Introduce BPF kfuncs to conveniently access memcg data: - bpf_mem_cgroup_vm_events(), - bpf_mem_cgroup_usage(), - bpf_mem_cgroup_page_state(), - bpf_mem_cgroup_flush_stats(). These functions are useful for implementing BPF OOM policies, but also can be used to accelerate access to the memcg data. Reading it through cgroupfs is much more expensive, roughly 5x, mostly because of the need to convert the data into the text and back. JP Kobryn: An experiment was setup to compare the performance of a program that uses the traditional method of reading memory.stat vs a program using the new kfuncs. The control program opens up the root memory.stat file and for 1M iterations reads, converts the string values to numeric data, then seeks back to the beginning. The experimental program sets up the requisite libbpf objects and for 1M iterations invokes a bpf program which uses the kfuncs to fetch all available stats for node_stat_item, memcg_stat_item, and vm_event_item types. The results showed a significant perf benefit on the experimental side, outperforming the control side by a margin of 93%. In kernel mode, elapsed time was reduced by 80%, while in user mode, over 99% of time was saved. control: elapsed time real 0m38.318s user 0m25.131s sys 0m13.070s experiment: elapsed time real 0m2.789s user 0m0.187s sys 0m2.512s control: perf data 33.43% a.out libc.so.6 [.] __vfscanf_internal 6.88% a.out [kernel.kallsyms] [k] vsnprintf 6.33% a.out libc.so.6 [.] _IO_fgets 5.51% a.out [kernel.kallsyms] [k] format_decode 4.31% a.out libc.so.6 [.] __GI_____strtoull_l_internal 3.78% a.out [kernel.kallsyms] [k] string 3.53% a.out [kernel.kallsyms] [k] number 2.71% a.out libc.so.6 [.] _IO_sputbackc 2.41% a.out [kernel.kallsyms] [k] strlen 1.98% a.out a.out [.] main 1.70% a.out libc.so.6 [.] _IO_getline_info 1.51% a.out libc.so.6 [.] __isoc99_sscanf 1.47% a.out [kernel.kallsyms] [k] memory_stat_format 1.47% a.out [kernel.kallsyms] [k] memcpy_orig 1.41% a.out [kernel.kallsyms] [k] seq_buf_printf experiment: perf data 10.55% memcgstat bpf_prog_..._query [k] bpf_prog_16aab2f19fa982a7_query 6.90% memcgstat [kernel.kallsyms] [k] memcg_page_state_output 3.55% memcgstat [kernel.kallsyms] [k] _raw_spin_lock 3.12% memcgstat [kernel.kallsyms] [k] memcg_events 2.87% memcgstat [kernel.kallsyms] [k] __memcg_slab_post_alloc_hook 2.73% memcgstat [kernel.kallsyms] [k] kmem_cache_free 2.70% memcgstat [kernel.kallsyms] [k] entry_SYSRETQ_unsafe_stack 2.25% memcgstat [kernel.kallsyms] [k] __memcg_slab_free_hook 2.06% memcgstat [kernel.kallsyms] [k] get_page_from_freelist Signed-off-by: Roman Gushchin Co-developed-by: JP Kobryn Signed-off-by: JP Kobryn Acked-by: Michal Hocko --- include/linux/memcontrol.h | 2 ++ mm/bpf_memcontrol.c | 55 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b309d13110af..8c1ba4477d36 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -949,6 +949,8 @@ 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 memcg_page_state_output(struct mem_cgroup *memcg, int item); unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx); diff --git a/mm/bpf_memcontrol.c b/mm/bpf_memcontrol.c index 6d0d73bf0dd1..4d9d7d909f6c 100644 --- a/mm/bpf_memcontrol.c +++ b/mm/bpf_memcontrol.c @@ -75,6 +75,56 @@ __bpf_kfunc void bpf_put_mem_cgroup(struct mem_cgroup *memcg) css_put(&memcg->css); } +/** + * bpf_mem_cgroup_vm_events - Read memory cgroup's vm event counter + * @memcg: memory cgroup + * @event: event id + * + * Allows to read memory cgroup event counters. + */ +__bpf_kfunc unsigned long bpf_mem_cgroup_vm_events(struct mem_cgroup *memcg, + enum vm_event_item event) +{ + 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) * PAGE_SIZE; +} + +/** + * bpf_mem_cgroup_page_state - Read memory cgroup's page state counter + * @memcg: memory cgroup + * @idx: counter idx + * + * Allows to read memory cgroup statistics. The output is in bytes. + */ +__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_output(memcg, idx); +} + +/** + * bpf_mem_cgroup_flush_stats - Flush memory cgroup's statistics + * @memcg: memory cgroup + * + * Propagate memory cgroup's statistics up the cgroup tree. + */ +__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) @@ -82,6 +132,11 @@ BTF_ID_FLAGS(func, bpf_get_root_mem_cgroup, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_get_mem_cgroup, KF_TRUSTED_ARGS | KF_ACQUIRE | KF_RET_NULL | KF_RCU) BTF_ID_FLAGS(func, bpf_put_mem_cgroup, KF_TRUSTED_ARGS | KF_RELEASE) +BTF_ID_FLAGS(func, bpf_mem_cgroup_vm_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 | KF_SLEEPABLE) + BTF_KFUNCS_END(bpf_memcontrol_kfuncs) static const struct btf_kfunc_id_set bpf_memcontrol_kfunc_set = { -- 2.52.0