From 98cfa4630912a80a575277d1bf193376ba66116a Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Mon, 12 Jun 2023 17:10:52 -0700 Subject: x86: Introduce userspace API for shadow stack Add three new arch_prctl() handles: - ARCH_SHSTK_ENABLE/DISABLE enables or disables the specified feature. Returns 0 on success or a negative value on error. - ARCH_SHSTK_LOCK prevents future disabling or enabling of the specified feature. Returns 0 on success or a negative value on error. The features are handled per-thread and inherited over fork(2)/clone(2), but reset on exec(). Co-developed-by: Kirill A. Shutemov Signed-off-by: Kirill A. Shutemov Signed-off-by: Rick Edgecombe Signed-off-by: Dave Hansen Reviewed-by: Borislav Petkov (AMD) Reviewed-by: Kees Cook Acked-by: Mike Rapoport (IBM) Tested-by: Pengfei Xu Tested-by: John Allen Tested-by: Kees Cook Link: https://lore.kernel.org/all/20230613001108.3040476-27-rick.p.edgecombe%40intel.com --- arch/x86/include/uapi/asm/prctl.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/x86/include/uapi/asm/prctl.h') diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index e8d7ebbca1a4..1cd44ecc9ce0 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -23,9 +23,15 @@ #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 +/* Don't use 0x3001-0x3004 because of old glibcs */ + #define ARCH_GET_UNTAG_MASK 0x4001 #define ARCH_ENABLE_TAGGED_ADDR 0x4002 #define ARCH_GET_MAX_TAG_BITS 0x4003 #define ARCH_FORCE_TAGGED_SVA 0x4004 +#define ARCH_SHSTK_ENABLE 0x5001 +#define ARCH_SHSTK_DISABLE 0x5002 +#define ARCH_SHSTK_LOCK 0x5003 + #endif /* _ASM_X86_PRCTL_H */ -- cgit v1.2.3 From 2d39a6add422ac78254927ec2194838c33ae4fb2 Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Mon, 12 Jun 2023 17:10:54 -0700 Subject: x86/shstk: Add user-mode shadow stack support Introduce basic shadow stack enabling/disabling/allocation routines. A task's shadow stack is allocated from memory with VM_SHADOW_STACK flag and has a fixed size of min(RLIMIT_STACK, 4GB). Keep the task's shadow stack address and size in thread_struct. This will be copied when cloning new threads, but needs to be cleared during exec, so add a function to do this. 32 bit shadow stack is not expected to have many users and it will complicate the signal implementation. So do not support IA32 emulation or x32. Co-developed-by: Yu-cheng Yu Signed-off-by: Yu-cheng Yu Signed-off-by: Rick Edgecombe Signed-off-by: Dave Hansen Reviewed-by: Borislav Petkov (AMD) Reviewed-by: Kees Cook Acked-by: Mike Rapoport (IBM) Tested-by: Pengfei Xu Tested-by: John Allen Tested-by: Kees Cook Link: https://lore.kernel.org/all/20230613001108.3040476-29-rick.p.edgecombe%40intel.com --- arch/x86/include/asm/processor.h | 2 + arch/x86/include/asm/shstk.h | 7 ++ arch/x86/include/uapi/asm/prctl.h | 3 + arch/x86/kernel/shstk.c | 145 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 157 insertions(+) (limited to 'arch/x86/include/uapi/asm/prctl.h') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 4e35f40ea1e6..b216ac80ebcc 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -479,6 +479,8 @@ struct thread_struct { #ifdef CONFIG_X86_USER_SHADOW_STACK unsigned long features; unsigned long features_locked; + + struct thread_shstk shstk; #endif /* Floating point and extended processor state */ diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h index ec753809f074..2b1f7c9b9995 100644 --- a/arch/x86/include/asm/shstk.h +++ b/arch/x86/include/asm/shstk.h @@ -8,12 +8,19 @@ struct task_struct; #ifdef CONFIG_X86_USER_SHADOW_STACK +struct thread_shstk { + u64 base; + u64 size; +}; + long shstk_prctl(struct task_struct *task, int option, unsigned long features); void reset_thread_features(void); +void shstk_free(struct task_struct *p); #else static inline long shstk_prctl(struct task_struct *task, int option, unsigned long arg2) { return -EINVAL; } static inline void reset_thread_features(void) {} +static inline void shstk_free(struct task_struct *p) {} #endif /* CONFIG_X86_USER_SHADOW_STACK */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index 1cd44ecc9ce0..6a8e0e1bff4a 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -34,4 +34,7 @@ #define ARCH_SHSTK_DISABLE 0x5002 #define ARCH_SHSTK_LOCK 0x5003 +/* ARCH_SHSTK_ features bits */ +#define ARCH_SHSTK_SHSTK (1ULL << 0) + #endif /* _ASM_X86_PRCTL_H */ diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c index 41ed6552e0a5..3cb85224d856 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -8,14 +8,159 @@ #include #include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include #include +static bool features_enabled(unsigned long features) +{ + return current->thread.features & features; +} + +static void features_set(unsigned long features) +{ + current->thread.features |= features; +} + +static void features_clr(unsigned long features) +{ + current->thread.features &= ~features; +} + +static unsigned long alloc_shstk(unsigned long size) +{ + int flags = MAP_ANONYMOUS | MAP_PRIVATE | MAP_ABOVE4G; + struct mm_struct *mm = current->mm; + unsigned long addr, unused; + + mmap_write_lock(mm); + addr = do_mmap(NULL, addr, size, PROT_READ, flags, + VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL); + + mmap_write_unlock(mm); + + return addr; +} + +static unsigned long adjust_shstk_size(unsigned long size) +{ + if (size) + return PAGE_ALIGN(size); + + return PAGE_ALIGN(min_t(unsigned long long, rlimit(RLIMIT_STACK), SZ_4G)); +} + +static void unmap_shadow_stack(u64 base, u64 size) +{ + while (1) { + int r; + + r = vm_munmap(base, size); + + /* + * vm_munmap() returns -EINTR when mmap_lock is held by + * something else, and that lock should not be held for a + * long time. Retry it for the case. + */ + if (r == -EINTR) { + cond_resched(); + continue; + } + + /* + * For all other types of vm_munmap() failure, either the + * system is out of memory or there is bug. + */ + WARN_ON_ONCE(r); + break; + } +} + +static int shstk_setup(void) +{ + struct thread_shstk *shstk = ¤t->thread.shstk; + unsigned long addr, size; + + /* Already enabled */ + if (features_enabled(ARCH_SHSTK_SHSTK)) + return 0; + + /* Also not supported for 32 bit and x32 */ + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || in_32bit_syscall()) + return -EOPNOTSUPP; + + size = adjust_shstk_size(0); + addr = alloc_shstk(size); + if (IS_ERR_VALUE(addr)) + return PTR_ERR((void *)addr); + + fpregs_lock_and_load(); + wrmsrl(MSR_IA32_PL3_SSP, addr + size); + wrmsrl(MSR_IA32_U_CET, CET_SHSTK_EN); + fpregs_unlock(); + + shstk->base = addr; + shstk->size = size; + features_set(ARCH_SHSTK_SHSTK); + + return 0; +} + void reset_thread_features(void) { + memset(¤t->thread.shstk, 0, sizeof(struct thread_shstk)); current->thread.features = 0; current->thread.features_locked = 0; } +void shstk_free(struct task_struct *tsk) +{ + struct thread_shstk *shstk = &tsk->thread.shstk; + + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || + !features_enabled(ARCH_SHSTK_SHSTK)) + return; + + if (!tsk->mm) + return; + + unmap_shadow_stack(shstk->base, shstk->size); +} + +static int shstk_disable(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) + return -EOPNOTSUPP; + + /* Already disabled? */ + if (!features_enabled(ARCH_SHSTK_SHSTK)) + return 0; + + fpregs_lock_and_load(); + /* Disable WRSS too when disabling shadow stack */ + wrmsrl(MSR_IA32_U_CET, 0); + wrmsrl(MSR_IA32_PL3_SSP, 0); + fpregs_unlock(); + + shstk_free(current); + features_clr(ARCH_SHSTK_SHSTK); + + return 0; +} + long shstk_prctl(struct task_struct *task, int option, unsigned long features) { if (option == ARCH_SHSTK_LOCK) { -- cgit v1.2.3 From 1d62c65372ab08599e4cf24af83d004434087ada Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Mon, 12 Jun 2023 17:11:01 -0700 Subject: x86/shstk: Support WRSS for userspace For the current shadow stack implementation, shadow stacks contents can't easily be provisioned with arbitrary data. This property helps apps protect themselves better, but also restricts any potential apps that may want to do exotic things at the expense of a little security. The x86 shadow stack feature introduces a new instruction, WRSS, which can be enabled to write directly to shadow stack memory from userspace. Allow it to get enabled via the prctl interface. Only enable the userspace WRSS instruction, which allows writes to userspace shadow stacks from userspace. Do not allow it to be enabled independently of shadow stack, as HW does not support using WRSS when shadow stack is disabled. >From a fault handler perspective, WRSS will behave very similar to WRUSS, which is treated like a user access from a #PF err code perspective. Signed-off-by: Rick Edgecombe Signed-off-by: Dave Hansen Reviewed-by: Borislav Petkov (AMD) Reviewed-by: Kees Cook Acked-by: Mike Rapoport (IBM) Tested-by: Pengfei Xu Tested-by: John Allen Tested-by: Kees Cook Link: https://lore.kernel.org/all/20230613001108.3040476-36-rick.p.edgecombe%40intel.com --- arch/x86/include/uapi/asm/prctl.h | 1 + arch/x86/kernel/shstk.c | 43 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 43 insertions(+), 1 deletion(-) (limited to 'arch/x86/include/uapi/asm/prctl.h') diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index 6a8e0e1bff4a..eedfde3b63be 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -36,5 +36,6 @@ /* ARCH_SHSTK_ features bits */ #define ARCH_SHSTK_SHSTK (1ULL << 0) +#define ARCH_SHSTK_WRSS (1ULL << 1) #endif /* _ASM_X86_PRCTL_H */ diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c index 04c37b33a625..ea0bf113f9cf 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -390,6 +390,47 @@ void shstk_free(struct task_struct *tsk) unmap_shadow_stack(shstk->base, shstk->size); } +static int wrss_control(bool enable) +{ + u64 msrval; + + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) + return -EOPNOTSUPP; + + /* + * Only enable WRSS if shadow stack is enabled. If shadow stack is not + * enabled, WRSS will already be disabled, so don't bother clearing it + * when disabling. + */ + if (!features_enabled(ARCH_SHSTK_SHSTK)) + return -EPERM; + + /* Already enabled/disabled? */ + if (features_enabled(ARCH_SHSTK_WRSS) == enable) + return 0; + + fpregs_lock_and_load(); + rdmsrl(MSR_IA32_U_CET, msrval); + + if (enable) { + features_set(ARCH_SHSTK_WRSS); + msrval |= CET_WRSS_EN; + } else { + features_clr(ARCH_SHSTK_WRSS); + if (!(msrval & CET_WRSS_EN)) + goto unlock; + + msrval &= ~CET_WRSS_EN; + } + + wrmsrl(MSR_IA32_U_CET, msrval); + +unlock: + fpregs_unlock(); + + return 0; +} + static int shstk_disable(void) { if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) @@ -406,7 +447,7 @@ static int shstk_disable(void) fpregs_unlock(); shstk_free(current); - features_clr(ARCH_SHSTK_SHSTK); + features_clr(ARCH_SHSTK_SHSTK | ARCH_SHSTK_WRSS); return 0; } -- cgit v1.2.3 From 680ed2f15e70d079c8148589a3ce9426fc0ff914 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 12 Jun 2023 17:11:07 -0700 Subject: x86/shstk: Add ARCH_SHSTK_UNLOCK Userspace loaders may lock features before a CRIU restore operation has the chance to set them to whatever state is required by the process being restored. Allow a way for CRIU to unlock features. Add it as an arch_prctl() like the other shadow stack operations, but restrict it being called by the ptrace arch_pctl() interface. [Merged into recent API changes, added commit log and docs] Signed-off-by: Mike Rapoport Signed-off-by: Rick Edgecombe Signed-off-by: Dave Hansen Reviewed-by: Borislav Petkov (AMD) Reviewed-by: Kees Cook Reviewed-by: David Hildenbrand Tested-by: Pengfei Xu Tested-by: John Allen Tested-by: Kees Cook Link: https://lore.kernel.org/all/20230613001108.3040476-42-rick.p.edgecombe%40intel.com --- Documentation/arch/x86/shstk.rst | 4 ++++ arch/x86/include/uapi/asm/prctl.h | 1 + arch/x86/kernel/process_64.c | 1 + arch/x86/kernel/shstk.c | 9 +++++++-- 4 files changed, 13 insertions(+), 2 deletions(-) (limited to 'arch/x86/include/uapi/asm/prctl.h') diff --git a/Documentation/arch/x86/shstk.rst b/Documentation/arch/x86/shstk.rst index f09afa504ec0..f3553cc8c758 100644 --- a/Documentation/arch/x86/shstk.rst +++ b/Documentation/arch/x86/shstk.rst @@ -75,6 +75,10 @@ arch_prctl(ARCH_SHSTK_LOCK, unsigned long features) are ignored. The mask is ORed with the existing value. So any feature bits set here cannot be enabled or disabled afterwards. +arch_prctl(ARCH_SHSTK_UNLOCK, unsigned long features) + Unlock features. 'features' is a mask of all features to unlock. All + bits set are processed, unset bits are ignored. Only works via ptrace. + The return values are as follows. On success, return 0. On error, errno can be:: diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index eedfde3b63be..3189c4a96468 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -33,6 +33,7 @@ #define ARCH_SHSTK_ENABLE 0x5001 #define ARCH_SHSTK_DISABLE 0x5002 #define ARCH_SHSTK_LOCK 0x5003 +#define ARCH_SHSTK_UNLOCK 0x5004 /* ARCH_SHSTK_ features bits */ #define ARCH_SHSTK_SHSTK (1ULL << 0) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 0f89aa0186d1..e6db21c470aa 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -899,6 +899,7 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) case ARCH_SHSTK_ENABLE: case ARCH_SHSTK_DISABLE: case ARCH_SHSTK_LOCK: + case ARCH_SHSTK_UNLOCK: return shstk_prctl(task, option, arg2); default: ret = -EINVAL; diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c index d723cdc93474..d43b7a9c57ce 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -489,9 +489,14 @@ long shstk_prctl(struct task_struct *task, int option, unsigned long features) return 0; } - /* Don't allow via ptrace */ - if (task != current) + /* Only allow via ptrace */ + if (task != current) { + if (option == ARCH_SHSTK_UNLOCK && IS_ENABLED(CONFIG_CHECKPOINT_RESTORE)) { + task->thread.features_locked &= ~features; + return 0; + } return -EINVAL; + } /* Do not allow to change locked features */ if (features & task->thread.features_locked) -- cgit v1.2.3 From 67840ad0fa14ad49a605074b12d5b0f3c3113ed1 Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Mon, 12 Jun 2023 17:11:08 -0700 Subject: x86/shstk: Add ARCH_SHSTK_STATUS CRIU and GDB need to get the current shadow stack and WRSS enablement status. This information is already available via /proc/pid/status, but this is inconvenient for CRIU because it involves parsing the text output in an area of the code where this is difficult. Provide a status arch_prctl(), ARCH_SHSTK_STATUS for retrieving the status. Have arg2 be a userspace address, and make the new arch_prctl simply copy the features out to userspace. Suggested-by: Mike Rapoport Signed-off-by: Rick Edgecombe Signed-off-by: Dave Hansen Reviewed-by: Borislav Petkov (AMD) Reviewed-by: Kees Cook Acked-by: Mike Rapoport (IBM) Tested-by: Pengfei Xu Tested-by: John Allen Tested-by: Kees Cook Link: https://lore.kernel.org/all/20230613001108.3040476-43-rick.p.edgecombe%40intel.com --- Documentation/arch/x86/shstk.rst | 6 ++++++ arch/x86/include/asm/shstk.h | 2 +- arch/x86/include/uapi/asm/prctl.h | 1 + arch/x86/kernel/process_64.c | 1 + arch/x86/kernel/shstk.c | 8 +++++++- 5 files changed, 16 insertions(+), 2 deletions(-) (limited to 'arch/x86/include/uapi/asm/prctl.h') diff --git a/Documentation/arch/x86/shstk.rst b/Documentation/arch/x86/shstk.rst index f3553cc8c758..60260e809baf 100644 --- a/Documentation/arch/x86/shstk.rst +++ b/Documentation/arch/x86/shstk.rst @@ -79,6 +79,11 @@ arch_prctl(ARCH_SHSTK_UNLOCK, unsigned long features) Unlock features. 'features' is a mask of all features to unlock. All bits set are processed, unset bits are ignored. Only works via ptrace. +arch_prctl(ARCH_SHSTK_STATUS, unsigned long addr) + Copy the currently enabled features to the address passed in addr. The + features are described using the bits passed into the others in + 'features'. + The return values are as follows. On success, return 0. On error, errno can be:: @@ -86,6 +91,7 @@ be:: -ENOTSUPP if the feature is not supported by the hardware or kernel. -EINVAL arguments (non existing feature, etc) + -EFAULT if could not copy information back to userspace The feature's bits supported are:: diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h index ecb23a8ca47d..42fee8959df7 100644 --- a/arch/x86/include/asm/shstk.h +++ b/arch/x86/include/asm/shstk.h @@ -14,7 +14,7 @@ struct thread_shstk { u64 size; }; -long shstk_prctl(struct task_struct *task, int option, unsigned long features); +long shstk_prctl(struct task_struct *task, int option, unsigned long arg2); void reset_thread_features(void); unsigned long shstk_alloc_thread_stack(struct task_struct *p, unsigned long clone_flags, unsigned long stack_size); diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index 3189c4a96468..384e2cc6ac19 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -34,6 +34,7 @@ #define ARCH_SHSTK_DISABLE 0x5002 #define ARCH_SHSTK_LOCK 0x5003 #define ARCH_SHSTK_UNLOCK 0x5004 +#define ARCH_SHSTK_STATUS 0x5005 /* ARCH_SHSTK_ features bits */ #define ARCH_SHSTK_SHSTK (1ULL << 0) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e6db21c470aa..33b268747bb7 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -900,6 +900,7 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) case ARCH_SHSTK_DISABLE: case ARCH_SHSTK_LOCK: case ARCH_SHSTK_UNLOCK: + case ARCH_SHSTK_STATUS: return shstk_prctl(task, option, arg2); default: ret = -EINVAL; diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c index d43b7a9c57ce..b26810c7cd1c 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -482,8 +482,14 @@ SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsi return alloc_shstk(addr, aligned_size, size, set_tok); } -long shstk_prctl(struct task_struct *task, int option, unsigned long features) +long shstk_prctl(struct task_struct *task, int option, unsigned long arg2) { + unsigned long features = arg2; + + if (option == ARCH_SHSTK_STATUS) { + return put_user(task->thread.features, (unsigned long __user *)arg2); + } + if (option == ARCH_SHSTK_LOCK) { task->thread.features_locked |= features; return 0; -- cgit v1.2.3