* [jkirsher/next-queue PATCH 5/7] net: Add generic ndo_select_queue functions
From: Alexander Duyck @ 2018-06-11 17:41 UTC (permalink / raw)
To: netdev, intel-wired-lan, jeffrey.t.kirsher
In-Reply-To: <20180611173003.41352.25621.stgit@ahduyck-green-test.jf.intel.com>
This patch adds a generic version of the ndo_select_queue functions for
either returning 0 or selecting a queue based on the processor ID. This is
generally meant to just reduce the number of functions we have to change
in the future when we have to deal with ndo_select_queue changes.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
drivers/net/ethernet/lantiq_etop.c | 10 +---------
drivers/net/ethernet/ti/netcp_core.c | 9 +--------
drivers/staging/netlogic/xlr_net.c | 9 +--------
include/linux/netdevice.h | 2 ++
net/core/dev.c | 12 ++++++++++++
net/packet/af_packet.c | 9 ++-------
6 files changed, 19 insertions(+), 32 deletions(-)
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index afc8100..7a637b5 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -563,14 +563,6 @@ struct ltq_etop_priv {
spin_unlock_irqrestore(&priv->lock, flags);
}
-static u16
-ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
-{
- /* we are currently only using the first queue */
- return 0;
-}
-
static int
ltq_etop_init(struct net_device *dev)
{
@@ -641,7 +633,7 @@ struct ltq_etop_priv {
.ndo_set_mac_address = ltq_etop_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = ltq_etop_set_multicast_list,
- .ndo_select_queue = ltq_etop_select_queue,
+ .ndo_select_queue = dev_pick_tx_zero,
.ndo_init = ltq_etop_init,
.ndo_tx_timeout = ltq_etop_tx_timeout,
};
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index e40aa3e..2c455bd 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1889,13 +1889,6 @@ static int netcp_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
return err;
}
-static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv,
- select_queue_fallback_t fallback)
-{
- return 0;
-}
-
static int netcp_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
@@ -1972,7 +1965,7 @@ static int netcp_setup_tc(struct net_device *dev, enum tc_setup_type type,
.ndo_vlan_rx_add_vid = netcp_rx_add_vid,
.ndo_vlan_rx_kill_vid = netcp_rx_kill_vid,
.ndo_tx_timeout = netcp_ndo_tx_timeout,
- .ndo_select_queue = netcp_select_queue,
+ .ndo_select_queue = dev_pick_tx_zero,
.ndo_setup_tc = netcp_setup_tc,
};
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index e461168..4e6611e 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -290,13 +290,6 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb,
return NETDEV_TX_OK;
}
-static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
- void *accel_priv,
- select_queue_fallback_t fallback)
-{
- return (u16)smp_processor_id();
-}
-
static void xlr_hw_set_mac_addr(struct net_device *ndev)
{
struct xlr_net_priv *priv = netdev_priv(ndev);
@@ -403,7 +396,7 @@ static void xlr_stats(struct net_device *ndev, struct rtnl_link_stats64 *stats)
.ndo_open = xlr_net_open,
.ndo_stop = xlr_net_stop,
.ndo_start_xmit = xlr_net_start_xmit,
- .ndo_select_queue = xlr_net_select_queue,
+ .ndo_select_queue = dev_pick_tx_cpu_id,
.ndo_set_mac_address = xlr_net_set_mac_addr,
.ndo_set_rx_mode = xlr_set_rx_mode,
.ndo_get_stats64 = xlr_stats,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 91b3ca9..f277149 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2551,6 +2551,8 @@ struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
void dev_close_many(struct list_head *head, bool unlink);
void dev_disable_lro(struct net_device *dev);
int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
+u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb);
+u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb);
int dev_queue_xmit(struct sk_buff *skb);
int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
diff --git a/net/core/dev.c b/net/core/dev.c
index 2249294..d746fdd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3505,6 +3505,18 @@ static inline int get_xps_queue(struct net_device *dev,
#endif
}
+u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb)
+{
+ return 0;
+}
+EXPORT_SYMBOL(dev_pick_tx_zero);
+
+u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb)
+{
+ return (u16)raw_smp_processor_id() % dev->real_num_tx_queues;
+}
+EXPORT_SYMBOL(dev_pick_tx_cpu_id);
+
static u16 ___netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev)
{
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ee01856..015a18d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -275,11 +275,6 @@ static bool packet_use_direct_xmit(const struct packet_sock *po)
return po->xmit == packet_direct_xmit;
}
-static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
-{
- return (u16) raw_smp_processor_id() % dev->real_num_tx_queues;
-}
-
static u16 packet_pick_tx_queue(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
@@ -288,10 +283,10 @@ static u16 packet_pick_tx_queue(struct sk_buff *skb)
if (ops->ndo_select_queue) {
queue_index = ops->ndo_select_queue(dev, skb, NULL,
- __packet_pick_tx_queue);
+ dev_pick_tx_cpu_id);
queue_index = netdev_cap_txqueue(dev, queue_index);
} else {
- queue_index = __packet_pick_tx_queue(dev, skb);
+ queue_index = dev_pick_tx_cpu_id(dev, skb);
}
return queue_index;
^ permalink raw reply related
* [jkirsher/next-queue PATCH 4/7] net: Add support for subordinate traffic classes to netdev_pick_tx
From: Alexander Duyck @ 2018-06-11 17:41 UTC (permalink / raw)
To: netdev, intel-wired-lan, jeffrey.t.kirsher
In-Reply-To: <20180611173003.41352.25621.stgit@ahduyck-green-test.jf.intel.com>
This change makes it so that we can support the concept of subordinate
device traffic classes to the core networking code. In doing this we can
start pulling out the driver specific bits needed to support selecting a
queue based on an upper device.
The solution at is currently stands is only partially implemented. I have
the start of some XPS bits in here, but I would still need to allow for
configuration of the XPS maps on the queues reserved for the subordinate
devices. For now I am using the reference to the sb_dev XPS map as just a
way to skip the lookup of the lower device XPS map for now as that would
result in the wrong queue being picked.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 19 +++-----
drivers/net/macvlan.c | 10 +---
include/linux/netdevice.h | 4 +-
net/core/dev.c | 57 +++++++++++++++----------
4 files changed, 45 insertions(+), 45 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 6e27848..053a54c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8219,20 +8219,17 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
input, common, ring->queue_index);
}
+#ifdef IXGBE_FCOE
static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
void *accel_priv, select_queue_fallback_t fallback)
{
- struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
-#ifdef IXGBE_FCOE
struct ixgbe_adapter *adapter;
struct ixgbe_ring_feature *f;
-#endif
int txq;
- if (fwd_adapter) {
- u8 tc = netdev_get_num_tc(dev) ?
- netdev_get_prio_tc_map(dev, skb->priority) : 0;
- struct net_device *vdev = fwd_adapter->netdev;
+ if (accel_priv) {
+ u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+ struct net_device *vdev = accel_priv;
txq = vdev->tc_to_txq[tc].offset;
txq += reciprocal_scale(skb_get_hash(skb),
@@ -8241,8 +8238,6 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
return txq;
}
-#ifdef IXGBE_FCOE
-
/*
* only execute the code below if protocol is FCoE
* or FIP and we have FCoE enabled on the adapter
@@ -8268,11 +8263,9 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
txq -= f->indices;
return txq + f->offset;
-#else
- return fallback(dev, skb);
-#endif
}
+#endif
static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
struct xdp_frame *xdpf)
{
@@ -10076,7 +10069,6 @@ static int ixgbe_xdp_xmit(struct net_device *dev, int n,
.ndo_open = ixgbe_open,
.ndo_stop = ixgbe_close,
.ndo_start_xmit = ixgbe_xmit_frame,
- .ndo_select_queue = ixgbe_select_queue,
.ndo_set_rx_mode = ixgbe_set_rx_mode,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = ixgbe_set_mac,
@@ -10099,6 +10091,7 @@ static int ixgbe_xdp_xmit(struct net_device *dev, int n,
.ndo_poll_controller = ixgbe_netpoll,
#endif
#ifdef IXGBE_FCOE
+ .ndo_select_queue = ixgbe_select_queue,
.ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get,
.ndo_fcoe_ddp_target = ixgbe_fcoe_ddp_target,
.ndo_fcoe_ddp_done = ixgbe_fcoe_ddp_put,
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index adde8fc..401e1d1 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -514,7 +514,6 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
const struct macvlan_dev *vlan = netdev_priv(dev);
const struct macvlan_port *port = vlan->port;
const struct macvlan_dev *dest;
- void *accel_priv = NULL;
if (vlan->mode == MACVLAN_MODE_BRIDGE) {
const struct ethhdr *eth = (void *)skb->data;
@@ -533,15 +532,10 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
return NET_XMIT_SUCCESS;
}
}
-
- /* For packets that are non-multicast and not bridged we will pass
- * the necessary information so that the lowerdev can distinguish
- * the source of the packets via the accel_priv value.
- */
- accel_priv = vlan->accel_priv;
xmit_world:
skb->dev = vlan->lowerdev;
- return dev_queue_xmit_accel(skb, accel_priv);
+ return dev_queue_xmit_accel(skb,
+ netdev_get_sb_channel(dev) ? dev : NULL);
}
static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 41b4660..91b3ca9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2090,7 +2090,7 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv);
+ struct net_device *sb_dev);
/* returns the headroom that the master device needs to take in account
* when forwarding to this dev
@@ -2552,7 +2552,7 @@ struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
void dev_disable_lro(struct net_device *dev);
int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
int dev_queue_xmit(struct sk_buff *skb);
-int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
+int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
int register_netdevice(struct net_device *dev);
void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
diff --git a/net/core/dev.c b/net/core/dev.c
index 27fe4f2..2249294 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2704,24 +2704,26 @@ void netif_device_attach(struct net_device *dev)
* Returns a Tx hash based on the given packet descriptor a Tx queues' number
* to be used as a distribution range.
*/
-static u16 skb_tx_hash(const struct net_device *dev, struct sk_buff *skb)
+static u16 skb_tx_hash(const struct net_device *dev,
+ const struct net_device *sb_dev,
+ struct sk_buff *skb)
{
u32 hash;
u16 qoffset = 0;
u16 qcount = dev->real_num_tx_queues;
+ if (dev->num_tc) {
+ u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+
+ qoffset = sb_dev->tc_to_txq[tc].offset;
+ qcount = sb_dev->tc_to_txq[tc].count;
+ }
+
if (skb_rx_queue_recorded(skb)) {
hash = skb_get_rx_queue(skb);
while (unlikely(hash >= qcount))
hash -= qcount;
- return hash;
- }
-
- if (dev->num_tc) {
- u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
-
- qoffset = dev->tc_to_txq[tc].offset;
- qcount = dev->tc_to_txq[tc].count;
+ return hash + qoffset;
}
return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
@@ -3465,7 +3467,9 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
}
#endif /* CONFIG_NET_EGRESS */
-static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+static inline int get_xps_queue(struct net_device *dev,
+ struct net_device *sb_dev,
+ struct sk_buff *skb)
{
#ifdef CONFIG_XPS
struct xps_dev_maps *dev_maps;
@@ -3473,7 +3477,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
int queue_index = -1;
rcu_read_lock();
- dev_maps = rcu_dereference(dev->xps_maps);
+ dev_maps = rcu_dereference(sb_dev->xps_maps);
if (dev_maps) {
unsigned int tci = skb->sender_cpu - 1;
@@ -3501,17 +3505,20 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
#endif
}
-static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+static u16 ___netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev)
{
struct sock *sk = skb->sk;
int queue_index = sk_tx_queue_get(sk);
+ sb_dev = sb_dev ? : dev;
+
if (queue_index < 0 || skb->ooo_okay ||
queue_index >= dev->real_num_tx_queues) {
- int new_index = get_xps_queue(dev, skb);
+ int new_index = get_xps_queue(dev, sb_dev, skb);
if (new_index < 0)
- new_index = skb_tx_hash(dev, skb);
+ new_index = skb_tx_hash(dev, sb_dev, skb);
if (queue_index != new_index && sk &&
sk_fullsock(sk) &&
@@ -3524,9 +3531,15 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
return queue_index;
}
+static u16 __netdev_pick_tx(struct net_device *dev,
+ struct sk_buff *skb)
+{
+ return ___netdev_pick_tx(dev, skb, NULL);
+}
+
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv)
+ struct net_device *sb_dev)
{
int queue_index = 0;
@@ -3541,10 +3554,10 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_select_queue)
- queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+ queue_index = ops->ndo_select_queue(dev, skb, sb_dev,
__netdev_pick_tx);
else
- queue_index = __netdev_pick_tx(dev, skb);
+ queue_index = ___netdev_pick_tx(dev, skb, sb_dev);
queue_index = netdev_cap_txqueue(dev, queue_index);
}
@@ -3556,7 +3569,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
/**
* __dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
- * @accel_priv: private data used for L2 forwarding offload
+ * @sb_dev: suboordinate device used for L2 forwarding offload
*
* Queue a buffer for transmission to a network device. The caller must
* have set the device and priority and built the buffer before calling
@@ -3579,7 +3592,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
* the BH enable code must have IRQs enabled so that it will not deadlock.
* --BLG
*/
-static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
+static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
{
struct net_device *dev = skb->dev;
struct netdev_queue *txq;
@@ -3618,7 +3631,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
else
skb_dst_force(skb);
- txq = netdev_pick_tx(dev, skb, accel_priv);
+ txq = netdev_pick_tx(dev, skb, sb_dev);
q = rcu_dereference_bh(txq->qdisc);
trace_net_dev_queue(skb);
@@ -3692,9 +3705,9 @@ int dev_queue_xmit(struct sk_buff *skb)
}
EXPORT_SYMBOL(dev_queue_xmit);
-int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
+int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev)
{
- return __dev_queue_xmit(skb, accel_priv);
+ return __dev_queue_xmit(skb, sb_dev);
}
EXPORT_SYMBOL(dev_queue_xmit_accel);
^ permalink raw reply related
* [jkirsher/next-queue PATCH 3/7] ixgbe: Add code to populate and use macvlan tc to Tx queue map
From: Alexander Duyck @ 2018-06-11 17:41 UTC (permalink / raw)
To: netdev, intel-wired-lan, jeffrey.t.kirsher
In-Reply-To: <20180611173003.41352.25621.stgit@ahduyck-green-test.jf.intel.com>
This patch makes it so that we use the tc_to_txq mapping in the macvlan
device in order to select the Tx queue for outgoing packets.
The idea here is to try and move away from using ixgbe_select_queue and to
come up with a generic way to make this work for devices going forward. By
encoding this information in the netdev this can become something that can
be used generically as a solution for similar setups going forward.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 44 ++++++++++++++++++++++---
1 file changed, 38 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index fc23e36..6e27848 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5271,6 +5271,8 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
struct ixgbe_fwd_adapter *accel)
{
+ u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;
+ int num_tc = netdev_get_num_tc(adapter->netdev);
struct net_device *vdev = accel->netdev;
int i, baseq, err;
@@ -5282,6 +5284,11 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
accel->rx_base_queue = baseq;
accel->tx_base_queue = baseq;
+ /* record configuration for macvlan interface in vdev */
+ for (i = 0; i < num_tc; i++)
+ netdev_bind_sb_channel_queue(adapter->netdev, vdev,
+ i, rss_i, baseq + (rss_i * i));
+
for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
adapter->rx_ring[baseq + i]->netdev = vdev;
@@ -5306,6 +5313,10 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n");
+ /* unbind the queues and drop the subordinate channel config */
+ netdev_unbind_sb_channel(adapter->netdev, vdev);
+ netdev_set_sb_channel(vdev, 0);
+
clear_bit(accel->pool, adapter->fwd_bitmask);
kfree(accel);
@@ -8212,18 +8223,22 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
void *accel_priv, select_queue_fallback_t fallback)
{
struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
- struct ixgbe_adapter *adapter;
- int txq;
#ifdef IXGBE_FCOE
+ struct ixgbe_adapter *adapter;
struct ixgbe_ring_feature *f;
#endif
+ int txq;
if (fwd_adapter) {
- adapter = netdev_priv(dev);
- txq = reciprocal_scale(skb_get_hash(skb),
- adapter->num_rx_queues_per_pool);
+ u8 tc = netdev_get_num_tc(dev) ?
+ netdev_get_prio_tc_map(dev, skb->priority) : 0;
+ struct net_device *vdev = fwd_adapter->netdev;
+
+ txq = vdev->tc_to_txq[tc].offset;
+ txq += reciprocal_scale(skb_get_hash(skb),
+ vdev->tc_to_txq[tc].count);
- return txq + fwd_adapter->tx_base_queue;
+ return txq;
}
#ifdef IXGBE_FCOE
@@ -8777,6 +8792,11 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data)
/* if we cannot find a free pool then disable the offload */
netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n");
macvlan_release_l2fw_offload(vdev);
+
+ /* unbind the queues and drop the subordinate channel config */
+ netdev_unbind_sb_channel(adapter->netdev, vdev);
+ netdev_set_sb_channel(vdev, 0);
+
kfree(accel);
return 0;
@@ -9785,6 +9805,13 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
if (!macvlan_supports_dest_filter(vdev))
return ERR_PTR(-EMEDIUMTYPE);
+ /* We need to lock down the macvlan to be a single queue device so that
+ * we can reuse the tc_to_txq field in the macvlan netdev to represent
+ * the queue mapping to our netdev.
+ */
+ if (netif_is_multiqueue(vdev))
+ return ERR_PTR(-ERANGE);
+
pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
if (pool == adapter->num_rx_pools) {
u16 used_pools = adapter->num_vfs + adapter->num_rx_pools;
@@ -9841,6 +9868,7 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
return ERR_PTR(-ENOMEM);
set_bit(pool, adapter->fwd_bitmask);
+ netdev_set_sb_channel(vdev, pool);
accel->pool = pool;
accel->netdev = vdev;
@@ -9882,6 +9910,10 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
ring->netdev = NULL;
}
+ /* unbind the queues and drop the subordinate channel config */
+ netdev_unbind_sb_channel(pdev, accel->netdev);
+ netdev_set_sb_channel(accel->netdev, 0);
+
clear_bit(accel->pool, adapter->fwd_bitmask);
kfree(accel);
}
^ permalink raw reply related
* [jkirsher/next-queue PATCH 2/7] net: Add support for subordinate device traffic classes
From: Alexander Duyck @ 2018-06-11 17:41 UTC (permalink / raw)
To: netdev, intel-wired-lan, jeffrey.t.kirsher
In-Reply-To: <20180611173003.41352.25621.stgit@ahduyck-green-test.jf.intel.com>
This patch is meant to provide the basic tools needed to allow us to create
subordinate device traffic classes. The general idea here is to allow
subdividing the queues of a device into queue groups accessible through an
upper device such as a macvlan.
The idea here is to enforce the idea that an upper device has to be a
single queue device, ideally with IFF_NO_QUQUE set. With that being the
case we can pretty much guarantee that the tc_to_txq mappings and XPS maps
for the upper device are unused. As such we could reuse those in order to
support subdividing the lower device and distributing those queues between
the subordinate devices.
In order to distinguish between a regular set of traffic classes and if a
device is carrying subordinate traffic classes I changed num_tc from a u8
to a s16 value and use the negative values to represent the suboordinate
pool values. So starting at -1 and running to -32768 we can encode those as
pool values, and the existing values of 0 to 15 can be maintained.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
include/linux/netdevice.h | 16 ++++++++
net/core/dev.c | 89 +++++++++++++++++++++++++++++++++++++++++++++
net/core/net-sysfs.c | 21 ++++++++++-
3 files changed, 124 insertions(+), 2 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3ec9850..41b4660 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -569,6 +569,9 @@ struct netdev_queue {
* (/sys/class/net/DEV/Q/trans_timeout)
*/
unsigned long trans_timeout;
+
+ /* Suboordinate device that the queue has been assigned to */
+ struct net_device *sb_dev;
/*
* write-mostly part
*/
@@ -1978,7 +1981,7 @@ struct net_device {
#ifdef CONFIG_DCB
const struct dcbnl_rtnl_ops *dcbnl_ops;
#endif
- u8 num_tc;
+ s16 num_tc;
struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
u8 prio_tc_map[TC_BITMASK + 1];
@@ -2032,6 +2035,17 @@ int netdev_get_num_tc(struct net_device *dev)
return dev->num_tc;
}
+void netdev_unbind_sb_channel(struct net_device *dev,
+ struct net_device *sb_dev);
+int netdev_bind_sb_channel_queue(struct net_device *dev,
+ struct net_device *sb_dev,
+ u8 tc, u16 count, u16 offset);
+int netdev_set_sb_channel(struct net_device *dev, u16 channel);
+static inline int netdev_get_sb_channel(struct net_device *dev)
+{
+ return max_t(int, -dev->num_tc, 0);
+}
+
static inline
struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
unsigned int index)
diff --git a/net/core/dev.c b/net/core/dev.c
index 6e18242..27fe4f2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2068,11 +2068,13 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq)
struct netdev_tc_txq *tc = &dev->tc_to_txq[0];
int i;
+ /* walk through the TCs and see if it falls into any of them */
for (i = 0; i < TC_MAX_QUEUE; i++, tc++) {
if ((txq - tc->offset) < tc->count)
return i;
}
+ /* didn't find it, just return -1 to indicate no match */
return -1;
}
@@ -2215,7 +2217,14 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
bool active = false;
if (dev->num_tc) {
+ /* Do not allow XPS on subordinate device directly */
num_tc = dev->num_tc;
+ if (num_tc < 0)
+ return -EINVAL;
+
+ /* If queue belongs to subordinate dev use its map */
+ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
tc = netdev_txq_to_tc(dev, index);
if (tc < 0)
return -EINVAL;
@@ -2366,11 +2375,25 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
EXPORT_SYMBOL(netif_set_xps_queue);
#endif
+static void netdev_unbind_all_sb_channels(struct net_device *dev)
+{
+ struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];
+
+ /* Unbind any subordinate channels */
+ while (txq-- != &dev->_tx[0]) {
+ if (txq->sb_dev)
+ netdev_unbind_sb_channel(dev, txq->sb_dev);
+ }
+}
+
void netdev_reset_tc(struct net_device *dev)
{
#ifdef CONFIG_XPS
netif_reset_xps_queues_gt(dev, 0);
#endif
+ netdev_unbind_all_sb_channels(dev);
+
+ /* Reset TC configuration of device */
dev->num_tc = 0;
memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq));
memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
@@ -2399,11 +2422,77 @@ int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
#ifdef CONFIG_XPS
netif_reset_xps_queues_gt(dev, 0);
#endif
+ netdev_unbind_all_sb_channels(dev);
+
dev->num_tc = num_tc;
return 0;
}
EXPORT_SYMBOL(netdev_set_num_tc);
+void netdev_unbind_sb_channel(struct net_device *dev,
+ struct net_device *sb_dev)
+{
+ struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];
+
+#ifdef CONFIG_XPS
+ netif_reset_xps_queues_gt(sb_dev, 0);
+#endif
+ memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq));
+ memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map));
+
+ while (txq-- != &dev->_tx[0]) {
+ if (txq->sb_dev == sb_dev)
+ txq->sb_dev = NULL;
+ }
+}
+EXPORT_SYMBOL(netdev_unbind_sb_channel);
+
+int netdev_bind_sb_channel_queue(struct net_device *dev,
+ struct net_device *sb_dev,
+ u8 tc, u16 count, u16 offset)
+{
+ /* Make certain the sb_dev and dev are already configured */
+ if (sb_dev->num_tc >= 0 || tc >= dev->num_tc)
+ return -EINVAL;
+
+ /* We cannot hand out queues we don't have */
+ if ((offset + count) > dev->real_num_tx_queues)
+ return -EINVAL;
+
+ /* Record the mapping */
+ sb_dev->tc_to_txq[tc].count = count;
+ sb_dev->tc_to_txq[tc].offset = offset;
+
+ /* Provide a way for Tx queue to find the tc_to_txq map or
+ * XPS map for itself.
+ */
+ while (count--)
+ netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev;
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_bind_sb_channel_queue);
+
+int netdev_set_sb_channel(struct net_device *dev, u16 channel)
+{
+ /* Do not use a multiqueue device to represent a subordinate channel */
+ if (netif_is_multiqueue(dev))
+ return -ENODEV;
+
+ /* We allow channels 1 - 32767 to be used for subordinate channels.
+ * Channel 0 is meant to be "native" mode and used only to represent
+ * the main root device. We allow writing 0 to reset the device back
+ * to normal mode after being used as a subordinate channel.
+ */
+ if (channel > S16_MAX)
+ return -EINVAL;
+
+ dev->num_tc = -channel;
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_set_sb_channel);
+
/*
* Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
* greater than real_num_tx_queues stale skbs on the qdisc must be flushed.
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 335c6a4..bd067b1 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1054,11 +1054,23 @@ static ssize_t traffic_class_show(struct netdev_queue *queue,
return -ENOENT;
index = get_netdev_queue_index(queue);
+
+ /* If queue belongs to subordinate dev use its tc mapping */
+ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
tc = netdev_txq_to_tc(dev, index);
if (tc < 0)
return -EINVAL;
- return sprintf(buf, "%u\n", tc);
+ /* We can report the traffic class one of two ways:
+ * Subordinate device traffic classes are reported with the traffic
+ * class first, and then the subordinate class so for example TC0 on
+ * subordinate device 2 will be reported as "0-2". If the queue
+ * belongs to the root device it will be reported with just the
+ * traffic class, so just "0" for TC 0 for example.
