[PATCH bpf-next v2 2/2] bpf, arm64: inline bpf_get_smp_processor_id() helper

From: Puranjay Mohan
Date: Wed Apr 24 2024 - 13:37:04 EST


As ARM64 JIT now implements BPF_MOV64_PERCPU_REG instruction, inline
bpf_get_smp_processor_id().

ARM64 uses the per-cpu variable cpu_number to store the cpu id.

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

BPF
=====
BEFORE AFTER
-------- -------

int cpu = bpf_get_smp_processor_id(); int cpu = bpf_get_smp_processor_id();
(85) call bpf_get_smp_processor_id#229032 (18) r0 = 0xffff800082072008
(bf) r0 = r0
(61) r0 = *(u32 *)(r0 +0)

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

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

int cpu = bpf_get_smp_processor_id(); int cpu = bpf_get_smp_processor_id();
mov x10, #0xfffffffffffff4d0 mov x7, #0xffff8000ffffffff
movk x10, #0x802b, lsl #16 movk x7, #0x8207, lsl #16
movk x10, #0x8000, lsl #32 movk x7, #0x2008
blr x10 mrs x10, tpidr_el1
add x7, x0, #0x0 add x7, x7, x10
ldr w7, [x7]

Performance improvement using benchmark[1]

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

glob-arr-inc : 23.817 ± 0.019M/s glob-arr-inc : 24.631 ± 0.027M/s
arr-inc : 23.253 ± 0.019M/s arr-inc : 23.742 ± 0.023M/s
hash-inc : 12.258 ± 0.010M/s hash-inc : 12.625 ± 0.004M/s

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

Signed-off-by: Puranjay Mohan <puranjay@xxxxxxxxxx>
---
kernel/bpf/verifier.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9715c88cc025..3373be261889 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20205,7 +20205,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
goto next_insn;
}

-#ifdef CONFIG_X86_64
+#if defined(CONFIG_X86_64) || defined(CONFIG_ARM64)
/* Implement bpf_get_smp_processor_id() inline. */
if (insn->imm == BPF_FUNC_get_smp_processor_id &&
prog->jit_requested && bpf_jit_supports_percpu_insn()) {
@@ -20214,11 +20214,20 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
* changed in some incompatible and hard to support
* way, it's fine to back out this inlining logic
*/
+#if defined(CONFIG_X86_64)
insn_buf[0] = BPF_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number);
insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0);
cnt = 3;
+#elif defined(CONFIG_ARM64)
+ struct bpf_insn cpu_number_addr[2] = { BPF_LD_IMM64(BPF_REG_0, (u64)&cpu_number) };

+ insn_buf[0] = cpu_number_addr[0];
+ insn_buf[1] = cpu_number_addr[1];
+ insn_buf[2] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
+ insn_buf[3] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0);
+ cnt = 4;
+#endif
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
--
2.40.1