1 files changed, 39 insertions, 21 deletions

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 4ff5d162ff9f..f4fa991406cd 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -112,7 +112,7 @@ enum ctx_state ist_enter(struct pt_regs *regs)
 {
         enum ctx_state prev_state;
 
-        if (user_mode_vm(regs)) {
+        if (user_mode(regs)) {
                 /* Other than that, we're just an exception. */
                 prev_state = exception_enter();
         } else {
@@ -146,7 +146,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
         /* Must be before exception_exit. */
         preempt_count_sub(HARDIRQ_OFFSET);
 
-        if (user_mode_vm(regs))
+        if (user_mode(regs))
                 return exception_exit(prev_state);
         else
                 rcu_nmi_exit();
@@ -158,7 +158,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
  *
  * IST exception handlers normally cannot schedule.  As a special
  * exception, if the exception interrupted userspace code (i.e.
- * user_mode_vm(regs) would return true) and the exception was not
+ * user_mode(regs) would return true) and the exception was not
  * a double fault, it can be safe to schedule.  ist_begin_non_atomic()
  * begins a non-atomic section within an ist_enter()/ist_exit() region.
  * Callers are responsible for enabling interrupts themselves inside
@@ -167,15 +167,15 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
  */
 void ist_begin_non_atomic(struct pt_regs *regs)
 {
-        BUG_ON(!user_mode_vm(regs));
+        BUG_ON(!user_mode(regs));
 
         /*
          * Sanity check: we need to be on the normal thread stack.  This
          * will catch asm bugs and any attempt to use ist_preempt_enable
          * from double_fault.
          */
-        BUG_ON(((current_stack_pointer() ^ this_cpu_read_stable(kernel_stack))
-                & ~(THREAD_SIZE - 1)) != 0);
+        BUG_ON((unsigned long)(current_top_of_stack() -
+                               current_stack_pointer()) >= THREAD_SIZE);
 
         preempt_count_sub(HARDIRQ_OFFSET);
 }
@@ -194,8 +194,7 @@ static nokprobe_inline int
 do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
                   struct pt_regs *regs, long error_code)
 {
-#ifdef CONFIG_X86_32
-        if (regs->flags & X86_VM_MASK) {
+        if (v8086_mode(regs)) {
                 /*
                  * Traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
                  * On nmi (interrupt 2), do_trap should not be called.
@@ -207,7 +206,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
                 }
                 return -1;
         }
-#endif
+
         if (!user_mode(regs)) {
                 if (!fixup_exception(regs)) {
                         tsk->thread.error_code = error_code;
@@ -384,7 +383,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
                 goto exit;
         conditional_sti(regs);
 
-        if (!user_mode_vm(regs))
+        if (!user_mode(regs))
                 die("bounds", regs, error_code);
 
         if (!cpu_feature_enabled(X86_FEATURE_MPX)) {
@@ -462,13 +461,11 @@ do_general_protection(struct pt_regs *regs, long error_code)
         prev_state = exception_enter();
         conditional_sti(regs);
 
-#ifdef CONFIG_X86_32
-        if (regs->flags & X86_VM_MASK) {
+        if (v8086_mode(regs)) {
                 local_irq_enable();
                 handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
                 goto exit;
         }
-#endif
 
         tsk = current;
         if (!user_mode(regs)) {
@@ -587,7 +584,7 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
         /* Copy the remainder of the stack from the current stack. */
         memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip));
 
-        BUG_ON(!user_mode_vm(&new_stack->regs));
+        BUG_ON(!user_mode(&new_stack->regs));
         return new_stack;
 }
 NOKPROBE_SYMBOL(fixup_bad_iret);
@@ -637,7 +634,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
          * then it's very likely the result of an icebp/int01 trap.
          * User wants a sigtrap for that.
          */
-        if (!dr6 && user_mode_vm(regs))
+        if (!dr6 && user_mode(regs))
                 user_icebp = 1;
 
         /* Catch kmemcheck conditions first of all! */
@@ -673,7 +670,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
         /* It's safe to allow irq's after DR6 has been saved */
         preempt_conditional_sti(regs);
 
-        if (regs->flags & X86_VM_MASK) {
+        if (v8086_mode(regs)) {
                 handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
                                         X86_TRAP_DB);
                 preempt_conditional_cli(regs);
@@ -721,7 +718,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
                 return;
         conditional_sti(regs);
 
-        if (!user_mode_vm(regs))
+        if (!user_mode(regs))
         {
                 if (!fixup_exception(regs)) {
                         task->thread.error_code = error_code;
@@ -734,7 +731,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
         /*
          * Save the info for the exception handler and clear the error.
          */
-        save_init_fpu(task);
+        unlazy_fpu(task);
         task->thread.trap_nr = trapnr;
         task->thread.error_code = error_code;
         info.si_signo = SIGFPE;
@@ -863,7 +860,7 @@ void math_state_restore(void)
         kernel_fpu_disable();
         __thread_fpu_begin(tsk);
         if (unlikely(restore_fpu_checking(tsk))) {
-                drop_init_fpu(tsk);
+                fpu_reset_state(tsk);
                 force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
         } else {
                 tsk->thread.fpu_counter++;
@@ -925,9 +922,21 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 /* Set of traps needed for early debugging. */
 void __init early_trap_init(void)
 {
-        set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
+        /*
+         * Don't use IST to set DEBUG_STACK as it doesn't work until TSS
+         * is ready in cpu_init() <-- trap_init(). Before trap_init(),
+         * CPU runs at ring 0 so it is impossible to hit an invalid
+         * stack.  Using the original stack works well enough at this
+         * early stage. DEBUG_STACK will be equipped after cpu_init() in
+         * trap_init().
+         *
+         * We don't need to set trace_idt_table like set_intr_gate(),
+         * since we don't have trace_debug and it will be reset to
+         * 'debug' in trap_init() by set_intr_gate_ist().
+         */
+        set_intr_gate_notrace(X86_TRAP_DB, debug);
         /* int3 can be called from all */
-        set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+        set_system_intr_gate(X86_TRAP_BP, &int3);
 #ifdef CONFIG_X86_32
         set_intr_gate(X86_TRAP_PF, page_fault);
 #endif
@@ -1005,6 +1014,15 @@ void __init trap_init(void)
          */
         cpu_init();
 
+        /*
+         * X86_TRAP_DB and X86_TRAP_BP have been set
+         * in early_trap_init(). However, ITS works only after
+         * cpu_init() loads TSS. See comments in early_trap_init().
+         */
+        set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
+        /* int3 can be called from all */
+        set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+
         x86_init.irqs.trap_init();
 
 #ifdef CONFIG_X86_64