2 files changed, 108 insertions, 22 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 8c1cef3bb677..8c41315a6e42 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -100,9 +100,6 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
         loff_t len, vma_len;
         int ret;
 
-        if ((vma->vm_flags & (VM_MAYSHARE | VM_WRITE)) == VM_WRITE)
-                return -EINVAL;
-
         if (vma->vm_pgoff & (HPAGE_SIZE / PAGE_SIZE - 1))
                 return -EINVAL;
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index cf8225108b2f..da8a211414c9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -261,11 +261,12 @@ struct vm_operations_struct hugetlb_vm_ops = {
         .nopage = hugetlb_nopage,
 };
 
-static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page)
+static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
+                                int writable)
 {
         pte_t entry;
 
-        if (vma->vm_flags & VM_WRITE) {
+        if (writable) {
                 entry =
                     pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
         } else {
@@ -277,12 +278,27 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page)
         return entry;
 }
 
+static void set_huge_ptep_writable(struct vm_area_struct *vma,
+                                   unsigned long address, pte_t *ptep)
+{
+        pte_t entry;
+
+        entry = pte_mkwrite(pte_mkdirty(*ptep));
+        ptep_set_access_flags(vma, address, ptep, entry, 1);
+        update_mmu_cache(vma, address, entry);
+        lazy_mmu_prot_update(entry);
+}
+
+
 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;
+        int cow;
+
+        cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
         for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
                 src_pte = huge_pte_offset(src, addr);
@@ -294,6 +310,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
                 spin_lock(&dst->page_table_lock);
                 spin_lock(&src->page_table_lock);
                 if (!pte_none(*src_pte)) {
+                        if (cow)
+                                ptep_set_wrprotect(src, addr, src_pte);
                         entry = *src_pte;
                         ptepage = pte_page(entry);
                         get_page(ptepage);
@@ -346,7 +364,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 }
 
 static struct page *find_or_alloc_huge_page(struct address_space *mapping,
-                                                unsigned long idx)
+                                unsigned long idx, int shared)
 {
         struct page *page;
         int err;
@@ -364,26 +382,80 @@ retry:
                 goto out;
         }
 
-        err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
-        if (err) {
-                put_page(page);
-                hugetlb_put_quota(mapping);
-                if (err == -EEXIST)
-                        goto retry;
-                page = NULL;
+        if (shared) {
+                err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
+                if (err) {
+                        put_page(page);
+                        hugetlb_put_quota(mapping);
+                        if (err == -EEXIST)
+                                goto retry;
+                        page = NULL;
+                }
+        } else {
+                /* Caller expects a locked page */
+                lock_page(page);
         }
 out:
         return page;
 }
 
+static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
+                        unsigned long address, pte_t *ptep, pte_t pte)
+{
+        struct page *old_page, *new_page;
+        int i, avoidcopy;
+
+        old_page = pte_page(pte);
+
+        /* If no-one else is actually using this page, avoid the copy
+         * and just make the page writable */
+        avoidcopy = (page_count(old_page) == 1);
+        if (avoidcopy) {
+                set_huge_ptep_writable(vma, address, ptep);
+                return VM_FAULT_MINOR;
+        }
+
+        page_cache_get(old_page);
+        new_page = alloc_huge_page();
+
+        if (!new_page) {
+                page_cache_release(old_page);
+
+                /* Logically this is OOM, not a SIGBUS, but an OOM
+                 * could cause the kernel to go killing other
+                 * processes which won't help the hugepage situation
+                 * at all (?) */
+                return VM_FAULT_SIGBUS;
+        }
+
+        spin_unlock(&mm->page_table_lock);
+        for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++)
+                copy_user_highpage(new_page + i, old_page + i,
+                                   address + i*PAGE_SIZE);
+        spin_lock(&mm->page_table_lock);
+
+        ptep = huge_pte_offset(mm, address & HPAGE_MASK);
+        if (likely(pte_same(*ptep, pte))) {
+                /* Break COW */
+                set_huge_pte_at(mm, address, ptep,
+                                make_huge_pte(vma, new_page, 1));
+                /* Make the old page be freed below */
+                new_page = old_page;
+        }
+        page_cache_release(new_page);
+        page_cache_release(old_page);
+        return VM_FAULT_MINOR;
+}
+
 int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
-                        unsigned long address, pte_t *ptep)
+                        unsigned long address, pte_t *ptep, int write_access)
 {
         int ret = VM_FAULT_SIGBUS;
         unsigned long idx;
         unsigned long size;
         struct page *page;
         struct address_space *mapping;
+        pte_t new_pte;
 
         mapping = vma->vm_file->f_mapping;
         idx = ((address - vma->vm_start) >> HPAGE_SHIFT)
@@ -393,10 +465,13 @@ int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
          * Use page lock to guard against racing truncation
          * before we get page_table_lock.
          */
-        page = find_or_alloc_huge_page(mapping, idx);
+        page = find_or_alloc_huge_page(mapping, idx,
+                        vma->vm_flags & VM_SHARED);
         if (!page)
                 goto out;
 
+        BUG_ON(!PageLocked(page));
+
         spin_lock(&mm->page_table_lock);
         size = i_size_read(mapping->host) >> HPAGE_SHIFT;
         if (idx >= size)
@@ -407,7 +482,15 @@ int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 goto backout;
 
         add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE);
-        set_huge_pte_at(mm, address, ptep, make_huge_pte(vma, page));
+        new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
+                                && (vma->vm_flags & VM_SHARED)));
+        set_huge_pte_at(mm, address, ptep, new_pte);
+
+        if (write_access && !(vma->vm_flags & VM_SHARED)) {
+                /* Optimization, do the COW without a second fault */
+                ret = hugetlb_cow(mm, vma, address, ptep, new_pte);
+        }
+
         spin_unlock(&mm->page_table_lock);
         unlock_page(page);
 out:
@@ -426,6 +509,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 {
         pte_t *ptep;
         pte_t entry;
+        int ret;
 
         ptep = huge_pte_alloc(mm, address);
         if (!ptep)
@@ -433,13 +517,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
         entry = *ptep;
         if (pte_none(entry))
-                return hugetlb_no_page(mm, vma, address, ptep);
+                return hugetlb_no_page(mm, vma, address, ptep, write_access);
 
-        /*
-         * We could get here if another thread instantiated the pte
-         * before the test above.
-         */
-        return VM_FAULT_MINOR;
+        ret = VM_FAULT_MINOR;
+
+        spin_lock(&mm->page_table_lock);
+        /* Check for a racing update before calling hugetlb_cow */
+        if (likely(pte_same(entry, *ptep)))
+                if (write_access && !pte_write(entry))
+                        ret = hugetlb_cow(mm, vma, address, ptep, entry);
+        spin_unlock(&mm->page_table_lock);
+
+        return ret;
 }
 
 int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,