aboutsummaryrefslogtreecommitdiff
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/diag.c12
-rw-r--r--net/mptcp/fastopen.c6
-rw-r--r--net/mptcp/mptcp_diag.c2
-rw-r--r--net/mptcp/mptcp_pm_gen.c7
-rw-r--r--net/mptcp/mptcp_pm_gen.h2
-rw-r--r--net/mptcp/options.c31
-rw-r--r--net/mptcp/pm.c29
-rw-r--r--net/mptcp/pm_netlink.c184
-rw-r--r--net/mptcp/pm_userspace.c259
-rw-r--r--net/mptcp/protocol.c193
-rw-r--r--net/mptcp/protocol.h133
-rw-r--r--net/mptcp/sockopt.c73
-rw-r--r--net/mptcp/subflow.c98
-rw-r--r--net/mptcp/token_test.c7
14 files changed, 702 insertions, 334 deletions
diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c
index a536586742f2..3ae46b545d2c 100644
--- a/net/mptcp/diag.c
+++ b/net/mptcp/diag.c
@@ -10,20 +10,24 @@
#include <linux/net.h>
#include <linux/inet_diag.h>
#include <net/netlink.h>
-#include <uapi/linux/mptcp.h>
#include "protocol.h"
-static int subflow_get_info(const struct sock *sk, struct sk_buff *skb)
+static int subflow_get_info(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *sf;
struct nlattr *start;
u32 flags = 0;
+ bool slow;
int err;
+ if (inet_sk_state_load(sk) == TCP_LISTEN)
+ return 0;
+
start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP);
if (!start)
return -EMSGSIZE;
+ slow = lock_sock_fast(sk);
rcu_read_lock();
sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data);
if (!sf) {
@@ -63,17 +67,19 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb)
sf->map_data_len) ||
nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) ||
nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) ||
- nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, sf->local_id)) {
+ nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) {
err = -EMSGSIZE;
goto nla_failure;
}
rcu_read_unlock();
+ unlock_sock_fast(sk, slow);
nla_nest_end(skb, start);
return 0;
nla_failure:
rcu_read_unlock();
+ unlock_sock_fast(sk, slow);
nla_nest_cancel(skb, start);
return err;
}
diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index 74698582a285..ad28da655f8b 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -59,13 +59,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
mptcp_data_unlock(sk);
}
-void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt)
+void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt)
{
struct sock *sk = (struct sock *)msk;
struct sk_buff *skb;
- mptcp_data_lock(sk);
skb = skb_peek_tail(&sk->sk_receive_queue);
if (skb) {
WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);
@@ -77,5 +76,4 @@ void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_
}
pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq);
- mptcp_data_unlock(sk);
}
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index 5409c2ea3f57..0566dd793810 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -10,7 +10,6 @@
#include <linux/net.h>
#include <linux/inet_diag.h>
#include <net/netlink.h>
-#include <uapi/linux/mptcp.h>
#include "protocol.h"
static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
@@ -225,6 +224,7 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
}
static const struct inet_diag_handler mptcp_diag_handler = {
+ .owner = THIS_MODULE,
.dump = mptcp_diag_dump,
.dump_one = mptcp_diag_dump_one,
.idiag_get_info = mptcp_diag_get_info,
diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c
index 670da7822e6c..c30a2a90a192 100644
--- a/net/mptcp/mptcp_pm_gen.c
+++ b/net/mptcp/mptcp_pm_gen.c
@@ -32,8 +32,9 @@ const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]
};
/* MPTCP_PM_CMD_GET_ADDR - do */
-const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = {
- [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy),
+const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ATTR_TOKEN + 1] = {
+ [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy),
+ [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, },
};
/* MPTCP_PM_CMD_FLUSH_ADDRS - do */
@@ -110,7 +111,7 @@ const struct genl_ops mptcp_pm_nl_ops[11] = {
.doit = mptcp_pm_nl_get_addr_doit,
.dumpit = mptcp_pm_nl_get_addr_dumpit,
.policy = mptcp_pm_get_addr_nl_policy,
- .maxattr = MPTCP_PM_ENDPOINT_ADDR,
+ .maxattr = MPTCP_PM_ATTR_TOKEN,
.flags = GENL_UNS_ADMIN_PERM,
},
{
diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h
index ac9fc7225b6a..e24258f6f819 100644
--- a/net/mptcp/mptcp_pm_gen.h
+++ b/net/mptcp/mptcp_pm_gen.h
@@ -18,7 +18,7 @@ extern const struct nla_policy mptcp_pm_add_addr_nl_policy[MPTCP_PM_ENDPOINT_ADD
extern const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1];
-extern const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1];
+extern const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ATTR_TOKEN + 1];
extern const struct nla_policy mptcp_pm_flush_addrs_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1];
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index d2527d189a79..27ca42c77b02 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -689,8 +689,8 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
if (!echo) {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX);
- opts->ahmac = add_addr_generate_hmac(msk->local_key,
- msk->remote_key,
+ opts->ahmac = add_addr_generate_hmac(READ_ONCE(msk->local_key),
+ READ_ONCE(msk->remote_key),
&opts->addr);
} else {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX);
@@ -792,7 +792,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk,
*size = TCPOLEN_MPTCP_FASTCLOSE;
opts->suboptions |= OPTION_MPTCP_FASTCLOSE;
- opts->rcvr_key = msk->remote_key;
+ opts->rcvr_key = READ_ONCE(msk->remote_key);
pr_debug("FASTCLOSE key=%llu", opts->rcvr_key);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);
@@ -962,9 +962,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
/* subflows are fully established as soon as we get any
* additional ack, including ADD_ADDR.
*/
- subflow->fully_established = 1;
- WRITE_ONCE(msk->fully_established, true);
- goto check_notify;
+ goto set_fully_established;
}
/* If the first established packet does not contain MP_CAPABLE + data
@@ -983,10 +981,13 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
if (mp_opt->deny_join_id0)
WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
-set_fully_established:
if (unlikely(!READ_ONCE(msk->pm.server_side)))
pr_warn_once("bogus mpc option on established client sk");
- mptcp_subflow_fully_established(subflow, mp_opt);
+
+set_fully_established:
+ mptcp_data_lock((struct sock *)msk);
+ __mptcp_subflow_fully_established(msk, subflow, mp_opt);
+ mptcp_data_unlock((struct sock *)msk);
check_notify:
/* if the subflow is not already linked into the conn_list, we can't
@@ -1030,7 +1031,7 @@ u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq)
static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una)
{
msk->bytes_acked += new_snd_una - msk->snd_una;
- msk->snd_una = new_snd_una;
+ WRITE_ONCE(msk->snd_una, new_snd_una);
}
static void ack_update_msk(struct mptcp_sock *msk,
@@ -1057,10 +1058,10 @@ static void ack_update_msk(struct mptcp_sock *msk,
new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd;
if (after64(new_wnd_end, msk->wnd_end))
- msk->wnd_end = new_wnd_end;
+ WRITE_ONCE(msk->wnd_end, new_wnd_end);
/* this assumes mptcp_incoming_options() is invoked after tcp_ack() */
- if (after64(msk->wnd_end, READ_ONCE(msk->snd_nxt)))
+ if (after64(msk->wnd_end, snd_nxt))
__mptcp_check_push(sk, ssk);
if (after64(new_snd_una, old_snd_una)) {
@@ -1071,7 +1072,7 @@ static void ack_update_msk(struct mptcp_sock *msk,
trace_ack_update_msk(mp_opt->data_ack,
old_snd_una, new_snd_una,
- new_wnd_end, msk->wnd_end);
+ new_wnd_end, READ_ONCE(msk->wnd_end));
}
bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit)
@@ -1099,8 +1100,8 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
if (mp_opt->echo)
return true;
- hmac = add_addr_generate_hmac(msk->remote_key,
- msk->local_key,
+ hmac = add_addr_generate_hmac(READ_ONCE(msk->remote_key),
