summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c6
-rw-r--r--drivers/net/phy/phylink.c3
-rw-r--r--include/net/xfrm.h3
-rw-r--r--net/devlink/rate.c4
-rw-r--r--net/ipv4/esp4_offload.c6
-rw-r--r--net/ipv6/esp6_offload.c6
-rw-r--r--net/mptcp/options.c54
-rw-r--r--net/mptcp/pm.c20
-rw-r--r--net/mptcp/pm_kernel.c2
-rw-r--r--net/mptcp/protocol.c59
-rw-r--r--net/mptcp/protocol.h3
-rw-r--r--net/unix/af_unix.c3
-rw-r--r--net/xfrm/xfrm_device.c2
-rw-r--r--net/xfrm/xfrm_output.c8
-rw-r--r--net/xfrm/xfrm_state.c30
-rw-r--r--net/xfrm/xfrm_user.c8
-rw-r--r--tools/testing/selftests/net/.gitignore1
-rw-r--r--tools/testing/selftests/net/af_unix/Makefile1
-rw-r--r--tools/testing/selftests/net/af_unix/so_peek_off.c162
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh27
20 files changed, 345 insertions, 63 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index e18a850c615c..aa3b5878e3da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -324,10 +324,8 @@ err_xa:
free_irq(irq->map.virq, &irq->nh);
err_req_irq:
#ifdef CONFIG_RFS_ACCEL
- if (i && rmap && *rmap) {
- free_irq_cpu_rmap(*rmap);
- *rmap = NULL;
- }
+ if (i && rmap && *rmap)
+ irq_cpu_rmap_remove(*rmap, irq->map.virq);
err_irq_rmap:
#endif
if (i && pci_msix_can_alloc_dyn(dev->pdev))
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 9d7799ea1c17..918244308215 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -637,6 +637,9 @@ static int phylink_validate(struct phylink *pl, unsigned long *supported,
static void phylink_fill_fixedlink_supported(unsigned long *supported)
{
+ linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported);
+ linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, supported);
+ linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, supported);
linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, supported);
linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, supported);
linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, supported);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index f3014e4f54fc..0a14daaa5dd4 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -536,7 +536,8 @@ static inline int xfrm_af2proto(unsigned int family)
static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto)
{
- if ((ipproto == IPPROTO_IPIP && x->props.family == AF_INET) ||
+ if ((x->sel.family != AF_UNSPEC) ||
+ (ipproto == IPPROTO_IPIP && x->props.family == AF_INET) ||
(ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6))
return &x->inner_mode;
else
diff --git a/net/devlink/rate.c b/net/devlink/rate.c
index 264fb82cba19..d157a8419bca 100644
--- a/net/devlink/rate.c
+++ b/net/devlink/rate.c
@@ -828,13 +828,15 @@ void devl_rate_nodes_destroy(struct devlink *devlink)
if (!devlink_rate->parent)
continue;
- refcount_dec(&devlink_rate->parent->refcnt);
if (devlink_rate_is_leaf(devlink_rate))
ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv,
NULL, NULL);
else if (devlink_rate_is_node(devlink_rate))
ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv,
NULL, NULL);
+
+ refcount_dec(&devlink_rate->parent->refcnt);
+ devlink_rate->parent = NULL;
}
list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) {
if (devlink_rate_is_node(devlink_rate)) {
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index e0d94270da28..05828d4cb6cd 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -122,8 +122,10 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x,
struct sk_buff *skb,
netdev_features_t features)
{
- __be16 type = x->inner_mode.family == AF_INET6 ? htons(ETH_P_IPV6)
- : htons(ETH_P_IP);
+ const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x,
+ XFRM_MODE_SKB_CB(skb)->protocol);
+ __be16 type = inner_mode->family == AF_INET6 ? htons(ETH_P_IPV6)
+ : htons(ETH_P_IP);
return skb_eth_gso_segment(skb, features, type);
}
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 7b41fb4f00b5..22410243ebe8 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -158,8 +158,10 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x,
struct sk_buff *skb,
netdev_features_t features)
{
- __be16 type = x->inner_mode.family == AF_INET ? htons(ETH_P_IP)
- : htons(ETH_P_IPV6);
+ const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x,
+ XFRM_MODE_SKB_CB(skb)->protocol);
+ __be16 type = inner_mode->family == AF_INET ? htons(ETH_P_IP)
+ : htons(ETH_P_IPV6);
return skb_eth_gso_segment(skb, features, type);
}
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 1103b3341a70..f24ae7d40e88 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -838,8 +838,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
opts->suboptions = 0;
+ /* Force later mptcp_write_options(), but do not use any actual
+ * option space.
+ */
if (unlikely(__mptcp_check_fallback(msk) && !mptcp_check_infinite_map(skb)))
- return false;
+ return true;
if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {
if (mptcp_established_options_fastclose(sk, &opt_size, remaining, opts) ||
@@ -1041,6 +1044,31 @@ static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una)
WRITE_ONCE(msk->snd_una, new_snd_una);
}
+static void rwin_update(struct mptcp_sock *msk, struct sock *ssk,
+ struct sk_buff *skb)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ struct tcp_sock *tp = tcp_sk(ssk);
+ u64 mptcp_rcv_wnd;
+
+ /* Avoid touching extra cachelines if TCP is going to accept this
+ * skb without filling the TCP-level window even with a possibly
+ * outdated mptcp-level rwin.
+ */
+ if (!skb->len || skb->len < tcp_receive_window(tp))
+ return;
+
+ mptcp_rcv_wnd = atomic64_read(&msk->rcv_wnd_sent);
+ if (!after64(mptcp_rcv_wnd, subflow->rcv_wnd_sent))
+ return;
+
+ /* Some other subflow grew the mptcp-level rwin since rcv_wup,
+ * resync.
+ */
+ tp->rcv_wnd += mptcp_rcv_wnd - subflow->rcv_wnd_sent;
+ subflow->rcv_wnd_sent = mptcp_rcv_wnd;
+}
+
static void ack_update_msk(struct mptcp_sock *msk,
struct sock *ssk,
struct mptcp_options_received *mp_opt)
@@ -1208,6 +1236,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
*/
if (mp_opt.use_ack)
ack_update_msk(msk, sk, &mp_opt);
+ rwin_update(msk, sk, skb);
/* Zero-data-length packets are dropped by the caller and not
* propagated to the MPTCP layer, so the skb extension does not
@@ -1294,6 +1323,10 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th)
if (rcv_wnd_new != rcv_wnd_old) {
raise_win:
+ /* The msk-level rcv wnd is after the tcp level one,
+ * sync the latter.
+ */
+ rcv_wnd_new = rcv_wnd_old;
win = rcv_wnd_old - ack_seq;
tp->rcv_wnd = min_t(u64, win, U32_MAX);
new_win = tp->rcv_wnd;
@@ -1317,6 +1350,21 @@ raise_win:
update_wspace:
WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
+ subflow->rcv_wnd_sent = rcv_wnd_new;
+}
+
+static void mptcp_track_rwin(struct tcp_sock *tp)
+{
+ const struct sock *ssk = (const struct sock *)tp;
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk;
+
+ if (!ssk)
+ return;
+
+ subflow = mptcp_subflow_ctx(ssk);
+ msk = mptcp_sk(subflow->conn);
+ WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
}
__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
@@ -1611,6 +1659,10 @@ mp_rst:
opts->reset_transient,
opts->reset_reason);
return;
+ } else if (unlikely(!opts->suboptions)) {
+ /* Fallback to TCP */
+ mptcp_track_rwin(tp);
+ return;
}
if (OPTION_MPTCP_PRIO & opts->suboptions) {
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 2ff1b9499568..9604b91902b8 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -18,6 +18,7 @@ struct mptcp_pm_add_entry {
u8 retrans_times;
struct timer_list add_timer;
struct mptcp_sock *sock;
+ struct rcu_head rcu;
};
static DEFINE_SPINLOCK(mptcp_pm_list_lock);
@@ -155,7 +156,7 @@ bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk,
entry = mptcp_pm_del_add_timer(msk, addr, false);
ret = entry;
- kfree(entry);
+ kfree_rcu(entry, rcu);
return ret;
}
@@ -345,22 +346,27 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
{
struct mptcp_pm_add_entry *entry;
struct sock *sk = (struct sock *)msk;
- struct timer_list *add_timer = NULL;
+ bool stop_timer = false;
+
+ rcu_read_lock();
spin_lock_bh(&msk->pm.lock);
entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
if (entry && (!check_id || entry->addr.id == addr->id)) {
entry->retrans_times = ADD_ADDR_RETRANS_MAX;
- add_timer = &entry->add_timer;
+ stop_timer = true;
}
if (!check_id && entry)
list_del(&entry->list);
spin_unlock_bh(&msk->pm.lock);
- /* no lock, because sk_stop_timer_sync() is calling timer_delete_sync() */
- if (add_timer)
- sk_stop_timer_sync(sk, add_timer);
+ /* Note: entry might have been removed by another thread.
+ * We hold rcu_read_lock() to ensure it is not freed under us.
+ */
+ if (stop_timer)
+ sk_stop_timer_sync(sk, &entry->add_timer);
+ rcu_read_unlock();
return entry;
}
@@ -415,7 +421,7 @@ static void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
list_for_each_entry_safe(entry, tmp, &free_list, list) {
sk_stop_timer_sync(sk, &entry->add_timer);
- kfree(entry);
+ kfree_rcu(entry, rcu);
}
}
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index 2ae95476dba3..0a50fd5edc06 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -672,7 +672,7 @@ 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)) {
+ 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);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e27e0fe2460f..a70267a74e3c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -76,6 +76,13 @@ bool __mptcp_try_fallback(struct mptcp_sock *msk, int fb_mib)
if (__mptcp_check_fallback(msk))
return true;
+ /* The caller possibly is not holding the msk socket lock, but
+ * in the fallback case only the current subflow is touching
+ * the OoO queue.
+ */
+ if (!RB_EMPTY_ROOT(&msk->out_of_order_queue))
+ return false;
+
spin_lock_bh(&msk->fallback_lock);
if (!msk->allow_infinite_fallback) {
spin_unlock_bh(&msk->fallback_lock);
@@ -2402,7 +2409,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
/* flags for __mptcp_close_ssk() */
#define MPTCP_CF_PUSH BIT(1)
-#define MPTCP_CF_FASTCLOSE BIT(2)
/* be sure to send a reset only if the caller asked for it, also
* clean completely the subflow status when the subflow reaches
@@ -2413,7 +2419,7 @@ static void __mptcp_subflow_disconnect(struct sock *ssk,
unsigned int flags)
{
if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
- (flags & MPTCP_CF_FASTCLOSE)) {
+ subflow->send_fastclose) {
/* The MPTCP code never wait on the subflow sockets, TCP-level
* disconnect should never fail
*/
@@ -2460,14 +2466,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
- if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) {
- /* be sure to force the tcp_close path
- * to generate the egress reset
- */
- ssk->sk_lingertime = 0;
- sock_set_flag(ssk, SOCK_LINGER);
- subflow->send_fastclose = 1;
- }
+ if (subflow->send_fastclose && ssk->sk_state != TCP_CLOSE)
+ tcp_set_state(ssk, TCP_CLOSE);
need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
if (!dispose_it) {
@@ -2563,7 +2563,8 @@ static void __mptcp_close_subflow(struct sock *sk)
if (ssk_state != TCP_CLOSE &&
(ssk_state != TCP_CLOSE_WAIT ||
- inet_sk_state_load(sk) != TCP_ESTABLISHED))
+ inet_sk_state_load(sk) != TCP_ESTABLISHED ||
+ __mptcp_check_fallback(msk)))
continue;
/* 'subflow_data_ready' will re-sched once rx queue is empty */
@@ -2771,9 +2772,26 @@ static void mptcp_do_fastclose(struct sock *sk)
struct mptcp_sock *msk = mptcp_sk(sk);
mptcp_set_state(sk, TCP_CLOSE);
- mptcp_for_each_subflow_safe(msk, subflow, tmp)
- __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow),
- subflow, MPTCP_CF_FASTCLOSE);
+
+ /* Explicitly send the fastclose reset as need */
+ if (__mptcp_check_fallback(msk))
+ return;
+
+ mptcp_for_each_subflow_safe(msk, subflow, tmp) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ lock_sock(ssk);
+
+ /* Some subflow socket states don't allow/need a reset.*/
+ if ((1 << ssk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+ goto unlock;
+
+ subflow->send_fastclose = 1;
+ tcp_send_active_reset(ssk, ssk->sk_allocation,
+ SK_RST_REASON_TCP_ABORT_ON_CLOSE);
+unlock:
+ release_sock(ssk);
+ }
}
static void mptcp_worker(struct work_struct *work)
@@ -2800,7 +2818,11 @@ static void mptcp_worker(struct work_struct *work)
__mptcp_close_subflow(sk);
if (mptcp_close_tout_expired(sk)) {
+ struct mptcp_subflow_context *subflow, *tmp;
+
mptcp_do_fastclose(sk);
+ mptcp_for_each_subflow_safe(msk, subflow, tmp)
+ __mptcp_close_ssk(sk, subflow->tcp_sock, subflow, 0);
mptcp_close_wake_up(sk);
}
@@ -3225,7 +3247,8 @@ static int mptcp_disconnect(struct sock *sk, int flags)
/* msk->subflow is still intact, the following will not free the first
* subflow
*/
- mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
+ mptcp_do_fastclose(sk);
+ mptcp_destroy_common(msk);
/* The first subflow is already in TCP_CLOSE status, the following
* can't overlap with a fallback anymore
@@ -3404,7 +3427,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
}
-void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
+void mptcp_destroy_common(struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow, *tmp;
struct sock *sk = (struct sock *)msk;
@@ -3413,7 +3436,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
/* join list will be eventually flushed (with rst) at sock lock release time */
mptcp_for_each_subflow_safe(msk, subflow, tmp)
- __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags);
+ __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, 0);
__skb_queue_purge(&sk->sk_receive_queue);
skb_rbtree_purge(&msk->out_of_order_queue);
@@ -3431,7 +3454,7 @@ static void mptcp_destroy(struct sock *sk)
/* allow the following to close even the initial subflow */
msk->free_first = 1;
- mptcp_destroy_common(msk, 0);
+ mptcp_destroy_common(msk);
sk_sockets_allocated_dec(sk);
}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 379a88e14e8d..6ca97096607c 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -509,6 +509,7 @@ struct mptcp_subflow_context {
u64 remote_key;
u64 idsn;
u64 map_seq;
+ u64 rcv_wnd_sent;
u32 snd_isn;
u32 token;
u32 rel_write_seq;
@@ -976,7 +977,7 @@ static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk)
local_bh_enable();
}
-void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags);
+void mptcp_destroy_common(struct mptcp_sock *msk);
#define MPTCP_TOKEN_MAX_RETRIES 4
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 768098dec231..833c3616d2a2 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2954,6 +2954,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
u = unix_sk(sk);
+redo:
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
*/
@@ -2965,7 +2966,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
struct sk_buff *skb, *last;
int chunk;
-redo:
unix_state_lock(sk);
if (sock_flag(sk, SOCK_DEAD)) {
err = -ECONNRESET;
@@ -3015,7 +3015,6 @@ again:
goto out;
}
- mutex_lock(&u->iolock);
goto redo;
unlock:
unix_state_unlock(sk);
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 44b9de6e4e77..52ae0e034d29 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -438,7 +438,7 @@ ok:
check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET &&
x->props.mode == XFRM_MODE_TUNNEL;
- switch (x->inner_mode.family) {
+ switch (skb_dst(skb)->ops->family) {
case AF_INET:
/* Check for IPv4 options */
if (ip_hdr(skb)->ihl != 5)
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 9077730ff7d0..54222fcbd7fd 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -698,7 +698,7 @@ static void xfrm_get_inner_ipproto(struct sk_buff *skb, struct xfrm_state *x)
return;
if (x->outer_mode.encap == XFRM_MODE_TUNNEL) {
- switch (x->outer_mode.family) {
+ switch (skb_dst(skb)->ops->family) {
case AF_INET:
xo->inner_ipproto = ip_hdr(skb)->protocol;
break;
@@ -772,8 +772,12 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
/* Exclusive direct xmit for tunnel mode, as
* some filtering or matching rules may apply
* in transport mode.
+ * Locally generated packets also require
+ * the normal XFRM path for L2 header setup,
+ * as the hardware needs the L2 header to match
+ * for encryption, so skip direct output as well.
*/
- if (x->props.mode == XFRM_MODE_TUNNEL)
+ if (x->props.mode == XFRM_MODE_TUNNEL && !skb->sk)
return xfrm_dev_direct_output(sk, x, skb);
return xfrm_output_resume(sk, skb, 0);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index d213ca3653a8..9e14e453b55c 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -592,6 +592,7 @@ void xfrm_state_free(struct xfrm_state *x)
}
EXPORT_SYMBOL(xfrm_state_free);
+static void xfrm_state_delete_tunnel(struct xfrm_state *x);
static void xfrm_state_gc_destroy(struct xfrm_state *x)
{
if (x->mode_cbs && x->mode_cbs->destroy_state)
@@ -607,6 +608,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x)
kfree(x->replay_esn);
kfree(x->preplay_esn);
xfrm_unset_type_offload(x);
+ xfrm_state_delete_tunnel(x);
if (x->type) {
x->type->destructor(x);
xfrm_put_type(x->type);
@@ -806,7 +808,6 @@ void __xfrm_state_destroy(struct xfrm_state *x)
}
EXPORT_SYMBOL(__xfrm_state_destroy);
-static void xfrm_state_delete_tunnel(struct xfrm_state *x);
int __xfrm_state_delete(struct xfrm_state *x)
{
struct net *net = xs_net(x);
@@ -2073,6 +2074,7 @@ static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig,
return x;
error:
+ x->km.state = XFRM_STATE_DEAD;
xfrm_state_put(x);
out:
return NULL;
@@ -2157,11 +2159,15 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
xfrm_state_insert(xc);
} else {
if (xfrm_state_add(xc) < 0)
- goto error;
+ goto error_add;
}
return xc;
+error_add:
+ if (xuo)
+ xfrm_dev_state_delete(xc);
error:
+ xc->km.state = XFRM_STATE_DEAD;
xfrm_state_put(xc);
return NULL;
}
@@ -2191,14 +2197,18 @@ int xfrm_state_update(struct xfrm_state *x)
}
if (x1->km.state == XFRM_STATE_ACQ) {
- if (x->dir && x1->dir != x->dir)
+ if (x->dir && x1->dir != x->dir) {
+ to_put = x1;
goto out;
+ }
__xfrm_state_insert(x);
x = NULL;
} else {
- if (x1->dir != x->dir)
+ if (x1->dir != x->dir) {
+ to_put = x1;
goto out;
+ }
}
err = 0;
@@ -3298,6 +3308,7 @@ out_bydst:
void xfrm_state_fini(struct net *net)
{
unsigned int sz;
+ int i;
flush_work(&net->xfrm.state_hash_work);
xfrm_state_flush(net, 0, false);
@@ -3305,14 +3316,17 @@ void xfrm_state_fini(struct net *net)
WARN_ON(!list_empty(&net->xfrm.state_all));
+ for (i = 0; i <= net->xfrm.state_hmask; i++) {
+ WARN_ON(!hlist_empty(net->xfrm.state_byseq + i));
+ WARN_ON(!hlist_empty(net->xfrm.state_byspi + i));
+ WARN_ON(!hlist_empty(net->xfrm.state_bysrc + i));
+ WARN_ON(!hlist_empty(net->xfrm.state_bydst + i));
+ }
+
sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head);
- WARN_ON(!hlist_empty(net->xfrm.state_byseq));
xfrm_hash_free(net->xfrm.state_byseq, sz);
- WARN_ON(!hlist_empty(net->xfrm.state_byspi));
xfrm_hash_free(net->xfrm.state_byspi, sz);
- WARN_ON(!hlist_empty(net->xfrm.state_bysrc));
xfrm_hash_free(net->xfrm.state_bysrc, sz);
- WARN_ON(!hlist_empty(net->xfrm.state_bydst));
