* [PATCH 5/6] net: Make ifindex generation per-net namespace
From: Pavel Emelyanov @ 2012-08-06 14:14 UTC (permalink / raw)
To: David Miller, Eric Dumazet, Eric W. Biederman, Linux Netdev List
In-Reply-To: <501FD0F2.4040609@parallels.com>
Strictly speaking this is only _really_ required for checkpoint-restore to
make loopback device always have the same index.
This change appears to be safe wrt "ifindex should be unique per-system"
concept, as all the ifindex usage is either already made per net namespace
of is explicitly limited with init_net only.
There are two cool side effects of this. The first one -- ifindices of
devices in container are always small, regardless of how many containers
we've started (and re-started) so far. The second one is -- we can speed
up the loopback ifidex access as shown in the next patch.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
---
include/net/net_namespace.h | 1 +
net/core/dev.c | 4 ++--
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index ae1cd6c..c5fbebf 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -62,6 +62,7 @@ struct net {
struct sock *rtnl; /* rtnetlink socket */
struct sock *genl_sock;
+ int ifindex;
struct list_head dev_base_head;
struct hlist_head *dev_name_head;
struct hlist_head *dev_index_head;
diff --git a/net/core/dev.c b/net/core/dev.c
index 3ca300d..1f06df8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5221,12 +5221,12 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
*/
static int dev_new_index(struct net *net)
{
- static int ifindex;
+ int ifindex = net->ifindex;
for (;;) {
if (++ifindex <= 0)
ifindex = 1;
if (!__dev_get_by_index(net, ifindex))
- return ifindex;
+ return net->ifindex = ifindex;
}
}
--
1.7.6.5
^ permalink raw reply related
* [PATCH 6/6] net: Loopback ifindex is constant now
From: Pavel Emelyanov @ 2012-08-06 14:15 UTC (permalink / raw)
To: David Miller, Eric Dumazet, Eric W. Biederman, Linux Netdev List
In-Reply-To: <501FD0F2.4040609@parallels.com>
As pointed out, there are places, that access net->loopback_dev->ifindex
and after ifindex generation is made per-net this value becomes constant
equals 1. So go ahead and introduce the LOOPBACK_IFINDEX constant and use
it where appropriate.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
---
drivers/net/loopback.c | 1 +
include/net/net_namespace.h | 7 +++++++
net/decnet/dn_route.c | 6 +++---
net/ipv4/fib_frontend.c | 2 +-
net/ipv4/ipmr.c | 2 +-
net/ipv4/netfilter/ipt_rpfilter.c | 2 +-
net/ipv4/route.c | 6 +++---
net/ipv6/route.c | 2 +-
8 files changed, 18 insertions(+), 10 deletions(-)
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index e2a06fd..4a075ba 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -197,6 +197,7 @@ static __net_init int loopback_net_init(struct net *net)
if (err)
goto out_free_netdev;
+ BUG_ON(dev->ifindex != LOOPBACK_IFINDEX);
net->loopback_dev = dev;
return 0;
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index c5fbebf..29a2370 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -105,6 +105,13 @@ struct net {
struct sock *diag_nlsk;
};
+/*
+ * ifindex generation is per-net namespace, and loopback is
+ * always the 1st device in ns (see net_dev_init), thus any
+ * loopback device should get ifindex 1
+ */
+
+#define LOOPBACK_IFINDEX 1
#include <linux/seq_file_net.h>
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 85a3604..c855e8d 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -961,7 +961,7 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowidn *o
.saddr = oldflp->saddr,
.flowidn_scope = RT_SCOPE_UNIVERSE,
.flowidn_mark = oldflp->flowidn_mark,
- .flowidn_iif = init_net.loopback_dev->ifindex,
+ .flowidn_iif = LOOPBACK_IFINDEX,
.flowidn_oif = oldflp->flowidn_oif,
};
struct dn_route *rt = NULL;
@@ -979,7 +979,7 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowidn *o
"dn_route_output_slow: dst=%04x src=%04x mark=%d"
" iif=%d oif=%d\n", le16_to_cpu(oldflp->daddr),
le16_to_cpu(oldflp->saddr),
- oldflp->flowidn_mark, init_net.loopback_dev->ifindex,
+ oldflp->flowidn_mark, LOOPBACK_IFINDEX,
oldflp->flowidn_oif);
/* If we have an output interface, verify its a DECnet device */
@@ -1042,7 +1042,7 @@ source_ok:
if (!fld.daddr)
goto out;
}
- fld.flowidn_oif = init_net.loopback_dev->ifindex;
+ fld.flowidn_oif = LOOPBACK_IFINDEX;
res.type = RTN_LOCAL;
goto make_route;
}
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c43ae3f..7f073a3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -218,7 +218,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
scope = RT_SCOPE_UNIVERSE;
if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
fl4.flowi4_oif = 0;
- fl4.flowi4_iif = net->loopback_dev->ifindex;
+ fl4.flowi4_iif = LOOPBACK_IFINDEX;
fl4.daddr = ip_hdr(skb)->saddr;
fl4.saddr = 0;
fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 8eec8f4..3a57570 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1798,7 +1798,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb)
.flowi4_oif = (rt_is_output_route(rt) ?
skb->dev->ifindex : 0),
.flowi4_iif = (rt_is_output_route(rt) ?
- net->loopback_dev->ifindex :
+ LOOPBACK_IFINDEX :
skb->dev->ifindex),
.flowi4_mark = skb->mark,
};
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index 31371be..c301300 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -85,7 +85,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
return ipv4_is_local_multicast(iph->daddr) ^ invert;
flow.flowi4_iif = 0;
} else {
- flow.flowi4_iif = dev_net(par->in)->loopback_dev->ifindex;
+ flow.flowi4_iif = LOOPBACK_IFINDEX;
}
flow.daddr = iph->saddr;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 21ad369..c581373 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1619,7 +1619,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
if (res.type == RTN_LOCAL) {
err = fib_validate_source(skb, saddr, daddr, tos,
- net->loopback_dev->ifindex,
+ LOOPBACK_IFINDEX,
dev, in_dev, &itag);
if (err < 0)
goto martian_source_keep_err;
@@ -1895,7 +1895,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
orig_oif = fl4->flowi4_oif;
- fl4->flowi4_iif = net->loopback_dev->ifindex;
+ fl4->flowi4_iif = LOOPBACK_IFINDEX;
fl4->flowi4_tos = tos & IPTOS_RT_MASK;
fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
@@ -1984,7 +1984,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
if (!fl4->daddr)
fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK);
dev_out = net->loopback_dev;
- fl4->flowi4_oif = net->loopback_dev->ifindex;
+ fl4->flowi4_oif = LOOPBACK_IFINDEX;
res.type = RTN_LOCAL;
flags |= RTCF_LOCAL;
goto make_route;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8e80fd2..0ddf2d1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -965,7 +965,7 @@ struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk,
{
int flags = 0;
- fl6->flowi6_iif = net->loopback_dev->ifindex;
+ fl6->flowi6_iif = LOOPBACK_IFINDEX;
if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
flags |= RT6_LOOKUP_F_IFACE;
--
1.7.6.5
^ permalink raw reply related
* RE: pch_gbe: dont-copy-payload (was [PATCH 1/4] ...)
From: Andy Cress @ 2012-08-06 14:19 UTC (permalink / raw)
To: Eric Dumazet; +Cc: netdev
In-Reply-To: <40680C535D6FE6498883F1640FACD44D011BBE1D@ka-exchange-1.kontronamerica.local>
I found out why the proposed dont-copy-payload patch didn't work with this pch_gbe NIC.
This NIC PHY requires 64-byte-aligned DMA, and the transmit buffers won't be transferred if skb->data is not 64-byte-aligned. Apparently the data copy has a by-product of aligning the buffers.
I tried using skb_reserve(skb,64) in pch_gbe_alloc_tx_buffers and pch-gbe_alloc_rx_buffers, but that didn't seem to resolve it.
How can I make sure that the transmit data buffers are 64-byte-aligned?
Andy
-----Original Message-----
From: Andy Cress
Sent: Wednesday, July 25, 2012 4:11 PM
Subject: RE: [PATCH 1/4] pch_gbe: Fix the checksum fill to the error location
[...]
I tried applying the dont-copy-payload patch you outlined below, and for some reason it won't send successfully with that change. I'm not sure why though. This approach seems sound, and should greatly help transmit performance, if I could figure out what else it needs.
Andy
-----Original Message-----
From: Eric Dumazet
Sent: Tuesday, July 17, 2012 3:33 AM
To: Andy Cress
Cc: netdev@vger.kernel.org; Zhong Hongbo
Subject: Re: [PATCH 1/4] pch_gbe: Fix the checksum fill to the error location
On Tue, 2012-07-17 at 09:09 +0200, Eric Dumazet wrote:
[...]
> There _must_ be a way to avoid most of these copies (ie not touching
> payload), only mess with the header to insert these 2 nul bytes ?
>
> /* [Header:14][payload] ---> [Header:14][paddong:2][payload] */
[...]
