From d1c56bfdaca465bd1d0e913053a9c5cafe8b6a6c Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 3 Feb 2022 14:14:05 +0100
Subject: tests: fix idmapped mount_setattr test
The test treated zero as a successful run when it really should treat
non-zero as a successful run. A mount's idmapping can't change once it
has been attached to the filesystem.
Link: https://lore.kernel.org/r/20220203131411.3093040-2-brauner@kernel.org
Fixes: 01eadc8dd96d ("tests: add mount_setattr() selftests")
Cc: Seth Forshee <seth.forshee@digitalocean.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: linux-fsdevel@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
tools/testing/selftests/mount_setattr/mount_setattr_test.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
index f31205f04ee0..8c5fea68ae67 100644
--- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c
+++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
@@ -1236,7 +1236,7 @@ static int get_userns_fd(unsigned long nsid, unsigned long hostid, unsigned long
}
/**
- * Validate that an attached mount in our mount namespace can be idmapped.
+ * Validate that an attached mount in our mount namespace cannot be idmapped.
* (The kernel enforces that the mount's mount namespace and the caller's mount
* namespace match.)
*/
@@ -1259,7 +1259,7 @@ TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace)
attr.userns_fd = get_userns_fd(0, 10000, 10000);
ASSERT_GE(attr.userns_fd, 0);
- ASSERT_EQ(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
ASSERT_EQ(close(attr.userns_fd), 0);
ASSERT_EQ(close(open_tree_fd), 0);
}
--
cgit v1.2.3
From a7e793a867ae312cecdeb6f06cceff98263e75dd Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@collabora.com>
Date: Thu, 10 Feb 2022 22:13:23 +0500
Subject: selftests/exec: Add non-regular to TEST_GEN_PROGS
non-regular file needs to be compiled and then copied to the output
directory. Remove it from TEST_PROGS and add it to TEST_GEN_PROGS. This
removes error thrown by rsync when non-regular object isn't found:
rsync: [sender] link_stat "/linux/tools/testing/selftests/exec/non-regular" failed: No such file or directory (2)
rsync error: some files/attrs were not transferred (see previous errors) (code 23) at main.c(1333) [sender=3.2.3]
Fixes: 0f71241a8e32 ("selftests/exec: add file type errno tests")
Reported-by: "kernelci.org bot" <bot@kernelci.org>
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Reviewed-by: Shuah Khan <skhan@linuxfoundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
tools/testing/selftests/exec/Makefile | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index 12c5e27d32c1..2d7fca446c7f 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -3,8 +3,8 @@ CFLAGS = -Wall
CFLAGS += -Wno-nonnull
CFLAGS += -D_GNU_SOURCE
-TEST_PROGS := binfmt_script non-regular
-TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216
+TEST_PROGS := binfmt_script
+TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 non-regular
TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir
# Makefile is a run-time dependency, since it's accessed by the execveat test
TEST_FILES := Makefile
--
cgit v1.2.3
From a7e75016a0753c24d6c995bc02501ae35368e333 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Wed, 9 Feb 2022 12:33:24 +0530
Subject: selftests/bpf: Add test for bpf_timer overwriting crash
Add a test that validates that timer value is not overwritten when doing
a copy_map_value call in the kernel. Without the prior fix, this test
triggers a crash.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220209070324.1093182-3-memxor@gmail.com
---
.../testing/selftests/bpf/prog_tests/timer_crash.c | 32 +++++++++++++
tools/testing/selftests/bpf/progs/timer_crash.c | 54 ++++++++++++++++++++++
2 files changed, 86 insertions(+)
create mode 100644 tools/testing/selftests/bpf/prog_tests/timer_crash.c
create mode 100644 tools/testing/selftests/bpf/progs/timer_crash.c
(limited to 'tools')
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
new file mode 100644
index 000000000000..f74b82305da8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "timer_crash.skel.h"
+
+enum {
+ MODE_ARRAY,
+ MODE_HASH,
+};
+
+static void test_timer_crash_mode(int mode)
+{
+ struct timer_crash *skel;
+
+ skel = timer_crash__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load"))
+ return;
+ skel->bss->pid = getpid();
+ skel->bss->crash_map = mode;
+ if (!ASSERT_OK(timer_crash__attach(skel), "timer_crash__attach"))
+ goto end;
+ usleep(1);
+end:
+ timer_crash__destroy(skel);
+}
+
+void test_timer_crash(void)
+{
+ if (test__start_subtest("array"))
+ test_timer_crash_mode(MODE_ARRAY);
+ if (test__start_subtest("hash"))
+ test_timer_crash_mode(MODE_HASH);
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_crash.c b/tools/testing/selftests/bpf/progs/timer_crash.c
new file mode 100644
index 000000000000..f8f7944e70da
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer_crash.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+struct map_elem {
+ struct bpf_timer timer;
+ struct bpf_spin_lock lock;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct map_elem);
+} amap SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct map_elem);
+} hmap SEC(".maps");
+
+int pid = 0;
+int crash_map = 0; /* 0 for amap, 1 for hmap */
+
+SEC("fentry/do_nanosleep")
+int sys_enter(void *ctx)
+{
+ struct map_elem *e, value = {};
+ void *map = crash_map ? (void *)&hmap : (void *)&amap;
+
+ if (bpf_get_current_task_btf()->tgid != pid)
+ return 0;
+
+ *(void **)&value = (void *)0xdeadcaf3;
+
+ bpf_map_update_elem(map, &(int){0}, &value, 0);
+ /* For array map, doing bpf_map_update_elem will do a
+ * check_and_free_timer_in_array, which will trigger the crash if timer
+ * pointer was overwritten, for hmap we need to use bpf_timer_cancel.
+ */
+ if (crash_map == 1) {
+ e = bpf_map_lookup_elem(map, &(int){0});
+ if (!e)
+ return 0;
+ bpf_timer_cancel(&e->timer);
+ }
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
--
cgit v1.2.3
From 21bffcb76ee2fbafc7d5946cef10abc9df5cfff7 Mon Sep 17 00:00:00 2001
From: Sherry Yang <sherry.yang@oracle.com>
Date: Thu, 10 Feb 2022 12:30:49 -0800
Subject: selftests/seccomp: Fix seccomp failure by adding missing headers
seccomp_bpf failed on tests 47 global.user_notification_filter_empty
and 48 global.user_notification_filter_empty_threaded when it's
tested on updated kernel but with old kernel headers. Because old
kernel headers don't have definition of macro __NR_clone3 which is
required for these two tests. Since under selftests/, we can install
headers once for all tests (the default INSTALL_HDR_PATH is
usr/include), fix it by adding usr/include to the list of directories
to be searched. Use "-isystem" to indicate it's a system directory as
the real kernel headers directories are.
Signed-off-by: Sherry Yang <sherry.yang@oracle.com>
Tested-by: Sherry Yang <sherry.yang@oracle.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
tools/testing/selftests/seccomp/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile
index 0ebfe8b0e147..585f7a0c10cb 100644
--- a/tools/testing/selftests/seccomp/Makefile
+++ b/tools/testing/selftests/seccomp/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-CFLAGS += -Wl,-no-as-needed -Wall
+CFLAGS += -Wl,-no-as-needed -Wall -isystem ../../../../usr/include/
LDFLAGS += -lpthread
TEST_GEN_PROGS := seccomp_bpf seccomp_benchmark
--
cgit v1.2.3
From 6fec1ab67f8d60704cc7de64abcfd389ab131542 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Date: Mon, 14 Feb 2022 09:36:57 +0100
Subject: selftests/ftrace: Do not trace do_softirq because of PREEMPT_RT
The PREEMPT_RT patchset does not use do_softirq() function thus trying
to filter for do_softirq fails for such kernel:
echo do_softirq
ftracetest: 81: echo: echo: I/O error
Choose some other visible function for the test. The function does not
have to be actually executed during the test, because it is only testing
filter API interface.
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Reviewed-by: Shuah Khan <skhan@linuxfoundation.org>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
index e96e279e0533..25432b8cd5bd 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
@@ -19,7 +19,7 @@ fail() { # mesg
FILTER=set_ftrace_filter
FUNC1="schedule"
-FUNC2="do_softirq"
+FUNC2="scheduler_tick"
ALL_FUNCS="#### all functions enabled ####"
--
cgit v1.2.3
From 61d06f01f9710b327a53492e5add9f972eb909b3 Mon Sep 17 00:00:00 2001
From: Felix Maurer <fmaurer@redhat.com>
Date: Fri, 11 Feb 2022 18:43:36 +0100
Subject: selftests: bpf: Check bpf_msg_push_data return value
bpf_msg_push_data may return a non-zero value to indicate an error. The
return value should be checked to prevent undetected errors.
To indicate an error, the BPF programs now perform a different action
than their intended one to make the userspace test program notice the
error, i.e., the programs supposed to pass/redirect drop, the program
supposed to drop passes.
Fixes: 84fbfe026acaa ("bpf: test_sockmap add options to use msg_push_data")
Signed-off-by: Felix Maurer <fmaurer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/89f767bb44005d6b4dd1f42038c438f76b3ebfad.1644601294.git.fmaurer@redhat.com
---
.../selftests/bpf/progs/test_sockmap_kern.h | 26 +++++++++++++++-------
1 file changed, 18 insertions(+), 8 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
index 2966564b8497..6c85b00f27b2 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
@@ -235,7 +235,7 @@ SEC("sk_msg1")
int bpf_prog4(struct sk_msg_md *msg)
{
int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
- int *start, *end, *start_push, *end_push, *start_pop, *pop;
+ int *start, *end, *start_push, *end_push, *start_pop, *pop, err = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
@@ -249,8 +249,11 @@ int bpf_prog4(struct sk_msg_md *msg)
bpf_msg_pull_data(msg, *start, *end, 0);
start_push = bpf_map_lookup_elem(&sock_bytes, &two);
end_push = bpf_map_lookup_elem(&sock_bytes, &three);
- if (start_push && end_push)
- bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (start_push && end_push) {
+ err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (err)
+ return SK_DROP;
+ }
start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
pop = bpf_map_lookup_elem(&sock_bytes, &five);
if (start_pop && pop)
@@ -263,6 +266,7 @@ int bpf_prog6(struct sk_msg_md *msg)
{
int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0;
int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f;
+ int err = 0;
__u64 flags = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
@@ -279,8 +283,11 @@ int bpf_prog6(struct sk_msg_md *msg)
start_push = bpf_map_lookup_elem(&sock_bytes, &two);
end_push = bpf_map_lookup_elem(&sock_bytes, &three);
- if (start_push && end_push)
- bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (start_push && end_push) {
+ err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (err)
+ return SK_DROP;
+ }
start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
pop = bpf_map_lookup_elem(&sock_bytes, &five);
@@ -338,7 +345,7 @@ SEC("sk_msg5")
int bpf_prog10(struct sk_msg_md *msg)
{
int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop;
- int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
+ int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, err = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
@@ -352,8 +359,11 @@ int bpf_prog10(struct sk_msg_md *msg)
bpf_msg_pull_data(msg, *start, *end, 0);
start_push = bpf_map_lookup_elem(&sock_bytes, &two);
end_push = bpf_map_lookup_elem(&sock_bytes, &three);
- if (start_push && end_push)
- bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (start_push && end_push) {
+ err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (err)
+ return SK_PASS;
+ }
start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
pop = bpf_map_lookup_elem(&sock_bytes, &five);
if (start_pop && pop)
--
cgit v1.2.3
From f268088f65af69aa6ae1fb65e696cbb6478bcc9a Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Fri, 18 Feb 2022 17:33:33 +0800
Subject: perf test: Skip failing sigtrap test for arm+aarch64
Skip the Sigtrap test for arm + arm64, same as was done for s390 in
commit a840974e96fd ("perf test: Test 73 Sig_trap fails on s390"). For
this, reuse BP_SIGNAL_IS_SUPPORTED - meaning that the arch can use BP to
generate signals - instead of BP_ACCOUNT_IS_SUPPORTED, which is
appropriate.
As described by Will at [0], in the test we get stuck in a loop of
handling the HW breakpoint exception and never making progress. GDB
handles this by stepping over the faulting instruction, but with perf
the kernel is expected to handle the step (which it doesn't for arm).
Dmitry made an attempt to get this work, also mentioned in the same
thread as [0], which was appreciated. But the best thing to do is skip
the test for now.
[0] https://lore.kernel.org/linux-perf-users/20220118124343.GC98966@leoy-ThinkPad-X240s/T/#m13b06c39d2a5100d340f009435df6f4d8ee57b5a
Fixes: 5504f67944484495 ("perf test sigtrap: Add basic stress test for sigtrap handling")
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Marco Elver <elver@google.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Marco Elver <elver@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux@armlinux.org.uk
Link: https://lore.kernel.org/r/1645176813-202756-1-git-send-email-john.garry@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/tests/sigtrap.c | 15 +--------------
1 file changed, 1 insertion(+), 14 deletions(-)
(limited to 'tools')
diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c
index 1f147fe6595f..e32ece90e164 100644
--- a/tools/perf/tests/sigtrap.c
+++ b/tools/perf/tests/sigtrap.c
@@ -22,19 +22,6 @@
#include "tests.h"
#include "../perf-sys.h"
-/*
- * PowerPC and S390 do not support creation of instruction breakpoints using the
- * perf_event interface.
- *
- * Just disable the test for these architectures until these issues are
- * resolved.
- */
-#if defined(__powerpc__) || defined(__s390x__)
-#define BP_ACCOUNT_IS_SUPPORTED 0
-#else
-#define BP_ACCOUNT_IS_SUPPORTED 1
-#endif
-
#define NUM_THREADS 5
static struct {
@@ -135,7 +122,7 @@ static int test__sigtrap(struct test_suite *test __maybe_unused, int subtest __m
char sbuf[STRERR_BUFSIZE];
int i, fd, ret = TEST_FAIL;
- if (!BP_ACCOUNT_IS_SUPPORTED) {
+ if (!BP_SIGNAL_IS_SUPPORTED) {
pr_debug("Test not supported on this architecture");
return TEST_SKIP;
}
--
cgit v1.2.3
From 8a3d2ee0de3828e0d01f9682d35ee53704659bd0 Mon Sep 17 00:00:00 2001
From: Zhengjun Xing <zhengjun.xing@linux.intel.com>
Date: Fri, 18 Feb 2022 17:31:27 +0800
Subject: perf evlist: Fix failed to use cpu list for uncore events
The 'perf record' and 'perf stat' commands have supported the option
'-C/--cpus' to count or collect only on the list of CPUs provided.
Commit 1d3351e631fc34d7 ("perf tools: Enable on a list of CPUs for
hybrid") add it to be supported for hybrid. For hybrid support, it
checks the cpu list are available on hybrid PMU. But when we test only
uncore events(or events not in cpu_core and cpu_atom), there is a bug:
Before:
# perf stat -C0 -e uncore_clock/clockticks/ sleep 1
failed to use cpu list 0
In this case, for uncore event, its pmu_name is not cpu_core or
cpu_atom, so in evlist__fix_hybrid_cpus, perf_pmu__find_hybrid_pmu
should return NULL,both events_nr and unmatched_count should be 0 ,then
the cpu list check function evlist__fix_hybrid_cpus return -1 and the
error "failed to use cpu list 0" will happen. Bypass "events_nr=0" case
then the issue is fixed.
After:
# perf stat -C0 -e uncore_clock/clockticks/ sleep 1
Performance counter stats for 'CPU(s) 0':
195,476,873 uncore_clock/clockticks/
1.004518677 seconds time elapsed
When testing with at least one core event and uncore events, it has no
issue.
# perf stat -C0 -e cpu_core/cpu-cycles/,uncore_clock/clockticks/ sleep 1
Performance counter stats for 'CPU(s) 0':
5,993,774 cpu_core/cpu-cycles/
301,025,912 uncore_clock/clockticks/
1.003964934 seconds time elapsed
Fixes: 1d3351e631fc34d7 ("perf tools: Enable on a list of CPUs for hybrid")
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Zhengjun Xing <zhengjun.xing@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: alexander.shishkin@intel.com
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20220218093127.1844241-1-zhengjun.xing@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/evlist-hybrid.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
(limited to 'tools')
diff --git a/tools/perf/util/evlist-hybrid.c b/tools/perf/util/evlist-hybrid.c
index 7f234215147d..57f02beef023 100644
--- a/tools/perf/util/evlist-hybrid.c
+++ b/tools/perf/util/evlist-hybrid.c
@@ -154,8 +154,8 @@ int evlist__fix_hybrid_cpus(struct evlist *evlist, const char *cpu_list)
perf_cpu_map__put(matched_cpus);
perf_cpu_map__put(unmatched_cpus);
}
-
- ret = (unmatched_count == events_nr) ? -1 : 0;
+ if (events_nr)
+ ret = (unmatched_count == events_nr) ? -1 : 0;
out:
perf_cpu_map__put(cpus);
return ret;
--
cgit v1.2.3
From 0cd33c5ffec12bd77a1c02db2469fac08f840939 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 18 Feb 2022 13:35:38 -0800
Subject: selftests: mptcp: fix diag instability
Instead of waiting for an arbitrary amount of time for the MPTCP
MP_CAPABLE handshake to complete, explicitly wait for the relevant
socket to enter into the established status.
Additionally let the data transfer application use the slowest
transfer mode available (-r), to cope with very slow host, or
high jitter caused by hosting VMs.
Fixes: df62f2ec3df6 ("selftests/mptcp: add diag interface tests")
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/258
Reported-and-tested-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/mptcp/diag.sh | 44 ++++++++++++++++++++++++++-----
1 file changed, 37 insertions(+), 7 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 2674ba20d524..ff821025d309 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -71,6 +71,36 @@ chk_msk_remote_key_nr()
__chk_nr "grep -c remote_key" $*
}
+# $1: ns, $2: port
+wait_local_port_listen()
+{
+ local listener_ns="${1}"
+ local port="${2}"
+
+ local port_hex i
+
+ port_hex="$(printf "%04X" "${port}")"
+ for i in $(seq 10); do
+ ip netns exec "${listener_ns}" cat /proc/net/tcp | \
+ awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
+ break
+ sleep 0.1
+ done
+}
+
+wait_connected()
+{
+ local listener_ns="${1}"
+ local port="${2}"
+
+ local port_hex i
+
+ port_hex="$(printf "%04X" "${port}")"
+ for i in $(seq 10); do
+ ip netns exec ${listener_ns} grep -q " 0100007F:${port_hex} " /proc/net/tcp && break
+ sleep 0.1
+ done
+}
trap cleanup EXIT
ip netns add $ns
@@ -81,15 +111,15 @@ echo "a" | \
ip netns exec $ns \
./mptcp_connect -p 10000 -l -t ${timeout_poll} \
0.0.0.0 >/dev/null &
-sleep 0.1
+wait_local_port_listen $ns 10000
chk_msk_nr 0 "no msk on netns creation"
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10000 -j -t ${timeout_poll} \
+ ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \
127.0.0.1 >/dev/null &
-sleep 0.1
+wait_connected $ns 10000
chk_msk_nr 2 "after MPC handshake "
chk_msk_remote_key_nr 2 "....chk remote_key"
chk_msk_fallback_nr 0 "....chk no fallback"
@@ -101,13 +131,13 @@ echo "a" | \
ip netns exec $ns \
./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \
0.0.0.0 >/dev/null &
-sleep 0.1
+wait_local_port_listen $ns 10001
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10001 -j -t ${timeout_poll} \
+ ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \
127.0.0.1 >/dev/null &
-sleep 0.1
+wait_connected $ns 10001
chk_msk_fallback_nr 1 "check fallback"
flush_pids
@@ -119,7 +149,7 @@ for I in `seq 1 $NR_CLIENTS`; do
./mptcp_connect -p $((I+10001)) -l -w 10 \
-t ${timeout_poll} 0.0.0.0 >/dev/null &
done
-sleep 0.1
+wait_local_port_listen $ns $((NR_CLIENTS + 10001))
for I in `seq 1 $NR_CLIENTS`; do
echo "b" | \
--
cgit v1.2.3
From 5b31dda736e31c58d1941c7349569c7452eafb6b Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 18 Feb 2022 13:35:39 -0800
Subject: selftests: mptcp: improve 'fair usage on close' stability
The mentioned test has to wait for a subflow creation failure.
The current code looks for TCP sockets in TW state and sometimes
misses the relevant event. Switch to a more stable check, looking
for the associated mib counter.
Fixes: 46e967d187ed ("selftests: mptcp: add tests for subflow creation failure")
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/257
Reported-and-tested-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/mptcp/mptcp_join.sh | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index c0801df15f54..10b3bd805ac6 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -961,7 +961,7 @@ wait_for_tw()
local ns=$1
while [ $time -lt $timeout_ms ]; do
- local cnt=$(ip netns exec $ns ss -t state time-wait |wc -l)
+ local cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}')
[ "$cnt" = 1 ] && return 1
time=$((time + 100))
--
cgit v1.2.3
From 6ef84b1517e08f6c2fc105b798a9d21bf4caa6cb Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 18 Feb 2022 13:35:43 -0800
Subject: selftests: mptcp: more robust signal race test
The in kernel MPTCP PM implementation can process a single
incoming add address option at any given time. In the
mentioned test the server can surpass such limit. Let the
setup cope with that allowing a faster add_addr retransmission.
Fixes: a88c9e496937 ("mptcp: do not block subflows creation on errors")
Fixes: f7efc7771eac ("mptcp: drop argument port from mptcp_pm_announce_addr")
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/254
Reported-and-tested-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/mptcp/mptcp_join.sh | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 10b3bd805ac6..0d6a71e7bb59 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -752,11 +752,17 @@ chk_add_nr()
local mis_ack_nr=${8:-0}
local count
local dump_stats
+ local timeout
+
+ timeout=`ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout`
printf "%-39s %s" " " "add"
- count=`ip netns exec $ns2 nstat -as | grep MPTcpExtAddAddr | awk '{print $2}'`
+ count=`ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}'`
[ -z "$count" ] && count=0
- if [ "$count" != "$add_nr" ]; then
+
+ # if the test configured a short timeout tolerate greater then expected
+ # add addrs options, due to retransmissions
+ if [ "$count" != "$add_nr" ] && [ "$timeout" -gt 1 -o "$count" -lt "$add_nr" ]; then
echo "[fail] got $count ADD_ADDR[s] expected $add_nr"
ret=1
dump_stats=1
@@ -1158,7 +1164,10 @@ signal_address_tests()
ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags signal
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags signal
ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags signal
- run_tests $ns1 $ns2 10.0.1.1
+
+ # the peer could possibly miss some addr notification, allow retransmission
+ ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1
+ run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow
chk_join_nr "signal addresses race test" 3 3 3
# the server will not signal the address terminating
--
cgit v1.2.3
From e35f885b357d47e04380a2056d1b2cc3e6f4f24b Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 18 Feb 2022 13:35:44 -0800
Subject: selftests: mptcp: be more conservative with cookie MPJ limits
Since commit 2843ff6f36db ("mptcp: remote addresses fullmesh"), an
MPTCP client can attempt creating multiple MPJ subflow simultaneusly.
In such scenario the server, when syncookies are enabled, could end-up
accepting incoming MPJ syn even above the configured subflow limit, as
the such limit can be enforced in a reliable way only after the subflow
creation. In case of syncookie, only after the 3rd ack reception.
As a consequence the related self-tests case sporadically fails, as it
verify that the server always accept the expected number of MPJ syn.
Address the issues relaxing the MPJ syn number constrain. Note that the
check on the accepted number of MPJ 3rd ack still remains intact.
Fixes: 2843ff6f36db ("mptcp: remote addresses fullmesh")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/mptcp/mptcp_join.sh | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 0d6a71e7bb59..0c8a2a20b96c 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -660,6 +660,7 @@ chk_join_nr()
local ack_nr=$4
local count
local dump_stats
+ local with_cookie
printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn"
count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'`
@@ -673,12 +674,20 @@ chk_join_nr()
fi
echo -n " - synack"
+ with_cookie=`ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies`
count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}'`
[ -z "$count" ] && count=0
if [ "$count" != "$syn_ack_nr" ]; then
- echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr"
- ret=1
- dump_stats=1
+ # simult connections exceeding the limit with cookie enabled could go up to
+ # synack validation as the conn limit can be enforced reliably only after
+ # the subflow creation
+ if [ "$with_cookie" = 2 ] && [ "$count" -gt "$syn_ack_nr" ] && [ "$count" -le "$syn_nr" ]; then
+ echo -n "[ ok ]"
+ else
+ echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr"
+ ret=1
+ dump_stats=1
+ fi
else
echo -n "[ ok ]"
fi
--
cgit v1.2.3
From d45476d9832409371537013ebdd8dc1a7781f97a Mon Sep 17 00:00:00 2001
From: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Date: Wed, 16 Feb 2022 20:57:00 +0100
Subject: x86/speculation: Rename RETPOLINE_AMD to RETPOLINE_LFENCE
The RETPOLINE_AMD name is unfortunate since it isn't necessarily
AMD only, in fact Hygon also uses it. Furthermore it will likely be
sufficient for some Intel processors. Therefore rename the thing to
RETPOLINE_LFENCE to better describe what it is.
