parisc: Optimze cache flush algorithms

The attached patch implements three optimizations:

1) Loops in flush_user_dcache_range_asm, flush_kernel_dcache_range_asm,
purge_kernel_dcache_range_asm, flush_user_icache_range_asm, and
flush_kernel_icache_range_asm are unrolled to reduce branch overhead.

2) The static branch prediction for cmpb instructions in pacache.S have
been reviewed and the operand order adjusted where necessary.

3) For flush routines in cache.c, we purge rather flush when we have no
context.  The pdc instruction at level 0 is not required to write back
dirty lines to memory. This provides a performance improvement over the
fdc instruction if the feature is implemented.

Version 2 adds alternative patching.

The patch provides an average improvement of about 2%.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>

2 files changed, 229 insertions, 20 deletions

diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 56dc9791ee23..804880efa11e 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -36,6 +36,7 @@ EXPORT_SYMBOL(dcache_stride);
 
 void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
 EXPORT_SYMBOL(flush_dcache_page_asm);
+void purge_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
 void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr);
 
 
@@ -303,6 +304,17 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 	preempt_enable();
 }
 
+static inline void
+__purge_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
+		   unsigned long physaddr)
+{
+	preempt_disable();
+	purge_dcache_page_asm(physaddr, vmaddr);
+	if (vma->vm_flags & VM_EXEC)
+		flush_icache_page_asm(physaddr, vmaddr);
+	preempt_enable();
+}
+
 void flush_dcache_page(struct page *page)
 {
 	struct address_space *mapping = page_mapping_file(page);
@@ -563,9 +575,12 @@ void flush_cache_mm(struct mm_struct *mm)
 			pfn = pte_pfn(*ptep);
 			if (!pfn_valid(pfn))
 				continue;
-			if (unlikely(mm->context))
+			if (unlikely(mm->context)) {
 				flush_tlb_page(vma, addr);
-			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+				__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+			} else {
+				__purge_cache_page(vma, addr, PFN_PHYS(pfn));
+			}
 		}
 	}
 }
@@ -600,9 +615,12 @@ void flush_cache_range(struct vm_area_struct *vma,
 			continue;
 		pfn = pte_pfn(*ptep);
 		if (pfn_valid(pfn)) {
-			if (unlikely(vma->vm_mm->context))
+			if (unlikely(vma->vm_mm->context)) {
 				flush_tlb_page(vma, addr);
-			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+				__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+			} else {
+				__purge_cache_page(vma, addr, PFN_PHYS(pfn));
+			}
 		}
 	}
 }
@@ -611,9 +629,12 @@ void
 flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn)
 {
 	if (pfn_valid(pfn)) {
-		if (likely(vma->vm_mm->context))
+		if (likely(vma->vm_mm->context)) {
 			flush_tlb_page(vma, vmaddr);
-		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
+			__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
+		} else {
+			__purge_cache_page(vma, vmaddr, PFN_PHYS(pfn));
+		}
 	}
 }
 
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index b41c0136a05f..187f032c9dd8 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -838,8 +838,7 @@ ENTRY_CFI(flush_dcache_page_asm)
 	add		%r28, %r25, %r25
 	sub		%r25, r31, %r25
 
-
-1:      fdc,m		r31(%r28)
+1:	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
@@ -854,7 +853,7 @@ ENTRY_CFI(flush_dcache_page_asm)
 	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
-	cmpb,COND(<<)	%r28, %r25,1b
+	cmpb,COND(>>)	%r25, %r28, 1b /* predict taken */
 	fdc,m		r31(%r28)
 
 89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
@@ -863,6 +862,67 @@ ENTRY_CFI(flush_dcache_page_asm)
 	nop
 ENDPROC_CFI(flush_dcache_page_asm)
 
