[IA64] 4-level page tables

This patch introduces 4-level page tables to ia64.  I have run
some benchmarks and found nothing interesting.  Performance has
consistently fallen within the noise range.

It also introduces a config option (setting the default to 3
levels).  The config option prevents having 4 level page
tables with 64k base page size.

Signed-off-by: Robin Holt <holt@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index d4de8a4..8796e12 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -164,6 +164,19 @@
 
 endchoice
 
+choice
+	prompt "Page Table Levels"
+	default PGTABLE_3
+
+config PGTABLE_3
+	bool "3 Levels"
+
+config PGTABLE_4
+	depends on !IA64_PAGE_SIZE_64KB
+	bool "4 Levels"
+
+endchoice
+
 source kernel/Kconfig.hz
 
 config IA64_BRL_EMU
diff --git a/arch/ia64/configs/sn2_defconfig b/arch/ia64/configs/sn2_defconfig
index 08112ab..87cfd31 100644
--- a/arch/ia64/configs/sn2_defconfig
+++ b/arch/ia64/configs/sn2_defconfig
@@ -80,6 +80,8 @@
 # CONFIG_IA64_PAGE_SIZE_8KB is not set
 CONFIG_IA64_PAGE_SIZE_16KB=y
 # CONFIG_IA64_PAGE_SIZE_64KB is not set
+# CONFIG_PGTABLE_3 is not set
+CONFIG_PGTABLE_4=y
 # CONFIG_HZ_100 is not set
 CONFIG_HZ_250=y
 # CONFIG_HZ_1000 is not set
diff --git a/arch/ia64/defconfig b/arch/ia64/defconfig
index 6e3f147..275a26c 100644
--- a/arch/ia64/defconfig
+++ b/arch/ia64/defconfig
@@ -82,6 +82,8 @@
 # CONFIG_IA64_PAGE_SIZE_8KB is not set
 CONFIG_IA64_PAGE_SIZE_16KB=y
 # CONFIG_IA64_PAGE_SIZE_64KB is not set
+CONFIG_PGTABLE_3=y
+# CONFIG_PGTABLE_4 is not set
 # CONFIG_HZ_100 is not set
 CONFIG_HZ_250=y
 # CONFIG_HZ_1000 is not set
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index c13ca0d..e06f21f 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -114,7 +114,7 @@
 	shl r21=r16,3				// shift bit 60 into sign bit
 	shr.u r17=r16,61			// get the region number into r17
 	;;
-	shr r22=r21,3
+	shr.u r22=r21,3
 #ifdef CONFIG_HUGETLB_PAGE
 	extr.u r26=r25,2,6
 	;;
@@ -140,20 +140,34 @@
 (p6)	dep r17=r18,r19,3,(PAGE_SHIFT-3)	// r17=PTA + IFA(33,42)*8
 (p7)	dep r17=r18,r17,3,(PAGE_SHIFT-6)	// r17=PTA + (((IFA(61,63) << 7) | IFA(33,39))*8)
 	cmp.eq p7,p6=0,r21			// unused address bits all zeroes?
-	shr.u r18=r22,PMD_SHIFT			// shift L2 index into position
+#ifdef CONFIG_PGTABLE_4
+	shr.u r28=r22,PUD_SHIFT			// shift L2 index into position
+#else
+	shr.u r18=r22,PMD_SHIFT			// shift L3 index into position
+#endif
 	;;
 	ld8 r17=[r17]				// fetch the L1 entry (may be 0)
 	;;
 (p7)	cmp.eq p6,p7=r17,r0			// was L1 entry NULL?
-	dep r17=r18,r17,3,(PAGE_SHIFT-3)	// compute address of L2 page table entry
+#ifdef CONFIG_PGTABLE_4
+	dep r28=r28,r17,3,(PAGE_SHIFT-3)	// compute address of L2 page table entry
 	;;
-(p7)	ld8 r20=[r17]				// fetch the L2 entry (may be 0)
-	shr.u r19=r22,PAGE_SHIFT		// shift L3 index into position
+	shr.u r18=r22,PMD_SHIFT			// shift L3 index into position
+(p7)	ld8 r29=[r28]				// fetch the L2 entry (may be 0)
 	;;
-(p7)	cmp.eq.or.andcm p6,p7=r20,r0		// was L2 entry NULL?
-	dep r21=r19,r20,3,(PAGE_SHIFT-3)	// compute address of L3 page table entry
+(p7)	cmp.eq.or.andcm p6,p7=r29,r0		// was L2 entry NULL?
+	dep r17=r18,r29,3,(PAGE_SHIFT-3)	// compute address of L3 page table entry
+#else
+	dep r17=r18,r17,3,(PAGE_SHIFT-3)	// compute address of L3 page table entry
+#endif
 	;;
-(p7)	ld8 r18=[r21]				// read the L3 PTE
+(p7)	ld8 r20=[r17]				// fetch the L3 entry (may be 0)
+	shr.u r19=r22,PAGE_SHIFT		// shift L4 index into position
+	;;
+(p7)	cmp.eq.or.andcm p6,p7=r20,r0		// was L3 entry NULL?
+	dep r21=r19,r20,3,(PAGE_SHIFT-3)	// compute address of L4 page table entry
+	;;
+(p7)	ld8 r18=[r21]				// read the L4 PTE
 	mov r19=cr.isr				// cr.isr bit 0 tells us if this is an insn miss
 	;;
 (p7)	tbit.z p6,p7=r18,_PAGE_P_BIT		// page present bit cleared?
@@ -192,14 +206,21 @@
 	 * between reading the pagetable and the "itc".  If so, flush the entry we
 	 * inserted and retry.
 	 */
-	ld8 r25=[r21]				// read L3 PTE again
-	ld8 r26=[r17]				// read L2 entry again
+	ld8 r25=[r21]				// read L4 entry again
+	ld8 r26=[r17]				// read L3 PTE again
+#ifdef CONFIG_PGTABLE_4
+	ld8 r18=[r28]				// read L2 entry again
+#endif
+	cmp.ne p6,p7=r0,r0
 	;;
-	cmp.ne p6,p7=r26,r20			// did L2 entry change
+	cmp.ne.or.andcm p6,p7=r26,r20		// did L3 entry change
+#ifdef CONFIG_PGTABLE_4
+	cmp.ne.or.andcm p6,p7=r29,r18		// did L4 PTE change
+#endif
 	mov r27=PAGE_SHIFT<<2
 	;;
 (p6)	ptc.l r22,r27				// purge PTE page translation
-(p7)	cmp.ne.or.andcm p6,p7=r25,r18		// did L3 PTE change
+(p7)	cmp.ne.or.andcm p6,p7=r25,r18		// did L4 PTE change
 	;;
 (p6)	ptc.l r16,r27				// purge translation
 #endif
@@ -432,18 +453,30 @@
 (p6)	dep r17=r18,r19,3,(PAGE_SHIFT-3)	// r17=PTA + IFA(33,42)*8
 (p7)	dep r17=r18,r17,3,(PAGE_SHIFT-6)	// r17=PTA + (((IFA(61,63) << 7) | IFA(33,39))*8)
 	cmp.eq p7,p6=0,r21			// unused address bits all zeroes?
-	shr.u r18=r22,PMD_SHIFT			// shift L2 index into position
+#ifdef CONFIG_PGTABLE_4
+	shr.u r18=r22,PUD_SHIFT			// shift L2 index into position
+#else
+	shr.u r18=r22,PMD_SHIFT			// shift L3 index into position
+#endif
 	;;
 	ld8 r17=[r17]				// fetch the L1 entry (may be 0)
 	;;
 (p7)	cmp.eq p6,p7=r17,r0			// was L1 entry NULL?
 	dep r17=r18,r17,3,(PAGE_SHIFT-3)	// compute address of L2 page table entry
 	;;
+#ifdef CONFIG_PGTABLE_4
 (p7)	ld8 r17=[r17]				// fetch the L2 entry (may be 0)
-	shr.u r19=r22,PAGE_SHIFT		// shift L3 index into position
+	shr.u r18=r22,PMD_SHIFT			// shift L3 index into position
 	;;
 (p7)	cmp.eq.or.andcm p6,p7=r17,r0		// was L2 entry NULL?
-	dep r17=r19,r17,3,(PAGE_SHIFT-3)	// compute address of L3 page table entry
+	dep r17=r18,r17,3,(PAGE_SHIFT-3)	// compute address of L2 page table entry
+	;;
+#endif
+(p7)	ld8 r17=[r17]				// fetch the L3 entry (may be 0)
+	shr.u r19=r22,PAGE_SHIFT		// shift L4 index into position
+	;;
+(p7)	cmp.eq.or.andcm p6,p7=r17,r0		// was L3 entry NULL?
+	dep r17=r19,r17,3,(PAGE_SHIFT-3)	// compute address of L4 page table entry
 (p6)	br.cond.spnt page_fault
 	mov b0=r30
 	br.sptk.many b0				// return to continuation point