x86/shstk: Add user control-protection fault handler

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.

Co-developed-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Tested-by: Pengfei Xu <pengfei.xu@intel.com>
Tested-by: John Allen <john.allen@amd.com>
Tested-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/all/20230613001108.3040476-28-rick.p.edgecombe%40intel.com

5 files changed, 88 insertions, 24 deletions

diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c
index 7ad22b705b64..cc10d8be9d74 100644
--- a/arch/x86/kernel/cet.c
+++ b/arch/x86/kernel/cet.c
@@ -4,10 +4,6 @@
 #include <asm/bugs.h>
 #include <asm/traps.h>
 
-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,
 
@@ -20,15 +16,80 @@ enum cp_error_code {
 	CP_ENCL	     = 1 << 15,
 };
 
-DEFINE_IDTENTRY_ERRORCODE(exc_control_protection)
+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)
 {
-	if (!cpu_feature_enabled(X86_FEATURE_IBT)) {
-		pr_err("Unexpected #CP\n");
-		BUG();
+	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");
 	}
 
-	if (WARN_ON_ONCE(user_mode(regs) || (error_code & CP_EC) != CP_ENDBR))
+	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;
@@ -74,3 +135,18 @@ static int __init ibt_setup(char *str)
 }
 
 __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 @@ Efault:
 */
 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 6f666dfa97de..f358350624b2 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)