From: Xiaotian Feng on
From 15437174f171e197ecdfa5fe71ae89334bb58fd2 Mon Sep 17 00:00:00 2001
From: Xiaotian Feng <dfeng(a)redhat.com>
Date: Tue, 13 Jul 2010 13:07:28 +0800
Subject: [PATCH 21/30] netvm: skb processing

In order to make sure emergency packets receive all memory needed to proceed
ensure processing of emergency SKBs happens under PF_MEMALLOC.

Use the (new) sk_backlog_rcv() wrapper to ensure this for backlog processing.

Skip taps, since those are user-space again.

Signed-off-by: Peter Zijlstra <a.p.zijlstra(a)chello.nl>
Signed-off-by: Suresh Jayaraman <sjayaraman(a)suse.de>
Signed-off-by: Xiaotian Feng <dfeng(a)redhat.com>
---
include/net/sock.h | 5 ++++
net/core/dev.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++++---
net/core/sock.c | 16 +++++++++++++++
3 files changed, 72 insertions(+), 4 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index ac87f6f..aadf15c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -680,8 +680,13 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
return 0;
}

+extern int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+
static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
+ if (skb_emergency(skb))
+ return __sk_backlog_rcv(sk, skb);
+
return sk->sk_backlog_rcv(sk, skb);
}

diff --git a/net/core/dev.c b/net/core/dev.c
index e85cc5f..7169b9b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2801,6 +2801,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
struct net_device *orig_or_bond;
int ret = NET_RX_DROP;
__be16 type;
+ unsigned long pflags = current->flags;

if (!netdev_tstamp_prequeue)
net_timestamp_check(skb);
@@ -2808,9 +2809,21 @@ static int __netif_receive_skb(struct sk_buff *skb)
if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb))
return NET_RX_SUCCESS;

+ /* Emergency skb are special, they should
+ * - be delivered to SOCK_MEMALLOC sockets only
+ * - stay away from userspace
+ * - have bounded memory usage
+ *
+ * Use PF_MEMALLOC as a poor mans memory pool - the grouping kind.
+ * This saves us from propagating the allocation context down to all
+ * allocation sites.
+ */
+ if (skb_emergency(skb))
+ current->flags |= PF_MEMALLOC;
+
/* if we've gotten here through NAPI, check netpoll */
if (netpoll_receive_skb(skb))
- return NET_RX_DROP;
+ goto out;

if (!skb->skb_iif)
skb->skb_iif = skb->dev->ifindex;
@@ -2852,6 +2865,9 @@ static int __netif_receive_skb(struct sk_buff *skb)
}
#endif

+ if (skb_emergency(skb))
+ goto skip_taps;
+
list_for_each_entry_rcu(ptype, &ptype_all, list) {
if (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
ptype->dev == orig_dev) {
@@ -2861,13 +2877,17 @@ static int __netif_receive_skb(struct sk_buff *skb)
}
}

+skip_taps:
#ifdef CONFIG_NET_CLS_ACT
skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
if (!skb)
- goto out;
+ goto unlock;
ncls:
#endif

+ if (!skb_emergency_protocol(skb))
+ goto drop;
+
/* Handle special case of bridge or macvlan */
rx_handler = rcu_dereference(skb->dev->rx_handler);
if (rx_handler) {
@@ -2877,7 +2897,7 @@ ncls:
}
skb = rx_handler(skb);
if (!skb)
- goto out;
+ goto unlock;
}

/*
@@ -2907,6 +2927,7 @@ ncls:
if (pt_prev) {
ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
} else {
+drop:
kfree_skb(skb);
/* Jamal, now you will not able to escape explaining
* me how you were going to use this. :-)
@@ -2914,11 +2935,37 @@ ncls:
ret = NET_RX_DROP;
}

-out:
+unlock:
rcu_read_unlock();
+out:
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
return ret;
}

+/*
+ * Filter the protocols for which the reserves are adequate.
+ *
+ * Before adding a protocol make sure that it is either covered by the existing
+ * reserves, or add reserves covering the memory need of the new protocol's
+ * packet processing.
+ */
+static int skb_emergency_protocol(struct sk_buff *skb)
+{
+ if (skb_emergency(skb))
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_ARP):
+ case __constant_htons(ETH_P_IP):
+ case __constant_htons(ETH_P_IPV6):
+ case __constant_htons(ETH_P_8021Q):
+ break;
+
+ default:
+ return 0;
+ }
+
+ return 1;
+}
+
/**
* netif_receive_skb - process receive buffer from network
* @skb: buffer to process
diff --git a/net/core/sock.c b/net/core/sock.c
index f24560c..dfc2dfe 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -322,6 +322,22 @@ int sk_clear_memalloc(struct sock *sk)
return set;
}
EXPORT_SYMBOL_GPL(sk_clear_memalloc);
+
+int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ int ret;
+ unsigned long pflags = current->flags;
+
+ /* these should have been dropped before queueing */
+ BUG_ON(!sk_has_memalloc(sk));
+
+ current->flags |= PF_MEMALLOC;
+ ret = sk->sk_backlog_rcv(sk, skb);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
+
+ return ret;
+}
+EXPORT_SYMBOL(__sk_backlog_rcv);
#endif

static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
--
1.7.1.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/