Le 11/03/2025 à 17:09, Saket Kumar Bhaskar a écrit :
[Vous ne recevez pas souvent de courriers de skb99@xxxxxxxxxxxxx. Découvrez pourquoi ceci est important à https://aka.ms/LearnAboutSenderIdentification ]
Inline the calls to bpf_get_smp_processor_id() in the powerpc bpf jit.
powerpc saves the Logical processor number (paca_index) 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 | 41.580 ± 0.034M/s | 54.137 ± 0.019M/s | + 30.20% |
| arr-inc | 39.592 ± 0.055M/s | 54.000 ± 0.026M/s | + 36.39% |
| hash-inc | 25.873 ± 0.012M/s | 26.334 ± 0.058M/s | + 1.78% |
+---------------+-------------------+-------------------+--------------+
Nice improvement.
I see that bpf_get_current_task() could be inlined as well, on PPC32 it
is in r2, on PPC64 it is in paca.
[1] https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fanakryiko%2Flinux%2Fcommit%2F8dec900975ef&data=05%7C02%7Cchristophe.leroy%40csgroup.eu%7C1d1f40ce41344cf1ecf508dd60b73ae0%7C8b87af7d86474dc78df45f69a2011bb5%7C0%7C0%7C638773062267813839%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=T%2BG206FHtW7hhFT1%2BXxRwN7pc%2BRzu8SiMlZ5njIlhB8%3D&reserved=0
Signed-off-by: Saket Kumar Bhaskar <skb99@xxxxxxxxxxxxx>
---
arch/powerpc/net/bpf_jit_comp.c | 10 ++++++++++
arch/powerpc/net/bpf_jit_comp64.c | 5 +++++
2 files changed, 15 insertions(+)
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 3d4bd45a9a22..4b79b2d95469 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -445,6 +445,16 @@ 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;
+ }
+}
What about PPC32 ?
+
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 06f06770ceea..a8de12c026da 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -1087,6 +1087,11 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
case BPF_JMP | BPF_CALL:
ctx->seen |= SEEN_FUNC;
+ if (insn[i].src_reg == 0 && imm == BPF_FUNC_get_smp_processor_id) {
Please use BPF_REG_0 instead of just 0.
+ EMIT(PPC_RAW_LHZ(bpf_to_ppc(BPF_REG_0), _R13, offsetof(struct paca_struct, paca_index)));
Can just use 'src_reg' instead of 'bpf_to_ppc(BPF_REG_0)'
+ break;
+ }
+
ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass,
&func_addr, &func_addr_fixed);
if (ret < 0)
--
2.43.5
