powerpc64/bpf: Inline bpf_get_smp_processor_id() and bpf_get_current_task/_btf()

Inline the calls to bpf_get_smp_processor_id() and bpf_get_current_task/_btf()
in the powerpc bpf jit.

powerpc saves the Logical processor number (paca_index) and pointer
to current task (__current) in paca.

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

Before:

cpu = bpf_get_smp_processor_id();

addis 12, 2, -517
addi 12, 12, -29456
mtctr 12
bctrl
mr	8, 3

After:

cpu = bpf_get_smp_processor_id();

lhz 8, 8(13)

To evaluate the performance improvements introduced by this change,
the benchmark described in [1] was employed.

+---------------+-------------------+-------------------+--------------+
|      Name     |      Before       |        After      |   % change   |
|---------------+-------------------+-------------------+--------------|
| glob-arr-inc  | 40.701 ± 0.008M/s | 55.207 ± 0.021M/s |   + 35.64%   |
| arr-inc       | 39.401 ± 0.007M/s | 56.275 ± 0.023M/s |   + 42.42%   |
| hash-inc      | 24.944 ± 0.004M/s | 26.212 ± 0.003M/s |   +  5.08%   |
+---------------+-------------------+-------------------+--------------+

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

Reviewed-by: Puranjay Mohan <puranjay@kernel.org>
Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Acked-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/89abfdd6f6721fbe7897865e74f2f691e5f7824a.1765343385.git.skb99@linux.ibm.com

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index d53e9cd7563fb7d067d1e8ea4ab34617592b9aef..b243ee2058851da2f88982f66ef35cd985ba4976 100644 (file)
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -471,6 +471,18 @@ bool bpf_jit_supports_percpu_insn(void)
        return IS_ENABLED(CONFIG_PPC64);
 }
 
+bool bpf_jit_inlines_helper_call(s32 imm)
+{
+       switch (imm) {
+       case BPF_FUNC_get_smp_processor_id:
+       case BPF_FUNC_get_current_task:
+       case BPF_FUNC_get_current_task_btf:
+               return true;
+       default:
+               return false;
+       }
+}
+
 void *arch_alloc_bpf_trampoline(unsigned int size)
 {
        return bpf_prog_pack_alloc(size, bpf_jit_fill_ill_insns);

diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 37723ee9344ed72d8a51462081c76ece03b145cf..6c827e7aa6912023d43fc99f50767280ae773a61 100644 (file)
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -1400,6 +1400,17 @@ emit_clear:
                case BPF_JMP | BPF_CALL:
                        ctx->seen |= SEEN_FUNC;
 
+                       if (src_reg == bpf_to_ppc(BPF_REG_0)) {
+                               if (imm == BPF_FUNC_get_smp_processor_id) {
+                                       EMIT(PPC_RAW_LHZ(src_reg, _R13, offsetof(struct paca_struct, paca_index)));
+                                       break;
+                               } else if (imm == BPF_FUNC_get_current_task ||
+                                          imm == BPF_FUNC_get_current_task_btf) {
+                                       EMIT(PPC_RAW_LD(src_reg, _R13, offsetof(struct paca_struct, __current)));
+                                       break;
+                               }
+                       }
+
                        ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass,
                                                    &func_addr, &func_addr_fixed);
                        if (ret < 0)