Merge branch 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull fpu state cleanups from Ingo Molnar:
 "This tree streamlines further aspects of FPU handling by eliminating
  the prepare_to_copy() complication and moving that logic to
  arch_dup_task_struct().

  It also fixes the FPU dumps in threaded core dumps, removes and old
  (and now invalid) assumption plus micro-optimizes the exit path by
  avoiding an FPU save for dead tasks."

Fixed up trivial add-add conflict in arch/sh/kernel/process.c that came
in because we now do the FPU handling in arch_dup_task_struct() rather
than the legacy (and now gone) prepare_to_copy().

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, fpu: drop the fpu state during thread exit
  x86, xsave: remove thread_has_fpu() bug check in __sanitize_i387_state()
  coredump: ensure the fpu state is flushed for proper multi-threaded core dump
  fork: move the real prepare_to_copy() users to arch_dup_task_struct()

4 files changed, 19 insertions, 26 deletions

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f2e8c0f951d6..735279e54e59 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -56,10 +56,16 @@ EXPORT_SYMBOL_GPL(idle_notifier_unregister);
 struct kmem_cache *task_xstate_cachep;
 EXPORT_SYMBOL_GPL(task_xstate_cachep);
 
+/*
+ * this gets called so that we can store lazy state into memory and copy the
+ * current task into the new thread.
+ */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	int ret;
 
+	unlazy_fpu(src);
+
 	*dst = *src;
 	if (fpu_allocated(&src->thread.fpu)) {
 		memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu));
@@ -89,6 +95,16 @@ void arch_task_cache_init(void)
 				  SLAB_PANIC | SLAB_NOTRACK, NULL);
 }
 
+static inline void drop_fpu(struct task_struct *tsk)
+{
+	/*
+	 * Forget coprocessor state..
+	 */
+	tsk->fpu_counter = 0;
+	clear_fpu(tsk);
+	clear_used_math();
+}
+
 /*
  * Free current thread data structures etc..
  */
@@ -111,6 +127,8 @@ void exit_thread(void)
 		put_cpu();
 		kfree(bp);
 	}
+
+	drop_fpu(me);
 }
 
 void show_regs_common(void)
@@ -145,12 +163,7 @@ void flush_thread(void)
 
 	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
-	/*
-	 * Forget coprocessor state..
-	 */
-	tsk->fpu_counter = 0;
-	clear_fpu(tsk);
-	clear_used_math();
+	drop_fpu(tsk);
 }
 
 static void hard_disable_TSC(void)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 01d8d40ccaf6..516fa186121b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -126,15 +126,6 @@ void release_thread(struct task_struct *dead_task)
 	release_vm86_irqs(dead_task);
 }
 
-/*
- * This gets called before we allocate a new thread and copy
- * the current task into it.
- */
-void prepare_to_copy(struct task_struct *tsk)
-{
-	unlazy_fpu(tsk);
-}
-
 int copy_thread(unsigned long clone_flags, unsigned long sp,
 	unsigned long unused,
 	struct task_struct *p, struct pt_regs *regs)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 28e810255a0a..61cdf7fdf099 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -145,15 +145,6 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls)
 	return get_desc_base(&t->thread.tls_array[tls]);
 }
 
-/*
- * This gets called before we allocate a new thread and copy
- * the current task into it.
- */
-void prepare_to_copy(struct task_struct *tsk)
-{
-	unlazy_fpu(tsk);
-}
-
 int copy_thread(unsigned long clone_flags, unsigned long sp,
 		unsigned long unused,
 	struct task_struct *p, struct pt_regs *regs)
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index e62728e30b01..bd18149b2b0f 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -48,8 +48,6 @@ void __sanitize_i387_state(struct task_struct *tsk)
 	if (!fx)
 		return;
 
-	BUG_ON(__thread_has_fpu(tsk));
-
 	xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
 
 	/*