| 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
| ||
|
Message-ID: <CAP01T77yTb69hhi0CtDp9afVzO3T0fyPqhBF7By-iYYy__uOjA@mail.gmail.com>
Date: Wed, 20 Aug 2025 11:21:10 +0200
From: Kumar Kartikeya Dwivedi <memxor@...il.com>
To: Roman Gushchin <roman.gushchin@...ux.dev>
Cc: linux-mm@...ck.org, bpf@...r.kernel.org,
Suren Baghdasaryan <surenb@...gle.com>, Johannes Weiner <hannes@...xchg.org>, Michal Hocko <mhocko@...e.com>,
David Rientjes <rientjes@...gle.com>, Matt Bobrowski <mattbobrowski@...gle.com>,
Song Liu <song@...nel.org>, Alexei Starovoitov <ast@...nel.org>,
Andrew Morton <akpm@...ux-foundation.org>, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v1 04/14] mm: introduce bpf kfuncs to deal with memcg pointers
On Mon, 18 Aug 2025 at 19:02, Roman Gushchin <roman.gushchin@...ux.dev> wrote:
>
> 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 | 1 +
> mm/bpf_memcontrol.c | 151 +++++++++++++++++++++++++++++++++++++
> 3 files changed, 154 insertions(+)
> create mode 100644 mm/bpf_memcontrol.c
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 87b6688f124a..785a064000cd 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 a714aba03759..c397af904a87 100644
> --- a/mm/Makefile
> +++ b/mm/Makefile
> @@ -107,6 +107,7 @@ obj-$(CONFIG_MEMCG) += swap_cgroup.o
> endif
> ifdef CONFIG_BPF_SYSCALL
> obj-y += bpf_oom.o
> +obj-$(CONFIG_MEMCG) += bpf_memcontrol.o
> endif
> obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
> obj-$(CONFIG_GUP_TEST) += gup_test.o
> diff --git a/mm/bpf_memcontrol.c b/mm/bpf_memcontrol.c
> new file mode 100644
> index 000000000000..66f2a359af7e
> --- /dev/null
> +++ b/mm/bpf_memcontrol.c
> @@ -0,0 +1,151 @@
> +// 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_get_mem_cgroup - Get a reference to a memory cgroup
> + * @css: pointer to the css structure
> + *
> + * Returns a pointer to a mem_cgroup structure after bumping
> + * the corresponding css's reference counter.
> + *
> + * It's fine to pass a css which belongs to any cgroup controller,
> + * e.g. unified hierarchy's main css.
> + *
> + * Implements KF_ACQUIRE semantics.
> + */
> +__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_put_mem_cgroup - Put a reference to a memory cgroup
> + * @memcg: memory cgroup to release
> + *
> + * Releases a previously acquired memcg reference.
> + * Implements KF_RELEASE semantics.
> + */
> +__bpf_kfunc void bpf_put_mem_cgroup(struct mem_cgroup *memcg)
> +{
> + css_put(&memcg->css);
> +}
> +
> +/**
> + * bpf_mem_cgroup_events - Read memory cgroup's event counter
> + * @memcg: memory cgroup
> + * @event: event idx
> + *
> + * Allows to read memory cgroup event counters.
> + */
> +__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_mem_cgroup_usage - Read memory cgroup's usage
> + * @memcg: memory cgroup
> + *
> + * Returns current memory cgroup size in bytes.
> + */
> +__bpf_kfunc unsigned long bpf_mem_cgroup_usage(struct mem_cgroup *memcg)
> +{
> + return page_counter_read(&memcg->memory);
> +}
> +
> +/**
> + * bpf_mem_cgroup_events - Read memory cgroup's page state counter
> + * @memcg: memory cgroup
> + * @event: event idx
> + *
> + * Allows to read memory cgroup statistics.
> + */
> +__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_mem_cgroup_flush_stats - Flush memory cgroup's statistics
> + * @memcg: memory cgroup
> + *
> + * Propagate memory cgroup's statistics up the cgroup tree.
> + *
> + * Note, that this function uses the rate-limited version of
> + * mem_cgroup_flush_stats() to avoid hurting the system-wide
> + * performance. So bpf_mem_cgroup_flush_stats() guarantees only
> + * that statistics is not stale beyond 2*FLUSH_TIME.
> + */
> +__bpf_kfunc void bpf_mem_cgroup_flush_stats(struct mem_cgroup *memcg)
> +{
> + mem_cgroup_flush_stats_ratelimited(memcg);
> +}
> +
> +__bpf_kfunc_end_defs();
> +
> +BTF_KFUNCS_START(bpf_memcontrol_kfuncs)
> +BTF_ID_FLAGS(func, bpf_get_mem_cgroup, KF_ACQUIRE | KF_RET_NULL)
I think you could set KF_TRUSTED_ARGS for this as well.
> +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_STRUCT_OPS,
> + &bpf_memcontrol_kfunc_set);
> + if (err)
> + pr_warn("error while registering bpf memcontrol kfuncs: %d", err);
> +
> + return err;
> +}
> +late_initcall(bpf_memcontrol_init);
> --
> 2.50.1
>
Powered by blists - more mailing lists