_close(&osd->o_con);
-		ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd,
-			      &osdc->osdmap->osd_addr[osd->o_osd]);
-		osd->o_incarnation++;
+
+		return -EAGAIN;
 	}
-	return ret;
+
+	ceph_con_close(&osd->o_con);
+	ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, peer_addr);
+	osd->o_incarnation++;
+
+	return 0;
 }
 
 static void __insert_osd(struct ceph_osd_client *osdc, struct ceph_osd *new)
@@ -1062,16 +1014,13 @@ static void __send_request(struct ceph_osd_client *osdc,
 /*
  * Send any requests in the queue (req_unsent).
  */
-static void send_queued(struct ceph_osd_client *osdc)
+static void __send_queued(struct ceph_osd_client *osdc)
 {
 	struct ceph_osd_request *req, *tmp;
 
-	dout("send_queued\n");
-	mutex_lock(&osdc->request_mutex);
-	list_for_each_entry_safe(req, tmp, &osdc->req_unsent, r_req_lru_item) {
+	dout("__send_queued\n");
+	list_for_each_entry_safe(req, tmp, &osdc->req_unsent, r_req_lru_item)
 		__send_request(osdc, req);
-	}
-	mutex_unlock(&osdc->request_mutex);
 }
 
 /*
@@ -1123,8 +1072,8 @@ static void handle_timeout(struct work_struct *work)
 	}
 
 	__schedule_osd_timeout(osdc);
+	__send_queued(osdc);
 	mutex_unlock(&osdc->request_mutex);
-	send_queued(osdc);
 	up_read(&osdc->map_sem);
 }
 
@@ -1462,7 +1411,9 @@ done:
 	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL))
 		ceph_monc_request_next_osdmap(&osdc->client->monc);
 
-	send_queued(osdc);
+	mutex_lock(&osdc->request_mutex);
+	__send_queued(osdc);
+	mutex_unlock(&osdc->request_mutex);
 	up_read(&osdc->map_sem);
 	wake_up_all(&osdc->client->auth_wq);
 	return;
@@ -1556,8 +1507,7 @@ static void __remove_event(struct ceph_osd_event *event)
 
 int ceph_osdc_create_event(struct ceph_osd_client *osdc,
 			   void (*event_cb)(u64, u64, u8, void *),
-			   int one_shot, void *data,
-			   struct ceph_osd_event **pevent)
+			   void *data, struct ceph_osd_event **pevent)
 {
 	struct ceph_osd_event *event;
 
@@ -1567,14 +1517,13 @@ int ceph_osdc_create_event(struct ceph_osd_client *osdc,
 
 	dout("create_event %p\n", event);
 	event->cb = event_cb;
-	event->one_shot = one_shot;
+	event->one_shot = 0;
 	event->data = data;
 	event->osdc = osdc;
 	INIT_LIST_HEAD(&event->osd_node);
 	RB_CLEAR_NODE(&event->node);
 	kref_init(&event->kref);   /* one ref for us */
 	kref_get(&event->kref);    /* one ref for the caller */
-	init_completion(&event->completion);
 
 	spin_lock(&osdc->event_lock);
 	event->cookie = ++osdc->event_count;
@@ -1610,7 +1559,6 @@ static void do_event_work(struct work_struct *work)
 
 	dout("do_event_work completing %p\n", event);
 	event->cb(ver, notify_id, opcode, event->data);
-	complete(&event->completion);
 	dout("do_event_work completed %p\n", event);
 	ceph_osdc_put_event(event);
 	kfree(event_work);
@@ -1620,7 +1568,8 @@ static void do_event_work(struct work_struct *work)
 /*
  * Process osd watch notifications
  */
-void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg)
+static void handle_watch_notify(struct ceph_osd_client *osdc,
+				struct ceph_msg *msg)
 {
 	void *p, *end;
 	u8 proto_ver;
@@ -1641,9 +1590,8 @@ void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 	spin_lock(&osdc->event_lock);
 	event = __find_event(osdc, cookie);
 	if (event) {
+		BUG_ON(event->one_shot);
 		get_event(event);
-		if (event->one_shot)
-			__remove_event(event);
 	}
 	spin_unlock(&osdc->event_lock);
 	dout("handle_watch_notify cookie %lld ver %lld event %p\n",
@@ -1668,7 +1616,6 @@ void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 	return;
 
 done_err:
-	complete(&event->completion);
 	ceph_osdc_put_event(event);
 	return;
 
