18 files changed, 1036 insertions, 504 deletions
diff --git a/net/Kconfig b/net/Kconfig
index d1f6f968fc0..d92afe4204d 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -243,7 +243,7 @@ config XPS
 	default y
 
 config CGROUP_NET_PRIO
-	tristate "Network priority cgroup"
+	bool "Network priority cgroup"
 	depends on CGROUPS
 	---help---
 	  Cgroup subsystem for use in assigning processes to network priorities on
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index b703790b4e4..a1ef53c0441 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -292,10 +292,12 @@ static int is_out(const struct crush_map *map,
  * @outpos: our position in that vector
  * @tries: number of attempts to make
  * @recurse_tries: number of attempts to have recursive chooseleaf make
- * @local_tries: localized retries
- * @local_fallback_tries: localized fallback retries
+ * @local_retries: localized retries
+ * @local_fallback_retries: localized fallback retries
  * @recurse_to_leaf: true if we want one device under each item of given type (chooseleaf instead of choose)
+ * @vary_r: pass r to recursive calls
  * @out2: second output vector for leaf items (if @recurse_to_leaf)
+ * @parent_r: r value passed from the parent
  */
 static int crush_choose_firstn(const struct crush_map *map,
 			       struct crush_bucket *bucket,
@@ -304,10 +306,12 @@ static int crush_choose_firstn(const struct crush_map *map,
 			       int *out, int outpos,
 			       unsigned int tries,
 			       unsigned int recurse_tries,
-			       unsigned int local_tries,
-			       unsigned int local_fallback_tries,
+			       unsigned int local_retries,
+			       unsigned int local_fallback_retries,
 			       int recurse_to_leaf,
-			       int *out2)
+			       unsigned int vary_r,
+			       int *out2,
+			       int parent_r)
 {
 	int rep;
 	unsigned int ftotal, flocal;
@@ -319,8 +323,11 @@ static int crush_choose_firstn(const struct crush_map *map,
 	int itemtype;
 	int collide, reject;
 
-	dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "",
-		bucket->id, x, outpos, numrep);
+	dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d\n",
+		recurse_to_leaf ? "_LEAF" : "",
+		bucket->id, x, outpos, numrep,
+		tries, recurse_tries, local_retries, local_fallback_retries,
+		parent_r);
 
 	for (rep = outpos; rep < numrep; rep++) {
 		/* keep trying until we get a non-out, non-colliding item */
@@ -335,7 +342,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 			do {
 				collide = 0;
 				retry_bucket = 0;
-				r = rep;
+				r = rep + parent_r;
 				/* r' = r + f_total */
 				r += ftotal;
 
@@ -344,9 +351,9 @@ static int crush_choose_firstn(const struct crush_map *map,
 					reject = 1;
 					goto reject;
 				}
-				if (local_fallback_tries > 0 &&
+				if (local_fallback_retries > 0 &&
 				    flocal >= (in->size>>1) &&
-				    flocal > local_fallback_tries)
+				    flocal > local_fallback_retries)
 					item = bucket_perm_choose(in, x, r);
 				else
 					item = crush_bucket_choose(in, x, r);
@@ -387,16 +394,23 @@ static int crush_choose_firstn(const struct crush_map *map,
 				reject = 0;
 				if (!collide && recurse_to_leaf) {
 					if (item < 0) {
+						int sub_r;
+						if (vary_r)
+							sub_r = r >> (vary_r-1);
+						else
+							sub_r = 0;
 						if (crush_choose_firstn(map,
 							 map->buckets[-1-item],
 							 weight, weight_max,
 							 x, outpos+1, 0,
 							 out2, outpos,
 							 recurse_tries, 0,
-							 local_tries,
-							 local_fallback_tries,
+							 local_retries,
+							 local_fallback_retries,
 							 0,
-							 NULL) <= outpos)
+							 vary_r,
+							 NULL,
+							 sub_r) <= outpos)
 							/* didn't get leaf */
 							reject = 1;
 					} else {
@@ -420,14 +434,14 @@ reject:
 					ftotal++;
 					flocal++;
 
-					if (collide && flocal <= local_tries)
+					if (collide && flocal <= local_retries)
 						/* retry locally a few times */
 						retry_bucket = 1;
-					else if (local_fallback_tries > 0 &&
-						 flocal <= in->size + local_fallback_tries)
+					else if (local_fallback_retries > 0 &&
+						 flocal <= in->size + local_fallback_retries)
 						/* exhaustive bucket search */
 						retry_bucket = 1;
-					else if (ftotal <= tries)
+					else if (ftotal < tries)
 						/* then retry descent */
 						retry_descent = 1;
 					else
@@ -640,10 +654,20 @@ int crush_do_rule(const struct crush_map *map,
 	__u32 step;
 	int i, j;
 	int numrep;
-	int choose_tries = map->choose_total_tries;
-	int choose_local_tries = map->choose_local_tries;
-	int choose_local_fallback_tries = map->choose_local_fallback_tries;
+	/*
+	 * the original choose_total_tries value was off by one (it
+	 * counted "retries" and not "tries").  add one.
+	 */
+	int choose_tries = map->choose_total_tries + 1;
 	int choose_leaf_tries = 0;
+	/*
+	 * the local tries values were counted as "retries", though,
+	 * and need no adjustment
+	 */
+	int choose_local_retries = map->choose_local_tries;
+	int choose_local_fallback_retries = map->choose_local_fallback_tries;
+
+	int vary_r = map->chooseleaf_vary_r;
 
 	if ((__u32)ruleno >= map->max_rules) {
 		dprintk(" bad ruleno %d\n", ruleno);
@@ -676,13 +700,18 @@ int crush_do_rule(const struct crush_map *map,
 			break;
 
 		case CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES:
-			if (curstep->arg1 > 0)
-				choose_local_tries = curstep->arg1;
+			if (curstep->arg1 >= 0)
+				choose_local_retries = curstep->arg1;
 			break;
 
 		case CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES:
-			if (curstep->arg1 > 0)
-				choose_local_fallback_tries = curstep->arg1;
+			if (curstep->arg1 >= 0)
+				choose_local_fallback_retries = curstep->arg1;
+			break;
+
+		case CRUSH_RULE_SET_CHOOSELEAF_VARY_R:
+			if (curstep->arg1 >= 0)
+				vary_r = curstep->arg1;
 			break;
 
 		case CRUSH_RULE_CHOOSELEAF_FIRSTN:
@@ -734,10 +763,12 @@ int crush_do_rule(const struct crush_map *map,
 						o+osize, j,
 						choose_tries,
 						recurse_tries,
-						choose_local_tries,
-						choose_local_fallback_tries,
+						choose_local_retries,
+						choose_local_fallback_retries,
 						recurse_to_leaf,
-						c+osize);
+						vary_r,
+						c+osize,
+						0);
 				} else {
 					crush_choose_indep(
 						map,
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 258a382e75e..10421a4b76f 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -53,34 +53,55 @@ static int osdmap_show(struct seq_file *s, void *p)
 {
 	int i;
 	struct ceph_client *client = s->private;
+	struct ceph_osdmap *map = client->osdc.osdmap;
 	struct rb_node *n;
 
-	if (client->osdc.osdmap == NULL)
+	if (map == NULL)
 		return 0;
-	seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch);
+
+	seq_printf(s, "epoch %d\n", map->epoch);
 	seq_printf(s, "flags%s%s\n",
-		   (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ?
-		   " NEARFULL" : "",
-		   (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ?
-		   " FULL" : "");
-	for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) {
+		   (map->flags & CEPH_OSDMAP_NEARFULL) ?  " NEARFULL" : "",
+		   (map->flags & CEPH_OSDMAP_FULL) ?  " FULL" : "");
+
+	for (n = rb_first(&map->pg_pools); n; n = rb_next(n)) {
 		struct ceph_pg_pool_info *pool =
 			rb_entry(n, struct ceph_pg_pool_info, node);
-		seq_printf(s, "pg_pool %llu pg_num %d / %d\n",
-			   (unsigned long long)pool->id, pool->pg_num,
-			   pool->pg_num_mask);
+
+		seq_printf(s, "pool %lld pg_num %u (%d) read_tier %lld write_tier %lld\n",
+			   pool->id, pool->pg_num, pool->pg_num_mask,
+			   pool->read_tier, pool->write_tier);
 	}
-	for (i = 0; i < client->osdc.osdmap->max_osd; i++) {
-		struct ceph_entity_addr *addr =
-			&client->osdc.osdmap->osd_addr[i];
-		int state = client->osdc.osdmap->osd_state[i];
+	for (i = 0; i < map->max_osd; i++) {
+		struct ceph_entity_addr *addr = &map->osd_addr[i];
+		int state = map->osd_state[i];
 		char sb[64];
 
-		seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n",
+		seq_printf(s, "osd%d\t%s\t%3d%%\t(%s)\t%3d%%\n",
 			   i, ceph_pr_addr(&addr->in_addr),
-			   ((client->osdc.osdmap->osd_weight[i]*100) >> 16),
-			   ceph_osdmap_state_str(sb, sizeof(sb), state));
+			   ((map->osd_weight[i]*100) >> 16),
+			   ceph_osdmap_state_str(sb, sizeof(sb), state),
+			   ((ceph_get_primary_affinity(map, i)*100) >> 16));
+	}
+	for (n = rb_first(&map->pg_temp); n; n = rb_next(n)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(n, struct ceph_pg_mapping, node);
+
+		seq_printf(s, "pg_temp %llu.%x [", pg->pgid.pool,
+			   pg->pgid.seed);
+		for (i = 0; i < pg->pg_temp.len; i++)
+			seq_printf(s, "%s%d", (i == 0 ? "" : ","),
+				   pg->pg_temp.osds[i]);
+		seq_printf(s, "]\n");
 	}
+	for (n = rb_first(&map->primary_temp); n; n = rb_next(n)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(n, struct ceph_pg_mapping, node);
+
+		seq_printf(s, "primary_temp %llu.%x %d\n", pg->pgid.pool,
+			   pg->pgid.seed, pg->primary_temp.osd);
+	}
+
 	return 0;
 }
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 30efc5c1862..4f55f9ce63f 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -919,6 +919,9 @@ static bool ceph_msg_data_pages_advance(struct ceph_msg_data_cursor *cursor,
 	if (!bytes || cursor->page_offset)
 		return false;	/* more bytes to process in the current page */
 
+	if (!cursor->resid)
+		return false;   /* no more data */
+
 	/* Move on to the next page; offset is already at 0 */
 
 	BUG_ON(cursor->page_index >= cursor->page_count);
@@ -1004,6 +1007,9 @@ static bool ceph_msg_data_pagelist_advance(struct ceph_msg_data_cursor *cursor,
 	if (!bytes || cursor->offset & ~PAGE_MASK)
 		return false;	/* more bytes to process in the current page */
 
+	if (!cursor->resid)
+		return false;   /* no more data */
+
 	/* Move on to the next page */
 
 	BUG_ON(list_is_last(&cursor->page->lru, &pagelist->head));
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 82750f91586..b0dfce77656 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -436,6 +436,7 @@ static bool osd_req_opcode_valid(u16 opcode)
 	case CEPH_OSD_OP_OMAPCLEAR:
 	case CEPH_OSD_OP_OMAPRMKEYS:
 	case CEPH_OSD_OP_OMAP_CMP:
+	case CEPH_OSD_OP_SETALLOCHINT:
 	case CEPH_OSD_OP_CLONERANGE:
 	case CEPH_OSD_OP_ASSERT_SRC_VERSION:
 	case CEPH_OSD_OP_SRC_CMPXATTR:
@@ -591,6 +592,26 @@ void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
 }
 EXPORT_SYMBOL(osd_req_op_watch_init);
 
