[PATCH] fuse: Add support for pid namespaces

From: Seth Forshee
Date: Wed Jul 02 2014 - 17:29:19 EST


If the userspace process servicing fuse requests is running in
a pid namespace then pids passed via the fuse fd need to be
translated relative to that namespace. Capture the pid namespace
in use when the filesystem is mounted and use this for pid
translation.

As with user namespaces, since no use case currently exists for
changing namespaces so all translations are done relative to the
pid namespace in use when /dev/fuse is opened. Mounting or
/dev/fuse IO from another namespace will return errors. This
restriction can be relaxed at a later time if needed.

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

Signed-off-by: Seth Forshee <seth.forshee@xxxxxxxxxxxxx>
---
fs/fuse/dev.c | 15 ++++++++++-----
fs/fuse/file.c | 23 ++++++++++++++++++-----
fs/fuse/fuse_i.h | 4 ++++
fs/fuse/inode.c | 3 +++
4 files changed, 35 insertions(+), 10 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 2ee0a7376e0e..627cbdbc63a3 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -19,6 +19,7 @@
#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");
@@ -127,7 +128,7 @@ static void fuse_req_init_context(struct fuse_conn *fc, struct fuse_req *req)
{
req->in.h.uid = from_kuid_munged(fc->user_ns, current_fsuid());
req->in.h.gid = from_kgid_munged(fc->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)
@@ -1124,7 +1125,8 @@ __releases(fc->lock)
arg.unique = req->in.h.unique;

spin_unlock(&fc->lock);
- if (fc->user_ns != current_user_ns())
+ if (fc->user_ns != current_user_ns() ||
+ fc->pid_ns != task_active_pid_ns(current))
return -EIO;
if (nbytes < reqsize)
return -EINVAL;
@@ -1178,7 +1180,8 @@ __releases(fc->lock)

spin_unlock(&fc->lock);
kfree(forget);
- if (fc->user_ns != current_user_ns())
+ if (fc->user_ns != current_user_ns() ||
+ fc->pid_ns != task_active_pid_ns(current))
return -EIO;
if (nbytes < ih.len)
return -EINVAL;
@@ -1218,7 +1221,8 @@ __releases(fc->lock)
head = dequeue_forget(fc, max_forgets, &count);
spin_unlock(&fc->lock);

- if (fc->user_ns != current_user_ns())
+ if (fc->user_ns != current_user_ns() ||
+ fc->pid_ns != task_active_pid_ns(current))
return -EIO;

arg.count = count;
@@ -1306,7 +1310,8 @@ static ssize_t fuse_dev_do_read(struct fuse_conn *fc, struct file *file,
req->state = FUSE_REQ_READING;
list_move(&req->list, &fc->io);

- if (fc->user_ns != current_user_ns()) {
+ if (fc->user_ns != current_user_ns() ||
+ fc->pid_ns != task_active_pid_ns(current)) {
req->out.h.error = -EIO;
request_end(fc, req);
return -EPERM;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 5ef05b5c4cff..126b1568dc4c 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2061,7 +2061,8 @@ static int fuse_direct_mmap(struct file *file, struct vm_area_struct *vma)
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) {
@@ -2076,7 +2077,15 @@ static int convert_fuse_file_lock(const struct fuse_file_lock *ffl,

fl->fl_start = ffl->start;
fl->fl_end = ffl->end;
- fl->fl_pid = ffl->pid;
+
+ /*
+ * Convert pid into the connection'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:
@@ -2125,7 +2134,7 @@ static int fuse_getlk(struct file *file, struct file_lock *fl)
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;
}
@@ -2137,7 +2146,8 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
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) {
@@ -2149,7 +2159,10 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
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 f6eddd8a2e06..3b7a301c0999 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -23,6 +23,7 @@
#include <linux/poll.h>
#include <linux/workqueue.h>
#include <linux/user_namespace.h>
+#include <linux/pid_namespace.h>

/** Max number of pages that can be used in a single read request */
#define FUSE_MAX_PAGES_PER_REQ 32
@@ -406,6 +407,9 @@ struct fuse_conn {
/** The user namespace for this mount */
struct user_namespace *user_ns;

+ /** The pid namespace for this mount */
+ struct pid_namespace *pid_ns;
+
/** The fuse mount flags for this mount */
unsigned flags;

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 0e2a35507f1a..d190ce2c9d8f 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -20,6 +20,7 @@
#include <linux/random.h>
#include <linux/sched.h>
#include <linux/exportfs.h>
+#include <linux/pid_namespace.h>

MODULE_AUTHOR("Miklos Szeredi <miklos@xxxxxxxxxx>");
MODULE_DESCRIPTION("Filesystem in Userspace");
@@ -627,6 +628,7 @@ void fuse_conn_init(struct fuse_conn *fc)
fc->attr_version = 1;
get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
fc->user_ns = get_user_ns(current_user_ns());
+ fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
}
EXPORT_SYMBOL_GPL(fuse_conn_init);

@@ -636,6 +638,7 @@ void fuse_conn_put(struct fuse_conn *fc)
if (fc->destroy_req)
fuse_request_free(fc->destroy_req);
put_user_ns(fc->user_ns);
+ put_pid_ns(fc->pid_ns);
fc->release(fc);
}
}

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/