[PATCH v3 2/7] shm: add sealing API

@@ -21,6 +21,7 @@
 #include <linux/rcupdate.h>
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
+#include <linux/shmem_fs.h>
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>

@@ -336,6 +337,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_GETPIPE_SZ:
 		err = pipe_fcntl(filp, cmd, arg);
 		break;
+	case F_ADD_SEALS:
+	case F_GET_SEALS:
+		err = shmem_fcntl(filp, cmd, arg);
+		break;
 	default:
 		break;
 	}

@@ -1,6 +1,7 @@
 #ifndef __SHMEM_FS_H
 #define __SHMEM_FS_H
 
+#include <linux/file.h>
 #include <linux/swap.h>
 #include <linux/mempolicy.h>
 #include <linux/pagemap.h>

@@ -11,6 +12,7 @@
 
 struct shmem_inode_info {
 	spinlock_t		lock;
+	unsigned int		seals;		/* shmem seals */
 	unsigned long		flags;
 	unsigned long		alloced;	/* data pages alloced to file */
 	union {

@@ -65,4 +67,19 @@ static inline struct page *shmem_read_mapping_page(
 					mapping_gfp_mask(mapping));
 }
 
+#ifdef CONFIG_TMPFS
+
+extern int shmem_add_seals(struct file *file, unsigned int seals);
+extern int shmem_get_seals(struct file *file);
+extern long shmem_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
+
+#else
+
+static inline long shmem_fcntl(struct file *f, unsigned int c, unsigned long a)
+{
+	return -EINVAL;
+}
+
+#endif
+
 #endif

@@ -28,6 +28,21 @@
 #define F_GETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 8)
 
 /*
+ * Set/Get seals
+ */
+#define F_ADD_SEALS	(F_LINUX_SPECIFIC_BASE + 9)
+#define F_GET_SEALS	(F_LINUX_SPECIFIC_BASE + 10)
+
+/*
+ * Types of seals
+ */
+#define F_SEAL_SEAL	0x0001	/* prevent further seals from being set */
+#define F_SEAL_SHRINK	0x0002	/* prevent file from shrinking */
+#define F_SEAL_GROW	0x0004	/* prevent file from growing */
+#define F_SEAL_WRITE	0x0008	/* prevent writes */
+/* (1U << 31) is reserved for signed error codes */
+
+/*
  * Types of directory notifications that may be requested.
  */
 #define DN_ACCESS	0x00000001	/* File accessed */

@@ -66,6 +66,7 @@ static struct vfsmount *shm_mnt;
 #include <linux/highmem.h>
 #include <linux/seq_file.h>
 #include <linux/magic.h>
+#include <linux/fcntl.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>

@@ -531,16 +532,23 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range);
 static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	loff_t oldsize = inode->i_size;
+	loff_t newsize = attr->ia_size;
 	int error;
 
 	error = inode_change_ok(inode, attr);
 	if (error)
 		return error;
 
-	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
-		loff_t oldsize = inode->i_size;
-		loff_t newsize = attr->ia_size;
+	/* protected by i_mutex */
+	if (attr->ia_valid & ATTR_SIZE) {
+		if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
+		    (newsize > oldsize && (info->seals & F_SEAL_GROW)))
+			return -EPERM;
+	}
 
+	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
 		if (newsize != oldsize) {
 			i_size_write(inode, newsize);
 			inode->i_ctime = inode->i_mtime = CURRENT_TIME;

@@ -1315,6 +1323,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		info = SHMEM_I(inode);
 		memset(info, 0, (char *)inode - (char *)info);
 		spin_lock_init(&info->lock);
+		info->seals = F_SEAL_SEAL;
 		info->flags = flags & VM_NORESERVE;
 		INIT_LIST_HEAD(&info->swaplist);
 		simple_xattrs_init(&info->xattrs);

@@ -1374,7 +1383,15 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 {
 	int ret;
 	struct inode *inode = mapping->host;
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+
+	/* i_mutex is held by caller */
+	if (info->seals & F_SEAL_WRITE)
+		return -EPERM;
+	if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size)
+		return -EPERM;
+
 	ret = shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
 	if (ret == 0 && *pagep)
 		init_page_accessed(*pagep);

@@ -1715,11 +1732,166 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 	return offset;
 }
 
+/*
+ * Setting SEAL_WRITE requires us to verify there's no pending writer. However,
+ * via get_user_pages(), drivers might have some pending I/O without any active
+ * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all pages
+ * and see whether it has an elevated ref-count. If so, we abort.
+ * The caller must guarantee that no new user will acquire writable references
+ * to those pages to avoid races.
+ */
+static int shmem_test_for_pins(struct address_space *mapping)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	pgoff_t start;
+	struct page *page;
+	int error;
+
+	/* flush additional refs in lru_add early */
+	lru_add_drain_all();
+
+	error = 0;
+	start = 0;
+	rcu_read_lock();
+
+restart:
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+		page = radix_tree_deref_slot(slot);
+		if (!page || radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page))
+				goto restart;
+		} else if (page_count(page) - page_mapcount(page) > 1) {
+			error = -EBUSY;
+			break;
+		}
+
+		if (need_resched()) {
+			cond_resched_rcu();
+			start = iter.index + 1;
+			goto restart;
+		}
+	}
+	rcu_read_unlock();
+
+	return error;
+}
+
+#define F_ALL_SEALS (F_SEAL_SEAL | \
+		     F_SEAL_SHRINK | \
+		     F_SEAL_GROW | \
+		     F_SEAL_WRITE)
+
+int shmem_add_seals(struct file *file, unsigned int seals)
+{
+	struct dentry *dentry = file->f_path.dentry;
+	struct inode *inode = dentry->d_inode;
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	int error;
+
+	/*
+	 * SEALING
+	 * Sealing allows multiple parties to share a shmem-file but restrict
+	 * access to a specific subset of file operations. Seals can only be
+	 * added, but never removed. This way, mutually untrusted parties can
+	 * share common memory regions with a well-defined policy. A malicious
+	 * peer can thus never perform unwanted operations on a shared object.
+	 *
+	 * Seals are only supported on special shmem-files and always affect
+	 * the whole underlying inode. Once a seal is set, it may prevent some
+	 * kinds of access to the file. Currently, the following seals are
+	 * defined:
+	 *   SEAL_SEAL: Prevent further seals from being set on this file
+	 *   SEAL_SHRINK: Prevent the file from shrinking
+	 *   SEAL_GROW: Prevent the file from growing
+	 *   SEAL_WRITE: Prevent write access to the file
+	 *
+	 * As we don't require any trust relationship between two parties, we
+	 * must prevent seals from being removed. Therefore, sealing a file
+	 * only adds a given set of seals to the file, it never touches
+	 * existing seals. Furthermore, the "setting seals"-operation can be
+	 * sealed itself, which basically prevents any further seal from being
+	 * added.
+	 *
+	 * Semantics of sealing are only defined on volatile files. Only
+	 * anonymous shmem files support sealing. More importantly, seals are
+	 * never written to disk. Therefore, there's no plan to support it on
+	 * other file types.
+	 */
+
+	if (file->f_op != &shmem_file_operations)
+		return -EINVAL;
+	if (!(file->f_mode & FMODE_WRITE))
+		return -EINVAL;
+	if (seals & ~(unsigned int)F_ALL_SEALS)
+		return -EINVAL;
+
+	mutex_lock(&inode->i_mutex);
+
+	if (info->seals & F_SEAL_SEAL) {
+		error = -EPERM;
+		goto unlock;
+	}
+
+	if ((seals & F_SEAL_WRITE) && !(info->seals & F_SEAL_WRITE)) {
+		error = mapping_deny_writable(file->f_mapping);
+		if (error)
+			goto unlock;
+
+		error = shmem_test_for_pins(file->f_mapping);
+		if (error) {
+			mapping_allow_writable(file->f_mapping);
+			goto unlock;
+		}
+	}
+
+	info->seals |= seals;
+	error = 0;
+
+unlock:
+	mutex_unlock(&inode->i_mutex);
+	return error;
+}
+EXPORT_SYMBOL_GPL(shmem_add_seals);
+
+int shmem_get_seals(struct file *file)
+{
+	if (file->f_op != &shmem_file_operations)
+		return -EINVAL;
+
+	return SHMEM_I(file_inode(file))->seals & F_ALL_SEALS;
+}
+EXPORT_SYMBOL_GPL(shmem_get_seals);
+
+long shmem_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	long error;
+
+	switch (cmd) {
+	case F_ADD_SEALS:
+		/* disallow upper 32bit */
+		if (arg >> 32)
+			return -EINVAL;
+
+		error = shmem_add_seals(file, arg);
+		break;
+	case F_GET_SEALS:
+		error = shmem_get_seals(file);
+		break;
+	default:
+		error = -EINVAL;
+		break;
+	}
+
+	return error;
+}
+
 static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 							 loff_t len)
 {
 	struct inode *inode = file_inode(file);
 	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct shmem_falloc shmem_falloc;
 	pgoff_t start, index, end;
 	int error;

@@ -1731,6 +1903,12 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		loff_t unmap_start = round_up(offset, PAGE_SIZE);
 		loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
 
+		/* protected by i_mutex */
+		if (info->seals & F_SEAL_WRITE) {
+			error = -EPERM;
+			goto out;
+		}
+
 		if ((u64)unmap_end > (u64)unmap_start)
 			unmap_mapping_range(mapping, unmap_start,
 					    1 + unmap_end - unmap_start, 0);

@@ -1745,6 +1923,11 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 	if (error)
 		goto out;
 
+	if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) {
+		error = -EPERM;
+		goto out;
+	}
+
 	start = offset >> PAGE_CACHE_SHIFT;
 	end = (offset + len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	/* Try to avoid a swapstorm if len is impossible to satisfy */