From: Deepak Gupta debug@rivosinc.com

Three architectures (x86, aarch64, riscv) have announced support for shadow stack. This patch adds arch-agnostic prtcl support to enable /disable/get/set status of shadow stack and forward control (landing pad) flow cfi statuses.

New prctls are - PR_GET_SHADOW_STACK_STATUS, PR_SET_SHADOW_STACK_STATUS

Signed-off-by: Deepak Gupta debug@rivosinc.com [Rebased onto current kernels, renumbering to track other allocations already upstream, dropping indirect LP, updating to pass arg to set by value, fix missing prototypes for weak functions and update title. -- broonie] Signed-off-by: Mark Brown broonie@kernel.org --- include/linux/mm.h | 3 +++ include/uapi/linux/prctl.h | 17 +++++++++++++++++ kernel/sys.c | 20 ++++++++++++++++++++ 3 files changed, 40 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h index 97eddc83d19c..bf16edf2fcd9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3947,4 +3947,7 @@ static inline void accept_memory(phys_addr_t start, phys_addr_t end)

#endif

+int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); +int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); + #endif /* _LINUX_MM_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 3c36aeade991..9fdc77fa2bfe 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -305,4 +305,21 @@ struct prctl_mm_map { # define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc # define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f

+/* + * get shadow stack status for current thread. Assumes shadow stack is min 4 byte aligned. + * Note shadow stack can be 8 byte aligned on 64bit. + * Lower 2 bits can give status of locked and enabled/disabled. + * size and address range can be obtained via /proc/maps. get_shadow_stack_status will + * return base of shadow stack. + */ +#define PR_GET_SHADOW_STACK_STATUS 71 +/* + * set shadow stack status for current thread (including enabling, disabling or locking) + * note that it will only set the status and setup of the shadow stack. Allocating shadow + * stack should be done separately using mmap. + */ +#define PR_SET_SHADOW_STACK_STATUS 72 +# define PR_SHADOW_STACK_LOCK (1UL << 0) +# define PR_SHADOW_STACK_ENABLE (1UL << 1) + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index 05f838929e72..ebf9ea5f0fae 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2302,6 +2302,16 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, return -EINVAL; }

+int __weak arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status) +{ + return -EINVAL; +} + +int __weak arch_set_shadow_stack_status(struct task_struct *t, unsigned long status) +{ + return -EINVAL; +} + #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE)

#ifdef CONFIG_ANON_VMA_NAME @@ -2720,6 +2730,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_RISCV_V_GET_CONTROL: error = RISCV_V_GET_CONTROL(); break; + case PR_GET_SHADOW_STACK_STATUS: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_get_shadow_stack_status(me, (unsigned long __user *) arg2); + break; + case PR_SET_SHADOW_STACK_STATUS: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_set_shadow_stack_status(me, arg2); + break; default: error = -EINVAL; break;

FEAT_GCS introduces a number of new system registers, we require that access to these registers is not trapped when we identify that the feature is detected.

Signed-off-by: Mark Brown broonie@kernel.org --- Documentation/arch/arm64/booting.rst | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+)

diff --git a/Documentation/arch/arm64/booting.rst b/Documentation/arch/arm64/booting.rst index b57776a68f15..de3679770c64 100644 --- a/Documentation/arch/arm64/booting.rst +++ b/Documentation/arch/arm64/booting.rst @@ -411,6 +411,28 @@ Before jumping into the kernel, the following conditions must be met:

- HFGRWR_EL2.nPIRE0_EL1 (bit 57) must be initialised to 0b1.

+ - For features with Guarded Control Stacks (FEAT_GCS): + + - If EL3 is present: + + - SCR_EL3.GCSEn (bit 39) must be initialised to 0b1. + + - If the kernel is entered at EL1 and EL2 is present: + + - HFGITR_EL2.nGCSEPP (bit 59) must be initialised to 0b1. + + - HFGITR_EL2.nGCSSTR_EL1 (bit 58) must be initialised to 0b1. + + - HFGITR_EL2.nGCSPUSHM_EL1 (bit 57) must be initialised to 0b1. + + - HFGRTR_EL2.nGCS_EL1 (bit 53) must be initialised to 0b1. + + - HFGRTR_EL2.nGCS_EL0 (bit 52) must be initialised to 0b1. + + - HFGWTR_EL2.nGCS_EL1 (bit 53) must be initialised to 0b1. + + - HFGWTR_EL2.nGCS_EL0 (bit 52) must be initialised to 0b1. + The requirements described above for CPU mode, caches, MMUs, architected timers, coherency and system registers apply to all CPUs. All CPUs must enter the kernel in the same exception level. Where the values documented

FEAT_GCS introduces a number of new system registers. Add the registers available up to EL2 to sysreg as per DDI0601 2022-12.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/tools/sysreg | 55 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+)

diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 1ea4a3dc68f8..516aef38eab7 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -1780,6 +1780,41 @@ Sysreg SMCR_EL1 3 0 1 2 6 Fields SMCR_ELx EndSysreg

+SysregFields GCSCR_ELx +Res0 63:10 +Field 9 STREn +Field 8 PUSHMEn +Res0 7 +Field 6 EXLOCKEN +Field 5 RVCHKEN +Res0 4:1 +Field 0 PCRSEL +EndSysregFields + +Sysreg GCSCR_EL1 3 0 2 5 0 +Fields GCSCR_ELx +EndSysreg + +SysregFields GCSPR_ELx +Field 63:3 PTR +Res0 2:0 +EndSysregFields + +Sysreg GCSPR_EL1 3 0 2 5 1 +Fields GCSPR_ELx +EndSysreg + +Sysreg GCSCRE0_EL1 3 0 2 5 2 +Res0 63:11 +Field 10 nTR +Field 9 STREn +Field 8 PUSHMEn +Res0 7:6 +Field 5 RVCHKEN +Res0 4:1 +Field 0 PCRSEL +EndSysreg + Sysreg ALLINT 3 0 4 3 0 Res0 63:14 Field 13 ALLINT @@ -2010,6 +2045,10 @@ Field 4 DZP Field 3:0 BS EndSysreg

+Sysreg GCSPR_EL0 3 3 2 5 1 +Fields GCSPR_ELx +EndSysreg + Sysreg SVCR 3 3 4 2 2 Res0 63:2 Field 1 ZA @@ -2209,6 +2248,14 @@ Sysreg SMCR_EL2 3 4 1 2 6 Fields SMCR_ELx EndSysreg

+Sysreg GCSCR_EL2 3 4 2 5 0 +Fields GCSCR_ELx +EndSysreg + +Sysreg GCSPR_EL2 3 4 2 5 1 +Fields GCSPR_ELx +EndSysreg + Sysreg DACR32_EL2 3 4 3 0 0 Res0 63:32 Field 31:30 D15 @@ -2268,6 +2315,14 @@ Sysreg SMCR_EL12 3 5 1 2 6 Fields SMCR_ELx EndSysreg

+Sysreg GCSCR_EL12 3 5 2 5 0 +Fields GCSCR_ELx +EndSysreg + +Sysreg GCSPR_EL12 3 5 2 5 1 +Fields GCSPR_ELx +EndSysreg + Sysreg FAR_EL12 3 5 6 0 0 Field 63:0 ADDR EndSysreg

Define C callable functions for GCS instructions used by the kernel. In order to avoid ambitious toolchain requirements for GCS support these are manually encoded, this means we have fixed register numbers which will be a bit limiting for the compiler but none of these should be used in sufficiently fast paths for this to be a problem.

Note that GCSSTTR is used to store to EL0.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/gcs.h | 51 ++++++++++++++++++++++++++++++++++++++++ arch/arm64/include/asm/uaccess.h | 22 +++++++++++++++++ 2 files changed, 73 insertions(+)

diff --git a/arch/arm64/include/asm/gcs.h b/arch/arm64/include/asm/gcs.h new file mode 100644 index 000000000000..7c5e95218db6 --- /dev/null +++ b/arch/arm64/include/asm/gcs.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 ARM Ltd. + */ +#ifndef __ASM_GCS_H +#define __ASM_GCS_H + +#include <asm/types.h> +#include <asm/uaccess.h> + +static inline void gcsb_dsync(void) +{ + asm volatile(".inst 0xd503227f" : : : "memory"); +} + +static inline void gcsstr(u64 *addr, u64 val) +{ + register u64 *_addr __asm__ ("x0") = addr; + register long _val __asm__ ("x1") = val; + + /* GCSSTTR x1, x0 */ + asm volatile( + ".inst 0xd91f1c01\n" + : + : "rZ" (_val), "r" (_addr) + : "memory"); +} + +static inline void gcsss1(u64 Xt) +{ + asm volatile ( + "sys #3, C7, C7, #2, %0\n" + : + : "rZ" (Xt) + : "memory"); +} + +static inline u64 gcsss2(void) +{ + u64 Xt; + + asm volatile( + "SYSL %0, #3, C7, C7, #3\n" + : "=r" (Xt) + : + : "memory"); + + return Xt; +} + +#endif diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 14be5000c5a0..22e10e79f56a 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -425,4 +425,26 @@ static inline size_t probe_subpage_writeable(const char __user *uaddr,

#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */

+#ifdef CONFIG_ARM64_GCS + +static inline int gcssttr(unsigned long __user *addr, unsigned long val) +{ + register unsigned long __user *_addr __asm__ ("x0") = addr; + register unsigned long _val __asm__ ("x1") = val; + int err = 0; + + /* GCSSTTR x1, x0 */ + asm volatile( + "1: .inst 0xd91f1c01\n" + "2: \n" + _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %w0) + : "+r" (err) + : "rZ" (_val), "r" (_addr) + : "memory"); + + return err; +} + +#endif /* CONFIG_ARM64_GCS */ + #endif /* __ASM_UACCESS_H */

Add a cpufeature for GCS, allowing other code to conditionally support it at runtime.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/cpufeature.h | 6 ++++++ arch/arm64/kernel/cpufeature.c | 20 ++++++++++++++++++++ arch/arm64/tools/cpucaps | 1 + 3 files changed, 27 insertions(+)

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 96e50227f940..189783142a96 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -831,6 +831,12 @@ static inline bool system_supports_tlb_range(void) cpus_have_const_cap(ARM64_HAS_TLB_RANGE); }

+static inline bool system_supports_gcs(void) +{ + return IS_ENABLED(CONFIG_ARM64_GCS) && + cpus_have_const_cap(ARM64_HAS_GCS); +} + int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt); bool try_emulate_mrs(struct pt_regs *regs, u32 isn);

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f9d456fe132d..92e730027d84 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -254,6 +254,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { };

static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_GCS), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_GCS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_SME_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_MPAM_frac_SHIFT, 4, 0), @@ -2219,6 +2221,12 @@ static void cpu_enable_mops(const struct arm64_cpu_capabilities *__unused) sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_MSCEn); }

+static void cpu_enable_gcs(const struct arm64_cpu_capabilities *__unused) +{ + /* GCS is not currently used at EL1 */ + write_sysreg_s(0, SYS_GCSCR_EL1); +} + /* Internal helper functions to match cpu capability type */ static bool cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) @@ -2715,6 +2723,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .min_field_value = ID_AA64MMFR2_EL1_EVT_IMP, .matches = has_cpuid_feature, }, + { + .desc = "Guarded Control Stack (GCS)", + .capability = ARM64_HAS_GCS, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .sys_reg = SYS_ID_AA64PFR1_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64PFR1_EL1_GCS_SHIFT, + .field_width = 4, + .min_field_value = ID_AA64PFR1_EL1_GCS_IMP, + .matches = has_cpuid_feature, + .cpu_enable = cpu_enable_gcs, + }, {}, };

diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index c80ed4f3cbce..ab582f592131 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -26,6 +26,7 @@ HAS_ECV HAS_ECV_CNTPOFF HAS_EPAN HAS_EVT +HAS_GCS HAS_GENERIC_AUTH HAS_GENERIC_AUTH_ARCH_QARMA3 HAS_GENERIC_AUTH_ARCH_QARMA5

Use VM_HIGH_ARCH_5 for guarded control stack pages.

Signed-off-by: Mark Brown broonie@kernel.org --- Documentation/filesystems/proc.rst | 2 +- fs/proc/task_mmu.c | 3 +++ include/linux/mm.h | 12 +++++++++++- 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 6ccb57089a06..086a0408a4d7 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -566,7 +566,7 @@ encoded manner. The codes are the following: mt arm64 MTE allocation tags are enabled um userfaultfd missing tracking uw userfaultfd wr-protect tracking - ss shadow stack page + ss shadow/guarded control stack page == =======================================

Note that there is no guarantee that every flag and associated mnemonic will diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index cfab855fe7e9..e8c50848bb16 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -711,6 +711,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ #ifdef CONFIG_X86_USER_SHADOW_STACK [ilog2(VM_SHADOW_STACK)] = "ss", +#endif +#ifdef CONFIG_ARM64_GCS + [ilog2(VM_SHADOW_STACK)] = "ss", #endif }; size_t i; diff --git a/include/linux/mm.h b/include/linux/mm.h index bf16edf2fcd9..f526032c4dc6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -372,7 +372,17 @@ extern unsigned int kobjsize(const void *objp); * having a PAGE_SIZE guard gap. */ # define VM_SHADOW_STACK VM_HIGH_ARCH_5 -#else +#endif + +#if defined(CONFIG_ARM64_GCS) +/* + * arm64's Guarded Control Stack implements similar functionality and + * has similar constraints to shadow stacks. + */ +# define VM_SHADOW_STACK VM_HIGH_ARCH_5 +#endif + +#ifndef VM_SHADOW_STACK # define VM_SHADOW_STACK VM_NONE #endif

GCS introduces a number of system registers for EL1 and EL0, on systems with GCS we need to context switch them and expose them to VMMs to allow guests to use GCS. Traps are already disabled.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 12 ++++++++++++ arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 17 +++++++++++++++++ arch/arm64/kvm/sys_regs.c | 22 ++++++++++++++++++++++ 3 files changed, 51 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 8b6096753740..67f3894a86f1 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -364,6 +364,12 @@ enum vcpu_sysreg { PIR_EL1, /* Permission Indirection Register 1 (EL1) */ PIRE0_EL1, /* Permission Indirection Register 0 (EL1) */

+ /* Guarded Control Stack registers */ + GCSCRE0_EL1, /* Guarded Control Stack Control (EL0) */ + GCSCR_EL1, /* Guarded Control Stack Control (EL1) */ + GCSPR_EL0, /* Guarded Control Stack Pointer (EL0) */ + GCSPR_EL1, /* Guarded Control Stack Pointer (EL1) */ + /* 32bit specific registers. */ DACR32_EL2, /* Domain Access Control Register */ IFSR32_EL2, /* Instruction Fault Status Register */ @@ -1134,6 +1140,12 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); #define kvm_vm_has_ran_once(kvm) \ (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &(kvm)->arch.flags))

+static inline bool has_gcs(void) +{ + return IS_ENABLED(CONFIG_ARM64_GCS) && + cpus_have_final_cap(ARM64_HAS_GCS); +} + int kvm_trng_call(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM extern phys_addr_t hyp_mem_base; diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index bb6b571ec627..ec34d4a90717 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -25,6 +25,8 @@ static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt) { ctxt_sys_reg(ctxt, TPIDR_EL0) = read_sysreg(tpidr_el0); ctxt_sys_reg(ctxt, TPIDRRO_EL0) = read_sysreg(tpidrro_el0); + if (has_gcs()) + ctxt_sys_reg(ctxt, GCSPR_EL0) = read_sysreg_s(SYS_GCSPR_EL0); }

static inline bool ctxt_has_mte(struct kvm_cpu_context *ctxt) @@ -62,6 +64,12 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) ctxt_sys_reg(ctxt, PAR_EL1) = read_sysreg_par(); ctxt_sys_reg(ctxt, TPIDR_EL1) = read_sysreg(tpidr_el1);

+ if (has_gcs()) { + ctxt_sys_reg(ctxt, GCSPR_EL1) = read_sysreg_el1(SYS_GCSPR); + ctxt_sys_reg(ctxt, GCSCR_EL1) = read_sysreg_el1(SYS_GCSCR); + ctxt_sys_reg(ctxt, GCSCRE0_EL1) = read_sysreg_s(SYS_GCSCRE0_EL1); + } + if (ctxt_has_mte(ctxt)) { ctxt_sys_reg(ctxt, TFSR_EL1) = read_sysreg_el1(SYS_TFSR); ctxt_sys_reg(ctxt, TFSRE0_EL1) = read_sysreg_s(SYS_TFSRE0_EL1); @@ -95,6 +103,8 @@ static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL0), tpidr_el0); write_sysreg(ctxt_sys_reg(ctxt, TPIDRRO_EL0), tpidrro_el0); + if (has_gcs()) + write_sysreg_s(ctxt_sys_reg(ctxt, GCSPR_EL0), SYS_GCSPR_EL0); }

static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) @@ -138,6 +148,13 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1), par_el1); write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1), tpidr_el1);

+ if (has_gcs()) { + write_sysreg_el1(ctxt_sys_reg(ctxt, GCSPR_EL1), SYS_GCSPR); + write_sysreg_el1(ctxt_sys_reg(ctxt, GCSCR_EL1), SYS_GCSCR); + write_sysreg_s(ctxt_sys_reg(ctxt, GCSCRE0_EL1), + SYS_GCSCRE0_EL1); + } + if (ctxt_has_mte(ctxt)) { write_sysreg_el1(ctxt_sys_reg(ctxt, TFSR_EL1), SYS_TFSR); write_sysreg_s(ctxt_sys_reg(ctxt, TFSRE0_EL1), SYS_TFSRE0_EL1); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index bd3431823ec5..e829400aa911 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1768,6 +1768,23 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu, .visibility = mte_visibility, \ }

+static unsigned int gcs_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + if (has_gcs()) + return 0; + + return REG_HIDDEN; +} + +#define GCS_REG(name) { \ + SYS_DESC(SYS_##name), \ + .access = undef_access, \ + .reset = reset_unknown, \ + .reg = name, \ + .visibility = gcs_visibility, \ +} + static unsigned int el2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { @@ -2080,6 +2097,10 @@ static const struct sys_reg_desc sys_reg_descs[] = { PTRAUTH_KEY(APDB), PTRAUTH_KEY(APGA),

+ GCS_REG(GCSCR_EL1), + GCS_REG(GCSPR_EL1), + GCS_REG(GCSCRE0_EL1), + { SYS_DESC(SYS_SPSR_EL1), access_spsr}, { SYS_DESC(SYS_ELR_EL1), access_elr},

@@ -2162,6 +2183,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_SMIDR_EL1), undef_access }, { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, + GCS_REG(GCSPR_EL0), { SYS_DESC(SYS_SVCR), undef_access },

{ PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr,

Hook up an override for GCS, allowing it to be disabled from the command line by specifying arm64.nogcs in case there are problems.

Signed-off-by: Mark Brown broonie@kernel.org --- Documentation/admin-guide/kernel-parameters.txt | 3 +++ arch/arm64/kernel/idreg-override.c | 2 ++ 2 files changed, 5 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a1457995fd41..86662eed3003 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -418,6 +418,9 @@ arm64.nobti [ARM64] Unconditionally disable Branch Target Identification support

+ arm64.nogcs [ARM64] Unconditionally disable Guarded Control Stack + support + arm64.nopauth [ARM64] Unconditionally disable Pointer Authentication support

diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index 2fe2491b692c..49269a5cff10 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -99,6 +99,7 @@ static const struct ftr_set_desc pfr1 __initconst = { .override = &id_aa64pfr1_override, .fields = { FIELD("bt", ID_AA64PFR1_EL1_BT_SHIFT, NULL ), + FIELD("gcs", ID_AA64PFR1_EL1_GCS_SHIFT, NULL), FIELD("mte", ID_AA64PFR1_EL1_MTE_SHIFT, NULL), FIELD("sme", ID_AA64PFR1_EL1_SME_SHIFT, pfr1_sme_filter), {} @@ -178,6 +179,7 @@ static const struct { { "arm64.nosve", "id_aa64pfr0.sve=0" }, { "arm64.nosme", "id_aa64pfr1.sme=0" }, { "arm64.nobti", "id_aa64pfr1.bt=0" }, + { "arm64.nogcs", "id_aa64pfr1.gcs=0" }, { "arm64.nopauth", "id_aa64isar1.gpi=0 id_aa64isar1.gpa=0 " "id_aa64isar1.api=0 id_aa64isar1.apa=0 "

A new exception code is defined for GCS specific faults other than standard load/store faults, for example GCS token validation failures, add handling for this. These faults are reported to userspace as segfaults with code SEGV_CPERR (protection error), mirroring the reporting for x86 shadow stack errors.

GCS faults due to memory load/store operations generate data aborts with a flag set, these will be handled separately as part of the data abort handling.

Since we do not currently enable GCS for EL1 we should not get any faults there but while we're at it we wire things up there, treating any GCS fault as fatal.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/esr.h | 26 +++++++++++++++++++++++++- arch/arm64/include/asm/exception.h | 2 ++ arch/arm64/kernel/entry-common.c | 23 +++++++++++++++++++++++ arch/arm64/kernel/traps.c | 11 +++++++++++ 4 files changed, 61 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index ae35939f395b..c5a72172fcf1 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -51,7 +51,8 @@ #define ESR_ELx_EC_FP_EXC32 (0x28) /* Unallocated EC: 0x29 - 0x2B */ #define ESR_ELx_EC_FP_EXC64 (0x2C) -/* Unallocated EC: 0x2D - 0x2E */ +#define ESR_ELx_EC_GCS (0x2D) +/* Unallocated EC: 0x2E */ #define ESR_ELx_EC_SERROR (0x2F) #define ESR_ELx_EC_BREAKPT_LOW (0x30) #define ESR_ELx_EC_BREAKPT_CUR (0x31) @@ -382,6 +383,29 @@ #define ESR_ELx_MOPS_ISS_SRCREG(esr) (((esr) & (UL(0x1f) << 5)) >> 5) #define ESR_ELx_MOPS_ISS_SIZEREG(esr) (((esr) & (UL(0x1f) << 0)) >> 0)

+/* ISS field definitions for GCS */ +#define ESR_ELx_ExType_SHIFT (20) +#define ESR_ELx_ExType_MASK GENMASK(23, 20) +#define ESR_ELx_Raddr_SHIFT (14) +#define ESR_ELx_Raddr_MASK GENMASK(14, 10) +#define ESR_ELx_Rn_SHIFT (5) +#define ESR_ELx_Rn_MASK GENMASK(9, 5) +#define ESR_ELx_IT_SHIFT (0) +#define ESR_ELx_IT_MASK GENMASK(4, 0) + +#define ESR_ELx_ExType_DATA_CHECK 0 +#define ESR_ELx_ExType_EXLOCK 1 +#define ESR_ELx_ExType_STR 2 + +#define ESR_ELx_IT_RET 0 +#define ESR_ELx_IT_GCSPOPM 1 +#define ESR_ELx_IT_RET_KEYA 2 +#define ESR_ELx_IT_RET_KEYB 3 +#define ESR_ELx_IT_GCSSS1 4 +#define ESR_ELx_IT_GCSSS2 5 +#define ESR_ELx_IT_GCSPOPCX 6 +#define ESR_ELx_IT_GCSPOPX 7 + #ifndef __ASSEMBLY__ #include <asm/types.h>

diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index ad688e157c9b..99caff458e20 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -57,6 +57,8 @@ void do_el0_undef(struct pt_regs *regs, unsigned long esr); void do_el1_undef(struct pt_regs *regs, unsigned long esr); void do_el0_bti(struct pt_regs *regs); void do_el1_bti(struct pt_regs *regs, unsigned long esr); +void do_el0_gcs(struct pt_regs *regs, unsigned long esr); +void do_el1_gcs(struct pt_regs *regs, unsigned long esr); void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr, struct pt_regs *regs); void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs); diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 6b2e0c367702..4d86216962e5 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -400,6 +400,15 @@ static void noinstr el1_bti(struct pt_regs *regs, unsigned long esr) exit_to_kernel_mode(regs); }

+static void noinstr el1_gcs(struct pt_regs *regs, unsigned long esr) +{ + enter_from_kernel_mode(regs); + local_daif_inherit(regs); + do_el1_gcs(regs, esr); + local_daif_mask(); + exit_to_kernel_mode(regs); +} + static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -442,6 +451,9 @@ asmlinkage void noinstr el1h_64_sync_handler(struct pt_regs *regs) case ESR_ELx_EC_BTI: el1_bti(regs, esr); break; + case ESR_ELx_EC_GCS: + el1_gcs(regs, esr); + break; case ESR_ELx_EC_BREAKPT_CUR: case ESR_ELx_EC_SOFTSTP_CUR: case ESR_ELx_EC_WATCHPT_CUR: @@ -621,6 +633,14 @@ static void noinstr el0_mops(struct pt_regs *regs, unsigned long esr) exit_to_user_mode(regs); }

+static void noinstr el0_gcs(struct pt_regs *regs, unsigned long esr) +{ + enter_from_user_mode(regs); + local_daif_restore(DAIF_PROCCTX); + do_el0_gcs(regs, esr); + exit_to_user_mode(regs); +} + static void noinstr el0_inv(struct pt_regs *regs, unsigned long esr) { enter_from_user_mode(regs); @@ -701,6 +721,9 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs) case ESR_ELx_EC_MOPS: el0_mops(regs, esr); break; + case ESR_ELx_EC_GCS: + el0_gcs(regs, esr); + 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/traps.c b/arch/arm64/kernel/traps.c index 8b70759cdbb9..65dab959f620 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -500,6 +500,16 @@ void do_el1_bti(struct pt_regs *regs, unsigned long esr) die("Oops - BTI", regs, esr); }

+void do_el0_gcs(struct pt_regs *regs, unsigned long esr) +{ + force_signal_inject(SIGSEGV, SEGV_CPERR, regs->pc, 0); +} + +void do_el1_gcs(struct pt_regs *regs, unsigned long esr) +{ + die("Oops - GCS", regs, esr); +} + void do_el0_fpac(struct pt_regs *regs, unsigned long esr) { force_signal_inject(SIGILL, ILL_ILLOPN, regs->pc, esr); @@ -884,6 +894,7 @@ static const char *esr_class_str[] = { [ESR_ELx_EC_MOPS] = "MOPS", [ESR_ELx_EC_FP_EXC32] = "FP (AArch32)", [ESR_ELx_EC_FP_EXC64] = "FP (AArch64)", + [ESR_ELx_EC_GCS] = "Guarded Control Stack", [ESR_ELx_EC_SERROR] = "SError", [ESR_ELx_EC_BREAKPT_LOW] = "Breakpoint (lower EL)", [ESR_ELx_EC_BREAKPT_CUR] = "Breakpoint (current EL)",

All GCS operations at EL0 must happen on a page which is marked as having UnprivGCS access, including read operations. If a GCS operation attempts to access a page without this then it will generate a data abort with the GCS bit set in ESR_EL1.ISS2.

EL0 may validly generate such faults, for example due to copy on write which will cause the GCS data to be stored in a read only page with no GCS permissions until the actual copy happens. Since UnprivGCS allows both reads and writes to the GCS (though only through GCS operations) we need to ensure that the memory management subsystem handles GCS accesses as writes at all times. Do this by adding FAULT_FLAG_WRITE to any GCS page faults, adding handling to ensure that invalid cases are identfied as such early so the memory management core does not think they will succeed. The core cannot distinguish between VMAs which are generally writeable and VMAs which are only writeable through GCS operations.

EL1 may validly write to EL0 GCS for management purposes (eg, while initialising with cap tokens).

We also report any GCS faults in VMAs not marked as part of a GCS as access violations, causing a fault to be delivered to userspace if it attempts to do GCS operations outside a GCS.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/mm/fault.c | 75 +++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 67 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3fe516b32577..facade819abb 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -494,13 +494,30 @@ static void do_bad_area(unsigned long far, unsigned long esr, } }

+/* + * Note: not valid for EL1 DC IVAC, but we never use that such that it + * should fault. EL0 cannot issue DC IVAC (undef). + */ +static bool is_write_abort(unsigned long esr) +{ + return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); +} + +static bool is_gcs_fault(unsigned long esr) +{ + if (!esr_is_data_abort(esr)) + return false; + + return ESR_ELx_ISS2(esr) & ESR_ELx_GCS; +} + #define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) #define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000)

static vm_fault_t __do_page_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned int mm_flags, unsigned long vm_flags, - struct pt_regs *regs) + unsigned long esr, struct pt_regs *regs) { /* * Ok, we have a good vm_area for this memory access, so we can handle @@ -510,6 +527,26 @@ static vm_fault_t __do_page_fault(struct mm_struct *mm, */ if (!(vma->vm_flags & vm_flags)) return VM_FAULT_BADACCESS; + + if (vma->vm_flags & VM_SHADOW_STACK) { + /* + * Writes to a GCS must either be generated by a GCS + * operation or be from EL1. + */ + if (is_write_abort(esr) && + !(is_gcs_fault(esr) || is_el1_data_abort(esr))) + return VM_FAULT_BADACCESS; + } else { + /* + * GCS faults should never happen for pages that are + * not part of a GCS and the operation being attempted + * can never succeed. + */ + if (is_gcs_fault(esr)) + return VM_FAULT_BADACCESS; + } + + return handle_mm_fault(vma, addr, mm_flags, regs); }

@@ -518,13 +555,15 @@ static bool is_el0_instruction_abort(unsigned long esr) return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; }

-/* - * Note: not valid for EL1 DC IVAC, but we never use that such that it - * should fault. EL0 cannot issue DC IVAC (undef). - */ -static bool is_write_abort(unsigned long esr) +static bool is_invalid_el0_gcs_access(struct vm_area_struct *vma, u64 esr) { - return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); + if (!system_supports_gcs()) + return false; + if (likely(!(vma->vm_flags & VM_SHADOW_STACK))) + return false; + if (is_gcs_fault(esr)) + return false; + return is_write_abort(esr); }

static int __kprobes do_page_fault(unsigned long far, unsigned long esr, @@ -573,6 +612,13 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, /* If EPAN is absent then exec implies read */ if (!cpus_have_const_cap(ARM64_HAS_EPAN)) vm_flags |= VM_EXEC; + /* + * Upgrade read faults to write faults, GCS reads must + * occur on a page marked as GCS so we need to trigger + * copy on write always. + */ + if (is_gcs_fault(esr)) + mm_flags |= FAULT_FLAG_WRITE; }

if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) { @@ -595,6 +641,19 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, if (!vma) goto lock_mmap;

+ /* + * We get legitimate write faults for GCS pages from GCS + * operations and from EL1 writes to EL0 pages but just plain + * EL0 writes are invalid. Specifically check for this since + * as a result of upgrading read faults to write faults for + * CoW the mm core isn't able to distinguish these invalid + * writes. + */ + if (is_invalid_el0_gcs_access(vma, esr)) { + vma_end_read(vma); + goto lock_mmap; + } + if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); goto lock_mmap; @@ -624,7 +683,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, goto done; }

- fault = __do_page_fault(mm, vma, addr, mm_flags, vm_flags, regs); + fault = __do_page_fault(mm, vma, addr, mm_flags, vm_flags, esr, regs);

/* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) {

We do not currently have a mechanism to specify a new GCS for a new thread so when a thread is created which has GCS enabled allocate one for it. Since there is no current API for specifying the size of the GCS we follow the extensively discussed x86 implementation and allocate min(RLIMIT_STACK, 4G). Since the GCS only stores the call stack and not any variables this should be more than sufficient for most applications.

When allocating the stack we initialise GCSPR_EL0 to point to one entry below the end of the region allocated, this keeps the top entry of the stack 0 so software walking the GCS can easily detect the end of the region.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/gcs.h | 7 ++++++ arch/arm64/kernel/process.c | 30 ++++++++++++++++++++++++ arch/arm64/mm/gcs.c | 56 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 93 insertions(+)

diff --git a/arch/arm64/include/asm/gcs.h b/arch/arm64/include/asm/gcs.h index 04594ef59dad..4371a2f99b4a 100644 --- a/arch/arm64/include/asm/gcs.h +++ b/arch/arm64/include/asm/gcs.h @@ -58,6 +58,8 @@ static inline bool task_gcs_el0_enabled(struct task_struct *task) void gcs_set_el0_mode(struct task_struct *task); void gcs_free(struct task_struct *task); void gcs_preserve_current_state(void); +unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, + unsigned long clone_flags, size_t size);

#else

@@ -69,6 +71,11 @@ static inline bool task_gcs_el0_enabled(struct task_struct *task) static inline void gcs_set_el0_mode(struct task_struct *task) { } static inline void gcs_free(struct task_struct *task) { } static inline void gcs_preserve_current_state(void) { } +static inline unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, + unsigned long clone_flags, size_t size) +{ + return -ENOTSUPP; +}

#endif

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 0d07f78b6c85..ce0a68d3539f 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -283,9 +283,34 @@ static void flush_gcs(void) } }

+static int copy_thread_gcs(struct task_struct *p, unsigned long clone_flags, + size_t stack_size) +{ + unsigned long gcs; + + if (!system_supports_gcs()) + return 0; + + if (!task_gcs_el0_enabled(p)) + return 0; + + p->thread.gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0); + + gcs = gcs_alloc_thread_stack(p, clone_flags, stack_size); + if (IS_ERR_VALUE(gcs)) + return PTR_ERR((void *)gcs); + + return 0; +} + #else

static void flush_gcs(void) { } +static int copy_thread_gcs(struct task_struct *p, unsigned long clone_flags, + size_t stack_size) +{ + return 0; +}

#endif

@@ -367,6 +392,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) unsigned long stack_start = args->stack; unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); + int ret;

memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));

@@ -408,6 +434,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.uw.tp_value = tls; p->thread.tpidr2_el0 = 0; } + + ret = copy_thread_gcs(p, clone_flags, args->stack_size); + if (ret != 0) + return ret; } else { /* * A kthread has no context to ERET to, so ensure any buggy diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index b0a67efc522b..1e059c37088d 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -8,6 +8,62 @@ #include <asm/cpufeature.h> #include <asm/page.h>

+static unsigned long alloc_gcs(unsigned long addr, unsigned long size, + unsigned long token_offset, bool set_res_tok) +{ + int flags = MAP_ANONYMOUS | MAP_PRIVATE; + struct mm_struct *mm = current->mm; + unsigned long mapped_addr, unused; + + if (addr) + flags |= MAP_FIXED_NOREPLACE; + + mmap_write_lock(mm); + mapped_addr = do_mmap(NULL, addr, size, PROT_READ, flags, + VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL); + mmap_write_unlock(mm); + + return mapped_addr; +} + +static unsigned long gcs_size(unsigned long size) +{ + if (size) + return PAGE_ALIGN(size); + + /* Allocate RLIMIT_STACK with limits of PAGE_SIZE..4G */ + size = PAGE_ALIGN(min_t(unsigned long long, + rlimit(RLIMIT_STACK), SZ_4G)); + return max(PAGE_SIZE, size); +} + +unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, + unsigned long clone_flags, size_t size) +{ + unsigned long addr; + + if (!system_supports_gcs()) + return 0; + + if (!task_gcs_el0_enabled(tsk)) + return 0; + + if ((clone_flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM) + return 0; + + size = gcs_size(size); + + addr = alloc_gcs(0, size, 0, 0); + if (IS_ERR_VALUE(addr)) + return addr; + + tsk->thread.gcs_base = addr; + tsk->thread.gcs_size = size; + tsk->thread.gcspr_el0 = addr + size - sizeof(u64); + + return addr; +} + /* * Apply the GCS mode configured for the specified task to the * hardware.

As discussed extensively in the changelog for the addition of this syscall on x86 ("x86/shstk: Introduce map_shadow_stack syscall") the existing mmap() and madvise() syscalls do not map entirely well onto the security requirements for guarded control stacks since they lead to windows where memory is allocated but not yet protected or stacks which are not properly and safely initialised. Instead a new syscall map_shadow_stack() has been defined which allocates and initialises a shadow stack page.

Implement this for arm64, initialising memory allocated this way with the top two entries in the stack being 0 (to allow detection of the end of the GCS) and a GCS cap token (to allow switching to the newly allocated GCS via the GCS switch instructions).

Since the x86 code has not yet been rebased to v6.5-rc1 this includes the architecture neutral parts of Rick Edgecmbe's "x86/shstk: Introduce map_shadow_stack syscall".

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/mm/gcs.c | 44 ++++++++++++++++++++++++++++++++++++++- include/linux/syscalls.h | 1 + include/uapi/asm-generic/unistd.h | 5 ++++- kernel/sys_ni.c | 1 + 4 files changed, 49 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index b137493c594d..4a0a736800c0 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -52,7 +52,6 @@ unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, return 0;

size = gcs_size(size); - addr = alloc_gcs(0, size, 0, 0); if (IS_ERR_VALUE(addr)) return addr; @@ -64,6 +63,49 @@ unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, return addr; }

+SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags) +{ + unsigned long aligned_size; + unsigned long __user *cap_ptr; + unsigned long cap_val; + int ret; + + if (!system_supports_gcs()) + return -EOPNOTSUPP; + + if (flags) + return -EINVAL; + + /* + * An overflow would result in attempting to write the restore token + * to the wrong location. Not catastrophic, but just return the right + * error code and block it. + */ + aligned_size = PAGE_ALIGN(size); + if (aligned_size < size) + return -EOVERFLOW; + + addr = alloc_gcs(addr, aligned_size, 0, false); + if (IS_ERR_VALUE(addr)) + return addr; + + /* + * Put a cap token at the end of the allocated region so it + * can be switched to. + */ + cap_ptr = (unsigned long __user *)(addr + aligned_size - + (2 * sizeof(unsigned long))); + cap_val = GCS_CAP(cap_ptr); + + ret = copy_to_user_gcs(cap_ptr, &cap_val, 1); + if (ret != 0) { + vm_munmap(addr, size); + return -EFAULT; + } + + return addr; +} + /* * Apply the GCS mode configured for the specified task to the * hardware. diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 03e3d0121d5e..7f6dc0988197 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -953,6 +953,7 @@ asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long l asmlinkage long sys_cachestat(unsigned int fd, struct cachestat_range __user *cstat_range, struct cachestat __user *cstat, unsigned int flags); +asmlinkage long sys_map_shadow_stack(unsigned long addr, unsigned long size, unsigned int flags);

/* * Architecture-specific system calls diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index fd6c1cb585db..38885a795ea6 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -820,8 +820,11 @@ __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) #define __NR_cachestat 451 __SYSCALL(__NR_cachestat, sys_cachestat)

+#define __NR_map_shadow_stack 452 +__SYSCALL(__NR_map_shadow_stack, sys_map_shadow_stack) + #undef __NR_syscalls -#define __NR_syscalls 452 +#define __NR_syscalls 453

/* * 32 bit systems traditionally used different diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 781de7cc6a4e..e137c1385c56 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -274,6 +274,7 @@ COND_SYSCALL(vm86old); COND_SYSCALL(modify_ldt); COND_SYSCALL(vm86); COND_SYSCALL(kexec_file_load); +COND_SYSCALL(map_shadow_stack);

/* s390 */ COND_SYSCALL(s390_pci_mmio_read);

When invoking a signal handler we use the GCS configuration and stack for the current thread.

Since we implement signal return by calling the signal handler with a return address set up pointing to a trampoline in the vDSO we need to also configure any active GCS for this by pushing a frame for the trampoline onto the GCS. If we do not do this then signal return will generate a GCS protection fault.

In order to guard against attempts to bypass GCS protections via signal return we only allow returning with GCSPR_EL0 pointing to an address where it was previously preempted by a signal. We do this by pushing a cap onto the GCS, this takes the form of an architectural GCS cap token with the top bit set which we add on signal entry and validate and pop off on signal return. Since the top bit is set address validation for the token will fail if an attempt is made to use it with the stack switch instructions.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/gcs.h | 2 + arch/arm64/kernel/signal.c | 134 +++++++++++++++++++++++++++++++++++++++++-- arch/arm64/mm/gcs.c | 1 + 3 files changed, 132 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/gcs.h b/arch/arm64/include/asm/gcs.h index 8655ba8054c7..8ef2313522b4 100644 --- a/arch/arm64/include/asm/gcs.h +++ b/arch/arm64/include/asm/gcs.h @@ -8,6 +8,8 @@ #include <asm/types.h> #include <asm/uaccess.h>

+struct ksignal; + static inline void gcsb_dsync(void) { asm volatile(".inst 0xd503227f" : : : "memory"); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 0df8cc295ea5..922b694fa0aa 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -25,6 +25,7 @@ #include <asm/elf.h> #include <asm/exception.h> #include <asm/cacheflush.h> +#include <asm/gcs.h> #include <asm/ucontext.h> #include <asm/unistd.h> #include <asm/fpsimd.h> @@ -34,6 +35,36 @@ #include <asm/traps.h> #include <asm/vdso.h>

+#ifdef CONFIG_ARM64_GCS +/* Extra bit set in the address distinguishing a signal cap token. */ +#define GCS_SIGNAL_CAP_FLAG BIT(63) + +#define GCS_SIGNAL_CAP(addr) (GCS_CAP(addr) | GCS_SIGNAL_CAP_FLAG) + +static bool gcs_signal_cap_valid(u64 addr, u64 val) +{ + /* + * The top bit should be set, this is an invalid address for + * EL0 and will only be set for caps created by signals. + */ + if (!(val & GCS_SIGNAL_CAP_FLAG)) + return false; + + /* The rest should be a standard architectural cap token. */ + val &= ~GCS_SIGNAL_CAP_FLAG; + + /* The cap must have the low bits set to a token value */ + if (GCS_CAP_TOKEN(val) != GCS_CAP_VALID_TOKEN) + return false; + + /* The cap must store the VA the cap was stored at */ + if (GCS_CAP_ADDR(addr) != GCS_CAP_ADDR(val)) + return false; + + return true; +} +#endif + /* * Do a signal return; undo the signal stack. These are aligned to 128-bit. */ @@ -815,6 +846,49 @@ static int restore_sigframe(struct pt_regs *regs, return err; }

+#ifdef CONFIG_ARM64_GCS +static int gcs_restore_signal(void) +{ + u64 gcspr_el0, cap; + int ret; + + if (!system_supports_gcs()) + return 0; + + if (!(current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE)) + return 0; + + /* + * We are exiting from a signal, the in memory state will be the + * most up to date value. + */ + gcspr_el0 = current->thread.gcspr_el0; + + /* + * GCSPR_EL0 should be pointing at a capped GCS, read the cap... + */ + gcsb_dsync(); + ret = copy_from_user(&cap, (__user void*)gcspr_el0, sizeof(cap)); + if (ret) + return -EFAULT; + + /* + * ...then check that the cap is the actual GCS before + * restoring it. + */ + if (!gcs_signal_cap_valid(gcspr_el0, cap)) + return -EINVAL; + + current->thread.gcspr_el0 = gcspr_el0 + sizeof(cap); + write_sysreg_s(current->thread.gcspr_el0, SYS_GCSPR_EL0); + + return 0; +} + +#else +static int gcs_restore_signal(void) { return 0; } +#endif + SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); @@ -841,6 +915,9 @@ SYSCALL_DEFINE0(rt_sigreturn) if (restore_altstack(&frame->uc.uc_stack)) goto badframe;

+ if (gcs_restore_signal()) + goto badframe; + return regs->regs[0];

badframe: @@ -1071,7 +1148,52 @@ static int get_sigframe(struct rt_sigframe_user_layout *user, return 0; }

-static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, +#ifdef CONFIG_ARM64_GCS + +static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig) +{ + unsigned long __user *gcspr_el0; + unsigned long cap[2]; + int ret; + + if (!system_supports_gcs()) + return 0; + + if (!task_gcs_el0_enabled(current)) + return 0; + + /* + * We are entering a signal handler, current register state is + * active. + */ + gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0); + + /* + * Push a cap and the GCS entry for the trampoline onto the GCS. + */ + cap[1] = GCS_SIGNAL_CAP(gcspr_el0 - 1); + cap[0] = (unsigned long)sigtramp; + ret = copy_to_user_gcs(gcspr_el0 - 2, cap, ARRAY_SIZE(cap)); + if (ret != 0) + return ret; + + gcsb_dsync(); + + gcspr_el0 -= 2; + write_sysreg_s((unsigned long)gcspr_el0, SYS_GCSPR_EL0); + + return 0; +} +#else + +static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig) +{ + return 0; +} + +#endif + +static int setup_return(struct pt_regs *regs, struct ksignal *ksig, struct rt_sigframe_user_layout *user, int usig) { __sigrestore_t sigtramp; @@ -1079,7 +1201,7 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, regs->regs[0] = usig; regs->sp = (unsigned long)user->sigframe; regs->regs[29] = (unsigned long)&user->next_frame->fp; - regs->pc = (unsigned long)ka->sa.sa_handler; + regs->pc = (unsigned long)ksig->ka.sa.sa_handler;

/* * Signal delivery is a (wacky) indirect function call in @@ -1119,12 +1241,14 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, sme_smstop(); }

- if (ka->sa.sa_flags & SA_RESTORER) - sigtramp = ka->sa.sa_restorer; + if (ksig->ka.sa.sa_flags & SA_RESTORER) + sigtramp = ksig->ka.sa.sa_restorer; else sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp);

regs->regs[30] = (unsigned long)sigtramp; + + return gcs_signal_entry(sigtramp, ksig); }

static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, @@ -1147,7 +1271,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, err |= __save_altstack(&frame->uc.uc_stack, regs->sp); err |= setup_sigframe(&user, regs, set); if (err == 0) { - setup_return(regs, &ksig->ka, &user, usig); + err = setup_return(regs, ksig, &user, usig); if (ksig->ka.sa.sa_flags & SA_SIGINFO) { err |= copy_siginfo_to_user(&frame->info, &ksig->info); regs->regs[1] = (unsigned long)&frame->info; diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index 4a0a736800c0..ac7013fb05f3 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -6,6 +6,7 @@ #include <linux/types.h>

#include <asm/cpufeature.h> +#include <asm/gcs.h> #include <asm/page.h>

static unsigned long alloc_gcs(unsigned long addr, unsigned long size,

Provide a new register type NT_ARM_GCS reporting the current GCS mode and pointer for EL0. Due to the interactions with allocation and deallocation of Guarded Control Stacks we do not permit any changes to the GCS mode via ptrace, only GCSPR_EL0 may be changed.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/uapi/asm/ptrace.h | 7 +++++ arch/arm64/kernel/ptrace.c | 50 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 3 files changed, 58 insertions(+)

diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 7fa2f7036aa7..342d5abaca87 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -324,6 +324,13 @@ struct user_za_header { #define ZA_PT_SIZE(vq) \ (ZA_PT_ZA_OFFSET + ZA_PT_ZA_SIZE(vq))

+/* GCS state (NT_ARM_GCS) */ + +struct user_gcs { + __u64 features_enabled; + __u64 gcspr_el0; +}; + #endif /* __ASSEMBLY__ */

#endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index d7f4f0d1ae12..09f671b8f188 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -33,6 +33,7 @@ #include <asm/cpufeature.h> #include <asm/debug-monitors.h> #include <asm/fpsimd.h> +#include <asm/gcs.h> #include <asm/mte.h> #include <asm/pointer_auth.h> #include <asm/stacktrace.h> @@ -1390,6 +1391,42 @@ static int tagged_addr_ctrl_set(struct task_struct *target, const struct } #endif

+#ifdef CONFIG_ARM64_GCS +static int gcs_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct user_gcs user_gcs; + + if (target == current) + gcs_preserve_current_state(); + + user_gcs.features_enabled = target->thread.gcs_el0_mode; + user_gcs.gcspr_el0 = target->thread.gcspr_el0; + + return membuf_write(&to, &user_gcs, sizeof(user_gcs)); +} + +static int gcs_set(struct task_struct *target, const struct + user_regset *regset, unsigned int pos, + unsigned int count, const void *kbuf, const + void __user *ubuf) +{ + int ret; + struct user_gcs user_gcs; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_gcs, 0, -1); + if (ret) + return ret; + + if (user_gcs.features_enabled != target->thread.gcs_el0_mode) + return -EBUSY; + target->thread.gcspr_el0 = user_gcs.gcspr_el0; + + return 0; +} +#endif + enum aarch64_regset { REGSET_GPR, REGSET_FPR, @@ -1418,6 +1455,9 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI REGSET_TAGGED_ADDR_CTRL, #endif +#ifdef CONFIG_ARM64_GCS + REGSET_GCS, +#endif };

static const struct user_regset aarch64_regsets[] = { @@ -1568,6 +1608,16 @@ static const struct user_regset aarch64_regsets[] = { .set = tagged_addr_ctrl_set, }, #endif +#ifdef CONFIG_ARM64_GCS + [REGSET_GCS] = { + .core_note_type = NT_ARM_GCS, + .n = sizeof(struct user_gcs) / sizeof(u64), + .size = sizeof(u64), + .align = sizeof(u64), + .regset_get = gcs_get, + .set = gcs_set, + }, +#endif };

static const struct user_regset_view user_aarch64_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 0c8cf359ea5b..00f698a2ab17 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -438,6 +438,7 @@ typedef struct elf64_shdr { #define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ #define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARM_ZT 0x40d /* ARM SME ZT registers */ +#define NT_ARM_GCS 0x40e /* ARM GCS state */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */

In preparation for testing GCS related signal handling add it as a feature we check for in the signal handling support code.

Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/arm64/signal/test_signals.h | 2 ++ tools/testing/selftests/arm64/signal/test_signals_utils.c | 3 +++ 2 files changed, 5 insertions(+)

diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h index 1e6273d81575..7ada43688c02 100644 --- a/tools/testing/selftests/arm64/signal/test_signals.h +++ b/tools/testing/selftests/arm64/signal/test_signals.h @@ -35,6 +35,7 @@ enum { FSME_BIT, FSME_FA64_BIT, FSME2_BIT, + FGCS_BIT, FMAX_END };

@@ -43,6 +44,7 @@ enum { #define FEAT_SME (1UL << FSME_BIT) #define FEAT_SME_FA64 (1UL << FSME_FA64_BIT) #define FEAT_SME2 (1UL << FSME2_BIT) +#define FEAT_GCS (1UL << FGCS_BIT)

/* * A descriptor used to describe and configure a test case. diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 0dc948db3a4a..89ef95c1af0e 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -30,6 +30,7 @@ static char const *const feats_names[FMAX_END] = { " SME ", " FA64 ", " SME2 ", + " GCS ", };

#define MAX_FEATS_SZ 128 @@ -329,6 +330,8 @@ int test_init(struct tdescr *td) td->feats_supported |= FEAT_SME_FA64; if (getauxval(AT_HWCAP2) & HWCAP2_SME2) td->feats_supported |= FEAT_SME2; + if (getauxval(AT_HWCAP2) & HWCAP2_GCS) + td->feats_supported |= FEAT_GCS; if (feats_ok(td)) { if (td->feats_required & td->feats_supported) fprintf(stderr,

Currently we ignore si_code unless the expected signal is a SIGSEGV, in which case we enforce it being SEGV_ACCERR. Allow test cases to specify exactly which si_code should be generated so we can validate this, and test for other segfault codes.

Signed-off-by: Mark Brown broonie@kernel.org --- .../testing/selftests/arm64/signal/test_signals.h | 4 +++ .../selftests/arm64/signal/test_signals_utils.c | 29 ++++++++++++++-------- 2 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h index 7ada43688c02..ee75a2c25ce7 100644 --- a/tools/testing/selftests/arm64/signal/test_signals.h +++ b/tools/testing/selftests/arm64/signal/test_signals.h @@ -71,6 +71,10 @@ struct tdescr { * Zero when no signal is expected on success */ int sig_ok; + /* + * expected si_code for sig_ok, or 0 to not check + */ + int sig_ok_code; /* signum expected on unsupported CPU features. */ int sig_unsupp; /* a timeout in second for test completion */ diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 89ef95c1af0e..63deca32b0df 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -143,16 +143,25 @@ static bool handle_signal_ok(struct tdescr *td, "current->token ZEROED...test is probably broken!\n"); abort(); } - /* - * Trying to narrow down the SEGV to the ones generated by Kernel itself - * via arm64_notify_segfault(). This is a best-effort check anyway, and - * the si_code check may need to change if this aspect of the kernel - * ABI changes. - */ - if (td->sig_ok == SIGSEGV && si->si_code != SEGV_ACCERR) { - fprintf(stdout, - "si_code != SEGV_ACCERR...test is probably broken!\n"); - abort(); + if (td->sig_ok_code) { + if (si->si_code != td->sig_ok_code) { + fprintf(stdout, "si_code is %d not %d\n", + si->si_code, td->sig_ok_code); + abort(); + } + } else { + /* + * Trying to narrow down the SEGV to the ones + * generated by Kernel itself via + * arm64_notify_segfault(). This is a best-effort + * check anyway, and the si_code check may need to + * change if this aspect of the kernel ABI changes. + */ + if (td->sig_ok == SIGSEGV && si->si_code != SEGV_ACCERR) { + fprintf(stdout, + "si_code != SEGV_ACCERR...test is probably broken!\n"); + abort(); + } } td->pass = 1; /*

This test program just covers the basic GCS ABI, covering aspects of the ABI as standalone features without attempting to integrate things.

Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/arm64/Makefile | 2 +- tools/testing/selftests/arm64/gcs/.gitignore | 1 + tools/testing/selftests/arm64/gcs/Makefile | 17 ++ tools/testing/selftests/arm64/gcs/basic-gcs.c | 350 ++++++++++++++++++++++++++ tools/testing/selftests/arm64/gcs/gcs-util.h | 65 +++++ 5 files changed, 434 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile index 9460cbe81bcc..fd5d8d85aecb 100644 --- a/tools/testing/selftests/arm64/Makefile +++ b/tools/testing/selftests/arm64/Makefile @@ -4,7 +4,7 @@ ARCH ?= $(shell uname -m 2>/dev/null || echo not)

ifneq (,$(filter $(ARCH),aarch64 arm64)) -ARM64_SUBTARGETS ?= tags signal pauth fp mte bti abi +ARM64_SUBTARGETS ?= tags signal pauth fp mte bti abi gcs else ARM64_SUBTARGETS := endif diff --git a/tools/testing/selftests/arm64/gcs/.gitignore b/tools/testing/selftests/arm64/gcs/.gitignore new file mode 100644 index 000000000000..0e5e695ecba5 --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/.gitignore @@ -0,0 +1 @@ +basic-gcs diff --git a/tools/testing/selftests/arm64/gcs/Makefile b/tools/testing/selftests/arm64/gcs/Makefile new file mode 100644 index 000000000000..322c40d25f2e --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/Makefile @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2023 ARM Limited +# +# In order to avoid interaction with the toolchain and dynamic linker the +# portions of these tests that interact with the GCS are implemented using +# nolibc. +# + +TEST_GEN_PROGS := basic-gcs + +include ../../lib.mk + +$(OUTPUT)/basic-gcs: basic-gcs.c + $(CC) -g -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ + -static -include ../../../../include/nolibc/nolibc.h \ + -std=gnu99 -I../.. -g \ + -ffreestanding -Wall $^ -o $@ -lgcc diff --git a/tools/testing/selftests/arm64/gcs/basic-gcs.c b/tools/testing/selftests/arm64/gcs/basic-gcs.c new file mode 100644 index 000000000000..1cc14836c991 --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/basic-gcs.c @@ -0,0 +1,350 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 ARM Limited. + */ + +#include <limits.h> +#include <stdbool.h> + +#include <linux/prctl.h> + +#include "kselftest.h" +#include "gcs-util.h" + +/* nolibc doesn't have sysconf(), just hard code the maximum */ +static size_t page_size = 65536; + +static __attribute__((noinline)) void valid_gcs_function(void) +{ + /* Do something the compiler can't optimise out */ + my_syscall1(__NR_prctl, PR_SVE_GET_VL); +} + +static inline int gcs_set_status(unsigned long mode) +{ + int ret; + unsigned long new_mode; + + /* + * The prctl takes 1 argument but we need to ensure that the + * other 3 values passed in registers to the syscall are zero + * since the kernel validates them. + */ + ret = my_syscall5(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, mode, + 0, 0, 0); + + if (ret == 0) { + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, + &new_mode, 0, 0, 0); + if (ret == 0) { + if (new_mode != mode) { + ksft_print_msg("Mode set to %x not %x\n", + new_mode, mode); + ret = -EINVAL; + } + } else { + ksft_print_msg("Failed to validate mode: %d\n", ret); + } + } + + return ret; +} + +/* Try to read the status */ +static bool read_status(void) +{ + unsigned long state; + int ret; + + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, + &state, 0, 0, 0); + if (ret != 0) { + ksft_print_msg("Failed to read state: %d\n", ret); + return false; + } + + return state & PR_SHADOW_STACK_ENABLE; +} + +/* Just a straight enable */ +static bool base_enable(void) +{ + int ret; + + ret = gcs_set_status(PR_SHADOW_STACK_ENABLE); + if (ret) { + ksft_print_msg("PR_SHADOW_STACK_ENABLE failed %d\n", ret); + return false; + } + + return true; +} + +/* Check we can read GCSPR_EL0 when GCS is enabled */ +static bool read_gcspr_el0(void) +{ + unsigned long *gcspr_el0; + + ksft_print_msg("GET GCSPR\n"); + gcspr_el0 = get_gcspr(); + ksft_print_msg("GCSPR_EL0 is %p\n", gcspr_el0); + + return true; +} + +/* Also allow writes to stack */ +static bool enable_writeable(void) +{ + int ret; + + ret = gcs_set_status(PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE); + if (ret) { + ksft_print_msg("PR_SHADOW_STACK_ENABLE writeable failed: %d\n", ret); + return false; + } + + ret = gcs_set_status(PR_SHADOW_STACK_ENABLE); + if (ret) { + ksft_print_msg("failed to restore plain enable %d\n", ret); + return false; + } + + return true; +} + +/* Also allow writes to stack */ +static bool enable_push_pop(void) +{ + int ret; + + ret = gcs_set_status(PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_PUSH); + if (ret) { + ksft_print_msg("PR_SHADOW_STACK_ENABLE with push failed: %d\n", + ret); + return false; + } + + ret = gcs_set_status(PR_SHADOW_STACK_ENABLE); + if (ret) { + ksft_print_msg("failed to restore plain enable %d\n", ret); + return false; + } + + return true; +} + +/* Enable GCS and allow everything */ +static bool enable_all(void) +{ + int ret; + + ret = gcs_set_status(PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_PUSH | + PR_SHADOW_STACK_WRITE); + if (ret) { + ksft_print_msg("PR_SHADOW_STACK_ENABLE with everything failed: %d\n", + ret); + return false; + } + + ret = gcs_set_status(PR_SHADOW_STACK_ENABLE); + if (ret) { + ksft_print_msg("failed to restore plain enable %d\n", ret); + return false; + } + + return true; +} + +static bool enable_invalid(void) +{ + int ret = gcs_set_status(ULONG_MAX); + if (ret == 0) { + ksft_print_msg("GCS_SET_STATUS %lx succeeded\n", ULONG_MAX); + return false; + } + + return true; +} + +/* Map a GCS */ +static bool map_guarded_stack(void) +{ + int ret; + uint64_t *buf; + uint64_t expected_cap; + int elem; + bool pass = true; + + buf = (void *)my_syscall3(__NR_map_shadow_stack, 0, page_size, 0); + if (buf == MAP_FAILED) { + ksft_print_msg("Failed to map %d byte GCS: %d\n", + page_size, errno); + return false; + } + ksft_print_msg("Mapped GCS at %p-%p\n", buf, + (uint64_t)buf + page_size); + + /* The top of the newly allocated region should be 0 */ + elem = (page_size / sizeof(uint64_t)) - 1; + if (buf[elem]) { + ksft_print_msg("Last entry is 0x%lx not 0x0\n", buf[elem]); + pass = false; + } + + /* Then a valid cap token */ + elem--; + expected_cap = ((uint64_t)buf + page_size - 16); + expected_cap &= GCS_CAP_ADDR_MASK; + expected_cap |= GCS_CAP_VALID_TOKEN; + if (buf[elem] != expected_cap) { + ksft_print_msg("Cap entry is 0x%lx not 0x%lx\n", + buf[elem], expected_cap); + pass = false; + } + ksft_print_msg("cap token is 0x%lx\n", buf[elem]); + + /* The rest should be zeros */ + for (elem = 0; elem < page_size / sizeof(uint64_t) - 2; elem++) { + if (!buf[elem]) + continue; + ksft_print_msg("GCS slot %d is 0x%lx not 0x0\n", + elem, buf[elem]); + pass = false; + } + + ret = munmap(buf, page_size); + if (ret != 0) { + ksft_print_msg("Failed to unmap %d byte GCS: %d\n", + page_size, errno); + pass = false; + } + + return pass; +} + +/* A fork()ed process can run */ +static bool test_fork(void) +{ + unsigned long child_mode; + int ret, status; + pid_t pid; + bool pass = true; + + pid = fork(); + if (pid == -1) { + ksft_print_msg("fork() failed: %d\n", errno); + pass = false; + goto out; + } + if (pid == 0) { + /* In child, make sure we can call a function, read + * the GCS pointer and status and then exit */ + valid_gcs_function(); + get_gcspr(); + + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, + &child_mode, 0, 0, 0); + if (ret == 0 && !(child_mode & PR_SHADOW_STACK_ENABLE)) { + ksft_print_msg("GCS not enabled in child\n"); + ret = -EINVAL; + } + + exit(ret); + } + + /* + * In parent, check we can still do function calls then block + * for the child. + */ + valid_gcs_function(); + + ksft_print_msg("Waiting for child %d\n", pid); + + ret = waitpid(pid, &status, 0); + if (ret == -1) { + ksft_print_msg("Failed to wait for child: %d\n", + errno); + return false; + } + + if (!WIFEXITED(status)) { + ksft_print_msg("Child exited due to signal %d\n", + WTERMSIG(status)); + pass = false; + } else { + if (WEXITSTATUS(status)) { + ksft_print_msg("Child exited with status %d\n", + WEXITSTATUS(status)); + pass = false; + } + } + +out: + + return pass; +} + +typedef bool (*gcs_test)(void); + +static struct { + char *name; + gcs_test test; + bool needs_enable; +} tests[] = { + { "read_status", read_status }, + { "base_enable", base_enable, true }, + { "read_gcspr_el0", read_gcspr_el0 }, + { "enable_writeable", enable_writeable, true }, + { "enable_push_pop", enable_push_pop, true }, + { "enable_all", enable_all, true }, + { "enable_invalid", enable_invalid, true }, + { "map_guarded_stack", map_guarded_stack }, + { "fork", test_fork }, +}; + +int main(void) +{ + int i, ret; + unsigned long gcs_mode; + bool gcs_locked; + + ksft_print_header(); + + /* + * We don't have getauxval() with nolibc so treat a failure to + * read GCS state as a lack of support and skip. + */ + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, + &gcs_mode, 0, 0, 0); + if (ret != 0) + ksft_exit_skip("Failed to read GCS state: %d\n", ret); + + if (!(gcs_mode & PR_SHADOW_STACK_ENABLE)) { + gcs_mode = PR_SHADOW_STACK_ENABLE; + ret = my_syscall5(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, + gcs_mode, 0, 0, 0); + if (ret != 0) + ksft_exit_fail_msg("Failed to enable GCS: %d\n", ret); + } + + gcs_locked = gcs_mode & PR_SHADOW_STACK_LOCK; + + ksft_set_plan(ARRAY_SIZE(tests)); + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + if (gcs_locked && tests[i].needs_enable) + ksft_test_result_skip("%s\n", tests[i].name); + else + ksft_test_result((*tests[i].test)(), "%s\n", + tests[i].name); + } + + /* One last test: disable GCS, we can do this one time */ + my_syscall5(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, 0, 0, 0, 0); + if (ret != 0) + ksft_print_msg("Failed to disable GCS: %d\n", ret); + + ksft_finished(); + + return 0; +} diff --git a/tools/testing/selftests/arm64/gcs/gcs-util.h b/tools/testing/selftests/arm64/gcs/gcs-util.h new file mode 100644 index 000000000000..90130c77463e --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/gcs-util.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 ARM Limited. + */ + +#ifndef GCS_UTIL_H +#define GCS_UTIL_H + +#include <stdbool.h> + +#ifndef __NR_map_shadow_stack +#define __NR_map_shadow_stack 452 +#endif + +#ifndef __NR_prctl +#define __NR_prctl 167 +#endif + +/* Shadow Stack/Guarded Control Stack interface */ +#define PR_GET_SHADOW_STACK_STATUS 71 +#define PR_SET_SHADOW_STACK_STATUS 72 +# define PR_SHADOW_STACK_LOCK (1UL << 0) +# define PR_SHADOW_STACK_ENABLE (1UL << 1) +# define PR_SHADOW_STACK_WRITE (1UL << 2) +# define PR_SHADOW_STACK_PUSH (1UL << 3) + +#define GCS_CAP_ADDR_MASK (0xfffffffffffff000UL) +#define GCS_CAP_VALID_TOKEN 1 + +static unsigned long *get_gcspr(void) +{ + unsigned long *gcspr; + + asm volatile( + "mrs %0, S3_3_C2_C5_1" + : "=r" (gcspr) + : + : "cc"); + + return gcspr; +} + +static inline void __attribute__((always_inline)) gcsss1(unsigned long Xt) +{ + asm volatile ( + "sys #3, C7, C7, #2, %0\n" + : + : "rZ" (Xt) + : "memory"); +} + +static inline unsigned long __attribute__((always_inline)) gcsss2(void) +{ + unsigned long Xt; + + asm volatile( + "SYSL %0, #3, C7, C7, #3\n" + : "=r" (Xt) + : + : "memory"); + + return Xt; +} + +#endif

Do some testing of the signal handling for GCS, checking that a GCS frame has the expected information in it and that the expected signals are delivered with invalid operations.

Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/arm64/signal/.gitignore | 1 + .../selftests/arm64/signal/test_signals_utils.h | 10 +++ .../arm64/signal/testcases/gcs_exception_fault.c | 59 ++++++++++++++++ .../selftests/arm64/signal/testcases/gcs_frame.c | 78 ++++++++++++++++++++++ .../arm64/signal/testcases/gcs_write_fault.c | 67 +++++++++++++++++++ 5 files changed, 215 insertions(+)

diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index 839e3a252629..26de12918890 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only mangle_* fake_sigreturn_* +gcs_* sme_* ssve_* sve_* diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h index 1cea64986baa..d41f237db28d 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.h +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h @@ -6,6 +6,7 @@

#include <assert.h> #include <stdio.h> +#include <stdint.h> #include <string.h>

#include "test_signals.h" @@ -45,6 +46,15 @@ void test_result(struct tdescr *td); _arg1; \ })

+static inline __attribute__((always_inline)) uint64_t get_gcspr_el0(void) +{ + uint64_t val; + + asm volatile("mrs %0, S3_3_C2_C5_1" : "=r" (val)); + + return val; +} + static inline bool feats_ok(struct tdescr *td) { if (td->feats_incompatible & td->feats_supported) diff --git a/tools/testing/selftests/arm64/signal/testcases/gcs_exception_fault.c b/tools/testing/selftests/arm64/signal/testcases/gcs_exception_fault.c new file mode 100644 index 000000000000..532d533592a1 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/gcs_exception_fault.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 ARM Limited + */ + +#include <errno.h> +#include <signal.h> +#include <unistd.h> + +#include <sys/mman.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +/* This should be includable from some standard header, but which? */ +#ifndef SEGV_CPERR +#define SEGV_CPERR 10 +#endif + +static inline void gcsss1(uint64_t Xt) +{ + asm volatile ( + "sys #3, C7, C7, #2, %0\n" + : + : "rZ" (Xt) + : "memory"); +} + +static int gcs_op_fault_trigger(struct tdescr *td) +{ + /* + * The slot below our current GCS should be in a valid GCS but + * must not have a valid cap in it. + */ + gcsss1(get_gcspr_el0() - 8); + + return 0; +} + +static int gcs_op_fault_signal(struct tdescr *td, siginfo_t *si, + ucontext_t *uc) +{ + ASSERT_GOOD_CONTEXT(uc); + + return 1; +} + +struct tdescr tde = { + .name = "Invalid GCS operation", + .descr = "An invalid GCS operation generates the expected signal", + .feats_required = FEAT_GCS, + .timeout = 3, + .sig_ok = SIGSEGV, + .sig_ok_code = SEGV_CPERR, + .sanity_disabled = true, + .trigger = gcs_op_fault_trigger, + .run = gcs_op_fault_signal, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/gcs_frame.c b/tools/testing/selftests/arm64/signal/testcases/gcs_frame.c new file mode 100644 index 000000000000..d67cb26195a6 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/gcs_frame.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 ARM Limited + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +static union { + ucontext_t uc; + char buf[1024 * 64]; +} context; + +static int gcs_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + size_t offset; + struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context); + struct gcs_context *gcs; + unsigned long expected, gcspr; + int ret; + + ret = prctl(PR_GET_SHADOW_STACK_STATUS, &expected, 0, 0, 0); + if (ret != 0) { + fprintf(stderr, "Unable to query GCS status\n"); + return 1; + } + + /* We expect a cap to be added to the GCS in the signal frame */ + gcspr = get_gcspr_el0(); + gcspr -= 8; + fprintf(stderr, "Expecting GCSPR_EL0 %lx\n", gcspr); + + if (!get_current_context(td, &context.uc, sizeof(context))) { + fprintf(stderr, "Failed getting context\n"); + return 1; + } + fprintf(stderr, "Got context\n"); + + head = get_header(head, GCS_MAGIC, GET_BUF_RESV_SIZE(context), + &offset); + if (!head) { + fprintf(stderr, "No GCS context\n"); + return 1; + } + + gcs = (struct gcs_context *)head; + + /* Basic size validation is done in get_current_context() */ + + if (gcs->features_enabled != expected) { + fprintf(stderr, "Features enabled %llx but expected %lx\n", + gcs->features_enabled, expected); + return 1; + } + + if (gcs->gcspr != gcspr) { + fprintf(stderr, "Got GCSPR %llx but expected %lx\n", + gcs->gcspr, gcspr); + return 1; + } + + fprintf(stderr, "GCS context validated\n"); + td->pass = 1; + + return 0; +} + +struct tdescr tde = { + .name = "GCS basics", + .descr = "Validate a GCS signal context", + .feats_required = FEAT_GCS, + .timeout = 3, + .run = gcs_regs, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/gcs_write_fault.c b/tools/testing/selftests/arm64/signal/testcases/gcs_write_fault.c new file mode 100644 index 000000000000..126b1a294a29 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/gcs_write_fault.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 ARM Limited + */ + +#include <errno.h> +#include <signal.h> +#include <unistd.h> + +#include <sys/mman.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +static uint64_t *gcs_page; + +#ifndef __NR_map_shadow_stack +#define __NR_map_shadow_stack 452 +#endif + +static bool alloc_gcs(struct tdescr *td) +{ + long page_size = sysconf(_SC_PAGE_SIZE); + + gcs_page = (void *)syscall(__NR_map_shadow_stack, 0, + page_size, 0); + if (gcs_page == MAP_FAILED) { + fprintf(stderr, "Failed to map %ld byte GCS: %d\n", + page_size, errno); + return false; + } + + return true; +} + +static int gcs_write_fault_trigger(struct tdescr *td) +{ + /* Verify that the page is readable (ie, not completely unmapped) */ + fprintf(stderr, "Read value 0x%lx\n", gcs_page[0]); + + /* A regular write should trigger a fault */ + gcs_page[0] = EINVAL; + + return 0; +} + +static int gcs_write_fault_signal(struct tdescr *td, siginfo_t *si, + ucontext_t *uc) +{ + ASSERT_GOOD_CONTEXT(uc); + + return 1; +} + + +struct tdescr tde = { + .name = "GCS write fault", + .descr = "Normal writes to a GCS segfault", + .feats_required = FEAT_GCS, + .timeout = 3, + .sig_ok = SIGSEGV, + .sanity_disabled = true, + .init = alloc_gcs, + .trigger = gcs_write_fault_trigger, + .run = gcs_write_fault_signal, +};