linux-kernel - Re: [PATCH v2] bonding: "primary_reselect" with "failure" is not working properly

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <24978.1435869761@famine>
Date:	Thu, 02 Jul 2015 13:42:41 -0700
From:	Jay Vosburgh <jay.vosburgh@...onical.com>
To:	Mazhar Rana <ranamazharp@...il.com>
cc:	netdev@...r.kernel.org, vfalico@...il.com,
	gospo@...ulusnetworks.com, davem@...emloft.net,
	sanket.shah@...eroam.com, mazhar.rana@...eroam.com,
	linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2] bonding: "primary_reselect" with "failure" is not working properly


	[ added netdev to cc ]

Mazhar Rana <ranamazharp@...il.com> wrote:

>When "primary_reselect" is set to "failure", primary interface should
>not become active until current active slave is up. But if we set first

	I think you mean "until current active slave is down" here, not
"up."

>member of bond device as a "primary" interface and "primary_reselect"
>is set to "failure" then whenever primary interface's link get back(up)
>it become active slave even if current active slave is still up.
>
>With this patch, "bond_find_best_slave" will not traverse members if
>primary interface is not candidate for failover/reselection and current
>active slave is still up.
>
>Signed-off-by: Mazhar Rana <mazhar.rana@...eroam.com>
>Reviewed-by: Sanket Shah <sanket.shah@...eroam.com>
>---
>v2: return "curr" instead of "bond->curr_active_slave".
>
> drivers/net/bonding/bond_main.c | 10 +++++++++-
> 1 file changed, 9 insertions(+), 1 deletion(-)
>
>diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
>index 19eb990..ac71261 100644
>--- a/drivers/net/bonding/bond_main.c
>+++ b/drivers/net/bonding/bond_main.c
>@@ -715,7 +715,7 @@ static bool bond_should_change_active(struct bonding *bond)
>  */
> static struct slave *bond_find_best_slave(struct bonding *bond)
> {
>-	struct slave *slave, *bestslave = NULL, *primary;
>+	struct slave *slave, *bestslave = NULL, *primary, *curr;
> 	struct list_head *iter;
> 	int mintime = bond->params.updelay;
> 
>@@ -724,6 +724,14 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
> 	    bond_should_change_active(bond))
> 		return primary;
> 
>+	/* We are here means primary interface is not candidate for
>+	 * reslection/failover. If currenet active slave is still up
>+	 * then there is no meaning to traverse  members.
>+	 */
>+	curr = rtnl_dereference(bond->curr_active_slave);
>+	if (curr && curr->link == BOND_LINK_UP)
>+		return curr;
>+
> 	bond_for_each_slave(bond, slave, iter) {
> 		if (slave->link == BOND_LINK_UP)
> 			return slave;
>-- 

	I believe the above patch will work, but I also think these
functions are kind of hacky, as bond_should_change_active() doesn't
really give the answer its name implies, so we have to second guess
here.

	I think the following, while a bigger change, ends up with
clearer code.  Compile tested only.  Comments?

	-J

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 19eb990..8c30f6b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -689,40 +689,54 @@ out:
 
 }
 
-static bool bond_should_change_active(struct bonding *bond)
+static struct slave *bond_choose_primary_or_current(struct bonding *bond)
 {
 	struct slave *prim = rtnl_dereference(bond->primary_slave);
 	struct slave *curr = rtnl_dereference(bond->curr_active_slave);
 
-	if (!prim || !curr || curr->link != BOND_LINK_UP)
-		return true;
+	if (!prim || !prim->link == BOND_LINK_UP)
+		return curr;
+
 	if (bond->force_primary) {
 		bond->force_primary = false;
-		return true;
+		return prim;
+	}
+
+	if (!curr || curr->link != BOND_LINK_UP)
+		return prim;
+
+	/* At this point, prim and curr are both up */
+	switch (bond->params.primary_reselect) {
+	case BOND_PRI_RESELECT_ALWAYS:
+		return prim;
+	case BOND_PRI_RESELECT_BETTER:
+		if (prim->speed < curr->speed)
+			return curr;
+		if (prim->speed == curr->speed && prim->duplex <= curr->duplex)
+			return curr;
+		return prim;
+	case BOND_PRI_RESELECT_FAILURE:
+		return curr;
+	default:
+		netdev_err(bond->dev, "impossible primary_reselect %d\n",
+			   bond->params.primary_reselect);
+		return curr;
 	}
-	if (bond->params.primary_reselect == BOND_PRI_RESELECT_BETTER &&
-	    (prim->speed < curr->speed ||
-	     (prim->speed == curr->speed && prim->duplex <= curr->duplex)))
-		return false;
-	if (bond->params.primary_reselect == BOND_PRI_RESELECT_FAILURE)
-		return false;
-	return true;
 }
 
 /**
- * find_best_interface - select the best available slave to be the active one
+ * bond_find_best_slave - select the best available slave to be the active one
  * @bond: our bonding struct
  */
 static struct slave *bond_find_best_slave(struct bonding *bond)
 {
-	struct slave *slave, *bestslave = NULL, *primary;
+	struct slave *slave, *bestslave = NULL;
 	struct list_head *iter;
 	int mintime = bond->params.updelay;
 
-	primary = rtnl_dereference(bond->primary_slave);
-	if (primary && primary->link == BOND_LINK_UP &&
-	    bond_should_change_active(bond))
-		return primary;
+	slave = bond_choose_primary_or_current(bond);
+	if (slave)
+		return slave;
 
 	bond_for_each_slave(bond, slave, iter) {
 		if (slave->link == BOND_LINK_UP)

---
	-Jay Vosburgh, jay.vosburgh@...onical.com
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/