[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220929222936.14584-25-rick.p.edgecombe@intel.com>
Date: Thu, 29 Sep 2022 15:29:21 -0700
From: Rick Edgecombe <rick.p.edgecombe@...el.com>
To: x86@...nel.org, "H . Peter Anvin" <hpa@...or.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, linux-kernel@...r.kernel.org,
linux-doc@...r.kernel.org, linux-mm@...ck.org,
linux-arch@...r.kernel.org, linux-api@...r.kernel.org,
Arnd Bergmann <arnd@...db.de>,
Andy Lutomirski <luto@...nel.org>,
Balbir Singh <bsingharora@...il.com>,
Borislav Petkov <bp@...en8.de>,
Cyrill Gorcunov <gorcunov@...il.com>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Eugene Syromiatnikov <esyr@...hat.com>,
Florian Weimer <fweimer@...hat.com>,
"H . J . Lu" <hjl.tools@...il.com>, Jann Horn <jannh@...gle.com>,
Jonathan Corbet <corbet@....net>,
Kees Cook <keescook@...omium.org>,
Mike Kravetz <mike.kravetz@...cle.com>,
Nadav Amit <nadav.amit@...il.com>,
Oleg Nesterov <oleg@...hat.com>, Pavel Machek <pavel@....cz>,
Peter Zijlstra <peterz@...radead.org>,
Randy Dunlap <rdunlap@...radead.org>,
"Ravi V . Shankar" <ravi.v.shankar@...el.com>,
Weijiang Yang <weijiang.yang@...el.com>,
"Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
joao.moreira@...el.com, John Allen <john.allen@....com>,
kcc@...gle.com, eranian@...gle.com, rppt@...nel.org,
jamorris@...ux.microsoft.com, dethoma@...rosoft.com
Cc: rick.p.edgecombe@...el.com, Yu-cheng Yu <yu-cheng.yu@...el.com>
Subject: [PATCH v2 24/39] x86/cet/shstk: Add user-mode shadow stack support
From: Yu-cheng Yu <yu-cheng.yu@...el.com>
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.
Do not support IA32 emulation.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@...el.com>
Co-developed-by: Rick Edgecombe <rick.p.edgecombe@...el.com>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@...el.com>
Cc: Kees Cook <keescook@...omium.org>
---
v2:
- Get rid of unnessary shstk->base checks
- Don't support IA32 emulation
v1:
- Switch to xsave helpers.
- Expand commit log.
Yu-cheng v30:
- Remove superfluous comments for struct thread_shstk.
- Replace 'populate' with 'unused'.
Yu-cheng v28:
- Update shstk_setup() with wrmsrl_safe(), returns success when shadow
stack feature is not present (since this is a setup function).
arch/x86/include/asm/cet.h | 13 +++
arch/x86/include/asm/msr.h | 11 +++
arch/x86/include/asm/processor.h | 5 ++
arch/x86/include/uapi/asm/prctl.h | 2 +
arch/x86/kernel/Makefile | 2 +
arch/x86/kernel/process_64.c | 2 +
arch/x86/kernel/shstk.c | 143 ++++++++++++++++++++++++++++++
7 files changed, 178 insertions(+)
diff --git a/arch/x86/include/asm/cet.h b/arch/x86/include/asm/cet.h
index 0fa4dbc98c49..a4a1f4c0089b 100644
--- a/arch/x86/include/asm/cet.h
+++ b/arch/x86/include/asm/cet.h
@@ -7,12 +7,25 @@
struct task_struct;
+struct thread_shstk {
+ u64 base;
+ u64 size;
+};
+
#ifdef CONFIG_X86_SHADOW_STACK
long cet_prctl(struct task_struct *task, int option,
unsigned long features);
+int shstk_setup(void);
+void shstk_free(struct task_struct *p);
+int shstk_disable(void);
+void reset_thread_shstk(void);
#else
static inline long cet_prctl(struct task_struct *task, int option,
unsigned long features) { return -EINVAL; }
+static inline int shstk_setup(void) { return -EOPNOTSUPP; }
+static inline void shstk_free(struct task_struct *p) {}
+static inline int shstk_disable(void) { return -EOPNOTSUPP; }
+static inline void reset_thread_shstk(void) {}
#endif /* CONFIG_X86_SHADOW_STACK */
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 65ec1965cd28..a9cb4c434e60 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -310,6 +310,17 @@ void msrs_free(struct msr *msrs);
int msr_set_bit(u32 msr, u8 bit);
int msr_clear_bit(u32 msr, u8 bit);
+static inline void set_clr_bits_msrl(u32 msr, u64 set, u64 clear)
+{
+ u64 val, new_val;
+
+ rdmsrl(msr, val);
+ new_val = (val & ~clear) | set;
+
+ if (new_val != val)
+ wrmsrl(msr, new_val);
+}
+
#ifdef CONFIG_SMP
int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a92bf76edafe..3a0c9d9d4d1d 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -27,6 +27,7 @@ struct vm86;
#include <asm/unwind_hints.h>
#include <asm/vmxfeatures.h>
#include <asm/vdso/processor.h>
+#include <asm/cet.h>
#include <linux/personality.h>
#include <linux/cache.h>
@@ -533,6 +534,10 @@ struct thread_struct {
unsigned long features;
unsigned long features_locked;
+#ifdef CONFIG_X86_SHADOW_STACK
+ struct thread_shstk shstk;
+#endif
+
/* Floating point and extended processor state */
struct fpu fpu;
/*
diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h
index 028158e35269..41af3a8c4fa4 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -26,4 +26,6 @@
#define ARCH_CET_DISABLE 0x4002
#define ARCH_CET_LOCK 0x4003
+#define CET_SHSTK 0x1
+
#endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index a20a5ebfacd7..8950d1f71226 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -139,6 +139,8 @@ obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o
+obj-$(CONFIG_X86_SHADOW_STACK) += shstk.o
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 8fa2c2b7de65..be544b4b4c8b 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -514,6 +514,8 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
load_gs_index(__USER_DS);
}
+ reset_thread_shstk();
+
loadsegment(fs, 0);
loadsegment(es, _ds);
loadsegment(ds, _ds);
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index e3276ac9e9b9..a0b8d4adb2bf 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -8,8 +8,151 @@
#include <linux/sched.h>
#include <linux/bitops.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/sched/signal.h>
+#include <linux/compat.h>
+#include <linux/sizes.h>
+#include <linux/user.h>
+#include <asm/msr.h>
+#include <asm/fpu/xstate.h>
+#include <asm/fpu/types.h>
+#include <asm/cet.h>
+#include <asm/special_insns.h>
+#include <asm/fpu/api.h>
#include <asm/prctl.h>
+static bool feature_enabled(unsigned long features)
+{
+ return current->thread.features & features;
+}
+
+static void feature_set(unsigned long features)
+{
+ current->thread.features |= features;
+}
+
+static void feature_clr(unsigned long features)
+{
+ current->thread.features &= ~features;
+}
+
+static unsigned long alloc_shstk(unsigned long size)
+{
+ int flags = MAP_ANONYMOUS | MAP_PRIVATE;
+ 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 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;
+ }
+}
+
+int shstk_setup(void)
+{
+ struct thread_shstk *shstk = ¤t->thread.shstk;
+ unsigned long addr, size;
+
+ /* Already enabled */
+ if (feature_enabled(CET_SHSTK))
+ return 0;
+
+ /* Also not supported for 32 bit */
+ if (!cpu_feature_enabled(X86_FEATURE_SHSTK) || in_ia32_syscall())
+ return -EOPNOTSUPP;
+
+ size = PAGE_ALIGN(min_t(unsigned long long, rlimit(RLIMIT_STACK), SZ_4G));
+ addr = alloc_shstk(size);
+ if (IS_ERR_VALUE(addr))
+ return PTR_ERR((void *)addr);
+
+ fpu_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;
+ feature_set(CET_SHSTK);
+
+ return 0;
+}
+
+void reset_thread_shstk(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_SHSTK) ||
+ !feature_enabled(CET_SHSTK))
+ return;
+
+ if (!tsk->mm)
+ return;
+
+ unmap_shadow_stack(shstk->base, shstk->size);
+}
+
+int shstk_disable(void)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_SHSTK))
+ return -EOPNOTSUPP;
+
+ /* Already disabled? */
+ if (!feature_enabled(CET_SHSTK))
+ return 0;
+
+ fpu_lock_and_load();
+ /* Disable WRSS too when disabling shadow stack */
+ set_clr_bits_msrl(MSR_IA32_U_CET, 0, CET_SHSTK_EN);
+ wrmsrl(MSR_IA32_PL3_SSP, 0);
+ fpregs_unlock();
+
+ shstk_free(current);
+ feature_clr(CET_SHSTK);
+
+ return 0;
+}
+
long cet_prctl(struct task_struct *task, int option, unsigned long features)
{
if (option == ARCH_CET_LOCK) {
--
2.17.1
Powered by blists - more mailing lists