+ */
+ return dev->num_tc < 0 ? sprintf(buf, "%u%d\n", tc, dev->num_tc) :
+ sprintf(buf, "%u\n", tc);
}
#ifdef CONFIG_XPS
@@ -1225,7 +1237,14 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
index = get_netdev_queue_index(queue);
if (dev->num_tc) {
+ /* Do not allow XPS on subordinate device directly */
num_tc = dev->num_tc;
+ if (num_tc < 0)
+ return -EINVAL;
+
+ /* If queue belongs to subordinate dev use its map */
+ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
tc = netdev_txq_to_tc(dev, index);
if (tc < 0)
return -EINVAL;
^ permalink raw reply related
* [jkirsher/next-queue PATCH 1/7] net-sysfs: Drop support for XPS and traffic_class on single queue device
From: Alexander Duyck @ 2018-06-11 17:40 UTC (permalink / raw)
To: netdev, intel-wired-lan, jeffrey.t.kirsher
In-Reply-To: <20180611173003.41352.25621.stgit@ahduyck-green-test.jf.intel.com>
This patch makes it so that we do not report the traffic class or allow XPS
configuration on single queue devices. This is mostly to avoid unnecessary
complexity with changes I have planned that will allow us to reuse
the unused tc_to_txq and XPS configuration on a single queue device to
allow it to make use of a subset of queues on an underlying device.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
net/core/net-sysfs.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index bb7e80f..335c6a4 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1047,9 +1047,14 @@ static ssize_t traffic_class_show(struct netdev_queue *queue,
char *buf)
{
struct net_device *dev = queue->dev;
- int index = get_netdev_queue_index(queue);
- int tc = netdev_txq_to_tc(dev, index);
+ int index;
+ int tc;
+ if (!netif_is_multiqueue(dev))
+ return -ENOENT;
+
+ index = get_netdev_queue_index(queue);
+ tc = netdev_txq_to_tc(dev, index);
if (tc < 0)
return -EINVAL;
@@ -1214,6 +1219,9 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
cpumask_var_t mask;
unsigned long index;
+ if (!netif_is_multiqueue(dev))
+ return -ENOENT;
+
index = get_netdev_queue_index(queue);
if (dev->num_tc) {
@@ -1260,6 +1268,9 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue,
cpumask_var_t mask;
int err;
+ if (!netif_is_multiqueue(dev))
+ return -ENOENT;
+
if (!capable(CAP_NET_ADMIN))
return -EPERM;
^ permalink raw reply related
* [jkirsher/next-queue PATCH 0/7] Add support for L2 Fwd Offload w/o ndo_select_queue
From: Alexander Duyck @ 2018-06-11 17:40 UTC (permalink / raw)
To: netdev, intel-wired-lan, jeffrey.t.kirsher
This patch series is meant to allow support for the L2 forward offload, aka
MACVLAN offload without the need for using ndo_select_queue.
The existing solution currently requires that we use ndo_select_queue in
the transmit path if we want to associate specific Tx queues with a given
MACVLAN interface. In order to get away from this we need to repurpose the
tc_to_txq array and XPS pointer for the MACVLAN interface and use those as
a means of accessing the queues on the lower device. As a result we cannot
offload a device that is configured as multiqueue, however it doesn't
really make sense to configure a macvlan interfaced as being multiqueue
anyway since it doesn't really have a qdisc of its own in the first place.
I am submitting this as an RFC for the netdev mailing list, and officially
submitting it for testing to Jeff Kirsher's next-queue in order to validate
the ixgbe specific bits.
The big changes in this set are:
Allow lower device to update tc_to_txq and XPS map of offloaded MACVLAN
Disable XPS for single queue devices
Replace accel_priv with sb_dev in ndo_select_queue
Add sb_dev parameter to fallback function for ndo_select_queue
Consolidated ndo_select_queue functions that appeared to be duplicates
---
Alexander Duyck (7):
net-sysfs: Drop support for XPS and traffic_class on single queue device
net: Add support for subordinate device traffic classes
ixgbe: Add code to populate and use macvlan tc to Tx queue map
net: Add support for subordinate traffic classes to netdev_pick_tx
net: Add generic ndo_select_queue functions
net: allow ndo_select_queue to pass netdev
net: allow fallback function to pass netdev
drivers/infiniband/hw/hfi1/vnic_main.c | 2
drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c | 4 -
drivers/net/bonding/bond_main.c | 3
drivers/net/ethernet/amazon/ena/ena_netdev.c | 5 -
drivers/net/ethernet/broadcom/bcmsysport.c | 6 -
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 6 +
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 3
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 5 -
drivers/net/ethernet/hisilicon/hns/hns_enet.c | 5 -
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 62 ++++++--
drivers/net/ethernet/lantiq_etop.c | 10 -
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 7 +
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3
drivers/net/ethernet/mellanox/mlx5/core/en.h | 3
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 5 -
drivers/net/ethernet/renesas/ravb_main.c | 3
drivers/net/ethernet/sun/ldmvsw.c | 3
drivers/net/ethernet/sun/sunvnet.c | 3
drivers/net/ethernet/ti/netcp_core.c | 9 -
drivers/net/hyperv/netvsc_drv.c | 6 -
drivers/net/macvlan.c | 10 -
drivers/net/net_failover.c | 7 +
drivers/net/team/team.c | 3
drivers/net/tun.c | 3
drivers/net/wireless/marvell/mwifiex/main.c | 3
drivers/net/xen-netback/interface.c | 4 -
drivers/net/xen-netfront.c | 3
drivers/staging/netlogic/xlr_net.c | 9 -
drivers/staging/rtl8188eu/os_dep/os_intfs.c | 3
drivers/staging/rtl8723bs/os_dep/os_intfs.c | 7 -
include/linux/netdevice.h | 32 ++++
net/core/dev.c | 154 ++++++++++++++++++---
net/core/net-sysfs.c | 36 +++++
net/mac80211/iface.c | 4 -
net/packet/af_packet.c | 9 -
35 files changed, 306 insertions(+), 134 deletions(-)
^ permalink raw reply
* Backport bonding patches to fix active-passive
From: Nate Clark @ 2018-06-11 17:44 UTC (permalink / raw)
Cc: netdev
Hi,
On the latest 4.9 stable active-passive bonding does not always
failover to the passive slave when carrier is lost on the active
slave. It seems that the issue stems from the backport of
c4adfc822bf5d8e97660b6114b5a8892530ce8cb, bonding: make speed, duplex
setting consistent with link state. There were subsequent patches
which resolved issues with the change to bond_update_speed_duplex
which were not backported. The three commits which seem to resolve the
issue are b5bf0f5b16b9c316c34df9f31d4be8729eb86845,
3f3c278c94dd994fe0d9f21679ae19b9c0a55292 and
ad729bc9acfb7c47112964b4877ef5404578ed13. There are other commits in
mainline which also revolve around
c4adfc822bf5d8e97660b6114b5a8892530ce8cb but are not necessary to
resolving the active-passive failover problems.
Would it be possible to queue up the three commits for backporting to
4.9 stable:
b5bf0f5b16b9c316c34df9f31d4be8729eb86845 bonding: correctly update
link status during mii-commit
3f3c278c94dd994fe0d9f21679ae19b9c0a55292 bonding: fix active-backup transition
ad729bc9acfb7c47112964b4877ef5404578ed13 bonding: require speed/duplex
only for 802.3ad, alb and tlb
All of those commits apply cleanly to 4.9.107.
Thanks,
-nate
^ permalink raw reply
* Re: Qualcomm rmnet driver and qmi_wwan
From: Bjørn Mork @ 2018-06-11 17:43 UTC (permalink / raw)
To: Subash Abhinov Kasiviswanathan; +Cc: Daniele Palmas, Dan Williams, netdev
In-Reply-To: <4b74bb1d92b9e9351bc504d18f96116b@codeaurora.org>
Subash Abhinov Kasiviswanathan <subashab@codeaurora.org> writes:
>> thanks, I will test it on Monday.
>>
>> Just a question for my knowledge: is the new sysfs attribute really
>> needed? I mean, is there not any other way to understand from qmi_wwan
>> without user intervention that there is the rmnet device attached?
>>
>> Regards,
>> Daniele
>>
>
> Hi Daniele
>
> You can check for the rx_handler attached to qmi_wwan dev and see if it
> belongs to rmnet. You can use the attached patch for it but it think the
> sysfs way might be a bit cleaner.
>
> --
> Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
> a Linux Foundation Collaborative Project
>
> From f7a2b90948da47ade1b345eddb37b721f5ab65f4 Mon Sep 17 00:00:00 2001
> From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
> Date: Sat, 9 Jun 2018 11:14:22 -0600
> Subject: [PATCH] net: qmi_wwan: Allow packets to pass through to rmnet
>
> Pass through mode is to allow packets in MAP format to be passed
> on to rmnet if the rmnet rx handler is attached to it.
>
> Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
> ---
> drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 4 +++-
> drivers/net/usb/qmi_wwan.c | 10 ++++++++++
> include/linux/if_rmnet.h | 20 ++++++++++++++++++++
> 3 files changed, 33 insertions(+), 1 deletion(-)
> create mode 100644 include/linux/if_rmnet.h
>
> diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
> index 5f4e447..164a18f 100644
> --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
> +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
> @@ -17,6 +17,7 @@
> #include <linux/module.h>
> #include <linux/netlink.h>
> #include <linux/netdevice.h>
> +#include <linux/if_rmnet.h>
> #include "rmnet_config.h"
> #include "rmnet_handlers.h"
> #include "rmnet_vnd.h"
> @@ -48,10 +49,11 @@
> [IFLA_RMNET_FLAGS] = { .len = sizeof(struct ifla_rmnet_flags) },
> };
>
> -static int rmnet_is_real_dev_registered(const struct net_device *real_dev)
> +int rmnet_is_real_dev_registered(const struct net_device *real_dev)
> {
> return rcu_access_pointer(real_dev->rx_handler) == rmnet_rx_handler;
> }
> +EXPORT_SYMBOL(rmnet_is_real_dev_registered);
>
> /* Needs rtnl lock */
> static struct rmnet_port*
> diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
> index f52a9be..abdae63 100644
> --- a/drivers/net/usb/qmi_wwan.c
> +++ b/drivers/net/usb/qmi_wwan.c
> @@ -22,6 +22,7 @@
> #include <linux/usb/cdc.h>
> #include <linux/usb/usbnet.h>
> #include <linux/usb/cdc-wdm.h>
> +#include <linux/if_rmnet.h>
>
> /* This driver supports wwan (3G/LTE/?) devices using a vendor
> * specific management protocol called Qualcomm MSM Interface (QMI) -
> @@ -354,6 +355,10 @@ static ssize_t add_mux_store(struct device *d, struct device_attribute *attr, c
> if (kstrtou8(buf, 0, &mux_id))
> return -EINVAL;
>
> + /* rmnet is already attached here */
> + if (rmnet_is_real_dev_registered(to_net_dev(d)))
> + return -EINVAL;
> +
Maybe rmnet_is_real_dev_registered(dev->net) instead, since we use that
elsewhere in this function?
> /* mux_id [1 - 0x7f] range empirically found */
> if (mux_id < 1 || mux_id > 0x7f)
> return -EINVAL;
> @@ -543,6 +548,11 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
> if (skb->len < dev->net->hard_header_len)
> return 0;
>
> + if (rawip && rmnet_is_real_dev_registered(skb->dev)) {
> + skb->protocol = htons(ETH_P_MAP);
> + return (netif_rx(skb) == NET_RX_SUCCESS);
> + }
Like Daniele said: It would be good to have some way to know when the
rawip condition fails. Or even better: Automatically force rawip mode
when the rmnet driver attaches. But that doesn't seem possible? No
notifications or anything when an rx handler is registered?
Hmm, looking at this I wonder: Is the rawip check really necessary? You
skip all the extra rawip code in the driver anyway, so I don't see how
it matters. But maybe the ethernet header_ops are a problem?
And I wonder about using skb->dev here. Does that really work? I
didn't think we set that until later. Why not use dev->net instead?
Bjørn
^ permalink raw reply
* Re: [PATCH] qemu: Introduce VIRTIO_NET_F_STANDBY feature bit to virtio_net
From: Michael S. Tsirkin @ 2018-06-11 17:26 UTC (permalink / raw)
To: Sridhar Samudrala
Cc: netdev, virtualization, virtio-dev, jesse.brandeburg,
alexander.h.duyck, kubakici, jasowang, loseweigh, jiri,
aaron.f.brown, qemu-devel
In-Reply-To: <1525734594-11134-1-git-send-email-sridhar.samudrala@intel.com>
On Mon, May 07, 2018 at 04:09:54PM -0700, Sridhar Samudrala wrote:
> This feature bit can be used by hypervisor to indicate virtio_net device to
> act as a standby for another device with the same MAC address.
>
> I tested this with a small change to the patch to mark the STANDBY feature 'true'
> by default as i am using libvirt to start the VMs.