@@ -1677,21 +1624,6 @@ bad:
 	return;
 }
 
-int ceph_osdc_wait_event(struct ceph_osd_event *event, unsigned long timeout)
-{
-	int err;
-
-	dout("wait_event %p\n", event);
-	err = wait_for_completion_interruptible_timeout(&event->completion,
-							timeout * HZ);
-	ceph_osdc_put_event(event);
-	if (err > 0)
-		err = 0;
-	dout("wait_event %p returns %d\n", event, err);
-	return err;
-}
-EXPORT_SYMBOL(ceph_osdc_wait_event);
-
 /*
  * Register request, send initial attempt.
  */
@@ -1706,7 +1638,7 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,
 #ifdef CONFIG_BLOCK
 	req->r_request->bio = req->r_bio;
 #endif
-	req->r_request->trail = req->r_trail;
+	req->r_request->trail = &req->r_trail;
 
 	register_request(osdc, req);
 
@@ -1865,7 +1797,6 @@ out_mempool:
 out:
 	return err;
 }
-EXPORT_SYMBOL(ceph_osdc_init);
 
 void ceph_osdc_stop(struct ceph_osd_client *osdc)
 {
@@ -1882,7 +1813,6 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc)
 	ceph_msgpool_destroy(&osdc->msgpool_op);
 	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
 }
-EXPORT_SYMBOL(ceph_osdc_stop);
 
 /*
  * Read some contiguous pages.  If we cross a stripe boundary, shorten
@@ -1902,7 +1832,7 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
 	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, page_align);
+				    false, page_align);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -1931,8 +1861,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 			 u64 off, u64 len,
 			 u32 truncate_seq, u64 truncate_size,
 			 struct timespec *mtime,
-			 struct page **pages, int num_pages,
-			 int flags, int do_sync, bool nofail)
+			 struct page **pages, int num_pages)
 {
 	struct ceph_osd_request *req;
 	int rc = 0;
@@ -1941,11 +1870,10 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 	BUG_ON(vino.snap != CEPH_NOSNAP);
 	req = ceph_osdc_new_request(osdc, layout, vino, off, &len,
 				    CEPH_OSD_OP_WRITE,
-				    flags | CEPH_OSD_FLAG_ONDISK |
-					    CEPH_OSD_FLAG_WRITE,
-				    snapc, do_sync,
+				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
+				    snapc, 0,
 				    truncate_seq, truncate_size, mtime,
-				    nofail, 1, page_align);
+				    true, page_align);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -1954,7 +1882,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 	dout("writepages %llu~%llu (%d pages)\n", off, len,
 	     req->r_num_pages);
 
-	rc = ceph_osdc_start_request(osdc, req, nofail);
+	rc = ceph_osdc_start_request(osdc, req, true);
 	if (!rc)
 		rc = ceph_osdc_wait_request(osdc, req);
 
@@ -2047,7 +1975,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	if (data_len > 0) {
 		int want = calc_pages_for(req->r_page_alignment, data_len);
 
-		if (unlikely(req->r_num_pages < want)) {
+		if (req->r_pages && unlikely(req->r_num_pages < want)) {
 			pr_warning("tid %lld reply has %d bytes %d pages, we"
 				   " had only %d pages ready\n", tid, data_len,
 				   want, req->r_num_pages);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index de73214..3c61e216 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -13,26 +13,18 @@
 
 char *ceph_osdmap_state_str(char *str, int len, int state)
 {
-	int flag = 0;
-
 	if (!len)
-		goto done;
-
-	*str = '\0';
-	if (state) {
-		if (state & CEPH_OSD_EXISTS) {
-			snprintf(str, len, "exists");
-			flag = 1;
-		}
-		if (state & CEPH_OSD_UP) {
-			snprintf(str, len, "%s%s%s", str, (flag ? ", " : ""),
-				 "up");
-			flag = 1;
-		}
-	} else {
+		return str;
+
+	if ((state & CEPH_OSD_EXISTS) && (state & CEPH_OSD_UP))
+		snprintf(str, len, "exists, up");
+	else if (state & CEPH_OSD_EXISTS)
+		snprintf(str, len, "exists");
+	else if (state & CEPH_OSD_UP)
+		snprintf(str, len, "up");
+	else
 		snprintf(str, len, "doesn't exist");
-	}
-done:
+
 	return str;
 }
 
@@ -170,6 +162,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
         c->choose_local_tries = 2;
         c->choose_local_fallback_tries = 5;
         c->choose_total_tries = 19;
+	c->chooseleaf_descend_once = 0;
 
 	ceph_decode_need(p, end, 4*sizeof(u32), bad);
 	magic = ceph_decode_32(p);
@@ -336,6 +329,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
         dout("crush decode tunable choose_total_tries = %d",
              c->choose_total_tries);
 
+	ceph_decode_need(p, end, sizeof(u32), done);
+	c->chooseleaf_descend_once = ceph_decode_32(p);
+	dout("crush decode tunable chooseleaf_descend_once = %d",
+	     c->chooseleaf_descend_once);
+
 done:
 	dout("crush_decode success\n");
 	return c;
@@ -1010,7 +1008,7 @@ bad:
  * pass a stride back to the caller.
  */
 int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
-				   u64 off, u64 *plen,
+				   u64 off, u64 len,
 				   u64 *ono,
 				   u64 *oxoff, u64 *oxlen)
 {
@@ -1021,7 +1019,7 @@ int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 	u32 su_per_object;
 	u64 t, su_offset;
 
-	dout("mapping %llu~%llu  osize %u fl_su %u\n", off, *plen,
+	dout("mapping %llu~%llu  osize %u fl_su %u\n", off, len,
 	     osize, su);
 	if (su == 0 || sc == 0)
 		goto invalid;
@@ -1054,11 +1052,10 @@ int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 
 	/*
 	 * Calculate the length of the extent being written to the selected
-	 * object. This is the minimum of the full length requested (plen) or
+	 * object. This is the minimum of the full length requested (len) or
 	 * the remainder of the current stripe being written to.
 	 */
-	*oxlen = min_t(u64, *plen, su - su_offset);
-	*plen = *oxlen;
+	*oxlen = min_t(u64, len, su - su_offset);
 
 	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
 	return 0;
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index cd9c21d..815a224 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -12,7 +12,7 @@
 /*
  * build a vector of user pages
  */
-struct page **ceph_get_direct_page_vector(const char __user *data,
+struct page **ceph_get_direct_page_vector(const void __user *data,
 					  int num_pages, bool write_page)
 {
 	struct page **pages;
@@ -93,7 +93,7 @@ EXPORT_SYMBOL(ceph_alloc_page_vector);
  * copy user data into a page vector
  */
 int ceph_copy_user_to_page_vector(struct page **pages,
-					 const char __user *data,
+					 const void __user *data,
 					 loff_t off, size_t len)
 {
 	int i = 0;
@@ -118,17 +118,17 @@ int ceph_copy_user_to_page_vector(struct page **pages,
 }
 EXPORT_SYMBOL(ceph_copy_user_to_page_vector);
 
-int ceph_copy_to_page_vector(struct page **pages,
-				    const char *data,
+void ceph_copy_to_page_vector(struct page **pages,
+				    const void *data,
 				    loff_t off, size_t len)
 {
 	int i = 0;
 	size_t po = off & ~PAGE_CACHE_MASK;
 	size_t left = len;
-	size_t l;
 
 	while (left > 0) {
-		l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+		size_t l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+
 		memcpy(page_address(pages[i]) + po, data, l);
 		data += l;
 		left -= l;
@@ -138,21 +138,20 @@ int ceph_copy_to_page_vector(struct page **pages,
 			i++;
 		}
 	}
-	return len;
 }
 EXPORT_SYMBOL(ceph_copy_to_page_vector);
 
-int ceph_copy_from_page_vector(struct page **pages,
-				    char *data,
+void ceph_copy_from_page_vector(struct page **pages,
+				    void *data,
 				    loff_t off, size_t len)
 {
 	int i = 0;
 	size_t po = off & ~PAGE_CACHE_MASK;
 	size_t left = len;
-	size_t l;
 
 	while (left > 0) {
-		l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+		size_t l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+
 		memcpy(data, page_address(pages[i]) + po, l);
 		data += l;
 		left -= l;
@@ -162,7 +161,6 @@ int ceph_copy_from_page_vector(struct page **pages,
 			i++;
 		}
 	}
-	return len;
 }
 EXPORT_SYMBOL(ceph_copy_from_page_vector);
 
@@ -170,7 +168,7 @@ EXPORT_SYMBOL(ceph_copy_from_page_vector);
  * copy user data from a page vector into a user pointer
  */
 int ceph_copy_page_vector_to_user(struct page **pages,
-					 char __user *data,
+					 void __user *data,
 					 loff_t off, size_t len)
 {
 	int i = 0;