diff options
Diffstat (limited to 'tools/testing/selftests/mm')
79 files changed, 19308 insertions, 3046 deletions
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 7e2a982383c0..c2a8586e51a1 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -5,6 +5,8 @@ hugepage-mremap hugepage-shm hugepage-vmemmap hugetlb-madvise +hugetlb-read-hwpoison +hugetlb-soft-offline khugepaged map_hugetlb map_populate @@ -17,12 +19,17 @@ mremap_dontunmap mremap_test on-fault-limit transhuge-stress +pagemap_ioctl +pfnmap +process_madv +*.tmp* protection_keys protection_keys_32 protection_keys_64 madv_populate uffd-stress uffd-unit-tests +uffd-wp-mremap mlock-intersect-test mlock-random-test virtual_address_range @@ -42,3 +49,14 @@ mdwe_test gup_longterm mkdirty va_high_addr_switch +hugetlb_fault_after_madv +hugetlb_madv_vs_map +mseal_test +droppable +hugetlb_dio +pkey_sighandler_tests_32 +pkey_sighandler_tests_64 +guard-regions +merge +prctl_thp_disable +rmap diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 66d7c07dc177..eaf9312097f7 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -2,6 +2,7 @@ # Makefile for mm selftests LOCAL_HDRS += $(selfdir)/mm/local_config.h $(top_srcdir)/mm/gup_test.h +LOCAL_HDRS += $(selfdir)/mm/mseal_helpers.h include local_config.mk @@ -12,7 +13,7 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) else uname_M := $(shell echo $(CROSS_COMPILE) | grep -o '^[a-z0-9]\+') endif -ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/powerpc/') endif # Without this, failed build products remain, with up-to-date timestamps, @@ -32,42 +33,81 @@ endif # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) -LDLIBS = -lrt -lpthread - -TEST_GEN_PROGS = cow -TEST_GEN_PROGS += compaction_test -TEST_GEN_PROGS += gup_longterm -TEST_GEN_PROGS += gup_test -TEST_GEN_PROGS += hmm-tests -TEST_GEN_PROGS += hugetlb-madvise -TEST_GEN_PROGS += hugepage-mmap -TEST_GEN_PROGS += hugepage-mremap -TEST_GEN_PROGS += hugepage-shm -TEST_GEN_PROGS += hugepage-vmemmap -TEST_GEN_PROGS += khugepaged -TEST_GEN_PROGS += madv_populate -TEST_GEN_PROGS += map_fixed_noreplace -TEST_GEN_PROGS += map_hugetlb -TEST_GEN_PROGS += map_populate -TEST_GEN_PROGS += memfd_secret -TEST_GEN_PROGS += migration -TEST_GEN_PROGS += mkdirty -TEST_GEN_PROGS += mlock-random-test -TEST_GEN_PROGS += mlock2-tests -TEST_GEN_PROGS += mrelease_test -TEST_GEN_PROGS += mremap_dontunmap -TEST_GEN_PROGS += mremap_test -TEST_GEN_PROGS += on-fault-limit -TEST_GEN_PROGS += thuge-gen -TEST_GEN_PROGS += transhuge-stress -TEST_GEN_PROGS += uffd-stress -TEST_GEN_PROGS += uffd-unit-tests -TEST_GEN_PROGS += soft-dirty -TEST_GEN_PROGS += split_huge_page_test -TEST_GEN_PROGS += ksm_tests -TEST_GEN_PROGS += ksm_functional_tests -TEST_GEN_PROGS += mdwe_test +CFLAGS = -Wall -O2 -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +CFLAGS += -Wunreachable-code +LDLIBS = -lrt -lpthread -lm + +# Some distributions (such as Ubuntu) configure GCC so that _FORTIFY_SOURCE is +# automatically enabled at -O1 or above. This triggers various unused-result +# warnings where functions such as read() or write() are called and their +# return value is not checked. Disable _FORTIFY_SOURCE to silence those +# warnings. +CFLAGS += -U_FORTIFY_SOURCE + +KDIR ?= /lib/modules/$(shell uname -r)/build +ifneq (,$(wildcard $(KDIR)/Module.symvers)) +ifneq (,$(wildcard $(KDIR)/include/linux/page_frag_cache.h)) +TEST_GEN_MODS_DIR := page_frag +else +PAGE_FRAG_WARNING = "missing page_frag_cache.h, please use a newer kernel" +endif +else +PAGE_FRAG_WARNING = "missing Module.symvers, please have the kernel built first" +endif + +TEST_GEN_FILES = cow +TEST_GEN_FILES += compaction_test +TEST_GEN_FILES += gup_longterm +TEST_GEN_FILES += gup_test +TEST_GEN_FILES += hmm-tests +TEST_GEN_FILES += hugetlb-madvise +TEST_GEN_FILES += hugetlb-read-hwpoison +TEST_GEN_FILES += hugetlb-soft-offline +TEST_GEN_FILES += hugepage-mmap +TEST_GEN_FILES += hugepage-mremap +TEST_GEN_FILES += hugepage-shm +TEST_GEN_FILES += hugepage-vmemmap +TEST_GEN_FILES += khugepaged +TEST_GEN_FILES += madv_populate +TEST_GEN_FILES += map_fixed_noreplace +TEST_GEN_FILES += map_hugetlb +TEST_GEN_FILES += map_populate +ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64)) +TEST_GEN_FILES += memfd_secret +endif +TEST_GEN_FILES += migration +TEST_GEN_FILES += mkdirty +TEST_GEN_FILES += mlock-random-test +TEST_GEN_FILES += mlock2-tests +TEST_GEN_FILES += mrelease_test +TEST_GEN_FILES += mremap_dontunmap +TEST_GEN_FILES += mremap_test +TEST_GEN_FILES += mseal_test +TEST_GEN_FILES += on-fault-limit +TEST_GEN_FILES += pagemap_ioctl +TEST_GEN_FILES += pfnmap +TEST_GEN_FILES += process_madv +TEST_GEN_FILES += prctl_thp_disable +TEST_GEN_FILES += thuge-gen +TEST_GEN_FILES += transhuge-stress +TEST_GEN_FILES += uffd-stress +TEST_GEN_FILES += uffd-unit-tests +TEST_GEN_FILES += uffd-wp-mremap +TEST_GEN_FILES += split_huge_page_test +TEST_GEN_FILES += ksm_tests +TEST_GEN_FILES += ksm_functional_tests +TEST_GEN_FILES += mdwe_test +TEST_GEN_FILES += hugetlb_fault_after_madv +TEST_GEN_FILES += hugetlb_madv_vs_map +TEST_GEN_FILES += hugetlb_dio +TEST_GEN_FILES += droppable +TEST_GEN_FILES += guard-regions +TEST_GEN_FILES += merge +TEST_GEN_FILES += rmap + +ifneq ($(ARCH),arm64) +TEST_GEN_FILES += soft-dirty +endif ifeq ($(ARCH),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) @@ -75,6 +115,7 @@ CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_pr CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) VMTARGETS := protection_keys +VMTARGETS += pkey_sighandler_tests BINARIES_32 := $(VMTARGETS:%=%_32) BINARIES_64 := $(VMTARGETS:%=%_64) @@ -83,24 +124,26 @@ CFLAGS += -no-pie endif ifeq ($(CAN_BUILD_I386),1) -TEST_GEN_PROGS += $(BINARIES_32) +TEST_GEN_FILES += $(BINARIES_32) endif ifeq ($(CAN_BUILD_X86_64),1) -TEST_GEN_PROGS += $(BINARIES_64) +TEST_GEN_FILES += $(BINARIES_64) endif -else -ifneq (,$(findstring $(ARCH),ppc64)) -TEST_GEN_PROGS += protection_keys +else ifeq ($(ARCH),arm64) +TEST_GEN_FILES += protection_keys +TEST_GEN_FILES += pkey_sighandler_tests +else ifeq ($(ARCH),powerpc) +TEST_GEN_FILES += protection_keys endif +ifneq (,$(filter $(ARCH),arm64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64 s390)) +TEST_GEN_FILES += va_high_addr_switch +ifneq ($(ARCH),riscv64) +TEST_GEN_FILES += virtual_address_range endif - -ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) -TEST_GEN_PROGS += va_high_addr_switch -TEST_GEN_PROGS += virtual_address_range -TEST_GEN_PROGS += write_to_hugetlbfs +TEST_GEN_FILES += write_to_hugetlbfs endif TEST_PROGS := run_vmtests.sh @@ -108,18 +151,30 @@ TEST_PROGS := run_vmtests.sh TEST_FILES := test_vmalloc.sh TEST_FILES += test_hmm.sh TEST_FILES += va_high_addr_switch.sh +TEST_FILES += charge_reserved_hugetlb.sh +TEST_FILES += hugetlb_reparenting_test.sh +TEST_FILES += test_page_frag.sh + +# required by charge_reserved_hugetlb.sh +TEST_FILES += write_hugetlb_memory.sh include ../lib.mk -$(TEST_GEN_PROGS): vm_util.c +$(TEST_GEN_PROGS): vm_util.c thp_settings.c +$(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 @@ -176,6 +231,8 @@ $(OUTPUT)/ksm_tests: LDLIBS += -lnuma $(OUTPUT)/migration: LDLIBS += -lnuma +$(OUTPUT)/rmap: LDLIBS += -lnuma + local_config.mk local_config.h: check_config.sh /bin/sh ./check_config.sh $(CC) @@ -189,3 +246,12 @@ warn_missing_liburing: echo "Warning: missing liburing support. Some tests will be skipped." ; \ echo endif + +ifneq ($(PAGE_FRAG_WARNING),) +all: warn_missing_page_frag + +warn_missing_page_frag: + @echo ; \ + echo "Warning: $(PAGE_FRAG_WARNING). page_frag test will be skipped." ; \ + echo +endif diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh index a5cb4b09a46c..e1fe16bcbbe8 100755 --- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Kselftest framework requirement - SKIP code is 4. @@ -11,6 +11,8 @@ if [[ $(id -u) -ne 0 ]]; then exit $ksft_skip fi +nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) + fault_limit_file=limit_in_bytes reservation_limit_file=rsvd.limit_in_bytes fault_usage_file=usage_in_bytes @@ -25,17 +27,17 @@ if [[ "$1" == "-cgroup-v2" ]]; then fi if [[ $cgroup2 ]]; then - cgroup_path=$(mount -t cgroup2 | head -1 | awk -e '{print $3}') + cgroup_path=$(mount -t cgroup2 | head -1 | awk '{print $3}') if [[ -z "$cgroup_path" ]]; then - cgroup_path=/dev/cgroup/memory + cgroup_path=$(mktemp -d) mount -t cgroup2 none $cgroup_path do_umount=1 fi echo "+hugetlb" >$cgroup_path/cgroup.subtree_control else - cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}') + cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}') if [[ -z "$cgroup_path" ]]; then - cgroup_path=/dev/cgroup/memory + cgroup_path=$(mktemp -d) mount -t cgroup memory,hugetlb $cgroup_path do_umount=1 fi @@ -252,7 +254,7 @@ function cleanup_hugetlb_memory() { local cgroup="$1" if [[ "$(pgrep -f write_to_hugetlbfs)" != "" ]]; then echo killing write_to_hugetlbfs - killall -2 write_to_hugetlbfs + killall -2 --wait write_to_hugetlbfs wait_for_hugetlb_memory_to_get_depleted $cgroup fi set -e @@ -582,3 +584,5 @@ if [[ $do_umount ]]; then umount $cgroup_path rmdir $cgroup_path fi + +echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 9b420140ba2b..30209c40b697 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -16,7 +16,7 @@ #include <unistd.h> #include <string.h> -#include "../kselftest.h" +#include "kselftest.h" #define MAP_SIZE_MB 100 #define MAP_SIZE (MAP_SIZE_MB * 1024 * 1024) @@ -33,7 +33,7 @@ int read_memory_info(unsigned long *memfree, unsigned long *hugepagesize) FILE *cmdfile = popen(cmd, "r"); if (!(fgets(buffer, sizeof(buffer), cmdfile))) { - perror("Failed to read meminfo\n"); + ksft_print_msg("Failed to read meminfo: %s\n", strerror(errno)); return -1; } @@ -44,7 +44,7 @@ int read_memory_info(unsigned long *memfree, unsigned long *hugepagesize) cmdfile = popen(cmd, "r"); if (!(fgets(buffer, sizeof(buffer), cmdfile))) { - perror("Failed to read meminfo\n"); + ksft_print_msg("Failed to read meminfo: %s\n", strerror(errno)); return -1; } @@ -62,14 +62,14 @@ int prereq(void) fd = open("/proc/sys/vm/compact_unevictable_allowed", O_RDONLY | O_NONBLOCK); if (fd < 0) { - perror("Failed to open\n" - "/proc/sys/vm/compact_unevictable_allowed\n"); + ksft_print_msg("Failed to open /proc/sys/vm/compact_unevictable_allowed: %s\n", + strerror(errno)); return -1; } if (read(fd, &allowed, sizeof(char)) != sizeof(char)) { - perror("Failed to read from\n" - "/proc/sys/vm/compact_unevictable_allowed\n"); + ksft_print_msg("Failed to read from /proc/sys/vm/compact_unevictable_allowed: %s\n", + strerror(errno)); close(fd); return -1; } @@ -78,15 +78,23 @@ int prereq(void) if (allowed == '1') return 0; + ksft_print_msg("Compaction isn't allowed\n"); return -1; } -int check_compaction(unsigned long mem_free, unsigned int hugepage_size) +int check_compaction(unsigned long mem_free, unsigned long hugepage_size, + unsigned long initial_nr_hugepages) { - int fd; + unsigned long nr_hugepages_ul; + int fd, ret = -1; int compaction_index = 0; - char initial_nr_hugepages[10] = {0}; - char nr_hugepages[10] = {0}; + char nr_hugepages[20] = {0}; + char init_nr_hugepages[24] = {0}; + char target_nr_hugepages[24] = {0}; + int slen; + + snprintf(init_nr_hugepages, sizeof(init_nr_hugepages), + "%lu", initial_nr_hugepages); /* We want to test with 80% of available memory. Else, OOM killer comes in to play */ @@ -94,102 +102,138 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); if (fd < 0) { - perror("Failed to open /proc/sys/vm/nr_hugepages"); - return -1; + ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + ret = -1; + goto out; } - if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) { - perror("Failed to read from /proc/sys/vm/nr_hugepages"); + /* + * Request huge pages for about half of the free memory. The Kernel + * will allocate as much as it can, and we expect it will get at least 1/3 + */ + nr_hugepages_ul = mem_free / hugepage_size / 2; + snprintf(target_nr_hugepages, sizeof(target_nr_hugepages), + "%lu", nr_hugepages_ul); + + slen = strlen(target_nr_hugepages); + if (write(fd, target_nr_hugepages, slen) != slen) { + ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n", + nr_hugepages_ul, strerror(errno)); goto close_fd; } - /* Start with the initial condition of 0 huge pages*/ - if (write(fd, "0", sizeof(char)) != sizeof(char)) { - perror("Failed to write 0 to /proc/sys/vm/nr_hugepages\n"); + lseek(fd, 0, SEEK_SET); + + if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { + ksft_print_msg("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); goto close_fd; } - lseek(fd, 0, SEEK_SET); - - /* Request a large number of huge pages. The Kernel will allocate - as much as it can */ - if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - perror("Failed to write 100000 to /proc/sys/vm/nr_hugepages\n"); + /* We should have been able to request at least 1/3 rd of the memory in + huge pages */ + nr_hugepages_ul = strtoul(nr_hugepages, NULL, 10); + if (!nr_hugepages_ul) { + ksft_print_msg("ERROR: No memory is available as huge pages\n"); goto close_fd; } + compaction_index = mem_free/(nr_hugepages_ul * hugepage_size); lseek(fd, 0, SEEK_SET); - if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - perror("Failed to re-read from /proc/sys/vm/nr_hugepages\n"); + if (write(fd, init_nr_hugepages, strlen(init_nr_hugepages)) + != strlen(init_nr_hugepages)) { + ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); goto close_fd; } - /* We should have been able to request at least 1/3 rd of the memory in - huge pages */ - compaction_index = mem_free/(atoi(nr_hugepages) * hugepage_size); + ksft_print_msg("Number of huge pages allocated = %lu\n", + nr_hugepages_ul); if (compaction_index > 3) { - printf("No of huge pages allocated = %d\n", - (atoi(nr_hugepages))); - fprintf(stderr, "ERROR: Less that 1/%d of memory is available\n" - "as huge pages\n", compaction_index); + ksft_print_msg("ERROR: Less than 1/%d of memory is available\n" + "as huge pages\n", compaction_index); goto close_fd; } - printf("No of huge pages allocated = %d\n", - (atoi(nr_hugepages))); + ret = 0; + + close_fd: + close(fd); + out: + ksft_test_result(ret == 0, "check_compaction\n"); + return ret; +} + +int set_zero_hugepages(unsigned long *initial_nr_hugepages) +{ + int fd, ret = -1; + char nr_hugepages[20] = {0}; + + fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + if (fd < 0) { + ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto out; + } + if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { + ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto close_fd; + } lseek(fd, 0, SEEK_SET); - if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages)) - != strlen(initial_nr_hugepages)) { - perror("Failed to write value to /proc/sys/vm/nr_hugepages\n"); + /* Start with the initial condition of 0 huge pages */ + if (write(fd, "0", sizeof(char)) != sizeof(char)) { + ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); goto close_fd; } - close(fd); - return 0; + *initial_nr_hugepages = strtoul(nr_hugepages, NULL, 10); + ret = 0; close_fd: close(fd); - printf("Not OK. Compaction test failed."); - return -1; -} + out: + return ret; +} int main(int argc, char **argv) { struct rlimit lim; - struct map_list *list, *entry; + struct map_list *list = NULL, *entry; size_t page_size, i; void *map = NULL; unsigned long mem_free = 0; unsigned long hugepage_size = 0; long mem_fragmentable_MB = 0; + unsigned long initial_nr_hugepages; - if (prereq() != 0) { - printf("Either the sysctl compact_unevictable_allowed is not\n" - "set to 1 or couldn't read the proc file.\n" - "Skipping the test\n"); - return KSFT_SKIP; - } + ksft_print_header(); + + if (prereq() || geteuid()) + ksft_exit_skip("Prerequisites unsatisfied\n"); + + ksft_set_plan(1); + + /* Start the test without hugepages reducing mem_free */ + if (set_zero_hugepages(&initial_nr_hugepages)) + ksft_exit_fail(); lim.rlim_cur = RLIM_INFINITY; lim.rlim_max = RLIM_INFINITY; - if (setrlimit(RLIMIT_MEMLOCK, &lim)) { - perror("Failed to set rlimit:\n"); - return -1; - } + if (setrlimit(RLIMIT_MEMLOCK, &lim)) + ksft_exit_fail_msg("Failed to set rlimit: %s\n", strerror(errno)); page_size = getpagesize(); - list = NULL; - - if (read_memory_info(&mem_free, &hugepage_size) != 0) { - printf("ERROR: Cannot read meminfo\n"); - return -1; - } + if (read_memory_info(&mem_free, &hugepage_size) != 0) + ksft_exit_fail_msg("Failed to get meminfo\n"); mem_fragmentable_MB = mem_free * 0.8 / 1024; @@ -224,8 +268,9 @@ int main(int argc, char **argv) entry = entry->next; } - if (check_compaction(mem_free, hugepage_size) == 0) - return 0; + if (check_compaction(mem_free, hugepage_size, + initial_nr_hugepages) == 0) + ksft_exit_pass(); - return -1; + ksft_exit_fail(); } diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config index be087c4bc396..deba93379c80 100644 --- a/tools/testing/selftests/mm/config +++ b/tools/testing/selftests/mm/config @@ -1,8 +1,13 @@ CONFIG_SYSVIPC=y CONFIG_USERFAULTFD=y +CONFIG_PTE_MARKER_UFFD_WP=y CONFIG_TEST_VMALLOC=m CONFIG_DEVICE_PRIVATE=y CONFIG_TEST_HMM=m CONFIG_GUP_TEST=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_MEM_SOFT_DIRTY=y +CONFIG_ANON_VMA_NAME=y +CONFIG_FTRACE=y +CONFIG_PROFILING=y +CONFIG_UPROBES=y diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 7324ce5363c0..accfd198dbda 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -27,40 +27,44 @@ #endif /* LOCAL_CONFIG_HAVE_LIBURING */ #include "../../../../mm/gup_test.h" -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" +#include "thp_settings.h" static size_t pagesize; static int pagemap_fd; -static size_t thpsize; +static size_t pmdsize; +static int nr_thpsizes; +static size_t thpsizes[20]; static int nr_hugetlbsizes; static size_t hugetlbsizes[10]; static int gup_fd; static bool has_huge_zeropage; -static void detect_huge_zeropage(void) +static int detect_thp_sizes(size_t sizes[], int max) { - int fd = open("/sys/kernel/mm/transparent_hugepage/use_zero_page", - O_RDONLY); - size_t enabled = 0; - char buf[15]; - int ret; + int count = 0; + unsigned long orders; + size_t kb; + int i; - if (fd < 0) - return; + /* thp not supported at all. */ + if (!pmdsize) + return 0; - ret = pread(fd, buf, sizeof(buf), 0); - if (ret > 0 && ret < sizeof(buf)) { - buf[ret] = 0; + orders = 1UL << sz2ord(pmdsize, pagesize); + orders |= thp_supported_orders(); - enabled = strtoul(buf, NULL, 10); - if (enabled == 1) { - has_huge_zeropage = true; - ksft_print_msg("[INFO] huge zeropage is enabled\n"); - } + 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); } - close(fd); + return count; } static bool range_is_swapped(void *addr, size_t size) @@ -78,9 +82,12 @@ struct comm_pipes { static int setup_comm_pipes(struct comm_pipes *comm_pipes) { - if (pipe(comm_pipes->child_ready) < 0) + if (pipe(comm_pipes->child_ready) < 0) { + ksft_perror("pipe() failed"); return -errno; + } if (pipe(comm_pipes->parent_ready) < 0) { + ksft_perror("pipe() failed"); close(comm_pipes->child_ready[0]); close(comm_pipes->child_ready[1]); return -errno; @@ -165,7 +172,7 @@ static int child_vmsplice_memcmp_fn(char *mem, size_t size, typedef int (*child_fn)(char *mem, size_t size, struct comm_pipes *comm_pipes); static void do_test_cow_in_parent(char *mem, size_t size, bool do_mprotect, - child_fn fn) + child_fn fn, bool xfail) { struct comm_pipes comm_pipes; char buf; @@ -173,13 +180,14 @@ static void do_test_cow_in_parent(char *mem, size_t size, bool do_mprotect, ret = setup_comm_pipes(&comm_pipes); if (ret) { - ksft_test_result_fail("pipe() failed\n"); + log_test_result(KSFT_FAIL); return; } ret = fork(); if (ret < 0) { - ksft_test_result_fail("fork() failed\n"); + ksft_perror("fork() failed"); + log_test_result(KSFT_FAIL); goto close_comm_pipes; } else if (!ret) { exit(fn(mem, size, &comm_pipes)); @@ -194,9 +202,18 @@ static void do_test_cow_in_parent(char *mem, size_t size, bool do_mprotect, * write-faults by directly mapping pages writable. */ ret = mprotect(mem, size, PROT_READ); - ret |= mprotect(mem, size, PROT_READ|PROT_WRITE); if (ret) { - ksft_test_result_fail("mprotect() failed\n"); + ksft_perror("mprotect() failed"); + log_test_result(KSFT_FAIL); + write(comm_pipes.parent_ready[1], "0", 1); + wait(&ret); + goto close_comm_pipes; + } + + ret = mprotect(mem, size, PROT_READ|PROT_WRITE); + if (ret) { + ksft_perror("mprotect() failed"); + log_test_result(KSFT_FAIL); write(comm_pipes.parent_ready[1], "0", 1); wait(&ret); goto close_comm_pipes; @@ -213,39 +230,55 @@ static void do_test_cow_in_parent(char *mem, size_t size, bool do_mprotect, else ret = -EINVAL; - ksft_test_result(!ret, "No leak from parent into child\n"); + if (!ret) { + log_test_result(KSFT_PASS); + } else if (xfail) { + /* + * With hugetlb, some vmsplice() tests are currently expected to + * fail because (a) harder to fix and (b) nobody really cares. + * Flag them as expected failure for now. + */ + ksft_print_msg("Leak from parent into child\n"); + log_test_result(KSFT_XFAIL); + } else { + ksft_print_msg("Leak from parent into child\n"); + log_test_result(KSFT_FAIL); + } close_comm_pipes: close_comm_pipes(&comm_pipes); } -static void test_cow_in_parent(char *mem, size_t size) +static void test_cow_in_parent(char *mem, size_t size, bool is_hugetlb) { - do_test_cow_in_parent(mem, size, false, child_memcmp_fn); + do_test_cow_in_parent(mem, size, false, child_memcmp_fn, false); } -static void test_cow_in_parent_mprotect(char *mem, size_t size) +static void test_cow_in_parent_mprotect(char *mem, size_t size, bool is_hugetlb) { - do_test_cow_in_parent(mem, size, true, child_memcmp_fn); + do_test_cow_in_parent(mem, size, true, child_memcmp_fn, false); } -static void test_vmsplice_in_child(char *mem, size_t size) +static void test_vmsplice_in_child(char *mem, size_t size, bool is_hugetlb) { - do_test_cow_in_parent(mem, size, false, child_vmsplice_memcmp_fn); + do_test_cow_in_parent(mem, size, false, child_vmsplice_memcmp_fn, + is_hugetlb); } -static void test_vmsplice_in_child_mprotect(char *mem, size_t size) +static void test_vmsplice_in_child_mprotect(char *mem, size_t size, + bool is_hugetlb) { - do_test_cow_in_parent(mem, size, true, child_vmsplice_memcmp_fn); + do_test_cow_in_parent(mem, size, true, child_vmsplice_memcmp_fn, + is_hugetlb); } static void do_test_vmsplice_in_parent(char *mem, size_t size, - bool before_fork) + bool before_fork, bool xfail) { struct iovec iov = { .iov_base = mem, .iov_len = size, }; - ssize_t cur, total, transferred; + ssize_t cur, total, transferred = 0; struct comm_pipes comm_pipes; char *old, *new; int ret, fds[2]; @@ -258,26 +291,29 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size, ret = setup_comm_pipes(&comm_pipes); if (ret) { - ksft_test_result_fail("pipe() failed\n"); + log_test_result(KSFT_FAIL); goto free; } if (pipe(fds) < 0) { - ksft_test_result_fail("pipe() failed\n"); + ksft_perror("pipe() failed"); + log_test_result(KSFT_FAIL); goto close_comm_pipes; } if (before_fork) { transferred = vmsplice(fds[1], &iov, 1, 0); if (transferred <= 0) { - ksft_test_result_fail("vmsplice() failed\n"); + ksft_perror("vmsplice() failed\n"); + log_test_result(KSFT_FAIL); goto close_pipe; } } ret = fork(); if (ret < 0) { - ksft_test_result_fail("fork() failed\n"); + ksft_perror("fork() failed\n"); + log_test_result(KSFT_FAIL); goto close_pipe; } else if (!ret) { write(comm_pipes.child_ready[1], "0", 1); @@ -291,7 +327,8 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size, if (!before_fork) { transferred = vmsplice(fds[1], &iov, 1, 0); if (transferred <= 0) { - ksft_test_result_fail("vmsplice() failed\n"); + ksft_perror("vmsplice() failed"); + log_test_result(KSFT_FAIL); wait(&ret); goto close_pipe; } @@ -300,7 +337,8 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size, while (read(comm_pipes.child_ready[0], &buf, 1) != 1) ; if (munmap(mem, size) < 0) { - ksft_test_result_fail("munmap() failed\n"); + ksft_perror("munmap() failed"); + log_test_result(KSFT_FAIL); goto close_pipe; } write(comm_pipes.parent_ready[1], "0", 1); @@ -308,7 +346,8 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size, /* Wait until the child is done writing. */ wait(&ret); if (!WIFEXITED(ret)) { - ksft_test_result_fail("wait() failed\n"); + ksft_perror("wait() failed"); + log_test_result(KSFT_FAIL); goto close_pipe; } @@ -316,13 +355,26 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size, for (total = 0; total < transferred; total += cur) { cur = read(fds[0], new + total, transferred - total); if (cur < 0) { - ksft_test_result_fail("read() failed\n"); + ksft_perror("read() failed"); + log_test_result(KSFT_FAIL); goto close_pipe; } } - ksft_test_result(!memcmp(old, new, transferred), - "No leak from child into parent\n"); + if (!memcmp(old, new, transferred)) { + log_test_result(KSFT_PASS); + } else if (xfail) { + /* + * With hugetlb, some vmsplice() tests are currently expected to + * fail because (a) harder to fix and (b) nobody really cares. + * Flag them as expected failure for now. + */ + ksft_print_msg("Leak from child into parent\n"); + log_test_result(KSFT_XFAIL); + } else { + ksft_print_msg("Leak from child into parent\n"); + log_test_result(KSFT_FAIL); + } close_pipe: close(fds[0]); close(fds[1]); @@ -333,14 +385,14 @@ free: free(new); } -static void test_vmsplice_before_fork(char *mem, size_t size) +static void test_vmsplice_before_fork(char *mem, size_t size, bool is_hugetlb) { - do_test_vmsplice_in_parent(mem, size, true); + do_test_vmsplice_in_parent(mem, size, true, is_hugetlb); } -static void test_vmsplice_after_fork(char *mem, size_t size) +static void test_vmsplice_after_fork(char *mem, size_t size, bool is_hugetlb) { - do_test_vmsplice_in_parent(mem, size, false); + do_test_vmsplice_in_parent(mem, size, false, is_hugetlb); } #ifdef LOCAL_CONFIG_HAVE_LIBURING @@ -358,13 +410,14 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork) ret = setup_comm_pipes(&comm_pipes); if (ret) { - ksft_test_result_fail("pipe() failed\n"); + log_test_result(KSFT_FAIL); return; } file = tmpfile(); if (!file) { - ksft_test_result_fail("tmpfile() failed\n"); + ksft_perror("tmpfile() failed"); + log_test_result(KSFT_FAIL); goto close_comm_pipes; } fd = fileno(file); @@ -372,14 +425,16 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork) tmp = malloc(size); if (!tmp) { - ksft_test_result_fail("malloc() failed\n"); + ksft_print_msg("malloc() failed\n"); + log_test_result(KSFT_FAIL); goto close_file; } /* Skip on errors, as we might just lack kernel support. */ ret = io_uring_queue_init(1, &ring, 0); if (ret < 0) { - ksft_test_result_skip("io_uring_queue_init() failed\n"); + ksft_print_msg("io_uring_queue_init() failed\n"); + log_test_result(KSFT_SKIP); goto free_tmp; } @@ -394,7 +449,8 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork) iov.iov_len = size; ret = io_uring_register_buffers(&ring, &iov, 1); if (ret) { - ksft_test_result_skip("io_uring_register_buffers() failed\n"); + ksft_print_msg("io_uring_register_buffers() failed\n"); + log_test_result(KSFT_SKIP); goto queue_exit; } @@ -405,7 +461,8 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork) */ ret = fork(); if (ret < 0) { - ksft_test_result_fail("fork() failed\n"); + ksft_perror("fork() failed"); + log_test_result(KSFT_FAIL); goto unregister_buffers; } else if (!ret) { write(comm_pipes.child_ready[1], "0", 1); @@ -425,10 +482,17 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork) * if the page is mapped R/O vs. R/W). */ ret = mprotect(mem, size, PROT_READ); + if (ret) { + ksft_perror("mprotect() failed"); + log_test_result(KSFT_FAIL); + goto unregister_buffers; + } + clear_softdirty(); - ret |= mprotect(mem, size, PROT_READ | PROT_WRITE); + ret = mprotect(mem, size, PROT_READ | PROT_WRITE); if (ret) { - ksft_test_result_fail("mprotect() failed\n"); + ksft_perror("mprotect() failed"); + log_test_result(KSFT_FAIL); goto unregister_buffers; } } @@ -440,25 +504,29 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork) memset(mem, 0xff, size); sqe = io_uring_get_sqe(&ring); if (!sqe) { - ksft_test_result_fail("io_uring_get_sqe() failed\n"); + ksft_print_msg("io_uring_get_sqe() failed\n"); + log_test_result(KSFT_FAIL); goto quit_child; } io_uring_prep_write_fixed(sqe, fd, mem, size, 0, 0); ret = io_uring_submit(&ring); if (ret < 0) { - ksft_test_result_fail("io_uring_submit() failed\n"); + ksft_print_msg("io_uring_submit() failed\n"); + log_test_result(KSFT_FAIL); goto quit_child; } ret = io_uring_wait_cqe(&ring, &cqe); if (ret < 0) { - ksft_test_result_fail("io_uring_wait_cqe() failed\n"); + ksft_print_msg("io_uring_wait_cqe() failed\n"); + log_test_result(KSFT_FAIL); goto quit_child; } if (cqe->res != size) { - ksft_test_result_fail("write_fixed failed\n"); + ksft_print_msg("write_fixed failed\n"); + log_test_result(KSFT_FAIL); goto quit_child; } io_uring_cqe_seen(&ring, cqe); @@ -468,15 +536,20 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork) while (total < size) { cur = pread(fd, tmp + total, size - total, total); if (cur < 0) { - ksft_test_result_fail("pread() failed\n"); + ksft_perror("pread() failed\n"); + log_test_result(KSFT_FAIL); goto quit_child; } total += cur; } /* Finally, check if we read what we expected. */ - ksft_test_result(!memcmp(mem, tmp, size), - "Longterm R/W pin is reliable\n"); + if (!memcmp(mem, tmp, size)) { + log_test_result(KSFT_PASS); + } else { + ksft_print_msg("Longtom R/W pin is not reliable\n"); + log_test_result(KSFT_FAIL); + } quit_child: if (use_fork) { @@ -495,12 +568,12 @@ close_comm_pipes: close_comm_pipes(&comm_pipes); } -static void test_iouring_ro(char *mem, size_t size) +static void test_iouring_ro(char *mem, size_t size, bool is_hugetlb) { do_test_iouring(mem, size, false); } -static void test_iouring_fork(char *mem, size_t size) +static void test_iouring_fork(char *mem, size_t size, bool is_hugetlb) { do_test_iouring(mem, size, true); } @@ -524,19 +597,21 @@ static void do_test_ro_pin(char *mem, size_t size, enum ro_pin_test test, int ret; if (gup_fd < 0) { - ksft_test_result_skip("gup_test not available\n"); + ksft_print_msg("gup_test not available\n"); + log_test_result(KSFT_SKIP); return; } tmp = malloc(size); if (!tmp) { - ksft_test_result_fail("malloc() failed\n"); + ksft_perror("malloc() failed\n"); + log_test_result(KSFT_FAIL); return; } ret = setup_comm_pipes(&comm_pipes); if (ret) { - ksft_test_result_fail("pipe() failed\n"); + log_test_result(KSFT_FAIL); goto free_tmp; } @@ -551,7 +626,8 @@ static void do_test_ro_pin(char *mem, size_t size, enum ro_pin_test test, */ ret = fork(); if (ret < 0) { - ksft_test_result_fail("fork() failed\n"); + ksft_perror("fork() failed"); + log_test_result(KSFT_FAIL); goto close_comm_pipes; } else if (!ret) { write(comm_pipes.child_ready[1], "0", 1); @@ -588,7 +664,8 @@ static void do_test_ro_pin(char *mem, size_t size, enum ro_pin_test test, clear_softdirty(); ret |= mprotect(mem, size, PROT_READ | PROT_WRITE); if (ret) { - ksft_test_result_fail("mprotect() failed\n"); + ksft_perror("mprotect() failed"); + log_test_result(KSFT_FAIL); goto close_comm_pipes; } break; @@ -603,9 +680,11 @@ static void do_test_ro_pin(char *mem, size_t size, enum ro_pin_test test, ret = ioctl(gup_fd, PIN_LONGTERM_TEST_START, &args); if (ret) { if (errno == EINVAL) - ksft_test_result_skip("PIN_LONGTERM_TEST_START failed\n"); + ret = KSFT_SKIP; else - ksft_test_result_fail("PIN_LONGTERM_TEST_START failed\n"); + ret = KSFT_FAIL; + ksft_perror("PIN_LONGTERM_TEST_START failed"); + log_test_result(ret); goto wait; } @@ -618,22 +697,28 @@ static void do_test_ro_pin(char *mem, size_t size, enum ro_pin_test test, */ tmp_val = (__u64)(uintptr_t)tmp; ret = ioctl(gup_fd, PIN_LONGTERM_TEST_READ, &tmp_val); - if (ret) - ksft_test_result_fail("PIN_LONGTERM_TEST_READ failed\n"); - else - ksft_test_result(!memcmp(mem, tmp, size), - "Longterm R/O pin is reliable\n"); + if (ret) { + ksft_perror("PIN_LONGTERM_TEST_READ failed"); + log_test_result(KSFT_FAIL); + } else { + if (!memcmp(mem, tmp, size)) { + log_test_result(KSFT_PASS); + } else { + ksft_print_msg("Longterm R/O pin is not reliable\n"); + log_test_result(KSFT_FAIL); + } + } ret = ioctl(gup_fd, PIN_LONGTERM_TEST_STOP); if (ret) - ksft_print_msg("[INFO] PIN_LONGTERM_TEST_STOP failed\n"); + ksft_perror("PIN_LONGTERM_TEST_STOP failed"); wait: switch (test) { case RO_PIN_TEST_SHARED: write(comm_pipes.parent_ready[1], "0", 1); wait(&ret); if (!WIFEXITED(ret)) - ksft_print_msg("[INFO] wait() failed\n"); + ksft_perror("wait() failed"); break; default: break; @@ -644,37 +729,41 @@ free_tmp: free(tmp); } -static void test_ro_pin_on_shared(char *mem, size_t size) +static void test_ro_pin_on_shared(char *mem, size_t size, bool is_hugetlb) { do_test_ro_pin(mem, size, RO_PIN_TEST_SHARED, false); } -static void test_ro_fast_pin_on_shared(char *mem, size_t size) +static void test_ro_fast_pin_on_shared(char *mem, size_t size, bool is_hugetlb) { do_test_ro_pin(mem, size, RO_PIN_TEST_SHARED, true); } -static void test_ro_pin_on_ro_previously_shared(char *mem, size_t size) +static void test_ro_pin_on_ro_previously_shared(char *mem, size_t size, + bool is_hugetlb) { do_test_ro_pin(mem, size, RO_PIN_TEST_PREVIOUSLY_SHARED, false); } -static void test_ro_fast_pin_on_ro_previously_shared(char *mem, size_t size) +static void test_ro_fast_pin_on_ro_previously_shared(char *mem, size_t size, + bool is_hugetlb) { do_test_ro_pin(mem, size, RO_PIN_TEST_PREVIOUSLY_SHARED, true); } -static void test_ro_pin_on_ro_exclusive(char *mem, size_t size) +static void test_ro_pin_on_ro_exclusive(char *mem, size_t size, + bool is_hugetlb) { do_test_ro_pin(mem, size, RO_PIN_TEST_RO_EXCLUSIVE, false); } -static void test_ro_fast_pin_on_ro_exclusive(char *mem, size_t size) +static void test_ro_fast_pin_on_ro_exclusive(char *mem, size_t size, + bool is_hugetlb) { do_test_ro_pin(mem, size, RO_PIN_TEST_RO_EXCLUSIVE, true); } -typedef void (*test_fn)(char *mem, size_t size); +typedef void (*test_fn)(char *mem, size_t size, bool hugetlb); static void do_run_with_base_page(test_fn fn, bool swapout) { @@ -684,42 +773,45 @@ static void do_run_with_base_page(test_fn fn, bool swapout) mem = mmap(NULL, pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (mem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); return; } ret = madvise(mem, pagesize, MADV_NOHUGEPAGE); /* Ignore if not around on a kernel. */ if (ret && errno != EINVAL) { - ksft_test_result_fail("MADV_NOHUGEPAGE failed\n"); + ksft_perror("MADV_NOHUGEPAGE failed"); + log_test_result(KSFT_FAIL); goto munmap; } /* Populate a base page. */ - memset(mem, 0, pagesize); + memset(mem, 1, pagesize); if (swapout) { madvise(mem, pagesize, MADV_PAGEOUT); if (!pagemap_is_swapped(pagemap_fd, mem)) { - ksft_test_result_skip("MADV_PAGEOUT did not work, is swap enabled?\n"); + ksft_print_msg("MADV_PAGEOUT did not work, is swap enabled?\n"); + log_test_result(KSFT_SKIP); goto munmap; } } - fn(mem, pagesize); + fn(mem, pagesize, false); munmap: munmap(mem, pagesize); } static void run_with_base_page(test_fn fn, const char *desc) { - ksft_print_msg("[RUN] %s ... with base page\n", desc); + log_test_start("%s ... with base page", desc); do_run_with_base_page(fn, false); } static void run_with_base_page_swap(test_fn fn, const char *desc) { - ksft_print_msg("[RUN] %s ... with swapped out base page\n", desc); + log_test_start("%s ... with swapped out base page", desc); do_run_with_base_page(fn, true); } @@ -734,7 +826,7 @@ enum thp_run { THP_RUN_PARTIAL_SHARED, }; -static void do_run_with_thp(test_fn fn, enum thp_run thp_run) +static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize) { char *mem, *mmap_mem, *tmp, *mremap_mem = MAP_FAILED; size_t size, mmap_size, mremap_size; @@ -745,7 +837,8 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run) mmap_mem = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (mmap_mem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); return; } @@ -754,40 +847,46 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run) ret = madvise(mem, thpsize, MADV_HUGEPAGE); if (ret) { - ksft_test_result_fail("MADV_HUGEPAGE failed\n"); + ksft_perror("MADV_HUGEPAGE failed"); + log_test_result(KSFT_FAIL); goto munmap; } /* - * Try to populate a THP. Touch the first sub-page and test if we get - * another sub-page populated automatically. + * Try to populate a THP. Touch the first sub-page and test if + * we get the last sub-page populated automatically. */ - mem[0] = 0; - if (!pagemap_is_populated(pagemap_fd, mem + pagesize)) { - ksft_test_result_skip("Did not get a THP populated\n"); + mem[0] = 1; + if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { + ksft_print_msg("Did not get a THP populated\n"); + log_test_result(KSFT_SKIP); goto munmap; } - memset(mem, 0, thpsize); + memset(mem, 1, thpsize); size = thpsize; switch (thp_run) { case THP_RUN_PMD: case THP_RUN_PMD_SWAPOUT: + assert(thpsize == pmdsize); break; case THP_RUN_PTE: case THP_RUN_PTE_SWAPOUT: /* * Trigger PTE-mapping the THP by temporarily mapping a single - * subpage R/O. + * subpage R/O. This is a noop if the THP is not pmdsize (and + * therefore already PTE-mapped). */ ret = mprotect(mem + pagesize, pagesize, PROT_READ); if (ret) { - ksft_test_result_fail("mprotect() failed\n"); + ksft_perror("mprotect() failed"); + log_test_result(KSFT_FAIL); goto munmap; } ret = mprotect(mem + pagesize, pagesize, PROT_READ | PROT_WRITE); if (ret) { - ksft_test_result_fail("mprotect() failed\n"); + ksft_perror("mprotect() failed"); + log_test_result(KSFT_FAIL); goto munmap; } break; @@ -799,7 +898,8 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run) */ ret = madvise(mem + pagesize, thpsize - pagesize, MADV_DONTNEED); if (ret) { - ksft_test_result_fail("MADV_DONTNEED failed\n"); + ksft_perror("MADV_DONTNEED failed"); + log_test_result(KSFT_FAIL); goto munmap; } size = pagesize; @@ -812,14 +912,16 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run) mremap_size = thpsize / 2; mremap_mem = mmap(NULL, mremap_size, PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); - if (mem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + if (mremap_mem == MAP_FAILED) { + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); goto munmap; } tmp = mremap(mem + mremap_size, mremap_size, mremap_size, MREMAP_MAYMOVE | MREMAP_FIXED, mremap_mem); if (tmp != mremap_mem) { - ksft_test_result_fail("mremap() failed\n"); + ksft_perror("mremap() failed"); + log_test_result(KSFT_FAIL); goto munmap; } size = mremap_size; @@ -832,12 +934,14 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run) */ ret = madvise(mem + pagesize, thpsize - pagesize, MADV_DONTFORK); if (ret) { - ksft_test_result_fail("MADV_DONTFORK failed\n"); + ksft_perror("MADV_DONTFORK failed"); + log_test_result(KSFT_FAIL); goto munmap; } ret = fork(); if (ret < 0) { - ksft_test_result_fail("fork() failed\n"); + ksft_perror("fork() failed"); + log_test_result(KSFT_FAIL); goto munmap; } else if (!ret) { exit(0); @@ -846,7 +950,8 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run) /* Allow for sharing all pages again. */ ret = madvise(mem + pagesize, thpsize - pagesize, MADV_DOFORK); if (ret) { - ksft_test_result_fail("MADV_DOFORK failed\n"); + ksft_perror("MADV_DOFORK failed"); + log_test_result(KSFT_FAIL); goto munmap; } break; @@ -860,7 +965,8 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run) case THP_RUN_SINGLE_PTE_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"); + ksft_print_msg("MADV_PAGEOUT did not work, is swap enabled?\n"); + log_test_result(KSFT_SKIP); goto munmap; } break; @@ -868,59 +974,67 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run) break; } - fn(mem, size); + fn(mem, size, false); munmap: munmap(mmap_mem, mmap_size); if (mremap_mem != MAP_FAILED) munmap(mremap_mem, mremap_size); } -static void run_with_thp(test_fn fn, const char *desc) +static void run_with_thp(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with THP\n", desc); - do_run_with_thp(fn, THP_RUN_PMD); + log_test_start("%s ... with THP (%zu kB)", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PMD, size); } -static void run_with_thp_swap(test_fn fn, const char *desc) +static void run_with_thp_swap(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with swapped-out THP\n", desc); - do_run_with_thp(fn, THP_RUN_PMD_SWAPOUT); + log_test_start("%s ... with swapped-out THP (%zu kB)", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PMD_SWAPOUT, size); } -static void run_with_pte_mapped_thp(test_fn fn, const char *desc) +static void run_with_pte_mapped_thp(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with PTE-mapped THP\n", desc); - do_run_with_thp(fn, THP_RUN_PTE); + log_test_start("%s ... with PTE-mapped THP (%zu kB)", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PTE, size); } -static void run_with_pte_mapped_thp_swap(test_fn fn, const char *desc) +static void run_with_pte_mapped_thp_swap(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with swapped-out, PTE-mapped THP\n", desc); - do_run_with_thp(fn, THP_RUN_PTE_SWAPOUT); + log_test_start("%s ... with swapped-out, PTE-mapped THP (%zu kB)", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PTE_SWAPOUT, size); } -static void run_with_single_pte_of_thp(test_fn fn, const char *desc) +static void run_with_single_pte_of_thp(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with single PTE of THP\n", desc); - do_run_with_thp(fn, THP_RUN_SINGLE_PTE); + log_test_start("%s ... with single PTE of THP (%zu kB)", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_SINGLE_PTE, size); } -static void run_with_single_pte_of_thp_swap(test_fn fn, const char *desc) +static void run_with_single_pte_of_thp_swap(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with single PTE of swapped-out THP\n", desc); - do_run_with_thp(fn, THP_RUN_SINGLE_PTE_SWAPOUT); + log_test_start("%s ... with single PTE of swapped-out THP (%zu kB)", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_SINGLE_PTE_SWAPOUT, size); } -static void run_with_partial_mremap_thp(test_fn fn, const char *desc) +static void run_with_partial_mremap_thp(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with partially mremap()'ed THP\n", desc); - do_run_with_thp(fn, THP_RUN_PARTIAL_MREMAP); + log_test_start("%s ... with partially mremap()'ed THP (%zu kB)", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PARTIAL_MREMAP, size); } -static void run_with_partial_shared_thp(test_fn fn, const char *desc) +static void run_with_partial_shared_thp(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with partially shared THP\n", desc); - do_run_with_thp(fn, THP_RUN_PARTIAL_SHARED); + log_test_start("%s ... with partially shared THP (%zu kB)", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PARTIAL_SHARED, size); } static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize) @@ -928,19 +1042,20 @@ static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize) int flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB; char *mem, *dummy; - ksft_print_msg("[RUN] %s ... with hugetlb (%zu kB)\n", desc, + log_test_start("%s ... with hugetlb (%zu kB)", desc, hugetlbsize / 1024); flags |= __builtin_ctzll(hugetlbsize) << MAP_HUGE_SHIFT; mem = mmap(NULL, hugetlbsize, PROT_READ | PROT_WRITE, flags, -1, 0); if (mem == MAP_FAILED) { - ksft_test_result_skip("need more free huge pages\n"); + ksft_perror("need more free huge pages"); + log_test_result(KSFT_SKIP); return; } /* Populate an huge page. */ - memset(mem, 0, hugetlbsize); + memset(mem, 1, hugetlbsize); /* * We need a total of two hugetlb pages to handle COW/unsharing @@ -948,12 +1063,13 @@ static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize) */ dummy = mmap(NULL, hugetlbsize, PROT_READ | PROT_WRITE, flags, -1, 0); if (dummy == MAP_FAILED) { - ksft_test_result_skip("need more free huge pages\n"); + ksft_perror("need more free huge pages"); + log_test_result(KSFT_SKIP); goto munmap; } munmap(dummy, hugetlbsize); - fn(mem, hugetlbsize); + fn(mem, hugetlbsize, true); munmap: munmap(mem, hugetlbsize); } @@ -992,7 +1108,7 @@ static const struct test_case anon_test_cases[] = { */ { "vmsplice() + unmap in child", - test_vmsplice_in_child + test_vmsplice_in_child, }, /* * vmsplice() test, but do an additional mprotect(PROT_READ)+ @@ -1000,7 +1116,7 @@ static const struct test_case anon_test_cases[] = { */ { "vmsplice() + unmap in child with mprotect() optimization", - test_vmsplice_in_child_mprotect + test_vmsplice_in_child_mprotect, }, /* * vmsplice() [R/O GUP] in parent before fork(), unmap in parent after @@ -1091,15 +1207,27 @@ static void run_anon_test_case(struct test_case const *test_case) run_with_base_page(test_case->fn, test_case->desc); run_with_base_page_swap(test_case->fn, test_case->desc); - if (thpsize) { - run_with_thp(test_case->fn, test_case->desc); - run_with_thp_swap(test_case->fn, test_case->desc); - run_with_pte_mapped_thp(test_case->fn, test_case->desc); - run_with_pte_mapped_thp_swap(test_case->fn, test_case->desc); - run_with_single_pte_of_thp(test_case->fn, test_case->desc); - run_with_single_pte_of_thp_swap(test_case->fn, test_case->desc); - run_with_partial_mremap_thp(test_case->fn, test_case->desc); - run_with_partial_shared_thp(test_case->fn, test_case->desc); + for (i = 0; i < nr_thpsizes; i++) { + size_t size = thpsizes[i]; + struct thp_settings settings = *thp_current_settings(); + + settings.hugepages[sz2ord(pmdsize, pagesize)].enabled = THP_NEVER; + settings.hugepages[sz2ord(size, pagesize)].enabled = THP_ALWAYS; + thp_push_settings(&settings); + + if (size == pmdsize) { + run_with_thp(test_case->fn, test_case->desc, size); + run_with_thp_swap(test_case->fn, test_case->desc, size); + } + + run_with_pte_mapped_thp(test_case->fn, test_case->desc, size); + run_with_pte_mapped_thp_swap(test_case->fn, test_case->desc, size); + run_with_single_pte_of_thp(test_case->fn, test_case->desc, size); + run_with_single_pte_of_thp_swap(test_case->fn, test_case->desc, size); + run_with_partial_mremap_thp(test_case->fn, test_case->desc, size); + run_with_partial_shared_thp(test_case->fn, test_case->desc, size); + + thp_pop_settings(); } for (i = 0; i < nr_hugetlbsizes; i++) run_with_hugetlb(test_case->fn, test_case->desc, @@ -1120,8 +1248,9 @@ static int tests_per_anon_test_case(void) { int tests = 2 + nr_hugetlbsizes; - if (thpsize) - tests += 8; + tests += 6 * nr_thpsizes; + if (pmdsize) + tests += 2; return tests; } @@ -1141,7 +1270,7 @@ static void do_test_anon_thp_collapse(char *mem, size_t size, ret = setup_comm_pipes(&comm_pipes); if (ret) { - ksft_test_result_fail("pipe() failed\n"); + log_test_result(KSFT_FAIL); return; } @@ -1151,12 +1280,14 @@ static void do_test_anon_thp_collapse(char *mem, size_t size, */ ret = mprotect(mem + pagesize, pagesize, PROT_READ); if (ret) { - ksft_test_result_fail("mprotect() failed\n"); + ksft_perror("mprotect() failed"); + log_test_result(KSFT_FAIL); goto close_comm_pipes; } ret = mprotect(mem + pagesize, pagesize, PROT_READ | PROT_WRITE); if (ret) { - ksft_test_result_fail("mprotect() failed\n"); + ksft_perror("mprotect() failed"); + log_test_result(KSFT_FAIL); goto close_comm_pipes; } @@ -1165,8 +1296,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size, /* Collapse before actually COW-sharing the page. */ ret = madvise(mem, size, MADV_COLLAPSE); if (ret) { - ksft_test_result_skip("MADV_COLLAPSE failed: %s\n", - strerror(errno)); + ksft_perror("MADV_COLLAPSE failed"); + log_test_result(KSFT_SKIP); goto close_comm_pipes; } break; @@ -1177,7 +1308,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size, /* Don't COW-share the upper part of the THP. */ ret = madvise(mem + size / 2, size / 2, MADV_DONTFORK); if (ret) { - ksft_test_result_fail("MADV_DONTFORK failed\n"); + ksft_perror("MADV_DONTFORK failed"); + log_test_result(KSFT_FAIL); goto close_comm_pipes; } break; @@ -1185,7 +1317,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size, /* Don't COW-share the lower part of the THP. */ ret = madvise(mem, size / 2, MADV_DONTFORK); if (ret) { - ksft_test_result_fail("MADV_DONTFORK failed\n"); + ksft_perror("MADV_DONTFORK failed"); + log_test_result(KSFT_FAIL); goto close_comm_pipes; } break; @@ -1195,7 +1328,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size, ret = fork(); if (ret < 0) { - ksft_test_result_fail("fork() failed\n"); + ksft_perror("fork() failed"); + log_test_result(KSFT_FAIL); goto close_comm_pipes; } else if (!ret) { switch (test) { @@ -1229,7 +1363,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size, */ ret = madvise(mem, size, MADV_DOFORK); if (ret) { - ksft_test_result_fail("MADV_DOFORK failed\n"); + ksft_perror("MADV_DOFORK failed"); + log_test_result(KSFT_FAIL); write(comm_pipes.parent_ready[1], "0", 1); wait(&ret); goto close_comm_pipes; @@ -1239,8 +1374,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size, /* Collapse before anyone modified the COW-shared page. */ ret = madvise(mem, size, MADV_COLLAPSE); if (ret) { - ksft_test_result_skip("MADV_COLLAPSE failed: %s\n", - strerror(errno)); + ksft_perror("MADV_COLLAPSE failed"); + log_test_result(KSFT_SKIP); write(comm_pipes.parent_ready[1], "0", 1); wait(&ret); goto close_comm_pipes; @@ -1260,28 +1395,41 @@ static void do_test_anon_thp_collapse(char *mem, size_t size, else ret = -EINVAL; - ksft_test_result(!ret, "No leak from parent into child\n"); + if (!ret) { + log_test_result(KSFT_PASS); + } else { + ksft_print_msg("Leak from parent into child\n"); + log_test_result(KSFT_FAIL); + } close_comm_pipes: close_comm_pipes(&comm_pipes); } -static void test_anon_thp_collapse_unshared(char *mem, size_t size) +static void test_anon_thp_collapse_unshared(char *mem, size_t size, + bool is_hugetlb) { + assert(!is_hugetlb); do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_UNSHARED); } -static void test_anon_thp_collapse_fully_shared(char *mem, size_t size) +static void test_anon_thp_collapse_fully_shared(char *mem, size_t size, + bool is_hugetlb) { + assert(!is_hugetlb); do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_FULLY_SHARED); } -static void test_anon_thp_collapse_lower_shared(char *mem, size_t size) +static void test_anon_thp_collapse_lower_shared(char *mem, size_t size, + bool is_hugetlb) { + assert(!is_hugetlb); do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_LOWER_SHARED); } -static void test_anon_thp_collapse_upper_shared(char *mem, size_t size) +static void test_anon_thp_collapse_upper_shared(char *mem, size_t size, + bool is_hugetlb) { + assert(!is_hugetlb); do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_UPPER_SHARED); } @@ -1329,7 +1477,7 @@ static void run_anon_thp_test_cases(void) { int i; - if (!thpsize) + if (!pmdsize) return; ksft_print_msg("[INFO] Anonymous THP tests\n"); @@ -1337,14 +1485,14 @@ static void run_anon_thp_test_cases(void) for (i = 0; i < ARRAY_SIZE(anon_thp_test_cases); i++) { struct test_case const *test_case = &anon_thp_test_cases[i]; - ksft_print_msg("[RUN] %s\n", test_case->desc); - do_run_with_thp(test_case->fn, THP_RUN_PMD); + log_test_start("%s", test_case->desc); + do_run_with_thp(test_case->fn, THP_RUN_PMD, pmdsize); } } static int tests_per_anon_thp_test_case(void) { - return thpsize ? 1 : 0; + return pmdsize ? 1 : 0; } typedef void (*non_anon_test_fn)(char *mem, const char *smem, size_t size); @@ -1360,8 +1508,12 @@ static void test_cow(char *mem, const char *smem, size_t size) memset(mem, 0xff, size); /* See if we still read the old values via the other mapping. */ - ksft_test_result(!memcmp(smem, old, size), - "Other mapping not modified\n"); + if (!memcmp(smem, old, size)) { + log_test_result(KSFT_PASS); + } else { + ksft_print_msg("Other mapping modified\n"); + log_test_result(KSFT_FAIL); + } free(old); } @@ -1377,26 +1529,28 @@ static void test_ro_fast_pin(char *mem, const char *smem, size_t size) static void run_with_zeropage(non_anon_test_fn fn, const char *desc) { - char *mem, *smem, tmp; + char *mem, *smem; - ksft_print_msg("[RUN] %s ... with shared zeropage\n", desc); + log_test_start("%s ... with shared zeropage", desc); mem = mmap(NULL, pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); if (mem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); return; } smem = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0); - if (mem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + if (smem == MAP_FAILED) { + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); goto munmap; } /* Read from the page to populate the shared zeropage. */ - tmp = *mem + *smem; - asm volatile("" : "+r" (tmp)); + FORCE_READ(*mem); + FORCE_READ(*smem); fn(mem, smem, pagesize); munmap: @@ -1407,40 +1561,49 @@ munmap: static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc) { - char *mem, *smem, *mmap_mem, *mmap_smem, tmp; + char *mem, *smem, *mmap_mem, *mmap_smem; size_t mmap_size; int ret; - ksft_print_msg("[RUN] %s ... with huge zeropage\n", desc); + log_test_start("%s ... with huge zeropage", desc); if (!has_huge_zeropage) { - ksft_test_result_skip("Huge zeropage not enabled\n"); + ksft_print_msg("Huge zeropage not enabled\n"); + log_test_result(KSFT_SKIP); return; } /* For alignment purposes, we need twice the thp size. */ - mmap_size = 2 * thpsize; + mmap_size = 2 * pmdsize; mmap_mem = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (mmap_mem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); return; } mmap_smem = mmap(NULL, mmap_size, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (mmap_smem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); goto munmap; } /* We need a THP-aligned memory area. */ - mem = (char *)(((uintptr_t)mmap_mem + thpsize) & ~(thpsize - 1)); - smem = (char *)(((uintptr_t)mmap_smem + thpsize) & ~(thpsize - 1)); + mem = (char *)(((uintptr_t)mmap_mem + pmdsize) & ~(pmdsize - 1)); + smem = (char *)(((uintptr_t)mmap_smem + pmdsize) & ~(pmdsize - 1)); - ret = madvise(mem, thpsize, MADV_HUGEPAGE); - ret |= madvise(smem, thpsize, MADV_HUGEPAGE); + ret = madvise(mem, pmdsize, MADV_HUGEPAGE); + if (ret) { + ksft_perror("madvise()"); + log_test_result(KSFT_FAIL); + goto munmap; + } + ret = madvise(smem, pmdsize, MADV_HUGEPAGE); if (ret) { - ksft_test_result_fail("MADV_HUGEPAGE failed\n"); + ksft_perror("madvise()"); + log_test_result(KSFT_FAIL); goto munmap; } @@ -1449,15 +1612,15 @@ static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc) * the first sub-page and test if we get another sub-page populated * automatically. */ - tmp = *mem + *smem; - asm volatile("" : "+r" (tmp)); + FORCE_READ(mem); + FORCE_READ(smem); if (!pagemap_is_populated(pagemap_fd, mem + pagesize) || !pagemap_is_populated(pagemap_fd, smem + pagesize)) { ksft_test_result_skip("Did not get THPs populated\n"); goto munmap; } - fn(mem, smem, thpsize); + fn(mem, smem, pmdsize); munmap: munmap(mmap_mem, mmap_size); if (mmap_smem != MAP_FAILED) @@ -1466,38 +1629,42 @@ munmap: static void run_with_memfd(non_anon_test_fn fn, const char *desc) { - char *mem, *smem, tmp; + char *mem, *smem; int fd; - ksft_print_msg("[RUN] %s ... with memfd\n", desc); + log_test_start("%s ... with memfd", desc); fd = memfd_create("test", 0); if (fd < 0) { - ksft_test_result_fail("memfd_create() failed\n"); + ksft_perror("memfd_create() failed"); + log_test_result(KSFT_FAIL); return; } /* File consists of a single page filled with zeroes. */ if (fallocate(fd, 0, 0, pagesize)) { - ksft_test_result_fail("fallocate() failed\n"); + ksft_perror("fallocate() failed"); + log_test_result(KSFT_FAIL); goto close; } /* Create a private mapping of the memfd. */ mem = mmap(NULL, pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); if (mem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); goto close; } smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + if (smem == MAP_FAILED) { + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); goto munmap; } /* Fault the page in. */ - tmp = *mem + *smem; - asm volatile("" : "+r" (tmp)); + FORCE_READ(mem); + FORCE_READ(smem); fn(mem, smem, pagesize); munmap: @@ -1510,45 +1677,50 @@ close: static void run_with_tmpfile(non_anon_test_fn fn, const char *desc) { - char *mem, *smem, tmp; + char *mem, *smem; FILE *file; int fd; - ksft_print_msg("[RUN] %s ... with tmpfile\n", desc); + log_test_start("%s ... with tmpfile", desc); file = tmpfile(); if (!file) { - ksft_test_result_fail("tmpfile() failed\n"); + ksft_perror("tmpfile() failed"); + log_test_result(KSFT_FAIL); return; } fd = fileno(file); if (fd < 0) { - ksft_test_result_skip("fileno() failed\n"); + ksft_perror("fileno() failed"); + log_test_result(KSFT_SKIP); return; } /* File consists of a single page filled with zeroes. */ if (fallocate(fd, 0, 0, pagesize)) { - ksft_test_result_fail("fallocate() failed\n"); + ksft_perror("fallocate() failed"); + log_test_result(KSFT_FAIL); goto close; } /* Create a private mapping of the memfd. */ mem = mmap(NULL, pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); if (mem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); goto close; } smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + if (smem == MAP_FAILED) { + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); goto munmap; } /* Fault the page in. */ - tmp = *mem + *smem; - asm volatile("" : "+r" (tmp)); + FORCE_READ(mem); + FORCE_READ(smem); fn(mem, smem, pagesize); munmap: @@ -1563,23 +1735,25 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc, size_t hugetlbsize) { int flags = MFD_HUGETLB; - char *mem, *smem, tmp; + char *mem, *smem; int fd; - ksft_print_msg("[RUN] %s ... with memfd hugetlb (%zu kB)\n", desc, + log_test_start("%s ... with memfd hugetlb (%zu kB)", desc, hugetlbsize / 1024); flags |= __builtin_ctzll(hugetlbsize) << MFD_HUGE_SHIFT; fd = memfd_create("test", flags); if (fd < 0) { - ksft_test_result_skip("memfd_create() failed\n"); + ksft_perror("memfd_create() failed"); + log_test_result(KSFT_SKIP); return; } /* File consists of a single page filled with zeroes. */ if (fallocate(fd, 0, 0, hugetlbsize)) { - ksft_test_result_skip("need more free huge pages\n"); + ksft_perror("need more free huge pages"); + log_test_result(KSFT_SKIP); goto close; } @@ -1587,23 +1761,25 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc, mem = mmap(NULL, hugetlbsize, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); if (mem == MAP_FAILED) { - ksft_test_result_skip("need more free huge pages\n"); + ksft_perror("need more free huge pages"); + log_test_result(KSFT_SKIP); goto close; } smem = mmap(NULL, hugetlbsize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); + if (smem == MAP_FAILED) { + ksft_perror("mmap() failed"); + log_test_result(KSFT_FAIL); goto munmap; } /* Fault the page in. */ - tmp = *mem + *smem; - asm volatile("" : "+r" (tmp)); + FORCE_READ(mem); + FORCE_READ(smem); fn(mem, smem, hugetlbsize); munmap: munmap(mem, hugetlbsize); - if (mem != MAP_FAILED) + if (smem != MAP_FAILED) munmap(smem, hugetlbsize); close: close(fd); @@ -1650,7 +1826,7 @@ static void run_non_anon_test_case(struct non_anon_test_case const *test_case) run_with_zeropage(test_case->fn, test_case->desc); run_with_memfd(test_case->fn, test_case->desc); run_with_tmpfile(test_case->fn, test_case->desc); - if (thpsize) + if (pmdsize) run_with_huge_zeropage(test_case->fn, test_case->desc); for (i = 0; i < nr_hugetlbsizes; i++) run_with_memfd_hugetlb(test_case->fn, test_case->desc, @@ -1671,25 +1847,34 @@ static int tests_per_non_anon_test_case(void) { int tests = 3 + nr_hugetlbsizes; - if (thpsize) + if (pmdsize) tests += 1; return tests; } int main(int argc, char **argv) { - int err; + struct thp_settings default_settings; + + ksft_print_header(); pagesize = getpagesize(); - thpsize = read_pmd_pagesize(); - if (thpsize) - ksft_print_msg("[INFO] detected THP size: %zu KiB\n", - thpsize / 1024); + pmdsize = read_pmd_pagesize(); + if (pmdsize) { + /* Only if THP is supported. */ + thp_read_settings(&default_settings); + default_settings.hugepages[sz2ord(pmdsize, pagesize)].enabled = THP_INHERIT; + thp_save_settings(); + thp_push_settings(&default_settings); + + ksft_print_msg("[INFO] detected PMD size: %zu KiB\n", + pmdsize / 1024); + nr_thpsizes = detect_thp_sizes(thpsizes, ARRAY_SIZE(thpsizes)); + } nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, ARRAY_SIZE(hugetlbsizes)); - detect_huge_zeropage(); + has_huge_zeropage = detect_huge_zeropage(); - ksft_print_header(); ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() + ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() + ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case()); @@ -1703,9 +1888,10 @@ int main(int argc, char **argv) run_anon_thp_test_cases(); run_non_anon_test_cases(); - err = ksft_get_fail_cnt(); - if (err) - ksft_exit_fail_msg("%d out of %d tests failed\n", - err, ksft_test_num()); - return ksft_exit_pass(); + if (pmdsize) { + /* Only if THP is supported. */ + thp_restore_settings(); + } + + ksft_finished(); } diff --git a/tools/testing/selftests/mm/droppable.c b/tools/testing/selftests/mm/droppable.c new file mode 100644 index 000000000000..44940f75c461 --- /dev/null +++ b/tools/testing/selftests/mm/droppable.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ + +#include <assert.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <signal.h> +#include <sys/mman.h> +#include <linux/mman.h> + +#include "kselftest.h" + +int main(int argc, char *argv[]) +{ + size_t alloc_size = 134217728; + size_t page_size = getpagesize(); + void *alloc; + pid_t child; + + ksft_print_header(); + ksft_set_plan(1); + + alloc = mmap(0, alloc_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_DROPPABLE, -1, 0); + assert(alloc != MAP_FAILED); + memset(alloc, 'A', alloc_size); + for (size_t i = 0; i < alloc_size; i += page_size) + assert(*(uint8_t *)(alloc + i)); + + child = fork(); + assert(child >= 0); + if (!child) { + for (;;) + *(char *)malloc(page_size) = 'B'; + } + + for (bool done = false; !done;) { + for (size_t i = 0; i < alloc_size; i += page_size) { + if (!*(uint8_t *)(alloc + i)) { + done = true; + break; + } + } + } + kill(child, SIGTERM); + + ksft_test_result_pass("MAP_DROPPABLE: PASS\n"); + exit(KSFT_PASS); +} diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c new file mode 100644 index 000000000000..dbd21d66d383 --- /dev/null +++ b/tools/testing/selftests/mm/guard-regions.c @@ -0,0 +1,2326 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE +#include "kselftest_harness.h" +#include <asm-generic/mman.h> /* Force the import of the tools version. */ +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/limits.h> +#include <linux/userfaultfd.h> +#include <linux/fs.h> +#include <setjmp.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <sys/uio.h> +#include <unistd.h> +#include "vm_util.h" + +#include "../pidfd/pidfd.h" + +/* + * Ignore the checkpatch warning, as per the C99 standard, section 7.14.1.1: + * + * "If the signal occurs other than as the result of calling the abort or raise + * function, the behavior is undefined if the signal handler refers to any + * object with static storage duration other than by assigning a value to an + * object declared as volatile sig_atomic_t" + */ +static volatile sig_atomic_t signal_jump_set; +static sigjmp_buf signal_jmp_buf; + +/* + * How is the test backing the mapping being tested? + */ +enum backing_type { + ANON_BACKED, + SHMEM_BACKED, + LOCAL_FILE_BACKED, +}; + +FIXTURE(guard_regions) +{ + unsigned long page_size; + char path[PATH_MAX]; + int fd; +}; + +FIXTURE_VARIANT(guard_regions) +{ + enum backing_type backing; +}; + +FIXTURE_VARIANT_ADD(guard_regions, anon) +{ + .backing = ANON_BACKED, +}; + +FIXTURE_VARIANT_ADD(guard_regions, shmem) +{ + .backing = SHMEM_BACKED, +}; + +FIXTURE_VARIANT_ADD(guard_regions, file) +{ + .backing = LOCAL_FILE_BACKED, +}; + +static bool is_anon_backed(const FIXTURE_VARIANT(guard_regions) * variant) +{ + switch (variant->backing) { + case ANON_BACKED: + case SHMEM_BACKED: + return true; + default: + return false; + } +} + +static void *mmap_(FIXTURE_DATA(guard_regions) * self, + const FIXTURE_VARIANT(guard_regions) * variant, + void *addr, size_t length, int prot, int extra_flags, + off_t offset) +{ + int fd; + int flags = extra_flags; + + switch (variant->backing) { + case ANON_BACKED: + flags |= MAP_PRIVATE | MAP_ANON; + fd = -1; + offset = 0; + break; + case SHMEM_BACKED: + case LOCAL_FILE_BACKED: + flags |= MAP_SHARED; + fd = self->fd; + break; + default: + ksft_exit_fail(); + break; + } + + return mmap(addr, length, prot, flags, fd, offset); +} + +static int userfaultfd(int flags) +{ + return syscall(SYS_userfaultfd, flags); +} + +static void handle_fatal(int c) +{ + if (!signal_jump_set) + return; + + siglongjmp(signal_jmp_buf, c); +} + +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 + * signal. + */ +static bool try_access_buf(char *ptr, bool write) +{ + bool failed; + + /* Tell signal handler to jump back here on fatal signal. */ + signal_jump_set = true; + /* If a fatal signal arose, we will jump back here and failed is set. */ + failed = sigsetjmp(signal_jmp_buf, 0) != 0; + + if (!failed) { + if (write) + *ptr = 'x'; + else + FORCE_READ(*ptr); + } + + signal_jump_set = false; + return !failed; +} + +/* Try and read from a buffer, return true if no fatal signal. */ +static bool try_read_buf(char *ptr) +{ + return try_access_buf(ptr, false); +} + +/* Try and write to a buffer, return true if no fatal signal. */ +static bool try_write_buf(char *ptr) +{ + return try_access_buf(ptr, true); +} + +/* + * Try and BOTH read from AND write to a buffer, return true if BOTH operations + * succeed. + */ +static bool try_read_write_buf(char *ptr) +{ + return try_read_buf(ptr) && try_write_buf(ptr); +} + +static void setup_sighandler(void) +{ + struct sigaction act = { + .sa_handler = &handle_fatal, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + if (sigaction(SIGSEGV, &act, NULL)) + ksft_exit_fail_perror("sigaction"); +} + +static void teardown_sighandler(void) +{ + struct sigaction act = { + .sa_handler = SIG_DFL, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + sigaction(SIGSEGV, &act, NULL); +} + +static int open_file(const char *prefix, char *path) +{ + int fd; + + snprintf(path, PATH_MAX, "%sguard_regions_test_file_XXXXXX", prefix); + fd = mkstemp(path); + if (fd < 0) + ksft_exit_fail_perror("mkstemp"); + + return fd; +} + +/* Establish a varying pattern in a buffer. */ +static void set_pattern(char *ptr, size_t num_pages, size_t page_size) +{ + size_t i; + + for (i = 0; i < num_pages; i++) { + char *ptr2 = &ptr[i * page_size]; + + memset(ptr2, 'a' + (i % 26), page_size); + } +} + +/* + * Check that a buffer contains the pattern set by set_pattern(), starting at a + * page offset of pgoff within the buffer. + */ +static bool check_pattern_offset(char *ptr, size_t num_pages, size_t page_size, + size_t pgoff) +{ + size_t i; + + for (i = 0; i < num_pages * page_size; i++) { + size_t offset = pgoff * page_size + i; + char actual = ptr[offset]; + char expected = 'a' + ((offset / page_size) % 26); + + if (actual != expected) + return false; + } + + return true; +} + +/* Check that a buffer contains the pattern set by set_pattern(). */ +static bool check_pattern(char *ptr, size_t num_pages, size_t page_size) +{ + return check_pattern_offset(ptr, num_pages, page_size, 0); +} + +/* Determine if a buffer contains only repetitions of a specified char. */ +static bool is_buf_eq(char *buf, size_t size, char chr) +{ + size_t i; + + for (i = 0; i < size; i++) { + if (buf[i] != chr) + return false; + } + + return true; +} + +/* + * Some file systems have issues with merging due to changing merge-sensitive + * parameters in the .mmap callback, and prior to .mmap_prepare being + * implemented everywhere this will now result in an unexpected failure to + * merge (e.g. - overlayfs). + * + * Perform a simple test to see if the local file system suffers from this, if + * it does then we can skip test logic that assumes local file system merging is + * sane. + */ +static bool local_fs_has_sane_mmap(FIXTURE_DATA(guard_regions) * self, + const FIXTURE_VARIANT(guard_regions) * variant) +{ + const unsigned long page_size = self->page_size; + char *ptr, *ptr2; + struct procmap_fd procmap; + + if (variant->backing != LOCAL_FILE_BACKED) + return true; + + /* Map 10 pages. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ | PROT_WRITE, 0, 0); + if (ptr == MAP_FAILED) + return false; + /* Unmap the middle. */ + munmap(&ptr[5 * page_size], page_size); + + /* Map again. */ + ptr2 = mmap_(self, variant, &ptr[5 * page_size], page_size, PROT_READ | PROT_WRITE, + MAP_FIXED, 5 * page_size); + + if (ptr2 == MAP_FAILED) + return false; + + /* Now make sure they all merged. */ + if (open_self_procmap(&procmap) != 0) + return false; + if (!find_vma_procmap(&procmap, ptr)) + return false; + if (procmap.query.vma_start != (unsigned long)ptr) + return false; + if (procmap.query.vma_end != (unsigned long)ptr + 10 * page_size) + return false; + close_procmap(&procmap); + + return true; +} + +FIXTURE_SETUP(guard_regions) +{ + self->page_size = (unsigned long)sysconf(_SC_PAGESIZE); + setup_sighandler(); + + switch (variant->backing) { + case ANON_BACKED: + return; + case LOCAL_FILE_BACKED: + self->fd = open_file("", self->path); + break; + case SHMEM_BACKED: + self->fd = memfd_create(self->path, 0); + break; + } + + /* We truncate file to at least 100 pages, tests can modify as needed. */ + ASSERT_EQ(ftruncate(self->fd, 100 * self->page_size), 0); +}; + +FIXTURE_TEARDOWN_PARENT(guard_regions) +{ + teardown_sighandler(); + + if (variant->backing == ANON_BACKED) + return; + + if (self->fd >= 0) + close(self->fd); + + if (self->path[0] != '\0') + unlink(self->path); +} + +TEST_F(guard_regions, basic) +{ + const unsigned long NUM_PAGES = 10; + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + ptr = mmap_(self, variant, NULL, NUM_PAGES * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Trivially assert we can touch the first page. */ + ASSERT_TRUE(try_read_write_buf(ptr)); + + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + + /* Establish that 1st page SIGSEGV's. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + + /* Ensure we can touch everything else.*/ + for (i = 1; i < NUM_PAGES; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Establish a guard page at the end of the mapping. */ + ASSERT_EQ(madvise(&ptr[(NUM_PAGES - 1) * page_size], page_size, + MADV_GUARD_INSTALL), 0); + + /* Check that both guard pages result in SIGSEGV. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[(NUM_PAGES - 1) * page_size])); + + /* Remove the first guard page. */ + ASSERT_FALSE(madvise(ptr, page_size, MADV_GUARD_REMOVE)); + + /* Make sure we can touch it. */ + ASSERT_TRUE(try_read_write_buf(ptr)); + + /* Remove the last guard page. */ + ASSERT_FALSE(madvise(&ptr[(NUM_PAGES - 1) * page_size], page_size, + MADV_GUARD_REMOVE)); + + /* Make sure we can touch it. */ + ASSERT_TRUE(try_read_write_buf(&ptr[(NUM_PAGES - 1) * page_size])); + + /* + * Test setting a _range_ of pages, namely the first 3. The first of + * these be faulted in, so this also tests that we can install guard + * pages over backed pages. + */ + ASSERT_EQ(madvise(ptr, 3 * page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure they are all guard pages. */ + for (i = 0; i < 3; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Make sure the rest are not. */ + for (i = 3; i < NUM_PAGES; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Remove guard pages. */ + ASSERT_EQ(madvise(ptr, NUM_PAGES * page_size, MADV_GUARD_REMOVE), 0); + + /* Now make sure we can touch everything. */ + for (i = 0; i < NUM_PAGES; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* + * Now remove all guard pages, make sure we don't remove existing + * entries. + */ + ASSERT_EQ(madvise(ptr, NUM_PAGES * page_size, MADV_GUARD_REMOVE), 0); + + for (i = 0; i < NUM_PAGES * page_size; i += page_size) { + char chr = ptr[i]; + + ASSERT_EQ(chr, 'x'); + } + + ASSERT_EQ(munmap(ptr, NUM_PAGES * page_size), 0); +} + +/* Assert that operations applied across multiple VMAs work as expected. */ +TEST_F(guard_regions, multi_vma) +{ + const unsigned long page_size = self->page_size; + char *ptr_region, *ptr, *ptr1, *ptr2, *ptr3; + int i; + + /* Reserve a 100 page region over which we can install VMAs. */ + ptr_region = mmap_(self, variant, NULL, 100 * page_size, + PROT_NONE, 0, 0); + ASSERT_NE(ptr_region, MAP_FAILED); + + /* Place a VMA of 10 pages size at the start of the region. */ + ptr1 = mmap_(self, variant, ptr_region, 10 * page_size, + PROT_READ | PROT_WRITE, MAP_FIXED, 0); + ASSERT_NE(ptr1, MAP_FAILED); + + /* Place a VMA of 5 pages size 50 pages into the region. */ + ptr2 = mmap_(self, variant, &ptr_region[50 * page_size], 5 * page_size, + PROT_READ | PROT_WRITE, MAP_FIXED, 0); + ASSERT_NE(ptr2, MAP_FAILED); + + /* Place a VMA of 20 pages size at the end of the region. */ + ptr3 = mmap_(self, variant, &ptr_region[80 * page_size], 20 * page_size, + PROT_READ | PROT_WRITE, MAP_FIXED, 0); + ASSERT_NE(ptr3, MAP_FAILED); + + /* Unmap gaps. */ + ASSERT_EQ(munmap(&ptr_region[10 * page_size], 40 * page_size), 0); + ASSERT_EQ(munmap(&ptr_region[55 * page_size], 25 * page_size), 0); + + /* + * We end up with VMAs like this: + * + * 0 10 .. 50 55 .. 80 100 + * [---] [---] [---] + */ + + /* + * Now mark the whole range as guard pages and make sure all VMAs are as + * such. + */ + + /* + * madvise() is certifiable and lets you perform operations over gaps, + * everything works, but it indicates an error and errno is set to + * -ENOMEM. Also if anything runs out of memory it is set to + * -ENOMEM. You are meant to guess which is which. + */ + ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_INSTALL), -1); + ASSERT_EQ(errno, ENOMEM); + + for (i = 0; i < 10; i++) { + char *curr = &ptr1[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + for (i = 0; i < 5; i++) { + char *curr = &ptr2[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + for (i = 0; i < 20; i++) { + char *curr = &ptr3[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Now remove guar pages over range and assert the opposite. */ + + ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_REMOVE), -1); + ASSERT_EQ(errno, ENOMEM); + + for (i = 0; i < 10; i++) { + char *curr = &ptr1[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + for (i = 0; i < 5; i++) { + char *curr = &ptr2[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + for (i = 0; i < 20; i++) { + char *curr = &ptr3[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Now map incompatible VMAs in the gaps. */ + ptr = mmap_(self, variant, &ptr_region[10 * page_size], 40 * page_size, + PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr = mmap_(self, variant, &ptr_region[55 * page_size], 25 * page_size, + PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * We end up with VMAs like this: + * + * 0 10 .. 50 55 .. 80 100 + * [---][xxxx][---][xxxx][---] + * + * Where 'x' signifies VMAs that cannot be merged with those adjacent to + * them. + */ + + /* Multiple VMAs adjacent to one another should result in no error. */ + ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_INSTALL), 0); + for (i = 0; i < 100; i++) { + char *curr = &ptr_region[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_REMOVE), 0); + for (i = 0; i < 100; i++) { + char *curr = &ptr_region[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr_region, 100 * page_size), 0); +} + +/* + * Assert that batched operations performed using process_madvise() work as + * expected. + */ +TEST_F(guard_regions, process_madvise) +{ + const unsigned long page_size = self->page_size; + char *ptr_region, *ptr1, *ptr2, *ptr3; + ssize_t count; + struct iovec vec[6]; + + /* Reserve region to map over. */ + ptr_region = mmap_(self, variant, NULL, 100 * page_size, + PROT_NONE, 0, 0); + ASSERT_NE(ptr_region, MAP_FAILED); + + /* + * 10 pages offset 1 page into reserve region. We MAP_POPULATE so we + * overwrite existing entries and test this code path against + * overwriting existing entries. + */ + ptr1 = mmap_(self, variant, &ptr_region[page_size], 10 * page_size, + PROT_READ | PROT_WRITE, MAP_FIXED | MAP_POPULATE, 0); + ASSERT_NE(ptr1, MAP_FAILED); + /* We want guard markers at start/end of each VMA. */ + vec[0].iov_base = ptr1; + vec[0].iov_len = page_size; + vec[1].iov_base = &ptr1[9 * page_size]; + vec[1].iov_len = page_size; + + /* 5 pages offset 50 pages into reserve region. */ + ptr2 = mmap_(self, variant, &ptr_region[50 * page_size], 5 * page_size, + PROT_READ | PROT_WRITE, MAP_FIXED, 0); + ASSERT_NE(ptr2, MAP_FAILED); + vec[2].iov_base = ptr2; + vec[2].iov_len = page_size; + vec[3].iov_base = &ptr2[4 * page_size]; + vec[3].iov_len = page_size; + + /* 20 pages offset 79 pages into reserve region. */ + ptr3 = mmap_(self, variant, &ptr_region[79 * page_size], 20 * page_size, + PROT_READ | PROT_WRITE, MAP_FIXED, 0); + ASSERT_NE(ptr3, MAP_FAILED); + vec[4].iov_base = ptr3; + vec[4].iov_len = page_size; + vec[5].iov_base = &ptr3[19 * page_size]; + vec[5].iov_len = page_size; + + /* Free surrounding VMAs. */ + ASSERT_EQ(munmap(ptr_region, page_size), 0); + ASSERT_EQ(munmap(&ptr_region[11 * page_size], 39 * page_size), 0); + ASSERT_EQ(munmap(&ptr_region[55 * page_size], 24 * page_size), 0); + ASSERT_EQ(munmap(&ptr_region[99 * page_size], page_size), 0); + + /* Now guard in one step. */ + count = sys_process_madvise(PIDFD_SELF, vec, 6, MADV_GUARD_INSTALL, 0); + + /* OK we don't have permission to do this, skip. */ + if (count == -1 && errno == EPERM) + SKIP(return, "No process_madvise() permissions, try running as root.\n"); + + /* Returns the number of bytes advised. */ + ASSERT_EQ(count, 6 * page_size); + + /* Now make sure the guarding was applied. */ + + ASSERT_FALSE(try_read_write_buf(ptr1)); + ASSERT_FALSE(try_read_write_buf(&ptr1[9 * page_size])); + + ASSERT_FALSE(try_read_write_buf(ptr2)); + ASSERT_FALSE(try_read_write_buf(&ptr2[4 * page_size])); + + ASSERT_FALSE(try_read_write_buf(ptr3)); + ASSERT_FALSE(try_read_write_buf(&ptr3[19 * page_size])); + + /* Now do the same with unguard... */ + count = sys_process_madvise(PIDFD_SELF, vec, 6, MADV_GUARD_REMOVE, 0); + + /* ...and everything should now succeed. */ + + ASSERT_TRUE(try_read_write_buf(ptr1)); + ASSERT_TRUE(try_read_write_buf(&ptr1[9 * page_size])); + + ASSERT_TRUE(try_read_write_buf(ptr2)); + ASSERT_TRUE(try_read_write_buf(&ptr2[4 * page_size])); + + ASSERT_TRUE(try_read_write_buf(ptr3)); + ASSERT_TRUE(try_read_write_buf(&ptr3[19 * page_size])); + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr1, 10 * page_size), 0); + ASSERT_EQ(munmap(ptr2, 5 * page_size), 0); + ASSERT_EQ(munmap(ptr3, 20 * page_size), 0); +} + +/* Assert that unmapping ranges does not leave guard markers behind. */ +TEST_F(guard_regions, munmap) +{ + const unsigned long page_size = self->page_size; + char *ptr, *ptr_new1, *ptr_new2; + + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard first and last pages. */ + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + ASSERT_EQ(madvise(&ptr[9 * page_size], page_size, MADV_GUARD_INSTALL), 0); + + /* Assert that they are guarded. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[9 * page_size])); + + /* Unmap them. */ + ASSERT_EQ(munmap(ptr, page_size), 0); + ASSERT_EQ(munmap(&ptr[9 * page_size], page_size), 0); + + /* Map over them.*/ + ptr_new1 = mmap_(self, variant, ptr, page_size, PROT_READ | PROT_WRITE, + MAP_FIXED, 0); + ASSERT_NE(ptr_new1, MAP_FAILED); + ptr_new2 = mmap_(self, variant, &ptr[9 * page_size], page_size, + PROT_READ | PROT_WRITE, MAP_FIXED, 0); + ASSERT_NE(ptr_new2, MAP_FAILED); + + /* Assert that they are now not guarded. */ + ASSERT_TRUE(try_read_write_buf(ptr_new1)); + ASSERT_TRUE(try_read_write_buf(ptr_new2)); + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Assert that mprotect() operations have no bearing on guard markers. */ +TEST_F(guard_regions, mprotect) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard the middle of the range. */ + ASSERT_EQ(madvise(&ptr[5 * page_size], 2 * page_size, + MADV_GUARD_INSTALL), 0); + + /* Assert that it is indeed guarded. */ + ASSERT_FALSE(try_read_write_buf(&ptr[5 * page_size])); + ASSERT_FALSE(try_read_write_buf(&ptr[6 * page_size])); + + /* Now make these pages read-only. */ + ASSERT_EQ(mprotect(&ptr[5 * page_size], 2 * page_size, PROT_READ), 0); + + /* Make sure the range is still guarded. */ + ASSERT_FALSE(try_read_buf(&ptr[5 * page_size])); + ASSERT_FALSE(try_read_buf(&ptr[6 * page_size])); + + /* Make sure we can guard again without issue.*/ + ASSERT_EQ(madvise(&ptr[5 * page_size], 2 * page_size, + MADV_GUARD_INSTALL), 0); + + /* Make sure the range is, yet again, still guarded. */ + ASSERT_FALSE(try_read_buf(&ptr[5 * page_size])); + ASSERT_FALSE(try_read_buf(&ptr[6 * page_size])); + + /* Now unguard the whole range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* Make sure the whole range is readable. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Split and merge VMAs and make sure guard pages still behave. */ +TEST_F(guard_regions, split_merge) +{ + const unsigned long page_size = self->page_size; + char *ptr, *ptr_new; + int i; + + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard the whole range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure the whole range is guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Now unmap some pages in the range so we split. */ + ASSERT_EQ(munmap(&ptr[2 * page_size], page_size), 0); + ASSERT_EQ(munmap(&ptr[5 * page_size], page_size), 0); + ASSERT_EQ(munmap(&ptr[8 * page_size], page_size), 0); + + /* Make sure the remaining ranges are guarded post-split. */ + for (i = 0; i < 2; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + for (i = 2; i < 5; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + for (i = 6; i < 8; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + for (i = 9; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Now map them again - the unmap will have cleared the guards. */ + ptr_new = mmap_(self, variant, &ptr[2 * page_size], page_size, + PROT_READ | PROT_WRITE, MAP_FIXED, 0); + ASSERT_NE(ptr_new, MAP_FAILED); + ptr_new = mmap_(self, variant, &ptr[5 * page_size], page_size, + PROT_READ | PROT_WRITE, MAP_FIXED, 0); + ASSERT_NE(ptr_new, MAP_FAILED); + ptr_new = mmap_(self, variant, &ptr[8 * page_size], page_size, + PROT_READ | PROT_WRITE, MAP_FIXED, 0); + ASSERT_NE(ptr_new, MAP_FAILED); + + /* Now make sure guard pages are established. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_write_buf(curr); + bool expect_true = i == 2 || i == 5 || i == 8; + + ASSERT_TRUE(expect_true ? result : !result); + } + + /* Now guard everything again. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure the whole range is guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Now split the range into three. */ + ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ), 0); + ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size, PROT_READ), 0); + + /* Make sure the whole range is guarded for read. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_buf(curr)); + } + + /* Now reset protection bits so we merge the whole thing. */ + ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ | PROT_WRITE), 0); + ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE), 0); + + /* Make sure the whole range is still guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Split range into 3 again... */ + ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ), 0); + ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size, PROT_READ), 0); + + /* ...and unguard the whole range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* Make sure the whole range is remedied for read. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_buf(curr)); + } + + /* Merge them again. */ + ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ | PROT_WRITE), 0); + ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE), 0); + + /* Now ensure the merged range is remedied for read/write. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Assert that MADV_DONTNEED does not remove guard markers. */ +TEST_F(guard_regions, dontneed) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Back the whole range. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + *curr = 'y'; + } + + /* Guard every other page. */ + for (i = 0; i < 10; i += 2) { + char *curr = &ptr[i * page_size]; + int res = madvise(curr, page_size, MADV_GUARD_INSTALL); + + ASSERT_EQ(res, 0); + } + + /* Indicate that we don't need any of the range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_DONTNEED), 0); + + /* Check to ensure guard markers are still in place. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_buf(curr); + + if (i % 2 == 0) { + ASSERT_FALSE(result); + } else { + ASSERT_TRUE(result); + switch (variant->backing) { + case ANON_BACKED: + /* If anon, then we get a zero page. */ + ASSERT_EQ(*curr, '\0'); + break; + default: + /* Otherwise, we get the file data. */ + ASSERT_EQ(*curr, 'y'); + break; + } + } + + /* Now write... */ + result = try_write_buf(&ptr[i * page_size]); + + /* ...and make sure same result. */ + ASSERT_TRUE(i % 2 != 0 ? result : !result); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Assert that mlock()'ed pages work correctly with guard markers. */ +TEST_F(guard_regions, mlock) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Populate. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + *curr = 'y'; + } + + /* Lock. */ + ASSERT_EQ(mlock(ptr, 10 * page_size), 0); + + /* Now try to guard, should fail with EINVAL. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), -1); + ASSERT_EQ(errno, EINVAL); + + /* OK unlock. */ + ASSERT_EQ(munlock(ptr, 10 * page_size), 0); + + /* Guard first half of range, should now succeed. */ + ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure guard works. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_write_buf(curr); + + if (i < 5) { + ASSERT_FALSE(result); + } else { + ASSERT_TRUE(result); + ASSERT_EQ(*curr, 'x'); + } + } + + /* + * Now lock the latter part of the range. We can't lock the guard pages, + * as this would result in the pages being populated and the guarding + * would cause this to error out. + */ + ASSERT_EQ(mlock(&ptr[5 * page_size], 5 * page_size), 0); + + /* + * Now remove guard pages, we permit mlock()'d ranges to have guard + * pages removed as it is a non-destructive operation. + */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* Now check that no guard pages remain. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* + * Assert that moving, extending and shrinking memory via mremap() retains + * guard markers where possible. + * + * - Moving a mapping alone should retain markers as they are. + */ +TEST_F(guard_regions, mremap_move) +{ + const unsigned long page_size = self->page_size; + char *ptr, *ptr_new; + + /* Map 5 pages. */ + ptr = mmap_(self, variant, NULL, 5 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Place guard markers at both ends of the 5 page span. */ + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + ASSERT_EQ(madvise(&ptr[4 * page_size], page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure the guard pages are in effect. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size])); + + /* Map a new region we will move this range into. Doing this ensures + * that we have reserved a range to map into. + */ + ptr_new = mmap_(self, variant, NULL, 5 * page_size, PROT_NONE, 0, 0); + ASSERT_NE(ptr_new, MAP_FAILED); + + ASSERT_EQ(mremap(ptr, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr_new), ptr_new); + + /* Make sure the guard markers are retained. */ + ASSERT_FALSE(try_read_write_buf(ptr_new)); + ASSERT_FALSE(try_read_write_buf(&ptr_new[4 * page_size])); + + /* + * Clean up - we only need reference the new pointer as we overwrote the + * PROT_NONE range and moved the existing one. + */ + munmap(ptr_new, 5 * page_size); +} + +/* + * Assert that moving, extending and shrinking memory via mremap() retains + * guard markers where possible. + * + * Expanding should retain guard pages, only now in different position. The user + * will have to remove guard pages manually to fix up (they'd have to do the + * same if it were a PROT_NONE mapping). + */ +TEST_F(guard_regions, mremap_expand) +{ + const unsigned long page_size = self->page_size; + char *ptr, *ptr_new; + + /* Map 10 pages... */ + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + /* ...But unmap the last 5 so we can ensure we can expand into them. */ + ASSERT_EQ(munmap(&ptr[5 * page_size], 5 * page_size), 0); + + /* Place guard markers at both ends of the 5 page span. */ + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + ASSERT_EQ(madvise(&ptr[4 * page_size], page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure the guarding is in effect. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size])); + + /* Now expand to 10 pages. */ + ptr = mremap(ptr, 5 * page_size, 10 * page_size, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Make sure the guard markers are retained in their original positions. + */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size])); + + /* Reserve a region which we can move to and expand into. */ + ptr_new = mmap_(self, variant, NULL, 20 * page_size, PROT_NONE, 0, 0); + ASSERT_NE(ptr_new, MAP_FAILED); + + /* Now move and expand into it. */ + ptr = mremap(ptr, 10 * page_size, 20 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr_new); + ASSERT_EQ(ptr, ptr_new); + + /* + * Again, make sure the guard markers are retained in their original positions. + */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size])); + + /* + * A real user would have to remove guard markers, but would reasonably + * expect all characteristics of the mapping to be retained, including + * guard markers. + */ + + /* Cleanup. */ + munmap(ptr, 20 * page_size); +} +/* + * Assert that moving, extending and shrinking memory via mremap() retains + * guard markers where possible. + * + * Shrinking will result in markers that are shrunk over being removed. Again, + * if the user were using a PROT_NONE mapping they'd have to manually fix this + * up also so this is OK. + */ +TEST_F(guard_regions, mremap_shrink) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + /* Map 5 pages. */ + ptr = mmap_(self, variant, NULL, 5 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Place guard markers at both ends of the 5 page span. */ + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + ASSERT_EQ(madvise(&ptr[4 * page_size], page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure the guarding is in effect. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size])); + + /* Now shrink to 3 pages. */ + ptr = mremap(ptr, 5 * page_size, 3 * page_size, MREMAP_MAYMOVE); + ASSERT_NE(ptr, MAP_FAILED); + + /* We expect the guard marker at the start to be retained... */ + ASSERT_FALSE(try_read_write_buf(ptr)); + + /* ...But remaining pages will not have guard markers. */ + for (i = 1; i < 3; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* + * As with expansion, a real user would have to remove guard pages and + * fixup. But you'd have to do similar manual things with PROT_NONE + * mappings too. + */ + + /* + * If we expand back to the original size, the end marker will, of + * course, no longer be present. + */ + ptr = mremap(ptr, 3 * page_size, 5 * page_size, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Again, we expect the guard marker at the start to be retained... */ + ASSERT_FALSE(try_read_write_buf(ptr)); + + /* ...But remaining pages will not have guard markers. */ + for (i = 1; i < 5; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + munmap(ptr, 5 * page_size); +} + +/* + * Assert that forking a process with VMAs that do not have VM_WIPEONFORK set + * retain guard pages. + */ +TEST_F(guard_regions, fork) +{ + const unsigned long page_size = self->page_size; + char *ptr; + pid_t pid; + int i; + + /* Map 10 pages. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Establish guard pages in the first 5 pages. */ + ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0); + + pid = fork(); + ASSERT_NE(pid, -1); + if (!pid) { + /* This is the child process now. */ + + /* Assert that the guarding is in effect. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_write_buf(curr); + + ASSERT_TRUE(i >= 5 ? result : !result); + } + + /* Now unguard the range.*/ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + exit(0); + } + + /* Parent process. */ + + /* Parent simply waits on child. */ + waitpid(pid, NULL, 0); + + /* Child unguard does not impact parent page table state. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_write_buf(curr); + + ASSERT_TRUE(i >= 5 ? result : !result); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* + * Assert expected behaviour after we fork populated ranges of anonymous memory + * and then guard and unguard the range. + */ +TEST_F(guard_regions, fork_cow) +{ + const unsigned long page_size = self->page_size; + char *ptr; + pid_t pid; + int i; + + if (variant->backing != ANON_BACKED) + SKIP(return, "CoW only supported on anon mappings"); + + /* Map 10 pages. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 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. + */ +TEST_F(guard_regions, fork_wipeonfork) +{ + const unsigned long page_size = self->page_size; + char *ptr; + pid_t pid; + int i; + + if (variant->backing != ANON_BACKED) + SKIP(return, "Wipe on fork only supported on anon mappings"); + + /* Map 10 pages. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Mark wipe on fork. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_WIPEONFORK), 0); + + /* Guard the first 5 pages. */ + ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0); + + pid = fork(); + ASSERT_NE(pid, -1); + if (!pid) { + /* This is the child process now. */ + + /* Guard will have been wiped. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + exit(0); + } + + /* Parent process. */ + + waitpid(pid, NULL, 0); + + /* Guard markers should be in effect.*/ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_write_buf(curr); + + ASSERT_TRUE(i >= 5 ? result : !result); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Ensure that MADV_FREE retains guard entries as expected. */ +TEST_F(guard_regions, lazyfree) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + if (variant->backing != ANON_BACKED) + SKIP(return, "MADV_FREE only supported on anon mappings"); + + /* Map 10 pages. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* Ensure guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Lazyfree range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_FREE), 0); + + /* This should leave the guard markers in place. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Ensure that MADV_POPULATE_READ, MADV_POPULATE_WRITE behave as expected. */ +TEST_F(guard_regions, populate) +{ + const unsigned long page_size = self->page_size; + char *ptr; + + /* Map 10 pages. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* Populate read should error out... */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_POPULATE_READ), -1); + ASSERT_EQ(errno, EFAULT); + + /* ...as should populate write. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_POPULATE_WRITE), -1); + ASSERT_EQ(errno, EFAULT); + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Ensure that MADV_COLD, MADV_PAGEOUT do not remove guard markers. */ +TEST_F(guard_regions, cold_pageout) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + /* Map 10 pages. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* Ensured guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Now mark cold. This should have no impact on guard markers. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_COLD), 0); + + /* Should remain guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* OK, now page out. This should equally, have no effect on markers. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_PAGEOUT), 0); + + /* Should remain guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Ensure that guard pages do not break userfaultd. */ +TEST_F(guard_regions, uffd) +{ + const unsigned long page_size = self->page_size; + int uffd; + char *ptr; + int i; + struct uffdio_api api = { + .api = UFFD_API, + .features = 0, + }; + struct uffdio_register reg; + struct uffdio_range range; + + if (!is_anon_backed(variant)) + SKIP(return, "uffd only works on anon backing"); + + /* Set up uffd. */ + uffd = userfaultfd(0); + if (uffd == -1) { + switch (errno) { + case EPERM: + SKIP(return, "No userfaultfd permissions, try running as root."); + break; + case ENOSYS: + SKIP(return, "userfaultfd is not supported/not enabled."); + break; + default: + ksft_exit_fail_msg("userfaultfd failed with %s\n", + strerror(errno)); + break; + } + } + + ASSERT_NE(uffd, -1); + + ASSERT_EQ(ioctl(uffd, UFFDIO_API, &api), 0); + + /* Map 10 pages. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Register the range with uffd. */ + range.start = (unsigned long)ptr; + range.len = 10 * page_size; + reg.range = range; + reg.mode = UFFDIO_REGISTER_MODE_MISSING; + ASSERT_EQ(ioctl(uffd, UFFDIO_REGISTER, ®), 0); + + /* Guard the range. This should not trigger the uffd. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* The guarding should behave as usual with no uffd intervention. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(ioctl(uffd, UFFDIO_UNREGISTER, &range), 0); + close(uffd); + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* + * Mark a region within a file-backed mapping using MADV_SEQUENTIAL so we + * aggressively read-ahead, then install guard regions and assert that it + * behaves correctly. + * + * We page out using MADV_PAGEOUT before checking guard regions so we drop page + * cache folios, meaning we maximise the possibility of some broken readahead. + */ +TEST_F(guard_regions, madvise_sequential) +{ + char *ptr; + int i; + const unsigned long page_size = self->page_size; + + if (variant->backing == ANON_BACKED) + SKIP(return, "MADV_SEQUENTIAL meaningful only for file-backed"); + + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Establish a pattern of data in the file. */ + set_pattern(ptr, 10, page_size); + ASSERT_TRUE(check_pattern(ptr, 10, page_size)); + + /* Mark it as being accessed sequentially. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_SEQUENTIAL), 0); + + /* Mark every other page a guard page. */ + for (i = 0; i < 10; i += 2) { + char *ptr2 = &ptr[i * page_size]; + + ASSERT_EQ(madvise(ptr2, page_size, MADV_GUARD_INSTALL), 0); + } + + /* Now page it out. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_PAGEOUT), 0); + + /* Now make sure pages are as expected. */ + for (i = 0; i < 10; i++) { + char *chrp = &ptr[i * page_size]; + + if (i % 2 == 0) { + bool result = try_read_write_buf(chrp); + + ASSERT_FALSE(result); + } else { + ASSERT_EQ(*chrp, 'a' + i); + } + } + + /* Now remove guard pages. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* Now make sure all data is as expected. */ + if (!check_pattern(ptr, 10, page_size)) + ASSERT_TRUE(false); + + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* + * Check that file-backed mappings implement guard regions with MAP_PRIVATE + * correctly. + */ +TEST_F(guard_regions, map_private) +{ + const unsigned long page_size = self->page_size; + char *ptr_shared, *ptr_private; + int i; + + if (variant->backing == ANON_BACKED) + SKIP(return, "MAP_PRIVATE test specific to file-backed"); + + ptr_shared = mmap_(self, variant, NULL, 10 * page_size, PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr_shared, MAP_FAILED); + + /* Manually mmap(), do not use mmap_() wrapper so we can force MAP_PRIVATE. */ + ptr_private = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, self->fd, 0); + ASSERT_NE(ptr_private, MAP_FAILED); + + /* Set pattern in shared mapping. */ + set_pattern(ptr_shared, 10, page_size); + + /* Install guard regions in every other page in the shared mapping. */ + for (i = 0; i < 10; i += 2) { + char *ptr = &ptr_shared[i * page_size]; + + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + } + + for (i = 0; i < 10; i++) { + /* Every even shared page should be guarded. */ + ASSERT_EQ(try_read_buf(&ptr_shared[i * page_size]), i % 2 != 0); + /* Private mappings should always be readable. */ + ASSERT_TRUE(try_read_buf(&ptr_private[i * page_size])); + } + + /* Install guard regions in every other page in the private mapping. */ + for (i = 0; i < 10; i += 2) { + char *ptr = &ptr_private[i * page_size]; + + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + } + + for (i = 0; i < 10; i++) { + /* Every even shared page should be guarded. */ + ASSERT_EQ(try_read_buf(&ptr_shared[i * page_size]), i % 2 != 0); + /* Every odd private page should be guarded. */ + ASSERT_EQ(try_read_buf(&ptr_private[i * page_size]), i % 2 != 0); + } + + /* Remove guard regions from shared mapping. */ + ASSERT_EQ(madvise(ptr_shared, 10 * page_size, MADV_GUARD_REMOVE), 0); + + for (i = 0; i < 10; i++) { + /* Shared mappings should always be readable. */ + ASSERT_TRUE(try_read_buf(&ptr_shared[i * page_size])); + /* Every even private page should be guarded. */ + ASSERT_EQ(try_read_buf(&ptr_private[i * page_size]), i % 2 != 0); + } + + /* Remove guard regions from private mapping. */ + ASSERT_EQ(madvise(ptr_private, 10 * page_size, MADV_GUARD_REMOVE), 0); + + for (i = 0; i < 10; i++) { + /* Shared mappings should always be readable. */ + ASSERT_TRUE(try_read_buf(&ptr_shared[i * page_size])); + /* Private mappings should always be readable. */ + ASSERT_TRUE(try_read_buf(&ptr_private[i * page_size])); + } + + /* Ensure patterns are intact. */ + ASSERT_TRUE(check_pattern(ptr_shared, 10, page_size)); + ASSERT_TRUE(check_pattern(ptr_private, 10, page_size)); + + /* Now write out every other page to MAP_PRIVATE. */ + for (i = 0; i < 10; i += 2) { + char *ptr = &ptr_private[i * page_size]; + + memset(ptr, 'a' + i, page_size); + } + + /* + * At this point the mapping is: + * + * 0123456789 + * SPSPSPSPSP + * + * Where S = shared, P = private mappings. + */ + + /* Now mark the beginning of the mapping guarded. */ + ASSERT_EQ(madvise(ptr_private, 5 * page_size, MADV_GUARD_INSTALL), 0); + + /* + * This renders the mapping: + * + * 0123456789 + * xxxxxPSPSP + */ + + for (i = 0; i < 10; i++) { + char *ptr = &ptr_private[i * page_size]; + + /* Ensure guard regions as expected. */ + ASSERT_EQ(try_read_buf(ptr), i >= 5); + /* The shared mapping should always succeed. */ + ASSERT_TRUE(try_read_buf(&ptr_shared[i * page_size])); + } + + /* Remove the guard regions altogether. */ + ASSERT_EQ(madvise(ptr_private, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* + * + * We now expect the mapping to be: + * + * 0123456789 + * SSSSSPSPSP + * + * As we removed guard regions, the private pages from the first 5 will + * have been zapped, so on fault will reestablish the shared mapping. + */ + + for (i = 0; i < 10; i++) { + char *ptr = &ptr_private[i * page_size]; + + /* + * Assert that shared mappings in the MAP_PRIVATE mapping match + * the shared mapping. + */ + if (i < 5 || i % 2 == 0) { + char *ptr_s = &ptr_shared[i * page_size]; + + ASSERT_EQ(memcmp(ptr, ptr_s, page_size), 0); + continue; + } + + /* Everything else is a private mapping. */ + ASSERT_TRUE(is_buf_eq(ptr, page_size, 'a' + i)); + } + + ASSERT_EQ(munmap(ptr_shared, 10 * page_size), 0); + ASSERT_EQ(munmap(ptr_private, 10 * page_size), 0); +} + +/* Test that guard regions established over a read-only mapping function correctly. */ +TEST_F(guard_regions, readonly_file) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + if (variant->backing != LOCAL_FILE_BACKED) + SKIP(return, "Read-only test specific to file-backed"); + + /* Map shared so we can populate with pattern, populate it, unmap. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + set_pattern(ptr, 10, page_size); + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); + /* Close the fd so we can re-open read-only. */ + ASSERT_EQ(close(self->fd), 0); + + /* Re-open read-only. */ + self->fd = open(self->path, O_RDONLY); + ASSERT_NE(self->fd, -1); + /* Re-map read-only. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Mark every other page guarded. */ + for (i = 0; i < 10; i += 2) { + char *ptr_pg = &ptr[i * page_size]; + + ASSERT_EQ(madvise(ptr_pg, page_size, MADV_GUARD_INSTALL), 0); + } + + /* Assert that the guard regions are in place.*/ + for (i = 0; i < 10; i++) { + char *ptr_pg = &ptr[i * page_size]; + + ASSERT_EQ(try_read_buf(ptr_pg), i % 2 != 0); + } + + /* Remove guard regions. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* Ensure the data is as expected. */ + ASSERT_TRUE(check_pattern(ptr, 10, page_size)); + + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +TEST_F(guard_regions, fault_around) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + if (variant->backing == ANON_BACKED) + SKIP(return, "Fault-around test specific to file-backed"); + + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Establish a pattern in the backing file. */ + set_pattern(ptr, 10, page_size); + + /* + * Now drop it from the page cache so we get major faults when next we + * map it. + */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_PAGEOUT), 0); + + /* Unmap and remap 'to be sure'. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Now make every even page guarded. */ + for (i = 0; i < 10; i += 2) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(madvise(ptr_p, page_size, MADV_GUARD_INSTALL), 0); + } + + /* Now fault in every odd page. This should trigger fault-around. */ + for (i = 1; i < 10; i += 2) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_buf(ptr_p)); + } + + /* Finally, ensure that guard regions are intact as expected. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(try_read_buf(ptr_p), i % 2 != 0); + } + + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +TEST_F(guard_regions, truncation) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + if (variant->backing == ANON_BACKED) + SKIP(return, "Truncation test specific to file-backed"); + + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Establish a pattern in the backing file, just so there is data + * there. + */ + set_pattern(ptr, 10, page_size); + + /* Now make every even page guarded. */ + for (i = 0; i < 10; i += 2) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(madvise(ptr_p, page_size, MADV_GUARD_INSTALL), 0); + } + + /* Now assert things are as expected. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(try_read_write_buf(ptr_p), i % 2 != 0); + } + + /* Now truncate to actually used size (initialised to 100). */ + ASSERT_EQ(ftruncate(self->fd, 10 * page_size), 0); + + /* Here the guard regions will remain intact. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(try_read_write_buf(ptr_p), i % 2 != 0); + } + + /* Now truncate to half the size, then truncate again to the full size. */ + ASSERT_EQ(ftruncate(self->fd, 5 * page_size), 0); + ASSERT_EQ(ftruncate(self->fd, 10 * page_size), 0); + + /* Again, guard pages will remain intact. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(try_read_write_buf(ptr_p), i % 2 != 0); + } + + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +TEST_F(guard_regions, hole_punch) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + if (variant->backing == ANON_BACKED) + SKIP(return, "Truncation test specific to file-backed"); + + /* Establish pattern in mapping. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + set_pattern(ptr, 10, page_size); + + /* Install a guard region in the middle of the mapping. */ + ASSERT_EQ(madvise(&ptr[3 * page_size], 4 * page_size, + MADV_GUARD_INSTALL), 0); + + /* + * The buffer will now be: + * + * 0123456789 + * ***xxxx*** + * + * Where * is data and x is the guard region. + */ + + /* Ensure established. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(try_read_buf(ptr_p), i < 3 || i >= 7); + } + + /* Now hole punch the guarded region. */ + ASSERT_EQ(madvise(&ptr[3 * page_size], 4 * page_size, + MADV_REMOVE), 0); + + /* Ensure guard regions remain. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(try_read_buf(ptr_p), i < 3 || i >= 7); + } + + /* Now remove guard region throughout. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* Check that the pattern exists in non-hole punched region. */ + ASSERT_TRUE(check_pattern(ptr, 3, page_size)); + /* Check that hole punched region is zeroed. */ + ASSERT_TRUE(is_buf_eq(&ptr[3 * page_size], 4 * page_size, '\0')); + /* Check that the pattern exists in the remainder of the file. */ + ASSERT_TRUE(check_pattern_offset(ptr, 3, page_size, 7)); + + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* + * Ensure that a memfd works correctly with guard regions, that we can write + * seal it then open the mapping read-only and still establish guard regions + * within, remove those guard regions and have everything work correctly. + */ +TEST_F(guard_regions, memfd_write_seal) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + if (variant->backing != SHMEM_BACKED) + SKIP(return, "memfd write seal test specific to shmem"); + + /* OK, we need a memfd, so close existing one. */ + ASSERT_EQ(close(self->fd), 0); + + /* Create and truncate memfd. */ + self->fd = memfd_create("guard_regions_memfd_seals_test", + MFD_ALLOW_SEALING); + ASSERT_NE(self->fd, -1); + ASSERT_EQ(ftruncate(self->fd, 10 * page_size), 0); + + /* Map, set pattern, unmap. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + set_pattern(ptr, 10, page_size); + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); + + /* Write-seal the memfd. */ + ASSERT_EQ(fcntl(self->fd, F_ADD_SEALS, F_SEAL_WRITE), 0); + + /* Now map the memfd readonly. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Ensure pattern is as expected. */ + ASSERT_TRUE(check_pattern(ptr, 10, page_size)); + + /* Now make every even page guarded. */ + for (i = 0; i < 10; i += 2) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(madvise(ptr_p, page_size, MADV_GUARD_INSTALL), 0); + } + + /* Now assert things are as expected. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(try_read_buf(ptr_p), i % 2 != 0); + } + + /* Now remove guard regions. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* Ensure pattern is as expected. */ + ASSERT_TRUE(check_pattern(ptr, 10, page_size)); + + /* Ensure write seal intact. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_FALSE(try_write_buf(ptr_p)); + } + + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + + +/* + * Since we are now permitted to establish guard regions in read-only anonymous + * mappings, for the sake of thoroughness, though it probably has no practical + * use, test that guard regions function with a mapping to the anonymous zero + * page. + */ +TEST_F(guard_regions, anon_zeropage) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + if (!is_anon_backed(variant)) + SKIP(return, "anon zero page test specific to anon/shmem"); + + /* Obtain a read-only i.e. anon zero page mapping. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Now make every even page guarded. */ + for (i = 0; i < 10; i += 2) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(madvise(ptr_p, page_size, MADV_GUARD_INSTALL), 0); + } + + /* Now assert things are as expected. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(try_read_buf(ptr_p), i % 2 != 0); + } + + /* Now remove all guard regions. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* Now assert things are as expected. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_buf(ptr_p)); + } + + /* Ensure zero page...*/ + ASSERT_TRUE(is_buf_eq(ptr, 10 * page_size, '\0')); + + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* + * Assert that /proc/$pid/pagemap correctly identifies guard region ranges. + */ +TEST_F(guard_regions, pagemap) +{ + const unsigned long page_size = self->page_size; + int proc_fd; + char *ptr; + int i; + + proc_fd = open("/proc/self/pagemap", O_RDONLY); + ASSERT_NE(proc_fd, -1); + + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Read from pagemap, and assert no guard regions are detected. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + unsigned long entry = pagemap_get_entry(proc_fd, ptr_p); + unsigned long masked = entry & PM_GUARD_REGION; + + ASSERT_EQ(masked, 0); + } + + /* Install a guard region in every other page. */ + for (i = 0; i < 10; i += 2) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(madvise(ptr_p, page_size, MADV_GUARD_INSTALL), 0); + } + + /* Re-read from pagemap, and assert guard regions are detected. */ + for (i = 0; i < 10; i++) { + char *ptr_p = &ptr[i * page_size]; + unsigned long entry = pagemap_get_entry(proc_fd, ptr_p); + unsigned long masked = entry & PM_GUARD_REGION; + + ASSERT_EQ(masked, i % 2 == 0 ? PM_GUARD_REGION : 0); + } + + ASSERT_EQ(close(proc_fd), 0); + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* + * Assert that PAGEMAP_SCAN correctly reports guard region ranges. + */ +TEST_F(guard_regions, pagemap_scan) +{ + const unsigned long page_size = self->page_size; + struct page_region pm_regs[10]; + struct pm_scan_arg pm_scan_args = { + .size = sizeof(struct pm_scan_arg), + .category_anyof_mask = PAGE_IS_GUARD, + .return_mask = PAGE_IS_GUARD, + .vec = (long)&pm_regs, + .vec_len = ARRAY_SIZE(pm_regs), + }; + int proc_fd, i; + char *ptr; + + proc_fd = open("/proc/self/pagemap", O_RDONLY); + ASSERT_NE(proc_fd, -1); + + ptr = mmap_(self, variant, NULL, 10 * page_size, + PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + pm_scan_args.start = (long)ptr; + pm_scan_args.end = (long)ptr + 10 * page_size; + ASSERT_EQ(ioctl(proc_fd, PAGEMAP_SCAN, &pm_scan_args), 0); + ASSERT_EQ(pm_scan_args.walk_end, (long)ptr + 10 * page_size); + + /* Install a guard region in every other page. */ + for (i = 0; i < 10; i += 2) { + char *ptr_p = &ptr[i * page_size]; + + ASSERT_EQ(syscall(__NR_madvise, ptr_p, page_size, MADV_GUARD_INSTALL), 0); + } + + /* + * Assert ioctl() returns the count of located regions, where each + * region spans every other page within the range of 10 pages. + */ + ASSERT_EQ(ioctl(proc_fd, PAGEMAP_SCAN, &pm_scan_args), 5); + ASSERT_EQ(pm_scan_args.walk_end, (long)ptr + 10 * page_size); + + /* Re-read from pagemap, and assert guard regions are detected. */ + for (i = 0; i < 5; i++) { + long ptr_p = (long)&ptr[2 * i * page_size]; + + ASSERT_EQ(pm_regs[i].start, ptr_p); + ASSERT_EQ(pm_regs[i].end, ptr_p + page_size); + ASSERT_EQ(pm_regs[i].categories, PAGE_IS_GUARD); + } + + ASSERT_EQ(close(proc_fd), 0); + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +TEST_F(guard_regions, collapse) +{ + const unsigned long page_size = self->page_size; + const unsigned long size = 2 * HPAGE_SIZE; + const unsigned long num_pages = size / page_size; + char *ptr; + int i; + + /* Need file to be correct size for tests for non-anon. */ + if (variant->backing != ANON_BACKED) + ASSERT_EQ(ftruncate(self->fd, size), 0); + + /* + * We must close and re-open local-file backed as read-only for + * CONFIG_READ_ONLY_THP_FOR_FS to work. + */ + if (variant->backing == LOCAL_FILE_BACKED) { + ASSERT_EQ(close(self->fd), 0); + + self->fd = open(self->path, O_RDONLY); + ASSERT_GE(self->fd, 0); + } + + ptr = mmap_(self, variant, NULL, size, PROT_READ, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Prevent being faulted-in as huge. */ + ASSERT_EQ(madvise(ptr, size, MADV_NOHUGEPAGE), 0); + /* Fault in. */ + ASSERT_EQ(madvise(ptr, size, MADV_POPULATE_READ), 0); + + /* Install guard regions in ever other page. */ + for (i = 0; i < num_pages; i += 2) { + char *ptr_page = &ptr[i * page_size]; + + ASSERT_EQ(madvise(ptr_page, page_size, MADV_GUARD_INSTALL), 0); + /* Accesses should now fail. */ + ASSERT_FALSE(try_read_buf(ptr_page)); + } + + /* Allow huge page throughout region. */ + ASSERT_EQ(madvise(ptr, size, MADV_HUGEPAGE), 0); + + /* + * Now collapse the entire region. This should fail in all cases. + * + * The madvise() call will also fail if CONFIG_READ_ONLY_THP_FOR_FS is + * not set for the local file case, but we can't differentiate whether + * this occurred or if the collapse was rightly rejected. + */ + EXPECT_NE(madvise(ptr, size, MADV_COLLAPSE), 0); + + /* + * If we introduce a bug that causes the collapse to succeed, gather + * data on whether guard regions are at least preserved. The test will + * fail at this point in any case. + */ + for (i = 0; i < num_pages; i += 2) { + char *ptr_page = &ptr[i * page_size]; + + /* Accesses should still fail. */ + ASSERT_FALSE(try_read_buf(ptr_page)); + } +} + +TEST_F(guard_regions, smaps) +{ + const unsigned long page_size = self->page_size; + struct procmap_fd procmap; + char *ptr, *ptr2; + int i; + + /* Map a region. */ + ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ | PROT_WRITE, 0, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* We shouldn't yet see a guard flag. */ + ASSERT_FALSE(check_vmflag_guard(ptr)); + + /* Install a single guard region. */ + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + + /* Now we should see a guard flag. */ + ASSERT_TRUE(check_vmflag_guard(ptr)); + + /* + * Removing the guard region should not change things because we simply + * cannot accurately track whether a given VMA has had all of its guard + * regions removed. + */ + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_REMOVE), 0); + ASSERT_TRUE(check_vmflag_guard(ptr)); + + /* Install guard regions throughout. */ + for (i = 0; i < 10; i++) { + ASSERT_EQ(madvise(&ptr[i * page_size], page_size, MADV_GUARD_INSTALL), 0); + /* We should always see the guard region flag. */ + ASSERT_TRUE(check_vmflag_guard(ptr)); + } + + /* Split into two VMAs. */ + ASSERT_EQ(munmap(&ptr[4 * page_size], page_size), 0); + + /* Both VMAs should have the guard flag set. */ + ASSERT_TRUE(check_vmflag_guard(ptr)); + ASSERT_TRUE(check_vmflag_guard(&ptr[5 * page_size])); + + /* + * If the local file system is unable to merge VMAs due to having + * unusual characteristics, there is no point in asserting merge + * behaviour. + */ + if (!local_fs_has_sane_mmap(self, variant)) { + TH_LOG("local filesystem does not support sane merging skipping merge test"); + return; + } + + /* Map a fresh VMA between the two split VMAs. */ + ptr2 = mmap_(self, variant, &ptr[4 * page_size], page_size, + PROT_READ | PROT_WRITE, MAP_FIXED, 4 * page_size); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Check the procmap to ensure that this VMA merged with the adjacent + * two. The guard region flag is 'sticky' so should not preclude + * merging. + */ + ASSERT_EQ(open_self_procmap(&procmap), 0); + ASSERT_TRUE(find_vma_procmap(&procmap, ptr)); + ASSERT_EQ(procmap.query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap.query.vma_end, (unsigned long)ptr + 10 * page_size); + ASSERT_EQ(close_procmap(&procmap), 0); + /* And, of course, this VMA should have the guard flag set. */ + ASSERT_TRUE(check_vmflag_guard(ptr)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c index d33d3e68ffab..6279893a0adc 100644 --- a/tools/testing/selftests/mm/gup_longterm.c +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -27,7 +27,7 @@ #endif /* LOCAL_CONFIG_HAVE_LIBURING */ #include "../../../../mm/gup_test.h" -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" static size_t pagesize; @@ -93,40 +93,75 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) __fsword_t fs_type = get_fs_type(fd); bool should_work; char *mem; + int result = KSFT_PASS; int ret; + if (fd < 0) { + result = KSFT_FAIL; + goto report; + } + if (ftruncate(fd, size)) { - ksft_test_result_fail("ftruncate() failed\n"); + if (errno == ENOENT) { + skip_test_dodgy_fs("ftruncate()"); + } else { + ksft_print_msg("ftruncate() failed (%s)\n", + strerror(errno)); + result = KSFT_FAIL; + goto report; + } return; } if (fallocate(fd, 0, 0, size)) { - if (size == pagesize) - ksft_test_result_fail("fallocate() failed\n"); - else - ksft_test_result_skip("need more free huge pages\n"); - return; + /* + * Some filesystems (eg, NFSv3) don't support + * fallocate(), report this as a skip rather than a + * test failure. + */ + if (errno == EOPNOTSUPP) { + ksft_print_msg("fallocate() not supported by filesystem\n"); + result = KSFT_SKIP; + } else if (size == pagesize) { + ksft_print_msg("fallocate() failed (%s)\n", strerror(errno)); + result = KSFT_FAIL; + } else { + ksft_print_msg("need more free huge pages\n"); + result = KSFT_SKIP; + } + goto report; } mem = mmap(NULL, size, PROT_READ | PROT_WRITE, shared ? MAP_SHARED : MAP_PRIVATE, fd, 0); if (mem == MAP_FAILED) { - if (size == pagesize || shared) - ksft_test_result_fail("mmap() failed\n"); - else - ksft_test_result_skip("need more free huge pages\n"); - return; + if (size == pagesize || shared) { + ksft_print_msg("mmap() failed (%s)\n", strerror(errno)); + result = KSFT_FAIL; + } else { + ksft_print_msg("need more free huge pages\n"); + result = KSFT_SKIP; + } + goto report; } - /* - * Fault in the page writable such that GUP-fast can eventually pin - * it immediately. - */ + /* Fault in the page such that GUP-fast can pin it directly. */ memset(mem, 0, size); switch (type) { case TEST_TYPE_RO: case TEST_TYPE_RO_FAST: + /* + * Cover more cases regarding unsharing decisions when + * long-term R/O pinning by mapping the page R/O. + */ + ret = mprotect(mem, size, PROT_READ); + if (ret) { + ksft_print_msg("mprotect() failed (%s)\n", strerror(errno)); + result = KSFT_FAIL; + goto munmap; + } + /* FALLTHROUGH */ case TEST_TYPE_RW: case TEST_TYPE_RW_FAST: { struct pin_longterm_test args; @@ -136,18 +171,20 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) type == TEST_TYPE_RW_FAST; if (gup_fd < 0) { - ksft_test_result_skip("gup_test not available\n"); + ksft_print_msg("gup_test not available\n"); + result = KSFT_SKIP; break; } if (rw && shared && fs_is_unknown(fs_type)) { - ksft_test_result_skip("Unknown filesystem\n"); + ksft_print_msg("Unknown filesystem\n"); + result = KSFT_SKIP; return; } /* * R/O pinning or pinning in a private mapping is always * expected to work. Otherwise, we expect long-term R/W pinning - * to only succeed for special fielesystems. + * to only succeed for special filesystems. */ should_work = !shared || !rw || fs_supports_writable_longterm_pinning(fs_type); @@ -158,25 +195,35 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) args.flags |= rw ? PIN_LONGTERM_TEST_FLAG_USE_WRITE : 0; ret = ioctl(gup_fd, PIN_LONGTERM_TEST_START, &args); if (ret && errno == EINVAL) { - ksft_test_result_skip("PIN_LONGTERM_TEST_START failed\n"); + ksft_print_msg("PIN_LONGTERM_TEST_START failed (EINVAL)n"); + result = KSFT_SKIP; break; } else if (ret && errno == EFAULT) { - ksft_test_result(!should_work, "Should have failed\n"); + if (should_work) + result = KSFT_FAIL; + else + result = KSFT_PASS; break; } else if (ret) { - ksft_test_result_fail("PIN_LONGTERM_TEST_START failed\n"); + ksft_print_msg("PIN_LONGTERM_TEST_START failed (%s)\n", + strerror(errno)); + result = KSFT_FAIL; break; } if (ioctl(gup_fd, PIN_LONGTERM_TEST_STOP)) - ksft_print_msg("[INFO] PIN_LONGTERM_TEST_STOP failed\n"); + ksft_print_msg("[INFO] PIN_LONGTERM_TEST_STOP failed (%s)\n", + strerror(errno)); /* * TODO: if the kernel ever supports long-term R/W pinning on * some previously unsupported filesystems, we might want to * perform some additional tests for possible data corruptions. */ - ksft_test_result(should_work, "Should have worked\n"); + if (should_work) + result = KSFT_PASS; + else + result = KSFT_FAIL; break; } #ifdef LOCAL_CONFIG_HAVE_LIBURING @@ -186,8 +233,9 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) /* io_uring always pins pages writable. */ if (shared && fs_is_unknown(fs_type)) { - ksft_test_result_skip("Unknown filesystem\n"); - return; + ksft_print_msg("Unknown filesystem\n"); + result = KSFT_SKIP; + goto report; } should_work = !shared || fs_supports_writable_longterm_pinning(fs_type); @@ -195,7 +243,9 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) /* Skip on errors, as we might just lack kernel support. */ ret = io_uring_queue_init(1, &ring, 0); if (ret < 0) { - ksft_test_result_skip("io_uring_queue_init() failed\n"); + ksft_print_msg("io_uring_queue_init() failed (%s)\n", + strerror(-ret)); + result = KSFT_SKIP; break; } /* @@ -208,15 +258,28 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) /* Only new kernels return EFAULT. */ if (ret && (errno == ENOSPC || errno == EOPNOTSUPP || errno == EFAULT)) { - ksft_test_result(!should_work, "Should have failed\n"); + if (should_work) { + ksft_print_msg("Should have failed (%s)\n", + strerror(errno)); + result = KSFT_FAIL; + } else { + result = KSFT_PASS; + } } else if (ret) { /* * We might just lack support or have insufficient * MEMLOCK limits. */ - ksft_test_result_skip("io_uring_register_buffers() failed\n"); + ksft_print_msg("io_uring_register_buffers() failed (%s)\n", + strerror(-ret)); + result = KSFT_SKIP; } else { - ksft_test_result(should_work, "Should have worked\n"); + if (should_work) { + result = KSFT_PASS; + } else { + ksft_print_msg("Should have worked\n"); + result = KSFT_FAIL; + } io_uring_unregister_buffers(&ring); } @@ -228,7 +291,10 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) assert(false); } +munmap: munmap(mem, size); +report: + log_test_result(result); } typedef void (*test_fn)(int fd, size_t size); @@ -237,11 +303,12 @@ static void run_with_memfd(test_fn fn, const char *desc) { int fd; - ksft_print_msg("[RUN] %s ... with memfd\n", desc); + log_test_start("%s ... with memfd", desc); fd = memfd_create("test", 0); if (fd < 0) { - ksft_test_result_fail("memfd_create() failed\n"); + ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno)); + log_test_result(KSFT_SKIP); return; } @@ -254,22 +321,23 @@ static void run_with_tmpfile(test_fn fn, const char *desc) FILE *file; int fd; - ksft_print_msg("[RUN] %s ... with tmpfile\n", desc); + log_test_start("%s ... with tmpfile", desc); file = tmpfile(); if (!file) { - ksft_test_result_fail("tmpfile() failed\n"); - return; - } - - fd = fileno(file); - if (fd < 0) { - ksft_test_result_fail("fileno() failed\n"); - return; + ksft_print_msg("tmpfile() failed (%s)\n", strerror(errno)); + fd = -1; + } else { + fd = fileno(file); + if (fd < 0) { + ksft_print_msg("fileno() failed (%s)\n", strerror(errno)); + } } fn(fd, pagesize); - fclose(file); + + if (file) + fclose(file); } static void run_with_local_tmpfile(test_fn fn, const char *desc) @@ -277,22 +345,22 @@ static void run_with_local_tmpfile(test_fn fn, const char *desc) char filename[] = __FILE__"_tmpfile_XXXXXX"; int fd; - ksft_print_msg("[RUN] %s ... with local tmpfile\n", desc); + log_test_start("%s ... with local tmpfile", desc); fd = mkstemp(filename); - if (fd < 0) { - ksft_test_result_fail("mkstemp() failed\n"); - return; - } + if (fd < 0) + ksft_print_msg("mkstemp() failed (%s)\n", strerror(errno)); if (unlink(filename)) { - ksft_test_result_fail("unlink() failed\n"); - goto close; + ksft_print_msg("unlink() failed (%s)\n", strerror(errno)); + close(fd); + fd = -1; } fn(fd, pagesize); -close: - close(fd); + + if (fd >= 0) + close(fd); } static void run_with_memfd_hugetlb(test_fn fn, const char *desc, @@ -301,14 +369,15 @@ static void run_with_memfd_hugetlb(test_fn fn, const char *desc, int flags = MFD_HUGETLB; int fd; - ksft_print_msg("[RUN] %s ... with memfd hugetlb (%zu kB)\n", desc, + log_test_start("%s ... with memfd hugetlb (%zu kB)", desc, hugetlbsize / 1024); flags |= __builtin_ctzll(hugetlbsize) << MFD_HUGE_SHIFT; fd = memfd_create("test", flags); if (fd < 0) { - ksft_test_result_skip("memfd_create() failed\n"); + ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno)); + log_test_result(KSFT_SKIP); return; } @@ -437,7 +506,7 @@ static int tests_per_test_case(void) int main(int argc, char **argv) { - int i, err; + int i; pagesize = getpagesize(); nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, @@ -451,9 +520,5 @@ int main(int argc, char **argv) for (i = 0; i < ARRAY_SIZE(test_cases); i++) run_test_case(&test_cases[i]); - err = ksft_get_fail_cnt(); - if (err) - ksft_exit_fail_msg("%d out of %d tests failed\n", - err, ksft_test_num()); - return ksft_exit_pass(); + ksft_finished(); } diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c index ec2229136384..fb8f9ae49efa 100644 --- a/tools/testing/selftests/mm/gup_test.c +++ b/tools/testing/selftests/mm/gup_test.c @@ -1,3 +1,4 @@ +#define __SANE_USERSPACE_TYPES__ // Use ll64 #include <fcntl.h> #include <errno.h> #include <stdio.h> @@ -11,14 +12,13 @@ #include <pthread.h> #include <assert.h> #include <mm/gup_test.h> -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" #define MB (1UL << 20) -/* Just the flags we need, copied from mm.h: */ +/* Just the flags we need, copied from the kernel internals. */ #define FOLL_WRITE 0x01 /* check pte is writable */ -#define FOLL_TOUCH 0x02 /* mark page accessed */ #define GUP_TEST_FILE "/sys/kernel/debug/gup_test" @@ -50,39 +50,41 @@ static char *cmd_to_str(unsigned long cmd) void *gup_thread(void *data) { struct gup_test gup = *(struct gup_test *)data; - int i; + int i, status; /* Only report timing information on the *_BENCHMARK commands: */ if ((cmd == PIN_FAST_BENCHMARK) || (cmd == GUP_FAST_BENCHMARK) || (cmd == PIN_LONGTERM_BENCHMARK)) { for (i = 0; i < repeats; i++) { gup.size = size; - if (ioctl(gup_fd, cmd, &gup)) - perror("ioctl"), exit(1); + status = ioctl(gup_fd, cmd, &gup); + if (status) + break; pthread_mutex_lock(&print_mutex); - printf("%s: Time: get:%lld put:%lld us", - cmd_to_str(cmd), gup.get_delta_usec, - gup.put_delta_usec); + ksft_print_msg("%s: Time: get:%lld put:%lld us", + cmd_to_str(cmd), gup.get_delta_usec, + gup.put_delta_usec); if (gup.size != size) - printf(", truncated (size: %lld)", gup.size); - printf("\n"); + ksft_print_msg(", truncated (size: %lld)", gup.size); + ksft_print_msg("\n"); pthread_mutex_unlock(&print_mutex); } } else { gup.size = size; - if (ioctl(gup_fd, cmd, &gup)) { - perror("ioctl"); - exit(1); - } + status = ioctl(gup_fd, cmd, &gup); + if (status) + goto return_; pthread_mutex_lock(&print_mutex); - printf("%s: done\n", cmd_to_str(cmd)); + ksft_print_msg("%s: done\n", cmd_to_str(cmd)); if (gup.size != size) - printf("Truncated (size: %lld)\n", gup.size); + ksft_print_msg("Truncated (size: %lld)\n", gup.size); pthread_mutex_unlock(&print_mutex); } +return_: + ksft_test_result(!status, "ioctl status %d\n", status); return NULL; } @@ -90,7 +92,7 @@ int main(int argc, char **argv) { struct gup_test gup = { 0 }; int filed, i, opt, nr_pages = 1, thp = -1, write = 1, nthreads = 1, ret; - int flags = MAP_PRIVATE, touch = 0; + int flags = MAP_PRIVATE; char *file = "/dev/zero"; pthread_t *tid; char *p; @@ -136,6 +138,8 @@ int main(int argc, char **argv) break; case 'n': nr_pages = atoi(optarg); + if (nr_pages < 0) + nr_pages = size / psize(); break; case 't': thp = 1; @@ -165,12 +169,8 @@ int main(int argc, char **argv) case 'H': flags |= (MAP_HUGETLB | MAP_ANONYMOUS); break; - case 'z': - /* fault pages in gup, do not fault in userland */ - touch = 1; - break; default: - return -1; + ksft_exit_fail_msg("Wrong argument\n"); } } @@ -198,11 +198,12 @@ int main(int argc, char **argv) } } - filed = open(file, O_RDWR|O_CREAT); - if (filed < 0) { - perror("open"); - exit(filed); - } + ksft_print_header(); + ksft_set_plan(nthreads); + + filed = open(file, O_RDWR|O_CREAT, 0664); + if (filed < 0) + ksft_exit_fail_msg("Unable to open %s: %s\n", file, strerror(errno)); gup.nr_pages_per_call = nr_pages; if (write) @@ -213,27 +214,24 @@ int main(int argc, char **argv) switch (errno) { case EACCES: if (getuid()) - printf("Please run this test as root\n"); + ksft_print_msg("Please run this test as root\n"); break; case ENOENT: - if (opendir("/sys/kernel/debug") == NULL) { - printf("mount debugfs at /sys/kernel/debug\n"); - break; - } - printf("check if CONFIG_GUP_TEST is enabled in kernel config\n"); + if (opendir("/sys/kernel/debug") == NULL) + ksft_print_msg("mount debugfs at /sys/kernel/debug\n"); + ksft_print_msg("check if CONFIG_GUP_TEST is enabled in kernel config\n"); break; default: - perror("failed to open " GUP_TEST_FILE); + ksft_print_msg("failed to open %s: %s\n", GUP_TEST_FILE, strerror(errno)); break; } - exit(KSFT_SKIP); + ksft_test_result_skip("Please run this test as root\n"); + ksft_exit_pass(); } p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0); - if (p == MAP_FAILED) { - perror("mmap"); - exit(1); - } + if (p == MAP_FAILED) + ksft_exit_fail_msg("mmap: %s\n", strerror(errno)); gup.addr = (unsigned long)p; if (thp == 1) @@ -241,18 +239,9 @@ int main(int argc, char **argv) else if (thp == 0) madvise(p, size, MADV_NOHUGEPAGE); - /* - * FOLL_TOUCH, in gup_test, is used as an either/or case: either - * fault pages in from the kernel via FOLL_TOUCH, or fault them - * in here, from user space. This allows comparison of performance - * between those two cases. - */ - if (touch) { - gup.gup_flags |= FOLL_TOUCH; - } else { - for (; (unsigned long)p < gup.addr + size; p += psize()) - p[0] = 0; - } + /* Fault them in here, from user space. */ + for (; (unsigned long)p < gup.addr + size; p += psize()) + p[0] = 0; tid = malloc(sizeof(pthread_t) * nthreads); assert(tid); @@ -264,7 +253,8 @@ int main(int argc, char **argv) ret = pthread_join(tid[i], NULL); assert(ret == 0); } + free(tid); - return 0; + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index 4adaad1b822f..e8328c89d855 100644 --- a/tools/testing/selftests/mm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c @@ -10,7 +10,7 @@ * bugs. */ -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include <errno.h> #include <fcntl.h> @@ -25,6 +25,7 @@ #include <sys/stat.h> #include <sys/mman.h> #include <sys/ioctl.h> +#include <sys/time.h> /* @@ -50,6 +51,8 @@ enum { HMM_COHERENCE_DEVICE_TWO, }; +#define ONEKB (1 << 10) +#define ONEMEG (1 << 20) #define TWOMEG (1 << 21) #define HMM_BUFFER_SIZE (1024 << 12) #define HMM_PATH_MAX 64 @@ -57,9 +60,14 @@ enum { #define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1))) /* Just the flags we need, copied from mm.h: */ + +#ifndef FOLL_WRITE #define FOLL_WRITE 0x01 /* check pte is writable */ -#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite */ +#endif +#ifndef FOLL_LONGTERM +#define FOLL_LONGTERM 0x100 /* mapping lifetime is indefinite */ +#endif FIXTURE(hmm) { int fd; @@ -133,7 +141,7 @@ FIXTURE_SETUP(hmm) self->fd = hmm_open(variant->device_number); if (self->fd < 0 && hmm_is_coherent_type(variant->device_number)) - SKIP(exit(0), "DEVICE_COHERENT not available"); + SKIP(return, "DEVICE_COHERENT not available"); ASSERT_GE(self->fd, 0); } @@ -144,7 +152,7 @@ FIXTURE_SETUP(hmm2) self->fd0 = hmm_open(variant->device_number0); if (self->fd0 < 0 && hmm_is_coherent_type(variant->device_number0)) - SKIP(exit(0), "DEVICE_COHERENT not available"); + SKIP(return, "DEVICE_COHERENT not available"); ASSERT_GE(self->fd0, 0); self->fd1 = hmm_open(variant->device_number1); ASSERT_GE(self->fd1, 0); @@ -202,8 +210,10 @@ static void hmm_buffer_free(struct hmm_buffer *buffer) if (buffer == NULL) return; - if (buffer->ptr) + if (buffer->ptr) { munmap(buffer->ptr, buffer->size); + buffer->ptr = NULL; + } free(buffer->mirror); free(buffer); } @@ -520,6 +530,8 @@ TEST_F(hmm, anon_write_prot) /* * Check that a device writing an anonymous private mapping * will copy-on-write if a child process inherits the mapping. + * + * Also verifies after fork() memory the device can be read by child. */ TEST_F(hmm, anon_write_child) { @@ -527,72 +539,101 @@ TEST_F(hmm, anon_write_child) unsigned long npages; unsigned long size; unsigned long i; + void *old_ptr; + void *map; int *ptr; pid_t pid; int child_fd; - int ret; - - npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift; - ASSERT_NE(npages, 0); - size = npages << self->page_shift; - - buffer = malloc(sizeof(*buffer)); - ASSERT_NE(buffer, NULL); - - buffer->fd = -1; - buffer->size = size; - buffer->mirror = malloc(size); - ASSERT_NE(buffer->mirror, NULL); - - buffer->ptr = mmap(NULL, size, - PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, - buffer->fd, 0); - ASSERT_NE(buffer->ptr, MAP_FAILED); - - /* Initialize buffer->ptr so we can tell if it is written. */ - for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) - ptr[i] = i; - - /* Initialize data that the device will write to buffer->ptr. */ - for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) - ptr[i] = -i; + int ret, use_thp, migrate; + + for (migrate = 0; migrate < 2; ++migrate) { + for (use_thp = 0; use_thp < 2; ++use_thp) { + npages = ALIGN(use_thp ? TWOMEG : HMM_BUFFER_SIZE, + self->page_size) >> self->page_shift; + ASSERT_NE(npages, 0); + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size * 2; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size * 2, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + old_ptr = buffer->ptr; + if (use_thp) { + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + buffer->ptr = map; + } + + /* Initialize buffer->ptr so we can tell if it is written. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Initialize data that the device will write to buffer->ptr. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ptr[i] = -i; + + if (migrate) { + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + } + + pid = fork(); + if (pid == -1) + ASSERT_EQ(pid, 0); + if (pid != 0) { + waitpid(pid, &ret, 0); + ASSERT_EQ(WIFEXITED(ret), 1); + + /* Check that the parent's buffer did not change. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); + continue; + } + + /* Check that we see the parent's values. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + if (!migrate) { + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], -i); + } + + /* The child process needs its own mirror to its own mm. */ + child_fd = hmm_open(0); + ASSERT_GE(child_fd, 0); + + /* Simulate a device writing system memory. */ + ret = hmm_dmirror_cmd(child_fd, HMM_DMIRROR_WRITE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + ASSERT_EQ(buffer->faults, 1); - pid = fork(); - if (pid == -1) - ASSERT_EQ(pid, 0); - if (pid != 0) { - waitpid(pid, &ret, 0); - ASSERT_EQ(WIFEXITED(ret), 1); + /* Check what the device wrote. */ + if (!migrate) { + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], -i); + } - /* Check that the parent's buffer did not change. */ - for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) - ASSERT_EQ(ptr[i], i); - return; + close(child_fd); + exit(0); + } } - - /* Check that we see the parent's values. */ - for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) - ASSERT_EQ(ptr[i], i); - for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) - ASSERT_EQ(ptr[i], -i); - - /* The child process needs its own mirror to its own mm. */ - child_fd = hmm_open(0); - ASSERT_GE(child_fd, 0); - - /* Simulate a device writing system memory. */ - ret = hmm_dmirror_cmd(child_fd, HMM_DMIRROR_WRITE, buffer, npages); - ASSERT_EQ(ret, 0); - ASSERT_EQ(buffer->cpages, npages); - ASSERT_EQ(buffer->faults, 1); - - /* Check what the device wrote. */ - for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) - ASSERT_EQ(ptr[i], -i); - - close(child_fd); - exit(0); } /* @@ -1652,7 +1693,7 @@ TEST_F(hmm2, double_map) buffer->fd = -1; buffer->size = size; - buffer->mirror = malloc(npages); + buffer->mirror = malloc(size); ASSERT_NE(buffer->mirror, NULL); /* Reserve a range of addresses. */ @@ -2022,11 +2063,10 @@ TEST_F(hmm, hmm_cow_in_device) if (pid == -1) ASSERT_EQ(pid, 0); if (!pid) { - /* Child process waitd for SIGTERM from the parent. */ + /* Child process waits for SIGTERM from the parent. */ while (1) { } - perror("Should not reach this\n"); - exit(0); + /* Should not reach this */ } /* Parent process writes to COW pages(s) and gets a * new copy in system. In case of device private pages, @@ -2051,4 +2091,765 @@ TEST_F(hmm, hmm_cow_in_device) hmm_buffer_free(buffer); } + +/* + * Migrate private anonymous huge empty page. + */ +TEST_F(hmm, migrate_anon_huge_empty) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret; + + size = TWOMEG; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, size); + + buffer->ptr = mmap(NULL, 2 * size, + PROT_READ, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + old_ptr = buffer->ptr; + buffer->ptr = map; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], 0); + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); +} + +/* + * Migrate private anonymous huge zero page. + */ +TEST_F(hmm, migrate_anon_huge_zero) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret; + int val; + + size = TWOMEG; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, size); + + buffer->ptr = mmap(NULL, 2 * size, + PROT_READ, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + old_ptr = buffer->ptr; + buffer->ptr = map; + + /* Initialize a read-only zero huge page. */ + val = *(int *)buffer->ptr; + ASSERT_EQ(val, 0); + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], 0); + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) { + ASSERT_EQ(ptr[i], 0); + /* If it asserts once, it probably will 500,000 times */ + if (ptr[i] != 0) + break; + } + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); +} + +/* + * Migrate private anonymous huge page and free. + */ +TEST_F(hmm, migrate_anon_huge_free) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret; + + size = TWOMEG; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, size); + + buffer->ptr = mmap(NULL, 2 * size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + old_ptr = buffer->ptr; + buffer->ptr = map; + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + /* Try freeing it. */ + ret = madvise(map, size, MADV_FREE); + ASSERT_EQ(ret, 0); + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); +} + +/* + * Migrate private anonymous huge page and fault back to sysmem. + */ +TEST_F(hmm, migrate_anon_huge_fault) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret; + + size = TWOMEG; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, size); + + buffer->ptr = mmap(NULL, 2 * size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + old_ptr = buffer->ptr; + buffer->ptr = map; + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); +} + +/* + * Migrate memory and fault back to sysmem after partially unmapping. + */ +TEST_F(hmm, migrate_partial_unmap_fault) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size = TWOMEG; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret, j, use_thp; + int offsets[] = { 0, 512 * ONEKB, ONEMEG }; + + for (use_thp = 0; use_thp < 2; ++use_thp) { + for (j = 0; j < ARRAY_SIZE(offsets); ++j) { + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, size); + + buffer->ptr = mmap(NULL, 2 * size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + if (use_thp) + ret = madvise(map, size, MADV_HUGEPAGE); + else + ret = madvise(map, size, MADV_NOHUGEPAGE); + ASSERT_EQ(ret, 0); + old_ptr = buffer->ptr; + buffer->ptr = map; + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + munmap(buffer->ptr + offsets[j], ONEMEG); + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + if (i * sizeof(int) < offsets[j] || + i * sizeof(int) >= offsets[j] + ONEMEG) + ASSERT_EQ(ptr[i], i); + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); + } + } +} + +TEST_F(hmm, migrate_remap_fault) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size = TWOMEG; + unsigned long i; + void *old_ptr, *new_ptr = NULL; + void *map; + int *ptr; + int ret, j, use_thp, dont_unmap, before; + int offsets[] = { 0, 512 * ONEKB, ONEMEG }; + + for (before = 0; before < 2; ++before) { + for (dont_unmap = 0; dont_unmap < 2; ++dont_unmap) { + for (use_thp = 0; use_thp < 2; ++use_thp) { + for (j = 0; j < ARRAY_SIZE(offsets); ++j) { + int flags = MREMAP_MAYMOVE | MREMAP_FIXED; + + if (dont_unmap) + flags |= MREMAP_DONTUNMAP; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 8 * size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, size); + + buffer->ptr = mmap(NULL, buffer->size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + if (use_thp) + ret = madvise(map, size, MADV_HUGEPAGE); + else + ret = madvise(map, size, MADV_NOHUGEPAGE); + ASSERT_EQ(ret, 0); + old_ptr = buffer->ptr; + munmap(map + size, size * 2); + buffer->ptr = map; + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; + i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + if (before) { + new_ptr = mremap((void *)map, size, size, flags, + map + size + offsets[j]); + ASSERT_NE(new_ptr, MAP_FAILED); + buffer->ptr = new_ptr; + } + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; + i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + if (!before) { + new_ptr = mremap((void *)map, size, size, flags, + map + size + offsets[j]); + ASSERT_NE(new_ptr, MAP_FAILED); + buffer->ptr = new_ptr; + } + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; + i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + munmap(new_ptr, size); + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); + } + } + } + } +} + +/* + * Migrate private anonymous huge page with allocation errors. + */ +TEST_F(hmm, migrate_anon_huge_err) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret; + + size = TWOMEG; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(2 * size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, 2 * size); + + old_ptr = mmap(NULL, 2 * size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, buffer->fd, 0); + ASSERT_NE(old_ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)old_ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + buffer->ptr = map; + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device but force a THP allocation error. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_FLAGS, buffer, + HMM_DMIRROR_FLAG_FAIL_ALLOC); + ASSERT_EQ(ret, 0); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) { + ASSERT_EQ(ptr[i], i); + if (ptr[i] != i) + break; + } + + /* Try faulting back a single (PAGE_SIZE) page. */ + ptr = buffer->ptr; + ASSERT_EQ(ptr[2048], 2048); + + /* unmap and remap the region to reset things. */ + ret = munmap(old_ptr, 2 * size); + ASSERT_EQ(ret, 0); + old_ptr = mmap(NULL, 2 * size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, buffer->fd, 0); + ASSERT_NE(old_ptr, MAP_FAILED); + map = (void *)ALIGN((uintptr_t)old_ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + buffer->ptr = map; + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate THP to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* + * Force an allocation error when faulting back a THP resident in the + * device. + */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_FLAGS, buffer, + HMM_DMIRROR_FLAG_FAIL_ALLOC); + ASSERT_EQ(ret, 0); + + ret = hmm_migrate_dev_to_sys(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ptr = buffer->ptr; + ASSERT_EQ(ptr[2048], 2048); + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); +} + +/* + * Migrate private anonymous huge zero page with allocation errors. + */ +TEST_F(hmm, migrate_anon_huge_zero_err) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret; + + size = TWOMEG; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(2 * size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, 2 * size); + + old_ptr = mmap(NULL, 2 * size, PROT_READ, + MAP_PRIVATE | MAP_ANONYMOUS, buffer->fd, 0); + ASSERT_NE(old_ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)old_ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + buffer->ptr = map; + + /* Migrate memory to device but force a THP allocation error. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_FLAGS, buffer, + HMM_DMIRROR_FLAG_FAIL_ALLOC); + ASSERT_EQ(ret, 0); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], 0); + + /* Try faulting back a single (PAGE_SIZE) page. */ + ptr = buffer->ptr; + ASSERT_EQ(ptr[2048], 0); + + /* unmap and remap the region to reset things. */ + ret = munmap(old_ptr, 2 * size); + ASSERT_EQ(ret, 0); + old_ptr = mmap(NULL, 2 * size, PROT_READ, + MAP_PRIVATE | MAP_ANONYMOUS, buffer->fd, 0); + ASSERT_NE(old_ptr, MAP_FAILED); + map = (void *)ALIGN((uintptr_t)old_ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + buffer->ptr = map; + + /* Initialize buffer in system memory (zero THP page). */ + ret = ptr[0]; + ASSERT_EQ(ret, 0); + + /* Migrate memory to device but force a THP allocation error. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_FLAGS, buffer, + HMM_DMIRROR_FLAG_FAIL_ALLOC); + ASSERT_EQ(ret, 0); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Fault the device memory back and check it. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], 0); + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); +} + +struct benchmark_results { + double sys_to_dev_time; + double dev_to_sys_time; + double throughput_s2d; + double throughput_d2s; +}; + +static double get_time_ms(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000.0) + (tv.tv_usec / 1000.0); +} + +static inline struct hmm_buffer *hmm_buffer_alloc(unsigned long size) +{ + struct hmm_buffer *buffer; + + buffer = malloc(sizeof(*buffer)); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + memset(buffer->mirror, 0xFF, size); + return buffer; +} + +static void print_benchmark_results(const char *test_name, size_t buffer_size, + struct benchmark_results *thp, + struct benchmark_results *regular) +{ + double s2d_improvement = ((regular->sys_to_dev_time - thp->sys_to_dev_time) / + regular->sys_to_dev_time) * 100.0; + double d2s_improvement = ((regular->dev_to_sys_time - thp->dev_to_sys_time) / + regular->dev_to_sys_time) * 100.0; + double throughput_s2d_improvement = ((thp->throughput_s2d - regular->throughput_s2d) / + regular->throughput_s2d) * 100.0; + double throughput_d2s_improvement = ((thp->throughput_d2s - regular->throughput_d2s) / + regular->throughput_d2s) * 100.0; + + printf("\n=== %s (%.1f MB) ===\n", test_name, buffer_size / (1024.0 * 1024.0)); + printf(" | With THP | Without THP | Improvement\n"); + printf("---------------------------------------------------------------------\n"); + printf("Sys->Dev Migration | %.3f ms | %.3f ms | %.1f%%\n", + thp->sys_to_dev_time, regular->sys_to_dev_time, s2d_improvement); + printf("Dev->Sys Migration | %.3f ms | %.3f ms | %.1f%%\n", + thp->dev_to_sys_time, regular->dev_to_sys_time, d2s_improvement); + printf("S->D Throughput | %.2f GB/s | %.2f GB/s | %.1f%%\n", + thp->throughput_s2d, regular->throughput_s2d, throughput_s2d_improvement); + printf("D->S Throughput | %.2f GB/s | %.2f GB/s | %.1f%%\n", + thp->throughput_d2s, regular->throughput_d2s, throughput_d2s_improvement); +} + +/* + * Run a single migration benchmark + * fd: file descriptor for hmm device + * use_thp: whether to use THP + * buffer_size: size of buffer to allocate + * iterations: number of iterations + * results: where to store results + */ +static inline int run_migration_benchmark(int fd, int use_thp, size_t buffer_size, + int iterations, struct benchmark_results *results) +{ + struct hmm_buffer *buffer; + unsigned long npages = buffer_size / sysconf(_SC_PAGESIZE); + double start, end; + double s2d_total = 0, d2s_total = 0; + int ret, i; + int *ptr; + + buffer = hmm_buffer_alloc(buffer_size); + + /* Map memory */ + buffer->ptr = mmap(NULL, buffer_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + if (!buffer->ptr) + return -1; + + /* Apply THP hint if requested */ + if (use_thp) + ret = madvise(buffer->ptr, buffer_size, MADV_HUGEPAGE); + else + ret = madvise(buffer->ptr, buffer_size, MADV_NOHUGEPAGE); + + if (ret) + return ret; + + /* Initialize memory to make sure pages are allocated */ + ptr = (int *)buffer->ptr; + for (i = 0; i < buffer_size / sizeof(int); i++) + ptr[i] = i & 0xFF; + + /* Warmup iteration */ + ret = hmm_migrate_sys_to_dev(fd, buffer, npages); + if (ret) + return ret; + + ret = hmm_migrate_dev_to_sys(fd, buffer, npages); + if (ret) + return ret; + + /* Benchmark iterations */ + for (i = 0; i < iterations; i++) { + /* System to device migration */ + start = get_time_ms(); + + ret = hmm_migrate_sys_to_dev(fd, buffer, npages); + if (ret) + return ret; + + end = get_time_ms(); + s2d_total += (end - start); + + /* Device to system migration */ + start = get_time_ms(); + + ret = hmm_migrate_dev_to_sys(fd, buffer, npages); + if (ret) + return ret; + + end = get_time_ms(); + d2s_total += (end - start); + } + + /* Calculate average times and throughput */ + results->sys_to_dev_time = s2d_total / iterations; + results->dev_to_sys_time = d2s_total / iterations; + results->throughput_s2d = (buffer_size / (1024.0 * 1024.0 * 1024.0)) / + (results->sys_to_dev_time / 1000.0); + results->throughput_d2s = (buffer_size / (1024.0 * 1024.0 * 1024.0)) / + (results->dev_to_sys_time / 1000.0); + + /* Cleanup */ + hmm_buffer_free(buffer); + return 0; +} + +/* + * Benchmark THP migration with different buffer sizes + */ +TEST_F_TIMEOUT(hmm, benchmark_thp_migration, 120) +{ + struct benchmark_results thp_results, regular_results; + size_t thp_size = 2 * 1024 * 1024; /* 2MB - typical THP size */ + int iterations = 5; + + printf("\nHMM THP Migration Benchmark\n"); + printf("---------------------------\n"); + printf("System page size: %ld bytes\n", sysconf(_SC_PAGESIZE)); + + /* Test different buffer sizes */ + size_t test_sizes[] = { + thp_size / 4, /* 512KB - smaller than THP */ + thp_size / 2, /* 1MB - half THP */ + thp_size, /* 2MB - single THP */ + thp_size * 2, /* 4MB - two THPs */ + thp_size * 4, /* 8MB - four THPs */ + thp_size * 8, /* 16MB - eight THPs */ + thp_size * 128, /* 256MB - one twenty eight THPs */ + }; + + static const char *const test_names[] = { + "Small Buffer (512KB)", + "Half THP Size (1MB)", + "Single THP Size (2MB)", + "Two THP Size (4MB)", + "Four THP Size (8MB)", + "Eight THP Size (16MB)", + "One twenty eight THP Size (256MB)" + }; + + int num_tests = ARRAY_SIZE(test_sizes); + + /* Run all tests */ + for (int i = 0; i < num_tests; i++) { + /* Test with THP */ + ASSERT_EQ(run_migration_benchmark(self->fd, 1, test_sizes[i], + iterations, &thp_results), 0); + + /* Test without THP */ + ASSERT_EQ(run_migration_benchmark(self->fd, 0, test_sizes[i], + iterations, ®ular_results), 0); + + /* Print results */ + print_benchmark_results(test_names[i], test_sizes[i], + &thp_results, ®ular_results); + } +} TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/hugepage-mmap.c b/tools/testing/selftests/mm/hugepage-mmap.c index 955ef87f382c..d543419de040 100644 --- a/tools/testing/selftests/mm/hugepage-mmap.c +++ b/tools/testing/selftests/mm/hugepage-mmap.c @@ -8,13 +8,6 @@ * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this * example, the app is requesting memory of size 256MB that is backed by * huge pages. - * - * For the ia64 architecture, the Linux kernel reserves Region number 4 for - * huge pages. That means that if one requires a fixed address, a huge page - * aligned address starting with 0x800000... will be required. If a fixed - * address is not required, the kernel will select an address in the proper - * range. - * Other architectures, such as ppc64, i386 or x86_64 are not so constrained. */ #define _GNU_SOURCE #include <stdlib.h> @@ -22,22 +15,14 @@ #include <unistd.h> #include <sys/mman.h> #include <fcntl.h> +#include "kselftest.h" #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) -/* Only ia64 requires this */ -#ifdef __ia64__ -#define ADDR (void *)(0x8000000000000000UL) -#define FLAGS (MAP_SHARED | MAP_FIXED) -#else -#define ADDR (void *)(0x0UL) -#define FLAGS (MAP_SHARED) -#endif - static void check_bytes(char *addr) { - printf("First hex is %x\n", *((unsigned int *)addr)); + ksft_print_msg("First hex is %x\n", *((unsigned int *)addr)); } static void write_bytes(char *addr) @@ -55,7 +40,7 @@ static int read_bytes(char *addr) check_bytes(addr); for (i = 0; i < LENGTH; i++) if (*(addr + i) != (char)i) { - printf("Mismatch at %lu\n", i); + ksft_print_msg("Error: Mismatch at %lu\n", i); return 1; } return 0; @@ -66,20 +51,20 @@ int main(void) void *addr; int fd, ret; + ksft_print_header(); + ksft_set_plan(1); + fd = memfd_create("hugepage-mmap", MFD_HUGETLB); - if (fd < 0) { - perror("memfd_create() failed"); - exit(1); - } + if (fd < 0) + ksft_exit_fail_msg("memfd_create() failed: %s\n", strerror(errno)); - addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0); + addr = mmap(NULL, LENGTH, PROTECTION, MAP_SHARED, fd, 0); if (addr == MAP_FAILED) { - perror("mmap"); close(fd); - exit(1); + ksft_exit_fail_msg("mmap(): %s\n", strerror(errno)); } - printf("Returned address is %p\n", addr); + ksft_print_msg("Returned address is %p\n", addr); check_bytes(addr); write_bytes(addr); ret = read_bytes(addr); @@ -87,5 +72,7 @@ int main(void) munmap(addr, LENGTH); close(fd); - return ret; + ksft_test_result(!ret, "Read same data\n"); + + ksft_exit(!ret); } diff --git a/tools/testing/selftests/mm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c index cabd0084f57b..b8f7d92e5a35 100644 --- a/tools/testing/selftests/mm/hugepage-mremap.c +++ b/tools/testing/selftests/mm/hugepage-mremap.c @@ -24,6 +24,7 @@ #include <sys/ioctl.h> #include <string.h> #include <stdbool.h> +#include "kselftest.h" #include "vm_util.h" #define DEFAULT_LENGTH_MB 10UL @@ -34,7 +35,7 @@ static void check_bytes(char *addr) { - printf("First hex is %x\n", *((unsigned int *)addr)); + ksft_print_msg("First hex is %x\n", *((unsigned int *)addr)); } static void write_bytes(char *addr, size_t len) @@ -52,7 +53,7 @@ static int read_bytes(char *addr, size_t len) check_bytes(addr); for (i = 0; i < len; i++) if (*(addr + i) != (char)i) { - printf("Mismatch at %lu\n", i); + ksft_print_msg("Mismatch at %lu\n", i); return 1; } return 0; @@ -64,19 +65,25 @@ static void register_region_with_uffd(char *addr, size_t len) struct uffdio_api uffdio_api; /* Create and enable userfaultfd object. */ - uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); if (uffd == -1) { - perror("userfaultfd"); - exit(1); + switch (errno) { + case EPERM: + ksft_exit_skip("Insufficient permissions, try running as root.\n"); + break; + case ENOSYS: + ksft_exit_skip("userfaultfd is not supported/not enabled.\n"); + break; + default: + ksft_exit_fail_msg("userfaultfd failed with %s\n", strerror(errno)); + break; + } } uffdio_api.api = UFFD_API; uffdio_api.features = 0; - if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) { - perror("ioctl-UFFDIO_API"); - exit(1); - } + if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) + ksft_exit_fail_msg("ioctl-UFFDIO_API: %s\n", strerror(errno)); /* Create a private anonymous mapping. The memory will be * demand-zero paged--that is, not yet allocated. When we @@ -86,21 +93,17 @@ static void register_region_with_uffd(char *addr, size_t len) addr = mmap(NULL, len, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); - if (addr == MAP_FAILED) { - perror("mmap"); - exit(1); - } + if (addr == MAP_FAILED) + ksft_exit_fail_msg("mmap: %s\n", strerror(errno)); - printf("Address returned by mmap() = %p\n", addr); + ksft_print_msg("Address returned by mmap() = %p\n", addr); /* Register the memory range of the mapping we just created for * handling by the userfaultfd object. In mode, we request to track * missing pages (i.e., pages that have not yet been faulted in). */ - if (uffd_register(uffd, addr, len, true, false, false)) { - perror("ioctl-UFFDIO_REGISTER"); - exit(1); - } + if (uffd_register(uffd, addr, len, true, false, false)) + ksft_exit_fail_msg("ioctl-UFFDIO_REGISTER: %s\n", strerror(errno)); } int main(int argc, char *argv[]) @@ -108,10 +111,11 @@ int main(int argc, char *argv[]) size_t length = 0; int ret = 0, fd; - if (argc >= 2 && !strcmp(argv[1], "-h")) { - printf("Usage: %s [length_in_MB]\n", argv[0]); - exit(1); - } + ksft_print_header(); + ksft_set_plan(1); + + if (argc >= 2 && !strcmp(argv[1], "-h")) + ksft_exit_fail_msg("Usage: %s [length_in_MB]\n", argv[0]); /* Read memory length as the first arg if valid, otherwise fallback to * the default length. @@ -123,50 +127,40 @@ int main(int argc, char *argv[]) length = MB_TO_BYTES(length); fd = memfd_create(argv[0], MFD_HUGETLB); - if (fd < 0) { - perror("Open failed"); - exit(1); - } + if (fd < 0) + ksft_exit_fail_msg("Open failed: %s\n", strerror(errno)); /* mmap to a PUD aligned address to hopefully trigger pmd sharing. */ unsigned long suggested_addr = 0x7eaa40000000; void *haddr = mmap((void *)suggested_addr, length, PROTECTION, MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0); - printf("Map haddr: Returned address is %p\n", haddr); - if (haddr == MAP_FAILED) { - perror("mmap1"); - exit(1); - } + ksft_print_msg("Map haddr: Returned address is %p\n", haddr); + if (haddr == MAP_FAILED) + ksft_exit_fail_msg("mmap1: %s\n", strerror(errno)); /* mmap again to a dummy address to hopefully trigger pmd sharing. */ suggested_addr = 0x7daa40000000; void *daddr = mmap((void *)suggested_addr, length, PROTECTION, MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0); - printf("Map daddr: Returned address is %p\n", daddr); - if (daddr == MAP_FAILED) { - perror("mmap3"); - exit(1); - } + ksft_print_msg("Map daddr: Returned address is %p\n", daddr); + if (daddr == MAP_FAILED) + ksft_exit_fail_msg("mmap3: %s\n", strerror(errno)); suggested_addr = 0x7faa40000000; void *vaddr = mmap((void *)suggested_addr, length, PROTECTION, FLAGS, -1, 0); - printf("Map vaddr: Returned address is %p\n", vaddr); - if (vaddr == MAP_FAILED) { - perror("mmap2"); - exit(1); - } + ksft_print_msg("Map vaddr: Returned address is %p\n", vaddr); + if (vaddr == MAP_FAILED) + ksft_exit_fail_msg("mmap2: %s\n", strerror(errno)); register_region_with_uffd(haddr, length); void *addr = mremap(haddr, length, length, MREMAP_MAYMOVE | MREMAP_FIXED, vaddr); - if (addr == MAP_FAILED) { - perror("mremap"); - exit(1); - } + if (addr == MAP_FAILED) + ksft_exit_fail_msg("mremap: %s\n", strerror(errno)); - printf("Mremap: Returned address is %p\n", addr); + ksft_print_msg("Mremap: Returned address is %p\n", addr); check_bytes(addr); write_bytes(addr, length); ret = read_bytes(addr, length); @@ -174,12 +168,11 @@ int main(int argc, char *argv[]) munmap(addr, length); addr = mremap(addr, length, length, 0); - if (addr != MAP_FAILED) { - printf("mremap: Expected failure, but call succeeded\n"); - exit(1); - } + if (addr != MAP_FAILED) + ksft_exit_fail_msg("mremap: Expected failure, but call succeeded\n"); close(fd); - return ret; + ksft_test_result(!ret, "Read same data\n"); + ksft_exit(!ret); } diff --git a/tools/testing/selftests/mm/hugepage-shm.c b/tools/testing/selftests/mm/hugepage-shm.c index 478bb1e989e9..ef06260802b5 100644 --- a/tools/testing/selftests/mm/hugepage-shm.c +++ b/tools/testing/selftests/mm/hugepage-shm.c @@ -8,13 +8,6 @@ * SHM_HUGETLB in the shmget system call to inform the kernel that it is * requesting huge pages. * - * For the ia64 architecture, the Linux kernel reserves Region number 4 for - * huge pages. That means that if one requires a fixed address, a huge page - * aligned address starting with 0x800000... will be required. If a fixed - * address is not required, the kernel will select an address in the proper - * range. - * Other architectures, such as ppc64, i386 or x86_64 are not so constrained. - * * Note: The default shared memory limit is quite low on many kernels, * you may need to increase it via: * @@ -39,15 +32,6 @@ #define dprintf(x) printf(x) -/* Only ia64 requires this */ -#ifdef __ia64__ -#define ADDR (void *)(0x8000000000000000UL) -#define SHMAT_FLAGS (SHM_RND) -#else -#define ADDR (void *)(0x0UL) -#define SHMAT_FLAGS (0) -#endif - int main(void) { int shmid; @@ -61,7 +45,7 @@ int main(void) } printf("shmid: 0x%x\n", shmid); - shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS); + shmaddr = shmat(shmid, NULL, 0); if (shmaddr == (char *)-1) { perror("Shared memory attach failure"); shmctl(shmid, IPC_RMID, NULL); diff --git a/tools/testing/selftests/mm/hugepage-vmemmap.c b/tools/testing/selftests/mm/hugepage-vmemmap.c index 5b354c209e93..df366a4d1b92 100644 --- a/tools/testing/selftests/mm/hugepage-vmemmap.c +++ b/tools/testing/selftests/mm/hugepage-vmemmap.c @@ -10,10 +10,7 @@ #include <unistd.h> #include <sys/mman.h> #include <fcntl.h> - -#define MAP_LENGTH (2UL * 1024 * 1024) - -#define PAGE_SIZE 4096 +#include "vm_util.h" #define PAGE_COMPOUND_HEAD (1UL << 15) #define PAGE_COMPOUND_TAIL (1UL << 16) @@ -25,19 +22,8 @@ #define PM_PFRAME_BITS 55 #define PM_PFRAME_MASK ~((1UL << PM_PFRAME_BITS) - 1) -/* - * For ia64 architecture, Linux kernel reserves Region number 4 for hugepages. - * That means the addresses starting with 0x800000... will need to be - * specified. Specifying a fixed address is not required on ppc64, i386 - * or x86_64. - */ -#ifdef __ia64__ -#define MAP_ADDR (void *)(0x8000000000000000UL) -#define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_FIXED) -#else -#define MAP_ADDR NULL -#define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB) -#endif +static size_t pagesize; +static size_t maplength; static void write_bytes(char *addr, size_t length) { @@ -56,7 +42,7 @@ static unsigned long virt_to_pfn(void *addr) if (fd < 0) return -1UL; - lseek(fd, (unsigned long)addr / PAGE_SIZE * sizeof(pagemap), SEEK_SET); + lseek(fd, (unsigned long)addr / pagesize * sizeof(pagemap), SEEK_SET); read(fd, &pagemap, sizeof(pagemap)); close(fd); @@ -86,7 +72,7 @@ static int check_page_flags(unsigned long pfn) * this also verifies kernel has correctly set the fake page_head to tail * while hugetlb_free_vmemmap is enabled. */ - for (i = 1; i < MAP_LENGTH / PAGE_SIZE; i++) { + for (i = 1; i < maplength / pagesize; i++) { read(fd, &pageflags, sizeof(pageflags)); if ((pageflags & TAIL_PAGE_FLAGS) != TAIL_PAGE_FLAGS || (pageflags & HEAD_PAGE_FLAGS) == HEAD_PAGE_FLAGS) { @@ -106,18 +92,26 @@ int main(int argc, char **argv) void *addr; unsigned long pfn; - addr = mmap(MAP_ADDR, MAP_LENGTH, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0); + pagesize = psize(); + maplength = default_huge_page_size(); + if (!maplength) { + printf("Unable to determine huge page size\n"); + exit(1); + } + + addr = mmap(NULL, maplength, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); exit(1); } /* Trigger allocation of HugeTLB page. */ - write_bytes(addr, MAP_LENGTH); + write_bytes(addr, maplength); pfn = virt_to_pfn(addr); if (pfn == -1UL) { - munmap(addr, MAP_LENGTH); + munmap(addr, maplength); perror("virt_to_pfn"); exit(1); } @@ -125,13 +119,13 @@ int main(int argc, char **argv) printf("Returned address is %p whose pfn is %lx\n", addr, pfn); if (check_page_flags(pfn) < 0) { - munmap(addr, MAP_LENGTH); + munmap(addr, maplength); perror("check_page_flags"); exit(1); } /* munmap() length of MAP_HUGETLB memory must be hugepage aligned */ - if (munmap(addr, MAP_LENGTH)) { + if (munmap(addr, maplength)) { perror("munmap"); exit(1); } diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index d55322df4b73..05d9d2805ae4 100644 --- a/tools/testing/selftests/mm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c @@ -19,6 +19,7 @@ #include <sys/mman.h> #include <fcntl.h> #include "vm_util.h" +#include "kselftest.h" #define MIN_FREE_PAGES 20 #define NR_HUGE_PAGES 10 /* common number of pages to map/allocate */ @@ -36,25 +37,6 @@ unsigned long huge_page_size; unsigned long base_page_size; -unsigned long get_free_hugepages(void) -{ - unsigned long fhp = 0; - char *line = NULL; - size_t linelen = 0; - FILE *f = fopen("/proc/meminfo", "r"); - - if (!f) - return fhp; - while (getline(&line, &linelen, f) > 0) { - if (sscanf(line, "HugePages_Free: %lu", &fhp) == 1) - break; - } - - free(line); - fclose(f); - return fhp; -} - void write_fault_pages(void *addr, unsigned long nr_pages) { unsigned long i; @@ -65,14 +47,13 @@ void write_fault_pages(void *addr, unsigned long nr_pages) void read_fault_pages(void *addr, unsigned long nr_pages) { - volatile unsigned long dummy = 0; unsigned long i; for (i = 0; i < nr_pages; i++) { - dummy += *((unsigned long *)(addr + (i * huge_page_size))); - + unsigned long *addr2 = + ((unsigned long *)(addr + (i * huge_page_size))); /* Prevent the compiler from optimizing out the entire loop: */ - asm volatile("" : "+r" (dummy)); + FORCE_READ(*addr2); } } @@ -97,7 +78,7 @@ int main(int argc, char **argv) free_hugepages = get_free_hugepages(); if (free_hugepages < MIN_FREE_PAGES) { printf("Not enough free huge pages to test, exiting!\n"); - exit(1); + exit(KSFT_SKIP); } fd = memfd_create(argv[0], MFD_HUGETLB); diff --git a/tools/testing/selftests/mm/hugetlb-read-hwpoison.c b/tools/testing/selftests/mm/hugetlb-read-hwpoison.c new file mode 100644 index 000000000000..46230462ad48 --- /dev/null +++ b/tools/testing/selftests/mm/hugetlb-read-hwpoison.c @@ -0,0 +1,322 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <stdlib.h> +#include <stdio.h> +#include <string.h> + +#include <linux/magic.h> +#include <sys/mman.h> +#include <sys/statfs.h> +#include <errno.h> +#include <stdbool.h> + +#include "kselftest.h" + +#define PREFIX " ... " +#define ERROR_PREFIX " !!! " + +#define MAX_WRITE_READ_CHUNK_SIZE (getpagesize() * 16) +#define MAX(a, b) (((a) > (b)) ? (a) : (b)) + +enum test_status { + TEST_PASSED = 0, + TEST_FAILED = 1, + TEST_SKIPPED = 2, +}; + +static char *status_to_str(enum test_status status) +{ + switch (status) { + case TEST_PASSED: + return "TEST_PASSED"; + case TEST_FAILED: + return "TEST_FAILED"; + case TEST_SKIPPED: + return "TEST_SKIPPED"; + default: + return "TEST_???"; + } +} + +static int setup_filemap(char *filemap, size_t len, size_t wr_chunk_size) +{ + char iter = 0; + + for (size_t offset = 0; offset < len; + offset += wr_chunk_size) { + iter++; + memset(filemap + offset, iter, wr_chunk_size); + } + + return 0; +} + +static bool verify_chunk(char *buf, size_t len, char val) +{ + size_t i; + + for (i = 0; i < len; ++i) { + if (buf[i] != val) { + printf(PREFIX ERROR_PREFIX "check fail: buf[%lu] = %u != %u\n", + i, buf[i], val); + return false; + } + } + + return true; +} + +static bool seek_read_hugepage_filemap(int fd, size_t len, size_t wr_chunk_size, + off_t offset, size_t expected) +{ + char buf[MAX_WRITE_READ_CHUNK_SIZE]; + ssize_t ret_count = 0; + ssize_t total_ret_count = 0; + char val = offset / wr_chunk_size + offset % wr_chunk_size; + + printf(PREFIX PREFIX "init val=%u with offset=0x%lx\n", val, offset); + printf(PREFIX PREFIX "expect to read 0x%lx bytes of data in total\n", + expected); + if (lseek(fd, offset, SEEK_SET) < 0) { + perror(PREFIX ERROR_PREFIX "seek failed"); + return false; + } + + while (offset + total_ret_count < len) { + ret_count = read(fd, buf, wr_chunk_size); + if (ret_count == 0) { + printf(PREFIX PREFIX "read reach end of the file\n"); + break; + } else if (ret_count < 0) { + perror(PREFIX ERROR_PREFIX "read failed"); + break; + } + ++val; + if (!verify_chunk(buf, ret_count, val)) + return false; + + total_ret_count += ret_count; + } + printf(PREFIX PREFIX "actually read 0x%lx bytes of data in total\n", + total_ret_count); + + return total_ret_count == expected; +} + +static bool read_hugepage_filemap(int fd, size_t len, + size_t wr_chunk_size, size_t expected) +{ + char buf[MAX_WRITE_READ_CHUNK_SIZE]; + ssize_t ret_count = 0; + ssize_t total_ret_count = 0; + char val = 0; + + printf(PREFIX PREFIX "expect to read 0x%lx bytes of data in total\n", + expected); + while (total_ret_count < len) { + ret_count = read(fd, buf, wr_chunk_size); + if (ret_count == 0) { + printf(PREFIX PREFIX "read reach end of the file\n"); + break; + } else if (ret_count < 0) { + perror(PREFIX ERROR_PREFIX "read failed"); + break; + } + ++val; + if (!verify_chunk(buf, ret_count, val)) + return false; + + total_ret_count += ret_count; + } + printf(PREFIX PREFIX "actually read 0x%lx bytes of data in total\n", + total_ret_count); + + return total_ret_count == expected; +} + +static enum test_status +test_hugetlb_read(int fd, size_t len, size_t wr_chunk_size) +{ + enum test_status status = TEST_SKIPPED; + char *filemap = NULL; + + if (ftruncate(fd, len) < 0) { + perror(PREFIX ERROR_PREFIX "ftruncate failed"); + return status; + } + + filemap = mmap(NULL, len, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, 0); + if (filemap == MAP_FAILED) { + perror(PREFIX ERROR_PREFIX "mmap for primary mapping failed"); + goto done; + } + + setup_filemap(filemap, len, wr_chunk_size); + status = TEST_FAILED; + + if (read_hugepage_filemap(fd, len, wr_chunk_size, len)) + status = TEST_PASSED; + + munmap(filemap, len); +done: + if (ftruncate(fd, 0) < 0) { + perror(PREFIX ERROR_PREFIX "ftruncate back to 0 failed"); + status = TEST_FAILED; + } + + return status; +} + +static enum test_status +test_hugetlb_read_hwpoison(int fd, size_t len, size_t wr_chunk_size, + bool skip_hwpoison_page) +{ + enum test_status status = TEST_SKIPPED; + char *filemap = NULL; + char *hwp_addr = NULL; + const unsigned long pagesize = getpagesize(); + + if (ftruncate(fd, len) < 0) { + perror(PREFIX ERROR_PREFIX "ftruncate failed"); + return status; + } + + filemap = mmap(NULL, len, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, 0); + if (filemap == MAP_FAILED) { + perror(PREFIX ERROR_PREFIX "mmap for primary mapping failed"); + goto done; + } + + setup_filemap(filemap, len, wr_chunk_size); + status = TEST_FAILED; + + /* + * Poisoned hugetlb page layout (assume hugepagesize=2MB): + * |<---------------------- 1MB ---------------------->| + * |<---- healthy page ---->|<---- HWPOISON page ----->| + * |<------------------- (1MB - 8KB) ----------------->| + */ + hwp_addr = filemap + len / 2 + pagesize; + if (madvise(hwp_addr, pagesize, MADV_HWPOISON) < 0) { + perror(PREFIX ERROR_PREFIX "MADV_HWPOISON failed"); + goto unmap; + } + + if (!skip_hwpoison_page) { + /* + * Userspace should be able to read (1MB + 1 page) from + * the beginning of the HWPOISONed hugepage. + */ + if (read_hugepage_filemap(fd, len, wr_chunk_size, + len / 2 + pagesize)) + status = TEST_PASSED; + } else { + /* + * Userspace should be able to read (1MB - 2 pages) from + * HWPOISONed hugepage. + */ + if (seek_read_hugepage_filemap(fd, len, wr_chunk_size, + len / 2 + MAX(2 * pagesize, wr_chunk_size), + len / 2 - MAX(2 * pagesize, wr_chunk_size))) + status = TEST_PASSED; + } + +unmap: + munmap(filemap, len); +done: + if (ftruncate(fd, 0) < 0) { + perror(PREFIX ERROR_PREFIX "ftruncate back to 0 failed"); + status = TEST_FAILED; + } + + return status; +} + +static int create_hugetlbfs_file(struct statfs *file_stat) +{ + int fd; + + fd = memfd_create("hugetlb_tmp", MFD_HUGETLB); + if (fd < 0) { + perror(PREFIX ERROR_PREFIX "could not open hugetlbfs file"); + return -1; + } + + memset(file_stat, 0, sizeof(*file_stat)); + if (fstatfs(fd, file_stat)) { + perror(PREFIX ERROR_PREFIX "fstatfs failed"); + goto close; + } + if (file_stat->f_type != HUGETLBFS_MAGIC) { + printf(PREFIX ERROR_PREFIX "not hugetlbfs file\n"); + goto close; + } + + return fd; +close: + close(fd); + return -1; +} + +int main(void) +{ + int fd; + struct statfs file_stat; + enum test_status status; + /* Test read() in different granularity. */ + size_t wr_chunk_sizes[] = { + getpagesize() / 2, getpagesize(), + getpagesize() * 2, getpagesize() * 4 + }; + size_t i; + + for (i = 0; i < ARRAY_SIZE(wr_chunk_sizes); ++i) { + printf("Write/read chunk size=0x%lx\n", + wr_chunk_sizes[i]); + + fd = create_hugetlbfs_file(&file_stat); + if (fd < 0) + goto create_failure; + printf(PREFIX "HugeTLB read regression test...\n"); + status = test_hugetlb_read(fd, file_stat.f_bsize, + wr_chunk_sizes[i]); + printf(PREFIX "HugeTLB read regression test...%s\n", + status_to_str(status)); + close(fd); + if (status == TEST_FAILED) + return -1; + + fd = create_hugetlbfs_file(&file_stat); + if (fd < 0) + goto create_failure; + printf(PREFIX "HugeTLB read HWPOISON test...\n"); + status = test_hugetlb_read_hwpoison(fd, file_stat.f_bsize, + wr_chunk_sizes[i], false); + printf(PREFIX "HugeTLB read HWPOISON test...%s\n", + status_to_str(status)); + close(fd); + if (status == TEST_FAILED) + return -1; + + fd = create_hugetlbfs_file(&file_stat); + if (fd < 0) + goto create_failure; + printf(PREFIX "HugeTLB seek then read HWPOISON test...\n"); + status = test_hugetlb_read_hwpoison(fd, file_stat.f_bsize, + wr_chunk_sizes[i], true); + printf(PREFIX "HugeTLB seek then read HWPOISON test...%s\n", + status_to_str(status)); + close(fd); + if (status == TEST_FAILED) + return -1; + } + + return 0; + +create_failure: + printf(ERROR_PREFIX "Abort test: failed to create hugetlbfs file\n"); + return -1; +} diff --git a/tools/testing/selftests/mm/hugetlb-soft-offline.c b/tools/testing/selftests/mm/hugetlb-soft-offline.c new file mode 100644 index 000000000000..a8bc02688085 --- /dev/null +++ b/tools/testing/selftests/mm/hugetlb-soft-offline.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test soft offline behavior for HugeTLB pages: + * - if enable_soft_offline = 0, hugepages should stay intact and soft + * offlining failed with EOPNOTSUPP. + * - if enable_soft_offline = 1, a hugepage should be dissolved and + * nr_hugepages/free_hugepages should be reduced by 1. + * + * Before running, make sure more than 2 hugepages of default_hugepagesz + * are allocated. For example, if /proc/meminfo/Hugepagesize is 2048kB: + * echo 8 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> + +#include <linux/magic.h> +#include <linux/memfd.h> +#include <sys/mman.h> +#include <sys/statfs.h> +#include <sys/types.h> + +#include "kselftest.h" + +#ifndef MADV_SOFT_OFFLINE +#define MADV_SOFT_OFFLINE 101 +#endif + +#define EPREFIX " !!! " + +static int do_soft_offline(int fd, size_t len, int expect_errno) +{ + char *filemap = NULL; + char *hwp_addr = NULL; + const unsigned long pagesize = getpagesize(); + int ret = 0; + + if (ftruncate(fd, len) < 0) { + ksft_perror(EPREFIX "ftruncate to len failed"); + return -1; + } + + filemap = mmap(NULL, len, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, 0); + if (filemap == MAP_FAILED) { + ksft_perror(EPREFIX "mmap failed"); + ret = -1; + goto untruncate; + } + + memset(filemap, 0xab, len); + ksft_print_msg("Allocated %#lx bytes of hugetlb pages\n", len); + + hwp_addr = filemap + len / 2; + ret = madvise(hwp_addr, pagesize, MADV_SOFT_OFFLINE); + ksft_print_msg("MADV_SOFT_OFFLINE %p ret=%d, errno=%d\n", + hwp_addr, ret, errno); + if (ret != 0) + ksft_perror(EPREFIX "madvise failed"); + + if (errno == expect_errno) + ret = 0; + else { + ksft_print_msg("MADV_SOFT_OFFLINE should ret %d\n", + expect_errno); + ret = -1; + } + + munmap(filemap, len); +untruncate: + if (ftruncate(fd, 0) < 0) + ksft_perror(EPREFIX "ftruncate back to 0 failed"); + + return ret; +} + +static int set_enable_soft_offline(int value) +{ + char cmd[256] = {0}; + FILE *cmdfile = NULL; + + if (value != 0 && value != 1) + return -EINVAL; + + sprintf(cmd, "echo %d > /proc/sys/vm/enable_soft_offline", value); + cmdfile = popen(cmd, "r"); + + if (cmdfile) + ksft_print_msg("enable_soft_offline => %d\n", value); + else { + ksft_perror(EPREFIX "failed to set enable_soft_offline"); + return errno; + } + + pclose(cmdfile); + return 0; +} + +static int read_nr_hugepages(unsigned long hugepage_size, + unsigned long *nr_hugepages) +{ + char buffer[256] = {0}; + char cmd[256] = {0}; + + sprintf(cmd, "cat /sys/kernel/mm/hugepages/hugepages-%ldkB/nr_hugepages", + hugepage_size); + FILE *cmdfile = popen(cmd, "r"); + + if (cmdfile == NULL) { + ksft_perror(EPREFIX "failed to popen nr_hugepages"); + return -1; + } + + if (!fgets(buffer, sizeof(buffer), cmdfile)) { + ksft_perror(EPREFIX "failed to read nr_hugepages"); + pclose(cmdfile); + return -1; + } + + *nr_hugepages = atoll(buffer); + pclose(cmdfile); + return 0; +} + +static int create_hugetlbfs_file(struct statfs *file_stat) +{ + int fd; + + fd = memfd_create("hugetlb_tmp", MFD_HUGETLB); + if (fd < 0) { + ksft_perror(EPREFIX "could not open hugetlbfs file"); + return -1; + } + + memset(file_stat, 0, sizeof(*file_stat)); + if (fstatfs(fd, file_stat)) { + ksft_perror(EPREFIX "fstatfs failed"); + goto close; + } + if (file_stat->f_type != HUGETLBFS_MAGIC) { + ksft_print_msg(EPREFIX "not hugetlbfs file\n"); + goto close; + } + + return fd; +close: + close(fd); + return -1; +} + +static void test_soft_offline_common(int enable_soft_offline) +{ + int fd; + int expect_errno = enable_soft_offline ? 0 : EOPNOTSUPP; + struct statfs file_stat; + unsigned long hugepagesize_kb = 0; + unsigned long nr_hugepages_before = 0; + unsigned long nr_hugepages_after = 0; + int ret; + + ksft_print_msg("Test soft-offline when enabled_soft_offline=%d\n", + enable_soft_offline); + + fd = create_hugetlbfs_file(&file_stat); + if (fd < 0) + ksft_exit_fail_msg("Failed to create hugetlbfs file\n"); + + hugepagesize_kb = file_stat.f_bsize / 1024; + ksft_print_msg("Hugepagesize is %ldkB\n", hugepagesize_kb); + + if (set_enable_soft_offline(enable_soft_offline) != 0) { + close(fd); + ksft_exit_fail_msg("Failed to set enable_soft_offline\n"); + } + + if (read_nr_hugepages(hugepagesize_kb, &nr_hugepages_before) != 0) { + close(fd); + ksft_exit_fail_msg("Failed to read nr_hugepages\n"); + } + + ksft_print_msg("Before MADV_SOFT_OFFLINE nr_hugepages=%ld\n", + nr_hugepages_before); + + ret = do_soft_offline(fd, 2 * file_stat.f_bsize, expect_errno); + + if (read_nr_hugepages(hugepagesize_kb, &nr_hugepages_after) != 0) { + close(fd); + ksft_exit_fail_msg("Failed to read nr_hugepages\n"); + } + + ksft_print_msg("After MADV_SOFT_OFFLINE nr_hugepages=%ld\n", + nr_hugepages_after); + + // No need for the hugetlbfs file from now on. + close(fd); + + if (enable_soft_offline) { + if (nr_hugepages_before != nr_hugepages_after + 1) { + ksft_test_result_fail("MADV_SOFT_OFFLINE should reduced 1 hugepage\n"); + return; + } + } else { + if (nr_hugepages_before != nr_hugepages_after) { + ksft_test_result_fail("MADV_SOFT_OFFLINE reduced %lu hugepages\n", + nr_hugepages_before - nr_hugepages_after); + return; + } + } + + ksft_test_result(ret == 0, + "Test soft-offline when enabled_soft_offline=%d\n", + enable_soft_offline); +} + +int main(int argc, char **argv) +{ + ksft_print_header(); + ksft_set_plan(2); + + test_soft_offline_common(1); + test_soft_offline_common(0); + + ksft_finished(); +} diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c new file mode 100644 index 000000000000..9ac62eb4c97d --- /dev/null +++ b/tools/testing/selftests/mm/hugetlb_dio.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This program tests for hugepage leaks after DIO writes to a file using a + * hugepage as the user buffer. During DIO, the user buffer is pinned and + * should be properly unpinned upon completion. This patch verifies that the + * kernel correctly unpins the buffer at DIO completion for both aligned and + * unaligned user buffer offsets (w.r.t page boundary), ensuring the hugepage + * is freed upon unmapping. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <sys/stat.h> +#include <stdlib.h> +#include <fcntl.h> +#include <stdint.h> +#include <unistd.h> +#include <string.h> +#include <sys/mman.h> +#include "vm_util.h" +#include "kselftest.h" + +void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) +{ + int fd; + char *buffer = NULL; + char *orig_buffer = NULL; + size_t h_pagesize = 0; + size_t writesize; + int free_hpage_b = 0; + int free_hpage_a = 0; + const int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB; + const int mmap_prot = PROT_READ | PROT_WRITE; + + writesize = end_off - start_off; + + /* Get the default huge page size */ + h_pagesize = default_huge_page_size(); + if (!h_pagesize) + ksft_exit_fail_msg("Unable to determine huge page size\n"); + + /* Open the file to DIO */ + fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664); + if (fd < 0) + ksft_exit_fail_perror("Error opening file\n"); + + /* Get the free huge pages before allocation */ + free_hpage_b = get_free_hugepages(); + if (free_hpage_b == 0) { + close(fd); + ksft_exit_skip("No free hugepage, exiting!\n"); + } + + /* Allocate a hugetlb page */ + orig_buffer = mmap(NULL, h_pagesize, mmap_prot, mmap_flags, -1, 0); + if (orig_buffer == MAP_FAILED) { + close(fd); + ksft_exit_fail_perror("Error mapping memory\n"); + } + buffer = orig_buffer; + buffer += start_off; + + memset(buffer, 'A', writesize); + + /* Write the buffer to the file */ + if (write(fd, buffer, writesize) != (writesize)) { + munmap(orig_buffer, h_pagesize); + close(fd); + ksft_exit_fail_perror("Error writing to file\n"); + } + + /* unmap the huge page */ + munmap(orig_buffer, h_pagesize); + close(fd); + + /* Get the free huge pages after unmap*/ + free_hpage_a = get_free_hugepages(); + + ksft_print_msg("No. Free pages before allocation : %d\n", free_hpage_b); + ksft_print_msg("No. Free pages after munmap : %d\n", free_hpage_a); + + /* + * If the no. of free hugepages before allocation and after unmap does + * not match - that means there could still be a page which is pinned. + */ + ksft_test_result(free_hpage_a == free_hpage_b, + "free huge pages from %u-%u\n", start_off, end_off); +} + +int main(void) +{ + size_t pagesize = 0; + int fd; + + ksft_print_header(); + + /* Open the file to DIO */ + fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664); + if (fd < 0) + ksft_exit_skip("Unable to allocate file: %s\n", strerror(errno)); + close(fd); + + /* Check if huge pages are free */ + if (!get_free_hugepages()) + ksft_exit_skip("No free hugepage, exiting\n"); + + ksft_set_plan(4); + + /* Get base page size */ + pagesize = psize(); + + /* start and end is aligned to pagesize */ + run_dio_using_hugetlb(0, (pagesize * 3)); + + /* start is aligned but end is not aligned */ + run_dio_using_hugetlb(0, (pagesize * 3) - (pagesize / 2)); + + /* start is unaligned and end is aligned */ + run_dio_using_hugetlb(pagesize / 2, (pagesize * 3)); + + /* both start and end are unaligned */ + run_dio_using_hugetlb(pagesize / 2, (pagesize * 3) + (pagesize / 2)); + + ksft_finished(); +} diff --git a/tools/testing/selftests/mm/hugetlb_fault_after_madv.c b/tools/testing/selftests/mm/hugetlb_fault_after_madv.c new file mode 100644 index 000000000000..b4b257775b74 --- /dev/null +++ b/tools/testing/selftests/mm/hugetlb_fault_after_madv.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <pthread.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <unistd.h> +#include <setjmp.h> +#include <signal.h> + +#include "vm_util.h" +#include "kselftest.h" + +#define INLOOP_ITER 100 + +static char *huge_ptr; +static size_t huge_page_size; + +static sigjmp_buf sigbuf; +static bool sigbus_triggered; + +static void signal_handler(int signal) +{ + if (signal == SIGBUS) { + sigbus_triggered = true; + siglongjmp(sigbuf, 1); + } +} + +/* Touch the memory while it is being madvised() */ +void *touch(void *unused) +{ + char *ptr = (char *)huge_ptr; + + if (sigsetjmp(sigbuf, 1)) + return NULL; + + for (int i = 0; i < INLOOP_ITER; i++) + ptr[0] = '.'; + + return NULL; +} + +void *madv(void *unused) +{ + usleep(rand() % 10); + + for (int i = 0; i < INLOOP_ITER; i++) + madvise(huge_ptr, huge_page_size, MADV_DONTNEED); + + return NULL; +} + +int main(void) +{ + unsigned long free_hugepages; + pthread_t thread1, thread2; + /* + * On kernel 6.4, we are able to reproduce the problem with ~1000 + * interactions + */ + int max = 10000; + int err; + + ksft_print_header(); + ksft_set_plan(1); + + srand(getpid()); + + if (signal(SIGBUS, signal_handler) == SIG_ERR) + ksft_exit_skip("Could not register signal handler."); + + huge_page_size = default_huge_page_size(); + if (!huge_page_size) + ksft_exit_skip("Could not detect default hugetlb page size."); + + ksft_print_msg("[INFO] detected default hugetlb page size: %zu KiB\n", + huge_page_size / 1024); + + free_hugepages = get_free_hugepages(); + if (free_hugepages != 1) { + ksft_exit_skip("This test needs one and only one page to execute. Got %lu\n", + free_hugepages); + } + + while (max--) { + huge_ptr = mmap(NULL, huge_page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + + if ((unsigned long)huge_ptr == -1) + ksft_exit_skip("Failed to allocated huge page\n"); + + pthread_create(&thread1, NULL, madv, NULL); + pthread_create(&thread2, NULL, touch, NULL); + + pthread_join(thread1, NULL); + pthread_join(thread2, NULL); + munmap(huge_ptr, huge_page_size); + } + + ksft_test_result(!sigbus_triggered, "SIGBUS behavior\n"); + + err = ksft_get_fail_cnt(); + if (err) + ksft_exit_fail_msg("%d out of %d tests failed\n", + err, ksft_test_num()); + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/mm/hugetlb_madv_vs_map.c b/tools/testing/selftests/mm/hugetlb_madv_vs_map.c new file mode 100644 index 000000000000..efd774b41389 --- /dev/null +++ b/tools/testing/selftests/mm/hugetlb_madv_vs_map.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A test case that must run on a system with one and only one huge page available. + * # echo 1 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages + * + * During setup, the test allocates the only available page, and starts three threads: + * - thread1: + * * madvise(MADV_DONTNEED) on the allocated huge page + * - thread 2: + * * Write to the allocated huge page + * - thread 3: + * * Try to allocated an extra huge page (which must not available) + * + * The test fails if thread3 is able to allocate a page. + * + * Touching the first page after thread3's allocation will raise a SIGBUS + * + * Author: Breno Leitao <leitao@debian.org> + */ +#include <pthread.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <unistd.h> + +#include "vm_util.h" +#include "kselftest.h" + +#define INLOOP_ITER 100 + +size_t mmap_size; +char *huge_ptr; + +/* Touch the memory while it is being madvised() */ +void *touch(void *unused) +{ + for (int i = 0; i < INLOOP_ITER; i++) + huge_ptr[0] = '.'; + + return NULL; +} + +void *madv(void *unused) +{ + for (int i = 0; i < INLOOP_ITER; i++) + madvise(huge_ptr, mmap_size, MADV_DONTNEED); + + return NULL; +} + +/* + * We got here, and there must be no huge page available for mapping + * The other hugepage should be flipping from used <-> reserved, because + * of madvise(DONTNEED). + */ +void *map_extra(void *unused) +{ + void *ptr; + + for (int i = 0; i < INLOOP_ITER; i++) { + ptr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + + if ((long)ptr != -1) { + /* Touching the other page now will cause a SIGBUG + * huge_ptr[0] = '1'; + */ + return ptr; + } + } + + return NULL; +} + +int main(void) +{ + pthread_t thread1, thread2, thread3; + unsigned long free_hugepages; + void *ret; + + /* + * On kernel 6.7, we are able to reproduce the problem with ~10 + * interactions + */ + int max = 10; + + free_hugepages = get_free_hugepages(); + + if (free_hugepages != 1) { + ksft_exit_skip("This test needs one and only one page to execute. Got %lu\n", + free_hugepages); + } + + mmap_size = default_huge_page_size(); + + while (max--) { + huge_ptr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + + if ((unsigned long)huge_ptr == -1) { + ksft_test_result_fail("Failed to allocate huge page\n"); + return KSFT_FAIL; + } + + pthread_create(&thread1, NULL, madv, NULL); + pthread_create(&thread2, NULL, touch, NULL); + pthread_create(&thread3, NULL, map_extra, NULL); + + pthread_join(thread1, NULL); + pthread_join(thread2, NULL); + pthread_join(thread3, &ret); + + if (ret) { + ksft_test_result_fail("Unexpected huge page allocation\n"); + return KSFT_FAIL; + } + + /* Unmap and restart */ + munmap(huge_ptr, mmap_size); + } + + return KSFT_PASS; +} diff --git a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh index bf2d2a684edf..0dd31892ff67 100755 --- a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh +++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh @@ -11,6 +11,7 @@ if [[ $(id -u) -ne 0 ]]; then exit $ksft_skip fi +nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) usage_file=usage_in_bytes if [[ "$1" == "-cgroup-v2" ]]; then @@ -20,22 +21,22 @@ fi if [[ $cgroup2 ]]; then - CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk -e '{print $3}') + CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk '{print $3}') if [[ -z "$CGROUP_ROOT" ]]; then - CGROUP_ROOT=/dev/cgroup/memory + CGROUP_ROOT=$(mktemp -d) mount -t cgroup2 none $CGROUP_ROOT do_umount=1 fi echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control else - CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}') + CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}') if [[ -z "$CGROUP_ROOT" ]]; then CGROUP_ROOT=/dev/cgroup/memory mount -t cgroup memory,hugetlb $CGROUP_ROOT do_umount=1 fi fi -MNT='/mnt/huge/' +MNT='/mnt/huge' function get_machine_hugepage_size() { hpz=$(grep -i hugepagesize /proc/meminfo) @@ -55,10 +56,45 @@ function cleanup() { rmdir "$CGROUP_ROOT"/a/b 2>/dev/null rmdir "$CGROUP_ROOT"/a 2>/dev/null rmdir "$CGROUP_ROOT"/test1 2>/dev/null - echo 0 >/proc/sys/vm/nr_hugepages + echo $nr_hugepgs >/proc/sys/vm/nr_hugepages set -e } +function assert_with_retry() { + local actual_path="$1" + local expected="$2" + local tolerance=$((7 * 1024 * 1024)) + local timeout=20 + local interval=1 + local start_time + local now + local elapsed + local actual + + start_time=$(date +%s) + + while true; do + actual="$(cat "$actual_path")" + + if [[ $actual -ge $(($expected - $tolerance)) ]] && + [[ $actual -le $(($expected + $tolerance)) ]]; then + return 0 + fi + + now=$(date +%s) + elapsed=$((now - start_time)) + + if [[ $elapsed -ge $timeout ]]; then + echo "actual = $((${actual%% *} / 1024 / 1024)) MB" + echo "expected = $((${expected%% *} / 1024 / 1024)) MB" + cleanup + exit 1 + fi + + sleep $interval + done +} + function assert_state() { local expected_a="$1" local expected_a_hugetlb="$2" @@ -69,58 +105,13 @@ function assert_state() { expected_b="$3" expected_b_hugetlb="$4" fi - local tolerance=$((5 * 1024 * 1024)) - - local actual_a - actual_a="$(cat "$CGROUP_ROOT"/a/memory.$usage_file)" - if [[ $actual_a -lt $(($expected_a - $tolerance)) ]] || - [[ $actual_a -gt $(($expected_a + $tolerance)) ]]; then - echo actual a = $((${actual_a%% *} / 1024 / 1024)) MB - echo expected a = $((${expected_a%% *} / 1024 / 1024)) MB - echo fail - - cleanup - exit 1 - fi - - local actual_a_hugetlb - actual_a_hugetlb="$(cat "$CGROUP_ROOT"/a/hugetlb.${MB}MB.$usage_file)" - if [[ $actual_a_hugetlb -lt $(($expected_a_hugetlb - $tolerance)) ]] || - [[ $actual_a_hugetlb -gt $(($expected_a_hugetlb + $tolerance)) ]]; then - echo actual a hugetlb = $((${actual_a_hugetlb%% *} / 1024 / 1024)) MB - echo expected a hugetlb = $((${expected_a_hugetlb%% *} / 1024 / 1024)) MB - echo fail - - cleanup - exit 1 - fi - - if [[ -z "$expected_b" || -z "$expected_b_hugetlb" ]]; then - return - fi - local actual_b - actual_b="$(cat "$CGROUP_ROOT"/a/b/memory.$usage_file)" - if [[ $actual_b -lt $(($expected_b - $tolerance)) ]] || - [[ $actual_b -gt $(($expected_b + $tolerance)) ]]; then - echo actual b = $((${actual_b%% *} / 1024 / 1024)) MB - echo expected b = $((${expected_b%% *} / 1024 / 1024)) MB - echo fail + assert_with_retry "$CGROUP_ROOT/a/memory.$usage_file" "$expected_a" + assert_with_retry "$CGROUP_ROOT/a/hugetlb.${MB}MB.$usage_file" "$expected_a_hugetlb" - cleanup - exit 1 - fi - - local actual_b_hugetlb - actual_b_hugetlb="$(cat "$CGROUP_ROOT"/a/b/hugetlb.${MB}MB.$usage_file)" - if [[ $actual_b_hugetlb -lt $(($expected_b_hugetlb - $tolerance)) ]] || - [[ $actual_b_hugetlb -gt $(($expected_b_hugetlb + $tolerance)) ]]; then - echo actual b hugetlb = $((${actual_b_hugetlb%% *} / 1024 / 1024)) MB - echo expected b hugetlb = $((${expected_b_hugetlb%% *} / 1024 / 1024)) MB - echo fail - - cleanup - exit 1 + if [[ -n "$expected_b" && -n "$expected_b_hugetlb" ]]; then + assert_with_retry "$CGROUP_ROOT/a/b/memory.$usage_file" "$expected_b" + assert_with_retry "$CGROUP_ROOT/a/b/hugetlb.${MB}MB.$usage_file" "$expected_b_hugetlb" fi } @@ -174,7 +165,6 @@ size=$((${MB} * 1024 * 1024 * 25)) # 50MB = 25 * 2MB hugepages. cleanup echo -echo echo Test charge, rmdir, uncharge setup echo mkdir @@ -194,7 +184,6 @@ cleanup echo done echo -echo if [[ ! $cgroup2 ]]; then echo "Test parent and child hugetlb usage" setup @@ -211,7 +200,6 @@ if [[ ! $cgroup2 ]]; then assert_state 0 $(($size * 2)) 0 $size rmdir "$CGROUP_ROOT"/a/b - sleep 5 echo Assert memory reparent correctly. assert_state 0 $(($size * 2)) @@ -224,7 +212,6 @@ if [[ ! $cgroup2 ]]; then fi echo -echo echo "Test child only hugetlb usage" echo setup setup @@ -248,5 +235,9 @@ cleanup echo ALL PASS -umount $CGROUP_ROOT -rm -rf $CGROUP_ROOT +if [[ $do_umount ]]; then + umount $CGROUP_ROOT + rm -rf $CGROUP_ROOT +fi + +echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 030667cb5533..3fe7ef04ac62 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -22,13 +22,14 @@ #include "linux/magic.h" #include "vm_util.h" +#include "thp_settings.h" #define BASE_ADDR ((void *)(1UL << 30)) static unsigned long hpage_pmd_size; static unsigned long page_size; static int hpage_pmd_nr; +static int anon_order; -#define THP_SYSFS "/sys/kernel/mm/transparent_hugepage/" #define PID_SMAPS "/proc/self/smaps" #define TEST_FILE "collapse_test_file" @@ -71,78 +72,7 @@ struct file_info { }; static struct file_info finfo; - -enum thp_enabled { - THP_ALWAYS, - THP_MADVISE, - THP_NEVER, -}; - -static const char *thp_enabled_strings[] = { - "always", - "madvise", - "never", - NULL -}; - -enum thp_defrag { - THP_DEFRAG_ALWAYS, - THP_DEFRAG_DEFER, - THP_DEFRAG_DEFER_MADVISE, - THP_DEFRAG_MADVISE, - THP_DEFRAG_NEVER, -}; - -static const char *thp_defrag_strings[] = { - "always", - "defer", - "defer+madvise", - "madvise", - "never", - NULL -}; - -enum shmem_enabled { - SHMEM_ALWAYS, - SHMEM_WITHIN_SIZE, - SHMEM_ADVISE, - SHMEM_NEVER, - SHMEM_DENY, - SHMEM_FORCE, -}; - -static const char *shmem_enabled_strings[] = { - "always", - "within_size", - "advise", - "never", - "deny", - "force", - NULL -}; - -struct khugepaged_settings { - bool defrag; - unsigned int alloc_sleep_millisecs; - unsigned int scan_sleep_millisecs; - unsigned int max_ptes_none; - unsigned int max_ptes_swap; - unsigned int max_ptes_shared; - unsigned long pages_to_scan; -}; - -struct settings { - enum thp_enabled thp_enabled; - enum thp_defrag thp_defrag; - enum shmem_enabled shmem_enabled; - bool use_zero_page; - struct khugepaged_settings khugepaged; - unsigned long read_ahead_kb; -}; - -static struct settings saved_settings; static bool skip_settings_restore; - static int exit_status; static void success(const char *msg) @@ -161,260 +91,34 @@ static void skip(const char *msg) printf(" \e[33m%s\e[0m\n", msg); } -static int read_file(const char *path, char *buf, size_t buflen) -{ - int fd; - ssize_t numread; - - fd = open(path, O_RDONLY); - if (fd == -1) - return 0; - - numread = read(fd, buf, buflen - 1); - if (numread < 1) { - close(fd); - return 0; - } - - buf[numread] = '\0'; - close(fd); - - return (unsigned int) numread; -} - -static int write_file(const char *path, const char *buf, size_t buflen) -{ - int fd; - ssize_t numwritten; - - fd = open(path, O_WRONLY); - if (fd == -1) { - printf("open(%s)\n", path); - exit(EXIT_FAILURE); - return 0; - } - - numwritten = write(fd, buf, buflen - 1); - close(fd); - if (numwritten < 1) { - printf("write(%s)\n", buf); - exit(EXIT_FAILURE); - return 0; - } - - return (unsigned int) numwritten; -} - -static int read_string(const char *name, const char *strings[]) -{ - char path[PATH_MAX]; - char buf[256]; - char *c; - int ret; - - ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); - if (ret >= PATH_MAX) { - printf("%s: Pathname is too long\n", __func__); - exit(EXIT_FAILURE); - } - - if (!read_file(path, buf, sizeof(buf))) { - perror(path); - exit(EXIT_FAILURE); - } - - c = strchr(buf, '['); - if (!c) { - printf("%s: Parse failure\n", __func__); - exit(EXIT_FAILURE); - } - - c++; - memmove(buf, c, sizeof(buf) - (c - buf)); - - c = strchr(buf, ']'); - if (!c) { - printf("%s: Parse failure\n", __func__); - exit(EXIT_FAILURE); - } - *c = '\0'; - - ret = 0; - while (strings[ret]) { - if (!strcmp(strings[ret], buf)) - return ret; - ret++; - } - - printf("Failed to parse %s\n", name); - exit(EXIT_FAILURE); -} - -static void write_string(const char *name, const char *val) -{ - char path[PATH_MAX]; - int ret; - - ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); - if (ret >= PATH_MAX) { - printf("%s: Pathname is too long\n", __func__); - exit(EXIT_FAILURE); - } - - if (!write_file(path, val, strlen(val) + 1)) { - perror(path); - exit(EXIT_FAILURE); - } -} - -static const unsigned long _read_num(const char *path) +static void restore_settings_atexit(void) { - char buf[21]; - - if (read_file(path, buf, sizeof(buf)) < 0) { - perror("read_file(read_num)"); - exit(EXIT_FAILURE); - } - - return strtoul(buf, NULL, 10); -} - -static const unsigned long read_num(const char *name) -{ - char path[PATH_MAX]; - int ret; - - ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); - if (ret >= PATH_MAX) { - printf("%s: Pathname is too long\n", __func__); - exit(EXIT_FAILURE); - } - return _read_num(path); -} - -static void _write_num(const char *path, unsigned long num) -{ - char buf[21]; - - sprintf(buf, "%ld", num); - if (!write_file(path, buf, strlen(buf) + 1)) { - perror(path); - exit(EXIT_FAILURE); - } -} - -static void write_num(const char *name, unsigned long num) -{ - char path[PATH_MAX]; - int ret; - - ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); - if (ret >= PATH_MAX) { - printf("%s: Pathname is too long\n", __func__); - exit(EXIT_FAILURE); - } - _write_num(path, num); -} - -static void write_settings(struct settings *settings) -{ - struct khugepaged_settings *khugepaged = &settings->khugepaged; - - write_string("enabled", thp_enabled_strings[settings->thp_enabled]); - write_string("defrag", thp_defrag_strings[settings->thp_defrag]); - write_string("shmem_enabled", - shmem_enabled_strings[settings->shmem_enabled]); - write_num("use_zero_page", settings->use_zero_page); - - write_num("khugepaged/defrag", khugepaged->defrag); - write_num("khugepaged/alloc_sleep_millisecs", - khugepaged->alloc_sleep_millisecs); - write_num("khugepaged/scan_sleep_millisecs", - khugepaged->scan_sleep_millisecs); - write_num("khugepaged/max_ptes_none", khugepaged->max_ptes_none); - write_num("khugepaged/max_ptes_swap", khugepaged->max_ptes_swap); - write_num("khugepaged/max_ptes_shared", khugepaged->max_ptes_shared); - write_num("khugepaged/pages_to_scan", khugepaged->pages_to_scan); - - if (file_ops && finfo.type == VMA_FILE) - _write_num(finfo.dev_queue_read_ahead_path, - settings->read_ahead_kb); -} - -#define MAX_SETTINGS_DEPTH 4 -static struct settings settings_stack[MAX_SETTINGS_DEPTH]; -static int settings_index; - -static struct settings *current_settings(void) -{ - if (!settings_index) { - printf("Fail: No settings set"); - exit(EXIT_FAILURE); - } - return settings_stack + settings_index - 1; -} + if (skip_settings_restore) + return; -static void push_settings(struct settings *settings) -{ - if (settings_index >= MAX_SETTINGS_DEPTH) { - printf("Fail: Settings stack exceeded"); - exit(EXIT_FAILURE); - } - settings_stack[settings_index++] = *settings; - write_settings(current_settings()); -} + printf("Restore THP and khugepaged settings..."); + thp_restore_settings(); + success("OK"); -static void pop_settings(void) -{ - if (settings_index <= 0) { - printf("Fail: Settings stack empty"); - exit(EXIT_FAILURE); - } - --settings_index; - write_settings(current_settings()); + skip_settings_restore = true; } static void restore_settings(int sig) { - if (skip_settings_restore) - goto out; - - printf("Restore THP and khugepaged settings..."); - write_settings(&saved_settings); - success("OK"); - if (sig) - exit(EXIT_FAILURE); -out: - exit(exit_status); + /* exit() will invoke the restore_settings_atexit handler. */ + exit(sig ? EXIT_FAILURE : exit_status); } static void save_settings(void) { printf("Save THP and khugepaged settings..."); - saved_settings = (struct settings) { - .thp_enabled = read_string("enabled", thp_enabled_strings), - .thp_defrag = read_string("defrag", thp_defrag_strings), - .shmem_enabled = - read_string("shmem_enabled", shmem_enabled_strings), - .use_zero_page = read_num("use_zero_page"), - }; - saved_settings.khugepaged = (struct khugepaged_settings) { - .defrag = read_num("khugepaged/defrag"), - .alloc_sleep_millisecs = - read_num("khugepaged/alloc_sleep_millisecs"), - .scan_sleep_millisecs = - read_num("khugepaged/scan_sleep_millisecs"), - .max_ptes_none = read_num("khugepaged/max_ptes_none"), - .max_ptes_swap = read_num("khugepaged/max_ptes_swap"), - .max_ptes_shared = read_num("khugepaged/max_ptes_shared"), - .pages_to_scan = read_num("khugepaged/pages_to_scan"), - }; if (file_ops && finfo.type == VMA_FILE) - saved_settings.read_ahead_kb = - _read_num(finfo.dev_queue_read_ahead_path); + thp_set_read_ahead_path(finfo.dev_queue_read_ahead_path); + thp_save_settings(); success("OK"); + atexit(restore_settings_atexit); signal(SIGTERM, restore_settings); signal(SIGINT, restore_settings); signal(SIGHUP, restore_settings); @@ -690,7 +394,7 @@ static void *file_setup_area(int nr_hpages) perror("open()"); exit(EXIT_FAILURE); } - p = mmap(BASE_ADDR, size, PROT_READ | PROT_EXEC, + p = mmap(BASE_ADDR, size, PROT_READ, MAP_PRIVATE, finfo.fd, 0); if (p == MAP_FAILED || p != BASE_ADDR) { perror("mmap()"); @@ -793,7 +497,7 @@ static void __madvise_collapse(const char *msg, char *p, int nr_hpages, struct mem_ops *ops, bool expect) { int ret; - struct settings settings = *current_settings(); + struct thp_settings settings = *thp_current_settings(); printf("%s...", msg); @@ -803,7 +507,7 @@ static void __madvise_collapse(const char *msg, char *p, int nr_hpages, */ settings.thp_enabled = THP_NEVER; settings.shmem_enabled = SHMEM_NEVER; - push_settings(&settings); + thp_push_settings(&settings); /* Clear VM_NOHUGEPAGE */ madvise(p, nr_hpages * hpage_pmd_size, MADV_HUGEPAGE); @@ -815,7 +519,7 @@ static void __madvise_collapse(const char *msg, char *p, int nr_hpages, else success("OK"); - pop_settings(); + thp_pop_settings(); } static void madvise_collapse(const char *msg, char *p, int nr_hpages, @@ -845,20 +549,18 @@ static bool wait_for_scan(const char *msg, char *p, int nr_hpages, madvise(p, nr_hpages * hpage_pmd_size, MADV_HUGEPAGE); /* Wait until the second full_scan completed */ - full_scans = read_num("khugepaged/full_scans") + 2; + full_scans = thp_read_num("khugepaged/full_scans") + 2; printf("%s...", msg); while (timeout--) { if (ops->check_huge(p, nr_hpages)) break; - if (read_num("khugepaged/full_scans") >= full_scans) + if (thp_read_num("khugepaged/full_scans") >= full_scans) break; printf("."); usleep(TICK); } - madvise(p, nr_hpages * hpage_pmd_size, MADV_NOHUGEPAGE); - return timeout == -1; } @@ -904,13 +606,18 @@ static bool is_tmpfs(struct mem_ops *ops) return ops == &__file_ops && finfo.type == VMA_SHMEM; } +static bool is_anon(struct mem_ops *ops) +{ + return ops == &__anon_ops; +} + static void alloc_at_fault(void) { - struct settings settings = *current_settings(); + struct thp_settings settings = *thp_current_settings(); char *p; settings.thp_enabled = THP_ALWAYS; - push_settings(&settings); + thp_push_settings(&settings); p = alloc_mapping(1); *p = 1; @@ -920,7 +627,7 @@ static void alloc_at_fault(void) else fail("Fail"); - pop_settings(); + thp_pop_settings(); madvise(p, page_size, MADV_DONTNEED); printf("Split huge PMD on MADV_DONTNEED..."); @@ -968,11 +675,12 @@ static void collapse_single_pte_entry(struct collapse_context *c, struct mem_ops static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *ops) { int max_ptes_none = hpage_pmd_nr / 2; - struct settings settings = *current_settings(); + struct thp_settings settings = *thp_current_settings(); void *p; + int fault_nr_pages = is_anon(ops) ? 1 << anon_order : 1; settings.khugepaged.max_ptes_none = max_ptes_none; - push_settings(&settings); + thp_push_settings(&settings); p = ops->setup_area(1); @@ -983,10 +691,10 @@ static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *o goto skip; } - ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); + ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none - fault_nr_pages) * page_size); c->collapse("Maybe collapse with max_ptes_none exceeded", p, 1, ops, !c->enforce_pte_scan_limits); - validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); + validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - fault_nr_pages) * page_size); if (c->enforce_pte_scan_limits) { ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); @@ -997,7 +705,7 @@ static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *o } skip: ops->cleanup_area(p, hpage_pmd_size); - pop_settings(); + thp_pop_settings(); } static void collapse_swapin_single_pte(struct collapse_context *c, struct mem_ops *ops) @@ -1028,7 +736,7 @@ out: static void collapse_max_ptes_swap(struct collapse_context *c, struct mem_ops *ops) { - int max_ptes_swap = read_num("khugepaged/max_ptes_swap"); + int max_ptes_swap = thp_read_num("khugepaged/max_ptes_swap"); void *p; p = ops->setup_area(1); @@ -1245,11 +953,11 @@ static void collapse_fork_compound(struct collapse_context *c, struct mem_ops *o fail("Fail"); ops->fault(p, 0, page_size); - write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1); + thp_write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1); c->collapse("Collapse PTE table full of compound pages in child", p, 1, ops, true); - write_num("khugepaged/max_ptes_shared", - current_settings()->khugepaged.max_ptes_shared); + thp_write_num("khugepaged/max_ptes_shared", + thp_current_settings()->khugepaged.max_ptes_shared); validate_memory(p, 0, hpage_pmd_size); ops->cleanup_area(p, hpage_pmd_size); @@ -1270,7 +978,7 @@ static void collapse_fork_compound(struct collapse_context *c, struct mem_ops *o static void collapse_max_ptes_shared(struct collapse_context *c, struct mem_ops *ops) { - int max_ptes_shared = read_num("khugepaged/max_ptes_shared"); + int max_ptes_shared = thp_read_num("khugepaged/max_ptes_shared"); int wstatus; void *p; @@ -1373,7 +1081,7 @@ static void madvise_retracted_page_tables(struct collapse_context *c, static void usage(void) { - fprintf(stderr, "\nUsage: ./khugepaged <test type> [dir]\n\n"); + fprintf(stderr, "\nUsage: ./khugepaged [OPTIONS] <test type> [dir]\n\n"); fprintf(stderr, "\t<test type>\t: <context>:<mem_type>\n"); fprintf(stderr, "\t<context>\t: [all|khugepaged|madvise]\n"); fprintf(stderr, "\t<mem_type>\t: [all|anon|file|shmem]\n"); @@ -1381,16 +1089,35 @@ static void usage(void) fprintf(stderr, "\n\t\"file,all\" mem_type requires kernel built with\n"); fprintf(stderr, "\tCONFIG_READ_ONLY_THP_FOR_FS=y\n"); fprintf(stderr, "\n\tif [dir] is a (sub)directory of a tmpfs mount, tmpfs must be\n"); - fprintf(stderr, "\tmounted with huge=madvise option for khugepaged tests to work\n"); + fprintf(stderr, "\tmounted with huge=advise option for khugepaged tests to work\n"); + fprintf(stderr, "\n\tSupported Options:\n"); + fprintf(stderr, "\t\t-h: This help message.\n"); + fprintf(stderr, "\t\t-s: mTHP size, expressed as page order.\n"); + fprintf(stderr, "\t\t Defaults to 0. Use this size for anon or shmem allocations.\n"); exit(1); } -static void parse_test_type(int argc, const char **argv) +static void parse_test_type(int argc, char **argv) { + int opt; char *buf; const char *token; - if (argc == 1) { + while ((opt = getopt(argc, argv, "s:h")) != -1) { + switch (opt) { + case 's': + anon_order = atoi(optarg); + break; + case 'h': + default: + usage(); + } + } + + argv += optind; + argc -= optind; + + if (argc == 0) { /* Backwards compatibility */ khugepaged_context = &__khugepaged_context; madvise_context = &__madvise_context; @@ -1398,7 +1125,7 @@ static void parse_test_type(int argc, const char **argv) return; } - buf = strdup(argv[1]); + buf = strdup(argv[0]); token = strsep(&buf, ":"); if (!strcmp(token, "all")) { @@ -1432,13 +1159,16 @@ static void parse_test_type(int argc, const char **argv) if (!file_ops) return; - if (argc != 3) + if (argc != 2) usage(); + + get_finfo(argv[1]); } -int main(int argc, const char **argv) +int main(int argc, char **argv) { - struct settings default_settings = { + int hpage_pmd_order; + struct thp_settings default_settings = { .thp_enabled = THP_MADVISE, .thp_defrag = THP_DEFRAG_ALWAYS, .shmem_enabled = SHMEM_ADVISE, @@ -1458,10 +1188,12 @@ int main(int argc, const char **argv) .read_ahead_kb = 0, }; - parse_test_type(argc, argv); + if (!thp_is_enabled()) { + printf("Transparent Hugepages not available\n"); + return KSFT_SKIP; + } - if (file_ops) - get_finfo(argv[2]); + parse_test_type(argc, argv); setbuf(stdout, NULL); @@ -1472,14 +1204,19 @@ int main(int argc, const char **argv) exit(EXIT_FAILURE); } hpage_pmd_nr = hpage_pmd_size / page_size; + hpage_pmd_order = __builtin_ctz(hpage_pmd_nr); default_settings.khugepaged.max_ptes_none = hpage_pmd_nr - 1; default_settings.khugepaged.max_ptes_swap = hpage_pmd_nr / 8; default_settings.khugepaged.max_ptes_shared = hpage_pmd_nr / 2; default_settings.khugepaged.pages_to_scan = hpage_pmd_nr * 8; + default_settings.hugepages[hpage_pmd_order].enabled = THP_INHERIT; + default_settings.hugepages[anon_order].enabled = THP_ALWAYS; + default_settings.shmem_hugepages[hpage_pmd_order].enabled = SHMEM_INHERIT; + default_settings.shmem_hugepages[anon_order].enabled = SHMEM_ALWAYS; save_settings(); - push_settings(&default_settings); + thp_push_settings(&default_settings); alloc_at_fault(); diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index 26853badae70..8d874c4754f3 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -21,17 +21,30 @@ #include <sys/wait.h> #include <linux/userfaultfd.h> -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" #define KiB 1024u #define MiB (1024 * KiB) +#define FORK_EXEC_CHILD_PRG_NAME "ksm_fork_exec_child" -static int ksm_fd; -static int ksm_full_scans_fd; +#define MAP_MERGE_FAIL ((void *)-1) +#define MAP_MERGE_SKIP ((void *)-2) + +enum ksm_merge_mode { + KSM_MERGE_PRCTL, + KSM_MERGE_MADVISE, + KSM_MERGE_NONE, /* PRCTL already set */ +}; + +static int mem_fd; +static int pages_to_scan_fd; +static int sleep_millisecs_fd; static int pagemap_fd; static size_t pagesize; +static void init_global_file_handles(void); + static bool range_maps_duplicates(char *addr, unsigned long size) { unsigned long offs_a, offs_b, pfn_a, pfn_b; @@ -59,82 +72,104 @@ static bool range_maps_duplicates(char *addr, unsigned long size) return false; } -static long ksm_get_full_scans(void) -{ - char buf[10]; - ssize_t ret; - - ret = pread(ksm_full_scans_fd, buf, sizeof(buf) - 1, 0); - if (ret <= 0) - return -errno; - buf[ret] = 0; - - return strtol(buf, NULL, 10); -} - -static int ksm_merge(void) -{ - long start_scans, end_scans; - - /* Wait for two full scans such that any possible merging happened. */ - start_scans = ksm_get_full_scans(); - if (start_scans < 0) - return start_scans; - if (write(ksm_fd, "1", 1) != 1) - return -errno; - do { - end_scans = ksm_get_full_scans(); - if (end_scans < 0) - return end_scans; - } while (end_scans < start_scans + 2); - - return 0; -} - -static char *mmap_and_merge_range(char val, unsigned long size, bool use_prctl) +static char *__mmap_and_merge_range(char val, unsigned long size, int prot, + enum ksm_merge_mode mode) { char *map; + char *err_map = MAP_MERGE_FAIL; int ret; + /* Stabilize accounting by disabling KSM completely. */ + if (ksm_stop() < 0) { + ksft_print_msg("Disabling (unmerging) KSM failed\n"); + return err_map; + } + + if (ksm_get_self_merging_pages() > 0) { + ksft_print_msg("Still pages merged\n"); + return err_map; + } + map = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0); if (map == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); - return MAP_FAILED; + ksft_print_msg("mmap() failed\n"); + return err_map; } /* Don't use THP. Ignore if THP are not around on a kernel. */ if (madvise(map, size, MADV_NOHUGEPAGE) && errno != EINVAL) { - ksft_test_result_fail("MADV_NOHUGEPAGE failed\n"); + ksft_print_msg("MADV_NOHUGEPAGE failed\n"); goto unmap; } /* Make sure each page contains the same values to merge them. */ memset(map, val, size); - if (use_prctl) { + if (mprotect(map, size, prot)) { + ksft_print_msg("mprotect() failed\n"); + err_map = MAP_MERGE_SKIP; + goto unmap; + } + + switch (mode) { + case KSM_MERGE_PRCTL: ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); if (ret < 0 && errno == EINVAL) { - ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n"); + ksft_print_msg("PR_SET_MEMORY_MERGE not supported\n"); + err_map = MAP_MERGE_SKIP; goto unmap; } else if (ret) { - ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n"); + ksft_print_msg("PR_SET_MEMORY_MERGE=1 failed\n"); goto unmap; } - } else if (madvise(map, size, MADV_MERGEABLE)) { - ksft_test_result_fail("MADV_MERGEABLE failed\n"); - goto unmap; + break; + case KSM_MERGE_MADVISE: + if (madvise(map, size, MADV_MERGEABLE)) { + ksft_print_msg("MADV_MERGEABLE failed\n"); + goto unmap; + } + break; + case KSM_MERGE_NONE: + break; } /* Run KSM to trigger merging and wait. */ - if (ksm_merge()) { - ksft_test_result_fail("Running KSM failed\n"); + if (ksm_start() < 0) { + ksft_print_msg("Running KSM failed\n"); goto unmap; } + + /* + * Check if anything was merged at all. Ignore the zero page that is + * accounted differently (depending on kernel support). + */ + if (val && !ksm_get_self_merging_pages()) { + ksft_print_msg("No pages got merged\n"); + goto unmap; + } + return map; unmap: munmap(map, size); - return MAP_FAILED; + return err_map; +} + +static char *mmap_and_merge_range(char val, unsigned long size, int prot, + enum ksm_merge_mode mode) +{ + char *map; + char *ret = MAP_FAILED; + + map = __mmap_and_merge_range(val, size, prot, mode); + if (map == MAP_MERGE_FAIL) + ksft_test_result_fail("Merging memory failed"); + else if (map == MAP_MERGE_SKIP) + ksft_test_result_skip("Merging memory skipped"); + else + ret = map; + + return ret; } static void test_unmerge(void) @@ -144,7 +179,7 @@ static void test_unmerge(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, false); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_MADVISE); if (map == MAP_FAILED) return; @@ -156,6 +191,69 @@ static void test_unmerge(void) ksft_test_result(!range_maps_duplicates(map, size), "Pages were unmerged\n"); unmap: + ksm_stop(); + munmap(map, size); +} + +static void test_unmerge_zero_pages(void) +{ + const unsigned int size = 2 * MiB; + char *map; + unsigned int offs; + unsigned long pages_expected; + + ksft_print_msg("[RUN] %s\n", __func__); + + if (ksm_get_self_zero_pages() < 0) { + ksft_test_result_skip("accessing \"/proc/self/ksm_stat\" failed\n"); + return; + } + + if (ksm_use_zero_pages() < 0) { + ksft_test_result_skip("write \"/sys/kernel/mm/ksm/use_zero_pages\" failed\n"); + return; + } + + /* Let KSM deduplicate zero pages. */ + map = mmap_and_merge_range(0x00, size, PROT_READ | PROT_WRITE, KSM_MERGE_MADVISE); + if (map == MAP_FAILED) + return; + + /* Check if ksm_zero_pages is updated correctly after KSM merging */ + pages_expected = size / pagesize; + if (pages_expected != ksm_get_self_zero_pages()) { + ksft_test_result_fail("'ksm_zero_pages' updated after merging\n"); + goto unmap; + } + + /* Try to unmerge half of the region */ + if (madvise(map, size / 2, MADV_UNMERGEABLE)) { + ksft_test_result_fail("MADV_UNMERGEABLE failed\n"); + goto unmap; + } + + /* Check if ksm_zero_pages is updated correctly after unmerging */ + pages_expected /= 2; + if (pages_expected != ksm_get_self_zero_pages()) { + ksft_test_result_fail("'ksm_zero_pages' updated after unmerging\n"); + goto unmap; + } + + /* Trigger unmerging of the other half by writing to the pages. */ + for (offs = size / 2; offs < size; offs += pagesize) + *((unsigned int *)&map[offs]) = offs; + + /* Now we should have no zeropages remaining. */ + if (ksm_get_self_zero_pages()) { + ksft_test_result_fail("'ksm_zero_pages' updated after write fault\n"); + goto unmap; + } + + /* Check if ksm zero pages are really unmerged */ + ksft_test_result(!range_maps_duplicates(map, size), + "KSM zero pages were unmerged\n"); +unmap: + ksm_stop(); munmap(map, size); } @@ -166,7 +264,7 @@ static void test_unmerge_discarded(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, false); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_MADVISE); if (map == MAP_FAILED) return; @@ -184,6 +282,7 @@ static void test_unmerge_discarded(void) ksft_test_result(!range_maps_duplicates(map, size), "Pages were unmerged\n"); unmap: + ksm_stop(); munmap(map, size); } @@ -198,7 +297,7 @@ static void test_unmerge_uffd_wp(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, false); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_MADVISE); if (map == MAP_FAILED) return; @@ -211,9 +310,13 @@ static void test_unmerge_uffd_wp(void) /* See if UFFD-WP is around. */ uffdio_api.api = UFFD_API; - uffdio_api.features = UFFD_FEATURE_PAGEFAULT_FLAG_WP; + uffdio_api.features = 0; if (ioctl(uffd, UFFDIO_API, &uffdio_api) < 0) { - ksft_test_result_fail("UFFDIO_API failed\n"); + if (errno == EINVAL) + ksft_test_result_skip("The API version requested is not supported\n"); + else + ksft_test_result_fail("UFFDIO_API failed: %s\n", strerror(errno)); + goto close_uffd; } if (!(uffdio_api.features & UFFD_FEATURE_PAGEFAULT_FLAG_WP)) { @@ -221,6 +324,26 @@ static void test_unmerge_uffd_wp(void) goto close_uffd; } + /* + * UFFDIO_API must only be called once to enable features. + * So we close the old userfaultfd and create a new one to + * actually enable UFFD_FEATURE_PAGEFAULT_FLAG_WP. + */ + close(uffd); + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd < 0) { + ksft_test_result_fail("__NR_userfaultfd failed\n"); + goto unmap; + } + + /* Now, enable it ("two-step handshake") */ + uffdio_api.api = UFFD_API; + uffdio_api.features = UFFD_FEATURE_PAGEFAULT_FLAG_WP; + if (ioctl(uffd, UFFDIO_API, &uffdio_api) < 0) { + ksft_test_result_fail("UFFDIO_API failed: %s\n", strerror(errno)); + goto close_uffd; + } + /* Register UFFD-WP, no need for an actual handler. */ if (uffd_register(uffd, map, size, false, true, false)) { ksft_test_result_fail("UFFDIO_REGISTER_MODE_WP failed\n"); @@ -246,6 +369,7 @@ static void test_unmerge_uffd_wp(void) close_uffd: close(uffd); unmap: + ksm_stop(); munmap(map, size); } #endif @@ -293,6 +417,39 @@ static void test_prctl(void) ksft_test_result_pass("Setting/clearing PR_SET_MEMORY_MERGE works\n"); } +static int test_child_ksm(void) +{ + const unsigned int size = 2 * MiB; + char *map; + + /* Test if KSM is enabled for the process. */ + if (prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0) != 1) + return 1; + + /* Test if merge could really happen. */ + map = __mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_NONE); + if (map == MAP_MERGE_FAIL) + return 2; + else if (map == MAP_MERGE_SKIP) + return 3; + + ksm_stop(); + munmap(map, size); + return 0; +} + +static void test_child_ksm_err(int status) +{ + if (status == 1) + ksft_test_result_fail("unexpected PR_GET_MEMORY_MERGE result in child\n"); + else if (status == 2) + ksft_test_result_fail("Merge in child failed\n"); + else if (status == 3) + ksft_test_result_skip("Merge in child skipped\n"); + else if (status == 4) + ksft_test_result_fail("Binary not found\n"); +} + /* Verify that prctl ksm flag is inherited. */ static void test_prctl_fork(void) { @@ -312,7 +469,8 @@ static void test_prctl_fork(void) child_pid = fork(); if (!child_pid) { - exit(prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0)); + init_global_file_handles(); + exit(test_child_ksm()); } else if (child_pid < 0) { ksft_test_result_fail("fork() failed\n"); return; @@ -321,8 +479,11 @@ static void test_prctl_fork(void) if (waitpid(child_pid, &status, 0) < 0) { ksft_test_result_fail("waitpid() failed\n"); return; - } else if (WEXITSTATUS(status) != 1) { - ksft_test_result_fail("unexpected PR_GET_MEMORY_MERGE result in child\n"); + } + + status = WEXITSTATUS(status); + if (status) { + test_child_ksm_err(status); return; } @@ -334,6 +495,106 @@ static void test_prctl_fork(void) ksft_test_result_pass("PR_SET_MEMORY_MERGE value is inherited\n"); } +static int start_ksmd_and_set_frequency(char *pages_to_scan, char *sleep_ms) +{ + int ksm_fd; + + ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); + if (ksm_fd < 0) + return -errno; + + if (write(ksm_fd, "1", 1) != 1) + return -errno; + + if (write(pages_to_scan_fd, pages_to_scan, strlen(pages_to_scan)) <= 0) + return -errno; + + if (write(sleep_millisecs_fd, sleep_ms, strlen(sleep_ms)) <= 0) + return -errno; + + return 0; +} + +static int stop_ksmd_and_restore_frequency(void) +{ + int ksm_fd; + + ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); + if (ksm_fd < 0) + return -errno; + + if (write(ksm_fd, "2", 1) != 1) + return -errno; + + if (write(pages_to_scan_fd, "100", 3) <= 0) + return -errno; + + if (write(sleep_millisecs_fd, "20", 2) <= 0) + return -errno; + + return 0; +} + +static void test_prctl_fork_exec(void) +{ + int ret, status; + pid_t child_pid; + + ksft_print_msg("[RUN] %s\n", __func__); + + if (start_ksmd_and_set_frequency("2000", "0")) + ksft_test_result_fail("set ksmd's scanning frequency failed\n"); + + ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); + if (ret < 0 && errno == EINVAL) { + ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n"); + return; + } else if (ret) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n"); + return; + } + + child_pid = fork(); + if (child_pid == -1) { + ksft_test_result_skip("fork() failed\n"); + return; + } else if (child_pid == 0) { + char *prg_name = "./ksm_functional_tests"; + char *argv_for_program[] = { prg_name, FORK_EXEC_CHILD_PRG_NAME, NULL }; + + execv(prg_name, argv_for_program); + exit(4); + } + + if (waitpid(child_pid, &status, 0) > 0) { + if (WIFEXITED(status)) { + status = WEXITSTATUS(status); + if (status) { + test_child_ksm_err(status); + return; + } + } else { + ksft_test_result_fail("program didn't terminate normally\n"); + return; + } + } else { + ksft_test_result_fail("waitpid() failed\n"); + return; + } + + if (prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0)) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n"); + return; + } + + if (stop_ksmd_and_restore_frequency()) { + ksft_test_result_fail("restore ksmd frequency failed\n"); + return; + } + + ksft_test_result_pass("PR_SET_MEMORY_MERGE value is inherited\n"); +} + static void test_prctl_unmerge(void) { const unsigned int size = 2 * MiB; @@ -341,7 +602,7 @@ static void test_prctl_unmerge(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, true); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_PRCTL); if (map == MAP_FAILED) return; @@ -353,14 +614,117 @@ static void test_prctl_unmerge(void) ksft_test_result(!range_maps_duplicates(map, size), "Pages were unmerged\n"); unmap: + ksm_stop(); + munmap(map, size); +} + +static void test_prot_none(void) +{ + const unsigned int size = 2 * MiB; + char *map; + int i; + + ksft_print_msg("[RUN] %s\n", __func__); + + map = mmap_and_merge_range(0x11, size, PROT_NONE, KSM_MERGE_MADVISE); + if (map == MAP_FAILED) + goto unmap; + + /* Store a unique value in each page on one half using ptrace */ + for (i = 0; i < size / 2; i += pagesize) { + lseek(mem_fd, (uintptr_t) map + i, SEEK_SET); + if (write(mem_fd, &i, sizeof(i)) != sizeof(i)) { + ksft_test_result_fail("ptrace write failed\n"); + goto unmap; + } + } + + /* Trigger unsharing on the other half. */ + if (madvise(map + size / 2, size / 2, MADV_UNMERGEABLE)) { + ksft_test_result_fail("MADV_UNMERGEABLE failed\n"); + goto unmap; + } + + ksft_test_result(!range_maps_duplicates(map, size), + "Pages were unmerged\n"); +unmap: + ksm_stop(); + munmap(map, size); +} + +static void test_fork_ksm_merging_page_count(void) +{ + const unsigned int size = 2 * MiB; + char *map; + pid_t child_pid; + int status; + + ksft_print_msg("[RUN] %s\n", __func__); + + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_MADVISE); + if (map == MAP_FAILED) + return; + + child_pid = fork(); + if (!child_pid) { + init_global_file_handles(); + exit(ksm_get_self_merging_pages()); + } else if (child_pid < 0) { + ksft_test_result_fail("fork() failed\n"); + goto unmap; + } + + if (waitpid(child_pid, &status, 0) < 0) { + ksft_test_result_fail("waitpid() failed\n"); + goto unmap; + } + + status = WEXITSTATUS(status); + if (status) { + ksft_test_result_fail("ksm_merging_page in child: %d\n", status); + goto unmap; + } + + ksft_test_result_pass("ksm_merging_pages is not inherited after fork\n"); + +unmap: + ksm_stop(); munmap(map, size); } +static void init_global_file_handles(void) +{ + mem_fd = open("/proc/self/mem", O_RDWR); + if (mem_fd < 0) + ksft_exit_fail_msg("opening /proc/self/mem failed\n"); + if (ksm_stop() < 0) + ksft_exit_skip("accessing \"/sys/kernel/mm/ksm/run\") failed\n"); + if (ksm_get_full_scans() < 0) + ksft_exit_skip("accessing \"/sys/kernel/mm/ksm/full_scans\") failed\n"); + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd < 0) + ksft_exit_skip("open(\"/proc/self/pagemap\") failed\n"); + if (ksm_get_self_merging_pages() < 0) + ksft_exit_skip("accessing \"/proc/self/ksm_merging_pages\") failed\n"); + + pages_to_scan_fd = open("/sys/kernel/mm/ksm/pages_to_scan", O_RDWR); + if (pages_to_scan_fd < 0) + ksft_exit_fail_msg("opening /sys/kernel/mm/ksm/pages_to_scan failed\n"); + sleep_millisecs_fd = open("/sys/kernel/mm/ksm/sleep_millisecs", O_RDWR); + if (sleep_millisecs_fd < 0) + ksft_exit_fail_msg("opening /sys/kernel/mm/ksm/sleep_millisecs failed\n"); +} + int main(int argc, char **argv) { - unsigned int tests = 5; + unsigned int tests = 9; int err; + if (argc > 1 && !strcmp(argv[1], FORK_EXEC_CHILD_PRG_NAME)) { + init_global_file_handles(); + exit(test_child_ksm()); + } + #ifdef __NR_userfaultfd tests++; #endif @@ -370,29 +734,26 @@ int main(int argc, char **argv) pagesize = getpagesize(); - ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); - if (ksm_fd < 0) - ksft_exit_skip("open(\"/sys/kernel/mm/ksm/run\") failed\n"); - ksm_full_scans_fd = open("/sys/kernel/mm/ksm/full_scans", O_RDONLY); - if (ksm_full_scans_fd < 0) - ksft_exit_skip("open(\"/sys/kernel/mm/ksm/full_scans\") failed\n"); - pagemap_fd = open("/proc/self/pagemap", O_RDONLY); - if (pagemap_fd < 0) - ksft_exit_skip("open(\"/proc/self/pagemap\") failed\n"); + init_global_file_handles(); test_unmerge(); + test_unmerge_zero_pages(); test_unmerge_discarded(); #ifdef __NR_userfaultfd test_unmerge_uffd_wp(); #endif + test_prot_none(); + test_prctl(); test_prctl_fork(); + test_prctl_fork_exec(); test_prctl_unmerge(); + test_fork_ksm_merging_page_count(); err = ksft_get_fail_cnt(); if (err) ksft_exit_fail_msg("%d out of %d tests failed\n", err, ksft_test_num()); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index 435acebdc325..a0b48b839d54 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -12,9 +12,10 @@ #include <stdint.h> #include <err.h> -#include "../kselftest.h" +#include "kselftest.h" #include <include/vdso/time64.h> #include "vm_util.h" +#include "thp_settings.h" #define KSM_SYSFS_PATH "/sys/kernel/mm/ksm/" #define KSM_FP(s) (KSM_SYSFS_PATH s) @@ -58,40 +59,12 @@ int debug; static int ksm_write_sysfs(const char *file_path, unsigned long val) { - FILE *f = fopen(file_path, "w"); - - if (!f) { - fprintf(stderr, "f %s\n", file_path); - perror("fopen"); - return 1; - } - if (fprintf(f, "%lu", val) < 0) { - perror("fprintf"); - fclose(f); - return 1; - } - fclose(f); - - return 0; + return write_sysfs(file_path, val); } static int ksm_read_sysfs(const char *file_path, unsigned long *val) { - FILE *f = fopen(file_path, "r"); - - if (!f) { - fprintf(stderr, "f %s\n", file_path); - perror("fopen"); - return 1; - } - if (fscanf(f, "%lu", val) != 1) { - perror("fscanf"); - fclose(f); - return 1; - } - fclose(f); - - return 0; + return read_sysfs(file_path, val); } static void ksm_print_sysfs(void) @@ -555,6 +528,11 @@ static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot, unsigned long scan_time_ns; int pagemap_fd, n_normal_pages, n_huge_pages; + if (!thp_is_enabled()) { + printf("Transparent Hugepages not available\n"); + return KSFT_SKIP; + } + map_size *= MB; size_t len = map_size; @@ -566,7 +544,7 @@ static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot, if (map_ptr_orig == MAP_FAILED) err(2, "initial mmap"); - if (madvise(map_ptr, len + HPAGE_SIZE, MADV_HUGEPAGE)) + if (madvise(map_ptr, len, MADV_HUGEPAGE)) err(2, "MADV_HUGEPAGE"); pagemap_fd = open("/proc/self/pagemap", O_RDONLY); @@ -776,7 +754,7 @@ 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; @@ -831,6 +809,7 @@ int main(int argc, char *argv[]) printf("Size must be greater than 0\n"); return KSFT_FAIL; } + break; case 't': { int tmp = atoi(optarg); diff --git a/tools/testing/selftests/mm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c index 60547245e479..88050e0f829a 100644 --- a/tools/testing/selftests/mm/madv_populate.c +++ b/tools/testing/selftests/mm/madv_populate.c @@ -17,7 +17,7 @@ #include <linux/mman.h> #include <sys/mman.h> -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" /* @@ -172,12 +172,12 @@ static void test_populate_read(void) if (addr == MAP_FAILED) ksft_exit_fail_msg("mmap failed\n"); ksft_test_result(range_is_not_populated(addr, SIZE), - "range initially not populated\n"); + "read range initially not populated\n"); ret = madvise(addr, SIZE, MADV_POPULATE_READ); ksft_test_result(!ret, "MADV_POPULATE_READ\n"); ksft_test_result(range_is_populated(addr, SIZE), - "range is populated\n"); + "read range is populated\n"); munmap(addr, SIZE); } @@ -194,12 +194,12 @@ static void test_populate_write(void) if (addr == MAP_FAILED) ksft_exit_fail_msg("mmap failed\n"); ksft_test_result(range_is_not_populated(addr, SIZE), - "range initially not populated\n"); + "write range initially not populated\n"); ret = madvise(addr, SIZE, MADV_POPULATE_WRITE); ksft_test_result(!ret, "MADV_POPULATE_WRITE\n"); ksft_test_result(range_is_populated(addr, SIZE), - "range is populated\n"); + "write range is populated\n"); munmap(addr, SIZE); } @@ -247,31 +247,35 @@ static void test_softdirty(void) /* Clear any softdirty bits. */ clear_softdirty(); ksft_test_result(range_is_not_softdirty(addr, SIZE), - "range is not softdirty\n"); + "cleared range is not softdirty\n"); /* Populating READ should set softdirty. */ ret = madvise(addr, SIZE, MADV_POPULATE_READ); - ksft_test_result(!ret, "MADV_POPULATE_READ\n"); + ksft_test_result(!ret, "softdirty MADV_POPULATE_READ\n"); ksft_test_result(range_is_not_softdirty(addr, SIZE), - "range is not softdirty\n"); + "range is not softdirty after MADV_POPULATE_READ\n"); /* Populating WRITE should set softdirty. */ ret = madvise(addr, SIZE, MADV_POPULATE_WRITE); - ksft_test_result(!ret, "MADV_POPULATE_WRITE\n"); + ksft_test_result(!ret, "softdirty MADV_POPULATE_WRITE\n"); ksft_test_result(range_is_softdirty(addr, SIZE), - "range is softdirty\n"); + "range is softdirty after MADV_POPULATE_WRITE \n"); munmap(addr, SIZE); } int main(int argc, char **argv) { + int nr_tests = 16; int err; pagesize = getpagesize(); + if (softdirty_supported()) + nr_tests += 5; + ksft_print_header(); - ksft_set_plan(21); + ksft_set_plan(nr_tests); sense_support(); test_prot_read(); @@ -279,11 +283,12 @@ int main(int argc, char **argv) test_holes(); test_populate_read(); test_populate_write(); - test_softdirty(); + if (softdirty_supported()) + test_softdirty(); err = ksft_get_fail_cnt(); if (err) ksft_exit_fail_msg("%d out of %d tests failed\n", err, ksft_test_num()); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/map_fixed_noreplace.c b/tools/testing/selftests/mm/map_fixed_noreplace.c index 598159f3df1f..11241edde7fe 100644 --- a/tools/testing/selftests/mm/map_fixed_noreplace.c +++ b/tools/testing/selftests/mm/map_fixed_noreplace.c @@ -12,6 +12,7 @@ #include <stdio.h> #include <stdlib.h> #include <unistd.h> +#include "kselftest.h" static void dump_maps(void) { @@ -28,15 +29,12 @@ static unsigned long find_base_addr(unsigned long size) flags = MAP_PRIVATE | MAP_ANONYMOUS; addr = mmap(NULL, size, PROT_NONE, flags, -1, 0); - if (addr == MAP_FAILED) { - printf("Error: couldn't map the space we need for the test\n"); - return 0; - } + if (addr == MAP_FAILED) + ksft_exit_fail_msg("Error: couldn't map the space we need for the test\n"); + + if (munmap(addr, size) != 0) + ksft_exit_fail_msg("Error: munmap failed\n"); - if (munmap(addr, size) != 0) { - printf("Error: couldn't map the space we need for the test\n"); - return 0; - } return (unsigned long)addr; } @@ -46,51 +44,41 @@ int main(void) unsigned long flags, addr, size, page_size; char *p; + ksft_print_header(); + ksft_set_plan(9); + page_size = sysconf(_SC_PAGE_SIZE); - //let's find a base addr that is free before we start the tests + /* let's find a base addr that is free before we start the tests */ size = 5 * page_size; base_addr = find_base_addr(size); - if (!base_addr) { - printf("Error: couldn't map the space we need for the test\n"); - return 1; - } flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE; - // Check we can map all the areas we need below - errno = 0; + /* Check we can map all the areas we need below */ addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p == MAP_FAILED) { dump_maps(); - printf("Error: couldn't map the space we need for the test\n"); - return 1; + ksft_exit_fail_msg("Error: couldn't map the space we need for the test\n"); } - - errno = 0; if (munmap((void *)addr, 5 * page_size) != 0) { dump_maps(); - printf("Error: munmap failed!?\n"); - return 1; + ksft_exit_fail_msg("Error: munmap failed!?\n"); } - printf("unmap() successful\n"); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 5*PAGE_SIZE at base\n"); - errno = 0; addr = base_addr + page_size; size = 3 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p == MAP_FAILED) { dump_maps(); - printf("Error: first mmap() failed unexpectedly\n"); - return 1; + ksft_exit_fail_msg("Error: first mmap() failed unexpectedly\n"); } + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 3*PAGE_SIZE at base+PAGE_SIZE\n"); /* * Exact same mapping again: @@ -100,17 +88,15 @@ int main(void) * +3 | mapped | new * +4 | free | new */ - errno = 0; addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p != MAP_FAILED) { dump_maps(); - printf("Error:1: mmap() succeeded when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:1: mmap() succeeded when it shouldn't have\n"); } + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("Second mmap() 5*PAGE_SIZE at base\n"); /* * Second mapping contained within first: @@ -121,17 +107,15 @@ int main(void) * +3 | mapped | * +4 | free | */ - errno = 0; addr = base_addr + (2 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p != MAP_FAILED) { dump_maps(); - printf("Error:2: mmap() succeeded when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:2: mmap() succeeded when it shouldn't have\n"); } + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 2*PAGE_SIZE at base+PAGE_SIZE\n"); /* * Overlap end of existing mapping: @@ -141,17 +125,15 @@ int main(void) * +3 | mapped | new * +4 | free | new */ - errno = 0; addr = base_addr + (3 * page_size); size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p != MAP_FAILED) { dump_maps(); - printf("Error:3: mmap() succeeded when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:3: mmap() succeeded when it shouldn't have\n"); } + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 2*PAGE_SIZE at base+(3*PAGE_SIZE)\n"); /* * Overlap start of existing mapping: @@ -161,17 +143,15 @@ int main(void) * +3 | mapped | * +4 | free | */ - errno = 0; addr = base_addr; size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p != MAP_FAILED) { dump_maps(); - printf("Error:4: mmap() succeeded when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:4: mmap() succeeded when it shouldn't have\n"); } + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 2*PAGE_SIZE bytes at base\n"); /* * Adjacent to start of existing mapping: @@ -181,17 +161,15 @@ int main(void) * +3 | mapped | * +4 | free | */ - errno = 0; addr = base_addr; size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p == MAP_FAILED) { dump_maps(); - printf("Error:5: mmap() failed when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:5: mmap() failed when it shouldn't have\n"); } + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() PAGE_SIZE at base\n"); /* * Adjacent to end of existing mapping: @@ -201,27 +179,23 @@ int main(void) * +3 | mapped | * +4 | free | new */ - errno = 0; addr = base_addr + (4 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); - printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); - if (p == MAP_FAILED) { dump_maps(); - printf("Error:6: mmap() failed when it shouldn't have\n"); - return 1; + ksft_exit_fail_msg("Error:6: mmap() failed when it shouldn't have\n"); } + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() PAGE_SIZE at base+(4*PAGE_SIZE)\n"); addr = base_addr; size = 5 * page_size; if (munmap((void *)addr, size) != 0) { dump_maps(); - printf("Error: munmap failed!?\n"); - return 1; + ksft_exit_fail_msg("Error: munmap failed!?\n"); } - printf("unmap() successful\n"); + ksft_test_result_pass("Base Address unmap() successful\n"); - printf("OK\n"); - return 0; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c index 193281560b61..aa409107611b 100644 --- a/tools/testing/selftests/mm/map_hugetlb.c +++ b/tools/testing/selftests/mm/map_hugetlb.c @@ -4,33 +4,21 @@ * system call with MAP_HUGETLB flag. Before running this program make * sure the administrator has allocated enough default sized huge pages * to cover the 256 MB allocation. - * - * For ia64 architecture, Linux kernel reserves Region number 4 for hugepages. - * That means the addresses starting with 0x800000... will need to be - * specified. Specifying a fixed address is not required on ppc64, i386 - * or x86_64. */ #include <stdlib.h> #include <stdio.h> #include <unistd.h> #include <sys/mman.h> #include <fcntl.h> +#include "vm_util.h" +#include "kselftest.h" #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) -/* Only ia64 requires this */ -#ifdef __ia64__ -#define ADDR (void *)(0x8000000000000000UL) -#define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_FIXED) -#else -#define ADDR (void *)(0x0UL) -#define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB) -#endif - static void check_bytes(char *addr) { - printf("First hex is %x\n", *((unsigned int *)addr)); + ksft_print_msg("First hex is %x\n", *((unsigned int *)addr)); } static void write_bytes(char *addr, size_t length) @@ -41,27 +29,34 @@ static void write_bytes(char *addr, size_t length) *(addr + i) = (char)i; } -static int read_bytes(char *addr, size_t length) +static void read_bytes(char *addr, size_t length) { unsigned long i; check_bytes(addr); for (i = 0; i < length; i++) - if (*(addr + i) != (char)i) { - printf("Mismatch at %lu\n", i); - return 1; - } - return 0; + if (*(addr + i) != (char)i) + ksft_exit_fail_msg("Mismatch at %lu\n", i); + + ksft_test_result_pass("Read correct data\n"); } int main(int argc, char **argv) { void *addr; - int ret; + size_t hugepage_size; size_t length = LENGTH; - int flags = FLAGS; + int flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB; int shift = 0; + hugepage_size = default_huge_page_size(); + /* munmap with fail if the length is not page aligned */ + if (hugepage_size > length) + length = hugepage_size; + + ksft_print_header(); + ksft_set_plan(1); + if (argc > 1) length = atol(argv[1]) << 20; if (argc > 2) { @@ -71,27 +66,23 @@ int main(int argc, char **argv) } if (shift) - printf("%u kB hugepages\n", 1 << (shift - 10)); + ksft_print_msg("%u kB hugepages\n", 1 << (shift - 10)); else - printf("Default size hugepages\n"); - printf("Mapping %lu Mbytes\n", (unsigned long)length >> 20); + ksft_print_msg("Default size hugepages\n"); + ksft_print_msg("Mapping %lu Mbytes\n", (unsigned long)length >> 20); - addr = mmap(ADDR, length, PROTECTION, flags, -1, 0); - if (addr == MAP_FAILED) { - perror("mmap"); - exit(1); - } + addr = mmap(NULL, length, PROTECTION, flags, -1, 0); + if (addr == MAP_FAILED) + ksft_exit_fail_msg("mmap: %s\n", strerror(errno)); - printf("Returned address is %p\n", addr); + ksft_print_msg("Returned address is %p\n", addr); check_bytes(addr); write_bytes(addr, length); - ret = read_bytes(addr, length); + read_bytes(addr, length); /* munmap() length of MAP_HUGETLB memory must be hugepage aligned */ - if (munmap(addr, length)) { - perror("munmap"); - exit(1); - } + if (munmap(addr, length)) + ksft_exit_fail_msg("munmap: %s\n", strerror(errno)); - return ret; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/map_populate.c b/tools/testing/selftests/mm/map_populate.c index 240f2d9dae7a..712327f4e932 100644 --- a/tools/testing/selftests/mm/map_populate.c +++ b/tools/testing/selftests/mm/map_populate.c @@ -16,19 +16,23 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> +#include "kselftest.h" + +#include "vm_util.h" #define MMAP_SZ 4096 -#define BUG_ON(condition, description) \ - do { \ - if (condition) { \ - fprintf(stderr, "[FAIL]\t%s:%d\t%s:%s\n", __func__, \ - __LINE__, (description), strerror(errno)); \ - exit(1); \ - } \ +#define BUG_ON(condition, description) \ + do { \ + if (condition) \ + ksft_exit_fail_msg("[FAIL]\t%s:%d\t%s:%s\n", \ + __func__, __LINE__, (description), \ + strerror(errno)); \ } while (0) -static int parent_f(int sock, unsigned long *smap, int child) +#define TESTS_IN_CHILD 2 + +static void parent_f(int sock, unsigned long *smap, int child) { int status, ret; @@ -43,9 +47,10 @@ static int parent_f(int sock, unsigned long *smap, int child) BUG_ON(ret <= 0, "write(sock)"); waitpid(child, &status, 0); - BUG_ON(!WIFEXITED(status), "child in unexpected state"); - return WEXITSTATUS(status); + /* The ksft macros don't keep counters between processes */ + ksft_cnt.ksft_pass = WEXITSTATUS(status); + ksft_cnt.ksft_fail = TESTS_IN_CHILD - WEXITSTATUS(status); } static int child_f(int sock, unsigned long *smap, int fd) @@ -64,10 +69,11 @@ static int child_f(int sock, unsigned long *smap, int fd) ret = read(sock, &buf, sizeof(int)); BUG_ON(ret <= 0, "read(sock)"); - BUG_ON(*smap == 0x22222BAD, "MAP_POPULATE didn't COW private page"); - BUG_ON(*smap != 0xdeadbabe, "mapping was corrupted"); + ksft_test_result(*smap != 0x22222BAD, "MAP_POPULATE COW private page\n"); + ksft_test_result(*smap == 0xdeadbabe, "The mapping state\n"); - return 0; + /* The ksft macros don't keep counters between processes */ + return ksft_cnt.ksft_pass; } int main(int argc, char **argv) @@ -76,10 +82,16 @@ int main(int argc, char **argv) FILE *ftmp; unsigned long *smap; + ksft_print_header(); + ksft_set_plan(TESTS_IN_CHILD); + ftmp = tmpfile(); - BUG_ON(ftmp == 0, "tmpfile()"); + BUG_ON(!ftmp, "tmpfile()"); ret = ftruncate(fileno(ftmp), MMAP_SZ); + if (ret < 0 && errno == ENOENT) { + skip_test_dodgy_fs("ftruncate()"); + } BUG_ON(ret, "ftruncate()"); smap = mmap(0, MMAP_SZ, PROT_READ | PROT_WRITE, @@ -101,7 +113,9 @@ int main(int argc, char **argv) ret = close(sock[0]); BUG_ON(ret, "close()"); - return parent_f(sock[1], smap, child); + parent_f(sock[1], smap, child); + + ksft_finished(); } ret = close(sock[1]); diff --git a/tools/testing/selftests/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c index bc91bef5d254..647779653da0 100644 --- a/tools/testing/selftests/mm/mdwe_test.c +++ b/tools/testing/selftests/mm/mdwe_test.c @@ -14,7 +14,7 @@ #include <sys/wait.h> #include <unistd.h> -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #ifndef __aarch64__ # define PROT_BTI 0 @@ -22,15 +22,104 @@ TEST(prctl_flags) { + EXPECT_LT(prctl(PR_SET_MDWE, PR_MDWE_NO_INHERIT, 0L, 0L, 7L), 0); + EXPECT_EQ(errno, EINVAL); + EXPECT_LT(prctl(PR_SET_MDWE, 7L, 0L, 0L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_SET_MDWE, 0L, 7L, 0L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_SET_MDWE, 0L, 0L, 7L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_SET_MDWE, 0L, 0L, 0L, 7L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_GET_MDWE, 7L, 0L, 0L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_GET_MDWE, 0L, 7L, 0L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_GET_MDWE, 0L, 0L, 7L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_GET_MDWE, 0L, 0L, 0L, 7L), 0); + EXPECT_EQ(errno, EINVAL); +} + +FIXTURE(consecutive_prctl_flags) {}; +FIXTURE_SETUP(consecutive_prctl_flags) {} +FIXTURE_TEARDOWN(consecutive_prctl_flags) {} + +FIXTURE_VARIANT(consecutive_prctl_flags) +{ + unsigned long first_flags; + unsigned long second_flags; + bool should_work; +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, can_keep_no_flags) +{ + .first_flags = 0, + .second_flags = 0, + .should_work = true, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, can_keep_exec_gain) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN, + .second_flags = PR_MDWE_REFUSE_EXEC_GAIN, + .should_work = true, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, can_keep_both_flags) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT, + .second_flags = PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT, + .should_work = true, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, cant_disable_mdwe) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN, + .second_flags = 0, + .should_work = false, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, cant_disable_mdwe_no_inherit) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT, + .second_flags = 0, + .should_work = false, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, cant_disable_no_inherit) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT, + .second_flags = PR_MDWE_REFUSE_EXEC_GAIN, + .should_work = false, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, cant_enable_no_inherit) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN, + .second_flags = PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT, + .should_work = false, +}; + +TEST_F(consecutive_prctl_flags, two_prctls) +{ + int ret; + + EXPECT_EQ(prctl(PR_SET_MDWE, variant->first_flags, 0L, 0L, 0L), 0); + + ret = prctl(PR_SET_MDWE, variant->second_flags, 0L, 0L, 0L); + if (variant->should_work) { + EXPECT_EQ(ret, 0); + + ret = prctl(PR_GET_MDWE, 0L, 0L, 0L, 0L); + ASSERT_EQ(ret, variant->second_flags); + } else { + EXPECT_NE(ret, 0); + ASSERT_EQ(errno, EPERM); + } } FIXTURE(mdwe) @@ -45,28 +134,45 @@ FIXTURE_VARIANT(mdwe) { bool enabled; bool forked; + bool inherit; }; FIXTURE_VARIANT_ADD(mdwe, stock) { - .enabled = false, + .enabled = false, .forked = false, + .inherit = false, }; FIXTURE_VARIANT_ADD(mdwe, enabled) { - .enabled = true, + .enabled = true, .forked = false, + .inherit = true, +}; + +FIXTURE_VARIANT_ADD(mdwe, inherited) +{ + .enabled = true, + .forked = true, + .inherit = true, }; -FIXTURE_VARIANT_ADD(mdwe, forked) +FIXTURE_VARIANT_ADD(mdwe, not_inherited) { - .enabled = true, + .enabled = true, .forked = true, + .inherit = false, }; +static bool executable_map_should_fail(const FIXTURE_VARIANT(mdwe) *variant) +{ + return variant->enabled && (!variant->forked || variant->inherit); +} + FIXTURE_SETUP(mdwe) { + unsigned long mdwe_flags; int ret, status; self->p = NULL; @@ -76,13 +182,17 @@ FIXTURE_SETUP(mdwe) if (!variant->enabled) return; - ret = prctl(PR_SET_MDWE, PR_MDWE_REFUSE_EXEC_GAIN, 0L, 0L, 0L); + mdwe_flags = PR_MDWE_REFUSE_EXEC_GAIN; + if (!variant->inherit) + mdwe_flags |= PR_MDWE_NO_INHERIT; + + ret = prctl(PR_SET_MDWE, mdwe_flags, 0L, 0L, 0L); ASSERT_EQ(ret, 0) { TH_LOG("PR_SET_MDWE failed or unsupported"); } ret = prctl(PR_GET_MDWE, 0L, 0L, 0L, 0L); - ASSERT_EQ(ret, 1); + ASSERT_EQ(ret, mdwe_flags); if (variant->forked) { self->pid = fork(); @@ -113,7 +223,7 @@ TEST_F(mdwe, mmap_READ_EXEC) TEST_F(mdwe, mmap_WRITE_EXEC) { self->p = mmap(NULL, self->size, PROT_WRITE | PROT_EXEC, self->flags, 0, 0); - if (variant->enabled) { + if (executable_map_should_fail(variant)) { EXPECT_EQ(self->p, MAP_FAILED); } else { EXPECT_NE(self->p, MAP_FAILED); @@ -139,7 +249,7 @@ TEST_F(mdwe, mprotect_add_EXEC) ASSERT_NE(self->p, MAP_FAILED); ret = mprotect(self->p, self->size, PROT_READ | PROT_EXEC); - if (variant->enabled) { + if (executable_map_should_fail(variant)) { EXPECT_LT(ret, 0); } else { EXPECT_EQ(ret, 0); @@ -154,7 +264,7 @@ TEST_F(mdwe, mprotect_WRITE_EXEC) ASSERT_NE(self->p, MAP_FAILED); ret = mprotect(self->p, self->size, PROT_WRITE | PROT_EXEC); - if (variant->enabled) { + if (executable_map_should_fail(variant)) { EXPECT_LT(ret, 0); } else { EXPECT_EQ(ret, 0); @@ -168,13 +278,10 @@ TEST_F(mdwe, mmap_FIXED) self->p = mmap(NULL, self->size, PROT_READ, self->flags, 0, 0); ASSERT_NE(self->p, MAP_FAILED); - p = mmap(self->p + self->size, self->size, PROT_READ | PROT_EXEC, + /* MAP_FIXED unmaps the existing page before mapping which is allowed */ + p = mmap(self->p, self->size, PROT_READ | PROT_EXEC, self->flags | MAP_FIXED, 0, 0); - if (variant->enabled) { - EXPECT_EQ(p, MAP_FAILED); - } else { - EXPECT_EQ(p, self->p); - } + EXPECT_EQ(p, self->p); } TEST_F(mdwe, arm64_BTI) diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c index 957b9e18c729..aac4f795c327 100644 --- a/tools/testing/selftests/mm/memfd_secret.c +++ b/tools/testing/selftests/mm/memfd_secret.c @@ -20,8 +20,9 @@ #include <unistd.h> #include <errno.h> #include <stdio.h> +#include <fcntl.h> -#include "../kselftest.h" +#include "kselftest.h" #define fail(fmt, ...) ksft_test_result_fail(fmt, ##__VA_ARGS__) #define pass(fmt, ...) ksft_test_result_pass(fmt, ##__VA_ARGS__) @@ -62,6 +63,9 @@ static void test_mlock_limit(int fd) char *mem; len = mlock_limit_cur; + if (len % page_size != 0) + len = (len/page_size) * page_size; + mem = mmap(NULL, len, prot, mode, fd, 0); if (mem == MAP_FAILED) { fail("unable to mmap secret memory\n"); @@ -80,6 +84,45 @@ static void test_mlock_limit(int fd) pass("mlock limit is respected\n"); } +static void test_vmsplice(int fd, const char *desc) +{ + ssize_t transferred; + struct iovec iov; + int pipefd[2]; + char *mem; + + if (pipe(pipefd)) { + fail("pipe failed: %s\n", strerror(errno)); + return; + } + + mem = mmap(NULL, page_size, prot, mode, fd, 0); + if (mem == MAP_FAILED) { + fail("Unable to mmap secret memory\n"); + goto close_pipe; + } + + /* + * vmsplice() may use GUP-fast, which must also fail. Prefault the + * page table, so GUP-fast could find it. + */ + memset(mem, PATTERN, page_size); + + iov.iov_base = mem; + iov.iov_len = page_size; + transferred = vmsplice(pipefd[1], &iov, 1, 0); + + if (transferred < 0 && errno == EFAULT) + pass("vmsplice is blocked as expected with %s\n", desc); + else + fail("vmsplice: unexpected memory access with %s\n", desc); + + munmap(mem, page_size); +close_pipe: + close(pipefd[0]); + close(pipefd[1]); +} + static void try_process_vm_read(int fd, int pipefd[2]) { struct iovec liov, riov; @@ -184,7 +227,6 @@ static void test_remote_access(int fd, const char *name, return; } - ftruncate(fd, page_size); memset(mem, PATTERN, page_size); if (write(pipefd[1], &mem, sizeof(mem)) < 0) { @@ -255,7 +297,7 @@ static void prepare(void) strerror(errno)); } -#define NUM_TESTS 4 +#define NUM_TESTS 6 int main(int argc, char *argv[]) { @@ -274,9 +316,17 @@ int main(int argc, char *argv[]) ksft_exit_fail_msg("memfd_secret failed: %s\n", strerror(errno)); } + if (ftruncate(fd, page_size)) + ksft_exit_fail_msg("ftruncate failed: %s\n", strerror(errno)); test_mlock_limit(fd); test_file_apis(fd); + /* + * We have to run the first vmsplice test before any secretmem page was + * allocated for this fd. + */ + test_vmsplice(fd, "fresh page"); + test_vmsplice(fd, "existing page"); test_process_vm_read(fd); test_ptrace(fd); diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c new file mode 100644 index 000000000000..363c1033cc7d --- /dev/null +++ b/tools/testing/selftests/mm/merge.c @@ -0,0 +1,1174 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE +#include "kselftest_harness.h" +#include <linux/prctl.h> +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/mman.h> +#include <sys/prctl.h> +#include <sys/syscall.h> +#include <sys/wait.h> +#include <linux/perf_event.h> +#include "vm_util.h" +#include <linux/mman.h> + +FIXTURE(merge) +{ + unsigned int page_size; + char *carveout; + struct procmap_fd procmap; +}; + +FIXTURE_SETUP(merge) +{ + self->page_size = psize(); + /* Carve out PROT_NONE region to map over. */ + self->carveout = mmap(NULL, 30 * self->page_size, PROT_NONE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(self->carveout, MAP_FAILED); + /* Setup PROCMAP_QUERY interface. */ + ASSERT_EQ(open_self_procmap(&self->procmap), 0); +} + +FIXTURE_TEARDOWN(merge) +{ + ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); + ASSERT_EQ(close_procmap(&self->procmap), 0); + /* + * Clear unconditionally, as some tests set this. It is no issue if this + * fails (KSM may be disabled for instance). + */ + prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); +} + +TEST_F(merge, mprotect_unfaulted_left) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr; + + /* + * Map 10 pages of R/W memory within. MAP_NORESERVE so we don't hit + * merge failure due to lack of VM_ACCOUNT flag by mistake. + * + * |-----------------------| + * | unfaulted | + * |-----------------------| + */ + ptr = mmap(&carveout[page_size], 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED | MAP_NORESERVE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + /* + * Now make the first 5 pages read-only, splitting the VMA: + * + * RO RW + * |-----------|-----------| + * | unfaulted | unfaulted | + * |-----------|-----------| + */ + ASSERT_EQ(mprotect(ptr, 5 * page_size, PROT_READ), 0); + /* + * Fault in the first of the last 5 pages so it gets an anon_vma and + * thus the whole VMA becomes 'faulted': + * + * RO RW + * |-----------|-----------| + * | unfaulted | faulted | + * |-----------|-----------| + */ + ptr[5 * page_size] = 'x'; + /* + * Now mprotect() the RW region read-only, we should merge (though for + * ~15 years we did not! :): + * + * RO + * |-----------------------| + * | faulted | + * |-----------------------| + */ + ASSERT_EQ(mprotect(&ptr[5 * page_size], 5 * page_size, PROT_READ), 0); + + /* Assert that the merge succeeded using PROCMAP_QUERY. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 10 * page_size); +} + +TEST_F(merge, mprotect_unfaulted_right) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr; + + /* + * |-----------------------| + * | unfaulted | + * |-----------------------| + */ + ptr = mmap(&carveout[page_size], 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED | MAP_NORESERVE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + /* + * Now make the last 5 pages read-only, splitting the VMA: + * + * RW RO + * |-----------|-----------| + * | unfaulted | unfaulted | + * |-----------|-----------| + */ + ASSERT_EQ(mprotect(&ptr[5 * page_size], 5 * page_size, PROT_READ), 0); + /* + * Fault in the first of the first 5 pages so it gets an anon_vma and + * thus the whole VMA becomes 'faulted': + * + * RW RO + * |-----------|-----------| + * | faulted | unfaulted | + * |-----------|-----------| + */ + ptr[0] = 'x'; + /* + * Now mprotect() the RW region read-only, we should merge: + * + * RO + * |-----------------------| + * | faulted | + * |-----------------------| + */ + ASSERT_EQ(mprotect(ptr, 5 * page_size, PROT_READ), 0); + + /* Assert that the merge succeeded using PROCMAP_QUERY. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 10 * page_size); +} + +TEST_F(merge, mprotect_unfaulted_both) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr; + + /* + * |-----------------------| + * | unfaulted | + * |-----------------------| + */ + ptr = mmap(&carveout[2 * page_size], 9 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED | MAP_NORESERVE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + /* + * Now make the first and last 3 pages read-only, splitting the VMA: + * + * RO RW RO + * |-----------|-----------|-----------| + * | unfaulted | unfaulted | unfaulted | + * |-----------|-----------|-----------| + */ + ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ), 0); + ASSERT_EQ(mprotect(&ptr[6 * page_size], 3 * page_size, PROT_READ), 0); + /* + * Fault in the first of the middle 3 pages so it gets an anon_vma and + * thus the whole VMA becomes 'faulted': + * + * RO RW RO + * |-----------|-----------|-----------| + * | unfaulted | faulted | unfaulted | + * |-----------|-----------|-----------| + */ + ptr[3 * page_size] = 'x'; + /* + * Now mprotect() the RW region read-only, we should merge: + * + * RO + * |-----------------------| + * | faulted | + * |-----------------------| + */ + ASSERT_EQ(mprotect(&ptr[3 * page_size], 3 * page_size, PROT_READ), 0); + + /* Assert that the merge succeeded using PROCMAP_QUERY. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 9 * page_size); +} + +TEST_F(merge, mprotect_faulted_left_unfaulted_right) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr; + + /* + * |-----------------------| + * | unfaulted | + * |-----------------------| + */ + ptr = mmap(&carveout[2 * page_size], 9 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED | MAP_NORESERVE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + /* + * Now make the last 3 pages read-only, splitting the VMA: + * + * RW RO + * |-----------------------|-----------| + * | unfaulted | unfaulted | + * |-----------------------|-----------| + */ + ASSERT_EQ(mprotect(&ptr[6 * page_size], 3 * page_size, PROT_READ), 0); + /* + * Fault in the first of the first 6 pages so it gets an anon_vma and + * thus the whole VMA becomes 'faulted': + * + * RW RO + * |-----------------------|-----------| + * | unfaulted | unfaulted | + * |-----------------------|-----------| + */ + ptr[0] = 'x'; + /* + * Now make the first 3 pages read-only, splitting the VMA: + * + * RO RW RO + * |-----------|-----------|-----------| + * | faulted | faulted | unfaulted | + * |-----------|-----------|-----------| + */ + ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ), 0); + /* + * Now mprotect() the RW region read-only, we should merge: + * + * RO + * |-----------------------| + * | faulted | + * |-----------------------| + */ + ASSERT_EQ(mprotect(&ptr[3 * page_size], 3 * page_size, PROT_READ), 0); + + /* Assert that the merge succeeded using PROCMAP_QUERY. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 9 * page_size); +} + +TEST_F(merge, mprotect_unfaulted_left_faulted_right) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr; + + /* + * |-----------------------| + * | unfaulted | + * |-----------------------| + */ + ptr = mmap(&carveout[2 * page_size], 9 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED | MAP_NORESERVE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + /* + * Now make the first 3 pages read-only, splitting the VMA: + * + * RO RW + * |-----------|-----------------------| + * | unfaulted | unfaulted | + * |-----------|-----------------------| + */ + ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ), 0); + /* + * Fault in the first of the last 6 pages so it gets an anon_vma and + * thus the whole VMA becomes 'faulted': + * + * RO RW + * |-----------|-----------------------| + * | unfaulted | faulted | + * |-----------|-----------------------| + */ + ptr[3 * page_size] = 'x'; + /* + * Now make the last 3 pages read-only, splitting the VMA: + * + * RO RW RO + * |-----------|-----------|-----------| + * | unfaulted | faulted | faulted | + * |-----------|-----------|-----------| + */ + ASSERT_EQ(mprotect(&ptr[6 * page_size], 3 * page_size, PROT_READ), 0); + /* + * Now mprotect() the RW region read-only, we should merge: + * + * RO + * |-----------------------| + * | faulted | + * |-----------------------| + */ + ASSERT_EQ(mprotect(&ptr[3 * page_size], 3 * page_size, PROT_READ), 0); + + /* Assert that the merge succeeded using PROCMAP_QUERY. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 9 * page_size); +} + +TEST_F(merge, forked_target_vma) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + pid_t pid; + char *ptr, *ptr2; + int i; + + /* + * |-----------| + * | unfaulted | + * |-----------| + */ + ptr = mmap(&carveout[page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Fault in process. + * + * |-----------| + * | faulted | + * |-----------| + */ + ptr[0] = 'x'; + + pid = fork(); + ASSERT_NE(pid, -1); + + if (pid != 0) { + wait(NULL); + return; + } + + /* Child process below: */ + + /* Reopen for child. */ + ASSERT_EQ(close_procmap(&self->procmap), 0); + ASSERT_EQ(open_self_procmap(&self->procmap), 0); + + /* unCOWing everything does not cause the AVC to go away. */ + for (i = 0; i < 5 * page_size; i += page_size) + ptr[i] = 'x'; + + /* + * Map in adjacent VMA in child. + * + * forked + * |-----------|-----------| + * | faulted | unfaulted | + * |-----------|-----------| + * ptr ptr2 + */ + ptr2 = mmap(&ptr[5 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + + /* Make sure not merged. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 5 * page_size); +} + +TEST_F(merge, forked_source_vma) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + pid_t pid; + char *ptr, *ptr2; + int i; + + /* + * |-----------|------------| + * | unfaulted | <unmapped> | + * |-----------|------------| + */ + ptr = mmap(&carveout[page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED | MAP_NORESERVE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Fault in process. + * + * |-----------|------------| + * | faulted | <unmapped> | + * |-----------|------------| + */ + ptr[0] = 'x'; + + pid = fork(); + ASSERT_NE(pid, -1); + + if (pid != 0) { + wait(NULL); + return; + } + + /* Child process below: */ + + /* Reopen for child. */ + ASSERT_EQ(close_procmap(&self->procmap), 0); + ASSERT_EQ(open_self_procmap(&self->procmap), 0); + + /* unCOWing everything does not cause the AVC to go away. */ + for (i = 0; i < 5 * page_size; i += page_size) + ptr[i] = 'x'; + + /* + * Map in adjacent VMA in child, ptr2 after ptr, but incompatible. + * + * forked RW RWX + * |-----------|-----------| + * | faulted | unfaulted | + * |-----------|-----------| + * ptr ptr2 + */ + ptr2 = mmap(&carveout[6 * page_size], 5 * page_size, PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_ANON | MAP_PRIVATE | MAP_FIXED | MAP_NORESERVE, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + + /* Make sure not merged. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr2)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr2); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr2 + 5 * page_size); + + /* + * Now mprotect forked region to RWX so it becomes the source for the + * merge to unfaulted region: + * + * forked RWX RWX + * |-----------|-----------| + * | faulted | unfaulted | + * |-----------|-----------| + * ptr ptr2 + * + * This should NOT result in a merge, as ptr was forked. + */ + ASSERT_EQ(mprotect(ptr, 5 * page_size, PROT_READ | PROT_WRITE | PROT_EXEC), 0); + /* Again, make sure not merged. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr2)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr2); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr2 + 5 * page_size); +} + +TEST_F(merge, handle_uprobe_upon_merged_vma) +{ + const size_t attr_sz = sizeof(struct perf_event_attr); + unsigned int page_size = self->page_size; + const char *probe_file = "./foo"; + char *carveout = self->carveout; + struct perf_event_attr attr; + unsigned long type; + void *ptr1, *ptr2; + int fd; + + fd = open(probe_file, O_RDWR|O_CREAT, 0600); + ASSERT_GE(fd, 0); + + ASSERT_EQ(ftruncate(fd, page_size), 0); + if (read_sysfs("/sys/bus/event_source/devices/uprobe/type", &type) != 0) { + SKIP(goto out, "Failed to read uprobe sysfs file, skipping"); + } + + memset(&attr, 0, attr_sz); + attr.size = attr_sz; + attr.type = type; + attr.config1 = (__u64)(long)probe_file; + attr.config2 = 0x0; + + ASSERT_GE(syscall(__NR_perf_event_open, &attr, 0, -1, -1, 0), 0); + + ptr1 = mmap(&carveout[page_size], 10 * page_size, PROT_EXEC, + MAP_PRIVATE | MAP_FIXED, fd, 0); + ASSERT_NE(ptr1, MAP_FAILED); + + ptr2 = mremap(ptr1, page_size, 2 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr1 + 5 * page_size); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_NE(mremap(ptr2, page_size, page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr1), MAP_FAILED); + +out: + close(fd); + remove(probe_file); +} + +TEST_F(merge, ksm_merge) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2; + int err; + + /* + * Map two R/W immediately adjacent to one another, they should + * trivially merge: + * + * |-----------|-----------| + * | R/W | R/W | + * |-----------|-----------| + * ptr ptr2 + */ + + ptr = mmap(&carveout[page_size], page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr2 = mmap(&carveout[2 * page_size], page_size, + PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 2 * page_size); + + /* Unmap the second half of this merged VMA. */ + ASSERT_EQ(munmap(ptr2, page_size), 0); + + /* OK, now enable global KSM merge. We clear this on test teardown. */ + err = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); + if (err == -1) { + int errnum = errno; + + /* Only non-failure case... */ + ASSERT_EQ(errnum, EINVAL); + /* ...but indicates we should skip. */ + SKIP(return, "KSM memory merging not supported, skipping."); + } + + /* + * Now map a VMA adjacent to the existing that was just made + * VM_MERGEABLE, this should merge as well. + */ + ptr2 = mmap(&carveout[2 * page_size], page_size, + PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 2 * page_size); + + /* Now this VMA altogether. */ + ASSERT_EQ(munmap(ptr, 2 * page_size), 0); + + /* Try the same operation as before, asserting this also merges fine. */ + ptr = mmap(&carveout[page_size], page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr2 = mmap(&carveout[2 * page_size], page_size, + PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 2 * page_size); +} + +TEST_F(merge, mremap_unfaulted_to_faulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2; + + /* + * Map two distinct areas: + * + * |-----------| |-----------| + * | unfaulted | | unfaulted | + * |-----------| |-----------| + * ptr ptr2 + */ + ptr = mmap(&carveout[page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr2 = mmap(&carveout[7 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + + /* Offset ptr2 further away. */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Fault in ptr: + * \ + * |-----------| / |-----------| + * | faulted | \ | unfaulted | + * |-----------| / |-----------| + * ptr \ ptr2 + */ + ptr[0] = 'x'; + + /* + * Now move ptr2 adjacent to ptr: + * + * |-----------|-----------| + * | faulted | unfaulted | + * |-----------|-----------| + * ptr ptr2 + * + * It should merge: + * + * |----------------------| + * | faulted | + * |----------------------| + * ptr + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 10 * page_size); +} + +TEST_F(merge, mremap_unfaulted_behind_faulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2; + + /* + * Map two distinct areas: + * + * |-----------| |-----------| + * | unfaulted | | unfaulted | + * |-----------| |-----------| + * ptr ptr2 + */ + ptr = mmap(&carveout[6 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr2 = mmap(&carveout[14 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + + /* Offset ptr2 further away. */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Fault in ptr: + * \ + * |-----------| / |-----------| + * | faulted | \ | unfaulted | + * |-----------| / |-----------| + * ptr \ ptr2 + */ + ptr[0] = 'x'; + + /* + * Now move ptr2 adjacent, but behind, ptr: + * + * |-----------|-----------| + * | unfaulted | faulted | + * |-----------|-----------| + * ptr2 ptr + * + * It should merge: + * + * |----------------------| + * | faulted | + * |----------------------| + * ptr2 + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &carveout[page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr2)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr2); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr2 + 10 * page_size); +} + +TEST_F(merge, mremap_unfaulted_between_faulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2, *ptr3; + + /* + * Map three distinct areas: + * + * |-----------| |-----------| |-----------| + * | unfaulted | | unfaulted | | unfaulted | + * |-----------| |-----------| |-----------| + * ptr ptr2 ptr3 + */ + ptr = mmap(&carveout[page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr2 = mmap(&carveout[7 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + ptr3 = mmap(&carveout[14 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr3, MAP_FAILED); + + /* Offset ptr3 further away. */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr3 + page_size * 2000); + ASSERT_NE(ptr3, MAP_FAILED); + + /* Offset ptr2 further away. */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Fault in ptr, ptr3: + * \ \ + * |-----------| / |-----------| / |-----------| + * | faulted | \ | unfaulted | \ | faulted | + * |-----------| / |-----------| / |-----------| + * ptr \ ptr2 \ ptr3 + */ + ptr[0] = 'x'; + ptr3[0] = 'x'; + + /* + * Move ptr3 back into place, leaving a place for ptr2: + * \ + * |-----------| |-----------| / |-----------| + * | faulted | | faulted | \ | unfaulted | + * |-----------| |-----------| / |-----------| + * ptr ptr3 \ ptr2 + */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[10 * page_size]); + ASSERT_NE(ptr3, MAP_FAILED); + + /* + * Finally, move ptr2 into place: + * + * |-----------|-----------|-----------| + * | faulted | unfaulted | faulted | + * |-----------|-----------|-----------| + * ptr ptr2 ptr3 + * + * It should merge, but only ptr, ptr2: + * + * |-----------------------|-----------| + * | faulted | unfaulted | + * |-----------------------|-----------| + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 10 * page_size); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr3)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr3); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr3 + 5 * page_size); +} + +TEST_F(merge, mremap_unfaulted_between_faulted_unfaulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2, *ptr3; + + /* + * Map three distinct areas: + * + * |-----------| |-----------| |-----------| + * | unfaulted | | unfaulted | | unfaulted | + * |-----------| |-----------| |-----------| + * ptr ptr2 ptr3 + */ + ptr = mmap(&carveout[page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr2 = mmap(&carveout[7 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + ptr3 = mmap(&carveout[14 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr3, MAP_FAILED); + + /* Offset ptr3 further away. */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr3 + page_size * 2000); + ASSERT_NE(ptr3, MAP_FAILED); + + + /* Offset ptr2 further away. */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Fault in ptr: + * \ \ + * |-----------| / |-----------| / |-----------| + * | faulted | \ | unfaulted | \ | unfaulted | + * |-----------| / |-----------| / |-----------| + * ptr \ ptr2 \ ptr3 + */ + ptr[0] = 'x'; + + /* + * Move ptr3 back into place, leaving a place for ptr2: + * \ + * |-----------| |-----------| / |-----------| + * | faulted | | unfaulted | \ | unfaulted | + * |-----------| |-----------| / |-----------| + * ptr ptr3 \ ptr2 + */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[10 * page_size]); + ASSERT_NE(ptr3, MAP_FAILED); + + /* + * Finally, move ptr2 into place: + * + * |-----------|-----------|-----------| + * | faulted | unfaulted | unfaulted | + * |-----------|-----------|-----------| + * ptr ptr2 ptr3 + * + * It should merge: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); +} + +TEST_F(merge, mremap_unfaulted_between_correctly_placed_faulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2; + + /* + * Map one larger area: + * + * |-----------------------------------| + * | unfaulted | + * |-----------------------------------| + */ + ptr = mmap(&carveout[page_size], 15 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Fault in ptr: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + */ + ptr[0] = 'x'; + + /* + * Unmap middle: + * + * |-----------| |-----------| + * | faulted | | faulted | + * |-----------| |-----------| + * + * Now the faulted areas are compatible with each other (anon_vma the + * same, vma->vm_pgoff equal to virtual page offset). + */ + ASSERT_EQ(munmap(&ptr[5 * page_size], 5 * page_size), 0); + + /* + * Map a new area, ptr2: + * \ + * |-----------| |-----------| / |-----------| + * | faulted | | faulted | \ | unfaulted | + * |-----------| |-----------| / |-----------| + * ptr \ ptr2 + */ + ptr2 = mmap(&carveout[20 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Finally, move ptr2 into place: + * + * |-----------|-----------|-----------| + * | faulted | unfaulted | faulted | + * |-----------|-----------|-----------| + * ptr ptr2 ptr3 + * + * It should merge: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); +} + +TEST_F(merge, mremap_correct_placed_faulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2, *ptr3; + + /* + * Map one larger area: + * + * |-----------------------------------| + * | unfaulted | + * |-----------------------------------| + */ + ptr = mmap(&carveout[page_size], 15 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Fault in ptr: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + */ + ptr[0] = 'x'; + + /* + * Offset the final and middle 5 pages further away: + * \ \ + * |-----------| / |-----------| / |-----------| + * | faulted | \ | faulted | \ | faulted | + * |-----------| / |-----------| / |-----------| + * ptr \ ptr2 \ ptr3 + */ + ptr3 = &ptr[10 * page_size]; + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr3 + page_size * 2000); + ASSERT_NE(ptr3, MAP_FAILED); + ptr2 = &ptr[5 * page_size]; + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Move ptr2 into its correct place: + * \ + * |-----------|-----------| / |-----------| + * | faulted | faulted | \ | faulted | + * |-----------|-----------| / |-----------| + * ptr ptr2 \ ptr3 + * + * It should merge: + * \ + * |-----------------------| / |-----------| + * | faulted | \ | faulted | + * |-----------------------| / |-----------| + * ptr \ ptr3 + */ + + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 10 * page_size); + + /* + * Now move ptr out of place: + * \ \ + * |-----------| / |-----------| / |-----------| + * | faulted | \ | faulted | \ | faulted | + * |-----------| / |-----------| / |-----------| + * ptr2 \ ptr \ ptr3 + */ + ptr = sys_mremap(ptr, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr + page_size * 1000); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Now move ptr back into place: + * \ + * |-----------|-----------| / |-----------| + * | faulted | faulted | \ | faulted | + * |-----------|-----------| / |-----------| + * ptr ptr2 \ ptr3 + * + * It should merge: + * \ + * |-----------------------| / |-----------| + * | faulted | \ | faulted | + * |-----------------------| / |-----------| + * ptr \ ptr3 + */ + ptr = sys_mremap(ptr, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &carveout[page_size]); + ASSERT_NE(ptr, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 10 * page_size); + + /* + * Now move ptr out of place again: + * \ \ + * |-----------| / |-----------| / |-----------| + * | faulted | \ | faulted | \ | faulted | + * |-----------| / |-----------| / |-----------| + * ptr2 \ ptr \ ptr3 + */ + ptr = sys_mremap(ptr, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr + page_size * 1000); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Now move ptr3 back into place: + * \ + * |-----------|-----------| / |-----------| + * | faulted | faulted | \ | faulted | + * |-----------|-----------| / |-----------| + * ptr2 ptr3 \ ptr + * + * It should merge: + * \ + * |-----------------------| / |-----------| + * | faulted | \ | faulted | + * |-----------------------| / |-----------| + * ptr2 \ ptr + */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr2[5 * page_size]); + ASSERT_NE(ptr3, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr2)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr2); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr2 + 10 * page_size); + + /* + * Now move ptr back into place: + * + * |-----------|-----------------------| + * | faulted | faulted | + * |-----------|-----------------------| + * ptr ptr2 + * + * It should merge: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + * ptr + */ + ptr = sys_mremap(ptr, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &carveout[page_size]); + ASSERT_NE(ptr, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); + + /* + * Now move ptr2 out of the way: + * \ + * |-----------| |-----------| / |-----------| + * | faulted | | faulted | \ | faulted | + * |-----------| |-----------| / |-----------| + * ptr ptr3 \ ptr2 + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Now move it back: + * + * |-----------|-----------|-----------| + * | faulted | faulted | faulted | + * |-----------|-----------|-----------| + * ptr ptr2 ptr3 + * + * It should merge: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + * ptr + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); + + /* + * Move ptr3 out of place: + * \ + * |-----------------------| / |-----------| + * | faulted | \ | faulted | + * |-----------------------| / |-----------| + * ptr \ ptr3 + */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr3 + page_size * 1000); + ASSERT_NE(ptr3, MAP_FAILED); + + /* + * Now move it back: + * + * |-----------|-----------|-----------| + * | faulted | faulted | faulted | + * |-----------|-----------|-----------| + * ptr ptr2 ptr3 + * + * It should merge: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + * ptr + */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[10 * page_size]); + ASSERT_NE(ptr3, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index 379581567f27..ee24b88c2b24 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -4,20 +4,24 @@ * paths in the kernel. */ -#include "../kselftest_harness.h" +#include "kselftest_harness.h" +#include "thp_settings.h" + #include <strings.h> #include <pthread.h> #include <numa.h> #include <numaif.h> #include <sys/mman.h> +#include <sys/prctl.h> #include <sys/types.h> #include <signal.h> #include <time.h> +#include "vm_util.h" -#define TWOMEG (2<<20) -#define RUNTIME (60) - -#define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1))) +#define TWOMEG (2<<20) +#define RUNTIME (20) +#define MAX_RETRIES 100 +#define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1))) FIXTURE(migration) { @@ -64,6 +68,7 @@ int migrate(uint64_t *ptr, int n1, int n2) int ret, tmp; int status = 0; struct timespec ts1, ts2; + int failures = 0; if (clock_gettime(CLOCK_MONOTONIC, &ts1)) return -1; @@ -78,13 +83,17 @@ int migrate(uint64_t *ptr, int n1, int n2) ret = move_pages(0, 1, (void **) &ptr, &n2, &status, MPOL_MF_MOVE_ALL); if (ret) { - if (ret > 0) + if (ret > 0) { + /* Migration is best effort; try again */ + if (++failures < MAX_RETRIES) + continue; printf("Didn't migrate %d pages\n", ret); + } else perror("Couldn't migrate pages"); return -2; } - + failures = 0; tmp = n2; n2 = n1; n1 = tmp; @@ -95,15 +104,13 @@ int migrate(uint64_t *ptr, int n1, int n2) void *access_mem(void *ptr) { - volatile uint64_t y = 0; - volatile uint64_t *x = ptr; - while (1) { pthread_testcancel(); - y += *x; - - /* Prevent the compiler from optimizing out the writes to y: */ - asm volatile("" : "+r" (y)); + /* Force a read from the memory pointed to by ptr. This ensures + * the memory access actually happens and prevents the compiler + * from optimizing away this entire loop. + */ + FORCE_READ(*(uint64_t *)ptr); } return NULL; @@ -155,10 +162,15 @@ TEST_F_TIMEOUT(migration, shared_anon, 2*RUNTIME) memset(ptr, 0xde, TWOMEG); for (i = 0; i < self->nthreads - 1; i++) { pid = fork(); - if (!pid) + 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 + } else { self->pids[i] = pid; + } } ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); @@ -174,6 +186,9 @@ TEST_F_TIMEOUT(migration, private_anon_thp, 2*RUNTIME) uint64_t *ptr; int i; + if (!thp_is_enabled()) + SKIP(return, "Transparent Hugepages not available"); + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) SKIP(return, "Not enough threads or NUMA nodes available"); @@ -193,4 +208,106 @@ 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 (!thp_is_enabled()) + SKIP(return, "Transparent Hugepages not available"); + + 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 301abb99e027..68dd447a5454 100644 --- a/tools/testing/selftests/mm/mkdirty.c +++ b/tools/testing/selftests/mm/mkdirty.c @@ -22,7 +22,7 @@ #include <linux/userfaultfd.h> #include <linux/mempolicy.h> -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" static size_t pagesize; @@ -281,6 +281,7 @@ 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; } @@ -375,5 +376,5 @@ int main(void) if (err) ksft_exit_fail_msg("%d out of %d tests failed\n", err, ksft_test_num()); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c index 1fba77df7f62..9d349c151360 100644 --- a/tools/testing/selftests/mm/mlock-random-test.c +++ b/tools/testing/selftests/mm/mlock-random-test.c @@ -13,6 +13,7 @@ #include <sys/ipc.h> #include <sys/shm.h> #include <time.h> +#include "kselftest.h" #include "mlock2.h" #define CHUNK_UNIT (128 * 1024) @@ -31,14 +32,14 @@ int set_cap_limits(rlim_t max) new.rlim_cur = max; new.rlim_max = max; if (setrlimit(RLIMIT_MEMLOCK, &new)) { - perror("setrlimit() returns error\n"); + ksft_perror("setrlimit() returns error\n"); return -1; } /* drop capabilities including CAP_IPC_LOCK */ if (cap_set_proc(cap)) { - perror("cap_set_proc() returns error\n"); - return -2; + ksft_perror("cap_set_proc() returns error\n"); + return -1; } return 0; @@ -52,27 +53,24 @@ int get_proc_locked_vm_size(void) unsigned long lock_size = 0; f = fopen("/proc/self/status", "r"); - if (!f) { - perror("fopen"); - return -1; - } + if (!f) + ksft_exit_fail_msg("fopen: %s\n", strerror(errno)); while (fgets(line, 1024, f)) { if (strstr(line, "VmLck")) { ret = sscanf(line, "VmLck:\t%8lu kB", &lock_size); if (ret <= 0) { - printf("sscanf() on VmLck error: %s: %d\n", - line, ret); fclose(f); - return -1; + ksft_exit_fail_msg("sscanf() on VmLck error: %s: %d\n", + line, ret); } fclose(f); return (int)(lock_size << 10); } } - perror("cannot parse VmLck in /proc/self/status\n"); fclose(f); + ksft_exit_fail_msg("cannot parse VmLck in /proc/self/status: %s\n", strerror(errno)); return -1; } @@ -91,10 +89,8 @@ int get_proc_page_size(unsigned long addr) size_t size; smaps = seek_to_smaps_entry(addr); - if (!smaps) { - printf("Unable to parse /proc/self/smaps\n"); - return 0; - } + if (!smaps) + ksft_exit_fail_msg("Unable to parse /proc/self/smaps\n"); while (getline(&line, &size, smaps) > 0) { if (!strstr(line, "MMUPageSize")) { @@ -105,12 +101,9 @@ int get_proc_page_size(unsigned long addr) } /* found the MMUPageSize of this section */ - if (sscanf(line, "MMUPageSize: %8lu kB", - &mmupage_size) < 1) { - printf("Unable to parse smaps entry for Size:%s\n", - line); - break; - } + if (sscanf(line, "MMUPageSize: %8lu kB", &mmupage_size) < 1) + ksft_exit_fail_msg("Unable to parse smaps entry for Size:%s\n", + line); } free(line); @@ -136,7 +129,7 @@ int get_proc_page_size(unsigned long addr) * return value: 0 - success * else: failure */ -int test_mlock_within_limit(char *p, int alloc_size) +static void test_mlock_within_limit(char *p, int alloc_size) { int i; int ret = 0; @@ -145,11 +138,9 @@ int test_mlock_within_limit(char *p, int alloc_size) int page_size = 0; getrlimit(RLIMIT_MEMLOCK, &cur); - if (cur.rlim_cur < alloc_size) { - printf("alloc_size[%d] < %u rlimit,lead to mlock failure\n", - alloc_size, (unsigned int)cur.rlim_cur); - return -1; - } + if (cur.rlim_cur < alloc_size) + ksft_exit_fail_msg("alloc_size[%d] < %u rlimit,lead to mlock failure\n", + alloc_size, (unsigned int)cur.rlim_cur); srand(time(NULL)); for (i = 0; i < TEST_LOOP; i++) { @@ -169,13 +160,11 @@ int test_mlock_within_limit(char *p, int alloc_size) ret = mlock2_(p + start_offset, lock_size, MLOCK_ONFAULT); - if (ret) { - printf("%s() failure at |%p(%d)| mlock:|%p(%d)|\n", - is_mlock ? "mlock" : "mlock2", - p, alloc_size, - p + start_offset, lock_size); - return ret; - } + if (ret) + ksft_exit_fail_msg("%s() failure (%s) at |%p(%d)| mlock:|%p(%d)|\n", + is_mlock ? "mlock" : "mlock2", + strerror(errno), p, alloc_size, + p + start_offset, lock_size); } /* @@ -183,18 +172,12 @@ int test_mlock_within_limit(char *p, int alloc_size) */ locked_vm_size = get_proc_locked_vm_size(); page_size = get_proc_page_size((unsigned long)p); - if (page_size == 0) { - printf("cannot get proc MMUPageSize\n"); - return -1; - } - if (locked_vm_size > PAGE_ALIGN(alloc_size, page_size) + page_size) { - printf("test_mlock_within_limit() left VmLck:%d on %d chunk\n", - locked_vm_size, alloc_size); - return -1; - } + if (locked_vm_size > PAGE_ALIGN(alloc_size, page_size) + page_size) + ksft_exit_fail_msg("%s left VmLck:%d on %d chunk\n", + __func__, locked_vm_size, alloc_size); - return 0; + ksft_test_result_pass("%s\n", __func__); } @@ -213,7 +196,7 @@ int test_mlock_within_limit(char *p, int alloc_size) * return value: 0 - success * else: failure */ -int test_mlock_outof_limit(char *p, int alloc_size) +static void test_mlock_outof_limit(char *p, int alloc_size) { int i; int ret = 0; @@ -221,11 +204,9 @@ int test_mlock_outof_limit(char *p, int alloc_size) struct rlimit cur; getrlimit(RLIMIT_MEMLOCK, &cur); - if (cur.rlim_cur >= alloc_size) { - printf("alloc_size[%d] >%u rlimit, violates test condition\n", - alloc_size, (unsigned int)cur.rlim_cur); - return -1; - } + if (cur.rlim_cur >= alloc_size) + ksft_exit_fail_msg("alloc_size[%d] >%u rlimit, violates test condition\n", + alloc_size, (unsigned int)cur.rlim_cur); old_locked_vm_size = get_proc_locked_vm_size(); srand(time(NULL)); @@ -240,56 +221,47 @@ int test_mlock_outof_limit(char *p, int alloc_size) else ret = mlock2_(p + start_offset, lock_size, MLOCK_ONFAULT); - if (ret == 0) { - printf("%s() succeeds? on %p(%d) mlock%p(%d)\n", - is_mlock ? "mlock" : "mlock2", - p, alloc_size, - p + start_offset, lock_size); - return -1; - } + if (ret == 0) + ksft_exit_fail_msg("%s() succeeds? on %p(%d) mlock%p(%d)\n", + is_mlock ? "mlock" : "mlock2", + p, alloc_size, p + start_offset, lock_size); } locked_vm_size = get_proc_locked_vm_size(); - if (locked_vm_size != old_locked_vm_size) { - printf("tests leads to new mlocked page: old[%d], new[%d]\n", - old_locked_vm_size, - locked_vm_size); - return -1; - } + if (locked_vm_size != old_locked_vm_size) + ksft_exit_fail_msg("tests leads to new mlocked page: old[%d], new[%d]\n", + old_locked_vm_size, + locked_vm_size); - return 0; + ksft_test_result_pass("%s\n", __func__); } int main(int argc, char **argv) { char *p = NULL; - int ret = 0; + + ksft_print_header(); if (set_cap_limits(MLOCK_RLIMIT_SIZE)) - return -1; + ksft_finished(); + + ksft_set_plan(2); p = malloc(MLOCK_WITHIN_LIMIT_SIZE); - if (p == NULL) { - perror("malloc() failure\n"); - return -1; - } - ret = test_mlock_within_limit(p, MLOCK_WITHIN_LIMIT_SIZE); - if (ret) - return ret; + if (p == NULL) + ksft_exit_fail_msg("malloc() failure: %s\n", strerror(errno)); + + test_mlock_within_limit(p, MLOCK_WITHIN_LIMIT_SIZE); munlock(p, MLOCK_WITHIN_LIMIT_SIZE); free(p); - p = malloc(MLOCK_OUTOF_LIMIT_SIZE); - if (p == NULL) { - perror("malloc() failure\n"); - return -1; - } - ret = test_mlock_outof_limit(p, MLOCK_OUTOF_LIMIT_SIZE); - if (ret) - return ret; + if (p == NULL) + ksft_exit_fail_msg("malloc() failure: %s\n", strerror(errno)); + + test_mlock_outof_limit(p, MLOCK_OUTOF_LIMIT_SIZE); munlock(p, MLOCK_OUTOF_LIMIT_SIZE); free(p); - return 0; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/mlock2-tests.c b/tools/testing/selftests/mm/mlock2-tests.c index 80cddc0de206..b474f2b20def 100644 --- a/tools/testing/selftests/mm/mlock2-tests.c +++ b/tools/testing/selftests/mm/mlock2-tests.c @@ -7,10 +7,9 @@ #include <sys/time.h> #include <sys/resource.h> #include <stdbool.h> +#include "kselftest.h" #include "mlock2.h" -#include "../kselftest.h" - struct vm_boundaries { unsigned long start; unsigned long end; @@ -21,8 +20,6 @@ static int get_vm_area(unsigned long addr, struct vm_boundaries *area) FILE *file; int ret = 1; char line[1024] = {0}; - char *end_addr; - char *stop; unsigned long start; unsigned long end; @@ -38,22 +35,11 @@ static int get_vm_area(unsigned long addr, struct vm_boundaries *area) memset(area, 0, sizeof(struct vm_boundaries)); while(fgets(line, 1024, file)) { - end_addr = strchr(line, '-'); - if (!end_addr) { - printf("cannot parse /proc/self/maps\n"); - goto out; - } - *end_addr = '\0'; - end_addr++; - stop = strchr(end_addr, ' '); - if (!stop) { - printf("cannot parse /proc/self/maps\n"); + if (sscanf(line, "%lx-%lx", &start, &end) != 2) { + ksft_print_msg("cannot parse /proc/self/maps\n"); goto out; } - sscanf(line, "%lx", &start); - sscanf(end_addr, "%lx", &end); - if (start <= addr && end > addr) { area->start = start; area->end = end; @@ -78,7 +64,7 @@ static bool is_vmflag_set(unsigned long addr, const char *vmflag) smaps = seek_to_smaps_entry(addr); if (!smaps) { - printf("Unable to parse /proc/self/smaps\n"); + ksft_print_msg("Unable to parse /proc/self/smaps\n"); goto out; } @@ -115,7 +101,7 @@ static unsigned long get_value_for_name(unsigned long addr, const char *name) smaps = seek_to_smaps_entry(addr); if (!smaps) { - printf("Unable to parse /proc/self/smaps\n"); + ksft_print_msg("Unable to parse /proc/self/smaps\n"); goto out; } @@ -129,7 +115,7 @@ static unsigned long get_value_for_name(unsigned long addr, const char *name) value_ptr = line + strlen(name); if (sscanf(value_ptr, "%lu kB", &value) < 1) { - printf("Unable to parse smaps entry for Size\n"); + ksft_print_msg("Unable to parse smaps entry for Size\n"); goto out; } break; @@ -180,57 +166,45 @@ static int lock_check(unsigned long addr) static int unlock_lock_check(char *map) { if (is_vmflag_set((unsigned long)map, LOCKED)) { - printf("VMA flag %s is present on page 1 after unlock\n", LOCKED); + ksft_print_msg("VMA flag %s is present on page 1 after unlock\n", LOCKED); return 1; } return 0; } -static int test_mlock_lock() +static void test_mlock_lock(void) { char *map; - int ret = 1; unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (map == MAP_FAILED) { - perror("test_mlock_locked mmap"); - goto out; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); if (mlock2_(map, 2 * page_size, 0)) { - if (errno == ENOSYS) { - printf("Cannot call new mlock family, skipping test\n"); - _exit(KSFT_SKIP); - } - perror("mlock2(0)"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("mlock2(0): %s\n", strerror(errno)); } - if (!lock_check((unsigned long)map)) - goto unmap; + ksft_test_result(lock_check((unsigned long)map), "%s: Locked\n", __func__); /* Now unlock and recheck attributes */ if (munlock(map, 2 * page_size)) { - perror("munlock()"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("munlock(): %s\n", strerror(errno)); } - ret = unlock_lock_check(map); - -unmap: + ksft_test_result(!unlock_lock_check(map), "%s: Unlocked\n", __func__); munmap(map, 2 * page_size); -out: - return ret; } static int onfault_check(char *map) { *map = 'a'; if (!is_vma_lock_on_fault((unsigned long)map)) { - printf("VMA is not marked for lock on fault\n"); + ksft_print_msg("VMA is not marked for lock on fault\n"); return 1; } @@ -243,172 +217,131 @@ static int unlock_onfault_check(char *map) if (is_vma_lock_on_fault((unsigned long)map) || is_vma_lock_on_fault((unsigned long)map + page_size)) { - printf("VMA is still lock on fault after unlock\n"); + ksft_print_msg("VMA is still lock on fault after unlock\n"); return 1; } return 0; } -static int test_mlock_onfault() +static void test_mlock_onfault(void) { char *map; - int ret = 1; unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (map == MAP_FAILED) { - perror("test_mlock_locked mmap"); - goto out; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) { - if (errno == ENOSYS) { - printf("Cannot call new mlock family, skipping test\n"); - _exit(KSFT_SKIP); - } - perror("mlock2(MLOCK_ONFAULT)"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("mlock2(MLOCK_ONFAULT): %s\n", strerror(errno)); } - if (onfault_check(map)) - goto unmap; + ksft_test_result(!onfault_check(map), "%s: VMA marked for lock on fault\n", __func__); /* Now unlock and recheck attributes */ if (munlock(map, 2 * page_size)) { - if (errno == ENOSYS) { - printf("Cannot call new mlock family, skipping test\n"); - _exit(KSFT_SKIP); - } - perror("munlock()"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("munlock(): %s\n", strerror(errno)); } - ret = unlock_onfault_check(map); -unmap: + ksft_test_result(!unlock_onfault_check(map), "VMA open lock after fault\n"); munmap(map, 2 * page_size); -out: - return ret; } -static int test_lock_onfault_of_present() +static void test_lock_onfault_of_present(void) { char *map; - int ret = 1; unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (map == MAP_FAILED) { - perror("test_mlock_locked mmap"); - goto out; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); *map = 'a'; if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) { - if (errno == ENOSYS) { - printf("Cannot call new mlock family, skipping test\n"); - _exit(KSFT_SKIP); - } - perror("mlock2(MLOCK_ONFAULT)"); - goto unmap; + munmap(map, 2 * page_size); + ksft_test_result_fail("mlock2(MLOCK_ONFAULT) error: %s", strerror(errno)); } - if (!is_vma_lock_on_fault((unsigned long)map) || - !is_vma_lock_on_fault((unsigned long)map + page_size)) { - printf("VMA with present pages is not marked lock on fault\n"); - goto unmap; - } - ret = 0; -unmap: + ksft_test_result(is_vma_lock_on_fault((unsigned long)map) || + is_vma_lock_on_fault((unsigned long)map + page_size), + "VMA with present pages is not marked lock on fault\n"); munmap(map, 2 * page_size); -out: - return ret; } -static int test_munlockall() +static void test_munlockall0(void) { char *map; - int ret = 1; unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - - if (map == MAP_FAILED) { - perror("test_munlockall mmap"); - goto out; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s\n", strerror(errno)); if (mlockall(MCL_CURRENT)) { - perror("mlockall(MCL_CURRENT)"); - goto out; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("mlockall(MCL_CURRENT): %s\n", strerror(errno)); } - if (!lock_check((unsigned long)map)) - goto unmap; + ksft_test_result(lock_check((unsigned long)map), "%s: Locked memory area\n", __func__); if (munlockall()) { - perror("munlockall()"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("munlockall(): %s\n", strerror(errno)); } - if (unlock_lock_check(map)) - goto unmap; - + ksft_test_result(!unlock_lock_check(map), "%s: No locked memory\n", __func__); munmap(map, 2 * page_size); +} + +static void test_munlockall1(void) +{ + char *map; + unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - - if (map == MAP_FAILED) { - perror("test_munlockall second mmap"); - goto out; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); if (mlockall(MCL_CURRENT | MCL_ONFAULT)) { - perror("mlockall(MCL_CURRENT | MCL_ONFAULT)"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("mlockall(MCL_CURRENT | MCL_ONFAULT): %s\n", strerror(errno)); } - if (onfault_check(map)) - goto unmap; + ksft_test_result(!onfault_check(map), "%s: VMA marked for lock on fault\n", __func__); if (munlockall()) { - perror("munlockall()"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("munlockall(): %s\n", strerror(errno)); } - if (unlock_onfault_check(map)) - goto unmap; + ksft_test_result(!unlock_onfault_check(map), "%s: Unlocked\n", __func__); if (mlockall(MCL_CURRENT | MCL_FUTURE)) { - perror("mlockall(MCL_CURRENT | MCL_FUTURE)"); - goto out; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("mlockall(MCL_CURRENT | MCL_FUTURE): %s\n", strerror(errno)); } - if (!lock_check((unsigned long)map)) - goto unmap; + ksft_test_result(lock_check((unsigned long)map), "%s: Locked\n", __func__); if (munlockall()) { - perror("munlockall()"); - goto unmap; + munmap(map, 2 * page_size); + ksft_exit_fail_msg("munlockall() %s\n", strerror(errno)); } - ret = unlock_lock_check(map); - -unmap: + ksft_test_result(!unlock_lock_check(map), "%s: No locked memory\n", __func__); munmap(map, 2 * page_size); -out: - munlockall(); - return ret; } -static int test_vma_management(bool call_mlock) +static void test_vma_management(bool call_mlock) { - int ret = 1; void *map; unsigned long page_size = getpagesize(); struct vm_boundaries page1; @@ -417,25 +350,19 @@ static int test_vma_management(bool call_mlock) map = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (map == MAP_FAILED) { - perror("mmap()"); - return ret; - } + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); if (call_mlock && mlock2_(map, 3 * page_size, MLOCK_ONFAULT)) { - if (errno == ENOSYS) { - printf("Cannot call new mlock family, skipping test\n"); - _exit(KSFT_SKIP); - } - perror("mlock(ONFAULT)\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("mlock error: %s", strerror(errno)); } if (get_vm_area((unsigned long)map, &page1) || get_vm_area((unsigned long)map + page_size, &page2) || get_vm_area((unsigned long)map + page_size * 2, &page3)) { - printf("couldn't find mapping in /proc/self/maps\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("couldn't find mapping in /proc/self/maps"); } /* @@ -444,76 +371,86 @@ static int test_vma_management(bool call_mlock) * not a failure) */ if (page1.start != page2.start || page2.start != page3.start) { - printf("VMAs are not merged to start, aborting test\n"); - ret = 0; - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("VMAs are not merged to start, aborting test"); } if (munlock(map + page_size, page_size)) { - perror("munlock()"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("munlock(): %s", strerror(errno)); } if (get_vm_area((unsigned long)map, &page1) || get_vm_area((unsigned long)map + page_size, &page2) || get_vm_area((unsigned long)map + page_size * 2, &page3)) { - printf("couldn't find mapping in /proc/self/maps\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("couldn't find mapping in /proc/self/maps"); } /* All three VMAs should be different */ if (page1.start == page2.start || page2.start == page3.start) { - printf("failed to split VMA for munlock\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("failed to split VMA for munlock"); } /* Now unlock the first and third page and check the VMAs again */ if (munlock(map, page_size * 3)) { - perror("munlock()"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("munlock(): %s", strerror(errno)); } if (get_vm_area((unsigned long)map, &page1) || get_vm_area((unsigned long)map + page_size, &page2) || get_vm_area((unsigned long)map + page_size * 2, &page3)) { - printf("couldn't find mapping in /proc/self/maps\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("couldn't find mapping in /proc/self/maps"); } /* Now all three VMAs should be the same */ if (page1.start != page2.start || page2.start != page3.start) { - printf("failed to merge VMAs after munlock\n"); - goto out; + munmap(map, 3 * page_size); + ksft_test_result_fail("failed to merge VMAs after munlock"); } - ret = 0; -out: + ksft_test_result_pass("%s call_mlock %d\n", __func__, call_mlock); munmap(map, 3 * page_size); - return ret; } -static int test_mlockall(int (test_function)(bool call_mlock)) +static void test_mlockall(void) { - int ret = 1; + if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) + ksft_exit_fail_msg("mlockall failed: %s\n", strerror(errno)); - if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) { - perror("mlockall"); - return ret; - } - - ret = test_function(false); + test_vma_management(false); munlockall(); - return ret; } int main(int argc, char **argv) { - int ret = 0; - ret += test_mlock_lock(); - ret += test_mlock_onfault(); - ret += test_munlockall(); - ret += test_lock_onfault_of_present(); - ret += test_vma_management(true); - ret += test_mlockall(test_vma_management); - return ret; + int ret, size = 3 * getpagesize(); + void *map; + + ksft_print_header(); + + map = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap error: %s", strerror(errno)); + + ret = mlock2_(map, size, MLOCK_ONFAULT); + if (ret && errno == ENOSYS) + ksft_finished(); + + munmap(map, size); + + ksft_set_plan(13); + + test_mlock_lock(); + test_mlock_onfault(); + test_munlockall0(); + test_munlockall1(); + test_lock_onfault_of_present(); + test_vma_management(true); + test_mlockall(); + + ksft_finished(); } diff --git a/tools/testing/selftests/mm/mlock2.h b/tools/testing/selftests/mm/mlock2.h index 8e02991b313c..81e77fa41901 100644 --- a/tools/testing/selftests/mm/mlock2.h +++ b/tools/testing/selftests/mm/mlock2.h @@ -6,12 +6,13 @@ static int mlock2_(void *start, size_t len, int flags) { -#ifdef __NR_mlock2 - return syscall(__NR_mlock2, start, len, flags); -#else - errno = ENOSYS; - return -1; -#endif + int ret = syscall(__NR_mlock2, start, len, flags); + + if (ret) { + errno = ret; + return -1; + } + return 0; } static FILE *seek_to_smaps_entry(unsigned long addr) @@ -27,10 +28,8 @@ static FILE *seek_to_smaps_entry(unsigned long addr) char path[BUFSIZ]; file = fopen("/proc/self/smaps", "r"); - if (!file) { - perror("fopen smaps"); - _exit(1); - } + if (!file) + ksft_exit_fail_msg("fopen smaps: %s\n", strerror(errno)); while (getline(&line, &size, file) > 0) { if (sscanf(line, "%lx-%lx %s %lx %s %lu %s\n", diff --git a/tools/testing/selftests/mm/mrelease_test.c b/tools/testing/selftests/mm/mrelease_test.c index dca21042b679..64e8d00ae944 100644 --- a/tools/testing/selftests/mm/mrelease_test.c +++ b/tools/testing/selftests/mm/mrelease_test.c @@ -7,11 +7,12 @@ #include <stdbool.h> #include <stdio.h> #include <stdlib.h> +#include <sys/syscall.h> #include <sys/wait.h> #include <unistd.h> #include <asm-generic/unistd.h> #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" #define MB(x) (x << 20) #define MAX_SIZE_MB 1024 @@ -25,19 +26,15 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) buf = (char *)mmap(NULL, nr_pages * psize(), PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, 0, 0); - if (buf == MAP_FAILED) { - perror("mmap failed, halting the test"); - return KSFT_FAIL; - } + if (buf == MAP_FAILED) + ksft_exit_fail_msg("mmap failed, halting the test: %s\n", strerror(errno)); for (i = 0; i < nr_pages; i++) *((unsigned long *)(buf + (i * psize()))) = i; /* Signal the parent that the child is ready */ - if (write(pipefd, "", 1) < 0) { - perror("write"); - return KSFT_FAIL; - } + if (write(pipefd, "", 1) < 0) + ksft_exit_fail_msg("write: %s\n", strerror(errno)); /* Wait to be killed (when reparenting happens) */ while (getppid() == ppid && timeout > 0) { @@ -53,23 +50,17 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) /* The process_mrelease calls in this test are expected to fail */ static void run_negative_tests(int pidfd) { - int res; /* Test invalid flags. Expect to fail with EINVAL error code. */ if (!syscall(__NR_process_mrelease, pidfd, (unsigned int)-1) || errno != EINVAL) { - res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); - perror("process_mrelease with wrong flags"); - exit(res); + ksft_exit_fail_msg("process_mrelease with wrong flags: %s\n", strerror(errno)); } /* * Test reaping while process is alive with no pending SIGKILL. * Expect to fail with EINVAL error code. */ - if (!syscall(__NR_process_mrelease, pidfd, 0) || errno != EINVAL) { - res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); - perror("process_mrelease on a live process"); - exit(res); - } + if (!syscall(__NR_process_mrelease, pidfd, 0) || errno != EINVAL) + ksft_exit_fail_msg("process_mrelease on a live process: %s\n", strerror(errno)); } static int child_main(int pipefd[], size_t size) @@ -92,11 +83,18 @@ int main(void) char byte; int res; + ksft_print_header(); + ksft_set_plan(1); + /* Test a wrong pidfd */ if (!syscall(__NR_process_mrelease, -1, 0) || errno != EBADF) { - res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); - perror("process_mrelease with wrong pidfd"); - exit(res); + if (errno == ENOSYS) { + ksft_test_result_skip("process_mrelease not implemented\n"); + ksft_finished(); + } else { + ksft_exit_fail_msg("process_mrelease with wrong pidfd: %s", + strerror(errno)); + } } /* Start the test with 1MB child memory allocation */ @@ -106,16 +104,14 @@ retry: * Pipe for the child to signal when it's done allocating * memory */ - if (pipe(pipefd)) { - perror("pipe"); - exit(KSFT_FAIL); - } + if (pipe(pipefd)) + ksft_exit_fail_msg("pipe: %s\n", strerror(errno)); + pid = fork(); if (pid < 0) { - perror("fork"); close(pipefd[0]); close(pipefd[1]); - exit(KSFT_FAIL); + ksft_exit_fail_msg("fork: %s\n", strerror(errno)); } if (pid == 0) { @@ -133,28 +129,23 @@ retry: res = read(pipefd[0], &byte, 1); close(pipefd[0]); if (res < 0) { - perror("read"); if (!kill(pid, SIGKILL)) waitpid(pid, NULL, 0); - exit(KSFT_FAIL); + ksft_exit_fail_msg("read: %s\n", strerror(errno)); } pidfd = syscall(__NR_pidfd_open, pid, 0); if (pidfd < 0) { - perror("pidfd_open"); if (!kill(pid, SIGKILL)) waitpid(pid, NULL, 0); - exit(KSFT_FAIL); + ksft_exit_fail_msg("pidfd_open: %s\n", strerror(errno)); } /* Run negative tests which require a live child */ run_negative_tests(pidfd); - if (kill(pid, SIGKILL)) { - res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); - perror("kill"); - exit(res); - } + if (kill(pid, SIGKILL)) + ksft_exit_fail_msg("kill: %s\n", strerror(errno)); success = (syscall(__NR_process_mrelease, pidfd, 0) == 0); if (!success) { @@ -168,18 +159,15 @@ retry: if (errno == ESRCH) { retry = (size <= MAX_SIZE_MB); } else { - res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); - perror("process_mrelease"); waitpid(pid, NULL, 0); - exit(res); + ksft_exit_fail_msg("process_mrelease: %s\n", strerror(errno)); } } /* Cleanup to prevent zombies */ - if (waitpid(pid, NULL, 0) < 0) { - perror("waitpid"); - exit(KSFT_FAIL); - } + if (waitpid(pid, NULL, 0) < 0) + ksft_exit_fail_msg("waitpid: %s\n", strerror(errno)); + close(pidfd); if (!success) { @@ -187,11 +175,10 @@ retry: size *= 2; goto retry; } - printf("All process_mrelease attempts failed!\n"); - exit(KSFT_FAIL); + ksft_exit_fail_msg("All process_mrelease attempts failed!\n"); } - printf("Success reaping a child with %zuMB of memory allocations\n", - size); - return KSFT_PASS; + ksft_test_result_pass("Success reaping a child with %zuMB of memory allocations\n", + size); + ksft_finished(); } diff --git a/tools/testing/selftests/mm/mremap_dontunmap.c b/tools/testing/selftests/mm/mremap_dontunmap.c index ca2359835e75..a4f75d836733 100644 --- a/tools/testing/selftests/mm/mremap_dontunmap.c +++ b/tools/testing/selftests/mm/mremap_dontunmap.c @@ -7,13 +7,14 @@ */ #define _GNU_SOURCE #include <sys/mman.h> +#include <linux/mman.h> #include <errno.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <unistd.h> -#include "../kselftest.h" +#include "kselftest.h" unsigned long page_size; char *page_buffer; @@ -26,14 +27,14 @@ static void dump_maps(void) system(cmd); } -#define BUG_ON(condition, description) \ - do { \ - if (condition) { \ - fprintf(stderr, "[FAIL]\t%s():%d\t%s:%s\n", __func__, \ - __LINE__, (description), strerror(errno)); \ - dump_maps(); \ - exit(1); \ - } \ +#define BUG_ON(condition, description) \ + do { \ + if (condition) { \ + dump_maps(); \ + ksft_exit_fail_msg("[FAIL]\t%s:%d\t%s:%s\n", \ + __func__, __LINE__, (description), \ + strerror(errno)); \ + } \ } while (0) // Try a simple operation for to "test" for kernel support this prevents @@ -121,6 +122,7 @@ static void mremap_dontunmap_simple() "unable to unmap destination mapping"); BUG_ON(munmap(source_mapping, num_pages * page_size) == -1, "unable to unmap source mapping"); + ksft_test_result_pass("%s\n", __func__); } // This test validates that MREMAP_DONTUNMAP on a shared mapping works as expected. @@ -172,6 +174,7 @@ static void mremap_dontunmap_simple_shmem() "unable to unmap destination mapping"); BUG_ON(munmap(source_mapping, num_pages * page_size) == -1, "unable to unmap source mapping"); + ksft_test_result_pass("%s\n", __func__); } // This test validates MREMAP_DONTUNMAP will move page tables to a specific @@ -218,6 +221,7 @@ static void mremap_dontunmap_simple_fixed() "unable to unmap destination mapping"); BUG_ON(munmap(source_mapping, num_pages * page_size) == -1, "unable to unmap source mapping"); + ksft_test_result_pass("%s\n", __func__); } // This test validates that we can MREMAP_DONTUNMAP for a portion of an @@ -268,6 +272,7 @@ static void mremap_dontunmap_partial_mapping() "unable to unmap destination mapping"); BUG_ON(munmap(source_mapping, num_pages * page_size) == -1, "unable to unmap source mapping"); + ksft_test_result_pass("%s\n", __func__); } // This test validates that we can remap over only a portion of a mapping. @@ -327,19 +332,24 @@ static void mremap_dontunmap_partial_mapping_overwrite(void) "unable to unmap destination mapping"); BUG_ON(munmap(source_mapping, 5 * page_size) == -1, "unable to unmap source mapping"); + ksft_test_result_pass("%s\n", __func__); } int main(void) { + ksft_print_header(); + page_size = sysconf(_SC_PAGE_SIZE); // test for kernel support for MREMAP_DONTUNMAP skipping the test if // not. if (kernel_support_for_mremap_dontunmap() != 0) { - printf("No kernel support for MREMAP_DONTUNMAP\n"); - return KSFT_SKIP; + ksft_print_msg("No kernel support for MREMAP_DONTUNMAP\n"); + ksft_finished(); } + ksft_set_plan(5); + // Keep a page sized buffer around for when we need it. page_buffer = mmap(NULL, page_size, PROT_READ | PROT_WRITE, @@ -355,6 +365,5 @@ int main(void) BUG_ON(munmap(page_buffer, page_size) == -1, "unable to unmap page buffer"); - printf("OK\n"); - return 0; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 5c3773de9f0f..308576437228 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -5,14 +5,18 @@ #define _GNU_SOURCE #include <errno.h> +#include <fcntl.h> +#include <linux/userfaultfd.h> #include <stdlib.h> #include <stdio.h> #include <string.h> +#include <sys/ioctl.h> #include <sys/mman.h> +#include <syscall.h> #include <time.h> #include <stdbool.h> -#include "../kselftest.h" +#include "kselftest.h" #define EXPECT_SUCCESS 0 #define EXPECT_FAILURE 1 @@ -22,13 +26,19 @@ #define VALIDATION_DEFAULT_THRESHOLD 4 /* 4MB */ #define VALIDATION_NO_THRESHOLD 0 /* Verify the entire region */ +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) +#define MAX(X, Y) ((X) > (Y) ? (X) : (Y)) +#endif +#define SIZE_MB(m) ((size_t)m * (1024 * 1024)) +#define SIZE_KB(k) ((size_t)k * 1024) struct config { unsigned long long src_alignment; unsigned long long dest_alignment; unsigned long long region_size; int overlapping; + unsigned int dest_preamble_size; }; struct test { @@ -44,6 +54,7 @@ enum { _1MB = 1ULL << 20, _2MB = 2ULL << 20, _4MB = 4ULL << 20, + _5MB = 5ULL << 20, _1GB = 1ULL << 30, _2GB = 2ULL << 30, PMD = _2MB, @@ -65,6 +76,27 @@ enum { .expect_failure = should_fail \ } +/* compute square root using binary search */ +static unsigned long get_sqrt(unsigned long val) +{ + unsigned long low = 1; + + /* assuming rand_size is less than 1TB */ + unsigned long high = (1UL << 20); + + while (low <= high) { + unsigned long mid = low + (high - low) / 2; + unsigned long temp = mid * mid; + + if (temp == val) + return mid; + if (temp < val) + low = mid + 1; + high = mid - 1; + } + return low; +} + /* * Returns false if the requested remap region overlaps with an * existing mapping (e.g text, stack) else returns true. @@ -122,22 +154,25 @@ static unsigned long long get_mmap_min_addr(void) * Using /proc/self/maps, assert that the specified address range is contained * within a single mapping. */ -static bool is_range_mapped(FILE *maps_fp, void *start, void *end) +static bool is_range_mapped(FILE *maps_fp, unsigned long start, + unsigned long end) { char *line = NULL; size_t len = 0; bool success = false; + unsigned long first_val, second_val; rewind(maps_fp); while (getline(&line, &len, maps_fp) != -1) { - char *first = strtok(line, "- "); - void *first_val = (void *)strtol(first, NULL, 16); - char *second = strtok(NULL, "- "); - void *second_val = (void *) strtol(second, NULL, 16); + if (sscanf(line, "%lx-%lx", &first_val, &second_val) != 2) { + ksft_exit_fail_msg("cannot parse /proc/self/maps\n"); + break; + } if (first_val <= start && second_val >= end) { success = true; + fflush(maps_fp); break; } } @@ -145,6 +180,69 @@ static bool is_range_mapped(FILE *maps_fp, void *start, void *end) return success; } +/* Check if [ptr, ptr + size) mapped in /proc/self/maps. */ +static bool is_ptr_mapped(FILE *maps_fp, void *ptr, unsigned long size) +{ + unsigned long start = (unsigned long)ptr; + unsigned long end = start + size; + + return is_range_mapped(maps_fp, start, end); +} + +/* + * Returns the start address of the mapping on success, else returns + * NULL on failure. + */ +static void *get_source_mapping(struct config c) +{ + unsigned long long addr = 0ULL; + void *src_addr = NULL; + unsigned long long mmap_min_addr; + + mmap_min_addr = get_mmap_min_addr(); + /* + * For some tests, we need to not have any mappings below the + * source mapping. Add some headroom to mmap_min_addr for this. + */ + mmap_min_addr += 10 * _4MB; + +retry: + addr += c.src_alignment; + if (addr < mmap_min_addr) + goto retry; + + src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); + if (src_addr == MAP_FAILED) { + if (errno == EPERM || errno == EEXIST) + goto retry; + goto error; + } + /* + * Check that the address is aligned to the specified alignment. + * Addresses which have alignments that are multiples of that + * specified are not considered valid. For instance, 1GB address is + * 2MB-aligned, however it will not be considered valid for a + * requested alignment of 2MB. This is done to reduce coincidental + * alignment in the tests. + */ + if (((unsigned long long) src_addr & (c.src_alignment - 1)) || + !((unsigned long long) src_addr & c.src_alignment)) { + munmap(src_addr, c.region_size); + goto retry; + } + + if (!src_addr) + goto error; + + return src_addr; +error: + ksft_print_msg("Failed to map source region: %s\n", + strerror(errno)); + return NULL; +} + /* * This test validates that merge is called when expanding a mapping. * Mapping containing three pages is created, middle page is unmapped @@ -175,7 +273,8 @@ static void mremap_expand_merge(FILE *maps_fp, unsigned long page_size) goto out; } - success = is_range_mapped(maps_fp, start, start + 3 * page_size); + success = is_range_mapped(maps_fp, (unsigned long)start, + (unsigned long)(start + 3 * page_size)); munmap(start, 3 * page_size); out: @@ -214,7 +313,8 @@ static void mremap_expand_merge_offset(FILE *maps_fp, unsigned long page_size) goto out; } - success = is_range_mapped(maps_fp, start, start + 3 * page_size); + success = is_range_mapped(maps_fp, (unsigned long)start, + (unsigned long)(start + 3 * page_size)); munmap(start, 3 * page_size); out: @@ -225,63 +325,681 @@ out: } /* - * Returns the start address of the mapping on success, else returns - * NULL on failure. + * Verify that an mremap within a range does not cause corruption + * of unrelated part of range. + * + * Consider the following range which is 2MB aligned and is + * a part of a larger 20MB range which is not shown. Each + * character is 256KB below making the source and destination + * 2MB each. The lower case letters are moved (s to d) and the + * upper case letters are not moved. The below test verifies + * that the upper case S letters are not corrupted by the + * adjacent mremap. + * + * |DDDDddddSSSSssss| */ -static void *get_source_mapping(struct config c) +static void mremap_move_within_range(unsigned int pattern_seed, char *rand_addr) { - unsigned long long addr = 0ULL; - void *src_addr = NULL; - unsigned long long mmap_min_addr; + char *test_name = "mremap mremap move within range"; + void *src, *dest; + unsigned int i, success = 1; + + size_t size = SIZE_MB(20); + void *ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (ptr == MAP_FAILED) { + perror("mmap"); + success = 0; + goto out; + } + memset(ptr, 0, size); - mmap_min_addr = get_mmap_min_addr(); + src = ptr + SIZE_MB(6); + src = (void *)((unsigned long)src & ~(SIZE_MB(2) - 1)); -retry: - addr += c.src_alignment; - if (addr < mmap_min_addr) - goto retry; + /* Set byte pattern for source block. */ + memcpy(src, rand_addr, SIZE_MB(2)); - src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, - MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, - -1, 0); - if (src_addr == MAP_FAILED) { - if (errno == EPERM || errno == EEXIST) - goto retry; - goto error; + dest = src - SIZE_MB(2); + + void *new_ptr = mremap(src + SIZE_MB(1), SIZE_MB(1), SIZE_MB(1), + MREMAP_MAYMOVE | MREMAP_FIXED, dest + SIZE_MB(1)); + if (new_ptr == MAP_FAILED) { + perror("mremap"); + success = 0; + goto out; } + + /* Verify byte pattern after remapping */ + srand(pattern_seed); + for (i = 0; i < SIZE_MB(1); i++) { + char c = (char) rand(); + + if (((char *)src)[i] != c) { + ksft_print_msg("Data at src at %d got corrupted due to unrelated mremap\n", + i); + ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, + ((char *) src)[i] & 0xff); + success = 0; + } + } + +out: + if (munmap(ptr, size) == -1) + perror("munmap"); + + if (success) + ksft_test_result_pass("%s\n", test_name); + else + ksft_test_result_fail("%s\n", test_name); +} + +static bool is_multiple_vma_range_ok(unsigned int pattern_seed, + char *ptr, unsigned long page_size) +{ + int i; + + srand(pattern_seed); + for (i = 0; i <= 10; i += 2) { + int j; + char *buf = &ptr[i * page_size]; + size_t size = i == 4 ? 2 * page_size : page_size; + + for (j = 0; j < size; j++) { + char chr = rand(); + + if (chr != buf[j]) { + ksft_print_msg("page %d offset %d corrupted, expected %d got %d\n", + i, j, chr, buf[j]); + return false; + } + } + } + + return true; +} + +static void mremap_move_multiple_vmas(unsigned int pattern_seed, + unsigned long page_size, + bool dont_unmap) +{ + int mremap_flags = MREMAP_FIXED | MREMAP_MAYMOVE; + char *test_name = "mremap move multiple vmas"; + const size_t size = 11 * page_size; + bool success = true; + char *ptr, *tgt_ptr; + int i; + + if (dont_unmap) + mremap_flags |= MREMAP_DONTUNMAP; + + ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, -1, 0); + if (ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out; + } + + tgt_ptr = mmap(NULL, 2 * size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, -1, 0); + if (tgt_ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out; + } + if (munmap(tgt_ptr, 2 * size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + /* - * Check that the address is aligned to the specified alignment. - * Addresses which have alignments that are multiples of that - * specified are not considered valid. For instance, 1GB address is - * 2MB-aligned, however it will not be considered valid for a - * requested alignment of 2MB. This is done to reduce coincidental - * alignment in the tests. + * Unmap so we end up with: + * + * 0 2 4 5 6 8 10 offset in buffer + * |*| |*| |*****| |*| |*| + * |*| |*| |*****| |*| |*| + * 0 1 2 3 4 5 6 pattern offset */ - if (((unsigned long long) src_addr & (c.src_alignment - 1)) || - !((unsigned long long) src_addr & c.src_alignment)) { - munmap(src_addr, c.region_size); - goto retry; + for (i = 1; i < 10; i += 2) { + if (i == 5) + continue; + + if (munmap(&ptr[i * page_size], page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } } - if (!src_addr) - goto error; + srand(pattern_seed); - return src_addr; -error: - ksft_print_msg("Failed to map source region: %s\n", - strerror(errno)); - return NULL; + /* Set up random patterns. */ + for (i = 0; i <= 10; i += 2) { + int j; + size_t size = i == 4 ? 2 * page_size : page_size; + char *buf = &ptr[i * page_size]; + + for (j = 0; j < size; j++) + buf[j] = rand(); + } + + /* First, just move the whole thing. */ + if (mremap(ptr, size, size, mremap_flags, tgt_ptr) == MAP_FAILED) { + perror("mremap"); + success = false; + goto out_unmap; + } + /* Check move was ok. */ + if (!is_multiple_vma_range_ok(pattern_seed, tgt_ptr, page_size)) { + success = false; + goto out_unmap; + } + + /* Move next to itself. */ + if (mremap(tgt_ptr, size, size, mremap_flags, + &tgt_ptr[size]) == MAP_FAILED) { + perror("mremap"); + success = false; + goto out_unmap; + } + /* Check that the move is ok. */ + if (!is_multiple_vma_range_ok(pattern_seed, &tgt_ptr[size], page_size)) { + success = false; + goto out_unmap; + } + + /* Map a range to overwrite. */ + if (mmap(tgt_ptr, size, PROT_NONE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0) == MAP_FAILED) { + perror("mmap tgt"); + success = false; + goto out_unmap; + } + /* Move and overwrite. */ + if (mremap(&tgt_ptr[size], size, size, + mremap_flags, tgt_ptr) == MAP_FAILED) { + perror("mremap"); + success = false; + goto out_unmap; + } + /* Check that the move is ok. */ + if (!is_multiple_vma_range_ok(pattern_seed, tgt_ptr, page_size)) { + success = false; + goto out_unmap; + } + +out_unmap: + if (munmap(tgt_ptr, 2 * size)) + perror("munmap tgt"); + if (munmap(ptr, size)) + perror("munmap src"); + +out: + if (success) + ksft_test_result_pass("%s%s\n", test_name, + dont_unmap ? " [dontunnmap]" : ""); + else + ksft_test_result_fail("%s%s\n", test_name, + dont_unmap ? " [dontunnmap]" : ""); +} + +static void mremap_shrink_multiple_vmas(unsigned long page_size, + bool inplace) +{ + char *test_name = "mremap shrink multiple vmas"; + const size_t size = 10 * page_size; + bool success = true; + char *ptr, *tgt_ptr; + void *res; + int i; + + ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, -1, 0); + if (ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out; + } + + tgt_ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, -1, 0); + if (tgt_ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out; + } + if (munmap(tgt_ptr, size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + + /* + * Unmap so we end up with: + * + * 0 2 4 6 8 10 offset in buffer + * |*| |*| |*| |*| |*| |*| + * |*| |*| |*| |*| |*| |*| + */ + for (i = 1; i < 10; i += 2) { + if (munmap(&ptr[i * page_size], page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + } + + /* + * Shrink in-place across multiple VMAs and gaps so we end up with: + * + * 0 + * |*| + * |*| + */ + if (inplace) + res = mremap(ptr, size, page_size, 0); + else + res = mremap(ptr, size, page_size, MREMAP_MAYMOVE | MREMAP_FIXED, + tgt_ptr); + + if (res == MAP_FAILED) { + perror("mremap"); + success = false; + goto out_unmap; + } + +out_unmap: + if (munmap(tgt_ptr, size)) + perror("munmap tgt"); + if (munmap(ptr, size)) + perror("munmap src"); +out: + if (success) + ksft_test_result_pass("%s%s\n", test_name, + inplace ? " [inplace]" : ""); + else + ksft_test_result_fail("%s%s\n", test_name, + inplace ? " [inplace]" : ""); +} + +static void mremap_move_multiple_vmas_split(unsigned int pattern_seed, + unsigned long page_size, + bool dont_unmap) +{ + char *test_name = "mremap move multiple vmas split"; + int mremap_flags = MREMAP_FIXED | MREMAP_MAYMOVE; + const size_t size = 10 * page_size; + bool success = true; + char *ptr, *tgt_ptr; + int i; + + if (dont_unmap) + mremap_flags |= MREMAP_DONTUNMAP; + + ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, -1, 0); + if (ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out; + } + + tgt_ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, -1, 0); + if (tgt_ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out; + } + if (munmap(tgt_ptr, size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + + /* + * Unmap so we end up with: + * + * 0 1 2 3 4 5 6 7 8 9 10 offset in buffer + * |**********| |*******| + * |**********| |*******| + * 0 1 2 3 4 5 6 7 8 9 pattern offset + */ + if (munmap(&ptr[5 * page_size], page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + + /* Set up random patterns. */ + srand(pattern_seed); + for (i = 0; i < 10; i++) { + int j; + char *buf = &ptr[i * page_size]; + + if (i == 5) + continue; + + for (j = 0; j < page_size; j++) + buf[j] = rand(); + } + + /* + * Move the below: + * + * <-------------> + * 0 1 2 3 4 5 6 7 8 9 10 offset in buffer + * |**********| |*******| + * |**********| |*******| + * 0 1 2 3 4 5 6 7 8 9 pattern offset + * + * Into: + * + * 0 1 2 3 4 5 6 7 offset in buffer + * |*****| |*****| + * |*****| |*****| + * 2 3 4 5 6 7 pattern offset + */ + if (mremap(&ptr[2 * page_size], size - 3 * page_size, size - 3 * page_size, + mremap_flags, tgt_ptr) == MAP_FAILED) { + perror("mremap"); + success = false; + goto out_unmap; + } + + /* Offset into random pattern. */ + srand(pattern_seed); + for (i = 0; i < 2 * page_size; i++) + rand(); + + /* Check pattern. */ + for (i = 0; i < 7; i++) { + int j; + char *buf = &tgt_ptr[i * page_size]; + + if (i == 3) + continue; + + for (j = 0; j < page_size; j++) { + char chr = rand(); + + if (chr != buf[j]) { + ksft_print_msg("page %d offset %d corrupted, expected %d got %d\n", + i, j, chr, buf[j]); + goto out_unmap; + } + } + } + +out_unmap: + if (munmap(tgt_ptr, size)) + perror("munmap tgt"); + if (munmap(ptr, size)) + perror("munmap src"); +out: + if (success) + ksft_test_result_pass("%s%s\n", test_name, + dont_unmap ? " [dontunnmap]" : ""); + else + ksft_test_result_fail("%s%s\n", test_name, + dont_unmap ? " [dontunnmap]" : ""); } +#ifdef __NR_userfaultfd +static void mremap_move_multi_invalid_vmas(FILE *maps_fp, + unsigned long page_size) +{ + char *test_name = "mremap move multiple invalid vmas"; + const size_t size = 10 * page_size; + bool success = true; + char *ptr, *tgt_ptr; + int uffd, err, i; + void *res; + struct uffdio_api api = { + .api = UFFD_API, + .features = UFFD_EVENT_PAGEFAULT, + }; + + uffd = syscall(__NR_userfaultfd, O_NONBLOCK); + if (uffd == -1) { + err = errno; + perror("userfaultfd"); + if (err == EPERM) { + ksft_test_result_skip("%s - missing uffd", test_name); + return; + } + success = false; + goto out; + } + if (ioctl(uffd, UFFDIO_API, &api)) { + perror("ioctl UFFDIO_API"); + success = false; + goto out_close_uffd; + } + + ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, -1, 0); + if (ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_close_uffd; + } + + tgt_ptr = mmap(NULL, size, PROT_NONE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (tgt_ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_close_uffd; + } + if (munmap(tgt_ptr, size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + + /* + * Unmap so we end up with: + * + * 0 2 4 6 8 10 offset in buffer + * |*| |*| |*| |*| |*| + * |*| |*| |*| |*| |*| + * + * Additionally, register each with UFFD. + */ + for (i = 0; i < 10; i += 2) { + void *unmap_ptr = &ptr[(i + 1) * page_size]; + unsigned long start = (unsigned long)&ptr[i * page_size]; + struct uffdio_register reg = { + .range = { + .start = start, + .len = page_size, + }, + .mode = UFFDIO_REGISTER_MODE_MISSING, + }; + + if (ioctl(uffd, UFFDIO_REGISTER, ®) == -1) { + perror("ioctl UFFDIO_REGISTER"); + success = false; + goto out_unmap; + } + if (munmap(unmap_ptr, page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + } + + /* + * Now try to move the entire range which is invalid for multi VMA move. + * + * This will fail, and no VMA should be moved, as we check this ahead of + * time. + */ + res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + err = errno; + if (res != MAP_FAILED) { + fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n"); + success = false; + goto out_unmap; + } + if (err != EFAULT) { + errno = err; + perror("mremap() unexpected error"); + success = false; + goto out_unmap; + } + if (is_ptr_mapped(maps_fp, tgt_ptr, page_size)) { + fprintf(stderr, + "Invalid uffd-armed VMA at start of multi range moved\n"); + success = false; + goto out_unmap; + } + + /* + * Now try to move a single VMA, this should succeed as not multi VMA + * move. + */ + res = mremap(ptr, page_size, page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + if (res == MAP_FAILED) { + perror("mremap single invalid-multi VMA"); + success = false; + goto out_unmap; + } + + /* + * Unmap the VMA, and remap a non-uffd registered (therefore, multi VMA + * move valid) VMA at the start of ptr range. + */ + if (munmap(tgt_ptr, page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + res = mmap(ptr, page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + if (res == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_unmap; + } + + /* + * Now try to move the entire range, we should succeed in moving the + * first VMA, but no others, and report a failure. + */ + res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + err = errno; + if (res != MAP_FAILED) { + fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n"); + success = false; + goto out_unmap; + } + if (err != EFAULT) { + errno = err; + perror("mremap() unexpected error"); + success = false; + goto out_unmap; + } + if (!is_ptr_mapped(maps_fp, tgt_ptr, page_size)) { + fprintf(stderr, "Valid VMA not moved\n"); + success = false; + goto out_unmap; + } + + /* + * Unmap the VMA, and map valid VMA at start of ptr range, and replace + * all existing multi-move invalid VMAs, except the last, with valid + * multi-move VMAs. + */ + if (munmap(tgt_ptr, page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + if (munmap(ptr, size - 2 * page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + for (i = 0; i < 8; i += 2) { + res = mmap(&ptr[i * page_size], page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + if (res == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_unmap; + } + } + + /* + * Now try to move the entire range, we should succeed in moving all but + * the last VMA, and report a failure. + */ + res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + err = errno; + if (res != MAP_FAILED) { + fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n"); + success = false; + goto out_unmap; + } + if (err != EFAULT) { + errno = err; + perror("mremap() unexpected error"); + success = false; + goto out_unmap; + } + + for (i = 0; i < 10; i += 2) { + bool is_mapped = is_ptr_mapped(maps_fp, + &tgt_ptr[i * page_size], page_size); + + if (i < 8 && !is_mapped) { + fprintf(stderr, "Valid VMA not moved at %d\n", i); + success = false; + goto out_unmap; + } else if (i == 8 && is_mapped) { + fprintf(stderr, "Invalid VMA moved at %d\n", i); + success = false; + goto out_unmap; + } + } + +out_unmap: + if (munmap(tgt_ptr, size)) + perror("munmap tgt"); + if (munmap(ptr, size)) + perror("munmap src"); +out_close_uffd: + close(uffd); +out: + if (success) + ksft_test_result_pass("%s\n", test_name); + else + ksft_test_result_fail("%s\n", test_name); +} +#else +static void mremap_move_multi_invalid_vmas(FILE *maps_fp, unsigned long page_size) +{ + char *test_name = "mremap move multiple invalid vmas"; + + ksft_test_result_skip("%s - missing uffd", test_name); +} +#endif /* __NR_userfaultfd */ + /* Returns the time taken for the remap on success else returns -1. */ static long long remap_region(struct config c, unsigned int threshold_mb, - char pattern_seed) + char *rand_addr) { - void *addr, *src_addr, *dest_addr; - unsigned long long i; + void *addr, *tmp_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; unsigned long long threshold; + unsigned long num_chunks; if (threshold_mb == VALIDATION_NO_THRESHOLD) threshold = c.region_size; @@ -294,10 +1012,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb, goto out; } - /* Set byte pattern */ - srand(pattern_seed); - for (i = 0; i < threshold; i++) - memset((char *) src_addr + i, (char) rand(), 1); + /* Set byte pattern for source block. */ + memcpy(src_addr, rand_addr, threshold); /* Mask to zero out lower bits of address for alignment */ align_mask = ~(c.dest_alignment - 1); @@ -306,6 +1022,9 @@ static long long remap_region(struct config c, unsigned int threshold_mb, addr = (void *) (((unsigned long long) src_addr + c.region_size + offset) & align_mask); + /* Remap after the destination block preamble. */ + addr += c.dest_preamble_size; + /* See comment in get_source_mapping() */ if (!((unsigned long long) addr & c.dest_alignment)) addr = (void *) ((unsigned long long) addr | c.dest_alignment); @@ -313,14 +1032,31 @@ static long long remap_region(struct config c, unsigned int threshold_mb, /* Don't destroy existing mappings unless expected to overlap */ while (!is_remap_region_valid(addr, c.region_size) && !c.overlapping) { /* Check for unsigned overflow */ - if (addr + c.dest_alignment < addr) { + tmp_addr = addr + c.dest_alignment; + if (tmp_addr < addr) { ksft_print_msg("Couldn't find a valid region to remap to\n"); ret = -1; - goto out; + goto clean_up_src; } addr += c.dest_alignment; } + if (c.dest_preamble_size) { + dest_preamble_addr = mmap((void *) addr - c.dest_preamble_size, c.dest_preamble_size, + PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); + if (dest_preamble_addr == MAP_FAILED) { + ksft_print_msg("Failed to map dest preamble region: %s\n", + strerror(errno)); + ret = -1; + goto clean_up_src; + } + + /* Set byte pattern for the dest preamble block. */ + memcpy(dest_preamble_addr, rand_addr, c.dest_preamble_size); + } + clock_gettime(CLOCK_MONOTONIC, &t_start); dest_addr = mremap(src_addr, c.region_size, c.region_size, MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); @@ -329,24 +1065,90 @@ static long long remap_region(struct config c, unsigned int threshold_mb, if (dest_addr == MAP_FAILED) { ksft_print_msg("mremap failed: %s\n", strerror(errno)); ret = -1; - goto clean_up_src; + goto clean_up_dest_preamble; } - /* Verify byte pattern after remapping */ - srand(pattern_seed); - for (i = 0; i < threshold; i++) { - char c = (char) rand(); + /* + * Verify byte pattern after remapping. Employ an algorithm with a + * square root time complexity in threshold: divide the range into + * chunks, if memcmp() returns non-zero, only then perform an + * iteration in that chunk to find the mismatch index. + */ + num_chunks = get_sqrt(threshold); + for (unsigned long i = 0; i < num_chunks; ++i) { + size_t chunk_size = threshold / num_chunks; + unsigned long shift = i * chunk_size; + + if (!memcmp(dest_addr + shift, rand_addr + shift, chunk_size)) + continue; + + /* brute force iteration only over mismatch segment */ + for (t = shift; t < shift + chunk_size; ++t) { + if (((char *) dest_addr)[t] != rand_addr[t]) { + ksft_print_msg("Data after remap doesn't match at offset %llu\n", + t); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[t] & 0xff, + ((char *) dest_addr)[t] & 0xff); + ret = -1; + goto clean_up_dest; + } + } + } - if (((char *) dest_addr)[i] != c) { - ksft_print_msg("Data after remap doesn't match at offset %d\n", - i); - ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, - ((char *) dest_addr)[i] & 0xff); + /* + * if threshold is not divisible by num_chunks, then check the + * last chunk + */ + for (t = num_chunks * (threshold / num_chunks); t < threshold; ++t) { + if (((char *) dest_addr)[t] != rand_addr[t]) { + ksft_print_msg("Data after remap doesn't match at offset %llu\n", + t); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[t] & 0xff, + ((char *) dest_addr)[t] & 0xff); + ret = -1; + goto clean_up_dest; + } + } + + /* Verify the dest preamble byte pattern after remapping */ + if (!c.dest_preamble_size) + goto no_preamble; + + num_chunks = get_sqrt(c.dest_preamble_size); + + for (unsigned long i = 0; i < num_chunks; ++i) { + size_t chunk_size = c.dest_preamble_size / num_chunks; + unsigned long shift = i * chunk_size; + + if (!memcmp(dest_preamble_addr + shift, rand_addr + shift, + chunk_size)) + continue; + + /* brute force iteration only over mismatched segment */ + for (d = shift; d < shift + chunk_size; ++d) { + if (((char *) dest_preamble_addr)[d] != rand_addr[d]) { + ksft_print_msg("Preamble data after remap doesn't match at offset %llu\n", + d); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[d] & 0xff, + ((char *) dest_preamble_addr)[d] & 0xff); + ret = -1; + goto clean_up_dest; + } + } + } + + for (d = num_chunks * (c.dest_preamble_size / num_chunks); d < c.dest_preamble_size; ++d) { + if (((char *) dest_preamble_addr)[d] != rand_addr[d]) { + ksft_print_msg("Preamble data after remap doesn't match at offset %llu\n", + d); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[d] & 0xff, + ((char *) dest_preamble_addr)[d] & 0xff); ret = -1; goto clean_up_dest; } } +no_preamble: start_ns = t_start.tv_sec * NS_PER_SEC + t_start.tv_nsec; end_ns = t_end.tv_sec * NS_PER_SEC + t_end.tv_nsec; ret = end_ns - start_ns; @@ -359,18 +1161,96 @@ static long long remap_region(struct config c, unsigned int threshold_mb, */ clean_up_dest: munmap(dest_addr, c.region_size); +clean_up_dest_preamble: + if (c.dest_preamble_size && dest_preamble_addr) + munmap(dest_preamble_addr, c.dest_preamble_size); clean_up_src: munmap(src_addr, c.region_size); out: return ret; } +/* + * Verify that an mremap aligning down does not destroy + * the beginning of the mapping just because the aligned + * down address landed on a mapping that maybe does not exist. + */ +static void mremap_move_1mb_from_start(unsigned int pattern_seed, + char *rand_addr) +{ + char *test_name = "mremap move 1mb from start at 1MB+256KB aligned src"; + void *src = NULL, *dest = NULL; + unsigned int i, success = 1; + + /* Config to reuse get_source_mapping() to do an aligned mmap. */ + struct config c = { + .src_alignment = SIZE_MB(1) + SIZE_KB(256), + .region_size = SIZE_MB(6) + }; + + src = get_source_mapping(c); + if (!src) { + success = 0; + goto out; + } + + c.src_alignment = SIZE_MB(1) + SIZE_KB(256); + dest = get_source_mapping(c); + if (!dest) { + success = 0; + goto out; + } + + /* Set byte pattern for source block. */ + memcpy(src, rand_addr, SIZE_MB(2)); + + /* + * Unmap the beginning of dest so that the aligned address + * falls on no mapping. + */ + munmap(dest, SIZE_MB(1)); + + void *new_ptr = mremap(src + SIZE_MB(1), SIZE_MB(1), SIZE_MB(1), + MREMAP_MAYMOVE | MREMAP_FIXED, dest + SIZE_MB(1)); + if (new_ptr == MAP_FAILED) { + perror("mremap"); + success = 0; + goto out; + } + + /* Verify byte pattern after remapping */ + srand(pattern_seed); + for (i = 0; i < SIZE_MB(1); i++) { + char c = (char) rand(); + + if (((char *)src)[i] != c) { + ksft_print_msg("Data at src at %d got corrupted due to unrelated mremap\n", + i); + ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, + ((char *) src)[i] & 0xff); + success = 0; + } + } + +out: + if (src && munmap(src, c.region_size) == -1) + perror("munmap src"); + + if (dest && munmap(dest, c.region_size) == -1) + perror("munmap dest"); + + if (success) + ksft_test_result_pass("%s\n", test_name); + else + ksft_test_result_fail("%s\n", test_name); +} + static void run_mremap_test_case(struct test test_case, int *failures, unsigned int threshold_mb, - unsigned int pattern_seed) + char *rand_addr) { long long remap_time = remap_region(test_case.config, threshold_mb, - pattern_seed); + rand_addr); if (remap_time < 0) { if (test_case.expect_failure) @@ -434,16 +1314,26 @@ static int parse_args(int argc, char **argv, unsigned int *threshold_mb, return 0; } -#define MAX_TEST 13 +#define MAX_TEST 15 #define MAX_PERF_TEST 3 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 */ + size_t max_test_variable_region_size = _2GB; + size_t max_test_constant_region_size = _2MB; + size_t dest_preamble_size = 10 * _4MB; + unsigned int pattern_seed; + char *rand_addr; + size_t rand_size; int num_expand_tests = 2; - struct test test_cases[MAX_TEST]; + int num_misc_tests = 9; + struct test test_cases[MAX_TEST] = {}; struct test perf_test_cases[MAX_PERF_TEST]; int page_size; time_t t; @@ -457,6 +1347,31 @@ int main(int argc, char **argv) ksft_print_msg("Test configs:\n\tthreshold_mb=%u\n\tpattern_seed=%u\n\n", threshold_mb, pattern_seed); + /* + * set preallocated random array according to test configs; see the + * functions for the logic of setting the size + */ + if (!threshold_mb) + rand_size = MAX(max_test_variable_region_size, + max_test_constant_region_size); + else + rand_size = MAX(MIN(threshold_mb * _1MB, + max_test_variable_region_size), + max_test_constant_region_size); + rand_size = MAX(dest_preamble_size, rand_size); + + rand_addr = (char *)mmap(NULL, rand_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (rand_addr == MAP_FAILED) { + perror("mmap"); + ksft_exit_fail_msg("cannot mmap rand_addr\n"); + } + + /* fill stream of random bytes */ + srand(pattern_seed); + for (unsigned long i = 0; i < rand_size; ++i) + rand_addr[i] = (char) rand(); + page_size = sysconf(_SC_PAGESIZE); /* Expected mremap failures */ @@ -500,6 +1415,15 @@ int main(int argc, char **argv) test_cases[12] = MAKE_TEST(PUD, PUD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS, "2GB mremap - Source PUD-aligned, Destination PUD-aligned"); + /* Src and Dest addr 1MB aligned. 5MB mremap. */ + test_cases[13] = MAKE_TEST(_1MB, _1MB, _5MB, NON_OVERLAPPING, EXPECT_SUCCESS, + "5MB mremap - Source 1MB-aligned, Destination 1MB-aligned"); + + /* Src and Dest addr 1MB aligned. 5MB mremap. */ + test_cases[14] = MAKE_TEST(_1MB, _1MB, _5MB, NON_OVERLAPPING, EXPECT_SUCCESS, + "5MB mremap - Source 1MB-aligned, Dest 1MB-aligned with 40MB Preamble"); + test_cases[14].config.dest_preamble_size = 10 * _4MB; + perf_test_cases[0] = MAKE_TEST(page_size, page_size, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS, "1GB mremap - Source PTE-aligned, Destination PTE-aligned"); /* @@ -515,22 +1439,32 @@ int main(int argc, char **argv) (threshold_mb * _1MB >= _1GB); ksft_set_plan(ARRAY_SIZE(test_cases) + (run_perf_tests ? - ARRAY_SIZE(perf_test_cases) : 0) + num_expand_tests); + ARRAY_SIZE(perf_test_cases) : 0) + num_expand_tests + num_misc_tests); for (i = 0; i < ARRAY_SIZE(test_cases); i++) run_mremap_test_case(test_cases[i], &failures, threshold_mb, - pattern_seed); + rand_addr); maps_fp = fopen("/proc/self/maps", "r"); if (maps_fp == NULL) { - ksft_print_msg("Failed to read /proc/self/maps: %s\n", strerror(errno)); - exit(KSFT_FAIL); + munmap(rand_addr, rand_size); + ksft_exit_fail_msg("Failed to read /proc/self/maps: %s\n", strerror(errno)); } mremap_expand_merge(maps_fp, page_size); mremap_expand_merge_offset(maps_fp, page_size); + mremap_move_within_range(pattern_seed, rand_addr); + mremap_move_1mb_from_start(pattern_seed, rand_addr); + mremap_shrink_multiple_vmas(page_size, /* inplace= */true); + mremap_shrink_multiple_vmas(page_size, /* inplace= */false); + mremap_move_multiple_vmas(pattern_seed, page_size, /* dontunmap= */ false); + mremap_move_multiple_vmas(pattern_seed, page_size, /* dontunmap= */ true); + mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ false); + mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ true); + mremap_move_multi_invalid_vmas(maps_fp, page_size); + fclose(maps_fp); if (run_perf_tests) { @@ -538,9 +1472,12 @@ 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); } + munmap(rand_addr, rand_size); + if (failures > 0) ksft_exit_fail(); else diff --git a/tools/testing/selftests/mm/mseal_helpers.h b/tools/testing/selftests/mm/mseal_helpers.h new file mode 100644 index 000000000000..0cfce31c76d2 --- /dev/null +++ b/tools/testing/selftests/mm/mseal_helpers.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#define FAIL_TEST_IF_FALSE(test_passed) \ + do { \ + if (!(test_passed)) { \ + ksft_test_result_fail("%s: line:%d\n", \ + __func__, __LINE__); \ + return; \ + } \ + } while (0) + +#define SKIP_TEST_IF_FALSE(test_passed) \ + do { \ + if (!(test_passed)) { \ + ksft_test_result_skip("%s: line:%d\n", \ + __func__, __LINE__); \ + return; \ + } \ + } while (0) + +#define REPORT_TEST_PASS() ksft_test_result_pass("%s\n", __func__) + +#ifndef PKEY_DISABLE_ACCESS +#define PKEY_DISABLE_ACCESS 0x1 +#endif + +#ifndef PKEY_DISABLE_WRITE +#define PKEY_DISABLE_WRITE 0x2 +#endif + +#ifndef PKEY_BITS_PER_PKEY +#define PKEY_BITS_PER_PKEY 2 +#endif + +#ifndef PKEY_MASK +#define PKEY_MASK (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE) +#endif + +#ifndef u64 +#define u64 unsigned long long +#endif diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c new file mode 100644 index 000000000000..faad4833366a --- /dev/null +++ b/tools/testing/selftests/mm/mseal_test.c @@ -0,0 +1,1989 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <linux/mman.h> +#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" + +static unsigned long get_vma_size(void *addr, int *prot) +{ + FILE *maps; + char line[256]; + int size = 0; + uintptr_t addr_start, addr_end; + char protstr[5]; + *prot = 0; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) + return 0; + + while (fgets(line, sizeof(line), maps)) { + if (sscanf(line, "%lx-%lx %4s", &addr_start, &addr_end, protstr) == 3) { + if (addr_start == (uintptr_t) addr) { + size = addr_end - addr_start; + if (protstr[0] == 'r') + *prot |= 0x4; + if (protstr[1] == 'w') + *prot |= 0x2; + if (protstr[2] == 'x') + *prot |= 0x1; + break; + } + } + } + fclose(maps); + return size; +} + +/* + * 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 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 int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey) +{ + int sret; + + errno = 0; + sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); + return sret; +} + +static int sys_munmap(void *ptr, size_t size) +{ + int sret; + + errno = 0; + sret = syscall(__NR_munmap, ptr, size); + return sret; +} + +static int sys_madvise(void *start, size_t len, int types) +{ + int sret; + + errno = 0; + sret = syscall(__NR_madvise, start, len, types); + return sret; +} + +static void *sys_mremap(void *addr, size_t old_len, size_t new_len, + unsigned long flags, void *new_addr) +{ + void *sret; + + errno = 0; + sret = (void *) syscall(__NR_mremap, addr, old_len, new_len, flags, new_addr); + return sret; +} + +static int sys_pkey_alloc(unsigned long flags, unsigned long init_val) +{ + int ret = syscall(__NR_pkey_alloc, flags, init_val); + + return ret; +} + +static unsigned int __read_pkey_reg(void) +{ + unsigned int pkey_reg = 0; +#if defined(__i386__) || defined(__x86_64__) /* arch */ + unsigned int eax, edx; + unsigned int ecx = 0; + + asm volatile(".byte 0x0f,0x01,0xee\n\t" + : "=a" (eax), "=d" (edx) + : "c" (ecx)); + pkey_reg = eax; +#endif + return pkey_reg; +} + +static void __write_pkey_reg(u64 pkey_reg) +{ +#if defined(__i386__) || defined(__x86_64__) /* arch */ + unsigned int eax = pkey_reg; + unsigned int ecx = 0; + unsigned int edx = 0; + + asm volatile(".byte 0x0f,0x01,0xef\n\t" + : : "a" (eax), "c" (ecx), "d" (edx)); +#endif +} + +static unsigned long pkey_bit_position(int pkey) +{ + return pkey * PKEY_BITS_PER_PKEY; +} + +static u64 set_pkey_bits(u64 reg, int pkey, u64 flags) +{ + unsigned long shift = pkey_bit_position(pkey); + + /* mask out bits from pkey in old value */ + reg &= ~((u64)PKEY_MASK << shift); + /* OR in new bits for pkey */ + reg |= (flags & PKEY_MASK) << shift; + return reg; +} + +static void set_pkey(int pkey, unsigned long pkey_value) +{ + u64 new_pkey_reg; + + new_pkey_reg = set_pkey_bits(__read_pkey_reg(), pkey, pkey_value); + __write_pkey_reg(new_pkey_reg); +} + +static void setup_single_address(int size, void **ptrOut) +{ + void *ptr; + + ptr = mmap(NULL, size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + *ptrOut = ptr; +} + +static void setup_single_address_rw(int size, void **ptrOut) +{ + void *ptr; + unsigned long mapflags = MAP_ANONYMOUS | MAP_PRIVATE; + + ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, mapflags, -1, 0); + *ptrOut = ptr; +} + +static int clean_single_address(void *ptr, int size) +{ + int ret; + ret = munmap(ptr, size); + return ret; +} + +static int seal_single_address(void *ptr, int size) +{ + int ret; + ret = sys_mseal(ptr, size); + return ret; +} + +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; +} + +bool pkey_supported(void) +{ +#if defined(__i386__) || defined(__x86_64__) /* arch */ + int pkey = sys_pkey_alloc(0, PKEY_UNRESTRICTED); + + if (pkey > 0) + return true; +#endif + return false; +} + +static void test_seal_addseal(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_unmapped_start(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* munmap 2 pages from ptr. */ + ret = sys_munmap(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail because 2 pages from ptr are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail because 2 pages from ptr are unmapped. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + ret = sys_mseal(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_unmapped_middle(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* munmap 2 pages from ptr + page. */ + ret = sys_munmap(ptr + page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail, since middle 2 pages are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* we still can add seal to the first page and last page*/ + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mseal(ptr + 3 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_unmapped_end(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap last 2 pages. */ + ret = sys_munmap(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail since last 2 pages are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* The first 2 pages is not sealed, and can add seals */ + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_multiple_vmas(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split the vma into 3. */ + ret = sys_mprotect(ptr + page_size, 2 * page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will get applied to all 4 pages - 3 VMAs. */ + ret = sys_mprotect(ptr, size, PROT_READ); + FAIL_TEST_IF_FALSE(!ret); + + /* use mprotect to split the vma into 3. */ + ret = sys_mprotect(ptr + page_size, 2 * page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mseal get applied to all 4 pages - 3 VMAs. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_split_start(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split at middle */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first page, this will split the VMA */ + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* add seal to the remain 3 pages */ + ret = sys_mseal(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_split_end(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split at middle */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the last page */ + ret = sys_mseal(ptr + 3 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* Adding seals to the first 3 pages */ + ret = sys_mseal(ptr, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_invalid_input(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(8 * page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + ret = clean_single_address(ptr + 4 * page_size, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* invalid flag */ + ret = syscall(__NR_mseal, ptr, size, 0x20); + FAIL_TEST_IF_FALSE(ret < 0); + + /* unaligned address */ + ret = sys_mseal(ptr + 1, 2 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* length too big */ + ret = sys_mseal(ptr, 5 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* length overflow */ + ret = sys_mseal(ptr, UINT64_MAX/page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* start is not in a valid VMA */ + ret = sys_mseal(ptr - page_size, 5 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + REPORT_TEST_PASS(); +} + +static void test_seal_zero_length(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mprotect(ptr, 0, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal 0 length will be OK, same as mprotect */ + ret = sys_mseal(ptr, 0); + FAIL_TEST_IF_FALSE(!ret); + + /* verify the 4 pages are not sealed by previous call. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_zero_address(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + /* use mmap to change protection. */ + ptr = mmap(0, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + FAIL_TEST_IF_FALSE(ptr == 0); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + /* verify the 4 pages are sealed by previous call. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_twice(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + /* apply the same seal will be OK. idempotent. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_start_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* the first page is sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* pages after the first page is not sealed. */ + ret = sys_mprotect(ptr + page_size, page_size * 3, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_end_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* first page is not sealed */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* last 3 page are sealed */ + ret = sys_mprotect(ptr + page_size, page_size * 3, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_mprotect_unalign_len(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, page_size * 2 - 1); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 2 pages are sealed. */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 2, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_mprotect_unalign_len_variant_2(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + if (seal) { + ret = seal_single_address(ptr, page_size * 2 + 1); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 3 pages are sealed. */ + ret = sys_mprotect(ptr, page_size * 3, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 3, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_mprotect_two_vma(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = seal_single_address(ptr, page_size * 4); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 2, page_size * 2, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_mprotect_two_vma_with_split(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split as two vma. */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mseal can apply across 2 vma, also split them. */ + if (seal) { + ret = seal_single_address(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + } + + /* the first page is not sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* the second page is sealed. */ + ret = sys_mprotect(ptr + page_size, page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* the third page is sealed. */ + ret = sys_mprotect(ptr + 2 * page_size, page_size, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* the fouth page is not sealed. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_mprotect_partial_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* seal one page. */ + if (seal) { + ret = seal_single_address(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mprotect first 2 page will fail, since the first page are sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_mprotect_partial_mprotect_tail(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 2 * page_size; + int ret; + int prot; + + /* + * Check if a partial mseal (that results in two vmas) works correctly. + * It might mprotect the first, but it'll never touch the second (msealed) vma. + */ + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr + page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_mprotect(ptr, size, PROT_EXEC); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + FAIL_TEST_IF_FALSE(get_vma_size(ptr + page_size, &prot) > 0); + FAIL_TEST_IF_FALSE(prot == 0x4); + } + + REPORT_TEST_PASS(); +} + + +static void test_seal_mprotect_two_vma_with_gap(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* use munmap to free two pages in the middle */ + ret = sys_munmap(ptr + page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail, because there is a gap in the address. */ + /* notes, internally mprotect still updated the first page. */ + ret = sys_mprotect(ptr, 4 * page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, 4 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* the first page is not sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + /* the last page is not sealed. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + REPORT_TEST_PASS(); +} + +static void test_seal_mprotect_split(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal all 4 pages. */ + if (seal) { + ret = sys_mseal(ptr, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mprotect is sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + + ret = sys_mprotect(ptr + 2 * page_size, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_mprotect_merge(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split one page. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal first two pages. */ + if (seal) { + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 2 pages are sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* last 2 pages are not sealed. */ + ret = sys_mprotect(ptr + 2 * page_size, 2 * page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + REPORT_TEST_PASS(); +} + +static void test_seal_munmap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 4 pages are sealed. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +/* + * allocate 4 pages, + * use mprotect to split it as two VMAs + * seal the whole range + * munmap will fail on both + */ +static void test_seal_munmap_two_vma(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_munmap(ptr, page_size * 2); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr + page_size, page_size * 2); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +/* + * allocate a VMA with 4 pages. + * munmap the middle 2 pages. + * seal the whole 4 pages, will fail. + * munmap the first page will be OK. + * munmap the last page will be OK. + */ +static void test_seal_munmap_vma_with_gap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_munmap(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + /* can't have gap in the middle. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + } + + ret = sys_munmap(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr + page_size * 2, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_munmap_partial_across_vmas(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 2 * page_size; + int ret; + int prot; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr + page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + FAIL_TEST_IF_FALSE(get_vma_size(ptr + page_size, &prot) > 0); + FAIL_TEST_IF_FALSE(prot == 0x4); + } + + REPORT_TEST_PASS(); +} + +static void test_munmap_start_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap the first page. */ + ret = sys_munmap(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the last 3 pages. */ + if (seal) { + ret = sys_mseal(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* unmap from the first page. */ + ret = sys_munmap(ptr, size); + if (seal) { + FAIL_TEST_IF_FALSE(ret < 0); + + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size * 3); + } else { + /* note: this will be OK, even the first page is */ + /* already unmapped. */ + FAIL_TEST_IF_FALSE(!ret); + + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 0); + } + + REPORT_TEST_PASS(); +} + +static void test_munmap_end_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap last page. */ + ret = sys_munmap(ptr + page_size * 3, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first 3 pages. */ + if (seal) { + ret = sys_mseal(ptr, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* unmap all pages. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_munmap_middle_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap 2 pages in the middle. */ + ret = sys_munmap(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first page. */ + if (seal) { + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* munmap all 4 pages. */ + ret = sys_munmap(ptr, size); + if (seal) { + FAIL_TEST_IF_FALSE(ret < 0); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + + size = get_vma_size(ptr + page_size * 3, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + } else { + FAIL_TEST_IF_FALSE(!ret); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == 0); + + size = get_vma_size(ptr + page_size * 3, &prot); + FAIL_TEST_IF_FALSE(size == 0); + } + + REPORT_TEST_PASS(); +} + +static void test_seal_mremap_shrink(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* shrink from 4 pages to 2 pages. */ + ret2 = sys_mremap(ptr, size, 2 * page_size, 0, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == (void *) MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != (void *) MAP_FAILED); + + } + + REPORT_TEST_PASS(); +} + +static void test_seal_mremap_expand(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + /* ummap last 2 pages. */ + ret = sys_munmap(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* expand from 2 page to 4 pages. */ + ret2 = sys_mremap(ptr, 2 * page_size, 4 * page_size, 0, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 == ptr); + + } + + REPORT_TEST_PASS(); +} + +static void test_seal_mremap_move(bool seal) +{ + void *ptr, *newPtr; + unsigned long page_size = getpagesize(); + unsigned long size = page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newPtr); + FAIL_TEST_IF_FALSE(newPtr != (void *)-1); + ret = clean_single_address(newPtr, size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* move from ptr to fixed address. */ + ret2 = sys_mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newPtr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + + } + + REPORT_TEST_PASS(); +} + +static void test_seal_mmap_overwrite_prot(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to change protection. */ + ret2 = mmap(ptr, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + REPORT_TEST_PASS(); +} + +static void test_seal_mmap_expand(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 12 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + /* ummap last 4 pages. */ + ret = sys_munmap(ptr + 8 * page_size, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, 8 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to expand. */ + ret2 = mmap(ptr, size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + REPORT_TEST_PASS(); +} + +static void test_seal_mmap_shrink(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 12 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to shrink. */ + ret2 = mmap(ptr, 8 * page_size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + REPORT_TEST_PASS(); +} + +static void test_seal_mremap_shrink_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move and shrink to fixed address */ + ret2 = sys_mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, + newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + REPORT_TEST_PASS(); +} + +static void test_seal_mremap_expand_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(newAddr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move and expand to fixed address */ + ret2 = sys_mremap(ptr, page_size, size, MREMAP_MAYMOVE | MREMAP_FIXED, + newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + REPORT_TEST_PASS(); +} + +static void test_seal_mremap_move_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(newAddr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move to fixed address */ + ret2 = sys_mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + REPORT_TEST_PASS(); +} + +static void test_seal_mremap_move_fixed_zero(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* + * MREMAP_FIXED can move the mapping to zero address + */ + ret2 = sys_mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, + 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 == 0); + } + + REPORT_TEST_PASS(); +} + +static void test_seal_mremap_move_dontunmap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move, and don't unmap src addr. */ + ret2 = sys_mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + /* kernel will allocate a new address */ + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + } + + REPORT_TEST_PASS(); +} + +static void test_seal_mremap_move_dontunmap_anyaddr(bool seal) +{ + void *ptr, *ptr2; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* + * The new address is any address that not allocated. + * use allocate/free to similate that. + */ + setup_single_address(size, &ptr2); + FAIL_TEST_IF_FALSE(ptr2 != (void *)-1); + ret = sys_munmap(ptr2, size); + FAIL_TEST_IF_FALSE(!ret); + + /* + * remap to any address. + */ + ret2 = sys_mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + (void *) ptr2); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + /* remap success and return ptr2 */ + FAIL_TEST_IF_FALSE(ret2 == ptr2); + } + + REPORT_TEST_PASS(); +} + +static void test_seal_merge_and_split(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size; + int ret; + int prot; + + /* (24 RO) */ + setup_single_address(24 * page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect(NONE) to set out boundary */ + /* (1 NONE) (22 RO) (1 NONE) */ + ret = sys_mprotect(ptr, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(!ret); + ret = sys_mprotect(ptr + 23 * page_size, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 22 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + + /* use mseal to split from beginning */ + /* (1 NONE) (1 RO_SEAL) (21 RO) (1 NONE) */ + ret = sys_mseal(ptr + page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 2 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 21 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* use mseal to split from the end. */ + /* (1 NONE) (1 RO_SEAL) (20 RO) (1 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 22 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 22 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 2 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 20 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge with prev. */ + /* (1 NONE) (2 RO_SEAL) (19 RO) (1 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 2 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge with after. */ + /* (1 NONE) (2 RO_SEAL) (18 RO) (2 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 21 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 21 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 2 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* split and merge from prev */ + /* (1 NONE) (3 RO_SEAL) (17 RO) (2 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 1 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 3 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + ret = sys_munmap(ptr + page_size, page_size); + FAIL_TEST_IF_FALSE(ret < 0); + ret = sys_mprotect(ptr + 2 * page_size, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* split and merge from next */ + /* (1 NONE) (3 RO_SEAL) (16 RO) (3 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 20 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 20 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 3 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge from middle of prev and middle of next. */ + /* (1 NONE) (22 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, 20 * page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 22 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + REPORT_TEST_PASS(); +} + +static void test_seal_discard_ro_anon_on_rw(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address_rw(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't take effect on RW memory. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + /* base seal still apply. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_discard_ro_anon_on_pkey(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int pkey; + + SKIP_TEST_IF_FALSE(pkey_supported()); + + setup_single_address_rw(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + pkey = sys_pkey_alloc(0, PKEY_UNRESTRICTED); + FAIL_TEST_IF_FALSE(pkey > 0); + + ret = sys_mprotect_pkey((void *)ptr, size, PROT_READ | PROT_WRITE, pkey); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't take effect if PKRU allow write. */ + set_pkey(pkey, PKEY_UNRESTRICTED); + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + /* sealing will take effect if PKRU deny write. */ + set_pkey(pkey, PKEY_DISABLE_WRITE); + ret = sys_madvise(ptr, size, MADV_DONTNEED); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* base seal still apply. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_discard_ro_anon_on_filebacked(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int fd; + unsigned long mapflags = MAP_PRIVATE; + + fd = memfd_create("test", 0); + FAIL_TEST_IF_FALSE(fd > 0); + + ret = fallocate(fd, 0, 0, size); + FAIL_TEST_IF_FALSE(!ret); + + ptr = mmap(NULL, size, PROT_READ, mapflags, fd, 0); + FAIL_TEST_IF_FALSE(ptr != MAP_FAILED); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't apply for file backed mapping. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + close(fd); + + REPORT_TEST_PASS(); +} + +static void test_seal_discard_ro_anon_on_shared(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + unsigned long mapflags = MAP_ANONYMOUS | MAP_SHARED; + + ptr = mmap(NULL, size, PROT_READ, mapflags, -1, 0); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't apply for shared mapping. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_discard_ro_anon(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_madvise(ptr, size, MADV_DONTNEED); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +static void test_seal_discard_across_vmas(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 2 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr + page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_madvise(ptr, size, MADV_DONTNEED); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + + +static void test_seal_madvise_nodiscard(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* + * Test a random madvise flag like MADV_RANDOM that does not touch page + * contents (and thus should work for msealed VMAs). RANDOM also happens to + * share bits with other discard-ish flags like REMOVE. + */ + ret = sys_madvise(ptr, size, MADV_RANDOM); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + +int main(void) +{ + bool test_seal = seal_support(); + + ksft_print_header(); + + if (!test_seal) + ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); + + if (!pkey_supported()) + ksft_print_msg("PKEY not supported\n"); + + ksft_set_plan(88); + + test_seal_addseal(); + test_seal_unmapped_start(); + test_seal_unmapped_middle(); + test_seal_unmapped_end(); + test_seal_multiple_vmas(); + test_seal_split_start(); + test_seal_split_end(); + test_seal_invalid_input(); + test_seal_zero_length(); + test_seal_twice(); + + test_seal_mprotect(false); + test_seal_mprotect(true); + + test_seal_start_mprotect(false); + test_seal_start_mprotect(true); + + test_seal_end_mprotect(false); + test_seal_end_mprotect(true); + + test_seal_mprotect_unalign_len(false); + test_seal_mprotect_unalign_len(true); + + test_seal_mprotect_unalign_len_variant_2(false); + test_seal_mprotect_unalign_len_variant_2(true); + + test_seal_mprotect_two_vma(false); + test_seal_mprotect_two_vma(true); + + test_seal_mprotect_two_vma_with_split(false); + test_seal_mprotect_two_vma_with_split(true); + + test_seal_mprotect_partial_mprotect(false); + test_seal_mprotect_partial_mprotect(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); + + test_seal_mprotect_split(false); + test_seal_mprotect_split(true); + + test_seal_mprotect_partial_mprotect_tail(false); + test_seal_mprotect_partial_mprotect_tail(true); + + test_seal_munmap(false); + test_seal_munmap(true); + test_seal_munmap_two_vma(false); + test_seal_munmap_two_vma(true); + test_seal_munmap_vma_with_gap(false); + test_seal_munmap_vma_with_gap(true); + test_seal_munmap_partial_across_vmas(false); + test_seal_munmap_partial_across_vmas(true); + + test_munmap_start_freed(false); + test_munmap_start_freed(true); + test_munmap_middle_freed(false); + test_munmap_middle_freed(true); + test_munmap_end_freed(false); + test_munmap_end_freed(true); + + test_seal_mremap_shrink(false); + test_seal_mremap_shrink(true); + test_seal_mremap_expand(false); + test_seal_mremap_expand(true); + test_seal_mremap_move(false); + test_seal_mremap_move(true); + + test_seal_mremap_shrink_fixed(false); + test_seal_mremap_shrink_fixed(true); + test_seal_mremap_expand_fixed(false); + test_seal_mremap_expand_fixed(true); + test_seal_mremap_move_fixed(false); + test_seal_mremap_move_fixed(true); + test_seal_mremap_move_dontunmap(false); + test_seal_mremap_move_dontunmap(true); + test_seal_mremap_move_fixed_zero(false); + test_seal_mremap_move_fixed_zero(true); + test_seal_mremap_move_dontunmap_anyaddr(false); + test_seal_mremap_move_dontunmap_anyaddr(true); + test_seal_madvise_nodiscard(false); + test_seal_madvise_nodiscard(true); + test_seal_discard_ro_anon(false); + test_seal_discard_ro_anon(true); + test_seal_discard_across_vmas(false); + test_seal_discard_across_vmas(true); + test_seal_discard_ro_anon_on_rw(false); + test_seal_discard_ro_anon_on_rw(true); + test_seal_discard_ro_anon_on_shared(false); + test_seal_discard_ro_anon_on_shared(true); + test_seal_discard_ro_anon_on_filebacked(false); + test_seal_discard_ro_anon_on_filebacked(true); + test_seal_mmap_overwrite_prot(false); + test_seal_mmap_overwrite_prot(true); + test_seal_mmap_expand(false); + test_seal_mmap_expand(true); + test_seal_mmap_shrink(false); + test_seal_mmap_shrink(true); + + test_seal_merge_and_split(); + test_seal_zero_address(); + + test_seal_discard_ro_anon_on_pkey(false); + test_seal_discard_ro_anon_on_pkey(true); + + ksft_finished(); +} diff --git a/tools/testing/selftests/mm/on-fault-limit.c b/tools/testing/selftests/mm/on-fault-limit.c index b5888d613f34..fc4117453c84 100644 --- a/tools/testing/selftests/mm/on-fault-limit.c +++ b/tools/testing/selftests/mm/on-fault-limit.c @@ -5,40 +5,38 @@ #include <string.h> #include <sys/time.h> #include <sys/resource.h> +#include "kselftest.h" -static int test_limit(void) +static void test_limit(void) { - int ret = 1; struct rlimit lims; void *map; - if (getrlimit(RLIMIT_MEMLOCK, &lims)) { - perror("getrlimit"); - return ret; - } + if (getrlimit(RLIMIT_MEMLOCK, &lims)) + ksft_exit_fail_msg("getrlimit: %s\n", strerror(errno)); - if (mlockall(MCL_ONFAULT | MCL_FUTURE)) { - perror("mlockall"); - return ret; - } + if (mlockall(MCL_ONFAULT | MCL_FUTURE)) + ksft_exit_fail_msg("mlockall: %s\n", strerror(errno)); map = mmap(NULL, 2 * lims.rlim_max, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, -1, 0); + + ksft_test_result(map == MAP_FAILED, "The map failed respecting mlock limits\n"); + if (map != MAP_FAILED) - printf("mmap should have failed, but didn't\n"); - else { - ret = 0; munmap(map, 2 * lims.rlim_max); - } - munlockall(); - return ret; } int main(int argc, char **argv) { - int ret = 0; + ksft_print_header(); + ksft_set_plan(1); + + if (!getuid()) + ksft_test_result_skip("The test must be run from a normal user\n"); + else + test_limit(); - ret += test_limit(); - return ret; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile new file mode 100644 index 000000000000..8c8bb39ffa28 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/Makefile @@ -0,0 +1,18 @@ +PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= /lib/modules/$(shell uname -r)/build + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = page_frag_test.ko + +obj-m += page_frag_test.o + +all: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) clean diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c new file mode 100644 index 000000000000..e806c1866e36 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Test module for page_frag cache + * + * Copyright (C) 2024 Yunsheng Lin <linyunsheng@huawei.com> + */ + +#include <linux/module.h> +#include <linux/cpumask.h> +#include <linux/completion.h> +#include <linux/ptr_ring.h> +#include <linux/kthread.h> +#include <linux/page_frag_cache.h> + +#define TEST_FAILED_PREFIX "page_frag_test failed: " + +static struct ptr_ring ptr_ring; +static int nr_objs = 512; +static atomic_t nthreads; +static struct completion wait; +static struct page_frag_cache test_nc; +static int test_popped; +static int test_pushed; +static bool force_exit; + +static int nr_test = 2000000; +module_param(nr_test, int, 0); +MODULE_PARM_DESC(nr_test, "number of iterations to test"); + +static bool test_align; +module_param(test_align, bool, 0); +MODULE_PARM_DESC(test_align, "use align API for testing"); + +static int test_alloc_len = 2048; +module_param(test_alloc_len, int, 0); +MODULE_PARM_DESC(test_alloc_len, "alloc len for testing"); + +static int test_push_cpu; +module_param(test_push_cpu, int, 0); +MODULE_PARM_DESC(test_push_cpu, "test cpu for pushing fragment"); + +static int test_pop_cpu; +module_param(test_pop_cpu, int, 0); +MODULE_PARM_DESC(test_pop_cpu, "test cpu for popping fragment"); + +static int page_frag_pop_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_frag pop test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_popped < nr_test) { + void *obj = __ptr_ring_consume(ring); + + if (obj) { + test_popped++; + page_frag_free(obj); + } else { + if (force_exit) + break; + + cond_resched(); + } + } + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + pr_info("page_frag pop test thread exits on cpu %d\n", + smp_processor_id()); + + return 0; +} + +static int page_frag_push_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_frag push test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_pushed < nr_test && !force_exit) { + void *va; + int ret; + + if (test_align) { + va = page_frag_alloc_align(&test_nc, test_alloc_len, + GFP_KERNEL, SMP_CACHE_BYTES); + + if ((unsigned long)va & (SMP_CACHE_BYTES - 1)) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "unaligned va returned\n"); + } + } else { + va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + } + + if (!va) + continue; + + ret = __ptr_ring_produce(ring, va); + if (ret) { + page_frag_free(va); + cond_resched(); + } else { + test_pushed++; + } + } + + pr_info("page_frag push test thread exits on cpu %d\n", + smp_processor_id()); + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + return 0; +} + +static int __init page_frag_test_init(void) +{ + struct task_struct *tsk_push, *tsk_pop; + int last_pushed = 0, last_popped = 0; + ktime_t start; + u64 duration; + int ret; + + page_frag_cache_init(&test_nc); + atomic_set(&nthreads, 2); + init_completion(&wait); + + if (test_alloc_len > PAGE_SIZE || test_alloc_len <= 0 || + !cpu_active(test_push_cpu) || !cpu_active(test_pop_cpu)) + return -EINVAL; + + ret = ptr_ring_init(&ptr_ring, nr_objs, GFP_KERNEL); + if (ret) + return ret; + + tsk_push = kthread_create_on_cpu(page_frag_push_thread, &ptr_ring, + test_push_cpu, "page_frag_push"); + if (IS_ERR(tsk_push)) + return PTR_ERR(tsk_push); + + tsk_pop = kthread_create_on_cpu(page_frag_pop_thread, &ptr_ring, + test_pop_cpu, "page_frag_pop"); + if (IS_ERR(tsk_pop)) { + kthread_stop(tsk_push); + return PTR_ERR(tsk_pop); + } + + start = ktime_get(); + wake_up_process(tsk_push); + wake_up_process(tsk_pop); + + pr_info("waiting for test to complete\n"); + + while (!wait_for_completion_timeout(&wait, msecs_to_jiffies(10000))) { + /* exit if there is no progress for push or pop size */ + if (last_pushed == test_pushed || last_popped == test_popped) { + WARN_ONCE(true, TEST_FAILED_PREFIX "no progress\n"); + force_exit = true; + continue; + } + + last_pushed = test_pushed; + last_popped = test_popped; + pr_info("page_frag_test progress: pushed = %d, popped = %d\n", + test_pushed, test_popped); + } + + if (force_exit) { + pr_err(TEST_FAILED_PREFIX "exit with error\n"); + goto out; + } + + duration = (u64)ktime_us_delta(ktime_get(), start); + pr_info("%d of iterations for %s testing took: %lluus\n", nr_test, + test_align ? "aligned" : "non-aligned", duration); + +out: + ptr_ring_cleanup(&ptr_ring, NULL); + page_frag_cache_drain(&test_nc); + + return -EAGAIN; +} + +static void __exit page_frag_test_exit(void) +{ +} + +module_init(page_frag_test_init); +module_exit(page_frag_test_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yunsheng Lin <linyunsheng@huawei.com>"); +MODULE_DESCRIPTION("Test module for page_frag"); diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c new file mode 100644 index 000000000000..2cb5441f29c7 --- /dev/null +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -0,0 +1,1738 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <stdio.h> +#include <fcntl.h> +#include <string.h> +#include <sys/mman.h> +#include <errno.h> +#include <malloc.h> +#include "vm_util.h" +#include "kselftest.h" +#include <linux/types.h> +#include <linux/memfd.h> +#include <linux/userfaultfd.h> +#include <linux/fs.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <math.h> +#include <asm/unistd.h> +#include <pthread.h> +#include <sys/resource.h> +#include <assert.h> +#include <sys/ipc.h> +#include <sys/shm.h> + +#define PAGEMAP_BITS_ALL (PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | \ + PAGE_IS_FILE | PAGE_IS_PRESENT | \ + PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | \ + PAGE_IS_HUGE) +#define PAGEMAP_NON_WRITTEN_BITS (PAGE_IS_WPALLOWED | PAGE_IS_FILE | \ + PAGE_IS_PRESENT | PAGE_IS_SWAPPED | \ + PAGE_IS_PFNZERO | PAGE_IS_HUGE) + +#define TEST_ITERATIONS 100 +#define PAGEMAP "/proc/self/pagemap" +int pagemap_fd; +int uffd; +size_t page_size; +size_t hpage_size; +const char *progname; + +#define LEN(region) ((region.end - region.start)/page_size) + +static long pagemap_ioctl(void *start, int len, void *vec, int vec_len, int flag, + int max_pages, long required_mask, long anyof_mask, long excluded_mask, + long return_mask) +{ + struct pm_scan_arg arg; + + arg.start = (uintptr_t)start; + arg.end = (uintptr_t)(start + len); + arg.vec = (uintptr_t)vec; + arg.vec_len = vec_len; + arg.flags = flag; + arg.size = sizeof(struct pm_scan_arg); + arg.max_pages = max_pages; + arg.category_mask = required_mask; + arg.category_anyof_mask = anyof_mask; + arg.category_inverted = excluded_mask; + arg.return_mask = return_mask; + + return ioctl(pagemap_fd, PAGEMAP_SCAN, &arg); +} + +static long pagemap_ioc(void *start, int len, void *vec, int vec_len, int flag, + int max_pages, long required_mask, long anyof_mask, long excluded_mask, + long return_mask, long *walk_end) +{ + struct pm_scan_arg arg; + int ret; + + arg.start = (uintptr_t)start; + arg.end = (uintptr_t)(start + len); + arg.vec = (uintptr_t)vec; + arg.vec_len = vec_len; + arg.flags = flag; + arg.size = sizeof(struct pm_scan_arg); + arg.max_pages = max_pages; + arg.category_mask = required_mask; + arg.category_anyof_mask = anyof_mask; + arg.category_inverted = excluded_mask; + arg.return_mask = return_mask; + + ret = ioctl(pagemap_fd, PAGEMAP_SCAN, &arg); + + if (walk_end) + *walk_end = arg.walk_end; + + return ret; +} + + +int init_uffd(void) +{ + struct uffdio_api uffdio_api; + + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY); + if (uffd == -1) + return uffd; + + uffdio_api.api = UFFD_API; + uffdio_api.features = UFFD_FEATURE_WP_UNPOPULATED | UFFD_FEATURE_WP_ASYNC | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM; + if (ioctl(uffd, UFFDIO_API, &uffdio_api)) + return -1; + + if (!(uffdio_api.api & UFFDIO_REGISTER_MODE_WP) || + !(uffdio_api.features & UFFD_FEATURE_WP_UNPOPULATED) || + !(uffdio_api.features & UFFD_FEATURE_WP_ASYNC) || + !(uffdio_api.features & UFFD_FEATURE_WP_HUGETLBFS_SHMEM)) + return -1; + + return 0; +} + +int wp_init(void *lpBaseAddress, long dwRegionSize) +{ + struct uffdio_register uffdio_register; + struct uffdio_writeprotect wp; + + uffdio_register.range.start = (unsigned long)lpBaseAddress; + uffdio_register.range.len = dwRegionSize; + uffdio_register.mode = UFFDIO_REGISTER_MODE_WP; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + ksft_exit_fail_msg("ioctl(UFFDIO_REGISTER) %d %s\n", errno, strerror(errno)); + + if (!(uffdio_register.ioctls & UFFDIO_WRITEPROTECT)) + ksft_exit_fail_msg("ioctl set is incorrect\n"); + + wp.range.start = (unsigned long)lpBaseAddress; + wp.range.len = dwRegionSize; + wp.mode = UFFDIO_WRITEPROTECT_MODE_WP; + + if (ioctl(uffd, UFFDIO_WRITEPROTECT, &wp)) + ksft_exit_fail_msg("ioctl(UFFDIO_WRITEPROTECT)\n"); + + return 0; +} + +int wp_free(void *lpBaseAddress, long dwRegionSize) +{ + struct uffdio_register uffdio_register; + + uffdio_register.range.start = (unsigned long)lpBaseAddress; + uffdio_register.range.len = dwRegionSize; + uffdio_register.mode = UFFDIO_REGISTER_MODE_WP; + if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) + ksft_exit_fail_msg("ioctl unregister failure\n"); + return 0; +} + +int wp_addr_range(void *lpBaseAddress, int dwRegionSize) +{ + if (pagemap_ioctl(lpBaseAddress, dwRegionSize, NULL, 0, + PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN) < 0) + ksft_exit_fail_msg("error %d %d %s\n", 1, errno, strerror(errno)); + + return 0; +} + +void *gethugetlb_mem(int size, int *shmid) +{ + char *mem; + + if (shmid) { + *shmid = shmget(2, size, SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W); + if (*shmid < 0) + return NULL; + + mem = shmat(*shmid, 0, 0); + if (mem == (char *)-1) { + shmctl(*shmid, IPC_RMID, NULL); + ksft_exit_fail_msg("Shared memory attach failure\n"); + } + } else { + mem = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_HUGETLB | MAP_PRIVATE, -1, 0); + if (mem == MAP_FAILED) + return NULL; + } + + return mem; +} + +int userfaultfd_tests(void) +{ + long mem_size, vec_size, written, num_pages = 16; + char *mem, *vec; + + mem_size = num_pages * page_size; + mem = mmap(NULL, mem_size, PROT_NONE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + + wp_init(mem, mem_size); + + /* Change protection of pages differently */ + mprotect(mem, mem_size/8, PROT_READ|PROT_WRITE); + mprotect(mem + 1 * mem_size/8, mem_size/8, PROT_READ); + mprotect(mem + 2 * mem_size/8, mem_size/8, PROT_READ|PROT_WRITE); + mprotect(mem + 3 * mem_size/8, mem_size/8, PROT_READ); + mprotect(mem + 4 * mem_size/8, mem_size/8, PROT_READ|PROT_WRITE); + mprotect(mem + 5 * mem_size/8, mem_size/8, PROT_NONE); + mprotect(mem + 6 * mem_size/8, mem_size/8, PROT_READ|PROT_WRITE); + mprotect(mem + 7 * mem_size/8, mem_size/8, PROT_READ); + + wp_addr_range(mem + (mem_size/16), mem_size - 2 * (mem_size/8)); + wp_addr_range(mem, mem_size); + + vec_size = mem_size/page_size; + vec = calloc(vec_size, sizeof(struct page_region)); + + written = pagemap_ioctl(mem, mem_size, vec, 1, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + vec_size - 2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); + if (written < 0) + ksft_exit_fail_msg("error %ld %d %s\n", written, errno, strerror(errno)); + + ksft_test_result(written == 0, "%s all new pages must not be written (dirty)\n", __func__); + + wp_free(mem, mem_size); + munmap(mem, mem_size); + free(vec); + return 0; +} + +int get_reads(struct page_region *vec, int vec_size) +{ + int i, sum = 0; + + for (i = 0; i < vec_size; i++) + sum += LEN(vec[i]); + + return sum; +} + +int sanity_tests_sd(void) +{ + 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]; + long walk_end; + + vec_size = num_pages/2; + mem_size = num_pages * page_size; + + vec = calloc(vec_size, sizeof(struct page_region)); + if (!vec) + ksft_exit_fail_msg("error nomem\n"); + + vec2 = calloc(vec_size, sizeof(struct page_region)); + if (!vec2) + ksft_exit_fail_msg("error nomem\n"); + + mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + /* 1. wrong operation */ + ksft_test_result(pagemap_ioctl(mem, 0, vec, vec_size, 0, + 0, PAGEMAP_BITS_ALL, 0, 0, PAGEMAP_BITS_ALL) == 0, + "%s Zero range size is valid\n", __func__); + + ksft_test_result(pagemap_ioctl(mem, mem_size, NULL, vec_size, 0, + 0, PAGEMAP_BITS_ALL, 0, 0, PAGEMAP_BITS_ALL) < 0, + "%s output buffer must be specified with size\n", __func__); + + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, 0, 0, + 0, PAGEMAP_BITS_ALL, 0, 0, PAGEMAP_BITS_ALL) == 0, + "%s output buffer can be 0\n", __func__); + + ksft_test_result(pagemap_ioctl(mem, mem_size, 0, 0, 0, + 0, PAGEMAP_BITS_ALL, 0, 0, PAGEMAP_BITS_ALL) == 0, + "%s output buffer can be 0\n", __func__); + + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, -1, + 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN) < 0, + "%s wrong flag specified\n", __func__); + + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, + PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC | 0xFF, + 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN) < 0, + "%s flag has extra bits specified\n", __func__); + + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0, + 0, 0, 0, 0, PAGE_IS_WRITTEN) >= 0, + "%s no selection mask is specified\n", __func__); + + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0, + 0, PAGE_IS_WRITTEN, PAGE_IS_WRITTEN, 0, 0) == 0, + "%s no return mask is specified\n", __func__); + + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0, + 0, PAGE_IS_WRITTEN, 0, 0, 0x1000) < 0, + "%s wrong return mask specified\n", __func__); + + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, + PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + 0, 0xFFF, PAGE_IS_WRITTEN, 0, PAGE_IS_WRITTEN) < 0, + "%s mixture of correct and wrong flag\n", __func__); + + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, + PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + 0, 0, 0, PAGEMAP_BITS_ALL, PAGE_IS_WRITTEN) >= 0, + "%s PAGEMAP_BITS_ALL can be specified with PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC\n", + __func__); + + /* 2. Clear area with larger vec size */ + ret = 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); + ksft_test_result(ret >= 0, "%s Clear area with larger vec size\n", __func__); + + /* 3. Repeated pattern of written and non-written pages */ + for (i = 0; i < mem_size; i += 2 * page_size) + mem[i]++; + + 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 %ld %d %s\n", ret, errno, strerror(errno)); + + 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 */ + ret = pagemap_ioctl(mem, mem_size, vec, vec_size, + 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 %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 %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 %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 %ld %ld %ld\n", + __func__, ret, ret3, ret2); + + /* 5. Repeated pattern of written and non-written pages max_pages */ + for (i = 0; i < mem_size; i += 2 * page_size) + mem[i]++; + mem[(mem_size/page_size - 1) * page_size]++; + + ret = pagemap_ioctl(mem, mem_size, vec, vec_size, + 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 %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 %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", + __func__); + + /* 6. only get 2 dirty pages and clear them as well */ + vec_size = mem_size/page_size; + memset(mem, -1, mem_size); + + /* get and clear second and third pages */ + ret = pagemap_ioctl(mem + page_size, 2 * page_size, vec, 1, + 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 %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 %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) && + ret2 == 2 && LEN(vec2[0]) == 1 && vec2[0].start == (uintptr_t)mem && + LEN(vec2[1]) == vec_size - 3 && + vec2[1].start == (uintptr_t)(mem + 3 * page_size), + "%s only get 2 written pages and clear them as well\n", __func__); + + wp_free(mem, mem_size); + munmap(mem, mem_size); + + /* 7. Two regions */ + m[0] = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (m[0] == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + m[1] = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (m[1] == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + + wp_init(m[0], mem_size); + wp_init(m[1], mem_size); + wp_addr_range(m[0], mem_size); + wp_addr_range(m[1], mem_size); + + memset(m[0], 'a', mem_size); + memset(m[1], 'b', mem_size); + + wp_addr_range(m[0], mem_size); + + 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 %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__); + + wp_free(m[0], mem_size); + wp_free(m[1], mem_size); + munmap(m[0], mem_size); + munmap(m[1], mem_size); + + free(vec); + free(vec2); + + /* 8. Smaller vec */ + mem_size = 1050 * page_size; + vec_size = mem_size/(page_size*2); + + vec = calloc(vec_size, sizeof(struct page_region)); + if (!vec) + ksft_exit_fail_msg("error nomem\n"); + + mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + ret = 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 (ret < 0) + 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]++; + + ret = pagemap_ioctl(mem, mem_size, vec, vec_size, + 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 %ld %d %s\n", ret, errno, strerror(errno)); + + total_pages += ret; + + ret = pagemap_ioctl(mem, mem_size, vec, vec_size, + 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 %ld %d %s\n", ret, errno, strerror(errno)); + + total_pages += ret; + + ret = pagemap_ioctl(mem, mem_size, vec, vec_size, + 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 %ld %d %s\n", ret, errno, strerror(errno)); + + total_pages += ret; + + ksft_test_result(total_pages == mem_size/(page_size*2), "%s Smaller max_pages\n", __func__); + + free(vec); + wp_free(mem, mem_size); + munmap(mem, mem_size); + total_pages = 0; + + /* 9. Smaller vec */ + mem_size = 10000 * page_size; + vec_size = 50; + + vec = calloc(vec_size, sizeof(struct page_region)); + if (!vec) + ksft_exit_fail_msg("error nomem\n"); + + mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + for (count = 0; count < TEST_ITERATIONS; count++) { + total_writes = total_reads = 0; + walk_end = (long)mem; + + for (i = 0; i < mem_size; i += page_size) { + if (rand() % 2) { + mem[i]++; + total_writes++; + } + } + + while (total_reads < total_writes) { + ret = pagemap_ioc((void *)walk_end, mem_size-(walk_end - (long)mem), 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 %ld %d %s\n", ret, errno, strerror(errno)); + + if ((unsigned long)ret > vec_size) + break; + + reads = get_reads(vec, ret); + total_reads += reads; + } + + if (total_reads != total_writes) + break; + } + + ksft_test_result(count == TEST_ITERATIONS, "Smaller vec\n"); + + free(vec); + wp_free(mem, mem_size); + munmap(mem, mem_size); + + /* 10. Walk_end tester */ + vec_size = 1000; + mem_size = vec_size * page_size; + + vec = calloc(vec_size, sizeof(struct page_region)); + if (!vec) + ksft_exit_fail_msg("error nomem\n"); + + mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + memset(mem, 0, mem_size); + + 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 %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 %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 %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 %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 %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 %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 %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 %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 %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), + "Walk_end: max pages\n"); + + wp_addr_range(mem, mem_size); + for (i = 0; i < mem_size; i += 2 * page_size) + mem[i]++; + + 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 %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 %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 %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 %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 %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 %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 %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"); + + free(vec); + wp_free(mem, mem_size); + munmap(mem, mem_size); + + return 0; +} + +int base_tests(char *prefix, char *mem, unsigned long long mem_size, int skip) +{ + unsigned long long vec_size; + int written; + struct page_region *vec, *vec2; + + if (skip) { + ksft_test_result_skip("%s all new pages must not be written (dirty)\n", prefix); + ksft_test_result_skip("%s all pages must be written (dirty)\n", prefix); + ksft_test_result_skip("%s all pages dirty other than first and the last one\n", + prefix); + ksft_test_result_skip("%s PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC\n", prefix); + ksft_test_result_skip("%s only middle page dirty\n", prefix); + ksft_test_result_skip("%s only two middle pages dirty\n", prefix); + return 0; + } + + vec_size = mem_size/page_size; + vec = calloc(vec_size, sizeof(struct page_region)); + vec2 = calloc(vec_size, sizeof(struct page_region)); + + /* 1. all new pages must be not be written (dirty) */ + written = pagemap_ioctl(mem, mem_size, vec, 1, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + vec_size - 2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); + if (written < 0) + ksft_exit_fail_msg("error %d %d %s\n", written, errno, strerror(errno)); + + ksft_test_result(written == 0, "%s all new pages must not be written (dirty)\n", prefix); + + /* 2. all pages must be written */ + memset(mem, -1, mem_size); + + written = pagemap_ioctl(mem, mem_size, vec, 1, 0, 0, PAGE_IS_WRITTEN, 0, 0, + PAGE_IS_WRITTEN); + if (written < 0) + ksft_exit_fail_msg("error %d %d %s\n", written, errno, strerror(errno)); + + ksft_test_result(written == 1 && LEN(vec[0]) == mem_size/page_size, + "%s all pages must be written (dirty)\n", prefix); + + /* 3. all pages dirty other than first and the last one */ + written = pagemap_ioctl(mem, mem_size, vec, 1, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); + if (written < 0) + ksft_exit_fail_msg("error %d %d %s\n", written, errno, strerror(errno)); + + memset(mem + page_size, 0, mem_size - (2 * page_size)); + + written = pagemap_ioctl(mem, mem_size, vec, 1, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); + if (written < 0) + ksft_exit_fail_msg("error %d %d %s\n", written, errno, strerror(errno)); + + ksft_test_result(written == 1 && LEN(vec[0]) >= vec_size - 2 && LEN(vec[0]) <= vec_size, + "%s all pages dirty other than first and the last one\n", prefix); + + written = pagemap_ioctl(mem, mem_size, vec, 1, 0, 0, + PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); + if (written < 0) + ksft_exit_fail_msg("error %d %d %s\n", written, errno, strerror(errno)); + + ksft_test_result(written == 0, + "%s PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC\n", prefix); + + /* 4. only middle page dirty */ + written = pagemap_ioctl(mem, mem_size, vec, 1, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); + if (written < 0) + ksft_exit_fail_msg("error %d %d %s\n", written, errno, strerror(errno)); + + mem[vec_size/2 * page_size]++; + + written = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, + 0, 0, PAGE_IS_WRITTEN); + if (written < 0) + ksft_exit_fail_msg("error %d %d %s\n", written, errno, strerror(errno)); + + ksft_test_result(written == 1 && LEN(vec[0]) >= 1, + "%s only middle page dirty\n", prefix); + + /* 5. only two middle pages dirty and walk over only middle pages */ + written = pagemap_ioctl(mem, mem_size, vec, 1, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN | PAGE_IS_HUGE); + if (written < 0) + ksft_exit_fail_msg("error %d %d %s\n", written, errno, strerror(errno)); + + mem[vec_size/2 * page_size]++; + mem[(vec_size/2 + 1) * page_size]++; + + written = pagemap_ioctl(&mem[vec_size/2 * page_size], 2 * page_size, vec, 1, 0, + 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN | PAGE_IS_HUGE); + if (written < 0) + ksft_exit_fail_msg("error %d %d %s\n", written, errno, strerror(errno)); + + ksft_test_result(written == 1 && vec[0].start == (uintptr_t)(&mem[vec_size/2 * page_size]) + && LEN(vec[0]) == 2, + "%s only two middle pages dirty\n", prefix); + + free(vec); + free(vec2); + return 0; +} + +void *gethugepage(int map_size) +{ + int ret; + char *map; + + map = memalign(hpage_size, map_size); + if (!map) + ksft_exit_fail_msg("memalign failed %d %s\n", errno, strerror(errno)); + + ret = madvise(map, map_size, MADV_HUGEPAGE); + if (ret) + return NULL; + + memset(map, 0, map_size); + + return map; +} + +int hpage_unit_tests(void) +{ + char *map; + int ret, ret2; + size_t num_pages = 10; + unsigned long long map_size = hpage_size * num_pages; + unsigned long long vec_size = map_size/page_size; + struct page_region *vec, *vec2; + + vec = calloc(vec_size, sizeof(struct page_region)); + vec2 = calloc(vec_size, sizeof(struct page_region)); + if (!vec || !vec2) + ksft_exit_fail_msg("malloc failed\n"); + + map = gethugepage(map_size); + if (map) { + wp_init(map, map_size); + wp_addr_range(map, map_size); + + /* 1. all new huge page must not be written (dirty) */ + ret = pagemap_ioctl(map, map_size, vec, vec_size, + 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_test_result(ret == 0, "%s all new huge page must not be written (dirty)\n", + __func__); + + /* 2. all the huge page must not be written */ + ret = pagemap_ioctl(map, map_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_test_result(ret == 0, "%s all the huge page must not be written\n", __func__); + + /* 3. all the huge page must be written and clear dirty as well */ + memset(map, -1, map_size); + ret = pagemap_ioctl(map, map_size, vec, vec_size, + 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_test_result(ret == 1 && vec[0].start == (uintptr_t)map && + LEN(vec[0]) == vec_size && vec[0].categories == PAGE_IS_WRITTEN, + "%s all the huge page must be written and clear\n", __func__); + + /* 4. only middle page written */ + wp_free(map, map_size); + free(map); + map = gethugepage(map_size); + wp_init(map, map_size); + wp_addr_range(map, map_size); + map[vec_size/2 * page_size]++; + + ret = pagemap_ioctl(map, map_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_test_result(ret == 1 && LEN(vec[0]) > 0, + "%s only middle page written\n", __func__); + + wp_free(map, map_size); + free(map); + } else { + ksft_test_result_skip("%s all new huge page must be written\n", __func__); + ksft_test_result_skip("%s all the huge page must not be written\n", __func__); + ksft_test_result_skip("%s all the huge page must be written and clear\n", __func__); + ksft_test_result_skip("%s only middle page written\n", __func__); + } + + /* 5. clear first half of huge page */ + map = gethugepage(map_size); + if (map) { + wp_init(map, map_size); + wp_addr_range(map, map_size); + + memset(map, 0, map_size); + + wp_addr_range(map, map_size/2); + + ret = pagemap_ioctl(map, map_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_test_result(ret == 1 && LEN(vec[0]) == vec_size/2 && + vec[0].start == (uintptr_t)(map + map_size/2), + "%s clear first half of huge page\n", __func__); + wp_free(map, map_size); + free(map); + } else { + ksft_test_result_skip("%s clear first half of huge page\n", __func__); + } + + /* 6. clear first half of huge page with limited buffer */ + map = gethugepage(map_size); + if (map) { + wp_init(map, map_size); + wp_addr_range(map, map_size); + + memset(map, 0, map_size); + + ret = pagemap_ioctl(map, map_size, vec, vec_size, + PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + vec_size/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)); + + ret = pagemap_ioctl(map, map_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_test_result(ret == 1 && LEN(vec[0]) == vec_size/2 && + vec[0].start == (uintptr_t)(map + map_size/2), + "%s clear first half of huge page with limited buffer\n", + __func__); + wp_free(map, map_size); + free(map); + } else { + ksft_test_result_skip("%s clear first half of huge page with limited buffer\n", + __func__); + } + + /* 7. clear second half of huge page */ + map = gethugepage(map_size); + if (map) { + wp_init(map, map_size); + wp_addr_range(map, map_size); + + memset(map, -1, map_size); + + ret = pagemap_ioctl(map + map_size/2, map_size/2, vec, vec_size, + PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, vec_size/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)); + + ret = pagemap_ioctl(map, map_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_test_result(ret == 1 && LEN(vec[0]) == vec_size/2, + "%s clear second half huge page\n", __func__); + wp_free(map, map_size); + free(map); + } else { + ksft_test_result_skip("%s clear second half huge page\n", __func__); + } + + /* 8. get half huge page */ + map = gethugepage(map_size); + if (map) { + wp_init(map, map_size); + wp_addr_range(map, map_size); + + memset(map, -1, map_size); + usleep(100); + + ret = pagemap_ioctl(map, map_size, vec, 1, + PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + hpage_size/(2*page_size), 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_test_result(ret == 1 && LEN(vec[0]) == hpage_size/(2*page_size), + "%s get half huge page\n", __func__); + + ret2 = pagemap_ioctl(map, map_size, vec, 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_test_result(ret2 == 1 && LEN(vec[0]) == (map_size - hpage_size/2)/page_size, + "%s get half huge page\n", __func__); + + wp_free(map, map_size); + free(map); + } else { + ksft_test_result_skip("%s get half huge page\n", __func__); + ksft_test_result_skip("%s get half huge page\n", __func__); + } + + free(vec); + free(vec2); + return 0; +} + +int unmapped_region_tests(void) +{ + void *start = (void *)0x10000000; + int written, len = 0x00040000; + long vec_size = len / page_size; + struct page_region *vec = calloc(vec_size, sizeof(struct page_region)); + + /* 1. Get written pages */ + written = pagemap_ioctl(start, len, vec, vec_size, 0, 0, + PAGEMAP_NON_WRITTEN_BITS, 0, 0, PAGEMAP_NON_WRITTEN_BITS); + if (written < 0) + ksft_exit_fail_msg("error %d %d %s\n", written, errno, strerror(errno)); + + ksft_test_result(written >= 0, "%s Get status of pages\n", __func__); + + free(vec); + return 0; +} + +static void test_simple(void) +{ + int i; + char *map; + struct page_region vec; + + map = aligned_alloc(page_size, page_size); + if (!map) + ksft_exit_fail_msg("aligned_alloc failed\n"); + + wp_init(map, page_size); + wp_addr_range(map, page_size); + + for (i = 0 ; i < TEST_ITERATIONS; i++) { + if (pagemap_ioctl(map, page_size, &vec, 1, 0, 0, + PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN) == 1) { + ksft_print_msg("written bit was 1, but should be 0 (i=%d)\n", i); + break; + } + + wp_addr_range(map, page_size); + /* Write something to the page to get the written bit enabled on the page */ + map[0]++; + + if (pagemap_ioctl(map, page_size, &vec, 1, 0, 0, + PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN) == 0) { + ksft_print_msg("written bit was 0, but should be 1 (i=%d)\n", i); + break; + } + + wp_addr_range(map, page_size); + } + wp_free(map, page_size); + free(map); + + ksft_test_result(i == TEST_ITERATIONS, "Test %s\n", __func__); +} + +int sanity_tests(void) +{ + unsigned long long mem_size, vec_size; + long ret, fd, i, buf_size; + struct page_region *vec; + char *mem, *fmem; + struct stat sbuf; + char *tmp_buf; + + /* 1. wrong operation */ + mem_size = 10 * page_size; + vec_size = mem_size / page_size; + + vec = calloc(vec_size, sizeof(struct page_region)); + mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED || vec == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, + PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, + 0, PAGEMAP_BITS_ALL, 0, 0, PAGEMAP_BITS_ALL) >= 0, + "%s WP op can be specified with !PAGE_IS_WRITTEN\n", __func__); + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, + PAGEMAP_BITS_ALL, 0, 0, PAGEMAP_BITS_ALL) >= 0, + "%s required_mask specified\n", __func__); + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, + 0, PAGEMAP_BITS_ALL, 0, PAGEMAP_BITS_ALL) >= 0, + "%s anyof_mask specified\n", __func__); + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, + 0, 0, PAGEMAP_BITS_ALL, PAGEMAP_BITS_ALL) >= 0, + "%s excluded_mask specified\n", __func__); + ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, + PAGEMAP_BITS_ALL, PAGEMAP_BITS_ALL, 0, + PAGEMAP_BITS_ALL) >= 0, + "%s required_mask and anyof_mask specified\n", __func__); + wp_free(mem, mem_size); + munmap(mem, mem_size); + + /* 2. Get sd and present pages with anyof_mask */ + mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + memset(mem, 0, mem_size); + + ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, + 0, PAGEMAP_BITS_ALL, 0, PAGEMAP_BITS_ALL); + ksft_test_result(ret >= 0 && vec[0].start == (uintptr_t)mem && LEN(vec[0]) == vec_size && + (vec[0].categories & (PAGE_IS_WRITTEN | PAGE_IS_PRESENT)) == + (PAGE_IS_WRITTEN | PAGE_IS_PRESENT), + "%s Get sd and present pages with anyof_mask\n", __func__); + + /* 3. Get sd and present pages with required_mask */ + ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, + PAGEMAP_BITS_ALL, 0, 0, PAGEMAP_BITS_ALL); + ksft_test_result(ret >= 0 && vec[0].start == (uintptr_t)mem && LEN(vec[0]) == vec_size && + (vec[0].categories & (PAGE_IS_WRITTEN | PAGE_IS_PRESENT)) == + (PAGE_IS_WRITTEN | PAGE_IS_PRESENT), + "%s Get all the pages with required_mask\n", __func__); + + /* 4. Get sd and present pages with required_mask and anyof_mask */ + ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, + PAGE_IS_WRITTEN, PAGE_IS_PRESENT, 0, PAGEMAP_BITS_ALL); + ksft_test_result(ret >= 0 && vec[0].start == (uintptr_t)mem && LEN(vec[0]) == vec_size && + (vec[0].categories & (PAGE_IS_WRITTEN | PAGE_IS_PRESENT)) == + (PAGE_IS_WRITTEN | PAGE_IS_PRESENT), + "%s Get sd and present pages with required_mask and anyof_mask\n", + __func__); + + /* 5. Don't get sd pages */ + ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, + PAGE_IS_WRITTEN, 0, PAGE_IS_WRITTEN, PAGEMAP_BITS_ALL); + ksft_test_result(ret == 0, "%s Don't get sd pages\n", __func__); + + /* 6. Don't get present pages */ + ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, + PAGE_IS_PRESENT, 0, PAGE_IS_PRESENT, PAGEMAP_BITS_ALL); + ksft_test_result(ret == 0, "%s Don't get present pages\n", __func__); + + wp_free(mem, mem_size); + munmap(mem, mem_size); + + /* 8. Find written present pages with return mask */ + mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + memset(mem, 0, mem_size); + + ret = pagemap_ioctl(mem, mem_size, vec, vec_size, + PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, + 0, PAGEMAP_BITS_ALL, 0, PAGE_IS_WRITTEN); + ksft_test_result(ret >= 0 && vec[0].start == (uintptr_t)mem && LEN(vec[0]) == vec_size && + vec[0].categories == PAGE_IS_WRITTEN, + "%s Find written present pages with return mask\n", __func__); + wp_free(mem, mem_size); + munmap(mem, mem_size); + + /* 9. Memory mapped file */ + fd = open(progname, O_RDONLY); + if (fd < 0) + ksft_exit_fail_msg("%s Memory mapped file\n", __func__); + + ret = stat(progname, &sbuf); + if (ret < 0) + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + + fmem = mmap(NULL, sbuf.st_size, PROT_READ, MAP_PRIVATE, fd, 0); + if (fmem == MAP_FAILED) + ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno)); + + tmp_buf = malloc(sbuf.st_size); + memcpy(tmp_buf, fmem, sbuf.st_size); + + ret = pagemap_ioctl(fmem, sbuf.st_size, vec, vec_size, 0, 0, + 0, PAGEMAP_NON_WRITTEN_BITS, 0, PAGEMAP_NON_WRITTEN_BITS); + + ksft_test_result(ret >= 0 && vec[0].start == (uintptr_t)fmem && + LEN(vec[0]) == ceilf((float)sbuf.st_size/page_size) && + (vec[0].categories & PAGE_IS_FILE), + "%s Memory mapped file\n", __func__); + + munmap(fmem, sbuf.st_size); + close(fd); + + /* 10. Create and read/write to a memory mapped file */ + buf_size = page_size * 10; + + fd = open(__FILE__".tmp2", O_RDWR | O_CREAT, 0666); + if (fd < 0) + ksft_exit_fail_msg("Read/write to memory: %s\n", + strerror(errno)); + + for (i = 0; i < buf_size; i++) + if (write(fd, "c", 1) < 0) + ksft_exit_fail_msg("Create and read/write to a memory mapped file\n"); + + fmem = mmap(NULL, buf_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + if (fmem == MAP_FAILED) + ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno)); + + wp_init(fmem, buf_size); + wp_addr_range(fmem, buf_size); + + for (i = 0; i < buf_size; i++) + fmem[i] = 'z'; + + msync(fmem, buf_size, MS_SYNC); + + ret = pagemap_ioctl(fmem, buf_size, vec, vec_size, 0, 0, + PAGE_IS_WRITTEN, PAGE_IS_PRESENT | PAGE_IS_SWAPPED | PAGE_IS_FILE, 0, + PAGEMAP_BITS_ALL); + + ksft_test_result(ret >= 0 && vec[0].start == (uintptr_t)fmem && + LEN(vec[0]) == (buf_size/page_size) && + (vec[0].categories & PAGE_IS_WRITTEN), + "%s Read/write to memory\n", __func__); + + wp_free(fmem, buf_size); + munmap(fmem, buf_size); + close(fd); + + free(vec); + return 0; +} + +int mprotect_tests(void) +{ + int ret; + char *mem, *mem2; + struct page_region vec; + int pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + + if (pagemap_fd < 0) { + fprintf(stderr, "open() failed\n"); + exit(1); + } + + /* 1. Map two pages */ + mem = mmap(0, 2 * page_size, PROT_READ|PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + wp_init(mem, 2 * page_size); + wp_addr_range(mem, 2 * page_size); + + /* Populate both pages. */ + memset(mem, 1, 2 * page_size); + + ret = pagemap_ioctl(mem, 2 * page_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_test_result(ret == 1 && LEN(vec) == 2, "%s Both pages written\n", __func__); + + /* 2. Start tracking */ + wp_addr_range(mem, 2 * page_size); + + ksft_test_result(pagemap_ioctl(mem, 2 * page_size, &vec, 1, 0, 0, + PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN) == 0, + "%s Both pages are not written (dirty)\n", __func__); + + /* 3. Remap the second page */ + mem2 = mmap(mem + page_size, page_size, PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANON|MAP_FIXED, -1, 0); + if (mem2 == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + wp_init(mem2, page_size); + wp_addr_range(mem2, page_size); + + /* Protect + unprotect. */ + mprotect(mem, page_size, PROT_NONE); + mprotect(mem, 2 * page_size, PROT_READ); + mprotect(mem, 2 * page_size, PROT_READ|PROT_WRITE); + + /* Modify both pages. */ + memset(mem, 2, 2 * page_size); + + /* Protect + unprotect. */ + mprotect(mem, page_size, PROT_NONE); + mprotect(mem, page_size, PROT_READ); + mprotect(mem, page_size, PROT_READ|PROT_WRITE); + + ret = pagemap_ioctl(mem, 2 * page_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_test_result(ret == 1 && LEN(vec) == 2, + "%s Both pages written after remap and mprotect\n", __func__); + + /* 4. Clear and make the pages written */ + wp_addr_range(mem, 2 * page_size); + + memset(mem, 'A', 2 * page_size); + + ret = pagemap_ioctl(mem, 2 * page_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_test_result(ret == 1 && LEN(vec) == 2, + "%s Clear and make the pages written\n", __func__); + + wp_free(mem, 2 * page_size); + munmap(mem, 2 * page_size); + return 0; +} + +/* transact test */ +static const unsigned int nthreads = 6, pages_per_thread = 32, access_per_thread = 8; +static pthread_barrier_t start_barrier, end_barrier; +static unsigned int extra_thread_faults; +static unsigned int iter_count = 1000; +static volatile int finish; + +static ssize_t get_dirty_pages_reset(char *mem, unsigned int count, + int reset, int page_size) +{ + struct pm_scan_arg arg = {0}; + struct page_region rgns[256]; + unsigned long long i, j; + long ret; + int cnt; + + arg.size = sizeof(struct pm_scan_arg); + arg.start = (uintptr_t)mem; + arg.max_pages = count; + arg.end = (uintptr_t)(mem + count * page_size); + arg.vec = (uintptr_t)rgns; + arg.vec_len = sizeof(rgns) / sizeof(*rgns); + if (reset) + arg.flags |= PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC; + arg.category_mask = PAGE_IS_WRITTEN; + arg.return_mask = PAGE_IS_WRITTEN; + + ret = ioctl(pagemap_fd, PAGEMAP_SCAN, &arg); + if (ret < 0) + ksft_exit_fail_msg("ioctl failed\n"); + + cnt = 0; + for (i = 0; i < (unsigned long)ret; ++i) { + if (rgns[i].categories != PAGE_IS_WRITTEN) + ksft_exit_fail_msg("wrong flags\n"); + + for (j = 0; j < LEN(rgns[i]); ++j) + cnt++; + } + + return cnt; +} + +void *thread_proc(void *mem) +{ + int *m = mem; + long curr_faults, faults; + struct rusage r; + unsigned int i; + int ret; + + if (getrusage(RUSAGE_THREAD, &r)) + ksft_exit_fail_msg("getrusage\n"); + + curr_faults = r.ru_minflt; + + while (!finish) { + ret = pthread_barrier_wait(&start_barrier); + if (ret && ret != PTHREAD_BARRIER_SERIAL_THREAD) + ksft_exit_fail_msg("pthread_barrier_wait\n"); + + for (i = 0; i < access_per_thread; ++i) + __atomic_add_fetch(m + i * (0x1000 / sizeof(*m)), 1, __ATOMIC_SEQ_CST); + + ret = pthread_barrier_wait(&end_barrier); + if (ret && ret != PTHREAD_BARRIER_SERIAL_THREAD) + ksft_exit_fail_msg("pthread_barrier_wait\n"); + + if (getrusage(RUSAGE_THREAD, &r)) + ksft_exit_fail_msg("getrusage\n"); + + faults = r.ru_minflt - curr_faults; + if (faults < access_per_thread) + ksft_exit_fail_msg("faults < access_per_thread"); + + __atomic_add_fetch(&extra_thread_faults, faults - access_per_thread, + __ATOMIC_SEQ_CST); + curr_faults = r.ru_minflt; + } + + return NULL; +} + +static void transact_test(int page_size) +{ + unsigned int i, count, extra_pages; + unsigned int c; + pthread_t th; + char *mem; + int ret; + + if (pthread_barrier_init(&start_barrier, NULL, nthreads + 1)) + ksft_exit_fail_msg("pthread_barrier_init\n"); + + if (pthread_barrier_init(&end_barrier, NULL, nthreads + 1)) + ksft_exit_fail_msg("pthread_barrier_init\n"); + + mem = mmap(NULL, 0x1000 * nthreads * pages_per_thread, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("Error mmap %s.\n", strerror(errno)); + + wp_init(mem, 0x1000 * nthreads * pages_per_thread); + wp_addr_range(mem, 0x1000 * nthreads * pages_per_thread); + + 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 %u\n", __func__, count); + count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); + ksft_test_result(count == 0, "%s count %u\n", __func__, count); + + finish = 0; + for (i = 0; i < nthreads; ++i) + pthread_create(&th, NULL, thread_proc, mem + 0x1000 * i * pages_per_thread); + + extra_pages = 0; + for (i = 0; i < iter_count; ++i) { + count = 0; + + ret = pthread_barrier_wait(&start_barrier); + if (ret && ret != PTHREAD_BARRIER_SERIAL_THREAD) + ksft_exit_fail_msg("pthread_barrier_wait\n"); + + count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, + page_size); + + ret = pthread_barrier_wait(&end_barrier); + if (ret && ret != PTHREAD_BARRIER_SERIAL_THREAD) + ksft_exit_fail_msg("pthread_barrier_wait\n"); + + if (count > nthreads * access_per_thread) + 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); + count += c; + + if (c > nthreads * access_per_thread) { + ksft_test_result_fail(" %s count > nthreads\n", __func__); + return; + } + + if (count != nthreads * access_per_thread) { + /* + * The purpose of the test is to make sure that no page updates are lost + * when the page updates and read-resetting soft dirty flags are performed + * in parallel. However, it is possible that the application will get the + * soft dirty flags twice on the two consecutive read-resets. This seems + * unavoidable as soft dirty flag is handled in software through page faults + * in kernel. While the updating the flags is supposed to be synchronized + * between page fault handling and read-reset, it is possible that + * read-reset happens after page fault PTE update but before the application + * re-executes write instruction. So read-reset gets the flag, clears write + * access and application gets page fault again for the same write. + */ + if (count < nthreads * access_per_thread) { + ksft_test_result_fail("Lost update, iter %u, %u vs %u.\n", i, count, + nthreads * access_per_thread); + return; + } + + extra_pages += count - nthreads * access_per_thread; + } + } + + pthread_barrier_wait(&start_barrier); + finish = 1; + pthread_barrier_wait(&end_barrier); + + 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); +} + +void zeropfn_tests(void) +{ + unsigned long long mem_size; + struct page_region vec; + int i, ret; + char *mmap_mem, *mem; + + /* Test with normal memory */ + mem_size = 10 * page_size; + mem = mmap(NULL, mem_size, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + + /* Touch each page to ensure it's mapped */ + for (i = 0; i < mem_size; i += page_size) + (void)((volatile char *)mem)[i]; + + ret = pagemap_ioctl(mem, mem_size, &vec, 1, 0, + (mem_size / page_size), PAGE_IS_PFNZERO, 0, 0, PAGE_IS_PFNZERO); + if (ret < 0) + ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + + ksft_test_result(ret == 1 && LEN(vec) == (mem_size / page_size), + "%s all pages must have PFNZERO set\n", __func__); + + munmap(mem, mem_size); + + /* Test with huge page if user_zero_page is set to 1 */ + if (!detect_huge_zeropage()) { + ksft_test_result_skip("%s use_zero_page not supported or set to 1\n", __func__); + return; + } + + mem_size = 2 * hpage_size; + mmap_mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (mmap_mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + + /* We need a THP-aligned memory area. */ + mem = (char *)(((uintptr_t)mmap_mem + hpage_size) & ~(hpage_size - 1)); + + ret = madvise(mem, hpage_size, MADV_HUGEPAGE); + if (!ret) { + FORCE_READ(*mem); + + ret = pagemap_ioctl(mem, hpage_size, &vec, 1, 0, + 0, PAGE_IS_PFNZERO, 0, 0, PAGE_IS_PFNZERO); + if (ret < 0) + ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + + ksft_test_result(ret == 1 && LEN(vec) == (hpage_size / page_size), + "%s all huge pages must have PFNZERO set\n", __func__); + } else { + ksft_test_result_skip("%s huge page not supported\n", __func__); + } + + munmap(mmap_mem, mem_size); +} + +int main(int __attribute__((unused)) argc, char *argv[]) +{ + int shmid, buf_size, fd, i, ret; + unsigned long long mem_size; + char *mem, *map, *fmem; + struct stat sbuf; + + progname = argv[0]; + + ksft_print_header(); + + if (init_uffd()) + ksft_exit_pass(); + + ksft_set_plan(117); + + page_size = getpagesize(); + hpage_size = read_pmd_pagesize(); + + pagemap_fd = open(PAGEMAP, O_RDONLY); + if (pagemap_fd < 0) + return -EINVAL; + + /* 1. Sanity testing */ + sanity_tests_sd(); + + /* 2. Normal page testing */ + mem_size = 10 * page_size; + mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + base_tests("Page testing:", mem, mem_size, 0); + + wp_free(mem, mem_size); + munmap(mem, mem_size); + + /* 3. Large page testing */ + mem_size = 512 * 10 * page_size; + mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + base_tests("Large Page testing:", mem, mem_size, 0); + + wp_free(mem, mem_size); + munmap(mem, mem_size); + + /* 4. Huge page testing */ + map = gethugepage(hpage_size); + if (map) { + wp_init(map, hpage_size); + wp_addr_range(map, hpage_size); + base_tests("Huge page testing:", map, hpage_size, 0); + wp_free(map, hpage_size); + free(map); + } else { + base_tests("Huge page testing:", NULL, 0, 1); + } + + /* 5. SHM Hugetlb page testing */ + mem_size = 2*1024*1024; + mem = gethugetlb_mem(mem_size, &shmid); + if (mem) { + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + base_tests("Hugetlb shmem testing:", mem, mem_size, 0); + + wp_free(mem, mem_size); + shmctl(shmid, IPC_RMID, NULL); + } else { + base_tests("Hugetlb shmem testing:", NULL, 0, 1); + } + + /* 6. Hugetlb page testing */ + mem = gethugetlb_mem(mem_size, NULL); + if (mem) { + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + base_tests("Hugetlb mem testing:", mem, mem_size, 0); + + wp_free(mem, mem_size); + } else { + base_tests("Hugetlb mem testing:", NULL, 0, 1); + } + + /* 7. File Hugetlb testing */ + mem_size = 2*1024*1024; + fd = memfd_create("uffd-test", MFD_HUGETLB | MFD_NOEXEC_SEAL); + if (fd < 0) + ksft_exit_fail_msg("uffd-test creation failed %d %s\n", errno, strerror(errno)); + mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (mem != MAP_FAILED) { + wp_init(mem, mem_size); + wp_addr_range(mem, mem_size); + + base_tests("Hugetlb shmem testing:", mem, mem_size, 0); + + wp_free(mem, mem_size); + shmctl(shmid, IPC_RMID, NULL); + } else { + base_tests("Hugetlb shmem testing:", NULL, 0, 1); + } + close(fd); + + /* 8. File memory testing */ + buf_size = page_size * 10; + + fd = open(__FILE__".tmp0", O_RDWR | O_CREAT, 0777); + if (fd < 0) + ksft_exit_fail_msg("Create and read/write to a memory mapped file: %s\n", + strerror(errno)); + + for (i = 0; i < buf_size; i++) + if (write(fd, "c", 1) < 0) + ksft_exit_fail_msg("Create and read/write to a memory mapped file\n"); + + ret = stat(__FILE__".tmp0", &sbuf); + if (ret < 0) + ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + + fmem = mmap(NULL, sbuf.st_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + if (fmem == MAP_FAILED) + ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno)); + + wp_init(fmem, sbuf.st_size); + wp_addr_range(fmem, sbuf.st_size); + + base_tests("File memory testing:", fmem, sbuf.st_size, 0); + + wp_free(fmem, sbuf.st_size); + munmap(fmem, sbuf.st_size); + close(fd); + + /* 9. File memory testing */ + buf_size = page_size * 10; + + fd = memfd_create(__FILE__".tmp00", MFD_NOEXEC_SEAL); + if (fd < 0) + ksft_exit_fail_msg("Create and read/write to a memory mapped file: %s\n", + strerror(errno)); + + if (ftruncate(fd, buf_size)) + ksft_exit_fail_msg("Error ftruncate\n"); + + for (i = 0; i < buf_size; i++) + if (write(fd, "c", 1) < 0) + ksft_exit_fail_msg("Create and read/write to a memory mapped file\n"); + + fmem = mmap(NULL, buf_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + if (fmem == MAP_FAILED) + ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno)); + + wp_init(fmem, buf_size); + wp_addr_range(fmem, buf_size); + + base_tests("File anonymous memory testing:", fmem, buf_size, 0); + + wp_free(fmem, buf_size); + munmap(fmem, buf_size); + close(fd); + + /* 10. Huge page tests */ + hpage_unit_tests(); + + /* 11. Iterative test */ + test_simple(); + + /* 12. Mprotect test */ + mprotect_tests(); + + /* 13. Transact test */ + transact_test(page_size); + + /* 14. Sanity testing */ + sanity_tests(); + + /*15. Unmapped address test */ + unmapped_region_tests(); + + /* 16. Userfaultfd tests */ + userfaultfd_tests(); + + /* 17. ZEROPFN tests */ + zeropfn_tests(); + + close(pagemap_fd); + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/mm/pfnmap.c b/tools/testing/selftests/mm/pfnmap.c new file mode 100644 index 000000000000..f546dfb10cae --- /dev/null +++ b/tools/testing/selftests/mm/pfnmap.c @@ -0,0 +1,269 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Basic VM_PFNMAP tests relying on mmap() of input file provided. + * Use '/dev/mem' as default. + * + * Copyright 2025, Red Hat, Inc. + * + * Author(s): David Hildenbrand <david@redhat.com> + */ +#define _GNU_SOURCE +#include <stdlib.h> +#include <string.h> +#include <stdint.h> +#include <unistd.h> +#include <errno.h> +#include <stdio.h> +#include <ctype.h> +#include <fcntl.h> +#include <signal.h> +#include <setjmp.h> +#include <linux/mman.h> +#include <sys/mman.h> +#include <sys/wait.h> + +#include "kselftest_harness.h" +#include "vm_util.h" + +static sigjmp_buf sigjmp_buf_env; +static char *file = "/dev/mem"; + +static void signal_handler(int sig) +{ + siglongjmp(sigjmp_buf_env, -EFAULT); +} + +static int test_read_access(char *addr, size_t size, size_t pagesize) +{ + size_t offs; + int ret; + + if (signal(SIGSEGV, signal_handler) == SIG_ERR) + return -EINVAL; + + ret = sigsetjmp(sigjmp_buf_env, 1); + if (!ret) { + for (offs = 0; offs < size; offs += pagesize) + /* Force a read that the compiler cannot optimize out. */ + *((volatile char *)(addr + offs)); + } + if (signal(SIGSEGV, SIG_DFL) == SIG_ERR) + return -EINVAL; + + return ret; +} + +static int find_ram_target(off_t *offset, + unsigned long long pagesize) +{ + unsigned long long start, end; + char line[80], *end_ptr; + FILE *file; + + /* Search /proc/iomem for the first suitable "System RAM" range. */ + file = fopen("/proc/iomem", "r"); + if (!file) + return -errno; + + while (fgets(line, sizeof(line), file)) { + /* Ignore any child nodes. */ + if (!isalnum(line[0])) + continue; + + if (!strstr(line, "System RAM\n")) + continue; + + start = strtoull(line, &end_ptr, 16); + /* Skip over the "-" */ + end_ptr++; + /* Make end "exclusive". */ + end = strtoull(end_ptr, NULL, 16) + 1; + + /* Actual addresses are not exported */ + if (!start && !end) + break; + + /* We need full pages. */ + start = (start + pagesize - 1) & ~(pagesize - 1); + end &= ~(pagesize - 1); + + if (start != (off_t)start) + break; + + /* We need two pages. */ + if (end > start + 2 * pagesize) { + fclose(file); + *offset = start; + return 0; + } + } + return -ENOENT; +} + +FIXTURE(pfnmap) +{ + off_t offset; + size_t pagesize; + int dev_mem_fd; + char *addr1; + size_t size1; + char *addr2; + size_t size2; +}; + +FIXTURE_SETUP(pfnmap) +{ + self->pagesize = getpagesize(); + + if (strncmp(file, "/dev/mem", strlen("/dev/mem")) == 0) { + /* We'll require two physical pages throughout our tests ... */ + if (find_ram_target(&self->offset, self->pagesize)) + SKIP(return, + "Cannot find ram target in '/proc/iomem'\n"); + } else { + self->offset = 0; + } + + self->dev_mem_fd = open(file, O_RDONLY); + if (self->dev_mem_fd < 0) + SKIP(return, "Cannot open '%s'\n", file); + + self->size1 = self->pagesize * 2; + self->addr1 = mmap(NULL, self->size1, PROT_READ, MAP_SHARED, + self->dev_mem_fd, self->offset); + if (self->addr1 == MAP_FAILED) + SKIP(return, "Cannot mmap '%s'\n", file); + + if (!check_vmflag_pfnmap(self->addr1)) + SKIP(return, "Invalid file: '%s'. Not pfnmap'ed\n", file); + + /* ... and want to be able to read from them. */ + if (test_read_access(self->addr1, self->size1, self->pagesize)) + SKIP(return, "Cannot read-access mmap'ed '%s'\n", file); + + self->size2 = 0; + self->addr2 = MAP_FAILED; +} + +FIXTURE_TEARDOWN(pfnmap) +{ + if (self->addr2 != MAP_FAILED) + munmap(self->addr2, self->size2); + if (self->addr1 != MAP_FAILED) + munmap(self->addr1, self->size1); + if (self->dev_mem_fd >= 0) + close(self->dev_mem_fd); +} + +TEST_F(pfnmap, madvise_disallowed) +{ + int advices[] = { + MADV_DONTNEED, + MADV_DONTNEED_LOCKED, + MADV_FREE, + MADV_WIPEONFORK, + MADV_COLD, + MADV_PAGEOUT, + MADV_POPULATE_READ, + MADV_POPULATE_WRITE, + }; + int i; + + /* All these advices must be rejected. */ + for (i = 0; i < ARRAY_SIZE(advices); i++) { + EXPECT_LT(madvise(self->addr1, self->pagesize, advices[i]), 0); + EXPECT_EQ(errno, EINVAL); + } +} + +TEST_F(pfnmap, munmap_split) +{ + /* + * Unmap the first page. This munmap() call is not really expected to + * fail, but we might be able to trigger other internal issues. + */ + ASSERT_EQ(munmap(self->addr1, self->pagesize), 0); + + /* + * Remap the first page while the second page is still mapped. This + * makes sure that any PAT tracking on x86 will allow for mmap()'ing + * a page again while some parts of the first mmap() are still + * around. + */ + self->size2 = self->pagesize; + self->addr2 = mmap(NULL, self->pagesize, PROT_READ, MAP_SHARED, + self->dev_mem_fd, self->offset); + ASSERT_NE(self->addr2, MAP_FAILED); +} + +TEST_F(pfnmap, mremap_fixed) +{ + char *ret; + + /* Reserve a destination area. */ + self->size2 = self->size1; + self->addr2 = mmap(NULL, self->size2, PROT_READ, MAP_ANON | MAP_PRIVATE, + -1, 0); + ASSERT_NE(self->addr2, MAP_FAILED); + + /* mremap() over our destination. */ + ret = mremap(self->addr1, self->size1, self->size2, + MREMAP_FIXED | MREMAP_MAYMOVE, self->addr2); + ASSERT_NE(ret, MAP_FAILED); +} + +TEST_F(pfnmap, mremap_shrink) +{ + char *ret; + + /* Shrinking is expected to work. */ + ret = mremap(self->addr1, self->size1, self->size1 - self->pagesize, 0); + ASSERT_NE(ret, MAP_FAILED); +} + +TEST_F(pfnmap, mremap_expand) +{ + /* + * Growing is not expected to work, and getting it right would + * be challenging. So this test primarily serves as an early warning + * that something that probably should never work suddenly works. + */ + self->size2 = self->size1 + self->pagesize; + self->addr2 = mremap(self->addr1, self->size1, self->size2, MREMAP_MAYMOVE); + ASSERT_EQ(self->addr2, MAP_FAILED); +} + +TEST_F(pfnmap, fork) +{ + pid_t pid; + int ret; + + /* fork() a child and test if the child can access the pages. */ + pid = fork(); + ASSERT_GE(pid, 0); + + if (!pid) { + EXPECT_EQ(test_read_access(self->addr1, self->size1, + self->pagesize), 0); + exit(0); + } + + wait(&ret); + if (WIFEXITED(ret)) + ret = WEXITSTATUS(ret); + else + ret = -EINVAL; + ASSERT_EQ(ret, 0); +} + +int main(int argc, char **argv) +{ + for (int i = 1; i < argc; i++) { + if (strcmp(argv[i], "--") == 0) { + if (i + 1 < argc && strlen(argv[i + 1]) > 0) + file = argv[i + 1]; + return test_harness_run(i, argv); + } + } + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/mm/pkey-arm64.h b/tools/testing/selftests/mm/pkey-arm64.h new file mode 100644 index 000000000000..8e9685e03c44 --- /dev/null +++ b/tools/testing/selftests/mm/pkey-arm64.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Arm Ltd. + */ + +#ifndef _PKEYS_ARM64_H +#define _PKEYS_ARM64_H + +#include "vm_util.h" +/* for signal frame parsing */ +#include "../arm64/signal/testcases/testcases.h" + +#ifndef SYS_mprotect_key +# define SYS_mprotect_key 288 +#endif +#ifndef SYS_pkey_alloc +# define SYS_pkey_alloc 289 +# define SYS_pkey_free 290 +#endif +#define MCONTEXT_IP(mc) mc.pc +#define MCONTEXT_TRAPNO(mc) -1 + +#define PKEY_MASK 0xf + +#define POE_NONE 0x0 +#define POE_X 0x2 +#define POE_RX 0x3 +#define POE_RWX 0x7 + +#define NR_PKEYS 8 +#define NR_RESERVED_PKEYS 1 /* pkey-0 */ + +#define PKEY_REG_ALLOW_ALL 0x77777777 +#define PKEY_REG_ALLOW_NONE 0x0 + +#define PKEY_BITS_PER_PKEY 4 +#define PAGE_SIZE sysconf(_SC_PAGESIZE) +#undef HPAGE_SIZE +#define HPAGE_SIZE default_huge_page_size() + +/* 4-byte instructions * 16384 = 64K page */ +#define __page_o_noops() asm(".rept 16384 ; nop; .endr") + +static inline u64 __read_pkey_reg(void) +{ + u64 pkey_reg = 0; + + // POR_EL0 + asm volatile("mrs %0, S3_3_c10_c2_4" : "=r" (pkey_reg)); + + return pkey_reg; +} + +static inline void __write_pkey_reg(u64 pkey_reg) +{ + u64 por = pkey_reg; + + dprintf4("%s() changing %016llx to %016llx\n", + __func__, __read_pkey_reg(), pkey_reg); + + // POR_EL0 + asm volatile("msr S3_3_c10_c2_4, %0\nisb" :: "r" (por) :); + + dprintf4("%s() pkey register after changing %016llx to %016llx\n", + __func__, __read_pkey_reg(), pkey_reg); +} + +static inline int cpu_has_pkeys(void) +{ + /* No simple way to determine this */ + return 1; +} + +static inline u32 pkey_bit_position(int pkey) +{ + return pkey * PKEY_BITS_PER_PKEY; +} + +static inline int get_arch_reserved_keys(void) +{ + return NR_RESERVED_PKEYS; +} + +static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) +{ +} + +static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +{ + return PTR_ERR_ENOTSUP; +} + +#define set_pkey_bits set_pkey_bits +static inline u64 set_pkey_bits(u64 reg, int pkey, u64 flags) +{ + u32 shift = pkey_bit_position(pkey); + u64 new_val = POE_RWX; + + /* mask out bits from pkey in old value */ + reg &= ~((u64)PKEY_MASK << shift); + + if (flags & PKEY_DISABLE_ACCESS) + new_val = POE_X; + else if (flags & PKEY_DISABLE_WRITE) + new_val = POE_RX; + + /* OR in new bits for pkey */ + reg |= new_val << shift; + + return reg; +} + +#define get_pkey_bits get_pkey_bits +static inline u64 get_pkey_bits(u64 reg, int pkey) +{ + u32 shift = pkey_bit_position(pkey); + /* + * shift down the relevant bits to the lowest four, then + * mask off all the other higher bits + */ + u32 perm = (reg >> shift) & PKEY_MASK; + + if (perm == POE_X) + return PKEY_DISABLE_ACCESS; + if (perm == POE_RX) + return PKEY_DISABLE_WRITE; + return 0; +} + +static inline void aarch64_write_signal_pkey(ucontext_t *uctxt, u64 pkey) +{ + struct _aarch64_ctx *ctx = GET_UC_RESV_HEAD(uctxt); + struct poe_context *poe_ctx = + (struct poe_context *) get_header(ctx, POE_MAGIC, + sizeof(uctxt->uc_mcontext), NULL); + if (poe_ctx) + poe_ctx->por_el0 = pkey; +} + +#endif /* _PKEYS_ARM64_H */ diff --git a/tools/testing/selftests/mm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h index 92f3be3dd8e5..7c29f075e40b 100644 --- a/tools/testing/selftests/mm/pkey-helpers.h +++ b/tools/testing/selftests/mm/pkey-helpers.h @@ -13,28 +13,29 @@ #include <ucontext.h> #include <sys/mman.h> -#include "../kselftest.h" +#include <linux/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; #ifdef __GNUC__ -__attribute__((format(printf, 1, 2))) +__printf(1, 2) #endif static inline void sigsafe_printf(const char *format, ...) { @@ -79,10 +80,19 @@ extern void abort_hooks(void); } \ } while (0) -__attribute__((noinline)) int read_ptr(int *ptr); -void expected_pkey_fault(int pkey); +#define barrier() __asm__ __volatile__("": : :"memory") +#ifndef noinline +# define noinline __attribute__((noinline)) +#endif + 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); @@ -91,12 +101,24 @@ void record_pkey_malloc(void *ptr, long size, int prot); #include "pkey-x86.h" #elif defined(__powerpc64__) /* arch */ #include "pkey-powerpc.h" +#elif defined(__aarch64__) /* arch */ +#include "pkey-arm64.h" #else /* arch */ #error Architecture not supported #endif /* arch */ +#ifndef PKEY_MASK #define PKEY_MASK (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE) +#endif + +/* + * FIXME: Remove once the generic PKEY_UNRESTRICTED definition is merged. + */ +#ifndef PKEY_UNRESTRICTED +#define PKEY_UNRESTRICTED 0x0 +#endif +#ifndef set_pkey_bits static inline u64 set_pkey_bits(u64 reg, int pkey, u64 flags) { u32 shift = pkey_bit_position(pkey); @@ -106,7 +128,9 @@ static inline u64 set_pkey_bits(u64 reg, int pkey, u64 flags) reg |= (flags & PKEY_MASK) << shift; return reg; } +#endif +#ifndef get_pkey_bits static inline u64 get_pkey_bits(u64 reg, int pkey) { u32 shift = pkey_bit_position(pkey); @@ -116,6 +140,7 @@ static inline u64 get_pkey_bits(u64 reg, int pkey) */ return ((reg >> shift) & PKEY_MASK); } +#endif extern u64 shadow_pkey_reg; @@ -145,38 +170,6 @@ 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) \ @@ -198,7 +191,7 @@ static inline u32 *siginfo_get_pkey_ptr(siginfo_t *si) static inline int kernel_has_pkeys(void) { /* try allocating a key and see if it succeeds */ - int ret = sys_pkey_alloc(0, 0); + int ret = sys_pkey_alloc(0, PKEY_UNRESTRICTED); if (ret <= 0) { return 0; } diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h index ae5df26104e5..17bf2d1b0192 100644 --- a/tools/testing/selftests/mm/pkey-powerpc.h +++ b/tools/testing/selftests/mm/pkey-powerpc.h @@ -3,12 +3,17 @@ #ifndef _PKEYS_POWERPC_H #define _PKEYS_POWERPC_H +#include <sys/stat.h> + #ifndef SYS_pkey_alloc # define SYS_pkey_alloc 384 # define SYS_pkey_free 385 #endif #define REG_IP_IDX PT_NIP +#define MCONTEXT_IP(mc) mc.gp_regs[REG_IP_IDX] +#define MCONTEXT_TRAPNO(mc) mc.gp_regs[REG_TRAPNO] #define REG_TRAPNO PT_TRAP +#define MCONTEXT_FPREGS #define gregs gp_regs #define fpregs fp_regs #define si_pkey_offset 0x20 @@ -88,7 +93,7 @@ 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 @@ -99,10 +104,20 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey) return; } +#define REPEAT_8(s) s s s s s s s s +#define REPEAT_64(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) \ + REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) +#define REPEAT_512(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) \ + REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) +#define REPEAT_4096(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) \ + REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) +#define REPEAT_16384(s) REPEAT_4096(s) REPEAT_4096(s) \ + REPEAT_4096(s) REPEAT_4096(s) + /* 4-byte instructions * 16384 = 64K page */ -#define __page_o_noops() asm(".rept 16384 ; nop; .endr") +#define __page_o_noops() asm(REPEAT_16384("nop\n")) -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 814758e109c0..f7ecd335df1e 100644 --- a/tools/testing/selftests/mm/pkey-x86.h +++ b/tools/testing/selftests/mm/pkey-x86.h @@ -15,6 +15,10 @@ #endif +#define MCONTEXT_IP(mc) mc.gregs[REG_IP_IDX] +#define MCONTEXT_TRAPNO(mc) mc.gregs[REG_TRAPNO] +#define MCONTEXT_FPREGS + #ifndef PKEY_DISABLE_ACCESS # define PKEY_DISABLE_ACCESS 0x1 #endif @@ -30,6 +34,8 @@ #define PAGE_SIZE 4096 #define MB (1<<20) +#define PKEY_REG_ALLOW_NONE 0x55555555 + static inline void __page_o_noops(void) { /* 8-bytes of instruction * 512 bytes = 1 page */ @@ -107,7 +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; @@ -142,7 +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; @@ -151,7 +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 new file mode 100644 index 000000000000..302fef54049c --- /dev/null +++ b/tools/testing/selftests/mm/pkey_sighandler_tests.c @@ -0,0 +1,546 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Tests Memory Protection Keys (see Documentation/core-api/protection-keys.rst) + * + * The testcases in this file exercise various flows related to signal handling, + * using an alternate signal stack, with the default pkey (pkey 0) disabled. + * + * Compile with: + * gcc -mxsave -o pkey_sighandler_tests -O2 -g -std=gnu99 -pthread -Wall pkey_sighandler_tests.c -I../../../../tools/include -lrt -ldl -lm + * gcc -mxsave -m32 -o pkey_sighandler_tests -O2 -g -std=gnu99 -pthread -Wall pkey_sighandler_tests.c -I../../../../tools/include -lrt -ldl -lm + */ +#define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ +#include <linux/mman.h> +#include <errno.h> +#include <sys/syscall.h> +#include <string.h> +#include <stdio.h> +#include <stdint.h> +#include <stdbool.h> +#include <signal.h> +#include <assert.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <pthread.h> +#include <limits.h> + +#include "pkey-helpers.h" + +#define STACK_SIZE PTHREAD_STACK_MIN + +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 + * syscall will attempt to access the PLT in order to call a library function + * which is protected by MPK 0 which we don't have access to. + */ +static __always_inline +long syscall_raw(long n, long a1, long a2, long a3, long a4, long a5, long a6) +{ + unsigned long ret; +#ifdef __x86_64__ + register long r10 asm("r10") = a4; + register long r8 asm("r8") = a5; + register long r9 asm("r9") = a6; + asm volatile ("syscall" + : "=a"(ret) + : "a"(n), "D"(a1), "S"(a2), "d"(a3), "r"(r10), "r"(r8), "r"(r9) + : "rcx", "r11", "memory"); +#elif defined __i386__ + asm volatile ("int $0x80" + : "=a"(ret) + : "a"(n), "b"(a1), "c"(a2), "d"(a3), "S"(a4), "D"(a5) + : "memory"); +#elif defined __aarch64__ + register long x0 asm("x0") = a1; + register long x1 asm("x1") = a2; + register long x2 asm("x2") = a3; + register long x3 asm("x3") = a4; + register long x4 asm("x4") = a5; + register long x5 asm("x5") = a6; + register long x8 asm("x8") = n; + asm volatile ("svc #0" + : "=r"(x0) + : "r"(x0), "r"(x1), "r"(x2), "r"(x3), "r"(x4), "r"(x5), "r"(x8) + : "memory"); + ret = x0; +#else +# error syscall_raw() not implemented +#endif + return ret; +} + +static inline long clone_raw(unsigned long flags, void *stack, + int *parent_tid, int *child_tid) +{ + long a1 = flags; + long a2 = (long)stack; + long a3 = (long)parent_tid; +#if defined(__x86_64__) || defined(__i386) + long a4 = (long)child_tid; + long a5 = 0; +#elif defined(__aarch64__) + long a4 = 0; + long a5 = (long)child_tid; +#else +# error clone_raw() not implemented +#endif + + return syscall_raw(SYS_clone, a1, a2, a3, a4, a5, 0); +} + +/* + * Returns the most restrictive pkey register value that can be used by the + * tests. + */ +static inline u64 pkey_reg_restrictive_default(void) +{ + /* + * Disallow everything except execution on pkey 0, so that each caller + * doesn't need to enable it explicitly (the selftest code runs with + * its code mapped with pkey 0). + */ + return set_pkey_bits(PKEY_REG_ALLOW_NONE, 0, PKEY_DISABLE_ACCESS); +} + +static void sigsegv_handler(int signo, siginfo_t *info, void *ucontext) +{ + pthread_mutex_lock(&mutex); + + memcpy(&siginfo, info, sizeof(siginfo_t)); + + pthread_cond_signal(&cond); + pthread_mutex_unlock(&mutex); + + syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); +} + +static void sigusr1_handler(int signo, siginfo_t *info, void *ucontext) +{ + pthread_mutex_lock(&mutex); + + memcpy(&siginfo, info, sizeof(siginfo_t)); + + pthread_cond_signal(&cond); + pthread_mutex_unlock(&mutex); +} + +static void sigusr2_handler(int signo, siginfo_t *info, void *ucontext) +{ + /* + * pkru should be the init_pkru value which enabled MPK 0 so + * we can use library functions. + */ + printf("%s invoked.\n", __func__); +} + +static void raise_sigusr2(void) +{ + pid_t tid = 0; + + tid = syscall_raw(SYS_gettid, 0, 0, 0, 0, 0, 0); + + syscall_raw(SYS_tkill, tid, SIGUSR2, 0, 0, 0, 0); + + /* + * We should return from the signal handler here and be able to + * return to the interrupted thread. + */ +} + +static void *thread_segv_with_pkey0_disabled(void *ptr) +{ + /* Disable MPK 0 (and all others too) */ + __write_pkey_reg(pkey_reg_restrictive_default()); + + /* Segfault (with SEGV_MAPERR) */ + *(volatile int *)NULL = 1; + return NULL; +} + +static void *thread_segv_pkuerr_stack(void *ptr) +{ + /* Disable MPK 0 (and all others too) */ + __write_pkey_reg(pkey_reg_restrictive_default()); + + /* After we disable MPK 0, we can't access the stack to return */ + return NULL; +} + +static void *thread_segv_maperr_ptr(void *ptr) +{ + stack_t *stack = ptr; + u64 pkey_reg; + + /* + * Setup alternate signal stack, which should be pkey_mprotect()ed by + * MPK 0. The thread's stack cannot be used for signals because it is + * not accessible by the default init_pkru value of 0x55555554. + */ + syscall_raw(SYS_sigaltstack, (long)stack, 0, 0, 0, 0, 0); + + /* Disable MPK 0. Only MPK 1 is enabled. */ + pkey_reg = pkey_reg_restrictive_default(); + pkey_reg = set_pkey_bits(pkey_reg, 1, PKEY_UNRESTRICTED); + __write_pkey_reg(pkey_reg); + + /* Segfault */ + *(volatile int *)NULL = 1; + syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); + return NULL; +} + +/* + * Verify that the sigsegv handler is invoked when pkey 0 is disabled. + * Note that the new thread stack and the alternate signal stack is + * protected by MPK 0. + */ +static void test_sigsegv_handler_with_pkey0_disabled(void) +{ + struct sigaction sa; + pthread_attr_t attr; + pthread_t thr; + + sa.sa_flags = SA_SIGINFO; + + sa.sa_sigaction = sigsegv_handler; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGSEGV, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + memset(&siginfo, 0, sizeof(siginfo)); + + pthread_attr_init(&attr); + pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED); + + pthread_create(&thr, &attr, thread_segv_with_pkey0_disabled, NULL); + + pthread_mutex_lock(&mutex); + while (siginfo.si_signo == 0) + pthread_cond_wait(&cond, &mutex); + pthread_mutex_unlock(&mutex); + + ksft_test_result(siginfo.si_signo == SIGSEGV && + siginfo.si_code == SEGV_MAPERR && + siginfo.si_addr == NULL, + "%s\n", __func__); +} + +/* + * Verify that the sigsegv handler is invoked when pkey 0 is disabled. + * Note that the new thread stack and the alternate signal stack is + * protected by MPK 0, which renders them inaccessible when MPK 0 + * is disabled. So just the return from the thread should cause a + * segfault with SEGV_PKUERR. + */ +static void test_sigsegv_handler_cannot_access_stack(void) +{ + struct sigaction sa; + pthread_attr_t attr; + pthread_t thr; + + sa.sa_flags = SA_SIGINFO; + + sa.sa_sigaction = sigsegv_handler; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGSEGV, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + memset(&siginfo, 0, sizeof(siginfo)); + + pthread_attr_init(&attr); + pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED); + + pthread_create(&thr, &attr, thread_segv_pkuerr_stack, NULL); + + pthread_mutex_lock(&mutex); + while (siginfo.si_signo == 0) + pthread_cond_wait(&cond, &mutex); + pthread_mutex_unlock(&mutex); + + ksft_test_result(siginfo.si_signo == SIGSEGV && + siginfo.si_code == SEGV_PKUERR, + "%s\n", __func__); +} + +/* + * Verify that the sigsegv handler that uses an alternate signal stack + * is correctly invoked for a thread which uses a non-zero MPK to protect + * its own stack, and disables all other MPKs (including 0). + */ +static void test_sigsegv_handler_with_different_pkey_for_stack(void) +{ + struct sigaction sa; + static stack_t sigstack; + void *stack; + int pkey; + int parent_pid = 0; + int child_pid = 0; + u64 pkey_reg; + + sa.sa_flags = SA_SIGINFO | SA_ONSTACK; + + sa.sa_sigaction = sigsegv_handler; + + sigemptyset(&sa.sa_mask); + if (sigaction(SIGSEGV, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + stack = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + assert(stack != MAP_FAILED); + + /* Allow access to MPK 0 and MPK 1 */ + pkey_reg = pkey_reg_restrictive_default(); + pkey_reg = set_pkey_bits(pkey_reg, 0, PKEY_UNRESTRICTED); + pkey_reg = set_pkey_bits(pkey_reg, 1, PKEY_UNRESTRICTED); + __write_pkey_reg(pkey_reg); + + /* Protect the new stack with MPK 1 */ + pkey = sys_pkey_alloc(0, PKEY_UNRESTRICTED); + 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, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + sigstack.ss_flags = 0; + sigstack.ss_size = STACK_SIZE; + + memset(&siginfo, 0, sizeof(siginfo)); + + /* Use clone to avoid newer glibcs using rseq on new threads */ + long ret = clone_raw(CLONE_VM | CLONE_FS | CLONE_FILES | + CLONE_SIGHAND | CLONE_THREAD | CLONE_SYSVSEM | + CLONE_PARENT_SETTID | CLONE_CHILD_CLEARTID | + CLONE_DETACHED, + stack + STACK_SIZE, + &parent_pid, + &child_pid); + + if (ret < 0) { + errno = -ret; + perror("clone"); + } else if (ret == 0) { + thread_segv_maperr_ptr(&sigstack); + syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); + } + + pthread_mutex_lock(&mutex); + while (siginfo.si_signo == 0) + pthread_cond_wait(&cond, &mutex); + pthread_mutex_unlock(&mutex); + + ksft_test_result(siginfo.si_signo == SIGSEGV && + siginfo.si_code == SEGV_MAPERR && + siginfo.si_addr == NULL, + "%s\n", __func__); +} + +/* + * Verify that the PKRU value set by the application is correctly + * restored upon return from signal handling. + */ +static void test_pkru_preserved_after_sigusr1(void) +{ + struct sigaction sa; + u64 pkey_reg; + + /* Allow access to MPK 0 and an arbitrary set of keys */ + pkey_reg = pkey_reg_restrictive_default(); + pkey_reg = set_pkey_bits(pkey_reg, 0, PKEY_UNRESTRICTED); + pkey_reg = set_pkey_bits(pkey_reg, 3, PKEY_UNRESTRICTED); + pkey_reg = set_pkey_bits(pkey_reg, 7, PKEY_UNRESTRICTED); + + sa.sa_flags = SA_SIGINFO; + + sa.sa_sigaction = sigusr1_handler; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGUSR1, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + memset(&siginfo, 0, sizeof(siginfo)); + + __write_pkey_reg(pkey_reg); + + raise(SIGUSR1); + + pthread_mutex_lock(&mutex); + while (siginfo.si_signo == 0) + pthread_cond_wait(&cond, &mutex); + pthread_mutex_unlock(&mutex); + + /* Ensure the pkru value is the same after returning from signal. */ + ksft_test_result(pkey_reg == __read_pkey_reg() && + siginfo.si_signo == SIGUSR1, + "%s\n", __func__); +} + +static noinline void *thread_sigusr2_self(void *ptr) +{ + /* + * A const char array like "Resuming after SIGUSR2" won't be stored on + * the stack and the code could access it via an offset from the program + * counter. This makes sure it's on the function's stack frame. + */ + char str[] = {'R', 'e', 's', 'u', 'm', 'i', 'n', 'g', ' ', + 'a', 'f', 't', 'e', 'r', ' ', + 'S', 'I', 'G', 'U', 'S', 'R', '2', + '.', '.', '.', '\n', '\0'}; + stack_t *stack = ptr; + u64 pkey_reg; + + /* + * Setup alternate signal stack, which should be pkey_mprotect()ed by + * MPK 0. The thread's stack cannot be used for signals because it is + * not accessible by the default init_pkru value of 0x55555554. + */ + syscall(SYS_sigaltstack, (long)stack, 0, 0, 0, 0, 0); + + /* Disable MPK 0. Only MPK 2 is enabled. */ + pkey_reg = pkey_reg_restrictive_default(); + pkey_reg = set_pkey_bits(pkey_reg, 2, PKEY_UNRESTRICTED); + __write_pkey_reg(pkey_reg); + + raise_sigusr2(); + + /* Do something, to show the thread resumed execution after the signal */ + syscall_raw(SYS_write, 1, (long) str, sizeof(str) - 1, 0, 0, 0); + + /* + * We can't return to test_pkru_sigreturn because it + * will attempt to use a %rbp value which is on the stack + * of the main thread. + */ + syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); + return NULL; +} + +/* + * Verify that sigreturn is able to restore altstack even if the thread had + * disabled pkey 0. + */ +static void test_pkru_sigreturn(void) +{ + struct sigaction sa = {0}; + static stack_t sigstack; + void *stack; + int pkey; + int parent_pid = 0; + int child_pid = 0; + u64 pkey_reg; + + sa.sa_handler = SIG_DFL; + sa.sa_flags = 0; + sigemptyset(&sa.sa_mask); + + /* + * For this testcase, we do not want to handle SIGSEGV. Reset handler + * to default so that the application can crash if it receives SIGSEGV. + */ + if (sigaction(SIGSEGV, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + sa.sa_flags = SA_SIGINFO | SA_ONSTACK; + sa.sa_sigaction = sigusr2_handler; + sigemptyset(&sa.sa_mask); + + if (sigaction(SIGUSR2, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + stack = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + assert(stack != MAP_FAILED); + + /* + * Allow access to MPK 0 and MPK 2. The child thread (to be created + * later in this flow) will have its stack protected by MPK 2, whereas + * the current thread's stack is protected by the default MPK 0. Hence + * both need to be enabled. + */ + pkey_reg = pkey_reg_restrictive_default(); + pkey_reg = set_pkey_bits(pkey_reg, 0, PKEY_UNRESTRICTED); + pkey_reg = set_pkey_bits(pkey_reg, 2, PKEY_UNRESTRICTED); + __write_pkey_reg(pkey_reg); + + /* Protect the stack with MPK 2 */ + pkey = sys_pkey_alloc(0, PKEY_UNRESTRICTED); + 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, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + sigstack.ss_flags = 0; + sigstack.ss_size = STACK_SIZE; + + /* Use clone to avoid newer glibcs using rseq on new threads */ + long ret = clone_raw(CLONE_VM | CLONE_FS | CLONE_FILES | + CLONE_SIGHAND | CLONE_THREAD | CLONE_SYSVSEM | + CLONE_PARENT_SETTID | CLONE_CHILD_CLEARTID | + CLONE_DETACHED, + stack + STACK_SIZE, + &parent_pid, + &child_pid); + + if (ret < 0) { + errno = -ret; + perror("clone"); + } else if (ret == 0) { + thread_sigusr2_self(&sigstack); + syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); + } + + child_pid = ret; + /* Check that thread exited */ + do { + sched_yield(); + ret = syscall_raw(SYS_tkill, child_pid, 0, 0, 0, 0, 0); + } while (ret != -ESRCH && ret != -EINVAL); + + ksft_test_result_pass("%s\n", __func__); +} + +static void (*pkey_tests[])(void) = { + test_sigsegv_handler_with_pkey0_disabled, + test_sigsegv_handler_cannot_access_stack, + test_sigsegv_handler_with_different_pkey_for_stack, + test_pkru_preserved_after_sigusr1, + test_pkru_sigreturn +}; + +int main(int argc, char *argv[]) +{ + int i; + + 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])(); + + ksft_finished(); + return 0; +} diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c new file mode 100644 index 000000000000..255b332f7a08 --- /dev/null +++ b/tools/testing/selftests/mm/pkey_util.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define __SANE_USERSPACE_TYPES__ +#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/prctl_thp_disable.c b/tools/testing/selftests/mm/prctl_thp_disable.c new file mode 100644 index 000000000000..ca27200596a4 --- /dev/null +++ b/tools/testing/selftests/mm/prctl_thp_disable.c @@ -0,0 +1,291 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Basic tests for PR_GET/SET_THP_DISABLE prctl calls + * + * Author(s): Usama Arif <usamaarif642@gmail.com> + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/mman.h> +#include <linux/mman.h> +#include <sys/prctl.h> +#include <sys/wait.h> + +#include "kselftest_harness.h" +#include "thp_settings.h" +#include "vm_util.h" + +#ifndef PR_THP_DISABLE_EXCEPT_ADVISED +#define PR_THP_DISABLE_EXCEPT_ADVISED (1 << 1) +#endif + +enum thp_collapse_type { + THP_COLLAPSE_NONE, + THP_COLLAPSE_MADV_NOHUGEPAGE, + THP_COLLAPSE_MADV_HUGEPAGE, /* MADV_HUGEPAGE before access */ + THP_COLLAPSE_MADV_COLLAPSE, /* MADV_COLLAPSE after access */ +}; + +/* + * Function to mmap a buffer, fault it in, madvise it appropriately (before + * page fault for MADV_HUGE, and after for MADV_COLLAPSE), and check if the + * mmap region is huge. + * Returns: + * 0 if test doesn't give hugepage + * 1 if test gives a hugepage + * -errno if mmap fails + */ +static int test_mmap_thp(enum thp_collapse_type madvise_buf, size_t pmdsize) +{ + char *mem, *mmap_mem; + size_t mmap_size; + int ret; + + /* For alignment purposes, we need twice the THP size. */ + mmap_size = 2 * pmdsize; + mmap_mem = (char *)mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (mmap_mem == MAP_FAILED) + return -errno; + + /* We need a THP-aligned memory area. */ + mem = (char *)(((uintptr_t)mmap_mem + pmdsize) & ~(pmdsize - 1)); + + if (madvise_buf == THP_COLLAPSE_MADV_HUGEPAGE) + madvise(mem, pmdsize, MADV_HUGEPAGE); + else if (madvise_buf == THP_COLLAPSE_MADV_NOHUGEPAGE) + madvise(mem, pmdsize, MADV_NOHUGEPAGE); + + /* Ensure memory is allocated */ + memset(mem, 1, pmdsize); + + if (madvise_buf == THP_COLLAPSE_MADV_COLLAPSE) + madvise(mem, pmdsize, MADV_COLLAPSE); + + /* HACK: make sure we have a separate VMA that we can check reliably. */ + mprotect(mem, pmdsize, PROT_READ); + + ret = check_huge_anon(mem, 1, pmdsize); + munmap(mmap_mem, mmap_size); + return ret; +} + +static void prctl_thp_disable_completely_test(struct __test_metadata *const _metadata, + size_t pmdsize, + enum thp_enabled thp_policy) +{ + ASSERT_EQ(prctl(PR_GET_THP_DISABLE, NULL, NULL, NULL, NULL), 1); + + /* tests after prctl overrides global policy */ + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 0); + + /* Reset to global policy */ + ASSERT_EQ(prctl(PR_SET_THP_DISABLE, 0, NULL, NULL, NULL), 0); + + /* tests after prctl is cleared, and only global policy is effective */ + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize), + thp_policy == THP_ALWAYS ? 1 : 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize), + thp_policy == THP_NEVER ? 0 : 1); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 1); +} + +FIXTURE(prctl_thp_disable_completely) +{ + struct thp_settings settings; + size_t pmdsize; +}; + +FIXTURE_VARIANT(prctl_thp_disable_completely) +{ + enum thp_enabled thp_policy; +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, never) +{ + .thp_policy = THP_NEVER, +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, madvise) +{ + .thp_policy = THP_MADVISE, +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, always) +{ + .thp_policy = THP_ALWAYS, +}; + +FIXTURE_SETUP(prctl_thp_disable_completely) +{ + if (!thp_available()) + SKIP(return, "Transparent Hugepages not available\n"); + + self->pmdsize = read_pmd_pagesize(); + if (!self->pmdsize) + SKIP(return, "Unable to read PMD size\n"); + + if (prctl(PR_SET_THP_DISABLE, 1, NULL, NULL, NULL)) + SKIP(return, "Unable to disable THPs completely for the process\n"); + + thp_save_settings(); + thp_read_settings(&self->settings); + self->settings.thp_enabled = variant->thp_policy; + self->settings.hugepages[sz2ord(self->pmdsize, getpagesize())].enabled = THP_INHERIT; + thp_write_settings(&self->settings); +} + +FIXTURE_TEARDOWN(prctl_thp_disable_completely) +{ + thp_restore_settings(); +} + +TEST_F(prctl_thp_disable_completely, nofork) +{ + prctl_thp_disable_completely_test(_metadata, self->pmdsize, variant->thp_policy); +} + +TEST_F(prctl_thp_disable_completely, fork) +{ + int ret = 0; + pid_t pid; + + /* Make sure prctl changes are carried across fork */ + pid = fork(); + ASSERT_GE(pid, 0); + + if (!pid) { + prctl_thp_disable_completely_test(_metadata, self->pmdsize, variant->thp_policy); + return; + } + + wait(&ret); + if (WIFEXITED(ret)) + ret = WEXITSTATUS(ret); + else + ret = -EINVAL; + ASSERT_EQ(ret, 0); +} + +static void prctl_thp_disable_except_madvise_test(struct __test_metadata *const _metadata, + size_t pmdsize, + enum thp_enabled thp_policy) +{ + ASSERT_EQ(prctl(PR_GET_THP_DISABLE, NULL, NULL, NULL, NULL), 3); + + /* tests after prctl overrides global policy */ + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize), + thp_policy == THP_NEVER ? 0 : 1); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 1); + + /* Reset to global policy */ + ASSERT_EQ(prctl(PR_SET_THP_DISABLE, 0, NULL, NULL, NULL), 0); + + /* tests after prctl is cleared, and only global policy is effective */ + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize), + thp_policy == THP_ALWAYS ? 1 : 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize), + thp_policy == THP_NEVER ? 0 : 1); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 1); +} + +FIXTURE(prctl_thp_disable_except_madvise) +{ + struct thp_settings settings; + size_t pmdsize; +}; + +FIXTURE_VARIANT(prctl_thp_disable_except_madvise) +{ + enum thp_enabled thp_policy; +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_except_madvise, never) +{ + .thp_policy = THP_NEVER, +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_except_madvise, madvise) +{ + .thp_policy = THP_MADVISE, +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_except_madvise, always) +{ + .thp_policy = THP_ALWAYS, +}; + +FIXTURE_SETUP(prctl_thp_disable_except_madvise) +{ + if (!thp_available()) + SKIP(return, "Transparent Hugepages not available\n"); + + self->pmdsize = read_pmd_pagesize(); + if (!self->pmdsize) + SKIP(return, "Unable to read PMD size\n"); + + if (prctl(PR_SET_THP_DISABLE, 1, PR_THP_DISABLE_EXCEPT_ADVISED, NULL, NULL)) + SKIP(return, "Unable to set PR_THP_DISABLE_EXCEPT_ADVISED\n"); + + thp_save_settings(); + thp_read_settings(&self->settings); + self->settings.thp_enabled = variant->thp_policy; + self->settings.hugepages[sz2ord(self->pmdsize, getpagesize())].enabled = THP_INHERIT; + thp_write_settings(&self->settings); +} + +FIXTURE_TEARDOWN(prctl_thp_disable_except_madvise) +{ + thp_restore_settings(); +} + +TEST_F(prctl_thp_disable_except_madvise, nofork) +{ + prctl_thp_disable_except_madvise_test(_metadata, self->pmdsize, variant->thp_policy); +} + +TEST_F(prctl_thp_disable_except_madvise, fork) +{ + int ret = 0; + pid_t pid; + + /* Make sure prctl changes are carried across fork */ + pid = fork(); + ASSERT_GE(pid, 0); + + if (!pid) { + prctl_thp_disable_except_madvise_test(_metadata, self->pmdsize, + variant->thp_policy); + return; + } + + wait(&ret); + if (WIFEXITED(ret)) + ret = WEXITSTATUS(ret); + else + ret = -EINVAL; + ASSERT_EQ(ret, 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/process_madv.c b/tools/testing/selftests/mm/process_madv.c new file mode 100644 index 000000000000..cd4610baf5d7 --- /dev/null +++ b/tools/testing/selftests/mm/process_madv.c @@ -0,0 +1,344 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE +#include "kselftest_harness.h" +#include <errno.h> +#include <setjmp.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <linux/mman.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <sched.h> +#include "vm_util.h" + +#include "../pidfd/pidfd.h" + +FIXTURE(process_madvise) +{ + unsigned long page_size; + pid_t child_pid; + int remote_pidfd; + int pidfd; +}; + +FIXTURE_SETUP(process_madvise) +{ + self->page_size = (unsigned long)sysconf(_SC_PAGESIZE); + self->pidfd = PIDFD_SELF; + self->remote_pidfd = -1; + self->child_pid = -1; +}; + +FIXTURE_TEARDOWN_PARENT(process_madvise) +{ + /* This teardown is guaranteed to run, even if tests SKIP or ASSERT */ + if (self->child_pid > 0) { + kill(self->child_pid, SIGKILL); + waitpid(self->child_pid, NULL, 0); + } + + if (self->remote_pidfd >= 0) + close(self->remote_pidfd); +} + +static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, + size_t vlen, int advice, unsigned int flags) +{ + return syscall(__NR_process_madvise, pidfd, iovec, vlen, advice, flags); +} + +/* + * This test uses PIDFD_SELF to target the current process. The main + * goal is to verify the basic behavior of process_madvise() with + * a vector of non-contiguous memory ranges, not its cross-process + * capabilities. + */ +TEST_F(process_madvise, basic) +{ + const unsigned long pagesize = self->page_size; + const int madvise_pages = 4; + struct iovec vec[madvise_pages]; + int pidfd = self->pidfd; + ssize_t ret; + char *map; + + /* + * Create a single large mapping. We will pick pages from this + * mapping to advise on. This ensures we test non-contiguous iovecs. + */ + map = mmap(NULL, pagesize * 10, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (map == MAP_FAILED) + SKIP(return, "mmap failed, not enough memory.\n"); + + /* Fill the entire region with a known pattern. */ + memset(map, 'A', pagesize * 10); + + /* + * Setup the iovec to point to 4 non-contiguous pages + * within the mapping. + */ + vec[0].iov_base = &map[0 * pagesize]; + vec[0].iov_len = pagesize; + vec[1].iov_base = &map[3 * pagesize]; + vec[1].iov_len = pagesize; + vec[2].iov_base = &map[5 * pagesize]; + vec[2].iov_len = pagesize; + vec[3].iov_base = &map[8 * pagesize]; + vec[3].iov_len = pagesize; + + ret = sys_process_madvise(pidfd, vec, madvise_pages, MADV_DONTNEED, 0); + if (ret == -1 && errno == EPERM) + SKIP(return, + "process_madvise() unsupported or permission denied, try running as root.\n"); + else if (errno == EINVAL) + SKIP(return, + "process_madvise() unsupported or parameter invalid, please check arguments.\n"); + + /* The call should succeed and report the total bytes processed. */ + ASSERT_EQ(ret, madvise_pages * pagesize); + + /* Check that advised pages are now zero. */ + for (int i = 0; i < madvise_pages; i++) { + char *advised_page = (char *)vec[i].iov_base; + + /* Content must be 0, not 'A'. */ + ASSERT_EQ(*advised_page, '\0'); + } + + /* Check that an un-advised page in between is still 'A'. */ + char *unadvised_page = &map[1 * pagesize]; + + for (int i = 0; i < pagesize; i++) + ASSERT_EQ(unadvised_page[i], 'A'); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize * 10), 0); +} + +/* + * This test deterministically validates process_madvise() with MADV_COLLAPSE + * on a remote process, other advices are difficult to verify reliably. + * + * The test verifies that a memory region in a child process, + * focus on process_madv remote result, only check addresses and lengths. + * The correctness of the MADV_COLLAPSE can be found in the relevant test examples in khugepaged. + */ +TEST_F(process_madvise, remote_collapse) +{ + const unsigned long pagesize = self->page_size; + long huge_page_size; + int pipe_info[2]; + ssize_t ret; + struct iovec vec; + + struct child_info { + pid_t pid; + void *map_addr; + } info; + + huge_page_size = read_pmd_pagesize(); + if (huge_page_size <= 0) + SKIP(return, "Could not determine a valid huge page size.\n"); + + ASSERT_EQ(pipe(pipe_info), 0); + + self->child_pid = fork(); + ASSERT_NE(self->child_pid, -1); + + if (self->child_pid == 0) { + char *map; + size_t map_size = 2 * huge_page_size; + + close(pipe_info[0]); + + map = mmap(NULL, map_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(map, MAP_FAILED); + + /* Fault in as small pages */ + for (size_t i = 0; i < map_size; i += pagesize) + map[i] = 'A'; + + /* Send info and pause */ + info.pid = getpid(); + info.map_addr = map; + ret = write(pipe_info[1], &info, sizeof(info)); + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[1]); + + pause(); + exit(0); + } + + close(pipe_info[1]); + + /* Receive child info */ + ret = read(pipe_info[0], &info, sizeof(info)); + if (ret <= 0) { + waitpid(self->child_pid, NULL, 0); + SKIP(return, "Failed to read child info from pipe.\n"); + } + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[0]); + self->child_pid = info.pid; + + self->remote_pidfd = syscall(__NR_pidfd_open, self->child_pid, 0); + ASSERT_GE(self->remote_pidfd, 0); + + vec.iov_base = info.map_addr; + vec.iov_len = huge_page_size; + + ret = sys_process_madvise(self->remote_pidfd, &vec, 1, MADV_COLLAPSE, + 0); + if (ret == -1) { + if (errno == EINVAL) + SKIP(return, "PROCESS_MADV_ADVISE is not supported.\n"); + else if (errno == EPERM) + SKIP(return, + "No process_madvise() permissions, try running as root.\n"); + return; + } + + ASSERT_EQ(ret, huge_page_size); +} + +/* + * Test process_madvise() with a pidfd for a process that has already + * exited to ensure correct error handling. + */ +TEST_F(process_madvise, exited_process_pidfd) +{ + const unsigned long pagesize = self->page_size; + struct iovec vec; + char *map; + ssize_t ret; + + map = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, + 0); + if (map == MAP_FAILED) + SKIP(return, "mmap failed, not enough memory.\n"); + + vec.iov_base = map; + vec.iov_len = pagesize; + + /* + * Using a pidfd for a process that has already exited should fail + * with ESRCH. + */ + self->child_pid = fork(); + ASSERT_NE(self->child_pid, -1); + + if (self->child_pid == 0) + exit(0); + + self->remote_pidfd = syscall(__NR_pidfd_open, self->child_pid, 0); + ASSERT_GE(self->remote_pidfd, 0); + + /* Wait for the child to ensure it has terminated. */ + waitpid(self->child_pid, NULL, 0); + + ret = sys_process_madvise(self->remote_pidfd, &vec, 1, MADV_DONTNEED, + 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ESRCH); +} + +/* + * Test process_madvise() with bad pidfds to ensure correct error + * handling. + */ +TEST_F(process_madvise, bad_pidfd) +{ + const unsigned long pagesize = self->page_size; + struct iovec vec; + char *map; + ssize_t ret; + + map = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, + 0); + if (map == MAP_FAILED) + SKIP(return, "mmap failed, not enough memory.\n"); + + vec.iov_base = map; + vec.iov_len = pagesize; + + /* Using an invalid fd number (-1) should fail with EBADF. */ + ret = sys_process_madvise(-1, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); + + /* + * Using a valid fd that is not a pidfd (e.g. stdin) should fail + * with EBADF. + */ + ret = sys_process_madvise(STDIN_FILENO, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); +} + +/* + * Test that process_madvise() rejects vlen > UIO_MAXIOV. + * The kernel should return -EINVAL when the number of iovecs exceeds 1024. + */ +TEST_F(process_madvise, invalid_vlen) +{ + const unsigned long pagesize = self->page_size; + int pidfd = self->pidfd; + struct iovec vec; + char *map; + ssize_t ret; + + map = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, + 0); + if (map == MAP_FAILED) + SKIP(return, "mmap failed, not enough memory.\n"); + + vec.iov_base = map; + vec.iov_len = pagesize; + + ret = sys_process_madvise(pidfd, &vec, 1025, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize), 0); +} + +/* + * Test process_madvise() with an invalid flag value. Currently, only a flag + * value of 0 is supported. This test is reserved for the future, e.g., if + * synchronous flags are added. + */ +TEST_F(process_madvise, flag) +{ + const unsigned long pagesize = self->page_size; + unsigned int invalid_flag; + int pidfd = self->pidfd; + struct iovec vec; + char *map; + ssize_t ret; + + map = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, + 0); + if (map == MAP_FAILED) + SKIP(return, "mmap failed, not enough memory.\n"); + + vec.iov_base = map; + vec.iov_len = pagesize; + + invalid_flag = 0x80000000; + + ret = sys_process_madvise(pidfd, &vec, 1, MADV_DONTNEED, invalid_flag); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 48dc151f8fca..2085982dba69 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()) @@ -147,13 +153,13 @@ void abort_hooks(void) * will then fault, which makes sure that the fault code handles * execute-only memory properly. */ -#ifdef __powerpc64__ +#if defined(__powerpc64__) || defined(__aarch64__) /* This way, both 4K and 64K alignment are maintained */ __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; @@ -207,12 +213,11 @@ 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; int pkey_rights; - u64 orig_pkey_reg = read_pkey_reg(); dprintf1("START->%s(%d, 0x%x)\n", __func__, pkey, flags); @@ -242,18 +247,15 @@ void pkey_disable_set(int pkey, int flags) dprintf1("%s(%d) pkey_reg: 0x%016llx\n", __func__, pkey, read_pkey_reg()); - if (flags) - pkey_assert(read_pkey_reg() >= orig_pkey_reg); dprintf1("END<---%s(%d, 0x%x)\n", __func__, 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; int pkey_rights = hw_pkey_get(pkey, syscall_flags); - u64 orig_pkey_reg = read_pkey_reg(); pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE)); @@ -273,23 +275,21 @@ void pkey_disable_clear(int pkey, int flags) dprintf1("%s(%d) pkey_reg: 0x%016llx\n", __func__, pkey, read_pkey_reg()); - if (flags) - assert(read_pkey_reg() <= orig_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); } @@ -307,14 +307,16 @@ 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; unsigned long ip; +#ifdef MCONTEXT_FPREGS char *fpregs; +#endif #if defined(__i386__) || defined(__x86_64__) /* arch */ u32 *pkey_reg_ptr; int pkey_reg_offset; @@ -328,9 +330,11 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) __func__, __LINE__, __read_pkey_reg(), shadow_pkey_reg); - trapno = uctxt->uc_mcontext.gregs[REG_TRAPNO]; - ip = uctxt->uc_mcontext.gregs[REG_IP_IDX]; + trapno = MCONTEXT_TRAPNO(uctxt->uc_mcontext); + ip = MCONTEXT_IP(uctxt->uc_mcontext); +#ifdef MCONTEXT_FPREGS fpregs = (char *) uctxt->uc_mcontext.fpregs; +#endif dprintf2("%s() trapno: %d ip: 0x%016lx info->si_code: %s/%d\n", __func__, trapno, ip, si_code_str(si->si_code), @@ -359,7 +363,9 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) #endif /* arch */ dprintf1("siginfo: %p\n", si); +#ifdef MCONTEXT_FPREGS dprintf1(" fpregs: %p\n", fpregs); +#endif if ((si->si_code == SEGV_MAPERR) || (si->si_code == SEGV_ACCERR) || @@ -389,26 +395,22 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) #elif defined(__powerpc64__) /* arch */ /* restore access and let the faulting instruction continue */ pkey_access_allow(siginfo_pkey); +#elif defined(__aarch64__) + 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; @@ -434,13 +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; @@ -458,38 +460,10 @@ 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; + unsigned long init_val = PKEY_UNRESTRICTED; dprintf1("%s()::%d, pkey_reg: 0x%016llx shadow: %016llx\n", __func__, __LINE__, __read_pkey_reg(), shadow_pkey_reg); @@ -532,19 +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; @@ -590,13 +557,11 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, int nr_iterations = random() % 100; int ret; - while (0) { + while (nr_iterations-- >= 0) { int rpkey = alloc_random_pkey(); ret = sys_mprotect_pkey(ptr, size, orig_prot, pkey); dprintf1("sys_mprotect_pkey(%p, %zx, prot=0x%lx, pkey=%ld) ret: %d\n", ptr, size, orig_prot, pkey, ret); - if (nr_iterations-- < 0) - break; dprintf1("%s()::%d, ret: %d pkey_reg: 0x%016llx" " shadow: 0x%016llx\n", @@ -627,7 +592,7 @@ 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; @@ -665,7 +630,7 @@ 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; @@ -692,8 +657,7 @@ 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; @@ -713,7 +677,7 @@ 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; @@ -743,10 +707,10 @@ 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; @@ -794,7 +758,7 @@ 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; @@ -815,42 +779,15 @@ 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; @@ -880,7 +817,7 @@ 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) { @@ -902,7 +839,9 @@ void expected_pkey_fault(int pkey) * test program continue. We now have to restore it. */ if (__read_pkey_reg() != 0) -#else /* arch */ +#elif defined(__aarch64__) + if (__read_pkey_reg() != PKEY_REG_ALLOW_ALL) +#else if (__read_pkey_reg() != shadow_pkey_reg) #endif /* arch */ pkey_assert(0); @@ -920,9 +859,9 @@ 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)); @@ -930,14 +869,14 @@ 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; @@ -950,17 +889,7 @@ void close_test_fds(void) nr_test_fds = 0; } -#define barrier() __asm__ __volatile__("": : :"memory") -__attribute__((noinline)) int read_ptr(int *ptr) -{ - /* - * Keep GCC from optimizing this away somehow - */ - barrier(); - return *ptr; -} - -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; @@ -1012,7 +941,7 @@ 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; @@ -1022,7 +951,7 @@ 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; @@ -1034,7 +963,7 @@ 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; @@ -1051,7 +980,7 @@ 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__; @@ -1062,14 +991,14 @@ 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); @@ -1077,7 +1006,7 @@ 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__; @@ -1088,7 +1017,7 @@ 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(); @@ -1100,7 +1029,8 @@ 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(); @@ -1113,7 +1043,7 @@ 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; @@ -1135,7 +1065,7 @@ 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; @@ -1153,7 +1083,7 @@ 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; @@ -1176,7 +1106,7 @@ 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; @@ -1186,7 +1116,7 @@ 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; @@ -1202,7 +1132,7 @@ 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}; @@ -1269,7 +1199,7 @@ 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; @@ -1308,7 +1238,7 @@ 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}; @@ -1346,7 +1276,7 @@ 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; @@ -1370,9 +1300,9 @@ 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; + __always_unused int peek_result; pid_t child_pid; void *ignored = 0; long ret; @@ -1446,7 +1376,7 @@ 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; @@ -1467,7 +1397,7 @@ 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; @@ -1492,9 +1422,14 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey) lots_o_noops_around_write(&scratch); do_not_expect_pkey_fault("executing on PROT_EXEC memory"); expect_fault_on_read_execonly_key(p1, pkey); + + // Reset back to PROT_EXEC | PROT_READ for architectures that support + // non-PKEY execute-only permissions. + ret = mprotect_pkey(p1, PAGE_SIZE, PROT_EXEC | PROT_READ, (u64)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; @@ -1543,7 +1478,7 @@ 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 +1600,85 @@ void test_ptrace_modifies_pkru(int *ptr, u16 pkey) } #endif -void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) +#if defined(__aarch64__) +static void test_ptrace_modifies_pkru(int *ptr, u16 pkey) +{ + pid_t child; + int status, ret; + struct iovec iov; + u64 trace_pkey; + /* Just a random pkey value.. */ + u64 new_pkey = (POE_X << PKEY_BITS_PER_PKEY * 2) | + (POE_NONE << PKEY_BITS_PER_PKEY) | + POE_RWX; + + child = fork(); + pkey_assert(child >= 0); + dprintf3("[%d] fork() ret: %d\n", getpid(), child); + if (!child) { + ptrace(PTRACE_TRACEME, 0, 0, 0); + + /* Stop and allow the tracer to modify PKRU directly */ + raise(SIGSTOP); + + /* + * need __read_pkey_reg() version so we do not do shadow_pkey_reg + * checking + */ + if (__read_pkey_reg() != new_pkey) + exit(1); + + raise(SIGSTOP); + + exit(0); + } + + pkey_assert(child == waitpid(child, &status, 0)); + dprintf3("[%d] waitpid(%d) status: %x\n", getpid(), child, status); + pkey_assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP); + + iov.iov_base = &trace_pkey; + iov.iov_len = 8; + ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_ARM_POE, &iov); + pkey_assert(ret == 0); + pkey_assert(trace_pkey == read_pkey_reg()); + + trace_pkey = new_pkey; + + ret = ptrace(PTRACE_SETREGSET, child, (void *)NT_ARM_POE, &iov); + pkey_assert(ret == 0); + + /* Test that the modification is visible in ptrace before any execution */ + memset(&trace_pkey, 0, sizeof(trace_pkey)); + ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_ARM_POE, &iov); + pkey_assert(ret == 0); + pkey_assert(trace_pkey == new_pkey); + + /* Execute the tracee */ + ret = ptrace(PTRACE_CONT, child, 0, 0); + pkey_assert(ret == 0); + + /* Test that the tracee saw the PKRU value change */ + pkey_assert(child == waitpid(child, &status, 0)); + dprintf3("[%d] waitpid(%d) status: %x\n", getpid(), child, status); + pkey_assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP); + + /* Test that the modification is visible in ptrace after execution */ + memset(&trace_pkey, 0, sizeof(trace_pkey)); + ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_ARM_POE, &iov); + pkey_assert(ret == 0); + pkey_assert(trace_pkey == new_pkey); + + ret = ptrace(PTRACE_CONT, child, 0, 0); + pkey_assert(ret == 0); + pkey_assert(child == waitpid(child, &status, 0)); + dprintf3("[%d] waitpid(%d) status: %x\n", getpid(), child, status); + pkey_assert(WIFEXITED(status)); + pkey_assert(WEXITSTATUS(status) == 0); +} +#endif + +static void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) { int size = PAGE_SIZE; int sret; @@ -1679,7 +1692,7 @@ 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, @@ -1700,12 +1713,12 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = { test_pkey_syscalls_bad_args, test_pkey_alloc_exhaust, test_pkey_alloc_free_attach_pkey0, -#if defined(__i386__) || defined(__x86_64__) +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) test_ptrace_modifies_pkru, #endif }; -void run_tests_once(void) +static void run_tests_once(void) { int *ptr; int prot = PROT_READ|PROT_WRITE; @@ -1739,7 +1752,7 @@ 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/rmap.c b/tools/testing/selftests/mm/rmap.c new file mode 100644 index 000000000000..53f2058b0ef2 --- /dev/null +++ b/tools/testing/selftests/mm/rmap.c @@ -0,0 +1,433 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RMAP functional tests + * + * Author(s): Wei Yang <richard.weiyang@gmail.com> + */ + +#include "kselftest_harness.h" +#include <strings.h> +#include <pthread.h> +#include <numa.h> +#include <numaif.h> +#include <sys/mman.h> +#include <sys/prctl.h> +#include <sys/types.h> +#include <signal.h> +#include <time.h> +#include <sys/sem.h> +#include <unistd.h> +#include <fcntl.h> + +#include "vm_util.h" + +#define TOTAL_LEVEL 5 +#define MAX_CHILDREN 3 + +#define FAIL_ON_CHECK (1 << 0) +#define FAIL_ON_WORK (1 << 1) + +struct sembuf sem_wait = {0, -1, 0}; +struct sembuf sem_signal = {0, 1, 0}; + +enum backend_type { + ANON, + SHM, + NORM_FILE, +}; + +#define PREFIX "kst_rmap" +#define MAX_FILENAME_LEN 256 +const char *suffixes[] = { + "", + "_shm", + "_file", +}; + +struct global_data; +typedef int (*work_fn)(struct global_data *data); +typedef int (*check_fn)(struct global_data *data); +typedef void (*prepare_fn)(struct global_data *data); + +struct global_data { + int worker_level; + + int semid; + int pipefd[2]; + + unsigned int mapsize; + unsigned int rand_seed; + char *region; + + prepare_fn do_prepare; + work_fn do_work; + check_fn do_check; + + enum backend_type backend; + char filename[MAX_FILENAME_LEN]; + + unsigned long *expected_pfn; +}; + +/* + * Create a process tree with TOTAL_LEVEL height and at most MAX_CHILDREN + * children for each. + * + * It will randomly select one process as 'worker' process which will + * 'do_work' until all processes are created. And all other processes will + * wait until 'worker' finish its work. + */ +void propagate_children(struct __test_metadata *_metadata, struct global_data *data) +{ + pid_t root_pid, pid; + unsigned int num_child; + int status; + int ret = 0; + int curr_child, worker_child; + int curr_level = 1; + bool is_worker = true; + + root_pid = getpid(); +repeat: + num_child = rand_r(&data->rand_seed) % MAX_CHILDREN + 1; + worker_child = is_worker ? rand_r(&data->rand_seed) % num_child : -1; + + for (curr_child = 0; curr_child < num_child; curr_child++) { + pid = fork(); + + if (pid < 0) { + perror("Error: fork\n"); + } else if (pid == 0) { + curr_level++; + + if (curr_child != worker_child) + is_worker = false; + + if (curr_level == TOTAL_LEVEL) + break; + + data->rand_seed += curr_child; + goto repeat; + } + } + + if (data->do_prepare) + data->do_prepare(data); + + close(data->pipefd[1]); + + if (is_worker && curr_level == data->worker_level) { + /* This is the worker process, first wait last process created */ + char buf; + + while (read(data->pipefd[0], &buf, 1) > 0) + ; + + if (data->do_work) + ret = data->do_work(data); + + /* Kick others */ + semctl(data->semid, 0, IPC_RMID); + } else { + /* Wait worker finish */ + semop(data->semid, &sem_wait, 1); + if (data->do_check) + ret = data->do_check(data); + } + + /* Wait all child to quit */ + while (wait(&status) > 0) { + if (WIFEXITED(status)) + ret |= WEXITSTATUS(status); + } + + if (getpid() == root_pid) { + if (ret & FAIL_ON_WORK) + SKIP(return, "Failed in worker"); + + ASSERT_EQ(ret, 0); + } else { + exit(ret); + } +} + +FIXTURE(migrate) +{ + struct global_data data; +}; + +FIXTURE_SETUP(migrate) +{ + struct global_data *data = &self->data; + + if (numa_available() < 0) + SKIP(return, "NUMA not available"); + if (numa_bitmask_weight(numa_all_nodes_ptr) <= 1) + SKIP(return, "Not enough NUMA nodes available"); + + data->mapsize = getpagesize(); + + data->expected_pfn = mmap(0, sizeof(unsigned long), + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(data->expected_pfn, MAP_FAILED); + + /* Prepare semaphore */ + data->semid = semget(IPC_PRIVATE, 1, 0666 | IPC_CREAT); + ASSERT_NE(data->semid, -1); + ASSERT_NE(semctl(data->semid, 0, SETVAL, 0), -1); + + /* Prepare pipe */ + ASSERT_NE(pipe(data->pipefd), -1); + + data->rand_seed = time(NULL); + srand(data->rand_seed); + + data->worker_level = rand() % TOTAL_LEVEL + 1; + + data->do_prepare = NULL; + data->do_work = NULL; + data->do_check = NULL; + + data->backend = ANON; +}; + +FIXTURE_TEARDOWN(migrate) +{ + struct global_data *data = &self->data; + + if (data->region != MAP_FAILED) + munmap(data->region, data->mapsize); + data->region = MAP_FAILED; + if (data->expected_pfn != MAP_FAILED) + munmap(data->expected_pfn, sizeof(unsigned long)); + data->expected_pfn = MAP_FAILED; + semctl(data->semid, 0, IPC_RMID); + data->semid = -1; + + close(data->pipefd[0]); + + switch (data->backend) { + case ANON: + break; + case SHM: + shm_unlink(data->filename); + break; + case NORM_FILE: + unlink(data->filename); + break; + } +} + +void access_region(struct global_data *data) +{ + /* + * Force read "region" to make sure page fault in. + */ + FORCE_READ(*data->region); +} + +int try_to_move_page(char *region) +{ + int ret; + int node; + int status = 0; + int failures = 0; + + ret = move_pages(0, 1, (void **)®ion, NULL, &status, MPOL_MF_MOVE_ALL); + if (ret != 0) { + perror("Failed to get original numa"); + return FAIL_ON_WORK; + } + + /* Pick up a different target node */ + for (node = 0; node <= numa_max_node(); node++) { + if (numa_bitmask_isbitset(numa_all_nodes_ptr, node) && node != status) + break; + } + + if (node > numa_max_node()) { + ksft_print_msg("Couldn't find available numa node for testing\n"); + return FAIL_ON_WORK; + } + + while (1) { + ret = move_pages(0, 1, (void **)®ion, &node, &status, MPOL_MF_MOVE_ALL); + + /* migrate successfully */ + if (!ret) + break; + + /* error happened */ + if (ret < 0) { + ksft_perror("Failed to move pages"); + return FAIL_ON_WORK; + } + + /* migration is best effort; try again */ + if (++failures >= 100) + return FAIL_ON_WORK; + } + + return 0; +} + +int move_region(struct global_data *data) +{ + int ret; + int pagemap_fd; + + ret = try_to_move_page(data->region); + if (ret != 0) + return ret; + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd == -1) + return FAIL_ON_WORK; + *data->expected_pfn = pagemap_get_pfn(pagemap_fd, data->region); + + return 0; +} + +int has_same_pfn(struct global_data *data) +{ + unsigned long pfn; + int pagemap_fd; + + if (data->region == MAP_FAILED) + return 0; + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd == -1) + return FAIL_ON_CHECK; + + pfn = pagemap_get_pfn(pagemap_fd, data->region); + if (pfn != *data->expected_pfn) + return FAIL_ON_CHECK; + + return 0; +} + +TEST_F(migrate, anon) +{ + struct global_data *data = &self->data; + + /* Map an area and fault in */ + data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(data->region, MAP_FAILED); + memset(data->region, 0xcf, data->mapsize); + + data->do_prepare = access_region; + data->do_work = move_region; + data->do_check = has_same_pfn; + + propagate_children(_metadata, data); +} + +TEST_F(migrate, shm) +{ + int shm_fd; + struct global_data *data = &self->data; + + snprintf(data->filename, MAX_FILENAME_LEN, "%s%s", PREFIX, suffixes[SHM]); + shm_fd = shm_open(data->filename, O_CREAT | O_RDWR, 0666); + ASSERT_NE(shm_fd, -1); + ftruncate(shm_fd, data->mapsize); + data->backend = SHM; + + /* Map a shared area and fault in */ + data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE, + MAP_SHARED, shm_fd, 0); + ASSERT_NE(data->region, MAP_FAILED); + memset(data->region, 0xcf, data->mapsize); + close(shm_fd); + + data->do_prepare = access_region; + data->do_work = move_region; + data->do_check = has_same_pfn; + + propagate_children(_metadata, data); +} + +TEST_F(migrate, file) +{ + int fd; + struct global_data *data = &self->data; + + snprintf(data->filename, MAX_FILENAME_LEN, "%s%s", PREFIX, suffixes[NORM_FILE]); + fd = open(data->filename, O_CREAT | O_RDWR | O_EXCL, 0666); + ASSERT_NE(fd, -1); + ftruncate(fd, data->mapsize); + data->backend = NORM_FILE; + + /* Map a shared area and fault in */ + data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + ASSERT_NE(data->region, MAP_FAILED); + memset(data->region, 0xcf, data->mapsize); + close(fd); + + data->do_prepare = access_region; + data->do_work = move_region; + data->do_check = has_same_pfn; + + propagate_children(_metadata, data); +} + +void prepare_local_region(struct global_data *data) +{ + /* Allocate range and set the same data */ + data->region = mmap(NULL, data->mapsize, PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANON, -1, 0); + if (data->region == MAP_FAILED) + return; + + memset(data->region, 0xcf, data->mapsize); +} + +int merge_and_migrate(struct global_data *data) +{ + int pagemap_fd; + int ret = 0; + + if (data->region == MAP_FAILED) + return FAIL_ON_WORK; + + if (ksm_start() < 0) + return FAIL_ON_WORK; + + ret = try_to_move_page(data->region); + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd == -1) + return FAIL_ON_WORK; + *data->expected_pfn = pagemap_get_pfn(pagemap_fd, data->region); + + return ret; +} + +TEST_F(migrate, ksm) +{ + int ret; + struct global_data *data = &self->data; + + if (ksm_stop() < 0) + SKIP(return, "accessing \"/sys/kernel/mm/ksm/run\") failed"); + if (ksm_get_full_scans() < 0) + SKIP(return, "accessing \"/sys/kernel/mm/ksm/full_scan\") failed"); + + ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); + if (ret < 0 && errno == EINVAL) + SKIP(return, "PR_SET_MEMORY_MERGE not supported"); + else if (ret) + ksft_exit_fail_perror("PR_SET_MEMORY_MERGE=1 failed"); + + data->do_prepare = prepare_local_region; + data->do_work = merge_and_migrate; + data->do_check = has_same_pfn; + + propagate_children(_metadata, data); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 3f26f6e15b2a..d9173f2312b7 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -5,6 +5,7 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +count_total=0 count_pass=0 count_fail=0 count_skip=0 @@ -12,11 +13,16 @@ exitcode=0 usage() { cat <<EOF -usage: ${BASH_SOURCE[0]:-$0} [ -h | -t "<categories>"] +usage: ${BASH_SOURCE[0]:-$0} [ options ] + + -a: run all tests, including extra ones (other than destructive ones) -t: specify specific categories to tests to run -h: display this message + -n: disable TAP output + -d: run destructive tests -The default behavior is to run all tests. +The default behavior is to run required tests only. If -a is specified, +will run all tests. Alternatively, specific groups tests can be run by passing a string to the -t argument containing one or more of the following categories @@ -39,6 +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 @@ -53,18 +61,49 @@ separated by spaces: memory protection key tests - soft_dirty test soft dirty page bit semantics +- pagemap + test pagemap_scan IOCTL +- pfnmap + tests for VM_PFNMAP handling +- process_madv + test for process_madv - cow test copy-on-write semantics +- thp + test transparent huge pages +- hugetlb + test hugetlbfs huge pages +- migration + invoke move_pages(2) to exercise the migration entry code + paths in the kernel +- mkdirty + test handling of code that might set PTE/PMD dirty in + read-only VMAs +- mdwe + test prctl(PR_SET_MDWE, ...) +- page_frag + test handling of page fragment allocation and freeing +- vma_merge + test VMA merge cases behave as expected +- rmap + test rmap behaves as expected + example: ./run_vmtests.sh -t "hmm mmap ksm" EOF exit 0 } +RUN_ALL=false +RUN_DESTRUCTIVE=false +TAP_PREFIX="# " -while getopts "ht:" OPT; do +while getopts "aht:n" OPT; do case ${OPT} in + "a") RUN_ALL=true ;; "h") usage ;; "t") VM_SELFTEST_ITEMS=${OPTARG} ;; + "n") TAP_PREFIX= ;; + "d") RUN_DESTRUCTIVE=true ;; esac done shift $((OPTIND -1)) @@ -85,6 +124,30 @@ test_selected() { fi } +run_gup_matrix() { + # -t: thp=on, -T: thp=off, -H: hugetlb=on + local hugetlb_mb=$(( needmem_KB / 1024 )) + + for huge in -t -T "-H -m $hugetlb_mb"; do + # -u: gup-fast, -U: gup-basic, -a: pin-fast, -b: pin-basic, -L: pin-longterm + for test_cmd in -u -U -a -b -L; do + # -w: write=1, -W: write=0 + for write in -w -W; do + # -S: shared + for share in -S " "; do + # -n: How many pages to fetch together? 512 is special + # because it's default thp size (or 2M on x86), 123 to + # just test partial gup when hit a huge in whatever form + for num in "-n 1" "-n 512" "-n 123" "-n -1"; do + CATEGORY="gup_test" run_test ./gup_test \ + $huge $test_cmd $write $share $num + done + done + done + done + done +} + # get huge pagesize and freepages from /proc/meminfo while read -r name size unit; do if [ "$name" = "HugePages_Free:" ]; then @@ -101,19 +164,23 @@ done < /proc/meminfo # both of these requirements into account and attempt to increase # number of huge pages available. nr_cpus=$(nproc) -hpgsize_MB=$((hpgsize_KB / 1024)) -half_ufd_size_MB=$((((nr_cpus * hpgsize_MB + 127) / 128) * 128)) -needmem_KB=$((half_ufd_size_MB * 2 * 1024)) +uffd_min_KB=$((hpgsize_KB * nr_cpus * 2)) +hugetlb_min_KB=$((256 * 1024)) +if [[ $uffd_min_KB -gt $hugetlb_min_KB ]]; then + needmem_KB=$uffd_min_KB +else + needmem_KB=$hugetlb_min_KB +fi # set proper nr_hugepages if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then - nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) + orig_nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) needpgs=$((needmem_KB / hpgsize_KB)) tries=2 while [ "$tries" -gt 0 ] && [ "$freepgs" -lt "$needpgs" ]; do lackpgs=$((needpgs - freepgs)) echo 3 > /proc/sys/vm/drop_caches - if ! echo $((lackpgs + nr_hugepgs)) > /proc/sys/vm/nr_hugepages; then + if ! echo $((lackpgs + orig_nr_hugepgs)) > /proc/sys/vm/nr_hugepages; then echo "Please run this test as root" exit $ksft_skip fi @@ -124,48 +191,91 @@ if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then done < /proc/meminfo tries=$((tries - 1)) done + nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) if [ "$freepgs" -lt "$needpgs" ]; then printf "Not enough huge pages available (%d < %d)\n" \ "$freepgs" "$needpgs" - exit 1 fi + HAVE_HUGEPAGES=1 else echo "no hugetlbfs support in kernel?" - exit 1 + HAVE_HUGEPAGES=0 fi # filter 64bit architectures -ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sparc64 x86_64" +ARCH64STR="arm64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sparc64 x86_64" if [ -z "$ARCH" ]; then ARCH=$(uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/') fi VADDR64=0 echo "$ARCH64STR" | grep "$ARCH" &>/dev/null && VADDR64=1 +tap_prefix() { + sed -e "s/^/${TAP_PREFIX}/" +} + +tap_output() { + if [[ ! -z "$TAP_PREFIX" ]]; then + read str + echo $str + fi +} + +pretty_name() { + echo "$*" | sed -e 's/^\(bash \)\?\.\///' +} + # Usage: run_test [test binary] [arbitrary test arguments...] run_test() { if test_selected ${CATEGORY}; then + local skip=0 + + # On memory constrainted systems some tests can fail to allocate hugepages. + # perform some cleanup before the test for a higher success rate. + if [ ${CATEGORY} == "thp" -o ${CATEGORY} == "hugetlb" ]; then + if [ "${HAVE_HUGEPAGES}" = "1" ]; then + echo 3 > /proc/sys/vm/drop_caches + sleep 2 + echo 1 > /proc/sys/vm/compact_memory + sleep 2 + else + echo "hugepages not supported" | tap_prefix + skip=1 + fi + fi + + local test=$(pretty_name "$*") local title="running $*" local sep=$(echo -n "$title" | tr "[:graph:][:space:]" -) - printf "%s\n%s\n%s\n" "$sep" "$title" "$sep" + printf "%s\n%s\n%s\n" "$sep" "$title" "$sep" | tap_prefix - "$@" - local ret=$? + if [ "${skip}" != "1" ]; then + ("$@" 2>&1) | tap_prefix + local ret=${PIPESTATUS[0]} + else + local ret=$ksft_skip + fi + count_total=$(( count_total + 1 )) if [ $ret -eq 0 ]; then count_pass=$(( count_pass + 1 )) - echo "[PASS]" + echo "[PASS]" | tap_prefix + echo "ok ${count_total} ${test}" | tap_output elif [ $ret -eq $ksft_skip ]; then count_skip=$(( count_skip + 1 )) - echo "[SKIP]" + echo "[SKIP]" | tap_prefix + echo "ok ${count_total} ${test} # SKIP" | tap_output exitcode=$ksft_skip else count_fail=$(( count_fail + 1 )) - echo "[FAIL]" + echo "[FAIL]" | tap_prefix + echo "not ok ${count_total} ${test} # exit=$ret" | tap_output exitcode=1 fi fi # test_selected } +echo "TAP version 13" | tap_output + CATEGORY="hugetlb" run_test ./hugepage-mmap shmmax=$(cat /proc/sys/kernel/shmmax) @@ -180,40 +290,90 @@ CATEGORY="hugetlb" run_test ./map_hugetlb CATEGORY="hugetlb" run_test ./hugepage-mremap CATEGORY="hugetlb" run_test ./hugepage-vmemmap CATEGORY="hugetlb" run_test ./hugetlb-madvise +CATEGORY="hugetlb" run_test ./hugetlb_dio + +if [ "${HAVE_HUGEPAGES}" = "1" ]; then + nr_hugepages_tmp=$(cat /proc/sys/vm/nr_hugepages) + # For this test, we need one and just one huge page + echo 1 > /proc/sys/vm/nr_hugepages + CATEGORY="hugetlb" run_test ./hugetlb_fault_after_madv + CATEGORY="hugetlb" run_test ./hugetlb_madv_vs_map + # Restore the previous number of huge pages, since further tests rely on it + echo "$nr_hugepages_tmp" > /proc/sys/vm/nr_hugepages +fi if test_selected "hugetlb"; then - echo "NOTE: These hugetlb tests provide minimal coverage. Use" - echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" - echo " hugetlb regression testing." + echo "NOTE: These hugetlb tests provide minimal coverage. Use" | tap_prefix + echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" | tap_prefix + echo " hugetlb regression testing." | tap_prefix fi CATEGORY="mmap" run_test ./map_fixed_noreplace -# get_user_pages_fast() benchmark -CATEGORY="gup_test" run_test ./gup_test -u -# pin_user_pages_fast() benchmark -CATEGORY="gup_test" run_test ./gup_test -a +if $RUN_ALL; then + run_gup_matrix +else + # get_user_pages_fast() benchmark + CATEGORY="gup_test" run_test ./gup_test -u -n 1 + CATEGORY="gup_test" run_test ./gup_test -u -n -1 + # pin_user_pages_fast() benchmark + CATEGORY="gup_test" run_test ./gup_test -a -n 1 + CATEGORY="gup_test" run_test ./gup_test -a -n -1 +fi # Dump pages 0, 19, and 4096, using pin_user_pages: CATEGORY="gup_test" run_test ./gup_test -ct -F 0x1 0 19 0x1000 - CATEGORY="gup_test" run_test ./gup_longterm CATEGORY="userfaultfd" run_test ./uffd-unit-tests uffd_stress_bin=./uffd-stress CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16 -# Hugetlb tests require source and destination huge pages. Pass in half -# the size ($half_ufd_size_MB), which is used for *each*. +# Hugetlb tests require source and destination huge pages. Pass in almost half +# the size of the free pages we have, which is used for *each*. An adjustment +# of (nr_parallel - 1) is done (see nr_parallel in uffd-stress.c) to have some +# extra hugepages - this is done to prevent the test from failing by racily +# reserving more hugepages than strictly required. +# uffd-stress expects a region expressed in MiB, so we adjust +# half_ufd_size_MB accordingly. +adjustment=$(( (31 < (nr_cpus - 1)) ? 31 : (nr_cpus - 1) )) +half_ufd_size_MB=$((((freepgs - adjustment) * hpgsize_KB) / 1024 / 2)) CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 32 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 ${uffd_stress_bin} shmem-private 20 16 +# uffd-wp-mremap requires at least one page of each size. +have_all_size_hugepgs=true +declare -A nr_size_hugepgs +for f in /sys/kernel/mm/hugepages/**/nr_hugepages; do + old=$(cat $f) + nr_size_hugepgs["$f"]="$old" + if [ "$old" == 0 ]; then + echo 1 > "$f" + fi + if [ $(cat "$f") == 0 ]; then + have_all_size_hugepgs=false + break + fi +done +if $have_all_size_hugepgs; then + CATEGORY="userfaultfd" run_test ./uffd-wp-mremap +else + echo "# SKIP ./uffd-wp-mremap" +fi #cleanup +for f in "${!nr_size_hugepgs[@]}"; do + echo "${nr_size_hugepgs["$f"]}" > "$f" +done echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages CATEGORY="compaction" run_test ./compaction_test -CATEGORY="mlock" run_test sudo -u nobody ./on-fault-limit +if command -v sudo &> /dev/null && sudo -u nobody ls ./on-fault-limit >/dev/null; +then + CATEGORY="mlock" run_test sudo -u nobody ./on-fault-limit +else + echo "# SKIP ./on-fault-limit" +fi CATEGORY="mmap" run_test ./map_populate @@ -226,6 +386,17 @@ CATEGORY="process_mrelease" run_test ./mrelease_test CATEGORY="mremap" run_test ./mremap_test CATEGORY="hugetlb" run_test ./thuge-gen +CATEGORY="hugetlb" run_test ./charge_reserved_hugetlb.sh -cgroup-v2 +CATEGORY="hugetlb" run_test ./hugetlb_reparenting_test.sh -cgroup-v2 +if $RUN_DESTRUCTIVE; then +nr_hugepages_tmp=$(cat /proc/sys/vm/nr_hugepages) +enable_soft_offline=$(cat /proc/sys/vm/enable_soft_offline) +echo 8 > /proc/sys/vm/nr_hugepages +CATEGORY="hugetlb" run_test ./hugetlb-soft-offline +echo "$nr_hugepages_tmp" > /proc/sys/vm/nr_hugepages +echo "$enable_soft_offline" > /proc/sys/vm/enable_soft_offline +CATEGORY="hugetlb" run_test ./hugetlb-read-hwpoison +fi if [ $VADDR64 -ne 0 ]; then @@ -233,10 +404,12 @@ if [ $VADDR64 -ne 0 ]; then # allows high virtual address allocation requests independent # of platform's physical memory. - prev_policy=$(cat /proc/sys/vm/overcommit_memory) - echo 1 > /proc/sys/vm/overcommit_memory - CATEGORY="hugevm" run_test ./virtual_address_range - echo $prev_policy > /proc/sys/vm/overcommit_memory + if [ -x ./virtual_address_range ]; then + prev_policy=$(cat /proc/sys/vm/overcommit_memory) + echo 1 > /proc/sys/vm/overcommit_memory + CATEGORY="hugevm" run_test ./virtual_address_range + echo $prev_policy > /proc/sys/vm/overcommit_memory + fi # va high address boundary switch test ARCH_ARM64="arm64" @@ -257,11 +430,31 @@ CATEGORY="mremap" run_test ./mremap_dontunmap CATEGORY="hmm" run_test bash ./test_hmm.sh smoke +# MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests +CATEGORY="madv_guard" run_test ./guard-regions + # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate +# PROCESS_MADV test +CATEGORY="process_madv" run_test ./process_madv + +CATEGORY="vma_merge" run_test ./merge + +if [ -x ./memfd_secret ] +then +if [ -f /proc/sys/kernel/yama/ptrace_scope ]; then + (echo 0 > /proc/sys/kernel/yama/ptrace_scope 2>&1) | tap_prefix +fi CATEGORY="memfd_secret" run_test ./memfd_secret +fi +# KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100 +if [ "${HAVE_HUGEPAGES}" = "1" ]; then + CATEGORY="ksm" run_test ./ksm_tests -H -s 100 +fi +# KSM KSM_MERGE_TIME test with size of 100 +CATEGORY="ksm" run_test ./ksm_tests -P -s 100 # KSM MADV_MERGEABLE test with 10 identical pages CATEGORY="ksm" run_test ./ksm_tests -M -p 10 # KSM unmerge test @@ -277,9 +470,8 @@ CATEGORY="ksm_numa" run_test ./ksm_tests -N -m 0 CATEGORY="ksm" run_test ./ksm_functional_tests -run_test ./ksm_functional_tests - # protection_keys tests +nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) if [ -x ./protection_keys_32 ] then CATEGORY="pkey" run_test ./protection_keys_32 @@ -289,12 +481,73 @@ if [ -x ./protection_keys_64 ] then CATEGORY="pkey" run_test ./protection_keys_64 fi +echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages + +if [ -x ./soft-dirty ] +then + CATEGORY="soft_dirty" run_test ./soft-dirty +fi -CATEGORY="soft_dirty" run_test ./soft-dirty +CATEGORY="pagemap" run_test ./pagemap_ioctl + +CATEGORY="pfnmap" run_test ./pfnmap # COW tests CATEGORY="cow" run_test ./cow -echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" +CATEGORY="thp" run_test ./khugepaged + +CATEGORY="thp" run_test ./khugepaged -s 2 + +CATEGORY="thp" run_test ./khugepaged all:shmem + +CATEGORY="thp" run_test ./khugepaged -s 4 all:shmem + +CATEGORY="thp" run_test ./transhuge-stress -d 20 + +# Try to create XFS if not provided +if [ -z "${SPLIT_HUGE_PAGE_TEST_XFS_PATH}" ]; then + if [ "${HAVE_HUGEPAGES}" = "1" ]; then + if test_selected "thp"; then + if grep xfs /proc/filesystems &>/dev/null; then + XFS_IMG=$(mktemp /tmp/xfs_img_XXXXXX) + SPLIT_HUGE_PAGE_TEST_XFS_PATH=$(mktemp -d /tmp/xfs_dir_XXXXXX) + truncate -s 314572800 ${XFS_IMG} + mkfs.xfs -q ${XFS_IMG} + mount -o loop ${XFS_IMG} ${SPLIT_HUGE_PAGE_TEST_XFS_PATH} + MOUNTED_XFS=1 + fi + fi + fi +fi + +CATEGORY="thp" run_test ./split_huge_page_test ${SPLIT_HUGE_PAGE_TEST_XFS_PATH} + +if [ -n "${MOUNTED_XFS}" ]; then + umount ${SPLIT_HUGE_PAGE_TEST_XFS_PATH} + rmdir ${SPLIT_HUGE_PAGE_TEST_XFS_PATH} + rm -f ${XFS_IMG} +fi + +CATEGORY="migration" run_test ./migration + +CATEGORY="mkdirty" run_test ./mkdirty + +CATEGORY="mdwe" run_test ./mdwe_test + +CATEGORY="page_frag" run_test ./test_page_frag.sh smoke + +CATEGORY="page_frag" run_test ./test_page_frag.sh aligned + +CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned + +CATEGORY="rmap" run_test ./rmap + +if [ "${HAVE_HUGEPAGES}" = 1 ]; then + echo "$orig_nr_hugepgs" > /proc/sys/vm/nr_hugepages +fi + +echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix +echo "1..${count_total}" | tap_output exit $exitcode diff --git a/tools/testing/selftests/mm/settings b/tools/testing/selftests/mm/settings index 9abfc60e9e6f..e2206265f67c 100644 --- a/tools/testing/selftests/mm/settings +++ b/tools/testing/selftests/mm/settings @@ -1 +1 @@ -timeout=45 +timeout=900 diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index cc5f144430d4..59c0dbe99a9b 100644 --- a/tools/testing/selftests/mm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c @@ -6,8 +6,10 @@ #include <stdint.h> #include <malloc.h> #include <sys/mman.h> -#include "../kselftest.h" + +#include "kselftest.h" #include "vm_util.h" +#include "thp_settings.h" #define PAGEMAP_FILE_PATH "/proc/self/pagemap" #define TEST_ITERATIONS 10000 @@ -78,8 +80,13 @@ static void test_hugepage(int pagemap_fd, int pagesize) { char *map; int i, ret; - size_t hpage_len = read_pmd_pagesize(); + if (!thp_is_enabled()) { + ksft_test_result_skip("Transparent Hugepages not available\n"); + return; + } + + size_t hpage_len = read_pmd_pagesize(); if (!hpage_len) ksft_exit_fail_msg("Reading PMD pagesize failed"); @@ -128,7 +135,7 @@ 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) { @@ -137,7 +144,7 @@ static void test_mprotect(int pagemap_fd, int pagesize, bool anon) if (!map) ksft_exit_fail_msg("anon mmap failed\n"); } else { - test_fd = open(fname, O_RDWR | O_CREAT); + test_fd = open(fname, O_RDWR | O_CREAT, 0664); if (test_fd < 0) { ksft_test_result_skip("Test %s open() file failed\n", __func__); return; @@ -177,6 +184,130 @@ static void test_mprotect(int pagemap_fd, int pagesize, bool anon) close(test_fd); } +static void test_merge(int pagemap_fd, int pagesize) +{ + char *reserved, *map, *map2; + + /* + * Reserve space for tests: + * + * ---padding to --- + * | avoid adj. | + * v merge v + * |---|---|---|---|---| + * | | 1 | 2 | 3 | | + * |---|---|---|---|---| + */ + reserved = mmap(NULL, 5 * pagesize, PROT_NONE, + MAP_ANON | MAP_PRIVATE, -1, 0); + if (reserved == MAP_FAILED) + ksft_exit_fail_msg("mmap failed\n"); + munmap(reserved, 4 * pagesize); + + /* + * Establish initial VMA: + * + * S/D + * |---|---|---|---|---| + * | | 1 | | | | + * |---|---|---|---|---| + */ + map = mmap(&reserved[pagesize], pagesize, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap failed\n"); + + /* This will clear VM_SOFTDIRTY too. */ + clear_softdirty(); + + /* + * Now place a new mapping which will be marked VM_SOFTDIRTY. Away from + * map: + * + * - S/D + * |---|---|---|---|---| + * | | 1 | | 2 | | + * |---|---|---|---|---| + */ + map2 = mmap(&reserved[3 * pagesize], pagesize, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (map2 == MAP_FAILED) + ksft_exit_fail_msg("mmap failed\n"); + + /* + * Now remap it immediately adjacent to map, if the merge correctly + * propagates VM_SOFTDIRTY, we should then observe the VMA as a whole + * being marked soft-dirty: + * + * merge + * S/D + * |---|-------|---|---| + * | | 1 | | | + * |---|-------|---|---| + */ + map2 = mremap(map2, pagesize, pagesize, MREMAP_FIXED | MREMAP_MAYMOVE, + &reserved[2 * pagesize]); + if (map2 == MAP_FAILED) + ksft_exit_fail_msg("mremap failed\n"); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 1, + "Test %s-anon soft-dirty after remap merge 1st pg\n", + __func__); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map2) == 1, + "Test %s-anon soft-dirty after remap merge 2nd pg\n", + __func__); + + munmap(map, 2 * pagesize); + + /* + * Now establish another VMA: + * + * S/D + * |---|---|---|---|---| + * | | 1 | | | | + * |---|---|---|---|---| + */ + map = mmap(&reserved[pagesize], pagesize, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap failed\n"); + + /* Clear VM_SOFTDIRTY... */ + clear_softdirty(); + /* ...and establish incompatible adjacent VMA: + * + * - S/D + * |---|---|---|---|---| + * | | 1 | 2 | | | + * |---|---|---|---|---| + */ + map2 = mmap(&reserved[2 * pagesize], pagesize, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (map2 == MAP_FAILED) + ksft_exit_fail_msg("mmap failed\n"); + + /* + * Now mprotect() VMA 1 so it's compatible with 2 and therefore merges: + * + * merge + * S/D + * |---|-------|---|---| + * | | 1 | | | + * |---|-------|---|---| + */ + if (mprotect(map, pagesize, PROT_READ | PROT_WRITE | PROT_EXEC)) + ksft_exit_fail_msg("mprotect failed\n"); + + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 1, + "Test %s-anon soft-dirty after mprotect merge 1st pg\n", + __func__); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map2) == 1, + "Test %s-anon soft-dirty after mprotect merge 2nd pg\n", + __func__); + + munmap(map, 2 * pagesize); +} + static void test_mprotect_anon(int pagemap_fd, int pagesize) { test_mprotect(pagemap_fd, pagesize, true); @@ -193,8 +324,11 @@ int main(int argc, char **argv) int pagesize; ksft_print_header(); - ksft_set_plan(15); + if (!softdirty_supported()) + ksft_exit_skip("soft-dirty is not support\n"); + + ksft_set_plan(19); pagemap_fd = open(PAGEMAP_FILE_PATH, O_RDONLY); if (pagemap_fd < 0) ksft_exit_fail_msg("Failed to open %s\n", PAGEMAP_FILE_PATH); @@ -206,8 +340,9 @@ int main(int argc, char **argv) test_hugepage(pagemap_fd, pagesize); test_mprotect_anon(pagemap_fd, pagesize); test_mprotect_file(pagemap_fd, pagesize); + test_merge(pagemap_fd, pagesize); close(pagemap_fd); - return ksft_exit_pass(); + ksft_finished(); } diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 0e74635c8c3d..40799f3f0213 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -5,6 +5,7 @@ */ #define _GNU_SOURCE +#include <assert.h> #include <stdio.h> #include <stdlib.h> #include <stdarg.h> @@ -14,57 +15,259 @@ #include <fcntl.h> #include <sys/mman.h> #include <sys/mount.h> +#include <sys/param.h> #include <malloc.h> #include <stdbool.h> +#include <time.h> #include "vm_util.h" +#include "kselftest.h" uint64_t pagesize; unsigned int pageshift; uint64_t pmd_pagesize; +unsigned int pmd_order; +int *expected_orders; #define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages" +#define SMAP_PATH "/proc/self/smaps" #define INPUT_MAX 80 -#define PID_FMT "%d,0x%lx,0x%lx" -#define PATH_FMT "%s,0x%lx,0x%lx" +#define PID_FMT "%d,0x%lx,0x%lx,%d" +#define PID_FMT_OFFSET "%d,0x%lx,0x%lx,%d,%d" +#define PATH_FMT "%s,0x%lx,0x%lx,%d" -#define PFN_MASK ((1UL<<55)-1) -#define KPF_THP (1UL<<22) +const char *pagemap_proc = "/proc/self/pagemap"; +const char *kpageflags_proc = "/proc/kpageflags"; +int pagemap_fd; +int kpageflags_fd; -int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file) +static bool is_backed_by_folio(char *vaddr, int order, int pagemap_fd, + int kpageflags_fd) { - uint64_t paddr; - uint64_t page_flags; + const uint64_t folio_head_flags = KPF_THP | KPF_COMPOUND_HEAD; + const uint64_t folio_tail_flags = KPF_THP | KPF_COMPOUND_TAIL; + const unsigned long nr_pages = 1UL << order; + unsigned long pfn_head; + uint64_t pfn_flags; + unsigned long pfn; + unsigned long i; + + pfn = pagemap_get_pfn(pagemap_fd, vaddr); + + /* non present page */ + if (pfn == -1UL) + return false; + + if (pageflags_get(pfn, kpageflags_fd, &pfn_flags)) + goto fail; + + /* check for order-0 pages */ + if (!order) { + if (pfn_flags & (folio_head_flags | folio_tail_flags)) + return false; + return true; + } + + /* non THP folio */ + if (!(pfn_flags & KPF_THP)) + return false; + + pfn_head = pfn & ~(nr_pages - 1); + + if (pageflags_get(pfn_head, kpageflags_fd, &pfn_flags)) + goto fail; + + /* head PFN has no compound_head flag set */ + if ((pfn_flags & folio_head_flags) != folio_head_flags) + return false; + + /* check all tail PFN flags */ + for (i = 1; i < nr_pages; i++) { + if (pageflags_get(pfn_head + i, kpageflags_fd, &pfn_flags)) + goto fail; + if ((pfn_flags & folio_tail_flags) != folio_tail_flags) + return false; + } + + /* + * check the PFN after this folio, but if its flags cannot be obtained, + * assume this folio has the expected order + */ + if (pageflags_get(pfn_head + nr_pages, kpageflags_fd, &pfn_flags)) + return true; + + /* If we find another tail page, then the folio is larger. */ + return (pfn_flags & folio_tail_flags) != folio_tail_flags; +fail: + ksft_exit_fail_msg("Failed to get folio info\n"); + return false; +} + +static int vaddr_pageflags_get(char *vaddr, int pagemap_fd, int kpageflags_fd, + uint64_t *flags) +{ + unsigned long pfn; + + pfn = pagemap_get_pfn(pagemap_fd, vaddr); + + /* non-present PFN */ + if (pfn == -1UL) + return 1; - if (pagemap_file) { - pread(pagemap_file, &paddr, sizeof(paddr), - ((long)vaddr >> pageshift) * sizeof(paddr)); + if (pageflags_get(pfn, kpageflags_fd, flags)) + return -1; + + return 0; +} + +/* + * gather_after_split_folio_orders - scan through [vaddr_start, len) and record + * folio orders + * + * @vaddr_start: start vaddr + * @len: range length + * @pagemap_fd: file descriptor to /proc/<pid>/pagemap + * @kpageflags_fd: file descriptor to /proc/kpageflags + * @orders: output folio order array + * @nr_orders: folio order array size + * + * gather_after_split_folio_orders() scan through [vaddr_start, len) and check + * all folios within the range and record their orders. All order-0 pages will + * be recorded. Non-present vaddr is skipped. + * + * NOTE: the function is used to check folio orders after a split is performed, + * so it assumes [vaddr_start, len) fully maps to after-split folios within that + * range. + * + * Return: 0 - no error, -1 - unhandled cases + */ +static int gather_after_split_folio_orders(char *vaddr_start, size_t len, + int pagemap_fd, int kpageflags_fd, int orders[], int nr_orders) +{ + uint64_t page_flags = 0; + int cur_order = -1; + char *vaddr; + + if (pagemap_fd == -1 || kpageflags_fd == -1) + return -1; + if (!orders) + return -1; + if (nr_orders <= 0) + return -1; + + for (vaddr = vaddr_start; vaddr < vaddr_start + len;) { + char *next_folio_vaddr; + int status; + + status = vaddr_pageflags_get(vaddr, pagemap_fd, kpageflags_fd, + &page_flags); + if (status < 0) + return -1; + + /* skip non present vaddr */ + if (status == 1) { + vaddr += psize(); + continue; + } + + /* all order-0 pages with possible false postive (non folio) */ + if (!(page_flags & (KPF_COMPOUND_HEAD | KPF_COMPOUND_TAIL))) { + orders[0]++; + vaddr += psize(); + continue; + } + + /* skip non thp compound pages */ + if (!(page_flags & KPF_THP)) { + vaddr += psize(); + continue; + } - if (kpageflags_file) { - pread(kpageflags_file, &page_flags, sizeof(page_flags), - (paddr & PFN_MASK) * sizeof(page_flags)); + /* vpn points to part of a THP at this point */ + if (page_flags & KPF_COMPOUND_HEAD) + cur_order = 1; + else { + vaddr += psize(); + continue; + } - return !!(page_flags & KPF_THP); + next_folio_vaddr = vaddr + (1UL << (cur_order + pshift())); + + if (next_folio_vaddr >= vaddr_start + len) + break; + + while ((status = vaddr_pageflags_get(next_folio_vaddr, + pagemap_fd, kpageflags_fd, + &page_flags)) >= 0) { + /* + * non present vaddr, next compound head page, or + * order-0 page + */ + if (status == 1 || + (page_flags & KPF_COMPOUND_HEAD) || + !(page_flags & (KPF_COMPOUND_HEAD | KPF_COMPOUND_TAIL))) { + if (cur_order < nr_orders) { + orders[cur_order]++; + cur_order = -1; + vaddr = next_folio_vaddr; + } + break; + } + + cur_order++; + next_folio_vaddr = vaddr + (1UL << (cur_order + pshift())); } + + if (status < 0) + return status; } + if (cur_order > 0 && cur_order < nr_orders) + orders[cur_order]++; return 0; } -static int write_file(const char *path, const char *buf, size_t buflen) +static int check_after_split_folio_orders(char *vaddr_start, size_t len, + int pagemap_fd, int kpageflags_fd, int orders[], int nr_orders) +{ + int *vaddr_orders; + int status; + int i; + + vaddr_orders = (int *)malloc(sizeof(int) * nr_orders); + + if (!vaddr_orders) + ksft_exit_fail_msg("Cannot allocate memory for vaddr_orders"); + + memset(vaddr_orders, 0, sizeof(int) * nr_orders); + status = gather_after_split_folio_orders(vaddr_start, len, pagemap_fd, + kpageflags_fd, vaddr_orders, nr_orders); + if (status) + ksft_exit_fail_msg("gather folio info failed\n"); + + for (i = 0; i < nr_orders; i++) + if (vaddr_orders[i] != orders[i]) { + ksft_print_msg("order %d: expected: %d got %d\n", i, + orders[i], vaddr_orders[i]); + status = -1; + } + + free(vaddr_orders); + return status; +} + +static void write_file(const char *path, const char *buf, size_t buflen) { int fd; ssize_t numwritten; fd = open(path, O_WRONLY); if (fd == -1) - return 0; + ksft_exit_fail_msg("%s open failed: %s\n", path, strerror(errno)); numwritten = write(fd, buf, buflen - 1); close(fd); if (numwritten < 1) - return 0; - - return (unsigned int) numwritten; + ksft_exit_fail_msg("Write failed\n"); } static void write_debugfs(const char *fmt, ...) @@ -77,237 +280,558 @@ static void write_debugfs(const char *fmt, ...) ret = vsnprintf(input, INPUT_MAX, fmt, argp); va_end(argp); - if (ret >= INPUT_MAX) { - printf("%s: Debugfs input is too long\n", __func__); - exit(EXIT_FAILURE); - } + if (ret >= INPUT_MAX) + ksft_exit_fail_msg("%s: Debugfs input is too long\n", __func__); - if (!write_file(SPLIT_DEBUGFS, input, ret + 1)) { - perror(SPLIT_DEBUGFS); - exit(EXIT_FAILURE); - } + write_file(SPLIT_DEBUGFS, input, ret + 1); } -void split_pmd_thp(void) +static char *allocate_zero_filled_hugepage(size_t len) { - char *one_page; - size_t len = 4 * pmd_pagesize; + char *result; size_t i; - one_page = memalign(pmd_pagesize, len); - - if (!one_page) { + result = memalign(pmd_pagesize, len); + if (!result) { printf("Fail to allocate memory\n"); exit(EXIT_FAILURE); } - madvise(one_page, len, MADV_HUGEPAGE); + madvise(result, len, MADV_HUGEPAGE); for (i = 0; i < len; i++) - one_page[i] = (char)i; + result[i] = (char)0; - if (!check_huge_anon(one_page, 4, pmd_pagesize)) { - printf("No THP is allocated\n"); - exit(EXIT_FAILURE); - } + return result; +} + +static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hpages, size_t len) +{ + unsigned long rss_anon_before, rss_anon_after; + size_t i; + + if (!check_huge_anon(one_page, nr_hpages, pmd_pagesize)) + ksft_exit_fail_msg("No THP is allocated\n"); + + rss_anon_before = rss_anon(); + 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); + (uint64_t)one_page + len, 0); for (i = 0; i < len; i++) - if (one_page[i] != (char)i) { - 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)) + ksft_exit_fail_msg("Still AnonHugePages not split\n"); - if (!check_huge_anon(one_page, 0, pmd_pagesize)) { - printf("Still AnonHugePages not split\n"); - exit(EXIT_FAILURE); - } + rss_anon_after = rss_anon(); + 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); +} - printf("Split huge pages successful\n"); +static void split_pmd_zero_pages(void) +{ + char *one_page; + int nr_hpages = 4; + size_t len = nr_hpages * pmd_pagesize; + + one_page = allocate_zero_filled_hugepage(len); + verify_rss_anon_split_huge_page_all_zeroes(one_page, nr_hpages, len); + ksft_test_result_pass("Split zero filled huge pages successful\n"); free(one_page); } -void split_pte_mapped_thp(void) +static void split_pmd_thp_to_order(int order) { - char *one_page, *pte_mapped, *pte_mapped2; + char *one_page; size_t len = 4 * pmd_pagesize; - uint64_t thp_size; size_t i; - const char *pagemap_template = "/proc/%d/pagemap"; - const char *kpageflags_proc = "/proc/kpageflags"; - char pagemap_proc[255]; - int pagemap_fd; - int kpageflags_fd; - - if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) { - perror("get pagemap proc error"); - exit(EXIT_FAILURE); - } - pagemap_fd = open(pagemap_proc, O_RDONLY); - if (pagemap_fd == -1) { - perror("read pagemap:"); - exit(EXIT_FAILURE); - } + one_page = memalign(pmd_pagesize, len); + if (!one_page) + ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno)); - kpageflags_fd = open(kpageflags_proc, O_RDONLY); + madvise(one_page, len, MADV_HUGEPAGE); - if (kpageflags_fd == -1) { - perror("read kpageflags:"); - exit(EXIT_FAILURE); - } + for (i = 0; i < len; i++) + one_page[i] = (char)i; - one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (!check_huge_anon(one_page, 4, pmd_pagesize)) + ksft_exit_fail_msg("No THP is allocated\n"); - madvise(one_page, len, MADV_HUGEPAGE); + /* split all THPs */ + write_debugfs(PID_FMT, getpid(), (uint64_t)one_page, + (uint64_t)one_page + len, order); for (i = 0; i < len; i++) - one_page[i] = (char)i; + if (one_page[i] != (char)i) + ksft_exit_fail_msg("%ld byte corrupted\n", i); - if (!check_huge_anon(one_page, 4, pmd_pagesize)) { - printf("No THP is allocated\n"); - exit(EXIT_FAILURE); + memset(expected_orders, 0, sizeof(int) * (pmd_order + 1)); + expected_orders[order] = 4 << (pmd_order - order); + + if (check_after_split_folio_orders(one_page, len, pagemap_fd, + kpageflags_fd, expected_orders, + (pmd_order + 1))) + ksft_exit_fail_msg("Unexpected THP split\n"); + + 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 to order %d successful\n", order); + free(one_page); +} + +static void split_pte_mapped_thp(void) +{ + const size_t nr_thps = 4; + const size_t thp_area_size = nr_thps * pmd_pagesize; + const size_t page_area_size = nr_thps * pagesize; + char *thp_area, *tmp, *page_area = MAP_FAILED; + size_t i; + + thp_area = mmap((void *)(1UL << 30), thp_area_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (thp_area == MAP_FAILED) { + ksft_test_result_fail("Fail to allocate memory: %s\n", strerror(errno)); + return; } - /* remap the first pagesize of first THP */ - pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE); + madvise(thp_area, thp_area_size, MADV_HUGEPAGE); - /* remap the Nth pagesize of Nth THP */ - for (i = 1; i < 4; i++) { - pte_mapped2 = mremap(one_page + pmd_pagesize * i + pagesize * i, - pagesize, pagesize, - MREMAP_MAYMOVE|MREMAP_FIXED, - pte_mapped + pagesize * i); - if (pte_mapped2 == (char *)-1) { - perror("mremap failed"); - exit(EXIT_FAILURE); - } + for (i = 0; i < thp_area_size; i++) + thp_area[i] = (char)i; + + if (!check_huge_anon(thp_area, nr_thps, pmd_pagesize)) { + ksft_test_result_skip("Not all THPs allocated\n"); + goto out; } - /* smap does not show THPs after mremap, use kpageflags instead */ - thp_size = 0; - for (i = 0; i < pagesize * 4; i++) - if (i % pagesize == 0 && - is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) - thp_size++; + /* + * To challenge spitting code, we will mremap a single page of each + * THP (page[i] of thp[i]) in the thp_area into page_area. This will + * replace the PMD mappings in the thp_area by PTE mappings first, + * but leaving the THP unsplit, to then create a page-sized hole in + * the thp_area. + * We will then manually trigger splitting of all THPs through the + * single mremap'ed pages of each THP in the page_area. + */ + page_area = mmap(NULL, page_area_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (page_area == MAP_FAILED) { + ksft_test_result_fail("Fail to allocate memory: %s\n", strerror(errno)); + goto out; + } - if (thp_size != 4) { - printf("Some THPs are missing during mremap\n"); - exit(EXIT_FAILURE); + for (i = 0; i < nr_thps; i++) { + tmp = mremap(thp_area + pmd_pagesize * i + pagesize * i, + pagesize, pagesize, MREMAP_MAYMOVE|MREMAP_FIXED, + page_area + pagesize * i); + if (tmp != MAP_FAILED) + continue; + ksft_test_result_fail("mremap failed: %s\n", strerror(errno)); + goto out; } - /* split all remapped THPs */ - write_debugfs(PID_FMT, getpid(), (uint64_t)pte_mapped, - (uint64_t)pte_mapped + pagesize * 4); + /* + * Verify that our THPs were not split yet. Note that + * check_huge_anon() cannot be used as it checks for PMD mappings. + */ + for (i = 0; i < nr_thps; i++) { + if (is_backed_by_folio(page_area + i * pagesize, pmd_order, + pagemap_fd, kpageflags_fd)) + continue; + ksft_test_result_fail("THP %zu missing after mremap\n", i); + goto out; + } - /* smap does not show THPs after mremap, use kpageflags instead */ - thp_size = 0; - for (i = 0; i < pagesize * 4; i++) { - if (pte_mapped[i] != (char)i) { - printf("%ld byte corrupted\n", i); - exit(EXIT_FAILURE); - } - if (i % pagesize == 0 && - is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) - thp_size++; + /* Split all THPs through the remapped pages. */ + write_debugfs(PID_FMT, getpid(), (uint64_t)page_area, + (uint64_t)page_area + page_area_size, 0); + + /* Corruption during mremap or split? */ + for (i = 0; i < page_area_size; i++) { + if (page_area[i] == (char)i) + continue; + ksft_test_result_fail("%zu byte corrupted\n", i); + goto out; } - if (thp_size) { - printf("Still %ld THPs not split\n", thp_size); - exit(EXIT_FAILURE); + /* Split failed? */ + for (i = 0; i < nr_thps; i++) { + if (is_backed_by_folio(page_area + i * pagesize, 0, + pagemap_fd, kpageflags_fd)) + continue; + ksft_test_result_fail("THP %zu not split\n", i); } - printf("Split PTE-mapped huge pages successful\n"); - munmap(one_page, len); - close(pagemap_fd); - close(kpageflags_fd); + ksft_test_result_pass("Split PTE-mapped huge pages successful\n"); +out: + munmap(thp_area, thp_area_size); + if (page_area != MAP_FAILED) + munmap(page_area, page_area_size); } -void split_file_backed_thp(void) +static void split_file_backed_thp(int order) { int status; int fd; - ssize_t num_written; char tmpfs_template[] = "/tmp/thp_split_XXXXXX"; const char *tmpfs_loc = mkdtemp(tmpfs_template); char testfile[INPUT_MAX]; + ssize_t num_written, num_read; + char *file_buf1, *file_buf2; uint64_t pgoff_start = 0, pgoff_end = 1024; + int i; - printf("Please enable pr_debug in split_huge_pages_in_file() if you need more info.\n"); + ksft_print_msg("Please enable pr_debug in split_huge_pages_in_file() for more info.\n"); - status = mount("tmpfs", tmpfs_loc, "tmpfs", 0, "huge=always,size=4m"); + file_buf1 = (char *)malloc(pmd_pagesize); + file_buf2 = (char *)malloc(pmd_pagesize); - if (status) { - printf("Unable to create a tmpfs for testing\n"); - exit(EXIT_FAILURE); + if (!file_buf1 || !file_buf2) { + ksft_print_msg("cannot allocate file buffers\n"); + goto out; } + for (i = 0; i < pmd_pagesize; i++) + file_buf1[i] = (char)i; + memset(file_buf2, 0, pmd_pagesize); + + status = mount("tmpfs", tmpfs_loc, "tmpfs", 0, "huge=always,size=4m"); + + if (status) + ksft_exit_fail_msg("Unable to create a tmpfs for testing\n"); + status = snprintf(testfile, INPUT_MAX, "%s/thp_file", tmpfs_loc); if (status >= INPUT_MAX) { - printf("Fail to create file-backed THP split testing file\n"); + ksft_print_msg("Fail to create file-backed THP split testing file\n"); goto cleanup; } - fd = open(testfile, O_CREAT|O_WRONLY); + fd = open(testfile, O_CREAT|O_RDWR, 0664); if (fd == -1) { - perror("Cannot open testing file\n"); + ksft_perror("Cannot open testing file"); goto cleanup; } - /* write something to the file, so a file-backed THP can be allocated */ - num_written = write(fd, tmpfs_loc, strlen(tmpfs_loc) + 1); - close(fd); + /* write pmd size data to the file, so a file-backed THP can be allocated */ + num_written = write(fd, file_buf1, pmd_pagesize); - if (num_written < 1) { - printf("Fail to write data to testing file\n"); - goto cleanup; + if (num_written == -1 || num_written != pmd_pagesize) { + ksft_perror("Failed to write data to testing file"); + goto close_file; } /* split the file-backed THP */ - write_debugfs(PATH_FMT, testfile, pgoff_start, pgoff_end); + write_debugfs(PATH_FMT, testfile, pgoff_start, pgoff_end, order); + + /* check file content after split */ + status = lseek(fd, 0, SEEK_SET); + if (status == -1) { + ksft_perror("Cannot lseek file"); + goto close_file; + } + + num_read = read(fd, file_buf2, num_written); + if (num_read == -1 || num_read != num_written) { + ksft_perror("Cannot read file content back"); + goto close_file; + } + + if (strncmp(file_buf1, file_buf2, pmd_pagesize) != 0) { + ksft_print_msg("File content changed\n"); + goto close_file; + } + close(fd); status = unlink(testfile); - if (status) - perror("Cannot remove testing file\n"); + if (status) { + ksft_perror("Cannot remove testing file"); + goto cleanup; + } -cleanup: status = umount(tmpfs_loc); if (status) { - printf("Unable to umount %s\n", tmpfs_loc); - exit(EXIT_FAILURE); + rmdir(tmpfs_loc); + ksft_exit_fail_msg("Unable to umount %s\n", tmpfs_loc); } + status = rmdir(tmpfs_loc); - if (status) { - perror("cannot remove tmp dir"); - exit(EXIT_FAILURE); + if (status) + ksft_exit_fail_msg("cannot remove tmp dir: %s\n", strerror(errno)); + + ksft_print_msg("Please check dmesg for more information\n"); + ksft_test_result_pass("File-backed THP split to order %d test done\n", order); + return; + +close_file: + close(fd); +cleanup: + umount(tmpfs_loc); + rmdir(tmpfs_loc); +out: + ksft_exit_fail_msg("Error occurred\n"); +} + +static bool prepare_thp_fs(const char *xfs_path, char *thp_fs_template, + const char **thp_fs_loc) +{ + if (xfs_path) { + *thp_fs_loc = xfs_path; + return false; + } + + *thp_fs_loc = mkdtemp(thp_fs_template); + + if (!*thp_fs_loc) + ksft_exit_fail_msg("cannot create temp folder\n"); + + return true; +} + +static void cleanup_thp_fs(const char *thp_fs_loc, bool created_tmp) +{ + int status; + + if (!created_tmp) + return; + + status = rmdir(thp_fs_loc); + if (status) + ksft_exit_fail_msg("cannot remove tmp dir: %s\n", + strerror(errno)); +} + +static int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, + int *fd, char **addr) +{ + size_t i; + unsigned char buf[1024]; + + srand(time(NULL)); + + *fd = open(testfile, O_CREAT | O_RDWR, 0664); + if (*fd == -1) + ksft_exit_fail_msg("Failed to create a file at %s\n", testfile); + + assert(fd_size % sizeof(buf) == 0); + for (i = 0; i < sizeof(buf); i++) + buf[i] = (unsigned char)i; + for (i = 0; i < fd_size; i += sizeof(buf)) + write(*fd, buf, sizeof(buf)); + + close(*fd); + sync(); + *fd = open("/proc/sys/vm/drop_caches", O_WRONLY); + if (*fd == -1) { + ksft_perror("open drop_caches"); + goto err_out_unlink; + } + if (write(*fd, "3", 1) != 1) { + ksft_perror("write to drop_caches"); + goto err_out_unlink; + } + close(*fd); + + *fd = open(testfile, O_RDWR); + if (*fd == -1) { + ksft_perror("Failed to open testfile\n"); + goto err_out_unlink; + } + + *addr = mmap(NULL, fd_size, PROT_READ|PROT_WRITE, MAP_SHARED, *fd, 0); + if (*addr == (char *)-1) { + ksft_perror("cannot mmap"); + goto err_out_close; + } + madvise(*addr, fd_size, MADV_HUGEPAGE); + + for (size_t i = 0; i < fd_size; i++) { + char *addr2 = *addr + i; + + FORCE_READ(*addr2); + } + + if (!check_huge_file(*addr, fd_size / pmd_pagesize, pmd_pagesize)) { + ksft_print_msg("No large pagecache folio generated, please provide a filesystem supporting large folio\n"); + munmap(*addr, fd_size); + close(*fd); + unlink(testfile); + ksft_test_result_skip("Pagecache folio split skipped\n"); + return -2; + } + return 0; +err_out_close: + close(*fd); +err_out_unlink: + unlink(testfile); + ksft_exit_fail_msg("Failed to create large pagecache folios\n"); + return -1; +} + +static void split_thp_in_pagecache_to_order_at(size_t fd_size, + const char *fs_loc, int order, int offset) +{ + int fd; + char *split_addr; + char *addr; + size_t i; + char testfile[INPUT_MAX]; + int err = 0; + + err = snprintf(testfile, INPUT_MAX, "%s/test", fs_loc); + + if (err < 0) + ksft_exit_fail_msg("cannot generate right test file name\n"); + + err = create_pagecache_thp_and_fd(testfile, fd_size, &fd, &addr); + if (err) + return; + + err = 0; + + memset(expected_orders, 0, sizeof(int) * (pmd_order + 1)); + /* + * use [split_addr, split_addr + pagesize) range to split THPs, since + * the debugfs function always split a range with pagesize step and + * providing a full [addr, addr + fd_size) range can trigger multiple + * splits, complicating after-split result checking. + */ + if (offset == -1) { + for (split_addr = addr; split_addr < addr + fd_size; split_addr += pmd_pagesize) + write_debugfs(PID_FMT, getpid(), (uint64_t)split_addr, + (uint64_t)split_addr + pagesize, order); + + expected_orders[order] = fd_size / (pagesize << order); + } else { + int times = fd_size / pmd_pagesize; + + for (split_addr = addr; split_addr < addr + fd_size; split_addr += pmd_pagesize) + write_debugfs(PID_FMT_OFFSET, getpid(), (uint64_t)split_addr, + (uint64_t)split_addr + pagesize, order, offset); + + for (i = order + 1; i < pmd_order; i++) + expected_orders[i] = times; + expected_orders[order] = 2 * times; + } + + for (i = 0; i < fd_size; i++) + if (*(addr + i) != (char)i) { + ksft_print_msg("%lu byte corrupted in the file\n", i); + err = EXIT_FAILURE; + goto out; + } + + if (check_after_split_folio_orders(addr, fd_size, pagemap_fd, + kpageflags_fd, expected_orders, + (pmd_order + 1))) { + ksft_print_msg("Unexpected THP split\n"); + err = 1; + goto out; } - printf("file-backed THP split test done, please check dmesg for more information\n"); + if (!check_huge_file(addr, 0, pmd_pagesize)) { + ksft_print_msg("Still FilePmdMapped not split\n"); + err = EXIT_FAILURE; + goto out; + } + +out: + munmap(addr, fd_size); + close(fd); + unlink(testfile); + if (offset == -1) { + if (err) + ksft_exit_fail_msg("Split PMD-mapped pagecache folio to order %d failed\n", order); + ksft_test_result_pass("Split PMD-mapped pagecache folio to order %d passed\n", order); + } else { + if (err) + ksft_exit_fail_msg("Split PMD-mapped pagecache folio to order %d at in-folio offset %d failed\n", order, offset); + ksft_test_result_pass("Split PMD-mapped pagecache folio to order %d at in-folio offset %d passed\n", order, offset); + } } int main(int argc, char **argv) { + int i; + size_t fd_size; + char *optional_xfs_path = NULL; + char fs_loc_template[] = "/tmp/thp_fs_XXXXXX"; + const char *fs_loc; + bool created_tmp; + int offset; + unsigned int nr_pages; + unsigned int tests; + + ksft_print_header(); + if (geteuid() != 0) { - printf("Please run the benchmark as root\n"); - exit(EXIT_FAILURE); + ksft_print_msg("Please run the benchmark as root\n"); + ksft_finished(); } + if (argc > 1) + optional_xfs_path = argv[1]; + pagesize = getpagesize(); pageshift = ffs(pagesize) - 1; pmd_pagesize = read_pmd_pagesize(); - if (!pmd_pagesize) { - printf("Reading PMD pagesize failed\n"); - exit(EXIT_FAILURE); - } + if (!pmd_pagesize) + ksft_exit_fail_msg("Reading PMD pagesize failed\n"); + + nr_pages = pmd_pagesize / pagesize; + pmd_order = sz2ord(pmd_pagesize, pagesize); + + expected_orders = (int *)malloc(sizeof(int) * (pmd_order + 1)); + if (!expected_orders) + ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno)); + + tests = 2 + (pmd_order - 1) + (2 * pmd_order) + (pmd_order - 1) * 4 + 2; + ksft_set_plan(tests); + + pagemap_fd = open(pagemap_proc, O_RDONLY); + if (pagemap_fd == -1) + ksft_exit_fail_msg("read pagemap: %s\n", strerror(errno)); + + kpageflags_fd = open(kpageflags_proc, O_RDONLY); + if (kpageflags_fd == -1) + ksft_exit_fail_msg("read kpageflags: %s\n", strerror(errno)); + + fd_size = 2 * pmd_pagesize; + + split_pmd_zero_pages(); + + for (i = 0; i < pmd_order; i++) + if (i != 1) + split_pmd_thp_to_order(i); - split_pmd_thp(); split_pte_mapped_thp(); - split_file_backed_thp(); + for (i = 0; i < pmd_order; i++) + split_file_backed_thp(i); + + created_tmp = prepare_thp_fs(optional_xfs_path, fs_loc_template, + &fs_loc); + for (i = pmd_order - 1; i >= 0; i--) + split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, -1); + + for (i = 0; i < pmd_order; i++) + for (offset = 0; + offset < nr_pages; + offset += MAX(nr_pages / 4, 1 << i)) + split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, offset); + cleanup_thp_fs(fs_loc, created_tmp); + + close(pagemap_fd); + close(kpageflags_fd); + free(expected_orders); + + ksft_finished(); return 0; } diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh new file mode 100755 index 000000000000..f55b105084cf --- /dev/null +++ b/tools/testing/selftests/mm/test_page_frag.sh @@ -0,0 +1,175 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2024 Yunsheng Lin <linyunsheng@huawei.com> +# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki@gmail.com> +# +# This is a test script for the kernel test driver to test the +# correctness and performance of page_frag's implementation. +# Therefore it is just a kernel module loader. You can specify +# and pass different parameters in order to: +# a) analyse performance of page fragment allocations; +# b) stressing and stability check of page_frag subsystem. + +DRIVER="./page_frag/page_frag_test.ko" +CPU_LIST=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2) +TEST_CPU_0=$(echo $CPU_LIST | awk '{print $1}') + +if [ $(echo $CPU_LIST | wc -w) -gt 1 ]; then + TEST_CPU_1=$(echo $CPU_LIST | awk '{print $2}') + NR_TEST=100000000 +else + TEST_CPU_1=$TEST_CPU_0 + NR_TEST=1000000 +fi + +# 1 if fails +exitcode=1 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +check_test_failed_prefix() { + if dmesg | grep -q 'page_frag_test failed:';then + echo "page_frag_test failed, please check dmesg" + exit $exitcode + fi +} + +# +# Static templates for testing of page_frag APIs. +# Also it is possible to pass any supported parameters manually. +# +SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1" +NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST" +ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1" + +check_test_requirements() +{ + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit $ksft_skip + fi + + if ! which insmod > /dev/null 2>&1; then + echo "$0: You need insmod installed" + exit $ksft_skip + fi + + if [ ! -f $DRIVER ]; then + echo "$0: You need to compile page_frag_test module" + exit $ksft_skip + fi +} + +run_nonaligned_check() +{ + echo "Run performance tests to evaluate how fast nonaligned alloc API is." + + insmod $DRIVER $NONALIGNED_PARAM > /dev/null 2>&1 +} + +run_aligned_check() +{ + echo "Run performance tests to evaluate how fast aligned alloc API is." + + insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1 +} + +run_smoke_check() +{ + echo "Run smoke test." + + insmod $DRIVER $SMOKE_PARAM > /dev/null 2>&1 +} + +usage() +{ + echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | " + echo "manual parameters" + echo + echo "Valid tests and parameters:" + echo + modinfo $DRIVER + echo + echo "Example usage:" + echo + echo "# Shows help message" + echo "$0" + echo + echo "# Smoke testing" + echo "$0 smoke" + echo + echo "# Performance testing for nonaligned alloc API" + echo "$0 nonaligned" + echo + echo "# Performance testing for aligned alloc API" + echo "$0 aligned" + echo + exit 0 +} + +function validate_passed_args() +{ + VALID_ARGS=`modinfo $DRIVER | awk '/parm:/ {print $2}' | sed 's/:.*//'` + + # + # Something has been passed, check it. + # + for passed_arg in $@; do + key=${passed_arg//=*/} + valid=0 + + for valid_arg in $VALID_ARGS; do + if [[ $key = $valid_arg ]]; then + valid=1 + break + fi + done + + if [[ $valid -ne 1 ]]; then + echo "Error: key is not correct: ${key}" + exit $exitcode + fi + done +} + +function run_manual_check() +{ + # + # Validate passed parameters. If there is wrong one, + # the script exists and does not execute further. + # + validate_passed_args $@ + + echo "Run the test with following parameters: $@" + insmod $DRIVER $@ > /dev/null 2>&1 +} + +function run_test() +{ + if [ $# -eq 0 ]; then + usage + else + if [[ "$1" = "smoke" ]]; then + run_smoke_check + elif [[ "$1" = "nonaligned" ]]; then + run_nonaligned_check + elif [[ "$1" = "aligned" ]]; then + run_aligned_check + else + run_manual_check $@ + fi + fi + + check_test_failed_prefix + + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +check_test_requirements +run_test $@ + +exit 0 diff --git a/tools/testing/selftests/mm/test_vmalloc.sh b/tools/testing/selftests/mm/test_vmalloc.sh index d73b846736f1..d39096723fca 100755 --- a/tools/testing/selftests/mm/test_vmalloc.sh +++ b/tools/testing/selftests/mm/test_vmalloc.sh @@ -47,14 +47,14 @@ check_test_requirements() fi } -run_perfformance_check() +run_performance_check() { echo "Run performance tests to evaluate how fast vmalloc allocation is." echo "It runs all test cases on one single CPU with sequential order." modprobe $DRIVER $PERF_PARAM > /dev/null 2>&1 echo "Done." - echo "Ccheck the kernel message buffer to see the summary." + echo "Check the kernel message buffer to see the summary." } run_stability_check() @@ -160,7 +160,7 @@ function run_test() usage else if [[ "$1" = "performance" ]]; then - run_perfformance_check + run_performance_check elif [[ "$1" = "stress" ]]; then run_stability_check elif [[ "$1" = "smoke" ]]; then diff --git a/tools/testing/selftests/mm/thp_settings.c b/tools/testing/selftests/mm/thp_settings.c new file mode 100644 index 000000000000..574bd0f8ae48 --- /dev/null +++ b/tools/testing/selftests/mm/thp_settings.c @@ -0,0 +1,401 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <fcntl.h> +#include <limits.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include "thp_settings.h" + +#define THP_SYSFS "/sys/kernel/mm/transparent_hugepage/" +#define MAX_SETTINGS_DEPTH 4 +static struct thp_settings settings_stack[MAX_SETTINGS_DEPTH]; +static int settings_index; +static struct thp_settings saved_settings; +static char dev_queue_read_ahead_path[PATH_MAX]; + +static const char * const thp_enabled_strings[] = { + "never", + "always", + "inherit", + "madvise", + NULL +}; + +static const char * const thp_defrag_strings[] = { + "always", + "defer", + "defer+madvise", + "madvise", + "never", + NULL +}; + +static const char * const shmem_enabled_strings[] = { + "never", + "always", + "within_size", + "advise", + "inherit", + "deny", + "force", + NULL +}; + +int read_file(const char *path, char *buf, size_t buflen) +{ + int fd; + ssize_t numread; + + fd = open(path, O_RDONLY); + if (fd == -1) + return 0; + + numread = read(fd, buf, buflen - 1); + if (numread < 1) { + close(fd); + return 0; + } + + buf[numread] = '\0'; + close(fd); + + return (unsigned int) numread; +} + +int write_file(const char *path, const char *buf, size_t buflen) +{ + int fd; + ssize_t numwritten; + + fd = open(path, O_WRONLY); + if (fd == -1) { + printf("open(%s)\n", path); + exit(EXIT_FAILURE); + return 0; + } + + numwritten = write(fd, buf, buflen - 1); + close(fd); + if (numwritten < 1) { + printf("write(%s)\n", buf); + exit(EXIT_FAILURE); + return 0; + } + + return (unsigned int) numwritten; +} + +unsigned long read_num(const char *path) +{ + char buf[21]; + + if (read_file(path, buf, sizeof(buf)) < 0) { + perror("read_file()"); + exit(EXIT_FAILURE); + } + + return strtoul(buf, NULL, 10); +} + +void write_num(const char *path, unsigned long num) +{ + char buf[21]; + + sprintf(buf, "%ld", num); + if (!write_file(path, buf, strlen(buf) + 1)) { + perror(path); + exit(EXIT_FAILURE); + } +} + +int thp_read_string(const char *name, const char * const strings[]) +{ + char path[PATH_MAX]; + char buf[256]; + char *c; + int ret; + + ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); + if (ret >= PATH_MAX) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + + if (!read_file(path, buf, sizeof(buf))) { + perror(path); + exit(EXIT_FAILURE); + } + + c = strchr(buf, '['); + if (!c) { + printf("%s: Parse failure\n", __func__); + exit(EXIT_FAILURE); + } + + c++; + memmove(buf, c, sizeof(buf) - (c - buf)); + + c = strchr(buf, ']'); + if (!c) { + printf("%s: Parse failure\n", __func__); + exit(EXIT_FAILURE); + } + *c = '\0'; + + ret = 0; + while (strings[ret]) { + if (!strcmp(strings[ret], buf)) + return ret; + ret++; + } + + printf("Failed to parse %s\n", name); + exit(EXIT_FAILURE); +} + +void thp_write_string(const char *name, const char *val) +{ + char path[PATH_MAX]; + int ret; + + ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); + if (ret >= PATH_MAX) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + + if (!write_file(path, val, strlen(val) + 1)) { + perror(path); + exit(EXIT_FAILURE); + } +} + +unsigned long thp_read_num(const char *name) +{ + char path[PATH_MAX]; + int ret; + + ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); + if (ret >= PATH_MAX) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + return read_num(path); +} + +void thp_write_num(const char *name, unsigned long num) +{ + char path[PATH_MAX]; + int ret; + + ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); + if (ret >= PATH_MAX) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + write_num(path, num); +} + +void thp_read_settings(struct thp_settings *settings) +{ + unsigned long orders = thp_supported_orders(); + unsigned long shmem_orders = thp_shmem_supported_orders(); + char path[PATH_MAX]; + int i; + + *settings = (struct thp_settings) { + .thp_enabled = thp_read_string("enabled", thp_enabled_strings), + .thp_defrag = thp_read_string("defrag", thp_defrag_strings), + .shmem_enabled = + thp_read_string("shmem_enabled", shmem_enabled_strings), + .use_zero_page = thp_read_num("use_zero_page"), + }; + settings->khugepaged = (struct khugepaged_settings) { + .defrag = thp_read_num("khugepaged/defrag"), + .alloc_sleep_millisecs = + thp_read_num("khugepaged/alloc_sleep_millisecs"), + .scan_sleep_millisecs = + thp_read_num("khugepaged/scan_sleep_millisecs"), + .max_ptes_none = thp_read_num("khugepaged/max_ptes_none"), + .max_ptes_swap = thp_read_num("khugepaged/max_ptes_swap"), + .max_ptes_shared = thp_read_num("khugepaged/max_ptes_shared"), + .pages_to_scan = thp_read_num("khugepaged/pages_to_scan"), + }; + if (dev_queue_read_ahead_path[0]) + settings->read_ahead_kb = read_num(dev_queue_read_ahead_path); + + for (i = 0; i < NR_ORDERS; i++) { + if (!((1 << i) & orders)) { + settings->hugepages[i].enabled = THP_NEVER; + continue; + } + snprintf(path, PATH_MAX, "hugepages-%ukB/enabled", + (getpagesize() >> 10) << i); + settings->hugepages[i].enabled = + thp_read_string(path, thp_enabled_strings); + } + + for (i = 0; i < NR_ORDERS; i++) { + if (!((1 << i) & shmem_orders)) { + settings->shmem_hugepages[i].enabled = SHMEM_NEVER; + continue; + } + snprintf(path, PATH_MAX, "hugepages-%ukB/shmem_enabled", + (getpagesize() >> 10) << i); + settings->shmem_hugepages[i].enabled = + thp_read_string(path, shmem_enabled_strings); + } +} + +void thp_write_settings(struct thp_settings *settings) +{ + struct khugepaged_settings *khugepaged = &settings->khugepaged; + unsigned long orders = thp_supported_orders(); + unsigned long shmem_orders = thp_shmem_supported_orders(); + char path[PATH_MAX]; + int enabled; + int i; + + thp_write_string("enabled", thp_enabled_strings[settings->thp_enabled]); + thp_write_string("defrag", thp_defrag_strings[settings->thp_defrag]); + thp_write_string("shmem_enabled", + shmem_enabled_strings[settings->shmem_enabled]); + thp_write_num("use_zero_page", settings->use_zero_page); + + thp_write_num("khugepaged/defrag", khugepaged->defrag); + thp_write_num("khugepaged/alloc_sleep_millisecs", + khugepaged->alloc_sleep_millisecs); + thp_write_num("khugepaged/scan_sleep_millisecs", + khugepaged->scan_sleep_millisecs); + thp_write_num("khugepaged/max_ptes_none", khugepaged->max_ptes_none); + thp_write_num("khugepaged/max_ptes_swap", khugepaged->max_ptes_swap); + thp_write_num("khugepaged/max_ptes_shared", khugepaged->max_ptes_shared); + thp_write_num("khugepaged/pages_to_scan", khugepaged->pages_to_scan); + + if (dev_queue_read_ahead_path[0]) + write_num(dev_queue_read_ahead_path, settings->read_ahead_kb); + + for (i = 0; i < NR_ORDERS; i++) { + if (!((1 << i) & orders)) + continue; + snprintf(path, PATH_MAX, "hugepages-%ukB/enabled", + (getpagesize() >> 10) << i); + enabled = settings->hugepages[i].enabled; + thp_write_string(path, thp_enabled_strings[enabled]); + } + + for (i = 0; i < NR_ORDERS; i++) { + if (!((1 << i) & shmem_orders)) + continue; + snprintf(path, PATH_MAX, "hugepages-%ukB/shmem_enabled", + (getpagesize() >> 10) << i); + enabled = settings->shmem_hugepages[i].enabled; + thp_write_string(path, shmem_enabled_strings[enabled]); + } +} + +struct thp_settings *thp_current_settings(void) +{ + if (!settings_index) { + printf("Fail: No settings set"); + exit(EXIT_FAILURE); + } + return settings_stack + settings_index - 1; +} + +void thp_push_settings(struct thp_settings *settings) +{ + if (settings_index >= MAX_SETTINGS_DEPTH) { + printf("Fail: Settings stack exceeded"); + exit(EXIT_FAILURE); + } + settings_stack[settings_index++] = *settings; + thp_write_settings(thp_current_settings()); +} + +void thp_pop_settings(void) +{ + if (settings_index <= 0) { + printf("Fail: Settings stack empty"); + exit(EXIT_FAILURE); + } + --settings_index; + thp_write_settings(thp_current_settings()); +} + +void thp_restore_settings(void) +{ + thp_write_settings(&saved_settings); +} + +void thp_save_settings(void) +{ + thp_read_settings(&saved_settings); +} + +void thp_set_read_ahead_path(char *path) +{ + if (!path) { + dev_queue_read_ahead_path[0] = '\0'; + return; + } + + strncpy(dev_queue_read_ahead_path, path, + sizeof(dev_queue_read_ahead_path)); + dev_queue_read_ahead_path[sizeof(dev_queue_read_ahead_path) - 1] = '\0'; +} + +static unsigned long __thp_supported_orders(bool is_shmem) +{ + unsigned long orders = 0; + char path[PATH_MAX]; + char buf[256]; + int ret, i; + char anon_dir[] = "enabled"; + char shmem_dir[] = "shmem_enabled"; + + for (i = 0; i < NR_ORDERS; i++) { + ret = snprintf(path, PATH_MAX, THP_SYSFS "hugepages-%ukB/%s", + (getpagesize() >> 10) << i, is_shmem ? shmem_dir : anon_dir); + if (ret >= PATH_MAX) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + + ret = read_file(path, buf, sizeof(buf)); + if (ret) + orders |= 1UL << i; + } + + return orders; +} + +unsigned long thp_supported_orders(void) +{ + return __thp_supported_orders(false); +} + +unsigned long thp_shmem_supported_orders(void) +{ + return __thp_supported_orders(true); +} + +bool thp_available(void) +{ + if (access(THP_SYSFS, F_OK) != 0) + return false; + return true; +} + +bool thp_is_enabled(void) +{ + if (!thp_available()) + return false; + + int mode = thp_read_string("enabled", thp_enabled_strings); + + /* THP is considered enabled if it's either "always" or "madvise" */ + return mode == 1 || mode == 3; +} diff --git a/tools/testing/selftests/mm/thp_settings.h b/tools/testing/selftests/mm/thp_settings.h new file mode 100644 index 000000000000..76eeb712e5f1 --- /dev/null +++ b/tools/testing/selftests/mm/thp_settings.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __THP_SETTINGS_H__ +#define __THP_SETTINGS_H__ + +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> + +enum thp_enabled { + THP_NEVER, + THP_ALWAYS, + THP_INHERIT, + THP_MADVISE, +}; + +enum thp_defrag { + THP_DEFRAG_ALWAYS, + THP_DEFRAG_DEFER, + THP_DEFRAG_DEFER_MADVISE, + THP_DEFRAG_MADVISE, + THP_DEFRAG_NEVER, +}; + +enum shmem_enabled { + SHMEM_NEVER, + SHMEM_ALWAYS, + SHMEM_WITHIN_SIZE, + SHMEM_ADVISE, + SHMEM_INHERIT, + SHMEM_DENY, + SHMEM_FORCE, +}; + +#define NR_ORDERS 20 + +struct hugepages_settings { + enum thp_enabled enabled; +}; + +struct khugepaged_settings { + bool defrag; + unsigned int alloc_sleep_millisecs; + unsigned int scan_sleep_millisecs; + unsigned int max_ptes_none; + unsigned int max_ptes_swap; + unsigned int max_ptes_shared; + unsigned long pages_to_scan; +}; + +struct shmem_hugepages_settings { + enum shmem_enabled enabled; +}; + +struct thp_settings { + enum thp_enabled thp_enabled; + enum thp_defrag thp_defrag; + enum shmem_enabled shmem_enabled; + bool use_zero_page; + struct khugepaged_settings khugepaged; + unsigned long read_ahead_kb; + struct hugepages_settings hugepages[NR_ORDERS]; + struct shmem_hugepages_settings shmem_hugepages[NR_ORDERS]; +}; + +int read_file(const char *path, char *buf, size_t buflen); +int write_file(const char *path, const char *buf, size_t buflen); +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); +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); +void thp_read_settings(struct thp_settings *settings); +struct thp_settings *thp_current_settings(void); +void thp_push_settings(struct thp_settings *settings); +void thp_pop_settings(void); +void thp_restore_settings(void); +void thp_save_settings(void); + +void thp_set_read_ahead_path(char *path); +unsigned long thp_supported_orders(void); +unsigned long thp_shmem_supported_orders(void); + +bool thp_available(void); +bool thp_is_enabled(void); + +#endif /* __THP_SETTINGS_H__ */ diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c index 380ab5f0a534..77813d34dcc2 100644 --- a/tools/testing/selftests/mm/thuge-gen.c +++ b/tools/testing/selftests/mm/thuge-gen.c @@ -3,7 +3,8 @@ Before running this huge pages for each huge page size must have been reserved. - For large pages beyond MAX_ORDER (like 1GB on x86) boot options must be used. + For large pages beyond MAX_PAGE_ORDER (like 1GB on x86) boot options must + be used. 1GB wouldn't be tested if it isn't available. Also shmmax must be increased. And you need to run as root to work around some weird permissions in shm. And nothing using huge pages should run in parallel. @@ -12,8 +13,9 @@ sudo ipcs | awk '$1 == "0x00000000" {print $2}' | xargs -n1 sudo ipcrm -m (warning this will remove all if someone else uses them) */ -#define _GNU_SOURCE 1 +#define _GNU_SOURCE #include <sys/mman.h> +#include <linux/mman.h> #include <stdlib.h> #include <stdio.h> #include <sys/ipc.h> @@ -25,29 +27,29 @@ #include <stdarg.h> #include <string.h> #include "vm_util.h" +#include "kselftest.h" -#define err(x) perror(x), exit(1) - -#define MAP_HUGE_2MB (21 << MAP_HUGE_SHIFT) -#define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT) -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f #if !defined(MAP_HUGETLB) #define MAP_HUGETLB 0x40000 #endif #define SHM_HUGETLB 04000 /* segment will use huge TLB pages */ +#ifndef SHM_HUGE_SHIFT #define SHM_HUGE_SHIFT 26 +#endif +#ifndef SHM_HUGE_MASK #define SHM_HUGE_MASK 0x3f +#endif +#ifndef SHM_HUGE_2MB #define SHM_HUGE_2MB (21 << SHM_HUGE_SHIFT) +#endif +#ifndef SHM_HUGE_1GB #define SHM_HUGE_1GB (30 << SHM_HUGE_SHIFT) +#endif #define NUM_PAGESIZES 5 - #define NUM_PAGES 4 -#define Dprintf(fmt...) // printf(fmt) - unsigned long page_sizes[NUM_PAGESIZES]; int num_page_sizes; @@ -59,28 +61,15 @@ int ilog2(unsigned long v) return l; } -void find_pagesizes(void) -{ - glob_t g; - int i; - glob("/sys/kernel/mm/hugepages/hugepages-*kB", 0, NULL, &g); - assert(g.gl_pathc <= NUM_PAGESIZES); - for (i = 0; i < g.gl_pathc; i++) { - sscanf(g.gl_pathv[i], "/sys/kernel/mm/hugepages/hugepages-%lukB", - &page_sizes[i]); - page_sizes[i] <<= 10; - printf("Found %luMB\n", page_sizes[i] >> 20); - } - num_page_sizes = g.gl_pathc; - globfree(&g); -} - void show(unsigned long ps) { char buf[100]; + if (ps == getpagesize()) return; - printf("%luMB: ", ps >> 20); + + ksft_print_msg("%luMB: ", ps >> 20); + fflush(stdout); snprintf(buf, sizeof buf, "cat /sys/kernel/mm/hugepages/hugepages-%lukB/free_hugepages", @@ -88,153 +77,158 @@ void show(unsigned long ps) system(buf); } -unsigned long read_sysfs(int warn, char *fmt, ...) +unsigned long read_free(unsigned long ps) { - char *line = NULL; - size_t linelen = 0; - char buf[100]; - FILE *f; - va_list ap; unsigned long val = 0; + char buf[100]; - va_start(ap, fmt); - vsnprintf(buf, sizeof buf, fmt, ap); - va_end(ap); + snprintf(buf, sizeof(buf), + "/sys/kernel/mm/hugepages/hugepages-%lukB/free_hugepages", + ps >> 10); + if (read_sysfs(buf, &val) && ps != getpagesize()) + ksft_print_msg("missing %s\n", buf); - f = fopen(buf, "r"); - if (!f) { - if (warn) - printf("missing %s\n", buf); - return 0; - } - if (getline(&line, &linelen, f) > 0) { - sscanf(line, "%lu", &val); - } - fclose(f); - free(line); return val; } -unsigned long read_free(unsigned long ps) -{ - return read_sysfs(ps != getpagesize(), - "/sys/kernel/mm/hugepages/hugepages-%lukB/free_hugepages", - ps >> 10); -} - void test_mmap(unsigned long size, unsigned flags) { char *map; unsigned long before, after; - int err; before = read_free(size); map = mmap(NULL, size*NUM_PAGES, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS|MAP_HUGETLB|flags, -1, 0); + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap: %s\n", strerror(errno)); - if (map == (char *)-1) err("mmap"); memset(map, 0xff, size*NUM_PAGES); after = read_free(size); - Dprintf("before %lu after %lu diff %ld size %lu\n", - before, after, before - after, size); - assert(size == getpagesize() || (before - after) == NUM_PAGES); + show(size); - err = munmap(map, size); - assert(!err); + ksft_test_result(size == getpagesize() || (before - after) == NUM_PAGES, + "%s mmap %lu %x\n", __func__, size, flags); + + if (munmap(map, size * NUM_PAGES)) + ksft_exit_fail_msg("%s: unmap %s\n", __func__, strerror(errno)); } void test_shmget(unsigned long size, unsigned flags) { int id; unsigned long before, after; - int err; + struct shm_info i; + char *map; before = read_free(size); id = shmget(IPC_PRIVATE, size * NUM_PAGES, IPC_CREAT|0600|flags); - if (id < 0) err("shmget"); - - struct shm_info i; - if (shmctl(id, SHM_INFO, (void *)&i) < 0) err("shmctl"); - Dprintf("alloc %lu res %lu\n", i.shm_tot, i.shm_rss); + if (id < 0) { + if (errno == EPERM) { + ksft_test_result_skip("shmget requires root privileges: %s\n", + strerror(errno)); + return; + } + ksft_exit_fail_msg("shmget: %s\n", strerror(errno)); + } + if (shmctl(id, SHM_INFO, (void *)&i) < 0) + ksft_exit_fail_msg("shmctl: %s\n", strerror(errno)); - Dprintf("id %d\n", id); - char *map = shmat(id, NULL, 0600); - if (map == (char*)-1) err("shmat"); + map = shmat(id, NULL, 0600); + if (map == MAP_FAILED) + ksft_exit_fail_msg("shmat: %s\n", strerror(errno)); shmctl(id, IPC_RMID, NULL); memset(map, 0xff, size*NUM_PAGES); after = read_free(size); - Dprintf("before %lu after %lu diff %ld size %lu\n", - before, after, before - after, size); - assert(size == getpagesize() || (before - after) == NUM_PAGES); show(size); - err = shmdt(map); - assert(!err); + ksft_test_result(size == getpagesize() || (before - after) == NUM_PAGES, + "%s: mmap %lu %x\n", __func__, size, flags); + if (shmdt(map)) + ksft_exit_fail_msg("%s: shmdt: %s\n", __func__, strerror(errno)); } -void sanity_checks(void) +void find_pagesizes(void) { - int i; unsigned long largest = getpagesize(); + unsigned long shmmax_val = 0; + int i; + glob_t g; - for (i = 0; i < num_page_sizes; i++) { - if (page_sizes[i] > largest) + glob("/sys/kernel/mm/hugepages/hugepages-*kB", 0, NULL, &g); + assert(g.gl_pathc <= NUM_PAGESIZES); + for (i = 0; (i < g.gl_pathc) && (num_page_sizes < NUM_PAGESIZES); i++) { + sscanf(g.gl_pathv[i], "/sys/kernel/mm/hugepages/hugepages-%lukB", + &page_sizes[num_page_sizes]); + page_sizes[num_page_sizes] <<= 10; + ksft_print_msg("Found %luMB\n", page_sizes[i] >> 20); + + if (page_sizes[num_page_sizes] > largest) largest = page_sizes[i]; - if (read_free(page_sizes[i]) < NUM_PAGES) { - printf("Not enough huge pages for page size %lu MB, need %u\n", - page_sizes[i] >> 20, - NUM_PAGES); - exit(0); - } + if (read_free(page_sizes[num_page_sizes]) >= NUM_PAGES) + num_page_sizes++; + else + ksft_print_msg("SKIP for size %lu MB as not enough huge pages, need %u\n", + page_sizes[num_page_sizes] >> 20, NUM_PAGES); } + globfree(&g); - if (read_sysfs(0, "/proc/sys/kernel/shmmax") < NUM_PAGES * largest) { - printf("Please do echo %lu > /proc/sys/kernel/shmmax", largest * NUM_PAGES); - exit(0); + read_sysfs("/proc/sys/kernel/shmmax", &shmmax_val); + if (shmmax_val < NUM_PAGES * largest) { + ksft_print_msg("WARNING: shmmax is too small to run this test.\n"); + ksft_print_msg("Please run the following command to increase shmmax:\n"); + ksft_print_msg("echo %lu > /proc/sys/kernel/shmmax\n", largest * NUM_PAGES); + ksft_exit_skip("Test skipped due to insufficient shmmax value.\n"); } #if defined(__x86_64__) if (largest != 1U<<30) { - printf("No GB pages available on x86-64\n" - "Please boot with hugepagesz=1G hugepages=%d\n", NUM_PAGES); - exit(0); + ksft_exit_skip("No GB pages available on x86-64\n" + "Please boot with hugepagesz=1G hugepages=%d\n", NUM_PAGES); } #endif } int main(void) { - int i; unsigned default_hps = default_huge_page_size(); + int i; + + ksft_print_header(); find_pagesizes(); - sanity_checks(); + if (!num_page_sizes) + ksft_finished(); + + ksft_set_plan(2 * num_page_sizes + 3); for (i = 0; i < num_page_sizes; i++) { unsigned long ps = page_sizes[i]; int arg = ilog2(ps) << MAP_HUGE_SHIFT; - printf("Testing %luMB mmap with shift %x\n", ps >> 20, arg); + + ksft_print_msg("Testing %luMB mmap with shift %x\n", ps >> 20, arg); test_mmap(ps, MAP_HUGETLB | arg); } - printf("Testing default huge mmap\n"); - test_mmap(default_hps, SHM_HUGETLB); - puts("Testing non-huge shmget"); + ksft_print_msg("Testing default huge mmap\n"); + test_mmap(default_hps, MAP_HUGETLB); + + ksft_print_msg("Testing non-huge shmget\n"); test_shmget(getpagesize(), 0); for (i = 0; i < num_page_sizes; i++) { unsigned long ps = page_sizes[i]; int arg = ilog2(ps) << SHM_HUGE_SHIFT; - printf("Testing %luMB shmget with shift %x\n", ps >> 20, arg); + ksft_print_msg("Testing %luMB shmget with shift %x\n", ps >> 20, arg); test_shmget(ps, SHM_HUGETLB | arg); } - puts("default huge shmget"); + + ksft_print_msg("default huge shmget\n"); test_shmget(default_hps, SHM_HUGETLB); - return 0; + ksft_finished(); } diff --git a/tools/testing/selftests/mm/transhuge-stress.c b/tools/testing/selftests/mm/transhuge-stress.c index ba9d37ad3a89..bcad47c09518 100644 --- a/tools/testing/selftests/mm/transhuge-stress.c +++ b/tools/testing/selftests/mm/transhuge-stress.c @@ -16,6 +16,7 @@ #include <string.h> #include <sys/mman.h> #include "vm_util.h" +#include "kselftest.h" int backing_fd = -1; int mmap_flags = MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE; @@ -25,13 +26,16 @@ int main(int argc, char **argv) { size_t ram, len; void *ptr, *p; - struct timespec a, b; + struct timespec start, a, b; int i = 0; char *name = NULL; double s; uint8_t *map; size_t map_len; int pagemap_fd; + int duration = 0; + + ksft_print_header(); ram = sysconf(_SC_PHYS_PAGES); if (ram > SIZE_MAX / psize() / 4) @@ -42,17 +46,22 @@ int main(int argc, char **argv) while (++i < argc) { if (!strcmp(argv[i], "-h")) - errx(1, "usage: %s [size in MiB]", argv[0]); + ksft_exit_fail_msg("usage: %s [-f <filename>] [-d <duration>] [size in MiB]\n", + argv[0]); else if (!strcmp(argv[i], "-f")) name = argv[++i]; + else if (!strcmp(argv[i], "-d")) + duration = atoi(argv[++i]); else len = atoll(argv[i]) << 20; } + ksft_set_plan(1); + if (name) { backing_fd = open(name, O_RDWR); if (backing_fd == -1) - errx(2, "open %s", name); + ksft_exit_fail_msg("open %s\n", name); mmap_flags = MAP_SHARED; } @@ -62,21 +71,23 @@ int main(int argc, char **argv) pagemap_fd = open("/proc/self/pagemap", O_RDONLY); if (pagemap_fd < 0) - err(2, "open pagemap"); + ksft_exit_fail_msg("open pagemap\n"); len -= len % HPAGE_SIZE; ptr = mmap(NULL, len + HPAGE_SIZE, PROT_RW, mmap_flags, backing_fd, 0); if (ptr == MAP_FAILED) - err(2, "initial mmap"); + ksft_exit_fail_msg("initial mmap"); ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE; if (madvise(ptr, len, MADV_HUGEPAGE)) - err(2, "MADV_HUGEPAGE"); + ksft_exit_fail_msg("MADV_HUGEPAGE"); map_len = ram >> (HPAGE_SHIFT - 1); map = malloc(map_len); if (!map) - errx(2, "map malloc"); + ksft_exit_fail_msg("map malloc\n"); + + clock_gettime(CLOCK_MONOTONIC, &start); while (1) { int nr_succeed = 0, nr_failed = 0, nr_pages = 0; @@ -98,7 +109,7 @@ int main(int argc, char **argv) if (idx >= map_len) { map = realloc(map, idx + 1); if (!map) - errx(2, "map realloc"); + ksft_exit_fail_msg("map realloc\n"); memset(map + map_len, 0, idx + 1 - map_len); map_len = idx + 1; } @@ -109,14 +120,19 @@ int main(int argc, char **argv) /* split transhuge page, keep last page */ if (madvise(p, HPAGE_SIZE - psize(), MADV_DONTNEED)) - err(2, "MADV_DONTNEED"); + ksft_exit_fail_msg("MADV_DONTNEED"); } clock_gettime(CLOCK_MONOTONIC, &b); s = b.tv_sec - a.tv_sec + (b.tv_nsec - a.tv_nsec) / 1000000000.; - warnx("%.3f s/loop, %.3f ms/page, %10.3f MiB/s\t" - "%4d succeed, %4d failed, %4d different pages", - s, s * 1000 / (len >> HPAGE_SHIFT), len / s / (1 << 20), - nr_succeed, nr_failed, nr_pages); + ksft_print_msg("%.3f s/loop, %.3f ms/page, %10.3f MiB/s\t" + "%4d succeed, %4d failed, %4d different pages\n", + s, s * 1000 / (len >> HPAGE_SHIFT), len / s / (1 << 20), + nr_succeed, nr_failed, nr_pages); + + if (duration > 0 && b.tv_sec - start.tv_sec >= duration) { + ksft_test_result_pass("Completed\n"); + ksft_finished(); + } } } diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index ba20d7504022..edd02328f77b 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -7,16 +7,28 @@ #include "uffd-common.h" -#define BASE_PMD_ADDR ((void *)(1UL << 30)) - -volatile bool test_uffdio_copy_eexist = true; -unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; -char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; -int uffd = -1, uffd_flags, finished, *pipefd, test_type; -bool map_shared; -bool test_uffdio_wp = true; -unsigned long long *count_verify; uffd_test_ops_t *uffd_test_ops; +uffd_test_case_ops_t *uffd_test_case_ops; + + +/* pthread_mutex_t starts at page offset 0 */ +pthread_mutex_t *area_mutex(char *area, unsigned long nr, uffd_global_test_opts_t *gopts) +{ + return (pthread_mutex_t *) (area + nr * gopts->page_size); +} + +/* + * count is placed in the page after pthread_mutex_t naturally aligned + * to avoid non alignment faults on non-x86 archs. + */ +volatile unsigned long long *area_count(char *area, unsigned long nr, + uffd_global_test_opts_t *gopts) +{ + return (volatile unsigned long long *) + ((unsigned long)(area + nr * gopts->page_size + + sizeof(pthread_mutex_t) + sizeof(unsigned long long) - 1) & + ~(unsigned long)(sizeof(unsigned long long) - 1)); +} static int uffd_mem_fd_create(off_t mem_size, bool hugetlb) { @@ -38,15 +50,15 @@ static int uffd_mem_fd_create(off_t mem_size, bool hugetlb) return mem_fd; } -static void anon_release_pages(char *rel_area) +static void anon_release_pages(uffd_global_test_opts_t *gopts, char *rel_area) { - if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); } -static int anon_allocate_area(void **alloc_area, bool is_src) +static int anon_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src) { - *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + *alloc_area = mmap(NULL, gopts->nr_pages * gopts->page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (*alloc_area == MAP_FAILED) { *alloc_area = NULL; @@ -55,31 +67,32 @@ static int anon_allocate_area(void **alloc_area, bool is_src) return 0; } -static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) +static void noop_alias_mapping(uffd_global_test_opts_t *gopts, __u64 *start, + size_t len, unsigned long offset) { } -static void hugetlb_release_pages(char *rel_area) +static void hugetlb_release_pages(uffd_global_test_opts_t *gopts, char *rel_area) { - if (!map_shared) { - if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + if (!gopts->map_shared) { + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); } else { - if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_REMOVE)) err("madvise(MADV_REMOVE) failed"); } } -static int hugetlb_allocate_area(void **alloc_area, bool is_src) +static int hugetlb_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src) { - off_t size = nr_pages * page_size; + off_t size = gopts->nr_pages * gopts->page_size; off_t offset = is_src ? 0 : size; void *area_alias = NULL; char **alloc_area_alias; int mem_fd = uffd_mem_fd_create(size * 2, true); *alloc_area = mmap(NULL, size, PROT_READ | PROT_WRITE, - (map_shared ? MAP_SHARED : MAP_PRIVATE) | + (gopts->map_shared ? MAP_SHARED : MAP_PRIVATE) | (is_src ? 0 : MAP_NORESERVE), mem_fd, offset); if (*alloc_area == MAP_FAILED) { @@ -87,7 +100,7 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src) return -errno; } - if (map_shared) { + if (gopts->map_shared) { area_alias = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, mem_fd, offset); if (area_alias == MAP_FAILED) @@ -95,9 +108,9 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src) } if (is_src) { - alloc_area_alias = &area_src_alias; + alloc_area_alias = &gopts->area_src_alias; } else { - alloc_area_alias = &area_dst_alias; + alloc_area_alias = &gopts->area_dst_alias; } if (area_alias) *alloc_area_alias = area_alias; @@ -106,73 +119,82 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src) return 0; } -static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) +static void hugetlb_alias_mapping(uffd_global_test_opts_t *gopts, __u64 *start, + size_t len, unsigned long offset) { - if (!map_shared) + if (!gopts->map_shared) return; - *start = (unsigned long) area_dst_alias + offset; + *start = (unsigned long) gopts->area_dst_alias + offset; } -static void shmem_release_pages(char *rel_area) +static void shmem_release_pages(uffd_global_test_opts_t *gopts, char *rel_area) { - if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_REMOVE)) err("madvise(MADV_REMOVE) failed"); } -static int shmem_allocate_area(void **alloc_area, bool is_src) +static int shmem_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src) { void *area_alias = NULL; - size_t bytes = nr_pages * page_size, hpage_size = read_pmd_pagesize(); + size_t bytes = gopts->nr_pages * gopts->page_size, hpage_size = read_pmd_pagesize(); unsigned long offset = is_src ? 0 : bytes; char *p = NULL, *p_alias = NULL; int mem_fd = uffd_mem_fd_create(bytes * 2, false); + size_t region_size = bytes * 2 + hpage_size; + + void *reserve = mmap(NULL, region_size, PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, + -1, 0); + if (reserve == MAP_FAILED) { + close(mem_fd); + return -errno; + } - /* TODO: clean this up. Use a static addr is ugly */ - p = BASE_PMD_ADDR; - if (!is_src) - /* src map + alias + interleaved hpages */ - p += 2 * (bytes + hpage_size); + p = reserve; p_alias = p; p_alias += bytes; p_alias += hpage_size; /* Prevent src/dst VMA merge */ - *alloc_area = mmap(p, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, + *alloc_area = mmap(p, bytes, PROT_READ | PROT_WRITE, MAP_FIXED | MAP_SHARED, mem_fd, offset); if (*alloc_area == MAP_FAILED) { *alloc_area = NULL; + munmap(reserve, region_size); + close(mem_fd); return -errno; } if (*alloc_area != p) err("mmap of memfd failed at %p", p); - area_alias = mmap(p_alias, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, + area_alias = mmap(p_alias, bytes, PROT_READ | PROT_WRITE, MAP_FIXED | MAP_SHARED, mem_fd, offset); if (area_alias == MAP_FAILED) { - munmap(*alloc_area, bytes); *alloc_area = NULL; + munmap(reserve, region_size); + close(mem_fd); return -errno; } if (area_alias != p_alias) err("mmap of anonymous memory failed at %p", p_alias); if (is_src) - area_src_alias = area_alias; + gopts->area_src_alias = area_alias; else - area_dst_alias = area_alias; + gopts->area_dst_alias = area_alias; close(mem_fd); return 0; } -static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) +static void shmem_alias_mapping(uffd_global_test_opts_t *gopts, __u64 *start, + size_t len, unsigned long offset) { - *start = (unsigned long)area_dst_alias + offset; + *start = (unsigned long)gopts->area_dst_alias + offset; } -static void shmem_check_pmd_mapping(void *p, int expect_nr_hpages) +static void shmem_check_pmd_mapping(uffd_global_test_opts_t *gopts, void *p, int expect_nr_hpages) { - if (!check_huge_shmem(area_dst_alias, expect_nr_hpages, + if (!check_huge_shmem(gopts->area_dst_alias, expect_nr_hpages, read_pmd_pagesize())) err("Did not find expected %d number of hugepages", expect_nr_hpages); @@ -232,18 +254,18 @@ void uffd_stats_report(struct uffd_args *args, int n_cpus) printf("\n"); } -int userfaultfd_open(uint64_t *features) +int userfaultfd_open(uffd_global_test_opts_t *gopts, uint64_t *features) { struct uffdio_api uffdio_api; - uffd = uffd_open(UFFD_FLAGS); - if (uffd < 0) + gopts->uffd = uffd_open(UFFD_FLAGS); + if (gopts->uffd < 0) return -1; - uffd_flags = fcntl(uffd, F_GETFD, NULL); + gopts->uffd_flags = fcntl(gopts->uffd, F_GETFD, NULL); uffdio_api.api = UFFD_API; uffdio_api.features = *features; - if (ioctl(uffd, UFFDIO_API, &uffdio_api)) + if (ioctl(gopts->uffd, UFFDIO_API, &uffdio_api)) /* Probably lack of CAP_PTRACE? */ return -1; if (uffdio_api.api != UFFD_API) @@ -253,76 +275,90 @@ int userfaultfd_open(uint64_t *features) return 0; } -static inline void munmap_area(void **area) +static inline void munmap_area(uffd_global_test_opts_t *gopts, void **area) { if (*area) - if (munmap(*area, nr_pages * page_size)) + if (munmap(*area, gopts->nr_pages * gopts->page_size)) err("munmap"); *area = NULL; } -static void uffd_test_ctx_clear(void) +void uffd_test_ctx_clear(uffd_global_test_opts_t *gopts) { size_t i; - if (pipefd) { - for (i = 0; i < nr_cpus * 2; ++i) { - if (close(pipefd[i])) + if (gopts->pipefd) { + for (i = 0; i < gopts->nr_parallel * 2; ++i) { + if (close(gopts->pipefd[i])) err("close pipefd"); } - free(pipefd); - pipefd = NULL; + free(gopts->pipefd); + gopts->pipefd = NULL; } - if (count_verify) { - free(count_verify); - count_verify = NULL; + if (gopts->count_verify) { + free(gopts->count_verify); + gopts->count_verify = NULL; } - if (uffd != -1) { - if (close(uffd)) + if (gopts->uffd != -1) { + if (close(gopts->uffd)) err("close uffd"); - uffd = -1; + gopts->uffd = -1; } - munmap_area((void **)&area_src); - munmap_area((void **)&area_src_alias); - munmap_area((void **)&area_dst); - munmap_area((void **)&area_dst_alias); - munmap_area((void **)&area_remap); + munmap_area(gopts, (void **)&gopts->area_src); + munmap_area(gopts, (void **)&gopts->area_src_alias); + munmap_area(gopts, (void **)&gopts->area_dst); + munmap_area(gopts, (void **)&gopts->area_dst_alias); + munmap_area(gopts, (void **)&gopts->area_remap); } -int uffd_test_ctx_init(uint64_t features, const char **errmsg) +int uffd_test_ctx_init(uffd_global_test_opts_t *gopts, uint64_t features, const char **errmsg) { unsigned long nr, cpu; int ret; - uffd_test_ctx_clear(); + gopts->area_src_alias = NULL; + gopts->area_dst_alias = NULL; + gopts->area_remap = NULL; + + if (uffd_test_case_ops && uffd_test_case_ops->pre_alloc) { + ret = uffd_test_case_ops->pre_alloc(gopts, errmsg); + if (ret) + return ret; + } - ret = uffd_test_ops->allocate_area((void **)&area_src, true); - ret |= uffd_test_ops->allocate_area((void **)&area_dst, false); + ret = uffd_test_ops->allocate_area(gopts, (void **) &gopts->area_src, true); + ret |= uffd_test_ops->allocate_area(gopts, (void **) &gopts->area_dst, false); if (ret) { if (errmsg) *errmsg = "memory allocation failed"; return ret; } - ret = userfaultfd_open(&features); + if (uffd_test_case_ops && uffd_test_case_ops->post_alloc) { + ret = uffd_test_case_ops->post_alloc(gopts, errmsg); + if (ret) + return ret; + } + + ret = userfaultfd_open(gopts, &features); if (ret) { if (errmsg) - *errmsg = "possible lack of priviledge"; + *errmsg = "possible lack of privilege"; return ret; } - count_verify = malloc(nr_pages * sizeof(unsigned long long)); - if (!count_verify) + gopts->count_verify = malloc(gopts->nr_pages * sizeof(unsigned long long)); + if (!gopts->count_verify) err("count_verify"); - for (nr = 0; nr < nr_pages; nr++) { - *area_mutex(area_src, nr) = + for (nr = 0; nr < gopts->nr_pages; nr++) { + *area_mutex(gopts->area_src, nr, gopts) = (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER; - count_verify[nr] = *area_count(area_src, nr) = 1; + gopts->count_verify[nr] = *area_count(gopts->area_src, nr, gopts) = 1; /* * In the transition between 255 to 256, powerpc will * read out of order in my_bcmp and see both bytes as @@ -330,13 +366,13 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg) * after the count, to avoid my_bcmp to trigger false * positives. */ - *(area_count(area_src, nr) + 1) = 1; + *(area_count(gopts->area_src, nr, gopts) + 1) = 1; } /* * After initialization of area_src, we must explicitly release pages * for area_dst to make sure it's fully empty. Otherwise we could have - * some area_dst pages be errornously initialized with zero pages, + * some area_dst pages be erroneously initialized with zero pages, * hence we could hit memory corruption later in the test. * * One example is when THP is globally enabled, above allocate_area() @@ -351,13 +387,13 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg) * proactively split the thp and drop any accidentally initialized * pages within area_dst. */ - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); - pipefd = malloc(sizeof(int) * nr_cpus * 2); - if (!pipefd) + gopts->pipefd = malloc(sizeof(int) * gopts->nr_parallel * 2); + if (!gopts->pipefd) err("pipefd"); - for (cpu = 0; cpu < nr_cpus; cpu++) - if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) + if (pipe2(&gopts->pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) err("pipe"); return 0; @@ -404,9 +440,9 @@ static void continue_range(int ufd, __u64 start, __u64 len, bool wp) ret, (int64_t) req.mapped); } -int uffd_read_msg(int ufd, struct uffd_msg *msg) +int uffd_read_msg(uffd_global_test_opts_t *gopts, struct uffd_msg *msg) { - int ret = read(uffd, msg, sizeof(*msg)); + int ret = read(gopts->uffd, msg, sizeof(*msg)); if (ret != sizeof(*msg)) { if (ret < 0) { @@ -421,7 +457,8 @@ int uffd_read_msg(int ufd, struct uffd_msg *msg) return 0; } -void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) +void uffd_handle_page_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg, + struct uffd_args *args) { unsigned long offset; @@ -430,7 +467,7 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) { /* Write protect page faults */ - wp_range(uffd, msg->arg.pagefault.address, page_size, false); + wp_range(gopts->uffd, msg->arg.pagefault.address, gopts->page_size, false); args->wp_faults++; } else if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_MINOR) { uint8_t *area; @@ -448,12 +485,12 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) * (UFFD-registered). */ - area = (uint8_t *)(area_dst + - ((char *)msg->arg.pagefault.address - - area_dst_alias)); - for (b = 0; b < page_size; ++b) + area = (uint8_t *)(gopts->area_dst + + ((char *)msg->arg.pagefault.address - + gopts->area_dst_alias)); + for (b = 0; b < gopts->page_size; ++b) area[b] = ~area[b]; - continue_range(uffd, msg->arg.pagefault.address, page_size, + continue_range(gopts->uffd, msg->arg.pagefault.address, gopts->page_size, args->apply_wp); args->minor_faults++; } else { @@ -481,10 +518,10 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) err("unexpected write fault"); - offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; - offset &= ~(page_size-1); + offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst; + offset &= ~(gopts->page_size-1); - if (copy_page(uffd, offset, args->apply_wp)) + if (copy_page(gopts, offset, args->apply_wp)) args->missing_faults++; } } @@ -492,6 +529,7 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) void *uffd_poll_thread(void *arg) { struct uffd_args *args = (struct uffd_args *)arg; + uffd_global_test_opts_t *gopts = args->gopts; unsigned long cpu = args->cpu; struct pollfd pollfd[2]; struct uffd_msg msg; @@ -499,11 +537,16 @@ void *uffd_poll_thread(void *arg) int ret; char tmp_chr; - pollfd[0].fd = uffd; + if (!args->handle_fault) + args->handle_fault = uffd_handle_page_fault; + + pollfd[0].fd = gopts->uffd; pollfd[0].events = POLLIN; - pollfd[1].fd = pipefd[cpu*2]; + pollfd[1].fd = gopts->pipefd[cpu*2]; pollfd[1].events = POLLIN; + gopts->ready_for_fork = true; + for (;;) { ret = poll(pollfd, 2, -1); if (ret <= 0) { @@ -520,30 +563,30 @@ void *uffd_poll_thread(void *arg) } if (!(pollfd[0].revents & POLLIN)) err("pollfd[0].revents %d", pollfd[0].revents); - if (uffd_read_msg(uffd, &msg)) + if (uffd_read_msg(gopts, &msg)) continue; switch (msg.event) { default: err("unexpected msg event %u\n", msg.event); break; case UFFD_EVENT_PAGEFAULT: - uffd_handle_page_fault(&msg, args); + args->handle_fault(gopts, &msg, args); break; case UFFD_EVENT_FORK: - close(uffd); - uffd = msg.arg.fork.ufd; - pollfd[0].fd = uffd; + close(gopts->uffd); + gopts->uffd = msg.arg.fork.ufd; + pollfd[0].fd = gopts->uffd; break; case UFFD_EVENT_REMOVE: uffd_reg.range.start = msg.arg.remove.start; uffd_reg.range.len = msg.arg.remove.end - msg.arg.remove.start; - if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) + if (ioctl(gopts->uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) err("remove failure"); break; case UFFD_EVENT_REMAP: - area_remap = area_dst; /* save for later unmap */ - area_dst = (char *)(unsigned long)msg.arg.remap.to; + gopts->area_remap = gopts->area_dst; /* save for later unmap */ + gopts->area_dst = (char *)(unsigned long)msg.arg.remap.to; break; } } @@ -551,17 +594,18 @@ void *uffd_poll_thread(void *arg) return NULL; } -static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy, +static void retry_copy_page(uffd_global_test_opts_t *gopts, struct uffdio_copy *uffdio_copy, unsigned long offset) { - uffd_test_ops->alias_mapping(&uffdio_copy->dst, + uffd_test_ops->alias_mapping(gopts, + &uffdio_copy->dst, uffdio_copy->len, offset); - if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) { + if (ioctl(gopts->uffd, UFFDIO_COPY, uffdio_copy)) { /* real retval in ufdio_copy.copy */ if (uffdio_copy->copy != -EEXIST) err("UFFDIO_COPY retry error: %"PRId64, - (int64_t)uffdio_copy->copy); + (int64_t)uffdio_copy->copy); } else { err("UFFDIO_COPY retry unexpected: %"PRId64, (int64_t)uffdio_copy->copy); @@ -580,41 +624,65 @@ static void wake_range(int ufd, unsigned long addr, unsigned long len) addr), exit(1); } -int __copy_page(int ufd, unsigned long offset, bool retry, bool wp) +int __copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool retry, bool wp) { struct uffdio_copy uffdio_copy; - if (offset >= nr_pages * page_size) + if (offset >= gopts->nr_pages * gopts->page_size) err("unexpected offset %lu\n", offset); - uffdio_copy.dst = (unsigned long) area_dst + offset; - uffdio_copy.src = (unsigned long) area_src + offset; - uffdio_copy.len = page_size; + uffdio_copy.dst = (unsigned long) gopts->area_dst + offset; + uffdio_copy.src = (unsigned long) gopts->area_src + offset; + uffdio_copy.len = gopts->page_size; if (wp) uffdio_copy.mode = UFFDIO_COPY_MODE_WP; else uffdio_copy.mode = 0; uffdio_copy.copy = 0; - if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) { + if (ioctl(gopts->uffd, UFFDIO_COPY, &uffdio_copy)) { /* real retval in ufdio_copy.copy */ if (uffdio_copy.copy != -EEXIST) err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy); - wake_range(ufd, uffdio_copy.dst, page_size); - } else if (uffdio_copy.copy != page_size) { + wake_range(gopts->uffd, uffdio_copy.dst, gopts->page_size); + } else if (uffdio_copy.copy != gopts->page_size) { err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy); } else { - if (test_uffdio_copy_eexist && retry) { - test_uffdio_copy_eexist = false; - retry_copy_page(ufd, &uffdio_copy, offset); + if (gopts->test_uffdio_copy_eexist && retry) { + gopts->test_uffdio_copy_eexist = false; + retry_copy_page(gopts, &uffdio_copy, offset); } return 1; } return 0; } -int copy_page(int ufd, unsigned long offset, bool wp) +int copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool wp) +{ + return __copy_page(gopts, offset, false, wp); +} + +int move_page(uffd_global_test_opts_t *gopts, unsigned long offset, unsigned long len) { - return __copy_page(ufd, offset, false, wp); + struct uffdio_move uffdio_move; + + if (offset + len > gopts->nr_pages * gopts->page_size) + err("unexpected offset %lu and length %lu\n", offset, len); + uffdio_move.dst = (unsigned long) gopts->area_dst + offset; + uffdio_move.src = (unsigned long) gopts->area_src + offset; + uffdio_move.len = len; + uffdio_move.mode = UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES; + uffdio_move.move = 0; + if (ioctl(gopts->uffd, UFFDIO_MOVE, &uffdio_move)) { + /* real retval in uffdio_move.move */ + if (uffdio_move.move != -EEXIST) + err("UFFDIO_MOVE error: %"PRId64, + (int64_t)uffdio_move.move); + wake_range(gopts->uffd, uffdio_move.dst, len); + } else if (uffdio_move.move != len) { + err("UFFDIO_MOVE error: %"PRId64, (int64_t)uffdio_move.move); + } else + return 1; + return 0; } int uffd_open_dev(unsigned int flags) diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 197f5262fe0d..844a85ab31eb 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -8,6 +8,7 @@ #define __UFFD_COMMON_H__ #define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ // Use ll64 #include <stdio.h> #include <errno.h> #include <unistd.h> @@ -32,8 +33,9 @@ #include <inttypes.h> #include <stdint.h> #include <sys/random.h> +#include <stdatomic.h> -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" #define UFFD_FLAGS (O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY) @@ -54,20 +56,17 @@ #define err(fmt, ...) errexit(1, fmt, ##__VA_ARGS__) -/* pthread_mutex_t starts at page offset 0 */ -#define area_mutex(___area, ___nr) \ - ((pthread_mutex_t *) ((___area) + (___nr)*page_size)) -/* - * count is placed in the page after pthread_mutex_t naturally aligned - * to avoid non alignment faults on non-x86 archs. - */ -#define area_count(___area, ___nr) \ - ((volatile unsigned long long *) ((unsigned long) \ - ((___area) + (___nr)*page_size + \ - sizeof(pthread_mutex_t) + \ - sizeof(unsigned long long) - 1) & \ - ~(unsigned long)(sizeof(unsigned long long) \ - - 1))) +struct uffd_global_test_opts { + unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size; + char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; + int uffd, uffd_flags, finished, *pipefd, test_type; + bool map_shared; + bool test_uffdio_wp; + unsigned long long *count_verify; + volatile bool test_uffdio_copy_eexist; + atomic_bool ready_for_fork; +}; +typedef struct uffd_global_test_opts uffd_global_test_opts_t; /* Userfaultfd test statistics */ struct uffd_args { @@ -77,37 +76,55 @@ struct uffd_args { unsigned long missing_faults; unsigned long wp_faults; unsigned long minor_faults; + struct uffd_global_test_opts *gopts; + + /* A custom fault handler; defaults to uffd_handle_page_fault. */ + void (*handle_fault)(struct uffd_global_test_opts *gopts, + struct uffd_msg *msg, + struct uffd_args *args); }; struct uffd_test_ops { - int (*allocate_area)(void **alloc_area, bool is_src); - void (*release_pages)(char *rel_area); - void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); - void (*check_pmd_mapping)(void *p, int expect_nr_hpages); + int (*allocate_area)(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src); + void (*release_pages)(uffd_global_test_opts_t *gopts, char *rel_area); + void (*alias_mapping)(uffd_global_test_opts_t *gopts, + __u64 *start, + size_t len, + unsigned long offset); + void (*check_pmd_mapping)(uffd_global_test_opts_t *gopts, void *p, int expect_nr_hpages); }; typedef struct uffd_test_ops uffd_test_ops_t; -extern unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; -extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; -extern int uffd, uffd_flags, finished, *pipefd, test_type; -extern bool map_shared; -extern bool test_uffdio_wp; -extern unsigned long long *count_verify; -extern volatile bool test_uffdio_copy_eexist; +struct uffd_test_case_ops { + int (*pre_alloc)(uffd_global_test_opts_t *gopts, const char **errmsg); + int (*post_alloc)(uffd_global_test_opts_t *gopts, const char **errmsg); +}; +typedef struct uffd_test_case_ops uffd_test_case_ops_t; +extern uffd_global_test_opts_t *uffd_gtest_opts; extern uffd_test_ops_t anon_uffd_test_ops; extern uffd_test_ops_t shmem_uffd_test_ops; extern uffd_test_ops_t hugetlb_uffd_test_ops; extern uffd_test_ops_t *uffd_test_ops; +extern uffd_test_case_ops_t *uffd_test_case_ops; + +pthread_mutex_t *area_mutex(char *area, unsigned long nr, uffd_global_test_opts_t *gopts); +volatile unsigned long long *area_count(char *area, + unsigned long nr, + uffd_global_test_opts_t *gopts); void uffd_stats_report(struct uffd_args *args, int n_cpus); -int uffd_test_ctx_init(uint64_t features, const char **errmsg); -int userfaultfd_open(uint64_t *features); -int uffd_read_msg(int ufd, struct uffd_msg *msg); +int uffd_test_ctx_init(uffd_global_test_opts_t *gopts, uint64_t features, const char **errmsg); +void uffd_test_ctx_clear(uffd_global_test_opts_t *gopts); +int userfaultfd_open(uffd_global_test_opts_t *gopts, uint64_t *features); +int uffd_read_msg(uffd_global_test_opts_t *gopts, struct uffd_msg *msg); void wp_range(int ufd, __u64 start, __u64 len, bool wp); -void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args); -int __copy_page(int ufd, unsigned long offset, bool retry, bool wp); -int copy_page(int ufd, unsigned long offset, bool wp); +void uffd_handle_page_fault(uffd_global_test_opts_t *gopts, + struct uffd_msg *msg, + struct uffd_args *args); +int __copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool retry, bool wp); +int copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool wp); +int move_page(uffd_global_test_opts_t *gopts, unsigned long offset, unsigned long len); void *uffd_poll_thread(void *arg); int uffd_open_dev(unsigned int flags); diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index 995ff13e74c7..700fbaa18d44 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -36,6 +36,7 @@ #include "uffd-common.h" +uint64_t features; #ifdef __NR_userfaultfd #define BOUNCE_RANDOM (1<<0) @@ -43,6 +44,12 @@ #define BOUNCE_VERIFY (1<<2) #define BOUNCE_POLL (1<<3) static int bounces; +/* defined globally for this particular test as the sigalrm handler + * depends on test_uffdio_*_eexist. + * XXX: define gopts in main() when we figure out a way to deal with + * test_uffdio_*_eexist. + */ +static uffd_global_test_opts_t *gopts; /* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */ #define ALARM_INTERVAL_SECS 10 @@ -50,24 +57,24 @@ static char *zeropage; pthread_attr_t attr; #define swap(a, b) \ - do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) + do { __auto_type __tmp = (a); (a) = (b); (b) = __tmp; } while (0) const char *examples = - "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" - "./userfaultfd anon 100 99999\n\n" - "# Run share memory test on 1GiB region with 99 bounces:\n" - "./userfaultfd shmem 1000 99\n\n" - "# Run hugetlb memory test on 256MiB region with 50 bounces:\n" - "./userfaultfd hugetlb 256 50\n\n" - "# Run the same hugetlb test but using private file:\n" - "./userfaultfd hugetlb-private 256 50\n\n" - "# 10MiB-~6GiB 999 bounces anonymous test, " - "continue forever unless an error triggers\n" - "while ./userfaultfd anon $[RANDOM % 6000 + 10] 999; do true; done\n\n"; + "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" + "./uffd-stress anon 100 99999\n\n" + "# Run share memory test on 1GiB region with 99 bounces:\n" + "./uffd-stress shmem 1000 99\n\n" + "# Run hugetlb memory test on 256MiB region with 50 bounces:\n" + "./uffd-stress hugetlb 256 50\n\n" + "# Run the same hugetlb test but using private file:\n" + "./uffd-stress hugetlb-private 256 50\n\n" + "# 10MiB-~6GiB 999 bounces anonymous test, " + "continue forever unless an error triggers\n" + "while ./uffd-stress anon $[RANDOM % 6000 + 10] 999; do true; done\n\n"; static void usage(void) { - fprintf(stderr, "\nUsage: ./userfaultfd <test type> <MiB> <bounces>\n\n"); + fprintf(stderr, "\nUsage: ./uffd-stress <test type> <MiB> <bounces>\n\n"); fprintf(stderr, "Supported <test type>: anon, hugetlb, " "hugetlb-private, shmem, shmem-private\n\n"); fprintf(stderr, "Examples:\n\n"); @@ -75,54 +82,58 @@ static void usage(void) exit(1); } -static void uffd_stats_reset(struct uffd_args *args, unsigned long n_cpus) +static void uffd_stats_reset(uffd_global_test_opts_t *gopts, struct uffd_args *args, + unsigned long n_cpus) { int i; for (i = 0; i < n_cpus; i++) { args[i].cpu = i; - args[i].apply_wp = test_uffdio_wp; + args[i].apply_wp = gopts->test_uffdio_wp; args[i].missing_faults = 0; args[i].wp_faults = 0; args[i].minor_faults = 0; + args[i].gopts = gopts; } } static void *locking_thread(void *arg) { - unsigned long cpu = (unsigned long) arg; + struct uffd_args *args = (struct uffd_args *) arg; + uffd_global_test_opts_t *gopts = args->gopts; + unsigned long cpu = (unsigned long) args->cpu; unsigned long page_nr; unsigned long long count; if (!(bounces & BOUNCE_RANDOM)) { page_nr = -bounces; if (!(bounces & BOUNCE_RACINGFAULTS)) - page_nr += cpu * nr_pages_per_cpu; + page_nr += cpu * gopts->nr_pages_per_cpu; } - while (!finished) { + while (!gopts->finished) { if (bounces & BOUNCE_RANDOM) { if (getrandom(&page_nr, sizeof(page_nr), 0) != sizeof(page_nr)) err("getrandom failed"); } else page_nr += 1; - page_nr %= nr_pages; - pthread_mutex_lock(area_mutex(area_dst, page_nr)); - count = *area_count(area_dst, page_nr); - if (count != count_verify[page_nr]) + page_nr %= gopts->nr_pages; + pthread_mutex_lock(area_mutex(gopts->area_dst, page_nr, gopts)); + count = *area_count(gopts->area_dst, page_nr, gopts); + if (count != gopts->count_verify[page_nr]) err("page_nr %lu memory corruption %llu %llu", - page_nr, count, count_verify[page_nr]); + page_nr, count, gopts->count_verify[page_nr]); count++; - *area_count(area_dst, page_nr) = count_verify[page_nr] = count; - pthread_mutex_unlock(area_mutex(area_dst, page_nr)); + *area_count(gopts->area_dst, page_nr, gopts) = gopts->count_verify[page_nr] = count; + pthread_mutex_unlock(area_mutex(gopts->area_dst, page_nr, gopts)); } return NULL; } -static int copy_page_retry(int ufd, unsigned long offset) +static int copy_page_retry(uffd_global_test_opts_t *gopts, unsigned long offset) { - return __copy_page(ufd, offset, true, test_uffdio_wp); + return __copy_page(gopts, offset, true, gopts->test_uffdio_wp); } pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; @@ -130,15 +141,16 @@ pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; static void *uffd_read_thread(void *arg) { struct uffd_args *args = (struct uffd_args *)arg; + uffd_global_test_opts_t *gopts = args->gopts; struct uffd_msg msg; pthread_mutex_unlock(&uffd_read_mutex); /* from here cancellation is ok */ for (;;) { - if (uffd_read_msg(uffd, &msg)) + if (uffd_read_msg(gopts, &msg)) continue; - uffd_handle_page_fault(&msg, args); + uffd_handle_page_fault(gopts, &msg, args); } return NULL; @@ -146,32 +158,34 @@ static void *uffd_read_thread(void *arg) static void *background_thread(void *arg) { - unsigned long cpu = (unsigned long) arg; + struct uffd_args *args = (struct uffd_args *) arg; + uffd_global_test_opts_t *gopts = args->gopts; + unsigned long cpu = (unsigned long) args->cpu; unsigned long page_nr, start_nr, mid_nr, end_nr; - start_nr = cpu * nr_pages_per_cpu; - end_nr = (cpu+1) * nr_pages_per_cpu; + start_nr = cpu * gopts->nr_pages_per_cpu; + end_nr = (cpu+1) * gopts->nr_pages_per_cpu; mid_nr = (start_nr + end_nr) / 2; /* Copy the first half of the pages */ for (page_nr = start_nr; page_nr < mid_nr; page_nr++) - copy_page_retry(uffd, page_nr * page_size); + copy_page_retry(gopts, page_nr * gopts->page_size); /* * If we need to test uffd-wp, set it up now. Then we'll have * at least the first half of the pages mapped already which * can be write-protected for testing */ - if (test_uffdio_wp) - wp_range(uffd, (unsigned long)area_dst + start_nr * page_size, - nr_pages_per_cpu * page_size, true); + if (gopts->test_uffdio_wp) + wp_range(gopts->uffd, (unsigned long)gopts->area_dst + start_nr * gopts->page_size, + gopts->nr_pages_per_cpu * gopts->page_size, true); /* * Continue the 2nd half of the page copying, handling write * protection faults if any */ for (page_nr = mid_nr; page_nr < end_nr; page_nr++) - copy_page_retry(uffd, page_nr * page_size); + copy_page_retry(gopts, page_nr * gopts->page_size); return NULL; } @@ -179,20 +193,22 @@ static void *background_thread(void *arg) static int stress(struct uffd_args *args) { unsigned long cpu; - pthread_t locking_threads[nr_cpus]; - pthread_t uffd_threads[nr_cpus]; - pthread_t background_threads[nr_cpus]; + uffd_global_test_opts_t *gopts = args->gopts; + pthread_t locking_threads[gopts->nr_parallel]; + pthread_t uffd_threads[gopts->nr_parallel]; + pthread_t background_threads[gopts->nr_parallel]; - finished = 0; - for (cpu = 0; cpu < nr_cpus; cpu++) { + gopts->finished = 0; + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) { if (pthread_create(&locking_threads[cpu], &attr, - locking_thread, (void *)cpu)) + locking_thread, (void *)&args[cpu])) return 1; if (bounces & BOUNCE_POLL) { - if (pthread_create(&uffd_threads[cpu], &attr, + if (pthread_create(&uffd_threads[cpu], + &attr, uffd_poll_thread, - (void *)&args[cpu])) - return 1; + (void *) &args[cpu])) + err("uffd_poll_thread create"); } else { if (pthread_create(&uffd_threads[cpu], &attr, uffd_read_thread, @@ -201,10 +217,10 @@ static int stress(struct uffd_args *args) pthread_mutex_lock(&uffd_read_mutex); } if (pthread_create(&background_threads[cpu], &attr, - background_thread, (void *)cpu)) + background_thread, (void *)&args[cpu])) return 1; } - for (cpu = 0; cpu < nr_cpus; cpu++) + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) if (pthread_join(background_threads[cpu], NULL)) return 1; @@ -217,17 +233,17 @@ static int stress(struct uffd_args *args) * UFFDIO_COPY without writing zero pages into area_dst * because the background threads already completed). */ - uffd_test_ops->release_pages(area_src); + uffd_test_ops->release_pages(gopts, gopts->area_src); - finished = 1; - for (cpu = 0; cpu < nr_cpus; cpu++) + gopts->finished = 1; + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) if (pthread_join(locking_threads[cpu], NULL)) return 1; - for (cpu = 0; cpu < nr_cpus; cpu++) { - char c; + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) { + char c = '\0'; if (bounces & BOUNCE_POLL) { - if (write(pipefd[cpu*2+1], &c, 1) != 1) + if (write(gopts->pipefd[cpu*2+1], &c, 1) != 1) err("pipefd write error"); if (pthread_join(uffd_threads[cpu], (void *)&args[cpu])) @@ -243,20 +259,26 @@ static int stress(struct uffd_args *args) return 0; } -static int userfaultfd_stress(void) +static int userfaultfd_stress(uffd_global_test_opts_t *gopts) { void *area; unsigned long nr; - struct uffd_args args[nr_cpus]; - uint64_t mem_size = nr_pages * page_size; + struct uffd_args args[gopts->nr_parallel]; + uint64_t mem_size = gopts->nr_pages * gopts->page_size; + int flags = 0; - if (uffd_test_ctx_init(UFFD_FEATURE_WP_UNPOPULATED, NULL)) + memset(args, 0, sizeof(struct uffd_args) * gopts->nr_parallel); + + if (features & UFFD_FEATURE_WP_UNPOPULATED && gopts->test_type == TEST_ANON) + flags = UFFD_FEATURE_WP_UNPOPULATED; + + if (uffd_test_ctx_init(gopts, flags, NULL)) err("context init failed"); - if (posix_memalign(&area, page_size, page_size)) + if (posix_memalign(&area, gopts->page_size, gopts->page_size)) err("out of memory"); zeropage = area; - bzero(zeropage, page_size); + bzero(zeropage, gopts->page_size); pthread_mutex_lock(&uffd_read_mutex); @@ -279,18 +301,18 @@ static int userfaultfd_stress(void) fflush(stdout); if (bounces & BOUNCE_POLL) - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); else - fcntl(uffd, F_SETFL, uffd_flags & ~O_NONBLOCK); + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags & ~O_NONBLOCK); /* register */ - if (uffd_register(uffd, area_dst, mem_size, - true, test_uffdio_wp, false)) + if (uffd_register(gopts->uffd, gopts->area_dst, mem_size, + true, gopts->test_uffdio_wp, false)) err("register failure"); - if (area_dst_alias) { - if (uffd_register(uffd, area_dst_alias, mem_size, - true, test_uffdio_wp, false)) + if (gopts->area_dst_alias) { + if (uffd_register(gopts->uffd, gopts->area_dst_alias, mem_size, + true, gopts->test_uffdio_wp, false)) err("register failure alias"); } @@ -318,86 +340,88 @@ static int userfaultfd_stress(void) * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's * required to MADV_DONTNEED here. */ - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); - uffd_stats_reset(args, nr_cpus); + uffd_stats_reset(gopts, args, gopts->nr_parallel); /* bounce pass */ - if (stress(args)) + if (stress(args)) { + uffd_test_ctx_clear(gopts); return 1; + } /* Clear all the write protections if there is any */ - if (test_uffdio_wp) - wp_range(uffd, (unsigned long)area_dst, - nr_pages * page_size, false); + if (gopts->test_uffdio_wp) + wp_range(gopts->uffd, (unsigned long)gopts->area_dst, + gopts->nr_pages * gopts->page_size, false); /* unregister */ - if (uffd_unregister(uffd, area_dst, mem_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, mem_size)) err("unregister failure"); - if (area_dst_alias) { - if (uffd_unregister(uffd, area_dst_alias, mem_size)) + if (gopts->area_dst_alias) { + if (uffd_unregister(gopts->uffd, gopts->area_dst_alias, mem_size)) err("unregister failure alias"); } /* verification */ if (bounces & BOUNCE_VERIFY) - for (nr = 0; nr < nr_pages; nr++) - if (*area_count(area_dst, nr) != count_verify[nr]) + for (nr = 0; nr < gopts->nr_pages; nr++) + if (*area_count(gopts->area_dst, nr, gopts) != + gopts->count_verify[nr]) err("error area_count %llu %llu %lu\n", - *area_count(area_src, nr), - count_verify[nr], nr); + *area_count(gopts->area_src, nr, gopts), + gopts->count_verify[nr], nr); /* prepare next bounce */ - swap(area_src, area_dst); + swap(gopts->area_src, gopts->area_dst); - swap(area_src_alias, area_dst_alias); + swap(gopts->area_src_alias, gopts->area_dst_alias); - uffd_stats_report(args, nr_cpus); + uffd_stats_report(args, gopts->nr_parallel); } + uffd_test_ctx_clear(gopts); return 0; } -static void set_test_type(const char *type) +static void set_test_type(uffd_global_test_opts_t *gopts, const char *type) { if (!strcmp(type, "anon")) { - test_type = TEST_ANON; + gopts->test_type = TEST_ANON; uffd_test_ops = &anon_uffd_test_ops; } else if (!strcmp(type, "hugetlb")) { - test_type = TEST_HUGETLB; + gopts->test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; - map_shared = true; + gopts->map_shared = true; } else if (!strcmp(type, "hugetlb-private")) { - test_type = TEST_HUGETLB; + gopts->test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; } else if (!strcmp(type, "shmem")) { - map_shared = true; - test_type = TEST_SHMEM; + gopts->map_shared = true; + gopts->test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; } else if (!strcmp(type, "shmem-private")) { - test_type = TEST_SHMEM; + gopts->test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; } } -static void parse_test_type_arg(const char *raw_type) +static void parse_test_type_arg(uffd_global_test_opts_t *gopts, const char *raw_type) { - uint64_t features = UFFD_API_FEATURES; - - set_test_type(raw_type); + set_test_type(gopts, raw_type); - if (!test_type) + if (!gopts->test_type) err("failed to parse test type argument: '%s'", raw_type); - if (test_type == TEST_HUGETLB) - page_size = default_huge_page_size(); + if (gopts->test_type == TEST_HUGETLB) + gopts->page_size = default_huge_page_size(); else - page_size = sysconf(_SC_PAGE_SIZE); + gopts->page_size = sysconf(_SC_PAGE_SIZE); - if (!page_size) + if (!gopts->page_size) err("Unable to determine page size"); - if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2 - > page_size) + if ((unsigned long) area_count(NULL, 0, gopts) + sizeof(unsigned long long) * 2 + > gopts->page_size) err("Impossible to run this test"); /* @@ -406,28 +430,34 @@ static void parse_test_type_arg(const char *raw_type) * feature. */ - if (userfaultfd_open(&features)) - err("Userfaultfd open failed"); + if (uffd_get_features(&features) && errno == ENOENT) + ksft_exit_skip("failed to get available features (%d)\n", errno); - test_uffdio_wp = test_uffdio_wp && + gopts->test_uffdio_wp = gopts->test_uffdio_wp && (features & UFFD_FEATURE_PAGEFAULT_FLAG_WP); - close(uffd); - uffd = -1; + if (gopts->test_type != TEST_ANON && !(features & UFFD_FEATURE_WP_HUGETLBFS_SHMEM)) + gopts->test_uffdio_wp = false; + + close(gopts->uffd); + gopts->uffd = -1; } static void sigalrm(int sig) { if (sig != SIGALRM) abort(); - test_uffdio_copy_eexist = true; + gopts->test_uffdio_copy_eexist = true; alarm(ALARM_INTERVAL_SECS); } int main(int argc, char **argv) { + unsigned long nr_cpus; size_t bytes; + gopts = (uffd_global_test_opts_t *) malloc(sizeof(uffd_global_test_opts_t)); + if (argc < 4) usage(); @@ -435,14 +465,34 @@ int main(int argc, char **argv) err("failed to arm SIGALRM"); alarm(ALARM_INTERVAL_SECS); - parse_test_type_arg(argv[1]); + parse_test_type_arg(gopts, argv[1]); bytes = atol(argv[2]) * 1024 * 1024; nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + if (nr_cpus > 32) { + /* Don't let calculation below go to zero. */ + ksft_print_msg("_SC_NPROCESSORS_ONLN (%lu) too large, capping nr_threads to 32\n", + nr_cpus); + gopts->nr_parallel = 32; + } else { + gopts->nr_parallel = nr_cpus; + } + + /* + * src and dst each require bytes / page_size number of hugepages. + * Ensure nr_parallel - 1 hugepages on top of that to account + * for racy extra reservation of hugepages. + */ + if (gopts->test_type == TEST_HUGETLB && + get_free_hugepages() < 2 * (bytes / gopts->page_size) + gopts->nr_parallel - 1) { + printf("skip: Skipping userfaultfd... not enough hugepages\n"); + return KSFT_SKIP; + } - nr_pages_per_cpu = bytes / page_size / nr_cpus; - if (!nr_pages_per_cpu) { - _err("invalid MiB"); + gopts->nr_pages_per_cpu = bytes / gopts->page_size / gopts->nr_parallel; + if (!gopts->nr_pages_per_cpu) { + _err("pages_per_cpu = 0, cannot test (%lu / %lu / %lu)", + bytes, gopts->page_size, gopts->nr_parallel); usage(); } @@ -451,11 +501,11 @@ int main(int argc, char **argv) _err("invalid bounces"); usage(); } - nr_pages = nr_pages_per_cpu * nr_cpus; + gopts->nr_pages = gopts->nr_pages_per_cpu * gopts->nr_parallel; printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n", - nr_pages, nr_pages_per_cpu); - return userfaultfd_stress(); + gopts->nr_pages, gopts->nr_pages_per_cpu); + return userfaultfd_stress(gopts); } #else /* __NR_userfaultfd */ diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 04d91f144d1c..f4807242c5b2 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -23,6 +23,11 @@ #define MEM_ALL (MEM_ANON | MEM_SHMEM | MEM_SHMEM_PRIVATE | \ MEM_HUGETLB | MEM_HUGETLB_PRIVATE) +#define ALIGN_UP(x, align_to) \ + ((__typeof__(x))((((unsigned long)(x)) + ((align_to)-1)) & ~((align_to)-1))) + +#define MAX(a, b) (((a) > (b)) ? (a) : (b)) + struct mem_type { const char *name; unsigned int mem_flag; @@ -71,13 +76,14 @@ struct uffd_test_args { typedef struct uffd_test_args uffd_test_args_t; /* Returns: UFFD_TEST_* */ -typedef void (*uffd_test_fn)(uffd_test_args_t *); +typedef void (*uffd_test_fn)(uffd_global_test_opts_t *, uffd_test_args_t *); typedef struct { const char *name; uffd_test_fn uffd_fn; unsigned int mem_targets; uint64_t uffd_feature_required; + uffd_test_case_ops_t *test_case_ops; } uffd_test_case_t; static void uffd_test_report(void) @@ -175,31 +181,6 @@ out: return 1; } -/* - * This function initializes the global variables. TODO: remove global - * vars and then remove this. - */ -static int -uffd_setup_environment(uffd_test_args_t *args, uffd_test_case_t *test, - mem_type_t *mem_type, const char **errmsg) -{ - map_shared = mem_type->shared; - uffd_test_ops = mem_type->mem_ops; - - if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB)) - page_size = default_huge_page_size(); - else - page_size = psize(); - - nr_pages = UFFD_TEST_MEM_SIZE / page_size; - /* TODO: remove this global var.. it's so ugly */ - nr_cpus = 1; - - /* Initialize test arguments */ - args->mem_type = mem_type; - - return uffd_test_ctx_init(test->uffd_feature_required, errmsg); -} static bool uffd_feature_supported(uffd_test_case_t *test) { @@ -229,7 +210,8 @@ static int pagemap_open(void) } while (0) typedef struct { - int parent_uffd, child_uffd; + uffd_global_test_opts_t *gopts; + int child_uffd; } fork_event_args; static void *fork_event_consumer(void *data) @@ -237,8 +219,10 @@ static void *fork_event_consumer(void *data) fork_event_args *args = data; struct uffd_msg msg = { 0 }; + args->gopts->ready_for_fork = true; + /* Read until a full msg received */ - while (uffd_read_msg(args->parent_uffd, &msg)); + while (uffd_read_msg(args->gopts, &msg)); if (msg.event != UFFD_EVENT_FORK) err("wrong message: %u\n", msg.event); @@ -294,9 +278,9 @@ static void unpin_pages(pin_args *args) args->pinned = false; } -static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) +static int pagemap_test_fork(uffd_global_test_opts_t *gopts, bool with_event, bool test_pin) { - fork_event_args args = { .parent_uffd = uffd, .child_uffd = -1 }; + fork_event_args args = { .gopts = gopts, .child_uffd = -1 }; pthread_t thread; pid_t child; uint64_t value; @@ -304,8 +288,11 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) /* Prepare a thread to resolve EVENT_FORK */ if (with_event) { + gopts->ready_for_fork = false; if (pthread_create(&thread, NULL, fork_event_consumer, &args)) err("pthread_create()"); + while (!gopts->ready_for_fork) + ; /* Wait for the poll_thread to start executing before forking */ } child = fork(); @@ -315,14 +302,14 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) fd = pagemap_open(); - if (test_pin && pin_pages(&args, area_dst, page_size)) + if (test_pin && pin_pages(&args, gopts->area_dst, gopts->page_size)) /* * Normally when reach here we have pinned in * previous tests, so shouldn't fail anymore */ err("pin page failed in child"); - value = pagemap_get_entry(fd, area_dst); + value = pagemap_get_entry(fd, gopts->area_dst); /* * After fork(), we should handle uffd-wp bit differently: * @@ -348,70 +335,70 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) return result; } -static void uffd_wp_unpopulated_test(uffd_test_args_t *args) +static void uffd_wp_unpopulated_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { uint64_t value; int pagemap_fd; - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, false, true, false)) err("register failed"); pagemap_fd = pagemap_open(); /* Test applying pte marker to anon unpopulated */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - value = pagemap_get_entry(pagemap_fd, area_dst); + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, true); /* Test unprotect on anon pte marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, false); - value = pagemap_get_entry(pagemap_fd, area_dst); + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, false); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Test zap on anon marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - if (madvise(area_dst, page_size, MADV_DONTNEED)) + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); - value = pagemap_get_entry(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Test fault in after marker removed */ - *area_dst = 1; - value = pagemap_get_entry(pagemap_fd, area_dst); + *gopts->area_dst = 1; + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Drop it to make pte none again */ - if (madvise(area_dst, page_size, MADV_DONTNEED)) + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); /* Test read-zero-page upon pte marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - *(volatile char *)area_dst; + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + *(volatile char *)gopts->area_dst; /* Drop it to make pte none again */ - if (madvise(area_dst, page_size, MADV_DONTNEED)) + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); uffd_test_pass(); } -static void uffd_wp_fork_test_common(uffd_test_args_t *args, +static void uffd_wp_fork_test_common(uffd_global_test_opts_t *gopts, uffd_test_args_t *args, bool with_event) { int pagemap_fd; uint64_t value; - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, false, true, false)) err("register failed"); pagemap_fd = pagemap_open(); /* Touch the page */ - *area_dst = 1; - wp_range(uffd, (uint64_t)area_dst, page_size, true); - value = pagemap_get_entry(pagemap_fd, area_dst); + *gopts->area_dst = 1; + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, true); - if (pagemap_test_fork(uffd, with_event, false)) { + if (pagemap_test_fork(gopts, with_event, false)) { uffd_test_fail("Detected %s uffd-wp bit in child in present pte", with_event ? "missing" : "stall"); goto out; @@ -429,79 +416,80 @@ static void uffd_wp_fork_test_common(uffd_test_args_t *args, * to expose pte markers. */ if (args->mem_type->shared) { - if (madvise(area_dst, page_size, MADV_DONTNEED)) + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("MADV_DONTNEED"); } else { /* * NOTE: ignore retval because private-hugetlb doesn't yet * support swapping, so it could fail. */ - madvise(area_dst, page_size, MADV_PAGEOUT); + madvise(gopts->area_dst, gopts->page_size, MADV_PAGEOUT); } /* Uffd-wp should persist even swapped out */ - value = pagemap_get_entry(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, true); - if (pagemap_test_fork(uffd, with_event, false)) { + if (pagemap_test_fork(gopts, with_event, false)) { uffd_test_fail("Detected %s uffd-wp bit in child in zapped pte", with_event ? "missing" : "stall"); goto out; } /* Unprotect; this tests swap pte modifications */ - wp_range(uffd, (uint64_t)area_dst, page_size, false); - value = pagemap_get_entry(pagemap_fd, area_dst); + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, false); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Fault in the page from disk */ - *area_dst = 2; - value = pagemap_get_entry(pagemap_fd, area_dst); + *gopts->area_dst = 2; + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); uffd_test_pass(); out: - if (uffd_unregister(uffd, area_dst, nr_pages * page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size)) err("unregister failed"); close(pagemap_fd); } -static void uffd_wp_fork_test(uffd_test_args_t *args) +static void uffd_wp_fork_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_test_common(args, false); + uffd_wp_fork_test_common(gopts, args, false); } -static void uffd_wp_fork_with_event_test(uffd_test_args_t *args) +static void uffd_wp_fork_with_event_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_test_common(args, true); + uffd_wp_fork_test_common(gopts, args, true); } -static void uffd_wp_fork_pin_test_common(uffd_test_args_t *args, +static void uffd_wp_fork_pin_test_common(uffd_global_test_opts_t *gopts, + uffd_test_args_t *args, bool with_event) { int pagemap_fd; pin_args pin_args = {}; - if (uffd_register(uffd, area_dst, page_size, false, true, false)) + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->page_size, false, true, false)) err("register failed"); pagemap_fd = pagemap_open(); /* Touch the page */ - *area_dst = 1; - wp_range(uffd, (uint64_t)area_dst, page_size, true); + *gopts->area_dst = 1; + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); /* * 1. First pin, then fork(). This tests fork() special path when * doing early CoW if the page is private. */ - if (pin_pages(&pin_args, area_dst, page_size)) { + if (pin_pages(&pin_args, gopts->area_dst, gopts->page_size)) { uffd_test_skip("Possibly CONFIG_GUP_TEST missing " "or unprivileged"); close(pagemap_fd); - uffd_unregister(uffd, area_dst, page_size); + uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size); return; } - if (pagemap_test_fork(uffd, with_event, false)) { + if (pagemap_test_fork(gopts, with_event, false)) { uffd_test_fail("Detected %s uffd-wp bit in early CoW of fork()", with_event ? "missing" : "stall"); unpin_pages(&pin_args); @@ -514,49 +502,50 @@ static void uffd_wp_fork_pin_test_common(uffd_test_args_t *args, * 2. First fork(), then pin (in the child, where test_pin==true). * This tests COR, aka, page unsharing on private memories. */ - if (pagemap_test_fork(uffd, with_event, true)) { + if (pagemap_test_fork(gopts, with_event, true)) { uffd_test_fail("Detected %s uffd-wp bit when RO pin", with_event ? "missing" : "stall"); goto out; } uffd_test_pass(); out: - if (uffd_unregister(uffd, area_dst, page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size)) err("register failed"); close(pagemap_fd); } -static void uffd_wp_fork_pin_test(uffd_test_args_t *args) +static void uffd_wp_fork_pin_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_pin_test_common(args, false); + uffd_wp_fork_pin_test_common(gopts, args, false); } -static void uffd_wp_fork_pin_with_event_test(uffd_test_args_t *args) +static void uffd_wp_fork_pin_with_event_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_pin_test_common(args, true); + uffd_wp_fork_pin_test_common(gopts, args, true); } -static void check_memory_contents(char *p) +static void check_memory_contents(uffd_global_test_opts_t *gopts, char *p) { unsigned long i, j; uint8_t expected_byte; - for (i = 0; i < nr_pages; ++i) { + for (i = 0; i < gopts->nr_pages; ++i) { expected_byte = ~((uint8_t)(i % ((uint8_t)-1))); - for (j = 0; j < page_size; j++) { - uint8_t v = *(uint8_t *)(p + (i * page_size) + j); + for (j = 0; j < gopts->page_size; j++) { + uint8_t v = *(uint8_t *)(p + (i * gopts->page_size) + j); if (v != expected_byte) err("unexpected page contents"); } } } -static void uffd_minor_test_common(bool test_collapse, bool test_wp) +static void uffd_minor_test_common(uffd_global_test_opts_t *gopts, bool test_collapse, bool test_wp) { unsigned long p; pthread_t uffd_mon; - char c; + char c = '\0'; struct uffd_args args = { 0 }; + args.gopts = gopts; /* * NOTE: MADV_COLLAPSE is not yet compatible with WP, so testing @@ -564,7 +553,7 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp) */ assert(!(test_collapse && test_wp)); - if (uffd_register(uffd, area_dst_alias, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst_alias, gopts->nr_pages * gopts->page_size, /* NOTE! MADV_COLLAPSE may not work with uffd-wp */ false, test_wp, true)) err("register failure"); @@ -573,9 +562,9 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp) * After registering with UFFD, populate the non-UFFD-registered side of * the shared mapping. This should *not* trigger any UFFD minor faults. */ - for (p = 0; p < nr_pages; ++p) - memset(area_dst + (p * page_size), p % ((uint8_t)-1), - page_size); + for (p = 0; p < gopts->nr_pages; ++p) + memset(gopts->area_dst + (p * gopts->page_size), p % ((uint8_t)-1), + gopts->page_size); args.apply_wp = test_wp; if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) @@ -587,50 +576,51 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp) * fault. uffd_poll_thread will resolve the fault by bit-flipping the * page's contents, and then issuing a CONTINUE ioctl. */ - check_memory_contents(area_dst_alias); + check_memory_contents(gopts, gopts->area_dst_alias); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, NULL)) err("join() failed"); if (test_collapse) { - if (madvise(area_dst_alias, nr_pages * page_size, + if (madvise(gopts->area_dst_alias, gopts->nr_pages * gopts->page_size, MADV_COLLAPSE)) { /* It's fine to fail for this one... */ uffd_test_skip("MADV_COLLAPSE failed"); return; } - uffd_test_ops->check_pmd_mapping(area_dst, - nr_pages * page_size / + uffd_test_ops->check_pmd_mapping(gopts, + gopts->area_dst, + gopts->nr_pages * gopts->page_size / read_pmd_pagesize()); /* * This won't cause uffd-fault - it purely just makes sure there * was no corruption. */ - check_memory_contents(area_dst_alias); + check_memory_contents(gopts, gopts->area_dst_alias); } - if (args.missing_faults != 0 || args.minor_faults != nr_pages) + if (args.missing_faults != 0 || args.minor_faults != gopts->nr_pages) uffd_test_fail("stats check error"); else uffd_test_pass(); } -void uffd_minor_test(uffd_test_args_t *args) +void uffd_minor_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_minor_test_common(false, false); + uffd_minor_test_common(gopts, false, false); } -void uffd_minor_wp_test(uffd_test_args_t *args) +void uffd_minor_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_minor_test_common(false, true); + uffd_minor_test_common(gopts, false, true); } -void uffd_minor_collapse_test(uffd_test_args_t *args) +void uffd_minor_collapse_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_minor_test_common(true, false); + uffd_minor_test_common(gopts, true, false); } static sigjmp_buf jbuf, *sigbuf; @@ -665,7 +655,7 @@ static void sighndl(int sig, siginfo_t *siginfo, void *ptr) * This also tests UFFD_FEATURE_EVENT_FORK event along with the signal * feature. Using monitor thread, verify no userfault events are generated. */ -static int faulting_process(int signal_test, bool wp) +static int faulting_process(uffd_global_test_opts_t *gopts, int signal_test, bool wp) { unsigned long nr, i; unsigned long long count; @@ -674,7 +664,7 @@ static int faulting_process(int signal_test, bool wp) struct sigaction act; volatile unsigned long signalled = 0; - split_nr_pages = (nr_pages + 1) / 2; + split_nr_pages = (gopts->nr_pages + 1) / 2; if (signal_test) { sigbuf = &jbuf; @@ -688,7 +678,7 @@ static int faulting_process(int signal_test, bool wp) for (nr = 0; nr < split_nr_pages; nr++) { volatile int steps = 1; - unsigned long offset = nr * page_size; + unsigned long offset = nr * gopts->page_size; if (signal_test) { if (sigsetjmp(*sigbuf, 1) != 0) { @@ -700,15 +690,15 @@ static int faulting_process(int signal_test, bool wp) if (steps == 1) { /* This is a MISSING request */ steps++; - if (copy_page(uffd, offset, wp)) + if (copy_page(gopts, offset, wp)) signalled++; } else { /* This is a WP request */ assert(steps == 2); - wp_range(uffd, - (__u64)area_dst + + wp_range(gopts->uffd, + (__u64)gopts->area_dst + offset, - page_size, false); + gopts->page_size, false); } } else { signalled++; @@ -717,85 +707,93 @@ static int faulting_process(int signal_test, bool wp) } } - count = *area_count(area_dst, nr); - if (count != count_verify[nr]) + count = *area_count(gopts->area_dst, nr, gopts); + if (count != gopts->count_verify[nr]) err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[nr]); + nr, count, gopts->count_verify[nr]); /* * Trigger write protection if there is by writing * the same value back. */ - *area_count(area_dst, nr) = count; + *area_count(gopts->area_dst, nr, gopts) = count; } if (signal_test) return signalled != split_nr_pages; - area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size, - MREMAP_MAYMOVE | MREMAP_FIXED, area_src); - if (area_dst == MAP_FAILED) + gopts->area_dst = mremap(gopts->area_dst, gopts->nr_pages * gopts->page_size, + gopts->nr_pages * gopts->page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, + gopts->area_src); + if (gopts->area_dst == MAP_FAILED) err("mremap"); /* Reset area_src since we just clobbered it */ - area_src = NULL; + gopts->area_src = NULL; - for (; nr < nr_pages; nr++) { - count = *area_count(area_dst, nr); - if (count != count_verify[nr]) { + for (; nr < gopts->nr_pages; nr++) { + count = *area_count(gopts->area_dst, nr, gopts); + if (count != gopts->count_verify[nr]) { err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[nr]); + nr, count, gopts->count_verify[nr]); } /* * Trigger write protection if there is by writing * the same value back. */ - *area_count(area_dst, nr) = count; + *area_count(gopts->area_dst, nr, gopts) = count; } - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); - for (nr = 0; nr < nr_pages; nr++) - for (i = 0; i < page_size; i++) - if (*(area_dst + nr * page_size + i) != 0) + for (nr = 0; nr < gopts->nr_pages; nr++) + for (i = 0; i < gopts->page_size; i++) + if (*(gopts->area_dst + nr * gopts->page_size + i) != 0) err("page %lu offset %lu is not zero", nr, i); return 0; } -static void uffd_sigbus_test_common(bool wp) +static void uffd_sigbus_test_common(uffd_global_test_opts_t *gopts, bool wp) { unsigned long userfaults; pthread_t uffd_mon; pid_t pid; int err; - char c; + char c = '\0'; struct uffd_args args = { 0 }; + args.gopts = gopts; + + gopts->ready_for_fork = false; - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, true, wp, false)) err("register failure"); - if (faulting_process(1, wp)) + if (faulting_process(gopts, 1, wp)) err("faulting process failed"); - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); args.apply_wp = wp; if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); + while (!gopts->ready_for_fork) + ; /* Wait for the poll_thread to start executing before forking */ + pid = fork(); if (pid < 0) err("fork"); if (!pid) - exit(faulting_process(2, wp)); + exit(faulting_process(gopts, 2, wp)); waitpid(pid, &err, 0); if (err) err("faulting process failed"); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, (void **)&userfaults)) err("pthread_join()"); @@ -806,26 +804,29 @@ static void uffd_sigbus_test_common(bool wp) uffd_test_pass(); } -static void uffd_sigbus_test(uffd_test_args_t *args) +static void uffd_sigbus_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_sigbus_test_common(false); + uffd_sigbus_test_common(gopts, false); } -static void uffd_sigbus_wp_test(uffd_test_args_t *args) +static void uffd_sigbus_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_sigbus_test_common(true); + uffd_sigbus_test_common(gopts, true); } -static void uffd_events_test_common(bool wp) +static void uffd_events_test_common(uffd_global_test_opts_t *gopts, bool wp) { pthread_t uffd_mon; pid_t pid; int err; - char c; + char c = '\0'; struct uffd_args args = { 0 }; + args.gopts = gopts; - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); - if (uffd_register(uffd, area_dst, nr_pages * page_size, + gopts->ready_for_fork = false; + + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, true, wp, false)) err("register failure"); @@ -833,44 +834,47 @@ static void uffd_events_test_common(bool wp) if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); + while (!gopts->ready_for_fork) + ; /* Wait for the poll_thread to start executing before forking */ + pid = fork(); if (pid < 0) err("fork"); if (!pid) - exit(faulting_process(0, wp)); + exit(faulting_process(gopts, 0, wp)); waitpid(pid, &err, 0); if (err) err("faulting process failed"); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, NULL)) err("pthread_join()"); - if (args.missing_faults != nr_pages) + if (args.missing_faults != gopts->nr_pages) uffd_test_fail("Fault counts wrong"); else uffd_test_pass(); } -static void uffd_events_test(uffd_test_args_t *args) +static void uffd_events_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_events_test_common(false); + uffd_events_test_common(gopts, false); } -static void uffd_events_wp_test(uffd_test_args_t *args) +static void uffd_events_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_events_test_common(true); + uffd_events_test_common(gopts, true); } -static void retry_uffdio_zeropage(int ufd, +static void retry_uffdio_zeropage(uffd_global_test_opts_t *gopts, struct uffdio_zeropage *uffdio_zeropage) { - uffd_test_ops->alias_mapping(&uffdio_zeropage->range.start, + uffd_test_ops->alias_mapping(gopts, &uffdio_zeropage->range.start, uffdio_zeropage->range.len, 0); - if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { + if (ioctl(gopts->uffd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { if (uffdio_zeropage->zeropage != -EEXIST) err("UFFDIO_ZEROPAGE error: %"PRId64, (int64_t)uffdio_zeropage->zeropage); @@ -880,16 +884,16 @@ static void retry_uffdio_zeropage(int ufd, } } -static bool do_uffdio_zeropage(int ufd, bool has_zeropage) +static bool do_uffdio_zeropage(uffd_global_test_opts_t *gopts, bool has_zeropage) { struct uffdio_zeropage uffdio_zeropage = { 0 }; int ret; __s64 res; - uffdio_zeropage.range.start = (unsigned long) area_dst; - uffdio_zeropage.range.len = page_size; + uffdio_zeropage.range.start = (unsigned long) gopts->area_dst; + uffdio_zeropage.range.len = gopts->page_size; uffdio_zeropage.mode = 0; - ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage); + ret = ioctl(gopts->uffd, UFFDIO_ZEROPAGE, &uffdio_zeropage); res = uffdio_zeropage.zeropage; if (ret) { /* real retval in ufdio_zeropage.zeropage */ @@ -898,10 +902,10 @@ static bool do_uffdio_zeropage(int ufd, bool has_zeropage) else if (res != -EINVAL) err("UFFDIO_ZEROPAGE not -EINVAL"); } else if (has_zeropage) { - if (res != page_size) + if (res != gopts->page_size) err("UFFDIO_ZEROPAGE unexpected size"); else - retry_uffdio_zeropage(ufd, &uffdio_zeropage); + retry_uffdio_zeropage(gopts, &uffdio_zeropage); return true; } else err("UFFDIO_ZEROPAGE succeeded"); @@ -927,42 +931,546 @@ uffd_register_detect_zeropage(int uffd, void *addr, uint64_t len) } /* exercise UFFDIO_ZEROPAGE */ -static void uffd_zeropage_test(uffd_test_args_t *args) +static void uffd_zeropage_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { bool has_zeropage; int i; - has_zeropage = uffd_register_detect_zeropage(uffd, area_dst, page_size); - if (area_dst_alias) + has_zeropage = uffd_register_detect_zeropage(gopts->uffd, + gopts->area_dst, + gopts->page_size); + if (gopts->area_dst_alias) /* Ignore the retval; we already have it */ - uffd_register_detect_zeropage(uffd, area_dst_alias, page_size); + uffd_register_detect_zeropage(gopts->uffd, gopts->area_dst_alias, gopts->page_size); - if (do_uffdio_zeropage(uffd, has_zeropage)) - for (i = 0; i < page_size; i++) - if (area_dst[i] != 0) + if (do_uffdio_zeropage(gopts, has_zeropage)) + for (i = 0; i < gopts->page_size; i++) + if (gopts->area_dst[i] != 0) err("data non-zero at offset %d\n", i); - if (uffd_unregister(uffd, area_dst, page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size)) err("unregister"); - if (area_dst_alias && uffd_unregister(uffd, area_dst_alias, page_size)) + if (gopts->area_dst_alias && uffd_unregister(gopts->uffd, + gopts->area_dst_alias, + gopts->page_size)) err("unregister"); uffd_test_pass(); } +static void uffd_register_poison(int uffd, void *addr, uint64_t len) +{ + uint64_t ioctls = 0; + uint64_t expected = (1 << _UFFDIO_COPY) | (1 << _UFFDIO_POISON); + + if (uffd_register_with_ioctls(uffd, addr, len, true, + false, false, &ioctls)) + err("poison register fail"); + + if ((ioctls & expected) != expected) + err("registered area doesn't support COPY and POISON ioctls"); +} + +static void do_uffdio_poison(uffd_global_test_opts_t *gopts, unsigned long offset) +{ + struct uffdio_poison uffdio_poison = { 0 }; + int ret; + __s64 res; + + uffdio_poison.range.start = (unsigned long) gopts->area_dst + offset; + uffdio_poison.range.len = gopts->page_size; + uffdio_poison.mode = 0; + ret = ioctl(gopts->uffd, UFFDIO_POISON, &uffdio_poison); + res = uffdio_poison.updated; + + if (ret) + err("UFFDIO_POISON error: %"PRId64, (int64_t)res); + else if (res != gopts->page_size) + err("UFFDIO_POISON unexpected size: %"PRId64, (int64_t)res); +} + +static void uffd_poison_handle_fault(uffd_global_test_opts_t *gopts, + struct uffd_msg *msg, + struct uffd_args *args) +{ + unsigned long offset; + + if (msg->event != UFFD_EVENT_PAGEFAULT) + err("unexpected msg event %u", msg->event); + + if (msg->arg.pagefault.flags & + (UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR)) + err("unexpected fault type %llu", msg->arg.pagefault.flags); + + offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst; + offset &= ~(gopts->page_size-1); + + /* Odd pages -> copy zeroed page; even pages -> poison. */ + if (offset & gopts->page_size) + copy_page(gopts, offset, false); + else + do_uffdio_poison(gopts, offset); +} + +/* Make sure to cover odd/even, and minimum duplications */ +#define UFFD_POISON_TEST_NPAGES 4 + +static void uffd_poison_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) +{ + pthread_t uffd_mon; + char c; + struct uffd_args args = { 0 }; + struct sigaction act = { 0 }; + unsigned long nr_sigbus = 0; + unsigned long nr, poison_pages = UFFD_POISON_TEST_NPAGES; + + if (gopts->nr_pages < poison_pages) { + uffd_test_skip("Too less pages for POISON test"); + return; + } + + args.gopts = gopts; + + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); + + uffd_register_poison(gopts->uffd, gopts->area_dst, poison_pages * gopts->page_size); + memset(gopts->area_src, 0, poison_pages * gopts->page_size); + + args.handle_fault = uffd_poison_handle_fault; + if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) + err("uffd_poll_thread create"); + + sigbuf = &jbuf; + act.sa_sigaction = sighndl; + act.sa_flags = SA_SIGINFO; + if (sigaction(SIGBUS, &act, 0)) + err("sigaction"); + + for (nr = 0; nr < poison_pages; ++nr) { + unsigned long offset = nr * gopts->page_size; + const char *bytes = (const char *) gopts->area_dst + offset; + const char *i; + + if (sigsetjmp(*sigbuf, 1)) { + /* + * Access below triggered a SIGBUS, which was caught by + * sighndl, which then jumped here. Count this SIGBUS, + * and move on to next page. + */ + ++nr_sigbus; + continue; + } + + for (i = bytes; i < bytes + gopts->page_size; ++i) { + if (*i) + err("nonzero byte in area_dst (%p) at %p: %u", + gopts->area_dst, i, *i); + } + } + + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); + if (pthread_join(uffd_mon, NULL)) + err("pthread_join()"); + + if (nr_sigbus != poison_pages / 2) + err("expected to receive %lu SIGBUS, actually received %lu", + poison_pages / 2, nr_sigbus); + + uffd_test_pass(); +} + +static void +uffd_move_handle_fault_common(uffd_global_test_opts_t *gopts, + struct uffd_msg *msg, + struct uffd_args *args, + unsigned long len) +{ + unsigned long offset; + + if (msg->event != UFFD_EVENT_PAGEFAULT) + err("unexpected msg event %u", msg->event); + + if (msg->arg.pagefault.flags & + (UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR | UFFD_PAGEFAULT_FLAG_WRITE)) + err("unexpected fault type %llu", msg->arg.pagefault.flags); + + offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst; + offset &= ~(len-1); + + if (move_page(gopts, offset, len)) + args->missing_faults++; +} + +static void uffd_move_handle_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg, + struct uffd_args *args) +{ + uffd_move_handle_fault_common(gopts, msg, args, gopts->page_size); +} + +static void uffd_move_pmd_handle_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg, + struct uffd_args *args) +{ + uffd_move_handle_fault_common(gopts, msg, args, read_pmd_pagesize()); +} + +static void +uffd_move_test_common(uffd_global_test_opts_t *gopts, + uffd_test_args_t *targs, + unsigned long chunk_size, + void (*handle_fault)(struct uffd_global_test_opts *gopts, + struct uffd_msg *msg, struct uffd_args *args) +) +{ + unsigned long nr; + pthread_t uffd_mon; + char c = '\0'; + unsigned long long count; + struct uffd_args args = { 0 }; + 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; + + args.gopts = gopts; + + /* Prevent source pages from being mapped more than once */ + if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_DONTFORK)) + err("madvise(MADV_DONTFORK) failure"); + + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, + true, false, false)) + err("register failure"); + + args.handle_fault = handle_fault; + if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) + err("uffd_poll_thread create"); + + step_size = chunk_size / gopts->page_size; + step_count = gopts->nr_pages / step_size; + + if (chunk_size > gopts->page_size) { + char *aligned_src = ALIGN_UP(gopts->area_src, chunk_size); + char *aligned_dst = ALIGN_UP(gopts->area_dst, chunk_size); + + if (aligned_src != gopts->area_src || aligned_dst != gopts->area_dst) { + src_offs = (aligned_src - gopts->area_src) / gopts->page_size; + dst_offs = (aligned_dst - gopts->area_dst) / gopts->page_size; + step_count--; + } + orig_area_src = gopts->area_src; + orig_area_dst = gopts->area_dst; + gopts->area_src = aligned_src; + gopts->area_dst = aligned_dst; + } + + /* + * Read each of the pages back using the UFFD-registered mapping. We + * expect that the first time we touch a page, it will result in a missing + * fault. uffd_poll_thread will resolve the fault by moving source + * page to destination. + */ + for (nr = 0; nr < step_count * step_size; nr += step_size) { + unsigned long i; + + /* Check area_src content */ + for (i = 0; i < step_size; i++) { + count = *area_count(gopts->area_src, nr + i, gopts); + if (count != gopts->count_verify[src_offs + nr + i]) + err("nr %lu source memory invalid %llu %llu\n", + nr + i, count, gopts->count_verify[src_offs + nr + i]); + } + + /* Faulting into area_dst should move the page or the huge page */ + for (i = 0; i < step_size; i++) { + count = *area_count(gopts->area_dst, nr + i, gopts); + if (count != gopts->count_verify[dst_offs + nr + i]) + err("nr %lu memory corruption %llu %llu\n", + nr, count, gopts->count_verify[dst_offs + nr + i]); + } + + /* Re-check area_src content which should be empty */ + for (i = 0; i < step_size; i++) { + count = *area_count(gopts->area_src, nr + i, gopts); + if (count != 0) + err("nr %lu move failed %llu %llu\n", + nr, count, gopts->count_verify[src_offs + nr + i]); + } + } + if (chunk_size > gopts->page_size) { + gopts->area_src = orig_area_src; + gopts->area_dst = orig_area_dst; + } + + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); + if (pthread_join(uffd_mon, NULL)) + err("join() failed"); + + if (args.missing_faults != step_count || args.minor_faults != 0) + uffd_test_fail("stats check error"); + else + uffd_test_pass(); +} + +static void uffd_move_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) +{ + uffd_move_test_common(gopts, targs, gopts->page_size, uffd_move_handle_fault); +} + +static void uffd_move_pmd_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) +{ + if (madvise(gopts->area_dst, gopts->nr_pages * gopts->page_size, MADV_HUGEPAGE)) + err("madvise(MADV_HUGEPAGE) failure"); + uffd_move_test_common(gopts, targs, read_pmd_pagesize(), + uffd_move_pmd_handle_fault); +} + +static void uffd_move_pmd_split_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) +{ + if (madvise(gopts->area_dst, gopts->nr_pages * gopts->page_size, MADV_NOHUGEPAGE)) + err("madvise(MADV_NOHUGEPAGE) failure"); + uffd_move_test_common(gopts, targs, read_pmd_pagesize(), + uffd_move_pmd_handle_fault); +} + +static bool +uffdio_verify_results(const char *name, int ret, int error, long result) +{ + /* + * Should always return -1 with errno=EAGAIN, with corresponding + * result field updated in ioctl() args to be -EAGAIN too + * (e.g. copy.copy field for UFFDIO_COPY). + */ + if (ret != -1) { + uffd_test_fail("%s should have returned -1", name); + return false; + } + + if (error != EAGAIN) { + uffd_test_fail("%s should have errno==EAGAIN", name); + return false; + } + + if (result != -EAGAIN) { + uffd_test_fail("%s should have been updated for -EAGAIN", + name); + return false; + } + + return true; +} + +/* + * This defines a function to test one ioctl. Note that here "field" can + * be 1 or anything not -EAGAIN. With that initial value set, we can + * verify later that it should be updated by kernel (when -EAGAIN + * returned), by checking whether it is also updated to -EAGAIN. + */ +#define DEFINE_MMAP_CHANGING_TEST(name, ioctl_name, field) \ + static bool uffdio_mmap_changing_test_##name(int fd) \ + { \ + int ret; \ + struct uffdio_##name args = { \ + .field = 1, \ + }; \ + ret = ioctl(fd, ioctl_name, &args); \ + return uffdio_verify_results(#ioctl_name, ret, errno, args.field); \ + } + +DEFINE_MMAP_CHANGING_TEST(zeropage, UFFDIO_ZEROPAGE, zeropage) +DEFINE_MMAP_CHANGING_TEST(copy, UFFDIO_COPY, copy) +DEFINE_MMAP_CHANGING_TEST(move, UFFDIO_MOVE, move) +DEFINE_MMAP_CHANGING_TEST(poison, UFFDIO_POISON, updated) +DEFINE_MMAP_CHANGING_TEST(continue, UFFDIO_CONTINUE, mapped) + +typedef enum { + /* We actually do not care about any state except UNINTERRUPTIBLE.. */ + THR_STATE_UNKNOWN = 0, + THR_STATE_UNINTERRUPTIBLE, +} thread_state; + +typedef struct { + uffd_global_test_opts_t *gopts; + volatile pid_t *pid; +} mmap_changing_thread_args; + +static void sleep_short(void) +{ + usleep(1000); +} + +static thread_state thread_state_get(pid_t tid) +{ + const char *header = "State:\t"; + char tmp[256], *p, c; + FILE *fp; + + snprintf(tmp, sizeof(tmp), "/proc/%d/status", tid); + fp = fopen(tmp, "r"); + + if (!fp) + return THR_STATE_UNKNOWN; + + while (fgets(tmp, sizeof(tmp), fp)) { + p = strstr(tmp, header); + if (p) { + /* For example, "State:\tD (disk sleep)" */ + c = *(p + sizeof(header) - 1); + return c == 'D' ? + THR_STATE_UNINTERRUPTIBLE : THR_STATE_UNKNOWN; + } + } + + return THR_STATE_UNKNOWN; +} + +static void thread_state_until(pid_t tid, thread_state state) +{ + thread_state s; + + do { + s = thread_state_get(tid); + sleep_short(); + } while (s != state); +} + +static void *uffd_mmap_changing_thread(void *opaque) +{ + mmap_changing_thread_args *args = opaque; + uffd_global_test_opts_t *gopts = args->gopts; + volatile pid_t *pid = args->pid; + int ret; + + /* Unfortunately, it's only fetch-able from the thread itself.. */ + assert(*pid == 0); + *pid = syscall(SYS_gettid); + + /* Inject an event, this will hang solid until the event read */ + ret = madvise(gopts->area_dst, gopts->page_size, MADV_REMOVE); + if (ret) + err("madvise(MADV_REMOVE) failed"); + + return NULL; +} + +static void uffd_consume_message(uffd_global_test_opts_t *gopts) +{ + struct uffd_msg msg = { 0 }; + + while (uffd_read_msg(gopts, &msg)); +} + +static void uffd_mmap_changing_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) +{ + /* + * This stores the real PID (which can be different from how tid is + * defined..) for the child thread, 0 means not initialized. + */ + pid_t pid = 0; + pthread_t tid; + int ret; + mmap_changing_thread_args args = { gopts, &pid }; + + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, + true, false, false)) + err("uffd_register() failed"); + + /* Create a thread to generate the racy event */ + ret = pthread_create(&tid, NULL, uffd_mmap_changing_thread, &args); + if (ret) + err("pthread_create() failed"); + + /* + * Wait until the thread setup the pid. Use volatile to make sure + * it reads from RAM not regs. + */ + while (!(volatile pid_t)pid) + sleep_short(); + + /* Wait until the thread hangs at REMOVE event */ + thread_state_until(pid, THR_STATE_UNINTERRUPTIBLE); + + if (!uffdio_mmap_changing_test_copy(gopts->uffd)) + return; + + if (!uffdio_mmap_changing_test_zeropage(gopts->uffd)) + return; + + if (!uffdio_mmap_changing_test_move(gopts->uffd)) + return; + + if (!uffdio_mmap_changing_test_poison(gopts->uffd)) + return; + + if (!uffdio_mmap_changing_test_continue(gopts->uffd)) + return; + + /* + * All succeeded above! Recycle everything. Start by reading the + * event so as to kick the thread roll again.. + */ + uffd_consume_message(gopts); + + ret = pthread_join(tid, NULL); + assert(ret == 0); + + uffd_test_pass(); +} + +static int prevent_hugepages(uffd_global_test_opts_t *gopts, const char **errmsg) +{ + /* This should be done before source area is populated */ + if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_NOHUGEPAGE)) { + /* Ignore only if CONFIG_TRANSPARENT_HUGEPAGE=n */ + if (errno != EINVAL) { + if (errmsg) + *errmsg = "madvise(MADV_NOHUGEPAGE) failed"; + return -errno; + } + } + return 0; +} + +static int request_hugepages(uffd_global_test_opts_t *gopts, const char **errmsg) +{ + /* This should be done before source area is populated */ + if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_HUGEPAGE)) { + if (errmsg) { + *errmsg = (errno == EINVAL) ? + "CONFIG_TRANSPARENT_HUGEPAGE is not set" : + "madvise(MADV_HUGEPAGE) failed"; + } + return -errno; + } + return 0; +} + +struct uffd_test_case_ops uffd_move_test_case_ops = { + .post_alloc = prevent_hugepages, +}; + +struct uffd_test_case_ops uffd_move_test_pmd_case_ops = { + .post_alloc = request_hugepages, +}; + /* * Test the returned uffdio_register.ioctls with different register modes. * Note that _UFFDIO_ZEROPAGE is tested separately in the zeropage test. */ static void -do_register_ioctls_test(uffd_test_args_t *args, bool miss, bool wp, bool minor) +do_register_ioctls_test(uffd_global_test_opts_t *gopts, + uffd_test_args_t *args, + bool miss, + bool wp, + bool minor) { uint64_t ioctls = 0, expected = BIT_ULL(_UFFDIO_WAKE); mem_type_t *mem_type = args->mem_type; int ret; - ret = uffd_register_with_ioctls(uffd, area_dst, page_size, + ret = uffd_register_with_ioctls(gopts->uffd, gopts->area_dst, gopts->page_size, miss, wp, minor, &ioctls); /* @@ -993,18 +1501,18 @@ do_register_ioctls_test(uffd_test_args_t *args, bool miss, bool wp, bool minor) "(miss=%d, wp=%d, minor=%d): expected=0x%"PRIx64", " "returned=0x%"PRIx64, miss, wp, minor, expected, ioctls); - if (uffd_unregister(uffd, area_dst, page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size)) err("unregister"); } -static void uffd_register_ioctls_test(uffd_test_args_t *args) +static void uffd_register_ioctls_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { int miss, wp, minor; for (miss = 0; miss <= 1; miss++) for (wp = 0; wp <= 1; wp++) for (minor = 0; minor <= 1; minor++) - do_register_ioctls_test(args, miss, wp, minor); + do_register_ioctls_test(gopts, args, miss, wp, minor); uffd_test_pass(); } @@ -1029,6 +1537,27 @@ uffd_test_case_t uffd_tests[] = { .uffd_feature_required = 0, }, { + .name = "move", + .uffd_fn = uffd_move_test, + .mem_targets = MEM_ANON, + .uffd_feature_required = UFFD_FEATURE_MOVE, + .test_case_ops = &uffd_move_test_case_ops, + }, + { + .name = "move-pmd", + .uffd_fn = uffd_move_pmd_test, + .mem_targets = MEM_ANON, + .uffd_feature_required = UFFD_FEATURE_MOVE, + .test_case_ops = &uffd_move_test_pmd_case_ops, + }, + { + .name = "move-pmd-split", + .uffd_fn = uffd_move_pmd_split_test, + .mem_targets = MEM_ANON, + .uffd_feature_required = UFFD_FEATURE_MOVE, + .test_case_ops = &uffd_move_test_pmd_case_ops, + }, + { .name = "wp-fork", .uffd_fn = uffd_wp_fork_test, .mem_targets = MEM_ALL, @@ -1108,7 +1637,8 @@ uffd_test_case_t uffd_tests[] = { .uffd_fn = uffd_sigbus_wp_test, .mem_targets = MEM_ALL, .uffd_feature_required = UFFD_FEATURE_SIGBUS | - UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_PAGEFAULT_FLAG_WP, + UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM, }, { .name = "events", @@ -1126,6 +1656,38 @@ uffd_test_case_t uffd_tests[] = { UFFD_FEATURE_PAGEFAULT_FLAG_WP | UFFD_FEATURE_WP_HUGETLBFS_SHMEM, }, + { + .name = "poison", + .uffd_fn = uffd_poison_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_POISON, + }, + { + .name = "mmap-changing", + .uffd_fn = uffd_mmap_changing_test, + /* + * There's no point running this test over all mem types as + * they share the same code paths. + * + * Choose shmem for simplicity, because (1) shmem supports + * MINOR mode to cover UFFDIO_CONTINUE, and (2) shmem is + * almost always available (unlike hugetlb). Here we + * abused SHMEM for UFFDIO_MOVE, but the test we want to + * cover doesn't yet need the correct memory type.. + */ + .mem_targets = MEM_SHMEM, + /* + * Any UFFD_FEATURE_EVENT_* should work to trigger the + * race logically, but choose the simplest (REMOVE). + * + * Meanwhile, since we'll cover quite a few new ioctl()s + * (CONTINUE, POISON, MOVE), skip this test for old kernels + * by choosing all of them. + */ + .uffd_feature_required = UFFD_FEATURE_EVENT_REMOVE | + UFFD_FEATURE_MOVE | UFFD_FEATURE_POISON | + UFFD_FEATURE_MINOR_SHMEM, + }, }; static void usage(const char *prog) @@ -1188,6 +1750,33 @@ int main(int argc, char *argv[]) } for (j = 0; j < n_mems; j++) { mem_type = &mem_types[j]; + + /* Initialize global test options */ + uffd_global_test_opts_t gopts = { 0 }; + + gopts.map_shared = mem_type->shared; + uffd_test_ops = mem_type->mem_ops; + uffd_test_case_ops = test->test_case_ops; + + if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB)) { + gopts.page_size = default_huge_page_size(); + if (gopts.page_size == 0) { + uffd_test_skip("huge page size is 0, feature missing?"); + continue; + } + } else { + gopts.page_size = psize(); + } + + /* Ensure we have at least 2 pages */ + gopts.nr_pages = MAX(UFFD_TEST_MEM_SIZE, gopts.page_size * 2) + / gopts.page_size; + + gopts.nr_parallel = 1; + + /* Initialize test arguments */ + args.mem_type = mem_type; + if (!(test->mem_targets & mem_type->mem_flag)) continue; @@ -1196,12 +1785,12 @@ int main(int argc, char *argv[]) uffd_test_skip("feature missing"); continue; } - if (uffd_setup_environment(&args, test, mem_type, - &errmsg)) { + if (uffd_test_ctx_init(&gopts, test->uffd_feature_required, &errmsg)) { uffd_test_skip(errmsg); continue; } - test->uffd_fn(&args); + test->uffd_fn(&gopts, &args); + uffd_test_ctx_clear(&gopts); } } 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..17186d4a4147 --- /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 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, pagesize)].enabled = THP_ALWAYS; + else + settings.shmem_hugepages[sz2ord(size, pagesize)].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(uffd_global_test_opts_t *gopts, 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(gopts, &features)) { + if (errno == ENOENT) + ksft_test_result_skip("userfaultfd not available\n"); + else + ksft_test_result_fail("userfaultfd_open() failed\n"); + goto out; + } + if (uffd_register(gopts->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(gopts->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 (gopts->uffd >= 0) { + close(gopts->uffd); + gopts->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) +{ + uffd_global_test_opts_t gopts = { 0 }; + 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(&gopts, 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/va_high_addr_switch.c b/tools/testing/selftests/mm/va_high_addr_switch.c index 7cfaf4a74c57..02f290a69132 100644 --- a/tools/testing/selftests/mm/va_high_addr_switch.c +++ b/tools/testing/selftests/mm/va_high_addr_switch.c @@ -9,25 +9,8 @@ #include <sys/mman.h> #include <string.h> -#include "../kselftest.h" - -#ifdef __powerpc64__ -#define PAGE_SIZE (64 << 10) -/* - * This will work with 16M and 2M hugepage size - */ -#define HUGETLB_SIZE (16 << 20) -#elif __aarch64__ -/* - * The default hugepage size for 64k base pagesize - * is 512MB. - */ -#define PAGE_SIZE (64 << 10) -#define HUGETLB_SIZE (512 << 20) -#else -#define PAGE_SIZE (4 << 10) -#define HUGETLB_SIZE (2 << 20) -#endif +#include "vm_util.h" +#include "kselftest.h" /* * The hint addr value is used to allocate addresses @@ -37,18 +20,8 @@ #define ADDR_MARK_128TB (1UL << 47) #define ADDR_MARK_256TB (1UL << 48) -#define HIGH_ADDR_128TB ((void *) (1UL << 48)) -#define HIGH_ADDR_256TB ((void *) (1UL << 49)) - -#define LOW_ADDR ((void *) (1UL << 30)) - -#ifdef __aarch64__ -#define ADDR_SWITCH_HINT ADDR_MARK_256TB -#define HIGH_ADDR HIGH_ADDR_256TB -#else -#define ADDR_SWITCH_HINT ADDR_MARK_128TB -#define HIGH_ADDR HIGH_ADDR_128TB -#endif +#define HIGH_ADDR_128TB (1UL << 48) +#define HIGH_ADDR_256TB (1UL << 49) struct testcase { void *addr; @@ -59,195 +32,230 @@ struct testcase { unsigned int keep_mapped:1; }; -static struct testcase testcases[] = { - { - /* - * If stack is moved, we could possibly allocate - * this at the requested address. - */ - .addr = ((void *)(ADDR_SWITCH_HINT - PAGE_SIZE)), - .size = PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(ADDR_SWITCH_HINT - PAGE_SIZE, PAGE_SIZE)", - .low_addr_required = 1, - }, - { - /* - * Unless MAP_FIXED is specified, allocation based on hint - * addr is never at requested address or above it, which is - * beyond high address switch boundary in this case. Instead, - * a suitable allocation is found in lower address space. - */ - .addr = ((void *)(ADDR_SWITCH_HINT - PAGE_SIZE)), - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(ADDR_SWITCH_HINT - PAGE_SIZE, (2 * PAGE_SIZE))", - .low_addr_required = 1, - }, - { - /* - * Exact mapping at high address switch boundary, should - * be obtained even without MAP_FIXED as area is free. - */ - .addr = ((void *)(ADDR_SWITCH_HINT)), - .size = PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(ADDR_SWITCH_HINT, PAGE_SIZE)", - .keep_mapped = 1, - }, - { - .addr = (void *)(ADDR_SWITCH_HINT), - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, - .msg = "mmap(ADDR_SWITCH_HINT, 2 * PAGE_SIZE, MAP_FIXED)", - }, - { - .addr = NULL, - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(NULL)", - .low_addr_required = 1, - }, - { - .addr = LOW_ADDR, - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(LOW_ADDR)", - .low_addr_required = 1, - }, - { - .addr = HIGH_ADDR, - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(HIGH_ADDR)", - .keep_mapped = 1, - }, - { - .addr = HIGH_ADDR, - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(HIGH_ADDR) again", - .keep_mapped = 1, - }, - { - .addr = HIGH_ADDR, - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, - .msg = "mmap(HIGH_ADDR, MAP_FIXED)", - }, - { - .addr = (void *) -1, - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(-1)", - .keep_mapped = 1, - }, - { - .addr = (void *) -1, - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(-1) again", - }, - { - .addr = ((void *)(ADDR_SWITCH_HINT - PAGE_SIZE)), - .size = PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(ADDR_SWITCH_HINT - PAGE_SIZE, PAGE_SIZE)", - .low_addr_required = 1, - }, - { - .addr = (void *)(ADDR_SWITCH_HINT - PAGE_SIZE), - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(ADDR_SWITCH_HINT - PAGE_SIZE, 2 * PAGE_SIZE)", - .low_addr_required = 1, - .keep_mapped = 1, - }, - { - .addr = (void *)(ADDR_SWITCH_HINT - PAGE_SIZE / 2), - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(ADDR_SWITCH_HINT - PAGE_SIZE/2 , 2 * PAGE_SIZE)", - .low_addr_required = 1, - .keep_mapped = 1, - }, - { - .addr = ((void *)(ADDR_SWITCH_HINT)), - .size = PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(ADDR_SWITCH_HINT, PAGE_SIZE)", - }, - { - .addr = (void *)(ADDR_SWITCH_HINT), - .size = 2 * PAGE_SIZE, - .flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, - .msg = "mmap(ADDR_SWITCH_HINT, 2 * PAGE_SIZE, MAP_FIXED)", - }, -}; +static struct testcase *testcases; +static struct testcase *hugetlb_testcases; +static int sz_testcases, sz_hugetlb_testcases; +static unsigned long switch_hint; -static struct testcase hugetlb_testcases[] = { - { - .addr = NULL, - .size = HUGETLB_SIZE, - .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(NULL, MAP_HUGETLB)", - .low_addr_required = 1, - }, - { - .addr = LOW_ADDR, - .size = HUGETLB_SIZE, - .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(LOW_ADDR, MAP_HUGETLB)", - .low_addr_required = 1, - }, - { - .addr = HIGH_ADDR, - .size = HUGETLB_SIZE, - .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(HIGH_ADDR, MAP_HUGETLB)", - .keep_mapped = 1, - }, - { - .addr = HIGH_ADDR, - .size = HUGETLB_SIZE, - .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(HIGH_ADDR, MAP_HUGETLB) again", - .keep_mapped = 1, - }, - { - .addr = HIGH_ADDR, - .size = HUGETLB_SIZE, - .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, - .msg = "mmap(HIGH_ADDR, MAP_FIXED | MAP_HUGETLB)", - }, - { - .addr = (void *) -1, - .size = HUGETLB_SIZE, - .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(-1, MAP_HUGETLB)", - .keep_mapped = 1, - }, - { - .addr = (void *) -1, - .size = HUGETLB_SIZE, - .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(-1, MAP_HUGETLB) again", - }, - { - .addr = (void *)(ADDR_SWITCH_HINT - PAGE_SIZE), - .size = 2 * HUGETLB_SIZE, - .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, - .msg = "mmap(ADDR_SWITCH_HINT - PAGE_SIZE, 2*HUGETLB_SIZE, MAP_HUGETLB)", - .low_addr_required = 1, - .keep_mapped = 1, - }, - { - .addr = (void *)(ADDR_SWITCH_HINT), - .size = 2 * HUGETLB_SIZE, - .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, - .msg = "mmap(ADDR_SWITCH_HINT , 2*HUGETLB_SIZE, MAP_FIXED | MAP_HUGETLB)", - }, -}; +/* Initialize testcases inside a function to compute parameters at runtime */ +void testcases_init(void) +{ + unsigned long pagesize = getpagesize(); + unsigned long hugepagesize = default_huge_page_size(); + unsigned long low_addr = (1UL << 30); + unsigned long addr_switch_hint = ADDR_MARK_128TB; + unsigned long high_addr = HIGH_ADDR_128TB; + +#ifdef __aarch64__ + + /* Post LPA2, the lower userspace VA on a 16K pagesize is 47 bits. */ + if (pagesize != (16UL << 10)) { + addr_switch_hint = ADDR_MARK_256TB; + high_addr = HIGH_ADDR_256TB; + } +#endif + + struct testcase t[] = { + { + /* + * If stack is moved, we could possibly allocate + * this at the requested address. + */ + .addr = ((void *)(addr_switch_hint - pagesize)), + .size = pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(addr_switch_hint - pagesize, pagesize)", + .low_addr_required = 1, + }, + { + /* + * Unless MAP_FIXED is specified, allocation based on hint + * addr is never at requested address or above it, which is + * beyond high address switch boundary in this case. Instead, + * a suitable allocation is found in lower address space. + */ + .addr = ((void *)(addr_switch_hint - pagesize)), + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(addr_switch_hint - pagesize, (2 * pagesize))", + .low_addr_required = 1, + }, + { + /* + * Exact mapping at high address switch boundary, should + * be obtained even without MAP_FIXED as area is free. + */ + .addr = ((void *)(addr_switch_hint)), + .size = pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(addr_switch_hint, pagesize)", + .keep_mapped = 1, + }, + { + .addr = (void *)(addr_switch_hint), + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, + .msg = "mmap(addr_switch_hint, 2 * pagesize, MAP_FIXED)", + }, + { + .addr = NULL, + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(NULL)", + .low_addr_required = 1, + }, + { + .addr = (void *)low_addr, + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(low_addr)", + .low_addr_required = 1, + }, + { + .addr = (void *)high_addr, + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(high_addr)", + .keep_mapped = 1, + }, + { + .addr = (void *)high_addr, + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(high_addr) again", + .keep_mapped = 1, + }, + { + .addr = (void *)high_addr, + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, + .msg = "mmap(high_addr, MAP_FIXED)", + }, + { + .addr = (void *) -1, + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(-1)", + .keep_mapped = 1, + }, + { + .addr = (void *) -1, + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(-1) again", + }, + { + .addr = ((void *)(addr_switch_hint - pagesize)), + .size = pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(addr_switch_hint - pagesize, pagesize)", + .low_addr_required = 1, + }, + { + .addr = (void *)(addr_switch_hint - pagesize), + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(addr_switch_hint - pagesize, 2 * pagesize)", + .low_addr_required = 1, + .keep_mapped = 1, + }, + { + .addr = (void *)(addr_switch_hint - pagesize / 2), + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(addr_switch_hint - pagesize/2 , 2 * pagesize)", + .low_addr_required = 1, + .keep_mapped = 1, + }, + { + .addr = ((void *)(addr_switch_hint)), + .size = pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(addr_switch_hint, pagesize)", + }, + { + .addr = (void *)(addr_switch_hint), + .size = 2 * pagesize, + .flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, + .msg = "mmap(addr_switch_hint, 2 * pagesize, MAP_FIXED)", + }, + }; + + struct testcase ht[] = { + { + .addr = NULL, + .size = hugepagesize, + .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(NULL, MAP_HUGETLB)", + .low_addr_required = 1, + }, + { + .addr = (void *)low_addr, + .size = hugepagesize, + .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(low_addr, MAP_HUGETLB)", + .low_addr_required = 1, + }, + { + .addr = (void *)high_addr, + .size = hugepagesize, + .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(high_addr, MAP_HUGETLB)", + .keep_mapped = 1, + }, + { + .addr = (void *)high_addr, + .size = hugepagesize, + .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(high_addr, MAP_HUGETLB) again", + .keep_mapped = 1, + }, + { + .addr = (void *)high_addr, + .size = hugepagesize, + .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, + .msg = "mmap(high_addr, MAP_FIXED | MAP_HUGETLB)", + }, + { + .addr = (void *) -1, + .size = hugepagesize, + .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(-1, MAP_HUGETLB)", + .keep_mapped = 1, + }, + { + .addr = (void *) -1, + .size = hugepagesize, + .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(-1, MAP_HUGETLB) again", + }, + { + .addr = (void *)(addr_switch_hint - hugepagesize), + .size = 2 * hugepagesize, + .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS, + .msg = "mmap(addr_switch_hint - hugepagesize, 2*hugepagesize, MAP_HUGETLB)", + .low_addr_required = 1, + .keep_mapped = 1, + }, + { + .addr = (void *)(addr_switch_hint), + .size = 2 * hugepagesize, + .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, + .msg = "mmap(addr_switch_hint , 2*hugepagesize, MAP_FIXED | MAP_HUGETLB)", + }, + }; + + testcases = malloc(sizeof(t)); + hugetlb_testcases = malloc(sizeof(ht)); + + /* Copy into global arrays */ + memcpy(testcases, t, sizeof(t)); + memcpy(hugetlb_testcases, ht, sizeof(ht)); + + sz_testcases = ARRAY_SIZE(t); + sz_hugetlb_testcases = ARRAY_SIZE(ht); + switch_hint = addr_switch_hint; +} static int run_test(struct testcase *test, int count) { @@ -267,7 +275,7 @@ static int run_test(struct testcase *test, int count) continue; } - if (t->low_addr_required && p >= (void *)(ADDR_SWITCH_HINT)) { + if (t->low_addr_required && p >= (void *)(switch_hint)) { printf("FAILED\n"); ret = KSFT_FAIL; } else { @@ -285,6 +293,20 @@ static int run_test(struct testcase *test, int count) return ret; } +#ifdef __aarch64__ +/* Check if userspace VA > 48 bits */ +static int high_address_present(void) +{ + void *ptr = mmap((void *)(1UL << 50), 1, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0); + if (ptr == MAP_FAILED) + return 0; + + munmap(ptr, 1); + return 1; +} +#endif + static int supported_arch(void) { #if defined(__powerpc64__) @@ -292,7 +314,7 @@ static int supported_arch(void) #elif defined(__x86_64__) return 1; #elif defined(__aarch64__) - return 1; + return high_address_present(); #else return 0; #endif @@ -305,8 +327,10 @@ int main(int argc, char **argv) if (!supported_arch()) return KSFT_SKIP; - ret = run_test(testcases, ARRAY_SIZE(testcases)); + testcases_init(); + + ret = run_test(testcases, sz_testcases); if (argc == 2 && !strcmp(argv[1], "--run-hugetlb")) - ret = run_test(hugetlb_testcases, ARRAY_SIZE(hugetlb_testcases)); + ret = run_test(hugetlb_testcases, sz_hugetlb_testcases); return ret; } diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh index 45cae7cab27e..a7d4b02b21dd 100755 --- a/tools/testing/selftests/mm/va_high_addr_switch.sh +++ b/tools/testing/selftests/mm/va_high_addr_switch.sh @@ -7,31 +7,55 @@ # real test to check that the kernel is configured to support at least 5 # pagetable levels. -# 1 means the test failed -exitcode=1 - # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +orig_nr_hugepages=0 -fail() +skip() { echo "$1" - exit $exitcode + exit $ksft_skip } check_supported_x86_64() { local config="/proc/config.gz" [[ -f "${config}" ]] || config="/boot/config-$(uname -r)" - [[ -f "${config}" ]] || fail "Cannot find kernel config in /proc or /boot" + [[ -f "${config}" ]] || skip "Cannot find kernel config in /proc or /boot" # gzip -dcfq automatically handles both compressed and plaintext input. # See man 1 gzip under '-f'. local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2) + local cpu_supports_pl5=$(awk '/^flags/ {if (/la57/) {print 0;} + else {print 1}; exit}' /proc/cpuinfo 2>/dev/null) + if [[ "${pg_table_levels}" -lt 5 ]]; then - echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test" - exit $ksft_skip + skip "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test" + elif [[ "${cpu_supports_pl5}" -ne 0 ]]; then + skip "$0: CPU does not have the necessary la57 flag to support page table level 5" + fi +} + +check_supported_ppc64() +{ + local config="/proc/config.gz" + [[ -f "${config}" ]] || config="/boot/config-$(uname -r)" + [[ -f "${config}" ]] || skip "Cannot find kernel config in /proc or /boot" + + local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2) + if [[ "${pg_table_levels}" -lt 5 ]]; then + skip "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test" + fi + + local mmu_support=$(grep -m1 "mmu" /proc/cpuinfo | awk '{print $3}') + if [[ "$mmu_support" != "radix" ]]; then + skip "$0: System does not use Radix MMU, required for 5-level paging" + fi + + local hugepages_total=$(awk '/HugePages_Total/ {print $2}' /proc/meminfo) + if [[ "${hugepages_total}" -eq 0 ]]; then + skip "$0: HugePages are not enabled, required for some tests" fi } @@ -44,15 +68,50 @@ check_test_requirements() "x86_64") check_supported_x86_64 ;; + "ppc64le"|"ppc64") + check_supported_ppc64 + ;; *) return 0 ;; esac } -check_test_requirements -./va_high_addr_switch +save_nr_hugepages() +{ + orig_nr_hugepages=$(cat /proc/sys/vm/nr_hugepages) +} + +restore_nr_hugepages() +{ + echo "$orig_nr_hugepages" > /proc/sys/vm/nr_hugepages +} -# In order to run hugetlb testcases, "--run-hugetlb" must be appended -# to the binary. +setup_nr_hugepages() +{ + local needpgs=$1 + while read -r name size unit; do + if [ "$name" = "HugePages_Free:" ]; then + freepgs="$size" + break + fi + done < /proc/meminfo + if [ "$freepgs" -ge "$needpgs" ]; then + return + fi + local hpgs=$((orig_nr_hugepages + needpgs)) + echo $hpgs > /proc/sys/vm/nr_hugepages + + local nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) + if [ "$nr_hugepgs" != "$hpgs" ]; then + restore_nr_hugepages + skip "$0: no enough hugepages for testing" + fi +} + +check_test_requirements +save_nr_hugepages +# 4 keep_mapped pages, and one for tmp usage +setup_nr_hugepages 5 ./va_high_addr_switch --run-hugetlb +restore_nr_hugepages diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index bae0ceaf95b1..4f0923825ed7 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -10,8 +10,13 @@ #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" /* * Maximum address range mapped with a single mmap() @@ -39,12 +44,18 @@ * On Arm64 the address space is 256TB and support for * high mappings up to 4PB virtual address space has * been added. + * + * On PowerPC64, the address space up to 128TB can be + * mapped without a hint. Addresses beyond 128TB, up to + * 4PB, can be mapped with a hint. + * */ #define NR_CHUNKS_128TB ((128 * SZ_1TB) / MAP_CHUNK_SIZE) /* Number of chunks for 128TB */ #define NR_CHUNKS_256TB (NR_CHUNKS_128TB * 2UL) #define NR_CHUNKS_384TB (NR_CHUNKS_128TB * 3UL) #define NR_CHUNKS_3840TB (NR_CHUNKS_128TB * 30UL) +#define NR_CHUNKS_3968TB (NR_CHUNKS_128TB * 31UL) #define ADDR_MARK_128TB (1UL << 47) /* First address beyond 128TB */ #define ADDR_MARK_256TB (1UL << 48) /* First address beyond 256TB */ @@ -54,6 +65,11 @@ #define HIGH_ADDR_SHIFT 49 #define NR_CHUNKS_LOW NR_CHUNKS_256TB #define NR_CHUNKS_HIGH NR_CHUNKS_3840TB +#elif defined(__PPC64__) +#define HIGH_ADDR_MARK ADDR_MARK_128TB +#define HIGH_ADDR_SHIFT 48 +#define NR_CHUNKS_LOW NR_CHUNKS_128TB +#define NR_CHUNKS_HIGH NR_CHUNKS_3968TB #else #define HIGH_ADDR_MARK ADDR_MARK_128TB #define HIGH_ADDR_SHIFT 48 @@ -61,30 +77,43 @@ #define NR_CHUNKS_HIGH NR_CHUNKS_384TB #endif -static char *hind_addr(void) +static char *hint_addr(void) { int bits = HIGH_ADDR_SHIFT + rand() % (63 - HIGH_ADDR_SHIFT); return (char *) (1UL << bits); } -static int validate_addr(char *ptr, int high_addr) +static void validate_addr(char *ptr, int high_addr) { unsigned long addr = (unsigned long) ptr; if (high_addr) { - if (addr < HIGH_ADDR_MARK) { - printf("Bad address %lx\n", addr); - return 1; - } - return 0; + if (addr < HIGH_ADDR_MARK) + ksft_exit_fail_msg("Bad address %lx\n", addr); + return; } - if (addr > HIGH_ADDR_MARK) { - printf("Bad address %lx\n", addr); - return 1; + if (addr > HIGH_ADDR_MARK) + 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"); + } } - return 0; +} + +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) @@ -92,7 +121,7 @@ static int validate_lower_address_hint(void) char *ptr; ptr = mmap((void *) (1UL << 45), MAP_CHUNK_SIZE, PROT_READ | - PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (ptr == MAP_FAILED) return 0; @@ -100,6 +129,77 @@ static int validate_lower_address_hint(void) return 1; } +static int validate_complete_va_space(void) +{ + unsigned long start_addr, end_addr, prev_end_addr; + char line[400]; + char prot[6]; + FILE *file; + int fd; + + fd = open("va_dump", O_CREAT | O_WRONLY, 0600); + unlink("va_dump"); + if (fd < 0) { + ksft_test_result_skip("cannot create or open dump file\n"); + ksft_finished(); + } + + file = fopen("/proc/self/maps", "r"); + if (file == NULL) + ksft_exit_fail_msg("cannot open /proc/self/maps\n"); + + 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 %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; + + /* /proc/self/maps must have gaps less than MAP_CHUNK_SIZE */ + if (start_addr - prev_end_addr >= MAP_CHUNK_SIZE) + return 1; + + prev_end_addr = end_addr; + + 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 + * addresses after that. If the address was not held by this + * process, write would fail with errno set to EFAULT. + * Anyways, if write returns anything apart from 1, exit the + * program since that would mean a bug in /proc/self/maps. + */ + hop = 0; + while (start_addr + hop < end_addr) { + if (write(fd, (void *)(start_addr + hop), 1) != 1) + 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; + } + } + return 0; +} + int main(int argc, char *argv[]) { char *ptr[NR_CHUNKS_LOW]; @@ -107,36 +207,45 @@ int main(int argc, char *argv[]) char *hint; unsigned long i, lchunks, hchunks; + ksft_print_header(); + ksft_set_plan(1); + for (i = 0; i < NR_CHUNKS_LOW; i++) { - ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (ptr[i] == MAP_FAILED) { if (validate_lower_address_hint()) - return 1; + ksft_exit_fail_msg("mmap unexpectedly succeeded with hint\n"); break; } - if (validate_addr(ptr[i], 0)) - return 1; + mark_range(ptr[i], MAP_CHUNK_SIZE); + validate_addr(ptr[i], 0); } lchunks = i; hptr = (char **) calloc(NR_CHUNKS_HIGH, sizeof(char *)); - if (hptr == NULL) - return 1; + if (hptr == NULL) { + ksft_test_result_skip("Memory constraint not fulfilled\n"); + ksft_finished(); + } for (i = 0; i < NR_CHUNKS_HIGH; i++) { - hint = hind_addr(); - hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + hint = hint_addr(); + hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (hptr[i] == MAP_FAILED) break; - if (validate_addr(hptr[i], 1)) - return 1; + mark_range(hptr[i], MAP_CHUNK_SIZE); + validate_addr(hptr[i], 1); } hchunks = i; + if (validate_complete_va_space()) { + ksft_test_result_fail("BUG in mmap() or /proc/self/maps\n"); + ksft_finished(); + } for (i = 0; i < lchunks; i++) munmap(ptr[i], MAP_CHUNK_SIZE); @@ -145,5 +254,7 @@ int main(int argc, char *argv[]) munmap(hptr[i], MAP_CHUNK_SIZE); free(hptr); - return 0; + + ksft_test_result_pass("Test\n"); + ksft_finished(); } diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 558c9cd8901c..d954bf91afd5 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -1,16 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> +#include <errno.h> #include <fcntl.h> #include <dirent.h> +#include <inttypes.h> #include <sys/ioctl.h> #include <linux/userfaultfd.h> +#include <linux/fs.h> #include <sys/syscall.h> #include <unistd.h> -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" #define PMD_SIZE_FILE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" #define SMAP_FILE_PATH "/proc/self/smaps" +#define STATUS_FILE_PATH "/proc/self/status" #define MAX_LINE_LENGTH 500 unsigned int __page_size; @@ -28,19 +32,92 @@ uint64_t pagemap_get_entry(int fd, char *start) return entry; } +static uint64_t __pagemap_scan_get_categories(int fd, char *start, struct page_region *r) +{ + struct pm_scan_arg arg; + + arg.start = (uintptr_t)start; + arg.end = (uintptr_t)(start + psize()); + arg.vec = (uintptr_t)r; + arg.vec_len = 1; + arg.flags = 0; + arg.size = sizeof(struct pm_scan_arg); + arg.max_pages = 0; + arg.category_inverted = 0; + arg.category_mask = 0; + arg.category_anyof_mask = PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | PAGE_IS_FILE | + PAGE_IS_PRESENT | PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | + PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY; + arg.return_mask = arg.category_anyof_mask; + + return ioctl(fd, PAGEMAP_SCAN, &arg); +} + +static uint64_t pagemap_scan_get_categories(int fd, char *start) +{ + struct page_region r; + long ret; + + ret = __pagemap_scan_get_categories(fd, start, &r); + if (ret < 0) + ksft_exit_fail_msg("PAGEMAP_SCAN failed: %s\n", strerror(errno)); + if (ret == 0) + return 0; + return r.categories; +} + +/* `start` is any valid address. */ +static bool pagemap_scan_supported(int fd, char *start) +{ + static int supported = -1; + int ret; + + if (supported != -1) + return supported; + + /* Provide an invalid address in order to trigger EFAULT. */ + ret = __pagemap_scan_get_categories(fd, start, (struct page_region *) ~0UL); + if (ret == 0) + ksft_exit_fail_msg("PAGEMAP_SCAN succeeded unexpectedly\n"); + + supported = errno == EFAULT; + + return supported; +} + +static bool page_entry_is(int fd, char *start, char *desc, + uint64_t pagemap_flags, uint64_t pagescan_flags) +{ + bool m = pagemap_get_entry(fd, start) & pagemap_flags; + + if (pagemap_scan_supported(fd, start)) { + bool s = pagemap_scan_get_categories(fd, start) & pagescan_flags; + + if (m == s) + return m; + + ksft_exit_fail_msg( + "read and ioctl return unmatched results for %s: %d %d", desc, m, s); + } + return m; +} + bool pagemap_is_softdirty(int fd, char *start) { - return pagemap_get_entry(fd, start) & PM_SOFT_DIRTY; + return page_entry_is(fd, start, "soft-dirty", + PM_SOFT_DIRTY, PAGE_IS_SOFT_DIRTY); } bool pagemap_is_swapped(int fd, char *start) { - return pagemap_get_entry(fd, start) & PM_SWAP; + return page_entry_is(fd, start, "swap", PM_SWAP, PAGE_IS_SWAPPED); } bool pagemap_is_populated(int fd, char *start) { - return pagemap_get_entry(fd, start) & (PM_PRESENT | PM_SWAP); + return page_entry_is(fd, start, "populated", + PM_PRESENT | PM_SWAP, + PAGE_IS_PRESENT | PAGE_IS_SWAPPED); } unsigned long pagemap_get_pfn(int fd, char *start) @@ -63,7 +140,7 @@ 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"); } @@ -97,13 +174,32 @@ uint64_t read_pmd_pagesize(void) return strtoul(buf, NULL, 10); } -bool __check_huge(void *addr, char *pattern, int nr_hpages, - uint64_t hpage_size) +unsigned long rss_anon(void) { - uint64_t thp = -1; - int ret; + unsigned long rss_anon = 0; FILE *fp; char buffer[MAX_LINE_LENGTH]; + + fp = fopen(STATUS_FILE_PATH, "r"); + if (!fp) + ksft_exit_fail_msg("%s: Failed to open file %s\n", __func__, STATUS_FILE_PATH); + + if (!check_for_pattern(fp, "RssAnon:", buffer, sizeof(buffer))) + goto err_out; + + if (sscanf(buffer, "RssAnon:%10lu kB", &rss_anon) != 1) + ksft_exit_fail_msg("Reading status error\n"); + +err_out: + fclose(fp); + return rss_anon; +} + +char *__get_smap_entry(void *addr, const char *pattern, char *buf, size_t len) +{ + int ret; + FILE *fp; + char *entry = NULL; char addr_pattern[MAX_LINE_LENGTH]; ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", @@ -115,23 +211,40 @@ 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)); } @@ -158,17 +271,17 @@ int64_t allocate_transhuge(void *ptr, int pagemap_fd) if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, MAP_FIXED | MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) - errx(2, "mmap transhuge"); + ksft_exit_fail_msg("mmap transhuge\n"); if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) - err(2, "MADV_HUGEPAGE"); + ksft_exit_fail_msg("MADV_HUGEPAGE\n"); /* allocate transparent huge page */ *(volatile void **)ptr = ptr; if (pread(pagemap_fd, ent, sizeof(ent), (uintptr_t)ptr >> (pshift() - 3)) != sizeof(ent)) - err(2, "read pagemap"); + ksft_exit_fail_msg("read pagemap\n"); if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && @@ -225,6 +338,19 @@ int detect_hugetlb_page_sizes(size_t sizes[], int max) return count; } +int pageflags_get(unsigned long pfn, int kpageflags_fd, uint64_t *flags) +{ + size_t count; + + count = pread(kpageflags_fd, flags, sizeof(*flags), + pfn * sizeof(*flags)); + + if (count != sizeof(*flags)) + return -1; + + return 0; +} + /* If `ioctls' non-NULL, the allowed ioctls will be returned into the var */ int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls) @@ -269,3 +395,331 @@ int uffd_unregister(int uffd, void *addr, uint64_t len) return ret; } + +unsigned long get_free_hugepages(void) +{ + unsigned long fhp = 0; + char *line = NULL; + size_t linelen = 0; + FILE *f = fopen("/proc/meminfo", "r"); + + if (!f) + return fhp; + while (getline(&line, &linelen, f) > 0) { + if (sscanf(line, "HugePages_Free: %lu", &fhp) == 1) + break; + } + + free(line); + fclose(f); + return fhp; +} + +static bool check_vmflag(void *addr, const char *flag) +{ + 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(flag) && !memcmp(flags, flag, flaglen)) + return true; + + flags += flaglen; + } +} + +bool check_vmflag_io(void *addr) +{ + return check_vmflag(addr, "io"); +} + +bool check_vmflag_pfnmap(void *addr) +{ + return check_vmflag(addr, "pf"); +} + +bool check_vmflag_guard(void *addr) +{ + return check_vmflag(addr, "gu"); +} + +bool softdirty_supported(void) +{ + char *addr; + bool supported = false; + const size_t pagesize = getpagesize(); + + /* New mappings are expected to be marked with VM_SOFTDIRTY (sd). */ + addr = mmap(0, pagesize, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + if (!addr) + ksft_exit_fail_msg("mmap failed\n"); + + supported = check_vmflag(addr, "sd"); + munmap(addr, pagesize); + return supported; +} + +/* + * Open an fd at /proc/$pid/maps and configure procmap_out ready for + * PROCMAP_QUERY query. Returns 0 on success, or an error code otherwise. + */ +int open_procmap(pid_t pid, struct procmap_fd *procmap_out) +{ + char path[256]; + int ret = 0; + + memset(procmap_out, '\0', sizeof(*procmap_out)); + sprintf(path, "/proc/%d/maps", pid); + procmap_out->query.size = sizeof(procmap_out->query); + procmap_out->fd = open(path, O_RDONLY); + if (procmap_out->fd < 0) + ret = -errno; + + return ret; +} + +/* Perform PROCMAP_QUERY. Returns 0 on success, or an error code otherwise. */ +int query_procmap(struct procmap_fd *procmap) +{ + int ret = 0; + + if (ioctl(procmap->fd, PROCMAP_QUERY, &procmap->query) == -1) + ret = -errno; + + return ret; +} + +/* + * Try to find the VMA at specified address, returns true if found, false if not + * found, and the test is failed if any other error occurs. + * + * On success, procmap->query is populated with the results. + */ +bool find_vma_procmap(struct procmap_fd *procmap, void *address) +{ + int err; + + procmap->query.query_flags = 0; + procmap->query.query_addr = (unsigned long)address; + err = query_procmap(procmap); + if (!err) + return true; + + if (err != -ENOENT) + ksft_exit_fail_msg("%s: Error %d on ioctl(PROCMAP_QUERY)\n", + __func__, err); + return false; +} + +/* + * Close fd used by PROCMAP_QUERY mechanism. Returns 0 on success, or an error + * code otherwise. + */ +int close_procmap(struct procmap_fd *procmap) +{ + return close(procmap->fd); +} + +int write_sysfs(const char *file_path, unsigned long val) +{ + FILE *f = fopen(file_path, "w"); + + if (!f) { + fprintf(stderr, "f %s\n", file_path); + perror("fopen"); + return 1; + } + if (fprintf(f, "%lu", val) < 0) { + perror("fprintf"); + fclose(f); + return 1; + } + fclose(f); + + return 0; +} + +int read_sysfs(const char *file_path, unsigned long *val) +{ + FILE *f = fopen(file_path, "r"); + + if (!f) { + fprintf(stderr, "f %s\n", file_path); + perror("fopen"); + return 1; + } + if (fscanf(f, "%lu", val) != 1) { + perror("fscanf"); + fclose(f); + return 1; + } + fclose(f); + + return 0; +} + +void *sys_mremap(void *old_address, unsigned long old_size, + unsigned long new_size, int flags, void *new_address) +{ + return (void *)syscall(__NR_mremap, (unsigned long)old_address, + old_size, new_size, flags, + (unsigned long)new_address); +} + +bool detect_huge_zeropage(void) +{ + int fd = open("/sys/kernel/mm/transparent_hugepage/use_zero_page", + O_RDONLY); + bool enabled = 0; + char buf[15]; + int ret; + + if (fd < 0) + return 0; + + ret = pread(fd, buf, sizeof(buf), 0); + if (ret > 0 && ret < sizeof(buf)) { + buf[ret] = 0; + + if (strtoul(buf, NULL, 10) == 1) + enabled = 1; + } + + close(fd); + return enabled; +} + +long ksm_get_self_zero_pages(void) +{ + int proc_self_ksm_stat_fd; + char buf[200]; + char *substr_ksm_zero; + size_t value_pos; + ssize_t read_size; + + proc_self_ksm_stat_fd = open("/proc/self/ksm_stat", O_RDONLY); + if (proc_self_ksm_stat_fd < 0) + return -errno; + + read_size = pread(proc_self_ksm_stat_fd, buf, sizeof(buf) - 1, 0); + close(proc_self_ksm_stat_fd); + if (read_size < 0) + return -errno; + + buf[read_size] = 0; + + substr_ksm_zero = strstr(buf, "ksm_zero_pages"); + if (!substr_ksm_zero) + return 0; + + value_pos = strcspn(substr_ksm_zero, "0123456789"); + return strtol(substr_ksm_zero + value_pos, NULL, 10); +} + +long ksm_get_self_merging_pages(void) +{ + int proc_self_ksm_merging_pages_fd; + char buf[10]; + ssize_t ret; + + proc_self_ksm_merging_pages_fd = open("/proc/self/ksm_merging_pages", + O_RDONLY); + if (proc_self_ksm_merging_pages_fd < 0) + return -errno; + + ret = pread(proc_self_ksm_merging_pages_fd, buf, sizeof(buf) - 1, 0); + close(proc_self_ksm_merging_pages_fd); + if (ret <= 0) + return -errno; + buf[ret] = 0; + + return strtol(buf, NULL, 10); +} + +long ksm_get_full_scans(void) +{ + int ksm_full_scans_fd; + char buf[10]; + ssize_t ret; + + ksm_full_scans_fd = open("/sys/kernel/mm/ksm/full_scans", O_RDONLY); + if (ksm_full_scans_fd < 0) + return -errno; + + ret = pread(ksm_full_scans_fd, buf, sizeof(buf) - 1, 0); + close(ksm_full_scans_fd); + if (ret <= 0) + return -errno; + buf[ret] = 0; + + return strtol(buf, NULL, 10); +} + +int ksm_use_zero_pages(void) +{ + int ksm_use_zero_pages_fd; + ssize_t ret; + + ksm_use_zero_pages_fd = open("/sys/kernel/mm/ksm/use_zero_pages", O_RDWR); + if (ksm_use_zero_pages_fd < 0) + return -errno; + + ret = write(ksm_use_zero_pages_fd, "1", 1); + close(ksm_use_zero_pages_fd); + return ret == 1 ? 0 : -errno; +} + +int ksm_start(void) +{ + int ksm_fd; + ssize_t ret; + long start_scans, end_scans; + + ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); + if (ksm_fd < 0) + return -errno; + + /* Wait for two full scans such that any possible merging happened. */ + start_scans = ksm_get_full_scans(); + if (start_scans < 0) { + close(ksm_fd); + return start_scans; + } + ret = write(ksm_fd, "1", 1); + close(ksm_fd); + if (ret != 1) + return -errno; + do { + end_scans = ksm_get_full_scans(); + if (end_scans < 0) + return end_scans; + } while (end_scans < start_scans + 2); + + return 0; +} + +int ksm_stop(void) +{ + int ksm_fd; + ssize_t ret; + + ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); + if (ksm_fd < 0) + return -errno; + + ret = write(ksm_fd, "2", 1); + close(ksm_fd); + return ret == 1 ? 0 : -errno; +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index c7fa61f0dff8..6ad32b1830f1 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -3,20 +3,43 @@ #include <stdbool.h> #include <sys/mman.h> #include <err.h> -#include <string.h> /* ffsl() */ +#include <stdarg.h> +#include <strings.h> /* ffsl() */ #include <unistd.h> /* _SC_PAGESIZE */ +#include "kselftest.h" +#include <linux/fs.h> #define BIT_ULL(nr) (1ULL << (nr)) #define PM_SOFT_DIRTY BIT_ULL(55) #define PM_MMAP_EXCLUSIVE BIT_ULL(56) #define PM_UFFD_WP BIT_ULL(57) +#define PM_GUARD_REGION BIT_ULL(58) #define PM_FILE BIT_ULL(61) #define PM_SWAP BIT_ULL(62) #define PM_PRESENT BIT_ULL(63) +#define KPF_COMPOUND_HEAD BIT_ULL(15) +#define KPF_COMPOUND_TAIL BIT_ULL(16) +#define KPF_THP BIT_ULL(22) +/* + * Ignore the checkpatch warning, we must read from x but don't want to do + * anything with it in order to trigger a read page fault. We therefore must use + * volatile to stop the compiler from optimising this away. + */ +#define FORCE_READ(x) (*(const volatile typeof(x) *)&(x)) + extern unsigned int __page_size; extern unsigned int __page_shift; +/* + * Represents an open fd and PROCMAP_QUERY state for binary (via ioctl) + * /proc/$pid/[s]maps lookup. + */ +struct procmap_fd { + int fd; + struct procmap_query query; +}; + static inline unsigned int psize(void) { if (!__page_size) @@ -31,6 +54,25 @@ static inline unsigned int pshift(void) return __page_shift; } +bool detect_huge_zeropage(void); + +/* + * Plan 9 FS has bugs (at least on QEMU) where certain operations fail with + * ENOENT on unlinked files. See + * https://gitlab.com/qemu-project/qemu/-/issues/103 for some info about such + * bugs. There are rumours of NFS implementations with similar bugs. + * + * Ideally, tests should just detect filesystems known to have such issues and + * bail early. But 9pfs has the additional "feature" that it causes fstatfs to + * pass through the f_type field from the host filesystem. To avoid having to + * scrape /proc/mounts or some other hackery, tests can call this function when + * it seems such a bug might have been encountered. + */ +static inline void skip_test_dodgy_fs(const char *op_name) +{ + ksft_test_result_skip("%s failed with ENOENT. Filesystem might be buggy (9pfs?)\n", op_name); +} + uint64_t pagemap_get_entry(int fd, char *start); bool pagemap_is_softdirty(int fd, char *start); bool pagemap_is_swapped(int fd, char *start); @@ -39,18 +81,72 @@ unsigned long pagemap_get_pfn(int fd, char *start); void clear_softdirty(void); bool check_for_pattern(FILE *fp, const char *pattern, char *buf, size_t len); uint64_t read_pmd_pagesize(void); +unsigned long rss_anon(void); bool check_huge_anon(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_file(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size); int64_t allocate_transhuge(void *ptr, int pagemap_fd); unsigned long default_huge_page_size(void); int detect_hugetlb_page_sizes(size_t sizes[], int max); +int pageflags_get(unsigned long pfn, int kpageflags_fd, uint64_t *flags); int uffd_register(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor); 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); +bool check_vmflag_pfnmap(void *addr); +bool check_vmflag_guard(void *addr); +int open_procmap(pid_t pid, struct procmap_fd *procmap_out); +int query_procmap(struct procmap_fd *procmap); +bool find_vma_procmap(struct procmap_fd *procmap, void *address); +int close_procmap(struct procmap_fd *procmap); +int write_sysfs(const char *file_path, unsigned long val); +int read_sysfs(const char *file_path, unsigned long *val); +bool softdirty_supported(void); + +static inline int open_self_procmap(struct procmap_fd *procmap_out) +{ + pid_t pid = getpid(); + + return open_procmap(pid, procmap_out); +} + +/* These helpers need to be inline to match the kselftest.h idiom. */ +static char test_name[1024]; + +static inline void log_test_start(const char *name, ...) +{ + va_list args; + va_start(args, name); + + vsnprintf(test_name, sizeof(test_name), name, args); + ksft_print_msg("[RUN] %s\n", test_name); + + va_end(args); +} + +static inline void log_test_result(int result) +{ + ksft_test_result_report(result, "%s\n", test_name); +} + +static inline int sz2ord(size_t size, size_t pagesize) +{ + return __builtin_ctzll(size / pagesize); +} + +void *sys_mremap(void *old_address, unsigned long old_size, + unsigned long new_size, int flags, void *new_address); + +long ksm_get_self_zero_pages(void); +long ksm_get_self_merging_pages(void); +long ksm_get_full_scans(void); +int ksm_use_zero_pages(void); +int ksm_start(void); +int ksm_stop(void); /* * On ppc64 this will only work with radix 2M hugepage size diff --git a/tools/testing/selftests/mm/write_hugetlb_memory.sh b/tools/testing/selftests/mm/write_hugetlb_memory.sh index 70a02301f4c2..3d2d2eb9d6ff 100755 --- a/tools/testing/selftests/mm/write_hugetlb_memory.sh +++ b/tools/testing/selftests/mm/write_hugetlb_memory.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/testing/selftests/mm/write_to_hugetlbfs.c b/tools/testing/selftests/mm/write_to_hugetlbfs.c index 6a2caba19ee1..34c91f7e6128 100644 --- a/tools/testing/selftests/mm/write_to_hugetlbfs.c +++ b/tools/testing/selftests/mm/write_to_hugetlbfs.c @@ -28,7 +28,7 @@ enum method { /* Global variables. */ static const char *self; -static char *shmaddr; +static int *shmaddr; static int shmid; /* @@ -47,15 +47,17 @@ void sig_handler(int signo) { printf("Received %d.\n", signo); if (signo == SIGINT) { - printf("Deleting the memory\n"); - if (shmdt((const void *)shmaddr) != 0) { - perror("Detach failure"); + if (shmaddr) { + printf("Deleting the memory\n"); + if (shmdt((const void *)shmaddr) != 0) { + perror("Detach failure"); + shmctl(shmid, IPC_RMID, NULL); + exit(4); + } + shmctl(shmid, IPC_RMID, NULL); - exit(4); + printf("Done deleting the memory\n"); } - - shmctl(shmid, IPC_RMID, NULL); - printf("Done deleting the memory\n"); } exit(2); } @@ -87,7 +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) { @@ -211,7 +213,8 @@ int main(int argc, char **argv) shmctl(shmid, IPC_RMID, NULL); exit(2); } - printf("shmaddr: %p\n", ptr); + shmaddr = ptr; + printf("shmaddr: %p\n", shmaddr); break; default: |