Can generate PC holes in eh_elfs

Before, the space between FDEs was abstracted away, thought as dead
space that produced an error when queried. This is not the case, though:
empty FDEs indicate undefined DWARF

generate_eh_elf.py

@@ -52,6 +52,7 @@ class Config:
                  use_pc_list=False,
                  c_opt_level='3',
                  enable_deref_arg=False,
+                 keep_holes=False,
                  cc_debug=False,
                  remote=None):
         self.output = '.' if output is None else output
@@ -65,6 +66,7 @@ class Config:
         self.use_pc_list = use_pc_list
         self.c_opt_level = c_opt_level
         self.enable_deref_arg = enable_deref_arg
+        self.keep_holes = keep_holes
         self.cc_debug = cc_debug
         self.remote = remote
 
@@ -78,6 +80,8 @@ class Config:
         out.append(self.sw_gen_policy.value)
         if self.enable_deref_arg:
             out.append('--enable-deref-arg')
+        if self.keep_holes:
+            out.append('--keep-holes')
         return out
 
     def cc_opts(self):
@@ -309,6 +313,9 @@ def process_args():
                               "dwarf-assembly, enabling an extra `deref` "
                               "argument for each lookup function, allowing "
                               "to work on remote address spaces."))
+    parser.add_argument('--keep-holes', action='store_true',
+                        help=("Keep holes between FDEs instead of filling "
+                              "them with junk. More accurate, less compact."))
     parser.add_argument("-g", "--cc-debug", action='store_true',
                         help=("Compile the source file with -g for easy "
                               "debugging"))
@@ -356,17 +363,18 @@ def process_args():
 def main():
     args = process_args()
     config = Config(
-        args.output,
-        args.aux,
-        args.no_dft_aux,
-        args.object,
-        args.sw_gen_policy,
-        args.force,
-        args.use_pc_list,
-        args.c_opt_level,
-        args.enable_deref_arg,
-        args.cc_debug,
-        args.remote,
+        output=args.output,
+        aux=args.aux,
+        no_dft_aux=args.no_dft_aux,
+        objects=args.object,
+        sw_gen_policy=args.sw_gen_policy,
+        force=args.force,
+        use_pc_list=args.use_pc_list,
+        c_opt_level=args.c_opt_level,
+        enable_deref_arg=args.enable_deref_arg,
+        keep_holes=args.keep_holes,
+        cc_debug=args.cc_debug,
+        remote=args.remote,
     )
 
     for obj in args.object:

src/CodeGenerator.cpp

@@ -271,6 +271,16 @@ void CodeGenerator::gen_of_reg(const SimpleDwarf::DwRegister& reg,
             }
             break;
         }
+        case SimpleDwarf::DwRegister::REG_PLT_EXPR: {
+            /*
+            if(settings::enable_deref_arg)
+                stream << "(deref(";
+            else
+                stream << "*((uintptr_t*)(";
+            */
+            stream << "(((ctx.rip & 15) >= 11) ? 8 : 0) + ctx.rsp";
+            break;
+        }
         case SimpleDwarf::DwRegister::REG_NOT_IMPLEMENTED:
             stream << "0";
             throw UnhandledRegister();

src/ConseqEquivFilter.cpp

@@ -2,7 +2,7 @@
 
 using namespace std;
 
-ConseqEquivFilter::ConseqEquivFilter() {}
+ConseqEquivFilter::ConseqEquivFilter(bool enable): SimpleDwarfFilter(enable) {}
 
 static bool equiv_reg(
         const SimpleDwarf::DwRegister& r1,

src/ConseqEquivFilter.hpp

@@ -9,7 +9,7 @@
 
 class ConseqEquivFilter: public SimpleDwarfFilter {
     public:
-        ConseqEquivFilter();
+        ConseqEquivFilter(bool enable=true);
 
     private:
         SimpleDwarf do_apply(const SimpleDwarf& dw) const;

src/EmptyFdeDeleter.cpp

@@ -0,0 +1,21 @@
+#include "EmptyFdeDeleter.hpp"
+
+#include <algorithm>
+#include <cstdio>
+
+using namespace std;
+
+EmptyFdeDeleter::EmptyFdeDeleter(bool enable): SimpleDwarfFilter(enable) {}
+
+SimpleDwarf EmptyFdeDeleter::do_apply(const SimpleDwarf& dw) const {
+    SimpleDwarf out(dw);
+
+    auto fde = out.fde_list.begin();
+    while(fde != out.fde_list.end()) {
+        if(fde->rows.empty())
+            fde = out.fde_list.erase(fde);
+        else
+            ++fde;
+    }
+    return out;
+}

