LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org, netdev@vger.kernel.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Trond Myklebust <trond.myklebust@fys.uio.no>,
	Thomas Graf <tgraf@suug.ch>, David Miller <davem@davemloft.net>
Subject: [PATCH 19/29] netvm: skb processing
Date: Wed, 21 Feb 2007 15:43:23 +0100	[thread overview]
Message-ID: <20070221144843.433257000@taijtu.programming.kicks-ass.net> (raw)
In-Reply-To: <20070221144304.512721000@taijtu.programming.kicks-ass.net>

[-- Attachment #1: netvm.patch --]
[-- Type: text/plain, Size: 4730 bytes --]

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@chello.nl>
---
 include/net/sock.h |    4 ++++
 net/core/dev.c     |   42 +++++++++++++++++++++++++++++++++++++-----
 net/core/sock.c    |   19 +++++++++++++++++++
 3 files changed, 60 insertions(+), 5 deletions(-)

Index: linux-2.6-git/net/core/dev.c
===================================================================
--- linux-2.6-git.orig/net/core/dev.c	2007-02-14 12:16:03.000000000 +0100
+++ linux-2.6-git/net/core/dev.c	2007-02-14 12:28:33.000000000 +0100
@@ -1767,10 +1767,23 @@ int netif_receive_skb(struct sk_buff *sk
 	struct net_device *orig_dev;
 	int ret = NET_RX_DROP;
 	__be16 type;
+	unsigned long pflags = current->flags;
+
+	/* Emergency skb are special, they should
+	 *  - be delivered to SOCK_VMIO 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 (skb->dev->poll && netpoll_rx(skb))
-		return NET_RX_DROP;
+		goto out;
 
 	if (!skb->tstamp.off_sec)
 		net_timestamp(skb);
@@ -1781,7 +1794,7 @@ int netif_receive_skb(struct sk_buff *sk
 	orig_dev = skb_bond(skb);
 
 	if (!orig_dev)
-		return NET_RX_DROP;
+		goto out;
 
 	__get_cpu_var(netdev_rx_stat).total++;
 
@@ -1799,6 +1812,9 @@ int netif_receive_skb(struct sk_buff *sk
 	}
 #endif
 
+	if (skb_emergency(skb))
+		goto skip_taps;
+
 	list_for_each_entry_rcu(ptype, &ptype_all, list) {
 		if (!ptype->dev || ptype->dev == skb->dev) {
 			if (pt_prev)
@@ -1807,6 +1823,7 @@ int netif_receive_skb(struct sk_buff *sk
 		}
 	}
 
+skip_taps:
 #ifdef CONFIG_NET_CLS_ACT
 	if (pt_prev) {
 		ret = deliver_skb(skb, pt_prev, orig_dev);
@@ -1819,15 +1836,27 @@ int netif_receive_skb(struct sk_buff *sk
 
 	if (ret == TC_ACT_SHOT || (ret == TC_ACT_STOLEN)) {
 		kfree_skb(skb);
-		goto out;
+		goto unlock;
 	}
 
 	skb->tc_verd = 0;
 ncls:
 #endif
 
+	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:
+				goto drop;
+		}
+
 	if (handle_bridge(&skb, &pt_prev, &ret, orig_dev))
-		goto out;
+		goto unlock;
 
 	type = skb->protocol;
 	list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type)&15], list) {
@@ -1842,6 +1871,7 @@ 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. :-)
@@ -1849,8 +1879,10 @@ ncls:
 		ret = NET_RX_DROP;
 	}
 
-out:
+unlock:
 	rcu_read_unlock();
+out:
+	current->flags = pflags;
 	return ret;
 }
 
Index: linux-2.6-git/include/net/sock.h
===================================================================
--- linux-2.6-git.orig/include/net/sock.h	2007-02-14 12:32:03.000000000 +0100
+++ linux-2.6-git/include/net/sock.h	2007-02-14 12:32:37.000000000 +0100
@@ -510,10 +510,14 @@ static inline void sk_add_backlog(struct
 	skb->next = NULL;
 }
 
+#ifndef CONFIG_NETVM
 static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
 	return sk->sk_backlog_rcv(sk, skb);
 }
+#else
+extern int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+#endif
 
 #define sk_wait_event(__sk, __timeo, __condition)		\
 ({	int rc;							\
Index: linux-2.6-git/net/core/sock.c
===================================================================
--- linux-2.6-git.orig/net/core/sock.c	2007-02-14 12:32:07.000000000 +0100
+++ linux-2.6-git/net/core/sock.c	2007-02-14 12:37:11.000000000 +0100
@@ -332,6 +332,25 @@ int sk_clear_vmio(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sk_clear_vmio);
 
+#ifdef CONFIG_NETVM
+int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+{
+	if (skb_emergency(skb)) {
+		int ret;
+		unsigned long pflags = current->flags;
+	       	/* these should have been dropped before queueing */
+		BUG_ON(!sk_has_vmio(sk));
+		current->flags |= PF_MEMALLOC;
+		ret = sk->sk_backlog_rcv(sk, skb);
+		current->flags = pflags;
+		return ret;
+	}
+
+	return sk->sk_backlog_rcv(sk, skb);
+}
+EXPORT_SYMBOL(sk_backlog_rcv);
+#endif
+
 static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
 {
 	struct timeval tv;