Something like the following (untested) patch
drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 55 +++++-----
1 file changed, 29 insertions(+), 26 deletions(-)
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index b100656..2d3d982 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -1163,7 +1163,7 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter,
struct pch_gbe_hw *hw = &adapter->hw;
struct pch_gbe_tx_desc *tx_desc;
struct pch_gbe_buffer *buffer_info;
- struct sk_buff *tmp_skb;
+ char *ptr;
unsigned int frame_ctrl;
unsigned int ring_num;
@@ -1221,18 +1221,27 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter,
buffer_info = &tx_ring->buffer_info[ring_num];
- tmp_skb = buffer_info->skb;
+ if (skb_headroom(skb) < 2) {
+ struct sk_buff *skb_new;
+
+ skb_new = skb_realloc_headroom(skb, 2);
+ if (!skb_new) {
+ tx_ring->next_to_use = ring_num;
+ dev_kfree_skb_any(skb);
+ return;
+ }
+ consume_skb(skb);
+ skb = skb_new;
+ }
/* [Header:14][payload] ---> [Header:14][paddong:2][payload] */
- memcpy(tmp_skb->data, skb->data, ETH_HLEN);
- tmp_skb->data[ETH_HLEN] = 0x00;
- tmp_skb->data[ETH_HLEN + 1] = 0x00;
- tmp_skb->len = skb->len;
- memcpy(&tmp_skb->data[ETH_HLEN + 2], &skb->data[ETH_HLEN],
- (skb->len - ETH_HLEN));
+ ptr = skb_push(skb, 2);
+ memmove(ptr, ptr + 2, ETH_HLEN);
+ ptr[ETH_HLEN] = 0x00;
+ ptr[ETH_HLEN + 1] = 0x00;
/*-- Set Buffer information --*/
- buffer_info->length = tmp_skb->len;
- buffer_info->dma = dma_map_single(&adapter->pdev->dev, tmp_skb->data,
+ buffer_info->length = skb->len;
+ buffer_info->dma = dma_map_single(&adapter->pdev->dev, skb->data,
buffer_info->length,
DMA_TO_DEVICE);
if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma)) {
@@ -1240,18 +1249,20 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter,
buffer_info->dma = 0;
buffer_info->time_stamp = 0;
tx_ring->next_to_use = ring_num;
+ dev_kfree_skb_any(skb);
return;
}
buffer_info->mapped = true;
buffer_info->time_stamp = jiffies;
+ buffer_info->skb = skb;
/*-- Set Tx descriptor --*/
tx_desc = PCH_GBE_TX_DESC(*tx_ring, ring_num);
- tx_desc->buffer_addr = (buffer_info->dma);
- tx_desc->length = (tmp_skb->len);
- tx_desc->tx_words_eob = ((tmp_skb->len + 3));
+ tx_desc->buffer_addr = buffer_info->dma;
+ tx_desc->length = skb->len;
+ tx_desc->tx_words_eob = skb->len + 3;
tx_desc->tx_frame_ctrl = (frame_ctrl);
- tx_desc->gbec_status = (DSC_INIT16);
+ tx_desc->gbec_status = DSC_INIT16;
if (unlikely(++ring_num == tx_ring->count))
ring_num = 0;
@@ -1265,7 +1276,6 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter,
pch_tx_timestamp(adapter, skb);
#endif
- dev_kfree_skb_any(skb);
}
/**
@@ -1543,19 +1553,12 @@ static void pch_gbe_alloc_tx_buffers(struct pch_gbe_adapter *adapter,
struct pch_gbe_tx_ring *tx_ring)
{
struct pch_gbe_buffer *buffer_info;
- struct sk_buff *skb;
unsigned int i;
- unsigned int bufsz;
struct pch_gbe_tx_desc *tx_desc;
- bufsz =
- adapter->hw.mac.max_frame_size + PCH_GBE_DMA_ALIGN + NET_IP_ALIGN;
-
for (i = 0; i < tx_ring->count; i++) {
buffer_info = &tx_ring->buffer_info[i];
- skb = netdev_alloc_skb(adapter->netdev, bufsz);
- skb_reserve(skb, PCH_GBE_DMA_ALIGN);
- buffer_info->skb = skb;
+ buffer_info->skb = NULL;
tx_desc = PCH_GBE_TX_DESC(*tx_ring, i);
tx_desc->gbec_status = (DSC_INIT16);
}
@@ -1622,9 +1625,9 @@ pch_gbe_clean_tx(struct pch_gbe_adapter *adapter,
buffer_info->length, DMA_TO_DEVICE);
buffer_info->mapped = false;
}
- if (buffer_info->skb) {
- pr_debug("trim buffer_info->skb : %d\n", i);
- skb_trim(buffer_info->skb, 0);
+ if (skb) {
+ dev_kfree_skb_any(skb);
+ buffer_info->skb = NULL;
}
tx_desc->gbec_status = DSC_INIT16;
if (unlikely(++i == tx_ring->count))
^ permalink raw reply related
* [PATCH v2 0/8] some netpoll and netconsole fixes
From: Cong Wang @ 2012-08-06 14:23 UTC (permalink / raw)
To: netdev; +Cc: Cong Wang, David S. Miller
V2:
* update patch 1/8 as Eric suggested
* drop the bridge patch, add comments instead
* add patch 8/8
This patch fixes serval problems in netconsole and netpoll.
I ran this patch in my KVM guest with some netpoll test cases,
even covered with some corner cases, everything worked as expected.
BTW, my kernel config enables the following validatation options:
CONFIG_DEBUG_ATOMIC_SLEEP=y
CONFIG_PROVE_LOCKING=y
CONFIG_PROVE_RCU=y
CONFIG_LOCKDEP=y
CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_LOCKUP_DETECTOR=y
CONFIG_HARDLOCKUP_DETECTOR=y
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
Cong Wang (8):
netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup()
netpoll: make __netpoll_cleanup non-block
netconsole: do not release spin_lock when calling __netpoll_cleanup
netpoll: take rcu_read_lock_bh() in netpoll_rx()
netpoll: use netpoll_rx_on() in netpoll_rx()
netpoll: take rcu_read_lock_bh() in netpoll_send_skb_on_dev()
bridge: add some comments for NETDEV_RELEASE
bridge: use list_for_each_entry() in netpoll functions
drivers/net/bonding/bond_main.c | 10 ++---
drivers/net/netconsole.c | 5 --
drivers/net/team/team.c | 16 ++++---
include/linux/netdevice.h | 3 +-
include/linux/netpoll.h | 27 +++++++------
net/8021q/vlan_dev.c | 13 ++----
net/bridge/br_device.c | 27 +++++-------
net/bridge/br_if.c | 6 ++-
net/bridge/br_private.h | 4 +-
net/core/netpoll.c | 84 +++++++++++++++++++++++++--------------
10 files changed, 107 insertions(+), 88 deletions(-)
--
1.7.7.6
^ permalink raw reply
* [PATCH 1/8] netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup()
From: Cong Wang @ 2012-08-06 14:23 UTC (permalink / raw)
To: netdev; +Cc: Cong Wang, Eric Dumazet, David S. Miller
In-Reply-To: <1344263012-4031-1-git-send-email-amwang@redhat.com>
slave_enable_netpoll() and __netpoll_setup() may be called
with read_lock() held, so should use GFP_ATOMIC to allocate
memory. Eric suggested to pass gfp flags to __netpoll_setup().
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
drivers/net/bonding/bond_main.c | 6 +++---
drivers/net/team/team.c | 16 +++++++++-------
include/linux/netdevice.h | 3 ++-
include/linux/netpoll.h | 2 +-
net/8021q/vlan_dev.c | 7 ++++---
net/bridge/br_device.c | 12 ++++++------
net/bridge/br_if.c | 2 +-
net/bridge/br_private.h | 4 ++--
net/core/netpoll.c | 8 ++++----
9 files changed, 32 insertions(+), 28 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 6fae5f3..8697136 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1235,12 +1235,12 @@ static inline int slave_enable_netpoll(struct slave *slave)
struct netpoll *np;
int err = 0;
- np = kzalloc(sizeof(*np), GFP_KERNEL);
+ np = kzalloc(sizeof(*np), GFP_ATOMIC);
err = -ENOMEM;
if (!np)
goto out;
- err = __netpoll_setup(np, slave->dev);
+ err = __netpoll_setup(np, slave->dev, GFP_ATOMIC);
if (err) {
kfree(np);
goto out;
@@ -1292,7 +1292,7 @@ static void bond_netpoll_cleanup(struct net_device *bond_dev)
read_unlock(&bond->lock);
}
-static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
+static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp)
{
struct bonding *bond = netdev_priv(dev);
struct slave *slave;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ba10c46..bbb8524 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -913,16 +913,17 @@ static void team_port_leave(struct team *team, struct team_port *port)
}
#ifdef CONFIG_NET_POLL_CONTROLLER
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int team_port_enable_netpoll(struct team *team, struct team_port *port,
+ gfp_t gfp)
{
struct netpoll *np;
int err;
- np = kzalloc(sizeof(*np), GFP_KERNEL);
+ np = kzalloc(sizeof(*np), gfp);
if (!np)
return -ENOMEM;
- err = __netpoll_setup(np, port->dev);
+ err = __netpoll_setup(np, port->dev, gfp);
if (err) {
kfree(np);
return err;
@@ -951,7 +952,8 @@ static struct netpoll_info *team_netpoll_info(struct team *team)
}
#else
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int team_port_enable_netpoll(struct team *team, struct team_port *port,
+ gfp_t gfp)
{
return 0;
}
@@ -1032,7 +1034,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
}
if (team_netpoll_info(team)) {
- err = team_port_enable_netpoll(team, port);
+ err = team_port_enable_netpoll(team, port, GFP_KERNEL);
if (err) {
netdev_err(dev, "Failed to enable netpoll on device %s\n",
portname);
@@ -1627,7 +1629,7 @@ static void team_netpoll_cleanup(struct net_device *dev)
}
static int team_netpoll_setup(struct net_device *dev,
- struct netpoll_info *npifo)
+ struct netpoll_info *npifo, gfp_t gfp)
{
struct team *team = netdev_priv(dev);
struct team_port *port;
@@ -1635,7 +1637,7 @@ static int team_netpoll_setup(struct net_device *dev,
mutex_lock(&team->lock);
list_for_each_entry(port, &team->port_list, list) {
- err = team_port_enable_netpoll(team, port);
+ err = team_port_enable_netpoll(team, port, gfp);
if (err) {
__team_netpoll_cleanup(team);
break;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a9db4f3..3560d68 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -953,7 +953,8 @@ struct net_device_ops {
#ifdef CONFIG_NET_POLL_CONTROLLER
void (*ndo_poll_controller)(struct net_device *dev);
int (*ndo_netpoll_setup)(struct net_device *dev,
- struct netpoll_info *info);
+ struct netpoll_info *info,
+ gfp_t gfp);
void (*ndo_netpoll_cleanup)(struct net_device *dev);
#endif
int (*ndo_set_vf_mac)(struct net_device *dev,
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 28f5389..bf2d51e 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -43,7 +43,7 @@ struct netpoll_info {
void netpoll_send_udp(struct netpoll *np, const char *msg, int len);
void netpoll_print_options(struct netpoll *np);
int netpoll_parse_options(struct netpoll *np, char *opt);
-int __netpoll_setup(struct netpoll *np, struct net_device *ndev);
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp);
int netpoll_setup(struct netpoll *np);
int netpoll_trap(void);
void netpoll_set_trap(int trap);
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 73a2a83..ee4ae09 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -669,19 +669,20 @@ static void vlan_dev_poll_controller(struct net_device *dev)
return;
}
-static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo)
+static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo,
+ gfp_t gfp)
{
struct vlan_dev_priv *info = vlan_dev_priv(dev);
struct net_device *real_dev = info->real_dev;
struct netpoll *netpoll;
int err = 0;
- netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
+ netpoll = kzalloc(sizeof(*netpoll), gfp);
err = -ENOMEM;
if (!netpoll)
goto out;
- err = __netpoll_setup(netpoll, real_dev);
+ err = __netpoll_setup(netpoll, real_dev, gfp);
if (err) {
kfree(netpoll);
goto out;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 3334845..ed0e0f9 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -213,7 +213,8 @@ static void br_netpoll_cleanup(struct net_device *dev)
}
}
-static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
+static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
+ gfp_t gfp)
{
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *p, *n;
@@ -222,8 +223,7 @@ static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
list_for_each_entry_safe(p, n, &br->port_list, list) {
if (!p->dev)
continue;
-
- err = br_netpoll_enable(p);
+ err = br_netpoll_enable(p, gfp);
if (err)
goto fail;
}
@@ -236,17 +236,17 @@ fail:
goto out;
}
-int br_netpoll_enable(struct net_bridge_port *p)
+int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
{
struct netpoll *np;
int err = 0;
- np = kzalloc(sizeof(*p->np), GFP_KERNEL);
+ np = kzalloc(sizeof(*p->np), gfp);
err = -ENOMEM;
if (!np)
goto out;
- err = __netpoll_setup(np, p->dev);
+ err = __netpoll_setup(np, p->dev, gfp);
if (err) {
kfree(np);
goto out;
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index e1144e1..171fd6b 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -361,7 +361,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
if (err)
goto err2;
- if (br_netpoll_info(br) && ((err = br_netpoll_enable(p))))
+ if (br_netpoll_info(br) && ((err = br_netpoll_enable(p, GFP_KERNEL))))
goto err3;
err = netdev_set_master(dev, br->dev);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index a768b24..f507d2a 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -316,7 +316,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
netpoll_send_skb(np, skb);
}
-extern int br_netpoll_enable(struct net_bridge_port *p);
+extern int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp);
extern void br_netpoll_disable(struct net_bridge_port *p);
#else
static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br)
@@ -329,7 +329,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
{
}
-static inline int br_netpoll_enable(struct net_bridge_port *p)
+static inline int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
{
return 0;
}
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index b4c90e4..37cc854 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -715,7 +715,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
}
EXPORT_SYMBOL(netpoll_parse_options);
-int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
{
struct netpoll_info *npinfo;
const struct net_device_ops *ops;
@@ -734,7 +734,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
}
if (!ndev->npinfo) {
- npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
+ npinfo = kmalloc(sizeof(*npinfo), gfp);
if (!npinfo) {
err = -ENOMEM;
goto out;
@@ -752,7 +752,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
ops = np->dev->netdev_ops;
if (ops->ndo_netpoll_setup) {
- err = ops->ndo_netpoll_setup(ndev, npinfo);
+ err = ops->ndo_netpoll_setup(ndev, npinfo, gfp);
if (err)
goto free_npinfo;
}
@@ -857,7 +857,7 @@ int netpoll_setup(struct netpoll *np)
refill_skbs();
rtnl_lock();
- err = __netpoll_setup(np, ndev);
+ err = __netpoll_setup(np, ndev, GFP_KERNEL);
rtnl_unlock();
if (err)
--
1.7.7.6
^ permalink raw reply related
* [PATCH 2/8] netpoll: make __netpoll_cleanup non-block
From: Cong Wang @ 2012-08-06 14:23 UTC (permalink / raw)
To: netdev; +Cc: Cong Wang, David S. Miller
In-Reply-To: <1344263012-4031-1-git-send-email-amwang@redhat.com>
Like the previous patch, slave_disable_netpoll() and __netpoll_cleanup()
may be called with read_lock() held too, so we should make them
non-block, by moving the cleanup and kfree() to call_rcu_bh() callbacks.
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
drivers/net/bonding/bond_main.c | 4 +--
include/linux/netpoll.h | 3 ++
net/8021q/vlan_dev.c | 6 +----
net/bridge/br_device.c | 6 +----
net/core/netpoll.c | 42 +++++++++++++++++++++++++++++---------
5 files changed, 38 insertions(+), 23 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8697136..e428916 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1257,9 +1257,7 @@ static inline void slave_disable_netpoll(struct slave *slave)
return;
slave->np = NULL;
- synchronize_rcu_bh();
- __netpoll_cleanup(np);
- kfree(np);
+ __netpoll_free_rcu(np);
}
static inline bool slave_dev_support_netpoll(struct net_device *slave_dev)
{
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index bf2d51e..907812e 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -23,6 +23,7 @@ struct netpoll {
u8 remote_mac[ETH_ALEN];
struct list_head rx; /* rx_np list element */
+ struct rcu_head rcu;
};
struct netpoll_info {
@@ -38,6 +39,7 @@ struct netpoll_info {
struct delayed_work tx_work;
struct netpoll *netpoll;
+ struct rcu_head rcu;
};
void netpoll_send_udp(struct netpoll *np, const char *msg, int len);
@@ -48,6 +50,7 @@ int netpoll_setup(struct netpoll *np);
int netpoll_trap(void);
void netpoll_set_trap(int trap);
void __netpoll_cleanup(struct netpoll *np);
+void __netpoll_free_rcu(struct netpoll *np);
void netpoll_cleanup(struct netpoll *np);
int __netpoll_rx(struct sk_buff *skb);
void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index ee4ae09..b65623f 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -704,11 +704,7 @@ static void vlan_dev_netpoll_cleanup(struct net_device *dev)
info->netpoll = NULL;
- /* Wait for transmitting packets to finish before freeing. */
- synchronize_rcu_bh();
-
- __netpoll_cleanup(netpoll);
- kfree(netpoll);
+ __netpoll_free_rcu(netpoll);
}
#endif /* CONFIG_NET_POLL_CONTROLLER */
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index ed0e0f9..f41ba40 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -267,11 +267,7 @@ void br_netpoll_disable(struct net_bridge_port *p)
p->np = NULL;
- /* Wait for transmitting packets to finish before freeing. */
- synchronize_rcu_bh();
-
- __netpoll_cleanup(np);
- kfree(np);
+ __netpoll_free_rcu(np);
}
#endif
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 37cc854..dc17f1d 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -878,6 +878,24 @@ static int __init netpoll_init(void)
}
core_initcall(netpoll_init);
+static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
+{
+ struct netpoll_info *npinfo =
+ container_of(rcu_head, struct netpoll_info, rcu);
+
+ skb_queue_purge(&npinfo->arp_tx);
+ skb_queue_purge(&npinfo->txq);
+
+ /* we can't call cancel_delayed_work_sync here, as we are in softirq */
+ cancel_delayed_work(&npinfo->tx_work);
+
+ /* clean after last, unfinished work */
+ __skb_queue_purge(&npinfo->txq);
+ /* now cancel it again */
+ cancel_delayed_work(&npinfo->tx_work);
+ kfree(npinfo);
+}
+
void __netpoll_cleanup(struct netpoll *np)
{
struct netpoll_info *npinfo;
@@ -903,20 +921,24 @@ void __netpoll_cleanup(struct netpoll *np)
ops->ndo_netpoll_cleanup(np->dev);
RCU_INIT_POINTER(np->dev->npinfo, NULL);
+ call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
+ }
+}
+EXPORT_SYMBOL_GPL(__netpoll_cleanup);
- /* avoid racing with NAPI reading npinfo */
- synchronize_rcu_bh();
+static void rcu_cleanup_netpoll(struct rcu_head *rcu_head)
+{
+ struct netpoll *np = container_of(rcu_head, struct netpoll, rcu);
- skb_queue_purge(&npinfo->arp_tx);
- skb_queue_purge(&npinfo->txq);
- cancel_delayed_work_sync(&npinfo->tx_work);
+ __netpoll_cleanup(np);
+ kfree(np);
+}
- /* clean after last, unfinished work */
- __skb_queue_purge(&npinfo->txq);
- kfree(npinfo);
- }
+void __netpoll_free_rcu(struct netpoll *np)
+{
+ call_rcu_bh(&np->rcu, rcu_cleanup_netpoll);
}
-EXPORT_SYMBOL_GPL(__netpoll_cleanup);
+EXPORT_SYMBOL_GPL(__netpoll_free_rcu);
void netpoll_cleanup(struct netpoll *np)
{
--
1.7.7.6
^ permalink raw reply related
* [PATCH 3/8] netconsole: do not release spin_lock when calling __netpoll_cleanup
From: Cong Wang @ 2012-08-06 14:23 UTC (permalink / raw)
To: netdev; +Cc: Cong Wang, David S. Miller
In-Reply-To: <1344263012-4031-1-git-send-email-amwang@redhat.com>
With the previous patch applied, __netpoll_cleanup() is non-block now,
so we don't need to release the spin_lock before calling it.