+ READ_ONCE(msk->local_key),
&mp_opt->addr);
pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n",
@@ -1147,7 +1148,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
if (unlikely(mp_opt.suboptions != OPTION_MPTCP_DSS)) {
if ((mp_opt.suboptions & OPTION_MPTCP_FASTCLOSE) &&
- msk->local_key == mp_opt.rcvr_key) {
+ READ_ONCE(msk->local_key) == mp_opt.rcvr_key) {
WRITE_ONCE(msk->rcv_fastclose, true);
mptcp_schedule_work((struct sock *)msk);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSERX);
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 4ae19113b8eb..55406720c607 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -6,7 +6,6 @@
#define pr_fmt(fmt) "MPTCP: " fmt
#include <linux/kernel.h>
-#include <net/tcp.h>
#include <net/mptcp.h>
#include "protocol.h"
@@ -77,7 +76,7 @@ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int
{
struct mptcp_pm_data *pm = &msk->pm;
- pr_debug("msk=%p, token=%u side=%d", msk, msk->token, server_side);
+ pr_debug("msk=%p, token=%u side=%d", msk, READ_ONCE(msk->token), server_side);
WRITE_ONCE(pm->server_side, server_side);
mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC);
@@ -441,13 +440,27 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id
return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, 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_get_addr(struct sk_buff *skb, struct genl_info *info)
{
- if (token)
- return mptcp_userspace_pm_set_flags(net, token, loc, rem, bkup);
- return mptcp_pm_nl_set_flags(net, loc, bkup);
+ if (info->attrs[MPTCP_PM_ATTR_TOKEN])
+ return mptcp_userspace_pm_get_addr(skb, info);
+ return mptcp_pm_nl_get_addr(skb, info);
+}
+
+int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb)
+{
+ const struct genl_info *info = genl_info_dump(cb);
+
+ if (info->attrs[MPTCP_PM_ATTR_TOKEN])
+ return mptcp_userspace_pm_dump_addr(msg, cb);
+ return mptcp_pm_nl_dump_addr(msg, cb);
+}
+
+int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
+{
+ if (info->attrs[MPTCP_PM_ATTR_TOKEN])
+ return mptcp_userspace_pm_set_flags(skb, info);
+ return mptcp_pm_nl_set_flags(skb, info);
}
void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 287a60381eae..5c17d39146ea 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -8,19 +8,13 @@
#include <linux/inet.h>
#include <linux/kernel.h>
-#include <net/tcp.h>
#include <net/inet_common.h>
#include <net/netns/generic.h>
#include <net/mptcp.h>
-#include <net/genetlink.h>
-#include <uapi/linux/mptcp.h>
#include "protocol.h"
#include "mib.h"
-/* forward declaration */
-static struct genl_family mptcp_genl_family;
-
static int pm_nl_pernet_id;
struct mptcp_pm_add_entry {
@@ -396,19 +390,6 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
}
}
-static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr,
- const struct mptcp_addr_info *addr)
-{
- int i;
-
- for (i = 0; i < nr; i++) {
- if (addrs[i].id == addr->id)
- return true;
- }
-
- return false;
-}
-
/* Fill all the remote addresses into the array addrs[],
* and return the array size.
*/
@@ -440,18 +421,34 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
msk->pm.subflows++;
addrs[i++] = remote;
} else {
+ DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+
+ /* Forbid creation of new subflows matching existing
+ * ones, possibly already created by incoming ADD_ADDR
+ */
+ bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+ mptcp_for_each_subflow(msk, subflow)
+ if (READ_ONCE(subflow->local_id) == local->id)
+ __set_bit(subflow->remote_id, unavail_id);
+
mptcp_for_each_subflow(msk, subflow) {
ssk = mptcp_subflow_tcp_sock(subflow);
remote_address((struct sock_common *)ssk, &addrs[i]);
- addrs[i].id = subflow->remote_id;
+ addrs[i].id = READ_ONCE(subflow->remote_id);
if (deny_id0 && !addrs[i].id)
continue;
+ if (test_bit(addrs[i].id, unavail_id))
+ continue;
+
if (!mptcp_pm_addr_families_match(sk, local, &addrs[i]))
continue;
- if (!lookup_address_in_vec(addrs, i, &addrs[i]) &&
- msk->pm.subflows < subflows_max) {
+ if (msk->pm.subflows < subflows_max) {
+ /* forbid creating multiple address towards
+ * this id
+ */
+ __set_bit(addrs[i].id, unavail_id);
msk->pm.subflows++;
i++;
}
@@ -502,15 +499,12 @@ __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id)
}
static struct mptcp_pm_addr_entry *
-__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info,
- bool lookup_by_id)
+__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
{
struct mptcp_pm_addr_entry *entry;
list_for_each_entry(entry, &pernet->local_addr_list, list) {
- if ((!lookup_by_id &&
- mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) ||
- (lookup_by_id && entry->addr.id == info->id))
+ if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port))
return entry;
}
return NULL;
@@ -540,7 +534,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
mptcp_local_address((struct sock_common *)msk->first, &mpc_addr);
rcu_read_lock();
- entry = __lookup_addr(pernet, &mpc_addr, false);
+ entry = __lookup_addr(pernet, &mpc_addr);
if (entry) {
__clear_bit(entry->addr.id, msk->pm.id_avail_bitmap);
msk->mpc_endpoint_id = entry->addr.id;
@@ -799,18 +793,18 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
mptcp_for_each_subflow_safe(msk, subflow, tmp) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ u8 remote_id = READ_ONCE(subflow->remote_id);
int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
- u8 id = subflow->local_id;
+ u8 id = subflow_get_local_id(subflow);
- if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id)
+ if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id)
continue;
if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id))
continue;
pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
- i, rm_id, subflow->local_id, subflow->remote_id,
- msk->mpc_endpoint_id);
+ i, rm_id, id, remote_id, msk->mpc_endpoint_id);
spin_unlock_bh(&msk->pm.lock);
mptcp_subflow_shutdown(sk, ssk, how);
@@ -901,7 +895,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
}
static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
- struct mptcp_pm_addr_entry *entry)
+ struct mptcp_pm_addr_entry *entry,
+ bool needs_id)
{
struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
unsigned int addr_max;
@@ -949,7 +944,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
}
}
- if (!entry->addr.id) {
+ if (!entry->addr.id && needs_id) {
find_next:
entry->addr.id = find_next_zero_bit(pernet->id_bitmap,
MPTCP_PM_MAX_ADDR_ID + 1,
@@ -960,7 +955,7 @@ find_next:
}
}
- if (!entry->addr.id)
+ if (!entry->addr.id && needs_id)
goto out;
__set_bit(entry->addr.id, pernet->id_bitmap);
@@ -1092,7 +1087,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
entry->ifindex = 0;
entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
entry->lsk = NULL;
- ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
+ ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true);
if (ret < 0)
kfree(entry);
@@ -1285,6 +1280,18 @@ next:
return 0;
}
+static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr,
+ struct genl_info *info)
+{
+ struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];
+
+ if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr,
+ mptcp_pm_address_nl_policy, info->extack) &&
+ tb[MPTCP_PM_ADDR_ATTR_ID])
+ return true;
+ return false;
+}
+
int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
@@ -1326,7 +1333,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
goto out_free;
}
}
- ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
+ ret = mptcp_pm_nl_append_new_local_addr(pernet, entry,
+ !mptcp_pm_has_addr_attr_id(attr, info));
if (ret < 0) {
GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret);
goto out_free;
@@ -1533,8 +1541,8 @@ 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)
+static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
+ struct list_head *rm_list)
{
struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 };
struct mptcp_pm_addr_entry *entry;
@@ -1619,8 +1627,8 @@ int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info)
return 0;
}
-static int mptcp_nl_fill_addr(struct sk_buff *skb,
- struct mptcp_pm_addr_entry *entry)
+int mptcp_nl_fill_addr(struct sk_buff *skb,
+ struct mptcp_pm_addr_entry *entry)
{
struct mptcp_addr_info *addr = &entry->addr;
struct nlattr *attr;
@@ -1658,7 +1666,7 @@ nla_put_failure:
return -EMSGSIZE;
}
-int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info)
+int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
@@ -1708,8 +1716,13 @@ fail:
return ret;
}
-int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg,
- struct netlink_callback *cb)
+int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ return mptcp_pm_get_addr(skb, info);
+}
+
+int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
+ struct netlink_callback *cb)
{
struct net *net = sock_net(msg->sk);
struct mptcp_pm_addr_entry *entry;
@@ -1751,6 +1764,12 @@ int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg,
return msg->len;
}
+int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ return mptcp_pm_dump_addr(msg, cb);
+}
+
static int parse_limit(struct genl_info *info, int id, unsigned int *limit)
{
struct nlattr *attr = info->attrs[id];
@@ -1865,66 +1884,63 @@ next:
return ret;
}
-int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup)
+int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info)
{
- struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);
+ struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, };
+ struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
MPTCP_PM_ADDR_FLAG_FULLMESH;
+ struct net *net = sock_net(skb->sk);
struct mptcp_pm_addr_entry *entry;
+ struct pm_nl_pernet *pernet;
u8 lookup_by_id = 0;
+ u8 bkup = 0;
+ int ret;
- if (addr->addr.family == AF_UNSPEC) {
+ pernet = pm_nl_get_pernet(net);
+
+ ret = mptcp_pm_parse_entry(attr, info, false, &addr);
+ if (ret < 0)
+ return ret;
+
+ if (addr.addr.family == AF_UNSPEC) {
lookup_by_id = 1;
- if (!addr->addr.id)
+ if (!addr.addr.id) {
+ GENL_SET_ERR_MSG(info, "missing required inputs");
return -EOPNOTSUPP;
+ }
}
+ if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
+ bkup = 1;
+
spin_lock_bh(&pernet->lock);
- entry = __lookup_addr(pernet, &addr->addr, lookup_by_id);
+ entry = lookup_by_id ? __lookup_addr_by_id(pernet, addr.addr.id) :
+ __lookup_addr(pernet, &addr.addr);
if (!entry) {
spin_unlock_bh(&pernet->lock);
+ GENL_SET_ERR_MSG(info, "address not found");
return -EINVAL;
}
- if ((addr->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
+ if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
spin_unlock_bh(&pernet->lock);
+ GENL_SET_ERR_MSG(info, "invalid addr flags");
return -EINVAL;
}
- changed = (addr->flags ^ entry->flags) & mask;
- entry->flags = (entry->flags & ~mask) | (addr->flags & mask);
- *addr = *entry;
+ changed = (addr.flags ^ entry->flags) & mask;
+ entry->flags = (entry->flags & ~mask) | (addr.flags & mask);
+ addr = *entry;
spin_unlock_bh(&pernet->lock);
- mptcp_nl_set_flags(net, &addr->addr, bkup, changed);
+ mptcp_nl_set_flags(net, &addr.addr, bkup, changed);
return 0;
}
int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info)
{
- struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, };
- struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, };
- struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
- struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
- struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
- struct net *net = sock_net(skb->sk);
- u8 bkup = 0;
- int ret;
-
- ret = mptcp_pm_parse_entry(attr, info, false, &addr);
- if (ret < 0)
- return ret;
-
- if (attr_rem) {
- ret = mptcp_pm_parse_entry(attr_rem, info, false, &remote);
- if (ret < 0)
- return ret;
- }
-
- if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
- bkup = 1;
-
- return mptcp_pm_set_flags(net, token, &addr, &remote, bkup);
+ return mptcp_pm_set_flags(skb, info);
}
static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp)
@@ -1980,7 +1996,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk)
if (WARN_ON_ONCE(!sf))
return -EINVAL;
- if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id))
+ if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf)))
return -EMSGSIZE;
if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id))
@@ -1997,7 +2013,7 @@ static int mptcp_event_put_token_and_ssk(struct sk_buff *skb,
const struct mptcp_subflow_context *sf;
u8 sk_err;
- if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token))
+ if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)))
return -EMSGSIZE;
if (mptcp_event_add_subflow(skb, ssk))
@@ -2055,7 +2071,7 @@ static int mptcp_event_created(struct sk_buff *skb,
const struct mptcp_sock *msk,
const struct sock *ssk)
{
- int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token);
+ int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token));
if (err)
return err;
@@ -2083,7 +2099,7 @@ void mptcp_event_addr_removed(const struct mptcp_sock *msk, uint8_t id)
if (!nlh)
goto nla_put_failure;
- if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token))
+ if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)))
goto nla_put_failure;
if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, id))
@@ -2118,7 +2134,7 @@ void mptcp_event_addr_announced(const struct sock *ssk,
if (!nlh)
goto nla_put_failure;
- if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token))
+ if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)))
goto nla_put_failure;
if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, info->id))
@@ -2234,7 +2250,7 @@ void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk,
goto nla_put_failure;
break;
case MPTCP_EVENT_CLOSED:
- if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token) < 0)
+ if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)) < 0)
goto nla_put_failure;
break;
case MPTCP_EVENT_ANNOUNCED:
@@ -2264,7 +2280,7 @@ nla_put_failure:
nlmsg_free(skb);
}
-static struct genl_family mptcp_genl_family __ro_after_init = {
+struct genl_family mptcp_genl_family __ro_after_init = {
.name = MPTCP_PM_NAME,
.version = MPTCP_PM_VER,
.netnsok = true,
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index efecbe3cf415..9f5d422d5ef6 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -26,7 +26,8 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk)
}
static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
- struct mptcp_pm_addr_entry *entry)
+ struct mptcp_pm_addr_entry *entry,
+ bool needs_id)
{
DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
struct mptcp_pm_addr_entry *match = NULL;
@@ -41,7 +42,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
spin_lock_bh(&msk->pm.lock);
list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) {
addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true);
- if (addr_match && entry->addr.id == 0)
+ if (addr_match && entry->addr.id == 0 && needs_id)
entry->addr.id = e->addr.id;
id_match = (e->addr.id == entry->addr.id);
if (addr_match && id_match) {
@@ -64,7 +65,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
}
*e = *entry;
- if (!e->addr.id)
+ if (!e->addr.id && needs_id)
e->addr.id = find_next_zero_bit(id_bitmap,
MPTCP_PM_MAX_ADDR_ID + 1,
1);
@@ -105,19 +106,26 @@ static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk,
return -EINVAL;
}
+static struct mptcp_pm_addr_entry *
+mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id)
+{
+ struct mptcp_pm_addr_entry *entry;
+
+ list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
+ if (entry->addr.id == id)
+ return entry;
+ }
+ return NULL;
+}
+
int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
unsigned int id,
u8 *flags, int *ifindex)
{
- struct mptcp_pm_addr_entry *entry, *match = NULL;
+ struct mptcp_pm_addr_entry *match;
spin_lock_bh(&msk->pm.lock);
