diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index f32de8704d4d9..4da8bde92e1ef 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -14,6 +14,13 @@
 #include <asm/ppc-opcode.h>
 #include <linux/build_bug.h>
 
+/*
+ * We need at least 2 passes for proper code generation, and may need
+ * additional passes if code size changes between passes.
+ */
+#define CODEGEN_MIN_PASSES    2
+#define CODEGEN_MAX_PASSES    3
+
 #ifdef CONFIG_PPC64_ELF_ABI_V1
 #define FUNCTION_DESCR_SIZE	24
 #else
@@ -188,6 +195,12 @@ struct codegen_context {
 
 #define bpf_to_ppc(r)	(ctx->b2p[r])
 
+#ifdef CONFIG_PPC64
+#define PPC_RAW_CMPLLI(a, i)    PPC_RAW_CMPLDI(a, i)
+#else
+#define PPC_RAW_CMPLLI(a, i)    PPC_RAW_CMPLWI(a, i)
+#endif
+
 #ifdef CONFIG_PPC32
 #define BPF_FIXUP_LEN	3 /* Three instructions => 12 bytes */
 #else
@@ -214,10 +227,11 @@ int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *
 int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx,
 		       u32 *addrs, int pass, bool extra_pass);
 void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx);
-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_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx);
+void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, 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_jit_emit_exit_insn(u32 *image, u32 *fimage, struct codegen_context *ctx, int tmp_reg,
+										long exit_addr);
 void prepare_for_fsession_fentry(u32 *image, struct codegen_context *ctx, int cookie_cnt,
 								int cookie_off, int retval_off);
 void store_func_meta(u32 *image, struct codegen_context *ctx, u64 func_meta, int func_meta_off);
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 7b07b43575f11..395f1458db2e6 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -49,11 +49,37 @@ asm (
 "	.popsection				;"
 );
 
-void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
+void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context *ctx)
 {
 	int ool_stub_idx, long_branch_stub_idx;
+	int stub_sz;
 
 	/*
+	 * The dummy_tramp_addr field is placed at bottom of Long branch stub.
+	 * In the final pass, align the mis-aligned dummy_tramp_addr field
+	 * in the fimage. The alignment NOP must appear before OOL stub,
+	 * to make ool_stub_idx & long_branch_stub_idx constant from end.
+	 *
+	 * dummy_tramp_addr must be 8-byte aligned for load-register
+	 * compatibility. The fimage can be non 8-byte aligned, so final
+	 * alignment depends on start of fimage and the stub's instruction
+	 * count. The stubs block has 11 instructions (with
+	 * CONFIG_PPC_FTRACE_OUT_OF_LINE) or 10 instructions (without)
+	 * before dummy_tramp_addr field. Emit a NOP if the address of
+	 * dummy_tramp_addr is non aligned.
+	 *
+	 * In pass=0 when image==NULL, conservatively account for space
+	 * required to accommodate alignment NOP. In case final pass skips
+	 * emitting alignment NOP, the image buffer have 4 spare bytes and
+	 * jited_len signifies correct program size.
+	 */
+
+	stub_sz = IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) ? 44 : 40;
+	if (!image || !IS_ALIGNED((unsigned long)fimage + ctx->idx*4 + stub_sz, SZL))
+		EMIT(PPC_RAW_NOP());
+
+	/*
+	 *      nop     // optional, for alignment of dummy_tramp_addr
 	 * Out-of-line stub:
 	 *	mflr	r0
 	 *	[b|bl]	tramp
@@ -70,44 +96,46 @@ void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
 
 	/*
 	 * Long branch stub:
-	 *	.long	<dummy_tramp_addr>
 	 *	mflr	r11
 	 *	bcl	20,31,$+4
-	 *	mflr	r12
-	 *	ld	r12, -8-SZL(r12)
+	 *	mflr	r12	// lr/r12 stores pc of current(this) inst.
+	 *	ld	r12, 20(r12) // offset(dummy_tramp_addr) from prev inst. is 20
 	 *	mtctr	r12
-	 *	mtlr	r11 // needed to retain ftrace ABI
+	 *	mtlr	r11	// needed to retain ftrace ABI
 	 *	bctr
+	 *	.long	<dummy_tramp_addr>  // SZL bytes aligned
 	 */
-	if (image)
-		*((unsigned long *)&image[ctx->idx]) = (unsigned long)dummy_tramp;
-	ctx->idx += SZL / 4;
 	long_branch_stub_idx = ctx->idx;
 	EMIT(PPC_RAW_MFLR(_R11));
 	EMIT(PPC_RAW_BCL4());
 	EMIT(PPC_RAW_MFLR(_R12));
-	EMIT(PPC_RAW_LL(_R12, _R12, -8-SZL));
+	EMIT(PPC_RAW_LL(_R12, _R12, 20));
 	EMIT(PPC_RAW_MTCTR(_R12));
 	EMIT(PPC_RAW_MTLR(_R11));
 	EMIT(PPC_RAW_BCTR());
 
