From: Roman Gushchin <roman.gushchin@linux.dev>

When a struct ops is being attached and a bpf link is created,
allow to pass a cgroup fd using bpf attr, so that struct ops
can be attached to a cgroup instead of globally.

Attached struct ops doesn't hold a reference to the cgroup,
only preserves cgroup id.

Signed-off-by: Roman Gushchin <roman.gushchin@linux.dev>
---
 include/linux/bpf.h         |  1 +
 kernel/bpf/bpf_struct_ops.c | 13 +++++++++++++
 2 files changed, 14 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 031682f1ad39..7c15bac782fc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1885,6 +1885,7 @@ struct bpf_struct_ops_link {
 	struct bpf_link link;
 	struct bpf_map __rcu *map;
 	wait_queue_head_t wait_hup;
+	u64 cgroup_id;
 };
 
 struct bpf_link_primer {
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index de01cf3025b3..f575c5cd0dc8 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -13,6 +13,7 @@
 #include <linux/btf_ids.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/poll.h>
+#include <linux/cgroup.h>
 
 struct bpf_struct_ops_value {
 	struct bpf_struct_ops_common_value common;
@@ -1377,6 +1378,18 @@ int bpf_struct_ops_link_create(union bpf_attr *attr)
 	}
 	bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_map_lops, NULL,
 		      attr->link_create.attach_type);
+#ifdef CONFIG_CGROUPS
+	if (attr->link_create.cgroup.relative_fd) {
+		struct cgroup *cgrp;
+
+		cgrp = cgroup_get_from_fd(attr->link_create.cgroup.relative_fd);
+		if (IS_ERR(cgrp))
+			return PTR_ERR(cgrp);
+
+		link->cgroup_id = cgroup_id(cgrp);
+		cgroup_put(cgrp);
+	}
+#endif /* CONFIG_CGROUPS */
 
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err)
-- 
2.43.0

> diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
> index de01cf3025b3..f575c5cd0dc8 100644

[ ... ]

> @@ -1377,6 +1378,18 @@ int bpf_struct_ops_link_create(union bpf_attr *attr)
>  	}
>  	bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_map_lops, NULL,
>  		      attr->link_create.attach_type);
> +#ifdef CONFIG_CGROUPS
> +	if (attr->link_create.cgroup.relative_fd) {
> +		struct cgroup *cgrp;
> +
> +		cgrp = cgroup_get_from_fd(attr->link_create.cgroup.relative_fd);
> +		if (IS_ERR(cgrp))
> +			return PTR_ERR(cgrp);
                        ^^^^^^^^^^^^^^^^^

When cgroup_get_from_fd() fails, this returns directly without cleaning
up. At this point in bpf_struct_ops_link_create(), link has already been
allocated via kzalloc() and map has a reference from bpf_map_get().

Should this use goto err_out instead? The err_out label calls
bpf_map_put(map) and kfree(link), which would be needed here but are
bypassed by the direct return.

> +
> +		link->cgroup_id = cgroup_id(cgrp);
> +		cgroup_put(cgrp);
> +	}
> +#endif /* CONFIG_CGROUPS */
>
>  	err = bpf_link_prime(&link->link, &link_primer);
>  	if (err)


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/21280790825