From: Joanne Koong <joannekoong@fb.com>
Date: Wed, 27 Oct 2021 16:45:00 -0700
Subject: bpf: Add bloom filter map implementation
Patch-mainline: v5.16-rc1
Git-commit: 9330986c03006ab1d33d243b7cfe598a7a3c1baa
References: jsc#PED-1377
This patch adds the kernel-side changes for the implementation of
a bpf bloom filter map.
The bloom filter map supports peek (determining whether an element
is present in the map) and push (adding an element to the map)
operations.These operations are exposed to userspace applications
through the already existing syscalls in the following way:
BPF_MAP_LOOKUP_ELEM -> peek
BPF_MAP_UPDATE_ELEM -> push
The bloom filter map does not have keys, only values. In light of
this, the bloom filter map's API matches that of queue stack maps:
user applications use BPF_MAP_LOOKUP_ELEM/BPF_MAP_UPDATE_ELEM
which correspond internally to bpf_map_peek_elem/bpf_map_push_elem,
and bpf programs must use the bpf_map_peek_elem and bpf_map_push_elem
APIs to query or add an element to the bloom filter map. When the
bloom filter map is created, it must be created with a key_size of 0.
For updates, the user will pass in the element to add to the map
as the value, with a NULL key. For lookups, the user will pass in the
element to query in the map as the value, with a NULL key. In the
verifier layer, this requires us to modify the argument type of
a bloom filter's BPF_FUNC_map_peek_elem call to ARG_PTR_TO_MAP_VALUE;
as well, in the syscall layer, we need to copy over the user value
so that in bpf_map_peek_elem, we know which specific value to query.
A few things to please take note of:
* If there are any concurrent lookups + updates, the user is
responsible for synchronizing this to ensure no false negative lookups
occur.
* The number of hashes to use for the bloom filter is configurable from
userspace. If no number is specified, the default used will be 5 hash
functions. The benchmarks later in this patchset can help compare the
performance of using different number of hashes on different entry
sizes. In general, using more hashes decreases both the false positive
rate and the speed of a lookup.
* Deleting an element in the bloom filter map is not supported.
* The bloom filter map may be used as an inner map.
* The "max_entries" size that is specified at map creation time is used
to approximate a reasonable bitmap size for the bloom filter, and is not
otherwise strictly enforced. If the user wishes to insert more entries
into the bloom filter than "max_entries", they may do so but they should
be aware that this may lead to a higher false positive rate.
Signed-off-by: Joanne Koong <joannekoong@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211027234504.30744-2-joannekoong@fb.com
Acked-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
---
include/linux/bpf.h | 1
include/linux/bpf_types.h | 1
include/uapi/linux/bpf.h | 9 +
kernel/bpf/Makefile | 2
kernel/bpf/bloom_filter.c | 195 +++++++++++++++++++++++++++++++++++++++++
kernel/bpf/syscall.c | 24 ++++-
kernel/bpf/verifier.c | 19 +++
tools/include/uapi/linux/bpf.h | 9 +
8 files changed, 253 insertions(+), 7 deletions(-)
create mode 100644 kernel/bpf/bloom_filter.c
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -169,6 +169,7 @@ struct bpf_map {
u32 value_size;
u32 max_entries;
u32 map_flags;
+ u64 map_extra; /* any per-map-type extra fields */
int spin_lock_off; /* >=0 valid offset, <0 error */
int timer_off; /* >=0 valid offset, <0 error */
u32 id;
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -125,6 +125,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_m
BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops)
BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint)
BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -906,6 +906,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_RINGBUF,
BPF_MAP_TYPE_INODE_STORAGE,
BPF_MAP_TYPE_TASK_STORAGE,
+ BPF_MAP_TYPE_BLOOM_FILTER,
};
/* Note that tracing related programs such as
@@ -1274,6 +1275,13 @@ union bpf_attr {
* struct stored as the
* map value
*/
+ /* Any per-map-type extra fields
+ *
+ * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
+ * number of hash functions (if 0, the bloom filter will default
+ * to using 5 hash functions).