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
drivers/net/netconsole.c | 5 -----
1 files changed, 0 insertions(+), 5 deletions(-)
diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index f9347ea..f0ad56c 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -640,12 +640,7 @@ static int netconsole_netdev_event(struct notifier_block *this,
* rtnl_lock already held
*/
if (nt->np.dev) {
- spin_unlock_irqrestore(
- &target_list_lock,
- flags);
__netpoll_cleanup(&nt->np);
- spin_lock_irqsave(&target_list_lock,
- flags);
dev_put(nt->np.dev);
nt->np.dev = NULL;
netconsole_target_put(nt);
--
1.7.7.6
^ permalink raw reply related
* [PATCH 4/8] netpoll: take rcu_read_lock_bh() in netpoll_rx()
From: Cong Wang @ 2012-08-06 14:23 UTC (permalink / raw)
To: netdev; +Cc: Cong Wang, David S. Miller
In-Reply-To: <1344263012-4031-1-git-send-email-amwang@redhat.com>
In __netpoll_rx(), it dereferences ->npinfo without rcu_dereference_bh(),
this patch fixes it by using the 'npinfo' passed from netpoll_rx()
where it is already dereferenced with rcu_dereference_bh().
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
include/linux/netpoll.h | 4 ++--
net/core/netpoll.c | 3 +--
2 files changed, 3 insertions(+), 4 deletions(-)
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 907812e..5d881c3 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -52,7 +52,7 @@ void netpoll_set_trap(int trap);
void __netpoll_cleanup(struct netpoll *np);
void __netpoll_free_rcu(struct netpoll *np);
void netpoll_cleanup(struct netpoll *np);
-int __netpoll_rx(struct sk_buff *skb);
+int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo);
void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
struct net_device *dev);
static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
@@ -77,7 +77,7 @@ static inline bool netpoll_rx(struct sk_buff *skb)
spin_lock(&npinfo->rx_lock);
/* check rx_flags again with the lock held */
- if (npinfo->rx_flags && __netpoll_rx(skb))
+ if (npinfo->rx_flags && __netpoll_rx(skb, npinfo))
ret = true;
spin_unlock(&npinfo->rx_lock);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index dc17f1d..d055bb0 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -543,13 +543,12 @@ static void arp_reply(struct sk_buff *skb)
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
}
-int __netpoll_rx(struct sk_buff *skb)
+int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
{
int proto, len, ulen;
int hits = 0;
const struct iphdr *iph;
struct udphdr *uh;
- struct netpoll_info *npinfo = skb->dev->npinfo;
struct netpoll *np, *tmp;
if (list_empty(&npinfo->rx_np))
--
1.7.7.6
^ permalink raw reply related
* [PATCH 7/8] bridge: add some comments for NETDEV_RELEASE
From: Cong Wang @ 2012-08-06 14:23 UTC (permalink / raw)
To: netdev; +Cc: Cong Wang, Stephen Hemminger
In-Reply-To: <1344263012-4031-1-git-send-email-amwang@redhat.com>
Add comments on why we don't notify NETDEV_RELEASE.
Cc: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
net/bridge/br_if.c | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 171fd6b..910f4aa 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -427,6 +427,10 @@ int br_del_if(struct net_bridge *br, struct net_device *dev)
if (!p || p->br != br)
return -EINVAL;
+ /*
+ * We don't notify NETDEV_RELEASE event, as this will
+ * stop netconsole on the bridge.
+ */
del_nbp(p);
spin_lock_bh(&br->lock);
--
1.7.7.6
^ permalink raw reply related
* [PATCH 6/8] netpoll: take rcu_read_lock_bh() in netpoll_send_skb_on_dev()
From: Cong Wang @ 2012-08-06 14:23 UTC (permalink / raw)
To: netdev; +Cc: Cong Wang, David S. Miller
In-Reply-To: <1344263012-4031-1-git-send-email-amwang@redhat.com>
This patch fixes several problems in the call path of
netpoll_send_skb_on_dev():
1. We already disable IRQ's before calling netpoll_send_skb_on_dev(),
so we don't need to disable IRQ's again.
2. All the callees of netpoll_send_skb_on_dev() should use
rcu_dereference_bh() to dereference ->npinfo.
3. Rename arp_reply() to netpoll_arp_reply(), the former is too generic.
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
net/core/netpoll.c | 31 +++++++++++++++++--------------
1 files changed, 17 insertions(+), 14 deletions(-)
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index d055bb0..174346a 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -54,7 +54,7 @@ static atomic_t trapped;
MAX_UDP_CHUNK)
static void zap_completion_queue(void);
-static void arp_reply(struct sk_buff *skb);
+static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
static unsigned int carrier_timeout = 4;
module_param(carrier_timeout, uint, 0644);
@@ -170,7 +170,8 @@ static void poll_napi(struct net_device *dev)
list_for_each_entry(napi, &dev->napi_list, dev_list) {
if (napi->poll_owner != smp_processor_id() &&
spin_trylock(&napi->poll_lock)) {
- budget = poll_one_napi(dev->npinfo, napi, budget);
+ budget = poll_one_napi(rcu_dereference_bh(dev->npinfo),
+ napi, budget);
spin_unlock(&napi->poll_lock);
if (!budget)
@@ -185,13 +186,14 @@ static void service_arp_queue(struct netpoll_info *npi)
struct sk_buff *skb;
while ((skb = skb_dequeue(&npi->arp_tx)))
- arp_reply(skb);
+ netpoll_arp_reply(skb, npi);
}
}
static void netpoll_poll_dev(struct net_device *dev)
{
const struct net_device_ops *ops;
+ struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
if (!dev || !netif_running(dev))
return;
@@ -206,17 +208,18 @@ static void netpoll_poll_dev(struct net_device *dev)
poll_napi(dev);
if (dev->flags & IFF_SLAVE) {
- if (dev->npinfo) {
+ if (ni) {
struct net_device *bond_dev = dev->master;
struct sk_buff *skb;
- while ((skb = skb_dequeue(&dev->npinfo->arp_tx))) {
+ struct netpoll_info *bond_ni = rcu_dereference_bh(bond_dev->npinfo);
+ while ((skb = skb_dequeue(&ni->arp_tx))) {
skb->dev = bond_dev;
- skb_queue_tail(&bond_dev->npinfo->arp_tx, skb);
+ skb_queue_tail(&bond_ni->arp_tx, skb);
}
}
}
- service_arp_queue(dev->npinfo);
+ service_arp_queue(ni);
zap_completion_queue();
}
@@ -302,6 +305,7 @@ static int netpoll_owner_active(struct net_device *dev)
return 0;
}
+/* call with IRQ disabled */
void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
struct net_device *dev)
{
@@ -309,8 +313,11 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
unsigned long tries;
const struct net_device_ops *ops = dev->netdev_ops;
/* It is up to the caller to keep npinfo alive. */
- struct netpoll_info *npinfo = np->dev->npinfo;
+ struct netpoll_info *npinfo;
+
+ WARN_ON_ONCE(!irqs_disabled());
+ npinfo = rcu_dereference_bh(np->dev->npinfo);
if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
__kfree_skb(skb);
return;
@@ -319,11 +326,9 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
/* don't get messages out of order, and no recursion */
if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
struct netdev_queue *txq;
- unsigned long flags;
txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
- local_irq_save(flags);
/* try until next clock tick */
for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
tries > 0; --tries) {
@@ -347,10 +352,9 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
}
WARN_ONCE(!irqs_disabled(),
- "netpoll_send_skb(): %s enabled interrupts in poll (%pF)\n",
+ "netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
dev->name, ops->ndo_start_xmit);
- local_irq_restore(flags);
}
if (status != NETDEV_TX_OK) {
@@ -423,9 +427,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
}
EXPORT_SYMBOL(netpoll_send_udp);
-static void arp_reply(struct sk_buff *skb)
+static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
{
- struct netpoll_info *npinfo = skb->dev->npinfo;
struct arphdr *arp;
unsigned char *arp_ptr;
int size, type = ARPOP_REPLY, ptype = ETH_P_ARP;
--
1.7.7.6
^ permalink raw reply related
* [PATCH 5/8] netpoll: use netpoll_rx_on() in netpoll_rx()
From: Cong Wang @ 2012-08-06 14:23 UTC (permalink / raw)
To: netdev; +Cc: Cong Wang, David S. Miller
In-Reply-To: <1344263012-4031-1-git-send-email-amwang@redhat.com>
The logic of the code is same, just call netpoll_rx_on().
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
include/linux/netpoll.h | 18 +++++++++---------
1 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 5d881c3..2d178ba 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -63,6 +63,13 @@ static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
#ifdef CONFIG_NETPOLL
+static inline int netpoll_rx_on(struct sk_buff *skb)
+{
+ struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo);
+
+ return npinfo && (!list_empty(&npinfo->rx_np) || npinfo->rx_flags);
+}
+
static inline bool netpoll_rx(struct sk_buff *skb)
{
struct netpoll_info *npinfo;
@@ -70,11 +77,11 @@ static inline bool netpoll_rx(struct sk_buff *skb)
bool ret = false;
local_irq_save(flags);
- npinfo = rcu_dereference_bh(skb->dev->npinfo);
- if (!npinfo || (list_empty(&npinfo->rx_np) && !npinfo->rx_flags))
+ if (!netpoll_rx_on(skb))
goto out;
+ npinfo = rcu_dereference_bh(skb->dev->npinfo);
spin_lock(&npinfo->rx_lock);
/* check rx_flags again with the lock held */
if (npinfo->rx_flags && __netpoll_rx(skb, npinfo))
@@ -86,13 +93,6 @@ out:
return ret;
}
-static inline int netpoll_rx_on(struct sk_buff *skb)
-{
- struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo);
-
- return npinfo && (!list_empty(&npinfo->rx_np) || npinfo->rx_flags);
-}
-
static inline int netpoll_receive_skb(struct sk_buff *skb)
{
if (!list_empty(&skb->dev->napi_list))
--
1.7.7.6
^ permalink raw reply related
* [PATCH 8/8] bridge: use list_for_each_entry() in netpoll functions
From: Cong Wang @ 2012-08-06 14:23 UTC (permalink / raw)
To: netdev; +Cc: Cong Wang, Stephen Hemminger
In-Reply-To: <1344263012-4031-1-git-send-email-amwang@redhat.com>
We don't delete 'p' from the list in the loop,
so we can just use list_for_each_entry().
Cc: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
net/bridge/br_device.c | 9 ++++-----
1 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index f41ba40..32211fa 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -206,21 +206,20 @@ static void br_poll_controller(struct net_device *br_dev)
static void br_netpoll_cleanup(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
- struct net_bridge_port *p, *n;
+ struct net_bridge_port *p;
- list_for_each_entry_safe(p, n, &br->port_list, list) {
+ list_for_each_entry(p, &br->port_list, list)
br_netpoll_disable(p);
- }
}
static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
gfp_t gfp)
{
struct net_bridge *br = netdev_priv(dev);
- struct net_bridge_port *p, *n;
+ struct net_bridge_port *p;
int err = 0;
- list_for_each_entry_safe(p, n, &br->port_list, list) {
+ list_for_each_entry(p, &br->port_list, list) {
if (!p->dev)
continue;
err = br_netpoll_enable(p, gfp);
--
1.7.7.6
^ permalink raw reply related
* [BUG] af_packet: loop at reception when using fanout
From: Eric Leblond @ 2012-08-06 14:21 UTC (permalink / raw)
To: netdev, David Miller
[-- Attachment #1: Type: text/plain, Size: 1640 bytes --]
Hello,
When using fanout mode on a AF_PACKET socket, the packet sent via one of
the fanout socket are sent back to one of the socket in the fanout set.
I've read the code and the error seems to be in dev.c.
The code check if skb->sk is not equal to ptype->af_packet_priv but in
the fanout case, we should check that skb->sk is not in the sockets of
the fanout set.
Here's how could look a possible implementation of the fix:
diff --git a/net/core/dev.c b/net/core/dev.c
index 1cb0d8a..63d144f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1654,7 +1654,12 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
*/
if ((ptype->dev == dev || !ptype->dev) &&
(ptype->af_packet_priv == NULL ||
- (struct sock *)ptype->af_packet_priv != skb->sk)) {
+ (((struct sock *)ptype->af_packet_priv != skb->sk)
+ &&
+ /* MISSING CHECK: af_packet_priv skb->sk one of the socket in fanout id of skb */
+ ! packet_sk_in_fanout(ptype, skb->sk)
+ )
+ ) {
if (pt_prev) {
deliver_skb(skb2, pt_prev, skb->dev);
pt_prev = ptype;
If this is done, we will have to export one function from the af_packet
module and I don't like the idea. If it is correct way to do it I can
implement this and propose a patch.
BR,
--
Eric Leblond
Blog: http://home.regit.org/ - Portfolio: http://regit.500px.com/
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 198 bytes --]
^ permalink raw reply related
* RE: pch_gbe: dont-copy-payload (was [PATCH 1/4] ...)
From: Eric Dumazet @ 2012-08-06 14:52 UTC (permalink / raw)
To: Andy Cress; +Cc: netdev
In-Reply-To: <40680C535D6FE6498883F1640FACD44D0122CF12@ka-exchange-1.kontronamerica.local>
On Mon, 2012-08-06 at 07:19 -0700, Andy Cress wrote:
> I found out why the proposed dont-copy-payload patch didn't work with
> this pch_gbe NIC.
> This NIC PHY requires 64-byte-aligned DMA, and the transmit buffers
> won't be transferred if skb->data is not 64-byte-aligned. Apparently
> the data copy has a by-product of aligning the buffers.
>
> I tried using skb_reserve(skb,64) in pch_gbe_alloc_tx_buffers and
> pch-gbe_alloc_rx_buffers, but that didn't seem to resolve it.
>
> How can I make sure that the transmit data buffers are
> 64-byte-aligned?
>
There is no support for such requirement in linux stacks.
Only solution for the driver is to copy all frames to 64-byte-aligned
bounce buffers.
^ permalink raw reply
* [PATCH 0/2] Add device tree support for davinci_mdio driver and fix cpsw DT binding documentation
From: Mugunthan V N @ 2012-08-06 15:05 UTC (permalink / raw)
To: netdev
Cc: Mugunthan V N, devicetree-discuss, linux-omap, davem,
linux-arm-kernel
This patch set adds support for device tree for Davinci MDIO driver and fixes
CPSW DT binding documentation to make it copy pastable to dts file.
This patch set is tested with the following git tree on AM335X Beagle Bone
https://github.com/hvaibhav/am335x-linux/tree/am335x-upstream-staging-cpsw
Mugunthan V N (2):
drivers: net: ethernet: davince_mdio: device tree implementation
documentation: dt: bindings: cpsw: fixing the examples for directly
using it in dts file
Documentation/devicetree/bindings/net/cpsw.txt | 101 ++++++++++---------
.../devicetree/bindings/net/davinci-mdio.txt | 33 +++++++
drivers/net/ethernet/ti/davinci_mdio.c | 41 +++++++-
3 files changed, 123 insertions(+), 52 deletions(-)
create mode 100644 Documentation/devicetree/bindings/net/davinci-mdio.txt
^ permalink raw reply
* [PATCH 1/2] drivers: net: ethernet: davince_mdio: device tree implementation
From: Mugunthan V N @ 2012-08-06 15:05 UTC (permalink / raw)
To: netdev
Cc: davem, devicetree-discuss, linux-arm-kernel, linux-omap,
Mugunthan V N
In-Reply-To: <1344265558-5724-1-git-send-email-mugunthanvnm@ti.com>
device tree implementation for davinci mdio driver
Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
---
.../devicetree/bindings/net/davinci-mdio.txt | 33 ++++++++++++++++
drivers/net/ethernet/ti/davinci_mdio.c | 41 ++++++++++++++++++--
2 files changed, 70 insertions(+), 4 deletions(-)
create mode 100644 Documentation/devicetree/bindings/net/davinci-mdio.txt
diff --git a/Documentation/devicetree/bindings/net/davinci-mdio.txt b/Documentation/devicetree/bindings/net/davinci-mdio.txt
new file mode 100644
index 0000000..72efaaf
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/davinci-mdio.txt
@@ -0,0 +1,33 @@
+TI SoC Davinci MDIO Controller Device Tree Bindings
+---------------------------------------------------
+
+Required properties:
+- compatible : Should be "ti,davinci_mdio"
+- reg : physical base address and size of the davinci mdio
+ registers map
+- bus_freq : Mdio Bus frequency
+
+Optional properties:
+- ti,hwmods : Must be "davinci_mdio"
+
+Note: "ti,hwmods" field is used to fetch the base address and irq
+resources from TI, omap hwmod data base during device registration.
+Future plan is to migrate hwmod data base contents into device tree
+blob so that, all the required data will be used from device tree dts
+file.
