x86/fpu: Clean up and fix MXCSR handling

The code has the following problems:

 - it uses a single global 'fx_scratch' area that multiple CPUs could
   write into simultaneously, in theory.

 - it wastes 512 bytes of .data for something that is only rarely used.

Fix this by moving the state buffer to the stack. Note that while
this is 512 bytes, we don't ever call this function in very deep
callchains, so its stack usage should not be a problem.

Also add comments to explain the magic 0x0000ffbf default value.

Reviewed-by: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 33df056b1624cf8be39c3a9a59a166138c48160a..0b16f61cb2a4e838bae0bd5ffd9f2d3e470f4f61 100644 (file)
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -68,18 +68,26 @@ void fpu__init_check_bugs(void)
  * Boot time FPU feature detection code:
  */
 unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+
 unsigned int xstate_size;
 EXPORT_SYMBOL_GPL(xstate_size);
-static struct i387_fxsave_struct fx_scratch;
 
 static void mxcsr_feature_mask_init(void)
 {
-       unsigned long mask = 0;
+       unsigned int mask = 0;
 
        if (cpu_has_fxsr) {
-               memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
-               asm volatile("fxsave %0" : "+m" (fx_scratch));
-               mask = fx_scratch.mxcsr_mask;
+               struct i387_fxsave_struct fx_tmp __aligned(32) = { };
+
+               asm volatile("fxsave %0" : "+m" (fx_tmp));
+
+               mask = fx_tmp.mxcsr_mask;
+
+               /*
+                * If zero then use the default features mask,
+                * which has all features set, except the
+                * denormals-are-zero feature bit:
+                */
                if (mask == 0)
                        mask = 0x0000ffbf;
        }