+ */
+ __u64 map_extra;
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -5638,6 +5646,7 @@ struct bpf_map_info {
__u32 btf_id;
__u32 btf_key_type_id;
__u32 btf_value_type_id;
+ __u64 map_extra;
} __attribute__((aligned(8)));
struct bpf_btf_info {
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -7,7 +7,7 @@ endif
CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
-obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
+obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o
obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o
--- /dev/null
+++ b/kernel/bpf/bloom_filter.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <linux/bitmap.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+#include <linux/jhash.h>
+#include <linux/random.h>
+
+#define BLOOM_CREATE_FLAG_MASK \
+ (BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK)
+
+struct bpf_bloom_filter {
+ struct bpf_map map;
+ u32 bitset_mask;
+ u32 hash_seed;
+ /* If the size of the values in the bloom filter is u32 aligned,
+ * then it is more performant to use jhash2 as the underlying hash
+ * function, else we use jhash. This tracks the number of u32s
+ * in an u32-aligned value size. If the value size is not u32 aligned,
+ * this will be 0.
+ */
+ u32 aligned_u32_count;
+ u32 nr_hash_funcs;
+ unsigned long bitset[];
+};
+
+static u32 hash(struct bpf_bloom_filter *bloom, void *value,
+ u32 value_size, u32 index)
+{
+ u32 h;
+
+ if (bloom->aligned_u32_count)
+ h = jhash2(value, bloom->aligned_u32_count,
+ bloom->hash_seed + index);
+ else
+ h = jhash(value, value_size, bloom->hash_seed + index);
+
+ return h & bloom->bitset_mask;
+}
+
+static int peek_elem(struct bpf_map *map, void *value)
+{
+ struct bpf_bloom_filter *bloom =
+ container_of(map, struct bpf_bloom_filter, map);
+ u32 i, h;
+
+ for (i = 0; i < bloom->nr_hash_funcs; i++) {
+ h = hash(bloom, value, map->value_size, i);
+ if (!test_bit(h, bloom->bitset))
+ return -ENOENT;
+ }
+
+ return 0;
+}
+
+static int push_elem(struct bpf_map *map, void *value, u64 flags)
+{
+ struct bpf_bloom_filter *bloom =
+ container_of(map, struct bpf_bloom_filter, map);
+ u32 i, h;
+
+ if (flags != BPF_ANY)
+ return -EINVAL;
+
+ for (i = 0; i < bloom->nr_hash_funcs; i++) {
+ h = hash(bloom, value, map->value_size, i);
+ set_bit(h, bloom->bitset);
+ }
+
+ return 0;
+}
+
+static int pop_elem(struct bpf_map *map, void *value)
+{
+ return -EOPNOTSUPP;
+}
+
+static struct bpf_map *map_alloc(union bpf_attr *attr)
+{
+ u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits;
+ int numa_node = bpf_map_attr_numa_node(attr);
+ struct bpf_bloom_filter *bloom;
+
+ if (!bpf_capable())
+ return ERR_PTR(-EPERM);
+
+ if (attr->key_size != 0 || attr->value_size == 0 ||
+ attr->max_entries == 0 ||
+ attr->map_flags & ~BLOOM_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags) ||
+ (attr->map_extra & ~0xF))
+ return ERR_PTR(-EINVAL);
+
+ /* The lower 4 bits of map_extra specify the number of hash functions */
+ nr_hash_funcs = attr->map_extra & 0xF;
+ if (nr_hash_funcs == 0)
+ /* Default to using 5 hash functions if unspecified */
+ nr_hash_funcs = 5;
+
+ /* For the bloom filter, the optimal bit array size that minimizes the
+ * false positive probability is n * k / ln(2) where n is the number of
+ * expected entries in the bloom filter and k is the number of hash
+ * functions. We use 7 / 5 to approximate 1 / ln(2).
+ *
+ * We round this up to the nearest power of two to enable more efficient
+ * hashing using bitmasks. The bitmask will be the bit array size - 1.
+ *
+ * If this overflows a u32, the bit array size will have 2^32 (4
+ * GB) bits.
