X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lnet%2Flnet%2Fnet_fault.c;h=98f9b314c5de5f46fdbb900f60eb3671b41c76e9;hp=56365fd6c148aa03c5368fc2339f8f433dcfce05;hb=3b760208109b249fd9051d97dbc98664ca4b5769;hpb=d02659db163e65ed1c00a96d6d098069b449dfaf

diff --git a/lnet/lnet/net_fault.c b/lnet/lnet/net_fault.c
index 56365fd6..98f9b31 100644
--- a/lnet/lnet/net_fault.c
+++ b/lnet/lnet/net_fault.c
@@ -25,7 +25,6 @@
  */
 /*
  * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
  *
  * lnet/lnet/net_fault.c
  *
@@ -66,12 +65,16 @@ struct lnet_drop_rule {
 };
 
 static bool
-lnet_fault_nid_match(lnet_nid_t nid, lnet_nid_t msg_nid)
+lnet_fault_nid_match(lnet_nid_t nid, struct lnet_nid *msg_nid)
 {
-	if (nid == msg_nid || nid == LNET_NID_ANY)
+	if (nid == LNET_NID_ANY)
+		return true;
+	if (!msg_nid)
+		return false;
+	if (lnet_nid_to_nid4(msg_nid) == nid)
 		return true;
 
-	if (LNET_NIDNET(nid) != LNET_NIDNET(msg_nid))
+	if (LNET_NIDNET(nid) != LNET_NID_NET(msg_nid))
 		return false;
 
 	/* 255.255.255.255@net is wildcard for all addresses in a network */
@@ -79,8 +82,10 @@ lnet_fault_nid_match(lnet_nid_t nid, lnet_nid_t msg_nid)
 }
 
 static bool
-lnet_fault_attr_match(struct lnet_fault_attr *attr, lnet_nid_t src,
-		      lnet_nid_t local_nid, lnet_nid_t dst,
+lnet_fault_attr_match(struct lnet_fault_attr *attr,
+		      struct lnet_nid *src,
+		      struct lnet_nid *local_nid,
+		      struct lnet_nid *dst,
 		      unsigned int type, unsigned int portal)
 {
 	if (!lnet_fault_nid_match(attr->fa_src, src) ||
@@ -88,7 +93,7 @@ lnet_fault_attr_match(struct lnet_fault_attr *attr, lnet_nid_t src,
 	    !lnet_fault_nid_match(attr->fa_local_nid, local_nid))
 		return false;
 
-	if (!(attr->fa_msg_mask & (1 << type)))
+	if (!(attr->fa_msg_mask & BIT(type)))
 		return false;
 
 	/* NB: ACK and REPLY have no portal, but they should have been
@@ -313,7 +318,7 @@ lnet_fault_match_health(enum lnet_msg_hstatus *hstatus, __u32 mask)
 		return;
 	}
 
-	if (mask & (1 << choice)) {
+	if (mask & BIT(choice)) {
 		*hstatus = choice;
 		return;
 	}
@@ -322,7 +327,7 @@ lnet_fault_match_health(enum lnet_msg_hstatus *hstatus, __u32 mask)
 	i = HSTATUS_END;
 	best_delta = HSTATUS_END;
 	while (i > 0) {
-		if (mask & (1 << i)) {
+		if (mask & BIT(i)) {
 			delta = choice - i;
 			if (delta < 0)
 				delta *= -1;
@@ -342,8 +347,10 @@ lnet_fault_match_health(enum lnet_msg_hstatus *hstatus, __u32 mask)
  * decide whether should drop this message or not
  */
 static bool
-drop_rule_match(struct lnet_drop_rule *rule, lnet_nid_t src,
-		lnet_nid_t local_nid, lnet_nid_t dst,
+drop_rule_match(struct lnet_drop_rule *rule,
+		struct lnet_nid *src,
+		struct lnet_nid *local_nid,
+		struct lnet_nid *dst,
 		unsigned int type, unsigned int portal,
 		enum lnet_msg_hstatus *hstatus)
 {
@@ -427,12 +434,10 @@ drop_matched:
  */
 bool
 lnet_drop_rule_match(struct lnet_hdr *hdr,
-		     lnet_nid_t local_nid,
+		     struct lnet_nid *local_nid,
 		     enum lnet_msg_hstatus *hstatus)
 {
-	lnet_nid_t src = le64_to_cpu(hdr->src_nid);
-	lnet_nid_t dst = le64_to_cpu(hdr->dest_nid);
-	unsigned int typ = le32_to_cpu(hdr->type);
+	unsigned int typ = hdr->type;
 	struct lnet_drop_rule *rule;
 	unsigned int ptl = -1;
 	bool drop = false;
@@ -447,7 +452,8 @@ lnet_drop_rule_match(struct lnet_hdr *hdr,
 
