Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/viro/vfs

Pull more vfs updates from Al Viro:
 "Embarrassing braino fix + pipe page accounting + fixing an eyesore in
  find_filesystem() (checking that s1 is equal to prefix of s2 of given
  length can be done in many ways, but "compare strlen(s1) with length
  and then do strncmp()" is not a good one...)"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  [regression] fix braino in fs/dlm/user.c
  pipe: limit the per-user amount of pages allocated in pipes
  find_filesystem(): simplify comparison

Documentation/sysctl/fs.txt

@@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/fs:
 - nr_open
 - overflowuid
 - overflowgid
+- pipe-user-pages-hard
+- pipe-user-pages-soft
 - protected_hardlinks
 - protected_symlinks
 - suid_dumpable
@@ -159,6 +161,27 @@ The default is 65534.
 
 ==============================================================
 
+pipe-user-pages-hard:
+
+Maximum total number of pages a non-privileged user may allocate for pipes.
+Once this limit is reached, no new pipes may be allocated until usage goes
+below the limit again. When set to 0, no limit is applied, which is the default
+setting.
+
+==============================================================
+
+pipe-user-pages-soft:
+
+Maximum total number of pages a non-privileged user may allocate for pipes
+before the pipe size gets limited to a single page. Once this limit is reached,
+new pipes will be limited to a single page in size for this user in order to
+limit total memory usage, and trying to increase them using fcntl() will be
+denied until usage goes below the limit again. The default value allows to
+allocate up to 1024 pipes at their default size. When set to 0, no limit is
+applied.
+
+==============================================================
+
 protected_hardlinks:
 
 A long-standing class of security issues is the hardlink-based

fs/dlm/user.c

@@ -516,7 +516,7 @@ static ssize_t device_write(struct file *file, const char __user *buf,
 		return -EINVAL;
 
 	kbuf = memdup_user_nul(buf, count);
-	if (!IS_ERR(kbuf))
+	if (IS_ERR(kbuf))
 		return PTR_ERR(kbuf);
 
 	if (check_version(kbuf)) {

fs/filesystems.c

@@ -46,9 +46,9 @@ void put_filesystem(struct file_system_type *fs)
 static struct file_system_type **find_filesystem(const char *name, unsigned len)
 {
 	struct file_system_type **p;
-	for (p=&file_systems; *p; p=&(*p)->next)
-		if (strlen((*p)->name) == len &&
-		    strncmp((*p)->name, name, len) == 0)
+	for (p = &file_systems; *p; p = &(*p)->next)
+		if (strncmp((*p)->name, name, len) == 0 &&
+		    !(*p)->name[len])
 			break;
 	return p;
 }

fs/pipe.c

@@ -38,6 +38,12 @@ unsigned int pipe_max_size = 1048576;
  */
 unsigned int pipe_min_size = PAGE_SIZE;
 
+/* Maximum allocatable pages per user. Hard limit is unset by default, soft
+ * matches default values.
+ */
+unsigned long pipe_user_pages_hard;
+unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
+
 /*
  * We use a start+len construction, which provides full use of the 
  * allocated memory.
@@ -583,20 +589,49 @@ pipe_fasync(int fd, struct file *filp, int on)
 	return retval;
 }
 
+static void account_pipe_buffers(struct pipe_inode_info *pipe,
+                                 unsigned long old, unsigned long new)
+{
+	atomic_long_add(new - old, &pipe->user->pipe_bufs);
+}
+
+static bool too_many_pipe_buffers_soft(struct user_struct *user)
+{
+	return pipe_user_pages_soft &&
+	       atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_soft;
+}
+
+static bool too_many_pipe_buffers_hard(struct user_struct *user)
+{
+	return pipe_user_pages_hard &&
+	       atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_hard;
+}
+
 struct pipe_inode_info *alloc_pipe_info(void)
 {
 	struct pipe_inode_info *pipe;
 
 	pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
 	if (pipe) {
-		pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL);
+		unsigned long pipe_bufs = PIPE_DEF_BUFFERS;
+		struct user_struct *user = get_current_user();
+
+		if (!too_many_pipe_buffers_hard(user)) {
+			if (too_many_pipe_buffers_soft(user))
+				pipe_bufs = 1;
+			pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * pipe_bufs, GFP_KERNEL);
+		}
+
 		if (pipe->bufs) {
 			init_waitqueue_head(&pipe->wait);
 			pipe->r_counter = pipe->w_counter = 1;
-			pipe->buffers = PIPE_DEF_BUFFERS;
+			pipe->buffers = pipe_bufs;
+			pipe->user = user;
+			account_pipe_buffers(pipe, 0, pipe_bufs);
 			mutex_init(&pipe->mutex);
 			return pipe;
 		}
+		free_uid(user);
 		kfree(pipe);
 	}
 
@@ -607,6 +642,8 @@ void free_pipe_info(struct pipe_inode_info *pipe)
 {
 	int i;
 
+	account_pipe_buffers(pipe, pipe->buffers, 0);
+	free_uid(pipe->user);
 	for (i = 0; i < pipe->buffers; i++) {
 		struct pipe_buffer *buf = pipe->bufs + i;
 		if (buf->ops)
@@ -998,6 +1035,7 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
 			memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer));
 	}
 
+	account_pipe_buffers(pipe, pipe->buffers, nr_pages);
 	pipe->curbuf = 0;
 	kfree(pipe->bufs);
 	pipe->bufs = bufs;
@@ -1069,6 +1107,11 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) {
 			ret = -EPERM;
 			goto out;
+		} else if ((too_many_pipe_buffers_hard(pipe->user) ||
+			    too_many_pipe_buffers_soft(pipe->user)) &&
+		           !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) {
+			ret = -EPERM;
+			goto out;
 		}
 		ret = pipe_set_size(pipe, nr_pages);
 		break;

include/linux/pipe_fs_i.h

@@ -42,6 +42,7 @@ struct pipe_buffer {
  *	@fasync_readers: reader side fasync
  *	@fasync_writers: writer side fasync
  *	@bufs: the circular array of pipe buffers
+ *	@user: the user who created this pipe
  **/
 struct pipe_inode_info {
 	struct mutex mutex;
@@ -57,6 +58,7 @@ struct pipe_inode_info {
 	struct fasync_struct *fasync_readers;
 	struct fasync_struct *fasync_writers;
 	struct pipe_buffer *bufs;
+	struct user_struct *user;
 };
 
 /*
@@ -123,6 +125,8 @@ void pipe_unlock(struct pipe_inode_info *);
 void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *);
 
 extern unsigned int pipe_max_size, pipe_min_size;
+extern unsigned long pipe_user_pages_hard;
+extern unsigned long pipe_user_pages_soft;
 int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *);
 
 

include/linux/sched.h

@@ -835,6 +835,7 @@ struct user_struct {
 #endif
 	unsigned long locked_shm; /* How many pages of mlocked shm ? */
 	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
+	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */
 
 #ifdef CONFIG_KEYS
 	struct key *uid_keyring;	/* UID specific keyring */

kernel/sysctl.c

@@ -1757,6 +1757,20 @@ static struct ctl_table fs_table[] = {
 		.proc_handler	= &pipe_proc_fn,
 		.extra1		= &pipe_min_size,
 	},
+	{
+		.procname	= "pipe-user-pages-hard",
+		.data		= &pipe_user_pages_hard,
+		.maxlen		= sizeof(pipe_user_pages_hard),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+	{
+		.procname	= "pipe-user-pages-soft",
+		.data		= &pipe_user_pages_soft,
+		.maxlen		= sizeof(pipe_user_pages_soft),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
 	{ }
 };