1 files changed, 170 insertions, 48 deletions

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 4fa0b17e5043..c5c897a86418 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -42,6 +42,7 @@
 #include <linux/hardirq.h>
 #include <linux/atomic.h>
 #include <linux/iommu.h>
+#include <linux/ubsan.h>
 
 #include <asm/stacktrace.h>
 #include <asm/processor.h>
@@ -67,6 +68,7 @@
 #include <asm/vdso.h>
 #include <asm/tdx.h>
 #include <asm/cfi.h>
+#include <asm/msr.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/x86_init.h>
@@ -91,6 +93,96 @@ __always_inline int is_valid_bugaddr(unsigned long addr)
 	return *(unsigned short *)addr == INSN_UD2;
 }
 
+/*
+ * Check for UD1 or UD2, accounting for Address Size Override Prefixes.
+ * If it's a UD1, further decode to determine its use:
+ *
+ * FineIBT:      ea                      (bad)
+ * FineIBT:      f0 75 f9                lock jne . - 6
+ * UBSan{0}:     67 0f b9 00             ud1    (%eax),%eax
+ * UBSan{10}:    67 0f b9 40 10          ud1    0x10(%eax),%eax
+ * static_call:  0f b9 cc                ud1    %esp,%ecx
+ *
+ * Notably UBSAN uses EAX, static_call uses ECX.
+ */
+__always_inline int decode_bug(unsigned long addr, s32 *imm, int *len)
+{
+	unsigned long start = addr;
+	bool lock = false;
+	u8 v;
+
+	if (addr < TASK_SIZE_MAX)
+		return BUG_NONE;
+
+	v = *(u8 *)(addr++);
+	if (v == INSN_ASOP)
+		v = *(u8 *)(addr++);
+
+	if (v == INSN_LOCK) {
+		lock = true;
+		v = *(u8 *)(addr++);
+	}
+
+	switch (v) {
+	case 0x70 ... 0x7f: /* Jcc.d8 */
+		addr += 1; /* d8 */
+		*len = addr - start;
+		WARN_ON_ONCE(!lock);
+		return BUG_LOCK;
+
+	case 0xea:
+		*len = addr - start;
+		return BUG_EA;
+
+	case OPCODE_ESCAPE:
+		break;
+
+	default:
+		return BUG_NONE;
+	}
+
+	v = *(u8 *)(addr++);
+	if (v == SECOND_BYTE_OPCODE_UD2) {
+		*len = addr - start;
+		return BUG_UD2;
+	}
+
+	if (v != SECOND_BYTE_OPCODE_UD1)
+		return BUG_NONE;
+
+	*imm = 0;
+	v = *(u8 *)(addr++);		/* ModRM */
+
+	if (X86_MODRM_MOD(v) != 3 && X86_MODRM_RM(v) == 4)
+		addr++;			/* SIB */
+
+	/* Decode immediate, if present */
+	switch (X86_MODRM_MOD(v)) {
+	case 0: if (X86_MODRM_RM(v) == 5)
+			addr += 4; /* RIP + disp32 */
+		break;
+
+	case 1: *imm = *(s8 *)addr;
+		addr += 1;
+		break;
+
+	case 2: *imm = *(s32 *)addr;
+		addr += 4;
+		break;
+
+	case 3: break;
+	}
+
+	/* record instruction length */
+	*len = addr - start;
+
+	if (X86_MODRM_REG(v) == 0)	/* EAX */
+		return BUG_UD1_UBSAN;
+
+	return BUG_UD1;
+}
+
+
 static nokprobe_inline int
 do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str,
 		  struct pt_regs *regs,	long error_code)
@@ -215,15 +307,13 @@ static inline void handle_invalid_op(struct pt_regs *regs)
 
 static noinstr bool handle_bug(struct pt_regs *regs)
 {
+	unsigned long addr = regs->ip;
 	bool handled = false;
+	int ud_type, ud_len;
+	s32 ud_imm;
 
-	/*
-	 * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug()
-	 * is a rare case that uses @regs without passing them to
-	 * irqentry_enter().
-	 */
-	kmsan_unpoison_entry_regs(regs);
-	if (!is_valid_bugaddr(regs->ip))
+	ud_type = decode_bug(addr, &ud_imm, &ud_len);
+	if (ud_type == BUG_NONE)
 		return handled;
 
 	/*
@@ -231,16 +321,58 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	 */
 	instrumentation_begin();
 	/*
+	 * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug()
+	 * is a rare case that uses @regs without passing them to
+	 * irqentry_enter().
+	 */
+	kmsan_unpoison_entry_regs(regs);
+	/*
 	 * Since we're emulating a CALL with exceptions, restore the interrupt
 	 * state to what it was at the exception site.
 	 */
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_enable();
-	if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN ||
-	    handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
-		regs->ip += LEN_UD2;
-		handled = true;
+
+	switch (ud_type) {
+	case BUG_UD2:
+		if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
+			handled = true;
+			break;
+		}
+		fallthrough;
+
+	case BUG_EA:
+	case BUG_LOCK:
+		if (handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
+			handled = true;
+			break;
+		}
+		break;
+
+	case BUG_UD1_UBSAN:
+		if (IS_ENABLED(CONFIG_UBSAN_TRAP)) {
+			pr_crit("%s at %pS\n",
+				report_ubsan_failure(ud_imm),
+				(void *)regs->ip);
+		}
+		break;
+
+	default:
+		break;
+	}
+
+	/*
+	 * When continuing, and regs->ip hasn't changed, move it to the next
+	 * instruction. When not continuing execution, restore the instruction
+	 * pointer.
+	 */
+	if (handled) {
+		if (regs->ip == addr)
+			regs->ip += ud_len;
+	} else {
+		regs->ip = addr;
 	}
+
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_disable();
 	instrumentation_end();
@@ -331,6 +463,21 @@ __visible void __noreturn handle_stack_overflow(struct pt_regs *regs,
 #endif
 
 /*
+ * Prevent the compiler and/or objtool from marking the !CONFIG_X86_ESPFIX64
+ * version of exc_double_fault() as noreturn.  Otherwise the noreturn mismatch
+ * between configs triggers objtool warnings.
+ *
+ * This is a temporary hack until we have compiler or plugin support for
+ * annotating noreturns.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+#define always_true() true
+#else
+bool always_true(void);
+bool __weak always_true(void) { return true; }
+#endif
+
+/*
  * Runs on an IST stack for x86_64 and on a special task stack for x86_32.
  *
  * On x86_64, this is more or less a normal kernel entry.  Notwithstanding the
@@ -465,7 +612,8 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
 
 	pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code);
 	die("double fault", regs, error_code);
-	panic("Machine halted.");
+	if (always_true())
+		panic("Machine halted.");
 	instrumentation_end();
 }
 
@@ -602,7 +750,7 @@ static bool try_fixup_enqcmd_gp(void)
 	if (current->pasid_activated)
 		return false;
 
-	wrmsrl(MSR_IA32_PASID, pasid | MSR_IA32_PASID_VALID);
+	wrmsrq(MSR_IA32_PASID, pasid | MSR_IA32_PASID_VALID);
 	current->pasid_activated = 1;
 
 	return true;
@@ -735,16 +883,16 @@ static void do_int3_user(struct pt_regs *regs)
 DEFINE_IDTENTRY_RAW(exc_int3)
 {
 	/*
-	 * poke_int3_handler() is completely self contained code; it does (and
+	 * smp_text_poke_int3_handler() is completely self contained code; it does (and
 	 * must) *NOT* call out to anything, lest it hits upon yet another
 	 * INT3.
 	 */
-	if (poke_int3_handler(regs))
+	if (smp_text_poke_int3_handler(regs))
 		return;
 
 	/*
 	 * irqentry_enter_from_user_mode() uses static_branch_{,un}likely()
-	 * and therefore can trigger INT3, hence poke_int3_handler() must
+	 * and therefore can trigger INT3, hence smp_text_poke_int3_handler() must
 	 * be done before. If the entry came from kernel mode, then use
 	 * nmi_enter() because the INT3 could have been hit in any context
 	 * including NMI.
@@ -973,9 +1121,9 @@ static noinstr void exc_debug_kernel(struct pt_regs *regs, unsigned long dr6)
 		 */
 		unsigned long debugctl;
 
-		rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+		rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 		debugctl |= DEBUGCTLMSR_BTF;
-		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+		wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 	}
 
 	/*
@@ -1148,7 +1296,7 @@ DEFINE_IDTENTRY_RAW(exc_debug)
 static void math_error(struct pt_regs *regs, int trapnr)
 {
 	struct task_struct *task = current;
-	struct fpu *fpu = &task->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(task);
 	int si_code;
 	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
 						"simd exception";
@@ -1239,11 +1387,11 @@ static bool handle_xfd_event(struct pt_regs *regs)
 	if (!IS_ENABLED(CONFIG_X86_64) || !cpu_feature_enabled(X86_FEATURE_XFD))
 		return false;
 
-	rdmsrl(MSR_IA32_XFD_ERR, xfd_err);
+	rdmsrq(MSR_IA32_XFD_ERR, xfd_err);
 	if (!xfd_err)
 		return false;
 
-	wrmsrl(MSR_IA32_XFD_ERR, 0);
+	wrmsrq(MSR_IA32_XFD_ERR, 0);
 
 	/* Die if that happens in kernel space */
 	if (WARN_ON(!user_mode(regs)))
@@ -1402,34 +1550,8 @@ DEFINE_IDTENTRY_SW(iret_error)
 }
 #endif
 
-/* Do not enable FRED by default yet. */
-static bool enable_fred __ro_after_init = false;
-
-#ifdef CONFIG_X86_FRED
-static int __init fred_setup(char *str)
-{
-	if (!str)
-		return -EINVAL;
-
-	if (!cpu_feature_enabled(X86_FEATURE_FRED))
-		return 0;
-
-	if (!strcmp(str, "on"))
-		enable_fred = true;
-	else if (!strcmp(str, "off"))
-		enable_fred = false;
-	else
-		pr_warn("invalid FRED option: 'fred=%s'\n", str);
-	return 0;
-}
-early_param("fred", fred_setup);
-#endif
-
 void __init trap_init(void)
 {
-	if (cpu_feature_enabled(X86_FEATURE_FRED) && !enable_fred)
-		setup_clear_cpu_cap(X86_FEATURE_FRED);
-
 	/* Init cpu_entry_area before IST entries are set up */
 	setup_cpu_entry_areas();
 
@@ -1437,7 +1559,7 @@ void __init trap_init(void)
 	sev_es_init_vc_handling();
 
 	/* Initialize TSS before setting up traps so ISTs work */
-	cpu_init_exception_handling();
+	cpu_init_exception_handling(true);
 
 	/* Setup traps as cpu_init() might #GP */
 	if (!cpu_feature_enabled(X86_FEATURE_FRED))