From: Abhishek Dubey <redacted>

Move the long branch address field to the bottom of the long
branch stub. This allows uninterrupted disassembly until the
last 8 bytes. The last bytes exclusion is logically necessary to
prevent disassembly failure, otherwise the actual program layout
is never altered. Hence no effect on overall program size.
Also, align dummy_tramp_addr field with 8-byte boundary.

Following is disassembler output for test program with moved down
dummy_tramp_addr field:
.....
.....
pc:68    left:44     a6 03 08 7c  :  mtlr 0
pc:72    left:40     bc ff ff 4b  :  b .-68
pc:76    left:36     a6 02 68 7d  :  mflr 11
pc:80    left:32     05 00 9f 42  :  bcl 20, 31, .+4
pc:84    left:28     a6 02 88 7d  :  mflr 12
pc:88    left:24     14 00 8c e9  :  ld 12, 20(12)
pc:92    left:20     a6 03 89 7d  :  mtctr 12
pc:96    left:16     a6 03 68 7d  :  mtlr 11
pc:100   left:12     20 04 80 4e  :  bctr
pc:104   left:8      c0 34 1d 00  :

Failure log:
Can't disasm instruction at offset 104: c0 34 1d 00 00 00 00 c0
Disassembly logic can truncate at 104, ignoring last 8 bytes.

Update the dummy_tramp_addr field offset calculation from the end
of the program to reflect its new location, for bpf_arch_text_poke()
to update the actual trampoline's address in this field.

All BPF trampoline selftests continue to pass with this patch applied.

Signed-off-by: Abhishek Dubey <redacted>
---
  arch/powerpc/net/bpf_jit.h        |  3 +-
  arch/powerpc/net/bpf_jit_comp.c   | 51 ++++++++++++++++---------------
  arch/powerpc/net/bpf_jit_comp64.c |  3 +-
  3 files changed, 31 insertions(+), 26 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 71e6e7d01057..6632de9871dd 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h

@@ -217,7 +217,8 @@ void bpf_jit_build_prologue(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,
  								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 79288ff789b5..ebee23d33396 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c

@@ -52,9 +52,10 @@ 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_instrs;
+	int stubs_instrs;
  
  	/*
+	 * 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.

@@ -62,13 +63,10 @@ void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context
  	 * 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).
+	 * 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

@@ -76,8 +74,8 @@ void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context
  	 * 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))
+	stubs_instrs = IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) ? 11*4 : 10*4;

+	if (!image || !IS_ALIGNED((unsigned long)fimage + ctx->idx*4 + stubs_instrs, SZL))
  		EMIT(PPC_RAW_NOP());
  
  	/*

@@ -98,35 +96,37 @@ 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>  // 8-byte 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))) {
  		PPC_JMP(exit_addr);

@@ -136,7 +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, NULL, ctx);
+		bpf_jit_build_epilogue(image, fimage, ctx);
  	}
  
  	return 0;

@@ -1289,6 +1289,7 @@ 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>

@@ -1296,14 +1297,14 @@ 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.
   *

@@ -1405,10 +1406,12 @@ 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_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 885dc8cf55a2..eaf816a07f14 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c

@@ -1726,7 +1726,8 @@ 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;
  			}