Re: [PATCH v13 5/8] powerpc/bpf: Move out dummy_tramp_addr after Long branch stub

---
  arch/powerpc/net/bpf_jit_comp.c | 44 ++++++++++++++++++---------------
  1 file changed, 24 insertions(+), 20 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 8ca36a933c7a..c2717f0d9cdd 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c

@@ -52,19 +52,19 @@ asm (
  void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context *ctx)
  {
  	int ool_stub_idx, long_branch_stub_idx;
-	int ool_stub_sz;
+	int stub_sz;
  
  	/*
+	 * The dummy_tramp_addr field is placed at bottom of Long branch stub.
  	 * 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.
  	 *
  	 * 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 size is 4 instructions (with CONFIG_PPC_FTRACE_OUT_OF_LINE)
-	 * or 3 instructions (without) before dummy_tramp_addr.
-	 *
-	 * Emit a NOP here if address is not SZL aligned.
+	 * 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

@@ -72,8 +72,8 @@ void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context
  	 * jited_len signifies correct program size.
  	 */
  
-	ool_stub_sz = IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) ? 16 : 12;
-	if (!image || !IS_ALIGNED((unsigned long)fimage + ctx->idx*4 + ool_stub_sz, SZL))
+	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());
  
  	/*

@@ -94,28 +94,29 @@ void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context
  
  	/*
  	 * Long branch stub:
-	 *	.long	<dummy_tramp_addr>  // 8-byte aligned
  	 *	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;

@@ -1309,6 +1310,7 @@ 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>

@@ -1316,14 +1318,14 @@ 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.
   *

@@ -1425,10 +1427,12 @@ 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)