[RFC PATCH REBASED 1/3] sh: Move fpu_counter into ARCH specific thread_struct

From: Vineet Gupta
Date: Tue Sep 17 2013 - 02:18:37 EST


Only a couple of arches (sh/x86) use fpu_counter in task_struct so it
can be moved out into ARCH specific thread_struct, reducing the size of
task_struct for other arches.

Compile tested sh defconfig + sh4-linux-gcc (4.6.3)

Signed-off-by: Vineet Gupta <vgupta@xxxxxxxxxxxx>
Cc: Paul Mundt <lethal@xxxxxxxxxxxx>
Cc: Michel Lespinasse <walken@xxxxxxxxxx>
Cc: Kuninori Morimoto <kuninori.morimoto.gx@xxxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Jesper Nilsson <jesper.nilsson@xxxxxxxx>
Cc: Chris Metcalf <cmetcalf@xxxxxxxxxx>
Cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: linux-arch@xxxxxxxxxxxxxxx
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: linux-sh@xxxxxxxxxxxxxxx
---
arch/sh/include/asm/fpu.h | 2 +-
arch/sh/include/asm/processor_32.h | 10 ++++++++++
arch/sh/include/asm/processor_64.h | 10 ++++++++++
arch/sh/kernel/cpu/fpu.c | 2 +-
arch/sh/kernel/process_32.c | 6 +++---
5 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/arch/sh/include/asm/fpu.h b/arch/sh/include/asm/fpu.h
index 06c4281..09fc2bc 100644
--- a/arch/sh/include/asm/fpu.h
+++ b/arch/sh/include/asm/fpu.h
@@ -46,7 +46,7 @@ static inline void __unlazy_fpu(struct task_struct *tsk, struct pt_regs *regs)
save_fpu(tsk);
release_fpu(regs);
} else
- tsk->fpu_counter = 0;
+ tsk->thread.fpu_counter = 0;
}

static inline void unlazy_fpu(struct task_struct *tsk, struct pt_regs *regs)
diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h
index e699a12..18e0377 100644
--- a/arch/sh/include/asm/processor_32.h
+++ b/arch/sh/include/asm/processor_32.h
@@ -111,6 +111,16 @@ struct thread_struct {

/* Extended processor state */
union thread_xstate *xstate;
+
+ /*
+ * fpu_counter contains the number of consecutive context switches
+ * that the FPU is used. If this is over a threshold, the lazy fpu
+ * saving becomes unlazy to save the trap. This is an unsigned char
+ * so that after 256 times the counter wraps and the behavior turns
+ * lazy again; this to deal with bursty apps that only use FPU for
+ * a short time
+ */
+ unsigned char fpu_counter;
};

#define INIT_THREAD { \
diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h
index 1cc7d31..eedd4f6 100644
--- a/arch/sh/include/asm/processor_64.h
+++ b/arch/sh/include/asm/processor_64.h
@@ -126,6 +126,16 @@ struct thread_struct {

/* floating point info */
union thread_xstate *xstate;
+
+ /*
+ * fpu_counter contains the number of consecutive context switches
+ * that the FPU is used. If this is over a threshold, the lazy fpu
+ * saving becomes unlazy to save the trap. This is an unsigned char
+ * so that after 256 times the counter wraps and the behavior turns
+ * lazy again; this to deal with bursty apps that only use FPU for
+ * a short time
+ */
+ unsigned char fpu_counter;
};

#define INIT_MMAP \
diff --git a/arch/sh/kernel/cpu/fpu.c b/arch/sh/kernel/cpu/fpu.c
index f8f7af5..4e33224 100644
--- a/arch/sh/kernel/cpu/fpu.c
+++ b/arch/sh/kernel/cpu/fpu.c
@@ -44,7 +44,7 @@ void __fpu_state_restore(void)
restore_fpu(tsk);

task_thread_info(tsk)->status |= TS_USEDFPU;
- tsk->fpu_counter++;
+ tsk->thread.fpu_counter++;
}

void fpu_state_restore(struct pt_regs *regs)
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index ebd3933..2885fc9 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -156,7 +156,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
#endif
ti->addr_limit = KERNEL_DS;
ti->status &= ~TS_USEDFPU;
- p->fpu_counter = 0;
+ p->thread.fpu_counter = 0;
return 0;
}
*childregs = *current_pt_regs();
@@ -189,7 +189,7 @@ __switch_to(struct task_struct *prev, struct task_struct *next)
unlazy_fpu(prev, task_pt_regs(prev));

/* we're going to use this soon, after a few expensive things */
- if (next->fpu_counter > 5)
+ if (next->thread.fpu_counter > 5)
prefetch(next_t->xstate);

#ifdef CONFIG_MMU
@@ -207,7 +207,7 @@ __switch_to(struct task_struct *prev, struct task_struct *next)
* restore of the math state immediately to avoid the trap; the
* chances of needing FPU soon are obviously high now
*/
- if (next->fpu_counter > 5)
+ if (next->thread.fpu_counter > 5)
__fpu_state_restore();

return prev;
--
1.8.1.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/