From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from 69-171-232-181.mail-mxout.facebook.com (69-171-232-181.mail-mxout.facebook.com [69.171.232.181]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id CD655346E70 for ; Thu, 7 May 2026 21:32:08 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=69.171.232.181 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778189530; cv=none; b=a6oKbCzA53c4uEpHYMtSDh/MuCv+9qkYHdaRwW1voJENeIzaa7AvnWP9EUCqy2eqI7o/zuCvk9OstHoyeSVNJAkXDDJ5UBlfaqjLE2ZwL86KQPDllp63ygeP8fikS3rsb/dnLtqNKnGf0qi9jAk3j2SVSwHz6BT7D33f2iW6SE8= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778189530; c=relaxed/simple; bh=xsayAz1tcoWNQqwgMf6y5HQCbUU0yAL1Q8vOYl5yFjI=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=SU1RrOcB6IT3s56AhShERzDvfawU+vf3nIFs5e3Nv6A6s6s7iHrGwftCUvLmsdzEToSB51FAPQZJHGSwt+jVW8BNXC0U6+W3zBZtx5qrQeyb2/lUz0S+J0jbW5hKMB19D6Rd8EFi1me80OOD4To+sLCftvaN3YnPFx5KJ5txTYk= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=fail (p=none dis=none) header.from=linux.dev; spf=fail smtp.mailfrom=linux.dev; arc=none smtp.client-ip=69.171.232.181 Authentication-Results: smtp.subspace.kernel.org; dmarc=fail (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=fail smtp.mailfrom=linux.dev Received: by devvm16039.vll0.facebook.com (Postfix, from userid 128203) id 754D492BBF8D8; Thu, 7 May 2026 14:32:01 -0700 (PDT) From: Yonghong Song To: bpf@vger.kernel.org Cc: Alexei Starovoitov , Andrii Nakryiko , Daniel Borkmann , "Jose E . Marchesi" , kernel-team@fb.com, Martin KaFai Lau , Puranjay Mohan Subject: [PATCH bpf-next v2 22/23] bpf, arm64: Add JIT support for stack arguments Date: Thu, 7 May 2026 14:32:01 -0700 Message-ID: <20260507213201.1140284-1-yonghong.song@linux.dev> X-Mailer: git-send-email 2.52.0 In-Reply-To: <20260507212942.1122000-1-yonghong.song@linux.dev> References: <20260507212942.1122000-1-yonghong.song@linux.dev> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable From: Puranjay Mohan Implement stack argument passing for BPF-to-BPF and kfunc calls with more than 5 parameters on arm64, following the AAPCS64 calling convention. BPF R1-R5 already map to x0-x4. With BPF_REG_0 moved to x8 by the previous commit, x5-x7 are free for arguments 6-8. Arguments 9-12 spill onto the stack at [SP+0], [SP+8], ... and the callee reads them from [FP+16], [FP+24], ... (above the saved FP/LR pair). BPF convention uses fixed offsets from BPF_REG_PARAMS (r11): off=3D-8 is always arg 6, off=3D-16 arg 7, etc. The verifier invalidates all outgoing stack arg slots after each call, so the compiler must re-store before every call. This means x5-x7 don't need to be saved on stack. Signed-off-by: Puranjay Mohan Signed-off-by: Yonghong Song --- arch/arm64/net/bpf_jit_comp.c | 87 ++++++++++++++++++++++++++++++++++- 1 file changed, 86 insertions(+), 1 deletion(-) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.= c index 085e650662e3..9b9d2501d2d3 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -86,6 +86,7 @@ struct jit_ctx { __le32 *image; __le32 *ro_image; u32 stack_size; + u16 stack_arg_size; u64 user_vm_start; u64 arena_vm_start; bool fp_used; @@ -533,13 +534,19 @@ static int build_prologue(struct jit_ctx *ctx, bool= ebpf_from_cbpf) * | | * +-----+ <=3D (BPF_FP - prog->aux->stack_depth= ) * |RSVD | padding - * current A64_SP =3D> +-----+ <=3D (BPF_FP - ctx->stack_size) + * +-----+ <=3D (BPF_FP - ctx->stack_size) + * | | + * | ... | outgoing stack args (9+, if any) + * | | + * current A64_SP =3D> +-----+ * | | * | ... | Function call stack * | | * +-----+ * low * + * Stack args 6-8 are passed in x5-x7, args 9+ at [SP]. + * Incoming args 9+ are at [FP + 16], [FP + 24], ... */ =20 emit_kcfi(is_main_prog ? cfi_bpf_hash : cfi_bpf_subprog_hash, ctx); @@ -613,6 +620,9 @@ static int build_prologue(struct jit_ctx *ctx, bool e= bpf_from_cbpf) if (ctx->stack_size && !ctx->priv_sp_used) emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); =20 + if (ctx->stack_arg_size) + emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_arg_size), ctx); + if (ctx->arena_vm_start) emit_a64_mov_i64(arena_vm_base, ctx->arena_vm_start, ctx); =20 @@ -673,6 +683,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) /* Update tail_call_cnt if the slot is populated. */ emit(A64_STR64I(tcc, ptr, 0), ctx); =20 + if (ctx->stack_arg_size) + emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_arg_size), ctx); + /* restore SP */ if (ctx->stack_size && !ctx->priv_sp_used) emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); @@ -1034,6 +1047,9 @@ static void build_epilogue(struct jit_ctx *ctx, boo= l was_classic) const u8 r0 =3D bpf2a64[BPF_REG_0]; const u8 ptr =3D bpf2a64[TCCNT_PTR]; =20 + if (ctx->stack_arg_size) + emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_arg_size), ctx); + /* We're done with BPF stack */ if (ctx->stack_size && !ctx->priv_sp_used) emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); @@ -1191,6 +1207,41 @@ static int add_exception_handler(const struct bpf_= insn *insn, return 0; } =20 +static const u8 stack_arg_reg[] =3D { A64_R(5), A64_R(6), A64_R(7) }; + +#define NR_STACK_ARG_REGS ARRAY_SIZE(stack_arg_reg) + +static void emit_stack_arg_load(u8 dst, s16 bpf_off, struct jit_ctx *ctx= ) +{ + int idx =3D bpf_off / sizeof(u64) - 1; + + if (idx < NR_STACK_ARG_REGS) + emit(A64_MOV(1, dst, stack_arg_reg[idx]), ctx); + else + emit(A64_LDR64I(dst, A64_FP, (idx - NR_STACK_ARG_REGS) * sizeof(u64) += 16), ctx); +} + +static void emit_stack_arg_store(u8 src_a64, s16 bpf_off, struct jit_ctx= *ctx) +{ + int idx =3D -bpf_off / sizeof(u64) - 1; + + if (idx < NR_STACK_ARG_REGS) + emit(A64_MOV(1, stack_arg_reg[idx], src_a64), ctx); + else + emit(A64_STR64I(src_a64, A64_SP, (idx - NR_STACK_ARG_REGS) * sizeof(u6= 4)), ctx); +} + +static void emit_stack_arg_store_imm(s32 imm, s16 bpf_off, const u8 tmp,= struct jit_ctx *ctx) +{ + int idx =3D -bpf_off / sizeof(u64) - 1; + + emit_a64_mov_i(1, tmp, imm, ctx); + if (idx < NR_STACK_ARG_REGS) + emit(A64_MOV(1, stack_arg_reg[idx], tmp), ctx); + else + emit(A64_STR64I(tmp, A64_SP, (idx - NR_STACK_ARG_REGS) * sizeof(u64)),= ctx); +} + /* JITs an eBPF instruction. * Returns: * 0 - successfully JITed an 8-byte eBPF instruction. @@ -1646,6 +1697,11 @@ static int build_insn(const struct bpf_verifier_en= v *env, const struct bpf_insn case BPF_LDX | BPF_MEM | BPF_H: case BPF_LDX | BPF_MEM | BPF_B: case BPF_LDX | BPF_MEM | BPF_DW: + if (insn->src_reg =3D=3D BPF_REG_PARAMS) { + emit_stack_arg_load(dst, off, ctx); + break; + } + fallthrough; case BPF_LDX | BPF_PROBE_MEM | BPF_DW: case BPF_LDX | BPF_PROBE_MEM | BPF_W: case BPF_LDX | BPF_PROBE_MEM | BPF_H: @@ -1672,6 +1728,8 @@ static int build_insn(const struct bpf_verifier_env= *env, const struct bpf_insn if (src =3D=3D fp) { src_adj =3D ctx->priv_sp_used ? priv_sp : A64_SP; off_adj =3D off + ctx->stack_size; + if (!ctx->priv_sp_used) + off_adj +=3D ctx->stack_arg_size; } else { src_adj =3D src; off_adj =3D off; @@ -1752,6 +1810,11 @@ static int build_insn(const struct bpf_verifier_en= v *env, const struct bpf_insn case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: case BPF_ST | BPF_MEM | BPF_DW: + if (insn->dst_reg =3D=3D BPF_REG_PARAMS) { + emit_stack_arg_store_imm(imm, off, tmp, ctx); + break; + } + fallthrough; case BPF_ST | BPF_PROBE_MEM32 | BPF_B: case BPF_ST | BPF_PROBE_MEM32 | BPF_H: case BPF_ST | BPF_PROBE_MEM32 | BPF_W: @@ -1763,6 +1826,8 @@ static int build_insn(const struct bpf_verifier_env= *env, const struct bpf_insn if (dst =3D=3D fp) { dst_adj =3D ctx->priv_sp_used ? priv_sp : A64_SP; off_adj =3D off + ctx->stack_size; + if (!ctx->priv_sp_used) + off_adj +=3D ctx->stack_arg_size; } else { dst_adj =3D dst; off_adj =3D off; @@ -1814,6 +1879,11 @@ static int build_insn(const struct bpf_verifier_en= v *env, const struct bpf_insn case BPF_STX | BPF_MEM | BPF_H: case BPF_STX | BPF_MEM | BPF_B: case BPF_STX | BPF_MEM | BPF_DW: + if (insn->dst_reg =3D=3D BPF_REG_PARAMS) { + emit_stack_arg_store(src, off, ctx); + break; + } + fallthrough; case BPF_STX | BPF_PROBE_MEM32 | BPF_B: case BPF_STX | BPF_PROBE_MEM32 | BPF_H: case BPF_STX | BPF_PROBE_MEM32 | BPF_W: @@ -1825,6 +1895,8 @@ static int build_insn(const struct bpf_verifier_env= *env, const struct bpf_insn if (dst =3D=3D fp) { dst_adj =3D ctx->priv_sp_used ? priv_sp : A64_SP; off_adj =3D off + ctx->stack_size; + if (!ctx->priv_sp_used) + off_adj +=3D ctx->stack_arg_size; } else { dst_adj =3D dst; off_adj =3D off; @@ -2065,6 +2137,14 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_ve= rifier_env *env, struct bpf_pr ctx.user_vm_start =3D bpf_arena_get_user_vm_start(prog->aux->arena); ctx.arena_vm_start =3D bpf_arena_get_kern_vm_start(prog->aux->arena); =20 + if (prog->aux->stack_arg_cnt > prog->aux->incoming_stack_arg_cnt) { + u16 outgoing_cnt =3D prog->aux->stack_arg_cnt - prog->aux->incoming_st= ack_arg_cnt; + int nr_on_stack =3D outgoing_cnt - NR_STACK_ARG_REGS; + + if (nr_on_stack > 0) + ctx.stack_arg_size =3D round_up(nr_on_stack * sizeof(u64), 16); + } + if (priv_stack_ptr) ctx.priv_sp_used =3D true; =20 @@ -2229,6 +2309,11 @@ bool bpf_jit_supports_kfunc_call(void) return true; } =20 +bool bpf_jit_supports_stack_args(void) +{ + return true; +} + void *bpf_arch_text_copy(void *dst, void *src, size_t len) { if (!aarch64_insn_copy(dst, src, len)) --=20 2.53.0-Meta