powerpc: Introduce local (non-broadcast) forms of tlb invalidates

Introduced a new set of low level tlb invalidate functions that do not
broadcast invalidates on the bus:

_tlbil_all - invalidate all
_tlbil_pid - invalidate based on process id (or mm context)
_tlbil_va  - invalidate based on virtual address (ea + pid)

On non-SMP configs _tlbil_all should be functionally equivalent to _tlbia and
_tlbil_va should be functionally equivalent to _tlbie.

The intent of this change is to handle SMP based invalidates via IPIs instead
of broadcasts as the mechanism scales better for larger number of cores.

On e500 (fsl-booke mmu) based cores move to using MMUCSR for invalidate alls
and tlbsx/tlbwe for invalidate virtual address.
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>

arch/powerpc/include/asm/reg_booke.h

@@ -109,6 +109,7 @@
 #define SPRN_EVPR	0x3D6	/* Exception Vector Prefix Register */
 #define SPRN_L1CSR0	0x3F2	/* L1 Cache Control and Status Register 0 */
 #define SPRN_L1CSR1	0x3F3	/* L1 Cache Control and Status Register 1 */
+#define SPRN_MMUCSR0	0x3F4	/* MMU Control and Status Register 0 */
 #define SPRN_PIT	0x3DB	/* Programmable Interval Timer */
 #define SPRN_BUCSR	0x3F5	/* Branch Unit Control and Status */
 #define SPRN_L2CSR0	0x3F9	/* L2 Data Cache Control and Status Register 0 */
@@ -410,6 +411,12 @@
 #define L2CSR0_L2LOA	0x00000080	/* L2 Cache Lock Overflow Allocate */
 #define L2CSR0_L2LO	0x00000020	/* L2 Cache Lock Overflow */
 
+/* Bit definitions for MMUCSR0 */
+#define MMUCSR0_TLB1FI	0x00000002	/* TLB1 Flash invalidate */
+#define MMUCSR0_TLB0FI	0x00000004	/* TLB0 Flash invalidate */
+#define MMUCSR0_TLB2FI	0x00000040	/* TLB2 Flash invalidate */
+#define MMUCSR0_TLB3FI	0x00000020	/* TLB3 Flash invalidate */
+
 /* Bit definitions for SGR. */
 #define SGR_NORMAL	0		/* Speculative fetching allowed. */
 #define SGR_GUARDED	1		/* Speculative fetching disallowed. */

arch/powerpc/include/asm/tlbflush.h

@@ -29,6 +29,9 @@
 #include <linux/mm.h>
 
 extern void _tlbie(unsigned long address, unsigned int pid);
+extern void _tlbil_all(void);
+extern void _tlbil_pid(unsigned int pid);
+extern void _tlbil_va(unsigned long address, unsigned int pid);
 
 #if defined(CONFIG_40x) || defined(CONFIG_8xx)
 #define _tlbia()	asm volatile ("tlbia; sync" : : : "memory")
@@ -38,31 +41,31 @@ extern void _tlbia(void);
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
 {
-	_tlbia();
+	_tlbil_pid(mm->context.id);
 }
 
 static inline void flush_tlb_page(struct vm_area_struct *vma,
 				  unsigned long vmaddr)
 {
-	_tlbie(vmaddr, vma ? vma->vm_mm->context.id : 0);
+	_tlbil_va(vmaddr, vma ? vma->vm_mm->context.id : 0);
 }
 
 static inline void flush_tlb_page_nohash(struct vm_area_struct *vma,
 					 unsigned long vmaddr)
 {
-	_tlbie(vmaddr, vma ? vma->vm_mm->context.id : 0);
+	flush_tlb_page(vma, vmaddr);
 }
 
 static inline void flush_tlb_range(struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end)
 {
-	_tlbia();
+	_tlbil_pid(vma->vm_mm->context.id);
 }
 
 static inline void flush_tlb_kernel_range(unsigned long start,
 					  unsigned long end)
 {
-	_tlbia();
+	_tlbil_pid(0);
 }
 
 #elif defined(CONFIG_PPC32)

arch/powerpc/kernel/misc_32.S

@@ -274,6 +274,10 @@ _GLOBAL(real_writeb)
 /*
  * Flush MMU TLB
  */
+#ifndef CONFIG_FSL_BOOKE
+_GLOBAL(_tlbil_all)
+_GLOBAL(_tlbil_pid)
+#endif
 _GLOBAL(_tlbia)
 #if defined(CONFIG_40x)
 	sync			/* Flush to memory before changing mapping */
@@ -344,6 +348,9 @@ _GLOBAL(_tlbia)
 /*
  * Flush MMU TLB for a particular address
  */
+#ifndef CONFIG_FSL_BOOKE
+_GLOBAL(_tlbil_va)
+#endif
 _GLOBAL(_tlbie)
 #if defined(CONFIG_40x)
 	/* We run the search with interrupts disabled because we have to change
@@ -436,6 +443,53 @@ _GLOBAL(_tlbie)
 #endif /* ! CONFIG_40x */
 	blr
 
+#if defined(CONFIG_FSL_BOOKE)
+/*
+ * Flush MMU TLB, but only on the local processor (no broadcast)
+ */
+_GLOBAL(_tlbil_all)
+#define MMUCSR0_TLBFI	(MMUCSR0_TLB0FI | MMUCSR0_TLB1FI | \
+			 MMUCSR0_TLB2FI | MMUCSR0_TLB3FI)
+	li	r3,(MMUCSR0_TLBFI)@l
+	mtspr	SPRN_MMUCSR0, r3
+1:
+	mfspr	r3,SPRN_MMUCSR0
+	andi.	r3,r3,MMUCSR0_TLBFI@l
+	bne	1b
+	blr
+
+/*
+ * Flush MMU TLB for a particular process id, but only on the local processor
+ * (no broadcast)
+ */
+_GLOBAL(_tlbil_pid)
+/* we currently do an invalidate all since we don't have per pid invalidate */
+	li	r3,(MMUCSR0_TLBFI)@l
+	mtspr	SPRN_MMUCSR0, r3
+1:
+	mfspr	r3,SPRN_MMUCSR0
+	andi.	r3,r3,MMUCSR0_TLBFI@l
+	bne	1b
+	blr
+
+/*
+ * Flush MMU TLB for a particular address, but only on the local processor
+ * (no broadcast)
+ */
+_GLOBAL(_tlbil_va)
+	slwi	r4,r4,16
+	mtspr	SPRN_MAS6,r4		/* assume AS=0 for now */
+	tlbsx	0,r3
+	mfspr	r4,SPRN_MAS1		/* check valid */
+	andis.	r3,r4,MAS1_VALID@h
+	beqlr
+	rlwinm	r4,r4,0,1,31
+	mtspr	SPRN_MAS1,r4
+	tlbwe
+	blr
+#endif /* CONFIG_FSL_BOOKE */
+
+
 /*
  * Flush instruction cache.
  * This is a no-op on the 601.

arch/powerpc/kernel/ppc_ksyms.c

@@ -119,6 +119,9 @@ EXPORT_SYMBOL(flush_instruction_cache);
 EXPORT_SYMBOL(flush_tlb_kernel_range);
 EXPORT_SYMBOL(flush_tlb_page);
 EXPORT_SYMBOL(_tlbie);
+#if defined(CONFIG_4xx) || defined(CONFIG_8xx) || defined(CONFIG_FSL_BOOKE)
+EXPORT_SYMBOL(_tlbil_va);
+#endif
 #endif
 EXPORT_SYMBOL(__flush_icache_range);
 EXPORT_SYMBOL(flush_dcache_range);