* [PATCH net-next 1/6] mptcp: adjust mptcp receive buffer limit if subflow has larger one
2020-10-30 22:45 [PATCH net-next 0/6] mptcp: Miscellaneous MPTCP fixes Mat Martineau
@ 2020-10-30 22:45 ` Mat Martineau
2020-10-30 22:45 ` [PATCH net-next 2/6] mptcp: use _fast lock version in __mptcp_move_skbs Mat Martineau
` (4 subsequent siblings)
5 siblings, 0 replies; 9+ messages in thread
From: Mat Martineau @ 2020-10-30 22:45 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal, mptcp, kuba, davem, Mat Martineau
From: Florian Westphal <fw@strlen.de>
In addition to tcp autotuning during read, it may also increase the
receive buffer in tcp_clamp_window().
In this case, mptcp should adjust its receive buffer size as well so
it can move all pending skbs from the subflow socket to the mptcp socket.
At this time, TCP can have more skbs ready for processing than what the
mptcp receive buffer size allows.
In the mptcp case, the receive window announced is based on the free
space of the mptcp parent socket instead of the individual subflows.
Following the subflow allows mptcp to grow its receive buffer.
This is especially noticeable for loopback traffic where two skbs are
enough to fill the initial receive window.
In mptcp_data_ready() we do not hold the mptcp socket lock, so modifying
mptcp_sk->sk_rcvbuf is racy. Do it when moving skbs from subflow to
mptcp socket, both sockets are locked in this case.
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/mptcp/protocol.c | 27 ++++++++++++++++++++++-----
1 file changed, 22 insertions(+), 5 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e7419fd15d84..e010ef7585bf 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -466,6 +466,18 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
struct tcp_sock *tp;
u32 old_copied_seq;
bool done = false;
+ int sk_rbuf;
+
+ sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+
+ if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+ int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+
+ if (unlikely(ssk_rbuf > sk_rbuf)) {
+ WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf);
+ sk_rbuf = ssk_rbuf;
+ }
+ }
pr_debug("msk=%p ssk=%p", msk, ssk);
tp = tcp_sk(ssk);
@@ -528,7 +540,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
WRITE_ONCE(tp->copied_seq, seq);
more_data_avail = mptcp_subflow_data_available(ssk);
- if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) {
+ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) {
done = true;
break;
}
@@ -622,6 +634,7 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct mptcp_sock *msk = mptcp_sk(sk);
+ int sk_rbuf, ssk_rbuf;
bool wake;
/* move_skbs_to_msk below can legitly clear the data_avail flag,
@@ -632,12 +645,16 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
if (wake)
set_bit(MPTCP_DATA_READY, &msk->flags);
- if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) &&
- move_skbs_to_msk(msk, ssk))
+ ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+ sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+ if (unlikely(ssk_rbuf > sk_rbuf))
+ sk_rbuf = ssk_rbuf;
+
+ /* over limit? can't append more skbs to msk */
+ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
goto wake;
- /* don't schedule if mptcp sk is (still) over limit */
- if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf))
+ if (move_skbs_to_msk(msk, ssk))
goto wake;
/* mptcp socket is owned, release_cb should retry */
--
2.29.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH net-next 2/6] mptcp: use _fast lock version in __mptcp_move_skbs
2020-10-30 22:45 [PATCH net-next 0/6] mptcp: Miscellaneous MPTCP fixes Mat Martineau
2020-10-30 22:45 ` [PATCH net-next 1/6] mptcp: adjust mptcp receive buffer limit if subflow has larger one Mat Martineau
@ 2020-10-30 22:45 ` Mat Martineau
2020-10-30 22:45 ` [PATCH net-next 3/6] tcp: propagate MPTCP skb extensions on xmit splits Mat Martineau
` (3 subsequent siblings)
5 siblings, 0 replies; 9+ messages in thread
From: Mat Martineau @ 2020-10-30 22:45 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal, mptcp, kuba, davem, Paolo Abeni, Mat Martineau
From: Florian Westphal <fw@strlen.de>
The function is short and won't sleep, so this can use the _fast version.
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/mptcp/protocol.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e010ef7585bf..f5bacfc55006 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1493,13 +1493,14 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
__mptcp_flush_join_list(msk);
do {
struct sock *ssk = mptcp_subflow_recv_lookup(msk);
+ bool slowpath;
if (!ssk)
break;
- lock_sock(ssk);
+ slowpath = lock_sock_fast(ssk);
done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
- release_sock(ssk);
+ unlock_sock_fast(ssk, slowpath);
} while (!done);
if (mptcp_ofo_queue(msk) || moved > 0) {
--
2.29.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH net-next 3/6] tcp: propagate MPTCP skb extensions on xmit splits
2020-10-30 22:45 [PATCH net-next 0/6] mptcp: Miscellaneous MPTCP fixes Mat Martineau
2020-10-30 22:45 ` [PATCH net-next 1/6] mptcp: adjust mptcp receive buffer limit if subflow has larger one Mat Martineau
2020-10-30 22:45 ` [PATCH net-next 2/6] mptcp: use _fast lock version in __mptcp_move_skbs Mat Martineau
@ 2020-10-30 22:45 ` Mat Martineau
2020-10-30 22:45 ` [PATCH net-next 4/6] mptcp: split mptcp_clean_una function Mat Martineau
` (2 subsequent siblings)
5 siblings, 0 replies; 9+ messages in thread
From: Mat Martineau @ 2020-10-30 22:45 UTC (permalink / raw)
To: netdev; +Cc: Paolo Abeni, mptcp, kuba, davem, Mat Martineau
From: Paolo Abeni <pabeni@redhat.com>
When the TCP stack splits a packet on the write queue, the tail
half currently lose the associated skb extensions, and will not
carry the DSM on the wire.
The above does not cause functional problems and is allowed by
the RFC, but interact badly with GRO and RX coalescing, as possible
candidates for aggregation will carry different TCP options.
This change tries to improve the MPTCP behavior, propagating the
skb extensions on split.
Additionally, we must prevent the MPTCP stack from updating the
mapping after the split occur: that will both violate the RFC and
fool the reader.
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
include/net/mptcp.h | 21 ++++++++++++++++++++-
net/ipv4/tcp_output.c | 3 +++
net/mptcp/protocol.c | 7 +++++--
3 files changed, 28 insertions(+), 3 deletions(-)
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 753ba7e755d6..6e706d838e4e 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -29,7 +29,8 @@ struct mptcp_ext {
use_ack:1,
ack64:1,
mpc_map:1,
- __unused:2;
+ frozen:1,
+ __unused:1;
/* one byte hole */
};
@@ -106,6 +107,19 @@ static inline void mptcp_skb_ext_move(struct sk_buff *to,
from->active_extensions = 0;
}
+static inline void mptcp_skb_ext_copy(struct sk_buff *to,
+ struct sk_buff *from)
+{
+ struct mptcp_ext *from_ext;
+
+ from_ext = skb_ext_find(from, SKB_EXT_MPTCP);
+ if (!from_ext)
+ return;
+
+ from_ext->frozen = 1;
+ skb_ext_copy(to, from);
+}
+
static inline bool mptcp_ext_matches(const struct mptcp_ext *to_ext,
const struct mptcp_ext *from_ext)
{
@@ -193,6 +207,11 @@ static inline void mptcp_skb_ext_move(struct sk_buff *to,
{
}
+static inline void mptcp_skb_ext_copy(struct sk_buff *to,
+ struct sk_buff *from)
+{
+}
+
static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
const struct sk_buff *from)
{
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bf48cd73e967..9abf5a0358d5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1569,6 +1569,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
if (!buff)
return -ENOMEM; /* We'll just try again later. */
skb_copy_decrypted(buff, skb);
+ mptcp_skb_ext_copy(buff, skb);
sk_wmem_queued_add(sk, buff->truesize);
sk_mem_charge(sk, buff->truesize);
@@ -2123,6 +2124,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
if (unlikely(!buff))
return -ENOMEM;
skb_copy_decrypted(buff, skb);
+ mptcp_skb_ext_copy(buff, skb);
sk_wmem_queued_add(sk, buff->truesize);
sk_mem_charge(sk, buff->truesize);
@@ -2393,6 +2395,7 @@ static int tcp_mtu_probe(struct sock *sk)
skb = tcp_send_head(sk);
skb_copy_decrypted(nskb, skb);
+ mptcp_skb_ext_copy(nskb, skb);
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index f5bacfc55006..25d12183d1ca 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -771,8 +771,11 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq,
if (!tcp_skb_can_collapse_to(skb))
return false;
- /* can collapse only if MPTCP level sequence is in order */
- return mpext && mpext->data_seq + mpext->data_len == write_seq;
+ /* can collapse only if MPTCP level sequence is in order and this
+ * mapping has not been xmitted yet
+ */
+ return mpext && mpext->data_seq + mpext->data_len == write_seq &&
+ !mpext->frozen;
}
static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
--
2.29.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH net-next 4/6] mptcp: split mptcp_clean_una function
2020-10-30 22:45 [PATCH net-next 0/6] mptcp: Miscellaneous MPTCP fixes Mat Martineau
` (2 preceding siblings ...)
2020-10-30 22:45 ` [PATCH net-next 3/6] tcp: propagate MPTCP skb extensions on xmit splits Mat Martineau
@ 2020-10-30 22:45 ` Mat Martineau
2020-10-30 22:45 ` [PATCH net-next 5/6] mptcp: add a new sysctl add_addr_timeout Mat Martineau
2020-10-30 22:45 ` [PATCH net-next 6/6] selftests: mptcp: add ADD_ADDR timeout test case Mat Martineau
5 siblings, 0 replies; 9+ messages in thread
From: Mat Martineau @ 2020-10-30 22:45 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal, mptcp, kuba, davem, Mat Martineau
From: Florian Westphal <fw@strlen.de>
mptcp_clean_una() will wake writers in case memory could be reclaimed.
When called from mptcp_sendmsg the wakeup code isn't needed.
Move the wakeup to a new helper and then use that from the mptcp worker.
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/mptcp/protocol.c | 28 +++++++++++++++++-----------
1 file changed, 17 insertions(+), 11 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 25d12183d1ca..b84b84adc9ad 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -853,19 +853,25 @@ static void mptcp_clean_una(struct sock *sk)
}
out:
- if (cleaned) {
+ if (cleaned)
sk_mem_reclaim_partial(sk);
+}
- /* Only wake up writers if a subflow is ready */
- if (mptcp_is_writeable(msk)) {
- set_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags);
- smp_mb__after_atomic();
+static void mptcp_clean_una_wakeup(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
- /* set SEND_SPACE before sk_stream_write_space clears
- * NOSPACE
- */
- sk_stream_write_space(sk);
- }
+ mptcp_clean_una(sk);
+
+ /* Only wake up writers if a subflow is ready */
+ if (mptcp_is_writeable(msk)) {
+ set_bit(MPTCP_SEND_SPACE, &msk->flags);
+ smp_mb__after_atomic();
+
+ /* set SEND_SPACE before sk_stream_write_space clears
+ * NOSPACE
+ */
+ sk_stream_write_space(sk);
}
}
@@ -1769,7 +1775,7 @@ static void mptcp_worker(struct work_struct *work)
long timeo = 0;
lock_sock(sk);
- mptcp_clean_una(sk);
+ mptcp_clean_una_wakeup(sk);
mptcp_check_data_fin_ack(sk);
__mptcp_flush_join_list(msk);
if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
--
2.29.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH net-next 5/6] mptcp: add a new sysctl add_addr_timeout
2020-10-30 22:45 [PATCH net-next 0/6] mptcp: Miscellaneous MPTCP fixes Mat Martineau
` (3 preceding siblings ...)
2020-10-30 22:45 ` [PATCH net-next 4/6] mptcp: split mptcp_clean_una function Mat Martineau
@ 2020-10-30 22:45 ` Mat Martineau
2020-11-02 23:33 ` Jakub Kicinski
2020-10-30 22:45 ` [PATCH net-next 6/6] selftests: mptcp: add ADD_ADDR timeout test case Mat Martineau
5 siblings, 1 reply; 9+ messages in thread
From: Mat Martineau @ 2020-10-30 22:45 UTC (permalink / raw)
To: netdev; +Cc: Geliang Tang, mptcp, kuba, davem, Matthieu Baerts, Paolo Abeni
From: Geliang Tang <geliangtang@gmail.com>
This patch added a new sysctl, named add_addr_timeout, to control the
timeout value (in seconds) of the ADD_ADDR retransmission.
Suggested-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
---
net/mptcp/ctrl.c | 14 ++++++++++++++
net/mptcp/pm_netlink.c | 8 ++++++--
net/mptcp/protocol.h | 1 +
3 files changed, 21 insertions(+), 2 deletions(-)
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 54b888f94009..96ba616f59bf 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -18,6 +18,7 @@ struct mptcp_pernet {
struct ctl_table_header *ctl_table_hdr;
int mptcp_enabled;
+ unsigned int add_addr_timeout;
};
static struct mptcp_pernet *mptcp_get_pernet(struct net *net)
@@ -30,6 +31,11 @@ int mptcp_is_enabled(struct net *net)
return mptcp_get_pernet(net)->mptcp_enabled;
}
+unsigned int mptcp_get_add_addr_timeout(struct net *net)
+{
+ return mptcp_get_pernet(net)->add_addr_timeout;
+}
+
static struct ctl_table mptcp_sysctl_table[] = {
{
.procname = "enabled",
@@ -40,12 +46,19 @@ static struct ctl_table mptcp_sysctl_table[] = {
*/
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "add_addr_timeout",
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
{}
};
static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
{
pernet->mptcp_enabled = 1;
+ pernet->add_addr_timeout = TCP_RTO_MAX;
}
static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -61,6 +74,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
}
table[0].data = &pernet->mptcp_enabled;
+ table[1].data = &pernet->add_addr_timeout;
hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
if (!hdr)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 0d6f3d912891..ed60538df7b2 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -206,6 +206,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer);
struct mptcp_sock *msk = entry->sock;
struct sock *sk = (struct sock *)msk;
+ struct net *net = sock_net(sk);
pr_debug("msk=%p", msk);
@@ -232,7 +233,8 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
}
if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
- sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX);
+ sk_reset_timer(sk, timer,
+ jiffies + mptcp_get_add_addr_timeout(net));
spin_unlock_bh(&msk->pm.lock);
@@ -264,6 +266,7 @@ static 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);
if (lookup_anno_list_by_saddr(msk, &entry->addr))
return false;
@@ -279,7 +282,8 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
add_entry->retrans_times = 0;
timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
- sk_reset_timer(sk, &add_entry->add_timer, jiffies + TCP_RTO_MAX);
+ sk_reset_timer(sk, &add_entry->add_timer,
+ jiffies + mptcp_get_add_addr_timeout(net));
return true;
}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 13ab89dc1914..278c88c405e8 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -362,6 +362,7 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
}
int mptcp_is_enabled(struct net *net);
+unsigned int mptcp_get_add_addr_timeout(struct net *net);
void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
struct mptcp_options_received *mp_opt);
bool mptcp_subflow_data_available(struct sock *sk);
--
2.29.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* Re: [PATCH net-next 5/6] mptcp: add a new sysctl add_addr_timeout
2020-10-30 22:45 ` [PATCH net-next 5/6] mptcp: add a new sysctl add_addr_timeout Mat Martineau
@ 2020-11-02 23:33 ` Jakub Kicinski
2020-11-03 0:35 ` Mat Martineau
0 siblings, 1 reply; 9+ messages in thread
From: Jakub Kicinski @ 2020-11-02 23:33 UTC (permalink / raw)
To: Mat Martineau
Cc: netdev, Geliang Tang, mptcp, davem, Matthieu Baerts, Paolo Abeni
On Fri, 30 Oct 2020 15:45:05 -0700 Mat Martineau wrote:
> From: Geliang Tang <geliangtang@gmail.com>
>
> This patch added a new sysctl, named add_addr_timeout, to control the
> timeout value (in seconds) of the ADD_ADDR retransmission.
Please document the new sysctl.
^ permalink raw reply [flat|nested] 9+ messages in thread
* Re: [PATCH net-next 5/6] mptcp: add a new sysctl add_addr_timeout
2020-11-02 23:33 ` Jakub Kicinski
@ 2020-11-03 0:35 ` Mat Martineau
0 siblings, 0 replies; 9+ messages in thread
From: Mat Martineau @ 2020-11-03 0:35 UTC (permalink / raw)
To: Jakub Kicinski
Cc: netdev, Geliang Tang, mptcp, davem, Matthieu Baerts, Paolo Abeni
On Mon, 2 Nov 2020, Jakub Kicinski wrote:
> On Fri, 30 Oct 2020 15:45:05 -0700 Mat Martineau wrote:
>> From: Geliang Tang <geliangtang@gmail.com>
>>
>> This patch added a new sysctl, named add_addr_timeout, to control the
>> timeout value (in seconds) of the ADD_ADDR retransmission.
>
> Please document the new sysctl.
>
Thanks Jakub. I will add a patch to document this new sysctl and the
existing 'enabled' sysctl for MPTCP.
--
Mat Martineau
Intel
^ permalink raw reply [flat|nested] 9+ messages in thread
* [PATCH net-next 6/6] selftests: mptcp: add ADD_ADDR timeout test case
2020-10-30 22:45 [PATCH net-next 0/6] mptcp: Miscellaneous MPTCP fixes Mat Martineau
` (4 preceding siblings ...)
2020-10-30 22:45 ` [PATCH net-next 5/6] mptcp: add a new sysctl add_addr_timeout Mat Martineau
@ 2020-10-30 22:45 ` Mat Martineau
5 siblings, 0 replies; 9+ messages in thread
From: Mat Martineau @ 2020-10-30 22:45 UTC (permalink / raw)
To: netdev; +Cc: Geliang Tang, mptcp, kuba, davem, Matthieu Baerts, Paolo Abeni
From: Geliang Tang <geliangtang@gmail.com>
This patch added the test case for retransmitting ADD_ADDR when timeout
occurs. It set NS1's add_addr_timeout to 1 second, and drop NS2's ADD_ADDR
echo packets.
Here we need to slow down the transfer process of all data to let the
ADD_ADDR suboptions can be retransmitted three times. So we added a new
parameter "speed" for do_transfer, it can be set with fast or slow.
We also added three new optional parameters for run_tests, and dropped
run_remove_tests function.
Since we added the netfilter rules in this test case, we need to update
the "config" file.
Suggested-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
---
tools/testing/selftests/net/mptcp/config | 10 ++
.../testing/selftests/net/mptcp/mptcp_join.sh | 94 ++++++++++++++-----
2 files changed, 80 insertions(+), 24 deletions(-)
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index 741a1c4f4ae8..0faaccd21447 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -5,3 +5,13 @@ CONFIG_INET_DIAG=m
CONFIG_INET_MPTCP_DIAG=m
CONFIG_VETH=y
CONFIG_NET_SCH_NETEM=m
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_ADVANCED=y
+CONFIG_NETFILTER_NETLINK=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_COMPAT=m
+CONFIG_NETFILTER_XTABLES=m
+CONFIG_NETFILTER_XT_MATCH_BPF=m
+CONFIG_NF_TABLES_IPV4=y
+CONFIG_NF_TABLES_IPV6=y
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 08f53d86dedc..0d93b243695f 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -13,6 +13,24 @@ capture=0
TEST_COUNT=0
+# generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) ||
+# (ip6 && (ip6[74] & 0xf0) == 0x30)'"
+CBPF_MPTCP_SUBOPTION_ADD_ADDR="14,
+ 48 0 0 0,
+ 84 0 0 240,
+ 21 0 3 64,
+ 48 0 0 54,
+ 84 0 0 240,
+ 21 6 7 48,
+ 48 0 0 0,
+ 84 0 0 240,
+ 21 0 4 96,
+ 48 0 0 74,
+ 84 0 0 240,
+ 21 0 1 48,
+ 6 0 0 65535,
+ 6 0 0 0"
+
init()
{
capout=$(mktemp)
@@ -82,6 +100,26 @@ reset_with_cookies()
done
}
+reset_with_add_addr_timeout()
+{
+ local ip="${1:-4}"
+ local tables
+
+ tables="iptables"
+ if [ $ip -eq 6 ]; then
+ tables="ip6tables"
+ fi
+
+ reset
+
+ ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1
+ ip netns exec $ns2 $tables -A OUTPUT -p tcp \
+ -m tcp --tcp-option 30 \
+ -m bpf --bytecode \
+ "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \
+ -j DROP
+}
+
for arg in "$@"; do
if [ "$arg" = "-c" ]; then
capture=1
@@ -94,6 +132,17 @@ if [ $? -ne 0 ];then
exit $ksft_skip
fi
+iptables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run all tests without iptables tool"
+ exit $ksft_skip
+fi
+
+ip6tables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run all tests without ip6tables tool"
+ exit $ksft_skip
+fi
check_transfer()
{
@@ -135,6 +184,7 @@ do_transfer()
connect_addr="$5"
rm_nr_ns1="$6"
rm_nr_ns2="$7"
+ speed="$8"
port=$((10000+$TEST_COUNT))
TEST_COUNT=$((TEST_COUNT+1))
@@ -159,7 +209,7 @@ do_transfer()
sleep 1
fi
- if [[ $rm_nr_ns1 -eq 0 && $rm_nr_ns2 -eq 0 ]]; then
+ if [ $speed = "fast" ]; then
mptcp_connect="./mptcp_connect -j"
else
mptcp_connect="./mptcp_connect -r"
@@ -250,26 +300,13 @@ run_tests()
listener_ns="$1"
connector_ns="$2"
connect_addr="$3"
+ rm_nr_ns1="${4:-0}"
+ rm_nr_ns2="${5:-0}"
+ speed="${6:-fast}"
lret=0
- do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} 0 0
- lret=$?
- if [ $lret -ne 0 ]; then
- ret=$lret
- return
- fi
-}
-
-run_remove_tests()
-{
- listener_ns="$1"
- connector_ns="$2"
- connect_addr="$3"
- rm_nr_ns1="$4"
- rm_nr_ns2="$5"
- lret=0
-
- do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${rm_nr_ns1} ${rm_nr_ns2}
+ do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \
+ ${rm_nr_ns1} ${rm_nr_ns2} ${speed}
lret=$?
if [ $lret -ne 0 ]; then
ret=$lret
@@ -491,12 +528,21 @@ run_tests $ns1 $ns2 10.0.1.1
chk_join_nr "multiple subflows and signal" 3 3 3
chk_add_nr 1 1
+# add_addr timeout
+reset_with_add_addr_timeout
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+run_tests $ns1 $ns2 10.0.1.1 0 0 slow
+chk_join_nr "signal address, ADD_ADDR timeout" 1 1 1
+chk_add_nr 4 0
+
# single subflow, remove
reset
ip netns exec $ns1 ./pm_nl_ctl limits 0 1
ip netns exec $ns2 ./pm_nl_ctl limits 0 1
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 0 1
+run_tests $ns1 $ns2 10.0.1.1 0 1 slow
chk_join_nr "remove single subflow" 1 1 1
chk_rm_nr 1 1
@@ -506,7 +552,7 @@ ip netns exec $ns1 ./pm_nl_ctl limits 0 2
ip netns exec $ns2 ./pm_nl_ctl limits 0 2
ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 0 2
+run_tests $ns1 $ns2 10.0.1.1 0 2 slow
chk_join_nr "remove multiple subflows" 2 2 2
chk_rm_nr 2 2
@@ -515,7 +561,7 @@ reset
ip netns exec $ns1 ./pm_nl_ctl limits 0 1
ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
ip netns exec $ns2 ./pm_nl_ctl limits 1 1
-run_remove_tests $ns1 $ns2 10.0.1.1 1 0
+run_tests $ns1 $ns2 10.0.1.1 1 0 slow
chk_join_nr "remove single address" 1 1 1
chk_add_nr 1 1
chk_rm_nr 0 0
@@ -526,7 +572,7 @@ ip netns exec $ns1 ./pm_nl_ctl limits 0 2
ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
ip netns exec $ns2 ./pm_nl_ctl limits 1 2
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 1 1
+run_tests $ns1 $ns2 10.0.1.1 1 1 slow
chk_join_nr "remove subflow and signal" 2 2 2
chk_add_nr 1 1
chk_rm_nr 1 1
@@ -538,7 +584,7 @@ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
ip netns exec $ns2 ./pm_nl_ctl limits 1 3
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 1 2
+run_tests $ns1 $ns2 10.0.1.1 1 2 slow
chk_join_nr "remove subflows and signal" 3 3 3
chk_add_nr 1 1
chk_rm_nr 2 2
--
2.29.2
^ permalink raw reply related [flat|nested] 9+ messages in thread