powerpc64/bpf: Support internal-only MOV instruction to resolve per-CPU addrs

With the introduction of commit 7bdbf74 ("bpf: add special
internal-only MOV instruction to resolve per-CPU addrs"),
a new BPF instruction BPF_MOV64_PERCPU_REG has been added to
resolve absolute addresses of per-CPU data from their per-CPU
offsets. This update requires enabling support for this
instruction in the powerpc JIT compiler.

As of commit 7a0268f ("[PATCH] powerpc/64: per cpu data
optimisations"), the per-CPU data offset for the CPU is stored in
the paca.

To support this BPF instruction in the powerpc JIT, the following
powerpc instructions are emitted:

ld tmp1_reg, 48(13)		//Load per-CPU data offset from paca(r13) in tmp1_reg.
add dst_reg, src_reg, tmp1_reg	//Add the per cpu offset to the dst.
mr dst_reg, src_reg		//Move src_reg to dst_reg, if src_reg != dst_reg

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

Before Change:
glob-arr-inc   :   41.580 ± 0.034M/s
arr-inc        :   39.592 ± 0.055M/s
hash-inc       :   25.873 ± 0.012M/s

After Change:
glob-arr-inc   :   42.024 ± 0.049M/s
arr-inc        :   55.447 ± 0.031M/s
hash-inc       :   26.565 ± 0.014M/s

[1] anakryiko/linux@8dec900975ef

Signed-off-by: Saket Kumar Bhaskar <[email protected]>

Author: Saket Kumar Bhaskar

arch/powerpc/net/bpf_jit_comp.c

@@ -466,6 +466,11 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
 	return true;
 }
 
+bool bpf_jit_supports_percpu_insn(void)
+{
+	return IS_ENABLED(CONFIG_PPC64);
+}
+
 void *arch_alloc_bpf_trampoline(unsigned int size)
 {
 	return bpf_prog_pack_alloc(size, bpf_jit_fill_ill_insns);

arch/powerpc/net/bpf_jit_comp64.c

@@ -918,6 +918,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 		case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
 		case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
 
+			if (insn_is_mov_percpu_addr(&insn[i])) {
+				if (IS_ENABLED(CONFIG_SMP)) {
+					EMIT(PPC_RAW_LD(tmp1_reg, _R13, offsetof(struct paca_struct, data_offset)));
+					EMIT(PPC_RAW_ADD(dst_reg, src_reg, tmp1_reg));
+				} else {
+					EMIT(PPC_RAW_MR(dst_reg, src_reg));
+				}
+			}
+
 			if (insn_is_cast_user(&insn[i])) {
 				EMIT(PPC_RAW_RLDICL_DOT(tmp1_reg, src_reg, 0, 32));
 				PPC_LI64(dst_reg, (ctx->user_vm_start & 0xffffffff00000000UL));