From db751e309ff05461a0c8e114b1238d7a69cc1f18 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:43 +0000 Subject: [PATCH 01/15] ELF: UAPI and Kconfig additions for ELF program properties Pull the basic ELF definitions relating to the NT_GNU_PROPERTY_TYPE_0 note from Yu-Cheng Yu's earlier x86 shstk series. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Signed-off-by: Yu-cheng Yu Reviewed-by: Catalin Marinas Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- fs/Kconfig.binfmt | 3 +++ include/linux/elf.h | 12 ++++++++++++ include/uapi/linux/elf.h | 1 + 3 files changed, 16 insertions(+) diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 62dc4f577ba1..d2cfe0729a73 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -36,6 +36,9 @@ config COMPAT_BINFMT_ELF config ARCH_BINFMT_ELF_STATE bool +config ARCH_USE_GNU_PROPERTY + bool + config BINFMT_ELF_FDPIC bool "Kernel support for FDPIC ELF binaries" default y if !BINFMT_ELF diff --git a/include/linux/elf.h b/include/linux/elf.h index e3649b3e970e..f7b24c5fcfb6 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -2,6 +2,7 @@ #ifndef _LINUX_ELF_H #define _LINUX_ELF_H +#include #include #include @@ -56,4 +57,15 @@ static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) { extern int elf_coredump_extra_notes_size(void); extern int elf_coredump_extra_notes_write(struct coredump_params *cprm); #endif + +/* + * NT_GNU_PROPERTY_TYPE_0 header: + * Keep this internal until/unless there is an agreed UAPI definition. + * pr_type values (GNU_PROPERTY_*) are public and defined in the UAPI header. + */ +struct gnu_property { + u32 pr_type; + u32 pr_datasz; +}; + #endif /* _LINUX_ELF_H */ diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 34c02e4290fe..c37731407074 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -36,6 +36,7 @@ typedef __s64 Elf64_Sxword; #define PT_LOPROC 0x70000000 #define PT_HIPROC 0x7fffffff #define PT_GNU_EH_FRAME 0x6474e550 +#define PT_GNU_PROPERTY 0x6474e553 #define PT_GNU_STACK (PT_LOOS + 0x474e551) From 00e19ceec80b03a43f626f891fcc53e57919f1b3 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:44 +0000 Subject: [PATCH 02/15] ELF: Add ELF program property parsing support ELF program properties will be needed for detecting whether to enable optional architecture or ABI features for a new ELF process. For now, there are no generic properties that we care about, so do nothing unless CONFIG_ARCH_USE_GNU_PROPERTY=y. Otherwise, the presence of properties using the PT_PROGRAM_PROPERTY phdrs entry (if any), and notify each property to the arch code. For now, the added code is not used. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- fs/binfmt_elf.c | 127 +++++++++++++++++++++++++++++++++++++++ fs/compat_binfmt_elf.c | 4 ++ include/linux/elf.h | 19 ++++++ include/uapi/linux/elf.h | 4 ++ 4 files changed, 154 insertions(+) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index f4713ea76e82..1fb67e506b68 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -39,12 +39,18 @@ #include #include #include +#include +#include #include #include #include #include #include +#ifndef ELF_COMPAT +#define ELF_COMPAT 0 +#endif + #ifndef user_long_t #define user_long_t long #endif @@ -681,6 +687,111 @@ out: * libraries. There is no binary dependent code anywhere else. */ +static int parse_elf_property(const char *data, size_t *off, size_t datasz, + struct arch_elf_state *arch, + bool have_prev_type, u32 *prev_type) +{ + size_t o, step; + const struct gnu_property *pr; + int ret; + + if (*off == datasz) + return -ENOENT; + + if (WARN_ON_ONCE(*off > datasz || *off % ELF_GNU_PROPERTY_ALIGN)) + return -EIO; + o = *off; + datasz -= *off; + + if (datasz < sizeof(*pr)) + return -ENOEXEC; + pr = (const struct gnu_property *)(data + o); + o += sizeof(*pr); + datasz -= sizeof(*pr); + + if (pr->pr_datasz > datasz) + return -ENOEXEC; + + WARN_ON_ONCE(o % ELF_GNU_PROPERTY_ALIGN); + step = round_up(pr->pr_datasz, ELF_GNU_PROPERTY_ALIGN); + if (step > datasz) + return -ENOEXEC; + + /* Properties are supposed to be unique and sorted on pr_type: */ + if (have_prev_type && pr->pr_type <= *prev_type) + return -ENOEXEC; + *prev_type = pr->pr_type; + + ret = arch_parse_elf_property(pr->pr_type, data + o, + pr->pr_datasz, ELF_COMPAT, arch); + if (ret) + return ret; + + *off = o + step; + return 0; +} + +#define NOTE_DATA_SZ SZ_1K +#define GNU_PROPERTY_TYPE_0_NAME "GNU" +#define NOTE_NAME_SZ (sizeof(GNU_PROPERTY_TYPE_0_NAME)) + +static int parse_elf_properties(struct file *f, const struct elf_phdr *phdr, + struct arch_elf_state *arch) +{ + union { + struct elf_note nhdr; + char data[NOTE_DATA_SZ]; + } note; + loff_t pos; + ssize_t n; + size_t off, datasz; + int ret; + bool have_prev_type; + u32 prev_type; + + if (!IS_ENABLED(CONFIG_ARCH_USE_GNU_PROPERTY) || !phdr) + return 0; + + /* load_elf_binary() shouldn't call us unless this is true... */ + if (WARN_ON_ONCE(phdr->p_type != PT_GNU_PROPERTY)) + return -ENOEXEC; + + /* If the properties are crazy large, that's too bad (for now): */ + if (phdr->p_filesz > sizeof(note)) + return -ENOEXEC; + + pos = phdr->p_offset; + n = kernel_read(f, ¬e, phdr->p_filesz, &pos); + + BUILD_BUG_ON(sizeof(note) < sizeof(note.nhdr) + NOTE_NAME_SZ); + if (n < 0 || n < sizeof(note.nhdr) + NOTE_NAME_SZ) + return -EIO; + + if (note.nhdr.n_type != NT_GNU_PROPERTY_TYPE_0 || + note.nhdr.n_namesz != NOTE_NAME_SZ || + strncmp(note.data + sizeof(note.nhdr), + GNU_PROPERTY_TYPE_0_NAME, n - sizeof(note.nhdr))) + return -ENOEXEC; + + off = round_up(sizeof(note.nhdr) + NOTE_NAME_SZ, + ELF_GNU_PROPERTY_ALIGN); + if (off > n) + return -ENOEXEC; + + if (note.nhdr.n_descsz > n - off) + return -ENOEXEC; + datasz = off + note.nhdr.n_descsz; + + have_prev_type = false; + do { + ret = parse_elf_property(note.data, &off, datasz, arch, + have_prev_type, &prev_type); + have_prev_type = true; + } while (!ret); + + return ret == -ENOENT ? 0 : ret; +} + static int load_elf_binary(struct linux_binprm *bprm) { struct file *interpreter = NULL; /* to shut gcc up */ @@ -688,6 +799,7 @@ static int load_elf_binary(struct linux_binprm *bprm) int load_addr_set = 0; unsigned long error; struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL; + struct elf_phdr *elf_property_phdata = NULL; unsigned long elf_bss, elf_brk; int bss_prot = 0; int retval, i; @@ -733,6 +845,11 @@ static int load_elf_binary(struct linux_binprm *bprm) for (i = 0; i < elf_ex->e_phnum; i++, elf_ppnt++) { char *elf_interpreter; + if (elf_ppnt->p_type == PT_GNU_PROPERTY) { + elf_property_phdata = elf_ppnt; + continue; + } + if (elf_ppnt->p_type != PT_INTERP) continue; @@ -820,9 +937,14 @@ out_free_interp: goto out_free_dentry; /* Pass PT_LOPROC..PT_HIPROC headers to arch code */ + elf_property_phdata = NULL; elf_ppnt = interp_elf_phdata; for (i = 0; i < loc->interp_elf_ex.e_phnum; i++, elf_ppnt++) switch (elf_ppnt->p_type) { + case PT_GNU_PROPERTY: + elf_property_phdata = elf_ppnt; + break; + case PT_LOPROC ... PT_HIPROC: retval = arch_elf_pt_proc(&loc->interp_elf_ex, elf_ppnt, interpreter, @@ -833,6 +955,11 @@ out_free_interp: } } + retval = parse_elf_properties(interpreter ?: bprm->file, + elf_property_phdata, &arch_state); + if (retval) + goto out_free_dentry; + /* * Allow arch code to reject the ELF at this point, whilst it's * still possible to return an error to the code that invoked diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index aaad4ca1217e..13a087bc816b 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -17,6 +17,8 @@ #include #include +#define ELF_COMPAT 1 + /* * Rename the basic ELF layout types to refer to the 32-bit class of files. */ @@ -28,11 +30,13 @@ #undef elf_shdr #undef elf_note #undef elf_addr_t +#undef ELF_GNU_PROPERTY_ALIGN #define elfhdr elf32_hdr #define elf_phdr elf32_phdr #define elf_shdr elf32_shdr #define elf_note elf32_note #define elf_addr_t Elf32_Addr +#define ELF_GNU_PROPERTY_ALIGN ELF32_GNU_PROPERTY_ALIGN /* * Some data types as stored in coredump. diff --git a/include/linux/elf.h b/include/linux/elf.h index f7b24c5fcfb6..db5113479f5e 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -22,6 +22,9 @@ SET_PERSONALITY(ex) #endif +#define ELF32_GNU_PROPERTY_ALIGN 4 +#define ELF64_GNU_PROPERTY_ALIGN 8 + #if ELF_CLASS == ELFCLASS32 extern Elf32_Dyn _DYNAMIC []; @@ -32,6 +35,7 @@ extern Elf32_Dyn _DYNAMIC []; #define elf_addr_t Elf32_Off #define Elf_Half Elf32_Half #define Elf_Word Elf32_Word +#define ELF_GNU_PROPERTY_ALIGN ELF32_GNU_PROPERTY_ALIGN #else @@ -43,6 +47,7 @@ extern Elf64_Dyn _DYNAMIC []; #define elf_addr_t Elf64_Off #define Elf_Half Elf64_Half #define Elf_Word Elf64_Word +#define ELF_GNU_PROPERTY_ALIGN ELF64_GNU_PROPERTY_ALIGN #endif @@ -68,4 +73,18 @@ struct gnu_property { u32 pr_datasz; }; +struct arch_elf_state; + +#ifndef CONFIG_ARCH_USE_GNU_PROPERTY +static inline int arch_parse_elf_property(u32 type, const void *data, + size_t datasz, bool compat, + struct arch_elf_state *arch) +{ + return 0; +} +#else +extern int arch_parse_elf_property(u32 type, const void *data, size_t datasz, + bool compat, struct arch_elf_state *arch); +#endif + #endif /* _LINUX_ELF_H */ diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index c37731407074..20900f4496b7 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -368,6 +368,7 @@ typedef struct elf64_shdr { * Notes used in ET_CORE. Architectures export some of the arch register sets * using the corresponding note types via the PTRACE_GETREGSET and * PTRACE_SETREGSET requests. + * The note name for all these is "LINUX". */ #define NT_PRSTATUS 1 #define NT_PRFPREG 2 @@ -430,6 +431,9 @@ typedef struct elf64_shdr { #define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */ #define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */ +/* Note types with note name "GNU" */ +#define NT_GNU_PROPERTY_TYPE_0 5 + /* Note header in a PT_NOTE section */ typedef struct elf32_note { Elf32_Word n_namesz; /* Name size */ From 8ef8f360cf30be12382f89ff48a57fbbd9b31c14 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:45 +0000 Subject: [PATCH 03/15] arm64: Basic Branch Target Identification support This patch adds the bare minimum required to expose the ARMv8.5 Branch Target Identification feature to userspace. By itself, this does _not_ automatically enable BTI for any initial executable pages mapped by execve(). This will come later, but for now it should be possible to enable BTI manually on those pages by using mprotect() from within the target process. Other arches already using the generic mman.h are already using 0x10 for arch-specific prot flags, so we use that for PROT_BTI here. For consistency, signal handler entry points in BTI guarded pages are required to be annotated as such, just like any other function. This blocks a relatively minor attack vector, but comforming userspace will have the annotations anyway, so we may as well enforce them. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Catalin Marinas Signed-off-by: Catalin Marinas --- Documentation/arm64/cpu-feature-registers.rst | 2 + Documentation/arm64/elf_hwcaps.rst | 5 +++ arch/arm64/include/asm/cpucaps.h | 3 +- arch/arm64/include/asm/cpufeature.h | 6 +++ arch/arm64/include/asm/esr.h | 2 +- arch/arm64/include/asm/exception.h | 1 + arch/arm64/include/asm/hwcap.h | 1 + arch/arm64/include/asm/mman.h | 37 +++++++++++++++++++ arch/arm64/include/asm/pgtable-hwdef.h | 1 + arch/arm64/include/asm/pgtable.h | 2 +- arch/arm64/include/asm/ptrace.h | 1 + arch/arm64/include/asm/sysreg.h | 4 ++ arch/arm64/include/uapi/asm/hwcap.h | 1 + arch/arm64/include/uapi/asm/mman.h | 9 +++++ arch/arm64/include/uapi/asm/ptrace.h | 9 +++++ arch/arm64/kernel/cpufeature.c | 33 +++++++++++++++++ arch/arm64/kernel/cpuinfo.c | 1 + arch/arm64/kernel/entry-common.c | 11 ++++++ arch/arm64/kernel/ptrace.c | 2 +- arch/arm64/kernel/signal.c | 16 ++++++++ arch/arm64/kernel/syscall.c | 18 +++++++++ arch/arm64/kernel/traps.c | 8 ++++ include/linux/mm.h | 3 ++ 23 files changed, 172 insertions(+), 4 deletions(-) create mode 100644 arch/arm64/include/asm/mman.h create mode 100644 arch/arm64/include/uapi/asm/mman.h diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst index 41937a8091aa..314fa5bc2655 100644 --- a/Documentation/arm64/cpu-feature-registers.rst +++ b/Documentation/arm64/cpu-feature-registers.rst @@ -176,6 +176,8 @@ infrastructure: +------------------------------+---------+---------+ | SSBS | [7-4] | y | +------------------------------+---------+---------+ + | BT | [3-0] | y | + +------------------------------+---------+---------+ 4) MIDR_EL1 - Main ID Register diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst index 7dfb97dfe416..84a9fd2d41b4 100644 --- a/Documentation/arm64/elf_hwcaps.rst +++ b/Documentation/arm64/elf_hwcaps.rst @@ -236,6 +236,11 @@ HWCAP2_RNG Functionality implied by ID_AA64ISAR0_EL1.RNDR == 0b0001. +HWCAP2_BTI + + Functionality implied by ID_AA64PFR0_EL1.BT == 0b0001. + + 4. Unused AT_HWCAP bits ----------------------- diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index 865e0253fc1e..58e776c22aab 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -58,7 +58,8 @@ #define ARM64_WORKAROUND_SPECULATIVE_AT_NVHE 48 #define ARM64_HAS_E0PD 49 #define ARM64_HAS_RNG 50 +#define ARM64_BTI 51 -#define ARM64_NCAPS 51 +#define ARM64_NCAPS 52 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 92ef9539874a..e3ebcc59e83b 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -613,6 +613,12 @@ static inline bool system_has_prio_mask_debugging(void) system_uses_irq_prio_masking(); } +static inline bool system_supports_bti(void) +{ + return IS_ENABLED(CONFIG_ARM64_BTI) && + cpus_have_const_cap(ARM64_BTI); +} + static inline bool system_capabilities_finalized(void) { return static_branch_likely(&arm64_const_caps_ready); diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index cb29253ae86b..390b8ba67830 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -22,7 +22,7 @@ #define ESR_ELx_EC_PAC (0x09) /* EL2 and above */ /* Unallocated EC: 0x0A - 0x0B */ #define ESR_ELx_EC_CP14_64 (0x0C) -/* Unallocated EC: 0x0d */ +#define ESR_ELx_EC_BTI (0x0D) #define ESR_ELx_EC_ILL (0x0E) /* Unallocated EC: 0x0F - 0x10 */ #define ESR_ELx_EC_SVC32 (0x11) diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 7a6e81ca23a8..7577a754d443 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -34,6 +34,7 @@ static inline u32 disr_to_esr(u64 disr) asmlinkage void enter_from_user_mode(void); void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); +void do_bti(struct pt_regs *regs); asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr); void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, struct pt_regs *regs); diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 0f00265248b5..d683bcbf1e7c 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -94,6 +94,7 @@ #define KERNEL_HWCAP_BF16 __khwcap2_feature(BF16) #define KERNEL_HWCAP_DGH __khwcap2_feature(DGH) #define KERNEL_HWCAP_RNG __khwcap2_feature(RNG) +#define KERNEL_HWCAP_BTI __khwcap2_feature(BTI) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h new file mode 100644 index 000000000000..081ec8de9ea6 --- /dev/null +++ b/arch/arm64/include/asm/mman.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMAN_H__ +#define __ASM_MMAN_H__ + +#include +#include +#include + +static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, + unsigned long pkey __always_unused) +{ + if (system_supports_bti() && (prot & PROT_BTI)) + return VM_ARM64_BTI; + + return 0; +} +#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) + +static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags) +{ + return (vm_flags & VM_ARM64_BTI) ? __pgprot(PTE_GP) : __pgprot(0); +} +#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags) + +static inline bool arch_validate_prot(unsigned long prot, + unsigned long addr __always_unused) +{ + unsigned long supported = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM; + + if (system_supports_bti()) + supported |= PROT_BTI; + + return (prot & ~supported) == 0; +} +#define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr) + +#endif /* ! __ASM_MMAN_H__ */ diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 6bf5e650da78..167f1d1d48aa 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -151,6 +151,7 @@ #define PTE_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */ #define PTE_AF (_AT(pteval_t, 1) << 10) /* Access Flag */ #define PTE_NG (_AT(pteval_t, 1) << 11) /* nG */ +#define PTE_GP (_AT(pteval_t, 1) << 50) /* BTI guarded */ #define PTE_DBM (_AT(pteval_t, 1) << 51) /* Dirty Bit Management */ #define PTE_CONT (_AT(pteval_t, 1) << 52) /* Contiguous range */ #define PTE_PXN (_AT(pteval_t, 1) << 53) /* Privileged XN */ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 538c85e62f86..4fbf516d8cb2 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -660,7 +660,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | - PTE_PROT_NONE | PTE_VALID | PTE_WRITE; + PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP; /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) pte = pte_mkdirty(pte); diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index bf57308fcd63..2172ec7594ba 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -35,6 +35,7 @@ #define GIC_PRIO_PSR_I_SET (1 << 4) /* Additional SPSR bits not exposed in the UABI */ + #define PSR_IL_BIT (1 << 20) /* AArch32-specific ptrace requests */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index b91570ff9db1..db08ceb4cc9a 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -514,6 +514,8 @@ #endif /* SCTLR_EL1 specific flags. */ +#define SCTLR_EL1_BT1 (BIT(36)) +#define SCTLR_EL1_BT0 (BIT(35)) #define SCTLR_EL1_UCI (BIT(26)) #define SCTLR_EL1_E0E (BIT(24)) #define SCTLR_EL1_SPAN (BIT(23)) @@ -620,10 +622,12 @@ /* id_aa64pfr1 */ #define ID_AA64PFR1_SSBS_SHIFT 4 +#define ID_AA64PFR1_BT_SHIFT 0 #define ID_AA64PFR1_SSBS_PSTATE_NI 0 #define ID_AA64PFR1_SSBS_PSTATE_ONLY 1 #define ID_AA64PFR1_SSBS_PSTATE_INSNS 2 +#define ID_AA64PFR1_BT_BTI 0x1 /* id_aa64zfr0 */ #define ID_AA64ZFR0_F64MM_SHIFT 56 diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 7752d93bb50f..2d6ba1c2592e 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -73,5 +73,6 @@ #define HWCAP2_BF16 (1 << 14) #define HWCAP2_DGH (1 << 15) #define HWCAP2_RNG (1 << 16) +#define HWCAP2_BTI (1 << 17) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/mman.h b/arch/arm64/include/uapi/asm/mman.h new file mode 100644 index 000000000000..6fdd71eb644f --- /dev/null +++ b/arch/arm64/include/uapi/asm/mman.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__ASM_MMAN_H +#define _UAPI__ASM_MMAN_H + +#include + +#define PROT_BTI 0x10 /* BTI guarded page */ + +#endif /* ! _UAPI__ASM_MMAN_H */ diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index d1bb5b69f1ce..42cbe34d95ce 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -46,6 +46,7 @@ #define PSR_I_BIT 0x00000080 #define PSR_A_BIT 0x00000100 #define PSR_D_BIT 0x00000200 +#define PSR_BTYPE_MASK 0x00000c00 #define PSR_SSBS_BIT 0x00001000 #define PSR_PAN_BIT 0x00400000 #define PSR_UAO_BIT 0x00800000 @@ -55,6 +56,8 @@ #define PSR_Z_BIT 0x40000000 #define PSR_N_BIT 0x80000000 +#define PSR_BTYPE_SHIFT 10 + /* * Groups of PSR bits */ @@ -63,6 +66,12 @@ #define PSR_x 0x0000ff00 /* Extension */ #define PSR_c 0x000000ff /* Control */ +/* Convenience names for the values of PSTATE.BTYPE */ +#define PSR_BTYPE_NONE (0b00 << PSR_BTYPE_SHIFT) +#define PSR_BTYPE_JC (0b01 << PSR_BTYPE_SHIFT) +#define PSR_BTYPE_C (0b10 << PSR_BTYPE_SHIFT) +#define PSR_BTYPE_J (0b11 << PSR_BTYPE_SHIFT) + /* syscall emulation path in ptrace */ #define PTRACE_SYSEMU 31 #define PTRACE_SYSEMU_SINGLESTEP 32 diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0b6715625cf6..e6d31776e49b 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -179,6 +179,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_BTI), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_BT_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -1347,6 +1349,21 @@ static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry, } #endif +#ifdef CONFIG_ARM64_BTI +static void bti_enable(const struct arm64_cpu_capabilities *__unused) +{ + /* + * Use of X16/X17 for tail-calls and trampolines that jump to + * function entry points using BR is a requirement for + * marking binaries with GNU_PROPERTY_AARCH64_FEATURE_1_BTI. + * So, be strict and forbid other BRs using other registers to + * jump onto a PACIxSP instruction: + */ + sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_BT0 | SCTLR_EL1_BT1); + isb(); +} +#endif /* CONFIG_ARM64_BTI */ + static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "GIC system register CPU interface", @@ -1671,6 +1688,19 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sign = FTR_UNSIGNED, .min_field_value = 1, }, +#endif +#ifdef CONFIG_ARM64_BTI + { + .desc = "Branch Target Identification", + .capability = ARM64_BTI, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_cpuid_feature, + .cpu_enable = bti_enable, + .sys_reg = SYS_ID_AA64PFR1_EL1, + .field_pos = ID_AA64PFR1_BT_SHIFT, + .min_field_value = ID_AA64PFR1_BT_BTI, + .sign = FTR_UNSIGNED, + }, #endif {}, }; @@ -1781,6 +1811,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F64MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_F64MM, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), #endif HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS), +#ifdef CONFIG_ARM64_BTI + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_BT_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_BT_BTI, CAP_HWCAP, KERNEL_HWCAP_BTI), +#endif #ifdef CONFIG_ARM64_PTR_AUTH HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA), HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG), diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 86136075ae41..5e47e93b5dc1 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -92,6 +92,7 @@ static const char *const hwcap_str[] = { "bf16", "dgh", "rng", + "bti", NULL }; diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index fde59981445c..55ec0627f5a7 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -188,6 +188,14 @@ static void notrace el0_undef(struct pt_regs *regs) } NOKPROBE_SYMBOL(el0_undef); +static void notrace el0_bti(struct pt_regs *regs) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_bti(regs); +} +NOKPROBE_SYMBOL(el0_bti); + static void notrace el0_inv(struct pt_regs *regs, unsigned long esr) { user_exit_irqoff(); @@ -255,6 +263,9 @@ asmlinkage void notrace el0_sync_handler(struct pt_regs *regs) case ESR_ELx_EC_UNKNOWN: el0_undef(regs); break; + case ESR_ELx_EC_BTI: + el0_bti(regs); + break; case ESR_ELx_EC_BREAKPT_LOW: case ESR_ELx_EC_SOFTSTP_LOW: case ESR_ELx_EC_WATCHPT_LOW: diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index cd6e5fa48b9c..fd8ac7cf68e7 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1874,7 +1874,7 @@ void syscall_trace_exit(struct pt_regs *regs) */ #define SPSR_EL1_AARCH64_RES0_BITS \ (GENMASK_ULL(63, 32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \ - GENMASK_ULL(20, 13) | GENMASK_ULL(11, 10) | GENMASK_ULL(5, 5)) + GENMASK_ULL(20, 13) | GENMASK_ULL(5, 5)) #define SPSR_EL1_AARCH32_RES0_BITS \ (GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20)) diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 339882db5a91..801d56cdf701 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -732,6 +732,22 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, regs->regs[29] = (unsigned long)&user->next_frame->fp; regs->pc = (unsigned long)ka->sa.sa_handler; + /* + * Signal delivery is a (wacky) indirect function call in + * userspace, so simulate the same setting of BTYPE as a BLR + * . + * Signal delivery to a location in a PROT_BTI guarded page + * that is not a function entry point will now trigger a + * SIGILL in userspace. + * + * If the signal handler entry point is not in a PROT_BTI + * guarded page, this is harmless. + */ + if (system_supports_bti()) { + regs->pstate &= ~PSR_BTYPE_MASK; + regs->pstate |= PSR_BTYPE_C; + } + if (ka->sa.sa_flags & SA_RESTORER) sigtramp = ka->sa.sa_restorer; else diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index a12c0c88d345..5f5b868292f5 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -98,6 +98,24 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, regs->orig_x0 = regs->regs[0]; regs->syscallno = scno; + /* + * BTI note: + * The architecture does not guarantee that SPSR.BTYPE is zero + * on taking an SVC, so we could return to userspace with a + * non-zero BTYPE after the syscall. + * + * This shouldn't matter except when userspace is explicitly + * doing something stupid, such as setting PROT_BTI on a page + * that lacks conforming BTI/PACIxSP instructions, falling + * through from one executable page to another with differing + * PROT_BTI, or messing with BTYPE via ptrace: in such cases, + * userspace should not be surprised if a SIGILL occurs on + * syscall return. + * + * So, don't touch regs->pstate & PSR_BTYPE_MASK here. + * (Similarly for HVC and SMC elsewhere.) + */ + cortex_a76_erratum_1463225_svc_handler(); local_daif_restore(DAIF_PROCCTX); user_exit(); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index cf402be5c573..b8c714dda851 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -411,6 +411,13 @@ void do_undefinstr(struct pt_regs *regs) } NOKPROBE_SYMBOL(do_undefinstr); +void do_bti(struct pt_regs *regs) +{ + BUG_ON(!user_mode(regs)); + force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc); +} +NOKPROBE_SYMBOL(do_bti); + #define __user_cache_maint(insn, address, res) \ if (address >= user_addr_max()) { \ res = -EFAULT; \ @@ -753,6 +760,7 @@ static const char *esr_class_str[] = { [ESR_ELx_EC_CP10_ID] = "CP10 MRC/VMRS", [ESR_ELx_EC_PAC] = "PAC", [ESR_ELx_EC_CP14_64] = "CP14 MCRR/MRRC", + [ESR_ELx_EC_BTI] = "BTI", [ESR_ELx_EC_ILL] = "PSTATE.IL", [ESR_ELx_EC_SVC32] = "SVC (AArch32)", [ESR_ELx_EC_HVC32] = "HVC (AArch32)", diff --git a/include/linux/mm.h b/include/linux/mm.h index 52269e56c514..9e5fce1b2099 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -324,6 +324,9 @@ extern unsigned int kobjsize(const void *objp); #elif defined(CONFIG_SPARC64) # define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ # define VM_ARCH_CLEAR VM_SPARC_ADI +#elif defined(CONFIG_ARM64) +# define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */ +# define VM_ARCH_CLEAR VM_ARM64_BTI #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif From fe0f67660ee9c99408be5261ae045f8b41953b05 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:46 +0000 Subject: [PATCH 04/15] elf: Allow arch to tweak initial mmap prot flags An arch may want to tweak the mmap prot flags for an ELFexecutable's initial mappings. For example, arm64 is going to need to add PROT_BTI for executable pages in an ELF process whose executable is marked as using Branch Target Identification (an ARMv8.5-A control flow integrity feature). So that this can be done in a generic way, add a hook arch_elf_adjust_prot() to modify the prot flags as desired: arches can select CONFIG_HAVE_ELF_PROT and implement their own backend where necessary. By default, leave the prot flags unchanged. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Catalin Marinas Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- fs/Kconfig.binfmt | 3 +++ fs/binfmt_elf.c | 18 ++++++++++++------ include/linux/elf.h | 12 ++++++++++++ 3 files changed, 27 insertions(+), 6 deletions(-) diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index d2cfe0729a73..2358368319b8 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -36,6 +36,9 @@ config COMPAT_BINFMT_ELF config ARCH_BINFMT_ELF_STATE bool +config ARCH_HAVE_ELF_PROT + bool + config ARCH_USE_GNU_PROPERTY bool diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 1fb67e506b68..cceb29d6ef1d 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -544,7 +544,8 @@ static inline int arch_check_elf(struct elfhdr *ehdr, bool has_interp, #endif /* !CONFIG_ARCH_BINFMT_ELF_STATE */ -static inline int make_prot(u32 p_flags) +static inline int make_prot(u32 p_flags, struct arch_elf_state *arch_state, + bool has_interp, bool is_interp) { int prot = 0; @@ -554,7 +555,8 @@ static inline int make_prot(u32 p_flags) prot |= PROT_WRITE; if (p_flags & PF_X) prot |= PROT_EXEC; - return prot; + + return arch_elf_adjust_prot(prot, arch_state, has_interp, is_interp); } /* This is much more generalized than the library routine read function, @@ -564,7 +566,8 @@ static inline int make_prot(u32 p_flags) static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, struct file *interpreter, - unsigned long no_base, struct elf_phdr *interp_elf_phdata) + unsigned long no_base, struct elf_phdr *interp_elf_phdata, + struct arch_elf_state *arch_state) { struct elf_phdr *eppnt; unsigned long load_addr = 0; @@ -596,7 +599,8 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) { if (eppnt->p_type == PT_LOAD) { int elf_type = MAP_PRIVATE | MAP_DENYWRITE; - int elf_prot = make_prot(eppnt->p_flags); + int elf_prot = make_prot(eppnt->p_flags, arch_state, + true, true); unsigned long vaddr = 0; unsigned long k, map_addr; @@ -1041,7 +1045,8 @@ out_free_interp: } } - elf_prot = make_prot(elf_ppnt->p_flags); + elf_prot = make_prot(elf_ppnt->p_flags, &arch_state, + !!interpreter, false); elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE; @@ -1184,7 +1189,8 @@ out_free_interp: if (interpreter) { elf_entry = load_elf_interp(&loc->interp_elf_ex, interpreter, - load_bias, interp_elf_phdata); + load_bias, interp_elf_phdata, + &arch_state); if (!IS_ERR((void *)elf_entry)) { /* * load_elf_interp() returns relocation diff --git a/include/linux/elf.h b/include/linux/elf.h index db5113479f5e..5d5b0321da0b 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -87,4 +87,16 @@ extern int arch_parse_elf_property(u32 type, const void *data, size_t datasz, bool compat, struct arch_elf_state *arch); #endif +#ifdef CONFIG_ARCH_HAVE_ELF_PROT +int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state, + bool has_interp, bool is_interp); +#else +static inline int arch_elf_adjust_prot(int prot, + const struct arch_elf_state *state, + bool has_interp, bool is_interp) +{ + return prot; +} +#endif + #endif /* _LINUX_ELF_H */ From ab7876a98a2160092133de4c648e94b18bc3f139 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:47 +0000 Subject: [PATCH 05/15] arm64: elf: Enable BTI at exec based on ELF program properties For BTI protection to be as comprehensive as possible, it is desirable to have BTI enabled from process startup. If this is not done, the process must use mprotect() to enable BTI for each of its executable mappings, but this is painful to do in the libc startup code. It's simpler and more sound to have the kernel do it instead. To this end, detect BTI support in the executable (or ELF interpreter, as appropriate), via the NT_GNU_PROGRAM_PROPERTY_TYPE_0 note, and tweak the initial prot flags for the process' executable pages to include PROT_BTI as appropriate. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 3 +++ arch/arm64/include/asm/elf.h | 50 ++++++++++++++++++++++++++++++++++++ arch/arm64/kernel/process.c | 19 ++++++++++++++ include/uapi/linux/elf.h | 6 +++++ 4 files changed, 78 insertions(+) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 0b30e884e088..8a15bc68dadd 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -9,6 +9,7 @@ config ARM64 select ACPI_MCFG if (ACPI && PCI) select ACPI_SPCR_TABLE if ACPI select ACPI_PPTT if ACPI + select ARCH_BINFMT_ELF_STATE select ARCH_CLOCKSOURCE_DATA select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED @@ -33,6 +34,7 @@ config ARM64 select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST + select ARCH_HAVE_ELF_PROT select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK if !PREEMPTION select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION @@ -62,6 +64,7 @@ config ARM64 select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION select ARCH_KEEP_MEMBLOCK select ARCH_USE_CMPXCHG_LOCKREF + select ARCH_USE_GNU_PROPERTY if BINFMT_ELF select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS select ARCH_SUPPORTS_MEMORY_FAILURE diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index b618017205a3..4f00d50585a4 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -114,7 +114,11 @@ #ifndef __ASSEMBLY__ +#include #include +#include +#include +#include #include /* for signal_minsigstksz, used by ARCH_DLINFO */ typedef unsigned long elf_greg_t; @@ -224,6 +228,52 @@ extern int aarch32_setup_additional_pages(struct linux_binprm *bprm, #endif /* CONFIG_COMPAT */ +struct arch_elf_state { + int flags; +}; + +#define ARM64_ELF_BTI (1 << 0) + +#define INIT_ARCH_ELF_STATE { \ + .flags = 0, \ +} + +static inline int arch_parse_elf_property(u32 type, const void *data, + size_t datasz, bool compat, + struct arch_elf_state *arch) +{ + /* No known properties for AArch32 yet */ + if (IS_ENABLED(CONFIG_COMPAT) && compat) + return 0; + + if (type == GNU_PROPERTY_AARCH64_FEATURE_1_AND) { + const u32 *p = data; + + if (datasz != sizeof(*p)) + return -ENOEXEC; + + if (system_supports_bti() && + (*p & GNU_PROPERTY_AARCH64_FEATURE_1_BTI)) + arch->flags |= ARM64_ELF_BTI; + } + + return 0; +} + +static inline int arch_elf_pt_proc(void *ehdr, void *phdr, + struct file *f, bool is_interp, + struct arch_elf_state *state) +{ + return 0; +} + +static inline int arch_check_elf(void *ehdr, bool has_interp, + void *interp_ehdr, + struct arch_elf_state *state) +{ + return 0; +} + #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 00626057a384..b8e3faa8d406 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -18,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -654,3 +656,20 @@ asmlinkage void __sched arm64_preempt_schedule_irq(void) if (system_capabilities_finalized()) preempt_schedule_irq(); } + +#ifdef CONFIG_BINFMT_ELF +int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state, + bool has_interp, bool is_interp) +{ + if (is_interp != has_interp) + return prot; + + if (!(state->flags & ARM64_ELF_BTI)) + return prot; + + if (prot & PROT_EXEC) + prot |= PROT_BTI; + + return prot; +} +#endif diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 20900f4496b7..c6dd0215482e 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -448,4 +448,10 @@ typedef struct elf64_note { Elf64_Word n_type; /* Content type */ } Elf64_Nhdr; +/* .note.gnu.property types for EM_AARCH64: */ +#define GNU_PROPERTY_AARCH64_FEATURE_1_AND 0xc0000000 + +/* Bits for GNU_PROPERTY_AARCH64_FEATURE_1_BTI */ +#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1U << 0) + #endif /* _UAPI_LINUX_ELF_H */ From ec94a46ee7ac999b0f10f7772c40aed3f604831b Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:48 +0000 Subject: [PATCH 06/15] arm64: BTI: Decode BYTPE bits when printing PSTATE The current code to print PSTATE symbolically when generating backtraces etc., does not include the BYTPE field used by Branch Target Identification. So, decode BYTPE and print it too. In the interests of human-readability, print the classes of BTI matched. The symbolic notation, BYTPE (PSTATE[11:10]) and permitted classes of subsequent instruction are: -- (BTYPE=0b00): any insn jc (BTYPE=0b01): BTI jc, BTI j, BTI c, PACIxSP -c (BYTPE=0b10): BTI jc, BTI c, PACIxSP j- (BTYPE=0b11): BTI jc, BTI j Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- arch/arm64/kernel/process.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index b8e3faa8d406..24af13d7bde6 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -211,6 +211,15 @@ void machine_restart(char *cmd) while (1); } +#define bstr(suffix, str) [PSR_BTYPE_ ## suffix >> PSR_BTYPE_SHIFT] = str +static const char *const btypes[] = { + bstr(NONE, "--"), + bstr( JC, "jc"), + bstr( C, "-c"), + bstr( J , "j-") +}; +#undef bstr + static void print_pstate(struct pt_regs *regs) { u64 pstate = regs->pstate; @@ -229,7 +238,10 @@ static void print_pstate(struct pt_regs *regs) pstate & PSR_AA32_I_BIT ? 'I' : 'i', pstate & PSR_AA32_F_BIT ? 'F' : 'f'); } else { - printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO)\n", + const char *btype_str = btypes[(pstate & PSR_BTYPE_MASK) >> + PSR_BTYPE_SHIFT]; + + printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO BTYPE=%s)\n", pstate, pstate & PSR_N_BIT ? 'N' : 'n', pstate & PSR_Z_BIT ? 'Z' : 'z', @@ -240,7 +252,8 @@ static void print_pstate(struct pt_regs *regs) pstate & PSR_I_BIT ? 'I' : 'i', pstate & PSR_F_BIT ? 'F' : 'f', pstate & PSR_PAN_BIT ? '+' : '-', - pstate & PSR_UAO_BIT ? '+' : '-'); + pstate & PSR_UAO_BIT ? '+' : '-', + btype_str); } } From 172a797661d95873c4af528c497cb5e1dfa8b91f Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:49 +0000 Subject: [PATCH 07/15] arm64: unify native/compat instruction skipping Skipping of an instruction on AArch32 works a bit differently from AArch64, mainly due to the different CPSR/PSTATE semantics. Currently arm64_skip_faulting_instruction() is only suitable for AArch64, and arm64_compat_skip_faulting_instruction() handles the IT state machine but is local to traps.c. Since manual instruction skipping implies a trap, it's a relatively slow path. So, make arm64_skip_faulting_instruction() handle both compat and native, and get rid of the arm64_compat_skip_faulting_instruction() special case. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Kees Cook Reviewed-by: Mark Rutland Signed-off-by: Catalin Marinas --- arch/arm64/kernel/traps.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index b8c714dda851..bc9f4292bfc3 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -272,6 +272,8 @@ void arm64_notify_die(const char *str, struct pt_regs *regs, } } +static void advance_itstate(struct pt_regs *regs); + void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size) { regs->pc += size; @@ -282,6 +284,9 @@ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size) */ if (user_mode(regs)) user_fastforward_single_step(current); + + if (regs->pstate & PSR_MODE32_BIT) + advance_itstate(regs); } static LIST_HEAD(undef_hook); @@ -644,19 +649,12 @@ static void advance_itstate(struct pt_regs *regs) compat_set_it_state(regs, it); } -static void arm64_compat_skip_faulting_instruction(struct pt_regs *regs, - unsigned int sz) -{ - advance_itstate(regs); - arm64_skip_faulting_instruction(regs, sz); -} - static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs) { int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT; pt_regs_write_reg(regs, reg, arch_timer_get_rate()); - arm64_compat_skip_faulting_instruction(regs, 4); + arm64_skip_faulting_instruction(regs, 4); } static const struct sys64_hook cp15_32_hooks[] = { @@ -676,7 +674,7 @@ static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs) pt_regs_write_reg(regs, rt, lower_32_bits(val)); pt_regs_write_reg(regs, rt2, upper_32_bits(val)); - arm64_compat_skip_faulting_instruction(regs, 4); + arm64_skip_faulting_instruction(regs, 4); } static const struct sys64_hook cp15_64_hooks[] = { @@ -697,7 +695,7 @@ void do_cp15instr(unsigned int esr, struct pt_regs *regs) * There is no T16 variant of a CP access, so we * always advance PC by 4 bytes. */ - arm64_compat_skip_faulting_instruction(regs, 4); + arm64_skip_faulting_instruction(regs, 4); return; } From d2c2ee4cc33bea814eb6739f14d8cb6a4b5265bb Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:50 +0000 Subject: [PATCH 08/15] arm64: traps: Shuffle code to eliminate forward declarations Hoist the IT state handling code earlier in traps.c, to avoid accumulating forward declarations. No functional change. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- arch/arm64/kernel/traps.c | 107 ++++++++++++++++++++------------------ 1 file changed, 55 insertions(+), 52 deletions(-) diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index bc9f4292bfc3..3c986c8ca204 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -272,7 +272,60 @@ void arm64_notify_die(const char *str, struct pt_regs *regs, } } -static void advance_itstate(struct pt_regs *regs); +#ifdef CONFIG_COMPAT +#define PSTATE_IT_1_0_SHIFT 25 +#define PSTATE_IT_1_0_MASK (0x3 << PSTATE_IT_1_0_SHIFT) +#define PSTATE_IT_7_2_SHIFT 10 +#define PSTATE_IT_7_2_MASK (0x3f << PSTATE_IT_7_2_SHIFT) + +static u32 compat_get_it_state(struct pt_regs *regs) +{ + u32 it, pstate = regs->pstate; + + it = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT; + it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2; + + return it; +} + +static void compat_set_it_state(struct pt_regs *regs, u32 it) +{ + u32 pstate_it; + + pstate_it = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK; + pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK; + + regs->pstate &= ~PSR_AA32_IT_MASK; + regs->pstate |= pstate_it; +} + +static void advance_itstate(struct pt_regs *regs) +{ + u32 it; + + /* ARM mode */ + if (!(regs->pstate & PSR_AA32_T_BIT) || + !(regs->pstate & PSR_AA32_IT_MASK)) + return; + + it = compat_get_it_state(regs); + + /* + * If this is the last instruction of the block, wipe the IT + * state. Otherwise advance it. + */ + if (!(it & 7)) + it = 0; + else + it = (it & 0xe0) | ((it << 1) & 0x1f); + + compat_set_it_state(regs, it); +} +#else +static void advance_itstate(struct pt_regs *regs) +{ +} +#endif void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size) { @@ -285,7 +338,7 @@ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size) if (user_mode(regs)) user_fastforward_single_step(current); - if (regs->pstate & PSR_MODE32_BIT) + if (compat_user_mode(regs)) advance_itstate(regs); } @@ -578,34 +631,7 @@ static const struct sys64_hook sys64_hooks[] = { {}, }; - #ifdef CONFIG_COMPAT -#define PSTATE_IT_1_0_SHIFT 25 -#define PSTATE_IT_1_0_MASK (0x3 << PSTATE_IT_1_0_SHIFT) -#define PSTATE_IT_7_2_SHIFT 10 -#define PSTATE_IT_7_2_MASK (0x3f << PSTATE_IT_7_2_SHIFT) - -static u32 compat_get_it_state(struct pt_regs *regs) -{ - u32 it, pstate = regs->pstate; - - it = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT; - it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2; - - return it; -} - -static void compat_set_it_state(struct pt_regs *regs, u32 it) -{ - u32 pstate_it; - - pstate_it = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK; - pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK; - - regs->pstate &= ~PSR_AA32_IT_MASK; - regs->pstate |= pstate_it; -} - static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs) { int cond; @@ -626,29 +652,6 @@ static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs) return aarch32_opcode_cond_checks[cond](regs->pstate); } -static void advance_itstate(struct pt_regs *regs) -{ - u32 it; - - /* ARM mode */ - if (!(regs->pstate & PSR_AA32_T_BIT) || - !(regs->pstate & PSR_AA32_IT_MASK)) - return; - - it = compat_get_it_state(regs); - - /* - * If this is the last instruction of the block, wipe the IT - * state. Otherwise advance it. - */ - if (!(it & 7)) - it = 0; - else - it = (it & 0xe0) | ((it << 1) & 0x1f); - - compat_set_it_state(regs, it); -} - static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs) { int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT; From 0537c4cd71e3c729c278c82f5b088460fb66fc33 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:51 +0000 Subject: [PATCH 09/15] arm64: BTI: Reset BTYPE when skipping emulated instructions Since normal execution of any non-branch instruction resets the PSTATE BTYPE field to 0, so do the same thing when emulating a trapped instruction. Branches don't trap directly, so we should never need to assign a non-zero value to BTYPE here. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Signed-off-by: Catalin Marinas --- arch/arm64/kernel/traps.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 3c986c8ca204..10d6451b2776 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -340,6 +340,8 @@ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size) if (compat_user_mode(regs)) advance_itstate(regs); + else + regs->pstate &= ~PSR_BTYPE_MASK; } static LIST_HEAD(undef_hook); From 30685d789c48f27f97f6ecde6185b606a6c7abf6 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:52 +0000 Subject: [PATCH 10/15] KVM: arm64: BTI: Reset BTYPE when skipping emulated instructions Since normal execution of any non-branch instruction resets the PSTATE BTYPE field to 0, so do the same thing when emulating a trapped instruction. Branches don't trap directly, so we should never need to assign a non-zero value to BTYPE here. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Acked-by: Marc Zyngier Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/kvm_emulate.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 688c63412cc2..dee51c1dcb93 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -506,10 +506,12 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) { - if (vcpu_mode_is_32bit(vcpu)) + if (vcpu_mode_is_32bit(vcpu)) { kvm_skip_instr32(vcpu, is_wide_instr); - else + } else { *vcpu_pc(vcpu) += 4; + *vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK; + } /* advance the singlestep state machine */ *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; From de48bb369242fe17022fab3a2addc9c6dacad43f Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 16 Mar 2020 16:50:53 +0000 Subject: [PATCH 11/15] arm64: mm: Display guarded pages in ptdump v8.5-BTI introduces the GP field in stage 1 translation tables which indicates that blocks and pages with it set are guarded pages for which branch target identification checks should be performed. Decode this when dumping the page tables to aid debugging. Signed-off-by: Mark Brown Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- arch/arm64/mm/dump.