Sending Ipv6 packets in a loop via a raw socket triggers an issue where a
route is cloned by ip6_rt_cache_alloc() for each packet sent. This quickly
consumes the Ipv6 max_size threshold which defaults to 4096 resulting in
these warnings:
[1] 99.187805] dst_alloc: 7728 callbacks suppressed
[2] Route cache is full: consider increasing sysctl net.ipv6.route.max_size.
.
.
[300] Route cache is full: consider increasing sysctl net.ipv6.route.max_size.
When this happens the packet is dropped and sendto() gets a network is
unreachable error:
# ./a.out -s
remaining pkt 200557 errno 101
remaining pkt 196462 errno 101
.
.
remaining pkt 126821 errno 101
Implement David Aherns suggestion to remove max_size check seeing that Ipv6
has a GC to manage memory usage. Ipv4 already does not check max_size.
Here are some memory comparisons for Ipv4 vs Ipv6 with the patch:
Test by running 5 instances of a program that sends UDP packets to a raw
socket 5000000 times. Compare Ipv4 and Ipv6 performance with a similar
program.
Ipv4:
Before test:
# grep -e Slab -e Free /proc/meminfo
MemFree: 29427108 kB
Slab: 237612 kB
# grep dst_cache /proc/slabinfo
ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0
xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
ip_dst_cache 2881 3990 192 42 2 : tunables 0 0 0
During test:
# grep -e Slab -e Free /proc/meminfo
MemFree: 29417608 kB
Slab: 247712 kB
# grep dst_cache /proc/slabinfo
ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0
xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
ip_dst_cache 44394 44394 192 42 2 : tunables 0 0 0
After test:
# grep -e Slab -e Free /proc/meminfo
MemFree: 29422308 kB
Slab: 238104 kB
# grep dst_cache /proc/slabinfo
ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0
xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0
Ipv6 with patch:
Errno 101 errors are not observed anymore with the patch.
Before test:
# grep -e Slab -e Free /proc/meminfo
MemFree: 29422308 kB
Slab: 238104 kB
# grep dst_cache /proc/slabinfo
ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0
xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0
During Test:
# grep -e Slab -e Free /proc/meminfo
MemFree: 29431516 kB
Slab: 240940 kB
# grep dst_cache /proc/slabinfo
ip6_dst_cache 11980 12064 256 32 2 : tunables 0 0 0
xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0
After Test:
# grep -e Slab -e Free /proc/meminfo
MemFree: 29441816 kB
Slab: 238132 kB
# grep dst_cache /proc/slabinfo
ip6_dst_cache 1902 2432 256 32 2 : tunables 0 0 0
xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0
Tested-by: Andrea Mayer <[email protected]>
Signed-off-by: Jon Maxwell <[email protected]>
---
include/net/dst_ops.h | 2 +-
net/core/dst.c | 8 ++------
net/ipv6/route.c | 13 +++++--------
3 files changed, 8 insertions(+), 15 deletions(-)
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 88ff7bb2bb9b..632086b2f644 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -16,7 +16,7 @@ struct dst_ops {
unsigned short family;
unsigned int gc_thresh;
- int (*gc)(struct dst_ops *ops);
+ void (*gc)(struct dst_ops *ops);
struct dst_entry * (*check)(struct dst_entry *, __u32 cookie);
unsigned int (*default_advmss)(const struct dst_entry *);
unsigned int (*mtu)(const struct dst_entry *);
diff --git a/net/core/dst.c b/net/core/dst.c
index 6d2dd03dafa8..31c08a3386d3 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -82,12 +82,8 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
if (ops->gc &&
!(flags & DST_NOCOUNT) &&
- dst_entries_get_fast(ops) > ops->gc_thresh) {
- if (ops->gc(ops)) {
- pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n");
- return NULL;
- }
- }
+ dst_entries_get_fast(ops) > ops->gc_thresh)
+ ops->gc(ops);
dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC);
if (!dst)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e74e0361fd92..53b09de61a4a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -91,7 +91,7 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *);
static void ip6_dst_destroy(struct dst_entry *);
static void ip6_dst_ifdown(struct dst_entry *,
struct net_device *dev, int how);
-static int ip6_dst_gc(struct dst_ops *ops);
+static void ip6_dst_gc(struct dst_ops *ops);
static int ip6_pkt_discard(struct sk_buff *skb);
static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb);
@@ -3284,11 +3284,10 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
return dst;
}
-static int ip6_dst_gc(struct dst_ops *ops)
+static void ip6_dst_gc(struct dst_ops *ops)
{
struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops);
int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval;
- int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size;
int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity;
int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout;
unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc;
@@ -3296,11 +3295,10 @@ static int ip6_dst_gc(struct dst_ops *ops)
int entries;
entries = dst_entries_get_fast(ops);
- if (entries > rt_max_size)
+ if (entries > gc_thresh)
entries = dst_entries_get_slow(ops);
- if (time_after(rt_last_gc + rt_min_interval, jiffies) &&
- entries <= rt_max_size)
+ if (time_after(rt_last_gc + rt_min_interval, jiffies))
goto out;
fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true);
@@ -3310,7 +3308,6 @@ static int ip6_dst_gc(struct dst_ops *ops)
out:
val = atomic_read(&net->ipv6.ip6_rt_gc_expire);
atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity));
- return entries > rt_max_size;
}
static int ip6_nh_lookup_table(struct net *net, struct fib6_config *cfg,
@@ -6512,7 +6509,7 @@ static int __net_init ip6_route_net_init(struct net *net)
#endif
net->ipv6.sysctl.flush_delay = 0;
- net->ipv6.sysctl.ip6_rt_max_size = 4096;
+ net->ipv6.sysctl.ip6_rt_max_size = INT_MAX;
net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2;
net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ;
net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ;
--
2.31.1
Hi Jon,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on net-next/master]
url: https://github.com/intel-lab-lkp/linux/commits/Jon-Maxwell/ipv6-remove-max_size-check-inline-with-ipv4/20230112-053517
patch link: https://lore.kernel.org/r/20230111213306.265239-1-jmaxwell37%40gmail.com
patch subject: [net-next] ipv6: remove max_size check inline with ipv4
config: m68k-allmodconfig
compiler: m68k-linux-gcc (GCC) 12.1.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/intel-lab-lkp/linux/commit/6fb29b5595df9235f531daa3af1ab4aebf0c1834
git remote add linux-review https://github.com/intel-lab-lkp/linux
git fetch --no-tags linux-review Jon-Maxwell/ipv6-remove-max_size-check-inline-with-ipv4/20230112-053517
git checkout 6fb29b5595df9235f531daa3af1ab4aebf0c1834
# save the config file
mkdir build_dir && cp config build_dir/.config
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.1.0 make.cross W=1 O=build_dir ARCH=m68k olddefconfig
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.1.0 make.cross W=1 O=build_dir ARCH=m68k SHELL=/bin/bash net/
If you fix the issue, kindly add following tag where applicable
| Reported-by: kernel test robot <[email protected]>
All errors (new ones prefixed by >>):
net/ipv6/route.c: In function 'ip6_dst_gc':
>> net/ipv6/route.c:3298:23: error: 'gc_thresh' undeclared (first use in this function)
3298 | if (entries > gc_thresh)
| ^~~~~~~~~
net/ipv6/route.c:3298:23: note: each undeclared identifier is reported only once for each function it appears in
vim +/gc_thresh +3298 net/ipv6/route.c
3286
3287 static void ip6_dst_gc(struct dst_ops *ops)
3288 {
3289 struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops);
3290 int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval;
3291 int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity;
3292 int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout;
3293 unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc;
3294 unsigned int val;
3295 int entries;
3296
3297 entries = dst_entries_get_fast(ops);
> 3298 if (entries > gc_thresh)
3299 entries = dst_entries_get_slow(ops);
3300
3301 if (time_after(rt_last_gc + rt_min_interval, jiffies))
3302 goto out;
3303
3304 fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true);
3305 entries = dst_entries_get_slow(ops);
3306 if (entries < ops->gc_thresh)
3307 atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1);
3308 out:
3309 val = atomic_read(&net->ipv6.ip6_rt_gc_expire);
3310 atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity));
3311 }
3312
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests