1 files changed, 77 insertions, 34 deletions

diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 82dfe5d0c41..f1a0dace3ef 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -33,19 +33,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
-/*
- * We need to delay page freeing for SMP as other CPUs can access pages
- * which have been removed but not yet had their TLB entries invalidated.
- * Also, as ARMv7 speculative prefetch can drag new entries into the TLB,
- * we need to apply this same delaying tactic to ensure correct operation.
- */
-#if defined(CONFIG_SMP) || defined(CONFIG_CPU_32v7)
-#define tlb_fast_mode(tlb)	0
-#define FREE_PTE_NR		500
-#else
-#define tlb_fast_mode(tlb)	1
-#define FREE_PTE_NR		0
-#endif
+#define MMU_GATHER_BUNDLE	8
 
 /*
  * TLB handling.  This allows us to remove pages from the page
@@ -55,10 +43,13 @@ struct mmu_gather {
 	struct mm_struct	*mm;
 	unsigned int		fullmm;
 	struct vm_area_struct	*vma;
+	unsigned long		start, end;
 	unsigned long		range_start;
 	unsigned long		range_end;
 	unsigned int		nr;
-	struct page		*pages[FREE_PTE_NR];
+	unsigned int		max;
+	struct page		**pages;
+	struct page		*local[MMU_GATHER_BUNDLE];
 };
 
 DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
@@ -97,26 +88,47 @@ static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
 	}
 }
 
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 {
-	tlb_flush(tlb);
-	if (!tlb_fast_mode(tlb)) {
-		free_pages_and_swap_cache(tlb->pages, tlb->nr);
-		tlb->nr = 0;
+	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 struct mmu_gather *
-tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
+static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
-	struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
+	tlb_flush(tlb);
+}
 
+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
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+{
 	tlb->mm = mm;
-	tlb->fullmm = full_mm_flush;
+	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;
-
-	return tlb;
+	__tlb_alloc_page(tlb);
 }
 
 static inline void
@@ -127,7 +139,8 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
 	/* keep the page table cache within bounds */
 	check_pgt_cache();
 
-	put_cpu_var(mmu_gathers);
+	if (tlb->pages != tlb->local)
+		free_pages((unsigned long)tlb->pages, 0);
 }
 
 /*
@@ -162,27 +175,57 @@ tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 		tlb_flush(tlb);
 }
 
+static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	tlb->pages[tlb->nr++] = page;
+	VM_BUG_ON(tlb->nr > tlb->max);
+	return tlb->max - tlb->nr;
+}
+
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
-	if (tlb_fast_mode(tlb)) {
-		free_page_and_swap_cache(page);
-	} else {
-		tlb->pages[tlb->nr++] = page;
-		if (tlb->nr >= FREE_PTE_NR)
-			tlb_flush_mmu(tlb);
-	}
+	if (!__tlb_remove_page(tlb, page))
+		tlb_flush_mmu(tlb);
 }
 
 static inline void __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
+	/*
+	 * 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);
+#endif
+
 	tlb_remove_page(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_page(tlb, virt_to_page(pmdp));
+#endif
+}
+
+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)->mm, pmdp)
+#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)