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 860c00ec8bd3..78163b7a7dde 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -145,6 +145,11 @@ static const struct prot_bits pte_bits[] = { .val = PTE_UXN, .set = "UXN", .clear = " ", + }, { + .mask = PTE_GP, + .val = PTE_GP, + .set = "GP", + .clear = " ", }, { .mask = PTE_ATTRINDX_MASK, .val = PTE_ATTRINDX(MT_DEVICE_nGnRnE), From 424037b77519d1537872442ba144dda1464988d7 Mon Sep 17 00:00:00 2001 From: Daniel Kiss Date: Mon, 16 Mar 2020 16:50:54 +0000 Subject: [PATCH 12/15] mm: smaps: Report arm64 guarded pages in smaps The arm64 Branch Target Identification support is activated by marking executable pages as guarded pages. Report pages mapped this way in smaps to aid diagnostics. Signed-off-by: Mark Brown Signed-off-by: Daniel Kiss Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- Documentation/filesystems/proc.txt | 1 + fs/proc/task_mmu.c | 3 +++ 2 files changed, 4 insertions(+) diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 99ca040e3f90..ed5465d0f435 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -519,6 +519,7 @@ manner. The codes are the following: hg - huge page advise flag nh - no-huge page advise flag mg - mergable advise flag + bt - arm64 BTI guarded page Note that there is no guarantee that every flag and associated mnemonic will be present in all further kernel releases. Things get changed, the flags may diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3ba9ae83bff5..1e3409c484d1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -668,6 +668,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_ARCH_1)] = "ar", [ilog2(VM_WIPEONFORK)] = "wf", [ilog2(VM_DONTDUMP)] = "dd", +#ifdef CONFIG_ARM64_BTI + [ilog2(VM_ARM64_BTI)] = "bt", +#endif #ifdef CONFIG_MEM_SOFT_DIRTY [ilog2(VM_SOFTDIRTY)] = "sd", #endif From 383499f8863ea8ce869ba62cec91d9f709c9459b Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:55 +0000 Subject: [PATCH 13/15] arm64: BTI: Add Kconfig entry for userspace BTI Now that the code for userspace BTI support is in the kernel add the Kconfig entry so that it can be built and used. [Split out of "arm64: Basic Branch Target Identification support" -- broonie] Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 8a15bc68dadd..d65d226a77ec 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1522,6 +1522,28 @@ endmenu menu "ARMv8.5 architectural features" +config ARM64_BTI + bool "Branch Target Identification support" + default y + help + Branch Target Identification (part of the ARMv8.5 Extensions) + provides a mechanism to limit the set of locations to which computed + branch instructions such as BR or BLR can jump. + + To make use of BTI on CPUs that support it, say Y. + + BTI is intended to provide complementary protection to other control + flow integrity protection mechanisms, such as the Pointer + authentication mechanism provided as part of the ARMv8.3 Extensions. + For this reason, it does not make sense to enable this option without + also enabling support for pointer authentication. Thus, when + enabling this option you should also select ARM64_PTR_AUTH=y. + + Userspace binaries must also be specifically compiled to make use of + this mechanism. If you say N here or the hardware does not support + BTI, such binaries can still run, but you get no additional + enforcement of branch destinations. + config ARM64_E0PD bool "Enable support for E0PD" default y From bf7f15c585d5b9b843e662aa78f9fc71037db968 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 18 Mar 2020 08:28:31 +0000 Subject: [PATCH 14/15] arm64: elf: Fix allnoconfig kernel build with !ARCH_USE_GNU_PROPERTY Commit ab7876a98a21 ("arm64: elf: Enable BTI at exec based on ELF program properties") introduced the conditional selection of ARCH_USE_GNU_PROPERTY if BINFMT_ELF is enabled. With allnoconfig, this option is no longer selected and the arm64 arch_parse_elf_property() function clashes with the generic dummy implementation. Link: http://lkml.kernel.org/r/20200318082830.GA31312@willie-the-truck Fixes: ab7876a98a21 ("arm64: elf: Enable BTI at exec based on ELF program properties") Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index d65d226a77ec..53c77711f752 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -64,7 +64,7 @@ config ARM64 select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION select ARCH_KEEP_MEMBLOCK select ARCH_USE_CMPXCHG_LOCKREF - select ARCH_USE_GNU_PROPERTY if BINFMT_ELF + select ARCH_USE_GNU_PROPERTY select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS select ARCH_SUPPORTS_MEMORY_FAILURE From 5d1b631c773ffbbadcbb3176a2ae0ea9d1c114c7 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 23 Mar 2020 17:01:19 +0000 Subject: [PATCH 15/15] arm64: bti: Document behaviour for dynamically linked binaries For dynamically linked binaries the interpreter is responsible for setting PROT_BTI on everything except itself. The dynamic linker needs to be aware of PROT_BTI, for example in order to avoid dropping that when marking executable pages read only after doing relocations, and doing everything in userspace ensures that we don't get any issues due to divergences in behaviour between the kernel and dynamic linker within a single executable. Add a comment indicating that this is intentional to the code to help people trying to understand what's going on. Signed-off-by: Mark Brown Signed-off-by: Catalin Marinas --- arch/arm64/kernel/process.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 24af13d7bde6..127aee478433 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -674,6 +674,11 @@ asmlinkage void __sched arm64_preempt_schedule_irq(void) int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state, bool has_interp, bool is_interp) { + /* + * For dynamically linked executables the interpreter is + * responsible for setting PROT_BTI on everything except + * itself. + */ if (is_interp != has_interp) return prot;