From b118509076b39cc5e616c0680312b5caaca535fe Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 26 Aug 2022 08:49:16 +0200
Subject: netfilter: remove nf_conntrack_helper sysctl and modparam toggles

__nf_ct_try_assign_helper() remains in place but it now requires a
template to configure the helper.

A toggle to disable automatic helper assignment was added by:

  a9006892643a ("netfilter: nf_ct_helper: allow to disable automatic helper assignment")

in 2012 to address the issues described in "Secure use of iptables and
connection tracking helpers". Automatic conntrack helper assignment was
disabled by:

  3bb398d925ec ("netfilter: nf_ct_helper: disable automatic helper assignment")

back in 2016.

This patch removes the sysctl and modparam toggles, users now have to
rely on explicit conntrack helper configuration via ruleset.

Update tools/testing/selftests/netfilter/nft_conntrack_helper.sh to
check that auto-assignment does not happen anymore.

Acked-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack.h | 2 --
 include/net/netns/conntrack.h        | 1 -
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index a32be8aa7ed2..6a2019aaa464 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -53,8 +53,6 @@ struct nf_conntrack_net {
 	/* only used when new connection is allocated: */
 	atomic_t count;
 	unsigned int expect_count;
-	u8 sysctl_auto_assign_helper;
-	bool auto_assign_helper_warned;
 
 	/* only used from work queues, configuration plane, and so on: */
 	unsigned int users4;
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index c396a3862e80..e1290c159184 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -101,7 +101,6 @@ struct netns_ct {
 	u8			sysctl_log_invalid; /* Log invalid packets */
 	u8			sysctl_events;
 	u8			sysctl_acct;
-	u8			sysctl_auto_assign_helper;
 	u8			sysctl_tstamp;
 	u8			sysctl_checksum;
 
-- 
cgit v1.2.3


From ac56a0b48da86fd1b4389632fb7c4c8a5d86eefa Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 26 Aug 2022 15:39:28 +0100
Subject: rxrpc: Fix ICMP/ICMP6 error handling

Because rxrpc pretends to be a tunnel on top of a UDP/UDP6 socket, allowing
it to siphon off UDP packets early in the handling of received UDP packets
thereby avoiding the packet going through the UDP receive queue, it doesn't
get ICMP packets through the UDP ->sk_error_report() callback.  In fact, it
doesn't appear that there's any usable option for getting hold of ICMP
packets.

Fix this by adding a new UDP encap hook to distribute error messages for
UDP tunnels.  If the hook is set, then the tunnel driver will be able to
see ICMP packets.  The hook provides the offset into the packet of the UDP
header of the original packet that caused the notification.

An alternative would be to call the ->error_handler() hook - but that
requires that the skbuff be cloned (as ip_icmp_error() or ipv6_cmp_error()
do, though isn't really necessary or desirable in rxrpc's case is we want
to parse them there and then, not queue them).

Changes
=======
ver #3)
 - Fixed an uninitialised variable.

ver #2)
 - Fixed some missing CONFIG_AF_RXRPC_IPV6 conditionals.

Fixes: 5271953cad31 ("rxrpc: Use the UDP encap_rcv hook")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/linux/udp.h        |   1 +
 include/net/udp_tunnel.h   |   4 +
 net/ipv4/udp.c             |   2 +
 net/ipv4/udp_tunnel_core.c |   1 +
 net/ipv6/udp.c             |   5 +-
 net/rxrpc/ar-internal.h    |   1 +
 net/rxrpc/local_object.c   |   1 +
 net/rxrpc/peer_event.c     | 293 +++++++++++++++++++++++++++++++++++++++------
 8 files changed, 270 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/udp.h b/include/linux/udp.h
index 254a2654400f..e96da4157d04 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -70,6 +70,7 @@ struct udp_sock {
 	 * For encapsulation sockets.
 	 */
 	int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
+	void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset);
 	int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb);
 	void (*encap_destroy)(struct sock *sk);
 
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index afc7ce713657..72394f441dad 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -67,6 +67,9 @@ static inline int udp_sock_create(struct net *net,
 typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
 typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk,
 					     struct sk_buff *skb);
+typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk,
+					   struct sk_buff *skb,
+					   unsigned int udp_offset);
 typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
 typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
 						    struct list_head *head,
@@ -80,6 +83,7 @@ struct udp_tunnel_sock_cfg {
 	__u8  encap_type;
 	udp_tunnel_encap_rcv_t encap_rcv;
 	udp_tunnel_encap_err_lookup_t encap_err_lookup;
+	udp_tunnel_encap_err_rcv_t encap_err_rcv;
 	udp_tunnel_encap_destroy_t encap_destroy;
 	udp_tunnel_gro_receive_t gro_receive;
 	udp_tunnel_gro_complete_t gro_complete;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 34eda973bbf1..cd72158e953a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -783,6 +783,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	 */
 	if (tunnel) {
 		/* ...not for tunnels though: we don't have a sending socket */
+		if (udp_sk(sk)->encap_err_rcv)
+			udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2);
 		goto out;
 	}
 	if (!inet->recverr) {
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index 8efaf8c3fe2a..8242c8947340 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -72,6 +72,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 
 	udp_sk(sk)->encap_type = cfg->encap_type;
 	udp_sk(sk)->encap_rcv = cfg->encap_rcv;
+	udp_sk(sk)->encap_err_rcv = cfg->encap_err_rcv;
 	udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup;
 	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
 	udp_sk(sk)->gro_receive = cfg->gro_receive;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 16c176e7c69a..3366d6a77ff2 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -616,8 +616,11 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	}
 
 	/* Tunnels don't have an application socket: don't pass errors back */
-	if (tunnel)
+	if (tunnel) {
+		if (udp_sk(sk)->encap_err_rcv)
+			udp_sk(sk)->encap_err_rcv(sk, skb, offset);
 		goto out;
+	}
 
 	if (!np->recverr) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 571436064cd6..62c70709d798 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -982,6 +982,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
 /*
  * peer_event.c
  */
+void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset);
 void rxrpc_error_report(struct sock *);
 void rxrpc_peer_keepalive_worker(struct work_struct *);
 
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 96ecb7356c0f..79bb02eb67b2 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -137,6 +137,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 
 	tuncfg.encap_type = UDP_ENCAP_RXRPC;
 	tuncfg.encap_rcv = rxrpc_input_packet;
+	tuncfg.encap_err_rcv = rxrpc_encap_err_rcv;
 	tuncfg.sk_user_data = local;
 	setup_udp_tunnel_sock(net, local->socket, &tuncfg);
 
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index be032850ae8c..32561e9567fe 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -16,22 +16,105 @@
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include <net/ip.h>
+#include <net/icmp.h>
 #include "ar-internal.h"
 
+static void rxrpc_adjust_mtu(struct rxrpc_peer *, unsigned int);
 static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
 static void rxrpc_distribute_error(struct rxrpc_peer *, int,
 				   enum rxrpc_call_completion);
 
 /*
- * Find the peer associated with an ICMP packet.
+ * Find the peer associated with an ICMPv4 packet.
  */
 static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
-						     const struct sk_buff *skb,
+						     struct sk_buff *skb,
+						     unsigned int udp_offset,
+						     unsigned int *info,
 						     struct sockaddr_rxrpc *srx)
 {
-	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+	struct iphdr *ip, *ip0 = ip_hdr(skb);
+	struct icmphdr *icmp = icmp_hdr(skb);
+	struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset);
 
-	_enter("");
+	_enter("%u,%u,%u", ip0->protocol, icmp->type, icmp->code);
+
+	switch (icmp->type) {
+	case ICMP_DEST_UNREACH:
+		*info = ntohs(icmp->un.frag.mtu);
+		fallthrough;
+	case ICMP_TIME_EXCEEDED:
+	case ICMP_PARAMETERPROB:
+		ip = (struct iphdr *)((void *)icmp + 8);
+		break;
+	default:
+		return NULL;
+	}
+
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport_len = local->srx.transport_len;
+	srx->transport.family = local->srx.transport.family;
+
+	/* Can we see an ICMP4 packet on an ICMP6 listening socket?  and vice
+	 * versa?
+	 */
+	switch (srx->transport.family) {
+	case AF_INET:
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr, &ip->daddr,
+		       sizeof(struct in_addr));
+		break;
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case AF_INET6:
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr, &ip->daddr,
+		       sizeof(struct in_addr));
+		break;
+#endif
+
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	_net("ICMP {%pISp}", &srx->transport);
+	return rxrpc_lookup_peer_rcu(local, srx);
+}
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+/*
+ * Find the peer associated with an ICMPv6 packet.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_icmp6_rcu(struct rxrpc_local *local,
+						      struct sk_buff *skb,
+						      unsigned int udp_offset,
+						      unsigned int *info,
+						      struct sockaddr_rxrpc *srx)
+{
+	struct icmp6hdr *icmp = icmp6_hdr(skb);
+	struct ipv6hdr *ip, *ip0 = ipv6_hdr(skb);
+	struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset);
+
+	_enter("%u,%u,%u", ip0->nexthdr, icmp->icmp6_type, icmp->icmp6_code);
+
+	switch (icmp->icmp6_type) {
+	case ICMPV6_DEST_UNREACH:
+		*info = ntohl(icmp->icmp6_mtu);
+		fallthrough;
+	case ICMPV6_PKT_TOOBIG:
+	case ICMPV6_TIME_EXCEED:
+	case ICMPV6_PARAMPROB:
+		ip = (struct ipv6hdr *)((void *)icmp + 8);
+		break;
+	default:
+		return NULL;
+	}
 
 	memset(srx, 0, sizeof(*srx));
 	srx->transport_type = local->srx.transport_type;
@@ -41,6 +124,165 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 	/* Can we see an ICMP4 packet on an ICMP6 listening socket?  and vice
 	 * versa?
 	 */
+	switch (srx->transport.family) {
+	case AF_INET:
+		_net("Rx ICMP6 on v4 sock");
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr,
+		       &ip->daddr.s6_addr32[3], sizeof(struct in_addr));
+		break;
+	case AF_INET6:
+		_net("Rx ICMP6");
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin6.sin6_addr, &ip->daddr,
+		       sizeof(struct in6_addr));
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	_net("ICMP {%pISp}", &srx->transport);
+	return rxrpc_lookup_peer_rcu(local, srx);
+}
+#endif /* CONFIG_AF_RXRPC_IPV6 */
+
+/*
+ * Handle an error received on the local endpoint as a tunnel.
+ */
+void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb,
+			 unsigned int udp_offset)
+{
+	struct sock_extended_err ee;
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_local *local;
+	struct rxrpc_peer *peer;
+	unsigned int info = 0;
+	int err;
+	u8 version = ip_hdr(skb)->version;
+	u8 type = icmp_hdr(skb)->type;
+	u8 code = icmp_hdr(skb)->code;
+
+	rcu_read_lock();
+	local = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!local)) {
+		rcu_read_unlock();
+		return;
+	}
+
+	rxrpc_new_skb(skb, rxrpc_skb_received);
+
+	switch (ip_hdr(skb)->version) {
+	case IPVERSION:
+		peer = rxrpc_lookup_peer_icmp_rcu(local, skb, udp_offset,
+						  &info, &srx);
+		break;
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case 6:
+		peer = rxrpc_lookup_peer_icmp6_rcu(local, skb, udp_offset,
+						   &info, &srx);
+		break;
+#endif
+	default:
+		rcu_read_unlock();
+		return;
+	}
+
+	if (peer && !rxrpc_get_peer_maybe(peer))
+		peer = NULL;
+	if (!peer) {
+		rcu_read_unlock();
+		return;
+	}
+
+	memset(&ee, 0, sizeof(ee));
+
+	switch (version) {
+	case IPVERSION:
+		switch (type) {
+		case ICMP_DEST_UNREACH:
+			switch (code) {
+			case ICMP_FRAG_NEEDED:
+				rxrpc_adjust_mtu(peer, info);
+				rcu_read_unlock();
+				rxrpc_put_peer(peer);
+				return;
+			default:
+				break;
+			}
+
+			err = EHOSTUNREACH;
+			if (code <= NR_ICMP_UNREACH) {
+				/* Might want to do something different with
+				 * non-fatal errors
+				 */
+				//harderr = icmp_err_convert[code].fatal;
+				err = icmp_err_convert[code].errno;
+			}
+			break;
+
+		case ICMP_TIME_EXCEEDED:
+			err = EHOSTUNREACH;
+			break;
+		default:
+			err = EPROTO;
+			break;
+		}
+
+		ee.ee_origin = SO_EE_ORIGIN_ICMP;
+		ee.ee_type = type;
+		ee.ee_code = code;
+		ee.ee_errno = err;
+		break;
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case 6:
+		switch (type) {
+		case ICMPV6_PKT_TOOBIG:
+			rxrpc_adjust_mtu(peer, info);
+			rcu_read_unlock();
+			rxrpc_put_peer(peer);
+			return;
+		}
+
+		icmpv6_err_convert(type, code, &err);
+
+		if (err == EACCES)
+			err = EHOSTUNREACH;
+
+		ee.ee_origin = SO_EE_ORIGIN_ICMP6;
+		ee.ee_type = type;
+		ee.ee_code = code;
+		ee.ee_errno = err;
+		break;
+#endif
+	}
+
+	trace_rxrpc_rx_icmp(peer, &ee, &srx);
+
+	rxrpc_distribute_error(peer, err, RXRPC_CALL_NETWORK_ERROR);
+	rcu_read_unlock();
+	rxrpc_put_peer(peer);
+}
+
+/*
+ * Find the peer associated with a local error.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_local_rcu(struct rxrpc_local *local,
+						      const struct sk_buff *skb,
+						      struct sockaddr_rxrpc *srx)
+{
+	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+
+	_enter("");
+
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport_len = local->srx.transport_len;
+	srx->transport.family = local->srx.transport.family;
+
 	switch (srx->transport.family) {
 	case AF_INET:
 		srx->transport_len = sizeof(srx->transport.sin);
@@ -104,10 +346,8 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 /*
  * Handle an MTU/fragmentation problem.
  */
-static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr)
+static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu)
 {
-	u32 mtu = serr->ee.ee_info;
-
 	_net("Rx ICMP Fragmentation Needed (%d)", mtu);
 
 	/* wind down the local interface MTU */
@@ -148,7 +388,7 @@ void rxrpc_error_report(struct sock *sk)
 	struct sock_exterr_skb *serr;
 	struct sockaddr_rxrpc srx;
 	struct rxrpc_local *local;
-	struct rxrpc_peer *peer;
+	struct rxrpc_peer *peer = NULL;
 	struct sk_buff *skb;
 
 	rcu_read_lock();
@@ -172,41 +412,20 @@ void rxrpc_error_report(struct sock *sk)
 	}
 	rxrpc_new_skb(skb, rxrpc_skb_received);
 	serr = SKB_EXT_ERR(skb);
-	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
-		_leave("UDP empty message");
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		return;
-	}
 
-	peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
-	if (peer && !rxrpc_get_peer_maybe(peer))
-		peer = NULL;
-	if (!peer) {
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		_leave(" [no peer]");
-		return;
-	}
-
-	trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
-
-	if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
-	     serr->ee.ee_type == ICMP_DEST_UNREACH &&
-	     serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
-		rxrpc_adjust_mtu(peer, serr);
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		rxrpc_put_peer(peer);
-		_leave(" [MTU update]");
-		return;
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) {
+		peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx);
+		if (peer && !rxrpc_get_peer_maybe(peer))
+			peer = NULL;
+		if (peer) {
+			trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
+			rxrpc_store_error(peer, serr);
+		}
 	}
 
-	rxrpc_store_error(peer, serr);
 	rcu_read_unlock();
 	rxrpc_free_skb(skb, rxrpc_skb_freed);
 	rxrpc_put_peer(peer);
-
 	_leave("");
 }
 
-- 
cgit v1.2.3


From 21457f4a91cb522f1a3ad9741ff1d25fadfaa3c5 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 31 Aug 2022 13:24:44 +0100
Subject: rxrpc: Remove rxrpc_get_reply_time() which is no longer used

Remove rxrpc_get_reply_time() as that is no longer used now that the call
issue time is used instead of the reply time.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 Documentation/networking/rxrpc.rst | 11 ----------
 include/net/af_rxrpc.h             |  2 --
 net/rxrpc/recvmsg.c                | 43 --------------------------------------
 3 files changed, 56 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst
index 39c2249c7aa7..39494a6ea739 100644
--- a/Documentation/networking/rxrpc.rst
+++ b/Documentation/networking/rxrpc.rst
@@ -1055,17 +1055,6 @@ The kernel interface functions are as follows:
      first function to change.  Note that this must be called in TASK_RUNNING
      state.
 
- (#) Get reply timestamp::
-
-	bool rxrpc_kernel_get_reply_time(struct socket *sock,
-					 struct rxrpc_call *call,
-					 ktime_t *_ts)
-
-     This allows the timestamp on the first DATA packet of the reply of a
-     client call to be queried, provided that it is still in the Rx ring.  If
-     successful, the timestamp will be stored into ``*_ts`` and true will be
-     returned; false will be returned otherwise.
-
  (#) Get remote client epoch::
 
 	u32 rxrpc_kernel_get_epoch(struct socket *sock,
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index cee5f83c0f11..b69ca695935c 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -66,8 +66,6 @@ int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
 void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
 bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *);
 u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *);
-bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *,
-				 ktime_t *);
 bool rxrpc_kernel_call_is_complete(struct rxrpc_call *);
 void rxrpc_kernel_set_max_life(struct socket *, struct rxrpc_call *,
 			       unsigned long);
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 250f23bc1c07..7e39c262fd79 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -771,46 +771,3 @@ call_complete:
 	goto out;
 }
 EXPORT_SYMBOL(rxrpc_kernel_recv_data);
-
-/**
- * rxrpc_kernel_get_reply_time - Get timestamp on first reply packet
- * @sock: The socket that the call exists on
- * @call: The call to query
- * @_ts: Where to put the timestamp
- *
- * Retrieve the timestamp from the first DATA packet of the reply if it is
- * in the ring.  Returns true if successful, false if not.
- */
-bool rxrpc_kernel_get_reply_time(struct socket *sock, struct rxrpc_call *call,
-				 ktime_t *_ts)
-{
-	struct sk_buff *skb;
-	rxrpc_seq_t hard_ack, top, seq;
-	bool success = false;
-
-	mutex_lock(&call->user_mutex);
-
-	if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_RECV_REPLY)
-		goto out;
-
-	hard_ack = call->rx_hard_ack;
-	if (hard_ack != 0)
-		goto out;
-
-	seq = hard_ack + 1;
-	top = smp_load_acquire(&call->rx_top);
-	if (after(seq, top))
-		goto out;
-
-	skb = call->rxtx_buffer[seq & RXRPC_RXTX_BUFF_MASK];
-	if (!skb)
-		goto out;
-
-	*_ts = skb_get_ktime(skb);
-	success = true;
-
-out:
-	mutex_unlock(&call->user_mutex);
-	return success;
-}
-EXPORT_SYMBOL(rxrpc_kernel_get_reply_time);
-- 
cgit v1.2.3


From 3261400639463a853ba2b3be8bd009c2a8089775 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 31 Aug 2022 23:38:09 +0000
Subject: tcp: TX zerocopy should not sense pfmemalloc status

We got a recent syzbot report [1] showing a possible misuse
of pfmemalloc page status in TCP zerocopy paths.

