summaryrefslogtreecommitdiff
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/crypto.c35
-rw-r--r--net/mptcp/ctrl.c9
-rw-r--r--net/mptcp/mib.c12
-rw-r--r--net/mptcp/mptcp_diag.c15
-rw-r--r--net/mptcp/options.c6
-rw-r--r--net/mptcp/pm.c60
-rw-r--r--net/mptcp/pm_kernel.c569
-rw-r--r--net/mptcp/pm_netlink.c16
-rw-r--r--net/mptcp/pm_userspace.c2
-rw-r--r--net/mptcp/protocol.c235
-rw-r--r--net/mptcp/protocol.h29
-rw-r--r--net/mptcp/sockopt.c33
-rw-r--r--net/mptcp/subflow.c15
13 files changed, 630 insertions, 406 deletions
diff --git a/net/mptcp/crypto.c b/net/mptcp/crypto.c
index b08ba959ac4f..31948e18d97d 100644
--- a/net/mptcp/crypto.c
+++ b/net/mptcp/crypto.c
@@ -22,7 +22,6 @@
#include <linux/kernel.h>
#include <crypto/sha2.h>
-#include <linux/unaligned.h>
#include "protocol.h"
@@ -43,39 +42,9 @@ void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn)
void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac)
{
- u8 input[SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE];
- u8 key1be[8];
- u8 key2be[8];
- int i;
+ __be64 key[2] = { cpu_to_be64(key1), cpu_to_be64(key2) };
- if (WARN_ON_ONCE(len > SHA256_DIGEST_SIZE))
- len = SHA256_DIGEST_SIZE;
-
- put_unaligned_be64(key1, key1be);
- put_unaligned_be64(key2, key2be);
-
- /* Generate key xored with ipad */
- memset(input, 0x36, SHA256_BLOCK_SIZE);
- for (i = 0; i < 8; i++)
- input[i] ^= key1be[i];
- for (i = 0; i < 8; i++)
- input[i + 8] ^= key2be[i];
-
- memcpy(&input[SHA256_BLOCK_SIZE], msg, len);
-
- /* emit sha256(K1 || msg) on the second input block, so we can
- * reuse 'input' for the last hashing
- */
- sha256(input, SHA256_BLOCK_SIZE + len, &input[SHA256_BLOCK_SIZE]);
-
- /* Prepare second part of hmac */
- memset(input, 0x5C, SHA256_BLOCK_SIZE);
- for (i = 0; i < 8; i++)
- input[i] ^= key1be[i];
- for (i = 0; i < 8; i++)
- input[i + 8] ^= key2be[i];
-
- sha256(input, SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE, hmac);
+ hmac_sha256_usingrawkey((const u8 *)key, sizeof(key), msg, len, hmac);
}
#if IS_MODULE(CONFIG_MPTCP_KUNIT_TEST)
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index fed40dae5583..d96130e49942 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -501,10 +501,15 @@ void mptcp_active_enable(struct sock *sk)
struct mptcp_pernet *pernet = mptcp_get_pernet(sock_net(sk));
if (atomic_read(&pernet->active_disable_times)) {
- struct dst_entry *dst = sk_dst_get(sk);
+ struct net_device *dev;
+ struct dst_entry *dst;
- if (dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK))
+ rcu_read_lock();
+ dst = __sk_dst_get(sk);
+ dev = dst ? dst_dev_rcu(dst) : NULL;
+ if (!(dev && (dev->flags & IFF_LOOPBACK)))
atomic_set(&pernet->active_disable_times, 0);
+ rcu_read_unlock();
}
}
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index cf879c188ca2..6003e47c770a 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -85,7 +85,6 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("DssFallback", MPTCP_MIB_DSSFALLBACK),
SNMP_MIB_ITEM("SimultConnectFallback", MPTCP_MIB_SIMULTCONNFALLBACK),
SNMP_MIB_ITEM("FallbackFailed", MPTCP_MIB_FALLBACKFAILED),
- SNMP_MIB_SENTINEL
};
/* mptcp_mib_alloc - allocate percpu mib counters
@@ -108,22 +107,23 @@ bool mptcp_mib_alloc(struct net *net)
void mptcp_seq_show(struct seq_file *seq)
{
- unsigned long sum[ARRAY_SIZE(mptcp_snmp_list) - 1];
+ unsigned long sum[ARRAY_SIZE(mptcp_snmp_list)];
+ const int cnt = ARRAY_SIZE(mptcp_snmp_list);
struct net *net = seq->private;
int i;
seq_puts(seq, "MPTcpExt:");
- for (i = 0; mptcp_snmp_list[i].name; i++)
+ for (i = 0; i < cnt; i++)
seq_printf(seq, " %s", mptcp_snmp_list[i].name);
seq_puts(seq, "\nMPTcpExt:");
memset(sum, 0, sizeof(sum));
if (net->mib.mptcp_statistics)
- snmp_get_cpu_field_batch(sum, mptcp_snmp_list,
- net->mib.mptcp_statistics);
+ snmp_get_cpu_field_batch_cnt(sum, mptcp_snmp_list, cnt,
+ net->mib.mptcp_statistics);
- for (i = 0; mptcp_snmp_list[i].name; i++)
+ for (i = 0; i < cnt; i++)
seq_printf(seq, " %lu", sum[i]);
seq_putc(seq, '\n');
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index 0566dd793810..ac974299de71 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -15,9 +15,9 @@
static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
struct netlink_callback *cb,
const struct inet_diag_req_v2 *req,
- struct nlattr *bc, bool net_admin)
+ bool net_admin)
{
- if (!inet_diag_bc_sk(bc, sk))
+ if (!inet_diag_bc_sk(cb->data, sk))
return 0;
return inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, req, NLM_F_MULTI,
@@ -76,9 +76,7 @@ static void mptcp_diag_dump_listeners(struct sk_buff *skb, struct netlink_callba
const struct inet_diag_req_v2 *r,
bool net_admin)
{
- struct inet_diag_dump_data *cb_data = cb->data;
struct mptcp_diag_ctx *diag_ctx = (void *)cb->ctx;
- struct nlattr *bc = cb_data->inet_diag_nla_bc;
struct net *net = sock_net(skb->sk);
struct inet_hashinfo *hinfo;
int i;
@@ -121,7 +119,7 @@ static void mptcp_diag_dump_listeners(struct sk_buff *skb, struct netlink_callba
if (!refcount_inc_not_zero(&sk->sk_refcnt))
goto next_listen;
- ret = sk_diag_dump(sk, skb, cb, r, bc, net_admin);
+ ret = sk_diag_dump(sk, skb, cb, r, net_admin);
sock_put(sk);
@@ -154,15 +152,10 @@ static void mptcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
struct mptcp_diag_ctx *diag_ctx = (void *)cb->ctx;
struct net *net = sock_net(skb->sk);
- struct inet_diag_dump_data *cb_data;
struct mptcp_sock *msk;
- struct nlattr *bc;
BUILD_BUG_ON(sizeof(cb->ctx) < sizeof(*diag_ctx));
- cb_data = cb->data;
- bc = cb_data->inet_diag_nla_bc;
-
while ((msk = mptcp_token_iter_next(net, &diag_ctx->s_slot,
&diag_ctx->s_num)) != NULL) {
struct inet_sock *inet = (struct inet_sock *)msk;
@@ -181,7 +174,7 @@ static void mptcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
r->id.idiag_dport)
goto next;
- ret = sk_diag_dump(sk, skb, cb, r, bc, net_admin);
+ ret = sk_diag_dump(sk, skb, cb, r, net_admin);
next:
sock_put(sk);
if (ret < 0) {
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 2a8ea28442b2..1103b3341a70 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -985,13 +985,13 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
return false;
}
- if (mp_opt->deny_join_id0)
- WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
-
if (unlikely(!READ_ONCE(msk->pm.server_side)))
pr_warn_once("bogus mpc option on established client sk");
set_fully_established:
+ if (mp_opt->deny_join_id0)
+ WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
+
mptcp_data_lock((struct sock *)msk);
__mptcp_subflow_fully_established(msk, subflow, mp_opt);
mptcp_data_unlock((struct sock *)msk);
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 136a380602ca..2ff1b9499568 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -268,6 +268,27 @@ int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
return -EINVAL;
}
+static unsigned int mptcp_adjust_add_addr_timeout(struct mptcp_sock *msk)
+{
+ const struct net *net = sock_net((struct sock *)msk);
+ unsigned int rto = mptcp_get_add_addr_timeout(net);
+ struct mptcp_subflow_context *subflow;
+ unsigned int max = 0;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ struct inet_connection_sock *icsk = inet_csk(ssk);
+
+ if (icsk->icsk_rto > max)
+ max = icsk->icsk_rto;
+ }
+
+ if (max && max < rto)
+ rto = max;
+
+ return rto;
+}
+
static void mptcp_pm_add_timer(struct timer_list *timer)
{
struct mptcp_pm_add_entry *entry = timer_container_of(entry, timer,
@@ -292,7 +313,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
goto out;
}
- timeout = mptcp_get_add_addr_timeout(sock_net(sk));
+ timeout = mptcp_adjust_add_addr_timeout(msk);
if (!timeout)
goto out;
@@ -307,7 +328,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
sk_reset_timer(sk, timer,
- jiffies + timeout);
+ jiffies + (timeout << entry->retrans_times));
spin_unlock_bh(&msk->pm.lock);
@@ -348,7 +369,6 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
{
struct mptcp_pm_add_entry *add_entry = NULL;
struct sock *sk = (struct sock *)msk;
- struct net *net = sock_net(sk);
unsigned int timeout;
lockdep_assert_held(&msk->pm.lock);
@@ -374,7 +394,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
reset_timer:
- timeout = mptcp_get_add_addr_timeout(net);
+ timeout = mptcp_adjust_add_addr_timeout(msk);
if (timeout)
sk_reset_timer(sk, &add_entry->add_timer, jiffies + timeout);
@@ -463,23 +483,24 @@ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int
bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
{
struct mptcp_pm_data *pm = &msk->pm;
- unsigned int subflows_max;
+ unsigned int limit_extra_subflows;
int ret = 0;
if (mptcp_pm_is_userspace(msk)) {
if (mptcp_userspace_pm_active(msk)) {
spin_lock_bh(&pm->lock);
- pm->subflows++;
+ pm->extra_subflows++;
spin_unlock_bh(&pm->lock);
return true;
}
return false;
}
- subflows_max = mptcp_pm_get_subflows_max(msk);
+ limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk);
- pr_debug("msk=%p subflows=%d max=%d allow=%d\n", msk, pm->subflows,
- subflows_max, READ_ONCE(pm->accept_subflow));
+ pr_debug("msk=%p subflows=%d max=%d allow=%d\n", msk,
+ pm->extra_subflows, limit_extra_subflows,
+ READ_ONCE(pm->accept_subflow));
/* try to avoid acquiring the lock below */
if (!READ_ONCE(pm->accept_subflow))
@@ -487,8 +508,8 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
spin_lock_bh(&pm->lock);
if (READ_ONCE(pm->accept_subflow)) {
- ret = pm->subflows < subflows_max;
- if (ret && ++pm->subflows == subflows_max)
+ ret = pm->extra_subflows < limit_extra_subflows;
+ if (ret && ++pm->extra_subflows == limit_extra_subflows)
WRITE_ONCE(pm->accept_subflow, false);
}
spin_unlock_bh(&pm->lock);
@@ -574,7 +595,7 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk,
if (mptcp_pm_is_userspace(msk)) {
if (update_subflows) {
spin_lock_bh(&pm->lock);
- pm->subflows--;
+ pm->extra_subflows--;
spin_unlock_bh(&pm->lock);
}
return;
@@ -617,9 +638,12 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
} else {
__MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP);
}
- /* id0 should not have a different address */
+ /* - id0 should not have a different address
+ * - special case for C-flag: linked to fill_local_addresses_vec()
+ */
} else if ((addr->id == 0 && !mptcp_pm_is_init_remote_addr(msk, addr)) ||
- (addr->id > 0 && !READ_ONCE(pm->accept_addr))) {
+ (addr->id > 0 && !READ_ONCE(pm->accept_addr) &&
+ !mptcp_pm_add_addr_c_flag_case(msk))) {
mptcp_pm_announce_addr(msk, addr, true);
mptcp_pm_add_addr_send_ack(msk);
} else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {
@@ -1005,17 +1029,17 @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
WRITE_ONCE(pm->pm_type, pm_type);
if (pm_type == MPTCP_PM_TYPE_KERNEL) {
- bool subflows_allowed = !!mptcp_pm_get_subflows_max(msk);
+ bool subflows_allowed = !!mptcp_pm_get_limit_extra_subflows(msk);
/* pm->work_pending must be only be set to 'true' when
* pm->pm_type is set to MPTCP_PM_TYPE_KERNEL
*/
WRITE_ONCE(pm->work_pending,
- (!!mptcp_pm_get_local_addr_max(msk) &&
+ (!!mptcp_pm_get_endp_subflow_max(msk) &&
subflows_allowed) ||
- !!mptcp_pm_get_add_addr_signal_max(msk));
+ !!mptcp_pm_get_endp_signal_max(msk));
WRITE_ONCE(pm->accept_addr,
- !!mptcp_pm_get_add_addr_accept_max(msk) &&
+ !!mptcp_pm_get_limit_add_addr_accepted(msk) &&
subflows_allowed);
WRITE_ONCE(pm->accept_subflow, subflows_allowed);
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index 667803d72b64..e0f44dc232aa 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -17,14 +17,14 @@ static int pm_nl_pernet_id;
struct pm_nl_pernet {
/* protects pernet updates */
spinlock_t lock;
- struct list_head local_addr_list;
- unsigned int addrs;
- unsigned int stale_loss_cnt;
- unsigned int add_addr_signal_max;
- unsigned int add_addr_accept_max;
- unsigned int local_addr_max;
- unsigned int subflows_max;
- unsigned int next_id;
+ struct list_head endp_list;
+ u8 endpoints;
+ u8 endp_signal_max;
+ u8 endp_subflow_max;
+ u8 endp_laminar_max;
+ u8 limit_add_addr_accepted;
+ u8 limit_extra_subflows;
+ u8 next_id;
DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
};
@@ -46,37 +46,45 @@ static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info)
return pm_nl_get_pernet(genl_info_net(info));
}
-unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk)
+u8 mptcp_pm_get_endp_signal_max(const struct mptcp_sock *msk)
{
const struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
- return READ_ONCE(pernet->add_addr_signal_max);
+ return READ_ONCE(pernet->endp_signal_max);
}
-EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_signal_max);
+EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_signal_max);
-unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk)
+u8 mptcp_pm_get_endp_subflow_max(const struct mptcp_sock *msk)
{
struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
- return READ_ONCE(pernet->add_addr_accept_max);
+ return READ_ONCE(pernet->endp_subflow_max);
}
-EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_accept_max);
+EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_subflow_max);
-unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk)
+u8 mptcp_pm_get_endp_laminar_max(const struct mptcp_sock *msk)
{
struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
- return READ_ONCE(pernet->subflows_max);
+ return READ_ONCE(pernet->endp_laminar_max);
}
-EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max);
+EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_laminar_max);
-unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk)
+u8 mptcp_pm_get_limit_add_addr_accepted(const struct mptcp_sock *msk)
{
struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
- return READ_ONCE(pernet->local_addr_max);
+ return READ_ONCE(pernet->limit_add_addr_accepted);
}
-EXPORT_SYMBOL_GPL(mptcp_pm_get_local_addr_max);
+EXPORT_SYMBOL_GPL(mptcp_pm_get_limit_add_addr_accepted);
+
+u8 mptcp_pm_get_limit_extra_subflows(const struct mptcp_sock *msk)
+{
+ struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+
+ return READ_ONCE(pernet->limit_extra_subflows);
+}
+EXPORT_SYMBOL_GPL(mptcp_pm_get_limit_extra_subflows);
static bool lookup_subflow_by_daddr(const struct list_head *list,
const struct mptcp_addr_info *daddr)
@@ -110,7 +118,7 @@ select_local_address(const struct pm_nl_pernet *pernet,
msk_owned_by_me(msk);
rcu_read_lock();
- list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+ list_for_each_entry_rcu(entry, &pernet->endp_list, list) {
if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
continue;
@@ -141,7 +149,7 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
* Note: removal from the local address list during the msk life-cycle
* can lead to additional addresses not being announced.
*/
- list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+ list_for_each_entry_rcu(entry, &pernet->endp_list, list) {
if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
continue;
@@ -159,80 +167,96 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
return found;
}
-/* Fill all the remote addresses into the array addrs[],
- * and return the array size.
- */
-static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
- struct mptcp_addr_info *local,
- bool fullmesh,
- struct mptcp_addr_info *addrs)
+static unsigned int
+fill_remote_addr(struct mptcp_sock *msk, struct mptcp_addr_info *local,
+ struct mptcp_addr_info *addrs)
{
bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0);
- struct sock *sk = (struct sock *)msk, *ssk;
- struct mptcp_subflow_context *subflow;
struct mptcp_addr_info remote = { 0 };
- unsigned int subflows_max;
- int i = 0;
+ struct sock *sk = (struct sock *)msk;
+
+ if (deny_id0)
+ return 0;
- subflows_max = mptcp_pm_get_subflows_max(msk);
mptcp_remote_address((struct sock_common *)sk, &remote);
- /* Non-fullmesh endpoint, fill in the single entry
- * corresponding to the primary MPC subflow remote address
- */
- if (!fullmesh) {
- if (deny_id0)
- return 0;
+ if (!mptcp_pm_addr_families_match(sk, local, &remote))
+ return 0;
- if (!mptcp_pm_addr_families_match(sk, local, &remote))
- return 0;
+ msk->pm.extra_subflows++;
+ *addrs = remote;
- msk->pm.subflows++;
- addrs[i++] = remote;
- } else {
- DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+ return 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);
- mptcp_remote_address((struct sock_common *)ssk, &addrs[i]);
- addrs[i].id = READ_ONCE(subflow->remote_id);
- if (deny_id0 && !addrs[i].id)
- continue;
+static unsigned int
+fill_remote_addresses_fullmesh(struct mptcp_sock *msk,
+ struct mptcp_addr_info *local,
+ struct mptcp_addr_info *addrs)
+{
+ u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk);
+ bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0);
+ DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+ struct sock *sk = (struct sock *)msk, *ssk;
+ struct mptcp_subflow_context *subflow;
+ int i = 0;
- if (test_bit(addrs[i].id, unavail_id))
- continue;
+ /* 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);
+ mptcp_remote_address((struct sock_common *)ssk, &addrs[i]);
+ addrs[i].id = READ_ONCE(subflow->remote_id);
+ if (deny_id0 && !addrs[i].id)
+ continue;
- if (!mptcp_pm_addr_families_match(sk, local, &addrs[i]))
- continue;
+ if (test_bit(addrs[i].id, unavail_id))
+ continue;
- if (msk->pm.subflows < subflows_max) {
- /* forbid creating multiple address towards
- * this id
- */
- __set_bit(addrs[i].id, unavail_id);
- msk->pm.subflows++;
- i++;
- }
- }
+ if (!mptcp_pm_addr_families_match(sk, local, &addrs[i]))
+ continue;
+
+ /* forbid creating multiple address towards this id */
+ __set_bit(addrs[i].id, unavail_id);
+ msk->pm.extra_subflows++;
+ i++;
+
+ if (msk->pm.extra_subflows >= limit_extra_subflows)
+ break;
}
return i;
}
+/* Fill all the remote addresses into the array addrs[],
+ * and return the array size.
+ */
+static unsigned int
+fill_remote_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *local,
+ bool fullmesh, struct mptcp_addr_info *addrs)
+{
+ /* Non-fullmesh: fill in the single entry corresponding to the primary
+ * MPC subflow remote address, and return 1, corresponding to 1 entry.
+ */
+ if (!fullmesh)
+ return fill_remote_addr(msk, local, addrs);
+
+ /* Fullmesh endpoint: fill all possible remote addresses */
+ return fill_remote_addresses_fullmesh(msk, local, addrs);
+}
+
static struct mptcp_pm_addr_entry *
__lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id)
{
struct mptcp_pm_addr_entry *entry;
- list_for_each_entry_rcu(entry, &pernet->local_addr_list, list,
+ list_for_each_entry_rcu(entry, &pernet->endp_list, list,
lockdep_is_held(&pernet->lock)) {
if (entry->addr.id == id)
return entry;
@@ -245,7 +269,7 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
{
struct mptcp_pm_addr_entry *entry;
- list_for_each_entry_rcu(entry, &pernet->local_addr_list, list,
+ list_for_each_entry_rcu(entry, &pernet->endp_list, list,
lockdep_is_held(&pernet->lock)) {
if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port))
return entry;
@@ -253,52 +277,65 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
return NULL;
}
-static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *addr)
{
- struct sock *sk = (struct sock *)msk;
- unsigned int add_addr_signal_max;
- bool signal_and_subflow = false;
- unsigned int local_addr_max;
- struct pm_nl_pernet *pernet;
- struct mptcp_pm_local local;
- unsigned int subflows_max;
-
- pernet = pm_nl_get_pernet(sock_net(sk));
+ return msk->mpc_endpoint_id == addr->id ? 0 : addr->id;
+}
- add_addr_signal_max = mptcp_pm_get_add_addr_signal_max(msk);
- local_addr_max = mptcp_pm_get_local_addr_max(msk);
- subflows_max = mptcp_pm_get_subflows_max(msk);
+/* Set mpc_endpoint_id, and send MP_PRIO for ID0 if needed */
+static void mptcp_mpc_endpoint_setup(struct mptcp_sock *msk)
+{
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_pm_addr_entry *entry;
+ struct mptcp_addr_info mpc_addr;
+ struct pm_nl_pernet *pernet;
+ bool backup = false;
/* do lazy endpoint usage accounting for the MPC subflows */
- if (unlikely(!(msk->pm.status & BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED))) && msk->first) {
- struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(msk->first);
- struct mptcp_pm_addr_entry *entry;
- struct mptcp_addr_info mpc_addr;
- bool backup = false;
-
- mptcp_local_address((struct sock_common *)msk->first, &mpc_addr);
- rcu_read_lock();
- 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;
- backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
- }
- rcu_read_unlock();
+ if (likely(msk->pm.status & BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED)) ||
+ !msk->first)
+ return;
- if (backup)
- mptcp_pm_send_ack(msk, subflow, true, backup);
+ subflow = mptcp_subflow_ctx(msk->first);
+ pernet = pm_nl_get_pernet_from_msk(msk);
- msk->pm.status |= BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED);
+ mptcp_local_address((struct sock_common *)msk->first, &mpc_addr);
+ rcu_read_lock();
+ 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;
+ backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
}
+ rcu_read_unlock();
+
+ /* Send MP_PRIO */
+ if (backup)
+ mptcp_pm_send_ack(msk, subflow, true, backup);
+
+ msk->pm.status |= BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED);
+}
+
+static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+{
+ u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk);
+ struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+ u8 endp_subflow_max = mptcp_pm_get_endp_subflow_max(msk);
+ u8 endp_signal_max = mptcp_pm_get_endp_signal_max(msk);
+ struct sock *sk = (struct sock *)msk;
+ bool signal_and_subflow = false;
+ struct mptcp_pm_local local;
+
+ mptcp_mpc_endpoint_setup(msk);
pr_debug("local %d:%d signal %d:%d subflows %d:%d\n",
- msk->pm.local_addr_used, local_addr_max,
- msk->pm.add_addr_signaled, add_addr_signal_max,
- msk->pm.subflows, subflows_max);
+ msk->pm.local_addr_used, endp_subflow_max,
+ msk->pm.add_addr_signaled, endp_signal_max,
+ msk->pm.extra_subflows, limit_extra_subflows);
/* check first for announce */
- if (msk->pm.add_addr_signaled < add_addr_signal_max) {
+ if (msk->pm.add_addr_signaled < endp_signal_max) {
/* due to racing events on both ends we can reach here while
* previous add address is still running: if we invoke now
* mptcp_pm_announce_addr(), that will fail and the
@@ -334,8 +371,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
subflow:
/* check if should create a new subflow */
- while (msk->pm.local_addr_used < local_addr_max &&
- msk->pm.subflows < subflows_max) {
+ while (msk->pm.local_addr_used < endp_subflow_max &&
+ msk->pm.extra_subflows < limit_extra_subflows) {
struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX];
bool fullmesh;
int i, nr;
@@ -377,90 +414,225 @@ static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk)
mptcp_pm_create_subflow_or_signal_addr(msk);
}
-/* Fill all the local addresses into the array addrs[],
- * and return the array size.
- */
-static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
- struct mptcp_addr_info *remote,
- struct mptcp_pm_local *locals)
+static unsigned int
+fill_local_addresses_vec_fullmesh(struct mptcp_sock *msk,
+ struct mptcp_addr_info *remote,
+ struct mptcp_pm_local *locals,
+ bool c_flag_case)
{
+ u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk);
+ struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
struct sock *sk = (struct sock *)msk;
struct mptcp_pm_addr_entry *entry;
- struct mptcp_addr_info mpc_addr;
- struct pm_nl_pernet *pernet;
- unsigned int subflows_max;
+ struct mptcp_pm_local *local;
int i = 0;
- pernet = pm_nl_get_pernet_from_msk(msk);
- subflows_max = mptcp_pm_get_subflows_max(msk);
-
- mptcp_local_address((struct sock_common *)msk, &mpc_addr);
-
rcu_read_lock();
- list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+ list_for_each_entry_rcu(entry, &pernet->endp_list, list) {
+ bool is_id0;
+
if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
continue;
if (!mptcp_pm_addr_families_match(sk, &entry->addr, remote))
continue;
- if (msk->pm.subflows < subflows_max) {
- locals[i].addr = entry->addr;
- locals[i].flags = entry->flags;
- locals[i].ifindex = entry->ifindex;
+ local = &locals[i];
+ local->addr = entry->addr;
+ local->flags = entry->flags;
+ local->ifindex = entry->ifindex;
- /* Special case for ID0: set the correct ID */
- if (mptcp_addresses_equal(&locals[i].addr, &mpc_addr, locals[i].addr.port))
- locals[i].addr.id = 0;
+ is_id0 = local->addr.id == msk->mpc_endpoint_id;
- msk->pm.subflows++;
- i++;
+ if (c_flag_case &&
+ (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)) {
+ __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+
+ if (!is_id0)
+ msk->pm.local_addr_used++;
}
+
+ /* Special case for ID0: set the correct ID */
+ if (is_id0)
+ local->addr.id = 0;
+
+ msk->pm.extra_subflows++;
+ i++;
+
+ if (msk->pm.extra_subflows >= limit_extra_subflows)
+ break;
}
rcu_read_unlock();
- /* If the array is empty, fill in the single
- * 'IPADDRANY' local address
+ return i;
+}
+
+static unsigned int
+fill_local_laminar_endp(struct mptcp_sock *msk, struct mptcp_addr_info *remote,
+ struct mptcp_pm_local *locals)
+{
+ struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+ DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+ struct mptcp_subflow_context *subflow;
+ struct sock *sk = (struct sock *)msk;
+ struct mptcp_pm_addr_entry *entry;
+ struct mptcp_pm_local *local;
+ int found = 0;
+
+ /* Forbid creation of new subflows matching existing ones, possibly
+ * already created by 'subflow' endpoints
*/
- if (!i) {
- memset(&locals[i], 0, sizeof(locals[i]));
- locals[i].addr.family =
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
- remote->family == AF_INET6 &&
- ipv6_addr_v4mapped(&remote->addr6) ? AF_INET :
-#endif
- remote->family;
+ bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ if ((1 << inet_sk_state_load(ssk)) &
+ (TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING |
+ TCPF_CLOSE))
+ continue;
+
+ __set_bit(subflow_get_local_id(subflow), unavail_id);
+ }
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(entry, &pernet->endp_list, list) {
+ if (!(entry->flags & MPTCP_PM_ADDR_FLAG_LAMINAR))
+ continue;
+
+ if (!mptcp_pm_addr_families_match(sk, &entry->addr, remote))
+ continue;
+
+ if (test_bit(mptcp_endp_get_local_id(msk, &entry->addr),
+ unavail_id))
+ continue;
+
+ local = &locals[0];
+ local->addr = entry->addr;
+ local->flags = entry->flags;
+ local->ifindex = entry->ifindex;
+
+ if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
+ __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+
+ if (local->addr.id != msk->mpc_endpoint_id)
+ msk->pm.local_addr_used++;
+ }
+
+ msk->pm.extra_subflows++;
+ found = 1;
+ break;
+ }
+ rcu_read_unlock();
+
+ return found;
+}
+
+static unsigned int
+fill_local_addresses_vec_c_flag(struct mptcp_sock *msk,
+ struct mptcp_addr_info *remote,
+ struct mptcp_pm_local *locals)
+{
+ u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk);
+ struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+ u8 endp_subflow_max = mptcp_pm_get_endp_subflow_max(msk);
+ struct sock *sk = (struct sock *)msk;
+ struct mptcp_pm_local *local;
+ int i = 0;
+
+ while (msk->pm.local_addr_used < endp_subflow_max) {
+ local = &locals[i];
- if (!mptcp_pm_addr_families_match(sk, &locals[i].addr, remote))
- return 0;
+ if (!select_local_address(pernet, msk, local))
+ break;
+
+ __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
- msk->pm.subflows++;
+ if (!mptcp_pm_addr_families_match(sk, &local->addr, remote))
+ continue;
+
+ if (local->addr.id == msk->mpc_endpoint_id)
+ continue;
+
+ msk->pm.local_addr_used++;
+ msk->pm.extra_subflows++;
i++;
+
+ if (msk->pm.extra_subflows >= limit_extra_subflows)
+ break;
}
return i;
}
+static unsigned int
+fill_local_address_any(struct mptcp_sock *msk, struct mptcp_addr_info *remote,
+ struct mptcp_pm_local *local)
+{
+ struct sock *sk = (struct sock *)msk;
+
+ memset(local, 0, sizeof(*local));
+ local->addr.family =
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+ remote->family == AF_INET6 &&
+ ipv6_addr_v4mapped(&remote->addr6) ? AF_INET :
+#endif
+ remote->family;
+
+ if (!mptcp_pm_addr_families_match(sk, &local->addr, remote))
+ return 0;
+
+ msk->pm.extra_subflows++;
+
+ return 1;
+}
+
+/* Fill all the local addresses into the array addrs[],
+ * and return the array size.
+ */
+static unsigned int
+fill_local_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *remote,
+ struct mptcp_pm_local *locals)
+{
+ bool c_flag_case = remote->id && mptcp_pm_add_addr_c_flag_case(msk);
+ int i;
+
+ /* If there is at least one MPTCP endpoint with a fullmesh flag */
+ i = fill_local_addresses_vec_fullmesh(msk, remote, locals, c_flag_case);
+ if (i)
+ return i;
+
+ /* If there is at least one MPTCP endpoint with a laminar flag */
+ if (mptcp_pm_get_endp_laminar_max(msk))
+ return fill_local_laminar_endp(msk, remote, locals);
+
+ /* Special case: peer sets the C flag, accept one ADD_ADDR if default
+ * limits are used -- accepting no ADD_ADDR -- and use subflow endpoints
+ */
+ if (c_flag_case)
+ return fill_local_addresses_vec_c_flag(msk, remote, locals);
+
+ /* No special case: fill in the single 'IPADDRANY' local address */
+ return fill_local_address_any(msk, remote, &locals[0]);
+}
+
static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
{
+ u8 limit_add_addr_accepted = mptcp_pm_get_limit_add_addr_accepted(msk);
+ u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk);
struct mptcp_pm_local locals[MPTCP_PM_ADDR_MAX];
struct sock *sk = (struct sock *)msk;
- unsigned int add_addr_accept_max;
struct mptcp_addr_info remote;
- unsigned int subflows_max;
bool sf_created = false;
int i, nr;
- add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk);
- subflows_max = mptcp_pm_get_subflows_max(msk);
-
pr_debug("accepted %d:%d remote family %d\n",
- msk->pm.add_addr_accepted, add_addr_accept_max,
+ msk->pm.add_addr_accepted, limit_add_addr_accepted,
msk->pm.remote.family);
remote = msk->pm.remote;
mptcp_pm_announce_addr(msk, &remote, true);
mptcp_pm_addr_send_ack(msk);
+ mptcp_mpc_endpoint_setup(msk);
if (lookup_subflow_by_daddr(&msk->conn_list, &remote))
return;
@@ -486,8 +658,8 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
/* add_addr_accepted is not decr for ID 0 */
if (remote.id)
msk->pm.add_addr_accepted++;
- if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
- msk->pm.subflows >= subflows_max)
+ if (msk->pm.add_addr_accepted >= limit_add_addr_accepted ||
+ msk->pm.extra_subflows >= limit_extra_subflows)
WRITE_ONCE(msk->pm.accept_addr, false);
}
}
@@ -495,10 +667,13 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id)
{
if (rm_id && WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) {
+ u8 limit_add_addr_accepted =
+ mptcp_pm_get_limit_add_addr_accepted(msk);
+
/* Note: if the subflow has been closed before, this
* add_addr_accepted counter will not be decremented.
*/
- if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk))
+ if (--msk->pm.add_addr_accepted < limit_add_addr_accepted)
WRITE_ONCE(msk->pm.accept_addr, true);
}
}
@@ -523,8 +698,8 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
bool needs_id, bool replace)
{
struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
- unsigned int addr_max;
int ret = -EINVAL;
+ u8 addr_max;
spin_lock_bh(&pernet->lock);
/* to keep the code simple, don't do IDR-like allocation for address ID,
@@ -532,7 +707,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
*/
if (pernet->next_id == MPTCP_PM_MAX_ADDR_ID)
pernet->next_id = 1;
- if (pernet->addrs >= MPTCP_PM_ADDR_MAX) {
+ if (pernet->endpoints >= MPTCP_PM_ADDR_MAX) {
ret = -ERANGE;
goto out;
}
@@ -546,7 +721,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
*/
if (!address_use_port(entry))
entry->addr.port = 0;
- list_for_each_entry(cur, &pernet->local_addr_list, list) {
+ list_for_each_entry(cur, &pernet->endp_list, list) {
if (mptcp_addresses_equal(&cur->addr, &entry->addr,
cur->addr.port || entry->addr.port)) {
/* allow replacing the exiting endpoint only if such
@@ -571,7 +746,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
goto out;
}
- pernet->addrs--;
+ pernet->endpoints--;
entry->addr.id = cur->addr.id;
list_del_rcu(&cur->list);
del_entry = cur;
@@ -598,19 +773,23 @@ find_next:
pernet->next_id = entry->addr.id;
if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
- addr_max = pernet->add_addr_signal_max;
- WRITE_ONCE(pernet->add_addr_signal_max, addr_max + 1);
+ addr_max = pernet->endp_signal_max;
+ WRITE_ONCE(pernet->endp_signal_max, addr_max + 1);
}
if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
- addr_max = pernet->local_addr_max;
- WRITE_ONCE(pernet->local_addr_max, addr_max + 1);
+ addr_max = pernet->endp_subflow_max;
+ WRITE_ONCE(pernet->endp_subflow_max, addr_max + 1);
+ }
+ if (entry->flags & MPTCP_PM_ADDR_FLAG_LAMINAR) {
+ addr_max = pernet->endp_laminar_max;
+ WRITE_ONCE(pernet->endp_laminar_max, addr_max + 1);
}
- pernet->addrs++;
+ pernet->endpoints++;
if (!entry->addr.port)
- list_add_tail_rcu(&entry->list, &pernet->local_addr_list);
+ list_add_tail_rcu(&entry->list, &pernet->endp_list);
else
- list_add_rcu(&entry->list, &pernet->local_addr_list);
+ list_add_rcu(&entry->list, &pernet->endp_list);
ret = entry->addr.id;
out:
@@ -845,12 +1024,6 @@ out_free:
return ret;
}
-static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk,
- const struct mptcp_addr_info *addr)
-{
- return msk->mpc_endpoint_id == addr->id ? 0 : addr->id;
-}
-
static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr,
bool force)
@@ -969,8 +1142,8 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info)
{
struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
struct mptcp_pm_addr_entry addr, *entry;
- unsigned int addr_max;
struct nlattr *attr;
+ u8 addr_max;
int ret;
if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
@@ -997,15 +1170,19 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info)
return -EINVAL;
}
if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
- addr_max = pernet->add_addr_signal_max;
- WRITE_ONCE(pernet->add_addr_signal_max, addr_max - 1);
+ addr_max = pernet->endp_signal_max;
+ WRITE_ONCE(pernet->endp_signal_max, addr_max - 1);
}
if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
- addr_max = pernet->local_addr_max;
- WRITE_ONCE(pernet->local_addr_max, addr_max - 1);
+ addr_max = pernet->endp_subflow_max;
+ WRITE_ONCE(pernet->endp_subflow_max, addr_max - 1);
+ }
+ if (entry->flags & MPTCP_PM_ADDR_FLAG_LAMINAR) {
+ addr_max = pernet->endp_laminar_max;
+ WRITE_ONCE(pernet->endp_laminar_max, addr_max - 1);
}
- pernet->addrs--;
+ pernet->endpoints--;
list_del_rcu(&entry->list);
__clear_bit(entry->addr.id, pernet->id_bitmap);
spin_unlock_bh(&pernet->lock);
@@ -1084,9 +1261,10 @@ static void __flush_addrs(struct list_head *list)
static void __reset_counters(struct pm_nl_pernet *pernet)
{
- WRITE_ONCE(pernet->add_addr_signal_max, 0);
- WRITE_ONCE(pernet->local_addr_max, 0);
- pernet->addrs = 0;
+ WRITE_ONCE(pernet->endp_signal_max, 0);
+ WRITE_ONCE(pernet->endp_subflow_max, 0);
+ WRITE_ONCE(pernet->endp_laminar_max, 0);
+ pernet->endpoints = 0;
}
int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info)
@@ -1095,7 +1273,7 @@ int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info)
LIST_HEAD(free_list);
spin_lock_bh(&pernet->lock);
- list_splice_init(&pernet->local_addr_list, &free_list);
+ list_splice_init(&pernet->endp_list, &free_list);
__reset_counters(pernet);
pernet->next_id = 1;
bitmap_zero(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
@@ -1181,18 +1359,18 @@ int mptcp_pm_nl_set_limits_doit(struct sk_buff *skb, struct genl_info *info)
int ret;
spin_lock_bh(&pernet->lock);
- rcv_addrs = pernet->add_addr_accept_max;
+ rcv_addrs = pernet->limit_add_addr_accepted;
ret = parse_limit(info, MPTCP_PM_ATTR_RCV_ADD_ADDRS, &rcv_addrs);
if (ret)
goto unlock;
- subflows = pernet->subflows_max;
+ subflows = pernet->limit_extra_subflows;
ret = parse_limit(info, MPTCP_PM_ATTR_SUBFLOWS, &subflows);
if (ret)
goto unlock;
- WRITE_ONCE(pernet->add_addr_accept_max, rcv_addrs);
- WRITE_ONCE(pernet->subflows_max, subflows);
+ WRITE_ONCE(pernet->limit_add_addr_accepted, rcv_addrs);
+ WRITE_ONCE(pernet->limit_extra_subflows, subflows);
unlock:
spin_unlock_bh(&pernet->lock);
@@ -1215,11 +1393,11 @@ int mptcp_pm_nl_get_limits_doit(struct sk_buff *skb, struct genl_info *info)
goto fail;
if (nla_put_u32(msg, MPTCP_PM_ATTR_RCV_ADD_ADDRS,
- READ_ONCE(pernet->add_addr_accept_max)))
+ READ_ONCE(pernet->limit_add_addr_accepted)))
goto fail;
if (nla_put_u32(msg, MPTCP_PM_ATTR_SUBFLOWS,
- READ_ONCE(pernet->subflows_max)))
+ READ_ONCE(pernet->limit_extra_subflows)))
goto fail;
genlmsg_end(msg, reply);
@@ -1328,7 +1506,7 @@ bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk)
{
struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
- if (msk->pm.subflows == mptcp_pm_get_subflows_max(msk) ||
+ if (msk->pm.extra_subflows == mptcp_pm_get_limit_extra_subflows(msk) ||
(find_next_and_bit(pernet->id_bitmap, msk->pm.id_avail_bitmap,
MPTCP_PM_MAX_ADDR_ID + 1, 0) == MPTCP_PM_MAX_ADDR_ID + 1)) {
WRITE_ONCE(msk->pm.work_pending, false);
@@ -1360,12 +1538,11 @@ static int __net_init pm_nl_init_net(struct net *net)
{
struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);
- INIT_LIST_HEAD_RCU(&pernet->local_addr_list);
+ INIT_LIST_HEAD_RCU(&pernet->endp_list);
/* Cit. 2 subflows ought to be enough for anybody. */
- pernet->subflows_max = 2;
+ pernet->limit_extra_subflows = 2;
pernet->next_id = 1;
- pernet->stale_loss_cnt = 4;
spin_lock_init(&pernet->lock);
/* No need to initialize other pernet fields, the struct is zeroed at
@@ -1386,7 +1563,7 @@ static void __net_exit pm_nl_exit_net(struct list_head *net_list)
* other modifiers, also netns core already waited for a
* RCU grace period.
*/
- __flush_addrs(&pernet->local_addr_list);
+ __flush_addrs(&pernet->endp_list);
}
}
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 50aaf259959a..d5b383870f79 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -113,7 +113,7 @@ int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info,
return err;
if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX]) {
- u32 val = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]);
+ s32 val = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]);
entry->ifindex = val;
}
@@ -408,11 +408,23 @@ static int mptcp_event_created(struct sk_buff *skb,
const struct sock *ssk)
{
int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token));
+ u16 flags = 0;
if (err)
return err;
- if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, READ_ONCE(msk->pm.server_side)))
+ if (READ_ONCE(msk->pm.server_side)) {
+ flags |= MPTCP_PM_EV_FLAG_SERVER_SIDE;
+
+ /* Deprecated, and only set when it is the server side */
+ if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, 1))
+ return -EMSGSIZE;
+ }
+
+ if (READ_ONCE(msk->pm.remote_deny_join_id0))
+ flags |= MPTCP_PM_EV_FLAG_DENY_JOIN_ID0;
+
+ if (flags && nla_put_u16(skb, MPTCP_ATTR_FLAGS, flags))
return -EMSGSIZE;
return mptcp_event_add_subflow(skb, ssk);
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index a715dcbe0146..8cbc1920afb4 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -419,7 +419,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
if (err)
mptcp_userspace_pm_delete_local_addr(msk, &entry);
else
- msk->pm.subflows++;
+ msk->pm.extra_subflows++;
spin_unlock_bh(&msk->pm.lock);
create_err:
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 9a287b75c1b3..0292162a14ee 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -12,6 +12,7 @@
#include <linux/sched/signal.h>
#include <linux/atomic.h>
#include <net/aligned_data.h>
+#include <net/rps.h>
#include <net/sock.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
@@ -137,26 +138,37 @@ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk)
static void mptcp_drop(struct sock *sk, struct sk_buff *skb)
{
- sk_drops_add(sk, skb);
+ sk_drops_skbadd(sk, skb);
__kfree_skb(skb);
}
-static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
- struct sk_buff *from)
+static bool __mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
+ struct sk_buff *from, bool *fragstolen,
+ int *delta)
{
- bool fragstolen;
- int delta;
+ int limit = READ_ONCE(sk->sk_rcvbuf);
if (unlikely(MPTCP_SKB_CB(to)->cant_coalesce) ||
MPTCP_SKB_CB(from)->offset ||
- ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) ||
- !skb_try_coalesce(to, from, &fragstolen, &delta))
+ ((to->len + from->len) > (limit >> 3)) ||
+ !skb_try_coalesce(to, from, fragstolen, delta))
return false;
pr_debug("colesced seq %llx into %llx new len %d new end seq %llx\n",
MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq,
to->len, MPTCP_SKB_CB(from)->end_seq);
MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq;
+ return true;
+}
+
+static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
+ struct sk_buff *from)
+{
+ bool fragstolen;
+ int delta;
+
+ if (!__mptcp_try_coalesce(sk, to, from, &fragstolen, &delta))
+ return false;
/* note the fwd memory can reach a negative value after accounting
* for the delta, but the later skb free will restore a non
@@ -178,6 +190,35 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to,
return mptcp_try_coalesce((struct sock *)msk, to, from);
}
+/* "inspired" by tcp_rcvbuf_grow(), main difference:
+ * - mptcp does not maintain a msk-level window clamp
+ * - returns true when the receive buffer is actually updated
+ */
+static bool mptcp_rcvbuf_grow(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ const struct net *net = sock_net(sk);
+ int rcvwin, rcvbuf, cap;
+
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) ||
+ (sk->sk_userlocks & SOCK_RCVBUF_LOCK))
+ return false;
+
+ rcvwin = msk->rcvq_space.space << 1;
+
+ if (!RB_EMPTY_ROOT(&msk->out_of_order_queue))
+ rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq;
+
+ cap = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
+
+ rcvbuf = min_t(u32, mptcp_space_from_win(sk, rcvwin), cap);
+ if (rcvbuf > sk->sk_rcvbuf) {
+ WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+ return true;
+ }
+ return false;
+}
+
/* "inspired" by tcp_data_queue_ofo(), main differences:
* - use mptcp seqs
* - don't cope with sacks
@@ -291,29 +332,16 @@ merge_right:
end:
skb_condense(skb);
skb_set_owner_r(skb, sk);
+ /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */
+ if (sk->sk_socket)
+ mptcp_rcvbuf_grow(sk);
}
-static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
- struct sk_buff *skb, unsigned int offset,
- size_t copy_len)
+static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset,
+ int copy_len)
{
- struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
- struct sock *sk = (struct sock *)msk;
- struct sk_buff *tail;
- bool has_rxtstamp;
-
- __skb_unlink(skb, &ssk->sk_receive_queue);
-
- skb_ext_reset(skb);
- skb_orphan(skb);
-
- /* try to fetch required memory from subflow */
- if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
- goto drop;
- }
-
- has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
+ const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ bool has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
/* the skb map_seq accounts for the skb offset:
* mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq
@@ -325,6 +353,24 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp;
MPTCP_SKB_CB(skb)->cant_coalesce = 0;
+ __skb_unlink(skb, &ssk->sk_receive_queue);
+
+ skb_ext_reset(skb);
+ skb_dst_drop(skb);
+}
+
+static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb)
+{
+ u64 copy_len = MPTCP_SKB_CB(skb)->end_seq - MPTCP_SKB_CB(skb)->map_seq;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct sk_buff *tail;
+
+ /* try to fetch required memory from subflow */
+ if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
+ goto drop;
+ }
+
if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
/* in sequence */
msk->bytes_received += copy_len;
@@ -371,6 +417,20 @@ static void mptcp_close_wake_up(struct sock *sk)
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
}
+static void mptcp_shutdown_subflows(struct mptcp_sock *msk)
+{
+ struct mptcp_subflow_context *subflow;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow;
+
+ slow = lock_sock_fast(ssk);
+ tcp_shutdown(ssk, SEND_SHUTDOWN);
+ unlock_sock_fast(ssk, slow);
+ }
+}
+
/* called under the msk socket lock */
static bool mptcp_pending_data_fin_ack(struct sock *sk)
{
@@ -395,6 +455,7 @@ static void mptcp_check_data_fin_ack(struct sock *sk)
break;
case TCP_CLOSING:
case TCP_LAST_ACK:
+ mptcp_shutdown_subflows(msk);
mptcp_set_state(sk, TCP_CLOSE);
break;
}
@@ -529,11 +590,10 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied)
}
}
-static bool mptcp_check_data_fin(struct sock *sk)
+static void mptcp_check_data_fin(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
u64 rcv_data_fin_seq;
- bool ret = false;
/* Need to ack a DATA_FIN received from a peer while this side
* of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2.
@@ -563,6 +623,7 @@ static bool mptcp_check_data_fin(struct sock *sk)
mptcp_set_state(sk, TCP_CLOSING);
break;
case TCP_FIN_WAIT2:
+ mptcp_shutdown_subflows(msk);
mptcp_set_state(sk, TCP_CLOSE);
break;
default:
@@ -571,12 +632,10 @@ static bool mptcp_check_data_fin(struct sock *sk)
break;
}
- ret = true;
if (!__mptcp_check_fallback(msk))
mptcp_send_ack(msk);
mptcp_close_wake_up(sk);
}
- return ret;
}
static void mptcp_dss_corruption(struct mptcp_sock *msk, struct sock *ssk)
@@ -632,7 +691,9 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
if (offset < skb->len) {
size_t len = skb->len - offset;
- ret = __mptcp_move_skb(msk, ssk, skb, offset, len) || ret;
+ mptcp_init_skb(ssk, skb, offset, len);
+ skb_orphan(skb);
+ ret = __mptcp_move_skb(sk, skb) || ret;
seq += len;
if (unlikely(map_remaining < len)) {
@@ -753,12 +814,8 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
moved = __mptcp_move_skbs_from_subflow(msk, ssk);
__mptcp_ofo_queue(msk);
- if (unlikely(ssk->sk_err)) {
- if (!sock_owned_by_user(sk))
- __mptcp_error_report(sk);
- else
- __set_bit(MPTCP_ERROR_REPORT, &msk->cb_flags);
- }
+ if (unlikely(ssk->sk_err))
+ __mptcp_subflow_error_report(sk, ssk);
/* If the moves have caught up with the DATA_FIN sequence number
* it's time to ack the DATA_FIN and change socket state, but
@@ -770,18 +827,10 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
return moved;
}
-static void __mptcp_rcvbuf_update(struct sock *sk, struct sock *ssk)
-{
- if (unlikely(ssk->sk_rcvbuf > sk->sk_rcvbuf))
- WRITE_ONCE(sk->sk_rcvbuf, ssk->sk_rcvbuf);
-}
-
static void __mptcp_data_ready(struct sock *sk, struct sock *ssk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- __mptcp_rcvbuf_update(sk, ssk);
-
/* Wake-up the reader only for in-sequence data */
if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk))
sk->sk_data_ready(sk);
@@ -1740,6 +1789,20 @@ static u32 mptcp_send_limit(const struct sock *sk)
return limit - not_sent;
}
+static void mptcp_rps_record_subflows(const struct mptcp_sock *msk)
+{
+ struct mptcp_subflow_context *subflow;
+
+ if (!rfs_is_needed())
+ return;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ sock_rps_record_flow(ssk);
+ }
+}
+
static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1753,6 +1816,8 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
lock_sock(sk);
+ mptcp_rps_record_subflows(msk);
+
if (unlikely(inet_test_bit(DEFER_CONNECT, sk) ||
msg->msg_flags & MSG_FASTOPEN)) {
int copied_syn = 0;
@@ -1913,12 +1978,13 @@ static int __mptcp_recvmsg_mskq(struct sock *sk,
}
if (!(flags & MSG_PEEK)) {
- /* avoid the indirect call, we know the destructor is sock_wfree */
+ /* avoid the indirect call, we know the destructor is sock_rfree */
skb->destructor = NULL;
+ skb->sk = NULL;
atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
sk_mem_uncharge(sk, skb->truesize);
__skb_unlink(skb, &sk->sk_receive_queue);
- __kfree_skb(skb);
+ skb_attempt_defer_free(skb);
msk->bytes_consumed += count;
}
@@ -1983,48 +2049,26 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
if (msk->rcvq_space.copied <= msk->rcvq_space.space)
goto new_measure;
- if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
- !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
- u64 rcvwin, grow;
- int rcvbuf;
-
- rcvwin = ((u64)msk->rcvq_space.copied << 1) + 16 * advmss;
-
- grow = rcvwin * (msk->rcvq_space.copied - msk->rcvq_space.space);
-
- do_div(grow, msk->rcvq_space.space);
- rcvwin += (grow << 1);
-
- rcvbuf = min_t(u64, mptcp_space_from_win(sk, rcvwin),
- READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
-
- if (rcvbuf > sk->sk_rcvbuf) {
- u32 window_clamp;
-
- window_clamp = mptcp_win_from_space(sk, rcvbuf);
- WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+ msk->rcvq_space.space = msk->rcvq_space.copied;
+ if (mptcp_rcvbuf_grow(sk)) {
- /* Make subflows follow along. If we do not do this, we
- * get drops at subflow level if skbs can't be moved to
- * the mptcp rx queue fast enough (announced rcv_win can
- * exceed ssk->sk_rcvbuf).
- */
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *ssk;
- bool slow;
+ /* Make subflows follow along. If we do not do this, we
+ * get drops at subflow level if skbs can't be moved to
+ * the mptcp rx queue fast enough (announced rcv_win can
+ * exceed ssk->sk_rcvbuf).
+ */
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk;
+ bool slow;
- ssk = mptcp_subflow_tcp_sock(subflow);
- slow = lock_sock_fast(ssk);
- WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf);
- WRITE_ONCE(tcp_sk(ssk)->window_clamp, window_clamp);
- if (tcp_can_send_ack(ssk))
- tcp_cleanup_rbuf(ssk, 1);
- unlock_sock_fast(ssk, slow);
- }
+ ssk = mptcp_subflow_tcp_sock(subflow);
+ slow = lock_sock_fast(ssk);
+ tcp_sk(ssk)->rcvq_space.space = msk->rcvq_space.copied;
+ tcp_rcvbuf_grow(ssk);
+ unlock_sock_fast(ssk, slow);
}
}
- msk->rcvq_space.space = msk->rcvq_space.copied;
new_measure:
msk->rcvq_space.copied = 0;
msk->rcvq_space.time = mstamp;
@@ -2053,11 +2097,6 @@ static bool __mptcp_move_skbs(struct sock *sk)
if (list_empty(&msk->conn_list))
return false;
- /* verify we can move any data from the subflow, eventually updating */
- if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK))
- mptcp_for_each_subflow(msk, subflow)
- __mptcp_rcvbuf_update(sk, subflow->tcp_sock);
-
subflow = list_first_entry(&msk->conn_list,
struct mptcp_subflow_context, node);
for (;;) {
@@ -2131,6 +2170,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
goto out_err;
}
+ mptcp_rps_record_subflows(msk);
+
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
len = min_t(size_t, len, INT_MAX);
@@ -2173,14 +2214,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
break;
}
- if (sk->sk_shutdown & RCV_SHUTDOWN) {
- /* race breaker: the shutdown could be after the
- * previous receive queue check
- */
- if (__mptcp_move_skbs(sk))
- continue;
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
break;
- }
if (sk->sk_state == TCP_CLOSE) {
copied = -ENOTCONN;
@@ -2587,7 +2622,8 @@ static void __mptcp_retrans(struct sock *sk)
if (mptcp_data_fin_enabled(msk)) {
struct inet_connection_sock *icsk = inet_csk(sk);
- icsk->icsk_retransmits++;
+ WRITE_ONCE(icsk->icsk_retransmits,
+ icsk->icsk_retransmits + 1);
mptcp_set_datafin_timeout(sk);
mptcp_send_ack(msk);
@@ -3554,7 +3590,6 @@ void mptcp_sock_graft(struct sock *sk, struct socket *parent)
write_lock_bh(&sk->sk_callback_lock);
rcu_assign_pointer(sk->sk_wq, &parent->wq);
sk_set_socket(sk, parent);
- WRITE_ONCE(sk->sk_uid, SOCK_INODE(parent)->i_uid);
write_unlock_bh(&sk->sk_callback_lock);
}
@@ -3921,6 +3956,8 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
mptcp_sock_graft(ssk, newsock);
}
+ mptcp_rps_record_subflows(msk);
+
/* Do late cleanup for the first subflow as necessary. Also
* deal with bad peers not doing a complete shutdown.
*/
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index b15d7fab5c4b..52f9cfa4ce95 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -235,7 +235,7 @@ struct mptcp_pm_data {
u8 add_addr_accepted;
u8 local_addr_used;
u8 pm_type;
- u8 subflows;
+ u8 extra_subflows;
u8 status;
);
@@ -341,8 +341,8 @@ struct mptcp_sock {
struct mptcp_pm_data pm;
struct mptcp_sched_ops *sched;
struct {
- u32 space; /* bytes copied in last measurement window */
- u32 copied; /* bytes copied in this measurement window */
+ int space; /* bytes copied in last measurement window */
+ int copied; /* bytes copied in this measurement window */
u64 time; /* start time of measurement window */
u64 rtt_us; /* last maximum rtt of subflows */
} rcvq_space;
@@ -788,9 +788,7 @@ static inline bool mptcp_epollin_ready(const struct sock *sk)
* as it can always coalesce them
*/
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);
+ tcp_under_memory_pressure(sk);
}
int mptcp_set_rcvlowat(struct sock *sk, int val);
@@ -1182,15 +1180,16 @@ void __init mptcp_pm_userspace_register(void);
void __init mptcp_pm_nl_init(void);
void mptcp_pm_worker(struct mptcp_sock *msk);
void __mptcp_pm_kernel_worker(struct mptcp_sock *msk);
-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);
-unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk);
+u8 mptcp_pm_get_endp_signal_max(const struct mptcp_sock *msk);
+u8 mptcp_pm_get_endp_subflow_max(const struct mptcp_sock *msk);
+u8 mptcp_pm_get_endp_laminar_max(const struct mptcp_sock *msk);
+u8 mptcp_pm_get_limit_add_addr_accepted(const struct mptcp_sock *msk);
+u8 mptcp_pm_get_limit_extra_subflows(const struct mptcp_sock *msk);
/* called under PM lock */
static inline void __mptcp_pm_close_subflow(struct mptcp_sock *msk)
{
- if (--msk->pm.subflows < mptcp_pm_get_subflows_max(msk))
+ if (--msk->pm.extra_subflows < mptcp_pm_get_limit_extra_subflows(msk))
WRITE_ONCE(msk->pm.accept_subflow, true);
}
@@ -1201,6 +1200,14 @@ static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk)
spin_unlock_bh(&msk->pm.lock);
}
+static inline bool mptcp_pm_add_addr_c_flag_case(struct mptcp_sock *msk)
+{
+ return READ_ONCE(msk->pm.remote_deny_join_id0) &&
+ msk->pm.local_addr_used == 0 &&
+ mptcp_pm_get_limit_add_addr_accepted(msk) == 0 &&
+ msk->pm.extra_subflows < mptcp_pm_get_limit_extra_subflows(msk);
+}
+
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)
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 2c267aff95be..a28a48385885 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -962,7 +962,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
memset(info, 0, sizeof(*info));
- info->mptcpi_subflows = READ_ONCE(msk->pm.subflows);
+ info->mptcpi_extra_subflows = READ_ONCE(msk->pm.extra_subflows);
info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled);
info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted);
info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used);
@@ -972,14 +972,16 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
/* The following limits only make sense for the in-kernel PM */
if (mptcp_pm_is_kernel(msk)) {
- info->mptcpi_subflows_max =
- mptcp_pm_get_subflows_max(msk);
- info->mptcpi_add_addr_signal_max =
- mptcp_pm_get_add_addr_signal_max(msk);
- info->mptcpi_add_addr_accepted_max =
- mptcp_pm_get_add_addr_accept_max(msk);
- info->mptcpi_local_addr_max =
- mptcp_pm_get_local_addr_max(msk);
+ info->mptcpi_limit_extra_subflows =
+ mptcp_pm_get_limit_extra_subflows(msk);
+ info->mptcpi_endp_signal_max =
+ mptcp_pm_get_endp_signal_max(msk);
+ info->mptcpi_limit_add_addr_accepted =
+ mptcp_pm_get_limit_add_addr_accepted(msk);
+ info->mptcpi_endp_subflow_max =
+ mptcp_pm_get_endp_subflow_max(msk);
+ info->mptcpi_endp_laminar_max =
+ mptcp_pm_get_endp_laminar_max(msk);
}
if (__mptcp_check_fallback(msk))
@@ -996,7 +998,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
info->mptcpi_bytes_sent = msk->bytes_sent;
info->mptcpi_bytes_received = msk->bytes_received;
info->mptcpi_bytes_retrans = msk->bytes_retrans;
- info->mptcpi_subflows_total = info->mptcpi_subflows +
+ info->mptcpi_subflows_total = info->mptcpi_extra_subflows +
__mptcp_has_initial_subflow(msk);
now = tcp_jiffies32;
info->mptcpi_last_data_sent = jiffies_to_msecs(now - msk->last_data_sent);
@@ -1532,13 +1534,12 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
{
static const unsigned int tx_rx_locks = SOCK_RCVBUF_LOCK | SOCK_SNDBUF_LOCK;
struct sock *sk = (struct sock *)msk;
+ bool keep_open;
- if (ssk->sk_prot->keepalive) {
- if (sock_flag(sk, SOCK_KEEPOPEN))
- ssk->sk_prot->keepalive(ssk, 1);
- else
- ssk->sk_prot->keepalive(ssk, 0);
- }
+ keep_open = sock_flag(sk, SOCK_KEEPOPEN);
+ if (ssk->sk_prot->keepalive)
+ ssk->sk_prot->keepalive(ssk, keep_open);
+ sock_valbool_flag(ssk, SOCK_KEEPOPEN, keep_open);
ssk->sk_priority = sk->sk_priority;
ssk->sk_bound_dev_if = sk->sk_bound_dev_if;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 3f1b62a9fe88..e8325890a322 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -883,6 +883,10 @@ create_child:
ctx->subflow_id = 1;
owner = mptcp_sk(ctx->conn);
+
+ if (mp_opt.deny_join_id0)
+ WRITE_ONCE(owner->pm.remote_deny_join_id0, true);
+
mptcp_pm_new_connection(owner, child, 1);
/* with OoO packets we can reach here without ingress
@@ -1717,19 +1721,14 @@ static void mptcp_attach_cgroup(struct sock *parent, struct sock *child)
/* only the additional subflows created by kworkers have to be modified */
if (cgroup_id(sock_cgroup_ptr(parent_skcd)) !=
cgroup_id(sock_cgroup_ptr(child_skcd))) {
-#ifdef CONFIG_MEMCG
- struct mem_cgroup *memcg = parent->sk_memcg;
-
- mem_cgroup_sk_free(child);
- if (memcg && css_tryget(&memcg->css))
- child->sk_memcg = memcg;
-#endif /* CONFIG_MEMCG */
-
cgroup_sk_free(child_skcd);
*child_skcd = *parent_skcd;
cgroup_sk_clone(child_skcd);
}
#endif /* CONFIG_SOCK_CGROUP_DATA */
+
+ if (mem_cgroup_sockets_enabled)
+ mem_cgroup_sk_inherit(parent, child);
}
static void mptcp_subflow_ops_override(struct sock *ssk)
generated by cgit v1.2.3 (git 2.46.0) at 2025-10-03 22:54:27 +0000