Date:   Fri,  2 Dec 2022 16:35:53 -0800
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>,
        Weijiang Yang <weijiang.yang@...el.com>,
        "Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
        John Allen <john.allen@....com>, kcc@...gle.com,
        eranian@...gle.com, rppt@...nel.org, jamorris@...ux.microsoft.com,
        dethoma@...rosoft.com, akpm@...ux-foundation.org,
        Andrew.Cooper3@...rix.com, christina.schimpe@...el.com
Cc:     rick.p.edgecombe@...el.com, Yu-cheng Yu <yu-cheng.yu@...el.com>
Subject: [PATCH v4 26/39] x86/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 or x32.

Tested-by: Pengfei Xu <pengfei.xu@...el.com>
Tested-by: John Allen <john.allen@....com>
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>
---

v4:
 - Just set MSR_IA32_U_CET when disabling shadow stack, since we don't
   have IBT yet. (Peterz)

v3:
 - Use define for set_clr_bits_msrl() (Kees)
 - Make some functions static (Kees)
 - Change feature_foo() to features_foo() (Kees)
 - Centralize shadow stack size rlimit checks (Kees)
 - Disable x32 support

v2:
 - Get rid of unnessary shstk->base checks
 - Don't support IA32 emulation

v1:
 - Switch to xsave helpers.
 - Expand commit log.

 arch/x86/include/asm/msr.h        |  11 +++
 arch/x86/include/asm/processor.h  |   3 +
 arch/x86/include/asm/shstk.h      |   7 ++
 arch/x86/include/uapi/asm/prctl.h |   3 +
 arch/x86/kernel/shstk.c           | 146 ++++++++++++++++++++++++++++++
 5 files changed, 170 insertions(+)

diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 65ec1965cd28..a4b86eb537d6 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);
 
+/* Helper that can never get accidentally un-inlined. */
+#define set_clr_bits_msrl(msr, set, clear)	do {	\
+	u64 __val, __new_val;				\
+							\
+	rdmsrl(msr, __val);				\
+	__new_val = (__val & ~(clear)) | (set);		\
+							\
+	if (__new_val != __val)				\
+		wrmsrl(msr, __new_val);			\
+} while (0)
+
 #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 ff1c0b1aca8c..3c257a1a0757 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -28,6 +28,7 @@ struct vm86;
 #include <asm/unwind_hints.h>
 #include <asm/vmxfeatures.h>
 #include <asm/vdso/processor.h>
+#include <asm/shstk.h>
 
 #include <linux/personality.h>
 #include <linux/cache.h>
@@ -478,6 +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 58f9ee675be0..f40414a982e8 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 features) { 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 8b427aea2345..fc97ca7c4884 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -31,4 +31,7 @@
 #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..64f2521cae23 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -8,14 +8,160 @@
 
 #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/shstk.h>
+#include <asm/special_insns.h>
+#include <asm/fpu/api.h>
 #include <asm/prctl.h>
 
+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;
+	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 = &current->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(&current->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) {
-- 
2.17.1

Powered by blists - more mailing lists