- Linux-kselftest-mirror - lists.linaro.org

[PATCH][RESEND] selftests: splice: Adjust for handler fallback removal

by Kees Cook

Some pseudo-filesystems do not have an explicit splice fops since adding commit 36e2c7421f02 ("fs: don't allow splice read/write without explicit ops"), and now will reject attempts to use splice() in those filesystem paths. Reported-by: kernel test robot <rong.a.chen(a)intel.com> Link: https://lore.kernel.org/lkml/202009181443.C2179FB@keescook/ Fixes: 36e2c7421f02 ("fs: don't allow splice read/write without explicit ops") Cc: Christoph Hellwig <hch(a)lst.de> Cc: Shuah Khan <shuah(a)kernel.org> Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Kees Cook <keescook(a)chromium.org> --- Resend of https://lore.kernel.org/linux-kselftest/20201005204517.2652730-1-keescook@c… --- .../selftests/splice/short_splice_read.sh | 119 ++++++++++++++---- 1 file changed, 98 insertions(+), 21 deletions(-) diff --git a/tools/testing/selftests/splice/short_splice_read.sh b/tools/testing/selftests/splice/short_splice_read.sh index 7810d3589d9a..22b6c8910b18 100755 --- a/tools/testing/selftests/splice/short_splice_read.sh +++ b/tools/testing/selftests/splice/short_splice_read.sh @@ -1,21 +1,87 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 +# +# Test for mishandling of splice() on pseudofilesystems, which should catch +# bugs like 11990a5bd7e5 ("module: Correctly truncate sysfs sections output") +# +# Since splice fallback was removed as part of the set_fs() rework, many of these +# tests expect to fail now. See https://lore.kernel.org/lkml/202009181443.C2179FB@keescook/ set -e +DIR=$(dirname "$0") + ret=0 +expect_success() +{ + title="$1" + shift + + echo "" >&2 + echo "$title ..." >&2 + + set +e + "$@" + rc=$? + set -e + + case "$rc" in + 0) + echo "ok: $title succeeded" >&2 + ;; + 1) + echo "FAIL: $title should work" >&2 + ret=$(( ret + 1 )) + ;; + *) + echo "FAIL: something else went wrong" >&2 + ret=$(( ret + 1 )) + ;; + esac +} + +expect_failure() +{ + title="$1" + shift + + echo "" >&2 + echo "$title ..." >&2 + + set +e + "$@" + rc=$? + set -e + + case "$rc" in + 0) + echo "FAIL: $title unexpectedly worked" >&2 + ret=$(( ret + 1 )) + ;; + 1) + echo "ok: $title correctly failed" >&2 + ;; + *) + echo "FAIL: something else went wrong" >&2 + ret=$(( ret + 1 )) + ;; + esac +} + do_splice() { filename="$1" bytes="$2" expected="$3" + report="$4" - out=$(./splice_read "$filename" "$bytes" | cat) + out=$("$DIR"/splice_read "$filename" "$bytes" | cat) if [ "$out" = "$expected" ] ; then - echo "ok: $filename $bytes" + echo " matched $report" >&2 + return 0 else - echo "FAIL: $filename $bytes" - ret=1 + echo " no match: '$out' vs $report" >&2 + return 1 fi } @@ -23,34 +89,45 @@ test_splice() { filename="$1" + echo " checking $filename ..." >&2 + full=$(cat "$filename") + rc=$? + if [ $rc -ne 0 ] ; then + return 2 + fi + two=$(echo "$full" | grep -m1 . | cut -c-2) # Make sure full splice has the same contents as a standard read. - do_splice "$filename" 4096 "$full" + echo " splicing 4096 bytes ..." >&2 + if ! do_splice "$filename" 4096 "$full" "full read" ; then + return 1 + fi # Make sure a partial splice see the first two characters. - do_splice "$filename" 2 "$two" + echo " splicing 2 bytes ..." >&2 + if ! do_splice "$filename" 2 "$two" "'$two'" ; then + return 1 + fi + + return 0 } -# proc_single_open(), seq_read() -test_splice /proc/$$/limits -# special open, seq_read() -test_splice /proc/$$/comm +### /proc/$pid/ has no splice interface; these should all fail. +expect_failure "proc_single_open(), seq_read() splice" test_splice /proc/$$/limits +expect_failure "special open(), seq_read() splice" test_splice /proc/$$/comm -# proc_handler, proc_dointvec_minmax -test_splice /proc/sys/fs/nr_open -# proc_handler, proc_dostring -test_splice /proc/sys/kernel/modprobe -# proc_handler, special read -test_splice /proc/sys/kernel/version +### /proc/sys/ has a splice interface; these should all succeed. +expect_success "proc_handler: proc_dointvec_minmax() splice" test_splice /proc/sys/fs/nr_open +expect_success "proc_handler: proc_dostring() splice" test_splice /proc/sys/kernel/modprobe +expect_success "proc_handler: special read splice" test_splice /proc/sys/kernel/version +### /sys/ has no splice interface; these should all fail. if ! [ -d /sys/module/test_module/sections ] ; then - modprobe test_module + expect_success "test_module kernel module load" modprobe test_module fi -# kernfs, attr -test_splice /sys/module/test_module/coresize -# kernfs, binattr -test_splice /sys/module/test_module/sections/.init.text +expect_failure "kernfs attr splice" test_splice /sys/module/test_module/coresize +expect_failure "kernfs binattr splice" test_splice /sys/module/test_module/sections/.init.text exit $ret -- 2.25.1

4 years

2
1
0 0

[PATCH] selftests: lib.mk: Also install "config" and "settings"

by Kees Cook

Installed seccomp tests would time out because the "settings" file was missing. Install both "settings" (needed for proper test execution) and "config" (needed for informational purposes) with the other test targets. Signed-off-by: Kees Cook <keescook(a)chromium.org> --- tools/testing/selftests/lib.mk | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 0af84ad48aa7..fa2ac0e56b43 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -100,6 +100,7 @@ define INSTALL_RULE $(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE) $(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE) $(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(wildcard config settings)) $(INSTALL_SINGLE_RULE) endef install: all -- 2.25.1

4 years

2
1
0 0

[PATCH AUTOSEL 5.12 37/43] bpf, selftests: Adjust few selftest result_unpriv outcomes

by Sasha Levin

From: Daniel Borkmann <daniel(a)iogearbox.net> [ Upstream commit 1bad6fd52be4ce12d207e2820ceb0f29ab31fc53 ] Given we don't need to simulate the speculative domain for registers with immediates anymore since the verifier uses direct imm-based rewrites instead of having to mask, we can also lift a few cases that were previously rejected. Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Acked-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/verifier/stack_ptr.c | 2 -- tools/testing/selftests/bpf/verifier/value_ptr_arith.c | 8 -------- 2 files changed, 10 deletions(-) diff --git a/tools/testing/selftests/bpf/verifier/stack_ptr.c b/tools/testing/selftests/bpf/verifier/stack_ptr.c index 07eaa04412ae..8ab94d65f3d5 100644 --- a/tools/testing/selftests/bpf/verifier/stack_ptr.c +++ b/tools/testing/selftests/bpf/verifier/stack_ptr.c @@ -295,8 +295,6 @@ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), BPF_EXIT_INSN(), }, - .result_unpriv = REJECT, - .errstr_unpriv = "invalid write to stack R1 off=0 size=1", .result = ACCEPT, .retval = 42, }, diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index e5913fd3b903..7ae2859d495c 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -300,8 +300,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -371,8 +369,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -472,8 +468,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -766,8 +760,6 @@ }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { -- 2.30.2

4 years

1
0
0 0

[PATCH] proc: Add .gitignore for proc-subset-pid selftest

by David Matlack

This new selftest needs an entry in the .gitignore file otherwise git will try to track the binary. Signed-off-by: David Matlack <dmatlack(a)google.com> --- tools/testing/selftests/proc/.gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore index bed4b5318a86..8f3e72e626fa 100644 --- a/tools/testing/selftests/proc/.gitignore +++ b/tools/testing/selftests/proc/.gitignore @@ -10,6 +10,7 @@ /proc-self-map-files-002 /proc-self-syscall /proc-self-wchan +/proc-subset-pid /proc-uptime-001 /proc-uptime-002 /read -- 2.32.0.rc0.204.g9fa02ecfa5-goog

4 years

3
2
0 0

[PATCH 0/2] selftests: futex: Expand futex testing

by André Almeida

This patchset expands test coverage for futex, implementing two new selftests: one for testing different types of futexes and one for the requeue operation. André Almeida (2): selftests: futex: Add futex wait test selftests: futex: Add futex compare requeue test .../selftests/futex/functional/.gitignore | 2 + .../selftests/futex/functional/Makefile | 4 +- .../futex/functional/futex_requeue.c | 145 ++++++++++++++ .../selftests/futex/functional/futex_wait.c | 180 ++++++++++++++++++ .../testing/selftests/futex/functional/run.sh | 6 + 5 files changed, 336 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/futex/functional/futex_requeue.c create mode 100644 tools/testing/selftests/futex/functional/futex_wait.c -- 2.31.1

4 years

2
3
0 0

[PATCH net-next v4 0/3] net/sched: act_vlan: Fix modify to allow 0

by Boris Sukholitko

Currently vlan modification action checks existence of vlan priority by comparing it to 0. Therefore it is impossible to modify existing vlan tag to have priority 0. For example, the following tc command will change the vlan id but will not affect vlan priority: tc filter add dev eth1 ingress matchall action vlan modify id 300 \ priority 0 pipe mirred egress redirect dev eth2 The incoming packet on eth1: ethertype 802.1Q (0x8100), vlan 200, p 4, ethertype IPv4 will be changed to: ethertype 802.1Q (0x8100), vlan 300, p 4, ethertype IPv4 although the user has intended to have p == 0. The fix is to add tcfv_push_prio_exists flag to struct tcf_vlan_params and rely on it when deciding to set the priority. The same flag is used to avoid dumping unset vlan priority. Change Log: v3 -> v4: - revert tcf_vlan_get_fill_size change: total size calculation may race vs dump v2 -> v3: - Push assumes that the priority is being set - tcf_vlan_get_fill_size accounts for priority existence v1 -> v2: - Do not dump unset priority and fix tests accordingly - Test for priority 0 modification Boris Sukholitko (3): net/sched: act_vlan: Fix modify to allow 0 net/sched: act_vlan: No dump for unset priority net/sched: act_vlan: Test priority 0 modification include/net/tc_act/tc_vlan.h | 1 + net/sched/act_vlan.c | 11 +++++--- .../tc-testing/tc-tests/actions/vlan.json | 28 +++++++++++++++++-- 3 files changed, 34 insertions(+), 6 deletions(-) -- 2.29.3

4 years

3
5
0 0

[PATCH net-next v3 0/3] net/sched: act_vlan: Fix modify to allow 0

by Boris Sukholitko

Currently vlan modification action checks existence of vlan priority by comparing it to 0. Therefore it is impossible to modify existing vlan tag to have priority 0. For example, the following tc command will change the vlan id but will not affect vlan priority: tc filter add dev eth1 ingress matchall action vlan modify id 300 \ priority 0 pipe mirred egress redirect dev eth2 The incoming packet on eth1: ethertype 802.1Q (0x8100), vlan 200, p 4, ethertype IPv4 will be changed to: ethertype 802.1Q (0x8100), vlan 300, p 4, ethertype IPv4 although the user has intended to have p == 0. The fix is to add tcfv_push_prio_exists flag to struct tcf_vlan_params and rely on it when deciding to set the priority. The same flag is used to avoid dumping unset vlan priority. Change Log: v2 -> v3: - Push assumes that the priority is being set - tcf_vlan_get_fill_size accounts for priority existence v1 -> v2: - Do not dump unset priority and fix tests accordingly - Test for priority 0 modification Boris Sukholitko (3): net/sched: act_vlan: Fix modify to allow 0 net/sched: act_vlan: No dump for unset priority net/sched: act_vlan: Test priority 0 modification include/net/tc_act/tc_vlan.h | 1 + net/sched/act_vlan.c | 26 ++++++++++++----- .../tc-testing/tc-tests/actions/vlan.json | 28 +++++++++++++++++-- 3 files changed, 46 insertions(+), 9 deletions(-) -- 2.29.3

4 years

4
8
0 0

[PATCH][next] KVM: selftests: Fix spelling mistake "UFFDIO_CONINUE" -> "UFFDIO_CONTINUE"

by Colin King

From: Colin Ian King <colin.king(a)canonical.com> There is a spelling mistake in a debug message. Fix it. Signed-off-by: Colin Ian King <colin.king(a)canonical.com> --- tools/testing/selftests/kvm/demand_paging_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index b74704305835..874dc8f7248f 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -230,7 +230,7 @@ static void setup_demand_paging(struct kvm_vm *vm, PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n", is_minor ? "MINOR" : "MISSING", - is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY"); + is_minor ? "UFFDIO_CONTINUE" : "UFFDIO_COPY"); /* In order to get minor faults, prefault via the alias. */ if (is_minor) { -- 2.31.1

4 years

1
0
0 0

tools/testing/selftests/ptrace/vmaccess.c hangs

by Vitaly Chikunov

Hi, Possible ptrace related bug in tools/testing/selftests/ptrace/vmaccess.c - it timeout every time I run it on any kernel I try, in vm or bare metal. Does it run correctly for anybody? Example vmaccess from v5.12 source tree run on 5.13.0+rc2 on bare metal Supermicro server (AMD EPYC): 5.10.35-rt-alt1.rt39:~# /usr/lib/kselftests/ptrace/vmaccess TAP version 13 1..2 # Starting 2 tests from 1 test cases. # RUN global.vmaccess ... # OK global.vmaccess ok 1 global.vmaccess # RUN global.attach ... # attach: Test terminated by timeout # FAIL global.attach not ok 2 global.attach # FAILED: 1 / 2 tests passed. # Totals: pass:1 fail:1 xfail:0 xpass:0 skip:0 error:0 Just to confirm for the latest kernel, it behaves the same [for drm-tip based] on 5.13rc2. Also, just tested on 5.11.21 with the same failure. Other ptrace tests pass. Thanks,

4 years, 1 month

2
1
0 0

[PATCH] selftests/bpf: Fix return value check in attach_bpf()

by Yu Kuai

use libbpf_get_error() to check the return value of bpf_program__attach(). Reported-by: Hulk Robot <hulkci(a)huawei.com> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> --- tools/testing/selftests/bpf/benchs/bench_rename.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c index c7ec114eca56..b7d4a1d74fca 100644 --- a/tools/testing/selftests/bpf/benchs/bench_rename.c +++ b/tools/testing/selftests/bpf/benchs/bench_rename.c @@ -65,7 +65,7 @@ static void attach_bpf(struct bpf_program *prog) struct bpf_link *link; link = bpf_program__attach(prog); - if (!link) { + if (libbpf_get_error(link)) { fprintf(stderr, "failed to attach program!\n"); exit(1); } -- 2.25.4

4 years, 1 month

5
5
0 0

[PATCH] selftest: Add test for Soft-Dirty PTE bit

by Gabriel Krisman Bertazi

This introduces three tests: 1) Sanity check soft dirty basic semantics: allocate area, clean, dirty, check if the SD bit flipped. 2) Check VMA reuse: validate the VM_SOFTDIRTY usage 3) Check soft-dirty on huge pages This was motivated by Will Deacon's fix commit 912efa17e512 ("mm: proc: Invalidate TLB after clearing soft-dirty page state"). I was tracking the same issue that he fixed, and this test would have caught it. Cc: Will Deacon <will(a)kernel.org> Signed-off-by: Gabriel Krisman Bertazi <krisman(a)collabora.com> --- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/soft-dirty/.gitignore | 1 + tools/testing/selftests/soft-dirty/Makefile | 9 + .../testing/selftests/soft-dirty/soft-dirty.c | 254 ++++++++++++++++++ 4 files changed, 265 insertions(+) create mode 100644 tools/testing/selftests/soft-dirty/.gitignore create mode 100644 tools/testing/selftests/soft-dirty/Makefile create mode 100644 tools/testing/selftests/soft-dirty/soft-dirty.c diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index bc3299a20338..c8dcd7defd33 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -55,6 +55,7 @@ TARGETS += seccomp TARGETS += sgx TARGETS += sigaltstack TARGETS += size +TARGETS += soft-dirty TARGETS += sparc64 TARGETS += splice TARGETS += static_keys diff --git a/tools/testing/selftests/soft-dirty/.gitignore b/tools/testing/selftests/soft-dirty/.gitignore new file mode 100644 index 000000000000..cfb0cfda9bdf --- /dev/null +++ b/tools/testing/selftests/soft-dirty/.gitignore @@ -0,0 +1 @@ +soft-dirty diff --git a/tools/testing/selftests/soft-dirty/Makefile b/tools/testing/selftests/soft-dirty/Makefile new file mode 100644 index 000000000000..d76ad8e0f10d --- /dev/null +++ b/tools/testing/selftests/soft-dirty/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 +top_srcdir = ../../../.. +INSTALL_HDR_PATH = $(top_srcdir)/usr +LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ + +CFLAGS += -Wall -I$(LINUX_HDR_PATH) -O0 -g3 + +TEST_GEN_PROGS := soft-dirty +include ../lib.mk diff --git a/tools/testing/selftests/soft-dirty/soft-dirty.c b/tools/testing/selftests/soft-dirty/soft-dirty.c new file mode 100644 index 000000000000..47af76f9df50 --- /dev/null +++ b/tools/testing/selftests/soft-dirty/soft-dirty.c @@ -0,0 +1,254 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <stdint.h> +#include <unistd.h> +#include <stdio.h> +#include <unistd.h> +#include <syscall.h> +#include <errno.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <err.h> +#include <string.h> +#include <stdbool.h> +#include <malloc.h> + +#define PAGEMAP_PATH "/proc/self/pagemap" +#define CLEAR_REFS_PATH "/proc/self/clear_refs" +#define SMAP_PATH "/proc/self/smaps" +#define MAX_LINE_LENGTH 512 + +#define TEST_ITERATIONS 10000 + +#define PMD_SIZE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" + +int clear_refs; +int pagemap; + +int pagesize; +int mmap_size; /* Size of test region */ + +static void clear_all_refs(void) +{ + if (write(clear_refs, "4\n", 2) != 2) + printf("%s: failed to clear references\n", __func__); +} + +static void touch_page(char *map, int n) +{ + map[(page_size * n) + 1]++; +} + +static int check_page(char *map, uint64_t n, int clear) +{ + uint64_t off; + uint64_t buf = 0; + + off = (n + ((uint64_t)map >> 12)) << 3; + + if (lseek(pagemap, off, SEEK_SET) == (off_t) -1) + errx(EXIT_FAILURE, "pagemap llseek failed"); + + if (read(pagemap, &buf, 8) != 8) + errx(EXIT_FAILURE, "pagemap read failed"); + + if (clear) + clear_all_refs(); + + return ((buf >> 55) & 1); +} + +static void test_simple(void) +{ + int i; + char *map; + + printf("- Test %s:\n", __func__); + + map = aligned_alloc(page_size, mmap_size); + if (!map) + errx(EXIT_FAILURE, "mmap"); + + clear_all_refs(); + + for (i = 0 ; i < TEST_ITERATIONS; i++) { + if (check_page(map, 2, 1) == 1) { + errx(EXIT_FAILURE, "dirty bit was 1, but should be 0 (i=%d)", i); + break; + } + + touch_page(map, 2); + + if (check_page(map, 2, 1) == 0) { + errx(EXIT_FAILURE, "dirty bit was 0, but should be 1 (i=%d)", i); + break; + } + + } + free(map); + + printf("success\n"); +} + +static void test_vma_reuse(void) +{ + char *map, *map2; + + printf("- Test %s:\n", __func__); + + map = (char *) 0x900000000000; + map = mmap(map, mmap_size, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0); + if (map == MAP_FAILED) + errx(EXIT_FAILURE, "mmap"); + + clear_all_refs(); + touch_page(map, 2); + + munmap(map, mmap_size); + map2 = mmap(map, mmap_size, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0); + if (map2 == MAP_FAILED) + errx(EXIT_FAILURE, "mmap2"); + + if (map != map2) + errx(EXIT_FAILURE, "map != map2"); + + if (check_page(map, 2, 1) == 0) + errx(-1, "map/unmap lost dirty"); + + munmap(map2, mmap_size); + + printf("success\n"); +} + +/* + * read_pmd_pagesize(), check_for_pattern() and check_huge() adapted + * from 'tools/testing/selftest/vm/split_huge_page_test.c' + */ +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) + errx(EXIT_FAILURE, "Open hpage_pmd_size failed"); + + num_read = read(fd, buf, 19); + if (num_read < 1) { + close(fd); + errx(EXIT_FAILURE, "Read hpage_pmd_size failed"); + } + buf[num_read] = '\0'; + close(fd); + + return strtoul(buf, NULL, 10); +} + +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) + errx(EXIT_FAILURE, "%s: Pattern is too long\n", __func__); + + fp = fopen(SMAP_PATH, "r"); + if (!fp) + errx(EXIT_FAILURE, "%s: Failed to open file %s\n", __func__, SMAP_PATH); + + 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) + errx(EXIT_FAILURE, "Reading smap error\n"); + +err_out: + fclose(fp); + + return thp; +} + +static void test_hugepage(void) +{ + char *map; + int i, ret; + size_t hpage_len = read_pmd_pagesize(); + + printf("- Test %s:\n", __func__); + + map = memalign(hpage_len, hpage_len); + if (!map) + errx(EXIT_FAILURE, "memalign"); + + ret = madvise(map, hpage_len, MADV_HUGEPAGE); + if (ret) + errx(EXIT_FAILURE, "madvise %d", ret); + + for (i = 0; i < hpage_len; i++) + map[i] = (char)i; + + if (!check_huge(map)) + errx(EXIT_FAILURE, "failed to allocate THP"); + + clear_all_refs(); + for (i = 0 ; i < TEST_ITERATIONS ; i++) { + if (check_page(map, 2, 1) == 1) { + errx(EXIT_FAILURE, "dirty bit was 1, but should be 0 (i=%d)", i); + break; + } + + touch_page(map, 2); + + if (check_page(map, 2, 1) == 0) { + errx(EXIT_FAILURE, "dirty bit was 0, but should be 1 (i=%d)", i); + break; + } + } + munmap(map, mmap_size); + + printf("success\n"); +} + +int main(int argc, char **argv) +{ + pagemap = open(PAGEMAP_PATH, O_RDONLY, 0); + if (pagemap < 0) + errx(EXIT_FAILURE, "Failed to open %s", PAGEMAP_PATH); + + clear_refs = open(CLEAR_REFS_PATH, O_WRONLY, 0); + if (clear_refs < 0) + errx(EXIT_FAILURE, "Failed to open %s", CLEAR_REFS_PATH); + + pagesize = getpagesize(); + mmap_size = 10 * pagesize(); + + test_simple(); + test_vma_reuse(); + test_hugepage(); + + return 0; +} -- 2.31.0

4 years, 1 month

1
0
0 0

[PATCH -next] khugepaged: selftests: remove debug_cow

by Nanyong Sun

The debug_cow attribute had been removed since commit 4958e4d86ecb01 ("mm: thp: remove debug_cow switch"), so remove it in selftest code too, otherwise the khugepaged test will fail. Signed-off-by: Nanyong Sun <sunnanyong(a)huawei.com> --- tools/testing/selftests/vm/khugepaged.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index 8b7582130..155120b67 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -86,7 +86,6 @@ struct settings { enum thp_enabled thp_enabled; enum thp_defrag thp_defrag; enum shmem_enabled shmem_enabled; - bool debug_cow; bool use_zero_page; struct khugepaged_settings khugepaged; }; @@ -95,7 +94,6 @@ static struct settings default_settings = { .thp_enabled = THP_MADVISE, .thp_defrag = THP_DEFRAG_ALWAYS, .shmem_enabled = SHMEM_NEVER, - .debug_cow = 0, .use_zero_page = 0, .khugepaged = { .defrag = 1, @@ -268,7 +266,6 @@ static void write_settings(struct settings *settings) write_string("defrag", thp_defrag_strings[settings->thp_defrag]); write_string("shmem_enabled", shmem_enabled_strings[settings->shmem_enabled]); - write_num("debug_cow", settings->debug_cow); write_num("use_zero_page", settings->use_zero_page); write_num("khugepaged/defrag", khugepaged->defrag); @@ -304,7 +301,6 @@ static void save_settings(void) .thp_defrag = read_string("defrag", thp_defrag_strings), .shmem_enabled = read_string("shmem_enabled", shmem_enabled_strings), - .debug_cow = read_num("debug_cow"), .use_zero_page = read_num("use_zero_page"), }; saved_settings.khugepaged = (struct khugepaged_settings) { -- 2.25.1

4 years, 1 month

3
2
0 0

[PATCH v2 0/4] kunit: tool: add support for QEMU

by Brendan Higgins

TL;DR: Add support to kunit_tool to dispatch tests via QEMU. Also add support to immediately shutdown a kernel after running KUnit tests. Background ---------- KUnit has supported running on all architectures for quite some time; however, kunit_tool - the script commonly used to invoke KUnit tests - has only fully supported KUnit run on UML. Its functionality has been broken up for some time to separate the configure, build, run, and parse phases making it possible to be used in part on other architectures to a small extent. Nevertheless, kunit_tool has not supported running tests on other architectures. What this patchset does ----------------------- This patchset introduces first class support to kunit_tool for KUnit to be run on many popular architectures via QEMU. It does this by adding two new flags: `--arch` and `--cross_compile`. `--arch` allows an architecture to be specified by the name the architecture is given in `arch/`. It uses the specified architecture to select a minimal amount of Kconfigs and QEMU configs needed for the architecture to run in QEMU and provide a console from which KTAP results can be scraped. `--cross_compile` allows a toolchain prefix to be specified to make similar to how `CROSS_COMPILE` is used. Additionally, this patchset revives the previously considered "kunit: tool: add support for QEMU"[1] patchs. The motivation for this new kernel command line flags, `kunit_shutdown`, is to better support running KUnit tests inside of QEMU. For most popular architectures, QEMU can be made to terminate when the Linux kernel that is being run is reboted, halted, or powered off. As Kees pointed out in a previous discussion[2], it is possible to make a kernel initrd that can reboot the kernel immediately, doing this for every architecture would likely be infeasible. Instead, just having an option for the kernel to shutdown when it is done with testing seems a lot simpler, especially since it is an option which would only available in testing configurations of the kernel anyway. Changes since last revision --------------------------- I pulled out the QemuConfigs into their own files; the way in which I did this also allows new QemuConfigs to be added without making any changes to kunit_tool. I changed how Kconfigs are loaded; they are now merged inside of kunit_tool instead of letting Kbuild do it. I also made numerous nit fixes. Finally, I added a new section to the kunit_tool documentation to document the new command line flags I added. [1] http://patches.linaro.org/patch/208336/ [2] https://lkml.org/lkml/2020/6/26/988 Brendan Higgins (3): Documentation: Add kunit_shutdown to kernel-parameters.txt kunit: tool: add support for QEMU Documentation: kunit: document support for QEMU in kunit_tool David Gow (1): kunit: Add 'kunit_shutdown' option .../admin-guide/kernel-parameters.txt | 8 + Documentation/dev-tools/kunit/kunit-tool.rst | 48 +++++ Documentation/dev-tools/kunit/usage.rst | 50 +++-- lib/kunit/executor.c | 20 ++ tools/testing/kunit/kunit.py | 57 +++++- tools/testing/kunit/kunit_config.py | 7 +- tools/testing/kunit/kunit_kernel.py | 177 +++++++++++++++--- tools/testing/kunit/kunit_parser.py | 2 +- tools/testing/kunit/kunit_tool_test.py | 18 +- tools/testing/kunit/qemu_config.py | 16 ++ tools/testing/kunit/qemu_configs/alpha.py | 10 + tools/testing/kunit/qemu_configs/arm.py | 13 ++ tools/testing/kunit/qemu_configs/arm64.py | 12 ++ tools/testing/kunit/qemu_configs/i386.py | 10 + tools/testing/kunit/qemu_configs/powerpc.py | 12 ++ tools/testing/kunit/qemu_configs/riscv.py | 31 +++ tools/testing/kunit/qemu_configs/s390.py | 14 ++ tools/testing/kunit/qemu_configs/sparc.py | 10 + tools/testing/kunit/qemu_configs/x86_64.py | 10 + 19 files changed, 471 insertions(+), 54 deletions(-) create mode 100644 tools/testing/kunit/qemu_config.py create mode 100644 tools/testing/kunit/qemu_configs/alpha.py create mode 100644 tools/testing/kunit/qemu_configs/arm.py create mode 100644 tools/testing/kunit/qemu_configs/arm64.py create mode 100644 tools/testing/kunit/qemu_configs/i386.py create mode 100644 tools/testing/kunit/qemu_configs/powerpc.py create mode 100644 tools/testing/kunit/qemu_configs/riscv.py create mode 100644 tools/testing/kunit/qemu_configs/s390.py create mode 100644 tools/testing/kunit/qemu_configs/sparc.py create mode 100644 tools/testing/kunit/qemu_configs/x86_64.py base-commit: d7eab3df8f39b116d934bc17f8070861e18cfb62 -- 2.31.1.818.g46aad6cb9e-goog

4 years, 1 month

3
6
0 0

[PATCH v3 bpf-next 0/2] libbpf: BTF dumper support for typed data

by Alan Maguire

Add a libbpf dumper function that supports dumping a representation of data passed in using the BTF id associated with the data in a manner similar to the bpf_snprintf_btf helper. Default output format is identical to that dumped by bpf_snprintf_btf() (bar using tabs instead of spaces for indentation); for example, a "struct sk_buff" representation would look like this: (struct sk_buff){ (union){ (struct){ .next = (struct sk_buff *)0xffffffffffffffff, .prev = (struct sk_buff *)0xffffffffffffffff, (union){ .dev = (struct net_device *)0xffffffffffffffff, .dev_scratch = (long unsigned int)18446744073709551615, }, }, ... Patch 1 implements the dump functionality in a manner similar to that in kernel/bpf/btf.c, but with a view to fitting into libbpf more naturally. For example, rather than using flags, boolean dump options are used to control output. In addition, rather than combining checks for display (such as is this field zero?) and actual display - as is done for the kernel code - the code is organized to separate zero and overflow checks from type display. Patch 2 consists of selftests that utilize a dump printf function to snprintf the dump output to a string for comparison with expected output. Tests deliberately mirror those in snprintf_btf helper test to keep output consistent, but also cover overflow handling, var/section display. Apologies for the long time lag between v2 and this revision. Changes since v2 [1] - Renamed function to btf_dump__dump_type_data, reorganized arguments such that opts are last (Andrii) - Modified code to separate questions about display such as have we overflowed?/is this field zero? from actual display of typed data, such that we ask those questions separately from the code that actually displays typed data (Andrii) - Reworked code to handle overflow - where we do not provide enough data for the type we wish to display - by returning -E2BIG and attempting to present as much data as possible. Such a mode of operation allows for tracers which retrieve partial data (such as first 1024 bytes of a "struct task_struct" say), and want to display that partial data, while also knowing that it is not the full type. Such tracers can then denote this (perhaps via "..." or similar). - Explored reusing existing type emit functions, such as passing in a type id stack with a single type id to btf_dump_emit_type_chain() to support the display of typed data where a "cast" is prepended to the data to denote its type; "(int)1", "(struct foo){", etc. However the task of emitting a ".field_name = (typecast)" did not match well with model of walking the stack to display innermost types first and made the resultant code harder to read. Added a dedicated btf_dump_emit_type_name() function instead which is only ~70 lines (Andrii) - Various cleanups around bitfield macros, unneeded member iteration macros, avoiding compiler complaints when displaying int da ta by casting to long long, etc (Andrii) - Use DECLARE_LIBBPF_OPTS() in defining opts for tests (Andrii) - Added more type tests, overflow tests, var tests and section tests. Changes since RFC [2] - The initial approach explored was to share the kernel code with libbpf using #defines to paper over the different needs; however it makes more sense to try and fit in with libbpf code style for maintenance. A comment in the code points at the implementation in kernel/bpf/btf.c and notes that any issues found in it should be fixed there or vice versa; mirroring the tests should help with this also (Andrii) [1] https://lore.kernel.org/bpf/1610921764-7526-1-git-send-email-alan.maguire@o… [2] https://lore.kernel.org/bpf/1610386373-24162-1-git-send-email-alan.maguire@… Alan Maguire (2): libbpf: BTF dumper support for typed data selftests/bpf: add dump type data tests to btf dump tests tools/lib/bpf/btf.h | 17 + tools/lib/bpf/btf_dump.c | 901 ++++++++++++++++++++++ tools/lib/bpf/libbpf.map | 5 + tools/testing/selftests/bpf/prog_tests/btf_dump.c | 524 +++++++++++++ 4 files changed, 1447 insertions(+) -- 1.8.3.1

4 years, 1 month

2
3
0 0

[PATCH 1/3] kunit: Support skipped tests

by David Gow

The kunit_mark_skipped() macro marks the current test as "skipped", with the provided reason. The kunit_skip() macro will mark the test as skipped, and abort the test. The TAP specification supports this "SKIP directive" as a comment after the "ok" / "not ok" for a test. See the "Directives" section of the TAP spec for details: https://testanything.org/tap-specification.html#directives The 'success' field for KUnit tests is replaced with a kunit_status enum, which can be SUCCESS, FAILURE, or SKIPPED, combined with a 'status_comment' containing information on why a test was skipped. A new 'kunit_status' test suite is added to test this. Signed-off-by: David Gow <davidgow(a)google.com> --- This change depends on the assertion typechecking fix here: https://lore.kernel.org/linux-kselftest/20210513193204.816681-1-davidgow@go… Only the first two patches in the series are required. This is the long-awaited follow-up to the skip tests RFC: https://lore.kernel.org/linux-kselftest/20200513042956.109987-1-davidgow@go… There are quite a few changes since that version, principally: - A kunit_status enum is now used, with SKIPPED a distinct state - The kunit_mark_skipped() and kunit_skip() macros now take printf-style format strings. - There is now a kunit_status test suite providing basic tests of this functionality. - The kunit_tool changes have been split into a separate commit. - The example skipped tests have been expanded an moved to their own suite, which is not enabled by KUNIT_ALL_TESTS. - A number of other fixes and changes here and there. Cheers, -- David include/kunit/test.h | 68 ++++++++++++++++++++++++++++++++++++++---- lib/kunit/kunit-test.c | 42 +++++++++++++++++++++++++- lib/kunit/test.c | 51 ++++++++++++++++++------------- 3 files changed, 134 insertions(+), 27 deletions(-) diff --git a/include/kunit/test.h b/include/kunit/test.h index b68c61348121..40b536da027e 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -105,6 +105,18 @@ struct kunit; #define KUNIT_SUBTEST_INDENT " " #define KUNIT_SUBSUBTEST_INDENT " " +/** + * enum kunit_status - Type of result for a test or test suite + * @KUNIT_SUCCESS: Denotes the test suite has not failed nor been skipped + * @KUNIT_FAILURE: Denotes the test has failed. + * @KUNIT_SKIPPED: Denotes the test has been skipped. + */ +enum kunit_status { + KUNIT_SUCCESS, + KUNIT_FAILURE, + KUNIT_SKIPPED, +}; + /** * struct kunit_case - represents an individual test case. * @@ -148,13 +160,20 @@ struct kunit_case { const void* (*generate_params)(const void *prev, char *desc); /* private: internal use only. */ - bool success; + enum kunit_status status; char *log; }; -static inline char *kunit_status_to_string(bool status) +static inline char *kunit_status_to_string(enum kunit_status status) { - return status ? "ok" : "not ok"; + switch (status) { + case KUNIT_SKIPPED: + case KUNIT_SUCCESS: + return "ok"; + case KUNIT_FAILURE: + return "not ok"; + } + return "invalid"; } /** @@ -212,6 +231,7 @@ struct kunit_suite { struct kunit_case *test_cases; /* private: internal use only */ + char status_comment[256]; struct dentry *debugfs; char *log; }; @@ -245,19 +265,21 @@ struct kunit { * be read after the test case finishes once all threads associated * with the test case have terminated. */ - bool success; /* Read only after test_case finishes! */ spinlock_t lock; /* Guards all mutable test state. */ + enum kunit_status status; /* Read only after test_case finishes! */ /* * Because resources is a list that may be updated multiple times (with * new resources) from any thread associated with a test case, we must * protect it with some type of lock. */ struct list_head resources; /* Protected by lock. */ + + char status_comment[256]; }; static inline void kunit_set_failure(struct kunit *test) { - WRITE_ONCE(test->success, false); + WRITE_ONCE(test->status, KUNIT_FAILURE); } void kunit_init_test(struct kunit *test, const char *name, char *log); @@ -348,7 +370,7 @@ static inline int kunit_run_all_tests(void) #define kunit_suite_for_each_test_case(suite, test_case) \ for (test_case = suite->test_cases; test_case->run_case; test_case++) -bool kunit_suite_has_succeeded(struct kunit_suite *suite); +enum kunit_status kunit_suite_has_succeeded(struct kunit_suite *suite); /* * Like kunit_alloc_resource() below, but returns the struct kunit_resource @@ -612,6 +634,40 @@ void kunit_cleanup(struct kunit *test); void kunit_log_append(char *log, const char *fmt, ...); +/** + * kunit_mark_skipped() - Marks @test_or_suite as skipped + * + * @test_or_suite: The test context object. + * @fmt: A printk() style format string. + * + * Marks the test as skipped. @fmt is given output as the test status + * comment, typically the reason the test was skipped. + * + * Test execution continues after kunit_mark_skipped() is called. + */ +#define kunit_mark_skipped(test_or_suite, fmt, ...) \ + do { \ + WRITE_ONCE((test_or_suite)->status, KUNIT_SKIPPED); \ + scnprintf((test_or_suite)->status_comment, 256, fmt, ##__VA_ARGS__); \ + } while (0) + +/** + * kunit_skip() - Marks @test_or_suite as skipped + * + * @test_or_suite: The test context object. + * @fmt: A printk() style format string. + * + * Skips the test. @fmt is given output as the test status + * comment, typically the reason the test was skipped. + * + * Test execution is halted after kunit_skip() is called. + */ +#define kunit_skip(test_or_suite, fmt, ...) \ + do { \ + kunit_mark_skipped((test_or_suite), fmt, ##__VA_ARGS__);\ + kunit_try_catch_throw(&((test_or_suite)->try_catch)); \ + } while (0) + /* * printk and log to per-test or per-suite log buffer. Logging only done * if CONFIG_KUNIT_DEBUGFS is 'y'; if it is 'n', no log is allocated/used. diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index 69f902440a0e..d69efcbed624 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -437,7 +437,47 @@ static void kunit_log_test(struct kunit *test) #endif } +static void kunit_status_set_failure_test(struct kunit *test) +{ + struct kunit fake; + + kunit_init_test(&fake, "fake test", NULL); + + KUNIT_EXPECT_EQ(test, fake.status, (enum kunit_status)KUNIT_SUCCESS); + kunit_set_failure(&fake); + KUNIT_EXPECT_EQ(test, fake.status, (enum kunit_status)KUNIT_FAILURE); +} + +static void kunit_status_mark_skipped_test(struct kunit *test) +{ + struct kunit fake; + + kunit_init_test(&fake, "fake test", NULL); + + /* Before: Should be SUCCESS with no comment. */ + KUNIT_EXPECT_EQ(test, fake.status, KUNIT_SUCCESS); + KUNIT_EXPECT_STREQ(test, fake.status_comment, ""); + + /* Mark the test as skipped. */ + kunit_mark_skipped(&fake, "Accepts format string: %s", "YES"); + + /* After: Should be SKIPPED with our comment. */ + KUNIT_EXPECT_EQ(test, fake.status, (enum kunit_status)KUNIT_SKIPPED); + KUNIT_EXPECT_STREQ(test, fake.status_comment, "Accepts format string: YES"); +} + +static struct kunit_case kunit_status_test_cases[] = { + KUNIT_CASE(kunit_status_set_failure_test), + KUNIT_CASE(kunit_status_mark_skipped_test), + {} +}; + +static struct kunit_suite kunit_status_test_suite = { + .name = "kunit_status", + .test_cases = kunit_status_test_cases, +}; + kunit_test_suites(&kunit_try_catch_test_suite, &kunit_resource_test_suite, - &kunit_log_test_suite); + &kunit_log_test_suite, &kunit_status_test_suite); MODULE_LICENSE("GPL v2"); diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 2f6cc0123232..0ee07705d2b0 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -98,12 +98,14 @@ static void kunit_print_subtest_start(struct kunit_suite *suite) static void kunit_print_ok_not_ok(void *test_or_suite, bool is_test, - bool is_ok, + enum kunit_status status, size_t test_number, - const char *description) + const char *description, + const char *directive) { struct kunit_suite *suite = is_test ? NULL : test_or_suite; struct kunit *test = is_test ? test_or_suite : NULL; + const char *directive_header = (status == KUNIT_SKIPPED) ? " # SKIP " : ""; /* * We do not log the test suite results as doing so would @@ -114,25 +116,31 @@ static void kunit_print_ok_not_ok(void *test_or_suite, * representation. */ if (suite) - pr_info("%s %zd - %s\n", - kunit_status_to_string(is_ok), - test_number, description); + pr_info("%s %zd - %s%s%s\n", + kunit_status_to_string(status), + test_number, description, + directive_header, directive ? directive : ""); else - kunit_log(KERN_INFO, test, KUNIT_SUBTEST_INDENT "%s %zd - %s", - kunit_status_to_string(is_ok), - test_number, description); + kunit_log(KERN_INFO, test, + KUNIT_SUBTEST_INDENT "%s %zd - %s%s%s", + kunit_status_to_string(status), + test_number, description, + directive_header, directive ? directive : ""); } -bool kunit_suite_has_succeeded(struct kunit_suite *suite) +enum kunit_status kunit_suite_has_succeeded(struct kunit_suite *suite) { const struct kunit_case *test_case; + enum kunit_status status = KUNIT_SKIPPED; kunit_suite_for_each_test_case(suite, test_case) { - if (!test_case->success) - return false; + if (test_case->status == KUNIT_FAILURE) + return KUNIT_FAILURE; + else if (test_case->status == KUNIT_SUCCESS) + status = KUNIT_SUCCESS; } - return true; + return status; } EXPORT_SYMBOL_GPL(kunit_suite_has_succeeded); @@ -143,7 +151,8 @@ static void kunit_print_subtest_end(struct kunit_suite *suite) kunit_print_ok_not_ok((void *)suite, false, kunit_suite_has_succeeded(suite), kunit_suite_counter++, - suite->name); + suite->name, + suite->status_comment); } unsigned int kunit_test_case_num(struct kunit_suite *suite, @@ -252,7 +261,8 @@ void kunit_init_test(struct kunit *test, const char *name, char *log) test->log = log; if (test->log) test->log[0] = '\0'; - test->success = true; + test->status = KUNIT_SUCCESS; + test->status_comment[0] = '\0'; } EXPORT_SYMBOL_GPL(kunit_init_test); @@ -376,7 +386,8 @@ static void kunit_run_case_catch_errors(struct kunit_suite *suite, context.test_case = test_case; kunit_try_catch_run(try_catch, &context); - test_case->success = test->success; + test_case->status = test->status; + } int kunit_run_tests(struct kunit_suite *suite) @@ -388,7 +399,6 @@ int kunit_run_tests(struct kunit_suite *suite) kunit_suite_for_each_test_case(suite, test_case) { struct kunit test = { .param_value = NULL, .param_index = 0 }; - bool test_success = true; if (test_case->generate_params) { /* Get initial param. */ @@ -398,7 +408,6 @@ int kunit_run_tests(struct kunit_suite *suite) do { kunit_run_case_catch_errors(suite, test_case, &test); - test_success &= test_case->success; if (test_case->generate_params) { if (param_desc[0] == '\0') { @@ -410,7 +419,7 @@ int kunit_run_tests(struct kunit_suite *suite) KUNIT_SUBTEST_INDENT "# %s: %s %d - %s", test_case->name, - kunit_status_to_string(test.success), + kunit_status_to_string(test.status), test.param_index + 1, param_desc); /* Get next param. */ @@ -420,9 +429,10 @@ int kunit_run_tests(struct kunit_suite *suite) } } while (test.param_value); - kunit_print_ok_not_ok(&test, true, test_success, + kunit_print_ok_not_ok(&test, true, test_case->status, kunit_test_case_num(suite, test_case), - test_case->name); + test_case->name, + test.status_comment); } kunit_print_subtest_end(suite); @@ -434,6 +444,7 @@ EXPORT_SYMBOL_GPL(kunit_run_tests); static void kunit_init_suite(struct kunit_suite *suite) { kunit_debugfs_create_suite(suite); + suite->status_comment[0] = '\0'; } int __kunit_test_suites_init(struct kunit_suite * const * const suites) -- 2.31.1.818.g46aad6cb9e-goog

4 years, 1 month

4
16
0 0

[PATCH v6 0/4] KVM statistics data fd-based binary interface

by Jing Zhang

This patchset provides a file descriptor for every VM and VCPU to read KVM statistics data in binary format. It is meant to provide a lightweight, flexible, scalable and efficient lock-free solution for user space telemetry applications to pull the statistics data periodically for large scale systems. The pulling frequency could be as high as a few times per second. In this patchset, every statistics data are treated to have some attributes as below: * architecture dependent or common * VM statistics data or VCPU statistics data * type: cumulative, instantaneous, * unit: none for simple counter, nanosecond, microsecond, millisecond, second, Byte, KiByte, MiByte, GiByte. Clock Cycles Since no lock/synchronization is used, the consistency between all the statistics data is not guaranteed. That means not all statistics data are read out at the exact same time, since the statistics date are still being updated by KVM subsystems while they are read out. --- * v5 -> v6 - Use designated initializers for STATS_DESC - Change KVM_STATS_SCALE... to KVM_STATS_BASE... - Use a common function for kvm_[vm|vcpu]_stats_read - Fix some documentation errors/missings - Use TEST_ASSERT in selftest - Use a common function for [vm|vcpu]_stats_test in selftest * v4 -> v5 - Rebase to kvm/queue, commit a4345a7cecfb ("Merge tag 'kvmarm-fixes-5.13-1'") - Change maximum stats name length to 48 - Replace VM_STATS_COMMON/VCPU_STATS_COMMON macros with stats descriptor definition macros. - Fixed some errors/warnings reported by checkpatch.pl * v3 -> v4 - Rebase to kvm/queue, commit 9f242010c3b4 ("KVM: avoid "deadlock" between install_new_memslots and MMU notifier") - Use C-stype comments in the whole patch - Fix wrong count for x86 VCPU stats descriptors - Fix KVM stats data size counting and validity check in selftest * v2 -> v3 - Rebase to kvm/queue, commit edf408f5257b ("KVM: avoid "deadlock" between install_new_memslots and MMU notifier") - Resolve some nitpicks about format * v1 -> v2 - Use ARRAY_SIZE to count the number of stats descriptors - Fix missing `size` field initialization in macro STATS_DESC [1] https://lore.kernel.org/kvm/20210402224359.2297157-1-jingzhangos@google.com [2] https://lore.kernel.org/kvm/20210415151741.1607806-1-jingzhangos@google.com [3] https://lore.kernel.org/kvm/20210423181727.596466-1-jingzhangos@google.com [4] https://lore.kernel.org/kvm/20210429203740.1935629-1-jingzhangos@google.com [5] https://lore.kernel.org/kvm/20210517145314.157626-1-jingzhangos@google.com --- Jing Zhang (4): KVM: stats: Separate common stats from architecture specific ones KVM: stats: Add fd-based API to read binary stats data KVM: stats: Add documentation for statistics data binary interface KVM: selftests: Add selftest for KVM statistics data binary interface Documentation/virt/kvm/api.rst | 179 +++++++++++++++ arch/arm64/include/asm/kvm_host.h | 9 +- arch/arm64/kvm/guest.c | 38 ++- arch/mips/include/asm/kvm_host.h | 9 +- arch/mips/kvm/mips.c | 64 +++++- arch/powerpc/include/asm/kvm_host.h | 9 +- arch/powerpc/kvm/book3s.c | 64 +++++- arch/powerpc/kvm/book3s_hv.c | 12 +- arch/powerpc/kvm/book3s_pr.c | 2 +- arch/powerpc/kvm/book3s_pr_papr.c | 2 +- arch/powerpc/kvm/booke.c | 59 ++++- arch/s390/include/asm/kvm_host.h | 9 +- arch/s390/kvm/kvm-s390.c | 129 ++++++++++- arch/x86/include/asm/kvm_host.h | 9 +- arch/x86/kvm/x86.c | 67 +++++- include/linux/kvm_host.h | 141 +++++++++++- include/linux/kvm_types.h | 12 + include/uapi/linux/kvm.h | 50 ++++ tools/testing/selftests/kvm/.gitignore | 1 + tools/testing/selftests/kvm/Makefile | 3 + .../testing/selftests/kvm/include/kvm_util.h | 3 + .../selftests/kvm/kvm_bin_form_stats.c | 216 ++++++++++++++++++ tools/testing/selftests/kvm/lib/kvm_util.c | 12 + virt/kvm/kvm_main.c | 179 ++++++++++++++- 24 files changed, 1188 insertions(+), 90 deletions(-) create mode 100644 tools/testing/selftests/kvm/kvm_bin_form_stats.c base-commit: a4345a7cecfb91ae78cd43d26b0c6a956420761a -- 2.31.1.818.g46aad6cb9e-goog

4 years, 1 month

3
15
0 0

[PATCH] selftests/resctrl: Fix incorrect parsing of option "-t"

by Xiaochen Shen

Resctrl test suite accepts command line argument "-t" to specify the unit tests to run in the test list (e.g., -t mbm,mba,cmt,cat) as documented in the help. When calling strtok() to parse the option, the incorrect delimiters argument ":\t" is used. As a result, passing "-t mbm,mba,cmt,cat" throws an invalid option error. Fix this by using delimiters argument "," instead of ":\t" for parsing of unit tests list. At the same time, remove the unnecessary "spaces" between the unit tests in help documentation to prevent confusion. Fixes: 790bf585b0ee ("selftests/resctrl: Add Cache Allocation Technology (CAT) selftest") Fixes: 78941183d1b1 ("selftests/resctrl: Add Cache QoS Monitoring (CQM) selftest") Fixes: ecdbb911f22d ("selftests/resctrl: Add MBM test") Fixes: 034c7678dd2c ("selftests/resctrl: Add README for resctrl tests") Cc: stable(a)vger.kernel.org Signed-off-by: Xiaochen Shen <xiaochen.shen(a)intel.com> Reviewed-by: Tony Luck <tony.luck(a)intel.com> --- tools/testing/selftests/resctrl/README | 2 +- tools/testing/selftests/resctrl/resctrl_tests.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/resctrl/README b/tools/testing/selftests/resctrl/README index 4b36b25b6ac0..3d2bbd4fa3aa 100644 --- a/tools/testing/selftests/resctrl/README +++ b/tools/testing/selftests/resctrl/README @@ -47,7 +47,7 @@ Parameter '-h' shows usage information. usage: resctrl_tests [-h] [-b "benchmark_cmd [options]"] [-t test list] [-n no_of_bits] -b benchmark_cmd [options]: run specified benchmark for MBM, MBA and CMT default benchmark is builtin fill_buf - -t test list: run tests specified in the test list, e.g. -t mbm, mba, cmt, cat + -t test list: run tests specified in the test list, e.g. -t mbm,mba,cmt,cat -n no_of_bits: run cache tests using specified no of bits in cache bit mask -p cpu_no: specify CPU number to run the test. 1 is default -h: help diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index f51b5fc066a3..973f09a66e1e 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -40,7 +40,7 @@ static void cmd_help(void) printf("\t-b benchmark_cmd [options]: run specified benchmark for MBM, MBA and CMT\n"); printf("\t default benchmark is builtin fill_buf\n"); printf("\t-t test list: run tests specified in the test list, "); - printf("e.g. -t mbm, mba, cmt, cat\n"); + printf("e.g. -t mbm,mba,cmt,cat\n"); printf("\t-n no_of_bits: run cache tests using specified no of bits in cache bit mask\n"); printf("\t-p cpu_no: specify CPU number to run the test. 1 is default\n"); printf("\t-h: help\n"); @@ -173,7 +173,7 @@ int main(int argc, char **argv) return -1; } - token = strtok(NULL, ":\t"); + token = strtok(NULL, ","); } break; case 'p': -- 1.8.3.1

4 years, 1 month

1
0
0 0

x86/fpu/xsave: protection key test failures

by Babu Moger

Hi All, We have been noticing protection key test failures on our systems here. Shggy(Dave Kleikamp) from oracle reported to this problem couple of weeks ago. Here the is the failure. # ./protection_keys_64 has pkeys: 1 startup pkey_reg: 0000000055555550 test 0 PASSED (iteration 1) test 1 PASSED (iteration 1) test 2 PASSED (iteration 1) test 3 PASSED (iteration 1) test 4 PASSED (iteration 1) test 5 PASSED (iteration 1) test 6 PASSED (iteration 1) test 7 PASSED (iteration 1) test 8 PASSED (iteration 1) test 9 PASSED (iteration 1) test 10 PASSED (iteration 1) test 11 PASSED (iteration 1) test 12 PASSED (iteration 1) test 13 PASSED (iteration 1) protection_keys_64: pkey-helpers.h:127: _read_pkey_reg: Assertion `pkey_reg == shadow_pkey_reg' failed. Aborted (core dumped) The test that is failing is "test_ptrace_of_child". Sometimes it fails even earlier also. Sometimes(very rarely) it passes when I insert few printfs. Most probably it fails with test_ptrace_of_child. In the test "test_ptrace_of_child", the parent thread attaches to the child and modifies the data structure associated with protection key. Verifies the access results based on the key permissions. While running the test, the tool finds the key permission changes out of nowhere. The test fails with assert "assert(pkey_reg == shadow_pkey_reg);" Investigation so far. 1. The test fails on AMD(Milan) systems. Test appears to pass on Intel systems. Tested on old Intel system available here. 2. I was trying to see if the hardware(or firmware) is corrupting the pkru register value. At this point, it does not appear that way. I was able to trace all the MSR writes to the application or kernel. At this point, it does not appear to me as an hardware issue. I see that kernel appears to do save/restore properly during the context switch. This value stays default(value 0x55555554) in most cases unless the application changes the default permissions. Only application that changes here is "protection_keys". 3. I played with the test tool little bit. The behavior changes drastically when I make minor changes. For example, in the following code. void setup_handlers(void) { signal(SIGCHLD, &sig_chld); setup_sigsegv_handler(); } Just commenting the first line "signal(SIGCHLD, &sig_chld);" changes the behavior drastically. I see some tests PASS after this change. The first line appear to not do anything except some printing. I still have not figured out completely what is going on with setup_sigsegv_handler();. It seems very odd modifying some structures in the signal handler. I am not sure about some of the offsets it is trying to modify. I feel it may be messing up something there. I am not sure though. Will have to investigate. 4. I took the traces(x86_fpu) while running test. It appears to show some of the feature headers are not copied during the test. But I could not figure out why it was happening. It appears to show not all the feature headers are copied when the new child is created. When I printed the feature bits, they all appear to be intact. Here is the trace. protection_keys-17350 [035] 59275.833511: x86_fpu_regs_activated: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 202 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834197: x86_fpu_copy_src: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 202 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834197: x86_fpu_copy_dst: x86/fpu: 0xffff93d722877800 load: 0 xfeatures: 2 xcomp_bv: 8000000000000207 protection_keys-17351 [040] 59275.834274: x86_fpu_regs_activated: x86/fpu: 0xffff93d722877800 load: 1 xfeatures: 2 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834283: x86_fpu_regs_deactivated: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 2 xcomp_bv: 8000000000000207 protection_keys-17351 [040] 59275.834289: x86_fpu_regs_deactivated: x86/fpu: 0xffff93d722877800 load: 0 xfeatures: 2 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834296: x86_fpu_regs_activated: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 2 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834298: x86_fpu_regs_activated: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 2 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834406: x86_fpu_before_save: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 2 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834406: x86_fpu_after_save: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 202 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834408: x86_fpu_before_save: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 202 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834408: x86_fpu_after_save: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 202 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834654: x86_fpu_regs_deactivated: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 202 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834654: x86_fpu_dropped: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 202 xcomp_bv: 8000000000000207 auditd-1834 [036] 59275.834655: x86_fpu_regs_activated: x86/fpu: 0xffff93d713fef800 load: 1 xfeatures: 202 xcomp_bv: 8000000000000207 protection_keys-17350 [035] 59275.834665: x86_fpu_regs_deactivated: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 202 xcomp_bv: 8000000000000207 <...>-17285 [041] 59275.834679: x86_fpu_regs_activated: x86/fpu: 0xffff93d716d0df40 load: 1 xfeatures: 202 xcomp_bv: 8000000000000207 5. I instrumented parent child interactions using a separate standalone application(without the signal handler), it appears to work just fine. I see PRKU register staying intact swiching from parent to child. My suspicion at this point is towards the selftest tool protection_keys.c. I will keep looking. Any feedback would be much appreciated to debug further. Shaggy, Feel free to add if I missed something. Thanks Babu

4 years, 1 month

4
12
0 0

[PATCH v2 00/10] KVM: selftests: exercise userfaultfd minor faults

by Axel Rasmussen

Base ==== These patches are based upon Andrew Morton's v5.13-rc1-mmots-2021-05-13-17-23 tag. This is because this series depends on: - UFFD minor fault support for hugetlbfs (in v5.13-rc1) [1] - UFFD minor fault support for shmem (in Andrew's tree) [2] [1] https://lore.kernel.org/linux-fsdevel/20210301222728.176417-1-axelrasmussen… [2] https://lore.kernel.org/patchwork/cover/1420967/ Changelog ========= v1->v2: - Picked up Reviewed-by's. - Change backing_src_is_shared() to check the flags, instead of the type. This makes it robust to adding new backing source types in the future. - Add another commit which refactors setup_demand_paging() error handling. - Print UFFD ioctl type once in setup_demand_paging, instead of on every page-in operation. - Expand comment on why we use MFD_HUGETLB instead of MAP_HUGETLB. - Reworded comment on addr_gpa2alias. - Moved demand_paging_test.c timing calls outside of the if (), deduplicating them. - Split trivial comment / logging fixups into a separate commit. - Add another commit which prints a clarifying message on test skip. - Split the commit allowing backing src_type to be modified in two. - Split the commit adding the shmem backing type in two. - Rebased onto v5.13-rc1-mmots-2021-05-13-17-23. Overview ======== Minor fault handling is a new userfaultfd feature whose goal is generally to improve performance. In particular, it is intended for use with demand paging. There are more details in the cover letters for this new feature (linked above), but at a high level the idea is that we think of these three phases of live migration of a VM: 1. Precopy, where we copy "some" pages from the source to the target, while the VM is still running on the source machine. 2. Blackout, where execution stops on the source, and begins on the target. 3. Postcopy, where the VM is running on the target, some pages are already up to date, and others are not (because they weren't copied, or were modified after being copied). During postcopy, the first time the guest touches memory, we intercept a minor fault. Userspace checks whether or not the page is already up to date. If needed, we copy the final version of the page from the soure machine. This could be done with RDMA for example, to do it truly in place / with no copying. At this point, all that's left is to setup PTEs for the guest: so we issue UFFDIO_CONTINUE. No copying or page allocation needed. Because of this use case, it's useful to exercise this as part of the demand paging test. It lets us ensure the use case works correctly end-to-end, and also gives us an in-tree way to profile the end-to-end flow for future performance improvements. Axel Rasmussen (10): KVM: selftests: trivial comment/logging fixes KVM: selftests: simplify setup_demand_paging error handling KVM: selftests: print a message when skipping KVM tests KVM: selftests: compute correct demand paging size KVM: selftests: allow different backing source types KVM: selftests: refactor vm_mem_backing_src_type flags KVM: selftests: add shmem backing source type KVM: selftests: create alias mappings when using shared memory KVM: selftests: allow using UFFD minor faults for demand paging KVM: selftests: add shared hugetlbfs backing source type .../selftests/kvm/demand_paging_test.c | 175 +++++++++++------- .../testing/selftests/kvm/include/kvm_util.h | 1 + .../testing/selftests/kvm/include/test_util.h | 12 ++ tools/testing/selftests/kvm/lib/kvm_util.c | 84 ++++++++- .../selftests/kvm/lib/kvm_util_internal.h | 2 + tools/testing/selftests/kvm/lib/test_util.c | 51 +++-- 6 files changed, 238 insertions(+), 87 deletions(-) -- 2.31.1.751.gd2f1c929bd-goog

4 years, 1 month

4
31
0 0

[PATCH] kunit: tool: internal refactor of parser input handling

by Daniel Latypov

Note: this does not change the parser behavior at all (except for making one error message more useful). This is just an internal refactor. The TAP output parser currently operates over a List[str]. This works, but we only ever need to be able to "peek" at the current line and the ability to "pop" it off. Also, using a List means we need to wait for all the output before we can start parsing. While this is not an issue for most tests which are really lightweight, we do have some longer (~5 minutes) tests. This patch introduces an Input wrapper class that * Exposes a peek()/pop() interface instead of manipulating an array * this allows us to more easily add debugging code [1] * Can consume an input from a generator * we can now parse results as tests are running (the parser code currently doesn't print until the end, so no impact yet). * Tracks the current line number to print better error messages * Would allow us to add additional features more easily, e.g. storing N previous lines so we can print out invalid lines in context, etc. [1] The parsing logic is currently quite fragile. E.g. it'll often say the kernel "CRASHED" if there's something slightly wrong with the output format. When debugging a test that had some memory corruption issues, it resulted in very misleading errors from the parser. Now we could easily add this to trace all the lines consumed and why def pop(self) -> str: n = self._next + print(f'popping {n[0]}: {n[1].ljust(40, " ")}| caller={inspect.stack()[1].function}') Example output: popping 77: TAP version 14 | caller=parse_tap_header popping 78: 1..1 | caller=parse_test_plan popping 79: # Subtest: kunit_executor_test | caller=parse_subtest_header popping 80: 1..2 | caller=parse_subtest_plan popping 81: ok 1 - parse_filter_test | caller=parse_ok_not_ok_test_case popping 82: ok 2 - filter_subsuite_test | caller=parse_ok_not_ok_test_case popping 83: ok 1 - kunit_executor_test | caller=parse_ok_not_ok_test_suite If we introduce an invalid line, we can see the parser go down the wrong path: popping 77: TAP version 14 | caller=parse_tap_header popping 78: 1..1 | caller=parse_test_plan popping 79: # Subtest: kunit_executor_test | caller=parse_subtest_header popping 80: 1..2 | caller=parse_subtest_plan popping 81: 1..2 # this is invalid! | caller=parse_ok_not_ok_test_case popping 82: ok 1 - parse_filter_test | caller=parse_ok_not_ok_test_case popping 83: ok 2 - filter_subsuite_test | caller=parse_ok_not_ok_test_case popping 84: ok 1 - kunit_executor_test | caller=parse_ok_not_ok_test_case [ERROR] ran out of lines before end token Signed-off-by: Daniel Latypov <dlatypov(a)google.com> --- tools/testing/kunit/kunit_parser.py | 136 ++++++++++++++++--------- tools/testing/kunit/kunit_tool_test.py | 18 ++-- 2 files changed, 99 insertions(+), 55 deletions(-) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index e8bcc139702e..65adb386364a 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -47,22 +47,63 @@ class TestStatus(Enum): NO_TESTS = auto() FAILURE_TO_PARSE_TESTS = auto() +class Input: + """Provides a more convenient interface over isolate_kunit_output().""" + _lines: Iterator[Tuple[int, str]] + _next: Tuple[int, str] + _done: bool + + def __init__(self, lines: Iterator[Tuple[int, str]]): + self._lines = lines + self._done = False + self._next = (0, '') + self._get_next() + + def _get_next(self) -> None: + try: + self._next = next(self._lines) + except StopIteration: + self._done = True + + def peek(self) -> str: + return self._next[1] + + def pop(self) -> str: + n = self._next + self._get_next() + return n[1] + + def __bool__(self) -> bool: + return not self._done + + # Only used by kunit_tool_test.py. + def __iter__(self) -> Iterator[str]: + while bool(self): + yield self.pop() + + def line_number(self) -> int: + return self._next[0] + kunit_start_re = re.compile(r'TAP version [0-9]+$') kunit_end_re = re.compile('(List of all partitions:|' 'Kernel panic - not syncing: VFS:)') -def isolate_kunit_output(kernel_output) -> Iterator[str]: - started = False - for line in kernel_output: - line = line.rstrip() # line always has a trailing \n - if kunit_start_re.search(line): - prefix_len = len(line.split('TAP version')[0]) - started = True - yield line[prefix_len:] if prefix_len > 0 else line - elif kunit_end_re.search(line): - break - elif started: - yield line[prefix_len:] if prefix_len > 0 else line +def get_input(kernel_output: Iterable[str]) -> Input: + def isolate_kunit_output(kernel_output: Iterable[str]) -> Iterator[Tuple[int, str]]: + line_num = 0 + started = False + for line in kernel_output: + line_num += 1 + line = line.rstrip() # line always has a trailing \n + if kunit_start_re.search(line): + prefix_len = len(line.split('TAP version')[0]) + started = True + yield line_num, line[prefix_len:] + elif kunit_end_re.search(line): + break + elif started: + yield line_num, line[prefix_len:] + return Input(lines=isolate_kunit_output(kernel_output)) def raw_output(kernel_output) -> None: for line in kernel_output: @@ -97,14 +138,14 @@ def print_log(log) -> None: TAP_ENTRIES = re.compile(r'^(TAP|[\s]*ok|[\s]*not ok|[\s]*[0-9]+\.\.[0-9]+|[\s]*#).*$') -def consume_non_diagnostic(lines: List[str]) -> None: - while lines and not TAP_ENTRIES.match(lines[0]): - lines.pop(0) +def consume_non_diagnostic(lines: Input) -> None: + while lines and not TAP_ENTRIES.match(lines.peek()): + lines.pop() -def save_non_diagnostic(lines: List[str], test_case: TestCase) -> None: - while lines and not TAP_ENTRIES.match(lines[0]): - test_case.log.append(lines[0]) - lines.pop(0) +def save_non_diagnostic(lines: Input, test_case: TestCase) -> None: + while lines and not TAP_ENTRIES.match(lines.peek()): + test_case.log.append(lines.peek()) + lines.pop() OkNotOkResult = namedtuple('OkNotOkResult', ['is_ok','description', 'text']) @@ -112,18 +153,18 @@ OK_NOT_OK_SUBTEST = re.compile(r'^[\s]+(ok|not ok) [0-9]+ - (.*)$') OK_NOT_OK_MODULE = re.compile(r'^(ok|not ok) ([0-9]+) - (.*)$') -def parse_ok_not_ok_test_case(lines: List[str], test_case: TestCase) -> bool: +def parse_ok_not_ok_test_case(lines: Input, test_case: TestCase) -> bool: save_non_diagnostic(lines, test_case) if not lines: test_case.status = TestStatus.TEST_CRASHED return True - line = lines[0] + line = lines.peek() match = OK_NOT_OK_SUBTEST.match(line) while not match and lines: - line = lines.pop(0) + line = lines.pop() match = OK_NOT_OK_SUBTEST.match(line) if match: - test_case.log.append(lines.pop(0)) + test_case.log.append(lines.pop()) test_case.name = match.group(2) if test_case.status == TestStatus.TEST_CRASHED: return True @@ -138,14 +179,14 @@ def parse_ok_not_ok_test_case(lines: List[str], test_case: TestCase) -> bool: SUBTEST_DIAGNOSTIC = re.compile(r'^[\s]+# (.*)$') DIAGNOSTIC_CRASH_MESSAGE = re.compile(r'^[\s]+# .*?: kunit test case crashed!$') -def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool: +def parse_diagnostic(lines: Input, test_case: TestCase) -> bool: save_non_diagnostic(lines, test_case) if not lines: return False - line = lines[0] + line = lines.peek() match = SUBTEST_DIAGNOSTIC.match(line) if match: - test_case.log.append(lines.pop(0)) + test_case.log.append(lines.pop()) crash_match = DIAGNOSTIC_CRASH_MESSAGE.match(line) if crash_match: test_case.status = TestStatus.TEST_CRASHED @@ -153,7 +194,7 @@ def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool: else: return False -def parse_test_case(lines: List[str]) -> Optional[TestCase]: +def parse_test_case(lines: Input) -> Optional[TestCase]: test_case = TestCase() save_non_diagnostic(lines, test_case) while parse_diagnostic(lines, test_case): @@ -165,24 +206,24 @@ def parse_test_case(lines: List[str]) -> Optional[TestCase]: SUBTEST_HEADER = re.compile(r'^[\s]+# Subtest: (.*)$') -def parse_subtest_header(lines: List[str]) -> Optional[str]: +def parse_subtest_header(lines: Input) -> Optional[str]: consume_non_diagnostic(lines) if not lines: return None - match = SUBTEST_HEADER.match(lines[0]) + match = SUBTEST_HEADER.match(lines.peek()) if match: - lines.pop(0) + lines.pop() return match.group(1) else: return None SUBTEST_PLAN = re.compile(r'[\s]+[0-9]+\.\.([0-9]+)') -def parse_subtest_plan(lines: List[str]) -> Optional[int]: +def parse_subtest_plan(lines: Input) -> Optional[int]: consume_non_diagnostic(lines) - match = SUBTEST_PLAN.match(lines[0]) + match = SUBTEST_PLAN.match(lines.peek()) if match: - lines.pop(0) + lines.pop() return int(match.group(1)) else: return None @@ -199,17 +240,17 @@ def max_status(left: TestStatus, right: TestStatus) -> TestStatus: else: return TestStatus.SUCCESS -def parse_ok_not_ok_test_suite(lines: List[str], +def parse_ok_not_ok_test_suite(lines: Input, test_suite: TestSuite, expected_suite_index: int) -> bool: consume_non_diagnostic(lines) if not lines: test_suite.status = TestStatus.TEST_CRASHED return False - line = lines[0] + line = lines.peek() match = OK_NOT_OK_MODULE.match(line) if match: - lines.pop(0) + lines.pop() if match.group(1) == 'ok': test_suite.status = TestStatus.SUCCESS else: @@ -231,7 +272,7 @@ def bubble_up_test_case_errors(test_suite: TestSuite) -> TestStatus: max_test_case_status = bubble_up_errors(x.status for x in test_suite.cases) return max_status(max_test_case_status, test_suite.status) -def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[TestSuite]: +def parse_test_suite(lines: Input, expected_suite_index: int) -> Optional[TestSuite]: if not lines: return None consume_non_diagnostic(lines) @@ -257,26 +298,26 @@ def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[Te print_with_timestamp(red('[ERROR] ') + 'ran out of lines before end token') return test_suite else: - print('failed to parse end of suite' + lines[0]) + print(f'failed to parse end of suite "{name}", at line {lines.line_number()}: {lines.peek()}') return None TAP_HEADER = re.compile(r'^TAP version 14$') -def parse_tap_header(lines: List[str]) -> bool: +def parse_tap_header(lines: Input) -> bool: consume_non_diagnostic(lines) - if TAP_HEADER.match(lines[0]): - lines.pop(0) + if TAP_HEADER.match(lines.peek()): + lines.pop() return True else: return False TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)') -def parse_test_plan(lines: List[str]) -> Optional[int]: +def parse_test_plan(lines: Input) -> Optional[int]: consume_non_diagnostic(lines) - match = TEST_PLAN.match(lines[0]) + match = TEST_PLAN.match(lines.peek()) if match: - lines.pop(0) + lines.pop() return int(match.group(1)) else: return None @@ -284,7 +325,7 @@ def parse_test_plan(lines: List[str]) -> Optional[int]: def bubble_up_suite_errors(test_suites: Iterable[TestSuite]) -> TestStatus: return bubble_up_errors(x.status for x in test_suites) -def parse_test_result(lines: List[str]) -> TestResult: +def parse_test_result(lines: Input) -> TestResult: consume_non_diagnostic(lines) if not lines or not parse_tap_header(lines): return TestResult(TestStatus.NO_TESTS, [], lines) @@ -338,11 +379,12 @@ def print_and_count_results(test_result: TestResult) -> Tuple[int, int, int]: print_with_timestamp('') return total_tests, failed_tests, crashed_tests -def parse_run_tests(kernel_output) -> TestResult: +def parse_run_tests(kernel_output: Iterable[str]) -> TestResult: total_tests = 0 failed_tests = 0 crashed_tests = 0 - test_result = parse_test_result(list(isolate_kunit_output(kernel_output))) + lines = get_input(kernel_output) + test_result = parse_test_result(lines) if test_result.status == TestStatus.NO_TESTS: print(red('[ERROR] ') + yellow('no tests run!')) elif test_result.status == TestStatus.FAILURE_TO_PARSE_TESTS: diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 2e809dd956a7..e82678a25bef 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -11,6 +11,7 @@ from unittest import mock import tempfile, shutil # Handling test_tmpdir +import itertools import json import signal import os @@ -92,17 +93,18 @@ class KconfigTest(unittest.TestCase): class KUnitParserTest(unittest.TestCase): - def assertContains(self, needle, haystack): - for line in haystack: + def assertContains(self, needle: str, haystack: kunit_parser.Input): + # Clone the iterator so we can print the contents on failure. + copy, backup = itertools.tee(haystack) + for line in copy: if needle in line: return - raise AssertionError('"' + - str(needle) + '" not found in "' + str(haystack) + '"!') + raise AssertionError(f'"{needle}" not found in {list(backup)}!') def test_output_isolated_correctly(self): log_path = test_data_path('test_output_isolated_correctly.log') with open(log_path) as file: - result = kunit_parser.isolate_kunit_output(file.readlines()) + result = kunit_parser.get_input(file.readlines()) self.assertContains('TAP version 14', result) self.assertContains(' # Subtest: example', result) self.assertContains(' 1..2', result) @@ -113,7 +115,7 @@ class KUnitParserTest(unittest.TestCase): def test_output_with_prefix_isolated_correctly(self): log_path = test_data_path('test_pound_sign.log') with open(log_path) as file: - result = kunit_parser.isolate_kunit_output(file.readlines()) + result = kunit_parser.get_input(file.readlines()) self.assertContains('TAP version 14', result) self.assertContains(' # Subtest: kunit-resource-test', result) self.assertContains(' 1..5', result) @@ -159,7 +161,7 @@ class KUnitParserTest(unittest.TestCase): empty_log = test_data_path('test_is_test_passed-no_tests_run.log') with open(empty_log) as file: result = kunit_parser.parse_run_tests( - kunit_parser.isolate_kunit_output(file.readlines())) + kunit_parser.get_input(file.readlines())) self.assertEqual(0, len(result.suites)) self.assertEqual( kunit_parser.TestStatus.NO_TESTS, @@ -170,7 +172,7 @@ class KUnitParserTest(unittest.TestCase): print_mock = mock.patch('builtins.print').start() with open(crash_log) as file: result = kunit_parser.parse_run_tests( - kunit_parser.isolate_kunit_output(file.readlines())) + kunit_parser.get_input(file.readlines())) print_mock.assert_any_call(StrContains('no tests run!')) print_mock.stop() file.close() base-commit: c3d0e3fd41b7f0f5d5d5b6022ab7e813f04ea727 -- 2.31.1.818.g46aad6cb9e-goog

4 years, 1 month

2
2
0 0

[PATCH v6 1/3] selftests/sgx: Rename 'eenter' and 'sgx_call_vdso'

by Jarkko Sakkinen

Rename symbols for better clarity: * 'eenter' might be confused for directly calling ENCLU[EENTER]. It does not. It calls into the VDSO, which actually has the EENTER instruction. * 'sgx_call_vdso' is *only* used for entering the enclave. It's not some generic SGX call into the VDSO. Signed-off-by: Jarkko Sakkinen <jarkko(a)kernel.org> --- v3: Refine the commit message according to Dave's suggestions. v2: Refined the renames just a bit. tools/testing/selftests/sgx/call.S | 6 +++--- tools/testing/selftests/sgx/main.c | 25 +++++++++++++------------ tools/testing/selftests/sgx/main.h | 4 ++-- 3 files changed, 18 insertions(+), 17 deletions(-) diff --git a/tools/testing/selftests/sgx/call.S b/tools/testing/selftests/sgx/call.S index 4ecadc7490f4..b09a25890f3b 100644 --- a/tools/testing/selftests/sgx/call.S +++ b/tools/testing/selftests/sgx/call.S @@ -5,8 +5,8 @@ .text - .global sgx_call_vdso -sgx_call_vdso: + .global sgx_enter_enclave +sgx_enter_enclave: .cfi_startproc push %r15 .cfi_adjust_cfa_offset 8 @@ -27,7 +27,7 @@ sgx_call_vdso: .cfi_adjust_cfa_offset 8 push 0x38(%rsp) .cfi_adjust_cfa_offset 8 - call *eenter(%rip) + call *vdso_sgx_enter_enclave(%rip) add $0x10, %rsp .cfi_adjust_cfa_offset -0x10 pop %rbx diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c index d304a4044eb9..43da68388e25 100644 --- a/tools/testing/selftests/sgx/main.c +++ b/tools/testing/selftests/sgx/main.c @@ -21,7 +21,7 @@ #include "../kselftest.h" static const uint64_t MAGIC = 0x1122334455667788ULL; -vdso_sgx_enter_enclave_t eenter; +vdso_sgx_enter_enclave_t vdso_sgx_enter_enclave; struct vdso_symtab { Elf64_Sym *elf_symtab; @@ -149,7 +149,7 @@ int main(int argc, char *argv[]) { struct sgx_enclave_run run; struct vdso_symtab symtab; - Elf64_Sym *eenter_sym; + Elf64_Sym *sgx_enter_enclave_sym; uint64_t result = 0; struct encl encl; unsigned int i; @@ -194,29 +194,30 @@ int main(int argc, char *argv[]) if (!vdso_get_symtab(addr, &symtab)) goto err; - eenter_sym = vdso_symtab_get(&symtab, "__vdso_sgx_enter_enclave"); - if (!eenter_sym) + sgx_enter_enclave_sym = vdso_symtab_get(&symtab, "__vdso_sgx_enter_enclave"); + if (!sgx_enter_enclave_sym) goto err; - eenter = addr + eenter_sym->st_value; + vdso_sgx_enter_enclave = addr + sgx_enter_enclave_sym->st_value; - ret = sgx_call_vdso((void *)&MAGIC, &result, 0, EENTER, NULL, NULL, &run); - if (!report_results(&run, ret, result, "sgx_call_vdso")) + ret = sgx_enter_enclave((void *)&MAGIC, &result, 0, EENTER, + NULL, NULL, &run); + if (!report_results(&run, ret, result, "sgx_enter_enclave_unclobbered")) goto err; /* Invoke the vDSO directly. */ result = 0; - ret = eenter((unsigned long)&MAGIC, (unsigned long)&result, 0, EENTER, - 0, 0, &run); - if (!report_results(&run, ret, result, "eenter")) + ret = vdso_sgx_enter_enclave((unsigned long)&MAGIC, (unsigned long)&result, + 0, EENTER, 0, 0, &run); + if (!report_results(&run, ret, result, "sgx_enter_enclave")) goto err; /* And with an exit handler. */ run.user_handler = (__u64)user_handler; run.user_data = 0xdeadbeef; - ret = eenter((unsigned long)&MAGIC, (unsigned long)&result, 0, EENTER, - 0, 0, &run); + ret = vdso_sgx_enter_enclave((unsigned long)&MAGIC, (unsigned long)&result, + 0, EENTER, 0, 0, &run); if (!report_results(&run, ret, result, "user_handler")) goto err; diff --git a/tools/testing/selftests/sgx/main.h b/tools/testing/selftests/sgx/main.h index 67211a708f04..68672fd86cf9 100644 --- a/tools/testing/selftests/sgx/main.h +++ b/tools/testing/selftests/sgx/main.h @@ -35,7 +35,7 @@ bool encl_load(const char *path, struct encl *encl); bool encl_measure(struct encl *encl); bool encl_build(struct encl *encl); -int sgx_call_vdso(void *rdi, void *rsi, long rdx, u32 function, void *r8, void *r9, - struct sgx_enclave_run *run); +int sgx_enter_enclave(void *rdi, void *rsi, long rdx, u32 function, void *r8, void *r9, + struct sgx_enclave_run *run); #endif /* MAIN_H */ -- 2.31.1

4 years, 1 month

1
2
0 0

[PATCH] kselftest/arm64: Add missing newline to SVE test skipping output

by Mark Brown

The newline is expected to come from the caller but got missed for this test. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/arm64/fp/sve-probe-vls.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/arm64/fp/sve-probe-vls.c b/tools/testing/selftests/arm64/fp/sve-probe-vls.c index b29cbc642c57..76e138525d55 100644 --- a/tools/testing/selftests/arm64/fp/sve-probe-vls.c +++ b/tools/testing/selftests/arm64/fp/sve-probe-vls.c @@ -25,7 +25,7 @@ int main(int argc, char **argv) ksft_set_plan(2); if (!(getauxval(AT_HWCAP) & HWCAP_SVE)) - ksft_exit_skip("SVE not available"); + ksft_exit_skip("SVE not available\n"); /* * Enumerate up to SVE_VQ_MAX vector lengths -- 2.20.1

4 years, 1 month

2
1
0 0

[PATCH] selftests: Use kselftest skip code for skipped tests

by Po-Hsu Lin

There are several test cases still using exit 0 when they need to be skipped. Use kselftest framework skip code instead so it can help us to distinguish the proper return status. Criterion to filter out what should be fixed in selftests directory: grep -r "exit 0" -B1 | grep -i skip This change might cause some false-positives if people are running these test scripts directly and only checking their return codes, which will change from 0 to 4. However I think the impact should be small as most of our scripts here are already using this skip code. And there will be no such issue if running them with the kselftest framework. Signed-off-by: Po-Hsu Lin <po-hsu.lin(a)canonical.com> --- tools/testing/selftests/bpf/test_bpftool_build.sh | 5 ++++- tools/testing/selftests/bpf/test_xdp_meta.sh | 5 ++++- tools/testing/selftests/bpf/test_xdp_vlan.sh | 7 +++++-- tools/testing/selftests/net/fcnal-test.sh | 5 ++++- tools/testing/selftests/net/fib_rule_tests.sh | 7 +++++-- tools/testing/selftests/net/forwarding/lib.sh | 5 ++++- tools/testing/selftests/net/forwarding/router_mpath_nh.sh | 5 ++++- tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh | 5 ++++- tools/testing/selftests/net/run_afpackettests | 5 ++++- tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh | 9 ++++++--- tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh | 9 ++++++--- tools/testing/selftests/net/unicast_extensions.sh | 5 ++++- tools/testing/selftests/net/vrf_strict_mode_test.sh | 9 ++++++--- tools/testing/selftests/ptp/phc.sh | 7 +++++-- tools/testing/selftests/vm/charge_reserved_hugetlb.sh | 5 ++++- tools/testing/selftests/vm/hugetlb_reparenting_test.sh | 5 ++++- 16 files changed, 73 insertions(+), 25 deletions(-) diff --git a/tools/testing/selftests/bpf/test_bpftool_build.sh b/tools/testing/selftests/bpf/test_bpftool_build.sh index ac349a5..b6fab1e 100755 --- a/tools/testing/selftests/bpf/test_bpftool_build.sh +++ b/tools/testing/selftests/bpf/test_bpftool_build.sh @@ -1,6 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + case $1 in -h|--help) echo -e "$0 [-j <n>]" @@ -22,7 +25,7 @@ KDIR_ROOT_DIR=$(realpath $PWD/$SCRIPT_REL_DIR/../../../../) cd $KDIR_ROOT_DIR if [ ! -e tools/bpf/bpftool/Makefile ]; then echo -e "skip: bpftool files not found!\n" - exit 0 + exit $ksft_skip fi ERROR=0 diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh index 637fcf4..fd3f218 100755 --- a/tools/testing/selftests/bpf/test_xdp_meta.sh +++ b/tools/testing/selftests/bpf/test_xdp_meta.sh @@ -1,5 +1,8 @@ #!/bin/sh +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + cleanup() { if [ "$?" = "0" ]; then @@ -17,7 +20,7 @@ cleanup() ip link set dev lo xdp off 2>/dev/null > /dev/null if [ $? -ne 0 ];then echo "selftests: [SKIP] Could not run test without the ip xdp support" - exit 0 + exit $ksft_skip fi set -e diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index bb8b0da..1aa7404 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -2,6 +2,9 @@ # SPDX-License-Identifier: GPL-2.0 # Author: Jesper Dangaard Brouer <hawk(a)kernel.org> +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + # Allow wrapper scripts to name test if [ -z "$TESTNAME" ]; then TESTNAME=xdp_vlan @@ -94,7 +97,7 @@ while true; do -h | --help ) usage; echo "selftests: $TESTNAME [SKIP] usage help info requested" - exit 0 + exit $ksft_skip ;; * ) shift @@ -117,7 +120,7 @@ fi ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null if [ $? -ne 0 ]; then echo "selftests: $TESTNAME [SKIP] need ip xdp support" - exit 0 + exit $ksft_skip fi # Interactive mode likely require us to cleanup netns diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index a8ad928..9074e25 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -37,6 +37,9 @@ # # server / client nomenclature relative to ns-A +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + VERBOSE=0 NSA_DEV=eth1 @@ -3946,7 +3949,7 @@ fi which nettest >/dev/null if [ $? -ne 0 ]; then echo "'nettest' command not found; skipping tests" - exit 0 + exit $ksft_skip fi declare -i nfail=0 diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index a93e6b6..43ea840 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -3,6 +3,9 @@ # This test is for checking IPv4 and IPv6 FIB rules API +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + ret=0 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} @@ -238,12 +241,12 @@ run_fibrule_tests() if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" - exit 0 + exit $ksft_skip fi if [ ! -x "$(command -v ip)" ]; then echo "SKIP: Could not run test without ip tool" - exit 0 + exit $ksft_skip fi # start clean diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 42e28c9..eed9f08 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -4,6 +4,9 @@ ############################################################################## # Defines +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + # Can be overridden by the configuration file. PING=${PING:=ping} PING6=${PING6:=ping6} @@ -121,7 +124,7 @@ check_ethtool_lanes_support() if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" - exit 0 + exit $ksft_skip fi if [[ "$CHECK_TC" = "yes" ]]; then diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh index 76efb1f..bb7dc6d 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh @@ -1,6 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + ALL_TESTS=" ping_ipv4 ping_ipv6 @@ -411,7 +414,7 @@ ping_ipv6() ip nexthop ls >/dev/null 2>&1 if [ $? -ne 0 ]; then echo "Nexthop objects not supported; skipping tests" - exit 0 + exit $ksft_skip fi trap cleanup EXIT diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh index 4898dd4..e7bb976 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh @@ -1,6 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + ALL_TESTS=" ping_ipv4 ping_ipv6 @@ -386,7 +389,7 @@ ping_ipv6() ip nexthop ls >/dev/null 2>&1 if [ $? -ne 0 ]; then echo "Nexthop objects not supported; skipping tests" - exit 0 + exit $ksft_skip fi trap cleanup EXIT diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index 8b42e8b..a59cb6a 100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests @@ -1,9 +1,12 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + if [ $(id -u) != 0 ]; then echo $msg must be run as root >&2 - exit 0 + exit $ksft_skip fi ret=0 diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh index ad7a9fc..1003119 100755 --- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -163,6 +163,9 @@ # +---------------------------------------------------+ # +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + readonly LOCALSID_TABLE_ID=90 readonly IPv6_RT_NETWORK=fd00 readonly IPv4_HS_NETWORK=10.0.0 @@ -464,18 +467,18 @@ host_vpn_isolation_tests() if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" - exit 0 + exit $ksft_skip fi if [ ! -x "$(command -v ip)" ]; then echo "SKIP: Could not run test without ip tool" - exit 0 + exit $ksft_skip fi modprobe vrf &>/dev/null if [ ! -e /proc/sys/net/vrf/strict_mode ]; then echo "SKIP: vrf sysctl does not exist" - exit 0 + exit $ksft_skip fi cleanup &>/dev/null diff --git a/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh index 68708f5..b9b06ef 100755 --- a/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh @@ -164,6 +164,9 @@ # +---------------------------------------------------+ # +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + readonly LOCALSID_TABLE_ID=90 readonly IPv6_RT_NETWORK=fd00 readonly IPv6_HS_NETWORK=cafe @@ -472,18 +475,18 @@ host_vpn_isolation_tests() if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" - exit 0 + exit $ksft_skip fi if [ ! -x "$(command -v ip)" ]; then echo "SKIP: Could not run test without ip tool" - exit 0 + exit $ksft_skip fi modprobe vrf &>/dev/null if [ ! -e /proc/sys/net/vrf/strict_mode ]; then echo "SKIP: vrf sysctl does not exist" - exit 0 + exit $ksft_skip fi cleanup &>/dev/null diff --git a/tools/testing/selftests/net/unicast_extensions.sh b/tools/testing/selftests/net/unicast_extensions.sh index dbf0421..728e4d5 100755 --- a/tools/testing/selftests/net/unicast_extensions.sh +++ b/tools/testing/selftests/net/unicast_extensions.sh @@ -28,12 +28,15 @@ # These tests provide an easy way to flip the expected result of any # of these behaviors for testing kernel patches that change them. +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + # nettest can be run from PATH or from same directory as this selftest if ! which nettest >/dev/null; then PATH=$PWD:$PATH if ! which nettest >/dev/null; then echo "'nettest' command not found; skipping tests" - exit 0 + exit $ksft_skip fi fi diff --git a/tools/testing/selftests/net/vrf_strict_mode_test.sh b/tools/testing/selftests/net/vrf_strict_mode_test.sh index 18b982d..865d53c 100755 --- a/tools/testing/selftests/net/vrf_strict_mode_test.sh +++ b/tools/testing/selftests/net/vrf_strict_mode_test.sh @@ -3,6 +3,9 @@ # This test is designed for testing the new VRF strict_mode functionality. +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + ret=0 # identifies the "init" network namespace which is often called root network @@ -371,18 +374,18 @@ vrf_strict_mode_check_support() if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" - exit 0 + exit $ksft_skip fi if [ ! -x "$(command -v ip)" ]; then echo "SKIP: Could not run test without ip tool" - exit 0 + exit $ksft_skip fi modprobe vrf &>/dev/null if [ ! -e /proc/sys/net/vrf/strict_mode ]; then echo "SKIP: vrf sysctl does not exist" - exit 0 + exit $ksft_skip fi cleanup &> /dev/null diff --git a/tools/testing/selftests/ptp/phc.sh b/tools/testing/selftests/ptp/phc.sh index ac6e5a6..ca3c844c 100755 --- a/tools/testing/selftests/ptp/phc.sh +++ b/tools/testing/selftests/ptp/phc.sh @@ -1,6 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + ALL_TESTS=" settime adjtime @@ -13,12 +16,12 @@ DEV=$1 if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" - exit 0 + exit $ksft_skip fi if [[ "$DEV" == "" ]]; then echo "SKIP: PTP device not provided" - exit 0 + exit $ksft_skip fi require_command() diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh index 18d3368..fe8fcfb 100644 --- a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh @@ -1,11 +1,14 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + set -e if [[ $(id -u) -ne 0 ]]; then echo "This test must be run as root. Skipping..." - exit 0 + exit $ksft_skip fi fault_limit_file=limit_in_bytes diff --git a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh index d11d1fe..4a9a3af 100644 --- a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh +++ b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh @@ -1,11 +1,14 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + set -e if [[ $(id -u) -ne 0 ]]; then echo "This test must be run as root. Skipping..." - exit 0 + exit $ksft_skip fi usage_file=usage_in_bytes -- 2.7.4

4 years, 1 month

3
3
0 0

[PATCH] selftests: kvm: make allocation of extra memory take effect

by Zhenzhong Duan

The extra memory pages is missed to be allocated during VM creating. perf_test_util and kvm_page_table_test use it to alloc extra memory currently. Fix it by adding extra_mem_pages to the total memory calculation before allocate. Signed-off-by: Zhenzhong Duan <zhenzhong.duan(a)intel.com> --- tools/testing/selftests/kvm/lib/kvm_util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index fc83f6c5902d..159f4d62241d 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -295,7 +295,7 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, */ uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages; + uint64_t pages = DEFAULT_GUEST_PHY_PAGES + extra_mem_pages + vcpu_pages + extra_pg_pages; struct kvm_vm *vm; int i; -- 2.25.1

4 years, 1 month

4
4
0 0

[PATCH 1/2] KVM: Deliver VM fault signals to userspace

by James Houghton

This patch has been written to support page-ins using userfaultfd's SIGBUS feature. When a userfaultfd is created with UFFD_FEATURE_SIGBUS, `handle_userfault` will return VM_FAULT_SIGBUS instead of putting the calling thread to sleep. Normal (non-guest) threads that access memory that has been registered with a UFFD_FEATURE_SIGBUS userfaultfd receive a SIGBUS. When a vCPU gets an EPT page fault in a userfaultfd-registered region, KVM calls into `handle_userfault` to resolve the page fault. With UFFD_FEATURE_SIGBUS, VM_FAULT_SIGBUS is returned, but a SIGBUS is never delivered to the userspace thread. This patch propagates the VM_FAULT_SIGBUS error up to KVM, where we then send the signal. Upon receiving a VM_FAULT_SIGBUS, the KVM_RUN ioctl will exit to userspace. This functionality already exists. This allows a hypervisor to do page-ins with UFFD_FEATURE_SIGBUS: 1. Setup a SIGBUS handler to save the address of the SIGBUS (to a thread-local variable). 2. Enter the guest. 3. Immediately after KVM_RUN returns, check if the address has been set. 4. If an address has been set, we exited due to a page fault that we can now handle. 5. Userspace can do anything it wants to make the memory available, using MODE_NOWAKE for the UFFDIO memory installation ioctls. 6. Re-enter the guest. If the memory still isn't ready, this process will repeat. This style of demand paging is significantly faster than the standard poll/read/wake mechanism userfaultfd uses and completely bypasses the userfaultfd waitq. For a single vCPU, page-in throughput increases by about 3-4x. Signed-off-by: James Houghton <jthoughton(a)google.com> Suggested-by: Jue Wang <juew(a)google.com> --- include/linux/hugetlb.h | 2 +- include/linux/mm.h | 3 ++- mm/gup.c | 57 +++++++++++++++++++++++++++-------------- mm/hugetlb.c | 5 +++- virt/kvm/kvm_main.c | 30 +++++++++++++++++++++- 5 files changed, 74 insertions(+), 23 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b92f25ccef58..a777fb254df0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -119,7 +119,7 @@ int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_ar long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, unsigned long *, long, unsigned int, - int *); + int *, int *); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *); void __unmap_hugepage_range_final(struct mmu_gather *tlb, diff --git a/include/linux/mm.h b/include/linux/mm.h index 322ec61d0da7..1dcd1ac81992 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1824,7 +1824,8 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages, long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, - struct page **pages, unsigned int gup_flags); + struct page **pages, unsigned int gup_flags, + int *fault_error); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); diff --git a/mm/gup.c b/mm/gup.c index 0697134b6a12..ab55a67aef78 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -881,7 +881,8 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, * is, *@locked will be set to 0 and -EBUSY returned. */ static int faultin_page(struct vm_area_struct *vma, - unsigned long address, unsigned int *flags, int *locked) + unsigned long address, unsigned int *flags, int *locked, + int *fault_error) { unsigned int fault_flags = 0; vm_fault_t ret; @@ -906,6 +907,8 @@ static int faultin_page(struct vm_area_struct *vma, } ret = handle_mm_fault(vma, address, fault_flags, NULL); + if (fault_error) + *fault_error = ret; if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -996,6 +999,8 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * @vmas: array of pointers to vmas corresponding to each page. * Or NULL if the caller does not require them. * @locked: whether we're still with the mmap_lock held + * @fault_error: VM fault error from handle_mm_fault. NULL if the caller + * does not require this error. * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: @@ -1040,6 +1045,13 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * when it's been released. Otherwise, it must be held for either * reading or writing and will not be released. * + * If @fault_error != NULL, __get_user_pages will return the VM fault error + * from handle_mm_fault() in this argument in the event of a VM fault error. + * On success (ret == nr_pages) fault_error is zero. + * On failure (ret != nr_pages) fault_error may still be 0 if the error did + * not originate from handle_mm_fault(). + * + * * In most cases, get_user_pages or get_user_pages_fast should be used * instead of __get_user_pages. __get_user_pages should be used only if * you need some special @gup_flags. @@ -1047,7 +1059,8 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) static long __get_user_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas, int *locked) + struct vm_area_struct **vmas, int *locked, + int *fault_error) { long ret = 0, i = 0; struct vm_area_struct *vma = NULL; @@ -1097,7 +1110,7 @@ static long __get_user_pages(struct mm_struct *mm, if (is_vm_hugetlb_page(vma)) { i = follow_hugetlb_page(mm, vma, pages, vmas, &start, &nr_pages, i, - gup_flags, locked); + gup_flags, locked, fault_error); if (locked && *locked == 0) { /* * We've got a VM_FAULT_RETRY @@ -1124,7 +1137,8 @@ static long __get_user_pages(struct mm_struct *mm, page = follow_page_mask(vma, start, foll_flags, &ctx); if (!page) { - ret = faultin_page(vma, start, &foll_flags, locked); + ret = faultin_page(vma, start, &foll_flags, locked, + fault_error); switch (ret) { case 0: goto retry; @@ -1280,7 +1294,8 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, struct page **pages, struct vm_area_struct **vmas, int *locked, - unsigned int flags) + unsigned int flags, + int *fault_error) { long ret, pages_done; bool lock_dropped; @@ -1311,7 +1326,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, lock_dropped = false; for (;;) { ret = __get_user_pages(mm, start, nr_pages, flags, pages, - vmas, locked); + vmas, locked, fault_error); if (!locked) /* VM_FAULT_RETRY couldn't trigger, bypass */ return ret; @@ -1371,7 +1386,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, *locked = 1; ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED, - pages, NULL, locked); + pages, NULL, locked, fault_error); if (!*locked) { /* Continue to retry until we succeeded */ BUG_ON(ret != 0); @@ -1458,7 +1473,7 @@ long populate_vma_page_range(struct vm_area_struct *vma, * not result in a stack expansion that recurses back here. */ return __get_user_pages(mm, start, nr_pages, gup_flags, - NULL, NULL, locked); + NULL, NULL, locked, NULL); } /* @@ -1524,7 +1539,7 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, struct vm_area_struct **vmas, int *locked, - unsigned int foll_flags) + unsigned int foll_flags, int *fault_error) { struct vm_area_struct *vma; unsigned long vm_flags; @@ -1590,7 +1605,8 @@ struct page *get_dump_page(unsigned long addr) if (mmap_read_lock_killable(mm)) return NULL; ret = __get_user_pages_locked(mm, addr, 1, &page, NULL, &locked, - FOLL_FORCE | FOLL_DUMP | FOLL_GET); + FOLL_FORCE | FOLL_DUMP | FOLL_GET, + NULL); if (locked) mmap_read_unlock(mm); @@ -1704,11 +1720,11 @@ static long __gup_longterm_locked(struct mm_struct *mm, if (!(gup_flags & FOLL_LONGTERM)) return __get_user_pages_locked(mm, start, nr_pages, pages, vmas, - NULL, gup_flags); + NULL, gup_flags, NULL); flags = memalloc_pin_save(); do { rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, - NULL, gup_flags); + NULL, gup_flags, NULL); if (rc <= 0) break; rc = check_and_migrate_movable_pages(rc, pages, gup_flags); @@ -1764,7 +1780,8 @@ static long __get_user_pages_remote(struct mm_struct *mm, return __get_user_pages_locked(mm, start, nr_pages, pages, vmas, locked, - gup_flags | FOLL_TOUCH | FOLL_REMOTE); + gup_flags | FOLL_TOUCH | FOLL_REMOTE, + NULL); } /** @@ -1941,7 +1958,7 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages, return __get_user_pages_locked(current->mm, start, nr_pages, pages, NULL, locked, - gup_flags | FOLL_TOUCH); + gup_flags | FOLL_TOUCH, NULL); } EXPORT_SYMBOL(get_user_pages_locked); @@ -1961,7 +1978,8 @@ EXPORT_SYMBOL(get_user_pages_locked); * (e.g. FOLL_FORCE) are not required. */ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, - struct page **pages, unsigned int gup_flags) + struct page **pages, unsigned int gup_flags, + int *fault_error) { struct mm_struct *mm = current->mm; int locked = 1; @@ -1978,7 +1996,8 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, mmap_read_lock(mm); ret = __get_user_pages_locked(mm, start, nr_pages, pages, NULL, - &locked, gup_flags | FOLL_TOUCH); + &locked, gup_flags | FOLL_TOUCH, + fault_error); if (locked) mmap_read_unlock(mm); return ret; @@ -2550,7 +2569,7 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages, mmap_read_unlock(current->mm); } else { ret = get_user_pages_unlocked(start, nr_pages, - pages, gup_flags); + pages, gup_flags, NULL); } return ret; @@ -2880,7 +2899,7 @@ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, return -EINVAL; gup_flags |= FOLL_PIN; - return get_user_pages_unlocked(start, nr_pages, pages, gup_flags); + return get_user_pages_unlocked(start, nr_pages, pages, gup_flags, NULL); } EXPORT_SYMBOL(pin_user_pages_unlocked); @@ -2909,6 +2928,6 @@ long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, gup_flags |= FOLL_PIN; return __get_user_pages_locked(current->mm, start, nr_pages, pages, NULL, locked, - gup_flags | FOLL_TOUCH); + gup_flags | FOLL_TOUCH, NULL); } EXPORT_SYMBOL(pin_user_pages_locked); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3db405dea3dc..889ac33d57d5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5017,7 +5017,8 @@ static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma, long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, unsigned long *nr_pages, - long i, unsigned int flags, int *locked) + long i, unsigned int flags, int *locked, + int *fault_error) { unsigned long pfn_offset; unsigned long vaddr = *position; @@ -5103,6 +5104,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, } ret = hugetlb_fault(mm, vma, vaddr, fault_flags); if (ret & VM_FAULT_ERROR) { + if (fault_error) + *fault_error = ret; err = vm_fault_to_errno(ret, flags); remainder = 0; break; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2799c6660cce..0a20d926ae32 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2004,6 +2004,30 @@ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault, return false; } +static void kvm_send_vm_fault_signal(int fault_error, int errno, + unsigned long address, + struct task_struct *tsk) +{ + kernel_siginfo_t info; + + clear_siginfo(&info); + + if (fault_error == VM_FAULT_SIGBUS) + info.si_signo = SIGBUS; + else if (fault_error == VM_FAULT_SIGSEGV) + info.si_signo = SIGSEGV; + else + // Other fault errors should not result in a signal. + return; + + info.si_errno = errno; + info.si_code = BUS_ADRERR; + info.si_addr = (void __user *)address; + info.si_addr_lsb = PAGE_SHIFT; + + send_sig_info(info.si_signo, &info, tsk); +} + /* * The slow path to get the pfn of the specified host virtual address, * 1 indicates success, -errno is returned if error is detected. @@ -2014,6 +2038,7 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, unsigned int flags = FOLL_HWPOISON; struct page *page; int npages = 0; + int fault_error; might_sleep(); @@ -2025,7 +2050,10 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, if (async) flags |= FOLL_NOWAIT; - npages = get_user_pages_unlocked(addr, 1, &page, flags); + npages = get_user_pages_unlocked(addr, 1, &page, flags, &fault_error); + if (fault_error & VM_FAULT_ERROR) + kvm_send_vm_fault_signal(fault_error, npages, addr, current); + if (npages != 1) return npages; -- 2.31.1.751.gd2f1c929bd-goog

4 years, 1 month

3
5
0 0

[PATCH 1/2] kselftest/vm: Rename TARGETS to BUILD_TARGETS

by Alistair Popple

The TARGETS variable can be used when building selftests to specify a subset of selftests to build and run like so: make -C tools/testing/selftests TARGETS=ptrace run_tests However specifying TARGETS=vm results in the following build error as the TARGETS variable is used internally in the Makefile: make[1]: *** No rule to make target 'vm.c', needed by 'linux/kselftest/vm/vm_32'. Stop. Fix this by renaming the vm Makefile TARGETS variable to BUILD_TARGETS. Signed-off-by: Alistair Popple <apopple(a)nvidia.com> --- tools/testing/selftests/vm/Makefile | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 73e1cc96d7c2..110751ce8701 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -49,9 +49,9 @@ CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_progra 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) +BUILD_TARGETS := protection_keys +BINARIES_32 := $(BUILD_TARGETS:%=%_32) +BINARIES_64 := $(BUILD_TARGETS:%=%_64) ifeq ($(CAN_BUILD_WITH_NOPIE),1) CFLAGS += -no-pie @@ -104,7 +104,7 @@ $(BINARIES_32): CFLAGS += -m32 $(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)))) +$(foreach t,$(BUILD_TARGETS),$(eval $(call gen-target-rule-32,$(t)))) endif ifeq ($(CAN_BUILD_X86_64),1) @@ -112,7 +112,7 @@ $(BINARIES_64): CFLAGS += -m64 $(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)))) +$(foreach t,$(BUILD_TARGETS),$(eval $(call gen-target-rule-64,$(t)))) endif # x86_64 users should be encouraged to install 32-bit libraries -- 2.20.1

4 years, 1 month

1
1
0 0

[PATCH v2 1/2] KVM: selftests: Keep track of memslots more efficiently

by Maciej S. Szmigiero

From: "Maciej S. Szmigiero" <maciej.szmigiero(a)oracle.com> The KVM selftest framework was using a simple list for keeping track of the memslots currently in use. This resulted in lookups and adding a single memslot being O(n), the later due to linear scanning of the existing memslot set to check for the presence of any conflicting entries. Before this change, benchmarking high count of memslots was more or less impossible as pretty much all the benchmark time was spent in the selftest framework code. We can simply use a rbtree for keeping track of both of gfn and hva. We don't need an interval tree for hva here as we can't have overlapping memslots because we allocate a completely new memory chunk for each new memslot. Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero(a)oracle.com> Reviewed-by: Andrew Jones <drjones(a)redhat.com> --- Changes from v1: * Add Andrew's Reviewed-by: tag tools/testing/selftests/kvm/Makefile | 2 +- tools/testing/selftests/kvm/lib/kvm_util.c | 141 ++++++++++++++---- .../selftests/kvm/lib/kvm_util_internal.h | 15 +- tools/testing/selftests/kvm/lib/rbtree.c | 1 + 4 files changed, 124 insertions(+), 35 deletions(-) create mode 100644 tools/testing/selftests/kvm/lib/rbtree.c diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index a6d61f451f88..c30a21c1d676 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -33,7 +33,7 @@ ifeq ($(ARCH),s390) UNAME_M := s390x endif -LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c +LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index e5fbf16f725b..69ee0a72c7d8 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -197,7 +197,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_ASSERT(vm != NULL, "Insufficient Memory"); INIT_LIST_HEAD(&vm->vcpus); - INIT_LIST_HEAD(&vm->userspace_mem_regions); + vm->regions.gpa_tree = RB_ROOT; + vm->regions.hva_tree = RB_ROOT; + hash_init(vm->regions.slot_hash); vm->mode = mode; vm->type = 0; @@ -349,13 +351,14 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, */ void kvm_vm_restart(struct kvm_vm *vmp, int perm) { + int ctr; struct userspace_mem_region *region; vm_open(vmp, perm); if (vmp->has_irqchip) vm_create_irqchip(vmp); - list_for_each_entry(region, &vmp->userspace_mem_regions, list) { + hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) { int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, &region->region); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" @@ -418,14 +421,21 @@ uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) static struct userspace_mem_region * userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + for (node = vm->regions.gpa_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, gpa_node); uint64_t existing_start = region->region.guest_phys_addr; uint64_t existing_end = region->region.guest_phys_addr + region->region.memory_size - 1; if (start <= existing_end && end >= existing_start) return region; + + if (start < existing_start) + node = node->rb_left; + else + node = node->rb_right; } return NULL; @@ -540,11 +550,16 @@ void kvm_vm_release(struct kvm_vm *vmp) } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region) + struct userspace_mem_region *region, + bool unlink) { int ret; - list_del(&region->list); + if (unlink) { + rb_erase(&region->gpa_node, &vm->regions.gpa_tree); + rb_erase(&region->hva_node, &vm->regions.hva_tree); + hash_del(&region->slot_node); + } region->region.memory_size = 0; ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region); @@ -563,14 +578,16 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, */ void kvm_vm_free(struct kvm_vm *vmp) { - struct userspace_mem_region *region, *tmp; + int ctr; + struct hlist_node *node; + struct userspace_mem_region *region; if (vmp == NULL) return; /* Free userspace_mem_regions. */ - list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list) - __vm_mem_region_delete(vmp, region); + hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) + __vm_mem_region_delete(vmp, region, false); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -652,6 +669,57 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) return 0; } +static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &gpa_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), gpa_node); + parent = *cur; + if (region->region.guest_phys_addr < + cregion->region.guest_phys_addr) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->region.guest_phys_addr != + cregion->region.guest_phys_addr, + "Duplicate GPA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(&region->gpa_node, parent, cur); + rb_insert_color(&region->gpa_node, gpa_tree); +} + +static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &hva_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), hva_node); + parent = *cur; + if (region->host_mem < cregion->host_mem) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->host_mem != + cregion->host_mem, + "Duplicate HVA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(&region->hva_node, parent, cur); + rb_insert_color(&region->hva_node, hva_tree); +} + /* * VM Userspace Memory Region Add * @@ -716,7 +784,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, (uint64_t) region->region.memory_size); /* Confirm no region with the requested slot already exists. */ - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + slot) { if (region->region.slot != slot) continue; @@ -796,8 +865,10 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, ret, errno, slot, flags, guest_paddr, (uint64_t) region->region.memory_size); - /* Add to linked-list of memory regions. */ - list_add(&region->list, &vm->userspace_mem_regions); + /* Add to quick lookup data structures */ + vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); + vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region); + hash_add(vm->regions.slot_hash, &region->slot_node, slot); } /* @@ -820,10 +891,10 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + memslot) if (region->region.slot == memslot) return region; - } fprintf(stderr, "No mem region with the requested slot found,\n" " requested slot: %u\n", memslot); @@ -908,7 +979,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) */ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) { - __vm_mem_region_delete(vm, memslot2region(vm, slot)); + __vm_mem_region_delete(vm, memslot2region(vm, slot), true); } /* @@ -1180,16 +1251,14 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((gpa >= region->region.guest_phys_addr) - && (gpa <= (region->region.guest_phys_addr - + region->region.memory_size - 1))) - return (void *) ((uintptr_t) region->host_mem - + (gpa - region->region.guest_phys_addr)); + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) { + TEST_FAIL("No vm physical memory at 0x%lx", gpa); + return NULL; } - TEST_FAIL("No vm physical memory at 0x%lx", gpa); - return NULL; + return (void *)((uintptr_t)region->host_mem + + (gpa - region->region.guest_phys_addr)); } /* @@ -1211,15 +1280,22 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) */ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) { - struct userspace_mem_region *region; + struct rb_node *node; + + for (node = vm->regions.hva_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, hva_node); + + if (hva >= region->host_mem) { + if (hva <= (region->host_mem + + region->region.memory_size - 1)) + return (vm_paddr_t)((uintptr_t) + region->region.guest_phys_addr + + (hva - (uintptr_t)region->host_mem)); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((hva >= region->host_mem) - && (hva <= (region->host_mem - + region->region.memory_size - 1))) - return (vm_paddr_t) ((uintptr_t) - region->region.guest_phys_addr - + (hva - (uintptr_t) region->host_mem)); + node = node->rb_right; + } else + node = node->rb_left; } TEST_FAIL("No mapping to a guest physical address, hva: %p", hva); @@ -1745,6 +1821,7 @@ int _kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) */ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { + int ctr; struct userspace_mem_region *region; struct vcpu *vcpu; @@ -1752,7 +1829,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd); fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size); fprintf(stream, "%*sMem Regions:\n", indent, ""); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) { fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx " "host_virt: %p\n", indent + 2, "", (uint64_t) region->region.guest_phys_addr, diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 34465dc562d8..af310110602b 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -8,6 +8,9 @@ #ifndef SELFTEST_KVM_UTIL_INTERNAL_H #define SELFTEST_KVM_UTIL_INTERNAL_H +#include "linux/hashtable.h" +#include "linux/rbtree.h" + #include "sparsebit.h" #define KVM_DEV_PATH "/dev/kvm" @@ -20,7 +23,9 @@ struct userspace_mem_region { void *host_mem; void *mmap_start; size_t mmap_size; - struct list_head list; + struct rb_node gpa_node; + struct rb_node hva_node; + struct hlist_node slot_node; }; struct vcpu { @@ -33,6 +38,12 @@ struct vcpu { uint32_t dirty_gfns_count; }; +struct userspace_mem_regions { + struct rb_root gpa_tree; + struct rb_root hva_tree; + DECLARE_HASHTABLE(slot_hash, 9); +}; + struct kvm_vm { int mode; unsigned long type; @@ -45,7 +56,7 @@ struct kvm_vm { unsigned int va_bits; uint64_t max_gfn; struct list_head vcpus; - struct list_head userspace_mem_regions; + struct userspace_mem_regions regions; struct sparsebit *vpages_valid; struct sparsebit *vpages_mapped; bool has_irqchip; diff --git a/tools/testing/selftests/kvm/lib/rbtree.c b/tools/testing/selftests/kvm/lib/rbtree.c new file mode 100644 index 000000000000..a703f0194ea3 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/rbtree.c @@ -0,0 +1 @@ +#include "../../../../lib/rbtree.c"

4 years, 1 month

2
2
0 0

[PATCH v5 26/28] selftest/x86/amx: Test case for AMX state copy optimization in signal delivery

by Chang S. Bae

Add a test case to verify that unused states are excluded, by leaving a known pattern on the signal stack and verifying that it is still intact after taking a subsequent signal. Signed-off-by: Chang S. Bae <chang.seok.bae(a)intel.com> Reviewed-by: Len Brown <len.brown(a)intel.com> Cc: x86(a)kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org --- Changes from v4: * Separated out as a new patch. * Improved the test routine by explicitly checking sigframe write. --- tools/testing/selftests/x86/amx.c | 137 ++++++++++++++++++++++++++++++ 1 file changed, 137 insertions(+) diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c index 7d177c03cdcf..c5a5582e2b6f 100644 --- a/tools/testing/selftests/x86/amx.c +++ b/tools/testing/selftests/x86/amx.c @@ -562,6 +562,142 @@ static void test_ptrace(void) test_tile_write(); } +/* Signal handling test */ + +static bool init_tiledata_state_before_signal; +static bool load_tiledata_at_first; +static bool sigalarmed, sigused; + +#define SIGFRAME_TILEDATA_SIGNATURE 0xFF + +static void handle_sigusr1(int sig, siginfo_t *info, void *ctx_void) +{ + void *xsave = ((ucontext_t *)ctx_void)->uc_mcontext.fpregs; + + memset(xsave + xsave_xtiledata_offset, SIGFRAME_TILEDATA_SIGNATURE, xsave_xtiledata_size); + + sigused = true; +} + +static void handle_sigalrm(int sig, siginfo_t *info, void *ctx_void) +{ + void *xsave = ((ucontext_t *)ctx_void)->uc_mcontext.fpregs; + char d = SIGFRAME_TILEDATA_SIGNATURE; + bool written = false; + int i; + + for (i = 0; i < xsave_xtiledata_size; i++) { + written = memcmp(xsave + xsave_xtiledata_offset + i, &d, 1); + if (written) + break; + } + + if (__xgetbv(1) & XFEATURE_MASK_XTILEDATA) + err(1, "tile data state at signal delivery"); + + if (init_tiledata_state_before_signal && written) { + errs++; + printf("[FAIL]\tTile data was %swritten on sigframe.\n", !written ? "not " : ""); + } + + set_xstatebv(xsave_buffer, XFEATURE_MASK_XTILEDATA); + set_tiledata(xsave_buffer + xsave_xtiledata_offset); + xrstor(xsave_buffer, -1, -1); + sigalarmed = true; +} + +static void test_signal_handling(void) +{ + pid_t child; + + sigalarmed = false; + sigused = false; + + child = fork(); + if (child < 0) { + err(1, "fork"); + } else if (child > 0) { + do { + int status; + + wait(&status); + if (WIFSTOPPED(status)) + kill(child, SIGCONT); + else if (WIFEXITED(status) && !WEXITSTATUS(status)) + break; + else + err(1, "signal test child"); + } while (1); + return; + } + + printf("\tBefore signal, load tile data -- %s, re-initialized -- %s:\n", + load_tiledata_at_first ? "yes" : "no", + init_tiledata_state_before_signal ? "yes" : "no"); + + syscall(SYS_arch_prctl, ARCH_GET_XSTATE, XFEATURE_MASK_XTILE); + + raise(SIGUSR1); + if (!sigused) + err(1, "SIGUSR1"); + + if (load_tiledata_at_first) { + set_xstatebv(xsave_buffer, XFEATURE_MASK_XTILEDATA); + set_tiledata(xsave_buffer + xsave_xtiledata_offset); + xrstor(xsave_buffer, -1, -1); + memcpy(tiledata, xsave_buffer + xsave_xtiledata_offset, xsave_xtiledata_size); + } + + if (init_tiledata_state_before_signal) { + set_xstatebv(xsave_buffer, 0); + xrstor(xsave_buffer, -1, -1); + memset(tiledata, 0, xsave_xtiledata_size); + } + + raise(SIGALRM); + if (!sigalarmed) + err(1, "SIGALRM"); + + __xsave(xsave_buffer, XFEATURE_MASK_XTILEDATA, 0); + if (memcmp(tiledata, xsave_buffer + xsave_xtiledata_offset, xsave_xtiledata_size)) { + errs++; + printf("[FAIL]\tTile data was not restored at sigreturn\n"); + } + + if (errs) + nerrs++; + else + printf("[OK]\tTile data was %swritten on sigframe and restored at sigreturn\n", + init_tiledata_state_before_signal ? "not " : ""); + _exit(0); +} + +static void test_signal(void) +{ + printf("[RUN]\tCheck tile data state in signal path:\n"); + + sethandler(SIGALRM, handle_sigalrm, 0); + sethandler(SIGUSR1, handle_sigusr1, 0); + + load_tiledata_at_first = false; + init_tiledata_state_before_signal = true; + errs = 0; + test_signal_handling(); + + load_tiledata_at_first = true; + init_tiledata_state_before_signal = false; + errs = 0; + test_signal_handling(); + + load_tiledata_at_first = true; + init_tiledata_state_before_signal = true; + errs = 0; + test_signal_handling(); + + clearhandler(SIGALRM); + clearhandler(SIGUSR1); +} + int main(void) { /* Check hardware availability at first */ @@ -592,6 +728,7 @@ int main(void) test_fork(); test_context_switch(); test_ptrace(); + test_signal(); clearhandler(SIGSEGV); -- 2.17.1

4 years, 1 month

1
0
0 0

[PATCH v5 23/28] selftest/x86/amx: Test cases for the AMX state management

by Chang S. Bae

This selftest verifies that the xstate arch_prctl works for AMX state and that a forked task has the AMX state in the INIT-state. In addition, this test verifies that the kernel correctly context switches unique AMX data, when multiple threads are using AMX. Finally, the test verifies that ptrace() can insert data into existing threads. These test cases do not depend on AMX compiler support, as they employ userspace-XSAVE directly to access AMX state. Signed-off-by: Chang S. Bae <chang.seok.bae(a)intel.com> Reviewed-by: Len Brown <len.brown(a)intel.com> Cc: linux-kernel(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org --- Changes from v4: * Added test for arch_prctl. * Excluded tile config details to focus on testing the kernel's ability to manage dynamic user state. * Removed tile instructions. * Simplified the fork() and ptrace() test routine. * Massaged the changelog. Changes from v2: * Updated the test messages and the changelog as tile data is not inherited to a child anymore. * Removed bytecode for the instructions already supported by binutils. * Changed to check the XSAVE availability in a reliable way. Changes from v1: * Removed signal testing code --- tools/testing/selftests/x86/Makefile | 2 +- tools/testing/selftests/x86/amx.c | 601 +++++++++++++++++++++++++++ 2 files changed, 602 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/x86/amx.c diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 333980375bc7..2f7feb03867b 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -17,7 +17,7 @@ TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer -TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering +TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering amx # Some selftests require 32bit support enabled also on 64bit systems TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c new file mode 100644 index 000000000000..7d177c03cdcf --- /dev/null +++ b/tools/testing/selftests/x86/amx.c @@ -0,0 +1,601 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <err.h> +#include <errno.h> +#include <elf.h> +#include <pthread.h> +#include <setjmp.h> +#include <stdio.h> +#include <string.h> +#include <stdbool.h> +#include <unistd.h> +#include <x86intrin.h> + +#include <linux/futex.h> + +#include <sys/ptrace.h> +#include <sys/shm.h> +#include <sys/syscall.h> +#include <sys/wait.h> +#include <sys/uio.h> + +#ifndef __x86_64__ +# error This test is 64-bit only +#endif + +static inline uint64_t __xgetbv(uint32_t index) +{ + uint32_t eax, edx; + + asm volatile("xgetbv;" + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax + ((uint64_t)edx << 32); +} + +static inline void __cpuid(uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx) +{ + asm volatile("cpuid;" + : "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline void __xsave(void *buffer, uint32_t lo, uint32_t hi) +{ + asm volatile("xsave (%%rdi)" + : : "D" (buffer), "a" (lo), "d" (hi) + : "memory"); +} + +static inline void __xrstor(void *buffer, uint32_t lo, uint32_t hi) +{ + asm volatile("xrstor (%%rdi)" + : : "D" (buffer), "a" (lo), "d" (hi)); +} + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static jmp_buf jmpbuf; + +/* Hardware info check: */ + +static bool xsave_disabled; + +static void handle_sigill(int sig, siginfo_t *si, void *ctx_void) +{ + xsave_disabled = true; + siglongjmp(jmpbuf, 1); +} + +#define XFEATURE_XTILECFG 17 +#define XFEATURE_XTILEDATA 18 +#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG) +#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA) +#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA) + +static inline bool check_xsave_capability(void) +{ + sethandler(SIGILL, handle_sigill, 0); + + if ((!sigsetjmp(jmpbuf, 1)) && (__xgetbv(0) & XFEATURE_MASK_XTILEDATA)) { + clearhandler(SIGILL); + return true; + } + + clearhandler(SIGILL); + return false; +} + +static uint32_t xsave_size; + +static uint32_t xsave_xtiledata_offset; +static uint32_t xsave_xtiledata_size; + +static uint32_t xsave_xtilecfg_offset; +static uint32_t xsave_xtilecfg_size; + +#define XSTATE_CPUID 0xd +#define XSTATE_USER_STATE_SUBLEAVE 0x0 + +static void check_cpuid(void) +{ + uint32_t eax, ebx, ecx, edx; + + eax = XSTATE_CPUID; + ecx = XSTATE_USER_STATE_SUBLEAVE; + + __cpuid(&eax, &ebx, &ecx, &edx); + if (!ebx) + err(1, "xstate cpuid: xsave size"); + + xsave_size = ebx; + + eax = XSTATE_CPUID; + ecx = XFEATURE_XTILECFG; + + __cpuid(&eax, &ebx, &ecx, &edx); + if (!eax || !ebx) + err(1, "xstate cpuid: tile config state"); + + xsave_xtilecfg_size = eax; + xsave_xtilecfg_offset = ebx; + + eax = XSTATE_CPUID; + ecx = XFEATURE_XTILEDATA; + + __cpuid(&eax, &ebx, &ecx, &edx); + if (!eax || !ebx) + err(1, "xstate cpuid: tile data state"); + + xsave_xtiledata_size = eax; + xsave_xtiledata_offset = ebx; +} + +/* The helpers for managing XSAVE buffer and tile states: */ + +#define XSAVE_HDR_OFFSET 512 + +static inline uint64_t get_xstatebv(void *xsave) +{ + return *(uint64_t *)(xsave + XSAVE_HDR_OFFSET); +} + +static inline void set_xstatebv(void *xsave, uint64_t bv) +{ + *(uint64_t *)(xsave + XSAVE_HDR_OFFSET) = bv; +} + +static void set_tiledata(void *tiledata) +{ + int *ptr = tiledata; + int data = rand(); + int i; + + for (i = 0; i < xsave_xtiledata_size / sizeof(int); i++, ptr++) + *ptr = data; +} + +static void *xsave_buffer, *tiledata; +static int nerrs, errs; + +static void handle_sigsegv(int sig, siginfo_t *si, void *ctx_void) +{ + siglongjmp(jmpbuf, 1); +} + +static bool xrstor(void *buffer, uint32_t lo, uint32_t hi) +{ + if (!sigsetjmp(jmpbuf, 1)) { + __xrstor(buffer, lo, hi); + return true; + } else { + return false; + } +} + +/* arch_prctl test */ + +#define ARCH_GET_XSTATE 0x1021 +#define ARCH_PUT_XSTATE 0x1022 + +#define ARCH_PRCTL_REPEAT 10 + +static void test_arch_prctl(void) +{ + bool xfd_armed; + pid_t child; + int rc, i; + + child = fork(); + if (child < 0) { + err(1, "fork"); + } else if (child > 0) { + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + err(1, "arch_prctl test child"); + return; + } + + set_xstatebv(xsave_buffer, XFEATURE_MASK_XTILE); + set_tiledata(xsave_buffer + xsave_xtiledata_offset); + + printf("[RUN]\tCheck ARCH_GET_XSTATE/ARCH_SET_XSTATE.\n"); + + printf("\tLoad tile data without GET:\n"); + + if (!xrstor(xsave_buffer, -1, -1)) { + printf("[OK]\tBlocked.\n"); + } else { + nerrs++; + printf("[FAIL]\tSucceeded.\n"); + } + + printf("\tGET with invalid arg:\n"); + + rc = syscall(SYS_arch_prctl, ARCH_GET_XSTATE, -1); + if (rc == -EPERM) { + printf("[OK]\tEPERM was returned.\n"); + } else { + nerrs++; + printf("[FAIL]\tNo EPERM was returned.\n"); + } + + printf("\tGET with AMX state %d-times:\n", ARCH_PRCTL_REPEAT); + + for (i = 0; i < ARCH_PRCTL_REPEAT; i++) { + rc = syscall(SYS_arch_prctl, ARCH_GET_XSTATE, XFEATURE_MASK_XTILE); + if (rc != 0) + break; + + xfd_armed = !xrstor(xsave_buffer, -1, -1); + if (xfd_armed) + break; + } + + if (i == ARCH_PRCTL_REPEAT) { + printf("[OK]\tNo error and correctly disarmed XFD.\n"); + } else { + nerrs++; + i++; + if (rc) + printf("[FAIL]\t%d-th GET returned error (rc=%d).\n", i, rc); + else + printf("[FAIL]\t%d-th GET failed to disarm XFD.\n", i); + } + + printf("\tPUT with AMX state %d-times:\n", ARCH_PRCTL_REPEAT); + + for (i = 0; i < ARCH_PRCTL_REPEAT; i++) { + rc = syscall(SYS_arch_prctl, ARCH_PUT_XSTATE, XFEATURE_MASK_XTILE); + if (rc != 0) + break; + + xfd_armed = !xrstor(xsave_buffer, -1, -1); + if (xfd_armed) + break; + } + + if ((i == (ARCH_PRCTL_REPEAT - 1)) && xfd_armed) { + printf("[OK]\tNo error and re-armed XFD at the end.\n"); + } else { + nerrs++; + i++; + if (rc) + printf("[FAIL]\t%d-th PUT returned error (rc=%d).\n", i, rc); + else if (i == ARCH_PRCTL_REPEAT) + printf("[FAIL]\tthe final PUT failed to arm XFD.\n"); + else + printf("[FAIL]\t%d-th PUT disarm XFD.\n", i); + } + + _exit(0); +} + +/* Testing tile data inheritance */ + +static void test_fork(void) +{ + pid_t child, grandchild; + + child = fork(); + if (child < 0) { + err(1, "fork"); + } else if (child > 0) { + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + err(1, "fork test child"); + return; + } + + printf("[RUN]\tCheck tile data inheritance.\n\tBefore fork(), load tile data -- yes:\n"); + + set_xstatebv(xsave_buffer, XFEATURE_MASK_XTILE); + set_tiledata(xsave_buffer + xsave_xtiledata_offset); + memset(xsave_buffer + xsave_xtilecfg_offset, 1, xsave_xtilecfg_size); + syscall(SYS_arch_prctl, ARCH_GET_XSTATE, XFEATURE_MASK_XTILE); + xrstor(xsave_buffer, -1, -1); + + grandchild = fork(); + if (grandchild < 0) { + err(1, "fork"); + } else if (grandchild > 0) { + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + err(1, "fork test child"); + _exit(0); + } + + if (__xgetbv(1) & XFEATURE_MASK_XTILE) { + nerrs++; + printf("[FAIL]\tIn a child, AMX state is not initialized.\n"); + } else { + printf("[OK]\tIn a child, AMX state is initialized.\n"); + } + _exit(0); +} + +/* Context switching test */ + +#define ITERATIONS 10 +#define NUM_THREADS 5 + +struct futex_info { + int current; + int *futex; + int next; +}; + +static inline void command_wait(struct futex_info *info, int value) +{ + do { + sched_yield(); + } while (syscall(SYS_futex, info->futex, FUTEX_WAIT, value, 0, 0, 0)); +} + +static inline void command_wake(struct futex_info *info, int value) +{ + do { + *info->futex = value; + while (!syscall(SYS_futex, info->futex, FUTEX_WAKE, 1, 0, 0, 0)) + sched_yield(); + } while (0); +} + +static inline int get_iterative_value(int id) +{ + return ((id << 1) & ~0x1); +} + +static inline int get_endpoint_value(int id) +{ + return ((id << 1) | 0x1); +} + +static void *check_tiledata(void *info) +{ + struct futex_info *finfo = (struct futex_info *)info; + void *xsave, *tiledata; + int i; + + xsave = aligned_alloc(64, xsave_size); + if (!xsave) + err(1, "aligned_alloc()"); + + tiledata = malloc(xsave_xtiledata_size); + if (!tiledata) + err(1, "malloc()"); + + set_xstatebv(xsave, XFEATURE_MASK_XTILEDATA); + set_tiledata(xsave + xsave_xtiledata_offset); + syscall(SYS_arch_prctl, ARCH_GET_XSTATE, XFEATURE_MASK_XTILE); + xrstor(xsave, -1, -1); + memcpy(tiledata, xsave + xsave_xtiledata_offset, xsave_xtiledata_size); + + for (i = 0; i < ITERATIONS; i++) { + command_wait(finfo, get_iterative_value(finfo->current)); + + __xsave(xsave, XFEATURE_MASK_XTILEDATA, 0); + if (memcmp(tiledata, xsave + xsave_xtiledata_offset, xsave_xtiledata_size)) + errs++; + + set_tiledata(xsave + xsave_xtiledata_offset); + syscall(SYS_arch_prctl, ARCH_GET_XSTATE, XFEATURE_MASK_XTILE); + xrstor(xsave, -1, -1); + memcpy(tiledata, xsave + xsave_xtiledata_offset, xsave_xtiledata_size); + + command_wake(finfo, get_iterative_value(finfo->next)); + } + + command_wait(finfo, get_endpoint_value(finfo->current)); + + free(xsave); + free(tiledata); + return NULL; +} + +static int create_threads(int num, struct futex_info *finfo) +{ + const int shm_id = shmget(IPC_PRIVATE, sizeof(int), IPC_CREAT | 0666); + int *futex = shmat(shm_id, NULL, 0); + pthread_t thread; + int i; + + for (i = 0; i < num; i++) { + finfo[i].futex = futex; + finfo[i].current = i + 1; + finfo[i].next = (i + 2) % (num + 1); + + if (pthread_create(&thread, NULL, check_tiledata, &finfo[i])) + err(1, "pthread_create()"); + } + return 0; +} + +static void test_context_switch(void) +{ + struct futex_info *finfo; + cpu_set_t cpuset; + int i; + + printf("[RUN]\tCheck tile data context switches.\n"); + printf("\t# of context switches -- %u, # of threads -- %d:\n", + ITERATIONS * NUM_THREADS, NUM_THREADS); + + errs = 0; + + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) + err(1, "sched_setaffinity to CPU 0"); + + finfo = malloc(sizeof(*finfo) * NUM_THREADS); + if (!finfo) + err(1, "malloc()"); + + create_threads(NUM_THREADS, finfo); + + for (i = 0; i < ITERATIONS; i++) { + command_wake(finfo, get_iterative_value(1)); + command_wait(finfo, get_iterative_value(0)); + } + + for (i = 1; i <= NUM_THREADS; i++) + command_wake(finfo, get_endpoint_value(i)); + + if (errs) { + nerrs += errs; + printf("[FAIL]\tIncorrect cases were found -- (%d / %u).\n", + errs, ITERATIONS * NUM_THREADS); + free(finfo); + return; + } + + free(finfo); + printf("[OK]\tNo incorrect case was found.\n"); +} + +/* Ptrace test */ + +static bool set_tiledata_state; + +static int write_tiledata(pid_t child) +{ + struct iovec iov; + + iov.iov_base = xsave_buffer; + iov.iov_len = xsave_size; + + set_xstatebv(xsave_buffer, set_tiledata_state ? XFEATURE_MASK_XTILEDATA : 0); + set_tiledata(xsave_buffer + xsave_xtiledata_offset); + if (set_tiledata_state) + memcpy(tiledata, xsave_buffer + xsave_xtiledata_offset, xsave_xtiledata_size); + else + memset(tiledata, 0, xsave_xtiledata_size); + + if (ptrace(PTRACE_SETREGSET, child, (uint32_t)NT_X86_XSTATE, &iov)) + err(1, "PTRACE_SETREGSET"); + + if (ptrace(PTRACE_GETREGSET, child, (uint32_t)NT_X86_XSTATE, &iov)) + err(1, "PTRACE_GETREGSET"); + + return memcmp(tiledata, xsave_buffer + xsave_xtiledata_offset, xsave_xtiledata_size); +} + +static void test_tile_write(void) +{ + pid_t child; + int status; + + child = fork(); + if (child < 0) + err(1, "fork"); + + if (!child) { + printf("\tInject tile data -- %s:\n", + set_tiledata_state ? "yes" : "no"); + + if (ptrace(PTRACE_TRACEME, 0, NULL, NULL)) + err(1, "PTRACE_TRACEME"); + + raise(SIGTRAP); + _exit(0); + } + + do { + wait(&status); + } while (WSTOPSIG(status) != SIGTRAP); + + errs = write_tiledata(child); + if (errs) { + nerrs++; + printf("[FAIL]\tTile data was %swritten on ptracee.\n", + set_tiledata_state ? "not " : ""); + } else { + printf("[OK]\tTile data was %swritten on ptracee.\n", + set_tiledata_state ? "" : "not "); + } + + ptrace(PTRACE_DETACH, child, NULL, NULL); + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + err(1, "fork test child"); +} + +static void test_ptrace(void) +{ + printf("[RUN]\tCheck ptrace() to inject tile data.\n"); + + set_tiledata_state = true; + test_tile_write(); + + set_tiledata_state = false; + test_tile_write(); +} + +int main(void) +{ + /* Check hardware availability at first */ + + if (!check_xsave_capability()) { + if (xsave_disabled) + printf("XSAVE disabled.\n"); + else + printf("Tile data not available.\n"); + return 0; + } + + check_cpuid(); + + xsave_buffer = aligned_alloc(64, xsave_size); + if (!xsave_buffer) + err(1, "aligned_alloc()"); + + tiledata = malloc(xsave_xtiledata_size); + if (!tiledata) + err(1, "malloc()"); + + nerrs = 0; + + sethandler(SIGSEGV, handle_sigsegv, 0); + + test_arch_prctl(); + test_fork(); + test_context_switch(); + test_ptrace(); + + clearhandler(SIGSEGV); + + free(xsave_buffer); + free(tiledata); + return nerrs ? 1 : 0; +} -- 2.17.1

4 years, 1 month

1
0
0 0

[PATCH v7 0/7] Fork brute force attack mitigation

by John Wood

Attacks against vulnerable userspace applications with the purpose to break ASLR or bypass canaries traditionally use some level of brute force with the help of the fork system call. This is possible since when creating a new process using fork its memory contents are the same as those of the parent process (the process that called the fork system call). So, the attacker can test the memory infinite times to find the correct memory values or the correct memory addresses without worrying about crashing the application. Based on the above scenario it would be nice to have this detected and mitigated, and this is the goal of this patch serie. Specifically the following attacks are expected to be detected: 1.- Launching (fork()/exec()) a setuid/setgid process repeatedly until a desirable memory layout is got (e.g. Stack Clash). 2.- Connecting to an exec()ing network daemon (e.g. xinetd) repeatedly until a desirable memory layout is got (e.g. what CTFs do for simple network service). 3.- Launching processes without exec() (e.g. Android Zygote) and exposing state to attack a sibling. 4.- Connecting to a fork()ing network daemon (e.g. apache) repeatedly until the previously shared memory layout of all the other children is exposed (e.g. kind of related to HeartBleed). In each case, a privilege boundary has been crossed: Case 1: setuid/setgid process Case 2: network to local Case 3: privilege changes Case 4: network to local So, what will really be detected are fork/exec brute force attacks that cross any of the commented bounds. The implementation details and comparison against other existing implementations can be found in the "Documentation" patch. It is important to mention that this version has changed the method used to track the information related to the application crashes. Prior this version, a pointer per process (in the task_struct structure) held a reference to the shared statistical data. Or in other words, these stats were shared by all the fork hierarchy processes. But this has an important drawback: a brute force attack that happens through the execve system call losts the faults info since these statistics are freed when the fork hierarchy disappears. So, the solution adopted in the v6 version was to use an upper fork hierarchy to track the info for this attack type. But, as Valdis Kletnieks pointed out during this discussion [1], this method can be easily bypassed using a double exec (well, this was the method used in the kselftest to avoid the detection ;) ). So, in this version, to track all the statistical data (info related with application crashes), the extended attributes feature for the executable files are used. The xattr is also used to mark the executables as "not allowed" when an attack is detected. Then, the execve system call rely on this flag to avoid following executions of this file. [1] https://lore.kernel.org/kernelnewbies/20210330173459.GA3163@ubuntu/ Moreover, I think this solves another problem pointed out by Andi Kleen during the v5 review [2] related to the possibility that a supervisor respawns processes killed by the Brute LSM. He suggested adding some way so a supervisor can know that a process has been killed by Brute and then decide to respawn or not. So, now, the supervisor can read the brute xattr of one executable and know if it is blocked by Brute and why (using the statistical data). [2] https://lore.kernel.org/kernel-hardening/878s78dnrm.fsf@linux.intel.com/ Knowing all this information I will explain now the different patches: The 1/7 patch defines a new LSM hook to get the fatal signal of a task. This will be useful during the attack detection phase. The 2/7 patch defines a new LSM and the necessary sysctl attributes to fine tuning the attack detection. The 3/7 patch detects a fork/exec brute force attack and narrows the possible cases taken into account the privilege boundary crossing. The 4/7 patch mitigates a brute force attack. The 5/7 patch adds self-tests to validate the Brute LSM expectations. The 6/7 patch adds the documentation to explain this implementation. The 7/7 patch updates the maintainers file. This patch serie is a task of the KSPP [3] and can also be accessed from my github tree [4] in the "brute_v7" branch. [3] https://github.com/KSPP/linux/issues/39 [4] https://github.com/johwood/linux/ When I ran the "checkpatch" script I got the following errors, but I think they are false positives as I follow the same coding style for the others extended attributes suffixes. ---------------------------------------------------------------------------- ../patches/brute_v7/v7-0003-security-brute-Detect-a-brute-force-attack.patch ---------------------------------------------------------------------------- ERROR: Macros with complex values should be enclosed in parentheses 89: FILE: include/uapi/linux/xattr.h:80: +#define XATTR_NAME_BRUTE XATTR_SECURITY_PREFIX XATTR_BRUTE_SUFFIX ----------------------------------------------------------------------------- ../patches/brute_v7/v7-0005-selftests-brute-Add-tests-for-the-Brute-LSM.patch ----------------------------------------------------------------------------- ERROR: Macros with complex values should be enclosed in parentheses 100: FILE: tools/testing/selftests/brute/rmxattr.c:18: +#define XATTR_NAME_BRUTE XATTR_SECURITY_PREFIX XATTR_BRUTE_SUFFIX When I ran the "kernel-doc" script with the following parameters: ./scripts/kernel-doc --none -v security/brute/brute.c I got the following warning: security/brute/brute.c:65: warning: contents before sections But I don't understand why it is complaining. Could it be a false positive? The previous versions can be found in: RFC https://lore.kernel.org/kernel-hardening/20200910202107.3799376-1-keescook@… Version 2 https://lore.kernel.org/kernel-hardening/20201025134540.3770-1-john.wood@gm… Version 3 https://lore.kernel.org/lkml/20210221154919.68050-1-john.wood@gmx.com/ Version 4 https://lore.kernel.org/lkml/20210227150956.6022-1-john.wood@gmx.com/ Version 5 https://lore.kernel.org/kernel-hardening/20210227153013.6747-1-john.wood@gm… Version 6 https://lore.kernel.org/kernel-hardening/20210307113031.11671-1-john.wood@g… Changelog RFC -> v2 ------------------- - Rename this feature with a more suitable name (Jann Horn, Kees Cook). - Convert the code to an LSM (Kees Cook). - Add locking to avoid data races (Jann Horn). - Add a new LSM hook to get the fatal signal of a task (Jann Horn, Kees Cook). - Add the last crashes timestamps list to avoid false positives in the attack detection (Jann Horn). - Use "period" instead of "rate" (Jann Horn). - Other minor changes suggested (Jann Horn, Kees Cook). Changelog v2 -> v3 ------------------ - Compute the application crash period on an on-going basis (Kees Cook). - Detect a brute force attack through the execve system call (Kees Cook). - Detect an slow brute force attack (Randy Dunlap). - Fine tuning the detection taken into account privilege boundary crossing (Kees Cook). - Taken into account only fatal signals delivered by the kernel (Kees Cook). - Remove the sysctl attributes to fine tuning the detection (Kees Cook). - Remove the prctls to allow per process enabling/disabling (Kees Cook). - Improve the documentation (Kees Cook). - Fix some typos in the documentation (Randy Dunlap). - Add self-test to validate the expectations (Kees Cook). Changelog v3 -> v4 ------------------ - Fix all the warnings shown by the tool "scripts/kernel-doc" (Randy Dunlap). Changelog v4 -> v5 ------------------ - Fix some typos (Randy Dunlap). Changelog v5 -> v6 ------------------ - Fix a reported deadlock (kernel test robot). - Add high level details to the documentation (Andi Kleen). Changelog v6 -> v7 ------------------ - Add the "Reviewed-by:" tag to the first patch. - Rearrange the brute LSM between lockdown and yama (Kees Cook). - Split subdir and obj in security/Makefile (Kees Cook). - Reduce the number of header files included (Kees Cook). - Print the pid when an attack is detected (Kees Cook). - Use the socket_accept LSM hook instead of socket_sock_rcv_skb hook to avoid running a hook on every incoming network packet (Kees Cook). - Update the documentation and fix it to render it properly (Jonathan Corbet). - Manage correctly an exec brute force attack avoiding the bypass (Valdis Kletnieks). - Other minor changes and cleanups. Any constructive comments are welcome. Thanks in advance. John Wood (7): security: Add LSM hook at the point where a task gets a fatal signal security/brute: Define a LSM and add sysctl attributes security/brute: Detect a brute force attack security/brute: Mitigate a brute force attack selftests/brute: Add tests for the Brute LSM Documentation: Add documentation for the Brute LSM MAINTAINERS: Add a new entry for the Brute LSM Documentation/admin-guide/LSM/Brute.rst | 334 +++++++++++ Documentation/admin-guide/LSM/index.rst | 1 + MAINTAINERS | 7 + include/linux/lsm_hook_defs.h | 1 + include/linux/lsm_hooks.h | 4 + include/linux/security.h | 4 + include/uapi/linux/xattr.h | 3 + kernel/signal.c | 1 + security/Kconfig | 11 +- security/Makefile | 2 + security/brute/Kconfig | 15 + security/brute/Makefile | 2 + security/brute/brute.c | 716 +++++++++++++++++++++++ security/security.c | 5 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/brute/.gitignore | 2 + tools/testing/selftests/brute/Makefile | 5 + tools/testing/selftests/brute/config | 1 + tools/testing/selftests/brute/rmxattr.c | 34 ++ tools/testing/selftests/brute/test.c | 507 ++++++++++++++++ tools/testing/selftests/brute/test.sh | 256 ++++++++ 21 files changed, 1907 insertions(+), 5 deletions(-) create mode 100644 Documentation/admin-guide/LSM/Brute.rst create mode 100644 security/brute/Kconfig create mode 100644 security/brute/Makefile create mode 100644 security/brute/brute.c create mode 100644 tools/testing/selftests/brute/.gitignore create mode 100644 tools/testing/selftests/brute/Makefile create mode 100644 tools/testing/selftests/brute/config create mode 100644 tools/testing/selftests/brute/rmxattr.c create mode 100644 tools/testing/selftests/brute/test.c create mode 100755 tools/testing/selftests/brute/test.sh -- 2.25.1

4 years, 1 month

2
11
0 0

[PATCH v1 0/4] kunit: tool: add support for QEMU

by Brendan Higgins

TL;DR: Add support to kunit_tool to dispatch tests via QEMU. Also add support to immediately shutdown a kernel after running KUnit tests. Background ---------- KUnit has supported running on all architectures for quite some time; however, kunit_tool - the script commonly used to invoke KUnit tests - has only fully supported KUnit run on UML. Its functionality has been broken up for some time to separate the configure, build, run, and parse phases making it possible to be used in part on other architectures to a small extent. Nevertheless, kunit_tool has not supported running tests on other architectures. What this patchset does ----------------------- This patchset introduces first class support to kunit_tool for KUnit to be run on many popular architectures via QEMU. It does this by adding two new flags: `--arch` and `--cross_compile`. `--arch` allows an architecture to be specified by the name the architecture is given in `arch/`. It uses the specified architecture to select a minimal amount of Kconfigs and QEMU configs needed for the architecture to run in QEMU and provide a console from which KTAP results can be scraped. `--cross_compile` allows a toolchain prefix to be specified to make similar to how `CROSS_COMPILE` is used. Additionally, this patchset revives the previously considered "kunit: tool: add support for QEMU"[1] patchs. The motivation for this new kernel command line flags, `kunit_shutdown`, is to better support running KUnit tests inside of QEMU. For most popular architectures, QEMU can be made to terminate when the Linux kernel that is being run is reboted, halted, or powered off. As Kees pointed out in a previous discussion[2], it is possible to make a kernel initrd that can reboot the kernel immediately, doing this for every architecture would likely be infeasible. Instead, just having an option for the kernel to shutdown when it is done with testing seems a lot simpler, especially since it is an option which would only available in testing configurations of the kernel anyway. Changes since last revision --------------------------- Mostly fixed lots of minor issues suggested/poited out by David and Daniel. Also reworked how qemu_configs are loaded: Now each config is in its own Python file and is loaded dynamically. Given the number of improvements that address the biggest concerns I had in the last RFC, I decided to promote this to a normal patch set. What discussion remains for this patchset? ------------------------------------------ I am still hoping to see some discussion regarding the kunit_shutdown patch: I want to make sure with the added context of QEMU running under kunit_tool that this is now a reasonable approach. Nevertheless, I am pretty happy with this patchset as is, and I did not get any negative feedback on the previous revision, so I think we can probably just move forward as is. Brendan Higgins (3): Documentation: Add kunit_shutdown to kernel-parameters.txt kunit: tool: add support for QEMU Documentation: kunit: document support for QEMU in kunit_tool David Gow (1): kunit: Add 'kunit_shutdown' option .../admin-guide/kernel-parameters.txt | 8 + Documentation/dev-tools/kunit/usage.rst | 37 +++- lib/kunit/executor.c | 20 ++ tools/testing/kunit/kunit.py | 57 +++++- tools/testing/kunit/kunit_config.py | 7 +- tools/testing/kunit/kunit_kernel.py | 172 +++++++++++++++--- tools/testing/kunit/kunit_parser.py | 2 +- tools/testing/kunit/kunit_tool_test.py | 18 +- tools/testing/kunit/qemu_config.py | 17 ++ tools/testing/kunit/qemu_configs/alpha.py | 10 + tools/testing/kunit/qemu_configs/arm.py | 13 ++ tools/testing/kunit/qemu_configs/arm64.py | 12 ++ tools/testing/kunit/qemu_configs/i386.py | 10 + tools/testing/kunit/qemu_configs/powerpc.py | 12 ++ tools/testing/kunit/qemu_configs/riscv.py | 31 ++++ tools/testing/kunit/qemu_configs/s390.py | 14 ++ tools/testing/kunit/qemu_configs/sparc.py | 10 + tools/testing/kunit/qemu_configs/x86_64.py | 10 + 18 files changed, 411 insertions(+), 49 deletions(-) create mode 100644 tools/testing/kunit/qemu_config.py create mode 100644 tools/testing/kunit/qemu_configs/alpha.py create mode 100644 tools/testing/kunit/qemu_configs/arm.py create mode 100644 tools/testing/kunit/qemu_configs/arm64.py create mode 100644 tools/testing/kunit/qemu_configs/i386.py create mode 100644 tools/testing/kunit/qemu_configs/powerpc.py create mode 100644 tools/testing/kunit/qemu_configs/riscv.py create mode 100644 tools/testing/kunit/qemu_configs/s390.py create mode 100644 tools/testing/kunit/qemu_configs/sparc.py create mode 100644 tools/testing/kunit/qemu_configs/x86_64.py base-commit: 38182162b50aa4e970e5997df0a0c4288147a153 -- 2.31.1.607.g51e8a6a459-goog

4 years, 1 month

2
15
0 0

[PATCH v5 0/4] KVM statistics data fd-based binary interface

by Jing Zhang

This patchset provides a file descriptor for every VM and VCPU to read KVM statistics data in binary format. It is meant to provide a lightweight, flexible, scalable and efficient lock-free solution for user space telemetry applications to pull the statistics data periodically for large scale systems. The pulling frequency could be as high as a few times per second. In this patchset, every statistics data are treated to have some attributes as below: * architecture dependent or common * VM statistics data or VCPU statistics data * type: cumulative, instantaneous, * unit: none for simple counter, nanosecond, microsecond, millisecond, second, Byte, KiByte, MiByte, GiByte. Clock Cycles Since no lock/synchronization is used, the consistency between all the statistics data is not guaranteed. That means not all statistics data are read out at the exact same time, since the statistics date are still being updated by KVM subsystems while they are read out. --- * v4 -> v5 - Rebase to kvm/queue, commit a4345a7cecfb ("Merge tag 'kvmarm-fixes-5.13-1'") - Change maximum stats name length to 48 - Replace VM_STATS_COMMON/VCPU_STATS_COMMON macros with stats descriptor definition macros. - Fixed some errors/warnings reported by checkpatch.pl * v3 -> v4 - Rebase to kvm/queue, commit 9f242010c3b4 ("KVM: avoid "deadlock" between install_new_memslots and MMU notifier") - Use C-stype comments in the whole patch - Fix wrong count for x86 VCPU stats descriptors - Fix KVM stats data size counting and validity check in selftest * v2 -> v3 - Rebase to kvm/queue, commit edf408f5257b ("KVM: avoid "deadlock" between install_new_memslots and MMU notifier") - Resolve some nitpicks about format * v1 -> v2 - Use ARRAY_SIZE to count the number of stats descriptors - Fix missing `size` field initialization in macro STATS_DESC [1] https://lore.kernel.org/kvm/20210402224359.2297157-1-jingzhangos@google.com [2] https://lore.kernel.org/kvm/20210415151741.1607806-1-jingzhangos@google.com [3] https://lore.kernel.org/kvm/20210423181727.596466-1-jingzhangos@google.com [4] https://lore.kernel.org/kvm/20210429203740.1935629-1-jingzhangos@google.com --- Jing Zhang (4): KVM: stats: Separate common stats from architecture specific ones KVM: stats: Add fd-based API to read binary stats data KVM: stats: Add documentation for statistics data binary interface KVM: selftests: Add selftest for KVM statistics data binary interface Documentation/virt/kvm/api.rst | 171 ++++++++ arch/arm64/include/asm/kvm_host.h | 9 +- arch/arm64/kvm/guest.c | 38 +- arch/mips/include/asm/kvm_host.h | 9 +- arch/mips/kvm/mips.c | 64 ++- arch/powerpc/include/asm/kvm_host.h | 9 +- arch/powerpc/kvm/book3s.c | 64 ++- arch/powerpc/kvm/book3s_hv.c | 12 +- arch/powerpc/kvm/book3s_pr.c | 2 +- arch/powerpc/kvm/book3s_pr_papr.c | 2 +- arch/powerpc/kvm/booke.c | 59 ++- arch/s390/include/asm/kvm_host.h | 9 +- arch/s390/kvm/kvm-s390.c | 129 +++++- arch/x86/include/asm/kvm_host.h | 9 +- arch/x86/kvm/x86.c | 67 +++- include/linux/kvm_host.h | 136 ++++++- include/linux/kvm_types.h | 12 + include/uapi/linux/kvm.h | 50 +++ tools/testing/selftests/kvm/.gitignore | 1 + tools/testing/selftests/kvm/Makefile | 3 + .../testing/selftests/kvm/include/kvm_util.h | 3 + .../selftests/kvm/kvm_bin_form_stats.c | 379 ++++++++++++++++++ tools/testing/selftests/kvm/lib/kvm_util.c | 12 + virt/kvm/kvm_main.c | 237 ++++++++++- 24 files changed, 1396 insertions(+), 90 deletions(-) create mode 100644 tools/testing/selftests/kvm/kvm_bin_form_stats.c base-commit: a4345a7cecfb91ae78cd43d26b0c6a956420761a -- 2.31.1.751.gd2f1c929bd-goog

4 years, 1 month

4
29
0 0

[PATCH] selftests: net: devlink_port_split.py: skip the test if no devlink device

by Po-Hsu Lin

When there is no devlink device, the following command will return: $ devlink -j dev show {dev:{}} This will cause IndexError when trying to access the first element in dev of this json dataset. Use the kselftest framework skip code to skip this test in this case. Example output with this change: # selftests: net: devlink_port_split.py # no devlink device was found, test skipped ok 7 selftests: net: devlink_port_split.py # SKIP Link: https://bugs.launchpad.net/bugs/1928889 Signed-off-by: Po-Hsu Lin <po-hsu.lin(a)canonical.com> --- tools/testing/selftests/net/devlink_port_split.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py index 834066d..2b5d6ff 100755 --- a/tools/testing/selftests/net/devlink_port_split.py +++ b/tools/testing/selftests/net/devlink_port_split.py @@ -18,6 +18,8 @@ import sys # +# Kselftest framework requirement - SKIP code is 4 +KSFT_SKIP=4 Port = collections.namedtuple('Port', 'bus_info name') @@ -239,7 +241,11 @@ def main(cmdline=None): assert stderr == "" devs = json.loads(stdout)['dev'] - dev = list(devs.keys())[0] + if devs: + dev = list(devs.keys())[0] + else: + print("no devlink device was found, test skipped") + sys.exit(KSFT_SKIP) cmd = "devlink dev show %s" % dev stdout, stderr = run_command(cmd) -- 2.7.4

4 years, 1 month

2
1
0 0

[PATCH] selftests: Add .gitignore for nci test suite

by David Matlack

Building the nci test suite produces a binary, nci_dev, that git then tries to track. Add a .gitignore file to tell git to ignore this binary. Signed-off-by: David Matlack <dmatlack(a)google.com> --- tools/testing/selftests/nci/.gitignore | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/testing/selftests/nci/.gitignore diff --git a/tools/testing/selftests/nci/.gitignore b/tools/testing/selftests/nci/.gitignore new file mode 100644 index 000000000000..448eeb4590fc --- /dev/null +++ b/tools/testing/selftests/nci/.gitignore @@ -0,0 +1 @@ +/nci_dev -- 2.31.1.751.gd2f1c929bd-goog

4 years, 1 month

2
1
0 0

[PATCH v5 1/2] selftests/sgx: Rename 'eenter' and 'sgx_call_vdso'

by Jarkko Sakkinen

Rename symbols for better clarity: * 'eenter' might be confused for directly calling ENCLU[EENTER]. It does not. It calls into the VDSO, which actually has the EENTER instruction. * 'sgx_call_vdso' is *only* used for entering the enclave. It's not some generic SGX call into the VDSO. Signed-off-by: Jarkko Sakkinen <jarkko(a)kernel.org> --- v3: Refine the commit message according to Dave's suggestions. v2: Refined the renames just a bit. tools/testing/selftests/sgx/call.S | 6 +++--- tools/testing/selftests/sgx/main.c | 25 +++++++++++++------------ tools/testing/selftests/sgx/main.h | 4 ++-- 3 files changed, 18 insertions(+), 17 deletions(-) diff --git a/tools/testing/selftests/sgx/call.S b/tools/testing/selftests/sgx/call.S index 4ecadc7490f4..b09a25890f3b 100644 --- a/tools/testing/selftests/sgx/call.S +++ b/tools/testing/selftests/sgx/call.S @@ -5,8 +5,8 @@ .text - .global sgx_call_vdso -sgx_call_vdso: + .global sgx_enter_enclave +sgx_enter_enclave: .cfi_startproc push %r15 .cfi_adjust_cfa_offset 8 @@ -27,7 +27,7 @@ sgx_call_vdso: .cfi_adjust_cfa_offset 8 push 0x38(%rsp) .cfi_adjust_cfa_offset 8 - call *eenter(%rip) + call *vdso_sgx_enter_enclave(%rip) add $0x10, %rsp .cfi_adjust_cfa_offset -0x10 pop %rbx diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c index d304a4044eb9..43da68388e25 100644 --- a/tools/testing/selftests/sgx/main.c +++ b/tools/testing/selftests/sgx/main.c @@ -21,7 +21,7 @@ #include "../kselftest.h" static const uint64_t MAGIC = 0x1122334455667788ULL; -vdso_sgx_enter_enclave_t eenter; +vdso_sgx_enter_enclave_t vdso_sgx_enter_enclave; struct vdso_symtab { Elf64_Sym *elf_symtab; @@ -149,7 +149,7 @@ int main(int argc, char *argv[]) { struct sgx_enclave_run run; struct vdso_symtab symtab; - Elf64_Sym *eenter_sym; + Elf64_Sym *sgx_enter_enclave_sym; uint64_t result = 0; struct encl encl; unsigned int i; @@ -194,29 +194,30 @@ int main(int argc, char *argv[]) if (!vdso_get_symtab(addr, &symtab)) goto err; - eenter_sym = vdso_symtab_get(&symtab, "__vdso_sgx_enter_enclave"); - if (!eenter_sym) + sgx_enter_enclave_sym = vdso_symtab_get(&symtab, "__vdso_sgx_enter_enclave"); + if (!sgx_enter_enclave_sym) goto err; - eenter = addr + eenter_sym->st_value; + vdso_sgx_enter_enclave = addr + sgx_enter_enclave_sym->st_value; - ret = sgx_call_vdso((void *)&MAGIC, &result, 0, EENTER, NULL, NULL, &run); - if (!report_results(&run, ret, result, "sgx_call_vdso")) + ret = sgx_enter_enclave((void *)&MAGIC, &result, 0, EENTER, + NULL, NULL, &run); + if (!report_results(&run, ret, result, "sgx_enter_enclave_unclobbered")) goto err; /* Invoke the vDSO directly. */ result = 0; - ret = eenter((unsigned long)&MAGIC, (unsigned long)&result, 0, EENTER, - 0, 0, &run); - if (!report_results(&run, ret, result, "eenter")) + ret = vdso_sgx_enter_enclave((unsigned long)&MAGIC, (unsigned long)&result, + 0, EENTER, 0, 0, &run); + if (!report_results(&run, ret, result, "sgx_enter_enclave")) goto err; /* And with an exit handler. */ run.user_handler = (__u64)user_handler; run.user_data = 0xdeadbeef; - ret = eenter((unsigned long)&MAGIC, (unsigned long)&result, 0, EENTER, - 0, 0, &run); + ret = vdso_sgx_enter_enclave((unsigned long)&MAGIC, (unsigned long)&result, + 0, EENTER, 0, 0, &run); if (!report_results(&run, ret, result, "user_handler")) goto err; diff --git a/tools/testing/selftests/sgx/main.h b/tools/testing/selftests/sgx/main.h index 67211a708f04..68672fd86cf9 100644 --- a/tools/testing/selftests/sgx/main.h +++ b/tools/testing/selftests/sgx/main.h @@ -35,7 +35,7 @@ bool encl_load(const char *path, struct encl *encl); bool encl_measure(struct encl *encl); bool encl_build(struct encl *encl); -int sgx_call_vdso(void *rdi, void *rsi, long rdx, u32 function, void *r8, void *r9, - struct sgx_enclave_run *run); +int sgx_enter_enclave(void *rdi, void *rsi, long rdx, u32 function, void *r8, void *r9, + struct sgx_enclave_run *run); #endif /* MAIN_H */ -- 2.31.1

4 years, 1 month

2
6
0 0

RE: [PATCH] selftests: net: devlink_port_split.py: skip the test if no devlink device

by Danielle Ratson

> -----Original Message----- > From: Po-Hsu Lin <po-hsu.lin(a)canonical.com> > Sent: Thursday, May 20, 2021 1:50 PM > To: linux-kernel(a)vger.kernel.org; linux-kselftest(a)vger.kernel.org; netdev(a)vger.kernel.org > Cc: po-hsu.lin(a)canonical.com; shuah(a)kernel.org; kuba(a)kernel.org; davem(a)davemloft.net; skhan(a)linuxfoundation.org > Subject: [PATCH] selftests: net: devlink_port_split.py: skip the test if no devlink device > > When there is no devlink device, the following command will return: > $ devlink -j dev show > {dev:{}} > > This will cause IndexError when trying to access the first element in dev of this json dataset. Use the kselftest framework skip code to > skip this test in this case. > > Example output with this change: > # selftests: net: devlink_port_split.py > # no devlink device was found, test skipped > ok 7 selftests: net: devlink_port_split.py # SKIP > > Link: https://bugs.launchpad.net/bugs/1928889 > Signed-off-by: Po-Hsu Lin <po-hsu.lin(a)canonical.com> Reviewed-by: Danielle Ratson <danieller(a)nvidia.com>

4 years, 1 month

1
0
0 0

[PATCH v8 RESEND 1/4] lib: vsprintf: scanf: Negative number must have field width > 1

by Richard Fitzgerald

If a signed number field starts with a '-' the field width must be > 1, or unlimited, to allow at least one digit after the '-'. This patch adds a check for this. If a signed field starts with '-' and field_width == 1 the scanf will quit. It is ok for a signed number field to have a field width of 1 if it starts with a digit. In that case the single digit can be converted. Signed-off-by: Richard Fitzgerald <rf(a)opensource.cirrus.com> Reviewed-by: Petr Mladek <pmladek(a)suse.com> Acked-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com> --- lib/vsprintf.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 41ddc353ebb8..f78651e9b030 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -3466,8 +3466,12 @@ int vsscanf(const char *buf, const char *fmt, va_list args) str = skip_spaces(str); digit = *str; - if (is_sign && digit == '-') + if (is_sign && digit == '-') { + if (field_width == 1) + break; + digit = *(str + 1); + } if (!digit || (base == 16 && !isxdigit(digit)) -- 2.20.1

4 years, 1 month

2
4
0 0

[PATCH v19 0/8] mm: introduce memfd_secret system call to create "secret" memory areas

by Mike Rapoport

From: Mike Rapoport <rppt(a)linux.ibm.com> Hi, @Andrew, this is based on v5.13-rc1, I can rebase whatever way you prefer. This is an implementation of "secret" mappings backed by a file descriptor. The file descriptor backing secret memory mappings is created using a dedicated memfd_secret system call The desired protection mode for the memory is configured using flags parameter of the system call. The mmap() of the file descriptor created with memfd_secret() will create a "secret" memory mapping. The pages in that mapping will be marked as not present in the direct map and will be present only in the page table of the owning mm. Although normally Linux userspace mappings are protected from other users, such secret mappings are useful for environments where a hostile tenant is trying to trick the kernel into giving them access to other tenants mappings. It's designed to provide the following protections: * Enhanced protection (in conjunction with all the other in-kernel attack prevention systems) against ROP attacks. Seceretmem makes "simple" ROP insufficient to perform exfiltration, which increases the required complexity of the attack. Along with other protections like the kernel stack size limit and address space layout randomization which make finding gadgets is really hard, absence of any in-kernel primitive for accessing secret memory means the one gadget ROP attack can't work. Since the only way to access secret memory is to reconstruct the missing mapping entry, the attacker has to recover the physical page and insert a PTE pointing to it in the kernel and then retrieve the contents. That takes at least three gadgets which is a level of difficulty beyond most standard attacks. * Prevent cross-process secret userspace memory exposures. Once the secret memory is allocated, the user can't accidentally pass it into the kernel to be transmitted somewhere. The secreremem pages cannot be accessed via the direct map and they are disallowed in GUP. * Harden against exploited kernel flaws. In order to access secretmem, a kernel-side attack would need to either walk the page tables and create new ones, or spawn a new privileged uiserspace process to perform secrets exfiltration using ptrace. In the future the secret mappings may be used as a mean to protect guest memory in a virtual machine host. For demonstration of secret memory usage we've created a userspace library https://git.kernel.org/pub/scm/linux/kernel/git/jejb/secret-memory-preloade… that does two things: the first is act as a preloader for openssl to redirect all the OPENSSL_malloc calls to secret memory meaning any secret keys get automatically protected this way and the other thing it does is expose the API to the user who needs it. We anticipate that a lot of the use cases would be like the openssl one: many toolkits that deal with secret keys already have special handling for the memory to try to give them greater protection, so this would simply be pluggable into the toolkits without any need for user application modification. Hiding secret memory mappings behind an anonymous file allows usage of the page cache for tracking pages allocated for the "secret" mappings as well as using address_space_operations for e.g. page migration callbacks. The anonymous file may be also used implicitly, like hugetlb files, to implement mmap(MAP_SECRET) and use the secret memory areas with "native" mm ABIs in the future. Removing of the pages from the direct map may cause its fragmentation on architectures that use large pages to map the physical memory which affects the system performance. However, the original Kconfig text for CONFIG_DIRECT_GBPAGES said that gigabyte pages in the direct map "... can improve the kernel's performance a tiny bit ..." (commit 00d1c5e05736 ("x86: add gbpages switches")) and the recent report [1] showed that "... although 1G mappings are a good default choice, there is no compelling evidence that it must be the only choice". Hence, it is sufficient to have secretmem disabled by default with the ability of a system administrator to enable it at boot time. In addition, there is also a long term goal to improve management of the direct map. [1] https://lore.kernel.org/linux-mm/213b4567-46ce-f116-9cdf-bbd0c884eb3c@linux… v19: * block /dev/mem mmap access, per David * disallow mmap/mprotect with PROT_EXEC, per Kees * simplify return in page_is_secretmem(), per Matthew * use unsigned int for syscall falgs, per Yury v18: https://lore.kernel.org/lkml/20210303162209.8609-1-rppt@kernel.org * rebase on v5.12-rc1 * merge kfence fix into the original patch * massage commit message of the patch introducing the memfd_secret syscall v17: https://lore.kernel.org/lkml/20210208084920.2884-1-rppt@kernel.org * Remove pool of large pages backing secretmem allocations, per Michal Hocko * Add secretmem pages to unevictable LRU, per Michal Hocko * Use GFP_HIGHUSER as secretmem mapping mask, per Michal Hocko * Make secretmem an opt-in feature that is disabled by default v16: https://lore.kernel.org/lkml/20210121122723.3446-1-rppt@kernel.org * Fix memory leak intorduced in v15 * Clean the data left from previous page user before handing the page to the userspace v15: https://lore.kernel.org/lkml/20210120180612.1058-1-rppt@kernel.org * Add riscv/Kconfig update to disable set_memory operations for nommu builds (patch 3) * Update the code around add_to_page_cache() per Matthew's comments (patches 6,7) * Add fixups for build/checkpatch errors discovered by CI systems Older history: v14: https://lore.kernel.org/lkml/20201203062949.5484-1-rppt@kernel.org v13: https://lore.kernel.org/lkml/20201201074559.27742-1-rppt@kernel.org v12: https://lore.kernel.org/lkml/20201125092208.12544-1-rppt@kernel.org v11: https://lore.kernel.org/lkml/20201124092556.12009-1-rppt@kernel.org v10: https://lore.kernel.org/lkml/20201123095432.5860-1-rppt@kernel.org v9: https://lore.kernel.org/lkml/20201117162932.13649-1-rppt@kernel.org v8: https://lore.kernel.org/lkml/20201110151444.20662-1-rppt@kernel.org v7: https://lore.kernel.org/lkml/20201026083752.13267-1-rppt@kernel.org v6: https://lore.kernel.org/lkml/20200924132904.1391-1-rppt@kernel.org v5: https://lore.kernel.org/lkml/20200916073539.3552-1-rppt@kernel.org v4: https://lore.kernel.org/lkml/20200818141554.13945-1-rppt@kernel.org v3: https://lore.kernel.org/lkml/20200804095035.18778-1-rppt@kernel.org v2: https://lore.kernel.org/lkml/20200727162935.31714-1-rppt@kernel.org v1: https://lore.kernel.org/lkml/20200720092435.17469-1-rppt@kernel.org rfc-v2: https://lore.kernel.org/lkml/20200706172051.19465-1-rppt@kernel.org/ rfc-v1: https://lore.kernel.org/lkml/20200130162340.GA14232@rapoport-lnx/ rfc-v0: https://lore.kernel.org/lkml/1572171452-7958-1-git-send-email-rppt@kernel.o… Mike Rapoport (8): mmap: make mlock_future_check() global riscv/Kconfig: make direct map manipulation options depend on MMU set_memory: allow set_direct_map_*_noflush() for multiple pages set_memory: allow querying whether set_direct_map_*() is actually enabled mm: introduce memfd_secret system call to create "secret" memory areas PM: hibernate: disable when there are active secretmem users arch, mm: wire up memfd_secret system call where relevant secretmem: test: add basic selftest for memfd_secret(2) arch/arm64/include/asm/Kbuild | 1 - arch/arm64/include/asm/cacheflush.h | 6 - arch/arm64/include/asm/kfence.h | 2 +- arch/arm64/include/asm/set_memory.h | 17 ++ arch/arm64/include/uapi/asm/unistd.h | 1 + arch/arm64/kernel/machine_kexec.c | 1 + arch/arm64/mm/mmu.c | 6 +- arch/arm64/mm/pageattr.c | 23 +- arch/riscv/Kconfig | 4 +- arch/riscv/include/asm/set_memory.h | 4 +- arch/riscv/include/asm/unistd.h | 1 + arch/riscv/mm/pageattr.c | 8 +- arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/x86/include/asm/set_memory.h | 4 +- arch/x86/mm/pat/set_memory.c | 8 +- drivers/char/mem.c | 4 + include/linux/secretmem.h | 54 ++++ include/linux/set_memory.h | 16 +- include/linux/syscalls.h | 1 + include/uapi/asm-generic/unistd.h | 7 +- include/uapi/linux/magic.h | 1 + kernel/power/hibernate.c | 5 +- kernel/power/snapshot.c | 4 +- kernel/sys_ni.c | 2 + mm/Kconfig | 4 + mm/Makefile | 1 + mm/gup.c | 12 + mm/internal.h | 3 + mm/mlock.c | 3 +- mm/mmap.c | 5 +- mm/secretmem.c | 254 +++++++++++++++++++ mm/vmalloc.c | 5 +- scripts/checksyscalls.sh | 4 + tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 3 +- tools/testing/selftests/vm/memfd_secret.c | 296 ++++++++++++++++++++++ tools/testing/selftests/vm/run_vmtests.sh | 17 ++ 38 files changed, 744 insertions(+), 46 deletions(-) create mode 100644 arch/arm64/include/asm/set_memory.h create mode 100644 include/linux/secretmem.h create mode 100644 mm/secretmem.c create mode 100644 tools/testing/selftests/vm/memfd_secret.c base-commit: 6efb943b8616ec53a5e444193dccf1af9ad627b5 -- 2.28.0

4 years, 1 month

6
31
0 0

[PATCH v20 0/7] mm: introduce memfd_secret system call to create "secret" memory areas

by Mike Rapoport

From: Mike Rapoport <rppt(a)linux.ibm.com> Hi, @Andrew, this is based on v5.13-rc1, I can rebase whatever way you prefer. This is an implementation of "secret" mappings backed by a file descriptor. The file descriptor backing secret memory mappings is created using a dedicated memfd_secret system call The desired protection mode for the memory is configured using flags parameter of the system call. The mmap() of the file descriptor created with memfd_secret() will create a "secret" memory mapping. The pages in that mapping will be marked as not present in the direct map and will be present only in the page table of the owning mm. Although normally Linux userspace mappings are protected from other users, such secret mappings are useful for environments where a hostile tenant is trying to trick the kernel into giving them access to other tenants mappings. It's designed to provide the following protections: * Enhanced protection (in conjunction with all the other in-kernel attack prevention systems) against ROP attacks. Seceretmem makes "simple" ROP insufficient to perform exfiltration, which increases the required complexity of the attack. Along with other protections like the kernel stack size limit and address space layout randomization which make finding gadgets is really hard, absence of any in-kernel primitive for accessing secret memory means the one gadget ROP attack can't work. Since the only way to access secret memory is to reconstruct the missing mapping entry, the attacker has to recover the physical page and insert a PTE pointing to it in the kernel and then retrieve the contents. That takes at least three gadgets which is a level of difficulty beyond most standard attacks. * Prevent cross-process secret userspace memory exposures. Once the secret memory is allocated, the user can't accidentally pass it into the kernel to be transmitted somewhere. The secreremem pages cannot be accessed via the direct map and they are disallowed in GUP. * Harden against exploited kernel flaws. In order to access secretmem, a kernel-side attack would need to either walk the page tables and create new ones, or spawn a new privileged uiserspace process to perform secrets exfiltration using ptrace. In the future the secret mappings may be used as a mean to protect guest memory in a virtual machine host. For demonstration of secret memory usage we've created a userspace library https://git.kernel.org/pub/scm/linux/kernel/git/jejb/secret-memory-preloade… that does two things: the first is act as a preloader for openssl to redirect all the OPENSSL_malloc calls to secret memory meaning any secret keys get automatically protected this way and the other thing it does is expose the API to the user who needs it. We anticipate that a lot of the use cases would be like the openssl one: many toolkits that deal with secret keys already have special handling for the memory to try to give them greater protection, so this would simply be pluggable into the toolkits without any need for user application modification. Hiding secret memory mappings behind an anonymous file allows usage of the page cache for tracking pages allocated for the "secret" mappings as well as using address_space_operations for e.g. page migration callbacks. The anonymous file may be also used implicitly, like hugetlb files, to implement mmap(MAP_SECRET) and use the secret memory areas with "native" mm ABIs in the future. Removing of the pages from the direct map may cause its fragmentation on architectures that use large pages to map the physical memory which affects the system performance. However, the original Kconfig text for CONFIG_DIRECT_GBPAGES said that gigabyte pages in the direct map "... can improve the kernel's performance a tiny bit ..." (commit 00d1c5e05736 ("x86: add gbpages switches")) and the recent report [1] showed that "... although 1G mappings are a good default choice, there is no compelling evidence that it must be the only choice". Hence, it is sufficient to have secretmem disabled by default with the ability of a system administrator to enable it at boot time. In addition, there is also a long term goal to improve management of the direct map. [1] https://lore.kernel.org/linux-mm/213b4567-46ce-f116-9cdf-bbd0c884eb3c@linux… v20: * Drop the patch that enable multi-page updates to the direct map, per David * Drop the changes to /dev/mem, they anyway have no effect when CONFIG_STRICT_DEVMEM=y * Add Acked-by and Reviewed-by tags v19: https://lore.kernel.org/lkml/20210513184734.29317-1-rppt@kernel.org * block /dev/mem mmap access, per David * disallow mmap/mprotect with PROT_EXEC, per Kees * simplify return in page_is_secretmem(), per Matthew * use unsigned int for syscall falgs, per Yury v18: https://lore.kernel.org/lkml/20210303162209.8609-1-rppt@kernel.org * rebase on v5.12-rc1 * merge kfence fix into the original patch * massage commit message of the patch introducing the memfd_secret syscall v17: https://lore.kernel.org/lkml/20210208084920.2884-1-rppt@kernel.org * Remove pool of large pages backing secretmem allocations, per Michal Hocko * Add secretmem pages to unevictable LRU, per Michal Hocko * Use GFP_HIGHUSER as secretmem mapping mask, per Michal Hocko * Make secretmem an opt-in feature that is disabled by default v16: https://lore.kernel.org/lkml/20210121122723.3446-1-rppt@kernel.org * Fix memory leak intorduced in v15 * Clean the data left from previous page user before handing the page to the userspace Older history: v15: https://lore.kernel.org/lkml/20210120180612.1058-1-rppt@kernel.org v14: https://lore.kernel.org/lkml/20201203062949.5484-1-rppt@kernel.org v13: https://lore.kernel.org/lkml/20201201074559.27742-1-rppt@kernel.org v12: https://lore.kernel.org/lkml/20201125092208.12544-1-rppt@kernel.org v11: https://lore.kernel.org/lkml/20201124092556.12009-1-rppt@kernel.org v10: https://lore.kernel.org/lkml/20201123095432.5860-1-rppt@kernel.org v9: https://lore.kernel.org/lkml/20201117162932.13649-1-rppt@kernel.org v8: https://lore.kernel.org/lkml/20201110151444.20662-1-rppt@kernel.org v7: https://lore.kernel.org/lkml/20201026083752.13267-1-rppt@kernel.org v6: https://lore.kernel.org/lkml/20200924132904.1391-1-rppt@kernel.org v5: https://lore.kernel.org/lkml/20200916073539.3552-1-rppt@kernel.org v4: https://lore.kernel.org/lkml/20200818141554.13945-1-rppt@kernel.org v3: https://lore.kernel.org/lkml/20200804095035.18778-1-rppt@kernel.org v2: https://lore.kernel.org/lkml/20200727162935.31714-1-rppt@kernel.org v1: https://lore.kernel.org/lkml/20200720092435.17469-1-rppt@kernel.org rfc-v2: https://lore.kernel.org/lkml/20200706172051.19465-1-rppt@kernel.org/ rfc-v1: https://lore.kernel.org/lkml/20200130162340.GA14232@rapoport-lnx/ rfc-v0: https://lore.kernel.org/lkml/1572171452-7958-1-git-send-email-rppt@kernel.o… Mike Rapoport (7): mmap: make mlock_future_check() global riscv/Kconfig: make direct map manipulation options depend on MMU set_memory: allow querying whether set_direct_map_*() is actually enabled mm: introduce memfd_secret system call to create "secret" memory areas PM: hibernate: disable when there are active secretmem users arch, mm: wire up memfd_secret system call where relevant secretmem: test: add basic selftest for memfd_secret(2) arch/arm64/include/asm/Kbuild | 1 - arch/arm64/include/asm/cacheflush.h | 6 - arch/arm64/include/asm/kfence.h | 2 +- arch/arm64/include/asm/set_memory.h | 17 ++ arch/arm64/include/uapi/asm/unistd.h | 1 + arch/arm64/kernel/machine_kexec.c | 1 + arch/arm64/mm/mmu.c | 6 +- arch/arm64/mm/pageattr.c | 13 +- arch/riscv/Kconfig | 4 +- arch/riscv/include/asm/unistd.h | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + include/linux/secretmem.h | 54 ++++ include/linux/set_memory.h | 12 + include/linux/syscalls.h | 1 + include/uapi/asm-generic/unistd.h | 7 +- include/uapi/linux/magic.h | 1 + kernel/power/hibernate.c | 5 +- kernel/sys_ni.c | 2 + mm/Kconfig | 5 + mm/Makefile | 1 + mm/gup.c | 12 + mm/internal.h | 3 + mm/mlock.c | 3 +- mm/mmap.c | 5 +- mm/secretmem.c | 254 +++++++++++++++++++ scripts/checksyscalls.sh | 4 + tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 3 +- tools/testing/selftests/vm/memfd_secret.c | 296 ++++++++++++++++++++++ tools/testing/selftests/vm/run_vmtests.sh | 17 ++ 31 files changed, 716 insertions(+), 24 deletions(-) create mode 100644 arch/arm64/include/asm/set_memory.h create mode 100644 include/linux/secretmem.h create mode 100644 mm/secretmem.c create mode 100644 tools/testing/selftests/vm/memfd_secret.c base-commit: 6efb943b8616ec53a5e444193dccf1af9ad627b5 -- 2.28.0

4 years, 1 month

2
9
0 0

[PATCH v5 00/10] userfaultfd: add minor fault handling for shmem

by Axel Rasmussen

Base ==== This series is based on (and therefore should apply cleanly to) the tag "v5.12-rc7-mmots-2021-04-11-20-49", additionally with Peter's selftest cleanup series applied first: https://lore.kernel.org/patchwork/cover/1412450/ Changelog ========= v4->v5: - Picked up {Reviewed,Acked}-by's. - Fix cleanup in error path in shmem_mcopy_atomic_pte(). [Hugh, Peter] - Mention switching to lru_cache_add() in the commit message of 9/10. [Hugh] - Split + reorder commits, so now we 1) implement the faulting path, 2) implement the CONTINUE ioctl, and 3) advertise the feature. Squash the documentation update into step (3). [Hugh, Peter] - Reorder install_pte() cleanup to come before selftest changes. [Hugh] v3->v4: - Fix handling of the shmem private mcopy case. Previously, I had (incorrectly) assumed that !vma_is_anonymous() was equivalent to "the page will be in the page cache". But, in this case we have an optimization where we allocate a new *anonymous* page. So, use a new "bool page_in_cache" instead, which checks if page->mapping is set. Correct several places with this new check. [Hugh] - Fix calling mm_counter() before page_add_..._rmap(). [Hugh] - When modifying shmem_mcopy_atomic_pte() to use the new install_pte() helper, just use lru_cache_add_inactive_or_unevictable(), no need to branch and maybe use lru_cache_add(). [Hugh] - De-pluralize mcopy_atomic_install_pte(s). [Hugh] - Make "writable" a bool, and initialize consistently. [Hugh] v2->v3: - Picked up {Reviewed,Acked}-by's. - Reorder commits: introduce CONTINUE before MINOR registration. [Hugh, Peter] - Don't try to {unlock,put}_page an xarray value in shmem_getpage_gfp. [Hugh] - Move enum mcopy_atomic_mode forward declare out of CONFIG_HUGETLB_PAGE. [Hugh] - Keep mistakenly removed UFFD_USER_MODE_ONLY in selftest. [Peter] - Cleanup context management in self test (make clear implicit, remove unneeded return values now that we have err()). [Peter] - Correct dst_pte argument to dst_pmd in shmem_mcopy_atomic_pte macro. [Hugh] - Mention the new shmem support feature in documentation. [Hugh] v1->v2: - Pick up Reviewed-by's. - Don't swapin page when a minor fault occurs. Notice that it needs to be swapped in, and just immediately fire the minor fault. Let a future CONTINUE deal with swapping in the page. [Peter] - Clarify comment about i_size checks in mm/userfaultfd.c. [Peter] - Only forward declare once (out of #ifdef) in hugetlb.h. [Peter] Changes since [2]: - Squash the fixes ([2]) in with the original series ([1]). This makes reviewing easier, as we no longer have to sift through deltas undoing what we had done before. [Hugh, Peter] - Modify shmem_mcopy_atomic_pte() to use the new mcopy_atomic_install_ptes() helper, reducing code duplication. [Hugh] - Properly trigger handle_userfault() in the shmem_swapin_page() case. [Hugh] - Use shmem_getpage() instead of find_lock_page() to lookup the existing page in for continue. This properly deals with swapped-out pages. [Hugh] - Unconditionally pte_mkdirty() for anon memory (as before). [Peter] - Don't include userfaultfd_k.h in either hugetlb.h or shmem_fs.h. [Hugh] - Add comment for UFFD_FEATURE_MINOR_SHMEM (to match _HUGETLBFS). [Hugh] - Fix some small cleanup issues (parens, reworded conditionals, reduced plumbing of some parameters, simplify labels/gotos, ...). [Hugh, Peter] Overview ======== See the series which added minor faults for hugetlbfs [3] for a detailed overview of minor fault handling in general. This series adds the same support for shmem-backed areas. This series is structured as follows: - Commits 1 and 2 are cleanups. - Commits 3 and 4 implement the new feature (minor fault handling for shmem). - Commit 5 advertises that the feature is now available since at this point it's fully implemented. - Commit 6 is a final cleanup, modifying an existing code path to re-use a new helper we've introduced. - Commits 7, 8, 9, 10 update the userfaultfd selftest to exercise the feature. Use Case ======== In some cases it is useful to have VM memory backed by tmpfs instead of hugetlbfs. So, this feature will be used to support the same VM live migration use case described in my original series. Additionally, Android folks (Lokesh Gidra <lokeshgidra(a)google.com>) hope to optimize the Android Runtime garbage collector using this feature: "The plan is to use userfaultfd for concurrently compacting the heap. With this feature, the heap can be shared-mapped at another location where the GC-thread(s) could continue the compaction operation without the need to invoke userfault ioctl(UFFDIO_COPY) each time. OTOH, if and when Java threads get faults on the heap, UFFDIO_CONTINUE can be used to resume execution. Furthermore, this feature enables updating references in the 'non-moving' portion of the heap efficiently. Without this feature, uneccessary page copying (ioctl(UFFDIO_COPY)) would be required." [1] https://lore.kernel.org/patchwork/cover/1388144/ [2] https://lore.kernel.org/patchwork/patch/1408161/ [3] https://lore.kernel.org/linux-fsdevel/20210301222728.176417-1-axelrasmussen… Axel Rasmussen (10): userfaultfd/hugetlbfs: avoid including userfaultfd_k.h in hugetlb.h userfaultfd/shmem: combine shmem_{mcopy_atomic,mfill_zeropage}_pte userfaultfd/shmem: support minor fault registration for shmem userfaultfd/shmem: support UFFDIO_CONTINUE for shmem userfaultfd/shmem: advertise shmem minor fault support userfaultfd/shmem: modify shmem_mcopy_atomic_pte to use install_pte() userfaultfd/selftests: use memfd_create for shmem test type userfaultfd/selftests: create alias mappings in the shmem test userfaultfd/selftests: reinitialize test context in each test userfaultfd/selftests: exercise minor fault handling shmem support Documentation/admin-guide/mm/userfaultfd.rst | 3 +- fs/userfaultfd.c | 6 +- include/linux/hugetlb.h | 4 +- include/linux/shmem_fs.h | 17 +- include/linux/userfaultfd_k.h | 5 + include/uapi/linux/userfaultfd.h | 7 +- mm/hugetlb.c | 1 + mm/memory.c | 8 +- mm/shmem.c | 110 +++----- mm/userfaultfd.c | 175 ++++++++---- tools/testing/selftests/vm/userfaultfd.c | 274 ++++++++++++------- 11 files changed, 360 insertions(+), 250 deletions(-) -- 2.31.1.498.g6c1eba8ee3d-goog

4 years, 1 month

3
23
0 0

[PATCH v2] lib/test: convert test_overflow.c to use KUnit

by Daniel Latypov

This largely consists of: * replacing `err |= test_func(...)` calls with `test_func(test, ...)`. * changing pr_warn to KUNIT_*_MSG() macros to mark the failed test while printing a diagnostic message * dropping __init as there are concerns of this causing issues w/ KUnit when running on some other arches. With the exception of now needing to set CONFIG_KUNIT=y, the test can still be run as before, at boot time or as a test module. But now the output of the test will be TAP (Test Anything Protocol), the format used by kselftest instead of just warnings and printing "FAIL!" , see [1]. But now the test can also be run more quickly via kunit.py $ ./tools/testing/kunit/kunit.py run --kunitconfig /dev/stdin <<EOF CONFIG_KUNIT=y CONFIG_TEST_OVERFLOW=y EOF Note: after a mrproper this took > Elapsed time: 38.683s total, 3.598s configuring, 32.141s building, 0.000s running (Normally would be less clunky as you wouldn't use a heredoc). [1] Here's an example failure message after tweaking the test array: TAP version 14 1..1 # Subtest: lib_overflow 1..10 # test_u8_overflow: u8 : 18 arithmetic tests # test_u8_overflow: EXPECTATION FAILED at lib/test_overflow.c:251 Expected _got == p->sum, but _got == 0 p->sum == 1 wrong result for 0 + 0 (type u8) ... not ok 1 - test_u8_overflow # test_s8_overflow: s8 : 19 arithmetic tests ok 2 - test_s8_overflow ... # test_overflow_shift: ok: (s32)(0 << 31) == 0 # test_overflow_shift: ok: (s64)(0 << 63) == 0 ok 9 - test_overflow_shift Signed-off-by: Daniel Latypov <dlatypov(a)google.com> Tested-by: David Gow <davidgow(a)google.com> -- v1 -> v2: * Use kunit_info() instead of pr_info(). * means messages are printed prefixed with "# test_name: " * Add in missing conversion to KUNIT_EXPECT_* macros --- lib/Kconfig.debug | 4 +- lib/test_overflow.c | 433 ++++++++++++++++++++------------------------ 2 files changed, 196 insertions(+), 241 deletions(-) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 678c13967580..8e19ba9ac22c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2195,7 +2195,9 @@ config TEST_XARRAY tristate "Test the XArray code at runtime" config TEST_OVERFLOW - tristate "Test check_*_overflow() functions at runtime" + tristate "Test check_*_overflow() functions at runtime" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS config TEST_RHASHTABLE tristate "Perform selftest on resizable hash table" diff --git a/lib/test_overflow.c b/lib/test_overflow.c index 7a4b6f6c5473..098339251908 100644 --- a/lib/test_overflow.c +++ b/lib/test_overflow.c @@ -2,10 +2,9 @@ /* * Test cases for arithmetic overflow checks. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <kunit/test.h> #include <linux/device.h> -#include <linux/init.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/module.h> @@ -19,7 +18,7 @@ t a, b; \ t sum, diff, prod; \ bool s_of, d_of, p_of; \ - } t ## _tests[] __initconst + } t ## _tests[] DEFINE_TEST_ARRAY(u8) = { {0, 0, 0, 0, 0, false, false, false}, @@ -215,48 +214,38 @@ DEFINE_TEST_ARRAY(s64) = { {0, -S64_MAX, -S64_MAX, S64_MAX, 0, false, false, false}, }; -#define check_one_op(t, fmt, op, sym, a, b, r, of) do { \ - t _r; \ - bool _of; \ - \ - _of = check_ ## op ## _overflow(a, b, &_r); \ - if (_of != of) { \ - pr_warn("expected "fmt" "sym" "fmt \ - " to%s overflow (type %s)\n", \ - a, b, of ? "" : " not", #t); \ - err = 1; \ - } \ - if (_r != r) { \ - pr_warn("expected "fmt" "sym" "fmt" == " \ - fmt", got "fmt" (type %s)\n", \ - a, b, r, _r, #t); \ - err = 1; \ - } \ +#define check_one_op(t, fmt, op, sym, a, b, want, of) do { \ + t _got; \ + bool _of; \ + \ + _of = check_ ## op ## _overflow(a, b, &_got); \ + KUNIT_EXPECT_EQ_MSG(test, _of, of, \ + "expected " fmt " " sym " " fmt " to%s overflow " \ + "(type %s)", a, b, of ? "" : " not", #t); \ + \ + KUNIT_EXPECT_EQ_MSG(test, _got, want, \ + "wrong result for " fmt " " sym " " fmt " (type %s)", \ + a, b, #t); \ } while (0) #define DEFINE_TEST_FUNC(t, fmt) \ -static int __init do_test_ ## t(const struct test_ ## t *p) \ -{ \ - int err = 0; \ - \ +static void do_test_ ## t(struct kunit *test, const struct test_ ## t *p)\ +{ \ check_one_op(t, fmt, add, "+", p->a, p->b, p->sum, p->s_of); \ check_one_op(t, fmt, add, "+", p->b, p->a, p->sum, p->s_of); \ check_one_op(t, fmt, sub, "-", p->a, p->b, p->diff, p->d_of); \ check_one_op(t, fmt, mul, "*", p->a, p->b, p->prod, p->p_of); \ check_one_op(t, fmt, mul, "*", p->b, p->a, p->prod, p->p_of); \ - \ - return err; \ } \ \ -static int __init test_ ## t ## _overflow(void) { \ - int err = 0; \ +static void test_ ## t ## _overflow(struct kunit *test) \ +{ \ unsigned i; \ \ - pr_info("%-3s: %zu arithmetic tests\n", #t, \ - ARRAY_SIZE(t ## _tests)); \ + kunit_info(test, "%-3s: %zu arithmetic tests\n", #t, \ + ARRAY_SIZE(t ## _tests)); \ for (i = 0; i < ARRAY_SIZE(t ## _tests); ++i) \ - err |= do_test_ ## t(&t ## _tests[i]); \ - return err; \ + do_test_ ## t(test, &t ## _tests[i]); \ } DEFINE_TEST_FUNC(u8, "%d"); @@ -270,199 +259,174 @@ DEFINE_TEST_FUNC(u64, "%llu"); DEFINE_TEST_FUNC(s64, "%lld"); #endif -static int __init test_overflow_calculation(void) +static void test_overflow_shift(struct kunit *test) { - int err = 0; - - err |= test_u8_overflow(); - err |= test_s8_overflow(); - err |= test_u16_overflow(); - err |= test_s16_overflow(); - err |= test_u32_overflow(); - err |= test_s32_overflow(); -#if BITS_PER_LONG == 64 - err |= test_u64_overflow(); - err |= test_s64_overflow(); -#endif - - return err; -} - -static int __init test_overflow_shift(void) -{ - int err = 0; - /* Args are: value, shift, type, expected result, overflow expected */ -#define TEST_ONE_SHIFT(a, s, t, expect, of) ({ \ +#define TEST_ONE_SHIFT(a, s, t, expect, of) do { \ int __failed = 0; \ typeof(a) __a = (a); \ typeof(s) __s = (s); \ - t __e = (expect); \ - t __d; \ - bool __of = check_shl_overflow(__a, __s, &__d); \ + t __want = (expect); \ + t __got; \ + bool __of = check_shl_overflow(__a, __s, &__got); \ if (__of != of) { \ - pr_warn("expected (%s)(%s << %s) to%s overflow\n", \ - #t, #a, #s, of ? "" : " not"); \ + KUNIT_FAIL(test, "expected (%s)(%s << %s) to%s overflow"\ + #t, #a, #s, of ? "" : " not"); \ __failed = 1; \ - } else if (!__of && __d != __e) { \ - pr_warn("expected (%s)(%s << %s) == %s\n", \ + } else if (!__of && __got != __want) { \ + KUNIT_EXPECT_EQ_MSG(test, __got, __want, \ + "expected (%s)(%s << %s) == %s", \ #t, #a, #s, #expect); \ - if ((t)-1 < 0) \ - pr_warn("got %lld\n", (s64)__d); \ - else \ - pr_warn("got %llu\n", (u64)__d); \ __failed = 1; \ } \ if (!__failed) \ - pr_info("ok: (%s)(%s << %s) == %s\n", #t, #a, #s, \ - of ? "overflow" : #expect); \ - __failed; \ -}) + kunit_info(test, "ok: (%s)(%s << %s) == %s\n", #t, #a, \ + #s, of ? "overflow" : #expect); \ +} while (0) /* Sane shifts. */ - err |= TEST_ONE_SHIFT(1, 0, u8, 1 << 0, false); - err |= TEST_ONE_SHIFT(1, 4, u8, 1 << 4, false); - err |= TEST_ONE_SHIFT(1, 7, u8, 1 << 7, false); - err |= TEST_ONE_SHIFT(0xF, 4, u8, 0xF << 4, false); - err |= TEST_ONE_SHIFT(1, 0, u16, 1 << 0, false); - err |= TEST_ONE_SHIFT(1, 10, u16, 1 << 10, false); - err |= TEST_ONE_SHIFT(1, 15, u16, 1 << 15, false); - err |= TEST_ONE_SHIFT(0xFF, 8, u16, 0xFF << 8, false); - err |= TEST_ONE_SHIFT(1, 0, int, 1 << 0, false); - err |= TEST_ONE_SHIFT(1, 16, int, 1 << 16, false); - err |= TEST_ONE_SHIFT(1, 30, int, 1 << 30, false); - err |= TEST_ONE_SHIFT(1, 0, s32, 1 << 0, false); - err |= TEST_ONE_SHIFT(1, 16, s32, 1 << 16, false); - err |= TEST_ONE_SHIFT(1, 30, s32, 1 << 30, false); - err |= TEST_ONE_SHIFT(1, 0, unsigned int, 1U << 0, false); - err |= TEST_ONE_SHIFT(1, 20, unsigned int, 1U << 20, false); - err |= TEST_ONE_SHIFT(1, 31, unsigned int, 1U << 31, false); - err |= TEST_ONE_SHIFT(0xFFFFU, 16, unsigned int, 0xFFFFU << 16, false); - err |= TEST_ONE_SHIFT(1, 0, u32, 1U << 0, false); - err |= TEST_ONE_SHIFT(1, 20, u32, 1U << 20, false); - err |= TEST_ONE_SHIFT(1, 31, u32, 1U << 31, false); - err |= TEST_ONE_SHIFT(0xFFFFU, 16, u32, 0xFFFFU << 16, false); - err |= TEST_ONE_SHIFT(1, 0, u64, 1ULL << 0, false); - err |= TEST_ONE_SHIFT(1, 40, u64, 1ULL << 40, false); - err |= TEST_ONE_SHIFT(1, 63, u64, 1ULL << 63, false); - err |= TEST_ONE_SHIFT(0xFFFFFFFFULL, 32, u64, - 0xFFFFFFFFULL << 32, false); + TEST_ONE_SHIFT(1, 0, u8, 1 << 0, false); + TEST_ONE_SHIFT(1, 4, u8, 1 << 4, false); + TEST_ONE_SHIFT(1, 7, u8, 1 << 7, false); + TEST_ONE_SHIFT(0xF, 4, u8, 0xF << 4, false); + TEST_ONE_SHIFT(1, 0, u16, 1 << 0, false); + TEST_ONE_SHIFT(1, 10, u16, 1 << 10, false); + TEST_ONE_SHIFT(1, 15, u16, 1 << 15, false); + TEST_ONE_SHIFT(0xFF, 8, u16, 0xFF << 8, false); + TEST_ONE_SHIFT(1, 0, int, 1 << 0, false); + TEST_ONE_SHIFT(1, 16, int, 1 << 16, false); + TEST_ONE_SHIFT(1, 30, int, 1 << 30, false); + TEST_ONE_SHIFT(1, 0, s32, 1 << 0, false); + TEST_ONE_SHIFT(1, 16, s32, 1 << 16, false); + TEST_ONE_SHIFT(1, 30, s32, 1 << 30, false); + TEST_ONE_SHIFT(1, 0, unsigned int, 1U << 0, false); + TEST_ONE_SHIFT(1, 20, unsigned int, 1U << 20, false); + TEST_ONE_SHIFT(1, 31, unsigned int, 1U << 31, false); + TEST_ONE_SHIFT(0xFFFFU, 16, unsigned int, 0xFFFFU << 16, false); + TEST_ONE_SHIFT(1, 0, u32, 1U << 0, false); + TEST_ONE_SHIFT(1, 20, u32, 1U << 20, false); + TEST_ONE_SHIFT(1, 31, u32, 1U << 31, false); + TEST_ONE_SHIFT(0xFFFFU, 16, u32, 0xFFFFU << 16, false); + TEST_ONE_SHIFT(1, 0, u64, 1ULL << 0, false); + TEST_ONE_SHIFT(1, 40, u64, 1ULL << 40, false); + TEST_ONE_SHIFT(1, 63, u64, 1ULL << 63, false); + TEST_ONE_SHIFT(0xFFFFFFFFULL, 32, u64, 0xFFFFFFFFULL << 32, false); /* Sane shift: start and end with 0, without a too-wide shift. */ - err |= TEST_ONE_SHIFT(0, 7, u8, 0, false); - err |= TEST_ONE_SHIFT(0, 15, u16, 0, false); - err |= TEST_ONE_SHIFT(0, 31, unsigned int, 0, false); - err |= TEST_ONE_SHIFT(0, 31, u32, 0, false); - err |= TEST_ONE_SHIFT(0, 63, u64, 0, false); + TEST_ONE_SHIFT(0, 7, u8, 0, false); + TEST_ONE_SHIFT(0, 15, u16, 0, false); + TEST_ONE_SHIFT(0, 31, unsigned int, 0, false); + TEST_ONE_SHIFT(0, 31, u32, 0, false); + TEST_ONE_SHIFT(0, 63, u64, 0, false); /* Sane shift: start and end with 0, without reaching signed bit. */ - err |= TEST_ONE_SHIFT(0, 6, s8, 0, false); - err |= TEST_ONE_SHIFT(0, 14, s16, 0, false); - err |= TEST_ONE_SHIFT(0, 30, int, 0, false); - err |= TEST_ONE_SHIFT(0, 30, s32, 0, false); - err |= TEST_ONE_SHIFT(0, 62, s64, 0, false); + TEST_ONE_SHIFT(0, 6, s8, 0, false); + TEST_ONE_SHIFT(0, 14, s16, 0, false); + TEST_ONE_SHIFT(0, 30, int, 0, false); + TEST_ONE_SHIFT(0, 30, s32, 0, false); + TEST_ONE_SHIFT(0, 62, s64, 0, false); /* Overflow: shifted the bit off the end. */ - err |= TEST_ONE_SHIFT(1, 8, u8, 0, true); - err |= TEST_ONE_SHIFT(1, 16, u16, 0, true); - err |= TEST_ONE_SHIFT(1, 32, unsigned int, 0, true); - err |= TEST_ONE_SHIFT(1, 32, u32, 0, true); - err |= TEST_ONE_SHIFT(1, 64, u64, 0, true); + TEST_ONE_SHIFT(1, 8, u8, 0, true); + TEST_ONE_SHIFT(1, 16, u16, 0, true); + TEST_ONE_SHIFT(1, 32, unsigned int, 0, true); + TEST_ONE_SHIFT(1, 32, u32, 0, true); + TEST_ONE_SHIFT(1, 64, u64, 0, true); /* Overflow: shifted into the signed bit. */ - err |= TEST_ONE_SHIFT(1, 7, s8, 0, true); - err |= TEST_ONE_SHIFT(1, 15, s16, 0, true); - err |= TEST_ONE_SHIFT(1, 31, int, 0, true); - err |= TEST_ONE_SHIFT(1, 31, s32, 0, true); - err |= TEST_ONE_SHIFT(1, 63, s64, 0, true); + TEST_ONE_SHIFT(1, 7, s8, 0, true); + TEST_ONE_SHIFT(1, 15, s16, 0, true); + TEST_ONE_SHIFT(1, 31, int, 0, true); + TEST_ONE_SHIFT(1, 31, s32, 0, true); + TEST_ONE_SHIFT(1, 63, s64, 0, true); /* Overflow: high bit falls off unsigned types. */ /* 10010110 */ - err |= TEST_ONE_SHIFT(150, 1, u8, 0, true); + TEST_ONE_SHIFT(150, 1, u8, 0, true); /* 1000100010010110 */ - err |= TEST_ONE_SHIFT(34966, 1, u16, 0, true); + TEST_ONE_SHIFT(34966, 1, u16, 0, true); /* 10000100000010001000100010010110 */ - err |= TEST_ONE_SHIFT(2215151766U, 1, u32, 0, true); - err |= TEST_ONE_SHIFT(2215151766U, 1, unsigned int, 0, true); + TEST_ONE_SHIFT(2215151766U, 1, u32, 0, true); + TEST_ONE_SHIFT(2215151766U, 1, unsigned int, 0, true); /* 1000001000010000010000000100000010000100000010001000100010010110 */ - err |= TEST_ONE_SHIFT(9372061470395238550ULL, 1, u64, 0, true); + TEST_ONE_SHIFT(9372061470395238550ULL, 1, u64, 0, true); /* Overflow: bit shifted into signed bit on signed types. */ /* 01001011 */ - err |= TEST_ONE_SHIFT(75, 1, s8, 0, true); + TEST_ONE_SHIFT(75, 1, s8, 0, true); /* 0100010001001011 */ - err |= TEST_ONE_SHIFT(17483, 1, s16, 0, true); + TEST_ONE_SHIFT(17483, 1, s16, 0, true); /* 01000010000001000100010001001011 */ - err |= TEST_ONE_SHIFT(1107575883, 1, s32, 0, true); - err |= TEST_ONE_SHIFT(1107575883, 1, int, 0, true); + TEST_ONE_SHIFT(1107575883, 1, s32, 0, true); + TEST_ONE_SHIFT(1107575883, 1, int, 0, true); /* 0100000100001000001000000010000001000010000001000100010001001011 */ - err |= TEST_ONE_SHIFT(4686030735197619275LL, 1, s64, 0, true); + TEST_ONE_SHIFT(4686030735197619275LL, 1, s64, 0, true); /* Overflow: bit shifted past signed bit on signed types. */ /* 01001011 */ - err |= TEST_ONE_SHIFT(75, 2, s8, 0, true); + TEST_ONE_SHIFT(75, 2, s8, 0, true); /* 0100010001001011 */ - err |= TEST_ONE_SHIFT(17483, 2, s16, 0, true); + TEST_ONE_SHIFT(17483, 2, s16, 0, true); /* 01000010000001000100010001001011 */ - err |= TEST_ONE_SHIFT(1107575883, 2, s32, 0, true); - err |= TEST_ONE_SHIFT(1107575883, 2, int, 0, true); + TEST_ONE_SHIFT(1107575883, 2, s32, 0, true); + TEST_ONE_SHIFT(1107575883, 2, int, 0, true); /* 0100000100001000001000000010000001000010000001000100010001001011 */ - err |= TEST_ONE_SHIFT(4686030735197619275LL, 2, s64, 0, true); + TEST_ONE_SHIFT(4686030735197619275LL, 2, s64, 0, true); /* Overflow: values larger than destination type. */ - err |= TEST_ONE_SHIFT(0x100, 0, u8, 0, true); - err |= TEST_ONE_SHIFT(0xFF, 0, s8, 0, true); - err |= TEST_ONE_SHIFT(0x10000U, 0, u16, 0, true); - err |= TEST_ONE_SHIFT(0xFFFFU, 0, s16, 0, true); - err |= TEST_ONE_SHIFT(0x100000000ULL, 0, u32, 0, true); - err |= TEST_ONE_SHIFT(0x100000000ULL, 0, unsigned int, 0, true); - err |= TEST_ONE_SHIFT(0xFFFFFFFFUL, 0, s32, 0, true); - err |= TEST_ONE_SHIFT(0xFFFFFFFFUL, 0, int, 0, true); - err |= TEST_ONE_SHIFT(0xFFFFFFFFFFFFFFFFULL, 0, s64, 0, true); + TEST_ONE_SHIFT(0x100, 0, u8, 0, true); + TEST_ONE_SHIFT(0xFF, 0, s8, 0, true); + TEST_ONE_SHIFT(0x10000U, 0, u16, 0, true); + TEST_ONE_SHIFT(0xFFFFU, 0, s16, 0, true); + TEST_ONE_SHIFT(0x100000000ULL, 0, u32, 0, true); + TEST_ONE_SHIFT(0x100000000ULL, 0, unsigned int, 0, true); + TEST_ONE_SHIFT(0xFFFFFFFFUL, 0, s32, 0, true); + TEST_ONE_SHIFT(0xFFFFFFFFUL, 0, int, 0, true); + TEST_ONE_SHIFT(0xFFFFFFFFFFFFFFFFULL, 0, s64, 0, true); /* Nonsense: negative initial value. */ - err |= TEST_ONE_SHIFT(-1, 0, s8, 0, true); - err |= TEST_ONE_SHIFT(-1, 0, u8, 0, true); - err |= TEST_ONE_SHIFT(-5, 0, s16, 0, true); - err |= TEST_ONE_SHIFT(-5, 0, u16, 0, true); - err |= TEST_ONE_SHIFT(-10, 0, int, 0, true); - err |= TEST_ONE_SHIFT(-10, 0, unsigned int, 0, true); - err |= TEST_ONE_SHIFT(-100, 0, s32, 0, true); - err |= TEST_ONE_SHIFT(-100, 0, u32, 0, true); - err |= TEST_ONE_SHIFT(-10000, 0, s64, 0, true); - err |= TEST_ONE_SHIFT(-10000, 0, u64, 0, true); + TEST_ONE_SHIFT(-1, 0, s8, 0, true); + TEST_ONE_SHIFT(-1, 0, u8, 0, true); + TEST_ONE_SHIFT(-5, 0, s16, 0, true); + TEST_ONE_SHIFT(-5, 0, u16, 0, true); + TEST_ONE_SHIFT(-10, 0, int, 0, true); + TEST_ONE_SHIFT(-10, 0, unsigned int, 0, true); + TEST_ONE_SHIFT(-100, 0, s32, 0, true); + TEST_ONE_SHIFT(-100, 0, u32, 0, true); + TEST_ONE_SHIFT(-10000, 0, s64, 0, true); + TEST_ONE_SHIFT(-10000, 0, u64, 0, true); /* Nonsense: negative shift values. */ - err |= TEST_ONE_SHIFT(0, -5, s8, 0, true); - err |= TEST_ONE_SHIFT(0, -5, u8, 0, true); - err |= TEST_ONE_SHIFT(0, -10, s16, 0, true); - err |= TEST_ONE_SHIFT(0, -10, u16, 0, true); - err |= TEST_ONE_SHIFT(0, -15, int, 0, true); - err |= TEST_ONE_SHIFT(0, -15, unsigned int, 0, true); - err |= TEST_ONE_SHIFT(0, -20, s32, 0, true); - err |= TEST_ONE_SHIFT(0, -20, u32, 0, true); - err |= TEST_ONE_SHIFT(0, -30, s64, 0, true); - err |= TEST_ONE_SHIFT(0, -30, u64, 0, true); + TEST_ONE_SHIFT(0, -5, s8, 0, true); + TEST_ONE_SHIFT(0, -5, u8, 0, true); + TEST_ONE_SHIFT(0, -10, s16, 0, true); + TEST_ONE_SHIFT(0, -10, u16, 0, true); + TEST_ONE_SHIFT(0, -15, int, 0, true); + TEST_ONE_SHIFT(0, -15, unsigned int, 0, true); + TEST_ONE_SHIFT(0, -20, s32, 0, true); + TEST_ONE_SHIFT(0, -20, u32, 0, true); + TEST_ONE_SHIFT(0, -30, s64, 0, true); + TEST_ONE_SHIFT(0, -30, u64, 0, true); /* Overflow: shifted at or beyond entire type's bit width. */ - err |= TEST_ONE_SHIFT(0, 8, u8, 0, true); - err |= TEST_ONE_SHIFT(0, 9, u8, 0, true); - err |= TEST_ONE_SHIFT(0, 8, s8, 0, true); - err |= TEST_ONE_SHIFT(0, 9, s8, 0, true); - err |= TEST_ONE_SHIFT(0, 16, u16, 0, true); - err |= TEST_ONE_SHIFT(0, 17, u16, 0, true); - err |= TEST_ONE_SHIFT(0, 16, s16, 0, true); - err |= TEST_ONE_SHIFT(0, 17, s16, 0, true); - err |= TEST_ONE_SHIFT(0, 32, u32, 0, true); - err |= TEST_ONE_SHIFT(0, 33, u32, 0, true); - err |= TEST_ONE_SHIFT(0, 32, int, 0, true); - err |= TEST_ONE_SHIFT(0, 33, int, 0, true); - err |= TEST_ONE_SHIFT(0, 32, s32, 0, true); - err |= TEST_ONE_SHIFT(0, 33, s32, 0, true); - err |= TEST_ONE_SHIFT(0, 64, u64, 0, true); - err |= TEST_ONE_SHIFT(0, 65, u64, 0, true); - err |= TEST_ONE_SHIFT(0, 64, s64, 0, true); - err |= TEST_ONE_SHIFT(0, 65, s64, 0, true); + TEST_ONE_SHIFT(0, 8, u8, 0, true); + TEST_ONE_SHIFT(0, 9, u8, 0, true); + TEST_ONE_SHIFT(0, 8, s8, 0, true); + TEST_ONE_SHIFT(0, 9, s8, 0, true); + TEST_ONE_SHIFT(0, 16, u16, 0, true); + TEST_ONE_SHIFT(0, 17, u16, 0, true); + TEST_ONE_SHIFT(0, 16, s16, 0, true); + TEST_ONE_SHIFT(0, 17, s16, 0, true); + TEST_ONE_SHIFT(0, 32, u32, 0, true); + TEST_ONE_SHIFT(0, 33, u32, 0, true); + TEST_ONE_SHIFT(0, 32, int, 0, true); + TEST_ONE_SHIFT(0, 33, int, 0, true); + TEST_ONE_SHIFT(0, 32, s32, 0, true); + TEST_ONE_SHIFT(0, 33, s32, 0, true); + TEST_ONE_SHIFT(0, 64, u64, 0, true); + TEST_ONE_SHIFT(0, 65, u64, 0, true); + TEST_ONE_SHIFT(0, 64, s64, 0, true); + TEST_ONE_SHIFT(0, 65, s64, 0, true); /* * Corner case: for unsigned types, we fail when we've shifted @@ -473,13 +437,11 @@ static int __init test_overflow_shift(void) * signed bit). So, for now, we will test this condition but * mark it as not expected to overflow. */ - err |= TEST_ONE_SHIFT(0, 7, s8, 0, false); - err |= TEST_ONE_SHIFT(0, 15, s16, 0, false); - err |= TEST_ONE_SHIFT(0, 31, int, 0, false); - err |= TEST_ONE_SHIFT(0, 31, s32, 0, false); - err |= TEST_ONE_SHIFT(0, 63, s64, 0, false); - - return err; + TEST_ONE_SHIFT(0, 7, s8, 0, false); + TEST_ONE_SHIFT(0, 15, s16, 0, false); + TEST_ONE_SHIFT(0, 31, int, 0, false); + TEST_ONE_SHIFT(0, 31, s32, 0, false); + TEST_ONE_SHIFT(0, 63, s64, 0, false); } /* @@ -499,7 +461,7 @@ static int __init test_overflow_shift(void) #define TEST_SIZE (5 * 4096) #define DEFINE_TEST_ALLOC(func, free_func, want_arg, want_gfp, want_node)\ -static int __init test_ ## func (void *arg) \ +static void test_ ## func (struct kunit *test, void *arg) \ { \ volatile size_t a = TEST_SIZE; \ volatile size_t b = (SIZE_MAX / TEST_SIZE) + 1; \ @@ -507,31 +469,26 @@ static int __init test_ ## func (void *arg) \ \ /* Tiny allocation test. */ \ ptr = alloc ## want_arg ## want_gfp ## want_node (func, arg, 1);\ - if (!ptr) { \ - pr_warn(#func " failed regular allocation?!\n"); \ - return 1; \ - } \ + KUNIT_ASSERT_NOT_ERR_OR_NULL_MSG(test, ptr, \ + #func " failed regular allocation?!"); \ free ## want_arg (free_func, arg, ptr); \ \ /* Wrapped allocation test. */ \ ptr = alloc ## want_arg ## want_gfp ## want_node (func, arg, \ a * b); \ - if (!ptr) { \ - pr_warn(#func " unexpectedly failed bad wrapping?!\n"); \ - return 1; \ - } \ + KUNIT_ASSERT_NOT_ERR_OR_NULL_MSG(test, ptr, \ + #func " unexpectedly failed bad wrapping?!"); \ free ## want_arg (free_func, arg, ptr); \ \ /* Saturated allocation test. */ \ ptr = alloc ## want_arg ## want_gfp ## want_node (func, arg, \ array_size(a, b)); \ if (ptr) { \ - pr_warn(#func " missed saturation!\n"); \ + KUNIT_FAIL(test, #func " missed saturation!\n"); \ free ## want_arg (free_func, arg, ptr); \ - return 1; \ + return; \ } \ - pr_info(#func " detected saturation\n"); \ - return 0; \ + kunit_info(test, #func " detected saturation\n"); \ } /* @@ -555,60 +512,56 @@ DEFINE_TEST_ALLOC(kvzalloc_node, kvfree, 0, 1, 1); DEFINE_TEST_ALLOC(devm_kmalloc, devm_kfree, 1, 1, 0); DEFINE_TEST_ALLOC(devm_kzalloc, devm_kfree, 1, 1, 0); -static int __init test_overflow_allocation(void) +static void test_overflow_allocation(struct kunit *test) { const char device_name[] = "overflow-test"; struct device *dev; - int err = 0; /* Create dummy device for devm_kmalloc()-family tests. */ dev = root_device_register(device_name); - if (IS_ERR(dev)) { - pr_warn("Cannot register test device\n"); - return 1; - } - - err |= test_kmalloc(NULL); - err |= test_kmalloc_node(NULL); - err |= test_kzalloc(NULL); - err |= test_kzalloc_node(NULL); - err |= test_kvmalloc(NULL); - err |= test_kvmalloc_node(NULL); - err |= test_kvzalloc(NULL); - err |= test_kvzalloc_node(NULL); - err |= test_vmalloc(NULL); - err |= test_vmalloc_node(NULL); - err |= test_vzalloc(NULL); - err |= test_vzalloc_node(NULL); - err |= test_devm_kmalloc(dev); - err |= test_devm_kzalloc(dev); + KUNIT_ASSERT_NOT_ERR_OR_NULL_MSG(test, dev, + "Cannot register test device"); + + test_kmalloc(test, NULL); + test_kmalloc_node(test, NULL); + test_kzalloc(test, NULL); + test_kzalloc_node(test, NULL); + test_kvmalloc(test, NULL); + test_kvmalloc_node(test, NULL); + test_kvzalloc(test, NULL); + test_kvzalloc_node(test, NULL); + test_vmalloc(test, NULL); + test_vmalloc_node(test, NULL); + test_vzalloc(test, NULL); + test_vzalloc_node(test, NULL); + test_devm_kmalloc(test, dev); + test_devm_kzalloc(test, dev); device_unregister(dev); - - return err; } -static int __init test_module_init(void) -{ - int err = 0; - - err |= test_overflow_calculation(); - err |= test_overflow_shift(); - err |= test_overflow_allocation(); +static struct kunit_case overflow_test_cases[] = { + KUNIT_CASE(test_u8_overflow), + KUNIT_CASE(test_s8_overflow), + KUNIT_CASE(test_u16_overflow), + KUNIT_CASE(test_s16_overflow), + KUNIT_CASE(test_u32_overflow), + KUNIT_CASE(test_s32_overflow), +#if BITS_PER_LONG == 64 + KUNIT_CASE(test_u64_overflow), + KUNIT_CASE(test_s64_overflow), +#endif - if (err) { - pr_warn("FAIL!\n"); - err = -EINVAL; - } else { - pr_info("all tests passed\n"); - } + KUNIT_CASE(test_overflow_shift), + KUNIT_CASE(test_overflow_allocation), + {} +}; - return err; -} +static struct kunit_suite overflow_test_suite = { + .name = "lib_overflow", + .test_cases = overflow_test_cases, +}; -static void __exit test_module_exit(void) -{ } +kunit_test_suites(&overflow_test_suite); -module_init(test_module_init); -module_exit(test_module_exit); MODULE_LICENSE("Dual MIT/GPL"); base-commit: 88b06399c9c766c283e070b022b5ceafa4f63f19 -- 2.31.1.607.g51e8a6a459-goog

4 years, 1 month

3
2
0 0

[PATCH] kunit: arch/um/configs: Enable KUNIT_ALL_TESTS by default

by David Gow

Make the default .kunitconfig (specified in arch/um/configs/kunit_defconfig) specify CONFIG_KUNIT_ALL_TESTS by default. KUNIT_ALL_TESTS runs all tests which have satisfied dependencies in the current .config (which would be the architecture defconfig). Currently, the default .kunitconfig enables only the example tests and KUnit's own tests. While this does provide a good example of what a .kunitconfig for running a few individual tests should look like, it does mean that kunit_tool runs a pretty paltry collection of tests by default. A default run of ./tools/testing/kunit/kunit.py run now runs 70 tests instead of 14. Signed-off-by: David Gow <davidgow(a)google.com> --- arch/um/configs/kunit_defconfig | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/um/configs/kunit_defconfig b/arch/um/configs/kunit_defconfig index 9235b7d42d38..becf3432a375 100644 --- a/arch/um/configs/kunit_defconfig +++ b/arch/um/configs/kunit_defconfig @@ -1,3 +1,2 @@ CONFIG_KUNIT=y -CONFIG_KUNIT_TEST=y -CONFIG_KUNIT_EXAMPLE_TEST=y +CONFIG_KUNIT_ALL_TESTS=y -- 2.31.1.751.gd2f1c929bd-goog

4 years, 1 month

3
2
0 0

[PATCH v9 6/6] selftest/x86/signal: Include test cases for validating sigaltstack

by Chang S. Bae

The test measures the kernel's signal delivery with different (enough vs. insufficient) stack sizes. Signed-off-by: Chang S. Bae <chang.seok.bae(a)intel.com> Reviewed-by: Len Brown <len.brown(a)intel.com> Cc: x86(a)kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org --- Changes from v3: * Revised test messages again (Borislav Petkov) Changes from v2: * Revised test messages (Borislav Petkov) --- tools/testing/selftests/x86/Makefile | 2 +- tools/testing/selftests/x86/sigaltstack.c | 128 ++++++++++++++++++++++ 2 files changed, 129 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/x86/sigaltstack.c diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 333980375bc7..65bba2ae86ee 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -13,7 +13,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ test_vsyscall mov_ss_trap \ - syscall_arg_fault fsgsbase_restore + syscall_arg_fault fsgsbase_restore sigaltstack TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/sigaltstack.c b/tools/testing/selftests/x86/sigaltstack.c new file mode 100644 index 000000000000..f689af75e979 --- /dev/null +++ b/tools/testing/selftests/x86/sigaltstack.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define _GNU_SOURCE +#include <signal.h> +#include <stdio.h> +#include <stdbool.h> +#include <string.h> +#include <err.h> +#include <errno.h> +#include <limits.h> +#include <sys/mman.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <sys/resource.h> +#include <setjmp.h> + +/* sigaltstack()-enforced minimum stack */ +#define ENFORCED_MINSIGSTKSZ 2048 + +#ifndef AT_MINSIGSTKSZ +# define AT_MINSIGSTKSZ 51 +#endif + +static int nerrs; + +static bool sigalrm_expected; + +static unsigned long at_minstack_size; + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static int setup_altstack(void *start, unsigned long size) +{ + stack_t ss; + + memset(&ss, 0, sizeof(ss)); + ss.ss_size = size; + ss.ss_sp = start; + + return sigaltstack(&ss, NULL); +} + +static jmp_buf jmpbuf; + +static void sigsegv(int sig, siginfo_t *info, void *ctx_void) +{ + if (sigalrm_expected) { + printf("[FAIL]\tWrong signal delivered: SIGSEGV (expected SIGALRM)."); + nerrs++; + } else { + printf("[OK]\tSIGSEGV signal delivered.\n"); + } + + siglongjmp(jmpbuf, 1); +} + +static void sigalrm(int sig, siginfo_t *info, void *ctx_void) +{ + if (!sigalrm_expected) { + printf("[FAIL]\tWrong signal delivered: SIGALRM (expected SIGSEGV)."); + nerrs++; + } else { + printf("[OK]\tSIGALRM signal delivered.\n"); + } +} + +static void test_sigaltstack(void *altstack, unsigned long size) +{ + if (setup_altstack(altstack, size)) + err(1, "sigaltstack()"); + + sigalrm_expected = (size > at_minstack_size) ? true : false; + + sethandler(SIGSEGV, sigsegv, 0); + sethandler(SIGALRM, sigalrm, SA_ONSTACK); + + if (!sigsetjmp(jmpbuf, 1)) { + printf("[RUN]\tTest an alternate signal stack of %ssufficient size.\n", + sigalrm_expected ? "" : "in"); + printf("\tRaise SIGALRM. %s is expected to be delivered.\n", + sigalrm_expected ? "It" : "SIGSEGV"); + raise(SIGALRM); + } + + clearhandler(SIGALRM); + clearhandler(SIGSEGV); +} + +int main(void) +{ + void *altstack; + + at_minstack_size = getauxval(AT_MINSIGSTKSZ); + + altstack = mmap(NULL, at_minstack_size + SIGSTKSZ, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (altstack == MAP_FAILED) + err(1, "mmap()"); + + if ((ENFORCED_MINSIGSTKSZ + 1) < at_minstack_size) + test_sigaltstack(altstack, ENFORCED_MINSIGSTKSZ + 1); + + test_sigaltstack(altstack, at_minstack_size + SIGSTKSZ); + + return nerrs == 0 ? 0 : 1; +} -- 2.17.1

4 years, 1 month

1
0
0 0

[PATCH v9 4/6] selftest/sigaltstack: Use the AT_MINSIGSTKSZ aux vector if available

by Chang S. Bae

The SIGSTKSZ constant may not represent enough stack size in some architectures as the hardware state size grows. Use getauxval(AT_MINSIGSTKSZ) to increase the stack size. Signed-off-by: Chang S. Bae <chang.seok.bae(a)intel.com> Reviewed-by: Len Brown <len.brown(a)intel.com> Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org --- Changes from v5: * Added as a new patch. --- tools/testing/selftests/sigaltstack/sas.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index 8934a3766d20..c53b070755b6 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -17,6 +17,7 @@ #include <string.h> #include <assert.h> #include <errno.h> +#include <sys/auxv.h> #include "../kselftest.h" @@ -24,6 +25,11 @@ #define SS_AUTODISARM (1U << 31) #endif +#ifndef AT_MINSIGSTKSZ +#define AT_MINSIGSTKSZ 51 +#endif + +static unsigned int stack_size; static void *sstack, *ustack; static ucontext_t uc, sc; static const char *msg = "[OK]\tStack preserved"; @@ -47,7 +53,7 @@ void my_usr1(int sig, siginfo_t *si, void *u) #endif if (sp < (unsigned long)sstack || - sp >= (unsigned long)sstack + SIGSTKSZ) { + sp >= (unsigned long)sstack + stack_size) { ksft_exit_fail_msg("SP is not on sigaltstack\n"); } /* put some data on stack. other sighandler will try to overwrite it */ @@ -108,6 +114,10 @@ int main(void) stack_t stk; int err; + /* Make sure more than the required minimum. */ + stack_size = getauxval(AT_MINSIGSTKSZ) + SIGSTKSZ; + ksft_print_msg("[NOTE]\tthe stack size is %lu\n", stack_size); + ksft_print_header(); ksft_set_plan(3); @@ -117,7 +127,7 @@ int main(void) sigaction(SIGUSR1, &act, NULL); act.sa_sigaction = my_usr2; sigaction(SIGUSR2, &act, NULL); - sstack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, + sstack = mmap(NULL, stack_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); if (sstack == MAP_FAILED) { ksft_exit_fail_msg("mmap() - %s\n", strerror(errno)); @@ -139,7 +149,7 @@ int main(void) } stk.ss_sp = sstack; - stk.ss_size = SIGSTKSZ; + stk.ss_size = stack_size; stk.ss_flags = SS_ONSTACK | SS_AUTODISARM; err = sigaltstack(&stk, NULL); if (err) { @@ -161,7 +171,7 @@ int main(void) } } - ustack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, + ustack = mmap(NULL, stack_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); if (ustack == MAP_FAILED) { ksft_exit_fail_msg("mmap() - %s\n", strerror(errno)); @@ -170,7 +180,7 @@ int main(void) getcontext(&uc); uc.uc_link = NULL; uc.uc_stack.ss_sp = ustack; - uc.uc_stack.ss_size = SIGSTKSZ; + uc.uc_stack.ss_size = stack_size; makecontext(&uc, switch_fn, 0); raise(SIGUSR1); -- 2.17.1

4 years, 1 month

1
0
0 0

[PATCH 0/5] KVM: selftests: exercise userfaultfd minor faults

by Axel Rasmussen

Base ==== These patches are based upon Andrew Morton's v5.13-rc1-mmots-2021-05-10-22-15 tag. This is because this series depends on: - UFFD minor fault support for hugetlbfs (in v5.13-rc1) [1] - UFFD minor fault support for shmem (in Andrew's tree) [2] [1] https://lore.kernel.org/linux-fsdevel/20210301222728.176417-1-axelrasmussen… [2] https://lore.kernel.org/patchwork/cover/1420967/ Overview ======== Minor fault handling is a new userfaultfd feature whose goal is generally to improve performance. In particular, it is intended for use with demand paging. There are more details in the cover letters for this new feature (linked above), but at a high level the idea is that we think of these three phases of live migration of a VM: 1. Precopy, where we copy "some" pages from the source to the target, while the VM is still running on the source machine. 2. Blackout, where execution stops on the source, and begins on the target. 3. Postcopy, where the VM is running on the target, some pages are already up to date, and others are not (because they weren't copied, or were modified after being copied). During postcopy, the first time the guest touches memory, we intercept a minor fault. Userspace checks whether or not the page is already up to date. If needed, we copy the final version of the page from the soure machine. This could be done with RDMA for example, to do it truly in place / with no copying. At this point, all that's left is to setup PTEs for the guest: so we issue UFFDIO_CONTINUE. No copying or page allocation needed. Because of this use case, it's useful to exercise this as part of the demand paging test. It lets us ensure the use case works correctly end-to-end, and also gives us an in-tree way to profile the end-to-end flow for future performance improvements. Axel Rasmussen (5): KVM: selftests: allow different backing memory types for demand paging KVM: selftests: add shmem backing source type KVM: selftests: create alias mappings when using shared memory KVM: selftests: allow using UFFD minor faults for demand paging KVM: selftests: add shared hugetlbfs backing source type .../selftests/kvm/demand_paging_test.c | 146 +++++++++++++----- .../testing/selftests/kvm/include/kvm_util.h | 1 + .../testing/selftests/kvm/include/test_util.h | 11 ++ tools/testing/selftests/kvm/lib/kvm_util.c | 79 +++++++++- .../selftests/kvm/lib/kvm_util_internal.h | 2 + tools/testing/selftests/kvm/lib/test_util.c | 46 ++++-- 6 files changed, 222 insertions(+), 63 deletions(-) -- 2.31.1.607.g51e8a6a459-goog

4 years, 1 month

2
13
0 0

[PATCH 1/1] selftests/powerpc: Remove duplicated header file inclusion

by Zhen Lei

The header file <pthread.h> is already included above and can be removed here. Signed-off-by: Zhen Lei <thunder.leizhen(a)huawei.com> --- tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c index e2a0c07e8362..9ef37a9836ac 100644 --- a/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c +++ b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c @@ -17,7 +17,6 @@ #include <pthread.h> #include <sys/mman.h> #include <unistd.h> -#include <pthread.h> #include "tm.h" #include "utils.h" -- 2.25.1

4 years, 1 month

1
0
0 0

[PATCH] [v2] selftests: powerpc: Remove unneeded variables

by Wan Jiabing

Fix coccicheck warning: ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:539:5-7: Unneeded variable: "rc". Return "0" on line 562 ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:567:5-7: Unneeded variable: "rc". Return "0" on line 580 ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:585:5-7: Unneeded variable: "rc". Return "0" on line 594 ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:600:5-7: Unneeded variable: "rc". Return "0" on line 611 ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:416:5-7: Unneeded variable: "rc". Return "0" on line 470 ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:475:5-7: Unneeded variable: "rc". Return "0" on line 485 ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:490:5-7: Unneeded variable: "rc". Return "0" on line 506 ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:511:5-7: Unneeded variable: "rc". Return "0" on line 534 ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:331:5-7: Unneeded variable: "rc". Return "0" on line 344 ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:349:5-7: Unneeded variable: "rc". Return "0" on line 360 ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:365:5-7: Unneeded variable: "rc". Return "0" on line 392 ./tools/testing/selftests/powerpc/alignment/alignment_handler.c:397:5-7: Unneeded variable: "rc". Return "0" on line 411 Signed-off-by: Wan Jiabing <wanjiabing(a)vivo.com> --- Changelog: v2: - Modify the subject line. --- .../powerpc/alignment/alignment_handler.c | 48 +++++-------------- 1 file changed, 12 insertions(+), 36 deletions(-) diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c index c25cf7cd45e9..48bfb7b36d84 100644 --- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c +++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c @@ -328,8 +328,6 @@ static bool can_open_cifile(void) int test_alignment_handler_vsx_206(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); @@ -341,13 +339,11 @@ int test_alignment_handler_vsx_206(void) STORE_VSX_XFORM_TEST(stxvd2x); STORE_VSX_XFORM_TEST(stxvw4x); STORE_VSX_XFORM_TEST(stxsdx); - return rc; + return 0; } int test_alignment_handler_vsx_207(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07)); @@ -357,13 +353,11 @@ int test_alignment_handler_vsx_207(void) LOAD_VSX_XFORM_TEST(lxsiwzx); STORE_VSX_XFORM_TEST(stxsspx); STORE_VSX_XFORM_TEST(stxsiwx); - return rc; + return 0; } int test_alignment_handler_vsx_300(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); @@ -389,13 +383,11 @@ int test_alignment_handler_vsx_300(void) STORE_VSX_XFORM_TEST(stxvx); STORE_VSX_XFORM_TEST(stxvl); STORE_VSX_XFORM_TEST(stxvll); - return rc; + return 0; } int test_alignment_handler_vsx_prefix(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); @@ -408,13 +400,11 @@ int test_alignment_handler_vsx_prefix(void) STORE_VSX_8LS_PREFIX_TEST(PSTXSSP, 0); STORE_VSX_8LS_PREFIX_TEST(PSTXV0, 0); STORE_VSX_8LS_PREFIX_TEST(PSTXV1, 1); - return rc; + return 0; } int test_alignment_handler_integer(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); printf("Integer\n"); @@ -467,13 +457,11 @@ int test_alignment_handler_integer(void) STORE_DFORM_TEST(stmw); #endif - return rc; + return 0; } int test_alignment_handler_integer_206(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); @@ -482,13 +470,11 @@ int test_alignment_handler_integer_206(void) LOAD_XFORM_TEST(ldbrx); STORE_XFORM_TEST(stdbrx); - return rc; + return 0; } int test_alignment_handler_integer_prefix(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); @@ -503,13 +489,11 @@ int test_alignment_handler_integer_prefix(void) STORE_MLS_PREFIX_TEST(PSTH); STORE_MLS_PREFIX_TEST(PSTW); STORE_8LS_PREFIX_TEST(PSTD); - return rc; + return 0; } int test_alignment_handler_vmx(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); SKIP_IF(!have_hwcap(PPC_FEATURE_HAS_ALTIVEC)); @@ -531,13 +515,11 @@ int test_alignment_handler_vmx(void) STORE_VMX_XFORM_TEST(stvehx); STORE_VMX_XFORM_TEST(stvewx); STORE_VMX_XFORM_TEST(stvxl); - return rc; + return 0; } int test_alignment_handler_fp(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); printf("Floating point\n"); @@ -559,13 +541,11 @@ int test_alignment_handler_fp(void) STORE_FLOAT_XFORM_TEST(stfsux); STORE_FLOAT_XFORM_TEST(stfiwx); - return rc; + return 0; } int test_alignment_handler_fp_205(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_05)); @@ -577,13 +557,11 @@ int test_alignment_handler_fp_205(void) STORE_FLOAT_DFORM_TEST(stfdp); STORE_FLOAT_XFORM_TEST(stfdpx); - return rc; + return 0; } int test_alignment_handler_fp_206(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); @@ -591,14 +569,12 @@ int test_alignment_handler_fp_206(void) LOAD_FLOAT_XFORM_TEST(lfiwzx); - return rc; + return 0; } int test_alignment_handler_fp_prefix(void) { - int rc = 0; - SKIP_IF(!can_open_cifile()); SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); @@ -608,7 +584,7 @@ int test_alignment_handler_fp_prefix(void) LOAD_FLOAT_MLS_PREFIX_TEST(PLFD); STORE_FLOAT_MLS_PREFIX_TEST(PSTFS); STORE_FLOAT_MLS_PREFIX_TEST(PSTFD); - return rc; + return 0; } void usage(char *prog) -- 2.30.2

4 years, 1 month

2
1
0 0

[PATCH RESEND v2 1/2] KVM: selftests: Keep track of memslots more efficiently

by Maciej S. Szmigiero

From: "Maciej S. Szmigiero" <maciej.szmigiero(a)oracle.com> The KVM selftest framework was using a simple list for keeping track of the memslots currently in use. This resulted in lookups and adding a single memslot being O(n), the later due to linear scanning of the existing memslot set to check for the presence of any conflicting entries. Before this change, benchmarking high count of memslots was more or less impossible as pretty much all the benchmark time was spent in the selftest framework code. We can simply use a rbtree for keeping track of both of gfn and hva. We don't need an interval tree for hva here as we can't have overlapping memslots because we allocate a completely new memory chunk for each new memslot. Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero(a)oracle.com> Reviewed-by: Andrew Jones <drjones(a)redhat.com> --- This is just a resend of this patch without any changes. tools/testing/selftests/kvm/Makefile | 2 +- tools/testing/selftests/kvm/lib/kvm_util.c | 141 ++++++++++++++---- .../selftests/kvm/lib/kvm_util_internal.h | 15 +- tools/testing/selftests/kvm/lib/rbtree.c | 1 + 4 files changed, 124 insertions(+), 35 deletions(-) create mode 100644 tools/testing/selftests/kvm/lib/rbtree.c diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index e439d027939d..a8c30f888d40 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -33,7 +33,7 @@ ifeq ($(ARCH),s390) UNAME_M := s390x endif -LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c +LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index fc83f6c5902d..646e94cc101b 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -203,7 +203,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_ASSERT(vm != NULL, "Insufficient Memory"); INIT_LIST_HEAD(&vm->vcpus); - INIT_LIST_HEAD(&vm->userspace_mem_regions); + vm->regions.gpa_tree = RB_ROOT; + vm->regions.hva_tree = RB_ROOT; + hash_init(vm->regions.slot_hash); vm->mode = mode; vm->type = 0; @@ -355,13 +357,14 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, */ void kvm_vm_restart(struct kvm_vm *vmp, int perm) { + int ctr; struct userspace_mem_region *region; vm_open(vmp, perm); if (vmp->has_irqchip) vm_create_irqchip(vmp); - list_for_each_entry(region, &vmp->userspace_mem_regions, list) { + hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) { int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, &region->region); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" @@ -424,14 +427,21 @@ uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) static struct userspace_mem_region * userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + for (node = vm->regions.gpa_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, gpa_node); uint64_t existing_start = region->region.guest_phys_addr; uint64_t existing_end = region->region.guest_phys_addr + region->region.memory_size - 1; if (start <= existing_end && end >= existing_start) return region; + + if (start < existing_start) + node = node->rb_left; + else + node = node->rb_right; } return NULL; @@ -546,11 +556,16 @@ void kvm_vm_release(struct kvm_vm *vmp) } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region) + struct userspace_mem_region *region, + bool unlink) { int ret; - list_del(&region->list); + if (unlink) { + rb_erase(&region->gpa_node, &vm->regions.gpa_tree); + rb_erase(&region->hva_node, &vm->regions.hva_tree); + hash_del(&region->slot_node); + } region->region.memory_size = 0; ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region); @@ -569,14 +584,16 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, */ void kvm_vm_free(struct kvm_vm *vmp) { - struct userspace_mem_region *region, *tmp; + int ctr; + struct hlist_node *node; + struct userspace_mem_region *region; if (vmp == NULL) return; /* Free userspace_mem_regions. */ - list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list) - __vm_mem_region_delete(vmp, region); + hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) + __vm_mem_region_delete(vmp, region, false); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -658,6 +675,57 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) return 0; } +static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &gpa_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), gpa_node); + parent = *cur; + if (region->region.guest_phys_addr < + cregion->region.guest_phys_addr) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->region.guest_phys_addr != + cregion->region.guest_phys_addr, + "Duplicate GPA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(&region->gpa_node, parent, cur); + rb_insert_color(&region->gpa_node, gpa_tree); +} + +static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &hva_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), hva_node); + parent = *cur; + if (region->host_mem < cregion->host_mem) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->host_mem != + cregion->host_mem, + "Duplicate HVA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(&region->hva_node, parent, cur); + rb_insert_color(&region->hva_node, hva_tree); +} + /* * VM Userspace Memory Region Add * @@ -722,7 +790,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, (uint64_t) region->region.memory_size); /* Confirm no region with the requested slot already exists. */ - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + slot) { if (region->region.slot != slot) continue; @@ -793,8 +862,10 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, ret, errno, slot, flags, guest_paddr, (uint64_t) region->region.memory_size); - /* Add to linked-list of memory regions. */ - list_add(&region->list, &vm->userspace_mem_regions); + /* Add to quick lookup data structures */ + vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); + vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region); + hash_add(vm->regions.slot_hash, &region->slot_node, slot); } /* @@ -817,10 +888,10 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + memslot) if (region->region.slot == memslot) return region; - } fprintf(stderr, "No mem region with the requested slot found,\n" " requested slot: %u\n", memslot); @@ -905,7 +976,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) */ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) { - __vm_mem_region_delete(vm, memslot2region(vm, slot)); + __vm_mem_region_delete(vm, memslot2region(vm, slot), true); } /* @@ -1177,16 +1248,14 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((gpa >= region->region.guest_phys_addr) - && (gpa <= (region->region.guest_phys_addr - + region->region.memory_size - 1))) - return (void *) ((uintptr_t) region->host_mem - + (gpa - region->region.guest_phys_addr)); + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) { + TEST_FAIL("No vm physical memory at 0x%lx", gpa); + return NULL; } - TEST_FAIL("No vm physical memory at 0x%lx", gpa); - return NULL; + return (void *)((uintptr_t)region->host_mem + + (gpa - region->region.guest_phys_addr)); } /* @@ -1208,15 +1277,22 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) */ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) { - struct userspace_mem_region *region; + struct rb_node *node; + + for (node = vm->regions.hva_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, hva_node); + + if (hva >= region->host_mem) { + if (hva <= (region->host_mem + + region->region.memory_size - 1)) + return (vm_paddr_t)((uintptr_t) + region->region.guest_phys_addr + + (hva - (uintptr_t)region->host_mem)); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((hva >= region->host_mem) - && (hva <= (region->host_mem - + region->region.memory_size - 1))) - return (vm_paddr_t) ((uintptr_t) - region->region.guest_phys_addr - + (hva - (uintptr_t) region->host_mem)); + node = node->rb_right; + } else + node = node->rb_left; } TEST_FAIL("No mapping to a guest physical address, hva: %p", hva); @@ -1822,6 +1898,7 @@ int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, */ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { + int ctr; struct userspace_mem_region *region; struct vcpu *vcpu; @@ -1829,7 +1906,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd); fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size); fprintf(stream, "%*sMem Regions:\n", indent, ""); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) { fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx " "host_virt: %p\n", indent + 2, "", (uint64_t) region->region.guest_phys_addr, diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 91ce1b5d480b..b30e8c7b119b 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -8,6 +8,9 @@ #ifndef SELFTEST_KVM_UTIL_INTERNAL_H #define SELFTEST_KVM_UTIL_INTERNAL_H +#include "linux/hashtable.h" +#include "linux/rbtree.h" + #include "sparsebit.h" struct userspace_mem_region { @@ -18,7 +21,9 @@ struct userspace_mem_region { void *host_mem; void *mmap_start; size_t mmap_size; - struct list_head list; + struct rb_node gpa_node; + struct rb_node hva_node; + struct hlist_node slot_node; }; struct vcpu { @@ -31,6 +36,12 @@ struct vcpu { uint32_t dirty_gfns_count; }; +struct userspace_mem_regions { + struct rb_root gpa_tree; + struct rb_root hva_tree; + DECLARE_HASHTABLE(slot_hash, 9); +}; + struct kvm_vm { int mode; unsigned long type; @@ -43,7 +54,7 @@ struct kvm_vm { unsigned int va_bits; uint64_t max_gfn; struct list_head vcpus; - struct list_head userspace_mem_regions; + struct userspace_mem_regions regions; struct sparsebit *vpages_valid; struct sparsebit *vpages_mapped; bool has_irqchip; diff --git a/tools/testing/selftests/kvm/lib/rbtree.c b/tools/testing/selftests/kvm/lib/rbtree.c new file mode 100644 index 000000000000..a703f0194ea3 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/rbtree.c @@ -0,0 +1 @@ +#include "../../../../lib/rbtree.c"

4 years, 1 month

1
1
0 0

[RFC PATCH v2 07/11] selftests/x86: Test Key Locker internal key maintenance

by Chang S. Bae

The test validates the internal key to be the same in all CPUs. It performs the validation again with the Suspend-To-RAM (ACPI S3) state. Signed-off-by: Chang S. Bae <chang.seok.bae(a)intel.com> Cc: linux-kernel(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org --- Changes from RFC v1: * Commented the binutils version number for ENCODEKEY128 (Peter Zijlstra) --- tools/testing/selftests/x86/Makefile | 2 +- tools/testing/selftests/x86/keylocker.c | 177 ++++++++++++++++++++++++ 2 files changed, 178 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/x86/keylocker.c diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 333980375bc7..09237cc84108 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -13,7 +13,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ test_vsyscall mov_ss_trap \ - syscall_arg_fault fsgsbase_restore + syscall_arg_fault fsgsbase_restore keylocker TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/keylocker.c b/tools/testing/selftests/x86/keylocker.c new file mode 100644 index 000000000000..78bbb7939b1a --- /dev/null +++ b/tools/testing/selftests/x86/keylocker.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * keylocker.c, validate the internal key management. + */ +#undef _GNU_SOURCE +#define _GNU_SOURCE 1 + +#include <stdio.h> +#include <stdbool.h> +#include <string.h> +#include <fcntl.h> +#include <err.h> +#include <sched.h> +#include <setjmp.h> +#include <signal.h> +#include <unistd.h> + +#define HANDLE_SIZE 48 + +static bool keylocker_disabled; + +/* Encode a 128-bit key to a 384-bit handle */ +static inline void __encode_key(char *handle) +{ + static const unsigned char aeskey[] = { 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, + 0x71, 0x77, 0x74, 0x69, 0x6f, 0x6b, 0x6c, 0x78 }; + + asm volatile ("movdqu %0, %%xmm0" : : "m" (*aeskey) :); + + /* Set no restriction to the handle */ + asm volatile ("mov $0, %%eax" :); + + /* ENCODEKEY128 %EAX (supported by binutils >= 2.36) */ + asm volatile (".byte 0xf3, 0xf, 0x38, 0xfa, 0xc0"); + + asm volatile ("movdqu %%xmm0, %0; movdqu %%xmm1, %1; movdqu %%xmm2, %2;" + : "=m" (handle[0]), "=m" (handle[0x10]), "=m" (handle[0x20])); +} + +static jmp_buf jmpbuf; + +static void handle_sigill(int sig, siginfo_t *si, void *ctx_void) +{ + keylocker_disabled = true; + siglongjmp(jmpbuf, 1); +} + +static bool encode_key(char *handle) +{ + bool success = true; + struct sigaction sa; + int ret; + + memset(&sa, 0, sizeof(sa)); + + /* Set signal handler */ + sa.sa_flags = SA_SIGINFO; + sa.sa_sigaction = handle_sigill; + sigemptyset(&sa.sa_mask); + ret = sigaction(SIGILL, &sa, 0); + if (ret) + err(1, "sigaction"); + + if (sigsetjmp(jmpbuf, 1)) + success = false; + else + __encode_key(handle); + + /* Clear signal handler */ + sa.sa_flags = 0; + sa.sa_sigaction = NULL; + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + ret = sigaction(SIGILL, &sa, 0); + if (ret) + err(1, "sigaction"); + + return success; +} + +/* + * Test if the internal key is the same in all the CPUs: + * + * Since the value is not readable, compare the encoded output of a AES key + * between CPUs. + */ + +static int nerrs; + +static unsigned char cpu0_handle[HANDLE_SIZE] = { 0 }; + +static void test_internal_key(bool slept, long cpus) +{ + int cpu, errs; + + printf("Test the internal key consistency between CPUs\n"); + + for (cpu = 0, errs = 0; cpu < cpus; cpu++) { + char handle[HANDLE_SIZE] = { 0 }; + cpu_set_t mask; + bool success; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + sched_setaffinity(0, sizeof(cpu_set_t), &mask); + + success = encode_key(handle); + if (!success) { + /* The encode should success after the S3 sleep */ + if (slept) + errs++; + printf("[%s]\tKey Locker disabled at CPU%d\n", + slept ? "FAIL" : "NOTE", cpu); + continue; + } + + if (cpu == 0 && !slept) { + /* Record the first handle value as reference */ + memcpy(cpu0_handle, handle, HANDLE_SIZE); + } else if (memcmp(cpu0_handle, handle, HANDLE_SIZE)) { + printf("[FAIL]\tMismatched internal key at CPU%d\n", + cpu); + errs++; + } + } + + if (errs == 0 && !keylocker_disabled) + printf("[OK]\tAll the internal keys are the same\n"); + else + nerrs += errs; +} + +static void switch_to_sleep(bool *slept) +{ + ssize_t bytes; + int fd; + + printf("Transition to Suspend-To-RAM state\n"); + + fd = open("/sys/power/mem_sleep", O_RDWR); + if (fd < 0) + err(1, "Open /sys/power/mem_sleep"); + + bytes = write(fd, "deep", strlen("deep")); + if (bytes != strlen("deep")) + err(1, "Write /sys/power/mem_sleep"); + close(fd); + + fd = open("/sys/power/state", O_RDWR); + if (fd < 0) + err(1, "Open /sys/power/state"); + + bytes = write(fd, "mem", strlen("mem")); + if (bytes != strlen("mem")) + err(1, "Write /sys/power/state"); + close(fd); + + printf("Wake up from Suspend-To-RAM state\n"); + *slept = true; +} + +int main(void) +{ + bool slept = false; + long cpus; + + cpus = sysconf(_SC_NPROCESSORS_ONLN); + printf("%ld CPUs in the system\n", cpus); + + test_internal_key(slept, cpus); + if (keylocker_disabled) + return nerrs ? 1 : 0; + + switch_to_sleep(&slept); + test_internal_key(slept, cpus); + return nerrs ? 1 : 0; +} -- 2.17.1

4 years, 1 month

1
0
0 0

[PATCH] selftests/bpf: only munmap the mmaped ringbuf pages

by Thadeu Lima de Souza Cascardo

One the mmap tests will map a single page, then try to extend the mapping by use of mremap, which should fail. Right after that, it unmaps the extended area, which may end up unmapping other valid mapped areas, this causing a segfault. Only unmap the area that is expected to be mapped. Fixes: b2fb299c9aa4 ("selftests/bpf: test ringbuf mmap read-only and read-write restrictions") Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo(a)canonical.com> --- tools/testing/selftests/bpf/prog_tests/ringbuf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index 197e30b83298..f9a8ae331963 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -146,7 +146,7 @@ void test_ringbuf(void) ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_WRITE), "write_protect"); ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_protect"); ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 3 * page_size, MREMAP_MAYMOVE), "ro_remap"); - ASSERT_OK(munmap(mmap_ptr, 3 * page_size), "unmap_ro"); + ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_ro"); /* only trigger BPF program for current process */ skel->bss->pid = getpid(); -- 2.30.2

4 years, 1 month

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror