@@ -214,8 +214,8 @@ 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);
 void prepare_for_fsession_fentry(u32 *image, struct codegen_context *ctx, int cookie_cnt,

@@ -49,11 +49,39 @@ 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 ool_instrs;
 
 	/*
+	 * 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 offset. The OOL stub has 4 instructions (with
+	 * CONFIG_PPC_FTRACE_OUT_OF_LINE) or 3 instructions (without)
+	 * before dummy_tramp_addr.
+	 *
+	 * Emit a NOP here if (ctx->idx + ool_instrs) is odd, so that
+	 * dummy_tramp_addr lands at an even instruction offset (== 8-byte
+	 * aligned from an 8-byte aligned base).
+	 *
+	 * 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.
+	 */
+
+	ool_instrs = IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) ? 4*4 : 3*4;
+	if (!image || !IS_ALIGNED((unsigned long)fimage + ctx->idx*4 + ool_instrs, SZL))
+		EMIT(PPC_RAW_NOP());
+
+	/*
+	 *      nop     // optional, for alignment of dummy_tramp_addr
 	 * Out-of-line stub:
 	 *	mflr	r0
 	 *	[b|bl]	tramp

@@ -70,7 +98,7 @@ void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
 
 	/*
 	 * Long branch stub:
-	 *	.long	<dummy_tramp_addr>
+	 *	.long	<dummy_tramp_addr>  // 8-byte aligned
 	 *	mflr	r11
 	 *	bcl	20,31,$+4
 	 *	mflr	r12

@@ -81,6 +109,7 @@ void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
 	 */
 	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));

@@ -107,7 +136,7 @@ int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg,
 		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, NULL, ctx);
 	}
 
 	return 0;

@@ -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);

@@ -318,7 +347,7 @@ 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);
+		bpf_jit_build_epilogue(code_base, fcode_base, &cgctx);
 
 		if (bpf_jit_enable > 1)
 			pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass,

@@ -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 */

@@ -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);
 }
 
 /*