April 2024 - Linux-kselftest-mirror

[PATCH v22 5/5] ring-buffer/selftest: Add ring-buffer mapping test

by Vincent Donnefort

This test maps a ring-buffer and validate the meta-page after reset and after emitting few events. Cc: Shuah Khan <shuah(a)kernel.org> Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org Acked-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Signed-off-by: Vincent Donnefort <vdonnefort(a)google.com> diff --git a/tools/testing/selftests/ring-buffer/.gitignore b/tools/testing/selftests/ring-buffer/.gitignore new file mode 100644 index 000000000000..3aed1a2a6c67 --- /dev/null +++ b/tools/testing/selftests/ring-buffer/.gitignore @@ -0,0 +1 @@ +map_test diff --git a/tools/testing/selftests/ring-buffer/Makefile b/tools/testing/selftests/ring-buffer/Makefile new file mode 100644 index 000000000000..627c5fa6d1ab --- /dev/null +++ b/tools/testing/selftests/ring-buffer/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -Wl,-no-as-needed -Wall +CFLAGS += $(KHDR_INCLUDES) +CFLAGS += -D_GNU_SOURCE + +TEST_GEN_PROGS = map_test + +include ../lib.mk diff --git a/tools/testing/selftests/ring-buffer/config b/tools/testing/selftests/ring-buffer/config new file mode 100644 index 000000000000..d936f8f00e78 --- /dev/null +++ b/tools/testing/selftests/ring-buffer/config @@ -0,0 +1,2 @@ +CONFIG_FTRACE=y +CONFIG_TRACER_SNAPSHOT=y diff --git a/tools/testing/selftests/ring-buffer/map_test.c b/tools/testing/selftests/ring-buffer/map_test.c new file mode 100644 index 000000000000..b95eedddbb8c --- /dev/null +++ b/tools/testing/selftests/ring-buffer/map_test.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Ring-buffer memory mapping tests + * + * Copyright (c) 2024 Vincent Donnefort <vdonnefort(a)google.com> + */ +#include <fcntl.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <linux/trace_mmap.h> + +#include <sys/mman.h> +#include <sys/ioctl.h> + +#include "../user_events/user_events_selftests.h" /* share tracefs setup */ +#include "../kselftest_harness.h" + +#define TRACEFS_ROOT "/sys/kernel/tracing" + +static int __tracefs_write(const char *path, const char *value) +{ + int fd, ret; + + fd = open(path, O_WRONLY | O_TRUNC); + if (fd < 0) + return fd; + + ret = write(fd, value, strlen(value)); + + close(fd); + + return ret == -1 ? -errno : 0; +} + +static int __tracefs_write_int(const char *path, int value) +{ + char *str; + int ret; + + if (asprintf(&str, "%d", value) < 0) + return -1; + + ret = __tracefs_write(path, str); + + free(str); + + return ret; +} + +#define tracefs_write_int(path, value) \ + ASSERT_EQ(__tracefs_write_int((path), (value)), 0) + +#define tracefs_write(path, value) \ + ASSERT_EQ(__tracefs_write((path), (value)), 0) + +static int tracefs_reset(void) +{ + if (__tracefs_write_int(TRACEFS_ROOT"/tracing_on", 0)) + return -1; + if (__tracefs_write(TRACEFS_ROOT"/trace", "")) + return -1; + if (__tracefs_write(TRACEFS_ROOT"/set_event", "")) + return -1; + if (__tracefs_write(TRACEFS_ROOT"/current_tracer", "nop")) + return -1; + + return 0; +} + +struct tracefs_cpu_map_desc { + struct trace_buffer_meta *meta; + int cpu_fd; +}; + +int tracefs_cpu_map(struct tracefs_cpu_map_desc *desc, int cpu) +{ + int page_size = getpagesize(); + char *cpu_path; + void *map; + + if (asprintf(&cpu_path, + TRACEFS_ROOT"/per_cpu/cpu%d/trace_pipe_raw", + cpu) < 0) + return -ENOMEM; + + desc->cpu_fd = open(cpu_path, O_RDONLY | O_NONBLOCK); + free(cpu_path); + if (desc->cpu_fd < 0) + return -ENODEV; + + map = mmap(NULL, page_size, PROT_READ, MAP_SHARED, desc->cpu_fd, 0); + if (map == MAP_FAILED) + return -errno; + + desc->meta = (struct trace_buffer_meta *)map; + + return 0; +} + +void tracefs_cpu_unmap(struct tracefs_cpu_map_desc *desc) +{ + munmap(desc->meta, desc->meta->meta_page_size); + close(desc->cpu_fd); +} + +FIXTURE(map) { + struct tracefs_cpu_map_desc map_desc; + bool umount; +}; + +FIXTURE_VARIANT(map) { + int subbuf_size; +}; + +FIXTURE_VARIANT_ADD(map, subbuf_size_4k) { + .subbuf_size = 4, +}; + +FIXTURE_VARIANT_ADD(map, subbuf_size_8k) { + .subbuf_size = 8, +}; + +FIXTURE_SETUP(map) +{ + int cpu = sched_getcpu(); + cpu_set_t cpu_mask; + bool fail, umount; + char *message; + + if (!tracefs_enabled(&message, &fail, &umount)) { + if (fail) { + TH_LOG("Tracefs setup failed: %s", message); + ASSERT_FALSE(fail); + } + SKIP(return, "Skipping: %s", message); + } + + self->umount = umount; + + ASSERT_GE(cpu, 0); + + ASSERT_EQ(tracefs_reset(), 0); + + tracefs_write_int(TRACEFS_ROOT"/buffer_subbuf_size_kb", variant->subbuf_size); + + ASSERT_EQ(tracefs_cpu_map(&self->map_desc, cpu), 0); + + /* + * Ensure generated events will be found on this very same ring-buffer. + */ + CPU_ZERO(&cpu_mask); + CPU_SET(cpu, &cpu_mask); + ASSERT_EQ(sched_setaffinity(0, sizeof(cpu_mask), &cpu_mask), 0); +} + +FIXTURE_TEARDOWN(map) +{ + tracefs_reset(); + + if (self->umount) + tracefs_unmount(); + + tracefs_cpu_unmap(&self->map_desc); +} + +TEST_F(map, meta_page_check) +{ + struct tracefs_cpu_map_desc *desc = &self->map_desc; + int cnt = 0; + + ASSERT_EQ(desc->meta->entries, 0); + ASSERT_EQ(desc->meta->overrun, 0); + ASSERT_EQ(desc->meta->read, 0); + + ASSERT_EQ(desc->meta->reader.id, 0); + ASSERT_EQ(desc->meta->reader.read, 0); + + ASSERT_EQ(ioctl(desc->cpu_fd, TRACE_MMAP_IOCTL_GET_READER), 0); + ASSERT_EQ(desc->meta->reader.id, 0); + + tracefs_write_int(TRACEFS_ROOT"/tracing_on", 1); + for (int i = 0; i < 16; i++) + tracefs_write_int(TRACEFS_ROOT"/trace_marker", i); +again: + ASSERT_EQ(ioctl(desc->cpu_fd, TRACE_MMAP_IOCTL_GET_READER), 0); + + ASSERT_EQ(desc->meta->entries, 16); + ASSERT_EQ(desc->meta->overrun, 0); + ASSERT_EQ(desc->meta->read, 16); + + ASSERT_EQ(desc->meta->reader.id, 1); + + if (!(cnt++)) + goto again; +} + +TEST_F(map, data_mmap) +{ + struct tracefs_cpu_map_desc *desc = &self->map_desc; + unsigned long meta_len, data_len; + void *data; + + meta_len = desc->meta->meta_page_size; + data_len = desc->meta->subbuf_size * desc->meta->nr_subbufs; + + /* Map all the available subbufs */ + data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, + desc->cpu_fd, meta_len); + ASSERT_NE(data, MAP_FAILED); + munmap(data, data_len); + + /* Map all the available subbufs - 1 */ + data_len -= desc->meta->subbuf_size; + data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, + desc->cpu_fd, meta_len); + ASSERT_NE(data, MAP_FAILED); + munmap(data, data_len); + + /* Overflow the available subbufs by 1 */ + meta_len += desc->meta->subbuf_size * 2; + data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, + desc->cpu_fd, meta_len); + ASSERT_EQ(data, MAP_FAILED); +} + +FIXTURE(snapshot) { + bool umount; +}; + +FIXTURE_SETUP(snapshot) +{ + bool fail, umount; + struct stat sb; + char *message; + + if (stat(TRACEFS_ROOT"/snapshot", &sb)) + SKIP(return, "Skipping: %s", "snapshot not available"); + + if (!tracefs_enabled(&message, &fail, &umount)) { + if (fail) { + TH_LOG("Tracefs setup failed: %s", message); + ASSERT_FALSE(fail); + } + SKIP(return, "Skipping: %s", message); + } + + self->umount = umount; +} + +FIXTURE_TEARDOWN(snapshot) +{ + __tracefs_write(TRACEFS_ROOT"/events/sched/sched_switch/trigger", + "!snapshot"); + tracefs_reset(); + + if (self->umount) + tracefs_unmount(); +} + +TEST_F(snapshot, excludes_map) +{ + struct tracefs_cpu_map_desc map_desc; + int cpu = sched_getcpu(); + + ASSERT_GE(cpu, 0); + tracefs_write(TRACEFS_ROOT"/events/sched/sched_switch/trigger", + "snapshot"); + ASSERT_EQ(tracefs_cpu_map(&map_desc, cpu), -EBUSY); +} + +TEST_F(snapshot, excluded_by_map) +{ + struct tracefs_cpu_map_desc map_desc; + int cpu = sched_getcpu(); + + ASSERT_EQ(tracefs_cpu_map(&map_desc, cpu), 0); + + ASSERT_EQ(__tracefs_write(TRACEFS_ROOT"/events/sched/sched_switch/trigger", + "snapshot"), -EBUSY); + ASSERT_EQ(__tracefs_write(TRACEFS_ROOT"/snapshot", + "1"), -EBUSY); +} + +TEST_HARNESS_MAIN -- 2.44.0.769.g3c40516874-goog

26 minutes

1
0
0 0

[PATCH bpf-next v3 0/3] bpf_wq followup series

by Benjamin Tissoires

Few patches that should have been there from day 1. Anyway, they are coming now. Signed-off-by: Benjamin Tissoires <bentiss(a)kernel.org> --- Changes in v3: - fixed bpf_test module not being able to be removed, because the bpf_wq was never freed - Link to v2: https://lore.kernel.org/r/20240430-bpf-next-v2-0-140aa50f0f19@kernel.org Changes in v2: - fix wq in hashtabs not being freed (and static call not being used) - Link to v1: https://lore.kernel.org/r/20240425-bpf-next-v1-0-1d8330e6c643@kernel.org --- Benjamin Tissoires (3): bpf: do not walk twice the map on free bpf: do not walk twice the hash map on free selftests/bpf: drop an unused local variable kernel/bpf/arraymap.c | 15 ++++----- kernel/bpf/hashtab.c | 49 ++++++++--------------------- tools/testing/selftests/bpf/prog_tests/wq.c | 2 -- 3 files changed, 21 insertions(+), 45 deletions(-) --- base-commit: 1bba3b3d373dbafae891e7cb06b8c82c8d62aba1 change-id: 20240425-bpf-next-2114350587e3 Best regards, -- Benjamin Tissoires <bentiss(a)kernel.org>

56 minutes

1
3
0 0

[PATCH v2 0/3] bpf_wq followup series

by Benjamin Tissoires

Few patches that should have been there from day 1. Anyway, they are coming now. Signed-off-by: Benjamin Tissoires <bentiss(a)kernel.org> --- Changes in v2: - fix wq in hashtabs not being freed (and static call not being used) - Link to v1: https://lore.kernel.org/r/20240425-bpf-next-v1-0-1d8330e6c643@kernel.org --- Benjamin Tissoires (3): bpf: do not walk twice the map on free bpf: do not walk twice the hash map on free selftests/bpf: drop an unused local variable kernel/bpf/arraymap.c | 15 ++++----- kernel/bpf/hashtab.c | 49 ++++++++--------------------- tools/testing/selftests/bpf/prog_tests/wq.c | 2 -- 3 files changed, 21 insertions(+), 45 deletions(-) --- base-commit: 1bba3b3d373dbafae891e7cb06b8c82c8d62aba1 change-id: 20240425-bpf-next-2114350587e3 Best regards, -- Benjamin Tissoires <bentiss(a)kernel.org>

1 hour

1
4
0 0

[PATCH 0/3] bpf_wq followup series

by Benjamin Tissoires

Few patches that should have been there from day 1. Anyway, they are coming now. Signed-off-by: Benjamin Tissoires <bentiss(a)kernel.org> --- Benjamin Tissoires (3): bpf: do not walk twice the map on free bpf: do not walk twice the hash map on free selftests/bpf: drop an unused local variable kernel/bpf/arraymap.c | 15 ++++++++------- kernel/bpf/hashtab.c | 16 +++++----------- tools/testing/selftests/bpf/prog_tests/wq.c | 2 -- 3 files changed, 13 insertions(+), 20 deletions(-) --- base-commit: 52578f7f53ff8fe3a8f6f3bc8b5956615c07a16e change-id: 20240425-bpf-next-2114350587e3 Best regards, -- Benjamin Tissoires <bentiss(a)kernel.org>

2 hours, 19 minutes

3
6
0 0

[PATCH] kunit: Cover 'assert.c' with tests

by Ivan Orlov

There are multiple assertion formatting functions in the `assert.c` file, which are not covered with tests yet. Implement the KUnit test for these functions. The test consists of 11 test cases for the following functions: 1) 'is_literal' 2) 'is_str_literal' 3) 'kunit_assert_prologue', test case for multiple assert types 4) 'kunit_assert_print_msg' 5) 'kunit_unary_assert_format' 6) 'kunit_ptr_not_err_assert_format' 7) 'kunit_binary_assert_format' 8) 'kunit_binary_ptr_assert_format' 9) 'kunit_binary_str_assert_format' 10) 'kunit_assert_hexdump' 11) 'kunit_mem_assert_format' The test aims at maximizing the branch coverage for the assertion formatting functions. As you can see, it covers some of the static helper functions as well, so we have to import the test source in the `assert.c` file in order to be able to call and validate them. Signed-off-by: Ivan Orlov <ivan.orlov0322(a)gmail.com> --- lib/kunit/assert.c | 4 + lib/kunit/assert_test.c | 416 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 420 insertions(+) create mode 100644 lib/kunit/assert_test.c diff --git a/lib/kunit/assert.c b/lib/kunit/assert.c index dd1d633d0fe2..ab68c6daf546 100644 --- a/lib/kunit/assert.c +++ b/lib/kunit/assert.c @@ -270,3 +270,7 @@ void kunit_mem_assert_format(const struct kunit_assert *assert, } } EXPORT_SYMBOL_GPL(kunit_mem_assert_format); + +#if IS_ENABLED(CONFIG_KUNIT_TEST) +#include "assert_test.c" +#endif diff --git a/lib/kunit/assert_test.c b/lib/kunit/assert_test.c new file mode 100644 index 000000000000..d54841740761 --- /dev/null +++ b/lib/kunit/assert_test.c @@ -0,0 +1,416 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * KUnit test for the assertion formatting functions. + * Author: Ivan Orlov <ivan.orlov0322(a)gmail.com> + */ +#include <kunit/test.h> + +#define TEST_PTR_EXPECTED_BUF_SIZE 128 + +static void kunit_test_is_literal(struct kunit *test) +{ + KUNIT_EXPECT_TRUE(test, is_literal("5", 5)); + KUNIT_EXPECT_TRUE(test, is_literal("0", 0)); + KUNIT_EXPECT_TRUE(test, is_literal("1234567890", 1234567890)); + KUNIT_EXPECT_TRUE(test, is_literal("-1234567890", -1234567890)); + KUNIT_EXPECT_FALSE(test, is_literal("05", 5)); + KUNIT_EXPECT_FALSE(test, is_literal("", 0)); + KUNIT_EXPECT_FALSE(test, is_literal("-0", 0)); + KUNIT_EXPECT_FALSE(test, is_literal("12#45", 1245)); +} + +static void kunit_test_is_str_literal(struct kunit *test) +{ + KUNIT_EXPECT_TRUE(test, is_str_literal("\"Hello, World!\"", "Hello, World!")); + KUNIT_EXPECT_TRUE(test, is_str_literal("\"\"", "")); + KUNIT_EXPECT_TRUE(test, is_str_literal("\"\"\"", "\"")); + KUNIT_EXPECT_FALSE(test, is_str_literal("", "")); + KUNIT_EXPECT_FALSE(test, is_str_literal("\"", "\"")); + KUNIT_EXPECT_FALSE(test, is_str_literal("\"Abacaba", "Abacaba")); + KUNIT_EXPECT_FALSE(test, is_str_literal("Abacaba\"", "Abacaba")); + KUNIT_EXPECT_FALSE(test, is_str_literal("\"Abacaba\"", "\"Abacaba\"")); +} + +KUNIT_DEFINE_ACTION_WRAPPER(kfree_wrapper, kfree, const void *); + +/* this function is used to get a "char *" string from the string stream and defer its cleanup */ +static char *get_str_from_stream(struct kunit *test, struct string_stream *stream) +{ + char *str = string_stream_get_string(stream); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, str); + kunit_add_action(test, kfree_wrapper, (void *)str); + + return str; +} + +static void kunit_test_assert_prologue(struct kunit *test) +{ + struct string_stream *stream; + const struct kunit_loc location = { + .file = "testfile.c", + .line = 1337, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* Test an expectation fail prologue */ + kunit_assert_prologue(&location, KUNIT_EXPECTATION, stream); + KUNIT_EXPECT_STREQ(test, get_str_from_stream(test, stream), + "EXPECTATION FAILED at testfile.c:1337\n"); + + /* Test an assertion fail prologue */ + string_stream_clear(stream); + kunit_assert_prologue(&location, KUNIT_ASSERTION, stream); + KUNIT_EXPECT_STREQ(test, get_str_from_stream(test, stream), + "ASSERTION FAILED at testfile.c:1337\n"); +} + +/* + * This function accepts an arbitrary count of parameters and generates a va_format struct, + * which can be used to validate kunit_assert_print_msg function + */ +static void verify_assert_print_msg(struct kunit *test, + struct string_stream *stream, + char *expected, const char *format, ...) +{ + va_list list; + const struct va_format vformat = { + .fmt = format, + .va = &list, + }; + + va_start(list, format); + string_stream_clear(stream); + kunit_assert_print_msg(&vformat, stream); + KUNIT_EXPECT_STREQ(test, get_str_from_stream(test, stream), expected); +} + +static void kunit_test_assert_print_msg(struct kunit *test) +{ + struct string_stream *stream; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + verify_assert_print_msg(test, stream, "\nTest", "Test"); + verify_assert_print_msg(test, stream, "\nAbacaba -123 234", "%s %d %u", + "Abacaba", -123, 234U); + verify_assert_print_msg(test, stream, "", NULL); +} + +/* + * Further code contains the tests for different assert format functions. + * This helper function accepts the assert format function, executes it and + * validates the result string from the stream. + */ +static void validate_assert(assert_format_t format_func, struct kunit *test, + const struct kunit_assert *assert, + const char *expected, struct string_stream *stream) +{ + struct va_format message = { NULL, NULL }; + + string_stream_clear(stream); + format_func(assert, &message, stream); + KUNIT_EXPECT_STREQ(test, get_str_from_stream(test, stream), expected); +} + +static void kunit_test_unary_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + struct kunit_unary_assert un_assert = { + .assert = assert, + .condition = "expr", + .expected_true = true, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + validate_assert(kunit_unary_assert_format, test, &un_assert.assert, + KUNIT_SUBTEST_INDENT + "Expected expr to be true, but is false\n", + stream); + + un_assert.expected_true = false; + validate_assert(kunit_unary_assert_format, test, &un_assert.assert, + KUNIT_SUBTEST_INDENT + "Expected expr to be false, but is true\n", + stream); +} + +static void kunit_test_ptr_not_err_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + struct kunit_ptr_not_err_assert not_err_assert = { + .assert = assert, + .text = "expr", + .value = NULL, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* Value is NULL. The corresponding message should be printed out */ + validate_assert(kunit_ptr_not_err_assert_format, test, + &not_err_assert.assert, + KUNIT_SUBTEST_INDENT + "Expected expr is not null, but is\n", + stream); + + /* Value is not NULL, but looks like an error pointer. Error should be printed out */ + not_err_assert.value = (void *)-12; + validate_assert(kunit_ptr_not_err_assert_format, test, + &not_err_assert.assert, + KUNIT_SUBTEST_INDENT + "Expected expr is not error, but is: -12\n", + stream); +} + +static void kunit_test_binary_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + struct kunit_binary_assert_text text = { + .left_text = "1 + 2", + .operation = "==", + .right_text = "2", + }; + const struct kunit_binary_assert binary_assert = { + .assert = assert, + .text = &text, + .left_value = 3, + .right_value = 2, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* + * the right argument is "literal" (see test for `is_literal` above), + * so the right argument won't be printed out separately. + */ + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + KUNIT_SUBTEST_INDENT + "Expected 1 + 2 == 2, but\n" KUNIT_SUBSUBTEST_INDENT + "1 + 2 == 3 (0x3)\n", + stream); + + /* Now both arguments are not "literal". They both will be printed out separately */ + text.right_text = "4 - 2"; + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + KUNIT_SUBTEST_INDENT + "Expected 1 + 2 == 4 - 2, but\n" KUNIT_SUBSUBTEST_INDENT + "1 + 2 == 3 (0x3)\n" KUNIT_SUBSUBTEST_INDENT + "4 - 2 == 2 (0x2)", + stream); + + /* Now the left argument is "literal", so it won't be printed out */ + text.left_text = "3"; + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + KUNIT_SUBTEST_INDENT + "Expected 3 == 4 - 2, but\n" KUNIT_SUBSUBTEST_INDENT + "4 - 2 == 2 (0x2)", + stream); + + /* The left and the right arguments are not "literal", so they won't be printed out */ + text.right_text = "2"; + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + KUNIT_SUBTEST_INDENT "Expected 3 == 2, but\n", stream); +} + +static void kunit_test_binary_ptr_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + char *expected; + static const void *var_a = (void *)0xDEADBEEF; + static const void *var_b = (void *)0xBADDCAFE; + struct kunit_binary_assert_text text = { + .left_text = "var_a", + .operation = "==", + .right_text = "var_b", + }; + struct kunit_binary_ptr_assert binary_ptr_assert = { + .assert = assert, + .text = &text, + .left_value = var_a, + .right_value = var_b, + }; + + expected = kunit_kzalloc(test, TEST_PTR_EXPECTED_BUF_SIZE, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, expected); + /* + * Print the expected string to the buffer first. + * This is necessary as we may have different count of leading zeros in the pointer + * on different architectures. + */ + snprintf(expected, TEST_PTR_EXPECTED_BUF_SIZE, + KUNIT_SUBTEST_INDENT + "Expected var_a == var_b, but\n" KUNIT_SUBSUBTEST_INDENT + "var_a == %px\n" KUNIT_SUBSUBTEST_INDENT "var_b == %px", + var_a, var_b); + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + validate_assert(kunit_binary_ptr_assert_format, test, + &binary_ptr_assert.assert, expected, stream); +} + +static void kunit_test_binary_str_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + static const char *var_a = "abacaba"; + static const char *var_b = "kernel"; + struct kunit_binary_assert_text text = { + .left_text = "var_a", + .operation = "==", + .right_text = "var_b", + }; + struct kunit_binary_str_assert binary_str_assert = { + .assert = assert, + .text = &text, + .left_value = var_a, + .right_value = var_b, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* Both arguments are not "string literals", so they should be printed separately */ + validate_assert(kunit_binary_str_assert_format, test, + &binary_str_assert.assert, + KUNIT_SUBTEST_INDENT + "Expected var_a == var_b, but\n" KUNIT_SUBSUBTEST_INDENT + "var_a == \"abacaba\"\n" KUNIT_SUBSUBTEST_INDENT + "var_b == \"kernel\"", + stream); + + /* Left argument is a "string literal", so it shouldn't be printed separately */ + text.left_text = "\"abacaba\""; + validate_assert(kunit_binary_str_assert_format, test, &binary_str_assert.assert, + KUNIT_SUBTEST_INDENT "Expected \"abacaba\" == var_b, but\n" + KUNIT_SUBSUBTEST_INDENT "var_b == \"kernel\"", stream); + + /* Both arguments are "string literals", so they shouldn't be printed separately */ + text.right_text = "\"kernel\""; + validate_assert(kunit_binary_str_assert_format, test, &binary_str_assert.assert, + KUNIT_SUBTEST_INDENT "Expected \"abacaba\" == \"kernel\", but\n", stream); +} + +static const u8 hex_testbuf1[] = { 0x26, 0x74, 0x6b, 0x9c, 0x55, + 0x45, 0x9d, 0x47, 0xd6, 0x47, + 0x1, 0x89, 0x8c, 0x81, 0x94, + 0x12, 0xfe, 0x01 }; +static const u8 hex_testbuf2[] = { 0x26, 0x74, 0x6b, 0x9c, 0x55, + 0x45, 0x9d, 0x47, 0x21, 0x47, + 0xcd, 0x89, 0x24, 0x50, 0x94, + 0x12, 0xba, 0x01 }; +static void kunit_test_assert_hexdump(struct kunit *test) +{ + struct string_stream *stream; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + /* + * Check that we are getting numbers like <xx> on the right places. + * Also check that we get a newline after 16 bytes + */ + kunit_assert_hexdump(stream, hex_testbuf1, hex_testbuf2, sizeof(hex_testbuf1)); + KUNIT_EXPECT_STREQ(test, get_str_from_stream(test, stream), KUNIT_SUBSUBTEST_INDENT + " 26 74 6b 9c 55 45 9d 47 <d6> 47 <01> 89 <8c><81> 94 12 \n" + KUNIT_SUBSUBTEST_INDENT "<fe> 01 "); + + /* + * We shouldn't get any <xx> numbers when comparing the buffer with itself. + * We still should get a newline after 16 printed bytes + */ + string_stream_clear(stream); + kunit_assert_hexdump(stream, hex_testbuf1, hex_testbuf1, sizeof(hex_testbuf1)); + KUNIT_EXPECT_STREQ(test, get_str_from_stream(test, stream), + KUNIT_SUBSUBTEST_INDENT + " 26 74 6b 9c 55 45 9d 47 d6 47 01 89 8c 81 94 12 \n" + KUNIT_SUBSUBTEST_INDENT " fe 01 "); +} + +static void kunit_test_mem_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct string_stream *expected_stream; + struct kunit_assert assert = {}; + static const struct kunit_binary_assert_text text = { + .left_text = "hex_testbuf1", + .operation = "==", + .right_text = "hex_testbuf2", + }; + struct kunit_mem_assert mem_assert = { + .assert = assert, + .text = &text, + .left_value = NULL, + .right_value = hex_testbuf2, + .size = sizeof(hex_testbuf1), + }; + + expected_stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, expected_stream); + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* The left value is NULL */ + validate_assert(kunit_mem_assert_format, test, &mem_assert.assert, + KUNIT_SUBTEST_INDENT + "Expected hex_testbuf1 is not null, but is\n", + stream); + + /* The right value is NULL, the left value is not NULL */ + mem_assert.left_value = hex_testbuf1; + mem_assert.right_value = NULL; + validate_assert(kunit_mem_assert_format, test, &mem_assert.assert, + KUNIT_SUBTEST_INDENT + "Expected hex_testbuf2 is not null, but is\n", + stream); + + /* Both arguments are not null */ + mem_assert.left_value = hex_testbuf1; + mem_assert.right_value = hex_testbuf2; + + /* + * Building the expected buffer. + */ + string_stream_add(expected_stream, + KUNIT_SUBTEST_INDENT "Expected hex_testbuf1 == hex_testbuf2, but\n"); + string_stream_add(expected_stream, KUNIT_SUBSUBTEST_INDENT "hex_testbuf1 ==\n"); + kunit_assert_hexdump(expected_stream, hex_testbuf1, hex_testbuf2, mem_assert.size); + string_stream_add(expected_stream, + "\n" KUNIT_SUBSUBTEST_INDENT "hex_testbuf2 ==\n"); + kunit_assert_hexdump(expected_stream, hex_testbuf2, hex_testbuf1, mem_assert.size); + + validate_assert(kunit_mem_assert_format, test, &mem_assert.assert, + get_str_from_stream(test, expected_stream), stream); +} + +struct kunit_case assert_test_cases[] = { + KUNIT_CASE(kunit_test_is_literal), + KUNIT_CASE(kunit_test_is_str_literal), + KUNIT_CASE(kunit_test_assert_prologue), + KUNIT_CASE(kunit_test_assert_print_msg), + KUNIT_CASE(kunit_test_unary_assert_format), + KUNIT_CASE(kunit_test_ptr_not_err_assert_format), + KUNIT_CASE(kunit_test_binary_assert_format), + KUNIT_CASE(kunit_test_binary_ptr_assert_format), + KUNIT_CASE(kunit_test_binary_str_assert_format), + KUNIT_CASE(kunit_test_assert_hexdump), + KUNIT_CASE(kunit_test_mem_assert_format), + {} +}; + +struct kunit_suite assert_test_suite = { + .name = "kunit-assert", + .test_cases = assert_test_cases, +}; + +kunit_test_suites(&assert_test_suite); -- 2.34.1

