From: Vineet Gupta <vgupta@synopsys.com>
Date: Tue, 2 May 2017 23:23:57 +0000 (-0700)
Subject: ARCv2: mm: micro-optimize region flush generated code
X-Git-Tag: v4.12-rc1~51^2~4
X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=f734a31083324b8f4f24b2c5cba178c7459db309;p=karo-tx-linux.git

ARCv2: mm: micro-optimize region flush generated code

DC_CTRL.RGN_OP is 3 bits wide, however only 1 bit is used in current
programming model (0: flush, 1: invalidate)

The current code targetting 3 bits leads to additional 8 byte AND
operation which can be elided given that only 1 bit is ever set by
software and/or looked at by hardware

before
------

| 80b63324 <__dma_cache_wback_inv_l1>:
| 80b63324:	clri	r3
| 80b63328:	lr	r2,[dc_ctrl]
| 80b6332c:	and	r2,r2,0xfffff1ff	<--- 8 bytes insn
| 80b63334:	or	r2,r2,576
| 80b63338:	sr	r2,[dc_ctrl]
| ...
| ...
| 80b63360 <__dma_cache_inv_l1>:
| 80b63360:	clri	r3
| 80b63364:	lr	r2,[dc_ctrl]
| 80b63368:	and	r2,r2,0xfffff1ff	<--- 8 bytes insn
| 80b63370:	bset_s	r2,r2,0x9
| 80b63372:	sr	r2,[dc_ctrl]
| ...
| ...
| 80b6338c <__dma_cache_wback_l1>:
| 80b6338c:	clri	r3
| 80b63390:	lr	r2,[dc_ctrl]
| 80b63394:	and	r2,r2,0xfffff1ff	<--- 8 bytes insn
| 80b6339c:	sr	r2,[dc_ctrl]

after (AND elided totally in 2 cases, replaced with 2 byte BCLR in 3rd)
-----

| 80b63324 <__dma_cache_wback_inv_l1>:
| 80b63324:	clri	r3
| 80b63328:	lr	r2,[dc_ctrl]
| 80b6332c:	or	r2,r2,576
| 80b63330:	sr	r2,[dc_ctrl]
| ...
| ...
| 80b63358 <__dma_cache_inv_l1>:
| 80b63358:	clri	r3
| 80b6335c:	lr	r2,[dc_ctrl]
| 80b63360:	bset_s	r2,r2,0x9
| 80b63362:	sr	r2,[dc_ctrl]
| ...
| ...
| 80b6337c <__dma_cache_wback_l1>:
| 80b6337c:	clri	r3
| 80b63380:	lr	r2,[dc_ctrl]
| 80b63384:	bclr_s	r2,r2,0x9
| 80b63386:	sr	r2,[dc_ctrl]

Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
---

diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 16e457706129..19ebddffb279 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -88,7 +88,7 @@ extern unsigned long perip_base, perip_end;
 #define DC_CTRL_INV_MODE_FLUSH	0x040
 #define DC_CTRL_FLUSH_STATUS	0x100
 #define DC_CTRL_RGN_OP_INV	0x200
-#define DC_CTRL_RGN_OP_MSK	0xE00
+#define DC_CTRL_RGN_OP_MSK	0x200
 
 /*System-level cache (L2 cache) related Auxiliary registers */
 #define ARC_REG_SLC_CFG		0x901