From 096eccdef0b32f47e9354231ddc3aaaf9527d51c Mon Sep 17 00:00:00 2001
From: Jussi Maki <joamaki@gmail.com>
Date: Wed, 5 May 2021 08:59:25 +0000
Subject: selftests/bpf: Rewrite test_tc_redirect.sh as
 prog_tests/tc_redirect.c

As discussed in [0], this ports test_tc_redirect.sh to the test_progs
framework and removes the old test.

This makes it more in line with rest of the tests and makes it possible
to run this test case with vmtest.sh and under the bpf CI.

The upcoming skb_change_head() helper fix in [0] is depending on it and
extending the test case to redirect a packet from L3 device to veth.

  [0] https://lore.kernel.org/bpf/20210427135550.807355-1-joamaki@gmail.com

Signed-off-by: Jussi Maki <joamaki@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210505085925.783985-1-joamaki@gmail.com
---
 tools/testing/selftests/bpf/network_helpers.c      |   2 +-
 tools/testing/selftests/bpf/network_helpers.h      |   1 +
 .../testing/selftests/bpf/prog_tests/tc_redirect.c | 589 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/test_tc_neigh.c  |  33 +-
 .../selftests/bpf/progs/test_tc_neigh_fib.c        |   9 +-
 tools/testing/selftests/bpf/progs/test_tc_peer.c   |  33 +-
 tools/testing/selftests/bpf/test_tc_redirect.sh    | 216 --------
 7 files changed, 617 insertions(+), 266 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/tc_redirect.c
 delete mode 100755 tools/testing/selftests/bpf/test_tc_redirect.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 12ee40284da0..2060bc122c53 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -40,7 +40,7 @@ struct ipv6_packet pkt_v6 = {
 	.tcp.doff = 5,
 };
 
-static int settimeo(int fd, int timeout_ms)
+int settimeo(int fd, int timeout_ms)
 {
 	struct timeval timeout = { .tv_sec = 3 };
 
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 7205f8afdba1..5e0d51c07b63 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -33,6 +33,7 @@ struct ipv6_packet {
 } __packed;
 extern struct ipv6_packet pkt_v6;
 
+int settimeo(int fd, int timeout_ms);
 int start_server(int family, int type, const char *addr, __u16 port,
 		 int timeout_ms);
 int connect_to_fd(int server_fd, int timeout_ms);
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
new file mode 100644
index 000000000000..95ef9fcd31d8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -0,0 +1,589 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/*
+ * This test sets up 3 netns (src <-> fwd <-> dst). There is no direct veth link
+ * between src and dst. The netns fwd has veth links to each src and dst. The
+ * client is in src and server in dst. The test installs a TC BPF program to each
+ * host facing veth in fwd which calls into i) bpf_redirect_neigh() to perform the
+ * neigh addr population and redirect or ii) bpf_redirect_peer() for namespace
+ * switch from ingress side; it also installs a checker prog on the egress side
+ * to drop unexpected traffic.
+ */
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <linux/limits.h>
+#include <linux/sysctl.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "test_tc_neigh_fib.skel.h"
+#include "test_tc_neigh.skel.h"
+#include "test_tc_peer.skel.h"
+
+#define NS_SRC "ns_src"
+#define NS_FWD "ns_fwd"
+#define NS_DST "ns_dst"
+
+#define IP4_SRC "172.16.1.100"
+#define IP4_DST "172.16.2.100"
+#define IP4_PORT 9004
+
+#define IP6_SRC "::1:dead:beef:cafe"
+#define IP6_DST "::2:dead:beef:cafe"
+#define IP6_PORT 9006
+
+#define IP4_SLL "169.254.0.1"
+#define IP4_DLL "169.254.0.2"
+#define IP4_NET "169.254.0.0"
+
+#define IFADDR_STR_LEN 18
+#define PING_ARGS "-c 3 -w 10 -q"
+
+#define SRC_PROG_PIN_FILE "/sys/fs/bpf/test_tc_src"
+#define DST_PROG_PIN_FILE "/sys/fs/bpf/test_tc_dst"
+#define CHK_PROG_PIN_FILE "/sys/fs/bpf/test_tc_chk"
+
+#define TIMEOUT_MILLIS 10000
+
+#define MAX_PROC_MODS 128
+#define MAX_PROC_VALUE_LEN 16
+
+#define log_err(MSG, ...) \
+	fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
+		__FILE__, __LINE__, strerror(errno), ##__VA_ARGS__)
+
+struct proc_mod {
+	char path[PATH_MAX];
+	char oldval[MAX_PROC_VALUE_LEN];
+	int oldlen;
+};
+
+static const char * const namespaces[] = {NS_SRC, NS_FWD, NS_DST, NULL};
+static int root_netns_fd = -1;
+static int num_proc_mods;
+static struct proc_mod proc_mods[MAX_PROC_MODS];
+
+/**
+ * modify_proc() - Modify entry in /proc
+ *
+ * Modifies an entry in /proc and saves the original value for later
+ * restoration with restore_proc().
+ */
+static int modify_proc(const char *path, const char *newval)
+{
+	struct proc_mod *mod;
+	FILE *f;
+
+	if (num_proc_mods + 1 > MAX_PROC_MODS)
+		return -1;
+
+	f = fopen(path, "r+");
+	if (!f)
+		return -1;
+
+	mod = &proc_mods[num_proc_mods];
+	num_proc_mods++;
+
+	strncpy(mod->path, path, PATH_MAX);
+
+	if (!fread(mod->oldval, 1, MAX_PROC_VALUE_LEN, f)) {
+		log_err("reading from %s failed", path);
+		goto fail;
+	}
+	rewind(f);
+	if (fwrite(newval, strlen(newval), 1, f) != 1) {
+		log_err("writing to %s failed", path);
+		goto fail;
+	}
+
+	fclose(f);
+	return 0;
+
+fail:
+	fclose(f);
+	num_proc_mods--;
+	return -1;
+}
+
+/**
+ * restore_proc() - Restore all /proc modifications
+ */
+static void restore_proc(void)
+{
+	int i;
+
+	for (i = 0; i < num_proc_mods; i++) {
+		struct proc_mod *mod = &proc_mods[i];
+		FILE *f;
+
+		f = fopen(mod->path, "w");
+		if (!f) {
+			log_err("fopen of %s failed", mod->path);
+			continue;
+		}
+
+		if (fwrite(mod->oldval, mod->oldlen, 1, f) != 1)
+			log_err("fwrite to %s failed", mod->path);
+
+		fclose(f);
+	}
+	num_proc_mods = 0;
+}
+
+/**
+ * setns_by_name() - Set networks namespace by name
+ */
+static int setns_by_name(const char *name)
+{
+	int nsfd;
+	char nspath[PATH_MAX];
+	int err;
+
+	snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name);
+	nsfd = open(nspath, O_RDONLY | O_CLOEXEC);
+	if (nsfd < 0)
+		return nsfd;
+
+	err = setns(nsfd, CLONE_NEWNET);
+	close(nsfd);
+
+	return err;
+}
+
+/**
+ * setns_root() - Set network namespace to original (root) namespace
+ *
+ * Not expected to ever fail, so error not returned, but failure logged
+ * and test marked as failed.
+ */
+static void setns_root(void)
+{
+	ASSERT_OK(setns(root_netns_fd, CLONE_NEWNET), "setns root");
+}
+
+static int netns_setup_namespaces(const char *verb)
+{
+	const char * const *ns = namespaces;
+	char cmd[128];
+
+	while (*ns) {
+		snprintf(cmd, sizeof(cmd), "ip netns %s %s", verb, *ns);
+		if (!ASSERT_OK(system(cmd), cmd))
+			return -1;
+		ns++;
+	}
+	return 0;
+}
+
+struct netns_setup_result {
+	int ifindex_veth_src_fwd;
+	int ifindex_veth_dst_fwd;
+};
+
+static int get_ifaddr(const char *name, char *ifaddr)
+{
+	char path[PATH_MAX];
+	FILE *f;
+	int ret;
+
+	snprintf(path, PATH_MAX, "/sys/class/net/%s/address", name);
+	f = fopen(path, "r");
+	if (!ASSERT_OK_PTR(f, path))
+		return -1;
+
+	ret = fread(ifaddr, 1, IFADDR_STR_LEN, f);
+	if (!ASSERT_EQ(ret, IFADDR_STR_LEN, "fread ifaddr")) {
+		fclose(f);
+		return -1;
+	}
+	fclose(f);
+	return 0;
+}
+
+static int get_ifindex(const char *name)
+{
+	char path[PATH_MAX];
+	char buf[32];
+	FILE *f;
+	int ret;
+
+	snprintf(path, PATH_MAX, "/sys/class/net/%s/ifindex", name);
+	f = fopen(path, "r");
+	if (!ASSERT_OK_PTR(f, path))
+		return -1;
+
+	ret = fread(buf, 1, sizeof(buf), f);
+	if (!ASSERT_GT(ret, 0, "fread ifindex")) {
+		fclose(f);
+		return -1;
+	}
+	fclose(f);
+	return atoi(buf);
+}
+
+#define SYS(fmt, ...)						\
+	({							\
+		char cmd[1024];					\
+		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
+		if (!ASSERT_OK(system(cmd), cmd))		\
+			goto fail;				\
+	})
+
+static int netns_setup_links_and_routes(struct netns_setup_result *result)
+{
+	char veth_src_fwd_addr[IFADDR_STR_LEN+1] = {};
+	char veth_dst_fwd_addr[IFADDR_STR_LEN+1] = {};
+
+	SYS("ip link add veth_src type veth peer name veth_src_fwd");
+	SYS("ip link add veth_dst type veth peer name veth_dst_fwd");
+	if (get_ifaddr("veth_src_fwd", veth_src_fwd_addr))
+		goto fail;
+	if (get_ifaddr("veth_dst_fwd", veth_dst_fwd_addr))
+		goto fail;
+
+	result->ifindex_veth_src_fwd = get_ifindex("veth_src_fwd");
+	if (result->ifindex_veth_src_fwd < 0)
+		goto fail;
+	result->ifindex_veth_dst_fwd = get_ifindex("veth_dst_fwd");
+	if (result->ifindex_veth_dst_fwd < 0)
+		goto fail;
+
+	SYS("ip link set veth_src netns " NS_SRC);
+	SYS("ip link set veth_src_fwd netns " NS_FWD);
+	SYS("ip link set veth_dst_fwd netns " NS_FWD);
+	SYS("ip link set veth_dst netns " NS_DST);
+
+	/** setup in 'src' namespace */
+	if (!ASSERT_OK(setns_by_name(NS_SRC), "setns src"))
+		goto fail;
+
+	SYS("ip addr add " IP4_SRC "/32 dev veth_src");
+	SYS("ip addr add " IP6_SRC "/128 dev veth_src nodad");
+	SYS("ip link set dev veth_src up");
+
+	SYS("ip route add " IP4_DST "/32 dev veth_src scope global");
+	SYS("ip route add " IP4_NET "/16 dev veth_src scope global");
+	SYS("ip route add " IP6_DST "/128 dev veth_src scope global");
+
+	SYS("ip neigh add " IP4_DST " dev veth_src lladdr %s",
+	    veth_src_fwd_addr);
+	SYS("ip neigh add " IP6_DST " dev veth_src lladdr %s",
+	    veth_src_fwd_addr);
+
+	/** setup in 'fwd' namespace */
+	if (!ASSERT_OK(setns_by_name(NS_FWD), "setns fwd"))
+		goto fail;
+
+	/* The fwd netns automatically gets a v6 LL address / routes, but also
+	 * needs v4 one in order to start ARP probing. IP4_NET route is added
+	 * to the endpoints so that the ARP processing will reply.
+	 */
+	SYS("ip addr add " IP4_SLL "/32 dev veth_src_fwd");
+	SYS("ip addr add " IP4_DLL "/32 dev veth_dst_fwd");
+	SYS("ip link set dev veth_src_fwd up");
+	SYS("ip link set dev veth_dst_fwd up");
+
+	SYS("ip route add " IP4_SRC "/32 dev veth_src_fwd scope global");
+	SYS("ip route add " IP6_SRC "/128 dev veth_src_fwd scope global");
+	SYS("ip route add " IP4_DST "/32 dev veth_dst_fwd scope global");
+	SYS("ip route add " IP6_DST "/128 dev veth_dst_fwd scope global");
+
+	/** setup in 'dst' namespace */
+	if (!ASSERT_OK(setns_by_name(NS_DST), "setns dst"))
+		goto fail;
+
+	SYS("ip addr add " IP4_DST "/32 dev veth_dst");
+	SYS("ip addr add " IP6_DST "/128 dev veth_dst nodad");
+	SYS("ip link set dev veth_dst up");
+
+	SYS("ip route add " IP4_SRC "/32 dev veth_dst scope global");
+	SYS("ip route add " IP4_NET "/16 dev veth_dst scope global");
+	SYS("ip route add " IP6_SRC "/128 dev veth_dst scope global");
+
+	SYS("ip neigh add " IP4_SRC " dev veth_dst lladdr %s",
+	    veth_dst_fwd_addr);
+	SYS("ip neigh add " IP6_SRC " dev veth_dst lladdr %s",
+	    veth_dst_fwd_addr);
+
+	setns_root();
+	return 0;
+fail:
+	setns_root();
+	return -1;
+}
+
+static int netns_load_bpf(void)
+{
+	if (!ASSERT_OK(setns_by_name(NS_FWD), "setns fwd"))
+		return -1;
+
+	SYS("tc qdisc add dev veth_src_fwd clsact");
+	SYS("tc filter add dev veth_src_fwd ingress bpf da object-pinned "
+	    SRC_PROG_PIN_FILE);
+	SYS("tc filter add dev veth_src_fwd egress bpf da object-pinned "
+	    CHK_PROG_PIN_FILE);
+
+	SYS("tc qdisc add dev veth_dst_fwd clsact");
+	SYS("tc filter add dev veth_dst_fwd ingress bpf da object-pinned "
+	    DST_PROG_PIN_FILE);
+	SYS("tc filter add dev veth_dst_fwd egress bpf da object-pinned "
+	    CHK_PROG_PIN_FILE);
+
+	setns_root();
+	return -1;
+fail:
+	setns_root();
+	return -1;
+}
+
+static int netns_unload_bpf(void)
+{
+	if (!ASSERT_OK(setns_by_name(NS_FWD), "setns fwd"))
+		goto fail;
+	SYS("tc qdisc delete dev veth_src_fwd clsact");
+	SYS("tc qdisc delete dev veth_dst_fwd clsact");
+
+	setns_root();
+	return 0;
+fail:
+	setns_root();
+	return -1;
+}
+
+
+static void test_tcp(int family, const char *addr, __u16 port)
+{
+	int listen_fd = -1, accept_fd = -1, client_fd = -1;
+	char buf[] = "testing testing";
+	int n;
+
+	if (!ASSERT_OK(setns_by_name(NS_DST), "setns dst"))
+		return;
+
+	listen_fd = start_server(family, SOCK_STREAM, addr, port, 0);
+	if (!ASSERT_GE(listen_fd, 0, "listen"))
+		goto done;
+
+	if (!ASSERT_OK(setns_by_name(NS_SRC), "setns src"))
+		goto done;
+
+	client_fd = connect_to_fd(listen_fd, TIMEOUT_MILLIS);
+	if (!ASSERT_GE(client_fd, 0, "connect_to_fd"))
+		goto done;
+
+	accept_fd = accept(listen_fd, NULL, NULL);
+	if (!ASSERT_GE(accept_fd, 0, "accept"))
+		goto done;
+
+	if (!ASSERT_OK(settimeo(accept_fd, TIMEOUT_MILLIS), "settimeo"))
+		goto done;
+
+	n = write(client_fd, buf, sizeof(buf));
+	if (!ASSERT_EQ(n, sizeof(buf), "send to server"))
+		goto done;
+
+	n = read(accept_fd, buf, sizeof(buf));
+	ASSERT_EQ(n, sizeof(buf), "recv from server");
+
+done:
+	setns_root();
+	if (listen_fd >= 0)
+		close(listen_fd);
+	if (accept_fd >= 0)
+		close(accept_fd);
+	if (client_fd >= 0)
+		close(client_fd);
+}
+
+static int test_ping(int family, const char *addr)
+{
+	const char *ping = family == AF_INET6 ? "ping6" : "ping";
+
+	SYS("ip netns exec " NS_SRC " %s " PING_ARGS " %s", ping, addr);
+	return 0;
+fail:
+	return -1;
+}
+
+static void test_connectivity(void)
+{
+	test_tcp(AF_INET, IP4_DST, IP4_PORT);
+	test_ping(AF_INET, IP4_DST);
+	test_tcp(AF_INET6, IP6_DST, IP6_PORT);
+	test_ping(AF_INET6, IP6_DST);
+}
+
+static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result)
+{
+	struct test_tc_neigh_fib *skel;
+	int err;
+
+	skel = test_tc_neigh_fib__open();
+	if (!ASSERT_OK_PTR(skel, "test_tc_neigh_fib__open"))
+		return;
+
+	if (!ASSERT_OK(test_tc_neigh_fib__load(skel), "test_tc_neigh_fib__load")) {
+		test_tc_neigh_fib__destroy(skel);
+		return;
+	}
+
+	err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE))
+		goto done;
+
+	err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE))
+		goto done;
+
+	err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE))
+		goto done;
+
+	if (netns_load_bpf())
+		goto done;
+
+	/* bpf_fib_lookup() checks if forwarding is enabled */
+	if (!ASSERT_OK(setns_by_name(NS_FWD), "setns fwd"))
+		goto done;
+
+	err = modify_proc("/proc/sys/net/ipv4/ip_forward", "1");
+	if (!ASSERT_OK(err, "set ipv4.ip_forward"))
+		goto done;
+
+	err = modify_proc("/proc/sys/net/ipv6/conf/all/forwarding", "1");
+	if (!ASSERT_OK(err, "set ipv6.forwarding"))
+		goto done;
+	setns_root();
+
+	test_connectivity();
+done:
+	bpf_program__unpin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
+	bpf_program__unpin(skel->progs.tc_chk, CHK_PROG_PIN_FILE);
+	bpf_program__unpin(skel->progs.tc_dst, DST_PROG_PIN_FILE);
+	test_tc_neigh_fib__destroy(skel);
+	netns_unload_bpf();
+	setns_root();
+	restore_proc();
+}
+
+static void test_tc_redirect_neigh(struct netns_setup_result *setup_result)
+{
+	struct test_tc_neigh *skel;
+	int err;
+
+	skel = test_tc_neigh__open();
+	if (!ASSERT_OK_PTR(skel, "test_tc_neigh__open"))
+		return;
+
+	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+
+	err = test_tc_neigh__load(skel);
+	if (!ASSERT_OK(err, "test_tc_neigh__load")) {
+		test_tc_neigh__destroy(skel);
+		return;
+	}
+
+	err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE))
+		goto done;
+
+	err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE))
+		goto done;
+
+	err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE))
+		goto done;
+
+	if (netns_load_bpf())
+		goto done;
+
+	test_connectivity();
+
+done:
+	bpf_program__unpin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
+	bpf_program__unpin(skel->progs.tc_chk, CHK_PROG_PIN_FILE);
+	bpf_program__unpin(skel->progs.tc_dst, DST_PROG_PIN_FILE);
+	test_tc_neigh__destroy(skel);
+	netns_unload_bpf();
+	setns_root();
+}
+
+static void test_tc_redirect_peer(struct netns_setup_result *setup_result)
+{
+	struct test_tc_peer *skel;
+	int err;
+
+	skel = test_tc_peer__open();
+	if (!ASSERT_OK_PTR(skel, "test_tc_peer__open"))
+		return;
+
+	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+
+	err = test_tc_peer__load(skel);
+	if (!ASSERT_OK(err, "test_tc_peer__load")) {
+		test_tc_peer__destroy(skel);
+		return;
+	}
+
+	err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE))
+		goto done;
+
+	err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE))
+		goto done;
+
+	err = bpf_program__pin(skel->progs.tc_dst, DST_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE))
+		goto done;
+
+	if (netns_load_bpf())
+		goto done;
+
+	test_connectivity();
+
+done:
+	bpf_program__unpin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
+	bpf_program__unpin(skel->progs.tc_chk, CHK_PROG_PIN_FILE);
+	bpf_program__unpin(skel->progs.tc_dst, DST_PROG_PIN_FILE);
+	test_tc_peer__destroy(skel);
+	netns_unload_bpf();
+	setns_root();
+}
+
+void test_tc_redirect(void)
+{
+	struct netns_setup_result setup_result;
+
+	root_netns_fd = open("/proc/self/ns/net", O_RDONLY);
+	if (!ASSERT_GE(root_netns_fd, 0, "open /proc/self/ns/net"))
+		return;
+
+	if (netns_setup_namespaces("add"))
+		goto done;
+
+	if (netns_setup_links_and_routes(&setup_result))
+		goto done;
+
+	if (test__start_subtest("tc_redirect_peer"))
+		test_tc_redirect_peer(&setup_result);
+
+	if (test__start_subtest("tc_redirect_neigh"))
+		test_tc_redirect_neigh(&setup_result);
+
+	if (test__start_subtest("tc_redirect_neigh_fib"))
+		test_tc_redirect_neigh_fib(&setup_result);
+
+done:
+	close(root_netns_fd);
+	netns_setup_namespaces("delete");
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c
index b985ac4e7a81..90f64a85998f 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c
@@ -33,17 +33,8 @@
 				 a.s6_addr32[3] == b.s6_addr32[3])
 #endif
 
-enum {
-	dev_src,
-	dev_dst,
-};
-
-struct bpf_map_def SEC("maps") ifindex_map = {
-	.type		= BPF_MAP_TYPE_ARRAY,
-	.key_size	= sizeof(int),
-	.value_size	= sizeof(int),
-	.max_entries	= 2,
-};
+static volatile const __u32 IFINDEX_SRC;
+static volatile const __u32 IFINDEX_DST;
 
 static __always_inline bool is_remote_ep_v4(struct __sk_buff *skb,
 					    __be32 addr)
@@ -79,14 +70,8 @@ static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb,
 	return v6_equal(ip6h->daddr, addr);
 }
 
-static __always_inline int get_dev_ifindex(int which)
-{
-	int *ifindex = bpf_map_lookup_elem(&ifindex_map, &which);
-
-	return ifindex ? *ifindex : 0;
-}
-
-SEC("chk_egress") int tc_chk(struct __sk_buff *skb)
+SEC("classifier/chk_egress")
+int tc_chk(struct __sk_buff *skb)
 {
 	void *data_end = ctx_ptr(skb->data_end);
 	void *data = ctx_ptr(skb->data);
@@ -98,7 +83,8 @@ SEC("chk_egress") int tc_chk(struct __sk_buff *skb)
 	return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK;
 }
 
-SEC("dst_ingress") int tc_dst(struct __sk_buff *skb)
+SEC("classifier/dst_ingress")
+int tc_dst(struct __sk_buff *skb)
 {
 	__u8 zero[ETH_ALEN * 2];
 	bool redirect = false;
@@ -119,10 +105,11 @@ SEC("dst_ingress") int tc_dst(struct __sk_buff *skb)
 	if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0)
 		return TC_ACT_SHOT;
 
-	return bpf_redirect_neigh(get_dev_ifindex(dev_src), NULL, 0, 0);
+	return bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0);
 }
 
-SEC("src_ingress") int tc_src(struct __sk_buff *skb)
+SEC("classifier/src_ingress")
+int tc_src(struct __sk_buff *skb)
 {
 	__u8 zero[ETH_ALEN * 2];
 	bool redirect = false;
@@ -143,7 +130,7 @@ SEC("src_ingress") int tc_src(struct __sk_buff *skb)
 	if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0)
 		return TC_ACT_SHOT;
 
-	return bpf_redirect_neigh(get_dev_ifindex(dev_dst), NULL, 0, 0);
+	return bpf_redirect_neigh(IFINDEX_DST, NULL, 0, 0);
 }
 
 char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c
index d82ed3457030..f7ab69cf018e 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c
@@ -75,7 +75,8 @@ static __always_inline int fill_fib_params_v6(struct __sk_buff *skb,
 	return 0;
 }
 
-SEC("chk_egress") int tc_chk(struct __sk_buff *skb)
+SEC("classifier/chk_egress")
+int tc_chk(struct __sk_buff *skb)
 {
 	void *data_end = ctx_ptr(skb->data_end);
 	void *data = ctx_ptr(skb->data);
@@ -142,12 +143,14 @@ static __always_inline int tc_redir(struct __sk_buff *skb)
 /* these are identical, but keep them separate for compatibility with the
  * section names expected by test_tc_redirect.sh
  */
-SEC("dst_ingress") int tc_dst(struct __sk_buff *skb)
+SEC("classifier/dst_ingress")
+int tc_dst(struct __sk_buff *skb)
 {
 	return tc_redir(skb);
 }
 
-SEC("src_ingress") int tc_src(struct __sk_buff *skb)
+SEC("classifier/src_ingress")
+int tc_src(struct __sk_buff *skb)
 {
 	return tc_redir(skb);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c
index fc84a7685aa2..72c72950c3bb 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_peer.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c
@@ -8,38 +8,25 @@
 
 #include <bpf/bpf_helpers.h>
 
-enum {
-	dev_src,
-	dev_dst,
-};
+static volatile const __u32 IFINDEX_SRC;
+static volatile const __u32 IFINDEX_DST;
 
-struct bpf_map_def SEC("maps") ifindex_map = {
-	.type		= BPF_MAP_TYPE_ARRAY,
-	.key_size	= sizeof(int),
-	.value_size	= sizeof(int),
-	.max_entries	= 2,
-};
-
-static __always_inline int get_dev_ifindex(int which)
-{
-	int *ifindex = bpf_map_lookup_elem(&ifindex_map, &which);
-
-	return ifindex ? *ifindex : 0;
-}
-
-SEC("chk_egress") int tc_chk(struct __sk_buff *skb)
+SEC("classifier/chk_egress")
+int tc_chk(struct __sk_buff *skb)
 {
 	return TC_ACT_SHOT;
 }
 
-SEC("dst_ingress") int tc_dst(struct __sk_buff *skb)
+SEC("classifier/dst_ingress")
+int tc_dst(struct __sk_buff *skb)
 {
-	return bpf_redirect_peer(get_dev_ifindex(dev_src), 0);
+	return bpf_redirect_peer(IFINDEX_SRC, 0);
 }
 
-SEC("src_ingress") int tc_src(struct __sk_buff *skb)
+SEC("classifier/src_ingress")
+int tc_src(struct __sk_buff *skb)
 {
-	return bpf_redirect_peer(get_dev_ifindex(dev_dst), 0);
+	return bpf_redirect_peer(IFINDEX_DST, 0);
 }
 
 char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tc_redirect.sh b/tools/testing/selftests/bpf/test_tc_redirect.sh
deleted file mode 100755
index 8868aa1ca902..000000000000
--- a/tools/testing/selftests/bpf/test_tc_redirect.sh
+++ /dev/null
@@ -1,216 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# This test sets up 3 netns (src <-> fwd <-> dst). There is no direct veth link
-# between src and dst. The netns fwd has veth links to each src and dst. The
-# client is in src and server in dst. The test installs a TC BPF program to each
-# host facing veth in fwd which calls into i) bpf_redirect_neigh() to perform the
-# neigh addr population and redirect or ii) bpf_redirect_peer() for namespace
-# switch from ingress side; it also installs a checker prog on the egress side
-# to drop unexpected traffic.
-
-if [[ $EUID -ne 0 ]]; then
-	echo "This script must be run as root"
-	echo "FAIL"
-	exit 1
-fi
-
-# check that needed tools are present
-command -v nc >/dev/null 2>&1 || \
-	{ echo >&2 "nc is not available"; exit 1; }
-command -v dd >/dev/null 2>&1 || \
-	{ echo >&2 "dd is not available"; exit 1; }
-command -v timeout >/dev/null 2>&1 || \
-	{ echo >&2 "timeout is not available"; exit 1; }
-command -v ping >/dev/null 2>&1 || \
-	{ echo >&2 "ping is not available"; exit 1; }
-if command -v ping6 >/dev/null 2>&1; then PING6=ping6; else PING6=ping; fi
-command -v perl >/dev/null 2>&1 || \
-	{ echo >&2 "perl is not available"; exit 1; }
-command -v jq >/dev/null 2>&1 || \
-	{ echo >&2 "jq is not available"; exit 1; }
-command -v bpftool >/dev/null 2>&1 || \
-	{ echo >&2 "bpftool is not available"; exit 1; }
-
-readonly GREEN='\033[0;92m'
-readonly RED='\033[0;31m'
-readonly NC='\033[0m' # No Color
-
-readonly PING_ARG="-c 3 -w 10 -q"
-
-readonly TIMEOUT=10
-
-readonly NS_SRC="ns-src-$(mktemp -u XXXXXX)"
-readonly NS_FWD="ns-fwd-$(mktemp -u XXXXXX)"
-readonly NS_DST="ns-dst-$(mktemp -u XXXXXX)"
-
-readonly IP4_SRC="172.16.1.100"
-readonly IP4_DST="172.16.2.100"
-
-readonly IP6_SRC="::1:dead:beef:cafe"
-readonly IP6_DST="::2:dead:beef:cafe"
-
-readonly IP4_SLL="169.254.0.1"
-readonly IP4_DLL="169.254.0.2"
-readonly IP4_NET="169.254.0.0"
-
-netns_cleanup()
-{
-	ip netns del ${NS_SRC}
-	ip netns del ${NS_FWD}
-	ip netns del ${NS_DST}
-}
-
-netns_setup()
-{
-	ip netns add "${NS_SRC}"
-	ip netns add "${NS_FWD}"
-	ip netns add "${NS_DST}"
-
-	ip link add veth_src type veth peer name veth_src_fwd
-	ip link add veth_dst type veth peer name veth_dst_fwd
-
-	ip link set veth_src netns ${NS_SRC}
-	ip link set veth_src_fwd netns ${NS_FWD}
-
-	ip link set veth_dst netns ${NS_DST}
-	ip link set veth_dst_fwd netns ${NS_FWD}
-
-	ip -netns ${NS_SRC} addr add ${IP4_SRC}/32 dev veth_src
-	ip -netns ${NS_DST} addr add ${IP4_DST}/32 dev veth_dst
-
-	# The fwd netns automatically get a v6 LL address / routes, but also
-	# needs v4 one in order to start ARP probing. IP4_NET route is added
-	# to the endpoints so that the ARP processing will reply.
-
-	ip -netns ${NS_FWD} addr add ${IP4_SLL}/32 dev veth_src_fwd
-	ip -netns ${NS_FWD} addr add ${IP4_DLL}/32 dev veth_dst_fwd
-
-	ip -netns ${NS_SRC} addr add ${IP6_SRC}/128 dev veth_src nodad
-	ip -netns ${NS_DST} addr add ${IP6_DST}/128 dev veth_dst nodad
-
-	ip -netns ${NS_SRC} link set dev veth_src up
-	ip -netns ${NS_FWD} link set dev veth_src_fwd up
-
-	ip -netns ${NS_DST} link set dev veth_dst up
-	ip -netns ${NS_FWD} link set dev veth_dst_fwd up
-
-	ip -netns ${NS_SRC} route add ${IP4_DST}/32 dev veth_src scope global
-	ip -netns ${NS_SRC} route add ${IP4_NET}/16 dev veth_src scope global
-	ip -netns ${NS_FWD} route add ${IP4_SRC}/32 dev veth_src_fwd scope global
-
-	ip -netns ${NS_SRC} route add ${IP6_DST}/128 dev veth_src scope global
-	ip -netns ${NS_FWD} route add ${IP6_SRC}/128 dev veth_src_fwd scope global
-
-	ip -netns ${NS_DST} route add ${IP4_SRC}/32 dev veth_dst scope global
-	ip -netns ${NS_DST} route add ${IP4_NET}/16 dev veth_dst scope global
-	ip -netns ${NS_FWD} route add ${IP4_DST}/32 dev veth_dst_fwd scope global
-
-	ip -netns ${NS_DST} route add ${IP6_SRC}/128 dev veth_dst scope global
-	ip -netns ${NS_FWD} route add ${IP6_DST}/128 dev veth_dst_fwd scope global
-
-	fmac_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/address)
-	fmac_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/address)
-
-	ip -netns ${NS_SRC} neigh add ${IP4_DST} dev veth_src lladdr $fmac_src
-	ip -netns ${NS_DST} neigh add ${IP4_SRC} dev veth_dst lladdr $fmac_dst
-
-	ip -netns ${NS_SRC} neigh add ${IP6_DST} dev veth_src lladdr $fmac_src
-	ip -netns ${NS_DST} neigh add ${IP6_SRC} dev veth_dst lladdr $fmac_dst
-}
-
-netns_test_connectivity()
-{
-	set +e
-
-	ip netns exec ${NS_DST} bash -c "nc -4 -l -p 9004 &"
-	ip netns exec ${NS_DST} bash -c "nc -6 -l -p 9006 &"
-
-	TEST="TCPv4 connectivity test"
-	ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP4_DST}/9004"
-	if [ $? -ne 0 ]; then
-		echo -e "${TEST}: ${RED}FAIL${NC}"
-		exit 1
-	fi
-	echo -e "${TEST}: ${GREEN}PASS${NC}"
-
-	TEST="TCPv6 connectivity test"
-	ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP6_DST}/9006"
-	if [ $? -ne 0 ]; then
-		echo -e "${TEST}: ${RED}FAIL${NC}"
-		exit 1
-	fi
-	echo -e "${TEST}: ${GREEN}PASS${NC}"
-
-	TEST="ICMPv4 connectivity test"
-	ip netns exec ${NS_SRC} ping  $PING_ARG ${IP4_DST}
-	if [ $? -ne 0 ]; then
-		echo -e "${TEST}: ${RED}FAIL${NC}"
-		exit 1
-	fi
-	echo -e "${TEST}: ${GREEN}PASS${NC}"
-
-	TEST="ICMPv6 connectivity test"
-	ip netns exec ${NS_SRC} $PING6 $PING_ARG ${IP6_DST}
-	if [ $? -ne 0 ]; then
-		echo -e "${TEST}: ${RED}FAIL${NC}"
-		exit 1
-	fi
-	echo -e "${TEST}: ${GREEN}PASS${NC}"
-
-	set -e
-}
-
-hex_mem_str()
-{
-	perl -e 'print join(" ", unpack("(H2)8", pack("L", @ARGV)))' $1
-}
-
-netns_setup_bpf()
-{
-	local obj=$1
-	local use_forwarding=${2:-0}
-
-	ip netns exec ${NS_FWD} tc qdisc add dev veth_src_fwd clsact
-	ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd ingress bpf da obj $obj sec src_ingress
-	ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd egress  bpf da obj $obj sec chk_egress
-
-	ip netns exec ${NS_FWD} tc qdisc add dev veth_dst_fwd clsact
-	ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd ingress bpf da obj $obj sec dst_ingress
-	ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd egress  bpf da obj $obj sec chk_egress
-
-	if [ "$use_forwarding" -eq "1" ]; then
-		# bpf_fib_lookup() checks if forwarding is enabled
-		ip netns exec ${NS_FWD} sysctl -w net.ipv4.ip_forward=1
-		ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_dst_fwd.forwarding=1
-		ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_src_fwd.forwarding=1
-		return 0
-	fi
-
-	veth_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/ifindex)
-	veth_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/ifindex)
-
-	progs=$(ip netns exec ${NS_FWD} bpftool net --json | jq -r '.[] | .tc | map(.id) | .[]')
-	for prog in $progs; do
-		map=$(bpftool prog show id $prog --json | jq -r '.map_ids | .? | .[]')
-		if [ ! -z "$map" ]; then
-			bpftool map update id $map key hex $(hex_mem_str 0) value hex $(hex_mem_str $veth_src)
-			bpftool map update id $map key hex $(hex_mem_str 1) value hex $(hex_mem_str $veth_dst)
-		fi
-	done
-}
-
-trap netns_cleanup EXIT
-set -e
-
-netns_setup
-netns_setup_bpf test_tc_neigh.o
-netns_test_connectivity
-netns_cleanup
-netns_setup
-netns_setup_bpf test_tc_neigh_fib.o 1
-netns_test_connectivity
-netns_cleanup
-netns_setup
-netns_setup_bpf test_tc_peer.o
-netns_test_connectivity
-- 
cgit v1.2.3


From 0683b53197b55343a166f1507086823030809a19 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sun, 2 May 2021 17:28:31 -0500
Subject: signal: Deliver all of the siginfo perf data in _perf

Don't abuse si_errno and deliver all of the perf data in _perf member
of siginfo_t.

Note: The data field in the perf data structures in a u64 to allow a
pointer to be encoded without needed to implement a 32bit and 64bit
version of the same structure.  There already exists a 32bit and 64bit
versions siginfo_t, and the 32bit version can not include a 64bit
member as it only has 32bit alignment.  So unsigned long is used in
siginfo_t instead of a u64 as unsigned long can encode a pointer on
all architectures linux supports.

v1: https://lkml.kernel.org/r/m11rarqqx2.fsf_-_@fess.ebiederm.org
v2: https://lkml.kernel.org/r/20210503203814.25487-10-ebiederm@xmission.com
v3: https://lkml.kernel.org/r/20210505141101.11519-11-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20210517195748.8880-4-ebiederm@xmission.com
Reviewed-by: Marco Elver <elver@google.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 tools/testing/selftests/perf_events/sigtrap_threads.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c
index 78ddf5e11625..8e83cf91513a 100644
--- a/tools/testing/selftests/perf_events/sigtrap_threads.c
+++ b/tools/testing/selftests/perf_events/sigtrap_threads.c
@@ -43,7 +43,7 @@ static struct {
 	siginfo_t first_siginfo;	/* First observed siginfo_t. */
 } ctx;
 
-/* Unique value to check si_perf is correctly set from perf_event_attr::sig_data. */
+/* Unique value to check si_perf_data is correctly set from perf_event_attr::sig_data. */
 #define TEST_SIG_DATA(addr) (~(unsigned long)(addr))
 
 static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr)
@@ -164,8 +164,8 @@ TEST_F(sigtrap_threads, enable_event)
 	EXPECT_EQ(ctx.signal_count, NUM_THREADS);
 	EXPECT_EQ(ctx.tids_want_signal, 0);
 	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
-	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
-	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+	EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
 
 	/* Check enabled for parent. */
 	ctx.iterate_on = 0;
@@ -183,8 +183,8 @@ TEST_F(sigtrap_threads, modify_and_enable_event)
 	EXPECT_EQ(ctx.signal_count, NUM_THREADS);
 	EXPECT_EQ(ctx.tids_want_signal, 0);
 	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
-	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
-	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+	EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
 
 	/* Check enabled for parent. */
 	ctx.iterate_on = 0;
@@ -203,8 +203,8 @@ TEST_F(sigtrap_threads, signal_stress)
 	EXPECT_EQ(ctx.signal_count, NUM_THREADS * ctx.iterate_on);
 	EXPECT_EQ(ctx.tids_want_signal, 0);
 	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
-	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
-	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+	EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
 }
 
 TEST_HARNESS_MAIN
-- 
cgit v1.2.3


From 5665bc35c1ed917ac8fd06cb651317bb47a65b10 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Thu, 20 May 2021 21:19:30 +1000
Subject: powerpc/64s/syscall: Use pt_regs.trap to distinguish syscall ABI
 difference between sc and scv syscalls

The sc and scv 0 system calls have different ABI conventions, and
ptracers need to know which system call type is being used if they want
to look at the syscall registers.