Indeed, for pages coming from user space or other layers,
using page_is_pfmemalloc() is moot, and possibly could give
false positives.

There has been attempts to make page_is_pfmemalloc() more robust,
but not using it in the first place in this context is probably better,
removing cpu cycles.

Note to stable teams :

You need to backport 84ce071e38a6 ("net: introduce
__skb_fill_page_desc_noacc") as a prereq.

Race is more probable after commit c07aea3ef4d4
("mm: add a signature in struct page") because page_is_pfmemalloc()
is now using low order bit from page->lru.next, which can change
more often than page->index.

Low order bit should never be set for lru.next (when used as an anchor
in LRU list), so KCSAN report is mostly a false positive.

Backporting to older kernel versions seems not necessary.

[1]
BUG: KCSAN: data-race in lru_add_fn / tcp_build_frag

write to 0xffffea0004a1d2c8 of 8 bytes by task 18600 on cpu 0:
__list_add include/linux/list.h:73 [inline]
list_add include/linux/list.h:88 [inline]
lruvec_add_folio include/linux/mm_inline.h:105 [inline]
lru_add_fn+0x440/0x520 mm/swap.c:228
folio_batch_move_lru+0x1e1/0x2a0 mm/swap.c:246
folio_batch_add_and_move mm/swap.c:263 [inline]
folio_add_lru+0xf1/0x140 mm/swap.c:490
filemap_add_folio+0xf8/0x150 mm/filemap.c:948
__filemap_get_folio+0x510/0x6d0 mm/filemap.c:1981
pagecache_get_page+0x26/0x190 mm/folio-compat.c:104
grab_cache_page_write_begin+0x2a/0x30 mm/folio-compat.c:116
ext4_da_write_begin+0x2dd/0x5f0 fs/ext4/inode.c:2988
generic_perform_write+0x1d4/0x3f0 mm/filemap.c:3738
ext4_buffered_write_iter+0x235/0x3e0 fs/ext4/file.c:270
ext4_file_write_iter+0x2e3/0x1210
call_write_iter include/linux/fs.h:2187 [inline]
new_sync_write fs/read_write.c:491 [inline]
vfs_write+0x468/0x760 fs/read_write.c:578
ksys_write+0xe8/0x1a0 fs/read_write.c:631
__do_sys_write fs/read_write.c:643 [inline]
__se_sys_write fs/read_write.c:640 [inline]
__x64_sys_write+0x3e/0x50 fs/read_write.c:640
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

read to 0xffffea0004a1d2c8 of 8 bytes by task 18611 on cpu 1:
page_is_pfmemalloc include/linux/mm.h:1740 [inline]
__skb_fill_page_desc include/linux/skbuff.h:2422 [inline]
skb_fill_page_desc include/linux/skbuff.h:2443 [inline]
tcp_build_frag+0x613/0xb20 net/ipv4/tcp.c:1018
do_tcp_sendpages+0x3e8/0xaf0 net/ipv4/tcp.c:1075
tcp_sendpage_locked net/ipv4/tcp.c:1140 [inline]
tcp_sendpage+0x89/0xb0 net/ipv4/tcp.c:1150
inet_sendpage+0x7f/0xc0 net/ipv4/af_inet.c:833
kernel_sendpage+0x184/0x300 net/socket.c:3561
sock_sendpage+0x5a/0x70 net/socket.c:1054
pipe_to_sendpage+0x128/0x160 fs/splice.c:361
splice_from_pipe_feed fs/splice.c:415 [inline]
__splice_from_pipe+0x222/0x4d0 fs/splice.c:559
splice_from_pipe fs/splice.c:594 [inline]
generic_splice_sendpage+0x89/0xc0 fs/splice.c:743
do_splice_from fs/splice.c:764 [inline]
direct_splice_actor+0x80/0xa0 fs/splice.c:931
splice_direct_to_actor+0x305/0x620 fs/splice.c:886
do_splice_direct+0xfb/0x180 fs/splice.c:974
do_sendfile+0x3bf/0x910 fs/read_write.c:1249
__do_sys_sendfile64 fs/read_write.c:1317 [inline]
__se_sys_sendfile64 fs/read_write.c:1303 [inline]
__x64_sys_sendfile64+0x10c/0x150 fs/read_write.c:1303
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x0000000000000000 -> 0xffffea0004a1d288

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 18611 Comm: syz-executor.4 Not tainted 6.0.0-rc2-syzkaller-00248-ge022620b5d05-dirty #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/22/2022

Fixes: c07aea3ef4d4 ("mm: add a signature in struct page")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 21 +++++++++++++++++++++
 net/core/datagram.c    |  2 +-
 net/ipv4/tcp.c         |  2 +-
 3 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ca8afa382bf2..18e163a3460d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2444,6 +2444,27 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
 	skb_shinfo(skb)->nr_frags = i + 1;
 }
 