> Is there a way to pass the newly added feature bit 'standby' to qemu via libvirt
> XML file?
>
> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
So I do not think we can commit to this interface: we
really need to control visibility of the primary device.
However just for testing purposes, we could add a non-stable
interface "x-standby" with the understanding that as any
x- prefix it's unstable and will be changed down the road,
likely in the next release.
> ---
> hw/net/virtio-net.c | 2 ++
> include/standard-headers/linux/virtio_net.h | 3 +++
> 2 files changed, 5 insertions(+)
>
> diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
> index 90502fca7c..38b3140670 100644
> --- a/hw/net/virtio-net.c
> +++ b/hw/net/virtio-net.c
> @@ -2198,6 +2198,8 @@ static Property virtio_net_properties[] = {
> true),
> DEFINE_PROP_INT32("speed", VirtIONet, net_conf.speed, SPEED_UNKNOWN),
> DEFINE_PROP_STRING("duplex", VirtIONet, net_conf.duplex_str),
> + DEFINE_PROP_BIT64("standby", VirtIONet, host_features, VIRTIO_NET_F_STANDBY,
> + false),
> DEFINE_PROP_END_OF_LIST(),
> };
>
> diff --git a/include/standard-headers/linux/virtio_net.h b/include/standard-headers/linux/virtio_net.h
> index e9f255ea3f..01ec09684c 100644
> --- a/include/standard-headers/linux/virtio_net.h
> +++ b/include/standard-headers/linux/virtio_net.h
> @@ -57,6 +57,9 @@
> * Steering */
> #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */
>
> +#define VIRTIO_NET_F_STANDBY 62 /* Act as standby for another device
> + * with the same MAC.
> + */
> #define VIRTIO_NET_F_SPEED_DUPLEX 63 /* Device set linkspeed and duplex */
>
> #ifndef VIRTIO_NET_NO_LEGACY
> --
> 2.14.3
^ permalink raw reply
* [PATCH] iwlwifi: pcie: make array prop static, shrinks object size
From: Colin King @ 2018-06-11 17:15 UTC (permalink / raw)
To: Johannes Berg, Emmanuel Grumbach, Luca Coelho,
Intel Linux Wireless, Kalle Valo, David S . Miller,
linux-wireless, netdev
Cc: kernel-janitors, linux-kernel
From: Colin Ian King <colin.king@canonical.com>
Don't populate the read-only array 'prop' on the stack but
instead make it static. Makes the object code smaller by 20 bytes:
Before:
text data bss dec hex filename
71659 14614 576 86849 15341 trans.o
After:
text data bss dec hex filename
71479 14774 576 86829 1532d trans.o
(gcc version 7.3.0 x86_64)
Signed-off-by: Colin Ian King <colin.king@canonical.com>
---
drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 7229991ae70d..c4626ebe5da1 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1946,7 +1946,7 @@ static void iwl_trans_pcie_removal_wk(struct work_struct *wk)
struct iwl_trans_pcie_removal *removal =
container_of(wk, struct iwl_trans_pcie_removal, work);
struct pci_dev *pdev = removal->pdev;
- char *prop[] = {"EVENT=INACCESSIBLE", NULL};
+ static char *prop[] = {"EVENT=INACCESSIBLE", NULL};
dev_err(&pdev->dev, "Device gone - attempting removal\n");
kobject_uevent_env(&pdev->dev.kobj, KOBJ_CHANGE, prop);
--
2.17.0
^ permalink raw reply related
* [net] fq_codel: fix NULL pointer deref in fq_codel_reset
From: Jeff Kirsher @ 2018-06-11 17:00 UTC (permalink / raw)
To: davem
Cc: Jacob Keller, netdev, nhorman, sassmann, jogreene, Eric Dumazet,
Jeff Kirsher
From: Jacob Keller <jacob.e.keller@intel.com>
The function qdisc_create_dftl attempts to create a default qdisc. If
this fails, it calls qdisc_destroy when cleaning up. The qdisc_destroy
function calls the ->reset op on the qdisc.
In the case of sch_fq_codel.c, this function will panic when the qdisc
wasn't properly initialized:
kernel: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
kernel: IP: fq_codel_reset+0x58/0xd0 [sch_fq_codel]
kernel: PGD 0 P4D 0
kernel: Oops: 0000 [#1] SMP PTI
kernel: Modules linked in: i40iw i40e(OE) xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack tun bridge stp llc devlink ebtable_filter ebtables ip6table_filter ip6_tables rpcrdma ib_isert iscsi_target_mod sunrpc ib_iser libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm intel_rapl sb_edac x86_pkg_temp_thermal intel_powerclamp coretemp kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel intel_cstate iTCO_wdt iTCO_vendor_support intel_uncore ib_core intel_rapl_perf mei_me mei joydev i2c_i801 lpc_ich ioatdma shpchp wmi sch_fq_codel xfs libcrc32c mgag200 ixgbe drm_kms_helper isci ttm fi
rewire_ohci
kernel: mdio drm igb libsas crc32c_intel firewire_core ptp pps_core scsi_transport_sas crc_itu_t dca i2c_algo_bit ipmi_si ipmi_devintf ipmi_msghandler [last unloaded: i40e]
kernel: CPU: 10 PID: 4219 Comm: ip Tainted: G OE 4.16.13custom-fq-codel-test+ #3
kernel: Hardware name: Intel Corporation S2600CO/S2600CO, BIOS SE5C600.86B.02.05.0004.051120151007 05/11/2015
kernel: RIP: 0010:fq_codel_reset+0x58/0xd0 [sch_fq_codel]
kernel: RSP: 0018:ffffbfbf4c1fb620 EFLAGS: 00010246
kernel: RAX: 0000000000000400 RBX: 0000000000000000 RCX: 00000000000005b9
kernel: RDX: 0000000000000000 RSI: ffff9d03264a60c0 RDI: ffff9cfd17b31c00
kernel: RBP: 0000000000000001 R08: 00000000000260c0 R09: ffffffffb679c3e9
kernel: R10: fffff1dab06a0e80 R11: ffff9cfd163af800 R12: ffff9cfd17b31c00
kernel: R13: 0000000000000001 R14: ffff9cfd153de600 R15: 0000000000000001
kernel: FS: 00007fdec2f92800(0000) GS:ffff9d0326480000(0000) knlGS:0000000000000000
kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
kernel: CR2: 0000000000000008 CR3: 0000000c1956a006 CR4: 00000000000606e0
kernel: Call Trace:
kernel: qdisc_destroy+0x56/0x140
kernel: qdisc_create_dflt+0x8b/0xb0
kernel: mq_init+0xc1/0xf0
kernel: qdisc_create_dflt+0x5a/0xb0
kernel: dev_activate+0x205/0x230
kernel: __dev_open+0xf5/0x160
kernel: __dev_change_flags+0x1a3/0x210
kernel: dev_change_flags+0x21/0x60
kernel: do_setlink+0x660/0xdf0
kernel: ? down_trylock+0x25/0x30
kernel: ? xfs_buf_trylock+0x1a/0xd0 [xfs]
kernel: ? rtnl_newlink+0x816/0x990
kernel: ? _xfs_buf_find+0x327/0x580 [xfs]
kernel: ? _cond_resched+0x15/0x30
kernel: ? kmem_cache_alloc+0x20/0x1b0
kernel: ? rtnetlink_rcv_msg+0x200/0x2f0
kernel: ? rtnl_calcit.isra.30+0x100/0x100
kernel: ? netlink_rcv_skb+0x4c/0x120
kernel: ? netlink_unicast+0x19e/0x260
kernel: ? netlink_sendmsg+0x1ff/0x3c0
kernel: ? sock_sendmsg+0x36/0x40
kernel: ? ___sys_sendmsg+0x295/0x2f0
kernel: ? ebitmap_cmp+0x6d/0x90
kernel: ? dev_get_by_name_rcu+0x73/0x90
kernel: ? skb_dequeue+0x52/0x60
kernel: ? __inode_wait_for_writeback+0x7f/0xf0
kernel: ? bit_waitqueue+0x30/0x30
kernel: ? fsnotify_grab_connector+0x3c/0x60
kernel: ? __sys_sendmsg+0x51/0x90
kernel: ? do_syscall_64+0x74/0x180
kernel: ? entry_SYSCALL_64_after_hwframe+0x3d/0xa2
kernel: Code: 00 00 48 89 87 00 02 00 00 8b 87 a0 01 00 00 85 c0 0f 84 84 00 00 00 31 ed 48 63 dd 83 c5 01 48 c1 e3 06 49 03 9c 24 90 01 00 00 <48> 8b 73 08 48 8b 3b e8 6c 9a 4f f6 48 8d 43 10 48 c7 03 00 00
kernel: RIP: fq_codel_reset+0x58/0xd0 [sch_fq_codel] RSP: ffffbfbf4c1fb620
kernel: CR2: 0000000000000008
kernel: ---[ end trace e81a62bede66274e ]---
This occurs because if fq_codel_init fails, it has left the private data
in an incomplete state. For example, if tcf_block_get fails, (as in the
above panic), then q->flows and q->backlogs will be NULL. Thus they will
cause NULL pointer access when attempting to reset them in
fq_codel_reset.
We could mitigate some of these issues by changing fq_codel_init to more
explicitly cleanup after itself when failing. For example, we could
ensure that q->flowcnt was set to 0 so that the loop over each flow in
fq_codel_reset would not trigger. However, this would not prevent a NULL
pointer dereference when attempting to memset the q->backlogs.
Instead, just add a NULL check prior to attempting to reset these
fields.
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
net/sched/sch_fq_codel.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 22fa13cf5d8b..1658c314ee40 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -352,14 +352,17 @@ static void fq_codel_reset(struct Qdisc *sch)
INIT_LIST_HEAD(&q->new_flows);
INIT_LIST_HEAD(&q->old_flows);
- for (i = 0; i < q->flows_cnt; i++) {
- struct fq_codel_flow *flow = q->flows + i;
+ if (q->flows) {
+ for (i = 0; i < q->flows_cnt; i++) {
+ struct fq_codel_flow *flow = q->flows + i;
- fq_codel_flow_purge(flow);
- INIT_LIST_HEAD(&flow->flowchain);
- codel_vars_init(&flow->cvars);
+ fq_codel_flow_purge(flow);
+ INIT_LIST_HEAD(&flow->flowchain);
+ codel_vars_init(&flow->cvars);
+ }
}
- memset(q->backlogs, 0, q->flows_cnt * sizeof(u32));
+ if (q->backlogs)
+ memset(q->backlogs, 0, q->flows_cnt * sizeof(u32));
sch->q.qlen = 0;
sch->qstats.backlog = 0;
q->memory_usage = 0;
--
2.17.1
^ permalink raw reply related
* Re: [PATCH nf-next] netfilter: nft_reject_bridge: remove unnecessary ttl set
From: Taehee Yoo @ 2018-06-11 16:54 UTC (permalink / raw)
To: davem, Steffen Klassert; +Cc: netdev, Taehee Yoo
In-Reply-To: <20180611163505.9827-1-ap420073@gmail.com>
2018-06-12 1:35 GMT+09:00 Taehee Yoo <ap420073@gmail.com>:
> In the nft_reject_br_send_v4_tcp_reset(), a ttl is set by
> the nf_reject_ip_tcphdr_put(). so, below code is unnecessary.
>
> Signed-off-by: Taehee Yoo <ap420073@gmail.com>
> ---
> net/bridge/netfilter/nft_reject_bridge.c | 3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
>
> diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
> index eaf05de..e0b082c 100644
> --- a/net/bridge/netfilter/nft_reject_bridge.c
> +++ b/net/bridge/netfilter/nft_reject_bridge.c
> @@ -89,8 +89,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net,
> niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
> net->ipv4.sysctl_ip_default_ttl);
> nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
> - niph->ttl = net->ipv4.sysctl_ip_default_ttl;
> - niph->tot_len = htons(nskb->len);
> + niph->tot_len = htons(nskb->len);
> ip_send_check(niph);
>
> nft_reject_br_push_etherhdr(oldskb, nskb);
> --
> 2.9.3
>
I'm so sorry, I sent this to you by mistake.
Please ignore this.
Thanks
^ permalink raw reply
* mainline: x86_64: kernel panic: RIP: 0010:__xfrm_policy_check+0xcb/0x690
From: Naresh Kamboju @ 2018-06-11 16:41 UTC (permalink / raw)
To: netdev
Cc: steffen.klassert, David S. Miller, herbert,
open list:KERNEL SELFTEST FRAMEWORK, open list
Kernel panic on x86_64 machine running mainline 4.17.0 kernel while testing
selftests bpf test_tunnel.sh test caused this kernel panic.
I have noticed this kernel panic start happening from
4.17.0-rc7-next-20180529 and still happening on 4.17.0-next-20180608.