src/EmptyFdeDeleter.hpp

@@ -0,0 +1,15 @@
+/** Deletes empty FDEs (that is, FDEs with no rows) from the FDEs collection.
+ * This is used to ensure they do not interfere with PcHoleFiller and such. */
+
+#pragma once
+
+#include "SimpleDwarf.hpp"
+#include "SimpleDwarfFilter.hpp"
+
+class EmptyFdeDeleter: public SimpleDwarfFilter {
+    public:
+        EmptyFdeDeleter(bool enable=true);
+
+    private:
+        SimpleDwarf do_apply(const SimpleDwarf& dw) const;
+};

src/FactoredSwitchCompiler.cpp

@@ -15,9 +15,11 @@ void FactoredSwitchCompiler::to_stream(
     JumpPointMap jump_points;
 
     gen_binsearch_tree(os, jump_points, sw.switch_var,
-            sw.cases.begin(), sw.cases.end());
+            sw.cases.begin(), sw.cases.end(),
+            make_pair(sw.cases.front().low_bound, sw.cases.back().high_bound));
 
-    os << indent_str(sw.default_case) << "\n"
+    os << indent() << "_factor_default:\n"
+       << indent_str(sw.default_case) << "\n"
        << indent() << "/* ===== LABELS  ============================== */\n\n";
 
     gen_jump_points_code(os, jump_points);
@@ -65,7 +67,8 @@ void FactoredSwitchCompiler::gen_binsearch_tree(
         FactoredSwitchCompiler::JumpPointMap& jump_map,
         const std::string& sw_var,
         const FactoredSwitchCompiler::case_iterator_t& begin,
-        const FactoredSwitchCompiler::case_iterator_t& end)
+        const FactoredSwitchCompiler::case_iterator_t& end,
+        const loc_range_t& loc_range)
 {
     size_t iter_delta = end - begin;
     if(iter_delta == 0)
@@ -73,6 +76,19 @@ void FactoredSwitchCompiler::gen_binsearch_tree(
     else if(iter_delta == 1) {
         FactorJumpPoint jump_point = get_jump_point(
                 jump_map, begin->content);
+        if(loc_range.first < begin->low_bound) {
+            os << indent() << "if(" << sw_var << " < 0x"
+               << hex << begin->low_bound << dec
+               << ") goto _factor_default; "
+               << "// IP=0x" << hex << loc_range.first << " ... 0x"
+               << begin->low_bound - 1 << "\n";
+        }
+        if(begin->high_bound + 1 < loc_range.second) {
+            os << indent() << "if(0x" << hex << begin->high_bound << dec
+               << " < " << sw_var << ") goto _factor_default; "
+               << "// IP=0x" << hex << begin->high_bound + 1 << " ... 0x"
+               << loc_range.second - 1 << "\n";
+        }
         os << indent() << "// IP=0x" << hex << begin->low_bound
                        << " ... 0x" << begin->high_bound << dec << "\n"
            << indent() << "goto " << jump_point << ";\n";
@@ -83,11 +99,15 @@ void FactoredSwitchCompiler::gen_binsearch_tree(
         os << indent() << "if(" << sw_var << " < 0x"
            << hex << mid->low_bound << dec << ") {\n";
         indent_count++;
-        gen_binsearch_tree(os, jump_map, sw_var, begin, mid);
+        gen_binsearch_tree(
+                os, jump_map, sw_var, begin, mid,
+                make_pair(loc_range.first, mid->low_bound));
         indent_count--;
         os << indent() << "} else {\n";
         indent_count++;
-        gen_binsearch_tree(os, jump_map, sw_var, mid, end);
+        gen_binsearch_tree(
+                os, jump_map, sw_var, mid, end,
+                make_pair(mid->low_bound, loc_range.second));
         indent_count--;
         os << indent() << "}\n";
     }

src/FactoredSwitchCompiler.hpp

@@ -24,6 +24,7 @@ class FactoredSwitchCompiler: public AbstractSwitchCompiler {
             JumpPointMap;
         typedef std::vector<SwitchStatement::SwitchCase>::const_iterator
             case_iterator_t;
+        typedef std::pair<uintptr_t, uintptr_t> loc_range_t;
 
     private:
         virtual void to_stream(std::ostream& os, const SwitchStatement& sw);
@@ -39,7 +40,9 @@ class FactoredSwitchCompiler: public AbstractSwitchCompiler {
                 JumpPointMap& jump_map,
                 const std::string& sw_var,
                 const case_iterator_t& begin,
-                const case_iterator_t& end);
+                const case_iterator_t& end,
+                const loc_range_t& loc_range // [beg, end[
+                );
 
         size_t cur_label_id;
 

src/Makefile

@@ -12,6 +12,7 @@ OBJS=\
 	PcListReader.o \
 	SimpleDwarfFilter.o \
 	PcHoleFiller.o \
+	EmptyFdeDeleter.o \
 	ConseqEquivFilter.o \
 	SwitchStatement.o \
 	NativeSwitchCompiler.o \

src/PcHoleFiller.cpp

@@ -5,7 +5,7 @@
 
 using namespace std;
 