+ENTRY_CFI(purge_dcache_page_asm)
+	ldil		L%(TMPALIAS_MAP_START), %r28
+#ifdef CONFIG_64BIT
+#if (TMPALIAS_MAP_START >= 0x80000000)
+	depdi		0, 31,32, %r28		/* clear any sign extension */
+#endif
+	convert_phys_for_tlb_insert20 %r26	/* convert phys addr to tlb insert format */
+	depd		%r25, 63,22, %r28	/* Form aliased virtual address 'to' */
+	depdi		0, 63,PAGE_SHIFT, %r28	/* Clear any offset bits */
+#else
+	extrw,u		%r26, 24,25, %r26	/* convert phys addr to tlb insert format */
+	depw		%r25, 31,22, %r28	/* Form aliased virtual address 'to' */
+	depwi		0, 31,PAGE_SHIFT, %r28	/* Clear any offset bits */
+#endif
+
+	/* Purge any old translation */
+
+#ifdef CONFIG_PA20
+	pdtlb,l		%r0(%r28)
+#else
+	tlb_lock	%r20,%r21,%r22
+0:	pdtlb		%r0(%r28)
+	tlb_unlock	%r20,%r21,%r22
+	ALTERNATIVE(0b, 0b+4, ALT_COND_NO_SMP, INSN_PxTLB)
+#endif
+
+88:	ldil		L%dcache_stride, %r1
+	ldw		R%dcache_stride(%r1), r31
+
+#ifdef CONFIG_64BIT
+	depdi,z		1, 63-PAGE_SHIFT,1, %r25
+#else
+	depwi,z		1, 31-PAGE_SHIFT,1, %r25
+#endif
+	add		%r28, %r25, %r25
+	sub		%r25, r31, %r25
+
+1:      pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	cmpb,COND(>>)	%r25, %r28, 1b /* predict taken */
+	pdc,m		r31(%r28)
+
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
+	sync
+	bv		%r0(%r2)
+	nop
+ENDPROC_CFI(purge_dcache_page_asm)
+
 ENTRY_CFI(flush_icache_page_asm)
 	ldil		L%(TMPALIAS_MAP_START), %r28
 #ifdef CONFIG_64BIT
@@ -908,7 +968,6 @@ ENTRY_CFI(flush_icache_page_asm)
 	add		%r28, %r25, %r25
 	sub		%r25, %r31, %r25
 
-
 	/* fic only has the type 26 form on PA1.1, requiring an
 	 * explicit space specification, so use %sr4 */
 1:      fic,m		%r31(%sr4,%r28)
@@ -926,7 +985,7 @@ ENTRY_CFI(flush_icache_page_asm)
 	fic,m		%r31(%sr4,%r28)
 	fic,m		%r31(%sr4,%r28)
 	fic,m		%r31(%sr4,%r28)
-	cmpb,COND(<<)	%r28, %r25,1b
+	cmpb,COND(>>)	%r25, %r28, 1b /* predict taken */
 	fic,m		%r31(%sr4,%r28)
 
 89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_ICACHE, INSN_NOP)
@@ -947,7 +1006,6 @@ ENTRY_CFI(flush_kernel_dcache_page_asm)
 	add		%r26, %r25, %r25
 	sub		%r25, %r23, %r25
 
-
 1:      fdc,m		%r23(%r26)
 	fdc,m		%r23(%r26)
 	fdc,m		%r23(%r26)
@@ -963,7 +1021,7 @@ ENTRY_CFI(flush_kernel_dcache_page_asm)
 	fdc,m		%r23(%r26)
 	fdc,m		%r23(%r26)
 	fdc,m		%r23(%r26)
-	cmpb,COND(<<)		%r26, %r25,1b
+	cmpb,COND(>>)	%r25, %r26, 1b /* predict taken */
 	fdc,m		%r23(%r26)
 
 89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
@@ -999,7 +1057,7 @@ ENTRY_CFI(purge_kernel_dcache_page_asm)
 	pdc,m		%r23(%r26)
 	pdc,m		%r23(%r26)
 	pdc,m		%r23(%r26)
-	cmpb,COND(<<)		%r26, %r25, 1b
+	cmpb,COND(>>)	%r25, %r26, 1b /* predict taken */
 	pdc,m		%r23(%r26)
 
 89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
@@ -1014,7 +1072,33 @@ ENTRY_CFI(flush_user_dcache_range_asm)
 	ldo		-1(%r23), %r21
 	ANDCM		%r26, %r21, %r26
 
-1:      cmpb,COND(<<),n	%r26, %r25, 1b
+#ifdef CONFIG_64BIT
+	depd,z		%r23, 59, 60, %r21
+#else
+	depw,z		%r23, 27, 28, %r21
+#endif
+	add		%r26, %r21, %r22
+	cmpb,COND(>>),n	%r22, %r25, 2f /* predict not taken */
+1:	add		%r22, %r21, %r22
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	cmpb,COND(<<=)	%r22, %r25, 1b /* predict taken */
+	fdc,m		%r23(%sr3, %r26)
+
+2:	cmpb,COND(>>),n	%r25, %r26, 2b
 	fdc,m		%r23(%sr3, %r26)
 
