arch/tlb: Clean up simple architectures

For the architectures that do not implement their own tlb_flush() but
do already use the generic mmu_gather, there are two options:

 1) the platform has an efficient flush_tlb_range() and
    asm-generic/tlb.h doesn't need any overrides at all.

 2) the platform lacks an efficient flush_tlb_range() and
    we select MMU_GATHER_NO_RANGE to minimize full invalidates.

Convert all 'simple' architectures to one of these two forms.

alpha:	    has no range invalidate -> 2
arc:	    already used flush_tlb_range() -> 1
c6x:	    has no range invalidate -> 2
hexagon:    has an efficient flush_tlb_range() -> 1
            (flush_tlb_mm() is in fact a full range invalidate,
	     so no need to shoot down everything)
m68k:	    has inefficient flush_tlb_range() -> 2
microblaze: has no flush_tlb_range() -> 2
mips:	    has efficient flush_tlb_range() -> 1
	    (even though it currently seems to use flush_tlb_mm())
nds32:	    already uses flush_tlb_range() -> 1
nios2:	    has inefficient flush_tlb_range() -> 2
	    (no limit on range iteration)
openrisc:   has inefficient flush_tlb_range() -> 2
	    (no limit on range iteration)
parisc:	    already uses flush_tlb_range() -> 1
sparc32:    already uses flush_tlb_range() -> 1
unicore32:  has inefficient flush_tlb_range() -> 2
	    (no limit on range iteration)
xtensa:	    has efficient flush_tlb_range() -> 1

Note this also fixes a bug in the existing code for a number
platforms. Those platforms that did:

  tlb_end_vma() -> if (!full_mm) flush_tlb_*()
  tlb_flush -> if (full_mm) flush_tlb_mm()

missed the case of shift_arg_pages(), which doesn't have @fullmm set,
nor calls into tlb_*vma(), but still frees page-tables and thus needs
an invalidate. The new code handles this by detecting a non-empty
range, and either issuing the matching range invalidate or a full
invalidate, depending on the capabilities.

No change in behavior intended.

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Aneesh Kumar K.V <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: David S. Miller <[email protected]>
Cc: Greentime Hu <[email protected]>
Cc: Guan Xuetao <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Helge Deller <[email protected]>
Cc: Jonas Bonn <[email protected]>
Cc: Ley Foon Tan <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Mark Salter <[email protected]>
Cc: Max Filippov <[email protected]>
Cc: Michal Simek <[email protected]>
Cc: Nick Piggin <[email protected]>
Cc: Paul Burton <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Richard Henderson <[email protected]>
Cc: Richard Kuo <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Vineet Gupta <[email protected]>
Cc: Will Deacon <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>

Author: Peter Zijlstra

arch/alpha/Kconfig

@@ -36,6 +36,7 @@ config ALPHA
 	select ODD_RT_SIGACTION
 	select OLD_SIGSUSPEND
 	select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67
+	select MMU_GATHER_NO_RANGE
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,

arch/alpha/include/asm/tlb.h

@@ -2,12 +2,6 @@
 #ifndef _ALPHA_TLB_H
 #define _ALPHA_TLB_H
 
-#define tlb_start_vma(tlb, vma)			do { } while (0)
-#define tlb_end_vma(tlb, vma)			do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, pte, addr)	do { } while (0)
-
-#define tlb_flush(tlb)				flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #define __pte_free_tlb(tlb, pte, address)		pte_free((tlb)->mm, pte)

arch/arc/include/asm/tlb.h

@@ -9,29 +9,6 @@
 #ifndef _ASM_ARC_TLB_H
 #define _ASM_ARC_TLB_H
 
-#define tlb_flush(tlb)				\
-do {						\
-	if (tlb->fullmm)			\
-		flush_tlb_mm((tlb)->mm);	\
-} while (0)
-
-/*
- * This pair is called at time of munmap/exit to flush cache and TLB entries
- * for mappings being torn down.
- * 1) cache-flush part -implemented via tlb_start_vma( ) for VIPT aliasing D$
- * 2) tlb-flush part - implemted via tlb_end_vma( ) flushes the TLB range
- *
- * Note, read http://lkml.org/lkml/2004/1/15/6
- */
-
-#define tlb_end_vma(tlb, vma)						\
-do {									\
-	if (!tlb->fullmm)						\
-		flush_tlb_range(vma, vma->vm_start, vma->vm_end);	\
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, ptep, address)
-
 #include <linux/pagemap.h>
 #include <asm-generic/tlb.h>
 

arch/c6x/Kconfig

@@ -20,6 +20,7 @@ config C6X
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
 	select ARCH_NO_COHERENT_DMA_MMAP
+	select MMU_GATHER_NO_RANGE if MMU
 
 config MMU
 	def_bool n

arch/c6x/include/asm/tlb.h

@@ -2,8 +2,6 @@
 #ifndef _ASM_C6X_TLB_H
 #define _ASM_C6X_TLB_H
 
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #endif /* _ASM_C6X_TLB_H */

arch/h8300/include/asm/tlb.h

@@ -2,8 +2,6 @@
 #ifndef __H8300_TLB_H__
 #define __H8300_TLB_H__
 
-#define tlb_flush(tlb)	do { } while (0)
-
 #include <asm-generic/tlb.h>
 
 #endif

arch/hexagon/include/asm/tlb.h

@@ -22,18 +22,6 @@
 #include <linux/pagemap.h>
 #include <asm/tlbflush.h>
 
-/*
- * We don't need any special per-pte or per-vma handling...
- */
-#define tlb_start_vma(tlb, vma)				do { } while (0)
-#define tlb_end_vma(tlb, vma)				do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address)	do { } while (0)
-
-/*
- * .. because we flush the whole mm when it fills up
- */
-#define tlb_flush(tlb)		flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #endif

arch/m68k/Kconfig

@@ -28,6 +28,7 @@ config M68K
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
 	select ARCH_DISCARD_MEMBLOCK
+	select MMU_GATHER_NO_RANGE if MMU
 
 config CPU_BIG_ENDIAN
 	def_bool y

arch/m68k/include/asm/tlb.h

@@ -2,20 +2,6 @@
 #ifndef _M68K_TLB_H
 #define _M68K_TLB_H
 
-/*
- * m68k doesn't need any special per-pte or
- * per-vma handling..
- */
-#define tlb_start_vma(tlb, vma)	do { } while (0)
-#define tlb_end_vma(tlb, vma)	do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address)	do { } while (0)
-
-/*
- * .. because we flush the whole mm when it
- * fills up.
- */
-#define tlb_flush(tlb)		flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #endif /* _M68K_TLB_H */

arch/microblaze/Kconfig

@@ -41,6 +41,7 @@ config MICROBLAZE
 	select TRACING_SUPPORT
 	select VIRT_TO_BUS
 	select CPU_NO_EFFICIENT_FFS
+	select MMU_GATHER_NO_RANGE if MMU
 
 # Endianness selection
 choice