Merge tag 'cgroup-for-6.1-rc1-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - Fix a recent regression where a sleeping kernfs function is called
   with css_set_lock (spinlock) held

 - Revert the commit to enable cgroup1 support for cgroup_get_from_fd/file()

   Multiple users assume that the lookup only works for cgroup2 and
   breaks when fed a cgroup1 file. Instead, introduce a separate set of
   functions to lookup both v1 and v2 and use them where the user
   explicitly wants to support both versions.

 - Compat update for tools/perf/util/bpf_skel/bperf_cgroup.bpf.c.

 - Add Josef Bacik as a blkcg maintainer.

* tag 'cgroup-for-6.1-rc1-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  blkcg: Update MAINTAINERS entry
  mm: cgroup: fix comments for get from fd/file helpers
  perf stat: Support old kernels for bperf cgroup counting
  bpf: cgroup_iter: support cgroup1 using cgroup fd
  cgroup: add cgroup_v1v2_get_from_[fd/file]()
  Revert "cgroup: enable cgroup_get_from_file() on cgroup1"
  cgroup: Reorganize css_set_lock and kernfs path processing

4 files changed, 83 insertions, 21 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index cf0f18502372..07938eab80dd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5266,6 +5266,7 @@ F:	tools/testing/selftests/cgroup/
 
 CONTROL GROUP - BLOCK IO CONTROLLER (BLKIO)
 M:	Tejun Heo <tj@kernel.org>
+M:	Josef Bacik <josef@toxicpanda.com>
 M:	Jens Axboe <axboe@kernel.dk>
 L:	cgroups@vger.kernel.org
 L:	linux-block@vger.kernel.org
@@ -5273,6 +5274,7 @@ T:	git git://git.kernel.dk/linux-block
 F:	Documentation/admin-guide/cgroup-v1/blkio-controller.rst
 F:	block/bfq-cgroup.c
 F:	block/blk-cgroup.c
+F:	block/blk-iocost.c
 F:	block/blk-iolatency.c
 F:	block/blk-throttle.c
 F:	include/linux/blk-cgroup.h
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f2a9f2274c3b..528bd44b59e2 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -106,6 +106,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 
 struct cgroup *cgroup_get_from_path(const char *path);
 struct cgroup *cgroup_get_from_fd(int fd);
+struct cgroup *cgroup_v1v2_get_from_fd(int fd);
 
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c
index 0d200a993489..9fcf09f2ef00 100644
--- a/kernel/bpf/cgroup_iter.c
+++ b/kernel/bpf/cgroup_iter.c
@@ -196,7 +196,7 @@ static int bpf_iter_attach_cgroup(struct bpf_prog *prog,
 		return -EINVAL;
 
 	if (fd)
-		cgrp = cgroup_get_from_fd(fd);
+		cgrp = cgroup_v1v2_get_from_fd(fd);
 	else if (id)
 		cgrp = cgroup_get_from_id(id);
 	else /* walk the entire hierarchy by default. */
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 7f486677ab1f..2319946715e0 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1392,6 +1392,9 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 	cgroup_free_root(root);
 }
 
+/*
+ * Returned cgroup is without refcount but it's valid as long as cset pins it.
+ */
 static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
 					    struct cgroup_root *root)
 {
@@ -1403,6 +1406,7 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
 		res_cgroup = cset->dfl_cgrp;
 	} else {
 		struct cgrp_cset_link *link;
+		lockdep_assert_held(&css_set_lock);
 
 		list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
 			struct cgroup *c = link->cgrp;
@@ -1414,6 +1418,7 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
 		}
 	}
 
+	BUG_ON(!res_cgroup);
 	return res_cgroup;
 }
 
@@ -1436,23 +1441,36 @@ current_cgns_cgroup_from_root(struct cgroup_root *root)
 
 	rcu_read_unlock();
 
-	BUG_ON(!res);
 	return res;
 }
 
+/*
+ * Look up cgroup associated with current task's cgroup namespace on the default
+ * hierarchy.
+ *
+ * Unlike current_cgns_cgroup_from_root(), this doesn't need locks:
+ * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu
+ *   pointers.
+ * - css_set_lock is not needed because we just read cset->dfl_cgrp.
+ * - As a bonus returned cgrp is pinned with the current because it cannot
+ *   switch cgroup_ns asynchronously.
+ */
+static struct cgroup *current_cgns_cgroup_dfl(void)
+{
+	struct css_set *cset;
+
+	cset = current->nsproxy->cgroup_ns->root_cset;
+	return __cset_cgroup_from_root(cset, &cgrp_dfl_root);
+}
+
 /* look up cgroup associated with given css_set on the specified hierarchy */
 static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
 					    struct cgroup_root *root)
 {
-	struct cgroup *res = NULL;
-
 	lockdep_assert_held(&cgroup_mutex);
 	lockdep_assert_held(&css_set_lock);
 
-	res = __cset_cgroup_from_root(cset, root);
-
-	BUG_ON(!res);
-	return res;
+	return __cset_cgroup_from_root(cset, root);
 }
 
 /*
@@ -6191,9 +6209,7 @@ struct cgroup *cgroup_get_from_id(u64 id)
 	if (!cgrp)
 		return ERR_PTR(-ENOENT);
 
-	spin_lock_irq(&css_set_lock);
-	root_cgrp = current_cgns_cgroup_from_root(&cgrp_dfl_root);
-	spin_unlock_irq(&css_set_lock);
+	root_cgrp = current_cgns_cgroup_dfl();
 	if (!cgroup_is_descendant(cgrp, root_cgrp)) {
 		cgroup_put(cgrp);
 		return ERR_PTR(-ENOENT);
@@ -6294,16 +6310,42 @@ void cgroup_fork(struct task_struct *child)
 	INIT_LIST_HEAD(&child->cg_list);
 }
 
-static struct cgroup *cgroup_get_from_file(struct file *f)
+/**
+ * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer
+ * @f: file corresponding to cgroup_dir
+ *
+ * Find the cgroup from a file pointer associated with a cgroup directory.
+ * Returns a pointer to the cgroup on success. ERR_PTR is returned if the
+ * cgroup cannot be found.
+ */
+static struct cgroup *cgroup_v1v2_get_from_file(struct file *f)
 {
 	struct cgroup_subsys_state *css;
-	struct cgroup *cgrp;
 
 	css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
 	if (IS_ERR(css))
 		return ERR_CAST(css);
 
-	cgrp = css->cgroup;
+	return css->cgroup;
+}
+
+/**
+ * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports
+ * cgroup2.
+ * @f: file corresponding to cgroup2_dir
+ */
+static struct cgroup *cgroup_get_from_file(struct file *f)
+{
+	struct cgroup *cgrp = cgroup_v1v2_get_from_file(f);
+
+	if (IS_ERR(cgrp))
+		return ERR_CAST(cgrp);
+
+	if (!cgroup_on_dfl(cgrp)) {
+		cgroup_put(cgrp);
+		return ERR_PTR(-EBADF);
+	}
+
 	return cgrp;
 }
 
@@ -6772,10 +6814,8 @@ struct cgroup *cgroup_get_from_path(const char *path)
 	struct cgroup *cgrp = ERR_PTR(-ENOENT);
 	struct cgroup *root_cgrp;
 
-	spin_lock_irq(&css_set_lock);
-	root_cgrp = current_cgns_cgroup_from_root(&cgrp_dfl_root);
+	root_cgrp = current_cgns_cgroup_dfl();
 	kn = kernfs_walk_and_get(root_cgrp->kn, path);
-	spin_unlock_irq(&css_set_lock);
 	if (!kn)
 		goto out;
 
@@ -6800,15 +6840,15 @@ out:
 EXPORT_SYMBOL_GPL(cgroup_get_from_path);
 
 /**
- * cgroup_get_from_fd - get a cgroup pointer from a fd
- * @fd: fd obtained by open(cgroup2_dir)
+ * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd
+ * @fd: fd obtained by open(cgroup_dir)
  *
  * Find the cgroup from a fd which should be obtained
  * by opening a cgroup directory.  Returns a pointer to the
  * cgroup on success. ERR_PTR is returned if the cgroup
  * cannot be found.
  */
-struct cgroup *cgroup_get_from_fd(int fd)
+struct cgroup *cgroup_v1v2_get_from_fd(int fd)
 {
 	struct cgroup *cgrp;
 	struct file *f;
@@ -6817,10 +6857,29 @@ struct cgroup *cgroup_get_from_fd(int fd)
 	if (!f)
 		return ERR_PTR(-EBADF);
 
-	cgrp = cgroup_get_from_file(f);
+	cgrp = cgroup_v1v2_get_from_file(f);
 	fput(f);
 	return cgrp;
 }
+
+/**
+ * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports
+ * cgroup2.
+ * @fd: fd obtained by open(cgroup2_dir)
+ */
+struct cgroup *cgroup_get_from_fd(int fd)
+{
+	struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd);
+
+	if (IS_ERR(cgrp))
+		return ERR_CAST(cgrp);
+
+	if (!cgroup_on_dfl(cgrp)) {
+		cgroup_put(cgrp);
+		return ERR_PTR(-EBADF);
+	}
+	return cgrp;
+}
 EXPORT_SYMBOL_GPL(cgroup_get_from_fd);
 
 static u64 power_of_ten(int power)