Since multiple architectures have support for shadow stacks and we need to select support for this feature in several places in the generic code provide a generic config option that the architectures can select.

Suggested-by: David Hildenbrand david@redhat.com Acked-by: David Hildenbrand david@redhat.com Reviewed-by: Deepak Gupta debug@rivosinc.com Reviewed-by: Rick Edgecombe rick.p.edgecombe@intel.com Reviewed-by: Mike Rapoport (IBM) rppt@kernel.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Reviewed-by: Kees Cook kees@kernel.org Tested-by: Kees Cook kees@kernel.org Acked-by: Shuah Khan skhan@linuxfoundation.org Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Signed-off-by: Mark Brown broonie@kernel.org --- arch/x86/Kconfig | 1 + fs/proc/task_mmu.c | 2 +- include/linux/mm.h | 2 +- mm/Kconfig | 6 ++++++ 4 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 007bab9f2a0e..320e1f411163 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1957,6 +1957,7 @@ config X86_USER_SHADOW_STACK depends on AS_WRUSS depends on X86_64 select ARCH_USES_HIGH_VMA_FLAGS + select ARCH_HAS_USER_SHADOW_STACK select X86_CET help Shadow stack protection is a hardware feature that detects function diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5f171ad7b436..0ea49725f524 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -984,7 +984,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR [ilog2(VM_UFFD_MINOR)] = "ui", #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ -#ifdef CONFIG_X86_USER_SHADOW_STACK +#ifdef CONFIG_ARCH_HAS_USER_SHADOW_STACK [ilog2(VM_SHADOW_STACK)] = "ss", #endif #ifdef CONFIG_64BIT diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..3357625c1db3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -342,7 +342,7 @@ extern unsigned int kobjsize(const void *objp); #endif #endif /* CONFIG_ARCH_HAS_PKEYS */

-#ifdef CONFIG_X86_USER_SHADOW_STACK +#ifdef CONFIG_ARCH_HAS_USER_SHADOW_STACK /* * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of * support core mm. diff --git a/mm/Kconfig b/mm/Kconfig index b72e7d040f78..3167be663bca 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1263,6 +1263,12 @@ config IOMMU_MM_DATA config EXECMEM bool

+config ARCH_HAS_USER_SHADOW_STACK + bool + help + The architecture has hardware support for userspace shadow call + stacks (eg, x86 CET, arm64 GCS or RISC-V Zicfiss). + source "mm/damon/Kconfig"

endmenu

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.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com 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 3357625c1db3..96faf26b6083 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4201,4 +4201,8 @@ void vma_pgtable_walk_end(struct vm_area_struct *vma);

int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *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 35791791a879..557a3d2ac1d4 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -328,4 +328,26 @@ struct prctl_mm_map { # define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC 0x10 /* Clear the aspect on exec */ # define PR_PPC_DEXCR_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 74 + +/* + * 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 75 +# 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 76 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index 3a2df1bd9f64..7e0c10e867cf 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2324,6 +2324,21 @@ 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 @@ -2782,6 +2797,21 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_RISCV_SET_ICACHE_FLUSH_CTX: error = RISCV_SET_ICACHE_FLUSH_CTX(arg2, arg3); 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;

In preparation for adding arm64 GCS support make the map_shadow_stack() SHADOW_STACK_SET_TOKEN flag generic and add _SET_MARKER. The existing flag indicates that a token usable for stack switch should be added to the top of the newly mapped GCS region while the new flag indicates that a top of stack marker suitable for use by unwinders should be added above that.

For arm64 the top of stack marker is all bits 0.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/x86/include/uapi/asm/mman.h | 3 --- include/uapi/asm-generic/mman.h | 4 ++++ 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h index 46cdc941f958..ac1e6277212b 100644 --- a/arch/x86/include/uapi/asm/mman.h +++ b/arch/x86/include/uapi/asm/mman.h @@ -5,9 +5,6 @@ #define MAP_32BIT 0x40 /* only give out 32bit addresses */ #define MAP_ABOVE4G 0x80 /* only map above 4GB */

-/* Flags for map_shadow_stack(2) */ -#define SHADOW_STACK_SET_TOKEN (1ULL << 0) /* Set up a restore token in the shadow stack */ - #include <asm-generic/mman.h>

#endif /* _ASM_X86_MMAN_H */ diff --git a/include/uapi/asm-generic/mman.h b/include/uapi/asm-generic/mman.h index 57e8195d0b53..5e3d61ddbd8c 100644 --- a/include/uapi/asm-generic/mman.h +++ b/include/uapi/asm-generic/mman.h @@ -19,4 +19,8 @@ #define MCL_FUTURE 2 /* lock all future mappings */ #define MCL_ONFAULT 4 /* lock all pages that are faulted in */

+#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 marker in the shadow stack */ + + #endif /* __ASM_GENERIC_MMAN_H */

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 present. There is also a HCRX_EL2 control to make GCS operations functional.

Since if GCS is enabled any function call instruction will cause a fault we also require that the feature be specifically disabled, existing kernels implicitly have this requirement and especially given that the MMU must be disabled it is difficult to see a situation where leaving GCS enabled would be reasonable.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- Documentation/arch/arm64/booting.rst | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+)

diff --git a/Documentation/arch/arm64/booting.rst b/Documentation/arch/arm64/booting.rst index b57776a68f15..aed6e9f47cf3 100644 --- a/Documentation/arch/arm64/booting.rst +++ b/Documentation/arch/arm64/booting.rst @@ -411,6 +411,38 @@ Before jumping into the kernel, the following conditions must be met:

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

+ - For CPUs with Guarded Control Stacks (FEAT_GCS): + + - GCSCR_EL1 must be initialised to 0. + + - GCSCRE0_EL1 must be initialised to 0. + + - If EL3 is present: + + - SCR_EL3.GCSEn (bit 39) must be initialised to 0b1. + + - If EL2 is present: + + - GCSCR_EL2 must be initialised to 0. + + - If the kernel is entered at EL1 and EL2 is present: + + - HCRX_EL2.GCSEn must be initialised to 0b1. + + - 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

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.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Acked-by: Catalin Marinas catalin.marinas@arm.com 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 28f665e0975a..6aba10e38d1c 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -502,4 +502,26 @@ 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 */

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.

We also initialise GCSCR_EL1 and GCSCRE0_EL1 to ensure that we can execute function call instructions without faulting regardless of the state when the kernel is started.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/el2_setup.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+)

diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index fd87c4b8f984..09211aebcf03 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 @@ -191,6 +199,15 @@ 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 @@ -204,6 +221,17 @@ .Lskip_fgt_@: .endm

+.macro __init_el2_gcs + mrs_s x1, SYS_ID_AA64PFR1_EL1 + ubfx x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4 + cbz x1, .Lskip_gcs_@ + + /* Ensure GCS is not enabled when we start trying to do BLs */ + msr_s SYS_GCSCR_EL1, xzr + msr_s SYS_GCSCRE0_EL1, xzr +.Lskip_gcs_@: +.endm + .macro __init_el2_nvhe_prepare_eret mov x0, #INIT_PSTATE_EL1 msr spsr_el2, x0 @@ -229,6 +257,7 @@ __init_el2_nvhe_idregs __init_el2_cptr __init_el2_fgt + __init_el2_gcs .endm

#ifndef __KVM_NVHE_HYPERVISOR__

Pages used for guarded control stacks need to be described to the hardware using the Permission Indirection Extension, GCS is not supported without PIE. In order to support copy on write for guarded stacks we allocate two values, one for active GCSs and one for GCS pages marked as read only prior to copy.

Since the actual effect is defined using PIE the specific bit pattern used does not matter to the hardware but we choose two values which differ only in PTE_WRITE in order to help share code with non-PIE cases.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/pgtable-prot.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index b11cfb9fdd37..545d54c88520 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -144,15 +144,23 @@ static inline bool __pure lpa2_is_enabled(void) /* 6: PTE_PXN | PTE_WRITE */ /* 7: PAGE_SHARED_EXEC PTE_PXN | PTE_WRITE | PTE_USER */ /* 8: PAGE_KERNEL_ROX PTE_UXN */ -/* 9: PTE_UXN | PTE_USER */ +/* 9: PAGE_GCS_RO PTE_UXN | PTE_USER */ /* a: PAGE_KERNEL_EXEC PTE_UXN | PTE_WRITE */ -/* b: PTE_UXN | PTE_WRITE | PTE_USER */ +/* b: PAGE_GCS PTE_UXN | PTE_WRITE | PTE_USER */ /* c: PAGE_KERNEL_RO PTE_UXN | PTE_PXN */ /* d: PAGE_READONLY PTE_UXN | PTE_PXN | PTE_USER */ /* e: PAGE_KERNEL PTE_UXN | PTE_PXN | PTE_WRITE */ /* f: PAGE_SHARED PTE_UXN | PTE_PXN | PTE_WRITE | PTE_USER */

+#define _PAGE_GCS (_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_WRITE | PTE_USER) +#define _PAGE_GCS_RO (_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_USER) + +#define PAGE_GCS __pgprot(_PAGE_GCS) +#define PAGE_GCS_RO __pgprot(_PAGE_GCS_RO) + #define PIE_E0 ( \ + PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS), PIE_GCS) | \ + PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS_RO), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_X_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RWX) | \ @@ -160,6 +168,8 @@ static inline bool __pure lpa2_is_enabled(void) PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED), PIE_RW))

#define PIE_E1 ( \ + PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS), PIE_NONE_O) | \ + PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS_RO), PIE_NONE_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_NONE_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RW) | \

Map pages flagged as being part of a GCS as such rather than using the full set of generic VM flags.

This is done using a conditional rather than extending the size of protection_map since that would make for a very sparse array.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/mman.h | 9 +++++++++ arch/arm64/mm/mmap.c | 9 ++++++++- 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h index c21849ffdd88..37dfd2882f04 100644 --- a/arch/arm64/include/asm/mman.h +++ b/arch/arm64/include/asm/mman.h @@ -61,6 +61,15 @@ static inline bool arch_validate_flags(unsigned long vm_flags) return false; }

+ if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) { + /* An executable GCS isn't a good idea. */ + if (vm_flags & VM_EXEC) + return false; + + /* The memory management core should prevent this */ + VM_WARN_ON(vm_flags & VM_SHARED); + } + return true;

} diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 642bdf908b22..5943898f366b 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -83,8 +83,15 @@ arch_initcall(adjust_protection_map);

pgprot_t vm_get_page_prot(unsigned long vm_flags) { - pteval_t prot = pgprot_val(protection_map[vm_flags & + pteval_t prot; + + /* Short circuit GCS to avoid bloating the table. */ + if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) { + prot = _PAGE_GCS_RO; + } else { + prot = pgprot_val(protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]); + }

if (vm_flags & VM_ARM64_BTI) prot |= PTE_GP;

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

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- Documentation/arch/arm64/elf_hwcaps.rst | 2 ++ 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, 8 insertions(+)

diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index 448c1664879b..cf87be078f33 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -365,6 +365,8 @@ HWCAP2_SME_SF8DP2 HWCAP2_SME_SF8DP4 Functionality implied by ID_AA64SMFR0_EL1.SF8DP4 == 0b1.

+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 4edd3b61df11..fd7e162e7e39 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -157,6 +157,7 @@ #define KERNEL_HWCAP_SME_SF8FMA __khwcap2_feature(SME_SF8FMA) #define KERNEL_HWCAP_SME_SF8DP4 __khwcap2_feature(SME_SF8DP4) #define KERNEL_HWCAP_SME_SF8DP2 __khwcap2_feature(SME_SF8DP2) +#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 285610e626f5..328fb7843e2f 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -122,5 +122,6 @@ #define HWCAP2_SME_SF8FMA (1UL << 60) #define HWCAP2_SME_SF8DP4 (1UL << 61) #define HWCAP2_SME_SF8DP2 (1UL << 62) +#define HWCAP2_GCS (1UL << 63)

#endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 315bd7be1106..e3e8290a4447 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2994,6 +2994,9 @@ 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 09eeaa24d456..2f539e3101ee 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -143,6 +143,7 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SME_SF8FMA] = "smesf8fma", [KERNEL_HWCAP_SME_SF8DP4] = "smesf8dp4", [KERNEL_HWCAP_SME_SF8DP2] = "smesf8dp2", + [KERNEL_HWCAP_GCS] = "gcs", };

#ifdef CONFIG_COMPAT

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

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

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

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/esr.h | 28 +++++++++++++++++++++++++++- arch/arm64/include/asm/exception.h | 2 ++ arch/arm64/kernel/entry-common.c | 23 +++++++++++++++++++++++ arch/arm64/kernel/traps.c | 11 +++++++++++ 4 files changed, 63 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 56c148890daf..0c231adf3867 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -51,7 +51,8 @@ #define ESR_ELx_EC_FP_EXC32 (0x28) /* Unallocated EC: 0x29 - 0x2B */ #define ESR_ELx_EC_FP_EXC64 (0x2C) -/* Unallocated EC: 0x2D - 0x2E */ +#define ESR_ELx_EC_GCS (0x2D) +/* Unallocated EC: 0x2E */ #define ESR_ELx_EC_SERROR (0x2F) #define ESR_ELx_EC_BREAKPT_LOW (0x30) #define ESR_ELx_EC_BREAKPT_CUR (0x31) @@ -385,6 +386,31 @@ #define ESR_ELx_MOPS_ISS_SRCREG(esr) (((esr) & (UL(0x1f) << 5)) >> 5) #define ESR_ELx_MOPS_ISS_SIZEREG(esr) (((esr) & (UL(0x1f) << 0)) >> 0)

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

diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index f296662590c7..674518464718 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -57,6 +57,8 @@ void do_el0_undef(struct pt_regs *regs, unsigned long esr); void do_el1_undef(struct pt_regs *regs, unsigned long esr); void do_el0_bti(struct pt_regs *regs); void do_el1_bti(struct pt_regs *regs, unsigned long esr); +void do_el0_gcs(struct pt_regs *regs, unsigned long esr); +void do_el1_gcs(struct pt_regs *regs, unsigned long esr); void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr, struct pt_regs *regs); void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs); diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index b77a15955f28..54f2d16d82f4 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -463,6 +463,15 @@ static void noinstr el1_bti(struct pt_regs *regs, unsigned long esr) exit_to_kernel_mode(regs); }

+static void noinstr el1_gcs(struct pt_regs *regs, unsigned long esr) +{ + enter_from_kernel_mode(regs); + local_daif_inherit(regs); + do_el1_gcs(regs, esr); + local_daif_mask(); + exit_to_kernel_mode(regs); +} + static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -505,6 +514,9 @@ asmlinkage void noinstr el1h_64_sync_handler(struct pt_regs *regs) case ESR_ELx_EC_BTI: el1_bti(regs, esr); break; + case ESR_ELx_EC_GCS: + el1_gcs(regs, esr); + break; case ESR_ELx_EC_BREAKPT_CUR: case ESR_ELx_EC_SOFTSTP_CUR: case ESR_ELx_EC_WATCHPT_CUR: @@ -684,6 +696,14 @@ static void noinstr el0_mops(struct pt_regs *regs, unsigned long esr) exit_to_user_mode(regs); }

+static void noinstr el0_gcs(struct pt_regs *regs, unsigned long esr) +{ + enter_from_user_mode(regs); + local_daif_restore(DAIF_PROCCTX); + do_el0_gcs(regs, esr); + exit_to_user_mode(regs); +} + static void noinstr el0_inv(struct pt_regs *regs, unsigned long esr) { enter_from_user_mode(regs); @@ -766,6 +786,9 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs) case ESR_ELx_EC_MOPS: el0_mops(regs, esr); break; + case ESR_ELx_EC_GCS: + el0_gcs(regs, esr); + break; case ESR_ELx_EC_BREAKPT_LOW: case ESR_ELx_EC_SOFTSTP_LOW: case ESR_ELx_EC_WATCHPT_LOW: diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 9e22683aa921..d410dcc12ed8 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -500,6 +500,16 @@ void do_el1_bti(struct pt_regs *regs, unsigned long esr) die("Oops - BTI", regs, esr); }

+void do_el0_gcs(struct pt_regs *regs, unsigned long esr) +{ + force_signal_inject(SIGSEGV, SEGV_CPERR, regs->pc, 0); +} + +void do_el1_gcs(struct pt_regs *regs, unsigned long esr) +{ + die("Oops - GCS", regs, esr); +} + void do_el0_fpac(struct pt_regs *regs, unsigned long esr) { force_signal_inject(SIGILL, ILL_ILLOPN, regs->pc, esr); @@ -838,6 +848,7 @@ static const char *esr_class_str[] = { [ESR_ELx_EC_MOPS] = "MOPS", [ESR_ELx_EC_FP_EXC32] = "FP (AArch32)", [ESR_ELx_EC_FP_EXC64] = "FP (AArch64)", + [ESR_ELx_EC_GCS] = "Guarded Control Stack", [ESR_ELx_EC_SERROR] = "SError", [ESR_ELx_EC_BREAKPT_LOW] = "Breakpoint (lower EL)", [ESR_ELx_EC_BREAKPT_CUR] = "Breakpoint (current EL)",

When a new thread is created by a thread with GCS enabled the GCS needs to be specified along with the regular stack.

Unfortunately plain clone() is not extensible and existing clone3() users will not specify a stack so all existing code would be broken if we mandated specifying the stack explicitly. 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 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, 2G). 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 will be freed when the thread exits.

Reviewed-by: Catalin Marinas catalin.marinas@arm.com Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/gcs.h | 9 ++++++ arch/arm64/kernel/process.c | 26 ++++++++++++++++ arch/arm64/mm/gcs.c | 70 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 105 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 3622956b6515..de59aa16919c 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); + + p->thread.gcs_el0_mode = current->thread.gcs_el0_mode; + p->thread.gcs_el0_locked = current->thread.gcs_el0_locked; + + 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

@@ -303,6 +323,7 @@ void flush_thread(void) void arch_release_task_struct(struct task_struct *tsk) { fpsimd_release_task(tsk); + gcs_free(tsk); }

int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) @@ -366,6 +387,7 @@ 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));

@@ -407,6 +429,10 @@ 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..6e8a5e14fff1 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -5,9 +5,69 @@ #include <linux/syscalls.h> #include <linux/types.h>

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

+static unsigned long alloc_gcs(unsigned long addr, unsigned long size) +{ + 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/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 (!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); + 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. @@ -30,6 +90,16 @@ void gcs_set_el0_mode(struct task_struct *task)

void gcs_free(struct task_struct *task) { + + /* + * When fork() with CLONE_VM fails, the child (tsk) already + * has a GCS allocated, and exit_thread() calls this function + * to free it. In this case the parent (current) and the + * child share the same mm struct. + */ + if (!task->mm || task->mm != current->mm) + return; + if (task->thread.gcs_base) vm_munmap(task->thread.gcs_base, task->thread.gcs_size);

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.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/mm/gcs.c | 64 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+)

diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index 979e02cece93..cdd4a9d7ff7d 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -68,6 +68,70 @@ 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 (!PAGE_ALIGNED(addr)) + return -EINVAL; + + if (size == 8 || !IS_ALIGNED(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); + 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 ordered before standard + * memory accesses to the same location. + */ + 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.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/gcs.h | 1 + arch/arm64/kernel/signal.c | 118 +++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 114 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 4a77f4976e11..3f52ce11f791 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 +35,15 @@ #include <asm/traps.h> #include <asm/vdso.h>

+#ifdef CONFIG_ARM64_GCS +#define GCS_SIGNAL_CAP(addr) (((unsigned long)addr) & GCS_CAP_ADDR_MASK) + +static bool gcs_signal_cap_valid(u64 addr, u64 val) +{ + return val == GCS_SIGNAL_CAP(addr); +} +#endif + /* * Do a signal return; undo the signal stack. These are aligned to 128-bit. */ @@ -860,6 +870,58 @@ static int restore_sigframe(struct pt_regs *regs, return err; }

+#ifdef CONFIG_ARM64_GCS +static int gcs_restore_signal(void) +{ + unsigned long __user *gcspr_el0; + u64 cap; + int ret; + + if (!system_supports_gcs()) + return 0; + + if (!(current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE)) + return 0; + + gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0); + + /* + * Ensure that any changes to the GCS done via GCS operations + * are visible to the normal reads we do to validate the + * token. + */ + gcsb_dsync(); + + /* + * GCSPR_EL0 should be pointing at a capped GCS, read the cap. + * We don't enforce that this is in a GCS page, if it is not + * then faults will be generated on GCS operations - the main + * concern is to protect GCS pages. + */ + ret = copy_from_user(&cap, gcspr_el0, sizeof(cap)); + if (ret) + return -EFAULT; + + /* + * Check that the cap is the actual GCS before replacing it. + */ + if (!gcs_signal_cap_valid((u64)gcspr_el0, cap)) + return -EINVAL; + + /* Invalidate the token to prevent reuse */ + put_user_gcs(0, (__user void*)gcspr_el0, &ret); + if (ret != 0) + return -EFAULT; + + write_sysreg_s(gcspr_el0 + 1, 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(); @@ -883,6 +945,9 @@ SYSCALL_DEFINE0(rt_sigreturn) if (restore_sigframe(regs, frame)) goto badframe;

+ if (gcs_restore_signal()) + goto badframe; + if (restore_altstack(&frame->uc.uc_stack)) goto badframe;

@@ -1130,7 +1195,48 @@ 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; + + 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; @@ -1138,7 +1244,7 @@ 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 @@ -1178,12 +1284,14 @@ 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, @@ -1206,7 +1314,7 @@ 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;

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

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/uapi/asm/ptrace.h | 8 ++++++ arch/arm64/kernel/ptrace.c | 54 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 3 files changed, 63 insertions(+)

diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 7fa2f7036aa7..0f39ba4f3efd 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -324,6 +324,14 @@ struct user_za_header { #define ZA_PT_SIZE(vq) \ (ZA_PT_ZA_OFFSET + ZA_PT_ZA_SIZE(vq))

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

#endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 0d022599eb61..88f525b0c4fb 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -34,6 +34,7 @@ #include <asm/cpufeature.h> #include <asm/debug-monitors.h> #include <asm/fpsimd.h> +#include <asm/gcs.h> #include <asm/mte.h> #include <asm/pointer_auth.h> #include <asm/stacktrace.h> @@ -1440,6 +1441,46 @@ static int tagged_addr_ctrl_set(struct task_struct *target, const struct } #endif

+#ifdef CONFIG_ARM64_GCS +static int gcs_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct user_gcs user_gcs; + + if (target == current) + gcs_preserve_current_state(); + + user_gcs.features_enabled = target->thread.gcs_el0_mode; + user_gcs.features_locked = target->thread.gcs_el0_locked; + user_gcs.gcspr_el0 = target->thread.gcspr_el0; + + return membuf_write(&to, &user_gcs, sizeof(user_gcs)); +} + +static int gcs_set(struct task_struct *target, const struct + user_regset *regset, unsigned int pos, + unsigned int count, const void *kbuf, const + void __user *ubuf) +{ + int ret; + struct user_gcs user_gcs; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_gcs, 0, -1); + if (ret) + return ret; + + if (user_gcs.features_enabled & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK) + return -EINVAL; + + target->thread.gcs_el0_mode = user_gcs.features_enabled; + target->thread.gcs_el0_locked = user_gcs.features_locked; + target->thread.gcspr_el0 = user_gcs.gcspr_el0; + + return 0; +} +#endif + enum aarch64_regset { REGSET_GPR, REGSET_FPR, @@ -1469,6 +1510,9 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI REGSET_TAGGED_ADDR_CTRL, #endif +#ifdef CONFIG_ARM64_GCS + REGSET_GCS, +#endif };

static const struct user_regset aarch64_regsets[] = { @@ -1628,6 +1672,16 @@ static const struct user_regset aarch64_regsets[] = { .set = tagged_addr_ctrl_set, }, #endif +#ifdef CONFIG_ARM64_GCS + [REGSET_GCS] = { + .core_note_type = NT_ARM_GCS, + .n = sizeof(struct user_gcs) / sizeof(u64), + .size = sizeof(u64), + .align = sizeof(u64), + .regset_get = gcs_get, + .set = gcs_set, + }, +#endif };

static const struct user_regset_view user_aarch64_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index b54b313bcf07..77d4910bbb9d 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -441,6 +441,7 @@ typedef struct elf64_shdr { #define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARM_ZT 0x40d /* ARM SME ZT registers */ #define NT_ARM_FPMR 0x40e /* ARM floating point mode register */ +#define NT_ARM_GCS 0x40f /* ARM GCS state */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */

Provide a Kconfig option allowing the user to select if GCS support is built into the kernel.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/Kconfig | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a2f8ff354ca6..3fa682151c8f 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -2137,6 +2137,27 @@ 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 + depends on !UPROBES + 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.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org 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.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org 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.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org 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 | 357 ++++++++++++++++++++++++++ tools/testing/selftests/arm64/gcs/gcs-util.h | 90 +++++++ 5 files changed, 467 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..3fb9742342a3 --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/basic-gcs.c @@ -0,0 +1,357 @@ +// 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 %lx not %lx\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 %lu byte GCS: %d\n", + page_size, errno); + return false; + } + ksft_print_msg("Mapped GCS at %p-%p\n", buf, + (void *)((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%llx 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%llx not 0x%llx\n", + buf[elem], expected_cap); + pass = false; + } + ksft_print_msg("cap token is 0x%llx\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%llx not 0x0\n", + elem, buf[elem]); + pass = false; + } + + ret = munmap(buf, page_size); + if (ret != 0) { + ksft_print_msg("Failed to unmap %ld 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..1ae6864d3f86 --- /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 74 +#define PR_SET_SHADOW_STACK_STATUS 75 +#define PR_LOCK_SHADOW_STACK_STATUS 76 + +# 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.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org 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.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org 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 | 530 +++++++++++++++++++++ 5 files changed, 848 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..b88b25217da5 --- /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 75 +# 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 +.endm + +// 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..a81417cd6f5c --- /dev/null +++ b/tools/testing/selftests/arm64/gcs/gcs-stress.c @@ -0,0 +1,530 @@ +// 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_finished(); +}

GCS adds new registers GCSCR_EL1, GCSCRE0_EL1, GCSPR_EL1 and GCSPR_EL0. Add these to those validated by get-reg-list.

Reviewed-by: Thiago Jung Bauermann thiago.bauermann@linaro.org Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/kvm/aarch64/get-reg-list.c | 28 ++++++++++++++++++++++ 1 file changed, 28 insertions(+)

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index 709d7d721760..9785f41e6042 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -29,6 +29,24 @@ static struct feature_id_reg feat_id_regs[] = { 0, 1 }, + { + ARM64_SYS_REG(3, 0, 2, 5, 0), /* GCSCR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */ + 44, + 1 + }, + { + ARM64_SYS_REG(3, 0, 2, 5, 1), /* GCSPR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */ + 44, + 1 + }, + { + ARM64_SYS_REG(3, 0, 2, 5, 2), /* GCSCRE0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */ + 44, + 1 + }, { ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ @@ -40,6 +58,12 @@ static struct feature_id_reg feat_id_regs[] = { ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ 4, 1 + }, + { + ARM64_SYS_REG(3, 3, 2, 5, 1), /* GCSPR_EL0 */ + ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */ + 44, + 1 } };

@@ -460,6 +484,9 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 3), /* TCR2_EL1 */ + ARM64_SYS_REG(3, 0, 2, 5, 0), /* GCSCR_EL1 */ + ARM64_SYS_REG(3, 0, 2, 5, 1), /* GCSPR_EL1 */ + ARM64_SYS_REG(3, 0, 2, 5, 2), /* GCSCRE0_EL1 */ ARM64_SYS_REG(3, 0, 5, 1, 0), /* AFSR0_EL1 */ ARM64_SYS_REG(3, 0, 5, 1, 1), /* AFSR1_EL1 */ ARM64_SYS_REG(3, 0, 5, 2, 0), /* ESR_EL1 */ @@ -475,6 +502,7 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 13, 0, 4), /* TPIDR_EL1 */ ARM64_SYS_REG(3, 0, 14, 1, 0), /* CNTKCTL_EL1 */ ARM64_SYS_REG(3, 2, 0, 0, 0), /* CSSELR_EL1 */ + ARM64_SYS_REG(3, 3, 2, 5, 1), /* GCSPR_EL0 */ ARM64_SYS_REG(3, 3, 13, 0, 2), /* TPIDR_EL0 */ ARM64_SYS_REG(3, 3, 13, 0, 3), /* TPIDRRO_EL0 */ ARM64_SYS_REG(3, 3, 14, 0, 1), /* CNTPCT_EL0 */