From 9683e5775c75097c46bd24e65411b16ac6c6cbb3 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 4 May 2021 16:49:10 -0700
Subject: libbpf: Add NULL check to add_dummy_ksym_var

Avoids a segv if btf isn't present. Seen on the call path
__bpf_object__open calling bpf_object__collect_externs.

Fixes: 5bd022ec01f0 (libbpf: Support extern kernel function)
Suggested-by: Stanislav Fomichev <sdf@google.com>
Suggested-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210504234910.976501-1-irogers@google.com
---
 tools/lib/bpf/libbpf.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e2a3cf437814..c41d9b2b59ac 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3216,6 +3216,9 @@ static int add_dummy_ksym_var(struct btf *btf)
 	const struct btf_var_secinfo *vs;
 	const struct btf_type *sec;
 
+	if (!btf)
+		return 0;
+
 	sec_btf_id = btf__find_by_name_kind(btf, KSYMS_SEC,
 					    BTF_KIND_DATASEC);
 	if (sec_btf_id < 0)
-- 
cgit v1.2.3


From 67e7ec0bd4535fc6e6d3f5d174f80e10a8a80c6e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@kernel.org>
Date: Sat, 8 May 2021 12:22:12 -0300
Subject: libbpf: Provide GELF_ST_VISIBILITY() define for older libelf

Where that macro isn't available.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/YJaspEh0qZr4LYOc@kernel.org
---
 tools/lib/bpf/libbpf_internal.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index ee426226928f..acbcf6c7bdf8 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -41,6 +41,11 @@
 #define ELF_C_READ_MMAP ELF_C_READ
 #endif
 
+/* Older libelf all end up in this expression, for both 32 and 64 bit */
+#ifndef GELF_ST_VISIBILITY
+#define GELF_ST_VISIBILITY(o) ((o) & 0x03)
+#endif
+
 #define BTF_INFO_ENC(kind, kind_flag, vlen) \
 	((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
 #define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type)
-- 
cgit v1.2.3


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')

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 c6de37dd5e48b883db032aa4dc0547a4858b9f20 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 21 Apr 2021 11:58:48 -0700
Subject: tools build: Fix quiet cmd indentation

The tools quiet cmd output has mismatched indentation (and extra space
character between cmd name and target name) compared to the rest of
kbuild out:

  HOSTCC  scripts/insert-sys-cert
  LD       /srv/code/tools/objtool/arch/x86/objtool-in.o
  LD       /srv/code/tools/objtool/libsubcmd-in.o
  AR       /srv/code/tools/objtool/libsubcmd.a
  HOSTLD  scripts/genksyms/genksyms
  CC      scripts/mod/empty.o
  HOSTCC  scripts/mod/mk_elfconfig
  CC      scripts/mod/devicetable-offsets.s
  MKELF   scripts/mod/elfconfig.h
  HOSTCC  scripts/mod/modpost.o
  HOSTCC  scripts/mod/file2alias.o
  HOSTCC  scripts/mod/sumversion.o
  LD       /srv/code/tools/objtool/objtool-in.o
  LINK     /srv/code/tools/objtool/objtool
  HOSTLD  scripts/mod/modpost
  CC      kernel/bounds.s

Adjust to match the rest of kbuild.

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 tools/build/Makefile.build     | 22 +++++++++++-----------
 tools/scripts/Makefile.include | 30 +++++++++++++++---------------
 2 files changed, 26 insertions(+), 26 deletions(-)

(limited to 'tools')

diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index cd72016c3cfa..715092fc6a23 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -51,39 +51,39 @@ subdir-obj-y :=
 build-file := $(dir)/Build
 -include $(build-file)
 
-quiet_cmd_flex  = FLEX     $@
-quiet_cmd_bison = BISON    $@
+quiet_cmd_flex  = FLEX    $@
+quiet_cmd_bison = BISON   $@
 
 # Create directory unless it exists
-quiet_cmd_mkdir = MKDIR    $(dir $@)
+quiet_cmd_mkdir = MKDIR   $(dir $@)
       cmd_mkdir = mkdir -p $(dir $@)
      rule_mkdir = $(if $(wildcard $(dir $@)),,@$(call echo-cmd,mkdir) $(cmd_mkdir))
 
 # Compile command
-quiet_cmd_cc_o_c = CC       $@
+quiet_cmd_cc_o_c = CC      $@
       cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $<
 
-quiet_cmd_host_cc_o_c = HOSTCC   $@
+quiet_cmd_host_cc_o_c = HOSTCC  $@
       cmd_host_cc_o_c = $(HOSTCC) $(host_c_flags) -c -o $@ $<
 
-quiet_cmd_cxx_o_c = CXX      $@
+quiet_cmd_cxx_o_c = CXX     $@
       cmd_cxx_o_c = $(CXX) $(cxx_flags) -c -o $@ $<
 
-quiet_cmd_cpp_i_c = CPP      $@
+quiet_cmd_cpp_i_c = CPP     $@
       cmd_cpp_i_c = $(CC) $(c_flags) -E -o $@ $<
 
-quiet_cmd_cc_s_c = AS       $@
+quiet_cmd_cc_s_c = AS      $@
       cmd_cc_s_c = $(CC) $(c_flags) -S -o $@ $<
 
-quiet_cmd_gen = GEN      $@
+quiet_cmd_gen = GEN     $@
 
 # Link agregate command
 # If there's nothing to link, create empty $@ object.
-quiet_cmd_ld_multi = LD       $@
+quiet_cmd_ld_multi = LD      $@
       cmd_ld_multi = $(if $(strip $(obj-y)),\
                      $(LD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(AR) rcs $@)
 
-quiet_cmd_host_ld_multi = HOSTLD   $@
+quiet_cmd_host_ld_multi = HOSTLD  $@
       cmd_host_ld_multi = $(if $(strip $(obj-y)),\
                           $(HOSTLD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(HOSTAR) rcs $@)
 
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index f9271f3ea912..071312f5eb92 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -131,29 +131,29 @@ QUIET_SUBDIR1  =
 
 ifneq ($(silent),1)
   ifneq ($(V),1)
-	QUIET_CC       = @echo '  CC       '$@;
-	QUIET_CC_FPIC  = @echo '  CC FPIC  '$@;
-	QUIET_CLANG    = @echo '  CLANG    '$@;
-	QUIET_AR       = @echo '  AR       '$@;
-	QUIET_LINK     = @echo '  LINK     '$@;
-	QUIET_MKDIR    = @echo '  MKDIR    '$@;
-	QUIET_GEN      = @echo '  GEN      '$@;
+	QUIET_CC       = @echo '  CC      '$@;
+	QUIET_CC_FPIC  = @echo '  CC FPIC '$@;
+	QUIET_CLANG    = @echo '  CLANG   '$@;
+	QUIET_AR       = @echo '  AR      '$@;
+	QUIET_LINK     = @echo '  LINK    '$@;
+	QUIET_MKDIR    = @echo '  MKDIR   '$@;
+	QUIET_GEN      = @echo '  GEN     '$@;
 	QUIET_SUBDIR0  = +@subdir=
 	QUIET_SUBDIR1  = ;$(NO_SUBDIR) \
-			  echo '  SUBDIR   '$$subdir; \
+			  echo '  SUBDIR  '$$subdir; \
 			 $(MAKE) $(PRINT_DIR) -C $$subdir
-	QUIET_FLEX     = @echo '  FLEX     '$@;
-	QUIET_BISON    = @echo '  BISON    '$@;
-	QUIET_GENSKEL  = @echo '  GEN-SKEL '$@;
+	QUIET_FLEX     = @echo '  FLEX    '$@;
+	QUIET_BISON    = @echo '  BISON   '$@;
+	QUIET_GENSKEL  = @echo '  GENSKEL '$@;
 
 	descend = \
-		+@echo	       '  DESCEND  '$(1); \
+		+@echo	       '  DESCEND '$(1); \
 		mkdir -p $(OUTPUT)$(1) && \
 		$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
 
-	QUIET_CLEAN    = @printf '  CLEAN    %s\n' $1;
-	QUIET_INSTALL  = @printf '  INSTALL  %s\n' $1;
-	QUIET_UNINST   = @printf '  UNINST   %s\n' $1;
+	QUIET_CLEAN    = @printf '  CLEAN   %s\n' $1;
+	QUIET_INSTALL  = @printf '  INSTALL %s\n' $1;
+	QUIET_UNINST   = @printf '  UNINST  %s\n' $1;
   endif
 endif
 
-- 
cgit v1.2.3


From c67d734975a25ba7b6e8f820c13e0d8eb4a2a77c Mon Sep 17 00:00:00 2001
From: Milian Wolff <milian.wolff@kdab.com>
Date: Thu, 29 Apr 2021 20:57:59 +0200
Subject: perf buildid-list: Initialize zstd_data

Fixes segmentation fault when trying to obtain buildid list (e.g. via
perf-archive) from a zstd-compressed `perf.data` file:

```
    $ perf record -z ls
    ...
    [ perf record: Captured and wrote 0,010 MB perf.data, compressed (original 0,001 MB, ratio is 2,190) ]
    $ memcheck perf buildid-list
    ...
    ==57268== Invalid read of size 4
    ==57268==    at 0x5260D88: ZSTD_decompressStream (in /usr/lib/libzstd.so.1.4.9)
    ==57268==    by 0x4BB51B: zstd_decompress_stream (zstd.c:100)
    ==57268==    by 0x425C6C: perf_session__process_compressed_event (session.c:73)
    ==57268==    by 0x427450: perf_session__process_user_event (session.c:1631)
    ==57268==    by 0x42A609: reader__process_events (session.c:2207)
    ==57268==    by 0x42A609: __perf_session__process_events (session.c:2264)
    ==57268==    by 0x42A609: perf_session__process_events (session.c:2297)
    ==57268==    by 0x343A62: perf_session__list_build_ids (builtin-buildid-list.c:88)
    ==57268==    by 0x343A62: cmd_buildid_list (builtin-buildid-list.c:120)
    ==57268==    by 0x3C7732: run_builtin (perf.c:313)
    ==57268==    by 0x331157: handle_internal_command (perf.c:365)
    ==57268==    by 0x331157: run_argv (perf.c:409)
    ==57268==    by 0x331157: main (perf.c:539)
    ==57268==  Address 0x7470 is not stack'd, malloc'd or (recently) free'd
```

Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Link: http://lore.kernel.org/lkml/20210429185759.59870-1-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-buildid-list.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 87f5b1a4a7fa..833405c27dae 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -80,6 +80,9 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
 	if (!perf_header__has_feat(&session->header, HEADER_BUILD_ID))
 		with_hits = true;
 
+	if (zstd_init(&(session->zstd_data), 0) < 0)
+		pr_warning("Decompression initialization failed. Reported data may be incomplete.\n");
+
 	/*
 	 * in pipe-mode, the only way to get the buildids is to parse
 	 * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
-- 
cgit v1.2.3


From 3c91e8efaf4838e4c8e465656e9707b5de26f3db Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 12 May 2021 12:35:07 -0300
Subject: tools arch kvm: Sync kvm headers with the kernel sources

To pick up the changes from:

  70f094f4f01dc4d6 ("KVM: nVMX: Properly pad 'struct kvm_vmx_nested_state_hdr'")

That don't entail changes in tooling.

This silences these tools/perf build warnings:

  Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/kvm.h' differs from latest version at 'arch/x86/include/uapi/asm/kvm.h'
  diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/kvm.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 5a3022c8af82..0662f644aad9 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -437,6 +437,8 @@ struct kvm_vmx_nested_state_hdr {
 		__u16 flags;
 	} smm;
 
+	__u16 pad;
+
 	__u32 flags;
 	__u64 preemption_timer_deadline;
 };
-- 
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>
---
 arch/m68k/kernel/signal.c                           |  3 ++-
 arch/x86/kernel/signal_compat.c                     |  6 ++++--
 fs/signalfd.c                                       |  3 ++-
 include/linux/compat.h                              |  5 ++++-
 include/uapi/asm-generic/siginfo.h                  |  8 ++++++--
 include/uapi/linux/perf_event.h                     |  2 +-
 include/uapi/linux/signalfd.h                       |  4 ++--
 kernel/signal.c                                     | 21 +++++++++++++--------
 .../testing/selftests/perf_events/sigtrap_threads.c | 14 +++++++-------
 9 files changed, 41 insertions(+), 25 deletions(-)

(limited to 'tools')

diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index a4b7ee1df211..8f215e79e70e 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -623,7 +623,8 @@ static inline void siginfo_build_tests(void)
 	BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x12);
 
 	/* _sigfault._perf */
-	BUILD_BUG_ON(offsetof(siginfo_t, si_perf) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x14);
 
 	/* _sigpoll */
 	BUILD_BUG_ON(offsetof(siginfo_t, si_band)   != 0x0c);
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index a9fcabd8a5e5..06743ec054d2 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -141,8 +141,10 @@ static inline void signal_compat_build_tests(void)
 	BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20);
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14);
 
-	BUILD_BUG_ON(offsetof(siginfo_t, si_perf) != 0x18);
-	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x18);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x20);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_data) != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_type) != 0x14);
 
 	CHECK_CSI_OFFSET(_sigpoll);
 	CHECK_CSI_SIZE  (_sigpoll, 2*sizeof(int));
diff --git a/fs/signalfd.c b/fs/signalfd.c
index e87e59581653..373df2f12415 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -134,7 +134,8 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 		break;
 	case SIL_PERF_EVENT:
 		new.ssi_addr = (long) kinfo->si_addr;
-		new.ssi_perf = kinfo->si_perf;
+		new.ssi_perf_type = kinfo->si_perf_type;
+		new.ssi_perf_data = kinfo->si_perf_data;
 		break;
 	case SIL_CHLD:
 		new.ssi_pid    = kinfo->si_pid;
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 6af7bef15e94..a27fffaae121 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -236,7 +236,10 @@ typedef struct compat_siginfo {
 					u32 _pkey;
 				} _addr_pkey;
 				/* used when si_code=TRAP_PERF */
-				compat_ulong_t _perf;
+				struct {
+					compat_ulong_t _data;
+					u32 _type;
+				} _perf;
 			};
 		} _sigfault;
 
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index e663bf117b46..5a3c221f4c9d 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -91,7 +91,10 @@ union __sifields {
 				__u32 _pkey;
 			} _addr_pkey;
 			/* used when si_code=TRAP_PERF */
-			unsigned long _perf;
+			struct {
+				unsigned long _data;
+				__u32 _type;
+			} _perf;
 		};
 	} _sigfault;
 
@@ -154,7 +157,8 @@ typedef struct siginfo {
 #define si_lower	_sifields._sigfault._addr_bnd._lower
 #define si_upper	_sifields._sigfault._addr_bnd._upper
 #define si_pkey		_sifields._sigfault._addr_pkey._pkey
-#define si_perf		_sifields._sigfault._perf
+#define si_perf_data	_sifields._sigfault._perf._data
+#define si_perf_type	_sifields._sigfault._perf._type
 #define si_band		_sifields._sigpoll._band
 #define si_fd		_sifields._sigpoll._fd
 #define si_call_addr	_sifields._sigsys._call_addr
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index e54e639248c8..7b14753b3d38 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -464,7 +464,7 @@ struct perf_event_attr {
 
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
-	 * siginfo_t::si_perf, e.g. to permit user to identify the event.
+	 * siginfo_t::si_perf_data, e.g. to permit user to identify the event.
 	 */
 	__u64	sig_data;
 };
diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h
index 7e333042c7e3..e78dddf433fc 100644
--- a/include/uapi/linux/signalfd.h
+++ b/include/uapi/linux/signalfd.h
@@ -39,8 +39,8 @@ struct signalfd_siginfo {
 	__s32 ssi_syscall;
 	__u64 ssi_call_addr;
 	__u32 ssi_arch;
-	__u32 __pad3;
-	__u64 ssi_perf;
+	__u32 ssi_perf_type;
+	__u64 ssi_perf_data;
 
 	/*
 	 * Pad strcture to 128 bytes. Remember to update the
diff --git a/kernel/signal.c b/kernel/signal.c
index 3a18d13c39b2..dca53515ae3f 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1768,11 +1768,13 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data)
 	struct kernel_siginfo info;
 
 	clear_siginfo(&info);
-	info.si_signo = SIGTRAP;
-	info.si_errno = type;
-	info.si_code  = TRAP_PERF;
-	info.si_addr  = addr;
-	info.si_perf  = sig_data;
+	info.si_signo     = SIGTRAP;
+	info.si_errno     = 0;
+	info.si_code      = TRAP_PERF;
+	info.si_addr      = addr;
+	info.si_perf_data = sig_data;
+	info.si_perf_type = type;
+
 	return force_sig_info(&info);
 }
 
@@ -3356,7 +3358,8 @@ void copy_siginfo_to_external32(struct compat_siginfo *to,
 		break;
 	case SIL_PERF_EVENT:
 		to->si_addr = ptr_to_compat(from->si_addr);
-		to->si_perf = from->si_perf;
+		to->si_perf_data = from->si_perf_data;
+		to->si_perf_type = from->si_perf_type;
 		break;
 	case SIL_CHLD:
 		to->si_pid = from->si_pid;
@@ -3432,7 +3435,8 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to,
 		break;
 	case SIL_PERF_EVENT:
 		to->si_addr = compat_ptr(from->si_addr);
-		to->si_perf = from->si_perf;
+		to->si_perf_data = from->si_perf_data;
+		to->si_perf_type = from->si_perf_type;
 		break;
 	case SIL_CHLD:
 		to->si_pid    = from->si_pid;
@@ -4615,7 +4619,8 @@ static inline void siginfo_buildtime_checks(void)
 	CHECK_OFFSET(si_lower);
 	CHECK_OFFSET(si_upper);
 	CHECK_OFFSET(si_pkey);
-	CHECK_OFFSET(si_perf);
+	CHECK_OFFSET(si_perf_data);
+	CHECK_OFFSET(si_perf_type);
 
 	/* sigpoll */
 	CHECK_OFFSET(si_band);
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 316a76a58c3f30735e5e416a6dc304d6bb86312d Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Mon, 17 May 2021 16:09:31 +0200
Subject: perf test: Fix libpfm4 support (63) test error for nested event
 groups

Compiling perf with make LIBPFM4=1 includes libpfm support and
enables test case 63 'Test libpfm4 support'. This test reports an error
on all platforms for subtest 63.2 'test groups of --pfm-events'.
The reported error message is 'nested event groups not supported'

 # ./perf test -F 63
 63: Test libpfm4 support                                            :
 63.1: test of individual --pfm-events                               :
 Error:
 failed to parse event stereolab : event not found
 Error:
 failed to parse event stereolab,instructions : event not found
 Error:
 failed to parse event instructions,stereolab : event not found
  Ok
 63.2: test groups of --pfm-events                                   :
 Error:
 nested event groups not supported    <------ Error message here
 Error:
 failed to parse event {stereolab} : event not found
 Error:
 failed to parse event {instructions,cycles},{instructions,stereolab} :\
	 event not found
 Ok
 #

This patch addresses the error message 'nested event groups not supported'.
The root cause is function parse_libpfm_events_option() which parses the
event string '{},{instructions}' and can not handle a leading empty
group notation '{},...'.

The code detects the first (empty) group indicator '{' but does not
terminate group processing on the following group closing character '}'.
So when the second group indicator '{' is detected, the code assumes
a nested group and returns an error.

With the error message fixed, also change the expected event number to
one for the test case to succeed.

While at it also fix a memory leak. In good case the function does not
free the duplicated string given as first parameter.

Output after:
 # ./perf test -F 63
 63: Test libpfm4 support                                            :
 63.1: test of individual --pfm-events                               :
 Error:
 failed to parse event stereolab : event not found
 Error:
 failed to parse event stereolab,instructions : event not found
 Error:
 failed to parse event instructions,stereolab : event not found
  Ok
 63.2: test groups of --pfm-events                                   :
 Error:
 failed to parse event {stereolab} : event not found
 Error:
 failed to parse event {instructions,cycles},{instructions,stereolab} : \
	 event not found
  Ok
 #
Error message 'nested event groups not supported' is gone.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-By: Ian Rogers <irogers@google.com>
Acked-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: http://lore.kernel.org/lkml/20210517140931.2559364-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/pfm.c |  4 ++--
 tools/perf/util/pfm.c  | 11 ++++++++++-
 2 files changed, 12 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/tests/pfm.c b/tools/perf/tests/pfm.c
index 76a53126efdf..d4b0ef74defc 100644
--- a/tools/perf/tests/pfm.c
+++ b/tools/perf/tests/pfm.c
@@ -131,8 +131,8 @@ static int test__pfm_group(void)
 		},
 		{
 			.events = "{},{instructions}",
-			.nr_events = 0,
-			.nr_groups = 0,
+			.nr_events = 1,
+			.nr_groups = 1,
 		},
 		{
 			.events = "{instructions},{instructions}",
diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c
index d735acb6c29c..6eef6dfeaa57 100644
--- a/tools/perf/util/pfm.c
+++ b/tools/perf/util/pfm.c
@@ -62,8 +62,16 @@ int parse_libpfm_events_option(const struct option *opt, const char *str,
 		}
 
 		/* no event */
-		if (*q == '\0')
+		if (*q == '\0') {
+			if (*sep == '}') {
+				if (grp_evt < 0) {
+					ui__error("cannot close a non-existing event group\n");
+					goto error;
+				}
+				grp_evt--;
+			}
 			continue;
+		}
 
 		memset(&attr, 0, sizeof(attr));
 		event_attr_init(&attr);
@@ -107,6 +115,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str,
 			grp_evt = -1;
 		}
 	}
+	free(p_orig);
 	return 0;
 error:
 	free(p_orig);
-- 
cgit v1.2.3


From cb7987837c31b217b28089bbc78922d5c9187869 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 19 May 2021 10:45:13 +0300
Subject: perf intel-pt: Fix transaction abort handling

When adding support for power events, some handling of FUP packets was
unified. That resulted in breaking reporting of TSX aborts, by not
considering the associated TIP packet. Fix that.

Example:

A machine that supports TSX is required. It will have flag "rtm". Kernel
parameter tsx=on may be required.

 # for w in `cat /proc/cpuinfo | grep -m1 flags `;do echo $w | grep rtm ; done
 rtm

Test program:

 #include <stdio.h>
 #include <immintrin.h>

 int main()
 {
        int x = 0;

        if (_xbegin() == _XBEGIN_STARTED) {
                x = 1;
                _xabort(1);
        } else {
                printf("x = %d\n", x);
        }
        return 0;
 }

Compile with -mrtm i.e.

 gcc -Wall -Wextra -mrtm xabort.c -o xabort

Record:

 perf record -e intel_pt/cyc/u --filter 'filter main @ ./xabort' ./xabort

Before:

 # perf script --itrace=be -F+flags,+addr,-period,-event --ns
          xabort  1478 [007] 92161.431348552:   tr strt                             0 [unknown] ([unknown]) =>           400b6d main+0x0 (/root/xabort)
          xabort  1478 [007] 92161.431348624:   jmp                            400b96 main+0x29 (/root/xabort) =>           400bae main+0x41 (/root/xabort)
          xabort  1478 [007] 92161.431348624:   return                         400bb4 main+0x47 (/root/xabort) =>           400b87 main+0x1a (/root/xabort)
          xabort  1478 [007] 92161.431348637:   jcc                            400b8a main+0x1d (/root/xabort) =>           400b98 main+0x2b (/root/xabort)
          xabort  1478 [007] 92161.431348644:   tr end  call                   400ba9 main+0x3c (/root/xabort) =>           40f690 printf+0x0 (/root/xabort)
          xabort  1478 [007] 92161.431360859:   tr strt                             0 [unknown] ([unknown]) =>           400bae main+0x41 (/root/xabort)
          xabort  1478 [007] 92161.431360882:   tr end  return                 400bb4 main+0x47 (/root/xabort) =>           401139 __libc_start_main+0x309 (/root/xabort)

After:

 # perf script --itrace=be -F+flags,+addr,-period,-event --ns
          xabort  1478 [007] 92161.431348552:   tr strt                             0 [unknown] ([unknown]) =>           400b6d main+0x0 (/root/xabort)
          xabort  1478 [007] 92161.431348624:   tx abrt                        400b93 main+0x26 (/root/xabort) =>           400b87 main+0x1a (/root/xabort)
          xabort  1478 [007] 92161.431348637:   jcc                            400b8a main+0x1d (/root/xabort) =>           400b98 main+0x2b (/root/xabort)
          xabort  1478 [007] 92161.431348644:   tr end  call                   400ba9 main+0x3c (/root/xabort) =>           40f690 printf+0x0 (/root/xabort)
          xabort  1478 [007] 92161.431360859:   tr strt                             0 [unknown] ([unknown]) =>           400bae main+0x41 (/root/xabort)
          xabort  1478 [007] 92161.431360882:   tr end  return                 400bb4 main+0x47 (/root/xabort) =>           401139 __libc_start_main+0x309 (/root/xabort)

Fixes: a472e65fc490a ("perf intel-pt: Add decoder support for ptwrite and power event packets")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lore.kernel.org/lkml/20210519074515.9262-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 8c59677bee13..20ad663978cc 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1146,6 +1146,8 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
 		decoder->set_fup_tx_flags = false;
 		decoder->tx_flags = decoder->fup_tx_flags;
 		decoder->state.type = INTEL_PT_TRANSACTION;
+		if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX)
+			decoder->state.type |= INTEL_PT_BRANCH;
 		decoder->state.from_ip = decoder->ip;
 		decoder->state.to_ip = 0;
 		decoder->state.flags = decoder->fup_tx_flags;
@@ -1220,8 +1222,10 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
 			return 0;
 		if (err == -EAGAIN ||
 		    intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) {
+			bool no_tip = decoder->pkt_state != INTEL_PT_STATE_FUP;
+
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-			if (intel_pt_fup_event(decoder))
+			if (intel_pt_fup_event(decoder) && no_tip)
 				return 0;
 			return -EAGAIN;
 		}
-- 
cgit v1.2.3


From c954eb72b31a9dc56c99b450253ec5b121add320 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 19 May 2021 10:45:14 +0300
Subject: perf intel-pt: Fix sample instruction bytes

The decoder reports the current instruction if it was decoded. In some
cases the current instruction is not decoded, in which case the instruction
bytes length must be set to zero. Ensure that is always done.

Note perf script can anyway get the instruction bytes for any samples where
they are not present.

Also note, that there is a redundant "ptq->insn_len = 0" statement which is
not removed until a subsequent patch in order to make this patch apply
cleanly to stable branches.

Example:

A machne that supports TSX is required. It will have flag "rtm". Kernel
parameter tsx=on may be required.

