[RFT PATCH v1 7/7] arm64: disable lazy load if FPSIMD registers are frequently used

[Jiang Liu]

From: Jiang Liu <jiang.liu at huawei.com>

Disable lazy load if FPSIMD registers are frequently used by the thread,
so we can reduce overhead of lazy FPSIMD restore for FPU extensive
applications. The thresholds are randomly chosen without thorough
benchmarks, we may need to tune it for really systems.

Signed-off-by: Jiang Liu <jiang.liu at huawei.com>
Cc: Jiang Liu <liuj97 at gmail.com>
---
 arch/arm64/include/asm/fpsimd.h | 1 +
 arch/arm64/kernel/fpsimd.c      | 9 +++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 3490935..de6e877 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -37,6 +37,7 @@ struct fpsimd_state {
 			u32 fpcr;
 			bool on_hw;	/* soft state: whether loaded onto hw */
 			int last_cpu;
+			int fpu_counter;
 		};
 	};
 };
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index a81af5f..03e96b8 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -107,7 +107,7 @@ static void fpsimd_load_state_lazy(struct fpsimd_state *state,
 	    __this_cpu_read(fpsimd_owner) == state)
 		return;
 
-	if (static_key_false(&fpsimd_lazy_mode)) {
+	if (state->fpu_counter < 5 && static_key_false(&fpsimd_lazy_mode)) {
 		fpsimd_clear_on_hw(state);
 		fpsimd_enable_trap();
 	} else if (tsk_used_math(tsk)) {
@@ -124,8 +124,11 @@ static void fpsimd_save_state_lazy(struct fpsimd_state *state)
 		return;
 
 	if (static_key_false(&fpsimd_lazy_mode)) {
-		if (!fpsimd_is_on_hw(state))
+		if (!fpsimd_is_on_hw(state)) {
+			state->fpu_counter = clamp(state->fpu_counter - 1,
+						   0, 10);
 			return;
+		}
 	}
 
 	fpsimd_save_state(state);
@@ -144,6 +147,7 @@ void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 	fpsimd_load_state(state);
 	if (static_key_false(&fpsimd_lazy_mode)) {
 		fpsimd_set_on_hw(state);
+		state->fpu_counter++;
 		if (!used_math())
 			set_used_math();
 	} else {
@@ -213,6 +217,7 @@ void fpsimd_dup_state(struct fpsimd_state *src, struct fpsimd_state *dst)
 		preempt_disable();
 		if (fpsimd_is_on_hw(src))
 			fpsimd_save_state(dst);
+		dst->fpu_counter = 0;
 		fpsimd_clear_on_hw(dst);
 		preempt_enable();
 	} else if (used_math()) {
-- 
1.8.1.2