5 files changed, 278 insertions, 7 deletions

diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 61f516b135b4..d0914781830e 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -49,6 +49,7 @@ Table of Contents
 3.3     Configuring Bonding Manually with Ifenslave
 3.3.1           Configuring Multiple Bonds Manually
 3.4     Configuring Bonding Manually via Sysfs
+3.5     Overriding Configuration for Special Cases
 
 4. Querying Bonding Configuration
 4.1     Bonding Configuration
@@ -1318,8 +1319,87 @@ echo 2000 > /sys/class/net/bond1/bonding/arp_interval
 echo +eth2 > /sys/class/net/bond1/bonding/slaves
 echo +eth3 > /sys/class/net/bond1/bonding/slaves
 
-
-4. Querying Bonding Configuration 
+3.5 Overriding Configuration for Special Cases
+----------------------------------------------
+When using the bonding driver, the physical port which transmits a frame is
+typically selected by the bonding driver, and is not relevant to the user or
+system administrator.  The output port is simply selected using the policies of
+the selected bonding mode.  On occasion however, it is helpful to direct certain
+classes of traffic to certain physical interfaces on output to implement
+slightly more complex policies.  For example, to reach a web server over a
+bonded interface in which eth0 connects to a private network, while eth1
+connects via a public network, it may be desirous to bias the bond to send said
+traffic over eth0 first, using eth1 only as a fall back, while all other traffic
+can safely be sent over either interface.  Such configurations may be achieved
+using the traffic control utilities inherent in linux.
+
+By default the bonding driver is multiqueue aware and 16 queues are created
+when the driver initializes (see Documentation/networking/multiqueue.txt
+for details).  If more or less queues are desired the module parameter
+tx_queues can be used to change this value.  There is no sysfs parameter
+available as the allocation is done at module init time.
+
+The output of the file /proc/net/bonding/bondX has changed so the output Queue
+ID is now printed for each slave:
+
+Bonding Mode: fault-tolerance (active-backup)
+Primary Slave: None
+Currently Active Slave: eth0
+MII Status: up
+MII Polling Interval (ms): 0
+Up Delay (ms): 0
+Down Delay (ms): 0
+
+Slave Interface: eth0
+MII Status: up
+Link Failure Count: 0
+Permanent HW addr: 00:1a:a0:12:8f:cb
+Slave queue ID: 0
+
+Slave Interface: eth1
+MII Status: up
+Link Failure Count: 0
+Permanent HW addr: 00:1a:a0:12:8f:cc
+Slave queue ID: 2
+
+The queue_id for a slave can be set using the command:
+
+# echo "eth1:2" > /sys/class/net/bond0/bonding/queue_id
+
+Any interface that needs a queue_id set should set it with multiple calls
+like the one above until proper priorities are set for all interfaces.  On
+distributions that allow configuration via initscripts, multiple 'queue_id'
+arguments can be added to BONDING_OPTS to set all needed slave queues.
+
+These queue id's can be used in conjunction with the tc utility to configure
+a multiqueue qdisc and filters to bias certain traffic to transmit on certain
+slave devices.  For instance, say we wanted, in the above configuration to
+force all traffic bound to 192.168.1.100 to use eth1 in the bond as its output
+device. The following commands would accomplish this:
+
+# tc qdisc add dev bond0 handle 1 root multiq
+
+# tc filter add dev bond0 protocol ip parent 1: prio 1 u32 match ip dst \
+        192.168.1.100 action skbedit queue_mapping 2
+
+These commands tell the kernel to attach a multiqueue queue discipline to the
+bond0 interface and filter traffic enqueued to it, such that packets with a dst
+ip of 192.168.1.100 have their output queue mapping value overwritten to 2.
+This value is then passed into the driver, causing the normal output path
+selection policy to be overridden, selecting instead qid 2, which maps to eth1.
+
+Note that qid values begin at 1.  Qid 0 is reserved to initiate to the driver
+that normal output policy selection should take place.  One benefit to simply
+leaving the qid for a slave to 0 is the multiqueue awareness in the bonding
+driver that is now present.  This awareness allows tc filters to be placed on
+slave devices as well as bond devices and the bonding driver will simply act as
+a pass-through for selecting output queues on the slave device rather than 
+output port selection.
+
+This feature first appeared in bonding driver version 3.7.0 and support for
+output slave selection was limited to round-robin and active-backup modes.
+
+4 Querying Bonding Configuration
 =================================
 