Document that pt_regs.trap can be used for this, and fix one in-tree user
to work with scv 0 syscalls.

Fixes: 7fa95f9adaee ("powerpc/64s: system call support for scv/rfscv instructions")
Cc: stable@vger.kernel.org # v5.9+
Reported-by: "Dmitry V. Levin" <ldv@altlinux.org>
Suggested-by: "Dmitry V. Levin" <ldv@altlinux.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210520111931.2597127-1-npiggin@gmail.com
---
 tools/testing/selftests/seccomp/seccomp_bpf.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 98c3b647f54d..e3d5c77a8612 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1753,16 +1753,25 @@ TEST_F(TRACE_poke, getpid_runs_normally)
 # define SYSCALL_RET_SET(_regs, _val)				\
 	do {							\
 		typeof(_val) _result = (_val);			\
-		/*						\
-		 * A syscall error is signaled by CR0 SO bit	\
-		 * and the code is stored as a positive value.	\
-		 */						\
-		if (_result < 0) {				\
-			SYSCALL_RET(_regs) = -_result;		\
-			(_regs).ccr |= 0x10000000;		\
-		} else {					\
+		if ((_regs.trap & 0xfff0) == 0x3000) {		\
+			/*					\
+			 * scv 0 system call uses -ve result	\
+			 * for error, so no need to adjust.	\
+			 */					\
 			SYSCALL_RET(_regs) = _result;		\
-			(_regs).ccr &= ~0x10000000;		\
+		} else {					\
+			/*					\
+			 * A syscall error is signaled by the	\
+			 * CR0 SO bit and the code is stored as	\
+			 * a positive value.			\
+			 */					\
+			if (_result < 0) {			\
+				SYSCALL_RET(_regs) = -_result;	\
+				(_regs).ccr |= 0x10000000;	\
+			} else {				\
+				SYSCALL_RET(_regs) = _result;	\
+				(_regs).ccr &= ~0x10000000;	\
+			}					\
 		}						\
 	} while (0)
 # define SYSCALL_RET_SET_ON_PTRACE_EXIT
-- 
cgit v1.2.3


From 8570e75a55430844a8e85e3458e5701556334ffd Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Wed, 19 May 2021 21:33:33 +0000
Subject: selftests: Add .gitignore for nci test suite

Building the nci test suite produces a binary, nci_dev, that git then
tries to track. Add a .gitignore file to tell git to ignore this binary.

Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/nci/.gitignore | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 tools/testing/selftests/nci/.gitignore

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/nci/.gitignore b/tools/testing/selftests/nci/.gitignore
new file mode 100644
index 000000000000..448eeb4590fc
--- /dev/null
+++ b/tools/testing/selftests/nci/.gitignore
@@ -0,0 +1 @@
+/nci_dev
-- 
cgit v1.2.3


From 8f1634b82189e715b0f82f16ce54fab43cfedd8a Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Fri, 14 May 2021 10:05:28 -0700
Subject: selftests/bpf: Convert static to global in tc_redirect progs

Both IFINDEX_SRC and IFINDEX_DST are set from the userspace
and it won't work once bpf merges with bpf-next.

Fixes: 096eccdef0b3 ("selftests/bpf: Rewrite test_tc_redirect.sh as prog_tests/tc_redirect.c")
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210514170528.3750250-1-sdf@google.com
---
 tools/testing/selftests/bpf/progs/test_tc_neigh.c | 4 ++--
 tools/testing/selftests/bpf/progs/test_tc_peer.c  | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c
index 90f64a85998f..0c93d326a663 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c
@@ -33,8 +33,8 @@
 				 a.s6_addr32[3] == b.s6_addr32[3])
 #endif
 
-static volatile const __u32 IFINDEX_SRC;
-static volatile const __u32 IFINDEX_DST;
+volatile const __u32 IFINDEX_SRC;
+volatile const __u32 IFINDEX_DST;
 
 static __always_inline bool is_remote_ep_v4(struct __sk_buff *skb,
 					    __be32 addr)
diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c
index 72c72950c3bb..ef264bced0e6 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_peer.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c
@@ -8,8 +8,8 @@
 
 #include <bpf/bpf_helpers.h>
 
-static volatile const __u32 IFINDEX_SRC;
-static volatile const __u32 IFINDEX_DST;
+volatile const __u32 IFINDEX_SRC;
+volatile const __u32 IFINDEX_DST;
 
 SEC("classifier/chk_egress")
 int tc_chk(struct __sk_buff *skb)
-- 
cgit v1.2.3


From 704e2beba23c45eaa056b1c03b5e1fb221e03f80 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 14 May 2021 11:07:26 -0700
Subject: selftests/bpf: Test ringbuf mmap read-only and read-write
 restrictions

Extend ringbuf selftest to validate read/write and read-only restrictions on
memory mapping consumer/producer/data pages. Ensure no "escalations" from
PROT_READ to PROT_WRITE/PROT_EXEC is allowed. And test that mremap() fails to
expand mmap()'ed area.

Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210514180726.843157-1-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 49 +++++++++++++++++++++++-
 1 file changed, 48 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index de78617f6550..f9a8ae331963 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -86,8 +86,9 @@ void test_ringbuf(void)
 	const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample);
 	pthread_t thread;
 	long bg_ret = -1;
-	int err, cnt;
+	int err, cnt, rb_fd;
 	int page_size = getpagesize();
+	void *mmap_ptr, *tmp_ptr;
 
 	skel = test_ringbuf__open();
 	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
@@ -101,6 +102,52 @@ void test_ringbuf(void)
 	if (CHECK(err != 0, "skel_load", "skeleton load failed\n"))
 		goto cleanup;
 
+	rb_fd = bpf_map__fd(skel->maps.ringbuf);
+	/* good read/write cons_pos */
+	mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0);
+	ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos");
+	tmp_ptr = mremap(mmap_ptr, page_size, 2 * page_size, MREMAP_MAYMOVE);
+	if (!ASSERT_ERR_PTR(tmp_ptr, "rw_extend"))
+		goto cleanup;
+	ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_cons_pos_protect");
+	ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw");
+
+	/* bad writeable prod_pos */
+	mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, page_size);
+	err = -errno;
+	ASSERT_ERR_PTR(mmap_ptr, "wr_prod_pos");
+	ASSERT_EQ(err, -EPERM, "wr_prod_pos_err");
+
+	/* bad writeable data pages */
+	mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, 2 * page_size);
+	err = -errno;
+	ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_one");
+	ASSERT_EQ(err, -EPERM, "wr_data_page_one_err");
+	mmap_ptr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, rb_fd, 3 * page_size);
+	ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_two");
+	mmap_ptr = mmap(NULL, 2 * page_size, PROT_WRITE, MAP_SHARED, rb_fd, 2 * page_size);
+	ASSERT_ERR_PTR(mmap_ptr, "wr_data_page_all");
+
+	/* good read-only pages */
+	mmap_ptr = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED, rb_fd, 0);
+	if (!ASSERT_OK_PTR(mmap_ptr, "ro_prod_pos"))
+		goto cleanup;
+
+	ASSERT_ERR(mprotect(mmap_ptr, 4 * page_size, PROT_WRITE), "write_protect");
+	ASSERT_ERR(mprotect(mmap_ptr, 4 * page_size, PROT_EXEC), "exec_protect");
+	ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 4 * page_size, MREMAP_MAYMOVE), "ro_remap");
+	ASSERT_OK(munmap(mmap_ptr, 4 * page_size), "unmap_ro");
+
+	/* good read-only pages with initial offset */
+	mmap_ptr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, rb_fd, page_size);
+	if (!ASSERT_OK_PTR(mmap_ptr, "ro_prod_pos"))
+		goto cleanup;
+
+	ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_WRITE), "write_protect");
+	ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_protect");
+	ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 3 * page_size, MREMAP_MAYMOVE), "ro_remap");
+	ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_ro");
+
 	/* only trigger BPF program for current process */
 	skel->bss->pid = getpid();
 
-- 
cgit v1.2.3


From 4d1cd3b2c5c1c32826454de3a18c6183238d47ed Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Sat, 22 May 2021 17:41:53 -0700
Subject: tools/testing/selftests/exec: fix link error

Fix the link error by adding '-static':

  gcc -Wall  -Wl,-z,max-page-size=0x1000 -pie load_address.c -o /home/yang/linux/tools/testing/selftests/exec/load_address_4096
  /usr/bin/ld: /tmp/ccopEGun.o: relocation R_AARCH64_ADR_PREL_PG_HI21 against symbol `stderr@@GLIBC_2.17' which may bind externally can not be used when making a shared object; recompile with -fPIC
  /usr/bin/ld: /tmp/ccopEGun.o(.text+0x158): unresolvable R_AARCH64_ADR_PREL_PG_HI21 relocation against symbol `stderr@@GLIBC_2.17'
  /usr/bin/ld: final link failed: bad value
  collect2: error: ld returned 1 exit status
  make: *** [Makefile:25: tools/testing/selftests/exec/load_address_4096] Error 1

Link: https://lkml.kernel.org/r/20210514092422.2367367-1-yangyingliang@huawei.com
Fixes: 206e22f01941 ("tools/testing/selftests: add self-test for verifying load alignment")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Cc: Chris Kennelly <ckennelly@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/exec/Makefile | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index cf69b2fcce59..dd61118df66e 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -28,8 +28,8 @@ $(OUTPUT)/execveat.denatured: $(OUTPUT)/execveat
 	cp $< $@
 	chmod -x $@
 $(OUTPUT)/load_address_4096: load_address.c
-	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -pie $< -o $@
+	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -pie -static $< -o $@
 $(OUTPUT)/load_address_2097152: load_address.c
-	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -pie $< -o $@
+	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -pie -static $< -o $@
 $(OUTPUT)/load_address_16777216: load_address.c
-	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -pie $< -o $@
+	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -pie -static $< -o $@
-- 
cgit v1.2.3


From 3a62fed2fd7b6fea96d720e779cafc30dfb3a22e Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 22 May 2021 15:14:45 +0200
Subject: net/sched: fq_pie: re-factor fix for fq_pie endless loop

the patch that fixed an endless loop in_fq_pie_init() was not considering
that 65535 is a valid class id. The correct bugfix for this infinite loop
is to change 'idx' to become an u32, like Colin proposed in the past [1].

Fix this as follows:
 - restore 65536 as maximum possible values of 'flows_cnt'
 - use u32 'idx' when iterating on 'q->flows'
 - fix the TDC selftest

This reverts commit bb2f930d6dd708469a587dc9ed1efe1ef969c0bf.

[1] https://lore.kernel.org/netdev/20210407163808.499027-1-colin.king@canonical.com/

CC: Colin Ian King <colin.king@canonical.com>
CC: stable@vger.kernel.org
Fixes: bb2f930d6dd7 ("net/sched: fix infinite loop in sch_fq_pie")
Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
index 1cda2e11b3ad..773c5027553d 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
@@ -9,11 +9,11 @@
         "setup": [
             "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
-        "cmdUnderTest": "$TC qdisc add dev $DUMMY root fq_pie flows 65536",
-        "expExitCode": "2",
+        "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_pie flows 65536",
+        "expExitCode": "0",
         "verifyCmd": "$TC qdisc show dev $DUMMY",
-        "matchPattern": "qdisc",
-        "matchCount": "0",
+        "matchPattern": "qdisc fq_pie 1: root refcnt 2 limit 10240p flows 65536",
+        "matchCount": "1",
         "teardown": [
             "$IP link del dev $DUMMY"
         ]
-- 
cgit v1.2.3


From 6fd5fb63820a9a1146aba0bba2fdbc1db4b903e7 Mon Sep 17 00:00:00 2001
From: Jussi Maki <joamaki@gmail.com>
Date: Tue, 25 May 2021 10:29:55 +0000
Subject: selftests/bpf: Add test for l3 use of bpf_redirect_peer

Add a test case for using bpf_skb_change_head() in combination with
bpf_redirect_peer() to redirect a packet from a L3 device to veth and back.

The test uses a BPF program that adds L2 headers to the packet coming
from a L3 device and then calls bpf_redirect_peer() to redirect the packet
to a veth device. The test fails as skb->mac_len is not set properly and
thus the ethernet headers are not properly skb_pull'd in cls_bpf_classify(),
causing tcp_v4_rcv() to point the TCP header into middle of the IP header.

Signed-off-by: Jussi Maki <joamaki@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210525102955.2811090-1-joamaki@gmail.com
---
 .../testing/selftests/bpf/prog_tests/tc_redirect.c | 552 ++++++++++++++-------
 tools/testing/selftests/bpf/progs/test_tc_peer.c   |  31 ++
 2 files changed, 405 insertions(+), 178 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index 95ef9fcd31d8..5703c918812b 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -11,14 +11,17 @@
  */
 
 #define _GNU_SOURCE
-#include <fcntl.h>
+
+#include <arpa/inet.h>
 #include <linux/limits.h>
 #include <linux/sysctl.h>
+#include <linux/if_tun.h>
+#include <linux/if.h>
 #include <sched.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <sys/stat.h>
-#include <sys/types.h>
+#include <sys/mount.h>
 
 #include "test_progs.h"
 #include "network_helpers.h"
@@ -32,18 +35,25 @@
 
 #define IP4_SRC "172.16.1.100"
 #define IP4_DST "172.16.2.100"
+#define IP4_TUN_SRC "172.17.1.100"
+#define IP4_TUN_FWD "172.17.1.200"
 #define IP4_PORT 9004
 
-#define IP6_SRC "::1:dead:beef:cafe"
-#define IP6_DST "::2:dead:beef:cafe"
+#define IP6_SRC "0::1:dead:beef:cafe"
+#define IP6_DST "0::2:dead:beef:cafe"
+#define IP6_TUN_SRC "1::1:dead:beef:cafe"
+#define IP6_TUN_FWD "1::2:dead:beef:cafe"
 #define IP6_PORT 9006
 
 #define IP4_SLL "169.254.0.1"
 #define IP4_DLL "169.254.0.2"
 #define IP4_NET "169.254.0.0"
 
+#define MAC_DST_FWD "00:11:22:33:44:55"
+#define MAC_DST "00:22:33:44:55:66"
+
 #define IFADDR_STR_LEN 18
-#define PING_ARGS "-c 3 -w 10 -q"
+#define PING_ARGS "-i 0.2 -c 3 -w 10 -q"
 
 #define SRC_PROG_PIN_FILE "/sys/fs/bpf/test_tc_src"
 #define DST_PROG_PIN_FILE "/sys/fs/bpf/test_tc_dst"
@@ -51,120 +61,104 @@
 
 #define TIMEOUT_MILLIS 10000
 
-#define MAX_PROC_MODS 128
-#define MAX_PROC_VALUE_LEN 16
-
 #define log_err(MSG, ...) \
 	fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
 		__FILE__, __LINE__, strerror(errno), ##__VA_ARGS__)
 
-struct proc_mod {
-	char path[PATH_MAX];
-	char oldval[MAX_PROC_VALUE_LEN];
-	int oldlen;
-};
-
 static const char * const namespaces[] = {NS_SRC, NS_FWD, NS_DST, NULL};
-static int root_netns_fd = -1;
-static int num_proc_mods;
-static struct proc_mod proc_mods[MAX_PROC_MODS];
 
-/**
- * modify_proc() - Modify entry in /proc
- *
- * Modifies an entry in /proc and saves the original value for later
- * restoration with restore_proc().
- */
-static int modify_proc(const char *path, const char *newval)
+static int write_file(const char *path, const char *newval)
 {
-	struct proc_mod *mod;
 	FILE *f;
 
-	if (num_proc_mods + 1 > MAX_PROC_MODS)
-		return -1;
-
 	f = fopen(path, "r+");
 	if (!f)
 		return -1;
-
-	mod = &proc_mods[num_proc_mods];
-	num_proc_mods++;
-
-	strncpy(mod->path, path, PATH_MAX);
-
-	if (!fread(mod->oldval, 1, MAX_PROC_VALUE_LEN, f)) {
-		log_err("reading from %s failed", path);
-		goto fail;
-	}
-	rewind(f);
 	if (fwrite(newval, strlen(newval), 1, f) != 1) {
 		log_err("writing to %s failed", path);
-		goto fail;
+		fclose(f);
+		return -1;
 	}
-
 	fclose(f);
 	return 0;
-
-fail:
-	fclose(f);
-	num_proc_mods--;
-	return -1;
 }
 
-/**
- * restore_proc() - Restore all /proc modifications
- */
-static void restore_proc(void)
+struct nstoken {
+	int orig_netns_fd;
+};
+
+static int setns_by_fd(int nsfd)
 {
-	int i;
+	int err;
 
-	for (i = 0; i < num_proc_mods; i++) {
-		struct proc_mod *mod = &proc_mods[i];
-		FILE *f;
+	err = setns(nsfd, CLONE_NEWNET);
+	close(nsfd);
 
-		f = fopen(mod->path, "w");
-		if (!f) {
-			log_err("fopen of %s failed", mod->path);
-			continue;
-		}
+	if (!ASSERT_OK(err, "setns"))
+		return err;
 
-		if (fwrite(mod->oldval, mod->oldlen, 1, f) != 1)
-			log_err("fwrite to %s failed", mod->path);
+	/* Switch /sys to the new namespace so that e.g. /sys/class/net
+	 * reflects the devices in the new namespace.
+	 */
+	err = unshare(CLONE_NEWNS);
+	if (!ASSERT_OK(err, "unshare"))
+		return err;
 
-		fclose(f);
-	}
-	num_proc_mods = 0;
+	err = umount2("/sys", MNT_DETACH);
+	if (!ASSERT_OK(err, "umount2 /sys"))
+		return err;
+
+	err = mount("sysfs", "/sys", "sysfs", 0, NULL);
+	if (!ASSERT_OK(err, "mount /sys"))
+		return err;
+
+	err = mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL);
+	if (!ASSERT_OK(err, "mount /sys/fs/bpf"))
+		return err;
+
+	return 0;
 }
 
 /**
- * setns_by_name() - Set networks namespace by name
+ * open_netns() - Switch to specified network namespace by name.
+ *
+ * Returns token with which to restore the original namespace
+ * using close_netns().
  */
-static int setns_by_name(const char *name)
+static struct nstoken *open_netns(const char *name)
 {
 	int nsfd;
 	char nspath[PATH_MAX];
 	int err;
+	struct nstoken *token;
+
+	token = malloc(sizeof(struct nstoken));
+	if (!ASSERT_OK_PTR(token, "malloc token"))
+		return NULL;
+
+	token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY);
+	if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net"))
+		goto fail;
 
 	snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name);
 	nsfd = open(nspath, O_RDONLY | O_CLOEXEC);
-	if (nsfd < 0)
-		return nsfd;
+	if (!ASSERT_GE(nsfd, 0, "open netns fd"))
+		goto fail;
 
-	err = setns(nsfd, CLONE_NEWNET);
-	close(nsfd);
+	err = setns_by_fd(nsfd);
+	if (!ASSERT_OK(err, "setns_by_fd"))
+		goto fail;
 