 89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
@@ -1029,7 +1113,33 @@ ENTRY_CFI(flush_kernel_dcache_range_asm)
 	ldo		-1(%r23), %r21
 	ANDCM		%r26, %r21, %r26
 
-1:      cmpb,COND(<<),n	%r26, %r25,1b
+#ifdef CONFIG_64BIT
+	depd,z		%r23, 59, 60, %r21
+#else
+	depw,z		%r23, 27, 28, %r21
+#endif
+	add		%r26, %r21, %r22
+	cmpb,COND(>>),n	%r22, %r25, 2f /* predict not taken */
+1:	add		%r22, %r21, %r22
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	cmpb,COND(<<=)	%r22, %r25, 1b /* predict taken */
+	fdc,m		%r23(%r26)
+
+2:	cmpb,COND(>>),n	%r25, %r26, 2b /* predict taken */
 	fdc,m		%r23(%r26)
 
 	sync
@@ -1045,7 +1155,33 @@ ENTRY_CFI(purge_kernel_dcache_range_asm)
 	ldo		-1(%r23), %r21
 	ANDCM		%r26, %r21, %r26
 
-1:      cmpb,COND(<<),n	%r26, %r25,1b
+#ifdef CONFIG_64BIT
+	depd,z		%r23, 59, 60, %r21
+#else
+	depw,z		%r23, 27, 28, %r21
+#endif
+	add		%r26, %r21, %r22
+	cmpb,COND(>>),n	%r22, %r25, 2f /* predict not taken */
+1:	add		%r22, %r21, %r22
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	cmpb,COND(<<=)	%r22, %r25, 1b /* predict taken */
+	pdc,m		%r23(%r26)
+
+2:	cmpb,COND(>>),n	%r25, %r26, 2b /* predict taken */
 	pdc,m		%r23(%r26)
 
 	sync
@@ -1061,7 +1197,33 @@ ENTRY_CFI(flush_user_icache_range_asm)
 	ldo		-1(%r23), %r21
 	ANDCM		%r26, %r21, %r26
 
-1:      cmpb,COND(<<),n	%r26, %r25,1b
+#ifdef CONFIG_64BIT
+	depd,z		%r23, 59, 60, %r21
+#else
+	depw,z		%r23, 27, 28, %r21
+#endif
+	add		%r26, %r21, %r22
+	cmpb,COND(>>),n	%r22, %r25, 2f /* predict not taken */
+1:	add		%r22, %r21, %r22
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	cmpb,COND(<<=)	%r22, %r25, 1b /* predict taken */
+	fic,m		%r23(%sr3, %r26)
+
+2:	cmpb,COND(>>),n	%r25, %r26, 2b
 	fic,m		%r23(%sr3, %r26)
 
 89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_ICACHE, INSN_NOP)
@@ -1098,7 +1260,7 @@ ENTRY_CFI(flush_kernel_icache_page)
 	fic,m		%r23(%sr4, %r26)
 	fic,m		%r23(%sr4, %r26)
 	fic,m		%r23(%sr4, %r26)
-	cmpb,COND(<<)		%r26, %r25, 1b
+	cmpb,COND(>>)	%r25, %r26, 1b /* predict taken */
 	fic,m		%r23(%sr4, %r26)
 
 89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_ICACHE, INSN_NOP)
@@ -1113,7 +1275,33 @@ ENTRY_CFI(flush_kernel_icache_range_asm)
 	ldo		-1(%r23), %r21
 	ANDCM		%r26, %r21, %r26
 
-1:      cmpb,COND(<<),n	%r26, %r25, 1b
+#ifdef CONFIG_64BIT
+	depd,z		%r23, 59, 60, %r21
+#else
+	depw,z		%r23, 27, 28, %r21
+#endif
+	add		%r26, %r21, %r22
+	cmpb,COND(>>),n	%r22, %r25, 2f /* predict not taken */
+1:	add		%r22, %r21, %r22
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	cmpb,COND(<<=)	%r22, %r25, 1b /* predict taken */
+	fic,m		%r23(%sr4, %r26)
+
+2:	cmpb,COND(>>),n	%r25, %r26, 2b /* predict taken */
 	fic,m		%r23(%sr4, %r26)
 
 89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_ICACHE, INSN_NOP)