Merge branch 'core-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull unified TLB flushing from Ingo Molnar:
 "This contains the generic mmu_gather feature from Peter Zijlstra,
  which is an all-arch unification of TLB flushing APIs, via the
  following (broad) steps:

   - enhance the <asm-generic/tlb.h> APIs to cover more arch details

   - convert most TLB flushing arch implementations to the generic
     <asm-generic/tlb.h> APIs.

   - remove leftovers of per arch implementations

  After this series every single architecture makes use of the unified
  TLB flushing APIs"

* 'core-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  mm/resource: Use resource_overlaps() to simplify region_intersects()
  ia64/tlb: Eradicate tlb_migrate_finish() callback
  asm-generic/tlb: Remove tlb_table_flush()
  asm-generic/tlb: Remove tlb_flush_mmu_free()
  asm-generic/tlb: Remove CONFIG_HAVE_GENERIC_MMU_GATHER
  asm-generic/tlb: Remove arch_tlb*_mmu()
  s390/tlb: Convert to generic mmu_gather
  asm-generic/tlb: Introduce CONFIG_HAVE_MMU_GATHER_NO_GATHER=y
  arch/tlb: Clean up simple architectures
  um/tlb: Convert to generic mmu_gather
  sh/tlb: Convert SH to generic mmu_gather
  ia64/tlb: Convert to generic mmu_gather
  arm/tlb: Convert to generic mmu_gather
  asm-generic/tlb, arch: Invert CONFIG_HAVE_RCU_TABLE_INVALIDATE
  asm-generic/tlb, ia64: Conditionally provide tlb_migrate_finish()
  asm-generic/tlb: Provide generic tlb_flush() based on flush_tlb_mm()
  asm-generic/tlb, arch: Provide generic tlb_flush() based on flush_tlb_range()
  asm-generic/tlb, arch: Provide generic VIPT cache flush
  asm-generic/tlb, arch: Provide CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
  asm-generic/tlb: Provide a comment

55 files changed, 482 insertions, 1296 deletions

diff --git a/Documentation/core-api/cachetlb.rst b/Documentation/core-api/cachetlb.rst
index 6eb9d3f090cd..93cb65d52720 100644
--- a/Documentation/core-api/cachetlb.rst
+++ b/Documentation/core-api/cachetlb.rst
@@ -101,16 +101,6 @@ changes occur:
 	translations for software managed TLB configurations.
 	The sparc64 port currently does this.
 
-6) ``void tlb_migrate_finish(struct mm_struct *mm)``
-
-	This interface is called at the end of an explicit
-	process migration. This interface provides a hook
-	to allow a platform to update TLB or context-specific
-	information for the address space.
-
-	The ia64 sn2 platform is one example of a platform
-	that uses this interface.
-
 Next, we have the cache flushing interfaces.  In general, when Linux
 is changing an existing virtual-->physical mapping to a new value,
 the sequence will be in one of the following forms::
diff --git a/arch/Kconfig b/arch/Kconfig
index 33687dddd86a..a826843470ed 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -383,7 +383,13 @@ config HAVE_ARCH_JUMP_LABEL_RELATIVE
 config HAVE_RCU_TABLE_FREE
 	bool
 
-config HAVE_RCU_TABLE_INVALIDATE
+config HAVE_RCU_TABLE_NO_INVALIDATE
+	bool
+
+config HAVE_MMU_GATHER_PAGE_SIZE
+	bool
+
+config HAVE_MMU_GATHER_NO_GATHER
 	bool
 
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 584a6e114853..c7c976eb6407 100644
--- a/arch/alpha/Kconfig
+++ b/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,
diff --git a/arch/alpha/include/asm/tlb.h b/arch/alpha/include/asm/tlb.h
index 8f5042b61875..4f79e331af5e 100644
--- a/arch/alpha/include/asm/tlb.h
+++ b/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)
diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h
index a9db5f62aaf3..90cac97643a4 100644
--- a/arch/arc/include/asm/tlb.h
+++ b/arch/arc/include/asm/tlb.h
@@ -9,38 +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
- */
-#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING
-#define tlb_start_vma(tlb, vma)
-#else
-#define tlb_start_vma(tlb, vma)						\
-do {									\
-	if (!tlb->fullmm)						\
-		flush_cache_range(vma, vma->vm_start, vma->vm_end);	\
-} while(0)
-#endif
-
-#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>
 
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index f854148c8d7c..bc6d04a09899 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -33,271 +33,42 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
-#define MMU_GATHER_BUNDLE	8
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 static inline void __tlb_remove_table(void *_table)
 {
 	free_page_and_swap_cache((struct page *)_table);
 }
 
-struct mmu_table_batch {
-	struct rcu_head		rcu;
-	unsigned int		nr;
-	void			*tables[0];
-};
-
-#define MAX_TABLE_BATCH		\
-	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
-
-extern void tlb_table_flush(struct mmu_gather *tlb);
-extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-
-#define tlb_remove_entry(tlb, entry)	tlb_remove_table(tlb, entry)
-#else
-#define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
-
-/*
- * TLB handling.  This allows us to remove pages from the page
- * tables, and efficiently handle the TLB issues.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	struct mmu_table_batch	*batch;
-	unsigned int		need_flush;
-#endif
-	unsigned int		fullmm;
-	struct vm_area_struct	*vma;
-	unsigned long		start, end;
-	unsigned long		range_start;
-	unsigned long		range_end;
-	unsigned int		nr;
-	unsigned int		max;
-	struct page		**pages;
-	struct page		*local[MMU_GATHER_BUNDLE];
-};
-
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-/*
- * This is unnecessarily complex.  There's three ways the TLB shootdown
- * code is used:
- *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
- *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.
- *  2. Unmapping all vmas.  See exit_mmap().
- *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.  Additionally, page tables will be freed.
- *  3. Unmapping argument pages.  See shift_arg_pages().
- *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
- *     tlb->vma will be NULL.
- */
-static inline void tlb_flush(struct mmu_gather *tlb)
-{
-	if (tlb->fullmm || !tlb->vma)
-		flush_tlb_mm(tlb->mm);
-	else if (tlb->range_end > 0) {
-		flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
-		tlb->range_start = TASK_SIZE;
-		tlb->range_end = 0;
-	}
-}
-
-static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
-{
-	if (!tlb->fullmm) {
-		if (addr < tlb->range_start)
-			tlb->range_start = addr;
-		if (addr + PAGE_SIZE > tlb->range_end)
-			tlb->range_end = addr + PAGE_SIZE;
-	}
-}
-
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
-	if (addr) {
-		tlb->pages = (void *)addr;
-		tlb->max = PAGE_SIZE / sizeof(struct page *);
-	}
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	tlb_flush(tlb);
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb_table_flush(tlb);
-#endif
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	free_pages_and_swap_cache(tlb->pages, tlb->nr);
-	tlb->nr = 0;
-	if (tlb->pages == tlb->local)
-		__tlb_alloc_page(tlb);
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->fullmm = !(start | (end+1));
-	tlb->start = start;
-	tlb->end = end;
-	tlb->vma = NULL;
-	tlb->max = ARRAY_SIZE(tlb->local);
-	tlb->pages = tlb->local;
-	tlb->nr = 0;
-	__tlb_alloc_page(tlb);
+#include <asm-generic/tlb.h>
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb->batch = NULL;
+#ifndef CONFIG_HAVE_RCU_TABLE_FREE
+#define tlb_remove_table(tlb, entry) tlb_remove_page(tlb, entry)
 #endif
-}
-
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-			unsigned long start, unsigned long end, bool force)
-{
-	if (force) {
-		tlb->range_start = start;
-		tlb->range_end = end;
-	}
-
-	tlb_flush_mmu(tlb);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	if (tlb->pages != tlb->local)
-		free_pages((unsigned long)tlb->pages, 0);
-}
-
-/*
- * Memorize the range for the TLB flush.
- */
-static inline void
-tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush.  When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void
-tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm) {
-		flush_cache_range(vma, vma->vm_start, vma->vm_end);
-		tlb->vma = vma;
-		tlb->range_start = TASK_SIZE;
-		tlb->range_end = 0;
-	}
-}
 
 static inline void
-tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm)
-		tlb_flush(tlb);
-}
-
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->pages[tlb->nr++] = page;
-	VM_WARN_ON(tlb->nr > tlb->max);
-	if (tlb->nr == tlb->max)
-		return true;
-	return false;
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
-	unsigned long addr)
+__pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr)
 {
 	pgtable_page_dtor(pte);
 
-#ifdef CONFIG_ARM_LPAE
-	tlb_add_flush(tlb, addr);
-#else
+#ifndef CONFIG_ARM_LPAE
 	/*
 	 * With the classic ARM MMU, a pte page has two corresponding pmd
 	 * entries, each covering 1MB.
 	 */
-	addr &= PMD_MASK;
-	tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE);
-	tlb_add_flush(tlb, addr + SZ_1M);
+	addr = (addr & PMD_MASK) + SZ_1M;
+	__tlb_adjust_range(tlb, addr - PAGE_SIZE, 2 * PAGE_SIZE);
 #endif
 
