bpf: Implement mprog API on top of existing cgroup progs

Current cgroup prog ordering is appending at attachment time. This is not
ideal. In some cases, users want specific ordering at a particular cgroup
level. To address this, the existing mprog API seems an ideal solution with
supporting BPF_F_BEFORE and BPF_F_AFTER flags.

But there are a few obstacles to directly use kernel mprog interface.
Currently cgroup bpf progs already support prog attach/detach/replace
and link-based attach/detach/replace. For example, in struct
bpf_prog_array_item, the cgroup_storage field needs to be together
with bpf prog. But the mprog API struct bpf_mprog_fp only has bpf_prog
as the member, which makes it difficult to use kernel mprog interface.

In another case, the current cgroup prog detach tries to use the
same flag as in attach. This is different from mprog kernel interface
which uses flags passed from user space.

So to avoid modifying existing behavior, I made the following changes to
support mprog API for cgroup progs:
 - The support is for prog list at cgroup level. Cross-level prog list
   (a.k.a. effective prog list) is not supported.
 - Previously, BPF_F_PREORDER is supported only for prog attach, now
   BPF_F_PREORDER is also supported by link-based attach.
 - For attach, BPF_F_BEFORE/BPF_F_AFTER/BPF_F_ID/BPF_F_LINK is supported
   similar to kernel mprog but with different implementation.
 - For detach and replace, use the existing implementation.
 - For attach, detach and replace, the revision for a particular prog
   list, associated with a particular attach type, will be updated
   by increasing count by 1.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20250606163141.2428937-1-yonghong.song@linux.dev

1 files changed, 31 insertions, 15 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 89d027cd7ca0..97ad57ffc404 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4186,6 +4186,25 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	}
 }
 
+static bool is_cgroup_prog_type(enum bpf_prog_type ptype, enum bpf_attach_type atype,
+				bool check_atype)
+{
+	switch (ptype) {
+	case BPF_PROG_TYPE_CGROUP_DEVICE:
+	case BPF_PROG_TYPE_CGROUP_SKB:
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_SOCK_OPS:
+		return true;
+	case BPF_PROG_TYPE_LSM:
+		return check_atype ? atype == BPF_LSM_CGROUP : true;
+	default:
+		return false;
+	}
+}
+
 #define BPF_PROG_ATTACH_LAST_FIELD expected_revision
 
 #define BPF_F_ATTACH_MASK_BASE	\
@@ -4216,6 +4235,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	if (bpf_mprog_supported(ptype)) {
 		if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
 			return -EINVAL;
+	} else if (is_cgroup_prog_type(ptype, 0, false)) {
+		if (attr->attach_flags & ~(BPF_F_ATTACH_MASK_BASE | BPF_F_ATTACH_MASK_MPROG))
+			return -EINVAL;
 	} else {
 		if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE)
 			return -EINVAL;
@@ -4233,6 +4255,11 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		return -EINVAL;
 	}
 
+	if (is_cgroup_prog_type(ptype, prog->expected_attach_type, true)) {
+		ret = cgroup_bpf_prog_attach(attr, ptype, prog);
+		goto out;
+	}
+
 	switch (ptype) {
 	case BPF_PROG_TYPE_SK_SKB:
 	case BPF_PROG_TYPE_SK_MSG:
@@ -4244,20 +4271,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 		ret = netns_bpf_prog_attach(attr, prog);
 		break;
-	case BPF_PROG_TYPE_CGROUP_DEVICE:
-	case BPF_PROG_TYPE_CGROUP_SKB:
-	case BPF_PROG_TYPE_CGROUP_SOCK:
-	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
-	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
-	case BPF_PROG_TYPE_CGROUP_SYSCTL:
-	case BPF_PROG_TYPE_SOCK_OPS:
-	case BPF_PROG_TYPE_LSM:
-		if (ptype == BPF_PROG_TYPE_LSM &&
-		    prog->expected_attach_type != BPF_LSM_CGROUP)
-			ret = -EINVAL;
-		else
-			ret = cgroup_bpf_prog_attach(attr, ptype, prog);
-		break;
 	case BPF_PROG_TYPE_SCHED_CLS:
 		if (attr->attach_type == BPF_TCX_INGRESS ||
 		    attr->attach_type == BPF_TCX_EGRESS)
@@ -4268,7 +4281,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	default:
 		ret = -EINVAL;
 	}
-
+out:
 	if (ret)
 		bpf_prog_put(prog);
 	return ret;
@@ -4296,6 +4309,9 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 			if (IS_ERR(prog))
 				return PTR_ERR(prog);
 		}
+	} else if (is_cgroup_prog_type(ptype, 0, false)) {
+		if (attr->attach_flags || attr->relative_fd)
+			return -EINVAL;
 	} else if (attr->attach_flags ||
 		   attr->relative_fd ||
 		   attr->expected_revision) {