Three architectures (x86, aarch64, riscv) have announced support for shadow stacks with fairly similar functionality. While x86 is using arch_prctl() to control the functionality neither arm64 nor riscv uses that interface so this patch adds arch-agnostic prctl() support to get and set status of shadow stacks and lock the current configuation to prevent further changes, with support for turning on and off individual subfeatures so applications can limit their exposure to features that they do not need. The features are:

- PR_SHADOW_STACK_ENABLE: Tracking and enforcement of shadow stacks, including allocation of a shadow stack if one is not already allocated. - PR_SHADOW_STACK_WRITE: Writes to specific addresses in the shadow stack. - PR_SHADOW_STACK_PUSH: Push additional values onto the shadow stack.

These features are expected to be inherited by new threads and cleared on exec(), unknown features should be rejected for enable but accepted for locking (in order to allow for future proofing).

This is based on a patch originally written by Deepak Gupta but modified fairly heavily, support for indirect landing pads is removed, additional modes added and the locking interface reworked. The set status prctl() is also reworked to just set flags, if setting/reading the shadow stack pointer is required this could be a separate prctl.

Signed-off-by: Mark Brown broonie@kernel.org --- include/linux/mm.h | 4 ++++ include/uapi/linux/prctl.h | 22 ++++++++++++++++++++++ kernel/sys.c | 30 ++++++++++++++++++++++++++++++ 3 files changed, 56 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h index 10462f354614..8b28483b4afa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4143,4 +4143,8 @@ static inline bool pfn_is_unaccepted_memory(unsigned long pfn) return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE); }

+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); +int arch_lock_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 370ed14b1ae0..3c66ed8f46d8 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -306,4 +306,26 @@ struct prctl_mm_map { # define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc # define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f

+/* + * Get the current shadow stack configuration for the current thread, + * this will be the value configured via PR_SET_SHADOW_STACK_STATUS. + */ +#define PR_GET_SHADOW_STACK_STATUS 71 + +/* + * Set the current shadow stack configuration. Enabling the shadow + * stack will cause a shadow stack to be allocated for the thread. + */ +#define PR_SET_SHADOW_STACK_STATUS 72 +# define PR_SHADOW_STACK_ENABLE (1UL << 0) +# define PR_SHADOW_STACK_WRITE (1UL << 1) +# define PR_SHADOW_STACK_PUSH (1UL << 2) + +/* + * Prevent further changes to the specified shadow stack + * configuration. All bits may be locked via this call, including + * undefined bits. + */ +#define PR_LOCK_SHADOW_STACK_STATUS 73 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index e219fcfa112d..96e8a6b5993a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2301,6 +2301,21 @@ 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; +} + +int __weak arch_lock_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 @@ -2743,6 +2758,21 @@ 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; + case PR_LOCK_SHADOW_STACK_STATUS: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_lock_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 96cbeeab4eec..d2ee46b63482 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -1790,6 +1790,41 @@ 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 @@ -2020,6 +2055,10 @@ 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 @@ -2348,6 +2387,14 @@ 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 @@ -2407,6 +2454,14 @@ 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 | 16 ++++++++++++++++ arch/arm64/tools/cpucaps | 1 + 3 files changed, 23 insertions(+)

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index f6d416fe49b0..5696a55cc1f8 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -819,6 +819,12 @@ static inline bool system_supports_tlb_range(void) return alternative_has_cap_unlikely(ARM64_HAS_TLB_RANGE); }

+static inline bool system_supports_gcs(void) +{ + return IS_ENABLED(CONFIG_ARM64_GCS) && + alternative_has_cap_unlikely(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 646591c67e7a..5477451cefa1 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -255,6 +255,8 @@ 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), @@ -2242,6 +2244,12 @@ 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) @@ -2731,6 +2739,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, EVT, IMP) }, + { + .desc = "Guarded Control Stack (GCS)", + .capability = ARM64_HAS_GCS, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .cpu_enable = cpu_enable_gcs, + .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, GCS, IMP) + }, {}, };

diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index b98c38288a9d..30d27f6301fd 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -28,6 +28,7 @@ HAS_EPAN HAS_EVT HAS_FGT HAS_FPSIMD +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 49ef12df631b..1dfc5cb20f28 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -570,7 +570,7 @@ 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 f0a904aeee8e..29fd7d6fbeb0 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -701,6 +701,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ #ifdef CONFIG_ARCH_HAS_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 8b28483b4afa..3c96fc6c1128 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -352,7 +352,17 @@ extern unsigned int kobjsize(const void *objp); * for more details on the guard size. */ # 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

There is a control HCRX_EL2.GCSEn which must be set to allow GCS features to take effect at lower ELs and also fine grained traps for GCS usage at EL0 and EL1. Configure all these to allow GCS usage by EL0 and EL1.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/el2_setup.h | 17 +++++++++++++++++ arch/arm64/include/asm/kvm_arm.h | 4 ++-- 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index b7afaa026842..17672563e333 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -27,6 +27,14 @@ ubfx x0, x0, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4 cbz x0, .Lskip_hcrx_@ mov_q x0, HCRX_HOST_FLAGS + + /* Enable GCS if supported */ + mrs_s x1, SYS_ID_AA64PFR1_EL1 + ubfx x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4 + cbz x1, .Lset_hcrx_@ + orr x0, x0, #HCRX_EL2_GCSEn + +.Lset_hcrx_@: msr_s SYS_HCRX_EL2, x0 .Lskip_hcrx_@: .endm @@ -190,6 +198,15 @@ orr x0, x0, #HFGxTR_EL2_nPIR_EL1 orr x0, x0, #HFGxTR_EL2_nPIRE0_EL1

+ /* GCS depends on PIE so we don't check it if PIE is absent */ + mrs_s x1, SYS_ID_AA64PFR1_EL1 + ubfx x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4 + cbz x1, .Lset_fgt_@ + + /* Disable traps of access to GCS registers at EL0 and EL1 */ + orr x0, x0, #HFGxTR_EL2_nGCS_EL1_MASK + orr x0, x0, #HFGxTR_EL2_nGCS_EL0_MASK + .Lset_fgt_@: msr_s SYS_HFGRTR_EL2, x0 msr_s SYS_HFGWTR_EL2, x0 diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index b85f46a73e21..e4b6a29879b7 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -103,9 +103,9 @@ #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)

#define HCRX_GUEST_FLAGS \ - (HCRX_EL2_SMPME | HCRX_EL2_TCR2En | \ + (HCRX_EL2_SMPME | HCRX_EL2_TCR2En | HCRX_EL2_GCSEn |\ (cpus_have_final_cap(ARM64_HAS_MOPS) ? (HCRX_EL2_MSCEn | HCRX_EL2_MCE2) : 0)) -#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En) +#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_GCSEn)

/* TCR_EL2 Registers bits */ #define TCR_EL2_RES1 ((1U << 31) | (1 << 23))

Provide a hwcap to enable userspace to detect support for GCS.

Signed-off-by: Mark Brown broonie@kernel.org --- Documentation/arch/arm64/elf_hwcaps.rst | 3 +++ arch/arm64/include/asm/hwcap.h | 1 + arch/arm64/include/uapi/asm/hwcap.h | 1 + arch/arm64/kernel/cpufeature.c | 3 +++ arch/arm64/kernel/cpuinfo.c | 1 + 5 files changed, 9 insertions(+)

diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index ced7b335e2e0..86d4ace9c75c 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -317,6 +317,9 @@ HWCAP2_LRCPC3 HWCAP2_LSE128 Functionality implied by ID_AA64ISAR0_EL1.Atomic == 0b0011.

+HWCAP2_GCS + Functionality implied by ID_AA64PFR1_EL1.GCS == 0b1 + 4. Unused AT_HWCAP bits -----------------------

diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index cd71e09ea14d..e01e6b72a839 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -142,6 +142,7 @@ #define KERNEL_HWCAP_SVE_B16B16 __khwcap2_feature(SVE_B16B16) #define KERNEL_HWCAP_LRCPC3 __khwcap2_feature(LRCPC3) #define KERNEL_HWCAP_LSE128 __khwcap2_feature(LSE128) +#define KERNEL_HWCAP_GCS __khwcap2_feature(GCS)

/* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 5023599fa278..996b5b5d4c4e 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -107,5 +107,6 @@ #define HWCAP2_SVE_B16B16 (1UL << 45) #define HWCAP2_LRCPC3 (1UL << 46) #define HWCAP2_LSE128 (1UL << 47) +#define HWCAP2_GCS (1UL << 48)

#endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 5477451cefa1..dab80391543f 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2859,6 +2859,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), HWCAP_CAP(ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), HWCAP_CAP(ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), +#endif +#ifdef CONFIG_ARM64_GCS + HWCAP_CAP(ID_AA64PFR1_EL1, GCS, IMP, CAP_HWCAP, KERNEL_HWCAP_GCS), #endif HWCAP_CAP(ID_AA64PFR1_EL1, SSBS, SSBS2, CAP_HWCAP, KERNEL_HWCAP_SSBS), #ifdef CONFIG_ARM64_BTI diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index a257da7b56fe..d557ee301464 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -130,6 +130,7 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SVE_B16B16] = "sveb16b16", [KERNEL_HWCAP_LRCPC3] = "lrcpc3", [KERNEL_HWCAP_LSE128] = "lse128", + [KERNEL_HWCAP_GCS] = "gcs", };

#ifdef CONFIG_COMPAT

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 | 79 +++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 71 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 460d799e1296..28de0807b4a1 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 +555,18 @@ 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))) { + if (is_gcs_fault(esr)) + return true; + 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 +615,13 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, /* If EPAN is absent then exec implies read */ if (!alternative_has_cap_unlikely(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)) { @@ -594,6 +643,20 @@ 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, even when the initial operation was a read, as + * a result of upgrading GCS accesses to writes for CoW but + * GCS acceses outside of a GCS must fail. Specifically check + * for this since the mm core isn't able to distinguish + * invalid GCS access from valid ones and will try to resolve + * the fault. + */ + 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; @@ -623,7 +686,7 @@ 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)) {

When a new thread is created by a thread with GCS enabled the GCS needs to be specified along with the regular stack. clone3() has been extended to support this case, allowing userspace to explicitly request the size for the GCS to be created, but plain clone() is not extensible and existing clone3() users will not specify a size.

For compatibility with these cases and also x86 (which did not initially implement clone3() support for shadow stacks) if no GCS is specified we will allocate one thread so when a thread is created which has GCS enabled allocate one for it. 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.

GCSs allocated via this mechanism then it will be freed when the thread exits.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/gcs.h | 9 ++++++ arch/arm64/kernel/process.c | 25 +++++++++++++++ arch/arm64/mm/gcs.c | 76 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 110 insertions(+)

diff --git a/arch/arm64/include/asm/gcs.h b/arch/arm64/include/asm/gcs.h index 04594ef59dad..c1f274fdb9c0 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 kernel_clone_args; + static inline void gcsb_dsync(void) { asm volatile(".inst 0xd503227f" : : : "memory"); @@ -58,6 +60,8 @@ 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, + const struct kernel_clone_args *args);

#else

@@ -69,6 +73,11 @@ 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, + const struct kernel_clone_args *args) +{ + return -ENOTSUPP; +}

#endif

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index fd80b43c2969..588d2bc4b329 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -285,9 +285,29 @@ static void flush_gcs(void) write_sysreg_s(0, SYS_GCSPR_EL0); }

+static int copy_thread_gcs(struct task_struct *p, + const struct kernel_clone_args *args) +{ + unsigned long gcs; + + gcs = gcs_alloc_thread_stack(p, args); + if (IS_ERR_VALUE(gcs)) + return PTR_ERR((void *)gcs); + + /* Ensure the current state of the GCS is seen by CoW */ + gcsb_dsync(); + + return 0; +} + #else

static void flush_gcs(void) { } +static int copy_thread_gcs(struct task_struct *p, + const struct kernel_clone_args *args) +{ + return 0; +}

#endif

@@ -369,6 +389,7 @@ 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));

@@ -410,6 +431,10 @@ 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, args); + 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..0d4881173b5f 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -8,6 +8,82 @@ #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 | PROT_WRITE, flags, + VM_SHADOW_STACK, 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/2 with limits of PAGE_SIZE..2G */ + size = PAGE_ALIGN(min_t(unsigned long long, + rlimit(RLIMIT_STACK) / 2, SZ_2G)); + return max(PAGE_SIZE, size); +} + +unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args) +{ + unsigned long addr, size; + + /* If the user specified a GCS use it. */ + if (args->shadow_stack_size) { + if (!system_supports_gcs()) + return (unsigned long)ERR_PTR(-EINVAL); + + size = args->shadow_stack_size; + + if (size < 8) + return (unsigned long)ERR_PTR(-EINVAL); + + } else { + /* + * Otherwise fall back to legacy clone() support and + * implicitly allocate a GCS if we need a new one. + */ + + if (!system_supports_gcs()) + return 0; + + if (!task_gcs_el0_enabled(tsk)) + return 0; + + if ((args->flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM) { + tsk->thread.gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0); + return 0; + } + + size = args->stack_size; + } + + 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.

Implement the architecture neutral prtctl() interface for setting the shadow stack status, this supports setting and reading the current GCS configuration for the current thread.

Userspace can enable basic GCS functionality and additionally also support for GCS pushes and arbatrary GCS stores. It is expected that this prctl() will be called very early in application startup, for example by the dynamic linker, and not subsequently adjusted during normal operation. Users should carefully note that after enabling GCS for a thread GCS will become active with no call stack so it is not normally possible to return from the function that invoked the prctl().

State is stored per thread, enabling GCS for a thread causes a GCS to be allocated for that thread.

Userspace may lock the current GCS configuration by specifying PR_SHADOW_STACK_ENABLE_LOCK, this prevents any further changes to the GCS configuration via any means.

If GCS is not being enabled then all flags other than _LOCK are ignored, it is not possible to enable stores or pops without enabling GCS.

When disabling the GCS we do not free the allocated stack, this allows for inspection of the GCS after disabling as part of fault reporting. Since it is not an expected use case and since it presents some complications in determining what to do with previously initialsed data on the GCS attempts to reenable GCS after this are rejected. This can be revisted if a use case arises.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/gcs.h | 22 ++++++++++ arch/arm64/include/asm/processor.h | 1 + arch/arm64/mm/gcs.c | 82 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 105 insertions(+)

diff --git a/arch/arm64/include/asm/gcs.h b/arch/arm64/include/asm/gcs.h index c1f274fdb9c0..48c97e63e56a 100644 --- a/arch/arm64/include/asm/gcs.h +++ b/arch/arm64/include/asm/gcs.h @@ -50,6 +50,9 @@ static inline u64 gcsss2(void) return Xt; }

+#define PR_SHADOW_STACK_SUPPORTED_STATUS_MASK \ + (PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE | PR_SHADOW_STACK_PUSH) + #ifdef CONFIG_ARM64_GCS

static inline bool task_gcs_el0_enabled(struct task_struct *task) @@ -63,6 +66,20 @@ void gcs_preserve_current_state(void); unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, const struct kernel_clone_args *args);

+static inline int gcs_check_locked(struct task_struct *task, + unsigned long new_val) +{ + unsigned long cur_val = task->thread.gcs_el0_mode; + + cur_val &= task->thread.gcs_el0_locked; + new_val &= task->thread.gcs_el0_locked; + + if (cur_val != new_val) + return -EBUSY; + + return 0; +} + #else

static inline bool task_gcs_el0_enabled(struct task_struct *task) @@ -78,6 +95,11 @@ static inline unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, { return -ENOTSUPP; } +static inline int gcs_check_locked(struct task_struct *task, + unsigned long new_val) +{ + return 0; +}

#endif

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index c28681cf9721..029d20ea7878 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -181,6 +181,7 @@ struct thread_struct { u64 tpidr2_el0; #ifdef CONFIG_ARM64_GCS unsigned int gcs_el0_mode; + unsigned int gcs_el0_locked; u64 gcspr_el0; u64 gcs_base; u64 gcs_size; diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index 0d4881173b5f..315bd698de86 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -113,3 +113,85 @@ void gcs_free(struct task_struct *task) task->thread.gcs_base = 0; task->thread.gcs_size = 0; } + +int arch_set_shadow_stack_status(struct task_struct *task, unsigned long arg) +{ + unsigned long gcs, size; + int ret; + + if (!system_supports_gcs()) + return -EINVAL; + + if (is_compat_thread(task_thread_info(task))) + return -EINVAL; + + /* Reject unknown flags */ + if (arg & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK) + return -EINVAL; + + ret = gcs_check_locked(task, arg); + if (ret != 0) + return ret; + + /* If we are enabling GCS then make sure we have a stack */ + if (arg & PR_SHADOW_STACK_ENABLE) { + if (!task_gcs_el0_enabled(task)) { + /* Do not allow GCS to be reenabled */ + if (task->thread.gcs_base) + return -EINVAL; + + if (task != current) + return -EBUSY; + + size = gcs_size(0); + gcs = alloc_gcs(task->thread.gcspr_el0, size, + 0, 0); + if (!gcs) + return -ENOMEM; + + task->thread.gcspr_el0 = gcs + size - sizeof(u64); + task->thread.gcs_base = gcs; + task->thread.gcs_size = size; + if (task == current) + write_sysreg_s(task->thread.gcspr_el0, + SYS_GCSPR_EL0); + + } + } + + task->thread.gcs_el0_mode = arg; + if (task == current) + gcs_set_el0_mode(task); + + return 0; +} + +int arch_get_shadow_stack_status(struct task_struct *task, + unsigned long __user *arg) +{ + if (!system_supports_gcs()) + return -EINVAL; + + if (is_compat_thread(task_thread_info(task))) + return -EINVAL; + + return put_user(task->thread.gcs_el0_mode, arg); +} + +int arch_lock_shadow_stack_status(struct task_struct *task, + unsigned long arg) +{ + if (!system_supports_gcs()) + return -EINVAL; + + if (is_compat_thread(task_thread_info(task))) + return -EINVAL; + + /* + * We support locking unknown bits so applications can prevent + * any changes in a future proof manner. + */ + task->thread.gcs_el0_locked |= arg; + + return 0; +}

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. Two flags are provided, allowing applications to request that the stack be initialised with a valid cap token at the top of the stack and optionally also an end of stack marker above that. We support requesting an end of stack marker alone but since this is a NULL pointer it is indistinguishable from not initialising anything by itself.

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 | 61 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 61 insertions(+)

diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index 315bd698de86..02f8f6046c10 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -84,6 +84,67 @@ 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 alloc_size; + unsigned long __user *cap_ptr; + unsigned long cap_val; + int ret = 0; + int cap_offset; + + if (!system_supports_gcs()) + return -EOPNOTSUPP; + + if (flags & ~(SHADOW_STACK_SET_TOKEN | SHADOW_STACK_SET_MARKER)) + return -EINVAL; + + if (addr && (addr % PAGE_SIZE)) + return -EINVAL; + + if (size == 8 || size % 8) + 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. + */ + alloc_size = PAGE_ALIGN(size); + if (alloc_size < size) + return -EOVERFLOW; + + addr = alloc_gcs(addr, alloc_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. + */ + if (flags & SHADOW_STACK_SET_TOKEN) { + /* Leave an extra empty frame as a top of stack marker? */ + if (flags & SHADOW_STACK_SET_MARKER) + cap_offset = 2; + else + cap_offset = 1; + + cap_ptr = (unsigned long __user *)(addr + size - + (cap_offset * sizeof(unsigned long))); + cap_val = GCS_CAP(cap_ptr); + + put_user_gcs(cap_val, cap_ptr, &ret); + if (ret != 0) { + vm_munmap(addr, size); + return -EFAULT; + } + + /* Ensure the new cap is viaible for GCS */ + gcsb_dsync(); + } + + return addr; +} + /* * Apply the GCS mode configured for the specified task to the * hardware.

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 and token type of 0 which we add on signal entry and validate and pop off on signal return. The combination of the top bit being set and the token type mean that this can't be interpreted as a valid token or address.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/gcs.h | 1 + arch/arm64/kernel/signal.c | 129 +++++++++++++++++++++++++++++++++++++++++-- arch/arm64/mm/gcs.c | 1 + 3 files changed, 126 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/gcs.h b/arch/arm64/include/asm/gcs.h index 48c97e63e56a..f50660603ecf 100644 --- a/arch/arm64/include/asm/gcs.h +++ b/arch/arm64/include/asm/gcs.h @@ -9,6 +9,7 @@ #include <asm/uaccess.h>

struct kernel_clone_args; +struct ksignal;

static inline void gcsb_dsync(void) { diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 0e8beb3349ea..b5dff91274fb 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 +35,37 @@ #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) ((((unsigned long)addr) & GCS_CAP_ADDR_MASK) | \ + 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) != 0) + 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 +847,45 @@ 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; + + gcspr_el0 = read_sysreg_s(SYS_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 +912,9 @@ 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 +1145,50 @@ 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; + int ret = 0; + + 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. + */ + put_user_gcs((unsigned long)sigtramp, gcspr_el0 - 2, &ret); + put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 1), gcspr_el0 - 1, &ret); + 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 +1196,7 @@ 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 +1236,14 @@ 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 +1266,7 @@ 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 02f8f6046c10..6f51429c5a46 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 Kconfig option allowing the user to select if GCS support is built into the kernel.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/Kconfig | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7b071a00425d..05cffc0f5786 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -2078,6 +2078,26 @@ config ARM64_EPAN if the cpu does not implement the feature. endmenu # "ARMv8.7 architectural features"

+menu "v9.4 architectural features" + +config ARM64_GCS + bool "Enable support for Guarded Control Stack (GCS)" + default y + select ARCH_HAS_USER_SHADOW_STACK + select ARCH_USES_HIGH_VMA_FLAGS + help + Guarded Control Stack (GCS) provides support for a separate + stack with restricted access which contains only return + addresses. This can be used to harden against some attacks + by comparing return address used by the program with what is + stored in the GCS, and may also be used to efficiently obtain + the call stack for applications such as profiling. + + The feature is detected at runtime, and will remain disabled + if the system does not implement the feature. + +endmenu # "v9.4 architectural features" + config ARM64_SVE bool "ARM Scalable Vector Extension support" default y

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 | 18 ++ tools/testing/selftests/arm64/gcs/basic-gcs.c | 428 ++++++++++++++++++++++++++ tools/testing/selftests/arm64/gcs/gcs-util.h | 90 ++++++ 5 files changed, 538 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile index 28b93cab8c0d..22029e60eff3 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 $(ARCH),aarch64 arm64)) -ARM64_SUBTARGETS ?= tags signal pauth fp mte bti abi +ARM64_SUBTARGETS ?= tags signal pauth fp mte bti abi gcs else ARM64_SUBTARGETS := endif diff --git a/tools/testing/selftests/arm64/gcs/.gitignore b/tools/testing/selftests/arm64/gcs/.gitignore new file mode 100644 index 000000000000..0e5e695ecba5 --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/.gitignore @@ -0,0 +1 @@ +basic-gcs diff --git a/tools/testing/selftests/arm64/gcs/Makefile b/tools/testing/selftests/arm64/gcs/Makefile new file mode 100644 index 000000000000..61a30f483429 --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/Makefile @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2023 ARM Limited +# +# In order to avoid interaction with the toolchain and dynamic linker the +# portions of these tests that interact with the GCS are implemented using +# nolibc. +# + +TEST_GEN_PROGS := basic-gcs + +include ../../lib.mk + +$(OUTPUT)/basic-gcs: basic-gcs.c + $(CC) -g -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ + -static -include ../../../../include/nolibc/nolibc.h \ + -I../../../../../usr/include \ + -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..3ef957e0065f --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/basic-gcs.c @@ -0,0 +1,428 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 ARM Limited. + */ + +#include <limits.h> +#include <stdbool.h> + +#include <linux/prctl.h> + +#include <sys/mman.h> +#include <asm/mman.h> +#include <linux/sched.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) +{ + bool enabling = mode & PR_SHADOW_STACK_ENABLE; + 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); + } + + if (enabling != chkfeat_gcs()) { + ksft_print_msg("%senabled by prctl but %senabled in CHKFEAT\n", + enabling ? "" : "not ", + chkfeat_gcs() ? "" : "not "); + ret = -EINVAL; + } + } + + 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, + SHADOW_STACK_SET_MARKER | + SHADOW_STACK_SET_TOKEN); + 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; +} + +/* Check that we can explicitly specify a GCS via clone3() */ +static bool test_clone3(void) +{ + struct clone_args args; + unsigned long child_mode; + pid_t pid = -1; + int status, ret; + bool pass; + + memset(&args, 0, sizeof(args)); + args.flags = CLONE_VM; + args.shadow_stack_size = page_size; + + pid = my_syscall2(__NR_clone3, &args, sizeof(args)); + if (pid < 0) { + ksft_print_msg("clone3() failed: %d\n", errno); + pass = false; + goto out; + } + + /* In child? */ + if (pid == 0) { + /* Do we have GCS enabled? */ + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, + &child_mode, 0, 0, 0); + if (ret != 0) { + ksft_print_msg("PR_GET_SHADOW_STACK_STATUS failed: %d\n", + ret); + exit(EXIT_FAILURE); + } + + if (!(child_mode & PR_SHADOW_STACK_ENABLE)) { + ksft_print_msg("GCS not enabled in child\n"); + exit(EXIT_FAILURE); + } + + ksft_print_msg("GCS enabled in child\n"); + + /* We've probably already called a function but make sure */ + valid_gcs_function(); + + exit(EXIT_SUCCESS); + } + + if (waitpid(-1, &status, __WALL) < 0) { + ksft_print_msg("waitpid() failed %d\n", errno); + pass = false; + goto out; + } + if (WIFEXITED(status)) { + if (WEXITSTATUS(status) == EXIT_SUCCESS) { + pass = true; + } else { + ksft_print_msg("Child returned status %d\n", + WEXITSTATUS(status)); + pass = false; + } + } else if (WIFSIGNALED(status)) { + ksft_print_msg("Child exited due to signal %d\n", + WTERMSIG(status)); + pass = false; + } else { + ksft_print_msg("Child exited uncleanly\n"); + 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 }, + { "clone3", test_clone3 }, +}; + +int main(void) +{ + int i, ret; + unsigned long gcs_mode; + + 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); + } + + ksft_set_plan(ARRAY_SIZE(tests)); + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + 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..b37801c95604 --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/gcs-util.h @@ -0,0 +1,90 @@ +/* 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 453 +#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_LOCK_SHADOW_STACK_STATUS 73 + +# define PR_SHADOW_STACK_ENABLE (1UL << 0) +# define PR_SHADOW_STACK_WRITE (1UL << 1) +# define PR_SHADOW_STACK_PUSH (1UL << 2) + +#define PR_SHADOW_STACK_ALL_MODES \ + PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE | PR_SHADOW_STACK_PUSH + +#define SHADOW_STACK_SET_TOKEN (1ULL << 0) /* Set up a restore token in the shadow stack */ +#define SHADOW_STACK_SET_MARKER (1ULL << 1) /* Set up a top of stack merker in the shadow stack */ + +#define GCS_CAP_ADDR_MASK (0xfffffffffffff000UL) +#define GCS_CAP_TOKEN_MASK (0x0000000000000fffUL) +#define GCS_CAP_VALID_TOKEN 1 +#define GCS_CAP_IN_PROGRESS_TOKEN 5 + +#define GCS_CAP(x) (((unsigned long)(x) & GCS_CAP_ADDR_MASK) | \ + GCS_CAP_VALID_TOKEN) + +static inline 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; +} + +static inline bool chkfeat_gcs(void) +{ + register long val __asm__ ("x16") = 1; + + /* CHKFEAT x16 */ + asm volatile( + "hint #0x28\n" + : "=r" (val) + : "r" (val)); + + return val != 1; +} + +#endif

Verify that we can lock individual GCS mode bits, that other modes aren't affected and as a side effect also that every combination of modes can be enabled.

Normally the inability to reenable GCS after disabling it would be an issue with testing but fortunately the kselftest_harness runs each test within a fork()ed child. This can be inconvenient for some kinds of testing but here it means that each test is in a separate thread and therefore won't be affected by other tests in the suite.

Once we get toolchains with support for enabling GCS by default we will need to take care to not do that in the build system but there are no such toolchains yet so it is not yet an issue.

Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/arm64/gcs/.gitignore | 1 + tools/testing/selftests/arm64/gcs/Makefile | 2 +- tools/testing/selftests/arm64/gcs/gcs-locking.c | 200 ++++++++++++++++++++++++ 3 files changed, 202 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/arm64/gcs/.gitignore b/tools/testing/selftests/arm64/gcs/.gitignore index 5810c4a163d4..0c86f53f68ad 100644 --- a/tools/testing/selftests/arm64/gcs/.gitignore +++ b/tools/testing/selftests/arm64/gcs/.gitignore @@ -1,2 +1,3 @@ basic-gcs libc-gcs +gcs-locking diff --git a/tools/testing/selftests/arm64/gcs/Makefile b/tools/testing/selftests/arm64/gcs/Makefile index a8fdf21e9a47..2173d6275956 100644 --- a/tools/testing/selftests/arm64/gcs/Makefile +++ b/tools/testing/selftests/arm64/gcs/Makefile @@ -6,7 +6,7 @@ # nolibc. #

-TEST_GEN_PROGS := basic-gcs libc-gcs +TEST_GEN_PROGS := basic-gcs libc-gcs gcs-locking

LDLIBS+=-lpthread

diff --git a/tools/testing/selftests/arm64/gcs/gcs-locking.c b/tools/testing/selftests/arm64/gcs/gcs-locking.c new file mode 100644 index 000000000000..f6a73254317e --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/gcs-locking.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 ARM Limited. + * + * Tests for GCS mode locking. These tests rely on both having GCS + * unconfigured on entry and on the kselftest harness running each + * test in a fork()ed process which will have it's own mode. + */ + +#include <limits.h> + +#include <sys/auxv.h> +#include <sys/prctl.h> + +#include <asm/hwcap.h> + +#include "kselftest_harness.h" + +#include "gcs-util.h" + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = 0; \ + register long _arg4 __asm__ ("x3") = 0; \ + register long _arg5 __asm__ ("x4") = 0; \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), \ + "r"(_arg3), "r"(_arg4), \ + "r"(_arg5), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +/* No mode bits are rejected for locking */ +TEST(lock_all_modes) +{ + int ret; + + ret = prctl(PR_LOCK_SHADOW_STACK_STATUS, ULONG_MAX, 0, 0, 0); + ASSERT_EQ(ret, 0); +} + +FIXTURE(valid_modes) +{ +}; + +FIXTURE_VARIANT(valid_modes) +{ + unsigned long mode; +}; + +FIXTURE_VARIANT_ADD(valid_modes, enable) +{ + .mode = PR_SHADOW_STACK_ENABLE, +}; + +FIXTURE_VARIANT_ADD(valid_modes, enable_write) +{ + .mode = PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE, +}; + +FIXTURE_VARIANT_ADD(valid_modes, enable_push) +{ + .mode = PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_PUSH, +}; + +FIXTURE_VARIANT_ADD(valid_modes, enable_write_push) +{ + .mode = PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE | + PR_SHADOW_STACK_PUSH, +}; + +FIXTURE_SETUP(valid_modes) +{ +} + +FIXTURE_TEARDOWN(valid_modes) +{ +} + +/* We can set the mode at all */ +TEST_F(valid_modes, set) +{ + int ret; + + ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, + variant->mode); + ASSERT_EQ(ret, 0); + + _exit(0); +} + +/* Enabling, locking then disabling is rejected */ +TEST_F(valid_modes, enable_lock_disable) +{ + unsigned long mode; + int ret; + + ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, + variant->mode); + ASSERT_EQ(ret, 0); + + ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0); + ASSERT_EQ(ret, 0); + ASSERT_EQ(mode, variant->mode); + + ret = prctl(PR_LOCK_SHADOW_STACK_STATUS, variant->mode, 0, 0, 0); + ASSERT_EQ(ret, 0); + + ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, 0); + ASSERT_EQ(ret, -EBUSY); + + _exit(0); +} + +/* Locking then enabling is rejected */ +TEST_F(valid_modes, lock_enable) +{ + unsigned long mode; + int ret; + + ret = prctl(PR_LOCK_SHADOW_STACK_STATUS, variant->mode, 0, 0, 0); + ASSERT_EQ(ret, 0); + + ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, + variant->mode); + ASSERT_EQ(ret, -EBUSY); + + ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0); + ASSERT_EQ(ret, 0); + ASSERT_EQ(mode, 0); + + _exit(0); +} + +/* Locking then changing other modes is fine */ +TEST_F(valid_modes, lock_enable_disable_others) +{ + unsigned long mode; + int ret; + + ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, + variant->mode); + ASSERT_EQ(ret, 0); + + ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0); + ASSERT_EQ(ret, 0); + ASSERT_EQ(mode, variant->mode); + + ret = prctl(PR_LOCK_SHADOW_STACK_STATUS, variant->mode, 0, 0, 0); + ASSERT_EQ(ret, 0); + + ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, + PR_SHADOW_STACK_ALL_MODES); + ASSERT_EQ(ret, 0); + + ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0); + ASSERT_EQ(ret, 0); + ASSERT_EQ(mode, PR_SHADOW_STACK_ALL_MODES); + + + ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, + variant->mode); + ASSERT_EQ(ret, 0); + + ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0); + ASSERT_EQ(ret, 0); + ASSERT_EQ(mode, variant->mode); + + _exit(0); +} + +int main(int argc, char **argv) +{ + unsigned long mode; + int ret; + + if (!(getauxval(AT_HWCAP2) & HWCAP2_GCS)) + ksft_exit_skip("SKIP GCS not supported\n"); + + ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0); + if (ret) { + ksft_print_msg("Failed to read GCS state: %d\n", ret); + return EXIT_FAILURE; + } + + if (mode & PR_SHADOW_STACK_ENABLE) { + ksft_print_msg("GCS was enabled, test unsupported\n"); + return KSFT_SKIP; + } + + return test_harness_run(argc, argv); +}

Add a stress test which runs one more process than we have CPUs spinning through a very recursive function with frequent syscalls immediately prior to return and signals being injected every 100ms. The goal is to flag up any scheduling related issues, for example failure to ensure that barriers are inserted when moving a GCS using task to another CPU. The test runs for a configurable amount of time, defaulting to 10 seconds.

Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/arm64/gcs/.gitignore | 2 + tools/testing/selftests/arm64/gcs/Makefile | 6 +- tools/testing/selftests/arm64/gcs/asm-offsets.h | 0 .../selftests/arm64/gcs/gcs-stress-thread.S | 311 ++++++++++++ tools/testing/selftests/arm64/gcs/gcs-stress.c | 532 +++++++++++++++++++++ 5 files changed, 850 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/arm64/gcs/.gitignore b/tools/testing/selftests/arm64/gcs/.gitignore index 0c86f53f68ad..1e8d1f6b27f2 100644 --- a/tools/testing/selftests/arm64/gcs/.gitignore +++ b/tools/testing/selftests/arm64/gcs/.gitignore @@ -1,3 +1,5 @@ basic-gcs libc-gcs gcs-locking +gcs-stress +gcs-stress-thread diff --git a/tools/testing/selftests/arm64/gcs/Makefile b/tools/testing/selftests/arm64/gcs/Makefile index 2173d6275956..d8b06ca51e22 100644 --- a/tools/testing/selftests/arm64/gcs/Makefile +++ b/tools/testing/selftests/arm64/gcs/Makefile @@ -6,7 +6,8 @@ # nolibc. #

-TEST_GEN_PROGS := basic-gcs libc-gcs gcs-locking +TEST_GEN_PROGS := basic-gcs libc-gcs gcs-locking gcs-stress +TEST_GEN_PROGS_EXTENDED := gcs-stress-thread

LDLIBS+=-lpthread

@@ -18,3 +19,6 @@ $(OUTPUT)/basic-gcs: basic-gcs.c -I../../../../../usr/include \ -std=gnu99 -I../.. -g \ -ffreestanding -Wall $^ -o $@ -lgcc + +$(OUTPUT)/gcs-stress-thread: gcs-stress-thread.S + $(CC) -nostdlib $^ -o $@ diff --git a/tools/testing/selftests/arm64/gcs/asm-offsets.h b/tools/testing/selftests/arm64/gcs/asm-offsets.h new file mode 100644 index 000000000000..e69de29bb2d1 diff --git a/tools/testing/selftests/arm64/gcs/gcs-stress-thread.S b/tools/testing/selftests/arm64/gcs/gcs-stress-thread.S new file mode 100644 index 000000000000..4fe8695333e5 --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/gcs-stress-thread.S @@ -0,0 +1,311 @@ +// Program that loops for ever doing lots of recursions and system calls, +// intended to be used as part of a stress test for GCS context switching. +// +// Copyright 2015-2023 Arm Ltd + +#include <asm/unistd.h> + +#define sa_sz 32 +#define sa_flags 8 +#define sa_handler 0 +#define sa_mask_sz 8 + +#define si_code 8 + +#define SIGINT 2 +#define SIGABRT 6 +#define SIGUSR1 10 +#define SIGSEGV 11 +#define SIGUSR2 12 +#define SIGTERM 15 +#define SEGV_CPERR 10 + +#define SA_NODEFER 1073741824 +#define SA_SIGINFO 4 +#define ucontext_regs 184 + +#define PR_SET_SHADOW_STACK_STATUS 72 +# define PR_SHADOW_STACK_ENABLE (1UL << 0) + +#define GCSPR_EL0 S3_3_C2_C5_1 + +.macro function name + .macro endfunction + .type \name, @function + .purgem endfunction + .endm +\name: +.endm + +// Print a single character x0 to stdout +// Clobbers x0-x2,x8 +function putc + str x0, [sp, #-16]! + + mov x0, #1 // STDOUT_FILENO + mov x1, sp + mov x2, #1 + mov x8, #__NR_write + svc #0 + + add sp, sp, #16 + ret +endfunction +.globl putc + +// Print a NUL-terminated string starting at address x0 to stdout +// Clobbers x0-x3,x8 +function puts + mov x1, x0 + + mov x2, #0 +0: ldrb w3, [x0], #1 + cbz w3, 1f + add x2, x2, #1 + b 0b + +1: mov w0, #1 // STDOUT_FILENO + mov x8, #__NR_write + svc #0 + + ret +endfunction +.globl puts + +// Utility macro to print a literal string +// Clobbers x0-x4,x8 +.macro puts string + .pushsection .rodata.str1.1, "aMS", @progbits, 1 +.L__puts_literal@: .string "\string" + .popsection + + ldr x0, =.L__puts_literal@ + bl puts +.endm + +// Print an unsigned decimal number x0 to stdout +// Clobbers x0-x4,x8 +function putdec + mov x1, sp + str x30, [sp, #-32]! // Result can't be > 20 digits + + mov x2, #0 + strb w2, [x1, #-1]! // Write the NUL terminator + + mov x2, #10 +0: udiv x3, x0, x2 // div-mod loop to generate the digits + msub x0, x3, x2, x0 + add w0, w0, #'0' + strb w0, [x1, #-1]! + mov x0, x3 + cbnz x3, 0b + + ldrb w0, [x1] + cbnz w0, 1f + mov w0, #'0' // Print "0" for 0, not "" + strb w0, [x1, #-1]! + +1: mov x0, x1 + bl puts + + ldr x30, [sp], #32 + ret +endfunction +.globl putdec + +// Print an unsigned decimal number x0 to stdout, followed by a newline +// Clobbers x0-x5,x8 +function putdecn + mov x5, x30 + + bl putdec + mov x0, #'\n' + bl putc + + ret x5 +endfunction +.globl putdecn + +// Fill x1 bytes starting at x0 with 0. +// Clobbers x1, x2. +function memclr + mov w2, #0 +endfunction +.globl memclr + // fall through to memfill + +// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2 +// Clobbers x1 +function memfill + cmp x1, #0 + b.eq 1f + +0: strb w2, [x0], #1 + subs x1, x1, #1 + b.ne 0b + +1: ret +endfunction +.globl memfill + +// w0: signal number +// x1: sa_action +// w2: sa_flags +// Clobbers x0-x6,x8 +function setsignal + str x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]! + + mov w4, w0 + mov x5, x1 + mov w6, w2 + + add x0, sp, #16 + mov x1, #sa_sz + bl memclr + + mov w0, w4 + add x1, sp, #16 + str w6, [x1, #sa_flags] + str x5, [x1, #sa_handler] + mov x2, #0 + mov x3, #sa_mask_sz + mov x8, #__NR_rt_sigaction + svc #0 + + cbz w0, 1f + + puts "sigaction failure\n" + b abort + +1: ldr x30, [sp], #((sa_sz + 15) / 16 * 16 + 16) + ret +endfunction + + +function tickle_handler + // Perhaps collect GCSPR_EL0 here in future? + ret +endfunction + +function terminate_handler + mov w21, w0 + mov x20, x2 + + puts "Terminated by signal " + mov w0, w21 + bl putdec + puts ", no error\n" + + mov x0, #0 + mov x8, #__NR_exit + svc #0 +endfunction + +function segv_handler + // stash the siginfo_t * + mov x20, x1 + + // Disable GCS, we don't want additional faults logging things + mov x0, PR_SET_SHADOW_STACK_STATUS + mov x1, xzr + mov x2, xzr + mov x3, xzr + mov x4, xzr + mov x5, xzr + mov x8, #__NR_prctl + svc #0 + + puts "Got SIGSEGV code " + + ldr x21, [x20, #si_code] + mov x0, x21 + bl putdec + + // GCS faults should have si_code SEGV_CPERR + cmp x21, #SEGV_CPERR + bne 1f + + puts " (GCS violation)" +1: + mov x0, '\n' + bl putc + b abort +endfunction + +// Recurse x20 times +.macro recurse id +function recurse\id + stp x29, x30, [sp, #-16]! + mov x29, sp + + cmp x20, 0 + beq 1f + sub x20, x20, 1 + bl recurse\id + +1: + ldp x29, x30, [sp], #16 + + // Do a syscall immediately prior to returning to try to provoke + // scheduling and migration at a point where coherency issues + // might trigger. + mov x8, #__NR_getpid + svc #0 + + ret +endfunction +.endmacro + +// Generate and use two copies so we're changing the GCS contents +recurse 1 +recurse 2 + +.globl _start +function _start + // Run with GCS + mov x0, PR_SET_SHADOW_STACK_STATUS + mov x1, PR_SHADOW_STACK_ENABLE + mov x2, xzr + mov x3, xzr + mov x4, xzr + mov x5, xzr + mov x8, #__NR_prctl + svc #0 + cbz x0, 1f + puts "Failed to enable GCS\n" + b abort +1: + + mov w0, #SIGTERM + adr x1, terminate_handler + mov w2, #SA_SIGINFO + bl setsignal + + mov w0, #SIGUSR1 + adr x1, tickle_handler + mov w2, #SA_SIGINFO + orr w2, w2, #SA_NODEFER + bl setsignal + + mov w0, #SIGSEGV + adr x1, segv_handler + mov w2, #SA_SIGINFO + orr w2, w2, #SA_NODEFER + bl setsignal + + puts "Running\n" + +loop: + // Small recursion depth so we're frequently flipping between + // the two recursors and changing what's on the stack + mov x20, #5 + bl recurse1 + mov x20, #5 + bl recurse2 + b loop +endfunction + +abort: + mov x0, #255 + mov x8, #__NR_exit + svc #0 diff --git a/tools/testing/selftests/arm64/gcs/gcs-stress.c b/tools/testing/selftests/arm64/gcs/gcs-stress.c new file mode 100644 index 000000000000..23fd8ec37bdc --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/gcs-stress.c @@ -0,0 +1,532 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022-3 ARM Limited. + */ + +#define _GNU_SOURCE +#define _POSIX_C_SOURCE 199309L + +#include <errno.h> +#include <getopt.h> +#include <poll.h> +#include <signal.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/auxv.h> +#include <sys/epoll.h> +#include <sys/prctl.h> +#include <sys/types.h> +#include <sys/uio.h> +#include <sys/wait.h> +#include <asm/hwcap.h> + +#include "../../kselftest.h" + +struct child_data { + char *name, *output; + pid_t pid; + int stdout; + bool output_seen; + bool exited; + int exit_status; + int exit_signal; +}; + +static int epoll_fd; +static struct child_data *children; +static struct epoll_event *evs; +static int tests; +static int num_children; +static bool terminate; + +static int startup_pipe[2]; + +static int num_processors(void) +{ + long nproc = sysconf(_SC_NPROCESSORS_CONF); + if (nproc < 0) { + perror("Unable to read number of processors\n"); + exit(EXIT_FAILURE); + } + + return nproc; +} + +static void start_thread(struct child_data *child) +{ + int ret, pipefd[2], i; + struct epoll_event ev; + + ret = pipe(pipefd); + if (ret != 0) + ksft_exit_fail_msg("Failed to create stdout pipe: %s (%d)\n", + strerror(errno), errno); + + child->pid = fork(); + if (child->pid == -1) + ksft_exit_fail_msg("fork() failed: %s (%d)\n", + strerror(errno), errno); + + if (!child->pid) { + /* + * In child, replace stdout with the pipe, errors to + * stderr from here as kselftest prints to stdout. + */ + ret = dup2(pipefd[1], 1); + if (ret == -1) { + fprintf(stderr, "dup2() %d\n", errno); + exit(EXIT_FAILURE); + } + + /* + * Duplicate the read side of the startup pipe to + * FD 3 so we can close everything else. + */ + ret = dup2(startup_pipe[0], 3); + if (ret == -1) { + fprintf(stderr, "dup2() %d\n", errno); + exit(EXIT_FAILURE); + } + + /* + * Very dumb mechanism to clean open FDs other than + * stdio. We don't want O_CLOEXEC for the pipes... + */ + for (i = 4; i < 8192; i++) + close(i); + + /* + * Read from the startup pipe, there should be no data + * and we should block until it is closed. We just + * carry on on error since this isn't super critical. + */ + ret = read(3, &i, sizeof(i)); + if (ret < 0) + fprintf(stderr, "read(startp pipe) failed: %s (%d)\n", + strerror(errno), errno); + if (ret > 0) + fprintf(stderr, "%d bytes of data on startup pipe\n", + ret); + close(3); + + ret = execl("gcs-stress-thread", "gcs-stress-thread", NULL); + fprintf(stderr, "execl(gcs-stress-thread) failed: %d (%s)\n", + errno, strerror(errno)); + + exit(EXIT_FAILURE); + } else { + /* + * In parent, remember the child and close our copy of the + * write side of stdout. + */ + close(pipefd[1]); + child->stdout = pipefd[0]; + child->output = NULL; + child->exited = false; + child->output_seen = false; + + ev.events = EPOLLIN | EPOLLHUP; + ev.data.ptr = child; + + ret = asprintf(&child->name, "Thread-%d", child->pid); + if (ret == -1) + ksft_exit_fail_msg("asprintf() failed\n"); + + ret = epoll_ctl(epoll_fd, EPOLL_CTL_ADD, child->stdout, &ev); + if (ret < 0) { + ksft_exit_fail_msg("%s EPOLL_CTL_ADD failed: %s (%d)\n", + child->name, strerror(errno), errno); + } + } + + ksft_print_msg("Started %s\n", child->name); + num_children++; +} + +static bool child_output_read(struct child_data *child) +{ + char read_data[1024]; + char work[1024]; + int ret, len, cur_work, cur_read; + + ret = read(child->stdout, read_data, sizeof(read_data)); + if (ret < 0) { + if (errno == EINTR) + return true; + + ksft_print_msg("%s: read() failed: %s (%d)\n", + child->name, strerror(errno), + errno); + return false; + } + len = ret; + + child->output_seen = true; + + /* Pick up any partial read */ + if (child->output) { + strncpy(work, child->output, sizeof(work) - 1); + cur_work = strnlen(work, sizeof(work)); + free(child->output); + child->output = NULL; + } else { + cur_work = 0; + } + + cur_read = 0; + while (cur_read < len) { + work[cur_work] = read_data[cur_read++]; + + if (work[cur_work] == '\n') { + work[cur_work] = '\0'; + ksft_print_msg("%s: %s\n", child->name, work); + cur_work = 0; + } else { + cur_work++; + } + } + + if (cur_work) { + work[cur_work] = '\0'; + ret = asprintf(&child->output, "%s", work); + if (ret == -1) + ksft_exit_fail_msg("Out of memory\n"); + } + + return false; +} + +static void child_output(struct child_data *child, uint32_t events, + bool flush) +{ + bool read_more; + + if (events & EPOLLIN) { + do { + read_more = child_output_read(child); + } while (read_more); + } + + if (events & EPOLLHUP) { + close(child->stdout); + child->stdout = -1; + flush = true; + } + + if (flush && child->output) { + ksft_print_msg("%s: %s<EOF>\n", child->name, child->output); + free(child->output); + child->output = NULL; + } +} + +static void child_tickle(struct child_data *child) +{ + if (child->output_seen && !child->exited) + kill(child->pid, SIGUSR1); +} + +static void child_stop(struct child_data *child) +{ + if (!child->exited) + kill(child->pid, SIGTERM); +} + +static void child_cleanup(struct child_data *child) +{ + pid_t ret; + int status; + bool fail = false; + + if (!child->exited) { + do { + ret = waitpid(child->pid, &status, 0); + if (ret == -1 && errno == EINTR) + continue; + + if (ret == -1) { + ksft_print_msg("waitpid(%d) failed: %s (%d)\n", + child->pid, strerror(errno), + errno); + fail = true; + break; + } + + if (WIFEXITED(status)) { + child->exit_status = WEXITSTATUS(status); + child->exited = true; + } + + if (WIFSIGNALED(status)) { + child->exit_signal = WTERMSIG(status); + ksft_print_msg("%s: Exited due to signal %d\n", + child->name); + fail = true; + child->exited = true; + } + } while (!child->exited); + } + + if (!child->output_seen) { + ksft_print_msg("%s no output seen\n", child->name); + fail = true; + } + + if (child->exit_status != 0) { + ksft_print_msg("%s exited with error code %d\n", + child->name, child->exit_status); + fail = true; + } + + ksft_test_result(!fail, "%s\n", child->name); +} + +static void handle_child_signal(int sig, siginfo_t *info, void *context) +{ + int i; + bool found = false; + + for (i = 0; i < num_children; i++) { + if (children[i].pid == info->si_pid) { + children[i].exited = true; + children[i].exit_status = info->si_status; + found = true; + break; + } + } + + if (!found) + ksft_print_msg("SIGCHLD for unknown PID %d with status %d\n", + info->si_pid, info->si_status); +} + +static void handle_exit_signal(int sig, siginfo_t *info, void *context) +{ + int i; + + /* If we're already exiting then don't signal again */ + if (terminate) + return; + + ksft_print_msg("Got signal, exiting...\n"); + + terminate = true; + + /* + * This should be redundant, the main loop should clean up + * after us, but for safety stop everything we can here. + */ + for (i = 0; i < num_children; i++) + child_stop(&children[i]); +} + +/* Handle any pending output without blocking */ +static void drain_output(bool flush) +{ + int ret = 1; + int i; + + while (ret > 0) { + ret = epoll_wait(epoll_fd, evs, tests, 0); + if (ret < 0) { + if (errno == EINTR) + continue; + ksft_print_msg("epoll_wait() failed: %s (%d)\n", + strerror(errno), errno); + } + + for (i = 0; i < ret; i++) + child_output(evs[i].data.ptr, evs[i].events, flush); + } +} + +static const struct option options[] = { + { "timeout", required_argument, NULL, 't' }, + { } +}; + +int main(int argc, char **argv) +{ + int seen_children; + bool all_children_started = false; + int gcs_threads; + int timeout = 10; + int ret, cpus, i, c; + struct sigaction sa; + + while ((c = getopt_long(argc, argv, "t:", options, NULL)) != -1) { + switch (c) { + case 't': + ret = sscanf(optarg, "%d", &timeout); + if (ret != 1) + ksft_exit_fail_msg("Failed to parse timeout %s\n", + optarg); + break; + default: + ksft_exit_fail_msg("Unknown argument\n"); + } + } + + cpus = num_processors(); + tests = 0; + + if (getauxval(AT_HWCAP2) & HWCAP2_GCS) { + /* One extra thread, trying to trigger migrations */ + gcs_threads = cpus + 1; + tests += gcs_threads; + } else { + gcs_threads = 0; + } + + ksft_print_header(); + ksft_set_plan(tests); + + ksft_print_msg("%d CPUs, %d GCS threads\n", + cpus, gcs_threads); + + if (!tests) + ksft_exit_skip("No tests scheduled\n"); + + if (timeout > 0) + ksft_print_msg("Will run for %ds\n", timeout); + else + ksft_print_msg("Will run until terminated\n"); + + children = calloc(sizeof(*children), tests); + if (!children) + ksft_exit_fail_msg("Unable to allocate child data\n"); + + ret = epoll_create1(EPOLL_CLOEXEC); + if (ret < 0) + ksft_exit_fail_msg("epoll_create1() failed: %s (%d)\n", + strerror(errno), ret); + epoll_fd = ret; + + /* Create a pipe which children will block on before execing */ + ret = pipe(startup_pipe); + if (ret != 0) + ksft_exit_fail_msg("Failed to create startup pipe: %s (%d)\n", + strerror(errno), errno); + + /* Get signal handers ready before we start any children */ + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handle_exit_signal; + sa.sa_flags = SA_RESTART | SA_SIGINFO; + sigemptyset(&sa.sa_mask); + ret = sigaction(SIGINT, &sa, NULL); + if (ret < 0) + ksft_print_msg("Failed to install SIGINT handler: %s (%d)\n", + strerror(errno), errno); + ret = sigaction(SIGTERM, &sa, NULL); + if (ret < 0) + ksft_print_msg("Failed to install SIGTERM handler: %s (%d)\n", + strerror(errno), errno); + sa.sa_sigaction = handle_child_signal; + ret = sigaction(SIGCHLD, &sa, NULL); + if (ret < 0) + ksft_print_msg("Failed to install SIGCHLD handler: %s (%d)\n", + strerror(errno), errno); + + evs = calloc(tests, sizeof(*evs)); + if (!evs) + ksft_exit_fail_msg("Failed to allocated %d epoll events\n", + tests); + + for (i = 0; i < gcs_threads; i++) + start_thread(&children[i]); + + /* + * All children started, close the startup pipe and let them + * run. + */ + close(startup_pipe[0]); + close(startup_pipe[1]); + + timeout *= 10; + for (;;) { + /* Did we get a signal asking us to exit? */ + if (terminate) + break; + + /* + * Timeout is counted in 100ms with no output, the + * tests print during startup then are silent when + * running so this should ensure they all ran enough + * to install the signal handler, this is especially + * useful in emulation where we will both be slow and + * likely to have a large set of VLs. + */ + ret = epoll_wait(epoll_fd, evs, tests, 100); + if (ret < 0) { + if (errno == EINTR) + continue; + ksft_exit_fail_msg("epoll_wait() failed: %s (%d)\n", + strerror(errno), errno); + } + + /* Output? */ + if (ret > 0) { + for (i = 0; i < ret; i++) { + child_output(evs[i].data.ptr, evs[i].events, + false); + } + continue; + } + + /* Otherwise epoll_wait() timed out */ + + /* + * If the child processes have not produced output they + * aren't actually running the tests yet. + */ + if (!all_children_started) { + seen_children = 0; + + for (i = 0; i < num_children; i++) + if (children[i].output_seen || + children[i].exited) + seen_children++; + + if (seen_children != num_children) { + ksft_print_msg("Waiting for %d children\n", + num_children - seen_children); + continue; + } + + all_children_started = true; + } + + ksft_print_msg("Sending signals, timeout remaining: %d00ms\n", + timeout); + + for (i = 0; i < num_children; i++) + child_tickle(&children[i]); + + /* Negative timeout means run indefinitely */ + if (timeout < 0) + continue; + if (--timeout == 0) + break; + } + + ksft_print_msg("Finishing up...\n"); + terminate = true; + + for (i = 0; i < tests; i++) + child_stop(&children[i]); + + drain_output(false); + + for (i = 0; i < tests; i++) + child_cleanup(&children[i]); + + drain_output(true); + + ksft_print_cnts(); + + return 0; +}