 4.1 Bonding Configuration
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f22f6bf43858..1b19276cff12 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -90,6 +90,7 @@
 #define BOND_LINK_ARP_INTERV    0
 
 static int max_bonds    = BOND_DEFAULT_MAX_BONDS;
+static int tx_queues    = BOND_DEFAULT_TX_QUEUES;
 static int num_grat_arp = 1;
 static int num_unsol_na = 1;
 static int miimon       = BOND_LINK_MON_INTERV;
@@ -111,6 +112,8 @@ static struct bond_params bonding_defaults;
 
 module_param(max_bonds, int, 0);
 MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
+module_param(tx_queues, int, 0);
+MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)");
 module_param(num_grat_arp, int, 0644);
 MODULE_PARM_DESC(num_grat_arp, "Number of gratuitous ARP packets to send on failover event");
 module_param(num_unsol_na, int, 0644);
@@ -1540,6 +1543,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
                 goto err_undo_flags;
         }
 
+        /*
+         * Set the new_slave's queue_id to be zero.  Queue ID mapping
+         * is set via sysfs or module option if desired.
+         */
+        new_slave->queue_id = 0;
+
         /* Save slave's original mtu and then set it to match the bond */
         new_slave->original_mtu = slave_dev->mtu;
         res = dev_set_mtu(slave_dev, bond->dev->mtu);
@@ -3285,6 +3294,7 @@ static void bond_info_show_slave(struct seq_file *seq,
                 else
                         seq_puts(seq, "Aggregator ID: N/A\n");
         }
+        seq_printf(seq, "Slave queue ID: %d\n", slave->queue_id);
 }
 
 static int bond_info_seq_show(struct seq_file *seq, void *v)
@@ -4421,9 +4431,59 @@ static void bond_set_xmit_hash_policy(struct bonding *bond)
         }
 }
 
+/*
+ * Lookup the slave that corresponds to a qid
+ */
+static inline int bond_slave_override(struct bonding *bond,
+                                      struct sk_buff *skb)
+{
+        int i, res = 1;
+        struct slave *slave = NULL;
+        struct slave *check_slave;
+
+        read_lock(&bond->lock);
+
+        if (!BOND_IS_OK(bond) || !skb->queue_mapping)
+                goto out;
+
+        /* Find out if any slaves have the same mapping as this skb. */
+        bond_for_each_slave(bond, check_slave, i) {
+                if (check_slave->queue_id == skb->queue_mapping) {
+                        slave = check_slave;
+                        break;
+                }
+        }
+
+        /* If the slave isn't UP, use default transmit policy. */
+        if (slave && slave->queue_id && IS_UP(slave->dev) &&
+            (slave->link == BOND_LINK_UP)) {
+                res = bond_dev_queue_xmit(bond, skb, slave->dev);
+        }
+
+out:
+        read_unlock(&bond->lock);
+        return res;
+}
+
+static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb)
+{
+        /*
+         * This helper function exists to help dev_pick_tx get the correct
+         * destination queue.  Using a helper function skips the a call to
+         * skb_tx_hash and will put the skbs in the queue we expect on their
+         * way down to the bonding driver.
+         */
+        return skb->queue_mapping;
+}
+
 static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-        const struct bonding *bond = netdev_priv(dev);
+        struct bonding *bond = netdev_priv(dev);
+
+        if (TX_QUEUE_OVERRIDE(bond->params.mode)) {
+                if (!bond_slave_override(bond, skb))
+                        return NETDEV_TX_OK;
+        }
 
         switch (bond->params.mode) {
         case BOND_MODE_ROUNDROBIN:
@@ -4508,6 +4568,7 @@ static const struct net_device_ops bond_netdev_ops = {
         .ndo_open               = bond_open,
         .ndo_stop               = bond_close,
         .ndo_start_xmit         = bond_start_xmit,
+        .ndo_select_queue       = bond_select_queue,
         .ndo_get_stats          = bond_get_stats,
         .ndo_do_ioctl           = bond_do_ioctl,
         .ndo_set_multicast_list = bond_set_multicast_list,
@@ -4776,6 +4837,13 @@ static int bond_check_params(struct bond_params *params)
                 }
         }
 