2 hours, 21 minutes

2
2
0 0

[PATCH v2 00/25] Enable FRED with KVM VMX

by Xin Li

This patch set enables the Intel flexible return and event delivery (FRED) architecture with KVM VMX to allow guests to utilize FRED. The FRED architecture defines simple new transitions that change privilege level (ring transitions). The FRED architecture was designed with the following goals: 1) Improve overall performance and response time by replacing event delivery through the interrupt descriptor table (IDT event delivery) and event return by the IRET instruction with lower latency transitions. 2) Improve software robustness by ensuring that event delivery establishes the full supervisor context and that event return establishes the full user context. The new transitions defined by the FRED architecture are FRED event delivery and, for returning from events, two FRED return instructions. FRED event delivery can effect a transition from ring 3 to ring 0, but it is used also to deliver events incident to ring 0. One FRED instruction (ERETU) effects a return from ring 0 to ring 3, while the other (ERETS) returns while remaining in ring 0. Collectively, FRED event delivery and the FRED return instructions are FRED transitions. Intel VMX architecture is extended to run FRED guests, and the major changes are: 1) New VMCS fields for FRED context management, which includes two new event data VMCS fields, eight new guest FRED context VMCS fields and eight new host FRED context VMCS fields. 2) VMX nested-exception support for proper virtualization of stack levels introduced with FRED architecture. Search for the latest FRED spec in most search engines with this search pattern: site:intel.com FRED (flexible return and event delivery) specification As the native FRED patches are committed in the tip tree "x86/fred" branch: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/log/?h=x86/fred, and we have received a good amount of review comments for v1, it's time to send out v2 based on this branch for further help from the community. Patch 1-2 are cleanups to VMX basic and misc MSRs, which were sent out earlier as a preparation for FRED changes: https://lore.kernel.org/kvm/20240206182032.1596-1-xin3.li@intel.com/T/#u Patch 3-15 add FRED support to VMX. Patch 16-21 add FRED support to nested VMX. Patch 22 exposes FRED and its baseline features to KVM guests. Patch 23-25 add FRED selftests. There is also a counterpart qemu patch set for FRED at: https://lore.kernel.org/qemu-devel/20231109072012.8078-1-xin3.li@intel.com/…, which works with this patch set to allow KVM to run FRED guests. Changes since v1: * Always load the secondary VM exit controls (Sean Christopherson). * Remove FRED VM entry/exit controls consistency checks in setup_vmcs_config() (Sean Christopherson). * Clear FRED VM entry/exit controls if FRED is not enumerated (Chao Gao). * Use guest_can_use() to trace FRED enumeration in a vcpu (Chao Gao). * Enable FRED MSRs intercept if FRED is no longer enumerated in CPUID (Chao Gao). * Move guest FRED states init into __vmx_vcpu_reset() (Chao Gao). * Don't use guest_cpuid_has() in vmx_prepare_switch_to_{host,guest}(), which are called from IRQ-disabled context (Chao Gao). * Reset msr_guest_fred_rsp0 in __vmx_vcpu_reset() (Chao Gao). * Fail host requested FRED MSRs access if KVM cannot virtualize FRED (Chao Gao). * Handle the case FRED MSRs are valid but KVM cannot virtualize FRED (Chao Gao). * Add sanity checks when writing to FRED MSRs. * Explain why it is ok to only check CR4.FRED in kvm_is_fred_enabled() (Chao Gao). * Document event data should be equal to CR2/DR6/IA32_XFD_ERR instead of using WARN_ON() (Chao Gao). * Zero event data if a #NM was not caused by extended feature disable (Chao Gao). * Set the nested flag when there is an original interrupt (Chao Gao). * Dump guest FRED states only if guest has FRED enabled (Nikolay Borisov). * Add a prerequisite to SHADOW_FIELD_R[OW] macros * Remove hyperv TLFS related changes (Jeremi Piotrowski). * Use kvm_cpu_cap_has() instead of cpu_feature_enabled() to decouple KVM's capability to virtualize a feature and host's enabling of a feature (Chao Gao). Xin Li (25): KVM: VMX: Cleanup VMX basic information defines and usages KVM: VMX: Cleanup VMX misc information defines and usages KVM: VMX: Add support for the secondary VM exit controls KVM: x86: Mark CR4.FRED as not reserved KVM: VMX: Initialize FRED VM entry/exit controls in vmcs_config KVM: VMX: Defer enabling FRED MSRs save/load until after set CPUID KVM: VMX: Set intercept for FRED MSRs KVM: VMX: Initialize VMCS FRED fields KVM: VMX: Switch FRED RSP0 between host and guest KVM: VMX: Add support for FRED context save/restore KVM: x86: Add kvm_is_fred_enabled() KVM: VMX: Handle FRED event data KVM: VMX: Handle VMX nested exception for FRED KVM: VMX: Disable FRED if FRED consistency checks fail KVM: VMX: Dump FRED context in dump_vmcs() KVM: VMX: Invoke vmx_set_cpu_caps() before nested setup KVM: nVMX: Add support for the secondary VM exit controls KVM: nVMX: Add a prerequisite to SHADOW_FIELD_R[OW] macros KVM: nVMX: Add FRED VMCS fields KVM: nVMX: Add support for VMX FRED controls KVM: nVMX: Add VMCS FRED states checking KVM: x86: Allow FRED/LKGS/WRMSRNS to be exposed to guests KVM: selftests: Run debug_regs test with FRED enabled KVM: selftests: Add a new VM guest mode to run user level code KVM: selftests: Add fred exception tests Documentation/virt/kvm/x86/nested-vmx.rst | 19 + arch/x86/include/asm/kvm_host.h | 8 +- arch/x86/include/asm/msr-index.h | 15 +- arch/x86/include/asm/vmx.h | 59 ++- arch/x86/kvm/cpuid.c | 4 +- arch/x86/kvm/governed_features.h | 1 + arch/x86/kvm/kvm_cache_regs.h | 17 + arch/x86/kvm/svm/svm.c | 4 +- arch/x86/kvm/vmx/capabilities.h | 30 +- arch/x86/kvm/vmx/nested.c | 329 ++++++++++++--- arch/x86/kvm/vmx/nested.h | 2 +- arch/x86/kvm/vmx/vmcs.h | 1 + arch/x86/kvm/vmx/vmcs12.c | 19 + arch/x86/kvm/vmx/vmcs12.h | 38 ++ arch/x86/kvm/vmx/vmcs_shadow_fields.h | 80 ++-- arch/x86/kvm/vmx/vmx.c | 385 +++++++++++++++--- arch/x86/kvm/vmx/vmx.h | 15 +- arch/x86/kvm/x86.c | 103 ++++- arch/x86/kvm/x86.h | 5 +- tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/kvm_util_base.h | 1 + .../selftests/kvm/include/x86_64/processor.h | 36 ++ tools/testing/selftests/kvm/lib/kvm_util.c | 5 +- .../selftests/kvm/lib/x86_64/processor.c | 15 +- tools/testing/selftests/kvm/lib/x86_64/vmx.c | 4 +- .../testing/selftests/kvm/x86_64/debug_regs.c | 50 ++- .../testing/selftests/kvm/x86_64/fred_test.c | 297 ++++++++++++++ 27 files changed, 1320 insertions(+), 223 deletions(-) create mode 100644 tools/testing/selftests/kvm/x86_64/fred_test.c base-commit: e13841907b8fda0ae0ce1ec03684665f578416a8 -- 2.43.0

2 hours, 30 minutes

5
44
0 0

[PATCH 6.6.y] kselftest: Add a ksft_perror() helper

by Edward Liaw

From: Mark Brown <broonie(a)kernel.org> [ Upstream commit 907f33028871fa7c9a3db1efd467b78ef82cce20 ] The standard library perror() function provides a convenient way to print an error message based on the current errno but this doesn't play nicely with KTAP output. Provide a helper which does an equivalent thing in a KTAP compatible format. nolibc doesn't have a strerror() and adding the table of strings required doesn't seem like a good fit for what it's trying to do so when we're using that only print the errno. Signed-off-by: Mark Brown <broonie(a)kernel.org> Reviewed-by: Kees Cook <keescook(a)chromium.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Stable-dep-of: 071af0c9e582 ("selftests: timers: Convert posix_timers test to generate KTAP output") Signed-off-by: Edward Liaw <edliaw(a)google.com> --- tools/testing/selftests/kselftest.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index e8eecbc83a60..ad7b97e16f37 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -48,6 +48,7 @@ #include <stdlib.h> #include <unistd.h> #include <stdarg.h> +#include <string.h> #include <stdio.h> #include <sys/utsname.h> #endif @@ -156,6 +157,19 @@ static inline void ksft_print_msg(const char *msg, ...) va_end(args); } +static inline void ksft_perror(const char *msg) +{ +#ifndef NOLIBC + ksft_print_msg("%s: %s (%d)\n", msg, strerror(errno), errno); +#else + /* + * nolibc doesn't provide strerror() and it seems + * inappropriate to add one, just print the errno. + */ + ksft_print_msg("%s: %d)\n", msg, errno); +#endif +} + static inline void ksft_test_result_pass(const char *msg, ...) { int saved_errno = errno; -- 2.44.0.769.g3c40516874-goog

3 hours, 48 minutes

2
1
0 0

[PATCH v4 00/11] Add support for a few Zc* extensions as well as Zcmop

by Clément Léger

Add support for (yet again) more RVA23U64 missing extensions. Add support for Zcmop, Zca, Zcf, Zcd and Zcb extensions isa string parsing, hwprobe and kvm support. Zce, Zcmt and Zcmp extensions have been left out since they target microcontrollers/embedded CPUs and are not needed by RVA23U64. Since Zc* extensions states that C implies Zca, Zcf (if F and RV32), Zcd (if D), this series modifies the way ISA string is parsed and now does it in two phases. First one parses the string and the second one validates it for the final ISA description. This series is based on the Zimop one [1]. An additional fix [2] should be applied to correctly test that series. Link: https://lore.kernel.org/linux-riscv/20240404103254.1752834-1-cleger@rivosin… [1] Link: https://lore.kernel.org/all/20240409143839.558784-1-cleger@rivosinc.com/ [2] --- v4: - Modify validate() callbacks to return an 0, -EPROBEDEFER or another error. - v3: https://lore.kernel.org/all/20240423124326.2532796-1-cleger@rivosinc.com/ v3: - Fix typo "exists" -> "exist" - Remove C implies Zca, Zcd, Zcf, dt-bindings rules - Rework ISA string resolver to handle dependencies - v2: https://lore.kernel.org/all/20240418124300.1387978-1-cleger@rivosinc.com/ v2: - Add Zc* dependencies validation in dt-bindings - v1: https://lore.kernel.org/lkml/20240410091106.749233-1-cleger@rivosinc.com/ Clément Léger (11): dt-bindings: riscv: add Zca, Zcf, Zcd and Zcb ISA extension description riscv: add ISA extensions validation riscv: add ISA parsing for Zca, Zcf, Zcd and Zcb riscv: hwprobe: export Zca, Zcf, Zcd and Zcb ISA extensions RISC-V: KVM: Allow Zca, Zcf, Zcd and Zcb extensions for Guest/VM KVM: riscv: selftests: Add some Zc* extensions to get-reg-list test dt-bindings: riscv: add Zcmop ISA extension description riscv: add ISA extension parsing for Zcmop riscv: hwprobe: export Zcmop ISA extension RISC-V: KVM: Allow Zcmop extension for Guest/VM KVM: riscv: selftests: Add Zcmop extension to get-reg-list test Documentation/arch/riscv/hwprobe.rst | 24 ++ .../devicetree/bindings/riscv/extensions.yaml | 90 ++++++ arch/riscv/include/asm/cpufeature.h | 1 + arch/riscv/include/asm/hwcap.h | 5 + arch/riscv/include/uapi/asm/hwprobe.h | 5 + arch/riscv/include/uapi/asm/kvm.h | 5 + arch/riscv/kernel/cpufeature.c | 259 ++++++++++++------ arch/riscv/kernel/sys_hwprobe.c | 5 + arch/riscv/kvm/vcpu_onereg.c | 10 + .../selftests/kvm/riscv/get-reg-list.c | 20 ++ 10 files changed, 337 insertions(+), 87 deletions(-) -- 2.43.0

4 hours, 21 minutes

2
13
0 0

[PATCH v8 00/24] RISC-V SBI v2.0 PMU improvements and Perf sampling in KVM guest

by Atish Patra

This series implements SBI PMU improvements done in SBI v2.0[1] i.e. PMU snapshot and fw_read_hi() functions. SBI v2.0 introduced PMU snapshot feature which allows the SBI implementation to provide counter information (i.e. values/overflow status) via a shared memory between the SBI implementation and supervisor OS. This allows to minimize the number of traps in when perf being used inside a kvm guest as it relies on SBI PMU + trap/emulation of the counters. The current set of ratified RISC-V specification also doesn't allow scountovf to be trap/emulated by the hypervisor. The SBI PMU snapshot bridges the gap in ISA as well and enables perf sampling in the guest. However, LCOFI in the guest only works via IRQ filtering in AIA specification. That's why, AIA has to be enabled in the hardware (at least the Ssaia extension) in order to use the sampling support in the perf. Here are the patch wise implementation details. PATCH 1,4,7,8,9,10,11,15 : Generic cleanups/improvements. PATCH 2,3,14 : FW_READ_HI function implementation PATCH 5-6: Add PMU snapshot feature in sbi pmu driver PATCH 12-13: KVM implementation for snapshot and sampling in kvm guests PATCH 16-17: Generic improvements for kvm selftests PATCH 18-22: KVM selftests for SBI PMU extension The series is based on v6.9-rc4 and is available at: https://github.com/atishp04/linux/tree/kvm_pmu_snapshot_v8 The kvmtool patch is also available at: https://github.com/atishp04/kvmtool/tree/sscofpmf It also requires Ssaia ISA extension to be present in the hardware in order to get perf sampling support in the guest. In Qemu virt machine, it can be done by the following config. ``` -cpu rv64,sscofpmf=true,x-ssaia=true ``` There is no other dependencies on AIA apart from that. Thus, Ssaia must be disabled for the guest if AIA patches are not available. Here is the example command. ``` ./lkvm-static run -m 256 -c2 --console serial -p "console=ttyS0 earlycon" --disable-ssaia -k ./Image --debug ``` The series has been tested only in Qemu. Here is the snippet of the perf running inside a kvm guest. =================================================== $ perf record -e cycles -e instructions perf bench sched messaging -g 5 ... $ Running 'sched/messaging' benchmark: ... [ 45.928723] perf_duration_warn: 2 callbacks suppressed [ 45.929000] perf: interrupt took too long (484426 > 483186), lowering kernel.perf_event_max_sample_rate to 250 $ 20 sender and receiver processes per group $ 5 groups == 200 processes run Total time: 14.220 [sec] [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.117 MB perf.data (1942 samples) ] $ perf report --stdio $ To display the perf.data header info, please use --header/--header-only optio> $ $ $ Total Lost Samples: 0 $ $ Samples: 943 of event 'cycles' $ Event count (approx.): 5128976844 $ $ Overhead Command Shared Object Symbol > $ ........ ............... ........................... .....................> $ 7.59% sched-messaging [kernel.kallsyms] [k] memcpy 5.48% sched-messaging [kernel.kallsyms] [k] percpu_counter_ad> 5.24% sched-messaging [kernel.kallsyms] [k] __sbi_rfence_v02_> 4.00% sched-messaging [kernel.kallsyms] [k] _raw_spin_unlock_> 3.79% sched-messaging [kernel.kallsyms] [k] set_pte_range 3.72% sched-messaging [kernel.kallsyms] [k] next_uptodate_fol> 3.46% sched-messaging [kernel.kallsyms] [k] filemap_map_pages 3.31% sched-messaging [kernel.kallsyms] [k] handle_mm_fault 3.20% sched-messaging [kernel.kallsyms] [k] finish_task_switc> 3.16% sched-messaging [kernel.kallsyms] [k] clear_page 3.03% sched-messaging [kernel.kallsyms] [k] mtree_range_walk 2.42% sched-messaging [kernel.kallsyms] [k] flush_icache_pte =================================================== [1] https://github.com/riscv-non-isa/riscv-sbi-doc Changes from v7->v8: 1. Updated event states so that shared memory is updated only during stop operations. 2. Avoid clobbering lower XLEN counter/overflow values in shared memory by maintaining a temporary copy for RV32. 3. Improved overflow handling in snapshot case by supporting all 64 values. 4. Minor cleanups based on suggestions on v7. Changes from v6->v7: 1. Used SBI_SHMEM_DISABLE in the driver. 2. Added RB Tags. 3. Improved the sbi_pmu_test commandline to allow disabling multiple tests. Changes from v5->v6: 1. Added a patch for command line option for the sbi pmu tests. 2. Removed redundant prints and restructure the code little bit. 3. Added a patch for computing the sbi minor version correctly. 4. Addressed all other comments on v5. Changes from v4->v5: 1. Moved sbi related definitions to its own header file from processor.h 2. Added few helper functions for selftests. 3. Improved firmware counter read and RV32 start/stop functions. 4. Converted all the shifting operations to use BIT macro 5. Addressed all other comments on v4. Changes from v3->v4: 1. Added selftests. 2. Fixed an issue to clear the interrupt pending bits. 3. Fixed the counter index in snapshot memory start function. Changes from v2->v3: 1. Fixed a patchwork warning on patch6. 2. Fixed a comment formatting & nit fix in PATCH 3 & 5. 3. Moved the hvien update and sscofpmf enabling to PATCH 9 from PATCH 8. Changes from v1->v2: 1. Fixed warning/errors from patchwork CI. 2. Rebased on top of kvm-next. 3. Added Acked-by tags. Changes from RFC->v1: 1. Addressed all the comments on RFC series. 2. Removed PATCH2 and merged into later patches. 3. Added 2 more patches for minor fixes. 4. Fixed KVM boot issue without Ssaia and made sscofpmf in guest dependent on Ssaia in the host. Atish Patra (24): RISC-V: Fix the typo in Scountovf CSR name RISC-V: Add FIRMWARE_READ_HI definition drivers/perf: riscv: Read upper bits of a firmware counter drivers/perf: riscv: Use BIT macro for shifting operations RISC-V: Add SBI PMU snapshot definitions RISC-V: KVM: Rename the SBI_STA_SHMEM_DISABLE to a generic name RISC-V: Use the minor version mask while computing sbi version drivers/perf: riscv: Fix counter mask iteration for RV32 drivers/perf: riscv: Implement SBI PMU snapshot function RISC-V: KVM: Fix the initial sample period value RISC-V: KVM: No need to update the counter value during reset RISC-V: KVM: No need to exit to the user space if perf event failed RISC-V: KVM: Implement SBI PMU Snapshot feature RISC-V: KVM: Add perf sampling support for guests RISC-V: KVM: Support 64 bit firmware counters on RV32 RISC-V: KVM: Improve firmware counter read function KVM: riscv: selftests: Move sbi definitions to its own header file KVM: riscv: selftests: Add helper functions for extension checks KVM: riscv: selftests: Add Sscofpmf to get-reg-list test KVM: riscv: selftests: Add SBI PMU extension definitions KVM: riscv: selftests: Add SBI PMU selftest KVM: riscv: selftests: Add a test for PMU snapshot functionality KVM: riscv: selftests: Add a test for counter overflow KVM: riscv: selftests: Add commandline option for SBI PMU test arch/riscv/include/asm/csr.h | 5 +- arch/riscv/include/asm/kvm_vcpu_pmu.h | 16 +- arch/riscv/include/asm/sbi.h | 38 +- arch/riscv/include/uapi/asm/kvm.h | 1 + arch/riscv/kernel/paravirt.c | 6 +- arch/riscv/kvm/aia.c | 5 + arch/riscv/kvm/vcpu.c | 15 +- arch/riscv/kvm/vcpu_onereg.c | 6 + arch/riscv/kvm/vcpu_pmu.c | 260 ++++++- arch/riscv/kvm/vcpu_sbi_pmu.c | 17 +- arch/riscv/kvm/vcpu_sbi_sta.c | 4 +- drivers/perf/riscv_pmu.c | 1 + drivers/perf/riscv_pmu_sbi.c | 309 +++++++- include/linux/perf/riscv_pmu.h | 6 + tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/riscv/processor.h | 49 +- .../testing/selftests/kvm/include/riscv/sbi.h | 141 ++++ .../selftests/kvm/include/riscv/ucall.h | 1 + .../selftests/kvm/lib/riscv/processor.c | 12 + .../testing/selftests/kvm/riscv/arch_timer.c | 2 +- .../selftests/kvm/riscv/get-reg-list.c | 4 + .../selftests/kvm/riscv/sbi_pmu_test.c | 681 ++++++++++++++++++ tools/testing/selftests/kvm/steal_time.c | 4 +- 23 files changed, 1467 insertions(+), 117 deletions(-) create mode 100644 tools/testing/selftests/kvm/include/riscv/sbi.h create mode 100644 tools/testing/selftests/kvm/riscv/sbi_pmu_test.c -- 2.34.1

5 hours, 45 minutes

6
44
0 0

[PATCH bpf-next v3 00/11] Add check for bpf lsm return value

by Xu Kuohai

From: Xu Kuohai <xukuohai(a)huawei.com> A bpf prog returning positive number attached to file_alloc_security hook will make kernel panic. Here is a panic log: [ 441.235774] BUG: kernel NULL pointer dereference, address: 00000000000009 [ 441.236748] #PF: supervisor write access in kernel mode [ 441.237429] #PF: error_code(0x0002) - not-present page [ 441.238119] PGD 800000000b02f067 P4D 800000000b02f067 PUD b031067 PMD 0 [ 441.238990] Oops: 0002 [#1] PREEMPT SMP PTI [ 441.239546] CPU: 0 PID: 347 Comm: loader Not tainted 6.8.0-rc6-gafe0cbf23373 #22 [ 441.240496] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b4 [ 441.241933] RIP: 0010:alloc_file+0x4b/0x190 [ 441.242485] Code: 8b 04 25 c0 3c 1f 00 48 8b b0 30 0c 00 00 e8 9c fe ff ff 48 3d 00 f0 ff fb [ 441.244820] RSP: 0018:ffffc90000c67c40 EFLAGS: 00010203 [ 441.245484] RAX: ffff888006a891a0 RBX: ffffffff8223bd00 RCX: 0000000035b08000 [ 441.246391] RDX: ffff88800b95f7b0 RSI: 00000000001fc110 RDI: f089cd0b8088ffff [ 441.247294] RBP: ffffc90000c67c58 R08: 0000000000000001 R09: 0000000000000001 [ 441.248209] R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000001 [ 441.249108] R13: ffffc90000c67c78 R14: ffffffff8223bd00 R15: fffffffffffffff4 [ 441.250007] FS: 00000000005f3300(0000) GS:ffff88803ec00000(0000) knlGS:0000000000000000 [ 441.251053] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 441.251788] CR2: 00000000000001a9 CR3: 000000000bdc4003 CR4: 0000000000170ef0 [ 441.252688] Call Trace: [ 441.253011] <TASK> [ 441.253296] ? __die+0x24/0x70 [ 441.253702] ? page_fault_oops+0x15b/0x480 [ 441.254236] ? fixup_exception+0x26/0x330 [ 441.254750] ? exc_page_fault+0x6d/0x1c0 [ 441.255257] ? asm_exc_page_fault+0x26/0x30 [ 441.255792] ? alloc_file+0x4b/0x190 [ 441.256257] alloc_file_pseudo+0x9f/0xf0 [ 441.256760] __anon_inode_getfile+0x87/0x190 [ 441.257311] ? lock_release+0x14e/0x3f0 [ 441.257808] bpf_link_prime+0xe8/0x1d0 [ 441.258315] bpf_tracing_prog_attach+0x311/0x570 [ 441.258916] ? __pfx_bpf_lsm_file_alloc_security+0x10/0x10 [ 441.259605] __sys_bpf+0x1bb7/0x2dc0 [ 441.260070] __x64_sys_bpf+0x20/0x30 [ 441.260533] do_syscall_64+0x72/0x140 [ 441.261004] entry_SYSCALL_64_after_hwframe+0x6e/0x76 [ 441.261643] RIP: 0033:0x4b0349 [ 441.262045] Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 88 [ 441.264355] RSP: 002b:00007fff74daee38 EFLAGS: 00000246 ORIG_RAX: 0000000000000141 [ 441.265293] RAX: ffffffffffffffda RBX: 00007fff74daef30 RCX: 00000000004b0349 [ 441.266187] RDX: 0000000000000040 RSI: 00007fff74daee50 RDI: 000000000000001c [ 441.267114] RBP: 000000000000001b R08: 00000000005ef820 R09: 0000000000000000 [ 441.268018] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000004 [ 441.268907] R13: 0000000000000004 R14: 00000000005ef018 R15: 00000000004004e8 The reason is that the positive number returned by bpf prog is not a valid errno, and could not be filtered out with IS_ERR which is used by the file system to check errors. As a result, the filesystem mistakenly uses this random positive number as file pointer, causing panic. To fix this issue, there are two schemes: 1. Modify the calling sites of file_alloc_security to take positive return values as zero. 2. Make the bpf verifier to ensure no unpredicted value returned by lsm bpf prog. Considering that hook file_alloc_security never returned positive number before bpf lsm was introduced, and other lsm hooks may have the same problem, scheme 2 is more reasonable. So this series adds lsm return value check in verifier to fix it. v3: 1. Fix incorrect lsm hook return value ranges, and add disabled hook list for bpf lsm, and merge two LSM_RET_INT patches. (KP Singh) 2. Avoid bpf lsm progs attached to different hooks to call each other with tail call 3. Fix a CI failure caused by false rejection of AND operation 4. Add tests v2: https://lore.kernel.org/bpf/20240325095653.1720123-1-xukuohai@huaweicloud.c… fix bpf ci failure v1: https://lore.kernel.org/bpf/20240316122359.1073787-1-xukuohai@huaweicloud.c… Xu Kuohai (11): bpf, lsm: Annotate lsm hook return value range bpf, lsm: Add helper to read lsm hook return value range bpf, lsm: Check bpf lsm hook return values in verifier bpf, lsm: Add bpf lsm disabled hook list bpf: Avoid progs for different hooks calling each other with tail call bpf: Fix compare error in function retval_range_within bpf: Fix a false rejection caused by AND operation selftests/bpf: Avoid load failure for token_lsm.c selftests/bpf: Add return value checks for failed tests selftests/bpf: Add test for lsm tail call selftests/bpf: Add verifier tests for bpf lsm include/linux/bpf.h | 2 + include/linux/bpf_lsm.h | 8 + include/linux/lsm_hook_defs.h | 591 +++++++++--------- include/linux/lsm_hooks.h | 6 - kernel/bpf/bpf_lsm.c | 84 ++- kernel/bpf/btf.c | 5 +- kernel/bpf/core.c | 22 +- kernel/bpf/verifier.c | 82 ++- security/security.c | 1 + .../selftests/bpf/prog_tests/test_lsm.c | 46 +- .../selftests/bpf/prog_tests/verifier.c | 3 +- tools/testing/selftests/bpf/progs/err.h | 10 + .../selftests/bpf/progs/lsm_tailcall.c | 34 + .../selftests/bpf/progs/test_sig_in_xattr.c | 4 + .../bpf/progs/test_verify_pkcs7_sig.c | 8 +- tools/testing/selftests/bpf/progs/token_lsm.c | 4 +- .../bpf/progs/verifier_global_subprogs.c | 7 +- .../selftests/bpf/progs/verifier_lsm.c | 155 +++++ 18 files changed, 754 insertions(+), 318 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/lsm_tailcall.c create mode 100644 tools/testing/selftests/bpf/progs/verifier_lsm.c -- 2.30.2

7 hours, 43 minutes

5
30
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror April 2024