+/**
+ * skb_fill_page_desc_noacc - initialise a paged fragment in an skb
+ * @skb: buffer containing fragment to be initialised
+ * @i: paged fragment index to initialise
+ * @page: the page to use for this fragment
+ * @off: the offset to the data with @page
+ * @size: the length of the data
+ *
+ * Variant of skb_fill_page_desc() which does not deal with
+ * pfmemalloc, if page is not owned by us.
+ */
+static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i,
+					    struct page *page, int off,
+					    int size)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+	__skb_fill_page_desc_noacc(shinfo, i, page, off, size);
+	shinfo->nr_frags = i + 1;
+}
+
 void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
 		     int size, unsigned int truesize);
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 7255531f63ae..e4ff2db40c98 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -677,7 +677,7 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 				page_ref_sub(last_head, refs);
 				refs = 0;
 			}
-			skb_fill_page_desc(skb, frag++, head, start, size);
+			skb_fill_page_desc_noacc(skb, frag++, head, start, size);
 		}
 		if (refs)
 			page_ref_sub(last_head, refs);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e5011c136fdb..6cdfce6f2867 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1015,7 +1015,7 @@ new_segment:
 		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 	} else {
 		get_page(page);
-		skb_fill_page_desc(skb, i, page, offset, copy);
+		skb_fill_page_desc_noacc(skb, i, page, offset, copy);
 	}
 
 	if (!(flags & MSG_NO_SHARED_FRAGS))
-- 
cgit v1.2.3


From 2aec909912da55a6e469fd6ee8412080a5433ed2 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Aug 2022 11:46:38 +0200
Subject: wifi: use struct_group to copy addresses

We sometimes copy all the addresses from the 802.11 header
for the AAD, which may cause complaints from fortify checks.
Use struct_group() to avoid the compiler warnings/errors.

Change-Id: Ic3ea389105e7813b22095b295079eecdabde5045
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h          | 8 +++++---
 net/mac80211/wpa.c                 | 4 ++--
 net/wireless/lib80211_crypt_ccmp.c | 2 +-
 3 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 55e6f4ad0ca6..b6e6d5b40774 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -310,9 +310,11 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2)
 struct ieee80211_hdr {
 	__le16 frame_control;
 	__le16 duration_id;
-	u8 addr1[ETH_ALEN];
-	u8 addr2[ETH_ALEN];
-	u8 addr3[ETH_ALEN];
+	struct_group(addrs,
+		u8 addr1[ETH_ALEN];
+		u8 addr2[ETH_ALEN];
+		u8 addr3[ETH_ALEN];
+	);
 	__le16 seq_ctrl;
 	u8 addr4[ETH_ALEN];
 } __packed __aligned(2);
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index 93ec2f349748..20f742b5503b 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -351,7 +351,7 @@ static u8 ccmp_gcmp_aad(struct sk_buff *skb, u8 *aad)
 	 * FC | A1 | A2 | A3 | SC | [A4] | [QC] */
 	put_unaligned_be16(len_a, &aad[0]);
 	put_unaligned(mask_fc, (__le16 *)&aad[2]);
-	memcpy(&aad[4], &hdr->addr1, 3 * ETH_ALEN);
+	memcpy(&aad[4], &hdr->addrs, 3 * ETH_ALEN);
 
 	/* Mask Seq#, leave Frag# */
 	aad[22] = *((u8 *) &hdr->seq_ctrl) & 0x0f;
@@ -792,7 +792,7 @@ static void bip_aad(struct sk_buff *skb, u8 *aad)
 				IEEE80211_FCTL_MOREDATA);
 	put_unaligned(mask_fc, (__le16 *) &aad[0]);
 	/* A1 || A2 || A3 */
-	memcpy(aad + 2, &hdr->addr1, 3 * ETH_ALEN);
+	memcpy(aad + 2, &hdr->addrs, 3 * ETH_ALEN);
 }
 
 
diff --git a/net/wireless/lib80211_crypt_ccmp.c b/net/wireless/lib80211_crypt_ccmp.c
index 6a5f08f7491e..cca5e1cf089e 100644
--- a/net/wireless/lib80211_crypt_ccmp.c
+++ b/net/wireless/lib80211_crypt_ccmp.c
@@ -136,7 +136,7 @@ static int ccmp_init_iv_and_aad(const struct ieee80211_hdr *hdr,
 	pos = (u8 *) hdr;
 	aad[0] = pos[0] & 0x8f;
 	aad[1] = pos[1] & 0xc7;
-	memcpy(aad + 2, hdr->addr1, 3 * ETH_ALEN);
+	memcpy(aad + 2, &hdr->addrs, 3 * ETH_ALEN);
 	pos = (u8 *) & hdr->seq_ctrl;
 	aad[20] = pos[0] & 0x0f;
 	aad[21] = 0;		/* all bits masked */
-- 
cgit v1.2.3


From 9cb252c4c1c53ae58bc565bab76e98133288f23a Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Mon, 5 Sep 2022 11:50:15 +0800
Subject: net: skb: export skb drop reaons to user by TRACE_DEFINE_ENUM

As Eric reported, the 'reason' field is not presented when trace the
kfree_skb event by perf:

$ perf record -e skb:kfree_skb -a sleep 10
$ perf script
  ip_defrag 14605 [021]   221.614303:   skb:kfree_skb:
  skbaddr=0xffff9d2851242700 protocol=34525 location=0xffffffffa39346b1
  reason:

The cause seems to be passing kernel address directly to TP_printk(),
which is not right. As the enum 'skb_drop_reason' is not exported to
user space through TRACE_DEFINE_ENUM(), perf can't get the drop reason
string from the 'reason' field, which is a number.

Therefore, we introduce the macro DEFINE_DROP_REASON(), which is used
to define the trace enum by TRACE_DEFINE_ENUM(). With the help of
DEFINE_DROP_REASON(), now we can remove the auto-generate that we
introduced in the commit ec43908dd556
("net: skb: use auto-generation to convert skb drop reason to string"),
and define the string array 'drop_reasons'.

Hmmmm...now we come back to the situation that have to maintain drop
reasons in both enum skb_drop_reason and DEFINE_DROP_REASON. But they
are both in dropreason.h, which makes it easier.

After this commit, now the format of kfree_skb is like this:

$ cat /tracing/events/skb/kfree_skb/format
name: kfree_skb
ID: 1524
format:
        field:unsigned short common_type;       offset:0;       size:2; signed:0;
        field:unsigned char common_flags;       offset:2;       size:1; signed:0;
        field:unsigned char common_preempt_count;       offset:3;       size:1; signed:0;
        field:int common_pid;   offset:4;       size:4; signed:1;

        field:void * skbaddr;   offset:8;       size:8; signed:0;
        field:void * location;  offset:16;      size:8; signed:0;
        field:unsigned short protocol;  offset:24;      size:2; signed:0;
        field:enum skb_drop_reason reason;      offset:28;      size:4; signed:0;

print fmt: "skbaddr=%p protocol=%u location=%p reason: %s", REC->skbaddr, REC->protocol, REC->location, __print_symbolic(REC->reason, { 1, "NOT_SPECIFIED" }, { 2, "NO_SOCKET" } ......

Fixes: ec43908dd556 ("net: skb: use auto-generation to convert skb drop reason to string")
Link: https://lore.kernel.org/netdev/CANn89i+bx0ybvE55iMYf5GJM48WwV1HNpdm9Q6t-HaEstqpCSA@mail.gmail.com/
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dropreason.h   | 67 ++++++++++++++++++++++++++++++++++++++++++++++
 include/trace/events/skb.h | 15 ++++++++++-
 net/core/.gitignore        |  1 -
 net/core/Makefile          | 22 +--------------
 net/core/skbuff.c          |  6 ++++-
 5 files changed, 87 insertions(+), 24 deletions(-)
 delete mode 100644 net/core/.gitignore

(limited to 'include')

diff --git a/include/net/dropreason.h b/include/net/dropreason.h
index fae9b40e54fa..c1cbcdbaf149 100644
--- a/include/net/dropreason.h
+++ b/include/net/dropreason.h
@@ -3,6 +3,73 @@
 #ifndef _LINUX_DROPREASON_H
 #define _LINUX_DROPREASON_H
 
+#define DEFINE_DROP_REASON(FN, FNe)	\
+	FN(NOT_SPECIFIED)		\
+	FN(NO_SOCKET)			\
+	FN(PKT_TOO_SMALL)		\
+	FN(TCP_CSUM)			\
+	FN(SOCKET_FILTER)		\
+	FN(UDP_CSUM)			\
+	FN(NETFILTER_DROP)		\
+	FN(OTHERHOST)			\
+	FN(IP_CSUM)			\
+	FN(IP_INHDR)			\
+	FN(IP_RPFILTER)			\
+	FN(UNICAST_IN_L2_MULTICAST)	\
+	FN(XFRM_POLICY)			\
+	FN(IP_NOPROTO)			\
+	FN(SOCKET_RCVBUFF)		\
+	FN(PROTO_MEM)			\
+	FN(TCP_MD5NOTFOUND)		\
+	FN(TCP_MD5UNEXPECTED)		\
+	FN(TCP_MD5FAILURE)		\
+	FN(SOCKET_BACKLOG)		\
+	FN(TCP_FLAGS)			\
+	FN(TCP_ZEROWINDOW)		\
+	FN(TCP_OLD_DATA)		\
+	FN(TCP_OVERWINDOW)		\
+	FN(TCP_OFOMERGE)		\
+	FN(TCP_RFC7323_PAWS)		\
+	FN(TCP_INVALID_SEQUENCE)	\
+	FN(TCP_RESET)			\
+	FN(TCP_INVALID_SYN)		\
+	FN(TCP_CLOSE)			\
+	FN(TCP_FASTOPEN)		\
+	FN(TCP_OLD_ACK)			\
+	FN(TCP_TOO_OLD_ACK)		\
+	FN(TCP_ACK_UNSENT_DATA)		\
+	FN(TCP_OFO_QUEUE_PRUNE)		\
+	FN(TCP_OFO_DROP)		\
+	FN(IP_OUTNOROUTES)		\
+	FN(BPF_CGROUP_EGRESS)		\
+	FN(IPV6DISABLED)		\
+	FN(NEIGH_CREATEFAIL)		\
+	FN(NEIGH_FAILED)		\
+	FN(NEIGH_QUEUEFULL)		\
+	FN(NEIGH_DEAD)			\
+	FN(TC_EGRESS)			\
+	FN(QDISC_DROP)			\
+	FN(CPU_BACKLOG)			\
+	FN(XDP)				\
+	FN(TC_INGRESS)			\
+	FN(UNHANDLED_PROTO)		\
+	FN(SKB_CSUM)			\
+	FN(SKB_GSO_SEG)			\
+	FN(SKB_UCOPY_FAULT)		\
+	FN(DEV_HDR)			\
+	FN(DEV_READY)			\
+	FN(FULL_RING)			\
+	FN(NOMEM)			\
+	FN(HDR_TRUNC)			\
+	FN(TAP_FILTER)			\
+	FN(TAP_TXFILTER)		\
+	FN(ICMP_CSUM)			\
+	FN(INVALID_PROTO)		\
+	FN(IP_INADDRERRORS)		\
+	FN(IP_INNOROUTES)		\
+	FN(PKT_TOO_BIG)			\
+	FNe(MAX)
+
 /**
  * enum skb_drop_reason - the reasons of skb drops
  *
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 45264e4bb254..50a974f7dfb4 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -9,6 +9,15 @@
 #include <linux/netdevice.h>
 #include <linux/tracepoint.h>
 
+#undef FN
+#define FN(reason)	TRACE_DEFINE_ENUM(SKB_DROP_REASON_##reason);
+DEFINE_DROP_REASON(FN, FN)
+
+#undef FN
+#undef FNe
+#define FN(reason)	{ SKB_DROP_REASON_##reason, #reason },
+#define FNe(reason)	{ SKB_DROP_REASON_##reason, #reason }
+
 /*
  * Tracepoint for free an sk_buff:
  */
@@ -35,9 +44,13 @@ TRACE_EVENT(kfree_skb,
 
 	TP_printk("skbaddr=%p protocol=%u location=%p reason: %s",
 		  __entry->skbaddr, __entry->protocol, __entry->location,
-		  drop_reasons[__entry->reason])
+		  __print_symbolic(__entry->reason,
+				   DEFINE_DROP_REASON(FN, FNe)))
 );
 
+#undef FN
+#undef FNe
+
 TRACE_EVENT(consume_skb,
 
 	TP_PROTO(struct sk_buff *skb),
diff --git a/net/core/.gitignore b/net/core/.gitignore
deleted file mode 100644
index df1e74372cce..000000000000
--- a/net/core/.gitignore
+++ /dev/null
@@ -1 +0,0 @@
-dropreason_str.c
diff --git a/net/core/Makefile b/net/core/Makefile
index e8ce3bd283a6..5857cec87b83 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -5,7 +5,7 @@
 
 obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \
 	 gen_stats.o gen_estimator.o net_namespace.o secure_seq.o \
-	 flow_dissector.o dropreason_str.o
+	 flow_dissector.o
 
 obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
 
@@ -40,23 +40,3 @@ obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o
 obj-$(CONFIG_BPF_SYSCALL) += sock_map.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o
 obj-$(CONFIG_OF)	+= of_net.o
-
-clean-files := dropreason_str.c
-
-quiet_cmd_dropreason_str = GEN     $@
-cmd_dropreason_str = awk -F ',' 'BEGIN{ print "\#include <net/dropreason.h>\n"; \
-	print "const char * const drop_reasons[] = {" }\
-	/^enum skb_drop/ { dr=1; }\
-	/^\};/ { dr=0; }\
-	/^\tSKB_DROP_REASON_/ {\
-		if (dr) {\
-			sub(/\tSKB_DROP_REASON_/, "", $$1);\
-			printf "\t[SKB_DROP_REASON_%s] = \"%s\",\n", $$1, $$1;\
-		}\
-	}\
-	END{ print "};" }' $< > $@
-
-$(obj)/dropreason_str.c: $(srctree)/include/net/dropreason.h
-	$(call cmd,dropreason_str)
-
-$(obj)/dropreason_str.o: $(obj)/dropreason_str.c
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 84bb5e188d0d..417463da4fac 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -91,7 +91,11 @@ static struct kmem_cache *skbuff_ext_cache __ro_after_init;
 int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
 EXPORT_SYMBOL(sysctl_max_skb_frags);
 
-/* The array 'drop_reasons' is auto-generated in dropreason_str.c */
+#undef FN
+#define FN(reason) [SKB_DROP_REASON_##reason] = #reason,
+const char * const drop_reasons[] = {
+	DEFINE_DROP_REASON(FN, FN)
+};
 EXPORT_SYMBOL(drop_reasons);
 
 /**
-- 
cgit v1.2.3