bpf: switch to memcg-based memory accounting

.travis.yml

@@ -0,0 +1,33 @@
+sudo: required
+language: bash
+dist: bionic
+services:
+    - docker
+
+env:
+    global:
+        - PROJECT_NAME='libbpf'
+        - AUTHOR_EMAIL="$(git log -1 --pretty=\"%aE\")"
+        - REPO_ROOT="$TRAVIS_BUILD_DIR"
+        - CI_ROOT="$REPO_ROOT/travis-ci"
+        - VMTEST_ROOT="$CI_ROOT/vmtest"
+
+addons:
+    apt:
+        packages:
+            - qemu-kvm
+            - zstd
+            - binutils-dev
+            - elfutils
+            - libcap-dev
+            - libelf-dev
+            - libdw-dev
+            - python3-docutils
+
+jobs:
+    include:
+        - stage: Builds & Tests
+          name: Kernel LATEST + selftests
+          language: bash
+          env: KERNEL=LATEST
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate 1

include/linux/bpf.h

@@ -37,6 +37,7 @@ struct bpf_iter_aux_info;
 struct bpf_local_storage;
 struct bpf_local_storage_map;
 struct kobject;
+struct mem_cgroup;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -135,11 +136,6 @@ struct bpf_map_ops {
 	const struct bpf_iter_seq_info *iter_seq_info;
 };
 
-struct bpf_map_memory {
-	u32 pages;
-	struct user_struct *user;
-};
-
 struct bpf_map {
 	/* The first two cachelines with read-mostly members of which some
 	 * are also accessed in fast-path (e.g. ops, max_entries).
@@ -160,7 +156,9 @@ struct bpf_map {
 	u32 btf_key_type_id;
 	u32 btf_value_type_id;
 	struct btf *btf;
-	struct bpf_map_memory memory;
+#ifdef CONFIG_MEMCG_KMEM
+	struct mem_cgroup *memcg;
+#endif
 	char name[BPF_OBJ_NAME_LEN];
 	u32 btf_vmlinux_value_type_id;
 	bool bypass_spec_v1;
@@ -1202,8 +1200,6 @@ void bpf_prog_sub(struct bpf_prog *prog, int i);
 void bpf_prog_inc(struct bpf_prog *prog);
 struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
-int __bpf_prog_charge(struct user_struct *user, u32 pages);
-void __bpf_prog_uncharge(struct user_struct *user, u32 pages);
 void __bpf_free_used_maps(struct bpf_prog_aux *aux,
 			  struct bpf_map **used_maps, u32 len);
 
@@ -1218,12 +1214,6 @@ void bpf_map_inc_with_uref(struct bpf_map *map);
 struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
-int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
-void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
-int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size);
-void bpf_map_charge_finish(struct bpf_map_memory *mem);
-void bpf_map_charge_move(struct bpf_map_memory *dst,
-			 struct bpf_map_memory *src);
 void *bpf_map_area_alloc(u64 size, int numa_node);
 void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
 void bpf_map_area_free(void *base);
@@ -1490,15 +1480,6 @@ bpf_prog_inc_not_zero(struct bpf_prog *prog)
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
-static inline int __bpf_prog_charge(struct user_struct *user, u32 pages)
-{
-	return 0;
-}
-
-static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
-{
-}
-
 static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
 				 const struct bpf_link_ops *ops,
 				 struct bpf_prog *prog)

kernel/bpf/arraymap.c

@@ -30,12 +30,12 @@ static void bpf_array_free_percpu(struct bpf_array *array)
 
 static int bpf_array_alloc_percpu(struct bpf_array *array)
 {
+	const gfp_t gfp = GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT;
 	void __percpu *ptr;
 	int i;
 
 	for (i = 0; i < array->map.max_entries; i++) {
-		ptr = __alloc_percpu_gfp(array->elem_size, 8,
-					 GFP_USER | __GFP_NOWARN);
+		ptr = __alloc_percpu_gfp(array->elem_size, 8, gfp);
 		if (!ptr) {
 			bpf_array_free_percpu(array);
 			return -ENOMEM;
@@ -81,11 +81,10 @@ int array_map_alloc_check(union bpf_attr *attr)
 static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 {
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
-	int ret, numa_node = bpf_map_attr_numa_node(attr);
+	int numa_node = bpf_map_attr_numa_node(attr);
 	u32 elem_size, index_mask, max_entries;
 	bool bypass_spec_v1 = bpf_bypass_spec_v1();
-	u64 cost, array_size, mask64;
-	struct bpf_map_memory mem;
+	u64 array_size, mask64;
 	struct bpf_array *array;
 
 	elem_size = round_up(attr->value_size, 8);
@@ -126,44 +125,29 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 		}
 	}
 
-	/* make sure there is no u32 overflow later in round_up() */
-	cost = array_size;
-	if (percpu)
-		cost += (u64)attr->max_entries * elem_size * num_possible_cpus();
-
-	ret = bpf_map_charge_init(&mem, cost);
-	if (ret < 0)
-		return ERR_PTR(ret);
-
 	/* allocate all map elements and zero-initialize them */
 	if (attr->map_flags & BPF_F_MMAPABLE) {
 		void *data;
 
 		/* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */
 		data = bpf_map_area_mmapable_alloc(array_size, numa_node);
-		if (!data) {
-			bpf_map_charge_finish(&mem);
+		if (!data)
 			return ERR_PTR(-ENOMEM);
-		}
 		array = data + PAGE_ALIGN(sizeof(struct bpf_array))
 			- offsetof(struct bpf_array, value);
 	} else {
 		array = bpf_map_area_alloc(array_size, numa_node);
 	}
-	if (!array) {
-		bpf_map_charge_finish(&mem);
+	if (!array)
 		return ERR_PTR(-ENOMEM);
-	}
 	array->index_mask = index_mask;
 	array->map.bypass_spec_v1 = bypass_spec_v1;
 
