summary refs log tree commit diff
path: root/net/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'net/ceph')
-rw-r--r--net/ceph/crush/mapper.c33
-rw-r--r--net/ceph/messenger.c15
-rw-r--r--net/ceph/osd_client.c14
-rw-r--r--net/ceph/osdmap.c19
4 files changed, 63 insertions, 18 deletions
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 393bfb22d5bb..5fcfb98f309e 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -403,6 +403,7 @@ static int is_out(const struct crush_map *map,
  * @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)
+ * @stable: stable mode starts rep=0 in the recursive call for all replicas
  * @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
@@ -419,6 +420,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 			       unsigned int local_fallback_retries,
 			       int recurse_to_leaf,
 			       unsigned int vary_r,
+			       unsigned int stable,
 			       int *out2,
 			       int parent_r)
 {
@@ -433,13 +435,13 @@ static int crush_choose_firstn(const struct crush_map *map,
 	int collide, reject;
 	int count = out_size;
 
-	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",
+	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 stable %d\n",
 		recurse_to_leaf ? "_LEAF" : "",
 		bucket->id, x, outpos, numrep,
 		tries, recurse_tries, local_retries, local_fallback_retries,
-		parent_r);
+		parent_r, stable);
 
-	for (rep = outpos; rep < numrep && count > 0 ; rep++) {
+	for (rep = stable ? 0 : outpos; rep < numrep && count > 0 ; rep++) {
 		/* keep trying until we get a non-out, non-colliding item */
 		ftotal = 0;
 		skip_rep = 0;
@@ -512,13 +514,14 @@ static int crush_choose_firstn(const struct crush_map *map,
 						if (crush_choose_firstn(map,
 							 map->buckets[-1-item],
 							 weight, weight_max,
-							 x, outpos+1, 0,
+							 x, stable ? 1 : outpos+1, 0,
 							 out2, outpos, count,
 							 recurse_tries, 0,
 							 local_retries,
 							 local_fallback_retries,
 							 0,
 							 vary_r,
+							 stable,
 							 NULL,
 							 sub_r) <= outpos)
 							/* didn't get leaf */
@@ -816,6 +819,7 @@ int crush_do_rule(const struct crush_map *map,
 	int choose_local_fallback_retries = map->choose_local_fallback_tries;
 
 	int vary_r = map->chooseleaf_vary_r;
+	int stable = map->chooseleaf_stable;
 
 	if ((__u32)ruleno >= map->max_rules) {
 		dprintk(" bad ruleno %d\n", ruleno);
@@ -835,7 +839,8 @@ int crush_do_rule(const struct crush_map *map,
 		case CRUSH_RULE_TAKE:
 			if ((curstep->arg1 >= 0 &&
 			     curstep->arg1 < map->max_devices) ||
-			    (-1-curstep->arg1 < map->max_buckets &&
+			    (-1-curstep->arg1 >= 0 &&
+			     -1-curstep->arg1 < map->max_buckets &&
 			     map->buckets[-1-curstep->arg1])) {
 				w[0] = curstep->arg1;
 				wsize = 1;
@@ -869,6 +874,11 @@ int crush_do_rule(const struct crush_map *map,
 				vary_r = curstep->arg1;
 			break;
 
+		case CRUSH_RULE_SET_CHOOSELEAF_STABLE:
+			if (curstep->arg1 >= 0)
+				stable = curstep->arg1;
+			break;
+
 		case CRUSH_RULE_CHOOSELEAF_FIRSTN:
 		case CRUSH_RULE_CHOOSE_FIRSTN:
 			firstn = 1;
@@ -888,6 +898,7 @@ int crush_do_rule(const struct crush_map *map,
 			osize = 0;
 
 			for (i = 0; i < wsize; i++) {
+				int bno;
 				/*
 				 * see CRUSH_N, CRUSH_N_MINUS macros.
 				 * basically, numrep <= 0 means relative to
@@ -900,6 +911,13 @@ int crush_do_rule(const struct crush_map *map,
 						continue;
 				}
 				j = 0;
+				/* make sure bucket id is valid */
+				bno = -1 - w[i];
+				if (bno < 0 || bno >= map->max_buckets) {
+					/* w[i] is probably CRUSH_ITEM_NONE */
+					dprintk("  bad w[i] %d\n", w[i]);
+					continue;
+				}
 				if (firstn) {
 					int recurse_tries;
 					if (choose_leaf_tries)
@@ -911,7 +929,7 @@ int crush_do_rule(const struct crush_map *map,
 						recurse_tries = choose_tries;
 					osize += crush_choose_firstn(
 						map,
-						map->buckets[-1-w[i]],
+						map->buckets[bno],
 						weight, weight_max,
 						x, numrep,
 						curstep->arg2,
@@ -923,6 +941,7 @@ int crush_do_rule(const struct crush_map *map,
 						choose_local_fallback_retries,
 						recurse_to_leaf,
 						vary_r,
+						stable,
 						c+osize,
 						0);
 				} else {
@@ -930,7 +949,7 @@ int crush_do_rule(const struct crush_map *map,
 						    numrep : (result_max-osize));
 					crush_choose_indep(
 						map,
-						map->buckets[-1-w[i]],
+						map->buckets[bno],
 						weight, weight_max,
 						x, out_size, numrep,
 						curstep->arg2,
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 9cfedf565f5b..9382619a405b 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1197,6 +1197,13 @@ static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
 	return new_piece;
 }
 