+        if (tx_queues < 1 || tx_queues > 255) {
+                pr_warning("Warning: tx_queues (%d) should be between "
+                           "1 and 255, resetting to %d\n",
+                           tx_queues, BOND_DEFAULT_TX_QUEUES);
+                tx_queues = BOND_DEFAULT_TX_QUEUES;
+        }
+
         if ((all_slaves_active != 0) && (all_slaves_active != 1)) {
                 pr_warning("Warning: all_slaves_active module parameter (%d), "
                            "not of valid value (0/1), so it was set to "
@@ -4953,6 +5021,7 @@ static int bond_check_params(struct bond_params *params)
         params->primary[0] = 0;
         params->primary_reselect = primary_reselect_value;
         params->fail_over_mac = fail_over_mac_value;
+        params->tx_queues = tx_queues;
         params->all_slaves_active = all_slaves_active;
 
         if (primary) {
@@ -5040,8 +5109,8 @@ int bond_create(struct net *net, const char *name)
 
         rtnl_lock();
 
-        bond_dev = alloc_netdev(sizeof(struct bonding), name ? name : "",
-                                bond_setup);
+        bond_dev = alloc_netdev_mq(sizeof(struct bonding), name ? name : "",
+                                bond_setup, tx_queues);
         if (!bond_dev) {
                 pr_err("%s: eek! can't alloc netdev!\n", name);
                 rtnl_unlock();
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 066311a5e084..f9a034361a8e 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1412,6 +1412,121 @@ static ssize_t bonding_show_ad_partner_mac(struct device *d,
 static DEVICE_ATTR(ad_partner_mac, S_IRUGO, bonding_show_ad_partner_mac, NULL);
 
 /*
+ * Show the queue_ids of the slaves in the current bond.
+ */
+static ssize_t bonding_show_queue_id(struct device *d,
+                                     struct device_attribute *attr,
+                                     char *buf)
+{
+        struct slave *slave;
+        int i, res = 0;
+        struct bonding *bond = to_bond(d);
+
+        if (!rtnl_trylock())
+                return restart_syscall();
+
+        read_lock(&bond->lock);
+        bond_for_each_slave(bond, slave, i) {
+                if (res > (PAGE_SIZE - 6)) {
+                        /* not enough space for another interface name */
+                        if ((PAGE_SIZE - res) > 10)
+                                res = PAGE_SIZE - 10;
+                        res += sprintf(buf + res, "++more++ ");
+                        break;
+                }
+                res += sprintf(buf + res, "%s:%d ",
+                               slave->dev->name, slave->queue_id);
+        }
+        read_unlock(&bond->lock);
+        if (res)
+                buf[res-1] = '\n'; /* eat the leftover space */
+        rtnl_unlock();
+        return res;
+}
+
+/*
+ * Set the queue_ids of the  slaves in the current bond.  The bond
+ * interface must be enslaved for this to work.
+ */
+static ssize_t bonding_store_queue_id(struct device *d,
+                                      struct device_attribute *attr,
+                                      const char *buffer, size_t count)
+{
+        struct slave *slave, *update_slave;
+        struct bonding *bond = to_bond(d);
+        u16 qid;
+        int i, ret = count;
+        char *delim;
+        struct net_device *sdev = NULL;
+
+        if (!rtnl_trylock())
+                return restart_syscall();
+
+        /* delim will point to queue id if successful */
+        delim = strchr(buffer, ':');
+        if (!delim)
+                goto err_no_cmd;
+
+        /*
+         * Terminate string that points to device name and bump it
+         * up one, so we can read the queue id there.
+         */
+        *delim = '\0';
+        if (sscanf(++delim, "%hd\n", &qid) != 1)
+                goto err_no_cmd;
+
+        /* Check buffer length, valid ifname and queue id */
+        if (strlen(buffer) > IFNAMSIZ ||
+            !dev_valid_name(buffer) ||
+            qid > bond->params.tx_queues)
+                goto err_no_cmd;
+
+        /* Get the pointer to that interface if it exists */
+        sdev = __dev_get_by_name(dev_net(bond->dev), buffer);
+        if (!sdev)
+                goto err_no_cmd;
+
+        read_lock(&bond->lock);
+
+        /* Search for thes slave and check for duplicate qids */
+        update_slave = NULL;
+        bond_for_each_slave(bond, slave, i) {
+                if (sdev == slave->dev)
+                        /*
+                         * We don't need to check the matching
+                         * slave for dups, since we're overwriting it
+                         */
+                        update_slave = slave;
+                else if (qid && qid == slave->queue_id) {
+                        goto err_no_cmd_unlock;
+                }
+        }
+
+        if (!update_slave)
+                goto err_no_cmd_unlock;
+
+        /* Actually set the qids for the slave */
+        update_slave->queue_id = qid;
+
+        read_unlock(&bond->lock);
+out:
+        rtnl_unlock();
+        return ret;
+
+err_no_cmd_unlock:
+        read_unlock(&bond->lock);
+err_no_cmd:
+        pr_info("invalid input for queue_id set for %s.\n",
+                bond->dev->name);
+        ret = -EPERM;
+        goto out;
+}
+
+static DEVICE_ATTR(queue_id, S_IRUGO | S_IWUSR, bonding_show_queue_id,
+                   bonding_store_queue_id);
+
+
+/*
  * Show and set the all_slaves_active flag.
  */
 static ssize_t bonding_show_slaves_active(struct device *d,
@@ -1489,6 +1604,7 @@ static struct attribute *per_bond_attrs[] = {
         &dev_attr_ad_actor_key.attr,
         &dev_attr_ad_partner_key.attr,
         &dev_attr_ad_partner_mac.attr,
+        &dev_attr_queue_id.attr,
         &dev_attr_all_slaves_active.attr,
         NULL,
 };
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index cecdea2a629f..c6fdd851579a 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -23,8 +23,8 @@
 #include "bond_3ad.h"
 #include "bond_alb.h"
 