+void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
+				unsigned int which,
+				u64 expected_object_size,
+				u64 expected_write_size)
+{
+	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
+						      CEPH_OSD_OP_SETALLOCHINT);
+
+	op->alloc_hint.expected_object_size = expected_object_size;
+	op->alloc_hint.expected_write_size = expected_write_size;
+
+	/*
+	 * CEPH_OSD_OP_SETALLOCHINT op is advisory and therefore deemed
+	 * not worth a feature bit.  Set FAILOK per-op flag to make
+	 * sure older osds don't trip over an unsupported opcode.
+	 */
+	op->flags |= CEPH_OSD_OP_FLAG_FAILOK;
+}
+EXPORT_SYMBOL(osd_req_op_alloc_hint_init);
+
 static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
 				struct ceph_osd_data *osd_data)
 {
@@ -681,6 +702,12 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 		dst->watch.ver = cpu_to_le64(src->watch.ver);
 		dst->watch.flag = src->watch.flag;
 		break;
+	case CEPH_OSD_OP_SETALLOCHINT:
+		dst->alloc_hint.expected_object_size =
+		    cpu_to_le64(src->alloc_hint.expected_object_size);
+		dst->alloc_hint.expected_write_size =
+		    cpu_to_le64(src->alloc_hint.expected_write_size);
+		break;
 	default:
 		pr_err("unsupported osd opcode %s\n",
 			ceph_osd_op_name(src->op));
@@ -688,7 +715,9 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 
 		return 0;
 	}
+
 	dst->op = cpu_to_le16(src->op);
+	dst->flags = cpu_to_le32(src->flags);
 	dst->payload_len = cpu_to_le32(src->payload_len);
 
 	return request_data_len;
@@ -1304,7 +1333,7 @@ static int __map_request(struct ceph_osd_client *osdc,
 {
 	struct ceph_pg pgid;
 	int acting[CEPH_PG_MAX_SIZE];
-	int o = -1, num = 0;
+	int num, o;
 	int err;
 	bool was_paused;
 
@@ -1317,11 +1346,9 @@ static int __map_request(struct ceph_osd_client *osdc,
 	}
 	req->r_pgid = pgid;
 
-	err = ceph_calc_pg_acting(osdc->osdmap, pgid, acting);
-	if (err > 0) {
-		o = acting[0];
-		num = err;
-	}
+	num = ceph_calc_pg_acting(osdc->osdmap, pgid, acting, &o);
+	if (num < 0)
+		num = 0;
 
 	was_paused = req->r_paused;
 	req->r_paused = __req_should_be_paused(osdc, req);
@@ -2033,7 +2060,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 			int skipped_map = 0;
 
 			dout("taking full map %u len %d\n", epoch, maplen);
-			newmap = osdmap_decode(&p, p+maplen);
+			newmap = ceph_osdmap_decode(&p, p+maplen);
 			if (IS_ERR(newmap)) {
 				err = PTR_ERR(newmap);
 				goto bad;
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index aade4a5c1c0..e632b5a52f5 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -343,7 +343,7 @@ bad:
 
 /*
  * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
- * to a set of osds)
+ * to a set of osds) and primary_temp (explicit primary setting)
  */
 static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
 {
@@ -506,7 +506,7 @@ static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
 	kfree(pi);
 }
 
-static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
+static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
 {
 	u8 ev, cv;
 	unsigned len, num;
@@ -587,7 +587,7 @@ bad:
 	return -EINVAL;
 }
 
-static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
+static int decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
 {
 	struct ceph_pg_pool_info *pi;
 	u32 num, len;
@@ -633,6 +633,13 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
 		rb_erase(&pg->node, &map->pg_temp);
 		kfree(pg);
 	}
+	while (!RB_EMPTY_ROOT(&map->primary_temp)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(rb_first(&map->primary_temp),
+				 struct ceph_pg_mapping, node);
+		rb_erase(&pg->node, &map->primary_temp);
+		kfree(pg);
+	}
 	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
 		struct ceph_pg_pool_info *pi =
 			rb_entry(rb_first(&map->pg_pools),
@@ -642,186 +649,516 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
 	kfree(map->osd_state);
 	kfree(map->osd_weight);
 	kfree(map->osd_addr);
+	kfree(map->osd_primary_affinity);
 	kfree(map);
 }
 
 /*
- * adjust max osd value.  reallocate arrays.
+ * Adjust max_osd value, (re)allocate arrays.
+ *
+ * The new elements are properly initialized.
  */
 static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
 {
 	u8 *state;
-	struct ceph_entity_addr *addr;
 	u32 *weight;
+	struct ceph_entity_addr *addr;
+	int i;
 
-	state = kcalloc(max, sizeof(*state), GFP_NOFS);
-	addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
-	weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
-	if (state == NULL || addr == NULL || weight == NULL) {
+	state = krealloc(map->osd_state, max*sizeof(*state), GFP_NOFS);
+	weight = krealloc(map->osd_weight, max*sizeof(*weight), GFP_NOFS);
+	addr = krealloc(map->osd_addr, max*sizeof(*addr), GFP_NOFS);
+	if (!state || !weight || !addr) {
 		kfree(state);
-		kfree(addr);
 		kfree(weight);
+		kfree(addr);
+
 		return -ENOMEM;
 	}
 
-	/* copy old? */
-	if (map->osd_state) {
-		memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
-		memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
-		memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
-		kfree(map->osd_state);
-		kfree(map->osd_addr);
-		kfree(map->osd_weight);
+	for (i = map->max_osd; i < max; i++) {
+		state[i] = 0;
+		weight[i] = CEPH_OSD_OUT;
+		memset(addr + i, 0, sizeof(*addr));
 	}
 
 	map->osd_state = state;
 	map->osd_weight = weight;
 	map->osd_addr = addr;
+
+	if (map->osd_primary_affinity) {
+		u32 *affinity;
+
+		affinity = krealloc(map->osd_primary_affinity,
+				    max*sizeof(*affinity), GFP_NOFS);
+		if (!affinity)
+			return -ENOMEM;
+
+		for (i = map->max_osd; i < max; i++)
+			affinity[i] = CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+
+		map->osd_primary_affinity = affinity;
+	}
+
 	map->max_osd = max;
+
 	return 0;
 }
 
+#define OSDMAP_WRAPPER_COMPAT_VER	7
+#define OSDMAP_CLIENT_DATA_COMPAT_VER	1
+
 /*
- * decode a full map.
+ * Return 0 or error.  On success, *v is set to 0 for old (v6) osdmaps,
+ * to struct_v of the client_data section for new (v7 and above)
+ * osdmaps.
  */
-struct ceph_osdmap *osdmap_decode(void **p, void *end)
+static int get_osdmap_client_data_v(void **p, void *end,
+				    const char *prefix, u8 *v)
 {
-	struct ceph_osdmap *map;
-	u16 version;
-	u32 len, max, i;
-	int err = -EINVAL;
-	void *start = *p;
-	struct ceph_pg_pool_info *pi;
+	u8 struct_v;
+
+	ceph_decode_8_safe(p, end, struct_v, e_inval);
+	if (struct_v >= 7) {
+		u8 struct_compat;
+
+		ceph_decode_8_safe(p, end, struct_compat, e_inval);
+		if (struct_compat > OSDMAP_WRAPPER_COMPAT_VER) {
+			pr_warning("got v %d cv %d > %d of %s ceph_osdmap\n",
+				   struct_v, struct_compat,
+				   OSDMAP_WRAPPER_COMPAT_VER, prefix);
+			return -EINVAL;
+		}
+		*p += 4; /* ignore wrapper struct_len */
+
+		ceph_decode_8_safe(p, end, struct_v, e_inval);
+		ceph_decode_8_safe(p, end, struct_compat, e_inval);
+		if (struct_compat > OSDMAP_CLIENT_DATA_COMPAT_VER) {
+			pr_warning("got v %d cv %d > %d of %s ceph_osdmap client data\n",
+				   struct_v, struct_compat,
+				   OSDMAP_CLIENT_DATA_COMPAT_VER, prefix);
+			return -EINVAL;
+		}
+		*p += 4; /* ignore client data struct_len */
+	} else {
+		u16 version;
+
+		*p -= 1;
+		ceph_decode_16_safe(p, end, version, e_inval);
+		if (version < 6) {
+			pr_warning("got v %d < 6 of %s ceph_osdmap\n", version,
+				   prefix);
+			return -EINVAL;
+		}
 
-	dout("osdmap_decode %p to %p len %d\n", *p, end, (int)(end - *p));
+		/* old osdmap enconding */
+		struct_v = 0;
+	}
 
-	map = kzalloc(sizeof(*map), GFP_NOFS);
-	if (map == NULL)
-		return ERR_PTR(-ENOMEM);
-	map->pg_temp = RB_ROOT;
+	*v = struct_v;
+	return 0;
 
-	ceph_decode_16_safe(p, end, version, bad);
-	if (version > 6) {
-		pr_warning("got unknown v %d > 6 of osdmap\n", version);
-		goto bad;
+e_inval:
+	return -EINVAL;
+}
+
+static int __decode_pools(void **p, void *end, struct ceph_osdmap *map,
+			  bool incremental)
+{
+	u32 n;
+
+	ceph_decode_32_safe(p, end, n, e_inval);
+	while (n--) {
+		struct ceph_pg_pool_info *pi;
+		u64 pool;
+		int ret;
+
+		ceph_decode_64_safe(p, end, pool, e_inval);
+
+		pi = __lookup_pg_pool(&map->pg_pools, pool);
+		if (!incremental || !pi) {
+			pi = kzalloc(sizeof(*pi), GFP_NOFS);
+			if (!pi)
+				return -ENOMEM;
+
+			pi->id = pool;
+
+			ret = __insert_pg_pool(&map->pg_pools, pi);
+			if (ret) {
+				kfree(pi);
+				return ret;
+			}
+		}
+
+		ret = decode_pool(p, end, pi);
+		if (ret)
+			return ret;
 	}
-	if (version < 6) {
-		pr_warning("got old v %d < 6 of osdmap\n", version);
-		goto bad;
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int decode_pools(void **p, void *end, struct ceph_osdmap *map)
+{
+	return __decode_pools(p, end, map, false);
+}
+
+static int decode_new_pools(void **p, void *end, struct ceph_osdmap *map)
+{
+	return __decode_pools(p, end, map, true);
+}
+
+static int __decode_pg_temp(void **p, void *end, struct ceph_osdmap *map,
+			    bool incremental)
+{
+	u32 n;
+
+	ceph_decode_32_safe(p, end, n, e_inval);
+	while (n--) {
+		struct ceph_pg pgid;
+		u32 len, i;
+		int ret;
+
+		ret = ceph_decode_pgid(p, end, &pgid);
+		if (ret)
+			return ret;
+
+		ceph_decode_32_safe(p, end, len, e_inval);
+
+		ret = __remove_pg_mapping(&map->pg_temp, pgid);
+		BUG_ON(!incremental && ret != -ENOENT);
+
+		if (!incremental || len > 0) {
+			struct ceph_pg_mapping *pg;
+
+			ceph_decode_need(p, end, len*sizeof(u32), e_inval);
+
+			if (len > (UINT_MAX - sizeof(*pg)) / sizeof(u32))
+				return -EINVAL;
+
+			pg = kzalloc(sizeof(*pg) + len*sizeof(u32), GFP_NOFS);
+			if (!pg)
+				return -ENOMEM;
+
+			pg->pgid = pgid;
+			pg->pg_temp.len = len;
+			for (i = 0; i < len; i++)
+				pg->pg_temp.osds[i] = ceph_decode_32(p);
+
+			ret = __insert_pg_mapping(pg, &map->pg_temp);
+			if (ret) {
+				kfree(pg);
+				return ret;
+			}
+		}
 	}
 
-	ceph_decode_need(p, end, 2*sizeof(u64)+6*sizeof(u32), bad);
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int decode_pg_temp(void **p, void *end, struct ceph_osdmap *map)
+{
+	return __decode_pg_temp(p, end, map, false);
+}
+
+static int decode_new_pg_temp(void **p, void *end, struct ceph_osdmap *map)
+{
+	return __decode_pg_temp(p, end, map, true);
+}
+
+static int __decode_primary_temp(void **p, void *end, struct ceph_osdmap *map,
+				 bool incremental)
+{
+	u32 n;
+
+	ceph_decode_32_safe(p, end, n, e_inval);
+	while (n--) {
+		struct ceph_pg pgid;
+		u32 osd;
+		int ret;
+
+		ret = ceph_decode_pgid(p, end, &pgid);
+		if (ret)
+			return ret;
+
+		ceph_decode_32_safe(p, end, osd, e_inval);
+
+		ret = __remove_pg_mapping(&map->primary_temp, pgid);
+		BUG_ON(!incremental && ret != -ENOENT);
+
+		if (!incremental || osd != (u32)-1) {
+			struct ceph_pg_mapping *pg;
+
+			pg = kzalloc(sizeof(*pg), GFP_NOFS);
+			if (!pg)
+				return -ENOMEM;
+
+			pg->pgid = pgid;
+			pg->primary_temp.osd = osd;
+
+			ret = __insert_pg_mapping(pg, &map->primary_temp);
+			if (ret) {
+				kfree(pg);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int decode_primary_temp(void **p, void *end, struct ceph_osdmap *map)
+{
+	return __decode_primary_temp(p, end, map, false);
+}
+
+static int decode_new_primary_temp(void **p, void *end,
+				   struct ceph_osdmap *map)
+{
+	return __decode_primary_temp(p, end, map, true);
+}
+
+u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd)
+{
+	BUG_ON(osd >= map->max_osd);
+
+	if (!map->osd_primary_affinity)
+		return CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+
+	return map->osd_primary_affinity[osd];
+}
+
+static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff)
+{
+	BUG_ON(osd >= map->max_osd);
+
+	if (!map->osd_primary_affinity) {
+		int i;
+
+		map->osd_primary_affinity = kmalloc(map->max_osd*sizeof(u32),
+						    GFP_NOFS);
+		if (!map->osd_primary_affinity)
+			return -ENOMEM;
+
+		for (i = 0; i < map->max_osd; i++)
+			map->osd_primary_affinity[i] =
+			    CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+	}
+
+	map->osd_primary_affinity[osd] = aff;
+
+	return 0;
+}
+
+static int decode_primary_affinity(void **p, void *end,
+				   struct ceph_osdmap *map)
+{
+	u32 len, i;
+
+	ceph_decode_32_safe(p, end, len, e_inval);
+	if (len == 0) {
+		kfree(map->osd_primary_affinity);
+		map->osd_primary_affinity = NULL;
+		return 0;
+	}
+	if (len != map->max_osd)
+		goto e_inval;
+
+	ceph_decode_need(p, end, map->max_osd*sizeof(u32), e_inval);
+
+	for (i = 0; i < map->max_osd; i++) {
+		int ret;
+
+		ret = set_primary_affinity(map, i, ceph_decode_32(p));
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int decode_new_primary_affinity(void **p, void *end,
+				       struct ceph_osdmap *map)
+{
+	u32 n;
+
+	ceph_decode_32_safe(p, end, n, e_inval);
+	while (n--) {
+		u32 osd, aff;
+		int ret;
+
+		ceph_decode_32_safe(p, end, osd, e_inval);
+		ceph_decode_32_safe(p, end, aff, e_inval);
+
+		ret = set_primary_affinity(map, osd, aff);
+		if (ret)
+			return ret;
+
+		pr_info("osd%d primary-affinity 0x%x\n", osd, aff);
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+/*
+ * decode a full map.
+ */
+static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
+{
+	u8 struct_v;
+	u32 epoch = 0;
+	void *start = *p;
+	u32 max;
+	u32 len, i;
+	int err;
+
+	dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p));
+
+	err = get_osdmap_client_data_v(p, end, "full", &struct_v);
+	if (err)
+		goto bad;
+
+	/* fsid, epoch, created, modified */
+	ceph_decode_need(p, end, sizeof(map->fsid) + sizeof(u32) +
+			 sizeof(map->created) + sizeof(map->modified), e_inval);
 	ceph_decode_copy(p, &map->fsid, sizeof(map->fsid));
-	map->epoch = ceph_decode_32(p);
+	epoch = map->epoch = ceph_decode_32(p);
 	ceph_decode_copy(p, &map->created, sizeof(map->created));
 	ceph_decode_copy(p, &map->modified, sizeof(map->modified));
 
-	ceph_decode_32_safe(p, end, max, bad);
-	while (max--) {
-		ceph_decode_need(p, end, 8 + 2, bad);
-		err = -ENOMEM;
-		pi = kzalloc(sizeof(*pi), GFP_NOFS);
-		if (!pi)
-			goto bad;
-		pi->id = ceph_decode_64(p);
-		err = __decode_pool(p, end, pi);
-		if (err < 0) {
-			kfree(pi);
-			goto bad;
-		}
-		__insert_pg_pool(&map->pg_pools, pi);
-	}
+	/* pools */
+	err = decode_pools(p, end, map);
+	if (err)
+		goto bad;
 
-	err = __decode_pool_names(p, end, map);
-	if (err < 0) {
-		dout("fail to decode pool names");
+	/* pool_name */
+	err = decode_pool_names(p, end, map);
+	if (err)
 		goto bad;
-	}
 
