diff options
| author | Alexei Starovoitov <ast@kernel.org> | 2022-02-08 05:13:02 +0300 |
|---|---|---|
| committer | Alexei Starovoitov <ast@kernel.org> | 2022-02-08 05:13:02 +0300 |
| commit | 80123f0ac4a6d89d0b9c0dfa163fb56f910ab718 (patch) | |
| tree | 13d4b4ee020abcbb5095ab6d38a99f22d892fdd0 /include/linux | |
| parent | 128dac5f21e950746aae3c1ef6df87e231d288a3 (diff) | |
| parent | 1022a5498f6f745c3b5fd3f050a5e11e7ca354f0 (diff) | |
| download | linux-80123f0ac4a6d89d0b9c0dfa163fb56f910ab718.tar.xz | |
Merge branch 'bpf_prog_pack allocator'
Song Liu says:
====================
Changes v8 => v9:
1. Fix an error with multi function program, in 4/9.
Changes v7 => v8:
1. Rebase and fix conflicts.
2. Lock text_mutex for text_poke_copy. (Daniel)
Changes v6 => v7:
1. Redesign the interface between generic and arch logic, based on feedback
from Alexei and Ilya.
2. Split 6/7 of v6 to 7/9 and 8/9 in v7, for cleaner logic.
3. Add bpf_arch_text_copy in 6/9.
Changes v5 => v6:
1. Make jit_hole_buffer 128 byte long. Only fill the first and last 128
bytes of header with INT3. (Alexei)
2. Use kvmalloc for temporary buffer. (Alexei)
3. Rename tmp_header/tmp_image => rw_header/rw_image. Remove tmp_image from
x64_jit_data. (Alexei)
4. Change fall back round_up_to in bpf_jit_binary_alloc_pack() from
BPF_PROG_MAX_PACK_PROG_SIZE to PAGE_SIZE.
Changes v4 => v5:
1. Do not use atomic64 for bpf_jit_current. (Alexei)
Changes v3 => v4:
1. Rename text_poke_jit() => text_poke_copy(). (Peter)
2. Change comment style. (Peter)
Changes v2 => v3:
1. Fix tailcall.
Changes v1 => v2:
1. Use text_poke instead of writing through linear mapping. (Peter)
2. Avoid making changes to non-x86_64 code.
Most BPF programs are small, but they consume a page each. For systems
with busy traffic and many BPF programs, this could also add significant
pressure to instruction TLB. High iTLB pressure usually causes slow down
for the whole system, which includes visible performance degradation for
production workloads.
This set tries to solve this problem with customized allocator that pack
multiple programs into a huge page.
Patches 1-6 prepare the work. Patch 7 contains key logic of bpf_prog_pack
allocator. Patch 8 contains bpf_jit_binary_pack_alloc logic on top of
bpf_prog_pack allocator. Patch 9 uses this allocator in x86_64 jit.
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/bpf.h | 7 | ||||
| -rw-r--r-- | include/linux/filter.h | 27 |
2 files changed, 20 insertions, 14 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6eb0b180d33b..2fc7e5c5ef41 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -846,8 +846,8 @@ void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); -int bpf_jit_charge_modmem(u32 pages); -void bpf_jit_uncharge_modmem(u32 pages); +int bpf_jit_charge_modmem(u32 size); +void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, @@ -953,6 +953,7 @@ struct bpf_prog_aux { bool sleepable; bool tail_call_reachable; bool xdp_has_frags; + bool use_bpf_prog_pack; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; @@ -2362,6 +2363,8 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +void *bpf_arch_text_copy(void *dst, void *src, size_t len); + struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); diff --git a/include/linux/filter.h b/include/linux/filter.h index d23e999dc032..1cb1af917617 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -548,7 +548,7 @@ struct sock_fprog_kern { #define BPF_IMAGE_ALIGNMENT 8 struct bpf_binary_header { - u32 pages; + u32 size; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; @@ -886,17 +886,8 @@ static inline void bpf_prog_lock_ro(struct bpf_prog *fp) static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); - set_memory_ro((unsigned long)hdr, hdr->pages); - set_memory_x((unsigned long)hdr, hdr->pages); -} - -static inline struct bpf_binary_header * -bpf_jit_binary_hdr(const struct bpf_prog *fp) -{ - unsigned long real_start = (unsigned long)fp->bpf_func; - unsigned long addr = real_start & PAGE_MASK; - - return (void *)addr; + set_memory_ro((unsigned long)hdr, hdr->size >> PAGE_SHIFT); + set_memory_x((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); @@ -1068,6 +1059,18 @@ void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); +struct bpf_binary_header * +bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, + unsigned int alignment, + struct bpf_binary_header **rw_hdr, + u8 **rw_image, + bpf_jit_fill_hole_t bpf_fill_ill_insns); +int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, + struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header); +void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header); + int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke); |