- list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
- if (id == entry->addr.id) {
- match = entry;
- break;
- }
- }
+ match = mptcp_userspace_pm_lookup_addr_by_id(msk, id);
spin_unlock_bh(&msk->pm.lock);
if (match) {
*flags = match->flags;
@@ -130,10 +138,21 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
struct mptcp_addr_info *skc)
{
- struct mptcp_pm_addr_entry new_entry;
+ struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry;
__be16 msk_sport = ((struct inet_sock *)
inet_sk((struct sock *)msk))->inet_sport;
+ spin_lock_bh(&msk->pm.lock);
+ list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) {
+ if (mptcp_addresses_equal(&e->addr, skc, false)) {
+ entry = e;
+ break;
+ }
+ }
+ spin_unlock_bh(&msk->pm.lock);
+ if (entry)
+ return entry->addr.id;
+
memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry));
new_entry.addr = *skc;
new_entry.addr.id = 0;
@@ -142,7 +161,7 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
if (new_entry.addr.port == msk_sport)
new_entry.addr.port = 0;
- return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry);
+ return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true);
}
int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
@@ -187,7 +206,7 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
goto announce_err;
}
- err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val);
+ err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val, false);
if (err < 0) {
GENL_SET_ERR_MSG(info, "did not match address and id");
goto announce_err;
@@ -222,7 +241,7 @@ static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk,
lock_sock(sk);
mptcp_for_each_subflow(msk, subflow) {
- if (subflow->local_id == 0) {
+ if (READ_ONCE(subflow->local_id) == 0) {
has_id_0 = true;
break;
}
@@ -249,7 +268,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
struct nlattr *id = info->attrs[MPTCP_PM_ATTR_LOC_ID];
- struct mptcp_pm_addr_entry *match = NULL;
+ struct mptcp_pm_addr_entry *match;
struct mptcp_pm_addr_entry *entry;
struct mptcp_sock *msk;
LIST_HEAD(free_list);
@@ -286,13 +305,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
lock_sock(sk);
- list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
- if (entry->addr.id == id_val) {
- match = entry;
- break;
- }
- }
-
+ match = mptcp_userspace_pm_lookup_addr_by_id(msk, id_val);
if (!match) {
GENL_SET_ERR_MSG(info, "address with specified id not found");
release_sock(sk);
@@ -322,7 +335,6 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR];
struct mptcp_pm_addr_entry local = { 0 };
struct mptcp_addr_info addr_r;
- struct mptcp_addr_info addr_l;
struct mptcp_sock *msk;
int err = -EINVAL;
struct sock *sk;
@@ -348,26 +360,32 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
goto create_err;
}
- err = mptcp_pm_parse_addr(laddr, info, &addr_l);
+ err = mptcp_pm_parse_entry(laddr, info, true, &local);
if (err < 0) {
NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr");
goto create_err;
}
+ if (local.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
+ GENL_SET_ERR_MSG(info, "invalid addr flags");
+ err = -EINVAL;
+ goto create_err;
+ }
+ local.flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW;
+
err = mptcp_pm_parse_addr(raddr, info, &addr_r);
if (err < 0) {
NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr");
goto create_err;
}
- if (!mptcp_pm_addr_families_match(sk, &addr_l, &addr_r)) {
+ if (!mptcp_pm_addr_families_match(sk, &local.addr, &addr_r)) {
GENL_SET_ERR_MSG(info, "families mismatch");
err = -EINVAL;
goto create_err;
}
- local.addr = addr_l;
- err = mptcp_userspace_pm_append_new_local_addr(msk, &local);
+ err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false);
if (err < 0) {
GENL_SET_ERR_MSG(info, "did not match address and id");
goto create_err;
@@ -375,7 +393,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
lock_sock(sk);
- err = __mptcp_subflow_connect(sk, &addr_l, &addr_r);
+ err = __mptcp_subflow_connect(sk, &local.addr, &addr_r);
release_sock(sk);
@@ -483,6 +501,16 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info
goto destroy_err;
}
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+ if (addr_l.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) {
+ ipv6_addr_set_v4mapped(addr_l.addr.s_addr, &addr_l.addr6);
+ addr_l.family = AF_INET6;
+ }
+ if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr6)) {
+ ipv6_addr_set_v4mapped(addr_r.addr.s_addr, &addr_r.addr6);
+ addr_r.family = AF_INET6;
+ }
+#endif
if (addr_l.family != addr_r.family) {
GENL_SET_ERR_MSG(info, "address families do not match");
err = -EINVAL;
@@ -518,35 +546,194 @@ destroy_err:
return err;
}
-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)
+int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
{
+ struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, };
+ struct mptcp_pm_addr_entry rem = { .addr = { .family = AF_UNSPEC }, };
+ struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
+ struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
+ struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
+ struct net *net = sock_net(skb->sk);
struct mptcp_sock *msk;
int ret = -EINVAL;
struct sock *sk;
u32 token_val;
+ u8 bkup = 0;
token_val = nla_get_u32(token);
msk = mptcp_token_get_sock(net, token_val);
- if (!msk)
+ if (!msk) {
+ NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token");
return ret;
+ }
sk = (struct sock *)msk;
- if (!mptcp_pm_is_userspace(msk))
+ if (!mptcp_pm_is_userspace(msk)) {
+ GENL_SET_ERR_MSG(info, "userspace PM not selected");
+ goto set_flags_err;
+ }
+
+ ret = mptcp_pm_parse_entry(attr, info, false, &loc);
+ if (ret < 0)
goto set_flags_err;
- if (loc->addr.family == AF_UNSPEC ||
- rem->addr.family == AF_UNSPEC)
+ if (attr_rem) {
+ ret = mptcp_pm_parse_entry(attr_rem, info, false, &rem);
+ if (ret < 0)
+ goto set_flags_err;
+ }
+
+ if (loc.addr.family == AF_UNSPEC ||
+ rem.addr.family == AF_UNSPEC) {
+ GENL_SET_ERR_MSG(info, "invalid address families");
+ ret = -EINVAL;
goto set_flags_err;
+ }
+
+ if (loc.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
+ bkup = 1;
lock_sock(sk);
- ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc->addr, &rem->addr, bkup);
+ ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc.addr, &rem.addr, bkup);
release_sock(sk);
set_flags_err:
sock_put(sk);
return ret;
}
+
+int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ struct id_bitmap {
+ DECLARE_BITMAP(map, MPTCP_PM_MAX_ADDR_ID + 1);
+ } *bitmap;
+ const struct genl_info *info = genl_info_dump(cb);
+ struct net *net = sock_net(msg->sk);
+ struct mptcp_pm_addr_entry *entry;
+ struct mptcp_sock *msk;
+ struct nlattr *token;
+ int ret = -EINVAL;
+ struct sock *sk;
+ void *hdr;
+
+ bitmap = (struct id_bitmap *)cb->ctx;
+ token = info->attrs[MPTCP_PM_ATTR_TOKEN];
+
+ msk = mptcp_token_get_sock(net, nla_get_u32(token));
+ if (!msk) {
+ NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token");
+ return ret;
+ }
+
+ sk = (struct sock *)msk;
+
+ if (!mptcp_pm_is_userspace(msk)) {
+ GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected");
+ goto out;
+ }
+
+ lock_sock(sk);
+ spin_lock_bh(&msk->pm.lock);
+ list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
+ if (test_bit(entry->addr.id, bitmap->map))
+ continue;
+
+ hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, &mptcp_genl_family,
+ NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR);
+ if (!hdr)
+ break;
+
+ if (mptcp_nl_fill_addr(msg, entry) < 0) {
+ genlmsg_cancel(msg, hdr);
+ break;
+ }
+
+ __set_bit(entry->addr.id, bitmap->map);
+ genlmsg_end(msg, hdr);
+ }
+ spin_unlock_bh(&msk->pm.lock);
+ release_sock(sk);
+ ret = msg->len;
+
+out:
+ sock_put(sk);
+ return ret;
+}
+
+int mptcp_userspace_pm_get_addr(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
+ struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
+ struct mptcp_pm_addr_entry addr, *entry;
+ struct net *net = sock_net(skb->sk);
+ struct mptcp_sock *msk;
+ struct sk_buff *msg;
+ int ret = -EINVAL;
+ struct sock *sk;
+ void *reply;
+
+ msk = mptcp_token_get_sock(net, nla_get_u32(token));
+ if (!msk) {
+ NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token");
+ return ret;
+ }
+
+ sk = (struct sock *)msk;
+
+ if (!mptcp_pm_is_userspace(msk)) {
+ GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected");
+ goto out;
+ }
+
+ ret = mptcp_pm_parse_entry(attr, info, false, &addr);
+ if (ret < 0)
+ goto out;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0,
+ info->genlhdr->cmd);
+ if (!reply) {
+ GENL_SET_ERR_MSG(info, "not enough space in Netlink message");
+ ret = -EMSGSIZE;
+ goto fail;
+ }
+
+ lock_sock(sk);
+ spin_lock_bh(&msk->pm.lock);
+ entry = mptcp_userspace_pm_lookup_addr_by_id(msk, addr.addr.id);
+ if (!entry) {
+ GENL_SET_ERR_MSG(info, "address not found");
+ ret = -EINVAL;
+ goto unlock_fail;
+ }
+
+ ret = mptcp_nl_fill_addr(msg, entry);
+ if (ret)
+ goto unlock_fail;
+
+ genlmsg_end(msg, reply);
+ ret = genlmsg_reply(msg, info);
+ spin_unlock_bh(&msk->pm.lock);
+ release_sock(sk);
+ sock_put(sk);
+ return ret;
+
+unlock_fail:
+ spin_unlock_bh(&msk->pm.lock);
+ release_sock(sk);
+fail:
+ nlmsg_free(msg);
+out:
+ sock_put(sk);
+ return ret;
+}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3ed4709a7509..3a1967bc7bad 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -15,7 +15,6 @@
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/protocol.h>
-#include <net/tcp.h>
#include <net/tcp_states.h>
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
#include <net/transp_v6.h>
@@ -85,7 +84,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
subflow->subflow_id = msk->subflow_id++;
/* This is the first subflow, always with id 0 */
- subflow->local_id_valid = 1;
+ WRITE_ONCE(subflow->local_id, 0);
mptcp_sock_graft(msk->first, sk->sk_socket);
iput(SOCK_INODE(ssock));
@@ -410,6 +409,7 @@ static void mptcp_close_wake_up(struct sock *sk)
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
}
+/* called under the msk socket lock */
static bool mptcp_pending_data_fin_ack(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -441,16 +441,17 @@ static void mptcp_check_data_fin_ack(struct sock *sk)
}
}
+/* can be called with no lock acquired */
static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq)
{
struct mptcp_sock *msk = mptcp_sk(sk);
if (READ_ONCE(msk->rcv_data_fin) &&
- ((1 << sk->sk_state) &
+ ((1 << inet_sk_state_load(sk)) &
(TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2))) {
u64 rcv_data_fin_seq = READ_ONCE(msk->rcv_data_fin_seq);
- if (msk->ack_seq == rcv_data_fin_seq) {
+ if (READ_ONCE(msk->ack_seq) == rcv_data_fin_seq) {
if (seq)
*seq = rcv_data_fin_seq;
@@ -748,7 +749,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
__skb_queue_tail(&sk->sk_receive_queue, skb);
}
msk->bytes_received += end_seq - msk->ack_seq;
- msk->ack_seq = end_seq;
+ WRITE_ONCE(msk->ack_seq, end_seq);
moved = true;
}
return moved;
@@ -985,6 +986,7 @@ static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag)
put_page(dfrag->page);
}
+/* called under both the msk socket lock and the data lock */
static void __mptcp_clean_una(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1033,13 +1035,15 @@ static void __mptcp_clean_una(struct sock *sk)
msk->recovery = false;
out:
- if (snd_una == READ_ONCE(msk->snd_nxt) &&
- snd_una == READ_ONCE(msk->write_seq)) {
+ if (snd_una == msk->snd_nxt && snd_una == msk->write_seq) {
if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk))
mptcp_stop_rtx_timer(sk);
} else {
mptcp_reset_rtx_timer(sk);
}
+
+ if (mptcp_pending_data_fin_ack(sk))
+ mptcp_schedule_work(sk);
}
static void __mptcp_clean_una_wakeup(struct sock *sk)
@@ -1260,6 +1264,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
mpext = mptcp_get_ext(skb);
if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) {
TCP_SKB_CB(skb)->eor = 1;
+ tcp_mark_push(tcp_sk(ssk), skb);
goto alloc_skb;
}
@@ -1499,14 +1504,17 @@ static void mptcp_update_post_push(struct mptcp_sock *msk,
*/
if (likely(after64(snd_nxt_new, msk->snd_nxt))) {
msk->bytes_sent += snd_nxt_new - msk->snd_nxt;
- msk->snd_nxt = snd_nxt_new;
+ WRITE_ONCE(msk->snd_nxt, snd_nxt_new);
}
}
void mptcp_check_and_set_pending(struct sock *sk)
{
- if (mptcp_send_head(sk))
- mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
+ if (mptcp_send_head(sk)) {
+ mptcp_data_lock(sk);
+ mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING);
+ mptcp_data_unlock(sk);
+ }
}
static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
@@ -1683,15 +1691,6 @@ out:
}
}
-static void mptcp_set_nospace(struct sock *sk)
-{
- /* enable autotune */
- set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-
- /* will be cleared on avail space */
- set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags);
-}
-
static int mptcp_disconnect(struct sock *sk, int flags);
static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
@@ -1762,6 +1761,30 @@ static int do_copy_data_nocache(struct sock *sk, int copy,
return 0;
}
+/* open-code sk_stream_memory_free() plus sent limit computation to
+ * avoid indirect calls in fast-path.
+ * Called under the msk socket lock, so we can avoid a bunch of ONCE
+ * annotations.
+ */
+static u32 mptcp_send_limit(const struct sock *sk)
+{
+ const struct mptcp_sock *msk = mptcp_sk(sk);
+ u32 limit, not_sent;
+
+ if (sk->sk_wmem_queued >= READ_ONCE(sk->sk_sndbuf))
+ return 0;
+
+ limit = mptcp_notsent_lowat(sk);
+ if (limit == UINT_MAX)
+ return UINT_MAX;
+
+ not_sent = msk->write_seq - msk->snd_nxt;
+ if (not_sent >= limit)
+ return 0;
+
+ return limit - not_sent;
+}
+
static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1806,6 +1829,12 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
struct mptcp_data_frag *dfrag;
bool dfrag_collapsed;
size_t psize, offset;
+ u32 copy_limit;
+
+ /* ensure fitting the notsent_lowat() constraint */
+ copy_limit = mptcp_send_limit(sk);
+ if (!copy_limit)
+ goto wait_for_memory;
/* reuse tail pfrag, if possible, or carve a new one from the
* page allocator
@@ -1813,9 +1842,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
dfrag = mptcp_pending_tail(sk);
dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
if (!dfrag_collapsed) {
- if (!sk_stream_memory_free(sk))
- goto wait_for_memory;
-
if (!mptcp_page_frag_refill(sk, pfrag))
goto wait_for_memory;
@@ -1830,6 +1856,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
offset = dfrag->offset + dfrag->data_len;
psize = pfrag->size - offset;
psize = min_t(size_t, psize, msg_data_left(msg));
+ psize = min_t(size_t, psize, copy_limit);
total_ts = psize + frag_truesize;
if (!sk_wmem_schedule(sk, total_ts))
@@ -1865,7 +1892,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
continue;
wait_for_memory:
- mptcp_set_nospace(sk);
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
__mptcp_push_pending(sk, msg->msg_flags);
ret = sk_stream_wait_memory(sk, &timeo);
if (ret)
@@ -1960,6 +1987,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
if (copied <= 0)
return;
+ if (!msk->rcvspace_init)
+ mptcp_rcv_space_init(msk, msk->first);
+
msk->rcvq_space.copied += copied;
mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC);
@@ -2108,7 +2138,7 @@ static unsigned int mptcp_inq_hint(const struct sock *sk)
skb = skb_peek(&msk->receive_queue);
if (skb) {
- u64 hint_val = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
+ u64 hint_val = READ_ONCE(msk->ack_seq) - MPTCP_SKB_CB(skb)->map_seq;
if (hint_val >= INT_MAX)
return INT_MAX;
@@ -2314,9 +2344,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
if (__mptcp_check_fallback(msk))
return false;
- if (tcp_rtx_and_write_queues_empty(sk))
- return false;
-
/* the closing socket has some data untransmitted and/or unacked:
* some data in the mptcp rtx queue has not really xmitted yet.
* keep it simple and re-inject the whole mptcp level rtx queue
@@ -2755,7 +2782,7 @@ static void __mptcp_init_sock(struct sock *sk)
__skb_queue_head_init(&msk->receive_queue);
msk->out_of_order_queue = RB_ROOT;
msk->first_pending = NULL;
- msk->rmem_fwd_alloc = 0;
+ WRITE_ONCE(msk->rmem_fwd_alloc, 0);
WRITE_ONCE(msk->rmem_released, 0);
msk->timer_ival = TCP_RTO_MIN;
msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO;
@@ -2971,7 +2998,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
sk->sk_prot->destroy(sk);
- WARN_ON_ONCE(msk->rmem_fwd_alloc);
+ WARN_ON_ONCE(READ_ONCE(msk->rmem_fwd_alloc));
WARN_ON_ONCE(msk->rmem_released);
sk_stream_kill_queues(sk);
xfrm_sk_free_policy(sk);
@@ -3145,22 +3172,22 @@ static int mptcp_disconnect(struct sock *sk, int flags)
mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
WRITE_ONCE(msk->flags, 0);
msk->cb_flags = 0;
- msk->push_pending = 0;
msk->recovery = false;
- msk->can_ack = false;
- msk->fully_established = false;
- msk->rcv_data_fin = false;
- msk->snd_data_fin_enable = false;
- msk->rcv_fastclose = false;
- msk->use_64bit_ack = false;
- msk->bytes_consumed = 0;
+ WRITE_ONCE(msk->can_ack, false);
+ WRITE_ONCE(msk->fully_established, false);
+ WRITE_ONCE(msk->rcv_data_fin, false);
+ WRITE_ONCE(msk->snd_data_fin_enable, false);
+ WRITE_ONCE(msk->rcv_fastclose, false);
+ WRITE_ONCE(msk->use_64bit_ack, false);
WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
mptcp_pm_data_reset(msk);
mptcp_ca_reset(sk);
+ msk->bytes_consumed = 0;
msk->bytes_acked = 0;
msk->bytes_received = 0;
msk->bytes_sent = 0;
msk->bytes_retrans = 0;
+ msk->rcvspace_init = 0;
WRITE_ONCE(sk->sk_shutdown, 0);
sk_error_report(sk);
@@ -3174,8 +3201,50 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
}
+
+static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk)
+{
+ const struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6_txoptions *opt;
+ struct ipv6_pinfo *newnp;
+
+ newnp = inet6_sk(newsk);
+
+ rcu_read_lock();
+ opt = rcu_dereference(np->opt);
+ if (opt) {
+ opt = ipv6_dup_options(newsk, opt);
+ if (!opt)
+ net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__);
+ }
+ RCU_INIT_POINTER(newnp->opt, opt);
+ rcu_read_unlock();
+}
#endif
+static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk)
+{
+ struct ip_options_rcu *inet_opt, *newopt = NULL;
+ const struct inet_sock *inet = inet_sk(sk);
+ struct inet_sock *newinet;
+
+ newinet = inet_sk(newsk);
+
+ rcu_read_lock();
+ inet_opt = rcu_dereference(inet->inet_opt);
+ if (inet_opt) {
+ newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
+ inet_opt->opt.optlen, GFP_ATOMIC);
+ if (newopt)
+ memcpy(newopt, inet_opt, sizeof(*inet_opt) +
+ inet_opt->opt.optlen);
+ else
+ net_warn_ratelimited("%s: Failed to copy ip options\n", __func__);
+ }
+ RCU_INIT_POINTER(newinet->inet_opt, newopt);
+ rcu_read_unlock();
+}
+
struct sock *mptcp_sk_clone_init(const struct sock *sk,
const struct mptcp_options_received *mp_opt,
struct sock *ssk,
@@ -3183,6 +3252,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
+ struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk;
if (!nsk)
@@ -3195,18 +3265,25 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
__mptcp_init_sock(nsk);
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+ if (nsk->sk_family == AF_INET6)
+ mptcp_copy_ip6_options(nsk, sk);
+ else
+#endif
+ mptcp_copy_ip_options(nsk, sk);
+
msk = mptcp_sk(nsk);
- msk->local_key = subflow_req->local_key;
- msk->token = subflow_req->token;
+ WRITE_ONCE(msk->local_key, subflow_req->local_key);
+ WRITE_ONCE(msk->token, subflow_req->token);
msk->in_accept_queue = 1;
WRITE_ONCE(msk->fully_established, false);
if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD)
WRITE_ONCE(msk->csum_enabled, true);
- msk->write_seq = subflow_req->idsn + 1;
- msk->snd_nxt = msk->write_seq;
- msk->snd_una = msk->write_seq;
- msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
+ WRITE_ONCE(msk->write_seq, subflow_req->idsn + 1);
+ WRITE_ONCE(msk->snd_nxt, msk->write_seq);
+ WRITE_ONCE(msk->snd_una, msk->write_seq);
+ WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
mptcp_init_sched(msk, mptcp_sk(sk)->sched);
@@ -3223,7 +3300,8 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
/* The msk maintain a ref to each subflow in the connections list */
WRITE_ONCE(msk->first, ssk);
- list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list);
+ subflow = mptcp_subflow_ctx(ssk);
+ list_add(&subflow->node, &msk->conn_list);
sock_hold(ssk);
/* new mpc subflow takes ownership of the newly
@@ -3238,6 +3316,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
__mptcp_propagate_sndbuf(nsk, ssk);
mptcp_rcv_space_init(msk, ssk);
+
+ if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK)
+ __mptcp_subflow_fully_established(msk, subflow, mp_opt);
bh_unlock_sock(nsk);
/* note: the newly allocated socket refcount is 2 now */
@@ -3248,6 +3329,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
{
const struct tcp_sock *tp = tcp_sk(ssk);
+ msk->rcvspace_init = 1;
msk->rcvq_space.copied = 0;
msk->rcvq_space.rtt_us = 0;
@@ -3258,8 +3340,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
TCP_INIT_CWND * tp->advmss);
if (msk->rcvq_space.space == 0)
msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
-
- WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
}
void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
@@ -3306,9 +3386,6 @@ void __mptcp_data_acked(struct sock *sk)
__mptcp_clean_una(sk);
else
__set_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->cb_flags);
-
- if (mptcp_pending_data_fin_ack(sk))
- mptcp_schedule_work(sk);
}
void __mptcp_check_push(struct sock *sk, struct sock *ssk)
@@ -3333,8 +3410,7 @@ static void mptcp_release_cb(struct sock *sk)
struct mptcp_sock *msk = mptcp_sk(sk);
for (;;) {
- unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
- msk->push_pending;
+ unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED);
struct list_head join_list;
if (!flags)
@@ -3350,7 +3426,6 @@ static void mptcp_release_cb(struct sock *sk)
* datapath acquires the msk socket spinlock while helding
* the subflow socket lock
*/
- msk->push_pending = 0;
msk->cb_flags &= ~flags;
spin_unlock_bh(&sk->sk_lock.slock);
@@ -3478,13 +3553,8 @@ void mptcp_finish_connect(struct sock *ssk)
* accessing the field below
*/
WRITE_ONCE(msk->local_key, subflow->local_key);
- WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
- WRITE_ONCE(msk->snd_nxt, msk->write_seq);
- WRITE_ONCE(msk->snd_una, msk->write_seq);
mptcp_pm_new_connection(msk, ssk, 0);
-
- mptcp_rcv_space_init(msk, ssk);
}
void mptcp_sock_graft(struct sock *sk, struct socket *parent)
@@ -3717,6 +3787,7 @@ static struct proto mptcp_prot = {
.unhash = mptcp_unhash,
.get_port = mptcp_get_port,
.forward_alloc_get = mptcp_forward_alloc_get,
+ .stream_memory_free = mptcp_stream_memory_free,
.sockets_allocated = &mptcp_sockets_allocated,
.memory_allocated = &tcp_memory_allocated,
@@ -3890,12 +3961,12 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
{
struct sock *sk = (struct sock *)msk;
- if (sk_stream_is_writeable(sk))
+ if (__mptcp_stream_is_writeable(sk, 1))
return EPOLLOUT | EPOLLWRNORM;
- mptcp_set_nospace(sk);
- smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
- if (sk_stream_is_writeable(sk))
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ smp_mb__after_atomic(); /* NOSPACE is changed by mptcp_write_space() */
+ if (__mptcp_stream_is_writeable(sk, 1))
return EPOLLOUT | EPOLLWRNORM;
return 0;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 3517f2d24a22..a10ebf3ee10a 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -113,10 +113,9 @@
#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
@@ -260,8 +259,10 @@ 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;
@@ -286,7 +287,6 @@ struct mptcp_sock {
int rmem_released;
unsigned long flags;
unsigned long cb_flags;
- unsigned long push_pending;
bool recovery; /* closing subflow write queue reinjected */
bool can_ack;
bool fully_established;
@@ -305,7 +305,9 @@ struct mptcp_sock {
nodelay:1,
fastopening:1,
in_accept_queue:1,
- free_first:1;
+ free_first:1,
+ rcvspace_init:1;
+ u32 notsent_lowat;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct rb_root out_of_order_queue;
@@ -341,12 +343,30 @@ 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
@@ -400,7 +420,7 @@ 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);
@@ -491,10 +511,9 @@ struct mptcp_subflow_context {
remote_key_valid : 1, /* received the peer key from */
disposable : 1, /* ctx can be free at ulp release time */
stale : 1, /* unable to snd/rcv data, do not use for xmit */
- local_id_valid : 1, /* local_id is correctly initialized */
valid_csum_seen : 1, /* at least one csum validated */
is_mptfo : 1, /* subflow is doing TFO */
- __unused : 9;
+ __unused : 10;
bool data_avail;
bool scheduled;
u32 remote_nonce;
@@ -505,7 +524,7 @@ struct mptcp_subflow_context {
u8 hmac[MPTCPOPT_HMAC_LEN]; /* MPJ subflow only */
u64 iasn; /* initial ack sequence number, MPC subflows only */
};
- u8 local_id;
+ s16 local_id; /* if negative not initialized yet */
u8 remote_id;
u8 reset_seen:1;
u8 reset_transient:1;
@@ -556,6 +575,7 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow)
{
memset(&subflow->reset, 0, sizeof(subflow->reset));
subflow->request_mptcp = 1;
+ WRITE_ONCE(subflow->local_id, -1);
}
static inline u64
@@ -622,8 +642,9 @@ 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_subflow_fully_established(struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt);
+void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
+ struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt);
bool __mptcp_retransmit_pending_data(struct sock *sk);
void mptcp_check_and_set_pending(struct sock *sk);
void __mptcp_push_pending(struct sock *sk, unsigned int flags);
@@ -789,6 +810,38 @@ 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)
+{
+ /* 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)
{
struct mptcp_subflow_context *subflow;
@@ -797,7 +850,7 @@ 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);
@@ -807,6 +860,7 @@ static inline void __mptcp_sync_sndbuf(struct sock *sk)
/* the msk max wmem limit is <nr_subflows> * tcp wmem[2] */
WRITE_ONCE(sk->sk_sndbuf, new_sndbuf);
+ mptcp_write_space(sk);
}
/* The called held both the msk socket and the subflow socket locks,
@@ -837,16 +891,6 @@ static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk)
local_bh_enable();
}
-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);
- }
-}
-
void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags);
#define MPTCP_TOKEN_MAX_RETRIES 4
@@ -926,21 +970,15 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int
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);
+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_free_local_addr_list(struct mptcp_sock *msk);
@@ -952,10 +990,12 @@ void mptcp_event_pm_listener(const struct sock *ssk,
enum mptcp_event_type event);
bool mptcp_userspace_pm_active(const struct mptcp_sock *msk);
-void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt);
+void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+ 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)
{
@@ -1020,6 +1060,24 @@ 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);
+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)
+{
+ int local_id = READ_ONCE(subflow->local_id);
+
+ if (local_id < 0)
+ return 0;
+ return local_id;
+}
void __init mptcp_pm_nl_init(void);
void mptcp_pm_nl_work(struct mptcp_sock *msk);
@@ -1128,7 +1186,8 @@ static inline bool subflow_simultaneous_connect(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) &&
+ return (1 << sk->sk_state) &
+ (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING) &&
is_active_ssk(subflow) &&
!subflow->conn_finished;
}
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index c40f1428e602..dcd1c76d2a3b 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -624,20 +624,11 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t
return ret;
}
-static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optval,
- unsigned int optlen)
+static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val)
{
struct mptcp_subflow_context *subflow;
struct sock *sk = (struct sock *)msk;
- int val;
- if (optlen < sizeof(int))
- return -EINVAL;
-
- if (copy_from_sockptr(&val, optval, sizeof(val)))
- return -EFAULT;
-
- lock_sock(sk);
sockopt_seq_inc(msk);
msk->cork = !!val;
mptcp_for_each_subflow(msk, subflow) {
@@ -649,25 +640,15 @@ static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optva
}
if (!val)
mptcp_check_and_set_pending(sk);
- release_sock(sk);
return 0;
}
-static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t optval,
- unsigned int optlen)
+static int __mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, int val)
{
struct mptcp_subflow_context *subflow;
struct sock *sk = (struct sock *)msk;
- int val;
-
- if (optlen < sizeof(int))
- return -EINVAL;
-
- if (copy_from_sockptr(&val, optval, sizeof(val)))
- return -EFAULT;
- lock_sock(sk);
sockopt_seq_inc(msk);
msk->nodelay = !!val;
mptcp_for_each_subflow(msk, subflow) {
@@ -679,8 +660,6 @@ static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t op
}
if (val)
mptcp_check_and_set_pending(sk);
- release_sock(sk);
-
return 0;
}
@@ -803,25 +782,10 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
int ret, val;
switch (optname) {
- case TCP_INQ:
- ret = mptcp_get_int_option(msk, optval, optlen, &val);
- if (ret)
- return ret;
- if (val < 0 || val > 1)
- return -EINVAL;
-
- lock_sock(sk);
- msk->recvmsg_inq = !!val;
- release_sock(sk);
- return 0;
case TCP_ULP:
return -EOPNOTSUPP;
case TCP_CONGESTION:
return mptcp_setsockopt_sol_tcp_congestion(msk, optval, optlen);
- case TCP_CORK:
- return mptcp_setsockopt_sol_tcp_cork(msk, optval, optlen);
- case TCP_NODELAY:
- return mptcp_setsockopt_sol_tcp_nodelay(msk, optval, optlen);
case TCP_DEFER_ACCEPT:
/* See tcp.c: TCP_DEFER_ACCEPT does not fail */
mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen);
@@ -834,7 +798,34 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
optval, optlen);
}
- return -EOPNOTSUPP;
+ ret = mptcp_get_int_option(msk, optval, optlen, &val);
+ if (ret)
+ return ret;
+
+ lock_sock(sk);
+ switch (optname) {
+ case TCP_INQ:
+ if (val < 0 || val > 1)
+ ret = -EINVAL;
+ else
+ msk->recvmsg_inq = !!val;
+ break;
+ case TCP_NOTSENT_LOWAT:
+ WRITE_ONCE(msk->notsent_lowat, val);
+ mptcp_write_space(sk);
+ break;
+ case TCP_CORK:
+ ret = __mptcp_setsockopt_sol_tcp_cork(msk, val);
+ break;
+ case TCP_NODELAY:
+ ret = __mptcp_setsockopt_sol_tcp_nodelay(msk, val);
+ break;
+ default:
+ ret = -ENOPROTOOPT;
+ }
+
+ release_sock(sk);
+ return ret;
}
int mptcp_setsockopt(struct sock *sk, int level, int optname,
@@ -942,7 +933,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
mptcp_data_unlock(sk);
slow = lock_sock_fast(sk);
- info->mptcpi_csum_enabled = msk->csum_enabled;
+ info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled);
info->mptcpi_token = msk->token;
info->mptcpi_write_seq = msk->write_seq;
info->mptcpi_retransmits = inet_csk(sk)->icsk_retransmits;
@@ -1349,6 +1340,8 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
return mptcp_put_int_option(msk, optval, optlen, msk->cork);
case TCP_NODELAY:
return mptcp_put_int_option(msk, optval, optlen, msk->nodelay);
+ case TCP_NOTSENT_LOWAT:
+ return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat);
}
return -EOPNOTSUPP;
}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 0dcb721c89d1..1626dd20c68f 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -15,13 +15,11 @@
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/protocol.h>
-#include <net/tcp.h>
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
#include <net/ip6_route.h>
#include <net/transp_v6.h>
#endif
#include <net/mptcp.h>
-#include <uapi/linux/mptcp.h>
#include "protocol.h"
#include "mib.h"
@@ -75,7 +73,8 @@ static void subflow_req_create_thmac(struct mptcp_subflow_request_sock *subflow_
get_random_bytes(&subflow_req->local_nonce, sizeof(u32));
- subflow_generate_hmac(msk->local_key, msk->remote_key,
+ subflow_generate_hmac(READ_ONCE(msk->local_key),
+ READ_ONCE(msk->remote_key),
subflow_req->local_nonce,
subflow_req->remote_nonce, hmac);
@@ -421,29 +420,26 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc
void __mptcp_sync_state(struct sock *sk, int state)
{
+ struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
+ struct sock *ssk = msk->first;
+
+ subflow = mptcp_subflow_ctx(ssk);
+ __mptcp_propagate_sndbuf(sk, ssk);
+ if (!msk->rcvspace_init)
+ mptcp_rcv_space_init(msk, ssk);
- __mptcp_propagate_sndbuf(sk, msk->first);
if (sk->sk_state == TCP_SYN_SENT) {
+ /* subflow->idsn is always available is TCP_SYN_SENT state,
+ * even for the FASTOPEN scenarios
+ */
+ WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
+ WRITE_ONCE(msk->snd_nxt, msk->write_seq);
mptcp_set_state(sk, state);
sk->sk_state_change(sk);
}
}
-static void mptcp_propagate_state(struct sock *sk, struct sock *ssk)
-{
- struct mptcp_sock *msk = mptcp_sk(sk);
-
- mptcp_data_lock(sk);
- if (!sock_owned_by_user(sk)) {
- __mptcp_sync_state(sk, ssk->sk_state);
- } else {
- msk->pending_state = ssk->sk_state;
- __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
- }
- mptcp_data_unlock(sk);
-}
-
static void subflow_set_remote_key(struct mptcp_sock *msk,
struct mptcp_subflow_context *subflow,
const struct mptcp_options_received *mp_opt)
@@ -465,6 +461,31 @@ static void subflow_set_remote_key(struct mptcp_sock *msk,
atomic64_set(&msk->rcv_wnd_sent, subflow->iasn);
}
+static void mptcp_propagate_state(struct sock *sk, struct sock *ssk,
+ struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ mptcp_data_lock(sk);
+ if (mp_opt) {
+ /* Options are available only in the non fallback cases
+ * avoid updating rx path fields otherwise
+ */
+ WRITE_ONCE(msk->snd_una, subflow->idsn + 1);
+ WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd);
+ subflow_set_remote_key(msk, subflow, mp_opt);
+ }
+
+ if (!sock_owned_by_user(sk)) {
+ __mptcp_sync_state(sk, ssk->sk_state);
+ } else {
+ msk->pending_state = ssk->sk_state;
+ __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
+ }
+ mptcp_data_unlock(sk);
+}
+
static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -499,10 +520,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
if (mp_opt.deny_join_id0)
WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
subflow->mp_capable = 1;
- subflow_set_remote_key(msk, subflow, &mp_opt);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
mptcp_finish_connect(sk);
- mptcp_propagate_state(parent, sk);
+ mptcp_propagate_state(parent, sk, subflow, &mp_opt);
} else if (subflow->request_join) {
u8 hmac[SHA256_DIGEST_SIZE];
@@ -514,7 +534,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->backup = mp_opt.backup;
subflow->thmac = mp_opt.thmac;
subflow->remote_nonce = mp_opt.nonce;
- subflow->remote_id = mp_opt.join_id;
+ WRITE_ONCE(subflow->remote_id, mp_opt.join_id);
pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d",
subflow, subflow->thmac, subflow->remote_nonce,
subflow->backup);
@@ -545,8 +565,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
}
} else if (mptcp_check_fallback(sk)) {
fallback:
- mptcp_rcv_space_init(msk, sk);
- mptcp_propagate_state(parent, sk);
+ mptcp_propagate_state(parent, sk, subflow, NULL);
}
return;
@@ -557,8 +576,8 @@ do_reset:
static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id)
{
- subflow->local_id = local_id;
- subflow->local_id_valid = 1;
+ WARN_ON_ONCE(local_id < 0 || local_id > 255);
+ WRITE_ONCE(subflow->local_id, local_id);
}
static int subflow_chk_local_id(struct sock *sk)
@@ -567,7 +586,7 @@ static int subflow_chk_local_id(struct sock *sk)
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
int err;
- if (likely(subflow->local_id_valid))
+ if (likely(subflow->local_id >= 0))
return 0;
err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk);
@@ -694,7 +713,8 @@ static bool subflow_hmac_valid(const struct request_sock *req,
if (!msk)
return false;
- subflow_generate_hmac(msk->remote_key, msk->local_key,
+ subflow_generate_hmac(READ_ONCE(msk->remote_key),
+ READ_ONCE(msk->local_key),
subflow_req->remote_nonce,
subflow_req->local_nonce, hmac);
@@ -731,17 +751,16 @@ void mptcp_subflow_drop_ctx(struct sock *ssk)
kfree_rcu(ctx, rcu);
}
-void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt)
+void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
+ struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt)
{
- struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-
subflow_set_remote_key(msk, subflow, mp_opt);
subflow->fully_established = 1;
WRITE_ONCE(msk->fully_established, true);
if (subflow->is_mptfo)
- mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
+ __mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
}
static struct sock *subflow_syn_recv_sock(const struct sock *sk,
@@ -834,7 +853,6 @@ create_child:
* mpc option
*/
if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) {
- mptcp_subflow_fully_established(ctx, &mp_opt);
mptcp_pm_fully_established(owner, child);
ctx->pm_notified = 1;
}
@@ -1530,8 +1548,8 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
mptcp_pm_get_flags_and_ifindex_by_id(msk, local_id,
&flags, &ifindex);
subflow->remote_key_valid = 1;
- subflow->remote_key = msk->remote_key;
- subflow->local_key = msk->local_key;
+ subflow->remote_key = READ_ONCE(msk->remote_key);
+ subflow->local_key = READ_ONCE(msk->local_key);
subflow->token = msk->token;
mptcp_info2sockaddr(loc, &addr, ssk->sk_family);
@@ -1549,7 +1567,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
remote_token, local_id, remote_id);
subflow->remote_token = remote_token;
- subflow->remote_id = remote_id;
+ WRITE_ONCE(subflow->remote_id, remote_id);
subflow->request_join = 1;
subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
subflow->subflow_id = msk->subflow_id++;
@@ -1713,6 +1731,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
pr_debug("subflow=%p", ctx);
ctx->tcp_sock = sk;
+ WRITE_ONCE(ctx->local_id, -1);
return ctx;
}
@@ -1744,10 +1763,9 @@ static void subflow_state_change(struct sock *sk)
msk = mptcp_sk(parent);
if (subflow_simultaneous_connect(sk)) {
mptcp_do_fallback(sk);
- mptcp_rcv_space_init(msk, sk);
pr_fallback(msk);
subflow->conn_finished = 1;
- mptcp_propagate_state(parent, sk);
+ mptcp_propagate_state(parent, sk, subflow, NULL);
}
/* as recvmsg() does not acquire the subflow socket for ssk selection
@@ -1949,14 +1967,14 @@ static void subflow_ulp_clone(const struct request_sock *req,
new_ctx->idsn = subflow_req->idsn;
/* this is the first subflow, id is always 0 */
- new_ctx->local_id_valid = 1;
+ subflow_set_local_id(new_ctx, 0);
} else if (subflow_req->mp_join) {
new_ctx->ssn_offset = subflow_req->ssn_offset;
new_ctx->mp_join = 1;
new_ctx->fully_established = 1;
new_ctx->remote_key_valid = 1;
new_ctx->backup = subflow_req->backup;
- new_ctx->remote_id = subflow_req->remote_id;
+ WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
new_ctx->token = subflow_req->token;
new_ctx->thmac = subflow_req->thmac;
diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c
index bfff53e668da..4fc39fa2e262 100644
--- a/net/mptcp/token_test.c
+++ b/net/mptcp/token_test.c
@@ -52,14 +52,19 @@ static struct mptcp_subflow_context *build_ctx(struct kunit *test)
static struct mptcp_sock *build_msk(struct kunit *test)
{
struct mptcp_sock *msk;
+ struct sock *sk;
msk = kunit_kzalloc(test, sizeof(struct mptcp_sock), GFP_USER);
KUNIT_EXPECT_NOT_ERR_OR_NULL(test, msk);
refcount_set(&((struct sock *)msk)->sk_refcnt, 1);
sock_net_set((struct sock *)msk, &init_net);
+ sk = (struct sock *)msk;
+
/* be sure the token helpers can dereference sk->sk_prot */
- ((struct sock *)msk)->sk_prot = &tcp_prot;
+ sk->sk_prot = &tcp_prot;
+ sk->sk_protocol = IPPROTO_MPTCP;
+
return msk;
}
Powered by cgit, Gruvboxed by Blaster4385.