Add the spectre_v2=retpoline,lfence option as an alias to
spectre_v2=retpoline,amd to preserve existing setups. However, the output
of /sys/devices/system/cpu/vulnerabilities/spectre_v2 will be changed.
[ bp: Fix typos, massage. ]
Co-developed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/x86/include/asm/cpufeatures.h | 2 +-
arch/x86/include/asm/nospec-branch.h | 12 ++++++------
arch/x86/kernel/alternative.c | 8 ++++----
arch/x86/kernel/cpu/bugs.c | 29 ++++++++++++++++++-----------
arch/x86/lib/retpoline.S | 2 +-
arch/x86/net/bpf_jit_comp.c | 2 +-
tools/arch/x86/include/asm/cpufeatures.h | 2 +-
7 files changed, 32 insertions(+), 25 deletions(-)
(limited to 'tools')
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 6db4e2932b3d..65d147974f8d 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -204,7 +204,7 @@
/* FREE! ( 7*32+10) */
#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */
#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index cc74dc584836..c91d97bee237 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -84,7 +84,7 @@
#ifdef CONFIG_RETPOLINE
ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
__stringify(jmp __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \
- __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD
+ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_LFENCE
#else
jmp *%\reg
#endif
@@ -94,7 +94,7 @@
#ifdef CONFIG_RETPOLINE
ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \
__stringify(call __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \
- __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_AMD
+ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_LFENCE
#else
call *%\reg
#endif
@@ -146,7 +146,7 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[];
"lfence;\n" \
ANNOTATE_RETPOLINE_SAFE \
"call *%[thunk_target]\n", \
- X86_FEATURE_RETPOLINE_AMD)
+ X86_FEATURE_RETPOLINE_LFENCE)
# define THUNK_TARGET(addr) [thunk_target] "r" (addr)
@@ -176,7 +176,7 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[];
"lfence;\n" \
ANNOTATE_RETPOLINE_SAFE \
"call *%[thunk_target]\n", \
- X86_FEATURE_RETPOLINE_AMD)
+ X86_FEATURE_RETPOLINE_LFENCE)
# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
#endif
@@ -188,8 +188,8 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[];
/* The Spectre V2 mitigation variants */
enum spectre_v2_mitigation {
SPECTRE_V2_NONE,
- SPECTRE_V2_RETPOLINE_GENERIC,
- SPECTRE_V2_RETPOLINE_AMD,
+ SPECTRE_V2_RETPOLINE,
+ SPECTRE_V2_LFENCE,
SPECTRE_V2_IBRS_ENHANCED,
};
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 5007c3ffe96f..b4470eabf151 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -389,7 +389,7 @@ static int emit_indirect(int op, int reg, u8 *bytes)
*
* CALL *%\reg
*
- * It also tries to inline spectre_v2=retpoline,amd when size permits.
+ * It also tries to inline spectre_v2=retpoline,lfence when size permits.
*/
static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
{
@@ -407,7 +407,7 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
BUG_ON(reg == 4);
if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
- !cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD))
+ !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE))
return -1;
op = insn->opcode.bytes[0];
@@ -438,9 +438,9 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
}
/*
- * For RETPOLINE_AMD: prepend the indirect CALL/JMP with an LFENCE.
+ * For RETPOLINE_LFENCE: prepend the indirect CALL/JMP with an LFENCE.
*/
- if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) {
+ if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
bytes[i++] = 0x0f;
bytes[i++] = 0xae;
bytes[i++] = 0xe8; /* LFENCE */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 1c1f218a701d..e3bb8afc6768 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -664,7 +664,7 @@ enum spectre_v2_mitigation_cmd {
SPECTRE_V2_CMD_FORCE,
SPECTRE_V2_CMD_RETPOLINE,
SPECTRE_V2_CMD_RETPOLINE_GENERIC,
- SPECTRE_V2_CMD_RETPOLINE_AMD,
+ SPECTRE_V2_CMD_RETPOLINE_LFENCE,
};
enum spectre_v2_user_cmd {
@@ -824,8 +824,8 @@ set_mode:
static const char * const spectre_v2_strings[] = {
[SPECTRE_V2_NONE] = "Vulnerable",
- [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline",
- [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline",
+ [SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines",
+ [SPECTRE_V2_LFENCE] = "Mitigation: LFENCE",
[SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS",
};
@@ -837,7 +837,8 @@ static const struct {
{ "off", SPECTRE_V2_CMD_NONE, false },
{ "on", SPECTRE_V2_CMD_FORCE, true },
{ "retpoline", SPECTRE_V2_CMD_RETPOLINE, false },
- { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false },
+ { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_LFENCE, false },
+ { "retpoline,lfence", SPECTRE_V2_CMD_RETPOLINE_LFENCE, false },
{ "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false },
{ "auto", SPECTRE_V2_CMD_AUTO, false },
};
@@ -875,13 +876,19 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
}
if ((cmd == SPECTRE_V2_CMD_RETPOLINE ||
- cmd == SPECTRE_V2_CMD_RETPOLINE_AMD ||
+ cmd == SPECTRE_V2_CMD_RETPOLINE_LFENCE ||
cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) &&
!IS_ENABLED(CONFIG_RETPOLINE)) {
pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option);
return SPECTRE_V2_CMD_AUTO;
}
+ if ((cmd == SPECTRE_V2_CMD_RETPOLINE_LFENCE) &&
+ !boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
+ pr_err("%s selected, but CPU doesn't have a serializing LFENCE. Switching to AUTO select\n", mitigation_options[i].option);
+ return SPECTRE_V2_CMD_AUTO;
+ }
+
spec_v2_print_cond(mitigation_options[i].option,
mitigation_options[i].secure);
return cmd;
@@ -916,9 +923,9 @@ static void __init spectre_v2_select_mitigation(void)
if (IS_ENABLED(CONFIG_RETPOLINE))
goto retpoline_auto;
break;
- case SPECTRE_V2_CMD_RETPOLINE_AMD:
+ case SPECTRE_V2_CMD_RETPOLINE_LFENCE:
if (IS_ENABLED(CONFIG_RETPOLINE))
- goto retpoline_amd;
+ goto retpoline_lfence;
break;
case SPECTRE_V2_CMD_RETPOLINE_GENERIC:
if (IS_ENABLED(CONFIG_RETPOLINE))
@@ -935,17 +942,17 @@ static void __init spectre_v2_select_mitigation(void)
retpoline_auto:
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
- retpoline_amd:
+ retpoline_lfence:
if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n");
goto retpoline_generic;
}
- mode = SPECTRE_V2_RETPOLINE_AMD;
- setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD);
+ mode = SPECTRE_V2_LFENCE;
+ setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE);
setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
} else {
retpoline_generic:
- mode = SPECTRE_V2_RETPOLINE_GENERIC;
+ mode = SPECTRE_V2_RETPOLINE;
setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
}
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 89b3fb244e15..afbdda539b80 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -34,7 +34,7 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
__stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \
- __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_AMD
+ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE
.endm
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 2b1e266ff95c..0ecb140864b2 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -394,7 +394,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
u8 *prog = *pprog;
#ifdef CONFIG_RETPOLINE
- if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) {
+ if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
EMIT_LFENCE();
EMIT2(0xFF, 0xE0 + reg);
} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 6db4e2932b3d..ab4e53715d8a 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -204,7 +204,7 @@
/* FREE! ( 7*32+10) */
#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCEs for Spectre variant 2 */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */
#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
--
cgit v1.2.3
From 221944736f66f38e9bdbce52c616d10df7f15c54 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Wed, 16 Feb 2022 12:43:30 -0800
Subject: tools/cgroup/slabinfo: update to work with struct slab
After the introduction of the dedicated struct slab to describe slab
pages by commit d122019bf061 ("mm: Split slab into its own type") and
the following removal of the corresponding struct page's fields by
commit 07f910f9b729 ("mm: Remove slab from struct page") the
memcg_slabinfo tool broke. An attempt to run it produces a trace like
this:
Traceback (most recent call last):
File "/usr/bin/drgn", line 33, in <module>
sys.exit(load_entry_point('drgn==0.0.16', 'console_scripts', 'drgn')())
File "/usr/lib64/python3.9/site-packages/drgn/internal/cli.py", line 133, in main
runpy.run_path(args.script[0], init_globals=init_globals, run_name="__main__")
File "/usr/lib64/python3.9/runpy.py", line 268, in run_path
return _run_module_code(code, init_globals, run_name,
File "/usr/lib64/python3.9/runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "/usr/lib64/python3.9/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "memcg_slabinfo.py", line 226, in <module>
main()
File "memcg_slabinfo.py", line 199, in main
cache = page.slab_cache
AttributeError: 'struct page' has no member 'slab_cache'
The problem can be fixed by explicitly casting struct page * to struct
slab * for slab pages. The tools works as expected with this fix, e.g.:
cred_jar 776 776 192 21 1 : tunables 0 0 0 : slabdata 547 547 0
kmalloc-cg-32 6 6 32 128 1 : tunables 0 0 0 : slabdata 9 9 0
files_cache 3 3 832 39 8 : tunables 0 0 0 : slabdata 8 8 0
kmalloc-cg-512 1 1 512 32 4 : tunables 0 0 0 : slabdata 10 10 0
task_struct 10 10 6720 4 8 : tunables 0 0 0 : slabdata 63 63 0
mm_struct 3 3 1664 19 8 : tunables 0 0 0 : slabdata 9 9 0
kmalloc-cg-16 1 1 16 256 1 : tunables 0 0 0 : slabdata 8 8 0
pde_opener 1 1 40 102 1 : tunables 0 0 0 : slabdata 8 8 0
anon_vma_chain 375 375 64 64 1 : tunables 0 0 0 : slabdata 81 81 0
radix_tree_node 3 3 584 28 4 : tunables 0 0 0 : slabdata 419 419 0
dentry 98 98 312 26 2 : tunables 0 0 0 : slabdata 1420 1420 0
btrfs_inode 3 3 2368 13 8 : tunables 0 0 0 : slabdata 730 730 0
signal_cache 3 3 1600 20 8 : tunables 0 0 0 : slabdata 17 17 0
sighand_cache 3 3 2240 14 8 : tunables 0 0 0 : slabdata 20 20 0
filp 90 90 512 32 4 : tunables 0 0 0 : slabdata 95 95 0
anon_vma 214 214 200 20 1 : tunables 0 0 0 : slabdata 162 162 0
kmalloc-cg-1k 1 1 1024 32 8 : tunables 0 0 0 : slabdata 22 22 0
pid 10 10 256 32 2 : tunables 0 0 0 : slabdata 14 14 0
kmalloc-cg-64 2 2 64 64 1 : tunables 0 0 0 : slabdata 8 8 0
kmalloc-cg-96 3 3 96 42 1 : tunables 0 0 0 : slabdata 8 8 0
sock_inode_cache 5 5 1408 23 8 : tunables 0 0 0 : slabdata 29 29 0
UNIX 7 7 1920 17 8 : tunables 0 0 0 : slabdata 21 21 0
inode_cache 36 36 1152 28 8 : tunables 0 0 0 : slabdata 680 680 0
proc_inode_cache 26 26 1224 26 8 : tunables 0 0 0 : slabdata 64 64 0
kmalloc-cg-2k 2 2 2048 16 8 : tunables 0 0 0 : slabdata 9 9 0
v2: change naming and count_partial()/count_free()/for_each_slab()
signatures to work with slabs, suggested by Matthew Wilcox
Fixes: 07f910f9b729 ("mm: Remove slab from struct page")
Reported-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: Roman Gushchin <guro@fb.com>
Tested-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/linux-patches/Yg2cKKnIboNu7j+p@carbon.DHCP.thefacebook.com/
---
tools/cgroup/memcg_slabinfo.py | 30 +++++++++++++++---------------
1 file changed, 15 insertions(+), 15 deletions(-)
(limited to 'tools')
diff --git a/tools/cgroup/memcg_slabinfo.py b/tools/cgroup/memcg_slabinfo.py
index 1600b17dbb8a..1d3a90d93fe2 100644
--- a/tools/cgroup/memcg_slabinfo.py
+++ b/tools/cgroup/memcg_slabinfo.py
@@ -11,7 +11,7 @@ from drgn.helpers.linux import list_for_each_entry, list_empty
from drgn.helpers.linux import for_each_page
from drgn.helpers.linux.cpumask import for_each_online_cpu
from drgn.helpers.linux.percpu import per_cpu_ptr
-from drgn import container_of, FaultError, Object
+from drgn import container_of, FaultError, Object, cast
DESC = """
@@ -69,15 +69,15 @@ def oo_objects(s):
def count_partial(n, fn):
- nr_pages = 0
- for page in list_for_each_entry('struct page', n.partial.address_of_(),
- 'lru'):
- nr_pages += fn(page)
- return nr_pages
+ nr_objs = 0
+ for slab in list_for_each_entry('struct slab', n.partial.address_of_(),
+ 'slab_list'):
+ nr_objs += fn(slab)
+ return nr_objs
-def count_free(page):
- return page.objects - page.inuse
+def count_free(slab):
+ return slab.objects - slab.inuse
def slub_get_slabinfo(s, cfg):
@@ -145,14 +145,14 @@ def detect_kernel_config():
return cfg
-def for_each_slab_page(prog):
+def for_each_slab(prog):
PGSlab = 1 << prog.constant('PG_slab')
PGHead = 1 << prog.constant('PG_head')
for page in for_each_page(prog):
try:
if page.flags.value_() & PGSlab:
- yield page
+ yield cast('struct slab *', page)
except FaultError:
pass
@@ -190,13 +190,13 @@ def main():
'list'):
obj_cgroups.add(ptr.value_())
- # look over all slab pages, belonging to non-root memcgs
- # and look for objects belonging to the given memory cgroup
- for page in for_each_slab_page(prog):
- objcg_vec_raw = page.memcg_data.value_()
+ # look over all slab folios and look for objects belonging
+ # to the given memory cgroup
+ for slab in for_each_slab(prog):
+ objcg_vec_raw = slab.memcg_data.value_()
if objcg_vec_raw == 0:
continue
- cache = page.slab_cache
+ cache = slab.slab_cache
if not cache:
continue
addr = cache.value_()
--
cgit v1.2.3
From 93b71801a8274cd9511557faf04365a5de487197 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Tue, 22 Feb 2022 09:06:54 -0500
Subject: KVM: PPC: reserve capability 210 for KVM_CAP_PPC_AIL_MODE_3
Add KVM_CAP_PPC_AIL_MODE_3 to advertise the capability to set the AIL
resource mode to 3 with the H_SET_MODE hypercall. This capability
differs between processor types and KVM types (PR, HV, Nested HV), and
affects guest-visible behaviour.
QEMU will implement a cap-ail-mode-3 to control this behaviour[1], and
use the KVM CAP if available to determine KVM support[2].
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
Documentation/virt/kvm/api.rst | 14 ++++++++++++++
include/uapi/linux/kvm.h | 1 +
tools/include/uapi/linux/kvm.h | 1 +
3 files changed, 16 insertions(+)
(limited to 'tools')
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index a4267104db50..9954568c7eab 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6997,6 +6997,20 @@ indicated by the fd to the VM this is called on.
This is intended to support intra-host migration of VMs between userspace VMMs,
upgrading the VMM process without interrupting the guest.
+7.30 KVM_CAP_PPC_AIL_MODE_3
+-------------------------------
+
+:Capability: KVM_CAP_PPC_AIL_MODE_3
+:Architectures: ppc
+:Type: vm
+
+This capability indicates that the kernel supports the mode 3 setting for the
+"Address Translation Mode on Interrupt" aka "Alternate Interrupt Location"
+resource that is controlled with the H_SET_MODE hypercall.
+
+This capability allows a guest kernel to use a better-performance mode for
+handling interrupts and system calls.
+
8. Other capabilities.
======================
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 5191b57e1562..507ee1f2aa96 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1134,6 +1134,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_VM_GPA_BITS 207
#define KVM_CAP_XSAVE2 208
#define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_PPC_AIL_MODE_3 210
#ifdef KVM_CAP_IRQ_ROUTING
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 5191b57e1562..507ee1f2aa96 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1134,6 +1134,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_VM_GPA_BITS 207
#define KVM_CAP_XSAVE2 208
#define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_PPC_AIL_MODE_3 210
#ifdef KVM_CAP_IRQ_ROUTING
--
cgit v1.2.3
From 69560e366fc4d5fca7bebb0e44edbfafc8bcaf05 Mon Sep 17 00:00:00 2001
From: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Date: Fri, 18 Feb 2022 18:23:41 +0300
Subject: perf data: Fix double free in perf_session__delete()
When perf_data__create_dir() fails, it calls close_dir(), but
perf_session__delete() also calls close_dir() and since dir.version and
dir.nr were initialized by perf_data__create_dir(), a double free occurs.
This patch moves the initialization of dir.version and dir.nr after
successful initialization of dir.files, that prevents double freeing.
This behavior is already implemented in perf_data__open_dir().
Fixes: 145520631130bd64 ("perf data: Add perf_data__(create_dir|close_dir) functions")
Signed-off-by: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Antonov <alexander.antonov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Budankov <abudankov@huawei.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220218152341.5197-2-alexey.v.bayduraev@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/data.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
(limited to 'tools')
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index f5d260b1df4d..15a4547d608e 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -44,10 +44,6 @@ int perf_data__create_dir(struct perf_data *data, int nr)
if (!files)
return -ENOMEM;
- data->dir.version = PERF_DIR_VERSION;
- data->dir.files = files;
- data->dir.nr = nr;
-
for (i = 0; i < nr; i++) {
struct perf_data_file *file = &files[i];
@@ -62,6 +58,9 @@ int perf_data__create_dir(struct perf_data *data, int nr)
file->fd = ret;
}
+ data->dir.version = PERF_DIR_VERSION;
+ data->dir.files = files;
+ data->dir.nr = nr;
return 0;
out_err:
--
cgit v1.2.3
From 5b061a322b05a5e023d9a0df1ae1f8bb562ed87b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 7 Aug 2020 08:45:47 -0300
Subject: tools arch x86: Sync the msr-index.h copy with the kernel sources
To pick up the changes in:
3915035282573c5e ("KVM: x86: SVM: move avic definitions from AMD's spec to svm.h")
Addressing these tools/perf build warnings:
diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h
Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h'
That makes the beautification scripts to pick some new entries:
$ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before
$ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h
$ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after
$ diff -u before after
--- before 2022-02-22 17:35:36.996271430 -0300
+++ after 2022-02-22 17:35:46.258503347 -0300
@@ -287,6 +287,7 @@
[0xc0010114 - x86_AMD_V_KVM_MSRs_offset] = "VM_CR",
[0xc0010115 - x86_AMD_V_KVM_MSRs_offset] = "VM_IGNNE",
[0xc0010117 - x86_AMD_V_KVM_MSRs_offset] = "VM_HSAVE_PA",
+ [0xc001011b - x86_AMD_V_KVM_MSRs_offset] = "AMD64_SVM_AVIC_DOORBELL",
[0xc001011e - x86_AMD_V_KVM_MSRs_offset] = "AMD64_VM_PAGE_FLUSH",
[0xc001011f - x86_AMD_V_KVM_MSRs_offset] = "AMD64_VIRT_SPEC_CTRL",
[0xc0010130 - x86_AMD_V_KVM_MSRs_offset] = "AMD64_SEV_ES_GHCB",
$
And this gets rebuilt:
CC /tmp/build/perf/trace/beauty/tracepoints/x86_msr.o
LD /tmp/build/perf/trace/beauty/tracepoints/perf-in.o
LD /tmp/build/perf/trace/beauty/perf-in.o
CC /tmp/build/perf/util/amd-sample-raw.o
LD /tmp/build/perf/util/perf-in.o
LD /tmp/build/perf/perf-in.o
LINK /tmp/build/perf/perf
Now one can trace systemwide asking to see backtraces to where those
MSRs are being read/written with:
# perf trace -e msr:*_msr/max-stack=32/ --filter="msr>=AMD64_SVM_AVIC_DOORBELL && msr<=AMD64_SEV_ES_GHCB"
^C#
If we use -v (verbose mode) we can see what it does behind the scenes:
# perf trace -v -e msr:*_msr/max-stack=32/ --filter="msr>=AMD64_SVM_AVIC_DOORBELL && msr<=AMD64_SEV_ES_GHCB"
Using CPUID AuthenticAMD-25-21-0
0xc001011b
0xc0010130
New filter for msr:read_msr: (msr>=0xc001011b && msr<=0xc0010130) && (common_pid != 1019953 && common_pid != 3629)
0xc001011b
0xc0010130
New filter for msr:write_msr: (msr>=0xc001011b && msr<=0xc0010130) && (common_pid != 1019953 && common_pid != 3629)
mmap size 528384B
^C#
Example with a frequent msr:
# perf trace -v -e msr:*_msr/max-stack=32/ --filter="msr==IA32_SPEC_CTRL" --max-events 2
Using CPUID AuthenticAMD-25-21-0
0x48
New filter for msr:read_msr: (msr==0x48) && (common_pid != 2612129 && common_pid != 3841)
0x48
New filter for msr:write_msr: (msr==0x48) && (common_pid != 2612129 && common_pid != 3841)
mmap size 528384B
Looking at the vmlinux_path (8 entries long)
symsrc__init: build id mismatch for vmlinux.
Using /proc/kcore for kernel data
Using /proc/kallsyms for symbols
0.000 Timer/2525383 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
do_trace_write_msr ([kernel.kallsyms])
do_trace_write_msr ([kernel.kallsyms])
__switch_to_xtra ([kernel.kallsyms])
__switch_to ([kernel.kallsyms])
__schedule ([kernel.kallsyms])
schedule ([kernel.kallsyms])
futex_wait_queue_me ([kernel.kallsyms])
futex_wait ([kernel.kallsyms])
do_futex ([kernel.kallsyms])
__x64_sys_futex ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
__futex_abstimed_wait_common64 (/usr/lib64/libpthread-2.33.so)
0.030 :0/0 msr:write_msr(msr: IA32_SPEC_CTRL, val: 2)
do_trace_write_msr ([kernel.kallsyms])
do_trace_write_msr ([kernel.kallsyms])
__switch_to_xtra ([kernel.kallsyms])
__switch_to ([kernel.kallsyms])
__schedule ([kernel.kallsyms])
schedule_idle ([kernel.kallsyms])
do_idle ([kernel.kallsyms])
cpu_startup_entry ([kernel.kallsyms])
secondary_startup_64_no_verify ([kernel.kallsyms])
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Maxim Levitsky <mlevitsk@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: http://lore.kernel.org/lkml/YhVKxaft+z8rpOfy@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/x86/include/asm/msr-index.h | 1 +
1 file changed, 1 insertion(+)
(limited to 'tools')
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 3faf0f97edb1..a4a39c3e0f19 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -476,6 +476,7 @@
#define MSR_AMD64_ICIBSEXTDCTL 0xc001103c
#define MSR_AMD64_IBSOPDATA4 0xc001103d
#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b
#define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e
#define MSR_AMD64_SEV_ES_GHCB 0xc0010130
#define MSR_AMD64_SEV 0xc0010131
--
cgit v1.2.3
From 13e741b834538a225512912608f0182079fc64e2 Mon Sep 17 00:00:00 2001
From: German Gomez <german.gomez@arm.com>
Date: Mon, 21 Feb 2022 17:17:06 +0000
Subject: perf script: Fix error when printing 'weight' field
In SPE traces the 'weight' field can't be printed in 'perf script'
because the 'dummy:u' event doesn't have the WEIGHT attribute set.
Use evsel__do_check_stype(..) to check this field, as it's done with
other fields such as "phys_addr".
Before:
$ perf record -e arm_spe_0// -- sleep 1
$ perf script -F event,ip,weight
Samples for 'dummy:u' event do not have WEIGHT attribute set. Cannot print 'weight' field.
After:
$ perf script -F event,ip,weight
l1d-access: 12 ffffaf629d4cb320
tlb-access: 12 ffffaf629d4cb320
memory: 12 ffffaf629d4cb320
Fixes: b0fde9c6e291e528 ("perf arm-spe: Add SPE total latency as PERF_SAMPLE_WEIGHT")
Signed-off-by: German Gomez <german.gomez@arm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20220221171707.62960-1-german.gomez@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-script.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index abae8184e171..fa478ddcd18a 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -463,7 +463,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
return -EINVAL;
if (PRINT_FIELD(WEIGHT) &&
- evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT))
+ evsel__do_check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT, allow_user_set))
return -EINVAL;
if (PRINT_FIELD(SYM) &&
--
cgit v1.2.3
From 63bb8239d80571204c61d19c73f7bf5e3d9ef5fa Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 24 Feb 2022 16:52:58 -0800
Subject: selftests: mptcp: do complete cleanup at exit
After commit 05be5e273c84 ("selftests: mptcp: add disconnect tests")
the mptcp selftests leave behind a couple of tmp files after
each run. run_tests_disconnect() misnames a few variables used to
track them. Address the issue setting the appropriate global variables
Fixes: 05be5e273c84 ("selftests: mptcp: add disconnect tests")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/mptcp/mptcp_connect.sh | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index cb5809b89081..f0f4ab96b8f3 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -763,8 +763,8 @@ run_tests_disconnect()
run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-I 3 -i $old_cin"
# restore previous status
- cout=$old_cout
- cout_disconnect="$cout".disconnect
+ sin=$old_sin
+ sin_disconnect="$cout".disconnect
cin=$old_cin
cin_disconnect="$cin".disconnect
connect_per_transfer=1
--
cgit v1.2.3
From 456f89e0928ab938122a40e9f094a6524cc158b4 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Wed, 23 Feb 2022 13:16:24 +0000
Subject: KVM: selftests: aarch64: Skip tests if we can't create a vgic-v3
The arch_timer and vgic_irq kselftests assume that they can create a
vgic-v3, using the library function vgic_v3_setup() which aborts with a
test failure if it is not possible to do so. Since vgic-v3 can only be
instantiated on systems where the host has GICv3 this leads to false
positives on older systems where that is not the case.
Fix this by changing vgic_v3_setup() to return an error if the vgic can't
be instantiated and have the callers skip if this happens. We could also
exit flagging a skip in vgic_v3_setup() but this would prevent future test
cases conditionally deciding which GIC to use or generally doing more
complex output.
Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Tested-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220223131624.1830351-1-broonie@kernel.org
---
tools/testing/selftests/kvm/aarch64/arch_timer.c | 7 ++++++-
tools/testing/selftests/kvm/aarch64/vgic_irq.c | 4 ++++
tools/testing/selftests/kvm/lib/aarch64/vgic.c | 4 +++-
3 files changed, 13 insertions(+), 2 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index 9ad38bd360a4..b08d30bf71c5 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -366,6 +366,7 @@ static struct kvm_vm *test_vm_create(void)
{
struct kvm_vm *vm;
unsigned int i;
+ int ret;
int nr_vcpus = test_args.nr_vcpus;
vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
@@ -382,7 +383,11 @@ static struct kvm_vm *test_vm_create(void)
ucall_init(vm, NULL);
test_init_timer_irq(vm);
- vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+ ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+ if (ret < 0) {
+ print_skip("Failed to create vgic-v3");
+ exit(KSFT_SKIP);
+ }
/* Make all the test's cmdline args visible to the guest */
sync_global_to_guest(vm, test_args);
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
index e6c7d7f8fbd1..7eca97799917 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
@@ -761,6 +761,10 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
gic_fd = vgic_v3_setup(vm, 1, nr_irqs,
GICD_BASE_GPA, GICR_BASE_GPA);
+ if (gic_fd < 0) {
+ print_skip("Failed to create vgic-v3, skipping");
+ exit(KSFT_SKIP);
+ }
vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT,
guest_irq_handlers[args.eoi_split][args.level_sensitive]);
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
index b3a0fca0d780..f5cd0c536d85 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -52,7 +52,9 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
nr_vcpus, nr_vcpus_created);
/* Distributor setup */
- gic_fd = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+ if (_kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3,
+ false, &gic_fd) != 0)
+ return -1;
kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS,
0, &nr_irqs, true);
--
cgit v1.2.3
From dd48f316a1216fa10f9ba26852457794417d9bc6 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Fri, 18 Feb 2022 18:57:07 +0100
Subject: rtla/hist: Make -E the short version of --entries
Currently, --entries uses -e as the short version in the hist mode of
timerlat and osnoise tools. But as -e is already used to enable events
on trace sessions by other tools, thus let's keep it available for the
same usage for all rtla tools.
Make -E the short version of --entries for hist mode on all tools.
Note: rtla was merged in this merge window, so rtla was not released yet.
Link: https://lkml.kernel.org/r/5dbf0cbe7364d3a05e708926b41a097c59a02b1e.1645206561.git.bristot@kernel.org
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
Documentation/tools/rtla/common_hist_options.rst | 2 +-
Documentation/tools/rtla/rtla-osnoise-hist.rst | 2 +-
tools/tracing/rtla/src/osnoise_hist.c | 10 +++++-----
tools/tracing/rtla/src/timerlat_hist.c | 10 +++++-----
4 files changed, 12 insertions(+), 12 deletions(-)
(limited to 'tools')
diff --git a/Documentation/tools/rtla/common_hist_options.rst b/Documentation/tools/rtla/common_hist_options.rst
index 0266cd08a6c9..df53ff835bfb 100644
--- a/Documentation/tools/rtla/common_hist_options.rst
+++ b/Documentation/tools/rtla/common_hist_options.rst
@@ -2,7 +2,7 @@
Set the histogram bucket size (default *1*).
-**-e**, **--entries** *N*
+**-E**, **--entries** *N*
Set the number of entries of the histogram (default 256).
diff --git a/Documentation/tools/rtla/rtla-osnoise-hist.rst b/Documentation/tools/rtla/rtla-osnoise-hist.rst
index 52298ddd8701..f2e79d22c4c4 100644
--- a/Documentation/tools/rtla/rtla-osnoise-hist.rst
+++ b/Documentation/tools/rtla/rtla-osnoise-hist.rst
@@ -36,7 +36,7 @@ default). The reason for reducing the runtime is to avoid starving the
**rtla** tool. The tool is also set to run for *one minute*. The output
histogram is set to group outputs in buckets of *10us* and *25* entries::
- [root@f34 ~/]# rtla osnoise hist -P F:1 -c 0-11 -r 900000 -d 1M -b 10 -e 25
+ [root@f34 ~/]# rtla osnoise hist -P F:1 -c 0-11 -r 900000 -d 1M -b 10 -E 25
# RTLA osnoise histogram
# Time unit is microseconds (us)
# Duration: 0 00:01:00
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index 1f0b7fce55cf..52c053cc1789 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -426,7 +426,7 @@ static void osnoise_hist_usage(char *usage)
static const char * const msg[] = {
"",
" usage: rtla osnoise hist [-h] [-D] [-d s] [-p us] [-r us] [-s us] [-S us] [-t[=file]] \\",
- " [-c cpu-list] [-P priority] [-b N] [-e N] [--no-header] [--no-summary] \\",
+ " [-c cpu-list] [-P priority] [-b N] [-E N] [--no-header] [--no-summary] \\",
" [--no-index] [--with-zeros]",
"",
" -h/--help: print this menu",
@@ -439,7 +439,7 @@ static void osnoise_hist_usage(char *usage)
" -D/--debug: print debug info",
" -t/--trace[=file]: save the stopped trace to [file|osnoise_trace.txt]",
" -b/--bucket-size N: set the histogram bucket size (default 1)",
- " -e/--entries N: set the number of entries of the histogram (default 256)",
+ " -E/--entries N: set the number of entries of the histogram (default 256)",
" --no-header: do not print header",
" --no-summary: do not print summary",
" --no-index: do not print index",
@@ -486,7 +486,7 @@ static struct osnoise_hist_params
while (1) {
static struct option long_options[] = {
{"bucket-size", required_argument, 0, 'b'},
- {"entries", required_argument, 0, 'e'},
+ {"entries", required_argument, 0, 'E'},
{"cpus", required_argument, 0, 'c'},
{"debug", no_argument, 0, 'D'},
{"duration", required_argument, 0, 'd'},
@@ -507,7 +507,7 @@ static struct osnoise_hist_params
/* getopt_long stores the option index here. */
int option_index = 0;
- c = getopt_long(argc, argv, "c:b:d:e:Dhp:P:r:s:S:t::0123",
+ c = getopt_long(argc, argv, "c:b:d:E:Dhp:P:r:s:S:t::0123",
long_options, &option_index);
/* detect the end of the options. */
@@ -534,7 +534,7 @@ static struct osnoise_hist_params
if (!params->duration)
osnoise_hist_usage("Invalid -D duration\n");
break;
- case 'e':
+ case 'E':
params->entries = get_llong_from_str(optarg);
if ((params->entries < 10) || (params->entries > 9999999))
osnoise_hist_usage("Entries must be > 10 and < 9999999\n");
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 436a799f9adf..237e1735afa7 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -429,7 +429,7 @@ static void timerlat_hist_usage(char *usage)
char *msg[] = {
"",
" usage: [rtla] timerlat hist [-h] [-q] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] [-t[=file]] \\",
- " [-c cpu-list] [-P priority] [-e N] [-b N] [--no-irq] [--no-thread] [--no-header] [--no-summary] \\",
+ " [-c cpu-list] [-P priority] [-E N] [-b N] [--no-irq] [--no-thread] [--no-header] [--no-summary] \\",
" [--no-index] [--with-zeros]",
"",
" -h/--help: print this menu",
@@ -443,7 +443,7 @@ static void timerlat_hist_usage(char *usage)
" -T/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt]",
" -n/--nano: display data in nanoseconds",
" -b/--bucket-size N: set the histogram bucket size (default 1)",
- " -e/--entries N: set the number of entries of the histogram (default 256)",
+ " -E/--entries N: set the number of entries of the histogram (default 256)",
" --no-irq: ignore IRQ latencies",
" --no-thread: ignore thread latencies",
" --no-header: do not print header",
@@ -494,7 +494,7 @@ static struct timerlat_hist_params
{"cpus", required_argument, 0, 'c'},
{"bucket-size", required_argument, 0, 'b'},
{"debug", no_argument, 0, 'D'},
- {"entries", required_argument, 0, 'e'},
+ {"entries", required_argument, 0, 'E'},
{"duration", required_argument, 0, 'd'},
{"help", no_argument, 0, 'h'},
{"irq", required_argument, 0, 'i'},
@@ -516,7 +516,7 @@ static struct timerlat_hist_params
/* getopt_long stores the option index here. */
int option_index = 0;
- c = getopt_long(argc, argv, "c:b:d:e:Dhi:np:P:s:t::T:012345",
+ c = getopt_long(argc, argv, "c:b:d:E:Dhi:np:P:s:t::T:012345",
long_options, &option_index);
/* detect the end of the options. */
@@ -543,7 +543,7 @@ static struct timerlat_hist_params
if (!params->duration)
timerlat_hist_usage("Invalid -D duration\n");
break;
- case 'e':
+ case 'E':
params->entries = get_llong_from_str(optarg);
if ((params->entries < 10) || (params->entries > 9999999))
timerlat_hist_usage("Entries must be > 10 and < 9999999\n");
--
cgit v1.2.3
From 316f710172461c501f9b73f3b2fc7ce8aa5b84a5 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Fri, 18 Feb 2022 18:57:08 +0100
Subject: rtla/osnoise: Free params at the exit
The variable that stores the parsed command line arguments are not
being free()d at the rtla osnoise top exit path.
Free params variable before exiting.
Link: https://lkml.kernel.org/r/0be31d8259c7c53b98a39769d60cfeecd8421785.1645206561.git.bristot@kernel.org
Fixes: 1eceb2fc2ca5 ("rtla/osnoise: Add osnoise top mode")
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
tools/tracing/rtla/src/osnoise_top.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'tools')
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index c67dc28ef716..7af769b9c0de 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -573,6 +573,7 @@ out_top:
osnoise_free_top(tool->data);
osnoise_destroy_tool(record);
osnoise_destroy_tool(tool);
+ free(params);
out_exit:
exit(return_value);
}
--
cgit v1.2.3
From 90f59ee41abf587ad4675a70434136c8707fdf4b Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Fri, 18 Feb 2022 18:57:09 +0100
Subject: rtla/osnoise: Fix error message when failing to enable trace instance
When a trace instance creation fails, tools are printing:
Could not enable -> osnoiser <- tracer for tracing
Print the actual (and correct) name of the tracer it fails to enable.
Link: https://lkml.kernel.org/r/53ef0582605af91eca14b19dba9fc9febb95d4f9.1645206561.git.bristot@kernel.org
Fixes: b1696371d865 ("rtla: Helper functions for rtla")
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
tools/tracing/rtla/src/osnoise.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/tracing/rtla/src/osnoise.c b/tools/tracing/rtla/src/osnoise.c
index 5648f9252e58..e60f1862bad0 100644
--- a/tools/tracing/rtla/src/osnoise.c
+++ b/tools/tracing/rtla/src/osnoise.c
@@ -810,7 +810,7 @@ struct osnoise_tool *osnoise_init_trace_tool(char *tracer)
retval = enable_tracer_by_name(trace->trace.inst, tracer);
if (retval) {
- err_msg("Could not enable osnoiser tracer for tracing\n");
+ err_msg("Could not enable %s tracer for tracing\n", tracer);
goto out_err;
}
--
cgit v1.2.3
From f39c58008dee7ab5fc94c3f1995a21e886801df0 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Date: Fri, 25 Feb 2022 19:11:08 -0800
Subject: selftest/vm: fix map_fixed_noreplace test failure
On the latest RHEL the test fails due to executable mapped at 256MB
address
# ./map_fixed_noreplace
mmap() @ 0x10000000-0x10050000 p=0xffffffffffffffff result=File exists
10000000-10010000 r-xp 00000000 fd:04 34905657 /root/rpmbuild/BUILD/kernel-5.14.0-56.el9/linux-5.14.0-56.el9.ppc64le/tools/testing/selftests/vm/map_fixed_noreplace
10010000-10020000 r--p 00000000 fd:04 34905657 /root/rpmbuild/BUILD/kernel-5.14.0-56.el9/linux-5.14.0-56.el9.ppc64le/tools/testing/selftests/vm/map_fixed_noreplace
10020000-10030000 rw-p 00010000 fd:04 34905657 /root/rpmbuild/BUILD/kernel-5.14.0-56.el9/linux-5.14.0-56.el9.ppc64le/tools/testing/selftests/vm/map_fixed_noreplace
10029b90000-10029bc0000 rw-p 00000000 00:00 0 [heap]
7fffbb510000-7fffbb750000 r-xp 00000000 fd:04 24534 /usr/lib64/libc.so.6
7fffbb750000-7fffbb760000 r--p 00230000 fd:04 24534 /usr/lib64/libc.so.6
7fffbb760000-7fffbb770000 rw-p 00240000 fd:04 24534 /usr/lib64/libc.so.6
7fffbb780000-7fffbb7a0000 r--p 00000000 00:00 0 [vvar]
7fffbb7a0000-7fffbb7b0000 r-xp 00000000 00:00 0 [vdso]
7fffbb7b0000-7fffbb800000 r-xp 00000000 fd:04 24514 /usr/lib64/ld64.so.2
7fffbb800000-7fffbb810000 r--p 00040000 fd:04 24514 /usr/lib64/ld64.so.2
7fffbb810000-7fffbb820000 rw-p 00050000 fd:04 24514 /usr/lib64/ld64.so.2
7fffd93f0000-7fffd9420000 rw-p 00000000 00:00 0 [stack]
Error: couldn't map the space we need for the test
Fix this by finding a free address using mmap instead of hardcoding
BASE_ADDRESS.
Link: https://lkml.kernel.org/r/20220217083417.373823-1-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Jann Horn <jannh@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
tools/testing/selftests/vm/map_fixed_noreplace.c | 49 ++++++++++++++++++------
1 file changed, 37 insertions(+), 12 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/vm/map_fixed_noreplace.c b/tools/testing/selftests/vm/map_fixed_noreplace.c
index d91bde511268..eed44322d1a6 100644
--- a/tools/testing/selftests/vm/map_fixed_noreplace.c
+++ b/tools/testing/selftests/vm/map_fixed_noreplace.c
@@ -17,9 +17,6 @@
#define MAP_FIXED_NOREPLACE 0x100000
#endif
-#define BASE_ADDRESS (256ul * 1024 * 1024)
-
-
static void dump_maps(void)
{
char cmd[32];
@@ -28,18 +25,46 @@ static void dump_maps(void)
system(cmd);
}
+static unsigned long find_base_addr(unsigned long size)
+{
+ void *addr;
+ unsigned long flags;
+
+ flags = MAP_PRIVATE | MAP_ANONYMOUS;
+ addr = mmap(NULL, size, PROT_NONE, flags, -1, 0);
+ if (addr == MAP_FAILED) {
+ printf("Error: couldn't map the space we need for the test\n");
+ return 0;
+ }
+
+ if (munmap(addr, size) != 0) {
+ printf("Error: couldn't map the space we need for the test\n");
+ return 0;
+ }
+ return (unsigned long)addr;
+}
+
int main(void)
{
+ unsigned long base_addr;
unsigned long flags, addr, size, page_size;
char *p;
page_size = sysconf(_SC_PAGE_SIZE);
+ //let's find a base addr that is free before we start the tests
+ size = 5 * page_size;
+ base_addr = find_base_addr(size);
+ if (!base_addr) {
+ printf("Error: couldn't map the space we need for the test\n");
+ return 1;
+ }
+
flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE;
// Check we can map all the areas we need below
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 5 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
@@ -60,7 +85,7 @@ int main(void)
printf("unmap() successful\n");
errno = 0;
- addr = BASE_ADDRESS + page_size;
+ addr = base_addr + page_size;
size = 3 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -80,7 +105,7 @@ int main(void)
* +4 | free | new
*/
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 5 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -101,7 +126,7 @@ int main(void)
* +4 | free |
*/
errno = 0;
- addr = BASE_ADDRESS + (2 * page_size);
+ addr = base_addr + (2 * page_size);
size = page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -121,7 +146,7 @@ int main(void)
* +4 | free | new
*/
errno = 0;
- addr = BASE_ADDRESS + (3 * page_size);
+ addr = base_addr + (3 * page_size);
size = 2 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -141,7 +166,7 @@ int main(void)
* +4 | free |
*/
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 2 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -161,7 +186,7 @@ int main(void)
* +4 | free |
*/
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -181,7 +206,7 @@ int main(void)
* +4 | free | new
*/
errno = 0;
- addr = BASE_ADDRESS + (4 * page_size);
+ addr = base_addr + (4 * page_size);
size = page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -192,7 +217,7 @@ int main(void)
return 1;
}
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 5 * page_size;
if (munmap((void *)addr, size) != 0) {
dump_maps();
--
cgit v1.2.3
From fda153c89af344d21df281009a9d046cf587ea0f Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz@oracle.com>
Date: Fri, 25 Feb 2022 19:11:26 -0800
Subject: selftests/memfd: clean up mapping in mfd_fail_write
Running the memfd script ./run_hugetlbfs_test.sh will often end in error
as follows:
memfd-hugetlb: CREATE
memfd-hugetlb: BASIC
memfd-hugetlb: SEAL-WRITE
memfd-hugetlb: SEAL-FUTURE-WRITE
memfd-hugetlb: SEAL-SHRINK
fallocate(ALLOC) failed: No space left on device
./run_hugetlbfs_test.sh: line 60: 166855 Aborted (core dumped) ./memfd_test hugetlbfs
opening: ./mnt/memfd
fuse: DONE
If no hugetlb pages have been preallocated, run_hugetlbfs_test.sh will
allocate 'just enough' pages to run the test. In the SEAL-FUTURE-WRITE
test the mfd_fail_write routine maps the file, but does not unmap. As a
result, two hugetlb pages remain reserved for the mapping. When the
fallocate call in the SEAL-SHRINK test attempts allocate all hugetlb
pages, it is short by the two reserved pages.
Fix by making sure to unmap in mfd_fail_write.
Link: https://lkml.kernel.org/r/20220219004340.56478-1-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
tools/testing/selftests/memfd/memfd_test.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'tools')
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 192a2899bae8..94df2692e6e4 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -455,6 +455,7 @@ static void mfd_fail_write(int fd)
printf("mmap()+mprotect() didn't fail as expected\n");
abort();
}
+ munmap(p, mfd_def_size);
}
/* verify PUNCH_HOLE fails */
--
cgit v1.2.3
From 2e78855d311c401083df9776aa450d32d716e83e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 25 Feb 2022 12:01:23 +0100
Subject: selftests: netfilter: add nfqueue TCP_NEW_SYN_RECV socket race test
causes:
BUG: KASAN: slab-out-of-bounds in sk_free+0x25/0x80
Write of size 4 at addr ffff888106df0284 by task nf-queue/1459
sk_free+0x25/0x80
nf_queue_entry_release_refs+0x143/0x1a0
nf_reinject+0x233/0x770
... without 'netfilter: nf_queue: don't assume sk is full socket'.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
tools/testing/selftests/netfilter/.gitignore | 1 +
tools/testing/selftests/netfilter/Makefile | 2 +-
tools/testing/selftests/netfilter/connect_close.c | 136 ++++++++++++++++++++++
tools/testing/selftests/netfilter/nft_queue.sh | 19 +++
4 files changed, 157 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/netfilter/connect_close.c
(limited to 'tools')
diff --git a/tools/testing/selftests/netfilter/.gitignore b/tools/testing/selftests/netfilter/.gitignore
index 8448f74adfec..4cb887b57413 100644
--- a/tools/testing/selftests/netfilter/.gitignore
+++ b/tools/testing/selftests/netfilter/.gitignore
@@ -1,2 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
nf-queue
+connect_close
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index e4f845dd942b..7e81c9a7fff9 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -9,6 +9,6 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
conntrack_vrf.sh nft_synproxy.sh
LDLIBS = -lmnl
-TEST_GEN_FILES = nf-queue
+TEST_GEN_FILES = nf-queue connect_close
include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/connect_close.c b/tools/testing/selftests/netfilter/connect_close.c
new file mode 100644
index 000000000000..1c3b0add54c4
--- /dev/null
+++ b/tools/testing/selftests/netfilter/connect_close.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+#include <signal.h>
+
+#include <arpa/inet.h>
+#include <sys/socket.h>
+
+#define PORT 12345
+#define RUNTIME 10
+
+static struct {
+ unsigned int timeout;
+ unsigned int port;
+} opts = {
+ .timeout = RUNTIME,
+ .port = PORT,
+};
+
+static void handler(int sig)
+{
+ _exit(sig == SIGALRM ? 0 : 1);
+}
+
+static void set_timeout(void)
+{
+ struct sigaction action = {
+ .sa_handler = handler,
+ };
+
+ sigaction(SIGALRM, &action, NULL);
+
+ alarm(opts.timeout);
+}
+
+static void do_connect(const struct sockaddr_in *dst)
+{
+ int s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+
+ if (s >= 0)
+ fcntl(s, F_SETFL, O_NONBLOCK);
+
+ connect(s, (struct sockaddr *)dst, sizeof(*dst));
+ close(s);
+}
+
+static void do_accept(const struct sockaddr_in *src)
+{
+ int c, one = 1, s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+
+ if (s < 0)
+ return;
+
+ setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one));
+ setsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
+
+ bind(s, (struct sockaddr *)src, sizeof(*src));
+
+ listen(s, 16);
+
+ c = accept(s, NULL, NULL);
+ if (c >= 0)
+ close(c);
+
+ close(s);
+}
+
+static int accept_loop(void)
+{
+ struct sockaddr_in src = {
+ .sin_family = AF_INET,
+ .sin_port = htons(opts.port),
+ };
+
+ inet_pton(AF_INET, "127.0.0.1", &src.sin_addr);
+
+ set_timeout();
+
+ for (;;)
+ do_accept(&src);
+
+ return 1;
+}
+
+static int connect_loop(void)
+{
+ struct sockaddr_in dst = {
+ .sin_family = AF_INET,
+ .sin_port = htons(opts.port),
+ };
+
+ inet_pton(AF_INET, "127.0.0.1", &dst.sin_addr);
+
+ set_timeout();
+
+ for (;;)
+ do_connect(&dst);
+
+ return 1;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "t:p:")) != -1) {
+ switch (c) {
+ case 't':
+ opts.timeout = atoi(optarg);
+ break;
+ case 'p':
+ opts.port = atoi(optarg);
+ break;
+ }
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ pid_t p;
+
+ parse_opts(argc, argv);
+
+ p = fork();
+ if (p < 0)
+ return 111;
+
+ if (p > 0)
+ return accept_loop();
+
+ return connect_loop();
+}
diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh
index 7d27f1f3bc01..e12729753351 100755
--- a/tools/testing/selftests/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/netfilter/nft_queue.sh
@@ -113,6 +113,7 @@ table inet $name {
chain output {
type filter hook output priority $prio; policy accept;
tcp dport 12345 queue num 3
+ tcp sport 23456 queue num 3
jump nfq
}
chain post {
@@ -296,6 +297,23 @@ test_tcp_localhost()
wait 2>/dev/null
}
+test_tcp_localhost_connectclose()
+{
+ tmpfile=$(mktemp) || exit 1
+
+ ip netns exec ${nsrouter} ./connect_close -p 23456 -t $timeout &
+
+ ip netns exec ${nsrouter} ./nf-queue -q 3 -t $timeout &
+ local nfqpid=$!
+
+ sleep 1
+ rm -f "$tmpfile"
+
+ wait $rpid
+ [ $? -eq 0 ] && echo "PASS: tcp via loopback with connect/close"
+ wait 2>/dev/null
+}
+
test_tcp_localhost_requeue()
{
ip netns exec ${nsrouter} nft -f /dev/stdin <<EOF
@@ -424,6 +442,7 @@ test_queue 20
test_tcp_forward
test_tcp_localhost
+test_tcp_localhost_connectclose
test_tcp_localhost_requeue
test_icmp_vrf
--
cgit v1.2.3
From dc9752075341e7beb653e37c6f4a3723074dc8bc Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Wed, 2 Mar 2022 18:14:46 +0200
Subject: selftests: mlxsw: tc_police_scale: Make test more robust
The test adds tc filters and checks how many of them were offloaded by
grepping for 'in_hw'.
iproute2 commit f4cd4f127047 ("tc: add skip_hw and skip_sw to control
action offload") added offload indication to tc actions, producing the
following output:
$ tc filter show dev swp2 ingress
...
filter protocol ipv6 pref 1000 flower chain 0 handle 0x7c0
eth_type ipv6
dst_ip 2001:db8:1::7bf
skip_sw
in_hw in_hw_count 1
action order 1: police 0x7c0 rate 10Mbit burst 100Kb mtu 2Kb action drop overhead 0b
ref 1 bind 1
not_in_hw
used_hw_stats immediate
The current grep expression matches on both 'in_hw' and 'not_in_hw',
resulting in incorrect results.
Fix that by using JSON output instead.
Fixes: 5061e773264b ("selftests: mlxsw: Add scale test for tc-police")
Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh
index 3e3e06ea5703..86e787895f78 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh
@@ -60,7 +60,8 @@ __tc_police_test()
tc_police_rules_create $count $should_fail
- offload_count=$(tc filter show dev $swp1 ingress | grep in_hw | wc -l)
+ offload_count=$(tc -j filter show dev $swp1 ingress |
+ jq "[.[] | select(.options.in_hw == true)] | length")
((offload_count == count))
check_err_fail $should_fail $? "tc police offload count"
}
--
cgit v1.2.3
From 196f9bc050cbc5085b4cbb61cce2efe380bc66d0 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Wed, 2 Mar 2022 18:14:47 +0200
Subject: selftests: mlxsw: resource_scale: Fix return value
The test runs several test cases and is supposed to return an error in
case at least one of them failed.
Currently, the check of the return value of each test case is in the
wrong place, which can result in the wrong return value. For example:
# TESTS='tc_police' ./resource_scale.sh
TEST: 'tc_police' [default] 968 [FAIL]
tc police offload count failed
Error: mlxsw_spectrum: Failed to allocate policer index.
We have an error talking to the kernel
Command failed /tmp/tmp.i7Oc5HwmXY:969
TEST: 'tc_police' [default] overflow 969 [ OK ]
...
TEST: 'tc_police' [ipv4_max] overflow 969 [ OK ]
$ echo $?
0
Fix this by moving the check to be done after each test case.
Fixes: 059b18e21c63 ("selftests: mlxsw: Return correct error code in resource scale test")
Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index bcb110e830ce..dea33dc93790 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -50,8 +50,8 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
else
log_test "'$current_test' [$profile] overflow $target"
fi
+ RET_FIN=$(( RET_FIN || RET ))
done
- RET_FIN=$(( RET_FIN || RET ))
done
done
current_test=""
--
cgit v1.2.3
From ff712a627f7296a42ea5d7356704525e1e909e05 Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz@oracle.com>
Date: Fri, 4 Mar 2022 20:28:48 -0800
Subject: selftests/vm: cleanup hugetlb file after mremap test
The hugepage-mremap test will create a file in a hugetlb filesystem. In
a default 'run_vmtests' run, the file will contain all the hugetlb
pages. After the test, the file remains and there are no free hugetlb
pages for subsequent tests. This causes those hugetlb tests to fail.
Change hugepage-mremap to take the name of the hugetlb file as an
argument. Unlink the file within the test, and just to be sure remove
the file in the run_vmtests script.
Link: https://lkml.kernel.org/r/20220201033459.156944-1-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Shuah Khan <skhan@linuxfoundation.org>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
tools/testing/selftests/vm/hugepage-mremap.c | 26 +++++++++++++++++++-------
tools/testing/selftests/vm/run_vmtests.sh | 3 ++-
2 files changed, 21 insertions(+), 8 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c
index 2a7c33631a29..1d689084a54b 100644
--- a/tools/testing/selftests/vm/hugepage-mremap.c
+++ b/tools/testing/selftests/vm/hugepage-mremap.c
@@ -3,9 +3,10 @@
* hugepage-mremap:
*
* Example of remapping huge page memory in a user application using the
- * mremap system call. Code assumes a hugetlbfs filesystem is mounted
- * at './huge'. The amount of memory used by this test is decided by a command
- * line argument in MBs. If missing, the default amount is 10MB.
+ * mremap system call. The path to a file in a hugetlbfs filesystem must
+ * be passed as the last argument to this test. The amount of memory used
+ * by this test in MBs can optionally be passed as an argument. If no memory
+ * amount is passed, the default amount is 10MB.
*
* To make sure the test triggers pmd sharing and goes through the 'unshare'
* path in the mremap code use 1GB (1024) or more.
@@ -25,7 +26,6 @@
#define DEFAULT_LENGTH_MB 10UL
#define MB_TO_BYTES(x) (x * 1024 * 1024)
-#define FILE_NAME "huge/hugepagefile"
#define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC)
#define FLAGS (MAP_SHARED | MAP_ANONYMOUS)
@@ -107,17 +107,26 @@ static void register_region_with_uffd(char *addr, size_t len)
int main(int argc, char *argv[])
{
+ size_t length;
+
+ if (argc != 2 && argc != 3) {
+ printf("Usage: %s [length_in_MB] <hugetlb_file>\n", argv[0]);
+ exit(1);
+ }
+
/* Read memory length as the first arg if valid, otherwise fallback to
- * the default length. Any additional args are ignored.
+ * the default length.
*/
- size_t length = argc > 1 ? (size_t)atoi(argv[1]) : 0UL;
+ if (argc == 3)
+ length = argc > 2 ? (size_t)atoi(argv[1]) : 0UL;
length = length > 0 ? length : DEFAULT_LENGTH_MB;
length = MB_TO_BYTES(length);
int ret = 0;
- int fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
+ /* last arg is the hugetlb file name */
+ int fd = open(argv[argc-1], O_CREAT | O_RDWR, 0755);
if (fd < 0) {
perror("Open failed");
@@ -169,5 +178,8 @@ int main(int argc, char *argv[])
munmap(addr, length);
+ close(fd);
+ unlink(argv[argc-1]);
+
return ret;
}
diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh
index 75d401741394..71d2dc198fc1 100755
--- a/tools/testing/selftests/vm/run_vmtests.sh
+++ b/tools/testing/selftests/vm/run_vmtests.sh
@@ -111,13 +111,14 @@ fi
echo "-----------------------"
echo "running hugepage-mremap"
echo "-----------------------"
-./hugepage-mremap 256
+./hugepage-mremap $mnt/huge_mremap
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
else
echo "[PASS]"
fi
+rm -f $mnt/huge_mremap
echo "NOTE: The above hugetlb tests provide minimal coverage. Use"
echo " https://github.com/libhugetlbfs/libhugetlbfs.git for"
--
cgit v1.2.3
From b773827e361952b3f53ac6fa4c4e39ccd632102e Mon Sep 17 00:00:00 2001
From: Chengming Zhou <zhouchengming@bytedance.com>
Date: Fri, 4 Mar 2022 20:29:04 -0800
Subject: kselftest/vm: fix tests build with old libc
The error message when I build vm tests on debian10 (GLIBC 2.28):
userfaultfd.c: In function `userfaultfd_pagemap_test':
userfaultfd.c:1393:37: error: `MADV_PAGEOUT' undeclared (first use
in this function); did you mean `MADV_RANDOM'?
if (madvise(area_dst, test_pgsize, MADV_PAGEOUT))
^~~~~~~~~~~~
MADV_RANDOM
This patch includes these newer definitions from UAPI linux/mman.h, is
useful to fix tests build on systems without these definitions in glibc
sys/mman.h.
Link: https://lkml.kernel.org/r/20220227055330.43087-2-zhouchengming@bytedance.com
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
tools/testing/selftests/vm/userfaultfd.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'tools')
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 2f49c9af1b58..3fc1d2ee2948 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -46,6 +46,7 @@
#include <signal.h>
#include <poll.h>
#include <string.h>
+#include <linux/mman.h>
#include <sys/mman.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
--
cgit v1.2.3
From 32f1b53fe8f03d962423ba81f8e92af5839814da Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Tue, 18 Jan 2022 16:06:31 +0100
Subject: tools/virtio: fix virtio_test execution
virtio_test hangs on __vring_new_virtqueue() because `vqs_list_lock`
is not initialized.
Let's initialize it in vdev_info_init().
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://lore.kernel.org/r/20220118150631.167015-1-sgarzare@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
tools/virtio/virtio_test.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'tools')
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index cb3f29c09aff..23f142af544a 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -130,6 +130,7 @@ static void vdev_info_init(struct vdev_info* dev, unsigned long long features)
memset(dev, 0, sizeof *dev);
dev->vdev.features = features;
INIT_LIST_HEAD(&dev->vdev.vqs);
+ spin_lock_init(&dev->vdev.vqs_list_lock);
dev->buf_size = 1024;
dev->buf = malloc(dev->buf_size);
assert(dev->buf);
--
cgit v1.2.3
From 3dd7d135e75cb37c8501ba02977332a2a487dd39 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Fri, 4 Mar 2022 12:10:38 -0500
Subject: tools/virtio: handle fallout from folio work
just add a stub
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
tools/virtio/linux/mm_types.h | 3 +++
1 file changed, 3 insertions(+)
create mode 100644 tools/virtio/linux/mm_types.h
(limited to 'tools')
diff --git a/tools/virtio/linux/mm_types.h b/tools/virtio/linux/mm_types.h
new file mode 100644
index 000000000000..356ba4d496f6
--- /dev/null
+++ b/tools/virtio/linux/mm_types.h
@@ -0,0 +1,3 @@
+struct folio {
+ struct page page;
+};
--
cgit v1.2.3
From 18dfc667550fe9c032a6dcc3402b50e691e18029 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Tue, 8 Mar 2022 23:15:00 +0100
Subject: selftests: pmtu.sh: Kill tcpdump processes launched by subshell.
The cleanup() function takes care of killing processes launched by the
test functions. It relies on variables like ${tcpdump_pids} to get the
relevant PIDs. But tests are run in their own subshell, so updated
*_pids values are invisible to other shells. Therefore cleanup() never
sees any process to kill:
$ ./tools/testing/selftests/net/pmtu.sh -t pmtu_ipv4_exception
TEST: ipv4: PMTU exceptions [ OK ]
TEST: ipv4: PMTU exceptions - nexthop objects [ OK ]
$ pgrep -af tcpdump
6084 tcpdump -s 0 -i veth_A-R1 -w pmtu_ipv4_exception_veth_A-R1.pcap
6085 tcpdump -s 0 -i veth_R1-A -w pmtu_ipv4_exception_veth_R1-A.pcap
6086 tcpdump -s 0 -i veth_R1-B -w pmtu_ipv4_exception_veth_R1-B.pcap
6087 tcpdump -s 0 -i veth_B-R1 -w pmtu_ipv4_exception_veth_B-R1.pcap
6088 tcpdump -s 0 -i veth_A-R2 -w pmtu_ipv4_exception_veth_A-R2.pcap
6089 tcpdump -s 0 -i veth_R2-A -w pmtu_ipv4_exception_veth_R2-A.pcap
6090 tcpdump -s 0 -i veth_R2-B -w pmtu_ipv4_exception_veth_R2-B.pcap
6091 tcpdump -s 0 -i veth_B-R2 -w pmtu_ipv4_exception_veth_B-R2.pcap
6228 tcpdump -s 0 -i veth_A-R1 -w pmtu_ipv4_exception_veth_A-R1.pcap
6229 tcpdump -s 0 -i veth_R1-A -w pmtu_ipv4_exception_veth_R1-A.pcap
6230 tcpdump -s 0 -i veth_R1-B -w pmtu_ipv4_exception_veth_R1-B.pcap
6231 tcpdump -s 0 -i veth_B-R1 -w pmtu_ipv4_exception_veth_B-R1.pcap
6232 tcpdump -s 0 -i veth_A-R2 -w pmtu_ipv4_exception_veth_A-R2.pcap
6233 tcpdump -s 0 -i veth_R2-A -w pmtu_ipv4_exception_veth_R2-A.pcap
6234 tcpdump -s 0 -i veth_R2-B -w pmtu_ipv4_exception_veth_R2-B.pcap
6235 tcpdump -s 0 -i veth_B-R2 -w pmtu_ipv4_exception_veth_B-R2.pcap
Fix this by running cleanup() in the context of the test subshell.
Now that each test cleans the environment after completion, there's no
need for calling cleanup() again when the next test starts. So let's
drop it from the setup() function. This is okay because cleanup() is
also called when pmtu.sh starts, so even the first test starts in a
clean environment.
Also, use tcpdump's immediate mode. Otherwise it might not have time to
process buffered packets, resulting in missing packets or even empty
pcap files for short tests.
Note: PAUSE_ON_FAIL is still evaluated before cleanup(), so one can
still inspect the test environment upon failure when using -p.
Fixes: a92a0a7b8e7c ("selftests: pmtu: Simplify cleanup and namespace names")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/pmtu.sh | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 543ad7513a8e..2e8972573d91 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -865,7 +865,6 @@ setup_ovs_bridge() {
setup() {
[ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip
- cleanup
for arg do
eval setup_${arg} || { echo " ${arg} not supported"; return 1; }
done
@@ -876,7 +875,7 @@ trace() {
for arg do
[ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue
- ${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null &
+ ${ns_cmd} tcpdump --immediate-mode -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null &
tcpdump_pids="${tcpdump_pids} $!"
ns_cmd=
done
@@ -1836,6 +1835,10 @@ run_test() {
unset IFS
+ # Since cleanup() relies on variables modified by this subshell, it
+ # has to run in this context.
+ trap cleanup EXIT
+
if [ "$VERBOSE" = "1" ]; then
printf "\n##########################################################################\n\n"
fi
--
cgit v1.2.3
From 94a4a4fe4c696413932eed8bdec46574de9576b8 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Tue, 8 Mar 2022 23:15:03 +0100
Subject: selftests: pmtu.sh: Kill nettest processes launched in subshell.
When using "run_cmd <command> &", then "$!" refers to the PID of the
subshell used to run <command>, not the command itself. Therefore
nettest_pids actually doesn't contain the list of the nettest commands
running in the background. So cleanup() can't kill them and the nettest
processes run until completion (fortunately they have a 5s timeout).
Fix this by defining a new command for running processes in the
background, for which "$!" really refers to the PID of the command run.
Also, double quote variables on the modified lines, to avoid shellcheck
warnings.
Fixes: ece1278a9b81 ("selftests: net: add ESP-in-UDP PMTU test")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/pmtu.sh | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
(limited to 'tools')
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 2e8972573d91..694732e4b344 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -374,6 +374,16 @@ run_cmd() {
return $rc
}
+run_cmd_bg() {
+ cmd="$*"
+
+ if [ "$VERBOSE" = "1" ]; then
+ printf " COMMAND: %s &\n" "${cmd}"
+ fi
+
+ $cmd 2>&1 &
+}
+
# Find the auto-generated name for this namespace
nsname() {
eval echo \$NS_$1
@@ -670,10 +680,10 @@ setup_nettest_xfrm() {
[ ${1} -eq 6 ] && proto="-6" || proto=""
port=${2}
- run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ run_cmd_bg "${ns_a}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5
nettest_pids="${nettest_pids} $!"
- run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ run_cmd_bg "${ns_b}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5
nettest_pids="${nettest_pids} $!"
}
--
cgit v1.2.3
From 3ec94eeaff9ad58a76be2232068b4a2546b2f6bb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 21 Dec 2020 12:53:44 -0300
Subject: tools kvm headers arm64: Update KVM headers from the kernel sources
To pick the changes from:
a5905d6af492ee6a ("KVM: arm64: Allow SMCCC_ARCH_WORKAROUND_3 to be discovered and migrated")
That don't causes any changes in tooling (when built on x86), only
addresses this perf build warning:
Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h'
diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h
Cc: James Morse <james.morse@arm.com>
Link: https://lore.kernel.org/lkml/YiyhAK6sVPc83FaI@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/arm64/include/uapi/asm/kvm.h | 5 +++++
1 file changed, 5 insertions(+)
(limited to 'tools')
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index b3edde68bc3e..323e251ed37b 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -281,6 +281,11 @@ struct kvm_arm_copy_mte_tags {
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 KVM_REG_ARM_FW_REG(3)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED 2
+
/* SVE registers */
#define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT)
--
cgit v1.2.3
From ec9d50ace39925f7fd0302bf0fad640e2c9826ea Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 1 Jul 2021 13:39:15 -0300
Subject: tools headers cpufeatures: Sync with the kernel sources
To pick the changes from:
d45476d983240937 ("x86/speculation: Rename RETPOLINE_AMD to RETPOLINE_LFENCE")
Its just a comment fixup.
This only causes these perf files to be rebuilt:
CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o
CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o
And addresses this perf build warning:
Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h'
diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h
Cc: Borislav Petkov <bp@suse.de>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/YiyiHatGaJQM7l/Y@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/x86/include/asm/cpufeatures.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index ab4e53715d8a..65d147974f8d 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -204,7 +204,7 @@
/* FREE! ( 7*32+10) */
#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCEs for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */
#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
--
cgit v1.2.3
From a7a72631f62445e3671b7cab5ad01f856c1aa90d Mon Sep 17 00:00:00 2001
From: Weiguo Li <liwg06@foxmail.com>
Date: Fri, 11 Mar 2022 21:06:57 +0800
Subject: perf parse-events: Fix NULL check against wrong variable
We did a null check after "tmp->symbol = strdup(...)", but we checked
"list->symbol" other than "tmp->symbol".
Reviewed-by: John Garry <john.garry@huawei.com>
Signed-off-by: Weiguo Li <liwg06@foxmail.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/tencent_DF39269807EC9425E24787E6DB632441A405@qq.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/parse-events.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 9739b05b999e..dfb50a5f83d0 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2193,7 +2193,7 @@ int perf_pmu__test_parse_init(void)
for (i = 0; i < ARRAY_SIZE(symbols); i++, tmp++) {
tmp->type = symbols[i].type;
tmp->symbol = strdup(symbols[i].symbol);
- if (!list->symbol)
+ if (!tmp->symbol)
goto err_free;
}
--
cgit v1.2.3
From 073a15c3512f6b8d36c0c05992cf31e845f4dfe0 Mon Sep 17 00:00:00 2001
From: Weiguo Li <liwg06@foxmail.com>
Date: Fri, 11 Mar 2022 21:07:16 +0800
Subject: perf bench: Fix NULL check against wrong variable
We did a NULL check after "epollfdp = calloc(...)", but we checked
"epollfd" instead of "epollfdp".
Signed-off-by: Weiguo Li <liwg06@foxmail.com>
Acked-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/tencent_B5D64530EB9C7DBB8D2C88A0C790F1489D0A@qq.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/bench/epoll-ctl.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index 740ae764537e..134612bde0cb 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -106,7 +106,7 @@ static void nest_epollfd(void)
printinfo("Nesting level(s): %d\n", nested);
epollfdp = calloc(nested, sizeof(int));
- if (!epollfd)
+ if (!epollfdp)
err(EXIT_FAILURE, "calloc");
for (i = 0; i < nested; i++) {
--
cgit v1.2.3
From 91c9923a473a694eb1c5c01ab778a77114969707 Mon Sep 17 00:00:00 2001
From: Zhengjun Xing <zhengjun.xing@linux.intel.com>
Date: Mon, 7 Mar 2022 23:16:27 +0800
Subject: perf parse: Fix event parser error for hybrid systems
This bug happened on hybrid systems when both cpu_core and cpu_atom
have the same event name such as "UOPS_RETIRED.MS" while their event
terms are different, then during perf stat, the event for cpu_atom
will parse fail and then no output for cpu_atom.
UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/
UOPS_RETIRED.MS -> cpu_atom/period=0x1e8483,umask=0x1,event=0xc2/
It is because event terms in the "head" of parse_events_multi_pmu_add
will be changed to event terms for cpu_core after parsing UOPS_RETIRED.MS
for cpu_core, then when parsing the same event for cpu_atom, it still
uses the event terms for cpu_core, but event terms for cpu_atom are
different with cpu_core, the event parses for cpu_atom will fail. This
patch fixes it, the event terms should be parsed from the original
event.
This patch can work for the hybrid systems that have the same event
in more than 2 PMUs. It also can work in non-hybrid systems.
Before:
# perf stat -v -e UOPS_RETIRED.MS -a sleep 1
Using CPUID GenuineIntel-6-97-1
UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/
Control descriptor is not initialized
UOPS_RETIRED.MS: 2737845 16068518485 16068518485
Performance counter stats for 'system wide':
2,737,845 cpu_core/UOPS_RETIRED.MS/
1.002553850 seconds time elapsed
After:
# perf stat -v -e UOPS_RETIRED.MS -a sleep 1
Using CPUID GenuineIntel-6-97-1
UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/
UOPS_RETIRED.MS -> cpu_atom/period=0x1e8483,umask=0x1,event=0xc2/
Control descriptor is not initialized
UOPS_RETIRED.MS: 1977555 16076950711 16076950711
UOPS_RETIRED.MS: 568684 8038694234 8038694234
Performance counter stats for 'system wide':
1,977,555 cpu_core/UOPS_RETIRED.MS/
568,684 cpu_atom/UOPS_RETIRED.MS/
1.004758259 seconds time elapsed
Fixes: fb0811535e92c6c1 ("perf parse-events: Allow config on kernel PMU events")
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Zhengjun Xing <zhengjun.xing@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220307151627.30049-1-zhengjun.xing@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/parse-events.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
(limited to 'tools')
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index dfb50a5f83d0..24997925ae00 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1648,6 +1648,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
{
struct parse_events_term *term;
struct list_head *list = NULL;
+ struct list_head *orig_head = NULL;
struct perf_pmu *pmu = NULL;
int ok = 0;
char *config;
@@ -1674,7 +1675,6 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
}
list_add_tail(&term->list, head);
-
/* Add it for all PMUs that support the alias */
list = malloc(sizeof(struct list_head));
if (!list)
@@ -1687,13 +1687,15 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
list_for_each_entry(alias, &pmu->aliases, list) {
if (!strcasecmp(alias->name, str)) {
+ parse_events_copy_term_list(head, &orig_head);
if (!parse_events_add_pmu(parse_state, list,
- pmu->name, head,
+ pmu->name, orig_head,
true, true)) {
pr_debug("%s -> %s/%s/\n", str,
pmu->name, alias->str);
ok++;
}
+ parse_events_terms__delete(orig_head);
}
}
}
--
cgit v1.2.3