diff options
Diffstat (limited to 'tools')
49 files changed, 1226 insertions, 868 deletions
diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config index b3b00269a52a..b0049be00c70 100644 --- a/tools/testing/kunit/configs/all_tests.config +++ b/tools/testing/kunit/configs/all_tests.config @@ -38,9 +38,6 @@ CONFIG_IWLWIFI=y CONFIG_DAMON=y CONFIG_DAMON_VADDR=y CONFIG_DAMON_PADDR=y -CONFIG_DEBUG_FS=y -CONFIG_DAMON_DBGFS=y -CONFIG_DAMON_DBGFS_DEPRECATED=y CONFIG_REGMAP_BUILD=y diff --git a/tools/testing/selftests/damon/.gitignore b/tools/testing/selftests/damon/.gitignore index 2ab675fecb6b..2f0297657c81 100644 --- a/tools/testing/selftests/damon/.gitignore +++ b/tools/testing/selftests/damon/.gitignore @@ -1,6 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -huge_count_read_write -debugfs_target_ids_read_before_terminate_race -debugfs_target_ids_pid_leak access_memory access_memory_even diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 812f656260fb..ecbf07afc6dd 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -1,15 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for damon selftests -TEST_GEN_FILES += huge_count_read_write -TEST_GEN_FILES += debugfs_target_ids_read_before_terminate_race -TEST_GEN_FILES += debugfs_target_ids_pid_leak TEST_GEN_FILES += access_memory access_memory_even -TEST_FILES = _chk_dependency.sh _debugfs_common.sh _damon_sysfs.py +TEST_FILES = _chk_dependency.sh _damon_sysfs.py # functionality tests -TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh TEST_PROGS += sysfs.sh TEST_PROGS += sysfs_update_schemes_tried_regions_wss_estimation.py TEST_PROGS += damos_quota.py damos_quota_goal.py damos_apply_interval.py @@ -17,11 +13,6 @@ TEST_PROGS += damos_tried_regions.py damon_nr_regions.py TEST_PROGS += reclaim.sh lru_sort.sh # regression tests (reproducers of previously found bugs) -TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh -TEST_PROGS += debugfs_duplicate_context_creation.sh -TEST_PROGS += debugfs_rm_non_contexts.sh -TEST_PROGS += debugfs_target_ids_read_before_terminate_race.sh -TEST_PROGS += debugfs_target_ids_pid_leak.sh TEST_PROGS += sysfs_update_removed_scheme_dir.sh TEST_PROGS += sysfs_update_schemes_tried_regions_hang.py diff --git a/tools/testing/selftests/damon/config b/tools/testing/selftests/damon/config index 0daf38974eb0..a68a9fead5dc 100644 --- a/tools/testing/selftests/damon/config +++ b/tools/testing/selftests/damon/config @@ -1,6 +1,5 @@ CONFIG_DAMON=y CONFIG_DAMON_SYSFS=y -CONFIG_DAMON_DBGFS=y CONFIG_DAMON_PADDR=y CONFIG_DAMON_VADDR=y CONFIG_DAMON_RECLAIM=y diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh deleted file mode 100755 index 902e312bca89..000000000000 --- a/tools/testing/selftests/damon/debugfs_attrs.sh +++ /dev/null @@ -1,17 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test attrs file -# =============== - -file="$DBGFS/attrs" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4 5" "$orig_content" "valid input" -test_write_fail "$file" "1 2 3 4" "$orig_content" "no enough fields" -test_write_fail "$file" "1 2 3 5 4" "$orig_content" \ - "min_nr_regions > max_nr_regions" -test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written" -echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh b/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh deleted file mode 100755 index bd6c22d96ead..000000000000 --- a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh +++ /dev/null @@ -1,27 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test duplicated context creation -# ================================ - -if ! echo foo > "$DBGFS/mk_contexts" -then - echo "context creation failed" - exit 1 -fi - -if echo foo > "$DBGFS/mk_contexts" 2> /dev/null -then - echo "duplicate context creation success" - exit 1 -fi - -if ! echo foo > "$DBGFS/rm_contexts" -then - echo "context deletion failed" - exit 1 -fi - -exit 0 diff --git a/tools/testing/selftests/damon/debugfs_empty_targets.sh b/tools/testing/selftests/damon/debugfs_empty_targets.sh deleted file mode 100755 index effbea33dc16..000000000000 --- a/tools/testing/selftests/damon/debugfs_empty_targets.sh +++ /dev/null @@ -1,21 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test empty targets case -# ======================= - -orig_target_ids=$(cat "$DBGFS/target_ids") -echo "" > "$DBGFS/target_ids" - -if [ -f "$DBGFS/monitor_on_DEPRECATED" ] -then - monitor_on_file="$DBGFS/monitor_on_DEPRECATED" -else - monitor_on_file="$DBGFS/monitor_on" -fi - -orig_monitor_on=$(cat "$monitor_on_file") -test_write_fail "$monitor_on_file" "on" "orig_monitor_on" "empty target ids" -echo "$orig_target_ids" > "$DBGFS/target_ids" diff --git a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh deleted file mode 100755 index 922cadac2950..000000000000 --- a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh +++ /dev/null @@ -1,22 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test huge count read write -# ========================== - -dmesg -C - -for file in "$DBGFS/"* -do - ./huge_count_read_write "$file" -done - -if dmesg | grep -q WARNING -then - dmesg - exit 1 -else - exit 0 -fi diff --git a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh b/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh deleted file mode 100755 index f3ffeb1343cf..000000000000 --- a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test putting non-ctx files/dirs to rm_contexts file -# =================================================== - -dmesg -C - -for file in "$DBGFS/"* -do - (echo "$(basename "$f")" > "$DBGFS/rm_contexts") &> /dev/null - if dmesg | grep -q BUG - then - dmesg - exit 1 - fi -done diff --git a/tools/testing/selftests/damon/debugfs_schemes.sh b/tools/testing/selftests/damon/debugfs_schemes.sh deleted file mode 100755 index 5b39ab44731c..000000000000 --- a/tools/testing/selftests/damon/debugfs_schemes.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test schemes file -# ================= - -file="$DBGFS/schemes" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \ - "$orig_content" "valid input" -test_write_fail "$file" "1 2 -3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines" -test_write_succ "$file" "" "$orig_content" "disabling" -test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \ - "$orig_content" "wrong condition ranges" -echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/debugfs_target_ids.sh b/tools/testing/selftests/damon/debugfs_target_ids.sh deleted file mode 100755 index 49aeabdb0aae..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test target_ids file -# ==================== - -file="$DBGFS/target_ids" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input" -test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input" -test_content "$file" "$orig_content" "1 2" "non-integer was there" -test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input" -test_content "$file" "$orig_content" "" "wrong input written" -test_write_succ "$file" "" "$orig_content" "empty input" -test_content "$file" "$orig_content" "" "empty input written" -echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c deleted file mode 100644 index 0cc2eef7d142..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c +++ /dev/null @@ -1,68 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Author: SeongJae Park <sj@kernel.org> - */ - -#define _GNU_SOURCE - -#include <fcntl.h> -#include <stdbool.h> -#include <stdint.h> -#include <stdio.h> -#include <stdlib.h> -#include <sys/types.h> -#include <sys/wait.h> -#include <sys/time.h> -#include <unistd.h> - -#define DBGFS_TARGET_IDS "/sys/kernel/debug/damon/target_ids" - -static void write_targetid_exit(void) -{ - int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); - char pid_str[128]; - - snprintf(pid_str, sizeof(pid_str), "%d", getpid()); - write(target_ids_fd, pid_str, sizeof(pid_str)); - close(target_ids_fd); - exit(0); -} - -unsigned long msec_timestamp(void) -{ - struct timeval tv; - - gettimeofday(&tv, NULL); - return tv.tv_sec * 1000UL + tv.tv_usec / 1000; -} - -int main(int argc, char *argv[]) -{ - unsigned long start_ms; - int time_to_run, nr_forks = 0; - - if (argc != 2) { - fprintf(stderr, "Usage: %s <msecs to run>\n", argv[0]); - exit(1); - } - time_to_run = atoi(argv[1]); - - start_ms = msec_timestamp(); - while (true) { - int pid = fork(); - - if (pid < 0) { - fprintf(stderr, "fork() failed\n"); - exit(1); - } - if (pid == 0) - write_targetid_exit(); - wait(NULL); - nr_forks++; - - if (msec_timestamp() - start_ms > time_to_run) - break; - } - printf("%d\n", nr_forks); - return 0; -} diff --git a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh deleted file mode 100755 index 31fe33c2b032..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh +++ /dev/null @@ -1,22 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -before=$(grep "^pid " /proc/slabinfo | awk '{print $2}') - -nr_leaks=$(./debugfs_target_ids_pid_leak 1000) -expected_after_max=$((before + nr_leaks / 2)) - -after=$(grep "^pid " /proc/slabinfo | awk '{print $2}') - -echo > /sys/kernel/debug/damon/target_ids - -echo "tried $nr_leaks pid leak" -echo "number of active pid slabs: $before -> $after" -echo "(up to $expected_after_max expected)" -if [ $after -gt $expected_after_max ] -then - echo "maybe pids are leaking" - exit 1 -else - exit 0 -fi diff --git a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c deleted file mode 100644 index b06f52a8ce2d..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c +++ /dev/null @@ -1,80 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Author: SeongJae Park <sj@kernel.org> - */ -#define _GNU_SOURCE - -#include <fcntl.h> -#include <stdbool.h> -#include <stdint.h> -#include <stdio.h> -#include <stdlib.h> -#include <sys/types.h> -#include <sys/wait.h> -#include <time.h> -#include <unistd.h> - -#define DBGFS_MONITOR_ON "/sys/kernel/debug/damon/monitor_on_DEPRECATED" -#define DBGFS_TARGET_IDS "/sys/kernel/debug/damon/target_ids" - -static void turn_damon_on_exit(void) -{ - int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); - int monitor_on_fd = open(DBGFS_MONITOR_ON, O_RDWR); - char pid_str[128]; - - snprintf(pid_str, sizeof(pid_str), "%d", getpid()); - write(target_ids_fd, pid_str, sizeof(pid_str)); - write(monitor_on_fd, "on\n", 3); - close(target_ids_fd); - close(monitor_on_fd); - usleep(1000); - exit(0); -} - -static void try_race(void) -{ - int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); - int pid = fork(); - int buf[256]; - - if (pid < 0) { - fprintf(stderr, "fork() failed\n"); - exit(1); - } - if (pid == 0) - turn_damon_on_exit(); - while (true) { - int status; - - read(target_ids_fd, buf, sizeof(buf)); - if (waitpid(-1, &status, WNOHANG) == pid) - break; - } - close(target_ids_fd); -} - -static inline uint64_t ts_to_ms(struct timespec *ts) -{ - return (uint64_t)ts->tv_sec * 1000 + (uint64_t)ts->tv_nsec / 1000000; -} - -int main(int argc, char *argv[]) -{ - struct timespec start_time, now; - int runtime_ms; - - if (argc != 2) { - fprintf(stderr, "Usage: %s <runtime in ms>\n", argv[0]); - exit(1); - } - runtime_ms = atoi(argv[1]); - clock_gettime(CLOCK_MONOTONIC, &start_time); - while (true) { - try_race(); - clock_gettime(CLOCK_MONOTONIC, &now); - if (ts_to_ms(&now) - ts_to_ms(&start_time) > runtime_ms) - break; - } - return 0; -} diff --git a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh deleted file mode 100755 index fc793c4c9aea..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh +++ /dev/null @@ -1,14 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -dmesg -C - -./debugfs_target_ids_read_before_terminate_race 5000 - -if dmesg | grep -q dbgfs_target_ids_read -then - dmesg - exit 1 -else - exit 0 -fi diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c deleted file mode 100644 index 53e69a669668..000000000000 --- a/tools/testing/selftests/damon/huge_count_read_write.c +++ /dev/null @@ -1,46 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Author: SeongJae Park <sj@kernel.org> - */ - -#include <fcntl.h> -#include <stdlib.h> -#include <unistd.h> -#include <stdio.h> - -#pragma GCC diagnostic push -#if __GNUC__ >= 11 && __GNUC_MINOR__ >= 1 -/* Ignore read(2) overflow and write(2) overread compile warnings */ -#pragma GCC diagnostic ignored "-Wstringop-overread" -#pragma GCC diagnostic ignored "-Wstringop-overflow" -#endif - -void write_read_with_huge_count(char *file) -{ - int filedesc = open(file, O_RDWR); - char buf[256]; - int ret; - - printf("%s %s\n", __func__, file); - if (filedesc < 0) { - fprintf(stderr, "failed opening %s\n", file); - exit(1); - } - - write(filedesc, "", 0xfffffffful); - ret = read(filedesc, buf, 0xfffffffful); - close(filedesc); -} - -#pragma GCC diagnostic pop - -int main(int argc, char *argv[]) -{ - if (argc != 2) { - fprintf(stderr, "Usage: %s <file>\n", argv[0]); - exit(1); - } - write_read_with_huge_count(argv[1]); - - return 0; -} diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index c0c53451a16d..5b993924cc3f 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -171,7 +171,7 @@ static void mfd_fail_new(const char *name, unsigned int flags) r = sys_memfd_create(name, flags); if (r >= 0) { printf("memfd_create(\"%s\", %u) succeeded, but failure expected\n", - name, flags); + name ? name : "NULL", flags); close(r); abort(); } diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 8f01f4da1c0d..121000c28c10 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -27,6 +27,7 @@ protection_keys_64 madv_populate uffd-stress uffd-unit-tests +uffd-wp-mremap mlock-intersect-test mlock-random-test virtual_address_range @@ -36,6 +37,9 @@ map_fixed_noreplace write_to_hugetlbfs hmm-tests memfd_secret +hugetlb_dio +pkey_sighandler_tests_32 +pkey_sighandler_tests_64 soft-dirty split_huge_page_test ksm_tests @@ -49,7 +53,6 @@ va_high_addr_switch hugetlb_fault_after_madv hugetlb_madv_vs_map mseal_test -seal_elf droppable hugetlb_dio pkey_sighandler_tests_32 diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 3de23ea4663f..63ce39d024bb 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -33,9 +33,16 @@ endif # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +CFLAGS = -Wall -O2 -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +# Some distributions (such as Ubuntu) configure GCC so that _FORTIFY_SOURCE is +# automatically enabled at -O1 or above. This triggers various unused-result +# warnings where functions such as read() or write() are called and their +# return value is not checked. Disable _FORTIFY_SOURCE to silence those +# warnings. +CFLAGS += -U_FORTIFY_SOURCE + KDIR ?= /lib/modules/$(shell uname -r)/build ifneq (,$(wildcard $(KDIR)/Module.symvers)) ifneq (,$(wildcard $(KDIR)/include/linux/page_frag_cache.h)) @@ -75,13 +82,13 @@ TEST_GEN_FILES += mrelease_test TEST_GEN_FILES += mremap_dontunmap TEST_GEN_FILES += mremap_test TEST_GEN_FILES += mseal_test -TEST_GEN_FILES += seal_elf TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += uffd-stress TEST_GEN_FILES += uffd-unit-tests +TEST_GEN_FILES += uffd-wp-mremap TEST_GEN_FILES += split_huge_page_test TEST_GEN_FILES += ksm_tests TEST_GEN_FILES += ksm_functional_tests @@ -152,11 +159,16 @@ $(TEST_GEN_FILES): vm_util.c thp_settings.c $(OUTPUT)/uffd-stress: uffd-common.c $(OUTPUT)/uffd-unit-tests: uffd-common.c +$(OUTPUT)/uffd-wp-mremap: uffd-common.c +$(OUTPUT)/protection_keys: pkey_util.c +$(OUTPUT)/pkey_sighandler_tests: pkey_util.c ifeq ($(ARCH),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) +$(BINARIES_32) $(BINARIES_64): pkey_util.c + define gen-target-rule-32 $(1) $(1)_32: $(OUTPUT)/$(1)_32 .PHONY: $(1) $(1)_32 diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config index 4309916f629e..a28baa536332 100644 --- a/tools/testing/selftests/mm/config +++ b/tools/testing/selftests/mm/config @@ -7,3 +7,4 @@ CONFIG_TEST_HMM=m CONFIG_GUP_TEST=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_MEM_SOFT_DIRTY=y +CONFIG_ANON_VMA_NAME=y diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 1238e1c5aae1..9446673645eb 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -1482,7 +1482,7 @@ static void run_with_zeropage(non_anon_test_fn fn, const char *desc) } smem = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1583,7 +1583,7 @@ static void run_with_memfd(non_anon_test_fn fn, const char *desc) goto close; } smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1634,7 +1634,7 @@ static void run_with_tmpfile(non_anon_test_fn fn, const char *desc) goto close; } smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1684,7 +1684,7 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc, goto close; } smem = mmap(NULL, hugetlbsize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1696,7 +1696,7 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc, fn(mem, smem, hugetlbsize); munmap: munmap(mem, hugetlbsize); - if (mem != MAP_FAILED) + if (smem != MAP_FAILED) munmap(smem, hugetlbsize); close: close(fd); diff --git a/tools/testing/selftests/mm/guard-pages.c b/tools/testing/selftests/mm/guard-pages.c index 7cdf815d0d63..ece37212a8a2 100644 --- a/tools/testing/selftests/mm/guard-pages.c +++ b/tools/testing/selftests/mm/guard-pages.c @@ -55,6 +55,12 @@ static int pidfd_open(pid_t pid, unsigned int flags) return syscall(SYS_pidfd_open, pid, flags); } +static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, + size_t n, int advice, unsigned int flags) +{ + return syscall(__NR_process_madvise, pidfd, iovec, n, advice, flags); +} + /* * Enable our signal catcher and try to read/write the specified buffer. The * return value indicates whether the read/write succeeds without a fatal @@ -419,7 +425,7 @@ TEST_F(guard_pages, process_madvise) ASSERT_EQ(munmap(&ptr_region[99 * page_size], page_size), 0); /* Now guard in one step. */ - count = process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0); + count = sys_process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0); /* OK we don't have permission to do this, skip. */ if (count == -1 && errno == EPERM) @@ -440,7 +446,7 @@ TEST_F(guard_pages, process_madvise) ASSERT_FALSE(try_read_write_buf(&ptr3[19 * page_size])); /* Now do the same with unguard... */ - count = process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0); + count = sys_process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0); /* ...and everything should now succeed. */ @@ -990,7 +996,7 @@ TEST_F(guard_pages, fork) MAP_ANON | MAP_PRIVATE, -1, 0); ASSERT_NE(ptr, MAP_FAILED); - /* Establish guard apges in the first 5 pages. */ + /* Establish guard pages in the first 5 pages. */ ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0); pid = fork(); @@ -1030,6 +1036,77 @@ TEST_F(guard_pages, fork) } /* + * Assert expected behaviour after we fork populated ranges of anonymous memory + * and then guard and unguard the range. + */ +TEST_F(guard_pages, fork_cow) +{ + const unsigned long page_size = self->page_size; + char *ptr; + pid_t pid; + int i; + + /* Map 10 pages. */ + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Populate range. */ + for (i = 0; i < 10 * page_size; i++) { + char chr = 'a' + (i % 26); + + ptr[i] = chr; + } + + pid = fork(); + ASSERT_NE(pid, -1); + if (!pid) { + /* This is the child process now. */ + + /* Ensure the range is as expected. */ + for (i = 0; i < 10 * page_size; i++) { + char expected = 'a' + (i % 26); + char actual = ptr[i]; + + ASSERT_EQ(actual, expected); + } + + /* Establish guard pages across the whole range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + /* Remove it. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* + * By removing the guard pages, the page tables will be + * cleared. Assert that we are looking at the zero page now. + */ + for (i = 0; i < 10 * page_size; i++) { + char actual = ptr[i]; + + ASSERT_EQ(actual, '\0'); + } + + exit(0); + } + + /* Parent process. */ + + /* Parent simply waits on child. */ + waitpid(pid, NULL, 0); + + /* Ensure the range is unchanged in parent anon range. */ + for (i = 0; i < 10 * page_size; i++) { + char expected = 'a' + (i % 26); + char actual = ptr[i]; + + ASSERT_EQ(actual, expected); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* * Assert that forking a process with VMAs that do have VM_WIPEONFORK set * behave as expected. */ diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index b748c48908d9..dcdd5bb20f3d 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -776,7 +776,7 @@ err_out: int main(int argc, char *argv[]) { - int ret, opt; + int ret = 0, opt; int prot = 0; int ksm_scan_limit_sec = KSM_SCAN_LIMIT_SEC_DEFAULT; int merge_type = KSM_MERGE_TYPE_DEFAULT; diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index 64bcbb7151cf..1e3a595fbf01 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -204,4 +204,103 @@ TEST_F_TIMEOUT(migration, private_anon_thp, 2*RUNTIME) ASSERT_EQ(pthread_cancel(self->threads[i]), 0); } +/* + * migration test with shared anon THP page + */ + +TEST_F_TIMEOUT(migration, shared_anon_thp, 2*RUNTIME) +{ + pid_t pid; + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, 2 * TWOMEG, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + ptr = (uint64_t *) ALIGN((uintptr_t) ptr, TWOMEG); + ASSERT_EQ(madvise(ptr, TWOMEG, MADV_HUGEPAGE), 0); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) { + pid = fork(); + if (!pid) { + prctl(PR_SET_PDEATHSIG, SIGHUP); + /* Parent may have died before prctl so check now. */ + if (getppid() == 1) + kill(getpid(), SIGHUP); + access_mem(ptr); + } else { + self->pids[i] = pid; + } + } + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(kill(self->pids[i], SIGTERM), 0); +} + +/* + * migration test with private anon hugetlb page + */ +TEST_F_TIMEOUT(migration, private_anon_htlb, 2*RUNTIME) +{ + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, TWOMEG, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) + if (pthread_create(&self->threads[i], NULL, access_mem, ptr)) + perror("Couldn't create thread"); + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(pthread_cancel(self->threads[i]), 0); +} + +/* + * migration test with shared anon hugetlb page + */ +TEST_F_TIMEOUT(migration, shared_anon_htlb, 2*RUNTIME) +{ + pid_t pid; + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, TWOMEG, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) { + pid = fork(); + if (!pid) { + prctl(PR_SET_PDEATHSIG, SIGHUP); + /* Parent may have died before prctl so check now. */ + if (getppid() == 1) + kill(getpid(), SIGHUP); + access_mem(ptr); + } else { + self->pids[i] = pid; + } + } + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(kill(self->pids[i], SIGTERM), 0); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c index 1db134063c38..af2fce496912 100644 --- a/tools/testing/selftests/mm/mkdirty.c +++ b/tools/testing/selftests/mm/mkdirty.c @@ -280,6 +280,7 @@ static void test_uffdio_copy(void) dst = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE|MAP_ANON, -1, 0); if (dst == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); + free(src); return; } diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 5a3a9bcba640..bb84476a177f 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -34,7 +34,7 @@ struct config { unsigned long long dest_alignment; unsigned long long region_size; int overlapping; - int dest_preamble_size; + unsigned int dest_preamble_size; }; struct test { @@ -328,7 +328,7 @@ static void mremap_move_within_range(unsigned int pattern_seed, char *rand_addr) { char *test_name = "mremap mremap move within range"; void *src, *dest; - int i, success = 1; + unsigned int i, success = 1; size_t size = SIZE_MB(20); void *ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, @@ -384,7 +384,7 @@ out: static long long remap_region(struct config c, unsigned int threshold_mb, char *rand_addr) { - void *addr, *src_addr, *dest_addr, *dest_preamble_addr; + void *addr, *src_addr, *dest_addr, *dest_preamble_addr = NULL; unsigned long long t, d; struct timespec t_start = {0, 0}, t_end = {0, 0}; long long start_ns, end_ns, align_mask, ret, offset; @@ -569,7 +569,7 @@ static void mremap_move_1mb_from_start(unsigned int pattern_seed, { char *test_name = "mremap move 1mb from start at 1MB+256KB aligned src"; void *src = NULL, *dest = NULL; - int i, success = 1; + unsigned int i, success = 1; /* Config to reuse get_source_mapping() to do an aligned mmap. */ struct config c = { @@ -636,7 +636,7 @@ out: static void run_mremap_test_case(struct test test_case, int *failures, unsigned int threshold_mb, - unsigned int pattern_seed, char *rand_addr) + char *rand_addr) { long long remap_time = remap_region(test_case.config, threshold_mb, rand_addr); @@ -708,7 +708,8 @@ static int parse_args(int argc, char **argv, unsigned int *threshold_mb, int main(int argc, char **argv) { int failures = 0; - int i, run_perf_tests; + unsigned int i; + int run_perf_tests; unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD; /* hard-coded test configs */ @@ -831,7 +832,7 @@ int main(int argc, char **argv) for (i = 0; i < ARRAY_SIZE(test_cases); i++) run_mremap_test_case(test_cases[i], &failures, threshold_mb, - pattern_seed, rand_addr); + rand_addr); maps_fp = fopen("/proc/self/maps", "r"); @@ -853,7 +854,7 @@ int main(int argc, char **argv) "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, + threshold_mb, rand_addr); } diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c index 01675c412b2a..ad17005521a8 100644 --- a/tools/testing/selftests/mm/mseal_test.c +++ b/tools/testing/selftests/mm/mseal_test.c @@ -802,7 +802,7 @@ static void test_seal_mprotect_partial_mprotect_tail(bool seal) } -static void test_seal_mprotect_two_vma_with_gap(bool seal) +static void test_seal_mprotect_two_vma_with_gap(void) { void *ptr; unsigned long page_size = getpagesize(); @@ -1864,7 +1864,7 @@ static void test_seal_madvise_nodiscard(bool seal) REPORT_TEST_PASS(); } -int main(int argc, char **argv) +int main(void) { bool test_seal = seal_support(); @@ -1913,8 +1913,8 @@ int main(int argc, char **argv) test_seal_mprotect_partial_mprotect(false); test_seal_mprotect_partial_mprotect(true); - test_seal_mprotect_two_vma_with_gap(false); - test_seal_mprotect_two_vma_with_gap(true); + test_seal_mprotect_two_vma_with_gap(); + test_seal_mprotect_two_vma_with_gap(); test_seal_mprotect_merge(false); test_seal_mprotect_merge(true); diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index bcc73b4e805c..57b4bba2b45f 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -34,8 +34,8 @@ #define PAGEMAP "/proc/self/pagemap" int pagemap_fd; int uffd; -int page_size; -int hpage_size; +unsigned int page_size; +unsigned int hpage_size; const char *progname; #define LEN(region) ((region.end - region.start)/page_size) @@ -235,7 +235,9 @@ int get_reads(struct page_region *vec, int vec_size) int sanity_tests_sd(void) { - int mem_size, vec_size, ret, ret2, ret3, i, num_pages = 1000, total_pages = 0; + unsigned long long mem_size, vec_size, i, total_pages = 0; + long ret, ret2, ret3; + int num_pages = 1000; int total_writes, total_reads, reads, count; struct page_region *vec, *vec2; char *mem, *m[2]; @@ -321,9 +323,9 @@ int sanity_tests_sd(void) ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == mem_size/(page_size * 2), + ksft_test_result((unsigned long long)ret == mem_size/(page_size * 2), "%s Repeated pattern of written and non-written pages\n", __func__); /* 4. Repeated pattern of written and non-written pages in parts */ @@ -331,21 +333,21 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, num_pages/2 - 2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ret2 = pagemap_ioctl(mem, mem_size, vec, 2, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret2 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno)); ret3 = pagemap_ioctl(mem, mem_size, vec, vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret3 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret3, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret3, errno, strerror(errno)); ksft_test_result((ret + ret3) == num_pages/2 && ret2 == 2, - "%s Repeated pattern of written and non-written pages in parts %d %d %d\n", + "%s Repeated pattern of written and non-written pages in parts %ld %ld %ld\n", __func__, ret, ret3, ret2); /* 5. Repeated pattern of written and non-written pages max_pages */ @@ -357,13 +359,13 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, num_pages/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ret2 = pagemap_ioctl(mem, mem_size, vec, vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret2 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno)); ksft_test_result(ret == num_pages/2 && ret2 == 1, "%s Repeated pattern of written and non-written pages max_pages\n", @@ -378,12 +380,12 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ret2 = pagemap_ioctl(mem, mem_size, vec2, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret2 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno)); ksft_test_result(ret == 1 && LEN(vec[0]) == 2 && vec[0].start == (uintptr_t)(mem + page_size) && @@ -416,7 +418,7 @@ int sanity_tests_sd(void) ret = pagemap_ioctl(m[1], mem_size, vec, 1, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && LEN(vec[0]) == mem_size/page_size, "%s Two regions\n", __func__); @@ -448,7 +450,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); for (i = 0; i < mem_size/page_size; i += 2) mem[i * page_size]++; @@ -457,7 +459,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); total_pages += ret; @@ -465,7 +467,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); total_pages += ret; @@ -473,7 +475,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); total_pages += ret; @@ -515,9 +517,9 @@ int sanity_tests_sd(void) vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); - if (ret > vec_size) + if ((unsigned long)ret > vec_size) break; reads = get_reads(vec, ret); @@ -554,63 +556,63 @@ int sanity_tests_sd(void) ret = pagemap_ioc(mem, 0, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 0 && walk_end == (long)mem, "Walk_end: Same start and end address\n"); ret = pagemap_ioc(mem, 0, vec, vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 0 && walk_end == (long)mem, "Walk_end: Same start and end with WP\n"); ret = pagemap_ioc(mem, 0, vec, 0, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 0 && walk_end == (long)mem, "Walk_end: Same start and end with 0 output buffer\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: Big vec\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: vec of minimum length\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, vec_size/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size/2), "Walk_end: Half max pages\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size), "Walk_end: 1 max page\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, -1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: max pages\n"); @@ -621,49 +623,49 @@ int sanity_tests_sd(void) ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_end sparse: Big vec\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2), "Walk_end sparse: vec of minimum length\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2), "Walk_end sparse: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size/2, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_end sparse: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_end sparse: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, vec_size/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_endsparse : Half max pages\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2), "Walk_end: 1 max page\n"); @@ -674,9 +676,10 @@ int sanity_tests_sd(void) return 0; } -int base_tests(char *prefix, char *mem, int mem_size, int skip) +int base_tests(char *prefix, char *mem, unsigned long long mem_size, int skip) { - int vec_size, written; + unsigned long long vec_size; + int written; struct page_region *vec, *vec2; if (skip) { @@ -799,8 +802,8 @@ int hpage_unit_tests(void) char *map; int ret, ret2; size_t num_pages = 10; - int map_size = hpage_size * num_pages; - int vec_size = map_size/page_size; + unsigned long long map_size = hpage_size * num_pages; + unsigned long long vec_size = map_size/page_size; struct page_region *vec, *vec2; vec = malloc(sizeof(struct page_region) * vec_size); @@ -1047,7 +1050,8 @@ static void test_simple(void) int sanity_tests(void) { - int mem_size, vec_size, ret, fd, i, buf_size; + unsigned long long mem_size, vec_size; + int ret, fd, i, buf_size; struct page_region *vec; char *mem, *fmem; struct stat sbuf; @@ -1312,7 +1316,9 @@ static ssize_t get_dirty_pages_reset(char *mem, unsigned int count, { struct pm_scan_arg arg = {0}; struct page_region rgns[256]; - int i, j, cnt, ret; + unsigned long long i, j; + long ret; + int cnt; arg.size = sizeof(struct pm_scan_arg); arg.start = (uintptr_t)mem; @@ -1330,7 +1336,7 @@ static ssize_t get_dirty_pages_reset(char *mem, unsigned int count, ksft_exit_fail_msg("ioctl failed\n"); cnt = 0; - for (i = 0; i < ret; ++i) { + for (i = 0; i < (unsigned long)ret; ++i) { if (rgns[i].categories != PAGE_IS_WRITTEN) ksft_exit_fail_msg("wrong flags\n"); @@ -1384,9 +1390,10 @@ void *thread_proc(void *mem) static void transact_test(int page_size) { unsigned int i, count, extra_pages; + unsigned int c; pthread_t th; char *mem; - int ret, c; + int ret; if (pthread_barrier_init(&start_barrier, NULL, nthreads + 1)) ksft_exit_fail_msg("pthread_barrier_init\n"); @@ -1405,9 +1412,9 @@ static void transact_test(int page_size) memset(mem, 0, 0x1000 * nthreads * pages_per_thread); count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); - ksft_test_result(count > 0, "%s count %d\n", __func__, count); + ksft_test_result(count > 0, "%s count %u\n", __func__, count); count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); - ksft_test_result(count == 0, "%s count %d\n", __func__, count); + ksft_test_result(count == 0, "%s count %u\n", __func__, count); finish = 0; for (i = 0; i < nthreads; ++i) @@ -1429,7 +1436,7 @@ static void transact_test(int page_size) ksft_exit_fail_msg("pthread_barrier_wait\n"); if (count > nthreads * access_per_thread) - ksft_exit_fail_msg("Too big count %d expected %d, iter %d\n", + ksft_exit_fail_msg("Too big count %u expected %u, iter %u\n", count, nthreads * access_per_thread, i); c = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); @@ -1454,7 +1461,7 @@ static void transact_test(int page_size) * access and application gets page fault again for the same write. */ if (count < nthreads * access_per_thread) { - ksft_test_result_fail("Lost update, iter %d, %d vs %d.\n", i, count, + ksft_test_result_fail("Lost update, iter %u, %u vs %u.\n", i, count, nthreads * access_per_thread); return; } @@ -1467,15 +1474,16 @@ static void transact_test(int page_size) finish = 1; pthread_barrier_wait(&end_barrier); - ksft_test_result_pass("%s Extra pages %u (%.1lf%%), extra thread faults %d.\n", __func__, + ksft_test_result_pass("%s Extra pages %u (%.1lf%%), extra thread faults %u.\n", __func__, extra_pages, 100.0 * extra_pages / (iter_count * nthreads * access_per_thread), extra_thread_faults); } -int main(int argc, char *argv[]) +int main(int __attribute__((unused)) argc, char *argv[]) { - int mem_size, shmid, buf_size, fd, i, ret; + int shmid, buf_size, fd, i, ret; + unsigned long long mem_size; char *mem, *map, *fmem; struct stat sbuf; diff --git a/tools/testing/selftests/mm/pkey-arm64.h b/tools/testing/selftests/mm/pkey-arm64.h index d9d2100eafc0..8e9685e03c44 100644 --- a/tools/testing/selftests/mm/pkey-arm64.h +++ b/tools/testing/selftests/mm/pkey-arm64.h @@ -30,7 +30,7 @@ #define NR_PKEYS 8 #define NR_RESERVED_PKEYS 1 /* pkey-0 */ -#define PKEY_ALLOW_ALL 0x77777777 +#define PKEY_REG_ALLOW_ALL 0x77777777 #define PKEY_REG_ALLOW_NONE 0x0 #define PKEY_BITS_PER_PKEY 4 @@ -81,11 +81,11 @@ static inline int get_arch_reserved_keys(void) return NR_RESERVED_PKEYS; } -void expect_fault_on_read_execonly_key(void *p1, int pkey) +static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) { } -void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) { return PTR_ERR_ENOTSUP; } diff --git a/tools/testing/selftests/mm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h index f7cfe163b0ff..f080e97b39be 100644 --- a/tools/testing/selftests/mm/pkey-helpers.h +++ b/tools/testing/selftests/mm/pkey-helpers.h @@ -13,22 +13,22 @@ #include <ucontext.h> #include <sys/mman.h> +#include <linux/types.h> + #include "../kselftest.h" /* Define some kernel-like types */ -#define u8 __u8 -#define u16 __u16 -#define u32 __u32 -#define u64 __u64 +typedef __u8 u8; +typedef __u16 u16; +typedef __u32 u32; +typedef __u64 u64; #define PTR_ERR_ENOTSUP ((void *)-ENOTSUP) #ifndef DEBUG_LEVEL #define DEBUG_LEVEL 0 #endif -#define DPRINT_IN_SIGNAL_BUF_SIZE 4096 extern int dprint_in_signal; -extern char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE]; extern int test_nr; extern int iteration_nr; @@ -83,17 +83,18 @@ extern void abort_hooks(void); #ifndef noinline # define noinline __attribute__((noinline)) #endif +#ifndef __maybe_unused +# define __maybe_unused __attribute__((__unused__)) +#endif -noinline int read_ptr(int *ptr) -{ - /* Keep GCC from optimizing this away somehow */ - barrier(); - return *ptr; -} - -void expected_pkey_fault(int pkey); int sys_pkey_alloc(unsigned long flags, unsigned long init_val); int sys_pkey_free(unsigned long pkey); +int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey); + +/* For functions called from protection_keys.c only */ +noinline int read_ptr(int *ptr); +void expected_pkey_fault(int pkey); int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, unsigned long pkey); void record_pkey_malloc(void *ptr, long size, int prot); @@ -171,38 +172,6 @@ static inline void write_pkey_reg(u64 pkey_reg) pkey_reg, __read_pkey_reg()); } -/* - * These are technically racy. since something could - * change PKEY register between the read and the write. - */ -static inline void __pkey_access_allow(int pkey, int do_allow) -{ - u64 pkey_reg = read_pkey_reg(); - int bit = pkey * 2; - - if (do_allow) - pkey_reg &= (1<<bit); - else - pkey_reg |= (1<<bit); - - dprintf4("pkey_reg now: %016llx\n", read_pkey_reg()); - write_pkey_reg(pkey_reg); -} - -static inline void __pkey_write_allow(int pkey, int do_allow_write) -{ - u64 pkey_reg = read_pkey_reg(); - int bit = pkey * 2 + 1; - - if (do_allow_write) - pkey_reg &= (1<<bit); - else - pkey_reg |= (1<<bit); - - write_pkey_reg(pkey_reg); - dprintf4("pkey_reg now: %016llx\n", read_pkey_reg()); -} - #define ALIGN_UP(x, align_to) (((x) + ((align_to)-1)) & ~((align_to)-1)) #define ALIGN_DOWN(x, align_to) ((x) & ~((align_to)-1)) #define ALIGN_PTR_UP(p, ptr_align_to) \ diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h index 3d0c0bdae5bc..1bad310d282a 100644 --- a/tools/testing/selftests/mm/pkey-powerpc.h +++ b/tools/testing/selftests/mm/pkey-powerpc.h @@ -91,7 +91,7 @@ static inline int get_arch_reserved_keys(void) return NR_RESERVED_PKEYS_64K_3KEYS; } -void expect_fault_on_read_execonly_key(void *p1, int pkey) +static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) { /* * powerpc does not allow userspace to change permissions of exec-only @@ -105,7 +105,7 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey) /* 4-byte instructions * 16384 = 64K page */ #define __page_o_noops() asm(".rept 16384 ; nop; .endr") -void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) { void *ptr; int ret; diff --git a/tools/testing/selftests/mm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h index ac91777c8917..f7ecd335df1e 100644 --- a/tools/testing/selftests/mm/pkey-x86.h +++ b/tools/testing/selftests/mm/pkey-x86.h @@ -113,7 +113,7 @@ static inline u32 pkey_bit_position(int pkey) #define XSTATE_PKEY 0x200 #define XSTATE_BV_OFFSET 512 -int pkey_reg_xstate_offset(void) +static inline int pkey_reg_xstate_offset(void) { unsigned int eax; unsigned int ebx; @@ -148,7 +148,7 @@ static inline int get_arch_reserved_keys(void) return NR_RESERVED_PKEYS; } -void expect_fault_on_read_execonly_key(void *p1, int pkey) +static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) { int ptr_contents; @@ -157,7 +157,7 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey) expected_pkey_fault(pkey); } -void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) { return PTR_ERR_ENOTSUP; } diff --git a/tools/testing/selftests/mm/pkey_sighandler_tests.c b/tools/testing/selftests/mm/pkey_sighandler_tests.c index c593a426341c..1ac8c8809880 100644 --- a/tools/testing/selftests/mm/pkey_sighandler_tests.c +++ b/tools/testing/selftests/mm/pkey_sighandler_tests.c @@ -32,11 +32,9 @@ #define STACK_SIZE PTHREAD_STACK_MIN -void expected_pkey_fault(int pkey) {} - -pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER; -pthread_cond_t cond = PTHREAD_COND_INITIALIZER; -siginfo_t siginfo = {0}; +static pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER; +static pthread_cond_t cond = PTHREAD_COND_INITIALIZER; +static siginfo_t siginfo = {0}; /* * We need to use inline assembly instead of glibc's syscall because glibc's @@ -163,7 +161,7 @@ static void *thread_segv_with_pkey0_disabled(void *ptr) __write_pkey_reg(pkey_reg_restrictive_default()); /* Segfault (with SEGV_MAPERR) */ - *(int *) (0x1) = 1; + *(volatile int *)NULL = 1; return NULL; } @@ -179,7 +177,6 @@ static void *thread_segv_pkuerr_stack(void *ptr) static void *thread_segv_maperr_ptr(void *ptr) { stack_t *stack = ptr; - int *bad = (int *)1; u64 pkey_reg; /* @@ -195,7 +192,7 @@ static void *thread_segv_maperr_ptr(void *ptr) __write_pkey_reg(pkey_reg); /* Segfault */ - *bad = 1; + *(volatile int *)NULL = 1; syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); return NULL; } @@ -234,7 +231,7 @@ static void test_sigsegv_handler_with_pkey0_disabled(void) ksft_test_result(siginfo.si_signo == SIGSEGV && siginfo.si_code == SEGV_MAPERR && - siginfo.si_addr == (void *)1, + siginfo.si_addr == NULL, "%s\n", __func__); } @@ -314,11 +311,11 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void) __write_pkey_reg(pkey_reg); /* Protect the new stack with MPK 1 */ - pkey = pkey_alloc(0, 0); - pkey_mprotect(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); + pkey = sys_pkey_alloc(0, 0); + sys_mprotect_pkey(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); /* Set up alternate signal stack that will use the default MPK */ - sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, + sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); sigstack.ss_flags = 0; sigstack.ss_size = STACK_SIZE; @@ -349,7 +346,7 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void) ksft_test_result(siginfo.si_signo == SIGSEGV && siginfo.si_code == SEGV_MAPERR && - siginfo.si_addr == (void *)1, + siginfo.si_addr == NULL, "%s\n", __func__); } @@ -487,11 +484,11 @@ static void test_pkru_sigreturn(void) __write_pkey_reg(pkey_reg); /* Protect the stack with MPK 2 */ - pkey = pkey_alloc(0, 0); - pkey_mprotect(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); + pkey = sys_pkey_alloc(0, 0); + sys_mprotect_pkey(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); /* Set up alternate signal stack that will use the default MPK */ - sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, + sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); sigstack.ss_flags = 0; sigstack.ss_size = STACK_SIZE; @@ -538,6 +535,9 @@ int main(int argc, char *argv[]) ksft_print_header(); ksft_set_plan(ARRAY_SIZE(pkey_tests)); + if (!is_pkeys_supported()) + ksft_exit_skip("pkeys not supported\n"); + for (i = 0; i < ARRAY_SIZE(pkey_tests); i++) (*pkey_tests[i])(); diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c new file mode 100644 index 000000000000..ca4ad0d44ab2 --- /dev/null +++ b/tools/testing/selftests/mm/pkey_util.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <sys/syscall.h> +#include <unistd.h> + +#include "pkey-helpers.h" + +int sys_pkey_alloc(unsigned long flags, unsigned long init_val) +{ + int ret = syscall(SYS_pkey_alloc, flags, init_val); + dprintf1("%s(flags=%lx, init_val=%lx) syscall ret: %d errno: %d\n", + __func__, flags, init_val, ret, errno); + return ret; +} + +int sys_pkey_free(unsigned long pkey) +{ + int ret = syscall(SYS_pkey_free, pkey); + dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret); + return ret; +} + +int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey) +{ + int sret; + + dprintf2("%s(0x%p, %zx, prot=%lx, pkey=%lx)\n", __func__, + ptr, size, orig_prot, pkey); + + errno = 0; + sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); + if (errno) { + dprintf2("SYS_mprotect_key sret: %d\n", sret); + dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot); + dprintf2("SYS_mprotect_key failed, errno: %d\n", errno); + if (DEBUG_LEVEL >= 2) + perror("SYS_mprotect_pkey"); + } + return sret; +} diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 4990f7ab4cb7..a4683f2476f2 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -53,9 +53,15 @@ int test_nr; u64 shadow_pkey_reg; int dprint_in_signal; -char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE]; -void cat_into_file(char *str, char *file) +noinline int read_ptr(int *ptr) +{ + /* Keep GCC from optimizing this away somehow */ + barrier(); + return *ptr; +} + +static void cat_into_file(char *str, char *file) { int fd = open(file, O_RDWR); int ret; @@ -82,7 +88,7 @@ void cat_into_file(char *str, char *file) #if CONTROL_TRACING > 0 static int warned_tracing; -int tracing_root_ok(void) +static int tracing_root_ok(void) { if (geteuid() != 0) { if (!warned_tracing) @@ -95,7 +101,7 @@ int tracing_root_ok(void) } #endif -void tracing_on(void) +static void tracing_on(void) { #if CONTROL_TRACING > 0 #define TRACEDIR "/sys/kernel/tracing" @@ -119,7 +125,7 @@ void tracing_on(void) #endif } -void tracing_off(void) +static void tracing_off(void) { #if CONTROL_TRACING > 0 if (!tracing_root_ok()) @@ -153,7 +159,7 @@ __attribute__((__aligned__(65536))) #else __attribute__((__aligned__(PAGE_SIZE))) #endif -void lots_o_noops_around_write(int *write_to_me) +static void lots_o_noops_around_write(int *write_to_me) { dprintf3("running %s()\n", __func__); __page_o_noops(); @@ -164,7 +170,7 @@ void lots_o_noops_around_write(int *write_to_me) dprintf3("%s() done\n", __func__); } -void dump_mem(void *dumpme, int len_bytes) +static void dump_mem(void *dumpme, int len_bytes) { char *c = (void *)dumpme; int i; @@ -207,7 +213,7 @@ static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags) return 0; } -void pkey_disable_set(int pkey, int flags) +static void pkey_disable_set(int pkey, int flags) { unsigned long syscall_flags = 0; int ret; @@ -245,7 +251,7 @@ void pkey_disable_set(int pkey, int flags) pkey, flags); } -void pkey_disable_clear(int pkey, int flags) +static void pkey_disable_clear(int pkey, int flags) { unsigned long syscall_flags = 0; int ret; @@ -271,19 +277,19 @@ void pkey_disable_clear(int pkey, int flags) pkey, read_pkey_reg()); } -void pkey_write_allow(int pkey) +__maybe_unused static void pkey_write_allow(int pkey) { pkey_disable_clear(pkey, PKEY_DISABLE_WRITE); } -void pkey_write_deny(int pkey) +__maybe_unused static void pkey_write_deny(int pkey) { pkey_disable_set(pkey, PKEY_DISABLE_WRITE); } -void pkey_access_allow(int pkey) +__maybe_unused static void pkey_access_allow(int pkey) { pkey_disable_clear(pkey, PKEY_DISABLE_ACCESS); } -void pkey_access_deny(int pkey) +__maybe_unused static void pkey_access_deny(int pkey) { pkey_disable_set(pkey, PKEY_DISABLE_ACCESS); } @@ -301,9 +307,9 @@ static char *si_code_str(int si_code) return "UNKNOWN"; } -int pkey_faults; -int last_si_pkey = -1; -void signal_handler(int signum, siginfo_t *si, void *vucontext) +static int pkey_faults; +static int last_si_pkey = -1; +static void signal_handler(int signum, siginfo_t *si, void *vucontext) { ucontext_t *uctxt = vucontext; int trapno; @@ -390,27 +396,21 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) /* restore access and let the faulting instruction continue */ pkey_access_allow(siginfo_pkey); #elif defined(__aarch64__) - aarch64_write_signal_pkey(uctxt, PKEY_ALLOW_ALL); + aarch64_write_signal_pkey(uctxt, PKEY_REG_ALLOW_ALL); #endif /* arch */ pkey_faults++; dprintf1("<<<<==================================================\n"); dprint_in_signal = 0; } -int wait_all_children(void) -{ - int status; - return waitpid(-1, &status, 0); -} - -void sig_chld(int x) +static void sig_chld(int x) { dprint_in_signal = 1; dprintf2("[%d] SIGCHLD: %d\n", getpid(), x); dprint_in_signal = 0; } -void setup_sigsegv_handler(void) +static void setup_sigsegv_handler(void) { int r, rs; struct sigaction newact; @@ -436,13 +436,13 @@ void setup_sigsegv_handler(void) pkey_assert(r == 0); } -void setup_handlers(void) +static void setup_handlers(void) { signal(SIGCHLD, &sig_chld); setup_sigsegv_handler(); } -pid_t fork_lazy_child(void) +static pid_t fork_lazy_child(void) { pid_t forkret; @@ -460,35 +460,7 @@ pid_t fork_lazy_child(void) return forkret; } -int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, - unsigned long pkey) -{ - int sret; - - dprintf2("%s(0x%p, %zx, prot=%lx, pkey=%lx)\n", __func__, - ptr, size, orig_prot, pkey); - - errno = 0; - sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); - if (errno) { - dprintf2("SYS_mprotect_key sret: %d\n", sret); - dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot); - dprintf2("SYS_mprotect_key failed, errno: %d\n", errno); - if (DEBUG_LEVEL >= 2) - perror("SYS_mprotect_pkey"); - } - return sret; -} - -int sys_pkey_alloc(unsigned long flags, unsigned long init_val) -{ - int ret = syscall(SYS_pkey_alloc, flags, init_val); - dprintf1("%s(flags=%lx, init_val=%lx) syscall ret: %d errno: %d\n", - __func__, flags, init_val, ret, errno); - return ret; -} - -int alloc_pkey(void) +static int alloc_pkey(void) { int ret; unsigned long init_val = 0x0; @@ -534,19 +506,12 @@ int alloc_pkey(void) return ret; } -int sys_pkey_free(unsigned long pkey) -{ - int ret = syscall(SYS_pkey_free, pkey); - dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret); - return ret; -} - /* * I had a bug where pkey bits could be set by mprotect() but * not cleared. This ensures we get lots of random bit sets * and clears on the vma and pte pkey bits. */ -int alloc_random_pkey(void) +static int alloc_random_pkey(void) { int max_nr_pkey_allocs; int ret; @@ -629,7 +594,7 @@ struct pkey_malloc_record { }; struct pkey_malloc_record *pkey_malloc_records; struct pkey_malloc_record *pkey_last_malloc_record; -long nr_pkey_malloc_records; +static long nr_pkey_malloc_records; void record_pkey_malloc(void *ptr, long size, int prot) { long i; @@ -667,7 +632,7 @@ void record_pkey_malloc(void *ptr, long size, int prot) nr_pkey_malloc_records++; } -void free_pkey_malloc(void *ptr) +static void free_pkey_malloc(void *ptr) { long i; int ret; @@ -694,8 +659,7 @@ void free_pkey_malloc(void *ptr) pkey_assert(false); } - -void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) +static void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) { void *ptr; int ret; @@ -715,7 +679,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) return ptr; } -void *malloc_pkey_anon_huge(long size, int prot, u16 pkey) +static void *malloc_pkey_anon_huge(long size, int prot, u16 pkey) { int ret; void *ptr; @@ -745,10 +709,10 @@ void *malloc_pkey_anon_huge(long size, int prot, u16 pkey) return ptr; } -int hugetlb_setup_ok; +static int hugetlb_setup_ok; #define SYSFS_FMT_NR_HUGE_PAGES "/sys/kernel/mm/hugepages/hugepages-%ldkB/nr_hugepages" #define GET_NR_HUGE_PAGES 10 -void setup_hugetlbfs(void) +static void setup_hugetlbfs(void) { int err; int fd; @@ -796,7 +760,7 @@ void setup_hugetlbfs(void) hugetlb_setup_ok = 1; } -void *malloc_pkey_hugetlb(long size, int prot, u16 pkey) +static void *malloc_pkey_hugetlb(long size, int prot, u16 pkey) { void *ptr; int flags = MAP_ANONYMOUS|MAP_PRIVATE|MAP_HUGETLB; @@ -817,42 +781,15 @@ void *malloc_pkey_hugetlb(long size, int prot, u16 pkey) return ptr; } -void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey) -{ - void *ptr; - int fd; - - dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__, - size, prot, pkey); - pkey_assert(pkey < NR_PKEYS); - fd = open("/dax/foo", O_RDWR); - pkey_assert(fd >= 0); - - ptr = mmap(0, size, prot, MAP_SHARED, fd, 0); - pkey_assert(ptr != (void *)-1); - - mprotect_pkey(ptr, size, prot, pkey); - - record_pkey_malloc(ptr, size, prot); - - dprintf1("mmap()'d for pkey %d @ %p\n", pkey, ptr); - close(fd); - return ptr; -} - -void *(*pkey_malloc[])(long size, int prot, u16 pkey) = { +static void *(*pkey_malloc[])(long size, int prot, u16 pkey) = { malloc_pkey_with_mprotect, malloc_pkey_with_mprotect_subpage, malloc_pkey_anon_huge, malloc_pkey_hugetlb -/* can not do direct with the pkey_mprotect() API: - malloc_pkey_mmap_direct, - malloc_pkey_mmap_dax, -*/ }; -void *malloc_pkey(long size, int prot, u16 pkey) +static void *malloc_pkey(long size, int prot, u16 pkey) { void *ret; static int malloc_type; @@ -882,7 +819,7 @@ void *malloc_pkey(long size, int prot, u16 pkey) return ret; } -int last_pkey_faults; +static int last_pkey_faults; #define UNKNOWN_PKEY -2 void expected_pkey_fault(int pkey) { @@ -905,7 +842,7 @@ void expected_pkey_fault(int pkey) */ if (__read_pkey_reg() != 0) #elif defined(__aarch64__) - if (__read_pkey_reg() != PKEY_ALLOW_ALL) + if (__read_pkey_reg() != PKEY_REG_ALLOW_ALL) #else if (__read_pkey_reg() != shadow_pkey_reg) #endif /* arch */ @@ -924,9 +861,9 @@ void expected_pkey_fault(int pkey) pkey_assert(last_pkey_faults == pkey_faults); \ } while (0) -int test_fds[10] = { -1 }; -int nr_test_fds; -void __save_test_fd(int fd) +static int test_fds[10] = { -1 }; +static int nr_test_fds; +static void __save_test_fd(int fd) { pkey_assert(fd >= 0); pkey_assert(nr_test_fds < ARRAY_SIZE(test_fds)); @@ -934,14 +871,14 @@ void __save_test_fd(int fd) nr_test_fds++; } -int get_test_read_fd(void) +static int get_test_read_fd(void) { int test_fd = open("/etc/passwd", O_RDONLY); __save_test_fd(test_fd); return test_fd; } -void close_test_fds(void) +static void close_test_fds(void) { int i; @@ -954,7 +891,7 @@ void close_test_fds(void) nr_test_fds = 0; } -void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey) +static void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey) { int i, err; int max_nr_pkey_allocs; @@ -1006,7 +943,7 @@ void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey) pkey_assert(!err); } -void test_read_of_write_disabled_region(int *ptr, u16 pkey) +static void test_read_of_write_disabled_region(int *ptr, u16 pkey) { int ptr_contents; @@ -1016,7 +953,7 @@ void test_read_of_write_disabled_region(int *ptr, u16 pkey) dprintf1("*ptr: %d\n", ptr_contents); dprintf1("\n"); } -void test_read_of_access_disabled_region(int *ptr, u16 pkey) +static void test_read_of_access_disabled_region(int *ptr, u16 pkey) { int ptr_contents; @@ -1028,7 +965,7 @@ void test_read_of_access_disabled_region(int *ptr, u16 pkey) expected_pkey_fault(pkey); } -void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr, +static void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr, u16 pkey) { int ptr_contents; @@ -1045,7 +982,7 @@ void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr, expected_pkey_fault(pkey); } -void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr, +static void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr, u16 pkey) { *ptr = __LINE__; @@ -1056,14 +993,14 @@ void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr, expected_pkey_fault(pkey); } -void test_write_of_write_disabled_region(int *ptr, u16 pkey) +static void test_write_of_write_disabled_region(int *ptr, u16 pkey) { dprintf1("disabling write access to PKEY[%02d], doing write\n", pkey); pkey_write_deny(pkey); *ptr = __LINE__; expected_pkey_fault(pkey); } -void test_write_of_access_disabled_region(int *ptr, u16 pkey) +static void test_write_of_access_disabled_region(int *ptr, u16 pkey) { dprintf1("disabling access to PKEY[%02d], doing write\n", pkey); pkey_access_deny(pkey); @@ -1071,7 +1008,7 @@ void test_write_of_access_disabled_region(int *ptr, u16 pkey) expected_pkey_fault(pkey); } -void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr, +static void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr, u16 pkey) { *ptr = __LINE__; @@ -1082,7 +1019,7 @@ void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr, expected_pkey_fault(pkey); } -void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey) +static void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey) { int ret; int test_fd = get_test_read_fd(); @@ -1094,7 +1031,8 @@ void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey) dprintf1("read ret: %d\n", ret); pkey_assert(ret); } -void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey) + +static void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey) { int ret; int test_fd = get_test_read_fd(); @@ -1107,7 +1045,7 @@ void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey) pkey_assert(ret); } -void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey) +static void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey) { int pipe_ret, vmsplice_ret; struct iovec iov; @@ -1129,7 +1067,7 @@ void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey) close(pipe_fds[1]); } -void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey) +static void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey) { int ignored = 0xdada; int futex_ret; @@ -1147,7 +1085,7 @@ void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey) } /* Assumes that all pkeys other than 'pkey' are unallocated */ -void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) +static void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) { int err; int i; @@ -1170,7 +1108,7 @@ void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) } /* Assumes that all pkeys other than 'pkey' are unallocated */ -void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) +static void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) { int err; int bad_pkey = NR_PKEYS+99; @@ -1180,7 +1118,7 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) pkey_assert(err); } -void become_child(void) +static void become_child(void) { pid_t forkret; @@ -1196,7 +1134,7 @@ void become_child(void) } /* Assumes that all pkeys other than 'pkey' are unallocated */ -void test_pkey_alloc_exhaust(int *ptr, u16 pkey) +static void test_pkey_alloc_exhaust(int *ptr, u16 pkey) { int err; int allocated_pkeys[NR_PKEYS] = {0}; @@ -1263,7 +1201,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) } } -void arch_force_pkey_reg_init(void) +static void arch_force_pkey_reg_init(void) { #if defined(__i386__) || defined(__x86_64__) /* arch */ u64 *buf; @@ -1302,7 +1240,7 @@ void arch_force_pkey_reg_init(void) * a long-running test that continually checks the pkey * register. */ -void test_pkey_init_state(int *ptr, u16 pkey) +static void test_pkey_init_state(int *ptr, u16 pkey) { int err; int allocated_pkeys[NR_PKEYS] = {0}; @@ -1340,7 +1278,7 @@ void test_pkey_init_state(int *ptr, u16 pkey) * have to call pkey_alloc() to use it first. Make sure that it * is usable. */ -void test_mprotect_with_pkey_0(int *ptr, u16 pkey) +static void test_mprotect_with_pkey_0(int *ptr, u16 pkey) { long size; int prot; @@ -1364,7 +1302,7 @@ void test_mprotect_with_pkey_0(int *ptr, u16 pkey) mprotect_pkey(ptr, size, prot, pkey); } -void test_ptrace_of_child(int *ptr, u16 pkey) +static void test_ptrace_of_child(int *ptr, u16 pkey) { __attribute__((__unused__)) int peek_result; pid_t child_pid; @@ -1440,7 +1378,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey) free(plain_ptr_unaligned); } -void *get_pointer_to_instructions(void) +static void *get_pointer_to_instructions(void) { void *p1; @@ -1461,7 +1399,7 @@ void *get_pointer_to_instructions(void) return p1; } -void test_executing_on_unreadable_memory(int *ptr, u16 pkey) +static void test_executing_on_unreadable_memory(int *ptr, u16 pkey) { void *p1; int scratch; @@ -1493,7 +1431,7 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey) pkey_assert(!ret); } -void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) +static void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) { void *p1; int scratch; @@ -1542,7 +1480,7 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) } #if defined(__i386__) || defined(__x86_64__) -void test_ptrace_modifies_pkru(int *ptr, u16 pkey) +static void test_ptrace_modifies_pkru(int *ptr, u16 pkey) { u32 new_pkru; pid_t child; @@ -1665,7 +1603,7 @@ void test_ptrace_modifies_pkru(int *ptr, u16 pkey) #endif #if defined(__aarch64__) -void test_ptrace_modifies_pkru(int *ptr, u16 pkey) +static void test_ptrace_modifies_pkru(int *ptr, u16 pkey) { pid_t child; int status, ret; @@ -1742,7 +1680,7 @@ void test_ptrace_modifies_pkru(int *ptr, u16 pkey) } #endif -void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) +static void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) { int size = PAGE_SIZE; int sret; @@ -1756,7 +1694,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) pkey_assert(sret < 0); } -void (*pkey_tests[])(int *ptr, u16 pkey) = { +static void (*pkey_tests[])(int *ptr, u16 pkey) = { test_read_of_write_disabled_region, test_read_of_access_disabled_region, test_read_of_access_disabled_region_with_page_already_mapped, @@ -1782,7 +1720,7 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = { #endif }; -void run_tests_once(void) +static void run_tests_once(void) { int *ptr; int prot = PROT_READ|PROT_WRITE; @@ -1816,7 +1754,7 @@ void run_tests_once(void) iteration_nr++; } -void pkey_setup_shadow(void) +static void pkey_setup_shadow(void) { shadow_pkey_reg = __read_pkey_reg(); } diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 2fc290d9430c..333c468c2699 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -45,6 +45,8 @@ separated by spaces: vmalloc smoke tests - hmm hmm smoke tests +- madv_guard + test madvise(2) MADV_GUARD_INSTALL and MADV_GUARD_REMOVE options - madv_populate test memadvise(2) MADV_POPULATE_{READ,WRITE} options - memfd_secret @@ -307,6 +309,7 @@ CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 3 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem-private 20 16 +CATEGORY="userfaultfd" run_test ./uffd-wp-mremap #cleanup echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages @@ -375,6 +378,9 @@ CATEGORY="mremap" run_test ./mremap_dontunmap CATEGORY="hmm" run_test bash ./test_hmm.sh smoke +# MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests +CATEGORY="madv_guard" run_test ./guard-pages + # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c deleted file mode 100644 index d9f8ba8d5050..000000000000 --- a/tools/testing/selftests/mm/seal_elf.c +++ /dev/null @@ -1,137 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE -#include <sys/mman.h> -#include <stdint.h> -#include <asm-generic/unistd.h> -#include <string.h> -#include <sys/time.h> -#include <sys/resource.h> -#include <stdbool.h> -#include "../kselftest.h" -#include <syscall.h> -#include <errno.h> -#include <stdio.h> -#include <stdlib.h> -#include <fcntl.h> -#include <sys/ioctl.h> -#include <sys/vfs.h> -#include <sys/stat.h> -#include "mseal_helpers.h" - -/* - * define sys_xyx to call syscall directly. - */ -static int sys_mseal(void *start, size_t len) -{ - int sret; - - errno = 0; - sret = syscall(__NR_mseal, start, len, 0); - return sret; -} - -static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) -{ - int sret; - - errno = 0; - sret = syscall(__NR_mprotect, ptr, size, prot); - return sret; -} - -static bool seal_support(void) -{ - int ret; - void *ptr; - unsigned long page_size = getpagesize(); - - ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (ptr == (void *) -1) - return false; - - ret = sys_mseal(ptr, page_size); - if (ret < 0) - return false; - - return true; -} - -const char somestr[4096] = {"READONLY"}; - -static void test_seal_elf(void) -{ - int ret; - FILE *maps; - char line[512]; - uintptr_t addr_start, addr_end; - char prot[5]; - char filename[256]; - unsigned long page_size = getpagesize(); - unsigned long long ptr = (unsigned long long) somestr; - char *somestr2 = (char *)somestr; - - /* - * Modify the protection of readonly somestr - */ - if (((unsigned long long)ptr % page_size) != 0) - ptr = (unsigned long long)ptr & ~(page_size - 1); - - ksft_print_msg("somestr = %s\n", somestr); - ksft_print_msg("change protection to rw\n"); - ret = sys_mprotect((void *)ptr, page_size, PROT_READ|PROT_WRITE); - FAIL_TEST_IF_FALSE(!ret); - *somestr2 = 'A'; - ksft_print_msg("somestr is modified to: %s\n", somestr); - ret = sys_mprotect((void *)ptr, page_size, PROT_READ); - FAIL_TEST_IF_FALSE(!ret); - - maps = fopen("/proc/self/maps", "r"); - FAIL_TEST_IF_FALSE(maps); - - /* - * apply sealing to elf binary - */ - while (fgets(line, sizeof(line), maps)) { - if (sscanf(line, "%lx-%lx %4s %*x %*x:%*x %*u %255[^\n]", - &addr_start, &addr_end, prot, filename) == 4) { - if (strlen(filename)) { - /* - * seal the mapping if read only. - */ - if (strstr(prot, "r-")) { - ret = sys_mseal((void *)addr_start, addr_end - addr_start); - FAIL_TEST_IF_FALSE(!ret); - ksft_print_msg("sealed: %lx-%lx %s %s\n", - addr_start, addr_end, prot, filename); - if ((uintptr_t) somestr >= addr_start && - (uintptr_t) somestr <= addr_end) - ksft_print_msg("mapping for somestr found\n"); - } - } - } - } - fclose(maps); - - ret = sys_mprotect((void *)ptr, page_size, PROT_READ | PROT_WRITE); - FAIL_TEST_IF_FALSE(ret < 0); - ksft_print_msg("somestr is sealed, mprotect is rejected\n"); - - REPORT_TEST_PASS(); -} - -int main(int argc, char **argv) -{ - bool test_seal = seal_support(); - - ksft_print_header(); - ksft_print_msg("pid=%d\n", getpid()); - - if (!test_seal) - ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); - - ksft_set_plan(1); - - test_seal_elf(); - - ksft_finished(); -} diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index bdfa5d085f00..8e1462ce0532 100644 --- a/tools/testing/selftests/mm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c @@ -128,7 +128,7 @@ static void test_mprotect(int pagemap_fd, int pagesize, bool anon) { const char *type[] = {"file", "anon"}; const char *fname = "./soft-dirty-test-file"; - int test_fd; + int test_fd = 0; char *map; if (anon) { diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index eb6d1b9fc362..3f353f3d070f 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -108,38 +108,28 @@ static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hp unsigned long rss_anon_before, rss_anon_after; size_t i; - if (!check_huge_anon(one_page, 4, pmd_pagesize)) { - printf("No THP is allocated\n"); - exit(EXIT_FAILURE); - } + if (!check_huge_anon(one_page, 4, pmd_pagesize)) + ksft_exit_fail_msg("No THP is allocated\n"); rss_anon_before = rss_anon(); - if (!rss_anon_before) { - printf("No RssAnon is allocated before split\n"); - exit(EXIT_FAILURE); - } + if (!rss_anon_before) + ksft_exit_fail_msg("No RssAnon is allocated before split\n"); /* split all THPs */ write_debugfs(PID_FMT, getpid(), (uint64_t)one_page, (uint64_t)one_page + len, 0); for (i = 0; i < len; i++) - if (one_page[i] != (char)0) { - printf("%ld byte corrupted\n", i); - exit(EXIT_FAILURE); - } + if (one_page[i] != (char)0) + ksft_exit_fail_msg("%ld byte corrupted\n", i); - if (!check_huge_anon(one_page, 0, pmd_pagesize)) { - printf("Still AnonHugePages not split\n"); - exit(EXIT_FAILURE); - } + if (!check_huge_anon(one_page, 0, pmd_pagesize)) + ksft_exit_fail_msg("Still AnonHugePages not split\n"); rss_anon_after = rss_anon(); - if (rss_anon_after >= rss_anon_before) { - printf("Incorrect RssAnon value. Before: %ld After: %ld\n", + if (rss_anon_after >= rss_anon_before) + ksft_exit_fail_msg("Incorrect RssAnon value. Before: %ld After: %ld\n", rss_anon_before, rss_anon_after); - exit(EXIT_FAILURE); - } } void split_pmd_zero_pages(void) @@ -150,11 +140,11 @@ void split_pmd_zero_pages(void) one_page = allocate_zero_filled_hugepage(len); verify_rss_anon_split_huge_page_all_zeroes(one_page, nr_hpages, len); - printf("Split zero filled huge pages successful\n"); + ksft_test_result_pass("Split zero filled huge pages successful\n"); free(one_page); } -void split_pmd_thp(void) +void split_pmd_thp_to_order(int order) { char *one_page; size_t len = 4 * pmd_pagesize; @@ -174,7 +164,7 @@ void split_pmd_thp(void) /* split all THPs */ write_debugfs(PID_FMT, getpid(), (uint64_t)one_page, - (uint64_t)one_page + len, 0); + (uint64_t)one_page + len, order); for (i = 0; i < len; i++) if (one_page[i] != (char)i) @@ -184,7 +174,7 @@ void split_pmd_thp(void) if (!check_huge_anon(one_page, 0, pmd_pagesize)) ksft_exit_fail_msg("Still AnonHugePages not split\n"); - ksft_test_result_pass("Split huge pages successful\n"); + ksft_test_result_pass("Split huge pages to order %d successful\n", order); free(one_page); } @@ -491,7 +481,7 @@ int main(int argc, char **argv) if (argc > 1) optional_xfs_path = argv[1]; - ksft_set_plan(3+9); + ksft_set_plan(1+8+2+9); pagesize = getpagesize(); pageshift = ffs(pagesize) - 1; @@ -502,7 +492,11 @@ int main(int argc, char **argv) fd_size = 2 * pmd_pagesize; split_pmd_zero_pages(); - split_pmd_thp(); + + for (i = 0; i < 9; i++) + if (i != 1) + split_pmd_thp_to_order(i); + split_pte_mapped_thp(); split_file_backed_thp(); diff --git a/tools/testing/selftests/mm/thp_settings.c b/tools/testing/selftests/mm/thp_settings.c index 577eaab6266f..ad872af1c81a 100644 --- a/tools/testing/selftests/mm/thp_settings.c +++ b/tools/testing/selftests/mm/thp_settings.c @@ -87,7 +87,7 @@ int write_file(const char *path, const char *buf, size_t buflen) return (unsigned int) numwritten; } -const unsigned long read_num(const char *path) +unsigned long read_num(const char *path) { char buf[21]; @@ -172,7 +172,7 @@ void thp_write_string(const char *name, const char *val) } } -const unsigned long thp_read_num(const char *name) +unsigned long thp_read_num(const char *name) { char path[PATH_MAX]; int ret; diff --git a/tools/testing/selftests/mm/thp_settings.h b/tools/testing/selftests/mm/thp_settings.h index 876235a23460..fc131d23d593 100644 --- a/tools/testing/selftests/mm/thp_settings.h +++ b/tools/testing/selftests/mm/thp_settings.h @@ -64,12 +64,12 @@ struct thp_settings { int read_file(const char *path, char *buf, size_t buflen); int write_file(const char *path, const char *buf, size_t buflen); -const unsigned long read_num(const char *path); +unsigned long read_num(const char *path); void write_num(const char *path, unsigned long num); int thp_read_string(const char *name, const char * const strings[]); void thp_write_string(const char *name, const char *val); -const unsigned long thp_read_num(const char *name); +unsigned long thp_read_num(const char *name); void thp_write_num(const char *name, unsigned long num); void thp_write_settings(struct thp_settings *settings); diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index a2e71b1636e7..9ff71fa1f9bf 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -1122,7 +1122,7 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size, char c; unsigned long long count; struct uffd_args args = { 0 }; - char *orig_area_src, *orig_area_dst; + char *orig_area_src = NULL, *orig_area_dst = NULL; unsigned long step_size, step_count; unsigned long src_offs = 0; unsigned long dst_offs = 0; @@ -1190,7 +1190,7 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size, nr, count, count_verify[src_offs + nr + i]); } } - if (step_size > page_size) { + if (chunk_size > page_size) { area_src = orig_area_src; area_dst = orig_area_dst; } diff --git a/tools/testing/selftests/mm/uffd-wp-mremap.c b/tools/testing/selftests/mm/uffd-wp-mremap.c new file mode 100644 index 000000000000..2c4f984bd73c --- /dev/null +++ b/tools/testing/selftests/mm/uffd-wp-mremap.c @@ -0,0 +1,380 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define _GNU_SOURCE +#include <stdbool.h> +#include <stdint.h> +#include <fcntl.h> +#include <assert.h> +#include <linux/mman.h> +#include <sys/mman.h> +#include "../kselftest.h" +#include "thp_settings.h" +#include "uffd-common.h" + +static int pagemap_fd; +static size_t pagesize; +static int nr_pagesizes = 1; +static int nr_thpsizes; +static size_t thpsizes[20]; +static int nr_hugetlbsizes; +static size_t hugetlbsizes[10]; + +static int sz2ord(size_t size) +{ + return __builtin_ctzll(size / pagesize); +} + +static int detect_thp_sizes(size_t sizes[], int max) +{ + int count = 0; + unsigned long orders; + size_t kb; + int i; + + /* thp not supported at all. */ + if (!read_pmd_pagesize()) + return 0; + + orders = thp_supported_orders(); + + for (i = 0; orders && count < max; i++) { + if (!(orders & (1UL << i))) + continue; + orders &= ~(1UL << i); + kb = (pagesize >> 10) << i; + sizes[count++] = kb * 1024; + ksft_print_msg("[INFO] detected THP size: %zu KiB\n", kb); + } + + return count; +} + +static void *mmap_aligned(size_t size, int prot, int flags) +{ + size_t mmap_size = size * 2; + char *mmap_mem, *mem; + + mmap_mem = mmap(NULL, mmap_size, prot, flags, -1, 0); + if (mmap_mem == MAP_FAILED) + return mmap_mem; + + mem = (char *)(((uintptr_t)mmap_mem + size - 1) & ~(size - 1)); + munmap(mmap_mem, mem - mmap_mem); + munmap(mem + size, mmap_mem + mmap_size - mem - size); + + return mem; +} + +static void *alloc_one_folio(size_t size, bool private, bool hugetlb) +{ + bool thp = !hugetlb && size > pagesize; + int flags = MAP_ANONYMOUS; + int prot = PROT_READ | PROT_WRITE; + char *mem, *addr; + + assert((size & (size - 1)) == 0); + + if (private) + flags |= MAP_PRIVATE; + else + flags |= MAP_SHARED; + + /* + * For THP, we must explicitly enable the THP size, allocate twice the + * required space then manually align. + */ + if (thp) { + struct thp_settings settings = *thp_current_settings(); + + if (private) + settings.hugepages[sz2ord(size)].enabled = THP_ALWAYS; + else + settings.shmem_hugepages[sz2ord(size)].enabled = SHMEM_ALWAYS; + + thp_push_settings(&settings); + + mem = mmap_aligned(size, prot, flags); + } else { + if (hugetlb) { + flags |= MAP_HUGETLB; + flags |= __builtin_ctzll(size) << MAP_HUGE_SHIFT; + } + + mem = mmap(NULL, size, prot, flags, -1, 0); + } + + if (mem == MAP_FAILED) { + mem = NULL; + goto out; + } + + assert(((uintptr_t)mem & (size - 1)) == 0); + + /* + * Populate the folio by writing the first byte and check that all pages + * are populated. Finally set the whole thing to non-zero data to avoid + * kernel from mapping it back to the zero page. + */ + mem[0] = 1; + for (addr = mem; addr < mem + size; addr += pagesize) { + if (!pagemap_is_populated(pagemap_fd, addr)) { + munmap(mem, size); + mem = NULL; + goto out; + } + } + memset(mem, 1, size); +out: + if (thp) + thp_pop_settings(); + + return mem; +} + +static bool check_uffd_wp_state(void *mem, size_t size, bool expect) +{ + uint64_t pte; + void *addr; + + for (addr = mem; addr < mem + size; addr += pagesize) { + pte = pagemap_get_entry(pagemap_fd, addr); + if (!!(pte & PM_UFFD_WP) != expect) { + ksft_test_result_fail("uffd-wp not %s for pte %lu!\n", + expect ? "set" : "clear", + (addr - mem) / pagesize); + return false; + } + } + + return true; +} + +static bool range_is_swapped(void *addr, size_t size) +{ + for (; size; addr += pagesize, size -= pagesize) + if (!pagemap_is_swapped(pagemap_fd, addr)) + return false; + return true; +} + +static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb) +{ + struct uffdio_writeprotect wp_prms; + uint64_t features = 0; + void *addr = NULL; + void *mem = NULL; + + assert(!(hugetlb && swapout)); + + ksft_print_msg("[RUN] %s(size=%zu, private=%s, swapout=%s, hugetlb=%s)\n", + __func__, + size, + private ? "true" : "false", + swapout ? "true" : "false", + hugetlb ? "true" : "false"); + + /* Allocate a folio of required size and type. */ + mem = alloc_one_folio(size, private, hugetlb); + if (!mem) { + ksft_test_result_fail("alloc_one_folio() failed\n"); + goto out; + } + + /* Register range for uffd-wp. */ + if (userfaultfd_open(&features)) { + ksft_test_result_fail("userfaultfd_open() failed\n"); + goto out; + } + if (uffd_register(uffd, mem, size, false, true, false)) { + ksft_test_result_fail("uffd_register() failed\n"); + goto out; + } + wp_prms.mode = UFFDIO_WRITEPROTECT_MODE_WP; + wp_prms.range.start = (uintptr_t)mem; + wp_prms.range.len = size; + if (ioctl(uffd, UFFDIO_WRITEPROTECT, &wp_prms)) { + ksft_test_result_fail("ioctl(UFFDIO_WRITEPROTECT) failed\n"); + goto out; + } + + if (swapout) { + madvise(mem, size, MADV_PAGEOUT); + if (!range_is_swapped(mem, size)) { + ksft_test_result_skip("MADV_PAGEOUT did not work, is swap enabled?\n"); + goto out; + } + } + + /* Check that uffd-wp is set for all PTEs in range. */ + if (!check_uffd_wp_state(mem, size, true)) + goto out; + + /* + * Move the mapping to a new, aligned location. Since + * UFFD_FEATURE_EVENT_REMAP is not set, we expect the uffd-wp bit for + * each PTE to be cleared in the new mapping. + */ + addr = mmap_aligned(size, PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS); + if (addr == MAP_FAILED) { + ksft_test_result_fail("mmap_aligned() failed\n"); + goto out; + } + if (mremap(mem, size, size, MREMAP_FIXED | MREMAP_MAYMOVE, addr) == MAP_FAILED) { + ksft_test_result_fail("mremap() failed\n"); + munmap(addr, size); + goto out; + } + mem = addr; + + /* Check that uffd-wp is cleared for all PTEs in range. */ + if (!check_uffd_wp_state(mem, size, false)) + goto out; + + ksft_test_result_pass("%s(size=%zu, private=%s, swapout=%s, hugetlb=%s)\n", + __func__, + size, + private ? "true" : "false", + swapout ? "true" : "false", + hugetlb ? "true" : "false"); +out: + if (mem) + munmap(mem, size); + if (uffd >= 0) { + close(uffd); + uffd = -1; + } +} + +struct testcase { + size_t *sizes; + int *nr_sizes; + bool private; + bool swapout; + bool hugetlb; +}; + +static const struct testcase testcases[] = { + /* base pages. */ + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = false, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = true, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = false, + .swapout = true, + .hugetlb = false, + }, + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = true, + .swapout = true, + .hugetlb = false, + }, + + /* thp. */ + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = false, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = true, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = false, + .swapout = true, + .hugetlb = false, + }, + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = true, + .swapout = true, + .hugetlb = false, + }, + + /* hugetlb. */ + { + .sizes = hugetlbsizes, + .nr_sizes = &nr_hugetlbsizes, + .private = false, + .swapout = false, + .hugetlb = true, + }, + { + .sizes = hugetlbsizes, + .nr_sizes = &nr_hugetlbsizes, + .private = true, + .swapout = false, + .hugetlb = true, + }, +}; + +int main(int argc, char **argv) +{ + struct thp_settings settings; + int i, j, plan = 0; + + pagesize = getpagesize(); + nr_thpsizes = detect_thp_sizes(thpsizes, ARRAY_SIZE(thpsizes)); + nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, + ARRAY_SIZE(hugetlbsizes)); + + /* If THP is supported, save THP settings and initially disable THP. */ + if (nr_thpsizes) { + thp_save_settings(); + thp_read_settings(&settings); + for (i = 0; i < NR_ORDERS; i++) { + settings.hugepages[i].enabled = THP_NEVER; + settings.shmem_hugepages[i].enabled = SHMEM_NEVER; + } + thp_push_settings(&settings); + } + + for (i = 0; i < ARRAY_SIZE(testcases); i++) + plan += *testcases[i].nr_sizes; + ksft_set_plan(plan); + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd < 0) + ksft_exit_fail_msg("opening pagemap failed\n"); + + for (i = 0; i < ARRAY_SIZE(testcases); i++) { + const struct testcase *tc = &testcases[i]; + + for (j = 0; j < *tc->nr_sizes; j++) + test_one_folio(tc->sizes[j], tc->private, tc->swapout, + tc->hugetlb); + } + + /* If THP is supported, restore original THP settings. */ + if (nr_thpsizes) + thp_restore_settings(); + + i = ksft_get_fail_cnt(); + if (i) + ksft_exit_fail_msg("%d out of %d tests failed\n", + i, ksft_test_num()); + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index 2a2b69e91950..b380e102b22f 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -10,10 +10,12 @@ #include <string.h> #include <unistd.h> #include <errno.h> +#include <sys/prctl.h> #include <sys/mman.h> #include <sys/time.h> #include <fcntl.h> +#include "vm_util.h" #include "../kselftest.h" /* @@ -82,6 +84,24 @@ static void validate_addr(char *ptr, int high_addr) ksft_exit_fail_msg("Bad address %lx\n", addr); } +static void mark_range(char *ptr, size_t size) +{ + if (prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, ptr, size, "virtual_address_range") == -1) { + if (errno == EINVAL) { + /* Depends on CONFIG_ANON_VMA_NAME */ + ksft_test_result_skip("prctl(PR_SET_VMA_ANON_NAME) not supported\n"); + ksft_finished(); + } else { + ksft_exit_fail_perror("prctl(PR_SET_VMA_ANON_NAME) failed\n"); + } + } +} + +static int is_marked_vma(const char *vma_name) +{ + return vma_name && !strcmp(vma_name, "[anon:virtual_address_range]\n"); +} + static int validate_lower_address_hint(void) { char *ptr; @@ -116,12 +136,17 @@ static int validate_complete_va_space(void) prev_end_addr = 0; while (fgets(line, sizeof(line), file)) { + const char *vma_name = NULL; + int vma_name_start = 0; unsigned long hop; - if (sscanf(line, "%lx-%lx %s[rwxp-]", - &start_addr, &end_addr, prot) != 3) + if (sscanf(line, "%lx-%lx %4s %*s %*s %*s %n", + &start_addr, &end_addr, prot, &vma_name_start) != 3) ksft_exit_fail_msg("cannot parse /proc/self/maps\n"); + if (vma_name_start) + vma_name = line + vma_name_start; + /* end of userspace mappings; ignore vsyscall mapping */ if (start_addr & (1UL << 63)) return 0; @@ -135,6 +160,9 @@ static int validate_complete_va_space(void) if (prot[0] != 'r') continue; + if (check_vmflag_io((void *)start_addr)) + continue; + /* * Confirm whether MAP_CHUNK_SIZE chunk can be found or not. * If write succeeds, no need to check MAP_CHUNK_SIZE - 1 @@ -149,6 +177,9 @@ static int validate_complete_va_space(void) return 1; lseek(fd, 0, SEEK_SET); + if (is_marked_vma(vma_name)) + munmap((char *)(start_addr + hop), MAP_CHUNK_SIZE); + hop += MAP_CHUNK_SIZE; } } @@ -166,7 +197,7 @@ int main(int argc, char *argv[]) ksft_set_plan(1); for (i = 0; i < NR_CHUNKS_LOW; i++) { - ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, + ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (ptr[i] == MAP_FAILED) { @@ -175,6 +206,7 @@ int main(int argc, char *argv[]) break; } + mark_range(ptr[i], MAP_CHUNK_SIZE); validate_addr(ptr[i], 0); } lchunks = i; @@ -186,12 +218,13 @@ int main(int argc, char *argv[]) for (i = 0; i < NR_CHUNKS_HIGH; i++) { hint = hint_addr(); - hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, + hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (hptr[i] == MAP_FAILED) break; + mark_range(ptr[i], MAP_CHUNK_SIZE); validate_addr(hptr[i], 1); } hchunks = i; diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index d8d0cf04bb57..a36734fb62f3 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -2,6 +2,7 @@ #include <string.h> #include <fcntl.h> #include <dirent.h> +#include <inttypes.h> #include <sys/ioctl.h> #include <linux/userfaultfd.h> #include <linux/fs.h> @@ -138,7 +139,7 @@ void clear_softdirty(void) ksft_exit_fail_msg("opening clear_refs failed\n"); ret = write(fd, ctrl, strlen(ctrl)); close(fd); - if (ret != strlen(ctrl)) + if (ret != (signed int)strlen(ctrl)) ksft_exit_fail_msg("writing clear_refs failed\n"); } @@ -193,13 +194,11 @@ err_out: return rss_anon; } -bool __check_huge(void *addr, char *pattern, int nr_hpages, - uint64_t hpage_size) +char *__get_smap_entry(void *addr, const char *pattern, char *buf, size_t len) { - uint64_t thp = -1; int ret; FILE *fp; - char buffer[MAX_LINE_LENGTH]; + char *entry = NULL; char addr_pattern[MAX_LINE_LENGTH]; ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", @@ -211,23 +210,40 @@ bool __check_huge(void *addr, char *pattern, int nr_hpages, if (!fp) ksft_exit_fail_msg("%s: Failed to open file %s\n", __func__, SMAP_FILE_PATH); - if (!check_for_pattern(fp, addr_pattern, buffer, sizeof(buffer))) + if (!check_for_pattern(fp, addr_pattern, buf, len)) goto err_out; - /* - * Fetch the pattern in the same block and check the number of - * hugepages. - */ - if (!check_for_pattern(fp, pattern, buffer, sizeof(buffer))) + /* Fetch the pattern in the same block */ + if (!check_for_pattern(fp, pattern, buf, len)) goto err_out; - snprintf(addr_pattern, MAX_LINE_LENGTH, "%s%%9ld kB", pattern); + /* Trim trailing newline */ + entry = strchr(buf, '\n'); + if (entry) + *entry = '\0'; - if (sscanf(buffer, addr_pattern, &thp) != 1) - ksft_exit_fail_msg("Reading smap error\n"); + entry = buf + strlen(pattern); err_out: fclose(fp); + return entry; +} + +bool __check_huge(void *addr, char *pattern, int nr_hpages, + uint64_t hpage_size) +{ + char buffer[MAX_LINE_LENGTH]; + uint64_t thp = -1; + char *entry; + + entry = __get_smap_entry(addr, pattern, buffer, sizeof(buffer)); + if (!entry) + goto err_out; + + if (sscanf(entry, "%9" SCNu64 " kB", &thp) != 1) + ksft_exit_fail_msg("Reading smap error\n"); + +err_out: return thp == (nr_hpages * (hpage_size >> 10)); } @@ -384,3 +400,27 @@ unsigned long get_free_hugepages(void) fclose(f); return fhp; } + +bool check_vmflag_io(void *addr) +{ + char buffer[MAX_LINE_LENGTH]; + const char *flags; + size_t flaglen; + + flags = __get_smap_entry(addr, "VmFlags:", buffer, sizeof(buffer)); + if (!flags) + ksft_exit_fail_msg("%s: No VmFlags for %p\n", __func__, addr); + + while (true) { + flags += strspn(flags, " "); + + flaglen = strcspn(flags, " "); + if (!flaglen) + return false; + + if (flaglen == strlen("io") && !memcmp(flags, "io", flaglen)) + return true; + + flags += flaglen; + } +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 2eaed8209925..b60ac68a9dc8 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -53,6 +53,7 @@ int uffd_unregister(int uffd, void *addr, uint64_t len); int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls); unsigned long get_free_hugepages(void); +bool check_vmflag_io(void *addr); /* * On ppc64 this will only work with radix 2M hugepage size diff --git a/tools/testing/selftests/mm/write_to_hugetlbfs.c b/tools/testing/selftests/mm/write_to_hugetlbfs.c index 1289d311efd7..34c91f7e6128 100644 --- a/tools/testing/selftests/mm/write_to_hugetlbfs.c +++ b/tools/testing/selftests/mm/write_to_hugetlbfs.c @@ -89,7 +89,7 @@ int main(int argc, char **argv) size = atoi(optarg); break; case 'p': - strncpy(path, optarg, sizeof(path)); + strncpy(path, optarg, sizeof(path) - 1); break; case 'm': if (atoi(optarg) >= MAX_METHOD) { diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c index 9bcf1736bf18..04ab45e27fb8 100644 --- a/tools/testing/vma/vma.c +++ b/tools/testing/vma/vma.c @@ -18,6 +18,12 @@ static bool fail_prealloc; #define vma_iter_prealloc(vmi, vma) \ (fail_prealloc ? -ENOMEM : mas_preallocate(&(vmi)->mas, (vma), GFP_KERNEL)) +#define CONFIG_DEFAULT_MMAP_MIN_ADDR 65536 + +unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; +unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; +unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; + /* * Directly import the VMA implementation here. Our vma_internal.h wrapper * provides userland-equivalent functionality for everything vma.c uses. @@ -47,6 +53,11 @@ struct task_struct *get_current(void) return &__current; } +unsigned long rlimit(unsigned int limit) +{ + return (unsigned long)-1; +} + /* Helper function to simply allocate a VMA. */ static struct vm_area_struct *alloc_vma(struct mm_struct *mm, unsigned long start, @@ -1563,6 +1574,57 @@ static bool test_expand_only_mode(void) return true; } +static bool test_mmap_region_basic(void) +{ + struct mm_struct mm = {}; + unsigned long addr; + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, &mm, 0); + + current->mm = &mm; + + /* Map at 0x300000, length 0x3000. */ + addr = __mmap_region(NULL, 0x300000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x300, NULL); + ASSERT_EQ(addr, 0x300000); + + /* Map at 0x250000, length 0x3000. */ + addr = __mmap_region(NULL, 0x250000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x250, NULL); + ASSERT_EQ(addr, 0x250000); + + /* Map at 0x303000, merging to 0x300000 of length 0x6000. */ + addr = __mmap_region(NULL, 0x303000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x303, NULL); + ASSERT_EQ(addr, 0x303000); + + /* Map at 0x24d000, merging to 0x250000 of length 0x6000. */ + addr = __mmap_region(NULL, 0x24d000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x24d, NULL); + ASSERT_EQ(addr, 0x24d000); + + ASSERT_EQ(mm.map_count, 2); + + for_each_vma(vmi, vma) { + if (vma->vm_start == 0x300000) { + ASSERT_EQ(vma->vm_end, 0x306000); + ASSERT_EQ(vma->vm_pgoff, 0x300); + } else if (vma->vm_start == 0x24d000) { + ASSERT_EQ(vma->vm_end, 0x253000); + ASSERT_EQ(vma->vm_pgoff, 0x24d); + } else { + ASSERT_FALSE(true); + } + } + + cleanup_mm(&mm, &vmi); + return true; +} + int main(void) { int num_tests = 0, num_fail = 0; @@ -1596,6 +1658,8 @@ int main(void) TEST(copy_vma); TEST(expand_only_mode); + TEST(mmap_region_basic); + #undef TEST printf("%d tests run, %d passed, %d failed.\n", diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index 1d9fc97b8e80..1eae23039854 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -27,11 +27,23 @@ #include <linux/rbtree.h> #include <linux/rwsem.h> +extern unsigned long stack_guard_gap; +#ifdef CONFIG_MMU +extern unsigned long mmap_min_addr; +extern unsigned long dac_mmap_min_addr; +#else +#define mmap_min_addr 0UL +#define dac_mmap_min_addr 0UL +#endif + #define VM_WARN_ON(_expr) (WARN_ON(_expr)) #define VM_WARN_ON_ONCE(_expr) (WARN_ON_ONCE(_expr)) +#define VM_WARN_ON_VMG(_expr, _vmg) (WARN_ON(_expr)) #define VM_BUG_ON(_expr) (BUG_ON(_expr)) #define VM_BUG_ON_VMA(_expr, _vma) (BUG_ON(_expr)) +#define MMF_HAS_MDWE 28 + #define VM_NONE 0x00000000 #define VM_READ 0x00000001 #define VM_WRITE 0x00000002 @@ -39,6 +51,7 @@ #define VM_SHARED 0x00000008 #define VM_MAYREAD 0x00000010 #define VM_MAYWRITE 0x00000020 +#define VM_MAYEXEC 0x00000040 #define VM_GROWSDOWN 0x00000100 #define VM_PFNMAP 0x00000400 #define VM_LOCKED 0x00002000 @@ -51,6 +64,8 @@ #define VM_STACK VM_GROWSDOWN #define VM_SHADOW_STACK VM_NONE #define VM_SOFTDIRTY 0 +#define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ +#define VM_GROWSUP VM_NONE #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) @@ -58,6 +73,20 @@ /* This mask represents all the VMA flag bits used by mlock */ #define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) +#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) + +#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) + +#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC + +#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK) + +#define RLIMIT_STACK 3 /* max stack size */ +#define RLIMIT_MEMLOCK 8 /* max locked-in-memory address space */ + +#define CAP_IPC_LOCK 14 + #ifdef CONFIG_64BIT /* VM is sealed, in vm_flags */ #define VM_SEALED _BITUL(63) @@ -122,10 +151,22 @@ enum { TASK_COMM_LEN = 16, }; +/* + * Flags for bug emulation. + * + * These occupy the top three bytes. + */ +enum { + READ_IMPLIES_EXEC = 0x0400000, +}; + struct task_struct { char comm[TASK_COMM_LEN]; pid_t pid; struct mm_struct *mm; + + /* Used for emulating ABI behavior of previous Linux versions: */ + unsigned int personality; }; struct task_struct *get_current(void); @@ -186,6 +227,10 @@ struct mm_struct { unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ unsigned long stack_vm; /* VM_STACK */ + + unsigned long def_flags; + + unsigned long flags; /* Must use atomic bitops to access */ }; struct vma_lock { @@ -373,6 +418,17 @@ struct vm_operations_struct { unsigned long addr); }; +struct vm_unmapped_area_info { +#define VM_UNMAPPED_AREA_TOPDOWN 1 + unsigned long flags; + unsigned long length; + unsigned long low_limit; + unsigned long high_limit; + unsigned long align_mask; + unsigned long align_offset; + unsigned long start_gap; +}; + static inline void vma_iter_invalidate(struct vma_iterator *vmi) { mas_pause(&vmi->mas); @@ -432,6 +488,8 @@ static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) extern const struct vm_operations_struct vma_dummy_vm_ops; +extern unsigned long rlimit(unsigned int limit); + static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { memset(vma, 0, sizeof(*vma)); @@ -853,6 +911,11 @@ static inline void mmap_write_unlock(struct mm_struct *) { } +static inline int mmap_write_lock_killable(struct mm_struct *) +{ + return 0; +} + static inline bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end) @@ -938,7 +1001,7 @@ static inline bool is_file_hugepages(struct file *) static inline int security_vm_enough_memory_mm(struct mm_struct *, long) { - return true; + return 0; } static inline bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long) @@ -1033,4 +1096,159 @@ static inline int mmap_file(struct file *, struct vm_area_struct *) return 0; } +static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_GROWSDOWN) + return stack_guard_gap; + + /* See reasoning around the VM_SHADOW_STACK definition */ + if (vma->vm_flags & VM_SHADOW_STACK) + return PAGE_SIZE; + + return 0; +} + +static inline unsigned long vm_start_gap(struct vm_area_struct *vma) +{ + unsigned long gap = stack_guard_start_gap(vma); + unsigned long vm_start = vma->vm_start; + + vm_start -= gap; + if (vm_start > vma->vm_start) + vm_start = 0; + return vm_start; +} + +static inline unsigned long vm_end_gap(struct vm_area_struct *vma) +{ + unsigned long vm_end = vma->vm_end; + + if (vma->vm_flags & VM_GROWSUP) { + vm_end += stack_guard_gap; + if (vm_end < vma->vm_end) + vm_end = -PAGE_SIZE; + } + return vm_end; +} + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} + +static inline bool vma_is_accessible(struct vm_area_struct *vma) +{ + return vma->vm_flags & VM_ACCESS_FLAGS; +} + +static inline bool capable(int cap) +{ + return true; +} + +static inline bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, + unsigned long bytes) +{ + unsigned long locked_pages, limit_pages; + + if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK)) + return true; + + locked_pages = bytes >> PAGE_SHIFT; + locked_pages += mm->locked_vm; + + limit_pages = rlimit(RLIMIT_MEMLOCK); + limit_pages >>= PAGE_SHIFT; + + return locked_pages <= limit_pages; +} + +static inline int __anon_vma_prepare(struct vm_area_struct *vma) +{ + struct anon_vma *anon_vma = calloc(1, sizeof(struct anon_vma)); + + if (!anon_vma) + return -ENOMEM; + + anon_vma->root = anon_vma; + vma->anon_vma = anon_vma; + + return 0; +} + +static inline int anon_vma_prepare(struct vm_area_struct *vma) +{ + if (likely(vma->anon_vma)) + return 0; + + return __anon_vma_prepare(vma); +} + +static inline void userfaultfd_unmap_complete(struct mm_struct *mm, + struct list_head *uf) +{ +} + +/* + * Denies creating a writable executable mapping or gaining executable permissions. + * + * This denies the following: + * + * a) mmap(PROT_WRITE | PROT_EXEC) + * + * b) mmap(PROT_WRITE) + * mprotect(PROT_EXEC) + * + * c) mmap(PROT_WRITE) + * mprotect(PROT_READ) + * mprotect(PROT_EXEC) + * + * But allows the following: + * + * d) mmap(PROT_READ | PROT_EXEC) + * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. + */ +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) +{ + /* If MDWE is disabled, we have nothing to deny. */ + if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + return false; + + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) + return true; + + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) + return true; + + return false; +} + +static inline int mapping_map_writable(struct address_space *mapping) +{ + int c = atomic_read(&mapping->i_mmap_writable); + + /* Derived from the raw_atomic_inc_unless_negative() implementation. */ + do { + if (c < 0) + return -EPERM; + } while (!__sync_bool_compare_and_swap(&mapping->i_mmap_writable, c, c+1)); + + return 0; +} + #endif /* __MM_VMA_INTERNAL_H */ |