summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig1
-rw-r--r--net/ipv4/Makefile1
-rw-r--r--net/ipv4/fib_trie.c11
-rw-r--r--net/ipv4/inet_diag.c21
-rw-r--r--net/ipv4/ip_fragment.c1
-rw-r--r--net/ipv4/ip_input.c5
-rw-r--r--net/ipv4/ip_output.c1
-rw-r--r--net/ipv4/ipconfig.c4
-rw-r--r--net/ipv4/netfilter/nf_defrag_ipv4.c2
-rw-r--r--net/ipv4/sysctl_net_ipv4.c1
-rw-r--r--net/ipv4/tcp.c15
-rw-r--r--net/ipv4/tcp_input.c12
-rw-r--r--net/ipv4/tcp_ipv4.c23
-rw-r--r--net/ipv4/tcp_memcontrol.c233
-rw-r--r--net/ipv4/tcp_output.c7
-rw-r--r--net/ipv4/udp.c32
16 files changed, 82 insertions, 288 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index c22920525e5d..775824720b6b 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -353,6 +353,7 @@ config INET_ESP
select CRYPTO_CBC
select CRYPTO_SHA1
select CRYPTO_DES
+ select CRYPTO_ECHAINIV
---help---
Support for IPsec ESP.
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index c29809f765dc..62c049b647e9 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -56,7 +56,6 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
-obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o
obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 744e5936c10d..d07fc076bea0 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -289,10 +289,8 @@ static void __node_free_rcu(struct rcu_head *head)
if (!n->tn_bits)
kmem_cache_free(trie_leaf_kmem, n);
- else if (n->tn_bits <= TNODE_KMALLOC_MAX)
- kfree(n);
else
- vfree(n);
+ kvfree(n);
}
#define node_free(n) call_rcu(&tn_info(n)->rcu, __node_free_rcu)
@@ -1396,9 +1394,10 @@ found:
struct fib_info *fi = fa->fa_info;
int nhsel, err;
- if ((index >= (1ul << fa->fa_slen)) &&
- ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen != KEYLENGTH)))
- continue;
+ if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) {
+ if (index >= (1ul << fa->fa_slen))
+ continue;
+ }
if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
continue;
if (fi->fib_dead)
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 8bb8e7ad8548..6029157a19ed 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -361,13 +361,20 @@ struct sock *inet_diag_find_one_icsk(struct net *net,
req->id.idiag_dport, req->id.idiag_src[0],
req->id.idiag_sport, req->id.idiag_if);
#if IS_ENABLED(CONFIG_IPV6)
- else if (req->sdiag_family == AF_INET6)
- sk = inet6_lookup(net, hashinfo,
- (struct in6_addr *)req->id.idiag_dst,
- req->id.idiag_dport,
- (struct in6_addr *)req->id.idiag_src,
- req->id.idiag_sport,
- req->id.idiag_if);
+ else if (req->sdiag_family == AF_INET6) {
+ if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
+ ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
+ sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3],
+ req->id.idiag_dport, req->id.idiag_src[3],
+ req->id.idiag_sport, req->id.idiag_if);
+ else
+ sk = inet6_lookup(net, hashinfo,
+ (struct in6_addr *)req->id.idiag_dst,
+ req->id.idiag_dport,
+ (struct in6_addr *)req->id.idiag_src,
+ req->id.idiag_sport,
+ req->id.idiag_if);
+ }
#endif
else
return ERR_PTR(-EINVAL);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 3f00810b7288..187c6fcc3027 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -661,6 +661,7 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
struct ipq *qp;
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
+ skb_orphan(skb);
/* Lookup (or create) queue header */
qp = ip_find(net, ip_hdr(skb), user, vif);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index b1209b63381f..d77eb0c3b684 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -316,7 +316,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
- if (sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk) {
+ if (sysctl_ip_early_demux &&
+ !skb_dst(skb) &&
+ !skb->sk &&
+ !ip_is_fragment(iph)) {
const struct net_protocol *ipprot;
int protocol = iph->protocol;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 512a44778cf2..64878efa045c 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -239,6 +239,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
* from host network stack.
*/
features = netif_skb_features(skb);
+ BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
if (IS_ERR_OR_NULL(segs)) {
kfree_skb(skb);
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 67f7c9de0b16..2ed9dd2b5f2f 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -143,7 +143,11 @@ static char dhcp_client_identifier[253] __initdata;
/* Persistent data: */
+#ifdef IPCONFIG_DYNAMIC
static int ic_proto_used; /* Protocol used, if any */
+#else
+#define ic_proto_used 0
+#endif
static __be32 ic_nameservers[CONF_NAMESERVERS_MAX]; /* DNS Server IP addresses */
static u8 ic_domain[64]; /* DNS (not NIS) domain name */
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 6fb869f646bf..a04dee536b8e 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -27,8 +27,6 @@ static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb,
{
int err;
- skb_orphan(skb);
-
local_bh_disable();
err = ip_defrag(net, skb, user);
local_bh_enable();
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 46ce410703b1..4d367b4139a3 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -24,7 +24,6 @@
#include <net/cipso_ipv4.h>
#include <net/inet_frag.h>
#include <net/ping.h>
-#include <net/tcp_memcontrol.h>
static int zero;
static int one = 1;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7bb1b091efd1..19746b3fcbbe 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -279,6 +279,7 @@
#include <asm/uaccess.h>
#include <asm/ioctls.h>
+#include <asm/unaligned.h>
#include <net/busy_poll.h>
int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
@@ -422,7 +423,8 @@ void tcp_init_sock(struct sock *sk)
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
local_bh_disable();
- sock_update_memcg(sk);
+ if (mem_cgroup_sockets_enabled)
+ sock_update_memcg(sk);
sk_sockets_allocated_inc(sk);
local_bh_enable();
}
@@ -2637,6 +2639,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 now = tcp_time_stamp;
unsigned int start;
+ u64 rate64;
u32 rate;
memset(info, 0, sizeof(*info));
@@ -2702,15 +2705,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_total_retrans = tp->total_retrans;
rate = READ_ONCE(sk->sk_pacing_rate);
- info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+ rate64 = rate != ~0U ? rate : ~0ULL;
+ put_unaligned(rate64, &info->tcpi_pacing_rate);
rate = READ_ONCE(sk->sk_max_pacing_rate);
- info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
+ rate64 = rate != ~0U ? rate : ~0ULL;
+ put_unaligned(rate64, &info->tcpi_max_pacing_rate);
do {
start = u64_stats_fetch_begin_irq(&tp->syncp);
- info->tcpi_bytes_acked = tp->bytes_acked;
- info->tcpi_bytes_received = tp->bytes_received;
+ put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked);
+ put_unaligned(tp->bytes_received, &info->tcpi_bytes_received);
} while (u64_stats_fetch_retry_irq(&tp->syncp, start));
info->tcpi_segs_out = tp->segs_out;
info->tcpi_segs_in = tp->segs_in;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 0003d409fec5..1c2a73406261 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2164,8 +2164,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int cnt, oldcnt;
- int err;
+ int cnt, oldcnt, lost;
unsigned int mss;
/* Use SACK to deduce losses of new sequences sent during recovery */
const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq;
@@ -2205,9 +2204,10 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
break;
mss = tcp_skb_mss(skb);
- err = tcp_fragment(sk, skb, (packets - oldcnt) * mss,
- mss, GFP_ATOMIC);
- if (err < 0)
+ /* If needed, chop off the prefix to mark as lost. */
+ lost = (packets - oldcnt) * mss;
+ if (lost < skb->len &&
+ tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0)
break;
cnt = packets;
}
@@ -2366,8 +2366,6 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
tp->snd_ssthresh = tp->prior_ssthresh;
tcp_ecn_withdraw_cwr(tp);
}
- } else {
- tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
}
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->undo_marker = 0;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 65947c1f4733..a4d523709ab3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -73,7 +73,6 @@
#include <net/timewait_sock.h>
#include <net/xfrm.h>
#include <net/secure_seq.h>
-#include <net/tcp_memcontrol.h>
#include <net/busy_poll.h>
#include <linux/inet.h>
@@ -708,7 +707,8 @@ release_sk1:
outside socket context is ugly, certainly. What can I do?
*/
-static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+static void tcp_v4_send_ack(struct net *net,
+ struct sk_buff *skb, u32 seq, u32 ack,
u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key,
int reply_flags, u8 tos)
@@ -723,7 +723,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
];
} rep;
struct ip_reply_arg arg;
- struct net *net = dev_net(skb_dst(skb)->dev);
memset(&rep.th, 0, sizeof(struct tcphdr));
memset(&arg, 0, sizeof(arg));
@@ -785,7 +784,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
- tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+ tcp_v4_send_ack(sock_net(sk), skb,
+ tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp + tcptw->tw_ts_offset,
tcptw->tw_ts_recent,
@@ -804,8 +804,10 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
* sk->sk_state == TCP_SYN_RECV -> for Fast Open.
*/
- tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
- tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+ u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
+ tcp_sk(sk)->snd_nxt;
+
+ tcp_v4_send_ack(sock_net(sk), skb, seq,
tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
tcp_time_stamp,
req->ts_recent,
@@ -1818,7 +1820,9 @@ void tcp_v4_destroy_sock(struct sock *sk)
tcp_saved_syn_free(tp);
sk_sockets_allocated_dec(sk);
- sock_release_memcg(sk);
+
+ if (mem_cgroup_sockets_enabled && sk->sk_memcg)
+ sock_release_memcg(sk);
}
EXPORT_SYMBOL(tcp_v4_destroy_sock);
@@ -2342,11 +2346,6 @@ struct proto tcp_prot = {
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
-#ifdef CONFIG_MEMCG_KMEM
- .init_cgroup = tcp_init_cgroup,
- .destroy_cgroup = tcp_destroy_cgroup,
- .proto_cgroup = tcp_proto_cgroup,
-#endif
.diag_destroy = tcp_abort,
};
EXPORT_SYMBOL(tcp_prot);
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
deleted file mode 100644
index 2379c1b4efb2..000000000000
--- a/net/ipv4/tcp_memcontrol.c
+++ /dev/null
@@ -1,233 +0,0 @@
-#include <net/tcp.h>
-#include <net/tcp_memcontrol.h>
-#include <net/sock.h>
-#include <net/ip.h>
-#include <linux/nsproxy.h>
-#include <linux/memcontrol.h>
-#include <linux/module.h>
-
-int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
-{
- /*
- * The root cgroup does not use page_counters, but rather,
- * rely on the data already collected by the network
- * subsystem
- */
- struct mem_cgroup *parent = parent_mem_cgroup(memcg);
- struct page_counter *counter_parent = NULL;
- struct cg_proto *cg_proto, *parent_cg;
-
- cg_proto = tcp_prot.proto_cgroup(memcg);
- if (!cg_proto)
- return 0;
-
- cg_proto->sysctl_mem[0] = sysctl_tcp_mem[0];
- cg_proto->sysctl_mem[1] = sysctl_tcp_mem[1];
- cg_proto->sysctl_mem[2] = sysctl_tcp_mem[2];
- cg_proto->memory_pressure = 0;
- cg_proto->memcg = memcg;
-
- parent_cg = tcp_prot.proto_cgroup(parent);
- if (parent_cg)
- counter_parent = &parent_cg->memory_allocated;
-
- page_counter_init(&cg_proto->memory_allocated, counter_parent);
- percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL);
-
- return 0;
-}
-EXPORT_SYMBOL(tcp_init_cgroup);
-
-void tcp_destroy_cgroup(struct mem_cgroup *memcg)
-{
- struct cg_proto *cg_proto;
-
- cg_proto = tcp_prot.proto_cgroup(memcg);
- if (!cg_proto)
- return;
-
- percpu_counter_destroy(&cg_proto->sockets_allocated);
-
- if (test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags))
- static_key_slow_dec(&memcg_socket_limit_enabled);
-
-}
-EXPORT_SYMBOL(tcp_destroy_cgroup);
-
-static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages)
-{
- struct cg_proto *cg_proto;
- int i;
- int ret;
-
- cg_proto = tcp_prot.proto_cgroup(memcg);
- if (!cg_proto)
- return -EINVAL;
-
- ret = page_counter_limit(&cg_proto->memory_allocated, nr_pages);
- if (ret)
- return ret;
-
- for (i = 0; i < 3; i++)
- cg_proto->sysctl_mem[i] = min_t(long, nr_pages,
- sysctl_tcp_mem[i]);
-
- if (nr_pages == PAGE_COUNTER_MAX)
- clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
- else {
- /*
- * 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;
-}
-
-enum {
- RES_USAGE,
- RES_LIMIT,
- RES_MAX_USAGE,
- RES_FAILCNT,
-};
-
-static DEFINE_MUTEX(tcp_limit_mutex);
-
-static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
-{
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned long nr_pages;
- int ret = 0;
-
- buf = strstrip(buf);
-
- switch (of_cft(of)->private) {
- case RES_LIMIT:
- /* see memcontrol.c */
- ret = page_counter_memparse(buf, "-1", &nr_pages);
- if (ret)
- break;
- mutex_lock(&tcp_limit_mutex);
- ret = tcp_update_limit(memcg, nr_pages);
- mutex_unlock(&tcp_limit_mutex);
- break;
- default:
- ret = -EINVAL;
- break;
- }
- return ret ?: nbytes;
-}
-
-static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
-{
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- struct cg_proto *cg_proto = tcp_prot.proto_cgroup(memcg);
- u64 val;
-
- switch (cft->private) {
- case RES_LIMIT:
- if (!cg_proto)
- return PAGE_COUNTER_MAX;
- val = cg_proto->memory_allocated.limit;
- val *= PAGE_SIZE;
- break;
- case RES_USAGE:
- if (!cg_proto)
- val = atomic_long_read(&tcp_memory_allocated);
- else
- val = page_counter_read(&cg_proto->memory_allocated);
- val *= PAGE_SIZE;
- break;
- case RES_FAILCNT:
- if (!cg_proto)
- return 0;
- val = cg_proto->memory_allocated.failcnt;
- break;
- case RES_MAX_USAGE:
- if (!cg_proto)
- return 0;
- val = cg_proto->memory_allocated.watermark;
- val *= PAGE_SIZE;
- break;
- default:
- BUG();
- }
- return val;
-}
-
-static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
-{
- struct mem_cgroup *memcg;
- struct cg_proto *cg_proto;
-
- memcg = mem_cgroup_from_css(of_css(of));
- cg_proto = tcp_prot.proto_cgroup(memcg);
- if (!cg_proto)
- return nbytes;
-
- switch (of_cft(of)->private) {
- case RES_MAX_USAGE:
- page_counter_reset_watermark(&cg_proto->memory_allocated);
- break;
- case RES_FAILCNT:
- cg_proto->memory_allocated.failcnt = 0;
- break;
- }
-
- return nbytes;
-}
-
-static struct cftype tcp_files[] = {
- {
- .name = "kmem.tcp.limit_in_bytes",
- .write = tcp_cgroup_write,
- .read_u64 = tcp_cgroup_read,
- .private = RES_LIMIT,
- },
- {
- .name = "kmem.tcp.usage_in_bytes",
- .read_u64 = tcp_cgroup_read,
- .private = RES_USAGE,
- },
- {
- .name = "kmem.tcp.failcnt",
- .private = RES_FAILCNT,
- .write = tcp_cgroup_reset,
- .read_u64 = tcp_cgroup_read,
- },
- {
- .name = "kmem.tcp.max_usage_in_bytes",
- .private = RES_MAX_USAGE,
- .write = tcp_cgroup_reset,
- .read_u64 = tcp_cgroup_read,
- },
- { } /* terminate */
-};
-
-static int __init tcp_memcontrol_init(void)
-{
- WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, tcp_files));
- return 0;
-}
-__initcall(tcp_memcontrol_init);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 412a920fe0ec..fda379cd600d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2813,13 +2813,16 @@ begin_fwd:
*/
void sk_forced_mem_schedule(struct sock *sk, int size)
{
- int amt, status;
+ int amt;
if (size <= sk->sk_forward_alloc)
return;
amt = sk_mem_pages(size);
sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
- sk_memory_allocated_add(sk, amt, &status);
+ sk_memory_allocated_add(sk, amt);
+
+ if (mem_cgroup_sockets_enabled && sk->sk_memcg)
+ mem_cgroup_charge_skmem(sk->sk_memcg, amt);
}
/* Send a FIN. The caller locks the socket for us.
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index dc45b538e237..be0b21852b13 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -499,6 +499,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
struct sock *sk, *result;
struct hlist_nulls_node *node;
int score, badness, matches = 0, reuseport = 0;
+ bool select_ok = true;
u32 hash = 0;
begin:
@@ -512,14 +513,18 @@ begin:
badness = score;
reuseport = sk->sk_reuseport;
if (reuseport) {
- struct sock *sk2;
hash = udp_ehashfn(net, daddr, hnum,
saddr, sport);
- sk2 = reuseport_select_sock(sk, hash, skb,
- sizeof(struct udphdr));
- if (sk2) {
- result = sk2;
- goto found;
+ if (select_ok) {
+ struct sock *sk2;
+
+ sk2 = reuseport_select_sock(sk, hash, skb,
+ sizeof(struct udphdr));
+ if (sk2) {
+ result = sk2;
+ select_ok = false;
+ goto found;
+ }
}
matches = 1;
}
@@ -563,6 +568,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
int score, badness, matches = 0, reuseport = 0;
+ bool select_ok = true;
u32 hash = 0;
rcu_read_lock();
@@ -601,14 +607,18 @@ begin:
badness = score;
reuseport = sk->sk_reuseport;
if (reuseport) {
- struct sock *sk2;
hash = udp_ehashfn(net, daddr, hnum,
saddr, sport);
- sk2 = reuseport_select_sock(sk, hash, skb,
+ if (select_ok) {
+ struct sock *sk2;
+
+ sk2 = reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
- if (sk2) {
- result = sk2;
- goto found;
+ if (sk2) {
+ result = sk2;
+ select_ok = false;
+ goto found;
+ }
}
matches = 1;
}
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-26 10:54:01 +0000