[ 213.638287] BUG: unable to handle kernel NULL pointer dereference
at 0000000000000008
++[ ip xfrm poli 213.674036] PGD 0 P4D 0
[ 213.674118] audit: type=1327 audit(1528917683.623:7):
proctitle=6970007866726D00706F6C69637900616464007372630031302E312E312E3130302F3332006473740031302E312E312E3230302F33320064697200696E00746D706C00737263003137322E31362E312E31303000647374003137322E31362E312E3230300070726F746F006573700072657169640031006D6F64650074756E6E
[ 213.677950] Oops: 0000 [#1] SMP PTI
cy[ add src 10.1. 213.677952] CPU: 2 PID: 0 Comm: swapper/2 Tainted:
G W 4.17.0-next-20180608 #1
[ 213.677953] Hardware name: Supermicro SYS-5019S-ML/X11SSH-F, BIOS
2.0b 07/27/2017
[ 213.726998] RIP: 0010:__xfrm_policy_check+0xcb/0x690
[ 213.731962] Code: 80 3d 0a d8 f1 00 00 0f 84 c1 02 00 00 4c 8b 25
2b af f4 00 e8 66 a6 6a ff 85 c0 74 0d 80 3d eb d7 f1 00 00 0f 84 d5
02 00 00 <49> 8b 44 24 08 48 85 c0 74 0c 48 8d b5 78 ff ff ff 4c 89 ff
ff d0
1.[100/32 dst 10. 213.750836] RSP: 0018:ffff91cf6fd03a48 EFLAGS: 00010246
[ 213.757441] RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000002
[ 213.764566] RDX: ffffffffb863ebe0 RSI: 0000000000000000 RDI: 0000000000000000
[ 213.771688] RBP: ffff91cf6fd03b18 R08: ffffffffb863ebe0 R09: 0000000000000000
[ 213.778813] R10: ffff91cf6fd039d0 R11: 0000000000000000 R12: 0000000000000000
[ 213.785935] R13: ffff91cf5b23d84e R14: ffff91cf5b779f80 R15: ffff91cf5589cc00
[ 213.793062] FS: 0000000000000000(0000) GS:ffff91cf6fd00000(0000)
knlGS:0000000000000000
[ 213.801162] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 213.806900] CR2: 0000000000000008 CR3: 000000004201e001 CR4: 00000000003606e0
[ 213.814025] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 213.821200] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 213.828324] Call Trace:
[ 213.830769] <IRQ>
[ 213.832783] ? trace_hardirqs_on+0xd/0x10
[ 213.836819] __xfrm_policy_check2.constprop.36+0x6c/0xc0
[ 213.842131] tcp_v4_rcv+0x9ef/0xbd0
[ 213.845615] ? ip_local_deliver_finish+0x26/0x340
[ 213.850314] ip_local_deliver_finish+0xc1/0x340
[ 213.854843] ip_local_deliver+0x74/0x220
[ 213.858761] ? inet_del_offload+0x40/0x40
[ 213.862767] ip_rcv_finish+0x1f0/0x550
[ 213.866519] ip_rcv+0x282/0x480
[ 213.869657] ? ip_local_deliver_finish+0x340/0x340
[ 213.874448] __netif_receive_skb_core+0x3b2/0xd30
[ 213.879145] ? lock_acquire+0xd5/0x1c0
[ 213.882891] __netif_receive_skb+0x18/0x60
[ 213.886990] ? __netif_receive_skb+0x18/0x60
[ 213.891252] netif_receive_skb_internal+0x79/0x370
[ 213.896062] napi_gro_receive+0x138/0x1b0
[ 213.900121] igb_poll+0x610/0xe70
[ 213.903440] net_rx_action+0x246/0x4b0
[ 213.907190] ? lock_acquire+0xd5/0x1c0
[ 213.910933] ? igb_msix_ring+0x5e/0x70
[ 213.914681] __do_softirq+0xbf/0x493
[ 213.918260] irq_exit+0xc3/0xd0
[ 213.921405] do_IRQ+0x65/0x110
[ 213.924464] common_interrupt+0xf/0xf
[ 213.928128] </IRQ>
[ 213.930225] RIP: 0010:cpuidle_enter_state+0xa7/0x370
1.[1.200/32 dir i 213.935182] Code: 47 e8 bd 9a 7f ff 48 89 45 d0 0f
1f 44 00 00 31 ff e8 2d a9 7f ff 80 7d c7 00 0f 85 ee 01 00 00 e8 ae
9f 81 ff fb 48 8b 4d d0 <48> 2b 4d c8 48 ba cf f7 53 e3 a5 9b c4 20 48
89 c8 48 c1 f9 3f 48
[ 213.955445] RSP: 0018:ffffab2c01943e38 EFLAGS: 00000246 ORIG_RAX:
ffffffffffffffdc
[ 213.963002] RAX: ffff91cf6fd21ec0 RBX: 0000000000000002 RCX: 00000031bdd50c87
[ 213.970127] RDX: 00000031bdd50c87 RSI: 000000002aaaaaaa RDI: ffffffffb84ab752
[ 213.977250] RBP: ffffab2c01943e78 R08: 0000000000000061 R09: 0000000000000018
[ 213.984375] R10: ffffab2c01943e18 R11: 0000000000000092 R12: ffff91cf5ce88000
[ 213.991497] R13: ffffffffb94cf278 R14: 0000000000000002 R15: ffffffffb94cf260
[ 213.998624] ? cpuidle_enter_state+0xa2/0x370
[ 214.002982] ? cpuidle_enter_state+0xa2/0x370
[ 214.007332] cpuidle_enter+0x17/0x20
[ 214.010902] call_cpuidle+0x23/0x40
[ 214.014387] do_idle+0x1f0/0x250
[ 214.017613] cpu_startup_entry+0x73/0x80
[ 214.021538] start_secondary+0x175/0x1a0
[ 214.025465] secondary_startup_64+0xa5/0xb0
[ 214.029651] Modules linked in: cls_bpf xt_mark algif_hash af_alg
x86_pkg_temp_thermal fuse
[ 214.037941] CR2: 0000000000000008
[ 214.041255] ---[ end trace a0b077febc9b99ca ]---
[ 214.045874] RIP: 0010:__xfrm_policy_check+0xcb/0x690
n tmpl src 172.1[ 214.050838] Code: 80 3d 0a d8 f1 00 00 0f 84 c1 02
00 00 4c 8b 25 2b af f4 00 e8 66 a6 6a ff 85 c0 74 0d 80 3d eb d7 f1
00 00 0f 84 d5 02 00 00 <49> 8b 44 24 08 48 85 c0 74 0c 48 8d b5 78 ff
ff ff 4c 89 ff ff d0
[ 214.071103] RSP: 0018:ffff91cf6fd03a48 EFLAGS: 00010246
[ 214.076327] RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000002
[ 214.083451] RDX: ffffffffb863ebe0 RSI: 0000000000000000 RDI: 0000000000000000
[ 214.090574] RBP: ffff91cf6fd03b18 R08: ffffffffb863ebe0 R09: 0000000000000000
[ 214.097699] R10: ffff91cf6fd039d0 R11: 0000000000000000 R12: 0000000000000000
[ 214.104821] R13: ffff91cf5b23d84e R14: ffff91cf5b779f80 R15: ffff91cf5589cc00
[ 214.111945] FS: 0000000000000000(0000) GS:ffff91cf6fd00000(0000)
knlGS:0000000000000000
[ 214.120022] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 214.125760] CR2: 0000000000000008 CR3: 000000004201e001 CR4: 00000000003606e0
[ 214.132885] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 214.140009] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 214.147131] Kernel panic - not syncing: Fatal exception in interrupt
[ 214.153519] Kernel Offset: 0x36c00000 from 0xffffffff81000000
(relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[ 214.164292] ---[ end Kernel panic - not syncing: Fatal exception in
interrupt ]---
[ 214.171852] ------------[ cut here ]------------
Kconfigs on this kernel,
-------------------------------
CONFIG_XFRM=y
CONFIG_XFRM_ALGO=y
CONFIG_XFRM_USER=y
# CONFIG_XFRM_SUB_POLICY is not set
# CONFIG_XFRM_MIGRATE is not set
# CONFIG_XFRM_STATISTICS is not set
http://snapshots.linaro.org/openembedded/lkft/morty/intel-core2-32/rpb/linux-next/274/config
Test case source:
--------------------------
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/tree/tools/testing/selftests/bpf/test_tunnel.sh#n565
steps to reproduce:
--------------------------
cd /tools/testing/selftests/bpf/
./test_tunnel.sh
Debugging shows it is coming from function
setup_xfrm_tunnel() {
<trim>
ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 \
reqid 1 mode tunnel auth-trunc 'hmac(sha1)' \
0x1111111111111111111111111111111111111111 96 enc 'cbc(aes)' \
0x22222222222222222222222222222222
<trim>
}
Complete test log can be found in this location,
https://lkft.validation.linaro.org/scheduler/job/269604#L2092
Best regards
Naresh Kamboju
^ permalink raw reply
* Re: [PATCH 3/6] arcnet: com20020: Add com20020 io mapped version
From: kbuild test robot @ 2018-06-11 16:35 UTC (permalink / raw)
To: Andrea Greco
Cc: kbuild-all, davem, tobin, Andrea Greco, Michael Grzeschik,
linux-kernel, netdev
In-Reply-To: <20180611142635.20712-1-andrea.greco.gapmilano@gmail.com>
Hi Andrea,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on net-next/master]
[also build test WARNING on v4.17 next-20180608]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Andrea-Greco/arcnet-leds-Removed-leds-dependecy/20180611-222941
reproduce:
# apt-get install sparse
make ARCH=x86_64 allmodconfig
make C=1 CF=-D__CHECK_ENDIAN__
sparse warnings: (new ones prefixed by >>)
>> drivers/net/arcnet/com20020-io.c:34:45: sparse: incorrect type in argument 1 (different address spaces) @@ expected void [noderef] <asn:2>*<noident> @@ got sn:2>*<noident> @@
drivers/net/arcnet/com20020-io.c:34:45: expected void [noderef] <asn:2>*<noident>
drivers/net/arcnet/com20020-io.c:34:45: got void *
drivers/net/arcnet/com20020-io.c:39:45: sparse: incorrect type in argument 2 (different address spaces) @@ expected void [noderef] <asn:2>*<noident> @@ got sn:2>*<noident> @@
drivers/net/arcnet/com20020-io.c:39:45: expected void [noderef] <asn:2>*<noident>
drivers/net/arcnet/com20020-io.c:39:45: got void *
>> drivers/net/arcnet/com20020-io.c:44:22: sparse: incorrect type in argument 1 (different address spaces) @@ expected void [noderef] <asn:2>*port @@ got void [noderef] <asn:2>*port @@
drivers/net/arcnet/com20020-io.c:44:22: expected void [noderef] <asn:2>*port
drivers/net/arcnet/com20020-io.c:44:22: got void *[noderef] <asn:2><noident>
drivers/net/arcnet/com20020-io.c:49:23: sparse: incorrect type in argument 1 (different address spaces) @@ expected void [noderef] <asn:2>*port @@ got void [noderef] <asn:2>*port @@
drivers/net/arcnet/com20020-io.c:49:23: expected void [noderef] <asn:2>*port
drivers/net/arcnet/com20020-io.c:49:23: got void *[noderef] <asn:2><noident>
>> drivers/net/arcnet/com20020-io.c:219:19: sparse: cast removes address space of expression
drivers/net/arcnet/com20020-io.c: In function 'io_arc_inb':
drivers/net/arcnet/com20020-io.c:34:17: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
return ioread8((void *__iomem) addr + offset);
^
drivers/net/arcnet/com20020-io.c: In function 'io_arc_outb':
drivers/net/arcnet/com20020-io.c:39:18: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
iowrite8(value, (void *__iomem)addr + offset);
^
drivers/net/arcnet/com20020-io.c: In function 'io_arc_insb':
drivers/net/arcnet/com20020-io.c:44:14: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
ioread8_rep((void *__iomem) (addr + offset), buffer, count);
^
drivers/net/arcnet/com20020-io.c: In function 'io_arc_outsb':
drivers/net/arcnet/com20020-io.c:49:15: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
iowrite8_rep((void *__iomem) (addr + offset), buffer, count);
^
drivers/net/arcnet/com20020-io.c: In function 'com20020_probe':
drivers/net/arcnet/com20020-io.c:219:11: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
ioaddr = (int)devm_ioremap(&pdev->dev, iores->start,
^
drivers/net/arcnet/com20020-io.c:288:27: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
devm_iounmap(&pdev->dev, (void __iomem *)ioaddr);
^
vim +34 drivers/net/arcnet/com20020-io.c
31
32 static unsigned int io_arc_inb(int addr, int offset)
33 {
> 34 return ioread8((void *__iomem) addr + offset);
35 }
36
37 static void io_arc_outb(int value, int addr, int offset)
38 {
> 39 iowrite8(value, (void *__iomem)addr + offset);
40 }
41
42 static void io_arc_insb(int addr, int offset, void *buffer, int count)
43 {
> 44 ioread8_rep((void *__iomem) (addr + offset), buffer, count);
45 }
46
47 static void io_arc_outsb(int addr, int offset, void *buffer, int count)
48 {
49 iowrite8_rep((void *__iomem) (addr + offset), buffer, count);
50 }
51
52 enum com20020_xtal_freq {
53 freq_10Mhz = 10,
54 freq_20Mhz = 20,
55 };
56
57 enum com20020_arcnet_speed {
58 arc_speed_10M_bps = 10000000,
59 arc_speed_5M_bps = 5000000,
60 arc_speed_2M50_bps = 2500000,
61 arc_speed_1M25_bps = 1250000,
62 arc_speed_625K_bps = 625000,
63 arc_speed_312K5_bps = 312500,
64 arc_speed_156K25_bps = 156250,
65 };
66
67 enum com20020_timeout {
68 arc_timeout_328us = 328000,
69 arc_timeout_164us = 164000,
70 arc_timeout_82us = 82000,
71 arc_timeout_20u5s = 20500,
72 };
73
74 static int setup_clock(int *clockp, int *clockm, int xtal, int arcnet_speed)
75 {
76 int pll_factor, req_clock_frq = 20;
77
78 switch (arcnet_speed) {
79 case arc_speed_10M_bps:
80 req_clock_frq = 80;
81 *clockp = 0;
82 break;
83 case arc_speed_5M_bps:
84 req_clock_frq = 40;
85 *clockp = 0;
86 break;
87 case arc_speed_2M50_bps:
88 *clockp = 0;
89 break;
90 case arc_speed_1M25_bps:
91 *clockp = 1;
92 break;
93 case arc_speed_625K_bps:
94 *clockp = 2;
95 break;
96 case arc_speed_312K5_bps:
97 *clockp = 3;
98 break;
99 case arc_speed_156K25_bps:
100 *clockp = 4;
101 break;
102 default:
103 return -EINVAL;
104 }
105
106 if (xtal != freq_10Mhz && xtal != freq_20Mhz)
107 return -EINVAL;
108
109 pll_factor = (unsigned int)req_clock_frq / xtal;
110
111 switch (pll_factor) {
112 case 1:
113 *clockm = 0;
114 break;
115 case 2:
116 *clockm = 1;
117 break;
118 case 4:
119 *clockm = 3;
120 break;
121 default:
122 return -EINVAL;
123 }
124
125 return 0;
126 }
127
128 static int setup_timeout(int *timeout)
129 {
130 switch (*timeout) {
131 case arc_timeout_328us:
132 *timeout = 0;
133 break;
134 case arc_timeout_164us:
135 *timeout = 1;
136 break;
137 case arc_timeout_82us:
138 *timeout = 2;
139 break;
140 case arc_timeout_20u5s:
141 *timeout = 3;
142 break;
143 default:
144 return -EINVAL;
145 }
146
147 return 0;
148 }
149
150 static int com20020_probe(struct platform_device *pdev)
151 {
152 struct device_node *np;
153 struct net_device *dev;
154 struct arcnet_local *lp;
155 struct resource res, *iores;
156 int ret, phy_reset;
157 u32 timeout, xtal, arc_speed;
158 int clockp, clockm;
159 bool backplane = false;
160 int ioaddr;
161
162 np = pdev->dev.of_node;
163
164 iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
165
166 ret = of_address_to_resource(np, 0, &res);
167 if (ret)
168 return ret;
169
170 ret = of_property_read_u32(np, "timeout-ns", &timeout);
171 if (ret) {
172 dev_err(&pdev->dev, "timeout is required param");
173 return ret;
174 }
175
176 ret = of_property_read_u32(np, "smsc,xtal-mhz", &xtal);
177 if (ret) {
178 dev_err(&pdev->dev, "xtal-mhz is required param");
179 return ret;
180 }
181
182 ret = of_property_read_u32(np, "bus-speed-bps", &arc_speed);
183 if (ret) {
184 dev_err(&pdev->dev, "Bus speed is required param");
185 return ret;
186 }
187
188 if (of_property_read_bool(np, "smsc,backplane-enabled"))
189 backplane = true;
190
191 phy_reset = of_get_named_gpio(np, "reset-gpios", 0);
192 if (!gpio_is_valid(phy_reset)) {
193 dev_err(&pdev->dev, "reset gpio not valid");
194 return phy_reset;
195 }
196
197 ret = devm_gpio_request_one(&pdev->dev, phy_reset, GPIOF_OUT_INIT_LOW,
198 "arcnet-reset");
199 if (ret) {
200 dev_err(&pdev->dev, "failed to get phy reset gpio: %d\n", ret);
201 return ret;
202 }
203
204 dev = alloc_arcdev(NULL);
205 dev->netdev_ops = &com20020_netdev_ops;
206 lp = netdev_priv(dev);
207
208 lp->card_flags = ARC_CAN_10MBIT;
209
210 /* Peak random address,
211 * if required user could set a new-one in userspace
212 */
213 get_random_bytes(dev->dev_addr, dev->addr_len);
214
215 if (!devm_request_mem_region(&pdev->dev, res.start, resource_size(&res),
216 lp->card_name))
217 return -EBUSY;
218
> 219 ioaddr = (int)devm_ioremap(&pdev->dev, iores->start,
220 resource_size(iores));
221 if (!ioaddr) {
222 dev_err(&pdev->dev, "ioremap fallied\n");
223 return -ENOMEM;
224 }
225
226 gpio_set_value_cansleep(phy_reset, 0);
227 ndelay(RESET_DELAY);
228 gpio_set_value_cansleep(phy_reset, 1);
229
230 lp->hw.arc_inb = io_arc_inb;
231 lp->hw.arc_outb = io_arc_outb;
232 lp->hw.arc_insb = io_arc_insb;
233 lp->hw.arc_outsb = io_arc_outsb;
234
235 /* ARCNET controller needs this access to detect bustype */
236 lp->hw.arc_outb(0x00, ioaddr, COM20020_REG_W_COMMAND);
237 lp->hw.arc_inb(ioaddr, COM20020_REG_R_DIAGSTAT);
238
239 dev->base_addr = (unsigned long)ioaddr;
240
241 dev->irq = of_get_named_gpio(np, "interrupts", 0);
242 if (dev->irq == -EPROBE_DEFER) {
243 return dev->irq;
244 } else if (!gpio_is_valid(dev->irq)) {
245 dev_err(&pdev->dev, "irq-gpios not valid !");
246 return -EIO;
247 }
248 dev->irq = gpio_to_irq(dev->irq);
249
250 ret = setup_clock(&clockp, &clockm, xtal, arc_speed);
251 if (ret) {
252 dev_err(&pdev->dev,
253 "Impossible use oscillator:%dMhz and arcnet bus speed:%dKbps",
254 xtal, arc_speed / 1000);
255 return ret;
256 }
257
258 ret = setup_timeout(&timeout);
259 if (ret) {
260 dev_err(&pdev->dev, "Timeout:%d is not valid value", timeout);
261 return ret;
262 }
263
264 lp->backplane = (int)backplane;
265 lp->timeout = timeout;
266 lp->clockm = clockm;
267 lp->clockp = clockp;
268 lp->hw.owner = THIS_MODULE;
269
270 if (lp->hw.arc_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) {
271 ret = -EIO;
272 goto err_release_mem;
273 }
274
275 if (com20020_check(dev)) {
276 ret = -EIO;
277 goto err_release_mem;
278 }
279
280 ret = com20020_found(dev, IRQF_TRIGGER_FALLING);
281 if (ret)
282 goto err_release_mem;
283
284 dev_dbg(&pdev->dev, "probe Done\n");
285 return 0;
286
287 err_release_mem:
288 devm_iounmap(&pdev->dev, (void __iomem *)ioaddr);
289 devm_release_mem_region(&pdev->dev, res.start, resource_size(&res));
290 dev_err(&pdev->dev, "probe failed!\n");
291 return ret;
292 }
293
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
^ permalink raw reply
* [PATCH nf-next] netfilter: nft_reject_bridge: remove unnecessary ttl set
From: Taehee Yoo @ 2018-06-11 16:35 UTC (permalink / raw)
To: davem, steffen.klassert; +Cc: netdev, Taehee Yoo
In the nft_reject_br_send_v4_tcp_reset(), a ttl is set by
the nf_reject_ip_tcphdr_put(). so, below code is unnecessary.
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
---
net/bridge/netfilter/nft_reject_bridge.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index eaf05de..e0b082c 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -89,8 +89,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net,
niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
net->ipv4.sysctl_ip_default_ttl);
nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
- niph->ttl = net->ipv4.sysctl_ip_default_ttl;
- niph->tot_len = htons(nskb->len);
+ niph->tot_len = htons(nskb->len);
ip_send_check(niph);
nft_reject_br_push_etherhdr(oldskb, nskb);
--
2.9.3
^ permalink raw reply related
* [PULL] vhost: cleanups and fixes
From: Michael S. Tsirkin @ 2018-06-11 16:23 UTC (permalink / raw)
To: Linus Torvalds
Cc: ohad, kevin, kvm, mst, netdev, liang.z.li, linux-remoteproc,
linux-kernel, stable, bjorn.andersson, mhocko, mhocko,
syzbot+87cfa083e727a224754b, akpm, virtualization
The following changes since commit 29dcea88779c856c7dc92040a0c01233263101d4:
Linux 4.17 (2018-06-03 14:15:21 -0700)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git tags/for_linus
for you to fetch changes up to aa15783ee62d57d69433101ede3e3ed11e48161d:
virtio: update the comments for transport features (2018-06-07 22:17:40 +0300)
----------------------------------------------------------------
virtio, vhost: features, fixes
VF support for virtio.
Free page hint request support for VM migration.
DMA barriers for virtio strong barriers.
Bugfixes.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
----------------------------------------------------------------
Michael S. Tsirkin (2):
virtio_ring: switch to dma_XX barriers for rpmsg
vhost: fix info leak due to uninitialized memory
Tiwei Bie (2):
virtio_pci: support enabling VFs
virtio: update the comments for transport features
Wei Wang (4):
mm: support reporting free page blocks
virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
mm/page_poison: expose page_poisoning_enabled to kernel modules
virtio-balloon: VIRTIO_BALLOON_F_PAGE_POISON
drivers/vhost/vhost.c | 3 +
drivers/virtio/virtio_balloon.c | 298 +++++++++++++++++++++++++++++++-----
drivers/virtio/virtio_pci_common.c | 30 ++++
drivers/virtio/virtio_pci_modern.c | 14 ++
include/linux/mm.h | 6 +
include/linux/virtio_ring.h | 4 +-
include/uapi/linux/virtio_balloon.h | 7 +
include/uapi/linux/virtio_config.h | 16 +-
mm/page_alloc.c | 97 ++++++++++++
mm/page_poison.c | 6 +
10 files changed, 439 insertions(+), 42 deletions(-)
^ permalink raw reply
* Re: [PATCH v2 15/24] net: qualcomm: MODULE_DEVICE_TABLE(serdev)
From: Ricardo Ribalda Delgado @ 2018-06-11 16:21 UTC (permalink / raw)
To: Marcel Holtmann
Cc: LKML, open list:SERIAL DRIVERS, Lino Sanfilippo, David Miller,
Stefan Wahren, Rob Herring, Johan Hovold, netdev
In-Reply-To: <07871EF5-D1D3-4677-8100-B5E7F14DB302@holtmann.org>
Hi Marcel,
On Mon, Jun 11, 2018 at 5:52 PM Marcel Holtmann <marcel@holtmann.org> wrote:
>
> Hi Ricardo,
>
> >>>> the commit message is misleading me. If I build something with ACPI or DT support, then modinfo will show all modalias information for ACPI and DT compatible strings. What else does udev/modprobe actually need? Is something broken with the modalias export?
> >>>
> >>> The main purpose is to autoload drivers for devices that have been
> >>> created via sysfs or another module.
> >>>
> >>> Eg1: We have a serial port on a standard computer that has connected a
> >>> GPS module. Since it is something that is not in the ACPI nor the DT
> >>> table the user will run
> >>>
> >>> echo serdev_gps > /sys/bus/serial/devices/serial0/new_device
> >>>
> >>> Eg2 module: https://github.com/ribalda/linux/blob/415bb3f0076c2b846ebe5409589b8e1e3004f55a/drivers/tty/serdev/test_platform.c
> >>>
> >>> Modprobe does not know what module to load for that device unless
> >>> there is a matching MODULE_DEVICE_TABLE
> >>> Today, we have the same functionality for i2c devices
> >>> https://www.kernel.org/doc/Documentation/i2c/instantiating-devices
> >>
> >> but why does this have to be the driver name? I would rather say, create a generic string that describes the hardware and then use that. I think you also want the special handling, as from USB for example, that lets you reference an existing .compatible or ACPI ID as reference so that the driver_data is copied.
> >
> > We can choose any name, but if there are no special variants (like the
> > rave-sp driver) I would prefer using the module name. We can of course
> > use more names, like the part number of the the device, but it is very
> > convenient to also use the module name, and other subsystems also do
> > that.
> >
> > If you want to add specific names for this device please let me know
> > and I will add them to the list. You know much more about this module
> > than myself.
>
> if we want to use the driver name, then why not build this into the new_device handling itself instead of duplicating that name in each serdev_device_id table. What is the reference here? For example platform device do matching on driver name if I recall this correctly.
We do the matching also over driver name at serdev_device_match():
if (sdrv->id_table)
return !!serdev_match_id(sdrv->id_table, sdev);
return strcmp(sdev->modalias, drv->name) == 0;
This is just for the module autoloading
>
> However what is most important is that device_get_match_data() actually works. There should be no difference between DT, ACPI or a dynamic device.
Agree, will take a look to this tomorrow morning.
>
> Regards
>
> Marcel
>
--
Ricardo Ribalda
^ permalink raw reply
* Re: [PATCH 3/6] arcnet: com20020: Add com20020 io mapped version
From: kbuild test robot @ 2018-06-11 16:15 UTC (permalink / raw)
To: Andrea Greco
Cc: kbuild-all, davem, tobin, Andrea Greco, Michael Grzeschik,
linux-kernel, netdev
In-Reply-To: <20180611142635.20712-1-andrea.greco.gapmilano@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 9979 bytes --]
Hi Andrea,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on net-next/master]
[also build test WARNING on v4.17 next-20180608]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Andrea-Greco/arcnet-leds-Removed-leds-dependecy/20180611-222941
config: sparc64-allmodconfig (attached as .config)
compiler: sparc64-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
GCC_VERSION=7.2.0 make.cross ARCH=sparc64
All warnings (new ones prefixed by >>):
drivers/net//arcnet/com20020-io.c: In function 'io_arc_inb':
>> drivers/net//arcnet/com20020-io.c:34:17: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
return ioread8((void *__iomem) addr + offset);
^
drivers/net//arcnet/com20020-io.c: In function 'io_arc_outb':
drivers/net//arcnet/com20020-io.c:39:18: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
iowrite8(value, (void *__iomem)addr + offset);
^
drivers/net//arcnet/com20020-io.c: In function 'io_arc_insb':
drivers/net//arcnet/com20020-io.c:44:14: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
ioread8_rep((void *__iomem) (addr + offset), buffer, count);
^
drivers/net//arcnet/com20020-io.c: In function 'io_arc_outsb':
drivers/net//arcnet/com20020-io.c:49:15: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
iowrite8_rep((void *__iomem) (addr + offset), buffer, count);
^
drivers/net//arcnet/com20020-io.c: In function 'com20020_probe':
>> drivers/net//arcnet/com20020-io.c:219:11: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
ioaddr = (int)devm_ioremap(&pdev->dev, iores->start,
^
drivers/net//arcnet/com20020-io.c:288:27: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
devm_iounmap(&pdev->dev, (void __iomem *)ioaddr);
^
vim +34 drivers/net//arcnet/com20020-io.c
31
32 static unsigned int io_arc_inb(int addr, int offset)
33 {
> 34 return ioread8((void *__iomem) addr + offset);
35 }
36
37 static void io_arc_outb(int value, int addr, int offset)
38 {
39 iowrite8(value, (void *__iomem)addr + offset);
40 }
41
42 static void io_arc_insb(int addr, int offset, void *buffer, int count)
43 {
> 44 ioread8_rep((void *__iomem) (addr + offset), buffer, count);
45 }
46
47 static void io_arc_outsb(int addr, int offset, void *buffer, int count)
48 {
49 iowrite8_rep((void *__iomem) (addr + offset), buffer, count);
50 }
51
52 enum com20020_xtal_freq {
53 freq_10Mhz = 10,
54 freq_20Mhz = 20,
55 };
56
57 enum com20020_arcnet_speed {
58 arc_speed_10M_bps = 10000000,
59 arc_speed_5M_bps = 5000000,
60 arc_speed_2M50_bps = 2500000,
61 arc_speed_1M25_bps = 1250000,
62 arc_speed_625K_bps = 625000,
63 arc_speed_312K5_bps = 312500,
64 arc_speed_156K25_bps = 156250,
65 };
66
67 enum com20020_timeout {
68 arc_timeout_328us = 328000,
69 arc_timeout_164us = 164000,
70 arc_timeout_82us = 82000,
71 arc_timeout_20u5s = 20500,
72 };
73
74 static int setup_clock(int *clockp, int *clockm, int xtal, int arcnet_speed)
75 {
76 int pll_factor, req_clock_frq = 20;
77
78 switch (arcnet_speed) {
79 case arc_speed_10M_bps:
80 req_clock_frq = 80;
81 *clockp = 0;
82 break;
83 case arc_speed_5M_bps:
84 req_clock_frq = 40;
85 *clockp = 0;
86 break;
87 case arc_speed_2M50_bps:
88 *clockp = 0;
89 break;
90 case arc_speed_1M25_bps:
91 *clockp = 1;
92 break;
93 case arc_speed_625K_bps:
94 *clockp = 2;
95 break;
96 case arc_speed_312K5_bps:
97 *clockp = 3;
98 break;
99 case arc_speed_156K25_bps:
100 *clockp = 4;
101 break;
102 default:
103 return -EINVAL;
104 }
105
106 if (xtal != freq_10Mhz && xtal != freq_20Mhz)
107 return -EINVAL;
108
109 pll_factor = (unsigned int)req_clock_frq / xtal;
110
111 switch (pll_factor) {
112 case 1:
113 *clockm = 0;
114 break;
115 case 2:
116 *clockm = 1;
117 break;
118 case 4:
119 *clockm = 3;
120 break;
121 default:
122 return -EINVAL;
123 }
124
125 return 0;
126 }
127
128 static int setup_timeout(int *timeout)
129 {
130 switch (*timeout) {
131 case arc_timeout_328us:
132 *timeout = 0;
133 break;
134 case arc_timeout_164us:
135 *timeout = 1;
136 break;
137 case arc_timeout_82us:
138 *timeout = 2;
139 break;
140 case arc_timeout_20u5s:
141 *timeout = 3;
142 break;
143 default:
144 return -EINVAL;
145 }
146
147 return 0;
148 }
149
150 static int com20020_probe(struct platform_device *pdev)
151 {
152 struct device_node *np;
153 struct net_device *dev;
154 struct arcnet_local *lp;
155 struct resource res, *iores;
156 int ret, phy_reset;
157 u32 timeout, xtal, arc_speed;
158 int clockp, clockm;
159 bool backplane = false;
160 int ioaddr;
161
162 np = pdev->dev.of_node;
163
164 iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
165
166 ret = of_address_to_resource(np, 0, &res);
167 if (ret)
168 return ret;
169
170 ret = of_property_read_u32(np, "timeout-ns", &timeout);
171 if (ret) {
172 dev_err(&pdev->dev, "timeout is required param");
173 return ret;
174 }
175
176 ret = of_property_read_u32(np, "smsc,xtal-mhz", &xtal);
177 if (ret) {
178 dev_err(&pdev->dev, "xtal-mhz is required param");
179 return ret;
180 }
181
182 ret = of_property_read_u32(np, "bus-speed-bps", &arc_speed);
183 if (ret) {
184 dev_err(&pdev->dev, "Bus speed is required param");
185 return ret;
186 }
187
188 if (of_property_read_bool(np, "smsc,backplane-enabled"))
189 backplane = true;
190
191 phy_reset = of_get_named_gpio(np, "reset-gpios", 0);
192 if (!gpio_is_valid(phy_reset)) {
193 dev_err(&pdev->dev, "reset gpio not valid");
194 return phy_reset;
195 }
196
197 ret = devm_gpio_request_one(&pdev->dev, phy_reset, GPIOF_OUT_INIT_LOW,
198 "arcnet-reset");
199 if (ret) {
200 dev_err(&pdev->dev, "failed to get phy reset gpio: %d\n", ret);
201 return ret;
202 }
203
204 dev = alloc_arcdev(NULL);
205 dev->netdev_ops = &com20020_netdev_ops;
206 lp = netdev_priv(dev);
207
208 lp->card_flags = ARC_CAN_10MBIT;
209
210 /* Peak random address,
211 * if required user could set a new-one in userspace
212 */
213 get_random_bytes(dev->dev_addr, dev->addr_len);
214
215 if (!devm_request_mem_region(&pdev->dev, res.start, resource_size(&res),
216 lp->card_name))
217 return -EBUSY;
218
> 219 ioaddr = (int)devm_ioremap(&pdev->dev, iores->start,
220 resource_size(iores));
221 if (!ioaddr) {
222 dev_err(&pdev->dev, "ioremap fallied\n");
223 return -ENOMEM;
224 }
225
226 gpio_set_value_cansleep(phy_reset, 0);
227 ndelay(RESET_DELAY);
228 gpio_set_value_cansleep(phy_reset, 1);
229
230 lp->hw.arc_inb = io_arc_inb;
231 lp->hw.arc_outb = io_arc_outb;
232 lp->hw.arc_insb = io_arc_insb;
233 lp->hw.arc_outsb = io_arc_outsb;
234
235 /* ARCNET controller needs this access to detect bustype */
236 lp->hw.arc_outb(0x00, ioaddr, COM20020_REG_W_COMMAND);
237 lp->hw.arc_inb(ioaddr, COM20020_REG_R_DIAGSTAT);
238
239 dev->base_addr = (unsigned long)ioaddr;
240
241 dev->irq = of_get_named_gpio(np, "interrupts", 0);
242 if (dev->irq == -EPROBE_DEFER) {
243 return dev->irq;
244 } else if (!gpio_is_valid(dev->irq)) {
245 dev_err(&pdev->dev, "irq-gpios not valid !");
246 return -EIO;
247 }
248 dev->irq = gpio_to_irq(dev->irq);
249
250 ret = setup_clock(&clockp, &clockm, xtal, arc_speed);
251 if (ret) {
252 dev_err(&pdev->dev,
253 "Impossible use oscillator:%dMhz and arcnet bus speed:%dKbps",
254 xtal, arc_speed / 1000);
255 return ret;
256 }
257
258 ret = setup_timeout(&timeout);
259 if (ret) {
260 dev_err(&pdev->dev, "Timeout:%d is not valid value", timeout);
261 return ret;
262 }
263
264 lp->backplane = (int)backplane;
265 lp->timeout = timeout;
266 lp->clockm = clockm;
267 lp->clockp = clockp;
268 lp->hw.owner = THIS_MODULE;
269
270 if (lp->hw.arc_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) {
271 ret = -EIO;
272 goto err_release_mem;
273 }
274
275 if (com20020_check(dev)) {
276 ret = -EIO;
277 goto err_release_mem;
278 }
279
280 ret = com20020_found(dev, IRQF_TRIGGER_FALLING);
281 if (ret)
282 goto err_release_mem;
283
284 dev_dbg(&pdev->dev, "probe Done\n");
285 return 0;
286
287 err_release_mem:
288 devm_iounmap(&pdev->dev, (void __iomem *)ioaddr);
289 devm_release_mem_region(&pdev->dev, res.start, resource_size(&res));
290 dev_err(&pdev->dev, "probe failed!\n");
291 return ret;
292 }
293
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 54207 bytes --]
^ permalink raw reply
* [net 5/5] ixgbe: Fix bit definitions and add support for testing for ipsec support
From: Jeff Kirsher @ 2018-06-11 16:16 UTC (permalink / raw)
To: davem
Cc: Alexander Duyck, netdev, nhorman, sassmann, jogreene, stable,
Jeff Kirsher
In-Reply-To: <20180611161630.21338-1-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch addresses two issues. First it adds the correct bit definitions
for the SECTXSTAT and SECRXSTAT registers. Then it makes use of those
definitions to test for if IPsec has been disabled on the part and if so we
do not enable it.
CC: stable <stable@vger.kernel.org>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Reported-by: Andre Tomt <andre@tomt.net>
Acked-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c | 14 +++++++++++++-
drivers/net/ethernet/intel/ixgbe/ixgbe_type.h | 6 ++++--
2 files changed, 17 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 7b23fb0c2d07..c116f459945d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -975,10 +975,22 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
**/
void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter)
{
+ struct ixgbe_hw *hw = &adapter->hw;
struct ixgbe_ipsec *ipsec;
+ u32 t_dis, r_dis;
size_t size;
- if (adapter->hw.mac.type == ixgbe_mac_82598EB)
+ if (hw->mac.type == ixgbe_mac_82598EB)
+ return;
+
+ /* If there is no support for either Tx or Rx offload
+ * we should not be advertising support for IPsec.
+ */
+ t_dis = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT) &
+ IXGBE_SECTXSTAT_SECTX_OFF_DIS;
+ r_dis = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT) &
+ IXGBE_SECRXSTAT_SECRX_OFF_DIS;
+ if (t_dis || r_dis)
return;
ipsec = kzalloc(sizeof(*ipsec), GFP_KERNEL);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index e8ed37749ab1..44cfb2021145 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -599,13 +599,15 @@ struct ixgbe_nvm_version {
#define IXGBE_SECTXCTRL_STORE_FORWARD 0x00000004
#define IXGBE_SECTXSTAT_SECTX_RDY 0x00000001
-#define IXGBE_SECTXSTAT_ECC_TXERR 0x00000002
+#define IXGBE_SECTXSTAT_SECTX_OFF_DIS 0x00000002
+#define IXGBE_SECTXSTAT_ECC_TXERR 0x00000004
#define IXGBE_SECRXCTRL_SECRX_DIS 0x00000001
#define IXGBE_SECRXCTRL_RX_DIS 0x00000002
#define IXGBE_SECRXSTAT_SECRX_RDY 0x00000001
-#define IXGBE_SECRXSTAT_ECC_RXERR 0x00000002
+#define IXGBE_SECRXSTAT_SECRX_OFF_DIS 0x00000002
+#define IXGBE_SECRXSTAT_ECC_RXERR 0x00000004
/* LinkSec (MacSec) Registers */
#define IXGBE_LSECTXCAP 0x08A00
--
2.17.1
^ permalink raw reply related
* [net 4/5] ixgbe: Avoid loopback and fix boolean logic in ipsec_stop_data
From: Jeff Kirsher @ 2018-06-11 16:16 UTC (permalink / raw)
To: davem
Cc: Alexander Duyck, netdev, nhorman, sassmann, jogreene, stable,
Jeff Kirsher
In-Reply-To: <20180611161630.21338-1-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch fixes two issues. First we add an early test for the Tx and Rx
security block ready bits. By doing this we can avoid the need for waits or
loopback in the event that the security block is already flushed out.
Secondly we fix the boolean logic that was testing for the Tx OR Rx ready
bits being set and change it so that we only exit if the Tx AND Rx ready
bits are both set.
CC: stable <stable@vger.kernel.org>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 38d8cf75e9ad..7b23fb0c2d07 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -158,7 +158,16 @@ static void ixgbe_ipsec_stop_data(struct ixgbe_adapter *adapter)
reg |= IXGBE_SECRXCTRL_RX_DIS;
IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, reg);
- IXGBE_WRITE_FLUSH(hw);
+ /* If both Tx and Rx are ready there are no packets
+ * that we need to flush so the loopback configuration
+ * below is not necessary.
+ */
+ t_rdy = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT) &
+ IXGBE_SECTXSTAT_SECTX_RDY;
+ r_rdy = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT) &
+ IXGBE_SECRXSTAT_SECRX_RDY;
+ if (t_rdy && r_rdy)
+ return;
/* If the tx fifo doesn't have link, but still has data,
* we can't clear the tx sec block. Set the MAC loopback
@@ -185,7 +194,7 @@ static void ixgbe_ipsec_stop_data(struct ixgbe_adapter *adapter)
IXGBE_SECTXSTAT_SECTX_RDY;
r_rdy = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT) &
IXGBE_SECRXSTAT_SECRX_RDY;
- } while (!t_rdy && !r_rdy && limit--);
+ } while (!(t_rdy && r_rdy) && limit--);
/* undo loopback if we played with it earlier */
if (!link) {
--
2.17.1
^ permalink raw reply related
* [net 3/5] ixgbe: Move ipsec init function to before reset call
From: Jeff Kirsher @ 2018-06-11 16:16 UTC (permalink / raw)
To: davem
Cc: Alexander Duyck, netdev, nhorman, sassmann, jogreene, stable,
Jeff Kirsher
In-Reply-To: <20180611161630.21338-1-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch moves the IPsec init function in ixgbe_sw_init. This way it is a
bit more consistent with the placement of similar initialization functions
and is placed before the reset_hw call which should allow us to clean up
any link issues that may be introduced by the fact that we force the link
up if somehow the device had IPsec still enabled before the driver was
loaded.
In addition to the function move it is necessary to change the assignment
of netdev->features. The easiest way to do this is to just test for the
existence of adapter->ipsec and if it is present we set the feature bits.
CC: stable <stable@vger.kernel.org>
Fixes: 49a94d74d948 ("ixgbe: add ipsec engine start and stop routines")
Reported-by: Andre Tomt <andre@tomt.net>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c | 7 -------
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 11 +++++++++--
2 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 344a1f213a5f..38d8cf75e9ad 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -1001,13 +1001,6 @@ void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter)
adapter->netdev->xfrmdev_ops = &ixgbe_xfrmdev_ops;
-#define IXGBE_ESP_FEATURES (NETIF_F_HW_ESP | \
- NETIF_F_HW_ESP_TX_CSUM | \
- NETIF_F_GSO_ESP)
-
- adapter->netdev->features |= IXGBE_ESP_FEATURES;
- adapter->netdev->hw_enc_features |= IXGBE_ESP_FEATURES;
-
return;
err2:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a925f05ec342..8d061af276d3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6117,6 +6117,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
#ifdef CONFIG_IXGBE_DCB
ixgbe_init_dcb(adapter);
#endif
+ ixgbe_init_ipsec_offload(adapter);
/* default flow control settings */
hw->fc.requested_mode = ixgbe_fc_full;
@@ -10429,6 +10430,14 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
if (hw->mac.type >= ixgbe_mac_82599EB)
netdev->features |= NETIF_F_SCTP_CRC;
+#ifdef CONFIG_XFRM_OFFLOAD
+#define IXGBE_ESP_FEATURES (NETIF_F_HW_ESP | \
+ NETIF_F_HW_ESP_TX_CSUM | \
+ NETIF_F_GSO_ESP)
+
+ if (adapter->ipsec)
+ netdev->features |= IXGBE_ESP_FEATURES;
+#endif
/* copy netdev features into list of user selectable features */
netdev->hw_features |= netdev->features |
NETIF_F_HW_VLAN_CTAG_FILTER |
@@ -10491,8 +10500,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
NETIF_F_FCOE_MTU;
}
#endif /* IXGBE_FCOE */
- ixgbe_init_ipsec_offload(adapter);
-
if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)
netdev->hw_features |= NETIF_F_LRO;
if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
--
2.17.1
^ permalink raw reply related
* [net 2/5] ixgbe: Use CONFIG_XFRM_OFFLOAD instead of CONFIG_XFRM
From: Jeff Kirsher @ 2018-06-11 16:16 UTC (permalink / raw)
To: davem
Cc: Alexander Duyck, netdev, nhorman, sassmann, jogreene, stable,
Jeff Kirsher
In-Reply-To: <20180611161630.21338-1-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
There is no point in adding code if CONFIG_XFRM is defined that we won't
use unless CONFIG_XFRM_OFFLOAD is defined. So instead of leaving this code
floating around I am replacing the ifdef with what I believe is the correct
one so that we only include the code and variables if they will actually be
used.
CC: stable <stable@vger.kernel.org>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 4 ++--
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index fc534e91c6b2..144d5fe6b944 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -760,9 +760,9 @@ struct ixgbe_adapter {
#define IXGBE_RSS_KEY_SIZE 40 /* size of RSS Hash Key in bytes */
u32 *rss_key;
-#ifdef CONFIG_XFRM
+#ifdef CONFIG_XFRM_OFFLOAD
struct ixgbe_ipsec *ipsec;
-#endif /* CONFIG_XFRM */
+#endif /* CONFIG_XFRM_OFFLOAD */
};
static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index f9e0dc041cfb..a925f05ec342 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9896,7 +9896,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev,
* the TSO, so it's the exception.
*/
if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) {
-#ifdef CONFIG_XFRM
+#ifdef CONFIG_XFRM_OFFLOAD
if (!skb->sp)
#endif
features &= ~NETIF_F_TSO;
--
2.17.1
^ permalink raw reply related
* [net 1/5] ixgbe: Fix setting of TC configuration for macvlan case
From: Jeff Kirsher @ 2018-06-11 16:16 UTC (permalink / raw)
To: davem
Cc: Alexander Duyck, netdev, nhorman, sassmann, jogreene, stable,
Jeff Kirsher
In-Reply-To: <20180611161630.21338-1-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
When we were enabling macvlan interfaces we weren't correctly configuring
things until ixgbe_setup_tc was called a second time either by tweaking the
number of queues or increasing the macvlan count past 15.
The issue came down to the fact that num_rx_pools is not populated until
after the queues and interrupts are reinitialized.
Instead of trying to set it sooner we can just move the call to setup at
least 1 traffic class to the SR-IOV/VMDq setup function so that we just set
it for this one case. We already had a spot that was configuring the queues
for TC 0 in the code here anyway so it makes sense to also set the number
of TCs here as well.
CC: stable <stable@vger.kernel.org>
Fixes: 49cfbeb7a95c ("ixgbe: Fix handling of macvlan Tx offload")
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c | 8 ++++++++
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 8 --------
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 893a9206e718..d361f570ca37 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -593,6 +593,14 @@ static bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter)
}
#endif
+ /* To support macvlan offload we have to use num_tc to
+ * restrict the queues that can be used by the device.
+ * By doing this we can avoid reporting a false number of
+ * queues.
+ */
+ if (vmdq_i > 1)
+ netdev_set_num_tc(adapter->netdev, 1);
+
/* populate TC0 for use by pool 0 */
netdev_set_tc_queue(adapter->netdev, 0,
adapter->num_rx_queues_per_pool, 0);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 4929f7265598..f9e0dc041cfb 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8822,14 +8822,6 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc)
} else {
netdev_reset_tc(dev);
- /* To support macvlan offload we have to use num_tc to
- * restrict the queues that can be used by the device.
- * By doing this we can avoid reporting a false number of
- * queues.
- */
- if (!tc && adapter->num_rx_pools > 1)
- netdev_set_num_tc(dev, 1);
-
if (adapter->hw.mac.type == ixgbe_mac_82598EB)
adapter->hw.fc.requested_mode = adapter->last_lfc_mode;
--
2.17.1
^ permalink raw reply related
* [net 0/5][pull request] Intel Wired LAN Driver Updates 2018-06-11
From: Jeff Kirsher @ 2018-06-11 16:16 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, nhorman, sassmann, jogreene
This series contains fixes to ixgbe IPsec and MACVLAN.
Alex provides the 5 fixes in this series, starting with fixing an issue
where num_rx_pools was not being populated until after the queues and
interrupts were reinitialized when enabling MACVLAN interfaces. Updated
to use CONFIG_XFRM_OFFLOAD instead of CONFIG_XFRM, since the code
requires CONFIG_XFRM_OFFLOAD to be enabled. Moved the IPsec
initialization function to be more consistent with the placement of
similar initialization functions and before the call to reset the
hardware, which will clean up any link issues that may have been
introduced. Fixed the boolean logic that was testing for transmit OR
receive ready bits, when it should have been testing for transmit AND
receive ready bits. Fixed the bit definitions for SECTXSTAT and SECRXSTAT
registers and ensure that if IPsec is disabled on the part, do not
enable it.
The following are changes since commit f0dc7f9c6dd99891611fca5849cbc4c6965b690e:
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
and are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue 10GbE
Alexander Duyck (5):
ixgbe: Fix setting of TC configuration for macvlan case
ixgbe: Use CONFIG_XFRM_OFFLOAD instead of CONFIG_XFRM
ixgbe: Move ipsec init function to before reset call
ixgbe: Avoid loopback and fix boolean logic in ipsec_stop_data
ixgbe: Fix bit definitions and add support for testing for ipsec
support
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 4 +--
.../net/ethernet/intel/ixgbe/ixgbe_ipsec.c | 34 +++++++++++++------
drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c | 8 +++++
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 21 ++++++------
drivers/net/ethernet/intel/ixgbe/ixgbe_type.h | 6 ++--
5 files changed, 48 insertions(+), 25 deletions(-)
--
2.17.1
^ permalink raw reply
* Re: [PATCH net] ipv6: allow PMTU exceptions to local routes
From: Martin KaFai Lau @ 2018-06-11 16:07 UTC (permalink / raw)
To: Julian Anastasov; +Cc: David Miller, netdev, kernel-team, lvs-devel
In-Reply-To: <20180610230254.6347-1-ja@ssi.bg>
On Mon, Jun 11, 2018 at 02:02:54AM +0300, Julian Anastasov wrote:
> IPVS setups with local client and remote tunnel server need
> to create exception for the local virtual IP. What we do is to
> change PMTU from 64KB (on "lo") to 1460 in the common case.
>
> Suggested-by: Martin KaFai Lau <kafai@fb.com>
> Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu exception")
> Fixes: 7343ff31ebf0 ("ipv6: Don't create clones of host routes.")
> Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Martin KaFai Lau <kafai@fb.com>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox