From: Abhishek Dubey <[email protected]> Enabling tailcalls with subprog combinations by referencing method. The actual tailcall count is always maintained in the tail_call_info variable present in the frame of main function (also called entry function). The tail_call_info field in the stack frame of subprogs contains reference to the tail_call_info field in the stack frame of main BPF program.
Dynamic resolution interprets the tail_call_info either as value or reference depending on the context of active frame while tailcall is invoked. Signed-off-by: Abhishek Dubey <[email protected]> --- arch/powerpc/net/bpf_jit.h | 13 ++++++ arch/powerpc/net/bpf_jit_comp.c | 59 +++++++++++++++++++++++---- arch/powerpc/net/bpf_jit_comp64.c | 68 +++++++++++++++++++++++-------- 3 files changed, 117 insertions(+), 23 deletions(-) diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 9f6ec00bd02e..56f56fdd4969 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -52,6 +52,13 @@ EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc)); \ } while (0) +/* When constant jump offset is known prior */ +#define PPC_BCC_CONST_SHORT(cond, offset) \ + do { \ + BUILD_BUG_ON(offset < -0x8000 || offset > 0x7fff || (offset & 0x3)); \ + EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc)); \ + } while (0) + /* * Sign-extended 32-bit immediate load * @@ -73,6 +80,10 @@ } } while (0) #ifdef CONFIG_PPC64 + +/* for gpr non volatile registers BPG_REG_6 to 10 */ +#define BPF_PPC_STACK_SAVE (6 * 8) + /* If dummy pass (!image), account for maximum possible instructions */ #define PPC_LI64(d, i) do { \ if (!image) \ @@ -167,6 +178,7 @@ struct codegen_context { unsigned int alt_exit_addr; u64 arena_vm_start; u64 user_vm_start; + bool is_subprog; }; #define bpf_to_ppc(r) (ctx->b2p[r]) @@ -206,6 +218,7 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass struct codegen_context *ctx, int insn_idx, int jmp_off, int dst_reg, u32 code); +int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx); #endif #endif diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index d5757577f933..f3ee031edc26 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -206,6 +206,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) cgctx.stack_size = round_up(fp->aux->stack_depth, 16); cgctx.arena_vm_start = bpf_arena_get_kern_vm_start(fp->aux->arena); cgctx.user_vm_start = bpf_arena_get_user_vm_start(fp->aux->arena); + cgctx.is_subprog = bpf_is_subprog(fp); /* Scouting faux-generate pass 0 */ if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) { @@ -435,6 +436,11 @@ void bpf_jit_free(struct bpf_prog *fp) bpf_prog_unlock_free(fp); } +bool bpf_jit_supports_subprog_tailcalls(void) +{ + return IS_ENABLED(CONFIG_PPC64); +} + bool bpf_jit_supports_kfunc_call(void) { return true; @@ -600,15 +606,53 @@ static int invoke_bpf_mod_ret(u32 *image, u32 *ro_image, struct codegen_context return 0; } -static void bpf_trampoline_setup_tail_call_cnt(u32 *image, struct codegen_context *ctx, - int func_frame_offset, int r4_off) +/* + * Refer the label 'Generated stack layout' in this file for actual stack + * layout during trampoline invocation. + * + * Refer __arch_prepare_bpf_trampoline() for stack component details. + * + * The tailcall count/reference is present in caller's stack frame. Its required + * to copy the content of tail_call_info before calling the actual function + * to which the trampoline is attached. + */ +static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_context *ctx, + int func_frame_offset, + int bpf_dummy_frame_size, int r4_off) { if (IS_ENABLED(CONFIG_PPC64)) { /* See Generated stack layout */ - int tailcallcnt_offset = BPF_PPC_TAILCALL; + int tailcallinfo_offset = BPF_PPC_TAILCALL; - EMIT(PPC_RAW_LL(_R3, _R1, func_frame_offset - tailcallcnt_offset)); - EMIT(PPC_RAW_STL(_R3, _R1, -tailcallcnt_offset)); + /* + * func_frame_offset = ...(1) + * bpf_dummy_frame_size + trampoline_frame_size + */ + EMIT(PPC_RAW_LD(_R4, _R1, func_frame_offset)); + EMIT(PPC_RAW_LD(_R3, _R4, -tailcallinfo_offset)); + + /* + * Setting the tail_call_info in trampoline's frame + * depending on if previous frame had value or reference. + */ + EMIT(PPC_RAW_CMPLWI(_R3, MAX_TAIL_CALL_CNT)); + PPC_BCC_CONST_SHORT(COND_GT, 8); + EMIT(PPC_RAW_ADDI(_R3, _R4, bpf_jit_stack_tailcallinfo_offset(ctx))); + /* + * From ...(1) above: + * trampoline_frame_bottom = ...(2) + * func_frame_offset - bpf_dummy_frame_size + * + * Using ...(2) derived above: + * trampoline_tail_call_info_offset = ...(3) + * trampoline_frame_bottom - tailcallinfo_offset + * + * From ...(3): + * Use trampoline_tail_call_info_offset to write reference of main's + * tail_call_info in trampoline frame. + */ + EMIT(PPC_RAW_STL(_R3, _R1, (func_frame_offset - bpf_dummy_frame_size) + - tailcallinfo_offset)); } else { /* See bpf_jit_stack_offsetof() and BPF_PPC_TC */ EMIT(PPC_RAW_LL(_R4, _R1, r4_off)); @@ -714,7 +758,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im * LR save area [ r0 save (64-bit) ] | header * [ r0 save (32-bit) ] | * dummy frame for unwind [ back chain 1 ] -- - * [ tail_call_cnt ] optional - 64-bit powerpc + * [ tail_call_info ] optional - 64-bit powerpc * [ padding ] align stack frame * r4_off [ r4 (tailcallcnt) ] optional - 32-bit powerpc * alt_lr_off [ real lr (ool stub)] optional - actual lr @@ -905,7 +949,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im /* Replicate tail_call_cnt before calling the original BPF prog */ if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) - bpf_trampoline_setup_tail_call_cnt(image, ctx, func_frame_offset, r4_off); + bpf_trampoline_setup_tail_call_info(image, ctx, func_frame_offset, + bpf_dummy_frame_size, r4_off); /* Restore args */ bpf_trampoline_restore_args_stack(image, ctx, func_frame_offset, nr_regs, regs_off); diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 296e9ea14f2e..18da5a866447 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -26,8 +26,12 @@ * Ensure the top half (upto local_tmp_var) stays consistent * with our redzone usage. * + * tail_call_info - stores tailcall count value in main program's + * frame, stores reference to tail_call_info of + * main's frame in sub-prog's frame. + * * [ prev sp ] <------------- - * [ tail_call_cnt ] 8 | + * [ tail_call_info ] 8 | * [ nv gpr save area ] 6*8 | * [ local_tmp_var ] 24 | * fp (r31) --> [ ebpf stack space ] upto 512 | @@ -35,8 +39,6 @@ * sp (r1) ---> [ stack pointer ] -------------- */ -/* for gpr non volatile registers BPG_REG_6 to 10 */ -#define BPF_PPC_STACK_SAVE (6*8) /* for bpf JIT code internal usage */ #define BPF_PPC_STACK_LOCALS 24 /* stack frame excluding BPF stack, ensure this is quadword aligned */ @@ -98,7 +100,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx) * [ prev sp ] <------------- * [ ... ] | * sp (r1) ---> [ stack pointer ] -------------- - * [ tail_call_cnt ] 8 + * [ tail_call_info ] 8 * [ nv gpr save area ] 6*8 * [ local_tmp_var ] 24 * [ unused red zone ] 224 @@ -114,7 +116,7 @@ static int bpf_jit_stack_local(struct codegen_context *ctx) } } -static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx) +int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx) { return bpf_jit_stack_local(ctx) + BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE; } @@ -147,17 +149,32 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) #endif /* - * Initialize tail_call_cnt if we do tail calls. - * Otherwise, put in NOPs so that it can be skipped when we are - * invoked through a tail call. + * Tail call count(tcc) is saved & updated only in main + * program's frame and the address of tcc in main program's + * frame (tcc_ptr) is saved in subprogs frame. + * + * Offset of tail_call_info on any frame will be interpreted + * as either tcc_ptr or tcc value depending on whether it is + * greater than MAX_TAIL_CALL_CNT or not. */ - if (ctx->seen & SEEN_TAILCALL) { + if (!ctx->is_subprog) { EMIT(PPC_RAW_LI(bpf_to_ppc(TMP_REG_1), 0)); /* this goes in the redzone */ EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), _R1, -(BPF_PPC_TAILCALL))); } else { - EMIT(PPC_RAW_NOP()); - EMIT(PPC_RAW_NOP()); + /* + * if tail_call_info < MAX_TAIL_CALL_CNT + * main prog calling first subprog -> copy reference + * else + * subsequent subprog calling another subprog -> directly copy content + */ + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), _R1, 0)); + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), -(BPF_PPC_TAILCALL))); + EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT)); + PPC_BCC_CONST_SHORT(COND_GT, 8); + EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), + -(BPF_PPC_TAILCALL))); + EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), _R1, -(BPF_PPC_TAILCALL))); } if (bpf_has_stack_frame(ctx)) { @@ -352,19 +369,38 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o EMIT(PPC_RAW_CMPLW(b2p_index, bpf_to_ppc(TMP_REG_1))); PPC_BCC_SHORT(COND_GE, out); + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R1, bpf_jit_stack_tailcallinfo_offset(ctx))); + EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT)); + PPC_BCC_CONST_SHORT(COND_LE, 8); + + /* dereference TMP_REG_1 */ + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), 0)); + /* - * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) + * if (tail_call_info == MAX_TAIL_CALL_CNT) * goto out; */ - EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R1, bpf_jit_stack_tailcallcnt(ctx))); EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT)); - PPC_BCC_SHORT(COND_GE, out); + PPC_BCC_SHORT(COND_EQ, out); /* - * tail_call_cnt++; + * tail_call_info++; <- Actual value of tcc here */ EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), 1)); - EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), _R1, bpf_jit_stack_tailcallcnt(ctx))); + + /* + * Before writing updated tail_call_info, distinguish if current frame + * is storing a reference to tail_call_info or actual tcc value in + * tail_call_info. + */ + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), _R1, bpf_jit_stack_tailcallinfo_offset(ctx))); + EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_2), MAX_TAIL_CALL_CNT)); + PPC_BCC_CONST_SHORT(COND_GT, 8); + + /* First get address of tail_call_info */ + EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_2), _R1, bpf_jit_stack_tailcallinfo_offset(ctx))); + /* Writeback updated value to tail_call_info */ + EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), 0)); /* prog = array->ptrs[index]; */ EMIT(PPC_RAW_MULI(bpf_to_ppc(TMP_REG_1), b2p_index, 8)); -- 2.48.1
