fuse: Add support for pid namespaces

When the userspace process servicing fuse requests is running in
a pid namespace then pids passed via the fuse fd are not being
translated into that process' namespace. Translation is necessary
for the pid to be useful to that process.

Since no use case currently exists for changing namespaces all
translations can be done relative to the pid namespace in use
when fuse_conn_init() is called. For fuse this translates to
mount time, and for cuse this is when /dev/cuse is opened. IO for
this connection from another namespace will return errors.

Requests from processes whose pid cannot be translated into the
target namespace will have a value of 0 for in.h.pid.

File locking changes based on previous work done by Eric
Biederman.

Signed-off-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 5e815072b..f956821 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -20,6 +20,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/swap.h>
 #include <linux/splice.h>
+#include <linux/sched.h>
 
 MODULE_ALIAS_MISCDEV(FUSE_MINOR);
 MODULE_ALIAS("devname:fuse");
@@ -111,11 +112,11 @@
 	refcount_dec(&req->count);
 }
 
-static void fuse_req_init_context(struct fuse_req *req)
+static void fuse_req_init_context(struct fuse_conn *fc, struct fuse_req *req)
 {
 	req->in.h.uid = from_kuid_munged(&init_user_ns, current_fsuid());
 	req->in.h.gid = from_kgid_munged(&init_user_ns, current_fsgid());
-	req->in.h.pid = current->pid;
+	req->in.h.pid = pid_nr_ns(task_pid(current), fc->pid_ns);
 }
 
 void fuse_set_initialized(struct fuse_conn *fc)
@@ -162,7 +163,7 @@
 		goto out;
 	}
 
-	fuse_req_init_context(req);
+	fuse_req_init_context(fc, req);
 	__set_bit(FR_WAITING, &req->flags);
 	if (for_background)
 		__set_bit(FR_BACKGROUND, &req->flags);
@@ -255,7 +256,7 @@
 	if (!req)
 		req = get_reserved_req(fc, file);
 
-	fuse_req_init_context(req);
+	fuse_req_init_context(fc, req);
 	__set_bit(FR_WAITING, &req->flags);
 	__clear_bit(FR_BACKGROUND, &req->flags);
 	return req;
@@ -1222,6 +1223,9 @@
 	struct fuse_in *in;
 	unsigned reqsize;
 
+	if (task_active_pid_ns(current) != fc->pid_ns)
+		return -EIO;
+
  restart:
 	spin_lock(&fiq->waitq.lock);
 	err = -EAGAIN;
@@ -1820,6 +1824,9 @@
 	struct fuse_req *req;
 	struct fuse_out_header oh;
 
+	if (task_active_pid_ns(current) != fc->pid_ns)
+		return -EIO;
+
 	if (nbytes < sizeof(struct fuse_out_header))
 		return -EINVAL;
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 70770a0..aa93f09 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2083,7 +2083,8 @@
 	return generic_file_mmap(file, vma);
 }
 
-static int convert_fuse_file_lock(const struct fuse_file_lock *ffl,
+static int convert_fuse_file_lock(struct fuse_conn *fc,
+				  const struct fuse_file_lock *ffl,
 				  struct file_lock *fl)
 {
 	switch (ffl->type) {
@@ -2098,7 +2099,14 @@
 
 		fl->fl_start = ffl->start;
 		fl->fl_end = ffl->end;
-		fl->fl_pid = ffl->pid;
+
+		/*
+		 * Convert pid into the caller's pid namespace. If the pid
+		 * does not map into the namespace fl_pid will get set to 0.
+		 */
+		rcu_read_lock();
+		fl->fl_pid = pid_vnr(find_pid_ns(ffl->pid, fc->pid_ns));
+		rcu_read_unlock();
 		break;
 
 	default:
@@ -2147,7 +2155,7 @@
 	args.out.args[0].value = &outarg;
 	err = fuse_simple_request(fc, &args);
 	if (!err)
-		err = convert_fuse_file_lock(&outarg.lk, fl);
+		err = convert_fuse_file_lock(fc, &outarg.lk, fl);
 
 	return err;
 }
@@ -2159,7 +2167,8 @@
 	FUSE_ARGS(args);
 	struct fuse_lk_in inarg;
 	int opcode = (fl->fl_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
-	pid_t pid = fl->fl_type != F_UNLCK ? current->tgid : 0;
+	struct pid *pid = fl->fl_type != F_UNLCK ? task_tgid(current) : NULL;
+	pid_t pid_nr = pid_nr_ns(pid, fc->pid_ns);
 	int err;
 
 	if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
@@ -2171,7 +2180,10 @@
 	if (fl->fl_flags & FL_CLOSE)
 		return 0;
 
-	fuse_lk_fill(&args, file, fl, opcode, pid, flock, &inarg);
+	if (pid && pid_nr == 0)
+		return -EOVERFLOW;
+
+	fuse_lk_fill(&args, file, fl, opcode, pid_nr, flock, &inarg);
 	err = fuse_simple_request(fc, &args);
 
 	/* locking is restartable */
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 6c649f0..041521d 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -24,6 +24,7 @@
 #include <linux/workqueue.h>
 #include <linux/kref.h>
 #include <linux/xattr.h>
+#include <linux/pid_namespace.h>
 #include <linux/refcount.h>
 
 /** Max number of pages that can be used in a single read request */
@@ -462,6 +463,9 @@
 	/** The group id for this mount */
 	kgid_t group_id;
 
+	/** The pid namespace for this mount */
+	struct pid_namespace *pid_ns;
+
 	/** Maximum read size */
 	unsigned max_read;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 3961c5f..a137f1c 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/exportfs.h>
 #include <linux/posix_acl.h>
+#include <linux/pid_namespace.h>
 
 MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
 MODULE_DESCRIPTION("Filesystem in Userspace");
@@ -626,6 +627,7 @@
 	fc->connected = 1;
 	fc->attr_version = 1;
 	get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
+	fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
 }
 EXPORT_SYMBOL_GPL(fuse_conn_init);
 
@@ -634,6 +636,7 @@
 	if (refcount_dec_and_test(&fc->count)) {
 		if (fc->destroy_req)
 			fuse_request_free(fc->destroy_req);
+		put_pid_ns(fc->pid_ns);
 		fc->release(fc);
 	}
 }