+ */
+ if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) ||
+ check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) ||
+ nr_bits > (1UL << 31)) {
+ /* The bit array size is 2^32 bits but to avoid overflowing the
+ * u32, we use U32_MAX, which will round up to the equivalent
+ * number of bytes
+ */
+ bitset_bytes = BITS_TO_BYTES(U32_MAX);
+ bitset_mask = U32_MAX;
+ } else {
+ if (nr_bits <= BITS_PER_LONG)
+ nr_bits = BITS_PER_LONG;
+ else
+ nr_bits = roundup_pow_of_two(nr_bits);
+ bitset_bytes = BITS_TO_BYTES(nr_bits);
+ bitset_mask = nr_bits - 1;
+ }
+
+ bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long));
+ bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node);
+
+ if (!bloom)
+ return ERR_PTR(-ENOMEM);
+
+ bpf_map_init_from_attr(&bloom->map, attr);
+
+ bloom->nr_hash_funcs = nr_hash_funcs;
+ bloom->bitset_mask = bitset_mask;
+
+ /* Check whether the value size is u32-aligned */
+ if ((attr->value_size & (sizeof(u32) - 1)) == 0)
+ bloom->aligned_u32_count =
+ attr->value_size / sizeof(u32);
+
+ if (!(attr->map_flags & BPF_F_ZERO_SEED))
+ bloom->hash_seed = get_random_int();
+
+ return &bloom->map;
+}
+
+static void map_free(struct bpf_map *map)
+{
+ struct bpf_bloom_filter *bloom =
+ container_of(map, struct bpf_bloom_filter, map);
+
+ bpf_map_area_free(bloom);
+}
+
+static void *lookup_elem(struct bpf_map *map, void *key)
+{
+ /* The eBPF program should use map_peek_elem instead */
+ return ERR_PTR(-EINVAL);
+}
+
+static int update_elem(struct bpf_map *map, void *key,
+ void *value, u64 flags)
+{
+ /* The eBPF program should use map_push_elem instead */
+ return -EINVAL;
+}
+
+static int check_btf(const struct bpf_map *map, const struct btf *btf,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type)
+{
+ /* Bloom filter maps are keyless */
+ return btf_type_is_void(key_type) ? 0 : -EINVAL;
+}
+
+static int bpf_bloom_btf_id;
+const struct bpf_map_ops bloom_filter_map_ops = {
+ .map_meta_equal = bpf_map_meta_equal,
+ .map_alloc = map_alloc,
+ .map_free = map_free,
+ .map_push_elem = push_elem,
+ .map_peek_elem = peek_elem,
+ .map_pop_elem = pop_elem,
+ .map_lookup_elem = lookup_elem,
+ .map_update_elem = update_elem,
+ .map_check_btf = check_btf,
+ .map_btf_name = "bpf_bloom_filter",
+ .map_btf_id = &bpf_bloom_btf_id,
+};
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -199,7 +199,8 @@ static int bpf_map_update_value(struct b
err = bpf_fd_reuseport_array_update_elem(map, key, value,
flags);
} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
- map->map_type == BPF_MAP_TYPE_STACK) {
+ map->map_type == BPF_MAP_TYPE_STACK ||
+ map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
err = map->ops->map_push_elem(map, value, flags);
} else {
rcu_read_lock();
@@ -238,7 +239,8 @@ static int bpf_map_copy_value(struct bpf
} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
- map->map_type == BPF_MAP_TYPE_STACK) {
+ map->map_type == BPF_MAP_TYPE_STACK ||
+ map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
err = map->ops->map_peek_elem(map, value);
} else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
/* struct_ops map requires directly updating "value" */
@@ -348,6 +350,7 @@ void bpf_map_init_from_attr(struct bpf_m
map->max_entries = attr->max_entries;
map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags);
map->numa_node = bpf_map_attr_numa_node(attr);
+ map->map_extra = attr->map_extra;
}
static int bpf_map_alloc_id(struct bpf_map *map)
