Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2023-12-18

This PR is larger than usual and contains changes in various parts
of the kernel.

The main changes are:

1) Fix kCFI bugs in BPF, from Peter Zijlstra.

End result: all forms of indirect calls from BPF into kernel
and from kernel into BPF work with CFI enabled. This allows BPF
to work with CONFIG_FINEIBT=y.

2) Introduce BPF token object, from Andrii Nakryiko.

It adds an ability to delegate a subset of BPF features from privileged
daemon (e.g., systemd) through special mount options for userns-bound
BPF FS to a trusted unprivileged application. The design accommodates
suggestions from Christian Brauner and Paul Moore.

Example:
$ sudo mkdir -p /sys/fs/bpf/token
$ sudo mount -t bpf bpffs /sys/fs/bpf/token \
             -o delegate_cmds=prog_load:MAP_CREATE \
             -o delegate_progs=kprobe \
             -o delegate_attachs=xdp

3) Various verifier improvements and fixes, from Andrii Nakryiko, Andrei Matei.

 - Complete precision tracking support for register spills
 - Fix verification of possibly-zero-sized stack accesses
 - Fix access to uninit stack slots
 - Track aligned STACK_ZERO cases as imprecise spilled registers.
   It improves the verifier "instructions processed" metric from single
   digit to 50-60% for some programs.
 - Fix verifier retval logic

4) Support for VLAN tag in XDP hints, from Larysa Zaremba.

5) Allocate BPF trampoline via bpf_prog_pack mechanism, from Song Liu.

End result: better memory utilization and lower I$ miss for calls to BPF
via BPF trampoline.

6) Fix race between BPF prog accessing inner map and parallel delete,
from Hou Tao.

7) Add bpf_xdp_get_xfrm_state() kfunc, from Daniel Xu.

It allows BPF interact with IPSEC infra. The intent is to support
software RSS (via XDP) for the upcoming ipsec pcpu work.
Experiments on AWS demonstrate single tunnel pcpu ipsec reaching
line rate on 100G ENA nics.

8) Expand bpf_cgrp_storage to support cgroup1 non-attach, from Yafang Shao.

9) BPF file verification via fsverity, from Song Liu.

It allows BPF progs get fsverity digest.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (164 commits)
  bpf: Ensure precise is reset to false in __mark_reg_const_zero()
  selftests/bpf: Add more uprobe multi fail tests
  bpf: Fail uprobe multi link with negative offset
  selftests/bpf: Test the release of map btf
  s390/bpf: Fix indirect trampoline generation
  selftests/bpf: Temporarily disable dummy_struct_ops test on s390
  x86/cfi,bpf: Fix bpf_exception_cb() signature
  bpf: Fix dtor CFI
  cfi: Add CFI_NOSEAL()
  x86/cfi,bpf: Fix bpf_struct_ops CFI
  x86/cfi,bpf: Fix bpf_callback_t CFI
  x86/cfi,bpf: Fix BPF JIT call
  cfi: Flip headers
  selftests/bpf: Add test for abnormal cnt during multi-kprobe attachment
  selftests/bpf: Don't use libbpf_get_error() in kprobe_multi_test
  selftests/bpf: Add test for abnormal cnt during multi-uprobe attachment
  bpf: Limit the number of kprobes when attaching program to multiple kprobes
  bpf: Limit the number of uprobes when attaching program to multiple uprobes
  bpf: xdp: Register generic_kfunc_set with XDP programs
  selftests/bpf: utilize string values for delegate_xxx mount options
  ...
====================

Link: https://lore.kernel.org/r/20231219000520.34178-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 113 insertions, 19 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index 33cdf88efa6b..05edcf32f528 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -20,7 +20,7 @@
 
 #define UDP_PAYLOAD_BYTES 4
 
-#define AF_XDP_SOURCE_PORT 1234
+#define UDP_SOURCE_PORT 1234
 #define AF_XDP_CONSUMER_PORT 8080
 
 #define UMEM_NUM 16
@@ -33,6 +33,18 @@
 #define RX_ADDR "10.0.0.2"
 #define PREFIX_LEN "8"
 #define FAMILY AF_INET
+#define TX_NETNS_NAME "xdp_metadata_tx"
+#define RX_NETNS_NAME "xdp_metadata_rx"
+#define TX_MAC "00:00:00:00:00:01"
+#define RX_MAC "00:00:00:00:00:02"
+
+#define VLAN_ID 59
+#define VLAN_PROTO "802.1Q"
+#define VLAN_PID htons(ETH_P_8021Q)
+#define TX_NAME_VLAN TX_NAME "." TO_STR(VLAN_ID)
+
+#define XDP_RSS_TYPE_L4 BIT(3)
+#define VLAN_VID_MASK 0xfff
 
 struct xsk {
 	void *umem_area;
@@ -181,7 +193,7 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 	ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)");
 	ip_csum(iph);
 
-	udph->source = htons(AF_XDP_SOURCE_PORT);
+	udph->source = htons(UDP_SOURCE_PORT);
 	udph->dest = htons(dst_port);
 	udph->len = htons(sizeof(*udph) + UDP_PAYLOAD_BYTES);
 	udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
@@ -204,6 +216,30 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 	return 0;
 }
 
+static int generate_packet_inet(void)
+{
+	char udp_payload[UDP_PAYLOAD_BYTES];
+	struct sockaddr_in rx_addr;
+	int sock_fd, err = 0;
+
+	/* Build a packet */
+	memset(udp_payload, 0xAA, UDP_PAYLOAD_BYTES);
+	rx_addr.sin_addr.s_addr = inet_addr(RX_ADDR);
+	rx_addr.sin_family = AF_INET;
+	rx_addr.sin_port = htons(AF_XDP_CONSUMER_PORT);
+
+	sock_fd = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
+	if (!ASSERT_GE(sock_fd, 0, "socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP)"))
+		return sock_fd;
+
+	err = sendto(sock_fd, udp_payload, UDP_PAYLOAD_BYTES, MSG_DONTWAIT,
+		     (void *)&rx_addr, sizeof(rx_addr));
+	ASSERT_GE(err, 0, "sendto");
+
+	close(sock_fd);
+	return err;
+}
+
 static void complete_tx(struct xsk *xsk)
 {
 	struct xsk_tx_metadata *meta;
@@ -236,7 +272,7 @@ static void refill_rx(struct xsk *xsk, __u64 addr)
 	}
 }
 
-static int verify_xsk_metadata(struct xsk *xsk)
+static int verify_xsk_metadata(struct xsk *xsk, bool sent_from_af_xdp)
 {
 	const struct xdp_desc *rx_desc;
 	struct pollfd fds = {};
@@ -290,17 +326,42 @@ static int verify_xsk_metadata(struct xsk *xsk)
 	if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash"))
 		return -1;
 
+	if (!sent_from_af_xdp) {
+		if (!ASSERT_NEQ(meta->rx_hash_type & XDP_RSS_TYPE_L4, 0, "rx_hash_type"))
+			return -1;
+
+		if (!ASSERT_EQ(meta->rx_vlan_tci & VLAN_VID_MASK, VLAN_ID, "rx_vlan_tci"))
+			return -1;
+
+		if (!ASSERT_EQ(meta->rx_vlan_proto, VLAN_PID, "rx_vlan_proto"))
+			return -1;
+		goto done;
+	}
+
 	ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type");
 
 	/* checksum offload */
 	ASSERT_EQ(udph->check, htons(0x721c), "csum");
 
+done:
 	xsk_ring_cons__release(&xsk->rx, 1);
 	refill_rx(xsk, comp_addr);
 
 	return 0;
 }
 
+static void switch_ns_to_rx(struct nstoken **tok)
+{
+	close_netns(*tok);
+	*tok = open_netns(RX_NETNS_NAME);
+}
+
+static void switch_ns_to_tx(struct nstoken **tok)
+{
+	close_netns(*tok);
+	*tok = open_netns(TX_NETNS_NAME);
+}
+
 void test_xdp_metadata(void)
 {
 	struct xdp_metadata2 *bpf_obj2 = NULL;
@@ -318,27 +379,35 @@ void test_xdp_metadata(void)
 	int sock_fd;
 	int ret;
 
-	/* Setup new networking namespace, with a veth pair. */
+	/* Setup new networking namespaces, with a veth pair. */
+	SYS(out, "ip netns add " TX_NETNS_NAME);
+	SYS(out, "ip netns add " RX_NETNS_NAME);
 
-	SYS(out, "ip netns add xdp_metadata");
-	tok = open_netns("xdp_metadata");
+	tok = open_netns(TX_NETNS_NAME);
 	SYS(out, "ip link add numtxqueues 1 numrxqueues 1 " TX_NAME
 	    " type veth peer " RX_NAME " numtxqueues 1 numrxqueues 1");
-	SYS(out, "ip link set dev " TX_NAME " address 00:00:00:00:00:01");
-	SYS(out, "ip link set dev " RX_NAME " address 00:00:00:00:00:02");
+	SYS(out, "ip link set " RX_NAME " netns " RX_NETNS_NAME);
+
+	SYS(out, "ip link set dev " TX_NAME " address " TX_MAC);
 	SYS(out, "ip link set dev " TX_NAME " up");
+
+	SYS(out, "ip link add link " TX_NAME " " TX_NAME_VLAN
+		 " type vlan proto " VLAN_PROTO " id " TO_STR(VLAN_ID));
+	SYS(out, "ip link set dev " TX_NAME_VLAN " up");
+	SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME_VLAN);
+
+	/* Avoid ARP calls */
+	SYS(out, "ip -4 neigh add " RX_ADDR " lladdr " RX_MAC " dev " TX_NAME_VLAN);
+
+	switch_ns_to_rx(&tok);
+
+	SYS(out, "ip link set dev " RX_NAME " address " RX_MAC);
 	SYS(out, "ip link set dev " RX_NAME " up");
-	SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME);
 	SYS(out, "ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME);
 
 	rx_ifindex = if_nametoindex(RX_NAME);
-	tx_ifindex = if_nametoindex(TX_NAME);
-
-	/* Setup separate AF_XDP for TX and RX interfaces. */
 
-	ret = open_xsk(tx_ifindex, &tx_xsk);
-	if (!ASSERT_OK(ret, "open_xsk(TX_NAME)"))
-		goto out;
+	/* Setup separate AF_XDP for RX interface. */
 
 	ret = open_xsk(rx_ifindex, &rx_xsk);
 	if (!ASSERT_OK(ret, "open_xsk(RX_NAME)"))
@@ -379,18 +448,38 @@ void test_xdp_metadata(void)
 	if (!ASSERT_GE(ret, 0, "bpf_map_update_elem"))
 		goto out;
 
-	/* Send packet destined to RX AF_XDP socket. */
+	switch_ns_to_tx(&tok);
+
+	/* Setup separate AF_XDP for TX interface nad send packet to the RX socket. */
+	tx_ifindex = if_nametoindex(TX_NAME);
+	ret = open_xsk(tx_ifindex, &tx_xsk);
+	if (!ASSERT_OK(ret, "open_xsk(TX_NAME)"))
+		goto out;
+
 	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
 		       "generate AF_XDP_CONSUMER_PORT"))
 		goto out;
 
-	/* Verify AF_XDP RX packet has proper metadata. */
-	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk), 0,
+	switch_ns_to_rx(&tok);
+
+	/* Verify packet sent from AF_XDP has proper metadata. */
+	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, true), 0,
 		       "verify_xsk_metadata"))
 		goto out;
 
+	switch_ns_to_tx(&tok);
 	complete_tx(&tx_xsk);
 
+	/* Now check metadata of packet, generated with network stack */
+	if (!ASSERT_GE(generate_packet_inet(), 0, "generate UDP packet"))
+		goto out;
+
+	switch_ns_to_rx(&tok);
+
+	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, false), 0,
+		       "verify_xsk_metadata"))
+		goto out;
+
 	/* Make sure freplace correctly picks up original bound device
 	 * and doesn't crash.
 	 */
@@ -408,11 +497,15 @@ void test_xdp_metadata(void)
 	if (!ASSERT_OK(xdp_metadata2__attach(bpf_obj2), "attach freplace"))
 		goto out;
 
+	switch_ns_to_tx(&tok);
+
 	/* Send packet to trigger . */
 	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
 		       "generate freplace packet"))
 		goto out;
 
+	switch_ns_to_rx(&tok);
+
 	while (!retries--) {
 		if (bpf_obj2->bss->called)
 			break;
@@ -427,5 +520,6 @@ out:
 	xdp_metadata__destroy(bpf_obj);
 	if (tok)
 		close_netns(tok);
-	SYS_NOFAIL("ip netns del xdp_metadata");
+	SYS_NOFAIL("ip netns del " RX_NETNS_NAME);
+	SYS_NOFAIL("ip netns del " TX_NETNS_NAME);
 }