-	return err;
+	return token;
+fail:
+	free(token);
+	return NULL;
 }
 
-/**
- * setns_root() - Set network namespace to original (root) namespace
- *
- * Not expected to ever fail, so error not returned, but failure logged
- * and test marked as failed.
- */
-static void setns_root(void)
+static void close_netns(struct nstoken *token)
 {
-	ASSERT_OK(setns(root_netns_fd, CLONE_NEWNET), "setns root");
+	ASSERT_OK(setns_by_fd(token->orig_netns_fd), "setns_by_fd");
+	free(token);
 }
 
 static int netns_setup_namespaces(const char *verb)
@@ -237,15 +231,17 @@ static int get_ifindex(const char *name)
 
 static int netns_setup_links_and_routes(struct netns_setup_result *result)
 {
+	struct nstoken *nstoken = NULL;
 	char veth_src_fwd_addr[IFADDR_STR_LEN+1] = {};
-	char veth_dst_fwd_addr[IFADDR_STR_LEN+1] = {};
 
 	SYS("ip link add veth_src type veth peer name veth_src_fwd");
 	SYS("ip link add veth_dst type veth peer name veth_dst_fwd");
+
+	SYS("ip link set veth_dst_fwd address " MAC_DST_FWD);
+	SYS("ip link set veth_dst address " MAC_DST);
+
 	if (get_ifaddr("veth_src_fwd", veth_src_fwd_addr))
 		goto fail;
-	if (get_ifaddr("veth_dst_fwd", veth_dst_fwd_addr))
-		goto fail;
 
 	result->ifindex_veth_src_fwd = get_ifindex("veth_src_fwd");
 	if (result->ifindex_veth_src_fwd < 0)
@@ -260,7 +256,8 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	SYS("ip link set veth_dst netns " NS_DST);
 
 	/** setup in 'src' namespace */
-	if (!ASSERT_OK(setns_by_name(NS_SRC), "setns src"))
+	nstoken = open_netns(NS_SRC);
+	if (!ASSERT_OK_PTR(nstoken, "setns src"))
 		goto fail;
 
 	SYS("ip addr add " IP4_SRC "/32 dev veth_src");
@@ -276,8 +273,11 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	SYS("ip neigh add " IP6_DST " dev veth_src lladdr %s",
 	    veth_src_fwd_addr);
 
+	close_netns(nstoken);
+
 	/** setup in 'fwd' namespace */
-	if (!ASSERT_OK(setns_by_name(NS_FWD), "setns fwd"))
+	nstoken = open_netns(NS_FWD);
+	if (!ASSERT_OK_PTR(nstoken, "setns fwd"))
 		goto fail;
 
 	/* The fwd netns automatically gets a v6 LL address / routes, but also
@@ -294,8 +294,11 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	SYS("ip route add " IP4_DST "/32 dev veth_dst_fwd scope global");
 	SYS("ip route add " IP6_DST "/128 dev veth_dst_fwd scope global");
 
+	close_netns(nstoken);
+
 	/** setup in 'dst' namespace */
-	if (!ASSERT_OK(setns_by_name(NS_DST), "setns dst"))
+	nstoken = open_netns(NS_DST);
+	if (!ASSERT_OK_PTR(nstoken, "setns dst"))
 		goto fail;
 
 	SYS("ip addr add " IP4_DST "/32 dev veth_dst");
@@ -306,23 +309,20 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	SYS("ip route add " IP4_NET "/16 dev veth_dst scope global");
 	SYS("ip route add " IP6_SRC "/128 dev veth_dst scope global");
 
-	SYS("ip neigh add " IP4_SRC " dev veth_dst lladdr %s",
-	    veth_dst_fwd_addr);
-	SYS("ip neigh add " IP6_SRC " dev veth_dst lladdr %s",
-	    veth_dst_fwd_addr);
+	SYS("ip neigh add " IP4_SRC " dev veth_dst lladdr " MAC_DST_FWD);
+	SYS("ip neigh add " IP6_SRC " dev veth_dst lladdr " MAC_DST_FWD);
+
+	close_netns(nstoken);
 
-	setns_root();
 	return 0;
 fail:
-	setns_root();
+	if (nstoken)
+		close_netns(nstoken);
 	return -1;
 }
 
 static int netns_load_bpf(void)
 {
-	if (!ASSERT_OK(setns_by_name(NS_FWD), "setns fwd"))
-		return -1;
-
 	SYS("tc qdisc add dev veth_src_fwd clsact");
 	SYS("tc filter add dev veth_src_fwd ingress bpf da object-pinned "
 	    SRC_PROG_PIN_FILE);
@@ -335,42 +335,29 @@ static int netns_load_bpf(void)
 	SYS("tc filter add dev veth_dst_fwd egress bpf da object-pinned "
 	    CHK_PROG_PIN_FILE);
 
-	setns_root();
-	return -1;
-fail:
-	setns_root();
-	return -1;
-}
-
-static int netns_unload_bpf(void)
-{
-	if (!ASSERT_OK(setns_by_name(NS_FWD), "setns fwd"))
-		goto fail;
-	SYS("tc qdisc delete dev veth_src_fwd clsact");
-	SYS("tc qdisc delete dev veth_dst_fwd clsact");
-
-	setns_root();
 	return 0;
 fail:
-	setns_root();
 	return -1;
 }
 
-
 static void test_tcp(int family, const char *addr, __u16 port)
 {
 	int listen_fd = -1, accept_fd = -1, client_fd = -1;
 	char buf[] = "testing testing";
 	int n;
+	struct nstoken *nstoken;
 
-	if (!ASSERT_OK(setns_by_name(NS_DST), "setns dst"))
+	nstoken = open_netns(NS_DST);
+	if (!ASSERT_OK_PTR(nstoken, "setns dst"))
 		return;
 
 	listen_fd = start_server(family, SOCK_STREAM, addr, port, 0);
 	if (!ASSERT_GE(listen_fd, 0, "listen"))
 		goto done;
 
-	if (!ASSERT_OK(setns_by_name(NS_SRC), "setns src"))
+	close_netns(nstoken);
+	nstoken = open_netns(NS_SRC);
+	if (!ASSERT_OK_PTR(nstoken, "setns src"))
 		goto done;
 
 	client_fd = connect_to_fd(listen_fd, TIMEOUT_MILLIS);
@@ -392,7 +379,8 @@ static void test_tcp(int family, const char *addr, __u16 port)
 	ASSERT_EQ(n, sizeof(buf), "recv from server");
 
 done:
-	setns_root();
+	if (nstoken)
+		close_netns(nstoken);
 	if (listen_fd >= 0)
 		close(listen_fd);
 	if (accept_fd >= 0)
@@ -405,7 +393,7 @@ static int test_ping(int family, const char *addr)
 {
 	const char *ping = family == AF_INET6 ? "ping6" : "ping";
 
-	SYS("ip netns exec " NS_SRC " %s " PING_ARGS " %s", ping, addr);
+	SYS("ip netns exec " NS_SRC " %s " PING_ARGS " %s > /dev/null", ping, addr);
 	return 0;
 fail:
 	return -1;
@@ -419,19 +407,37 @@ static void test_connectivity(void)
 	test_ping(AF_INET6, IP6_DST);
 }
 
+static int set_forwarding(bool enable)
+{
+	int err;
+
+	err = write_file("/proc/sys/net/ipv4/ip_forward", enable ? "1" : "0");
+	if (!ASSERT_OK(err, "set ipv4.ip_forward=0"))
+		return err;
+
+	err = write_file("/proc/sys/net/ipv6/conf/all/forwarding", enable ? "1" : "0");
+	if (!ASSERT_OK(err, "set ipv6.forwarding=0"))
+		return err;
+
+	return 0;
+}
+
 static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result)
 {
-	struct test_tc_neigh_fib *skel;
+	struct nstoken *nstoken = NULL;
+	struct test_tc_neigh_fib *skel = NULL;
 	int err;
 
+	nstoken = open_netns(NS_FWD);
+	if (!ASSERT_OK_PTR(nstoken, "setns fwd"))
+		return;
+
 	skel = test_tc_neigh_fib__open();
 	if (!ASSERT_OK_PTR(skel, "test_tc_neigh_fib__open"))
-		return;
+		goto done;
 
-	if (!ASSERT_OK(test_tc_neigh_fib__load(skel), "test_tc_neigh_fib__load")) {
-		test_tc_neigh_fib__destroy(skel);
-		return;
-	}
+	if (!ASSERT_OK(test_tc_neigh_fib__load(skel), "test_tc_neigh_fib__load"))
+		goto done;
 
 	err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
 	if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE))
@@ -449,46 +455,37 @@ static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result)
 		goto done;
 
 	/* bpf_fib_lookup() checks if forwarding is enabled */
-	if (!ASSERT_OK(setns_by_name(NS_FWD), "setns fwd"))
+	if (!ASSERT_OK(set_forwarding(true), "enable forwarding"))
 		goto done;
 
-	err = modify_proc("/proc/sys/net/ipv4/ip_forward", "1");
-	if (!ASSERT_OK(err, "set ipv4.ip_forward"))
-		goto done;
-
-	err = modify_proc("/proc/sys/net/ipv6/conf/all/forwarding", "1");
-	if (!ASSERT_OK(err, "set ipv6.forwarding"))
-		goto done;
-	setns_root();
-
 	test_connectivity();
+
 done:
-	bpf_program__unpin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
-	bpf_program__unpin(skel->progs.tc_chk, CHK_PROG_PIN_FILE);
-	bpf_program__unpin(skel->progs.tc_dst, DST_PROG_PIN_FILE);
-	test_tc_neigh_fib__destroy(skel);
-	netns_unload_bpf();
-	setns_root();
-	restore_proc();
+	if (skel)
+		test_tc_neigh_fib__destroy(skel);
+	close_netns(nstoken);
 }
 
 static void test_tc_redirect_neigh(struct netns_setup_result *setup_result)
 {
-	struct test_tc_neigh *skel;
+	struct nstoken *nstoken = NULL;
+	struct test_tc_neigh *skel = NULL;
 	int err;
 
+	nstoken = open_netns(NS_FWD);
+	if (!ASSERT_OK_PTR(nstoken, "setns fwd"))
+		return;
+
 	skel = test_tc_neigh__open();
 	if (!ASSERT_OK_PTR(skel, "test_tc_neigh__open"))
-		return;
+		goto done;
 
 	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
 	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
 
 	err = test_tc_neigh__load(skel);
-	if (!ASSERT_OK(err, "test_tc_neigh__load")) {
-		test_tc_neigh__destroy(skel);
-		return;
-	}
+	if (!ASSERT_OK(err, "test_tc_neigh__load"))
+		goto done;
 
 	err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
 	if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE))
@@ -505,34 +502,37 @@ static void test_tc_redirect_neigh(struct netns_setup_result *setup_result)
 	if (netns_load_bpf())
 		goto done;
 
+	if (!ASSERT_OK(set_forwarding(false), "disable forwarding"))
+		goto done;
+
 	test_connectivity();
 
 done:
-	bpf_program__unpin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
-	bpf_program__unpin(skel->progs.tc_chk, CHK_PROG_PIN_FILE);
-	bpf_program__unpin(skel->progs.tc_dst, DST_PROG_PIN_FILE);
-	test_tc_neigh__destroy(skel);
-	netns_unload_bpf();
-	setns_root();
+	if (skel)
+		test_tc_neigh__destroy(skel);
+	close_netns(nstoken);
 }
 
 static void test_tc_redirect_peer(struct netns_setup_result *setup_result)
 {
+	struct nstoken *nstoken;
 	struct test_tc_peer *skel;
 	int err;
 
+	nstoken = open_netns(NS_FWD);
+	if (!ASSERT_OK_PTR(nstoken, "setns fwd"))
+		return;
+
 	skel = test_tc_peer__open();
 	if (!ASSERT_OK_PTR(skel, "test_tc_peer__open"))
-		return;
+		goto done;
 
 	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
 	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
 
 	err = test_tc_peer__load(skel);
-	if (!ASSERT_OK(err, "test_tc_peer__load")) {
-		test_tc_peer__destroy(skel);
-		return;
-	}
+	if (!ASSERT_OK(err, "test_tc_peer__load"))
+		goto done;
 
 	err = bpf_program__pin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
 	if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE))
@@ -549,41 +549,237 @@ static void test_tc_redirect_peer(struct netns_setup_result *setup_result)
 	if (netns_load_bpf())
 		goto done;
 
+	if (!ASSERT_OK(set_forwarding(false), "disable forwarding"))
+		goto done;
+
 	test_connectivity();
 
 done:
-	bpf_program__unpin(skel->progs.tc_src, SRC_PROG_PIN_FILE);
-	bpf_program__unpin(skel->progs.tc_chk, CHK_PROG_PIN_FILE);
-	bpf_program__unpin(skel->progs.tc_dst, DST_PROG_PIN_FILE);
-	test_tc_peer__destroy(skel);
-	netns_unload_bpf();
-	setns_root();
+	if (skel)
+		test_tc_peer__destroy(skel);
+	close_netns(nstoken);
 }
 
-void test_tc_redirect(void)
+static int tun_open(char *name)
+{
+	struct ifreq ifr;
+	int fd, err;
+
+	fd = open("/dev/net/tun", O_RDWR);
+	if (!ASSERT_GE(fd, 0, "open /dev/net/tun"))
+		return -1;
+
+	memset(&ifr, 0, sizeof(ifr));
+
+	ifr.ifr_flags = IFF_TUN | IFF_NO_PI;
+	if (*name)
+		strncpy(ifr.ifr_name, name, IFNAMSIZ);
+
+	err = ioctl(fd, TUNSETIFF, &ifr);
+	if (!ASSERT_OK(err, "ioctl TUNSETIFF"))
+		goto fail;
+
+	SYS("ip link set dev %s up", name);
+
+	return fd;
+fail:
+	close(fd);
+	return -1;
+}
+
+#define MAX(a, b) ((a) > (b) ? (a) : (b))
+enum {
+	SRC_TO_TARGET = 0,
+	TARGET_TO_SRC = 1,
+};
+
+static int tun_relay_loop(int src_fd, int target_fd)
 {
-	struct netns_setup_result setup_result;
+	fd_set rfds, wfds;
 
-	root_netns_fd = open("/proc/self/ns/net", O_RDONLY);
-	if (!ASSERT_GE(root_netns_fd, 0, "open /proc/self/ns/net"))
+	FD_ZERO(&rfds);
+	FD_ZERO(&wfds);
+
+	for (;;) {
+		char buf[1500];
+		int direction, nread, nwrite;
+
+		FD_SET(src_fd, &rfds);
+		FD_SET(target_fd, &rfds);
+
+		if (select(1 + MAX(src_fd, target_fd), &rfds, NULL, NULL, NULL) < 0) {
+			log_err("select failed");
+			return 1;
+		}
+
+		direction = FD_ISSET(src_fd, &rfds) ? SRC_TO_TARGET : TARGET_TO_SRC;
+
+		nread = read(direction == SRC_TO_TARGET ? src_fd : target_fd, buf, sizeof(buf));
+		if (nread < 0) {
+			log_err("read failed");
+			return 1;
+		}
+
+		nwrite = write(direction == SRC_TO_TARGET ? target_fd : src_fd, buf, nread);
+		if (nwrite != nread) {
+			log_err("write failed");
+			return 1;
+		}
+	}
+}
+
+static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
+{
+	struct test_tc_peer *skel = NULL;
+	struct nstoken *nstoken = NULL;
+	int err;
+	int tunnel_pid = -1;
+	int src_fd, target_fd;
+	int ifindex;
+
+	/* Start a L3 TUN/TAP tunnel between the src and dst namespaces.
+	 * This test is using TUN/TAP instead of e.g. IPIP or GRE tunnel as those
+	 * expose the L2 headers encapsulating the IP packet to BPF and hence
+	 * don't have skb in suitable state for this test. Alternative to TUN/TAP
+	 * would be e.g. Wireguard which would appear as a pure L3 device to BPF,
+	 * but that requires much more complicated setup.
+	 */
+	nstoken = open_netns(NS_SRC);
+	if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC))
 		return;
 
-	if (netns_setup_namespaces("add"))
-		goto done;
+	src_fd = tun_open("tun_src");
+	if (!ASSERT_GE(src_fd, 0, "tun_open tun_src"))
+		goto fail;
 
-	if (netns_setup_links_and_routes(&setup_result))
-		goto done;
+	close_netns(nstoken);
+
+	nstoken = open_netns(NS_FWD);
+	if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD))
+		goto fail;
 
-	if (test__start_subtest("tc_redirect_peer"))
-		test_tc_redirect_peer(&setup_result);
+	target_fd = tun_open("tun_fwd");
+	if (!ASSERT_GE(target_fd, 0, "tun_open tun_fwd"))
+		goto fail;
 
-	if (test__start_subtest("tc_redirect_neigh"))
-		test_tc_redirect_neigh(&setup_result);
+	tunnel_pid = fork();
+	if (!ASSERT_GE(tunnel_pid, 0, "fork tun_relay_loop"))
+		goto fail;
 
-	if (test__start_subtest("tc_redirect_neigh_fib"))
-		test_tc_redirect_neigh_fib(&setup_result);
+	if (tunnel_pid == 0)
+		exit(tun_relay_loop(src_fd, target_fd));
 
-done:
-	close(root_netns_fd);
-	netns_setup_namespaces("delete");
+	skel = test_tc_peer__open();
+	if (!ASSERT_OK_PTR(skel, "test_tc_peer__open"))
+		goto fail;
+
+	ifindex = get_ifindex("tun_fwd");
+	if (!ASSERT_GE(ifindex, 0, "get_ifindex tun_fwd"))
+		goto fail;
+
+	skel->rodata->IFINDEX_SRC = ifindex;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+
+	err = test_tc_peer__load(skel);
+	if (!ASSERT_OK(err, "test_tc_peer__load"))
+		goto fail;
+
+	err = bpf_program__pin(skel->progs.tc_src_l3, SRC_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " SRC_PROG_PIN_FILE))
+		goto fail;
+
+	err = bpf_program__pin(skel->progs.tc_dst_l3, DST_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " DST_PROG_PIN_FILE))
+		goto fail;
+
+	err = bpf_program__pin(skel->progs.tc_chk, CHK_PROG_PIN_FILE);
+	if (!ASSERT_OK(err, "pin " CHK_PROG_PIN_FILE))
+		goto fail;
+
+	/* Load "tc_src_l3" to the tun_fwd interface to redirect packets
+	 * towards dst, and "tc_dst" to redirect packets
+	 * and "tc_chk" on veth_dst_fwd to drop non-redirected packets.
+	 */
+	SYS("tc qdisc add dev tun_fwd clsact");
+	SYS("tc filter add dev tun_fwd ingress bpf da object-pinned "
+	    SRC_PROG_PIN_FILE);
+
+	SYS("tc qdisc add dev veth_dst_fwd clsact");
+	SYS("tc filter add dev veth_dst_fwd ingress bpf da object-pinned "
+	    DST_PROG_PIN_FILE);
+	SYS("tc filter add dev veth_dst_fwd egress bpf da object-pinned "
+	    CHK_PROG_PIN_FILE);
+
+	/* Setup route and neigh tables */
+	SYS("ip -netns " NS_SRC " addr add dev tun_src " IP4_TUN_SRC "/24");
+	SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP4_TUN_FWD "/24");
+
+	SYS("ip -netns " NS_SRC " addr add dev tun_src " IP6_TUN_SRC "/64 nodad");
+	SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP6_TUN_FWD "/64 nodad");
+
+	SYS("ip -netns " NS_SRC " route del " IP4_DST "/32 dev veth_src scope global");
+	SYS("ip -netns " NS_SRC " route add " IP4_DST "/32 via " IP4_TUN_FWD
+	    " dev tun_src scope global");
+	SYS("ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev veth_dst scope global");
+	SYS("ip -netns " NS_SRC " route del " IP6_DST "/128 dev veth_src scope global");
+	SYS("ip -netns " NS_SRC " route add " IP6_DST "/128 via " IP6_TUN_FWD
+	    " dev tun_src scope global");
+	SYS("ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev veth_dst scope global");
+
+	SYS("ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD);
+	SYS("ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD);
+
+	if (!ASSERT_OK(set_forwarding(false), "disable forwarding"))
+		goto fail;
+
+	test_connectivity();
+
+fail:
+	if (tunnel_pid > 0) {
+		kill(tunnel_pid, SIGTERM);
+		waitpid(tunnel_pid, NULL, 0);
+	}
+	if (src_fd >= 0)
+		close(src_fd);
+	if (target_fd >= 0)
+		close(target_fd);
+	if (skel)
+		test_tc_peer__destroy(skel);
+	if (nstoken)
+		close_netns(nstoken);
+}
+
+#define RUN_TEST(name)                                                                      \
+	({                                                                                  \
+		struct netns_setup_result setup_result;                                     \
+		if (test__start_subtest(#name))                                             \
+			if (ASSERT_OK(netns_setup_namespaces("add"), "setup namespaces")) { \
+				if (ASSERT_OK(netns_setup_links_and_routes(&setup_result),  \
+					      "setup links and routes"))                    \
+					test_ ## name(&setup_result);                       \
+				netns_setup_namespaces("delete");                           \
+			}                                                                   \
+	})
+
+static void *test_tc_redirect_run_tests(void *arg)
+{
+	RUN_TEST(tc_redirect_peer);
+	RUN_TEST(tc_redirect_peer_l3);
+	RUN_TEST(tc_redirect_neigh);
+	RUN_TEST(tc_redirect_neigh_fib);
+	return NULL;
+}
+
+void test_tc_redirect(void)
+{
+	pthread_t test_thread;
+	int err;
+
+	/* Run the tests in their own thread to isolate the namespace changes
+	 * so they do not affect the environment of other tests.
+	 * (specifically needed because of unshare(CLONE_NEWNS) in open_netns())
+	 */
+	err = pthread_create(&test_thread, NULL, &test_tc_redirect_run_tests, NULL);
+	if (ASSERT_OK(err, "pthread_create"))
+		ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join");
 }
diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c
index ef264bced0e6..fe818cd5f010 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_peer.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c
@@ -5,12 +5,17 @@
 #include <linux/bpf.h>
 #include <linux/stddef.h>
 #include <linux/pkt_cls.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
 
