X-Git-Url: http://git.rot13.org/?a=blobdiff_plain;f=mm%2Fmmap.c;h=84f997da78d70e607578afac5a87b64362b12558;hb=4f44d8ba09280a7f0887ab60277940d6c72f2b43;hp=e66a0b524affef544588a8c4f8a92d3473b79a34;hpb=48c068e0f49b3c507cbd1c332f4acdd5fc193040;p=powerpc.git

diff --git a/mm/mmap.c b/mm/mmap.c
index e66a0b524a..84f997da78 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -64,6 +64,13 @@ pgprot_t protection_map[16] = {
 	__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
 };
 
+pgprot_t vm_get_page_prot(unsigned long vm_flags)
+{
+	return protection_map[vm_flags &
+				(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)];
+}
+EXPORT_SYMBOL(vm_get_page_prot);
+
 int sysctl_overcommit_memory = OVERCOMMIT_GUESS;  /* heuristic overcommit */
 int sysctl_overcommit_ratio = 50;	/* default is 50% */
 int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
@@ -109,7 +116,7 @@ int __vm_enough_memory(long pages, int cap_sys_admin)
 		 * which are reclaimable, under pressure.  The dentry
 		 * cache and most inode caches should fall into this
 		 */
-		free += atomic_read(&slab_reclaim_pages);
+		free += global_page_state(NR_SLAB_RECLAIMABLE);
 
 		/*
 		 * Leave the last 3% for root
@@ -181,7 +188,7 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma,
 		struct file *file, struct address_space *mapping)
 {
 	if (vma->vm_flags & VM_DENYWRITE)
-		atomic_inc(&file->f_dentry->d_inode->i_writecount);
+		atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
 	if (vma->vm_flags & VM_SHARED)
 		mapping->i_mmap_writable--;
 
@@ -292,6 +299,8 @@ static int browse_rb(struct rb_root *root)
 			printk("vm_end %lx < vm_start %lx\n", vma->vm_end, vma->vm_start);
 		i++;
 		pn = nd;
+		prev = vma->vm_start;
+		pend = vma->vm_end;
 	}
 	j = 0;
 	for (nd = pn; nd; nd = rb_prev(nd)) {
@@ -392,7 +401,7 @@ static inline void __vma_link_file(struct vm_area_struct *vma)
 		struct address_space *mapping = file->f_mapping;
 
 		if (vma->vm_flags & VM_DENYWRITE)
-			atomic_dec(&file->f_dentry->d_inode->i_writecount);
+			atomic_dec(&file->f_path.dentry->d_inode->i_writecount);
 		if (vma->vm_flags & VM_SHARED)
 			mapping->i_mmap_writable++;
 
@@ -893,17 +902,6 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 	int accountable = 1;
 	unsigned long charged = 0, reqprot = prot;
 
-	if (file) {
-		if (is_file_hugepages(file))
-			accountable = 0;
-
-		if (!file->f_op || !file->f_op->mmap)
-			return -ENODEV;
-
-		if ((prot & PROT_EXEC) &&
-		    (file->f_vfsmnt->mnt_flags & MNT_NOEXEC))
-			return -EPERM;
-	}
 	/*
 	 * Does the application expect PROT_READ to imply PROT_EXEC?
 	 *
@@ -911,7 +909,7 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 	 *  mounted, in which case we dont add PROT_EXEC.)
 	 */
 	if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
-		if (!(file && (file->f_vfsmnt->mnt_flags & MNT_NOEXEC)))
+		if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC)))
 			prot |= PROT_EXEC;
 
 	if (!len)
@@ -964,7 +962,7 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 			return -EAGAIN;
 	}
 
-	inode = file ? file->f_dentry->d_inode : NULL;
+	inode = file ? file->f_path.dentry->d_inode : NULL;
 
 	if (file) {
 		switch (flags & MAP_TYPE) {
@@ -993,6 +991,16 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 		case MAP_PRIVATE:
 			if (!(file->f_mode & FMODE_READ))
 				return -EACCES;
+			if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
+				if (vm_flags & VM_EXEC)
+					return -EPERM;
+				vm_flags &= ~VM_MAYEXEC;
+			}
+			if (is_file_hugepages(file))
+				accountable = 0;
+
+			if (!file->f_op || !file->f_op->mmap)
+				return -ENODEV;
 			break;
 
 		default:
@@ -1098,12 +1106,6 @@ munmap_back:
 			goto free_vma;
 	}
 
-	/* Don't make the VMA automatically writable if it's shared, but the
-	 * backer wishes to know when pages are first written to */
-	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
-		vma->vm_page_prot =
-			protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC)];
-
 	/* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform
 	 * shmem_zero_setup (perhaps called through /dev/zero's ->mmap)
 	 * that memory reservation must be checked; but that reservation
@@ -1121,6 +1123,10 @@ munmap_back:
 	pgoff = vma->vm_pgoff;
 	vm_flags = vma->vm_flags;
 
+	if (vma_wants_writenotify(vma))
+		vma->vm_page_prot =
+			protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC)];
+
 	if (!file || !vma_merge(mm, prev, addr, vma->vm_end,
 			vma->vm_flags, NULL, file, pgoff, vma_policy(vma))) {
 		file = vma->vm_file;
@@ -1375,7 +1381,7 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		 * Check if the given range is hugepage aligned, and
 		 * can be made suitable for hugepages.
 		 */
-		ret = prepare_hugepage_range(addr, len);
+		ret = prepare_hugepage_range(addr, len, pgoff);
 	} else {
 		/*
 		 * Ensure that a normal request is not falling in a
@@ -1473,6 +1479,7 @@ static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, un
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct rlimit *rlim = current->signal->rlim;
+	unsigned long new_start;
 
 	/* address space limit tests */
 	if (!may_expand_vm(mm, grow))
@@ -1492,6 +1499,12 @@ static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, un
 			return -ENOMEM;
 	}
 
+	/* Check to ensure the stack will not grow into a hugetlb-only region */
+	new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start :
+			vma->vm_end - size;
+	if (is_hugepage_only_range(vma->vm_mm, new_start, size))
+		return -EFAULT;
+
 	/*
 	 * Overcommit..  This must be the final test, as it will
 	 * update security statistics.
@@ -1732,7 +1745,7 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 	if (mm->map_count >= sysctl_max_map_count)
 		return -ENOMEM;
 
-	new = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
@@ -1876,6 +1889,9 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
 	if ((addr + len) > TASK_SIZE || (addr + len) < addr)
 		return -EINVAL;
 
+	if (is_hugepage_only_range(mm, addr, len))
+		return -EINVAL;
+
 	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
 	error = arch_mmap_check(addr, len, flags);
@@ -2050,7 +2066,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		    vma_start < new_vma->vm_end)
 			*vmap = new_vma;
 	} else {
-		new_vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+		new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 		if (new_vma) {
 			*new_vma = *vma;
 			pol = mpol_copy(vma_policy(vma));
@@ -2087,3 +2103,75 @@ int may_expand_vm(struct mm_struct *mm, unsigned long npages)
 		return 0;
 	return 1;
 }
+
+
+static struct page *special_mapping_nopage(struct vm_area_struct *vma,
+					   unsigned long address, int *type)
+{
+	struct page **pages;
+
+	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+
+	address -= vma->vm_start;
+	for (pages = vma->vm_private_data; address > 0 && *pages; ++pages)
+		address -= PAGE_SIZE;
+
+	if (*pages) {
+		struct page *page = *pages;
+		get_page(page);
+		return page;
+	}
+
+	return NOPAGE_SIGBUS;
+}
+
+/*
+ * Having a close hook prevents vma merging regardless of flags.
+ */
+static void special_mapping_close(struct vm_area_struct *vma)
+{
+}
+
+static struct vm_operations_struct special_mapping_vmops = {
+	.close = special_mapping_close,
+	.nopage	= special_mapping_nopage,
+};
+
+/*
+ * Called with mm->mmap_sem held for writing.
+ * Insert a new vma covering the given region, with the given flags.
+ * Its pages are supplied by the given array of struct page *.
+ * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated.
+ * The region past the last page supplied will always produce SIGBUS.
+ * The array pointer and the pages it points to are assumed to stay alive
+ * for as long as this mapping might exist.
+ */
+int install_special_mapping(struct mm_struct *mm,
+			    unsigned long addr, unsigned long len,
+			    unsigned long vm_flags, struct page **pages)
+{
+	struct vm_area_struct *vma;
+
+	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	if (unlikely(vma == NULL))
+		return -ENOMEM;
+
+	vma->vm_mm = mm;
+	vma->vm_start = addr;
+	vma->vm_end = addr + len;
+
+	vma->vm_flags = vm_flags | mm->def_flags;
+	vma->vm_page_prot = protection_map[vma->vm_flags & 7];
+
+	vma->vm_ops = &special_mapping_vmops;
+	vma->vm_private_data = pages;
+
+	if (unlikely(insert_vm_struct(mm, vma))) {
+		kmem_cache_free(vm_area_cachep, vma);
+		return -ENOMEM;
+	}
+
+	mm->total_vm += len >> PAGE_SHIFT;
+
+	return 0;
+}