X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=arch%2Fia64%2Fmm%2Fhugetlbpage.c;h=eee5c1cfbe3223c1376c4d0a9239d4def44be824;hb=16c70f8c1b54b61c3b951b6fb220df250fe09b32;hp=c724358125863c7e68231040503753613d231a27;hpb=9213980e6a70d8473e0ffd4b39ab5b6caaba9ff5;p=linux-2.6.git

diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index c72435812..eee5c1cfb 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -8,7 +8,6 @@
  * Feb, 2004: dynamic hugetlb page size via boot parameter
  */
 
-#include <linux/config.h>
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
@@ -24,34 +23,42 @@
 
 unsigned int hpage_shift=HPAGE_SHIFT_DEFAULT;
 
-static pte_t *
+pte_t *
 huge_pte_alloc (struct mm_struct *mm, unsigned long addr)
 {
 	unsigned long taddr = htlbpage_to_page(addr);
 	pgd_t *pgd;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, taddr);
-	pmd = pmd_alloc(mm, pgd, taddr);
-	if (pmd)
-		pte = pte_alloc_map(mm, pmd, taddr);
+	pud = pud_alloc(mm, pgd, taddr);
+	if (pud) {
+		pmd = pmd_alloc(mm, pud, taddr);
+		if (pmd)
+			pte = pte_alloc_map(mm, pmd, taddr);
+	}
 	return pte;
 }
 
-static pte_t *
+pte_t *
 huge_pte_offset (struct mm_struct *mm, unsigned long addr)
 {
 	unsigned long taddr = htlbpage_to_page(addr);
 	pgd_t *pgd;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, taddr);
 	if (pgd_present(*pgd)) {
-		pmd = pmd_offset(pgd, taddr);
-		if (pmd_present(*pmd))
-			pte = pte_offset_map(pmd, taddr);
+		pud = pud_offset(pgd, taddr);
+		if (pud_present(*pud)) {
+			pmd = pmd_offset(pud, taddr);
+			if (pmd_present(*pmd))
+				pte = pte_offset_map(pmd, taddr);
+		}
 	}
 
 	return pte;
@@ -59,110 +66,28 @@ huge_pte_offset (struct mm_struct *mm, unsigned long addr)
 
 #define mk_pte_huge(entry) { pte_val(entry) |= _PAGE_P; }
 
-static void
-set_huge_pte (struct mm_struct *mm, struct vm_area_struct *vma,
-	      struct page *page, pte_t * page_table, int write_access)
-{
-	pte_t entry;
-
-	// mm->rss += (HPAGE_SIZE / PAGE_SIZE);
-	vx_rsspages_add(mm, HPAGE_SIZE / PAGE_SIZE);
-	if (write_access) {
-		entry =
-		    pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
-	} else
-		entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));
-	entry = pte_mkyoung(entry);
-	mk_pte_huge(entry);
-	set_pte(page_table, entry);
-	return;
-}
 /*
- * This function checks for proper alignment of input addr and len parameters.
+ * Don't actually need to do any preparation, but need to make sure
+ * the address is in the right region.
  */
-int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
+int prepare_hugepage_range(unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;
 	if (addr & ~HPAGE_MASK)
 		return -EINVAL;
-	if (REGION_NUMBER(addr) != REGION_HPAGE)
+	if (REGION_NUMBER(addr) != RGN_HPAGE)
 		return -EINVAL;
 
 	return 0;
 }
 
-int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
-			struct vm_area_struct *vma)
-{
-	pte_t *src_pte, *dst_pte, entry;
-	struct page *ptepage;
-	unsigned long addr = vma->vm_start;
-	unsigned long end = vma->vm_end;
-
-	while (addr < end) {
-		dst_pte = huge_pte_alloc(dst, addr);
-		if (!dst_pte)
-			goto nomem;
-		src_pte = huge_pte_offset(src, addr);
-		entry = *src_pte;
-		ptepage = pte_page(entry);
-		get_page(ptepage);
-		set_pte(dst_pte, entry);
-		// dst->rss += (HPAGE_SIZE / PAGE_SIZE);
-		vx_rsspages_add(dst, HPAGE_SIZE / PAGE_SIZE);
-		addr += HPAGE_SIZE;
-	}
-	return 0;
-nomem:
-	return -ENOMEM;
-}
-
-int
-follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
-		    struct page **pages, struct vm_area_struct **vmas,
-		    unsigned long *st, int *length, int i)
-{
-	pte_t *ptep, pte;
-	unsigned long start = *st;
-	unsigned long pstart;
-	int len = *length;
-	struct page *page;
-
-	do {
-		pstart = start & HPAGE_MASK;
-		ptep = huge_pte_offset(mm, start);
-		pte = *ptep;
-
-back1:
-		page = pte_page(pte);
-		if (pages) {
-			page += ((start & ~HPAGE_MASK) >> PAGE_SHIFT);
-			get_page(page);
-			pages[i] = page;
-		}
-		if (vmas)
-			vmas[i] = vma;
-		i++;
-		len--;
-		start += PAGE_SIZE;
-		if (((start & HPAGE_MASK) == pstart) && len &&
-				(start < vma->vm_end))
-			goto back1;
-	} while (len && start < vma->vm_end);
-	*length = len;
-	*st = start;
-	return i;
-}
-
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long addr, int write)
 {
 	struct page *page;
 	pte_t *ptep;
 
-	if (! mm->used_hugetlb)
-		return ERR_PTR(-EINVAL);
-	if (REGION_NUMBER(addr) != REGION_HPAGE)
+	if (REGION_NUMBER(addr) != RGN_HPAGE)
 		return ERR_PTR(-EINVAL);
 
 	ptep = huge_pte_offset(mm, addr);
@@ -182,133 +107,29 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int wri
 	return NULL;
 }
 
-/*
- * Same as generic free_pgtables(), except constant PGDIR_* and pgd_offset
- * are hugetlb region specific.
- */
-void hugetlb_free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *prev,
-	unsigned long start, unsigned long end)
+void hugetlb_free_pgd_range(struct mmu_gather **tlb,
+			unsigned long addr, unsigned long end,
+			unsigned long floor, unsigned long ceiling)
 {
-	unsigned long first = start & HUGETLB_PGDIR_MASK;
-	unsigned long last = end + HUGETLB_PGDIR_SIZE - 1;
-	unsigned long start_index, end_index;
-	struct mm_struct *mm = tlb->mm;
-
-	if (!prev) {
-		prev = mm->mmap;
-		if (!prev)
-			goto no_mmaps;
-		if (prev->vm_end > start) {
-			if (last > prev->vm_start)
-				last = prev->vm_start;
-			goto no_mmaps;
-		}
-	}
-	for (;;) {
-		struct vm_area_struct *next = prev->vm_next;
-
-		if (next) {
-			if (next->vm_start < start) {
-				prev = next;
-				continue;
-			}
-			if (last > next->vm_start)
-				last = next->vm_start;
-		}
-		if (prev->vm_end > first)
-			first = prev->vm_end + HUGETLB_PGDIR_SIZE - 1;
-		break;
-	}
-no_mmaps:
-	if (last < first)	/* for arches with discontiguous pgd indices */
-		return;
 	/*
-	 * If the PGD bits are not consecutive in the virtual address, the
-	 * old method of shifting the VA >> by PGDIR_SHIFT doesn't work.
+	 * This is called to free hugetlb page tables.
+	 *
+	 * The offset of these addresses from the base of the hugetlb
+	 * region must be scaled down by HPAGE_SIZE/PAGE_SIZE so that
+	 * the standard free_pgd_range will free the right page tables.
+	 *
+	 * If floor and ceiling are also in the hugetlb region, they
+	 * must likewise be scaled down; but if outside, left unchanged.
 	 */
 
-	start_index = pgd_index(htlbpage_to_page(first));
-	end_index = pgd_index(htlbpage_to_page(last));
-
-	if (end_index > start_index) {
-		clear_page_tables(tlb, start_index, end_index - start_index);
-	}
-}
-
-void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	unsigned long address;
-	pte_t *pte;
-	struct page *page;
-
-	BUG_ON(start & (HPAGE_SIZE - 1));
-	BUG_ON(end & (HPAGE_SIZE - 1));
+	addr = htlbpage_to_page(addr);
+	end  = htlbpage_to_page(end);
+	if (REGION_NUMBER(floor) == RGN_HPAGE)
+		floor = htlbpage_to_page(floor);
+	if (REGION_NUMBER(ceiling) == RGN_HPAGE)
+		ceiling = htlbpage_to_page(ceiling);
 
-	for (address = start; address < end; address += HPAGE_SIZE) {
-		pte = huge_pte_offset(mm, address);
-		if (pte_none(*pte))
-			continue;
-		page = pte_page(*pte);
-		put_page(page);
-		pte_clear(pte);
-	}
-	// mm->rss -= (end - start) >> PAGE_SHIFT;
-	vx_rsspages_sub(mm, (end - start) >> PAGE_SHIFT);
-	flush_tlb_range(vma, start, end);
-}
-
-int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long addr;
-	int ret = 0;
-
-	BUG_ON(vma->vm_start & ~HPAGE_MASK);
-	BUG_ON(vma->vm_end & ~HPAGE_MASK);
-
-	spin_lock(&mm->page_table_lock);
-	for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
-		unsigned long idx;
-		pte_t *pte = huge_pte_alloc(mm, addr);
-		struct page *page;
-
-		if (!pte) {
-			ret = -ENOMEM;
-			goto out;
-		}
-		if (!pte_none(*pte))
-			continue;
-
-		idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
-			+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
-		page = find_get_page(mapping, idx);
-		if (!page) {
-			/* charge the fs quota first */
-			if (hugetlb_get_quota(mapping)) {
-				ret = -ENOMEM;
-				goto out;
-			}
-			page = alloc_huge_page();
-			if (!page) {
-				hugetlb_put_quota(mapping);
-				ret = -ENOMEM;
-				goto out;
-			}
-			ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC);
-			if (! ret) {
-				unlock_page(page);
-			} else {
-				hugetlb_put_quota(mapping);
-				free_huge_page(page);
-				goto out;
-			}
-		}
-		set_huge_pte(mm, vma, page, pte, vma->vm_flags & VM_WRITE);
-	}
-out:
-	spin_unlock(&mm->page_table_lock);
-	return ret;
+	free_pgd_range(tlb, addr, end, floor, ceiling);
 }
 
 unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
@@ -320,8 +141,8 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, u
 		return -ENOMEM;
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;
-	/* This code assumes that REGION_HPAGE != 0. */
-	if ((REGION_NUMBER(addr) != REGION_HPAGE) || (addr & (HPAGE_SIZE - 1)))
+	/* This code assumes that RGN_HPAGE != 0. */
+	if ((REGION_NUMBER(addr) != RGN_HPAGE) || (addr & (HPAGE_SIZE - 1)))
 		addr = HPAGE_REGION_BASE;
 	else
 		addr = ALIGN(addr, HPAGE_SIZE);