summaryrefslogtreecommitdiff
path: root/net/mptcp/protocol.h
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp/protocol.h')
-rw-r--r--net/mptcp/protocol.h247
1 files changed, 186 insertions, 61 deletions
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 07f6242afc1a..ad21925af061 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -12,8 +12,7 @@
#include <net/inet_connection_sock.h>
#include <uapi/linux/mptcp.h>
#include <net/genetlink.h>
-
-#include "mptcp_pm_gen.h"
+#include <net/rstreason.h>
#define MPTCP_SUPPORTED_VERSION 1
@@ -113,10 +112,9 @@
#define MPTCP_RST_TRANSIENT BIT(0)
/* MPTCP socket atomic flags */
-#define MPTCP_NOSPACE 1
-#define MPTCP_WORK_RTX 2
-#define MPTCP_FALLBACK_DONE 4
-#define MPTCP_WORK_CLOSE_SUBFLOW 5
+#define MPTCP_WORK_RTX 1
+#define MPTCP_FALLBACK_DONE 2
+#define MPTCP_WORK_CLOSE_SUBFLOW 3
/* MPTCP socket release cb flags */
#define MPTCP_PUSH_PENDING 1
@@ -151,22 +149,24 @@ struct mptcp_options_received {
u32 subflow_seq;
u16 data_len;
__sum16 csum;
- u16 suboptions;
+ struct_group(status,
+ u16 suboptions;
+ u16 use_map:1,
+ dsn64:1,
+ data_fin:1,
+ use_ack:1,
+ ack64:1,
+ mpc_map:1,
+ reset_reason:4,
+ reset_transient:1,
+ echo:1,
+ backup:1,
+ deny_join_id0:1,
+ __unused:2;
+ );
+ u8 join_id;
u32 token;
u32 nonce;
- u16 use_map:1,
- dsn64:1,
- data_fin:1,
- use_ack:1,
- ack64:1,
- mpc_map:1,
- reset_reason:4,
- reset_transient:1,
- echo:1,
- backup:1,
- deny_join_id0:1,
- __unused:2;
- u8 join_id;
u64 thmac;
u8 hmac[MPTCPOPT_HMAC_LEN];
struct mptcp_addr_info addr;
@@ -238,6 +238,12 @@ struct mptcp_pm_data {
struct mptcp_rm_list rm_list_rx;
};
+struct mptcp_pm_local {
+ struct mptcp_addr_info addr;
+ u8 flags;
+ int ifindex;
+};
+
struct mptcp_pm_addr_entry {
struct list_head list;
struct mptcp_addr_info addr;
@@ -260,8 +266,10 @@ struct mptcp_data_frag {
struct mptcp_sock {
/* inet_connection_sock must be the first member */
struct inet_connection_sock sk;
- u64 local_key;
- u64 remote_key;
+ u64 local_key; /* protected by the first subflow socket lock
+ * lockless access read
+ */
+ u64 remote_key; /* same as above */
u64 write_seq;
u64 bytes_sent;
u64 snd_nxt;
@@ -281,6 +289,9 @@ struct mptcp_sock {
u64 bytes_acked;
u64 snd_una;
u64 wnd_end;
+ u32 last_data_sent;
+ u32 last_data_recv;
+ u32 last_ack_recv;
unsigned long timer_ival;
u32 token;
int rmem_released;
@@ -306,6 +317,10 @@ struct mptcp_sock {
in_accept_queue:1,
free_first:1,
rcvspace_init:1;
+ u32 notsent_lowat;
+ int keepalive_cnt;
+ int keepalive_idle;
+ int keepalive_intvl;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct rb_root out_of_order_queue;
@@ -341,12 +356,30 @@ struct mptcp_sock {
#define mptcp_for_each_subflow_safe(__msk, __subflow, __tmp) \
list_for_each_entry_safe(__subflow, __tmp, &((__msk)->conn_list), node)
+extern struct genl_family mptcp_genl_family;
+
static inline void msk_owned_by_me(const struct mptcp_sock *msk)
{
sock_owned_by_me((const struct sock *)msk);
}
+#ifdef CONFIG_DEBUG_NET
+/* MPTCP-specific: we might (indirectly) call this helper with the wrong sk */
+#undef tcp_sk
+#define tcp_sk(ptr) ({ \
+ typeof(ptr) _ptr = (ptr); \
+ WARN_ON(_ptr->sk_protocol != IPPROTO_TCP); \
+ container_of_const(_ptr, struct tcp_sock, inet_conn.icsk_inet.sk); \
+})
+#define mptcp_sk(ptr) ({ \
+ typeof(ptr) _ptr = (ptr); \
+ WARN_ON(_ptr->sk_protocol != IPPROTO_MPTCP); \
+ container_of_const(_ptr, struct mptcp_sock, sk.icsk_inet.sk); \
+})
+
+#else /* !CONFIG_DEBUG_NET */
#define mptcp_sk(ptr) container_of_const(ptr, struct mptcp_sock, sk.icsk_inet.sk)
+#endif
/* the msk socket don't use the backlog, also account for the bulk
* free memory
@@ -361,6 +394,11 @@ static inline int mptcp_win_from_space(const struct sock *sk, int space)
return __tcp_win_from_space(mptcp_sk(sk)->scaling_ratio, space);
}
+static inline int mptcp_space_from_win(const struct sock *sk, int win)
+{
+ return __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, win);
+}
+
static inline int __mptcp_space(const struct sock *sk)
{
return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk));
@@ -400,7 +438,7 @@ static inline struct mptcp_data_frag *mptcp_rtx_head(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- if (msk->snd_una == READ_ONCE(msk->snd_nxt))
+ if (msk->snd_una == msk->snd_nxt)
return NULL;
return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list);
@@ -418,6 +456,7 @@ struct mptcp_subflow_request_sock {
u16 mp_capable : 1,
mp_join : 1,
backup : 1,
+ request_bkup : 1,
csum_reqd : 1,
allow_join_id0 : 1;
u8 local_id;
@@ -476,7 +515,6 @@ struct mptcp_subflow_context {
request_bkup : 1,
mp_capable : 1, /* remote is MPTCP capable */
mp_join : 1, /* remote is JOINing */
- fully_established : 1, /* path validated */
pm_notified : 1, /* PM hook called for established status */
conn_finished : 1,
map_valid : 1,
@@ -493,9 +531,13 @@ struct mptcp_subflow_context {
stale : 1, /* unable to snd/rcv data, do not use for xmit */
valid_csum_seen : 1, /* at least one csum validated */
is_mptfo : 1, /* subflow is doing TFO */
- __unused : 10;
+ close_event_done : 1, /* has done the post-closed part */
+ mpc_drop : 1, /* the MPC option has been dropped in a rtx */
+ __unused : 9;
bool data_avail;
bool scheduled;
+ bool pm_listener; /* a listener managed by the kernel PM? */
+ bool fully_established; /* path validated */
u32 remote_nonce;
u64 thmac;
u32 local_nonce;
@@ -538,7 +580,7 @@ struct mptcp_subflow_context {
static inline struct mptcp_subflow_context *
mptcp_subflow_ctx(const struct sock *sk)
{
- struct inet_connection_sock *icsk = inet_csk(sk);
+ const struct inet_connection_sock *icsk = inet_csk(sk);
/* Use RCU on icsk_ulp_data only for sock diag code */
return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
@@ -558,6 +600,43 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow)
WRITE_ONCE(subflow->local_id, -1);
}
+/* Convert reset reasons in MPTCP to enum sk_rst_reason type */
+static inline enum sk_rst_reason
+sk_rst_convert_mptcp_reason(u32 reason)
+{
+ switch (reason) {
+ case MPTCP_RST_EUNSPEC:
+ return SK_RST_REASON_MPTCP_RST_EUNSPEC;
+ case MPTCP_RST_EMPTCP:
+ return SK_RST_REASON_MPTCP_RST_EMPTCP;
+ case MPTCP_RST_ERESOURCE:
+ return SK_RST_REASON_MPTCP_RST_ERESOURCE;
+ case MPTCP_RST_EPROHIBIT:
+ return SK_RST_REASON_MPTCP_RST_EPROHIBIT;
+ case MPTCP_RST_EWQ2BIG:
+ return SK_RST_REASON_MPTCP_RST_EWQ2BIG;
+ case MPTCP_RST_EBADPERF:
+ return SK_RST_REASON_MPTCP_RST_EBADPERF;
+ case MPTCP_RST_EMIDDLEBOX:
+ return SK_RST_REASON_MPTCP_RST_EMIDDLEBOX;
+ default:
+ /* It should not happen, or else errors may occur
+ * in MPTCP layer
+ */
+ return SK_RST_REASON_ERROR;
+ }
+}
+
+static inline void
+mptcp_send_active_reset_reason(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ enum sk_rst_reason reason;
+
+ reason = sk_rst_convert_mptcp_reason(subflow->reset_reason);
+ tcp_send_active_reset(sk, GFP_ATOMIC, reason);
+}
+
static inline u64
mptcp_subflow_get_map_offset(const struct mptcp_subflow_context *subflow)
{
@@ -622,6 +701,12 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net);
unsigned int mptcp_close_timeout(const struct sock *sk);
int mptcp_get_pm_type(const struct net *net);
const char *mptcp_get_scheduler(const struct net *net);
+
+void mptcp_active_disable(struct sock *sk);
+bool mptcp_active_should_disable(struct sock *ssk);
+void mptcp_active_enable(struct sock *sk);
+
+void mptcp_get_available_schedulers(char *buf, size_t maxlen);
void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
struct mptcp_subflow_context *subflow,
const struct mptcp_options_received *mp_opt);
@@ -649,7 +734,7 @@ bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr);
/* called with sk socket lock held */
-int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
+int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local,
const struct mptcp_addr_info *remote);
int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
struct socket **new_sock);
@@ -677,10 +762,15 @@ static inline u64 mptcp_data_avail(const struct mptcp_sock *msk)
static inline bool mptcp_epollin_ready(const struct sock *sk)
{
+ u64 data_avail = mptcp_data_avail(mptcp_sk(sk));
+
+ if (!data_avail)
+ return false;
+
/* mptcp doesn't have to deal with small skbs in the receive queue,
- * at it can always coalesce them
+ * as it can always coalesce them
*/
- return (mptcp_data_avail(mptcp_sk(sk)) >= sk->sk_rcvlowat) ||
+ return (data_avail >= sk->sk_rcvlowat) ||
(mem_cgroup_sockets_enabled && sk->sk_memcg &&
mem_cgroup_under_socket_pressure(sk->sk_memcg)) ||
READ_ONCE(tcp_memory_pressure);
@@ -697,7 +787,7 @@ static inline bool __tcp_can_send(const struct sock *ssk)
static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
{
/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
- if (subflow->request_join && !subflow->fully_established)
+ if (subflow->request_join && !READ_ONCE(subflow->fully_established))
return false;
return __tcp_can_send(mptcp_subflow_tcp_sock(subflow));
@@ -790,14 +880,36 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt);
}
+static inline u32 mptcp_notsent_lowat(const struct sock *sk)
+{
+ struct net *net = sock_net(sk);
+ u32 val;
+
+ val = READ_ONCE(mptcp_sk(sk)->notsent_lowat);
+ return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat);
+}
+
+static inline bool mptcp_stream_memory_free(const struct sock *sk, int wake)
+{
+ const struct mptcp_sock *msk = mptcp_sk(sk);
+ u32 notsent_bytes;
+
+ notsent_bytes = READ_ONCE(msk->write_seq) - READ_ONCE(msk->snd_nxt);
+ return (notsent_bytes << wake) < mptcp_notsent_lowat(sk);
+}
+
+static inline bool __mptcp_stream_is_writeable(const struct sock *sk, int wake)
+{
+ return mptcp_stream_memory_free(sk, wake) &&
+ __sk_stream_is_writeable(sk, wake);
+}
+
static inline void mptcp_write_space(struct sock *sk)
{
- if (sk_stream_is_writeable(sk)) {
- /* pairs with memory barrier in mptcp_poll */
- smp_mb();
- if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags))
- sk_stream_write_space(sk);
- }
+ /* pairs with memory barrier in mptcp_poll */
+ smp_mb();
+ if (mptcp_stream_memory_free(sk, 1))
+ sk_stream_write_space(sk);
}
static inline void __mptcp_sync_sndbuf(struct sock *sk)
@@ -808,7 +920,7 @@ static inline void __mptcp_sync_sndbuf(struct sock *sk)
if (sk->sk_userlocks & SOCK_SNDBUF_LOCK)
return;
- new_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[0];
+ new_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[0]);
mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
ssk_sndbuf = READ_ONCE(mptcp_subflow_tcp_sock(subflow)->sk_sndbuf);
@@ -901,6 +1013,8 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr);
void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
+bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *remote);
void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk);
void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
const struct mptcp_rm_list *rm_list);
@@ -920,29 +1034,19 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
struct mptcp_pm_add_entry *
mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk,
const struct mptcp_addr_info *addr);
-int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
- unsigned int id,
- u8 *flags, int *ifindex);
-int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
- u8 *flags, int *ifindex);
-int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
- unsigned int id,
- u8 *flags, int *ifindex);
-int mptcp_pm_set_flags(struct net *net, struct nlattr *token,
- struct mptcp_pm_addr_entry *loc,
- struct mptcp_pm_addr_entry *rem, u8 bkup);
-int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup);
-int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token,
- struct mptcp_pm_addr_entry *loc,
- struct mptcp_pm_addr_entry *rem, u8 bkup);
+bool mptcp_lookup_subflow_by_saddr(const struct list_head *list,
+ const struct mptcp_addr_info *saddr);
+bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *addr);
+int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info);
+int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info);
+int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info);
int mptcp_pm_announce_addr(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr,
bool echo);
int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
-void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list);
-void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
- struct list_head *rm_list);
+void mptcp_pm_remove_addr_entry(struct mptcp_sock *msk,
+ struct mptcp_pm_addr_entry *entry);
void mptcp_free_local_addr_list(struct mptcp_sock *msk);
@@ -958,6 +1062,8 @@ void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflo
const struct mptcp_options_received *mp_opt);
void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow,
struct request_sock *req);
+int mptcp_nl_fill_addr(struct sk_buff *skb,
+ struct mptcp_pm_addr_entry *entry);
static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
{
@@ -1022,6 +1128,18 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc);
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb);
+int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
+ struct netlink_callback *cb);
+int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
+ struct netlink_callback *cb);
+int mptcp_pm_get_addr(struct sk_buff *skb, struct genl_info *info);
+int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info);
+int mptcp_userspace_pm_get_addr(struct sk_buff *skb,
+ struct genl_info *info);
static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow)
{
@@ -1034,8 +1152,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
void __init mptcp_pm_nl_init(void);
void mptcp_pm_nl_work(struct mptcp_sock *msk);
-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
- const struct mptcp_rm_list *rm_list);
unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);
@@ -1055,7 +1171,6 @@ static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk)
spin_unlock_bh(&msk->pm.lock);
}
-void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk);
void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk);
static inline struct mptcp_ext *mptcp_get_ext(const struct sk_buff *skb)
@@ -1081,9 +1196,11 @@ static inline bool mptcp_check_fallback(const struct sock *sk)
static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
{
if (__mptcp_check_fallback(msk)) {
- pr_debug("TCP fallback already done (msk=%p)", msk);
+ pr_debug("TCP fallback already done (msk=%p)\n", msk);
return;
}
+ if (WARN_ON_ONCE(!READ_ONCE(msk->allow_infinite_fallback)))
+ return;
set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
}
@@ -1117,7 +1234,15 @@ static inline void mptcp_do_fallback(struct sock *ssk)
}
}
-#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
+#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)\n", __func__, a)
+
+static inline void mptcp_subflow_early_fallback(struct mptcp_sock *msk,
+ struct mptcp_subflow_context *subflow)
+{
+ pr_fallback(msk);
+ subflow->request_mptcp = 0;
+ __mptcp_do_fallback(msk);
+}
static inline bool mptcp_check_infinite_map(struct sk_buff *skb)
{
generated by cgit (git 2.34.1) at 2025-07-23 13:21:40 +0000