 # for w in `cat /proc/cpuinfo | grep -m1 flags `;do echo $w | grep rtm ; done
 rtm

Test program:

 #include <stdio.h>
 #include <immintrin.h>

 int main()
 {
        int x = 0;

        if (_xbegin() == _XBEGIN_STARTED) {
                x = 1;
                _xabort(1);
        } else {
                printf("x = %d\n", x);
        }
        return 0;
 }

Compile with -mrtm i.e.

 gcc -Wall -Wextra -mrtm xabort.c -o xabort

Record:

 perf record -e intel_pt/cyc/u --filter 'filter main @ ./xabort' ./xabort

Before:

 # perf script --itrace=xe -F+flags,+insn,-period --xed --ns
          xabort  1478 [007] 92161.431348581:   transactions:   x                              400b81 main+0x14 (/root/xabort)          mov $0xffffffff, %eax
          xabort  1478 [007] 92161.431348624:   transactions:   tx abrt                        400b93 main+0x26 (/root/xabort)          mov $0xffffffff, %eax

After:

 # perf script --itrace=xe -F+flags,+insn,-period --xed --ns
          xabort  1478 [007] 92161.431348581:   transactions:   x                              400b81 main+0x14 (/root/xabort)          xbegin 0x6
          xabort  1478 [007] 92161.431348624:   transactions:   tx abrt                        400b93 main+0x26 (/root/xabort)          xabort $0x1

Fixes: faaa87680b25d ("perf intel-pt/bts: Report instruction bytes and length in sample")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lore.kernel.org/lkml/20210519074515.9262-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 8658d42ce57a..beae5cbe9cc2 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -707,8 +707,10 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 
 			*ip += intel_pt_insn->length;
 
-			if (to_ip && *ip == to_ip)
+			if (to_ip && *ip == to_ip) {
+				intel_pt_insn->length = 0;
 				goto out_no_cache;
+			}
 
 			if (*ip >= al.map->end)
 				break;
@@ -1198,6 +1200,7 @@ static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt,
 
 static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 {
+	ptq->insn_len = 0;
 	if (ptq->state->flags & INTEL_PT_ABORT_TX) {
 		ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT;
 	} else if (ptq->state->flags & INTEL_PT_ASYNC) {
-- 
cgit v1.2.3


From 0a0c59724516fabf9705c0d9927fa12319908852 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 19 May 2021 10:45:15 +0300
Subject: perf intel-pt: Remove redundant setting of ptq->insn_len

Remove redundant "ptq->insn_len = 0" statement.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20210519074515.9262-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index beae5cbe9cc2..0dfec8761b9a 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1214,7 +1214,6 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 			ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
 				     PERF_IP_FLAG_ASYNC |
 				     PERF_IP_FLAG_INTERRUPT;
-		ptq->insn_len = 0;
 	} else {
 		if (ptq->state->from_ip)
 			ptq->flags = intel_pt_insn_type(ptq->state->insn_op);
-- 
cgit v1.2.3


From fb6c79d7261afb7e942251254ea47951c2a9a706 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 10 Feb 2021 17:33:27 +0900
Subject: perf tools: Add 'cgroup-switches' software event

It counts how often cgroups are changed actually during the context
switches.

  # perf stat -a -e context-switches,cgroup-switches -a sleep 1

   Performance counter stats for 'system wide':

              11,267      context-switches
              10,950      cgroup-switches

         1.015634369 seconds time elapsed

Committer notes:

The kernel patches landed in v5.13, but this entry wasn't filled in
perf's parse-events tables, which was leading to a segfault when running
'perf list' on a kernel with that feature, as reported by Thomas
Richter.

Also removed the part touching tools/include/uapi/linux/perf_event.h as
it was updated in the usual sync with the kernel UAPI headers, in a
previous, already upstream, patch.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: http://lore.kernel.org/lkml/20210210083327.22726-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 4 ++++
 tools/perf/util/parse-events.l | 1 +
 2 files changed, 5 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4dad14265b81..269997066f6e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -150,6 +150,10 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 		.symbol = "bpf-output",
 		.alias  = "",
 	},
+	[PERF_COUNT_SW_CGROUP_SWITCHES] = {
+		.symbol = "cgroup-switches",
+		.alias  = "",
+	},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index fb8646cc3e83..923849024b15 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -347,6 +347,7 @@ emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EM
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
 duration_time					{ return tool(yyscanner, PERF_TOOL_DURATION_TIME); }
 bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
+cgroup-switches					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); }
 
 	/*
 	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
-- 
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
---
 Documentation/powerpc/syscall64-abi.rst       | 10 ++++++++++
 tools/testing/selftests/seccomp/seccomp_bpf.c | 27 ++++++++++++++++++---------
 2 files changed, 28 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/Documentation/powerpc/syscall64-abi.rst b/Documentation/powerpc/syscall64-abi.rst
index dabee3729e5a..56490c4c0c07 100644
--- a/Documentation/powerpc/syscall64-abi.rst
+++ b/Documentation/powerpc/syscall64-abi.rst
@@ -109,6 +109,16 @@ auxiliary vector.
 
 scv 0 syscalls will always behave as PPC_FEATURE2_HTM_NOSC.
 
+ptrace
+------
+When ptracing system calls (PTRACE_SYSCALL), the pt_regs.trap value contains
+the system call type that can be used to distinguish between sc and scv 0
+system calls, and the different register conventions can be accounted for.
+
+If the value of (pt_regs.trap & 0xfff0) is 0xc00 then the system call was
+performed with the sc instruction, if it is 0x3000 then the system call was
+performed with the scv 0 instruction.
+
 vsyscall
 ========
 
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')

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')

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')

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 3b2f17ad1770e51b8b4e68b5069c4f1ee477eff8 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 19 May 2021 13:50:31 -0300
Subject: perf parse-events: Check if the software events array slots are
 populated

To avoid a NULL pointer dereference when the kernel supports the new
feature but the tooling still hasn't an entry for it.

This happened with the recently added PERF_COUNT_SW_CGROUP_SWITCHES
software event.

Reported-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Link: https://lore.kernel.org/linux-perf-users/YKVESEKRjKtILhog@kernel.org/
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 269997066f6e..84108c17f48d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2932,9 +2932,14 @@ restart:
 	}
 
 	for (i = 0; i < max; i++, syms++) {
+		/*
+		 * New attr.config still not supported here, the latest
+		 * example was PERF_COUNT_SW_CGROUP_SWITCHES
+		 */
+		if (syms->symbol == NULL)
+			continue;
 
-		if (event_glob != NULL && syms->symbol != NULL &&
-		    !(strglobmatch(syms->symbol, event_glob) ||
+		if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) ||
 		      (syms->alias && strglobmatch(syms->alias, event_glob))))
 			continue;
 
-- 
cgit v1.2.3


From ec347b7c319156c3b488681d1813d08d88499cc6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 21 May 2021 16:00:31 -0300
Subject: tools headers UAPI: Sync linux/fs.h with the kernel sources

To pick the trivial change in:

  63c8af5687f6b1b7 ("block: uapi: fix comment about block device ioctl")

This silences this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/fs.h' differs from latest version at 'include/uapi/linux/fs.h'
  diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h

Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index f44eb0a04afd..4c32e97dcdf0 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -185,7 +185,7 @@ struct fsxattr {
 #define BLKROTATIONAL _IO(0x12,126)
 #define BLKZEROOUT _IO(0x12,127)
 /*
- * A jump here: 130-131 are reserved for zoned block devices
+ * A jump here: 130-136 are reserved for zoned block devices
  * (see uapi/linux/blkzoned.h)
  */
 
-- 
cgit v1.2.3


From 4224680ee7aaf0f13ab762ffb2a77373737dce5e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 21 May 2021 16:00:31 -0300
Subject: tools headers UAPI: Sync linux/perf_event.h with the kernel sources

To pick the trivial change in:

  0683b53197b55343 ("signal: Deliver all of the siginfo perf data in _perf")

This silences this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/perf_event.h' differs from latest version at 'include/uapi/linux/perf_event.h'
  diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h

Cc: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/perf_event.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index bf8143505c49..f92880a15645 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -464,7 +464,7 @@ struct perf_event_attr {
 
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
-	 * siginfo_t::si_perf, e.g. to permit user to identify the event.
+	 * siginfo_t::si_perf_data, e.g. to permit user to identify the event.
 	 */
 	__u64	sig_data;
 };
-- 
cgit v1.2.3


From bffcbe79370e8fda7f1d19899de83aa2a833bf69 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 21 May 2021 16:14:00 -0300
Subject: tools headers UAPI: Sync files changed by the quotactl_path unwiring

To pick the changes in this csets:

  5b9fedb31e476693 ("quota: Disable quotactl_path syscall")

That silences these perf build warnings:

  Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h'
  diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h
  Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'
  diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
  Warning: Kernel ABI header at 'tools/perf/arch/powerpc/entry/syscalls/syscall.tbl' differs from latest version at 'arch/powerpc/kernel/syscalls/syscall.tbl'
  diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl
  Warning: Kernel ABI header at 'tools/perf/arch/s390/entry/syscalls/syscall.tbl' differs from latest version at 'arch/s390/kernel/syscalls/syscall.tbl'
  diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl
  Warning: Kernel ABI header at 'tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl' differs from latest version at 'arch/mips/kernel/syscalls/syscall_n64.tbl'
  diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl

Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl | 2 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl  | 2 +-
 tools/perf/arch/s390/entry/syscalls/syscall.tbl     | 2 +-
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl   | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 9974f5f8e49b..9cd1c34f31b5 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -357,7 +357,7 @@
 440	n64	process_madvise			sys_process_madvise
 441	n64	epoll_pwait2			sys_epoll_pwait2
 442	n64	mount_setattr			sys_mount_setattr
-443	n64	quotactl_path			sys_quotactl_path
+# 443 reserved for quotactl_path
 444	n64	landlock_create_ruleset		sys_landlock_create_ruleset
 445	n64	landlock_add_rule		sys_landlock_add_rule
 446	n64	landlock_restrict_self		sys_landlock_restrict_self
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 2e68fbb57cc6..8f052ff4058c 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -522,7 +522,7 @@
 440	common	process_madvise			sys_process_madvise
 441	common	epoll_pwait2			sys_epoll_pwait2		compat_sys_epoll_pwait2
 442	common	mount_setattr			sys_mount_setattr
-443	common	quotactl_path			sys_quotactl_path
+# 443 reserved for quotactl_path
 444	common	landlock_create_ruleset		sys_landlock_create_ruleset
 445	common	landlock_add_rule		sys_landlock_add_rule
 446	common	landlock_restrict_self		sys_landlock_restrict_self
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 7e4a2aba366d..0690263df1dd 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -445,7 +445,7 @@
 440  common	process_madvise		sys_process_madvise		sys_process_madvise
 441  common	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
 442  common	mount_setattr		sys_mount_setattr		sys_mount_setattr
-443  common	quotactl_path		sys_quotactl_path		sys_quotactl_path
+# 443 reserved for quotactl_path
 444  common	landlock_create_ruleset	sys_landlock_create_ruleset	sys_landlock_create_ruleset
 445  common	landlock_add_rule	sys_landlock_add_rule		sys_landlock_add_rule
 446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index ecd551b08d05..ce18119ea0d0 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -364,7 +364,7 @@
 440	common	process_madvise		sys_process_madvise
 441	common	epoll_pwait2		sys_epoll_pwait2
 442	common	mount_setattr		sys_mount_setattr
-443	common	quotactl_path		sys_quotactl_path
+# 443 reserved for quotactl_path
 444	common	landlock_create_ruleset	sys_landlock_create_ruleset
 445	common	landlock_add_rule	sys_landlock_add_rule
 446	common	landlock_restrict_self	sys_landlock_restrict_self
-- 
cgit v1.2.3


From a6172059758ba1b496ae024cece7d5bdc8d017db Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 21 May 2021 12:20:51 +0300
Subject: perf scripts python: exported-sql-viewer.py: Fix copy to clipboard
 from Top Calls by elapsed Time report

Provide missing argument to prevent following error when copying a
selection to the clipboard:

Traceback (most recent call last):
  File "tools/perf/scripts/python/exported-sql-viewer.py", line 4041, in <lambda>
    menu.addAction(CreateAction("&Copy selection", "Copy to clipboard", lambda: CopyCellsToClipboardHdr(self.view), self.view))
  File "tools/perf/scripts/python/exported-sql-viewer.py", line 4021, in CopyCellsToClipboardHdr
    CopyCellsToClipboard(view, False, True)
  File "tools/perf/scripts/python/exported-sql-viewer.py", line 4018, in CopyCellsToClipboard
    view.CopyCellsToClipboard(view, as_csv, with_hdr)
  File "tools/perf/scripts/python/exported-sql-viewer.py", line 3871, in CopyTableCellsToClipboard
    val = model.headerData(col, Qt.Horizontal)
TypeError: headerData() missing 1 required positional argument: 'role'

Fixes: 96c43b9a7ab3b ("perf scripts python: exported-sql-viewer.py: Add copy to clipboard")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lore.kernel.org/lkml/20210521092053.25683-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 7daa8bb70a5a..b5078d65704e 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -3868,7 +3868,7 @@ def CopyTableCellsToClipboard(view, as_csv=False, with_hdr=False):
 	if with_hdr:
 		model = indexes[0].model()
 		for col in range(min_col, max_col + 1):
-			val = model.headerData(col, Qt.Horizontal)
+			val = model.headerData(col, Qt.Horizontal, Qt.DisplayRole)
 			if as_csv:
 				text += sep + ToCSValue(val)
 				sep = ","
-- 
cgit v1.2.3


From fd931b2e234a7cc451a7bbb1965d6ce623189158 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 21 May 2021 12:20:52 +0300
Subject: perf scripts python: exported-sql-viewer.py: Fix Array TypeError

The 'Array' class is present in more than one python standard library.
In some versions of Python 3, the following error occurs:

Traceback (most recent call last):
  File "tools/perf/scripts/python/exported-sql-viewer.py", line 4702, in <lambda>
    reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda a=None,x=dbid: self.NewBranchView(x), self))
  File "tools/perf/scripts/python/exported-sql-viewer.py", line 4727, in NewBranchView
    BranchWindow(self.glb, event_id, ReportVars(), self)
  File "tools/perf/scripts/python/exported-sql-viewer.py", line 3208, in __init__
    self.model = LookupCreateModel(model_name, lambda: BranchModel(glb, event_id, report_vars.where_clause))
  File "tools/perf/scripts/python/exported-sql-viewer.py", line 343, in LookupCreateModel
    model = create_fn()
  File "tools/perf/scripts/python/exported-sql-viewer.py", line 3208, in <lambda>
    self.model = LookupCreateModel(model_name, lambda: BranchModel(glb, event_id, report_vars.where_clause))
  File "tools/perf/scripts/python/exported-sql-viewer.py", line 3124, in __init__
    self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample)
  File "tools/perf/scripts/python/exported-sql-viewer.py", line 2658, in __init__
    self.buffer = Array(c_char, self.buffer_size, lock=False)
TypeError: abstract class

This apparently happens because Python can be inconsistent about which
class of the name 'Array' gets imported. Fix by importing explicitly by
name so that only the desired 'Array' gets imported.

Fixes: 8392b74b575c3 ("perf scripts python: exported-sql-viewer.py: Add ability to display all the database tables")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lore.kernel.org/lkml/20210521092053.25683-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index b5078d65704e..4a63843f623c 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -125,8 +125,9 @@ if pyside_version_1:
 	from PySide.QtGui import *
 	from PySide.QtSql import *
 
-from decimal import *
-from ctypes import *
+from decimal import Decimal, ROUND_HALF_UP
+from ctypes import CDLL, Structure, create_string_buffer, addressof, sizeof, \
+		   c_void_p, c_bool, c_byte, c_char, c_int, c_uint, c_longlong, c_ulonglong
 from multiprocessing import Process, Array, Value, Event
 
 # xrange is range in Python3
-- 
cgit v1.2.3


From f56299a9c998e0bfbd4ab07cafe9eb8444512448 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 21 May 2021 12:20:53 +0300
Subject: perf scripts python: exported-sql-viewer.py: Fix warning display

Deprecation warnings are useful only for the developer, not an end user.
Display warnings only when requested using the python -W option. This
stops the display of warnings like:

 tools/perf/scripts/python/exported-sql-viewer.py:5102: DeprecationWarning:
         an integer is required (got type PySide2.QtCore.Qt.AlignmentFlag).
         Implicit conversion to integers using __int__ is deprecated, and
         may be removed in a future version of Python.
    err = app.exec_()

Since the warning can be fixed only in PySide2, we must wait for it to
be finally fixed there.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org      # v5.3+
Link: http://lore.kernel.org/lkml/20210521092053.25683-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 4a63843f623c..711d4f9f5645 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -91,6 +91,11 @@
 from __future__ import print_function
 
 import sys
+# Only change warnings if the python -W option was not used
+if not sys.warnoptions:
+	import warnings
+	# PySide2 causes deprecation warnings, ignore them.
+	warnings.filterwarnings("ignore", category=DeprecationWarning)
 import argparse
 import weakref
 import threading
-- 
cgit v1.2.3


From f42907e8a4515635615a6ffd44242454ef843c04 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 21 May 2021 20:51:27 +0300
Subject: perf script: Add missing PERF_IP_FLAG_CHARS for VM-Entry and VM-Exit

Add 'g' (guest) for VM-Entry and 'h' (host) for VM-Exit.

Fixes: c025d46cd932c ("perf script: Add branch types for VM-Entry and VM-Exit")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20210521175127.27264-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-intel-pt.txt | 6 +++---
 tools/perf/Documentation/perf-script.txt   | 7 ++++---
 tools/perf/util/event.h                    | 2 +-
 3 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 1dcec73c910c..bcf3eca5afbe 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -108,9 +108,9 @@ displayed as follows:
 
 	perf script --itrace=ibxwpe -F+flags
 
-The flags are "bcrosyiABEx" which stand for branch, call, return, conditional,
-system, asynchronous, interrupt, transaction abort, trace begin, trace end, and
-in transaction, respectively.
+The flags are "bcrosyiABExgh" which stand for branch, call, return, conditional,
+system, asynchronous, interrupt, transaction abort, trace begin, trace end,
+in transaction, VM-entry, and VM-exit respectively.
 
 perf script also supports higher level ways to dump instruction traces:
 
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5b8b61075039..48a5f5b26dd4 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -183,14 +183,15 @@ OPTIONS
 	At this point usage is displayed, and perf-script exits.
 
 	The flags field is synthesized and may have a value when Instruction
-	Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
+	Trace decoding. The flags are "bcrosyiABExgh" which stand for branch,
 	call, return, conditional, system, asynchronous, interrupt,
-	transaction abort, trace begin, trace end, and in transaction,
+	transaction abort, trace begin, trace end, in transaction, VM-Entry, and VM-Exit
 	respectively. Known combinations of flags are printed more nicely e.g.
 	"call" for "bc", "return" for "br", "jcc" for "bo", "jmp" for "b",
 	"int" for "bci", "iret" for "bri", "syscall" for "bcs", "sysret" for "brs",
 	"async" for "by", "hw int" for "bcyi", "tx abrt" for "bA", "tr strt" for "bB",
-	"tr end" for "bE". However the "x" flag will be display separately in those
+	"tr end" for "bE", "vmentry" for "bcg", "vmexit" for "bch".
+	However the "x" flag will be displayed separately in those
 	cases e.g. "jcc     (x)" for a condition branch within a transaction.
 
 	The callindent field is synthesized and may have a value when
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8a62fb39e365..19ad64f2bd83 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -100,7 +100,7 @@ enum {
 	PERF_IP_FLAG_VMEXIT		= 1ULL << 12,
 };
 
-#define PERF_IP_FLAG_CHARS "bcrosyiABEx"
+#define PERF_IP_FLAG_CHARS "bcrosyiABExgh"
 
 #define PERF_BRANCH_MASK		(\
 	PERF_IP_FLAG_BRANCH		|\
-- 
cgit v1.2.3


From f8b61bd20479c094fb421da42fef6b4ff22a589e Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Tue, 11 May 2021 23:51:16 -0700
Subject: perf stat: Skip evlist__[enable|disable] when all events uses BPF

When all events of a perf-stat session use BPF, it is not necessary to
call evlist__enable() and evlist__disable(). Skip them when
all_counters_use_bpf is true.

Signed-off-by: Song Liu <song@kernel.org>
Reported-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 13 ++++++++++---
 tools/perf/util/evlist.c  |  3 ---
 2 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5a830ae09418..f9f74a514315 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -572,7 +572,8 @@ static int enable_counters(void)
 	 * - we have initial delay configured
 	 */
 	if (!target__none(&target) || stat_config.initial_delay) {
-		evlist__enable(evsel_list);
+		if (!all_counters_use_bpf)
+			evlist__enable(evsel_list);
 		if (stat_config.initial_delay > 0)
 			pr_info(EVLIST_ENABLED_MSG);
 	}
@@ -581,13 +582,19 @@ static int enable_counters(void)
 
 static void disable_counters(void)
 {
+	struct evsel *counter;
+
 	/*
 	 * If we don't have tracee (attaching to task or cpu), counters may
 	 * still be running. To get accurate group ratios, we must stop groups
 	 * from counting before reading their constituent counters.
 	 */
-	if (!target__none(&target))
-		evlist__disable(evsel_list);
+	if (!target__none(&target)) {
+		evlist__for_each_entry(evsel_list, counter)
+			bpf_counter__disable(counter);
+		if (!all_counters_use_bpf)
+			evlist__disable(evsel_list);
+	}
 }
 
 static volatile int workload_exec_errno;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 6e5c41528c7d..6ea3e677dc1e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -425,9 +425,6 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name)
 	if (affinity__setup(&affinity) < 0)
 		return;
 
-	evlist__for_each_entry(evlist, pos)
-		bpf_counter__disable(pos);
-
 	/* Disable 'immediate' events last */
 	for (imm = 0; imm <= 1; imm++) {
 		evlist__for_each_cpu(evlist, i, cpu) {
-- 
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')

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 f747e6667ebb2ffb8133486c9cd19800d72b0d98 Mon Sep 17 00:00:00 2001
From: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Date: Sat, 22 May 2021 17:42:02 -0700
Subject: linux/bits.h: fix compilation error with GENMASK

GENMASK() has an input check which uses __builtin_choose_expr() to
enable a compile time sanity check of its inputs if they are known at
compile time.

However, it turns out that __builtin_constant_p() does not always return
a compile time constant [0].  It was thought this problem was fixed with
gcc 4.9 [1], but apparently this is not the case [2].

Switch to use __is_constexpr() instead which always returns a compile time
constant, regardless of its inputs.

Link: https://lore.kernel.org/lkml/42b4342b-aefc-a16a-0d43-9f9c0d63ba7a@rasmusvillemoes.dk [0]
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=19449 [1]
Link: https://lore.kernel.org/lkml/1ac7bbc2-45d9-26ed-0b33-bf382b8d858b@I-love.SAKURA.ne.jp [2]
Link: https://lkml.kernel.org/r/20210511203716.117010-1-rikard.falkeborn@gmail.com
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Yury Norov <yury.norov@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bits.h        |  2 +-
 include/linux/const.h       |  8 ++++++++
 include/linux/minmax.h      | 10 ++--------
 tools/include/linux/bits.h  |  2 +-
 tools/include/linux/const.h |  8 ++++++++
 5 files changed, 20 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/include/linux/bits.h b/include/linux/bits.h
index 7f475d59a097..87d112650dfb 100644
--- a/include/linux/bits.h
+++ b/include/linux/bits.h
@@ -22,7 +22,7 @@
 #include <linux/build_bug.h>
 #define GENMASK_INPUT_CHECK(h, l) \
 	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
-		__builtin_constant_p((l) > (h)), (l) > (h), 0)))
+		__is_constexpr((l) > (h)), (l) > (h), 0)))
 #else
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
diff --git a/include/linux/const.h b/include/linux/const.h
index 81b8aae5a855..435ddd72d2c4 100644
--- a/include/linux/const.h
+++ b/include/linux/const.h
@@ -3,4 +3,12 @@
 
 #include <vdso/const.h>
 
+/*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ */
+#define __is_constexpr(x) \
+	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
+
 #endif /* _LINUX_CONST_H */
diff --git a/include/linux/minmax.h b/include/linux/minmax.h
index c0f57b0c64d9..5433c08fcc68 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -2,6 +2,8 @@
 #ifndef _LINUX_MINMAX_H
 #define _LINUX_MINMAX_H
 
+#include <linux/const.h>
+
 /*
  * min()/max()/clamp() macros must accomplish three things:
  *
@@ -17,14 +19,6 @@
 #define __typecheck(x, y) \
 	(!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
 
-/*
- * This returns a constant expression while determining if an argument is
- * a constant expression, most importantly without evaluating the argument.
- * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
- */
-#define __is_constexpr(x) \
-	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
-
 #define __no_side_effects(x, y) \
 		(__is_constexpr(x) && __is_constexpr(y))
 
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 7f475d59a097..87d112650dfb 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -22,7 +22,7 @@
 #include <linux/build_bug.h>
 #define GENMASK_INPUT_CHECK(h, l) \
 	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
-		__builtin_constant_p((l) > (h)), (l) > (h), 0)))
+		__is_constexpr((l) > (h)), (l) > (h), 0)))
 #else
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h
index 81b8aae5a855..435ddd72d2c4 100644
--- a/tools/include/linux/const.h
+++ b/tools/include/linux/const.h
@@ -3,4 +3,12 @@
 
 #include <vdso/const.h>
 
+/*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ */
+#define __is_constexpr(x) \
+	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
+
 #endif /* _LINUX_CONST_H */
-- 
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>
---
 net/sched/sch_fq_pie.c                                         | 10 +++++-----
 tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json |  8 ++++----
 2 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 949163fe68af..266c7c1869d9 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -297,9 +297,9 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
 			goto flow_error;
 		}
 		q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]);
-		if (!q->flows_cnt || q->flows_cnt >= 65536) {
+		if (!q->flows_cnt || q->flows_cnt > 65536) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Number of flows must range in [1..65535]");
+					   "Number of flows must range in [1..65536]");
 			goto flow_error;
 		}
 	}
@@ -367,7 +367,7 @@ static void fq_pie_timer(struct timer_list *t)
 	struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer);
 	struct Qdisc *sch = q->sch;
 	spinlock_t *root_lock; /* to lock qdisc for probability calculations */
-	u16 idx;
+	u32 idx;
 
 	root_lock = qdisc_lock(qdisc_root_sleeping(sch));
 	spin_lock(root_lock);
@@ -388,7 +388,7 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct fq_pie_sched_data *q = qdisc_priv(sch);
 	int err;
-	u16 idx;
+	u32 idx;
 
 	pie_params_init(&q->p_params);
 	sch->limit = 10 * 1024;
@@ -500,7 +500,7 @@ static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 static void fq_pie_reset(struct Qdisc *sch)
 {
 	struct fq_pie_sched_data *q = qdisc_priv(sch);
-	u16 idx;
+	u32 idx;
 
 	INIT_LIST_HEAD(&q->new_flows);
 	INIT_LIST_HEAD(&q->old_flows);
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 a8deba8547e39f26440101164a3bbc2899c5b305 Mon Sep 17 00:00:00 2001
From: Liu Jian <liujian56@huawei.com>
Date: Tue, 25 May 2021 09:41:39 +0800
Subject: bpftool: Add sock_release help info for cgroup attach/prog load
 command

The help information was not added at the time when the function got added.
Fix this and add the missing information to its cli, documentation and bash
completion.

Fixes: db94cc0b4805 ("bpftool: Add support for BPF_CGROUP_INET_SOCK_RELEASE")
Signed-off-by: Liu Jian <liujian56@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20210525014139.323859-1-liujian56@huawei.com
---
 tools/bpf/bpftool/Documentation/bpftool-cgroup.rst | 4 +++-
 tools/bpf/bpftool/Documentation/bpftool-prog.rst   | 2 +-
 tools/bpf/bpftool/bash-completion/bpftool          | 6 +++---
 tools/bpf/bpftool/cgroup.c                         | 3 ++-
 tools/bpf/bpftool/prog.c                           | 2 +-
 5 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index 790944c35602..baee8591ac76 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -30,7 +30,8 @@ CGROUP COMMANDS
 |	*ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** |
 |		**bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** |
 |               **getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** |
-|               **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** }
+|               **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** |
+|               **sock_release** }
 |	*ATTACH_FLAGS* := { **multi** | **override** }
 
 DESCRIPTION
@@ -106,6 +107,7 @@ DESCRIPTION
 		  **getpeername6** call to getpeername(2) for an inet6 socket (since 5.8);
 		  **getsockname4** call to getsockname(2) for an inet4 socket (since 5.8);
 		  **getsockname6** call to getsockname(2) for an inet6 socket (since 5.8).
+		  **sock_release** closing an userspace inet socket (since 5.9).
 
