The kernel ABI for this is (finally) close to being merged: https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git/log/?h=for-next/bti-user I've made a couple of tweaks from v8: (1) Only map the interpreter or a static executable with BTI. The interpreter is responsible for handling the pages of a dynamic executable. This is a behaviour change in the kernel ABI since the last time I audited the code. (2) Rely on the recently released gcc 10 for building the test case. Thanks to Alex for helping me get a docker setup for that. Based-on: <20200519185645.3915-1-richard.henderson@linaro.org> ("linux-user: mmap/mprotect prot values") Based-on: An unpublished version of stsquad's testing/next So for avoidance of doubt, the complete tree may be found at https://github.com/rth7680/qemu/tree/tgt-arm-bti r~ Richard Henderson (5): linux-user/aarch64: Reset btype for signals linux-user: Set PAGE_TARGET_1 for TARGET_PROT_BTI include/elf: Add defines related to GNU property notes for AArch64 linux-user: Parse NT_GNU_PROPERTY_TYPE_0 notes tests/tcg/aarch64: Add bti smoke test include/elf.h | 22 +++++ include/exec/cpu-all.h | 2 + linux-user/qemu.h | 4 + linux-user/syscall_defs.h | 4 + linux-user/aarch64/signal.c | 10 ++- linux-user/elfload.c | 143 ++++++++++++++++++++++-------- linux-user/mmap.c | 16 ++++ target/arm/translate-a64.c | 6 +- tests/tcg/aarch64/bti-1.c | 62 +++++++++++++ tests/tcg/aarch64/bti-crt.inc.c | 51 +++++++++++ tests/tcg/aarch64/Makefile.target | 7 ++ tests/tcg/configure.sh | 4 + 12 files changed, 291 insertions(+), 40 deletions(-) create mode 100644 tests/tcg/aarch64/bti-1.c create mode 100644 tests/tcg/aarch64/bti-crt.inc.c -- 2.20.1 The kernel sets btype for the signal handler as if for a call. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/aarch64/signal.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, + offsetof(struct target_rt_frame_record, tramp); } env->xregs[0] = usig; - env->xregs[31] = frame_addr; env->xregs[29] = frame_addr + fr_ofs; - env->pc = ka->_sa_handler; env->xregs[30] = return_addr; + env->xregs[31] = frame_addr; + env->pc = ka->_sa_handler; + + /* Invoke the signal handler as if by indirect call. */ + if (cpu_isar_feature(aa64_bti, env_archcpu(env))) { + env->btype = 2; + } + if (info) { tswap_siginfo(&frame->info, info); env->xregs[1] = frame_addr + offsetof(struct target_rt_sigframe, info); -- 2.20.1 Transform the prot bit to a qemu internal page bit, and save it in the page tables. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu-all.h | 2 ++ linux-user/syscall_defs.h | 4 ++++ linux-user/mmap.c | 16 ++++++++++++++++ target/arm/translate-a64.c | 6 +++--- 4 files changed, 25 insertions(+), 3 deletions(-) diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-all.h +++ b/include/exec/cpu-all.h @@ -XXX,XX +XXX,XX @@ extern intptr_t qemu_host_page_mask; /* FIXME: Code that sets/uses this is broken and needs to go away. */ #define PAGE_RESERVED 0x0020 #endif +/* Target-specific bits that will be used via page_get_flags(). */ +#define PAGE_TARGET_1 0x0080 #if defined(CONFIG_USER_ONLY) void page_dump(FILE *f); diff --git a/linux-user/syscall_defs.h b/linux-user/syscall_defs.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall_defs.h +++ b/linux-user/syscall_defs.h @@ -XXX,XX +XXX,XX @@ struct target_winsize { #define TARGET_PROT_SEM 0x08 #endif +#ifdef TARGET_AARCH64 +#define TARGET_PROT_BTI 0x10 +#endif + /* Common */ #define TARGET_MAP_SHARED 0x01 /* Share changes */ #define TARGET_MAP_PRIVATE 0x02 /* Changes are private */ diff --git a/linux-user/mmap.c b/linux-user/mmap.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/mmap.c +++ b/linux-user/mmap.c @@ -XXX,XX +XXX,XX @@ static int validate_prot_to_pageflags(int *host_prot, int prot) *host_prot = (prot & (PROT_READ | PROT_WRITE)) | (prot & PROT_EXEC ? PROT_READ : 0); +#ifdef TARGET_AARCH64 + /* + * The PROT_BTI bit is only accepted if the cpu supports the feature. + * Since this is the unusual case, don't bother checking unless + * the bit has been requested. If set and valid, record the bit + * within QEMU's page_flags as PAGE_TARGET_1. + */ + if (prot & TARGET_PROT_BTI) { + ARMCPU *cpu = ARM_CPU(thread_cpu); + if (cpu_isar_feature(aa64_bti, cpu)) { + valid |= TARGET_PROT_BTI; + page_flags |= PAGE_TARGET_1; + } + } +#endif + return prot & ~valid ? 0 : page_flags; } diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_simd_fp(DisasContext *s, uint32_t insn) */ static bool is_guarded_page(CPUARMState *env, DisasContext *s) { -#ifdef CONFIG_USER_ONLY - return false; /* FIXME */ -#else uint64_t addr = s->base.pc_first; +#ifdef CONFIG_USER_ONLY + return page_get_flags(addr) & PAGE_TARGET_1; +#else int mmu_idx = arm_to_core_mmu_idx(s->mmu_idx); unsigned int index = tlb_index(env, mmu_idx, addr); CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr); -- 2.20.1 These are all of the defines required to parse GNU_PROPERTY_AARCH64_FEATURE_1_AND, copied from binutils. Other missing defines related to other GNU program headers and notes are elided for now. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/elf.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/include/elf.h b/include/elf.h index XXXXXXX..XXXXXXX 100644 --- a/include/elf.h +++ b/include/elf.h @@ -XXX,XX +XXX,XX @@ typedef int64_t Elf64_Sxword; #define PT_NOTE 4 #define PT_SHLIB 5 #define PT_PHDR 6 +#define PT_LOOS 0x60000000 +#define PT_HIOS 0x6fffffff #define PT_LOPROC 0x70000000 #define PT_HIPROC 0x7fffffff +#define PT_GNU_PROPERTY (PT_LOOS + 0x474e553) + #define PT_MIPS_REGINFO 0x70000000 #define PT_MIPS_RTPROC 0x70000001 #define PT_MIPS_OPTIONS 0x70000002 @@ -XXX,XX +XXX,XX @@ typedef struct elf64_shdr { #define NT_ARM_SYSTEM_CALL 0x404 /* ARM system call number */ #define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension regs */ +/* Defined note types for GNU systems. */ + +#define NT_GNU_PROPERTY_TYPE_0 5 /* Program property */ + +/* Values used in GNU .note.gnu.property notes (NT_GNU_PROPERTY_TYPE_0). */ + +#define GNU_PROPERTY_STACK_SIZE 1 +#define GNU_PROPERTY_NO_COPY_ON_PROTECTED 2 + +#define GNU_PROPERTY_LOPROC 0xc0000000 +#define GNU_PROPERTY_HIPROC 0xdfffffff +#define GNU_PROPERTY_LOUSER 0xe0000000 +#define GNU_PROPERTY_HIUSER 0xffffffff + +#define GNU_PROPERTY_AARCH64_FEATURE_1_AND 0xc0000000 +#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1u << 0) +#define GNU_PROPERTY_AARCH64_FEATURE_1_PAC (1u << 1) + /* * Physical entry point into the kernel. * -- 2.20.1 For aarch64, this includes the GNU_PROPERTY_AARCH64_FEATURE_1_BTI bit, which indicates that the image should be mapped with guarded pages. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v9: Only map the startup executable with BTI; anything else must be handled by the interpreter. --- linux-user/qemu.h | 4 ++ linux-user/elfload.c | 143 ++++++++++++++++++++++++++++++++----------- 2 files changed, 112 insertions(+), 35 deletions(-) diff --git a/linux-user/qemu.h b/linux-user/qemu.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/qemu.h +++ b/linux-user/qemu.h @@ -XXX,XX +XXX,XX @@ struct image_info { abi_ulong interpreter_loadmap_addr; abi_ulong interpreter_pt_dynamic_addr; struct image_info *other_info; + + /* For target-specific processing of NT_GNU_PROPERTY_TYPE_0. */ + uint32_t note_flags; + #ifdef TARGET_MIPS int fp_abi; int interp_fp_abi; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, struct elfhdr *ehdr = (struct elfhdr *)bprm_buf; struct elf_phdr *phdr; abi_ulong load_addr, load_bias, loaddr, hiaddr, error; - int i, retval; + int i, retval, prot_exec; const char *errmsg; /* First of all, some simple consistency checks */ @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, loaddr = -1, hiaddr = 0; info->alignment = 0; for (i = 0; i < ehdr->e_phnum; ++i) { - if (phdr[i].p_type == PT_LOAD) { - abi_ulong a = phdr[i].p_vaddr - phdr[i].p_offset; + struct elf_phdr *eppnt = phdr + i; + + if (eppnt->p_type == PT_LOAD) { + abi_ulong a = eppnt->p_vaddr - eppnt->p_offset; if (a < loaddr) { loaddr = a; } - a = phdr[i].p_vaddr + phdr[i].p_memsz; + a = eppnt->p_vaddr + eppnt->p_memsz; if (a > hiaddr) { hiaddr = a; } ++info->nsegs; - info->alignment |= phdr[i].p_align; + info->alignment |= eppnt->p_align; + } else if (eppnt->p_type == PT_INTERP && pinterp_name) { + char *interp_name; + + if (*pinterp_name) { + errmsg = "Multiple PT_INTERP entries"; + goto exit_errmsg; + } + interp_name = malloc(eppnt->p_filesz); + if (!interp_name) { + goto exit_perror; + } + + if (eppnt->p_offset + eppnt->p_filesz <= BPRM_BUF_SIZE) { + memcpy(interp_name, bprm_buf + eppnt->p_offset, + eppnt->p_filesz); + } else { + retval = pread(image_fd, interp_name, eppnt->p_filesz, + eppnt->p_offset); + if (retval != eppnt->p_filesz) { + goto exit_perror; + } + } + if (interp_name[eppnt->p_filesz - 1] != 0) { + errmsg = "Invalid PT_INTERP entry"; + goto exit_errmsg; + } + *pinterp_name = interp_name; + } else if (eppnt->p_type == PT_GNU_PROPERTY) { + /* Process NT_GNU_PROPERTY_TYPE_0. */ + const uint32_t gnu0_magic = const_le32('G' | 'N' << 8 | 'U' << 16); + uint32_t note[7]; + + /* + * The note contents are 7 words, but depending on LP64 vs ILP32 + * there may be an 8th padding word at the end. Check for and + * read the minimum size. Further checks below will validate + * that the sizes of everything involved are as we expect. + */ + if (eppnt->p_filesz < sizeof(note)) { + continue; + } + if (eppnt->p_offset + eppnt->p_filesz <= BPRM_BUF_SIZE) { + memcpy(note, bprm_buf + eppnt->p_offset, sizeof(note)); + } else { + retval = pread(image_fd, note, sizeof(note), eppnt->p_offset); + if (retval != sizeof(note)) { + goto exit_perror; + } + } +#ifdef BSWAP_NEEDED + for (i = 0; i < ARRAY_SIZE(note); ++i) { + bswap32s(note + i); + } +#endif + /* + * Check that this is a NT_GNU_PROPERTY_TYPE_0 note. + * Again, descsz includes padding. Full size validation + * awaits checking the final payload. + */ + if (note[0] != 4 || /* namesz */ + note[1] < 12 || /* descsz */ + note[2] != NT_GNU_PROPERTY_TYPE_0 || /* type */ + note[3] != gnu0_magic) { /* name */ + continue; + } +#ifdef TARGET_AARCH64 + if (note[4] == GNU_PROPERTY_AARCH64_FEATURE_1_AND && + note[5] == 4) { + info->note_flags = note[6]; + } +#endif /* TARGET_AARCH64 */ } } @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, info->brk = 0; info->elf_flags = ehdr->e_flags; + prot_exec = PROT_EXEC; +#ifdef TARGET_AARCH64 + /* + * If the BTI feature is present, this indicates that the executable + * pages of the startup binary should be mapped with PROT_BTI, so that + * branch targets are enforced. + * + * The startup executable is either the interpreter or the static + * binary. The interpreter is responsible for all pages of a + * dynamic executable. + * + * Elf notes are backward compatible to older cpus. + * Do not enable BTI unless it is supported. + */ + if ((info->note_flags & GNU_PROPERTY_AARCH64_FEATURE_1_BTI) + && (pinterp_name == NULL || *pinterp_name == 0) + && cpu_isar_feature(aa64_bti, ARM_CPU(thread_cpu))) { + prot_exec |= TARGET_PROT_BTI; + } +#endif + for (i = 0; i < ehdr->e_phnum; i++) { struct elf_phdr *eppnt = phdr + i; if (eppnt->p_type == PT_LOAD) { abi_ulong vaddr, vaddr_po, vaddr_ps, vaddr_ef, vaddr_em, vaddr_len; int elf_prot = 0; - if (eppnt->p_flags & PF_R) elf_prot = PROT_READ; - if (eppnt->p_flags & PF_W) elf_prot |= PROT_WRITE; - if (eppnt->p_flags & PF_X) elf_prot |= PROT_EXEC; + if (eppnt->p_flags & PF_R) { + elf_prot |= PROT_READ; + } + if (eppnt->p_flags & PF_W) { + elf_prot |= PROT_WRITE; + } + if (eppnt->p_flags & PF_X) { + elf_prot |= prot_exec; + } vaddr = load_bias + eppnt->p_vaddr; vaddr_po = TARGET_ELF_PAGEOFFSET(vaddr); @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, info->brk = vaddr_em; } } - } else if (eppnt->p_type == PT_INTERP && pinterp_name) { - char *interp_name; - - if (*pinterp_name) { - errmsg = "Multiple PT_INTERP entries"; - goto exit_errmsg; - } - interp_name = malloc(eppnt->p_filesz); - if (!interp_name) { - goto exit_perror; - } - - if (eppnt->p_offset + eppnt->p_filesz <= BPRM_BUF_SIZE) { - memcpy(interp_name, bprm_buf + eppnt->p_offset, - eppnt->p_filesz); - } else { - retval = pread(image_fd, interp_name, eppnt->p_filesz, - eppnt->p_offset); - if (retval != eppnt->p_filesz) { - goto exit_perror; - } - } - if (interp_name[eppnt->p_filesz - 1] != 0) { - errmsg = "Invalid PT_INTERP entry"; - goto exit_errmsg; - } - *pinterp_name = interp_name; #ifdef TARGET_MIPS } else if (eppnt->p_type == PT_MIPS_ABIFLAGS) { Mips_elf_abiflags_v0 abiflags; -- 2.20.1 This test requires gcc 10 for -mbranch-protection=standard. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v9: Expect and require gcc 10. --- tests/tcg/aarch64/bti-1.c | 62 +++++++++++++++++++++++++++++++ tests/tcg/aarch64/bti-crt.inc.c | 51 +++++++++++++++++++++++++ tests/tcg/aarch64/Makefile.target | 7 ++++ tests/tcg/configure.sh | 4 ++ 4 files changed, 124 insertions(+) create mode 100644 tests/tcg/aarch64/bti-1.c create mode 100644 tests/tcg/aarch64/bti-crt.inc.c diff --git a/tests/tcg/aarch64/bti-1.c b/tests/tcg/aarch64/bti-1.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/tcg/aarch64/bti-1.c @@ -XXX,XX +XXX,XX @@ +/* + * Branch target identification, basic notskip cases. + */ + +#include "bti-crt.inc.c" + +static void skip2_sigill(int sig, siginfo_t *info, ucontext_t *uc) +{ + uc->uc_mcontext.pc += 8; + uc->uc_mcontext.pstate = 1; +} + +#define NOP "nop" +#define BTI_N "hint #32" +#define BTI_C "hint #34" +#define BTI_J "hint #36" +#define BTI_JC "hint #38" + +#define BTYPE_1(DEST) \ + asm("mov %0,#1; adr x16, 1f; br x16; 1: " DEST "; mov %0,#0" \ + : "=r"(skipped) : : "x16") + +#define BTYPE_2(DEST) \ + asm("mov %0,#1; adr x16, 1f; blr x16; 1: " DEST "; mov %0,#0" \ + : "=r"(skipped) : : "x16", "x30") + +#define BTYPE_3(DEST) \ + asm("mov %0,#1; adr x15, 1f; br x15; 1: " DEST "; mov %0,#0" \ + : "=r"(skipped) : : "x15") + +#define TEST(WHICH, DEST, EXPECT) \ + do { WHICH(DEST); fail += skipped ^ EXPECT; } while (0) + + +int main() +{ + int fail = 0; + int skipped; + + /* Signal-like with SA_SIGINFO. */ + signal_info(SIGILL, skip2_sigill); + + TEST(BTYPE_1, NOP, 1); + TEST(BTYPE_1, BTI_N, 1); + TEST(BTYPE_1, BTI_C, 0); + TEST(BTYPE_1, BTI_J, 0); + TEST(BTYPE_1, BTI_JC, 0); + + TEST(BTYPE_2, NOP, 1); + TEST(BTYPE_2, BTI_N, 1); + TEST(BTYPE_2, BTI_C, 0); + TEST(BTYPE_2, BTI_J, 1); + TEST(BTYPE_2, BTI_JC, 0); + + TEST(BTYPE_3, NOP, 1); + TEST(BTYPE_3, BTI_N, 1); + TEST(BTYPE_3, BTI_C, 1); + TEST(BTYPE_3, BTI_J, 0); + TEST(BTYPE_3, BTI_JC, 0); + + return fail; +} diff --git a/tests/tcg/aarch64/bti-crt.inc.c b/tests/tcg/aarch64/bti-crt.inc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/tcg/aarch64/bti-crt.inc.c @@ -XXX,XX +XXX,XX @@ +/* + * Minimal user-environment for testing BTI. + * + * Normal libc is not (yet) built with BTI support enabled, + * and so could generate a BTI TRAP before ever reaching main. + */ + +#include <stdlib.h> +#include <signal.h> +#include <ucontext.h> +#include <asm/unistd.h> + +int main(void); + +void _start(void) +{ + exit(main()); +} + +void exit(int ret) +{ + register int x0 __asm__("x0") = ret; + register int x8 __asm__("x8") = __NR_exit; + + asm volatile("svc #0" : : "r"(x0), "r"(x8)); + __builtin_unreachable(); +} + +/* + * Irritatingly, the user API struct sigaction does not match the + * kernel API struct sigaction. So for simplicity, isolate the + * kernel ABI here, and make this act like signal. + */ +void signal_info(int sig, void (*fn)(int, siginfo_t *, ucontext_t *)) +{ + struct kernel_sigaction { + void (*handler)(int, siginfo_t *, ucontext_t *); + unsigned long flags; + unsigned long restorer; + unsigned long mask; + } sa = { fn, SA_SIGINFO, 0, 0 }; + + register int x0 __asm__("x0") = sig; + register void *x1 __asm__("x1") = &sa; + register void *x2 __asm__("x2") = 0; + register int x3 __asm__("x3") = sizeof(unsigned long); + register int x8 __asm__("x8") = __NR_rt_sigaction; + + asm volatile("svc #0" + : : "r"(x0), "r"(x1), "r"(x2), "r"(x3), "r"(x8) : "memory"); +} diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -XXX,XX +XXX,XX @@ run-pauth-%: QEMU_OPTS += -cpu max pauth-%: CFLAGS += -march=armv8.3-a endif +# BTI Tests +ifneq ($(DOCKER_IMAGE)$(CROSS_CC_HAS_ARMV8_BTI),) +AARCH64_TESTS += bti-1 +bti-%: CFLAGS += -mbranch-protection=standard +bti-%: LDFLAGS += -nostdlib +endif + # Semihosting smoke test for linux-user AARCH64_TESTS += semihosting run-semihosting: semihosting diff --git a/tests/tcg/configure.sh b/tests/tcg/configure.sh index XXXXXXX..XXXXXXX 100755 --- a/tests/tcg/configure.sh +++ b/tests/tcg/configure.sh @@ -XXX,XX +XXX,XX @@ for target in $target_list; do -march=armv8.3-a -o $TMPE $TMPC; then echo "CROSS_CC_HAS_ARMV8_3=y" >> $config_target_mak fi + if do_compiler "$target_compiler" $target_compiler_cflags \ + -mbranch-protection=standard -o $TMPE $TMPC; then + echo "CROSS_CC_HAS_ARMV8_BTI=y" >> $config_target_mak + fi ;; esac -- 2.20.1 The kernel abi for this was merged in v5.8, just as the qemu 5.1 merge window was closing, so this slipped to the next dev cycle. Changes from v11: * Fix the reported bti-2 crash. Work around a bug in ld from binutils 2.34 (in our docker image, and Linaro's aarch64 ubuntu 20 host), which has been fixed in binutils 2.35 (in my laptop's cross-compiler installation). Changes from v10: * Include Phil's plug of interp_name memory leak. * Convert error reporting to Error api. * Mirror the kernel's code structure for parsing notes (though Error means that it's not exactly the same). * Split aarch64 stuff from basic note parsing patch. Changes from v9: * Split what is now patch 7 into 3 more (pmm). * All prerequisites are now upstream. r~ Philippe Mathieu-Daudé (1): linux-user/elfload: Avoid leaking interp_name using GLib memory API Richard Henderson (11): linux-user/aarch64: Reset btype for signals linux-user: Set PAGE_TARGET_1 for TARGET_PROT_BTI include/elf: Add defines related to GNU property notes for AArch64 linux-user/elfload: Fix coding style in load_elf_image linux-user/elfload: Adjust iteration over phdr linux-user/elfload: Move PT_INTERP detection to first loop linux-user/elfload: Use Error for load_elf_image linux-user/elfload: Use Error for load_elf_interp linux-user/elfload: Parse NT_GNU_PROPERTY_TYPE_0 notes linux-user/elfload: Parse GNU_PROPERTY_AARCH64_FEATURE_1_AND tests/tcg/aarch64: Add bti smoke tests include/elf.h | 22 ++ include/exec/cpu-all.h | 2 + linux-user/qemu.h | 4 + linux-user/syscall_defs.h | 4 + target/arm/cpu.h | 5 + linux-user/aarch64/signal.c | 10 +- linux-user/elfload.c | 326 +++++++++++++++++++++++++----- linux-user/mmap.c | 16 ++ target/arm/translate-a64.c | 6 +- tests/tcg/aarch64/bti-1.c | 62 ++++++ tests/tcg/aarch64/bti-2.c | 116 +++++++++++ tests/tcg/aarch64/bti-crt.inc.c | 51 +++++ tests/tcg/aarch64/Makefile.target | 10 + tests/tcg/configure.sh | 4 + 14 files changed, 577 insertions(+), 61 deletions(-) create mode 100644 tests/tcg/aarch64/bti-1.c create mode 100644 tests/tcg/aarch64/bti-2.c create mode 100644 tests/tcg/aarch64/bti-crt.inc.c -- 2.25.1 The kernel sets btype for the signal handler as if for a call. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/aarch64/signal.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, + offsetof(struct target_rt_frame_record, tramp); } env->xregs[0] = usig; - env->xregs[31] = frame_addr; env->xregs[29] = frame_addr + fr_ofs; - env->pc = ka->_sa_handler; env->xregs[30] = return_addr; + env->xregs[31] = frame_addr; + env->pc = ka->_sa_handler; + + /* Invoke the signal handler as if by indirect call. */ + if (cpu_isar_feature(aa64_bti, env_archcpu(env))) { + env->btype = 2; + } + if (info) { tswap_siginfo(&frame->info, info); env->xregs[1] = frame_addr + offsetof(struct target_rt_sigframe, info); -- 2.25.1 Transform the prot bit to a qemu internal page bit, and save it in the page tables. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v10: Add PAGE_BTI define (pmm). --- include/exec/cpu-all.h | 2 ++ linux-user/syscall_defs.h | 4 ++++ target/arm/cpu.h | 5 +++++ linux-user/mmap.c | 16 ++++++++++++++++ target/arm/translate-a64.c | 6 +++--- 5 files changed, 30 insertions(+), 3 deletions(-) diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-all.h +++ b/include/exec/cpu-all.h @@ -XXX,XX +XXX,XX @@ extern intptr_t qemu_host_page_mask; /* FIXME: Code that sets/uses this is broken and needs to go away. */ #define PAGE_RESERVED 0x0020 #endif +/* Target-specific bits that will be used via page_get_flags(). */ +#define PAGE_TARGET_1 0x0080 #if defined(CONFIG_USER_ONLY) void page_dump(FILE *f); diff --git a/linux-user/syscall_defs.h b/linux-user/syscall_defs.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall_defs.h +++ b/linux-user/syscall_defs.h @@ -XXX,XX +XXX,XX @@ struct target_winsize { #define TARGET_PROT_SEM 0x08 #endif +#ifdef TARGET_AARCH64 +#define TARGET_PROT_BTI 0x10 +#endif + /* Common */ #define TARGET_MAP_SHARED 0x01 /* Share changes */ #define TARGET_MAP_PRIVATE 0x02 /* Changes are private */ diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline MemTxAttrs *typecheck_memtxattrs(MemTxAttrs *x) #define arm_tlb_bti_gp(x) (typecheck_memtxattrs(x)->target_tlb_bit0) #define arm_tlb_mte_tagged(x) (typecheck_memtxattrs(x)->target_tlb_bit1) +/* + * AArch64 usage of the PAGE_TARGET_* bits for linux-user. + */ +#define PAGE_BTI PAGE_TARGET_1 + /* * Naming convention for isar_feature functions: * Functions which test 32-bit ID registers should have _aa32_ in diff --git a/linux-user/mmap.c b/linux-user/mmap.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/mmap.c +++ b/linux-user/mmap.c @@ -XXX,XX +XXX,XX @@ static int validate_prot_to_pageflags(int *host_prot, int prot) *host_prot = (prot & (PROT_READ | PROT_WRITE)) | (prot & PROT_EXEC ? PROT_READ : 0); +#ifdef TARGET_AARCH64 + /* + * The PROT_BTI bit is only accepted if the cpu supports the feature. + * Since this is the unusual case, don't bother checking unless + * the bit has been requested. If set and valid, record the bit + * within QEMU's page_flags. + */ + if (prot & TARGET_PROT_BTI) { + ARMCPU *cpu = ARM_CPU(thread_cpu); + if (cpu_isar_feature(aa64_bti, cpu)) { + valid |= TARGET_PROT_BTI; + page_flags |= PAGE_BTI; + } + } +#endif + return prot & ~valid ? 0 : page_flags; } diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_simd_fp(DisasContext *s, uint32_t insn) */ static bool is_guarded_page(CPUARMState *env, DisasContext *s) { -#ifdef CONFIG_USER_ONLY - return false; /* FIXME */ -#else uint64_t addr = s->base.pc_first; +#ifdef CONFIG_USER_ONLY + return page_get_flags(addr) & PAGE_BTI; +#else int mmu_idx = arm_to_core_mmu_idx(s->mmu_idx); unsigned int index = tlb_index(env, mmu_idx, addr); CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr); -- 2.25.1 These are all of the defines required to parse GNU_PROPERTY_AARCH64_FEATURE_1_AND, copied from binutils. Other missing defines related to other GNU program headers and notes are elided for now. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/elf.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/include/elf.h b/include/elf.h index XXXXXXX..XXXXXXX 100644 --- a/include/elf.h +++ b/include/elf.h @@ -XXX,XX +XXX,XX @@ typedef int64_t Elf64_Sxword; #define PT_NOTE 4 #define PT_SHLIB 5 #define PT_PHDR 6 +#define PT_LOOS 0x60000000 +#define PT_HIOS 0x6fffffff #define PT_LOPROC 0x70000000 #define PT_HIPROC 0x7fffffff +#define PT_GNU_PROPERTY (PT_LOOS + 0x474e553) + #define PT_MIPS_REGINFO 0x70000000 #define PT_MIPS_RTPROC 0x70000001 #define PT_MIPS_OPTIONS 0x70000002 @@ -XXX,XX +XXX,XX @@ typedef struct elf64_shdr { #define NT_ARM_SYSTEM_CALL 0x404 /* ARM system call number */ #define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension regs */ +/* Defined note types for GNU systems. */ + +#define NT_GNU_PROPERTY_TYPE_0 5 /* Program property */ + +/* Values used in GNU .note.gnu.property notes (NT_GNU_PROPERTY_TYPE_0). */ + +#define GNU_PROPERTY_STACK_SIZE 1 +#define GNU_PROPERTY_NO_COPY_ON_PROTECTED 2 + +#define GNU_PROPERTY_LOPROC 0xc0000000 +#define GNU_PROPERTY_HIPROC 0xdfffffff +#define GNU_PROPERTY_LOUSER 0xe0000000 +#define GNU_PROPERTY_HIUSER 0xffffffff + +#define GNU_PROPERTY_AARCH64_FEATURE_1_AND 0xc0000000 +#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1u << 0) +#define GNU_PROPERTY_AARCH64_FEATURE_1_PAC (1u << 1) + /* * Physical entry point into the kernel. * -- 2.25.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Fix an unlikely memory leak in load_elf_image(). Fixes: bf858897b7 ("linux-user: Re-use load_elf_image for the main binary.") Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-Id: <20201003174944.1972444-1-f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/elfload.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, info->brk = vaddr_em; } } else if (eppnt->p_type == PT_INTERP && pinterp_name) { - char *interp_name; + g_autofree char *interp_name = NULL; if (*pinterp_name) { errmsg = "Multiple PT_INTERP entries"; goto exit_errmsg; } - interp_name = malloc(eppnt->p_filesz); + interp_name = g_malloc(eppnt->p_filesz); if (!interp_name) { goto exit_perror; } @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, errmsg = "Invalid PT_INTERP entry"; goto exit_errmsg; } - *pinterp_name = interp_name; + *pinterp_name = g_steal_pointer(&interp_name); #ifdef TARGET_MIPS } else if (eppnt->p_type == PT_MIPS_ABIFLAGS) { Mips_elf_abiflags_v0 abiflags; @@ -XXX,XX +XXX,XX @@ int load_elf_binary(struct linux_binprm *bprm, struct image_info *info) if (elf_interpreter) { info->load_bias = interp_info.load_bias; info->entry = interp_info.entry; - free(elf_interpreter); + g_free(elf_interpreter); } #ifdef USE_ELF_CORE_DUMP -- 2.25.1 Fixing this now will clarify following patches. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/elfload.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, abi_ulong vaddr, vaddr_po, vaddr_ps, vaddr_ef, vaddr_em, vaddr_len; int elf_prot = 0; - if (eppnt->p_flags & PF_R) elf_prot = PROT_READ; - if (eppnt->p_flags & PF_W) elf_prot |= PROT_WRITE; - if (eppnt->p_flags & PF_X) elf_prot |= PROT_EXEC; + if (eppnt->p_flags & PF_R) { + elf_prot |= PROT_READ; + } + if (eppnt->p_flags & PF_W) { + elf_prot |= PROT_WRITE; + } + if (eppnt->p_flags & PF_X) { + elf_prot |= PROT_EXEC; + } vaddr = load_bias + eppnt->p_vaddr; vaddr_po = TARGET_ELF_PAGEOFFSET(vaddr); -- 2.25.1 The second loop uses a loop induction variable, and the first does not. Transform the first to match the second, to simplify a following patch moving code between them. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/elfload.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, loaddr = -1, hiaddr = 0; info->alignment = 0; for (i = 0; i < ehdr->e_phnum; ++i) { - if (phdr[i].p_type == PT_LOAD) { - abi_ulong a = phdr[i].p_vaddr - phdr[i].p_offset; + struct elf_phdr *eppnt = phdr + i; + if (eppnt->p_type == PT_LOAD) { + abi_ulong a = eppnt->p_vaddr - eppnt->p_offset; if (a < loaddr) { loaddr = a; } - a = phdr[i].p_vaddr + phdr[i].p_memsz; + a = eppnt->p_vaddr + eppnt->p_memsz; if (a > hiaddr) { hiaddr = a; } ++info->nsegs; - info->alignment |= phdr[i].p_align; + info->alignment |= eppnt->p_align; } } -- 2.25.1 For BTI, we need to know if the executable is static or dynamic, which means looking for PT_INTERP earlier. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/elfload.c | 60 +++++++++++++++++++++++--------------------- 1 file changed, 31 insertions(+), 29 deletions(-) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, mmap_lock(); - /* Find the maximum size of the image and allocate an appropriate - amount of memory to handle that. */ + /* + * Find the maximum size of the image and allocate an appropriate + * amount of memory to handle that. Locate the interpreter, if any. + */ loaddr = -1, hiaddr = 0; info->alignment = 0; for (i = 0; i < ehdr->e_phnum; ++i) { @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, } ++info->nsegs; info->alignment |= eppnt->p_align; + } else if (eppnt->p_type == PT_INTERP && pinterp_name) { + g_autofree char *interp_name = NULL; + + if (*pinterp_name) { + errmsg = "Multiple PT_INTERP entries"; + goto exit_errmsg; + } + interp_name = g_malloc(eppnt->p_filesz); + if (!interp_name) { + goto exit_perror; + } + + if (eppnt->p_offset + eppnt->p_filesz <= BPRM_BUF_SIZE) { + memcpy(interp_name, bprm_buf + eppnt->p_offset, + eppnt->p_filesz); + } else { + retval = pread(image_fd, interp_name, eppnt->p_filesz, + eppnt->p_offset); + if (retval != eppnt->p_filesz) { + goto exit_perror; + } + } + if (interp_name[eppnt->p_filesz - 1] != 0) { + errmsg = "Invalid PT_INTERP entry"; + goto exit_errmsg; + } + *pinterp_name = g_steal_pointer(&interp_name); } } @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, if (vaddr_em > info->brk) { info->brk = vaddr_em; } - } else if (eppnt->p_type == PT_INTERP && pinterp_name) { - g_autofree char *interp_name = NULL; - - if (*pinterp_name) { - errmsg = "Multiple PT_INTERP entries"; - goto exit_errmsg; - } - interp_name = g_malloc(eppnt->p_filesz); - if (!interp_name) { - goto exit_perror; - } - - if (eppnt->p_offset + eppnt->p_filesz <= BPRM_BUF_SIZE) { - memcpy(interp_name, bprm_buf + eppnt->p_offset, - eppnt->p_filesz); - } else { - retval = pread(image_fd, interp_name, eppnt->p_filesz, - eppnt->p_offset); - if (retval != eppnt->p_filesz) { - goto exit_perror; - } - } - if (interp_name[eppnt->p_filesz - 1] != 0) { - errmsg = "Invalid PT_INTERP entry"; - goto exit_errmsg; - } - *pinterp_name = g_steal_pointer(&interp_name); #ifdef TARGET_MIPS } else if (eppnt->p_type == PT_MIPS_ABIFLAGS) { Mips_elf_abiflags_v0 abiflags; -- 2.25.1 This is a bit clearer than open-coding some of this with a bare c string. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/elfload.c | 37 ++++++++++++++++++++----------------- 1 file changed, 20 insertions(+), 17 deletions(-) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ #include "qemu/guest-random.h" #include "qemu/units.h" #include "qemu/selfmap.h" +#include "qapi/error.h" #ifdef _ARCH_PPC64 #undef ARCH_DLINFO @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, struct elf_phdr *phdr; abi_ulong load_addr, load_bias, loaddr, hiaddr, error; int i, retval; - const char *errmsg; + Error *err = NULL; /* First of all, some simple consistency checks */ - errmsg = "Invalid ELF image for this architecture"; if (!elf_check_ident(ehdr)) { + error_setg(&err, "Invalid ELF image for this architecture"); goto exit_errmsg; } bswap_ehdr(ehdr); if (!elf_check_ehdr(ehdr)) { + error_setg(&err, "Invalid ELF image for this architecture"); goto exit_errmsg; } @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, g_autofree char *interp_name = NULL; if (*pinterp_name) { - errmsg = "Multiple PT_INTERP entries"; + error_setg(&err, "Multiple PT_INTERP entries"); goto exit_errmsg; } + interp_name = g_malloc(eppnt->p_filesz); - if (!interp_name) { - goto exit_perror; - } if (eppnt->p_offset + eppnt->p_filesz <= BPRM_BUF_SIZE) { memcpy(interp_name, bprm_buf + eppnt->p_offset, @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, retval = pread(image_fd, interp_name, eppnt->p_filesz, eppnt->p_offset); if (retval != eppnt->p_filesz) { - goto exit_perror; + goto exit_read; } } if (interp_name[eppnt->p_filesz - 1] != 0) { - errmsg = "Invalid PT_INTERP entry"; + error_setg(&err, "Invalid PT_INTERP entry"); goto exit_errmsg; } *pinterp_name = g_steal_pointer(&interp_name); @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, (ehdr->e_type == ET_EXEC ? MAP_FIXED : 0), -1, 0); if (load_addr == -1) { - goto exit_perror; + goto exit_mmap; } load_bias = load_addr - loaddr; @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, image_fd, eppnt->p_offset - vaddr_po); if (error == -1) { - goto exit_perror; + goto exit_mmap; } } @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, } else if (eppnt->p_type == PT_MIPS_ABIFLAGS) { Mips_elf_abiflags_v0 abiflags; if (eppnt->p_filesz < sizeof(Mips_elf_abiflags_v0)) { - errmsg = "Invalid PT_MIPS_ABIFLAGS entry"; + error_setg(&err, "Invalid PT_MIPS_ABIFLAGS entry"); goto exit_errmsg; } if (eppnt->p_offset + eppnt->p_filesz <= BPRM_BUF_SIZE) { @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, retval = pread(image_fd, &abiflags, sizeof(Mips_elf_abiflags_v0), eppnt->p_offset); if (retval != sizeof(Mips_elf_abiflags_v0)) { - goto exit_perror; + goto exit_read; } } bswap_mips_abiflags(&abiflags); @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, exit_read: if (retval >= 0) { - errmsg = "Incomplete read of file header"; - goto exit_errmsg; + error_setg(&err, "Incomplete read of file header"); + } else { + error_setg_errno(&err, errno, "Error reading file header"); } - exit_perror: - errmsg = strerror(errno); + goto exit_errmsg; + exit_mmap: + error_setg_errno(&err, errno, "Error mapping file"); + goto exit_errmsg; exit_errmsg: - fprintf(stderr, "%s: %s\n", image_name, errmsg); + error_reportf_err(err, "%s: ", image_name); exit(-1); } -- 2.25.1 This is slightly clearer than just using strerror, though the different forms produced by error_setg_file_open and error_setg_errno isn't entirely convenient. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/elfload.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static void load_elf_interp(const char *filename, struct image_info *info, char bprm_buf[BPRM_BUF_SIZE]) { int fd, retval; + Error *err = NULL; fd = open(path(filename), O_RDONLY); if (fd < 0) { - goto exit_perror; + error_setg_file_open(&err, errno, filename); + error_report_err(err); + exit(-1); } retval = read(fd, bprm_buf, BPRM_BUF_SIZE); if (retval < 0) { - goto exit_perror; + error_setg_errno(&err, errno, "Error reading file header"); + error_reportf_err(err, "%s: ", filename); + exit(-1); } + if (retval < BPRM_BUF_SIZE) { memset(bprm_buf + retval, 0, BPRM_BUF_SIZE - retval); } load_elf_image(filename, fd, info, NULL, bprm_buf); - return; - - exit_perror: - fprintf(stderr, "%s: %s\n", filename, strerror(errno)); - exit(-1); } static int symfind(const void *s0, const void *s1) -- 2.25.1 This is generic support, with the code disabled for all targets. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v9: Only map the startup executable with BTI; anything else must be handled by the interpreter. v10: Split out preparatory patches (pmm). v11: Mirror(-ish) the kernel's code structure (pmm). --- linux-user/qemu.h | 4 ++ linux-user/elfload.c | 157 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 161 insertions(+) diff --git a/linux-user/qemu.h b/linux-user/qemu.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/qemu.h +++ b/linux-user/qemu.h @@ -XXX,XX +XXX,XX @@ struct image_info { abi_ulong interpreter_loadmap_addr; abi_ulong interpreter_pt_dynamic_addr; struct image_info *other_info; + + /* For target-specific processing of NT_GNU_PROPERTY_TYPE_0. */ + uint32_t note_flags; + #ifdef TARGET_MIPS int fp_abi; int interp_fp_abi; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static void elf_core_copy_regs(target_elf_gregset_t *regs, #include "elf.h" +static bool arch_parse_elf_property(uint32_t pr_type, uint32_t pr_datasz, + const uint32_t *data, + struct image_info *info, + Error **errp) +{ + g_assert_not_reached(); +} +#define ARCH_USE_GNU_PROPERTY 0 + struct exec { unsigned int a_info; /* Use macros N_MAGIC, etc for access */ @@ -XXX,XX +XXX,XX @@ void probe_guest_base(const char *image_name, abi_ulong guest_loaddr, "@ 0x%" PRIx64 "\n", (uint64_t)guest_base); } +enum { + /* The string "GNU\0" as a magic number. */ + GNU0_MAGIC = const_le32('G' | 'N' << 8 | 'U' << 16), + NOTE_DATA_SZ = 1 * KiB, + NOTE_NAME_SZ = 4, + ELF_GNU_PROPERTY_ALIGN = ELF_CLASS == ELFCLASS32 ? 4 : 8, +}; + +/* + * Process a single gnu_property entry. + * Return false for error. + */ +static bool parse_elf_property(const uint32_t *data, int *off, int datasz, + struct image_info *info, bool have_prev_type, + uint32_t *prev_type, Error **errp) +{ + uint32_t pr_type, pr_datasz, step; + + if (*off > datasz || !QEMU_IS_ALIGNED(*off, ELF_GNU_PROPERTY_ALIGN)) { + goto error_data; + } + datasz -= *off; + data += *off / sizeof(uint32_t); + + if (datasz < 2 * sizeof(uint32_t)) { + goto error_data; + } + pr_type = data[0]; + pr_datasz = data[1]; + data += 2; + datasz -= 2 * sizeof(uint32_t); + step = ROUND_UP(pr_datasz, ELF_GNU_PROPERTY_ALIGN); + if (step > datasz) { + goto error_data; + } + + /* Properties are supposed to be unique and sorted on pr_type. */ + if (have_prev_type && pr_type <= *prev_type) { + if (pr_type == *prev_type) { + error_setg(errp, "Duplicate property in PT_GNU_PROPERTY"); + } else { + error_setg(errp, "Unsorted property in PT_GNU_PROPERTY"); + } + return false; + } + *prev_type = pr_type; + + if (!arch_parse_elf_property(pr_type, pr_datasz, data, info, errp)) { + return false; + } + + *off += 2 * sizeof(uint32_t) + step; + return true; + + error_data: + error_setg(errp, "Ill-formed property in PT_GNU_PROPERTY"); + return false; +} + +/* Process NT_GNU_PROPERTY_TYPE_0. */ +static bool parse_elf_properties(int image_fd, + struct image_info *info, + const struct elf_phdr *phdr, + char bprm_buf[BPRM_BUF_SIZE], + Error **errp) +{ + union { + struct elf_note nhdr; + uint32_t data[NOTE_DATA_SZ / sizeof(uint32_t)]; + } note; + + int n, off, datasz; + bool have_prev_type; + uint32_t prev_type; + + /* Unless the arch requires properties, ignore them. */ + if (!ARCH_USE_GNU_PROPERTY) { + return true; + } + + /* If the properties are crazy large, that's too bad. */ + n = phdr->p_filesz; + if (n > sizeof(note)) { + error_setg(errp, "PT_GNU_PROPERTY too large"); + return false; + } + if (n < sizeof(note.nhdr)) { + error_setg(errp, "PT_GNU_PROPERTY too small"); + return false; + } + + if (phdr->p_offset + n <= BPRM_BUF_SIZE) { + memcpy(&note, bprm_buf + phdr->p_offset, n); + } else { + ssize_t len = pread(image_fd, &note, n, phdr->p_offset); + if (len != n) { + error_setg_errno(errp, errno, "Error reading file header"); + return false; + } + } + + /* + * The contents of a valid PT_GNU_PROPERTY is a sequence + * of uint32_t -- swap them all now. + */ +#ifdef BSWAP_NEEDED + for (int i = 0; i < n / 4; i++) { + bswap32s(note.data + i); + } +#endif + + /* + * Note that nhdr is 3 words, and that the "name" described by namesz + * immediately follows nhdr and is thus at the 4th word. Further, all + * of the inputs to the kernel's round_up are multiples of 4. + */ + if (note.nhdr.n_type != NT_GNU_PROPERTY_TYPE_0 || + note.nhdr.n_namesz != NOTE_NAME_SZ || + note.data[3] != GNU0_MAGIC) { + error_setg(errp, "Invalid note in PT_GNU_PROPERTY"); + return false; + } + off = sizeof(note.nhdr) + NOTE_NAME_SZ; + + datasz = note.nhdr.n_descsz + off; + if (datasz > n) { + error_setg(errp, "Invalid note size in PT_GNU_PROPERTY"); + return false; + } + + have_prev_type = false; + prev_type = 0; + while (1) { + if (off == datasz) { + return true; /* end, exit ok */ + } + if (!parse_elf_property(note.data, &off, datasz, info, + have_prev_type, &prev_type, errp)) { + return false; + } + have_prev_type = true; + } +} + /* Load an ELF image into the address space. IMAGE_NAME is the filename of the image, to use in error messages. @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, goto exit_errmsg; } *pinterp_name = g_steal_pointer(&interp_name); + } else if (eppnt->p_type == PT_GNU_PROPERTY) { + if (!parse_elf_properties(image_fd, info, eppnt, bprm_buf, &err)) { + goto exit_errmsg; + } } } -- 2.25.1 Use the new generic support for NT_GNU_PROPERTY_TYPE_0. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v11: Split out aarch64 bits from generic patch. --- linux-user/elfload.c | 48 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 46 insertions(+), 2 deletions(-) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static void elf_core_copy_regs(target_elf_gregset_t *regs, #include "elf.h" +/* We must delay the following stanzas until after "elf.h". */ +#if defined(TARGET_AARCH64) + +static bool arch_parse_elf_property(uint32_t pr_type, uint32_t pr_datasz, + const uint32_t *data, + struct image_info *info, + Error **errp) +{ + if (pr_type == GNU_PROPERTY_AARCH64_FEATURE_1_AND) { + if (pr_datasz != sizeof(uint32_t)) { + error_setg(errp, "Ill-formed GNU_PROPERTY_AARCH64_FEATURE_1_AND"); + return false; + } + /* We will extract GNU_PROPERTY_AARCH64_FEATURE_1_BTI later. */ + info->note_flags = *data; + } + return true; +} +#define ARCH_USE_GNU_PROPERTY 1 + +#else + static bool arch_parse_elf_property(uint32_t pr_type, uint32_t pr_datasz, const uint32_t *data, struct image_info *info, @@ -XXX,XX +XXX,XX @@ static bool arch_parse_elf_property(uint32_t pr_type, uint32_t pr_datasz, } #define ARCH_USE_GNU_PROPERTY 0 +#endif + struct exec { unsigned int a_info; /* Use macros N_MAGIC, etc for access */ @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, struct elfhdr *ehdr = (struct elfhdr *)bprm_buf; struct elf_phdr *phdr; abi_ulong load_addr, load_bias, loaddr, hiaddr, error; - int i, retval; + int i, retval, prot_exec; Error *err = NULL; /* First of all, some simple consistency checks */ @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, info->brk = 0; info->elf_flags = ehdr->e_flags; + prot_exec = PROT_EXEC; +#ifdef TARGET_AARCH64 + /* + * If the BTI feature is present, this indicates that the executable + * pages of the startup binary should be mapped with PROT_BTI, so that + * branch targets are enforced. + * + * The startup binary is either the interpreter or the static executable. + * The interpreter is responsible for all pages of a dynamic executable. + * + * Elf notes are backward compatible to older cpus. + * Do not enable BTI unless it is supported. + */ + if ((info->note_flags & GNU_PROPERTY_AARCH64_FEATURE_1_BTI) + && (pinterp_name == NULL || *pinterp_name == 0) + && cpu_isar_feature(aa64_bti, ARM_CPU(thread_cpu))) { + prot_exec |= TARGET_PROT_BTI; + } +#endif + for (i = 0; i < ehdr->e_phnum; i++) { struct elf_phdr *eppnt = phdr + i; if (eppnt->p_type == PT_LOAD) { @@ -XXX,XX +XXX,XX @@ static void load_elf_image(const char *image_name, int image_fd, elf_prot |= PROT_WRITE; } if (eppnt->p_flags & PF_X) { - elf_prot |= PROT_EXEC; + elf_prot |= prot_exec; } vaddr = load_bias + eppnt->p_vaddr; -- 2.25.1 The note test requires gcc 10 for -mbranch-protection=standard. The mmap test uses PROT_BTI and does not require special compiler support. Acked-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v9: Expect and require gcc 10. v11: Squash mmap smoke test. v12: Work around linker bug in bti-2. --- tests/tcg/aarch64/bti-1.c | 62 ++++++++++++++++ tests/tcg/aarch64/bti-2.c | 116 ++++++++++++++++++++++++++++++ tests/tcg/aarch64/bti-crt.inc.c | 51 +++++++++++++ tests/tcg/aarch64/Makefile.target | 10 +++ tests/tcg/configure.sh | 4 ++ 5 files changed, 243 insertions(+) create mode 100644 tests/tcg/aarch64/bti-1.c create mode 100644 tests/tcg/aarch64/bti-2.c create mode 100644 tests/tcg/aarch64/bti-crt.inc.c diff --git a/tests/tcg/aarch64/bti-1.c b/tests/tcg/aarch64/bti-1.