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

[PATCH] selftests: cgroup: Add 'malloc' failures checks in test_memcontrol

by Ivan Orlov

There are several 'malloc' calls in test_memcontrol, which can be unsuccessful. This patch will add 'malloc' failures checking to give more details about test's fail reasons and avoid possible undefined behavior during the future null dereference (like the one in alloc_anon_50M_check_swap function). Signed-off-by: Ivan Orlov <ivan.orlov0322(a)gmail.com> --- tools/testing/selftests/cgroup/test_memcontrol.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index 1e616a8c6a9c..f4f7c0aef702 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -98,6 +98,11 @@ static int alloc_anon_50M_check(const char *cgroup, void *arg) int ret = -1; buf = malloc(size); + if (buf == NULL) { + fprintf(stderr, "malloc() failed\n"); + return -1; + } + for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE) *ptr = 0; @@ -211,6 +216,11 @@ static int alloc_anon_noexit(const char *cgroup, void *arg) char *buf, *ptr; buf = malloc(size); + if (buf == NULL) { + fprintf(stderr, "malloc() failed\n"); + return -1; + } + for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE) *ptr = 0; @@ -778,6 +788,11 @@ static int alloc_anon_50M_check_swap(const char *cgroup, void *arg) int ret = -1; buf = malloc(size); + if (buf == NULL) { + fprintf(stderr, "malloc() failed\n"); + return -1; + } + for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE) *ptr = 0; -- 2.34.1

2 years, 1 month

5
4
0 0

[PATCH v2] selftests: prctl: Add new prctl test for PR_SET_VMA action

by Ivan Orlov

This patch will add the new test, which covers the prctl call with PR_SET_VMA command. The test tries to give a name to the anonymous VMA within the process memory map, and then checks the result of the operation by parsing 'maps' virtual file. Additionally, the test tries to call the prctl PR_SET_VMA command with invalid arguments, and checks the error codes for correctness. At the moment anonymous VMA naming through prctl call functionality is not covered with any tests, so I think implementing it makes sense. In version 2 of this patch I consider the selftest Makefile rule about TARGETS entries order - I moved the 'prctl' entry in the Makefile to follow the lexicographic order. In version 1 it was placed at the end of the list. Signed-off-by: Ivan Orlov <ivan.orlov0322(a)gmail.com> --- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/prctl/.gitignore | 1 + tools/testing/selftests/prctl/Makefile | 2 +- tools/testing/selftests/prctl/config | 1 + .../selftests/prctl/set-anon-vma-name-test.c | 104 ++++++++++++++++++ 5 files changed, 108 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/prctl/config create mode 100644 tools/testing/selftests/prctl/set-anon-vma-name-test.c diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 13a6837a0c6b..97dcdaa656f6 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -58,6 +58,7 @@ TARGETS += nsfs TARGETS += pidfd TARGETS += pid_namespace TARGETS += powerpc +TARGETS += prctl TARGETS += proc TARGETS += pstore TARGETS += ptrace diff --git a/tools/testing/selftests/prctl/.gitignore b/tools/testing/selftests/prctl/.gitignore index 91af2b631bc9..7a657b25f686 100644 --- a/tools/testing/selftests/prctl/.gitignore +++ b/tools/testing/selftests/prctl/.gitignore @@ -2,3 +2,4 @@ disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test disable-tsc-test +set-anon-vma-name-test diff --git a/tools/testing/selftests/prctl/Makefile b/tools/testing/selftests/prctl/Makefile index c7923b205222..c058b81eeb41 100644 --- a/tools/testing/selftests/prctl/Makefile +++ b/tools/testing/selftests/prctl/Makefile @@ -5,7 +5,7 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) ifeq ($(ARCH),x86) TEST_PROGS := disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test \ - disable-tsc-test + disable-tsc-test set-anon-vma-name-test all: $(TEST_PROGS) include ../lib.mk diff --git a/tools/testing/selftests/prctl/config b/tools/testing/selftests/prctl/config new file mode 100644 index 000000000000..c6ed03c544e5 --- /dev/null +++ b/tools/testing/selftests/prctl/config @@ -0,0 +1 @@ +CONFIG_ANON_VMA_NAME=y diff --git a/tools/testing/selftests/prctl/set-anon-vma-name-test.c b/tools/testing/selftests/prctl/set-anon-vma-name-test.c new file mode 100644 index 000000000000..26d853c5a0c1 --- /dev/null +++ b/tools/testing/selftests/prctl/set-anon-vma-name-test.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This test covers the anonymous VMA naming functionality through prctl calls + */ + +#include <errno.h> +#include <sys/prctl.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <string.h> + +#include "../kselftest_harness.h" + +#define AREA_SIZE 1024 + +#define GOOD_NAME "goodname" +#define BAD_NAME "badname\1" + +#ifndef PR_SET_VMA +#define PR_SET_VMA 0x53564d41 +#define PR_SET_VMA_ANON_NAME 0 +#endif + + +int rename_vma(unsigned long addr, unsigned long size, char *name) +{ + int res; + + res = prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, addr, size, name); + if (res < 0) + return -errno; + return res; +} + +int was_renaming_successful(char *target_name, unsigned long ptr) +{ + FILE *maps_file; + + char line_buf[512], name[128], mode[8]; + unsigned long start_addr, end_addr, offset; + unsigned int major_id, minor_id, node_id; + + char target_buf[128]; + int res = 0, sscanf_res; + + // The entry name in maps will be in format [anon:<target_name>] + sprintf(target_buf, "[anon:%s]", target_name); + maps_file = fopen("/proc/self/maps", "r"); + if (!maps_file) { + printf("## /proc/self/maps file opening error\n"); + return 0; + } + + // Parse the maps file to find the entry we renamed + while (fgets(line_buf, sizeof(line_buf), maps_file)) { + sscanf_res = sscanf(line_buf, "%lx-%lx %7s %lx %u:%u %u %s", &start_addr, + &end_addr, mode, &offset, &major_id, + &minor_id, &node_id, name); + if (sscanf_res == EOF) { + res = 0; + printf("## EOF while parsing the maps file\n"); + break; + } + if (!strcmp(name, target_buf) && start_addr == ptr) { + res = 1; + break; + } + } + fclose(maps_file); + return res; +} + +FIXTURE(vma) { + void *ptr_anon, *ptr_not_anon; +}; + +FIXTURE_SETUP(vma) { + self->ptr_anon = mmap(NULL, AREA_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); + ASSERT_NE(self->ptr_anon, NULL); + self->ptr_not_anon = mmap(NULL, AREA_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE, 0, 0); + ASSERT_NE(self->ptr_not_anon, NULL); +} + +FIXTURE_TEARDOWN(vma) { + munmap(self->ptr_anon, AREA_SIZE); + munmap(self->ptr_not_anon, AREA_SIZE); +} + +TEST_F(vma, renaming) { + TH_LOG("Try to rename the VMA with correct parameters"); + EXPECT_GE(rename_vma((unsigned long)self->ptr_anon, AREA_SIZE, GOOD_NAME), 0); + EXPECT_TRUE(was_renaming_successful(GOOD_NAME, (unsigned long)self->ptr_anon)); + + TH_LOG("Try to pass invalid name (with non-printable character \\1) to rename the VMA"); + EXPECT_EQ(rename_vma((unsigned long)self->ptr_anon, AREA_SIZE, BAD_NAME), -EINVAL); + + TH_LOG("Try to rename non-anonynous VMA"); + EXPECT_EQ(rename_vma((unsigned long) self->ptr_not_anon, AREA_SIZE, GOOD_NAME), -EINVAL); +} + +TEST_HARNESS_MAIN -- 2.34.1

2 years, 1 month

2
1
0 0

[PATCH v2] selftests: sched: Add more core schedule prctl calls

by Ivan Orlov

The core sched kselftest makes prctl calls only with correct parameters. This patch will extend this test with more core schedule prctl calls with wrong parameters to increase code coverage. Signed-off-by: Ivan Orlov <ivan.orlov0322(a)gmail.com> --- V1 -> V2: Unnecessary printing removed - 'validate' will automatically print the message in case or error tools/testing/selftests/sched/cs_prctl_test.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c index 25e0d95d3713..3e1619b6bf2d 100644 --- a/tools/testing/selftests/sched/cs_prctl_test.c +++ b/tools/testing/selftests/sched/cs_prctl_test.c @@ -334,6 +334,12 @@ int main(int argc, char *argv[]) validate(get_cs_cookie(pid) != 0); validate(get_cs_cookie(pid) == get_cs_cookie(procs[pidx].thr_tids[0])); + validate(_prctl(PR_SCHED_CORE, PR_SCHED_CORE_MAX, 0, PIDTYPE_PGID, 0) < 0 + && errno == EINVAL); + + validate(_prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_TO, 0, PIDTYPE_PGID, 1) < 0 + && errno == EINVAL); + if (errors) { printf("TESTS FAILED. errors: %d\n", errors); res = 10; -- 2.34.1

2 years, 1 month

2
1
0 0

[PATCH] tools/nolibc: tests: use volatile to force stack smashing

by Thomas Weißschuh

Use a volatile pointer to write outside the buffer so the compiler can't optimize it away. Reported-by: Alexey Dobriyan <adobriyan(a)gmail.com> Link: https://lore.kernel.org/lkml/c0584807-511c-4496-b062-1263ea38f349@p183/ Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- This is based on the "dev" branch of the rcu tree. --- tools/testing/selftests/nolibc/nolibc-test.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 21bacc928bf7..47013b78972e 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -667,17 +667,13 @@ int run_stdlib(int min, int max) return ret; } -#if defined(__clang__) -__attribute__((optnone)) -#elif defined(__GNUC__) -__attribute__((optimize("O0"))) -#endif static int smash_stack(void) { char buf[100]; + volatile char *ptr = buf; for (size_t i = 0; i < 200; i++) - buf[i] = 'P'; + ptr[i] = 'P'; return 1; } --- base-commit: 6e7cac3d5b8c77ddedfaa7efad23aa542cde53b2 change-id: 20230328-nolibc-smash-stack-volatile-0e87e9273fea Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

2 years, 1 month

1
0
0 0

new kunit infrastructure

by Johannes Berg

Hi all, Is there an established process for new kunit infrastructure? For example, we have this macro that makes KUNIT_ARRAY_PARAM easier by letting you just declare an array of test cases: /* Similar to KUNIT_ARRAY_PARAM, but avoiding an extra function */ #define KUNIT_ARRAY_PARAM_DESC(name, array, desc_member) \ static const void *name##_gen_params(const void *prev, char *desc) \ { \ typeof((array)[0]) *__next = prev ? ((typeof(__next)) prev) + 1 : (array); \ if (__next - (array) < ARRAY_SIZE((array))) { \ strscpy(desc, __next->desc_member, KUNIT_PARAM_DESC_SIZE); \ return __next; \ } \ return NULL; \ } Also, since we're working on wifi and thus networking, we want e.g. SKBs to be resource-managed, and added some helper macros/functions for using kunit_alloc_resource() with SKBs, that will be used at least in cfg80211 and mac80211 soon, so it would seem appropriate to have include/kunit/skb.h (and a corresponding C file somewhere) with these helpers. Is all of this just a case of "nobody needed it so far", or is there no expectation to add such infrastructure more generally? johannes

2 years, 1 month

2
3
0 0

[PATCH bpf-next] selftests/bpf: Remove two infinite loop bound check cases

by Xu Kuohai

From: Xu Kuohai <xukuohai(a)huawei.com> The two infinite loop bound check cases added by commit 1a3148fc171f ("selftests/bpf: Check when bounds are not in the 32-bit range") take a long time to execute but don't add much value. Remove them to reduce run time of test_verifier. Fixes: 1a3148fc171f ("selftests/bpf: Check when bounds are not in the 32-bit range") Signed-off-by: Xu Kuohai <xukuohai(a)huawei.com> --- tools/testing/selftests/bpf/verifier/bounds.c | 50 ------------------- 1 file changed, 50 deletions(-) diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index 74b1917d4208..515a8222f08f 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -777,31 +777,6 @@ .result = ACCEPT, .prog_type = BPF_PROG_TYPE_XDP, }, -{ - "bound check with JMP_JSLT for crossing 64-bit signed boundary", - .insns = { - BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), - BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), - BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1), - BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 8), - - BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_2, 0), - BPF_LD_IMM64(BPF_REG_0, 0x7fffffffffffff10), - BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), - - BPF_LD_IMM64(BPF_REG_0, 0x8000000000000000), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), - /* r1 signed range is [S64_MIN, S64_MAX] */ - BPF_JMP_REG(BPF_JSLT, BPF_REG_0, BPF_REG_1, -2), - - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }, - .errstr = "BPF program is too large", - .result = REJECT, - .prog_type = BPF_PROG_TYPE_XDP, -}, { "bound check for loop upper bound greater than U32_MAX", .insns = { @@ -849,28 +824,3 @@ .result = ACCEPT, .prog_type = BPF_PROG_TYPE_XDP, }, -{ - "bound check with JMP32_JSLT for crossing 32-bit signed boundary", - .insns = { - BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), - BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), - BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1), - BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 6), - - BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_2, 0), - BPF_MOV32_IMM(BPF_REG_0, 0x7fffff10), - BPF_ALU32_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), - - BPF_MOV32_IMM(BPF_REG_0, 0x80000000), - BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, 1), - /* r1 signed range is [S32_MIN, S32_MAX] */ - BPF_JMP32_REG(BPF_JSLT, BPF_REG_0, BPF_REG_1, -2), - - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }, - .errstr = "BPF program is too large", - .result = REJECT, - .prog_type = BPF_PROG_TYPE_XDP, -}, -- 2.30.2

2 years, 1 month

2
4
0 0

Słowa kluczowe do wypozycjonowania

by Adam Charachuta

Dzień dobry, zapoznałem się z Państwa ofertą i z przyjemnością przyznaję, że przyciąga uwagę i zachęca do dalszych rozmów. Pomyślałem, że może mógłbym mieć swój wkład w Państwa rozwój i pomóc dotrzeć z tą ofertą do większego grona odbiorców. Pozycjonuję strony www, dzięki czemu generują świetny ruch w sieci. Możemy porozmawiać w najbliższym czasie? Pozdrawiam Adam Charachuta

2 years, 1 month

1
0
0 0

[PATCH] selftests/ftrace: Improve integration with kselftest runner

by Mark Brown

The ftrace selftests do not currently produce KTAP output, they produce a custom format much nicer for human consumption. This means that when run in automated test systems we just get a single result for the suite as a whole rather than recording results for individual test cases, making it harder to look at the test data and masking things like inappropriate skips. Address this by adding support for KTAP output to the ftracetest script and providing a trivial wrapper which will be invoked by the kselftest runner to generate output in this format by default, users using ftracetest directly will continue to get the existing output. This is not the most elegant solution but it is simple and effective. I did consider implementing this by post processing the existing output format but that felt more complex and likely to result in all output being lost if something goes seriously wrong during the run which would not be helpful. I did also consider just writing a separate runner script but there's enough going on with things like the signal handling for that to seem like it would be duplicating too much. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/ftrace/Makefile | 3 +- tools/testing/selftests/ftrace/ftracetest | 63 ++++++++++++++++++++++++-- tools/testing/selftests/ftrace/ftracetest-ktap | 8 ++++ 3 files changed, 70 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index d6e106fbce11..a1e955d2de4c 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 all: -TEST_PROGS := ftracetest +TEST_PROGS_EXTENDED := ftracetest +TEST_PROGS := ftracetest-ktap TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index c3311c8c4089..539c8d6d5d71 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -13,6 +13,7 @@ echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" echo " Options:" echo " -h|--help Show help message" echo " -k|--keep Keep passed test logs" +echo " -K|--KTAP Output in KTAP format" echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" @@ -85,6 +86,10 @@ parse_opts() { # opts KEEP_LOG=1 shift 1 ;; + --ktap|-K) + KTAP=1 + shift 1 + ;; --verbose|-v|-vv|-vvv) if [ $VERBOSE -eq -1 ]; then usage "--console can not use with --verbose" @@ -178,6 +183,7 @@ TEST_DIR=$TOP_DIR/test.d TEST_CASES=`find_testcases $TEST_DIR` LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/ KEEP_LOG=0 +KTAP=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 @@ -229,7 +235,7 @@ prlog() { # messages newline= shift fi - printf "$*$newline" + [ "$KTAP" != "1" ] && printf "$*$newline" [ "$LOG_FILE" ] && printf "$*$newline" | strip_esc >> $LOG_FILE } catlog() { #file @@ -260,11 +266,11 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 +CASENAME= testcase() { # testfile CASENO=$((CASENO+1)) - desc=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` - prlog -n "[$CASENO]$INSTANCE$desc" + CASENAME=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` } checkreq() { # testfile @@ -277,40 +283,68 @@ test_on_instance() { # testfile grep -q "^#[ \t]*flags:.*instance" $1 } +ktaptest() { # result comment + if [ "$KTAP" != "1" ]; then + return + fi + + local result= + if [ "$1" = "1" ]; then + result="ok" + else + result="not ok" + fi + shift + + local comment=$* + if [ "$comment" != "" ]; then + comment="# $comment" + fi + + echo $CASENO $result $INSTANCE$CASENAME $comment +} + eval_result() { # sigval case $1 in $PASS) prlog " [${color_green}PASS${color_reset}]" + ktaptest 1 PASSED_CASES="$PASSED_CASES $CASENO" return 0 ;; $FAIL) prlog " [${color_red}FAIL${color_reset}]" + ktaptest 0 FAILED_CASES="$FAILED_CASES $CASENO" return 1 # this is a bug. ;; $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" + ktaptest 0 UNRESOLVED UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" + ktaptest 1 SKIP UNTESTED_CASES="$UNTESTED_CASES $CASENO" return 0 ;; $UNSUPPORTED) prlog " [${color_blue}UNSUPPORTED${color_reset}]" + ktaptest 1 SKIP UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO" return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) prlog " [${color_green}XFAIL${color_reset}]" + ktaptest 1 XFAIL XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; *) prlog " [${color_blue}UNDEFINED${color_reset}]" + ktaptest 0 error UNDEFINED_CASES="$UNDEFINED_CASES $CASENO" return 1 # this must be a test bug ;; @@ -371,6 +405,7 @@ __run_test() { # testfile run_test() { # testfile local testname=`basename $1` testcase $1 + prlog -n "[$CASENO]$INSTANCE$CASENAME" if [ ! -z "$LOG_FILE" ] ; then local testlog=`mktemp $LOG_DIR/${CASENO}-${testname}-log.XXXXXX` else @@ -405,6 +440,17 @@ run_test() { # testfile # load in the helper functions . $TEST_DIR/functions +if [ "$KTAP" = "1" ]; then + echo "TAP version 13" + + casecount=`echo $TEST_CASES | wc -w` + for t in $TEST_CASES; do + test_on_instance $t || continue + casecount=$((casecount+1)) + done + echo "1..${casecount}" +fi + # Main loop for t in $TEST_CASES; do run_test $t @@ -439,6 +485,17 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +if [ "$KTAP" = "1" ]; then + echo -n "# Totals:" + echo -n " pass:"`echo $PASSED_CASES | wc -w` + echo -n " faii:"`echo $FAILED_CASES | wc -w` + echo -n " xfail:"`echo $XFAILED_CASES | wc -w` + echo -n " xpass:0" + echo -n " skip:"`echo $UNTESTED_CASES $UNSUPPORTED_CASES | wc -w` + echo -n " error:"`echo $UNRESOLVED_CASES $UNDEFINED_CASES | wc -w` + echo +fi + cleanup # if no error, return 0 diff --git a/tools/testing/selftests/ftrace/ftracetest-ktap b/tools/testing/selftests/ftrace/ftracetest-ktap new file mode 100755 index 000000000000..b3284679ef3a --- /dev/null +++ b/tools/testing/selftests/ftrace/ftracetest-ktap @@ -0,0 +1,8 @@ +#!/bin/sh -e +# SPDX-License-Identifier: GPL-2.0-only +# +# ftracetest-ktap: Wrapper to integrate ftracetest with the kselftest runner +# +# Copyright (C) Arm Ltd., 2023 + +./ftracetest -K --- base-commit: fe15c26ee26efa11741a7b632e9f23b01aca4cc6 change-id: 20230302-ftrace-kselftest-ktap-9d7878691557 Best regards, -- Mark Brown <broonie(a)kernel.org>

2 years, 1 month

4
4
0 0

[PATCH] selftests: sched: Add more core schedule prctl calls

by Ivan Orlov

The core sched kselftest makes prctl calls only with correct parameters. This patch will extend this test with more core schedule prctl calls with wrong parameters to increase code coverage. Signed-off-by: Ivan Orlov <ivan.orlov0322(a)gmail.com> --- tools/testing/selftests/sched/cs_prctl_test.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c index 25e0d95d3713..df8e4629b3b5 100644 --- a/tools/testing/selftests/sched/cs_prctl_test.c +++ b/tools/testing/selftests/sched/cs_prctl_test.c @@ -334,6 +334,14 @@ int main(int argc, char *argv[]) validate(get_cs_cookie(pid) != 0); validate(get_cs_cookie(pid) == get_cs_cookie(procs[pidx].thr_tids[0])); + printf("\n## Try to pass wrong subcommand PR_SCHED_CORE_MAX = %d to prctl (shouldn't succeed)\n", PR_SCHED_CORE_MAX); + validate(_prctl(PR_SCHED_CORE, PR_SCHED_CORE_MAX, 0, PIDTYPE_PGID, 0) < 0 + && errno == EINVAL); + + printf("\n## Try to pass not-null uaddr with forbidden command (shouldn't succeed)\n"); + validate(_prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_TO, 0, PIDTYPE_PGID, 1) < 0 + && errno == EINVAL); + if (errors) { printf("TESTS FAILED. errors: %d\n", errors); res = 10; -- 2.34.1

2 years, 1 month

2
1
0 0

[PATCH rcu v2 0/7] RCU-related lockdep changes for v6.4

by Boqun Feng

Hi, Another week, another version ;-) Previous versions: v1: https://lore.kernel.org/rcu/20230317031339.10277-1-boqun.feng@gmail.com/ Changes since v1: * Minor typo fixes * Apply Acked-by tags * Add license and copyright headers for srcu_lockdep.sh Thank you all for helping improve this! You can also find this series at https://github/fbq/linux rcu/lockdep.2023.03.22a top commit is: 450ef54e199f List of changes: Boqun Feng (4): locking/lockdep: Introduce lock_sync() rcu: Annotate SRCU's update-side lockdep dependencies locking: Reduce the number of locks in ww_mutex stress tests locking/lockdep: Improve the deadlock scenario print for sync and read lock Paul E. McKenney (3): rcutorture: Add SRCU deadlock scenarios rcutorture: Add RCU Tasks Trace and SRCU deadlock scenarios rcutorture: Add srcu_lockdep.sh include/linux/lockdep.h | 8 +- include/linux/srcu.h | 34 +++- kernel/locking/lockdep.c | 64 +++++- kernel/locking/test-ww_mutex.c | 2 +- kernel/rcu/rcutorture.c | 185 ++++++++++++++++++ kernel/rcu/srcutiny.c | 2 + kernel/rcu/srcutree.c | 2 + .../selftests/rcutorture/bin/srcu_lockdep.sh | 78 ++++++++ 8 files changed, 364 insertions(+), 11 deletions(-) create mode 100755 tools/testing/selftests/rcutorture/bin/srcu_lockdep.sh -- 2.38.1

2 years, 1 month

2
8
0 0

[PATCH 0/5] usermode_driver: Add management library and API

by Roberto Sassu

From: Roberto Sassu <roberto.sassu(a)huawei.com> A User Mode Driver (UMD) is a specialization of a User Mode Helper (UMH), which runs a user space process from a binary blob, and creates a bidirectional pipe, so that the kernel can make a request to that process, and the latter provides its response. It is currently used by bpfilter, although it does not seem to do any useful work. The problem is, if other users would like to implement a UMD similar to bpfilter, they would have to duplicate the code. Instead, make an UMD management library and API from the existing bpfilter and sockopt code, and move it to common kernel code. Also, define the software architecture and the main components of the library: the UMD Manager, running in the kernel, acting as the frontend interface to any user or kernel-originated request; the UMD Loader, also running in the kernel, responsible to load the UMD Handler; the UMD Handler, running in user space, responsible to handle requests from the UMD Manager and to send to it the response. I have two use cases, but for sake of brevity I will propose one. I would like to add support for PGP keys and signatures in the kernel, so that I can extend secure boot to applications, and allow/deny code execution based on the signed file digests included in RPM headers. While I proposed a patch set a while ago (based on a previous work of David Howells), the main objection was that the PGP packet parser should not run in the kernel. That makes a perfect example for using a UMD. If the PGP parser is moved to user space (UMD Handler), and the kernel (UMD Manager) just instantiates the key and verifies the signature on already parsed data, this would address the concern. Patch 1 moves the function bpfilter_send_req() to usermode_driver.c and makes the pipe between the kernel and the user space process suitable for larger quantity of data (> 64K). Patch 2 introduces the management library and API. Patch 3 replaces the existing bpfilter and sockopt code with calls to the management API. To use the new mechanism, sockopt itself (acts as UMD Manager) now sends/receives messages to/from bpfilter_umh (acts as UMD Handler), instead of bpfilter (acts as UMD Loader). Patch 4 introduces a sample UMD, useful for other implementors, and uses it for testing. Patch 5 introduces the documentation of the new management library and API. Roberto Sassu (5): usermode_driver: Introduce umd_send_recv() from bpfilter usermode_driver_mgmt: Introduce management of user mode drivers bpfilter: Port to user mode driver management API selftests/umd_mgmt: Add selftests for UMD management library doc: Add documentation for the User Mode Driver management library Documentation/driver-api/index.rst | 1 + Documentation/driver-api/umd_mgmt.rst | 99 +++++++++++++ MAINTAINERS | 9 ++ include/linux/bpfilter.h | 12 +- include/linux/usermode_driver.h | 2 + include/linux/usermode_driver_mgmt.h | 35 +++++ kernel/Makefile | 2 +- kernel/usermode_driver.c | 47 +++++- kernel/usermode_driver_mgmt.c | 137 ++++++++++++++++++ net/bpfilter/bpfilter_kern.c | 120 +-------------- net/ipv4/bpfilter/sockopt.c | 67 +++++---- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/umd_mgmt/.gitignore | 1 + tools/testing/selftests/umd_mgmt/Makefile | 14 ++ tools/testing/selftests/umd_mgmt/config | 1 + .../selftests/umd_mgmt/sample_umd/Makefile | 22 +++ .../selftests/umd_mgmt/sample_umd/msgfmt.h | 13 ++ .../umd_mgmt/sample_umd/sample_binary_blob.S | 7 + .../umd_mgmt/sample_umd/sample_handler.c | 81 +++++++++++ .../umd_mgmt/sample_umd/sample_loader.c | 28 ++++ .../umd_mgmt/sample_umd/sample_mgr.c | 124 ++++++++++++++++ tools/testing/selftests/umd_mgmt/umd_mgmt.sh | 40 +++++ 22 files changed, 707 insertions(+), 156 deletions(-) create mode 100644 Documentation/driver-api/umd_mgmt.rst create mode 100644 include/linux/usermode_driver_mgmt.h create mode 100644 kernel/usermode_driver_mgmt.c create mode 100644 tools/testing/selftests/umd_mgmt/.gitignore create mode 100644 tools/testing/selftests/umd_mgmt/Makefile create mode 100644 tools/testing/selftests/umd_mgmt/config create mode 100644 tools/testing/selftests/umd_mgmt/sample_umd/Makefile create mode 100644 tools/testing/selftests/umd_mgmt/sample_umd/msgfmt.h create mode 100644 tools/testing/selftests/umd_mgmt/sample_umd/sample_binary_blob.S create mode 100644 tools/testing/selftests/umd_mgmt/sample_umd/sample_handler.c create mode 100644 tools/testing/selftests/umd_mgmt/sample_umd/sample_loader.c create mode 100644 tools/testing/selftests/umd_mgmt/sample_umd/sample_mgr.c create mode 100755 tools/testing/selftests/umd_mgmt/umd_mgmt.sh -- 2.25.1

2 years, 1 month

3
12
0 0

Re: [PATCH] selftests: cgroup: Fix exception handling in test_memcg_oom_group_score_events()

by David Vernet

On Mon, Mar 27, 2023 at 07:56:03AM +0200, Markus Elfring wrote: > >> 2. Can a cg_destroy() call ever work as expected if a cg_create() call failed? > > > > Perhaps next time you can answer your own question by spending 30 > > seconds actually reading the code you're "fixing": > > > > int cg_destroy(const char *cgroup) > > { > … > > ret = rmdir(cgroup); > … > > if (ret && errno == ENOENT) <<< that case is explicitly handled here > > ret = 0; > > > > return ret; > > } > > Is it interesting somehow that a non-existing directory (which would occasionally > not be found) is tolerated so far? > https://elixir.bootlin.com/linux/v6.3-rc3/source/tools/testing/selftests/cg… > > Should such a function call be avoided because of a failed cg_create() call? The point is that (a) you were wrong that this is fixing anything, and (b) this patch is functionally useless. Sure, we could move some goto's around and subjectively improve "something". Why? What's the point? It's highly debatable that what you're doing is even an improvement, and I'm not interested in wasting time pontificating about the merits of a trivial "fix" for a test cleanup function that isn't even broken. Several people have already either advised or directly asked you to stop sending these patches. I'm not sure why you're choosing to ignore them, but I'll throw my hat in the ring regardless and do the same. Please stop sending these fake cleanup patches.

2 years, 1 month

1
0
0 0

[PATCH net-next] selftests: tls: add a test for queuing data before setting the ULP

by Jakub Kicinski

Other tests set up the connection fully on both ends before communicating any data. Add a test which will queue up TLS records to TCP before the TLS ULP is installed. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/tls.c | 45 +++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 2cbb12736596..e699548d4247 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1820,4 +1820,49 @@ TEST(tls_v6ops) { close(sfd); } +TEST(prequeue) { + struct tls_crypto_info_keys tls12; + char buf[20000], buf2[20000]; + struct sockaddr_in addr; + int sfd, cfd, ret, fd; + socklen_t len; + + len = sizeof(addr); + memrnd(buf, sizeof(buf)); + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls12); + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ASSERT_EQ(bind(sfd, &addr, sizeof(addr)), 0); + ASSERT_EQ(listen(sfd, 10), 0); + ASSERT_EQ(getsockname(sfd, &addr, &len), 0); + ASSERT_EQ(connect(fd, &addr, sizeof(addr)), 0); + ASSERT_GE(cfd = accept(sfd, &addr, &len), 0); + close(sfd); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret) { + ASSERT_EQ(errno, ENOENT); + SKIP(return, "no TLS support"); + } + + ASSERT_EQ(setsockopt(fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + EXPECT_EQ(send(fd, buf, sizeof(buf), MSG_DONTWAIT), sizeof(buf)); + + ASSERT_EQ(setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")), 0); + ASSERT_EQ(setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + EXPECT_EQ(recv(cfd, buf2, sizeof(buf2), MSG_WAITALL), sizeof(buf2)); + + EXPECT_EQ(memcmp(buf, buf2, sizeof(buf)), 0); + + close(fd); + close(cfd); +} + TEST_HARNESS_MAIN -- 2.39.2

2 years, 1 month

2
1
0 0

[KTAP V2 PATCH] ktap_v2: add skip test result

by Rae Moar

Add the test result "skip" to KTAP version 2 as an alternative way to indicate a test was skipped. The current spec uses the "#SKIP" directive to indicate that a test was skipped. However, the "#SKIP" directive is not always evident when quickly skimming through KTAP results. The "skip" result would provide an alternative that could make it clearer that a test has not successfully passed because it was skipped. Before: KTAP version 1 1..1 KTAP version 1 1..2 ok 1 case_1 ok 2 case_2 #SKIP ok 1 suite After: KTAP version 2 1..1 KTAP version 2 1..2 ok 1 case_1 skip 2 case_2 ok 1 suite Here is a link to a version of the KUnit parser that is able to parse the skip test result for KTAP version 2. Note this parser is still able to parse the "#SKIP" directive. Link: https://kunit-review.googlesource.com/c/linux/+/5689 Signed-off-by: Rae Moar <rmoar(a)google.com> --- Note: this patch is based on Frank's ktap_spec_version_2 branch. Documentation/dev-tools/ktap.rst | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/Documentation/dev-tools/ktap.rst b/Documentation/dev-tools/ktap.rst index ff77f4aaa6ef..f48aa00db8f0 100644 --- a/Documentation/dev-tools/ktap.rst +++ b/Documentation/dev-tools/ktap.rst @@ -74,7 +74,8 @@ They are required and must have the format: <result> <number> [<description>][ # [<directive>] [<diagnostic data>]] The result can be either "ok", which indicates the test case passed, -or "not ok", which indicates that the test case failed. +"not ok", which indicates that the test case failed, or "skip", which indicates +the test case did not run. <number> represents the number of the test being performed. The first test must have the number 1 and the number then must increase by 1 for each additional @@ -91,12 +92,13 @@ A directive is a keyword that indicates a different outcome for a test other than passed and failed. The directive is optional, and consists of a single keyword preceding the diagnostic data. In the event that a parser encounters a directive it doesn't support, it should fall back to the "ok" / "not ok" -result. +/ "skip" result. Currently accepted directives are: -- "SKIP", which indicates a test was skipped (note the result of the test case - result line can be either "ok" or "not ok" if the SKIP directive is used) +- "SKIP", which indicates a test was skipped (note this is an alternative to + the "skip" result type and if the SKIP directive is used, the + result can be any type - "ok", "not ok", or "skip") - "TODO", which indicates that a test is not expected to pass at the moment, e.g. because the feature it is testing is known to be broken. While this directive is inherited from TAP, its use in the kernel is discouraged. @@ -110,7 +112,7 @@ Currently accepted directives are: The diagnostic data is a plain-text field which contains any additional details about why this result was produced. This is typically an error message for ERROR -or failed tests, or a description of missing dependencies for a SKIP result. +or failed tests, or a description of missing dependencies for a skipped test. The diagnostic data field is optional, and results which have neither a directive nor any diagnostic data do not need to include the "#" field @@ -130,11 +132,18 @@ The test "test_case_name" failed. :: - ok 1 test # SKIP necessary dependency unavailable + skip 1 test # necessary dependency unavailable -The test "test" was SKIPPED with the diagnostic message "necessary dependency +The test "test" was skipped with the diagnostic message "necessary dependency unavailable". +:: + + ok 1 test_2 # SKIP this test should not run + +The test "test_2" was skipped with the diagnostic message "this test +should not run". + :: not ok 1 test # TIMEOUT 30 seconds @@ -225,7 +234,7 @@ An example format with multiple levels of nested testing: not ok 1 test_1 ok 2 test_2 not ok 1 test_3 - ok 2 test_4 # SKIP + skip 2 test_4 not ok 1 example_test_1 ok 2 example_test_2 @@ -262,7 +271,7 @@ Example KTAP output ok 1 example_test_1 KTAP version 2 1..2 - ok 1 test_1 # SKIP test_1 skipped + skip 1 test_1 # test_1 skipped ok 2 test_2 ok 2 example_test_2 KTAP version 2 base-commit: 906f02e42adfbd5ae70d328ee71656ecb602aaf5 -- 2.40.0.rc1.284.g88254d51c5-goog

2 years, 1 month

5
14
0 0

Re: [PATCH] selftests: cgroup: Fix exception handling in test_memcg_oom_group_score_events()

by David Vernet

On Sun, Mar 26, 2023 at 10:15:31AM +0200, Markus Elfring wrote: [...] > >> > >> Fixes: a987785dcd6c8ae2915460582aebd6481c81eb67 ("Add tests for memory.oom.group") > > > > Fixes what in the what now? > > 1. Check repetition (which can be undesirable) > > 2. Can a cg_destroy() call ever work as expected if a cg_create() call failed? Perhaps next time you can answer your own question by spending 30 seconds actually reading the code you're "fixing": int cg_destroy(const char *cgroup) { int ret; retry: ret = rmdir(cgroup); if (ret && errno == EBUSY) { cg_killall(cgroup); usleep(100); goto retry; } if (ret && errno == ENOENT) <<< that case is explicitly handled here ret = 0; return ret; }

2 years, 1 month

1
0
0 0

[PATCH 0/5] cgroup/cpuset: Miscellaneous updates

by Waiman Long

This patch series includes miscellaneous update to the cpuset and its testing code. Patch 2 is actually a follow-up of commit 3fb906e7fabb ("cgroup/cpuset: Don't filter offline CPUs in cpuset_cpus_allowed() for top cpuset tasks"). Patches 3-4 are for handling corner cases when dealing with task_cpu_possible_mask(). Waiman Long (5): cgroup/cpuset: Skip task update if hotplug doesn't affect current cpuset cgroup/cpuset: Include offline CPUs when tasks' cpumasks in top_cpuset are updated cgroup/cpuset: Find another usable CPU if none found in current cpuset cgroup/cpuset: Add CONFIG_DEBUG_CPUSETS config for cpuset testing cgroup/cpuset: Minor updates to test_cpuset_prs.sh init/Kconfig | 5 + kernel/cgroup/cpuset.c | 155 +++++++++++++++++- .../selftests/cgroup/test_cpuset_prs.sh | 25 +-- 3 files changed, 165 insertions(+), 20 deletions(-) -- 2.31.1

2 years, 1 month

4
22
0 0

Re: [PATCH] selftests: cgroup: Fix exception handling in test_memcg_oom_group_score_events()

by Lorenzo Stoakes

On Sat, Mar 25, 2023 at 07:30:21PM +0100, Markus Elfring wrote: > Date: Sat, 25 Mar 2023 19:11:13 +0100 > > The label “cleanup” was used to jump to another pointer check despite of > the detail in the implementation of the function > “test_memcg_oom_group_score_events” that it was determined already > that a corresponding variable contained a null pointer. This is poorly writte and confusing. Something like 'avoid unnecessary null check/cg_destroy() invocation' would be far clearer. > > 1. Thus return directly after a call of the function “cg_name” failed. > This feels superfluious. > 2. Use an additional label. This also feels superfluious. > > 3. Delete a questionable check. This seems superfluois and frankly, rude. It's not questionable, it's readable, you should try to avoid language like 'questionable' when the purpose of the check is obvious. > > > This issue was detected by using the Coccinelle software. > > Fixes: a987785dcd6c8ae2915460582aebd6481c81eb67 ("Add tests for memory.oom.group") Fixes what in the what now? This is not a bug fix, it's a 'questionable' refactoring. > Signed-off-by: Markus Elfring <elfring(a)users.sourceforge.net> > --- > tools/testing/selftests/cgroup/test_memcontrol.c | 9 ++++----- > 1 file changed, 4 insertions(+), 5 deletions(-) > > diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c > index f4f7c0aef702..afcd1752413e 100644 > --- a/tools/testing/selftests/cgroup/test_memcontrol.c > +++ b/tools/testing/selftests/cgroup/test_memcontrol.c > @@ -1242,12 +1242,11 @@ static int test_memcg_oom_group_score_events(const char *root) > int safe_pid; > > memcg = cg_name(root, "memcg_test_0"); > - > if (!memcg) > - goto cleanup; > + return ret; > > if (cg_create(memcg)) > - goto cleanup; > + goto free_cg; > > if (cg_write(memcg, "memory.max", "50M")) > goto cleanup; > @@ -1275,8 +1274,8 @@ static int test_memcg_oom_group_score_events(const char *root) > ret = KSFT_PASS; > > cleanup: > - if (memcg) > - cg_destroy(memcg); > + cg_destroy(memcg); > +free_cg: > free(memcg); > > return ret; > -- > 2.40.0 > > I dislike this patch, it adds complexity for no discernible purpose and actively makes the code _less_ readable and in a self-test of all places (!) Not all pedantic Coccinelle results are actionable. Remember that it's humans who are reading the code. Your email client/scripting is still somehow broken, I couldn't get b4 to pull it correctly and it seems to have a duplicate message ID. You really need to take a look at that (git send-email should do this fine for example). Please try to filter the output of Coccinelle and instead of spamming thousands of pointless patches that add no value, try to choose those that do add value. My advice overall would be to just stop.

2 years, 1 month

1
0
0 0

Running KUnit using the wrapper script

by Mark Brown

I've been trying to do some stuff with KUnit but I can't seem to find a current tree where KUnit builds. Running on Debian stable starting from a clean -next tree and running: ./tools/testing/kunit/kunit.py config ./tools/testing/kunit/kunit.py build based on Documentation/dev-tools/kunit/start.rst. However I get: [00:42:59] Configuring KUnit Kernel ... [00:42:59] Building KUnit Kernel ... Populating config with: $ make ARCH=um O=.kunit olddefconfig Building with: $ make ARCH=um O=.kunit --jobs=8 ERROR:root:In file included from /usr/include/stdlib.h:1013, from ../arch/x86/um/os-Linux/registers.c:8: /usr/include/x86_64-linux-gnu/bits/stdlib-float.h: In function ‘atof’: /usr/include/x86_64-linux-gnu/bits/stdlib-float.h:26:1: error: SSE register return with SSE disabled 26 | { | ^ make[4]: *** [../scripts/Makefile.build:252: arch/x86/um/os-Linux/registers.o] Error 1 make[3]: *** [../scripts/Makefile.build:494: arch/x86/um/os-Linux] Error 2 make[3]: *** Waiting for unfinished jobs.... In file included from /usr/include/stdlib.h:1013, from ../arch/um/drivers/fd.c:7: /usr/include/x86_64-linux-gnu/bits/stdlib-float.h: In function ‘atof’: /usr/include/x86_64-linux-gnu/bits/stdlib-float.h:26:1: error: SSE register return with SSE disabled 26 | { | ^ make[3]: *** [../scripts/Makefile.build:252: arch/um/drivers/fd.o] Error 1 make[3]: *** Waiting for unfinished jobs.... In file included from /usr/include/stdlib.h:1013, from ../arch/um/os-Linux/skas/process.c:7: /usr/include/x86_64-linux-gnu/bits/stdlib-float.h: In function ‘atof’: /usr/include/x86_64-linux-gnu/bits/stdlib-float.h:26:1: error: SSE register return with SSE disabled 26 | { | ^ make[4]: *** [../scripts/Makefile.build:252: arch/um/os-Linux/skas/process.o] Error 1 make[3]: *** [../scripts/Makefile.build:494: arch/um/os-Linux/skas] Error 2 make[2]: *** [../scripts/Makefile.build:494: arch/um/os-Linux] Error 2 make[2]: *** Waiting for unfinished jobs.... make[2]: *** [../scripts/Makefile.build:494: arch/x86/um] Error 2 make[2]: *** [../scripts/Makefile.build:494: arch/um/drivers] Error 2 In file included from /usr/include/stdlib.h:1013, from arch/um/kernel/config.c:7: /usr/include/x86_64-linux-gnu/bits/stdlib-float.h: In function ‘atof’: /usr/include/x86_64-linux-gnu/bits/stdlib-float.h:26:1: error: SSE register return with SSE disabled 26 | { | ^ make[3]: *** [../scripts/Makefile.build:252: arch/um/kernel/config.o] Error 1 make[3]: *** Waiting for unfinished jobs.... make[2]: *** [../scripts/Makefile.build:494: arch/um/kernel] Error 2 make[1]: *** [/home/broonie/git/bisect/Makefile:2028: .] Error 2 make: *** [Makefile:226: __sub-make] Error 2 [00:43:20] Elapsed time: 20.233s which isn't ideal. v6.2 is also broken, albeit differently: ERROR:root:`.exit.text' referenced in section `.uml.exitcall.exit' of arch/um/drivers/virtio_uml.o: defined in discarded section `.exit.text' of arch/um/drivers/virtio_uml.o collect2: error: ld returned 1 exit status make[2]: *** [../scripts/Makefile.vmlinux:35: vmlinux] Error 1 make[1]: *** [/home/broonie/git/linux/Makefile:1264: vmlinux] Error 2 make: *** [Makefile:242: __sub-make] Error 2 which makes bisecting a bit of an issue. The kunit-fixes, kunit and kunit-next trees in -next have the former error. Can anyone point me at a tree/config/commands that's suitable for working on KUnit at the minute?

2 years, 1 month

2
2
0 0

[PATCH] selftests: prctl: Add new prctl test for PR_SET_VMA action

by Ivan Orlov

This patch will add the new test, which covers the prctl call with PR_SET_VMA command. The test tries to give a name to the anonymous VMA within the process memory map, and then checks the result of the operation by parsing 'maps' virtual file. Additionally, the test tries to call the prctl PR_SET_VMA command with invalid arguments, and checks the error codes for correctness. At the moment anonymous VMA naming through prctl call functionality is not covered with any tests, so I think implementing it makes sense. Signed-off-by: Ivan Orlov <ivan.orlov0322(a)gmail.com> --- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/prctl/.gitignore | 1 + tools/testing/selftests/prctl/Makefile | 2 +- tools/testing/selftests/prctl/config | 1 + .../selftests/prctl/set-anon-vma-name-test.c | 104 ++++++++++++++++++ 5 files changed, 108 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/prctl/config create mode 100644 tools/testing/selftests/prctl/set-anon-vma-name-test.c diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 13a6837a0c6b..dc2bfeaf4da7 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -89,6 +89,7 @@ TARGETS += vDSO TARGETS += mm TARGETS += x86 TARGETS += zram +TARGETS += prctl #Please keep the TARGETS list alphabetically sorted # Run "make quicktest=1 run_tests" or # "make quicktest=1 kselftest" from top level Makefile diff --git a/tools/testing/selftests/prctl/.gitignore b/tools/testing/selftests/prctl/.gitignore index 91af2b631bc9..7a657b25f686 100644 --- a/tools/testing/selftests/prctl/.gitignore +++ b/tools/testing/selftests/prctl/.gitignore @@ -2,3 +2,4 @@ disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test disable-tsc-test +set-anon-vma-name-test diff --git a/tools/testing/selftests/prctl/Makefile b/tools/testing/selftests/prctl/Makefile index c7923b205222..c058b81eeb41 100644 --- a/tools/testing/selftests/prctl/Makefile +++ b/tools/testing/selftests/prctl/Makefile @@ -5,7 +5,7 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) ifeq ($(ARCH),x86) TEST_PROGS := disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test \ - disable-tsc-test + disable-tsc-test set-anon-vma-name-test all: $(TEST_PROGS) include ../lib.mk diff --git a/tools/testing/selftests/prctl/config b/tools/testing/selftests/prctl/config new file mode 100644 index 000000000000..c6ed03c544e5 --- /dev/null +++ b/tools/testing/selftests/prctl/config @@ -0,0 +1 @@ +CONFIG_ANON_VMA_NAME=y diff --git a/tools/testing/selftests/prctl/set-anon-vma-name-test.c b/tools/testing/selftests/prctl/set-anon-vma-name-test.c new file mode 100644 index 000000000000..26d853c5a0c1 --- /dev/null +++ b/tools/testing/selftests/prctl/set-anon-vma-name-test.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This test covers the anonymous VMA naming functionality through prctl calls + */ + +#include <errno.h> +#include <sys/prctl.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <string.h> + +#include "../kselftest_harness.h" + +#define AREA_SIZE 1024 + +#define GOOD_NAME "goodname" +#define BAD_NAME "badname\1" + +#ifndef PR_SET_VMA +#define PR_SET_VMA 0x53564d41 +#define PR_SET_VMA_ANON_NAME 0 +#endif + + +int rename_vma(unsigned long addr, unsigned long size, char *name) +{ + int res; + + res = prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, addr, size, name); + if (res < 0) + return -errno; + return res; +} + +int was_renaming_successful(char *target_name, unsigned long ptr) +{ + FILE *maps_file; + + char line_buf[512], name[128], mode[8]; + unsigned long start_addr, end_addr, offset; + unsigned int major_id, minor_id, node_id; + + char target_buf[128]; + int res = 0, sscanf_res; + + // The entry name in maps will be in format [anon:<target_name>] + sprintf(target_buf, "[anon:%s]", target_name); + maps_file = fopen("/proc/self/maps", "r"); + if (!maps_file) { + printf("## /proc/self/maps file opening error\n"); + return 0; + } + + // Parse the maps file to find the entry we renamed + while (fgets(line_buf, sizeof(line_buf), maps_file)) { + sscanf_res = sscanf(line_buf, "%lx-%lx %7s %lx %u:%u %u %s", &start_addr, + &end_addr, mode, &offset, &major_id, + &minor_id, &node_id, name); + if (sscanf_res == EOF) { + res = 0; + printf("## EOF while parsing the maps file\n"); + break; + } + if (!strcmp(name, target_buf) && start_addr == ptr) { + res = 1; + break; + } + } + fclose(maps_file); + return res; +} + +FIXTURE(vma) { + void *ptr_anon, *ptr_not_anon; +}; + +FIXTURE_SETUP(vma) { + self->ptr_anon = mmap(NULL, AREA_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); + ASSERT_NE(self->ptr_anon, NULL); + self->ptr_not_anon = mmap(NULL, AREA_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE, 0, 0); + ASSERT_NE(self->ptr_not_anon, NULL); +} + +FIXTURE_TEARDOWN(vma) { + munmap(self->ptr_anon, AREA_SIZE); + munmap(self->ptr_not_anon, AREA_SIZE); +} + +TEST_F(vma, renaming) { + TH_LOG("Try to rename the VMA with correct parameters"); + EXPECT_GE(rename_vma((unsigned long)self->ptr_anon, AREA_SIZE, GOOD_NAME), 0); + EXPECT_TRUE(was_renaming_successful(GOOD_NAME, (unsigned long)self->ptr_anon)); + + TH_LOG("Try to pass invalid name (with non-printable character \\1) to rename the VMA"); + EXPECT_EQ(rename_vma((unsigned long)self->ptr_anon, AREA_SIZE, BAD_NAME), -EINVAL); + + TH_LOG("Try to rename non-anonynous VMA"); + EXPECT_EQ(rename_vma((unsigned long) self->ptr_not_anon, AREA_SIZE, GOOD_NAME), -EINVAL); +} + +TEST_HARNESS_MAIN -- 2.34.1

2 years, 1 month

1
0
0 0

[PATCH bpf-next v2 0/2] bpf: add bound tracking for BPF_MOD

by Xu Kuohai

From: Xu Kuohai <xukuohai(a)huawei.com> dst_reg is marked as unknown when BPF_MOD instruction is verified, causing the following bpf prog to be incorrectly rejected. 0: r0 = 0 1: r0 %= 1 // r0 is marked as unknown 2: r1 = 0 3: r1 += 1 4: if r1 < r0 goto pc-2 // verifier concludes the loop is unbounded 5: exit To teach verifier to accept the above prog, this series adds bound tracking for BPF_MOD. v2: - fix build warning reported by kernel test robot <lkp(a)intel.com> [0] - add two more cases and update commit message [0] https://lore.kernel.org/oe-kbuild-all/202303060036.zK05OC5M-lkp@intel.com v1: https://lore.kernel.org/bpf/20230306033119.2634976-1-xukuohai@huaweicloud.c… Xu Kuohai (2): bpf: add bound tracking for BPF_MOD selftests/bpf: check if verifier tracks dst_reg bound for BPF_MOD kernel/bpf/verifier.c | 98 ++++++- tools/testing/selftests/bpf/verifier/mod.c | 320 +++++++++++++++++++++ 2 files changed, 413 insertions(+), 5 deletions(-) create mode 100644 tools/testing/selftests/bpf/verifier/mod.c -- 2.30.2

2 years, 1 month

2
4
0 0

[PATCH] selftests: kvm: Add 'malloc' failure check in vcpu_save_state

by Ivan Orlov

There is a 'malloc' call in vcpu_save_state function, which can be unsuccessful. This patch will add the malloc failure checking to avoid possible null dereference and give more information about test fail reasons. Signed-off-by: Ivan Orlov <ivan.orlov0322(a)gmail.com> --- tools/testing/selftests/kvm/lib/x86_64/processor.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index c39a4353ba19..827647ff3d41 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -954,6 +954,7 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu) vcpu_run_complete_io(vcpu); state = malloc(sizeof(*state) + msr_list->nmsrs * sizeof(state->msrs.entries[0])); + TEST_ASSERT(state, "-ENOMEM when allocating kvm state"); vcpu_events_get(vcpu, &state->events); vcpu_mp_state_get(vcpu, &state->mp_state); -- 2.34.1

2 years, 1 month

2
1
0 0

[PATCH v3 00/13] Overhauling amx_test

by Mingwei Zhang

In this version, I have integrated Aaron's changes to the amx_test. In addition, we also integrated one fix patch for a kernel warning due to xsave address issue. Patch 1: Fix a host FPU kernel warning due to missing XTILEDATA in xinit. Patch 2-8: Overhaul amx_test. These patches were basically from v2. Patch 9-13: Overhaul amx_test from Aaron. I modified the changelog a little bit. v2 -> v3: - integrate Aaron's 5 commits with minor changes on commit message. - Add one fix patch for a kernel warning. v2: https://lore.kernel.org/all/20230214184606.510551-1-mizhang@google.com/ Aaron Lewis (5): KVM: selftests: x86: Assert that XTILE is XSAVE-enabled KVM: selftests: x86: Assert that both XTILE{CFG,DATA} are XSAVE-enabled KVM: selftests: x86: Remove redundant check that XSAVE is supported KVM: selftests: x86: Check that the palette table exists before using it KVM: selftests: x86: Check that XTILEDATA supports XFD Mingwei Zhang (8): x86/fpu/xstate: Avoid getting xstate address of init_fpstate if fpstate contains the component KVM: selftests: x86: Add a working xstate data structure KVM: selftests: x86: Fix an error in comment of amx_test KVM: selftests: x86: Add check of CR0.TS in the #NM handler in amx_test KVM: selftests: x86: Add the XFD check to IA32_XFD in #NM handler KVM: selftests: x86: Fix the checks to XFD_ERR using and operation KVM: selftests: x86: Enable checking on xcomp_bv in amx_test KVM: selftests: x86: Repeat the checking of xheader when IA32_XFD[XTILEDATA] is set in amx_test arch/x86/kernel/fpu/xstate.c | 10 ++- .../selftests/kvm/include/x86_64/processor.h | 14 ++++ tools/testing/selftests/kvm/x86_64/amx_test.c | 80 +++++++++---------- 3 files changed, 59 insertions(+), 45 deletions(-) -- 2.39.2.637.g21b0678d19-goog

2 years, 1 month

4
30
0 0

[PATCH v2 1/1] KVM: selftests: Adjust VM's initial stack address to align with SysV ABI spec

by Ackerley Tng

Align the guest stack to match calling sequence requirements in section "The Stack Frame" of the System V ABI AMD64 Architecture Processor Supplement, which requires the value (%rsp + 8), NOT %rsp, to be a multiple of 16 when control is transferred to the function entry point. I.e. in a normal function call, %rsp needs to be 16-byte aligned _before_ CALL, not after. This fixes unexpected #GPs in guest code when the compiler uses SSE instructions, e.g. to initialize memory, as many SSE instructions require memory operands (including those on the stack) to be 16-byte-aligned. Signed-off-by: Ackerley Tng <ackerleytng(a)google.com> --- This patch is a follow-up from discussions at https://lore.kernel.org/lkml/20230121001542.2472357-9-ackerleytng@google.co… v1 -> v2: Cleaned the patch up after getting comments from Sean in v1: https://lore.kernel.org/lkml/Y%2FfHLdvKHlK6D%2F1v@google.com/ Please also see https://lore.kernel.org/lkml/20230227174654.94641-1-ackerleytng@google.com/ regarding providing alignment macros for selftests. --- .../selftests/kvm/lib/x86_64/processor.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index ae1e573d94ce..a0669d31bb85 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -5,6 +5,7 @@ * Copyright (C) 2018, Google LLC. */ +#include "linux/bitmap.h" #include "test_util.h" #include "kvm_util.h" #include "processor.h" @@ -573,6 +574,21 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, DEFAULT_GUEST_STACK_VADDR_MIN, MEM_REGION_DATA); + stack_vaddr += DEFAULT_STACK_PGS * getpagesize(); + + /* + * Align stack to match calling sequence requirements in section "The + * Stack Frame" of the System V ABI AMD64 Architecture Processor + * Supplement, which requires the value (%rsp + 8) to be a multiple of + * 16 when control is transferred to the function entry point. + * + * If this code is ever used to launch a vCPU with 32-bit entry point it + * may need to subtract 4 bytes instead of 8 bytes. + */ + TEST_ASSERT(IS_ALIGNED(stack_vaddr, PAGE_SIZE), + "__vm_vaddr_alloc() did not provide a page-aligned address"); + stack_vaddr -= 8; + vcpu = __vm_vcpu_add(vm, vcpu_id); vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid()); vcpu_setup(vm, vcpu); @@ -580,7 +596,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, /* Setup guest general purpose registers */ vcpu_regs_get(vcpu, &regs); regs.rflags = regs.rflags | 0x2; - regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize()); + regs.rsp = stack_vaddr; regs.rip = (unsigned long) guest_code; vcpu_regs_set(vcpu, &regs); -- 2.39.2.722.g9855ee24e9-goog

2 years, 1 month

2
2
0 0

Re: [PATCH] selftests/bpf: Improve exception handling in rbtree_add_and_remove()

by Alexei Starovoitov

On Fri, Mar 24, 2023 at 7:13 AM Markus Elfring <Markus.Elfring(a)web.de> wrote: > > Date: Fri, 24 Mar 2023 14:54:18 +0100 > > The label “err_out” was used to jump to another pointer check despite of > the detail in the implementation of the function “rbtree_add_and_remove” > that it was determined already that a corresponding variable contained > a null pointer. > > 1. Thus return directly after the first call of the function > “bpf_obj_new” failed. > > 2. Delete two questionable checks. > > 3. Omit an extra initialisation (for the variable “m”) > which became unnecessary with this refactoring. > > > This issue was detected by using the Coccinelle software. > > Fixes: 215249f6adc0359e3546829e7ee622b5e309b0ad ("selftests/bpf: Add rbtree selftests") > Signed-off-by: Markus Elfring <elfring(a)users.sourceforge.net> Nack. Please stop sending such "cleanup" patches.

2 years, 1 month

1
0
0 0

[PATCH] capability: test_deny_namespace breakage due to capability conversion to u64

by Sasha Levin

Commit f122a08b197d ("capability: just use a 'u64' instead of a 'u32[2]' array") attempts to use BIT_LL() but actually wanted to use BIT_ULL(), fix it up to make the test compile and run again. Fixes: f122a08b197d ("capability: just use a 'u64' instead of a 'u32[2]' array") Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/Makefile | 2 +- tools/testing/selftests/bpf/progs/test_deny_namespace.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index b677dcd0b77af..91a4e61b61f6d 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -353,7 +353,7 @@ endif CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) BPF_CFLAGS = -g -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR) \ - -I$(abspath $(OUTPUT)/../usr/include) + -I$(abspath $(OUTPUT)/../usr/include) -I$(TOOLSINCDIR) CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \ -Wno-compare-distinct-pointer-types diff --git a/tools/testing/selftests/bpf/progs/test_deny_namespace.c b/tools/testing/selftests/bpf/progs/test_deny_namespace.c index 591104e79812e..0a619c34d692d 100644 --- a/tools/testing/selftests/bpf/progs/test_deny_namespace.c +++ b/tools/testing/selftests/bpf/progs/test_deny_namespace.c @@ -4,6 +4,7 @@ #include <bpf/bpf_tracing.h> #include <errno.h> #include <linux/capability.h> +#include <vdso/bits.h> struct kernel_cap_struct { __u64 val; @@ -19,7 +20,7 @@ SEC("lsm.s/userns_create") int BPF_PROG(test_userns_create, const struct cred *cred, int ret) { struct kernel_cap_struct caps = cred->cap_effective; - __u64 cap_mask = BIT_LL(CAP_SYS_ADMIN); + __u64 cap_mask = BIT_ULL(CAP_SYS_ADMIN); if (ret) return 0; -- 2.39.2

2 years, 1 month

3
2
0 0

[PATCH net-next 0/4] mptcp: a couple of cleanups and improvements

by Matthieu Baerts

Patch 1 removes an unneeded address copy in subflow_syn_recv_sock(). Patch 2 simplifies subflow_syn_recv_sock() to postpone some actions and to avoid a bunch of conditionals. Patch 3 stops reporting limits that are not taken into account when the userspace PM is used. Patch 4 adds a new test to validate that the 'subflows' field reported by the kernel is correct. Such info can be retrieved via Netlink (e.g. with ss) or getsockopt(SOL_MPTCP, MPTCP_INFO). Signed-off-by: Matthieu Baerts <matthieu.baerts(a)tessares.net> --- Geliang Tang (1): selftests: mptcp: add mptcp_info tests Matthieu Baerts (1): mptcp: do not fill info not used by the PM in used Paolo Abeni (2): mptcp: avoid unneeded address copy mptcp: simplify subflow_syn_recv_sock() net/mptcp/sockopt.c | 20 +++++++---- net/mptcp/subflow.c | 43 +++++++--------------- tools/testing/selftests/net/mptcp/mptcp_join.sh | 47 ++++++++++++++++++++++++- 3 files changed, 72 insertions(+), 38 deletions(-) --- base-commit: 323fe43cf9aef79159ba8937218a3f076bf505af change-id: 20230324-upstream-net-next-20230324-misc-features-178b2b618414 Best regards, -- Matthieu Baerts <matthieu.baerts(a)tessares.net>

2 years, 1 month

1
5
0 0

[PATCH v5 0/4] cover-letter: Add IO page table replacement support

by Nicolin Chen

[ This series depends on VFIO device cdev series ] Changelog v5: * Kept the cmd->id in the iommufd_test_create_access() so the access can be created with an ioas by default. Then, renamed the previous ioctl IOMMU_TEST_OP_ACCESS_SET_IOAS to IOMMU_TEST_OP_ACCESS_REPLACE_IOAS, so it would be used to replace an access->ioas pointer. * Added iommufd_access_replace() API after the introductions of the other two APIs iommufd_access_attach() and iommufd_access_detach(). * Since vdev->iommufd_attached is also set in emulated pathway too, call iommufd_access_update(), similar to the physical pathway. v4: https://lore.kernel.org/linux-iommu/cover.1678284812.git.nicolinc@nvidia.co… * Rebased on top of Jason's series adding replace() and hwpt_alloc() https://lore.kernel.org/linux-iommu/0-v2-51b9896e7862+8a8c-iommufd_alloc_jg… * Rebased on top of cdev series v6 https://lore.kernel.org/kvm/20230308132903.465159-1-yi.l.liu@intel.com/ * Dropped the patch that's moved to cdev series. * Added unmap function pointer sanity before calling it. * Added "Reviewed-by" from Kevin and Yi. * Added back the VFIO change updating the ATTACH uAPI. v3: https://lore.kernel.org/linux-iommu/cover.1677288789.git.nicolinc@nvidia.co… * Rebased on top of Jason's iommufd_hwpt branch: https://lore.kernel.org/linux-iommu/0-v2-406f7ac07936+6a-iommufd_hwpt_jgg@n… * Dropped patches from this series accordingly. There were a couple of VFIO patches that will be submitted after the VFIO cdev series. Also, renamed the series to be "emulated". * Moved dma_unmap sanity patch to the first in the series. * Moved dma_unmap sanity to cover both VFIO and IOMMUFD pathways. * Added Kevin's "Reviewed-by" to two of the patches. * Fixed a NULL pointer bug in vfio_iommufd_emulated_bind(). * Moved unmap() call to the common place in iommufd_access_set_ioas(). v2: https://lore.kernel.org/linux-iommu/cover.1675802050.git.nicolinc@nvidia.co… * Rebased on top of vfio_device cdev v2 series. * Update the kdoc and commit message of iommu_group_replace_domain(). * Dropped revert-to-core-domain part in iommu_group_replace_domain(). * Dropped !ops->dma_unmap check in vfio_iommufd_emulated_attach_ioas(). * Added missing rc value in vfio_iommufd_emulated_attach_ioas() from the iommufd_access_set_ioas() call. * Added a new patch in vfio_main to deny vfio_pin/unpin_pages() calls if vdev->ops->dma_unmap is not implemented. * Added a __iommmufd_device_detach helper and let the replace routine do a partial detach(). * Added restriction on auto_domains to use the replace feature. * Added the patch "iommufd/device: Make hwpt_list list_add/del symmetric" from the has_group removal series. v1: https://lore.kernel.org/linux-iommu/cover.1675320212.git.nicolinc@nvidia.co… Hi all, The existing IOMMU APIs provide a pair of functions: iommu_attach_group() for callers to attach a device from the default_domain (NULL if not being supported) to a given iommu domain, and iommu_detach_group() for callers to detach a device from a given domain to the default_domain. Internally, the detach_dev op is deprecated for the newer drivers with default_domain. This means that those drivers likely can switch an attaching domain to another one, without stagging the device at a blocking or default domain, for use cases such as: 1) vPASID mode, when a guest wants to replace a single pasid (PASID=0) table with a larger table (PASID=N) 2) Nesting mode, when switching the attaching device from an S2 domain to an S1 domain, or when switching between relevant S1 domains. This series is rebased on top of Jason Gunthorpe's series that introduces iommu_group_replace_domain API and IOMMUFD infrastructure for the IOMMUFD "physical" devices. The IOMMUFD "emulated" deivces will need some extra steps to replace the access->ioas object and its iopt pointer. You can also find this series on Github: https://github.com/nicolinc/iommufd/commits/iommu_group_replace_domain-v5 Thank you Nicolin Chen Nicolin Chen (4): vfio: Do not allow !ops->dma_unmap in vfio_pin/unpin_pages() iommufd: Add iommufd_access_replace() API iommufd/selftest: Add IOMMU_TEST_OP_ACCESS_REPLACE_IOAS coverage vfio: Support IO page table replacement drivers/iommu/iommufd/device.c | 60 +++++++++++++++---- drivers/iommu/iommufd/iommufd_test.h | 4 ++ drivers/iommu/iommufd/selftest.c | 19 ++++++ drivers/vfio/iommufd.c | 11 ++-- drivers/vfio/vfio_main.c | 4 ++ include/linux/iommufd.h | 1 + include/uapi/linux/vfio.h | 6 ++ tools/testing/selftests/iommu/iommfd*.c | 0 tools/testing/selftests/iommu/iommufd.c | 29 ++++++++- tools/testing/selftests/iommu/iommufd_utils.h | 19 ++++++ 10 files changed, 135 insertions(+), 18 deletions(-) create mode 100644 tools/testing/selftests/iommu/iommfd*.c -- 2.40.0

2 years, 1 month

2
7
0 0

[PATCH v2] kselftest/alsa: Fix -Wformat compiler warnings

by Alexander Heinrich

Fix compiler warnings caused by mixing long and unsigned int values: Change type of variables rate, channels, period_size and buffer_size to unsigned int (as used by rrate). Signed-off-by: Alexander Heinrich <hallo(a)alexanderheinrich.de> --- Hi Takashi, Thank you for your feedback on my first version of the patch! I have changed the variables to unsigned int, removed the casts and changed the relevant format specifiers to %d. This produced a new warnings in two places, where the 'rate' and 'channels' variables were being multiplied with 'snd_pcm_format_physical_width()', because this function returns an int (and can return a negative value on failure). I added a check for negative values, so that the return value can safely be cast to unsigned int. For the string to int conversion functions, the return values for the test cases in pcm-test.conf are non-negative and in the range of unsigned int, so I just cast them to unsigned int. Please let me know if I can further improve on my patch (it is my first)! Thanks and greetings, Alex tools/testing/selftests/alsa/pcm-test.c | 41 ++++++++++++++----------- 1 file changed, 23 insertions(+), 18 deletions(-) diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c index 3e390fe67eb9..d4420789837c 100644 --- a/tools/testing/selftests/alsa/pcm-test.c +++ b/tools/testing/selftests/alsa/pcm-test.c @@ -259,7 +259,7 @@ static void test_pcm_time(struct pcm_data *data, enum test_class class, { char name[64], key[128], msg[256]; const char *cs; - int i, err; + int i, err, phys_width; snd_pcm_t *handle = NULL; snd_pcm_access_t access = SND_PCM_ACCESS_RW_INTERLEAVED; snd_pcm_format_t format, old_format; @@ -267,8 +267,7 @@ static void test_pcm_time(struct pcm_data *data, enum test_class class, unsigned char *samples = NULL; snd_pcm_sframes_t frames; long long ms; - long rate, channels, period_size, buffer_size; - unsigned int rrate; + unsigned int rate, channels, period_size, buffer_size, rrate; snd_pcm_uframes_t rperiod_size, rbuffer_size, start_threshold; timestamp_t tstamp; bool pass = false; @@ -308,12 +307,15 @@ static void test_pcm_time(struct pcm_data *data, enum test_class class, ksft_exit_fail_msg("Wrong format '%s'\n", cs); conf_get_string_array(pcm_cfg, "alt_formats", NULL, alt_formats, ARRAY_SIZE(alt_formats), NULL); - rate = conf_get_long(pcm_cfg, "rate", NULL, 48000); - channels = conf_get_long(pcm_cfg, "channels", NULL, 2); - period_size = conf_get_long(pcm_cfg, "period_size", NULL, 4096); - buffer_size = conf_get_long(pcm_cfg, "buffer_size", NULL, 16384); - - samples = malloc((rate * channels * snd_pcm_format_physical_width(format)) / 8); + rate = (unsigned int)conf_get_long(pcm_cfg, "rate", NULL, 48000); + channels = (unsigned int)conf_get_long(pcm_cfg, "channels", NULL, 2); + period_size = (unsigned int)conf_get_long(pcm_cfg, "period_size", NULL, 4096); + buffer_size = (unsigned int)conf_get_long(pcm_cfg, "buffer_size", NULL, 16384); + + phys_width = snd_pcm_format_physical_width(format); + if (phys_width < 0) + ksft_exit_fail_msg("Unknown PCM format\n"); + samples = malloc((rate * channels * (unsigned int)phys_width) / 8); if (!samples) ksft_exit_fail_msg("Out of memory\n"); snd_pcm_format_set_silence(format, samples, rate * channels); @@ -357,8 +359,11 @@ static void test_pcm_time(struct pcm_data *data, enum test_class class, snd_pcm_access_name(access), snd_pcm_format_name(old_format), snd_pcm_format_name(format)); + phys_width = snd_pcm_format_physical_width(format); + if (phys_width < 0) + ksft_exit_fail_msg("Unknown PCM format\n"); samples = realloc(samples, (rate * channels * - snd_pcm_format_physical_width(format)) / 8); + (unsigned int)phys_width) / 8); if (!samples) ksft_exit_fail_msg("Out of memory\n"); snd_pcm_format_set_silence(format, samples, rate * channels); @@ -371,29 +376,29 @@ static void test_pcm_time(struct pcm_data *data, enum test_class class, } err = snd_pcm_hw_params_set_channels(handle, hw_params, channels); if (err < 0) { - snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_channels %ld: %s", channels, snd_strerror(err)); + snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_channels %d: %s", channels, snd_strerror(err)); goto __close; } rrate = rate; err = snd_pcm_hw_params_set_rate_near(handle, hw_params, &rrate, 0); if (err < 0) { - snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_rate %ld: %s", rate, snd_strerror(err)); + snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_rate %d: %s", rate, snd_strerror(err)); goto __close; } if (rrate != rate) { - snprintf(msg, sizeof(msg), "rate mismatch %ld != %ld", rate, rrate); + snprintf(msg, sizeof(msg), "rate mismatch %d != %d", rate, rrate); goto __close; } rperiod_size = period_size; err = snd_pcm_hw_params_set_period_size_near(handle, hw_params, &rperiod_size, 0); if (err < 0) { - snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_period_size %ld: %s", period_size, snd_strerror(err)); + snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_period_size %d: %s", period_size, snd_strerror(err)); goto __close; } rbuffer_size = buffer_size; err = snd_pcm_hw_params_set_buffer_size_near(handle, hw_params, &rbuffer_size); if (err < 0) { - snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_buffer_size %ld: %s", buffer_size, snd_strerror(err)); + snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_buffer_size %d: %s", buffer_size, snd_strerror(err)); goto __close; } err = snd_pcm_hw_params(handle, hw_params); @@ -428,14 +433,14 @@ static void test_pcm_time(struct pcm_data *data, enum test_class class, goto __close; } - ksft_print_msg("%s.%s.%d.%d.%d.%s hw_params.%s.%s.%ld.%ld.%ld.%ld sw_params.%ld\n", + ksft_print_msg("%s.%s.%d.%d.%d.%s hw_params.%s.%s.%d.%d.%d.%d sw_params.%ld\n", test_class_name, test_name, data->card, data->device, data->subdevice, snd_pcm_stream_name(data->stream), snd_pcm_access_name(access), snd_pcm_format_name(format), - (long)rate, (long)channels, - (long)rperiod_size, (long)rbuffer_size, + rate, channels, + rperiod_size, rbuffer_size, (long)start_threshold); /* Set all the params, actually run the test */ -- 2.34.1

2 years, 1 month

2
1
0 0

[PATCH 0/5] Split a folio to any lower order folios

by Zi Yan

From: Zi Yan <ziy(a)nvidia.com> Hi all, File folio supports any order and people would like to support flexible orders for anonymous folio[1] too. Currently, split_huge_page() only splits a huge page to order-0 pages, but splitting to orders higher than 0 is also useful. This patchset adds support for splitting a huge page to any lower order pages and uses it during folio truncate operations. The patchset is on top of mm-everything-2023-03-19-21-50. * Patch 1 and 2 add new_order parameter split_page_memcg() and split_page_owner() and prepare for upcoming changes. * Patch 3 adds split_huge_page_to_list_to_order() to split a huge page to any lower order. The original split_huge_page_to_list() calls split_huge_page_to_list_to_order() with new_order = 0. * Patch 4 uses split_huge_page_to_list_to_order() in large pagecache folio truncation instead of split the large folio all the way down to order-0. * Patch 5 adds a test API to debugfs and test cases in split_huge_page_test selftests. Comments and/or suggestions are welcome. [1] https://lore.kernel.org/linux-mm/Y%2FblF0GIunm+pRIC@casper.infradead.org/ Zi Yan (5): mm: memcg: make memcg huge page split support any order split. mm: page_owner: add support for splitting to any order in split page_owner. mm: thp: split huge page to any lower order pages. mm: truncate: split huge page cache page to a non-zero order if possible. mm: huge_memory: enable debugfs to split huge pages to any order. include/linux/huge_mm.h | 10 +- include/linux/memcontrol.h | 5 +- include/linux/page_owner.h | 12 +- mm/huge_memory.c | 138 ++++++++--- mm/memcontrol.c | 8 +- mm/page_alloc.c | 8 +- mm/page_owner.c | 11 +- mm/truncate.c | 21 +- .../selftests/mm/split_huge_page_test.c | 225 +++++++++++++++++- 9 files changed, 368 insertions(+), 70 deletions(-) -- 2.39.2

2 years, 1 month

4
10
0 0

[PATCH v1 0/2] KVM: s390: CMMA migration selftest and small bugfix

by Nico Boehr

Add a new selftest for CMMA migration. Also fix a small issue found during development of the test. Nico Boehr (2): KVM: s390: selftests: add selftest for CMMA migration KVM: s390: fix KVM_S390_GET_CMMA_BITS for GFNs in memslot holes arch/s390/kvm/kvm-s390.c | 4 + tools/testing/selftests/kvm/Makefile | 1 + tools/testing/selftests/kvm/s390x/cmma_test.c | 679 ++++++++++++++++++ 3 files changed, 684 insertions(+) create mode 100644 tools/testing/selftests/kvm/s390x/cmma_test.c -- 2.39.1

2 years, 1 month

2
10
0 0

[PATCH] kselftest/alsa: Fix -Wformat compiler warnings

by Alexander Heinrich

I noticed some -Wformat compiler warnings in pcm-test.c while building kselftest, fix them by using the same types for format specifier and arguments. Signed-off-by: Alexander Heinrich <hallo(a)alexanderheinrich.de> --- tools/testing/selftests/alsa/pcm-test.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c index 58b525a4a32c..44fc5f826ab5 100644 --- a/tools/testing/selftests/alsa/pcm-test.c +++ b/tools/testing/selftests/alsa/pcm-test.c @@ -371,7 +371,7 @@ static void test_pcm_time(struct pcm_data *data, enum test_class class, goto __close; } if (rrate != rate) { - snprintf(msg, sizeof(msg), "rate mismatch %ld != %ld", rate, rrate); + snprintf(msg, sizeof(msg), "rate mismatch %ld != %d", rate, rrate); goto __close; } rperiod_size = period_size; @@ -437,24 +437,24 @@ static void test_pcm_time(struct pcm_data *data, enum test_class class, frames = snd_pcm_writei(handle, samples, rate); if (frames < 0) { snprintf(msg, sizeof(msg), - "Write failed: expected %d, wrote %li", rate, frames); + "Write failed: expected %ld, wrote %li", rate, frames); goto __close; } if (frames < rate) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } } else { frames = snd_pcm_readi(handle, samples, rate); if (frames < 0) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } if (frames < rate) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } } -- 2.34.1

2 years, 1 month

2
2
0 0

[PATCH] kselftest/alsa - pcm-test: Don't include diagnostic message in test name

by Mark Brown

When reporting errors or skips we currently include the diagnostic message indicating why we're failing or skipping. This isn't ideal since KTAP defines the entire print as the test name, so if there's an error then test systems won't detect the test as being the same one as a passing test. Move the diagnostic to a separate ksft_print_msg() to avoid this issue, the test name part will always be the same for passes, fails and skips and the diagnostic information is still displayed. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/alsa/pcm-test.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c index 58b525a4a32c..bab56ea67e89 100644 --- a/tools/testing/selftests/alsa/pcm-test.c +++ b/tools/testing/selftests/alsa/pcm-test.c @@ -489,17 +489,18 @@ static void test_pcm_time(struct pcm_data *data, enum test_class class, } if (!skip) - ksft_test_result(pass, "%s.%s.%d.%d.%d.%s%s%s\n", + ksft_test_result(pass, "%s.%s.%d.%d.%d.%s\n", test_class_name, test_name, data->card, data->device, data->subdevice, - snd_pcm_stream_name(data->stream), - msg[0] ? " " : "", msg); + snd_pcm_stream_name(data->stream)); else - ksft_test_result_skip("%s.%s.%d.%d.%d.%s%s%s\n", + ksft_test_result_skip("%s.%s.%d.%d.%d.%s\n", test_class_name, test_name, data->card, data->device, data->subdevice, - snd_pcm_stream_name(data->stream), - msg[0] ? " " : "", msg); + snd_pcm_stream_name(data->stream)); + + if (msg[0]) + ksft_print_msg("%s\n", msg); pthread_mutex_unlock(&results_lock); --- base-commit: e8d018dd0257f744ca50a729e3d042cf2ec9da65 change-id: 20230323-alsa-pcm-test-names-bcd31b586ca9 Best regards, -- Mark Brown <broonie(a)kernel.org>

2 years, 1 month

2
1
0 0

[PATCH] kselftest/alsa - mixer-test: Log values associated with event issues

by Mark Brown

While it is common for driver bugs with events to apply to all events there are some issues which only trigger for specific values. Understanding these is easier if we know what we were trying to do when configuring the control so add logging for the specific values involved in the spurious event. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/alsa/mixer-test.c | 44 +++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c index 05f1749ae19d..15d2ef8d4d27 100644 --- a/tools/testing/selftests/alsa/mixer-test.c +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -445,6 +445,48 @@ static void test_ctl_name(struct ctl_data *ctl) ctl->card->card, ctl->elem); } +static void show_values(struct ctl_data *ctl, snd_ctl_elem_value_t *orig_val, + snd_ctl_elem_value_t *read_val) +{ + long long orig_int, read_int; + int i; + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + switch (snd_ctl_elem_info_get_type(ctl->info)) { + case SND_CTL_ELEM_TYPE_BOOLEAN: + orig_int = snd_ctl_elem_value_get_boolean(orig_val, i); + read_int = snd_ctl_elem_value_get_boolean(read_val, i); + break; + + case SND_CTL_ELEM_TYPE_INTEGER: + orig_int = snd_ctl_elem_value_get_integer(orig_val, i); + read_int = snd_ctl_elem_value_get_integer(read_val, i); + break; + + case SND_CTL_ELEM_TYPE_INTEGER64: + orig_int = snd_ctl_elem_value_get_integer64(orig_val, + i); + read_int = snd_ctl_elem_value_get_integer64(read_val, + i); + break; + + case SND_CTL_ELEM_TYPE_ENUMERATED: + orig_int = snd_ctl_elem_value_get_enumerated(orig_val, + i); + read_int = snd_ctl_elem_value_get_enumerated(read_val, + i); + break; + + default: + return; + } + + ksft_print_msg("%s.%d orig %lld read %lld, is_volatile %d\n", + ctl->name, i, orig_int, read_int, + snd_ctl_elem_info_is_volatile(ctl->info)); + } +} + static bool show_mismatch(struct ctl_data *ctl, int index, snd_ctl_elem_value_t *read_val, snd_ctl_elem_value_t *expected_val) @@ -584,12 +626,14 @@ static int write_and_verify(struct ctl_data *ctl, if (err < 1) { ksft_print_msg("No event generated for %s\n", ctl->name); + show_values(ctl, initial_val, read_val); ctl->event_missing++; } } else { if (err != 0) { ksft_print_msg("Spurious event generated for %s\n", ctl->name); + show_values(ctl, initial_val, read_val); ctl->event_spurious++; } } --- base-commit: e8d018dd0257f744ca50a729e3d042cf2ec9da65 change-id: 20230322-alsa-mixer-event-values-7498bca29241 Best regards, -- Mark Brown <broonie(a)kernel.org>

2 years, 1 month

2
1
0 0

[PATCH v2 0/8] tools/nolibc: add support for stack protector

by Thomas Weißschuh

This is useful when using nolibc for security-critical tools. Using nolibc has the advantage that the code is easily auditable and sandboxable with seccomp as no unexpected syscalls are used. Using compiler-assistent stack protection provides another security mechanism. For this to work the compiler and libc have to collaborate. This patch adds the following parts to nolibc that are required by the compiler: * __stack_chk_guard: random sentinel value * __stack_chk_fail: handler for detected stack smashes In addition an initialization function is added that randomizes the sentinel value. Only support for global guards is implemented. Register guards are useful in multi-threaded context which nolibc does not provide support for. Link: https://lwn.net/Articles/584225/ Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- Changes in v2: - Code and comments style fixes - Only use raw syscalls in stackprotector functions - Remove need for dedicated entrypoint and exec() during tests - Add more rationale - Shuffle some code around between commits - Provide compatibility with the -fno-stack-protector patch - Remove RFC status - Link to v1: https://lore.kernel.org/r/20230223-nolibc-stackprotector-v1-0-3e74d81b3f21@… This series is based on the current rcu/dev branch of Pauls rcu tree. --- Thomas Weißschuh (8): tools/nolibc: add definitions for standard fds tools/nolibc: add helpers for wait() signal exits tools/nolibc: tests: constify test_names tools/nolibc: add support for stack protector tools/nolibc: tests: fold in no-stack-protector cflags tools/nolibc: tests: add test for -fstack-protector tools/nolibc: i386: add stackprotector support tools/nolibc: x86_64: add stackprotector support tools/include/nolibc/Makefile | 4 +- tools/include/nolibc/arch-i386.h | 7 ++- tools/include/nolibc/arch-x86_64.h | 5 +++ tools/include/nolibc/nolibc.h | 1 + tools/include/nolibc/stackprotector.h | 53 +++++++++++++++++++++++ tools/include/nolibc/types.h | 2 + tools/include/nolibc/unistd.h | 5 +++ tools/testing/selftests/nolibc/Makefile | 11 ++++- tools/testing/selftests/nolibc/nolibc-test.c | 64 ++++++++++++++++++++++++++-- 9 files changed, 144 insertions(+), 8 deletions(-) --- base-commit: a9b8406e51603238941dbc6fa1437f8915254ebb change-id: 20230223-nolibc-stackprotector-d4d5f48ff771 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

2 years, 1 month

2
12
0 0

[PATCH v2 0/2] KVM: PPC: selftests: powerpc support

by Nicholas Piggin

Hi, This series adds initial KVM selftests support for powerpc (64-bit, BookS). It spans 3 maintainers but it does not really affect arch/powerpc, and it is well contained in selftests code, just touches some makefiles and a tiny bit headers so conflicts should be unlikely and trivial. Hey Paolo and KVM group, if you didn't take the v1 series yet, could you please take this instead. Otherwise I can send an incremental fixup. Since v1: - r2 (TOC) was not being set for guest code - MSR[VSX] was not being set for guest code - Proper guest interrupt handling instead of quick hack that just made a ucall out to host. - Adjust subject to better match kvm selftests convention. Thanks, Nick Nicholas Piggin (2): KVM: PPC: selftests: implement support for powerpc KVM: PPC: selftests: basic sanity tests tools/testing/selftests/kvm/Makefile | 15 + .../selftests/kvm/include/kvm_util_base.h | 13 + .../selftests/kvm/include/powerpc/hcall.h | 22 + .../selftests/kvm/include/powerpc/ppc_asm.h | 17 + .../selftests/kvm/include/powerpc/processor.h | 32 ++ tools/testing/selftests/kvm/lib/kvm_util.c | 10 + .../selftests/kvm/lib/powerpc/handlers.S | 96 ++++ .../testing/selftests/kvm/lib/powerpc/hcall.c | 45 ++ .../selftests/kvm/lib/powerpc/processor.c | 411 ++++++++++++++++++ .../testing/selftests/kvm/lib/powerpc/ucall.c | 30 ++ tools/testing/selftests/kvm/powerpc/helpers.h | 46 ++ .../testing/selftests/kvm/powerpc/null_test.c | 166 +++++++ .../selftests/kvm/powerpc/rtas_hcall.c | 146 +++++++ 13 files changed, 1049 insertions(+) create mode 100644 tools/testing/selftests/kvm/include/powerpc/hcall.h create mode 100644 tools/testing/selftests/kvm/include/powerpc/ppc_asm.h create mode 100644 tools/testing/selftests/kvm/include/powerpc/processor.h create mode 100644 tools/testing/selftests/kvm/lib/powerpc/handlers.S create mode 100644 tools/testing/selftests/kvm/lib/powerpc/hcall.c create mode 100644 tools/testing/selftests/kvm/lib/powerpc/processor.c create mode 100644 tools/testing/selftests/kvm/lib/powerpc/ucall.c create mode 100644 tools/testing/selftests/kvm/powerpc/helpers.h create mode 100644 tools/testing/selftests/kvm/powerpc/null_test.c create mode 100644 tools/testing/selftests/kvm/powerpc/rtas_hcall.c -- 2.37.2

2 years, 1 month

1
2
0 0

[PATCH v11 0/7] Implement IOCTL to get and optionally clear info about PTEs

by Muhammad Usama Anjum

These patches are based on next-20230307 and UFFD_FEATURE_WP_UNPOPULATED patches from Peter. *Changes in v11* - Rebase on top of next-20230307 - Base patches on UFFD_FEATURE_WP_UNPOPULATED (https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com) - Do a lot of cosmetic changes and review updates - Remove ENGAGE_WP + ! GET operation as it can be performed with UFFDIO_WRITEPROTECT *Changes in v10* - Add specific condition to return error if hugetlb is used with wp async - Move changes in tools/include/uapi/linux/fs.h to separate patch - Add documentation *Changes in v9:* - Correct fault resolution for userfaultfd wp async - Fix build warnings and errors which were happening on some configs - Simplify pagemap ioctl's code *Changes in v8:* - Update uffd async wp implementation - Improve PAGEMAP_IOCTL implementation *Changes in v7:* - Add uffd wp async - Update the IOCTL to use uffd under the hood instead of soft-dirty flags Hello, Note: Soft-dirty pages and pages which have been written-to are synonyms. As kernel already has soft-dirty feature inside which we have given up to use, we are using written-to terminology while using UFFD async WP under the hood. This IOCTL, PAGEMAP_SCAN on pagemap file can be used to get and/or clear the info about page table entries. The following operations are supported in this ioctl: - Get the information if the pages have been written-to (PAGE_IS_WRITTEN), file mapped (PAGE_IS_FILE), present (PAGE_IS_PRESENT) or swapped (PAGE_IS_SWAPPED). - Write-protect the pages (PAGEMAP_WP_ENGAGE) to start finding which pages have been written-to. - Find pages which have been written-to and write protect the pages (atomic PAGE_IS_WRITTEN + PAGEMAP_WP_ENGAGE) It is possible to find and clear soft-dirty pages entirely in userspace. But it isn't efficient: - The mprotect and SIGSEGV handler for bookkeeping - The userfaultfd wp (synchronous) with the handler for bookkeeping Some benchmarks can be seen here[1]. This series adds features that weren't present earlier: - There is no atomic get soft-dirty/Written-to status and clear present in the kernel. - The pages which have been written-to can not be found in accurate way. (Kernel's soft-dirty PTE bit + sof_dirty VMA bit shows more soft-dirty pages than there actually are.) Historically, soft-dirty PTE bit tracking has been used in the CRIU project. The procfs interface is enough for finding the soft-dirty bit status and clearing the soft-dirty bit of all the pages of a process. We have the use case where we need to track the soft-dirty PTE bit for only specific pages on-demand. We need this tracking and clear mechanism of a region of memory while the process is running to emulate the getWriteWatch() syscall of Windows. *(Moved to using UFFD instead of soft-dirtyi feature to find pages which have been written-to from v7 patch series)*: Stop using the soft-dirty flags for finding which pages have been written to. It is too delicate and wrong as it shows more soft-dirty pages than the actual soft-dirty pages. There is no interest in correcting it [2][3] as this is how the feature was written years ago. It shouldn't be updated to changed behaviour. Peter Xu has suggested using the async version of the UFFD WP [4] as it is based inherently on the PTEs. So in this patch series, I've added a new mode to the UFFD which is asynchronous version of the write protect. When this variant of the UFFD WP is used, the page faults are resolved automatically by the kernel. The pages which have been written-to can be found by reading pagemap file (!PM_UFFD_WP). This feature can be used successfully to find which pages have been written to from the time the pages were write protected. This works just like the soft-dirty flag without showing any extra pages which aren't soft-dirty in reality. The information related to pages if the page is file mapped, present and swapped is required for the CRIU project [5][6]. The addition of the required mask, any mask, excluded mask and return masks are also required for the CRIU project [5]. The IOCTL returns the addresses of the pages which match the specific masks. The page addresses are returned in struct page_region in a compact form. The max_pages is needed to support a use case where user only wants to get a specific number of pages. So there is no need to find all the pages of interest in the range when max_pages is specified. The IOCTL returns when the maximum number of the pages are found. The max_pages is optional. If max_pages is specified, it must be equal or greater than the vec_size. This restriction is needed to handle worse case when one page_region only contains info of one page and it cannot be compacted. This is needed to emulate the Windows getWriteWatch() syscall. The patch series include the detailed selftest which can be used as an example for the uffd async wp test and PAGEMAP_IOCTL. It shows the interface usages as well. [1] https://lore.kernel.org/lkml/54d4c322-cd6e-eefd-b161-2af2b56aae24@collabora… [2] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.… [3] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.… [4] https://lore.kernel.org/all/Y6Hc2d+7eTKs7AiH@x1n [5] https://lore.kernel.org/all/YyiDg79flhWoMDZB@gmail.com/ [6] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com/ Regards, Muhammad Usama Anjum Muhammad Usama Anjum (7): userfaultfd: Add UFFD WP Async support userfaultfd: Define dummy uffd_wp_range() userfaultfd: update documentation to describe UFFD_FEATURE_WP_ASYNC fs/proc/task_mmu: Implement IOCTL to get and optionally clear info about PTEs tools headers UAPI: Update linux/fs.h with the kernel sources mm/pagemap: add documentation of PAGEMAP_SCAN IOCTL selftests: mm: add pagemap ioctl tests Documentation/admin-guide/mm/pagemap.rst | 56 ++ Documentation/admin-guide/mm/userfaultfd.rst | 21 + fs/proc/task_mmu.c | 366 ++++++++ fs/userfaultfd.c | 25 +- include/linux/userfaultfd_k.h | 14 + include/uapi/linux/fs.h | 53 ++ include/uapi/linux/userfaultfd.h | 11 +- mm/memory.c | 27 +- tools/include/uapi/linux/fs.h | 53 ++ tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 4 +- tools/testing/selftests/mm/config | 1 + tools/testing/selftests/mm/pagemap_ioctl.c | 920 +++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 4 + 14 files changed, 1549 insertions(+), 7 deletions(-) create mode 100644 tools/testing/selftests/mm/pagemap_ioctl.c mode change 100644 => 100755 tools/testing/selftests/mm/run_vmtests.sh -- 2.39.2

2 years, 1 month

6
29
0 0

[PATCH 3/3] selftests/mm: Set overcommit_policy as OVERCOMMIT_ALWAYS

by Chaitanya S Prakash

The kernel's default behaviour is to obstruct the allocation of high virtual address as it handles memory overcommit in a heuristic manner. Setting the parameter as OVERCOMMIT_ALWAYS, ensures kernel isn't susceptible to the availability of a platform's physical memory when denying a memory allocation request. Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: David Hildenbrand <david(a)redhat.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: linux-mm(a)kvack.org Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Signed-off-by: Chaitanya S Prakash <chaitanyas.prakash(a)arm.com> --- tools/testing/selftests/mm/run_vmtests.sh | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 8984e0bb58c7..c0f93b668c0c 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -220,7 +220,15 @@ CATEGORY="mremap" run_test ./mremap_test CATEGORY="hugetlb" run_test ./thuge-gen if [ $VADDR64 -ne 0 ]; then + + # set overcommit_policy as OVERCOMMIT_ALWAYS so that kernel + # allows high virtual address allocation requests independent + # of platform's physical memory. + + prev_policy=$(cat /proc/sys/vm/overcommit_memory) + echo 1 > /proc/sys/vm/overcommit_memory CATEGORY="hugevm" run_test ./virtual_address_range + echo $prev_policy > /proc/sys/vm/overcommit_memory # virtual address 128TB switch test CATEGORY="hugevm" run_test ./va_128TBswitch.sh -- 2.30.2

2 years, 1 month

1
0
0 0

[PATCH 2/3] selftests/mm: Change NR_CHUNKS_HIGH for aarch64

by Chaitanya S Prakash

Although there is a provision for 52 bit VA on arm64 platform, it remains unutilised and higher addresses are not allocated. In order to accommodate 4PB [2^52] virtual address space where supported, NR_CHUNKS_HIGH is changed accordingly. Array holding addresses is changed from static allocation to dynamic allocation to accommodate its voluminous nature which otherwise might overflow the stack. Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: David Hildenbrand <david(a)redhat.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: linux-mm(a)kvack.org Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Signed-off-by: Chaitanya S Prakash <chaitanyas.prakash(a)arm.com> --- tools/testing/selftests/mm/virtual_address_range.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index 50564512c5ee..bae0ceaf95b1 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -36,13 +36,15 @@ * till it reaches 512TB. One with size 128TB and the * other being 384TB. * - * On Arm64 the address space is 256TB and no high mappings - * are supported so far. + * On Arm64 the address space is 256TB and support for + * high mappings up to 4PB virtual address space has + * been added. */ #define NR_CHUNKS_128TB ((128 * SZ_1TB) / MAP_CHUNK_SIZE) /* Number of chunks for 128TB */ #define NR_CHUNKS_256TB (NR_CHUNKS_128TB * 2UL) #define NR_CHUNKS_384TB (NR_CHUNKS_128TB * 3UL) +#define NR_CHUNKS_3840TB (NR_CHUNKS_128TB * 30UL) #define ADDR_MARK_128TB (1UL << 47) /* First address beyond 128TB */ #define ADDR_MARK_256TB (1UL << 48) /* First address beyond 256TB */ @@ -51,7 +53,7 @@ #define HIGH_ADDR_MARK ADDR_MARK_256TB #define HIGH_ADDR_SHIFT 49 #define NR_CHUNKS_LOW NR_CHUNKS_256TB -#define NR_CHUNKS_HIGH 0 +#define NR_CHUNKS_HIGH NR_CHUNKS_3840TB #else #define HIGH_ADDR_MARK ADDR_MARK_128TB #define HIGH_ADDR_SHIFT 48 @@ -101,7 +103,7 @@ static int validate_lower_address_hint(void) int main(int argc, char *argv[]) { char *ptr[NR_CHUNKS_LOW]; - char *hptr[NR_CHUNKS_HIGH]; + char **hptr; char *hint; unsigned long i, lchunks, hchunks; @@ -119,6 +121,9 @@ int main(int argc, char *argv[]) return 1; } lchunks = i; + hptr = (char **) calloc(NR_CHUNKS_HIGH, sizeof(char *)); + if (hptr == NULL) + return 1; for (i = 0; i < NR_CHUNKS_HIGH; i++) { hint = hind_addr(); @@ -139,5 +144,6 @@ int main(int argc, char *argv[]) for (i = 0; i < hchunks; i++) munmap(hptr[i], MAP_CHUNK_SIZE); + free(hptr); return 0; } -- 2.30.2

2 years, 1 month

1
0
0 0

[PATCH 1/3] selftests/mm: Change MAP_CHUNK_SIZE

by Chaitanya S Prakash

mmap() fails to allocate 16GB virtual space chunk, skipping both low and high VA range iterations. Hence, reduce MAP_CHUNK_SIZE to 1GB and update relevant macros as required. Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: David Hildenbrand <david(a)redhat.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: linux-mm(a)kvack.org Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Signed-off-by: Chaitanya S Prakash <chaitanyas.prakash(a)arm.com> --- tools/testing/selftests/mm/virtual_address_range.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index c0592646ed93..50564512c5ee 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -15,11 +15,15 @@ /* * Maximum address range mapped with a single mmap() - * call is little bit more than 16GB. Hence 16GB is + * call is little bit more than 1GB. Hence 1GB is * chosen as the single chunk size for address space * mapping. */ -#define MAP_CHUNK_SIZE 17179869184UL /* 16GB */ + +#define SZ_1GB (1024 * 1024 * 1024UL) +#define SZ_1TB (1024 * 1024 * 1024 * 1024UL) + +#define MAP_CHUNK_SIZE SZ_1GB /* * Address space till 128TB is mapped without any hint @@ -36,7 +40,7 @@ * are supported so far. */ -#define NR_CHUNKS_128TB 8192UL /* Number of 16GB chunks for 128TB */ +#define NR_CHUNKS_128TB ((128 * SZ_1TB) / MAP_CHUNK_SIZE) /* Number of chunks for 128TB */ #define NR_CHUNKS_256TB (NR_CHUNKS_128TB * 2UL) #define NR_CHUNKS_384TB (NR_CHUNKS_128TB * 3UL) -- 2.30.2

2 years, 1 month

1
0
0 0

[PATCH rcu v2 00/10] RCU torture test and tool updates for v6.4

by Boqun Feng

Hi, I of course took the opportunity at my first time to make a mistake: two patches were missing in v1.. please note that patch #9 and #10 are newly added. Previous version: v1: https://lore.kernel.org/rcu/20230315235454.2993-1-boqun.feng@gmail.com/ Changes since v1: * Add two missing patches. * Fix checkpatch warnings. You will also be able to find the series at: https://github.com/fbq/linux rcu/rcutorture.2023.03.20a top commit is: 6bc6e6b27524 List of changes: Bhaskar Chowdhury (1): tools: rcu: Add usage function and check for argument Paul E. McKenney (7): rcutorture: Add test_nmis module parameter rcutorture: Set CONFIG_BOOTPARAM_HOTPLUG_CPU0 to offline CPU 0 rcutorture: Make scenario TREE04 enable lazy call_rcu() torture: Permit kvm-again.sh --duration to default to previous run torture: Enable clocksource watchdog with "tsc=watchdog" rcuscale: Move shutdown from wait_event() to wait_event_idle() refscale: Move shutdown from wait_event() to wait_event_idle() Yue Hu (1): rcutorture: Eliminate variable n_rcu_torture_boost_rterror Zqiang (1): rcutorture: Create nocb kthreads only when testing rcu in CONFIG_RCU_NOCB_CPU=y kernels kernel/rcu/rcuscale.c | 7 ++- kernel/rcu/rcutorture.c | 49 +++++++++++++++---- kernel/rcu/refscale.c | 2 +- tools/rcu/extract-stall.sh | 26 +++++++--- .../selftests/rcutorture/bin/kvm-again.sh | 2 +- .../selftests/rcutorture/bin/torture.sh | 6 +-- .../selftests/rcutorture/configs/rcu/TREE01 | 1 + .../selftests/rcutorture/configs/rcu/TREE04 | 1 + 8 files changed, 69 insertions(+), 25 deletions(-) mode change 100644 => 100755 tools/rcu/extract-stall.sh -- 2.38.1

2 years, 1 month

1
10
0 0

[PATCH net-next v2 0/5] tls: implement key updates for TLS1.3

by Sabrina Dubroca

This adds support for receiving KeyUpdate messages (RFC 8446, 4.6.3 [1]). A sender transmits a KeyUpdate message and then changes its TX key. The receiver should react by updating its RX key before processing the next message. This patchset implements key updates by: 1. pausing decryption when a KeyUpdate message is received, to avoid attempting to use the old key to decrypt a record encrypted with the new key 2. returning -EKEYEXPIRED to syscalls that cannot receive the KeyUpdate message, until the rekey has been performed by userspace 3. passing the KeyUpdate message to userspace as a control message 4. allowing updates of the crypto_info via the TLS_TX/TLS_RX setsockopts This API has been tested with gnutls to make sure that it allows userspace libraries to implement key updates [2]. Thanks to Frantisek Krenzelok <fkrenzel(a)redhat.com> for providing the implementation in gnutls and testing the kernel patches. Note: in a future series, I'll clean up tls_set_sw_offload and eliminate the per-cipher copy-paste using tls_cipher_size_desc. [1] https://www.rfc-editor.org/rfc/rfc8446#section-4.6.3 [2] https://gitlab.com/gnutls/gnutls/-/merge_requests/1625 Changes in v2 use reverse xmas tree ordering in tls_set_sw_offload and do_tls_setsockopt_conf turn the alt_crypto_info into an else if selftests: add rekey_fail test Vadim suggested simplifying tls_set_sw_offload by copying the new crypto_info in the context in do_tls_setsockopt_conf, and then detecting the rekey in tls_set_sw_offload based on whether the iv was already set, but I don't think we can have a common error path (otherwise we'd free the aead etc on rekey failure). I decided instead to reorganize tls_set_sw_offload so that the context is unmodified until we know the rekey cannot fail. Some fields will be touched during the rekey, but they will be set to the same value they had before the rekey (prot->rec_seq_size, etc). Apoorv suggested to name the struct tls_crypto_info_keys "tls13" rather than "tls12". Since we're using the same crypto_info data for TLS1.3 as for 1.2, even if the tests only run for TLS1.3, I'd rather keep the "tls12" name, in case we end up adding a "tls13_crypto_info_aes_gcm_128" type in the future. Kuniyuki and Apoorv also suggested preventing rekeys on RX when we haven't received a matching KeyUpdate message, but I'd rather let userspace handle this and have a symmetric API between TX and RX on the kernel side. It's a bit of a foot-gun, but we can't really stop a broken userspace from rolling back the rec_seq on an existing crypto_info either, and that seems like a worse possible breakage. Sabrina Dubroca (5): tls: remove tls_context argument from tls_set_sw_offload tls: block decryption when a rekey is pending tls: implement rekey for TLS1.3 selftests: tls: add key_generation argument to tls_crypto_info_init selftests: tls: add rekey tests include/net/tls.h | 4 + net/tls/tls.h | 3 +- net/tls/tls_device.c | 2 +- net/tls/tls_main.c | 37 +++- net/tls/tls_sw.c | 189 +++++++++++++---- tools/testing/selftests/net/tls.c | 336 +++++++++++++++++++++++++++++- 6 files changed, 511 insertions(+), 60 deletions(-) -- 2.38.1

2 years, 1 month

2
20
0 0

[PATCH v2 00/41] RPCSEC GSS krb5 enhancements

by Chuck Lever

The purpose of this series is to improve/harden the security provided by the Linux kernel's RPCSEC GSS Kerberos 5 mechanism. There are lots of clean-ups in this series, but the pertinent feature is the addition of a clean deprecation path for the DES- and SHA1-based encryption types in accordance with Internet BCPs. This series disables DES-based enctypes by default, provides a mechanism for disabling SHA1-based enctypes, and introduces two modern enctypes that do not use deprecated crypto algorithms. Not only does that improve security for Kerberos 5 users, but it also prepares SunRPC for eventually switching to a shared common kernel Kerberos 5 implementation, which surely will not implement any deprecated encryption types (in particular, DES-based ones). Today, MIT supports both of the newly-introduced enctypes, but Heimdal does not appear to. Thus distributions can enable and disable kernel enctype support to match the set of enctypes supported in their user space Kerberos libraries. Scott has been kicking the tires -- we've found no regressions with the current SHA1-based enctypes, while the new ones are disabled by default until we have an opportunity for interop testing. The KUnit tests for the new enctypes pass and this implementation successfully interoperates with itself using these enctypes. Therefore I believe it to be safe to merge. When this series gets merged, the Linux NFS community should select and announce a date-certain for removal of SunRPC's DES-based enctype code. --- Changes since v1: - Addressed Simo's NAK on "SUNRPC: Improve Kerberos confounder generation" - Added Cc: linux-kselftest@ for review of the KUnit-related patches Chuck Lever (41): SUNRPC: Add header ifdefs to linux/sunrpc/gss_krb5.h SUNRPC: Remove .blocksize field from struct gss_krb5_enctype SUNRPC: Remove .conflen field from struct gss_krb5_enctype SUNRPC: Improve Kerberos confounder generation SUNRPC: Obscure Kerberos session key SUNRPC: Refactor set-up for aux_cipher SUNRPC: Obscure Kerberos encryption keys SUNRPC: Obscure Kerberos signing keys SUNRPC: Obscure Kerberos integrity keys SUNRPC: Refactor the GSS-API Per Message calls in the Kerberos mechanism SUNRPC: Remove another switch on ctx->enctype SUNRPC: Add /proc/net/rpc/gss_krb5_enctypes file NFSD: Replace /proc/fs/nfsd/supported_krb5_enctypes with a symlink SUNRPC: Replace KRB5_SUPPORTED_ENCTYPES macro SUNRPC: Enable rpcsec_gss_krb5.ko to be built without CRYPTO_DES SUNRPC: Remove ->encrypt and ->decrypt methods from struct gss_krb5_enctype SUNRPC: Rename .encrypt_v2 and .decrypt_v2 methods SUNRPC: Hoist KDF into struct gss_krb5_enctype SUNRPC: Clean up cipher set up for v1 encryption types SUNRPC: Parametrize the key length passed to context_v2_alloc_cipher() SUNRPC: Add new subkey length fields SUNRPC: Refactor CBC with CTS into helpers SUNRPC: Add gk5e definitions for RFC 8009 encryption types SUNRPC: Add KDF-HMAC-SHA2 SUNRPC: Add RFC 8009 encryption and decryption functions SUNRPC: Advertise support for RFC 8009 encryption types SUNRPC: Support the Camellia enctypes SUNRPC: Add KDF_FEEDBACK_CMAC SUNRPC: Advertise support for the Camellia encryption types SUNRPC: Move remaining internal definitions to gss_krb5_internal.h SUNRPC: Add KUnit tests for rpcsec_krb5.ko SUNRPC: Export get_gss_krb5_enctype() SUNRPC: Add KUnit tests RFC 3961 Key Derivation SUNRPC: Add Kunit tests for RFC 3962-defined encryption/decryption SUNRPC: Add KDF KUnit tests for the RFC 6803 encryption types SUNRPC: Add checksum KUnit tests for the RFC 6803 encryption types SUNRPC: Add encryption KUnit tests for the RFC 6803 encryption types SUNRPC: Add KDF-HMAC-SHA2 Kunit tests SUNRPC: Add RFC 8009 checksum KUnit tests SUNRPC: Add RFC 8009 encryption KUnit tests SUNRPC: Add encryption self-tests fs/nfsd/nfsctl.c | 74 +- include/linux/sunrpc/gss_krb5.h | 196 +-- include/linux/sunrpc/gss_krb5_enctypes.h | 41 - net/sunrpc/.kunitconfig | 30 + net/sunrpc/Kconfig | 96 +- net/sunrpc/auth_gss/Makefile | 2 + net/sunrpc/auth_gss/auth_gss.c | 17 + net/sunrpc/auth_gss/gss_krb5_crypto.c | 656 +++++-- net/sunrpc/auth_gss/gss_krb5_internal.h | 232 +++ net/sunrpc/auth_gss/gss_krb5_keys.c | 416 ++++- net/sunrpc/auth_gss/gss_krb5_mech.c | 730 +++++--- net/sunrpc/auth_gss/gss_krb5_seal.c | 122 +- net/sunrpc/auth_gss/gss_krb5_seqnum.c | 2 + net/sunrpc/auth_gss/gss_krb5_test.c | 2040 ++++++++++++++++++++++ net/sunrpc/auth_gss/gss_krb5_unseal.c | 63 +- net/sunrpc/auth_gss/gss_krb5_wrap.c | 124 +- net/sunrpc/auth_gss/svcauth_gss.c | 65 + 17 files changed, 4001 insertions(+), 905 deletions(-) delete mode 100644 include/linux/sunrpc/gss_krb5_enctypes.h create mode 100644 net/sunrpc/.kunitconfig create mode 100644 net/sunrpc/auth_gss/gss_krb5_internal.h create mode 100644 net/sunrpc/auth_gss/gss_krb5_test.c -- Chuck Lever

2 years, 1 month

8
64
0 0

[PATCH v2 0/6] use canonical ftrace path whenever possible

by Ross Zwisler

Changes in v2: * Dropped patches which were pulled into maintainer trees. * Split BPF patches out into another series targeting bpf-next. * trace-agent now falls back to debugfs if tracefs isn't present. * Added Acked-by from mst(a)redhat.com to series. * Added a typo fixup for the virtio-trace README. Steven, assuming there are no objections, would you feel comfortable taking this series through your tree? --- The canonical location for the tracefs filesystem is at /sys/kernel/tracing. But, from Documentation/trace/ftrace.rst: Before 4.1, all ftrace tracing control files were within the debugfs file system, which is typically located at /sys/kernel/debug/tracing. For backward compatibility, when mounting the debugfs file system, the tracefs file system will be automatically mounted at: /sys/kernel/debug/tracing There are many places where this older debugfs path is still used in code comments, selftests, examples and tools, so let's update them to avoid confusion. I've broken up the series as best I could by maintainer or directory, and I've only sent people the patches that I think they care about to avoid spamming everyone. Ross Zwisler (6): tracing: always use canonical ftrace path selftests: use canonical ftrace path leaking_addresses: also skip canonical ftrace path tools/kvm_stat: use canonical ftrace path tools/virtio: use canonical ftrace path tools/virtio: fix typo in README instructions include/linux/kernel.h | 2 +- include/linux/tracepoint.h | 4 ++-- kernel/trace/Kconfig | 20 +++++++++---------- kernel/trace/kprobe_event_gen_test.c | 2 +- kernel/trace/ring_buffer.c | 2 +- kernel/trace/synth_event_gen_test.c | 2 +- kernel/trace/trace.c | 2 +- samples/user_events/example.c | 4 ++-- scripts/leaking_addresses.pl | 1 + scripts/tracing/draw_functrace.py | 6 +++--- tools/kvm/kvm_stat/kvm_stat | 2 +- tools/lib/api/fs/tracing_path.c | 4 ++-- .../testing/selftests/user_events/dyn_test.c | 2 +- .../selftests/user_events/ftrace_test.c | 10 +++++----- .../testing/selftests/user_events/perf_test.c | 8 ++++---- tools/testing/selftests/vm/protection_keys.c | 4 ++-- tools/tracing/latency/latency-collector.c | 2 +- tools/virtio/virtio-trace/README | 4 ++-- tools/virtio/virtio-trace/trace-agent.c | 12 +++++++---- 19 files changed, 49 insertions(+), 44 deletions(-) -- 2.39.1.637.g21b0678d19-goog

2 years, 1 month

5
8
0 0

[PATCH net-next 1/2] net-zerocopy: Reduce compound page head access

by Coco Li

From: Xiaoyan Li <lixiaoyan(a)google.com> When compound pages are enabled, although the mm layer still returns an array of page pointers, a subset (or all) of them may have the same page head since a max 180kb skb can span 2 hugepages if it is on the boundary, be a mix of pages and 1 hugepage, or fit completely in a hugepage. Instead of referencing page head on all page pointers, use page length arithmetic to only call page head when referencing a known different page head to avoid touching a cold cacheline. Tested: See next patch with changes to tcp_mmap Correntess: On a pair of separate hosts as send with MSG_ZEROCOPY will force a copy on tx if using loopback alone, check that the SHA on the message sent is equivalent to checksum on the message received, since the current program already checks for the length. echo 1024 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages ./tcp_mmap -s -z ./tcp_mmap -H $DADDR -z SHA256 is correct received 2 MB (100 % mmap'ed) in 0.005914 s, 2.83686 Gbit cpu usage user:0.001984 sys:0.000963, 1473.5 usec per MB, 10 c-switches Performance: Run neper between adjacent hosts with the same config tcp_stream -Z --skip-rx-copy -6 -T 20 -F 1000 --stime-use-proc --test-length=30 Before patch: stime_end=37.670000 After patch: stime_end=30.310000 Signed-off-by: Coco Li <lixiaoyan(a)google.com> --- net/core/datagram.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/net/core/datagram.c b/net/core/datagram.c index e4ff2db40c98..5662dff3d381 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -622,12 +622,12 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, frag = skb_shinfo(skb)->nr_frags; while (length && iov_iter_count(from)) { + struct page *head, *last_head = NULL; struct page *pages[MAX_SKB_FRAGS]; - struct page *last_head = NULL; + int refs, order, n = 0; size_t start; ssize_t copied; unsigned long truesize; - int refs, n = 0; if (frag == MAX_SKB_FRAGS) return -EMSGSIZE; @@ -650,9 +650,17 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); } + + head = compound_head(pages[n]); + order = compound_order(head); + for (refs = 0; copied != 0; start = 0) { int size = min_t(int, copied, PAGE_SIZE - start); - struct page *head = compound_head(pages[n]); + + if (pages[n] - head > (1UL << order) - 1) { + head = compound_head(pages[n]); + order = compound_order(head); + } start += (pages[n] - head) << PAGE_SHIFT; copied -= size; -- 2.40.0.rc1.284.g88254d51c5-goog

2 years, 1 month

3
3
0 0

[PATCH mm-unstable v1] selftests/vm: cow: Add COW tests for collapsing of PTE-mapped anon THP

by David Hildenbrand

Currently, anonymous PTE-mapped THPs cannot be collapsed in-place: collapsing (e.g., via MADV_COLLAPSE) implies allocating a fresh THP and mapping that new THP via a PMD: as it's a fresh anon THP, it will get the exclusive flag set on the head page and everybody is happy. However, if the kernel would ever support in-place collapse of anonymous THPs (replacing a page table mapping each sub-page of a THP via PTEs with a single PMD mapping the complete THP), exclusivity information stored for each sub-page would have to be collapsed accordingly: (1) All PTEs map !exclusive anon sub-pages: the in-place collapsed THP must not not have the exclusive flag set on the head page mapped by the PMD. This is the easiest case to handle ("simply don't set any exclusive flags"). (2) All PTEs map exclusive anon sub-pages: when collapsing, we have to clear the exclusive flag from all tail pages and only leave the exclusive flag set for the head page. Otherwise, fork() after collapse would not clear the exclusive flags from the tail pages and we'd be in trouble once PTE-mapping the shared THP when writing to shared tail pages that still have the exclusive flag set. This would effectively revert what the PTE-mapping code does when propagating the exclusive flag to all sub-pages. (3) PTEs map a mixture of exclusive and !exclusive anon sub-pages (can happen e.g., due to MADV_DONTFORK before fork()). We must not collapse the THP in-place, otherwise bad things may happen: the exclusive flags of sub-pages would get ignored and the exclusive flag of the head page would get used instead. Now that we have MADV_COLLAPSE in place to trigger collapsing a THP, let's add some test cases that would bail out early, if we'd voluntarily/accidantially unlock in-place collapse for anon THPs and forget about taking proper care of exclusive flags. Running the test on a kernel with MADV_COLLAPSE support: # [INFO] Anonymous THP tests # [RUN] Basic COW after fork() when collapsing before fork() ok 169 No leak from parent into child # [RUN] Basic COW after fork() when collapsing after fork() (fully shared) ok 170 # SKIP MADV_COLLAPSE failed: Invalid argument # [RUN] Basic COW after fork() when collapsing after fork() (lower shared) ok 171 No leak from parent into child # [RUN] Basic COW after fork() when collapsing after fork() (upper shared) ok 172 No leak from parent into child For now, MADV_COLLAPSE always seems to fail if all PTEs map shared sub-pages. Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Hugh Dickins <hughd(a)google.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Nadav Amit <nadav.amit(a)gmail.com> Cc: Zach O'Keefe <zokeefe(a)google.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Signed-off-by: David Hildenbrand <david(a)redhat.com> --- A patch from Hugh made me explore the wonderful world of in-place collapse of THP, and I was briefly concerned that it would apply to anon THP as well. After thinking about it a bit, I decided to add test cases, to better be safe than sorry in any case, and to document how PG_anon_exclusive is to be handled in that case. --- tools/testing/selftests/vm/cow.c | 228 +++++++++++++++++++++++++++++++ 1 file changed, 228 insertions(+) diff --git a/tools/testing/selftests/vm/cow.c b/tools/testing/selftests/vm/cow.c index 26f6ea3079e2..16216d893d96 100644 --- a/tools/testing/selftests/vm/cow.c +++ b/tools/testing/selftests/vm/cow.c @@ -30,6 +30,10 @@ #include "../kselftest.h" #include "vm_util.h" +#ifndef MADV_COLLAPSE +#define MADV_COLLAPSE 25 +#endif + static size_t pagesize; static int pagemap_fd; static size_t thpsize; @@ -1178,6 +1182,228 @@ static int tests_per_anon_test_case(void) return tests; } +enum anon_thp_collapse_test { + ANON_THP_COLLAPSE_UNSHARED, + ANON_THP_COLLAPSE_FULLY_SHARED, + ANON_THP_COLLAPSE_LOWER_SHARED, + ANON_THP_COLLAPSE_UPPER_SHARED, +}; + +static void do_test_anon_thp_collapse(char *mem, size_t size, + enum anon_thp_collapse_test test) +{ + struct comm_pipes comm_pipes; + char buf; + int ret; + + ret = setup_comm_pipes(&comm_pipes); + if (ret) { + ksft_test_result_fail("pipe() failed\n"); + return; + } + + /* + * Trigger PTE-mapping the THP by temporarily mapping a single subpage + * R/O, such that we can try collapsing it later. + */ + ret = mprotect(mem + pagesize, pagesize, PROT_READ); + if (ret) { + ksft_test_result_fail("mprotect() failed\n"); + goto close_comm_pipes; + } + ret = mprotect(mem + pagesize, pagesize, PROT_READ | PROT_WRITE); + if (ret) { + ksft_test_result_fail("mprotect() failed\n"); + goto close_comm_pipes; + } + + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + /* Collapse before actually COW-sharing the page. */ + ret = madvise(mem, size, MADV_COLLAPSE); + if (ret) { + ksft_test_result_skip("MADV_COLLAPSE failed: %s\n", + strerror(errno)); + goto close_comm_pipes; + } + break; + case ANON_THP_COLLAPSE_FULLY_SHARED: + /* COW-share the full PTE-mapped THP. */ + break; + case ANON_THP_COLLAPSE_LOWER_SHARED: + /* Don't COW-share the upper part of the THP. */ + ret = madvise(mem + size / 2, size / 2, MADV_DONTFORK); + if (ret) { + ksft_test_result_fail("MADV_DONTFORK failed\n"); + goto close_comm_pipes; + } + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + /* Don't COW-share the lower part of the THP. */ + ret = madvise(mem, size / 2, MADV_DONTFORK); + if (ret) { + ksft_test_result_fail("MADV_DONTFORK failed\n"); + goto close_comm_pipes; + } + break; + default: + assert(false); + } + + ret = fork(); + if (ret < 0) { + ksft_test_result_fail("fork() failed\n"); + goto close_comm_pipes; + } else if (!ret) { + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + case ANON_THP_COLLAPSE_FULLY_SHARED: + exit(child_memcmp_fn(mem, size, &comm_pipes)); + break; + case ANON_THP_COLLAPSE_LOWER_SHARED: + exit(child_memcmp_fn(mem, size / 2, &comm_pipes)); + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + exit(child_memcmp_fn(mem + size / 2, size / 2, + &comm_pipes)); + break; + default: + assert(false); + } + } + + while (read(comm_pipes.child_ready[0], &buf, 1) != 1) + ; + + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + case ANON_THP_COLLAPSE_LOWER_SHARED: + /* + * Revert MADV_DONTFORK such that we merge the VMAs and are + * able to actually collapse. + */ + ret = madvise(mem, size, MADV_DOFORK); + if (ret) { + ksft_test_result_fail("MADV_DOFORK failed\n"); + write(comm_pipes.parent_ready[1], "0", 1); + wait(&ret); + goto close_comm_pipes; + } + /* FALLTHROUGH */ + case ANON_THP_COLLAPSE_FULLY_SHARED: + /* Collapse before anyone modified the COW-shared page. */ + ret = madvise(mem, size, MADV_COLLAPSE); + if (ret) { + ksft_test_result_skip("MADV_COLLAPSE failed: %s\n", + strerror(errno)); + write(comm_pipes.parent_ready[1], "0", 1); + wait(&ret); + goto close_comm_pipes; + } + break; + default: + assert(false); + } + + /* Modify the page. */ + memset(mem, 0xff, size); + write(comm_pipes.parent_ready[1], "0", 1); + + wait(&ret); + if (WIFEXITED(ret)) + ret = WEXITSTATUS(ret); + else + ret = -EINVAL; + + ksft_test_result(!ret, "No leak from parent into child\n"); +close_comm_pipes: + close_comm_pipes(&comm_pipes); +} + +static void test_anon_thp_collapse_unshared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_UNSHARED); +} + +static void test_anon_thp_collapse_fully_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_FULLY_SHARED); +} + +static void test_anon_thp_collapse_lower_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_LOWER_SHARED); +} + +static void test_anon_thp_collapse_upper_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_UPPER_SHARED); +} + +/* + * Test cases that are specific to anonymous THP: pages in private mappings + * that may get shared via COW during fork(). + */ +static const struct test_case anon_thp_test_cases[] = { + /* + * Basic COW test for fork() without any GUP when collapsing a THP + * before fork(). + * + * Re-mapping a PTE-mapped anon THP using a single PMD ("in-place + * collapse") might easily get COW handling wrong when not collapsing + * exclusivity information properly. + */ + { + "Basic COW after fork() when collapsing before fork()", + test_anon_thp_collapse_unshared, + }, + /* Basic COW test, but collapse after COW-sharing a full THP. */ + { + "Basic COW after fork() when collapsing after fork() (fully shared)", + test_anon_thp_collapse_fully_shared, + }, + /* + * Basic COW test, but collapse after COW-sharing the lower half of a + * THP. + */ + { + "Basic COW after fork() when collapsing after fork() (lower shared)", + test_anon_thp_collapse_lower_shared, + }, + /* + * Basic COW test, but collapse after COW-sharing the upper half of a + * THP. + */ + { + "Basic COW after fork() when collapsing after fork() (upper shared)", + test_anon_thp_collapse_upper_shared, + }, +}; + +static void run_anon_thp_test_cases(void) +{ + int i; + + if (!thpsize) + return; + + ksft_print_msg("[INFO] Anonymous THP tests\n"); + + for (i = 0; i < ARRAY_SIZE(anon_thp_test_cases); i++) { + struct test_case const *test_case = &anon_thp_test_cases[i]; + + ksft_print_msg("[RUN] %s\n", test_case->desc); + do_run_with_thp(test_case->fn, THP_RUN_PMD); + } +} + +static int tests_per_anon_thp_test_case(void) +{ + return thpsize ? 1 : 0; +} + typedef void (*non_anon_test_fn)(char *mem, const char *smem, size_t size); static void test_cow(char *mem, const char *smem, size_t size) @@ -1518,6 +1744,7 @@ int main(int argc, char **argv) ksft_print_header(); ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() + + ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() + ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case()); gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); @@ -1526,6 +1753,7 @@ int main(int argc, char **argv) ksft_exit_fail_msg("opening pagemap failed\n"); run_anon_test_cases(); + run_anon_thp_test_cases(); run_non_anon_test_cases(); err = ksft_get_fail_cnt(); -- 2.39.0

2 years, 1 month

2
2
0 0

[PATCH net-next v2 3/3] selftests: net: add SCM_PIDFD / SO_PEERPIDFD test

by Alexander Mikhalitsyn

Basic test to check consistency between: - SCM_CREDENTIALS and SCM_PIDFD - SO_PEERCRED and SO_PEERPIDFD Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Leon Romanovsky <leon(a)kernel.org> Cc: David Ahern <dsahern(a)kernel.org> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: Kees Cook <keescook(a)chromium.org> Cc: Christian Brauner <brauner(a)kernel.org> Cc: linux-kernel(a)vger.kernel.org Cc: netdev(a)vger.kernel.org Cc: linux-arch(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn(a)canonical.com> --- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/af_unix/Makefile | 3 +- .../testing/selftests/net/af_unix/scm_pidfd.c | 336 ++++++++++++++++++ 3 files changed, 339 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/net/af_unix/scm_pidfd.c diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index a6911cae368c..f2d23a1df596 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -25,6 +25,7 @@ reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack rxtimestamp +scm_pidfd sk_bind_sendto_listen sk_connect_zero_addr socket diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 1e4b397cece6..221c387a7d7f 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,3 +1,4 @@ -TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect +CFLAGS += $(KHDR_INCLUDES) +TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect scm_pidfd include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c new file mode 100644 index 000000000000..fa502510ee9e --- /dev/null +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <error.h> +#include <limits.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <linux/socket.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <sys/un.h> +#include <sys/signal.h> +#include <sys/types.h> +#include <sys/wait.h> + +#define clean_errno() (errno == 0 ? "None" : strerror(errno)) +#define log_err(MSG, ...) \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", __FILE__, __LINE__, \ + clean_errno(), ##__VA_ARGS__) + +#ifndef SCM_PIDFD +#define SCM_PIDFD 0x04 +#endif + +static pid_t client_pid; +static char sock_name[32]; + +static void die(int status) +{ + unlink(sock_name); + kill(client_pid, SIGTERM); + exit(status); +} + +static void child_die() +{ + kill(getppid(), SIGTERM); + exit(1); +} + +static int safe_int(const char *numstr, int *converted) +{ + char *err = NULL; + long sli; + + errno = 0; + sli = strtol(numstr, &err, 0); + if (errno == ERANGE && (sli == LONG_MAX || sli == LONG_MIN)) + return -ERANGE; + + if (errno != 0 && sli == 0) + return -EINVAL; + + if (err == numstr || *err != '\0') + return -EINVAL; + + if (sli > INT_MAX || sli < INT_MIN) + return -ERANGE; + + *converted = (int)sli; + return 0; +} + +static int char_left_gc(const char *buffer, size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (buffer[i] == ' ' || buffer[i] == '\t') + continue; + + return i; + } + + return 0; +} + +static int char_right_gc(const char *buffer, size_t len) +{ + int i; + + for (i = len - 1; i >= 0; i--) { + if (buffer[i] == ' ' || buffer[i] == '\t' || + buffer[i] == '\n' || buffer[i] == '\0') + continue; + + return i + 1; + } + + return 0; +} + +static char *trim_whitespace_in_place(char *buffer) +{ + buffer += char_left_gc(buffer, strlen(buffer)); + buffer[char_right_gc(buffer, strlen(buffer))] = '\0'; + return buffer; +} + +/* borrowed (with all helpers) from pidfd/pidfd_open_test.c */ +static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) +{ + int ret; + char path[512]; + FILE *f; + size_t n = 0; + pid_t result = -1; + char *line = NULL; + + snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", pidfd); + + f = fopen(path, "re"); + if (!f) + return -1; + + while (getline(&line, &n, f) != -1) { + char *numstr; + + if (strncmp(line, key, keylen)) + continue; + + numstr = trim_whitespace_in_place(line + 4); + ret = safe_int(numstr, &result); + if (ret < 0) + goto out; + + break; + } + +out: + free(line); + fclose(f); + return result; +} + +static int cmsg_check(int fd) +{ + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + struct iovec iov; + struct ucred *ucred = NULL; + int data = 0; + char control[CMSG_SPACE(sizeof(struct ucred)) + + CMSG_SPACE(sizeof(int))] = { 0 }; + int *pidfd = NULL; + pid_t parent_pid; + int err; + + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + err = recvmsg(fd, &msg, 0); + if (err < 0) { + log_err("recvmsg"); + return 1; + } + + if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_PIDFD) { + if (cmsg->cmsg_len < sizeof(*pidfd)) { + log_err("CMSG parse: SCM_PIDFD wrong len"); + return 1; + } + + pidfd = (void *)CMSG_DATA(cmsg); + } + + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_CREDENTIALS) { + if (cmsg->cmsg_len < sizeof(*ucred)) { + log_err("CMSG parse: SCM_CREDENTIALS wrong len"); + return 1; + } + + ucred = (void *)CMSG_DATA(cmsg); + } + } + + /* send(pfd, "x", sizeof(char), 0) */ + if (data != 'x') { + log_err("recvmsg: data corruption"); + return 1; + } + + if (!pidfd) { + log_err("CMSG parse: SCM_PIDFD not found"); + return 1; + } + + if (!ucred) { + log_err("CMSG parse: SCM_CREDENTIALS not found"); + return 1; + } + + /* pidfd from SCM_PIDFD should point to the parent process PID */ + parent_pid = + get_pid_from_fdinfo_file(*pidfd, "Pid:", sizeof("Pid:") - 1); + if (parent_pid != getppid()) { + log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + return 1; + } + + return 0; +} + +void client(struct sockaddr_un *listen_addr) +{ + int cfd; + socklen_t len; + struct ucred peer_cred; + int peer_pidfd; + pid_t peer_pid; + int on = 0; + + cfd = socket(AF_UNIX, SOCK_STREAM, 0); + if (cfd < 0) { + log_err("socket"); + child_die(); + } + + if (connect(cfd, (struct sockaddr *)listen_addr, + sizeof(*listen_addr)) != 0) { + log_err("connect"); + child_die(); + } + + on = 1; + if (setsockopt(cfd, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { + log_err("Failed to set SO_PASSCRED"); + child_die(); + } + + if (setsockopt(cfd, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { + log_err("Failed to set SO_PASSPIDFD"); + child_die(); + } + + if (cmsg_check(cfd)) { + log_err("cmsg_check failed"); + child_die(); + } + + len = sizeof(peer_cred); + if (getsockopt(cfd, SOL_SOCKET, SO_PEERCRED, &peer_cred, &len)) { + log_err("Failed to get SO_PEERCRED"); + child_die(); + } + + len = sizeof(peer_pidfd); + if (getsockopt(cfd, SOL_SOCKET, SO_PEERPIDFD, &peer_pidfd, &len)) { + log_err("Failed to get SO_PEERPIDFD"); + child_die(); + } + + /* pid from SO_PEERCRED should point to the parent process PID */ + if (peer_cred.pid != getppid()) { + log_err("Failed to get SO_PEERPIDFD"); + child_die(); + } + + peer_pid = get_pid_from_fdinfo_file(peer_pidfd, + "Pid:", sizeof("Pid:") - 1); + if (peer_pid != peer_cred.pid) { + log_err("Failed to get SO_PEERPIDFD"); + child_die(); + } +} + +int main(int argc, char **argv) +{ + int lfd, pfd; + int child_status = 0; + struct sockaddr_un listen_addr; + + lfd = socket(AF_UNIX, SOCK_STREAM, 0); + if (lfd < 0) { + perror("socket"); + exit(1); + } + + memset(&listen_addr, 0, sizeof(listen_addr)); + listen_addr.sun_family = AF_UNIX; + sprintf(sock_name, "scm_pidfd_%d", getpid()); + unlink(sock_name); + strcpy(listen_addr.sun_path, sock_name); + + if ((bind(lfd, (struct sockaddr *)&listen_addr, sizeof(listen_addr))) != + 0) { + perror("socket bind failed"); + exit(1); + } + + if (listen(lfd, 1) < 0) { + perror("listen"); + exit(1); + } + + client_pid = fork(); + if (client_pid < 0) { + perror("fork"); + exit(1); + } + + if (client_pid == 0) { + client(&listen_addr); + exit(0); + } + + pfd = accept(lfd, NULL, NULL); + if (pfd < 0) { + perror("accept"); + die(1); + } + + if (send(pfd, "x", sizeof(char), 0) < 0) { + perror("send"); + die(1); + } + + waitpid(client_pid, &child_status, 0); + die(WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); + die(0); +} \ No newline at end of file -- 2.34.1

2 years, 1 month

2
1
0 0

[PATCH v4 0/6] RISC-V Hardware Probing User Interface

by Evan Green

There's been a bunch of off-list discussions about this, including at Plumbers. The original plan was to do something involving providing an ISA string to userspace, but ISA strings just aren't sufficient for a stable ABI any more: in order to parse an ISA string users need the version of the specifications that the string is written to, the version of each extension (sometimes at a finer granularity than the RISC-V releases/versions encode), and the expected use case for the ISA string (ie, is it a U-mode or M-mode string). That's a lot of complexity to try and keep ABI compatible and it's probably going to continue to grow, as even if there's no more complexity in the specifications we'll have to deal with the various ISA string parsing oddities that end up all over userspace. Instead this patch set takes a very different approach and provides a set of key/value pairs that encode various bits about the system. The big advantage here is that we can clearly define what these mean so we can ensure ABI stability, but it also allows us to encode information that's unlikely to ever appear in an ISA string (see the misaligned access performance, for example). The resulting interface looks a lot like what arm64 and x86 do, and will hopefully fit well into something like ACPI in the future. The actual user interface is a syscall, with a vDSO function in front of it. The vDSO function can answer some queries without a syscall at all, and falls back to the syscall for cases it doesn't have answers to. Currently we prepopulate it with an array of answers for all keys and a CPU set of "all CPUs". This can be adjusted as necessary to provide fast answers to the most common queries. An example series in glibc exposing this syscall and using it in an ifunc selector for memcpy can be found at [1]. I'm about to send a v2 of that series out that incorporates the vDSO function. I was asked about the performance delta between this and something like sysfs. I created a small test program [2] and ran it on a Nezha D1 Allwinner board. Doing each operation 100000 times and dividing, these operations take the following amount of time: - open()+read()+close() of /sys/kernel/cpu_byteorder: 3.8us - access("/sys/kernel/cpu_byteorder", R_OK): 1.3us - riscv_hwprobe() vDSO and syscall: .0094us - riscv_hwprobe() vDSO with no syscall: 0.0091us These numbers get farther apart if we query multiple keys, as sysfs will scale linearly with the number of keys, where the dedicated syscall stays the same. To frame these numbers, I also did a tight fork/exec/wait loop, which I measured as 4.8ms. So doing 4 open/read/close operations is a delta of about 0.3%, versus a single vDSO call is a delta of essentially zero. [1] https://public-inbox.org/libc-alpha/20230206194819.1679472-1-evan@rivosinc.… [2] https://pastebin.com/x84NEKaS Changes in v4: - Used real types in syscall prototypes (Arnd) - Fixed static line break in do_riscv_hwprobe() (Conor) - Added newlines between documentation lists (Conor) - Crispen up size types to size_t, and cpu indices to int (Joe) - Fix copy_from_user() return logic bug (found via kselftests!) - Add __user to SYSCALL_DEFINE() to fix warning - More newlines in BASE_BEHAVIOR_IMA documentation (Conor) - Add newlines to CPUPERF_0 documentation (Conor) - Add UNSUPPORTED value (Conor) - Switched from DT to alternatives-based probing (Rob) - Crispen up cpu index type to always be int (Conor) - Fixed selftests commit description, no more tiny libc (Mark Brown) - Fixed selftest syscall prototype types to match v4. - Added a prototype to fix -Wmissing-prototype warning (lkp(a)intel.com) - Fixed rv32 build failure (lkp(a)intel.com) - Make vdso prototype match syscall types update Changes in v3: - Updated copyright date in cpufeature.h - Fixed typo in cpufeature.h comment (Conor) - Refactored functions so that kernel mode can query too, in preparation for the vDSO data population. - Changed the vendor/arch/imp IDs to return a value of -1 on mismatch rather than failing the whole call. - Const cpumask pointer in hwprobe_mid() - Embellished documentation WRT cpu_set and the returned values. - Renamed hwprobe_mid() to hwprobe_arch_id() (Conor) - Fixed machine ID doc warnings, changed elements to c:macro:. - Completed dangling unistd.h comment (Conor) - Fixed line breaks and minor logic optimization (Conor). - Use riscv_cached_mxxxid() (Conor) - Refactored base ISA behavior probe to allow kernel probing as well, in prep for vDSO data initialization. - Fixed doc warnings in IMA text list, use :c:macro:. - Have hwprobe_misaligned return int instead of long. - Constify cpumask pointer in hwprobe_misaligned() - Fix warnings in _PERF_O list documentation, use :c:macro:. - Move include cpufeature.h to misaligned patch. - Fix documentation mismatch for RISCV_HWPROBE_KEY_CPUPERF_0 (Conor) - Use for_each_possible_cpu() instead of NR_CPUS (Conor) - Break early in misaligned access iteration (Conor) - Increase MISALIGNED_MASK from 2 bits to 3 for possible UNSUPPORTED future value (Conor) - Introduced vDSO function Changes in v2: - Factored the move of struct riscv_cpuinfo to its own header - Changed the interface to look more like poll(). Rather than supplying key_offset and getting back an array of values with numerically contiguous keys, have the user pre-fill the key members of the array, and the kernel will fill in the corresponding values. For any key it doesn't recognize, it will set the key of that element to -1. This allows usermode to quickly ask for exactly the elements it cares about, and not get bogged down in a back and forth about newer keys that older kernels might not recognize. In other words, the kernel can communicate that it doesn't recognize some of the keys while still providing the data for the keys it does know. - Added a shortcut to the cpuset parameters that if a size of 0 and NULL is provided for the CPU set, the kernel will use a cpu mask of all online CPUs. This is convenient because I suspect most callers will only want to act on a feature if it's supported on all CPUs, and it's a headache to dynamically allocate an array of all 1s, not to mention a waste to have the kernel loop over all of the offline bits. - Fixed logic error in if(of_property_read_string...) that caused crash - Include cpufeature.h in cpufeature.h to avoid undeclared variable warning. - Added a _MASK define - Fix random checkpatch complaints - Updated the selftests to the new API and added some more. - Fixed indentation, comments in .S, and general checkpatch complaints. Evan Green (6): RISC-V: Move struct riscv_cpuinfo to new header RISC-V: Add a syscall for HW probing RISC-V: hwprobe: Add support for RISCV_HWPROBE_BASE_BEHAVIOR_IMA RISC-V: hwprobe: Support probing of misaligned access performance selftests: Test the new RISC-V hwprobe interface RISC-V: Add hwprobe vDSO function and data Documentation/riscv/hwprobe.rst | 86 +++++++ Documentation/riscv/index.rst | 1 + arch/riscv/Kconfig | 1 + arch/riscv/errata/thead/errata.c | 9 + arch/riscv/include/asm/alternative.h | 5 + arch/riscv/include/asm/cpufeature.h | 23 ++ arch/riscv/include/asm/hwprobe.h | 13 + arch/riscv/include/asm/syscall.h | 4 + arch/riscv/include/asm/vdso/data.h | 17 ++ arch/riscv/include/asm/vdso/gettimeofday.h | 8 + arch/riscv/include/uapi/asm/hwprobe.h | 37 +++ arch/riscv/include/uapi/asm/unistd.h | 9 + arch/riscv/kernel/alternative.c | 19 ++ arch/riscv/kernel/cpu.c | 8 +- arch/riscv/kernel/cpufeature.c | 3 + arch/riscv/kernel/smpboot.c | 1 + arch/riscv/kernel/sys_riscv.c | 225 +++++++++++++++++- arch/riscv/kernel/vdso.c | 6 - arch/riscv/kernel/vdso/Makefile | 2 + arch/riscv/kernel/vdso/hwprobe.c | 52 ++++ arch/riscv/kernel/vdso/sys_hwprobe.S | 15 ++ arch/riscv/kernel/vdso/vdso.lds.S | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/riscv/Makefile | 58 +++++ .../testing/selftests/riscv/hwprobe/Makefile | 10 + .../testing/selftests/riscv/hwprobe/hwprobe.c | 90 +++++++ .../selftests/riscv/hwprobe/sys_hwprobe.S | 12 + 27 files changed, 703 insertions(+), 13 deletions(-) create mode 100644 Documentation/riscv/hwprobe.rst create mode 100644 arch/riscv/include/asm/cpufeature.h create mode 100644 arch/riscv/include/asm/hwprobe.h create mode 100644 arch/riscv/include/asm/vdso/data.h create mode 100644 arch/riscv/include/uapi/asm/hwprobe.h create mode 100644 arch/riscv/kernel/vdso/hwprobe.c create mode 100644 arch/riscv/kernel/vdso/sys_hwprobe.S create mode 100644 tools/testing/selftests/riscv/Makefile create mode 100644 tools/testing/selftests/riscv/hwprobe/Makefile create mode 100644 tools/testing/selftests/riscv/hwprobe/hwprobe.c create mode 100644 tools/testing/selftests/riscv/hwprobe/sys_hwprobe.S -- 2.25.1

2 years, 1 month

2
2
0 0

[PATCH v2 00/11] clk: Add kunit tests for fixed rate and parent data

by Stephen Boyd

This patch series adds unit tests for the clk fixed rate basic type and the clk registration functions that use struct clk_parent_data. To get there, we add support for loading device tree overlays onto the live DTB along with probing platform drivers to bind to device nodes in the overlays. With this series, we're able to exercise some of the code in the common clk framework that uses devicetree lookups to find parents and the fixed rate clk code that scans device tree directly and creates clks. Please review. I Cced everyone to all the patches so they get the full context. I'm hoping I can take the whole pile through the clk tree as they almost all depend on each other. Changes from v1 (https://lore.kernel.org/r/20230302013822.1808711-1-sboyd@kernel.org): * Don't depend on UML, use unittest data approach to attach nodes * Introduce overlay loading API for KUnit * Move platform_device KUnit code to drivers/base/test * Use #define macros for constants shared between unit tests and overlays * Settle on "test" as a vendor prefix * Make KUnit wrappers have "_kunit" postfix Stephen Boyd (11): of: Load KUnit DTB from of_core_init() of: Add test managed wrappers for of_overlay_apply()/of_node_put() dt-bindings: vendor-prefixes: Add "test" vendor for KUnit and friends dt-bindings: test: Add KUnit empty node binding of: Add a KUnit test for overlays and test managed APIs platform: Add test managed platform_device/driver APIs dt-bindings: kunit: Add fixed rate clk consumer test clk: Add test managed clk provider/consumer APIs clk: Add KUnit tests for clk fixed rate basic type dt-bindings: clk: Add KUnit clk_parent_data test clk: Add KUnit tests for clks registered with struct clk_parent_data .../clock/test,clk-kunit-parent-data.yaml | 47 ++ .../kunit/test,clk-kunit-fixed-rate.yaml | 35 ++ .../bindings/test/test,kunit-empty.yaml | 30 ++ .../devicetree/bindings/vendor-prefixes.yaml | 2 + drivers/base/test/Makefile | 3 + drivers/base/test/platform_kunit-test.c | 108 +++++ drivers/base/test/platform_kunit.c | 186 +++++++ drivers/clk/.kunitconfig | 3 + drivers/clk/Kconfig | 7 + drivers/clk/Makefile | 9 +- drivers/clk/clk-fixed-rate_test.c | 299 ++++++++++++ drivers/clk/clk-fixed-rate_test.h | 8 + drivers/clk/clk_kunit.c | 219 +++++++++ drivers/clk/clk_parent_data_test.h | 10 + drivers/clk/clk_test.c | 459 +++++++++++++++++- drivers/clk/kunit_clk_fixed_rate_test.dtso | 19 + drivers/clk/kunit_clk_parent_data_test.dtso | 28 ++ drivers/of/.kunitconfig | 5 + drivers/of/Kconfig | 23 + drivers/of/Makefile | 7 + drivers/of/base.c | 182 +++++++ drivers/of/kunit.dtso | 10 + drivers/of/kunit_overlay_test.dtso | 9 + drivers/of/of_kunit.c | 123 +++++ drivers/of/of_private.h | 6 + drivers/of/of_test.c | 43 ++ drivers/of/overlay_test.c | 107 ++++ drivers/of/unittest.c | 101 +--- include/kunit/clk.h | 28 ++ include/kunit/of.h | 90 ++++ include/kunit/platform_device.h | 15 + 31 files changed, 2119 insertions(+), 102 deletions(-) create mode 100644 Documentation/devicetree/bindings/clock/test,clk-kunit-parent-data.yaml create mode 100644 Documentation/devicetree/bindings/kunit/test,clk-kunit-fixed-rate.yaml create mode 100644 Documentation/devicetree/bindings/test/test,kunit-empty.yaml create mode 100644 drivers/base/test/platform_kunit-test.c create mode 100644 drivers/base/test/platform_kunit.c create mode 100644 drivers/clk/clk-fixed-rate_test.c create mode 100644 drivers/clk/clk-fixed-rate_test.h create mode 100644 drivers/clk/clk_kunit.c create mode 100644 drivers/clk/clk_parent_data_test.h create mode 100644 drivers/clk/kunit_clk_fixed_rate_test.dtso create mode 100644 drivers/clk/kunit_clk_parent_data_test.dtso create mode 100644 drivers/of/.kunitconfig create mode 100644 drivers/of/kunit.dtso create mode 100644 drivers/of/kunit_overlay_test.dtso create mode 100644 drivers/of/of_kunit.c create mode 100644 drivers/of/of_test.c create mode 100644 drivers/of/overlay_test.c create mode 100644 include/kunit/clk.h create mode 100644 include/kunit/of.h create mode 100644 include/kunit/platform_device.h base-commit: fe15c26ee26efa11741a7b632e9f23b01aca4cc6 -- https://git.kernel.org/pub/scm/linux/kernel/git/clk/linux.git/ https://git.kernel.org/pub/scm/linux/kernel/git/sboyd/spmi.git

2 years, 1 month

4
18
0 0

BUG: selftests/net/tls: FAIL in sm4_ccm tests

by Mirsad Todorovac

Hi all, I don't know if this is expected result, so I am filing the bug report. Reports like this from tools/testing/selftests/net/tls: # RUN tls.13_sm4_ccm.sendfile ... # tls.c:323:sendfile:Expected ret (-1) == 0 (0) # sendfile: Test terminated by assertion # FAIL tls.13_sm4_ccm.sendfile not ok 251 tls.13_sm4_ccm.sendfile # RUN tls.13_sm4_ccm.send_then_sendfile ... # tls.c:323:send_then_sendfile:Expected ret (-1) == 0 (0) # send_then_sendfile: Test terminated by assertion # FAIL tls.13_sm4_ccm.send_then_sendfile not ok 252 tls.13_sm4_ccm.send_then_sendfile # RUN tls.13_sm4_ccm.multi_chunk_sendfile ... # tls.c:323:multi_chunk_sendfile:Expected ret (-1) == 0 (0) # multi_chunk_sendfile: Test terminated by assertion # FAIL tls.13_sm4_ccm.multi_chunk_sendfile not ok 253 tls.13_sm4_ccm.multi_chunk_sendfile Apparently, all are connected with sm4 hash ccm. (Please find the complete report attached in tls-6.3-rc3-1.log) The rest of the failed tests is as follows from this command: [marvin@pc-mtodorov linux_torvalds]$ grep -v '^#' ../kselftest-6.3-rc3-1.log | grep "not ok" not ok 2 selftests: alsa: pcm-test # TIMEOUT 45 seconds not ok 1 selftests: drivers/net/bonding: bond-arp-interval-causes-panic.sh # exit=1 not ok 2 selftests: drivers/net/bonding: bond-break-lacpdu-tx.sh # exit=1 not ok 1 selftests: filesystems/binderfs: binderfs_test # exit=1 not ok 1 selftests: ftrace: ftracetest # exit=1 not ok 1 selftests: gpio: gpio-mockup.sh # exit=1 not ok 1 selftests: intel_pstate: run.sh # TIMEOUT 45 seconds not ok 1 selftests: iommu: iommufd # exit=1 not ok 26 selftests: kvm: vmx_preemption_timer_test # exit=254 not ok 1 selftests: landlock: fs_test # exit=1 not ok 1 selftests: mincore: mincore_selftest # exit=1 not ok 2 selftests: mqueue: mq_perf_tests # TIMEOUT 45 seconds not ok 1 selftests: nci: nci_dev # exit=1 not ok 6 selftests: net: tls # exit=1 not ok 12 selftests: net: run_netsocktests # exit=1 not ok 28 selftests: net: udpgro_bench.sh # exit=255 not ok 29 selftests: net: udpgro.sh # exit=255 not ok 36 selftests: net: fcnal-test.sh # TIMEOUT 1500 seconds not ok 37 selftests: net: l2tp.sh # exit=2 not ok 45 selftests: net: icmp_redirect.sh # exit=1 not ok 49 selftests: net: txtimestamp.sh # exit=1 not ok 54 selftests: net: vrf_route_leaking.sh # exit=1 not ok 58 selftests: net: udpgro_fwd.sh # exit=1 not ok 59 selftests: net: udpgro_frglist.sh # exit=255 not ok 60 selftests: net: veth.sh # exit=1 not ok 67 selftests: net: srv6_end_dt46_l3vpn_test.sh # exit=1 not ok 68 selftests: net: srv6_end_dt4_l3vpn_test.sh # exit=1 not ok 82 selftests: net: rps_default_mask.sh # exit=1 not ok 85 selftests: net: test_ingress_egress_chaining.sh # exit=1 not ok 1 selftests: net/hsr: hsr_ping.sh # TIMEOUT 45 seconds not ok 3 selftests: net/mptcp: mptcp_join.sh # exit=1 not ok 3 selftests: netfilter: nft_nat.sh # exit=1 not ok 5 selftests: netfilter: conntrack_icmp_related.sh # exit=1 not ok 8 selftests: netfilter: nft_concat_range.sh # exit=1 not ok 14 selftests: netfilter: conntrack_tcp_unreplied.sh # exit=1 not ok 15 selftests: netfilter: conntrack_vrf.sh # exit=1 not ok 15 selftests: proc: read # exit=134 not ok 1 selftests: pstore: pstore_tests # exit=1 not ok 3 selftests: ptrace: vmaccess # exit=1 not ok 1 selftests: rlimits: rlimits-per-userns # exit=1 not ok 1 selftests: sgx: test_sgx # exit=1 not ok 2 selftests: splice: short_splice_read.sh # exit=3 not ok 1 selftests: tdx: tdx_guest_test # exit=1 not ok 3 selftests: mm: split_huge_page_test # exit=1 not ok 5 selftests: mm: mdwe_test # exit=1 [marvin@pc-mtodorov linux_torvalds]$ The environment is AlmaLinux 8.7 running 6.3-rc3 vanilla kernel with MGLRU, KMEMLEAK and CONFIG_DEBUG_KOBJECT=y enabled. Hw := LENOVO_MT_10TX_BU_Lenovo_FM_V530S-07ICB In case you are interested to debug this, I am available for additional diagnostics. As 45 bug reports might overwhelm me due to the overhead of bug submission, I will probably submit a bug or two at a time. Best regards, Mirsad -- Mirsad Goran Todorovac Sistem inženjer Grafički fakultet | Akademija likovnih umjetnosti Sveučilište u Zagrebu System engineer Faculty of Graphic Arts | Academy of Fine Arts University of Zagreb, Republic of Croatia

2 years, 1 month

3
2
0 0

[PATCH 00/14] Add iommufd physical device operations for replace and alloc hwpt

by Jason Gunthorpe

This is the basic functionality for iommufd to support iommufd_device_replace() and IOMMU_HWPT_ALLOC for physical devices. iommufd_device_replace() allows changing the HWPT associated with the device to a new IOAS or HWPT. Replace does this in way that failure leaves things unchanged, and utilizes the iommu iommu_group_replace_domain() API to allow the iommu driver to perform an optional non-disruptive change. IOMMU_HWPT_ALLOC allows HWPTs to be explicitly allocated by the user and used by attach or replace. At this point it isn't very useful since the HWPT is the same as the automatically managed HWPT from the IOAS. However a following series will allow userspace to customize the created HWPT. The implementation is complicated because we have to introduce some per-iommu_group memory in iommufd and redo how we think about multi-device groups to be more explicit. This solves all the locking problems in the prior attempts. This series is infrastructure work for the following series which: - Add replace for attach - Expose replace through VFIO APIs - Implement driver parameters for HWPT creation (nesting) Once review of this is complete I will keep it on a side branch and accumulate the following series when they are ready so we can have a stable base and make more incremental progress. When we have all the parts together to get a full implementation it can go to Linus. I have this on github: https://github.com/jgunthorpe/linux/commits/iommufd_hwpt Jason Gunthorpe (12): iommufd: Move isolated msi enforcement to iommufd_device_bind() iommufd: Add iommufd_group iommufd: Replace the hwpt->devices list with iommufd_group iommufd: Use the iommufd_group to avoid duplicate reserved groups and msi setup iommufd: Make sw_msi_start a group global iommufd: Move putting a hwpt to a helper function iommufd: Add enforced_cache_coherency to iommufd_hw_pagetable_alloc() iommufd: Add iommufd_device_replace() iommufd: Make destroy_rwsem use a lock class per object type iommufd: Add IOMMU_HWPT_ALLOC iommufd/selftest: Return the real idev id from selftest mock_domain iommufd/selftest: Add a selftest for IOMMU_HWPT_ALLOC Nicolin Chen (2): iommu: Introduce a new iommu_group_replace_domain() API iommufd/selftest: Test iommufd_device_replace() drivers/iommu/iommu-priv.h | 10 + drivers/iommu/iommu.c | 30 ++ drivers/iommu/iommufd/device.c | 482 +++++++++++++----- drivers/iommu/iommufd/hw_pagetable.c | 96 +++- drivers/iommu/iommufd/io_pagetable.c | 5 +- drivers/iommu/iommufd/iommufd_private.h | 44 +- drivers/iommu/iommufd/iommufd_test.h | 7 + drivers/iommu/iommufd/main.c | 17 +- drivers/iommu/iommufd/selftest.c | 40 ++ include/linux/iommufd.h | 1 + include/uapi/linux/iommufd.h | 26 + tools/testing/selftests/iommu/iommufd.c | 64 ++- .../selftests/iommu/iommufd_fail_nth.c | 57 ++- tools/testing/selftests/iommu/iommufd_utils.h | 59 ++- 14 files changed, 758 insertions(+), 180 deletions(-) create mode 100644 drivers/iommu/iommu-priv.h base-commit: ac395958f9156733246b5bc3a481c6d38c321a7a -- 2.39.1

2 years, 1 month

4
63
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror