[lldb] Fix "in function" detection in "thread until" (#123622)

The implementation has an optimization which detects the range of line
table entries covered by the function and then only searches for a
matching line between them.

This optimization was interfering with the logic for detecting whether a
line belongs to the function because the first call to FindLineEntry was
made with exact=false, which meant that if the function did not contain
any exact matches, we would just pick the closest line number in that
range, even if it was very far away.

This patch fixes that by first attempting an inexact search across the
entire line table, and then use the (potentially inexact) result of that
for searching within the function. This makes the optimization a less
effective, but I don't think we can differentiate between a line that
belongs to the function (but doesn't have any code) and a line outside
the function without that.

The patch also avoids the use of (deprecated) Function::GetAddressRange
by iterating over the GetAddressRanges result to find the full range of
line entries for the function.

Author: labath

lldb/source/Commands/CommandObjectThread.cpp

@@ -959,7 +959,6 @@ class CommandObjectThreadUntil : public CommandObjectParsed {
         }
 
         LineEntry function_start;
-        uint32_t index_ptr = 0, end_ptr = UINT32_MAX;
         std::vector<addr_t> address_list;
 
         // Find the beginning & end index of the function, but first make
@@ -970,19 +969,14 @@ class CommandObjectThreadUntil : public CommandObjectParsed {
           return;
         }
 
-        AddressRange fun_addr_range = sc.function->GetAddressRange();
-        Address fun_start_addr = fun_addr_range.GetBaseAddress();
-        line_table->FindLineEntryByAddress(fun_start_addr, function_start,
-                                           &index_ptr);
-
-        Address fun_end_addr(fun_start_addr.GetSection(),
-                             fun_start_addr.GetOffset() +
-                                 fun_addr_range.GetByteSize());
-
-        bool all_in_function = true;
+        RangeVector<uint32_t, uint32_t> line_idx_ranges;
+        for (const AddressRange &range : sc.function->GetAddressRanges()) {
+          auto [begin, end] = line_table->GetLineEntryIndexRange(range);
+          line_idx_ranges.Append(begin, end - begin);
+        }
+        line_idx_ranges.Sort();
 
-        line_table->FindLineEntryByAddress(fun_end_addr, function_start,
-                                           &end_ptr);
+        bool found_something = false;
 
         // Since not all source lines will contribute code, check if we are
         // setting the breakpoint on the exact line number or the nearest
@@ -991,45 +985,43 @@ class CommandObjectThreadUntil : public CommandObjectParsed {
         for (uint32_t line_number : line_numbers) {
           LineEntry line_entry;
           bool exact = false;
-          uint32_t start_idx_ptr = index_ptr;
-          start_idx_ptr = sc.comp_unit->FindLineEntry(
-              index_ptr, line_number, nullptr, exact, &line_entry);
-          if (start_idx_ptr != UINT32_MAX)
-            line_number = line_entry.line;
+          if (sc.comp_unit->FindLineEntry(0, line_number, nullptr, exact,
+                                          &line_entry) == UINT32_MAX)
+            continue;
+
+          found_something = true;
+          line_number = line_entry.line;
           exact = true;
-          start_idx_ptr = index_ptr;
-          while (start_idx_ptr <= end_ptr) {
-            start_idx_ptr = sc.comp_unit->FindLineEntry(
-                start_idx_ptr, line_number, nullptr, exact, &line_entry);
-            if (start_idx_ptr == UINT32_MAX)
-              break;
-
-            addr_t address =
-                line_entry.range.GetBaseAddress().GetLoadAddress(target);
-            if (address != LLDB_INVALID_ADDRESS) {
-              if (fun_addr_range.ContainsLoadAddress(address, target))
+          uint32_t end_func_idx = line_idx_ranges.GetMaxRangeEnd(0);
+          uint32_t idx = sc.comp_unit->FindLineEntry(
+              line_idx_ranges.GetMinRangeBase(UINT32_MAX), line_number, nullptr,
+              exact, &line_entry);
+          while (idx < end_func_idx) {
+            if (line_idx_ranges.FindEntryIndexThatContains(idx) != UINT32_MAX) {
+              addr_t address =
+                  line_entry.range.GetBaseAddress().GetLoadAddress(target);
+              if (address != LLDB_INVALID_ADDRESS)
                 address_list.push_back(address);
-              else
-                all_in_function = false;
             }
-            start_idx_ptr++;
+            idx = sc.comp_unit->FindLineEntry(idx + 1, line_number, nullptr,
+                                              exact, &line_entry);
           }
         }
 
