| 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
| ||
|
Date: Sun, 23 Jun 2013 20:24:11 -0700
From: John Fastabend <john.fastabend@...il.com>
To: netdev@...r.kernel.org
Cc: therbert@...gle.com, ben@...adent.org.uk,
jesse.brandeburg@...el.com, jeffrey.t.kirsher@...el.com
Subject: [RFC PATCH] net: add a tx_queue attribute rate_queue_limits in Mbps
This adds a rate_queue_limit attribute to the tx_queue sysfs entry
to allow rate limiting in units of Mpbs. Along with mqprio and BQL
this provides another knob to tune queue performance. By default it
is disabled with a setting of '0'.
By adding this as a queue attribute and _not_ a qdisc option allows
using rate limits with qdisc schemes that may not align with tx rings
and also allows using QOS schemes along with rate limits.
A sample implementation is provided for ixgbe. Any improvements or
suggestions welcome I would also be interested to know if this works
with other hardware and if Mbps is a good default unit.
I tested this briefly with iperf/netperf,
# echo 4000 > /sys/class/net/p3p2/queues/tx-0/tx_rate_limit
# cat /sys/class/net/p3p2/queues/tx-0/tx_rate_limit
4000
Signed-off-by: John Fastabend <john.r.fastabend@...el.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 1
drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 47 ++++++++++++++--
drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h | 2 +
include/linux/netdevice.h | 12 ++++
net/core/net-sysfs.c | 69 +++++++++++++++++++-----
5 files changed, 110 insertions(+), 21 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 047ebaa..8d168a0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7244,6 +7244,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
.ndo_fdb_add = ixgbe_ndo_fdb_add,
.ndo_bridge_setlink = ixgbe_ndo_bridge_setlink,
.ndo_bridge_getlink = ixgbe_ndo_bridge_getlink,
+ .ndo_set_ratelimit = ixgbe_set_rate_limit,
};
/**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 1e7d587..22f3df2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -1107,17 +1107,14 @@ static int ixgbe_link_mbps(struct ixgbe_adapter *adapter)
}
}
-static void ixgbe_set_vf_rate_limit(struct ixgbe_adapter *adapter, int vf)
+static u32 ixgbe_bcnrc_from_rate(struct ixgbe_adapter *adapter,
+ u16 tx_rate, int link_speed)
{
- struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
- struct ixgbe_hw *hw = &adapter->hw;
u32 bcnrc_val = 0;
- u16 queue, queues_per_pool;
- u16 tx_rate = adapter->vfinfo[vf].tx_rate;
if (tx_rate) {
/* start with base link speed value */
- bcnrc_val = adapter->vf_rate_link_speed;
+ bcnrc_val = link_speed;
/* Calculate the rate factor values to set */
bcnrc_val <<= IXGBE_RTTBCNRC_RF_INT_SHIFT;
@@ -1131,6 +1128,11 @@ static void ixgbe_set_vf_rate_limit(struct ixgbe_adapter *adapter, int vf)
bcnrc_val |= IXGBE_RTTBCNRC_RS_ENA;
}
+ return bcnrc_val;
+}
+
+static void ixgbe_set_xmit_compensation(struct ixgbe_hw *hw)
+{
/*
* Set global transmit compensation time to the MMW_SIZE in RTTBCNRM
* register. Typically MMW_SIZE=0x014 if 9728-byte jumbo is supported
@@ -1146,6 +1148,39 @@ static void ixgbe_set_vf_rate_limit(struct ixgbe_adapter *adapter, int vf)
default:
break;
}
+}
+
+int ixgbe_set_rate_limit(struct net_device *dev, int index, u32 *tx_rate)
+{
+ struct ixgbe_adapter *a = netdev_priv(dev);
+ struct ixgbe_hw *hw = &a->hw;
+ int linkspeed = ixgbe_link_mbps(a);
+ u8 reg_idx = a->tx_ring[index]->reg_idx;
+ u32 bcnrc = ixgbe_bcnrc_from_rate(a, *tx_rate, linkspeed);
+
+ /* rate limit cannot be less than 10Mbs or greater than link speed */
+ if (*tx_rate && ((*tx_rate <= 10) || (*tx_rate > linkspeed)))
+ return -EINVAL;
+
+ ixgbe_set_xmit_compensation(hw);
+
+ IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, reg_idx);
+ IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc);
+
+ return 0;
+}
+
+static void ixgbe_set_vf_rate_limit(struct ixgbe_adapter *adapter, int vf)
+{
+ struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 bcnrc_val = 0;
+ u16 queue, queues_per_pool;
+ u16 tx_rate = adapter->vfinfo[vf].tx_rate;
+
+ bcnrc_val = ixgbe_bcnrc_from_rate(adapter, tx_rate,
+ adapter->vf_rate_link_speed);
+ ixgbe_set_xmit_compensation(hw);
/* determine how many queues per pool based on VMDq mask */
queues_per_pool = __ALIGN_MASK(1, ~vmdq->mask);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
index 4713f9f..d8b4bbe 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
@@ -56,5 +56,7 @@ static inline void ixgbe_set_vmvir(struct ixgbe_adapter *adapter,
IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), vmvir);
}
+int ixgbe_set_rate_limit(struct net_device *dev, int index, u32 *tx_rate);
+
#endif /* _IXGBE_SRIOV_H_ */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 09b4188..d84d69a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -574,6 +574,7 @@ struct netdev_queue {
#ifdef CONFIG_BQL
struct dql dql;
#endif
+ unsigned long rate_limit;
} ____cacheline_aligned_in_smp;
static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
@@ -932,6 +933,14 @@ struct netdev_fcoe_hbainfo {
* that determine carrier state from physical hardware properties (eg
* network cables) or protocol-dependent mechanisms (eg
* USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function.
+ *
+ * int (*ndo_set_ratelimit)(struct net_device *dev,
+ * int queue_index, u32 *maxrate)
+ * Called to set the rate limit in Mpbs specified by maxrate of the
+ * specified queue_index. It is expected that hardware way may quantize
+ * the rate limits. In these cases the driver should guarentee the
+ * specfied maxrate is not exceeded and return the set value in maxrate.
+ * Zero should be returned on sucess otherwise use appropriate error code.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1060,6 +1069,9 @@ struct net_device_ops {
struct nlmsghdr *nlh);
int (*ndo_change_carrier)(struct net_device *dev,
bool new_carrier);
+ int (*ndo_set_ratelimit)(struct net_device *dev,
+ int queue_index,
+ u32 *max_rate);
};
/*
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 981fed3..ff61852 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -819,6 +819,59 @@ static ssize_t show_trans_timeout(struct netdev_queue *queue,
return sprintf(buf, "%lu", trans_timeout);
}
+static ssize_t show_rate_limit(struct netdev_queue *queue,
+ struct netdev_queue_attribute *attribute,
+ char *buf)
+{
+ return sprintf(buf, "%lu", queue->rate_limit);
+}
+
+static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
+{
+ struct net_device *dev = queue->dev;
+ int i;
+
+ for (i = 0; i < dev->num_tx_queues; i++)
+ if (queue == &dev->_tx[i])
+ break;
+
+ BUG_ON(i >= dev->num_tx_queues);
+
+ return i;
+}
+
+static ssize_t set_tx_rate_limit(struct netdev_queue *queue,
+ struct netdev_queue_attribute *attribute,
+ const char *buf, size_t len)
+{
+ struct net_device *dev = queue->dev;
+ int err, index = get_netdev_queue_index(queue);
+ u32 rate = 0;
+
+ err = kstrtou32(buf, 10, &rate);
+ if (err < 0)
+ return err;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ if (dev->netdev_ops->ndo_set_ratelimit)
+ err = dev->netdev_ops->ndo_set_ratelimit(dev, index, &rate);
+ else
+ err = -EOPNOTSUPP;
+ rtnl_unlock();
+
+ if (err < 0)
+ return err;
+
+ queue->rate_limit = rate;
+ return len;
+}
+
+static struct netdev_queue_attribute queue_rate_limit =
+ __ATTR(tx_rate_limit, S_IRUGO | S_IWUSR,
+ show_rate_limit, set_tx_rate_limit);
+
static struct netdev_queue_attribute queue_trans_timeout =
__ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL);
@@ -933,21 +986,6 @@ static struct attribute_group dql_group = {
#endif /* CONFIG_BQL */
#ifdef CONFIG_XPS
-static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
-{
- struct net_device *dev = queue->dev;
- int i;
-
- for (i = 0; i < dev->num_tx_queues; i++)
- if (queue == &dev->_tx[i])
- break;
-
- BUG_ON(i >= dev->num_tx_queues);
-
- return i;
-}
-
-
static ssize_t show_xps_map(struct netdev_queue *queue,
struct netdev_queue_attribute *attribute, char *buf)
{
@@ -1032,6 +1070,7 @@ static struct attribute *netdev_queue_default_attrs[] = {
#ifdef CONFIG_XPS
&xps_cpus_attribute.attr,
#endif
+ &queue_rate_limit.attr,
NULL
};
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists