diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index bb1223b213087..aaf004d943228 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -11,6 +11,7 @@ struct bpf_mem_caches; struct bpf_mem_alloc { struct bpf_mem_caches __percpu *caches; struct bpf_mem_cache __percpu *cache; + struct obj_cgroup *objcg; bool percpu; struct work_struct work; }; @@ -21,8 +22,15 @@ struct bpf_mem_alloc { * 'size = 0' is for bpf_mem_alloc which manages many fixed-size objects. * Alloc and free are done with bpf_mem_{alloc,free}() and the size of * the returned object is given by the size argument of bpf_mem_alloc(). + * If percpu equals true, error will be returned in order to avoid + * large memory consumption and the below bpf_mem_alloc_percpu_unit_init() + * should be used to do on-demand per-cpu allocation for each size. */ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu); +/* Initialize a non-fix-size percpu memory allocator */ +int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg); +/* The percpu allocation with a specific unit size. */ +int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); /* kmalloc/kfree equivalent: */ diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index aa0fbf000a12b..460c8f38fed6d 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -121,6 +121,8 @@ struct bpf_mem_caches { struct bpf_mem_cache cache[NUM_CACHES]; }; +static const u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096}; + static struct llist_node notrace *__llist_del_first(struct llist_head *head) { struct llist_node *entry, *next; @@ -462,11 +464,17 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c) * consume ~ 11 Kbyte per cpu. * Typical case will be between 11K and 116K closer to 11K. * bpf progs can and should share bpf_mem_cache when possible. + * + * Percpu allocation is typically rare. To avoid potential unnecessary large + * memory consumption, set low_mark = 1 and high_mark = 3, resulting in c->batch = 1. */ static void init_refill_work(struct bpf_mem_cache *c) { init_irq_work(&c->refill_work, bpf_mem_refill); - if (c->unit_size <= 256) { + if (c->percpu_size) { + c->low_watermark = 1; + c->high_watermark = 3; + } else if (c->unit_size <= 256) { c->low_watermark = 32; c->high_watermark = 96; } else { @@ -483,11 +491,16 @@ static void init_refill_work(struct bpf_mem_cache *c) static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) { - /* To avoid consuming memory assume that 1st run of bpf - * prog won't be doing more than 4 map_update_elem from - * irq disabled region + int cnt = 1; + + /* To avoid consuming memory, for non-percpu allocation, assume that + * 1st run of bpf prog won't be doing more than 4 map_update_elem from + * irq disabled region if unit size is less than or equal to 256. + * For all other cases, let us just do one allocation. */ - alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false); + if (!c->percpu_size && c->unit_size <= 256) + cnt = 4; + alloc_bulk(c, cnt, cpu_to_node(cpu), false); } /* When size != 0 bpf_mem_cache for each cpu. @@ -499,12 +512,14 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) */ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) { - static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096}; struct bpf_mem_caches *cc, __percpu *pcc; struct bpf_mem_cache *c, __percpu *pc; struct obj_cgroup *objcg = NULL; int cpu, i, unit_size, percpu_size = 0; + if (percpu && size == 0) + return -EINVAL; + /* room for llist_node and per-cpu pointer */ if (percpu) percpu_size = LLIST_NODE_SZ + sizeof(void *); @@ -523,6 +538,8 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) if (memcg_bpf_enabled()) objcg = get_obj_cgroup_from_current(); #endif + ma->objcg = objcg; + for_each_possible_cpu(cpu) { c = per_cpu_ptr(pc, cpu); c->unit_size = unit_size; @@ -542,6 +559,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) #ifdef CONFIG_MEMCG_KMEM objcg = get_obj_cgroup_from_current(); #endif + ma->objcg = objcg; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(pcc, cpu); for (i = 0; i < NUM_CACHES; i++) { @@ -560,6 +578,56 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) return 0; } +int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg) +{ + struct bpf_mem_caches __percpu *pcc; + + pcc = __alloc_percpu_gfp(sizeof(struct bpf_mem_caches), 8, GFP_KERNEL); + if (!pcc) + return -ENOMEM; + + ma->caches = pcc; + ma->objcg = objcg; + ma->percpu = true; + return 0; +} + +int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size) +{ + struct bpf_mem_caches *cc, __percpu *pcc; + int cpu, i, unit_size, percpu_size; + struct obj_cgroup *objcg; + struct bpf_mem_cache *c; + + i = bpf_mem_cache_idx(size); + if (i < 0) + return -EINVAL; + + /* room for llist_node and per-cpu pointer */ + percpu_size = LLIST_NODE_SZ + sizeof(void *); + + unit_size = sizes[i]; + objcg = ma->objcg; + pcc = ma->caches; + + for_each_possible_cpu(cpu) { + cc = per_cpu_ptr(pcc, cpu); + c = &cc->cache[i]; + if (cpu == 0 && c->unit_size) + break; + + c->unit_size = unit_size; + c->objcg = objcg; + c->percpu_size = percpu_size; + c->tgt = c; + + init_refill_work(c); + prefill_mem_cache(c, cpu); + } + + return 0; +} + static void drain_mem_cache(struct bpf_mem_cache *c) { bool percpu = !!c->percpu_size; @@ -691,9 +759,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } - /* objcg is the same across cpus */ - if (c->objcg) - obj_cgroup_put(c->objcg); + if (ma->objcg) + obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } if (ma->caches) { @@ -709,8 +776,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } } - if (c->objcg) - obj_cgroup_put(c->objcg); + if (ma->objcg) + obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } } @@ -833,7 +900,9 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size) if (!size) return NULL; - idx = bpf_mem_cache_idx(size + LLIST_NODE_SZ); + if (!ma->percpu) + size += LLIST_NODE_SZ; + idx = bpf_mem_cache_idx(size); if (idx < 0) return NULL; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d4e31f61de0ef..d5f4ff1eb235d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -195,6 +195,8 @@ struct bpf_verifier_stack_elem { POISON_POINTER_DELTA)) #define BPF_MAP_PTR(X) ((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV)) +#define BPF_GLOBAL_PERCPU_MA_MAX_SIZE 512 + static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx); static int release_reference(struct bpf_verifier_env *env, int ref_obj_id); static void invalidate_non_owning_refs(struct bpf_verifier_env *env); @@ -12139,20 +12141,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set) return -ENOMEM; - if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { - if (!bpf_global_percpu_ma_set) { - mutex_lock(&bpf_percpu_ma_lock); - if (!bpf_global_percpu_ma_set) { - err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true); - if (!err) - bpf_global_percpu_ma_set = true; - } - mutex_unlock(&bpf_percpu_ma_lock); - if (err) - return err; - } - } - if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) { verbose(env, "local type ID argument must be in range [0, U32_MAX]\n"); return -EINVAL; @@ -12173,6 +12161,35 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EINVAL; } + if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { + if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) { + verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n", + ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE); + return -EINVAL; + } + + if (!bpf_global_percpu_ma_set) { + mutex_lock(&bpf_percpu_ma_lock); + if (!bpf_global_percpu_ma_set) { + /* Charge memory allocated with bpf_global_percpu_ma to + * root memcg. The obj_cgroup for root memcg is NULL. + */ + err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL); + if (!err) + bpf_global_percpu_ma_set = true; + } + mutex_unlock(&bpf_percpu_ma_lock); + if (err) + return err; + } + + mutex_lock(&bpf_percpu_ma_lock); + err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size); + mutex_unlock(&bpf_percpu_ma_lock); + if (err) + return err; + } + struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id); if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) { diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c index d3491a84b3b98..ccae0b31ac6c6 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c +++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c @@ -14,7 +14,8 @@ static void do_bpf_ma_test(const char *name) struct test_bpf_ma *skel; struct bpf_program *prog; struct btf *btf; - int i, err; + int i, err, id; + char tname[32]; skel = test_bpf_ma__open(); if (!ASSERT_OK_PTR(skel, "open")) @@ -25,16 +26,21 @@ static void do_bpf_ma_test(const char *name) goto out; for (i = 0; i < ARRAY_SIZE(skel->rodata->data_sizes); i++) { - char name[32]; - int id; - - snprintf(name, sizeof(name), "bin_data_%u", skel->rodata->data_sizes[i]); - id = btf__find_by_name_kind(btf, name, BTF_KIND_STRUCT); - if (!ASSERT_GT(id, 0, "bin_data")) + snprintf(tname, sizeof(tname), "bin_data_%u", skel->rodata->data_sizes[i]); + id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT); + if (!ASSERT_GT(id, 0, tname)) goto out; skel->rodata->data_btf_ids[i] = id; } + for (i = 0; i < ARRAY_SIZE(skel->rodata->percpu_data_sizes); i++) { + snprintf(tname, sizeof(tname), "percpu_bin_data_%u", skel->rodata->percpu_data_sizes[i]); + id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT); + if (!ASSERT_GT(id, 0, tname)) + goto out; + skel->rodata->percpu_data_btf_ids[i] = id; + } + prog = bpf_object__find_program_by_name(skel->obj, name); if (!ASSERT_OK_PTR(prog, "invalid prog name")) goto out; diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c index 1a891d30f1fe0..f2b8eb2ff76f7 100644 --- a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c +++ b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c @@ -17,6 +17,10 @@ struct val_with_rb_root_t { struct bpf_spin_lock lock; }; +struct val_600b_t { + char b[600]; +}; + struct elem { long sum; struct val_t __percpu_kptr *pc; @@ -161,4 +165,18 @@ int BPF_PROG(test_array_map_7) return 0; } +SEC("?fentry.s/bpf_fentry_test1") +__failure __msg("bpf_percpu_obj_new type size (600) is greater than 512") +int BPF_PROG(test_array_map_8) +{ + struct val_600b_t __percpu_kptr *p; + + p = bpf_percpu_obj_new(struct val_600b_t); + if (!p) + return 0; + + bpf_percpu_obj_drop(p); + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c index b78f4f702ae0f..3494ca30fa7fe 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_ma.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c @@ -20,6 +20,9 @@ char _license[] SEC("license") = "GPL"; const unsigned int data_sizes[] = {16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096}; const volatile unsigned int data_btf_ids[ARRAY_SIZE(data_sizes)] = {}; +const unsigned int percpu_data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512}; +const volatile unsigned int percpu_data_btf_ids[ARRAY_SIZE(data_sizes)] = {}; + int err = 0; u32 pid = 0; @@ -27,10 +30,10 @@ u32 pid = 0; struct bin_data_##_size { \ char data[_size - sizeof(void *)]; \ }; \ + /* See Commit 5d8d6634ccc, force btf generation for type bin_data_##_size */ \ + struct bin_data_##_size *__bin_data_##_size; \ struct map_value_##_size { \ struct bin_data_##_size __kptr * data; \ - /* To emit BTF info for bin_data_xx */ \ - struct bin_data_##_size not_used; \ }; \ struct { \ __uint(type, BPF_MAP_TYPE_ARRAY); \ @@ -40,8 +43,12 @@ u32 pid = 0; } array_##_size SEC(".maps") #define DEFINE_ARRAY_WITH_PERCPU_KPTR(_size) \ + struct percpu_bin_data_##_size { \ + char data[_size]; \ + }; \ + struct percpu_bin_data_##_size *__percpu_bin_data_##_size; \ struct map_value_percpu_##_size { \ - struct bin_data_##_size __percpu_kptr * data; \ + struct percpu_bin_data_##_size __percpu_kptr * data; \ }; \ struct { \ __uint(type, BPF_MAP_TYPE_ARRAY); \ @@ -114,7 +121,7 @@ static __always_inline void batch_percpu_alloc(struct bpf_map *map, unsigned int return; } /* per-cpu allocator may not be able to refill in time */ - new = bpf_percpu_obj_new_impl(data_btf_ids[idx], NULL); + new = bpf_percpu_obj_new_impl(percpu_data_btf_ids[idx], NULL); if (!new) continue; @@ -179,7 +186,7 @@ DEFINE_ARRAY_WITH_KPTR(1024); DEFINE_ARRAY_WITH_KPTR(2048); DEFINE_ARRAY_WITH_KPTR(4096); -/* per-cpu kptr doesn't support bin_data_8 which is a zero-sized array */ +DEFINE_ARRAY_WITH_PERCPU_KPTR(8); DEFINE_ARRAY_WITH_PERCPU_KPTR(16); DEFINE_ARRAY_WITH_PERCPU_KPTR(32); DEFINE_ARRAY_WITH_PERCPU_KPTR(64); @@ -188,9 +195,6 @@ DEFINE_ARRAY_WITH_PERCPU_KPTR(128); DEFINE_ARRAY_WITH_PERCPU_KPTR(192); DEFINE_ARRAY_WITH_PERCPU_KPTR(256); DEFINE_ARRAY_WITH_PERCPU_KPTR(512); -DEFINE_ARRAY_WITH_PERCPU_KPTR(1024); -DEFINE_ARRAY_WITH_PERCPU_KPTR(2048); -DEFINE_ARRAY_WITH_PERCPU_KPTR(4096); SEC("?fentry/" SYS_PREFIX "sys_nanosleep") int test_batch_alloc_free(void *ctx) @@ -246,20 +250,18 @@ int test_batch_percpu_alloc_free(void *ctx) if ((u32)bpf_get_current_pid_tgid() != pid) return 0; - /* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling, - * then free 128 16-bytes per-cpu objects in batch to trigger freeing. + /* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling, + * then free 128 8-bytes per-cpu objects in batch to trigger freeing. */ - CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 0); - CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 1); - CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 2); - CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 3); - CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 4); - CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 5); - CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 6); - CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 7); - CALL_BATCH_PERCPU_ALLOC_FREE(1024, 32, 8); - CALL_BATCH_PERCPU_ALLOC_FREE(2048, 16, 9); - CALL_BATCH_PERCPU_ALLOC_FREE(4096, 8, 10); + CALL_BATCH_PERCPU_ALLOC_FREE(8, 128, 0); + CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 1); + CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 2); + CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 3); + CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 4); + CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 5); + CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 6); + CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 7); + CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 8); return 0; } @@ -270,20 +272,18 @@ int test_percpu_free_through_map_free(void *ctx) if ((u32)bpf_get_current_pid_tgid() != pid) return 0; - /* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling, + /* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling, * then free these object through map free. */ - CALL_BATCH_PERCPU_ALLOC(16, 128, 0); - CALL_BATCH_PERCPU_ALLOC(32, 128, 1); - CALL_BATCH_PERCPU_ALLOC(64, 128, 2); - CALL_BATCH_PERCPU_ALLOC(96, 128, 3); - CALL_BATCH_PERCPU_ALLOC(128, 128, 4); - CALL_BATCH_PERCPU_ALLOC(192, 128, 5); - CALL_BATCH_PERCPU_ALLOC(256, 128, 6); - CALL_BATCH_PERCPU_ALLOC(512, 64, 7); - CALL_BATCH_PERCPU_ALLOC(1024, 32, 8); - CALL_BATCH_PERCPU_ALLOC(2048, 16, 9); - CALL_BATCH_PERCPU_ALLOC(4096, 8, 10); + CALL_BATCH_PERCPU_ALLOC(8, 128, 0); + CALL_BATCH_PERCPU_ALLOC(16, 128, 1); + CALL_BATCH_PERCPU_ALLOC(32, 128, 2); + CALL_BATCH_PERCPU_ALLOC(64, 128, 3); + CALL_BATCH_PERCPU_ALLOC(96, 128, 4); + CALL_BATCH_PERCPU_ALLOC(128, 128, 5); + CALL_BATCH_PERCPU_ALLOC(192, 128, 6); + CALL_BATCH_PERCPU_ALLOC(256, 128, 7); + CALL_BATCH_PERCPU_ALLOC(512, 64, 8); return 0; }