From 50b3a910ffeb3b1d75fba099bba75024674c66b2 Mon Sep 17 00:00:00 2001 From: Saket Kumar Bhaskar Date: Mon, 17 Nov 2025 12:22:34 +0530 Subject: [PATCH 1/2] powerpc64/bpf: Support internal-only MOV instruction to resolve per-CPU addrs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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: 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] https://github.com/anakryiko/linux/commit/8dec900975ef Signed-off-by: Saket Kumar Bhaskar --- arch/powerpc/net/bpf_jit_comp.c | 5 +++++ arch/powerpc/net/bpf_jit_comp64.c | 9 +++++++++ 2 files changed, 14 insertions(+) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 5e976730b2f5f..d53e9cd7563fb 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/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); diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 1fe37128c8764..21486706b5eae 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/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)); From bb62a246e3a28c88bad46817ab076a7aa4b561c7 Mon Sep 17 00:00:00 2001 From: Saket Kumar Bhaskar Date: Mon, 17 Nov 2025 12:22:35 +0530 Subject: [PATCH 2/2] powerpc64/bpf: Inline bpf_get_smp_processor_id() and bpf_get_current_task() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Inline the calls to bpf_get_smp_processor_id()/bpf_get_current_task() 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 Signed-off-by: Saket Kumar Bhaskar --- arch/powerpc/net/bpf_jit_comp.c | 11 +++++++++++ arch/powerpc/net/bpf_jit_comp64.c | 10 ++++++++++ 2 files changed, 21 insertions(+) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index d53e9cd7563fb..ccc5ea9544723 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -471,6 +471,17 @@ 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: + 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 21486706b5eae..4e16434223708 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -1399,6 +1399,16 @@ 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 == BPF_REG_0) { + if (imm == BPF_FUNC_get_smp_processor_id) { + EMIT(PPC_RAW_LHZ(insn[i].src_reg, _R13, offsetof(struct paca_struct, paca_index))); + break; + } else if (imm == BPF_FUNC_get_current_task) { + EMIT(PPC_RAW_LD(insn[i].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)