@@ -555,6 +558,7 @@ static void bpf_map_show_fdinfo(struct s
"value_size:\t%u\n"
"max_entries:\t%u\n"
"map_flags:\t%#x\n"
+ "map_extra:\t%#llx\n"
"memlock:\t%lu\n"
"map_id:\t%u\n"
"frozen:\t%u\n",
@@ -563,6 +567,7 @@ static void bpf_map_show_fdinfo(struct s
map->value_size,
map->max_entries,
map->map_flags,
+ (unsigned long long)map->map_extra,
bpf_map_memory_footprint(map),
map->id,
READ_ONCE(map->frozen));
@@ -812,7 +817,7 @@ static int map_check_btf(struct bpf_map
return ret;
}
-#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id
+#define BPF_MAP_CREATE_LAST_FIELD map_extra
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
@@ -833,6 +838,10 @@ static int map_create(union bpf_attr *at
return -EINVAL;
}
+ if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER &&
+ attr->map_extra != 0)
+ return -EINVAL;
+
f_flags = bpf_get_file_flag(attr->map_flags);
if (f_flags < 0)
return f_flags;
@@ -1082,6 +1091,14 @@ static int map_lookup_elem(union bpf_att
if (!value)
goto free_key;
+ if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
+ if (copy_from_user(value, uvalue, value_size))
+ err = -EFAULT;
+ else
+ err = bpf_map_copy_value(map, key, value, attr->flags);
+ goto free_value;
+ }
+
err = bpf_map_copy_value(map, key, value, attr->flags);
if (err)
goto free_value;
@@ -3884,6 +3901,7 @@ static int bpf_map_get_info_by_fd(struct
info.value_size = map->value_size;
info.max_entries = map->max_entries;
info.map_flags = map->map_flags;
+ info.map_extra = map->map_extra;
memcpy(info.name, map->name, sizeof(map->name));
if (map->btf) {
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5002,7 +5002,10 @@ static int resolve_map_arg_type(struct b
return -EINVAL;
}
break;
-
+ case BPF_MAP_TYPE_BLOOM_FILTER:
+ if (meta->func_id == BPF_FUNC_map_peek_elem)
+ *arg_type = ARG_PTR_TO_MAP_VALUE;
+ break;
default:
break;
}
@@ -5577,6 +5580,11 @@ static int check_map_func_compatibility(
func_id != BPF_FUNC_task_storage_delete)
goto error;
break;
+ case BPF_MAP_TYPE_BLOOM_FILTER:
+ if (func_id != BPF_FUNC_map_peek_elem &&
+ func_id != BPF_FUNC_map_push_elem)
+ goto error;
+ break;
default:
break;
}
@@ -5644,13 +5652,18 @@ static int check_map_func_compatibility(
map->map_type != BPF_MAP_TYPE_SOCKHASH)
goto error;
break;
- case BPF_FUNC_map_peek_elem:
case BPF_FUNC_map_pop_elem:
- case BPF_FUNC_map_push_elem:
if (map->map_type != BPF_MAP_TYPE_QUEUE &&
map->map_type != BPF_MAP_TYPE_STACK)
goto error;
break;
+ case BPF_FUNC_map_peek_elem:
+ case BPF_FUNC_map_push_elem:
+ if (map->map_type != BPF_MAP_TYPE_QUEUE &&
+ map->map_type != BPF_MAP_TYPE_STACK &&
+ map->map_type != BPF_MAP_TYPE_BLOOM_FILTER)
+ goto error;
+ break;
case BPF_FUNC_sk_storage_get:
case BPF_FUNC_sk_storage_delete:
if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -909,6 +909,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_RINGBUF,
BPF_MAP_TYPE_INODE_STORAGE,
BPF_MAP_TYPE_TASK_STORAGE,
+ BPF_MAP_TYPE_BLOOM_FILTER,
};
/* Note that tracing related programs such as
@@ -1277,6 +1278,13 @@ union bpf_attr {
* struct stored as the
* map value
*/
+ /* Any per-map-type extra fields
+ *
+ * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
+ * number of hash functions (if 0, the bloom filter will default
+ * to using 5 hash functions).
+ */
+ __u64 map_extra;
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -5641,6 +5649,7 @@ struct bpf_map_info {
__u32 btf_id;
__u32 btf_key_type_id;
__u32 btf_value_type_id;
+ __u64 map_extra;
} __attribute__((aligned(8)));
struct bpf_btf_info {