-- 


  parent reply	other threads:[~2007-02-21 15:08 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-02-21 14:43 [PATCH 00/29] swap over networked storage -v11 Peter Zijlstra
2007-02-21 14:43 ` [PATCH 01/29] mm: page allocation rank Peter Zijlstra
2007-02-21 14:43 ` [PATCH 02/29] mm: slab allocation fairness Peter Zijlstra
2007-02-21 15:33   ` Pekka Enberg
2007-02-21 14:43 ` [PATCH 03/29] mm: allow PF_MEMALLOC from softirq context Peter Zijlstra
2007-02-21 15:53   ` Arjan van de Ven
2007-02-22  9:16     ` Peter Zijlstra
2007-02-22  9:48       ` Arjan van de Ven
2007-02-21 14:43 ` [PATCH 04/29] mm: serialize access to min_free_kbytes Peter Zijlstra
2007-02-21 14:43 ` [PATCH 05/29] mm: emergency pool Peter Zijlstra
2007-02-21 14:43 ` [PATCH 06/29] mm: __GFP_EMERGENCY Peter Zijlstra
2007-02-21 14:43 ` [PATCH 07/29] mm: allow mempool to fall back to memalloc reserves Peter Zijlstra
2007-02-21 14:43 ` [PATCH 08/29] mm: kmem_cache_objs_to_pages() Peter Zijlstra
2007-02-21 15:47   ` Pekka Enberg
2007-02-22  9:28     ` Peter Zijlstra
2007-02-22  9:45       ` Pekka Enberg
2007-02-22  9:49         ` Pekka Enberg
2007-02-21 14:43 ` [PATCH 09/29] selinux: tag avc cache alloc as non-critical Peter Zijlstra
2007-02-21 15:22   ` James Morris
2007-02-21 14:43 ` [PATCH 10/29] net: wrap sk->sk_backlog_rcv() Peter Zijlstra
2007-02-21 14:43 ` [PATCH 11/29] net: packet split receive api Peter Zijlstra
2007-02-21 14:43 ` [PATCH 12/29] net: remove alloc_skb_from_cache Peter Zijlstra
2007-02-21 14:43 ` [PATCH 13/29] netvm: link network to vm layer Peter Zijlstra
2007-02-21 14:43 ` [PATCH 14/29] netvm: INET reserves Peter Zijlstra
2007-02-21 14:43 ` [PATCH 15/29] netvm: hook skb allocation to reserves Peter Zijlstra
2007-02-21 14:43 ` [PATCH 16/29] netvm: filter emergency skbs Peter Zijlstra
2007-02-21 14:43 ` [PATCH 17/29] netvm: prevent a TCP specific deadlock Peter Zijlstra
2007-02-21 14:43 ` [PATCH 18/29] netfilter: notify about NF_QUEUE vs emergency skbs Peter Zijlstra
2007-02-24 15:27   ` Patrick McHardy
2007-02-24 15:46     ` Peter Zijlstra
2007-02-24 16:17       ` Patrick McHardy
2007-02-24 16:18         ` Peter Zijlstra
2007-02-24 16:40           ` Patrick McHardy
2007-02-24 16:55             ` Peter Zijlstra
2007-02-21 14:43 ` Peter Zijlstra [this message]
2007-02-21 14:43 ` [PATCH 20/29] uml: rename arch/um remove_mapping() Peter Zijlstra
2007-02-21 14:43 ` [PATCH 21/29] mm: prepare swap entry methods for use in page methods Peter Zijlstra
2007-02-21 14:43 ` [PATCH 22/29] mm: add support for non block device backed swap files Peter Zijlstra
2007-02-21 14:43 ` [PATCH 23/29] mm: methods for teaching filesystems about PG_swapcache pages Peter Zijlstra
2007-02-21 14:43 ` [PATCH 24/29] nfs: remove mempools Peter Zijlstra
2007-02-21 14:43 ` [PATCH 25/29] nfs: only use stable storage for swap Peter Zijlstra
2007-02-21 14:43 ` [PATCH 26/29] nfs: teach the NFS client how to treat PG_swapcache pages Peter Zijlstra
2007-02-21 14:43 ` [PATCH 27/29] nfs: disable data cache revalidation for swapfiles Peter Zijlstra
2007-02-21 14:43 ` [PATCH 28/29] nfs: enable swap on NFS Peter Zijlstra
2007-02-21 14:43 ` [PATCH 29/29] balance_dirty_pages() vs throttle_vm_writeout() deadlock Peter Zijlstra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20070221144843.433257000@taijtu.programming.kicks-ass.net \
    --to=a.p.zijlstra@chello.nl \
    --cc=davem@davemloft.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=netdev@vger.kernel.org \
    --cc=tgraf@suug.ch \
    --cc=trond.myklebust@fys.uio.no \
    --subject='Re: [PATCH 19/29] netvm: skb processing' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).