4 files changed, 127 insertions, 21 deletions

diff --git a/arch/i386/mm/highmem.c b/arch/i386/mm/highmem.c
index f9f647cdbc7..e0fa6cb655a 100644
--- a/arch/i386/mm/highmem.c
+++ b/arch/i386/mm/highmem.c
@@ -32,7 +32,7 @@ void *kmap_atomic(struct page *page, enum km_type type)
 	unsigned long vaddr;
 
 	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
-	inc_preempt_count();
+	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
 
@@ -50,26 +50,22 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
 	enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
 
-#ifdef CONFIG_DEBUG_HIGHMEM
-	if (vaddr >= PAGE_OFFSET && vaddr < (unsigned long)high_memory) {
-		dec_preempt_count();
-		preempt_check_resched();
-		return;
-	}
-
-	if (vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx))
-		BUG();
-#endif
 	/*
 	 * Force other mappings to Oops if they'll try to access this pte
 	 * without first remap it.  Keeping stale mappings around is a bad idea
 	 * also, in case the page changes cacheability attributes or becomes
 	 * a protected page in a hypervisor.
 	 */
-	kpte_clear_flush(kmap_pte-idx, vaddr);
+	if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
+		kpte_clear_flush(kmap_pte-idx, vaddr);
+	else {
+#ifdef CONFIG_DEBUG_HIGHMEM
+		BUG_ON(vaddr < PAGE_OFFSET);
+		BUG_ON(vaddr >= (unsigned long)high_memory);
+#endif
+	}
 
-	dec_preempt_count();
-	preempt_check_resched();
+	pagefault_enable();
 }
 
 /* This is the same as kmap_atomic() but can map memory that doesn't
@@ -80,7 +76,7 @@ void *kmap_atomic_pfn(unsigned long pfn, enum km_type type)
 	enum fixed_addresses idx;
 	unsigned long vaddr;
 
-	inc_preempt_count();
+	pagefault_disable();
 
 	idx = type + KM_TYPE_NR*smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
diff --git a/arch/i386/mm/hugetlbpage.c b/arch/i386/mm/hugetlbpage.c
index 1719a8141f8..34728e4afe4 100644
--- a/arch/i386/mm/hugetlbpage.c
+++ b/arch/i386/mm/hugetlbpage.c
@@ -17,6 +17,113 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
+static unsigned long page_table_shareable(struct vm_area_struct *svma,
+				struct vm_area_struct *vma,
+				unsigned long addr, pgoff_t idx)
+{
+	unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) +
+				svma->vm_start;
+	unsigned long sbase = saddr & PUD_MASK;
+	unsigned long s_end = sbase + PUD_SIZE;
+
+	/*
+	 * match the virtual addresses, permission and the alignment of the
+	 * page table page.
+	 */
+	if (pmd_index(addr) != pmd_index(saddr) ||
+	    vma->vm_flags != svma->vm_flags ||
+	    sbase < svma->vm_start || svma->vm_end < s_end)
+		return 0;
+
+	return saddr;
+}
+
+static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
+{
+	unsigned long base = addr & PUD_MASK;
+	unsigned long end = base + PUD_SIZE;
+
+	/*
+	 * check on proper vm_flags and page table alignment
+	 */
+	if (vma->vm_flags & VM_MAYSHARE &&
+	    vma->vm_start <= base && end <= vma->vm_end)
+		return 1;
+	return 0;
+}
+
+/*
+ * search for a shareable pmd page for hugetlb.
+ */
+static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+{
+	struct vm_area_struct *vma = find_vma(mm, addr);
+	struct address_space *mapping = vma->vm_file->f_mapping;
+	pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
+			vma->vm_pgoff;
+	struct prio_tree_iter iter;
+	struct vm_area_struct *svma;
+	unsigned long saddr;
+	pte_t *spte = NULL;
+
+	if (!vma_shareable(vma, addr))
+		return;
+
+	spin_lock(&mapping->i_mmap_lock);
+	vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
+		if (svma == vma)
+			continue;
+
+		saddr = page_table_shareable(svma, vma, addr, idx);
+		if (saddr) {
+			spte = huge_pte_offset(svma->vm_mm, saddr);
+			if (spte) {
+				get_page(virt_to_page(spte));
+				break;
+			}
+		}
+	}
+
+	if (!spte)
+		goto out;
+
+	spin_lock(&mm->page_table_lock);
+	if (pud_none(*pud))
+		pud_populate(mm, pud, (unsigned long) spte & PAGE_MASK);
+	else
+		put_page(virt_to_page(spte));
+	spin_unlock(&mm->page_table_lock);
+out:
+	spin_unlock(&mapping->i_mmap_lock);
+}
+
+/*
+ * unmap huge page backed by shared pte.
+ *
+ * Hugetlb pte page is ref counted at the time of mapping.  If pte is shared
+ * indicated by page_count > 1, unmap is achieved by clearing pud and
+ * decrementing the ref count. If count == 1, the pte page is not shared.
+ *
+ * called with vma->vm_mm->page_table_lock held.
+ *
+ * returns: 1 successfully unmapped a shared pte page
+ *	    0 the underlying pte page is not shared, or it is the last user
+ */
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+	pgd_t *pgd = pgd_offset(mm, *addr);
+	pud_t *pud = pud_offset(pgd, *addr);
+
+	BUG_ON(page_count(virt_to_page(ptep)) == 0);
+	if (page_count(virt_to_page(ptep)) == 1)
+		return 0;
+
+	pud_clear(pud);
+	put_page(virt_to_page(ptep));
+	*addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
+	return 1;
+}
+
 pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
@@ -25,8 +132,11 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
 
 	pgd = pgd_offset(mm, addr);
 	pud = pud_alloc(mm, pgd, addr);
-	if (pud)
+	if (pud) {
+		if (pud_none(*pud))
+			huge_pmd_share(mm, addr, pud);
 		pte = (pte_t *) pmd_alloc(mm, pud, addr);
+	}
 	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
 
 	return pte;
diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index f4dd048187f..84697dfc734 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -697,8 +697,8 @@ int remove_memory(u64 start, u64 size)
 #endif
 #endif
 
-kmem_cache_t *pgd_cache;
-kmem_cache_t *pmd_cache;
+struct kmem_cache *pgd_cache;
+struct kmem_cache *pmd_cache;
 
 void __init pgtable_cache_init(void)
 {
diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c
index 65b5c095903..f349eaf450b 100644
--- a/arch/i386/mm/pgtable.c
+++ b/arch/i386/mm/pgtable.c
@@ -196,7 +196,7 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	return pte;
 }
 
-void pmd_ctor(void *pmd, kmem_cache_t *cache, unsigned long flags)
+void pmd_ctor(void *pmd, struct kmem_cache *cache, unsigned long flags)
 {
 	memset(pmd, 0, PTRS_PER_PMD*sizeof(pmd_t));
 }
@@ -236,7 +236,7 @@ static inline void pgd_list_del(pgd_t *pgd)
 		set_page_private(next, (unsigned long)pprev);
 }
 
-void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused)
+void pgd_ctor(void *pgd, struct kmem_cache *cache, unsigned long unused)
 {
 	unsigned long flags;
 
@@ -256,7 +256,7 @@ void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused)
 }
 
 /* never called when PTRS_PER_PMD > 1 */
-void pgd_dtor(void *pgd, kmem_cache_t *cache, unsigned long unused)
+void pgd_dtor(void *pgd, struct kmem_cache *cache, unsigned long unused)
 {
 	unsigned long flags; /* can be called from interrupt context */