From 3d3be4333fdf6faa080947b331a6a19bce1a4f57 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Wed, 1 Sep 2010 00:50:51 +0000
Subject: gro: fix different skb headrooms
Packets entering GRO might have different headrooms, even for a given
flow (because of implementation details in drivers, like copybreak).
We cant force drivers to deliver packets with a fixed headroom.
1) fix skb_segment()
skb_segment() makes the false assumption headrooms of fragments are same
than the head. When CHECKSUM_PARTIAL is used, this can give csum_start
errors, and crash later in skb_copy_and_csum_dev()
2) allocate a minimal skb for head of frag_list
skb_gro_receive() uses netdev_alloc_skb(headroom + skb_gro_offset(p)) to
allocate a fresh skb. This adds NET_SKB_PAD to a padding already
provided by netdevice, depending on various things, like copybreak.
Use alloc_skb() to allocate an exact padding, to reduce cache line
needs:
NET_SKB_PAD + NET_IP_ALIGN
bugzilla : https://bugzilla.kernel.org/show_bug.cgi?id=16626
Many thanks to Plamen Petrov, testing many debugging patches !
With help of Jarek Poplawski.
Reported-by: Plamen Petrov <pvp-lsts@fs.uni-ruse.bg>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/skbuff.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
(limited to 'net/core')
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3a2513f0d0c..26396ff67cf 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2573,6 +2573,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features)
__copy_skb_header(nskb, skb);
nskb->mac_len = skb->mac_len;
+ /* nskb and skb might have different headroom */
+ if (nskb->ip_summed == CHECKSUM_PARTIAL)
+ nskb->csum_start += skb_headroom(nskb) - headroom;
+
skb_reset_mac_header(nskb);
skb_set_network_header(nskb, skb->mac_len);
nskb->transport_header = (nskb->network_header +
@@ -2702,8 +2706,8 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
} else if (skb_gro_len(p) != pinfo->gso_size)
return -E2BIG;
- headroom = skb_headroom(p);
- nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p));
+ headroom = NET_SKB_PAD + NET_IP_ALIGN;
+ nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC);
if (unlikely(!nskb))
return -ENOMEM;
--
cgit v1.2.3-18-g5258
From 0b5d404e349c0236b11466c0a4785520c0be6982 Mon Sep 17 00:00:00 2001
From: Jarek Poplawski <jarkao2@gmail.com>
Date: Thu, 2 Sep 2010 13:22:11 -0700
Subject: pkt_sched: Fix lockdep warning on est_tree_lock in gen_estimator
This patch fixes a lockdep warning:
[ 516.287584] =========================================================
[ 516.288386] [ INFO: possible irq lock inversion dependency detected ]
[ 516.288386] 2.6.35b #7
[ 516.288386] ---------------------------------------------------------
[ 516.288386] swapper/0 just changed the state of lock:
[ 516.288386] (&qdisc_tx_lock){+.-...}, at: [<c12eacda>] est_timer+0x62/0x1b4
[ 516.288386] but this lock took another, SOFTIRQ-unsafe lock in the past:
[ 516.288386] (est_tree_lock){+.+...}
[ 516.288386]
[ 516.288386] and interrupts could create inverse lock ordering between them.
...
So, est_tree_lock needs BH protection because it's taken by
qdisc_tx_lock, which is used both in BH and process contexts.
(Full warning with this patch at netdev, 02 Sep 2010.)
Fixes commit: ae638c47dc040b8def16d05dc6acdd527628f231
("pkt_sched: gen_estimator: add a new lock")
Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/gen_estimator.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
(limited to 'net/core')
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 9fbe7f7429b..6743146e4d6 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -232,7 +232,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
est->last_packets = bstats->packets;
est->avpps = rate_est->pps<<10;
- spin_lock(&est_tree_lock);
+ spin_lock_bh(&est_tree_lock);
if (!elist[idx].timer.function) {
INIT_LIST_HEAD(&elist[idx].list);
setup_timer(&elist[idx].timer, est_timer, idx);
@@ -243,7 +243,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
list_add_rcu(&est->list, &elist[idx].list);
gen_add_node(est);
- spin_unlock(&est_tree_lock);
+ spin_unlock_bh(&est_tree_lock);
return 0;
}
@@ -270,7 +270,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
{
struct gen_estimator *e;
- spin_lock(&est_tree_lock);
+ spin_lock_bh(&est_tree_lock);
while ((e = gen_find_node(bstats, rate_est))) {
rb_erase(&e->node, &est_root);
@@ -281,7 +281,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
list_del_rcu(&e->list);
call_rcu(&e->e_rcu, __gen_kill_estimator);
}
- spin_unlock(&est_tree_lock);
+ spin_unlock_bh(&est_tree_lock);
}
EXPORT_SYMBOL(gen_kill_estimator);
@@ -320,9 +320,9 @@ bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
ASSERT_RTNL();
- spin_lock(&est_tree_lock);
+ spin_lock_bh(&est_tree_lock);
res = gen_find_node(bstats, rate_est) != NULL;
- spin_unlock(&est_tree_lock);
+ spin_unlock_bh(&est_tree_lock);
return res;
}
--
cgit v1.2.3-18-g5258
From deabc772f39405054a438d711f408d2d94d26d96 Mon Sep 17 00:00:00 2001
From: Helmut Schaa <helmut.schaa@googlemail.com>
Date: Fri, 3 Sep 2010 02:39:56 +0000
Subject: net: fix tx queue selection for bridged devices implementing
select_queue
When a net device is implementing the select_queue callback and is part of
a bridge, frames coming from the bridge already have a tx queue associated
to the socket (introduced in commit a4ee3ce3293dc931fab19beb472a8bde1295aebe,
"net: Use sk_tx_queue_mapping for connected sockets"). The call to
sk_tx_queue_get will then return the tx queue used by the bridge instead
of calling the select_queue callback.
In case of mac80211 this broke QoS which is implemented by using the
select_queue callback. Furthermore it introduced problems with rt2x00
because frames with the same TID and RA sometimes appeared on different
tx queues which the hw cannot handle correctly.
Fix this by always calling select_queue first if it is available and only
afterwards use the socket tx queue mapping.
Signed-off-by: Helmut Schaa <helmut.schaa@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/dev.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
(limited to 'net/core')
diff --git a/net/core/dev.c b/net/core/dev.c
index 3721fbb9a83..b9b22a3c4c8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2058,16 +2058,16 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev,
struct sk_buff *skb)
{
int queue_index;
- struct sock *sk = skb->sk;
+ const struct net_device_ops *ops = dev->netdev_ops;
- queue_index = sk_tx_queue_get(sk);
- if (queue_index < 0) {
- const struct net_device_ops *ops = dev->netdev_ops;
+ if (ops->ndo_select_queue) {
+ queue_index = ops->ndo_select_queue(dev, skb);
+ queue_index = dev_cap_txqueue(dev, queue_index);
+ } else {
+ struct sock *sk = skb->sk;
+ queue_index = sk_tx_queue_get(sk);
+ if (queue_index < 0) {
- if (ops->ndo_select_queue) {
- queue_index = ops->ndo_select_queue(dev, skb);
- queue_index = dev_cap_txqueue(dev, queue_index);
- } else {
queue_index = 0;
if (dev->real_num_tx_queues > 1)
queue_index = skb_tx_hash(dev, skb);
--
cgit v1.2.3-18-g5258
From 64289c8e6851bca0e589e064c9a5c9fbd6ae5dd4 Mon Sep 17 00:00:00 2001
From: Jarek Poplawski <jarkao2@gmail.com>
Date: Sat, 4 Sep 2010 10:34:29 +0000
Subject: gro: Re-fix different skb headrooms
The patch: "gro: fix different skb headrooms" in its part:
"2) allocate a minimal skb for head of frag_list" is buggy. The copied
skb has p->data set at the ip header at the moment, and skb_gro_offset
is the length of ip + tcp headers. So, after the change the length of
mac header is skipped. Later skb_set_mac_header() sets it into the
NET_SKB_PAD area (if it's long enough) and ip header is misaligned at
NET_SKB_PAD + NET_IP_ALIGN offset. There is no reason to assume the
original skb was wrongly allocated, so let's copy it as it was.
bugzilla : https://bugzilla.kernel.org/show_bug.cgi?id=16626
fixes commit: 3d3be4333fdf6faa080947b331a6a19bce1a4f57
Reported-by: Plamen Petrov <pvp-lsts@fs.uni-ruse.bg>
Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
CC: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Tested-by: Plamen Petrov <pvp-lsts@fs.uni-ruse.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/skbuff.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'net/core')
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 26396ff67cf..c83b421341c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2706,7 +2706,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
} else if (skb_gro_len(p) != pinfo->gso_size)
return -E2BIG;
- headroom = NET_SKB_PAD + NET_IP_ALIGN;
+ headroom = skb_headroom(p);
nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC);
if (unlikely(!nskb))
return -ENOMEM;
--
cgit v1.2.3-18-g5258