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

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

by Chang S. Bae

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

4 years, 3 months

1
0
0 0

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

by John Wood

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

4 years, 3 months

2
11
0 0

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

by Brendan Higgins

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

4 years, 3 months

2
15
0 0

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

by Jing Zhang

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

4 years, 3 months

4
29
0 0

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

by Po-Hsu Lin

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

4 years, 3 months

2
1
0 0

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

by David Matlack

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

4 years, 3 months

2
1
0 0

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

by Jarkko Sakkinen

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

4 years, 3 months

2
6
0 0

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

by Danielle Ratson

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

4 years, 3 months

1
0
0 0

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

by Richard Fitzgerald

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

4 years, 3 months

2
4
0 0

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

by Mike Rapoport

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

4 years, 3 months

6
31
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror