diff options
Diffstat (limited to 'tools')
| -rw-r--r-- | tools/objtool/Documentation/stack-validation.txt | 6 | ||||
| -rw-r--r-- | tools/objtool/arch/x86/decode.c | 6 | ||||
| -rw-r--r-- | tools/objtool/check.c | 43 | ||||
| -rw-r--r-- | tools/objtool/elf.c | 33 | ||||
| -rw-r--r-- | tools/testing/nvdimm/test/nfit.c | 3 | ||||
| -rw-r--r-- | tools/testing/selftests/seccomp/Makefile | 18 | ||||
| -rw-r--r-- | tools/testing/selftests/seccomp/seccomp_benchmark.c | 99 | ||||
| -rw-r--r-- | tools/testing/selftests/seccomp/seccomp_bpf.c | 610 |
8 files changed, 681 insertions, 137 deletions
diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt index 6a1af43862df..3995735a878f 100644 --- a/tools/objtool/Documentation/stack-validation.txt +++ b/tools/objtool/Documentation/stack-validation.txt @@ -194,10 +194,10 @@ they mean, and suggestions for how to fix them. If it's a GCC-compiled .c file, the error may be because the function uses an inline asm() statement which has a "call" instruction. An asm() statement with a call instruction must declare the use of the - stack pointer in its output operand. For example, on x86_64: + stack pointer in its output operand. On x86_64, this means adding + the ASM_CALL_CONSTRAINT as an output constraint: - register void *__sp asm("rsp"); - asm volatile("call func" : "+r" (__sp)); + asm volatile("call func" : ASM_CALL_CONSTRAINT); Otherwise the stack frame may not get created before the call. diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 0e8c8ec4fd4e..0f22768c0d4d 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -208,14 +208,14 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, break; case 0x89: - if (rex == 0x48 && modrm == 0xe5) { + if (rex_w && !rex_r && modrm_mod == 3 && modrm_reg == 4) { - /* mov %rsp, %rbp */ + /* mov %rsp, reg */ *type = INSN_STACK; op->src.type = OP_SRC_REG; op->src.reg = CFI_SP; op->dest.type = OP_DEST_REG; - op->dest.reg = CFI_BP; + op->dest.reg = op_to_cfi_reg[modrm_rm][rex_b]; break; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f744617c9946..a0c518ecf085 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1203,24 +1203,39 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state) switch (op->src.type) { case OP_SRC_REG: - if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP) { + if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP && + cfa->base == CFI_SP && + regs[CFI_BP].base == CFI_CFA && + regs[CFI_BP].offset == -cfa->offset) { + + /* mov %rsp, %rbp */ + cfa->base = op->dest.reg; + state->bp_scratch = false; + } - if (cfa->base == CFI_SP && - regs[CFI_BP].base == CFI_CFA && - regs[CFI_BP].offset == -cfa->offset) { + else if (op->src.reg == CFI_SP && + op->dest.reg == CFI_BP && state->drap) { - /* mov %rsp, %rbp */ - cfa->base = op->dest.reg; - state->bp_scratch = false; - } + /* drap: mov %rsp, %rbp */ + regs[CFI_BP].base = CFI_BP; + regs[CFI_BP].offset = -state->stack_size; + state->bp_scratch = false; + } - else if (state->drap) { + else if (op->src.reg == CFI_SP && cfa->base == CFI_SP) { - /* drap: mov %rsp, %rbp */ - regs[CFI_BP].base = CFI_BP; - regs[CFI_BP].offset = -state->stack_size; - state->bp_scratch = false; - } + /* + * mov %rsp, %reg + * + * This is needed for the rare case where GCC + * does: + * + * mov %rsp, %rax + * ... + * mov %rax, %rsp + */ + state->vals[op->dest.reg].base = CFI_CFA; + state->vals[op->dest.reg].offset = -state->stack_size; } else if (op->dest.reg == cfa->base) { diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 6e9f980a7d26..24460155c82c 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -175,19 +175,20 @@ static int read_sections(struct elf *elf) return -1; } - sec->data = elf_getdata(s, NULL); - if (!sec->data) { - WARN_ELF("elf_getdata"); - return -1; - } - - if (sec->data->d_off != 0 || - sec->data->d_size != sec->sh.sh_size) { - WARN("unexpected data attributes for %s", sec->name); - return -1; + if (sec->sh.sh_size != 0) { + sec->data = elf_getdata(s, NULL); + if (!sec->data) { + WARN_ELF("elf_getdata"); + return -1; + } + if (sec->data->d_off != 0 || + sec->data->d_size != sec->sh.sh_size) { + WARN("unexpected data attributes for %s", + sec->name); + return -1; + } } - - sec->len = sec->data->d_size; + sec->len = sec->sh.sh_size; } /* sanity check, one more call to elf_nextscn() should return NULL */ @@ -508,6 +509,7 @@ struct section *elf_create_rela_section(struct elf *elf, struct section *base) strcat(relaname, base->name); sec = elf_create_section(elf, relaname, sizeof(GElf_Rela), 0); + free(relaname); if (!sec) return NULL; @@ -561,6 +563,7 @@ int elf_write(struct elf *elf) struct section *sec; Elf_Scn *s; + /* Update section headers for changed sections: */ list_for_each_entry(sec, &elf->sections, list) { if (sec->changed) { s = elf_getscn(elf->elf, sec->idx); @@ -568,13 +571,17 @@ int elf_write(struct elf *elf) WARN_ELF("elf_getscn"); return -1; } - if (!gelf_update_shdr (s, &sec->sh)) { + if (!gelf_update_shdr(s, &sec->sh)) { WARN_ELF("gelf_update_shdr"); return -1; } } } + /* Make sure the new section header entries get updated properly. */ + elf_flagelf(elf->elf, ELF_C_SET, ELF_F_DIRTY); + + /* Write all changes to the file. */ if (elf_update(elf->elf, ELF_C_WRITE) < 0) { WARN_ELF("elf_update"); return -1; diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index d20791c3f499..bef419d4266d 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1527,9 +1527,6 @@ static void nfit_test1_setup(struct nfit_test *t) set_bit(ND_CMD_ARS_START, &acpi_desc->bus_cmd_force_en); set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en); set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en); - set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_cmd_force_en); - set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en); - set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en); } static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa, diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile index aeb0c805f3ca..553d870b4ca9 100644 --- a/tools/testing/selftests/seccomp/Makefile +++ b/tools/testing/selftests/seccomp/Makefile @@ -1,8 +1,16 @@ -TEST_GEN_PROGS := seccomp_bpf -CFLAGS += -Wl,-no-as-needed -Wall -LDFLAGS += -lpthread +all: include ../lib.mk -$(TEST_GEN_PROGS): seccomp_bpf.c ../kselftest_harness.h - $(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ +.PHONY: all clean + +BINARIES := seccomp_bpf seccomp_benchmark +CFLAGS += -Wl,-no-as-needed -Wall + +seccomp_bpf: seccomp_bpf.c ../kselftest_harness.h + $(CC) $(CFLAGS) $(LDFLAGS) -lpthread $< -o $@ + +TEST_PROGS += $(BINARIES) +EXTRA_CLEAN := $(BINARIES) + +all: $(BINARIES) diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c new file mode 100644 index 000000000000..5838c8697ec3 --- /dev/null +++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c @@ -0,0 +1,99 @@ +/* + * Strictly speaking, this is not a test. But it can report during test + * runs so relative performace can be measured. + */ +#define _GNU_SOURCE +#include <assert.h> +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <unistd.h> +#include <linux/filter.h> +#include <linux/seccomp.h> +#include <sys/prctl.h> +#include <sys/syscall.h> +#include <sys/types.h> + +#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) + +unsigned long long timing(clockid_t clk_id, unsigned long long samples) +{ + pid_t pid, ret; + unsigned long long i; + struct timespec start, finish; + + pid = getpid(); + assert(clock_gettime(clk_id, &start) == 0); + for (i = 0; i < samples; i++) { + ret = syscall(__NR_getpid); + assert(pid == ret); + } + assert(clock_gettime(clk_id, &finish) == 0); + + i = finish.tv_sec - start.tv_sec; + i *= 1000000000; + i += finish.tv_nsec - start.tv_nsec; + + printf("%lu.%09lu - %lu.%09lu = %llu\n", + finish.tv_sec, finish.tv_nsec, + start.tv_sec, start.tv_nsec, + i); + + return i; +} + +unsigned long long calibrate(void) +{ + unsigned long long i; + + printf("Calibrating reasonable sample size...\n"); + + for (i = 5; ; i++) { + unsigned long long samples = 1 << i; + + /* Find something that takes more than 5 seconds to run. */ + if (timing(CLOCK_REALTIME, samples) / 1000000000ULL > 5) + return samples; + } +} + +int main(int argc, char *argv[]) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + unsigned long long samples; + unsigned long long native, filtered; + + if (argc > 1) + samples = strtoull(argv[1], NULL, 0); + else + samples = calibrate(); + + printf("Benchmarking %llu samples...\n", samples); + + native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; + printf("getpid native: %llu ns\n", native); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + assert(ret == 0); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); + assert(ret == 0); + + filtered = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; + printf("getpid RET_ALLOW: %llu ns\n", filtered); + + printf("Estimated seccomp overhead per syscall: %llu ns\n", + filtered - native); + + if (filtered == native) + printf("Trying running again with more samples.\n"); + + return 0; +} diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 4d6f92a9df6b..67c3e2764303 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -68,17 +68,7 @@ #define SECCOMP_MODE_FILTER 2 #endif -#ifndef SECCOMP_RET_KILL -#define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */ -#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ -#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ -#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ -#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ - -/* Masks for the return value sections. */ -#define SECCOMP_RET_ACTION 0x7fff0000U -#define SECCOMP_RET_DATA 0x0000ffffU - +#ifndef SECCOMP_RET_ALLOW struct seccomp_data { int nr; __u32 arch; @@ -87,6 +77,70 @@ struct seccomp_data { }; #endif +#ifndef SECCOMP_RET_KILL_PROCESS +#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */ +#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */ +#endif +#ifndef SECCOMP_RET_KILL +#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD +#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ +#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ +#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ +#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ +#endif +#ifndef SECCOMP_RET_LOG +#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ +#endif + +#ifndef __NR_seccomp +# if defined(__i386__) +# define __NR_seccomp 354 +# elif defined(__x86_64__) +# define __NR_seccomp 317 +# elif defined(__arm__) +# define __NR_seccomp 383 +# elif defined(__aarch64__) +# define __NR_seccomp 277 +# elif defined(__hppa__) +# define __NR_seccomp 338 +# elif defined(__powerpc__) +# define __NR_seccomp 358 +# elif defined(__s390__) +# define __NR_seccomp 348 +# else +# warning "seccomp syscall number unknown for this architecture" +# define __NR_seccomp 0xffff +# endif +#endif + +#ifndef SECCOMP_SET_MODE_STRICT +#define SECCOMP_SET_MODE_STRICT 0 +#endif + +#ifndef SECCOMP_SET_MODE_FILTER +#define SECCOMP_SET_MODE_FILTER 1 +#endif + +#ifndef SECCOMP_GET_ACTION_AVAIL +#define SECCOMP_GET_ACTION_AVAIL 2 +#endif + +#ifndef SECCOMP_FILTER_FLAG_TSYNC +#define SECCOMP_FILTER_FLAG_TSYNC 1 +#endif + +#ifndef SECCOMP_FILTER_FLAG_LOG +#define SECCOMP_FILTER_FLAG_LOG 2 +#endif + +#ifndef seccomp +int seccomp(unsigned int op, unsigned int flags, void *args) +{ + errno = 0; + return syscall(__NR_seccomp, op, flags, args); +} +#endif + #if __BYTE_ORDER == __LITTLE_ENDIAN #define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n])) #elif __BYTE_ORDER == __BIG_ENDIAN @@ -136,7 +190,7 @@ TEST(no_new_privs_support) } } -/* Tests kernel support by checking for a copy_from_user() fault on * NULL. */ +/* Tests kernel support by checking for a copy_from_user() fault on NULL. */ TEST(mode_filter_support) { long ret; @@ -342,6 +396,28 @@ TEST(empty_prog) EXPECT_EQ(EINVAL, errno); } +TEST(log_all) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + pid_t parent = getppid(); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); + ASSERT_EQ(0, ret); + + /* getppid() should succeed and be logged (no check for logging) */ + EXPECT_EQ(parent, syscall(__NR_getppid)); +} + TEST_SIGNAL(unknown_ret_is_kill_inside, SIGSYS) { struct sock_filter filter[] = { @@ -520,6 +596,117 @@ TEST_SIGNAL(KILL_one_arg_six, SIGSYS) close(fd); } +/* This is a thread task to die via seccomp filter violation. */ +void *kill_thread(void *data) +{ + bool die = (bool)data; + + if (die) { + prctl(PR_GET_SECCOMP, 0, 0, 0, 0); + return (void *)SIBLING_EXIT_FAILURE; + } + + return (void *)SIBLING_EXIT_UNKILLED; +} + +/* Prepare a thread that will kill itself or both of us. */ +void kill_thread_or_group(struct __test_metadata *_metadata, bool kill_process) +{ + pthread_t thread; + void *status; + /* Kill only when calling __NR_prctl. */ + struct sock_filter filter_thread[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_THREAD), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog_thread = { + .len = (unsigned short)ARRAY_SIZE(filter_thread), + .filter = filter_thread, + }; + struct sock_filter filter_process[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_PROCESS), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog_process = { + .len = (unsigned short)ARRAY_SIZE(filter_process), + .filter = filter_process, + }; + + ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, + kill_process ? &prog_process : &prog_thread)); + + /* + * Add the KILL_THREAD rule again to make sure that the KILL_PROCESS + * flag cannot be downgraded by a new filter. + */ + ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog_thread)); + + /* Start a thread that will exit immediately. */ + ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)false)); + ASSERT_EQ(0, pthread_join(thread, &status)); + ASSERT_EQ(SIBLING_EXIT_UNKILLED, (unsigned long)status); + + /* Start a thread that will die immediately. */ + ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)true)); + ASSERT_EQ(0, pthread_join(thread, &status)); + ASSERT_NE(SIBLING_EXIT_FAILURE, (unsigned long)status); + + /* + * If we get here, only the spawned thread died. Let the parent know + * the whole process didn't die (i.e. this thread, the spawner, + * stayed running). + */ + exit(42); +} + +TEST(KILL_thread) +{ + int status; + pid_t child_pid; + + child_pid = fork(); + ASSERT_LE(0, child_pid); + if (child_pid == 0) { + kill_thread_or_group(_metadata, false); + _exit(38); + } + + ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0)); + + /* If only the thread was killed, we'll see exit 42. */ + ASSERT_TRUE(WIFEXITED(status)); + ASSERT_EQ(42, WEXITSTATUS(status)); +} + +TEST(KILL_process) +{ + int status; + pid_t child_pid; + + child_pid = fork(); + ASSERT_LE(0, child_pid); + if (child_pid == 0) { + kill_thread_or_group(_metadata, true); + _exit(38); + } + + ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0)); + + /* If the entire process was killed, we'll see SIGSYS. */ + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_EQ(SIGSYS, WTERMSIG(status)); +} + /* TODO(wad) add 64-bit versus 32-bit arg tests. */ TEST(arg_out_of_range) { @@ -541,26 +728,30 @@ TEST(arg_out_of_range) EXPECT_EQ(EINVAL, errno); } +#define