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 0ead9d8013e8..43fe625b85aa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3964,4 +3964,8 @@ static inline void accept_memory(phys_addr_t start, phys_addr_t end)

#endif

+int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); +int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); +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 3c36aeade991..0de3d6ee18e0 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -305,4 +305,26 @@ 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 2410e3999ebe..b26423a614a9 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2302,6 +2302,21 @@ 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 @@ -2720,6 +2735,21 @@ 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;

Add some documentation of the userspace ABI for Guarded Control Stacks.

Signed-off-by: Mark Brown broonie@kernel.org --- Documentation/arch/arm64/gcs.rst | 228 +++++++++++++++++++++++++++++++++++++ Documentation/arch/arm64/index.rst | 1 + 2 files changed, 229 insertions(+)

diff --git a/Documentation/arch/arm64/gcs.rst b/Documentation/arch/arm64/gcs.rst new file mode 100644 index 000000000000..c0f43961fd4b --- /dev/null +++ b/Documentation/arch/arm64/gcs.rst @@ -0,0 +1,228 @@ +=============================================== +Guarded Control Stack support for AArch64 Linux +=============================================== + +This document outlines briefly the interface provided to userspace by Linux in +order to support use of the ARM Guarded Control Stack (GCS) feature. + +This is an outline of the most important features and issues only and not +intended to be exhaustive. + + + +1. General +----------- + +* GCS is an architecture feature intended to provide greater protection + against return oriented programming (ROP) attacks and to simplify the + implementation of features that need to collect stack traces such as + profiling. + +* When GCS is enabled a separate guarded control stack is maintained by the + PE which is writeable only through specific GCS operations. This + stores the call stack only, when a procedure call instruction is + performed the current PC is pushed onto the GCS and on RET the + address in the LR is verified against that on the top of the GCS. + +* When active current GCS pointer is stored in the system register + GCSPR_EL0. This is readable by userspace but can only be updated + via specific GCS instructions. + +* The architecture provides instructions for switching between guarded + control stacks with checks to ensure that the new stack is a valid + target for switching. + +* The functionality of GCS is similar to that provided by the x86 Shadow + Stack feature, due to sharing of userspace interfaces the ABI refers to + shadow stacks rather than GCS. + +* Support for GCS is reported to userspace via HWCAP2_GCS in the aux vector + AT_HWCAP2 entry. + +* GCS is enabled per thread. While there is support for disabling GCS + at runtime this should be done with great care. + +* GCS memory access faults are reported as normal memory access faults. + +* GCS specific errors (those reported with EC 0x2d) will be reported as + SIGSEGV with a si_code of SEGV_CPERR (control protection error). + +* GCS is supported only for AArch64. + +* On systems where GCS is supported GCSPR_EL0 is always readable by EL0 + regardless of the GCS configuration for the thread. + +* The architecture supports enabling GCS without verifying that return values + in LR match those in the GCS, the LR will be ignored. This is not supported + by Linux. + +* EL0 GCS entries with bit 63 set are reserved for use, one such use is defined + below for signals and should be ignored when parsing the stack if not + understood. + + +2. Enabling and disabling Guarded Control Stacks +------------------------------------------------- + +* GCS is enabled and disabled for a thread via the PR_SET_SHADOW_STACK_STATUS + prctl(), this takes a single flags argument specifying which GCS features + should be used. + +* When set PR_SHADOW_STACK_ENABLE flag allocates a Guarded Control Stack for + and enables GCS for the thread, enabling the functionality controlled by + GCSPRE0_EL1.{nTR, RVCHKEN, PCRSEL}. + +* When set the PR_SHADOW_STACK_PUSH flag enables the functionality controlled + by GCSCRE0_EL1.PUSHMEn, allowing explicit GCS pushes. + +* When set the PR_SHADOW_STACK_WRITE flag enables the functionality controlled + by GCSCRE0_EL1.STREn, allowing explicit stores to the Guarded Control Stack. + +* Any unknown flags will cause PR_SET_SHADOW_STACK_STATUS to return -EINVAL. + +* PR_LOCK_SHADOW_STACK_STATUS is passed a bitmask of features with the same + values as used for PR_SET_SHADOW_STACK_STATUS. Any future changes to the + status of the specified GCS mode bits will be rejected. + +* PR_LOCK_SHADOW_STACK_STATUS allows any bit to be locked, this allows + userspace to prevent changes to any future features. + +* PR_SET_SHADOW_STACK_STATUS and PR_LOCK_SHADOW_STACK_STATUS affect only the + thread the called them, any other running threads will be unaffected. + +* New threads inherit the GCS configuration of the thread that created them. + +* GCS is disabled on exec(). + +* The current GCS configuration for a thread may be read with the + PR_GET_SHADOW_STACK_STATUS prctl(), this returns the same flags that + are passed to PR_SET_SHADOW_STACK_STATUS. + +* If GCS is disabled for a thread after having previously been enabled then + the stack will remain allocated for the lifetime of the thread. At present + any attempt to reenable GCS for the thread will be rejected, this may be + revisited in future. + +* It should be noted that since enabling GCS will result in GCS becoming + active immediately it is not normally possible to return from the function + that invoked the prctl() that enabled GCS. It is expected that the normal + usage will be that GCS is enabled very early in execution of a program. + + + +3. Allocation of Guarded Control Stacks +---------------------------------------- + +* When GCS is enabled for a thread a new Guarded Control Stack will be + allocated for it of size RLIMIT_STACK / 2 or 2 gigabytes, whichever is + smaller. + +* When a new thread is created by a thread which has GCS enabled then a + new Guarded Control Stack will be allocated for the new thread with + half the size of the standard stack. + +* When a stack is allocated by enabling GCS or during thread creation then + the top 8 bytes of the stack will be initialised to 0 and GCSPR_EL0 will + be set to point to the address of this 0 value, this can be used to + detect the top of the stack. + +* Additional Guarded Control Stacks can be allocated using the + map_shadow_stack() system call. + +* Stacks allocated using map_shadow_stack() can optionally have an end of + stack marker and cap placed at the top of the stack. If the flag + SHADOW_STACK_SET_TOKEN is specified a cap will be placed on the stack, + if SHADOW_STACK_SET_MARKER is not specified the cap will be the top 8 + bytes of the stack and if it is specified then the cap will be the next + 8 bytes. While specifying just SHADOW_STACK_SET_MARKER by itself is + valid since the marker is all bits 0 it has no observable effect. + +* Stacks allocated using map_shadow_stack() must be larger than 16 bytes and + must be 16 bytes aligned. + +* When GCS is disabled for a thread the Guarded Control Stack initially + allocated for that thread will be freed. Note carefully that if the + stack has been switched this may not be the stack currently in use by + the thread. + + +4. Signal handling +-------------------- + +* A new signal frame record gcs_context encodes the current GCS mode and + pointer for the interrupted context on signal delivery. This will always + be present on systems that support GCS. + +* The record contains a flag field which reports the current GCS configuration + for the interrupted context as PR_GET_SHADOW_STACK_STATUS would. + +* The signal handler is run with the same GCS configuration as the interrupted + context. + +* When GCS is enabled for the interrupted thread a signal handling specific + GCS cap token will be written to the GCS, this is an architectural GCS cap + token with bit 63 set. The GCSPR_EL0 reported in the signal frame will + point to this cap token. + +* The signal handler will use the same GCS as the interrupted context. + +* When GCS is enabled on signal entry a frame with the address of the signal + return handler will be pushed onto the GCS, allowing return from the signal + handler via RET as normal. This will not be reported in the gcs_context in + the signal frame. + + +5. Signal return +----------------- + +When returning from a signal handler: + +* If there is a gcs_context record in the signal frame then the GCS flags + and GCSPR_EL0 will be restored from that context prior to further + validation. + +* If there is no gcs_context record in the signal frame then the GCS + configuration will be unchanged. + +* If GCS is enabled on return from a signal handler then GCSPR_EL0 must + point to a valid GCS signal cap record, this will be popped from the + GCS prior to signal return. + +* If the GCS configuration is locked when returning from a signal then any + attempt to change the GCS configuration will be treated as an error. This + is true even if GCS was not enabled prior to signal entry. + +* GCS may be disabled via signal return but any attempt to enable GCS via + signal return will be rejected. + + +7. ptrace extensions +--------------------- + +* A new regset NT_ARM_GCS is defined for use with PTRACE_GETREGSET and + PTRACE_SETREGSET. + +* Due to the complexity surrounding allocation and deallocation of stacks and + lack of practical application it is not possible to enable GCS via ptrace. + GCS may be disabled via the ptrace interface. + +* Other GCS modes may be configured via ptrace. + +* Configuration via ptrace ignores locking of GCS mode bits. + + +8. ELF coredump extensions +--------------------------- + +* NT_ARM_GCS notes will be added to each coredump for each thread of the + dumped process. The contents will be equivalent to the data that would + have been read if a PTRACE_GETREGSET of the corresponding type were + executed for each thread when the coredump was generated. + + + +9. /proc extensions +-------------------- + +* Guarded Control Stack pages will include "ss" in their VmFlags in + /proc/<pid>/smaps. diff --git a/Documentation/arch/arm64/index.rst b/Documentation/arch/arm64/index.rst index d08e924204bf..dcf3ee3eb8c0 100644 --- a/Documentation/arch/arm64/index.rst +++ b/Documentation/arch/arm64/index.rst @@ -14,6 +14,7 @@ ARM64 Architecture booting cpu-feature-registers elf_hwcaps + gcs hugetlbpage kdump legacy_instructions

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 65866bf819c3..20c12e65a304 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -1780,6 +1780,41 @@ Sysreg SMCR_EL1 3 0 1 2 6 Fields SMCR_ELx EndSysreg

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

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

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

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

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

Note that GCSSTTR is used to store to EL0.

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

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

#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */

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

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

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/cpufeature.h | 6 ++++++ arch/arm64/kernel/cpufeature.c | 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 96e50227f940..189783142a96 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -831,6 +831,12 @@ static inline bool system_supports_tlb_range(void) cpus_have_const_cap(ARM64_HAS_TLB_RANGE); }

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

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f9d456fe132d..91a14a6ccb04 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -254,6 +254,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { };

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

+static void cpu_enable_gcs(const struct arm64_cpu_capabilities *__unused) +{ + /* GCS is not currently used at EL1 */ + write_sysreg_s(0, SYS_GCSCR_EL1); +} + /* Internal helper functions to match cpu capability type */ static bool cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) @@ -2715,6 +2723,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .min_field_value = ID_AA64MMFR2_EL1_EVT_IMP, .matches = has_cpuid_feature, }, + { + .desc = "Guarded Control Stack (GCS)", + .capability = ARM64_HAS_GCS, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .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 c80ed4f3cbce..ab582f592131 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -26,6 +26,7 @@ HAS_ECV HAS_ECV_CNTPOFF HAS_EPAN HAS_EVT +HAS_GCS HAS_GENERIC_AUTH HAS_GENERIC_AUTH_ARCH_QARMA3 HAS_GENERIC_AUTH_ARCH_QARMA5

Use VM_HIGH_ARCH_5 for guarded control stack pages.

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

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

Note that there is no guarantee that every flag and associated mnemonic will diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index cfab855fe7e9..e8c50848bb16 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -711,6 +711,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ #ifdef CONFIG_X86_USER_SHADOW_STACK [ilog2(VM_SHADOW_STACK)] = "ss", +#endif +#ifdef CONFIG_ARM64_GCS + [ilog2(VM_SHADOW_STACK)] = "ss", #endif }; size_t i; diff --git a/include/linux/mm.h b/include/linux/mm.h index 43fe625b85aa..3f939ae212e5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -372,7 +372,17 @@ extern unsigned int kobjsize(const void *objp); * having a PAGE_SIZE guard gap. */ # define VM_SHADOW_STACK VM_HIGH_ARCH_5 -#else +#endif + +#if defined(CONFIG_ARM64_GCS) +/* + * arm64's Guarded Control Stack implements similar functionality and + * has similar constraints to shadow stacks. + */ +# define VM_SHADOW_STACK VM_HIGH_ARCH_5 +#endif + +#ifndef VM_SHADOW_STACK # define VM_SHADOW_STACK VM_NONE #endif

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 8e5ffb58f83e..45f3a7dcfd95 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 @@ -186,6 +194,15 @@ 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 58e5eb27da68..9c84e200217b 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -94,8 +94,8 @@ #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)

-#define HCRX_GUEST_FLAGS (HCRX_EL2_SMPME | HCRX_EL2_TCR2En) -#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En) +#define HCRX_GUEST_FLAGS (HCRX_EL2_SMPME | HCRX_EL2_TCR2En | HCRX_EL2_GCSEn) +#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 8c8addb4194c..75f3960cad39 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -305,6 +305,9 @@ HWCAP2_SMEF16F16 HWCAP2_MOPS Functionality implied by ID_AA64ISAR2_EL1.MOPS == 0b0001.

+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 692b1ec663b2..39f397a2b5b2 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -138,6 +138,7 @@ #define KERNEL_HWCAP_SME_B16B16 __khwcap2_feature(SME_B16B16) #define KERNEL_HWCAP_SME_F16F16 __khwcap2_feature(SME_F16F16) #define KERNEL_HWCAP_MOPS __khwcap2_feature(MOPS) +#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 a2cac4305b1e..7510c35e6864 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -103,5 +103,6 @@ #define HWCAP2_SME_B16B16 (1UL << 41) #define HWCAP2_SME_F16F16 (1UL << 42) #define HWCAP2_MOPS (1UL << 43) +#define HWCAP2_GCS (1UL << 44)

#endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 91a14a6ccb04..7b46e01140c4 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2840,6 +2840,9 @@ 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 58622dc85917..451fbbeffa39 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -126,6 +126,7 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SME_B16B16] = "smeb16b16", [KERNEL_HWCAP_SME_F16F16] = "smef16f16", [KERNEL_HWCAP_MOPS] = "mops", + [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 | 78 +++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 70 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3fe516b32577..ec392207a475 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 (!cpus_have_const_cap(ARM64_HAS_EPAN)) vm_flags |= VM_EXEC; + /* + * Upgrade read faults to write faults, GCS reads must + * occur on a page marked as GCS so we need to trigger + * copy on write always. + */ + if (is_gcs_fault(esr)) + mm_flags |= FAULT_FLAG_WRITE; }

if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) { @@ -595,6 +644,19 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, if (!vma) goto lock_mmap;

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

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

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

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

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

#else

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

#endif

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index b8a42471aea3..1de6371ca2d8 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -284,9 +284,34 @@ static void flush_gcs(void) } }

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

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

#endif

@@ -368,6 +393,7 @@ 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));

@@ -409,6 +435,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.uw.tp_value = tls; p->thread.tpidr2_el0 = 0; } + + ret = copy_thread_gcs(p, clone_flags, args->stack_size); + if (ret != 0) + return ret; } else { /* * A kthread has no context to ERET to, so ensure any buggy diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index b0a67efc522b..1e059c37088d 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -8,6 +8,62 @@ #include <asm/cpufeature.h> #include <asm/page.h>

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

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

Implement this for arm64. 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 | 58 ++++++++++++++++++++++++++++++++++++++- include/linux/syscalls.h | 1 + include/uapi/asm-generic/unistd.h | 5 +++- kernel/sys_ni.c | 1 + 4 files changed, 63 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index 64c9f9a85925..b41700d6695e 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -52,7 +52,6 @@ unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, return 0;

size = gcs_size(size); - addr = alloc_gcs(0, size, 0, 0); if (IS_ERR_VALUE(addr)) return addr; @@ -64,6 +63,63 @@ 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, cap_offset; + + if (!system_supports_gcs()) + return -EOPNOTSUPP; + + if (flags & ~(SHADOW_STACK_SET_TOKEN | SHADOW_STACK_SET_MARKER)) + return -EINVAL; + + if (addr % 8) + 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); + + ret = copy_to_user_gcs(cap_ptr, &cap_val, 1); + if (ret != 0) { + vm_munmap(addr, size); + return -EFAULT; + } + } + + return addr; +} + /* * Apply the GCS mode configured for the specified task to the * hardware. diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 03e3d0121d5e..7f6dc0988197 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -953,6 +953,7 @@ asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long l asmlinkage long sys_cachestat(unsigned int fd, struct cachestat_range __user *cstat_range, struct cachestat __user *cstat, unsigned int flags); +asmlinkage long sys_map_shadow_stack(unsigned long addr, unsigned long size, unsigned int flags);