         for (lldb::addr_t address : m_options.m_until_addrs) {
-          if (fun_addr_range.ContainsLoadAddress(address, target))
+          AddressRange unused;
+          if (sc.function->GetRangeContainingLoadAddress(address, *target,
+                                                         unused))
             address_list.push_back(address);
-          else
-            all_in_function = false;
         }
 
         if (address_list.empty()) {
-          if (all_in_function)
+          if (found_something)
             result.AppendErrorWithFormat(
-                "No line entries matching until target.\n");
+                "Until target outside of the current function.\n");
           else
             result.AppendErrorWithFormat(
-                "Until target outside of the current function.\n");
+                "No line entries matching until target.\n");
 
           return;
         }

lldb/test/API/functionalities/thread/step_until/TestStepUntil.py

@@ -16,9 +16,18 @@ def setUp(self):
         self.less_than_two = line_number("main.c", "Less than 2")
         self.greater_than_two = line_number("main.c", "Greater than or equal to 2.")
         self.back_out_in_main = line_number("main.c", "Back out in main")
+        self.in_foo = line_number("main.c", "In foo")
+
+    def _build_dict_for_discontinuity(self):
+        return dict(
+            CFLAGS_EXTRAS="-funique-basic-block-section-names "
+            + "-ffunction-sections -fbasic-block-sections=list="
+            + self.getSourcePath("function.list"),
+            LD_EXTRAS="-Wl,--script=" + self.getSourcePath("symbol.order"),
+        )
 
-    def common_setup(self, args):
-        self.build()
+    def _common_setup(self, build_dict, args):
+        self.build(dictionary=build_dict)
         exe = self.getBuildArtifact("a.out")
 
         target = self.dbg.CreateTarget(exe)
@@ -45,7 +54,7 @@ def common_setup(self, args):
         return thread
 
     def do_until(self, args, until_lines, expected_linenum):
-        thread = self.common_setup(args)
+        thread = self._common_setup(None, args)
 
         cmd_interp = self.dbg.GetCommandInterpreter()
         ret_obj = lldb.SBCommandReturnObject()
@@ -88,3 +97,30 @@ def test_missing_one(self):
         self.do_until(
             ["foo", "bar", "baz"], [self.less_than_two], self.back_out_in_main
         )
+
+    @no_debug_info_test
+    def test_bad_line(self):
+        """Test that we get an error if attempting to step outside the current
+        function"""
+        thread = self._common_setup(None, None)
+        self.expect(
+            f"thread until {self.in_foo}",
+            substrs=["Until target outside of the current function"],
+            error=True,
+        )
+
+    @no_debug_info_test
+    @skipIf(oslist=lldbplatformutil.getDarwinOSTriples() + ["windows"])
+    @skipIf(archs=no_match(["x86_64", "aarch64"]))
+    def test_bad_line_discontinuous(self):
+        """Test that we get an error if attempting to step outside the current
+        function -- and the function is discontinuous"""
+        self.build(dictionary=self._build_dict_for_discontinuity())
+        _, _, thread, _ = lldbutil.run_to_source_breakpoint(
+            self, "At the start", lldb.SBFileSpec(self.main_source)
+        )
+        self.expect(
+            f"thread until {self.in_foo}",
+            substrs=["Until target outside of the current function"],
+            error=True,
+        )