[PATCH v5 07/39] x86: Add user control-protection fault handler

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>

A control-protection fault is triggered when a control-flow transfer
attempt violates Shadow Stack or Indirect Branch Tracking constraints.
For example, the return address for a RET instruction differs from the copy
on the shadow stack.

There already exists a control-protection fault handler for handling kernel
IBT faults. Refactor this fault handler into separate user and kernel
handlers, like the page fault handler. Add a control-protection handler
for usermode. To avoid ifdeffery, put them both in a new file cet.c, which
is compiled in the case of either of the two CET features supported in the
kernel: kernel IBT or user mode shadow stack. Move some static inline
functions from traps.c into a header so they can be used in cet.c.

Opportunistically fix a comment in the kernel IBT part of the fault
handler that is on the end of the line instead of preceding it.

Keep the same behavior for the kernel side of the fault handler, except for
converting a BUG to a WARN in the case of a #CP happening when the feature
is missing. This unifies the behavior with the new shadow stack code, and
also prevents the kernel from crashing under this situation which is
potentially recoverable.

The control-protection fault handler works in a similar way as the general
protection fault handler. It provides the si_code SEGV_CPERR to the signal
handler.

Tested-by: Pengfei Xu <pengfei.xu@xxxxxxxxx>
Tested-by: John Allen <john.allen@xxxxxxx>
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
Co-developed-by: Rick Edgecombe <rick.p.edgecombe@xxxxxxxxx>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@xxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Michael Kerrisk <mtk.manpages@xxxxxxxxx>
---

v5:
 - Move to separate file to advoid ifdeffery (Boris)
 - Improvements to commit log (Boris)
 - Rename control_protection_err (Boris)
 - Move comment from end of line in IBT fault handler (Boris)

v3:
 - Shorten user/kernel #CP handler function names (peterz)
 - Restore CP_ENDBR check to kernel handler (peterz)
 - Utilize CONFIG_X86_CET (Kees)
 - Unify "unexpected" warnings (Andrew Cooper)
 - Use 2d array for error code chars (Andrew Cooper)
 - Add comment about why to read SSP MSR before enabling interrupts

v2:
 - Integrate with kernel IBT fault handler
 - Update printed messages. (Dave)
 - Remove array_index_nospec() usage. (Dave)
 - Remove IBT messages. (Dave)
 - Add enclave error code bit processing it case it can get triggered
   somehow.
 - Add extra "unknown" in control_protection_err.

v1:
 - Update static asserts for NSIGSEGV

 arch/arm/kernel/signal.c                 |   2 +-
 arch/arm64/kernel/signal.c               |   2 +-
 arch/arm64/kernel/signal32.c             |   2 +-
 arch/sparc/kernel/signal32.c             |   2 +-
 arch/sparc/kernel/signal_64.c            |   2 +-
 arch/x86/include/asm/disabled-features.h |   8 +-
 arch/x86/include/asm/idtentry.h          |   2 +-
 arch/x86/include/asm/traps.h             |  12 ++
 arch/x86/kernel/Makefile                 |   2 +
 arch/x86/kernel/cet.c                    | 152 +++++++++++++++++++++++
 arch/x86/kernel/idt.c                    |   2 +-
 arch/x86/kernel/signal_32.c              |   2 +-
 arch/x86/kernel/signal_64.c              |   2 +-
 arch/x86/kernel/traps.c                  |  87 -------------
 arch/x86/xen/enlighten_pv.c              |   2 +-
 arch/x86/xen/xen-asm.S                   |   2 +-
 include/uapi/asm-generic/siginfo.h       |   3 +-
 17 files changed, 186 insertions(+), 100 deletions(-)
 create mode 100644 arch/x86/kernel/cet.c

diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index e07f359254c3..9a3c9de5ac5e 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -681,7 +681,7 @@ asmlinkage void do_rseq_syscall(struct pt_regs *regs)
  */
 static_assert(NSIGILL	== 11);
 static_assert(NSIGFPE	== 15);
-static_assert(NSIGSEGV	== 9);
+static_assert(NSIGSEGV	== 10);
 static_assert(NSIGBUS	== 5);
 static_assert(NSIGTRAP	== 6);
 static_assert(NSIGCHLD	== 6);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index be279fd48248..4bced22213d5 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -1176,7 +1176,7 @@ void __init minsigstksz_setup(void)
  */
 static_assert(NSIGILL	== 11);
 static_assert(NSIGFPE	== 15);
-static_assert(NSIGSEGV	== 9);
+static_assert(NSIGSEGV	== 10);
 static_assert(NSIGBUS	== 5);
 static_assert(NSIGTRAP	== 6);
 static_assert(NSIGCHLD	== 6);
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 4700f8522d27..bbd542704730 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -460,7 +460,7 @@ void compat_setup_restart_syscall(struct pt_regs *regs)
  */
 static_assert(NSIGILL	== 11);
 static_assert(NSIGFPE	== 15);
-static_assert(NSIGSEGV	== 9);
+static_assert(NSIGSEGV	== 10);
 static_assert(NSIGBUS	== 5);
 static_assert(NSIGTRAP	== 6);
 static_assert(NSIGCHLD	== 6);
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index dad38960d1a8..82da8a2d769d 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -751,7 +751,7 @@ asmlinkage int do_sys32_sigstack(u32 u_ssptr, u32 u_ossptr, unsigned long sp)
  */
 static_assert(NSIGILL	== 11);
 static_assert(NSIGFPE	== 15);
-static_assert(NSIGSEGV	== 9);
+static_assert(NSIGSEGV	== 10);
 static_assert(NSIGBUS	== 5);
 static_assert(NSIGTRAP	== 6);
 static_assert(NSIGCHLD	== 6);
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 570e43e6fda5..b4e410976e0d 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -562,7 +562,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, unsigned long
  */
 static_assert(NSIGILL	== 11);
 static_assert(NSIGFPE	== 15);
-static_assert(NSIGSEGV	== 9);
+static_assert(NSIGSEGV	== 10);
 static_assert(NSIGBUS	== 5);
 static_assert(NSIGTRAP	== 6);
 static_assert(NSIGCHLD	== 6);
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 505f78ddca82..652e366b68a0 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -105,6 +105,12 @@
 #define DISABLE_USER_SHSTK	(1 << (X86_FEATURE_USER_SHSTK & 31))
 #endif
 
+#ifdef CONFIG_X86_KERNEL_IBT
+#define DISABLE_IBT	0
+#else
+#define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -128,7 +134,7 @@
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
 			 DISABLE_ENQCMD)
 #define DISABLED_MASK17	0
-#define DISABLED_MASK18	0
+#define DISABLED_MASK18	(DISABLE_IBT)
 #define DISABLED_MASK19	0
 #define DISABLED_MASK20	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 72184b0b2219..69e26f48d027 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -618,7 +618,7 @@ DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_DF,	xenpv_exc_double_fault);
 #endif
 
 /* #CP */
-#ifdef CONFIG_X86_KERNEL_IBT
+#ifdef CONFIG_X86_CET
 DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_CP,	exc_control_protection);
 #endif
 
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 47ecfff2c83d..75e0dabf0c45 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -47,4 +47,16 @@ void __noreturn handle_stack_overflow(struct pt_regs *regs,
 				      struct stack_info *info);
 #endif
 
+static inline void cond_local_irq_enable(struct pt_regs *regs)
+{
+	if (regs->flags & X86_EFLAGS_IF)
+		local_irq_enable();
+}
+
+static inline void cond_local_irq_disable(struct pt_regs *regs)
+{
+	if (regs->flags & X86_EFLAGS_IF)
+		local_irq_disable();
+}
+
 #endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index dd61752f4c96..92446f1dedd7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -144,6 +144,8 @@ obj-$(CONFIG_CFI_CLANG)			+= cfi.o
 
 obj-$(CONFIG_CALL_THUNKS)		+= callthunks.o
 
+obj-$(CONFIG_X86_CET)			+= cet.o
+
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c
new file mode 100644
index 000000000000..33d7d119be26
--- /dev/null
+++ b/arch/x86/kernel/cet.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/ptrace.h>
+#include <asm/bugs.h>
+#include <asm/traps.h>
+
+enum cp_error_code {
+	CP_EC        = (1 << 15) - 1,
+
+	CP_RET       = 1,
+	CP_IRET      = 2,
+	CP_ENDBR     = 3,
+	CP_RSTRORSSP = 4,
+	CP_SETSSBSY  = 5,
+
+	CP_ENCL	     = 1 << 15,
+};
+
+static const char cp_err[][10] = {
+	[0] = "unknown",
+	[1] = "near ret",
+	[2] = "far/iret",
+	[3] = "endbranch",
+	[4] = "rstorssp",
+	[5] = "setssbsy",
+};
+
+static const char *cp_err_string(unsigned long error_code)
+{
+	unsigned int cpec = error_code & CP_EC;
+
+	if (cpec >= ARRAY_SIZE(cp_err))
+		cpec = 0;
+	return cp_err[cpec];
+}
+
+static void do_unexpected_cp(struct pt_regs *regs, unsigned long error_code)
+{
+	WARN_ONCE(1, "Unexpected %s #CP, error_code: %s\n",
+		     user_mode(regs) ? "user mode" : "kernel mode",
+		     cp_err_string(error_code));
+}
+
+static DEFINE_RATELIMIT_STATE(cpf_rate, DEFAULT_RATELIMIT_INTERVAL,
+			      DEFAULT_RATELIMIT_BURST);
+
+static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code)
+{
+	struct task_struct *tsk;
+	unsigned long ssp;
+
+	/*
+	 * An exception was just taken from userspace. Since interrupts are disabled
+	 * here, no scheduling should have messed with the registers yet and they
+	 * will be whatever is live in userspace. So read the SSP before enabling
+	 * interrupts so locking the fpregs to do it later is not required.
+	 */
+	rdmsrl(MSR_IA32_PL3_SSP, ssp);
+
+	cond_local_irq_enable(regs);
+
+	tsk = current;
+	tsk->thread.error_code = error_code;
+	tsk->thread.trap_nr = X86_TRAP_CP;
+
+	/* Ratelimit to prevent log spamming. */
+	if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
+	    __ratelimit(&cpf_rate)) {
+		pr_emerg("%s[%d] control protection ip:%lx sp:%lx ssp:%lx error:%lx(%s)%s",
+			 tsk->comm, task_pid_nr(tsk),
+			 regs->ip, regs->sp, ssp, error_code,
+			 cp_err_string(error_code),
+			 error_code & CP_ENCL ? " in enclave" : "");
+		print_vma_addr(KERN_CONT " in ", regs->ip);
+		pr_cont("\n");
+	}
+
+	force_sig_fault(SIGSEGV, SEGV_CPERR, (void __user *)0);
+	cond_local_irq_disable(regs);
+}
+
+static __ro_after_init bool ibt_fatal = true;
+
+/* code label defined in asm below */
+extern void ibt_selftest_ip(void);
+
+static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code)
+{
+	if ((error_code & CP_EC) != CP_ENDBR) {
+		do_unexpected_cp(regs, error_code);
+		return;
+	}
+
+	if (unlikely(regs->ip == (unsigned long)&ibt_selftest_ip)) {
+		regs->ax = 0;
+		return;
+	}
+
+	pr_err("Missing ENDBR: %pS\n", (void *)instruction_pointer(regs));
+	if (!ibt_fatal) {
+		printk(KERN_DEFAULT CUT_HERE);
+		__warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL);
+		return;
+	}
+	BUG();
+}
+
+/* Must be noinline to ensure uniqueness of ibt_selftest_ip. */
+noinline bool ibt_selftest(void)
+{
+	unsigned long ret;
+
+	asm ("	lea ibt_selftest_ip(%%rip), %%rax\n\t"
+	     ANNOTATE_RETPOLINE_SAFE
+	     "	jmp *%%rax\n\t"
+	     "ibt_selftest_ip:\n\t"
+	     UNWIND_HINT_FUNC
+	     ANNOTATE_NOENDBR
+	     "	nop\n\t"
+
+	     : "=a" (ret) : : "memory");
+
+	return !ret;
+}
+
+static int __init ibt_setup(char *str)
+{
+	if (!strcmp(str, "off"))
+		setup_clear_cpu_cap(X86_FEATURE_IBT);
+
+	if (!strcmp(str, "warn"))
+		ibt_fatal = false;
+
+	return 1;
+}
+
+__setup("ibt=", ibt_setup);
+
+DEFINE_IDTENTRY_ERRORCODE(exc_control_protection)
+{
+	if (user_mode(regs)) {
+		if (cpu_feature_enabled(X86_FEATURE_USER_SHSTK))
+			do_user_cp_fault(regs, error_code);
+		else
+			do_unexpected_cp(regs, error_code);
+	} else {
+		if (cpu_feature_enabled(X86_FEATURE_IBT))
+			do_kernel_cp_fault(regs, error_code);
+		else
+			do_unexpected_cp(regs, error_code);
+	}
+}
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index a58c6bc1cd68..5074b8420359 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -107,7 +107,7 @@ static const __initconst struct idt_data def_idts[] = {
 	ISTG(X86_TRAP_MC,		asm_exc_machine_check, IST_INDEX_MCE),
 #endif
 
-#ifdef CONFIG_X86_KERNEL_IBT
+#ifdef CONFIG_X86_CET
 	INTG(X86_TRAP_CP,		asm_exc_control_protection),
 #endif
 
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 9027fc088f97..c12624bc82a3 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -402,7 +402,7 @@ int ia32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 */
 static_assert(NSIGILL  == 11);
 static_assert(NSIGFPE  == 15);
-static_assert(NSIGSEGV == 9);
+static_assert(NSIGSEGV == 10);
 static_assert(NSIGBUS  == 5);
 static_assert(NSIGTRAP == 6);
 static_assert(NSIGCHLD == 6);
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index 13a1e6083837..0e808c72bf7e 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -403,7 +403,7 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact)
 */
 static_assert(NSIGILL  == 11);
 static_assert(NSIGFPE  == 15);
-static_assert(NSIGSEGV == 9);
+static_assert(NSIGSEGV == 10);
 static_assert(NSIGBUS  == 5);
 static_assert(NSIGTRAP == 6);
 static_assert(NSIGCHLD == 6);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d317dc3d06a3..18fb9d620824 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -77,18 +77,6 @@
 
 DECLARE_BITMAP(system_vectors, NR_VECTORS);
 
-static inline void cond_local_irq_enable(struct pt_regs *regs)
-{
-	if (regs->flags & X86_EFLAGS_IF)
-		local_irq_enable();
-}
-
-static inline void cond_local_irq_disable(struct pt_regs *regs)
-{
-	if (regs->flags & X86_EFLAGS_IF)
-		local_irq_disable();
-}
-
 __always_inline int is_valid_bugaddr(unsigned long addr)
 {
 	if (addr < TASK_SIZE_MAX)
@@ -213,81 +201,6 @@ DEFINE_IDTENTRY(exc_overflow)
 	do_error_trap(regs, 0, "overflow", X86_TRAP_OF, SIGSEGV, 0, NULL);
 }
 
-#ifdef CONFIG_X86_KERNEL_IBT
-
-static __ro_after_init bool ibt_fatal = true;
-
-extern void ibt_selftest_ip(void); /* code label defined in asm below */
-
-enum cp_error_code {
-	CP_EC        = (1 << 15) - 1,
-
-	CP_RET       = 1,
-	CP_IRET      = 2,
-	CP_ENDBR     = 3,
-	CP_RSTRORSSP = 4,
-	CP_SETSSBSY  = 5,
-
-	CP_ENCL	     = 1 << 15,
-};
-
-DEFINE_IDTENTRY_ERRORCODE(exc_control_protection)
-{
-	if (!cpu_feature_enabled(X86_FEATURE_IBT)) {
-		pr_err("Unexpected #CP\n");
-		BUG();
-	}
-
-	if (WARN_ON_ONCE(user_mode(regs) || (error_code & CP_EC) != CP_ENDBR))
-		return;
-
-	if (unlikely(regs->ip == (unsigned long)&ibt_selftest_ip)) {
-		regs->ax = 0;
-		return;
-	}
-
-	pr_err("Missing ENDBR: %pS\n", (void *)instruction_pointer(regs));
-	if (!ibt_fatal) {
-		printk(KERN_DEFAULT CUT_HERE);
-		__warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL);
-		return;
-	}
-	BUG();
-}
-
-/* Must be noinline to ensure uniqueness of ibt_selftest_ip. */
-noinline bool ibt_selftest(void)
-{
-	unsigned long ret;
-
-	asm ("	lea ibt_selftest_ip(%%rip), %%rax\n\t"
-	     ANNOTATE_RETPOLINE_SAFE
-	     "	jmp *%%rax\n\t"
-	     "ibt_selftest_ip:\n\t"
-	     UNWIND_HINT_FUNC
-	     ANNOTATE_NOENDBR
-	     "	nop\n\t"
-
-	     : "=a" (ret) : : "memory");
-
-	return !ret;
-}
-
-static int __init ibt_setup(char *str)
-{
-	if (!strcmp(str, "off"))
-		setup_clear_cpu_cap(X86_FEATURE_IBT);
-
-	if (!strcmp(str, "warn"))
-		ibt_fatal = false;
-
-	return 1;
-}
-
-__setup("ibt=", ibt_setup);
-
-#endif /* CONFIG_X86_KERNEL_IBT */
-
 #ifdef CONFIG_X86_F00F_BUG
 void handle_invalid_op(struct pt_regs *regs)
 #else
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index bb59cc6ddb2d..9c29cd5393cc 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -640,7 +640,7 @@ static struct trap_array_entry trap_array[] = {
 	TRAP_ENTRY(exc_coprocessor_error,		false ),
 	TRAP_ENTRY(exc_alignment_check,			false ),
 	TRAP_ENTRY(exc_simd_coprocessor_error,		false ),
-#ifdef CONFIG_X86_KERNEL_IBT
+#ifdef CONFIG_X86_CET
 	TRAP_ENTRY(exc_control_protection,		false ),
 #endif
 };
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 4a184f6e4e4d..7cdcb4ce6976 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -148,7 +148,7 @@ xen_pv_trap asm_exc_page_fault
 xen_pv_trap asm_exc_spurious_interrupt_bug
 xen_pv_trap asm_exc_coprocessor_error
 xen_pv_trap asm_exc_alignment_check
-#ifdef CONFIG_X86_KERNEL_IBT
+#ifdef CONFIG_X86_CET
 xen_pv_trap asm_exc_control_protection
 #endif
 #ifdef CONFIG_X86_MCE
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index ffbe4cec9f32..0f52d0ac47c5 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -242,7 +242,8 @@ typedef struct siginfo {
 #define SEGV_ADIPERR	7	/* Precise MCD exception */
 #define SEGV_MTEAERR	8	/* Asynchronous ARM MTE error */
 #define SEGV_MTESERR	9	/* Synchronous ARM MTE exception */
-#define NSIGSEGV	9
+#define SEGV_CPERR	10	/* Control protection fault */
+#define NSIGSEGV	10
 
 /*
  * SIGBUS si_codes
-- 
2.17.1




[Index of Archives]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux