On Tue, Feb 6, 2024 at 2:05 PM Alexei Starovoitov
<alexei.starovoitov@xxxxxxxxx> wrote:
>
> From: Alexei Starovoitov <ast@xxxxxxxxxx>
>
> mmap() bpf_arena right after creation, since the kernel needs to
> remember the address returned from mmap. This is user_vm_start.
> LLVM will generate bpf_arena_cast_user() instructions where
> necessary and JIT will add upper 32-bit of user_vm_start
> to such pointers.
>
> Use traditional map->value_size * map->max_entries to calculate mmap sz,
> though it's not the best fit.
We should probably make bpf_map_mmap_sz() aware of specific map type
and do different calculations based on that. It makes sense to have
round_up(PAGE_SIZE) for BPF map arena, and use just just value_size or
max_entries to specify the size (fixing the other to be zero).
>
> Also don't set BTF at bpf_arena creation time, since it doesn't support it.
>
> Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxx>
> ---
> tools/lib/bpf/libbpf.c | 18 ++++++++++++++++++
> tools/lib/bpf/libbpf_probes.c | 6 ++++++
> 2 files changed, 24 insertions(+)
>
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index 01f407591a92..c5ce5946dc6d 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
> @@ -185,6 +185,7 @@ static const char * const map_type_name[] = {
> [BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter",
> [BPF_MAP_TYPE_USER_RINGBUF] = "user_ringbuf",
> [BPF_MAP_TYPE_CGRP_STORAGE] = "cgrp_storage",
> + [BPF_MAP_TYPE_ARENA] = "arena",
> };
>
> static const char * const prog_type_name[] = {
> @@ -4852,6 +4853,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
> case BPF_MAP_TYPE_SOCKHASH:
> case BPF_MAP_TYPE_QUEUE:
> case BPF_MAP_TYPE_STACK:
> + case BPF_MAP_TYPE_ARENA:
> create_attr.btf_fd = 0;
> create_attr.btf_key_type_id = 0;
> create_attr.btf_value_type_id = 0;
> @@ -4908,6 +4910,22 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
> if (map->fd == map_fd)
> return 0;
>
> + if (def->type == BPF_MAP_TYPE_ARENA) {
> + size_t mmap_sz;
> +
> + mmap_sz = bpf_map_mmap_sz(def->value_size, def->max_entries);
> + map->mmaped = mmap((void *)map->map_extra, mmap_sz, PROT_READ | PROT_WRITE,
> + map->map_extra ? MAP_SHARED | MAP_FIXED : MAP_SHARED,
> + map_fd, 0);
> + if (map->mmaped == MAP_FAILED) {
> + err = -errno;
> + map->mmaped = NULL;
> + pr_warn("map '%s': failed to mmap bpf_arena: %d\n",
> + bpf_map__name(map), err);
> + return err;
leaking map_fd here, you need to close(map_fd) before erroring out
> + }
> + }
> +
> /* Keep placeholder FD value but now point it to the BPF map object.
> * This way everything that relied on this map's FD (e.g., relocated
> * ldimm64 instructions) will stay valid and won't need adjustments.
> diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
> index ee9b1dbea9eb..cbc7f4c09060 100644
> --- a/tools/lib/bpf/libbpf_probes.c
> +++ b/tools/lib/bpf/libbpf_probes.c
> @@ -338,6 +338,12 @@ static int probe_map_create(enum bpf_map_type map_type)
> key_size = 0;
> max_entries = 1;
> break;
> + case BPF_MAP_TYPE_ARENA:
> + key_size = sizeof(__u64);
> + value_size = sizeof(__u64);
> + opts.map_extra = 0; /* can mmap() at any address */
> + opts.map_flags = BPF_F_MMAPABLE;
> + break;
> case BPF_MAP_TYPE_HASH:
> case BPF_MAP_TYPE_ARRAY:
> case BPF_MAP_TYPE_PROG_ARRAY:
> --
> 2.34.1
>