 	**bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
 		  Detach *PROG* from the cgroup *CGROUP* and attach type
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 358c7309d419..fe1b38e7e887 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -44,7 +44,7 @@ PROG COMMANDS
 |		**cgroup/connect4** | **cgroup/connect6** | **cgroup/getpeername4** | **cgroup/getpeername6** |
 |               **cgroup/getsockname4** | **cgroup/getsockname6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** |
 |		**cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** |
-|		**cgroup/getsockopt** | **cgroup/setsockopt** |
+|		**cgroup/getsockopt** | **cgroup/setsockopt** | **cgroup/sock_release** |
 |		**struct_ops** | **fentry** | **fexit** | **freplace** | **sk_lookup**
 |	}
 |       *ATTACH_TYPE* := {
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index d67518bcbd44..cc33c5824a2f 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -478,7 +478,7 @@ _bpftool()
                                 cgroup/recvmsg4 cgroup/recvmsg6 \
                                 cgroup/post_bind4 cgroup/post_bind6 \
                                 cgroup/sysctl cgroup/getsockopt \
-                                cgroup/setsockopt struct_ops \
+                                cgroup/setsockopt cgroup/sock_release struct_ops \
                                 fentry fexit freplace sk_lookup" -- \
                                                    "$cur" ) )
                             return 0
@@ -1021,7 +1021,7 @@ _bpftool()
                         device bind4 bind6 post_bind4 post_bind6 connect4 connect6 \
                         getpeername4 getpeername6 getsockname4 getsockname6 \
                         sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl getsockopt \
-                        setsockopt'
+                        setsockopt sock_release'
                     local ATTACH_FLAGS='multi override'
                     local PROG_TYPE='id pinned tag name'
                     case $prev in
@@ -1032,7 +1032,7 @@ _bpftool()
                         ingress|egress|sock_create|sock_ops|device|bind4|bind6|\
                         post_bind4|post_bind6|connect4|connect6|getpeername4|\
                         getpeername6|getsockname4|getsockname6|sendmsg4|sendmsg6|\
-                        recvmsg4|recvmsg6|sysctl|getsockopt|setsockopt)
+                        recvmsg4|recvmsg6|sysctl|getsockopt|setsockopt|sock_release)
                             COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \
                                 "$cur" ) )
                             return 0
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index d901cc1b904a..6e53b1d393f4 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -28,7 +28,8 @@
 	"                        connect6 | getpeername4 | getpeername6 |\n"   \
 	"                        getsockname4 | getsockname6 | sendmsg4 |\n"   \
 	"                        sendmsg6 | recvmsg4 | recvmsg6 |\n"           \
-	"                        sysctl | getsockopt | setsockopt }"
+	"                        sysctl | getsockopt | setsockopt |\n"	       \
+	"                        sock_release }"
 
 static unsigned int query_flags;
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 3f067d2d7584..da4846c9856a 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -2138,7 +2138,7 @@ static int do_help(int argc, char **argv)
 		"                 cgroup/getpeername4 | cgroup/getpeername6 |\n"
 		"                 cgroup/getsockname4 | cgroup/getsockname6 | cgroup/sendmsg4 |\n"
 		"                 cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n"
-		"                 cgroup/getsockopt | cgroup/setsockopt |\n"
+		"                 cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n"
 		"                 struct_ops | fentry | fexit | freplace | sk_lookup }\n"
 		"       ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n"
 		"                        flow_dissector }\n"
-- 
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')

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')

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 75ea44e356b5de8c817f821c9dd68ae329e82add Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 25 May 2021 18:07:58 +0200
Subject: perf jevents: Fix getting maximum number of fds

On some hosts, rlim.rlim_max can be returned as RLIM_INFINITY.
By casting it to int, it is interpreted as -1, which will cause get_maxfds
to return 0, causing "Invalid argument" errors in nftw() calls.
Fix this by casting the second argument of min() to rlim_t instead.

Fixes: 80eeb67fe577 ("perf jevents: Program to convert JSON file")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Link: http://lore.kernel.org/lkml/20210525160758.97829-1-nbd@nbd.name
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/jevents.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 7422b0ea8790..9604446f8360 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -960,7 +960,7 @@ static int get_maxfds(void)
 	struct rlimit rlim;
 
 	if (getrlimit(RLIMIT_NOFILE, &rlim) == 0)
-		return min((int)rlim.rlim_max / 2, 512);
+		return min(rlim.rlim_max / 2, (rlim_t)512);
 
 	return 512;
 }
-- 
cgit v1.2.3


From 39fe2fc96694164723846fccf6caa42c3aee6ec4 Mon Sep 17 00:00:00 2001
From: Zhenzhong Duan <zhenzhong.duan@intel.com>
Date: Wed, 12 May 2021 12:31:06 +0800
Subject: selftests: kvm: make allocation of extra memory take effect

The extra memory pages is missed to be allocated during VM creating.
perf_test_util and kvm_page_table_test use it to alloc extra memory
currently.

Fix it by adding extra_mem_pages to the total memory calculation before
allocate.

Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Message-Id: <20210512043107.30076-1-zhenzhong.duan@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/kvm_util.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index fc83f6c5902d..159f4d62241d 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -295,7 +295,7 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
 	 */
 	uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus;
 	uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2;
-	uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages;
+	uint64_t pages = DEFAULT_GUEST_PHY_PAGES + extra_mem_pages + vcpu_pages + extra_pg_pages;
 	struct kvm_vm *vm;
 	int i;
 
-- 
cgit v1.2.3


From a13534d6676d2f2a9aa286e27e482b4896ff90e3 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 24 May 2021 14:27:38 +0200
Subject: selftests: kvm: fix potential issue with ELF loading

vm_vaddr_alloc() sets up GVA to GPA mapping page by page; therefore, GPAs
may not be continuous if same memslot is used for data and page table allocation.

kvm_vm_elf_load() however expects a continuous range of HVAs (and thus GPAs)
because it does not try to read file data page by page.  Fix this mismatch
by allocating memory in one step.

Reported-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/kvm_util.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 159f4d62241d..12d953d8ee35 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1099,6 +1099,9 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
 	uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);
 
 	virt_pgd_alloc(vm, pgd_memslot);
+	vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages,
+					      KVM_UTIL_MIN_PFN * vm->page_size,
+					      data_memslot);
 
 	/*
 	 * Find an unused range of virtual page addresses of at least
@@ -1108,11 +1111,7 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
 
 	/* Map the virtual pages. */
 	for (vm_vaddr_t vaddr = vaddr_start; pages > 0;
-		pages--, vaddr += vm->page_size) {
-		vm_paddr_t paddr;
-
-		paddr = vm_phy_page_alloc(vm,
-				KVM_UTIL_MIN_PFN * vm->page_size, data_memslot);
+		pages--, vaddr += vm->page_size, paddr += vm->page_size) {
 
 		virt_pg_map(vm, vaddr, paddr, pgd_memslot);
 
-- 
cgit v1.2.3


From 22721a56109940f15b673d0f01907b7a7202275e Mon Sep 17 00:00:00 2001
From: "Maciej S. Szmigiero" <maciej.szmigiero@oracle.com>
Date: Tue, 13 Apr 2021 16:08:27 +0200
Subject: KVM: selftests: Keep track of memslots more efficiently

The KVM selftest framework was using a simple list for keeping track of
the memslots currently in use.
This resulted in lookups and adding a single memslot being O(n), the
later due to linear scanning of the existing memslot set to check for
the presence of any conflicting entries.

Before this change, benchmarking high count of memslots was more or less
impossible as pretty much all the benchmark time was spent in the
selftest framework code.

We can simply use a rbtree for keeping track of both of gfn and hva.
We don't need an interval tree for hva here as we can't have overlapping
memslots because we allocate a completely new memory chunk for each new
memslot.

Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Message-Id: <b12749d47ee860468240cf027412c91b76dbe3db.1618253574.git.maciej.szmigiero@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile               |   2 +-
 tools/testing/selftests/kvm/lib/kvm_util.c         | 141 ++++++++++++++++-----
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |  15 ++-
 tools/testing/selftests/kvm/lib/rbtree.c           |   1 +
 4 files changed, 124 insertions(+), 35 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/lib/rbtree.c

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index e439d027939d..a8c30f888d40 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -33,7 +33,7 @@ ifeq ($(ARCH),s390)
 	UNAME_M := s390x
 endif
 
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
+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_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 12d953d8ee35..1255744758e3 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -203,7 +203,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	TEST_ASSERT(vm != NULL, "Insufficient Memory");
 
 	INIT_LIST_HEAD(&vm->vcpus);
-	INIT_LIST_HEAD(&vm->userspace_mem_regions);
+	vm->regions.gpa_tree = RB_ROOT;
+	vm->regions.hva_tree = RB_ROOT;
+	hash_init(vm->regions.slot_hash);
 
 	vm->mode = mode;
 	vm->type = 0;
@@ -355,13 +357,14 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
  */
 void kvm_vm_restart(struct kvm_vm *vmp, int perm)
 {
+	int ctr;
 	struct userspace_mem_region *region;
 
 	vm_open(vmp, perm);
 	if (vmp->has_irqchip)
 		vm_create_irqchip(vmp);
 
-	list_for_each_entry(region, &vmp->userspace_mem_regions, list) {
+	hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) {
 		int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
 		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
 			    "  rc: %i errno: %i\n"
@@ -424,14 +427,21 @@ uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm)
 static struct userspace_mem_region *
 userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
 {
-	struct userspace_mem_region *region;
+	struct rb_node *node;
 
-	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
+	for (node = vm->regions.gpa_tree.rb_node; node; ) {
+		struct userspace_mem_region *region =
+			container_of(node, struct userspace_mem_region, gpa_node);
 		uint64_t existing_start = region->region.guest_phys_addr;
 		uint64_t existing_end = region->region.guest_phys_addr
 			+ region->region.memory_size - 1;
 		if (start <= existing_end && end >= existing_start)
 			return region;
+
+		if (start < existing_start)
+			node = node->rb_left;
+		else
+			node = node->rb_right;
 	}
 
 	return NULL;
@@ -546,11 +556,16 @@ void kvm_vm_release(struct kvm_vm *vmp)
 }
 
 static void __vm_mem_region_delete(struct kvm_vm *vm,
-				   struct userspace_mem_region *region)
+				   struct userspace_mem_region *region,
+				   bool unlink)
 {
 	int ret;
 
-	list_del(&region->list);
+	if (unlink) {
+		rb_erase(&region->gpa_node, &vm->regions.gpa_tree);
+		rb_erase(&region->hva_node, &vm->regions.hva_tree);
+		hash_del(&region->slot_node);
+	}
 
 	region->region.memory_size = 0;
 	ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
@@ -569,14 +584,16 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
  */
 void kvm_vm_free(struct kvm_vm *vmp)
 {
-	struct userspace_mem_region *region, *tmp;
+	int ctr;
+	struct hlist_node *node;
+	struct userspace_mem_region *region;
 
 	if (vmp == NULL)
 		return;
 
 	/* Free userspace_mem_regions. */
-	list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list)
-		__vm_mem_region_delete(vmp, region);
+	hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node)
+		__vm_mem_region_delete(vmp, region, false);
 
 	/* Free sparsebit arrays. */
 	sparsebit_free(&vmp->vpages_valid);
@@ -658,6 +675,57 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
 	return 0;
 }
 
+static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree,
+					       struct userspace_mem_region *region)
+{
+	struct rb_node **cur, *parent;
+
+	for (cur = &gpa_tree->rb_node, parent = NULL; *cur; ) {
+		struct userspace_mem_region *cregion;
+
+		cregion = container_of(*cur, typeof(*cregion), gpa_node);
+		parent = *cur;
+		if (region->region.guest_phys_addr <
+		    cregion->region.guest_phys_addr)
+			cur = &(*cur)->rb_left;
+		else {
+			TEST_ASSERT(region->region.guest_phys_addr !=
+				    cregion->region.guest_phys_addr,
+				    "Duplicate GPA in region tree");
+
+			cur = &(*cur)->rb_right;
+		}
+	}
+
+	rb_link_node(&region->gpa_node, parent, cur);
+	rb_insert_color(&region->gpa_node, gpa_tree);
+}
+
+static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree,
+					       struct userspace_mem_region *region)
+{
+	struct rb_node **cur, *parent;
+
+	for (cur = &hva_tree->rb_node, parent = NULL; *cur; ) {
+		struct userspace_mem_region *cregion;
+
+		cregion = container_of(*cur, typeof(*cregion), hva_node);
+		parent = *cur;
+		if (region->host_mem < cregion->host_mem)
+			cur = &(*cur)->rb_left;
+		else {
+			TEST_ASSERT(region->host_mem !=
+				    cregion->host_mem,
+				    "Duplicate HVA in region tree");
+
+			cur = &(*cur)->rb_right;
+		}
+	}
+
+	rb_link_node(&region->hva_node, parent, cur);
+	rb_insert_color(&region->hva_node, hva_tree);
+}
+
 /*
  * VM Userspace Memory Region Add
  *
@@ -722,7 +790,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 			(uint64_t) region->region.memory_size);
 
 	/* Confirm no region with the requested slot already exists. */
-	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
+	hash_for_each_possible(vm->regions.slot_hash, region, slot_node,
+			       slot) {
 		if (region->region.slot != slot)
 			continue;
 
@@ -793,8 +862,10 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		ret, errno, slot, flags,
 		guest_paddr, (uint64_t) region->region.memory_size);
 
-	/* Add to linked-list of memory regions. */
-	list_add(&region->list, &vm->userspace_mem_regions);
+	/* Add to quick lookup data structures */
+	vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region);
+	vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region);
+	hash_add(vm->regions.slot_hash, &region->slot_node, slot);
 }
 
 /*
@@ -817,10 +888,10 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot)
 {
 	struct userspace_mem_region *region;
 
-	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
+	hash_for_each_possible(vm->regions.slot_hash, region, slot_node,
+			       memslot)
 		if (region->region.slot == memslot)
 			return region;
-	}
 
 	fprintf(stderr, "No mem region with the requested slot found,\n"
 		"  requested slot: %u\n", memslot);
@@ -905,7 +976,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa)
  */
 void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot)
 {
-	__vm_mem_region_delete(vm, memslot2region(vm, slot));
+	__vm_mem_region_delete(vm, memslot2region(vm, slot), true);
 }
 
 /*
@@ -1176,16 +1247,14 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
 {
 	struct userspace_mem_region *region;
 
-	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
-		if ((gpa >= region->region.guest_phys_addr)
-			&& (gpa <= (region->region.guest_phys_addr
-				+ region->region.memory_size - 1)))
-			return (void *) ((uintptr_t) region->host_mem
-				+ (gpa - region->region.guest_phys_addr));
+	region = userspace_mem_region_find(vm, gpa, gpa);
+	if (!region) {
+		TEST_FAIL("No vm physical memory at 0x%lx", gpa);
+		return NULL;
 	}
 
-	TEST_FAIL("No vm physical memory at 0x%lx", gpa);
-	return NULL;
+	return (void *)((uintptr_t)region->host_mem
+		+ (gpa - region->region.guest_phys_addr));
 }
 
 /*
@@ -1207,15 +1276,22 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
  */
 vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
 {
-	struct userspace_mem_region *region;
+	struct rb_node *node;
+
+	for (node = vm->regions.hva_tree.rb_node; node; ) {
+		struct userspace_mem_region *region =
+			container_of(node, struct userspace_mem_region, hva_node);
+
+		if (hva >= region->host_mem) {
+			if (hva <= (region->host_mem
+				+ region->region.memory_size - 1))
+				return (vm_paddr_t)((uintptr_t)
+					region->region.guest_phys_addr
+					+ (hva - (uintptr_t)region->host_mem));
 
-	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
-		if ((hva >= region->host_mem)
-			&& (hva <= (region->host_mem
-				+ region->region.memory_size - 1)))
-			return (vm_paddr_t) ((uintptr_t)
-				region->region.guest_phys_addr
-				+ (hva - (uintptr_t) region->host_mem));
+			node = node->rb_right;
+		} else
+			node = node->rb_left;
 	}
 
 	TEST_FAIL("No mapping to a guest physical address, hva: %p", hva);
@@ -1821,6 +1897,7 @@ int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
  */
 void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 {
+	int ctr;
 	struct userspace_mem_region *region;
 	struct vcpu *vcpu;
 
@@ -1828,7 +1905,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd);
 	fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size);
 	fprintf(stream, "%*sMem Regions:\n", indent, "");
-	list_for_each_entry(region, &vm->userspace_mem_regions, list) {
+	hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) {
 		fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx "
 			"host_virt: %p\n", indent + 2, "",
 			(uint64_t) region->region.guest_phys_addr,
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 91ce1b5d480b..b30e8c7b119b 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -8,6 +8,9 @@
 #ifndef SELFTEST_KVM_UTIL_INTERNAL_H
 #define SELFTEST_KVM_UTIL_INTERNAL_H
 
+#include "linux/hashtable.h"
+#include "linux/rbtree.h"
+
 #include "sparsebit.h"
 
 struct userspace_mem_region {
@@ -18,7 +21,9 @@ struct userspace_mem_region {
 	void *host_mem;
 	void *mmap_start;
 	size_t mmap_size;
-	struct list_head list;
+	struct rb_node gpa_node;
+	struct rb_node hva_node;
+	struct hlist_node slot_node;
 };
 
 struct vcpu {
@@ -31,6 +36,12 @@ struct vcpu {
 	uint32_t dirty_gfns_count;
 };
 
+struct userspace_mem_regions {
+	struct rb_root gpa_tree;
+	struct rb_root hva_tree;
+	DECLARE_HASHTABLE(slot_hash, 9);
+};
+
 struct kvm_vm {
 	int mode;
 	unsigned long type;
@@ -43,7 +54,7 @@ struct kvm_vm {
 	unsigned int va_bits;
 	uint64_t max_gfn;
 	struct list_head vcpus;
-	struct list_head userspace_mem_regions;
+	struct userspace_mem_regions regions;
 	struct sparsebit *vpages_valid;
 	struct sparsebit *vpages_mapped;
 	bool has_irqchip;
diff --git a/tools/testing/selftests/kvm/lib/rbtree.c b/tools/testing/selftests/kvm/lib/rbtree.c
new file mode 100644
index 000000000000..a703f0194ea3
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/rbtree.c
@@ -0,0 +1 @@
+#include "../../../../lib/rbtree.c"
-- 
cgit v1.2.3


From cad347fab142bcb9bebc125b5ba0c1e52ce74fdc Mon Sep 17 00:00:00 2001
From: "Maciej S. Szmigiero" <maciej.szmigiero@oracle.com>
Date: Tue, 13 Apr 2021 16:08:28 +0200
Subject: KVM: selftests: add a memslot-related performance benchmark

This benchmark contains the following tests:
* Map test, where the host unmaps guest memory while the guest writes to
it (maps it).

The test is designed in a way to make the unmap operation on the host
take a negligible amount of time in comparison with the mapping
operation in the guest.

The test area is actually split in two: the first half is being mapped
by the guest while the second half in being unmapped by the host.
Then a guest <-> host sync happens and the areas are reversed.

* Unmap test which is broadly similar to the above map test, but it is
designed in an opposite way: to make the mapping operation in the guest
take a negligible amount of time in comparison with the unmap operation
on the host.
This test is available in two variants: with per-page unmap operation
or a chunked one (using 2 MiB chunk size).

* Move active area test which involves moving the last (highest gfn)
memslot a bit back and forth on the host while the guest is
concurrently writing around the area being moved (including over the
moved memslot).

* Move inactive area test which is similar to the previous move active
area test, but now guest writes all happen outside of the area being
moved.

* Read / write test in which the guest writes to the beginning of each
page of the test area while the host writes to the middle of each such
page.
Then each side checks the values the other side has written.
This particular test is not expected to give different results depending
on particular memslots implementation, it is meant as a rough sanity
check and to provide insight on the spread of test results expected.

Each test performs its operation in a loop until a test period ends
(this is 5 seconds by default, but it is configurable).
Then the total count of loops done is divided by the actual elapsed
time to give the test result.

The tests have a configurable memslot cap with the "-s" test option, by
default the system maximum is used.
Each test is repeated a particular number of times (by default 20
times), the best result achieved is printed.

The test memory area is divided equally between memslots, the reminder
is added to the last memslot.
The test area size does not depend on the number of memslots in use.

The tests also measure the time that it took to add all these memslots.
The best result from the tests that use the whole test area is printed
after all the requested tests are done.

In general, these tests are designed to use as much memory as possible
(within reason) while still doing 100+ loops even on high memslot counts
with the default test length.
Increasing the test runtime makes it increasingly more likely that some
event will happen on the system during the test run, which might lower
the test result.

Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Message-Id: <8d31bb3d92bc8fa33a9756fa802ee14266ab994e.1618253574.git.maciej.szmigiero@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore          |    1 +
 tools/testing/selftests/kvm/Makefile            |    1 +
 tools/testing/selftests/kvm/memslot_perf_test.c | 1037 +++++++++++++++++++++++
 3 files changed, 1039 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/memslot_perf_test.c

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index bd83158e0e0b..524c857a049c 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -41,5 +41,6 @@
 /kvm_create_max_vcpus
 /kvm_page_table_test
 /memslot_modification_stress_test
+/memslot_perf_test
 /set_memory_region_test
 /steal_time
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index a8c30f888d40..daaee1888b12 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -74,6 +74,7 @@ TEST_GEN_PROGS_x86_64 += hardware_disable_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_x86_64 += kvm_page_table_test
 TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test
+TEST_GEN_PROGS_x86_64 += memslot_perf_test
 TEST_GEN_PROGS_x86_64 += set_memory_region_test
 TEST_GEN_PROGS_x86_64 += steal_time
 
diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
new file mode 100644
index 000000000000..4ae0e5ec0f74
--- /dev/null
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -0,0 +1,1037 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A memslot-related performance benchmark.
+ *
+ * Copyright (C) 2021 Oracle and/or its affiliates.
+ *
+ * Basic guest setup / host vCPU thread code lifted from set_memory_region_test.
+ */
+#include <pthread.h>
+#include <sched.h>
+#include <semaphore.h>
+#include <stdatomic.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <time.h>
+#include <unistd.h>
+
+#include <linux/compiler.h>
+
+#include <test_util.h>
+#include <kvm_util.h>
+#include <processor.h>
+
+#define VCPU_ID 0
+
+#define MEM_SIZE		((512U << 20) + 4096)
+#define MEM_SIZE_PAGES		(MEM_SIZE / 4096)
+#define MEM_GPA		0x10000000UL
+#define MEM_AUX_GPA		MEM_GPA
+#define MEM_SYNC_GPA		MEM_AUX_GPA
+#define MEM_TEST_GPA		(MEM_AUX_GPA + 4096)
+#define MEM_TEST_SIZE		(MEM_SIZE - 4096)
+static_assert(MEM_SIZE % 4096 == 0, "invalid mem size");
+static_assert(MEM_TEST_SIZE % 4096 == 0, "invalid mem test size");
+
+/*
+ * 32 MiB is max size that gets well over 100 iterations on 509 slots.
+ * Considering that each slot needs to have at least one page up to
+ * 8194 slots in use can then be tested (although with slightly
+ * limited resolution).
+ */
+#define MEM_SIZE_MAP		((32U << 20) + 4096)
+#define MEM_SIZE_MAP_PAGES	(MEM_SIZE_MAP / 4096)
+#define MEM_TEST_MAP_SIZE	(MEM_SIZE_MAP - 4096)
+#define MEM_TEST_MAP_SIZE_PAGES (MEM_TEST_MAP_SIZE / 4096)
+static_assert(MEM_SIZE_MAP % 4096 == 0, "invalid map test region size");
+static_assert(MEM_TEST_MAP_SIZE % 4096 == 0, "invalid map test region size");
+static_assert(MEM_TEST_MAP_SIZE_PAGES % 2 == 0, "invalid map test region size");
+static_assert(MEM_TEST_MAP_SIZE_PAGES > 2, "invalid map test region size");
+
+/*
+ * 128 MiB is min size that fills 32k slots with at least one page in each
+ * while at the same time gets 100+ iterations in such test
+ */
+#define MEM_TEST_UNMAP_SIZE		(128U << 20)
+#define MEM_TEST_UNMAP_SIZE_PAGES	(MEM_TEST_UNMAP_SIZE / 4096)
+/* 2 MiB chunk size like a typical huge page */
+#define MEM_TEST_UNMAP_CHUNK_PAGES	(2U << (20 - 12))
+static_assert(MEM_TEST_UNMAP_SIZE <= MEM_TEST_SIZE,
+	      "invalid unmap test region size");
+static_assert(MEM_TEST_UNMAP_SIZE % 4096 == 0,
+	      "invalid unmap test region size");
+static_assert(MEM_TEST_UNMAP_SIZE_PAGES %
+	      (2 * MEM_TEST_UNMAP_CHUNK_PAGES) == 0,
+	      "invalid unmap test region size");
+
+/*
+ * For the move active test the middle of the test area is placed on
+ * a memslot boundary: half lies in the memslot being moved, half in
+ * other memslot(s).
+ *
+ * When running this test with 32k memslots (32764, really) each memslot
+ * contains 4 pages.
+ * The last one additionally contains the remaining 21 pages of memory,
+ * for the total size of 25 pages.
+ * Hence, the maximum size here is 50 pages.
+ */
+#define MEM_TEST_MOVE_SIZE_PAGES	(50)
+#define MEM_TEST_MOVE_SIZE		(MEM_TEST_MOVE_SIZE_PAGES * 4096)
+#define MEM_TEST_MOVE_GPA_DEST		(MEM_GPA + MEM_SIZE)
+static_assert(MEM_TEST_MOVE_SIZE <= MEM_TEST_SIZE,
+	      "invalid move test region size");
+
+#define MEM_TEST_VAL_1 0x1122334455667788
+#define MEM_TEST_VAL_2 0x99AABBCCDDEEFF00
+
+struct vm_data {
+	struct kvm_vm *vm;
+	pthread_t vcpu_thread;
+	uint32_t nslots;
+	uint64_t npages;
+	uint64_t pages_per_slot;
+	void **hva_slots;
+	bool mmio_ok;
+	uint64_t mmio_gpa_min;
+	uint64_t mmio_gpa_max;
+};
+
+struct sync_area {
+	atomic_bool start_flag;
+	atomic_bool exit_flag;
+	atomic_bool sync_flag;
+	void *move_area_ptr;
+};
+
+/*
+ * Technically, we need also for the atomic bool to be address-free, which
+ * is recommended, but not strictly required, by C11 for lockless
+ * implementations.
+ * However, in practice both GCC and Clang fulfill this requirement on
+ * all KVM-supported platforms.
+ */
+static_assert(ATOMIC_BOOL_LOCK_FREE == 2, "atomic bool is not lockless");
+
+static sem_t vcpu_ready;
+
+static bool map_unmap_verify;
+
+static bool verbose;
+#define pr_info_v(...)				\
+	do {					\
+		if (verbose)			\
+			pr_info(__VA_ARGS__);	\
+	} while (0)
+
+static void *vcpu_worker(void *data)
+{
+	struct vm_data *vm = data;
+	struct kvm_run *run;
+	struct ucall uc;
+	uint64_t cmd;
+
+	run = vcpu_state(vm->vm, VCPU_ID);
+	while (1) {
+		vcpu_run(vm->vm, VCPU_ID);
+
+		if (run->exit_reason == KVM_EXIT_IO) {
+			cmd = get_ucall(vm->vm, VCPU_ID, &uc);
+			if (cmd != UCALL_SYNC)
+				break;
+
+			sem_post(&vcpu_ready);
+			continue;
+		}
+
+		if (run->exit_reason != KVM_EXIT_MMIO)
+			break;
+
+		TEST_ASSERT(vm->mmio_ok, "Unexpected mmio exit");
+		TEST_ASSERT(run->mmio.is_write, "Unexpected mmio read");
+		TEST_ASSERT(run->mmio.len == 8,
+			    "Unexpected exit mmio size = %u", run->mmio.len);
+		TEST_ASSERT(run->mmio.phys_addr >= vm->mmio_gpa_min &&
+			    run->mmio.phys_addr <= vm->mmio_gpa_max,
+			    "Unexpected exit mmio address = 0x%llx",
+			    run->mmio.phys_addr);
+	}
+
+	if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT)
+		TEST_FAIL("%s at %s:%ld, val = %lu", (const char *)uc.args[0],
+			  __FILE__, uc.args[1], uc.args[2]);
+
+	return NULL;
+}
+
+static void wait_for_vcpu(void)
+{
+	struct timespec ts;
+
+	TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts),
+		    "clock_gettime() failed: %d\n", errno);
+
+	ts.tv_sec += 2;
+	TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts),
+		    "sem_timedwait() failed: %d\n", errno);
+}
+
+static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages)
+{
+	uint64_t gpage, pgoffs;
+	uint32_t slot, slotoffs;
+	void *base;
+
+	TEST_ASSERT(gpa >= MEM_GPA, "Too low gpa to translate");
+	TEST_ASSERT(gpa < MEM_GPA + data->npages * 4096,
+		    "Too high gpa to translate");
+	gpa -= MEM_GPA;
+
+	gpage = gpa / 4096;
+	pgoffs = gpa % 4096;
+	slot = min(gpage / data->pages_per_slot, (uint64_t)data->nslots - 1);
+	slotoffs = gpage - (slot * data->pages_per_slot);
+
+	if (rempages) {
+		uint64_t slotpages;
+
+		if (slot == data->nslots - 1)
+			slotpages = data->npages - slot * data->pages_per_slot;
+		else
+			slotpages = data->pages_per_slot;
+
+		TEST_ASSERT(!pgoffs,
+			    "Asking for remaining pages in slot but gpa not page aligned");
+		*rempages = slotpages - slotoffs;
+	}
+
+	base = data->hva_slots[slot];
+	return (uint8_t *)base + slotoffs * 4096 + pgoffs;
+}
+
+static uint64_t vm_slot2gpa(struct vm_data *data, uint32_t slot)
+{
+	TEST_ASSERT(slot < data->nslots, "Too high slot number");
+
+	return MEM_GPA + slot * data->pages_per_slot * 4096;
+}
+
+static struct vm_data *alloc_vm(void)
+{
+	struct vm_data *data;
+
+	data = malloc(sizeof(*data));
+	TEST_ASSERT(data, "malloc(vmdata) failed");
+
+	data->vm = NULL;
+	data->hva_slots = NULL;
+
+	return data;
+}
+
+static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots,
+		       void *guest_code, uint64_t mempages,
+		       struct timespec *slot_runtime)
+{
+	uint32_t max_mem_slots;
+	uint64_t rempages;
+	uint64_t guest_addr;
+	uint32_t slot;
+	struct timespec tstart;
+	struct sync_area *sync;
+
+	max_mem_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS);
+	TEST_ASSERT(max_mem_slots > 1,
+		    "KVM_CAP_NR_MEMSLOTS should be greater than 1");
+	TEST_ASSERT(nslots > 1 || nslots == -1,
+		    "Slot count cap should be greater than 1");
+	if (nslots != -1)
+		max_mem_slots = min(max_mem_slots, (uint32_t)nslots);
+	pr_info_v("Allowed number of memory slots: %"PRIu32"\n", max_mem_slots);
+
+	TEST_ASSERT(mempages > 1,
+		    "Can't test without any memory");
+
+	data->npages = mempages;
+	data->nslots = max_mem_slots - 1;
+	data->pages_per_slot = mempages / data->nslots;
+	if (!data->pages_per_slot) {
+		*maxslots = mempages + 1;
+		return false;
+	}
+
+	rempages = mempages % data->nslots;
+	data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots);
+	TEST_ASSERT(data->hva_slots, "malloc() fail");
+
+	data->vm = vm_create_default(VCPU_ID, mempages, guest_code);
+
+	pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n",
+		max_mem_slots - 1, data->pages_per_slot, rempages);
+
+	clock_gettime(CLOCK_MONOTONIC, &tstart);
+	for (slot = 1, guest_addr = MEM_GPA; slot < max_mem_slots; slot++) {
+		uint64_t npages;
+
+		npages = data->pages_per_slot;
+		if (slot == max_mem_slots - 1)
+			npages += rempages;
+
+		vm_userspace_mem_region_add(data->vm, VM_MEM_SRC_ANONYMOUS,
+					    guest_addr, slot, npages,
+					    0);
+		guest_addr += npages * 4096;
+	}
+	*slot_runtime = timespec_elapsed(tstart);
+
+	for (slot = 0, guest_addr = MEM_GPA; slot < max_mem_slots - 1; slot++) {
+		uint64_t npages;
+		uint64_t gpa;
+
+		npages = data->pages_per_slot;
+		if (slot == max_mem_slots - 2)
+			npages += rempages;
+
+		gpa = vm_phy_pages_alloc(data->vm, npages, guest_addr,
+					 slot + 1);
+		TEST_ASSERT(gpa == guest_addr,
+			    "vm_phy_pages_alloc() failed\n");
+
+		data->hva_slots[slot] = addr_gpa2hva(data->vm, guest_addr);
+		memset(data->hva_slots[slot], 0, npages * 4096);
+
+		guest_addr += npages * 4096;
+	}
+
+	virt_map(data->vm, MEM_GPA, MEM_GPA, mempages, 0);
+
+	sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL);
+	atomic_init(&sync->start_flag, false);
+	atomic_init(&sync->exit_flag, false);
+	atomic_init(&sync->sync_flag, false);
+
+	data->mmio_ok = false;
+
+	return true;
+}
+
+static void launch_vm(struct vm_data *data)
+{
+	pr_info_v("Launching the test VM\n");
+
+	pthread_create(&data->vcpu_thread, NULL, vcpu_worker, data);
+
+	/* Ensure the guest thread is spun up. */
+	wait_for_vcpu();
+}
+
+static void free_vm(struct vm_data *data)
+{
+	kvm_vm_free(data->vm);
+	free(data->hva_slots);
+	free(data);
+}
+
+static void wait_guest_exit(struct vm_data *data)
+{
+	pthread_join(data->vcpu_thread, NULL);
+}
+
+static void let_guest_run(struct sync_area *sync)
+{
+	atomic_store_explicit(&sync->start_flag, true, memory_order_release);
+}
+
+static void guest_spin_until_start(void)
+{
+	struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA;
+
+	while (!atomic_load_explicit(&sync->start_flag, memory_order_acquire))
+		;
+}
+
+static void make_guest_exit(struct sync_area *sync)
+{
+	atomic_store_explicit(&sync->exit_flag, true, memory_order_release);
+}
+
+static bool _guest_should_exit(void)
+{
+	struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA;
+
+	return atomic_load_explicit(&sync->exit_flag, memory_order_acquire);
+}
+
+#define guest_should_exit() unlikely(_guest_should_exit())
+
+/*
+ * noinline so we can easily see how much time the host spends waiting
+ * for the guest.
+ * For the same reason use alarm() instead of polling clock_gettime()
+ * to implement a wait timeout.
+ */
+static noinline void host_perform_sync(struct sync_area *sync)
+{
+	alarm(2);
+
+	atomic_store_explicit(&sync->sync_flag, true, memory_order_release);
+	while (atomic_load_explicit(&sync->sync_flag, memory_order_acquire))
+		;
+
+	alarm(0);
+}
+
+static bool guest_perform_sync(void)
+{
+	struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA;
+	bool expected;
+
+	do {
+		if (guest_should_exit())
+			return false;
+
+		expected = true;
+	} while (!atomic_compare_exchange_weak_explicit(&sync->sync_flag,
+							&expected, false,
+							memory_order_acq_rel,
+							memory_order_relaxed));
+
+	return true;
+}
+
+static void guest_code_test_memslot_move(void)
+{
+	struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA;
+	uintptr_t base = (typeof(base))READ_ONCE(sync->move_area_ptr);
+
+	GUEST_SYNC(0);
+
+	guest_spin_until_start();
+
+	while (!guest_should_exit()) {
+		uintptr_t ptr;
+
+		for (ptr = base; ptr < base + MEM_TEST_MOVE_SIZE;
+		     ptr += 4096)
+			*(uint64_t *)ptr = MEM_TEST_VAL_1;
+
+		/*
+		 * No host sync here since the MMIO exits are so expensive
+		 * that the host would spend most of its time waiting for
+		 * the guest and so instead of measuring memslot move
+		 * performance we would measure the performance and
+		 * likelihood of MMIO exits
+		 */
+	}
+
+	GUEST_DONE();
+}
+
+static void guest_code_test_memslot_map(void)
+{
+	struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA;
+
+	GUEST_SYNC(0);
+
+	guest_spin_until_start();
+
+	while (1) {
+		uintptr_t ptr;
+
+		for (ptr = MEM_TEST_GPA;
+		     ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; ptr += 4096)
+			*(uint64_t *)ptr = MEM_TEST_VAL_1;
+
+		if (!guest_perform_sync())
+			break;
+
+		for (ptr = MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2;
+		     ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE; ptr += 4096)
+			*(uint64_t *)ptr = MEM_TEST_VAL_2;
+
+		if (!guest_perform_sync())
+			break;
+	}
+
+	GUEST_DONE();
+}
+
+static void guest_code_test_memslot_unmap(void)
+{
+	struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA;
+
+	GUEST_SYNC(0);
+
+	guest_spin_until_start();
+
+	while (1) {
+		uintptr_t ptr = MEM_TEST_GPA;
+
+		/*
+		 * We can afford to access (map) just a small number of pages
+		 * per host sync as otherwise the host will spend
+		 * a significant amount of its time waiting for the guest
+		 * (instead of doing unmap operations), so this will
+		 * effectively turn this test into a map performance test.
+		 *
+		 * Just access a single page to be on the safe side.
+		 */
+		*(uint64_t *)ptr = MEM_TEST_VAL_1;
+
+		if (!guest_perform_sync())
+			break;
+
+		ptr += MEM_TEST_UNMAP_SIZE / 2;
+		*(uint64_t *)ptr = MEM_TEST_VAL_2;
+
+		if (!guest_perform_sync())
+			break;
+	}
+
+	GUEST_DONE();
+}
+
+static void guest_code_test_memslot_rw(void)
+{
+	GUEST_SYNC(0);
+
+	guest_spin_until_start();
+
+	while (1) {
+		uintptr_t ptr;
+
+		for (ptr = MEM_TEST_GPA;
+		     ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096)
+			*(uint64_t *)ptr = MEM_TEST_VAL_1;
+
+		if (!guest_perform_sync())
+			break;
+
+		for (ptr = MEM_TEST_GPA + 4096 / 2;
+		     ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096) {
+			uint64_t val = *(uint64_t *)ptr;
+
+			GUEST_ASSERT_1(val == MEM_TEST_VAL_2, val);
+			*(uint64_t *)ptr = 0;
+		}
+
+		if (!guest_perform_sync())
+			break;
+	}
+
+	GUEST_DONE();
+}
+
+static bool test_memslot_move_prepare(struct vm_data *data,
+				      struct sync_area *sync,
+				      uint64_t *maxslots, bool isactive)
+{
+	uint64_t movesrcgpa, movetestgpa;
+
+	movesrcgpa = vm_slot2gpa(data, data->nslots - 1);
+
+	if (isactive) {
+		uint64_t lastpages;
+
+		vm_gpa2hva(data, movesrcgpa, &lastpages);
+		if (lastpages < MEM_TEST_MOVE_SIZE_PAGES / 2) {
+			*maxslots = 0;
+			return false;
+		}
+	}
+
+	movetestgpa = movesrcgpa - (MEM_TEST_MOVE_SIZE / (isactive ? 2 : 1));
+	sync->move_area_ptr = (void *)movetestgpa;
+
+	if (isactive) {
+		data->mmio_ok = true;
+		data->mmio_gpa_min = movesrcgpa;
+		data->mmio_gpa_max = movesrcgpa + MEM_TEST_MOVE_SIZE / 2 - 1;
+	}
+
+	return true;
+}
+
+static bool test_memslot_move_prepare_active(struct vm_data *data,
+					     struct sync_area *sync,
+					     uint64_t *maxslots)
+{
+	return test_memslot_move_prepare(data, sync, maxslots, true);
+}
+
+static bool test_memslot_move_prepare_inactive(struct vm_data *data,
+					       struct sync_area *sync,
+					       uint64_t *maxslots)
+{
+	return test_memslot_move_prepare(data, sync, maxslots, false);
+}
+
+static void test_memslot_move_loop(struct vm_data *data, struct sync_area *sync)
+{
+	uint64_t movesrcgpa;
+
+	movesrcgpa = vm_slot2gpa(data, data->nslots - 1);
+	vm_mem_region_move(data->vm, data->nslots - 1 + 1,
+			   MEM_TEST_MOVE_GPA_DEST);
+	vm_mem_region_move(data->vm, data->nslots - 1 + 1, movesrcgpa);
+}
+
+static void test_memslot_do_unmap(struct vm_data *data,
+				  uint64_t offsp, uint64_t count)
+{
+	uint64_t gpa, ctr;
+
+	for (gpa = MEM_TEST_GPA + offsp * 4096, ctr = 0; ctr < count; ) {
+		uint64_t npages;
+		void *hva;
+		int ret;
+
+		hva = vm_gpa2hva(data, gpa, &npages);
+		TEST_ASSERT(npages, "Empty memory slot at gptr 0x%"PRIx64, gpa);
+		npages = min(npages, count - ctr);
+		ret = madvise(hva, npages * 4096, MADV_DONTNEED);
+		TEST_ASSERT(!ret,
+			    "madvise(%p, MADV_DONTNEED) on VM memory should not fail for gptr 0x%"PRIx64,
+			    hva, gpa);
+		ctr += npages;
+		gpa += npages * 4096;
+	}
+	TEST_ASSERT(ctr == count,
+		    "madvise(MADV_DONTNEED) should exactly cover all of the requested area");
+}
+
+static void test_memslot_map_unmap_check(struct vm_data *data,
+					 uint64_t offsp, uint64_t valexp)
+{
+	uint64_t gpa;
+	uint64_t *val;
+
+	if (!map_unmap_verify)
+		return;
+
+	gpa = MEM_TEST_GPA + offsp * 4096;
+	val = (typeof(val))vm_gpa2hva(data, gpa, NULL);
+	TEST_ASSERT(*val == valexp,
+		    "Guest written values should read back correctly before unmap (%"PRIu64" vs %"PRIu64" @ %"PRIx64")",
+		    *val, valexp, gpa);
+	*val = 0;
+}
+
+static void test_memslot_map_loop(struct vm_data *data, struct sync_area *sync)
+{
+	/*
+	 * Unmap the second half of the test area while guest writes to (maps)
+	 * the first half.
+	 */
+	test_memslot_do_unmap(data, MEM_TEST_MAP_SIZE_PAGES / 2,
+			      MEM_TEST_MAP_SIZE_PAGES / 2);
+
+	/*
+	 * Wait for the guest to finish writing the first half of the test
+	 * area, verify the written value on the first and the last page of
+	 * this area and then unmap it.
+	 * Meanwhile, the guest is writing to (mapping) the second half of
+	 * the test area.
+	 */
+	host_perform_sync(sync);
+	test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1);
+	test_memslot_map_unmap_check(data,
+				     MEM_TEST_MAP_SIZE_PAGES / 2 - 1,
+				     MEM_TEST_VAL_1);
+	test_memslot_do_unmap(data, 0, MEM_TEST_MAP_SIZE_PAGES / 2);
+
+
+	/*
+	 * Wait for the guest to finish writing the second half of the test
+	 * area and verify the written value on the first and the last page
+	 * of this area.
+	 * The area will be unmapped at the beginning of the next loop
+	 * iteration.
+	 * Meanwhile, the guest is writing to (mapping) the first half of
+	 * the test area.
+	 */
+	host_perform_sync(sync);
+	test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES / 2,
+				     MEM_TEST_VAL_2);
+	test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES - 1,
+				     MEM_TEST_VAL_2);
+}
+
+static void test_memslot_unmap_loop_common(struct vm_data *data,
+					   struct sync_area *sync,
+					   uint64_t chunk)
+{
+	uint64_t ctr;
+
+	/*
+	 * Wait for the guest to finish mapping page(s) in the first half
+	 * of the test area, verify the written value and then perform unmap
+	 * of this area.
+	 * Meanwhile, the guest is writing to (mapping) page(s) in the second
+	 * half of the test area.
+	 */
+	host_perform_sync(sync);
+	test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1);
+	for (ctr = 0; ctr < MEM_TEST_UNMAP_SIZE_PAGES / 2; ctr += chunk)
+		test_memslot_do_unmap(data, ctr, chunk);
+
+	/* Likewise, but for the opposite host / guest areas */
+	host_perform_sync(sync);
+	test_memslot_map_unmap_check(data, MEM_TEST_UNMAP_SIZE_PAGES / 2,
+				     MEM_TEST_VAL_2);
+	for (ctr = MEM_TEST_UNMAP_SIZE_PAGES / 2;
+	     ctr < MEM_TEST_UNMAP_SIZE_PAGES; ctr += chunk)
+		test_memslot_do_unmap(data, ctr, chunk);
+}
+
+static void test_memslot_unmap_loop(struct vm_data *data,
+				    struct sync_area *sync)
+{
+	test_memslot_unmap_loop_common(data, sync, 1);
+}
+
+static void test_memslot_unmap_loop_chunked(struct vm_data *data,
+					    struct sync_area *sync)
+{
+	test_memslot_unmap_loop_common(data, sync, MEM_TEST_UNMAP_CHUNK_PAGES);
+}
+
+static void test_memslot_rw_loop(struct vm_data *data, struct sync_area *sync)
+{
+	uint64_t gptr;
+
+	for (gptr = MEM_TEST_GPA + 4096 / 2;
+	     gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096)
+		*(uint64_t *)vm_gpa2hva(data, gptr, NULL) = MEM_TEST_VAL_2;
+
+	host_perform_sync(sync);
+
+	for (gptr = MEM_TEST_GPA;
+	     gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096) {
+		uint64_t *vptr = (typeof(vptr))vm_gpa2hva(data, gptr, NULL);
+		uint64_t val = *vptr;
+
+		TEST_ASSERT(val == MEM_TEST_VAL_1,
+			    "Guest written values should read back correctly (is %"PRIu64" @ %"PRIx64")",
+			    val, gptr);
+		*vptr = 0;
+	}
+
+	host_perform_sync(sync);
+}
+
+struct test_data {
+	const char *name;
+	uint64_t mem_size;
+	void (*guest_code)(void);
+	bool (*prepare)(struct vm_data *data, struct sync_area *sync,
+			uint64_t *maxslots);
+	void (*loop)(struct vm_data *data, struct sync_area *sync);
+};
+
+static bool test_execute(int nslots, uint64_t *maxslots,
+			 unsigned int maxtime,
+			 const struct test_data *tdata,
+			 uint64_t *nloops,
+			 struct timespec *slot_runtime,
+			 struct timespec *guest_runtime)
+{
+	uint64_t mem_size = tdata->mem_size ? : MEM_SIZE_PAGES;
+	struct vm_data *data;
+	struct sync_area *sync;
+	struct timespec tstart;
+	bool ret = true;
+
+	data = alloc_vm();
+	if (!prepare_vm(data, nslots, maxslots, tdata->guest_code,
+			mem_size, slot_runtime)) {
+		ret = false;
+		goto exit_free;
+	}
+
+	sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL);
+
+	if (tdata->prepare &&
+	    !tdata->prepare(data, sync, maxslots)) {
+		ret = false;
+		goto exit_free;
+	}
+
+	launch_vm(data);
+
+	clock_gettime(CLOCK_MONOTONIC, &tstart);
+	let_guest_run(sync);
+
+	while (1) {
+		*guest_runtime = timespec_elapsed(tstart);
+		if (guest_runtime->tv_sec >= maxtime)
+			break;
+
+		tdata->loop(data, sync);
+
+		(*nloops)++;
+	}
+
+	make_guest_exit(sync);
+	wait_guest_exit(data);
+
+exit_free:
+	free_vm(data);
+
+	return ret;
+}
+
+static const struct test_data tests[] = {
+	{
+		.name = "map",
+		.mem_size = MEM_SIZE_MAP_PAGES,
+		.guest_code = guest_code_test_memslot_map,
+		.loop = test_memslot_map_loop,
+	},
+	{
+		.name = "unmap",
+		.mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1,
+		.guest_code = guest_code_test_memslot_unmap,
+		.loop = test_memslot_unmap_loop,
+	},
+	{
+		.name = "unmap chunked",
+		.mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1,
+		.guest_code = guest_code_test_memslot_unmap,
+		.loop = test_memslot_unmap_loop_chunked,
+	},
+	{
+		.name = "move active area",
+		.guest_code = guest_code_test_memslot_move,
+		.prepare = test_memslot_move_prepare_active,
+		.loop = test_memslot_move_loop,
+	},
+	{
+		.name = "move inactive area",
+		.guest_code = guest_code_test_memslot_move,
+		.prepare = test_memslot_move_prepare_inactive,
+		.loop = test_memslot_move_loop,
+	},
+	{
+		.name = "RW",
+		.guest_code = guest_code_test_memslot_rw,
+		.loop = test_memslot_rw_loop
+	},
+};
+
+#define NTESTS ARRAY_SIZE(tests)
+
+struct test_args {
+	int tfirst;
+	int tlast;
+	int nslots;
+	int seconds;
+	int runs;
+};
+
+static void help(char *name, struct test_args *targs)
+{
+	int ctr;
+
+	pr_info("usage: %s [-h] [-v] [-d] [-s slots] [-f first_test] [-e last_test] [-l test_length] [-r run_count]\n",
+		name);
+	pr_info(" -h: print this help screen.\n");
+	pr_info(" -v: enable verbose mode (not for benchmarking).\n");
+	pr_info(" -d: enable extra debug checks.\n");
+	pr_info(" -s: specify memslot count cap (-1 means no cap; currently: %i)\n",
+		targs->nslots);
+	pr_info(" -f: specify the first test to run (currently: %i; max %zu)\n",
+		targs->tfirst, NTESTS - 1);
+	pr_info(" -e: specify the last test to run (currently: %i; max %zu)\n",
+		targs->tlast, NTESTS - 1);
+	pr_info(" -l: specify the test length in seconds (currently: %i)\n",
+		targs->seconds);
+	pr_info(" -r: specify the number of runs per test (currently: %i)\n",
+		targs->runs);
+
+	pr_info("\nAvailable tests:\n");
+	for (ctr = 0; ctr < NTESTS; ctr++)
+		pr_info("%d: %s\n", ctr, tests[ctr].name);
+}
+
+static bool parse_args(int argc, char *argv[],
+		       struct test_args *targs)
+{
+	int opt;
+
+	while ((opt = getopt(argc, argv, "hvds:f:e:l:r:")) != -1) {
+		switch (opt) {
+		case 'h':
+		default:
+			help(argv[0], targs);
+			return false;
+		case 'v':
+			verbose = true;
+			break;
+		case 'd':
+			map_unmap_verify = true;
+			break;
+		case 's':
+			targs->nslots = atoi(optarg);
+			if (targs->nslots <= 0 && targs->nslots != -1) {
+				pr_info("Slot count cap has to be positive or -1 for no cap\n");
+				return false;
+			}
+			break;
+		case 'f':
+			targs->tfirst = atoi(optarg);
+			if (targs->tfirst < 0) {
+				pr_info("First test to run has to be non-negative\n");
+				return false;
+			}
+			break;
+		case 'e':
+			targs->tlast = atoi(optarg);
+			if (targs->tlast < 0 || targs->tlast >= NTESTS) {
+				pr_info("Last test to run has to be non-negative and less than %zu\n",
+					NTESTS);
+				return false;
+			}
+			break;
+		case 'l':
+			targs->seconds = atoi(optarg);
+			if (targs->seconds < 0) {
+				pr_info("Test length in seconds has to be non-negative\n");
+				return false;
+			}
+			break;
+		case 'r':
+			targs->runs = atoi(optarg);
+			if (targs->runs <= 0) {
+				pr_info("Runs per test has to be positive\n");
+				return false;
+			}
+			break;
+		}
+	}
+
+	if (optind < argc) {
+		help(argv[0], targs);
+		return false;
+	}
+
+	if (targs->tfirst > targs->tlast) {
+		pr_info("First test to run cannot be greater than the last test to run\n");
+		return false;
+	}
+
+	return true;
+}
+
+struct test_result {
+	struct timespec slot_runtime, guest_runtime, iter_runtime;
+	int64_t slottimens, runtimens;
+	uint64_t nloops;
+};
+
+static bool test_loop(const struct test_data *data,
+		      const struct test_args *targs,
+		      struct test_result *rbestslottime,
+		      struct test_result *rbestruntime)
+{
+	uint64_t maxslots;
+	struct test_result result;
+
+	result.nloops = 0;
+	if (!test_execute(targs->nslots, &maxslots, targs->seconds, data,
+			  &result.nloops,
+			  &result.slot_runtime, &result.guest_runtime)) {
+		if (maxslots)
+			pr_info("Memslot count too high for this test, decrease the cap (max is %"PRIu64")\n",
+				maxslots);
+		else
+			pr_info("Memslot count may be too high for this test, try adjusting the cap\n");
+
+		return false;
+	}
+
+	pr_info("Test took %ld.%.9lds for slot setup + %ld.%.9lds all iterations\n",
+		result.slot_runtime.tv_sec, result.slot_runtime.tv_nsec,
+		result.guest_runtime.tv_sec, result.guest_runtime.tv_nsec);
+	if (!result.nloops) {
+		pr_info("No full loops done - too short test time or system too loaded?\n");
+		return true;
+	}
+
+	result.iter_runtime = timespec_div(result.guest_runtime,
+					   result.nloops);
+	pr_info("Done %"PRIu64" iterations, avg %ld.%.9lds each\n",
+		result.nloops,
+		result.iter_runtime.tv_sec,
+		result.iter_runtime.tv_nsec);
+	result.slottimens = timespec_to_ns(result.slot_runtime);
+	result.runtimens = timespec_to_ns(result.iter_runtime);
+
+	/*
+	 * Only rank the slot setup time for tests using the whole test memory
+	 * area so they are comparable
+	 */
+	if (!data->mem_size &&
+	    (!rbestslottime->slottimens ||
+	     result.slottimens < rbestslottime->slottimens))
+		*rbestslottime = result;
+	if (!rbestruntime->runtimens ||
+	    result.runtimens < rbestruntime->runtimens)
+		*rbestruntime = result;
+
+	return true;
+}
+
+int main(int argc, char *argv[])
+{
+	struct test_args targs = {
+		.tfirst = 0,
+		.tlast = NTESTS - 1,
+		.nslots = -1,
+		.seconds = 5,
+		.runs = 20,
+	};
+	struct test_result rbestslottime;
+	int tctr;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	if (!parse_args(argc, argv, &targs))
+		return -1;
+
+	rbestslottime.slottimens = 0;
+	for (tctr = targs.tfirst; tctr <= targs.tlast; tctr++) {
+		const struct test_data *data = &tests[tctr];
+		unsigned int runctr;
+		struct test_result rbestruntime;
+
+		if (tctr > targs.tfirst)
+			pr_info("\n");
+
+		pr_info("Testing %s performance with %i runs, %d seconds each\n",
+			data->name, targs.runs, targs.seconds);
+
+		rbestruntime.runtimens = 0;
+		for (runctr = 0; runctr < targs.runs; runctr++)
+			if (!test_loop(data, &targs,
+				       &rbestslottime, &rbestruntime))
+				break;
+
+		if (rbestruntime.runtimens)
+			pr_info("Best runtime result was %ld.%.9lds per iteration (with %"PRIu64" iterations)\n",
+				rbestruntime.iter_runtime.tv_sec,
+				rbestruntime.iter_runtime.tv_nsec,
+				rbestruntime.nloops);
+	}
+
+	if (rbestslottime.slottimens)
+		pr_info("Best slot setup time for the whole test area was %ld.%.9lds\n",
+			rbestslottime.slot_runtime.tv_sec,
+			rbestslottime.slot_runtime.tv_nsec);
+
+	return 0;
+}
-- 
cgit v1.2.3


From ef4c9f4f654622fa15b7a94a9bd1f19e76bb7feb Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Fri, 21 May 2021 17:38:28 +0000
Subject: KVM: selftests: Fix 32-bit truncation of vm_get_max_gfn()

vm_get_max_gfn() casts vm->max_gfn from a uint64_t to an unsigned int,
which causes the upper 32-bits of the max_gfn to get truncated.

Nobody noticed until now likely because vm_get_max_gfn() is only used
as a mechanism to create a memslot in an unused region of the guest
physical address space (the top), and the top of the 32-bit physical
address space was always good enough.

This fix reveals a bug in memslot_modification_stress_test which was
trying to create a dummy memslot past the end of guest physical memory.
Fix that by moving the dummy memslot lower.

Fixes: 52200d0d944e ("KVM: selftests: Remove duplicate guest mode handling")
Reviewed-by: Venkatesh Srinivas <venkateshs@chromium.org>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210521173828.1180619-1-dmatlack@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h         |  2 +-
 tools/testing/selftests/kvm/lib/kvm_util.c             |  2 +-
 tools/testing/selftests/kvm/lib/perf_test_util.c       |  4 +++-
 .../selftests/kvm/memslot_modification_stress_test.c   | 18 +++++++++++-------
 4 files changed, 16 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index a8f022794ce3..2e0d253dabd6 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -302,7 +302,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm);
 
 unsigned int vm_get_page_size(struct kvm_vm *vm);
 unsigned int vm_get_page_shift(struct kvm_vm *vm);
-unsigned int vm_get_max_gfn(struct kvm_vm *vm);
+uint64_t vm_get_max_gfn(struct kvm_vm *vm);
 int vm_get_fd(struct kvm_vm *vm);
 
 unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1255744758e3..ea3f0db85b3e 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -2117,7 +2117,7 @@ unsigned int vm_get_page_shift(struct kvm_vm *vm)
 	return vm->page_shift;
 }
 
-unsigned int vm_get_max_gfn(struct kvm_vm *vm)
+uint64_t vm_get_max_gfn(struct kvm_vm *vm)
 {
 	return vm->max_gfn;
 }
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 81490b9b4e32..abf381800a59 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (C) 2020, Google LLC.
  */
+#include <inttypes.h>
 
 #include "kvm_util.h"
 #include "perf_test_util.h"
@@ -80,7 +81,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	 */
 	TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
 		    "Requested more guest memory than address space allows.\n"
-		    "    guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
+		    "    guest pages: %" PRIx64 " max gfn: %" PRIx64
+		    " vcpus: %d wss: %" PRIx64 "]\n",
 		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
 		    vcpu_memory_bytes);
 
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 6096bf0a5b34..98351ba0933c 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -71,14 +71,22 @@ struct memslot_antagonist_args {
 };
 
 static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay,
-			      uint64_t nr_modifications, uint64_t gpa)
+			       uint64_t nr_modifications)
 {
+	const uint64_t pages = 1;
+	uint64_t gpa;
 	int i;
 
+	/*
+	 * Add the dummy memslot just below the perf_test_util memslot, which is
+	 * at the top of the guest physical address space.
+	 */
+	gpa = guest_test_phys_mem - pages * vm_get_page_size(vm);
+
 	for (i = 0; i < nr_modifications; i++) {
 		usleep(delay);
 		vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa,
-					    DUMMY_MEMSLOT_INDEX, 1, 0);
+					    DUMMY_MEMSLOT_INDEX, pages, 0);
 
 		vm_mem_region_delete(vm, DUMMY_MEMSLOT_INDEX);
 	}
@@ -120,11 +128,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	pr_info("Started all vCPUs\n");
 
 	add_remove_memslot(vm, p->memslot_modification_delay,
-			   p->nr_memslot_modifications,
-			   guest_test_phys_mem +
-			   (guest_percpu_mem_size * nr_vcpus) +
-			   perf_test_args.host_page_size +
-			   perf_test_args.guest_page_size);
+			   p->nr_memslot_modifications);
 
 	run_vcpus = false;
 
-- 
cgit v1.2.3


From 50bc913d526beb9937f1eb0159ec63c43234f961 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Wed, 19 May 2021 21:13:45 +0000
Subject: KVM: selftests: Ignore CPUID.0DH.1H in get_cpuid_test

Similar to CPUID.0DH.0H this entry depends on the vCPU's XCR0 register
and IA32_XSS MSR. Since this test does not control for either before
assigning the vCPU's CPUID, these entries will not necessarily match
the supported CPUID exposed by KVM.

This fixes get_cpuid_test on Cascade Lake CPUs.

Suggested-by: Jim Mattson <jmattson@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210519211345.3944063-1-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/x86_64/get_cpuid_test.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c
index 9b78e8889638..8c77537af5a1 100644
--- a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c
@@ -19,7 +19,12 @@ struct {
 	u32 function;
 	u32 index;
 } mangled_cpuids[] = {
+	/*
+	 * These entries depend on the vCPU's XCR0 register and IA32_XSS MSR,
+	 * which are not controlled for by this test.
+	 */
 	{.function = 0xd, .index = 0},
+	{.function = 0xd, .index = 1},
 };
 
 static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid)
-- 
cgit v1.2.3


From a10453c038a7e97169185405242d20d21de0bb91 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Fri, 14 May 2021 23:05:21 +0000
Subject: KVM: selftests: Fix hang in hardware_disable_test

If /dev/kvm is not available then hardware_disable_test will hang
indefinitely because the child process exits before posting to the
semaphore for which the parent is waiting.

Fix this by making the parent periodically check if the child has
exited. We have to be careful to forward the child's exit status to
preserve a KSFT_SKIP status.

I considered just checking for /dev/kvm before creating the child
process, but there are so many other reasons why the child could exit
early that it seemed better to handle that as general case.

Tested:

$ ./hardware_disable_test
/dev/kvm not available, skipping test
$ echo $?
4
$ modprobe kvm_intel
$ ./hardware_disable_test
$ echo $?
0

Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210514230521.2608768-1-dmatlack@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../testing/selftests/kvm/hardware_disable_test.c  | 32 +++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c
index 5aadf84c91c0..4b8db3bce610 100644
--- a/tools/testing/selftests/kvm/hardware_disable_test.c
+++ b/tools/testing/selftests/kvm/hardware_disable_test.c
@@ -132,6 +132,36 @@ static void run_test(uint32_t run)
 	TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run);
 }
 
+void wait_for_child_setup(pid_t pid)
+{
+	/*
+	 * Wait for the child to post to the semaphore, but wake up periodically
+	 * to check if the child exited prematurely.
+	 */
+	for (;;) {
+		const struct timespec wait_period = { .tv_sec = 1 };
+		int status;
+
+		if (!sem_timedwait(sem, &wait_period))
+			return;
+
+		/* Child is still running, keep waiting. */
+		if (pid != waitpid(pid, &status, WNOHANG))
+			continue;
+
+		/*
+		 * Child is no longer running, which is not expected.
+		 *
+		 * If it exited with a non-zero status, we explicitly forward
+		 * the child's status in case it exited with KSFT_SKIP.
+		 */
+		if (WIFEXITED(status))
+			exit(WEXITSTATUS(status));
+		else
+			TEST_ASSERT(false, "Child exited unexpectedly");
+	}
+}
+
 int main(int argc, char **argv)
 {
 	uint32_t i;
@@ -148,7 +178,7 @@ int main(int argc, char **argv)
 			run_test(i); /* This function always exits */
 
 		pr_debug("%s: [%d] waiting semaphore\n", __func__, i);
-		sem_wait(sem);
+		wait_for_child_setup(pid);
 		r = (rand() % DELAY_US_MAX) + 1;
 		pr_debug("%s: [%d] waiting %dus\n", __func__, i, r);
 		usleep(r);
-- 
cgit v1.2.3


From c887d6a126dfc50b27872527615dd46cb3d96bc1 Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Wed, 19 May 2021 13:03:30 -0700
Subject: KVM: selftests: trivial comment/logging fixes

Some trivial fixes I found while touching related code in this series,
factored out into a separate commit for easier reviewing:

- s/gor/got/ and add a newline in demand_paging_test.c
- s/backing_src/src_type/ in a comment to be consistent with the real
  function signature in kvm_util.c

Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Message-Id: <20210519200339.829146-2-axelrasmussen@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/demand_paging_test.c | 2 +-
 tools/testing/selftests/kvm/lib/kvm_util.c       | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 5f7a229c3af1..9398ba6ef023 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -169,7 +169,7 @@ static void *uffd_handler_thread_fn(void *arg)
 		if (r == -1) {
 			if (errno == EAGAIN)
 				continue;
-			pr_info("Read of uffd gor errno %d", errno);
+			pr_info("Read of uffd got errno %d\n", errno);
 			return NULL;
 		}
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index ea3f0db85b3e..f4484e1edcfa 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -731,8 +731,8 @@ static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree,
  *
  * Input Args:
  *   vm - Virtual Machine
- *   backing_src - Storage source for this region.
- *                 NULL to use anonymous memory.
+ *   src_type - Storage source for this region.
+ *              NULL to use anonymous memory.
  *   guest_paddr - Starting guest physical address
  *   slot - KVM region slot
  *   npages - Number of physical pages
-- 
cgit v1.2.3


From 2aab4b355cbbe1deacfd9349729c43509042b557 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Tue, 11 May 2021 20:21:20 +0000
Subject: KVM: selftests: Print a message if /dev/kvm is missing

If a KVM selftest is run on a machine without /dev/kvm, it will exit
silently. Make it easy to tell what's happening by printing an error
message.

Opportunistically consolidate all codepaths that open /dev/kvm into a
single function so they all print the same message.

This slightly changes the semantics of vm_is_unrestricted_guest() by
changing a TEST_ASSERT() to exit(KSFT_SKIP). However
vm_is_unrestricted_guest() is only called in one place
(x86_64/mmio_warning_test.c) and that is to determine if the test should
be skipped or not.

Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210511202120.1371800-1-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h     |  1 +
 tools/testing/selftests/kvm/lib/kvm_util.c         | 46 +++++++++++++++-------
 tools/testing/selftests/kvm/lib/x86_64/processor.c | 16 ++------
 .../selftests/kvm/x86_64/get_msr_index_features.c  |  8 +---
 4 files changed, 39 insertions(+), 32 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 2e0d253dabd6..5d9b35d09251 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -77,6 +77,7 @@ struct vm_guest_mode_params {
 };
 extern const struct vm_guest_mode_params vm_guest_mode_params[];
 
+int open_kvm_dev_path_or_exit(void);
 int kvm_check_cap(long cap);
 int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
 int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index f4484e1edcfa..d00e49b73d68 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -31,6 +31,34 @@ static void *align(void *x, size_t size)
 	return (void *) (((size_t) x + mask) & ~mask);
 }
 
+/*
+ * Open KVM_DEV_PATH if available, otherwise exit the entire program.
+ *
+ * Input Args:
+ *   flags - The flags to pass when opening KVM_DEV_PATH.
+ *
+ * Return:
+ *   The opened file descriptor of /dev/kvm.
+ */
+static int _open_kvm_dev_path_or_exit(int flags)
+{
+	int fd;
+
+	fd = open(KVM_DEV_PATH, flags);
+	if (fd < 0) {
+		print_skip("%s not available, is KVM loaded? (errno: %d)",
+			   KVM_DEV_PATH, errno);
+		exit(KSFT_SKIP);
+	}
+
+	return fd;
+}
+
+int open_kvm_dev_path_or_exit(void)
+{
+	return _open_kvm_dev_path_or_exit(O_RDONLY);
+}
+
 /*
  * Capability
  *
@@ -52,10 +80,7 @@ int kvm_check_cap(long cap)
 	int ret;
 	int kvm_fd;
 
-	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	if (kvm_fd < 0)
-		exit(KSFT_SKIP);
-
+	kvm_fd = open_kvm_dev_path_or_exit();
 	ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap);
 	TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n"
 		"  rc: %i errno: %i", ret, errno);
@@ -128,9 +153,7 @@ void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size)
 
 static void vm_open(struct kvm_vm *vm, int perm)
 {
-	vm->kvm_fd = open(KVM_DEV_PATH, perm);
-	if (vm->kvm_fd < 0)
-		exit(KSFT_SKIP);
+	vm->kvm_fd = _open_kvm_dev_path_or_exit(perm);
 
 	if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
 		print_skip("immediate_exit not available");
@@ -996,9 +1019,7 @@ static int vcpu_mmap_sz(void)
 {
 	int dev_fd, ret;
 
-	dev_fd = open(KVM_DEV_PATH, O_RDONLY);
-	if (dev_fd < 0)
-		exit(KSFT_SKIP);
+	dev_fd = open_kvm_dev_path_or_exit();
 
 	ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
 	TEST_ASSERT(ret >= sizeof(struct kvm_run),
@@ -2091,10 +2112,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm)
 
 	if (vm == NULL) {
 		/* Ensure that the KVM vendor-specific module is loaded. */
-		f = fopen(KVM_DEV_PATH, "r");
-		TEST_ASSERT(f != NULL, "Error in opening KVM dev file: %d",
-			    errno);
-		fclose(f);
+		close(open_kvm_dev_path_or_exit());
 	}
 
 	f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r");
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index a8906e60a108..efe235044421 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -657,9 +657,7 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
 		return cpuid;
 
 	cpuid = allocate_kvm_cpuid2();
-	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	if (kvm_fd < 0)
-		exit(KSFT_SKIP);
+	kvm_fd = open_kvm_dev_path_or_exit();
 
 	ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
 	TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
@@ -691,9 +689,7 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index)
 
 	buffer.header.nmsrs = 1;
 	buffer.entry.index = msr_index;
-	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	if (kvm_fd < 0)
-		exit(KSFT_SKIP);
+	kvm_fd = open_kvm_dev_path_or_exit();
 
 	r = ioctl(kvm_fd, KVM_GET_MSRS, &buffer.header);
 	TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n"
@@ -986,9 +982,7 @@ struct kvm_msr_list *kvm_get_msr_index_list(void)
 	struct kvm_msr_list *list;
 	int nmsrs, r, kvm_fd;
 
-	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	if (kvm_fd < 0)
-		exit(KSFT_SKIP);
+	kvm_fd = open_kvm_dev_path_or_exit();
 
 	nmsrs = kvm_get_num_msrs_fd(kvm_fd);
 	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
@@ -1312,9 +1306,7 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void)
 		return cpuid;
 
 	cpuid = allocate_kvm_cpuid2();
-	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	if (kvm_fd < 0)
-		exit(KSFT_SKIP);
+	kvm_fd = open_kvm_dev_path_or_exit();
 
 	ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
 	TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_HV_CPUID failed %d %d\n",
diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c
index cb953df4d7d0..8aed0db1331d 100644
--- a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c
+++ b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c
@@ -37,9 +37,7 @@ static void test_get_msr_index(void)
 	int old_res, res, kvm_fd, r;
 	struct kvm_msr_list *list;
 
-	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	if (kvm_fd < 0)
-		exit(KSFT_SKIP);
+	kvm_fd = open_kvm_dev_path_or_exit();
 
 	old_res = kvm_num_index_msrs(kvm_fd, 0);
 	TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0");
@@ -101,9 +99,7 @@ static void test_get_msr_feature(void)
 	int res, old_res, i, kvm_fd;
 	struct kvm_msr_list *feature_list;
 
-	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	if (kvm_fd < 0)
-		exit(KSFT_SKIP);
+	kvm_fd = open_kvm_dev_path_or_exit();
 
 	old_res = kvm_num_feature_msrs(kvm_fd, 0);
 	TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0");
-- 
cgit v1.2.3


From 25408e5a0246048e3e36d2cd513565ebcc481f51 Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Wed, 19 May 2021 13:03:31 -0700
Subject: KVM: selftests: simplify setup_demand_paging error handling

A small cleanup. Our caller writes:

  r = setup_demand_paging(...);
  if (r < 0) exit(-r);

Since we're just going to exit anyway, instead of returning an error we
can just re-use TEST_ASSERT. This makes the caller simpler, as well as
the function itself - no need to write our branches, etc.

Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Message-Id: <20210519200339.829146-3-axelrasmussen@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/demand_paging_test.c | 50 +++++++++---------------
 1 file changed, 18 insertions(+), 32 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 9398ba6ef023..8ce53488d6af 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -9,6 +9,7 @@
 
 #define _GNU_SOURCE /* for pipe2 */
 
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <time.h>
@@ -198,42 +199,32 @@ static void *uffd_handler_thread_fn(void *arg)
 	return NULL;
 }
 
-static int setup_demand_paging(struct kvm_vm *vm,
-			       pthread_t *uffd_handler_thread, int pipefd,
-			       useconds_t uffd_delay,
-			       struct uffd_handler_args *uffd_args,
-			       void *hva, uint64_t len)
+static void setup_demand_paging(struct kvm_vm *vm,
+				pthread_t *uffd_handler_thread, int pipefd,
+				useconds_t uffd_delay,
+				struct uffd_handler_args *uffd_args,
+				void *hva, uint64_t len)
 {
 	int uffd;
 	struct uffdio_api uffdio_api;
 	struct uffdio_register uffdio_register;
 
 	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
-	if (uffd == -1) {
-		pr_info("uffd creation failed\n");
-		return -1;
-	}
+	TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno);
 
 	uffdio_api.api = UFFD_API;
 	uffdio_api.features = 0;
-	if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) {
-		pr_info("ioctl uffdio_api failed\n");
-		return -1;
-	}
+	TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1,
+		    "ioctl UFFDIO_API failed: %" PRIu64,
+		    (uint64_t)uffdio_api.api);
 
 	uffdio_register.range.start = (uint64_t)hva;
 	uffdio_register.range.len = len;
 	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
-	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) {
-		pr_info("ioctl uffdio_register failed\n");
-		return -1;
-	}
-
-	if ((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) !=
-			UFFD_API_RANGE_IOCTLS) {
-		pr_info("unexpected userfaultfd ioctl set\n");
-		return -1;
-	}
+	TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1,
+		    "ioctl UFFDIO_REGISTER failed");
+	TEST_ASSERT((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) ==
+		    UFFD_API_RANGE_IOCTLS, "unexpected userfaultfd ioctl set");
 
 	uffd_args->uffd = uffd;
 	uffd_args->pipefd = pipefd;
@@ -243,8 +234,6 @@ static int setup_demand_paging(struct kvm_vm *vm,
 
 	PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
 		       hva, hva + len);
-
-	return 0;
 }
 
 struct test_params {
@@ -321,13 +310,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 				  O_CLOEXEC | O_NONBLOCK);
 			TEST_ASSERT(!r, "Failed to set up pipefd");
 
-			r = setup_demand_paging(vm,
-						&uffd_handler_threads[vcpu_id],
-						pipefds[vcpu_id * 2],
-						p->uffd_delay, &uffd_args[vcpu_id],
-						vcpu_hva, vcpu_mem_size);
-			if (r < 0)
-				exit(-r);
+			setup_demand_paging(vm, &uffd_handler_threads[vcpu_id],
+					    pipefds[vcpu_id * 2], p->uffd_delay,
+					    &uffd_args[vcpu_id], vcpu_hva,
+					    vcpu_mem_size);
 		}
 	}
 
-- 
cgit v1.2.3


From 32ffa4f71e10009498ae6b54da65ab316db967bd Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Wed, 19 May 2021 13:03:33 -0700
Subject: KVM: selftests: compute correct demand paging size

This is a preparatory commit needed before we can use different kinds of
backing pages for guest memory.

Previously, we used perf_test_args.host_page_size, which is the host's
native page size (commonly 4K). For VM_MEM_SRC_ANONYMOUS this turns out
to be okay, but in a follow-up commit we want to allow using different
kinds of backing memory.

Take VM_MEM_SRC_ANONYMOUS_HUGETLB for example. Without this change, if
we used that backing page type, when we issued a UFFDIO_COPY ioctl we'd
only do so with 4K, rather than the full 2M of a backing hugepage. In
this case, UFFDIO_COPY returns -EINVAL (__mcopy_atomic_hugetlb checks
the size).

Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Message-Id: <20210519200339.829146-5-axelrasmussen@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/demand_paging_test.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 8ce53488d6af..e6582f504c0f 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -39,6 +39,7 @@
 
 static int nr_vcpus = 1;
 static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+static size_t demand_paging_size;
 static char *guest_data_prototype;
 
 static void *vcpu_worker(void *data)
@@ -84,7 +85,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr)
 
 	copy.src = (uint64_t)guest_data_prototype;
 	copy.dst = addr;
-	copy.len = perf_test_args.host_page_size;
+	copy.len = demand_paging_size;
 	copy.mode = 0;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
@@ -101,7 +102,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr)
 	PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid,
 		       timespec_to_ns(ts_diff));
 	PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n",
-		       perf_test_args.host_page_size, addr, tid);
+		       demand_paging_size, addr, tid);
 
 	return 0;
 }
@@ -260,10 +261,12 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	perf_test_args.wr_fract = 1;
 
-	guest_data_prototype = malloc(perf_test_args.host_page_size);
+	demand_paging_size = get_backing_src_pagesz(VM_MEM_SRC_ANONYMOUS);
+
+	guest_data_prototype = malloc(demand_paging_size);
 	TEST_ASSERT(guest_data_prototype,
 		    "Failed to allocate buffer for guest data pattern");
-	memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size);
+	memset(guest_data_prototype, 0xAB, demand_paging_size);
 
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-- 
cgit v1.2.3


From 0368c2c1b422c94968b5286f289aed7fe6af93c2 Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Wed, 19 May 2021 13:03:34 -0700
Subject: KVM: selftests: allow different backing source types

Add an argument which lets us specify a different backing memory type
for the test. The default is just to use anonymous, matching existing
behavior.

This is in preparation for testing UFFD minor faults. For that, we'll
need to use a new backing memory type which is setup with MAP_SHARED.

Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Message-Id: <20210519200339.829146-6-axelrasmussen@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/demand_paging_test.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index e6582f504c0f..8c03484a5784 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -240,6 +240,7 @@ static void setup_demand_paging(struct kvm_vm *vm,
 struct test_params {
 	bool use_uffd;
 	useconds_t uffd_delay;
+	enum vm_mem_backing_src_type src_type;
 	bool partition_vcpu_memory_access;
 };
 
@@ -257,11 +258,11 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int r;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
-				 VM_MEM_SRC_ANONYMOUS);
+				 p->src_type);
 
 	perf_test_args.wr_fract = 1;
 
-	demand_paging_size = get_backing_src_pagesz(VM_MEM_SRC_ANONYMOUS);
+	demand_paging_size = get_backing_src_pagesz(p->src_type);
 
 	guest_data_prototype = malloc(demand_paging_size);
 	TEST_ASSERT(guest_data_prototype,
@@ -377,7 +378,7 @@ static void help(char *name)
 {
 	puts("");
 	printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n"
-	       "          [-b memory] [-v vcpus] [-o]\n", name);
+	       "          [-b memory] [-t type] [-v vcpus] [-o]\n", name);
 	guest_modes_help();
 	printf(" -u: use User Fault FD to handle vCPU page\n"
 	       "     faults.\n");
@@ -387,6 +388,8 @@ static void help(char *name)
 	printf(" -b: specify the size of the memory region which should be\n"
 	       "     demand paged by each vCPU. e.g. 10M or 3G.\n"
 	       "     Default: 1G\n");
+	printf(" -t: The type of backing memory to use. Default: anonymous\n");
+	backing_src_help();
 	printf(" -v: specify the number of vCPUs to run.\n");
 	printf(" -o: Overlap guest memory accesses instead of partitioning\n"
 	       "     them into a separate region of memory for each vCPU.\n");
@@ -398,13 +401,14 @@ int main(int argc, char *argv[])
 {
 	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
 	struct test_params p = {
+		.src_type = VM_MEM_SRC_ANONYMOUS,
 		.partition_vcpu_memory_access = true,
 	};
 	int opt;
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:ud:b:v:o")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:ud:b:t:v:o")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
@@ -419,6 +423,9 @@ int main(int argc, char *argv[])
 		case 'b':
 			guest_percpu_mem_size = parse_size(optarg);
 			break;
+		case 't':
+			p.src_type = parse_backing_src_type(optarg);
+			break;
 		case 'v':
 			nr_vcpus = atoi(optarg);
 			TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
-- 
cgit v1.2.3


From b3784bc28ccc0d9b44d265a1d947c8766295ba00 Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Wed, 19 May 2021 13:03:35 -0700
Subject: KVM: selftests: refactor vm_mem_backing_src_type flags

Each struct vm_mem_backing_src_alias has a flags field, which denotes
the flags used to mmap() an area of that type. Previously, this field
never included MAP_PRIVATE | MAP_ANONYMOUS, because
vm_userspace_mem_region_add assumed that *all* types would always use
those flags, and so it hardcoded them.

In a follow-up commit, we'll add a new type: shmem. Areas of this type
must not have MAP_PRIVATE | MAP_ANONYMOUS, and instead they must have
MAP_SHARED.

So, refactor things. Make it so that the flags field of
struct vm_mem_backing_src_alias really is a complete set of flags, and
don't add in any extras in vm_userspace_mem_region_add. This will let us
easily tack on shmem.

Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Message-Id: <20210519200339.829146-7-axelrasmussen@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/kvm_util.c  |  3 +--
 tools/testing/selftests/kvm/lib/test_util.c | 35 ++++++++++++++++-------------
 2 files changed, 20 insertions(+), 18 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index d00e49b73d68..491be22b410c 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -849,8 +849,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 
 	region->mmap_start = mmap(NULL, region->mmap_size,
 				  PROT_READ | PROT_WRITE,
-				  MAP_PRIVATE | MAP_ANONYMOUS
-				  | vm_mem_backing_src_alias(src_type)->flag,
+				  vm_mem_backing_src_alias(src_type)->flag,
 				  -1, 0);
 	TEST_ASSERT(region->mmap_start != MAP_FAILED,
 		    "test_malloc failed, mmap_start: %p errno: %i",
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 63d2bc7d757b..06ddde068736 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -168,70 +168,73 @@ size_t get_def_hugetlb_pagesz(void)
 
 const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i)
 {
+	static const int anon_flags = MAP_PRIVATE | MAP_ANONYMOUS;
+	static const int anon_huge_flags = anon_flags | MAP_HUGETLB;
+
 	static const struct vm_mem_backing_src_alias aliases[] = {
 		[VM_MEM_SRC_ANONYMOUS] = {
 			.name = "anonymous",
-			.flag = 0,
+			.flag = anon_flags,
 		},
 		[VM_MEM_SRC_ANONYMOUS_THP] = {
 			.name = "anonymous_thp",
-			.flag = 0,
+			.flag = anon_flags,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB] = {
 			.name = "anonymous_hugetlb",
-			.flag = MAP_HUGETLB,
+			.flag = anon_huge_flags,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB] = {
 			.name = "anonymous_hugetlb_16kb",
-			.flag = MAP_HUGETLB | MAP_HUGE_16KB,
+			.flag = anon_huge_flags | MAP_HUGE_16KB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB] = {
 			.name = "anonymous_hugetlb_64kb",
-			.flag = MAP_HUGETLB | MAP_HUGE_64KB,
+			.flag = anon_huge_flags | MAP_HUGE_64KB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB] = {
 			.name = "anonymous_hugetlb_512kb",
-			.flag = MAP_HUGETLB | MAP_HUGE_512KB,
+			.flag = anon_huge_flags | MAP_HUGE_512KB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB] = {
 			.name = "anonymous_hugetlb_1mb",
-			.flag = MAP_HUGETLB | MAP_HUGE_1MB,
+			.flag = anon_huge_flags | MAP_HUGE_1MB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB] = {
 			.name = "anonymous_hugetlb_2mb",
-			.flag = MAP_HUGETLB | MAP_HUGE_2MB,
+			.flag = anon_huge_flags | MAP_HUGE_2MB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB] = {
 			.name = "anonymous_hugetlb_8mb",
-			.flag = MAP_HUGETLB | MAP_HUGE_8MB,
+			.flag = anon_huge_flags | MAP_HUGE_8MB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB] = {
 			.name = "anonymous_hugetlb_16mb",
-			.flag = MAP_HUGETLB | MAP_HUGE_16MB,
+			.flag = anon_huge_flags | MAP_HUGE_16MB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB] = {
 			.name = "anonymous_hugetlb_32mb",
-			.flag = MAP_HUGETLB | MAP_HUGE_32MB,
+			.flag = anon_huge_flags | MAP_HUGE_32MB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB] = {
 			.name = "anonymous_hugetlb_256mb",
-			.flag = MAP_HUGETLB | MAP_HUGE_256MB,
+			.flag = anon_huge_flags | MAP_HUGE_256MB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB] = {
 			.name = "anonymous_hugetlb_512mb",
-			.flag = MAP_HUGETLB | MAP_HUGE_512MB,
+			.flag = anon_huge_flags | MAP_HUGE_512MB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB] = {
 			.name = "anonymous_hugetlb_1gb",
-			.flag = MAP_HUGETLB | MAP_HUGE_1GB,
+			.flag = anon_huge_flags | MAP_HUGE_1GB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB] = {
 			.name = "anonymous_hugetlb_2gb",
-			.flag = MAP_HUGETLB | MAP_HUGE_2GB,
+			.flag = anon_huge_flags | MAP_HUGE_2GB,
 		},
 		[VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB] = {
 			.name = "anonymous_hugetlb_16gb",
-			.flag = MAP_HUGETLB | MAP_HUGE_16GB,
+			.flag = anon_huge_flags | MAP_HUGE_16GB,
 		},
 	};
 	_Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES,
-- 
cgit v1.2.3


From c9befd5958fdf8913db69049d47b6ac1d970af03 Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Wed, 19 May 2021 13:03:36 -0700
Subject: KVM: selftests: add shmem backing source type

This lets us run the demand paging test on top of a shmem-backed area.
In follow-up commits, we'll 1) leverage this new capability to create an
alias mapping, and then 2) use the alias mapping to exercise UFFD minor
faults.

Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Message-Id: <20210519200339.829146-8-axelrasmussen@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/test_util.h |  1 +
 tools/testing/selftests/kvm/lib/kvm_util.c      | 17 ++++++++++++++++-
 tools/testing/selftests/kvm/lib/test_util.c     |  5 +++++
 3 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index fade3130eb01..7377f00469ef 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -84,6 +84,7 @@ enum vm_mem_backing_src_type {
 	VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB,
 	VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB,
 	VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB,
+	VM_MEM_SRC_SHMEM,
 	NUM_SRC_TYPES,
 };
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 491be22b410c..bc50ca6390d3 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -847,10 +847,25 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	if (alignment > 1)
 		region->mmap_size += alignment;
 
+	region->fd = -1;
+	if (src_type == VM_MEM_SRC_SHMEM) {
+		region->fd = memfd_create("kvm_selftest", MFD_CLOEXEC);
+		TEST_ASSERT(region->fd != -1,
+			    "memfd_create failed, errno: %i", errno);
+
+		ret = ftruncate(region->fd, region->mmap_size);
+		TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno);
+
+		ret = fallocate(region->fd,
+				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0,
+				region->mmap_size);
+		TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno);
+	}
+
 	region->mmap_start = mmap(NULL, region->mmap_size,
 				  PROT_READ | PROT_WRITE,
 				  vm_mem_backing_src_alias(src_type)->flag,
-				  -1, 0);
+				  region->fd, 0);
 	TEST_ASSERT(region->mmap_start != MAP_FAILED,
 		    "test_malloc failed, mmap_start: %p errno: %i",
 		    region->mmap_start, errno);
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 06ddde068736..c7a265da5090 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -236,6 +236,10 @@ const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i)
 			.name = "anonymous_hugetlb_16gb",
 			.flag = anon_huge_flags | MAP_HUGE_16GB,
 		},
+		[VM_MEM_SRC_SHMEM] = {
+			.name = "shmem",
+			.flag = MAP_SHARED,
+		},
 	};
 	_Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES,
 		       "Missing new backing src types?");
@@ -253,6 +257,7 @@ size_t get_backing_src_pagesz(uint32_t i)
 
 	switch (i) {
 	case VM_MEM_SRC_ANONYMOUS:
+	case VM_MEM_SRC_SHMEM:
 		return getpagesize();
 	case VM_MEM_SRC_ANONYMOUS_THP:
 		return get_trans_hugepagesz();
-- 
cgit v1.2.3


From 94f3f2b31a8a9e8bd30bf6f4903ff84acc612e0e Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Wed, 19 May 2021 13:03:37 -0700
Subject: KVM: selftests: create alias mappings when using shared memory

When a memory region is added with a src_type specifying that it should
use some kind of shared memory, also create an alias mapping to the same
underlying physical pages.

And, add an API so tests can get access to these alias addresses.
Basically, for a guest physical address, let us look up the analogous
host *alias* address.

In a future commit, we'll modify the demand paging test to take
advantage of this to exercise UFFD minor faults. The idea is, we
pre-fault the underlying pages *via the alias*. When the *guest*
faults, it gets a "minor" fault (PTEs don't exist yet, but a page is
already in the page cache). Then, the userfaultfd theads can handle the
fault: they could potentially modify the underlying memory *via the
alias* if they wanted to, and then they install the PTEs and let the
guest carry on via a UFFDIO_CONTINUE ioctl.

Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Message-Id: <20210519200339.829146-9-axelrasmussen@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h     |  1 +
 tools/testing/selftests/kvm/lib/kvm_util.c         | 49 ++++++++++++++++++++++
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |  2 +
 3 files changed, 52 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 5d9b35d09251..fcd8e3855111 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -147,6 +147,7 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
 void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
 vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
+void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa);
 
 /*
  * Address Guest Virtual to Guest Physical
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index bc50ca6390d3..f62780719176 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -903,6 +903,19 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region);
 	vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region);
 	hash_add(vm->regions.slot_hash, &region->slot_node, slot);
+
+	/* If shared memory, create an alias. */
+	if (region->fd >= 0) {
+		region->mmap_alias = mmap(NULL, region->mmap_size,
+					  PROT_READ | PROT_WRITE,
+					  vm_mem_backing_src_alias(src_type)->flag,
+					  region->fd, 0);
+		TEST_ASSERT(region->mmap_alias != MAP_FAILED,
+			    "mmap of alias failed, errno: %i", errno);
+
+		/* Align host alias address */
+		region->host_alias = align(region->mmap_alias, alignment);
+	}
 }
 
 /*
@@ -1333,6 +1346,42 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
 	return -1;
 }
 
+/*
+ * Address VM physical to Host Virtual *alias*.
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   gpa - VM physical address
+ *
+ * Output Args: None
+ *
+ * Return:
+ *   Equivalent address within the host virtual *alias* area, or NULL
+ *   (without failing the test) if the guest memory is not shared (so
+ *   no alias exists).
+ *
+ * When vm_create() and related functions are called with a shared memory
+ * src_type, we also create a writable, shared alias mapping of the
+ * underlying guest memory. This allows the host to manipulate guest memory
+ * without mapping that memory in the guest's address space. And, for
+ * userfaultfd-based demand paging, we can do so without triggering userfaults.
+ */
+void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa)
+{
+	struct userspace_mem_region *region;
+	uintptr_t offset;
+
+	region = userspace_mem_region_find(vm, gpa, gpa);
+	if (!region)
+		return NULL;
+
+	if (!region->host_alias)
+		return NULL;
+
+	offset = gpa - region->region.guest_phys_addr;
+	return (void *) ((uintptr_t) region->host_alias + offset);
+}
+
 /*
  * VM Create IRQ Chip
  *
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index b30e8c7b119b..a03febc24ba6 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -19,7 +19,9 @@ struct userspace_mem_region {
 	int fd;
 	off_t offset;
 	void *host_mem;
+	void *host_alias;
 	void *mmap_start;
+	void *mmap_alias;
 	size_t mmap_size;
 	struct rb_node gpa_node;
 	struct rb_node hva_node;
-- 
cgit v1.2.3


From a4b9722a5996017264feb19ebe86efe4380f7afb Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Wed, 19 May 2021 13:03:38 -0700
Subject: KVM: selftests: allow using UFFD minor faults for demand paging

UFFD handling of MINOR faults is a new feature whose use case is to
speed up demand paging (compared to MISSING faults). So, it's
interesting to let this selftest exercise this new mode.

Modify the demand paging test to have the option of using UFFD minor
faults, as opposed to missing faults. Now, when turning on userfaultfd
with '-u', the desired mode has to be specified ("MISSING" or "MINOR").

If we're in minor mode, before registering, prefault via the *alias*.
This way, the guest will trigger minor faults, instead of missing
faults, and we can UFFDIO_CONTINUE to resolve them.

Modify the page fault handler function to use the right ioctl depending
on the mode we're running in. In MINOR mode, use UFFDIO_CONTINUE.

Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Message-Id: <20210519200339.829146-10-axelrasmussen@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/demand_paging_test.c | 112 ++++++++++++++++-------
 1 file changed, 79 insertions(+), 33 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 8c03484a5784..fcba527c29a6 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -73,33 +73,48 @@ static void *vcpu_worker(void *data)
 	return NULL;
 }
 
-static int handle_uffd_page_request(int uffd, uint64_t addr)
+static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
 {
-	pid_t tid;
+	pid_t tid = syscall(__NR_gettid);
 	struct timespec start;
 	struct timespec ts_diff;
-	struct uffdio_copy copy;
 	int r;
 
-	tid = syscall(__NR_gettid);
+	clock_gettime(CLOCK_MONOTONIC, &start);
 
-	copy.src = (uint64_t)guest_data_prototype;
-	copy.dst = addr;
-	copy.len = demand_paging_size;
-	copy.mode = 0;
+	if (uffd_mode == UFFDIO_REGISTER_MODE_MISSING) {
+		struct uffdio_copy copy;
 
-	clock_gettime(CLOCK_MONOTONIC, &start);
+		copy.src = (uint64_t)guest_data_prototype;
+		copy.dst = addr;
+		copy.len = demand_paging_size;
+		copy.mode = 0;
+
+		r = ioctl(uffd, UFFDIO_COPY, &copy);
+		if (r == -1) {
+			pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d with errno: %d\n",
+				addr, tid, errno);
+			return r;
+		}
+	} else if (uffd_mode == UFFDIO_REGISTER_MODE_MINOR) {
+		struct uffdio_continue cont = {0};
+
+		cont.range.start = addr;
+		cont.range.len = demand_paging_size;
 
-	r = ioctl(uffd, UFFDIO_COPY, &copy);
-	if (r == -1) {
-		pr_info("Failed Paged in 0x%lx from thread %d with errno: %d\n",
-			addr, tid, errno);
-		return r;
+		r = ioctl(uffd, UFFDIO_CONTINUE, &cont);
+		if (r == -1) {
+			pr_info("Failed UFFDIO_CONTINUE in 0x%lx from thread %d with errno: %d\n",
+				addr, tid, errno);
+			return r;
+		}
+	} else {
+		TEST_FAIL("Invalid uffd mode %d", uffd_mode);
 	}
 
 	ts_diff = timespec_elapsed(start);
 
-	PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid,
+	PER_PAGE_DEBUG("UFFD page-in %d \t%ld ns\n", tid,
 		       timespec_to_ns(ts_diff));
 	PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n",
 		       demand_paging_size, addr, tid);
@@ -110,6 +125,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr)
 bool quit_uffd_thread;
 
 struct uffd_handler_args {
+	int uffd_mode;
 	int uffd;
 	int pipefd;
 	useconds_t delay;
@@ -186,7 +202,7 @@ static void *uffd_handler_thread_fn(void *arg)
 		if (delay)
 			usleep(delay);
 		addr =  msg.arg.pagefault.address;
-		r = handle_uffd_page_request(uffd, addr);
+		r = handle_uffd_page_request(uffd_args->uffd_mode, uffd, addr);
 		if (r < 0)
 			return NULL;
 		pages++;
@@ -202,13 +218,32 @@ static void *uffd_handler_thread_fn(void *arg)
 
 static void setup_demand_paging(struct kvm_vm *vm,
 				pthread_t *uffd_handler_thread, int pipefd,
-				useconds_t uffd_delay,
+				int uffd_mode, useconds_t uffd_delay,
 				struct uffd_handler_args *uffd_args,
-				void *hva, uint64_t len)
+				void *hva, void *alias, uint64_t len)
 {
+	bool is_minor = (uffd_mode == UFFDIO_REGISTER_MODE_MINOR);
 	int uffd;
 	struct uffdio_api uffdio_api;
 	struct uffdio_register uffdio_register;
+	uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY;
+
+	PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n",
+		       is_minor ? "MINOR" : "MISSING",
+		       is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY");
+
+	/* In order to get minor faults, prefault via the alias. */
+	if (is_minor) {
+		size_t p;
+
+		expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE;
+
+		TEST_ASSERT(alias != NULL, "Alias required for minor faults");
+		for (p = 0; p < (len / demand_paging_size); ++p) {
+			memcpy(alias + (p * demand_paging_size),
+			       guest_data_prototype, demand_paging_size);
+		}
+	}
 
 	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
 	TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno);
@@ -221,12 +256,13 @@ static void setup_demand_paging(struct kvm_vm *vm,
 
 	uffdio_register.range.start = (uint64_t)hva;
 	uffdio_register.range.len = len;
-	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+	uffdio_register.mode = uffd_mode;
 	TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1,
 		    "ioctl UFFDIO_REGISTER failed");
-	TEST_ASSERT((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) ==
-		    UFFD_API_RANGE_IOCTLS, "unexpected userfaultfd ioctl set");
+	TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) ==
+		    expected_ioctls, "missing userfaultfd ioctls");
 
+	uffd_args->uffd_mode = uffd_mode;
 	uffd_args->uffd = uffd;
 	uffd_args->pipefd = pipefd;
 	uffd_args->delay = uffd_delay;
@@ -238,7 +274,7 @@ static void setup_demand_paging(struct kvm_vm *vm,
 }
 
 struct test_params {
-	bool use_uffd;
+	int uffd_mode;
 	useconds_t uffd_delay;
 	enum vm_mem_backing_src_type src_type;
 	bool partition_vcpu_memory_access;
@@ -275,7 +311,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
 			      p->partition_vcpu_memory_access);
 
-	if (p->use_uffd) {
+	if (p->uffd_mode) {
 		uffd_handler_threads =
 			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
 		TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
@@ -289,6 +325,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
 			vm_paddr_t vcpu_gpa;
 			void *vcpu_hva;
+			void *vcpu_alias;
 			uint64_t vcpu_mem_size;
 
 
@@ -303,8 +340,9 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
 				       vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size);
 
-			/* Cache the HVA pointer of the region */
+			/* Cache the host addresses of the region */
 			vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
+			vcpu_alias = addr_gpa2alias(vm, vcpu_gpa);
 
 			/*
 			 * Set up user fault fd to handle demand paging
@@ -315,8 +353,9 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			TEST_ASSERT(!r, "Failed to set up pipefd");
 
 			setup_demand_paging(vm, &uffd_handler_threads[vcpu_id],
-					    pipefds[vcpu_id * 2], p->uffd_delay,
-					    &uffd_args[vcpu_id], vcpu_hva,
+					    pipefds[vcpu_id * 2], p->uffd_mode,
+					    p->uffd_delay, &uffd_args[vcpu_id],
+					    vcpu_hva, vcpu_alias,
 					    vcpu_mem_size);
 		}
 	}
@@ -345,7 +384,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	pr_info("All vCPU threads joined\n");
 
-	if (p->use_uffd) {
+	if (p->uffd_mode) {
 		char c;
 
 		/* Tell the user fault fd handler threads to quit */
@@ -367,7 +406,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	free(guest_data_prototype);
 	free(vcpu_threads);
-	if (p->use_uffd) {
+	if (p->uffd_mode) {
 		free(uffd_handler_threads);
 		free(uffd_args);
 		free(pipefds);
@@ -377,11 +416,11 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 static void help(char *name)
 {
 	puts("");
-	printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n"
+	printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n"
 	       "          [-b memory] [-t type] [-v vcpus] [-o]\n", name);
 	guest_modes_help();
-	printf(" -u: use User Fault FD to handle vCPU page\n"
-	       "     faults.\n");
+	printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n"
+	       "     UFFD registration mode: 'MISSING' or 'MINOR'.\n");
 	printf(" -d: add a delay in usec to the User Fault\n"
 	       "     FD handler to simulate demand paging\n"
 	       "     overheads. Ignored without -u.\n");
@@ -408,13 +447,17 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:ud:b:t:v:o")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
 			break;
 		case 'u':
-			p.use_uffd = true;
+			if (!strcmp("MISSING", optarg))
+				p.uffd_mode = UFFDIO_REGISTER_MODE_MISSING;
+			else if (!strcmp("MINOR", optarg))
+				p.uffd_mode = UFFDIO_REGISTER_MODE_MINOR;
+			TEST_ASSERT(p.uffd_mode, "UFFD mode must be 'MISSING' or 'MINOR'.");
 			break;
 		case 'd':
 			p.uffd_delay = strtoul(optarg, NULL, 0);
@@ -441,6 +484,9 @@ int main(int argc, char *argv[])
 		}
 	}
 
+	TEST_ASSERT(p.uffd_mode != UFFDIO_REGISTER_MODE_MINOR || p.src_type == VM_MEM_SRC_SHMEM,
+		    "userfaultfd MINOR mode requires shared memory; pick a different -t");
+
 	for_each_guest_mode(run_test, &p);
 
 	return 0;
-- 
cgit v1.2.3


From 33090a884da5e9760f11441ac269f754375f80f5 Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Wed, 19 May 2021 13:03:39 -0700
Subject: KVM: selftests: add shared hugetlbfs backing source type

This lets us run the demand paging test on top of a shared
hugetlbfs-backed area. The "shared" is key, as this allows us to
exercise userfaultfd minor faults on hugetlbfs.

Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Message-Id: <20210519200339.829146-11-axelrasmussen@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/demand_paging_test.c |  6 ++++--
 tools/testing/selftests/kvm/include/test_util.h  | 11 +++++++++++
 tools/testing/selftests/kvm/lib/kvm_util.c       |  9 +++++++--
 tools/testing/selftests/kvm/lib/test_util.c      | 11 +++++++++++
 4 files changed, 33 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index fcba527c29a6..b74704305835 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -484,8 +484,10 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	TEST_ASSERT(p.uffd_mode != UFFDIO_REGISTER_MODE_MINOR || p.src_type == VM_MEM_SRC_SHMEM,
-		    "userfaultfd MINOR mode requires shared memory; pick a different -t");
+	if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR &&
+	    !backing_src_is_shared(p.src_type)) {
+		TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t");
+	}
 
 	for_each_guest_mode(run_test, &p);
 
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 7377f00469ef..d79be15dd3d2 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -17,6 +17,7 @@
 #include <errno.h>
 #include <unistd.h>
 #include <fcntl.h>
+#include <sys/mman.h>
 #include "kselftest.h"
 
 static inline int _no_printf(const char *format, ...) { return 0; }
@@ -85,6 +86,7 @@ enum vm_mem_backing_src_type {
 	VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB,
 	VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB,
 	VM_MEM_SRC_SHMEM,
+	VM_MEM_SRC_SHARED_HUGETLB,
 	NUM_SRC_TYPES,
 };
 
@@ -101,4 +103,13 @@ size_t get_backing_src_pagesz(uint32_t i);
 void backing_src_help(void);
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
 
+/*
+ * Whether or not the given source type is shared memory (as opposed to
+ * anonymous).
+ */
+static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t)
+{
+	return vm_mem_backing_src_alias(t)->flag & MAP_SHARED;
+}
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index f62780719176..28e528c19d28 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -848,8 +848,13 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		region->mmap_size += alignment;
 
 	region->fd = -1;
-	if (src_type == VM_MEM_SRC_SHMEM) {
-		region->fd = memfd_create("kvm_selftest", MFD_CLOEXEC);
+	if (backing_src_is_shared(src_type)) {
+		int memfd_flags = MFD_CLOEXEC;
+
+		if (src_type == VM_MEM_SRC_SHARED_HUGETLB)
+			memfd_flags |= MFD_HUGETLB;
+
+		region->fd = memfd_create("kvm_selftest", memfd_flags);
 		TEST_ASSERT(region->fd != -1,
 			    "memfd_create failed, errno: %i", errno);
 
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index c7a265da5090..6ad6c8276b2e 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -240,6 +240,16 @@ const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i)
 			.name = "shmem",
 			.flag = MAP_SHARED,
 		},
+		[VM_MEM_SRC_SHARED_HUGETLB] = {
+			.name = "shared_hugetlb",
+			/*
+			 * No MAP_HUGETLB, we use MFD_HUGETLB instead. Since
+			 * we're using "file backed" memory, we need to specify
+			 * this when the FD is created, not when the area is
+			 * mapped.
+			 */
+			.flag = MAP_SHARED,
+		},
 	};
 	_Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES,
 		       "Missing new backing src types?");
@@ -262,6 +272,7 @@ size_t get_backing_src_pagesz(uint32_t i)
 	case VM_MEM_SRC_ANONYMOUS_THP:
 		return get_trans_hugepagesz();
 	case VM_MEM_SRC_ANONYMOUS_HUGETLB:
+	case VM_MEM_SRC_SHARED_HUGETLB:
 		return get_def_hugetlb_pagesz();
 	default:
 		return MAP_HUGE_PAGE_SIZE(flag);
-- 
cgit v1.2.3


From fb1070d18edb37daf3979662975bc54625a19953 Mon Sep 17 00:00:00 2001
From: Joe Richey <joerichey@google.com>
Date: Fri, 21 May 2021 01:58:43 -0700
Subject: KVM: X86: Use _BITUL() macro in UAPI headers

Replace BIT() in KVM's UPAI header with _BITUL(). BIT() is not defined
in the UAPI headers and its usage may cause userspace build errors.

Fixes: fb04a1eddb1a ("KVM: X86: Implement ring-based dirty memory tracking")
Signed-off-by: Joe Richey <joerichey@google.com>
Message-Id: <20210521085849.37676-3-joerichey94@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/uapi/linux/kvm.h       | 5 +++--
 tools/include/uapi/linux/kvm.h | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 3fd9a7e9d90c..79d9c44d1ad7 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -8,6 +8,7 @@
  * Note: you must update KVM_API_VERSION if you change this interface.
  */
 
+#include <linux/const.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
 #include <linux/ioctl.h>
@@ -1879,8 +1880,8 @@ struct kvm_hyperv_eventfd {
  * conversion after harvesting an entry.  Also, it must not skip any
  * dirty bits, so that dirty bits are always harvested in sequence.
  */
-#define KVM_DIRTY_GFN_F_DIRTY           BIT(0)
-#define KVM_DIRTY_GFN_F_RESET           BIT(1)
+#define KVM_DIRTY_GFN_F_DIRTY           _BITUL(0)
+#define KVM_DIRTY_GFN_F_RESET           _BITUL(1)
 #define KVM_DIRTY_GFN_F_MASK            0x3
 
 /*
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f6afee209620..26e6d94d64ed 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -8,6 +8,7 @@
  * Note: you must update KVM_API_VERSION if you change this interface.
  */
 
+#include <linux/const.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
 #include <linux/ioctl.h>
@@ -1834,8 +1835,8 @@ struct kvm_hyperv_eventfd {
  * conversion after harvesting an entry.  Also, it must not skip any
  * dirty bits, so that dirty bits are always harvested in sequence.
  */
-#define KVM_DIRTY_GFN_F_DIRTY           BIT(0)
-#define KVM_DIRTY_GFN_F_RESET           BIT(1)
+#define KVM_DIRTY_GFN_F_DIRTY           _BITUL(0)
+#define KVM_DIRTY_GFN_F_RESET           _BITUL(1)
 #define KVM_DIRTY_GFN_F_MASK            0x3
 
 /*
-- 
cgit v1.2.3


From fb0f94794bb7558c078ce37b1a6e30d881fd7888 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 26 May 2021 14:36:14 -0400
Subject: selftests: kvm: do only 1 memslot_perf_test run by default

The test takes a long time with the current implementation of
memslots, so cut the run time a bit.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/memslot_perf_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index 4ae0e5ec0f74..11239652d805 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -992,7 +992,7 @@ int main(int argc, char *argv[])
 		.tlast = NTESTS - 1,
 		.nslots = -1,
 		.seconds = 5,
-		.runs = 20,
+		.runs = 1,
 	};
 	struct test_result rbestslottime;
 	int tctr;
-- 
cgit v1.2.3


From c59870e2110e1229a6e4b2457aece6ffe8d68d99 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 19 May 2021 09:44:47 -0700
Subject: perf debug: Move debug initialization earlier

This avoids segfaults during option handlers that use pr_err. For
example, "perf --debug nopager list" segfaults before this change.

Fixes: 8abceacff87d (perf debug: Add debug_set_file function)
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20210519164447.2672030-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/perf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 20cb91ef06ff..2f6b67189b42 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -443,6 +443,8 @@ int main(int argc, const char **argv)
 	const char *cmd;
 	char sbuf[STRERR_BUFSIZE];
 
+	perf_debug_setup();
+
 	/* libsubcmd init */
 	exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT);
 	pager_init(PERF_PAGER_ENVIRONMENT);
@@ -531,8 +533,6 @@ int main(int argc, const char **argv)
 	 */
 	pthread__block_sigwinch();
 
-	perf_debug_setup();
-
 	while (1) {
 		static int done_help;
 
-- 
cgit v1.2.3


From c673b7f59e940061467200f1746820a178444bd0 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 27 May 2021 15:00:52 -0700
Subject: perf stat: Fix error check for bpf_program__attach

It seems the bpf_program__attach() returns a negative error code instead
of a NULL pointer in case of error.

Fixes: 7fac83aaf2ee ("perf stat: Introduce 'bperf' to share hardware PMCs with BPF")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Link: http://lore.kernel.org/lkml/20210527220052.1657578-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf_counter.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index ddb52f748c8e..974f10e356f0 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -451,10 +451,10 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd,
 		goto out;
 	}
 
-	err = -1;
 	link = bpf_program__attach(skel->progs.on_switch);
-	if (!link) {
+	if (IS_ERR(link)) {
 		pr_err("Failed to attach leader program\n");
+		err = PTR_ERR(link);
 		goto out;
 	}
 
-- 
cgit v1.2.3


From 8fc4e4aa2bfca8d32e8bc2a01526ea2da450e6cb Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Tue, 25 May 2021 12:07:23 +0530
Subject: perf vendor events powerpc: Fix eventcode of power10 JSON events

Fixed the eventcode values in the power10 JSON event files to prepend
"0x" since these are hexadecimal values.

The patch also changes the event description of the PM_EXEC_STALL_LOAD_FINISH
and PM_EXEC_STALL_NTC_FLUSH event and move some events to correct files.

Fixes: 32daa5d7899e ("perf vendor events: Initial JSON/events list for power10 platform")
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Reviewed-by: Paul A. Clarke <pc@us.ibm.com>
Tested-by: Nageswara R Sastry <rnsastry@linux.ibm.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lore.kernel.org/lkml/20210525063723.1191514-1-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../pmu-events/arch/powerpc/power10/cache.json     |  30 +++--
 .../arch/powerpc/power10/floating_point.json       |   2 +-
 .../pmu-events/arch/powerpc/power10/frontend.json  | 124 ++++++++++++-------
 .../pmu-events/arch/powerpc/power10/locks.json     |   4 +-
 .../pmu-events/arch/powerpc/power10/marked.json    |  61 +++++-----
 .../pmu-events/arch/powerpc/power10/memory.json    |  79 ++++++------
 .../pmu-events/arch/powerpc/power10/others.json    | 133 +++++++++-----------
 .../pmu-events/arch/powerpc/power10/pipeline.json  | 135 ++++++++++-----------
 .../perf/pmu-events/arch/powerpc/power10/pmc.json  |   8 +-
 .../arch/powerpc/power10/translation.json          |  22 ++--
 10 files changed, 299 insertions(+), 299 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/pmu-events/arch/powerpc/power10/cache.json b/tools/perf/pmu-events/arch/powerpc/power10/cache.json
index 616f29098c71..605be14f441c 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/cache.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/cache.json
@@ -1,46 +1,56 @@
 [
   {
-    "EventCode": "1003C",
+    "EventCode": "0x1003C",
     "EventName": "PM_EXEC_STALL_DMISS_L2L3",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from either the local L2 or local L3."
   },
   {
-    "EventCode": "34056",
+    "EventCode": "0x1E054",
+    "EventName": "PM_EXEC_STALL_DMISS_L21_L31",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip."
+  },
+  {
+    "EventCode": "0x34054",
+    "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict."
+  },
+  {
+    "EventCode": "0x34056",
     "EventName": "PM_EXEC_STALL_LOAD_FINISH",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ."
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction."
   },
   {
-    "EventCode": "3006C",
+    "EventCode": "0x3006C",
     "EventName": "PM_RUN_CYC_SMT2_MODE",
     "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT2 mode."
   },
   {
-    "EventCode": "300F4",
+    "EventCode": "0x300F4",
     "EventName": "PM_RUN_INST_CMPL_CONC",
     "BriefDescription": "PowerPC instructions completed by this thread when all threads in the core had the run-latch set."
   },
   {
-    "EventCode": "4C016",
+    "EventCode": "0x4C016",
     "EventName": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, with a dispatch conflict."
   },
   {
-    "EventCode": "4D014",
+    "EventCode": "0x4D014",
     "EventName": "PM_EXEC_STALL_LOAD",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a load instruction executing in the Load Store Unit."
   },
   {
-    "EventCode": "4D016",
+    "EventCode": "0x4D016",
     "EventName": "PM_EXEC_STALL_PTESYNC",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a PTESYNC instruction executing in the Load Store Unit."
   },
   {
-    "EventCode": "401EA",
+    "EventCode": "0x401EA",
     "EventName": "PM_THRESH_EXC_128",
     "BriefDescription": "Threshold counter exceeded a value of 128."
   },
   {
-    "EventCode": "400F6",
+    "EventCode": "0x400F6",
     "EventName": "PM_BR_MPRED_CMPL",
     "BriefDescription": "A mispredicted branch completed. Includes direction and target."
   }
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json
index 703cd431ae5b..54acb55e2c8c 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json
@@ -1,6 +1,6 @@
 [
   {
-    "EventCode": "4016E",
+    "EventCode": "0x4016E",
     "EventName": "PM_THRESH_NOT_MET",
     "BriefDescription": "Threshold counter did not meet threshold."
   }
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
index eac8609dcc90..558f9530f54e 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
@@ -1,216 +1,246 @@
 [
   {
-    "EventCode": "10004",
+    "EventCode": "0x10004",
     "EventName": "PM_EXEC_STALL_TRANSLATION",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss or ERAT miss and waited for it to resolve."
   },
   {
-    "EventCode": "10010",
+    "EventCode": "0x10006",
+    "EventName": "PM_DISP_STALL_HELD_OTHER_CYC",
+    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason."
+  },
+  {
+    "EventCode": "0x10010",
     "EventName": "PM_PMC4_OVERFLOW",
     "BriefDescription": "The event selected for PMC4 caused the event counter to overflow."
   },
   {
-    "EventCode": "10020",
+    "EventCode": "0x10020",
     "EventName": "PM_PMC4_REWIND",
     "BriefDescription": "The speculative event selected for PMC4 rewinds and the counter for PMC4 is not charged."
   },
   {
-    "EventCode": "10038",
+    "EventCode": "0x10038",
     "EventName": "PM_DISP_STALL_TRANSLATION",
     "BriefDescription": "Cycles when dispatch was stalled for this thread because the MMU was handling a translation miss."
   },
   {
-    "EventCode": "1003A",
+    "EventCode": "0x1003A",
     "EventName": "PM_DISP_STALL_BR_MPRED_IC_L2",
     "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2 after suffering a branch mispredict."
   },
   {
-    "EventCode": "1E050",
+    "EventCode": "0x1D05E",
+    "EventName": "PM_DISP_STALL_HELD_HALT_CYC",
+    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management."
+  },
+  {
+    "EventCode": "0x1E050",
     "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC",
     "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR."
   },
   {
-    "EventCode": "1F054",
+    "EventCode": "0x1F054",
     "EventName": "PM_DTLB_HIT",
     "BriefDescription": "The PTE required by the instruction was resident in the TLB (data TLB access). When MMCR1[16]=0 this event counts only demand hits. When MMCR1[16]=1 this event includes demand and prefetch. Applies to both HPT and RPT."
   },
   {
-    "EventCode": "101E8",
+    "EventCode": "0x10064",
+    "EventName": "PM_DISP_STALL_IC_L2",
+    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2."
+  },
+  {
+    "EventCode": "0x101E8",
     "EventName": "PM_THRESH_EXC_256",
     "BriefDescription": "Threshold counter exceeded a count of 256."
   },
   {
-    "EventCode": "101EC",
+    "EventCode": "0x101EC",
     "EventName": "PM_THRESH_MET",
     "BriefDescription": "Threshold exceeded."
   },
   {
-    "EventCode": "100F2",
+    "EventCode": "0x100F2",
     "EventName": "PM_1PLUS_PPC_CMPL",
     "BriefDescription": "Cycles in which at least one instruction is completed by this thread."
   },
   {
-    "EventCode": "100F6",
+    "EventCode": "0x100F6",
     "EventName": "PM_IERAT_MISS",
     "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event."
   },
   {
-    "EventCode": "100F8",
+    "EventCode": "0x100F8",
     "EventName": "PM_DISP_STALL_CYC",
     "BriefDescription": "Cycles the ICT has no itags assigned to this thread (no instructions were dispatched during these cycles)."
   },
   {
-    "EventCode": "20114",
+    "EventCode": "0x20006",
+    "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC",
+    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue."
+  },
+  {
+    "EventCode": "0x20114",
     "EventName": "PM_MRK_L2_RC_DISP",
     "BriefDescription": "Marked instruction RC dispatched in L2."
   },
   {
-    "EventCode": "2C010",
+    "EventCode": "0x2C010",
     "EventName": "PM_EXEC_STALL_LSU",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Load Store Unit. This does not include simple fixed point instructions."
   },
   {
-    "EventCode": "2C016",
+    "EventCode": "0x2C016",
     "EventName": "PM_DISP_STALL_IERAT_ONLY_MISS",
     "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction ERAT miss."
   },
   {
-    "EventCode": "2C01E",
+    "EventCode": "0x2C01E",
     "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3",
     "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3 after suffering a branch mispredict."
   },
   {
-    "EventCode": "2D01A",
+    "EventCode": "0x2D01A",
     "EventName": "PM_DISP_STALL_IC_MISS",
     "BriefDescription": "Cycles when dispatch was stalled for this thread due to an Icache Miss."
   },
   {
-    "EventCode": "2D01C",
-    "EventName": "PM_CMPL_STALL_STCX",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a stcx waiting for resolution from the nest before completing."
-  },
-  {
-    "EventCode": "2E018",
+    "EventCode": "0x2E018",
     "EventName": "PM_DISP_STALL_FETCH",
     "BriefDescription": "Cycles when dispatch was stalled for this thread because Fetch was being held."
   },
   {
-    "EventCode": "2E01A",
+    "EventCode": "0x2E01A",
     "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC",
     "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the XVFC mapper/SRB was full."
   },
   {
-    "EventCode": "2C142",
+    "EventCode": "0x2C142",
     "EventName": "PM_MRK_XFER_FROM_SRC_PMC2",
     "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
   {
-    "EventCode": "24050",
+    "EventCode": "0x24050",
     "EventName": "PM_IOPS_DISP",
     "BriefDescription": "Internal Operations dispatched. PM_IOPS_DISP / PM_INST_DISP will show the average number of internal operations per PowerPC instruction."
   },
   {
-    "EventCode": "2405E",
+    "EventCode": "0x2405E",
     "EventName": "PM_ISSUE_CANCEL",
     "BriefDescription": "An instruction issued and the issue was later cancelled. Only one cancel per PowerPC instruction."
   },
   {
-    "EventCode": "200FA",
+    "EventCode": "0x200FA",
     "EventName": "PM_BR_TAKEN_CMPL",
     "BriefDescription": "Branch Taken instruction completed."
   },
   {
-    "EventCode": "30012",
+    "EventCode": "0x30004",
+    "EventName": "PM_DISP_STALL_FLUSH",
+    "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC."
+  },
+  {
+    "EventCode": "0x3000A",
+    "EventName": "PM_DISP_STALL_ITLB_MISS",
+    "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction TLB miss."
+  },
+  {
+    "EventCode": "0x30012",
     "EventName": "PM_FLUSH_COMPLETION",
     "BriefDescription": "The instruction that was next to complete (oldest in the pipeline) did not complete because it suffered a flush."
   },
   {
-    "EventCode": "30014",
+    "EventCode": "0x30014",
     "EventName": "PM_EXEC_STALL_STORE",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store instruction executing in the Load Store Unit."
   },
   {
-    "EventCode": "30018",
+    "EventCode": "0x30018",
     "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC",
     "BriefDescription": "Cycles in which the NTC instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together."
   },
   {
-    "EventCode": "30026",
+    "EventCode": "0x30026",
     "EventName": "PM_EXEC_STALL_STORE_MISS",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store whose cache line was not resident in the L1 and was waiting for allocation of the missing line into the L1."
   },
   {
-    "EventCode": "3012A",
+    "EventCode": "0x3012A",
     "EventName": "PM_MRK_L2_RC_DONE",
     "BriefDescription": "L2 RC machine completed the transaction for the marked instruction."
   },
   {
-    "EventCode": "3F046",
+    "EventCode": "0x3F046",
     "EventName": "PM_ITLB_HIT_1G",
     "BriefDescription": "Instruction TLB hit (IERAT reload) page size 1G, which implies Radix Page Table translation is in use. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "34058",
+    "EventCode": "0x34058",
     "EventName": "PM_DISP_STALL_BR_MPRED_ICMISS",
     "BriefDescription": "Cycles when dispatch was stalled after a mispredicted branch resulted in an instruction cache miss."
   },
   {
-    "EventCode": "3D05C",
+    "EventCode": "0x3D05C",
     "EventName": "PM_DISP_STALL_HELD_RENAME_CYC",
     "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC."
   },
   {
-    "EventCode": "3E052",
+    "EventCode": "0x3E052",
     "EventName": "PM_DISP_STALL_IC_L3",
     "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3."
   },
   {
-    "EventCode": "3E054",
+    "EventCode": "0x3E054",
     "EventName": "PM_LD_MISS_L1",
     "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
   },
   {
-    "EventCode": "301EA",
+    "EventCode": "0x301EA",
     "EventName": "PM_THRESH_EXC_1024",
     "BriefDescription": "Threshold counter exceeded a value of 1024."
   },
   {
-    "EventCode": "300FA",
+    "EventCode": "0x300FA",
     "EventName": "PM_INST_FROM_L3MISS",
     "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss."
   },
   {
-    "EventCode": "40006",
+    "EventCode": "0x40006",
     "EventName": "PM_ISSUE_KILL",
     "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group."
   },
   {
-    "EventCode": "40116",
+    "EventCode": "0x40116",
     "EventName": "PM_MRK_LARX_FIN",
     "BriefDescription": "Marked load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock."
   },
   {
-    "EventCode": "4C010",
+    "EventCode": "0x4C010",
     "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3MISS",
     "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from sources beyond the local L3 after suffering a mispredicted branch."
   },
   {
-    "EventCode": "4D01E",
+    "EventCode": "0x4D01E",
     "EventName": "PM_DISP_STALL_BR_MPRED",
     "BriefDescription": "Cycles when dispatch was stalled for this thread due to a mispredicted branch."
   },
   {
-    "EventCode": "4E010",
+    "EventCode": "0x4E010",
     "EventName": "PM_DISP_STALL_IC_L3MISS",
     "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from any source beyond the local L3."
   },
   {
-    "EventCode": "4E01A",
+    "EventCode": "0x4E01A",
     "EventName": "PM_DISP_STALL_HELD_CYC",
     "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason."
   },
   {
-    "EventCode": "44056",
+    "EventCode": "0x4003C",
+    "EventName": "PM_DISP_STALL_HELD_SYNC_CYC",
+    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch."
+  },
+  {
+    "EventCode": "0x44056",
     "EventName": "PM_VECTOR_ST_CMPL",
     "BriefDescription": "Vector store instructions completed."
   }
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/locks.json b/tools/perf/pmu-events/arch/powerpc/power10/locks.json
index 016d8de0e14a..b5a0d6521963 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/locks.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/locks.json
@@ -1,11 +1,11 @@
 [
   {
-    "EventCode": "1E058",
+    "EventCode": "0x1E058",
     "EventName": "PM_STCX_FAIL_FIN",
     "BriefDescription": "Conditional store instruction (STCX) failed. LARX and STCX are instructions used to acquire a lock."
   },
   {
-    "EventCode": "4E050",
+    "EventCode": "0x4E050",
     "EventName": "PM_STCX_PASS_FIN",
     "BriefDescription": "Conditional store instruction (STCX) passed. LARX and STCX are instructions used to acquire a lock."
   }
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
index 93a5a5910648..58b5dfe3a273 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
@@ -1,146 +1,141 @@
 [
   {
-    "EventCode": "1002C",
+    "EventCode": "0x1002C",
     "EventName": "PM_LD_PREFETCH_CACHE_LINE_MISS",
     "BriefDescription": "The L1 cache was reloaded with a line that fulfills a prefetch request."
   },
   {
-    "EventCode": "10132",
+    "EventCode": "0x10132",
     "EventName": "PM_MRK_INST_ISSUED",
     "BriefDescription": "Marked instruction issued. Note that stores always get issued twice, the address gets issued to the LSU and the data gets issued to the VSU. Also, issues can sometimes get killed/cancelled and cause multiple sequential issues for the same instruction."
   },
   {
-    "EventCode": "101E0",
+    "EventCode": "0x101E0",
     "EventName": "PM_MRK_INST_DISP",
     "BriefDescription": "The thread has dispatched a randomly sampled marked instruction."
   },
   {
-    "EventCode": "101E2",
+    "EventCode": "0x101E2",
     "EventName": "PM_MRK_BR_TAKEN_CMPL",
     "BriefDescription": "Marked Branch Taken instruction completed."
   },
   {
-    "EventCode": "20112",
+    "EventCode": "0x20112",
     "EventName": "PM_MRK_NTF_FIN",
     "BriefDescription": "The marked instruction became the oldest in the pipeline before it finished. It excludes instructions that finish at dispatch."
   },
   {
-    "EventCode": "2C01C",
+    "EventCode": "0x2C01C",
     "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a remote chip."
   },
   {
-    "EventCode": "20138",
+    "EventCode": "0x20138",
     "EventName": "PM_MRK_ST_NEST",
     "BriefDescription": "A store has been sampled/marked and is at the point of execution where it has completed in the core and can no longer be flushed. At this point the store is sent to the L2."
   },
   {
-    "EventCode": "2013A",
+    "EventCode": "0x2013A",
     "EventName": "PM_MRK_BRU_FIN",
     "BriefDescription": "Marked Branch instruction finished."
   },
   {
-    "EventCode": "2C144",
+    "EventCode": "0x2C144",
     "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC2",
     "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[15:27]."
   },
   {
-    "EventCode": "24156",
+    "EventCode": "0x24156",
     "EventName": "PM_MRK_STCX_FIN",
     "BriefDescription": "Marked conditional store instruction (STCX) finished. LARX and STCX are instructions used to acquire a lock."
   },
   {
-    "EventCode": "24158",
+    "EventCode": "0x24158",
     "EventName": "PM_MRK_INST",
     "BriefDescription": "An instruction was marked. Includes both Random Instruction Sampling (RIS) at decode time and Random Event Sampling (RES) at the time the configured event happens."
   },
   {
-    "EventCode": "2415C",
+    "EventCode": "0x2415C",
     "EventName": "PM_MRK_BR_CMPL",
     "BriefDescription": "A marked branch completed. All branches are included."
   },
   {
-    "EventCode": "200FD",
+    "EventCode": "0x200FD",
     "EventName": "PM_L1_ICACHE_MISS",
     "BriefDescription": "Demand iCache Miss."
   },
   {
-    "EventCode": "30130",
+    "EventCode": "0x30130",
     "EventName": "PM_MRK_INST_FIN",
     "BriefDescription": "marked instruction finished. Excludes instructions that finish at dispatch. Note that stores always finish twice since the address gets issued to the LSU and the data gets issued to the VSU."
   },
   {
-    "EventCode": "34146",
+    "EventCode": "0x34146",
     "EventName": "PM_MRK_LD_CMPL",
     "BriefDescription": "Marked loads completed."
   },
   {
-    "EventCode": "3E158",
+    "EventCode": "0x3E158",
     "EventName": "PM_MRK_STCX_FAIL",
     "BriefDescription": "Marked conditional store instruction (STCX) failed. LARX and STCX are instructions used to acquire a lock."
   },
   {
-    "EventCode": "3E15A",
+    "EventCode": "0x3E15A",
     "EventName": "PM_MRK_ST_FIN",
     "BriefDescription": "The marked instruction was a store of any kind."
   },
   {
-    "EventCode": "30068",
+    "EventCode": "0x30068",
     "EventName": "PM_L1_ICACHE_RELOADED_PREF",
     "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)."
   },
   {
-    "EventCode": "301E4",
+    "EventCode": "0x301E4",
     "EventName": "PM_MRK_BR_MPRED_CMPL",
     "BriefDescription": "Marked Branch Mispredicted. Includes direction and target."
   },
   {
-    "EventCode": "300F6",
+    "EventCode": "0x300F6",
     "EventName": "PM_LD_DEMAND_MISS_L1",
     "BriefDescription": "The L1 cache was reloaded with a line that fulfills a demand miss request. Counted at reload time, before finish."
   },
   {
-    "EventCode": "300FE",
+    "EventCode": "0x300FE",
     "EventName": "PM_DATA_FROM_L3MISS",
     "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss."
   },
   {
-    "EventCode": "40012",
+    "EventCode": "0x40012",
     "EventName": "PM_L1_ICACHE_RELOADED_ALL",
     "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch."
   },
   {
-    "EventCode": "40134",
+    "EventCode": "0x40134",
     "EventName": "PM_MRK_INST_TIMEO",
     "BriefDescription": "Marked instruction finish timeout (instruction was lost)."
   },
   {
-    "EventCode": "4003C",
-    "EventName": "PM_DISP_STALL_HELD_SYNC_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch."
-  },
-  {
-    "EventCode": "4505A",
+    "EventCode": "0x4505A",
     "EventName": "PM_SP_FLOP_CMPL",
     "BriefDescription": "Single Precision floating point instructions completed."
   },
   {
-    "EventCode": "4D058",
+    "EventCode": "0x4D058",
     "EventName": "PM_VECTOR_FLOP_CMPL",
     "BriefDescription": "Vector floating point instructions completed."
   },
   {
-    "EventCode": "4D05A",
+    "EventCode": "0x4D05A",
     "EventName": "PM_NON_MATH_FLOP_CMPL",
     "BriefDescription": "Non Math instructions completed."
   },
   {
-    "EventCode": "401E0",
+    "EventCode": "0x401E0",
     "EventName": "PM_MRK_INST_CMPL",
     "BriefDescription": "marked instruction completed."
   },
   {
-    "EventCode": "400FE",
+    "EventCode": "0x400FE",
     "EventName": "PM_DATA_FROM_MEMORY",
     "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss."
   }
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/memory.json b/tools/perf/pmu-events/arch/powerpc/power10/memory.json
index b01141eeebee..843b51f531e9 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/memory.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/memory.json
@@ -1,191 +1,186 @@
 [
   {
-    "EventCode": "1000A",
+    "EventCode": "0x1000A",
     "EventName": "PM_PMC3_REWIND",
     "BriefDescription": "The speculative event selected for PMC3 rewinds and the counter for PMC3 is not charged."
   },
   {
-    "EventCode": "1C040",
+    "EventCode": "0x1C040",
     "EventName": "PM_XFER_FROM_SRC_PMC1",
     "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
   {
-    "EventCode": "1C142",
+    "EventCode": "0x1C142",
     "EventName": "PM_MRK_XFER_FROM_SRC_PMC1",
     "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
   {
-    "EventCode": "1C144",
+    "EventCode": "0x1C144",
     "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC1",
     "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[0:12]."
   },
   {
-    "EventCode": "1C056",
+    "EventCode": "0x1C056",
     "EventName": "PM_DERAT_MISS_4K",
     "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 4K. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "1C058",
+    "EventCode": "0x1C058",
     "EventName": "PM_DTLB_MISS_16G",
     "BriefDescription": "Data TLB reload (after a miss) page size 16G. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "1C05C",
+    "EventCode": "0x1C05C",
     "EventName": "PM_DTLB_MISS_2M",
     "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "1E056",
+    "EventCode": "0x1E056",
     "EventName": "PM_EXEC_STALL_STORE_PIPE",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the store unit. This does not include cycles spent handling store misses, PTESYNC instructions or TLBIE instructions."
   },
   {
-    "EventCode": "1F150",
+    "EventCode": "0x1F150",
     "EventName": "PM_MRK_ST_L2_CYC",
     "BriefDescription": "Cycles from L2 RC dispatch to L2 RC completion."
   },
   {
-    "EventCode": "10062",
+    "EventCode": "0x10062",
     "EventName": "PM_LD_L3MISS_PEND_CYC",
     "BriefDescription": "Cycles L3 miss was pending for this thread."
   },
   {
-    "EventCode": "20010",
+    "EventCode": "0x20010",
     "EventName": "PM_PMC1_OVERFLOW",
     "BriefDescription": "The event selected for PMC1 caused the event counter to overflow."
   },
   {
-    "EventCode": "2001A",
+    "EventCode": "0x2001A",
     "EventName": "PM_ITLB_HIT",
     "BriefDescription": "The PTE required to translate the instruction address was resident in the TLB (instruction TLB access/IERAT reload). Applies to both HPT and RPT. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "2003E",
+    "EventCode": "0x2003E",
     "EventName": "PM_PTESYNC_FIN",
     "BriefDescription": "Ptesync instruction finished in the store unit. Only one ptesync can finish at a time."
   },
   {
-    "EventCode": "2C040",
+    "EventCode": "0x2C040",
     "EventName": "PM_XFER_FROM_SRC_PMC2",
     "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
   {
-    "EventCode": "2C054",
+    "EventCode": "0x2C054",
     "EventName": "PM_DERAT_MISS_64K",
     "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "2C056",
+    "EventCode": "0x2C056",
     "EventName": "PM_DTLB_MISS_4K",
     "BriefDescription": "Data TLB reload (after a miss) page size 4K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "2D154",
+    "EventCode": "0x2D154",
     "EventName": "PM_MRK_DERAT_MISS_64K",
     "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "200F6",
+    "EventCode": "0x200F6",
     "EventName": "PM_DERAT_MISS",
     "BriefDescription": "DERAT Reloaded to satisfy a DERAT miss. All page sizes are counted by this event. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "3000A",
-    "EventName": "PM_DISP_STALL_ITLB_MISS",
-    "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction TLB miss."
-  },
-  {
-    "EventCode": "30016",
+    "EventCode": "0x30016",
     "EventName": "PM_EXEC_STALL_DERAT_DTLB_MISS",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss and waited for it resolve."
   },
   {
-    "EventCode": "3C040",
+    "EventCode": "0x3C040",
     "EventName": "PM_XFER_FROM_SRC_PMC3",
     "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
   {
-    "EventCode": "3C142",
+    "EventCode": "0x3C142",
     "EventName": "PM_MRK_XFER_FROM_SRC_PMC3",
     "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
   {
-    "EventCode": "3C144",
+    "EventCode": "0x3C144",
     "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC3",
     "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[30:42]."
   },
   {
-    "EventCode": "3C054",
+    "EventCode": "0x3C054",
     "EventName": "PM_DERAT_MISS_16M",
     "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "3C056",
+    "EventCode": "0x3C056",
     "EventName": "PM_DTLB_MISS_64K",
     "BriefDescription": "Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "3C058",
+    "EventCode": "0x3C058",
     "EventName": "PM_LARX_FIN",
     "BriefDescription": "Load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock."
   },
   {
-    "EventCode": "301E2",
+    "EventCode": "0x301E2",
     "EventName": "PM_MRK_ST_CMPL",
     "BriefDescription": "Marked store completed and sent to nest. Note that this count excludes cache-inhibited stores."
   },
   {
-    "EventCode": "300FC",
+    "EventCode": "0x300FC",
     "EventName": "PM_DTLB_MISS",
     "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. It includes pages of all sizes for demand and prefetch activity."
   },
   {
-    "EventCode": "4D02C",
+    "EventCode": "0x4D02C",
     "EventName": "PM_PMC1_REWIND",
     "BriefDescription": "The speculative event selected for PMC1 rewinds and the counter for PMC1 is not charged."
   },
   {
-    "EventCode": "4003E",
+    "EventCode": "0x4003E",
     "EventName": "PM_LD_CMPL",
     "BriefDescription": "Loads completed."
   },
   {
-    "EventCode": "4C040",
+    "EventCode": "0x4C040",
     "EventName": "PM_XFER_FROM_SRC_PMC4",
     "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
   {
-    "EventCode": "4C142",
+    "EventCode": "0x4C142",
     "EventName": "PM_MRK_XFER_FROM_SRC_PMC4",
     "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
   },
   {
-    "EventCode": "4C144",
+    "EventCode": "0x4C144",
     "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC4",
     "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[45:57]."
   },
   {
-    "EventCode": "4C056",
+    "EventCode": "0x4C056",
     "EventName": "PM_DTLB_MISS_16M",
     "BriefDescription": "Data TLB reload (after a miss) page size 16M. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "4C05A",
+    "EventCode": "0x4C05A",
     "EventName": "PM_DTLB_MISS_1G",
     "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "4C15E",
+    "EventCode": "0x4C15E",
     "EventName": "PM_MRK_DTLB_MISS_64K",
     "BriefDescription": "Marked Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "4D056",
+    "EventCode": "0x4D056",
     "EventName": "PM_NON_FMA_FLOP_CMPL",
     "BriefDescription": "Non FMA instruction completed."
   },
   {
-    "EventCode": "40164",
+    "EventCode": "0x40164",
     "EventName": "PM_MRK_DERAT_MISS_2M",
     "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   }
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json
index a119e56cbf1c..7d0de1a2860b 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/others.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json
@@ -1,296 +1,271 @@
 [
   {
-    "EventCode": "10016",
+    "EventCode": "0x10016",
     "EventName": "PM_VSU0_ISSUE",
     "BriefDescription": "VSU instructions issued to VSU pipe 0."
   },
   {
-    "EventCode": "1001C",
+    "EventCode": "0x1001C",
     "EventName": "PM_ULTRAVISOR_INST_CMPL",
     "BriefDescription": "PowerPC instructions that completed while the thread was in ultravisor state."
   },
   {
-    "EventCode": "100F0",
+    "EventCode": "0x100F0",
     "EventName": "PM_CYC",
     "BriefDescription": "Processor cycles."
   },
   {
-    "EventCode": "10134",
+    "EventCode": "0x10134",
     "EventName": "PM_MRK_ST_DONE_L2",
     "BriefDescription": "Marked stores completed in L2 (RC machine done)."
   },
   {
-    "EventCode": "1505E",
+    "EventCode": "0x1505E",
     "EventName": "PM_LD_HIT_L1",
     "BriefDescription": "Loads that finished without experiencing an L1 miss."
   },
   {
-    "EventCode": "1D05E",
-    "EventName": "PM_DISP_STALL_HELD_HALT_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management."
-  },
-  {
-    "EventCode": "1E054",
-    "EventName": "PM_EXEC_STALL_DMISS_L21_L31",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip."
-  },
-  {
-    "EventCode": "1E05A",
-    "EventName": "PM_CMPL_STALL_LWSYNC",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete."
-  },
-  {
-    "EventCode": "1F056",
+    "EventCode": "0x1F056",
     "EventName": "PM_DISP_SS0_2_INSTR_CYC",
     "BriefDescription": "Cycles in which Superslice 0 dispatches either 1 or 2 instructions."
   },
   {
-    "EventCode": "1F15C",
+    "EventCode": "0x1F15C",
     "EventName": "PM_MRK_STCX_L2_CYC",
     "BriefDescription": "Cycles spent in the nest portion of a marked Stcx instruction. It starts counting when the operation starts to drain to the L2 and it stops counting when the instruction retires from the Instruction Completion Table (ICT) in the Instruction Sequencing Unit (ISU)."
   },
   {
-    "EventCode": "10066",
+    "EventCode": "0x10066",
     "EventName": "PM_ADJUNCT_CYC",
     "BriefDescription": "Cycles in which the thread is in Adjunct state. MSR[S HV PR] bits = 011."
   },
   {
-    "EventCode": "101E4",
+    "EventCode": "0x101E4",
     "EventName": "PM_MRK_L1_ICACHE_MISS",
     "BriefDescription": "Marked Instruction suffered an icache Miss."
   },
   {
-    "EventCode": "101EA",
+    "EventCode": "0x101EA",
     "EventName": "PM_MRK_L1_RELOAD_VALID",
     "BriefDescription": "Marked demand reload."
   },
   {
-    "EventCode": "100F4",
+    "EventCode": "0x100F4",
     "EventName": "PM_FLOP_CMPL",
     "BriefDescription": "Floating Point Operations Completed. Includes any type. It counts once for each 1, 2, 4 or 8 flop instruction. Use PM_1|2|4|8_FLOP_CMPL events to count flops."
   },
   {
-    "EventCode": "100FA",
+    "EventCode": "0x100FA",
     "EventName": "PM_RUN_LATCH_ANY_THREAD_CYC",
     "BriefDescription": "Cycles when at least one thread has the run latch set."
   },
   {
-    "EventCode": "100FC",
+    "EventCode": "0x100FC",
     "EventName": "PM_LD_REF_L1",
     "BriefDescription": "All L1 D cache load references counted at finish, gated by reject. In P9 and earlier this event counted only cacheable loads but in P10 both cacheable and non-cacheable loads are included."
   },
   {
-    "EventCode": "20006",
-    "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue."
-  },
-  {
-    "EventCode": "2000C",
+    "EventCode": "0x2000C",
     "EventName": "PM_RUN_LATCH_ALL_THREADS_CYC",
     "BriefDescription": "Cycles when the run latch is set for all threads."
   },
   {
-    "EventCode": "2E010",
+    "EventCode": "0x2E010",
     "EventName": "PM_ADJUNCT_INST_CMPL",
     "BriefDescription": "PowerPC instructions that completed while the thread is in Adjunct state."
   },
   {
-    "EventCode": "2E014",
+    "EventCode": "0x2E014",
     "EventName": "PM_STCX_FIN",
     "BriefDescription": "Conditional store instruction (STCX) finished. LARX and STCX are instructions used to acquire a lock."
   },
   {
-    "EventCode": "20130",
+    "EventCode": "0x20130",
     "EventName": "PM_MRK_INST_DECODED",
     "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only."
   },
   {
-    "EventCode": "20132",
+    "EventCode": "0x20132",
     "EventName": "PM_MRK_DFU_ISSUE",
     "BriefDescription": "The marked instruction was a decimal floating point operation issued to the VSU. Measured at issue time."
   },
   {
-    "EventCode": "20134",
+    "EventCode": "0x20134",
     "EventName": "PM_MRK_FXU_ISSUE",
     "BriefDescription": "The marked instruction was a fixed point operation issued to the VSU. Measured at issue time."
   },
   {
-    "EventCode": "2505C",
+    "EventCode": "0x2505C",
     "EventName": "PM_VSU_ISSUE",
     "BriefDescription": "At least one VSU instruction was issued to one of the VSU pipes. Up to 4 per cycle. Includes fixed point operations."
   },
   {
-    "EventCode": "2F054",
+    "EventCode": "0x2F054",
     "EventName": "PM_DISP_SS1_2_INSTR_CYC",
     "BriefDescription": "Cycles in which Superslice 1 dispatches either 1 or 2 instructions."
   },
   {
-    "EventCode": "2F056",
+    "EventCode": "0x2F056",
     "EventName": "PM_DISP_SS1_4_INSTR_CYC",
     "BriefDescription": "Cycles in which Superslice 1 dispatches either 3 or 4 instructions."
   },
   {
-    "EventCode": "2006C",
+    "EventCode": "0x2006C",
     "EventName": "PM_RUN_CYC_SMT4_MODE",
     "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT4 mode."
   },
   {
-    "EventCode": "201E0",
+    "EventCode": "0x201E0",
     "EventName": "PM_MRK_DATA_FROM_MEMORY",
     "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss for a marked load."
   },
   {
-    "EventCode": "201E4",
+    "EventCode": "0x201E4",
     "EventName": "PM_MRK_DATA_FROM_L3MISS",
     "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked load."
   },
   {
-    "EventCode": "201E8",
+    "EventCode": "0x201E8",
     "EventName": "PM_THRESH_EXC_512",
     "BriefDescription": "Threshold counter exceeded a value of 512."
   },
   {
-    "EventCode": "200F2",
+    "EventCode": "0x200F2",
     "EventName": "PM_INST_DISP",
     "BriefDescription": "PowerPC instructions dispatched."
   },
   {
-    "EventCode": "30132",
+    "EventCode": "0x30132",
     "EventName": "PM_MRK_VSU_FIN",
     "BriefDescription": "VSU marked instructions finished. Excludes simple FX instructions issued to the Store Unit."
   },
   {
-    "EventCode": "30038",
+    "EventCode": "0x30038",
     "EventName": "PM_EXEC_STALL_DMISS_LMEM",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCapp cache, or local OpenCapp memory."
   },
   {
-    "EventCode": "3F04A",
+    "EventCode": "0x3F04A",
     "EventName": "PM_LSU_ST5_FIN",
     "BriefDescription": "LSU Finished an internal operation in ST2 port."
   },
   {
-    "EventCode": "34054",
-    "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict."
-  },
-  {
-    "EventCode": "3405A",
+    "EventCode": "0x3405A",
     "EventName": "PM_PRIVILEGED_INST_CMPL",
     "BriefDescription": "PowerPC Instructions that completed while the thread is in Privileged state."
   },
   {
-    "EventCode": "3F150",
+    "EventCode": "0x3F150",
     "EventName": "PM_MRK_ST_DRAIN_CYC",
     "BriefDescription": "cycles to drain st from core to L2."
   },
   {
-    "EventCode": "3F054",
+    "EventCode": "0x3F054",
     "EventName": "PM_DISP_SS0_4_INSTR_CYC",
     "BriefDescription": "Cycles in which Superslice 0 dispatches either 3 or 4 instructions."
   },
   {
-    "EventCode": "3F056",
+    "EventCode": "0x3F056",
     "EventName": "PM_DISP_SS0_8_INSTR_CYC",
     "BriefDescription": "Cycles in which Superslice 0 dispatches either 5, 6, 7 or 8 instructions."
   },
   {
-    "EventCode": "30162",
+    "EventCode": "0x30162",
     "EventName": "PM_MRK_ISSUE_DEPENDENT_LOAD",
     "BriefDescription": "The marked instruction was dependent on a load. It is eligible for issue kill."
   },
   {
-    "EventCode": "40114",
+    "EventCode": "0x40114",
     "EventName": "PM_MRK_START_PROBE_NOP_DISP",
     "BriefDescription": "Marked Start probe nop dispatched. Instruction AND R0,R0,R0."
   },
   {
-    "EventCode": "4001C",
+    "EventCode": "0x4001C",
     "EventName": "PM_VSU_FIN",
     "BriefDescription": "VSU instructions finished."
   },
   {
-    "EventCode": "4C01A",
+    "EventCode": "0x4C01A",
     "EventName": "PM_EXEC_STALL_DMISS_OFF_NODE",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a distant chip."
   },
   {
-    "EventCode": "4D012",
+    "EventCode": "0x4D012",
     "EventName": "PM_PMC3_SAVED",
     "BriefDescription": "The conditions for the speculative event selected for PMC3 are met and PMC3 is charged."
   },
   {
-    "EventCode": "4D022",
+    "EventCode": "0x4D022",
     "EventName": "PM_HYPERVISOR_INST_CMPL",
     "BriefDescription": "PowerPC instructions that completed while the thread is in hypervisor state."
   },
   {
-    "EventCode": "4D026",
+    "EventCode": "0x4D026",
     "EventName": "PM_ULTRAVISOR_CYC",
     "BriefDescription": "Cycles when the thread is in Ultravisor state. MSR[S HV PR]=110."
   },
   {
-    "EventCode": "4D028",
+    "EventCode": "0x4D028",
     "EventName": "PM_PRIVILEGED_CYC",
     "BriefDescription": "Cycles when the thread is in Privileged state. MSR[S HV PR]=x00."
   },
   {
-    "EventCode": "40030",
+    "EventCode": "0x40030",
     "EventName": "PM_INST_FIN",
     "BriefDescription": "Instructions finished."
   },
   {
-    "EventCode": "44146",
+    "EventCode": "0x44146",
     "EventName": "PM_MRK_STCX_CORE_CYC",
     "BriefDescription": "Cycles spent in the core portion of a marked Stcx instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2."
   },
   {
-    "EventCode": "44054",
+    "EventCode": "0x44054",
     "EventName": "PM_VECTOR_LD_CMPL",
     "BriefDescription": "Vector load instructions completed."
   },
   {
-    "EventCode": "45054",
+    "EventCode": "0x45054",
     "EventName": "PM_FMA_CMPL",
     "BriefDescription": "Two floating point instructions completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only."
   },
   {
-    "EventCode": "45056",
+    "EventCode": "0x45056",
     "EventName": "PM_SCALAR_FLOP_CMPL",
     "BriefDescription": "Scalar floating point instructions completed."
   },
   {
-    "EventCode": "4505C",
+    "EventCode": "0x4505C",
     "EventName": "PM_MATH_FLOP_CMPL",
     "BriefDescription": "Math floating point instructions completed."
   },
   {
-    "EventCode": "4D05E",
+    "EventCode": "0x4D05E",
     "EventName": "PM_BR_CMPL",
     "BriefDescription": "A branch completed. All branches are included."
   },
   {
-    "EventCode": "4E15E",
+    "EventCode": "0x4E15E",
     "EventName": "PM_MRK_INST_FLUSHED",
     "BriefDescription": "The marked instruction was flushed."
   },
   {
-    "EventCode": "401E6",
+    "EventCode": "0x401E6",
     "EventName": "PM_MRK_INST_FROM_L3MISS",
     "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked instruction."
   },
   {
-    "EventCode": "401E8",
+    "EventCode": "0x401E8",
     "EventName": "PM_MRK_DATA_FROM_L2MISS",
     "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss for a marked load."
   },
   {
-    "EventCode": "400F0",
+    "EventCode": "0x400F0",
     "EventName": "PM_LD_DEMAND_MISS_L1_FIN",
     "BriefDescription": "Load Missed L1, counted at finish time."
   },
   {
-    "EventCode": "400FA",
+    "EventCode": "0x400FA",
     "EventName": "PM_RUN_INST_CMPL",
     "BriefDescription": "Completed PowerPC instructions gated by the run latch."
   }
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
index b61b5cc157ee..b8aded6045fa 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
@@ -1,296 +1,291 @@
 [
   {
-    "EventCode": "100FE",
+    "EventCode": "0x100FE",
     "EventName": "PM_INST_CMPL",
     "BriefDescription": "PowerPC instructions completed."
   },
   {
-    "EventCode": "10006",
-    "EventName": "PM_DISP_STALL_HELD_OTHER_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason."
-  },
-  {
-    "EventCode": "1000C",
+    "EventCode": "0x1000C",
     "EventName": "PM_LSU_LD0_FIN",
     "BriefDescription": "LSU Finished an internal operation in LD0 port."
   },
   {
-    "EventCode": "1000E",
+    "EventCode": "0x1000E",
     "EventName": "PM_MMA_ISSUED",
     "BriefDescription": "MMA instructions issued."
   },
   {
-    "EventCode": "10012",
+    "EventCode": "0x10012",
     "EventName": "PM_LSU_ST0_FIN",
     "BriefDescription": "LSU Finished an internal operation in ST0 port."
   },
   {
-    "EventCode": "10014",
+    "EventCode": "0x10014",
     "EventName": "PM_LSU_ST4_FIN",
     "BriefDescription": "LSU Finished an internal operation in ST4 port."
   },
   {
-    "EventCode": "10018",
+    "EventCode": "0x10018",
     "EventName": "PM_IC_DEMAND_CYC",
     "BriefDescription": "Cycles in which an instruction reload is pending to satisfy a demand miss."
   },
   {
-    "EventCode": "10022",
+    "EventCode": "0x10022",
     "EventName": "PM_PMC2_SAVED",
     "BriefDescription": "The conditions for the speculative event selected for PMC2 are met and PMC2 is charged."
   },
   {
-    "EventCode": "10024",
+    "EventCode": "0x10024",
     "EventName": "PM_PMC5_OVERFLOW",
     "BriefDescription": "The event selected for PMC5 caused the event counter to overflow."
   },
   {
-    "EventCode": "10058",
+    "EventCode": "0x10058",
     "EventName": "PM_EXEC_STALL_FIN_AT_DISP",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline finished at dispatch and did not require execution in the LSU, BRU or VSU."
   },
   {
-    "EventCode": "1005A",
+    "EventCode": "0x1005A",
     "EventName": "PM_FLUSH_MPRED",
     "BriefDescription": "A flush occurred due to a mispredicted branch. Includes target and direction."
   },
   {
-    "EventCode": "1C05A",
+    "EventCode": "0x1C05A",
     "EventName": "PM_DERAT_MISS_2M",
     "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
   },
   {
-    "EventCode": "10064",
-    "EventName": "PM_DISP_STALL_IC_L2",
-    "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2."
+    "EventCode": "0x1E05A",
+    "EventName": "PM_CMPL_STALL_LWSYNC",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete."
   },
   {
-    "EventCode": "10068",
+    "EventCode": "0x10068",
     "EventName": "PM_BR_FIN",
     "BriefDescription": "A branch instruction finished. Includes predicted/mispredicted/unconditional."
   },
   {
-    "EventCode": "1006A",
+    "EventCode": "0x1006A",
     "EventName": "PM_FX_LSU_FIN",
     "BriefDescription": "Simple fixed point instruction issued to the store unit. Measured at finish time."
   },
   {
-    "EventCode": "1006C",
+    "EventCode": "0x1006C",
     "EventName": "PM_RUN_CYC_ST_MODE",
     "BriefDescription": "Cycles when the run latch is set and the core is in ST mode."
   },
   {
-    "EventCode": "20004",
+    "EventCode": "0x20004",
     "EventName": "PM_ISSUE_STALL",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was dispatched but not issued yet."
   },
   {
-    "EventCode": "2000A",
+    "EventCode": "0x2000A",
     "EventName": "PM_HYPERVISOR_CYC",
     "BriefDescription": "Cycles when the thread is in Hypervisor state. MSR[S HV PR]=010."
   },
   {
-    "EventCode": "2000E",
+    "EventCode": "0x2000E",
     "EventName": "PM_LSU_LD1_FIN",
     "BriefDescription": "LSU Finished an internal operation in LD1 port."
   },
   {
-    "EventCode": "2C014",
+    "EventCode": "0x2C014",
     "EventName": "PM_CMPL_STALL_SPECIAL",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline required special handling before completing."
   },
   {
-    "EventCode": "2C018",
+    "EventCode": "0x2C018",
     "EventName": "PM_EXEC_STALL_DMISS_L3MISS",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a source beyond the local L2 or local L3."
   },
   {
-    "EventCode": "2D010",
+    "EventCode": "0x2D010",
     "EventName": "PM_LSU_ST1_FIN",
     "BriefDescription": "LSU Finished an internal operation in ST1 port."
   },
   {
-    "EventCode": "2D012",
+    "EventCode": "0x2D012",
     "EventName": "PM_VSU1_ISSUE",
     "BriefDescription": "VSU instructions issued to VSU pipe 1."
   },
   {
-    "EventCode": "2D018",
+    "EventCode": "0x2D018",
     "EventName": "PM_EXEC_STALL_VSU",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the VSU (includes FXU, VSU, CRU)."
   },
   {
-    "EventCode": "2E01E",
+    "EventCode": "0x2D01C",
+    "EventName": "PM_CMPL_STALL_STCX",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a stcx waiting for resolution from the nest before completing."
+  },
+  {
+    "EventCode": "0x2E01E",
     "EventName": "PM_EXEC_STALL_NTC_FLUSH",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children."
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous NTF instruction is still completing and the new NTF instruction is stalled at dispatch."
   },
   {
-    "EventCode": "2013C",
+    "EventCode": "0x2013C",
     "EventName": "PM_MRK_FX_LSU_FIN",
     "BriefDescription": "The marked instruction was simple fixed point that was issued to the store unit. Measured at finish time."
   },
   {
-    "EventCode": "2405A",
+    "EventCode": "0x2405A",
     "EventName": "PM_NTC_FIN",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. Note that instructions can finish out of order, therefore not all the instructions that finish have a Next-to-complete status."
   },
   {
-    "EventCode": "201E2",
+    "EventCode": "0x201E2",
     "EventName": "PM_MRK_LD_MISS_L1",
     "BriefDescription": "Marked DL1 Demand Miss counted at finish time."
   },
   {
-    "EventCode": "200F4",
+    "EventCode": "0x200F4",
     "EventName": "PM_RUN_CYC",
     "BriefDescription": "Processor cycles gated by the run latch."
   },
   {
-    "EventCode": "30004",
-    "EventName": "PM_DISP_STALL_FLUSH",
-    "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC."
-  },
-  {
-    "EventCode": "30008",
+    "EventCode": "0x30008",
     "EventName": "PM_EXEC_STALL",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting to finish in one of the execution units (BRU, LSU, VSU). Only cycles between issue and finish are counted in this category."
   },
   {
-    "EventCode": "3001A",
+    "EventCode": "0x3001A",
     "EventName": "PM_LSU_ST2_FIN",
     "BriefDescription": "LSU Finished an internal operation in ST2 port."
   },
   {
-    "EventCode": "30020",
+    "EventCode": "0x30020",
     "EventName": "PM_PMC2_REWIND",
     "BriefDescription": "The speculative event selected for PMC2 rewinds and the counter for PMC2 is not charged."
   },
   {
-    "EventCode": "30022",
+    "EventCode": "0x30022",
     "EventName": "PM_PMC4_SAVED",
     "BriefDescription": "The conditions for the speculative event selected for PMC4 are met and PMC4 is charged."
   },
   {
-    "EventCode": "30024",
+    "EventCode": "0x30024",
     "EventName": "PM_PMC6_OVERFLOW",
     "BriefDescription": "The event selected for PMC6 caused the event counter to overflow."
   },
   {
-    "EventCode": "30028",
+    "EventCode": "0x30028",
     "EventName": "PM_CMPL_STALL_MEM_ECC",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC."
   },
   {
-    "EventCode": "30036",
+    "EventCode": "0x30036",
     "EventName": "PM_EXEC_STALL_SIMPLE_FX",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a simple fixed point instruction executing in the Load Store Unit."
   },
   {
-    "EventCode": "3003A",
+    "EventCode": "0x3003A",
     "EventName": "PM_CMPL_STALL_EXCEPTION",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was not allowed to complete because it was interrupted by ANY exception, which has to be serviced before the instruction can complete."
   },
   {
-    "EventCode": "3F044",
+    "EventCode": "0x3F044",
     "EventName": "PM_VSU2_ISSUE",
     "BriefDescription": "VSU instructions issued to VSU pipe 2."
   },
   {
-    "EventCode": "30058",
+    "EventCode": "0x30058",
     "EventName": "PM_TLBIE_FIN",
     "BriefDescription": "TLBIE instructions finished in the LSU. Two TLBIEs can finish each cycle. All will be counted."
   },
   {
-    "EventCode": "3D058",
+    "EventCode": "0x3D058",
     "EventName": "PM_SCALAR_FSQRT_FDIV_ISSUE",
     "BriefDescription": "Scalar versions of four floating point operations: fdiv,fsqrt (xvdivdp, xvdivsp, xvsqrtdp, xvsqrtsp)."
   },
   {
-    "EventCode": "30066",
+    "EventCode": "0x30066",
     "EventName": "PM_LSU_FIN",
     "BriefDescription": "LSU Finished an internal operation (up to 4 per cycle)."
   },
   {
-    "EventCode": "40004",
+    "EventCode": "0x40004",
     "EventName": "PM_FXU_ISSUE",
     "BriefDescription": "A fixed point instruction was issued to the VSU."
   },
   {
-    "EventCode": "40008",
+    "EventCode": "0x40008",
     "EventName": "PM_NTC_ALL_FIN",
     "BriefDescription": "Cycles in which both instructions in the ICT entry pair show as finished. These are the cycles between finish and completion for the oldest pair of instructions in the pipeline."
   },
   {
-    "EventCode": "40010",
+    "EventCode": "0x40010",
     "EventName": "PM_PMC3_OVERFLOW",
     "BriefDescription": "The event selected for PMC3 caused the event counter to overflow."
   },
   {
-    "EventCode": "4C012",
+    "EventCode": "0x4C012",
     "EventName": "PM_EXEC_STALL_DERAT_ONLY_MISS",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered an ERAT miss and waited for it resolve."
   },
   {
-    "EventCode": "4C018",
+    "EventCode": "0x4C018",
     "EventName": "PM_CMPL_STALL",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline cannot complete because the thread was blocked for any reason."
   },
   {
-    "EventCode": "4C01E",
+    "EventCode": "0x4C01E",
     "EventName": "PM_LSU_ST3_FIN",
     "BriefDescription": "LSU Finished an internal operation in ST3 port."
   },
   {
-    "EventCode": "4D018",
+    "EventCode": "0x4D018",
     "EventName": "PM_EXEC_STALL_BRU",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Branch unit."
   },
   {
-    "EventCode": "4D01A",
+    "EventCode": "0x4D01A",
     "EventName": "PM_CMPL_STALL_HWSYNC",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a hwsync waiting for response from L2 before completing."
   },
   {
-    "EventCode": "4D01C",
+    "EventCode": "0x4D01C",
     "EventName": "PM_EXEC_STALL_TLBIEL",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIEL instruction executing in the Load Store Unit. TLBIEL instructions have lower overhead than TLBIE instructions because they don't get set to the nest."
   },
   {
-    "EventCode": "4E012",
+    "EventCode": "0x4E012",
     "EventName": "PM_EXEC_STALL_UNKNOWN",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the NTF finishes and completions came too close together."
   },
   {
-    "EventCode": "4D020",
+    "EventCode": "0x4D020",
     "EventName": "PM_VSU3_ISSUE",
     "BriefDescription": "VSU instruction was issued to VSU pipe 3."
   },
   {
-    "EventCode": "40132",
+    "EventCode": "0x40132",
     "EventName": "PM_MRK_LSU_FIN",
     "BriefDescription": "LSU marked instruction finish."
   },
   {
-    "EventCode": "45058",
+    "EventCode": "0x45058",
     "EventName": "PM_IC_MISS_CMPL",
     "BriefDescription": "Non-speculative icache miss, counted at completion."
   },
   {
-    "EventCode": "4D050",
+    "EventCode": "0x4D050",
     "EventName": "PM_VSU_NON_FLOP_CMPL",
     "BriefDescription": "Non-floating point VSU instructions completed."
   },
   {
-    "EventCode": "4D052",
+    "EventCode": "0x4D052",
     "EventName": "PM_2FLOP_CMPL",
     "BriefDescription": "Double Precision vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg completed."
   },
   {
-    "EventCode": "400F2",
+    "EventCode": "0x400F2",
     "EventName": "PM_1PLUS_PPC_DISP",
     "BriefDescription": "Cycles at least one Instr Dispatched."
   },
   {
-    "EventCode": "400F8",
+    "EventCode": "0x400F8",
     "EventName": "PM_FLUSH",
     "BriefDescription": "Flush (any type)."
   }
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
index ea122a91ceb0..b5d1bd39cfb2 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
@@ -1,21 +1,21 @@
 [
   {
-    "EventCode": "301E8",
+    "EventCode": "0x301E8",
     "EventName": "PM_THRESH_EXC_64",
     "BriefDescription": "Threshold counter exceeded a value of 64."
   },
   {
-    "EventCode": "45050",
+    "EventCode": "0x45050",
     "EventName": "PM_1FLOP_CMPL",
     "BriefDescription": "One floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
   },
   {
-    "EventCode": "45052",
+    "EventCode": "0x45052",
     "EventName": "PM_4FLOP_CMPL",
     "BriefDescription": "Four floating point instructions completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
   },
   {
-    "EventCode": "4D054",
+    "EventCode": "0x4D054",
     "EventName": "PM_8FLOP_CMPL",
     "BriefDescription": "Four Double Precision vector instructions completed."
   }
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
index 5a714e3dd71a..db3766dca07c 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
@@ -1,56 +1,56 @@
 [
   {
-    "EventCode": "1F15E",
+    "EventCode": "0x1F15E",
     "EventName": "PM_MRK_START_PROBE_NOP_CMPL",
     "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed."
   },
   {
-    "EventCode": "20016",
+    "EventCode": "0x20016",
     "EventName": "PM_ST_FIN",
     "BriefDescription": "Store finish count. Includes speculative activity."
   },
   {
-    "EventCode": "20018",
+    "EventCode": "0x20018",
     "EventName": "PM_ST_FWD",
     "BriefDescription": "Store forwards that finished."
   },
   {
-    "EventCode": "2011C",
+    "EventCode": "0x2011C",
     "EventName": "PM_MRK_NTF_CYC",
     "BriefDescription": "Cycles during which the marked instruction is the oldest in the pipeline (NTF or NTC)."
   },
   {
-    "EventCode": "2E01C",
+    "EventCode": "0x2E01C",
     "EventName": "PM_EXEC_STALL_TLBIE",
     "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIE instruction executing in the Load Store Unit."
   },
   {
-    "EventCode": "201E6",
+    "EventCode": "0x201E6",
     "EventName": "PM_THRESH_EXC_32",
     "BriefDescription": "Threshold counter exceeded a value of 32."
   },
   {
-    "EventCode": "200F0",
+    "EventCode": "0x200F0",
     "EventName": "PM_ST_CMPL",
     "BriefDescription": "Stores completed from S2Q (2nd-level store queue). This event includes regular stores, stcx and cache inhibited stores. The following operations are excluded (pteupdate, snoop tlbie complete, store atomics, miso, load atomic payloads, tlbie, tlbsync, slbieg, isync, msgsnd, slbiag, cpabort, copy, tcheck, tend, stsync, dcbst, icbi, dcbf, hwsync, lwsync, ptesync, eieio, msgsync)."
   },
   {
-    "EventCode": "200FE",
+    "EventCode": "0x200FE",
     "EventName": "PM_DATA_FROM_L2MISS",
     "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss."
   },
   {
-    "EventCode": "30010",
+    "EventCode": "0x30010",
     "EventName": "PM_PMC2_OVERFLOW",
     "BriefDescription": "The event selected for PMC2 caused the event counter to overflow."
   },
   {
-    "EventCode": "4D010",
+    "EventCode": "0x4D010",
     "EventName": "PM_PMC1_SAVED",
     "BriefDescription": "The conditions for the speculative event selected for PMC1 are met and PMC1 is charged."
   },
   {
-    "EventCode": "4D05C",
+    "EventCode": "0x4D05C",
     "EventName": "PM_DPP_FLOP_CMPL",
     "BriefDescription": "Double-Precision or Quad-Precision instructions completed."
   }
-- 
cgit v1.2.3


From 000ac42953395a4f0a63d5db640c5e4c88a548c5 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 28 May 2021 15:10:58 -0400
Subject: selftests: kvm: fix overlapping addresses in memslot_perf_test

vm_create allocates memory and maps it close to GPA.  This memory
is separate from what is allocated in subsequent calls to
vm_userspace_mem_region_add, so it is incorrect to pass the
test memory size to vm_create_default.  Just pass a small
fixed amount of memory which can be used later for page table,
otherwise GPAs are already allocated at MEM_GPA and the
test aborts.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/memslot_perf_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index 11239652d805..9307f25d8130 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -267,7 +267,7 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots,
 	data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots);
 	TEST_ASSERT(data->hva_slots, "malloc() fail");
 
-	data->vm = vm_create_default(VCPU_ID, mempages, guest_code);
+	data->vm = vm_create_default(VCPU_ID, 1024, guest_code);
 
 	pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n",
 		max_mem_slots - 1, data->pages_per_slot, rempages);
-- 
cgit v1.2.3