diff options
Diffstat (limited to '')
35 files changed, 3508 insertions, 1259 deletions
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 2e7e86e85282..7b9dc2426f18 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -2,12 +2,16 @@ hugepage-mmap hugepage-mremap hugepage-shm +hugepage-vmemmap +hugetlb-madvise khugepaged map_hugetlb map_populate thuge-gen compaction_test +migration mlock2-tests +mrelease_test mremap_dontunmap mremap_test on-fault-limit @@ -26,6 +30,6 @@ map_fixed_noreplace write_to_hugetlbfs hmm-tests memfd_secret -local_config.* +soft-dirty split_huge_page_test ksm_tests diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 1607322a112c..163c2fde3cb3 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for vm selftests -include local_config.mk +LOCAL_HDRS += $(top_srcdir)/mm/gup_test.h uname_M := $(shell uname -m 2>/dev/null || echo not) MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') @@ -23,39 +23,44 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) +CFLAGS = -Wall -I $(top_srcdir) -I $(top_srcdir)/usr/include $(EXTRA_CFLAGS) $(KHDR_INCLUDES) LDLIBS = -lrt -lpthread TEST_GEN_FILES = compaction_test TEST_GEN_FILES += gup_test TEST_GEN_FILES += hmm-tests +TEST_GEN_FILES += hugetlb-madvise TEST_GEN_FILES += hugepage-mmap TEST_GEN_FILES += hugepage-mremap TEST_GEN_FILES += hugepage-shm +TEST_GEN_FILES += hugepage-vmemmap TEST_GEN_FILES += khugepaged -TEST_GEN_FILES += madv_populate +TEST_GEN_PROGS = madv_populate TEST_GEN_FILES += map_fixed_noreplace TEST_GEN_FILES += map_hugetlb TEST_GEN_FILES += map_populate TEST_GEN_FILES += memfd_secret +TEST_GEN_FILES += migration TEST_GEN_FILES += mlock-random-test TEST_GEN_FILES += mlock2-tests +TEST_GEN_FILES += mrelease_test TEST_GEN_FILES += mremap_dontunmap TEST_GEN_FILES += mremap_test TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd -TEST_GEN_FILES += split_huge_page_test +TEST_GEN_PROGS += soft-dirty +TEST_GEN_PROGS += split_huge_page_test TEST_GEN_FILES += ksm_tests ifeq ($(MACHINE),x86_64) -CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32) -CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_64bit_program.c) -CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_program.c -no-pie) +CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) +CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c) +CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) -TARGETS := protection_keys -BINARIES_32 := $(TARGETS:%=%_32) -BINARIES_64 := $(TARGETS:%=%_64) +VMTARGETS := protection_keys +BINARIES_32 := $(VMTARGETS:%=%_32) +BINARIES_64 := $(VMTARGETS:%=%_64) ifeq ($(CAN_BUILD_WITH_NOPIE),1) CFLAGS += -no-pie @@ -85,10 +90,17 @@ endif TEST_PROGS := run_vmtests.sh TEST_FILES := test_vmalloc.sh +TEST_FILES += test_hmm.sh +TEST_FILES += va_128TBswitch.sh -KSFT_KHDR_INSTALL := 1 include ../lib.mk +$(OUTPUT)/khugepaged: vm_util.c +$(OUTPUT)/madv_populate: vm_util.c +$(OUTPUT)/soft-dirty: vm_util.c +$(OUTPUT)/split_huge_page_test: vm_util.c +$(OUTPUT)/userfaultfd: vm_util.c + ifeq ($(MACHINE),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) @@ -108,7 +120,7 @@ $(BINARIES_32): CFLAGS += -m32 -mxsave $(BINARIES_32): LDLIBS += -lrt -ldl -lm $(BINARIES_32): $(OUTPUT)/%_32: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ -$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t)))) +$(foreach t,$(VMTARGETS),$(eval $(call gen-target-rule-32,$(t)))) endif ifeq ($(CAN_BUILD_X86_64),1) @@ -116,7 +128,7 @@ $(BINARIES_64): CFLAGS += -m64 -mxsave $(BINARIES_64): LDLIBS += -lrt -ldl $(BINARIES_64): $(OUTPUT)/%_64: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ -$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t)))) +$(foreach t,$(VMTARGETS),$(eval $(call gen-target-rule-64,$(t)))) endif # x86_64 users should be encouraged to install 32-bit libraries @@ -140,25 +152,6 @@ endif $(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap -$(OUTPUT)/gup_test: ../../../../mm/gup_test.h - -$(OUTPUT)/hmm-tests: local_config.h - -# HMM_EXTRA_LIBS may get set in local_config.mk, or it may be left empty. -$(OUTPUT)/hmm-tests: LDLIBS += $(HMM_EXTRA_LIBS) - $(OUTPUT)/ksm_tests: LDLIBS += -lnuma -local_config.mk local_config.h: check_config.sh - /bin/sh ./check_config.sh $(CC) - -EXTRA_CLEAN += local_config.mk local_config.h - -ifeq ($(HMM_EXTRA_LIBS),) -all: warn_missing_hugelibs - -warn_missing_hugelibs: - @echo ; \ - echo "Warning: missing libhugetlbfs support. Some HMM tests will be skipped." ; \ - echo -endif +$(OUTPUT)/migration: LDLIBS += -lnuma diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh index fe8fcfb334e0..a5cb4b09a46c 100644 --- a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh @@ -24,19 +24,23 @@ if [[ "$1" == "-cgroup-v2" ]]; then reservation_usage_file=rsvd.current fi -cgroup_path=/dev/cgroup/memory -if [[ ! -e $cgroup_path ]]; then - mkdir -p $cgroup_path - if [[ $cgroup2 ]]; then +if [[ $cgroup2 ]]; then + cgroup_path=$(mount -t cgroup2 | head -1 | awk -e '{print $3}') + if [[ -z "$cgroup_path" ]]; then + cgroup_path=/dev/cgroup/memory mount -t cgroup2 none $cgroup_path - else + do_umount=1 + fi + echo "+hugetlb" >$cgroup_path/cgroup.subtree_control +else + cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}') + if [[ -z "$cgroup_path" ]]; then + cgroup_path=/dev/cgroup/memory mount -t cgroup memory,hugetlb $cgroup_path + do_umount=1 fi fi - -if [[ $cgroup2 ]]; then - echo "+hugetlb" >/dev/cgroup/memory/cgroup.subtree_control -fi +export cgroup_path function cleanup() { if [[ $cgroup2 ]]; then @@ -108,7 +112,7 @@ function setup_cgroup() { function wait_for_hugetlb_memory_to_get_depleted() { local cgroup="$1" - local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file" + local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file" # Wait for hugetlbfs memory to get depleted. while [ $(cat $path) != 0 ]; do echo Waiting for hugetlb memory to get depleted. @@ -121,7 +125,7 @@ function wait_for_hugetlb_memory_to_get_reserved() { local cgroup="$1" local size="$2" - local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file" + local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file" # Wait for hugetlbfs memory to get written. while [ $(cat $path) != $size ]; do echo Waiting for hugetlb memory reservation to reach size $size. @@ -134,7 +138,7 @@ function wait_for_hugetlb_memory_to_get_written() { local cgroup="$1" local size="$2" - local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$fault_usage_file" + local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$fault_usage_file" # Wait for hugetlbfs memory to get written. while [ $(cat $path) != $size ]; do echo Waiting for hugetlb memory to reach size $size. @@ -574,5 +578,7 @@ for populate in "" "-o"; do done # populate done # method -umount $cgroup_path -rmdir $cgroup_path +if [[ $do_umount ]]; then + umount $cgroup_path + rmdir $cgroup_path +fi diff --git a/tools/testing/selftests/vm/check_config.sh b/tools/testing/selftests/vm/check_config.sh deleted file mode 100644 index 079c8a40b85d..000000000000 --- a/tools/testing/selftests/vm/check_config.sh +++ /dev/null @@ -1,31 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Probe for libraries and create header files to record the results. Both C -# header files and Makefile include fragments are created. - -OUTPUT_H_FILE=local_config.h -OUTPUT_MKFILE=local_config.mk - -# libhugetlbfs -tmpname=$(mktemp) -tmpfile_c=${tmpname}.c -tmpfile_o=${tmpname}.o - -echo "#include <sys/types.h>" > $tmpfile_c -echo "#include <hugetlbfs.h>" >> $tmpfile_c -echo "int func(void) { return 0; }" >> $tmpfile_c - -CC=${1:?"Usage: $0 <compiler> # example compiler: gcc"} -$CC -c $tmpfile_c -o $tmpfile_o >/dev/null 2>&1 - -if [ -f $tmpfile_o ]; then - echo "#define LOCAL_CONFIG_HAVE_LIBHUGETLBFS 1" > $OUTPUT_H_FILE - echo "HMM_EXTRA_LIBS = -lhugetlbfs" > $OUTPUT_MKFILE -else - echo "// No libhugetlbfs support found" > $OUTPUT_H_FILE - echo "# No libhugetlbfs support found, so:" > $OUTPUT_MKFILE - echo "HMM_EXTRA_LIBS = " >> $OUTPUT_MKFILE -fi - -rm ${tmpname}.* diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/vm/config index 60e82da0de85..be087c4bc396 100644 --- a/tools/testing/selftests/vm/config +++ b/tools/testing/selftests/vm/config @@ -4,3 +4,5 @@ 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 diff --git a/tools/testing/selftests/vm/gup_test.c b/tools/testing/selftests/vm/gup_test.c index fe043f67798b..e43879291dac 100644 --- a/tools/testing/selftests/vm/gup_test.c +++ b/tools/testing/selftests/vm/gup_test.c @@ -1,22 +1,28 @@ #include <fcntl.h> +#include <errno.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> +#include <dirent.h> #include <sys/ioctl.h> #include <sys/mman.h> #include <sys/stat.h> #include <sys/types.h> #include <pthread.h> #include <assert.h> -#include "../../../../mm/gup_test.h" +#include <mm/gup_test.h> +#include "../kselftest.h" + +#include "util.h" #define MB (1UL << 20) -#define PAGE_SIZE sysconf(_SC_PAGESIZE) /* Just the flags we need, copied from mm.h: */ #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ +#define GUP_TEST_FILE "/sys/kernel/debug/gup_test" + static unsigned long cmd = GUP_FAST_BENCHMARK; static int gup_fd, repeats = 1; static unsigned long size = 128 * MB; @@ -203,10 +209,25 @@ int main(int argc, char **argv) if (write) gup.gup_flags |= FOLL_WRITE; - gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); + gup_fd = open(GUP_TEST_FILE, O_RDWR); if (gup_fd == -1) { - perror("open"); - exit(1); + switch (errno) { + case EACCES: + if (getuid()) + printf("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"); + break; + default: + perror("failed to open " GUP_TEST_FILE); + break; + } + exit(KSFT_SKIP); } p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0); diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 864f126ffd78..4adaad1b822f 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -26,16 +26,13 @@ #include <sys/mman.h> #include <sys/ioctl.h> -#include "./local_config.h" -#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS -#include <hugetlbfs.h> -#endif /* * This is a private UAPI to the kernel test module so it isn't exported * in the usual include/uapi/... directory. */ -#include "../../../../lib/test_hmm_uapi.h" +#include <lib/test_hmm_uapi.h> +#include <mm/gup_test.h> struct hmm_buffer { void *ptr; @@ -46,12 +43,22 @@ struct hmm_buffer { uint64_t faults; }; +enum { + HMM_PRIVATE_DEVICE_ONE, + HMM_PRIVATE_DEVICE_TWO, + HMM_COHERENCE_DEVICE_ONE, + HMM_COHERENCE_DEVICE_TWO, +}; + #define TWOMEG (1 << 21) #define HMM_BUFFER_SIZE (1024 << 12) #define HMM_PATH_MAX 64 #define NTIMES 10 #define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1))) +/* Just the flags we need, copied from mm.h: */ +#define FOLL_WRITE 0x01 /* check pte is writable */ +#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite */ FIXTURE(hmm) { @@ -60,6 +67,21 @@ FIXTURE(hmm) unsigned int page_shift; }; +FIXTURE_VARIANT(hmm) +{ + int device_number; +}; + +FIXTURE_VARIANT_ADD(hmm, hmm_device_private) +{ + .device_number = HMM_PRIVATE_DEVICE_ONE, +}; + +FIXTURE_VARIANT_ADD(hmm, hmm_device_coherent) +{ + .device_number = HMM_COHERENCE_DEVICE_ONE, +}; + FIXTURE(hmm2) { int fd0; @@ -68,6 +90,24 @@ FIXTURE(hmm2) unsigned int page_shift; }; +FIXTURE_VARIANT(hmm2) +{ + int device_number0; + int device_number1; +}; + +FIXTURE_VARIANT_ADD(hmm2, hmm2_device_private) +{ + .device_number0 = HMM_PRIVATE_DEVICE_ONE, + .device_number1 = HMM_PRIVATE_DEVICE_TWO, +}; + +FIXTURE_VARIANT_ADD(hmm2, hmm2_device_coherent) +{ + .device_number0 = HMM_COHERENCE_DEVICE_ONE, + .device_number1 = HMM_COHERENCE_DEVICE_TWO, +}; + static int hmm_open(int unit) { char pathname[HMM_PATH_MAX]; @@ -81,12 +121,19 @@ static int hmm_open(int unit) return fd; } +static bool hmm_is_coherent_type(int dev_num) +{ + return (dev_num >= HMM_COHERENCE_DEVICE_ONE); +} + FIXTURE_SETUP(hmm) { self->page_size = sysconf(_SC_PAGE_SIZE); self->page_shift = ffs(self->page_size) - 1; - self->fd = hmm_open(0); + 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"); ASSERT_GE(self->fd, 0); } @@ -95,9 +142,11 @@ FIXTURE_SETUP(hmm2) self->page_size = sysconf(_SC_PAGE_SIZE); self->page_shift = ffs(self->page_size) - 1; - self->fd0 = hmm_open(0); + 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"); ASSERT_GE(self->fd0, 0); - self->fd1 = hmm_open(1); + self->fd1 = hmm_open(variant->device_number1); ASSERT_GE(self->fd1, 0); } @@ -211,6 +260,20 @@ static void hmm_nanosleep(unsigned int n) nanosleep(&t, NULL); } +static int hmm_migrate_sys_to_dev(int fd, + struct hmm_buffer *buffer, + unsigned long npages) +{ + return hmm_dmirror_cmd(fd, HMM_DMIRROR_MIGRATE_TO_DEV, buffer, npages); +} + +static int hmm_migrate_dev_to_sys(int fd, + struct hmm_buffer *buffer, + unsigned long npages) +{ + return hmm_dmirror_cmd(fd, HMM_DMIRROR_MIGRATE_TO_SYS, buffer, npages); +} + /* * Simple NULL test of device open/close. */ @@ -666,7 +729,54 @@ TEST_F(hmm, anon_write_huge) hmm_buffer_free(buffer); } -#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS +/* + * Read numeric data from raw and tagged kernel status files. Used to read + * /proc and /sys data (without a tag) and from /proc/meminfo (with a tag). + */ +static long file_read_ulong(char *file, const char *tag) +{ + int fd; + char buf[2048]; + int len; + char *p, *q; + long val; + + fd = open(file, O_RDONLY); + if (fd < 0) { + /* Error opening the file */ + return -1; + } + + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len < 0) { + /* Error in reading the file */ + return -1; + } + if (len == sizeof(buf)) { + /* Error file is too large */ + return -1; + } + buf[len] = '\0'; + + /* Search for a tag if provided */ + if (tag) { + p = strstr(buf, tag); + if (!p) + return -1; /* looks like the line we want isn't there */ + p += strlen(tag); + } else + p = buf; + + val = strtol(p, &q, 0); + if (*q != ' ') { + /* Error parsing the file */ + return -1; + } + + return val; +} + /* * Write huge TLBFS page. */ @@ -675,29 +785,27 @@ TEST_F(hmm, anon_write_hugetlbfs) struct hmm_buffer *buffer; unsigned long npages; unsigned long size; + unsigned long default_hsize; unsigned long i; int *ptr; int ret; - long pagesizes[4]; - int n, idx; - - /* Skip test if we can't allocate a hugetlbfs page. */ - n = gethugepagesizes(pagesizes, 4); - if (n <= 0) + default_hsize = file_read_ulong("/proc/meminfo", "Hugepagesize:"); + if (default_hsize < 0 || default_hsize*1024 < default_hsize) SKIP(return, "Huge page size could not be determined"); - for (idx = 0; --n > 0; ) { - if (pagesizes[n] < pagesizes[idx]) - idx = n; - } - size = ALIGN(TWOMEG, pagesizes[idx]); + default_hsize = default_hsize*1024; /* KB to B */ + + size = ALIGN(TWOMEG, default_hsize); npages = size >> self->page_shift; buffer = malloc(sizeof(*buffer)); ASSERT_NE(buffer, NULL); - buffer->ptr = get_hugepage_region(size, GHR_STRICT); - if (buffer->ptr == NULL) { + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + if (buffer->ptr == MAP_FAILED) { free(buffer); SKIP(return, "Huge page could not be allocated"); } @@ -721,11 +829,10 @@ TEST_F(hmm, anon_write_hugetlbfs) for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); - free_hugepage_region(buffer->ptr); + munmap(buffer->ptr, buffer->size); buffer->ptr = NULL; hmm_buffer_free(buffer); } -#endif /* LOCAL_CONFIG_HAVE_LIBHUGETLBFS */ /* * Read mmap'ed file memory. @@ -875,7 +982,7 @@ TEST_F(hmm, migrate) ptr[i] = i; /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, npages); @@ -923,7 +1030,7 @@ TEST_F(hmm, migrate_fault) ptr[i] = i; /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, npages); @@ -936,7 +1043,48 @@ TEST_F(hmm, migrate_fault) ASSERT_EQ(ptr[i], i); /* Migrate memory to the device again. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + 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); + + hmm_buffer_free(buffer); +} + +TEST_F(hmm, migrate_release) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + 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 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); @@ -944,6 +1092,14 @@ TEST_F(hmm, migrate_fault) for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); + /* Release device memory. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_RELEASE, buffer, npages); + ASSERT_EQ(ret, 0); + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / (2 * sizeof(*ptr)); ++i) + ASSERT_EQ(ptr[i], i); + hmm_buffer_free(buffer); } @@ -976,7 +1132,7 @@ TEST_F(hmm, migrate_shared) ASSERT_NE(buffer->ptr, MAP_FAILED); /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, -ENOENT); hmm_buffer_free(buffer); @@ -1015,7 +1171,7 @@ TEST_F(hmm2, migrate_mixed) p = buffer->ptr; /* Migrating a protected area should be an error. */ - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, npages); ASSERT_EQ(ret, -EINVAL); /* Punch a hole after the first page address. */ @@ -1023,7 +1179,7 @@ TEST_F(hmm2, migrate_mixed) ASSERT_EQ(ret, 0); /* We expect an error if the vma doesn't cover the range. */ - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 3); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 3); ASSERT_EQ(ret, -EINVAL); /* Page 2 will be a read-only zero page. */ @@ -1055,13 +1211,13 @@ TEST_F(hmm2, migrate_mixed) /* Now try to migrate pages 2-5 to device 1. */ buffer->ptr = p + 2 * self->page_size; - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 4); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 4); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, 4); /* Page 5 won't be migrated to device 0 because it's on device 1. */ buffer->ptr = p + 5 * self->page_size; - ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1); + ret = hmm_migrate_sys_to_dev(self->fd0, buffer, 1); ASSERT_EQ(ret, -ENOENT); buffer->ptr = p; @@ -1070,8 +1226,12 @@ TEST_F(hmm2, migrate_mixed) } /* - * Migrate anonymous memory to device private memory and fault it back to system - * memory multiple times. + * Migrate anonymous memory to device memory and back to system memory + * multiple times. In case of private zone configuration, this is done + * through fault pages accessed by CPU. In case of coherent zone configuration, + * the pages from the device should be explicitly migrated back to system memory. + * The reason is Coherent device zone has coherent access by CPU, therefore + * it will not generate any page fault. */ TEST_F(hmm, migrate_multiple) { @@ -1107,8 +1267,7 @@ TEST_F(hmm, migrate_multiple) ptr[i] = i; /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, - npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, npages); @@ -1116,7 +1275,13 @@ TEST_F(hmm, migrate_multiple) 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. */ + /* Migrate back to system memory and check them. */ + if (hmm_is_coherent_type(variant->device_number)) { + ret = hmm_migrate_dev_to_sys(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + } + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); @@ -1251,6 +1416,48 @@ TEST_F(hmm, anon_teardown) /* * Test memory snapshot without faulting in pages accessed by the device. */ +TEST_F(hmm, mixedmap) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned char *m; + int ret; + + npages = 1; + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(npages); + ASSERT_NE(buffer->mirror, NULL); + + + /* Reserve a range of addresses. */ + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, + self->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Simulate a device snapshotting CPU pagetables. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device saw. */ + m = buffer->mirror; + ASSERT_EQ(m[0], HMM_DMIRROR_PROT_READ); + + hmm_buffer_free(buffer); +} + +/* + * Test memory snapshot without faulting in pages accessed by the device. + */ TEST_F(hmm2, snapshot) { struct hmm_buffer *buffer; @@ -1312,13 +1519,13 @@ TEST_F(hmm2, snapshot) /* Page 5 will be migrated to device 0. */ buffer->ptr = p + 5 * self->page_size; - ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1); + ret = hmm_migrate_sys_to_dev(self->fd0, buffer, 1); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, 1); /* Page 6 will be migrated to device 1. */ buffer->ptr = p + 6 * self->page_size; - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 1); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 1); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, 1); @@ -1335,14 +1542,20 @@ TEST_F(hmm2, snapshot) ASSERT_EQ(m[2], HMM_DMIRROR_PROT_ZERO | HMM_DMIRROR_PROT_READ); ASSERT_EQ(m[3], HMM_DMIRROR_PROT_READ); ASSERT_EQ(m[4], HMM_DMIRROR_PROT_WRITE); - ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL | - HMM_DMIRROR_PROT_WRITE); - ASSERT_EQ(m[6], HMM_DMIRROR_PROT_NONE); + if (!hmm_is_coherent_type(variant->device_number0)) { + ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL | + HMM_DMIRROR_PROT_WRITE); + ASSERT_EQ(m[6], HMM_DMIRROR_PROT_NONE); + } else { + ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL | + HMM_DMIRROR_PROT_WRITE); + ASSERT_EQ(m[6], HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE | + HMM_DMIRROR_PROT_WRITE); + } hmm_buffer_free(buffer); } -#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS /* * Test the hmm_range_fault() HMM_PFN_PMD flag for large pages that * should be mapped by a large page table entry. @@ -1352,30 +1565,30 @@ TEST_F(hmm, compound) struct hmm_buffer *buffer; unsigned long npages; unsigned long size; + unsigned long default_hsize; int *ptr; unsigned char *m; int ret; - long pagesizes[4]; - int n, idx; unsigned long i; /* Skip test if we can't allocate a hugetlbfs page. */ - n = gethugepagesizes(pagesizes, 4); - if (n <= 0) - return; - for (idx = 0; --n > 0; ) { - if (pagesizes[n] < pagesizes[idx]) - idx = n; - } - size = ALIGN(TWOMEG, pagesizes[idx]); + default_hsize = file_read_ulong("/proc/meminfo", "Hugepagesize:"); + if (default_hsize < 0 || default_hsize*1024 < default_hsize) + SKIP(return, "Huge page size could not be determined"); + default_hsize = default_hsize*1024; /* KB to B */ + + size = ALIGN(TWOMEG, default_hsize); npages = size >> self->page_shift; buffer = malloc(sizeof(*buffer)); ASSERT_NE(buffer, NULL); - buffer->ptr = get_hugepage_region(size, GHR_STRICT); - if (buffer->ptr == NULL) { + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + if (buffer->ptr == MAP_FAILED) { free(buffer); return; } @@ -1414,11 +1627,10 @@ TEST_F(hmm, compound) ASSERT_EQ(m[i], HMM_DMIRROR_PROT_READ | HMM_DMIRROR_PROT_PMD); - free_hugepage_region(buffer->ptr); + munmap(buffer->ptr, buffer->size); buffer->ptr = NULL; hmm_buffer_free(buffer); } -#endif /* LOCAL_CONFIG_HAVE_LIBHUGETLBFS */ /* * Test two devices reading the same memory (double mapped). @@ -1478,9 +1690,19 @@ TEST_F(hmm2, double_map) for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); - /* Punch a hole after the first page address. */ - ret = munmap(buffer->ptr + self->page_size, self->page_size); + /* Migrate pages to device 1 and try to read from device 0. */ + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_READ, buffer, npages); ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + ASSERT_EQ(buffer->faults, 1); + + /* Check what device 0 read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); hmm_buffer_free(buffer); } @@ -1643,4 +1865,190 @@ TEST_F(hmm, exclusive_cow) hmm_buffer_free(buffer); } +static int gup_test_exec(int gup_fd, unsigned long addr, int cmd, + int npages, int size, int flags) +{ + struct gup_test gup = { + .nr_pages_per_call = npages, + .addr = addr, + .gup_flags = FOLL_WRITE | flags, + .size = size, + }; + + if (ioctl(gup_fd, cmd, &gup)) { + perror("ioctl on error\n"); + return errno; + } + + return 0; +} + +/* + * Test get user device pages through gup_test. Setting PIN_LONGTERM flag. + * This should trigger a migration back to system memory for both, private + * and coherent type pages. + * This test makes use of gup_test module. Make sure GUP_TEST_CONFIG is added + * to your configuration before you run it. + */ +TEST_F(hmm, hmm_gup_test) +{ + struct hmm_buffer *buffer; + int gup_fd; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + unsigned char *m; + + gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); + if (gup_fd == -1) + SKIP(return, "Skipping test, could not find gup_test driver"); + + npages = 4; + 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 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); + + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr, + GUP_BASIC_TEST, 1, self->page_size, 0), 0); + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr + 1 * self->page_size, + GUP_FAST_BENCHMARK, 1, self->page_size, 0), 0); + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr + 2 * self->page_size, + PIN_FAST_BENCHMARK, 1, self->page_size, FOLL_LONGTERM), 0); + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr + 3 * self->page_size, + PIN_LONGTERM_BENCHMARK, 1, self->page_size, 0), 0); + + /* Take snapshot to CPU pagetables */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + m = buffer->mirror; + if (hmm_is_coherent_type(variant->device_number)) { + ASSERT_EQ(HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL | HMM_DMIRROR_PROT_WRITE, m[0]); + ASSERT_EQ(HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL | HMM_DMIRROR_PROT_WRITE, m[1]); + } else { + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[0]); + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[1]); + } + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[2]); + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[3]); + /* + * Check again the content on the pages. Make sure there's no + * corrupted data. + */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + close(gup_fd); + hmm_buffer_free(buffer); +} + +/* + * Test copy-on-write in device pages. + * In case of writing to COW private page(s), a page fault will migrate pages + * back to system memory first. Then, these pages will be duplicated. In case + * of COW device coherent type, pages are duplicated directly from device + * memory. + */ +TEST_F(hmm, hmm_cow_in_device) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + unsigned char *m; + pid_t pid; + int status; + + npages = 4; + 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 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); + + pid = fork(); + if (pid == -1) + ASSERT_EQ(pid, 0); + if (!pid) { + /* Child process waitd for SIGTERM from the parent. */ + while (1) { + } + perror("Should not reach this\n"); + exit(0); + } + /* Parent process writes to COW pages(s) and gets a + * new copy in system. In case of device private pages, + * this write causes a migration to system mem first. + */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Terminate child and wait */ + EXPECT_EQ(0, kill(pid, SIGTERM)); + EXPECT_EQ(pid, waitpid(pid, &status, 0)); + EXPECT_NE(0, WIFSIGNALED(status)); + EXPECT_EQ(SIGTERM, WTERMSIG(status)); + + /* Take snapshot to CPU pagetables */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + m = buffer->mirror; + for (i = 0; i < npages; i++) + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[i]); + + hmm_buffer_free(buffer); +} TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c index 257df94697a5..e63a0214f639 100644 --- a/tools/testing/selftests/vm/hugepage-mremap.c +++ b/tools/testing/selftests/vm/hugepage-mremap.c @@ -3,8 +3,13 @@ * hugepage-mremap: * * Example of remapping huge page memory in a user application using the - * mremap system call. Code assumes a hugetlbfs filesystem is mounted - * at './huge'. The code will use 10MB worth of huge pages. + * mremap system call. The path to a file in a hugetlbfs filesystem must + * be passed as the last argument to this test. The amount of memory used + * by this test in MBs can optionally be passed as an argument. If no memory + * amount is passed, the default amount is 10MB. + * + * To make sure the test triggers pmd sharing and goes through the 'unshare' + * path in the mremap code use 1GB (1024) or more. */ #define _GNU_SOURCE @@ -18,7 +23,8 @@ #include <linux/userfaultfd.h> #include <sys/ioctl.h> -#define LENGTH (1UL * 1024 * 1024 * 1024) +#define DEFAULT_LENGTH_MB 10UL +#define MB_TO_BYTES(x) (x * 1024 * 1024) #define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC) #define FLAGS (MAP_SHARED | MAP_ANONYMOUS) @@ -28,20 +34,20 @@ static void check_bytes(char *addr) printf("First hex is %x\n", *((unsigned int *)addr)); } -static void write_bytes(char *addr) +static void write_bytes(char *addr, size_t len) { unsigned long i; - for (i = 0; i < LENGTH; i++) + for (i = 0; i < len; i++) *(addr + i) = (char)i; } -static int read_bytes(char *addr) +static int read_bytes(char *addr, size_t len) { unsigned long i; check_bytes(addr); - for (i = 0; i < LENGTH; i++) + for (i = 0; i < len; i++) if (*(addr + i) != (char)i) { printf("Mismatch at %lu\n", i); return 1; @@ -99,11 +105,28 @@ static void register_region_with_uffd(char *addr, size_t len) } } -int main(void) +int main(int argc, char *argv[]) { + size_t length = 0; + + if (argc != 2 && argc != 3) { + printf("Usage: %s [length_in_MB] <hugetlb_file>\n", argv[0]); + exit(1); + } + + /* Read memory length as the first arg if valid, otherwise fallback to + * the default length. + */ + if (argc == 3) + length = argc > 2 ? (size_t)atoi(argv[1]) : 0UL; + + length = length > 0 ? length : DEFAULT_LENGTH_MB; + length = MB_TO_BYTES(length); + int ret = 0; - int fd = open("/huge/test", O_CREAT | O_RDWR, 0755); + /* last arg is the hugetlb file name */ + int fd = open(argv[argc-1], O_CREAT | O_RDWR, 0755); if (fd < 0) { perror("Open failed"); @@ -112,7 +135,7 @@ int main(void) /* mmap to a PUD aligned address to hopefully trigger pmd sharing. */ unsigned long suggested_addr = 0x7eaa40000000; - void *haddr = mmap((void *)suggested_addr, LENGTH, PROTECTION, + 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) { @@ -122,7 +145,7 @@ int main(void) /* mmap again to a dummy address to hopefully trigger pmd sharing. */ suggested_addr = 0x7daa40000000; - void *daddr = mmap((void *)suggested_addr, LENGTH, PROTECTION, + 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) { @@ -132,16 +155,16 @@ int main(void) suggested_addr = 0x7faa40000000; void *vaddr = - mmap((void *)suggested_addr, LENGTH, PROTECTION, FLAGS, -1, 0); + 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); } - register_region_with_uffd(haddr, LENGTH); + register_region_with_uffd(haddr, length); - void *addr = mremap(haddr, LENGTH, LENGTH, + void *addr = mremap(haddr, length, length, MREMAP_MAYMOVE | MREMAP_FIXED, vaddr); if (addr == MAP_FAILED) { perror("mremap"); @@ -150,10 +173,19 @@ int main(void) printf("Mremap: Returned address is %p\n", addr); check_bytes(addr); - write_bytes(addr); - ret = read_bytes(addr); + write_bytes(addr, length); + ret = read_bytes(addr, length); + + munmap(addr, length); + + addr = mremap(addr, length, length, 0); + if (addr != MAP_FAILED) { + printf("mremap: Expected failure, but call succeeded\n"); + exit(1); + } - munmap(addr, LENGTH); + close(fd); + unlink(argv[argc-1]); return ret; } diff --git a/tools/testing/selftests/vm/hugepage-vmemmap.c b/tools/testing/selftests/vm/hugepage-vmemmap.c new file mode 100644 index 000000000000..557bdbd4f87e --- /dev/null +++ b/tools/testing/selftests/vm/hugepage-vmemmap.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A test case of using hugepage memory in a user application using the + * mmap system call with MAP_HUGETLB flag. Before running this program + * make sure the administrator has allocated enough default sized huge + * pages to cover the 2 MB allocation. + */ +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/mman.h> +#include <fcntl.h> + +#define MAP_LENGTH (2UL * 1024 * 1024) + +#ifndef MAP_HUGETLB +#define MAP_HUGETLB 0x40000 /* arch specific */ +#endif + +#define PAGE_SIZE 4096 + +#define PAGE_COMPOUND_HEAD (1UL << 15) +#define PAGE_COMPOUND_TAIL (1UL << 16) +#define PAGE_HUGE (1UL << 17) + +#define HEAD_PAGE_FLAGS (PAGE_COMPOUND_HEAD | PAGE_HUGE) +#define TAIL_PAGE_FLAGS (PAGE_COMPOUND_TAIL | PAGE_HUGE) + +#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 void write_bytes(char *addr, size_t length) +{ + unsigned long i; + + for (i = 0; i < length; i++) + *(addr + i) = (char)i; +} + +static unsigned long virt_to_pfn(void *addr) +{ + int fd; + unsigned long pagemap; + + fd = open("/proc/self/pagemap", O_RDONLY); + if (fd < 0) + return -1UL; + + lseek(fd, (unsigned long)addr / PAGE_SIZE * sizeof(pagemap), SEEK_SET); + read(fd, &pagemap, sizeof(pagemap)); + close(fd); + + return pagemap & ~PM_PFRAME_MASK; +} + +static int check_page_flags(unsigned long pfn) +{ + int fd, i; + unsigned long pageflags; + + fd = open("/proc/kpageflags", O_RDONLY); + if (fd < 0) + return -1; + + lseek(fd, pfn * sizeof(pageflags), SEEK_SET); + + read(fd, &pageflags, sizeof(pageflags)); + if ((pageflags & HEAD_PAGE_FLAGS) != HEAD_PAGE_FLAGS) { + close(fd); + printf("Head page flags (%lx) is invalid\n", pageflags); + return -1; + } + + /* + * pages other than the first page must be tail and shouldn't be head; + * 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++) { + read(fd, &pageflags, sizeof(pageflags)); + if ((pageflags & TAIL_PAGE_FLAGS) != TAIL_PAGE_FLAGS || + (pageflags & HEAD_PAGE_FLAGS) == HEAD_PAGE_FLAGS) { + close(fd); + printf("Tail page flags (%lx) is invalid\n", pageflags); + return -1; + } + } + + close(fd); + + return 0; +} + +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); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + /* Trigger allocation of HugeTLB page. */ + write_bytes(addr, MAP_LENGTH); + + pfn = virt_to_pfn(addr); + if (pfn == -1UL) { + munmap(addr, MAP_LENGTH); + perror("virt_to_pfn"); + exit(1); + } + + printf("Returned address is %p whose pfn is %lx\n", addr, pfn); + + if (check_page_flags(pfn) < 0) { + munmap(addr, MAP_LENGTH); + perror("check_page_flags"); + exit(1); + } + + /* munmap() length of MAP_HUGETLB memory must be hugepage aligned */ + if (munmap(addr, MAP_LENGTH)) { + perror("munmap"); + exit(1); + } + + return 0; +} diff --git a/tools/testing/selftests/vm/hugetlb-madvise.c b/tools/testing/selftests/vm/hugetlb-madvise.c new file mode 100644 index 000000000000..3c9943131881 --- /dev/null +++ b/tools/testing/selftests/vm/hugetlb-madvise.c @@ -0,0 +1,411 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * hugepage-madvise: + * + * Basic functional testing of madvise MADV_DONTNEED and MADV_REMOVE + * on hugetlb mappings. + * + * Before running this test, make sure the administrator has pre-allocated + * at least MIN_FREE_PAGES hugetlb pages and they are free. In addition, + * the test takes an argument that is the path to a file in a hugetlbfs + * filesystem. Therefore, a hugetlbfs filesystem must be mounted on some + * directory. + */ + +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/mman.h> +#define __USE_GNU +#include <fcntl.h> + +#define USAGE "USAGE: %s <hugepagefile_name>\n" +#define MIN_FREE_PAGES 20 +#define NR_HUGE_PAGES 10 /* common number of pages to map/allocate */ + +#define validate_free_pages(exp_free) \ + do { \ + int fhp = get_free_hugepages(); \ + if (fhp != (exp_free)) { \ + printf("Unexpected number of free huge " \ + "pages line %d\n", __LINE__); \ + exit(1); \ + } \ + } while (0) + +unsigned long huge_page_size; +unsigned long base_page_size; + +/* + * default_huge_page_size copied from mlock2-tests.c + */ +unsigned long default_huge_page_size(void) +{ + unsigned long hps = 0; + char *line = NULL; + size_t linelen = 0; + FILE *f = fopen("/proc/meminfo", "r"); + + if (!f) + return 0; + while (getline(&line, &linelen, f) > 0) { + if (sscanf(line, "Hugepagesize: %lu kB", &hps) == 1) { + hps <<= 10; + break; + } + } + + free(line); + fclose(f); + return hps; +} + +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; + + for (i = 0; i < nr_pages; i++) + *((unsigned long *)(addr + (i * huge_page_size))) = i; +} + +void read_fault_pages(void *addr, unsigned long nr_pages) +{ + unsigned long dummy = 0; + unsigned long i; + + for (i = 0; i < nr_pages; i++) + dummy += *((unsigned long *)(addr + (i * huge_page_size))); +} + +int main(int argc, char **argv) +{ + unsigned long free_hugepages; + void *addr, *addr2; + int fd; + int ret; + + if (argc != 2) { + printf(USAGE, argv[0]); + exit(1); + } + + huge_page_size = default_huge_page_size(); + if (!huge_page_size) { + printf("Unable to determine huge page size, exiting!\n"); + exit(1); + } + base_page_size = sysconf(_SC_PAGE_SIZE); + if (!huge_page_size) { + printf("Unable to determine base page size, exiting!\n"); + exit(1); + } + + free_hugepages = get_free_hugepages(); + if (free_hugepages < MIN_FREE_PAGES) { + printf("Not enough free huge pages to test, exiting!\n"); + exit(1); + } + + fd = open(argv[1], O_CREAT | O_RDWR, 0755); + if (fd < 0) { + perror("Open failed"); + exit(1); + } + + /* + * Test validity of MADV_DONTNEED addr and length arguments. mmap + * size is NR_HUGE_PAGES + 2. One page at the beginning and end of + * the mapping will be unmapped so we KNOW there is nothing mapped + * there. + */ + addr = mmap(NULL, (NR_HUGE_PAGES + 2) * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + if (munmap(addr, huge_page_size) || + munmap(addr + (NR_HUGE_PAGES + 1) * huge_page_size, + huge_page_size)) { + perror("munmap"); + exit(1); + } + addr = addr + huge_page_size; + + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* addr before mapping should fail */ + ret = madvise(addr - base_page_size, NR_HUGE_PAGES * huge_page_size, + MADV_DONTNEED); + if (!ret) { + printf("Unexpected success of madvise call with invalid addr line %d\n", + __LINE__); + exit(1); + } + + /* addr + length after mapping should fail */ + ret = madvise(addr, (NR_HUGE_PAGES * huge_page_size) + base_page_size, + MADV_DONTNEED); + if (!ret) { + printf("Unexpected success of madvise call with invalid length line %d\n", + __LINE__); + exit(1); + } + + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + + /* + * Test alignment of MADV_DONTNEED addr and length arguments + */ + addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* addr is not huge page size aligned and should fail */ + ret = madvise(addr + base_page_size, + NR_HUGE_PAGES * huge_page_size - base_page_size, + MADV_DONTNEED); + if (!ret) { + printf("Unexpected success of madvise call with unaligned start address %d\n", + __LINE__); + exit(1); + } + + /* addr + length should be aligned up to huge page size */ + if (madvise(addr, + ((NR_HUGE_PAGES - 1) * huge_page_size) + base_page_size, + MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + + /* should free all pages in mapping */ + validate_free_pages(free_hugepages); + + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + + /* + * Test MADV_DONTNEED on anonymous private mapping + */ + addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + + /* should free all pages in mapping */ + validate_free_pages(free_hugepages); + + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + + /* + * Test MADV_DONTNEED on private mapping of hugetlb file + */ + if (fallocate(fd, 0, 0, NR_HUGE_PAGES * huge_page_size)) { + perror("fallocate"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, fd, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + /* read should not consume any pages */ + read_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* madvise should not free any pages */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* writes should allocate private pages */ + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES)); + + /* madvise should free private pages */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* writes should allocate private pages */ + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES)); + + /* + * The fallocate below certainly should free the pages associated + * with the file. However, pages in the private mapping are also + * freed. This is not the 'correct' behavior, but is expected + * because this is how it has worked since the initial hugetlb + * implementation. + */ + if (fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + 0, NR_HUGE_PAGES * huge_page_size)) { + perror("fallocate"); + exit(1); + } + validate_free_pages(free_hugepages); + + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + + /* + * Test MADV_DONTNEED on shared mapping of hugetlb file + */ + if (fallocate(fd, 0, 0, NR_HUGE_PAGES * huge_page_size)) { + perror("fallocate"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + /* write should not consume any pages */ + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* madvise should not free any pages */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* + * Test MADV_REMOVE on shared mapping of hugetlb file + * + * madvise is same as hole punch and should free all pages. + */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_REMOVE)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages); + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + + /* + * Test MADV_REMOVE on shared and private mapping of hugetlb file + */ + if (fallocate(fd, 0, 0, NR_HUGE_PAGES * huge_page_size)) { + perror("fallocate"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + /* shared write should not consume any additional pages */ + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + addr2 = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, fd, 0); + if (addr2 == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + /* private read should not consume any pages */ + read_fault_pages(addr2, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* private write should consume additional pages */ + write_fault_pages(addr2, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES)); + + /* madvise of shared mapping should not free any pages */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES)); + + /* madvise of private mapping should free private pages */ + if (madvise(addr2, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* private write should consume additional pages again */ + write_fault_pages(addr2, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES)); + + /* + * madvise should free both file and private pages although this is + * not correct. private pages should not be freed, but this is + * expected. See comment associated with FALLOC_FL_PUNCH_HOLE call. + */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_REMOVE)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages); + + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + (void)munmap(addr2, NR_HUGE_PAGES * huge_page_size); + + close(fd); + unlink(argv[1]); + return 0; +} diff --git a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh index 4a9a3afe9fd4..bf2d2a684edf 100644 --- a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh +++ b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh @@ -18,19 +18,24 @@ if [[ "$1" == "-cgroup-v2" ]]; then usage_file=current fi -CGROUP_ROOT='/dev/cgroup/memory' -MNT='/mnt/huge/' -if [[ ! -e $CGROUP_ROOT ]]; then - mkdir -p $CGROUP_ROOT - if [[ $cgroup2 ]]; then +if [[ $cgroup2 ]]; then + CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk -e '{print $3}') + if [[ -z "$CGROUP_ROOT" ]]; then + CGROUP_ROOT=/dev/cgroup/memory mount -t cgroup2 none $CGROUP_ROOT - sleep 1 - echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control - else + do_umount=1 + fi + echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control +else + CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}') + if [[ -z "$CGROUP_ROOT" ]]; then + CGROUP_ROOT=/dev/cgroup/memory mount -t cgroup memory,hugetlb $CGROUP_ROOT + do_umount=1 fi fi +MNT='/mnt/huge/' function get_machine_hugepage_size() { hpz=$(grep -i hugepagesize /proc/meminfo) diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index 155120b67a16..64126c8cd561 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -1,6 +1,9 @@ #define _GNU_SOURCE +#include <ctype.h> +#include <errno.h> #include <fcntl.h> #include <limits.h> +#include <dirent.h> #include <signal.h> #include <stdio.h> #include <stdlib.h> @@ -10,10 +13,24 @@ #include <sys/mman.h> #include <sys/wait.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/sysmacros.h> +#include <sys/vfs.h> + +#include "linux/magic.h" + +#include "vm_util.h" #ifndef MADV_PAGEOUT #define MADV_PAGEOUT 21 #endif +#ifndef MADV_POPULATE_READ +#define MADV_POPULATE_READ 22 +#endif +#ifndef MADV_COLLAPSE +#define MADV_COLLAPSE 25 +#endif #define BASE_ADDR ((void *)(1UL << 30)) static unsigned long hpage_pmd_size; @@ -22,6 +39,47 @@ static int hpage_pmd_nr; #define THP_SYSFS "/sys/kernel/mm/transparent_hugepage/" #define PID_SMAPS "/proc/self/smaps" +#define TEST_FILE "collapse_test_file" + +#define MAX_LINE_LENGTH 500 + +enum vma_type { + VMA_ANON, + VMA_FILE, + VMA_SHMEM, +}; + +struct mem_ops { + void *(*setup_area)(int nr_hpages); + void (*cleanup_area)(void *p, unsigned long size); + void (*fault)(void *p, unsigned long start, unsigned long end); + bool (*check_huge)(void *addr, int nr_hpages); + const char *name; +}; + +static struct mem_ops *file_ops; +static struct mem_ops *anon_ops; +static struct mem_ops *shmem_ops; + +struct collapse_context { + void (*collapse)(const char *msg, char *p, int nr_hpages, + struct mem_ops *ops, bool expect); + bool enforce_pte_scan_limits; + const char *name; +}; + +static struct collapse_context *khugepaged_context; +static struct collapse_context *madvise_context; + +struct file_info { + const char *dir; + char path[PATH_MAX]; + enum vma_type type; + int fd; + char dev_queue_read_ahead_path[PATH_MAX]; +}; + +static struct file_info finfo; enum thp_enabled { THP_ALWAYS, @@ -88,18 +146,7 @@ struct settings { enum shmem_enabled shmem_enabled; bool use_zero_page; struct khugepaged_settings khugepaged; -}; - -static struct settings default_settings = { - .thp_enabled = THP_MADVISE, - .thp_defrag = THP_DEFRAG_ALWAYS, - .shmem_enabled = SHMEM_NEVER, - .use_zero_page = 0, - .khugepaged = { - .defrag = 1, - .alloc_sleep_millisecs = 10, - .scan_sleep_millisecs = 10, - }, + unsigned long read_ahead_kb; }; static struct settings saved_settings; @@ -118,6 +165,11 @@ static void fail(const char *msg) exit_status++; } +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; @@ -145,13 +197,19 @@ static int write_file(const char *path, const char *buf, size_t buflen) ssize_t numwritten; fd = open(path, O_WRONLY); - if (fd == -1) + if (fd == -1) { + printf("open(%s)\n", path); + exit(EXIT_FAILURE); return 0; + } numwritten = write(fd, buf, buflen - 1); close(fd); - if (numwritten < 1) + if (numwritten < 1) { + printf("write(%s)\n", buf); + exit(EXIT_FAILURE); return 0; + } return (unsigned int) numwritten; } @@ -218,20 +276,11 @@ static void write_string(const char *name, const char *val) } } -static const unsigned long read_num(const char *name) +static const unsigned long _read_num(const char *path) { - char path[PATH_MAX]; char buf[21]; - 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); - } - ret = read_file(path, buf, sizeof(buf)); - if (ret < 0) { + if (read_file(path, buf, sizeof(buf)) < 0) { perror("read_file(read_num)"); exit(EXIT_FAILURE); } @@ -239,10 +288,9 @@ static const unsigned long read_num(const char *name) return strtoul(buf, NULL, 10); } -static void write_num(const char *name, unsigned long num) +static const unsigned long read_num(const char *name) { char path[PATH_MAX]; - char buf[21]; int ret; ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); @@ -250,6 +298,12 @@ static void write_num(const char *name, unsigned long num) 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)) { @@ -258,6 +312,19 @@ static void write_num(const char *name, unsigned long num) } } +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; @@ -277,6 +344,43 @@ static void write_settings(struct settings *settings) 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; +} + +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()); +} + +static void pop_settings(void) +{ + if (settings_index <= 0) { + printf("Fail: Settings stack empty"); + exit(EXIT_FAILURE); + } + --settings_index; + write_settings(current_settings()); } static void restore_settings(int sig) @@ -314,6 +418,10 @@ static void save_settings(void) .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); + success("OK"); signal(SIGTERM, restore_settings); @@ -322,72 +430,90 @@ static void save_settings(void) signal(SIGQUIT, restore_settings); } -static void adjust_settings(void) +static void get_finfo(const char *dir) { + struct stat path_stat; + struct statfs fs; + char buf[1 << 10]; + char path[PATH_MAX]; + char *str, *end; - printf("Adjust settings..."); - write_settings(&default_settings); - success("OK"); -} - -#define MAX_LINE_LENGTH 500 - -static bool check_for_pattern(FILE *fp, char *pattern, char *buf) -{ - while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) { - if (!strncmp(buf, pattern, strlen(pattern))) - return true; + finfo.dir = dir; + stat(finfo.dir, &path_stat); + if (!S_ISDIR(path_stat.st_mode)) { + printf("%s: Not a directory (%s)\n", __func__, finfo.dir); + exit(EXIT_FAILURE); } - return false; -} - -static bool check_huge(void *addr) -{ - bool thp = false; - int ret; - FILE *fp; - char buffer[MAX_LINE_LENGTH]; - char addr_pattern[MAX_LINE_LENGTH]; - - ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", - (unsigned long) addr); - if (ret >= MAX_LINE_LENGTH) { - printf("%s: Pattern is too long\n", __func__); + if (snprintf(finfo.path, sizeof(finfo.path), "%s/" TEST_FILE, + finfo.dir) >= sizeof(finfo.path)) { + printf("%s: Pathname is too long\n", __func__); exit(EXIT_FAILURE); } - - - fp = fopen(PID_SMAPS, "r"); - if (!fp) { - printf("%s: Failed to open file %s\n", __func__, PID_SMAPS); + if (statfs(finfo.dir, &fs)) { + perror("statfs()"); exit(EXIT_FAILURE); } - if (!check_for_pattern(fp, addr_pattern, buffer)) - goto err_out; - - ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "AnonHugePages:%10ld kB", - hpage_pmd_size >> 10); - if (ret >= MAX_LINE_LENGTH) { - printf("%s: Pattern is too long\n", __func__); + finfo.type = fs.f_type == TMPFS_MAGIC ? VMA_SHMEM : VMA_FILE; + if (finfo.type == VMA_SHMEM) + return; + + /* Find owning device's queue/read_ahead_kb control */ + if (snprintf(path, sizeof(path), "/sys/dev/block/%d:%d/uevent", + major(path_stat.st_dev), minor(path_stat.st_dev)) + >= sizeof(path)) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + if (read_file(path, buf, sizeof(buf)) < 0) { + perror("read_file(read_num)"); + exit(EXIT_FAILURE); + } + if (strstr(buf, "DEVTYPE=disk")) { + /* Found it */ + if (snprintf(finfo.dev_queue_read_ahead_path, + sizeof(finfo.dev_queue_read_ahead_path), + "/sys/dev/block/%d:%d/queue/read_ahead_kb", + major(path_stat.st_dev), minor(path_stat.st_dev)) + >= sizeof(finfo.dev_queue_read_ahead_path)) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + return; + } + if (!strstr(buf, "DEVTYPE=partition")) { + printf("%s: Unknown device type: %s\n", __func__, path); exit(EXIT_FAILURE); } /* - * Fetch the AnonHugePages: in the same block and check whether it got - * the expected number of hugeepages next. + * Partition of block device - need to find actual device. + * Using naming convention that devnameN is partition of + * device devname. */ - if (!check_for_pattern(fp, "AnonHugePages:", buffer)) - goto err_out; - - if (strncmp(buffer, addr_pattern, strlen(addr_pattern))) - goto err_out; - - thp = true; -err_out: - fclose(fp); - return thp; + str = strstr(buf, "DEVNAME="); + if (!str) { + printf("%s: Could not read: %s", __func__, path); + exit(EXIT_FAILURE); + } + str += 8; + end = str; + while (*end) { + if (isdigit(*end)) { + *end = '\0'; + if (snprintf(finfo.dev_queue_read_ahead_path, + sizeof(finfo.dev_queue_read_ahead_path), + "/sys/block/%s/queue/read_ahead_kb", + str) >= sizeof(finfo.dev_queue_read_ahead_path)) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + return; + } + ++end; + } + printf("%s: Could not read: %s\n", __func__, path); + exit(EXIT_FAILURE); } - static bool check_swap(void *addr, unsigned long size) { bool swap = false; @@ -409,7 +535,7 @@ static bool check_swap(void *addr, unsigned long size) printf("%s: Failed to open file %s\n", __func__, PID_SMAPS); exit(EXIT_FAILURE); } - if (!check_for_pattern(fp, addr_pattern, buffer)) + if (!check_for_pattern(fp, addr_pattern, buffer, sizeof(buffer))) goto err_out; ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "Swap:%19ld kB", @@ -422,7 +548,7 @@ static bool check_swap(void *addr, unsigned long size) * Fetch the Swap: in the same block and check whether it got * the expected number of hugeepages next. */ - if (!check_for_pattern(fp, "Swap:", buffer)) + if (!check_for_pattern(fp, "Swap:", buffer, sizeof(buffer))) goto err_out; if (strncmp(buffer, addr_pattern, strlen(addr_pattern))) @@ -434,12 +560,12 @@ err_out: return swap; } -static void *alloc_mapping(void) +static void *alloc_mapping(int nr) { void *p; - p = mmap(BASE_ADDR, hpage_pmd_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + p = mmap(BASE_ADDR, nr * hpage_pmd_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (p != BASE_ADDR) { printf("Failed to allocate VMA at %p\n", BASE_ADDR); exit(EXIT_FAILURE); @@ -456,6 +582,60 @@ static void fill_memory(int *p, unsigned long start, unsigned long end) p[i * page_size / sizeof(*p)] = i + 0xdead0000; } +/* + * MADV_COLLAPSE is a best-effort request and may fail if an internal + * resource is temporarily unavailable, in which case it will set errno to + * EAGAIN. In such a case, immediately reattempt the operation one more + * time. + */ +static int madvise_collapse_retry(void *p, unsigned long size) +{ + bool retry = true; + int ret; + +retry: + ret = madvise(p, size, MADV_COLLAPSE); + if (ret && errno == EAGAIN && retry) { + retry = false; + goto retry; + } + return ret; +} + +/* + * Returns pmd-mapped hugepage in VMA marked VM_HUGEPAGE, filled with + * validate_memory()'able contents. + */ +static void *alloc_hpage(struct mem_ops *ops) +{ + void *p = ops->setup_area(1); + + ops->fault(p, 0, hpage_pmd_size); + + /* + * VMA should be neither VM_HUGEPAGE nor VM_NOHUGEPAGE. + * The latter is ineligible for collapse by MADV_COLLAPSE + * while the former might cause MADV_COLLAPSE to race with + * khugepaged on low-load system (like a test machine), which + * would cause MADV_COLLAPSE to fail with EAGAIN. + */ + printf("Allocate huge page..."); + if (madvise_collapse_retry(p, hpage_pmd_size)) { + perror("madvise(MADV_COLLAPSE)"); + exit(EXIT_FAILURE); + } + if (!ops->check_huge(p, 1)) { + perror("madvise(MADV_COLLAPSE)"); + exit(EXIT_FAILURE); + } + if (madvise(p, hpage_pmd_size, MADV_HUGEPAGE)) { + perror("madvise(MADV_HUGEPAGE)"); + exit(EXIT_FAILURE); + } + success("OK"); + return p; +} + static void validate_memory(int *p, unsigned long start, unsigned long end) { int i; @@ -469,26 +649,216 @@ static void validate_memory(int *p, unsigned long start, unsigned long end) } } +static void *anon_setup_area(int nr_hpages) +{ + return alloc_mapping(nr_hpages); +} + +static void anon_cleanup_area(void *p, unsigned long size) +{ + munmap(p, size); +} + +static void anon_fault(void *p, unsigned long start, unsigned long end) +{ + fill_memory(p, start, end); +} + +static bool anon_check_huge(void *addr, int nr_hpages) +{ + return check_huge_anon(addr, nr_hpages, hpage_pmd_size); +} + +static void *file_setup_area(int nr_hpages) +{ + int fd; + void *p; + unsigned long size; + + unlink(finfo.path); /* Cleanup from previous failed tests */ + printf("Creating %s for collapse%s...", finfo.path, + finfo.type == VMA_SHMEM ? " (tmpfs)" : ""); + fd = open(finfo.path, O_DSYNC | O_CREAT | O_RDWR | O_TRUNC | O_EXCL, + 777); + if (fd < 0) { + perror("open()"); + exit(EXIT_FAILURE); + } + + size = nr_hpages * hpage_pmd_size; + p = alloc_mapping(nr_hpages); + fill_memory(p, 0, size); + write(fd, p, size); + close(fd); + munmap(p, size); + success("OK"); + + printf("Opening %s read only for collapse...", finfo.path); + finfo.fd = open(finfo.path, O_RDONLY, 777); + if (finfo.fd < 0) { + perror("open()"); + exit(EXIT_FAILURE); + } + p = mmap(BASE_ADDR, size, PROT_READ | PROT_EXEC, + MAP_PRIVATE, finfo.fd, 0); + if (p == MAP_FAILED || p != BASE_ADDR) { + perror("mmap()"); + exit(EXIT_FAILURE); + } + + /* Drop page cache */ + write_file("/proc/sys/vm/drop_caches", "3", 2); + success("OK"); + return p; +} + +static void file_cleanup_area(void *p, unsigned long size) +{ + munmap(p, size); + close(finfo.fd); + unlink(finfo.path); +} + +static void file_fault(void *p, unsigned long start, unsigned long end) +{ + if (madvise(((char *)p) + start, end - start, MADV_POPULATE_READ)) { + perror("madvise(MADV_POPULATE_READ"); + exit(EXIT_FAILURE); + } +} + +static bool file_check_huge(void *addr, int nr_hpages) +{ + switch (finfo.type) { + case VMA_FILE: + return check_huge_file(addr, nr_hpages, hpage_pmd_size); + case VMA_SHMEM: + return check_huge_shmem(addr, nr_hpages, hpage_pmd_size); + default: + exit(EXIT_FAILURE); + return false; + } +} + +static void *shmem_setup_area(int nr_hpages) +{ + void *p; + unsigned long size = nr_hpages * hpage_pmd_size; + + finfo.fd = memfd_create("khugepaged-selftest-collapse-shmem", 0); + if (finfo.fd < 0) { + perror("memfd_create()"); + exit(EXIT_FAILURE); + } + if (ftruncate(finfo.fd, size)) { + perror("ftruncate()"); + exit(EXIT_FAILURE); + } + p = mmap(BASE_ADDR, size, PROT_READ | PROT_WRITE, MAP_SHARED, finfo.fd, + 0); + if (p != BASE_ADDR) { + perror("mmap()"); + exit(EXIT_FAILURE); + } + return p; +} + +static void shmem_cleanup_area(void *p, unsigned long size) +{ + munmap(p, size); + close(finfo.fd); +} + +static bool shmem_check_huge(void *addr, int nr_hpages) +{ + return check_huge_shmem(addr, nr_hpages, hpage_pmd_size); +} + +static struct mem_ops __anon_ops = { + .setup_area = &anon_setup_area, + .cleanup_area = &anon_cleanup_area, + .fault = &anon_fault, + .check_huge = &anon_check_huge, + .name = "anon", +}; + +static struct mem_ops __file_ops = { + .setup_area = &file_setup_area, + .cleanup_area = &file_cleanup_area, + .fault = &file_fault, + .check_huge = &file_check_huge, + .name = "file", +}; + +static struct mem_ops __shmem_ops = { + .setup_area = &shmem_setup_area, + .cleanup_area = &shmem_cleanup_area, + .fault = &anon_fault, + .check_huge = &shmem_check_huge, + .name = "shmem", +}; + +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(); + + printf("%s...", msg); + + /* + * Prevent khugepaged interference and tests that MADV_COLLAPSE + * ignores /sys/kernel/mm/transparent_hugepage/enabled + */ + settings.thp_enabled = THP_NEVER; + settings.shmem_enabled = SHMEM_NEVER; + push_settings(&settings); + + /* Clear VM_NOHUGEPAGE */ + madvise(p, nr_hpages * hpage_pmd_size, MADV_HUGEPAGE); + ret = madvise_collapse_retry(p, nr_hpages * hpage_pmd_size); + if (((bool)ret) == expect) + fail("Fail: Bad return value"); + else if (!ops->check_huge(p, expect ? nr_hpages : 0)) + fail("Fail: check_huge()"); + else + success("OK"); + + pop_settings(); +} + +static void madvise_collapse(const char *msg, char *p, int nr_hpages, + struct mem_ops *ops, bool expect) +{ + /* Sanity check */ + if (!ops->check_huge(p, 0)) { + printf("Unexpected huge page\n"); + exit(EXIT_FAILURE); + } + __madvise_collapse(msg, p, nr_hpages, ops, expect); +} + #define TICK 500000 -static bool wait_for_scan(const char *msg, char *p) +static bool wait_for_scan(const char *msg, char *p, int nr_hpages, + struct mem_ops *ops) { int full_scans; int timeout = 6; /* 3 seconds */ /* Sanity check */ - if (check_huge(p)) { + if (!ops->check_huge(p, 0)) { printf("Unexpected huge page\n"); exit(EXIT_FAILURE); } - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); + madvise(p, nr_hpages * hpage_pmd_size, MADV_HUGEPAGE); /* Wait until the second full_scan completed */ full_scans = read_num("khugepaged/full_scans") + 2; printf("%s...", msg); while (timeout--) { - if (check_huge(p)) + if (ops->check_huge(p, nr_hpages)) break; if (read_num("khugepaged/full_scans") >= full_scans) break; @@ -496,122 +866,155 @@ static bool wait_for_scan(const char *msg, char *p) usleep(TICK); } - madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); + madvise(p, nr_hpages * hpage_pmd_size, MADV_NOHUGEPAGE); return timeout == -1; } +static void khugepaged_collapse(const char *msg, char *p, int nr_hpages, + struct mem_ops *ops, bool expect) +{ + if (wait_for_scan(msg, p, nr_hpages, ops)) { + if (expect) + fail("Timeout"); + else + success("OK"); + return; + } + + /* + * For file and shmem memory, khugepaged only retracts pte entries after + * putting the new hugepage in the page cache. The hugepage must be + * subsequently refaulted to install the pmd mapping for the mm. + */ + if (ops != &__anon_ops) + ops->fault(p, 0, nr_hpages * hpage_pmd_size); + + if (ops->check_huge(p, expect ? nr_hpages : 0)) + success("OK"); + else + fail("Fail"); +} + +static struct collapse_context __khugepaged_context = { + .collapse = &khugepaged_collapse, + .enforce_pte_scan_limits = true, + .name = "khugepaged", +}; + +static struct collapse_context __madvise_context = { + .collapse = &madvise_collapse, + .enforce_pte_scan_limits = false, + .name = "madvise", +}; + +static bool is_tmpfs(struct mem_ops *ops) +{ + return ops == &__file_ops && finfo.type == VMA_SHMEM; +} + static void alloc_at_fault(void) { - struct settings settings = default_settings; + struct settings settings = *current_settings(); char *p; settings.thp_enabled = THP_ALWAYS; - write_settings(&settings); + push_settings(&settings); - p = alloc_mapping(); + p = alloc_mapping(1); *p = 1; printf("Allocate huge page on fault..."); - if (check_huge(p)) + if (check_huge_anon(p, 1, hpage_pmd_size)) success("OK"); else fail("Fail"); - write_settings(&default_settings); + pop_settings(); madvise(p, page_size, MADV_DONTNEED); printf("Split huge PMD on MADV_DONTNEED..."); - if (!check_huge(p)) + if (check_huge_anon(p, 0, hpage_pmd_size)) success("OK"); else fail("Fail"); munmap(p, hpage_pmd_size); } -static void collapse_full(void) +static void collapse_full(struct collapse_context *c, struct mem_ops *ops) { void *p; - - p = alloc_mapping(); - fill_memory(p, 0, hpage_pmd_size); - if (wait_for_scan("Collapse fully populated PTE table", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); - validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + int nr_hpages = 4; + unsigned long size = nr_hpages * hpage_pmd_size; + + p = ops->setup_area(nr_hpages); + ops->fault(p, 0, size); + c->collapse("Collapse multiple fully populated PTE table", p, nr_hpages, + ops, true); + validate_memory(p, 0, size); + ops->cleanup_area(p, size); } -static void collapse_empty(void) +static void collapse_empty(struct collapse_context *c, struct mem_ops *ops) { void *p; - p = alloc_mapping(); - if (wait_for_scan("Do not collapse empty PTE table", p)) - fail("Timeout"); - else if (check_huge(p)) - fail("Fail"); - else - success("OK"); - munmap(p, hpage_pmd_size); + p = ops->setup_area(1); + c->collapse("Do not collapse empty PTE table", p, 1, ops, false); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_single_pte_entry(void) +static void collapse_single_pte_entry(struct collapse_context *c, struct mem_ops *ops) { void *p; - p = alloc_mapping(); - fill_memory(p, 0, page_size); - if (wait_for_scan("Collapse PTE table with single PTE entry present", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); - validate_memory(p, 0, page_size); - munmap(p, hpage_pmd_size); + p = ops->setup_area(1); + ops->fault(p, 0, page_size); + c->collapse("Collapse PTE table with single PTE entry present", p, + 1, ops, true); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_max_ptes_none(void) +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 = default_settings; + struct settings settings = *current_settings(); void *p; settings.khugepaged.max_ptes_none = max_ptes_none; - write_settings(&settings); + push_settings(&settings); - p = alloc_mapping(); + p = ops->setup_area(1); - fill_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); - if (wait_for_scan("Do not collapse with max_ptes_none exceeded", p)) - fail("Timeout"); - else if (check_huge(p)) - fail("Fail"); - else - success("OK"); - validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); + if (is_tmpfs(ops)) { + /* shmem pages always in the page cache */ + printf("tmpfs..."); + skip("Skip"); + goto skip; + } - fill_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); - if (wait_for_scan("Collapse with max_ptes_none PTEs empty", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); - validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); + ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * 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); - munmap(p, hpage_pmd_size); - write_settings(&default_settings); + if (c->enforce_pte_scan_limits) { + ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); + c->collapse("Collapse with max_ptes_none PTEs empty", p, 1, ops, + true); + validate_memory(p, 0, + (hpage_pmd_nr - max_ptes_none) * page_size); + } +skip: + ops->cleanup_area(p, hpage_pmd_size); + pop_settings(); } -static void collapse_swapin_single_pte(void) +static void collapse_swapin_single_pte(struct collapse_context *c, struct mem_ops *ops) { void *p; - p = alloc_mapping(); - fill_memory(p, 0, hpage_pmd_size); + + p = ops->setup_area(1); + ops->fault(p, 0, hpage_pmd_size); printf("Swapout one page..."); if (madvise(p, page_size, MADV_PAGEOUT)) { @@ -625,25 +1028,21 @@ static void collapse_swapin_single_pte(void) goto out; } - if (wait_for_scan("Collapse with swapping in single PTE entry", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse with swapping in single PTE entry", p, 1, ops, + true); validate_memory(p, 0, hpage_pmd_size); out: - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_max_ptes_swap(void) +static void collapse_max_ptes_swap(struct collapse_context *c, struct mem_ops *ops) { int max_ptes_swap = read_num("khugepaged/max_ptes_swap"); void *p; - p = alloc_mapping(); + p = ops->setup_area(1); + ops->fault(p, 0, hpage_pmd_size); - fill_memory(p, 0, hpage_pmd_size); printf("Swapout %d of %d pages...", max_ptes_swap + 1, hpage_pmd_nr); if (madvise(p, (max_ptes_swap + 1) * page_size, MADV_PAGEOUT)) { perror("madvise(MADV_PAGEOUT)"); @@ -656,115 +1055,93 @@ static void collapse_max_ptes_swap(void) goto out; } - if (wait_for_scan("Do not collapse with max_ptes_swap exceeded", p)) - fail("Timeout"); - else if (check_huge(p)) - fail("Fail"); - else - success("OK"); + c->collapse("Maybe collapse with max_ptes_swap exceeded", p, 1, ops, + !c->enforce_pte_scan_limits); validate_memory(p, 0, hpage_pmd_size); - fill_memory(p, 0, hpage_pmd_size); - printf("Swapout %d of %d pages...", max_ptes_swap, hpage_pmd_nr); - if (madvise(p, max_ptes_swap * page_size, MADV_PAGEOUT)) { - perror("madvise(MADV_PAGEOUT)"); - exit(EXIT_FAILURE); - } - if (check_swap(p, max_ptes_swap * page_size)) { - success("OK"); - } else { - fail("Fail"); - goto out; - } + if (c->enforce_pte_scan_limits) { + ops->fault(p, 0, hpage_pmd_size); + printf("Swapout %d of %d pages...", max_ptes_swap, + hpage_pmd_nr); + if (madvise(p, max_ptes_swap * page_size, MADV_PAGEOUT)) { + perror("madvise(MADV_PAGEOUT)"); + exit(EXIT_FAILURE); + } + if (check_swap(p, max_ptes_swap * page_size)) { + success("OK"); + } else { + fail("Fail"); + goto out; + } - if (wait_for_scan("Collapse with max_ptes_swap pages swapped out", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); - validate_memory(p, 0, hpage_pmd_size); + c->collapse("Collapse with max_ptes_swap pages swapped out", p, + 1, ops, true); + validate_memory(p, 0, hpage_pmd_size); + } out: - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_single_pte_entry_compound(void) +static void collapse_single_pte_entry_compound(struct collapse_context *c, struct mem_ops *ops) { void *p; - p = alloc_mapping(); + p = alloc_hpage(ops); - printf("Allocate huge page..."); - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); - fill_memory(p, 0, hpage_pmd_size); - if (check_huge(p)) - success("OK"); - else - fail("Fail"); - madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); + if (is_tmpfs(ops)) { + /* MADV_DONTNEED won't evict tmpfs pages */ + printf("tmpfs..."); + skip("Skip"); + goto skip; + } + madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); printf("Split huge page leaving single PTE mapping compound page..."); madvise(p + page_size, hpage_pmd_size - page_size, MADV_DONTNEED); - if (!check_huge(p)) + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); - if (wait_for_scan("Collapse PTE table with single PTE mapping compound page", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse PTE table with single PTE mapping compound page", + p, 1, ops, true); validate_memory(p, 0, page_size); - munmap(p, hpage_pmd_size); +skip: + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_full_of_compound(void) +static void collapse_full_of_compound(struct collapse_context *c, struct mem_ops *ops) { void *p; - p = alloc_mapping(); - - printf("Allocate huge page..."); - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); - fill_memory(p, 0, hpage_pmd_size); - if (check_huge(p)) - success("OK"); - else - fail("Fail"); - + p = alloc_hpage(ops); printf("Split huge page leaving single PTE page table full of compound pages..."); madvise(p, page_size, MADV_NOHUGEPAGE); madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); - if (!check_huge(p)) + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); - if (wait_for_scan("Collapse PTE table full of compound pages", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse PTE table full of compound pages", p, 1, ops, + true); validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_compound_extreme(void) +static void collapse_compound_extreme(struct collapse_context *c, struct mem_ops *ops) { void *p; int i; - p = alloc_mapping(); + p = ops->setup_area(1); for (i = 0; i < hpage_pmd_nr; i++) { printf("\rConstruct PTE page table full of different PTE-mapped compound pages %3d/%d...", i + 1, hpage_pmd_nr); madvise(BASE_ADDR, hpage_pmd_size, MADV_HUGEPAGE); - fill_memory(BASE_ADDR, 0, hpage_pmd_size); - if (!check_huge(BASE_ADDR)) { + ops->fault(BASE_ADDR, 0, hpage_pmd_size); + if (!ops->check_huge(BASE_ADDR, 1)) { printf("Failed to allocate huge page\n"); exit(EXIT_FAILURE); } @@ -791,34 +1168,30 @@ static void collapse_compound_extreme(void) } } - munmap(BASE_ADDR, hpage_pmd_size); - fill_memory(p, 0, hpage_pmd_size); - if (!check_huge(p)) + ops->cleanup_area(BASE_ADDR, hpage_pmd_size); + ops->fault(p, 0, hpage_pmd_size); + if (!ops->check_huge(p, 1)) success("OK"); else fail("Fail"); - if (wait_for_scan("Collapse PTE table full of different compound pages", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse PTE table full of different compound pages", p, 1, + ops, true); validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_fork(void) +static void collapse_fork(struct collapse_context *c, struct mem_ops *ops) { int wstatus; void *p; - p = alloc_mapping(); + p = ops->setup_area(1); printf("Allocate small page..."); - fill_memory(p, 0, page_size); - if (!check_huge(p)) + ops->fault(p, 0, page_size); + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); @@ -829,22 +1202,17 @@ static void collapse_fork(void) skip_settings_restore = true; exit_status = 0; - if (!check_huge(p)) + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); - fill_memory(p, page_size, 2 * page_size); - - if (wait_for_scan("Collapse PTE table with single page shared with parent process", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + ops->fault(p, page_size, 2 * page_size); + c->collapse("Collapse PTE table with single page shared with parent process", + p, 1, ops, true); validate_memory(p, 0, page_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); exit(exit_status); } @@ -852,36 +1220,27 @@ static void collapse_fork(void) exit_status += WEXITSTATUS(wstatus); printf("Check if parent still has small page..."); - if (!check_huge(p)) + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); validate_memory(p, 0, page_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_fork_compound(void) +static void collapse_fork_compound(struct collapse_context *c, struct mem_ops *ops) { int wstatus; void *p; - p = alloc_mapping(); - - printf("Allocate huge page..."); - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); - fill_memory(p, 0, hpage_pmd_size); - if (check_huge(p)) - success("OK"); - else - fail("Fail"); - + p = alloc_hpage(ops); printf("Share huge page over fork()..."); if (!fork()) { /* Do not touch settings on child exit */ skip_settings_restore = true; exit_status = 0; - if (check_huge(p)) + if (ops->check_huge(p, 1)) success("OK"); else fail("Fail"); @@ -889,24 +1248,20 @@ static void collapse_fork_compound(void) printf("Split huge page PMD in child process..."); madvise(p, page_size, MADV_NOHUGEPAGE); madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); - if (!check_huge(p)) + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); - fill_memory(p, 0, page_size); + ops->fault(p, 0, page_size); write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1); - if (wait_for_scan("Collapse PTE table full of compound pages in child", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse PTE table full of compound pages in child", + p, 1, ops, true); write_num("khugepaged/max_ptes_shared", - default_settings.khugepaged.max_ptes_shared); + current_settings()->khugepaged.max_ptes_shared); validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); exit(exit_status); } @@ -914,74 +1269,59 @@ static void collapse_fork_compound(void) exit_status += WEXITSTATUS(wstatus); printf("Check if parent still has huge page..."); - if (check_huge(p)) + if (ops->check_huge(p, 1)) success("OK"); else fail("Fail"); validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_max_ptes_shared() +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 wstatus; void *p; - p = alloc_mapping(); - - printf("Allocate huge page..."); - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); - fill_memory(p, 0, hpage_pmd_size); - if (check_huge(p)) - success("OK"); - else - fail("Fail"); - + p = alloc_hpage(ops); printf("Share huge page over fork()..."); if (!fork()) { /* Do not touch settings on child exit */ skip_settings_restore = true; exit_status = 0; - if (check_huge(p)) + if (ops->check_huge(p, 1)) success("OK"); else fail("Fail"); printf("Trigger CoW on page %d of %d...", hpage_pmd_nr - max_ptes_shared - 1, hpage_pmd_nr); - fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared - 1) * page_size); - if (!check_huge(p)) - success("OK"); - else - fail("Fail"); - - if (wait_for_scan("Do not collapse with max_ptes_shared exceeded", p)) - fail("Timeout"); - else if (!check_huge(p)) - success("OK"); - else - fail("Fail"); - - printf("Trigger CoW on page %d of %d...", - hpage_pmd_nr - max_ptes_shared, hpage_pmd_nr); - fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared) * page_size); - if (!check_huge(p)) + ops->fault(p, 0, (hpage_pmd_nr - max_ptes_shared - 1) * page_size); + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); - - if (wait_for_scan("Collapse with max_ptes_shared PTEs shared", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Maybe collapse with max_ptes_shared exceeded", p, + 1, ops, !c->enforce_pte_scan_limits); + + if (c->enforce_pte_scan_limits) { + printf("Trigger CoW on page %d of %d...", + hpage_pmd_nr - max_ptes_shared, hpage_pmd_nr); + ops->fault(p, 0, (hpage_pmd_nr - max_ptes_shared) * + page_size); + if (ops->check_huge(p, 0)) + success("OK"); + else + fail("Fail"); + + c->collapse("Collapse with max_ptes_shared PTEs shared", + p, 1, ops, true); + } validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); exit(exit_status); } @@ -989,20 +1329,153 @@ static void collapse_max_ptes_shared() exit_status += WEXITSTATUS(wstatus); printf("Check if parent still has huge page..."); - if (check_huge(p)) + if (ops->check_huge(p, 1)) success("OK"); else fail("Fail"); validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -int main(void) +static void madvise_collapse_existing_thps(struct collapse_context *c, + struct mem_ops *ops) { + void *p; + + p = ops->setup_area(1); + ops->fault(p, 0, hpage_pmd_size); + c->collapse("Collapse fully populated PTE table...", p, 1, ops, true); + validate_memory(p, 0, hpage_pmd_size); + + /* c->collapse() will find a hugepage and complain - call directly. */ + __madvise_collapse("Re-collapse PMD-mapped hugepage", p, 1, ops, true); + validate_memory(p, 0, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); +} + +/* + * Test race with khugepaged where page tables have been retracted and + * pmd cleared. + */ +static void madvise_retracted_page_tables(struct collapse_context *c, + struct mem_ops *ops) +{ + void *p; + int nr_hpages = 1; + unsigned long size = nr_hpages * hpage_pmd_size; + + p = ops->setup_area(nr_hpages); + ops->fault(p, 0, size); + + /* Let khugepaged collapse and leave pmd cleared */ + if (wait_for_scan("Collapse and leave PMD cleared", p, nr_hpages, + ops)) { + fail("Timeout"); + return; + } + success("OK"); + c->collapse("Install huge PMD from page cache", p, nr_hpages, ops, + true); + validate_memory(p, 0, size); + ops->cleanup_area(p, size); +} + +static void usage(void) +{ + fprintf(stderr, "\nUsage: ./khugepaged <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"); + fprintf(stderr, "\n\t\"file,all\" mem_type requires [dir] argument\n"); + 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"); + exit(1); +} + +static void parse_test_type(int argc, const char **argv) +{ + char *buf; + const char *token; + + if (argc == 1) { + /* Backwards compatibility */ + khugepaged_context = &__khugepaged_context; + madvise_context = &__madvise_context; + anon_ops = &__anon_ops; + return; + } + + buf = strdup(argv[1]); + token = strsep(&buf, ":"); + + if (!strcmp(token, "all")) { + khugepaged_context = &__khugepaged_context; + madvise_context = &__madvise_context; + } else if (!strcmp(token, "khugepaged")) { + khugepaged_context = &__khugepaged_context; + } else if (!strcmp(token, "madvise")) { + madvise_context = &__madvise_context; + } else { + usage(); + } + + if (!buf) + usage(); + + if (!strcmp(buf, "all")) { + file_ops = &__file_ops; + anon_ops = &__anon_ops; + shmem_ops = &__shmem_ops; + } else if (!strcmp(buf, "anon")) { + anon_ops = &__anon_ops; + } else if (!strcmp(buf, "file")) { + file_ops = &__file_ops; + } else if (!strcmp(buf, "shmem")) { + shmem_ops = &__shmem_ops; + } else { + usage(); + } + + if (!file_ops) + return; + + if (argc != 3) + usage(); +} + +int main(int argc, const char **argv) +{ + struct settings default_settings = { + .thp_enabled = THP_MADVISE, + .thp_defrag = THP_DEFRAG_ALWAYS, + .shmem_enabled = SHMEM_ADVISE, + .use_zero_page = 0, + .khugepaged = { + .defrag = 1, + .alloc_sleep_millisecs = 10, + .scan_sleep_millisecs = 10, + }, + /* + * When testing file-backed memory, the collapse path + * looks at how many pages are found in the page cache, not + * what pages are mapped. Disable read ahead optimization so + * pages don't find their way into the page cache unless + * we mem_ops->fault() them in. + */ + .read_ahead_kb = 0, + }; + + parse_test_type(argc, argv); + + if (file_ops) + get_finfo(argv[2]); + setbuf(stdout, NULL); page_size = getpagesize(); - hpage_pmd_size = read_num("hpage_pmd_size"); + hpage_pmd_size = read_pmd_pagesize(); hpage_pmd_nr = hpage_pmd_size / page_size; default_settings.khugepaged.max_ptes_none = hpage_pmd_nr - 1; @@ -1011,21 +1484,75 @@ int main(void) default_settings.khugepaged.pages_to_scan = hpage_pmd_nr * 8; save_settings(); - adjust_settings(); + push_settings(&default_settings); alloc_at_fault(); - collapse_full(); - collapse_empty(); - collapse_single_pte_entry(); - collapse_max_ptes_none(); - collapse_swapin_single_pte(); - collapse_max_ptes_swap(); - collapse_single_pte_entry_compound(); - collapse_full_of_compound(); - collapse_compound_extreme(); - collapse_fork(); - collapse_fork_compound(); - collapse_max_ptes_shared(); + +#define TEST(t, c, o) do { \ + if (c && o) { \ + printf("\nRun test: " #t " (%s:%s)\n", c->name, o->name); \ + t(c, o); \ + } \ + } while (0) + + TEST(collapse_full, khugepaged_context, anon_ops); + TEST(collapse_full, khugepaged_context, file_ops); + TEST(collapse_full, khugepaged_context, shmem_ops); + TEST(collapse_full, madvise_context, anon_ops); + TEST(collapse_full, madvise_context, file_ops); + TEST(collapse_full, madvise_context, shmem_ops); + + TEST(collapse_empty, khugepaged_context, anon_ops); + TEST(collapse_empty, madvise_context, anon_ops); + + TEST(collapse_single_pte_entry, khugepaged_context, anon_ops); + TEST(collapse_single_pte_entry, khugepaged_context, file_ops); + TEST(collapse_single_pte_entry, khugepaged_context, shmem_ops); + TEST(collapse_single_pte_entry, madvise_context, anon_ops); + TEST(collapse_single_pte_entry, madvise_context, file_ops); + TEST(collapse_single_pte_entry, madvise_context, shmem_ops); + + TEST(collapse_max_ptes_none, khugepaged_context, anon_ops); + TEST(collapse_max_ptes_none, khugepaged_context, file_ops); + TEST(collapse_max_ptes_none, madvise_context, anon_ops); + TEST(collapse_max_ptes_none, madvise_context, file_ops); + + TEST(collapse_single_pte_entry_compound, khugepaged_context, anon_ops); + TEST(collapse_single_pte_entry_compound, khugepaged_context, file_ops); + TEST(collapse_single_pte_entry_compound, madvise_context, anon_ops); + TEST(collapse_single_pte_entry_compound, madvise_context, file_ops); + + TEST(collapse_full_of_compound, khugepaged_context, anon_ops); + TEST(collapse_full_of_compound, khugepaged_context, file_ops); + TEST(collapse_full_of_compound, khugepaged_context, shmem_ops); + TEST(collapse_full_of_compound, madvise_context, anon_ops); + TEST(collapse_full_of_compound, madvise_context, file_ops); + TEST(collapse_full_of_compound, madvise_context, shmem_ops); + + TEST(collapse_compound_extreme, khugepaged_context, anon_ops); + TEST(collapse_compound_extreme, madvise_context, anon_ops); + + TEST(collapse_swapin_single_pte, khugepaged_context, anon_ops); + TEST(collapse_swapin_single_pte, madvise_context, anon_ops); + + TEST(collapse_max_ptes_swap, khugepaged_context, anon_ops); + TEST(collapse_max_ptes_swap, madvise_context, anon_ops); + + TEST(collapse_fork, khugepaged_context, anon_ops); + TEST(collapse_fork, madvise_context, anon_ops); + + TEST(collapse_fork_compound, khugepaged_context, anon_ops); + TEST(collapse_fork_compound, madvise_context, anon_ops); + + TEST(collapse_max_ptes_shared, khugepaged_context, anon_ops); + TEST(collapse_max_ptes_shared, madvise_context, anon_ops); + + TEST(madvise_collapse_existing_thps, madvise_context, anon_ops); + TEST(madvise_collapse_existing_thps, madvise_context, file_ops); + TEST(madvise_collapse_existing_thps, madvise_context, shmem_ops); + + TEST(madvise_retracted_page_tables, madvise_context, file_ops); + TEST(madvise_retracted_page_tables, madvise_context, shmem_ops); restore_settings(0); } diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c index 1436e1a9a3d3..0d85be2350fa 100644 --- a/tools/testing/selftests/vm/ksm_tests.c +++ b/tools/testing/selftests/vm/ksm_tests.c @@ -11,7 +11,8 @@ #include <err.h> #include "../kselftest.h" -#include "../../../../include/vdso/time64.h" +#include <include/vdso/time64.h> +#include "util.h" #define KSM_SYSFS_PATH "/sys/kernel/mm/ksm/" #define KSM_FP(s) (KSM_SYSFS_PATH s) @@ -22,15 +23,6 @@ #define KSM_MERGE_ACROSS_NODES_DEFAULT true #define MB (1ul << 20) -#define PAGE_SHIFT 12 -#define HPAGE_SHIFT 21 - -#define PAGE_SIZE (1 << PAGE_SHIFT) -#define HPAGE_SIZE (1 << HPAGE_SHIFT) - -#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) -#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) - struct ksm_sysfs { unsigned long max_page_sharing; unsigned long merge_across_nodes; @@ -62,6 +54,7 @@ static int ksm_write_sysfs(const char *file_path, unsigned long val) } if (fprintf(f, "%lu", val) < 0) { perror("fprintf"); + fclose(f); return 1; } fclose(f); @@ -80,6 +73,7 @@ static int ksm_read_sysfs(const char *file_path, unsigned long *val) } if (fscanf(f, "%lu", val) != 1) { perror("fscanf"); + fclose(f); return 1; } fclose(f); @@ -229,7 +223,8 @@ static bool assert_ksm_pages_count(long dupl_page_count) static int ksm_save_def(struct ksm_sysfs *ksm_sysfs) { if (ksm_read_sysfs(KSM_FP("max_page_sharing"), &ksm_sysfs->max_page_sharing) || - ksm_read_sysfs(KSM_FP("merge_across_nodes"), &ksm_sysfs->merge_across_nodes) || + numa_available() ? 0 : + ksm_read_sysfs(KSM_FP("merge_across_nodes"), &ksm_sysfs->merge_across_nodes) || ksm_read_sysfs(KSM_FP("sleep_millisecs"), &ksm_sysfs->sleep_millisecs) || ksm_read_sysfs(KSM_FP("pages_to_scan"), &ksm_sysfs->pages_to_scan) || ksm_read_sysfs(KSM_FP("run"), &ksm_sysfs->run) || @@ -244,7 +239,8 @@ static int ksm_save_def(struct ksm_sysfs *ksm_sysfs) static int ksm_restore(struct ksm_sysfs *ksm_sysfs) { if (ksm_write_sysfs(KSM_FP("max_page_sharing"), ksm_sysfs->max_page_sharing) || - ksm_write_sysfs(KSM_FP("merge_across_nodes"), ksm_sysfs->merge_across_nodes) || + numa_available() ? 0 : + ksm_write_sysfs(KSM_FP("merge_across_nodes"), ksm_sysfs->merge_across_nodes) || ksm_write_sysfs(KSM_FP("pages_to_scan"), ksm_sysfs->pages_to_scan) || ksm_write_sysfs(KSM_FP("run"), ksm_sysfs->run) || ksm_write_sysfs(KSM_FP("sleep_millisecs"), ksm_sysfs->sleep_millisecs) || @@ -456,34 +452,6 @@ err_out: return KSFT_FAIL; } -int64_t allocate_transhuge(void *ptr, int pagemap_fd) -{ - uint64_t ent[2]; - - /* drop pmd */ - if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_FIXED | MAP_ANONYMOUS | - MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) - errx(2, "mmap transhuge"); - - if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) - err(2, "MADV_HUGEPAGE"); - - /* allocate transparent huge page */ - *(volatile void **)ptr = ptr; - - if (pread(pagemap_fd, ent, sizeof(ent), - (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent)) - err(2, "read pagemap"); - - if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && - PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && - !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1))) - return PAGEMAP_PFN(ent[0]); - - return -1; -} - static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t map_size) { void *map_ptr, *map_ptr_orig; @@ -756,7 +724,8 @@ int main(int argc, char *argv[]) if (ksm_write_sysfs(KSM_FP("run"), 2) || ksm_write_sysfs(KSM_FP("sleep_millisecs"), 0) || - ksm_write_sysfs(KSM_FP("merge_across_nodes"), 1) || + numa_available() ? 0 : + ksm_write_sysfs(KSM_FP("merge_across_nodes"), 1) || ksm_write_sysfs(KSM_FP("pages_to_scan"), page_count)) return KSFT_FAIL; diff --git a/tools/testing/selftests/vm/madv_populate.c b/tools/testing/selftests/vm/madv_populate.c index 3ee0e8275600..715a42e8e2cd 100644 --- a/tools/testing/selftests/vm/madv_populate.c +++ b/tools/testing/selftests/vm/madv_populate.c @@ -18,6 +18,7 @@ #include <sys/mman.h> #include "../kselftest.h" +#include "vm_util.h" /* * For now, we're using 2 MiB of private anonymous memory for all tests. @@ -26,18 +27,6 @@ static size_t pagesize; -static uint64_t pagemap_get_entry(int fd, char *start) -{ - const unsigned long pfn = (unsigned long)start / pagesize; - uint64_t entry; - int ret; - - ret = pread(fd, &entry, sizeof(entry), pfn * sizeof(entry)); - if (ret != sizeof(entry)) - ksft_exit_fail_msg("reading pagemap failed\n"); - return entry; -} - static bool pagemap_is_populated(int fd, char *start) { uint64_t entry = pagemap_get_entry(fd, start); @@ -46,13 +35,6 @@ static bool pagemap_is_populated(int fd, char *start) return entry & 0xc000000000000000ull; } -static bool pagemap_is_softdirty(int fd, char *start) -{ - uint64_t entry = pagemap_get_entry(fd, start); - - return entry & 0x0080000000000000ull; -} - static void sense_support(void) { char *addr; @@ -258,20 +240,6 @@ static bool range_is_not_softdirty(char *start, ssize_t size) return ret; } -static void clear_softdirty(void) -{ - int fd = open("/proc/self/clear_refs", O_WRONLY); - const char *ctrl = "4"; - int ret; - - if (fd < 0) - ksft_exit_fail_msg("opening clear_refs failed\n"); - ret = write(fd, ctrl, strlen(ctrl)); - if (ret != strlen(ctrl)) - ksft_exit_fail_msg("writing clear_refs failed\n"); - close(fd); -} - static void test_softdirty(void) { char *addr; diff --git a/tools/testing/selftests/vm/map_fixed_noreplace.c b/tools/testing/selftests/vm/map_fixed_noreplace.c index d91bde511268..eed44322d1a6 100644 --- a/tools/testing/selftests/vm/map_fixed_noreplace.c +++ b/tools/testing/selftests/vm/map_fixed_noreplace.c @@ -17,9 +17,6 @@ #define MAP_FIXED_NOREPLACE 0x100000 #endif -#define BASE_ADDRESS (256ul * 1024 * 1024) - - static void dump_maps(void) { char cmd[32]; @@ -28,18 +25,46 @@ static void dump_maps(void) system(cmd); } +static unsigned long find_base_addr(unsigned long size) +{ + void *addr; + unsigned long flags; + + flags = MAP_PRIVATE | MAP_ANONYMOUS; + addr = mmap(NULL, size, PROT_NONE, flags, -1, 0); + if (addr == MAP_FAILED) { + printf("Error: couldn't map the space we need for the test\n"); + return 0; + } + + if (munmap(addr, size) != 0) { + printf("Error: couldn't map the space we need for the test\n"); + return 0; + } + return (unsigned long)addr; +} + int main(void) { + unsigned long base_addr; unsigned long flags, addr, size, page_size; char *p; page_size = sysconf(_SC_PAGE_SIZE); + //let's find a base addr that is free before we start the tests + size = 5 * page_size; + base_addr = find_base_addr(size); + if (!base_addr) { + printf("Error: couldn't map the space we need for the test\n"); + return 1; + } + flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE; // Check we can map all the areas we need below errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); @@ -60,7 +85,7 @@ int main(void) printf("unmap() successful\n"); errno = 0; - addr = BASE_ADDRESS + page_size; + addr = base_addr + page_size; size = 3 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -80,7 +105,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -101,7 +126,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS + (2 * page_size); + addr = base_addr + (2 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -121,7 +146,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS + (3 * page_size); + addr = base_addr + (3 * page_size); size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -141,7 +166,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -161,7 +186,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -181,7 +206,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS + (4 * page_size); + addr = base_addr + (4 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -192,7 +217,7 @@ int main(void) return 1; } - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; if (munmap((void *)addr, size) != 0) { dump_maps(); diff --git a/tools/testing/selftests/vm/memfd_secret.c b/tools/testing/selftests/vm/memfd_secret.c index 93e7e7ffed33..957b9e18c729 100644 --- a/tools/testing/selftests/vm/memfd_secret.c +++ b/tools/testing/selftests/vm/memfd_secret.c @@ -282,7 +282,7 @@ int main(int argc, char *argv[]) close(fd); - ksft_exit(!ksft_get_fail_cnt()); + ksft_finished(); } #else /* __NR_memfd_secret */ diff --git a/tools/testing/selftests/vm/migration.c b/tools/testing/selftests/vm/migration.c new file mode 100644 index 000000000000..1cec8425e3ca --- /dev/null +++ b/tools/testing/selftests/vm/migration.c @@ -0,0 +1,193 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * The main purpose of the tests here is to exercise the migration entry code + * paths in the kernel. + */ + +#include "../kselftest_harness.h" +#include <strings.h> +#include <pthread.h> +#include <numa.h> +#include <numaif.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <signal.h> +#include <time.h> + +#define TWOMEG (2<<20) +#define RUNTIME (60) + +#define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1))) + +FIXTURE(migration) +{ + pthread_t *threads; + pid_t *pids; + int nthreads; + int n1; + int n2; +}; + +FIXTURE_SETUP(migration) +{ + int n; + + ASSERT_EQ(numa_available(), 0); + self->nthreads = numa_num_task_cpus() - 1; + self->n1 = -1; + self->n2 = -1; + + for (n = 0; n < numa_max_possible_node(); n++) + if (numa_bitmask_isbitset(numa_all_nodes_ptr, n)) { + if (self->n1 == -1) { + self->n1 = n; + } else { + self->n2 = n; + break; + } + } + + self->threads = malloc(self->nthreads * sizeof(*self->threads)); + ASSERT_NE(self->threads, NULL); + self->pids = malloc(self->nthreads * sizeof(*self->pids)); + ASSERT_NE(self->pids, NULL); +}; + +FIXTURE_TEARDOWN(migration) +{ + free(self->threads); + free(self->pids); +} + +int migrate(uint64_t *ptr, int n1, int n2) +{ + int ret, tmp; + int status = 0; + struct timespec ts1, ts2; + + if (clock_gettime(CLOCK_MONOTONIC, &ts1)) + return -1; + + while (1) { + if (clock_gettime(CLOCK_MONOTONIC, &ts2)) + return -1; + + if (ts2.tv_sec - ts1.tv_sec >= RUNTIME) + return 0; + + ret = move_pages(0, 1, (void **) &ptr, &n2, &status, + MPOL_MF_MOVE_ALL); + if (ret) { + if (ret > 0) + printf("Didn't migrate %d pages\n", ret); + else + perror("Couldn't migrate pages"); + return -2; + } + + tmp = n2; + n2 = n1; + n1 = tmp; + } + + return 0; +} + +void *access_mem(void *ptr) +{ + uint64_t y = 0; + volatile uint64_t *x = ptr; + + while (1) { + pthread_testcancel(); + y += *x; + } + + return NULL; +} + +/* + * Basic migration entry testing. One thread will move pages back and forth + * between nodes whilst other threads try and access them triggering the + * migration entry wait paths in the kernel. + */ +TEST_F_TIMEOUT(migration, private_anon, 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, -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); +} + +/* + * Same as the previous test but with shared memory. + */ +TEST_F_TIMEOUT(migration, shared_anon, 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, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) { + pid = fork(); + if (!pid) + 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); +} + +/* + * Tests the pmd migration entry paths. + */ +TEST_F_TIMEOUT(migration, private_anon_thp, 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, 2*TWOMEG, PROT_READ | PROT_WRITE, + MAP_PRIVATE | 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++) + 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); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/vm/mrelease_test.c b/tools/testing/selftests/vm/mrelease_test.c new file mode 100644 index 000000000000..6c62966ab5db --- /dev/null +++ b/tools/testing/selftests/vm/mrelease_test.c @@ -0,0 +1,206 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2022 Google LLC + */ +#define _GNU_SOURCE +#include <errno.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "util.h" + +#include "../kselftest.h" + +#ifndef __NR_pidfd_open +#define __NR_pidfd_open -1 +#endif + +#ifndef __NR_process_mrelease +#define __NR_process_mrelease -1 +#endif + +#define MB(x) (x << 20) +#define MAX_SIZE_MB 1024 + +static int alloc_noexit(unsigned long nr_pages, int pipefd) +{ + int ppid = getppid(); + int timeout = 10; /* 10sec timeout to get killed */ + unsigned long i; + char *buf; + + buf = (char *)mmap(NULL, nr_pages * PAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, 0, 0); + if (buf == MAP_FAILED) { + perror("mmap failed, halting the test"); + return KSFT_FAIL; + } + + for (i = 0; i < nr_pages; i++) + *((unsigned long *)(buf + (i * PAGE_SIZE))) = i; + + /* Signal the parent that the child is ready */ + if (write(pipefd, "", 1) < 0) { + perror("write"); + return KSFT_FAIL; + } + + /* Wait to be killed (when reparenting happens) */ + while (getppid() == ppid && timeout > 0) { + sleep(1); + timeout--; + } + + munmap(buf, nr_pages * PAGE_SIZE); + + return (timeout > 0) ? KSFT_PASS : KSFT_FAIL; +} + +/* 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); + } + /* + * 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); + } +} + +static int child_main(int pipefd[], size_t size) +{ + int res; + + /* Allocate and fault-in memory and wait to be killed */ + close(pipefd[0]); + res = alloc_noexit(MB(size) / PAGE_SIZE, pipefd[1]); + close(pipefd[1]); + return res; +} + +int main(void) +{ + int pipefd[2], pidfd; + bool success, retry; + size_t size; + pid_t pid; + char byte; + int res; + + /* 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); + } + + /* Start the test with 1MB child memory allocation */ + size = 1; +retry: + /* + * Pipe for the child to signal when it's done allocating + * memory + */ + if (pipe(pipefd)) { + perror("pipe"); + exit(KSFT_FAIL); + } + pid = fork(); + if (pid < 0) { + perror("fork"); + close(pipefd[0]); + close(pipefd[1]); + exit(KSFT_FAIL); + } + + if (pid == 0) { + /* Child main routine */ + res = child_main(pipefd, size); + exit(res); + } + + /* + * Parent main routine: + * Wait for the child to finish allocations, then kill and reap + */ + close(pipefd[1]); + /* Block until the child is ready */ + 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); + } + + pidfd = syscall(__NR_pidfd_open, pid, 0); + if (pidfd < 0) { + perror("pidfd_open"); + if (!kill(pid, SIGKILL)) + waitpid(pid, NULL, 0); + exit(KSFT_FAIL); + } + + /* 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); + } + + success = (syscall(__NR_process_mrelease, pidfd, 0) == 0); + if (!success) { + /* + * If we failed to reap because the child exited too soon, + * before we could call process_mrelease. Double child's memory + * which causes it to spend more time on cleanup and increases + * our chances of reaping its memory before it exits. + * Retry until we succeed or reach MAX_SIZE_MB. + */ + 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); + } + } + + /* Cleanup to prevent zombies */ + if (waitpid(pid, NULL, 0) < 0) { + perror("waitpid"); + exit(KSFT_FAIL); + } + close(pidfd); + + if (!success) { + if (retry) { + size *= 2; + goto retry; + } + printf("All process_mrelease attempts failed!\n"); + exit(KSFT_FAIL); + } + + printf("Success reaping a child with %zuMB of memory allocations\n", + size); + return KSFT_PASS; +} diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c index 0624d1bd71b5..9496346973d4 100644 --- a/tools/testing/selftests/vm/mremap_test.c +++ b/tools/testing/selftests/vm/mremap_test.c @@ -6,9 +6,11 @@ #include <errno.h> #include <stdlib.h> +#include <stdio.h> #include <string.h> #include <sys/mman.h> #include <time.h> +#include <stdbool.h> #include "../kselftest.h" @@ -20,7 +22,6 @@ #define VALIDATION_DEFAULT_THRESHOLD 4 /* 4MB */ #define VALIDATION_NO_THRESHOLD 0 /* Verify the entire region */ -#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) struct config { @@ -65,6 +66,103 @@ enum { } /* + * Returns false if the requested remap region overlaps with an + * existing mapping (e.g text, stack) else returns true. + */ +static bool is_remap_region_valid(void *addr, unsigned long long size) +{ + void *remap_addr = NULL; + bool ret = true; + + /* Use MAP_FIXED_NOREPLACE flag to ensure region is not mapped */ + remap_addr = mmap(addr, size, PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); + + if (remap_addr == MAP_FAILED) { + if (errno == EEXIST) + ret = false; + } else { + munmap(remap_addr, size); + } + + return ret; +} + +/* Returns mmap_min_addr sysctl tunable from procfs */ +static unsigned long long get_mmap_min_addr(void) +{ + FILE *fp; + int n_matched; + static unsigned long long addr; + + if (addr) + return addr; + + fp = fopen("/proc/sys/vm/mmap_min_addr", "r"); + if (fp == NULL) { + ksft_print_msg("Failed to open /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + exit(KSFT_SKIP); + } + + n_matched = fscanf(fp, "%llu", &addr); + if (n_matched != 1) { + ksft_print_msg("Failed to read /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + fclose(fp); + exit(KSFT_SKIP); + } + + fclose(fp); + return addr; +} + +/* + * This test validates that merge is called when expanding a mapping. + * Mapping containing three pages is created, middle page is unmapped + * and then the mapping containing the first page is expanded so that + * it fills the created hole. The two parts should merge creating + * single mapping with three pages. + */ +static void mremap_expand_merge(unsigned long page_size) +{ + char *test_name = "mremap expand merge"; + FILE *fp; + char *line = NULL; + size_t len = 0; + bool success = false; + char *start = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + munmap(start + page_size, page_size); + mremap(start, page_size, 2 * page_size, 0); + + fp = fopen("/proc/self/maps", "r"); + if (fp == NULL) { + ksft_test_result_fail("%s\n", test_name); + return; + } + + while (getline(&line, &len, 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 (first_val == start && second_val == start + 3 * page_size) { + success = true; + break; + } + } + if (success) + ksft_test_result_pass("%s\n", test_name); + else + ksft_test_result_fail("%s\n", test_name); + fclose(fp); +} + +/* * Returns the start address of the mapping on success, else returns * NULL on failure. */ @@ -72,11 +170,18 @@ 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(); + 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); + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); if (src_addr == MAP_FAILED) { if (errno == EPERM || errno == EEXIST) goto retry; @@ -91,8 +196,10 @@ retry: * alignment in the tests. */ if (((unsigned long long) src_addr & (c.src_alignment - 1)) || - !((unsigned long long) src_addr & c.src_alignment)) + !((unsigned long long) src_addr & c.src_alignment)) { + munmap(src_addr, c.region_size); goto retry; + } if (!src_addr) goto error; @@ -141,9 +248,20 @@ static long long remap_region(struct config c, unsigned int threshold_mb, if (!((unsigned long long) addr & c.dest_alignment)) addr = (void *) ((unsigned long long) addr | c.dest_alignment); + /* 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) { + ksft_print_msg("Couldn't find a valid region to remap to\n"); + ret = -1; + goto out; + } + addr += c.dest_alignment; + } + clock_gettime(CLOCK_MONOTONIC, &t_start); dest_addr = mremap(src_addr, c.region_size, c.region_size, - MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); + MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); clock_gettime(CLOCK_MONOTONIC, &t_end); if (dest_addr == MAP_FAILED) { @@ -194,7 +312,7 @@ static void run_mremap_test_case(struct test test_case, int *failures, if (remap_time < 0) { if (test_case.expect_failure) - ksft_test_result_pass("%s\n\tExpected mremap failure\n", + ksft_test_result_xfail("%s\n\tExpected mremap failure\n", test_case.name); else { ksft_test_result_fail("%s\n", test_case.name); @@ -262,6 +380,7 @@ int main(int argc, char **argv) int i, run_perf_tests; unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD; unsigned int pattern_seed; + int num_expand_tests = 1; struct test test_cases[MAX_TEST]; struct test perf_test_cases[MAX_PERF_TEST]; int page_size; @@ -333,12 +452,14 @@ 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)); + ARRAY_SIZE(perf_test_cases) : 0) + num_expand_tests); for (i = 0; i < ARRAY_SIZE(test_cases); i++) run_mremap_test_case(test_cases[i], &failures, threshold_mb, pattern_seed); + mremap_expand_merge(page_size); + if (run_perf_tests) { ksft_print_msg("\n%s\n", "mremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:"); diff --git a/tools/testing/selftests/vm/pkey-helpers.h b/tools/testing/selftests/vm/pkey-helpers.h index 622a85848f61..92f3be3dd8e5 100644 --- a/tools/testing/selftests/vm/pkey-helpers.h +++ b/tools/testing/selftests/vm/pkey-helpers.h @@ -13,6 +13,8 @@ #include <ucontext.h> #include <sys/mman.h> +#include "../kselftest.h" + /* Define some kernel-like types */ #define u8 __u8 #define u16 __u16 @@ -175,7 +177,6 @@ static inline void __pkey_write_allow(int pkey, int do_allow_write) dprintf4("pkey_reg now: %016llx\n", read_pkey_reg()); } -#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) #define ALIGN_UP(x, align_to) (((x) + ((align_to)-1)) & ~((align_to)-1)) #define ALIGN_DOWN(x, align_to) ((x) & ~((align_to)-1)) #define ALIGN_PTR_UP(p, ptr_align_to) \ diff --git a/tools/testing/selftests/vm/pkey-x86.h b/tools/testing/selftests/vm/pkey-x86.h index e4a4ce2b826d..b078ce9c6d2a 100644 --- a/tools/testing/selftests/vm/pkey-x86.h +++ b/tools/testing/selftests/vm/pkey-x86.h @@ -80,19 +80,6 @@ static inline void __write_pkey_reg(u64 pkey_reg) assert(pkey_reg == __read_pkey_reg()); } -static inline void __cpuid(unsigned int *eax, unsigned int *ebx, - unsigned int *ecx, unsigned int *edx) -{ - /* ecx is often an input as well as an output. */ - asm volatile( - "cpuid;" - : "=a" (*eax), - "=b" (*ebx), - "=c" (*ecx), - "=d" (*edx) - : "0" (*eax), "2" (*ecx)); -} - /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx) */ #define X86_FEATURE_PKU (1<<3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (1<<4) /* OS Protection Keys Enable */ @@ -104,9 +91,7 @@ static inline int cpu_has_pkeys(void) unsigned int ecx; unsigned int edx; - eax = 0x7; - ecx = 0x0; - __cpuid(&eax, &ebx, &ecx, &edx); + __cpuid_count(0x7, 0x0, eax, ebx, ecx, edx); if (!(ecx & X86_FEATURE_PKU)) { dprintf2("cpu does not have PKU\n"); @@ -142,9 +127,7 @@ int pkey_reg_xstate_offset(void) /* assume that XSTATE_PKEY is set in XCR0 */ leaf = XSTATE_PKEY_BIT; { - eax = XSTATE_CPUID; - ecx = leaf; - __cpuid(&eax, &ebx, &ecx, &edx); + __cpuid_count(XSTATE_CPUID, leaf, eax, ebx, ecx, edx); if (leaf == XSTATE_PKEY_BIT) { xstate_offset = ebx; diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index 2d0ae88665db..291bc1e07842 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -1523,7 +1523,7 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) /* * Reset the shadow, assuming that the above mprotect() * correctly changed PKRU, but to an unknown value since - * the actual alllocated pkey is unknown. + * the actual allocated pkey is unknown. */ shadow_pkey_reg = __read_pkey_reg(); diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index a24d30af3094..e780e76c26b8 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -9,12 +9,12 @@ mnt=./huge exitcode=0 #get huge pagesize and freepages from /proc/meminfo -while read name size unit; do +while read -r name size unit; do if [ "$name" = "HugePages_Free:" ]; then - freepgs=$size + freepgs="$size" fi if [ "$name" = "Hugepagesize:" ]; then - hpgsize_KB=$size + hpgsize_KB="$size" fi done < /proc/meminfo @@ -30,27 +30,26 @@ needmem_KB=$((half_ufd_size_MB * 2 * 1024)) #set proper nr_hugepages if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then - nr_hugepgs=`cat /proc/sys/vm/nr_hugepages` + nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) needpgs=$((needmem_KB / hpgsize_KB)) tries=2 - while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do - lackpgs=$(( $needpgs - $freepgs )) + while [ "$tries" -gt 0 ] && [ "$freepgs" -lt "$needpgs" ]; do + lackpgs=$((needpgs - freepgs)) echo 3 > /proc/sys/vm/drop_caches - echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages - if [ $? -ne 0 ]; then + if ! echo $((lackpgs + nr_hugepgs)) > /proc/sys/vm/nr_hugepages; then echo "Please run this test as root" exit $ksft_skip fi - while read name size unit; do + while read -r name size unit; do if [ "$name" = "HugePages_Free:" ]; then freepgs=$size fi done < /proc/meminfo tries=$((tries - 1)) done - if [ $freepgs -lt $needpgs ]; then + if [ "$freepgs" -lt "$needpgs" ]; then printf "Not enough huge pages available (%d < %d)\n" \ - $freepgs $needpgs + "$freepgs" "$needpgs" exit 1 fi else @@ -60,430 +59,142 @@ fi #filter 64bit architectures ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64" -if [ -z $ARCH ]; then - ARCH=`uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/'` +if [ -z "$ARCH" ]; then + ARCH=$(uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/') fi VADDR64=0 -echo "$ARCH64STR" | grep $ARCH && VADDR64=1 - -mkdir $mnt -mount -t hugetlbfs none $mnt - -echo "---------------------" -echo "running hugepage-mmap" -echo "---------------------" -./hugepage-mmap -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +echo "$ARCH64STR" | grep "$ARCH" && VADDR64=1 + +# Usage: run_test [test binary] [arbitrary test arguments...] +run_test() { + local title="running $*" + local sep=$(echo -n "$title" | tr "[:graph:][:space:]" -) + printf "%s\n%s\n%s\n" "$sep" "$title" "$sep" + + "$@" + local ret=$? + if [ $ret -eq 0 ]; then + echo "[PASS]" + elif [ $ret -eq $ksft_skip ]; then + echo "[SKIP]" + exitcode=$ksft_skip + else + echo "[FAIL]" + exitcode=1 + fi +} + +mkdir "$mnt" +mount -t hugetlbfs none "$mnt" + +run_test ./hugepage-mmap -shmmax=`cat /proc/sys/kernel/shmmax` -shmall=`cat /proc/sys/kernel/shmall` +shmmax=$(cat /proc/sys/kernel/shmmax) +shmall=$(cat /proc/sys/kernel/shmall) echo 268435456 > /proc/sys/kernel/shmmax echo 4194304 > /proc/sys/kernel/shmall -echo "--------------------" -echo "running hugepage-shm" -echo "--------------------" -./hugepage-shm -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi -echo $shmmax > /proc/sys/kernel/shmmax -echo $shmall > /proc/sys/kernel/shmall - -echo "-------------------" -echo "running map_hugetlb" -echo "-------------------" -./map_hugetlb -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./hugepage-shm +echo "$shmmax" > /proc/sys/kernel/shmmax +echo "$shmall" > /proc/sys/kernel/shmall -echo "-----------------------" -echo "running hugepage-mremap" -echo "-----------------------" -./hugepage-mremap -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./map_hugetlb + +run_test ./hugepage-mremap "$mnt"/huge_mremap +rm -f "$mnt"/huge_mremap + +run_test ./hugepage-vmemmap + +run_test ./hugetlb-madvise "$mnt"/madvise-test +rm -f "$mnt"/madvise-test echo "NOTE: The above hugetlb tests provide minimal coverage. Use" echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" echo " hugetlb regression testing." -echo "---------------------------" -echo "running map_fixed_noreplace" -echo "---------------------------" -./map_fixed_noreplace -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./map_fixed_noreplace + +# get_user_pages_fast() benchmark +run_test ./gup_test -u +# pin_user_pages_fast() benchmark +run_test ./gup_test -a +# Dump pages 0, 19, and 4096, using pin_user_pages: +run_test ./gup_test -ct -F 0x1 0 19 0x1000 + +uffd_mods=("" ":dev") +for mod in "${uffd_mods[@]}"; do + run_test ./userfaultfd anon${mod} 20 16 + # Hugetlb tests require source and destination huge pages. Pass in half + # the size ($half_ufd_size_MB), which is used for *each*. + run_test ./userfaultfd hugetlb${mod} "$half_ufd_size_MB" 32 + run_test ./userfaultfd hugetlb_shared${mod} "$half_ufd_size_MB" 32 "$mnt"/uffd-test + rm -f "$mnt"/uffd-test + run_test ./userfaultfd shmem${mod} 20 16 +done -echo "------------------------------------------------------" -echo "running: gup_test -u # get_user_pages_fast() benchmark" -echo "------------------------------------------------------" -./gup_test -u -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +#cleanup +umount "$mnt" +rm -rf "$mnt" +echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages -echo "------------------------------------------------------" -echo "running: gup_test -a # pin_user_pages_fast() benchmark" -echo "------------------------------------------------------" -./gup_test -a -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./compaction_test -echo "------------------------------------------------------------" -echo "# Dump pages 0, 19, and 4096, using pin_user_pages:" -echo "running: gup_test -ct -F 0x1 0 19 0x1000 # dump_page() test" -echo "------------------------------------------------------------" -./gup_test -ct -F 0x1 0 19 0x1000 -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test sudo -u nobody ./on-fault-limit -echo "-------------------" -echo "running userfaultfd" -echo "-------------------" -./userfaultfd anon 20 16 -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./map_populate -echo "---------------------------" -echo "running userfaultfd_hugetlb" -echo "---------------------------" -# Test requires source and destination huge pages. Size of source -# (half_ufd_size_MB) is passed as argument to test. -./userfaultfd hugetlb $half_ufd_size_MB 32 $mnt/ufd_test_file -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi -rm -f $mnt/ufd_test_file - -echo "-------------------------" -echo "running userfaultfd_shmem" -echo "-------------------------" -./userfaultfd shmem 20 16 -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./mlock-random-test -#cleanup -umount $mnt -rm -rf $mnt -echo $nr_hugepgs > /proc/sys/vm/nr_hugepages - -echo "-----------------------" -echo "running compaction_test" -echo "-----------------------" -./compaction_test -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./mlock2-tests -echo "----------------------" -echo "running on-fault-limit" -echo "----------------------" -sudo -u nobody ./on-fault-limit -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./mrelease_test -echo "--------------------" -echo "running map_populate" -echo "--------------------" -./map_populate -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./mremap_test -echo "-------------------------" -echo "running mlock-random-test" -echo "-------------------------" -./mlock-random-test -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi - -echo "--------------------" -echo "running mlock2-tests" -echo "--------------------" -./mlock2-tests -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi - -echo "-------------------" -echo "running mremap_test" -echo "-------------------" -./mremap_test -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi - -echo "-----------------" -echo "running thuge-gen" -echo "-----------------" -./thuge-gen -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./thuge-gen if [ $VADDR64 -ne 0 ]; then -echo "-----------------------------" -echo "running virtual_address_range" -echo "-----------------------------" -./virtual_address_range -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi + run_test ./virtual_address_range -echo "-----------------------------" -echo "running virtual address 128TB switch test" -echo "-----------------------------" -./va_128TBswitch -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi + # virtual address 128TB switch test + run_test ./va_128TBswitch.sh fi # VADDR64 -echo "------------------------------------" -echo "running vmalloc stability smoke test" -echo "------------------------------------" -./test_vmalloc.sh smoke -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi - -echo "------------------------------------" -echo "running MREMAP_DONTUNMAP smoke test" -echo "------------------------------------" -./mremap_dontunmap -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi - -echo "running HMM smoke test" -echo "------------------------------------" -./test_hmm.sh smoke -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +# vmalloc stability smoke test +run_test ./test_vmalloc.sh smoke -echo "--------------------------------------------------------" -echo "running MADV_POPULATE_READ and MADV_POPULATE_WRITE tests" -echo "--------------------------------------------------------" -./madv_populate -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +run_test ./mremap_dontunmap -echo "running memfd_secret test" -echo "------------------------------------" -./memfd_secret -ret_val=$? +run_test ./test_hmm.sh smoke -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +# MADV_POPULATE_READ and MADV_POPULATE_WRITE tests +run_test ./madv_populate -echo "-------------------------------------------------------" -echo "running KSM MADV_MERGEABLE test with 10 identical pages" -echo "-------------------------------------------------------" -./ksm_tests -M -p 10 -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +run_test ./memfd_secret -echo "------------------------" -echo "running KSM unmerge test" -echo "------------------------" -./ksm_tests -U -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +# KSM MADV_MERGEABLE test with 10 identical pages +run_test ./ksm_tests -M -p 10 +# KSM unmerge test +run_test ./ksm_tests -U +# KSM test with 10 zero pages and use_zero_pages = 0 +run_test ./ksm_tests -Z -p 10 -z 0 +# KSM test with 10 zero pages and use_zero_pages = 1 +run_test ./ksm_tests -Z -p 10 -z 1 +# KSM test with 2 NUMA nodes and merge_across_nodes = 1 +run_test ./ksm_tests -N -m 1 +# KSM test with 2 NUMA nodes and merge_across_nodes = 0 +run_test ./ksm_tests -N -m 0 -echo "----------------------------------------------------------" -echo "running KSM test with 10 zero pages and use_zero_pages = 0" -echo "----------------------------------------------------------" -./ksm_tests -Z -p 10 -z 0 -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 +# protection_keys tests +if [ -x ./protection_keys_32 ] +then + run_test ./protection_keys_32 fi -echo "----------------------------------------------------------" -echo "running KSM test with 10 zero pages and use_zero_pages = 1" -echo "----------------------------------------------------------" -./ksm_tests -Z -p 10 -z 1 -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi - -echo "-------------------------------------------------------------" -echo "running KSM test with 2 NUMA nodes and merge_across_nodes = 1" -echo "-------------------------------------------------------------" -./ksm_tests -N -m 1 -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 +if [ -x ./protection_keys_64 ] +then + run_test ./protection_keys_64 fi -echo "-------------------------------------------------------------" -echo "running KSM test with 2 NUMA nodes and merge_across_nodes = 0" -echo "-------------------------------------------------------------" -./ksm_tests -N -m 0 -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi - -exit $exitcode +run_test ./soft-dirty exit $exitcode diff --git a/tools/testing/selftests/vm/settings b/tools/testing/selftests/vm/settings new file mode 100644 index 000000000000..9abfc60e9e6f --- /dev/null +++ b/tools/testing/selftests/vm/settings @@ -0,0 +1 @@ +timeout=45 diff --git a/tools/testing/selftests/vm/soft-dirty.c b/tools/testing/selftests/vm/soft-dirty.c new file mode 100644 index 000000000000..21d8830c5f24 --- /dev/null +++ b/tools/testing/selftests/vm/soft-dirty.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> +#include <stdbool.h> +#include <fcntl.h> +#include <stdint.h> +#include <malloc.h> +#include <sys/mman.h> +#include "../kselftest.h" +#include "vm_util.h" + +#define PAGEMAP_FILE_PATH "/proc/self/pagemap" +#define TEST_ITERATIONS 10000 + +static void test_simple(int pagemap_fd, int pagesize) +{ + int i; + char *map; + + map = aligned_alloc(pagesize, pagesize); + if (!map) + ksft_exit_fail_msg("mmap failed\n"); + + clear_softdirty(); + + for (i = 0 ; i < TEST_ITERATIONS; i++) { + if (pagemap_is_softdirty(pagemap_fd, map) == 1) { + ksft_print_msg("dirty bit was 1, but should be 0 (i=%d)\n", i); + break; + } + + clear_softdirty(); + // Write something to the page to get the dirty bit enabled on the page + map[0]++; + + if (pagemap_is_softdirty(pagemap_fd, map) == 0) { + ksft_print_msg("dirty bit was 0, but should be 1 (i=%d)\n", i); + break; + } + + clear_softdirty(); + } + free(map); + + ksft_test_result(i == TEST_ITERATIONS, "Test %s\n", __func__); +} + +static void test_vma_reuse(int pagemap_fd, int pagesize) +{ + char *map, *map2; + + map = mmap(NULL, pagesize, (PROT_READ | PROT_WRITE), (MAP_PRIVATE | MAP_ANON), -1, 0); + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap failed"); + + // The kernel always marks new regions as soft dirty + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 1, + "Test %s dirty bit of allocated page\n", __func__); + + clear_softdirty(); + munmap(map, pagesize); + + map2 = mmap(NULL, pagesize, (PROT_READ | PROT_WRITE), (MAP_PRIVATE | MAP_ANON), -1, 0); + if (map2 == MAP_FAILED) + ksft_exit_fail_msg("mmap failed"); + + // Dirty bit is set for new regions even if they are reused + if (map == map2) + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map2) == 1, + "Test %s dirty bit of reused address page\n", __func__); + else + ksft_test_result_skip("Test %s dirty bit of reused address page\n", __func__); + + munmap(map2, pagesize); +} + +static void test_hugepage(int pagemap_fd, int pagesize) +{ + char *map; + int i, ret; + size_t hpage_len = read_pmd_pagesize(); + + map = memalign(hpage_len, hpage_len); + if (!map) + ksft_exit_fail_msg("memalign failed\n"); + + ret = madvise(map, hpage_len, MADV_HUGEPAGE); + if (ret) + ksft_exit_fail_msg("madvise failed %d\n", ret); + + for (i = 0; i < hpage_len; i++) + map[i] = (char)i; + + if (check_huge_anon(map, 1, hpage_len)) { + ksft_test_result_pass("Test %s huge page allocation\n", __func__); + + clear_softdirty(); + for (i = 0 ; i < TEST_ITERATIONS ; i++) { + if (pagemap_is_softdirty(pagemap_fd, map) == 1) { + ksft_print_msg("dirty bit was 1, but should be 0 (i=%d)\n", i); + break; + } + + clear_softdirty(); + // Write something to the page to get the dirty bit enabled on the page + map[0]++; + + if (pagemap_is_softdirty(pagemap_fd, map) == 0) { + ksft_print_msg("dirty bit was 0, but should be 1 (i=%d)\n", i); + break; + } + clear_softdirty(); + } + + ksft_test_result(i == TEST_ITERATIONS, "Test %s huge page dirty bit\n", __func__); + } else { + // hugepage allocation failed. skip these tests + ksft_test_result_skip("Test %s huge page allocation\n", __func__); + ksft_test_result_skip("Test %s huge page dirty bit\n", __func__); + } + free(map); +} + +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; + char *map; + + if (anon) { + map = mmap(NULL, pagesize, PROT_READ|PROT_WRITE, + MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); + if (!map) + ksft_exit_fail_msg("anon mmap failed\n"); + } else { + test_fd = open(fname, O_RDWR | O_CREAT); + if (test_fd < 0) { + ksft_test_result_skip("Test %s open() file failed\n", __func__); + return; + } + unlink(fname); + ftruncate(test_fd, pagesize); + map = mmap(NULL, pagesize, PROT_READ|PROT_WRITE, + MAP_SHARED, test_fd, 0); + if (!map) + ksft_exit_fail_msg("file mmap failed\n"); + } + + *map = 1; + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 1, + "Test %s-%s dirty bit of new written page\n", + __func__, type[anon]); + clear_softdirty(); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 0, + "Test %s-%s soft-dirty clear after clear_refs\n", + __func__, type[anon]); + mprotect(map, pagesize, PROT_READ); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 0, + "Test %s-%s soft-dirty clear after marking RO\n", + __func__, type[anon]); + mprotect(map, pagesize, PROT_READ|PROT_WRITE); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 0, + "Test %s-%s soft-dirty clear after marking RW\n", + __func__, type[anon]); + *map = 2; + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 1, + "Test %s-%s soft-dirty after rewritten\n", + __func__, type[anon]); + + munmap(map, pagesize); + + if (!anon) + close(test_fd); +} + +static void test_mprotect_anon(int pagemap_fd, int pagesize) +{ + test_mprotect(pagemap_fd, pagesize, true); +} + +static void test_mprotect_file(int pagemap_fd, int pagesize) +{ + test_mprotect(pagemap_fd, pagesize, false); +} + +int main(int argc, char **argv) +{ + int pagemap_fd; + int pagesize; + + ksft_print_header(); + ksft_set_plan(15); + + pagemap_fd = open(PAGEMAP_FILE_PATH, O_RDONLY); + if (pagemap_fd < 0) + ksft_exit_fail_msg("Failed to open %s\n", PAGEMAP_FILE_PATH); + + pagesize = getpagesize(); + + test_simple(pagemap_fd, pagesize); + test_vma_reuse(pagemap_fd, pagesize); + test_hugepage(pagemap_fd, pagesize); + test_mprotect_anon(pagemap_fd, pagesize); + test_mprotect_file(pagemap_fd, pagesize); + + close(pagemap_fd); + + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c index 52497b7b9f1d..76e1c36dd9e5 100644 --- a/tools/testing/selftests/vm/split_huge_page_test.c +++ b/tools/testing/selftests/vm/split_huge_page_test.c @@ -16,14 +16,13 @@ #include <sys/mount.h> #include <malloc.h> #include <stdbool.h> +#include "vm_util.h" uint64_t pagesize; unsigned int pageshift; uint64_t pmd_pagesize; -#define PMD_SIZE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" #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" @@ -51,30 +50,6 @@ int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file) return 0; } - -static uint64_t read_pmd_pagesize(void) -{ - int fd; - char buf[20]; - ssize_t num_read; - - fd = open(PMD_SIZE_PATH, O_RDONLY); - if (fd == -1) { - perror("Open hpage_pmd_size failed"); - exit(EXIT_FAILURE); - } - num_read = read(fd, buf, 19); - if (num_read < 1) { - close(fd); - perror("Read hpage_pmd_size failed"); - exit(EXIT_FAILURE); - } - buf[num_read] = '\0'; - close(fd); - - return strtoul(buf, NULL, 10); -} - static int write_file(const char *path, const char *buf, size_t buflen) { int fd; @@ -113,63 +88,10 @@ static void write_debugfs(const char *fmt, ...) } } -#define MAX_LINE_LENGTH 500 - -static bool check_for_pattern(FILE *fp, const char *pattern, char *buf) -{ - while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) { - if (!strncmp(buf, pattern, strlen(pattern))) - return true; - } - return false; -} - -static uint64_t check_huge(void *addr) -{ - uint64_t thp = 0; - int ret; - FILE *fp; - char buffer[MAX_LINE_LENGTH]; - char addr_pattern[MAX_LINE_LENGTH]; - - ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", - (unsigned long) addr); - if (ret >= MAX_LINE_LENGTH) { - printf("%s: Pattern is too long\n", __func__); - exit(EXIT_FAILURE); - } - - - fp = fopen(SMAP_PATH, "r"); - if (!fp) { - printf("%s: Failed to open file %s\n", __func__, SMAP_PATH); - exit(EXIT_FAILURE); - } - if (!check_for_pattern(fp, addr_pattern, buffer)) - goto err_out; - - /* - * Fetch the AnonHugePages: in the same block and check the number of - * hugepages. - */ - if (!check_for_pattern(fp, "AnonHugePages:", buffer)) - goto err_out; - - if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) { - printf("Reading smap error\n"); - exit(EXIT_FAILURE); - } - -err_out: - fclose(fp); - return thp; -} - void split_pmd_thp(void) { char *one_page; size_t len = 4 * pmd_pagesize; - uint64_t thp_size; size_t i; one_page = memalign(pmd_pagesize, len); @@ -184,8 +106,7 @@ void split_pmd_thp(void) for (i = 0; i < len; i++) one_page[i] = (char)i; - thp_size = check_huge(one_page); - if (!thp_size) { + if (!check_huge_anon(one_page, 1, pmd_pagesize)) { printf("No THP is allocated\n"); exit(EXIT_FAILURE); } @@ -201,9 +122,8 @@ void split_pmd_thp(void) } - thp_size = check_huge(one_page); - if (thp_size) { - printf("Still %ld kB AnonHugePages not split\n", thp_size); + if (check_huge_anon(one_page, 0, pmd_pagesize)) { + printf("Still AnonHugePages not split\n"); exit(EXIT_FAILURE); } @@ -249,8 +169,7 @@ void split_pte_mapped_thp(void) for (i = 0; i < len; i++) one_page[i] = (char)i; - thp_size = check_huge(one_page); - if (!thp_size) { + if (!check_huge_anon(one_page, 1, pmd_pagesize)) { printf("No THP is allocated\n"); exit(EXIT_FAILURE); } diff --git a/tools/testing/selftests/vm/test_hmm.sh b/tools/testing/selftests/vm/test_hmm.sh index 0647b525a625..46e19b5d648d 100755 --- a/tools/testing/selftests/vm/test_hmm.sh +++ b/tools/testing/selftests/vm/test_hmm.sh @@ -40,25 +40,30 @@ check_test_requirements() load_driver() { - modprobe $DRIVER > /dev/null 2>&1 - if [ $? == 0 ]; then - major=$(awk "\$2==\"HMM_DMIRROR\" {print \$1}" /proc/devices) - mknod /dev/hmm_dmirror0 c $major 0 - mknod /dev/hmm_dmirror1 c $major 1 + if [ $# -eq 0 ]; then + modprobe $DRIVER > /dev/null 2>&1 + else + if [ $# -eq 2 ]; then + modprobe $DRIVER spm_addr_dev0=$1 spm_addr_dev1=$2 + > /dev/null 2>&1 + else + echo "Missing module parameters. Make sure pass"\ + "spm_addr_dev0 and spm_addr_dev1" + usage + fi fi } unload_driver() { modprobe -r $DRIVER > /dev/null 2>&1 - rm -f /dev/hmm_dmirror? } run_smoke() { echo "Running smoke test. Note, this test provides basic coverage." - load_driver + load_driver $1 $2 $(dirname "${BASH_SOURCE[0]}")/hmm-tests unload_driver } @@ -75,6 +80,9 @@ usage() echo "# Smoke testing" echo "./${TEST_NAME}.sh smoke" echo + echo "# Smoke testing with SPM enabled" + echo "./${TEST_NAME}.sh smoke <spm_addr_dev0> <spm_addr_dev1>" + echo exit 0 } @@ -84,7 +92,7 @@ function run_test() usage else if [ "$1" = "smoke" ]; then - run_smoke + run_smoke $2 $3 else usage fi diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c index 5e4c036f6ad3..e3f00adb1b82 100644 --- a/tools/testing/selftests/vm/transhuge-stress.c +++ b/tools/testing/selftests/vm/transhuge-stress.c @@ -15,67 +15,46 @@ #include <fcntl.h> #include <string.h> #include <sys/mman.h> +#include "util.h" -#define PAGE_SHIFT 12 -#define HPAGE_SHIFT 21 - -#define PAGE_SIZE (1 << PAGE_SHIFT) -#define HPAGE_SIZE (1 << HPAGE_SHIFT) - -#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) -#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) - -int pagemap_fd; - -int64_t allocate_transhuge(void *ptr) -{ - uint64_t ent[2]; - - /* drop pmd */ - if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_FIXED | MAP_ANONYMOUS | - MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) - errx(2, "mmap transhuge"); - - if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) - err(2, "MADV_HUGEPAGE"); - - /* allocate transparent huge page */ - *(volatile void **)ptr = ptr; - - if (pread(pagemap_fd, ent, sizeof(ent), - (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent)) - err(2, "read pagemap"); - - if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && - PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && - !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1))) - return PAGEMAP_PFN(ent[0]); - - return -1; -} +int backing_fd = -1; +int mmap_flags = MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE; +#define PROT_RW (PROT_READ | PROT_WRITE) int main(int argc, char **argv) { size_t ram, len; void *ptr, *p; struct timespec a, b; + int i = 0; + char *name = NULL; double s; uint8_t *map; size_t map_len; + int pagemap_fd; ram = sysconf(_SC_PHYS_PAGES); if (ram > SIZE_MAX / sysconf(_SC_PAGESIZE) / 4) ram = SIZE_MAX / 4; else ram *= sysconf(_SC_PAGESIZE); + len = ram; + + while (++i < argc) { + if (!strcmp(argv[i], "-h")) + errx(1, "usage: %s [size in MiB]", argv[0]); + else if (!strcmp(argv[i], "-f")) + name = argv[++i]; + else + len = atoll(argv[i]) << 20; + } - if (argc == 1) - len = ram; - else if (!strcmp(argv[1], "-h")) - errx(1, "usage: %s [size in MiB]", argv[0]); - else - len = atoll(argv[1]) << 20; + if (name) { + backing_fd = open(name, O_RDWR); + if (backing_fd == -1) + errx(2, "open %s", name); + mmap_flags = MAP_SHARED; + } warnx("allocate %zd transhuge pages, using %zd MiB virtual memory" " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20, @@ -86,8 +65,7 @@ int main(int argc, char **argv) err(2, "open pagemap"); len -= len % HPAGE_SIZE; - ptr = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0); + ptr = mmap(NULL, len + HPAGE_SIZE, PROT_RW, mmap_flags, backing_fd, 0); if (ptr == MAP_FAILED) err(2, "initial mmap"); ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE; @@ -109,7 +87,7 @@ int main(int argc, char **argv) for (p = ptr; p < ptr + len; p += HPAGE_SIZE) { int64_t pfn; - pfn = allocate_transhuge(p); + pfn = allocate_transhuge(p, pagemap_fd); if (pfn < 0) { nr_failed++; diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 8a09057d2f22..297f250c1d95 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -46,6 +46,7 @@ #include <signal.h> #include <poll.h> #include <string.h> +#include <linux/mman.h> #include <sys/mman.h> #include <sys/syscall.h> #include <sys/ioctl.h> @@ -60,10 +61,11 @@ #include <sys/random.h> #include "../kselftest.h" +#include "vm_util.h" #ifdef __NR_userfaultfd -static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; +static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size, hpage_size; #define BOUNCE_RANDOM (1<<0) #define BOUNCE_RACINGFAULTS (1<<1) @@ -76,25 +78,32 @@ static int bounces; #define TEST_SHMEM 3 static int test_type; +#define UFFD_FLAGS (O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY) + +#define BASE_PMD_ADDR ((void *)(1UL << 30)) + +/* test using /dev/userfaultfd, instead of userfaultfd(2) */ +static bool test_dev_userfaultfd; + /* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */ #define ALARM_INTERVAL_SECS 10 static volatile bool test_uffdio_copy_eexist = true; static volatile bool test_uffdio_zeropage_eexist = true; /* Whether to test uffd write-protection */ -static bool test_uffdio_wp = false; +static bool test_uffdio_wp = true; /* Whether to test uffd minor faults */ static bool test_uffdio_minor = false; static bool map_shared; static int shm_fd; static int huge_fd; -static char *huge_fd_off0; static unsigned long long *count_verify; static int uffd = -1; static int uffd_flags, finished, *pipefd; -static char *area_src, *area_src_alias, *area_dst, *area_dst_alias; +static char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; static char *zeropage; pthread_attr_t attr; +static bool test_collapse; /* Userfaultfd test statistics */ struct uffd_stats { @@ -119,14 +128,21 @@ struct uffd_stats { ~(unsigned long)(sizeof(unsigned long long) \ - 1))) +#define swap(a, b) \ + do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) + +#define factor_of_2(x) ((x) ^ ((x) & ((x) - 1))) + const char *examples = "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" "./userfaultfd anon 100 99999\n\n" + "# Run the same anonymous memory test, but using /dev/userfaultfd:\n" + "./userfaultfd anon:dev 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 (using /dev/hugepages/hugefile):\n" - "./userfaultfd hugetlb 256 50 /dev/hugepages/hugefile\n\n" - "# Run the same hugetlb test but using shmem:\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 shared file:\n" "./userfaultfd hugetlb_shared 256 50 /dev/hugepages/hugefile\n\n" "# 10MiB-~6GiB 999 bounces anonymous test, " "continue forever unless an error triggers\n" @@ -138,6 +154,16 @@ static void usage(void) "[hugetlbfs_file]\n\n"); fprintf(stderr, "Supported <test type>: anon, hugetlb, " "hugetlb_shared, shmem\n\n"); + fprintf(stderr, "'Test mods' can be joined to the test type string with a ':'. " + "Supported mods:\n"); + fprintf(stderr, "\tsyscall - Use userfaultfd(2) (default)\n"); + fprintf(stderr, "\tdev - Use /dev/userfaultfd instead of userfaultfd(2)\n"); + fprintf(stderr, "\tcollapse - Test MADV_COLLAPSE of UFFDIO_REGISTER_MODE_MINOR\n" + "memory\n"); + fprintf(stderr, "\nExample test mod usage:\n"); + fprintf(stderr, "# Run anonymous memory test with /dev/userfaultfd:\n"); + fprintf(stderr, "./userfaultfd anon:dev 100 99999\n\n"); + fprintf(stderr, "Examples:\n\n"); fprintf(stderr, "%s", examples); exit(1); @@ -151,12 +177,14 @@ static void usage(void) ret, __LINE__); \ } while (0) -#define err(fmt, ...) \ +#define errexit(exitcode, fmt, ...) \ do { \ _err(fmt, ##__VA_ARGS__); \ - exit(1); \ + exit(exitcode); \ } while (0) +#define err(fmt, ...) errexit(1, fmt, ##__VA_ARGS__) + static void uffd_stats_reset(struct uffd_stats *uffd_stats, unsigned long n_cpus) { @@ -209,12 +237,10 @@ static void anon_release_pages(char *rel_area) err("madvise(MADV_DONTNEED) failed"); } -static void anon_allocate_area(void **alloc_area) +static void anon_allocate_area(void **alloc_area, bool is_src) { *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (*alloc_area == MAP_FAILED) - err("mmap of anonymous memory failed"); } static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) @@ -223,36 +249,51 @@ static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) static void hugetlb_release_pages(char *rel_area) { - if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, - rel_area == huge_fd_off0 ? 0 : nr_pages * page_size, - nr_pages * page_size)) - err("fallocate() failed"); + if (!map_shared) { + if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + } else { + if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + err("madvise(MADV_REMOVE) failed"); + } } -static void hugetlb_allocate_area(void **alloc_area) +static void hugetlb_allocate_area(void **alloc_area, bool is_src) { void *area_alias = NULL; char **alloc_area_alias; - *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - (map_shared ? MAP_SHARED : MAP_PRIVATE) | - MAP_HUGETLB, - huge_fd, *alloc_area == area_src ? 0 : - nr_pages * page_size); + if (!map_shared) + *alloc_area = mmap(NULL, + nr_pages * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | + (is_src ? 0 : MAP_NORESERVE), + -1, + 0); + else + *alloc_area = mmap(NULL, + nr_pages * page_size, + PROT_READ | PROT_WRITE, + MAP_SHARED | + (is_src ? 0 : MAP_NORESERVE), + huge_fd, + is_src ? 0 : nr_pages * page_size); if (*alloc_area == MAP_FAILED) err("mmap of hugetlbfs file failed"); if (map_shared) { - area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_HUGETLB, - huge_fd, *alloc_area == area_src ? 0 : - nr_pages * page_size); + area_alias = mmap(NULL, + nr_pages * page_size, + PROT_READ | PROT_WRITE, + MAP_SHARED, + huge_fd, + is_src ? 0 : nr_pages * page_size); if (area_alias == MAP_FAILED) err("mmap of hugetlb file alias failed"); } - if (*alloc_area == area_src) { - huge_fd_off0 = *alloc_area; + if (is_src) { alloc_area_alias = &area_src_alias; } else { alloc_area_alias = &area_dst_alias; @@ -265,12 +306,7 @@ static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset { if (!map_shared) return; - /* - * We can't zap just the pagetable with hugetlbfs because - * MADV_DONTEED won't work. So exercise -EEXIST on a alias - * mapping where the pagetables are not established initially, - * this way we'll exercise the -EEXEC at the fs level. - */ + *start = (unsigned long) area_dst_alias + offset; } @@ -280,21 +316,36 @@ static void shmem_release_pages(char *rel_area) err("madvise(MADV_REMOVE) failed"); } -static void shmem_allocate_area(void **alloc_area) +static void shmem_allocate_area(void **alloc_area, bool is_src) { void *area_alias = NULL; - bool is_src = alloc_area == (void **)&area_src; - unsigned long offset = is_src ? 0 : nr_pages * page_size; + size_t bytes = nr_pages * page_size; + unsigned long offset = is_src ? 0 : bytes; + char *p = NULL, *p_alias = NULL; + + if (test_collapse) { + p = BASE_PMD_ADDR; + if (!is_src) + /* src map + alias + interleaved hpages */ + p += 2 * (bytes + hpage_size); + p_alias = p; + p_alias += bytes; + p_alias += hpage_size; /* Prevent src/dst VMA merge */ + } - *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - MAP_SHARED, shm_fd, offset); + *alloc_area = mmap(p, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, + shm_fd, offset); if (*alloc_area == MAP_FAILED) err("mmap of memfd failed"); + if (test_collapse && *alloc_area != p) + err("mmap of memfd failed at %p", p); - area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - MAP_SHARED, shm_fd, offset); + area_alias = mmap(p_alias, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, + shm_fd, offset); if (area_alias == MAP_FAILED) err("mmap of memfd alias failed"); + if (test_collapse && area_alias != p_alias) + err("mmap of anonymous memory failed at %p", p_alias); if (is_src) area_src_alias = area_alias; @@ -307,28 +358,39 @@ static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) *start = (unsigned long)area_dst_alias + offset; } +static void shmem_check_pmd_mapping(void *p, int expect_nr_hpages) +{ + if (!check_huge_shmem(area_dst_alias, expect_nr_hpages, hpage_size)) + err("Did not find expected %d number of hugepages", + expect_nr_hpages); +} + struct uffd_test_ops { - void (*allocate_area)(void **alloc_area); + void (*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); }; static struct uffd_test_ops anon_uffd_test_ops = { .allocate_area = anon_allocate_area, .release_pages = anon_release_pages, .alias_mapping = noop_alias_mapping, + .check_pmd_mapping = NULL, }; static struct uffd_test_ops shmem_uffd_test_ops = { .allocate_area = shmem_allocate_area, .release_pages = shmem_release_pages, .alias_mapping = shmem_alias_mapping, + .check_pmd_mapping = shmem_check_pmd_mapping, }; static struct uffd_test_ops hugetlb_uffd_test_ops = { .allocate_area = hugetlb_allocate_area, .release_pages = hugetlb_release_pages, .alias_mapping = hugetlb_alias_mapping, + .check_pmd_mapping = NULL, }; static struct uffd_test_ops *uffd_test_ops; @@ -370,13 +432,34 @@ static void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls) } } +static int __userfaultfd_open_dev(void) +{ + int fd, _uffd; + + fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); + if (fd < 0) + errexit(KSFT_SKIP, "opening /dev/userfaultfd failed"); + + _uffd = ioctl(fd, USERFAULTFD_IOC_NEW, UFFD_FLAGS); + if (_uffd < 0) + errexit(errno == ENOTTY ? KSFT_SKIP : 1, + "creating userfaultfd failed"); + close(fd); + return _uffd; +} + static void userfaultfd_open(uint64_t *features) { struct uffdio_api uffdio_api; - uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY); - if (uffd < 0) - err("userfaultfd syscall not available in this kernel"); + if (test_dev_userfaultfd) + uffd = __userfaultfd_open_dev(); + else { + uffd = syscall(__NR_userfaultfd, UFFD_FLAGS); + if (uffd < 0) + errexit(errno == ENOSYS ? KSFT_SKIP : 1, + "creating userfaultfd failed"); + } uffd_flags = fcntl(uffd, F_GETFD, NULL); uffdio_api.api = UFFD_API; @@ -423,11 +506,11 @@ static void uffd_test_ctx_clear(void) uffd = -1; } - huge_fd_off0 = NULL; 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); } static void uffd_test_ctx_init(uint64_t features) @@ -436,8 +519,8 @@ static void uffd_test_ctx_init(uint64_t features) uffd_test_ctx_clear(); - uffd_test_ops->allocate_area((void **)&area_src); - uffd_test_ops->allocate_area((void **)&area_dst); + uffd_test_ops->allocate_area((void **)&area_src, true); + uffd_test_ops->allocate_area((void **)&area_dst, false); userfaultfd_open(&features); @@ -538,7 +621,7 @@ static void continue_range(int ufd, __u64 start, __u64 len) static void *locking_thread(void *arg) { unsigned long cpu = (unsigned long) arg; - unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */ + unsigned long page_nr; unsigned long long count; if (!(bounces & BOUNCE_RANDOM)) { @@ -644,7 +727,7 @@ static int uffd_read_msg(int ufd, struct uffd_msg *msg) if (ret != sizeof(*msg)) { if (ret < 0) { - if (errno == EAGAIN) + if (errno == EAGAIN || errno == EINTR) return 1; err("blocking read error"); } else { @@ -691,7 +774,27 @@ static void uffd_handle_page_fault(struct uffd_msg *msg, continue_range(uffd, msg->arg.pagefault.address, page_size); stats->minor_faults++; } else { - /* Missing page faults */ + /* + * Missing page faults. + * + * Here we force a write check for each of the missing mode + * faults. It's guaranteed because the only threads that + * will trigger uffd faults are the locking threads, and + * their first instruction to touch the missing page will + * always be pthread_mutex_lock(). + * + * Note that here we relied on an NPTL glibc impl detail to + * always read the lock type at the entry of the lock op + * (pthread_mutex_t.__data.__type, offset 0x10) before + * doing any locking operations to guarantee that. It's + * actually not good to rely on this impl detail because + * logically a pthread-compatible lib can implement the + * locks without types and we can fail when linking with + * them. However since we used to find bugs with this + * strict check we still keep it around. Hopefully this + * could be a good hint when it fails again. If one day + * it'll break on some other impl of glibc we'll revisit. + */ if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) err("unexpected write fault"); @@ -720,8 +823,11 @@ static void *uffd_poll_thread(void *arg) for (;;) { ret = poll(pollfd, 2, -1); - if (ret <= 0) + if (ret <= 0) { + if (errno == EINTR || errno == EAGAIN) + continue; err("poll error: %d", ret); + } if (pollfd[1].revents & POLLIN) { if (read(pollfd[1].fd, &tmp_chr, 1) != 1) err("read pipefd error"); @@ -751,6 +857,7 @@ static void *uffd_poll_thread(void *arg) 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; break; } @@ -845,7 +952,7 @@ static int stress(struct uffd_stats *uffd_stats) /* * Be strict and immediately zap area_src, the whole area has * been transferred already by the background treads. The - * area_src could then be faulted in in a racy way by still + * area_src could then be faulted in a racy way by still * running uffdio_threads reading zeropages after we zapped * area_src (but they're guaranteed to get -EEXIST from * UFFDIO_COPY without writing zero pages into area_dst @@ -916,12 +1023,9 @@ static int faulting_process(int signal_test) unsigned long split_nr_pages; unsigned long lastnr; struct sigaction act; - unsigned long signalled = 0; + volatile unsigned long signalled = 0; - if (test_type != TEST_HUGETLB) - split_nr_pages = (nr_pages + 1) / 2; - else - split_nr_pages = nr_pages; + split_nr_pages = (nr_pages + 1) / 2; if (signal_test) { sigbuf = &jbuf; @@ -934,7 +1038,7 @@ static int faulting_process(int signal_test) } for (nr = 0; nr < split_nr_pages; nr++) { - int steps = 1; + volatile int steps = 1; unsigned long offset = nr * page_size; if (signal_test) { @@ -978,9 +1082,6 @@ static int faulting_process(int signal_test) if (signal_test) return signalled != split_nr_pages; - if (test_type == TEST_HUGETLB) - return 0; - area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, area_src); if (area_dst == MAP_FAILED) @@ -1209,13 +1310,30 @@ static int userfaultfd_sig_test(void) return userfaults != 0; } +void check_memory_contents(char *p) +{ + unsigned long i; + uint8_t expected_byte; + void *expected_page; + + if (posix_memalign(&expected_page, page_size, page_size)) + err("out of memory"); + + for (i = 0; i < nr_pages; ++i) { + expected_byte = ~((uint8_t)(i % ((uint8_t)-1))); + memset(expected_page, expected_byte, page_size); + if (my_bcmp(expected_page, p + (i * page_size), page_size)) + err("unexpected page contents after minor fault"); + } + + free(expected_page); +} + static int userfaultfd_minor_test(void) { - struct uffdio_register uffdio_register; unsigned long p; + struct uffdio_register uffdio_register; pthread_t uffd_mon; - uint8_t expected_byte; - void *expected_page; char c; struct uffd_stats stats = { 0 }; @@ -1254,17 +1372,7 @@ static int userfaultfd_minor_test(void) * fault. uffd_poll_thread will resolve the fault by bit-flipping the * page's contents, and then issuing a CONTINUE ioctl. */ - - if (posix_memalign(&expected_page, page_size, page_size)) - err("out of memory"); - - for (p = 0; p < nr_pages; ++p) { - expected_byte = ~((uint8_t)(p % ((uint8_t)-1))); - memset(expected_page, expected_byte, page_size); - if (my_bcmp(expected_page, area_dst_alias + (p * page_size), - page_size)) - err("unexpected page contents after minor fault"); - } + check_memory_contents(area_dst_alias); if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); @@ -1273,6 +1381,23 @@ static int userfaultfd_minor_test(void) uffd_stats_report(&stats, 1); + if (test_collapse) { + printf("testing collapse of uffd memory into PMD-mapped THPs:"); + if (madvise(area_dst_alias, nr_pages * page_size, + MADV_COLLAPSE)) + err("madvise(MADV_COLLAPSE)"); + + uffd_test_ops->check_pmd_mapping(area_dst, + nr_pages * page_size / + hpage_size); + /* + * This won't cause uffd-fault - it purely just makes sure there + * was no corruption. + */ + check_memory_contents(area_dst_alias); + printf(" done.\n"); + } + return stats.missing_faults != 0 || stats.minor_faults != nr_pages; } @@ -1413,7 +1538,6 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) static int userfaultfd_stress(void) { void *area; - char *tmp_area; unsigned long nr; struct uffdio_register uffdio_register; struct uffd_stats uffd_stats[nr_cpus]; @@ -1524,13 +1648,9 @@ static int userfaultfd_stress(void) count_verify[nr], nr); /* prepare next bounce */ - tmp_area = area_src; - area_src = area_dst; - area_dst = tmp_area; + swap(area_src, area_dst); - tmp_area = area_src_alias; - area_src_alias = area_dst_alias; - area_dst_alias = tmp_area; + swap(area_src_alias, area_dst_alias); uffd_stats_report(uffd_stats, nr_cpus); } @@ -1580,13 +1700,9 @@ unsigned long default_huge_page_size(void) static void set_test_type(const char *type) { - uint64_t features = UFFD_API_FEATURES; - if (!strcmp(type, "anon")) { test_type = TEST_ANON; uffd_test_ops = &anon_uffd_test_ops; - /* Only enable write-protect test for anonymous test */ - test_uffdio_wp = true; } else if (!strcmp(type, "hugetlb")) { test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; @@ -1601,12 +1717,37 @@ static void set_test_type(const char *type) test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; test_uffdio_minor = true; - } else { - err("Unknown test type: %s", type); + } +} + +static void parse_test_type_arg(const char *raw_type) +{ + char *buf = strdup(raw_type); + uint64_t features = UFFD_API_FEATURES; + + while (buf) { + const char *token = strsep(&buf, ":"); + + if (!test_type) + set_test_type(token); + else if (!strcmp(token, "dev")) + test_dev_userfaultfd = true; + else if (!strcmp(token, "syscall")) + test_dev_userfaultfd = false; + else if (!strcmp(token, "collapse")) + test_collapse = true; + else + err("unrecognized test mod '%s'", token); } + if (!test_type) + err("failed to parse test type argument: '%s'", raw_type); + + if (test_collapse && test_type != TEST_SHMEM) + err("Unsupported test: %s", raw_type); + if (test_type == TEST_HUGETLB) - page_size = default_huge_page_size(); + page_size = hpage_size; else page_size = sysconf(_SC_PAGE_SIZE); @@ -1644,6 +1785,8 @@ static void sigalrm(int sig) int main(int argc, char **argv) { + size_t bytes; + if (argc < 4) usage(); @@ -1651,11 +1794,41 @@ int main(int argc, char **argv) err("failed to arm SIGALRM"); alarm(ALARM_INTERVAL_SECS); - set_test_type(argv[1]); + hpage_size = default_huge_page_size(); + parse_test_type_arg(argv[1]); + bytes = atol(argv[2]) * 1024 * 1024; + + if (test_collapse && bytes & (hpage_size - 1)) + err("MiB must be multiple of %lu if :collapse mod set", + hpage_size >> 20); nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); - nr_pages_per_cpu = atol(argv[2]) * 1024*1024 / page_size / - nr_cpus; + + if (test_collapse) { + /* nr_cpus must divide (bytes / page_size), otherwise, + * area allocations of (nr_pages * paze_size) won't be a + * multiple of hpage_size, even if bytes is a multiple of + * hpage_size. + * + * This means that nr_cpus must divide (N * (2 << (H-P)) + * where: + * bytes = hpage_size * N + * hpage_size = 2 << H + * page_size = 2 << P + * + * And we want to chose nr_cpus to be the largest value + * satisfying this constraint, not larger than the number + * of online CPUs. Unfortunately, prime factorization of + * N and nr_cpus may be arbitrary, so have to search for it. + * Instead, just use the highest power of 2 dividing both + * nr_cpus and (bytes / page_size). + */ + int x = factor_of_2(nr_cpus); + int y = factor_of_2(bytes / page_size); + + nr_cpus = x < y ? x : y; + } + nr_pages_per_cpu = bytes / page_size / nr_cpus; if (!nr_pages_per_cpu) { _err("invalid MiB"); usage(); @@ -1668,7 +1841,7 @@ int main(int argc, char **argv) } nr_pages = nr_pages_per_cpu * nr_cpus; - if (test_type == TEST_HUGETLB) { + if (test_type == TEST_HUGETLB && map_shared) { if (argc < 5) usage(); huge_fd = open(argv[4], O_CREAT | O_RDWR, 0755); diff --git a/tools/testing/selftests/vm/util.h b/tools/testing/selftests/vm/util.h new file mode 100644 index 000000000000..b27d26199334 --- /dev/null +++ b/tools/testing/selftests/vm/util.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __KSELFTEST_VM_UTIL_H +#define __KSELFTEST_VM_UTIL_H + +#include <stdint.h> +#include <sys/mman.h> +#include <err.h> +#include <string.h> /* ffsl() */ +#include <unistd.h> /* _SC_PAGESIZE */ + +static unsigned int __page_size; +static unsigned int __page_shift; + +static inline unsigned int page_size(void) +{ + if (!__page_size) + __page_size = sysconf(_SC_PAGESIZE); + return __page_size; +} + +static inline unsigned int page_shift(void) +{ + if (!__page_shift) + __page_shift = (ffsl(page_size()) - 1); + return __page_shift; +} + +#define PAGE_SHIFT (page_shift()) +#define PAGE_SIZE (page_size()) +/* + * On ppc64 this will only work with radix 2M hugepage size + */ +#define HPAGE_SHIFT 21 +#define HPAGE_SIZE (1 << HPAGE_SHIFT) + +#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) +#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) + + +static inline int64_t allocate_transhuge(void *ptr, int pagemap_fd) +{ + uint64_t ent[2]; + + /* drop pmd */ + if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANONYMOUS | + MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) + errx(2, "mmap transhuge"); + + if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) + err(2, "MADV_HUGEPAGE"); + + /* allocate transparent huge page */ + *(volatile void **)ptr = ptr; + + if (pread(pagemap_fd, ent, sizeof(ent), + (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent)) + err(2, "read pagemap"); + + if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && + PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && + !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1))) + return PAGEMAP_PFN(ent[0]); + + return -1; +} + +#endif diff --git a/tools/testing/selftests/vm/va_128TBswitch.c b/tools/testing/selftests/vm/va_128TBswitch.c index 83acdff26a13..1d2068989883 100644 --- a/tools/testing/selftests/vm/va_128TBswitch.c +++ b/tools/testing/selftests/vm/va_128TBswitch.c @@ -9,7 +9,7 @@ #include <sys/mman.h> #include <string.h> -#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) +#include "../kselftest.h" #ifdef __powerpc64__ #define PAGE_SIZE (64 << 10) @@ -231,7 +231,7 @@ static struct testcase hugetlb_testcases[] = { static int run_test(struct testcase *test, int count) { void *p; - int i, ret = 0; + int i, ret = KSFT_PASS; for (i = 0; i < count; i++) { struct testcase *t = test + i; @@ -242,13 +242,13 @@ static int run_test(struct testcase *test, int count) if (p == MAP_FAILED) { printf("FAILED\n"); - ret = 1; + ret = KSFT_FAIL; continue; } if (t->low_addr_required && p >= (void *)(ADDR_SWITCH_HINT)) { printf("FAILED\n"); - ret = 1; + ret = KSFT_FAIL; } else { /* * Do a dereference of the address returned so that we catch @@ -280,7 +280,7 @@ int main(int argc, char **argv) int ret; if (!supported_arch()) - return 0; + return KSFT_SKIP; ret = run_test(testcases, ARRAY_SIZE(testcases)); if (argc == 2 && !strcmp(argv[1], "--run-hugetlb")) diff --git a/tools/testing/selftests/vm/va_128TBswitch.sh b/tools/testing/selftests/vm/va_128TBswitch.sh new file mode 100755 index 000000000000..41580751dc51 --- /dev/null +++ b/tools/testing/selftests/vm/va_128TBswitch.sh @@ -0,0 +1,54 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2022 Adam Sindelar (Meta) <adam@wowsignal.io> +# +# This is a test for mmap behavior with 5-level paging. This script wraps the +# 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 + +fail() +{ + echo "$1" + exit $exitcode +} + +check_supported_x86_64() +{ + local config="/proc/config.gz" + [[ -f "${config}" ]] || config="/boot/config-$(uname -r)" + [[ -f "${config}" ]] || fail "Cannot find kernel config in /proc or /boot" + + # 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) + + if [[ "${pg_table_levels}" -lt 5 ]]; then + echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test" + exit $ksft_skip + fi +} + +check_test_requirements() +{ + # The test supports x86_64 and powerpc64. We currently have no useful + # eligibility check for powerpc64, and the test itself will reject other + # architectures. + case `uname -m` in + "x86_64") + check_supported_x86_64 + ;; + *) + return 0 + ;; + esac +} + +check_test_requirements +./va_128TBswitch diff --git a/tools/testing/selftests/vm/vm_util.c b/tools/testing/selftests/vm/vm_util.c new file mode 100644 index 000000000000..f11f8adda521 --- /dev/null +++ b/tools/testing/selftests/vm/vm_util.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include <fcntl.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 MAX_LINE_LENGTH 500 + +uint64_t pagemap_get_entry(int fd, char *start) +{ + const unsigned long pfn = (unsigned long)start / getpagesize(); + uint64_t entry; + int ret; + + ret = pread(fd, &entry, sizeof(entry), pfn * sizeof(entry)); + if (ret != sizeof(entry)) + ksft_exit_fail_msg("reading pagemap failed\n"); + return entry; +} + +bool pagemap_is_softdirty(int fd, char *start) +{ + uint64_t entry = pagemap_get_entry(fd, start); + + // Check if dirty bit (55th bit) is set + return entry & 0x0080000000000000ull; +} + +void clear_softdirty(void) +{ + int ret; + const char *ctrl = "4"; + int fd = open("/proc/self/clear_refs", O_WRONLY); + + if (fd < 0) + ksft_exit_fail_msg("opening clear_refs failed\n"); + ret = write(fd, ctrl, strlen(ctrl)); + close(fd); + if (ret != strlen(ctrl)) + ksft_exit_fail_msg("writing clear_refs failed\n"); +} + +bool check_for_pattern(FILE *fp, const char *pattern, char *buf, size_t len) +{ + while (fgets(buf, len, fp)) { + if (!strncmp(buf, pattern, strlen(pattern))) + return true; + } + return false; +} + +uint64_t read_pmd_pagesize(void) +{ + int fd; + char buf[20]; + ssize_t num_read; + + fd = open(PMD_SIZE_FILE_PATH, O_RDONLY); + if (fd == -1) + ksft_exit_fail_msg("Open hpage_pmd_size failed\n"); + + num_read = read(fd, buf, 19); + if (num_read < 1) { + close(fd); + ksft_exit_fail_msg("Read hpage_pmd_size failed\n"); + } + buf[num_read] = '\0'; + close(fd); + + return strtoul(buf, NULL, 10); +} + +bool __check_huge(void *addr, char *pattern, int nr_hpages, + uint64_t hpage_size) +{ + uint64_t thp = -1; + int ret; + FILE *fp; + char buffer[MAX_LINE_LENGTH]; + char addr_pattern[MAX_LINE_LENGTH]; + + ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", + (unsigned long) addr); + if (ret >= MAX_LINE_LENGTH) + ksft_exit_fail_msg("%s: Pattern is too long\n", __func__); + + fp = fopen(SMAP_FILE_PATH, "r"); + 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))) + 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))) + goto err_out; + + snprintf(addr_pattern, MAX_LINE_LENGTH, "%s%%9ld kB", pattern); + + if (sscanf(buffer, addr_pattern, &thp) != 1) + ksft_exit_fail_msg("Reading smap error\n"); + +err_out: + fclose(fp); + return thp == (nr_hpages * (hpage_size >> 10)); +} + +bool check_huge_anon(void *addr, int nr_hpages, uint64_t hpage_size) +{ + return __check_huge(addr, "AnonHugePages: ", nr_hpages, hpage_size); +} + +bool check_huge_file(void *addr, int nr_hpages, uint64_t hpage_size) +{ + return __check_huge(addr, "FilePmdMapped:", nr_hpages, hpage_size); +} + +bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size) +{ + return __check_huge(addr, "ShmemPmdMapped:", nr_hpages, hpage_size); +} diff --git a/tools/testing/selftests/vm/vm_util.h b/tools/testing/selftests/vm/vm_util.h new file mode 100644 index 000000000000..5c35de454e08 --- /dev/null +++ b/tools/testing/selftests/vm/vm_util.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <stdint.h> +#include <stdbool.h> + +uint64_t pagemap_get_entry(int fd, char *start); +bool pagemap_is_softdirty(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); +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); diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/vm/write_hugetlb_memory.sh index d3d0d108924d..70a02301f4c2 100644 --- a/tools/testing/selftests/vm/write_hugetlb_memory.sh +++ b/tools/testing/selftests/vm/write_hugetlb_memory.sh @@ -14,7 +14,7 @@ want_sleep=$8 reserve=$9 echo "Putting task in cgroup '$cgroup'" -echo $$ > /dev/cgroup/memory/"$cgroup"/cgroup.procs +echo $$ > ${cgroup_path:-/dev/cgroup/memory}/"$cgroup"/cgroup.procs echo "Method is $method" |