+	if (image)
+		*((unsigned long *)&image[ctx->idx]) = (unsigned long)dummy_tramp;
+
+	ctx->idx += SZL / 4;
+
 	if (!bpf_jit_ool_stub) {
 		bpf_jit_ool_stub = (ctx->idx - ool_stub_idx) * 4;
 		bpf_jit_long_branch_stub = (ctx->idx - long_branch_stub_idx) * 4;
 	}
 }
 
-int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr)
+int bpf_jit_emit_exit_insn(u32 *image, u32 *fimage, struct codegen_context *ctx,
+							int tmp_reg, long exit_addr)
 {
-	if (!exit_addr || is_offset_in_branch_range(exit_addr - (ctx->idx * 4))) {
+	if (exit_addr && is_offset_in_branch_range(exit_addr - (long)(ctx->idx * 4))) {
 		PPC_JMP(exit_addr);
-	} else if (ctx->alt_exit_addr) {
-		if (WARN_ON(!is_offset_in_branch_range((long)ctx->alt_exit_addr - (ctx->idx * 4))))
-			return -1;
+	} else if (ctx->alt_exit_addr && is_offset_in_branch_range(
+			(long)(ctx->alt_exit_addr) - (long)(ctx->idx * 4))) {
 		PPC_JMP(ctx->alt_exit_addr);
 	} else {
 		ctx->alt_exit_addr = ctx->idx * 4;
-		bpf_jit_build_epilogue(image, ctx);
+		bpf_jit_build_epilogue(image, fimage, ctx);
 	}
 
 	return 0;
@@ -274,6 +302,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 	 */
 	if (cgctx.seen & SEEN_TAILCALL || !is_offset_in_branch_range((long)cgctx.idx * 4)) {
 		cgctx.idx = 0;
+		cgctx.alt_exit_addr = 0;
 		if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false))
 			goto out_err;
 	}
@@ -286,7 +315,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 	 */
 	bpf_jit_build_prologue(NULL, &cgctx);
 	addrs[fp->len] = cgctx.idx * 4;
-	bpf_jit_build_epilogue(NULL, &cgctx);
+	bpf_jit_build_epilogue(NULL, NULL, &cgctx);
 
 	fixup_len = fp->aux->num_exentries * BPF_FIXUP_LEN * 4;
 	extable_len = fp->aux->num_exentries * sizeof(struct exception_table_entry);
@@ -306,10 +335,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 	code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
 	fcode_base = (u32 *)(fimage + FUNCTION_DESCR_SIZE);
 
-	/* Code generation passes 1-2 */
-	for (pass = 1; pass < 3; pass++) {
+	/* Code generation passes 1-2+, loop until program size converges. */
+	for (pass = 1; pass <= CODEGEN_MAX_PASSES; pass++) {
+		u32 prev_proglen = proglen;
+
 		/* Now build the prologue, body code & epilogue for real. */
 		cgctx.idx = 0;
+		cgctx.exentry_idx = 0;
 		cgctx.alt_exit_addr = 0;
 		bpf_jit_build_prologue(code_base, &cgctx);
 		if (bpf_jit_build_body(fp, code_base, fcode_base, &cgctx, addrs, pass,
@@ -318,11 +350,26 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 			bpf_jit_binary_pack_free(fhdr, hdr);
 			goto out_err;
 		}
-		bpf_jit_build_epilogue(code_base, &cgctx);
+		addrs[fp->len] = cgctx.idx * 4;
+		bpf_jit_build_epilogue(code_base, fcode_base, &cgctx);
+
+		proglen = cgctx.idx * 4;
 
 		if (bpf_jit_enable > 1)
 			pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass,
-				proglen - (cgctx.idx * 4), cgctx.seen);
+				prev_proglen - proglen, cgctx.seen);
+
+		/* Check if program size has converged, but ensure minimum passes */
+		if (pass >= CODEGEN_MIN_PASSES && proglen == prev_proglen)
+			break;
+
+		if (pass == CODEGEN_MAX_PASSES && proglen != prev_proglen) {
+			pr_err("BPF JIT: Program did not converge after %d passes\n",
+								CODEGEN_MAX_PASSES);
+			bpf_arch_text_copy(&fhdr->size, &hdr->size, sizeof(hdr->size));
+			bpf_jit_binary_pack_free(fhdr, hdr);
+			goto out_err;
+		}
 	}
 
 	if (bpf_jit_enable > 1)
@@ -357,7 +404,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 				(void *)fimage + FUNCTION_DESCR_SIZE);
 
 out_addrs:
-		if (!image && priv_stack_ptr) {
+		if (!fp->jited && priv_stack_ptr) {
 			fp->aux->priv_stack_ptr = NULL;
 			free_percpu(priv_stack_ptr);
 		}
@@ -399,7 +446,7 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass
 	u32 *fixup;
 
 	/* Populate extable entries only in the last pass */
-	if (pass != 2)
+	if (pass < CODEGEN_MIN_PASSES)
 		return 0;
 
 	if (!fp->aux->extable ||
@@ -739,7 +786,7 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 		 * 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));
+		EMIT(PPC_RAW_CMPLLI(_R3, MAX_TAIL_CALL_CNT));
 		PPC_BCC_CONST_SHORT(COND_GT, 8);
 		EMIT(PPC_RAW_ADDI(_R3, _R4, -BPF_PPC_TAILCALL));
 
@@ -1265,6 +1312,7 @@ static void do_isync(void *info __maybe_unused)
  * bpf_func:
  *	[nop|b]	ool_stub
  * 2. Out-of-line stub:
+ * 	nop	// optional nop for alignment
  * ool_stub:
  *	mflr	r0
  *	[b|bl]	<bpf_prog>/<long_branch_stub>
@@ -1272,14 +1320,14 @@ static void do_isync(void *info __maybe_unused)
  *	b	bpf_func + 4
  * 3. Long branch stub:
  * long_branch_stub:
- *	.long	<branch_addr>/<dummy_tramp>
  *	mflr	r11
  *	bcl	20,31,$+4
  *	mflr	r12
- *	ld	r12, -16(r12)
+ *	ld	r12, 20(r12)
  *	mtctr	r12
  *	mtlr	r11 // needed to retain ftrace ABI
  *	bctr
+ *	.long	<branch_addr>/<dummy_tramp>
  *
  * dummy_tramp is used to reduce synchronization requirements.
  *
@@ -1381,10 +1429,12 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
 	 * 1. Update the address in the long branch stub:
 	 * If new_addr is out of range, we will have to use the long branch stub, so patch new_addr
 	 * here. Otherwise, revert to dummy_tramp, but only if we had patched old_addr here.
+	 *
+	 * dummy_tramp_addr moved to bottom of long branch stub.
 	 */
 	if ((new_addr && !is_offset_in_branch_range(new_addr - ip)) ||
 	    (old_addr && !is_offset_in_branch_range(old_addr - ip)))
-		ret = patch_ulong((void *)(bpf_func_end - bpf_jit_long_branch_stub - SZL),
+		ret = patch_ulong((void *)(bpf_func_end - SZL), /* SZL: dummy_tramp_addr offset */
 				  (new_addr && !is_offset_in_branch_range(new_addr - ip)) ?
 				  (unsigned long)new_addr : (unsigned long)dummy_tramp);
 	if (ret)
diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index bfdc50740da8e..1cf12edf0343f 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -229,7 +229,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
 
 }
 
-void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
+void bpf_jit_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx)
 {
 	EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0)));
 
@@ -237,7 +237,7 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 
 	EMIT(PPC_RAW_BLR());
 
-	bpf_jit_build_fentry_stubs(image, ctx);
+	bpf_jit_build_fentry_stubs(image, fimage, ctx);
 }
 
 /* Relative offset needs to be calculated based on final image location */
@@ -1150,6 +1150,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 			 */
 			if (i != flen - 1) {
 				ret = bpf_jit_emit_exit_insn(image, ctx, _R0, exit_addr);
+				ret = bpf_jit_emit_exit_insn(image, fimage,
+								ctx, _R0, exit_addr);
 				if (ret)
 					return ret;
 			}
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index dab106cae22b5..e80312171aa74 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -276,7 +276,7 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 		 */
 		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));
+		EMIT(PPC_RAW_CMPLDI(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)));
@@ -398,7 +398,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
 	}
 }
 
-void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
+void bpf_jit_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx)
 {
 	bpf_jit_emit_common_epilogue(image, ctx);
 
@@ -407,7 +407,7 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 
 	EMIT(PPC_RAW_BLR());
 