-	tlb_remove_entry(tlb, pte);
-}
-
-static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
-				  unsigned long addr)
-{
-#ifdef CONFIG_ARM_LPAE
-	tlb_add_flush(tlb, addr);
-	tlb_remove_entry(tlb, virt_to_page(pmdp));
-#endif
+	tlb_remove_table(tlb, pte);
 }
 
 static inline void
-tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
-
-#define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
-#define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
-#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
-
-#define tlb_migrate_finish(mm)		do { } while (0)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
+__pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
 {
-}
-
-static inline void tlb_flush_remove_tables(struct mm_struct *mm)
-{
-}
+#ifdef CONFIG_ARM_LPAE
+	struct page *page = virt_to_page(pmdp);
 
-static inline void tlb_flush_remove_tables_local(void *arg)
-{
+	tlb_remove_table(tlb, page);
+#endif
 }
 
 #endif /* CONFIG_MMU */
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7e34b9eba5de..78d9fafac983 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -149,7 +149,6 @@ config ARM64
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RCU_TABLE_FREE
-	select HAVE_RCU_TABLE_INVALIDATE
 	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 106fdc951b6e..37603b5616a5 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -27,6 +27,7 @@ static inline void __tlb_remove_table(void *_table)
 	free_page_and_swap_cache((struct page *)_table);
 }
 
+#define tlb_flush tlb_flush
 static void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index e5cd3c5f8399..3bb75e674161 100644
--- a/arch/c6x/Kconfig
+++ b/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
diff --git a/arch/c6x/include/asm/tlb.h b/arch/c6x/include/asm/tlb.h
index 34525dea1356..240ba0febb57 100644
--- a/arch/c6x/include/asm/tlb.h
+++ b/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 */
diff --git a/arch/h8300/include/asm/tlb.h b/arch/h8300/include/asm/tlb.h
index 98f344279904..d8201ca31206 100644
--- a/arch/h8300/include/asm/tlb.h
+++ b/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
diff --git a/arch/hexagon/include/asm/tlb.h b/arch/hexagon/include/asm/tlb.h
index 2f00772cc08a..f71c4ba83614 100644
--- a/arch/hexagon/include/asm/tlb.h
+++ b/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
diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h
index 5133739966bc..beae261fbcb4 100644
--- a/arch/ia64/include/asm/machvec.h
+++ b/arch/ia64/include/asm/machvec.h
@@ -30,7 +30,6 @@ typedef void ia64_mv_irq_init_t (void);
 typedef void ia64_mv_send_ipi_t (int, int, int, int);
 typedef void ia64_mv_timer_interrupt_t (int, void *);
 typedef void ia64_mv_global_tlb_purge_t (struct mm_struct *, unsigned long, unsigned long, unsigned long);
-typedef void ia64_mv_tlb_migrate_finish_t (struct mm_struct *);
 typedef u8 ia64_mv_irq_to_vector (int);
 typedef unsigned int ia64_mv_local_vector_to_irq (u8);
 typedef char *ia64_mv_pci_get_legacy_mem_t (struct pci_bus *);
@@ -80,11 +79,6 @@ machvec_noop (void)
 }
 
 static inline void
-machvec_noop_mm (struct mm_struct *mm)
-{
-}
-
-static inline void
 machvec_noop_task (struct task_struct *task)
 {
 }
@@ -96,7 +90,6 @@ machvec_noop_bus (struct pci_bus *bus)
 
 extern void machvec_setup (char **);
 extern void machvec_timer_interrupt (int, void *);
-extern void machvec_tlb_migrate_finish (struct mm_struct *);
 
 # if defined (CONFIG_IA64_HP_SIM)
 #  include <asm/machvec_hpsim.h>
@@ -124,7 +117,6 @@ extern void machvec_tlb_migrate_finish (struct mm_struct *);
 #  define platform_send_ipi	ia64_mv.send_ipi
 #  define platform_timer_interrupt	ia64_mv.timer_interrupt
 #  define platform_global_tlb_purge	ia64_mv.global_tlb_purge
-#  define platform_tlb_migrate_finish	ia64_mv.tlb_migrate_finish
 #  define platform_dma_init		ia64_mv.dma_init
 #  define platform_dma_get_ops		ia64_mv.dma_get_ops
 #  define platform_irq_to_vector	ia64_mv.irq_to_vector
@@ -167,7 +159,6 @@ struct ia64_machine_vector {
 	ia64_mv_send_ipi_t *send_ipi;
 	ia64_mv_timer_interrupt_t *timer_interrupt;
 	ia64_mv_global_tlb_purge_t *global_tlb_purge;
-	ia64_mv_tlb_migrate_finish_t *tlb_migrate_finish;
 	ia64_mv_dma_init *dma_init;
 	ia64_mv_dma_get_ops *dma_get_ops;
 	ia64_mv_irq_to_vector *irq_to_vector;
@@ -206,7 +197,6 @@ struct ia64_machine_vector {
 	platform_send_ipi,			\
 	platform_timer_interrupt,		\
 	platform_global_tlb_purge,		\
-	platform_tlb_migrate_finish,		\
 	platform_dma_init,			\
 	platform_dma_get_ops,			\
 	platform_irq_to_vector,			\
@@ -270,9 +260,6 @@ extern const struct dma_map_ops *dma_get_ops(struct device *);
 #ifndef platform_global_tlb_purge
 # define platform_global_tlb_purge	ia64_global_tlb_purge /* default to architected version */
 #endif
-#ifndef platform_tlb_migrate_finish
-# define platform_tlb_migrate_finish	machvec_noop_mm
-#endif
 #ifndef platform_kernel_launch_event
 # define platform_kernel_launch_event	machvec_noop
 #endif
diff --git a/arch/ia64/include/asm/machvec_sn2.h b/arch/ia64/include/asm/machvec_sn2.h
index b5153d300289..a243e4fb4877 100644
--- a/arch/ia64/include/asm/machvec_sn2.h
+++ b/arch/ia64/include/asm/machvec_sn2.h
@@ -34,7 +34,6 @@ extern ia64_mv_irq_init_t sn_irq_init;
 extern ia64_mv_send_ipi_t sn2_send_IPI;
 extern ia64_mv_timer_interrupt_t sn_timer_interrupt;
 extern ia64_mv_global_tlb_purge_t sn2_global_tlb_purge;
-extern ia64_mv_tlb_migrate_finish_t	sn_tlb_migrate_finish;
 extern ia64_mv_irq_to_vector sn_irq_to_vector;
 extern ia64_mv_local_vector_to_irq sn_local_vector_to_irq;
 extern ia64_mv_pci_get_legacy_mem_t sn_pci_get_legacy_mem;
@@ -77,7 +76,6 @@ extern ia64_mv_pci_fixup_bus_t		sn_pci_fixup_bus;
 #define platform_send_ipi		sn2_send_IPI
 #define platform_timer_interrupt	sn_timer_interrupt
 #define platform_global_tlb_purge       sn2_global_tlb_purge
-#define platform_tlb_migrate_finish	sn_tlb_migrate_finish
 #define platform_pci_fixup		sn_pci_fixup
 #define platform_inb			__sn_inb
 #define platform_inw			__sn_inw
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 516355a774bf..86ec034ba499 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -47,263 +47,6 @@
 #include <asm/tlbflush.h>
 #include <asm/machvec.h>
 
