X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=arch%2Fi386%2Fmm%2Fhugetlbpage.c;h=34728e4afe4806ad88982922ebbf9654023e4b64;hb=39dde65c9940c97fcd178a3d2b1c57ed8b7b68aa;hp=57c486f0e896c71056fcd139a6b3e1faec925ba0;hpb=7bf07f3d4b4358aa6d99a26d7a0165f1e91c3fcc;p=safe%2Fjmp%2Flinux-2.6

diff --git a/arch/i386/mm/hugetlbpage.c b/arch/i386/mm/hugetlbpage.c
index 57c486f..34728e4 100644
--- a/arch/i386/mm/hugetlbpage.c
+++ b/arch/i386/mm/hugetlbpage.c
@@ -4,7 +4,6 @@
  * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
  */
 
-#include <linux/config.h>
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
@@ -18,24 +17,128 @@
 #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;
 	pud_t *pud;
-	pmd_t *pmd;
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, addr);
 	pud = pud_alloc(mm, pgd, addr);
-	pmd = pmd_alloc(mm, pud, addr);
-
-	if (!pmd)
-		goto out;
+	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));
 
-	pte = (pte_t *) pmd;
-	if (!pte_none(*pte) && !pte_huge(*pte))
-		hugetlb_clean_stale_pgtable(pte);
-out:
 	return pte;
 }
 
@@ -46,23 +149,14 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	pmd_t *pmd = NULL;
 
 	pgd = pgd_offset(mm, addr);
-	pud = pud_offset(pgd, addr);
-	pmd = pmd_offset(pud, addr);
+	if (pgd_present(*pgd)) {
+		pud = pud_offset(pgd, addr);
+		if (pud_present(*pud))
+			pmd = pmd_offset(pud, addr);
+	}
 	return (pte_t *) pmd;
 }
 
-/*
- * This function checks for proper alignment of input addr and len parameters.
- */
-int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
-{
-	if (len & ~HPAGE_MASK)
-		return -EINVAL;
-	if (addr & ~HPAGE_MASK)
-		return -EINVAL;
-	return 0;
-}
-
 #if 0	/* This is just for testing */
 struct page *
 follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
@@ -127,17 +221,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 }
 #endif
 
-void hugetlb_clean_stale_pgtable(pte_t *pte)
-{
-	pmd_t *pmd = (pmd_t *) pte;
-	struct page *page;
-
-	page = pmd_page(*pmd);
-	pmd_clear(pmd);
-	dec_page_state(nr_page_table_pages);
-	page_cache_release(page);
-}
-
 /* x86_64 also uses this file */
 
 #ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA