diff options
Diffstat (limited to 'net/ipv4')
| -rw-r--r-- | net/ipv4/fib_semantics.c | 12 | ||||
| -rw-r--r-- | net/ipv4/route.c | 1 | ||||
| -rw-r--r-- | net/ipv4/tcp.c | 2 | ||||
| -rw-r--r-- | net/ipv4/tcp_input.c | 5 | ||||
| -rw-r--r-- | net/ipv4/tcp_memcontrol.c | 34 | ||||
| -rw-r--r-- | net/ipv4/udp.c | 30 |
6 files changed, 51 insertions, 33 deletions
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index a8bdf7405433..e5b7182fa099 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -145,6 +145,12 @@ static void free_fib_info_rcu(struct rcu_head *head) { struct fib_info *fi = container_of(head, struct fib_info, rcu); + change_nexthops(fi) { + if (nexthop_nh->nh_dev) + dev_put(nexthop_nh->nh_dev); + } endfor_nexthops(fi); + + release_net(fi->fib_net); if (fi->fib_metrics != (u32 *) dst_default_metrics) kfree(fi->fib_metrics); kfree(fi); @@ -156,13 +162,7 @@ void free_fib_info(struct fib_info *fi) pr_warn("Freeing alive fib_info %p\n", fi); return; } - change_nexthops(fi) { - if (nexthop_nh->nh_dev) - dev_put(nexthop_nh->nh_dev); - nexthop_nh->nh_dev = NULL; - } endfor_nexthops(fi); fib_info_cnt--; - release_net(fi->fib_net); call_rcu(&fi->rcu, free_fib_info_rcu); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ffcb3b016843..98b30d08efe9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3452,6 +3452,7 @@ int __init ip_rt_init(void) 0, &rt_hash_log, &rt_hash_mask, + 0, rhash_entries ? 0 : 512 * 1024); memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket)); rt_hash_lock_init(); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bb485fcb077e..3ba605f60e4e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3514,6 +3514,7 @@ void __init tcp_init(void) 0, NULL, &tcp_hashinfo.ehash_mask, + 0, thash_entries ? 0 : 512 * 1024); for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) { INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); @@ -3530,6 +3531,7 @@ void __init tcp_init(void) 0, &tcp_hashinfo.bhash_size, NULL, + 0, 64 * 1024); tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index cfa2aa128342..b224eb8bce8b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4555,6 +4555,11 @@ static bool tcp_try_coalesce(struct sock *sk, if (tcp_hdr(from)->fin) return false; + + /* Its possible this segment overlaps with prior segment in queue */ + if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq) + return false; + if (!skb_try_coalesce(to, from, fragstolen, &delta)) return false; diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 151703791bb0..b6f3583ddfe8 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -74,9 +74,6 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg) percpu_counter_destroy(&tcp->tcp_sockets_allocated); val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT); - - if (val != RESOURCE_MAX) - static_key_slow_dec(&memcg_socket_limit_enabled); } EXPORT_SYMBOL(tcp_destroy_cgroup); @@ -107,10 +104,33 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT, net->ipv4.sysctl_tcp_mem[i]); - if (val == RESOURCE_MAX && old_lim != RESOURCE_MAX) - static_key_slow_dec(&memcg_socket_limit_enabled); - else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX) - static_key_slow_inc(&memcg_socket_limit_enabled); + if (val == RESOURCE_MAX) + clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); + else if (val != RESOURCE_MAX) { + /* + * The active bit needs to be written after the static_key + * update. This is what guarantees that the socket activation + * function is the last one to run. See sock_update_memcg() for + * details, and note that we don't mark any socket as belonging + * to this memcg until that flag is up. + * + * We need to do this, because static_keys will span multiple + * sites, but we can't control their order. If we mark a socket + * as accounted, but the accounting functions are not patched in + * yet, we'll lose accounting. + * + * We never race with the readers in sock_update_memcg(), + * because when this value change, the code to process it is not + * patched in yet. + * + * The activated bit is used to guarantee that no two writers + * will do the update in the same memcg. Without that, we can't + * properly shutdown the static key. + */ + if (!test_and_set_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) + static_key_slow_inc(&memcg_socket_limit_enabled); + set_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); + } return 0; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 609397ee78fb..eaca73644e79 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2192,26 +2192,16 @@ void __init udp_table_init(struct udp_table *table, const char *name) { unsigned int i; - if (!CONFIG_BASE_SMALL) - table->hash = alloc_large_system_hash(name, - 2 * sizeof(struct udp_hslot), - uhash_entries, - 21, /* one slot per 2 MB */ - 0, - &table->log, - &table->mask, - 64 * 1024); - /* - * Make sure hash table has the minimum size - */ - if (CONFIG_BASE_SMALL || table->mask < UDP_HTABLE_SIZE_MIN - 1) { - table->hash = kmalloc(UDP_HTABLE_SIZE_MIN * - 2 * sizeof(struct udp_hslot), GFP_KERNEL); - if (!table->hash) - panic(name); - table->log = ilog2(UDP_HTABLE_SIZE_MIN); - table->mask = UDP_HTABLE_SIZE_MIN - 1; - } + table->hash = alloc_large_system_hash(name, + 2 * sizeof(struct udp_hslot), + uhash_entries, + 21, /* one slot per 2 MB */ + 0, + &table->log, + &table->mask, + UDP_HTABLE_SIZE_MIN, + 64 * 1024); + table->hash2 = table->hash + (table->mask + 1); for (i = 0; i <= table->mask; i++) { INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i); |