powerpc64/bpf: Inline helper in powerpc JIT

This series add support for internal only per-CPU instructions, inlines the bpf_get_smp_processor_id() and bpf_get_current_task() helper calls for powerpc BPF JIT.

Changes since v2:
* Collected Reviewed-by tag.
* Inlined bpf_get_current_task/btf().
* Fixed addressing of src_reg and BPF_REG_0. (Christophe)
* Fixed condition for non smp case as suggested by Christophe.

v2: https://lore.kernel.org/all/[email protected]/

Changes since v1:
* Addressed Christophe's comments.
* Inlined bpf_get_current_task() as well.

v1: https://lore.kernel.org/all/[email protected]/
Saket Kumar Bhaskar (2):
powerpc64/bpf: Support internal-only MOV instruction to resolve
per-CPU addrs
powerpc64/bpf: Inline bpf_get_smp_processor_id() and

    bpf_get_current_task/_btf()

 arch/powerpc/net/bpf_jit_comp.c   | 17 +++++++++++++++++
 arch/powerpc/net/bpf_jit_comp64.c | 20 ++++++++++++++++++++
 2 files changed, 37 insertions(+)

2.51.0

With the introduction of commit 7bdbf7446305 ("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 7a0268fa1a36 ("[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:
if (IS_ENABLED(CONFIG_SMP))
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.
else if (src_reg != dst_reg)
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] https://github.com/anakryiko/linux/commit/8dec900975ef

---
 arch/powerpc/net/bpf_jit_comp.c   | 5 +++++
 arch/powerpc/net/bpf_jit_comp64.c | 9 +++++++++
 2 files changed, 14 insertions(+)

index 5e976730b2f5..d53e9cd7563f 100644
@@ -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);

index 1fe37128c876..816f9d7d9e5d 100644
@@ -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 if (src_reg != dst_reg) {
+					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));

2.51.0

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

---
 arch/powerpc/net/bpf_jit_comp.c   | 12 ++++++++++++
 arch/powerpc/net/bpf_jit_comp64.c | 11 +++++++++++
 2 files changed, 23 insertions(+)

index d53e9cd7563f..b243ee205885 100644
@@ -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);

index 816f9d7d9e5d..76a44f9ad7d2 100644
@@ -1399,6 +1399,17 @@ 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 (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)

2.51.0