From: Mel Gorman <mgorman@suse.de>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Linux-MM <linux-mm@kvack.org>,
Linux-Netdev <netdev@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
David Miller <davem@davemloft.net>, Neil Brown <neilb@suse.de>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Mike Christie <michaelc@cs.wisc.edu>,
Eric B Munson <emunson@mgebm.net>, Mel Gorman <mgorman@suse.de>
Subject: [PATCH 12/16] netvm: Set PF_MEMALLOC as appropriate during SKB processing
Date: Mon, 16 Apr 2012 13:16:59 +0100 [thread overview]
Message-ID: <1334578624-23257-13-git-send-email-mgorman@suse.de> (raw)
In-Reply-To: <1334578624-23257-1-git-send-email-mgorman@suse.de>
In order to make sure pfmemalloc packets receive all memory
needed to proceed, ensure processing of pfmemalloc SKBs happens
under PF_MEMALLOC. This is limited to a subset of protocols that
are expected to be used for writing to swap. Taps are not allowed to
use PF_MEMALLOC as these are expected to communicate with userspace
processes which could be paged out.
[a.p.zijlstra@chello.nl: Ideas taken from various patches]
[jslaby@suse.cz: Lock imbalance fix]
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/net/sock.h | 5 +++++
net/core/dev.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++------
net/core/sock.c | 16 ++++++++++++++++
3 files changed, 67 insertions(+), 6 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index a936614..de6ebda 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -728,8 +728,13 @@ 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_pfmemalloc(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 c25d453..ca7f264 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3153,6 +3153,23 @@ void netdev_rx_handler_unregister(struct net_device *dev)
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
+/*
+ * Limit the use of PFMEMALLOC reserves to those protocols that implement
+ * the special handling of PFMEMALLOC skbs.
+ */
+static bool skb_pfmemalloc_protocol(struct sk_buff *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):
+ return true;
+ default:
+ return false;
+ }
+}
+
static int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
@@ -3162,14 +3179,27 @@ static int __netif_receive_skb(struct sk_buff *skb)
bool deliver_exact = false;
int ret = NET_RX_DROP;
__be16 type;
+ unsigned long pflags = current->flags;
net_timestamp_check(!netdev_tstamp_prequeue, skb);
trace_netif_receive_skb(skb);
+ /*
+ * PFMEMALLOC skbs are special, they should
+ * - be delivered to SOCK_MEMALLOC sockets only
+ * - stay away from userspace
+ * - have bounded memory usage
+ *
+ * Use PF_MEMALLOC as this saves us from propagating the allocation
+ * context down to all allocation sites.
+ */
+ if (skb_pfmemalloc(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;
@@ -3190,7 +3220,7 @@ another_round:
if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
skb = vlan_untag(skb);
if (unlikely(!skb))
- goto out;
+ goto unlock;
}
#ifdef CONFIG_NET_CLS_ACT
@@ -3200,6 +3230,9 @@ another_round:
}
#endif
+ if (skb_pfmemalloc(skb))
+ goto skip_taps;
+
list_for_each_entry_rcu(ptype, &ptype_all, list) {
if (!ptype->dev || ptype->dev == skb->dev) {
if (pt_prev)
@@ -3208,13 +3241,17 @@ another_round:
}
}
+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_pfmemalloc(skb) && !skb_pfmemalloc_protocol(skb))
+ goto drop;
+
rx_handler = rcu_dereference(skb->dev->rx_handler);
if (vlan_tx_tag_present(skb)) {
if (pt_prev) {
@@ -3224,7 +3261,7 @@ ncls:
if (vlan_do_receive(&skb, !rx_handler))
goto another_round;
else if (unlikely(!skb))
- goto out;
+ goto unlock;
}
if (rx_handler) {
@@ -3234,7 +3271,7 @@ ncls:
}
switch (rx_handler(&skb)) {
case RX_HANDLER_CONSUMED:
- goto out;
+ goto unlock;
case RX_HANDLER_ANOTHER:
goto another_round;
case RX_HANDLER_EXACT:
@@ -3264,6 +3301,7 @@ 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
@@ -3272,8 +3310,10 @@ ncls:
ret = NET_RX_DROP;
}
-out:
+unlock:
rcu_read_unlock();
+out:
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
return ret;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index cd2ad2b..9ad1ed9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -292,6 +292,22 @@ void sk_clear_memalloc(struct sock *sk)
}
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(!sock_flag(sk, SOCK_MEMALLOC));
+
+ 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);
+
#if defined(CONFIG_CGROUPS)
#if !defined(CONFIG_NET_CLS_CGROUP)
int net_cls_subsys_id = -1;
--
1.7.9.2
next prev parent reply other threads:[~2012-04-16 12:23 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-04-16 12:16 [PATCH 00/16] Swap-over-NBD without deadlocking V9 Mel Gorman
2012-04-16 12:16 ` [PATCH 01/16] mm: Serialize access to min_free_kbytes Mel Gorman
2012-04-23 23:50 ` David Rientjes
2012-04-16 12:16 ` [PATCH 02/16] mm: sl[au]b: Add knowledge of PFMEMALLOC reserve pages Mel Gorman
2012-04-23 23:51 ` David Rientjes
2012-04-25 15:05 ` Mel Gorman
2012-04-16 12:16 ` [PATCH 03/16] mm: slub: Optimise the SLUB fast path to avoid pfmemalloc checks Mel Gorman
2012-04-16 12:16 ` [PATCH 04/16] mm: Introduce __GFP_MEMALLOC to allow access to emergency reserves Mel Gorman
2012-04-16 12:16 ` [PATCH 05/16] mm: allow PF_MEMALLOC from softirq context Mel Gorman
2012-05-01 22:08 ` Andrew Morton
2012-05-02 16:24 ` Mel Gorman
2012-04-16 12:16 ` [PATCH 06/16] mm: Ignore mempolicies when using ALLOC_NO_WATERMARK Mel Gorman
2012-04-16 12:16 ` [PATCH 07/16] net: Introduce sk_allocation() to allow addition of GFP flags depending on the individual socket Mel Gorman
2012-04-16 12:16 ` [PATCH 08/16] netvm: Allow the use of __GFP_MEMALLOC by specific sockets Mel Gorman
2012-04-16 12:16 ` [PATCH 09/16] netvm: Allow skb allocation to use PFMEMALLOC reserves Mel Gorman
2012-04-16 12:16 ` [PATCH 10/16] netvm: Propagate page->pfmemalloc to skb Mel Gorman
2012-04-16 12:16 ` [PATCH 11/16] netvm: Propagate page->pfmemalloc from netdev_alloc_page " Mel Gorman
2012-04-16 12:16 ` Mel Gorman [this message]
2012-04-16 12:17 ` [PATCH 13/16] mm: Micro-optimise slab to avoid a function call Mel Gorman
2012-04-16 12:17 ` [PATCH 14/16] nbd: Set SOCK_MEMALLOC for access to PFMEMALLOC reserves Mel Gorman
2012-04-16 12:17 ` [PATCH 15/16] mm: Throttle direct reclaimers if PF_MEMALLOC reserves are low and swap is backed by network storage Mel Gorman
2012-05-01 22:24 ` Andrew Morton
2012-05-02 16:24 ` Mel Gorman
2012-04-16 12:17 ` [PATCH 16/16] mm: Account for the number of times direct reclaimers get throttled Mel Gorman
2012-05-01 22:28 ` [PATCH 00/16] Swap-over-NBD without deadlocking V9 Andrew Morton
2012-05-03 15:00 ` Mel Gorman
2012-05-03 17:06 ` David Miller
2012-05-04 10:16 ` Mel Gorman
2012-06-22 14:30 [PATCH 00/17] Swap-over-NBD without deadlocking V13 Mel Gorman
2012-06-22 14:30 ` [PATCH 12/16] netvm: Set PF_MEMALLOC as appropriate during SKB processing Mel Gorman
2012-06-29 13:32 [PATCH 00/16] Swap-over-NBD without deadlocking V14 Mel Gorman
2012-06-29 13:32 ` [PATCH 12/16] netvm: Set PF_MEMALLOC as appropriate during SKB processing Mel Gorman
2012-07-12 6:40 [PATCH 00/16] Swap-over-NBD without deadlocking V15 Mel Gorman
2012-07-12 6:40 ` [PATCH 12/16] netvm: Set PF_MEMALLOC as appropriate during SKB processing Mel Gorman
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=1334578624-23257-13-git-send-email-mgorman@suse.de \
--to=mgorman@suse.de \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=davem@davemloft.net \
--cc=emunson@mgebm.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=michaelc@cs.wisc.edu \
--cc=neilb@suse.de \
--cc=netdev@vger.kernel.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).