1 files changed, 70 insertions, 8 deletions

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c3b2f863ac..4fa0b17e50 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -51,6 +51,7 @@
 #include <asm/ftrace.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
+#include <asm/fred.h>
 #include <asm/fpu/api.h>
 #include <asm/cpu.h>
 #include <asm/cpu_entry_area.h>
@@ -773,7 +774,7 @@ DEFINE_IDTENTRY_RAW(exc_int3)
  */
 asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs)
 {
-	struct pt_regs *regs = (struct pt_regs *)this_cpu_read(pcpu_hot.top_of_stack) - 1;
+	struct pt_regs *regs = (struct pt_regs *)current_top_of_stack() - 1;
 	if (regs != eregs)
 		*regs = *eregs;
 	return regs;
@@ -791,7 +792,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r
 	 * trust it and switch to the current kernel stack
 	 */
 	if (ip_within_syscall_gap(regs)) {
-		sp = this_cpu_read(pcpu_hot.top_of_stack);
+		sp = current_top_of_stack();
 		goto sync;
 	}
 
@@ -935,8 +936,7 @@ static bool notify_debug(struct pt_regs *regs, unsigned long *dr6)
 	return false;
 }
 
-static __always_inline void exc_debug_kernel(struct pt_regs *regs,
-					     unsigned long dr6)
+static noinstr void exc_debug_kernel(struct pt_regs *regs, unsigned long dr6)
 {
 	/*
 	 * Disable breakpoints during exception handling; recursive exceptions
@@ -948,6 +948,11 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 	 *
 	 * Entry text is excluded for HW_BP_X and cpu_entry_area, which
 	 * includes the entry stack is excluded for everything.
+	 *
+	 * For FRED, nested #DB should just work fine. But when a watchpoint or
+	 * breakpoint is set in the code path which is executed by #DB handler,
+	 * it results in an endless recursion and stack overflow. Thus we stay
+	 * with the IDT approach, i.e., save DR7 and disable #DB.
 	 */
 	unsigned long dr7 = local_db_save();
 	irqentry_state_t irq_state = irqentry_nmi_enter(regs);
@@ -977,7 +982,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 	 * Catch SYSENTER with TF set and clear DR_STEP. If this hit a
 	 * watchpoint at the same time then that will still be handled.
 	 */
-	if ((dr6 & DR_STEP) && is_sysenter_singlestep(regs))
+	if (!cpu_feature_enabled(X86_FEATURE_FRED) &&
+	    (dr6 & DR_STEP) && is_sysenter_singlestep(regs))
 		dr6 &= ~DR_STEP;
 
 	/*
@@ -1009,8 +1015,7 @@ out:
 	local_db_restore(dr7);
 }
 
-static __always_inline void exc_debug_user(struct pt_regs *regs,
-					   unsigned long dr6)
+static noinstr void exc_debug_user(struct pt_regs *regs, unsigned long dr6)
 {
 	bool icebp;
 
@@ -1094,6 +1099,34 @@ DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
 {
 	exc_debug_user(regs, debug_read_clear_dr6());
 }
+
+#ifdef CONFIG_X86_FRED
+/*
+ * When occurred on different ring level, i.e., from user or kernel
+ * context, #DB needs to be handled on different stack: User #DB on
+ * current task stack, while kernel #DB on a dedicated stack.
+ *
+ * This is exactly how FRED event delivery invokes an exception
+ * handler: ring 3 event on level 0 stack, i.e., current task stack;
+ * ring 0 event on the #DB dedicated stack specified in the
+ * IA32_FRED_STKLVLS MSR. So unlike IDT, the FRED debug exception
+ * entry stub doesn't do stack switch.
+ */
+DEFINE_FREDENTRY_DEBUG(exc_debug)
+{
+	/*
+	 * FRED #DB stores DR6 on the stack in the format which
+	 * debug_read_clear_dr6() returns for the IDT entry points.
+	 */
+	unsigned long dr6 = fred_event_data(regs);
+
+	if (user_mode(regs))
+		exc_debug_user(regs, dr6);
+	else
+		exc_debug_kernel(regs, dr6);
+}
+#endif /* CONFIG_X86_FRED */
+
 #else
 /* 32 bit does not have separate entry points. */
 DEFINE_IDTENTRY_RAW(exc_debug)
@@ -1369,8 +1402,34 @@ 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();
 
@@ -1379,7 +1438,10 @@ void __init trap_init(void)
 
 	/* Initialize TSS before setting up traps so ISTs work */
 	cpu_init_exception_handling();
+
 	/* Setup traps as cpu_init() might #GP */
-	idt_setup_traps();
+	if (!cpu_feature_enabled(X86_FEATURE_FRED))
+		idt_setup_traps();
+
 	cpu_init();
 }