[PATCH 1/2] bonding 802.3ad: Fix the state machine locking v2

[PATCH 1/2] bonding 802.3ad: Fix the state machine locking v2

[Nils Carlson]

Changes since v1:
* Clarify an unclear comment
* Move a (possible) name change to a separate patch

The ad_rx_machine, ad_periodic_machine and ad_port_selection_logic
functions all inspect and alter common fields within the port structure.
Previous to this patch, only the ad_rx_machines were mutexed, and the
periodic and port_selection could run unmutexed against an ad_rx_machine
trigged by an arriving LACPDU.

This patch remedies the situation by protecting all the state machines
from concurrency. This is accomplished by locking around all the state
machines for a given port, which are executed at regular intervals; and
the ad_rx_machine when handling an incoming LACPDU.

Signed-off-by: Nils Carlson <nils.carlson@ericsson.com>
---
 drivers/net/bonding/bond_3ad.c |   16 +++++++++++-----
 1 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 1024ae1..de30c8d 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -1025,9 +1025,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 {
 	rx_states_t last_state;
 
-	// Lock to prevent 2 instances of this function to run simultaneously(rx interrupt and periodic machine callback)
-	__get_rx_machine_lock(port);
-
 	// keep current State Machine state to compare later if it was changed
 	last_state = port->sm_rx_state;
 
@@ -1133,7 +1130,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 				pr_err("%s: An illegal loopback occurred on adapter (%s).\n"
 				       "Check the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n",
 				       port->slave->dev->master->name, port->slave->dev->name);
-				__release_rx_machine_lock(port);
 				return;
 			}
 			__update_selected(lacpdu, port);
@@ -1153,7 +1149,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 			break;
 		}
 	}
-	__release_rx_machine_lock(port);
 }
 
 /**
@@ -2155,6 +2150,12 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 			goto re_arm;
 		}
 
+		/* Lock around state machines to protect data accessed
+		 * by all (e.g., port->sm_vars).  ad_rx_machine may run
+		 * concurrently due to incoming LACPDU.
+		 */
+		__get_rx_machine_lock(port);
+
 		ad_rx_machine(NULL, port);
 		ad_periodic_machine(port);
 		ad_port_selection_logic(port);
@@ -2164,6 +2165,8 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 		// turn off the BEGIN bit, since we already handled it
 		if (port->sm_vars & AD_PORT_BEGIN)
 			port->sm_vars &= ~AD_PORT_BEGIN;
+
+		__release_rx_machine_lock(port);
 	}
 
 re_arm:
@@ -2200,7 +2203,10 @@ static void bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u
 		case AD_TYPE_LACPDU:
 			pr_debug("Received LACPDU on port %d\n",
 				 port->actor_port_number);
+			/* Protect against concurrent state machines */
+			__get_rx_machine_lock(port);
 			ad_rx_machine(lacpdu, port);
+			__release_rx_machine_lock(port);
 			break;
 
 		case AD_TYPE_MARKER:
-- 
1.7.1

[PATCH 2/2] bonding 802.3ad: Rename rx_machine_lock to state_machine_lock

[Nils Carlson]

Rename the rx_machine_lock to state_machine_lock as this makes more
sense in light of it now protecting all the state machines against
concurrency.

Signed-off-by: Nils Carlson <nils.carlson@ericsson.com>
---
 drivers/net/bonding/bond_3ad.c |   24 ++++++++++++------------
 drivers/net/bonding/bond_3ad.h |    3 ++-
 2 files changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index de30c8d..a5d5d0b 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -281,23 +281,23 @@ static inline int __check_agg_selection_timer(struct port *port)
 }
 
 /**
- * __get_rx_machine_lock - lock the port's RX machine
+ * __get_state_machine_lock - lock the port's state machines
  * @port: the port we're looking at
  *
  */
-static inline void __get_rx_machine_lock(struct port *port)
+static inline void __get_state_machine_lock(struct port *port)
 {
-	spin_lock_bh(&(SLAVE_AD_INFO(port->slave).rx_machine_lock));
+	spin_lock_bh(&(SLAVE_AD_INFO(port->slave).state_machine_lock));
 }
 
 /**
- * __release_rx_machine_lock - unlock the port's RX machine
+ * __release_state_machine_lock - unlock the port's state machines
  * @port: the port we're looking at
  *
  */
-static inline void __release_rx_machine_lock(struct port *port)
+static inline void __release_state_machine_lock(struct port *port)
 {
-	spin_unlock_bh(&(SLAVE_AD_INFO(port->slave).rx_machine_lock));
+	spin_unlock_bh(&(SLAVE_AD_INFO(port->slave).state_machine_lock));
 }
 
 /**
@@ -388,14 +388,14 @@ static u8 __get_duplex(struct port *port)
 }
 
 /**
- * __initialize_port_locks - initialize a port's RX machine spinlock
+ * __initialize_port_locks - initialize a port's STATE machine spinlock
  * @port: the port we're looking at
  *
  */
 static inline void __initialize_port_locks(struct port *port)
 {
 	// make sure it isn't called twice
-	spin_lock_init(&(SLAVE_AD_INFO(port->slave).rx_machine_lock));
+	spin_lock_init(&(SLAVE_AD_INFO(port->slave).state_machine_lock));
 }
 
 //conversions
@@ -2154,7 +2154,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 		 * by all (e.g., port->sm_vars).  ad_rx_machine may run
 		 * concurrently due to incoming LACPDU.
 		 */
-		__get_rx_machine_lock(port);
+		__get_state_machine_lock(port);
 
 		ad_rx_machine(NULL, port);
 		ad_periodic_machine(port);
@@ -2166,7 +2166,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 		if (port->sm_vars & AD_PORT_BEGIN)
 			port->sm_vars &= ~AD_PORT_BEGIN;
 
-		__release_rx_machine_lock(port);
+		__release_state_machine_lock(port);
 	}
 
 re_arm:
@@ -2204,9 +2204,9 @@ static void bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u
 			pr_debug("Received LACPDU on port %d\n",
 				 port->actor_port_number);
 			/* Protect against concurrent state machines */
-			__get_rx_machine_lock(port);
+			__get_state_machine_lock(port);
 			ad_rx_machine(lacpdu, port);
-			__release_rx_machine_lock(port);
+			__release_state_machine_lock(port);
 			break;
 
 		case AD_TYPE_MARKER:
diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h
index 2c46a15..b28baff 100644
--- a/drivers/net/bonding/bond_3ad.h
+++ b/drivers/net/bonding/bond_3ad.h
@@ -264,7 +264,8 @@ struct ad_bond_info {
 struct ad_slave_info {
 	struct aggregator aggregator;	    // 802.3ad aggregator structure
 	struct port port;		    // 802.3ad port structure
-	spinlock_t rx_machine_lock; // To avoid race condition between callback and receive interrupt
+	spinlock_t state_machine_lock; /* mutex state machines vs.
+					  incoming LACPDU */
 	u16 id;
 };
 
-- 
1.7.1

Re: [PATCH 2/2] bonding 802.3ad: Rename rx_machine_lock to state_machine_lock

[David Miller]

From: Nils Carlson <nils.carlson@ericsson.com>
Date: Fri, 4 Mar 2011 09:09:12 +0100

> Rename the rx_machine_lock to state_machine_lock as this makes more
> sense in light of it now protecting all the state machines against
> concurrency.
> 
> Signed-off-by: Nils Carlson <nils.carlson@ericsson.com>

Applied.

Re: [PATCH 1/2] bonding 802.3ad: Fix the state machine locking v2

[David Miller]

From: Nils Carlson <nils.carlson@ericsson.com>
Date: Fri, 4 Mar 2011 09:09:11 +0100

> Changes since v1:
> * Clarify an unclear comment
> * Move a (possible) name change to a separate patch
> 
> The ad_rx_machine, ad_periodic_machine and ad_port_selection_logic
> functions all inspect and alter common fields within the port structure.
> Previous to this patch, only the ad_rx_machines were mutexed, and the
> periodic and port_selection could run unmutexed against an ad_rx_machine
> trigged by an arriving LACPDU.
> 
> This patch remedies the situation by protecting all the state machines
> from concurrency. This is accomplished by locking around all the state
> machines for a given port, which are executed at regular intervals; and
> the ad_rx_machine when handling an incoming LACPDU.
> 
> Signed-off-by: Nils Carlson <nils.carlson@ericsson.com>

Applied.