about summary refs log blame commit diff stats
path: root/035compute_segment_address.cc
blob: 5c627a7bdd2fb879d2cf6609db0f46fd2c517d8a (plain) (tree)
//: make some recipes more friendly by trying to auto-convert their ingredients to text

:(scenarios transform)
:(scenario rewrite_stashes_to_text)
def main [
  local-scope
  n:num <- copy 34
  stash n
]
+transform: {stash_2_0: ("address" "array" "character")} <- to-text-line {n: "number"}
+transform: stash {stash_2_0: ("address" "array" "character")}

:(scenario rewrite_traces_to_text)
def main [
  local-scope
  n:num <- copy 34
  trace 2, [app], n
]
+transform: {trace_2_2: ("address" "array" "character")} <- to-text-line {n: "number"}
+transform: trace {2: "literal"}, {"app": "literal-string"}, {trace_2_2: ("address" "array" "character")}

//: special case: rewrite attempts to stash contents of most arrays to avoid
//: passing addresses around

:(scenario rewrite_stashes_of_arrays)
def main [
  local-scope
  n:&:@:num <- new number:type, 3
  stash *n
]
+transform: {stash_2_0: ("address" "array" "character")} <- array-to-text-line {n: ("address" "array" "number")}
+transform: stash {stash_2_0: ("address" "array" "character")}

:(scenario ignore_stashes_of_static_arrays)
def main [
  local-scope
  n:@:num:3 <- create-array
  stash n
]
+transform: stash {n: ("array" "number" "3")}

:(scenario rewrite_stashes_of_recipe_header_products)
container foo [
  x:num
]
def bar -> x:foo [
  local-scope
  load-ingredients
  x <- merge 34
  stash x
]
+transform: stash {stash_2_0: ("address" "array" "character")}

//: misplaced; should be in instruction inserting/deleting transforms, but has
//: prerequisites: deduce_types_from_header and check_or_set_types_by_name
:(after "Transform.push_back(deduce_types_from_header)")
Transform.push_back(convert_ingredients_to_text);  // idempotent

:(code)
void convert_ingredients_to_text(const recipe_ordinal r) {
  recipe& caller = get(Recipe, r);
  trace(9991, "transform") << "--- convert some ingredients to text in recipe " << caller.name << end();
  // in recipes without named locations, 'stash' is still not extensible
  if (contains_numeric_locations(caller)) return;
  convert_ingredients_to_text(caller);
pre { line-height: 125%; }
td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
.highlight .hll { background-color: #ffffcc }
.highlight .c { color: #888888 } /* Comment */
.highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */
.highlight .k { color: #008800; font-weight: bold } /* Keyword */
.highlight .ch { color: #888888 } /* Comment.Hashbang */
.highlight .cm { color: #888888 } /* Comment.Multiline */
.highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */
.highlight .cpf { color: #888888 } /* Comment.PreprocFile */
.highlight .c1 { color: #888888 } /* Comment.Single */
.highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */
.highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */
.highlight .ge { font-style: italic } /* Generic.Emph */
.highlight .ges { font-weight: bold; font-style: italic } /* Generic.EmphStrong */
.highlight .gr { color: #aa0000 } /* Generic.Error */
.highlight .gh { color: #333333 } /* Generic.Heading */
.highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #555555 } /* Generic.Prompt */
.highlight .gs { font-weight: bold } /* Generic.Strong */
.highlight .gu { color: #666666 } /* Generic.Subheading */
.highlight .gt { color: #aa0000 } /* Generic.Traceback */
.highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */
.highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */
.highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */
.highlight .kp { color: #008800 } /* Keyword.Pseudo */
.highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */
.highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */
.highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */
.highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */
.highlight .na { color: #336699 } /* Name.Attribute */
.highlight .nb { color: #003388 } /* Name.Builtin */
.highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */
.highlight .no { color: #003366; font-weight: bold } /* Name.Constant */
.highlight .nd { color: #555555 } /* Name.Decorator */
.highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */
.highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */
.highlight .nl { color: #336699; font-style: italic } /* Name.Label */
.highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */
.highlight .py { color: #336699; font-weight: bold } /* Name.Property */
.highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag */
.highlight .nv { color: #336699 } /* Name.Variable */
.highlight .ow { color: #008800 } /* Operator.Word */
.highlight .w { color: #bbbbbb } /* Text.Whitespace */
.highlight .mb { color: #0000DD; font-weight: bold } /* Literal.Number.Bin */
.highlight .mf { color: #0000DD; font-weight: bold } /* Literal.Number.Float */
.highlight .mh { color: #0000DD; font-weight: bold } /* Literal.Number.Hex */
.highlight .mi { color: #0000DD; font-weight: bold } /* Literal.Number.Integer */
.highlight .mo { color: #0000DD; font-weight: bold } /* Literal.Number.Oct */
.highlight .sa { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Affix */
.highlight .sb { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Backtick */
.highlight .sc { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Char */
.highlight .dl { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Delimiter */
.highlight .sd { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Doc */
.highlight .s2 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Double */
.highlight .se { color: #0044dd; background-color: #fff0f0 } /* Literal.String.Escape */
.highlight .sh { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Heredoc */
.highlight .si { color: #3333bb; background-color: #fff0f0 } /* Literal.String.Interpol */
.highlight .sx { color: #22bb22; background-color: #f0fff0 } /* Literal.String.Other */
.highlight .sr { color: #008800; background-color: #fff0ff } /* Literal.String.Regex */
.highlight .s1 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Single */
.highlight .ss { color: #aa6600; background-color: #fff0f0 } /* Literal.String.Symbol */
.highlight .bp { color: #003388 } /* Name.Builtin.Pseudo */
.highlight .fm { color: #0066bb; font-weight: bold } /* Name.Function.Magic */
.highlight .vc { color: #336699 } /* Name.Variable.Class */
.highlight .vg { color: #dd7700 } /* Name.Variable.Global */
.highlight .vi { color: #3333bb } /* Name.Variable.Instance */
.highlight .vm { color: #336699 } /* Name.Variable.Magic */
.highlight .il { color: #0000DD; font-weight: bold } /* Literal.Number.Integer.Long */
//: ELF binaries have finicky rules about the precise alignment each segment
//: should start at. They depend on the amount of code in a program.
//: We shouldn't expect people to adjust segment addresses everytime they make
//: a change to their programs.
//: Let's start taking the given segment addresses as guidelines, and adjust
//: them as necessary.
//: This gives up a measure of control in placing code and data.

void test_segment_name() {
  run(
      "== code 0x09000000\n"
      "05/add-to-EAX  0x0d0c0b0a/imm32\n"
      // code starts at 0x09000000 + p_offset, which is 0x54 for a single-segment binary
  );
  CHECK_TRACE_CONTENTS(
      "load: 0x09000054 -> 05\n"
      "load: 0x09000055 -> 0a\n"
      "load: 0x09000056 -> 0b\n"
      "load: 0x09000057 -> 0c\n"
      "load: 0x09000058 -> 0d\n"
      "run: add imm32 0x0d0c0b0a to EAX\n"
      "run: storing 0x0d0c0b0a\n"
  );
}

//: compute segment address

:(before "End Transforms")
Transform.push_back(compute_segment_starts);

:(code)
void compute_segment_starts(program& p) {
  trace(3, "transform") << "-- compute segment addresses" << end();
  uint32_t p_offset = /*size of ehdr*/0x34 + SIZE(p.segments)*0x20/*size of each phdr*/;
  for (size_t i = 0;  i < p.segments.size();  ++i) {
    segment& curr = p.segments.at(i);
    if (curr.start >= 0x08000000) {
      // valid address for user space, so assume we're creating a real ELF binary, not just running a test
      curr.start &= 0xfffff000;  // same number of zeros as the p_align used when emitting the ELF binary
      curr.start |= (p_offset & 0xfff);
      trace(99, "transform") << "segment " << i << " begins at address 0x" << HEXWORD << curr.start << end();
    }
    p_offset += size_of(curr);
    assert(p_offset < SEGMENT_ALIGNMENT);  // for now we get less and less available space in each successive segment
  }
}

uint32_t size_of(const segment& s) {
  uint32_t sum = 0;
  for (int i = 0;  i < SIZE(s.lines);  ++i)
    sum += num_bytes(s.lines.at(i));
  return sum;
}

// Assumes all bitfields are packed.
uint32_t num_bytes(const line& inst) {
  uint32_t sum = 0;
  for (int i = 0;  i < SIZE(inst.words);  ++i)
    sum += size_of(inst.words.at(i));
  return sum;
}

int size_of(const word& w) {
  if (has_argument_metadata(w, "disp32") || has_argument_metadata(w, "imm32"))
    return 4;
  else if (has_argument_metadata(w, "disp16"))
    return 2;
  // End size_of(word w) Special-cases
  else
    return 1;
}

//: Dependencies:
//: - We'd like to compute segment addresses before setting up global variables,
//:   because computing addresses for global variables requires knowing where
//:   the data segment starts.
//: - We'd like to finish expanding labels before computing segment addresses,
//:   because it would make computing the sizes of segments more self-contained
//:   (num_bytes).
//:
//: Decision: compute segment addresses before expanding labels, by being
//: aware in this layer of certain argument types that will eventually occupy
//: multiple bytes.
//:
//: The layer to expand labels later hooks into num_bytes() to teach this
//: layer that labels occupy zero space in the binary.
/span>return !x.type->atom && x.type->left->atom && x.type->left->name == "array"; } //: Supporting 'append' above requires remembering what name an instruction //: had before any rewrites or transforms. :(before "End instruction Fields") string name_before_rewrite; :(before "End instruction Clear") name_before_rewrite.clear(); :(before "End next_instruction(curr)") curr->name_before_rewrite = curr->name; :(scenarios run) :(scenario append_other_types_to_text) def main [ local-scope n:num <- copy 11 c:char <- copy 111/o a:text <- append [abc], 10, n, c expected:text <- new [abc1011o] 10:bool/raw <- equal a, expected ] //: Make sure that the new system is strictly better than just the 'stash' //: primitive by itself. :(scenario rewrite_stash_continues_to_fall_back_to_default_implementation) # type without a to-text implementation container foo [ x:num y:num ] def main [ local-scope x:foo <- merge 34, 35 stash x ] +app: 34 35