[PATCH v2 2/5] powerpc/bpf: Move out dummy_tramp_addr after Long branch stub

[adubey at linux.ibm.com]

From: Abhishek Dubey <adubey at linux.ibm.com>

Move the long branch address space to the bottom of the long
branch stub. This allows uninterrupted disassembly until the
last 8 bytes. Exclude these last bytes from the overall
program length to prevent failure in assembly generation.
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 <adubey at linux.ibm.com>
---
 arch/powerpc/net/bpf_jit_comp.c | 35 ++++++++++++++++++++++-----------
 1 file changed, 24 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 3cbb3647f7a0..00abad48fa6c 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -93,27 +93,36 @@ 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 current pc
+	 *	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
+	 *	nop		// for alignment of following address field
+	 *	.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());
+	/*
+	 * The start of Long branch stub is guaranteed to be aligned as
+	 * result of optional NOP injection before OOL stub above.
+	 * Append tail NOP to re-gain 8-byte alignment disturbed by odd
+	 * instruction count in Long branch stub.
+	 */
+	EMIT(PPC_RAW_NOP());
+
+	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;
@@ -1309,6 +1318,7 @@ 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>
@@ -1316,7 +1326,6 @@ 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
@@ -1324,6 +1333,8 @@ static void do_isync(void *info __maybe_unused)
  *	mtctr	r12
  *	mtlr	r11 // needed to retain ftrace ABI
  *	bctr
+ *	nop	// nop for mem alignment of dummy_tramp_addr
+ *	.long	<branch_addr>/<dummy_tramp>
  *
  * dummy_tramp is used to reduce synchronization requirements.
  *
@@ -1425,10 +1436,12 @@ 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)
-- 
2.52.0