+static size_t sizeof_footer(struct ceph_connection *con)
+{
+	return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ?
+	    sizeof(struct ceph_msg_footer) :
+	    sizeof(struct ceph_msg_footer_old);
+}
+
 static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
 {
 	BUG_ON(!msg);
@@ -2335,9 +2342,9 @@ static int read_partial_message(struct ceph_connection *con)
 			ceph_pr_addr(&con->peer_addr.in_addr),
 			seq, con->in_seq + 1);
 		con->in_base_pos = -front_len - middle_len - data_len -
-			sizeof(m->footer);
+			sizeof_footer(con);
 		con->in_tag = CEPH_MSGR_TAG_READY;
-		return 0;
+		return 1;
 	} else if ((s64)seq - (s64)con->in_seq > 1) {
 		pr_err("read_partial_message bad seq %lld expected %lld\n",
 		       seq, con->in_seq + 1);
@@ -2360,10 +2367,10 @@ static int read_partial_message(struct ceph_connection *con)
 			/* skip this message */
 			dout("alloc_msg said skip message\n");
 			con->in_base_pos = -front_len - middle_len - data_len -
-				sizeof(m->footer);
+				sizeof_footer(con);
 			con->in_tag = CEPH_MSGR_TAG_READY;
 			con->in_seq++;
-			return 0;
+			return 1;
 		}
 
 		BUG_ON(!con->in_msg);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index f8f235930d88..5bc053778fed 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1770,6 +1770,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 	u32 osdmap_epoch;
 	int already_completed;
 	u32 bytes;
+	u8 decode_redir;
 	unsigned int i;
 
 	tid = le64_to_cpu(msg->hdr.tid);
@@ -1841,6 +1842,15 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 		p += 8 + 4; /* skip replay_version */
 		p += 8; /* skip user_version */
 
+		if (le16_to_cpu(msg->hdr.version) >= 7)
+			ceph_decode_8_safe(&p, end, decode_redir, bad_put);
+		else
+			decode_redir = 1;
+	} else {
+		decode_redir = 0;
+	}
+
+	if (decode_redir) {
 		err = ceph_redirect_decode(&p, end, &redir);
 		if (err)
 			goto bad_put;
@@ -2843,8 +2853,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	mutex_lock(&osdc->request_mutex);
 	req = __lookup_request(osdc, tid);
 	if (!req) {
-		pr_warn("%s osd%d tid %llu unknown, skipping\n",
-			__func__, osd->o_osd, tid);
+		dout("%s osd%d tid %llu unknown, skipping\n", __func__,
+		     osd->o_osd, tid);
 		m = NULL;
 		*skip = 1;
 		goto out;
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 7d8f581d9f1f..243574c8cf33 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -342,23 +342,32 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
         c->choose_local_tries = ceph_decode_32(p);
         c->choose_local_fallback_tries =  ceph_decode_32(p);
         c->choose_total_tries = ceph_decode_32(p);
-        dout("crush decode tunable choose_local_tries = %d",
+        dout("crush decode tunable choose_local_tries = %d\n",
              c->choose_local_tries);
-        dout("crush decode tunable choose_local_fallback_tries = %d",
+        dout("crush decode tunable choose_local_fallback_tries = %d\n",
              c->choose_local_fallback_tries);
-        dout("crush decode tunable choose_total_tries = %d",
+        dout("crush decode tunable choose_total_tries = %d\n",
              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",
+	dout("crush decode tunable chooseleaf_descend_once = %d\n",
 	     c->chooseleaf_descend_once);
 
 	ceph_decode_need(p, end, sizeof(u8), done);
 	c->chooseleaf_vary_r = ceph_decode_8(p);
-	dout("crush decode tunable chooseleaf_vary_r = %d",
+	dout("crush decode tunable chooseleaf_vary_r = %d\n",
 	     c->chooseleaf_vary_r);
 
+	/* skip straw_calc_version, allowed_bucket_algs */
+	ceph_decode_need(p, end, sizeof(u8) + sizeof(u32), done);
+	*p += sizeof(u8) + sizeof(u32);
+
+	ceph_decode_need(p, end, sizeof(u8), done);
+	c->chooseleaf_stable = ceph_decode_8(p);
+	dout("crush decode tunable chooseleaf_stable = %d\n",
+	     c->chooseleaf_stable);
+
 done:
 	dout("crush_decode success\n");
 	return c;
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-10-15 19:31:11 +0000