i387: move AMD K7/K8 fpu fxsave/fxrstor workaround from save to restore

The AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
pending.  In order to not leak FIP state from one process to another, we
need to do a floating point load after the fxsave of the old process,
and before the fxrstor of the new FPU state.  That resets the state to
the (uninteresting) kernel load, rather than some potentially sensitive
user information.

We used to do this directly after the FPU state save, but that is
actually very inconvenient, since it

 (a) corrupts what is potentially perfectly good FPU state that we might
     want to lazy avoid restoring later and

 (b) on x86-64 it resulted in a very annoying ordering constraint, where
     "__unlazy_fpu()" in the task switch needs to be delayed until after
     the DS segment has been reloaded just to get the new DS value.

Coupling it to the fxrstor instead of the fxsave automatically avoids
both of these issues, and also ensures that we only do it when actually
necessary (the FP state after a save may never actually get used).  It's
simply a much more natural place for the leaked state cleanup.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86/include/asm/i387.h

@@ -211,15 +211,6 @@ static inline void fpu_fxsave(struct fpu *fpu)
 
 #endif	/* CONFIG_X86_64 */
 
-/* We need a safe address that is cheap to find and that is already
-   in L1 during context switch. The best choices are unfortunately
-   different for UP and SMP */
-#ifdef CONFIG_SMP
-#define safe_address (__per_cpu_offset[0])
-#else
-#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER])
-#endif
-
 /*
  * These must be called with preempt disabled
  */
@@ -243,16 +234,6 @@ static inline void fpu_save_init(struct fpu *fpu)
 
 	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
 		asm volatile("fnclex");
-
-	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
-	   is pending.  Clear the x87 state here by setting it to fixed
-	   values. safe_address is a random variable that should be in L1 */
-	alternative_input(
-		ASM_NOP8 ASM_NOP2,
-		"emms\n\t"	  	/* clear stack tags */
-		"fildl %P[addr]",	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (safe_address));
 }
 
 static inline void __save_init_fpu(struct task_struct *tsk)

arch/x86/kernel/process_64.c

@@ -387,6 +387,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	struct tss_struct *tss = &per_cpu(init_tss, cpu);
 	unsigned fsindex, gsindex;
 
+	__unlazy_fpu(prev_p);
+
 	/*
 	 * Reload esp0, LDT and the page table pointer:
 	 */
@@ -415,9 +417,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	load_TLS(next, cpu);
 
-	/* Must be after DS reload */
-	__unlazy_fpu(prev_p);
-
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so

arch/x86/kernel/traps.c

@@ -585,6 +585,10 @@ void math_state_restore(void)
 	struct thread_info *thread = current_thread_info();
 	struct task_struct *tsk = thread->task;
 
+	/* We need a safe address that is cheap to find and that is already
+	   in L1. We just brought in "thread->task", so use that */
+#define safe_address (thread->task)
+
 	if (!tsk_used_math(tsk)) {
 		local_irq_enable();
 		/*
@@ -602,6 +606,16 @@ void math_state_restore(void)
 
 	__thread_fpu_begin(thread);
 
+	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+	   is pending.  Clear the x87 state here by setting it to fixed
+	   values. safe_address is a random variable that should be in L1 */
+	alternative_input(
+		ASM_NOP8 ASM_NOP2,
+		"emms\n\t"	  	/* clear stack tags */
+		"fildl %P[addr]",	/* set F?P to defined value */
+		X86_FEATURE_FXSAVE_LEAK,
+		[addr] "m" (safe_address));
+
 	/*
 	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
 	 */