While it's a bit off topic for them the floating point stress tests do give us some coverage of context thrashing cases, and also of active signal delivery separate to the relatively complicated framework in the actual signals tests. Have the tests enable GCS on startup, ignoring failures so they continue to work as before on systems without GCS.

Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/arm64/fp/assembler.h | 15 +++++++++++++++ tools/testing/selftests/arm64/fp/fpsimd-test.S | 2 ++ tools/testing/selftests/arm64/fp/sve-test.S | 2 ++ tools/testing/selftests/arm64/fp/za-test.S | 2 ++ tools/testing/selftests/arm64/fp/zt-test.S | 2 ++ 5 files changed, 23 insertions(+)

diff --git a/tools/testing/selftests/arm64/fp/assembler.h b/tools/testing/selftests/arm64/fp/assembler.h index 9b38a0da407d..7012f9f796de 100644 --- a/tools/testing/selftests/arm64/fp/assembler.h +++ b/tools/testing/selftests/arm64/fp/assembler.h @@ -65,4 +65,19 @@ endfunction bl puts .endm

+#define PR_SET_SHADOW_STACK_STATUS 72 +# define PR_SHADOW_STACK_ENABLE (1UL << 0) + +.macro enable_gcs + // Run with GCS + mov x0, PR_SET_SHADOW_STACK_STATUS + mov x1, PR_SHADOW_STACK_ENABLE + mov x2, xzr + mov x3, xzr + mov x4, xzr + mov x5, xzr + mov x8, #__NR_prctl + svc #0 +.endm + #endif /* ! ASSEMBLER_H */ diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S index 8b960d01ed2e..b16fb7f42e3e 100644 --- a/tools/testing/selftests/arm64/fp/fpsimd-test.S +++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S @@ -215,6 +215,8 @@ endfunction // Main program entry point .globl _start function _start + enable_gcs + mov x23, #0 // signal count

mov w0, #SIGINT diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S index 547d077e3517..e29ab7c4e824 100644 --- a/tools/testing/selftests/arm64/fp/sve-test.S +++ b/tools/testing/selftests/arm64/fp/sve-test.S @@ -378,6 +378,8 @@ endfunction // Main program entry point .globl _start function _start + enable_gcs + mov x23, #0 // Irritation signal count

mov w0, #SIGINT diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S index 9dcd70911397..f789694fa3ea 100644 --- a/tools/testing/selftests/arm64/fp/za-test.S +++ b/tools/testing/selftests/arm64/fp/za-test.S @@ -231,6 +231,8 @@ endfunction // Main program entry point .globl _start function _start + enable_gcs + mov x23, #0 // signal count

mov w0, #SIGINT diff --git a/tools/testing/selftests/arm64/fp/zt-test.S b/tools/testing/selftests/arm64/fp/zt-test.S index d63286397638..ea5e55310705 100644 --- a/tools/testing/selftests/arm64/fp/zt-test.S +++ b/tools/testing/selftests/arm64/fp/zt-test.S @@ -200,6 +200,8 @@ endfunction // Main program entry point .globl _start function _start + enable_gcs + mov x23, #0 // signal count

mov w0, #SIGINT