The remaining callers of kernel_fpu_begin() in 64-bit kernels don't use 387
instructions, so there's no need to sanitize FCW. Skip it to get the
performance we lost back.
Reported-by: Krzysztof Olędzki <o...@ans.pl>
Signed-off-by: Andy Lutomirski <l...@kernel.org>
---
arch/x86/include/asm/fpu/api.h | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index e95a06845443..6e826796a734 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -40,7 +40,19 @@ extern void fpregs_mark_activate(void);
/* Code that is unaware of kernel_fpu_begin_mask() can use this */
static inline void kernel_fpu_begin(void)
{
+#ifdef CONFIG_X86_64
+ /*
+ * Any 64-bit code that uses 387 instructions must explicitly request
+ * KFPU_387.
+ */
+ kernel_fpu_begin_mask(KFPU_XYZMM);
+#else
+ /*
+ * 32-bit kernel code may use 387 operations as well as SSE2, etc,
+ * as long as it checks that the CPU has the required capability.
+ */
kernel_fpu_begin_mask(KFPU_387 | KFPU_XYZMM);
+#endif
}
/*
--
2.29.2