xfrm_hash_free(net->xfrm.state_bydst, sz);
free_percpu(net->xfrm.state_cache_input);
}
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 010c9e6638c0..403b5ecac2c5 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -947,8 +947,11 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
if (attrs[XFRMA_SA_PCPU]) {
x->pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]);
- if (x->pcpu_num >= num_possible_cpus())
+ if (x->pcpu_num >= num_possible_cpus()) {
+ err = -ERANGE;
+ NL_SET_ERR_MSG(extack, "pCPU number too big");
goto error;
+ }
}
err = __xfrm_init_state(x, extack);
@@ -3035,6 +3038,9 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh,
}
xfrm_state_free(x);
+ xfrm_dev_policy_delete(xp);
+ xfrm_dev_policy_free(xp);
+ security_xfrm_policy_free(xp->security);
kfree(xp);
return 0;
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 439101b518ee..8f9850a71f54 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -45,6 +45,7 @@ skf_net_off
socket
so_incoming_cpu
so_netns_cookie
+so_peek_off
so_txtime
so_rcv_listener
stress_reuseport_listen
diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile
index de805cbbdf69..528d14c598bb 100644
--- a/tools/testing/selftests/net/af_unix/Makefile
+++ b/tools/testing/selftests/net/af_unix/Makefile
@@ -6,6 +6,7 @@ TEST_GEN_PROGS := \
scm_inq \
scm_pidfd \
scm_rights \
+ so_peek_off \
unix_connect \
# end of TEST_GEN_PROGS
diff --git a/tools/testing/selftests/net/af_unix/so_peek_off.c b/tools/testing/selftests/net/af_unix/so_peek_off.c
new file mode 100644
index 000000000000..1a77728128e5
--- /dev/null
+++ b/tools/testing/selftests/net/af_unix/so_peek_off.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2025 Google LLC */
+
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+
+#include "../../kselftest_harness.h"
+
+FIXTURE(so_peek_off)
+{
+ int fd[2]; /* 0: sender, 1: receiver */
+};
+
+FIXTURE_VARIANT(so_peek_off)
+{
+ int type;
+};
+
+FIXTURE_VARIANT_ADD(so_peek_off, stream)
+{
+ .type = SOCK_STREAM,
+};
+
+FIXTURE_VARIANT_ADD(so_peek_off, dgram)
+{
+ .type = SOCK_DGRAM,
+};
+
+FIXTURE_VARIANT_ADD(so_peek_off, seqpacket)
+{
+ .type = SOCK_SEQPACKET,
+};
+
+FIXTURE_SETUP(so_peek_off)
+{
+ struct timeval timeout = {
+ .tv_sec = 0,
+ .tv_usec = 3000,
+ };
+ int ret;
+
+ ret = socketpair(AF_UNIX, variant->type, 0, self->fd);
+ ASSERT_EQ(0, ret);
+
+ ret = setsockopt(self->fd[1], SOL_SOCKET, SO_RCVTIMEO_NEW,
+ &timeout, sizeof(timeout));
+ ASSERT_EQ(0, ret);
+
+ ret = setsockopt(self->fd[1], SOL_SOCKET, SO_PEEK_OFF,
+ &(int){0}, sizeof(int));
+ ASSERT_EQ(0, ret);
+}
+
+FIXTURE_TEARDOWN(so_peek_off)
+{
+ close_range(self->fd[0], self->fd[1], 0);
+}
+
+#define sendeq(fd, str, flags) \
+ do { \
+ int bytes, len = strlen(str); \
+ \
+ bytes = send(fd, str, len, flags); \
+ ASSERT_EQ(len, bytes); \
+ } while (0)
+
+#define recveq(fd, str, buflen, flags) \
+ do { \
+ char buf[(buflen) + 1] = {}; \
+ int bytes; \
+ \
+ bytes = recv(fd, buf, buflen, flags); \
+ ASSERT_NE(-1, bytes); \
+ ASSERT_STREQ(str, buf); \
+ } while (0)
+
+#define async \
+ for (pid_t pid = (pid = fork(), \
+ pid < 0 ? \
+ __TH_LOG("Failed to start async {}"), \
+ _metadata->exit_code = KSFT_FAIL, \
+ __bail(1, _metadata), \
+ 0xdead : \
+ pid); \
+ !pid; exit(0))
+
+TEST_F(so_peek_off, single_chunk)
+{
+ sendeq(self->fd[0], "aaaabbbb", 0);
+
+ recveq(self->fd[1], "aaaa", 4, MSG_PEEK);
+ recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+}
+
+TEST_F(so_peek_off, two_chunks)
+{
+ sendeq(self->fd[0], "aaaa", 0);
+ sendeq(self->fd[0], "bbbb", 0);
+
+ recveq(self->fd[1], "aaaa", 4, MSG_PEEK);
+ recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+}
+
+TEST_F(so_peek_off, two_chunks_blocking)
+{
+ async {
+ usleep(1000);
+ sendeq(self->fd[0], "aaaa", 0);
+ }
+
+ recveq(self->fd[1], "aaaa", 4, MSG_PEEK);
+
+ async {
+ usleep(1000);
+ sendeq(self->fd[0], "bbbb", 0);
+ }
+
+ /* goto again; -> goto redo; in unix_stream_read_generic(). */
+ recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+}
+
+TEST_F(so_peek_off, two_chunks_overlap)
+{
+ sendeq(self->fd[0], "aaaa", 0);
+ recveq(self->fd[1], "aa", 2, MSG_PEEK);
+
+ sendeq(self->fd[0], "bbbb", 0);
+
+ if (variant->type == SOCK_STREAM) {
+ /* SOCK_STREAM tries to fill the buffer. */
+ recveq(self->fd[1], "aabb", 4, MSG_PEEK);
+ recveq(self->fd[1], "bb", 100, MSG_PEEK);
+ } else {
+ /* SOCK_DGRAM and SOCK_SEQPACKET returns at the skb boundary. */
+ recveq(self->fd[1], "aa", 100, MSG_PEEK);
+ recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+ }
+}
+
+TEST_F(so_peek_off, two_chunks_overlap_blocking)
+{
+ async {
+ usleep(1000);
+ sendeq(self->fd[0], "aaaa", 0);
+ }
+
+ recveq(self->fd[1], "aa", 2, MSG_PEEK);
+
+ async {
+ usleep(1000);
+ sendeq(self->fd[0], "bbbb", 0);
+ }
+
+ /* Even SOCK_STREAM does not wait if at least one byte is read. */
+ recveq(self->fd[1], "aa", 100, MSG_PEEK);
+
+ recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 41503c241989..43f31f8d587f 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3500,7 +3500,6 @@ fullmesh_tests()
fastclose_tests()
{
if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then
- MPTCP_LIB_SUBTEST_FLAKY=1
test_linkfail=1024 fastclose=client \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 0 0 0
@@ -3509,7 +3508,6 @@ fastclose_tests()
fi
if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then
- MPTCP_LIB_SUBTEST_FLAKY=1
test_linkfail=1024 fastclose=server \
run_tests $ns1 $ns2 10.0.1.1
join_rst_nr=1 \
@@ -3806,7 +3804,7 @@ userspace_tests()
continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
set_userspace_pm $ns1
pm_nl_set_limits $ns2 2 2
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
wait_mpj $ns1
@@ -3839,7 +3837,7 @@ userspace_tests()
continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
set_userspace_pm $ns2
pm_nl_set_limits $ns1 0 1
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
wait_mpj $ns2
@@ -3867,7 +3865,7 @@ userspace_tests()
continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
