Merge branch 'for-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "Several noteworthy changes.

   - Parav's rdma controller is finally merged. It is very straight
     forward and can limit the abosolute numbers of common rdma
     constructs used by different cgroups.

   - kernel/cgroup.c got too chubby and disorganized. Created
     kernel/cgroup/ subdirectory and moved all cgroup related files
     under kernel/ there and reorganized the core code. This hurts for
     backporting patches but was long overdue.

   - cgroup v2 process listing reimplemented so that it no longer
     depends on allocating a buffer large enough to cache the entire
     result to sort and uniq the output. v2 has always mangled the sort
     order to ensure that users don't depend on the sorted output, so
     this shouldn't surprise anybody. This makes the pid listing
     functions use the same iterators that are used internally, which
     have to have the same iterating capabilities anyway.

   - perf cgroup filtering now works automatically on cgroup v2. This
     patch was posted a long time ago but somehow fell through the
     cracks.

   - misc fixes asnd documentation updates"

* 'for-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (27 commits)
  kernfs: fix locking around kernfs_ops->release() callback
  cgroup: drop the matching uid requirement on migration for cgroup v2
  cgroup, perf_event: make perf_event controller work on cgroup2 hierarchy
  cgroup: misc cleanups
  cgroup: call subsys->*attach() only for subsystems which are actually affected by migration
  cgroup: track migration context in cgroup_mgctx
  cgroup: cosmetic update to cgroup_taskset_add()
  rdmacg: Fixed uninitialized current resource usage
  cgroup: Add missing cgroup-v2 PID controller documentation.
  rdmacg: Added documentation for rdmacg
  IB/core: added support to use rdma cgroup controller
  rdmacg: Added rdma cgroup controller
  cgroup: fix a comment typo
  cgroup: fix RCU related sparse warnings
  cgroup: move namespace code to kernel/cgroup/namespace.c
  cgroup: rename functions for consistency
  cgroup: move v1 mount functions to kernel/cgroup/cgroup-v1.c
  cgroup: separate out cgroup1_kf_syscall_ops
  cgroup: refactor mount path and clearly distinguish v1 and v2 paths
  cgroup: move cgroup v1 specific code to kernel/cgroup/cgroup-v1.c
  ...

1 files changed, 55 insertions, 7 deletions

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 4f0535890b30..35043a8c4529 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -515,7 +515,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
 		goto out_put;
 
 	rc = 0;
-	of->mmapped = 1;
+	of->mmapped = true;
 	of->vm_ops = vma->vm_ops;
 	vma->vm_ops = &kernfs_vm_ops;
 out_put:
@@ -707,7 +707,8 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 	if (error)
 		goto err_free;
 
-	((struct seq_file *)file->private_data)->private = of;
+	of->seq_file = file->private_data;
+	of->seq_file->private = of;
 
 	/* seq_file clears PWRITE unconditionally, restore it if WRITE */
 	if (file->f_mode & FMODE_WRITE)
@@ -716,13 +717,22 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 	/* make sure we have open node struct */
 	error = kernfs_get_open_node(kn, of);
 	if (error)
-		goto err_close;
+		goto err_seq_release;
+
+	if (ops->open) {
+		/* nobody has access to @of yet, skip @of->mutex */
+		error = ops->open(of);
+		if (error)
+			goto err_put_node;
+	}
 
 	/* open succeeded, put active references */
 	kernfs_put_active(kn);
 	return 0;
 
-err_close:
+err_put_node:
+	kernfs_put_open_node(kn, of);
+err_seq_release:
 	seq_release(inode, file);
 err_free:
 	kfree(of->prealloc_buf);
@@ -732,11 +742,41 @@ err_out:
 	return error;
 }
 
+/* used from release/drain to ensure that ->release() is called exactly once */
+static void kernfs_release_file(struct kernfs_node *kn,
+				struct kernfs_open_file *of)
+{
+	/*
+	 * @of is guaranteed to have no other file operations in flight and
+	 * we just want to synchronize release and drain paths.
+	 * @kernfs_open_file_mutex is enough.  @of->mutex can't be used
+	 * here because drain path may be called from places which can
+	 * cause circular dependency.
+	 */
+	lockdep_assert_held(&kernfs_open_file_mutex);
+
+	if (!of->released) {
+		/*
+		 * A file is never detached without being released and we
+		 * need to be able to release files which are deactivated
+		 * and being drained.  Don't use kernfs_ops().
+		 */
+		kn->attr.ops->release(of);
+		of->released = true;
+	}
+}
+
 static int kernfs_fop_release(struct inode *inode, struct file *filp)
 {
 	struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
 	struct kernfs_open_file *of = kernfs_of(filp);
 
+	if (kn->flags & KERNFS_HAS_RELEASE) {
+		mutex_lock(&kernfs_open_file_mutex);
+		kernfs_release_file(kn, of);
+		mutex_unlock(&kernfs_open_file_mutex);
+	}
+
 	kernfs_put_open_node(kn, of);
 	seq_release(inode, filp);
 	kfree(of->prealloc_buf);
@@ -745,12 +785,12 @@ static int kernfs_fop_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-void kernfs_unmap_bin_file(struct kernfs_node *kn)
+void kernfs_drain_open_files(struct kernfs_node *kn)
 {
 	struct kernfs_open_node *on;
 	struct kernfs_open_file *of;
 
-	if (!(kn->flags & KERNFS_HAS_MMAP))
+	if (!(kn->flags & (KERNFS_HAS_MMAP | KERNFS_HAS_RELEASE)))
 		return;
 
 	spin_lock_irq(&kernfs_open_node_lock);
@@ -762,10 +802,16 @@ void kernfs_unmap_bin_file(struct kernfs_node *kn)
 		return;
 
 	mutex_lock(&kernfs_open_file_mutex);
+
 	list_for_each_entry(of, &on->files, list) {
 		struct inode *inode = file_inode(of->file);
-		unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+
+		if (kn->flags & KERNFS_HAS_MMAP)
+			unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+
+		kernfs_release_file(kn, of);
 	}
+
 	mutex_unlock(&kernfs_open_file_mutex);
 
 	kernfs_put_open_node(kn, NULL);
@@ -964,6 +1010,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 		kn->flags |= KERNFS_HAS_SEQ_SHOW;
 	if (ops->mmap)
 		kn->flags |= KERNFS_HAS_MMAP;
+	if (ops->release)
+		kn->flags |= KERNFS_HAS_RELEASE;
 
 	rc = kernfs_add_one(kn);
 	if (rc) {