You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
184 lines
4.6 KiB
184 lines
4.6 KiB
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
|
|
Subject: [PATCH 22/31] netvm: skb processing
|
|
Patch-mainline: Not yet
|
|
|
|
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: Jiri Slaby <jslaby@suse.cz> [lock imbalance fix]
|
|
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
|
|
Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de>
|
|
---
|
|
include/net/sock.h | 5 ++++
|
|
net/core/dev.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++----
|
|
net/core/sock.c | 16 +++++++++++++++
|
|
3 files changed, 72 insertions(+), 4 deletions(-)
|
|
|
|
--- a/include/net/sock.h
|
|
+++ b/include/net/sock.h
|
|
@@ -682,8 +682,13 @@ static inline __must_check int sk_add_ba
|
|
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);
|
|
}
|
|
|
|
--- a/net/core/dev.c
|
|
+++ b/net/core/dev.c
|
|
@@ -2814,6 +2814,30 @@ int __skb_bond_should_drop(struct sk_buf
|
|
}
|
|
EXPORT_SYMBOL(__skb_bond_should_drop);
|
|
|
|
+/*
|
|
+ * 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;
|
|
+}
|
|
+
|
|
static int __netif_receive_skb(struct sk_buff *skb)
|
|
{
|
|
struct packet_type *ptype, *pt_prev;
|
|
@@ -2824,6 +2848,7 @@ static int __netif_receive_skb(struct sk
|
|
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);
|
|
@@ -2831,9 +2856,21 @@ static int __netif_receive_skb(struct sk
|
|
|
|
trace_netif_receive_skb(skb);
|
|
|
|
+ /* 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;
|
|
@@ -2875,6 +2912,9 @@ static int __netif_receive_skb(struct sk
|
|
}
|
|
#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) {
|
|
@@ -2884,13 +2924,17 @@ static int __netif_receive_skb(struct sk
|
|
}
|
|
}
|
|
|
|
+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) {
|
|
@@ -2900,7 +2944,7 @@ ncls:
|
|
}
|
|
skb = rx_handler(skb);
|
|
if (!skb)
|
|
- goto out;
|
|
+ goto unlock;
|
|
}
|
|
|
|
if (vlan_tx_tag_present(skb)) {
|
|
@@ -2930,6 +2974,7 @@ ncls:
|
|
if (pt_prev) {
|
|
ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
|
|
} else {
|
|
+drop:
|
|
atomic_long_inc(&skb->dev->rx_dropped);
|
|
kfree_skb(skb);
|
|
/* Jamal, now you will not able to escape explaining
|
|
@@ -2937,8 +2982,10 @@ ncls:
|
|
ret = NET_RX_DROP;
|
|
}
|
|
|
|
-out:
|
|
+unlock:
|
|
rcu_read_unlock();
|
|
+out:
|
|
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
|
|
return ret;
|
|
}
|
|
|
|
--- 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)
|