-	ceph_decode_32_safe(p, end, map->pool_max, bad);
+	ceph_decode_32_safe(p, end, map->pool_max, e_inval);
 
-	ceph_decode_32_safe(p, end, map->flags, bad);
+	ceph_decode_32_safe(p, end, map->flags, e_inval);
 
-	max = ceph_decode_32(p);
+	/* max_osd */
+	ceph_decode_32_safe(p, end, max, e_inval);
 
 	/* (re)alloc osd arrays */
 	err = osdmap_set_max_osd(map, max);
-	if (err < 0)
+	if (err)
 		goto bad;
-	dout("osdmap_decode max_osd = %d\n", map->max_osd);
 
-	/* osds */
-	err = -EINVAL;
+	/* osd_state, osd_weight, osd_addrs->client_addr */
 	ceph_decode_need(p, end, 3*sizeof(u32) +
 			 map->max_osd*(1 + sizeof(*map->osd_weight) +
-				       sizeof(*map->osd_addr)), bad);
-	*p += 4; /* skip length field (should match max) */
+				       sizeof(*map->osd_addr)), e_inval);
+
+	if (ceph_decode_32(p) != map->max_osd)
+		goto e_inval;
+
 	ceph_decode_copy(p, map->osd_state, map->max_osd);
 
-	*p += 4; /* skip length field (should match max) */
+	if (ceph_decode_32(p) != map->max_osd)
+		goto e_inval;
+
 	for (i = 0; i < map->max_osd; i++)
 		map->osd_weight[i] = ceph_decode_32(p);
 
-	*p += 4; /* skip length field (should match max) */
+	if (ceph_decode_32(p) != map->max_osd)
+		goto e_inval;
+
 	ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr));
 	for (i = 0; i < map->max_osd; i++)
 		ceph_decode_addr(&map->osd_addr[i]);
 
 	/* pg_temp */
-	ceph_decode_32_safe(p, end, len, bad);
-	for (i = 0; i < len; i++) {
-		int n, j;
-		struct ceph_pg pgid;
-		struct ceph_pg_mapping *pg;
+	err = decode_pg_temp(p, end, map);
+	if (err)
+		goto bad;
 
-		err = ceph_decode_pgid(p, end, &pgid);
+	/* primary_temp */
+	if (struct_v >= 1) {
+		err = decode_primary_temp(p, end, map);
 		if (err)
 			goto bad;
-		ceph_decode_need(p, end, sizeof(u32), bad);
-		n = ceph_decode_32(p);
-		err = -EINVAL;
-		if (n > (UINT_MAX - sizeof(*pg)) / sizeof(u32))
-			goto bad;
-		ceph_decode_need(p, end, n * sizeof(u32), bad);
-		err = -ENOMEM;
-		pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS);
-		if (!pg)
-			goto bad;
-		pg->pgid = pgid;
-		pg->len = n;
-		for (j = 0; j < n; j++)
-			pg->osds[j] = ceph_decode_32(p);
+	}
 
-		err = __insert_pg_mapping(pg, &map->pg_temp);
+	/* primary_affinity */
+	if (struct_v >= 2) {
+		err = decode_primary_affinity(p, end, map);
 		if (err)
 			goto bad;
-		dout(" added pg_temp %lld.%x len %d\n", pgid.pool, pgid.seed,
-		     len);
+	} else {
+		/* XXX can this happen? */
+		kfree(map->osd_primary_affinity);
+		map->osd_primary_affinity = NULL;
 	}
 
 	/* crush */
-	ceph_decode_32_safe(p, end, len, bad);
-	dout("osdmap_decode crush len %d from off 0x%x\n", len,
-	     (int)(*p - start));
-	ceph_decode_need(p, end, len, bad);
-	map->crush = crush_decode(*p, end);
-	*p += len;
+	ceph_decode_32_safe(p, end, len, e_inval);
+	map->crush = crush_decode(*p, min(*p + len, end));
 	if (IS_ERR(map->crush)) {
 		err = PTR_ERR(map->crush);
 		map->crush = NULL;
 		goto bad;
 	}
+	*p += len;
 
-	/* ignore the rest of the map */
+	/* ignore the rest */
 	*p = end;
 
-	dout("osdmap_decode done %p %p\n", *p, end);
-	return map;
+	dout("full osdmap epoch %d max_osd %d\n",