 	cpt = lnet_net_lock_current();
 	list_for_each_entry(rule, &the_lnet.ln_drop_rules, dr_link) {
-		drop = drop_rule_match(rule, src, local_nid, dst, typ, ptl,
+		drop = drop_rule_match(rule, &hdr->src_nid, local_nid,
+				       &hdr->dest_nid, typ, ptl,
 				       hstatus);
 		if (drop)
 			break;
@@ -531,22 +537,21 @@ delay_rule_decref(struct lnet_delay_rule *rule)
  * decide whether should delay this message or not
  */
 static bool
-delay_rule_match(struct lnet_delay_rule *rule, lnet_nid_t src,
-		lnet_nid_t dst, unsigned int type, unsigned int portal,
-		struct lnet_msg *msg)
+delay_rule_match(struct lnet_delay_rule *rule, struct lnet_nid *src,
+		 struct lnet_nid *dst, unsigned int type, unsigned int portal,
+		 struct lnet_msg *msg)
 {
-	struct lnet_fault_attr	*attr = &rule->dl_attr;
-	bool			 delay;
+	struct lnet_fault_attr *attr = &rule->dl_attr;
+	bool delay;
+	time64_t now = ktime_get_seconds();
 
-	if (!lnet_fault_attr_match(attr, src, LNET_NID_ANY,
+	if (!lnet_fault_attr_match(attr, src, NULL,
 				   dst, type, portal))
 		return false;
 
 	/* match this rule, check delay rate now */
 	spin_lock(&rule->dl_lock);
 	if (rule->dl_delay_time != 0) { /* time based delay */
-		time64_t now = ktime_get_seconds();
-
 		rule->dl_stat.fs_count++;
 		delay = now >= rule->dl_delay_time;
 		if (delay) {
@@ -588,11 +593,11 @@ delay_rule_match(struct lnet_delay_rule *rule, lnet_nid_t src,
 	rule->dl_stat.u.delay.ls_delayed++;
 
 	list_add_tail(&msg->msg_list, &rule->dl_msg_list);
-	msg->msg_delay_send = ktime_get_seconds() + attr->u.delay.la_latency;
+	msg->msg_delay_send = now + attr->u.delay.la_latency;
 	if (rule->dl_msg_send == -1) {
 		rule->dl_msg_send = msg->msg_delay_send;
 		mod_timer(&rule->dl_timer,
-			  jiffies + cfs_time_seconds(rule->dl_msg_send));
+			  jiffies + cfs_time_seconds(attr->u.delay.la_latency));
 	}
 
 	spin_unlock(&rule->dl_lock);
@@ -607,9 +612,7 @@ bool
 lnet_delay_rule_match_locked(struct lnet_hdr *hdr, struct lnet_msg *msg)
 {
 	struct lnet_delay_rule	*rule;
-	lnet_nid_t		 src = le64_to_cpu(hdr->src_nid);
-	lnet_nid_t		 dst = le64_to_cpu(hdr->dest_nid);
-	unsigned int		 typ = le32_to_cpu(hdr->type);
+	unsigned int		 typ = hdr->type;
 	unsigned int		 ptl = -1;
 
 	/* NB: called with hold of lnet_net_lock */
@@ -622,7 +625,8 @@ lnet_delay_rule_match_locked(struct lnet_hdr *hdr, struct lnet_msg *msg)
 		ptl = le32_to_cpu(hdr->msg.get.ptl_index);
 
 	list_for_each_entry(rule, &the_lnet.ln_delay_rules, dl_link) {
-		if (delay_rule_match(rule, src, dst, typ, ptl, msg))
+		if (delay_rule_match(rule, &hdr->src_nid, &hdr->dest_nid,
+				     typ, ptl, msg))
 			return true;
 	}
 
@@ -638,7 +642,7 @@ delayed_msg_check(struct lnet_delay_rule *rule, bool all,
 	struct lnet_msg *tmp;
 	time64_t now = ktime_get_seconds();
 