-	bpf_jit_build_fentry_stubs(image, ctx);
+	bpf_jit_build_fentry_stubs(image, fimage, ctx);
 }
 
 /*
@@ -662,7 +662,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	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));
+	EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
 	PPC_BCC_CONST_SHORT(COND_LE, 8);
 
 	/* dereference TMP_REG_1 */
@@ -672,7 +672,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	 * if (tail_call_info == MAX_TAIL_CALL_CNT)
 	 *   goto out;
 	 */
-	EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
+	EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
 	PPC_BCC_SHORT(COND_EQ, out);
 
 	/*
@@ -707,7 +707,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	 * 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));
+	EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_2), MAX_TAIL_CALL_CNT));
 	PPC_BCC_CONST_SHORT(COND_GT, 8);
 
 	/* First get address of tail_call_info */
@@ -1737,7 +1737,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 			 * we'll just fall through to the epilogue.
 			 */
 			if (i != flen - 1) {
-				ret = bpf_jit_emit_exit_insn(image, ctx, tmp1_reg, exit_addr);
+				ret = bpf_jit_emit_exit_insn(image, fimage, ctx,
+								tmp1_reg, exit_addr);
 				if (ret)
 					return ret;
 			}
diff --git a/tools/testing/selftests/bpf/jit_disasm_helpers.c b/tools/testing/selftests/bpf/jit_disasm_helpers.c
index 3558fe10e28cf..c4aa1d69d3bbf 100644
--- a/tools/testing/selftests/bpf/jit_disasm_helpers.c
+++ b/tools/testing/selftests/bpf/jit_disasm_helpers.c
@@ -179,9 +179,11 @@ int get_jited_program_text(int fd, char *text, size_t text_sz)
 	struct bpf_prog_info info = {};
 	__u32 info_len = sizeof(info);
 	__u32 jited_funcs, len, pc;
+	__u32 trunc_len = 0, disasm_len;
 	__u32 *func_lens = NULL;
 	FILE *text_out = NULL;
 	uint8_t *image = NULL;
+	char *triple = NULL;
 	int i, err = 0;
 
 	if (!llvm_initialized) {
@@ -225,9 +227,30 @@ int get_jited_program_text(int fd, char *text, size_t text_sz)
 	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd #2"))
 		goto out;
 
+	/*
+	 * last 8 bytes contains dummy_trampoline address in JIT
+	 * output on 64-bit and last 4 bytes on 32-bit powerpc,
+	 * which can't disassemble to a valid instruction.
+	 */
+	triple = LLVMGetDefaultTargetTriple();
+	if (triple) {
+		if (strstr(triple, "powerpc64") || strstr(triple, "ppc64"))
+			trunc_len = 8;
+		else if (strstr(triple, "powerpc") || strstr(triple, "ppc"))
+			trunc_len = 4;
+		LLVMDisposeMessage(triple);
+	}
+
 	for (pc = 0, i = 0; i < jited_funcs; ++i) {
+
 		fprintf(text_out, "func #%d:\n", i);
-		disasm_one_func(text_out, image + pc, func_lens[i]);
+		/*
+		 * Disabled JIT have zero func_lens, hence underflow
+		 */
+		disasm_len = func_lens[i] > trunc_len ?
+					func_lens[i] - trunc_len : 0;
+		disasm_one_func(text_out, image + pc, disasm_len);
+
 		fprintf(text_out, "\n");
 		pc += func_lens[i];
 	}
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 5eacf1b432521..c35359c97e44b 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -159,6 +159,7 @@
 #define __arch_riscv64		__arch("RISCV64")
 #define __arch_s390x		__arch("s390x")
 #define __arch_loongarch	__arch("LOONGARCH")
+#define __arch_powerpc64	__arch("POWERPC64")
 #define __caps_unpriv(caps)	__test_tag("test_caps_unpriv=" EXPAND_QUOTE(caps))
 #define __load_if_JITed()	__test_tag("load_mode=jited")
 #define __load_if_no_JITed()	__test_tag("load_mode=no_jited")
diff --git a/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c b/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
index 48fa34d2959f4..182302ff1db07 100644
--- a/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
+++ b/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
@@ -91,6 +91,81 @@ __jited("	popq	%rax")
 __jited("	jmp	{{.*}}")		/* jump to tail call tgt   */
 __jited("L0:	leave")
 __jited("	{{(retq|jmp	0x)}}")		/* return or jump to rethunk */
+__arch_powerpc64
+/* program entry for main(), regular function prologue */
+__jited("	nop")
+__jited("...")                          /* ld 2, 16(13) absent with CONFIG_PPC_KERNEL_PCREL */
+__jited("	li 9, 0")
+__jited("	std 9, -8(1)")
+__jited("	mflr 0")
+__jited("	std 0, 16(1)")
+__jited("	stdu 1, {{.*}}(1)")
+/* load address and call sub() via count register
+ *
+ * Address materialization differs between PCREL and non-PCREL kernels.
+ * Skip the address generation sequence and verify only that the call
+ * target is loaded into CTR before branching.
+ */
+__jited("...")
+__jited("...")
+__jited("...")
+__jited("...")
+__jited("...")
+__jited("	mtctr 12")
+__jited("	bctrl")
+__jited("	mr	8, 3")
+__jited("	li 8, 0")
+__jited("	addi 1, 1, {{.*}}")
+__jited("	ld 0, 16(1)")
+__jited("	mtlr 0")
+__jited("	mr	3, 8")
+__jited("	blr")
+__jited("...")
+__jited("func #1")
+/* subprogram entry for sub() */
+__jited("	nop")
+__jited("...")                          /* ld 2, 16(13) absent with CONFIG_PPC_KERNEL_PCREL */
+/* tail call prologue for subprogram */
+__jited("	ld 10, 0(1)")
+__jited("	ld 9, -8(10)")
+__jited("	cmpldi	9, 33")
+__jited("	bt	{{.*}}, {{.*}}")
+__jited("	addi 9, 10, -8")
+__jited("	std 9, -8(1)")
+__jited("	lis {{.*}}, {{.*}}")
+__jited("	sldi {{.*}}, {{.*}}, 32")
+__jited("	oris {{.*}}, {{.*}}, {{.*}}")
+__jited("	ori {{.*}}, {{.*}}, {{.*}}")
+__jited("	li {{.*}}, 0")
+__jited("	lwz 9, {{.*}}({{.*}})")
+__jited("	slwi {{.*}}, {{.*}}, 0")
+__jited("	cmplw	{{.*}}, 9")
+__jited("	bf	0, {{.*}}")
+/* bpf_tail_call implementation */
+__jited("	ld 9, -8(1)")
+__jited("	cmpldi	9, 33")
+__jited("	bf	{{.*}}, {{.*}}")
+__jited("	ld 9, 0(9)")
+__jited("	cmpldi	9, 33")
+__jited("	bt	{{.*}}, {{.*}}")
+__jited("	addi 9, 9, 1")
+__jited("	mulli 10, {{.*}}, 8")
+__jited("	add 10, 10, {{.*}}")
+__jited("	ld 10, {{.*}}(10)")
+__jited("	cmpldi	10, 0")
+__jited("	bt	{{.*}}, {{.*}}")
+__jited("	ld 10, {{.*}}(10)")
+__jited("	addi 10, 10, {{.*}}")    /* offset depends on CONFIG_PPC_KERNEL_PCREL */
+__jited("	mtctr 10")
+__jited("	ld 10, -8(1)")
+__jited("	cmpldi	10, 33")
+__jited("	bt	{{.*}}, {{.*}}")
+__jited("	addi 10, 1, -8")
+__jited("	std 9, 0(10)")
+__jited("	bctr")
+__jited("	mr	3, 8")
+__jited("	blr")
+
 SEC("tc")
 __naked int main(void)
 {
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 07807757b518d..221393f2a8ef4 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -378,6 +378,7 @@ enum arch {
 	ARCH_RISCV64	= 0x8,
 	ARCH_S390X	= 0x10,
 	ARCH_LOONGARCH	= 0x20,
+	ARCH_POWERPC64	= 0x40,
 };
 
 static int get_current_arch(void)
@@ -392,6 +393,8 @@ static int get_current_arch(void)
 	return ARCH_S390X;
 #elif defined(__loongarch__)
 	return ARCH_LOONGARCH;
+#elif defined(__powerpc64__)
+	return ARCH_POWERPC64;
 #endif
 	return ARCH_UNKNOWN;
 }
@@ -585,6 +588,8 @@ static int parse_test_spec(struct test_loader *tester,
 				arch = ARCH_S390X;
 			} else if (strcmp(val, "LOONGARCH") == 0) {
 				arch = ARCH_LOONGARCH;
+			} else if (strcmp(val, "POWERPC64") == 0) {
+				arch = ARCH_POWERPC64;
 			} else {
 				PRINT_FAIL("bad arch spec: '%s'\n", val);
 				err = -EINVAL;