linux-kernel - [PATCH rfc 05/12] mm: introduce bpf kfuncs to deal with memcg pointers

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250428033617.3797686-6-roman.gushchin@linux.dev>
Date: Mon, 28 Apr 2025 03:36:10 +0000
From: Roman Gushchin <roman.gushchin@...ux.dev>
To: linux-kernel@...r.kernel.org
Cc: Andrew Morton <akpm@...ux-foundation.org>,
	Alexei Starovoitov <ast@...nel.org>,
	Johannes Weiner <hannes@...xchg.org>,
	Michal Hocko <mhocko@...nel.org>,
	Shakeel Butt <shakeel.butt@...ux.dev>,
	Suren Baghdasaryan <surenb@...gle.com>,
	David Rientjes <rientjes@...gle.com>,
	Josh Don <joshdon@...gle.com>,
	Chuyi Zhou <zhouchuyi@...edance.com>,
	cgroups@...r.kernel.org,
	linux-mm@...ck.org,
	bpf@...r.kernel.org,
	Roman Gushchin <roman.gushchin@...ux.dev>
Subject: [PATCH rfc 05/12] mm: introduce bpf kfuncs to deal with memcg pointers

To effectively operate with memory cgroups in bpf there is a need
to convert css pointers to memcg pointers. A simple container_of
cast which is used in the kernel code can't be used in bpf because
from the verifier's point of view that's a out-of-bounds memory access.

Introduce helper get/put kfuncs which can be used to get
a refcounted memcg pointer from the css pointer:
  - bpf_get_mem_cgroup,
  - bpf_put_mem_cgroup.

bpf_get_mem_cgroup() can take both memcg's css and the corresponding
cgroup's "self" css. It allows it to be used with the existing cgroup
iterator which iterates over cgroup tree, not memcg tree.

Signed-off-by: Roman Gushchin <roman.gushchin@...ux.dev>
---
 include/linux/memcontrol.h |   2 +
 mm/Makefile                |   3 ++
 mm/bpf_memcontrol.c        | 101 +++++++++++++++++++++++++++++++++++++
 3 files changed, 106 insertions(+)
 create mode 100644 mm/bpf_memcontrol.c

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 53364526d877..a2ecd9caacfb 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -932,6 +932,8 @@ static inline void mod_memcg_page_state(struct page *page,
 	rcu_read_unlock();
 }
 
+unsigned long memcg_events(struct mem_cgroup *memcg, int event);
+unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap);
 unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx);
 unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx);
 unsigned long lruvec_page_state_local(struct lruvec *lruvec,
diff --git a/mm/Makefile b/mm/Makefile
index e7f6bbf8ae5f..3eedba68e8cb 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -105,6 +105,9 @@ obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
 ifdef CONFIG_SWAP
 obj-$(CONFIG_MEMCG) += swap_cgroup.o
 endif
+ifdef CONFIG_BPF_SYSCALL
+obj-$(CONFIG_MEMCG) += bpf_memcontrol.o
+endif
 obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
 obj-$(CONFIG_GUP_TEST) += gup_test.o
 obj-$(CONFIG_DMAPOOL_TEST) += dmapool_test.o
diff --git a/mm/bpf_memcontrol.c b/mm/bpf_memcontrol.c
new file mode 100644
index 000000000000..dacdf53735e5
--- /dev/null
+++ b/mm/bpf_memcontrol.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Memory Controller-related BPF kfuncs and auxiliary code
+ *
+ * Author: Roman Gushchin <roman.gushchin@...ux.dev>
+ */
+
+#include <linux/memcontrol.h>
+#include <linux/bpf.h>
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc struct mem_cgroup *
+bpf_get_mem_cgroup(struct cgroup_subsys_state *css)
+{
+	struct mem_cgroup *memcg = NULL;
+	bool rcu_unlock = false;
+
+	if (!root_mem_cgroup)
+		return NULL;
+
+	if (root_mem_cgroup->css.ss != css->ss) {
+		struct cgroup *cgroup = css->cgroup;
+		int ssid = root_mem_cgroup->css.ss->id;
+
+		rcu_read_lock();
+		rcu_unlock = true;
+		css = rcu_dereference_raw(cgroup->subsys[ssid]);
+	}
+
+	if (css && css_tryget(css))
+		memcg = container_of(css, struct mem_cgroup, css);
+
+	if (rcu_unlock)
+		rcu_read_unlock();
+
+	return memcg;
+}
+
+__bpf_kfunc void bpf_put_mem_cgroup(struct mem_cgroup *memcg)
+{
+	css_put(&memcg->css);
+}
+
+__bpf_kfunc unsigned long bpf_mem_cgroup_events(struct mem_cgroup *memcg, int event)
+{
+
+	if (event < 0 || event >= NR_VM_EVENT_ITEMS)
+		return (unsigned long)-1;
+
+	return memcg_events(memcg, event);
+}
+
+__bpf_kfunc unsigned long bpf_mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
+{
+	return mem_cgroup_usage(memcg, swap);
+}
+
+__bpf_kfunc unsigned long bpf_mem_cgroup_page_state(struct mem_cgroup *memcg, int idx)
+{
+	if (idx < 0 || idx >= MEMCG_NR_STAT)
+		return (unsigned long)-1;
+
+	return memcg_page_state(memcg, idx);
+}
+
+__bpf_kfunc void bpf_mem_cgroup_flush_stats(struct mem_cgroup *memcg)
+{
+	mem_cgroup_flush_stats(memcg);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(bpf_memcontrol_kfuncs)
+BTF_ID_FLAGS(func, bpf_get_mem_cgroup, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_put_mem_cgroup, KF_RELEASE)
+
+BTF_ID_FLAGS(func, bpf_mem_cgroup_events, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_mem_cgroup_usage, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_mem_cgroup_page_state, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_mem_cgroup_flush_stats, KF_TRUSTED_ARGS)
+
+BTF_KFUNCS_END(bpf_memcontrol_kfuncs)
+
+static const struct btf_kfunc_id_set bpf_memcontrol_kfunc_set = {
+	.owner          = THIS_MODULE,
+	.set            = &bpf_memcontrol_kfuncs,
+};
+
+static int __init bpf_memcontrol_init(void)
+{
+	int err;
+
+	err = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING,
+					&bpf_memcontrol_kfunc_set);
+	if (err)
+		pr_warn("error while registering bpf memcontrol kfuncs: %d", err);
+
+	return err;
+}
+late_initcall(bpf_memcontrol_init);
-- 
2.49.0.901.g37484f566f-goog