about summary refs log tree commit diff stats
path: root/subx/010---vm.cc
blob: 47b2c3dab41b18e603e32f30c5855c178de8da74 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
//: Core data structures for simulating the SubX VM (subset of an x86 processor)
//:
//: At the lowest level ("level 1") of abstraction, SubX executes x86
//: instructions provided in the form of an array of bytes, loaded into memory
//: starting at a specific address.

//:: registers
//: assume segment registers are hard-coded to 0
//: no floating-point, MMX, etc. yet

:(before "End Types")
enum {
  EAX,
  ECX,
  EDX,
  EBX,
  ESP,
  EBP,
  ESI,
  EDI,
  NUM_INT_REGISTERS,
};
union reg {
  int32_t i;
  uint32_t u;
};
:(before "End Globals")
reg Reg[NUM_INT_REGISTERS] = { {0} };
uint32_t EIP = 1;  // preserve null pointer
:(before "End Reset")
bzero(Reg, sizeof(Reg));
EIP = 1;  // preserve null pointer

:(before "End Help Contents")
cerr << "  registers\n";
:(before "End Help Texts")
put_new(Help, "registers",
  "SubX currently supports eight 32-bit integer registers. From 0 to 7, they are:\n"
  "  EAX ECX EDX EBX ESP EBP ESI EDI\n"
  "ESP contains the top of the stack.\n"
  "\n"
  "-- 8-bit registers\n"
  "Some instructions operate on eight *overlapping* 8-bit registers.\n"
  "From 0 to 7, they are:\n"
  "  AL CL DL BL AH CH DH BH\n"
  "The 8-bit registers overlap with the 32-bit ones. AL is the lowest signicant byte\n"
  "of EAX, AH is the second lowest significant byte, and so on.\n"
  "\n"
  "For example, if EBX contains 0x11223344, then BL contains 0x44, and BH contains 0x33.\n"
  "\n"
  "There is no way to access bytes within ESP, EBP, ESI or EDI.\n"
  "\n"
  "For complete details consult the IA-32 software developer's manual, volume 2,\n"
  "table 2-2, \"32-bit addressing forms with the ModR/M byte\".\n"
  "It is included in this repository as 'modrm.pdf'.\n"
  "The register encodings are described in the top row of the table, but you'll need\n"
  "to spend some time with it.\n"
  "\n"
  "-- flag registers\n"
  "Various instructions (particularly 'compare') modify one or more of three 1-bit 'flag'\n"
  "registers, as a side-effect:\n"
  "- the sign flag (SF): usually set if an arithmetic result is negative, or\n"
  "  reset if not.\n"
  "- the zero flag (ZF): usually set if a result is zero, or reset if not.\n"
  "- the overflow flag (OF): usually set if an arithmetic result overflows.\n"
  "The flag bits are read by conditional jumps.\n"
  "\n"
  "For complete details on how different instructions update the flags, consult the IA-32\n"
  "manual (volume 2). There's various versions of it online, such as https://c9x.me/x86,\n"
  "though of course you'll need to be careful to ignore instructions and flag registers\n"
  "that SubX doesn't support.\n"
  "\n"
  "It isn't simple, but if this is the processor you have running on your computer,\n"
  "might as well get good at it.\n"
);

:(before "End Globals")
// the subset of x86 flag registers we care about
bool SF = false;  // sign flag
bool ZF = false;  // zero flag
bool OF = false;  // overflow flag
:(before "End Reset")
SF = ZF = OF = false;

//: how the flag registers are updated after each instruction

:(before "End Includes")
// Combine 'arg1' and 'arg2' with arithmetic operation 'op' and store the
// result in 'arg1', then update flags.
// beware: no side-effects in args
#define BINARY_ARITHMETIC_OP(op, arg1, arg2) { \
  /* arg1 and arg2 must be signed */ \
  int64_t tmp = arg1 op arg2; \
  arg1 = arg1 op arg2; \
  trace(90, "run") << "storing 0x" << HEXWORD << arg1 << end(); \
  SF = (arg1 < 0); \
  ZF = (arg1 == 0); \
  OF = (arg1 != tmp); \
}

// Combine 'arg1' and 'arg2' with bitwise operation 'op' and store the result
// in 'arg1', then update flags.
#define BINARY_BITWISE_OP(op, arg1, arg2) { \
  /* arg1 and arg2 must be unsigned */ \
  arg1 = arg1 op arg2; \
  trace(90, "run") << "storing 0x" << HEXWORD << arg1 << end(); \
  SF = (arg1 >> 31); \
  ZF = (arg1 == 0); \
  OF = false; \
}

//:: simulated RAM

:(before "End Types")
const uint32_t INITIAL_SEGMENT_SIZE = 0x1000000 - 1;
// Subtract one just so we can start the first segment at address 1 without
// overflowing the first segment. Other segments will learn to adjust.