 #include <bpf/bpf_helpers.h>
 
 volatile const __u32 IFINDEX_SRC;
 volatile const __u32 IFINDEX_DST;
 
+static const __u8 src_mac[] = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55};
+static const __u8 dst_mac[] = {0x00, 0x22, 0x33, 0x44, 0x55, 0x66};
+
 SEC("classifier/chk_egress")
 int tc_chk(struct __sk_buff *skb)
 {
@@ -29,4 +34,30 @@ int tc_src(struct __sk_buff *skb)
 	return bpf_redirect_peer(IFINDEX_DST, 0);
 }
 
+SEC("classifier/dst_ingress_l3")
+int tc_dst_l3(struct __sk_buff *skb)
+{
+	return bpf_redirect(IFINDEX_SRC, 0);
+}
+
+SEC("classifier/src_ingress_l3")
+int tc_src_l3(struct __sk_buff *skb)
+{
+	__u16 proto = skb->protocol;
+
+	if (bpf_skb_change_head(skb, ETH_HLEN, 0) != 0)
+		return TC_ACT_SHOT;
+
+	if (bpf_skb_store_bytes(skb, 0, &src_mac, ETH_ALEN, 0) != 0)
+		return TC_ACT_SHOT;
+
+	if (bpf_skb_store_bytes(skb, ETH_ALEN, &dst_mac, ETH_ALEN, 0) != 0)
+		return TC_ACT_SHOT;
+
+	if (bpf_skb_store_bytes(skb, ETH_ALEN + ETH_ALEN, &proto, sizeof(__u16), 0) != 0)
+		return TC_ACT_SHOT;
+
+	return bpf_redirect_peer(IFINDEX_DST, 0);
+}
+
 char __license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 1bad6fd52be4ce12d207e2820ceb0f29ab31fc53 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 4 May 2021 08:58:25 +0000
Subject: bpf, selftests: Adjust few selftest result_unpriv outcomes

Given we don't need to simulate the speculative domain for registers with
immediates anymore since the verifier uses direct imm-based rewrites instead
of having to mask, we can also lift a few cases that were previously rejected.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/verifier/stack_ptr.c       | 2 --
 tools/testing/selftests/bpf/verifier/value_ptr_arith.c | 8 --------
 2 files changed, 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/verifier/stack_ptr.c b/tools/testing/selftests/bpf/verifier/stack_ptr.c
index 07eaa04412ae..8ab94d65f3d5 100644
--- a/tools/testing/selftests/bpf/verifier/stack_ptr.c
+++ b/tools/testing/selftests/bpf/verifier/stack_ptr.c
@@ -295,8 +295,6 @@
 	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
 	BPF_EXIT_INSN(),
 	},
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "invalid write to stack R1 off=0 size=1",
 	.result = ACCEPT,
 	.retval = 42,
 },
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index e5913fd3b903..7ae2859d495c 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -300,8 +300,6 @@
 	},
 	.fixup_map_array_48b = { 3 },
 	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
 	.retval = 1,
 },
 {
@@ -371,8 +369,6 @@
 	},
 	.fixup_map_array_48b = { 3 },
 	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
 	.retval = 1,
 },
 {
@@ -472,8 +468,6 @@
 	},
 	.fixup_map_array_48b = { 3 },
 	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
 	.retval = 1,
 },
 {
@@ -766,8 +760,6 @@
 	},
 	.fixup_map_array_48b = { 3 },
 	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
 	.retval = 1,
 },
 {
-- 
cgit v1.2.3


From b78f4a596692f6805e796a4c13f2d921b8a95166 Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Thu, 10 Jun 2021 18:10:15 -0700
Subject: KVM: selftests: Rename vm_handle_exception

Rename the vm_handle_exception function to a name that indicates more
clearly that it installs something: vm_install_exception_handler.

Reported-by: kernel test robot <oliver.sang@intel.com>
Suggested-by: Marc Zyngier <maz@kernel.org>
Suggested-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210611011020.3420067-2-ricarkol@google.com
---
 tools/testing/selftests/kvm/include/x86_64/processor.h       | 2 +-
 tools/testing/selftests/kvm/lib/x86_64/processor.c           | 4 ++--
 tools/testing/selftests/kvm/x86_64/evmcs_test.c              | 4 ++--
 tools/testing/selftests/kvm/x86_64/kvm_pv_test.c             | 2 +-
 tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c | 8 ++++----
 tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c          | 2 +-
 6 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 0b30b4e15c38..e9f584991332 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -391,7 +391,7 @@ struct ex_regs {
 
 void vm_init_descriptor_tables(struct kvm_vm *vm);
 void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
-void vm_handle_exception(struct kvm_vm *vm, int vector,
+void vm_install_exception_handler(struct kvm_vm *vm, int vector,
 			void (*handler)(struct ex_regs *));
 
 /*
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index efe235044421..257c5c33d04e 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1244,8 +1244,8 @@ void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid)
 	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
 }
 
-void vm_handle_exception(struct kvm_vm *vm, int vector,
-			 void (*handler)(struct ex_regs *))
+void vm_install_exception_handler(struct kvm_vm *vm, int vector,
+			       void (*handler)(struct ex_regs *))
 {
 	vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers);
 
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index 63096cea26c6..0864b2e3fd9e 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -154,8 +154,8 @@ int main(int argc, char *argv[])
 
 	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_handle_exception(vm, UD_VECTOR, guest_ud_handler);
-	vm_handle_exception(vm, NMI_VECTOR, guest_nmi_handler);
+	vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
+	vm_install_exception_handler(vm, NMI_VECTOR, guest_nmi_handler);
 
 	pr_info("Running L1 which uses EVMCS to run L2\n");
 
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
index 732b244d6956..04ed975662c9 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
+++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
@@ -227,7 +227,7 @@ int main(void)
 
 	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+	vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
 
 	enter_guest(vm);
 	kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
index 72c0d0797522..e3e20e8848d0 100644
--- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
+++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
@@ -574,7 +574,7 @@ static void test_msr_filter_allow(void) {
 	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vm, VCPU_ID);
 
-	vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+	vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
 
 	/* Process guest code userspace exits. */
 	run_guest_then_process_rdmsr(vm, MSR_IA32_XSS);
@@ -588,12 +588,12 @@ static void test_msr_filter_allow(void) {
 	run_guest_then_process_wrmsr(vm, MSR_NON_EXISTENT);
 	run_guest_then_process_rdmsr(vm, MSR_NON_EXISTENT);
 
-	vm_handle_exception(vm, UD_VECTOR, guest_ud_handler);
+	vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
 	run_guest(vm);
-	vm_handle_exception(vm, UD_VECTOR, NULL);
+	vm_install_exception_handler(vm, UD_VECTOR, NULL);
 
 	if (process_ucall(vm) != UCALL_DONE) {
-		vm_handle_exception(vm, GP_VECTOR, guest_fep_gp_handler);
+		vm_install_exception_handler(vm, GP_VECTOR, guest_fep_gp_handler);
 
 		/* Process emulated rdmsr and wrmsr instructions. */
 		run_guest_then_process_rdmsr(vm, MSR_IA32_XSS);
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
index 2f964cdc273c..ed27269a01bb 100644
--- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
@@ -462,7 +462,7 @@ int main(int argc, char *argv[])
 
 	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vm, HALTER_VCPU_ID);
-	vm_handle_exception(vm, IPI_VECTOR, guest_ipi_handler);
+	vm_install_exception_handler(vm, IPI_VECTOR, guest_ipi_handler);
 
 	virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA, 0);
 
-- 
cgit v1.2.3


From b7326c01122683b88e273a0cc826cd4c01234470 Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Thu, 10 Jun 2021 18:10:16 -0700
Subject: KVM: selftests: Complete x86_64/sync_regs_test ucall

The guest in sync_regs_test does raw ucalls by directly accessing the
ucall IO port. It makes these ucalls without setting %rdi to a `struct
ucall`, which is what a ucall uses to pass messages.  The issue is that
if the host did a get_ucall (the receiver side), it would try to access
the `struct ucall` at %rdi=0 which would lead to an error ("No mapping
for vm virtual address, gva: 0x0").

This issue is currently benign as there is no get_ucall in
sync_regs_test; however, that will change in the next commit as it
changes the unhandled exception reporting mechanism to use ucalls.  In
that case, every vcpu_run is followed by a get_ucall to check if the
guest is trying to report an unhandled exception.

Fix this in advance by setting %rdi to a UCALL_NONE struct ucall for the
sync_regs_test guest.

Tested with gcc-[8,9,10], and clang-[9,11].

Signed-off-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210611011020.3420067-3-ricarkol@google.com
---
 tools/testing/selftests/kvm/x86_64/sync_regs_test.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index d672f0a473f8..fc03a150278d 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -24,6 +24,10 @@
 
 #define UCALL_PIO_PORT ((uint16_t)0x1000)
 
+struct ucall uc_none = {
+	.cmd = UCALL_NONE,
+};
+
 /*
  * ucall is embedded here to protect against compiler reshuffling registers
  * before calling a function. In this test we only need to get KVM_EXIT_IO
@@ -34,7 +38,8 @@ void guest_code(void)
 	asm volatile("1: in %[port], %%al\n"
 		     "add $0x1, %%rbx\n"
 		     "jmp 1b"
-		     : : [port] "d" (UCALL_PIO_PORT) : "rax", "rbx");
+		     : : [port] "d" (UCALL_PIO_PORT), "D" (&uc_none)
+		     : "rax", "rbx");
 }
 
 static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
-- 
cgit v1.2.3


From 75275d7fbef47805b77e8af81a4d51e2d92db70f Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Thu, 10 Jun 2021 18:10:17 -0700
Subject: KVM: selftests: Introduce UCALL_UNHANDLED for unhandled vector
 reporting

x86, the only arch implementing exception handling, reports unhandled
vectors using port IO at a specific port number. This replicates what
ucall already does.

Introduce a new ucall type, UCALL_UNHANDLED, for guests to report
unhandled exceptions. Then replace the x86 unhandled vector exception
reporting to use it instead of port IO.  This new ucall type will be
used in the next commits by arm64 to report unhandled vectors as well.

Tested: Forcing a page fault in the ./x86_64/xapic_ipi_test
	halter_guest_code() shows this:

	$ ./x86_64/xapic_ipi_test
	...
	  Unexpected vectored event in guest (vector:0xe)

Signed-off-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210611011020.3420067-4-ricarkol@google.com
---
 tools/testing/selftests/kvm/include/kvm_util.h        |  1 +
 .../testing/selftests/kvm/include/x86_64/processor.h  |  2 --
 tools/testing/selftests/kvm/lib/x86_64/processor.c    | 19 ++++++++-----------
 3 files changed, 9 insertions(+), 13 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index fcd8e3855111..beb76d6deaa9 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -349,6 +349,7 @@ enum {
 	UCALL_SYNC,
 	UCALL_ABORT,
 	UCALL_DONE,
+	UCALL_UNHANDLED,
 };
 
 #define UCALL_MAX_ARGS 6
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index e9f584991332..92a62c6999bc 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -53,8 +53,6 @@
 #define CPUID_PKU		(1ul << 3)
 #define CPUID_LA57		(1ul << 16)
 
-#define UNEXPECTED_VECTOR_PORT 0xfff0u
-
 /* General Registers in 64-Bit Mode */
 struct gpr64_regs {
 	u64 rax;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 257c5c33d04e..a217515a9bc2 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1201,7 +1201,7 @@ static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
 
 void kvm_exit_unexpected_vector(uint32_t value)
 {
-	outl(UNEXPECTED_VECTOR_PORT, value);
+	ucall(UCALL_UNHANDLED, 1, value);
 }
 
 void route_exception(struct ex_regs *regs)
@@ -1254,16 +1254,13 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector,
 
 void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
 {
-	if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO
-		&& vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT
-		&& vcpu_state(vm, vcpuid)->io.size == 4) {
-		/* Grab pointer to io data */
-		uint32_t *data = (void *)vcpu_state(vm, vcpuid)
-			+ vcpu_state(vm, vcpuid)->io.data_offset;
-
-		TEST_ASSERT(false,
-			    "Unexpected vectored event in guest (vector:0x%x)",
-			    *data);
+	struct ucall uc;
+
+	if (get_ucall(vm, vcpuid, &uc) == UCALL_UNHANDLED) {
+		uint64_t vector = uc.args[0];
+
+		TEST_FAIL("Unexpected vectored event in guest (vector:0x%lx)",
+			  vector);
 	}
 }
 
-- 
cgit v1.2.3


From 67f709f52bf0b5c19f24d1234163123cbb6af545 Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Thu, 10 Jun 2021 18:10:18 -0700
Subject: KVM: selftests: Move GUEST_ASSERT_EQ to utils header

Move GUEST_ASSERT_EQ to a common header, kvm_util.h, for other
architectures and tests to use. Also modify __GUEST_ASSERT so it can be
reused to implement GUEST_ASSERT_EQ.

Signed-off-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210611011020.3420067-5-ricarkol@google.com
---
 tools/testing/selftests/kvm/include/kvm_util.h     | 22 ++++++++++++----------
 tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c |  9 ---------
 2 files changed, 12 insertions(+), 19 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index beb76d6deaa9..ce49e22843d8 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -368,26 +368,28 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc);
 				ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
 #define GUEST_SYNC(stage)	ucall(UCALL_SYNC, 2, "hello", stage)
 #define GUEST_DONE()		ucall(UCALL_DONE, 0)
-#define __GUEST_ASSERT(_condition, _nargs, _args...) do {	\
-	if (!(_condition))					\
-		ucall(UCALL_ABORT, 2 + _nargs,			\
-			"Failed guest assert: "			\
-			#_condition, __LINE__, _args);		\
+#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...) do {    \
+	if (!(_condition))                                              \
+		ucall(UCALL_ABORT, 2 + _nargs,                          \
+			"Failed guest assert: "                         \
+			_condstr, __LINE__, _args);                     \
 } while (0)
 
 #define GUEST_ASSERT(_condition) \
-	__GUEST_ASSERT((_condition), 0, 0)
+	__GUEST_ASSERT(_condition, #_condition, 0, 0)
 
 #define GUEST_ASSERT_1(_condition, arg1) \
-	__GUEST_ASSERT((_condition), 1, (arg1))
+	__GUEST_ASSERT(_condition, #_condition, 1, (arg1))
 
 #define GUEST_ASSERT_2(_condition, arg1, arg2) \
-	__GUEST_ASSERT((_condition), 2, (arg1), (arg2))
+	__GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2))
 
 #define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \
-	__GUEST_ASSERT((_condition), 3, (arg1), (arg2), (arg3))
+	__GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3))
 
 #define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \
-	__GUEST_ASSERT((_condition), 4, (arg1), (arg2), (arg3), (arg4))
+	__GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4))
+
+#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b)
 
 #endif /* SELFTEST_KVM_UTIL_H */
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
index e357d8e222d4..5a6a662f2e59 100644
--- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
@@ -18,15 +18,6 @@
 #define rounded_rdmsr(x)       ROUND(rdmsr(x))
 #define rounded_host_rdmsr(x)  ROUND(vcpu_get_msr(vm, 0, x))
 
-#define GUEST_ASSERT_EQ(a, b) do {				\
-	__typeof(a) _a = (a);					\
-	__typeof(b) _b = (b);					\
-	if (_a != _b)						\
-                ucall(UCALL_ABORT, 4,				\
-                        "Failed guest assert: "			\
-                        #a " == " #b, __LINE__, _a, _b);	\
-  } while(0)
-
 static void guest_code(void)
 {
 	u64 val = 0;
-- 
cgit v1.2.3


From e3db7579ef355a0b2bfef4448b84d9ac882c8f2c Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Thu, 10 Jun 2021 18:10:19 -0700
Subject: KVM: selftests: Add exception handling support for aarch64

Add the infrastructure needed to enable exception handling in aarch64
selftests. The exception handling defaults to an unhandled-exception
handler which aborts the test, just like x86. These handlers can be
overridden by calling vm_install_exception_handler(vector) or
vm_install_sync_handler(vector, ec). The unhandled exception reporting
from the guest is done using the ucall type introduced in a previous
commit, UCALL_UNHANDLED.

The exception handling code is inspired on kvm-unit-tests.

Signed-off-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210611011020.3420067-6-ricarkol@google.com
---
 tools/testing/selftests/kvm/Makefile               |   2 +-
 .../selftests/kvm/include/aarch64/processor.h      |  63 +++++++++++
 tools/testing/selftests/kvm/lib/aarch64/handlers.S | 126 +++++++++++++++++++++
 .../testing/selftests/kvm/lib/aarch64/processor.c  |  97 ++++++++++++++++
 4 files changed, 287 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/kvm/lib/aarch64/handlers.S

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index daaee1888b12..a77e6063f7e9 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -35,7 +35,7 @@ endif
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
 LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
-LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
+LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S
 LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index b7fa0c8551db..b2b3e9d626cb 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -8,6 +8,7 @@
 #define SELFTEST_KVM_PROCESSOR_H
 
 #include "kvm_util.h"
+#include <linux/stringify.h>
 
 
 #define ARM64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
@@ -18,6 +19,7 @@
 #define MAIR_EL1	3, 0, 10, 2, 0
 #define TTBR0_EL1	3, 0,  2, 0, 0
 #define SCTLR_EL1	3, 0,  1, 0, 0
+#define VBAR_EL1	3, 0, 12, 0, 0
 
 /*
  * Default MAIR
@@ -56,4 +58,65 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini
 void aarch64_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid,
 			      struct kvm_vcpu_init *init, void *guest_code);
 
+struct ex_regs {
+	u64 regs[31];
+	u64 sp;
+	u64 pc;
+	u64 pstate;
+};
+
+#define VECTOR_NUM	16
+
+enum {
+	VECTOR_SYNC_CURRENT_SP0,
+	VECTOR_IRQ_CURRENT_SP0,
+	VECTOR_FIQ_CURRENT_SP0,
+	VECTOR_ERROR_CURRENT_SP0,
+
+	VECTOR_SYNC_CURRENT,
+	VECTOR_IRQ_CURRENT,
+	VECTOR_FIQ_CURRENT,
+	VECTOR_ERROR_CURRENT,
+
+	VECTOR_SYNC_LOWER_64,
+	VECTOR_IRQ_LOWER_64,
+	VECTOR_FIQ_LOWER_64,
+	VECTOR_ERROR_LOWER_64,
+
+	VECTOR_SYNC_LOWER_32,
+	VECTOR_IRQ_LOWER_32,
+	VECTOR_FIQ_LOWER_32,
+	VECTOR_ERROR_LOWER_32,
+};
+
+#define VECTOR_IS_SYNC(v) ((v) == VECTOR_SYNC_CURRENT_SP0 || \
+			   (v) == VECTOR_SYNC_CURRENT     || \
+			   (v) == VECTOR_SYNC_LOWER_64    || \
+			   (v) == VECTOR_SYNC_LOWER_32)
+
+#define ESR_EC_NUM		64
+#define ESR_EC_SHIFT		26
+#define ESR_EC_MASK		(ESR_EC_NUM - 1)
+
+void vm_init_descriptor_tables(struct kvm_vm *vm);
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
+
+typedef void(*handler_fn)(struct ex_regs *);
+void vm_install_exception_handler(struct kvm_vm *vm,
+		int vector, handler_fn handler);
+void vm_install_sync_handler(struct kvm_vm *vm,
+		int vector, int ec, handler_fn handler);
+
+#define write_sysreg(reg, val)						  \
+({									  \
+	u64 __val = (u64)(val);						  \
+	asm volatile("msr " __stringify(reg) ", %x0" : : "rZ" (__val));	  \
+})
+
+#define read_sysreg(reg)						  \
+({	u64 val;							  \
+	asm volatile("mrs %0, "__stringify(reg) : "=r"(val) : : "memory");\
+	val;								  \
+})
+
 #endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/handlers.S b/tools/testing/selftests/kvm/lib/aarch64/handlers.S
new file mode 100644
index 000000000000..0e443eadfac6
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/handlers.S
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+.macro save_registers
+	add	sp, sp, #-16 * 17
+
+	stp	x0, x1, [sp, #16 * 0]
+	stp	x2, x3, [sp, #16 * 1]
+	stp	x4, x5, [sp, #16 * 2]
+	stp	x6, x7, [sp, #16 * 3]
+	stp	x8, x9, [sp, #16 * 4]
+	stp	x10, x11, [sp, #16 * 5]
+	stp	x12, x13, [sp, #16 * 6]
+	stp	x14, x15, [sp, #16 * 7]
+	stp	x16, x17, [sp, #16 * 8]
+	stp	x18, x19, [sp, #16 * 9]
+	stp	x20, x21, [sp, #16 * 10]
+	stp	x22, x23, [sp, #16 * 11]
+	stp	x24, x25, [sp, #16 * 12]
+	stp	x26, x27, [sp, #16 * 13]
+	stp	x28, x29, [sp, #16 * 14]
+
+	/*
+	 * This stores sp_el1 into ex_regs.sp so exception handlers can "look"
+	 * at it. It will _not_ be used to restore the sp on return from the
+	 * exception so handlers can not update it.
+	 */
+	add	x1, sp, #16 * 17
+	stp	x30, x1, [sp, #16 * 15] /* x30, SP */
+
+	mrs	x1, elr_el1
+	mrs	x2, spsr_el1
+	stp	x1, x2, [sp, #16 * 16] /* PC, PSTATE */
+.endm
+
+.macro restore_registers
+	ldp	x1, x2, [sp, #16 * 16] /* PC, PSTATE */
+	msr	elr_el1, x1
+	msr	spsr_el1, x2
+
+	/* sp is not restored */
+	ldp	x30, xzr, [sp, #16 * 15] /* x30, SP */
+
+	ldp	x28, x29, [sp, #16 * 14]
+	ldp	x26, x27, [sp, #16 * 13]
+	ldp	x24, x25, [sp, #16 * 12]
+	ldp	x22, x23, [sp, #16 * 11]
+	ldp	x20, x21, [sp, #16 * 10]
+	ldp	x18, x19, [sp, #16 * 9]
+	ldp	x16, x17, [sp, #16 * 8]
+	ldp	x14, x15, [sp, #16 * 7]
+	ldp	x12, x13, [sp, #16 * 6]
+	ldp	x10, x11, [sp, #16 * 5]
+	ldp	x8, x9, [sp, #16 * 4]
+	ldp	x6, x7, [sp, #16 * 3]
+	ldp	x4, x5, [sp, #16 * 2]
+	ldp	x2, x3, [sp, #16 * 1]
+	ldp	x0, x1, [sp, #16 * 0]
+
+	add	sp, sp, #16 * 17
+
+	eret
+.endm
+
+.pushsection ".entry.text", "ax"
+.balign 0x800
+.global vectors
+vectors:
+.popsection
+
+.set	vector, 0
+
+/*
+ * Build an exception handler for vector and append a jump to it into
+ * vectors (while making sure that it's 0x80 aligned).
+ */
+.macro HANDLER, label
+handler_\label:
+	save_registers
+	mov	x0, sp
+	mov	x1, #vector
+	bl	route_exception
+	restore_registers
+
+.pushsection ".entry.text", "ax"
+.balign 0x80
+	b	handler_\label
+.popsection
+
+.set	vector, vector + 1
+.endm
+
+.macro HANDLER_INVALID
+.pushsection ".entry.text", "ax"
+.balign 0x80
+/* This will abort so no need to save and restore registers. */
+	mov	x0, #vector
+	mov	x1, #0 /* ec */
+	mov	x2, #0 /* valid_ec */
+	b	kvm_exit_unexpected_exception
+.popsection
+
+.set	vector, vector + 1
+.endm
+
+/*
+ * Caution: be sure to not add anything between the declaration of vectors
+ * above and these macro calls that will build the vectors table below it.
+ */
+	HANDLER_INVALID                         // Synchronous EL1t
+	HANDLER_INVALID                         // IRQ EL1t
+	HANDLER_INVALID                         // FIQ EL1t
+	HANDLER_INVALID                         // Error EL1t
+
+	HANDLER	el1h_sync                       // Synchronous EL1h
+	HANDLER	el1h_irq                        // IRQ EL1h
+	HANDLER el1h_fiq                        // FIQ EL1h
+	HANDLER	el1h_error                      // Error EL1h
+
+	HANDLER	el0_sync_64                     // Synchronous 64-bit EL0
+	HANDLER	el0_irq_64                      // IRQ 64-bit EL0
+	HANDLER	el0_fiq_64                      // FIQ 64-bit EL0
+	HANDLER	el0_error_64                    // Error 64-bit EL0
+
+	HANDLER	el0_sync_32                     // Synchronous 32-bit EL0
+	HANDLER	el0_irq_32                      // IRQ 32-bit EL0
+	HANDLER	el0_fiq_32                      // FIQ 32-bit EL0
+	HANDLER	el0_error_32                    // Error 32-bit EL0
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index cee92d477dc0..48b55c93f858 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/compiler.h>
+#include <assert.h>
 
 #include "kvm_util.h"
 #include "../kvm_util_internal.h"
@@ -14,6 +15,8 @@
 #define KVM_GUEST_PAGE_TABLE_MIN_PADDR		0x180000
 #define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN	0xac0000
 
+static vm_vaddr_t exception_handlers;
+
 static uint64_t page_align(struct kvm_vm *vm, uint64_t v)
 {
 	return (v + vm->page_size) & ~(vm->page_size - 1);
@@ -334,6 +337,100 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
 	va_end(ap);
 }
 
+void kvm_exit_unexpected_exception(int vector, uint64_t ec, bool valid_ec)
+{
+	ucall(UCALL_UNHANDLED, 3, vector, ec, valid_ec);
+	while (1)
+		;
+}
+
 void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
 {
+	struct ucall uc;
+
+	if (get_ucall(vm, vcpuid, &uc) != UCALL_UNHANDLED)
+		return;
+
+	if (uc.args[2]) /* valid_ec */ {
+		assert(VECTOR_IS_SYNC(uc.args[0]));
+		TEST_FAIL("Unexpected exception (vector:0x%lx, ec:0x%lx)",
+			  uc.args[0], uc.args[1]);
+	} else {
+		assert(!VECTOR_IS_SYNC(uc.args[0]));
+		TEST_FAIL("Unexpected exception (vector:0x%lx)",
+			  uc.args[0]);
+	}
+}
+
+struct handlers {
+	handler_fn exception_handlers[VECTOR_NUM][ESR_EC_NUM];
+};
+
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	extern char vectors;
+
+	set_reg(vm, vcpuid, ARM64_SYS_REG(VBAR_EL1), (uint64_t)&vectors);
+}
+
+void route_exception(struct ex_regs *regs, int vector)
+{
+	struct handlers *handlers = (struct handlers *)exception_handlers;
+	bool valid_ec;
+	int ec = 0;
+
+	switch (vector) {
+	case VECTOR_SYNC_CURRENT:
+	case VECTOR_SYNC_LOWER_64:
+		ec = (read_sysreg(esr_el1) >> ESR_EC_SHIFT) & ESR_EC_MASK;
+		valid_ec = true;
+		break;
+	case VECTOR_IRQ_CURRENT:
+	case VECTOR_IRQ_LOWER_64:
+	case VECTOR_FIQ_CURRENT:
+	case VECTOR_FIQ_LOWER_64:
+	case VECTOR_ERROR_CURRENT:
+	case VECTOR_ERROR_LOWER_64:
+		ec = 0;
+		valid_ec = false;
+		break;
+	default:
+		valid_ec = false;
+		goto unexpected_exception;
+	}
+
+	if (handlers && handlers->exception_handlers[vector][ec])
+		return handlers->exception_handlers[vector][ec](regs);
+
+unexpected_exception:
+	kvm_exit_unexpected_exception(vector, ec, valid_ec);
+}
+
+void vm_init_descriptor_tables(struct kvm_vm *vm)
+{
+	vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers),
+			vm->page_size, 0, 0);
+
+	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
+}
+
+void vm_install_sync_handler(struct kvm_vm *vm, int vector, int ec,
+			 void (*handler)(struct ex_regs *))
+{
+	struct handlers *handlers = addr_gva2hva(vm, vm->handlers);
+
+	assert(VECTOR_IS_SYNC(vector));
+	assert(vector < VECTOR_NUM);
+	assert(ec < ESR_EC_NUM);
+	handlers->exception_handlers[vector][ec] = handler;
+}
+
+void vm_install_exception_handler(struct kvm_vm *vm, int vector,
+			 void (*handler)(struct ex_regs *))
+{
+	struct handlers *handlers = addr_gva2hva(vm, vm->handlers);
+
+	assert(!VECTOR_IS_SYNC(vector));
+	assert(vector < VECTOR_NUM);
+	handlers->exception_handlers[vector][0] = handler;
 }
-- 
cgit v1.2.3


From 4f05223acaeaabe0a1a188e25fab334735d85c5e Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Thu, 10 Jun 2021 18:10:20 -0700
Subject: KVM: selftests: Add aarch64/debug-exceptions test

Covers fundamental tests for debug exceptions. The guest installs and
handle its debug exceptions itself, without KVM_SET_GUEST_DEBUG.

Signed-off-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210611011020.3420067-7-ricarkol@google.com
---
 tools/testing/selftests/kvm/.gitignore             |   1 +
 tools/testing/selftests/kvm/Makefile               |   1 +
 .../selftests/kvm/aarch64/debug-exceptions.c       | 250 +++++++++++++++++++++
 .../selftests/kvm/include/aarch64/processor.h      |  22 +-
 4 files changed, 268 insertions(+), 6 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/aarch64/debug-exceptions.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 524c857a049c..7e2c66155b06 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
+/aarch64/debug-exceptions
 /aarch64/get-reg-list
 /aarch64/get-reg-list-sve
 /aarch64/vgic_init
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index a77e6063f7e9..36e4ebcc82f0 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -78,6 +78,7 @@ TEST_GEN_PROGS_x86_64 += memslot_perf_test
 TEST_GEN_PROGS_x86_64 += set_memory_region_test
 TEST_GEN_PROGS_x86_64 += steal_time
 
+TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
new file mode 100644
index 000000000000..e5e6c92b60da
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_util.h>
+#include <kvm_util.h>
+#include <processor.h>
+
+#define VCPU_ID 0
+
+#define MDSCR_KDE	(1 << 13)
+#define MDSCR_MDE	(1 << 15)
+#define MDSCR_SS	(1 << 0)
+
+#define DBGBCR_LEN8	(0xff << 5)
+#define DBGBCR_EXEC	(0x0 << 3)
+#define DBGBCR_EL1	(0x1 << 1)
+#define DBGBCR_E	(0x1 << 0)
+
+#define DBGWCR_LEN8	(0xff << 5)
+#define DBGWCR_RD	(0x1 << 3)
+#define DBGWCR_WR	(0x2 << 3)
+#define DBGWCR_EL1	(0x1 << 1)
+#define DBGWCR_E	(0x1 << 0)
+
+#define SPSR_D		(1 << 9)
+#define SPSR_SS		(1 << 21)
+
+extern unsigned char sw_bp, hw_bp, bp_svc, bp_brk, hw_wp, ss_start;
+static volatile uint64_t sw_bp_addr, hw_bp_addr;
+static volatile uint64_t wp_addr, wp_data_addr;
+static volatile uint64_t svc_addr;
+static volatile uint64_t ss_addr[4], ss_idx;
+#define  PC(v)  ((uint64_t)&(v))
+
+static void reset_debug_state(void)
+{
+	asm volatile("msr daifset, #8");
+
+	write_sysreg(osdlr_el1, 0);
+	write_sysreg(oslar_el1, 0);
+	isb();
+
+	write_sysreg(mdscr_el1, 0);
+	/* This test only uses the first bp and wp slot. */
+	write_sysreg(dbgbvr0_el1, 0);
+	write_sysreg(dbgbcr0_el1, 0);
+	write_sysreg(dbgwcr0_el1, 0);
+	write_sysreg(dbgwvr0_el1, 0);
+	isb();
+}
+
+static void install_wp(uint64_t addr)
+{
+	uint32_t wcr;
+	uint32_t mdscr;
+
+	wcr = DBGWCR_LEN8 | DBGWCR_RD | DBGWCR_WR | DBGWCR_EL1 | DBGWCR_E;
+	write_sysreg(dbgwcr0_el1, wcr);
+	write_sysreg(dbgwvr0_el1, addr);
+	isb();
+
+	asm volatile("msr daifclr, #8");
+
+	mdscr = read_sysreg(mdscr_el1) | MDSCR_KDE | MDSCR_MDE;
+	write_sysreg(mdscr_el1, mdscr);
+	isb();
+}
+
+static void install_hw_bp(uint64_t addr)
+{
+	uint32_t bcr;
+	uint32_t mdscr;
+
+	bcr = DBGBCR_LEN8 | DBGBCR_EXEC | DBGBCR_EL1 | DBGBCR_E;
+	write_sysreg(dbgbcr0_el1, bcr);
+	write_sysreg(dbgbvr0_el1, addr);
+	isb();
+
+	asm volatile("msr daifclr, #8");
+
+	mdscr = read_sysreg(mdscr_el1) | MDSCR_KDE | MDSCR_MDE;
+	write_sysreg(mdscr_el1, mdscr);
+	isb();
+}
+
+static void install_ss(void)
+{
+	uint32_t mdscr;
+
+	asm volatile("msr daifclr, #8");
+
+	mdscr = read_sysreg(mdscr_el1) | MDSCR_KDE | MDSCR_SS;
+	write_sysreg(mdscr_el1, mdscr);
+	isb();
+}
+
+static volatile char write_data;
+
+static void guest_code(void)
+{
+	GUEST_SYNC(0);
+
+	/* Software-breakpoint */
+	asm volatile("sw_bp: brk #0");
+	GUEST_ASSERT_EQ(sw_bp_addr, PC(sw_bp));
+
+	GUEST_SYNC(1);
+
+	/* Hardware-breakpoint */
+	reset_debug_state();
+	install_hw_bp(PC(hw_bp));
+	asm volatile("hw_bp: nop");
+	GUEST_ASSERT_EQ(hw_bp_addr, PC(hw_bp));
+
+	GUEST_SYNC(2);
+
+	/* Hardware-breakpoint + svc */
+	reset_debug_state();
+	install_hw_bp(PC(bp_svc));
+	asm volatile("bp_svc: svc #0");
+	GUEST_ASSERT_EQ(hw_bp_addr, PC(bp_svc));
+	GUEST_ASSERT_EQ(svc_addr, PC(bp_svc) + 4);
+
+	GUEST_SYNC(3);
+
+	/* Hardware-breakpoint + software-breakpoint */
+	reset_debug_state();
+	install_hw_bp(PC(bp_brk));
+	asm volatile("bp_brk: brk #0");
+	GUEST_ASSERT_EQ(sw_bp_addr, PC(bp_brk));
+	GUEST_ASSERT_EQ(hw_bp_addr, PC(bp_brk));
+
+	GUEST_SYNC(4);
+
+	/* Watchpoint */
+	reset_debug_state();
+	install_wp(PC(write_data));
+	write_data = 'x';
+	GUEST_ASSERT_EQ(write_data, 'x');
+	GUEST_ASSERT_EQ(wp_data_addr, PC(write_data));
+
+	GUEST_SYNC(5);
+
+	/* Single-step */
+	reset_debug_state();
+	install_ss();
+	ss_idx = 0;
+	asm volatile("ss_start:\n"
+		     "mrs x0, esr_el1\n"
+		     "add x0, x0, #1\n"
+		     "msr daifset, #8\n"
+		     : : : "x0");
+	GUEST_ASSERT_EQ(ss_addr[0], PC(ss_start));
+	GUEST_ASSERT_EQ(ss_addr[1], PC(ss_start) + 4);
+	GUEST_ASSERT_EQ(ss_addr[2], PC(ss_start) + 8);
+
+	GUEST_DONE();
+}
+
+static void guest_sw_bp_handler(struct ex_regs *regs)
+{
+	sw_bp_addr = regs->pc;
+	regs->pc += 4;
+}
+
+static void guest_hw_bp_handler(struct ex_regs *regs)
+{
+	hw_bp_addr = regs->pc;
+	regs->pstate |= SPSR_D;
+}
+
+static void guest_wp_handler(struct ex_regs *regs)
+{
+	wp_data_addr = read_sysreg(far_el1);
+	wp_addr = regs->pc;
+	regs->pstate |= SPSR_D;
+}
+
+static void guest_ss_handler(struct ex_regs *regs)
+{
+	GUEST_ASSERT_1(ss_idx < 4, ss_idx);
+	ss_addr[ss_idx++] = regs->pc;
+	regs->pstate |= SPSR_SS;
+}
+
+static void guest_svc_handler(struct ex_regs *regs)
+{
+	svc_addr = regs->pc;
+}
+
+static int debug_version(struct kvm_vm *vm)
+{
+	uint64_t id_aa64dfr0;
+
+	get_reg(vm, VCPU_ID, ARM64_SYS_REG(ID_AA64DFR0_EL1), &id_aa64dfr0);
+	return id_aa64dfr0 & 0xf;
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vm *vm;
+	struct ucall uc;
+	int stage;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	ucall_init(vm, NULL);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+	if (debug_version(vm) < 6) {
+		print_skip("Armv8 debug architecture not supported.");
+		kvm_vm_free(vm);
+		exit(KSFT_SKIP);
+	}
+
+	vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT,
+				ESR_EC_BRK_INS, guest_sw_bp_handler);
+	vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT,
+				ESR_EC_HW_BP_CURRENT, guest_hw_bp_handler);
+	vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT,
+				ESR_EC_WP_CURRENT, guest_wp_handler);
+	vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT,
+				ESR_EC_SSTEP_CURRENT, guest_ss_handler);
+	vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT,
+				ESR_EC_SVC64, guest_svc_handler);
+
+	for (stage = 0; stage < 7; stage++) {
+		vcpu_run(vm, VCPU_ID);
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_SYNC:
+			TEST_ASSERT(uc.args[1] == stage,
+				"Stage %d: Unexpected sync ucall, got %lx",
+				stage, (ulong)uc.args[1]);
+			break;
+		case UCALL_ABORT:
+			TEST_FAIL("%s at %s:%ld\n\tvalues: %#lx, %#lx",
+				(const char *)uc.args[0],
+				__FILE__, uc.args[1], uc.args[2], uc.args[3]);
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+	}
+
+done:
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index b2b3e9d626cb..27dc5c2e56b9 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -14,12 +14,14 @@
 #define ARM64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
 			   KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x))
 
-#define CPACR_EL1	3, 0,  1, 0, 2
-#define TCR_EL1		3, 0,  2, 0, 2
-#define MAIR_EL1	3, 0, 10, 2, 0
-#define TTBR0_EL1	3, 0,  2, 0, 0
-#define SCTLR_EL1	3, 0,  1, 0, 0
-#define VBAR_EL1	3, 0, 12, 0, 0
+#define CPACR_EL1               3, 0,  1, 0, 2
+#define TCR_EL1                 3, 0,  2, 0, 2
+#define MAIR_EL1                3, 0, 10, 2, 0
+#define TTBR0_EL1               3, 0,  2, 0, 0
+#define SCTLR_EL1               3, 0,  1, 0, 0
+#define VBAR_EL1                3, 0, 12, 0, 0
+
+#define ID_AA64DFR0_EL1         3, 0,  0, 5, 0
 
 /*
  * Default MAIR
@@ -98,6 +100,12 @@ enum {
 #define ESR_EC_SHIFT		26
 #define ESR_EC_MASK		(ESR_EC_NUM - 1)
 
+#define ESR_EC_SVC64		0x15
+#define ESR_EC_HW_BP_CURRENT	0x31
+#define ESR_EC_SSTEP_CURRENT	0x33
+#define ESR_EC_WP_CURRENT	0x35
+#define ESR_EC_BRK_INS		0x3c
+
 void vm_init_descriptor_tables(struct kvm_vm *vm);
 void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
 
@@ -119,4 +127,6 @@ void vm_install_sync_handler(struct kvm_vm *vm,
 	val;								  \
 })
 
+#define isb()	asm volatile("isb" : : : "memory")
+
 #endif /* SELFTEST_KVM_PROCESSOR_H */
-- 
cgit v1.2.3


From 2f9ace5d4557f8ceea07969d6214c320f5e50c0c Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Mon, 31 May 2021 12:33:40 +0200
Subject: KVM: arm64: selftests: get-reg-list: Introduce vcpu configs

We already break register lists into sublists that get selected based
on vcpu config. However, since we only had two configs (vregs and sve),
we didn't structure the code very well to manage them. Restructure it
now to more cleanly handle register sublists that are dependent on the
vcpu config.

This patch has no intended functional change (except for the vcpu
config name now being prepended to all output).

Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210531103344.29325-2-drjones@redhat.com
---
 tools/testing/selftests/kvm/aarch64/get-reg-list.c | 265 ++++++++++++++-------
 1 file changed, 175 insertions(+), 90 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 486932164cf2..7bb09ce20dde 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -37,7 +37,30 @@
 #define reg_list_sve() (false)
 #endif
 
-#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK)
+static struct kvm_reg_list *reg_list;
+static __u64 *blessed_reg, blessed_n;
+
+struct reg_sublist {
+	const char *name;
+	long capability;
+	int feature;
+	bool finalize;
+	__u64 *regs;
+	__u64 regs_n;
+	__u64 *rejects_set;
+	__u64 rejects_set_n;
+};
+
+struct vcpu_config {
+	char *name;
+	struct reg_sublist sublists[];
+};
+
+static struct vcpu_config vregs_config;
+static struct vcpu_config sve_config;
+
+#define for_each_sublist(c, s)							\
+	for ((s) = &(c)->sublists[0]; (s)->regs; ++(s))
 
 #define for_each_reg(i)								\
 	for ((i) = 0; (i) < reg_list->n; ++(i))
@@ -54,12 +77,41 @@
 	for_each_reg_filtered(i)						\
 		if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i]))
 
+static const char *config_name(struct vcpu_config *c)
+{
+	struct reg_sublist *s;
+	int len = 0;
 
-static struct kvm_reg_list *reg_list;
+	if (c->name)
+		return c->name;
 
-static __u64 base_regs[], vregs[], sve_regs[], rejects_set[];
-static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n;
-static __u64 *blessed_reg, blessed_n;
+	for_each_sublist(c, s)
+		len += strlen(s->name) + 1;
+
+	c->name = malloc(len);
+
+	len = 0;
+	for_each_sublist(c, s) {
+		if (!strcmp(s->name, "base"))
+			continue;
+		strcat(c->name + len, s->name);
+		len += strlen(s->name) + 1;
+		c->name[len - 1] = '+';
+	}
+	c->name[len - 1] = '\0';
+
+	return c->name;
+}
+
+static bool has_cap(struct vcpu_config *c, long capability)
+{
+	struct reg_sublist *s;
+
+	for_each_sublist(c, s)
+		if (s->capability == capability)
+			return true;
+	return false;
+}
 
 static bool filter_reg(__u64 reg)
 {
@@ -96,11 +148,13 @@ static const char *str_with_index(const char *template, __u64 index)
 	return (const char *)str;
 }
 
+#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK)
+
 #define CORE_REGS_XX_NR_WORDS	2
 #define CORE_SPSR_XX_NR_WORDS	2
 #define CORE_FPREGS_XX_NR_WORDS	4
 
-static const char *core_id_to_str(__u64 id)
+static const char *core_id_to_str(struct vcpu_config *c, __u64 id)
 {
 	__u64 core_off = id & ~REG_MASK, idx;
 
@@ -111,7 +165,7 @@ static const char *core_id_to_str(__u64 id)
 	case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
 	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
 		idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS;
-		TEST_ASSERT(idx < 31, "Unexpected regs.regs index: %lld", idx);
+		TEST_ASSERT(idx < 31, "%s: Unexpected regs.regs index: %lld", config_name(c), idx);
 		return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx);
 	case KVM_REG_ARM_CORE_REG(regs.sp):
 		return "KVM_REG_ARM_CORE_REG(regs.sp)";
@@ -126,12 +180,12 @@ static const char *core_id_to_str(__u64 id)
 	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
 	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
 		idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS;
-		TEST_ASSERT(idx < KVM_NR_SPSR, "Unexpected spsr index: %lld", idx);
+		TEST_ASSERT(idx < KVM_NR_SPSR, "%s: Unexpected spsr index: %lld", config_name(c), idx);
 		return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx);
 	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
 	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
 		idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS;
-		TEST_ASSERT(idx < 32, "Unexpected fp_regs.vregs index: %lld", idx);
+		TEST_ASSERT(idx < 32, "%s: Unexpected fp_regs.vregs index: %lld", config_name(c), idx);
 		return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx);
 	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
 		return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)";
@@ -139,11 +193,11 @@ static const char *core_id_to_str(__u64 id)
 		return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)";
 	}
 
-	TEST_FAIL("Unknown core reg id: 0x%llx", id);
+	TEST_FAIL("%s: Unknown core reg id: 0x%llx", config_name(c), id);
 	return NULL;
 }
 
-static const char *sve_id_to_str(__u64 id)
+static const char *sve_id_to_str(struct vcpu_config *c, __u64 id)
 {
 	__u64 sve_off, n, i;
 
@@ -153,37 +207,37 @@ static const char *sve_id_to_str(__u64 id)
 	sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1));
 	i = id & (KVM_ARM64_SVE_MAX_SLICES - 1);
 
-	TEST_ASSERT(i == 0, "Currently we don't expect slice > 0, reg id 0x%llx", id);
+	TEST_ASSERT(i == 0, "%s: Currently we don't expect slice > 0, reg id 0x%llx", config_name(c), id);
 
 	switch (sve_off) {
 	case KVM_REG_ARM64_SVE_ZREG_BASE ...
 	     KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1:
 		n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1);
 		TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0),
-			    "Unexpected bits set in SVE ZREG id: 0x%llx", id);
+			    "%s: Unexpected bits set in SVE ZREG id: 0x%llx", config_name(c), id);
 		return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n);
 	case KVM_REG_ARM64_SVE_PREG_BASE ...
 	     KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1:
 		n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1);
 		TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0),
-			    "Unexpected bits set in SVE PREG id: 0x%llx", id);
+			    "%s: Unexpected bits set in SVE PREG id: 0x%llx", config_name(c), id);
 		return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n);
 	case KVM_REG_ARM64_SVE_FFR_BASE:
 		TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0),
-			    "Unexpected bits set in SVE FFR id: 0x%llx", id);
+			    "%s: Unexpected bits set in SVE FFR id: 0x%llx", config_name(c), id);
 		return "KVM_REG_ARM64_SVE_FFR(0)";
 	}
 
 	return NULL;
 }
 
-static void print_reg(__u64 id)
+static void print_reg(struct vcpu_config *c, __u64 id)
 {
 	unsigned op0, op1, crn, crm, op2;
 	const char *reg_size = NULL;
 
 	TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64,
-		    "KVM_REG_ARM64 missing in reg id: 0x%llx", id);
+		    "%s: KVM_REG_ARM64 missing in reg id: 0x%llx", config_name(c), id);
 
 	switch (id & KVM_REG_SIZE_MASK) {
 	case KVM_REG_SIZE_U8:
@@ -214,17 +268,17 @@ static void print_reg(__u64 id)
 		reg_size = "KVM_REG_SIZE_U2048";
 		break;
 	default:
-		TEST_FAIL("Unexpected reg size: 0x%llx in reg id: 0x%llx",
-			  (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id);
+		TEST_FAIL("%s: Unexpected reg size: 0x%llx in reg id: 0x%llx",
+			  config_name(c), (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id);
 	}
 
 	switch (id & KVM_REG_ARM_COPROC_MASK) {
 	case KVM_REG_ARM_CORE:
-		printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(id));
+		printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(c, id));
 		break;
 	case KVM_REG_ARM_DEMUX:
 		TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)),
-			    "Unexpected bits set in DEMUX reg id: 0x%llx", id);
+			    "%s: Unexpected bits set in DEMUX reg id: 0x%llx", config_name(c), id);
 		printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n",
 		       reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK);
 		break;
@@ -235,23 +289,23 @@ static void print_reg(__u64 id)
 		crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT;
 		op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT;
 		TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2),
-			    "Unexpected bits set in SYSREG reg id: 0x%llx", id);
+			    "%s: Unexpected bits set in SYSREG reg id: 0x%llx", config_name(c), id);
 		printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2);
 		break;
 	case KVM_REG_ARM_FW:
 		TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff),
-			    "Unexpected bits set in FW reg id: 0x%llx", id);
+			    "%s: Unexpected bits set in FW reg id: 0x%llx", config_name(c), id);
 		printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff);
 		break;
 	case KVM_REG_ARM64_SVE:
-		if (reg_list_sve())
-			printf("\t%s,\n", sve_id_to_str(id));
+		if (has_cap(c, KVM_CAP_ARM_SVE))
+			printf("\t%s,\n", sve_id_to_str(c, id));
 		else
-			TEST_FAIL("KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", id);
+			TEST_FAIL("%s: KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", config_name(c), id);
 		break;
 	default:
-		TEST_FAIL("Unexpected coproc type: 0x%llx in reg id: 0x%llx",
-			  (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id);
+		TEST_FAIL("%s: Unexpected coproc type: 0x%llx in reg id: 0x%llx",
+			  config_name(c), (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id);
 	}
 }
 
@@ -312,40 +366,51 @@ static void core_reg_fixup(void)
 	reg_list = tmp;
 }
 
-static void prepare_vcpu_init(struct kvm_vcpu_init *init)
+static void prepare_vcpu_init(struct vcpu_config *c, struct kvm_vcpu_init *init)
 {
-	if (reg_list_sve())
-		init->features[0] |= 1 << KVM_ARM_VCPU_SVE;
+	struct reg_sublist *s;
+
+	for_each_sublist(c, s)
+		if (s->capability)
+			init->features[s->feature / 32] |= 1 << (s->feature % 32);
 }
 
-static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid, struct vcpu_config *c)
 {
+	struct reg_sublist *s;
 	int feature;
 
-	if (reg_list_sve()) {
-		feature = KVM_ARM_VCPU_SVE;
-		vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature);
+	for_each_sublist(c, s) {
+		if (s->finalize) {
+			feature = s->feature;
+			vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature);
+		}
 	}
 }
 
-static void check_supported(void)
+static void check_supported(struct vcpu_config *c)
 {
-	if (reg_list_sve() && !kvm_check_cap(KVM_CAP_ARM_SVE)) {
-		fprintf(stderr, "SVE not available, skipping tests\n");
-		exit(KSFT_SKIP);
+	struct reg_sublist *s;
+
+	for_each_sublist(c, s) {
+		if (s->capability && !kvm_check_cap(s->capability)) {
+			fprintf(stderr, "%s: %s not available, skipping tests\n", config_name(c), s->name);
+			exit(KSFT_SKIP);
+		}
 	}
 }
 
 int main(int ac, char **av)
 {
+	struct vcpu_config *c = reg_list_sve() ? &sve_config : &vregs_config;
 	struct kvm_vcpu_init init = { .target = -1, };
-	int new_regs = 0, missing_regs = 0, i;
+	int new_regs = 0, missing_regs = 0, i, n;
 	int failed_get = 0, failed_set = 0, failed_reject = 0;
 	bool print_list = false, print_filtered = false, fixup_core_regs = false;
 	struct kvm_vm *vm;
-	__u64 *vec_regs;
+	struct reg_sublist *s;
 
-	check_supported();
+	check_supported(c);
 
 	for (i = 1; i < ac; ++i) {
 		if (strcmp(av[i], "--core-reg-fixup") == 0)
@@ -359,9 +424,9 @@ int main(int ac, char **av)
 	}
 
 	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
-	prepare_vcpu_init(&init);
+	prepare_vcpu_init(c, &init);
 	aarch64_vcpu_add_default(vm, 0, &init, NULL);
-	finalize_vcpu(vm, 0);
+	finalize_vcpu(vm, 0, c);
 
 	reg_list = vcpu_get_reg_list(vm, 0);
 
@@ -374,7 +439,7 @@ int main(int ac, char **av)
 			__u64 id = reg_list->reg[i];
 			if ((print_list && !filter_reg(id)) ||
 			    (print_filtered && filter_reg(id)))
-				print_reg(id);
+				print_reg(c, id);
 		}
 		putchar('\n');
 		return 0;
@@ -396,50 +461,52 @@ int main(int ac, char **av)
 			.id = reg_list->reg[i],
 			.addr = (__u64)&addr,
 		};
+		bool reject_reg = false;
 		int ret;
 
 		ret = _vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, &reg);
 		if (ret) {
-			puts("Failed to get ");
-			print_reg(reg.id);
+			printf("%s: Failed to get ", config_name(c));
+			print_reg(c, reg.id);
 			putchar('\n');
 			++failed_get;
 		}
 
 		/* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */
-		if (find_reg(rejects_set, rejects_set_n, reg.id)) {
-			ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, &reg);
-			if (ret != -1 || errno != EPERM) {
-				printf("Failed to reject (ret=%d, errno=%d) ", ret, errno);
-				print_reg(reg.id);
-				putchar('\n');
-				++failed_reject;
+		for_each_sublist(c, s) {
+			if (s->rejects_set && find_reg(s->rejects_set, s->rejects_set_n, reg.id)) {
+				reject_reg = true;
+				ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, &reg);
+				if (ret != -1 || errno != EPERM) {
+					printf("%s: Failed to reject (ret=%d, errno=%d) ", config_name(c), ret, errno);
+					print_reg(c, reg.id);
+					putchar('\n');
+					++failed_reject;
+				}
+				break;
 			}
-			continue;
 		}
 
-		ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, &reg);
-		if (ret) {
-			puts("Failed to set ");
-			print_reg(reg.id);
-			putchar('\n');
-			++failed_set;
+		if (!reject_reg) {
+			ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, &reg);
+			if (ret) {
+				printf("%s: Failed to set ", config_name(c));
+				print_reg(c, reg.id);
+				putchar('\n');
+				++failed_set;
+			}
 		}
 	}
 
-	if (reg_list_sve()) {
-		blessed_n = base_regs_n + sve_regs_n;
-		vec_regs = sve_regs;
-	} else {
-		blessed_n = base_regs_n + vregs_n;
-		vec_regs = vregs;
-	}
-
+	for_each_sublist(c, s)
+		blessed_n += s->regs_n;
 	blessed_reg = calloc(blessed_n, sizeof(__u64));
-	for (i = 0; i < base_regs_n; ++i)
-		blessed_reg[i] = base_regs[i];
-	for (i = 0; i < blessed_n - base_regs_n; ++i)
-		blessed_reg[base_regs_n + i] = vec_regs[i];
+
+	n = 0;
+	for_each_sublist(c, s) {
+		for (i = 0; i < s->regs_n; ++i)
+			blessed_reg[n++] = s->regs[i];
+	}
 
 	for_each_new_reg(i)
 		++new_regs;
@@ -448,31 +515,31 @@ int main(int ac, char **av)
 		++missing_regs;
 
 	if (new_regs || missing_regs) {
-		printf("Number blessed registers: %5lld\n", blessed_n);
-		printf("Number registers:         %5lld\n", reg_list->n);
+		printf("%s: Number blessed registers: %5lld\n", config_name(c), blessed_n);
+		printf("%s: Number registers:         %5lld\n", config_name(c), reg_list->n);
 	}
 
 	if (new_regs) {
-		printf("\nThere are %d new registers.\n"
+		printf("\n%s: There are %d new registers.\n"
 		       "Consider adding them to the blessed reg "
-		       "list with the following lines:\n\n", new_regs);
+		       "list with the following lines:\n\n", config_name(c), new_regs);
 		for_each_new_reg(i)
-			print_reg(reg_list->reg[i]);
+			print_reg(c, reg_list->reg[i]);
 		putchar('\n');
 	}
 
 	if (missing_regs) {
-		printf("\nThere are %d missing registers.\n"
-		       "The following lines are missing registers:\n\n", missing_regs);
+		printf("\n%s: There are %d missing registers.\n"
+		       "The following lines are missing registers:\n\n", config_name(c), missing_regs);
 		for_each_missing_reg(i)
-			print_reg(blessed_reg[i]);
+			print_reg(c, blessed_reg[i]);
 		putchar('\n');
 	}
 
 	TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject,
-		    "There are %d missing registers; "
+		    "%s: There are %d missing registers; "
 		    "%d registers failed get; %d registers failed set; %d registers failed reject",
-		    missing_regs, failed_get, failed_set, failed_reject);
+		    config_name(c), missing_regs, failed_get, failed_set, failed_reject);
 
 	return 0;
 }
@@ -761,7 +828,6 @@ static __u64 base_regs[] = {
 	ARM64_SYS_REG(3, 4, 5, 0, 1),	/* IFSR32_EL2 */
 	ARM64_SYS_REG(3, 4, 5, 3, 0),	/* FPEXC32_EL2 */
 };
-static __u64 base_regs_n = ARRAY_SIZE(base_regs);
 
 static __u64 vregs[] = {
 	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]),
@@ -797,7 +863,6 @@ static __u64 vregs[] = {
 	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[30]),
 	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]),
 };
-static __u64 vregs_n = ARRAY_SIZE(vregs);
 
 static __u64 sve_regs[] = {
 	KVM_REG_ARM64_SVE_VLS,
@@ -852,11 +917,31 @@ static __u64 sve_regs[] = {
 	KVM_REG_ARM64_SVE_FFR(0),
 	ARM64_SYS_REG(3, 0, 1, 2, 0),   /* ZCR_EL1 */
 };
-static __u64 sve_regs_n = ARRAY_SIZE(sve_regs);
 
-static __u64 rejects_set[] = {
-#ifdef REG_LIST_SVE
+static __u64 sve_rejects_set[] = {
 	KVM_REG_ARM64_SVE_VLS,
-#endif
 };
-static __u64 rejects_set_n = ARRAY_SIZE(rejects_set);
+
+#define BASE_SUBLIST \
+	{ "base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), }
+#define VREGS_SUBLIST \
+	{ "vregs", .regs = vregs, .regs_n = ARRAY_SIZE(vregs), }
+#define SVE_SUBLIST \
+	{ "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \
+	  .regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \
+	  .rejects_set = sve_rejects_set, .rejects_set_n = ARRAY_SIZE(sve_rejects_set), }
+
+static struct vcpu_config vregs_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	VREGS_SUBLIST,
+	{0},
+	},
+};
+static struct vcpu_config sve_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	SVE_SUBLIST,
+	{0},
+	},
+};
-- 
cgit v1.2.3


From 94e9223c06bece9165a36f0f56bac3552a45cbfc Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Mon, 31 May 2021 12:33:41 +0200
Subject: KVM: arm64: selftests: get-reg-list: Prepare to run multiple configs
 at once

We don't want to have to create a new binary for each vcpu config, so
prepare to run the test for multiple vcpu configs in a single binary.
We do this by factoring out the test from main() and then looping over
configs. When given '--list' we still never print more than a single
reg-list for a single vcpu config though, because it would be confusing
otherwise.

No functional change intended.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210531103344.29325-3-drjones@redhat.com
---
 tools/testing/selftests/kvm/aarch64/get-reg-list.c | 68 ++++++++++++++++------
 1 file changed, 51 insertions(+), 17 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 7bb09ce20dde..14fc8d82e30f 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -56,8 +56,8 @@ struct vcpu_config {
 	struct reg_sublist sublists[];
 };
 
-static struct vcpu_config vregs_config;
-static struct vcpu_config sve_config;
+static struct vcpu_config *vcpu_configs[];
+static int vcpu_configs_n;
 
 #define for_each_sublist(c, s)							\
 	for ((s) = &(c)->sublists[0]; (s)->regs; ++(s))
@@ -400,29 +400,20 @@ static void check_supported(struct vcpu_config *c)
 	}
 }
 
-int main(int ac, char **av)
+static bool print_list;
+static bool print_filtered;
+static bool fixup_core_regs;
+
+static void run_test(struct vcpu_config *c)
 {
-	struct vcpu_config *c = reg_list_sve() ? &sve_config : &vregs_config;
 	struct kvm_vcpu_init init = { .target = -1, };
 	int new_regs = 0, missing_regs = 0, i, n;
 	int failed_get = 0, failed_set = 0, failed_reject = 0;
-	bool print_list = false, print_filtered = false, fixup_core_regs = false;
 	struct kvm_vm *vm;
 	struct reg_sublist *s;
 
 	check_supported(c);
 
-	for (i = 1; i < ac; ++i) {
-		if (strcmp(av[i], "--core-reg-fixup") == 0)
-			fixup_core_regs = true;
-		else if (strcmp(av[i], "--list") == 0)
-			print_list = true;
-		else if (strcmp(av[i], "--list-filtered") == 0)
-			print_filtered = true;
-		else
-			TEST_FAIL("Unknown option: %s\n", av[i]);
-	}
-
 	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
 	prepare_vcpu_init(c, &init);
 	aarch64_vcpu_add_default(vm, 0, &init, NULL);
@@ -442,7 +433,7 @@ int main(int ac, char **av)
 				print_reg(c, id);
 		}
 		putchar('\n');
-		return 0;
+		return;
 	}
 
 	/*
@@ -541,6 +532,44 @@ int main(int ac, char **av)
 		    "%d registers failed get; %d registers failed set; %d registers failed reject",
 		    config_name(c), missing_regs, failed_get, failed_set, failed_reject);
 
+	pr_info("%s: PASS\n", config_name(c));
+	blessed_n = 0;
+	free(blessed_reg);
+	free(reg_list);
+	kvm_vm_free(vm);
+}
+
+int main(int ac, char **av)
+{
+	struct vcpu_config *c, *sel = NULL;
+	int i;
+
+	for (i = 1; i < ac; ++i) {
+		if (strcmp(av[i], "--core-reg-fixup") == 0)
+			fixup_core_regs = true;
+		else if (strcmp(av[i], "--list") == 0)
+			print_list = true;
+		else if (strcmp(av[i], "--list-filtered") == 0)
+			print_filtered = true;
+		else
+			TEST_FAIL("Unknown option: %s\n", av[i]);
+	}
+
+	if (print_list || print_filtered) {
+		/*
+		 * We only want to print the register list of a single config.
+		 * TODO: Add command line support to pick which config.
+		 */
+		sel = vcpu_configs[0];
+	}
+
+	for (i = 0; i < vcpu_configs_n; ++i) {
+		c = vcpu_configs[i];
+		if (sel && c != sel)
+			continue;
+		run_test(c);
+	}
+
 	return 0;
 }
 
@@ -945,3 +974,8 @@ static struct vcpu_config sve_config = {
 	{0},
 	},
 };
+
+static struct vcpu_config *vcpu_configs[] = {
+	reg_list_sve() ? &sve_config : &vregs_config,
+};
+static int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
-- 
cgit v1.2.3


From f3032fcc9cf065733ce9a50057aaeffd6c464e2e Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Mon, 31 May 2021 12:33:42 +0200
Subject: KVM: arm64: selftests: get-reg-list: Provide config selection option

Add a new command line option that allows the user to select a specific
configuration, e.g. --config=sve will give the sve config. Also provide
help text and the --help/-h options.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210531103344.29325-4-drjones@redhat.com
---
 tools/testing/selftests/kvm/aarch64/get-reg-list.c | 56 ++++++++++++++++++++--
 1 file changed, 53 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 14fc8d82e30f..03e041d97a18 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -539,6 +539,52 @@ static void run_test(struct vcpu_config *c)
 	kvm_vm_free(vm);
 }
 
+static void help(void)
+{
+	struct vcpu_config *c;
+	int i;
+
+	printf(
+	"\n"
+	"usage: get-reg-list [--config=<selection>] [--list] [--list-filtered] [--core-reg-fixup]\n\n"
+	" --config=<selection>        Used to select a specific vcpu configuration for the test/listing\n"
+	"                             '<selection>' may be\n");
+
+	for (i = 0; i < vcpu_configs_n; ++i) {
+		c = vcpu_configs[i];
+		printf(
+	"                               '%s'\n", config_name(c));
+	}
+
+	printf(
+	"\n"
+	" --list                      Print the register list rather than test it (requires --config)\n"
+	" --list-filtered             Print registers that would normally be filtered out (requires --config)\n"
+	" --core-reg-fixup            Needed when running on old kernels with broken core reg listings\n"
+	"\n"
+	);
+}
+
+static struct vcpu_config *parse_config(const char *config)
+{
+	struct vcpu_config *c;
+	int i;
+
+	if (config[8] != '=')
+		help(), exit(1);
+
+	for (i = 0; i < vcpu_configs_n; ++i) {
+		c = vcpu_configs[i];
+		if (strcmp(config_name(c), &config[9]) == 0)
+			break;
+	}
+
+	if (i == vcpu_configs_n)
+		help(), exit(1);
+
+	return c;
+}
+
 int main(int ac, char **av)
 {
 	struct vcpu_config *c, *sel = NULL;
@@ -547,20 +593,24 @@ int main(int ac, char **av)
 	for (i = 1; i < ac; ++i) {
 		if (strcmp(av[i], "--core-reg-fixup") == 0)
 			fixup_core_regs = true;
+		else if (strncmp(av[i], "--config", 8) == 0)
+			sel = parse_config(av[i]);
 		else if (strcmp(av[i], "--list") == 0)
 			print_list = true;
 		else if (strcmp(av[i], "--list-filtered") == 0)
 			print_filtered = true;
+		else if (strcmp(av[i], "--help") == 0 || strcmp(av[1], "-h") == 0)
+			help(), exit(0);
 		else
-			TEST_FAIL("Unknown option: %s\n", av[i]);
+			help(), exit(1);
 	}
 
 	if (print_list || print_filtered) {
 		/*
 		 * We only want to print the register list of a single config.
-		 * TODO: Add command line support to pick which config.
 		 */
-		sel = vcpu_configs[0];
+		if (!sel)
+			help(), exit(1);
 	}
 
 	for (i = 0; i < vcpu_configs_n; ++i) {
-- 
cgit v1.2.3


From 32edd2290889d0cd0751dd11853e5a368188066d Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Mon, 31 May 2021 12:33:43 +0200
Subject: KVM: arm64: selftests: get-reg-list: Remove get-reg-list-sve

Now that we can easily run the test for multiple vcpu configs, let's
merge get-reg-list and get-reg-list-sve into just get-reg-list. We
also add a final change to make it more possible to run multiple
tests, which is to fork the test, rather than directly run it. That
allows a test to fail, but subsequent tests can still run.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210531103344.29325-5-drjones@redhat.com
---
 tools/testing/selftests/kvm/.gitignore             |  1 -
 tools/testing/selftests/kvm/Makefile               |  1 -
 .../selftests/kvm/aarch64/get-reg-list-sve.c       |  3 ---
 tools/testing/selftests/kvm/aarch64/get-reg-list.c | 31 +++++++++++++++-------
 4 files changed, 21 insertions(+), 15 deletions(-)
 delete mode 100644 tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 524c857a049c..dd36575b732a 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 /aarch64/get-reg-list
-/aarch64/get-reg-list-sve
 /aarch64/vgic_init
 /s390x/memop
 /s390x/resets
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index daaee1888b12..5c8f3725a7f0 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -79,7 +79,6 @@ TEST_GEN_PROGS_x86_64 += set_memory_region_test
 TEST_GEN_PROGS_x86_64 += steal_time
 
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
-TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c
deleted file mode 100644
index efba76682b4b..000000000000
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c
+++ /dev/null
@@ -1,3 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#define REG_LIST_SVE
-#include "get-reg-list.c"
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 03e041d97a18..b46b8a1fdc0c 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -27,16 +27,13 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
 #include "kvm_util.h"
 #include "test_util.h"
 #include "processor.h"
 
-#ifdef REG_LIST_SVE
-#define reg_list_sve() (true)
-#else
-#define reg_list_sve() (false)
-#endif
-
 static struct kvm_reg_list *reg_list;
 static __u64 *blessed_reg, blessed_n;
 
@@ -588,7 +585,8 @@ static struct vcpu_config *parse_config(const char *config)
 int main(int ac, char **av)
 {
 	struct vcpu_config *c, *sel = NULL;
-	int i;
+	int i, ret = 0;
+	pid_t pid;
 
 	for (i = 1; i < ac; ++i) {
 		if (strcmp(av[i], "--core-reg-fixup") == 0)
@@ -617,10 +615,22 @@ int main(int ac, char **av)
 		c = vcpu_configs[i];
 		if (sel && c != sel)
 			continue;
-		run_test(c);
+
+		pid = fork();
+
+		if (!pid) {
+			run_test(c);
+			exit(0);
+		} else {
+			int wstatus;
+			pid_t wpid = wait(&wstatus);
+			TEST_ASSERT(wpid == pid && WIFEXITED(wstatus), "wait: Unexpected return");
+			if (WEXITSTATUS(wstatus) && WEXITSTATUS(wstatus) != KSFT_SKIP)
+				ret = KSFT_FAIL;
+		}
 	}
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -1026,6 +1036,7 @@ static struct vcpu_config sve_config = {
 };
 
 static struct vcpu_config *vcpu_configs[] = {
-	reg_list_sve() ? &sve_config : &vregs_config,
+	&vregs_config,
+	&sve_config,
 };
 static int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
-- 
cgit v1.2.3


From 313673bad871750c0c829def53d037868af75b67 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Mon, 31 May 2021 12:33:44 +0200
Subject: KVM: arm64: selftests: get-reg-list: Split base and pmu registers

Since KVM commit 11663111cd49 ("KVM: arm64: Hide PMU registers from
userspace when not available") the get-reg-list* tests have been
failing with

  ...
  ... There are 74 missing registers.
  The following lines are missing registers:
  ...

where the 74 missing registers are all PMU registers. This isn't a
bug in KVM that the selftest found, even though it's true that a
KVM userspace that wasn't setting the KVM_ARM_VCPU_PMU_V3 VCPU
flag, but still expecting the PMU registers to be in the reg-list,
would suddenly no longer have their expectations met. In that case,
the expectations were wrong, though, so that KVM userspace needs to
be fixed, and so does this selftest. The fix for this selftest is to
pull the PMU registers out of the base register sublist into their
own sublist and then create new, pmu-enabled vcpu configs which can
be tested.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210531103344.29325-6-drjones@redhat.com
---
 tools/testing/selftests/kvm/aarch64/get-reg-list.c | 39 +++++++++++++++++-----
 1 file changed, 31 insertions(+), 8 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index b46b8a1fdc0c..a16c8f05366c 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -637,7 +637,7 @@ int main(int ac, char **av)
  * The current blessed list was primed with the output of kernel version
  * v4.15 with --core-reg-fixup and then later updated with new registers.
  *
- * The blessed list is up to date with kernel version v5.10-rc5
+ * The blessed list is up to date with kernel version v5.13-rc3
  */
 static __u64 base_regs[] = {
 	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]),
@@ -829,8 +829,6 @@ static __u64 base_regs[] = {
 	ARM64_SYS_REG(3, 0, 5, 2, 0),	/* ESR_EL1 */
 	ARM64_SYS_REG(3, 0, 6, 0, 0),	/* FAR_EL1 */
 	ARM64_SYS_REG(3, 0, 7, 4, 0),	/* PAR_EL1 */
-	ARM64_SYS_REG(3, 0, 9, 14, 1),	/* PMINTENSET_EL1 */
-	ARM64_SYS_REG(3, 0, 9, 14, 2),	/* PMINTENCLR_EL1 */
 	ARM64_SYS_REG(3, 0, 10, 2, 0),	/* MAIR_EL1 */
 	ARM64_SYS_REG(3, 0, 10, 3, 0),	/* AMAIR_EL1 */
 	ARM64_SYS_REG(3, 0, 12, 0, 0),	/* VBAR_EL1 */
@@ -839,6 +837,16 @@ static __u64 base_regs[] = {
 	ARM64_SYS_REG(3, 0, 13, 0, 4),	/* TPIDR_EL1 */
 	ARM64_SYS_REG(3, 0, 14, 1, 0),	/* CNTKCTL_EL1 */
 	ARM64_SYS_REG(3, 2, 0, 0, 0),	/* CSSELR_EL1 */
+	ARM64_SYS_REG(3, 3, 13, 0, 2),	/* TPIDR_EL0 */
+	ARM64_SYS_REG(3, 3, 13, 0, 3),	/* TPIDRRO_EL0 */
+	ARM64_SYS_REG(3, 4, 3, 0, 0),	/* DACR32_EL2 */
+	ARM64_SYS_REG(3, 4, 5, 0, 1),	/* IFSR32_EL2 */
+	ARM64_SYS_REG(3, 4, 5, 3, 0),	/* FPEXC32_EL2 */
+};
+
+static __u64 pmu_regs[] = {
+	ARM64_SYS_REG(3, 0, 9, 14, 1),	/* PMINTENSET_EL1 */
+	ARM64_SYS_REG(3, 0, 9, 14, 2),	/* PMINTENCLR_EL1 */
 	ARM64_SYS_REG(3, 3, 9, 12, 0),	/* PMCR_EL0 */
 	ARM64_SYS_REG(3, 3, 9, 12, 1),	/* PMCNTENSET_EL0 */
 	ARM64_SYS_REG(3, 3, 9, 12, 2),	/* PMCNTENCLR_EL0 */
@@ -848,8 +856,6 @@ static __u64 base_regs[] = {
 	ARM64_SYS_REG(3, 3, 9, 13, 0),	/* PMCCNTR_EL0 */
 	ARM64_SYS_REG(3, 3, 9, 14, 0),	/* PMUSERENR_EL0 */
 	ARM64_SYS_REG(3, 3, 9, 14, 3),	/* PMOVSSET_EL0 */
-	ARM64_SYS_REG(3, 3, 13, 0, 2),	/* TPIDR_EL0 */
-	ARM64_SYS_REG(3, 3, 13, 0, 3),	/* TPIDRRO_EL0 */
 	ARM64_SYS_REG(3, 3, 14, 8, 0),
 	ARM64_SYS_REG(3, 3, 14, 8, 1),
 	ARM64_SYS_REG(3, 3, 14, 8, 2),
@@ -913,9 +919,6 @@ static __u64 base_regs[] = {
 	ARM64_SYS_REG(3, 3, 14, 15, 5),
 	ARM64_SYS_REG(3, 3, 14, 15, 6),
 	ARM64_SYS_REG(3, 3, 14, 15, 7),	/* PMCCFILTR_EL0 */
-	ARM64_SYS_REG(3, 4, 3, 0, 0),	/* DACR32_EL2 */
-	ARM64_SYS_REG(3, 4, 5, 0, 1),	/* IFSR32_EL2 */
-	ARM64_SYS_REG(3, 4, 5, 3, 0),	/* FPEXC32_EL2 */
 };
 
 static __u64 vregs[] = {
@@ -1015,6 +1018,8 @@ static __u64 sve_rejects_set[] = {
 	{ "base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), }
 #define VREGS_SUBLIST \
 	{ "vregs", .regs = vregs, .regs_n = ARRAY_SIZE(vregs), }
+#define PMU_SUBLIST \
+	{ "pmu", .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), }
 #define SVE_SUBLIST \
 	{ "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \
 	  .regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \
@@ -1027,6 +1032,14 @@ static struct vcpu_config vregs_config = {
 	{0},
 	},
 };
+static struct vcpu_config vregs_pmu_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	VREGS_SUBLIST,
+	PMU_SUBLIST,
+	{0},
+	},
+};
 static struct vcpu_config sve_config = {
 	.sublists = {
 	BASE_SUBLIST,
@@ -1034,9 +1047,19 @@ static struct vcpu_config sve_config = {
 	{0},
 	},
 };
+static struct vcpu_config sve_pmu_config = {
+	.sublists = {
+	BASE_SUBLIST,
+	SVE_SUBLIST,
+	PMU_SUBLIST,
+	{0},
+	},
+};
 
 static struct vcpu_config *vcpu_configs[] = {
 	&vregs_config,
+	&vregs_pmu_config,
 	&sve_config,
+	&sve_pmu_config,
 };
 static int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
-- 
cgit v1.2.3