set_userspace_pm $ns2
pm_nl_set_limits $ns1 0 1
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
wait_mpj $ns2
@@ -3888,7 +3886,7 @@ userspace_tests()
continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
set_userspace_pm $ns2
pm_nl_set_limits $ns1 0 1
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
wait_mpj $ns2
@@ -3912,7 +3910,7 @@ userspace_tests()
continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
set_userspace_pm $ns1
pm_nl_set_limits $ns2 1 1
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
wait_mpj $ns1
@@ -3943,7 +3941,7 @@ endpoint_tests()
pm_nl_set_limits $ns1 2 2
pm_nl_set_limits $ns2 2 2
pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
- { test_linkfail=128 speed=slow \
+ { timeout_test=120 test_linkfail=128 speed=slow \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
@@ -3970,7 +3968,7 @@ endpoint_tests()
pm_nl_set_limits $ns2 0 3
pm_nl_add_endpoint $ns2 10.0.1.2 id 1 dev ns2eth1 flags subflow
pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
@@ -4048,7 +4046,7 @@ endpoint_tests()
# broadcast IP: no packet for this address will be received on ns1
pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
pm_nl_add_endpoint $ns1 10.0.1.1 id 42 flags signal
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
@@ -4057,38 +4055,45 @@ endpoint_tests()
$ns1 10.0.2.1 id 1 flags signal
chk_subflow_nr "before delete" 2
chk_mptcp_info subflows 1 subflows 1
+ chk_mptcp_info add_addr_signal 2 add_addr_accepted 1
pm_nl_del_endpoint $ns1 1 10.0.2.1
pm_nl_del_endpoint $ns1 2 224.0.0.1
sleep 0.5
chk_subflow_nr "after delete" 1
chk_mptcp_info subflows 0 subflows 0
+ chk_mptcp_info add_addr_signal 0 add_addr_accepted 0
pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal
wait_mpj $ns2
chk_subflow_nr "after re-add" 3
chk_mptcp_info subflows 2 subflows 2
+ chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
pm_nl_del_endpoint $ns1 42 10.0.1.1
sleep 0.5
chk_subflow_nr "after delete ID 0" 2
chk_mptcp_info subflows 2 subflows 2
+ chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal
wait_mpj $ns2
chk_subflow_nr "after re-add ID 0" 3
chk_mptcp_info subflows 3 subflows 3
+ chk_mptcp_info add_addr_signal 3 add_addr_accepted 2
pm_nl_del_endpoint $ns1 99 10.0.1.1
sleep 0.5
chk_subflow_nr "after re-delete ID 0" 2
chk_mptcp_info subflows 2 subflows 2
+ chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
pm_nl_add_endpoint $ns1 10.0.1.1 id 88 flags signal
wait_mpj $ns2
chk_subflow_nr "after re-re-add ID 0" 3
chk_mptcp_info subflows 3 subflows 3
+ chk_mptcp_info add_addr_signal 3 add_addr_accepted 2
mptcp_lib_kill_group_wait $tests_pid
kill_events_pids
@@ -4121,7 +4126,7 @@ endpoint_tests()
# broadcast IP: no packet for this address will be received on ns1
pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
- { test_linkfail=128 speed=20 \
+ { timeout_test=120 test_linkfail=128 speed=20 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
generated by cgit v1.2.3 (git 2.0.4) at 2025-12-13 15:32:25 +0000