x86/fpu: Factor out fpu__flush_thread() from flush_thread()

flush_thread() open codes a lot of FPU internals - create a separate
function for it in fpu/core.c.

Turns out that this does not hurt performance:

   text    data     bss     dec     hex filename
   11843039        1884440 1130496 14857975         e2b6f7 vmlinux.before
   11843039        1884440 1130496 14857975         e2b6f7 vmlinux.after

and since this is a slowpath clarity comes first anyway.

We can reconsider inlining decisions after the FPU code has been cleaned up.

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/i387.h b/arch/x86/include/asm/i387.h
index 6552a16e0e38aa1bfcab1b84f0b0a7929464422c..d6fc84440b73b37564fbf5988d40c514ba7d1340 100644 (file)
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -20,6 +20,7 @@ struct user_i387_struct;
 
 extern int fpstate_alloc_init(struct task_struct *curr);
 extern void fpstate_init(struct fpu *fpu);
+extern void fpu__flush_thread(struct task_struct *tsk);
 
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 extern void math_state_restore(void);

diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 9211582f5d3f994b5c2b9002d4ea9c95aef0cb9b..787bf57b842209259c394d568923ed918872b3d2 100644 (file)
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -227,6 +227,23 @@ static int fpu__unlazy_stopped(struct task_struct *child)
        return 0;
 }
 
+void fpu__flush_thread(struct task_struct *tsk)
+{
+       if (!use_eager_fpu()) {
+               /* FPU state will be reallocated lazily at the first use. */
+               drop_fpu(tsk);
+               fpstate_free(&tsk->thread.fpu);
+       } else {
+               if (!tsk_used_math(tsk)) {
+                       /* kthread execs. TODO: cleanup this horror. */
+               if (WARN_ON(fpstate_alloc_init(tsk)))
+                               force_sig(SIGKILL, tsk);
+                       user_fpu_begin();
+               }
+               restore_init_xstate();
+       }
+}
+
 /*
  * The xstateregs_active() routine is the same as the fpregs_active() routine,
  * as the "regset->n" for the xstate regset will be updated based on the feature

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6ab180f40a7ea2d47422c361e350db9987d4375f..52fd8f6f44c760246e3cb42798f17127f74fc0d2 100644 (file)
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -146,19 +146,7 @@ void flush_thread(void)
        flush_ptrace_hw_breakpoint(tsk);
        memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 
-       if (!use_eager_fpu()) {
-               /* FPU state will be reallocated lazily at the first use. */
-               drop_fpu(tsk);
-               fpstate_free(&tsk->thread.fpu);
-       } else {
-               if (!tsk_used_math(tsk)) {
-                       /* kthread execs. TODO: cleanup this horror. */
-               if (WARN_ON(fpstate_alloc_init(tsk)))
-                               force_sig(SIGKILL, tsk);
-                       user_fpu_begin();
-               }
-               restore_init_xstate();
-       }
+       fpu__flush_thread(tsk);
 }
 
 static void hard_disable_TSC(void)