x86/fpu: Get rid of PF_USED_MATH usage, convert it to fpu->fpstate_active

Introduce a simple fpu->fpstate_active flag in the fpu context data structure
and use that instead of PF_USED_MATH in task->flags.

Testing for this flag byte should be slightly more efficient than
testing a bit in a bitmask, but the main advantage is that most
FPU functions can now be performed on a 'struct fpu' alone, they
don't need access to 'struct task_struct' anymore.

There's a slight linecount increase, mostly due to the 'fpu' local
variables and due to extra comments. The local variables will go away
once we move most of the FPU methods to pure 'struct fpu' parameters.

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>

3 files changed, 12 insertions, 4 deletions

diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 2cac49e3b4bd..9311126571ab 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -375,7 +375,7 @@ static inline void drop_fpu(struct task_struct *tsk)
 		__thread_fpu_end(fpu);
 	}
 
-	tsk->flags &= ~PF_USED_MATH;
+	fpu->fpstate_active = 0;
 
 	preempt_enable();
 }
@@ -424,7 +424,7 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 	 * If the task has used the math, pre-load the FPU on xsave processors
 	 * or if the past 5 consecutive context-switches used math.
 	 */
-	fpu.preload = (new->flags & PF_USED_MATH) &&
+	fpu.preload = new_fpu->fpstate_active &&
 		      (use_eager_fpu() || new->thread.fpu.counter > 5);
 
 	if (old_fpu->has_fpu) {
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index efb520dcf38e..f6317d9aa808 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -137,6 +137,12 @@ struct fpu {
 	 * deal with bursty apps that only use the FPU for a short time:
 	 */
 	unsigned char			counter;
+	/*
+	 * This flag indicates whether this context is fpstate_active: if the task is
+	 * not running then we can restore from this context, if the task
+	 * is running then we should save into this context.
+	 */
+	unsigned char			fpstate_active;
 };
 
 #endif /* _ASM_X86_FPU_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d50cc7f61559..0f4add462697 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -385,6 +385,10 @@ struct thread_struct {
 	unsigned long		fs;
 #endif
 	unsigned long		gs;
+
+	/* Floating point and extended processor state */
+	struct fpu		fpu;
+
 	/* Save middle states of ptrace breakpoints */
 	struct perf_event	*ptrace_bps[HBP_NUM];
 	/* Debug status used for traps, single steps, etc... */
@@ -395,8 +399,6 @@ struct thread_struct {
 	unsigned long		cr2;
 	unsigned long		trap_nr;
 	unsigned long		error_code;
-	/* floating point and extended processor state */
-	struct fpu		fpu;
 #ifdef CONFIG_X86_32
 	/* Virtual 86 mode info */
 	struct vm86_struct __user *vm86_info;