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

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

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

/* s390 */ COND_SYSCALL(s390_pci_mmio_read);

Add a context for the GCS state and include it in the signal context when running on a system that supports GCS. We reuse the same flags that the prctl() uses to specify which GCS features are enabled and also provide the current GCS pointer.

We do not support enabling GCS via signal return, there is a conflict between specifying GCSPR_EL0 and allocation of a new GCS and this is not an ancticipated use case. We also enforce GCS configuration locking on signal return.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/uapi/asm/sigcontext.h | 9 +++ arch/arm64/kernel/signal.c | 107 +++++++++++++++++++++++++++++++ 2 files changed, 116 insertions(+)

diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index f23c1dc3f002..7b66d245f2d2 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -168,6 +168,15 @@ struct zt_context { __u16 __reserved[3]; };

+#define GCS_MAGIC 0x47435300 + +struct gcs_context { + struct _aarch64_ctx head; + __u64 gcspr; + __u64 features_enabled; + __u64 reserved; +}; + #endif /* !__ASSEMBLY__ */

#include <asm/sve_context.h> diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 1c31be0f373e..4cc0c7928cb3 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -87,6 +87,7 @@ struct rt_sigframe_user_layout {

unsigned long fpsimd_offset; unsigned long esr_offset; + unsigned long gcs_offset; unsigned long sve_offset; unsigned long tpidr2_offset; unsigned long za_offset; @@ -213,6 +214,8 @@ struct user_ctxs { u32 za_size; struct zt_context __user *zt; u32 zt_size; + struct gcs_context __user *gcs; + u32 gcs_size; };

static int preserve_fpsimd_context(struct fpsimd_context __user *ctx) @@ -605,6 +608,82 @@ extern int restore_zt_context(struct user_ctxs *user);

#endif /* ! CONFIG_ARM64_SME */

+#ifdef CONFIG_ARM64_GCS + +static int preserve_gcs_context(struct gcs_context __user *ctx) +{ + int err = 0; + u64 gcspr; + + /* + * We will add a cap token to the frame, include it in the + * GCSPR_EL0 we report to support stack switching via + * sigreturn. + */ + gcs_preserve_current_state(); + gcspr = current->thread.gcspr_el0; + if (task_gcs_el0_enabled(current)) + gcspr -= 8; + + __put_user_error(GCS_MAGIC, &ctx->head.magic, err); + __put_user_error(sizeof(*ctx), &ctx->head.size, err); + __put_user_error(gcspr, &ctx->gcspr, err); + __put_user_error(current->thread.gcs_el0_mode, + &ctx->features_enabled, err); + + return err; +} + +static int restore_gcs_context(struct user_ctxs *user) +{ + u64 gcspr, enabled; + int err = 0; + + if (user->gcs_size != sizeof(*user->gcs)) + return -EINVAL; + + __get_user_error(gcspr, &user->gcs->gcspr, err); + __get_user_error(enabled, &user->gcs->features_enabled, err); + if (err) + return err; + + /* Don't allow unknown modes */ + if (enabled & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK) + return -EINVAL; + + err = gcs_check_locked(current, enabled); + if (err != 0) + return err; + + /* Don't allow enabling */ + if (!task_gcs_el0_enabled(current) && + (enabled & PR_SHADOW_STACK_ENABLE)) + return -EINVAL; + + /* If we are disabling disable everything */ + if (!(enabled & PR_SHADOW_STACK_ENABLE)) + enabled = 0; + + current->thread.gcs_el0_mode = enabled; + + /* + * We let userspace set GCSPR_EL0 to anything here, we will + * validate later in gcs_restore_signal(). + */ + current->thread.gcspr_el0 = gcspr; + write_sysreg_s(current->thread.gcspr_el0, SYS_GCSPR_EL0); + + return 0; +} + +#else /* ! CONFIG_ARM64_GCS */ + +/* Turn any non-optimised out attempts to use these into a link error: */ +extern int preserve_gcs_context(void __user *ctx); +extern int restore_gcs_context(struct user_ctxs *user); + +#endif /* ! CONFIG_ARM64_GCS */ + static int parse_user_sigframe(struct user_ctxs *user, struct rt_sigframe __user *sf) { @@ -621,6 +700,7 @@ static int parse_user_sigframe(struct user_ctxs *user, user->tpidr2 = NULL; user->za = NULL; user->zt = NULL; + user->gcs = NULL;

if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; @@ -715,6 +795,17 @@ static int parse_user_sigframe(struct user_ctxs *user, user->zt_size = size; break;

+ case GCS_MAGIC: + if (!system_supports_gcs()) + goto invalid; + + if (user->gcs) + goto invalid; + + user->gcs = (struct gcs_context __user *)head; + user->gcs_size = size; + break; + case EXTRA_MAGIC: if (have_extra_context) goto invalid; @@ -834,6 +925,9 @@ static int restore_sigframe(struct pt_regs *regs, err = restore_fpsimd_context(&user); }

+ if (err == 0 && system_supports_gcs() && user.gcs) + err = restore_gcs_context(&user); + if (err == 0 && system_supports_tpidr2() && user.tpidr2) err = restore_tpidr2_context(&user);

@@ -948,6 +1042,13 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, return err; }

+ if (system_supports_gcs()) { + err = sigframe_alloc(user, &user->gcs_offset, + sizeof(struct gcs_context)); + if (err) + return err; + } + if (system_supports_sve() || system_supports_sme()) { unsigned int vq = 0;

@@ -1041,6 +1142,12 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, __put_user_error(current->thread.fault_code, &esr_ctx->esr, err); }

+ if (system_supports_gcs() && err == 0 && user->gcs_offset) { + struct gcs_context __user *gcs_ctx = + apply_user_offset(user, user->gcs_offset); + err |= preserve_gcs_context(gcs_ctx); + } + /* Scalable Vector Extension state (including streaming), if present */ if ((system_supports_sve() || system_supports_sme()) && err == 0 && user->sve_offset) {

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 | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a2511b30d0f6..b5ef1a698770 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -2093,6 +2093,25 @@ 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_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 | 356 ++++++++++++++++++++++++++ tools/testing/selftests/arm64/gcs/gcs-util.h | 87 +++++++ 5 files changed, 463 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..0fac554a3c4d --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/basic-gcs.c @@ -0,0 +1,356 @@ +// 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 "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; +} + +typedef bool (*gcs_test)(void); + +static struct { + char *name; + gcs_test test; + bool needs_enable; +} tests[] = { + { "read_status", read_status }, + { "base_enable", base_enable, true }, + { "read_gcspr_el0", read_gcspr_el0 }, + { "enable_writeable", enable_writeable, true }, + { "enable_push_pop", enable_push_pop, true }, + { "enable_all", enable_all, true }, + { "enable_invalid", enable_invalid, true }, + { "map_guarded_stack", map_guarded_stack }, + { "fork", test_fork }, +}; + +int main(void) +{ + int i, ret; + unsigned long gcs_mode; + + 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..c517f1a710c5 --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/gcs-util.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 ARM Limited. + */ + +#ifndef GCS_UTIL_H +#define GCS_UTIL_H + +#include <stdbool.h> + +#ifndef __NR_map_shadow_stack +#define __NR_map_shadow_stack 452 +#endif + +#ifndef __NR_prctl +#define __NR_prctl 167 +#endif + +/* Shadow Stack/Guarded Control Stack interface */ +#define PR_GET_SHADOW_STACK_STATUS 71 +#define PR_SET_SHADOW_STACK_STATUS 72 +#define PR_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 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; +}