-/*
- * If we can't allocate a page to make a big batch of page pointers
- * to work on, then just handle a few from the on-stack structure.
- */
-#define	IA64_GATHER_BUNDLE	8
-
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		nr;
-	unsigned int		max;
-	unsigned char		fullmm;		/* non-zero means full mm flush */
-	unsigned char		need_flush;	/* really unmapped some PTEs? */
-	unsigned long		start, end;
-	unsigned long		start_addr;
-	unsigned long		end_addr;
-	struct page		**pages;
-	struct page		*local[IA64_GATHER_BUNDLE];
-};
-
-struct ia64_tr_entry {
-	u64 ifa;
-	u64 itir;
-	u64 pte;
-	u64 rr;
-}; /*Record for tr entry!*/
-
-extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size);
-extern void ia64_ptr_entry(u64 target_mask, int slot);
-
-extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
-
-/*
- region register macros
-*/
-#define RR_TO_VE(val)   (((val) >> 0) & 0x0000000000000001)
-#define RR_VE(val)	(((val) & 0x0000000000000001) << 0)
-#define RR_VE_MASK	0x0000000000000001L
-#define RR_VE_SHIFT	0
-#define RR_TO_PS(val)	(((val) >> 2) & 0x000000000000003f)
-#define RR_PS(val)	(((val) & 0x000000000000003f) << 2)
-#define RR_PS_MASK	0x00000000000000fcL
-#define RR_PS_SHIFT	2
-#define RR_RID_MASK	0x00000000ffffff00L
-#define RR_TO_RID(val) 	((val >> 8) & 0xffffff)
-
-static inline void
-ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-	tlb->need_flush = 0;
-
-	if (tlb->fullmm) {
-		/*
-		 * Tearing down the entire address space.  This happens both as a result
-		 * of exit() and execve().  The latter case necessitates the call to
-		 * flush_tlb_mm() here.
-		 */
-		flush_tlb_mm(tlb->mm);
-	} else if (unlikely (end - start >= 1024*1024*1024*1024UL
-			     || REGION_NUMBER(start) != REGION_NUMBER(end - 1)))
-	{
-		/*
-		 * If we flush more than a tera-byte or across regions, we're probably
-		 * better off just flushing the entire TLB(s).  This should be very rare
-		 * and is not worth optimizing for.
-		 */
-		flush_tlb_all();
-	} else {
-		/*
-		 * flush_tlb_range() takes a vma instead of a mm pointer because
-		 * some architectures want the vm_flags for ITLB/DTLB flush.
-		 */
-		struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
-
-		/* flush the address range from the tlb: */
-		flush_tlb_range(&vma, start, end);
-		/* now flush the virt. page-table area mapping the address range: */
-		flush_tlb_range(&vma, ia64_thash(start), ia64_thash(end));
-	}
-
-}
-
-static inline void
-ia64_tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	unsigned long i;
-	unsigned int nr;
-
-	/* lastly, release the freed pages */
-	nr = tlb->nr;
-
-	tlb->nr = 0;
-	tlb->start_addr = ~0UL;
-	for (i = 0; i < nr; ++i)
-		free_page_and_swap_cache(tlb->pages[i]);
-}
-
-/*
- * Flush the TLB for address range START to END and, if not in fast mode, release the
- * freed pages that where gathered up to this point.
- */
-static inline void
-ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-	if (!tlb->need_flush)
-		return;
-	ia64_tlb_flush_mmu_tlbonly(tlb, start, end);
-	ia64_tlb_flush_mmu_free(tlb);
-}
-
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
-	if (addr) {
-		tlb->pages = (void *)addr;
-		tlb->max = PAGE_SIZE / sizeof(void *);
-	}
-}
-
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->max = ARRAY_SIZE(tlb->local);
-	tlb->pages = tlb->local;
-	tlb->nr = 0;
-	tlb->fullmm = !(start | (end+1));
-	tlb->start = start;
-	tlb->end = end;
-	tlb->start_addr = ~0UL;
-}
-
-/*
- * Called at the end of the shootdown operation to free up any resources that were
- * collected.
- */
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-			unsigned long start, unsigned long end, bool force)
-{
-	if (force)
-		tlb->need_flush = 1;
-	/*
-	 * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and
-	 * tlb->end_addr.
-	 */
-	ia64_tlb_flush_mmu(tlb, start, end);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	if (tlb->pages != tlb->local)
-		free_pages((unsigned long)tlb->pages, 0);
-}
-
-/*
- * Logically, this routine frees PAGE.  On MP machines, the actual freeing of the page
- * must be delayed until after the TLB has been flushed (see comments at the beginning of
- * this file).
- */
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->need_flush = 1;
-
-	if (!tlb->nr && tlb->pages == tlb->local)
-		__tlb_alloc_page(tlb);
-
-	tlb->pages[tlb->nr++] = page;
-	VM_WARN_ON(tlb->nr > tlb->max);
-	if (tlb->nr == tlb->max)
-		return true;
-	return false;
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	ia64_tlb_flush_mmu_tlbonly(tlb, tlb->start_addr, tlb->end_addr);
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	ia64_tlb_flush_mmu_free(tlb);
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	ia64_tlb_flush_mmu(tlb, tlb->start_addr, tlb->end_addr);
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-/*
- * Remove TLB entry for PTE mapped at virtual address ADDRESS.  This is called for any
- * PTE, not just those pointing to (normal) physical memory.
- */
-static inline void
-__tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
-{
-	if (tlb->start_addr == ~0UL)
-		tlb->start_addr = address;
-	tlb->end_addr = address + PAGE_SIZE;
-}
-
-#define tlb_migrate_finish(mm)	platform_tlb_migrate_finish(mm)
-
-#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, addr)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__tlb_remove_tlb_entry(tlb, ptep, addr);	\
-} while (0)
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pte_free_tlb(tlb, ptep, address);		\
-} while (0)
-
-#define pmd_free_tlb(tlb, ptep, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pmd_free_tlb(tlb, ptep, address);		\
-} while (0)
-
-#define pud_free_tlb(tlb, pudp, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pud_free_tlb(tlb, pudp, address);		\
-} while (0)
+#include <asm-generic/tlb.h>
 
 #endif /* _ASM_IA64_TLB_H */
diff --git a/arch/ia64/include/asm/tlbflush.h b/arch/ia64/include/asm/tlbflush.h
index 25e280810f6c..ceac10c4d6e2 100644
--- a/arch/ia64/include/asm/tlbflush.h
+++ b/arch/ia64/include/asm/tlbflush.h
@@ -14,6 +14,31 @@
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 
+struct ia64_tr_entry {
+	u64 ifa;
+	u64 itir;
+	u64 pte;
+	u64 rr;
+}; /*Record for tr entry!*/
+
+extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size);
+extern void ia64_ptr_entry(u64 target_mask, int slot);
+extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
+
+/*
+ region register macros
+*/
+#define RR_TO_VE(val)   (((val) >> 0) & 0x0000000000000001)
+#define RR_VE(val)     (((val) & 0x0000000000000001) << 0)
+#define RR_VE_MASK     0x0000000000000001L
+#define RR_VE_SHIFT    0
+#define RR_TO_PS(val)  (((val) >> 2) & 0x000000000000003f)
+#define RR_PS(val)     (((val) & 0x000000000000003f) << 2)
+#define RR_PS_MASK     0x00000000000000fcL
+#define RR_PS_SHIFT    2
+#define RR_RID_MASK    0x00000000ffffff00L
+#define RR_TO_RID(val)         ((val >> 8) & 0xffffff)
+
 /*
  * Now for some TLB flushing routines.  This is the kind of stuff that
  * can be very expensive, so try to avoid them whenever possible.
diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c
index 5fc89aabdce1..5158bd28de05 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -305,8 +305,8 @@ local_flush_tlb_all (void)
 	ia64_srlz_i();			/* srlz.i implies srlz.d */
 }
 
-void
-flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
+static void
+__flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
 		 unsigned long end)
 {
 	struct mm_struct *mm = vma->vm_mm;
@@ -343,6 +343,25 @@ flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
 	preempt_enable();
 	ia64_srlz_i();			/* srlz.i implies srlz.d */
 }
+
+void flush_tlb_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end)
+{
+	if (unlikely(end - start >= 1024*1024*1024*1024UL
+			|| REGION_NUMBER(start) != REGION_NUMBER(end - 1))) {
+		/*
+		 * If we flush more than a tera-byte or across regions, we're
+		 * probably better off just flushing the entire TLB(s).  This
+		 * should be very rare and is not worth optimizing for.
+		 */
+		flush_tlb_all();
+	} else {
+		/* flush the address range from the tlb */
+		__flush_tlb_range(vma, start, end);
+		/* flush the virt. page-table area mapping the addr range */
+		__flush_tlb_range(vma, ia64_thash(start), ia64_thash(end));
+	}
+}
 EXPORT_SYMBOL(flush_tlb_range);
 
 void ia64_tlb_init(void)
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index b73b0ebf8214..b510f4f17fd4 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -120,13 +120,6 @@ void sn_migrate(struct task_struct *task)
 		cpu_relax();
 }
 
-void sn_tlb_migrate_finish(struct mm_struct *mm)
-{
-	/* flush_tlb_mm is inefficient if more than 1 users of mm */
-	if (mm == current->mm && mm && atomic_read(&mm->mm_users) == 1)
-		flush_tlb_mm(mm);
-}
-
 static void
 sn2_ipi_flush_all_tlb(struct mm_struct *mm)
 {
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index b54206408f91..4e37efbc9296 100644
--- a/arch/m68k/Kconfig
+++ b/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
diff --git a/arch/m68k/include/asm/tlb.h b/arch/m68k/include/asm/tlb.h
index b4b9efb6f963..3c81f6adfc8b 100644
--- a/arch/m68k/include/asm/tlb.h
+++ b/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 */
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index a51b965b3b82..321e398ab6b5 100644
--- a/arch/microblaze/Kconfig
+++ b/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
diff --git a/arch/microblaze/include/asm/tlb.h b/arch/microblaze/include/asm/tlb.h
index 99b6ded54849..628a78ee0a72 100644
--- a/arch/microblaze/include/asm/tlb.h
+++ b/arch/microblaze/include/asm/tlb.h
@@ -11,16 +11,7 @@
 #ifndef _ASM_MICROBLAZE_TLB_H
 #define _ASM_MICROBLAZE_TLB_H
 
-#define tlb_flush(tlb)	flush_tlb_mm((tlb)->mm)
-
 #include <linux/pagemap.h>
-
-#ifdef CONFIG_MMU
-#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, address) do { } while (0)
-#endif
-
 #include <asm-generic/tlb.h>
 
 #endif /* _ASM_MICROBLAZE_TLB_H */
diff --git a/arch/mips/include/asm/tlb.h b/arch/mips/include/asm/tlb.h
index b6823b9e94da..90f3ad76d9e0 100644
--- a/arch/mips/include/asm/tlb.h
+++ b/arch/mips/include/asm/tlb.h
@@ -5,23 +5,6 @@
 #include <asm/cpu-features.h>
 #include <asm/mipsregs.h>
 
-/*
- * MIPS doesn't need any special per-pte or per-vma handling, except
- * we need to flush cache for area to be unmapped.
- */
-#define tlb_start_vma(tlb, vma)					\
-	do {							\
-		if (!tlb->fullmm)				\
-			flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-	}  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)
-
 #define _UNIQUE_ENTRYHI(base, idx)					\
 		(((base) + ((idx) << (PAGE_SHIFT + 1))) |		\
 		 (cpu_has_tlbinv ? MIPS_ENTRYHI_EHINV : 0))
diff --git a/arch/nds32/include/asm/tlb.h b/arch/nds32/include/asm/tlb.h
index b35ae5eae3ab..d5ae571c8d30 100644
--- a/arch/nds32/include/asm/tlb.h
+++ b/arch/nds32/include/asm/tlb.h
@@ -4,22 +4,6 @@
 #ifndef __ASMNDS32_TLB_H
 #define __ASMNDS32_TLB_H
 
-#define tlb_start_vma(tlb,vma)						\
-	do {								\
-		if (!tlb->fullmm)					\
-			flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-	} while (0)
-
-#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, 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, addr)	pte_free((tlb)->mm, pte)
diff --git a/arch/nds32/include/asm/tlbflush.h b/arch/nds32/include/asm/tlbflush.h
index 9b411f401903..38ee769b18d8 100644
--- a/arch/nds32/include/asm/tlbflush.h
+++ b/arch/nds32/include/asm/tlbflush.h
@@ -42,6 +42,5 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 
 void update_mmu_cache(struct vm_area_struct *vma,
 		      unsigned long address, pte_t * pte);
-void tlb_migrate_finish(struct mm_struct *mm);
 
 #endif
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 4ef15a61b7bc..3633f8144367 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -24,6 +24,7 @@ config NIOS2
 	select USB_ARCH_HAS_HCD if USB_SUPPORT
 	select CPU_NO_EFFICIENT_FFS
 	select ARCH_DISCARD_MEMBLOCK
+	select MMU_GATHER_NO_RANGE if MMU
 
 config GENERIC_CSUM
 	def_bool y
diff --git a/arch/nios2/include/asm/tlb.h b/arch/nios2/include/asm/tlb.h
index d3bc648e08b5..f9f2e27e32dd 100644
--- a/arch/nios2/include/asm/tlb.h
+++ b/arch/nios2/include/asm/tlb.h
@@ -11,22 +11,12 @@
 #ifndef _ASM_NIOS2_TLB_H
 #define _ASM_NIOS2_TLB_H
 
-#define tlb_flush(tlb)	flush_tlb_mm((tlb)->mm)
-
 extern void set_mmu_pid(unsigned long pid);
 
 /*
- * NiosII doesn't need any special per-pte or per-vma handling, except
- * we need to flush cache for the area to be unmapped.
+ * NIOS32 does have flush_tlb_range(), but it lacks a limit and fallback to
+ * full mm invalidation. So use flush_tlb_mm() for everything.
  */
-#define tlb_start_vma(tlb, vma)					\
-	do {							\
-		if (!tlb->fullmm)				\
-			flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-	}  while (0)
-
-#define tlb_end_vma(tlb, vma)	do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address)	do { } while (0)
 
 #include <linux/pagemap.h>
 #include <asm-generic/tlb.h>
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index a5e361fbb75a..c6cf8a49a0ab 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -36,6 +36,7 @@ config OPENRISC
 	select OMPIC if SMP
 	select ARCH_WANT_FRAME_POINTERS
 	select GENERIC_IRQ_MULTI_HANDLER
+	select MMU_GATHER_NO_RANGE if MMU
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/openrisc/include/asm/tlb.h b/arch/openrisc/include/asm/tlb.h
index fa4376a4515d..92d8a4209884 100644
--- a/arch/openrisc/include/asm/tlb.h
+++ b/arch/openrisc/include/asm/tlb.h
@@ -20,14 +20,10 @@
 #define __ASM_OPENRISC_TLB_H__
 
 /*
- * or32 doesn't need any special per-pte or
- * per-vma handling..
+ * OpenRISC doesn't have an efficient flush_tlb_range() so use flush_tlb_mm()
+ * for everything.
  */
-#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)
 
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
 #include <linux/pagemap.h>
 #include <asm-generic/tlb.h>
 
diff --git a/arch/parisc/include/asm/tlb.h b/arch/parisc/include/asm/tlb.h
index 0c881e74d8a6..8c0446b04c9e 100644
--- a/arch/parisc/include/asm/tlb.h
+++ b/arch/parisc/include/asm/tlb.h
@@ -2,24 +2,6 @@
 #ifndef _PARISC_TLB_H
 #define _PARISC_TLB_H
 
-#define tlb_flush(tlb)			\
-do {	if ((tlb)->fullmm)		\
-		flush_tlb_mm((tlb)->mm);\
-} while (0)
-
-#define tlb_start_vma(tlb, vma) \
-do {	if (!(tlb)->fullmm)	\
-		flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#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, pte, address) \
-	do { } while (0)
-
 #include <asm-generic/tlb.h>
 
 #define __pmd_free_tlb(tlb, pmd, addr)	pmd_free((tlb)->mm, pmd)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2d0be82c3061..8e1e2abf17eb 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -218,6 +218,8 @@ config PPC
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if SMP
+	select HAVE_RCU_TABLE_NO_INVALIDATE	if HAVE_RCU_TABLE_FREE
+	select HAVE_MMU_GATHER_PAGE_SIZE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
 	select HAVE_SYSCALL_TRACEPOINTS
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index e24c67d5ba75..34fba1ce27f7 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -27,8 +27,8 @@
 #define tlb_start_vma(tlb, vma)	do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
 #define __tlb_remove_tlb_entry	__tlb_remove_tlb_entry
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
 
+#define tlb_flush tlb_flush
 extern void tlb_flush(struct mmu_gather *tlb);
 
 /* Get the generic bits... */
@@ -46,22 +46,6 @@ static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
 #endif
 }
 
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-	if (!tlb->page_size)
-		tlb->page_size = page_size;
-	else if (tlb->page_size != page_size) {
-		if (!tlb->fullmm)
-			tlb_flush_mmu(tlb);
-		/*
-		 * update the page size after flush for the new
-		 * mmu_gather.
-		 */
-		tlb->page_size = page_size;
-	}
-}
-
 #ifdef CONFIG_SMP
 static inline int mm_is_core_local(struct mm_struct *mm)
 {
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 439dc7072e05..1ad8d093c58b 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -18,6 +18,7 @@ struct mmu_gather;
 
 static void tlb_flush(struct mmu_gather *tlb);
 
+#define tlb_flush tlb_flush
 #include <asm-generic/tlb.h>
 
 static inline void tlb_flush(struct mmu_gather *tlb)
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index b6e3d0653002..cf06e313e103 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -164,11 +164,13 @@ config S390
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_MEMBLOCK_PHYS_MAP
+	select HAVE_MMU_GATHER_NO_GATHER
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NOP_MCOUNT
 	select HAVE_OPROFILE
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
+	select HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index b31c779cf581..aa406c05a350 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -22,98 +22,39 @@
  * Pages used for the page tables is a different story. FIXME: more
  */
 
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <asm/processor.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-
-struct mmu_gather {
-	struct mm_struct *mm;
-	struct mmu_table_batch *batch;
-	unsigned int fullmm;
-	unsigned long start, end;
-};
-
-struct mmu_table_batch {
-	struct rcu_head		rcu;
-	unsigned int		nr;
-	void			*tables[0];
-};
-
-#define MAX_TABLE_BATCH		\
-	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
-
-extern void tlb_table_flush(struct mmu_gather *tlb);
-extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->start = start;
-	tlb->end = end;
-	tlb->fullmm = !(start | (end+1));
-	tlb->batch = NULL;
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	__tlb_flush_mm_lazy(tlb->mm);
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	tlb_table_flush(tlb);
-}
-
+void __tlb_remove_table(void *_table);
+static inline void tlb_flush(struct mmu_gather *tlb);
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size);
 
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
+#define tlb_start_vma(tlb, vma)			do { } while (0)
+#define tlb_end_vma(tlb, vma)			do { } while (0)
 
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
-{
-	if (force) {
-		tlb->start = start;
-		tlb->end = end;
-	}
+#define tlb_flush tlb_flush
+#define pte_free_tlb pte_free_tlb
+#define pmd_free_tlb pmd_free_tlb
+#define p4d_free_tlb p4d_free_tlb
+#define pud_free_tlb pud_free_tlb
 
-	tlb_flush_mmu(tlb);
-}
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm-generic/tlb.h>
 
 /*
  * Release the page cache reference for a pte removed by
  * tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page
  * has already been freed, so just do free_page_and_swap_cache.
  */
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	free_page_and_swap_cache(page);
-	return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	free_page_and_swap_cache(page);
-}
-
 static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
 					  struct page *page, int page_size)
 {
-	return __tlb_remove_page(tlb, page);
+	free_page_and_swap_cache(page);
+	return false;
 }
 
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
+static inline void tlb_flush(struct mmu_gather *tlb)
 {
-	return tlb_remove_page(tlb, page);
+	__tlb_flush_mm_lazy(tlb->mm);
 }
 
 /*
@@ -121,8 +62,17 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb,
  * page table from the tlb.
  */
 static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
-				unsigned long address)
+                                unsigned long address)
 {
+	__tlb_adjust_range(tlb, address, PAGE_SIZE);
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_ptes = 1;
+	/*
+	 * page_table_free_rcu takes care of the allocation bit masks
+	 * of the 2K table fragments in the 4K page table page,
+	 * then calls tlb_remove_table.
+	 */
 	page_table_free_rcu(tlb, (unsigned long *) pte, address);
 }
 
@@ -139,6 +89,10 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 	if (mm_pmd_folded(tlb->mm))
 		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
+	__tlb_adjust_range(tlb, address, PAGE_SIZE);
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_puds = 1;
 	tlb_remove_table(tlb, pmd);
 }
 
@@ -154,6 +108,10 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 {
 	if (mm_p4d_folded(tlb->mm))
 		return;
+	__tlb_adjust_range(tlb, address, PAGE_SIZE);
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_p4ds = 1;
 	tlb_remove_table(tlb, p4d);
 }
 
@@ -169,21 +127,11 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 {
 	if (mm_pud_folded(tlb->mm))
 		return;
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_puds = 1;
 	tlb_remove_table(tlb, pud);
 }
 
-#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, addr)	do { } while (0)
-#define tlb_remove_pmd_tlb_entry(tlb, pmdp, addr)	do { } while (0)
-#define tlb_migrate_finish(mm)			do { } while (0)
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
 
 #endif /* _S390_TLB_H */
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index db6bb2f97a2c..99e06213a22b 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -290,7 +290,7 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
 	tlb_remove_table(tlb, table);
 }
 
-static void __tlb_remove_table(void *_table)
+void __tlb_remove_table(void *_table)
 {
 	unsigned int mask = (unsigned long) _table & 3;
 	void *table = (void *)((unsigned long) _table ^ mask);
@@ -316,67 +316,6 @@ static void __tlb_remove_table(void *_table)
 	}
 }
 
-static void tlb_remove_table_smp_sync(void *arg)
-{
-	/* Simply deliver the interrupt */
-}
-
-static void tlb_remove_table_one(void *table)
-{
-	/*
-	 * This isn't an RCU grace period and hence the page-tables cannot be
-	 * assumed to be actually RCU-freed.
-	 *
-	 * It is however sufficient for software page-table walkers that rely
-	 * on IRQ disabling. See the comment near struct mmu_table_batch.
-	 */
-	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
-	__tlb_remove_table(table);
-}
-
-static void tlb_remove_table_rcu(struct rcu_head *head)
-{
-	struct mmu_table_batch *batch;
-	int i;
-
-	batch = container_of(head, struct mmu_table_batch, rcu);
-
-	for (i = 0; i < batch->nr; i++)
-		__tlb_remove_table(batch->tables[i]);
-
-	free_page((unsigned long)batch);
-}
-
-void tlb_table_flush(struct mmu_gather *tlb)
-{
-	struct mmu_table_batch **batch = &tlb->batch;
-
-	if (*batch) {
-		call_rcu(&(*batch)->rcu, tlb_remove_table_rcu);
-		*batch = NULL;
-	}
-}
-
-void tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct mmu_table_batch **batch = &tlb->batch;
-
-	tlb->mm->context.flush_mm = 1;
-	if (*batch == NULL) {
-		*batch = (struct mmu_table_batch *)
-			__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
-		if (*batch == NULL) {
-			__tlb_flush_mm_lazy(tlb->mm);
-			tlb_remove_table_one(table);
-			return;
-		}
-		(*batch)->nr = 0;
-	}
-	(*batch)->tables[(*batch)->nr++] = table;
-	if ((*batch)->nr == MAX_TABLE_BATCH)
-		tlb_flush_mmu(tlb);
-}
-
 /*
  * Base infrastructure required to generate basic asces, region, segment,
  * and page tables that do not make use of enhanced features like EDAT1.
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index 8ad73cb31121..b56f908b1395 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -70,6 +70,15 @@ do {							\
 	tlb_remove_page((tlb), (pte));			\
 } while (0)
 
+#if CONFIG_PGTABLE_LEVELS > 2
+#define __pmd_free_tlb(tlb, pmdp, addr)			\
+do {							\
+	struct page *page = virt_to_page(pmdp);		\
+	pgtable_pmd_page_dtor(page);			\
+	tlb_remove_page((tlb), page);			\
+} while (0);
+#endif
+
 static inline void check_pgt_cache(void)
 {
 	quicklist_trim(QUICK_PT, NULL, 25, 16);
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 77abe192fb43..bc77f3dd4261 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -11,133 +11,8 @@
 
 #ifdef CONFIG_MMU
 #include <linux/swap.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-#include <asm/mmu_context.h>
 
-/*
- * TLB handling.  This allows us to remove pages from the page
- * tables, and efficiently handle the TLB issues.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		fullmm;
-	unsigned long		start, end;
-};
-
-static inline void init_tlb_gather(struct mmu_gather *tlb)
-{
-	tlb->start = TASK_SIZE;
-	tlb->end = 0;
-
-	if (tlb->fullmm) {
-		tlb->start = 0;
-		tlb->end = TASK_SIZE;
-	}
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-		unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->start = start;
-	tlb->end = end;
-	tlb->fullmm = !(start | (end+1));
-
-	init_tlb_gather(tlb);
-}
-
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
-{
-	if (tlb->fullmm || force)
-		flush_tlb_mm(tlb->mm);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-}
-
-static inline void
-tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
-{
-	if (tlb->start > address)
-		tlb->start = address;
-	if (tlb->end < address + PAGE_SIZE)
-		tlb->end = address + PAGE_SIZE;
-}
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush.  When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void
-tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm)
-		flush_cache_range(vma, vma->vm_start, vma->vm_end);
-}
-
-static inline void
-tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm && tlb->end) {
-		flush_tlb_range(vma, tlb->start, tlb->end);
-		init_tlb_gather(tlb);
-	}
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-}
-
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	free_page_and_swap_cache(page);
-	return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	__tlb_remove_page(tlb, page);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, addr)	pte_free((tlb)->mm, ptep)
-#define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
-#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
-
-#define tlb_migrate_finish(mm)		do { } while (0)
+#include <asm-generic/tlb.h>
 
 #if defined(CONFIG_CPU_SH4) || defined(CONFIG_SUPERH64)
 extern void tlb_wire_entry(struct vm_area_struct *, unsigned long, pte_t);
@@ -157,11 +32,6 @@ static inline void tlb_unwire_entry(void)
 
 #else /* CONFIG_MMU */
 
-#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, address)	do { } while (0)
-#define tlb_flush(tlb)					do { } while (0)
-
 #include <asm-generic/tlb.h>
 
 #endif /* CONFIG_MMU */
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 40f8f4f73fe8..db79290ed6d5 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -63,6 +63,7 @@ config SPARC64
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
 	select HAVE_RCU_TABLE_FREE if SMP
+	select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_DYNAMIC_FTRACE
diff --git a/arch/sparc/include/asm/tlb_32.h b/arch/sparc/include/asm/tlb_32.h
index 343cea19e573..5cd28a8793e3 100644
--- a/arch/sparc/include/asm/tlb_32.h
+++ b/arch/sparc/include/asm/tlb_32.h
@@ -2,24 +2,6 @@
 #ifndef _SPARC_TLB_H
 #define _SPARC_TLB_H
 
-#define tlb_start_vma(tlb, vma) \
-do {								\
-	flush_cache_range(vma, vma->vm_start, vma->vm_end);	\
-} while (0)
-
-#define tlb_end_vma(tlb, vma) \
-do {								\
-	flush_tlb_range(vma, vma->vm_start, vma->vm_end);	\
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) \
-	do { } while (0)
-
-#define tlb_flush(tlb) \
-do {								\
-	flush_tlb_mm((tlb)->mm);				\
-} while (0)
-
 #include <asm-generic/tlb.h>
 
 #endif /* _SPARC_TLB_H */
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index dce6db147f24..70ee60383900 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -2,162 +2,8 @@
 #ifndef __UM_TLB_H
 #define __UM_TLB_H
 
