diff options
| author | Puranjay Mohan <puranjay12@gmail.com> | 2024-05-02 17:18:53 +0200 |
|---|---|---|
| committer | Alexei Starovoitov <ast@kernel.org> | 2024-05-13 01:54:34 +0200 |
| commit | 7a4c32222b0e14349a6311e72bf6ebd3e1d1064b (patch) | |
| tree | 9ddaf85ad93083fce7617d27bdae282c52eb2e16 /arch/arm64/net | |
| parent | riscv, bpf: inline bpf_get_smp_processor_id() (diff) | |
| download | linux-7a4c32222b0e14349a6311e72bf6ebd3e1d1064b.tar.xz linux-7a4c32222b0e14349a6311e72bf6ebd3e1d1064b.zip | |
arm64, bpf: add internal-only MOV instruction to resolve per-CPU addrs
Support an instruction for resolving absolute addresses of per-CPU
data from their per-CPU offsets. This instruction is internal-only and
users are not allowed to use them directly. They will only be used for
internal inlining optimizations for now between BPF verifier and BPF
JITs.
Since commit 7158627686f0 ("arm64: percpu: implement optimised pcpu
access using tpidr_el1"), the per-cpu offset for the CPU is stored in
the tpidr_el1/2 register of that CPU.
To support this BPF instruction in the ARM64 JIT, the following ARM64
instructions are emitted:
mov dst, src // Move src to dst, if src != dst
mrs tmp, tpidr_el1/2 // Move per-cpu offset of the current cpu in tmp.
add dst, dst, tmp // Add the per cpu offset to the dst.
To measure the performance improvement provided by this change, the
benchmark in [1] was used:
Before:
glob-arr-inc : 23.597 ± 0.012M/s
arr-inc : 23.173 ± 0.019M/s
hash-inc : 12.186 ± 0.028M/s
After:
glob-arr-inc : 23.819 ± 0.034M/s
arr-inc : 23.285 ± 0.017M/s
hash-inc : 12.419 ± 0.011M/s
[1] https://github.com/anakryiko/linux/commit/8dec900975ef
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240502151854.9810-4-puranjay@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'arch/arm64/net')
| -rw-r--r-- | arch/arm64/net/bpf_jit.h | 6 | ||||
| -rw-r--r-- | arch/arm64/net/bpf_jit_comp.c | 14 |
2 files changed, 20 insertions, 0 deletions
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index 23b1b34db088..b627ef7188c7 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -297,4 +297,10 @@ #define A64_ADR(Rd, offset) \ aarch64_insn_gen_adr(0, offset, Rd, AARCH64_INSN_ADR_TYPE_ADR) +/* MRS */ +#define A64_MRS_TPIDR_EL1(Rt) \ + aarch64_insn_gen_mrs(Rt, AARCH64_INSN_SYSREG_TPIDR_EL1) +#define A64_MRS_TPIDR_EL2(Rt) \ + aarch64_insn_gen_mrs(Rt, AARCH64_INSN_SYSREG_TPIDR_EL2) + #endif /* _BPF_JIT_H */ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 53347d4217f4..4e7954e9829d 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -890,6 +890,15 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit(A64_ORR(1, tmp, dst, tmp), ctx); emit(A64_MOV(1, dst, tmp), ctx); break; + } else if (insn_is_mov_percpu_addr(insn)) { + if (dst != src) + emit(A64_MOV(1, dst, src), ctx); + if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN)) + emit(A64_MRS_TPIDR_EL2(tmp), ctx); + else + emit(A64_MRS_TPIDR_EL1(tmp), ctx); + emit(A64_ADD(1, dst, dst, tmp), ctx); + break; } switch (insn->off) { case 0: @@ -2559,6 +2568,11 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) return true; } +bool bpf_jit_supports_percpu_insn(void) +{ + return true; +} + void bpf_jit_free(struct bpf_prog *prog) { if (prog->jited) { |