 	/* copy mandatory map attributes */
 	bpf_map_init_from_attr(&array->map, attr);
-	bpf_map_charge_move(&array->map.memory, &mem);
 	array->elem_size = elem_size;
 
 	if (percpu && bpf_array_alloc_percpu(array)) {
-		bpf_map_charge_finish(&array->map.memory);
 		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -1018,7 +1002,7 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
 	struct bpf_array_aux *aux;
 	struct bpf_map *map;
 
-	aux = kzalloc(sizeof(*aux), GFP_KERNEL);
+	aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT);
 	if (!aux)
 		return ERR_PTR(-ENOMEM);
 

kernel/bpf/bpf_local_storage.c

@@ -67,7 +67,8 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
 	if (charge_mem && mem_charge(smap, owner, smap->elem_size))
 		return NULL;
 
-	selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
+	selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN |
+			__GFP_ACCOUNT);
 	if (selem) {
 		if (value)
 			memcpy(SDATA(selem)->data, value, smap->map.value_size);
@@ -543,10 +544,8 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
 	struct bpf_local_storage_map *smap;
 	unsigned int i;
 	u32 nbuckets;
-	u64 cost;
-	int ret;
 
-	smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN);
+	smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT);
 	if (!smap)
 		return ERR_PTR(-ENOMEM);
 	bpf_map_init_from_attr(&smap->map, attr);
@@ -555,18 +554,9 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
 	/* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
 	nbuckets = max_t(u32, 2, nbuckets);
 	smap->bucket_log = ilog2(nbuckets);
-	cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);
-
-	ret = bpf_map_charge_init(&smap->map.memory, cost);
-	if (ret < 0) {
-		kfree(smap);
-		return ERR_PTR(ret);
-	}
-
 	smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
-				 GFP_USER | __GFP_NOWARN);
+				 GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT);
 	if (!smap->buckets) {
-		bpf_map_charge_finish(&smap->map.memory);
 		kfree(smap);
 		return ERR_PTR(-ENOMEM);
 	}

kernel/bpf/bpf_struct_ops.c

@@ -548,12 +548,10 @@ static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr)
 static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 {
 	const struct bpf_struct_ops *st_ops;
-	size_t map_total_size, st_map_size;
+	size_t st_map_size;
 	struct bpf_struct_ops_map *st_map;
 	const struct btf_type *t, *vt;
-	struct bpf_map_memory mem;
 	struct bpf_map *map;
-	int err;
 
 	if (!bpf_capable())
 		return ERR_PTR(-EPERM);
@@ -573,20 +571,11 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 		 * struct bpf_struct_ops_tcp_congestions_ops
 		 */
 		(vt->size - sizeof(struct bpf_struct_ops_value));
-	map_total_size = st_map_size +
-		/* uvalue */
-		sizeof(vt->size) +
-		/* struct bpf_progs **progs */
-		 btf_type_vlen(t) * sizeof(struct bpf_prog *);
-	err = bpf_map_charge_init(&mem, map_total_size);
-	if (err < 0)
-		return ERR_PTR(err);
 
 	st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE);
-	if (!st_map) {
-		bpf_map_charge_finish(&mem);
+	if (!st_map)
 		return ERR_PTR(-ENOMEM);
-	}
+
 	st_map->st_ops = st_ops;
 	map = &st_map->map;
 
@@ -597,14 +586,12 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
 	if (!st_map->uvalue || !st_map->progs || !st_map->image) {
 		bpf_struct_ops_map_free(map);
-		bpf_map_charge_finish(&mem);
 		return ERR_PTR(-ENOMEM);
 	}
 
 	mutex_init(&st_map->lock);
 	set_vm_flush_reset_perms(st_map->image);
 	bpf_map_init_from_attr(map, attr);
-	bpf_map_charge_move(&map->memory, &mem);
 
 	return map;
 }

kernel/bpf/core.c

@@ -77,7 +77,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
 
 struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags)
 {
-	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+	gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
 	struct bpf_prog_aux *aux;
 	struct bpf_prog *fp;
 
@@ -86,7 +86,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 	if (fp == NULL)
 		return NULL;
 
-	aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
+	aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags);
 	if (aux == NULL) {
 		vfree(fp);
 		return NULL;
@@ -106,7 +106,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 
 struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
 {
-	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+	gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
 	struct bpf_prog *prog;
 	int cpu;
 
@@ -138,7 +138,7 @@ int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog)
 
 	prog->aux->jited_linfo = kcalloc(prog->aux->nr_linfo,
 					 sizeof(*prog->aux->jited_linfo),
-					 GFP_KERNEL | __GFP_NOWARN);
+					 GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
 	if (!prog->aux->jited_linfo)
 		return -ENOMEM;
 
@@ -219,25 +219,17 @@ void bpf_prog_free_linfo(struct bpf_prog *prog)
 struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 				  gfp_t gfp_extra_flags)
 {
-	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+	gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
 	struct bpf_prog *fp;
-	u32 pages, delta;
-	int ret;
+	u32 pages;
 
 	size = round_up(size, PAGE_SIZE);
 	pages = size / PAGE_SIZE;
 	if (pages <= fp_old->pages)
 		return fp_old;
 
-	delta = pages - fp_old->pages;
-	ret = __bpf_prog_charge(fp_old->aux->user, delta);
-	if (ret)
-		return NULL;
-
 	fp = __vmalloc(size, gfp_flags);
-	if (fp == NULL) {
-		__bpf_prog_uncharge(fp_old->aux->user, delta);
-	} else {
+	if (fp) {
 		memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
 		fp->pages = pages;
 		fp->aux->prog = fp;