[PATCH 6/7] powerpc/mm: 64-bit: tlb handler micro-optimization

[Scott Wood]

A little more speed up measured on e5500.

Setting of U0-3 is dropped as it is not used by Linux as far as I can
see.

Signed-off-by: Scott Wood <scottwood at freescale.com>
---
 arch/powerpc/mm/tlb_low_64e.S |   21 ++++++++-------------
 1 files changed, 8 insertions(+), 13 deletions(-)

diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index e782023..a94c87b 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -47,10 +47,10 @@
 	 * We could probably also optimize by not saving SRR0/1 in the
 	 * linear mapping case but I'll leave that for later
 	 */
-	mfspr	r14,SPRN_ESR
 	mfspr	r16,SPRN_DEAR		/* get faulting address */
 	srdi	r15,r16,60		/* get region */
 	cmpldi	cr0,r15,0xc		/* linear mapping ? */
+	mfspr	r14,SPRN_ESR
 	TLB_MISS_STATS_SAVE_INFO
 	beq	tlb_load_linear		/* yes -> go to linear map load */
 
@@ -62,11 +62,11 @@
 	andi.	r10,r15,0x1
 	bne-	virt_page_table_tlb_miss
 
-	std	r14,EX_TLB_ESR(r12);	/* save ESR */
-	std	r16,EX_TLB_DEAR(r12);	/* save DEAR */
+	/* We need _PAGE_PRESENT and  _PAGE_ACCESSED set */
 
-	 /* We need _PAGE_PRESENT and  _PAGE_ACCESSED set */
+	std	r14,EX_TLB_ESR(r12);	/* save ESR */
 	li	r11,_PAGE_PRESENT
+	std	r16,EX_TLB_DEAR(r12);	/* save DEAR */
 	oris	r11,r11,_PAGE_ACCESSED at h
 
 	/* We do the user/kernel test for the PID here along with the RW test
@@ -225,21 +225,16 @@ finish_normal_tlb_miss:
 	 *                 yet implemented for now
 	 * MAS 2   :	Defaults not useful, need to be redone
 	 * MAS 3+7 :	Needs to be done
-	 *
-	 * TODO: mix up code below for better scheduling
 	 */
 	clrrdi	r11,r16,12		/* Clear low crap in EA */
+	rldicr	r15,r14,64-(PTE_RPN_SHIFT-PAGE_SHIFT),63-PAGE_SHIFT
 	rlwimi	r11,r14,32-19,27,31	/* Insert WIMGE */
+	clrldi	r15,r15,12		/* Clear crap at the top */
 	mtspr	SPRN_MAS2,r11
-
-	/* Move RPN in position */
-	rldicr	r11,r14,64-(PTE_RPN_SHIFT-PAGE_SHIFT),63-PAGE_SHIFT
-	clrldi	r15,r11,12		/* Clear crap at the top */
-	rlwimi	r15,r14,32-8,22,25	/* Move in U bits */
+	andi.	r11,r14,_PAGE_DIRTY
 	rlwimi	r15,r14,32-2,26,31	/* Move in BAP bits */
 
 	/* Mask out SW and UW if !DIRTY (XXX optimize this !) */
-	andi.	r11,r14,_PAGE_DIRTY
 	bne	1f
 	li	r11,MAS3_SW|MAS3_UW
 	andc	r15,r15,r11
@@ -483,10 +478,10 @@ virt_page_table_tlb_miss_whacko_fault:
 	 * We could probably also optimize by not saving SRR0/1 in the
 	 * linear mapping case but I'll leave that for later
 	 */
-	mfspr	r14,SPRN_ESR
 	mfspr	r16,SPRN_DEAR		/* get faulting address */
 	srdi	r11,r16,60		/* get region */
 	cmpldi	cr0,r11,0xc		/* linear mapping ? */
+	mfspr	r14,SPRN_ESR
 	TLB_MISS_STATS_SAVE_INFO
 	beq	tlb_load_linear		/* yes -> go to linear map load */
 
-- 
1.7.4.1