Merge branch 'linus' into cpus4096

[linux-2.6] / arch / x86 / mm / hugetlbpage.c

diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 6c06d9c0488ec28c05d45c226d77c1050a7394a8..8f307d914c2ec860c3b9093796362e9c4719ab41 100644 (file)
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -15,6 +15,7 @@
 #include <asm/mman.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
 
 static unsigned long page_table_shareable(struct vm_area_struct *svma,
                                struct vm_area_struct *vma,
@@ -88,7 +89,7 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 
        spin_lock(&mm->page_table_lock);
        if (pud_none(*pud))
-               pud_populate(mm, pud, (unsigned long) spte & PAGE_MASK);
+               pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK));
        else
                put_page(virt_to_page(spte));
        spin_unlock(&mm->page_table_lock);
@@ -123,7 +124,8 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
        return 1;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+                       unsigned long addr, unsigned long sz)
 {
        pgd_t *pgd;
        pud_t *pud;
@@ -132,9 +134,14 @@ 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_none(*pud))
-                       huge_pmd_share(mm, addr, pud);
-               pte = (pte_t *) pmd_alloc(mm, pud, addr);
+               if (sz == PUD_SIZE) {
+                       pte = (pte_t *)pud;
+               } else {
+                       BUG_ON(sz != PMD_SIZE);
+                       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));
 
@@ -150,8 +157,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
        pgd = pgd_offset(mm, addr);
        if (pgd_present(*pgd)) {
                pud = pud_offset(pgd, addr);
-               if (pud_present(*pud))
+               if (pud_present(*pud)) {
+                       if (pud_large(*pud))
+                               return (pte_t *)pud;
                        pmd = pmd_offset(pud, addr);
+               }
        }
        return (pte_t *) pmd;
 }
@@ -177,7 +187,7 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 
        page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
 
-       WARN_ON(!PageCompound(page));
+       WARN_ON(!PageHead(page));
 
        return page;
 }
@@ -187,6 +197,11 @@ int pmd_huge(pmd_t pmd)
        return 0;
 }
 
+int pud_huge(pud_t pud)
+{
+       return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
                pmd_t *pmd, int write)
@@ -207,6 +222,11 @@ int pmd_huge(pmd_t pmd)
        return !!(pmd_val(pmd) & _PAGE_PSE);
 }
 
+int pud_huge(pud_t pud)
+{
+       return !!(pud_val(pud) & _PAGE_PSE);
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
                pmd_t *pmd, int write)
@@ -215,9 +235,22 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 
        page = pte_page(*(pte_t *)pmd);
        if (page)
-               page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
+               page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+       return page;
+}
+
+struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+               pud_t *pud, int write)
+{
+       struct page *page;
+
+       page = pte_page(*(pte_t *)pud);
+       if (page)
+               page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
        return page;
 }
+
 #endif
 
 /* x86_64 also uses this file */
@@ -227,6 +260,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
                unsigned long addr, unsigned long len,
                unsigned long pgoff, unsigned long flags)
 {
+       struct hstate *h = hstate_file(file);
        struct mm_struct *mm = current->mm;
        struct vm_area_struct *vma;
        unsigned long start_addr;
@@ -239,7 +273,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
        }
 
 full_search:
-       addr = ALIGN(start_addr, HPAGE_SIZE);
+       addr = ALIGN(start_addr, huge_page_size(h));
 
        for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
                /* At this point:  (!vma || addr < vma->vm_end). */
@@ -261,7 +295,7 @@ full_search:
                }
                if (addr + mm->cached_hole_size < vma->vm_start)
                        mm->cached_hole_size = vma->vm_start - addr;
-               addr = ALIGN(vma->vm_end, HPAGE_SIZE);
+               addr = ALIGN(vma->vm_end, huge_page_size(h));
        }
 }
 
@@ -269,6 +303,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
                unsigned long addr0, unsigned long len,
                unsigned long pgoff, unsigned long flags)
 {
+       struct hstate *h = hstate_file(file);
        struct mm_struct *mm = current->mm;
        struct vm_area_struct *vma, *prev_vma;
        unsigned long base = mm->mmap_base, addr = addr0;
@@ -289,7 +324,7 @@ try_again:
                goto fail;
 
        /* either no address requested or cant fit in requested address hole */
-       addr = (mm->free_area_cache - len) & HPAGE_MASK;
+       addr = (mm->free_area_cache - len) & huge_page_mask(h);
        do {
                /*
                 * Lookup failure means no vma is above this address,
@@ -320,7 +355,7 @@ try_again:
                        largest_hole = vma->vm_start - addr;
 
                /* try just below the current vma->vm_start */
-               addr = (vma->vm_start - len) & HPAGE_MASK;
+               addr = (vma->vm_start - len) & huge_page_mask(h);
        } while (len <= vma->vm_start);
 
 fail:
@@ -358,22 +393,23 @@ unsigned long
 hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
                unsigned long len, unsigned long pgoff, unsigned long flags)
 {
+       struct hstate *h = hstate_file(file);
        struct mm_struct *mm = current->mm;
        struct vm_area_struct *vma;
 
-       if (len & ~HPAGE_MASK)
+       if (len & ~huge_page_mask(h))
                return -EINVAL;
        if (len > TASK_SIZE)
                return -ENOMEM;
 
        if (flags & MAP_FIXED) {
-               if (prepare_hugepage_range(addr, len))
+               if (prepare_hugepage_range(file, addr, len))
                        return -EINVAL;
                return addr;
        }
 
        if (addr) {
-               addr = ALIGN(addr, HPAGE_SIZE);
+               addr = ALIGN(addr, huge_page_size(h));
                vma = find_vma(mm, addr);
                if (TASK_SIZE - len >= addr &&
                    (!vma || addr + len <= vma->vm_start))
@@ -389,3 +425,20 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
 #endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/
 
+#ifdef CONFIG_X86_64
+static __init int setup_hugepagesz(char *opt)
+{
+       unsigned long ps = memparse(opt, &opt);
+       if (ps == PMD_SIZE) {
+               hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
+       } else if (ps == PUD_SIZE && cpu_has_gbpages) {
+               hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+       } else {
+               printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n",
+                       ps >> 20);
+               return 0;
+       }
+       return 1;
+}
+__setup("hugepagesz=", setup_hugepagesz);
+#endif