-PcHoleFiller::PcHoleFiller() {}
+PcHoleFiller::PcHoleFiller(bool enable): SimpleDwarfFilter(enable) {}
 
 SimpleDwarf PcHoleFiller::do_apply(const SimpleDwarf& dw) const {
     SimpleDwarf out(dw);

src/PcHoleFiller.hpp

@@ -8,7 +8,7 @@
 
 class PcHoleFiller: public SimpleDwarfFilter {
     public:
-        PcHoleFiller();
+        PcHoleFiller(bool enable=true);
 
     private:
         SimpleDwarf do_apply(const SimpleDwarf& dw) const;

src/SimpleDwarfFilter.cpp

@@ -1,10 +1,11 @@
 #include "SimpleDwarfFilter.hpp"
 
-SimpleDwarfFilter::SimpleDwarfFilter()
+SimpleDwarfFilter::SimpleDwarfFilter(bool enable): enable(enable)
 {}
 
 SimpleDwarf SimpleDwarfFilter::apply(const SimpleDwarf& dw) const {
-    // For convenience of future enhancements
+    if(!enable)
+        return dw;
     return do_apply(dw);
 }
 

src/SimpleDwarfFilter.hpp

@@ -9,7 +9,11 @@
 
 class SimpleDwarfFilter {
     public:
-        SimpleDwarfFilter();
+        /** Constructor
+         *
+         * @param apply set to false to disable this filter. This setting is
+         * convenient for compact filter-chaining code. */
+        SimpleDwarfFilter(bool enable=true);
 
         /// Applies the filter
         SimpleDwarf apply(const SimpleDwarf& dw) const;
@@ -19,4 +23,6 @@ class SimpleDwarfFilter {
 
     private:
         virtual SimpleDwarf do_apply(const SimpleDwarf& dw) const = 0;
+
+        bool enable;
 };

src/main.cpp

@@ -11,6 +11,7 @@
 #include "NativeSwitchCompiler.hpp"
 #include "FactoredSwitchCompiler.hpp"
 #include "PcHoleFiller.hpp"
+#include "EmptyFdeDeleter.hpp"
 #include "ConseqEquivFilter.hpp"
 
 #include "settings.hpp"
@@ -65,6 +66,10 @@ MainOptions options_parse(int argc, char** argv) {
         else if(option == "--enable-deref-arg") {
             settings::enable_deref_arg = true;
         }
+
+        else if(option == "--keep-holes") {
+            settings::keep_holes = true;
+        }
     }
 
     if(!seen_switch_gen_policy) {
@@ -84,6 +89,7 @@ MainOptions options_parse(int argc, char** argv) {
              << argv[0]
              << " [--switch-per-func | --global-switch]"
              << " [--enable-deref-arg]"
+             << " [--keep-holes]"
              << " [--pc-list PC_LIST_FILE] elf_path"
              << endl;
     }
@@ -98,9 +104,10 @@ int main(int argc, char** argv) {
     SimpleDwarf parsed_dwarf = DwarfReader(opts.elf_path).read();
 
     SimpleDwarf filtered_dwarf =
-        PcHoleFiller()(
+        PcHoleFiller(!settings::keep_holes)(
+        EmptyFdeDeleter()(
         ConseqEquivFilter()(
-            parsed_dwarf));
+            parsed_dwarf)));
 
     FactoredSwitchCompiler* sw_compiler = new FactoredSwitchCompiler(1);
     CodeGenerator code_gen(

src/settings.cpp

@@ -4,4 +4,5 @@ namespace settings {
     SwitchGenerationPolicy switch_generation_policy = SGP_SwitchPerFunc;
     std::string pc_list = "";
     bool enable_deref_arg = false;
+    bool keep_holes = false;
 }

src/settings.hpp

@@ -16,4 +16,6 @@ namespace settings {
     extern SwitchGenerationPolicy switch_generation_policy;
     extern std::string pc_list;
     extern bool enable_deref_arg;
+    extern bool keep_holes; /**< Keep holes between FDEs. Larger eh_elf files,
+                              but more accurate unwinding. */
 }