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <asm/percpu.h>
-#include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
-
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
-/* struct mmu_gather is an opaque type used by the mm code for passing around
- * any data needed by arch specific code for tlb_remove_page.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		need_flush; /* Really unmapped some ptes? */
-	unsigned long		start;
-	unsigned long		end;
-	unsigned int		fullmm; /* non-zero means full mm flush */
-};
-
-static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
-					  unsigned long address)
-{
-	if (tlb->start > address)
-		tlb->start = address;
-	if (tlb->end < address + PAGE_SIZE)
-		tlb->end = address + PAGE_SIZE;
-}
-
-static inline void init_tlb_gather(struct mmu_gather *tlb)
-{
-	tlb->need_flush = 0;
-
-	tlb->start = TASK_SIZE;
-	tlb->end = 0;
-
-	if (tlb->fullmm) {
-		tlb->start = 0;
-		tlb->end = TASK_SIZE;
-	}
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-		unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->start = start;
-	tlb->end = end;
-	tlb->fullmm = !(start | (end+1));
-
-	init_tlb_gather(tlb);
-}
-
-extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
-			       unsigned long end);
-
-static inline void
-tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end);
-}
-
-static inline void
-tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	init_tlb_gather(tlb);
-}
-
-static inline void
-tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	if (!tlb->need_flush)
-		return;
-
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
-
-/* arch_tlb_finish_mmu
- *	Called at the end of the shootdown operation to free up any resources
- *	that were required.
- */
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
-{
-	if (force) {
-		tlb->start = start;
-		tlb->end = end;
-		tlb->need_flush = 1;
-	}
-	tlb_flush_mmu(tlb);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-}
-
-/* tlb_remove_page
- *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)),
- *	while handling the additional races in SMP caused by other CPUs
- *	caching valid mappings in their TLBs.
- */
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->need_flush = 1;
-	free_page_and_swap_cache(page);
-	return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	__tlb_remove_page(tlb, page);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-/**
- * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
- *
- * Record the fact that pte's were really umapped in ->need_flush, so we can
- * later optimise away the tlb invalidate.   This helps when userspace is
- * unmapping already-unmapped pages, which happens quite a lot.
- */
-#define tlb_remove_tlb_entry(tlb, ptep, address)		\
-	do {							\
-		tlb->need_flush = 1;				\
-		__tlb_remove_tlb_entry(tlb, ptep, address);	\
-	} while (0)
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
-
-#define pud_free_tlb(tlb, pudp, addr) __pud_free_tlb(tlb, pudp, addr)
-
-#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr)
-
-#define tlb_migrate_finish(mm) do {} while (0)
+#include <asm-generic/cacheflush.h>
+#include <asm-generic/tlb.h>
 
 #endif
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 817d82608712..d83c8f70900d 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -20,6 +20,7 @@ config UNICORE32
 	select GENERIC_IOMAP
 	select MODULES_USE_ELF_REL
 	select NEED_DMA_MAP_STATE
+	select MMU_GATHER_NO_RANGE if MMU
 	help
 	  UniCore-32 is 32-bit Instruction Set Architecture,
 	  including a series of low-power-consumption RISC chip
diff --git a/arch/unicore32/include/asm/tlb.h b/arch/unicore32/include/asm/tlb.h
index 9cca15cdae94..00a8477333f6 100644
--- a/arch/unicore32/include/asm/tlb.h
+++ b/arch/unicore32/include/asm/tlb.h
@@ -12,10 +12,9 @@
 #ifndef __UNICORE_TLB_H__
 #define __UNICORE_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, ptep, address)	do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+/*
+ * unicore32 lacks an efficient flush_tlb_range(), use flush_tlb_mm().
+ */
 
 #define __pte_free_tlb(tlb, pte, addr)				\
 	do {							\
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 62fc3fda1a05..406a0cf30c57 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -183,7 +183,6 @@ config X86
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if PARAVIRT
-	select HAVE_RCU_TABLE_INVALIDATE	if HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
 	select HAVE_FUNCTION_ARG_ACCESS_API
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 404b8b1d44f5..f23e7aaff4cd 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -6,6 +6,7 @@
 #define tlb_end_vma(tlb, vma) do { } while (0)
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 
+#define tlb_flush tlb_flush
 static inline void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
diff --git a/arch/xtensa/include/asm/tlb.h b/arch/xtensa/include/asm/tlb.h
index 0d766f9c1083..50889935138a 100644
--- a/arch/xtensa/include/asm/tlb.h
+++ b/arch/xtensa/include/asm/tlb.h
@@ -14,32 +14,6 @@
 #include <asm/cache.h>
 #include <asm/page.h>
 
-#if (DCACHE_WAY_SIZE <= PAGE_SIZE)
-
-/* Note, read http://lkml.org/lkml/2004/1/15/6 */
-
-# define tlb_start_vma(tlb,vma)			do { } while (0)
-# define tlb_end_vma(tlb,vma)			do { } while (0)
-
-#else
-
-# define tlb_start_vma(tlb, vma)					      \
-	do {								      \
-		if (!tlb->fullmm)					      \
-			flush_cache_range(vma, vma->vm_start, vma->vm_end);   \
-	} while(0)
-
-# define tlb_end_vma(tlb, vma)						      \
-	do {								      \
-		if (!tlb->fullmm)					      \
-			flush_tlb_range(vma, vma->vm_start, vma->vm_end);     \
-	} while(0)
-
-#endif
-
-#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)
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 6be86c1c5c58..b9edc7608d90 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -19,9 +19,131 @@
 #include <linux/swap.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
 
 #ifdef CONFIG_MMU
 
+/*
+ * Generic MMU-gather implementation.
+ *
+ * The mmu_gather data structure is used by the mm code to implement the
+ * correct and efficient ordering of freeing pages and TLB invalidations.
+ *
+ * This correct ordering is:
+ *
+ *  1) unhook page
+ *  2) TLB invalidate page
+ *  3) free page
+ *
+ * That is, we must never free a page before we have ensured there are no live
+ * translations left to it. Otherwise it might be possible to observe (or
+ * worse, change) the page content after it has been reused.
+ *
+ * The mmu_gather API consists of:
+ *
+ *  - tlb_gather_mmu() / tlb_finish_mmu(); start and finish a mmu_gather
+ *
+ *    Finish in particular will issue a (final) TLB invalidate and free
+ *    all (remaining) queued pages.
+ *
+ *  - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA
+ *
+ *    Defaults to flushing at tlb_end_vma() to reset the range; helps when
+ *    there's large holes between the VMAs.
+ *
+ *  - tlb_remove_page() / __tlb_remove_page()
+ *  - tlb_remove_page_size() / __tlb_remove_page_size()
+ *
+ *    __tlb_remove_page_size() is the basic primitive that queues a page for
+ *    freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a
+ *    boolean indicating if the queue is (now) full and a call to
+ *    tlb_flush_mmu() is required.
+ *
+ *    tlb_remove_page() and tlb_remove_page_size() imply the call to
+ *    tlb_flush_mmu() when required and has no return value.
+ *
+ *  - tlb_change_page_size()
+ *
+ *    call before __tlb_remove_page*() to set the current page-size; implies a
+ *    possible tlb_flush_mmu() call.
+ *
+ *  - tlb_flush_mmu() / tlb_flush_mmu_tlbonly()
+ *
+ *    tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets
+ *                              related state, like the range)
+ *
+ *    tlb_flush_mmu() - in addition to the above TLB invalidate, also frees
+ *			whatever pages are still batched.
+ *
+ *  - mmu_gather::fullmm
+ *
+ *    A flag set by tlb_gather_mmu() to indicate we're going to free
+ *    the entire mm; this allows a number of optimizations.
+ *
+ *    - We can ignore tlb_{start,end}_vma(); because we don't
+ *      care about ranges. Everything will be shot down.
+ *
+ *    - (RISC) architectures that use ASIDs can cycle to a new ASID
+ *      and delay the invalidation until ASID space runs out.
+ *
+ *  - mmu_gather::need_flush_all
+ *
+ *    A flag that can be set by the arch code if it wants to force
+ *    flush the entire TLB irrespective of the range. For instance
+ *    x86-PAE needs this when changing top-level entries.
+ *
+ * And allows the architecture to provide and implement tlb_flush():
+ *
+ * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make
+ * use of:
+ *
+ *  - mmu_gather::start / mmu_gather::end
+ *
+ *    which provides the range that needs to be flushed to cover the pages to
+ *    be freed.
+ *
+ *  - mmu_gather::freed_tables
+ *
+ *    set when we freed page table pages
+ *
+ *  - tlb_get_unmap_shift() / tlb_get_unmap_size()
+ *
+ *    returns the smallest TLB entry size unmapped in this range.
+ *
+ * If an architecture does not provide tlb_flush() a default implementation
+ * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is
+ * specified, in which case we'll default to flush_tlb_mm().
+ *
+ * Additionally there are a few opt-in features:
+ *
+ *  HAVE_MMU_GATHER_PAGE_SIZE
+ *
+ *  This ensures we call tlb_flush() every time tlb_change_page_size() actually
+ *  changes the size and provides mmu_gather::page_size to tlb_flush().
+ *
+ *  HAVE_RCU_TABLE_FREE
+ *
+ *  This provides tlb_remove_table(), to be used instead of tlb_remove_page()
+ *  for page directores (__p*_free_tlb()). This provides separate freeing of
+ *  the page-table pages themselves in a semi-RCU fashion (see comment below).
+ *  Useful if your architecture doesn't use IPIs for remote TLB invalidates
+ *  and therefore doesn't naturally serialize with software page-table walkers.
+ *
+ *  When used, an architecture is expected to provide __tlb_remove_table()
+ *  which does the actual freeing of these pages.
+ *
+ *  HAVE_RCU_TABLE_NO_INVALIDATE
+ *
+ *  This makes HAVE_RCU_TABLE_FREE avoid calling tlb_flush_mmu_tlbonly() before
+ *  freeing the page-table pages. This can be avoided if you use
+ *  HAVE_RCU_TABLE_FREE and your architecture does _NOT_ use the Linux
+ *  page-tables natively.
+ *
+ *  MMU_GATHER_NO_RANGE
+ *
+ *  Use this if your architecture lacks an efficient flush_tlb_range().
+ */
+
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 /*
  * Semi RCU freeing of the page directories.
@@ -60,11 +182,11 @@ struct mmu_table_batch {
 #define MAX_TABLE_BATCH		\
 	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
 