-#define DRV_VERSION     "3.6.0"
-#define DRV_RELDATE     "September 26, 2009"
+#define DRV_VERSION     "3.7.0"
+#define DRV_RELDATE     "June 2, 2010"
 #define DRV_NAME        "bonding"
 #define DRV_DESCRIPTION "Ethernet Channel Bonding Driver"
 
@@ -60,6 +60,9 @@
                  ((mode) == BOND_MODE_TLB)          ||  \
                  ((mode) == BOND_MODE_ALB))
 
+#define TX_QUEUE_OVERRIDE(mode)                         \
+                        (((mode) == BOND_MODE_ACTIVEBACKUP) ||  \
+                         ((mode) == BOND_MODE_ROUNDROBIN))
 /*
  * Less bad way to call ioctl from within the kernel; this needs to be
  * done some other way to get the call out of interrupt context.
@@ -131,6 +134,7 @@ struct bond_params {
         char primary[IFNAMSIZ];
         int primary_reselect;
         __be32 arp_targets[BOND_MAX_ARP_TARGETS];
+        int tx_queues;
         int all_slaves_active;
 };
 
@@ -165,6 +169,7 @@ struct slave {
         u8     perm_hwaddr[ETH_ALEN];
         u16    speed;
         u8     duplex;
+        u16    queue_id;
         struct ad_slave_info ad_info; /* HUGE - better to dynamically alloc */
         struct tlb_slave_info tlb_info;
 };
diff --git a/include/linux/if_bonding.h b/include/linux/if_bonding.h
index cd525fae3c98..2c7994372bde 100644
--- a/include/linux/if_bonding.h
+++ b/include/linux/if_bonding.h
@@ -83,6 +83,7 @@
 
 #define BOND_DEFAULT_MAX_BONDS  1   /* Default maximum number of devices to support */
 
+#define BOND_DEFAULT_TX_QUEUES 16   /* Default number of tx queues per device */
 /* hashing types */
 #define BOND_XMIT_POLICY_LAYER2         0 /* layer 2 (MAC only), default */
 #define BOND_XMIT_POLICY_LAYER34        1 /* layer 3+4 (IP ^ (TCP || UDP)) */