-	if (!all && cfs_time_seconds(rule->dl_msg_send) > now)
+	if (!all && rule->dl_msg_send > now)
 		return;
 
 	spin_lock(&rule->dl_lock);
@@ -657,11 +661,12 @@ delayed_msg_check(struct lnet_delay_rule *rule, bool all,
 	} else if (!list_empty(msg_list)) {
 		/* dequeued some timedout messages, update timer for the
 		 * next delayed message on rule */
-		msg = list_entry(rule->dl_msg_list.next,
-				 struct lnet_msg, msg_list);
+		msg = list_first_entry(&rule->dl_msg_list,
+				       struct lnet_msg, msg_list);
 		rule->dl_msg_send = msg->msg_delay_send;
 		mod_timer(&rule->dl_timer,
-			  jiffies + cfs_time_seconds(rule->dl_msg_send));
+			  jiffies +
+			  cfs_time_seconds(msg->msg_delay_send - now));
 	}
 	spin_unlock(&rule->dl_lock);
 }
@@ -671,12 +676,25 @@ delayed_msg_process(struct list_head *msg_list, bool drop)
 {
 	struct lnet_msg	*msg;
 
-	while (!list_empty(msg_list)) {
+	while ((msg = list_first_entry_or_null(msg_list, struct lnet_msg,
+					       msg_list)) != NULL) {
 		struct lnet_ni *ni;
 		int		cpt;
 		int		rc;
 
-		msg = list_entry(msg_list->next, struct lnet_msg, msg_list);
+		if (msg->msg_sending) {
+			/* Delayed send */
+			list_del_init(&msg->msg_list);
+			ni = msg->msg_txni;
+			CDEBUG(D_NET, "TRACE: msg %p %s -> %s : %s\n", msg,
+			       libcfs_nidstr(&ni->ni_nid),
+			       libcfs_nidstr(&msg->msg_txpeer->lpni_nid),
+			       lnet_msgtyp2str(msg->msg_type));
+			lnet_ni_send(ni, msg);
+			continue;
+		}
+
+		/* Delayed receive */
 		LASSERT(msg->msg_rxpeer != NULL);
 		LASSERT(msg->msg_rxni != NULL);
 
@@ -701,7 +719,7 @@ delayed_msg_process(struct list_head *msg_list, bool drop)
 			case LNET_CREDIT_OK:
 				lnet_ni_recv(ni, msg->msg_private, msg, 0,
 					     0, msg->msg_len, msg->msg_len);
-				/* fallthrough */
+				fallthrough;
 			case LNET_CREDIT_WAIT:
 				continue;
 			default: /* failures */
@@ -735,8 +753,8 @@ lnet_delay_rule_check(void)
 			break;
 		}
 
-		rule = list_entry(delay_dd.dd_sched_rules.next,
-				  struct lnet_delay_rule, dl_sched_link);
+		rule = list_first_entry(&delay_dd.dd_sched_rules,
+					struct lnet_delay_rule, dl_sched_link);
 		list_del_init(&rule->dl_sched_link);
 		spin_unlock_bh(&delay_dd.dd_lock);
 
@@ -1075,10 +1093,10 @@ lnet_fault_ctl(int opc, struct libcfs_ioctl_data *data)
 int
 lnet_fault_init(void)
 {
-	BUILD_BUG_ON(LNET_PUT_BIT != 1 << LNET_MSG_PUT);
-	BUILD_BUG_ON(LNET_ACK_BIT != 1 << LNET_MSG_ACK);
-	BUILD_BUG_ON(LNET_GET_BIT != 1 << LNET_MSG_GET);
-	BUILD_BUG_ON(LNET_REPLY_BIT != 1 << LNET_MSG_REPLY);
+	BUILD_BUG_ON(LNET_PUT_BIT != BIT(LNET_MSG_PUT));
+	BUILD_BUG_ON(LNET_ACK_BIT != BIT(LNET_MSG_ACK));
+	BUILD_BUG_ON(LNET_GET_BIT != BIT(LNET_MSG_GET));
+	BUILD_BUG_ON(LNET_REPLY_BIT != BIT(LNET_MSG_REPLY));
 
 	mutex_init(&delay_dd.dd_mutex);
 	spin_lock_init(&delay_dd.dd_lock);