-extern void tlb_table_flush(struct mmu_gather *tlb);
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
 #endif
 
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
 /*
  * If we can't allocate a page to make a big batch of page pointers
  * to work on, then just handle a few from the on-stack structure.
@@ -89,14 +211,21 @@ struct mmu_gather_batch {
  */
 #define MAX_GATHER_BATCH_COUNT	(10000UL/MAX_GATHER_BATCH)
 
-/* struct mmu_gather is an opaque type used by the mm code for passing around
+extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
+				   int page_size);
+#endif
+
+/*
+ * struct mmu_gather is an opaque type used by the mm code for passing around
  * any data needed by arch specific code for tlb_remove_page.
  */
 struct mmu_gather {
 	struct mm_struct	*mm;
+
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	struct mmu_table_batch	*batch;
 #endif
+
 	unsigned long		start;
 	unsigned long		end;
 	/*
@@ -124,23 +253,30 @@ struct mmu_gather {
 	unsigned int		cleared_puds : 1;
 	unsigned int		cleared_p4ds : 1;
 
+	/*
+	 * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma
+	 */
+	unsigned int		vma_exec : 1;
+	unsigned int		vma_huge : 1;
+
+	unsigned int		batch_count;
+
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
-	unsigned int		batch_count;
-	int page_size;
-};
 
-#define HAVE_GENERIC_MMU_GATHER
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+	unsigned int page_size;
+#endif
+#endif
+};
 
 void arch_tlb_gather_mmu(struct mmu_gather *tlb,
 	struct mm_struct *mm, unsigned long start, unsigned long end);
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void arch_tlb_finish_mmu(struct mmu_gather *tlb,
 			 unsigned long start, unsigned long end, bool force);
-void tlb_flush_mmu_free(struct mmu_gather *tlb);
-extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
-				   int page_size);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 				      unsigned long address,
@@ -163,8 +299,94 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	tlb->cleared_pmds = 0;
 	tlb->cleared_puds = 0;
 	tlb->cleared_p4ds = 0;
+	/*
+	 * Do not reset mmu_gather::vma_* fields here, we do not
+	 * call into tlb_start_vma() again to set them if there is an
+	 * intermediate flush.
+	 */
+}
+
+#ifdef CONFIG_MMU_GATHER_NO_RANGE
+
+#if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma)
+#error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma()
+#endif
+
+/*
+ * When an architecture does not have efficient means of range flushing TLBs
+ * there is no point in doing intermediate flushes on tlb_end_vma() to keep the
+ * range small. We equally don't have to worry about page granularity or other
+ * things.
+ *
+ * All we need to do is issue a full flush for any !0 range.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	if (tlb->end)
+		flush_tlb_mm(tlb->mm);
+}
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#define tlb_end_vma tlb_end_vma
+static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#else /* CONFIG_MMU_GATHER_NO_RANGE */
+
+#ifndef tlb_flush
+
+#if defined(tlb_start_vma) || defined(tlb_end_vma)
+#error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma()
+#endif
+
+/*
+ * When an architecture does not provide its own tlb_flush() implementation
+ * but does have a reasonably efficient flush_vma_range() implementation
+ * use that.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	if (tlb->fullmm || tlb->need_flush_all) {
+		flush_tlb_mm(tlb->mm);
+	} else if (tlb->end) {
+		struct vm_area_struct vma = {
+			.vm_mm = tlb->mm,
+			.vm_flags = (tlb->vma_exec ? VM_EXEC    : 0) |
+				    (tlb->vma_huge ? VM_HUGETLB : 0),
+		};
+
+		flush_tlb_range(&vma, tlb->start, tlb->end);
+	}
 }
 
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	/*
+	 * flush_tlb_range() implementations that look at VM_HUGETLB (tile,
+	 * mips-4k) flush only large pages.
+	 *
+	 * flush_tlb_range() implementations that flush I-TLB also flush D-TLB
+	 * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing
+	 * range.
+	 *
+	 * We rely on tlb_end_vma() to issue a flush, such that when we reset
+	 * these values the batch is empty.
+	 */
+	tlb->vma_huge = !!(vma->vm_flags & VM_HUGETLB);
+	tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
+}
+
+#else
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#endif
+
+#endif /* CONFIG_MMU_GATHER_NO_RANGE */
+
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
 	if (!tlb->end)
@@ -196,21 +418,18 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	return tlb_remove_page_size(tlb, page, PAGE_SIZE);
 }
 
-#ifndef tlb_remove_check_page_size_change
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
+static inline void tlb_change_page_size(struct mmu_gather *tlb,
 						     unsigned int page_size)
 {
-	/*
-	 * We don't care about page size change, just update
-	 * mmu_gather page size here so that debug checks
-	 * doesn't throw false warning.
-	 */
-#ifdef CONFIG_DEBUG_VM
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+	if (tlb->page_size && tlb->page_size != page_size) {
+		if (!tlb->fullmm)
+			tlb_flush_mmu(tlb);
+	}
+
 	tlb->page_size = page_size;
 #endif
 }
-#endif
 
 static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb)
 {
@@ -237,17 +456,30 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
  * the vmas are adjusted to only cover the region to be torn down.
  */
 #ifndef tlb_start_vma
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#endif
+static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (tlb->fullmm)
+		return;
 
-#define __tlb_end_vma(tlb, vma)					\
-	do {							\
-		if (!tlb->fullmm)				\
-			tlb_flush_mmu_tlbonly(tlb);		\
-	} while (0)
+	tlb_update_vma_flags(tlb, vma);
+	flush_cache_range(vma, vma->vm_start, vma->vm_end);
+}
+#endif
 
 #ifndef tlb_end_vma
-#define tlb_end_vma	__tlb_end_vma
+static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (tlb->fullmm)
+		return;
+
+	/*
+	 * Do a TLB flush and reset the range at VMA boundaries; this avoids
+	 * the ranges growing with the unused space between consecutive VMAs,
+	 * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on
+	 * this.
+	 */
+	tlb_flush_mmu_tlbonly(tlb);
+}
 #endif
 
 #ifndef __tlb_remove_tlb_entry
@@ -372,6 +604,4 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
 
 #endif /* CONFIG_MMU */
 
-#define tlb_migrate_finish(mm) do {} while (0)
-
 #endif /* _ASM_GENERIC__TLB_H */
diff --git a/kernel/iomem.c b/kernel/iomem.c
index f7525e14ebc6..93c264444510 100644
--- a/kernel/iomem.c
+++ b/kernel/iomem.c
@@ -55,7 +55,7 @@ static void *try_ram_remap(resource_size_t offset, size_t size,
  *
  * MEMREMAP_WB - matches the default mapping for System RAM on
  * the architecture.  This is usually a read-allocate write-back cache.
- * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM
+ * Moreover, if MEMREMAP_WB is specified and the requested remap region is RAM
  * memremap() will bypass establishing a new mapping and instead return
  * a pointer into the direct map.
  *
@@ -86,7 +86,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
 	/* Try all mapping types requested until one returns non-NULL */
 	if (flags & MEMREMAP_WB) {
 		/*
-		 * MEMREMAP_WB is special in that it can be satisifed
+		 * MEMREMAP_WB is special in that it can be satisfied
 		 * from the direct map.  Some archs depend on the
 		 * capability of memremap() to autodetect cases where
 		 * the requested range is potentially in System RAM.
diff --git a/kernel/resource.c b/kernel/resource.c
index 92190f62ebc5..8c15f846e8ef 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -520,21 +520,20 @@ EXPORT_SYMBOL_GPL(page_is_ram);
 int region_intersects(resource_size_t start, size_t size, unsigned long flags,
 		      unsigned long desc)
 {
-	resource_size_t end = start + size - 1;
+	struct resource res;
 	int type = 0; int other = 0;
 	struct resource *p;
 
+	res.start = start;
+	res.end = start + size - 1;
+
 	read_lock(&resource_lock);
 	for (p = iomem_resource.child; p ; p = p->sibling) {
 		bool is_type = (((p->flags & flags) == flags) &&
 				((desc == IORES_DESC_NONE) ||
 				 (desc == p->desc)));
 
-		if (start >= p->start && start <= p->end)
-			is_type ? type++ : other++;
-		if (end >= p->start && end <= p->end)
-			is_type ? type++ : other++;
-		if (p->start >= start && p->end <= end)
+		if (resource_overlaps(p, &res))
 			is_type ? type++ : other++;
 	}
 	read_unlock(&resource_lock);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4778c48a7fda..ade3f2287d1f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1151,7 +1151,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		/* Need help from migration thread: drop lock and wait. */
 		task_rq_unlock(rq, p, &rf);
 		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
-		tlb_migrate_finish(p->mm);
 		return 0;
 	} else if (task_on_rq_queued(p)) {
 		/*
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 165ea46bf149..b6a34b32d8ac 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1677,7 +1677,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	struct mm_struct *mm = tlb->mm;
 	bool ret = false;
 
-	tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+	tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)
@@ -1753,7 +1753,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	pmd_t orig_pmd;
 	spinlock_t *ptl;
 
-	tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+	tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
 
 	ptl = __pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6cdc7b2d9100..641cedfc8c0f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3353,7 +3353,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	 * This is a hugetlb vma, all the pte entries should point
 	 * to huge page.
 	 */
-	tlb_remove_check_page_size_change(tlb, sz);
+	tlb_change_page_size(tlb, sz);
 	tlb_start_vma(tlb, vma);
 
 	/*
diff --git a/mm/madvise.c b/mm/madvise.c
index 21a7881a2db4..bb3a4554d5d5 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -328,7 +328,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 	if (pmd_trans_unstable(pmd))
 		return 0;
 
-	tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+	tlb_change_page_size(tlb, PAGE_SIZE);
 	orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	flush_tlb_batched_pending(mm);
 	arch_enter_lazy_mmu_mode();
diff --git a/mm/memory.c b/mm/memory.c
index ab650c21bccd..36aac6844662 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -356,7 +356,7 @@ void free_pgd_range(struct mmu_gather *tlb,
 	 * We add page table cache pages with PAGE_SIZE,
 	 * (see pte_free_tlb()), flush the tlb if we need
 	 */
-	tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+	tlb_change_page_size(tlb, PAGE_SIZE);
 	pgd = pgd_offset(tlb->mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
@@ -1046,7 +1046,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	pte_t *pte;
 	swp_entry_t entry;
 
-	tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+	tlb_change_page_size(tlb, PAGE_SIZE);
 again:
 	init_rss_vec(rss);
 	start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
@@ -1155,7 +1155,7 @@ again:
 	 */
 	if (force_flush) {
 		force_flush = 0;
-		tlb_flush_mmu_free(tlb);
+		tlb_flush_mmu(tlb);
 		if (addr != end)
 			goto again;
 	}
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index f2f03c655807..99740e1dd273 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -11,7 +11,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 
-#ifdef HAVE_GENERIC_MMU_GATHER
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
 
 static bool tlb_next_batch(struct mmu_gather *tlb)
 {
@@ -41,35 +41,10 @@ static bool tlb_next_batch(struct mmu_gather *tlb)
 	return true;
 }
 
-void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-				unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-
-	/* Is it from 0 to ~0? */
-	tlb->fullmm     = !(start | (end+1));
-	tlb->need_flush_all = 0;
-	tlb->local.next = NULL;
-	tlb->local.nr   = 0;
-	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
-	tlb->active     = &tlb->local;
-	tlb->batch_count = 0;
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb->batch = NULL;
-#endif
-	tlb->page_size = 0;
-
-	__tlb_reset_range(tlb);
-}
-
-void tlb_flush_mmu_free(struct mmu_gather *tlb)
+static void tlb_batch_pages_flush(struct mmu_gather *tlb)
 {
 	struct mmu_gather_batch *batch;
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb_table_flush(tlb);
-#endif
 	for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
 		free_pages_and_swap_cache(batch->pages, batch->nr);
 		batch->nr = 0;
@@ -77,31 +52,10 @@ void tlb_flush_mmu_free(struct mmu_gather *tlb)
 	tlb->active = &tlb->local;
 }
 
-void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
-
-/* tlb_finish_mmu
- *	Called at the end of the shootdown operation to free up any resources
- *	that were required.
- */
-void arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
+static void tlb_batch_list_free(struct mmu_gather *tlb)
 {
 	struct mmu_gather_batch *batch, *next;
 
-	if (force) {
-		__tlb_reset_range(tlb);
-		__tlb_adjust_range(tlb, start, end - start);
-	}
-
-	tlb_flush_mmu(tlb);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
 	for (batch = tlb->local.next; batch; batch = next) {
 		next = batch->next;
 		free_pages((unsigned long)batch, 0);
@@ -109,19 +63,15 @@ void arch_tlb_finish_mmu(struct mmu_gather *tlb,
 	tlb->local.next = NULL;
 }
 
-/* __tlb_remove_page
- *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
- *	handling the additional races in SMP caused by other CPUs caching valid
- *	mappings in their TLBs. Returns the number of free page slots left.
- *	When out of page slots we must call tlb_flush_mmu().
- *returns true if the caller should flush.
- */
 bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
 {
 	struct mmu_gather_batch *batch;
 
 	VM_BUG_ON(!tlb->end);
+
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
 	VM_WARN_ON(tlb->page_size != page_size);
+#endif
 
 	batch = tlb->active;
 	/*
@@ -139,7 +89,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 	return false;
 }
 
-#endif /* HAVE_GENERIC_MMU_GATHER */
+#endif /* HAVE_MMU_GATHER_NO_GATHER */
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 
@@ -152,7 +102,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
  */
 static inline void tlb_table_invalidate(struct mmu_gather *tlb)
 {
-#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
+#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE
 	/*
 	 * Invalidate page-table caches used by hardware walkers. Then we still
 	 * need to RCU-sched wait while freeing the pages because software
@@ -193,7 +143,7 @@ static void tlb_remove_table_rcu(struct rcu_head *head)
 	free_page((unsigned long)batch);
 }
 
-void tlb_table_flush(struct mmu_gather *tlb)
+static void tlb_table_flush(struct mmu_gather *tlb)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
@@ -225,6 +175,22 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 
+static void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb_table_flush(tlb);
+#endif
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+	tlb_batch_pages_flush(tlb);
+#endif
+}
+
+void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+	tlb_flush_mmu_tlbonly(tlb);
+	tlb_flush_mmu_free(tlb);
+}
+
 /**
  * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
  * @tlb: the mmu_gather structure to initialize
@@ -240,10 +206,40 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 			unsigned long start, unsigned long end)
 {
-	arch_tlb_gather_mmu(tlb, mm, start, end);
+	tlb->mm = mm;
+
+	/* Is it from 0 to ~0? */
+	tlb->fullmm     = !(start | (end+1));
+
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+	tlb->need_flush_all = 0;
+	tlb->local.next = NULL;
+	tlb->local.nr   = 0;
+	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
+	tlb->active     = &tlb->local;
+	tlb->batch_count = 0;
+#endif
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb->batch = NULL;
+#endif
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+	tlb->page_size = 0;
+#endif
+
+	__tlb_reset_range(tlb);
 	inc_tlb_flush_pending(tlb->mm);
 }
 
+/**
+ * tlb_finish_mmu - finish an mmu_gather structure
+ * @tlb: the mmu_gather structure to finish
+ * @start: start of the region that will be removed from the page-table
+ * @end: end of the region that will be removed from the page-table
+ *
+ * Called at the end of the shootdown operation to free up any resources that
+ * were required.
+ */
 void tlb_finish_mmu(struct mmu_gather *tlb,
 		unsigned long start, unsigned long end)
 {
@@ -254,8 +250,17 @@ void tlb_finish_mmu(struct mmu_gather *tlb,
 	 * the TLB by observing pte_none|!pte_dirty, for example so flush TLB
 	 * forcefully if we detect parallel PTE batching threads.
 	 */
-	bool force = mm_tlb_flush_nested(tlb->mm);
+	if (mm_tlb_flush_nested(tlb->mm)) {
+		__tlb_reset_range(tlb);
+		__tlb_adjust_range(tlb, start, end - start);
+	}
 
-	arch_tlb_finish_mmu(tlb, start, end, force);
+	tlb_flush_mmu(tlb);
+
+	/* keep the page table cache within bounds */
+	check_pgt_cache();
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+	tlb_batch_list_free(tlb);
+#endif
 	dec_tlb_flush_pending(tlb->mm);
 }