public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation•org>
To: linux-kernel@vger•kernel.org, netdev@vger•kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation•org>,
	stable@vger•kernel.org, Eric Dumazet <edumazet@google•com>,
	"David S. Miller" <davem@davemloft•net>
Subject: [PATCH 4.9 54/71] inet: frags: break the 2GB limit for frags storage
Date: Tue, 16 Oct 2018 19:09:51 +0200	[thread overview]
Message-ID: <20181016170542.081277817@linuxfoundation.org> (raw)
In-Reply-To: <20181016170539.315587743@linuxfoundation.org>

4.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <edumazet@google•com>

Some users are willing to provision huge amounts of memory to be able
to perform reassembly reasonnably well under pressure.

Current memory tracking is using one atomic_t and integers.

Switch to atomic_long_t so that 64bit arches can use more than 2GB,
without any cost for 32bit arches.

Note that this patch avoids an overflow error, if high_thresh was set
to ~2GB, since this test in inet_frag_alloc() was never true :

if (... || frag_mem_limit(nf) > nf->high_thresh)

Tested:

$ echo 16000000000 >/proc/sys/net/ipv4/ipfrag_high_thresh

<frag DDOS>

$ grep FRAG /proc/net/sockstat
FRAG: inuse 14705885 memory 16000002880

$ nstat -n ; sleep 1 ; nstat | grep Reas
IpReasmReqds                    3317150            0.0
IpReasmFails                    3317112            0.0

Signed-off-by: Eric Dumazet <edumazet@google•com>
Signed-off-by: David S. Miller <davem@davemloft•net>
(cherry picked from commit 3e67f106f619dcfaf6f4e2039599bdb69848c714)
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation•org>
---
 Documentation/networking/ip-sysctl.txt  |    4 ++--
 include/net/inet_frag.h                 |   20 ++++++++++----------
 net/ieee802154/6lowpan/reassembly.c     |   10 +++++-----
 net/ipv4/ip_fragment.c                  |   10 +++++-----
 net/ipv4/proc.c                         |    2 +-
 net/ipv6/netfilter/nf_conntrack_reasm.c |   10 +++++-----
 net/ipv6/proc.c                         |    2 +-
 net/ipv6/reassembly.c                   |    6 +++---
 8 files changed, 32 insertions(+), 32 deletions(-)

--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -122,10 +122,10 @@ min_adv_mss - INTEGER
 
 IP Fragmentation:
 
-ipfrag_high_thresh - INTEGER
+ipfrag_high_thresh - LONG INTEGER
 	Maximum memory used to reassemble IP fragments.
 
-ipfrag_low_thresh - INTEGER
+ipfrag_low_thresh - LONG INTEGER
 	(Obsolete since linux-4.17)
 	Maximum memory used to reassemble IP fragments before the kernel
 	begins to remove incomplete fragment queues to free up resources.
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -7,11 +7,11 @@ struct netns_frags {
 	struct rhashtable       rhashtable ____cacheline_aligned_in_smp;
 
 	/* Keep atomic mem on separate cachelines in structs that include it */
-	atomic_t		mem ____cacheline_aligned_in_smp;
+	atomic_long_t		mem ____cacheline_aligned_in_smp;
 	/* sysctls */
+	long			high_thresh;
+	long			low_thresh;
 	int			timeout;
-	int			high_thresh;
-	int			low_thresh;
 	int			max_dist;
 	struct inet_frags	*f;
 };
@@ -101,7 +101,7 @@ void inet_frags_fini(struct inet_frags *
 
 static inline int inet_frags_init_net(struct netns_frags *nf)
 {
-	atomic_set(&nf->mem, 0);
+	atomic_long_set(&nf->mem, 0);
 	return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
 }
 void inet_frags_exit_net(struct netns_frags *nf);
@@ -118,19 +118,19 @@ static inline void inet_frag_put(struct
 
 /* Memory Tracking Functions. */
 
-static inline int frag_mem_limit(struct netns_frags *nf)
+static inline long frag_mem_limit(const struct netns_frags *nf)
 {
-	return atomic_read(&nf->mem);
+	return atomic_long_read(&nf->mem);
 }
 
-static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void sub_frag_mem_limit(struct netns_frags *nf, long val)
 {
-	atomic_sub(i, &nf->mem);
+	atomic_long_sub(val, &nf->mem);
 }
 
-static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void add_frag_mem_limit(struct netns_frags *nf, long val)
 {
-	atomic_add(i, &nf->mem);
+	atomic_long_add(val, &nf->mem);
 }
 
 /* RFC 3168 support :
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -410,23 +410,23 @@ err:
 }
 
 #ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
 
 static struct ctl_table lowpan_frags_ns_ctl_table[] = {
 	{
 		.procname	= "6lowpanfrag_high_thresh",
 		.data		= &init_net.ieee802154_lowpan.frags.high_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.ieee802154_lowpan.frags.low_thresh
 	},
 	{
 		.procname	= "6lowpanfrag_low_thresh",
 		.data		= &init_net.ieee802154_lowpan.frags.low_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &init_net.ieee802154_lowpan.frags.high_thresh
 	},
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -681,23 +681,23 @@ struct sk_buff *ip_check_defrag(struct n
 EXPORT_SYMBOL(ip_check_defrag);
 
 #ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
 
 static struct ctl_table ip4_frags_ns_ctl_table[] = {
 	{
 		.procname	= "ipfrag_high_thresh",
 		.data		= &init_net.ipv4.frags.high_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.ipv4.frags.low_thresh
 	},
 	{
 		.procname	= "ipfrag_low_thresh",
 		.data		= &init_net.ipv4.frags.low_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &init_net.ipv4.frags.high_thresh
 	},
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -73,7 +73,7 @@ static int sockstat_seq_show(struct seq_
 		   sock_prot_inuse_get(net, &udplite_prot));
 	seq_printf(seq, "RAW: inuse %d\n",
 		   sock_prot_inuse_get(net, &raw_prot));
-	seq_printf(seq,  "FRAG: inuse %u memory %u\n",
+	seq_printf(seq,  "FRAG: inuse %u memory %lu\n",
 		   atomic_read(&net->ipv4.frags.rhashtable.nelems),
 		   frag_mem_limit(&net->ipv4.frags));
 	return 0;
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -63,7 +63,7 @@ struct nf_ct_frag6_skb_cb
 static struct inet_frags nf_frags;
 
 #ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
 
 static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{
@@ -76,18 +76,18 @@ static struct ctl_table nf_ct_frag6_sysc
 	{
 		.procname	= "nf_conntrack_frag6_low_thresh",
 		.data		= &init_net.nf_frag.frags.low_thresh,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &init_net.nf_frag.frags.high_thresh
 	},
 	{
 		.procname	= "nf_conntrack_frag6_high_thresh",
 		.data		= &init_net.nf_frag.frags.high_thresh,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.nf_frag.frags.low_thresh
 	},
 	{ }
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -47,7 +47,7 @@ static int sockstat6_seq_show(struct seq
 			sock_prot_inuse_get(net, &udplitev6_prot));
 	seq_printf(seq, "RAW6: inuse %d\n",
 		       sock_prot_inuse_get(net, &rawv6_prot));
-	seq_printf(seq, "FRAG6: inuse %u memory %u\n",
+	seq_printf(seq, "FRAG6: inuse %u memory %lu\n",
 		   atomic_read(&net->ipv6.frags.rhashtable.nelems),
 		   frag_mem_limit(&net->ipv6.frags));
 	return 0;
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -546,15 +546,15 @@ static struct ctl_table ip6_frags_ns_ctl
 	{
 		.procname	= "ip6frag_high_thresh",
 		.data		= &init_net.ipv6.frags.high_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.ipv6.frags.low_thresh
 	},
 	{
 		.procname	= "ip6frag_low_thresh",
 		.data		= &init_net.ipv6.frags.low_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,

  parent reply	other threads:[~2018-10-16 17:09 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20181016170539.315587743@linuxfoundation.org>
2018-10-16 17:09 ` [PATCH 4.9 43/71] inet: frags: change inet_frags_init_net() return value Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 44/71] inet: frags: add a pointer to struct netns_frags Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 45/71] inet: frags: refactor ipfrag_init() Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 46/71] inet: frags: refactor ipv6_frag_init() Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 47/71] inet: frags: refactor lowpan_net_frag_init() Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 48/71] ipv6: export ip6 fragments sysctl to unprivileged users Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 49/71] rhashtable: add schedule points Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 50/71] inet: frags: use rhashtables for reassembly units Greg Kroah-Hartman
2018-10-26 13:39   ` Stefan Schmidt
2018-11-29 12:54     ` Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 51/71] inet: frags: remove some helpers Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 52/71] inet: frags: get rif of inet_frag_evicting() Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 53/71] inet: frags: remove inet_frag_maybe_warn_overflow() Greg Kroah-Hartman
2018-10-16 17:09 ` Greg Kroah-Hartman [this message]
2018-10-16 17:09 ` [PATCH 4.9 55/71] inet: frags: do not clone skb in ip_expire() Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 56/71] ipv6: frags: rewrite ip6_expire_frag_queue() Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 57/71] rhashtable: reorganize struct rhashtable layout Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 58/71] inet: frags: reorganize struct netns_frags Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 59/71] inet: frags: get rid of ipfrag_skb_cb/FRAG_CB Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 60/71] inet: frags: fix ip6frag_low_thresh boundary Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 61/71] ip: discard IPv4 datagrams with overlapping segments Greg Kroah-Hartman
2018-10-16 17:09 ` [PATCH 4.9 62/71] net: speed up skb_rbtree_purge() Greg Kroah-Hartman
2018-10-16 17:10 ` [PATCH 4.9 63/71] net: modify skb_rbtree_purge to return the truesize of all purged skbs Greg Kroah-Hartman
2018-10-16 17:10 ` [PATCH 4.9 64/71] ipv6: defrag: drop non-last frags smaller than min mtu Greg Kroah-Hartman
2018-10-16 17:10 ` [PATCH 4.9 65/71] net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends Greg Kroah-Hartman
2018-10-16 17:10 ` [PATCH 4.9 66/71] net: add rb_to_skb() and other rb tree helpers Greg Kroah-Hartman
2018-10-16 17:10 ` [PATCH 4.9 67/71] ip: use rb trees for IP frag queue Greg Kroah-Hartman
2018-10-16 17:10 ` [PATCH 4.9 68/71] ip: add helpers to process in-order fragments faster Greg Kroah-Hartman
2018-10-16 17:10 ` [PATCH 4.9 69/71] ip: process in-order fragments efficiently Greg Kroah-Hartman
2018-10-16 17:10 ` [PATCH 4.9 70/71] ip: frags: fix crash in ip_do_fragment() Greg Kroah-Hartman
2018-10-16 17:10 ` [PATCH 4.9 71/71] ipv4: frags: precedence bug in ip_expire() Greg Kroah-Hartman

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=20181016170542.081277817@linuxfoundation.org \
    --to=gregkh@linuxfoundation$(echo .)org \
    --cc=davem@davemloft$(echo .)net \
    --cc=edumazet@google$(echo .)com \
    --cc=linux-kernel@vger$(echo .)kernel.org \
    --cc=netdev@vger$(echo .)kernel.org \
    --cc=stable@vger$(echo .)kernel.org \
    /path/to/YOUR_REPLY

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