// Like in real-world Linux, we'll allocate RAM for our programs in disjoint
// slabs called VMAs or Virtual Memory Areas.
struct vma {
  uint32_t start;  // inclusive
  uint32_t end;  // exclusive
  vector<uint8_t> _data;
  vma(uint32_t s, uint32_t e) :start(s), end(e) {}
  vma(uint32_t s) :start(s), end(s+INITIAL_SEGMENT_SIZE) {}
  bool match(uint32_t a) {
    return a >= start && a < end;
  }
  bool match32(uint32_t a) {
    return a >= start && a+4 <= end;
  }
  uint8_t& data(uint32_t a) {
    assert(match(a));
    uint32_t result_index = a-start;
    if (_data.size() <= result_index) {
      const int align = 0x1000;
      uint32_t result_size = result_index + 1;  // size needed for result_index to be valid
      #define align_upwards(x, align)  (((x)+(align)-1) & -(align))
      uint32_t new_size = align_upwards(result_size, align);
      #undef align_upwards
      // grow at least 2x to maintain some amortized complexity guarantees
      if (new_size < _data.size() * 2)
        new_size = _data.size() * 2;
      // never grow past the stated limit
      if (new_size > end-start)
        new_size = end-start;
      _data.resize(new_size);
    }
    return _data.at(result_index);
  }
  void grow_until(uint32_t new_end_address) {
    if (new_end_address < end) return;
    // Ugly: vma knows about the global Memory list of vmas
    void sanity_check(uint32_t start, uint32_t end);
    sanity_check(start, new_end_address);
    end = new_end_address;
  }
  // End vma Methods
};
:(code)
void sanity_check(uint32_t start, uint32_t end) {
  bool dup_found = false;
  for (int i = 0;  i < SIZE(Mem);  ++i) {
    const vma& curr = Mem.at(i);
    if (curr.start == start) {
      assert(!dup_found);
      dup_found = true;
    }
    else if (curr.start > start) {
      assert(curr.start > end);
    }
    else if (curr.start < start) {
      assert(curr.end < start);
    }
  }
}

:(before "End Globals")
// RAM is made of VMAs.
vector<vma> Mem;
:(code)
// The first 3 VMAs are special. When loading ELF binaries in later layers,
// we'll assume that the first VMA is for code, the second is for data
// (including the heap), and the third for the stack.
void grow_code_segment(uint32_t new_end_address) {
  assert(!Mem.empty());
  Mem.at(0).grow_until(new_end_address);
}
void grow_data_segment(uint32_t new_end_address) {
  assert(SIZE(Mem) > 1);
  Mem.at(1).grow_until(new_end_address);
}
:(before "End Globals")
uint32_t End_of_program = 0;  // when the program executes past this address in tests we'll stop the test
// The stack grows downward. Can't increase its size for now.
:(before "End Reset")
Mem.clear();
End_of_program = 0;
:(code)
// These helpers depend on Mem being laid out contiguously (so you can't use a
// map, etc.) and on the host also being little-endian.
inline uint8_t read_mem_u8(uint32_t addr) {
  uint8_t* handle = mem_addr_u8(addr);  // error messages get printed here
  return handle ? *handle : 0;
}
inline int8_t read_mem_i8(uint32_t addr) {
  return static_cast<int8_t>(read_mem_u8(addr));
}
inline uint32_t read_mem_u32(uint32_t addr) {
  uint32_t* handle = mem_addr_u32(addr);  // error messages get printed here
  return handle ? *handle : 0;
}
inline int32_t read_mem_i32(uint32_t addr) {
  return static_cast<int32_t>(read_mem_u32(addr));
}