+
+Examples:
+
+ mdio: davinci_mdio@4A101000 {
+ compatible = "ti,cpsw";
+ reg = <0x4A101000 0x1000>;
+ bus_freq = <1000000>;
+ };
+
+(or)
+
+ mdio: davinci_mdio@4A101000 {
+ compatible = "ti,cpsw";
+ ti,hwmods = "davinci_mdio";
+ bus_freq = <1000000>;
+ };
diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c
index cd7ee20..573f3be 100644
--- a/drivers/net/ethernet/ti/davinci_mdio.c
+++ b/drivers/net/ethernet/ti/davinci_mdio.c
@@ -36,6 +36,8 @@
#include <linux/io.h>
#include <linux/pm_runtime.h>
#include <linux/davinci_emac.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
/*
* This timeout definition is a worst-case ultra defensive measure against
@@ -289,6 +291,25 @@ static int davinci_mdio_write(struct mii_bus *bus, int phy_id,
return 0;
}
+static int davinci_mdio_probe_dt(struct mdio_platform_data *data,
+ struct platform_device *pdev)
+{
+ struct device_node *node = pdev->dev.of_node;
+ u32 prop;
+
+ if (!node)
+ return -EINVAL;
+
+ if (of_property_read_u32(node, "bus_freq", &prop)) {
+ pr_err("Missing bus_freq property in the DT.\n");
+ return -EINVAL;
+ }
+ data->bus_freq = prop;
+
+ return 0;
+}
+
+
static int __devinit davinci_mdio_probe(struct platform_device *pdev)
{
struct mdio_platform_data *pdata = pdev->dev.platform_data;
@@ -304,8 +325,6 @@ static int __devinit davinci_mdio_probe(struct platform_device *pdev)
return -ENOMEM;
}
- data->pdata = pdata ? (*pdata) : default_pdata;
-
data->bus = mdiobus_alloc();
if (!data->bus) {
dev_err(dev, "failed to alloc mii bus\n");
@@ -313,14 +332,22 @@ static int __devinit davinci_mdio_probe(struct platform_device *pdev)
goto bail_out;
}
+ if (dev->of_node) {
+ if (davinci_mdio_probe_dt(&data->pdata, pdev))
+ data->pdata = default_pdata;
+ snprintf(data->bus->id, MII_BUS_ID_SIZE, "%s", pdev->name);
+ } else {
+ data->pdata = pdata ? (*pdata) : default_pdata;
+ snprintf(data->bus->id, MII_BUS_ID_SIZE, "%s-%x",
+ pdev->name, pdev->id);
+ }
+
data->bus->name = dev_name(dev);
data->bus->read = davinci_mdio_read,
data->bus->write = davinci_mdio_write,
data->bus->reset = davinci_mdio_reset,
data->bus->parent = dev;
data->bus->priv = data;
- snprintf(data->bus->id, MII_BUS_ID_SIZE, "%s-%x",
- pdev->name, pdev->id);
pm_runtime_enable(&pdev->dev);
pm_runtime_get_sync(&pdev->dev);
@@ -454,11 +481,17 @@ static const struct dev_pm_ops davinci_mdio_pm_ops = {
.resume = davinci_mdio_resume,
};
+static const struct of_device_id davinci_mdio_of_mtable[] = {
+ { .compatible = "ti,davinci_mdio", },
+ { /* sentinel */ },
+};
+
static struct platform_driver davinci_mdio_driver = {
.driver = {
.name = "davinci_mdio",
.owner = THIS_MODULE,
.pm = &davinci_mdio_pm_ops,
+ .of_match_table = of_match_ptr(davinci_mdio_of_mtable),
},
.probe = davinci_mdio_probe,
.remove = __devexit_p(davinci_mdio_remove),
--
1.7.0.4
^ permalink raw reply related
* [PATCH 2/2] documentation: dt: bindings: cpsw: fixing the examples for directly using it in dts file
From: Mugunthan V N @ 2012-08-06 15:05 UTC (permalink / raw)
To: netdev
Cc: davem, devicetree-discuss, linux-arm-kernel, linux-omap,
Mugunthan V N
In-Reply-To: <1344265558-5724-1-git-send-email-mugunthanvnm@ti.com>
Fixing the cpsw device tree example to make it simpler to copy pastable to dts
file and use it directly.
Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
---
Documentation/devicetree/bindings/net/cpsw.txt | 101 ++++++++++++-----------
1 files changed, 53 insertions(+), 48 deletions(-)
diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index acca48c..dcaabe9 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -11,6 +11,7 @@ Required properties:
- cpdma_channels : Specifies number of channels in CPDMA
- host_port_no : Specifies host port shift
- cpdma_reg_ofs : Specifies CPDMA submodule register offset
+- cpdma_sram_ofs : Specifies CPDMA SRAM offset
- ale_reg_ofs : Specifies ALE submodule register offset
- ale_entries : Specifies No of entries ALE can hold
- host_port_reg_ofs : Specifies host port register offset
@@ -43,62 +44,66 @@ Examples:
reg = <0x4A100000 0x1000>;
interrupts = <55 0x4>;
interrupt-parent = <&intc>;
- cpdma_channels = 8;
- host_port_no = 0;
- cpdma_reg_ofs = 0x800;
- ale_reg_ofs = 0xd00;
- ale_entries = 1024;
- host_port_reg_ofs = 0x108;
- hw_stats_reg_ofs = 0x900;
- bd_ram_ofs = 0x2000;
- bd_ram_size = 0x2000;
- no_bd_ram = 0;
- rx_descs = 64;
- mac_control = 0x20;
- slaves = 2;
- slave@0 {
- slave_reg_ofs = 0x208;
- sliver_reg_ofs = 0xd80;
- phy_id = "davinci_mdio-0:00"
- mac-address = [00 04 9F 01 1B B8];
+ cpdma_channels = <8>;
+ host_port_no = <0>;
+ cpdma_reg_ofs = <0x800>;
+ cpdma_sram_ofs = <0xa00>;
+ ale_reg_ofs = <0xd00>;
+ ale_entries = <1024>;
+ host_port_reg_ofs = <0x108>;
+ hw_stats_reg_ofs = <0x900>;
+ bd_ram_ofs = <0x2000>;
+ bd_ram_size = <0x2000>;
+ no_bd_ram = <0>;
+ rx_descs = <64>;
+ mac_control = <0x20>;
+ slaves = <2>;
+ cpsw_emac0: slave@0 {
+ slave_reg_ofs = <0x208>;
+ sliver_reg_ofs = <0xd80>;
+ phy_id = "davinci_mdio.16:00";
+ /* Filled in by U-Boot */
+ mac-address = [ 00 00 00 00 00 00 ];
};
- slave@1 {
- slave_reg_ofs = 0x208;
- sliver_reg_ofs = 0xd80;
- phy_id = "davinci_mdio-0:01"
- mac-address = [00 04 9F 01 1B B9];
+ cpsw_emac1: slave@1 {
+ slave_reg_ofs = <0x308>;
+ sliver_reg_ofs = <0xdc0>;
+ phy_id = "davinci_mdio.16:01";
+ /* Filled in by U-Boot */
+ mac-address = [ 00 00 00 00 00 00 ];
};
};
(or)
-
mac: ethernet@4A100000 {
compatible = "ti,cpsw";
ti,hwmods = "cpgmac0";
- cpdma_channels = 8;
- host_port_no = 0;
- cpdma_reg_ofs = 0x800;
- ale_reg_ofs = 0xd00;
- ale_entries = 1024;
- host_port_reg_ofs = 0x108;
- hw_stats_reg_ofs = 0x900;
- bd_ram_ofs = 0x2000;
- bd_ram_size = 0x2000;
- no_bd_ram = 0;
- rx_descs = 64;
- mac_control = 0x20;
- slaves = 2;
- slave@0 {
- slave_reg_ofs = 0x208;
- sliver_reg_ofs = 0xd80;
- phy_id = "davinci_mdio-0:00"
- mac-address = [00 04 9F 01 1B B8];
+ cpdma_channels = <8>;
+ host_port_no = <0>;
+ cpdma_reg_ofs = <0x800>;
+ cpdma_sram_ofs = <0xa00>;
+ ale_reg_ofs = <0xd00>;
+ ale_entries = <1024>;
+ host_port_reg_ofs = <0x108>;
+ hw_stats_reg_ofs = <0x900>;
+ bd_ram_ofs = <0x2000>;
+ bd_ram_size = <0x2000>;
+ no_bd_ram = <0>;
+ rx_descs = <64>;
+ mac_control = <0x20>;
+ slaves = <2>;
+ cpsw_emac0: slave@0 {
+ slave_reg_ofs = <0x208>;
+ sliver_reg_ofs = <0xd80>;
+ phy_id = "davinci_mdio.16:00";
+ /* Filled in by U-Boot */
+ mac-address = [ 00 00 00 00 00 00 ];
};
- slave@1 {
- slave_reg_ofs = 0x208;
- sliver_reg_ofs = 0xd80;
- phy_id = "davinci_mdio-0:01"
- mac-address = [00 04 9F 01 1B B9];
+ cpsw_emac1: slave@1 {
+ slave_reg_ofs = <0x308>;
+ sliver_reg_ofs = <0xdc0>;
+ phy_id = "davinci_mdio.16:01";
+ /* Filled in by U-Boot */
+ mac-address = [ 00 00 00 00 00 00 ];
};
-
};
--
1.7.0.4
^ permalink raw reply related
* [PATCH] net: ipv6: fix TCP early demux
From: Eric Dumazet @ 2012-08-06 15:09 UTC (permalink / raw)
To: David Miller; +Cc: netdev
From: Eric Dumazet <edumazet@google.com>
IPv6 needs a cookie in dst_check() call.
We need to add rx_dst_cookie and provide a family independent
sk_rx_dst_set(sk, skb) method to properly support IPv6 TCP early demux.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
Note: we could group sk_rx_dst/rx_dst_ifindex/rx_dst_cookie
in same cache line (in sk)
include/linux/ipv6.h | 1 +
include/net/inet_connection_sock.h | 1 +
include/net/inet_sock.h | 9 ---------
net/ipv4/tcp_input.c | 4 +++-
net/ipv4/tcp_ipv4.c | 13 ++++++++++---
net/ipv4/tcp_minisocks.c | 2 +-
net/ipv6/tcp_ipv6.c | 27 +++++++++++++++++++++++++--
7 files changed, 41 insertions(+), 16 deletions(-)
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 379e433..879db26 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -369,6 +369,7 @@ struct ipv6_pinfo {
__u8 rcv_tclass;
__u32 dst_cookie;
+ __u32 rx_dst_cookie;
struct ipv6_mc_socklist __rcu *ipv6_mc_list;
struct ipv6_ac_socklist *ipv6_ac_list;
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 5ee66f5..ba1d361 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -39,6 +39,7 @@ struct inet_connection_sock_af_ops {
int (*queue_xmit)(struct sk_buff *skb, struct flowi *fl);
void (*send_check)(struct sock *sk, struct sk_buff *skb);
int (*rebuild_header)(struct sock *sk);
+ void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb);
int (*conn_request)(struct sock *sk, struct sk_buff *skb);
struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 83b567f..613cfa4 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -249,13 +249,4 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
return flags;
}
-static inline void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
-{
- struct dst_entry *dst = skb_dst(skb);
-
- dst_hold(dst);
- sk->sk_rx_dst = dst;
- inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
-}
-
#endif /* _INET_SOCK_H */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2fd2bc9..85308b9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5392,6 +5392,8 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
{
struct tcp_sock *tp = tcp_sk(sk);
+ if (unlikely(sk->sk_rx_dst == NULL))
+ inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
/*
* Header prediction.
* The code loosely follows the one in the famous
@@ -5605,7 +5607,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
tcp_set_state(sk, TCP_ESTABLISHED);
if (skb != NULL) {
- inet_sk_rx_dst_set(sk, skb);
+ icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
security_inet_conn_established(sk, skb);
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 42b2a6a..272241f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1627,9 +1627,6 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
sk->sk_rx_dst = NULL;
}
}
- if (unlikely(sk->sk_rx_dst == NULL))
- inet_sk_rx_dst_set(sk, skb);
-
if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
rsk = sk;
goto reset;
@@ -1872,10 +1869,20 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = {
.twsk_destructor= tcp_twsk_destructor,
};
+static void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+
+ dst_hold(dst);
+ sk->sk_rx_dst = dst;
+ inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+}
+
const struct inet_connection_sock_af_ops ipv4_specific = {
.queue_xmit = ip_queue_xmit,
.send_check = tcp_v4_send_check,
.rebuild_header = inet_sk_rebuild_header,
+ .sk_rx_dst_set = inet_sk_rx_dst_set,
.conn_request = tcp_v4_conn_request,
.syn_recv_sock = tcp_v4_syn_recv_sock,
.net_header_len = sizeof(struct iphdr),
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 232a90c..d9c9dce 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -387,7 +387,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
struct tcp_sock *oldtp = tcp_sk(sk);
struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
- inet_sk_rx_dst_set(newsk, skb);
+ newicsk->icsk_af_ops->sk_rx_dst_set(newsk, skb);
/* TCP Cookie Transactions require space for the cookie pair,
* as it differs for each connection. There is no need to
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c66b90f..5a439e9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1447,7 +1447,17 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC));
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
+ struct dst_entry *dst = sk->sk_rx_dst;
+
sock_rps_save_rxhash(sk, skb);
+ if (dst) {
+ if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
+ dst->ops->check(dst, np->rx_dst_cookie) == NULL) {
+ dst_release(dst);
+ sk->sk_rx_dst = NULL;
+ }
+ }
+
if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len))
goto reset;
if (opt_skb)
@@ -1705,9 +1715,9 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
struct dst_entry *dst = sk->sk_rx_dst;
struct inet_sock *icsk = inet_sk(sk);
if (dst)
- dst = dst_check(dst, 0);
+ dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
if (dst &&
- icsk->rx_dst_ifindex == inet6_iif(skb))
+ icsk->rx_dst_ifindex == skb->skb_iif)
skb_dst_set_noref(skb, dst);
}
}
@@ -1719,10 +1729,23 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = {
.twsk_destructor= tcp_twsk_destructor,
};
+static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ const struct rt6_info *rt = (const struct rt6_info *)dst;
+
+ dst_hold(dst);
+ sk->sk_rx_dst = dst;
+ inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+ if (rt->rt6i_node)
+ inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+}
+
static const struct inet_connection_sock_af_ops ipv6_specific = {
.queue_xmit = inet6_csk_xmit,
.send_check = tcp_v6_send_check,
.rebuild_header = inet6_sk_rebuild_header,
+ .sk_rx_dst_set = inet6_sk_rx_dst_set,
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
.net_header_len = sizeof(struct ipv6hdr),
^ permalink raw reply related
* Re: [PATCH 1/8] netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup()
From: Eric Dumazet @ 2012-08-06 15:20 UTC (permalink / raw)
To: Cong Wang; +Cc: netdev, David S. Miller
In-Reply-To: <1344263012-4031-2-git-send-email-amwang@redhat.com>
On Mon, 2012-08-06 at 22:23 +0800, Cong Wang wrote:
> slave_enable_netpoll() and __netpoll_setup() may be called
> with read_lock() held, so should use GFP_ATOMIC to allocate
> memory. Eric suggested to pass gfp flags to __netpoll_setup().
>
> Cc: Eric Dumazet <eric.dumazet@gmail.com>
> Cc: "David S. Miller" <davem@davemloft.net>
> Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
> Signed-off-by: Cong Wang <amwang@redhat.com>
> ---
You based this on net-next, but didnt add the net-next suffix in your
[PATCH ...] description.
Signed-off-by: Eric Dumazet <edumazet@google.com>
^ permalink raw reply
* [PATCH net] net_sched: act: Delete estimator in error path.
From: Hiroaki SHIMODA @ 2012-08-06 15:45 UTC (permalink / raw)
To: davem; +Cc: netdev
Some action modules free struct tcf_common in their error path
while estimator is still active. This results in est_timer()
dereference freed memory.
Add gen_kill_estimator() in ipt, pedit and simple action.
Signed-off-by: Hiroaki SHIMODA <shimoda.hiroaki@gmail.com>
---
net/sched/act_ipt.c | 7 ++++++-
net/sched/act_pedit.c | 5 ++++-
net/sched/act_simple.c | 5 ++++-
3 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 60e281a..58fb3c7 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -185,7 +185,12 @@ err3:
err2:
kfree(tname);
err1:
- kfree(pc);
+ if (ret == ACT_P_CREATED) {
+ if (est)
+ gen_kill_estimator(&pc->tcfc_bstats,
+ &pc->tcfc_rate_est);
+ kfree_rcu(pc, tcfc_rcu);
+ }
return err;
}
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 26aa2f6..45c53ab 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -74,7 +74,10 @@ static int tcf_pedit_init(struct nlattr *nla, struct nlattr *est,
p = to_pedit(pc);
keys = kmalloc(ksize, GFP_KERNEL);
if (keys == NULL) {
- kfree(pc);
+ if (est)
+ gen_kill_estimator(&pc->tcfc_bstats,
+ &pc->tcfc_rate_est);
+ kfree_rcu(pc, tcfc_rcu);
return -ENOMEM;
}
ret = ACT_P_CREATED;
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 3922f2a..3714f60 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -131,7 +131,10 @@ static int tcf_simp_init(struct nlattr *nla, struct nlattr *est,
d = to_defact(pc);
ret = alloc_defdata(d, defdata);
if (ret < 0) {
- kfree(pc);
+ if (est)
+ gen_kill_estimator(&pc->tcfc_bstats,
+ &pc->tcfc_rate_est);
+ kfree_rcu(pc, tcfc_rcu);
return ret;
}
d->tcf_action = parm->action;
--
1.7.8.6
^ permalink raw reply related
* WARNING: at net/ipv4/tcp.c:1598 tcp_recvmsg+0x641/0xd30()
From: Dave Jones @ 2012-08-06 15:46 UTC (permalink / raw)
To: netdev; +Cc: Fedora Kernel Team
We just got an automated report of this WARN being hit in 3.5
> backtrace:
> :WARNING: at net/ipv4/tcp.c:1598 tcp_recvmsg+0x641/0xd30()
> :Hardware name: P5Q DELUXE
> :recvmsg bug: copied 99F66400 seq 99F6A4A8 rcvnxt 99F6CDAD fl 0
> : [<ffffffff811848e6>] do_sync_read+0xe6/0x120
> : [<ffffffff81275eea>] ? inode_has_perm.isra.31.constprop.61+0x2a/0x30
> : [<ffffffff81272f32>] ? security_file_permission+0x92/0xb0
> : [<ffffffff81184d81>] ? rw_verify_area+0x61/0xf0
> : [<ffffffff811852cd>] vfs_read+0x15d/0x180
> : [<ffffffff8118533a>] sys_read+0x4a/0x90
> : [<ffffffff8160fc29>] system_call_fastpath+0x16/0x1b
1594 /* Now that we have two receive queues this
1595 * shouldn't happen.
1596 */
1597 if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
1598 "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n",
1599 *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
1600 flags))
1601 break;
Hopefully this means more to you guys than it does to me.
Dave
^ permalink raw reply
* Re: ethtool 3.5 released
From: Ben Hutchings @ 2012-08-06 16:41 UTC (permalink / raw)
To: Naoto MATSUMOTO; +Cc: netdev
In-Reply-To: <20120806102723.D637.C42C3789@sakura.ad.jp>
On Mon, 2012-08-06 at 10:27 +0900, Naoto MATSUMOTO wrote:
> Dear Ben.
>
> FYI(For Your Information)
> This is Naoto MATSUMOTO, Senior Researcher, SAKURA Internet.
>
> We tried ethtool 3.5 on 40GbE NIC(Mellanox), it's result here.
> -----------------------------------------------------------------------
> # ./ethtool --version
> ethtool version 3.5
>
> # ./ethtool eth1
> Settings for eth1:
> Supported ports: [ TP ]
> Supported link modes: 10000baseT/Full
> Supported pause frame use: No
> Supports auto-negotiation: No
> Advertised link modes: 10000baseT/Full
> Advertised pause frame use: No
> Advertised auto-negotiation: No
> Speed: 40000Mb/s
> Duplex: Full
> Port: Twisted Pair
40G twisted-pair, eh?
> PHYAD: 0
> Transceiver: internal
> Auto-negotiation: off
> MDI-X: Unknown
> Supports Wake-on: d
> Wake-on: d
> Current message level: 0x00000014 (20)
> link ifdown
> Link detected: yes
>
>
> Our 40GbE NIC Firmware/Dirver status are here.
> -----------------------------------------------------------------------
> Mellanox ConnectX HCA Ethernet driver v1.5.8.3 (June 2012)
> Ethernet controller: Mellanox Technologies MT27500 Family [ConnectX-3]
> Firmware Version: 2.10.800
> -----------------------------------------------------------------------
>
>
> And We were testing 10GbE(Intel) NIC and your 40GbE NIC in our lab
> using ethtool with added some debug code.
I work for Solarflare, not Mellanox... and the patch adding 40G link
modes came from Parav Pandit at Emulex.
[...]
> It's firmware problem I thinks. But Just Information for you ;-)
Also, the 40G link mode flags were only just defined, so the driver
probably has yet to be updated.
Ben.
--
Ben Hutchings, Staff Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply
* Atheros Communications Inc. AR8121/AR8113/AR8114 Gigabit or Fast Ethernet (rev b0) 1.0.0.7 md5 corrupted using NFS
From: Marco Castiglione @ 2012-08-06 17:02 UTC (permalink / raw)
To: netdev
Hi,
I have a problem with :
Ethernet controller: Atheros Communications Inc. AR8121/AR8113/AR8114
Gigabit or Fast Ethernet (rev b0)
Subsystem: ASUSTeK Computer Inc. Device 831c
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr-
Stepping- SERR+ FastB2B- DisINTx+
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort-
<TAbort- <MAbort- >SERR- <PERR- INTx-
Latency: 0, Cache Line Size: 64 bytes
Interrupt: pin A routed to IRQ 46
Region 0: Memory at fbec0000 (64-bit, non-prefetchable) [size=256K]
Region 2: I/O ports at dc00 [size=128]
Capabilities: <access denied>
Kernel driver in use: ATL1E
The driver working fine except for nfs3 and nfs4
If I try to copy a file bigger of 400 mb the file get corrupted, If I try
with multiple files I have a kernel oops
I tried different system and service (Ftp,samba) and they working fine.
I also tried to set nfs to use udp, it kinda fix the problem but only in
part (I get 1 on 3 big file with md5 mismatch).
I notice in almost every kernel from 2.6 to now 3.2.15 the driver is the
same version
Filename: /lib/modules/3.2.0-2-amd64/
kernel/drivers/net/ethernet/atheros/atl1e/atl1e.ko
version: 1.0.0.7-NAPI
license: GPL
description: Atheros 1000M Ethernet Network Driver
author: Atheros Corporation, <xiong.huang@atheros.com>, Jie Yang <
jie.yang@atheros.com>
srcversion: 6E5949327D7FDF32D5F4A5B
alias: pci:v00001969d00001066sv*sd*bc*sc*i*
alias: pci:v00001969d00001026sv*sd*bc*sc*i*
depends:
intree: Y
vermagic: 3.2.0-2-amd64 SMP mod_unload modversions
parm: tx_desc_cnt:Transmit description count (array of int)
parm: rx_mem_size:memory size of rx buffer(KB) (array of int)
parm: media_type:MediaType Select (array of int)
parm: int_mod_timer:Interrupt Moderator Timer (array of int)
I found on ubuntu website the last version of the driver is 1.0.1.14 with
this change log :
1.0.1.14
1. don't define napi_struct in kcompat.h when GRO isn't supported.
1.0.1.13
1. fix AR8151-A hang when plug in LAN cable by cleaning bit1 of
REG(0x1114).
1.0.1.12
1. fix tpd, rfd, rrs, configure error for powerpc
1.0.1.11
1. only save power when WOL enable.
1.0.1.10
1. add l1d 2.0 support.
2. fix atl1c_phy_power_saving bug.
1.0.1.9
1. fix AR8131 reset error TX pending.
2. add AR8152 description.
1.0.1.8
1. add L2CB V2.0 support.
1.0.1.7
1. fix L0s/L1 bug.
2. update suspend procedure.
1.0.1.6
1. fix valn error.
2. use common task instead of reset task and link change task.
3. reset phy when link down.
1.0.1.5
1. change rx mod.
1.0.1.4
1. add l1d support.
1.0.1.3
1. fix TSO error.
1.0.1.2
1. fix compile error for kernel >= 2.6.30.
1.0.1.1
1. add L2cB support.
1.0.0.10
1. fix memory leak when power suspend.
1.0.0.9
1. do power saving when bootup with link lost.
2. remove ATL1C_INTR_CLEAR_ON_READ for power saving
1.0.0.8
1. remove dump_stack(), which was used for debugging.
So I found out the TSO is corrupt in the current version and that explain
with the udp setting do the trick.
Now I tried to compile the new version from
AR81Family-linux-v1.0.1.14.tar.gz but was made for the 2.6 so I can't
compile.( <http://goog_56610235>
http://media.cdn.ubuntu-de.org/forum/attachments/2666793/AR81Family-linux-
v1.0.1.14_10.10.tar.gz
)
The Atheros support and web page is gone after Qualcomm acquisition and the
patch I found on Ubuntu forum don't work either (
http://ubuntuforums.org/attachment.php?attachmentid=182141&d=1296221015)
I found out lots of people have the same issue and they using samba at the
moment.
My temp solution is use a usb/eth adapter with ax8112 chipset but it run at
100mbps.
SO my request is this : Is possible for somebody of the kernel team look
the code inside AR81Family-linux-v1.0.1.14.tar.gz and update the one in
the kernel 3.x?
Thank you for you time and consideration
^ permalink raw reply
* [PATCH] net:appletalk:ddp:fixed coding style issue relating to
From: Jeffrin Jose @ 2012-08-06 17:31 UTC (permalink / raw)
To: acme, davem; +Cc: netdev, linux-kernel, Jeffrin Jose
Fixed coding style issue relating to indentation
in net/appletalk/ddp.c found by checkpatch.pl tool.
Signed-off-by: Jeffrin Jose <ahiliation@yahoo.co.in>
---
net/appletalk/ddp.c | 26 +++++++++++++-------------
1 file changed, 13 insertions(+), 13 deletions(-)
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 8685296..4023fca 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1796,7 +1796,7 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
switch (cmd) {
/* Protocol layer */
- case TIOCOUTQ: {
+ case TIOCOUTQ: {
long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk);
if (amount < 0)
@@ -1804,7 +1804,7 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
rc = put_user(amount, (int __user *)argp);
break;
}
- case TIOCINQ: {
+ case TIOCINQ: {
/*
* These two are safe on a single CPU system as only
* user tasks fiddle here
@@ -1817,27 +1817,27 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
rc = put_user(amount, (int __user *)argp);
break;
}
- case SIOCGSTAMP:
+ case SIOCGSTAMP:
rc = sock_get_timestamp(sk, argp);
break;
- case SIOCGSTAMPNS:
+ case SIOCGSTAMPNS:
rc = sock_get_timestampns(sk, argp);
break;
/* Routing */
- case SIOCADDRT:
- case SIOCDELRT:
+ case SIOCADDRT:
+ case SIOCDELRT:
rc = -EPERM;
if (capable(CAP_NET_ADMIN))
rc = atrtr_ioctl(cmd, argp);
break;
/* Interface */
- case SIOCGIFADDR:
- case SIOCSIFADDR:
- case SIOCGIFBRDADDR:
- case SIOCATALKDIFADDR:
- case SIOCDIFADDR:
- case SIOCSARP: /* proxy AARP */
- case SIOCDARP: /* proxy AARP */
+ case SIOCGIFADDR:
+ case SIOCSIFADDR:
+ case SIOCGIFBRDADDR:
+ case SIOCATALKDIFADDR:
+ case SIOCDIFADDR:
+ case SIOCSARP: /* proxy AARP */
+ case SIOCDARP: /* proxy AARP */
rtnl_lock();
rc = atif_ioctl(cmd, argp);
rtnl_unlock();
--
1.7.10
^ permalink raw reply related
* Re: [PATCH net-next] igb: use build_skb()
From: Alexander Duyck @ 2012-08-06 17:35 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Jeff Kirsher, netdev
In-Reply-To: <1343922692.9299.231.camel@edumazet-glaptop>
On 08/02/2012 08:51 AM, Eric Dumazet wrote:
> From: Eric Dumazet <edumazet@google.com>
>
> By using netdev_alloc_frag() & build_skb() instead of legacy
> netdev_alloc_skb_ip_align() calls, we reduce number of cache misses in
> RX path and size of working set.
>
> For a given rx workload, number of 'inuse' sk_buff can be reduced to a
> very minimum, especially when packets are dropped by our stack.
>
> (Before this patch, default sk_buff allocation was 2048 sk_buffs in rx
> ring buffer)
>
> They are initialized right before being delivered to stack, so can stay
> hot in cpu caches.
>
> Ethernet header prefetching is more effective (old prefetch of skb->data
> paid a stall to access skb->data pointer)
>
> I have 15% performance increase in a RX stress test, removing SLUB slow
> path in the profiles.
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Cc: Alexander Duyck <alexander.h.duyck@intel.com>
> ---
> drivers/net/ethernet/intel/igb/igb.h | 8 ++
> drivers/net/ethernet/intel/igb/igb_ethtool.c | 14 ++--
> drivers/net/ethernet/intel/igb/igb_main.c | 56 ++++++++++-------
> 3 files changed, 49 insertions(+), 29 deletions(-)
>
[...]
> diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
> index b7c2d50..8b732c9 100644
> --- a/drivers/net/ethernet/intel/igb/igb_main.c
> +++ b/drivers/net/ethernet/intel/igb/igb_main.c
[...]
> @@ -6091,6 +6095,15 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget)
> next_rxd = IGB_RX_DESC(rx_ring, i);
> prefetch(next_rxd);
>
> + if (!skb) {
> + skb = build_skb(data, IGB_FRAGSZ);
> + if (unlikely(!skb)) {
> + rx_ring->rx_stats.alloc_failed++;
> + buffer_info->data = data;
> + goto next_desc;
> + }
> + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
> + }
> /*
> * This memory barrier is needed to keep us from reading
> * any other fields out of the rx_desc until we know the
This logic is broken. If an allocation failure occurs it would leave
the data in the ring and could possibly give you a corrupted packet.
I was planning to move igb over to an ixgbe style receive path at some
point anyway. Since it seems like this is now a higher priority I
figured I would try to get the patches for it implemented in the next
week or so. Would there be any issue with us rejecting this patch and
instead switching igb over to the ixgbe style path?
Thanks,
Alex
^ 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