net-sched-prohibit-regrafting-ingress-or-clsact-qdis.patch
net-sched-fix-null-pointer-dereference-in-mq_attach.patch
net-netlink-fix-netlink_list_memberships-length-repo.patch
-sock-expose-so_timestamp-options-for-mptcp.patch
-sock-expose-so_timestamping-options-for-mptcp.patch
-tcp-remove-sk_-tr-x_skb_cache.patch
udp6-fix-race-condition-in-udp6_sendmsg-connect.patch
net-mlx5-read-embedded-cpu-after-init-bit-cleared.patch
net-sched-flower-fix-possible-oob-write-in-fl_set_ge.patch
+++ /dev/null
-From 96be4aecebc993609750ce66ca31fc6396932e5d Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 3 Jun 2021 16:24:27 -0700
-Subject: sock: expose so_timestamp options for mptcp
-
-From: Florian Westphal <fw@strlen.de>
-
-[ Upstream commit 371087aa476ab0ac0072303ac94a3bba2d7b0a1d ]
-
-This exports SO_TIMESTAMP_* function for re-use by MPTCP.
-
-Without this there is too much copy & paste needed to support
-this from mptcp setsockopt path.
-
-Acked-by: Paolo Abeni <pabeni@redhat.com>
-Signed-off-by: Florian Westphal <fw@strlen.de>
-Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Stable-dep-of: 448a5ce1120c ("udp6: Fix race condition in udp6_sendmsg & connect")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/net/sock.h | 1 +
- net/core/sock.c | 26 +++++++++++++++++++-------
- 2 files changed, 20 insertions(+), 7 deletions(-)
-
-diff --git a/include/net/sock.h b/include/net/sock.h
-index 3da0601b573ed..09cd879d0dda1 100644
---- a/include/net/sock.h
-+++ b/include/net/sock.h
-@@ -2775,6 +2775,7 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)
- void sock_def_readable(struct sock *sk);
-
- int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk);
-+void sock_set_timestamp(struct sock *sk, int optname, bool valbool);
- void sock_enable_timestamps(struct sock *sk);
- void sock_no_linger(struct sock *sk);
- void sock_set_keepalive(struct sock *sk);
-diff --git a/net/core/sock.c b/net/core/sock.c
-index c5ae520d4a69c..7d421b0f863f9 100644
---- a/net/core/sock.c
-+++ b/net/core/sock.c
-@@ -768,6 +768,24 @@ void sock_enable_timestamps(struct sock *sk)
- }
- EXPORT_SYMBOL(sock_enable_timestamps);
-
-+void sock_set_timestamp(struct sock *sk, int optname, bool valbool)
-+{
-+ switch (optname) {
-+ case SO_TIMESTAMP_OLD:
-+ __sock_set_timestamps(sk, valbool, false, false);
-+ break;
-+ case SO_TIMESTAMP_NEW:
-+ __sock_set_timestamps(sk, valbool, true, false);
-+ break;
-+ case SO_TIMESTAMPNS_OLD:
-+ __sock_set_timestamps(sk, valbool, false, true);
-+ break;
-+ case SO_TIMESTAMPNS_NEW:
-+ __sock_set_timestamps(sk, valbool, true, true);
-+ break;
-+ }
-+}
-+
- void sock_set_keepalive(struct sock *sk)
- {
- lock_sock(sk);
-@@ -989,16 +1007,10 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
- break;
-
- case SO_TIMESTAMP_OLD:
-- __sock_set_timestamps(sk, valbool, false, false);
-- break;
- case SO_TIMESTAMP_NEW:
-- __sock_set_timestamps(sk, valbool, true, false);
-- break;
- case SO_TIMESTAMPNS_OLD:
-- __sock_set_timestamps(sk, valbool, false, true);
-- break;
- case SO_TIMESTAMPNS_NEW:
-- __sock_set_timestamps(sk, valbool, true, true);
-+ sock_set_timestamp(sk, valbool, optname);
- break;
- case SO_TIMESTAMPING_NEW:
- case SO_TIMESTAMPING_OLD:
---
-2.39.2
-
+++ /dev/null
-From 1022e0aacca2382b0b688397a993c595fa9a3a71 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 3 Jun 2021 16:24:28 -0700
-Subject: sock: expose so_timestamping options for mptcp
-
-From: Florian Westphal <fw@strlen.de>
-
-[ Upstream commit ced122d90f52eb6ff37272e32941845d46ac64c6 ]
-
-Similar to previous patch: expose SO_TIMESTAMPING helper so we do not
-have to copy & paste this into the mptcp core.
-
-Acked-by: Paolo Abeni <pabeni@redhat.com>
-Signed-off-by: Florian Westphal <fw@strlen.de>
-Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Stable-dep-of: 448a5ce1120c ("udp6: Fix race condition in udp6_sendmsg & connect")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/net/sock.h | 2 ++
- net/core/sock.c | 71 +++++++++++++++++++++++-----------------------
- 2 files changed, 38 insertions(+), 35 deletions(-)
-
-diff --git a/include/net/sock.h b/include/net/sock.h
-index 09cd879d0dda1..71bd4f6741f1e 100644
---- a/include/net/sock.h
-+++ b/include/net/sock.h
-@@ -2776,6 +2776,8 @@ void sock_def_readable(struct sock *sk);
-
- int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk);
- void sock_set_timestamp(struct sock *sk, int optname, bool valbool);
-+int sock_set_timestamping(struct sock *sk, int optname, int val);
-+
- void sock_enable_timestamps(struct sock *sk);
- void sock_no_linger(struct sock *sk);
- void sock_set_keepalive(struct sock *sk);
-diff --git a/net/core/sock.c b/net/core/sock.c
-index 7d421b0f863f9..b8f8252d36819 100644
---- a/net/core/sock.c
-+++ b/net/core/sock.c
-@@ -786,6 +786,40 @@ void sock_set_timestamp(struct sock *sk, int optname, bool valbool)
- }
- }
-
-+int sock_set_timestamping(struct sock *sk, int optname, int val)
-+{
-+ if (val & ~SOF_TIMESTAMPING_MASK)
-+ return -EINVAL;
-+
-+ if (val & SOF_TIMESTAMPING_OPT_ID &&
-+ !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
-+ if (sk->sk_protocol == IPPROTO_TCP &&
-+ sk->sk_type == SOCK_STREAM) {
-+ if ((1 << sk->sk_state) &
-+ (TCPF_CLOSE | TCPF_LISTEN))
-+ return -EINVAL;
-+ sk->sk_tskey = tcp_sk(sk)->snd_una;
-+ } else {
-+ sk->sk_tskey = 0;
-+ }
-+ }
-+
-+ if (val & SOF_TIMESTAMPING_OPT_STATS &&
-+ !(val & SOF_TIMESTAMPING_OPT_TSONLY))
-+ return -EINVAL;
-+
-+ sk->sk_tsflags = val;
-+ sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
-+
-+ if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
-+ sock_enable_timestamp(sk,
-+ SOCK_TIMESTAMPING_RX_SOFTWARE);
-+ else
-+ sock_disable_timestamp(sk,
-+ (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
-+ return 0;
-+}
-+
- void sock_set_keepalive(struct sock *sk)
- {
- lock_sock(sk);
-@@ -1012,43 +1046,10 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
- case SO_TIMESTAMPNS_NEW:
- sock_set_timestamp(sk, valbool, optname);
- break;
-+
- case SO_TIMESTAMPING_NEW:
- case SO_TIMESTAMPING_OLD:
-- if (val & ~SOF_TIMESTAMPING_MASK) {
-- ret = -EINVAL;
-- break;
-- }
--
-- if (val & SOF_TIMESTAMPING_OPT_ID &&
-- !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
-- if (sk->sk_protocol == IPPROTO_TCP &&
-- sk->sk_type == SOCK_STREAM) {
-- if ((1 << sk->sk_state) &
-- (TCPF_CLOSE | TCPF_LISTEN)) {
-- ret = -EINVAL;
-- break;
-- }
-- sk->sk_tskey = tcp_sk(sk)->snd_una;
-- } else {
-- sk->sk_tskey = 0;
-- }
-- }
--
-- if (val & SOF_TIMESTAMPING_OPT_STATS &&
-- !(val & SOF_TIMESTAMPING_OPT_TSONLY)) {
-- ret = -EINVAL;
-- break;
-- }
--
-- sk->sk_tsflags = val;
-- sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
--
-- if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
-- sock_enable_timestamp(sk,
-- SOCK_TIMESTAMPING_RX_SOFTWARE);
-- else
-- sock_disable_timestamp(sk,
-- (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
-+ ret = sock_set_timestamping(sk, optname, val);
- break;
-
- case SO_RCVLOWAT:
---
-2.39.2
-
+++ /dev/null
-From 9057e4395d8c2432bef26bad16c64a0a376298b9 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Wed, 22 Sep 2021 19:26:43 +0200
-Subject: tcp: remove sk_{tr}x_skb_cache
-
-From: Eric Dumazet <edumazet@google.com>
-
-[ Upstream commit d8b81175e412c7abebdb5b37d8a84d5fd19b1aad ]
-
-This reverts the following patches :
-
-- commit 2e05fcae83c4 ("tcp: fix compile error if !CONFIG_SYSCTL")
-- commit 4f661542a402 ("tcp: fix zerocopy and notsent_lowat issues")
-- commit 472c2e07eef0 ("tcp: add one skb cache for tx")
-- commit 8b27dae5a2e8 ("tcp: add one skb cache for rx")
-
-Having a cache of one skb (in each direction) per TCP socket is fragile,
-since it can cause a significant increase of memory needs,
-and not good enough for high speed flows anyway where more than one skb
-is needed.
-
-We want instead to add a generic infrastructure, with more flexible
-per-cpu caches, for alien NUMA nodes.
-
-Acked-by: Paolo Abeni <pabeni@redhat.com>
-Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
-Signed-off-by: Eric Dumazet <edumazet@google.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Stable-dep-of: 448a5ce1120c ("udp6: Fix race condition in udp6_sendmsg & connect")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- Documentation/networking/ip-sysctl.rst | 8 --------
- include/net/sock.h | 19 -------------------
- net/ipv4/af_inet.c | 4 ----
- net/ipv4/sysctl_net_ipv4.c | 12 ------------
- net/ipv4/tcp.c | 26 --------------------------
- net/ipv4/tcp_ipv4.c | 6 ------
- net/ipv6/tcp_ipv6.c | 6 ------
- 7 files changed, 81 deletions(-)
-
-diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
-index df26cf4110ef5..7a58e8c8edb24 100644
---- a/Documentation/networking/ip-sysctl.rst
-+++ b/Documentation/networking/ip-sysctl.rst
-@@ -916,14 +916,6 @@ tcp_challenge_ack_limit - INTEGER
- in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks)
- Default: 1000
-
--tcp_rx_skb_cache - BOOLEAN
-- Controls a per TCP socket cache of one skb, that might help
-- performance of some workloads. This might be dangerous
-- on systems with a lot of TCP sockets, since it increases
-- memory usage.
--
-- Default: 0 (disabled)
--
- UDP variables
- =============
-
-diff --git a/include/net/sock.h b/include/net/sock.h
-index 71bd4f6741f1e..eb96f39a19f35 100644
---- a/include/net/sock.h
-+++ b/include/net/sock.h
-@@ -258,7 +258,6 @@ struct bpf_local_storage;
- * @sk_dst_cache: destination cache
- * @sk_dst_pending_confirm: need to confirm neighbour
- * @sk_policy: flow policy
-- * @sk_rx_skb_cache: cache copy of recently accessed RX skb
- * @sk_receive_queue: incoming packets
- * @sk_wmem_alloc: transmit queue bytes committed
- * @sk_tsq_flags: TCP Small Queues flags
-@@ -320,7 +319,6 @@ struct bpf_local_storage;
- * @sk_peek_off: current peek_offset value
- * @sk_send_head: front of stuff to transmit
- * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head]
-- * @sk_tx_skb_cache: cache copy of recently accessed TX skb
- * @sk_security: used by security modules
- * @sk_mark: generic packet mark
- * @sk_cgrp_data: cgroup data for this cgroup
-@@ -386,7 +384,6 @@ struct sock {
- atomic_t sk_drops;
- int sk_rcvlowat;
- struct sk_buff_head sk_error_queue;
-- struct sk_buff *sk_rx_skb_cache;
- struct sk_buff_head sk_receive_queue;
- /*
- * The backlog queue is special, it is always used with
-@@ -436,7 +433,6 @@ struct sock {
- struct sk_buff *sk_send_head;
- struct rb_root tcp_rtx_queue;
- };
-- struct sk_buff *sk_tx_skb_cache;
- struct sk_buff_head sk_write_queue;
- __s32 sk_peek_off;
- int sk_write_pending;
-@@ -1557,18 +1553,10 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
- __sk_mem_reclaim(sk, 1 << 20);
- }
-
--DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
- static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
- {
- sk_wmem_queued_add(sk, -skb->truesize);
- sk_mem_uncharge(sk, skb->truesize);
-- if (static_branch_unlikely(&tcp_tx_skb_cache_key) &&
-- !sk->sk_tx_skb_cache && !skb_cloned(skb)) {
-- skb_ext_reset(skb);
-- skb_zcopy_clear(skb, true);
-- sk->sk_tx_skb_cache = skb;
-- return;
-- }
- __kfree_skb(skb);
- }
-
-@@ -2579,7 +2567,6 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
- &skb_shinfo(skb)->tskey);
- }
-
--DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
- /**
- * sk_eat_skb - Release a skb if it is no longer needed
- * @sk: socket to eat this skb from
-@@ -2591,12 +2578,6 @@ DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
- static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
- {
- __skb_unlink(skb, &sk->sk_receive_queue);
-- if (static_branch_unlikely(&tcp_rx_skb_cache_key) &&
-- !sk->sk_rx_skb_cache) {
-- sk->sk_rx_skb_cache = skb;
-- skb_orphan(skb);
-- return;
-- }
- __kfree_skb(skb);
- }
-
-diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
-index acb4887351daf..6a8d17c891e5e 100644
---- a/net/ipv4/af_inet.c
-+++ b/net/ipv4/af_inet.c
-@@ -133,10 +133,6 @@ void inet_sock_destruct(struct sock *sk)
- struct inet_sock *inet = inet_sk(sk);
-
- __skb_queue_purge(&sk->sk_receive_queue);
-- if (sk->sk_rx_skb_cache) {
-- __kfree_skb(sk->sk_rx_skb_cache);
-- sk->sk_rx_skb_cache = NULL;
-- }
- __skb_queue_purge(&sk->sk_error_queue);
-
- sk_mem_reclaim(sk);
-diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
-index 3a34e9768bff0..f9bdba88269aa 100644
---- a/net/ipv4/sysctl_net_ipv4.c
-+++ b/net/ipv4/sysctl_net_ipv4.c
-@@ -522,18 +522,6 @@ static struct ctl_table ipv4_table[] = {
- .extra1 = &sysctl_fib_sync_mem_min,
- .extra2 = &sysctl_fib_sync_mem_max,
- },
-- {
-- .procname = "tcp_rx_skb_cache",
-- .data = &tcp_rx_skb_cache_key.key,
-- .mode = 0644,
-- .proc_handler = proc_do_static_key,
-- },
-- {
-- .procname = "tcp_tx_skb_cache",
-- .data = &tcp_tx_skb_cache_key.key,
-- .mode = 0644,
-- .proc_handler = proc_do_static_key,
-- },
- { }
- };
-
-diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
-index 82abbf1929851..2eb044c55855f 100644
---- a/net/ipv4/tcp.c
-+++ b/net/ipv4/tcp.c
-@@ -318,11 +318,6 @@ struct tcp_splice_state {
- unsigned long tcp_memory_pressure __read_mostly;
- EXPORT_SYMBOL_GPL(tcp_memory_pressure);
-
--DEFINE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
--EXPORT_SYMBOL(tcp_rx_skb_cache_key);
--
--DEFINE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
--
- void tcp_enter_memory_pressure(struct sock *sk)
- {
- unsigned long val;
-@@ -870,18 +865,6 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
- {
- struct sk_buff *skb;
-
-- if (likely(!size)) {
-- skb = sk->sk_tx_skb_cache;
-- if (skb) {
-- skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
-- sk->sk_tx_skb_cache = NULL;
-- pskb_trim(skb, 0);
-- INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
-- skb_shinfo(skb)->tx_flags = 0;
-- memset(TCP_SKB_CB(skb), 0, sizeof(struct tcp_skb_cb));
-- return skb;
-- }
-- }
- /* The TCP header must be at least 32-bit aligned. */
- size = ALIGN(size, 4);
-
-@@ -2728,11 +2711,6 @@ void tcp_write_queue_purge(struct sock *sk)
- sk_wmem_free_skb(sk, skb);
- }
- tcp_rtx_queue_purge(sk);
-- skb = sk->sk_tx_skb_cache;
-- if (skb) {
-- __kfree_skb(skb);
-- sk->sk_tx_skb_cache = NULL;
-- }
- INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
- sk_mem_reclaim(sk);
- tcp_clear_all_retrans_hints(tcp_sk(sk));
-@@ -2775,10 +2753,6 @@ int tcp_disconnect(struct sock *sk, int flags)
-
- tcp_clear_xmit_timers(sk);
- __skb_queue_purge(&sk->sk_receive_queue);
-- if (sk->sk_rx_skb_cache) {
-- __kfree_skb(sk->sk_rx_skb_cache);
-- sk->sk_rx_skb_cache = NULL;
-- }
- WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
- tp->urg_data = 0;
- tcp_write_queue_purge(sk);
-diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
-index 270b20e0907c2..2a0878179b5ec 100644
---- a/net/ipv4/tcp_ipv4.c
-+++ b/net/ipv4/tcp_ipv4.c
-@@ -1944,7 +1944,6 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
- int tcp_v4_rcv(struct sk_buff *skb)
- {
- struct net *net = dev_net(skb->dev);
-- struct sk_buff *skb_to_free;
- int sdif = inet_sdif(skb);
- int dif = inet_iif(skb);
- const struct iphdr *iph;
-@@ -2079,17 +2078,12 @@ int tcp_v4_rcv(struct sk_buff *skb)
- tcp_segs_in(tcp_sk(sk), skb);
- ret = 0;
- if (!sock_owned_by_user(sk)) {
-- skb_to_free = sk->sk_rx_skb_cache;
-- sk->sk_rx_skb_cache = NULL;
- ret = tcp_v4_do_rcv(sk, skb);
- } else {
- if (tcp_add_backlog(sk, skb))
- goto discard_and_relse;
-- skb_to_free = NULL;
- }
- bh_unlock_sock(sk);
-- if (skb_to_free)
-- __kfree_skb(skb_to_free);
-
- put_and_return:
- if (refcounted)
-diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
-index fe29bc66aeac7..1d118a953abe6 100644
---- a/net/ipv6/tcp_ipv6.c
-+++ b/net/ipv6/tcp_ipv6.c
-@@ -1602,7 +1602,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
-
- INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
- {
-- struct sk_buff *skb_to_free;
- int sdif = inet6_sdif(skb);
- int dif = inet6_iif(skb);
- const struct tcphdr *th;
-@@ -1730,17 +1729,12 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
- tcp_segs_in(tcp_sk(sk), skb);
- ret = 0;
- if (!sock_owned_by_user(sk)) {
-- skb_to_free = sk->sk_rx_skb_cache;
-- sk->sk_rx_skb_cache = NULL;
- ret = tcp_v6_do_rcv(sk, skb);
- } else {
- if (tcp_add_backlog(sk, skb))
- goto discard_and_relse;
-- skb_to_free = NULL;
- }
- bh_unlock_sock(sk);
-- if (skb_to_free)
-- __kfree_skb(skb_to_free);
- put_and_return:
- if (refcounted)
- sock_put(sk);
---
-2.39.2
-
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
- net/core/sock.c | 2 +-
+ net/core/sock.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
-diff --git a/net/core/sock.c b/net/core/sock.c
-index b8f8252d36819..2fba329e8c7a5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
-@@ -2029,7 +2029,6 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
+@@ -2016,7 +2016,6 @@ void sk_setup_caps(struct sock *sk, stru
{
u32 max_segs = 1;
sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps;
if (sk->sk_route_caps & NETIF_F_GSO)
sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
-@@ -2044,6 +2043,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
+@@ -2031,6 +2030,7 @@ void sk_setup_caps(struct sock *sk, stru
}
}
sk->sk_gso_max_segs = max_segs;
}
EXPORT_SYMBOL_GPL(sk_setup_caps);
---
-2.39.2
-
+++ /dev/null
-From 73f99197b24d6a978a0abe975f0239f3c20c13ca Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Wed, 3 Nov 2021 13:47:32 -0700
-Subject: bpf, sockmap: Use stricter sk state checks in sk_lookup_assign
-
-From: John Fastabend <john.fastabend@gmail.com>
-
-[ Upstream commit 40a34121ac1dc52ed9cd34a8f4e48e32517a52fd ]
-
-In order to fix an issue with sockets in TCP sockmap redirect cases we plan
-to allow CLOSE state sockets to exist in the sockmap. However, the check in
-bpf_sk_lookup_assign() currently only invalidates sockets in the
-TCP_ESTABLISHED case relying on the checks on sockmap insert to ensure we
-never SOCK_CLOSE state sockets in the map.
-
-To prepare for this change we flip the logic in bpf_sk_lookup_assign() to
-explicitly test for the accepted cases. Namely, a tcp socket in TCP_LISTEN
-or a udp socket in TCP_CLOSE state. This also makes the code more resilent
-to future changes.
-
-Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
-Signed-off-by: John Fastabend <john.fastabend@gmail.com>
-Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
-Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
-Link: https://lore.kernel.org/bpf/20211103204736.248403-2-john.fastabend@gmail.com
-Stable-dep-of: 448a5ce1120c ("udp6: Fix race condition in udp6_sendmsg & connect")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/linux/skmsg.h | 12 ++++++++++++
- net/core/filter.c | 6 ++++--
- net/core/sock_map.c | 6 ------
- 3 files changed, 16 insertions(+), 8 deletions(-)
-
-diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
-index 6e18ca234f812..fe2fbf1685494 100644
---- a/include/linux/skmsg.h
-+++ b/include/linux/skmsg.h
-@@ -505,6 +505,18 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
- return !!psock->saved_data_ready;
- }
-
-+static inline bool sk_is_tcp(const struct sock *sk)
-+{
-+ return sk->sk_type == SOCK_STREAM &&
-+ sk->sk_protocol == IPPROTO_TCP;
-+}
-+
-+static inline bool sk_is_udp(const struct sock *sk)
-+{
-+ return sk->sk_type == SOCK_DGRAM &&
-+ sk->sk_protocol == IPPROTO_UDP;
-+}
-+
- #if IS_ENABLED(CONFIG_NET_SOCK_MSG)
-
- #define BPF_F_STRPARSER (1UL << 1)
-diff --git a/net/core/filter.c b/net/core/filter.c
-index 519315a1acf3a..a28c51f4ab232 100644
---- a/net/core/filter.c
-+++ b/net/core/filter.c
-@@ -10508,8 +10508,10 @@ BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx,
- return -EINVAL;
- if (unlikely(sk && sk_is_refcounted(sk)))
- return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */
-- if (unlikely(sk && sk->sk_state == TCP_ESTABLISHED))
-- return -ESOCKTNOSUPPORT; /* reject connected sockets */
-+ if (unlikely(sk && sk_is_tcp(sk) && sk->sk_state != TCP_LISTEN))
-+ return -ESOCKTNOSUPPORT; /* only accept TCP socket in LISTEN */
-+ if (unlikely(sk && sk_is_udp(sk) && sk->sk_state != TCP_CLOSE))
-+ return -ESOCKTNOSUPPORT; /* only accept UDP socket in CLOSE */
-
- /* Check if socket is suitable for packet L3/L4 protocol */
- if (sk && sk->sk_protocol != ctx->protocol)
-diff --git a/net/core/sock_map.c b/net/core/sock_map.c
-index 86b4e8909ad1e..60774b79f2e3a 100644
---- a/net/core/sock_map.c
-+++ b/net/core/sock_map.c
-@@ -523,12 +523,6 @@ static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops)
- ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB;
- }
-
--static bool sk_is_tcp(const struct sock *sk)
--{
-- return sk->sk_type == SOCK_STREAM &&
-- sk->sk_protocol == IPPROTO_TCP;
--}
--
- static bool sock_map_redirect_allowed(const struct sock *sk)
- {
- if (sk_is_tcp(sk))
---
-2.39.2
-
net-sched-prohibit-regrafting-ingress-or-clsact-qdis.patch
net-sched-fix-null-pointer-dereference-in-mq_attach.patch
net-netlink-fix-netlink_list_memberships-length-repo.patch
-tcp-remove-sk_-tr-x_skb_cache.patch
-bpf-sockmap-use-stricter-sk-state-checks-in-sk_looku.patch
udp6-fix-race-condition-in-udp6_sendmsg-connect.patch
net-mlx5e-fix-error-handling-in-mlx5e_refresh_tirs.patch
net-mlx5-read-embedded-cpu-after-init-bit-cleared.patch
+++ /dev/null
-From a838f15e78adc8752ce13a6661ccef7216e20478 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Wed, 22 Sep 2021 19:26:43 +0200
-Subject: tcp: remove sk_{tr}x_skb_cache
-
-From: Eric Dumazet <edumazet@google.com>
-
-[ Upstream commit d8b81175e412c7abebdb5b37d8a84d5fd19b1aad ]
-
-This reverts the following patches :
-
-- commit 2e05fcae83c4 ("tcp: fix compile error if !CONFIG_SYSCTL")
-- commit 4f661542a402 ("tcp: fix zerocopy and notsent_lowat issues")
-- commit 472c2e07eef0 ("tcp: add one skb cache for tx")
-- commit 8b27dae5a2e8 ("tcp: add one skb cache for rx")
-
-Having a cache of one skb (in each direction) per TCP socket is fragile,
-since it can cause a significant increase of memory needs,
-and not good enough for high speed flows anyway where more than one skb
-is needed.
-
-We want instead to add a generic infrastructure, with more flexible
-per-cpu caches, for alien NUMA nodes.
-
-Acked-by: Paolo Abeni <pabeni@redhat.com>
-Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
-Signed-off-by: Eric Dumazet <edumazet@google.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Stable-dep-of: 448a5ce1120c ("udp6: Fix race condition in udp6_sendmsg & connect")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- Documentation/networking/ip-sysctl.rst | 8 --------
- include/net/sock.h | 19 -------------------
- net/ipv4/af_inet.c | 4 ----
- net/ipv4/sysctl_net_ipv4.c | 12 ------------
- net/ipv4/tcp.c | 26 --------------------------
- net/ipv4/tcp_ipv4.c | 6 ------
- net/ipv6/tcp_ipv6.c | 6 ------
- 7 files changed, 81 deletions(-)
-
-diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
-index 7890b395e629b..a4d0082bd3b90 100644
---- a/Documentation/networking/ip-sysctl.rst
-+++ b/Documentation/networking/ip-sysctl.rst
-@@ -991,14 +991,6 @@ tcp_challenge_ack_limit - INTEGER
- in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks)
- Default: 1000
-
--tcp_rx_skb_cache - BOOLEAN
-- Controls a per TCP socket cache of one skb, that might help
-- performance of some workloads. This might be dangerous
-- on systems with a lot of TCP sockets, since it increases
-- memory usage.
--
-- Default: 0 (disabled)
--
- UDP variables
- =============
-
-diff --git a/include/net/sock.h b/include/net/sock.h
-index 104d80d850e41..d0683b3c57456 100644
---- a/include/net/sock.h
-+++ b/include/net/sock.h
-@@ -261,7 +261,6 @@ struct bpf_local_storage;
- * @sk_dst_cache: destination cache
- * @sk_dst_pending_confirm: need to confirm neighbour
- * @sk_policy: flow policy
-- * @sk_rx_skb_cache: cache copy of recently accessed RX skb
- * @sk_receive_queue: incoming packets
- * @sk_wmem_alloc: transmit queue bytes committed
- * @sk_tsq_flags: TCP Small Queues flags
-@@ -328,7 +327,6 @@ struct bpf_local_storage;
- * @sk_peek_off: current peek_offset value
- * @sk_send_head: front of stuff to transmit
- * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head]
-- * @sk_tx_skb_cache: cache copy of recently accessed TX skb
- * @sk_security: used by security modules
- * @sk_mark: generic packet mark
- * @sk_cgrp_data: cgroup data for this cgroup
-@@ -394,7 +392,6 @@ struct sock {
- atomic_t sk_drops;
- int sk_rcvlowat;
- struct sk_buff_head sk_error_queue;
-- struct sk_buff *sk_rx_skb_cache;
- struct sk_buff_head sk_receive_queue;
- /*
- * The backlog queue is special, it is always used with
-@@ -447,7 +444,6 @@ struct sock {
- struct sk_buff *sk_send_head;
- struct rb_root tcp_rtx_queue;
- };
-- struct sk_buff *sk_tx_skb_cache;
- struct sk_buff_head sk_write_queue;
- __s32 sk_peek_off;
- int sk_write_pending;
-@@ -1596,18 +1592,10 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
- __sk_mem_reclaim(sk, 1 << 20);
- }
-
--DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
- static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
- {
- sk_wmem_queued_add(sk, -skb->truesize);
- sk_mem_uncharge(sk, skb->truesize);
-- if (static_branch_unlikely(&tcp_tx_skb_cache_key) &&
-- !sk->sk_tx_skb_cache && !skb_cloned(skb)) {
-- skb_ext_reset(skb);
-- skb_zcopy_clear(skb, true);
-- sk->sk_tx_skb_cache = skb;
-- return;
-- }
- __kfree_skb(skb);
- }
-
-@@ -2667,7 +2655,6 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
- &skb_shinfo(skb)->tskey);
- }
-
--DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
- /**
- * sk_eat_skb - Release a skb if it is no longer needed
- * @sk: socket to eat this skb from
-@@ -2679,12 +2666,6 @@ DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
- static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
- {
- __skb_unlink(skb, &sk->sk_receive_queue);
-- if (static_branch_unlikely(&tcp_rx_skb_cache_key) &&
-- !sk->sk_rx_skb_cache) {
-- sk->sk_rx_skb_cache = skb;
-- skb_orphan(skb);
-- return;
-- }
- __kfree_skb(skb);
- }
-
-diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
-index e46b11507edc2..4d1c55723ad56 100644
---- a/net/ipv4/af_inet.c
-+++ b/net/ipv4/af_inet.c
-@@ -133,10 +133,6 @@ void inet_sock_destruct(struct sock *sk)
- struct inet_sock *inet = inet_sk(sk);
-
- __skb_queue_purge(&sk->sk_receive_queue);
-- if (sk->sk_rx_skb_cache) {
-- __kfree_skb(sk->sk_rx_skb_cache);
-- sk->sk_rx_skb_cache = NULL;
-- }
- __skb_queue_purge(&sk->sk_error_queue);
-
- sk_mem_reclaim(sk);
-diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
-index 1f22e72074fdc..1aa3ecaf456c7 100644
---- a/net/ipv4/sysctl_net_ipv4.c
-+++ b/net/ipv4/sysctl_net_ipv4.c
-@@ -540,18 +540,6 @@ static struct ctl_table ipv4_table[] = {
- .extra1 = &sysctl_fib_sync_mem_min,
- .extra2 = &sysctl_fib_sync_mem_max,
- },
-- {
-- .procname = "tcp_rx_skb_cache",
-- .data = &tcp_rx_skb_cache_key.key,
-- .mode = 0644,
-- .proc_handler = proc_do_static_key,
-- },
-- {
-- .procname = "tcp_tx_skb_cache",
-- .data = &tcp_tx_skb_cache_key.key,
-- .mode = 0644,
-- .proc_handler = proc_do_static_key,
-- },
- { }
- };
-
-diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
-index fc0fa1f2ca9b1..bd7930b2be278 100644
---- a/net/ipv4/tcp.c
-+++ b/net/ipv4/tcp.c
-@@ -325,11 +325,6 @@ struct tcp_splice_state {
- unsigned long tcp_memory_pressure __read_mostly;
- EXPORT_SYMBOL_GPL(tcp_memory_pressure);
-
--DEFINE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
--EXPORT_SYMBOL(tcp_rx_skb_cache_key);
--
--DEFINE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
--
- void tcp_enter_memory_pressure(struct sock *sk)
- {
- unsigned long val;
-@@ -866,18 +861,6 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
- {
- struct sk_buff *skb;
-
-- if (likely(!size)) {
-- skb = sk->sk_tx_skb_cache;
-- if (skb) {
-- skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
-- sk->sk_tx_skb_cache = NULL;
-- pskb_trim(skb, 0);
-- INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
-- skb_shinfo(skb)->tx_flags = 0;
-- memset(TCP_SKB_CB(skb), 0, sizeof(struct tcp_skb_cb));
-- return skb;
-- }
-- }
- /* The TCP header must be at least 32-bit aligned. */
- size = ALIGN(size, 4);
-
-@@ -2952,11 +2935,6 @@ void tcp_write_queue_purge(struct sock *sk)
- sk_wmem_free_skb(sk, skb);
- }
- tcp_rtx_queue_purge(sk);
-- skb = sk->sk_tx_skb_cache;
-- if (skb) {
-- __kfree_skb(skb);
-- sk->sk_tx_skb_cache = NULL;
-- }
- INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
- sk_mem_reclaim(sk);
- tcp_clear_all_retrans_hints(tcp_sk(sk));
-@@ -2999,10 +2977,6 @@ int tcp_disconnect(struct sock *sk, int flags)
-
- tcp_clear_xmit_timers(sk);
- __skb_queue_purge(&sk->sk_receive_queue);
-- if (sk->sk_rx_skb_cache) {
-- __kfree_skb(sk->sk_rx_skb_cache);
-- sk->sk_rx_skb_cache = NULL;
-- }
- WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
- tp->urg_data = 0;
- tcp_write_queue_purge(sk);
-diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
-index db05ab4287e30..45d12484552fc 100644
---- a/net/ipv4/tcp_ipv4.c
-+++ b/net/ipv4/tcp_ipv4.c
-@@ -1975,7 +1975,6 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
- int tcp_v4_rcv(struct sk_buff *skb)
- {
- struct net *net = dev_net(skb->dev);
-- struct sk_buff *skb_to_free;
- int sdif = inet_sdif(skb);
- int dif = inet_iif(skb);
- const struct iphdr *iph;
-@@ -2124,17 +2123,12 @@ int tcp_v4_rcv(struct sk_buff *skb)
- tcp_segs_in(tcp_sk(sk), skb);
- ret = 0;
- if (!sock_owned_by_user(sk)) {
-- skb_to_free = sk->sk_rx_skb_cache;
-- sk->sk_rx_skb_cache = NULL;
- ret = tcp_v4_do_rcv(sk, skb);
- } else {
- if (tcp_add_backlog(sk, skb))
- goto discard_and_relse;
-- skb_to_free = NULL;
- }
- bh_unlock_sock(sk);
-- if (skb_to_free)
-- __kfree_skb(skb_to_free);
-
- put_and_return:
- if (refcounted)
-diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
-index b6f5a4474d8bc..7b81ab2b57011 100644
---- a/net/ipv6/tcp_ipv6.c
-+++ b/net/ipv6/tcp_ipv6.c
-@@ -1626,7 +1626,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
-
- INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
- {
-- struct sk_buff *skb_to_free;
- int sdif = inet6_sdif(skb);
- int dif = inet6_iif(skb);
- const struct tcphdr *th;
-@@ -1762,17 +1761,12 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
- tcp_segs_in(tcp_sk(sk), skb);
- ret = 0;
- if (!sock_owned_by_user(sk)) {
-- skb_to_free = sk->sk_rx_skb_cache;
-- sk->sk_rx_skb_cache = NULL;
- ret = tcp_v6_do_rcv(sk, skb);
- } else {
- if (tcp_add_backlog(sk, skb))
- goto discard_and_relse;
-- skb_to_free = NULL;
- }
- bh_unlock_sock(sk);
-- if (skb_to_free)
-- __kfree_skb(skb_to_free);
- put_and_return:
- if (refcounted)
- sock_put(sk);
---
-2.39.2
-
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
- net/core/sock.c | 2 +-
+ net/core/sock.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
-diff --git a/net/core/sock.c b/net/core/sock.c
-index ff7e8fc80731d..93fb3d64f48ee 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
-@@ -2165,7 +2165,6 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
+@@ -2165,7 +2165,6 @@ void sk_setup_caps(struct sock *sk, stru
{
u32 max_segs = 1;
sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps;
if (sk->sk_route_caps & NETIF_F_GSO)
sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
-@@ -2180,6 +2179,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
+@@ -2180,6 +2179,7 @@ void sk_setup_caps(struct sock *sk, stru
}
}
sk->sk_gso_max_segs = max_segs;
}
EXPORT_SYMBOL_GPL(sk_setup_caps);
---
-2.39.2
-
projects / thirdparty / kernel / stable-queue.git / commitdiff
