Merge branch 'bpf-reduce-memory-usage-for-bpf_global_percpu_ma'

Yonghong Song says:

====================
bpf: Reduce memory usage for bpf_global_percpu_ma

Currently when a bpf program intends to allocate memory for percpu kptr,
the verifier will call bpf_mem_alloc_init() to prefill all supported
unit sizes and this caused memory consumption very big for large number
of cpus. For example, for 128-cpu system, the total memory consumption
with initial prefill is ~175MB. Things will become worse for systems
with even more cpus.

Patch 1 avoids unnecessary extra percpu memory allocation.
Patch 2 adds objcg to bpf_mem_alloc at init stage so objcg can be
associated with root cgroup and objcg can be passed to later
bpf_mem_alloc_percpu_unit_init().
Patch 3 addresses memory consumption issue by avoiding to prefill
with all unit sizes, i.e. only prefilling with user specified size.
Patch 4 further reduces memory consumption by limiting the
number of prefill entries for percpu memory allocation.
Patch 5 has much smaller low/high watermarks for percpu allocation
to reduce memory consumption.
Patch 6 rejects percpu memory allocation with bpf_global_percpu_ma
when allocation size is greater than 512 bytes.
Patch 7 fixed test_bpf_ma test due to Patch 5.
Patch 8 added one test to show the verification failure log message.

Changelogs:
  v5 -> v6:
    . Change bpf_mem_alloc_percpu_init() to add objcg as one of parameters.
      For bpf_global_percpu_ma, the objcg is NULL, corresponding root memcg.
  v4 -> v5:
    . Do not do bpf_global_percpu_ma initialization at init stage, instead
      doing initialization when the verifier knows it is going to be used
      by bpf prog.
    . Using much smaller low/high watermarks for percpu allocation.
  v3 -> v4:
    . Add objcg to bpf_mem_alloc during init stage.
    . Initialize objcg at init stage but use it in bpf_mem_alloc_percpu_unit_init().
    . Remove check_obj_size() in bpf_mem_alloc_percpu_unit_init().
  v2 -> v3:
    . Clear the bpf_mem_cache if prefill fails.
    . Change test_bpf_ma percpu allocation tests to use bucket_size
      as allocation size instead of bucket_size - 8.
    . Remove __GFP_ZERO flag from __alloc_percpu_gfp() call.
  v1 -> v2:
    . Avoid unnecessary extra percpu memory allocation.
    . Add a separate function to do bpf_global_percpu_ma initialization
    . promote.
    . Promote function static 'sizes' array to file static.
    . Add comments to explain to refill only one item for percpu alloc.
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: Alexei Starovoitov

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: */

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;
 

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)) {

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;

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";