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

6 files changed, 47 insertions, 282 deletions

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)
 {