[PATCH 1/6] powerpc64/bpf: Support tailcalls with subprogs
adubey at linux.ibm.com
adubey at linux.ibm.com
Mon Jan 5 21:52:07 AEDT 2026
From: Abhishek Dubey <adubey at linux.ibm.com>
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 variables in
the frames of all other subprog contains reference to the
tail_call_info present in frame of main function.
Dynamic resolution interprets the tail_call_info either as
value or reference depending on the context of active frame
while tailcall is invoked.
Following is selftest run:
#./test_progs -t tailcalls
#425/1 tailcalls/tailcall_1:OK
#425/2 tailcalls/tailcall_2:OK
#425/3 tailcalls/tailcall_3:OK
#425/4 tailcalls/tailcall_4:OK
#425/5 tailcalls/tailcall_5:OK
#425/6 tailcalls/tailcall_6:OK
#425/7 tailcalls/tailcall_bpf2bpf_1:OK
#425/8 tailcalls/tailcall_bpf2bpf_2:OK
#425/9 tailcalls/tailcall_bpf2bpf_3:OK
#425/10 tailcalls/tailcall_bpf2bpf_4:OK
#425/11 tailcalls/tailcall_bpf2bpf_5:OK
#425/12 tailcalls/tailcall_bpf2bpf_6:OK
#425/13 tailcalls/tailcall_bpf2bpf_fentry:OK
#425/14 tailcalls/tailcall_bpf2bpf_fexit:OK
#425/15 tailcalls/tailcall_bpf2bpf_fentry_fexit:OK
#425/16 tailcalls/tailcall_bpf2bpf_fentry_entry:OK
#425/17 tailcalls/tailcall_poke:OK
#425/18 tailcalls/tailcall_bpf2bpf_hierarchy_1:OK
#425/19 tailcalls/tailcall_bpf2bpf_hierarchy_fentry:OK
#425/20 tailcalls/tailcall_bpf2bpf_hierarchy_fexit:OK
#425/21 tailcalls/tailcall_bpf2bpf_hierarchy_fentry_fexit:OK
#425/22 tailcalls/tailcall_bpf2bpf_hierarchy_fentry_entry:OK
#425/23 tailcalls/tailcall_bpf2bpf_hierarchy_2:OK
#425/24 tailcalls/tailcall_bpf2bpf_hierarchy_3:OK
#425/25 tailcalls/tailcall_freplace:OK
#425/26 tailcalls/tailcall_bpf2bpf_freplace:OK
#425/27 tailcalls/tailcall_failure:OK
#425/28 tailcalls/reject_tail_call_spin_lock:OK
#425/29 tailcalls/reject_tail_call_rcu_lock:OK
#425/30 tailcalls/reject_tail_call_preempt_lock:OK
#425/31 tailcalls/reject_tail_call_ref:OK
#425 tailcalls:OK
Summary: 1/31 PASSED, 0 SKIPPED, 0 FAILED
Signed-off-by: Abhishek Dubey <adubey at linux.ibm.com>
---
arch/powerpc/net/bpf_jit.h | 14 ++++++-
arch/powerpc/net/bpf_jit_comp.c | 10 ++++-
arch/powerpc/net/bpf_jit_comp64.c | 67 +++++++++++++++++++++++--------
3 files changed, 71 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 8334cd667bba..98e8b1f9c2f9 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -51,6 +51,12 @@
EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc)); \
} while (0)
+/* Same as PPC_BCC_SHORT, except valid dest is known prior to call. */
+#define PPC_COND_BRANCH(cond, dest) \
+ do { \
+ long offset = (long)(dest) - CTX_NIA(ctx); \
+ EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc)); \
+ } while (0)
/*
* Sign-extended 32-bit immediate load
*
@@ -72,6 +78,10 @@
} } 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) \
@@ -166,6 +176,7 @@ 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])
@@ -200,11 +211,10 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx);
void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx);
void bpf_jit_realloc_regs(struct codegen_context *ctx);
int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr);
-
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 5e976730b2f5..069a8822c30d 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;
@@ -604,7 +610,7 @@ static void bpf_trampoline_setup_tail_call_cnt(u32 *image, struct codegen_contex
int func_frame_offset, int r4_off)
{
if (IS_ENABLED(CONFIG_PPC64)) {
- /* See bpf_jit_stack_tailcallcnt() */
+ /* See bpf_jit_stack_tailcallinfo_offset() */
int tailcallcnt_offset = 7 * 8;
EMIT(PPC_RAW_LL(_R3, _R1, func_frame_offset - tailcallcnt_offset));
@@ -619,7 +625,7 @@ static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_cont
int func_frame_offset, int r4_off)
{
if (IS_ENABLED(CONFIG_PPC64)) {
- /* See bpf_jit_stack_tailcallcnt() */
+ /* See bpf_jit_stack_tailcallinfo_offset() */
int tailcallcnt_offset = 7 * 8;
EMIT(PPC_RAW_LL(_R3, _R1, -tailcallcnt_offset));
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 1fe37128c876..37c547b49da8 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -24,17 +24,19 @@
* 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 ] <-------------
* [ nv gpr save area ] 6*8 |
- * [ tail_call_cnt ] 8 |
+ * [ tail_call_info ] 8 |
* [ local_tmp_var ] 24 |
* fp (r31) --> [ ebpf stack space ] upto 512 |
* [ frame header ] 32/112 |
* 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 32
/* stack frame excluding BPF stack, ensure this is quadword aligned */
@@ -93,7 +95,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
* [ ... ] |
* sp (r1) ---> [ stack pointer ] --------------
* [ nv gpr save area ] 6*8
- * [ tail_call_cnt ] 8
+ * [ tail_call_info ] 8
* [ local_tmp_var ] 24
* [ unused red zone ] 224
*/
@@ -105,7 +107,7 @@ static int bpf_jit_stack_local(struct codegen_context *ctx)
return -(BPF_PPC_STACK_SAVE + 32);
}
-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) + 24;
}
@@ -138,17 +140,31 @@ 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_STACK_SAVE + 8)));
} 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_STACK_SAVE+8)));
+ EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
+ PPC_COND_BRANCH(COND_GT, CTX_NIA(ctx) + 8);
+ EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), -(BPF_PPC_STACK_SAVE + 8)));
+ EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), _R1, -(BPF_PPC_STACK_SAVE + 8)));
}
if (bpf_has_stack_frame(ctx)) {
@@ -343,19 +359,38 @@ 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_COND_BRANCH(COND_LE, CTX_NIA(ctx) + 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_COND_BRANCH(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_COND_BRANCH(COND_GT, CTX_NIA(ctx) + 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
More information about the Linuxppc-dev
mailing list