bpf, arm64: inline bpf_get_smp_processor_id() helper

Inline calls to bpf_get_smp_processor_id() helper in the JIT by emitting
a read from struct thread_info. The SP_EL0 system register holds the
pointer to the task_struct and thread_info is the first member of this
struct. We can read the cpu number from the thread_info.

Here is how the ARM64 JITed assembly changes after this commit:

                                      ARM64 JIT
                                     ===========

              BEFORE                                    AFTER
             --------                                  -------

int cpu = bpf_get_smp_processor_id();        int cpu = bpf_get_smp_processor_id();

mov     x10, #0xfffffffffffff4d0             mrs     x10, sp_el0
movk    x10, #0x802b, lsl #16                ldr     w7, [x10, #24]
movk    x10, #0x8000, lsl #32
blr     x10
add     x7, x0, #0x0

               Performance improvement using benchmark[1]

./benchs/run_bench_trigger.sh glob-arr-inc arr-inc hash-inc

+---------------+-------------------+-------------------+--------------+
|      Name     |      Before       |        After      |   % change   |
|---------------+-------------------+-------------------+--------------|
| glob-arr-inc  | 23.380 ± 1.675M/s | 25.893 ± 0.026M/s |   + 10.74%   |
| arr-inc       | 23.928 ± 0.034M/s | 25.213 ± 0.063M/s |   + 5.37%    |
| hash-inc      | 12.352 ± 0.005M/s | 12.609 ± 0.013M/s |   + 2.08%    |
+---------------+-------------------+-------------------+--------------+

[1] https://github.com/anakryiko/linux/commit/8dec900975ef

Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240502151854.9810-5-puranjay@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 8de0e39b29f388c985ae7e686149130ce99be632..8c0a36f72d6fcd8947229247dca4a8178b1fa783 100644 (file)
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -138,6 +138,7 @@ enum aarch64_insn_special_register {
 enum aarch64_insn_system_register {
        AARCH64_INSN_SYSREG_TPIDR_EL1   = 0x4684,
        AARCH64_INSN_SYSREG_TPIDR_EL2   = 0x6682,
+       AARCH64_INSN_SYSREG_SP_EL0      = 0x4208,
 };
 
 enum aarch64_insn_variant {

diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index b627ef7188c71e98030d839c62aebb46c2b1380e..b22ab2f97a3001a1239f1e49e4c660125a50830f 100644 (file)
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -302,5 +302,7 @@
        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)
+#define A64_MRS_SP_EL0(Rt) \
+       aarch64_insn_gen_mrs(Rt, AARCH64_INSN_SYSREG_SP_EL0)
 
 #endif /* _BPF_JIT_H */

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 4e7954e9829d8983d465df3d98d1eee73d336bc8..47151414a4507efe94aaba6644267e81b47e69a9 100644 (file)
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1228,6 +1228,21 @@ emit_cond_jmp:
                const u8 r0 = bpf2a64[BPF_REG_0];
                bool func_addr_fixed;
                u64 func_addr;
+               u32 cpu_offset;
+
+               /* Implement helper call to bpf_get_smp_processor_id() inline */
+               if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) {
+                       cpu_offset = offsetof(struct thread_info, cpu);
+
+                       emit(A64_MRS_SP_EL0(tmp), ctx);
+                       if (is_lsi_offset(cpu_offset, 2)) {
+                               emit(A64_LDR32I(r0, tmp, cpu_offset), ctx);
+                       } else {
+                               emit_a64_mov_i(1, tmp2, cpu_offset, ctx);
+                               emit(A64_LDR32(r0, tmp, tmp2), ctx);
+                       }
+                       break;
+               }
 
                ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
                                            &func_addr, &func_addr_fixed);
@@ -2573,6 +2588,16 @@ bool bpf_jit_supports_percpu_insn(void)
        return true;
 }
 
+bool bpf_jit_inlines_helper_call(s32 imm)
+{
+       switch (imm) {
+       case BPF_FUNC_get_smp_processor_id:
+               return true;
+       default:
+               return false;
+       }
+}
+
 void bpf_jit_free(struct bpf_prog *prog)
 {
        if (prog->jited) {