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/tcg/aarch64/bti-1.c @@ -XXX,XX +XXX,XX @@ +/* + * Branch target identification, basic notskip cases. + */ + +#include "bti-crt.inc.c" + +static void skip2_sigill(int sig, siginfo_t *info, ucontext_t *uc) +{ + uc->uc_mcontext.pc += 8; + uc->uc_mcontext.pstate = 1; +} + +#define NOP "nop" +#define BTI_N "hint #32" +#define BTI_C "hint #34" +#define BTI_J "hint #36" +#define BTI_JC "hint #38" + +#define BTYPE_1(DEST) \ + asm("mov %0,#1; adr x16, 1f; br x16; 1: " DEST "; mov %0,#0" \ + : "=r"(skipped) : : "x16") + +#define BTYPE_2(DEST) \ + asm("mov %0,#1; adr x16, 1f; blr x16; 1: " DEST "; mov %0,#0" \ + : "=r"(skipped) : : "x16", "x30") + +#define BTYPE_3(DEST) \ + asm("mov %0,#1; adr x15, 1f; br x15; 1: " DEST "; mov %0,#0" \ + : "=r"(skipped) : : "x15") + +#define TEST(WHICH, DEST, EXPECT) \ + do { WHICH(DEST); fail += skipped ^ EXPECT; } while (0) + + +int main() +{ + int fail = 0; + int skipped; + + /* Signal-like with SA_SIGINFO. */ + signal_info(SIGILL, skip2_sigill); + + TEST(BTYPE_1, NOP, 1); + TEST(BTYPE_1, BTI_N, 1); + TEST(BTYPE_1, BTI_C, 0); + TEST(BTYPE_1, BTI_J, 0); + TEST(BTYPE_1, BTI_JC, 0); + + TEST(BTYPE_2, NOP, 1); + TEST(BTYPE_2, BTI_N, 1); + TEST(BTYPE_2, BTI_C, 0); + TEST(BTYPE_2, BTI_J, 1); + TEST(BTYPE_2, BTI_JC, 0); + + TEST(BTYPE_3, NOP, 1); + TEST(BTYPE_3, BTI_N, 1); + TEST(BTYPE_3, BTI_C, 1); + TEST(BTYPE_3, BTI_J, 0); + TEST(BTYPE_3, BTI_JC, 0); + + return fail; +} diff --git a/tests/tcg/aarch64/bti-2.c b/tests/tcg/aarch64/bti-2.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/tcg/aarch64/bti-2.c @@ -XXX,XX +XXX,XX @@ +/* + * Branch target identification, basic notskip cases. + */ + +#include <stdio.h> +#include <signal.h> +#include <string.h> +#include <unistd.h> +#include <sys/mman.h> + +#ifndef PROT_BTI +#define PROT_BTI 0x10 +#endif + +static void skip2_sigill(int sig, siginfo_t *info, void *vuc) +{ + ucontext_t *uc = vuc; + uc->uc_mcontext.pc += 8; + uc->uc_mcontext.pstate = 1; +} + +#define NOP "nop" +#define BTI_N "hint #32" +#define BTI_C "hint #34" +#define BTI_J "hint #36" +#define BTI_JC "hint #38" + +#define BTYPE_1(DEST) \ + "mov x1, #1\n\t" \ + "adr x16, 1f\n\t" \ + "br x16\n" \ +"1: " DEST "\n\t" \ + "mov x1, #0" + +#define BTYPE_2(DEST) \ + "mov x1, #1\n\t" \ + "adr x16, 1f\n\t" \ + "blr x16\n" \ +"1: " DEST "\n\t" \ + "mov x1, #0" + +#define BTYPE_3(DEST) \ + "mov x1, #1\n\t" \ + "adr x15, 1f\n\t" \ + "br x15\n" \ +"1: " DEST "\n\t" \ + "mov x1, #0" + +#define TEST(WHICH, DEST, EXPECT) \ + WHICH(DEST) "\n" \ + ".if " #EXPECT "\n\t" \ + "eor x1, x1," #EXPECT "\n" \ + ".endif\n\t" \ + "add x0, x0, x1\n\t" + +asm("\n" +"test_begin:\n\t" + BTI_C "\n\t" + "mov x2, x30\n\t" + "mov x0, #0\n\t" + + TEST(BTYPE_1, NOP, 1) + TEST(BTYPE_1, BTI_N, 1) + TEST(BTYPE_1, BTI_C, 0) + TEST(BTYPE_1, BTI_J, 0) + TEST(BTYPE_1, BTI_JC, 0) + + TEST(BTYPE_2, NOP, 1) + TEST(BTYPE_2, BTI_N, 1) + TEST(BTYPE_2, BTI_C, 0) + TEST(BTYPE_2, BTI_J, 1) + TEST(BTYPE_2, BTI_JC, 0) + + TEST(BTYPE_3, NOP, 1) + TEST(BTYPE_3, BTI_N, 1) + TEST(BTYPE_3, BTI_C, 1) + TEST(BTYPE_3, BTI_J, 0) + TEST(BTYPE_3, BTI_JC, 0) + + "ret x2\n" +"test_end:" +); + +int main() +{ + struct sigaction sa; + void *tb, *te; + + void *p = mmap(0, getpagesize(), + PROT_EXEC | PROT_READ | PROT_WRITE | PROT_BTI, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (p == MAP_FAILED) { + perror("mmap"); + return 1; + } + + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = skip2_sigill; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGILL, &sa, NULL) < 0) { + perror("sigaction"); + return 1; + } + + /* + * ??? With "extern char test_begin[]", some compiler versions + * will use :got references, and some linker versions will + * resolve this reference to a static symbol incorrectly. + * Bypass this error by using a pc-relative reference directly. + */ + asm("adr %0, test_begin; adr %1, test_end" : "=r"(tb), "=r"(te)); + + memcpy(p, tb, te - tb); + + return ((int (*)(void))p)(); +} diff --git a/tests/tcg/aarch64/bti-crt.inc.c b/tests/tcg/aarch64/bti-crt.inc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/tcg/aarch64/bti-crt.inc.c @@ -XXX,XX +XXX,XX @@ +/* + * Minimal user-environment for testing BTI. + * + * Normal libc is not (yet) built with BTI support enabled, + * and so could generate a BTI TRAP before ever reaching main. + */ + +#include <stdlib.h> +#include <signal.h> +#include <ucontext.h> +#include <asm/unistd.h> + +int main(void); + +void _start(void) +{ + exit(main()); +} + +void exit(int ret) +{ + register int x0 __asm__("x0") = ret; + register int x8 __asm__("x8") = __NR_exit; + + asm volatile("svc #0" : : "r"(x0), "r"(x8)); + __builtin_unreachable(); +} + +/* + * Irritatingly, the user API struct sigaction does not match the + * kernel API struct sigaction. So for simplicity, isolate the + * kernel ABI here, and make this act like signal. + */ +void signal_info(int sig, void (*fn)(int, siginfo_t *, ucontext_t *)) +{ + struct kernel_sigaction { + void (*handler)(int, siginfo_t *, ucontext_t *); + unsigned long flags; + unsigned long restorer; + unsigned long mask; + } sa = { fn, SA_SIGINFO, 0, 0 }; + + register int x0 __asm__("x0") = sig; + register void *x1 __asm__("x1") = &sa; + register void *x2 __asm__("x2") = 0; + register int x3 __asm__("x3") = sizeof(unsigned long); + register int x8 __asm__("x8") = __NR_rt_sigaction; + + asm volatile("svc #0" + : : "r"(x0), "r"(x1), "r"(x2), "r"(x3), "r"(x8) : "memory"); +} diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -XXX,XX +XXX,XX @@ run-pauth-%: QEMU_OPTS += -cpu max run-plugin-pauth-%: QEMU_OPTS += -cpu max endif +# BTI Tests +# bti-1 tests the elf notes, so we require special compiler support. +ifneq ($(DOCKER_IMAGE)$(CROSS_CC_HAS_ARMV8_BTI),) +AARCH64_TESTS += bti-1 +bti-1: CFLAGS += -mbranch-protection=standard +bti-1: LDFLAGS += -nostdlib +endif +# bti-2 tests PROT_BTI, so no special compiler support required. +AARCH64_TESTS += bti-2 + # Semihosting smoke test for linux-user AARCH64_TESTS += semihosting run-semihosting: semihosting diff --git a/tests/tcg/configure.sh b/tests/tcg/configure.sh index XXXXXXX..XXXXXXX 100755 --- a/tests/tcg/configure.sh +++ b/tests/tcg/configure.sh @@ -XXX,XX +XXX,XX @@ for target in $target_list; do -march=armv8.3-a -o $TMPE $TMPC; then echo "CROSS_CC_HAS_ARMV8_3=y" >> $config_target_mak fi + if do_compiler "$target_compiler" $target_compiler_cflags \ + -mbranch-protection=standard -o $TMPE $TMPC; then + echo "CROSS_CC_HAS_ARMV8_BTI=y" >> $config_target_mak + fi ;; esac -- 2.25.1