x86, fpu: Fix math_state_restore() race with kernel_fpu_begin()

math_state_restore() can race with kernel_fpu_begin() if irq comes
right after __thread_fpu_begin(), __save_init_fpu() will overwrite
fpu->state we are going to restore.

Add 2 simple helpers, kernel_fpu_disable() and kernel_fpu_enable()
which simply set/clear in_kernel_fpu, and change math_state_restore()
to exclude kernel_fpu_begin() in between.

Alternatively we could use local_irq_save/restore, but probably these
new helpers can have more users.

Perhaps they should disable/enable preemption themselves, in this case
we can remove preempt_disable() in __restore_xstate_sig().
Signed-off-by: NOleg Nesterov <oleg@redhat.com>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: matt.fleming@intel.com
Cc: bp@suse.de
Cc: pbonzini@redhat.com
Cc: luto@amacapital.net
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Suresh Siddha <sbsiddha@gmail.com>
Link: http://lkml.kernel.org/r/20150115192028.GD27332@redhat.comSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

arch/x86/include/asm/i387.h

@@ -51,6 +51,10 @@ static inline void kernel_fpu_end(void)
 	preempt_enable();
 }
 
+/* Must be called with preempt disabled */
+extern void kernel_fpu_disable(void);
+extern void kernel_fpu_enable(void);
+
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
  * DNA fault but don't modify SSE registers. And these instructions

arch/x86/kernel/i387.c

@@ -21,6 +21,17 @@
 
 static DEFINE_PER_CPU(bool, in_kernel_fpu);
 
+void kernel_fpu_disable(void)
+{
+	WARN_ON(this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, true);
+}
+
+void kernel_fpu_enable(void)
+{
+	this_cpu_write(in_kernel_fpu, false);
+}
+
 /*
  * Were we in an interrupt that interrupted kernel mode?
  *

arch/x86/kernel/traps.c

@@ -788,18 +788,16 @@ void math_state_restore(void)
 		local_irq_disable();
 	}
 
+	/* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */
+	kernel_fpu_disable();
 	__thread_fpu_begin(tsk);
-
-	/*
-	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
-	 */
 	if (unlikely(restore_fpu_checking(tsk))) {
 		drop_init_fpu(tsk);
 		force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
-		return;
+	} else {
+		tsk->thread.fpu_counter++;
 	}
-
-	tsk->thread.fpu_counter++;
+	kernel_fpu_enable();
 }
 EXPORT_SYMBOL_GPL(math_state_restore);