ERRNO_FILTER(name, errno) \ + struct sock_filter _read_filter_##name[] = { \ + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, \ + offsetof(struct seccomp_data, nr)), \ + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1), \ + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | errno), \ + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), \ + }; \ + struct sock_fprog prog_##name = { \ + .len = (unsigned short)ARRAY_SIZE(_read_filter_##name), \ + .filter = _read_filter_##name, \ + } + +/* Make sure basic errno values are correctly passed through a filter. */ TEST(ERRNO_valid) { - struct sock_filter filter[] = { - BPF_STMT(BPF_LD|BPF_W|BPF_ABS, - offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | E2BIG), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), - }; - struct sock_fprog prog = { - .len = (unsigned short)ARRAY_SIZE(filter), - .filter = filter, - }; + ERRNO_FILTER(valid, E2BIG); long ret; pid_t parent = getppid(); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); ASSERT_EQ(0, ret); - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_valid); ASSERT_EQ(0, ret); EXPECT_EQ(parent, syscall(__NR_getppid)); @@ -568,26 +759,17 @@ TEST(ERRNO_valid) EXPECT_EQ(E2BIG, errno); } +/* Make sure an errno of zero is correctly handled by the arch code. */ TEST(ERRNO_zero) { - struct sock_filter filter[] = { - BPF_STMT(BPF_LD|BPF_W|BPF_ABS, - offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | 0), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), - }; - struct sock_fprog prog = { - .len = (unsigned short)ARRAY_SIZE(filter), - .filter = filter, - }; + ERRNO_FILTER(zero, 0); long ret; pid_t parent = getppid(); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); ASSERT_EQ(0, ret); - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_zero); ASSERT_EQ(0, ret); EXPECT_EQ(parent, syscall(__NR_getppid)); @@ -595,26 +777,21 @@ TEST(ERRNO_zero) EXPECT_EQ(0, read(0, NULL, 0)); } +/* + * The SECCOMP_RET_DATA mask is 16 bits wide, but errno is smaller. + * This tests that the errno value gets capped correctly, fixed by + * 580c57f10768 ("seccomp: cap SECCOMP_RET_ERRNO data to MAX_ERRNO"). + */ TEST(ERRNO_capped) { - struct sock_filter filter[] = { - BPF_STMT(BPF_LD|BPF_W|BPF_ABS, - offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | 4096), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), - }; - struct sock_fprog prog = { - .len = (unsigned short)ARRAY_SIZE(filter), - .filter = filter, - }; + ERRNO_FILTER(capped, 4096); long ret; pid_t parent = getppid(); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); ASSERT_EQ(0, ret); - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_capped); ASSERT_EQ(0, ret); EXPECT_EQ(parent, syscall(__NR_getppid)); @@ -622,6 +799,37 @@ TEST(ERRNO_capped) EXPECT_EQ(4095, errno); } +/* + * Filters are processed in reverse order: last applied is executed first. + * Since only the SECCOMP_RET_ACTION mask is tested for return values, the + * SECCOMP_RET_DATA mask results will follow the most recently applied + * matching filter return (and not the lowest or highest value). + */ +TEST(ERRNO_order) +{ + ERRNO_FILTER(first, 11); + ERRNO_FILTER(second, 13); + ERRNO_FILTER(third, 12); + long ret; + pid_t parent = getppid(); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_first); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_second); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_third); + ASSERT_EQ(0, ret); + + EXPECT_EQ(parent, syscall(__NR_getppid)); + EXPECT_EQ(-1, read(0, NULL, 0)); + EXPECT_EQ(12, errno); +} + FIXTURE_DATA(TRAP) { struct sock_fprog prog; }; @@ -735,6 +943,7 @@ TEST_F(TRAP, handler) FIXTURE_DATA(precedence) { struct sock_fprog allow; + struct sock_fprog log; struct sock_fprog trace; struct sock_fprog error; struct sock_fprog trap; @@ -746,6 +955,13 @@ FIXTURE_SETUP(precedence) struct sock_filter allow_insns[] = { BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; + struct sock_filter log_insns[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG), + }; struct sock_filter trace_insns[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, offsetof(struct seccomp_data, nr)), @@ -782,6 +998,7 @@ FIXTURE_SETUP(precedence) memcpy(self->_x.filter, &_x##_insns, sizeof(_x##_insns)); \ self->_x.len = (unsigned short)ARRAY_SIZE(_x##_insns) FILTER_ALLOC(allow); + FILTER_ALLOC(log); FILTER_ALLOC(trace); FILTER_ALLOC(error); FILTER_ALLOC(trap); @@ -792,6 +1009,7 @@ FIXTURE_TEARDOWN(precedence) { #define FILTER_FREE(_x) if (self->_x.filter) free(self->_x.filter) FILTER_FREE(allow); + FILTER_FREE(log); FILTER_FREE(trace); FILTER_FREE(error); FILTER_FREE(trap); @@ -809,6 +1027,8 @@ TEST_F(precedence, allow_ok) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -833,6 +1053,8 @@ TEST_F_SIGNAL(precedence, kill_is_highest, SIGSYS) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -864,6 +1086,8 @@ TEST_F_SIGNAL(precedence, kill_is_highest_in_any_order, SIGSYS) ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap); @@ -885,6 +1109,8 @@ TEST_F_SIGNAL(precedence, trap_is_second, SIGSYS) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -910,6 +1136,8 @@ TEST_F_SIGNAL(precedence, trap_is_second_in_any_order, SIGSYS) ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -931,6 +1159,8 @@ TEST_F(precedence, errno_is_third) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -949,6 +1179,8 @@ TEST_F(precedence, errno_is_third_in_any_order) ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); @@ -971,6 +1203,8 @@ TEST_F(precedence, trace_is_fourth) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); /* Should work just fine. */ @@ -992,12 +1226,54 @@ TEST_F(precedence, trace_is_fourth_in_any_order) ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); /* Should work just fine. */ EXPECT_EQ(parent, syscall(__NR_getppid)); /* No ptracer */ EXPECT_EQ(-1, syscall(__NR_getpid)); } +TEST_F(precedence, log_is_fifth) +{ + pid_t mypid, parent; + long ret; + + mypid = getpid(); + parent = getppid(); + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); + ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); + /* Should work just fine. */ + EXPECT_EQ(parent, syscall(__NR_getppid)); + /* Should also work just fine */ + EXPECT_EQ(mypid, syscall(__NR_getpid)); +} + +TEST_F(precedence, log_is_fifth_in_any_order) +{ + pid_t mypid, parent; + long ret; + + mypid = getpid(); + parent = getppid(); + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); + ASSERT_EQ(0, ret); + /* Should work just fine. */ + EXPECT_EQ(parent, syscall(__NR_getppid)); + /* Should also work just fine */ + EXPECT_EQ(mypid, syscall(__NR_getpid)); +} + #ifndef PTRACE_O_TRACESECCOMP #define PTRACE_O_TRACESECCOMP 0x00000080 #endif @@ -1262,6 +1538,13 @@ TEST_F(TRACE_poke, getpid_runs_normally) # error "Do not know how to find your architecture's registers and syscalls" #endif +/* When the syscall return can't be changed, stub out the tests for it. */ +#ifdef SYSCALL_NUM_RET_SHARE_REG +# define EXPECT_SYSCALL_RETURN(val, action) EXPECT_EQ(-1, action) +#else +# define EXPECT_SYSCALL_RETURN(val, action) EXPECT_EQ(val, action) +#endif + /* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for * architectures without HAVE_ARCH_TRACEHOOK (e.g. User-mode Linux). */ @@ -1357,7 +1640,7 @@ void change_syscall(struct __test_metadata *_metadata, #ifdef SYSCALL_NUM_RET_SHARE_REG TH_LOG("Can't modify syscall return on this architecture"); #else - regs.SYSCALL_RET = 1; + regs.SYSCALL_RET = EPERM; #endif #ifdef HAVE_GETREGS @@ -1426,6 +1709,8 @@ void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee, if (nr == __NR_getpid) change_syscall(_metadata, tracee, __NR_getppid); + if (nr == __NR_open) + change_syscall(_metadata, tracee, -1); } FIXTURE_DATA(TRACE_syscall) { @@ -1480,6 +1765,28 @@ FIXTURE_TEARDOWN(TRACE_syscall) free(self->prog.filter); } +TEST_F(TRACE_syscall, ptrace_syscall_redirected) +{ + /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ + teardown_trace_fixture(_metadata, self->tracer); + self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, + true); + + /* Tracer will redirect getpid to getppid. */ + EXPECT_NE(self->mypid, syscall(__NR_getpid)); +} + +TEST_F(TRACE_syscall, ptrace_syscall_dropped) +{ + /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ + teardown_trace_fixture(_metadata, self->tracer); + self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, + true); + + /* Tracer should skip the open syscall, resulting in EPERM. */ + EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_open)); +} + TEST_F(TRACE_syscall, syscall_allowed) { long ret; @@ -1520,13 +1827,8 @@ TEST_F(TRACE_syscall, syscall_dropped) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); ASSERT_EQ(0, ret); -#ifdef SYSCALL_NUM_RET_SHARE_REG - /* gettid has been skipped */ - EXPECT_EQ(-1, syscall(__NR_gettid)); -#else /* gettid has been skipped and an altered return value stored. */ - EXPECT_EQ(1, syscall(__NR_gettid)); -#endif + EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_gettid)); EXPECT_NE(self->mytid, syscall(__NR_gettid)); } @@ -1557,6 +1859,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE) ASSERT_EQ(0, ret); /* Tracer will redirect getpid to getppid, and we should see EPERM. */ + errno = 0; EXPECT_EQ(-1, syscall(__NR_getpid)); EXPECT_EQ(EPERM, errno); } @@ -1654,47 +1957,6 @@ TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) EXPECT_NE(self->mypid, syscall(__NR_getpid)); } -#ifndef __NR_seccomp -# if defined(__i386__) -# define __NR_seccomp 354 -# elif defined(__x86_64__) -# define __NR_seccomp 317 -# elif defined(__arm__) -# define __NR_seccomp 383 -# elif defined(__aarch64__) -# define __NR_seccomp 277 -# elif defined(__hppa__) -# define __NR_seccomp 338 -# elif defined(__powerpc__) -# define __NR_seccomp 358 -# elif defined(__s390__) -# define __NR_seccomp 348 -# else -# warning "seccomp syscall number unknown for this architecture" -# define __NR_seccomp 0xffff -# endif -#endif - -#ifndef SECCOMP_SET_MODE_STRICT -#define SECCOMP_SET_MODE_STRICT 0 -#endif - -#ifndef SECCOMP_SET_MODE_FILTER -#define SECCOMP_SET_MODE_FILTER 1 -#endif - -#ifndef SECCOMP_FILTER_FLAG_TSYNC -#define SECCOMP_FILTER_FLAG_TSYNC 1 -#endif - -#ifndef seccomp -int seccomp(unsigned int op, unsigned int flags, void *args) -{ - errno = 0; - return syscall(__NR_seccomp, op, flags, args); -} -#endif - TEST(seccomp_syscall) { struct sock_filter filter[] = { @@ -1783,6 +2045,67 @@ TEST(seccomp_syscall_mode_lock) } } +/* + * Test detection of known and unknown filter flags. Userspace needs to be able + * to check if a filter flag is supported by the current kernel and a good way + * of doing that is by attempting to enter filter mode, with the flag bit in + * question set, and a NULL pointer for the _args_ parameter. EFAULT indicates + * that the flag is valid and EINVAL indicates that the flag is invalid. + */ +TEST(detect_seccomp_filter_flags) +{ + unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC, + SECCOMP_FILTER_FLAG_LOG }; + unsigned int flag, all_flags; + int i; + long ret; + + /* Test detection of known-good filter flags */ + for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) { + flag = flags[i]; + ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } + EXPECT_EQ(-1, ret); + EXPECT_EQ(EFAULT, errno) { + TH_LOG("Failed to detect that a known-good filter flag (0x%X) is supported!", + flag); + } + + all_flags |= flag; + } + + /* Test detection of all known-good filter flags */ + ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EFAULT, errno) { + TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!", + all_flags); + } + + /* Test detection of an unknown filter flag */ + flag = -1; + ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno) { + TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported!", + flag); + } + + /* + * Test detection of an unknown filter flag that may simply need to be + * added to this test + */ + flag = flags[ARRAY_SIZE(flags) - 1] << 1; + ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno) { + TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported! Does a new flag need to be added to this test?", + flag); + } +} + TEST(TSYNC_first) { struct sock_filter filter[] = { @@ -2421,6 +2744,99 @@ TEST(syscall_restart) _metadata->passed = 0; } +TEST_SIGNAL(filter_flag_log, SIGSYS) +{ + struct sock_filter allow_filter[] = { + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_filter kill_filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog allow_prog = { + .len = (unsigned short)ARRAY_SIZE(allow_filter), + .filter = allow_filter, + }; + struct sock_fprog kill_prog = { + .len = (unsigned short)ARRAY_SIZE(kill_filter), + .filter = kill_filter, + }; + long ret; + pid_t parent = getppid(); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + /* Verify that the FILTER_FLAG_LOG flag isn't accepted in strict mode */ + ret = seccomp(SECCOMP_SET_MODE_STRICT, SECCOMP_FILTER_FLAG_LOG, + &allow_prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } + EXPECT_NE(0, ret) { + TH_LOG("Kernel accepted FILTER_FLAG_LOG flag in strict mode!"); + } + EXPECT_EQ(EINVAL, errno) { + TH_LOG("Kernel returned unexpected errno for FILTER_FLAG_LOG flag in strict mode!"); + } + + /* Verify that a simple, permissive filter can be added with no flags */ + ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &allow_prog); + EXPECT_EQ(0, ret); + + /* See if the same filter can be added with the FILTER_FLAG_LOG flag */ + ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG, + &allow_prog); + ASSERT_NE(EINVAL, errno) { + TH_LOG("Kernel does not support the FILTER_FLAG_LOG flag!"); + } + EXPECT_EQ(0, ret); + + /* Ensure that the kill filter works with the FILTER_FLAG_LOG flag */ + ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG, + &kill_prog); + EXPECT_EQ(0, ret); + + EXPECT_EQ(parent, syscall(__NR_getppid)); + /* getpid() should never return. */ + EXPECT_EQ(0, syscall(__NR_getpid)); +} + +TEST(get_action_avail) +{ + __u32 actions[] = { SECCOMP_RET_KILL_THREAD, SECCOMP_RET_TRAP, + SECCOMP_RET_ERRNO, SECCOMP_RET_TRACE, + SECCOMP_RET_LOG, SECCOMP_RET_ALLOW }; + __u32 unknown_action = 0x10000000U; + int i; + long ret; + + ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[0]); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } + ASSERT_NE(EINVAL, errno) { + TH_LOG("Kernel does not support SECCOMP_GET_ACTION_AVAIL operation!"); + } + EXPECT_EQ(ret, 0); + + for (i = 0; i < ARRAY_SIZE(actions); i++) { + ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[i]); + EXPECT_EQ(ret, 0) { + TH_LOG("Expected action (0x%X) not available!", + actions[i]); + } + } + + /* Check that an unknown action is handled properly (EOPNOTSUPP) */ + ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &unknown_action); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EOPNOTSUPP); +} + /* * TODO: * - add microbenchmarks @@ -2429,6 +2845,8 @@ TEST(syscall_restart) * - endianness checking when appropriate * - 64-bit arg prodding * - arch value testing (x86 modes especially) + * - verify that FILTER_FLAG_LOG filters generate log messages + * - verify that RET_LOG generates log messages * - ... */ |