From: Eric Dumazet edumazet@google.com
stable inclusion from stable-v4.19.304 commit 9635bd0a5296e2e725c6b33e530d0ef582e2f64e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I90HST
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
commit cf86a086a18095e33e0637cb78cda1fcf5280852 upstream.
percpu_counter_add() uses a default batch size which is quite big on platforms with 256 cpus. (2*256 -> 512)
This means dst_entries_get_fast() can be off by +/- 2*(nr_cpus^2) (131072 on servers with 256 cpus)
Reduce the batch size to something more reasonable, and add logic to ip6_dst_gc() to call dst_entries_get_slow() before calling the _very_ expensive fib6_run_gc() function.
Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Suraj Jitindar Singh surajjs@amazon.com Cc: stable@vger.kernel.org # 4.19.x Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Dong Chenchen dongchenchen2@huawei.com --- include/net/dst_ops.h | 4 +++- net/core/dst.c | 8 ++++---- net/ipv6/route.c | 3 +++ 3 files changed, 10 insertions(+), 5 deletions(-)
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 33392b9a701f..b8ee48ea07f1 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -63,9 +63,11 @@ static inline int dst_entries_get_slow(struct dst_ops *dst) return percpu_counter_sum_positive(&dst->pcpuc_entries); }
+#define DST_PERCPU_COUNTER_BATCH 32 static inline void dst_entries_add(struct dst_ops *dst, int val) { - percpu_counter_add(&dst->pcpuc_entries, val); + percpu_counter_add_batch(&dst->pcpuc_entries, val, + DST_PERCPU_COUNTER_BATCH); }
static inline int dst_entries_init(struct dst_ops *dst) diff --git a/net/core/dst.c b/net/core/dst.c index a263309df115..1a9f84f8cde1 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -97,11 +97,11 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, { struct dst_entry *dst;
- if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { + if (ops->gc && + !(flags & DST_NOCOUNT) && + dst_entries_get_fast(ops) > ops->gc_thresh) { if (ops->gc(ops)) { - printk_ratelimited(KERN_NOTICE "Route cache is full: " - "consider increasing sysctl " - "net.ipv[4|6].route.max_size.\n"); + pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n"); return NULL; } } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7b2ed1fb747e..344e1548fd94 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2781,6 +2781,9 @@ static int ip6_dst_gc(struct dst_ops *ops) int entries;
entries = dst_entries_get_fast(ops); + if (entries > rt_max_size) + entries = dst_entries_get_slow(ops); + if (time_after(rt_last_gc + rt_min_interval, jiffies) && entries <= rt_max_size) goto out;