PPC: Detect unpooled string literal references

Author: LagoLunatic

objdiff-core/src/arch/mod.rs

@@ -247,7 +247,13 @@ pub trait Arch: Send + Sync + Debug {
         SymbolFlagSet::default()
     }
 
-    fn guess_data_type(&self, _resolved: ResolvedInstructionRef) -> Option<DataType> { None }
+    fn guess_data_type(
+        &self,
+        _resolved: ResolvedInstructionRef,
+        _bytes: &[u8],
+    ) -> Option<DataType> {
+        None
+    }
 
     fn symbol_hover(&self, _obj: &Object, _symbol_index: usize) -> Vec<HoverItem> { Vec::new() }
 

objdiff-core/src/arch/ppc.rs

@@ -221,12 +221,21 @@ impl Arch for ArchPpc {
         }
     }
 
-    fn guess_data_type(&self, resolved: ResolvedInstructionRef) -> Option<DataType> {
+    fn guess_data_type(&self, resolved: ResolvedInstructionRef, bytes: &[u8]) -> Option<DataType> {
         if resolved.relocation.is_some_and(|r| r.symbol.name.starts_with("@stringBase")) {
+            // Pooled string.
             return Some(DataType::String);
         }
         let opcode = ppc750cl::Opcode::from(resolved.ins_ref.opcode as u8);
-        guess_data_type_from_load_store_inst_op(opcode)
+        if let Some(ty) = guess_data_type_from_load_store_inst_op(opcode) {
+            // Numeric type.
+            return Some(ty);
+        }
+        if bytes.len() >= 2 && bytes.iter().position(|&c| c == b'\0') == Some(bytes.len() - 1) {
+            // It may be an unpooled string if the symbol contains exactly one null byte at the end of the symbol.
+            return Some(DataType::String);
+        }
+        None
     }
 
     fn symbol_hover(&self, _obj: &Object, symbol_index: usize) -> Vec<HoverItem> {

objdiff-core/src/diff/code.rs

@@ -330,6 +330,7 @@ fn reloc_eq(
                     || address_eq(left_reloc, right_reloc))
                 && (diff_config.function_reloc_diffs == FunctionRelocDiffs::NameAddress
                     || left_reloc.symbol.kind != SymbolKind::Object
+                    || right_reloc.symbol.size == 0 // Likely a pool symbol like ...data, don't treat this as a diff
                     || display_ins_data_literals(left_obj, left_ins)
                         == display_ins_data_literals(right_obj, right_ins))
         }

objdiff-core/src/diff/display.rs

@@ -564,7 +564,8 @@ pub fn instruction_hover(
     if let Some(reloc) = resolved.relocation {
         out.push(HoverItem::Separator);
         out.append(&mut relocation_hover(obj, reloc, None));
-        if let Some(ty) = obj.arch.guess_data_type(resolved) {
+        let bytes = obj.symbol_data(reloc.relocation.target_symbol).unwrap_or(&[]);
+        if let Some(ty) = obj.arch.guess_data_type(resolved, bytes) {
             let literals = display_ins_data_literals(obj, resolved);
             if !literals.is_empty() {
                 out.push(HoverItem::Separator);
@@ -758,7 +759,7 @@ pub fn display_ins_data_labels(obj: &Object, resolved: ResolvedInstructionRef) -
     };
     let bytes = &data[reloc.relocation.addend as usize..];
     obj.arch
-        .guess_data_type(resolved)
+        .guess_data_type(resolved, bytes)
         .map(|ty| ty.display_labels(obj.endianness, bytes))
         .unwrap_or_default()
 }
@@ -775,7 +776,7 @@ pub fn display_ins_data_literals(obj: &Object, resolved: ResolvedInstructionRef)
     };
     let bytes = &data[reloc.relocation.addend as usize..];
     obj.arch
-        .guess_data_type(resolved)
+        .guess_data_type(resolved, bytes)
         .map(|ty| ty.display_literals(obj.endianness, bytes))
         .unwrap_or_default()
 }