diff options
author | Kalesh Singh <kaleshsingh@google.com> | 2020-12-14 19:07:25 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-12-15 12:13:40 -0800 |
commit | 7df666253f2610284f653bce0e2e50b4923c84aa (patch) | |
tree | bca60256307e0519b844c805eb58efc16d6342ee /tools | |
parent | 3a250629d7325f27b278dad1aaf44eab00090e76 (diff) | |
download | linux-7df666253f2610284f653bce0e2e50b4923c84aa.tar.bz2 |
kselftests: vm: add mremap tests
Patch series "Speed up mremap on large regions", v4.
mremap time can be optimized by moving entries at the PMD/PUD level if the
source and destination addresses are PMD/PUD-aligned and PMD/PUD-sized.
Enable moving at the PMD and PUD levels on arm64 and x86. Other
architectures where this type of move is supported and known to be safe
can also opt-in to these optimizations by enabling HAVE_MOVE_PMD and
HAVE_MOVE_PUD.
Observed Performance Improvements for remapping a PUD-aligned 1GB-sized
region on x86 and arm64:
- HAVE_MOVE_PMD is already enabled on x86 : N/A
- Enabling HAVE_MOVE_PUD on x86 : ~13x speed up
- Enabling HAVE_MOVE_PMD on arm64 : ~ 8x speed up
- Enabling HAVE_MOVE_PUD on arm64 : ~19x speed up
Altogether, HAVE_MOVE_PMD and HAVE_MOVE_PUD
give a total of ~150x speed up on arm64.
This patch (of 4):
Test mremap on regions of various sizes and alignments and validate data
after remapping. Also provide total time for remapping the region which
is useful for performance comparison of the mremap optimizations that move
pages at the PMD/PUD levels if HAVE_MOVE_PMD and/or HAVE_MOVE_PUD are
enabled.
Link: https://lkml.kernel.org/r/20201014005320.2233162-1-kaleshsingh@google.com
Link: https://lkml.kernel.org/r/20201014005320.2233162-2-kaleshsingh@google.com
Signed-off-by: Kalesh Singh <kaleshsingh@google.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Minchan Kim <minchan@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Sami Tolvanen <samitolvanen@google.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Hassan Naveed <hnaveed@wavecomp.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Gavin Shan <gshan@redhat.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Jia He <justin.he@arm.com>
Cc: Ram Pai <linuxram@us.ibm.com>
Cc: Sandipan Das <sandipan@linux.ibm.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: SeongJae Park <sjpark@amazon.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'tools')
-rw-r--r-- | tools/testing/selftests/vm/.gitignore | 1 | ||||
-rw-r--r-- | tools/testing/selftests/vm/Makefile | 1 | ||||
-rw-r--r-- | tools/testing/selftests/vm/mremap_test.c | 344 | ||||
-rwxr-xr-x | tools/testing/selftests/vm/run_vmtests | 11 |
4 files changed, 357 insertions, 0 deletions
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index e90d28bcd518..9a35c3f6a557 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -8,6 +8,7 @@ thuge-gen compaction_test mlock2-tests mremap_dontunmap +mremap_test on-fault-limit transhuge-stress protection_keys diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index bdd3fe7fd086..9a25307f6115 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -37,6 +37,7 @@ TEST_GEN_FILES += map_populate TEST_GEN_FILES += mlock-random-test TEST_GEN_FILES += mlock2-tests TEST_GEN_FILES += mremap_dontunmap +TEST_GEN_FILES += mremap_test TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c new file mode 100644 index 000000000000..9c391d016922 --- /dev/null +++ b/tools/testing/selftests/vm/mremap_test.c @@ -0,0 +1,344 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2020 Google LLC + */ +#define _GNU_SOURCE + +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <time.h> + +#include "../kselftest.h" + +#define EXPECT_SUCCESS 0 +#define EXPECT_FAILURE 1 +#define NON_OVERLAPPING 0 +#define OVERLAPPING 1 +#define NS_PER_SEC 1000000000ULL +#define VALIDATION_DEFAULT_THRESHOLD 4 /* 4MB */ +#define VALIDATION_NO_THRESHOLD 0 /* Verify the entire region */ + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) + +struct config { + unsigned long long src_alignment; + unsigned long long dest_alignment; + unsigned long long region_size; + int overlapping; +}; + +struct test { + const char *name; + struct config config; + int expect_failure; +}; + +enum { + _1KB = 1ULL << 10, /* 1KB -> not page aligned */ + _4KB = 4ULL << 10, + _8KB = 8ULL << 10, + _1MB = 1ULL << 20, + _2MB = 2ULL << 20, + _4MB = 4ULL << 20, + _1GB = 1ULL << 30, + _2GB = 2ULL << 30, + PTE = _4KB, + PMD = _2MB, + PUD = _1GB, +}; + +#define MAKE_TEST(source_align, destination_align, size, \ + overlaps, should_fail, test_name) \ +{ \ + .name = test_name, \ + .config = { \ + .src_alignment = source_align, \ + .dest_alignment = destination_align, \ + .region_size = size, \ + .overlapping = overlaps, \ + }, \ + .expect_failure = should_fail \ +} + +/* + * Returns the start address of the mapping on success, else returns + * NULL on failure. + */ +static void *get_source_mapping(struct config c) +{ + unsigned long long addr = 0ULL; + void *src_addr = NULL; +retry: + addr += c.src_alignment; + src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANONYMOUS | MAP_SHARED, -1, 0); + if (src_addr == MAP_FAILED) { + if (errno == EPERM) + goto retry; + goto error; + } + /* + * Check that the address is aligned to the specified alignment. + * Addresses which have alignments that are multiples of that + * specified are not considered valid. For instance, 1GB address is + * 2MB-aligned, however it will not be considered valid for a + * requested alignment of 2MB. This is done to reduce coincidental + * alignment in the tests. + */ + if (((unsigned long long) src_addr & (c.src_alignment - 1)) || + !((unsigned long long) src_addr & c.src_alignment)) + goto retry; + + if (!src_addr) + goto error; + + return src_addr; +error: + ksft_print_msg("Failed to map source region: %s\n", + strerror(errno)); + return NULL; +} + +/* Returns the time taken for the remap on success else returns -1. */ +static long long remap_region(struct config c, unsigned int threshold_mb, + char pattern_seed) +{ + void *addr, *src_addr, *dest_addr; + unsigned long long i; + struct timespec t_start = {0, 0}, t_end = {0, 0}; + long long start_ns, end_ns, align_mask, ret, offset; + unsigned long long threshold; + + if (threshold_mb == VALIDATION_NO_THRESHOLD) + threshold = c.region_size; + else + threshold = MIN(threshold_mb * _1MB, c.region_size); + + src_addr = get_source_mapping(c); + if (!src_addr) { + ret = -1; + goto out; + } + + /* Set byte pattern */ + srand(pattern_seed); + for (i = 0; i < threshold; i++) + memset((char *) src_addr + i, (char) rand(), 1); + + /* Mask to zero out lower bits of address for alignment */ + align_mask = ~(c.dest_alignment - 1); + /* Offset of destination address from the end of the source region */ + offset = (c.overlapping) ? -c.dest_alignment : c.dest_alignment; + addr = (void *) (((unsigned long long) src_addr + c.region_size + + offset) & align_mask); + + /* See comment in get_source_mapping() */ + if (!((unsigned long long) addr & c.dest_alignment)) + addr = (void *) ((unsigned long long) addr | c.dest_alignment); + + clock_gettime(CLOCK_MONOTONIC, &t_start); + dest_addr = mremap(src_addr, c.region_size, c.region_size, + MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); + clock_gettime(CLOCK_MONOTONIC, &t_end); + + if (dest_addr == MAP_FAILED) { + ksft_print_msg("mremap failed: %s\n", strerror(errno)); + ret = -1; + goto clean_up_src; + } + + /* Verify byte pattern after remapping */ + srand(pattern_seed); + for (i = 0; i < threshold; i++) { + char c = (char) rand(); + + if (((char *) dest_addr)[i] != c) { + ksft_print_msg("Data after remap doesn't match at offset %d\n", + i); + ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, + ((char *) dest_addr)[i] & 0xff); + ret = -1; + goto clean_up_dest; + } + } + + start_ns = t_start.tv_sec * NS_PER_SEC + t_start.tv_nsec; + end_ns = t_end.tv_sec * NS_PER_SEC + t_end.tv_nsec; + ret = end_ns - start_ns; + +/* + * Since the destination address is specified using MREMAP_FIXED, subsequent + * mremap will unmap any previous mapping at the address range specified by + * dest_addr and region_size. This significantly affects the remap time of + * subsequent tests. So we clean up mappings after each test. + */ +clean_up_dest: + munmap(dest_addr, c.region_size); +clean_up_src: + munmap(src_addr, c.region_size); +out: + return ret; +} + +static void run_mremap_test_case(struct test test_case, int *failures, + unsigned int threshold_mb, + unsigned int pattern_seed) +{ + long long remap_time = remap_region(test_case.config, threshold_mb, + pattern_seed); + + if (remap_time < 0) { + if (test_case.expect_failure) + ksft_test_result_pass("%s\n\tExpected mremap failure\n", + test_case.name); + else { + ksft_test_result_fail("%s\n", test_case.name); + *failures += 1; + } + } else { + /* + * Comparing mremap time is only applicable if entire region + * was faulted in. + */ + if (threshold_mb == VALIDATION_NO_THRESHOLD || + test_case.config.region_size <= threshold_mb * _1MB) + ksft_test_result_pass("%s\n\tmremap time: %12lldns\n", + test_case.name, remap_time); + else + ksft_test_result_pass("%s\n", test_case.name); + } +} + +static void usage(const char *cmd) +{ + fprintf(stderr, + "Usage: %s [[-t <threshold_mb>] [-p <pattern_seed>]]\n" + "-t\t only validate threshold_mb of the remapped region\n" + " \t if 0 is supplied no threshold is used; all tests\n" + " \t are run and remapped regions validated fully.\n" + " \t The default threshold used is 4MB.\n" + "-p\t provide a seed to generate the random pattern for\n" + " \t validating the remapped region.\n", cmd); +} + +static int parse_args(int argc, char **argv, unsigned int *threshold_mb, + unsigned int *pattern_seed) +{ + const char *optstr = "t:p:"; + int opt; + + while ((opt = getopt(argc, argv, optstr)) != -1) { + switch (opt) { + case 't': + *threshold_mb = atoi(optarg); + break; + case 'p': + *pattern_seed = atoi(optarg); + break; + default: + usage(argv[0]); + return -1; + } + } + + if (optind < argc) { + usage(argv[0]); + return -1; + } + + return 0; +} + +int main(int argc, char **argv) +{ + int failures = 0; + int i, run_perf_tests; + unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD; + unsigned int pattern_seed; + time_t t; + + pattern_seed = (unsigned int) time(&t); + + if (parse_args(argc, argv, &threshold_mb, &pattern_seed) < 0) + exit(EXIT_FAILURE); + + ksft_print_msg("Test configs:\n\tthreshold_mb=%u\n\tpattern_seed=%u\n\n", + threshold_mb, pattern_seed); + + struct test test_cases[] = { + /* Expected mremap failures */ + MAKE_TEST(_4KB, _4KB, _4KB, OVERLAPPING, EXPECT_FAILURE, + "mremap - Source and Destination Regions Overlapping"), + MAKE_TEST(_4KB, _1KB, _4KB, NON_OVERLAPPING, EXPECT_FAILURE, + "mremap - Destination Address Misaligned (1KB-aligned)"), + MAKE_TEST(_1KB, _4KB, _4KB, NON_OVERLAPPING, EXPECT_FAILURE, + "mremap - Source Address Misaligned (1KB-aligned)"), + + /* Src addr PTE aligned */ + MAKE_TEST(PTE, PTE, _8KB, NON_OVERLAPPING, EXPECT_SUCCESS, + "8KB mremap - Source PTE-aligned, Destination PTE-aligned"), + + /* Src addr 1MB aligned */ + MAKE_TEST(_1MB, PTE, _2MB, NON_OVERLAPPING, EXPECT_SUCCESS, + "2MB mremap - Source 1MB-aligned, Destination PTE-aligned"), + MAKE_TEST(_1MB, _1MB, _2MB, NON_OVERLAPPING, EXPECT_SUCCESS, + "2MB mremap - Source 1MB-aligned, Destination 1MB-aligned"), + + /* Src addr PMD aligned */ + MAKE_TEST(PMD, PTE, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS, + "4MB mremap - Source PMD-aligned, Destination PTE-aligned"), + MAKE_TEST(PMD, _1MB, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS, + "4MB mremap - Source PMD-aligned, Destination 1MB-aligned"), + MAKE_TEST(PMD, PMD, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS, + "4MB mremap - Source PMD-aligned, Destination PMD-aligned"), + + /* Src addr PUD aligned */ + MAKE_TEST(PUD, PTE, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS, + "2GB mremap - Source PUD-aligned, Destination PTE-aligned"), + MAKE_TEST(PUD, _1MB, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS, + "2GB mremap - Source PUD-aligned, Destination 1MB-aligned"), + MAKE_TEST(PUD, PMD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS, + "2GB mremap - Source PUD-aligned, Destination PMD-aligned"), + MAKE_TEST(PUD, PUD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS, + "2GB mremap - Source PUD-aligned, Destination PUD-aligned"), + }; + + struct test perf_test_cases[] = { + /* + * mremap 1GB region - Page table level aligned time + * comparison. + */ + MAKE_TEST(PTE, PTE, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS, + "1GB mremap - Source PTE-aligned, Destination PTE-aligned"), + MAKE_TEST(PMD, PMD, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS, + "1GB mremap - Source PMD-aligned, Destination PMD-aligned"), + MAKE_TEST(PUD, PUD, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS, + "1GB mremap - Source PUD-aligned, Destination PUD-aligned"), + }; + + run_perf_tests = (threshold_mb == VALIDATION_NO_THRESHOLD) || + (threshold_mb * _1MB >= _1GB); + + ksft_set_plan(ARRAY_SIZE(test_cases) + (run_perf_tests ? + ARRAY_SIZE(perf_test_cases) : 0)); + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) + run_mremap_test_case(test_cases[i], &failures, threshold_mb, + pattern_seed); + + if (run_perf_tests) { + ksft_print_msg("\n%s\n", + "mremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:"); + for (i = 0; i < ARRAY_SIZE(perf_test_cases); i++) + run_mremap_test_case(perf_test_cases[i], &failures, + threshold_mb, pattern_seed); + } + + if (failures > 0) + ksft_exit_fail(); + else + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index 9e8837768ee2..e953f3cd9664 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -253,6 +253,17 @@ else echo "[PASS]" fi +echo "-------------------" +echo "running mremap_test" +echo "-------------------" +./mremap_test +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "-----------------" echo "running thuge-gen" echo "-----------------" |