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

Pull namespace updates from Eric Biederman:
 "This is a bunch of small changes built against 3.16-rc6.  The most
  significant change for users is the first patch which makes setns
  drmatically faster by removing unneded rcu handling.

  The next chunk of changes are so that "mount -o remount,.." will not
  allow the user namespace root to drop flags on a mount set by the
  system wide root.  Aks this forces read-only mounts to stay read-only,
  no-dev mounts to stay no-dev, no-suid mounts to stay no-suid, no-exec
  mounts to stay no exec and it prevents unprivileged users from messing
  with a mounts atime settings.  I have included my test case as the
  last patch in this series so people performing backports can verify
  this change works correctly.

  The next change fixes a bug in NFS that was discovered while auditing
  nsproxy users for the first optimization.  Today you can oops the
  kernel by reading /proc/fs/nfsfs/{servers,volumes} if you are clever
  with pid namespaces.  I rebased and fixed the build of the
  !CONFIG_NFS_FS case yesterday when a build bot caught my typo.  Given
  that no one to my knowledge bases anything on my tree fixing the typo
  in place seems more responsible that requiring a typo-fix to be
  backported as well.

  The last change is a small semantic cleanup introducing
  /proc/thread-self and pointing /proc/mounts and /proc/net at it.  This
  prevents several kinds of problemantic corner cases.  It is a
  user-visible change so it has a minute chance of causing regressions
  so the change to /proc/mounts and /proc/net are individual one line
  commits that can be trivially reverted.  Unfortunately I lost and
  could not find the email of the original reporter so he is not
  credited.  From at least one perspective this change to /proc/net is a
  refgression fix to allow pthread /proc/net uses that were broken by
  the introduction of the network namespace"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  proc: Point /proc/mounts at /proc/thread-self/mounts instead of /proc/self/mounts
  proc: Point /proc/net at /proc/thread-self/net instead of /proc/self/net
  proc: Implement /proc/thread-self to point at the directory of the current thread
  proc: Have net show up under /proc/<tgid>/task/<tid>
  NFS: Fix /proc/fs/nfsfs/servers and /proc/fs/nfsfs/volumes
  mnt: Add tests for unprivileged remount cases that have found to be faulty
  mnt: Change the default remount atime from relatime to the existing value
  mnt: Correct permission checks in do_remount
  mnt: Move the test for MNT_LOCK_READONLY from change_mount_flags into do_remount
  mnt: Only change user settable mount flags in remount
  namespaces: Use task_lock and not rcu to protect nsproxy

1 files changed, 85 insertions, 0 deletions

diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
new file mode 100644
index 000000000000..59075b509df3
--- /dev/null
+++ b/fs/proc/thread_self.c
@@ -0,0 +1,85 @@
+#include <linux/sched.h>
+#include <linux/namei.h>
+#include <linux/slab.h>
+#include <linux/pid_namespace.h>
+#include "internal.h"
+
+/*
+ * /proc/thread_self:
+ */
+static int proc_thread_self_readlink(struct dentry *dentry, char __user *buffer,
+                              int buflen)
+{
+        struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+        pid_t tgid = task_tgid_nr_ns(current, ns);
+        pid_t pid = task_pid_nr_ns(current, ns);
+        char tmp[PROC_NUMBUF + 6 + PROC_NUMBUF];
+        if (!pid)
+                return -ENOENT;
+        sprintf(tmp, "%d/task/%d", tgid, pid);
+        return readlink_copy(buffer, buflen, tmp);
+}
+
+static void *proc_thread_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+        struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+        pid_t tgid = task_tgid_nr_ns(current, ns);
+        pid_t pid = task_pid_nr_ns(current, ns);
+        char *name = ERR_PTR(-ENOENT);
+        if (pid) {
+                name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
+                if (!name)
+                        name = ERR_PTR(-ENOMEM);
+                else
+                        sprintf(name, "%d/task/%d", tgid, pid);
+        }
+        nd_set_link(nd, name);
+        return NULL;
+}
+
+static const struct inode_operations proc_thread_self_inode_operations = {
+        .readlink       = proc_thread_self_readlink,
+        .follow_link    = proc_thread_self_follow_link,
+        .put_link       = kfree_put_link,
+};
+
+static unsigned thread_self_inum;
+
+int proc_setup_thread_self(struct super_block *s)
+{
+        struct inode *root_inode = s->s_root->d_inode;
+        struct pid_namespace *ns = s->s_fs_info;
+        struct dentry *thread_self;
+
+        mutex_lock(&root_inode->i_mutex);
+        thread_self = d_alloc_name(s->s_root, "thread-self");
+        if (thread_self) {
+                struct inode *inode = new_inode_pseudo(s);
+                if (inode) {
+                        inode->i_ino = thread_self_inum;
+                        inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+                        inode->i_mode = S_IFLNK | S_IRWXUGO;
+                        inode->i_uid = GLOBAL_ROOT_UID;
+                        inode->i_gid = GLOBAL_ROOT_GID;
+                        inode->i_op = &proc_thread_self_inode_operations;
+                        d_add(thread_self, inode);
+                } else {
+                        dput(thread_self);
+                        thread_self = ERR_PTR(-ENOMEM);
+                }
+        } else {
+                thread_self = ERR_PTR(-ENOMEM);
+        }
+        mutex_unlock(&root_inode->i_mutex);
+        if (IS_ERR(thread_self)) {
+                pr_err("proc_fill_super: can't allocate /proc/thread_self\n");
+                return PTR_ERR(thread_self);
+        }
+        ns->proc_thread_self = thread_self;
+        return 0;
+}
+
+void __init proc_thread_self_init(void)
+{
+        proc_alloc_inum(&thread_self_inum);
+}