| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1383059555.5464.33.camel@edumazet-glaptop.roam.corp.google.com>
Date: Tue, 29 Oct 2013 08:12:35 -0700
From: Eric Dumazet <eric.dumazet@...il.com>
To: Christoph Paasch <christoph.paasch@...ouvain.be>
Cc: David Miller <davem@...emloft.net>,
Herbert Xu <herbert@...dor.apana.org.au>,
netdev <netdev@...r.kernel.org>, Jerry Chu <hkchu@...gle.com>,
Michael Dalton <mwdalton@...gle.com>
Subject: [PATCH v2 net-next] net: introduce gro_frag_list_enable sysctl
From: Eric Dumazet <edumazet@...gle.com>
Christoph Paasch and Jerry Chu reported crashes in skb_segment() caused
by commit 8a29111c7ca6 ("net: gro: allow to build full sized skb")
(Jerry is working on adding native GRO support for tunnels)
skb_segment() only deals with a frag_list chain containing MSS sized
fragments.
This patch adds support any kind of frag, and adds a new sysctl,
as clearly the GRO layer should avoid building frag_list skbs
on a router, as the segmentation is adding cpu overhead.
Note that we could try to reuse page fragments instead of doing
copy to linear skbs, but this requires a fair amount of work,
and possible truesize nightmares, as we do not track individual
(per page fragment) truesizes.
/proc/sys/net/core/gro_frag_list_enable possible values are :
0 : GRO layer is not allowed to use frag_list to extend skb capacity
1 : GRO layer is allowed to use frag_list, but skb_segment()
automatically sets the sysctl to 0.
2 : GRO is allowed to use frag_list, and skb_segment() wont
clear the sysctl.
Default value is 1 : automatic discovery
Reported-by: Christoph Paasch <christoph.paasch@...ouvain.be>
Reported-by: Jerry Chu <hkchu@...gle.com>
Cc: Michael Dalton <mwdalton@...gle.com>
Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
v2: added missing sysctl definition in skbuff.c
Documentation/sysctl/net.txt | 19 +++++++++++++++++++
include/linux/netdevice.h | 1 +
net/core/skbuff.c | 31 ++++++++++++++++++++++---------
net/core/sysctl_net_core.c | 10 ++++++++++
4 files changed, 52 insertions(+), 9 deletions(-)
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index 9a0319a82470..8778568ae64e 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -87,6 +87,25 @@ sysctl.net.busy_read globally.
Will increase power usage.
Default: 0 (off)
+gro_frag_list_enable
+--------------------
+
+GRO layer can build full size GRO packets (~64K of payload) if it is allowed
+to extend skb using the frag_list pointer. However, this strategy is a win
+on hosts, where TCP flows are terminated. For a router, using frag_list
+skbs is not a win because we have to segment skbs before transmit,
+as most NIC drivers do not support frag_list.
+As soon as one frag_list skb has to be segmented, this sysctl is automatically
+changed from 1 to 0.
+If the value is set to 2, kernel wont change it.
+
+Choices : 0 (off),
+ 1 (on, with automatic change to 0)
+ 2 (on, permanent)
+
+Default: 1 (on, with automatic downgrade on a router)
+
+
rmem_default
------------
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 27f62f746621..b82ff52f301e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2807,6 +2807,7 @@ extern int netdev_max_backlog;
extern int netdev_tstamp_prequeue;
extern int weight_p;
extern int bpf_jit_enable;
+extern int sysctl_gro_frag_list_enable;
bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
bool netdev_has_any_upper_dev(struct net_device *dev);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 0ab32faa520f..e089cd2782e5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -74,6 +74,8 @@
struct kmem_cache *skbuff_head_cache __read_mostly;
static struct kmem_cache *skbuff_fclone_cache __read_mostly;
+int sysctl_gro_frag_list_enable __read_mostly = 1;
+
static void sock_pipe_buf_release(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
@@ -2761,7 +2763,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
unsigned int len;
__be16 proto;
bool csum;
- int sg = !!(features & NETIF_F_SG);
+ bool sg = !!(features & NETIF_F_SG);
int nfrags = skb_shinfo(skb)->nr_frags;
int err = -ENOMEM;
int i = 0;
@@ -2793,7 +2795,13 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
hsize = len;
if (!hsize && i >= nfrags) {
- BUG_ON(fskb->len != len);
+ if (fskb->len != len) {
+ if (sysctl_gro_frag_list_enable == 1)
+ sysctl_gro_frag_list_enable = 0;
+ hsize = len;
+ sg = false;
+ goto do_linear;
+ }
pos += len;
nskb = skb_clone(fskb, GFP_ATOMIC);
@@ -2812,6 +2820,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
skb_release_head_state(nskb);
__skb_push(nskb, doffset);
} else {
+do_linear:
nskb = __alloc_skb(hsize + doffset + headroom,
GFP_ATOMIC, skb_alloc_rx_flag(skb),
NUMA_NO_NODE);
@@ -2838,9 +2847,6 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
nskb->data - tnl_hlen,
doffset + tnl_hlen);
- if (fskb != skb_shinfo(skb)->frag_list)
- goto perform_csum_check;
-
if (!sg) {
nskb->ip_summed = CHECKSUM_NONE;
nskb->csum = skb_copy_and_csum_bits(skb, offset,
@@ -2849,6 +2855,9 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
continue;
}
+ if (fskb != skb_shinfo(skb)->frag_list)
+ goto perform_csum_check;
+
frag = skb_shinfo(nskb)->frags;
skb_copy_from_linear_data_offset(skb, offset,
@@ -2944,9 +2953,11 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
int i = skbinfo->nr_frags;
int nr_frags = pinfo->nr_frags + i;
- if (nr_frags > MAX_SKB_FRAGS)
+ if (unlikely(nr_frags > MAX_SKB_FRAGS)) {
+ if (!sysctl_gro_frag_list_enable)
+ return -E2BIG;
goto merge;
-
+ }
offset -= headlen;
pinfo->nr_frags = nr_frags;
skbinfo->nr_frags = 0;
@@ -2977,9 +2988,11 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
unsigned int first_size = headlen - offset;
unsigned int first_offset;
- if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS)
+ if (unlikely(nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS)) {
+ if (!sysctl_gro_frag_list_enable)
+ return -E2BIG;
goto merge;
-
+ }
first_offset = skb->data -
(unsigned char *)page_address(page) +
offset;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index cca444190907..2d6aaf6d5838 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -24,6 +24,7 @@
static int zero = 0;
static int one = 1;
+static int two = 2;
static int ushort_max = USHRT_MAX;
#ifdef CONFIG_RPS
@@ -360,6 +361,15 @@ static struct ctl_table net_core_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "gro_frag_list_enable",
+ .data = &sysctl_gro_frag_list_enable,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &two,
+ },
{ }
};
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists