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

[PATCH bpf-next v8] selftests/bpf: trace_helpers.c: optimize kallsyms cache

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Static ksyms often have problems because the number of symbols exceeds the MAX_SYMS limit. Like changing the MAX_SYMS from 300000 to 400000 in commit e76a014334a6("selftests/bpf: Bump and validate MAX_SYMS") solves the problem somewhat, but it's not the perfect way. This commit uses dynamic memory allocation, which completely solves the problem caused by the limitation of the number of kallsyms. Acked-by: Stanislav Fomichev <sdf(a)google.com> Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- v8: Resolves inter-thread contention for ksyms global variables. v7: https://lore.kernel.org/lkml/tencent_BD6E19C00BF565CD5C36A9A0BD828CFA210A@q… Fix __must_check macro. v6: https://lore.kernel.org/lkml/tencent_4A09A36F883A06EA428A593497642AF8AF08@q… Apply libbpf_ensure_mem() v5: https://lore.kernel.org/lkml/tencent_0E9E1A1C0981678D5E7EA9E4BDBA8EE2200A@q… Release the allocated memory once the load_kallsyms_refresh() upon error given it's dynamically allocated. v4: https://lore.kernel.org/lkml/tencent_59C74613113F0C728524B2A82FE5540A5E09@q… Make sure most cases we don't need the realloc() path to begin with, and check strdup() return value. v3: https://lore.kernel.org/lkml/tencent_50B4B2622FE7546A5FF9464310650C008509@q… Do not use structs and judge ksyms__add_symbol function return value. v2: https://lore.kernel.org/lkml/tencent_B655EE5E5D463110D70CD2846AB3262EED09@q… Do the usual len/capacity scheme here to amortize the cost of realloc, and don't free symbols. v1: https://lore.kernel.org/lkml/tencent_AB461510B10CD484E0B2F62E3754165F2909@q… --- samples/bpf/Makefile | 4 + samples/bpf/offwaketime_user.c | 7 +- samples/bpf/sampleip_user.c | 9 +- samples/bpf/spintest_user.c | 7 +- samples/bpf/task_fd_query_user.c | 13 +- samples/bpf/trace_event_user.c | 7 +- .../selftests/bpf/prog_tests/bpf_cookie.c | 7 +- .../selftests/bpf/prog_tests/fill_link_info.c | 9 +- .../bpf/prog_tests/get_stack_raw_tp.c | 10 +- .../bpf/prog_tests/kprobe_multi_test.c | 13 +- .../prog_tests/kprobe_multi_testmod_test.c | 13 +- tools/testing/selftests/bpf/trace_helpers.c | 116 ++++++++++++------ tools/testing/selftests/bpf/trace_helpers.h | 10 +- 13 files changed, 154 insertions(+), 71 deletions(-) diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 4ccf4236031c..6c707ebcebb9 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -175,6 +175,7 @@ TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ TPROGS_CFLAGS += -I$(LIBBPF_INCLUDE) TPROGS_CFLAGS += -I$(srctree)/tools/include TPROGS_CFLAGS += -I$(srctree)/tools/perf +TPROGS_CFLAGS += -I$(srctree)/tools/lib TPROGS_CFLAGS += -DHAVE_ATTR_TEST=0 ifdef SYSROOT @@ -314,6 +315,9 @@ XDP_SAMPLE_CFLAGS += -Wall -O2 \ $(obj)/$(XDP_SAMPLE): TPROGS_CFLAGS = $(XDP_SAMPLE_CFLAGS) $(obj)/$(XDP_SAMPLE): $(src)/xdp_sample_user.h $(src)/xdp_sample_shared.h +# Override includes for trace_helpers.o because __must_check won't be defined +# in our include path. +$(obj)/$(TRACE_HELPERS): TPROGS_CFLAGS := $(TPROGS_CFLAGS) -D__must_check= -include $(BPF_SAMPLES_PATH)/Makefile.target diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c index 5557b5393642..53c1a6b4ec44 100644 --- a/samples/bpf/offwaketime_user.c +++ b/samples/bpf/offwaketime_user.c @@ -16,6 +16,7 @@ /* counts, stackmap */ static int map_fd[2]; +struct ksyms *ksyms; static void print_ksym(__u64 addr) { @@ -23,7 +24,7 @@ static void print_ksym(__u64 addr) if (!addr) return; - sym = ksym_search(addr); + sym = ksym_search(ksyms, addr); if (!sym) { printf("ksym not found. Is kallsyms loaded?\n"); return; @@ -100,7 +101,8 @@ int main(int argc, char **argv) int delay = 1, i = 0; char filename[256]; - if (load_kallsyms()) { + ksyms = load_kallsyms(); + if (!ksyms) { printf("failed to process /proc/kallsyms\n"); return 2; } @@ -149,5 +151,6 @@ int main(int argc, char **argv) bpf_link__destroy(links[i]); bpf_object__close(obj); + free_kallsyms(ksyms); return 0; } diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c index 9283f47844fb..aec3d557aa6b 100644 --- a/samples/bpf/sampleip_user.c +++ b/samples/bpf/sampleip_user.c @@ -25,6 +25,7 @@ static int map_fd; static int nr_cpus; static long _text_addr; +struct ksyms *ksyms; static void usage(void) { @@ -109,7 +110,7 @@ static void print_ip_map(int fd) qsort(counts, max, sizeof(struct ipcount), count_cmp); for (i = 0; i < max; i++) { if (counts[i].ip > _text_addr) { - sym = ksym_search(counts[i].ip); + sym = ksym_search(ksyms, counts[i].ip); if (!sym) { printf("ksym not found. Is kallsyms loaded?\n"); continue; @@ -164,13 +165,14 @@ int main(int argc, char **argv) } /* initialize kernel symbol translation */ - if (load_kallsyms()) { + ksyms = load_kallsyms(); + if (!ksyms) { fprintf(stderr, "ERROR: loading /proc/kallsyms\n"); return 2; } /* used to determine whether the address is kernel space */ - _text_addr = ksym_get_addr("_text"); + _text_addr = ksym_get_addr(ksyms, "_text"); if (!_text_addr) { fprintf(stderr, "ERROR: no '_text' in /proc/kallsyms\n"); return 3; @@ -230,5 +232,6 @@ int main(int argc, char **argv) free(links); bpf_object__close(obj); + free_kallsyms(ksyms); return error; } diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c index 55971edb1088..db6a3c6d5329 100644 --- a/samples/bpf/spintest_user.c +++ b/samples/bpf/spintest_user.c @@ -16,8 +16,10 @@ int main(int ac, char **argv) int map_fd, i, j = 0; char filename[256]; struct ksym *sym; + struct ksyms *ksyms; - if (load_kallsyms()) { + ksyms = load_kallsyms(); + if (!ksyms) { printf("failed to process /proc/kallsyms\n"); return 2; } @@ -58,7 +60,7 @@ int main(int ac, char **argv) while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) { bpf_map_lookup_elem(map_fd, &next_key, &value); assert(next_key == value); - sym = ksym_search(value); + sym = ksym_search(ksyms, value); key = next_key; if (!sym) { printf("ksym not found. Is kallsyms loaded?\n"); @@ -80,5 +82,6 @@ int main(int ac, char **argv) bpf_link__destroy(links[j]); bpf_object__close(obj); + free_kallsyms(ksyms); return 0; } diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index 1e61f2180470..6e7710a4a96f 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -315,8 +315,10 @@ int main(int argc, char **argv) struct bpf_program *prog; struct bpf_object *obj; int i = 0, err = -1; + struct ksyms *ksyms; - if (load_kallsyms()) { + ksyms = load_kallsyms(); + if (!ksyms) { printf("failed to process /proc/kallsyms\n"); return err; } @@ -368,22 +370,22 @@ int main(int argc, char **argv) BPF_FD_TYPE_KRETPROBE, buf, sizeof(buf))); CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0, - ksym_get_addr("bpf_check"), false, + ksym_get_addr(ksyms, "bpf_check"), false, BPF_FD_TYPE_KPROBE, BPF_FD_TYPE_KRETPROBE, buf, sizeof(buf))); CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0, - ksym_get_addr("bpf_check"), false, + ksym_get_addr(ksyms, "bpf_check"), false, BPF_FD_TYPE_KPROBE, BPF_FD_TYPE_KRETPROBE, NULL, 0)); CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0, - ksym_get_addr("bpf_check"), true, + ksym_get_addr(ksyms, "bpf_check"), true, BPF_FD_TYPE_KPROBE, BPF_FD_TYPE_KRETPROBE, buf, sizeof(buf))); CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0, - ksym_get_addr("bpf_check"), true, + ksym_get_addr(ksyms, "bpf_check"), true, BPF_FD_TYPE_KPROBE, BPF_FD_TYPE_KRETPROBE, 0, 0)); @@ -419,5 +421,6 @@ int main(int argc, char **argv) bpf_link__destroy(links[i]); bpf_object__close(obj); + free_kallsyms(ksyms); return err; } diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 9664749bf618..b4822166182f 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -23,6 +23,7 @@ static int pid; static int map_fd[2]; struct bpf_program *prog; static bool sys_read_seen, sys_write_seen; +struct ksyms *ksyms; static void print_ksym(__u64 addr) { @@ -30,7 +31,7 @@ static void print_ksym(__u64 addr) if (!addr) return; - sym = ksym_search(addr); + sym = ksym_search(ksyms, addr); if (!sym) { printf("ksym not found. Is kallsyms loaded?\n"); return; @@ -303,7 +304,8 @@ int main(int argc, char **argv) signal(SIGINT, err_exit); signal(SIGTERM, err_exit); - if (load_kallsyms()) { + ksyms = load_kallsyms(); + if (!ksyms) { printf("failed to process /proc/kallsyms\n"); goto cleanup; } @@ -348,5 +350,6 @@ int main(int argc, char **argv) cleanup: bpf_object__close(obj); + free_kallsyms(ksyms); err_exit(error); } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 1454cebc262b..26bf1f33b8d5 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -104,8 +104,10 @@ static void kprobe_multi_link_api_subtest(void) LIBBPF_OPTS(bpf_link_create_opts, opts); unsigned long long addrs[8]; __u64 cookies[8]; + struct ksyms *ksyms; - if (!ASSERT_OK(load_kallsyms(), "load_kallsyms")) + ksyms = load_kallsyms(); + if (!ASSERT_OK(ksyms != NULL, "load_kallsyms")) goto cleanup; skel = kprobe_multi__open_and_load(); @@ -116,7 +118,7 @@ static void kprobe_multi_link_api_subtest(void) skel->bss->test_cookie = true; #define GET_ADDR(__sym, __addr) ({ \ - __addr = ksym_get_addr(__sym); \ + __addr = ksym_get_addr(ksyms, __sym); \ if (!ASSERT_NEQ(__addr, 0, "ksym_get_addr " #__sym)) \ goto cleanup; \ }) @@ -171,6 +173,7 @@ static void kprobe_multi_link_api_subtest(void) cleanup: close(link1_fd); close(link2_fd); + free_kallsyms(ksyms); kprobe_multi__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c index 9d768e083714..a134eda17446 100644 --- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c @@ -302,16 +302,18 @@ void test_fill_link_info(void) { struct test_fill_link_info *skel; int i; + struct ksyms *ksyms; skel = test_fill_link_info__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_open")) return; /* load kallsyms to compare the addr */ - if (!ASSERT_OK(load_kallsyms_refresh(), "load_kallsyms_refresh")) + ksyms = load_kallsyms_refresh(NULL); + if (!ASSERT_OK(ksyms != NULL, "load_kallsyms_refresh")) goto cleanup; - kprobe_addr = ksym_get_addr(KPROBE_FUNC); + kprobe_addr = ksym_get_addr(ksyms, KPROBE_FUNC); if (test__start_subtest("kprobe_link_info")) test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KPROBE, false); if (test__start_subtest("kretprobe_link_info")) @@ -329,7 +331,7 @@ void test_fill_link_info(void) qsort(kmulti_syms, KMULTI_CNT, sizeof(kmulti_syms[0]), symbols_cmp_r); for (i = 0; i < KMULTI_CNT; i++) - kmulti_addrs[i] = ksym_get_addr(kmulti_syms[i]); + kmulti_addrs[i] = ksym_get_addr(ksyms, kmulti_syms[i]); if (test__start_subtest("kprobe_multi_link_info")) test_kprobe_multi_fill_link_info(skel, false, false); if (test__start_subtest("kretprobe_multi_link_info")) @@ -339,4 +341,5 @@ void test_fill_link_info(void) cleanup: test_fill_link_info__destroy(skel); + free_kallsyms(ksyms); } diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c index 858e0575f502..7a5e7741da14 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c @@ -9,6 +9,7 @@ #define MAX_STACK_RAWTP 100 static int duration = 0; +static struct ksyms *ksyms; struct get_stack_trace_t { int pid; @@ -48,7 +49,7 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size) found = num_stack > 0; } else { for (i = 0; i < num_stack; i++) { - ks = ksym_search(raw_data[i]); + ks = ksym_search(ksyms, raw_data[i]); if (ks && (strcmp(ks->name, nonjit_func) == 0)) { found = true; break; @@ -65,7 +66,7 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size) good_kern_stack = num_stack > 0; } else { for (i = 0; i < num_stack; i++) { - ks = ksym_search(e.kern_stack[i]); + ks = ksym_search(ksyms, e.kern_stack[i]); if (ks && (strcmp(ks->name, nonjit_func) == 0)) { good_kern_stack = true; break; @@ -112,8 +113,8 @@ void test_get_stack_raw_tp(void) if (CHECK(!map, "bpf_find_map", "not found\n")) goto close_prog; - err = load_kallsyms(); - if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno)) + ksyms = load_kallsyms(); + if (CHECK(!ksyms, "load_kallsyms", "err %d errno %d\n", err, errno)) goto close_prog; CPU_ZERO(&cpu_set); @@ -146,4 +147,5 @@ void test_get_stack_raw_tp(void) bpf_link__destroy(link); perf_buffer__free(pb); bpf_object__close(obj); + free_kallsyms(ksyms); } diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index 179fe300534f..e902ea50de57 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -6,6 +6,8 @@ #include "bpf/libbpf_internal.h" #include "bpf/hashmap.h" +static struct ksyms *ksyms; + static void kprobe_multi_test_run(struct kprobe_multi *skel, bool test_return) { LIBBPF_OPTS(bpf_test_run_opts, topts); @@ -89,7 +91,7 @@ static void test_link_api(struct bpf_link_create_opts *opts) } #define GET_ADDR(__sym, __addr) ({ \ - __addr = ksym_get_addr(__sym); \ + __addr = ksym_get_addr(ksyms, __sym); \ if (!ASSERT_NEQ(__addr, 0, "kallsyms load failed for " #__sym)) \ return; \ }) @@ -222,8 +224,8 @@ static void test_attach_api_fails(void) }; __u64 cookies[2]; - addrs[0] = ksym_get_addr("bpf_fentry_test1"); - addrs[1] = ksym_get_addr("bpf_fentry_test2"); + addrs[0] = ksym_get_addr(ksyms, "bpf_fentry_test1"); + addrs[1] = ksym_get_addr(ksyms, "bpf_fentry_test2"); if (!ASSERT_FALSE(!addrs[0] || !addrs[1], "ksym_get_addr")) goto cleanup; @@ -463,7 +465,8 @@ void serial_test_kprobe_multi_bench_attach(void) void test_kprobe_multi_test(void) { - if (!ASSERT_OK(load_kallsyms(), "load_kallsyms")) + ksyms = load_kallsyms(); + if (!ASSERT_OK(ksyms != NULL, "load_kallsyms")) return; if (test__start_subtest("skel_api")) @@ -480,4 +483,6 @@ void test_kprobe_multi_test(void) test_attach_api_syms(); if (test__start_subtest("attach_api_fails")) test_attach_api_fails(); + + free_kallsyms(ksyms); } diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c index 1fbe7e4ac00a..69de53db63fd 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c @@ -4,6 +4,8 @@ #include "trace_helpers.h" #include "bpf/libbpf_internal.h" +static struct ksyms *ksyms; + static void kprobe_multi_testmod_check(struct kprobe_multi *skel) { ASSERT_EQ(skel->bss->kprobe_testmod_test1_result, 1, "kprobe_test1_result"); @@ -50,11 +52,11 @@ static void test_testmod_attach_api_addrs(void) LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); unsigned long long addrs[3]; - addrs[0] = ksym_get_addr("bpf_testmod_fentry_test1"); + addrs[0] = ksym_get_addr(ksyms, "bpf_testmod_fentry_test1"); ASSERT_NEQ(addrs[0], 0, "ksym_get_addr"); - addrs[1] = ksym_get_addr("bpf_testmod_fentry_test2"); + addrs[1] = ksym_get_addr(ksyms, "bpf_testmod_fentry_test2"); ASSERT_NEQ(addrs[1], 0, "ksym_get_addr"); - addrs[2] = ksym_get_addr("bpf_testmod_fentry_test3"); + addrs[2] = ksym_get_addr(ksyms, "bpf_testmod_fentry_test3"); ASSERT_NEQ(addrs[2], 0, "ksym_get_addr"); opts.addrs = (const unsigned long *) addrs; @@ -79,11 +81,14 @@ static void test_testmod_attach_api_syms(void) void serial_test_kprobe_multi_testmod_test(void) { - if (!ASSERT_OK(load_kallsyms_refresh(), "load_kallsyms_refresh")) + ksyms = load_kallsyms_refresh(NULL); + if (!ASSERT_OK(ksyms != NULL, "load_kallsyms_refresh")) return; if (test__start_subtest("testmod_attach_api_syms")) test_testmod_attach_api_syms(); if (test__start_subtest("testmod_attach_api_addrs")) test_testmod_attach_api_addrs(); + + free_kallsyms(ksyms); } diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index f83d9f65c65b..048522d2ac6e 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -14,99 +14,143 @@ #include <linux/limits.h> #include <libelf.h> #include <gelf.h> +#include "bpf/libbpf_internal.h" #define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe" #define DEBUGFS_PIPE "/sys/kernel/debug/tracing/trace_pipe" -#define MAX_SYMS 400000 -static struct ksym syms[MAX_SYMS]; -static int sym_cnt; +struct ksyms { + struct ksym *syms; + size_t sym_cap; + size_t sym_cnt; +}; + +static int ksyms__add_symbol(struct ksyms *ksyms, const char *name, + unsigned long addr) +{ + void *tmp; + + tmp = strdup(name); + if (!tmp) + return -ENOMEM; + ksyms->syms[ksyms->sym_cnt].addr = addr; + ksyms->syms[ksyms->sym_cnt].name = tmp; + + ksyms->sym_cnt++; + + return 0; +} + +void free_kallsyms(struct ksyms *ksyms) +{ + unsigned int i; + + if (!ksyms) + return; + + if (!ksyms->syms) { + free(ksyms); + return; + } + + for (i = 0; i < ksyms->sym_cnt; i++) + free(ksyms->syms[i].name); + free(ksyms->syms); + free(ksyms); +} static int ksym_cmp(const void *p1, const void *p2) { return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr; } -int load_kallsyms_refresh(void) +struct ksyms *load_kallsyms_refresh(struct ksyms *ksyms) { FILE *f; char func[256], buf[256]; char symbol; void *addr; - int i = 0; + int ret; - sym_cnt = 0; + /* flush kallsyms, free the previously allocated dynamic memory */ + free_kallsyms(ksyms); f = fopen("/proc/kallsyms", "r"); if (!f) - return -ENOENT; + return NULL; + + ksyms = calloc(1, sizeof(struct ksyms)); + if (!ksyms) + return NULL; while (fgets(buf, sizeof(buf), f)) { if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3) break; if (!addr) continue; - if (i >= MAX_SYMS) - return -EFBIG; - syms[i].addr = (long) addr; - syms[i].name = strdup(func); - i++; + ret = libbpf_ensure_mem((void **) &ksyms->syms, &ksyms->sym_cap, + sizeof(struct ksym), ksyms->sym_cnt + 1); + if (ret) + goto error; + ret = ksyms__add_symbol(ksyms, func, (unsigned long)addr); + if (ret) + goto error; } fclose(f); - sym_cnt = i; - qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp); - return 0; + qsort(ksyms->syms, ksyms->sym_cnt, sizeof(struct ksym), ksym_cmp); + return ksyms; + +error: + free_kallsyms(ksyms); + return NULL; } -int load_kallsyms(void) +struct ksyms *load_kallsyms(void) { - /* - * This is called/used from multiplace places, - * load symbols just once. - */ - if (sym_cnt) - return 0; - return load_kallsyms_refresh(); + return load_kallsyms_refresh(NULL); } -struct ksym *ksym_search(long key) +struct ksym *ksym_search(struct ksyms *ksyms, long key) { - int start = 0, end = sym_cnt; + int start = 0, end = ksyms->sym_cnt; int result; + if (!ksyms) + return NULL; + /* kallsyms not loaded. return NULL */ - if (sym_cnt <= 0) + if (ksyms->sym_cnt <= 0) return NULL; while (start < end) { size_t mid = start + (end - start) / 2; - result = key - syms[mid].addr; + result = key - ksyms->syms[mid].addr; if (result < 0) end = mid; else if (result > 0) start = mid + 1; else - return &syms[mid]; + return &ksyms->syms[mid]; } - if (start >= 1 && syms[start - 1].addr < key && - key < syms[start].addr) + if (start >= 1 && ksyms->syms[start - 1].addr < key && + key < ksyms->syms[start].addr) /* valid ksym */ - return &syms[start - 1]; + return &ksyms->syms[start - 1]; /* out of range. return _stext */ - return &syms[0]; + return &ksyms->syms[0]; } -long ksym_get_addr(const char *name) +long ksym_get_addr(struct ksyms *ksyms, const char *name) { int i; - for (i = 0; i < sym_cnt; i++) { - if (strcmp(syms[i].name, name) == 0) - return syms[i].addr; + for (i = 0; i < ksyms->sym_cnt; i++) { + if (strcmp(ksyms->syms[i].name, name) == 0) + return ksyms->syms[i].addr; } return 0; diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index 876f3e711df6..6be64f44dd76 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -11,12 +11,14 @@ struct ksym { long addr; char *name; }; +struct ksyms; -int load_kallsyms(void); -int load_kallsyms_refresh(void); +struct ksyms *load_kallsyms(void); +struct ksyms *load_kallsyms_refresh(struct ksyms *ksyms); +void free_kallsyms(struct ksyms *ksyms); -struct ksym *ksym_search(long key); -long ksym_get_addr(const char *name); +struct ksym *ksym_search(struct ksyms *ksyms, long key); +long ksym_get_addr(struct ksyms *ksyms, const char *name); /* open kallsyms and find addresses on the fly, faster than load + search. */ int kallsyms_find(const char *sym, unsigned long long *addr); -- 2.41.0

1 year, 10 months

3
6
0 0

[GIT PULL] scftorture changes for v6.4

by Paul E. McKenney

Hello, Linus, Once the merge window opens, please pull these scftorture changes: git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git tags/scftorture.2023.08.15a # HEAD: 3f68f9c822ebe208f961ab0402e49a10465278ca: scftorture: Add CONFIG_PREEMPT_DYNAMIC=n to NOPREEMPT scenario (2023-07-14 15:02:57 -0700) ---------------------------------------------------------------- smp_call_function torture-test updates for v6.6 This pull request prevents some memory-exhaustion false-postitive failures in scftorture testing. ---------------------------------------------------------------- Paul E. McKenney (4): torture: Scale scftorture memory based on number of CPUs scftorture: Forgive memory-allocation failure if KASAN scftorture: Pause testing after memory-allocation failure scftorture: Add CONFIG_PREEMPT_DYNAMIC=n to NOPREEMPT scenario kernel/scftorture.c | 12 +++++++++--- tools/testing/selftests/rcutorture/bin/torture.sh | 4 +++- tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT | 2 ++ 3 files changed, 14 insertions(+), 4 deletions(-)

1 year, 10 months

3
3
0 0

[PATCH v5 0/7] Optimize mremap during mutual alignment within PMD

by Joel Fernandes (Google)

Hello! Here is v5 of the mremap start address optimization / fix for exec warning. Description of patches ====================== These patches optimizes the start addresses in move_page_tables() and tests the changes. It addresses a warning [1] that occurs due to a downward, overlapping move on a mutually-aligned offset within a PMD during exec. By initiating the copy process at the PMD level when such alignment is present, we can prevent this warning and speed up the copying process at the same time. Linus Torvalds suggested this idea. Please check the individual patches for more details. [1] https://lore.kernel.org/all/ZB2GTBD%2FLWTrkOiO@dhcp22.suse.cz/ Link to v4: https://lore.kernel.org/all/20230531220807.2048037-1-joel@joelfernandes.org/ History of patches: v4->v5: 1. Rebased on mainline. 2. Several improvement suggestions from Lorenzo. v3->v4: 1. Care to be taken to move purely within a VMA, in other words this check in call_align_down(): if (vma->vm_start != addr_masked) return false; As an example of why this is needed: Consider the following range which is 2MB aligned and is a part of a larger 10MB range which is not shown. Each character is 256KB below making the source and destination 2MB each. The lower case letters are moved (s to d) and the upper case letters are not moved. |DDDDddddSSSSssss| If we align down 'ssss' to start from the 'SSSS', we will end up destroying SSSS. The above if statement prevents that and I verified it. I also added a test for this in the last patch. 2. Handle the stack case separately. We do not care about #1 for stack movement because the 'SSSS' does not matter during this move. Further we need to do this to prevent the stack move warning. if (!for_stack && vma->vm_start <= addr_masked) return false; v2->v3: 1. Masked address was stored in int, fixed it to unsigned long to avoid truncation. 2. We now handle moves happening purely within a VMA, a new test is added to handle this. 3. More code comments. v1->v2: 1. Trigger the optimization for mremaps smaller than a PMD. I tested by tracing that it works correctly. 2. Fix issue with bogus return value found by Linus if we broke out of the above loop for the first PMD itself. v1: Initial RFC. Joel Fernandes (1): selftests: mm: Add a test for moving from an offset from start of mapping Joel Fernandes (Google) (6): mm/mremap: Optimize the start addresses in move_page_tables() mm/mremap: Allow moves within the same VMA selftests: mm: Fix failure case when new remap region was not found selftests: mm: Add a test for mutually aligned moves > PMD size selftests: mm: Add a test for remapping to area immediately after existing mapping selftests: mm: Add a test for remapping within a range fs/exec.c | 2 +- include/linux/mm.h | 2 +- mm/mremap.c | 69 +++++- tools/testing/selftests/mm/mremap_test.c | 301 +++++++++++++++++++---- 4 files changed, 325 insertions(+), 49 deletions(-) -- 2.42.0.rc1.204.g551eb34607-goog

1 year, 10 months

3
24
0 0

[PATCH 0/3] selftests/hid: assorted fixes

by Benjamin Tissoires

These fixes have been triggered by [0]: basically, if you do not recompile the kernel first, and are running on an old kernel, vmlinux.h doesn't have the required symbols and the compilation fails. The tests will fail if you run them on that very same machine, of course, but the binary should compile. And while I was sorting out why it was failing, I realized I could do a couple of improvements on the Makefile. [0] https://lore.kernel.org/linux-input/56ba8125-2c6f-a9c9-d498-0ca1c153dcb2@re… Signed-off-by: Benjamin Tissoires <bentiss(a)kernel.org> --- Benjamin Tissoires (3): selftests/hid: ensure we can compile the tests on kernels pre-6.3 selftests/hid: do not manually call headers_install selftests/hid: force using our compiled libbpf headers tools/testing/selftests/hid/Makefile | 10 ++++------ tools/testing/selftests/hid/progs/hid.c | 3 --- tools/testing/selftests/hid/progs/hid_bpf_helpers.h | 20 ++++++++++++++++++++ 3 files changed, 24 insertions(+), 9 deletions(-) --- base-commit: 1d7546042f8fdc4bc39ab91ec966203e2d64f8bd change-id: 20230825-wip-selftests-9a7502b56542 Best regards, -- Benjamin Tissoires <bentiss(a)kernel.org>

1 year, 10 months

3
6
0 0

[PATCH v2 0/3] Add a test to catch unprobed Devicetree devices

by Nícolas F. R. A. Prado

Regressions that cause a device to no longer be probed by a driver can have a big impact on the platform's functionality, and despite being relatively common there isn't currently any generic test to detect them. As an example, bootrr [1] does test for device probe, but it requires defining the expected probed devices for each platform. Given that the Devicetree already provides a static description of devices on the system, it is a good basis for building such a test on top. This series introduces a test to catch regressions that prevent devices from probing. Patches 1 and 2 extend the existing dt-extract-compatibles to be able to output only the compatibles that can be expected to match a Devicetree node to a driver. Patch 2 adds a kselftest that walks over the Devicetree nodes on the current platform and compares the compatibles to the ones on the list, and on an ignore list, to point out devices that failed to be probed. A compatible list is needed because not all compatibles that can show up in a Devicetree node can be used to match to a driver, for example the code for that compatible might use "OF_DECLARE" type macros and avoid the driver framework, or the node might be controlled by a driver that was bound to a different node. An ignore list is needed for the few cases where it's common for a driver to match a device but not probe, like for the "simple-mfd" compatible, where the driver only probes if that compatible is the node's first compatible. The reason for parsing the kernel source instead of relying on information exposed by the kernel at runtime (say, looking at modaliases or introducing some other mechanism), is to be able to catch issues where a config was renamed or a driver moved across configs, and the .config used by the kernel not updated accordingly. We need to parse the source to find all compatibles present in the kernel independent of the current config being run. [1] https://github.com/kernelci/bootrr Changes in v2: - Extended dt-extract-compatibles script to be able to extract driver matching compatibles, instead of adding a new one in Coccinelle - Made kselftest output in the KTAP format Nícolas F. R. A. Prado (3): dt: dt-extract-compatibles: Handle cfile arguments in generator function dt: dt-extract-compatibles: Add flag for driver matching compatibles kselftest: Add new test for detecting unprobed Devicetree devices scripts/dtc/dt-extract-compatibles | 74 +++++++++++++---- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/dt/.gitignore | 1 + tools/testing/selftests/dt/Makefile | 21 +++++ .../selftests/dt/compatible_ignore_list | 1 + tools/testing/selftests/dt/ktap_helpers.sh | 57 +++++++++++++ .../selftests/dt/test_unprobed_devices.sh | 79 +++++++++++++++++++ 7 files changed, 218 insertions(+), 16 deletions(-) create mode 100644 tools/testing/selftests/dt/.gitignore create mode 100644 tools/testing/selftests/dt/Makefile create mode 100644 tools/testing/selftests/dt/compatible_ignore_list create mode 100644 tools/testing/selftests/dt/ktap_helpers.sh create mode 100755 tools/testing/selftests/dt/test_unprobed_devices.sh -- 2.41.0

1 year, 10 months

4
7
0 0

[PATCH v2 1/2] selftests: Provide local define of min() and max()

by Mahmoud Maatuq

to avoid manual calculation of min and max values and fix coccinelle warnings such WARNING opportunity for min()/max() adding one common definition that could be used in multiple files under selftests. there are also some defines for min/max scattered locally inside sources under selftests. this also prepares for cleaning up those redundant defines and include kselftest.h instead. Signed-off-by: Mahmoud Maatuq <mahmoudmatook.mm(a)gmail.com> Suggested-by: David Laight <David.Laight(a)aculab.com> --- changes in v2: redefine min/max in a more strict way to avoid signedness mismatch and multiple evaluation. is_signed_type() moved from selftests/kselftest_harness.h to selftests/kselftest.h. --- tools/testing/selftests/kselftest.h | 24 +++++++++++++++++++++ tools/testing/selftests/kselftest_harness.h | 2 -- 2 files changed, 24 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 829be379545a..93d029471cc9 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -55,6 +55,30 @@ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #endif +#ifndef is_signed_type +#define is_signed_type(var) (!!(((__typeof__(var))(-1)) < (__typeof__(var))1)) +#endif + +#ifndef min +#define min(x, y) ({ \ + _Static_assert(is_signed_type(typeof(x)) == is_signed_type(typeof(y)), \ + "min: signedness mismatch"); \ + typeof(x) _x = (x); \ + typeof(y) _y = (y); \ + _x < _y ? _x : _y; \ +}) +#endif + +#ifndef max +#define max(x, y) ({ \ + _Static_assert(is_signed_type(typeof(x)) == is_signed_type(typeof(y)), \ + "max: signedness mismatch"); \ + typeof(x) _x = (x); \ + typeof(y) _y = (y); \ + _x > _y ? _x : _y; \ +}) +#endif + /* * gcc cpuid.h provides __cpuid_count() since v4.4. * Clang/LLVM cpuid.h provides __cpuid_count() since v3.4.0. diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 5fd49ad0c696..e4e310815226 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -699,8 +699,6 @@ if (_metadata->passed && _metadata->step < 253) \ _metadata->step++; -#define is_signed_type(var) (!!(((__typeof__(var))(-1)) < (__typeof__(var))1)) - #define __EXPECT(_expected, _expected_str, _seen, _seen_str, _t, _assert) do { \ /* Avoid multiple evaluation of the cases */ \ __typeof__(_expected) __exp = (_expected); \ -- 2.34.1

1 year, 10 months

5
8
0 0

[PATCH 4.14 34/57] test_firmware: prevent race conditions by a correct implementation of locking

by Greg Kroah-Hartman

4.14-stable review patch. If anyone has any objections, please let me know. ------------------ From: Mirsad Goran Todorovac <mirsad.todorovac(a)alu.unizg.hr> commit 4acfe3dfde685a5a9eaec5555351918e2d7266a1 upstream. Dan Carpenter spotted a race condition in a couple of situations like these in the test_firmware driver: static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { u8 val; int ret; ret = kstrtou8(buf, 10, &val); if (ret) return ret; mutex_lock(&test_fw_mutex); *(u8 *)cfg = val; mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ return size; } static ssize_t config_num_requests_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int rc; mutex_lock(&test_fw_mutex); if (test_fw_config->reqs) { pr_err("Must call release_all_firmware prior to changing config\n"); rc = -EINVAL; mutex_unlock(&test_fw_mutex); goto out; } mutex_unlock(&test_fw_mutex); rc = test_dev_config_update_u8(buf, count, &test_fw_config->num_requests); out: return rc; } static ssize_t config_read_fw_idx_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return test_dev_config_update_u8(buf, count, &test_fw_config->read_fw_idx); } The function test_dev_config_update_u8() is called from both the locked and the unlocked context, function config_num_requests_store() and config_read_fw_idx_store() which can both be called asynchronously as they are driver's methods, while test_dev_config_update_u8() and siblings change their argument pointed to by u8 *cfg or similar pointer. To avoid deadlock on test_fw_mutex, the lock is dropped before calling test_dev_config_update_u8() and re-acquired within test_dev_config_update_u8() itself, but alas this creates a race condition. Having two locks wouldn't assure a race-proof mutual exclusion. This situation is best avoided by the introduction of a new, unlocked function __test_dev_config_update_u8() which can be called from the locked context and reducing test_dev_config_update_u8() to: static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { int ret; mutex_lock(&test_fw_mutex); ret = __test_dev_config_update_u8(buf, size, cfg); mutex_unlock(&test_fw_mutex); return ret; } doing the locking and calling the unlocked primitive, which enables both locked and unlocked versions without duplication of code. The similar approach was applied to all functions called from the locked and the unlocked context, which safely mitigates both deadlocks and race conditions in the driver. __test_dev_config_update_bool(), __test_dev_config_update_u8() and __test_dev_config_update_size_t() unlocked versions of the functions were introduced to be called from the locked contexts as a workaround without releasing the main driver's lock and thereof causing a race condition. The test_dev_config_update_bool(), test_dev_config_update_u8() and test_dev_config_update_size_t() locked versions of the functions are being called from driver methods without the unnecessary multiplying of the locking and unlocking code for each method, and complicating the code with saving of the return value across lock. Fixes: 7feebfa487b92 ("test_firmware: add support for request_firmware_into_buf") Cc: Luis Chamberlain <mcgrof(a)kernel.org> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Russ Weight <russell.h.weight(a)intel.com> Cc: Takashi Iwai <tiwai(a)suse.de> Cc: Tianfei Zhang <tianfei.zhang(a)intel.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Colin Ian King <colin.i.king(a)gmail.com> Cc: Randy Dunlap <rdunlap(a)infradead.org> Cc: linux-kselftest(a)vger.kernel.org Cc: stable(a)vger.kernel.org # v5.4 Suggested-by: Dan Carpenter <error27(a)gmail.com> Signed-off-by: Mirsad Goran Todorovac <mirsad.todorovac(a)alu.unizg.hr> Link: https://lore.kernel.org/r/20230509084746.48259-1-mirsad.todorovac@alu.unizg… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- lib/test_firmware.c | 37 ++++++++++++++++++++++++++++--------- 1 file changed, 28 insertions(+), 9 deletions(-) --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -283,16 +283,26 @@ static ssize_t config_test_show_str(char return len; } -static int test_dev_config_update_bool(const char *buf, size_t size, - bool *cfg) +static inline int __test_dev_config_update_bool(const char *buf, size_t size, + bool *cfg) { int ret; - mutex_lock(&test_fw_mutex); if (strtobool(buf, cfg) < 0) ret = -EINVAL; else ret = size; + + return ret; +} + +static int test_dev_config_update_bool(const char *buf, size_t size, + bool *cfg) +{ + int ret; + + mutex_lock(&test_fw_mutex); + ret = __test_dev_config_update_bool(buf, size, cfg); mutex_unlock(&test_fw_mutex); return ret; @@ -322,7 +332,7 @@ static ssize_t test_dev_config_show_int( return snprintf(buf, PAGE_SIZE, "%d\n", val); } -static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) +static inline int __test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { int ret; long new; @@ -334,14 +344,23 @@ static int test_dev_config_update_u8(con if (new > U8_MAX) return -EINVAL; - mutex_lock(&test_fw_mutex); *(u8 *)cfg = new; - mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ return size; } +static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) +{ + int ret; + + mutex_lock(&test_fw_mutex); + ret = __test_dev_config_update_u8(buf, size, cfg); + mutex_unlock(&test_fw_mutex); + + return ret; +} + static ssize_t test_dev_config_show_u8(char *buf, u8 cfg) { u8 val; @@ -374,10 +393,10 @@ static ssize_t config_num_requests_store mutex_unlock(&test_fw_mutex); goto out; } - mutex_unlock(&test_fw_mutex); - rc = test_dev_config_update_u8(buf, count, - &test_fw_config->num_requests); + rc = __test_dev_config_update_u8(buf, count, + &test_fw_config->num_requests); + mutex_unlock(&test_fw_mutex); out: return rc;

1 year, 10 months

1
0
0 0

[PATCH 4.19 071/129] test_firmware: prevent race conditions by a correct implementation of locking

by Greg Kroah-Hartman

4.19-stable review patch. If anyone has any objections, please let me know. ------------------ From: Mirsad Goran Todorovac <mirsad.todorovac(a)alu.unizg.hr> commit 4acfe3dfde685a5a9eaec5555351918e2d7266a1 upstream. Dan Carpenter spotted a race condition in a couple of situations like these in the test_firmware driver: static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { u8 val; int ret; ret = kstrtou8(buf, 10, &val); if (ret) return ret; mutex_lock(&test_fw_mutex); *(u8 *)cfg = val; mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ return size; } static ssize_t config_num_requests_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int rc; mutex_lock(&test_fw_mutex); if (test_fw_config->reqs) { pr_err("Must call release_all_firmware prior to changing config\n"); rc = -EINVAL; mutex_unlock(&test_fw_mutex); goto out; } mutex_unlock(&test_fw_mutex); rc = test_dev_config_update_u8(buf, count, &test_fw_config->num_requests); out: return rc; } static ssize_t config_read_fw_idx_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return test_dev_config_update_u8(buf, count, &test_fw_config->read_fw_idx); } The function test_dev_config_update_u8() is called from both the locked and the unlocked context, function config_num_requests_store() and config_read_fw_idx_store() which can both be called asynchronously as they are driver's methods, while test_dev_config_update_u8() and siblings change their argument pointed to by u8 *cfg or similar pointer. To avoid deadlock on test_fw_mutex, the lock is dropped before calling test_dev_config_update_u8() and re-acquired within test_dev_config_update_u8() itself, but alas this creates a race condition. Having two locks wouldn't assure a race-proof mutual exclusion. This situation is best avoided by the introduction of a new, unlocked function __test_dev_config_update_u8() which can be called from the locked context and reducing test_dev_config_update_u8() to: static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { int ret; mutex_lock(&test_fw_mutex); ret = __test_dev_config_update_u8(buf, size, cfg); mutex_unlock(&test_fw_mutex); return ret; } doing the locking and calling the unlocked primitive, which enables both locked and unlocked versions without duplication of code. The similar approach was applied to all functions called from the locked and the unlocked context, which safely mitigates both deadlocks and race conditions in the driver. __test_dev_config_update_bool(), __test_dev_config_update_u8() and __test_dev_config_update_size_t() unlocked versions of the functions were introduced to be called from the locked contexts as a workaround without releasing the main driver's lock and thereof causing a race condition. The test_dev_config_update_bool(), test_dev_config_update_u8() and test_dev_config_update_size_t() locked versions of the functions are being called from driver methods without the unnecessary multiplying of the locking and unlocking code for each method, and complicating the code with saving of the return value across lock. Fixes: 7feebfa487b92 ("test_firmware: add support for request_firmware_into_buf") Cc: Luis Chamberlain <mcgrof(a)kernel.org> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Russ Weight <russell.h.weight(a)intel.com> Cc: Takashi Iwai <tiwai(a)suse.de> Cc: Tianfei Zhang <tianfei.zhang(a)intel.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Colin Ian King <colin.i.king(a)gmail.com> Cc: Randy Dunlap <rdunlap(a)infradead.org> Cc: linux-kselftest(a)vger.kernel.org Cc: stable(a)vger.kernel.org # v5.4 Suggested-by: Dan Carpenter <error27(a)gmail.com> Signed-off-by: Mirsad Goran Todorovac <mirsad.todorovac(a)alu.unizg.hr> Link: https://lore.kernel.org/r/20230509084746.48259-1-mirsad.todorovac@alu.unizg… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- lib/test_firmware.c | 37 ++++++++++++++++++++++++++++--------- 1 file changed, 28 insertions(+), 9 deletions(-) --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -284,16 +284,26 @@ static ssize_t config_test_show_str(char return len; } -static int test_dev_config_update_bool(const char *buf, size_t size, - bool *cfg) +static inline int __test_dev_config_update_bool(const char *buf, size_t size, + bool *cfg) { int ret; - mutex_lock(&test_fw_mutex); if (strtobool(buf, cfg) < 0) ret = -EINVAL; else ret = size; + + return ret; +} + +static int test_dev_config_update_bool(const char *buf, size_t size, + bool *cfg) +{ + int ret; + + mutex_lock(&test_fw_mutex); + ret = __test_dev_config_update_bool(buf, size, cfg); mutex_unlock(&test_fw_mutex); return ret; @@ -323,7 +333,7 @@ static ssize_t test_dev_config_show_int( return snprintf(buf, PAGE_SIZE, "%d\n", val); } -static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) +static inline int __test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { int ret; long new; @@ -335,14 +345,23 @@ static int test_dev_config_update_u8(con if (new > U8_MAX) return -EINVAL; - mutex_lock(&test_fw_mutex); *(u8 *)cfg = new; - mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ return size; } +static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) +{ + int ret; + + mutex_lock(&test_fw_mutex); + ret = __test_dev_config_update_u8(buf, size, cfg); + mutex_unlock(&test_fw_mutex); + + return ret; +} + static ssize_t test_dev_config_show_u8(char *buf, u8 cfg) { u8 val; @@ -375,10 +394,10 @@ static ssize_t config_num_requests_store mutex_unlock(&test_fw_mutex); goto out; } - mutex_unlock(&test_fw_mutex); - rc = test_dev_config_update_u8(buf, count, - &test_fw_config->num_requests); + rc = __test_dev_config_update_u8(buf, count, + &test_fw_config->num_requests); + mutex_unlock(&test_fw_mutex); out: return rc;

1 year, 10 months

1
0
0 0

[PATCH 5.15 1/2] torture: Avoid torture-test reboot loops

by Joel Fernandes (Google)

From: "Paul E. McKenney" <paulmck(a)kernel.org> [ Upstream commit 10f84c2cfb5045e37d78cb5d4c8e8321e06ae18f ] Currently, the various torture tests sometimes react to an early-boot bug by rebooting. This is almost always counterproductive, needlessly consuming CPU time and bloating the console log. This commit therefore adds the "-no-reboot" argument to qemu so that reboot requests will cause qemu to exit. Signed-off-by: Paul E. McKenney <paulmck(a)kernel.org> Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org> --- tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index f4c8055dbf7a..c57be9563214 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -9,9 +9,10 @@ # # Usage: kvm-test-1-run.sh config resdir seconds qemu-args boot_args_in # -# qemu-args defaults to "-enable-kvm -nographic", along with arguments -# specifying the number of CPUs and other options -# generated from the underlying CPU architecture. +# qemu-args defaults to "-enable-kvm -nographic -no-reboot", along with +# arguments specifying the number of CPUs and +# other options generated from the underlying +# CPU architecture. # boot_args_in defaults to value returned by the per_version_boot_params # shell function. # @@ -141,7 +142,7 @@ then fi # Generate -smp qemu argument. -qemu_args="-enable-kvm -nographic $qemu_args" +qemu_args="-enable-kvm -nographic -no-reboot $qemu_args" cpu_count=`configNR_CPUS.sh $resdir/ConfigFragment` cpu_count=`configfrag_boot_cpus "$boot_args_in" "$config_template" "$cpu_count"` if test "$cpu_count" -gt "$TORTURE_ALLOTED_CPUS" -- 2.42.0.rc1.204.g551eb34607-goog

1 year, 10 months

3
3
0 0

[PATCH net-next,v3] selftests: bonding: create directly devices in the target namespaces

by Zhengchao Shao

If failed to set link1_1 to netns client, we should delete link1_1 in the cleanup path. But if set link1_1 to netns client successfully, delete link1_1 will report warning. So it will be safer creating directly the devices in the target namespaces. Reported-by: Hangbin Liu <liuhangbin(a)gmail.com> Closes: https://lore.kernel.org/all/ZNyJx1HtXaUzOkNA@Laptop-X1/ Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- v3: create the eth0 in the namespace v2: create directly devices in the target namespaces --- .../drivers/net/bonding/bond-arp-interval-causes-panic.sh | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh index 7b2d421f09cf..4917dbb35a44 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh @@ -22,14 +22,12 @@ server_ip4=192.168.1.254 echo 180 >/proc/sys/kernel/panic # build namespaces -ip link add dev link1_1 type veth peer name link1_2 - ip netns add "server" -ip link set dev link1_2 netns server up name eth0 +ip netns add "client" +ip -n client link add eth0 type veth peer name eth0 netns server +ip netns exec server ip link set dev eth0 up ip netns exec server ip addr add ${server_ip4}/24 dev eth0 -ip netns add "client" -ip link set dev link1_1 netns client down name eth0 ip netns exec client ip link add dev bond0 down type bond mode 1 \ miimon 100 all_slaves_active 1 ip netns exec client ip link set dev eth0 down master bond0 -- 2.34.1

1 year, 10 months

3
2
0 0

[PATCH net v2 0/3] Avoid TCP resets when using ECMP for load-balancing between multiple servers.

by Sriram Yagnaraman

All packets in the same flow (L3/L4 depending on multipath hash policy) should be directed to the same target, but after [0]/[1] we see stray packets directed towards other targets. This, for instance, causes RST to be sent on TCP connections. The first two patches solve the problem by ignoring route hints for destinations that are part of multipath group, by using new SKB flags for IPv4 and IPv6. The third patch is a selftest that tests the scenario. Thanks to Ido, for reviewing and suggesting a way forward in [2] and also suggesting how to write a selftest for this. v1->v2: - Update to commit messages describing the solution (Ido Schimmel) - Use perf stat to count fib table lookups in selftest (Ido Schimmel) Sriram Yagnaraman (3): ipv4: ignore dst hint for multipath routes ipv6: ignore dst hint for multipath routes selftests: forwarding: Add test for load-balancing between multiple servers include/linux/ipv6.h | 1 + include/net/ip.h | 1 + net/ipv4/ip_input.c | 3 +- net/ipv4/route.c | 1 + net/ipv6/ip6_input.c | 3 +- net/ipv6/route.c | 2 + .../testing/selftests/net/forwarding/Makefile | 1 + tools/testing/selftests/net/forwarding/lib.sh | 5 + .../net/forwarding/router_multipath_vip.sh | 255 ++++++++++++++++++ 9 files changed, 270 insertions(+), 2 deletions(-) create mode 100755 tools/testing/selftests/net/forwarding/router_multipath_vip.sh -- 2.34.1

1 year, 10 months

2
6
0 0

[PATCH 5.10 1/2] torture: Avoid torture-test reboot loops

by Joel Fernandes (Google)

From: "Paul E. McKenney" <paulmck(a)kernel.org> [ Upstream commit 10f84c2cfb5045e37d78cb5d4c8e8321e06ae18f ] Currently, the various torture tests sometimes react to an early-boot bug by rebooting. This is almost always counterproductive, needlessly consuming CPU time and bloating the console log. This commit therefore adds the "-no-reboot" argument to qemu so that reboot requests will cause qemu to exit. Signed-off-by: Paul E. McKenney <paulmck(a)kernel.org> Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org> --- tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 6dc2b49b85ea..bdd747dc61f2 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -9,7 +9,7 @@ # # Usage: kvm-test-1-run.sh config builddir resdir seconds qemu-args boot_args # -# qemu-args defaults to "-enable-kvm -nographic", along with arguments +# qemu-args defaults to "-enable-kvm -nographic -no-reboot", along with arguments # specifying the number of CPUs and other options # generated from the underlying CPU architecture. # boot_args defaults to value returned by the per_version_boot_params @@ -132,7 +132,7 @@ then fi # Generate -smp qemu argument. -qemu_args="-enable-kvm -nographic $qemu_args" +qemu_args="-enable-kvm -nographic -no-reboot $qemu_args" cpu_count=`configNR_CPUS.sh $resdir/ConfigFragment` cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"` if test "$cpu_count" -gt "$TORTURE_ALLOTED_CPUS" -- 2.42.0.rc1.204.g551eb34607-goog

1 year, 10 months

1
0
0 0

[PATCH 6.1] selftests/net: mv bpf/nat6to4.c to net folder

by Hardik Garg

From: Hangbin Liu <liuhangbin(a)gmail.com> commit 3c107f36db06 ("selftests/net: mv bpf/nat6to4.c to net folder") backport this v6.4 commit to v6.1 to fix this error: error: unable to open output file 'linux/kselftest/net/bpf/nat6to4.o': 'No such file or directory' There are some issues with the bpf/nat6to4.c building. 1. It use TEST_CUSTOM_PROGS, which will add the nat6to4.o to kselftest-list file and run by common run_tests. 2. When building the test via `make -C tools/testing/selftests/ TARGETS="net"`, the nat6to4.o will be build in selftests/net/bpf/ folder. But in test udpgro_frglist.sh it refers to ../bpf/nat6to4.o. The correct path should be ./bpf/nat6to4.o. 3. If building the test via `make -C tools/testing/selftests/ TARGETS="net" install`. The nat6to4.o will be installed to kselftest_install/net/ folder. Then the udpgro_frglist.sh should refer to ./nat6to4.o. To fix the confusing test path, let's just move the nat6to4.c to net folder and build it as TEST_GEN_FILES. Fixes: edae34a3ed92 ("selftests net: add UDP GRO fraglist + bpf self-tests") Tested-by: Björn Töpel <bjorn(a)kernel.org> Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> Link: https://lore.kernel.org/r/20230118020927.3971864-1-liuhangbin@gmail.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Hardik Garg <hargar(a)linux.microsoft.com> --- tools/testing/selftests/net/Makefile | 50 ++++++++++++++++++- tools/testing/selftests/net/bpf/Makefile | 14 ------ .../testing/selftests/net/{bpf => }/nat6to4.c | 0 tools/testing/selftests/net/udpgro_frglist.sh | 8 +-- 4 files changed, 52 insertions(+), 20 deletions(-) delete mode 100644 tools/testing/selftests/net/bpf/Makefile rename tools/testing/selftests/net/{bpf => }/nat6to4.c (100%) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 69c58362c0ed..48d1a68be1d5 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -71,14 +71,60 @@ TEST_GEN_FILES += bind_bhash TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr TEST_PROGS += test_ingress_egress_chaining.sh +TEST_GEN_FILES += nat6to4.o TEST_FILES := settings include ../lib.mk -include bpf/Makefile - $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread $(OUTPUT)/tcp_inq: LDLIBS += -lpthread $(OUTPUT)/bind_bhash: LDLIBS += -lpthread + +# Rules to generate bpf obj nat6to4.o +CLANG ?= clang +SCRATCH_DIR := $(OUTPUT)/tools +BUILD_DIR := $(SCRATCH_DIR)/build +BPFDIR := $(abspath ../../../lib/bpf) +APIDIR := $(abspath ../../../include/uapi) + +CCINCLUDE += -I../bpf +CCINCLUDE += -I../../../../usr/include/ +CCINCLUDE += -I$(SCRATCH_DIR)/include + +BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a + +MAKE_DIRS := $(BUILD_DIR)/libbpf +$(MAKE_DIRS): + mkdir -p $@ + +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| $/.*$|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +endef + +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) + +$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS) + $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ + +$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ + $(APIDIR)/linux/bpf.h \ + | $(BUILD_DIR)/libbpf + $(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ + EXTRA_CFLAGS='-g -O0' \ + DESTDIR=$(SCRATCH_DIR) prefix= all install_headers + +EXTRA_CLEAN := $(SCRATCH_DIR) diff --git a/tools/testing/selftests/net/bpf/Makefile b/tools/testing/selftests/net/bpf/Makefile deleted file mode 100644 index 8ccaf8732eb2..000000000000 --- a/tools/testing/selftests/net/bpf/Makefile +++ /dev/null @@ -1,14 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -CLANG ?= clang -CCINCLUDE += -I../../bpf -CCINCLUDE += -I../../../../lib -CCINCLUDE += -I../../../../../usr/include/ - -TEST_CUSTOM_PROGS = $(OUTPUT)/bpf/nat6to4.o -all: $(TEST_CUSTOM_PROGS) - -$(OUTPUT)/%.o: %.c - $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) -o $@ - -EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) diff --git a/tools/testing/selftests/net/bpf/nat6to4.c b/tools/testing/selftests/net/nat6to4.c similarity index 100% rename from tools/testing/selftests/net/bpf/nat6to4.c rename to tools/testing/selftests/net/nat6to4.c diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index c9c4b9d65839..0a6359bed0b9 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -40,8 +40,8 @@ run_one() { ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp tc -n "${PEER_NS}" qdisc add dev veth1 clsact - tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file ../bpf/nat6to4.o section schedcls/ingress6/nat_6 direct-action - tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file ../bpf/nat6to4.o section schedcls/egress4/snat4 direct-action + tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file nat6to4.o section schedcls/ingress6/nat_6 direct-action + tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file nat6to4.o section schedcls/egress4/snat4 direct-action echo ${rx_args} ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & @@ -88,8 +88,8 @@ if [ ! -f ${BPF_FILE} ]; then exit -1 fi -if [ ! -f bpf/nat6to4.o ]; then - echo "Missing nat6to4 helper. Build bpfnat6to4.o selftest first" +if [ ! -f nat6to4.o ]; then + echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first" exit -1 fi -- 2.33.8

1 year, 10 months

2
1
0 0

[PATCH v2 0/3] selftests/nolibc: add misc improvments

by Zhangjin Wu

Hi, Willy, Hi Thomas Based on Thomas' suggestion, V2 comes here with relative path support for O= option, v1 is [1]. // subdir $ pwd /labs/linux-lab/src/linux-stable/tools/testing/selftests/nolibc $ mkdir -p out $ make run-user O=out -C /labs/linux-lab/src/linux-stable/tools/testing/selftests/nolibc/ -j4 | grep status Makefile:122: srctree=/labs/linux-lab/src/linux-stable Makefile:123: objtree: out Makefile:124: COMMAND_O: O=/labs/linux-lab/src/linux-stable/tools/testing/selftests/nolibc/out Makefile:125: OUTPUT=/labs/linux-lab/src/linux-stable/tools/testing/selftests/nolibc/out/ 166 test(s): 158 passed, 8 skipped, 0 failed => status: warning // topdir $ pwd /labs/linux-lab/src/linux-stable $ mkdir -p out $ make run-user O=out -C /labs/linux-lab/src/linux-stable/tools/testing/selftests/nolibc/ -j4 | grep status Makefile:122: srctree=/labs/linux-lab/src/linux-stable Makefile:123: objtree: out Makefile:124: COMMAND_O: O=/labs/linux-lab/src/linux-stable/out Makefile:125: OUTPUT=/labs/linux-lab/src/linux-stable/out/ 166 test(s): 158 passed, 8 skipped, 0 failed => status: warning // outside $ pwd /labs/linux-lab/build $ mkdir -p out $ make run-user O=out -C /labs/linux-lab/src/linux-stable/tools/testing/selftests/nolibc/ -j4 | grep status Makefile:122: srctree=/labs/linux-lab/src/linux-stable Makefile:123: objtree: out Makefile:124: COMMAND_O: O=/labs/linux-lab/build/out Makefile:125: OUTPUT=/labs/linux-lab/build/out/ 166 test(s): 158 passed, 8 skipped, 0 failed => status: warning Changes from v1 --> v2: * selftests/nolibc: allow report with existing test log tools/nolibc: stackprotector.h: make __stack_chk_init static Add Reviewed-by line from Thomas * selftests/nolibc: fix up O= option support Now with relative path support with the help of $(COMMAND_O). Suggested by Thomas. Thanks! Zhangjin --- [1]: https://lore.kernel.org/lkml/cover.1691073180.git.falcon@tinylab.org/ Zhangjin Wu (3): selftests/nolibc: allow report with existing test log tools/nolibc: stackprotector.h: make __stack_chk_init static selftests/nolibc: fix up O= option support tools/include/nolibc/crt.h | 2 +- tools/include/nolibc/stackprotector.h | 5 ++--- tools/testing/selftests/nolibc/Makefile | 19 +++++++++++++------ 3 files changed, 16 insertions(+), 10 deletions(-) -- 2.25.1

1 year, 10 months

3
8
0 0

[PATCH bpf-next v7] selftests/bpf: trace_helpers.c: optimize kallsyms cache

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Static ksyms often have problems because the number of symbols exceeds the MAX_SYMS limit. Like changing the MAX_SYMS from 300000 to 400000 in commit e76a014334a6("selftests/bpf: Bump and validate MAX_SYMS") solves the problem somewhat, but it's not the perfect way. This commit uses dynamic memory allocation, which completely solves the problem caused by the limitation of the number of kallsyms. Acked-by: Stanislav Fomichev <sdf(a)google.com> Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- v7: Fix __must_check macro. v6: https://lore.kernel.org/lkml/tencent_4A09A36F883A06EA428A593497642AF8AF08@q… Apply libbpf_ensure_mem() v5: https://lore.kernel.org/lkml/tencent_0E9E1A1C0981678D5E7EA9E4BDBA8EE2200A@q… Release the allocated memory once the load_kallsyms_refresh() upon error given it's dynamically allocated. v4: https://lore.kernel.org/lkml/tencent_59C74613113F0C728524B2A82FE5540A5E09@q… Make sure most cases we don't need the realloc() path to begin with, and check strdup() return value. v3: https://lore.kernel.org/lkml/tencent_50B4B2622FE7546A5FF9464310650C008509@q… Do not use structs and judge ksyms__add_symbol function return value. v2: https://lore.kernel.org/lkml/tencent_B655EE5E5D463110D70CD2846AB3262EED09@q… Do the usual len/capacity scheme here to amortize the cost of realloc, and don't free symbols. v1: https://lore.kernel.org/lkml/tencent_AB461510B10CD484E0B2F62E3754165F2909@q… --- samples/bpf/Makefile | 2 + tools/testing/selftests/bpf/trace_helpers.c | 58 ++++++++++++++++----- 2 files changed, 48 insertions(+), 12 deletions(-) diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 4ccf4236031c..0cd45c42af2f 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -175,6 +175,7 @@ TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ TPROGS_CFLAGS += -I$(LIBBPF_INCLUDE) TPROGS_CFLAGS += -I$(srctree)/tools/include TPROGS_CFLAGS += -I$(srctree)/tools/perf +TPROGS_CFLAGS += -I$(srctree)/tools/lib TPROGS_CFLAGS += -DHAVE_ATTR_TEST=0 ifdef SYSROOT @@ -314,6 +315,7 @@ XDP_SAMPLE_CFLAGS += -Wall -O2 \ $(obj)/$(XDP_SAMPLE): TPROGS_CFLAGS = $(XDP_SAMPLE_CFLAGS) $(obj)/$(XDP_SAMPLE): $(src)/xdp_sample_user.h $(src)/xdp_sample_shared.h +$(obj)/$(TRACE_HELPERS): TPROGS_CFLAGS := $(TPROGS_CFLAGS) -D__must_check= -include $(BPF_SAMPLES_PATH)/Makefile.target diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index f83d9f65c65b..d62ab3b77153 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -14,13 +14,44 @@ #include <linux/limits.h> #include <libelf.h> #include <gelf.h> +#include "bpf/libbpf_internal.h" #define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe" #define DEBUGFS_PIPE "/sys/kernel/debug/tracing/trace_pipe" -#define MAX_SYMS 400000 -static struct ksym syms[MAX_SYMS]; -static int sym_cnt; +static struct ksym *syms; +static size_t sym_cap; +static size_t sym_cnt; + +static int ksyms__add_symbol(const char *name, unsigned long addr) +{ + void *tmp; + + tmp = strdup(name); + if (!tmp) + return -ENOMEM; + syms[sym_cnt].addr = addr; + syms[sym_cnt].name = tmp; + + sym_cnt++; + + return 0; +} + +static void ksyms__free(void) +{ + unsigned int i; + + if (!syms) + return; + + for (i = 0; i < sym_cnt; i++) + free(syms[i].name); + free(syms); + syms = NULL; + sym_cnt = 0; + sym_cap = 0; +} static int ksym_cmp(const void *p1, const void *p2) { @@ -33,9 +64,7 @@ int load_kallsyms_refresh(void) char func[256], buf[256]; char symbol; void *addr; - int i = 0; - - sym_cnt = 0; + int ret; f = fopen("/proc/kallsyms", "r"); if (!f) @@ -46,17 +75,22 @@ int load_kallsyms_refresh(void) break; if (!addr) continue; - if (i >= MAX_SYMS) - return -EFBIG; - syms[i].addr = (long) addr; - syms[i].name = strdup(func); - i++; + ret = libbpf_ensure_mem((void **) &syms, &sym_cap, + sizeof(struct ksym), sym_cnt + 1); + if (ret) + goto error; + ret = ksyms__add_symbol(func, (unsigned long)addr); + if (ret) + goto error; } fclose(f); - sym_cnt = i; qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp); return 0; + +error: + ksyms__free(); + return ret; } int load_kallsyms(void) -- 2.39.3

1 year, 10 months

2
2
0 0

Re: Re: fs/proc/task_mmu: Implement IOCTL for efficient page table scanning

by kernel test robot

Hi Michał, kernel test robot noticed the following build warnings: [auto build test WARNING on akpm-mm/mm-everything] [also build test WARNING on linus/master v6.5-rc7 next-20230825] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in https://git-scm.com/docs/git-format-patch#_base_tree_information] url: https://github.com/intel-lab-lkp/linux/commits/Micha-Miros-aw/Re-fs-proc-ta… base: https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything patch link: https://lore.kernel.org/r/a0b5c6776b2ed91f78a7575649f8b100e58bd3a9.16898810… patch subject: Re: fs/proc/task_mmu: Implement IOCTL for efficient page table scanning config: i386-randconfig-i004-20230720 (https://download.01.org/0day-ci/archive/20230826/202308262125.VHTuZ7uV-lkp@…) compiler: gcc-12 (Debian 12.2.0-14) 12.2.0 reproduce: (https://download.01.org/0day-ci/archive/20230826/202308262125.VHTuZ7uV-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202308262125.VHTuZ7uV-lkp@intel.com/ All warnings (new ones prefixed by >>): fs/proc/task_mmu.c: In function 'pagemap_scan_test_walk': fs/proc/task_mmu.c:1921:13: error: implicit declaration of function 'userfaultfd_wp_async'; did you mean 'userfaultfd_wp'? [-Werror=implicit-function-declaration] 1921 | if (userfaultfd_wp_async(vma) && userfaultfd_wp_use_markers(vma)) | ^~~~~~~~~~~~~~~~~~~~ | userfaultfd_wp fs/proc/task_mmu.c: In function 'pagemap_scan_init_bounce_buffer': fs/proc/task_mmu.c:2290:22: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] 2290 | p->vec_out = (void __user *)p->arg.vec; | ^ fs/proc/task_mmu.c: At top level: >> fs/proc/task_mmu.c:1967:13: warning: 'pagemap_scan_backout_range' defined but not used [-Wunused-function] 1967 | static void pagemap_scan_backout_range(struct pagemap_scan_private *p, | ^~~~~~~~~~~~~~~~~~~~~~~~~~ cc1: some warnings being treated as errors vim +/pagemap_scan_backout_range +1967 fs/proc/task_mmu.c 1966 > 1967 static void pagemap_scan_backout_range(struct pagemap_scan_private *p, 1968 unsigned long addr, unsigned long end) 1969 { 1970 struct page_region *cur_buf = &p->cur_buf; 1971 1972 if (cur_buf->start != addr) { 1973 cur_buf->end = addr; 1974 } else { 1975 cur_buf->start = cur_buf->end = 0; 1976 } 1977 1978 p->end_addr = 0; 1979 } 1980 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 year, 10 months

1
0
0 0

[PATCH net-next 03/17] selftests: tls: test some invalid inputs for setsockopt

by Sabrina Dubroca

This test will need to be updated if new ciphers are added. Signed-off-by: Sabrina Dubroca <sd(a)queasysnail.net> --- tools/testing/selftests/net/tls.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 0da6952a047a..297d972558fb 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -241,6 +241,31 @@ TEST_F(tls_basic, base_base) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); }; +TEST_F(tls_basic, bad_cipher) +{ + struct tls_crypto_info_keys tls12; + + tls12.crypto_info.version = 200; + tls12.crypto_info.cipher_type = TLS_CIPHER_AES_GCM_128; + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1); + + tls12.crypto_info.version = TLS_1_2_VERSION; + tls12.crypto_info.cipher_type = 50; + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1); + + tls12.crypto_info.version = TLS_1_2_VERSION; + tls12.crypto_info.cipher_type = 59; + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1); + + tls12.crypto_info.version = TLS_1_2_VERSION; + tls12.crypto_info.cipher_type = 10; + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1); + + tls12.crypto_info.version = TLS_1_2_VERSION; + tls12.crypto_info.cipher_type = 70; + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1); +} + FIXTURE(tls) { int fd, cfd; -- 2.40.1

1 year, 10 months

1
0
0 0

[PATCH net-next 02/17] selftests: tls: add getsockopt test

by Sabrina Dubroca

The kernel accepts fetching either just the version and cipher type, or exactly the per-cipher struct. Also check that getsockopt returns what we just passed to the kernel. Signed-off-by: Sabrina Dubroca <sd(a)queasysnail.net> --- tools/testing/selftests/net/tls.c | 35 +++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 95bef2be48cd..0da6952a047a 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -30,6 +30,7 @@ static int fips_enabled; struct tls_crypto_info_keys { union { + struct tls_crypto_info crypto_info; struct tls12_crypto_info_aes_gcm_128 aes128; struct tls12_crypto_info_chacha20_poly1305 chacha20; struct tls12_crypto_info_sm4_gcm sm4gcm; @@ -1496,6 +1497,40 @@ TEST_F(tls, shutdown_reuse) EXPECT_EQ(errno, EISCONN); } +TEST_F(tls, getsockopt) +{ + struct tls_crypto_info_keys expect, get; + socklen_t len; + + /* get only the version/cipher */ + len = sizeof(struct tls_crypto_info); + memrnd(&get, sizeof(get)); + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), 0); + EXPECT_EQ(len, sizeof(struct tls_crypto_info)); + EXPECT_EQ(get.crypto_info.version, variant->tls_version); + EXPECT_EQ(get.crypto_info.cipher_type, variant->cipher_type); + + /* get the full crypto_info */ + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &expect); + len = expect.len; + memrnd(&get, sizeof(get)); + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), 0); + EXPECT_EQ(len, expect.len); + EXPECT_EQ(get.crypto_info.version, variant->tls_version); + EXPECT_EQ(get.crypto_info.cipher_type, variant->cipher_type); + EXPECT_EQ(memcmp(&get, &expect, expect.len), 0); + + /* short get should fail */ + len = sizeof(struct tls_crypto_info) - 1; + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), -1); + EXPECT_EQ(errno, EINVAL); + + /* partial get of the cipher data should fail */ + len = expect.len - 1; + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), -1); + EXPECT_EQ(errno, EINVAL); +} + FIXTURE(tls_err) { int fd, cfd; -- 2.40.1

1 year, 10 months

1
0
0 0

[PATCH net-next 01/17] selftests: tls: add test variants for aria-gcm

by Sabrina Dubroca

Only supported for TLS1.2. Signed-off-by: Sabrina Dubroca <sd(a)queasysnail.net> --- tools/testing/selftests/net/config | 1 + tools/testing/selftests/net/tls.c | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+) diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index cd3cc52c59b4..8da562a9ae87 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -51,3 +51,4 @@ CONFIG_AMT=m CONFIG_VXLAN=m CONFIG_IP_SCTP=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_CRYPTO_ARIA=y diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 4b63708c6a81..95bef2be48cd 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -36,6 +36,8 @@ struct tls_crypto_info_keys { struct tls12_crypto_info_sm4_ccm sm4ccm; struct tls12_crypto_info_aes_ccm_128 aesccm128; struct tls12_crypto_info_aes_gcm_256 aesgcm256; + struct tls12_crypto_info_aria_gcm_128 ariagcm128; + struct tls12_crypto_info_aria_gcm_256 ariagcm256; }; size_t len; }; @@ -76,6 +78,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, tls12->aesgcm256.info.version = tls_version; tls12->aesgcm256.info.cipher_type = cipher_type; break; + case TLS_CIPHER_ARIA_GCM_128: + tls12->len = sizeof(struct tls12_crypto_info_aria_gcm_128); + tls12->ariagcm128.info.version = tls_version; + tls12->ariagcm128.info.cipher_type = cipher_type; + break; + case TLS_CIPHER_ARIA_GCM_256: + tls12->len = sizeof(struct tls12_crypto_info_aria_gcm_256); + tls12->ariagcm256.info.version = tls_version; + tls12->ariagcm256.info.cipher_type = cipher_type; + break; default: break; } @@ -312,6 +324,18 @@ FIXTURE_VARIANT_ADD(tls, 13_nopad) .nopad = true, }; +FIXTURE_VARIANT_ADD(tls, 12_aria_gcm) +{ + .tls_version = TLS_1_2_VERSION, + .cipher_type = TLS_CIPHER_ARIA_GCM_128, +}; + +FIXTURE_VARIANT_ADD(tls, 12_aria_gcm_256) +{ + .tls_version = TLS_1_2_VERSION, + .cipher_type = TLS_CIPHER_ARIA_GCM_256, +}; + FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12; -- 2.40.1

1 year, 10 months

1
0
0 0

selftests: hid: trouble building with clang due to missing header

by Justin Stitt

Hi, I'd like to get some help with building the kselftest target. I am running into some warnings within the hid tree: | progs/hid_bpf_helpers.h:9:38: error: declaration of 'struct hid_bpf_ctx' will \ | not be visible outside of this function [-Werror,-Wvisibility] | 9 | extern __u8 *hid_bpf_get_data(struct hid_bpf_ctx *ctx, | | ^ | progs/hid.c:23:35: error: incompatible pointer types passing 'struct hid_bpf_ctx *' \ | to parameter of type 'struct hid_bpf_ctx *' [-Werror,-Wincompatible-pointer-types] | 23 | __u8 *rw_data = hid_bpf_get_data(hid_ctx, 0 /* offset */, 3 /* size */); This warning, amongst others, is due to some symbol not being included. In this case, `struct hid_bpf_ctx` is not being defined anywhere that I can see inside of the testing tree itself. Instead, `struct hid_bpf_ctx` is defined and implemented at `include/linux/hid_bpf.h`. AFAIK, I cannot just include this header as the tools directory is a separate entity from kbuild and these tests are meant to be built/ran without relying on kernel headers. Am I correct in this assumption? At any rate, the include itself doesn't work. How can I properly include this struct definition and fix the warning(s)? Please note that we cannot just forward declare the struct as it is being dereferenced and would then yield a completely different error/warning for an incomplete type. We need the entire implementation for the struct included. Other symbols also defined in `include/linux/hid_bpf.h` that we need are `struct hid_report_type` and `HID_BPF_FLAG...` Here's the invocation I am running to build kselftest: `$ make LLVM=1 ARCH=x86_64 mrproper headers && make LLVM=1 ARCH=x86_64 -j128 V=1 -C tools/testing/selftests` If anyone is currently getting clean builds of kselftest with clang, what invocation works for you? Link: https://github.com/ClangBuiltLinux/linux/issues/1698 Full-build-log: https://gist.github.com/JustinStitt/b217f6e47c1d762e5e1cc6c3532f1bbb (V=1) Thanks. Justin

1 year, 10 months

4
13
0 0

[ANNOUNCE/CFP] Kernel Testing & Dependability Micro-conference at LPC 2023

by shuah

Hello, I am reaching out to announce that we are once again planning to gather to discuss testing and dependability related topics at the Kernel Testing & Dependability Micro-conference at LPC 2023. We invite you to submit proposals for discussion: - https://lpc.events/event/17/abstracts/1430/ The Linux Plumbers 2023 Kernel Testing & Dependability track focuses on advancing the current state of testing of the Linux Kernel and its related infrastructure. The main purpose is to improve software quality and dependability for applications that require predictability and trust. We aim to create connections between folks working on similar projects, and help individual projects make progress. This track is intended to promote collaboration between all the communities and people interested in the Kernel testing & dependability. This will help move the conversation forward from where we left off at the LPC 2022 Kernel Testing & Dependability MC. We ask that any topic discussions focus on issues/problems they are facing and possible alternatives to resolving them. The Micro-conference is open to all topics related to testing on Linux, not necessarily in the kernel space. Suggested topics: - KernelCI: Topics on improvements and enhancements for test coverage - Growing KCIDB, integrating more sources (https://kernelci.org/docs/kcidb/) - Sanitizers - Using Clang for better testing coverage - How to spread KUnit throughout the kernel? - Building and testing in-kernel Rust code. - Explore ways to improve testing framework and tests in the kernel with a specific goal to increase traceability and code coverage. - Explore how do SBOMs figure into dependability? Proposals can be submitted here, by August 20th: - https://lpc.events/event/17/abstracts/ Please reach out to MC leads: Shuah Khan (shuah(a)kernel.org) Sasha Levin <sashal(a)kernel.org> Guillaume Tucker <guillaume.tucker(a)collabora.com> thank you, -- Shuah

1 year, 10 months

2
2
0 0

[PATCH v5 00/10] kunit: Add dynamically-extending log

by Richard Fitzgerald

This patch chain changes the logging implementation to use string_stream so that the log will grow dynamically. The first 8 patches add test code for string_stream, and make some changes to string_stream needed to be able to use it for the log. The final patch adds a performance report of string_stream. CHANGES SINCE V4: - Re-ordered the first 3 patches from V4 to squash the first two sets of string_stream tests into a single patch. - Changed is_literal() so it doesn't need a struct kunit. - Split out the new resource-managed alloc and free functions into a pre-patch to reduce the amount of code churn when the string_stream is decoupled from kunit. - Wrapped the call to string_stream_geT_string() in string-stream-test in a local function to reduce the amount of code churn when the string_stream is decoupled from kunit. - Some minor changes to test implementations. - string_stream is now completely separated from kunit and the 'test' member of struct string_stream has been eliminated. Richard Fitzgerald (10): kunit: string-stream: Don't create a fragment for empty strings kunit: string-stream: Improve testing of string_stream kunit: string-stream: Add option to make all lines end with newline kunit: string-stream: Add cases for string_stream newline appending kunit: Don't use a managed alloc in is_literal() kunit: string-stream: Add kunit_alloc_string_stream() kunit: string-stream: Decouple string_stream from kunit kunit: string-stream: Add tests for freeing resource-managed string_stream kunit: Use string_stream for test log kunit: string-stream: Test performance of string_stream include/kunit/test.h | 14 +- lib/kunit/assert.c | 14 +- lib/kunit/debugfs.c | 36 ++- lib/kunit/kunit-test.c | 46 ++- lib/kunit/string-stream-test.c | 508 +++++++++++++++++++++++++++++++-- lib/kunit/string-stream.c | 100 +++++-- lib/kunit/string-stream.h | 16 +- lib/kunit/test.c | 50 +--- 8 files changed, 662 insertions(+), 122 deletions(-) -- 2.30.2

1 year, 10 months

4
31
0 0

[PATCH v3 9/9] selftests/bpf/sockopt: Add io_uring support

by Breno Leitao

Expand the sockopt test to use also check for io_uring {g,s}etsockopt commands operations. This patch starts by marking marks each test if they support io_uring support or not. Right now, io_uring cmd getsockopt() has a limitation of only accepting level == SOL_SOCKET, otherwise it returns -EOPNOTSUPP. Later, each test runs using regular {g,s}etsockopt systemcalls, and, if liburing is supported, execute the same test (again), but calling liburing {g,s}setsockopt commands. For that, leverage the mini liburing to do basic io_uring operations. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- tools/testing/selftests/bpf/Makefile | 1 + .../selftests/bpf/prog_tests/sockopt.c | 129 +++++++++++++++++- 2 files changed, 124 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 538df8fb8c42..4da04242b848 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -362,6 +362,7 @@ CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \ $(OUTPUT)/test_l4lb_noinline.o: BPF_CFLAGS += -fno-inline $(OUTPUT)/test_xdp_noinline.o: BPF_CFLAGS += -fno-inline +$(OUTPUT)/test_progs.o: CFLAGS += -I../../../include/ $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h $(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c index 9e6a5e3ed4de..4693ad8bfe8f 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <io_uring/mini_liburing.h> #include "cgroup_helpers.h" static char bpf_log_buf[4096]; @@ -38,6 +39,7 @@ static struct sockopt_test { socklen_t get_optlen_ret; enum sockopt_test_error error; + bool io_uring_support; } tests[] = { /* ==================== getsockopt ==================== */ @@ -53,6 +55,7 @@ static struct sockopt_test { .attach_type = BPF_CGROUP_GETSOCKOPT, .expected_attach_type = 0, .error = DENY_LOAD, + .io_uring_support = true, }, { .descr = "getsockopt: wrong expected_attach_type", @@ -65,6 +68,7 @@ static struct sockopt_test { .attach_type = BPF_CGROUP_GETSOCKOPT, .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .error = DENY_ATTACH, + .io_uring_support = true, }, { .descr = "getsockopt: bypass bpf hook", @@ -121,6 +125,7 @@ static struct sockopt_test { .attach_type = BPF_CGROUP_GETSOCKOPT, .expected_attach_type = BPF_CGROUP_GETSOCKOPT, .error = DENY_LOAD, + .io_uring_support = true, }, { .descr = "getsockopt: read ctx->level", @@ -164,6 +169,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_GETSOCKOPT, .error = DENY_LOAD, + .io_uring_support = true, }, { .descr = "getsockopt: read ctx->optname", @@ -225,6 +231,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_GETSOCKOPT, .error = DENY_LOAD, + .io_uring_support = true, }, { .descr = "getsockopt: read ctx->optlen", @@ -252,6 +259,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_GETSOCKOPT, .get_optlen = 64, + .io_uring_support = true, }, { .descr = "getsockopt: deny bigger ctx->optlen", @@ -276,6 +284,7 @@ static struct sockopt_test { .get_optlen = 64, .error = EFAULT_GETSOCKOPT, + .io_uring_support = true, }, { .descr = "getsockopt: ignore >PAGE_SIZE optlen", @@ -318,6 +327,7 @@ static struct sockopt_test { .get_optval = {}, /* the changes are ignored */ .get_optlen = PAGE_SIZE + 1, .error = EOPNOTSUPP_GETSOCKOPT, + .io_uring_support = true, }, { .descr = "getsockopt: support smaller ctx->optlen", @@ -339,6 +349,7 @@ static struct sockopt_test { .get_optlen = 64, .get_optlen_ret = 32, + .io_uring_support = true, }, { .descr = "getsockopt: deny writing to ctx->optval", @@ -353,6 +364,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_GETSOCKOPT, .error = DENY_LOAD, + .io_uring_support = true, }, { .descr = "getsockopt: deny writing to ctx->optval_end", @@ -367,6 +379,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_GETSOCKOPT, .error = DENY_LOAD, + .io_uring_support = true, }, { .descr = "getsockopt: rewrite value", @@ -421,6 +434,7 @@ static struct sockopt_test { .attach_type = BPF_CGROUP_SETSOCKOPT, .expected_attach_type = 0, .error = DENY_LOAD, + .io_uring_support = true, }, { .descr = "setsockopt: wrong expected_attach_type", @@ -433,6 +447,7 @@ static struct sockopt_test { .attach_type = BPF_CGROUP_SETSOCKOPT, .expected_attach_type = BPF_CGROUP_GETSOCKOPT, .error = DENY_ATTACH, + .io_uring_support = true, }, { .descr = "setsockopt: bypass bpf hook", @@ -518,6 +533,7 @@ static struct sockopt_test { .set_level = 123, .set_optlen = 1, + .io_uring_support = true, }, { .descr = "setsockopt: allow changing ctx->level", @@ -572,6 +588,7 @@ static struct sockopt_test { .set_optname = 123, .set_optlen = 1, + .io_uring_support = true, }, { .descr = "setsockopt: allow changing ctx->optname", @@ -624,6 +641,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .set_optlen = 64, + .io_uring_support = true, }, { .descr = "setsockopt: ctx->optlen == -1 is ok", @@ -640,6 +658,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .set_optlen = 64, + .io_uring_support = true, }, { .descr = "setsockopt: deny ctx->optlen < 0 (except -1)", @@ -658,6 +677,7 @@ static struct sockopt_test { .set_optlen = 4, .error = EFAULT_SETSOCKOPT, + .io_uring_support = true, }, { .descr = "setsockopt: deny ctx->optlen > input optlen", @@ -675,6 +695,7 @@ static struct sockopt_test { .set_optlen = 64, .error = EFAULT_SETSOCKOPT, + .io_uring_support = true, }, { .descr = "setsockopt: ignore >PAGE_SIZE optlen", @@ -775,6 +796,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .error = DENY_LOAD, + .io_uring_support = true, }, { .descr = "setsockopt: deny read ctx->retval", @@ -791,6 +813,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .error = DENY_LOAD, + .io_uring_support = true, }, { .descr = "setsockopt: deny writing to ctx->optval", @@ -805,6 +828,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .error = DENY_LOAD, + .io_uring_support = true, }, { .descr = "setsockopt: deny writing to ctx->optval_end", @@ -819,6 +843,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .error = DENY_LOAD, + .io_uring_support = true, }, { .descr = "setsockopt: allow IP_TOS <= 128", @@ -940,7 +965,94 @@ static int load_prog(const struct bpf_insn *insns, return fd; } -static int run_test(int cgroup_fd, struct sockopt_test *test) +/* Core function that handles io_uring ring initialization, + * sending SQE with sockopt command and waiting for the CQE. + */ +static int uring_sockopt(int op, int fd, int level, int optname, + const void *optval, socklen_t optlen) +{ + struct io_uring_cqe *cqe; + struct io_uring_sqe *sqe; + struct io_uring ring; + int err; + + err = io_uring_queue_init(1, &ring, 0); + if (err) { + log_err("Failed to initialize io_uring ring"); + return err; + } + + sqe = io_uring_get_sqe(&ring); + if (!sqe) { + log_err("Failed to get an SQE"); + return -1; + } + + io_uring_prep_cmd(sqe, op, fd, level, optname, optval, optlen); + + err = io_uring_submit(&ring); + if (err != 1) { + log_err("Failed to submit SQE"); + return err; + } + + err = io_uring_wait_cqe(&ring, &cqe); + if (err) { + log_err("Failed to wait for CQE"); + return err; + } + + err = cqe->res; + + io_uring_queue_exit(&ring); + + return err; +} + +static int uring_setsockopt(int fd, int level, int optname, const void *optval, + socklen_t optlen) +{ + return uring_sockopt(SOCKET_URING_OP_SETSOCKOPT, fd, level, optname, + optval, optlen); +} + +static int uring_getsockopt(int fd, int level, int optname, void *optval, + socklen_t *optlen) +{ + int ret = uring_sockopt(SOCKET_URING_OP_GETSOCKOPT, fd, level, optname, + optval, *optlen); + if (ret < 0) + return ret; + + /* Populate optlen back to be compatible with systemcall interface, + * and simplify the test. + */ + *optlen = ret; + + return 0; +} + +/* Execute the setsocktopt operation */ +static int call_setsockopt(bool use_io_uring, int fd, int level, int optname, + const void *optval, socklen_t optlen) +{ + if (use_io_uring) + return uring_setsockopt(fd, level, optname, optval, optlen); + + return setsockopt(fd, level, optname, optval, optlen); +} + +/* Execute the getsocktopt operation */ +static int call_getsockopt(bool use_io_uring, int fd, int level, int optname, + void *optval, socklen_t *optlen) +{ + if (use_io_uring) + return uring_getsockopt(fd, level, optname, optval, optlen); + + return getsockopt(fd, level, optname, optval, optlen); +} + +static int run_test(int cgroup_fd, struct sockopt_test *test, bool use_io_uring) { int sock_fd, err, prog_fd; void *optval = NULL; @@ -980,8 +1092,9 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) test->set_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder; } - err = setsockopt(sock_fd, test->set_level, test->set_optname, - test->set_optval, test->set_optlen); + err = call_setsockopt(use_io_uring, sock_fd, test->set_level, + test->set_optname, test->set_optval, + test->set_optlen); if (err) { if (errno == EPERM && test->error == EPERM_SETSOCKOPT) goto close_sock_fd; @@ -1008,8 +1121,8 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) socklen_t expected_get_optlen = test->get_optlen_ret ?: test->get_optlen; - err = getsockopt(sock_fd, test->get_level, test->get_optname, - optval, &optlen); + err = call_getsockopt(use_io_uring, sock_fd, test->get_level, + test->get_optname, optval, &optlen); if (err) { if (errno == EOPNOTSUPP && test->error == EOPNOTSUPP_GETSOCKOPT) goto free_optval; @@ -1063,7 +1176,11 @@ void test_sockopt(void) if (!test__start_subtest(tests[i].descr)) continue; - ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr); + ASSERT_OK(run_test(cgroup_fd, &tests[i], false), + tests[i].descr); + if (tests[i].io_uring_support) + ASSERT_OK(run_test(cgroup_fd, &tests[i], true), + tests[i].descr); } close(cgroup_fd); -- 2.34.1

1 year, 10 months

2
2
0 0

[PATCH v4 2/2] selftests/ftrace: Add new test case which checks non unique symbol

by Francis Laniel

If name_show() is non unique, this test will try to install a kprobe on this function which should fail returning EADDRNOTAVAIL. On kernel where name_show() is not unique, this test is skipped. Signed-off-by: Francis Laniel <flaniel(a)linux.microsoft.com> --- .../ftrace/test.d/kprobe/kprobe_non_uniq_symbol.tc | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_non_uniq_symbol.tc diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_non_uniq_symbol.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_non_uniq_symbol.tc new file mode 100644 index 000000000000..bc9514428dba --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_non_uniq_symbol.tc @@ -0,0 +1,13 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Test failure of registering kprobe on non unique symbol +# requires: kprobe_events + +SYMBOL='name_show' + +# We skip this test on kernel where SYMBOL is unique or does not exist. +if [ "$(grep -c -E "[[:alnum:]]+ t ${SYMBOL}" /proc/kallsyms)" -le '1' ]; then + exit_unsupported +fi + +! echo "p:test_non_unique ${SYMBOL}" > kprobe_events -- 2.34.1

1 year, 10 months

1
0
0 0

[PATCH bpf-next v6] selftests/bpf: trace_helpers.c: optimize kallsyms cache

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Static ksyms often have problems because the number of symbols exceeds the MAX_SYMS limit. Like changing the MAX_SYMS from 300000 to 400000 in commit e76a014334a6("selftests/bpf: Bump and validate MAX_SYMS") solves the problem somewhat, but it's not the perfect way. This commit uses dynamic memory allocation, which completely solves the problem caused by the limitation of the number of kallsyms. Acked-by: Stanislav Fomichev <sdf(a)google.com> Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- v6: Apply libbpf_ensure_mem() v5: https://lore.kernel.org/lkml/tencent_0E9E1A1C0981678D5E7EA9E4BDBA8EE2200A@q… Release the allocated memory once the load_kallsyms_refresh() upon error given it's dynamically allocated. v4: https://lore.kernel.org/lkml/tencent_59C74613113F0C728524B2A82FE5540A5E09@q… Make sure most cases we don't need the realloc() path to begin with, and check strdup() return value. v3: https://lore.kernel.org/lkml/tencent_50B4B2622FE7546A5FF9464310650C008509@q… Do not use structs and judge ksyms__add_symbol function return value. v2: https://lore.kernel.org/lkml/tencent_B655EE5E5D463110D70CD2846AB3262EED09@q… Do the usual len/capacity scheme here to amortize the cost of realloc, and don't free symbols. v1: https://lore.kernel.org/lkml/tencent_AB461510B10CD484E0B2F62E3754165F2909@q… --- samples/bpf/Makefile | 1 + tools/testing/selftests/bpf/trace_helpers.c | 59 +++++++++++++++++---- 2 files changed, 49 insertions(+), 11 deletions(-) diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 595b98d825ce..a49d0f759f5a 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -199,6 +199,7 @@ TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ TPROGS_CFLAGS += -I$(LIBBPF_INCLUDE) TPROGS_CFLAGS += -I$(srctree)/tools/include TPROGS_CFLAGS += -I$(srctree)/tools/perf +TPROGS_CFLAGS += -I$(srctree)/tools/lib TPROGS_CFLAGS += -DHAVE_ATTR_TEST=0 ifdef SYSROOT diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index f83d9f65c65b..316a7874a12b 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -14,14 +14,48 @@ #include <linux/limits.h> #include <libelf.h> #include <gelf.h> +#ifndef __must_check +#define __must_check +#endif +#include "bpf/libbpf_internal.h" #define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe" #define DEBUGFS_PIPE "/sys/kernel/debug/tracing/trace_pipe" -#define MAX_SYMS 400000 -static struct ksym syms[MAX_SYMS]; +static struct ksym *syms; +static size_t sym_cap; static int sym_cnt; +static int ksyms__add_symbol(const char *name, unsigned long addr) +{ + void *tmp; + + tmp = strdup(name); + if (!tmp) + return -ENOMEM; + syms[sym_cnt].addr = addr; + syms[sym_cnt].name = tmp; + + sym_cnt++; + + return 0; +} + +static void ksyms__free(void) +{ + unsigned int i; + + if (!syms) + return; + + for (i = 0; i < sym_cnt; i++) + free(syms[i].name); + free(syms); + syms = NULL; + sym_cnt = 0; + sym_cap = 0; +} + static int ksym_cmp(const void *p1, const void *p2) { return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr; @@ -33,9 +67,7 @@ int load_kallsyms_refresh(void) char func[256], buf[256]; char symbol; void *addr; - int i = 0; - - sym_cnt = 0; + int ret; f = fopen("/proc/kallsyms", "r"); if (!f) @@ -46,17 +78,22 @@ int load_kallsyms_refresh(void) break; if (!addr) continue; - if (i >= MAX_SYMS) - return -EFBIG; - syms[i].addr = (long) addr; - syms[i].name = strdup(func); - i++; + ret = libbpf_ensure_mem((void **) &syms, &sym_cap, + sizeof(struct ksym), sym_cnt + 1); + if (ret) + goto error; + ret = ksyms__add_symbol(func, (unsigned long)addr); + if (ret) + goto error; } fclose(f); - sym_cnt = i; qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp); return 0; + +error: + ksyms__free(); + return ret; } int load_kallsyms(void) -- 2.39.3

1 year, 10 months

2
4
0 0

[PATCH net-next,v2] selftests: bonding: create directly devices in the target namespaces

by Zhengchao Shao

If failed to set link1_1 to netns client, we should delete link1_1 in the cleanup path. But if set link1_1 to netns client successfully, delete link1_1 will report warning. So it will be safer creating directly the devices in the target namespaces. Reported-by: Hangbin Liu <liuhangbin(a)gmail.com> Closes: https://lore.kernel.org/all/ZNyJx1HtXaUzOkNA@Laptop-X1/ Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- v2: create directly devices in the target namespaces --- .../drivers/net/bonding/bond-arp-interval-causes-panic.sh | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh index 7b2d421f09cf..fe7c34f89fc7 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh @@ -22,14 +22,12 @@ server_ip4=192.168.1.254 echo 180 >/proc/sys/kernel/panic # build namespaces -ip link add dev link1_1 type veth peer name link1_2 - ip netns add "server" -ip link set dev link1_2 netns server up name eth0 +ip netns add "client" +ip link add dev eth0 netns client type veth peer name eth0 netns server +ip netns exec server ip link set dev eth0 up ip netns exec server ip addr add ${server_ip4}/24 dev eth0 -ip netns add "client" -ip link set dev link1_1 netns client down name eth0 ip netns exec client ip link add dev bond0 down type bond mode 1 \ miimon 100 all_slaves_active 1 ip netns exec client ip link set dev eth0 down master bond0 -- 2.34.1

1 year, 10 months

3
2
0 0

[PATCH V3 0/7] AMD Pstate Preferred Core

by Meng Li

Hi all: The core frequency is subjected to the process variation in semiconductors. Not all cores are able to reach the maximum frequency respecting the infrastructure limits. Consequently, AMD has redefined the concept of maximum frequency of a part. This means that a fraction of cores can reach maximum frequency. To find the best process scheduling policy for a given scenario, OS needs to know the core ordering informed by the platform through highest performance capability register of the CPPC interface. Earlier implementations of AMD Pstate Preferred Core only support a static core ranking and targeted performance. Now it has the ability to dynamically change the preferred core based on the workload and platform conditions and accounting for thermals and aging. AMD Pstate driver utilizes the functions and data structures provided by the ITMT architecture to enable the scheduler to favor scheduling on cores which can be get a higher frequency with lower voltage. We call it AMD Pstate Preferrred Core. Here sched_set_itmt_core_prio() is called to set priorities and sched_set_itmt_support() is called to enable ITMT feature. AMD Pstate driver uses the highest performance value to indicate the priority of CPU. The higher value has a higher priority. AMD Pstate driver will provide an initial core ordering at boot time. It relies on the CPPC interface to communicate the core ranking to the operating system and scheduler to make sure that OS is choosing the cores with highest performance firstly for scheduling the process. When AMD Pstate driver receives a message with the highest performance change, it will update the core ranking. Changes form V2->V3: - x86: - - Modify kconfig and description. - cpufreq: amd-pstate: - - Add Co-developed-by tag in commit message. - cpufreq: - - Modify commit message. - Documentation: amd-pstate: - - Modify inappropriate descriptions. Changes form V1->V2: - acpi: cppc: - - Add reference link. - cpufreq: - - Moidfy link error. - cpufreq: amd-pstate: - - Init the priorities of all online CPUs - - Use a single variable to represent the status of Preferred Core. - Documentation: - - Default enabled preferred core. - Documentation: amd-pstate: - - Modify inappropriate descriptions. - - Default enabled preferred core. - - Use a single variable to represent the status of Preferred Core. Meng Li (7): x86: Drop CPU_SUP_INTEL from SCHED_MC_PRIO for the expansion. acpi: cppc: Add get the highest performance cppc control cpufreq: amd-pstate: Enable AMD Pstate Preferred Core Supporting. cpufreq: Add a notification message that the highest perf has changed cpufreq: amd-pstate: Update AMD Pstate Preferred Core ranking dynamically Documentation: amd-pstate: introduce AMD Pstate Preferred Core Documentation: introduce AMD Pstate Preferrd Core mode kernel command line options .../admin-guide/kernel-parameters.txt | 5 + Documentation/admin-guide/pm/amd-pstate.rst | 53 ++++++ arch/x86/Kconfig | 5 +- drivers/acpi/cppc_acpi.c | 13 ++ drivers/acpi/processor_driver.c | 6 + drivers/cpufreq/amd-pstate.c | 152 ++++++++++++++++-- drivers/cpufreq/cpufreq.c | 13 ++ include/acpi/cppc_acpi.h | 5 + include/linux/amd-pstate.h | 1 + include/linux/cpufreq.h | 4 + 10 files changed, 239 insertions(+), 18 deletions(-) -- 2.34.1

1 year, 10 months

4
17
0 0

[PATCH v3 2/2] selftests/net: replace ternary operator with min()/max()

by Mahmoud Maatuq

Fix the following coccicheck warning: tools/testing/selftests/net/udpgso_bench_tx.c:297:18-19: WARNING opportunity for min() tools/testing/selftests/net/udpgso_bench_tx.c:354:27-28: WARNING opportunity for min() tools/testing/selftests/net/so_txtime.c:129:24-26: WARNING opportunity for max() tools/testing/selftests/net/so_txtime.c:96:30-31: WARNING opportunity for max() Signed-off-by: Mahmoud Maatuq <mahmoudmatook.mm(a)gmail.com> --- changes in v3: remove Suggested-by tag fix wrong comment inside selftests/net/Makefile changes in v2: cast var cfg_mss to int to avoid static assertion after providing a stricter version of min() that does signedness checking. --- tools/testing/selftests/net/Makefile | 2 ++ tools/testing/selftests/net/so_txtime.c | 7 ++++--- tools/testing/selftests/net/udpgso_bench_tx.c | 6 +++--- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 7f3ab2a93ed6..f50f04a513a7 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -3,6 +3,8 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES) +# Additional include path to include kselftest.h +CFLAGS += -I../ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \ rtnetlink.sh xfrm_policy.sh test_blackhole_dev.sh diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 2672ac0b6d1f..2936174e7de4 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -33,6 +33,8 @@ #include <unistd.h> #include <poll.h> +#include "kselftest.h" + static int cfg_clockid = CLOCK_TAI; static uint16_t cfg_port = 8000; static int cfg_variance_us = 4000; @@ -93,8 +95,7 @@ static void do_send_one(int fdt, struct timed_send *ts) msg.msg_controllen = sizeof(control); tdeliver = glob_tstart + ts->delay_us * 1000; - tdeliver_max = tdeliver_max > tdeliver ? - tdeliver_max : tdeliver; + tdeliver_max = max(tdeliver_max, tdeliver); cm = CMSG_FIRSTHDR(&msg); cm->cmsg_level = SOL_SOCKET; @@ -126,7 +127,7 @@ static void do_recv_one(int fdr, struct timed_send *ts) error(1, 0, "read: %dB", ret); tstop = (gettime_ns(cfg_clockid) - glob_tstart) / 1000; - texpect = ts->delay_us >= 0 ? ts->delay_us : 0; + texpect = max(ts->delay_us, 0); fprintf(stderr, "payload:%c delay:%lld expected:%lld (us)\n", rbuf[0], (long long)tstop, (long long)texpect); diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c index 477392715a9a..6bd32a312901 100644 --- a/tools/testing/selftests/net/udpgso_bench_tx.c +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -25,7 +25,7 @@ #include <sys/types.h> #include <unistd.h> -#include "../kselftest.h" +#include "kselftest.h" #ifndef ETH_MAX_MTU #define ETH_MAX_MTU 0xFFFFU @@ -294,7 +294,7 @@ static int send_udp(int fd, char *data) total_len = cfg_payload_len; while (total_len) { - len = total_len < cfg_mss ? total_len : cfg_mss; + len = min(total_len, (int)cfg_mss); ret = sendto(fd, data, len, cfg_zerocopy ? MSG_ZEROCOPY : 0, cfg_connected ? NULL : (void *)&cfg_dst_addr, @@ -351,7 +351,7 @@ static int send_udp_sendmmsg(int fd, char *data) error(1, 0, "sendmmsg: exceeds max_nr_msg"); iov[i].iov_base = data + off; - iov[i].iov_len = cfg_mss < left ? cfg_mss : left; + iov[i].iov_len = min(cfg_mss, left); mmsgs[i].msg_hdr.msg_iov = iov + i; mmsgs[i].msg_hdr.msg_iovlen = 1; -- 2.34.1

1 year, 10 months

2
1
0 0

[PATCH] KVM: selftests: Add tests - invalid inputs for KVM_CREATE_GUEST_MEMFD

by Ackerley Tng

Test that invalid inputs for KVM_CREATE_GUEST_MEMFD, such as non-page-aligned page size and invalid flags, are rejected by the KVM_CREATE_GUEST_MEMFD with EINVAL Signed-off-by: Ackerley Tng <ackerleytng(a)google.com> --- .../testing/selftests/kvm/guest_memfd_test.c | 33 +++++++++++++++++++ .../selftests/kvm/include/kvm_util_base.h | 11 +++++-- 2 files changed, 42 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index eb93c608a7e0..a8e37f001297 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -90,6 +90,37 @@ static void test_fallocate(int fd, size_t page_size, size_t total_size) TEST_ASSERT(!ret, "fallocate to restore punched hole should succeed"); } +static void test_create_guest_memfd_invalid(struct kvm_vm *vm, size_t page_size) +{ + int fd; + uint64_t size; + uint64_t flags; + uint64_t valid_flags = 0; + + for (size = 1; size < page_size; size++) { + fd = __vm_create_guest_memfd(vm, size, 0); + TEST_ASSERT( + fd == -1, + "Creating guest memfds with non-page-aligned page sizes should fail"); + TEST_ASSERT(errno == EINVAL, "... and errno should be set to EINVAL"); + } + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + valid_flags = KVM_GUEST_MEMFD_ALLOW_HUGEPAGE; +#endif + + for (flags = 1; flags; flags <<= 1) { + if (flags & valid_flags) + continue; + + fd = __vm_create_guest_memfd(vm, page_size, flags); + TEST_ASSERT( + fd == -1, + "Creating guest memfds with invalid flags should fail"); + TEST_ASSERT(errno == EINVAL, "... and errno should be set to EINVAL"); + } +} + int main(int argc, char *argv[]) { @@ -103,6 +134,8 @@ int main(int argc, char *argv[]) vm = vm_create_barebones(); + test_create_guest_memfd_invalid(vm, page_size); + fd = vm_create_guest_memfd(vm, total_size, 0); test_file_read_write(fd); diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index 39b38c75b99c..8bdfadd72349 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -474,7 +474,8 @@ static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name) } void vm_create_irqchip(struct kvm_vm *vm); -static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, + +static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, uint64_t flags) { struct kvm_create_guest_memfd gmem = { @@ -482,7 +483,13 @@ static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, .flags = flags, }; - int fd = __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &gmem); + return __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &gmem); +} + +static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, + uint64_t flags) +{ + int fd = __vm_create_guest_memfd(vm, size, flags); TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_GUEST_MEMFD, fd)); return fd; -- 2.42.0.rc1.204.g551eb34607-goog

1 year, 10 months

2
1
0 0

[PATCH net-next] selftests: bonding: delete link1_1 in the cleanup path

by Zhengchao Shao

If failed to set link1_1 to netns client, we should delete link1_1 in the cleanup path. But if set link1_1 to netns client successfully, delete link1_1 will report warning. So delete link1_1 in the cleanup path and drop any warning message. Reported-by: Hangbin Liu <liuhangbin(a)gmail.com> Closes: https://lore.kernel.org/all/ZNyJx1HtXaUzOkNA@Laptop-X1/ Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- .../drivers/net/bonding/bond-arp-interval-causes-panic.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh index 7b2d421f09cf..2b3c678c5205 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh @@ -11,6 +11,7 @@ finish() { ip netns delete server || true ip netns delete client || true + ip link del link1_1 >/dev/null 2>&1 } trap finish EXIT -- 2.34.1

1 year, 10 months

4
3
0 0

[PATCH 0/2] selftests: Introduce common min()/max() and apply them in net tests

by Mahmoud Maatuq

The first patch introduces a common definition of the min() and max() macros for use in multiple files under selftests. This avoids the redundancy of having scattered local definitions and prepares the groundwork for other files to simply include kselftest.h. The second patch then applies these new macros in the selftests/net files, replacing the ternary operations. This directly addresses several coccicheck warnings, making the code cleaner and more maintainable Mahmoud Maatuq (2): selftests: Provide local define of min() and max() selftests/net: replace ternary operator with min()/max() tools/testing/selftests/kselftest.h | 7 +++++++ tools/testing/selftests/net/Makefile | 2 ++ tools/testing/selftests/net/so_txtime.c | 7 ++++--- tools/testing/selftests/net/udpgso_bench_tx.c | 6 +++--- 4 files changed, 16 insertions(+), 6 deletions(-) -- 2.34.1

1 year, 10 months

4
10
0 0

kselftest/next kselftest-seccomp: 2 runs, 1 regressions (v6.5-rc3-32-g9b1db732866b)

by kernelci.org bot

kselftest/next kselftest-seccomp: 2 runs, 1 regressions (v6.5-rc3-32-g9b1db732866b) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------+-------+---------------+----------+------------------------------+------------ mt8173-elm-hana | arm64 | lab-collabora | gcc-10 | defconfig+kse...4-chromebook | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.5-rc3-32-g9b1… Test: kselftest-seccomp Tree: kselftest Branch: next Describe: v6.5-rc3-32-g9b1db732866b URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: 9b1db732866bee060b9bca9493e5ebf5e8874c48 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------+-------+---------------+----------+------------------------------+------------ mt8173-elm-hana | arm64 | lab-collabora | gcc-10 | defconfig+kse...4-chromebook | 1 Details: https://kernelci.org/test/plan/id/64dd560fd1781e463035b1e3 Results: 0 PASS, 1 FAIL, 0 SKIP Full config: defconfig+kselftest+arm64-chromebook Compiler: gcc-10 (aarch64-linux-gnu-gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//kselftest/next/v6.5-rc3-32-g9b1db732866b/arm6… HTML log: https://storage.kernelci.org//kselftest/next/v6.5-rc3-32-g9b1db732866b/arm6… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bullseye-kselftest/2023062… * kselftest-seccomp.login: https://kernelci.org/test/case/id/64dd560fd1781e463035b1e4 failing since 303 days (last pass: linux-kselftest-next-6.0-rc2-11-g144eeb2fc761, first fail: v6.1-rc1)

1 year, 10 months

1
0
0 0

kselftest/next build: 8 builds: 0 failed, 8 passed, 1 warning (v6.5-rc3-32-g9b1db732866b)

by kernelci.org bot

kselftest/next build: 8 builds: 0 failed, 8 passed, 1 warning (v6.5-rc3-32-g9b1db732866b) Full Build Summary: https://kernelci.org/build/kselftest/branch/next/kernel/v6.5-rc3-32-g9b1db7… Tree: kselftest Branch: next Git Describe: v6.5-rc3-32-g9b1db732866b Git Commit: 9b1db732866bee060b9bca9493e5ebf5e8874c48 Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 4 unique architectures Warnings Detected: arm64: arm: i386: x86_64: x86_64_defconfig+kselftest (clang-16): 1 warning Warnings summary: 2 vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x13df86 ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- defconfig+kselftest (arm64, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest (arm64, clang-16) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, clang-16) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-16) — PASS, 0 errors, 1 warning, 0 section mismatches Warnings: vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x13df86 --- For more info write to <info(a)kernelci.org>

1 year, 10 months

1
0
0 0

[PATCH v3 0/3] TDX Guest Quote generation support

by Kuppuswamy Sathyanarayanan

Hi All, In TDX guest, the attestation process is used to verify the TDX guest trustworthiness to other entities before provisioning secrets to the guest. The TDX guest attestation process consists of two steps: 1. TDREPORT generation 2. Quote generation. The First step (TDREPORT generation) involves getting the TDX guest measurement data in the format of TDREPORT which is further used to validate the authenticity of the TDX guest. The second step involves sending the TDREPORT to a Quoting Enclave (QE) server to generate a remotely verifiable Quote. TDREPORT by design can only be verified on the local platform. To support remote verification of the TDREPORT, TDX leverages Intel SGX Quoting Enclave to verify the TDREPORT locally and convert it to a remotely verifiable Quote. Although attestation software can use communication methods like TCP/IP or vsock to send the TDREPORT to QE, not all platforms support these communication models. So TDX GHCI specification [1] defines a method for Quote generation via hypercalls. Please check the discussion from Google [2] and Alibaba [3] which clarifies the need for hypercall based Quote generation support. This patch set adds this support. Support for TDREPORT generation already exists in the TDX guest driver. This patchset extends the same driver to add the Quote generation support. Following are the details of the patch set: Patch 1/3 -> Adds event notification IRQ support. Patch 2/3 -> Adds Quote generation support. Patch 3/3 -> Adds selftest support for Quote generation feature. [1] https://cdrdv2.intel.com/v1/dl/getContent/726790, section titled "TDG.VP.VMCALL<GetQuote>". [2] https://lore.kernel.org/lkml/CAAYXXYxxs2zy_978GJDwKfX5Hud503gPc8=1kQ-+JwG_k… [3] https://lore.kernel.org/lkml/a69faebb-11e8-b386-d591-dbd08330b008@linux.ali… Kuppuswamy Sathyanarayanan (3): x86/tdx: Add TDX Guest event notify interrupt support virt: tdx-guest: Add Quote generation support selftests/tdx: Test GetQuote TDX attestation feature Documentation/virt/coco/tdx-guest.rst | 11 ++ arch/x86/coco/tdx/tdx.c | 194 +++++++++++++++++++ arch/x86/include/asm/tdx.h | 8 + drivers/virt/coco/tdx-guest/tdx-guest.c | 175 ++++++++++++++++- include/uapi/linux/tdx-guest.h | 44 +++++ tools/testing/selftests/tdx/tdx_guest_test.c | 65 ++++++- 6 files changed, 490 insertions(+), 7 deletions(-) -- 2.34.1

1 year, 10 months

10
38
0 0

Repo for tests which fail currently?

by Wolfram Sang

Hi all, for my talk at EOSS23 about object life-time issues[1], I created a loose set of tests checking some longstanding problems in the Linux Kernel. I would like to improve these tests. Now, I wonder where I could contribute them to because their scope seems different to me. They are not for regression testing because I don't have a fix for most of them. Some fixes mean rewriting private data allocations for a whole subsystem and drivers. The tests are rather meant for documenting known problems and checking if someone started working on it. But it seems that kselftest (and LTP also?) only accept tests which do not fail by default. The question is now, is there another test collection project I could contribute these tests to? I'd be very happy for pointers, I started looking around but to no avail... Thanks and happy hacking, Wolfram [1] https://www.youtube.com/watch?v=HCiJL7djGw8

1 year, 10 months

3
5
0 0

[PATCH 0/3] Avoid TCP resets when using ECMP for load-balancing between multiple servers.

by Sriram Yagnaraman

All packets in the same flow (L3/L4 depending on multipath hash policy) should be directed to the same target, but after [0]/[1] we see stray packets directed towards other targets. This, for instance, causes RST to be sent on TCP connections. The first two patches solve the problem by ignoring route hints for destinations that are part of multipath group, by using new SKB flags for IPv4 and IPv6. The third patch is a selftest that tests the scenario. Thanks to Ido, for reviewing and suggesting a way forward in [2]. [0]: commit 02b24941619f ("ipv4: use dst hint for ipv4 list receive") [1]: commit 197dbf24e360 ("ipv6: introduce and uses route look hints for list input.") [2]: https://lore.kernel.org/netdev/20230815201048.1796-1-sriram.yagnaraman@est.… Sriram Yagnaraman (3): ipv4: ignore dst hint for multipath routes ipv6: ignore dst hint for multipath routes selftests: forwarding: Add test for load-balancing between multiple servers include/linux/ipv6.h | 1 + include/net/ip.h | 1 + net/ipv4/ip_input.c | 3 +- net/ipv4/route.c | 1 + net/ipv6/ip6_input.c | 3 +- net/ipv6/route.c | 2 + .../testing/selftests/net/forwarding/Makefile | 1 + .../net/forwarding/router_multipath_vip.sh | 403 ++++++++++++++++++ 8 files changed, 413 insertions(+), 2 deletions(-) create mode 100755 tools/testing/selftests/net/forwarding/router_multipath_vip.sh -- 2.34.1

1 year, 10 months

2
8
0 0

Re: [PATCH v3 3/3] selftests/tdx: Test GetQuote TDX attestation feature

by Thomas Gleixner

On Thu, Jun 22 2023 at 14:01, Erdem Aktas wrote: > On Mon, Jun 12, 2023 at 12:03 PM Dan Williams <dan.j.williams(a)intel.com> > wrote: >> Now multiple >> confidential computing vendors trying to develop similar flows with >> differentiated formats where that differentiation need not leak over the >> ABI boundary. >> > > <Just my personal opinion below> > I agree with this statement in the high level but it is also somehow > surprising for me after all the discussion happened around this topic. > Honestly, I feel like there are multiple versions of "Intel" working in > different directions. > > If we want multiple vendors trying to do the similar things behind a common > ABI, it should start with the spec. Since this comment is coming from > Intel, I wonder if there is any plan to combine the GHCB and GHCI > interfaces under common ABI in the future or why it did not even happen in > the first place. You are conflating things here. The GETQUOTE TDVMCALL interface is part of the Guest-Hypervisor Communication Interface (GHCI), which is a firmware interface. Firmware (likewise hardware) interfaces have the unfortunate property that they are mostly cast in stone. But that has absolutely nothing to do with the way how the kernel implements support for them. If we'd follow your reasoning then we'd have a gazillion of vendor specific SCSI stacks in the kernel. > What I see is that Intel has GETQUOTE TDVMCALL interface in its spec and > again Intel does not really want to provide support for it in linux. It > feels really frustrating. Intel definitely wants to provide support for this interface and this very thread is about that support. But Intel is not in a position to define what the kernel community has to accept or not, neither is Google. Sure, it would have been more efficient to come up with a better interface earlier, but that's neither an Intel nor a TDX specific problem. It's just how kernel development works. Some ideas look good on first sight, some stuff slips through and at some point the maintainers realize that this is not the way to go and request a proper generalized and maintainable implementation. If you can provide compelling technical reasons why the IOCTL is the better and more maintainable approach for the kernel, then we are all ears and happy to debate that on the technical level. Feel free to be frustrated, but I can assure you that the only way to resolve this dilemma is to sit down and actually get work done in a way which is acceptable by the kernel community at the technical level. Everything else is frustrating for everyone involved, not only you. Thanks, tglx

1 year, 10 months

1
0
0 0

[PATCH] selftests: alsa: make LDLIBS consistent

by Ricardo B. Marliere

In kselftest_deps.sh script, the level 3 parser is broken for the alsa subsystem Makefile. Output before patch: $ ./kselftest_deps.sh gcc alsa ======================================================== Kselftest Dependency Check for [./kselftest_deps.sh gcc alsa] results... ======================================================== Checked tests defining LDLIBS dependencies -------------------------------------------------------- Total tests with Dependencies: 6 Pass: 2 Fail: 4 -------------------------------------------------------- PASS: alsa/Makefile dependency check passed -lasound PASS: alsa/Makefile dependency check passed -lpthread -------------------------------------------------------- Targets passed build dependency check on system: alsa -------------------------------------------------------- FAIL: alsa/Makefile dependency check: $(shell FAIL: alsa/Makefile dependency check: pkg-config FAIL: alsa/Makefile dependency check: --libs FAIL: alsa/Makefile dependency check: alsa) -------------------------------------------------------- Targets failed build dependency check on system: alsa -------------------------------------------------------- Missing libraries system $(shell alsa) --libs pkg-config -------------------------------------------------------- ======================================================== Output after patch: $ ./kselftest_deps.sh gcc alsa ======================================================== Kselftest Dependency Check for [./kselftest_deps.sh gcc alsa] results... ======================================================== Checked tests defining LDLIBS dependencies -------------------------------------------------------- Total tests with Dependencies: 2 Pass: 2 Fail: 0 -------------------------------------------------------- PASS: alsa/Makefile dependency check passed -lasound PASS: alsa/Makefile dependency check passed -lpthread -------------------------------------------------------- Targets passed build dependency check on system: alsa -------------------------------------------------------- ======================================================== Signed-off-by: Ricardo B. Marliere <rbmarliere(a)gmail.com> --- tools/testing/selftests/alsa/Makefile | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index 5af9ba8a4645..b5670049c4e5 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -2,13 +2,13 @@ # CFLAGS += $(shell pkg-config --cflags alsa) -LDLIBS += $(shell pkg-config --libs alsa) -ifeq ($(LDLIBS),) -LDLIBS += -lasound +VAR_LDLIBS += $(shell pkg-config --libs alsa) +ifeq ($(VAR_LDLIBS),) +VAR_LDLIBS += -lasound endif CFLAGS += -L$(OUTPUT) -Wl,-rpath=./ -LDLIBS+=-lpthread +VAR_LDLIBS+=-lpthread OVERRIDE_TARGETS = 1 @@ -21,7 +21,7 @@ TEST_FILES := conf.d pcm-test.conf include ../lib.mk $(OUTPUT)/libatest.so: conf.c alsa-local.h - $(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@ + $(CC) $(CFLAGS) -shared -fPIC $< $(VAR_LDLIBS) -o $@ $(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) alsa-local.h - $(CC) $(CFLAGS) $< $(LDLIBS) -latest -o $@ + $(CC) $(CFLAGS) $< $(VAR_LDLIBS) -latest -o $@ -- 2.40.1

1 year, 11 months

3
2
0 0

[PATCH] selftests: fix dependency checker script

by Ricardo B. Marliere

This patch fixes inconsistencies in the parsing rules of the levels 1 and 2 of the kselftest_deps.sh. It was added the levels 4 and 5 to account for a few edge cases that are present in some tests, also some minor identation styling have been fixed (s/ /\t/g). Signed-off-by: Ricardo B. Marliere <rbmarliere(a)gmail.com> --- tools/testing/selftests/kselftest_deps.sh | 77 +++++++++++++++++++---- 1 file changed, 65 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/kselftest_deps.sh b/tools/testing/selftests/kselftest_deps.sh index 4bc14d9e8ff1..de59cc8f03c3 100755 --- a/tools/testing/selftests/kselftest_deps.sh +++ b/tools/testing/selftests/kselftest_deps.sh @@ -46,11 +46,11 @@ fi print_targets=0 while getopts "p" arg; do - case $arg in - p) + case $arg in + p) print_targets=1 shift;; - esac + esac done if [ $# -eq 0 ] @@ -92,6 +92,10 @@ pass_cnt=0 # Get all TARGETS from selftests Makefile targets=$(grep -E "^TARGETS +|^TARGETS =" Makefile | cut -d "=" -f2) +# Initially, in LDLIBS related lines, the dep checker needs +# to ignore lines containing the following strings: +filter="\$(VAR_LDLIBS)\|pkg-config\|PKG_CONFIG\|IOURING_EXTRA_LIBS" + # Single test case if [ $# -eq 2 ] then @@ -100,6 +104,8 @@ then l1_test $test l2_test $test l3_test $test + l4_test $test + l5_test $test print_results $1 $2 exit $? @@ -113,7 +119,7 @@ fi # Append space at the end of the list to append more tests. l1_tests=$(grep -r --include=Makefile "^LDLIBS" | \ - grep -v "VAR_LDLIBS" | awk -F: '{print $1}') + grep -v "$filter" | awk -F: '{print $1}' | uniq) # Level 2: LDLIBS set dynamically. # @@ -126,7 +132,7 @@ l1_tests=$(grep -r --include=Makefile "^LDLIBS" | \ # Append space at the end of the list to append more tests. l2_tests=$(grep -r --include=Makefile ": LDLIBS" | \ - grep -v "VAR_LDLIBS" | awk -F: '{print $1}') + grep -v "$filter" | awk -F: '{print $1}' | uniq) # Level 3 # memfd and others use pkg-config to find mount and fuse libs @@ -138,11 +144,32 @@ l2_tests=$(grep -r --include=Makefile ": LDLIBS" | \ # VAR_LDLIBS := $(shell pkg-config fuse --libs 2>/dev/null) l3_tests=$(grep -r --include=Makefile "^VAR_LDLIBS" | \ - grep -v "pkg-config" | awk -F: '{print $1}') + grep -v "pkg-config\|PKG_CONFIG" | awk -F: '{print $1}' | uniq) -#echo $l1_tests -#echo $l2_1_tests -#echo $l3_tests +# Level 4 +# some tests may fall back to default using `|| echo -l<libname>` +# if pkg-config doesn't find the libs, instead of using VAR_LDLIBS +# as per level 3 checks. +# e.g: +# netfilter/Makefile +# LDLIBS += $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) +l4_tests=$(grep -r --include=Makefile "^LDLIBS" | \ + grep "pkg-config\|PKG_CONFIG" | awk -F: '{print $1}' | uniq) + +# Level 5 +# some tests may use IOURING_EXTRA_LIBS to add extra libs to LDLIBS, +# which in turn may be defined in a sub-Makefile +# e.g.: +# mm/Makefile +# $(OUTPUT)/gup_longterm: LDLIBS += $(IOURING_EXTRA_LIBS) +l5_tests=$(grep -r --include=Makefile "LDLIBS +=.*\$(IOURING_EXTRA_LIBS)" | \ + awk -F: '{print $1}' | uniq) + +#echo l1_tests $l1_tests +#echo l2_tests $l2_tests +#echo l3_tests $l3_tests +#echo l4_tests $l4_tests +#echo l5_tests $l5_tests all_tests print_results $1 $2 @@ -164,24 +191,32 @@ all_tests() for test in $l3_tests; do l3_test $test done + + for test in $l4_tests; do + l4_test $test + done + + for test in $l5_tests; do + l5_test $test + done } # Use same parsing used for l1_tests and pick libraries this time. l1_test() { test_libs=$(grep --include=Makefile "^LDLIBS" $test | \ - grep -v "VAR_LDLIBS" | \ + grep -v "$filter" | \ sed -e 's/\:/ /' | \ sed -e 's/+/ /' | cut -d "=" -f 2) check_libs $test $test_libs } -# Use same parsing used for l2__tests and pick libraries this time. +# Use same parsing used for l2_tests and pick libraries this time. l2_test() { test_libs=$(grep --include=Makefile ": LDLIBS" $test | \ - grep -v "VAR_LDLIBS" | \ + grep -v "$filter" | \ sed -e 's/\:/ /' | sed -e 's/+/ /' | \ cut -d "=" -f 2) @@ -197,6 +232,24 @@ l3_test() check_libs $test $test_libs } +l4_test() +{ + test_libs=$(grep --include=Makefile "^VAR_LDLIBS\|^LDLIBS" $test | \ + grep "$pkg-config\|PKG_CONFIG$.*|| echo " | \ + sed -e 's/.*|| echo //' | sed -e 's/)$//') + + check_libs $test $test_libs +} + +l5_test() +{ + tests=$(find $(dirname "$test") -type f -name "*.mk") + test_libs=$(grep "^IOURING_EXTRA_LIBS +\?=" $tests | \ + cut -d "=" -f 2) + + check_libs $test $test_libs +} + check_libs() { -- 2.40.1

1 year, 11 months

1
0
0 0

[PATCH v5 00/37] arm64/gcs: Provide support for GCS in userspace

by Mark Brown

The arm64 Guarded Control Stack (GCS) feature provides support for hardware protected stacks of return addresses, intended to provide hardening against return oriented programming (ROP) attacks and to make it easier to gather call stacks for applications such as profiling. When GCS is active a secondary stack called the Guarded Control Stack is maintained, protected with a memory attribute which means that it can only be written with specific GCS operations. The current GCS pointer can not be directly written to by userspace. When a BL is executed the value stored in LR is also pushed onto the GCS, and when a RET is executed the top of the GCS is popped and compared to LR with a fault being raised if the values do not match. GCS operations may only be performed on GCS pages, a data abort is generated if they are not. The combination of hardware enforcement and lack of extra instructions in the function entry and exit paths should result in something which has less overhead and is more difficult to attack than a purely software implementation like clang's shadow stacks. This series implements support for use of GCS by userspace, along with support for use of GCS within KVM guests. It does not enable use of GCS by either EL1 or EL2, this will be implemented separately. Executables are started without GCS and must use a prctl() to enable it, it is expected that this will be done very early in application execution by the dynamic linker or other startup code. For dynamic linking this will be done by checking that everything in the executable is marked as GCS compatible. x86 has an equivalent feature called shadow stacks, this series depends on the x86 patches for generic memory management support for the new guarded/shadow stack page type and shares APIs as much as possible. As there has been extensive discussion with the wider community around the ABI for shadow stacks I have as far as practical kept implementation decisions close to those for x86, anticipating that review would lead to similar conclusions in the absence of strong reasoning for divergence. The main divergence I am concious of is that x86 allows shadow stack to be enabled and disabled repeatedly, freeing the shadow stack for the thread whenever disabled, while this implementation keeps the GCS allocated after disable but refuses to reenable it. This is to avoid races with things actively walking the GCS during a disable, we do anticipate that some systems will wish to disable GCS at runtime but are not aware of any demand for subsequently reenabling it. x86 uses an arch_prctl() to manage enable and disable, since only x86 and S/390 use arch_prctl() a generic prctl() was proposed[1] as part of a patch set for the equivalent RISC-V zisslpcfi feature which I initially adopted fairly directly but following review feedback has been revised quite a bit. There is an open issue with support for CRIU, on x86 this required the ability to set the GCS mode via ptrace. This series supports configuring mode bits other than enable/disable via ptrace but it needs to be confirmed if this is sufficient. There's a few bits where I'm not convinced with where I've placed things, in particular the GCS write operation is in the GCS header not in uaccess.h, I wasn't sure what was clearest there and am probably too close to the code to have a clear opinion. The reporting of GCS in /proc/PID/smaps is also a bit awkward. The series depends on the x86 shadow stack support: https://lore.kernel.org/lkml/20230227222957.24501-1-rick.p.edgecombe@intel.… I've rebased this onto v6.5-rc4 but not included it in the series in order to avoid confusion with Rick's work and cut down the size of the series, you can see the branch at: https://git.kernel.org/pub/scm/linux/kernel/git/broonie/misc.git arm64-gcs [1] https://lore.kernel.org/lkml/20230213045351.3945824-1-debug@rivosinc.com/ Pending feedback from Catalin: - Switch copy_to_user_gcs() to be put_user_gcs(). Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v5: - Don't map any permissions for user GCSs, we always use EL0 accessors or use a separate mapping of the page. - Reduce the standard size of the GCS to RLIMIT_STACK/2. - Enforce a PAGE_SIZE alignment requirement on map_shadow_stack(). - Clarifications and fixes to documentation. - More tests. - Link to v4: https://lore.kernel.org/r/20230807-arm64-gcs-v4-0-68cfa37f9069@kernel.org Changes in v4: - Implement flags for map_shadow_stack() allowing the cap and end of stack marker to be enabled independently or not at all. - Relax size and alignment requirements for map_shadow_stack(). - Add more blurb explaining the advantages of hardware enforcement. - Link to v3: https://lore.kernel.org/r/20230731-arm64-gcs-v3-0-cddf9f980d98@kernel.org Changes in v3: - Rebase onto v6.5-rc4. - Add a GCS barrier on context switch. - Add a GCS stress test. - Link to v2: https://lore.kernel.org/r/20230724-arm64-gcs-v2-0-dc2c1d44c2eb@kernel.org Changes in v2: - Rebase onto v6.5-rc3. - Rework prctl() interface to allow each bit to be locked independently. - map_shadow_stack() now places the cap token based on the size requested by the caller not the actual space allocated. - Mode changes other than enable via ptrace are now supported. - Expand test coverage. - Various smaller fixes and adjustments. - Link to v1: https://lore.kernel.org/r/20230716-arm64-gcs-v1-0-bf567f93bba6@kernel.org --- Mark Brown (37): arm64/mm: Restructure arch_validate_flags() for extensibility prctl: arch-agnostic prctl for shadow stack arm64: Document boot requirements for Guarded Control Stacks arm64/gcs: Document the ABI for Guarded Control Stacks arm64/sysreg: Add new system registers for GCS arm64/sysreg: Add definitions for architected GCS caps arm64/gcs: Add manual encodings of GCS instructions arm64/gcs: Provide copy_to_user_gcs() arm64/cpufeature: Runtime detection of Guarded Control Stack (GCS) arm64/mm: Allocate PIE slots for EL0 guarded control stack mm: Define VM_SHADOW_STACK for arm64 when we support GCS arm64/mm: Map pages for guarded control stack KVM: arm64: Manage GCS registers for guests arm64/gcs: Allow GCS usage at EL0 and EL1 arm64/idreg: Add overrride for GCS arm64/hwcap: Add hwcap for GCS arm64/traps: Handle GCS exceptions arm64/mm: Handle GCS data aborts arm64/gcs: Context switch GCS state for EL0 arm64/gcs: Allocate a new GCS for threads with GCS enabled arm64/gcs: Implement shadow stack prctl() interface arm64/mm: Implement map_shadow_stack() arm64/signal: Set up and restore the GCS context for signal handlers arm64/signal: Expose GCS state in signal frames arm64/ptrace: Expose GCS via ptrace and core files arm64: Add Kconfig for Guarded Control Stack (GCS) kselftest/arm64: Verify the GCS hwcap kselftest/arm64: Add GCS as a detected feature in the signal tests kselftest/arm64: Add framework support for GCS to signal handling tests kselftest/arm64: Allow signals tests to specify an expected si_code kselftest/arm64: Always run signals tests with GCS enabled kselftest/arm64: Add very basic GCS test program kselftest/arm64: Add a GCS test program built with the system libc kselftest/arm64: Add test coverage for GCS mode locking selftests/arm64: Add GCS signal tests kselftest/arm64: Add a GCS stress test kselftest/arm64: Enable GCS for the FP stress tests Documentation/admin-guide/kernel-parameters.txt | 3 + Documentation/arch/arm64/booting.rst | 22 + Documentation/arch/arm64/elf_hwcaps.rst | 3 + Documentation/arch/arm64/gcs.rst | 233 +++++++ Documentation/arch/arm64/index.rst | 1 + Documentation/filesystems/proc.rst | 2 +- arch/arm64/Kconfig | 19 + arch/arm64/include/asm/cpufeature.h | 6 + arch/arm64/include/asm/el2_setup.h | 17 + arch/arm64/include/asm/esr.h | 28 +- arch/arm64/include/asm/exception.h | 2 + arch/arm64/include/asm/gcs.h | 106 +++ arch/arm64/include/asm/hwcap.h | 1 + arch/arm64/include/asm/kvm_arm.h | 4 +- arch/arm64/include/asm/kvm_host.h | 12 + arch/arm64/include/asm/mman.h | 20 +- arch/arm64/include/asm/pgtable-prot.h | 14 +- arch/arm64/include/asm/processor.h | 7 + arch/arm64/include/asm/sysreg.h | 20 + arch/arm64/include/asm/uaccess.h | 42 ++ arch/arm64/include/uapi/asm/hwcap.h | 1 + arch/arm64/include/uapi/asm/ptrace.h | 8 + arch/arm64/include/uapi/asm/sigcontext.h | 9 + arch/arm64/kernel/cpufeature.c | 19 + arch/arm64/kernel/cpuinfo.c | 1 + arch/arm64/kernel/entry-common.c | 23 + arch/arm64/kernel/idreg-override.c | 2 + arch/arm64/kernel/process.c | 89 +++ arch/arm64/kernel/ptrace.c | 59 ++ arch/arm64/kernel/signal.c | 237 ++++++- arch/arm64/kernel/traps.c | 11 + arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 17 + arch/arm64/kvm/sys_regs.c | 22 + arch/arm64/mm/Makefile | 1 + arch/arm64/mm/fault.c | 79 ++- arch/arm64/mm/gcs.c | 225 +++++++ arch/arm64/mm/mmap.c | 13 +- arch/arm64/tools/cpucaps | 1 + arch/arm64/tools/sysreg | 55 ++ fs/proc/task_mmu.c | 3 + include/linux/mm.h | 16 +- include/linux/syscalls.h | 1 + include/uapi/asm-generic/unistd.h | 5 +- include/uapi/linux/elf.h | 1 + include/uapi/linux/prctl.h | 22 + kernel/sys.c | 30 + kernel/sys_ni.c | 1 + tools/testing/selftests/arm64/Makefile | 2 +- tools/testing/selftests/arm64/abi/hwcap.c | 19 + tools/testing/selftests/arm64/fp/assembler.h | 15 + tools/testing/selftests/arm64/fp/fpsimd-test.S | 2 + tools/testing/selftests/arm64/fp/sve-test.S | 2 + tools/testing/selftests/arm64/fp/za-test.S | 2 + tools/testing/selftests/arm64/fp/zt-test.S | 2 + tools/testing/selftests/arm64/gcs/.gitignore | 5 + tools/testing/selftests/arm64/gcs/Makefile | 24 + tools/testing/selftests/arm64/gcs/asm-offsets.h | 0 tools/testing/selftests/arm64/gcs/basic-gcs.c | 356 ++++++++++ tools/testing/selftests/arm64/gcs/gcs-locking.c | 200 ++++++ .../selftests/arm64/gcs/gcs-stress-thread.S | 311 +++++++++ tools/testing/selftests/arm64/gcs/gcs-stress.c | 532 +++++++++++++++ tools/testing/selftests/arm64/gcs/gcs-util.h | 100 +++ tools/testing/selftests/arm64/gcs/libc-gcs.c | 742 +++++++++++++++++++++ tools/testing/selftests/arm64/signal/.gitignore | 1 + .../testing/selftests/arm64/signal/test_signals.c | 17 +- .../testing/selftests/arm64/signal/test_signals.h | 6 + .../selftests/arm64/signal/test_signals_utils.c | 32 +- .../selftests/arm64/signal/test_signals_utils.h | 39 ++ .../arm64/signal/testcases/gcs_exception_fault.c | 59 ++ .../selftests/arm64/signal/testcases/gcs_frame.c | 78 +++ .../arm64/signal/testcases/gcs_write_fault.c | 67 ++ .../selftests/arm64/signal/testcases/testcases.c | 7 + .../selftests/arm64/signal/testcases/testcases.h | 1 + 73 files changed, 4096 insertions(+), 38 deletions(-) --- base-commit: e514f673179ed8af6c64d79f8d43e2569ad6cb9f change-id: 20230303-arm64-gcs-e311ab0d8729 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year, 11 months

4
42
0 0

[PATCH v2 0/2] selftests: cachestat: fix run on older kernels

by Andre Przywara

I ran all kernel selftests on some test machine, and stumbled upon cachestat failing (among others). These patches fix the run on older kernels and when the current directory is on a tmpfs instance. I dropped the first two fix patches from v1, since Shuah applied those already. [PATCH v2 1/2] is almost the same as [PATCH 3/3] from v1, but using the proper skip function from kselftest.h. I am not sure if Shuah applied that already, if yes, it's not a big problem, the output is the same. Patch 2/2 implements the tmpfs detection that Nhat suggested the last time (many thanks for pointing me to statfs and the magics!). Cheers, Andre Andre Przywara (2): selftests: cachestat: test for cachestat availability selftests: cachestat: catch failing fsync test on tmpfs .../selftests/cachestat/test_cachestat.c | 80 +++++++++++++++---- 1 file changed, 65 insertions(+), 15 deletions(-) -- 2.25.1

1 year, 11 months

2
4
0 0

[PATCH] selftests: Keep symlinks, when possible

by Björn Töpel

From: Björn Töpel <bjorn(a)rivosinc.com> When kselftest is built/installed with the 'gen_tar' target, rsync is used for the installation step to copy files. Extra care is needed for tests that have symlinks. Commit ae108c48b5d2 ("selftests: net: Fix cross-tree inclusion of scripts") added '-L' (transform symlink into referent file/dir) to rsync, to fix dangling links. However, that broke some tests where the symlink (being a symlink) is part of the test (e.g. exec:execveat). Use rsync's '--copy-unsafe-links' that does right thing. Fixes: ae108c48b5d2 ("selftests: net: Fix cross-tree inclusion of scripts") Signed-off-by: Björn Töpel <bjorn(a)rivosinc.com> --- tools/testing/selftests/lib.mk | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index d17854285f2b..118e0964bda9 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -106,7 +106,7 @@ endef run_tests: all ifdef building_out_of_srctree @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ - rsync -aLq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \ + rsync -aq --copy-unsafe-links $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \ fi @if [ "X$(TEST_PROGS)" != "X" ]; then \ $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) \ @@ -120,7 +120,7 @@ endif define INSTALL_SINGLE_RULE $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)) - $(if $(INSTALL_LIST),rsync -aL $(INSTALL_LIST) $(INSTALL_PATH)/) + $(if $(INSTALL_LIST),rsync -a --copy-unsafe-links $(INSTALL_LIST) $(INSTALL_PATH)/) endef define INSTALL_RULE base-commit: f7757129e3dea336c407551c98f50057c22bb266 -- 2.39.2

1 year, 11 months

2
1
0 0

[PATCH v4 00/10] kunit: Add dynamically-extending log

by Richard Fitzgerald

This patch chain changes the logging implementation to use string_stream so that the log will grow dynamically. The first 8 patches add test code for string_stream, and make some changes to string_stream needed to be able to use it for the log. The final patch adds a performance report of string_stream. CHANGES SINCE V3: Completely rewritten to use string_stream instead of implementing a separate extending-buffer implementation for logging. I have used the performance test from the final patch on my original fixed-size-fragment implementation from V3 to get a comparison of the two implementations (run on i3-8145UE CPU @ 2.20GHz): string_stream V3 fixed-size-buffer Time elapsed: 7748 us 3251 us Total string length: 573890 573890 Bytes requested: 823994 728336 Actual bytes allocated: 1061440 728352 I don't think the difference is enough to be worth complicating the string_stream implementation with my fixed-fragment implementation from V3 of this patch chain. Richard Fitzgerald (10): kunit: string-stream: Improve testing of string_stream kunit: string-stream: Don't create a fragment for empty strings kunit: string-stream: Add cases for adding empty strings to a string_stream kunit: string-stream: Add option to make all lines end with newline kunit: string-stream: Add cases for string_stream newline appending kunit: string-stream: Pass struct kunit to string_stream_get_string() kunit: string-stream: Decouple string_stream from kunit kunit: string-stream: Add test for freeing resource-managed string_stream kunit: Use string_stream for test log kunit: string-stream: Test performance of string_stream include/kunit/test.h | 14 +- lib/kunit/Makefile | 5 +- lib/kunit/debugfs.c | 36 ++- lib/kunit/kunit-test.c | 52 +--- lib/kunit/log-test.c | 72 ++++++ lib/kunit/string-stream-test.c | 447 +++++++++++++++++++++++++++++++-- lib/kunit/string-stream.c | 129 +++++++--- lib/kunit/string-stream.h | 22 +- lib/kunit/test.c | 48 +--- 9 files changed, 656 insertions(+), 169 deletions(-) create mode 100644 lib/kunit/log-test.c -- 2.30.2

1 year, 11 months

4
32
0 0

clang-17: selftests: sgx: clang: error: -z noexecstack: 'linker' input unused [-Werror,-Wunused-command-line-argument]

by Naresh Kamboju

Recently we have updated the toolchain clang-17 version. While building selftests sgx following warnings / errors noticed on the Linux next with clang-17. Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> sgx/main.o clang: error: -z noexecstack: 'linker' input unused [-Werror,-Wunused-command-line-argument] Links: - https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… Steps to reproduce: - https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… tuxmake --runtime podman --target-arch x86_64 --toolchain clang-17 --kconfig https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… LLVM=1 LLVM_IAS=1 debugkernel cpupower headers kernel kselftest modules -- Linaro LKFT https://lkft.linaro.org

1 year, 11 months

2
1
0 0

landlock: fs_test: fs_test.c:4524:9: error: initializer element is not a compile-time constant

by Naresh Kamboju

While building selftests landlock following warnings / errors noticed on the Linux next with clang-17. Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> Build errors: ------------ landlock/fs_test fs_test.c:4524:9: error: initializer element is not a compile-time constant 4524 | .mnt = mnt_tmp, | ^~~~~~~ 1 error generated. Links: - https://storage.tuxsuite.com/public/linaro/lkft/builds/2U69ue7AaypfY7eRU4UU… Steps to reproduce: tuxmake --runtime podman --target-arch arm64 --toolchain clang-17 --kconfig https://storage.tuxsuite.com/public/linaro/lkft/builds/2U69ue7AaypfY7eRU4UU… LLVM=1 LLVM_IAS=1 dtbs dtbs-legacy headers kernel kselftest modules -- Linaro LKFT https://lkft.linaro.org

1 year, 11 months

2
4
0 0

[PATCH v4 4.19 1/1] test_firmware: prevent race conditions by a correct implementation of locking

by Mirsad Goran Todorovac

[ Upstream commit 4acfe3dfde685a5a9eaec5555351918e2d7266a1 ] Dan Carpenter spotted a race condition in a couple of situations like these in the test_firmware driver: static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { u8 val; int ret; ret = kstrtou8(buf, 10, &val); if (ret) return ret; mutex_lock(&test_fw_mutex); *(u8 *)cfg = val; mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ return size; } static ssize_t config_num_requests_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int rc; mutex_lock(&test_fw_mutex); if (test_fw_config->reqs) { pr_err("Must call release_all_firmware prior to changing config\n"); rc = -EINVAL; mutex_unlock(&test_fw_mutex); goto out; } mutex_unlock(&test_fw_mutex); // NOTE: HERE is the race!!! Function can be preempted! // test_fw_config->reqs can change between the release of // the lock about and acquire of the lock in the // test_dev_config_update_u8() rc = test_dev_config_update_u8(buf, count, &test_fw_config->num_requests); out: return rc; } static ssize_t config_read_fw_idx_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return test_dev_config_update_u8(buf, count, &test_fw_config->read_fw_idx); } The function test_dev_config_update_u8() is called from both the locked and the unlocked context, function config_num_requests_store() and config_read_fw_idx_store() which can both be called asynchronously as they are driver's methods, while test_dev_config_update_u8() and siblings change their argument pointed to by u8 *cfg or similar pointer. To avoid deadlock on test_fw_mutex, the lock is dropped before calling test_dev_config_update_u8() and re-acquired within test_dev_config_update_u8() itself, but alas this creates a race condition. Having two locks wouldn't assure a race-proof mutual exclusion. This situation is best avoided by the introduction of a new, unlocked function __test_dev_config_update_u8() which can be called from the locked context and reducing test_dev_config_update_u8() to: static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { int ret; mutex_lock(&test_fw_mutex); ret = __test_dev_config_update_u8(buf, size, cfg); mutex_unlock(&test_fw_mutex); return ret; } doing the locking and calling the unlocked primitive, which enables both locked and unlocked versions without duplication of code. Fixes: c92316bf8e948 ("test_firmware: add batched firmware tests") Cc: Luis R. Rodriguez <mcgrof(a)kernel.org> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Russ Weight <russell.h.weight(a)intel.com> Cc: Takashi Iwai <tiwai(a)suse.de> Cc: Tianfei Zhang <tianfei.zhang(a)intel.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Colin Ian King <colin.i.king(a)gmail.com> Cc: Randy Dunlap <rdunlap(a)infradead.org> Cc: linux-kselftest(a)vger.kernel.org Cc: stable(a)vger.kernel.org # v5.4, 4.19, 4.14 Suggested-by: Dan Carpenter <error27(a)gmail.com> Link: https://lore.kernel.org/r/20230509084746.48259-1-mirsad.todorovac@alu.unizg… Signed-off-by: Mirsad Goran Todorovac <mirsad.todorovac(a)alu.unizg.hr> [ This is the patch to fix the racing condition in locking for the 5.4, ] [ 4.19 and 4.14 stable branches. Not all the fixes from the upstream ] [ commit apply, but those which do are verbatim equal to those in the ] [ upstream commit. ] --- v4: verbatim the same patch as for the 5.4 stable tree which patchwork failed to apply. lib/test_firmware.c | 37 ++++++++++++++++++++++++++++--------- 1 file changed, 28 insertions(+), 9 deletions(-) diff --git a/lib/test_firmware.c b/lib/test_firmware.c index b5e779bcfb34..be3baea88b61 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -284,16 +284,26 @@ static ssize_t config_test_show_str(char *dst, return len; } -static int test_dev_config_update_bool(const char *buf, size_t size, - bool *cfg) +static inline int __test_dev_config_update_bool(const char *buf, size_t size, + bool *cfg) { int ret; - mutex_lock(&test_fw_mutex); if (strtobool(buf, cfg) < 0) ret = -EINVAL; else ret = size; + + return ret; +} + +static int test_dev_config_update_bool(const char *buf, size_t size, + bool *cfg) +{ + int ret; + + mutex_lock(&test_fw_mutex); + ret = __test_dev_config_update_bool(buf, size, cfg); mutex_unlock(&test_fw_mutex); return ret; @@ -323,7 +333,7 @@ static ssize_t test_dev_config_show_int(char *buf, int cfg) return snprintf(buf, PAGE_SIZE, "%d\n", val); } -static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) +static inline int __test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { int ret; long new; @@ -335,14 +345,23 @@ static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) if (new > U8_MAX) return -EINVAL; - mutex_lock(&test_fw_mutex); *(u8 *)cfg = new; - mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ return size; } +static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) +{ + int ret; + + mutex_lock(&test_fw_mutex); + ret = __test_dev_config_update_u8(buf, size, cfg); + mutex_unlock(&test_fw_mutex); + + return ret; +} + static ssize_t test_dev_config_show_u8(char *buf, u8 cfg) { u8 val; @@ -375,10 +394,10 @@ static ssize_t config_num_requests_store(struct device *dev, mutex_unlock(&test_fw_mutex); goto out; } - mutex_unlock(&test_fw_mutex); - rc = test_dev_config_update_u8(buf, count, - &test_fw_config->num_requests); + rc = __test_dev_config_update_u8(buf, count, + &test_fw_config->num_requests); + mutex_unlock(&test_fw_mutex); out: return rc; -- 2.34.1

1 year, 11 months

3
2
0 0

[PATCH v32 0/6] Implement IOCTL to get and optionally clear info about PTEs

by Muhammad Usama Anjum

*Changes in v31 and v32*: - Minor updates *Changes in v30*: - Rebase on top of next-20230815 - Minor nitpicks *Changes in v29:* - Polish IOCTL and improve documentation *Changes in v28:* - Fix walk_end and add 17 test cases in selftests patch *Changes in v27:* - Handle review comments and minor improvements - Add performance improvement patch on top with test for easy review *Changes in v26:* - Code re-structurring and API changes in PAGEMAP_IOCTL *Changes in v25*: - Do proper filtering on hole as well (hole got missed earlier) *Changes in v24*: - Rebase on top of next-20230710 - Place WP markers in case of hole as well *Changes in v23*: - Set vec_buf_index in loop only when vec_buf_index is set - Return -EFAULT instead of -EINVAL if vec is NULL - Correctly return the walk ending address to the page granularity *Changes in v22*: - Interface change: - Replace [start start + len) with [start, end) - Return the ending address of the address walk in start *Changes in v21*: - Abort walk instead of returning error if WP is to be performed on partial hugetlb *Changes in v20* - Correct PAGE_IS_FILE and add PAGE_IS_PFNZERO *Changes in v19* - Minor changes and interface updates *Changes in v18* - Rebase on top of next-20230613 - Minor updates *Changes in v17* - Rebase on top of next-20230606 - Minor improvements in PAGEMAP_SCAN IOCTL patch *Changes in v16* - Fix a corner case - Add exclusive PM_SCAN_OP_WP back *Changes in v15* - Build fix (Add missed build fix in RESEND) *Changes in v14* - Fix build error caused by #ifdef added at last minute in some configs *Changes in v13* - Rebase on top of next-20230414 - Give-up on using uffd_wp_range() and write new helpers, flush tlb only once *Changes in v12* - Update and other memory types to UFFD_FEATURE_WP_ASYNC - Rebaase on top of next-20230406 - Review updates *Changes in v11* - Rebase on top of next-20230307 - Base patches on UFFD_FEATURE_WP_UNPOPULATED - 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 *Motivation* The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch() retrieves the addresses of the pages that are written to in a region of virtual memory. This syscall is used in Windows applications and games etc. This syscall is being emulated in pretty slow manner in userspace. Our purpose is to enhance the kernel such that we translate it efficiently in a better way. Currently some out of tree hack patches are being used to efficiently emulate it in some kernels. We intend to replace those with these patches. So the whole gaming on Linux can effectively get benefit from this. It means there would be tons of users of this code. CRIU use case [2] was mentioned by Andrei and Danylo: > Use cases for migrating sparse VMAs are binaries sanitized with ASAN, > MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of > shadow memory [4]. Being able to migrate such binaries allows to highly > reduce the amount of work needed to identify and fix post-migration > crashes, which happen constantly. Andrei's defines the following uses of this code: * it is more granular and allows us to track changed pages more effectively. The current interface can clear dirty bits for the entire process only. In addition, reading info about pages is a separate operation. It means we must freeze the process to read information about all its pages, reset dirty bits, only then we can start dumping pages. The information about pages becomes more and more outdated, while we are processing pages. The new interface solves both these downsides. First, it allows us to read pte bits and clear the soft-dirty bit atomically. It means that CRIU will not need to freeze processes to pre-dump their memory. Second, it clears soft-dirty bits for a specified region of memory. It means CRIU will have actual info about pages to the moment of dumping them. * The new interface has to be much faster because basic page filtering is happening in the kernel. With the old interface, we have to read pagemap for each page. *Implementation Evolution (Short Summary)* From the definition of GetWriteWatch(), we feel like kernel's soft-dirty feature can be used under the hood with some additions like: * reset soft-dirty flag for only a specific region of memory instead of clearing the flag for the entire process * get and clear soft-dirty flag for a specific region atomically So we decided to use ioctl on pagemap file to read or/and reset soft-dirty flag. But using soft-dirty flag, sometimes we get extra pages which weren't even written. They had become soft-dirty because of VMA merging and VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were able to by-pass this short coming by ignoring VM_SOFTDIRTY until David reported that mprotect etc messes up the soft-dirty flag while ignoring VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We discussed if we can revert these patches. But we could not reach to any conclusion. So at this point, I made couple of tries to solve this whole VM_SOFTDIRTY issue by correcting the soft-dirty implementation: * [7] Correct the bug fixed wrongly back in 2014. It had potential to cause regression. We left it behind. * [8] Keep a list of soft-dirty part of a VMA across splits and merges. I got the reply don't increase the size of the VMA by 8 bytes. At this point, we left soft-dirty considering it is too much delicate and userfaultfd [9] seemed like the only way forward. From there onward, we have been basing soft-dirty emulation on userfaultfd wp feature where kernel resolves the faults itself when WP_ASYNC feature is used. It was straight forward to add WP_ASYNC feature in userfautlfd. Now we get only those pages dirty or written-to which are really written in reality. (PS There is another WP_UNPOPULATED userfautfd feature is required which is needed to avoid pre-faulting memory before write-protecting [9].) All the different masks were added on the request of CRIU devs to create interface more generic and better. [1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-… [2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com [3] https://github.com/google/sanitizers [4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit [5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com [6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/ [7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.… [8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.… [9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com [10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com * Original Cover letter from v8* 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. 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-dirty 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 (5): fs/proc/task_mmu: Implement IOCTL to get and optionally clear info about PTEs fs/proc/task_mmu: Add fast paths to get/clear PAGE_IS_WRITTEN flag 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 Peter Xu (1): userfaultfd: UFFD_FEATURE_WP_ASYNC Documentation/admin-guide/mm/pagemap.rst | 89 + Documentation/admin-guide/mm/userfaultfd.rst | 35 + fs/proc/task_mmu.c | 705 ++++++++ fs/userfaultfd.c | 26 +- include/linux/hugetlb.h | 1 + include/linux/userfaultfd_k.h | 28 +- include/uapi/linux/fs.h | 59 + include/uapi/linux/userfaultfd.h | 9 +- mm/hugetlb.c | 34 +- mm/memory.c | 28 +- tools/include/uapi/linux/fs.h | 59 + tools/testing/selftests/mm/.gitignore | 2 + tools/testing/selftests/mm/Makefile | 3 +- tools/testing/selftests/mm/config | 1 + tools/testing/selftests/mm/pagemap_ioctl.c | 1660 ++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 4 + 16 files changed, 2719 insertions(+), 24 deletions(-) create mode 100644 tools/testing/selftests/mm/pagemap_ioctl.c -- 2.40.1

1 year, 11 months

4
11
0 0

clang-17: selftests: exec/load_address_4096 clang: error: argument unused during compilation: '-pie' [-Werror,-Wunused-command-line-argument]

by Naresh Kamboju

Recently we have updated the toolchain clang-17 version. While building selftests exec following warnings / errors noticed on the Linux next with clang-17. But pass with gcc-13. Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> exec/load_address_4096 clang: error: argument unused during compilation: '-pie' [-Werror,-Wunused-command-line-argument] Links: - https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… - https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20230821/te… Steps to reproduce: - https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… tuxmake --runtime podman --target-arch x86_64 --toolchain clang-17 --kconfig https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… LLVM=1 LLVM_IAS=1 debugkernel cpupower headers kernel kselftest modules -- Linaro LKFT https://lkft.linaro.org

1 year, 11 months

1
0
0 0

clang: error: cannot specify -o when generating multiple output files

by Naresh Kamboju

Recently we have updated the toolchain clang-17 version. While building selftests filesystems/binderfs, openat2, resctrl and x86 following warnings / errors noticed on the Linux next with clang-17. But pass with gcc-13. Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> Build logs: ======== binderfs_test clang: error: cannot specify -o when generating multiple output files ... openat2/openat2_test clang: error: cannot specify -o when generating multiple output files ... resctrl/resctrl_tests clang: error: cannot specify -o when generating multiple output files ... make[4]: Entering directory 'tools/testing/selftests/x86' clang --target=x86_64-linux-gnu -fintegrated-as -Werror=unknown-warning-option -Werror=ignored-optimization-argument -Werror=option-ignored -Werror=unused-command-line-argument --target=x86_64-linux-gnu -fintegrated-as -m64 -o /home/tuxbuild/.cache/tuxmake/builds/1/build/kselftest/x86/single_step_syscall_64 -O2 -g -std=gnu99 -pthread -Wall -isystem /home/tuxbuild/.cache/tuxmake/builds/1/build/usr/include -no-pie -DCAN_BUILD_64 single_step_syscall.c helpers.h -lrt -ldl clang: error: cannot specify -o when generating multiple output files make[4]: *** [Makefile:78: /home/tuxbuild/.cache/tuxmake/builds/1/build/kselftest/x86/single_step_syscall_64] Error 1 Links: - https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… - https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20230821/te… - https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20230821/te… - Steps to reproduce: - https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… tuxmake --runtime podman --target-arch x86_64 --toolchain clang-17 --kconfig https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… LLVM=1 LLVM_IAS=1 debugkernel cpupower headers kernel kselftest modules -- Linaro LKFT https://lkft.linaro.org

1 year, 11 months

1
0
0 0

clang-17: selftests: vdso_standalone_test_x86.c:(.text+0x1e6): undefined reference to `memcpy'

by Naresh Kamboju

Recently we have updated toolchain clang-17 version. While building selftests vdso following warnings / errors noticed on the Linux next with clang-17. but pass with gcc-13. Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> make[4]: Entering directory 'tools/testing/selftests/vDSO' clang --target=x86_64-linux-gnu -fintegrated-as -Werror=unknown-warning-option -Werror=ignored-optimization-argument -Werror=option-ignored -Werror=unused-command-line-argument --target=x86_64-linux-gnu -fintegrated-as -std=gnu99 -nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector \ vdso_standalone_test_x86.c parse_vdso.c \ -o /vDSO/vdso_standalone_test_x86 vdso_standalone_test_x86.c:73:16: warning: unknown attribute 'externally_visible' ignored [-Wunknown-attributes] 73 | __attribute__((externally_visible)) void c_main(void **stack) | ^~~~~~~~~~~~~~~~~~ 1 warning generated. parse_vdso.c:65:9: warning: using the result of an assignment as a condition without parentheses [-Wparentheses] 65 | if (g = h & 0xf0000000) | ~~^~~~~~~~~~~~~~~~ parse_vdso.c:65:9: note: place parentheses around the assignment to silence this warning 65 | if (g = h & 0xf0000000) | ^ | ( ) parse_vdso.c:65:9: note: use '==' to turn this assignment into an equality comparison 65 | if (g = h & 0xf0000000) | ^ | == parse_vdso.c:206:22: warning: passing 'const char *' to parameter of type 'const unsigned char *' converts between pointers to integer types where one is of the unique plain 'char' type and the other is not [-Wpointer-sign] 206 | ver_hash = elf_hash(version); | ^~~~~~~ parse_vdso.c:59:52: note: passing argument to parameter 'name' here 59 | static unsigned long elf_hash(const unsigned char *name) | ^ parse_vdso.c:207:46: warning: passing 'const char *' to parameter of type 'const unsigned char *' converts between pointers to integer types where one is of the unique plain 'char' type and the other is not [-Wpointer-sign] 207 | ELF(Word) chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket]; | ^~~~ parse_vdso.c:59:52: note: passing argument to parameter 'name' here 59 | static unsigned long elf_hash(const unsigned char *name) | ^ 3 warnings generated. /usr/bin/x86_64-linux-gnu-ld: /tmp/vdso_standalone_test_x86-31b09f.o: in function `c_main': vdso_standalone_test_x86.c:(.text+0x1e6): undefined reference to `memcpy' clang: error: linker command failed with exit code 1 (use -v to see invocation) make[4]: Leaving directory 'tools/testing/selftests/vDSO' Links: - https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… - https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20230821/te… Steps to reproduce: - https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… tuxmake --runtime podman --target-arch x86_64 --toolchain clang-17 --kconfig https://storage.tuxsuite.com/public/linaro/lkft/builds/2UHhSg0TPLhjp9Uq9EFc… LLVM=1 LLVM_IAS=1 debugkernel cpupower headers kernel kselftest modules -- Linaro LKFT https://lkft.linaro.org

1 year, 11 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror