x86/fpu: Uninline the irq_ts_save()/restore() functions

Especially the irq_ts_save() function is pretty bloaty, generating
over a dozen instructions, so uninline them.

Even though the API is used rarely, the space savings are measurable:

   text    data     bss     dec     hex filename
   13331995        2572920 1634304 17539219        10ba093 vmlinux.before
   13331739        2572920 1634304 17538963        10b9f93 vmlinux.after

( This also allows the removal of an include file inclusion from fpu/api.h,
  speeding up the kernel build slightly. )

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/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 0c713455fc63273ee63f7255f059f3010fc90853..62035cc1d9614b237f35a60db879b3ddd4324c34 100644 (file)
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -10,8 +10,6 @@
 #ifndef _ASM_X86_FPU_API_H
 #define _ASM_X86_FPU_API_H
 
-#include <linux/hardirq.h>
-
 /*
  * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
  * and they don't touch the preempt state on their own.
@@ -35,28 +33,7 @@ extern bool irq_fpu_usable(void);
  * in interrupt context interacting wrongly with other user/kernel fpu usage, we
  * should use them only in the context of irq_ts_save/restore()
  */
-static inline int irq_ts_save(void)
-{
-       /*
-        * If in process context and not atomic, we can take a spurious DNA fault.
-        * Otherwise, doing clts() in process context requires disabling preemption
-        * or some heavy lifting like kernel_fpu_begin()
-        */
-       if (!in_atomic())
-               return 0;
-
-       if (read_cr0() & X86_CR0_TS) {
-               clts();
-               return 1;
-       }
-
-       return 0;
-}
-
-static inline void irq_ts_restore(int TS_state)
-{
-       if (TS_state)
-               stts();
-}
+extern int  irq_ts_save(void);
+extern void irq_ts_restore(int TS_state);
 
 #endif /* _ASM_X86_FPU_API_H */

diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 8323a2a5241c32708f9a24dcbfec00d1fe4920f7..b20d4ea8e132fa4af49e9f22bd5a66ec069a5070 100644 (file)
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -6,6 +6,7 @@
  *     Gareth Hughes <gareth@valinux.com>, May 2000
  */
 #include <asm/fpu/internal.h>
+#include <linux/hardirq.h>
 
 /*
  * Track whether the kernel is using the FPU state
@@ -140,6 +141,35 @@ void kernel_fpu_end(void)
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 
+/*
+ * CR0::TS save/restore functions:
+ */
+int irq_ts_save(void)
+{
+       /*
+        * If in process context and not atomic, we can take a spurious DNA fault.
+        * Otherwise, doing clts() in process context requires disabling preemption
+        * or some heavy lifting like kernel_fpu_begin()
+        */
+       if (!in_atomic())
+               return 0;
+
+       if (read_cr0() & X86_CR0_TS) {
+               clts();
+               return 1;
+       }
+
+       return 0;
+}
+EXPORT_SYMBOL_GPL(irq_ts_save);
+
+void irq_ts_restore(int TS_state)
+{
+       if (TS_state)
+               stts();
+}
+EXPORT_SYMBOL_GPL(irq_ts_restore);
+
 static void __save_fpu(struct fpu *fpu)
 {
        if (use_xsave()) {