From 97a0e1ea7b41c2db762c1258632f6ccc22719510 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 12 Jan 2021 19:26:12 +0100
Subject: net, xdp: Introduce __xdp_build_skb_from_frame utility routine

Introduce __xdp_build_skb_from_frame utility routine to build
the skb from xdp_frame. Rely on __xdp_build_skb_from_frame in
cpumap code.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/4f9f4c6b3dd3933770c617eb6689dbc0c6e25863.1610475660.git.lorenzo@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/core/xdp.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

(limited to 'net/core')

diff --git a/net/core/xdp.c b/net/core/xdp.c
index 3a8c9ab4ecbe..aeb09ed0704c 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -513,3 +513,47 @@ void xdp_warn(const char *msg, const char *func, const int line)
 	WARN(1, "XDP_WARN: %s(line:%d): %s\n", func, line, msg);
 };
 EXPORT_SYMBOL_GPL(xdp_warn);
+
+struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
+					   struct sk_buff *skb,
+					   struct net_device *dev)
+{
+	unsigned int headroom, frame_size;
+	void *hard_start;
+
+	/* Part of headroom was reserved to xdpf */
+	headroom = sizeof(*xdpf) + xdpf->headroom;
+
+	/* Memory size backing xdp_frame data already have reserved
+	 * room for build_skb to place skb_shared_info in tailroom.
+	 */
+	frame_size = xdpf->frame_sz;
+
+	hard_start = xdpf->data - headroom;
+	skb = build_skb_around(skb, hard_start, frame_size);
+	if (unlikely(!skb))
+		return NULL;
+
+	skb_reserve(skb, headroom);
+	__skb_put(skb, xdpf->len);
+	if (xdpf->metasize)
+		skb_metadata_set(skb, xdpf->metasize);
+
+	/* Essential SKB info: protocol and skb->dev */
+	skb->protocol = eth_type_trans(skb, dev);
+
+	/* Optional SKB info, currently missing:
+	 * - HW checksum info		(skb->ip_summed)
+	 * - HW RX hash			(skb_set_hash)
+	 * - RX ring dev queue index	(skb_record_rx_queue)
+	 */
+
+	/* Until page_pool get SKB return path, release DMA here */
+	xdp_release_frame(xdpf);
+
+	/* Allow SKB to reuse area used by xdp_frame */
+	xdp_scrub_frame(xdpf);
+
+	return skb;
+}
+EXPORT_SYMBOL_GPL(__xdp_build_skb_from_frame);
-- 
cgit v1.2.3


From 89f479f0eccfc879e7bc0a69f44ed4a4639dfc32 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 12 Jan 2021 19:26:13 +0100
Subject: net, xdp: Introduce xdp_build_skb_from_frame utility routine

Introduce xdp_build_skb_from_frame utility routine to build the skb
from xdp_frame. Respect to __xdp_build_skb_from_frame,
xdp_build_skb_from_frame will allocate the skb object. Rely on
xdp_build_skb_from_frame in veth driver.
Introduce missing xdp metadata support in veth_xdp_rcv_one routine.
Add missing metadata support in veth_xdp_rcv_one().

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toshiaki Makita <toshiaki.makita1@gmail.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/94ade9e853162ae1947941965193190da97457bc.1610475660.git.lorenzo@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/veth.c | 18 +++---------------
 include/net/xdp.h  |  2 ++
 net/core/xdp.c     | 15 +++++++++++++++
 3 files changed, 20 insertions(+), 15 deletions(-)

(limited to 'net/core')

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 99caae7d1641..6e03b619c93c 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -567,16 +567,10 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 					struct veth_xdp_tx_bq *bq,
 					struct veth_stats *stats)
 {
-	void *hard_start = frame->data - frame->headroom;
-	int len = frame->len, delta = 0;
 	struct xdp_frame orig_frame;
 	struct bpf_prog *xdp_prog;
-	unsigned int headroom;
 	struct sk_buff *skb;
 
-	/* bpf_xdp_adjust_head() assures BPF cannot access xdp_frame area */
-	hard_start -= sizeof(struct xdp_frame);
-
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (likely(xdp_prog)) {
@@ -590,8 +584,8 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 
 		switch (act) {
 		case XDP_PASS:
-			delta = frame->data - xdp.data;
-			len = xdp.data_end - xdp.data;
+			if (xdp_update_frame_from_buff(&xdp, frame))
+				goto err_xdp;
 			break;
 		case XDP_TX:
 			orig_frame = *frame;
@@ -629,18 +623,12 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 	}
 	rcu_read_unlock();
 
-	headroom = sizeof(struct xdp_frame) + frame->headroom - delta;
-	skb = veth_build_skb(hard_start, headroom, len, frame->frame_sz);
+	skb = xdp_build_skb_from_frame(frame, rq->dev);
 	if (!skb) {
 		xdp_return_frame(frame);
 		stats->rx_drops++;
-		goto err;
 	}
 
-	xdp_release_frame(frame);
-	xdp_scrub_frame(frame);
-	skb->protocol = eth_type_trans(skb, rq->dev);
-err:
 	return skb;
 err_xdp:
 	rcu_read_unlock();
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 689206dee6de..c4bfdc9a8b79 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -167,6 +167,8 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp);
 struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					   struct sk_buff *skb,
 					   struct net_device *dev);
+struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
+					 struct net_device *dev);
 
 static inline
 void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
diff --git a/net/core/xdp.c b/net/core/xdp.c
index aeb09ed0704c..0d2630a35c3e 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -557,3 +557,18 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 	return skb;
 }
 EXPORT_SYMBOL_GPL(__xdp_build_skb_from_frame);
+
+struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
+					 struct net_device *dev)
+{
+	struct sk_buff *skb;
+
+	skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC);
+	if (unlikely(!skb))
+		return NULL;
+
+	memset(skb, 0, offsetof(struct sk_buff, tail));
+
+	return __xdp_build_skb_from_frame(xdpf, skb, dev);
+}
+EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame);
-- 
cgit v1.2.3


From 8063e184e49011f6f3f34f6c358dc8a83890bb5b Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Wed, 27 Jan 2021 14:15:01 -0800
Subject: skmsg: Make sk_psock_destroy() static

sk_psock_destroy() is a RCU callback, I can't see any reason why
it could be used outside.

Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Lorenz Bauer <lmb@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210127221501.46866-1-xiyou.wangcong@gmail.com
---
 include/linux/skmsg.h | 1 -
 net/core/skmsg.c      | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'net/core')

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index fec0c5ac1c4f..8edbbf5f2f93 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -390,7 +390,6 @@ static inline struct sk_psock *sk_psock_get(struct sock *sk)
 }
 
 void sk_psock_stop(struct sock *sk, struct sk_psock *psock);
-void sk_psock_destroy(struct rcu_head *rcu);
 void sk_psock_drop(struct sock *sk, struct sk_psock *psock);
 
 static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock)
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 25cdbb20f3a0..1261512d6807 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -669,14 +669,13 @@ static void sk_psock_destroy_deferred(struct work_struct *gc)
 	kfree(psock);
 }
 
-void sk_psock_destroy(struct rcu_head *rcu)
+static void sk_psock_destroy(struct rcu_head *rcu)
 {
 	struct sk_psock *psock = container_of(rcu, struct sk_psock, rcu);
 
 	INIT_WORK(&psock->gc, sk_psock_destroy_deferred);
 	schedule_work(&psock->gc);
 }
-EXPORT_SYMBOL_GPL(sk_psock_destroy);
 
 void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 {
-- 
cgit v1.2.3


From 62476cc1bf24b34d9442c7ba76e5eb6bf242f911 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Wed, 27 Jan 2021 15:28:50 -0800
Subject: bpf: Enable bpf_{g,s}etsockopt in BPF_CGROUP_UDP{4,6}_SENDMSG

Can be used to query/modify socket state for unconnected UDP sendmsg.
Those hooks run as BPF_CGROUP_RUN_SA_PROG_LOCK and operate on
a locked socket.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210127232853.3753823-2-sdf@google.com
---
 net/core/filter.c                                 |  4 ++++
 tools/testing/selftests/bpf/bpf_sockopt_helpers.h | 21 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/sendmsg4_prog.c |  7 +++++++
 tools/testing/selftests/bpf/progs/sendmsg6_prog.c |  5 +++++
 4 files changed, 37 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/bpf_sockopt_helpers.h

(limited to 'net/core')

diff --git a/net/core/filter.c b/net/core/filter.c
index 9ab94e90d660..3d7f78a19565 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7023,6 +7023,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UDP4_SENDMSG:
+		case BPF_CGROUP_UDP6_SENDMSG:
 			return &bpf_sock_addr_setsockopt_proto;
 		default:
 			return NULL;
@@ -7033,6 +7035,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UDP4_SENDMSG:
+		case BPF_CGROUP_UDP6_SENDMSG:
 			return &bpf_sock_addr_getsockopt_proto;
 		default:
 			return NULL;
diff --git a/tools/testing/selftests/bpf/bpf_sockopt_helpers.h b/tools/testing/selftests/bpf/bpf_sockopt_helpers.h
new file mode 100644
index 000000000000..11f3a0976174
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_sockopt_helpers.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <sys/socket.h>
+#include <bpf/bpf_helpers.h>
+
+int get_set_sk_priority(void *ctx)
+{
+	int prio;
+
+	/* Verify that context allows calling bpf_getsockopt and
+	 * bpf_setsockopt by reading and writing back socket
+	 * priority.
+	 */
+
+	if (bpf_getsockopt(ctx, SOL_SOCKET, SO_PRIORITY, &prio, sizeof(prio)))
+		return 0;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_PRIORITY, &prio, sizeof(prio)))
+		return 0;
+
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
index 092d9da536f3..ac5abc34cde8 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
@@ -8,6 +8,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include <bpf_sockopt_helpers.h>
+
 #define SRC1_IP4		0xAC100001U /* 172.16.0.1 */
 #define SRC2_IP4		0x00000000U
 #define SRC_REWRITE_IP4		0x7f000004U
@@ -21,9 +23,14 @@ int _version SEC("version") = 1;
 SEC("cgroup/sendmsg4")
 int sendmsg_v4_prog(struct bpf_sock_addr *ctx)
 {
+	int prio;
+
 	if (ctx->type != SOCK_DGRAM)
 		return 0;
 
+	if (!get_set_sk_priority(ctx))
+		return 0;
+
 	/* Rewrite source. */
 	if (ctx->msg_src_ip4 == bpf_htonl(SRC1_IP4) ||
 	    ctx->msg_src_ip4 == bpf_htonl(SRC2_IP4)) {
diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
index 255a432bc163..24694b1a8d82 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
@@ -8,6 +8,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include <bpf_sockopt_helpers.h>
+
 #define SRC_REWRITE_IP6_0	0
 #define SRC_REWRITE_IP6_1	0
 #define SRC_REWRITE_IP6_2	0
@@ -28,6 +30,9 @@ int sendmsg_v6_prog(struct bpf_sock_addr *ctx)
 	if (ctx->type != SOCK_DGRAM)
 		return 0;
 
+	if (!get_set_sk_priority(ctx))
+		return 0;
+
 	/* Rewrite source. */
 	if (ctx->msg_src_ip6[3] == bpf_htonl(1) ||
 	    ctx->msg_src_ip6[3] == bpf_htonl(0)) {
-- 
cgit v1.2.3


From 073f4ec124bb2c431d9e4136e7f583abfea7f290 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Wed, 27 Jan 2021 15:28:51 -0800
Subject: bpf: Enable bpf_{g,s}etsockopt in
 BPF_CGROUP_INET{4,6}_GET{PEER,SOCK}NAME

Those hooks run as BPF_CGROUP_RUN_SA_PROG_LOCK and operate on
a locked socket.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210127232853.3753823-3-sdf@google.com
---
 net/core/filter.c                                       | 8 ++++++++
 tools/testing/selftests/bpf/progs/connect_force_port4.c | 8 ++++++++
 tools/testing/selftests/bpf/progs/connect_force_port6.c | 8 ++++++++
 3 files changed, 24 insertions(+)

(limited to 'net/core')

diff --git a/net/core/filter.c b/net/core/filter.c
index 3d7f78a19565..ba436b1d70c2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7025,6 +7025,10 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_CONNECT:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
+		case BPF_CGROUP_INET4_GETPEERNAME:
+		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_INET4_GETSOCKNAME:
+		case BPF_CGROUP_INET6_GETSOCKNAME:
 			return &bpf_sock_addr_setsockopt_proto;
 		default:
 			return NULL;
@@ -7037,6 +7041,10 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_CONNECT:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
+		case BPF_CGROUP_INET4_GETPEERNAME:
+		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_INET4_GETSOCKNAME:
+		case BPF_CGROUP_INET6_GETSOCKNAME:
 			return &bpf_sock_addr_getsockopt_proto;
 		default:
 			return NULL;
diff --git a/tools/testing/selftests/bpf/progs/connect_force_port4.c b/tools/testing/selftests/bpf/progs/connect_force_port4.c
index 7396308677a3..a979aaef2a76 100644
--- a/tools/testing/selftests/bpf/progs/connect_force_port4.c
+++ b/tools/testing/selftests/bpf/progs/connect_force_port4.c
@@ -10,6 +10,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include <bpf_sockopt_helpers.h>
+
 char _license[] SEC("license") = "GPL";
 int _version SEC("version") = 1;
 
@@ -58,6 +60,9 @@ int connect4(struct bpf_sock_addr *ctx)
 SEC("cgroup/getsockname4")
 int getsockname4(struct bpf_sock_addr *ctx)
 {
+	if (!get_set_sk_priority(ctx))
+		return 1;
+
 	/* Expose local server as 1.2.3.4:60000 to client. */
 	if (ctx->user_port == bpf_htons(60123)) {
 		ctx->user_ip4 = bpf_htonl(0x01020304);
@@ -71,6 +76,9 @@ int getpeername4(struct bpf_sock_addr *ctx)
 {
 	struct svc_addr *orig;
 
+	if (!get_set_sk_priority(ctx))
+		return 1;
+
 	/* Expose service 1.2.3.4:60000 as peer instead of backend. */
 	if (ctx->user_port == bpf_htons(60123)) {
 		orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0, 0);
diff --git a/tools/testing/selftests/bpf/progs/connect_force_port6.c b/tools/testing/selftests/bpf/progs/connect_force_port6.c
index c1a2b555e9ad..afc8f1c5a9d6 100644
--- a/tools/testing/selftests/bpf/progs/connect_force_port6.c
+++ b/tools/testing/selftests/bpf/progs/connect_force_port6.c
@@ -9,6 +9,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include <bpf_sockopt_helpers.h>
+
 char _license[] SEC("license") = "GPL";
 int _version SEC("version") = 1;
 
@@ -63,6 +65,9 @@ int connect6(struct bpf_sock_addr *ctx)
 SEC("cgroup/getsockname6")
 int getsockname6(struct bpf_sock_addr *ctx)
 {
+	if (!get_set_sk_priority(ctx))
+		return 1;
+
 	/* Expose local server as [fc00::1]:60000 to client. */
 	if (ctx->user_port == bpf_htons(60124)) {
 		ctx->user_ip6[0] = bpf_htonl(0xfc000000);
@@ -79,6 +84,9 @@ int getpeername6(struct bpf_sock_addr *ctx)
 {
 	struct svc_addr *orig;
 
+	if (!get_set_sk_priority(ctx))
+		return 1;
+
 	/* Expose service [fc00::1]:60000 as peer instead of backend. */
 	if (ctx->user_port == bpf_htons(60124)) {
 		orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0, 0);
-- 
cgit v1.2.3


From 4c3384d7abe58a68d78fd1b8b3bffbf62e1e29a1 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Wed, 27 Jan 2021 15:28:53 -0800
Subject: bpf: Enable bpf_{g,s}etsockopt in BPF_CGROUP_UDP{4,6}_RECVMSG

Those hooks run as BPF_CGROUP_RUN_SA_PROG_LOCK and operate on a locked socket.

Note that we could remove the switch for prog->expected_attach_type altogether
since all current sock_addr attach types are covered. However, it makes sense
to keep it as a safe-guard in case new sock_addr attach types are added that
might not operate on a locked socket. Therefore, avoid to let this slip through.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210127232853.3753823-5-sdf@google.com
---
 net/core/filter.c                                 | 4 ++++
 tools/testing/selftests/bpf/progs/recvmsg4_prog.c | 5 +++++
 tools/testing/selftests/bpf/progs/recvmsg6_prog.c | 5 +++++
 3 files changed, 14 insertions(+)

(limited to 'net/core')

diff --git a/net/core/filter.c b/net/core/filter.c
index ba436b1d70c2..e15d4741719a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7023,6 +7023,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UDP4_RECVMSG:
+		case BPF_CGROUP_UDP6_RECVMSG:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
 		case BPF_CGROUP_INET4_GETPEERNAME:
@@ -7039,6 +7041,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UDP4_RECVMSG:
+		case BPF_CGROUP_UDP6_RECVMSG:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
 		case BPF_CGROUP_INET4_GETPEERNAME:
diff --git a/tools/testing/selftests/bpf/progs/recvmsg4_prog.c b/tools/testing/selftests/bpf/progs/recvmsg4_prog.c
index fc2fe8a952fa..3d1ae8b3402f 100644
--- a/tools/testing/selftests/bpf/progs/recvmsg4_prog.c
+++ b/tools/testing/selftests/bpf/progs/recvmsg4_prog.c
@@ -8,6 +8,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include <bpf_sockopt_helpers.h>
+
 #define SERV4_IP		0xc0a801feU /* 192.168.1.254 */
 #define SERV4_PORT		4040
 
@@ -28,6 +30,9 @@ int recvmsg4_prog(struct bpf_sock_addr *ctx)
 	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
 		return 1;
 
+	if (!get_set_sk_priority(ctx))
+		return 1;
+
 	ctx->user_ip4 = bpf_htonl(SERV4_IP);
 	ctx->user_port = bpf_htons(SERV4_PORT);
 
diff --git a/tools/testing/selftests/bpf/progs/recvmsg6_prog.c b/tools/testing/selftests/bpf/progs/recvmsg6_prog.c
index 6060fd63324b..27dfb21b21b4 100644
--- a/tools/testing/selftests/bpf/progs/recvmsg6_prog.c
+++ b/tools/testing/selftests/bpf/progs/recvmsg6_prog.c
@@ -8,6 +8,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include <bpf_sockopt_helpers.h>
+
 #define SERV6_IP_0		0xfaceb00c /* face:b00c:1234:5678::abcd */
 #define SERV6_IP_1		0x12345678
 #define SERV6_IP_2		0x00000000
@@ -31,6 +33,9 @@ int recvmsg6_prog(struct bpf_sock_addr *ctx)
 	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
 		return 1;
 
+	if (!get_set_sk_priority(ctx))
+		return 1;
+
 	ctx->user_ip6[0] = bpf_htonl(SERV6_IP_0);
 	ctx->user_ip6[1] = bpf_htonl(SERV6_IP_1);
 	ctx->user_ip6[2] = bpf_htonl(SERV6_IP_2);
-- 
cgit v1.2.3


From 65e6dcf73398ddb64bb782ff2acd918d3a37a53a Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 29 Jan 2021 23:04:08 +0100
Subject: net, veth: Alloc skb in bulk for ndo_xdp_xmit

Split ndo_xdp_xmit and ndo_start_xmit use cases in veth_xdp_rcv routine
in order to alloc skbs in bulk for XDP_PASS verdict.

Introduce xdp_alloc_skb_bulk utility routine to alloc skb bulk list.
The proposed approach has been tested in the following scenario:

eth (ixgbe) --> XDP_REDIRECT --> veth0 --> (remote-ns) veth1 --> XDP_PASS

XDP_REDIRECT: xdp_redirect_map bpf sample
XDP_PASS: xdp_rxq_info bpf sample

traffic generator: pkt_gen sending udp traffic on a remote device

bpf-next master: ~3.64Mpps
bpf-next + skb bulking allocation: ~3.79Mpps

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toshiaki Makita <toshiaki.makita1@gmail.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/a14a30d3c06fff24e13f836c733d80efc0bd6eb5.1611957532.git.lorenzo@kernel.org
---
 drivers/net/veth.c | 78 ++++++++++++++++++++++++++++++++++++++++--------------
 include/net/xdp.h  |  1 +
 net/core/xdp.c     | 11 ++++++++
 3 files changed, 70 insertions(+), 20 deletions(-)

(limited to 'net/core')

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 6e03b619c93c..aa1a66ad2ce5 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -35,6 +35,7 @@
 #define VETH_XDP_HEADROOM	(XDP_PACKET_HEADROOM + NET_IP_ALIGN)
 
 #define VETH_XDP_TX_BULK_SIZE	16
+#define VETH_XDP_BATCH		16
 
 struct veth_stats {
 	u64	rx_drops;
@@ -562,14 +563,13 @@ static int veth_xdp_tx(struct veth_rq *rq, struct xdp_buff *xdp,
 	return 0;
 }
 
-static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
-					struct xdp_frame *frame,
-					struct veth_xdp_tx_bq *bq,
-					struct veth_stats *stats)
+static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq,
+					  struct xdp_frame *frame,
+					  struct veth_xdp_tx_bq *bq,
+					  struct veth_stats *stats)
 {
 	struct xdp_frame orig_frame;
 	struct bpf_prog *xdp_prog;
-	struct sk_buff *skb;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -623,13 +623,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 	}
 	rcu_read_unlock();
 
-	skb = xdp_build_skb_from_frame(frame, rq->dev);
-	if (!skb) {
-		xdp_return_frame(frame);
-		stats->rx_drops++;
-	}
-
-	return skb;
+	return frame;
 err_xdp:
 	rcu_read_unlock();
 	xdp_return_frame(frame);
@@ -637,6 +631,37 @@ xdp_xmit:
 	return NULL;
 }
 
+/* frames array contains VETH_XDP_BATCH at most */
+static void veth_xdp_rcv_bulk_skb(struct veth_rq *rq, void **frames,
+				  int n_xdpf, struct veth_xdp_tx_bq *bq,
+				  struct veth_stats *stats)
+{
+	void *skbs[VETH_XDP_BATCH];
+	int i;
+
+	if (xdp_alloc_skb_bulk(skbs, n_xdpf,
+			       GFP_ATOMIC | __GFP_ZERO) < 0) {
+		for (i = 0; i < n_xdpf; i++)
+			xdp_return_frame(frames[i]);
+		stats->rx_drops += n_xdpf;
+
+		return;
+	}
+
+	for (i = 0; i < n_xdpf; i++) {
+		struct sk_buff *skb = skbs[i];
+
+		skb = __xdp_build_skb_from_frame(frames[i], skb,
+						 rq->dev);
+		if (!skb) {
+			xdp_return_frame(frames[i]);
+			stats->rx_drops++;
+			continue;
+		}
+		napi_gro_receive(&rq->xdp_napi, skb);
+	}
+}
+
 static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
 					struct sk_buff *skb,
 					struct veth_xdp_tx_bq *bq,
@@ -784,32 +809,45 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 			struct veth_xdp_tx_bq *bq,
 			struct veth_stats *stats)
 {
-	int i, done = 0;
+	int i, done = 0, n_xdpf = 0;
+	void *xdpf[VETH_XDP_BATCH];
 
 	for (i = 0; i < budget; i++) {
 		void *ptr = __ptr_ring_consume(&rq->xdp_ring);
-		struct sk_buff *skb;
 
 		if (!ptr)
 			break;
 
 		if (veth_is_xdp_frame(ptr)) {
+			/* ndo_xdp_xmit */
 			struct xdp_frame *frame = veth_ptr_to_xdp(ptr);
 
 			stats->xdp_bytes += frame->len;
-			skb = veth_xdp_rcv_one(rq, frame, bq, stats);
+			frame = veth_xdp_rcv_one(rq, frame, bq, stats);
+			if (frame) {
+				/* XDP_PASS */
+				xdpf[n_xdpf++] = frame;
+				if (n_xdpf == VETH_XDP_BATCH) {
+					veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf,
+							      bq, stats);
+					n_xdpf = 0;
+				}
+			}
 		} else {
-			skb = ptr;
+			/* ndo_start_xmit */
+			struct sk_buff *skb = ptr;
+
 			stats->xdp_bytes += skb->len;
 			skb = veth_xdp_rcv_skb(rq, skb, bq, stats);
+			if (skb)
+				napi_gro_receive(&rq->xdp_napi, skb);
 		}
-
-		if (skb)
-			napi_gro_receive(&rq->xdp_napi, skb);
-
 		done++;
 	}
 
+	if (n_xdpf)
+		veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf, bq, stats);
+
 	u64_stats_update_begin(&rq->stats.syncp);
 	rq->stats.vs.xdp_redirect += stats->xdp_redirect;
 	rq->stats.vs.xdp_bytes += stats->xdp_bytes;
diff --git a/include/net/xdp.h b/include/net/xdp.h
index c4bfdc9a8b79..a5bc214a49d9 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -169,6 +169,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					   struct net_device *dev);
 struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					 struct net_device *dev);
+int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp);
 
 static inline
 void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 0d2630a35c3e..05354976c1fc 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -514,6 +514,17 @@ void xdp_warn(const char *msg, const char *func, const int line)
 };
 EXPORT_SYMBOL_GPL(xdp_warn);
 
+int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp)
+{
+	n_skb = kmem_cache_alloc_bulk(skbuff_head_cache, gfp,
+				      n_skb, skbs);
+	if (unlikely(!n_skb))
+		return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xdp_alloc_skb_bulk);
+
 struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					   struct sk_buff *skb,
 					   struct net_device *dev)
-- 
cgit v1.2.3


From c5dbb89fc2ac013afe67b9e4fcb3743c02b567cd Mon Sep 17 00:00:00 2001
From: Florent Revest <revest@chromium.org>
Date: Wed, 10 Feb 2021 12:14:03 +0100
Subject: bpf: Expose bpf_get_socket_cookie to tracing programs

This needs a new helper that:
- can work in a sleepable context (using sock_gen_cookie)
- takes a struct sock pointer and checks that it's not NULL

Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: KP Singh <kpsingh@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210210111406.785541-2-revest@chromium.org
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       |  8 ++++++++
 kernel/trace/bpf_trace.c       |  2 ++
 net/core/filter.c              | 12 ++++++++++++
 tools/include/uapi/linux/bpf.h |  8 ++++++++
 5 files changed, 31 insertions(+)

(limited to 'net/core')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 1c8ea682c007..cccaef1088ea 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1885,6 +1885,7 @@ extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
 extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
 extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto;
 extern const struct bpf_func_proto bpf_sock_from_file_proto;
+extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index dbf10bf08582..07cc2e404291 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1673,6 +1673,14 @@ union bpf_attr {
  * 	Return
  * 		A 8-byte long unique number.
  *
+ * u64 bpf_get_socket_cookie(struct sock *sk)
+ * 	Description
+ * 		Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
+ * 		*sk*, but gets socket from a BTF **struct sock**. This helper
+ * 		also works for sleepable programs.
+ * 	Return
+ * 		A 8-byte long unique number or 0 if *sk* is NULL.
+ *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
  * 	Return
  * 		The owner UID of the socket associated to *skb*. If the socket
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 6c0018abe68a..845b2168e006 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1760,6 +1760,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_delete_tracing_proto;
 	case BPF_FUNC_sock_from_file:
 		return &bpf_sock_from_file_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_ptr_cookie_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
diff --git a/net/core/filter.c b/net/core/filter.c
index e15d4741719a..57aaed478362 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4631,6 +4631,18 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_1(bpf_get_socket_ptr_cookie, struct sock *, sk)
+{
+	return sk ? sock_gen_cookie(sk) : 0;
+}
+
+const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto = {
+	.func		= bpf_get_socket_ptr_cookie,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
+};
+
 BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx)
 {
 	return __sock_gen_cookie(ctx->sk);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index dbf10bf08582..07cc2e404291 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1673,6 +1673,14 @@ union bpf_attr {
  * 	Return
  * 		A 8-byte long unique number.
  *
+ * u64 bpf_get_socket_cookie(struct sock *sk)
+ * 	Description
+ * 		Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
+ * 		*sk*, but gets socket from a BTF **struct sock**. This helper
+ * 		also works for sleepable programs.
+ * 	Return
+ * 		A 8-byte long unique number or 0 if *sk* is NULL.
+ *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
  * 	Return
  * 		The owner UID of the socket associated to *skb*. If the socket
-- 
cgit v1.2.3


From 6306c1189e77a513bf02720450bb43bd4ba5d8ae Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 9 Feb 2021 14:38:09 +0100
Subject: bpf: Remove MTU check in __bpf_skb_max_len

Multiple BPF-helpers that can manipulate/increase the size of the SKB uses
__bpf_skb_max_len() as the max-length. This function limit size against
the current net_device MTU (skb->dev->mtu).

When a BPF-prog grow the packet size, then it should not be limited to the
MTU. The MTU is a transmit limitation, and software receiving this packet
should be allowed to increase the size. Further more, current MTU check in
__bpf_skb_max_len uses the MTU from ingress/current net_device, which in
case of redirects uses the wrong net_device.

This patch keeps a sanity max limit of SKB_MAX_ALLOC (16KiB). The real limit
is elsewhere in the system. Jesper's testing[1] showed it was not possible
to exceed 8KiB when expanding the SKB size via BPF-helper. The limiting
factor is the define KMALLOC_MAX_CACHE_SIZE which is 8192 for
SLUB-allocator (CONFIG_SLUB) in-case PAGE_SIZE is 4096. This define is
in-effect due to this being called from softirq context see code
__gfp_pfmemalloc_flags() and __do_kmalloc_node(). Jakub's testing showed
that frames above 16KiB can cause NICs to reset (but not crash). Keep this
sanity limit at this level as memory layer can differ based on kernel
config.

[1] https://github.com/xdp-project/bpf-examples/tree/master/MTU-tests

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/161287788936.790810.2937823995775097177.stgit@firesoul
---
 net/core/filter.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

(limited to 'net/core')

diff --git a/net/core/filter.c b/net/core/filter.c
index 57aaed478362..27022168fd78 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3552,11 +3552,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 	return 0;
 }
 
-static u32 __bpf_skb_max_len(const struct sk_buff *skb)
-{
-	return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len :
-			  SKB_MAX_ALLOC;
-}
+#define BPF_SKB_MAX_LEN SKB_MAX_ALLOC
 
 BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	   u32, mode, u64, flags)
@@ -3605,7 +3601,7 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 {
 	u32 len_cur, len_diff_abs = abs(len_diff);
 	u32 len_min = bpf_skb_net_base_len(skb);
-	u32 len_max = __bpf_skb_max_len(skb);
+	u32 len_max = BPF_SKB_MAX_LEN;
 	__be16 proto = skb->protocol;
 	bool shrink = len_diff < 0;
 	u32 off;
@@ -3688,7 +3684,7 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len)
 static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len,
 					u64 flags)
 {
-	u32 max_len = __bpf_skb_max_len(skb);
+	u32 max_len = BPF_SKB_MAX_LEN;
 	u32 min_len = __bpf_skb_min_len(skb);
 	int ret;
 
@@ -3764,7 +3760,7 @@ static const struct bpf_func_proto sk_skb_change_tail_proto = {
 static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room,
 					u64 flags)
 {
-	u32 max_len = __bpf_skb_max_len(skb);
+	u32 max_len = BPF_SKB_MAX_LEN;
 	u32 new_len = skb->len + head_room;
 	int ret;
 
-- 
cgit v1.2.3


From 2c0a10af688c02adcf127aad29e923e0056c6b69 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 9 Feb 2021 14:38:14 +0100
Subject: bpf: Fix bpf_fib_lookup helper MTU check for SKB ctx

BPF end-user on Cilium slack-channel (Carlo Carraro) wants to use
bpf_fib_lookup for doing MTU-check, but *prior* to extending packet size,
by adjusting fib_params 'tot_len' with the packet length plus the expected
encap size. (Just like the bpf_check_mtu helper supports). He discovered
that for SKB ctx the param->tot_len was not used, instead skb->len was used
(via MTU check in is_skb_forwardable() that checks against netdev MTU).

Fix this by using fib_params 'tot_len' for MTU check. If not provided (e.g.
zero) then keep existing TC behaviour intact. Notice that 'tot_len' for MTU
check is done like XDP code-path, which checks against FIB-dst MTU.

V16:
- Revert V13 optimization, 2nd lookup is against egress/resulting netdev

V13:
- Only do ifindex lookup one time, calling dev_get_by_index_rcu().

V10:
- Use same method as XDP for 'tot_len' MTU check

Fixes: 4c79579b44b1 ("bpf: Change bpf_fib_lookup to return lookup status")
Reported-by: Carlo Carraro <colrack@gmail.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/161287789444.790810.15247494756551413508.stgit@firesoul
---
 net/core/filter.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

(limited to 'net/core')

diff --git a/net/core/filter.c b/net/core/filter.c
index 27022168fd78..1fec2e998e37 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5581,6 +5581,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 {
 	struct net *net = dev_net(skb->dev);
 	int rc = -EAFNOSUPPORT;
+	bool check_mtu = false;
 
 	if (plen < sizeof(*params))
 		return -EINVAL;
@@ -5588,22 +5589,28 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 	if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT))
 		return -EINVAL;
 
+	if (params->tot_len)
+		check_mtu = true;
+
 	switch (params->family) {
 #if IS_ENABLED(CONFIG_INET)
 	case AF_INET:
-		rc = bpf_ipv4_fib_lookup(net, params, flags, false);
+		rc = bpf_ipv4_fib_lookup(net, params, flags, check_mtu);
 		break;
 #endif
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		rc = bpf_ipv6_fib_lookup(net, params, flags, false);
+		rc = bpf_ipv6_fib_lookup(net, params, flags, check_mtu);
 		break;
 #endif
 	}
 
-	if (!rc) {
+	if (rc == BPF_FIB_LKUP_RET_SUCCESS && !check_mtu) {
 		struct net_device *dev;
 
+		/* When tot_len isn't provided by user, check skb
+		 * against MTU of FIB lookup resulting net_device
+		 */
 		dev = dev_get_by_index_rcu(net, params->ifindex);
 		if (!is_skb_forwardable(dev, skb))
 			rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
-- 
cgit v1.2.3


From e1850ea9bd9eca3656820b4875967d6f9c11c237 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 9 Feb 2021 14:38:19 +0100
Subject: bpf: bpf_fib_lookup return MTU value as output when looked up

The BPF-helpers for FIB lookup (bpf_xdp_fib_lookup and bpf_skb_fib_lookup)
can perform MTU check and return BPF_FIB_LKUP_RET_FRAG_NEEDED. The BPF-prog
don't know the MTU value that caused this rejection.

If the BPF-prog wants to implement PMTU (Path MTU Discovery) (rfc1191) it
need to know this MTU value for the ICMP packet.

Patch change lookup and result struct bpf_fib_lookup, to contain this MTU
value as output via a union with 'tot_len' as this is the value used for
the MTU lookup.

V5:
 - Fixed uninit value spotted by Dan Carpenter.
 - Name struct output member mtu_result

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/161287789952.790810.13134700381067698781.stgit@firesoul
---
 include/uapi/linux/bpf.h       | 11 +++++++++--
 net/core/filter.c              | 22 +++++++++++++++-------
 tools/include/uapi/linux/bpf.h | 11 +++++++++--
 3 files changed, 33 insertions(+), 11 deletions(-)

(limited to 'net/core')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 07cc2e404291..6b1f6058cccf 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2239,6 +2239,9 @@ union bpf_attr {
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  *		  packet is not forwarded or needs assist from full stack
  *
+ *		If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ *		was exceeded and output params->mtu_result contains the MTU.
+ *
  * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
  *		Add an entry to, or update a sockhash *map* referencing sockets.
@@ -4990,9 +4993,13 @@ struct bpf_fib_lookup {
 	__be16	sport;
 	__be16	dport;
 
-	/* total length of packet from network header - used for MTU check */
-	__u16	tot_len;
+	union {	/* used for MTU check */
+		/* input to lookup */
+		__u16	tot_len; /* L3 length from network hdr (iph->tot_len) */
 
+		/* output: MTU value */
+		__u16	mtu_result;
+	};
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */
diff --git a/net/core/filter.c b/net/core/filter.c
index 1fec2e998e37..e7a9b1667dd6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5301,12 +5301,14 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = {
 #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6)
 static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
 				  const struct neighbour *neigh,
-				  const struct net_device *dev)
+				  const struct net_device *dev, u32 mtu)
 {
 	memcpy(params->dmac, neigh->ha, ETH_ALEN);
 	memcpy(params->smac, dev->dev_addr, ETH_ALEN);
 	params->h_vlan_TCI = 0;
 	params->h_vlan_proto = 0;
+	if (mtu)
+		params->mtu_result = mtu; /* union with tot_len */
 
 	return 0;
 }
@@ -5322,8 +5324,8 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	struct net_device *dev;
 	struct fib_result res;
 	struct flowi4 fl4;
+	u32 mtu = 0;
 	int err;
-	u32 mtu;
 
 	dev = dev_get_by_index_rcu(net, params->ifindex);
 	if (unlikely(!dev))
@@ -5390,8 +5392,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	if (check_mtu) {
 		mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
-		if (params->tot_len > mtu)
+		if (params->tot_len > mtu) {
+			params->mtu_result = mtu; /* union with tot_len */
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
+		}
 	}
 
 	nhc = res.nhc;
@@ -5425,7 +5429,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (!neigh)
 		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return bpf_fib_set_fwd_params(params, neigh, dev);
+	return bpf_fib_set_fwd_params(params, neigh, dev, mtu);
 }
 #endif
 
@@ -5442,7 +5446,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	struct flowi6 fl6;
 	int strict = 0;
 	int oif, err;
-	u32 mtu;
+	u32 mtu = 0;
 
 	/* link local addresses are never forwarded */
 	if (rt6_need_strict(dst) || rt6_need_strict(src))
@@ -5517,8 +5521,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	if (check_mtu) {
 		mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src);
-		if (params->tot_len > mtu)
+		if (params->tot_len > mtu) {
+			params->mtu_result = mtu; /* union with tot_len */
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
+		}
 	}
 
 	if (res.nh->fib_nh_lws)
@@ -5538,7 +5544,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (!neigh)
 		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return bpf_fib_set_fwd_params(params, neigh, dev);
+	return bpf_fib_set_fwd_params(params, neigh, dev, mtu);
 }
 #endif
 
@@ -5614,6 +5620,8 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 		dev = dev_get_by_index_rcu(net, params->ifindex);
 		if (!is_skb_forwardable(dev, skb))
 			rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
+
+		params->mtu_result = dev->mtu; /* union with tot_len */
 	}
 
 	return rc;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 07cc2e404291..6b1f6058cccf 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2239,6 +2239,9 @@ union bpf_attr {
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  *		  packet is not forwarded or needs assist from full stack
  *
+ *		If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ *		was exceeded and output params->mtu_result contains the MTU.
+ *
  * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
  *		Add an entry to, or update a sockhash *map* referencing sockets.
@@ -4990,9 +4993,13 @@ struct bpf_fib_lookup {
 	__be16	sport;
 	__be16	dport;
 
-	/* total length of packet from network header - used for MTU check */
-	__u16	tot_len;
+	union {	/* used for MTU check */
+		/* input to lookup */
+		__u16	tot_len; /* L3 length from network hdr (iph->tot_len) */
 
+		/* output: MTU value */
+		__u16	mtu_result;
+	};
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */
-- 
cgit v1.2.3


From 34b2021cc61642d61c3cf943d9e71925b827941b Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 9 Feb 2021 14:38:24 +0100
Subject: bpf: Add BPF-helper for MTU checking

This BPF-helper bpf_check_mtu() works for both XDP and TC-BPF programs.

The SKB object is complex and the skb->len value (accessible from
BPF-prog) also include the length of any extra GRO/GSO segments, but
without taking into account that these GRO/GSO segments get added
transport (L4) and network (L3) headers before being transmitted. Thus,
this BPF-helper is created such that the BPF-programmer don't need to
handle these details in the BPF-prog.

The API is designed to help the BPF-programmer, that want to do packet
context size changes, which involves other helpers. These other helpers
usually does a delta size adjustment. This helper also support a delta
size (len_diff), which allow BPF-programmer to reuse arguments needed by
these other helpers, and perform the MTU check prior to doing any actual
size adjustment of the packet context.

It is on purpose, that we allow the len adjustment to become a negative
result, that will pass the MTU check. This might seem weird, but it's not
this helpers responsibility to "catch" wrong len_diff adjustments. Other
helpers will take care of these checks, if BPF-programmer chooses to do
actual size adjustment.

V14:
 - Improve man-page desc of len_diff.

V13:
 - Enforce flag BPF_MTU_CHK_SEGS cannot use len_diff.

V12:
 - Simplify segment check that calls skb_gso_validate_network_len.
 - Helpers should return long

V9:
- Use dev->hard_header_len (instead of ETH_HLEN)
- Annotate with unlikely req from Daniel
- Fix logic error using skb_gso_validate_network_len from Daniel

V6:
- Took John's advice and dropped BPF_MTU_CHK_RELAX
- Returned MTU is kept at L3-level (like fib_lookup)

V4: Lot of changes
 - ifindex 0 now use current netdev for MTU lookup
 - rename helper from bpf_mtu_check to bpf_check_mtu
 - fix bug for GSO pkt length (as skb->len is total len)
 - remove __bpf_len_adj_positive, simply allow negative len adj

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/161287790461.790810.3429728639563297353.stgit@firesoul
---
 include/uapi/linux/bpf.h       |  75 +++++++++++++++++++++++++++
 net/core/filter.c              | 114 +++++++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  75 +++++++++++++++++++++++++++
 3 files changed, 264 insertions(+)

(limited to 'net/core')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6b1f6058cccf..4c24daa43bac 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3847,6 +3847,69 @@ union bpf_attr {
  *	Return
  *		A pointer to a struct socket on success or NULL if the file is
  *		not a socket.
+ *
+ * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
+ *	Description
+
+ *		Check ctx packet size against exceeding MTU of net device (based
+ *		on *ifindex*).  This helper will likely be used in combination
+ *		with helpers that adjust/change the packet size.
+ *
+ *		The argument *len_diff* can be used for querying with a planned
+ *		size change. This allows to check MTU prior to changing packet
+ *		ctx. Providing an *len_diff* adjustment that is larger than the
+ *		actual packet size (resulting in negative packet size) will in
+ *		principle not exceed the MTU, why it is not considered a
+ *		failure.  Other BPF-helpers are needed for performing the
+ *		planned size change, why the responsability for catch a negative
+ *		packet size belong in those helpers.
+ *
+ *		Specifying *ifindex* zero means the MTU check is performed
+ *		against the current net device.  This is practical if this isn't
+ *		used prior to redirect.
+ *
+ *		The Linux kernel route table can configure MTUs on a more
+ *		specific per route level, which is not provided by this helper.
+ *		For route level MTU checks use the **bpf_fib_lookup**\ ()
+ *		helper.
+ *
+ *		*ctx* is either **struct xdp_md** for XDP programs or
+ *		**struct sk_buff** for tc cls_act programs.
+ *
+ *		The *flags* argument can be a combination of one or more of the
+ *		following values:
+ *
+ *		**BPF_MTU_CHK_SEGS**
+ *			This flag will only works for *ctx* **struct sk_buff**.
+ *			If packet context contains extra packet segment buffers
+ *			(often knows as GSO skb), then MTU check is harder to
+ *			check at this point, because in transmit path it is
+ *			possible for the skb packet to get re-segmented
+ *			(depending on net device features).  This could still be
+ *			a MTU violation, so this flag enables performing MTU
+ *			check against segments, with a different violation
+ *			return code to tell it apart. Check cannot use len_diff.
+ *
+ *		On return *mtu_len* pointer contains the MTU value of the net
+ *		device.  Remember the net device configured MTU is the L3 size,
+ *		which is returned here and XDP and TX length operate at L2.
+ *		Helper take this into account for you, but remember when using
+ *		MTU value in your BPF-code.  On input *mtu_len* must be a valid
+ *		pointer and be initialized (to zero), else verifier will reject
+ *		BPF program.
+ *
+ *	Return
+ *		* 0 on success, and populate MTU value in *mtu_len* pointer.
+ *
+ *		* < 0 if any input argument is invalid (*mtu_len* not updated)
+ *
+ *		MTU violations return positive values, but also populate MTU
+ *		value in *mtu_len* pointer, as this can be needed for
+ *		implementing PMTU handing:
+ *
+ *		* **BPF_MTU_CHK_RET_FRAG_NEEDED**
+ *		* **BPF_MTU_CHK_RET_SEGS_TOOBIG**
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -4012,6 +4075,7 @@ union bpf_attr {
 	FN(ktime_get_coarse_ns),	\
 	FN(ima_inode_hash),		\
 	FN(sock_from_file),		\
+	FN(check_mtu),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5045,6 +5109,17 @@ struct bpf_redir_neigh {
 	};
 };
 
+/* bpf_check_mtu flags*/
+enum  bpf_check_mtu_flags {
+	BPF_MTU_CHK_SEGS  = (1U << 0),
+};
+
+enum bpf_check_mtu_ret {
+	BPF_MTU_CHK_RET_SUCCESS,      /* check and lookup successful */
+	BPF_MTU_CHK_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+	BPF_MTU_CHK_RET_SEGS_TOOBIG,  /* GSO re-segmentation needed to fwd */
+};
+
 enum bpf_task_fd_type {
 	BPF_FD_TYPE_RAW_TRACEPOINT,	/* tp name */
 	BPF_FD_TYPE_TRACEPOINT,		/* tp name */
diff --git a/net/core/filter.c b/net/core/filter.c
index e7a9b1667dd6..439f43f00483 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5637,6 +5637,116 @@ static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+static struct net_device *__dev_via_ifindex(struct net_device *dev_curr,
+					    u32 ifindex)
+{
+	struct net *netns = dev_net(dev_curr);
+
+	/* Non-redirect use-cases can use ifindex=0 and save ifindex lookup */
+	if (ifindex == 0)
+		return dev_curr;
+
+	return dev_get_by_index_rcu(netns, ifindex);
+}
+
+BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
+	   u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags)
+{
+	int ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
+	struct net_device *dev = skb->dev;
+	int skb_len, dev_len;
+	int mtu;
+
+	if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
+		return -EINVAL;
+
+	if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff))
+		return -EINVAL;
+
+	dev = __dev_via_ifindex(dev, ifindex);
+	if (unlikely(!dev))
+		return -ENODEV;
+
+	mtu = READ_ONCE(dev->mtu);
+
+	dev_len = mtu + dev->hard_header_len;
+	skb_len = skb->len + len_diff; /* minus result pass check */
+	if (skb_len <= dev_len) {
+		ret = BPF_MTU_CHK_RET_SUCCESS;
+		goto out;
+	}
+	/* At this point, skb->len exceed MTU, but as it include length of all
+	 * segments, it can still be below MTU.  The SKB can possibly get
+	 * re-segmented in transmit path (see validate_xmit_skb).  Thus, user
+	 * must choose if segs are to be MTU checked.
+	 */
+	if (skb_is_gso(skb)) {
+		ret = BPF_MTU_CHK_RET_SUCCESS;
+
+		if (flags & BPF_MTU_CHK_SEGS &&
+		    !skb_gso_validate_network_len(skb, mtu))
+			ret = BPF_MTU_CHK_RET_SEGS_TOOBIG;
+	}
+out:
+	/* BPF verifier guarantees valid pointer */
+	*mtu_len = mtu;
+
+	return ret;
+}
+
+BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
+	   u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags)
+{
+	struct net_device *dev = xdp->rxq->dev;
+	int xdp_len = xdp->data_end - xdp->data;
+	int ret = BPF_MTU_CHK_RET_SUCCESS;
+	int mtu, dev_len;
+
+	/* XDP variant doesn't support multi-buffer segment check (yet) */
+	if (unlikely(flags))
+		return -EINVAL;
+
+	dev = __dev_via_ifindex(dev, ifindex);
+	if (unlikely(!dev))
+		return -ENODEV;
+
+	mtu = READ_ONCE(dev->mtu);
+
+	/* Add L2-header as dev MTU is L3 size */
+	dev_len = mtu + dev->hard_header_len;
+
+	xdp_len += len_diff; /* minus result pass check */
+	if (xdp_len > dev_len)
+		ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
+
+	/* BPF verifier guarantees valid pointer */
+	*mtu_len = mtu;
+
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_skb_check_mtu_proto = {
+	.func		= bpf_skb_check_mtu,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_ANYTHING,
+	.arg3_type      = ARG_PTR_TO_INT,
+	.arg4_type      = ARG_ANYTHING,
+	.arg5_type      = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto bpf_xdp_check_mtu_proto = {
+	.func		= bpf_xdp_check_mtu,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_ANYTHING,
+	.arg3_type      = ARG_PTR_TO_INT,
+	.arg4_type      = ARG_ANYTHING,
+	.arg5_type      = ARG_ANYTHING,
+};
+
 #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len)
 {
@@ -7222,6 +7332,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_socket_uid_proto;
 	case BPF_FUNC_fib_lookup:
 		return &bpf_skb_fib_lookup_proto;
+	case BPF_FUNC_check_mtu:
+		return &bpf_skb_check_mtu_proto;
 	case BPF_FUNC_sk_fullsock:
 		return &bpf_sk_fullsock_proto;
 	case BPF_FUNC_sk_storage_get:
@@ -7291,6 +7403,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_adjust_tail_proto;
 	case BPF_FUNC_fib_lookup:
 		return &bpf_xdp_fib_lookup_proto;
+	case BPF_FUNC_check_mtu:
+		return &bpf_xdp_check_mtu_proto;
 #ifdef CONFIG_INET
 	case BPF_FUNC_sk_lookup_udp:
 		return &bpf_xdp_sk_lookup_udp_proto;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6b1f6058cccf..4c24daa43bac 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3847,6 +3847,69 @@ union bpf_attr {
  *	Return
  *		A pointer to a struct socket on success or NULL if the file is
  *		not a socket.
+ *
+ * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
+ *	Description
+
+ *		Check ctx packet size against exceeding MTU of net device (based
+ *		on *ifindex*).  This helper will likely be used in combination
+ *		with helpers that adjust/change the packet size.
+ *
+ *		The argument *len_diff* can be used for querying with a planned
+ *		size change. This allows to check MTU prior to changing packet
+ *		ctx. Providing an *len_diff* adjustment that is larger than the
+ *		actual packet size (resulting in negative packet size) will in
+ *		principle not exceed the MTU, why it is not considered a
+ *		failure.  Other BPF-helpers are needed for performing the
+ *		planned size change, why the responsability for catch a negative
+ *		packet size belong in those helpers.
+ *
+ *		Specifying *ifindex* zero means the MTU check is performed
+ *		against the current net device.  This is practical if this isn't
+ *		used prior to redirect.
+ *
+ *		The Linux kernel route table can configure MTUs on a more
+ *		specific per route level, which is not provided by this helper.
+ *		For route level MTU checks use the **bpf_fib_lookup**\ ()
+ *		helper.
+ *
+ *		*ctx* is either **struct xdp_md** for XDP programs or
+ *		**struct sk_buff** for tc cls_act programs.
+ *
+ *		The *flags* argument can be a combination of one or more of the
+ *		following values:
+ *
+ *		**BPF_MTU_CHK_SEGS**
+ *			This flag will only works for *ctx* **struct sk_buff**.
+ *			If packet context contains extra packet segment buffers
+ *			(often knows as GSO skb), then MTU check is harder to
+ *			check at this point, because in transmit path it is
+ *			possible for the skb packet to get re-segmented
+ *			(depending on net device features).  This could still be
+ *			a MTU violation, so this flag enables performing MTU
+ *			check against segments, with a different violation
+ *			return code to tell it apart. Check cannot use len_diff.
+ *
+ *		On return *mtu_len* pointer contains the MTU value of the net
+ *		device.  Remember the net device configured MTU is the L3 size,
+ *		which is returned here and XDP and TX length operate at L2.
+ *		Helper take this into account for you, but remember when using
+ *		MTU value in your BPF-code.  On input *mtu_len* must be a valid
+ *		pointer and be initialized (to zero), else verifier will reject
+ *		BPF program.
+ *
+ *	Return
+ *		* 0 on success, and populate MTU value in *mtu_len* pointer.
+ *
+ *		* < 0 if any input argument is invalid (*mtu_len* not updated)
+ *
+ *		MTU violations return positive values, but also populate MTU
+ *		value in *mtu_len* pointer, as this can be needed for
+ *		implementing PMTU handing:
+ *
+ *		* **BPF_MTU_CHK_RET_FRAG_NEEDED**
+ *		* **BPF_MTU_CHK_RET_SEGS_TOOBIG**
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -4012,6 +4075,7 @@ union bpf_attr {
 	FN(ktime_get_coarse_ns),	\
 	FN(ima_inode_hash),		\
 	FN(sock_from_file),		\
+	FN(check_mtu),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5045,6 +5109,17 @@ struct bpf_redir_neigh {
 	};
 };
 
+/* bpf_check_mtu flags*/
+enum  bpf_check_mtu_flags {
+	BPF_MTU_CHK_SEGS  = (1U << 0),
+};
+
+enum bpf_check_mtu_ret {
+	BPF_MTU_CHK_RET_SUCCESS,      /* check and lookup successful */
+	BPF_MTU_CHK_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+	BPF_MTU_CHK_RET_SEGS_TOOBIG,  /* GSO re-segmentation needed to fwd */
+};
+
 enum bpf_task_fd_type {
 	BPF_FD_TYPE_RAW_TRACEPOINT,	/* tp name */
 	BPF_FD_TYPE_TRACEPOINT,		/* tp name */
-- 
cgit v1.2.3


From 5f7d57280c1982d993d5f4ff0edac310f820f607 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 9 Feb 2021 14:38:29 +0100
Subject: bpf: Drop MTU check when doing TC-BPF redirect to ingress

The use-case for dropping the MTU check when TC-BPF does redirect to
ingress, is described by Eyal Birger in email[0]. The summary is the
ability to increase packet size (e.g. with IPv6 headers for NAT64) and
ingress redirect packet and let normal netstack fragment packet as needed.

[0] https://lore.kernel.org/netdev/CAHsH6Gug-hsLGHQ6N0wtixdOa85LDZ3HNRHVd0opR=19Qo4W4Q@mail.gmail.com/

V15:
 - missing static for function declaration

V9:
 - Make net_device "up" (IFF_UP) check explicit in skb_do_redirect

V4:
 - Keep net_device "up" (IFF_UP) check.
 - Adjustment to handle bpf_redirect_peer() helper

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/161287790971.790810.11785274340154740591.stgit@firesoul
---
 include/linux/netdevice.h | 32 ++++++++++++++++++++++++++++++--
 net/core/dev.c            | 32 ++++++++++++++------------------
 net/core/filter.c         |  6 +++---
 3 files changed, 47 insertions(+), 23 deletions(-)

(limited to 'net/core')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ef517254367d..b9bcbfde7849 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3931,14 +3931,42 @@ int xdp_umem_query(struct net_device *dev, u16 queue_id);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
+int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb);
 bool is_skb_forwardable(const struct net_device *dev,
 			const struct sk_buff *skb);
 
+static __always_inline bool __is_skb_forwardable(const struct net_device *dev,
+						 const struct sk_buff *skb,
+						 const bool check_mtu)
+{
+	const u32 vlan_hdr_len = 4; /* VLAN_HLEN */
+	unsigned int len;
+
+	if (!(dev->flags & IFF_UP))
+		return false;
+
+	if (!check_mtu)
+		return true;
+
+	len = dev->mtu + dev->hard_header_len + vlan_hdr_len;
+	if (skb->len <= len)
+		return true;
+
+	/* if TSO is enabled, we don't care about the length as the packet
+	 * could be forwarded without being segmented before
+	 */
+	if (skb_is_gso(skb))
+		return true;
+
+	return false;
+}
+
 static __always_inline int ____dev_forward_skb(struct net_device *dev,
-					       struct sk_buff *skb)
+					       struct sk_buff *skb,
+					       const bool check_mtu)
 {
 	if (skb_orphan_frags(skb, GFP_ATOMIC) ||
-	    unlikely(!is_skb_forwardable(dev, skb))) {
+	    unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) {
 		atomic_long_inc(&dev->rx_dropped);
 		kfree_skb(skb);
 		return NET_RX_DROP;
diff --git a/net/core/dev.c b/net/core/dev.c
index 07a0347c33fb..8c820fe0eff3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2194,28 +2194,14 @@ static inline void net_timestamp_set(struct sk_buff *skb)
 
 bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb)
 {
-	unsigned int len;
-
-	if (!(dev->flags & IFF_UP))
-		return false;
-
-	len = dev->mtu + dev->hard_header_len + VLAN_HLEN;
-	if (skb->len <= len)
-		return true;
-
-	/* if TSO is enabled, we don't care about the length as the packet
-	 * could be forwarded without being segmented before
-	 */
-	if (skb_is_gso(skb))
-		return true;
-
-	return false;
+	return __is_skb_forwardable(dev, skb, true);
 }
 EXPORT_SYMBOL_GPL(is_skb_forwardable);
 
-int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+static int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb,
+			      bool check_mtu)
 {
-	int ret = ____dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, check_mtu);
 
 	if (likely(!ret)) {
 		skb->protocol = eth_type_trans(skb, dev);
@@ -2224,6 +2210,11 @@ int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 
 	return ret;
 }
+
+int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	return __dev_forward_skb2(dev, skb, true);
+}
 EXPORT_SYMBOL_GPL(__dev_forward_skb);
 
 /**
@@ -2250,6 +2241,11 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
 
+int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb)
+{
+	return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb);
+}
+
 static inline int deliver_skb(struct sk_buff *skb,
 			      struct packet_type *pt_prev,
 			      struct net_device *orig_dev)
diff --git a/net/core/filter.c b/net/core/filter.c
index 439f43f00483..7059cf604d94 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2083,13 +2083,13 @@ static const struct bpf_func_proto bpf_csum_level_proto = {
 
 static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
 {
-	return dev_forward_skb(dev, skb);
+	return dev_forward_skb_nomtu(dev, skb);
 }
 
 static inline int __bpf_rx_skb_no_mac(struct net_device *dev,
 				      struct sk_buff *skb)
 {
-	int ret = ____dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, false);
 
 	if (likely(!ret)) {
 		skb->dev = dev;
@@ -2480,7 +2480,7 @@ int skb_do_redirect(struct sk_buff *skb)
 			goto out_drop;
 		dev = ops->ndo_get_peer_dev(dev);
 		if (unlikely(!dev ||
-			     !is_skb_forwardable(dev, skb) ||
+			     !(dev->flags & IFF_UP) ||
 			     net_eq(net, dev_net(dev))))
 			goto out_drop;
 		skb->dev = dev;
-- 
cgit v1.2.3