inline uint8_t* mem_addr_u8(uint32_t addr) {
  uint8_t* result = NULL;
  for (int i = 0;  i < SIZE(Mem);  ++i) {
    if (Mem.at(i).match(addr)) {
      if (result)
        raise << "address 0x" << HEXWORD << addr << " is in two segments\n" << end();
      result = &Mem.at(i).data(addr);
    }
  }
  if (result == NULL)
    raise << "Tried to access uninitialized memory at address 0x" << HEXWORD << addr << '\n' << end();
  return result;
}
inline int8_t* mem_addr_i8(uint32_t addr) {
  return reinterpret_cast<int8_t*>(mem_addr_u8(addr));
}
inline uint32_t* mem_addr_u32(uint32_t addr) {
  uint32_t* result = NULL;
  for (int i = 0;  i < SIZE(Mem);  ++i) {
    if (Mem.at(i).match32(addr)) {
      if (result)
        raise << "address 0x" << HEXWORD << addr << " is in two segments\n" << end();
      result = reinterpret_cast<uint32_t*>(&Mem.at(i).data(addr));
    }
  }
  if (result == NULL) {
    raise << "Tried to access uninitialized memory at address 0x" << HEXWORD << addr << '\n' << end();
    raise << "The entire 4-byte word should be initialized and lie in a single segment.\n" << end();
  }
  return result;
}
inline int32_t* mem_addr_i32(uint32_t addr) {
  return reinterpret_cast<int32_t*>(mem_addr_u32(addr));
}
// helper for some syscalls. But read-only.
inline const char* mem_addr_kernel_string(uint32_t addr) {
  return reinterpret_cast<const char*>(mem_addr_u8(addr));
}
inline string mem_addr_string(uint32_t addr, uint32_t size) {
  ostringstream out;
  for (size_t i = 0;  i < size;  ++i)
    out << read_mem_u8(addr+i);
  return out.str();
}


inline void write_mem_u8(uint32_t addr, uint8_t val) {
  uint8_t* handle = mem_addr_u8(addr);
  if (handle != NULL) *handle = val;
}
inline void write_mem_i8(uint32_t addr, int8_t val) {
  int8_t* handle = mem_addr_i8(addr);
  if (handle != NULL) *handle = val;
}
inline void write_mem_u32(uint32_t addr, uint32_t val) {
  uint32_t* handle = mem_addr_u32(addr);
  if (handle != NULL) *handle = val;
}
inline void write_mem_i32(uint32_t addr, int32_t val) {
  int32_t* handle = mem_addr_i32(addr);
  if (handle != NULL) *handle = val;
}

inline bool already_allocated(uint32_t addr) {
  bool result = false;
  for (int i = 0;  i < SIZE(Mem);  ++i) {
    if (Mem.at(i).match(addr)) {
      if (result)
        raise << "address 0x" << HEXWORD << addr << " is in two segments\n" << end();
      result = true;
    }
  }
  return result;
}

//:: core interpreter loop

:(code)
// skeleton of how x86 instructions are decoded
void run_one_instruction() {
  uint8_t op=0, op2=0, op3=0;
  // Run One Instruction
  trace(90, "run") << "inst: 0x" << HEXWORD << EIP << end();
  op = next();
  if (Dump_trace) {
    cerr << "opcode: " << HEXBYTE << NUM(op) << '\n';
    cerr << "registers at start: ";
    dump_registers();
//?     dump_stack();  // for debugging; not defined until later layer
  }
  switch (op) {
  case 0xf4:  // hlt
    EIP = End_of_program;
    break;
  // End Single-Byte Opcodes
  case 0x0f:
    switch(op2 = next()) {
    // End Two-Byte Opcodes Starting With 0f
    default:
      cerr << "unrecognized second opcode after 0f: " << HEXBYTE << NUM(op2) << '\n';
      DUMP("");
      exit(1);
    }
    break;
  case 0xf2:
    switch(op2 = next()) {
    // End Two-Byte Opcodes Starting With f2
    case 0x0f:
      switch(op3 = next()) {
      // End Three-Byte Opcodes Starting With f2 0f
      default:
        cerr << "unrecognized third opcode after f2 0f: " << HEXBYTE << NUM(op3) << '\n';
        DUMP("");
        exit(1);
      }
      break;
    default:
      cerr << "unrecognized second opcode after f2: " << HEXBYTE << NUM(op2) << '\n';
      DUMP("");
      exit(1);
    }
    break;
  case 0xf3:
    switch(op2 = next()) {
    // End Two-Byte Opcodes Starting With f3
    case 0x0f:
      switch(op3 = next()) {
      // End Three-Byte Opcodes Starting With f3 0f
      default:
        cerr << "unrecognized third opcode after f3 0f: " << HEXBYTE << NUM(op3) << '\n';
        DUMP("");
        exit(1);
      }
      break;
    default:
      cerr << "unrecognized second opcode after f3: " << HEXBYTE << NUM(op2) << '\n';
      DUMP("");
      exit(1);
    }
    break;
  default:
    cerr << "unrecognized opcode: " << HEXBYTE << NUM(op) << '\n';
    DUMP("");
    exit(1);
  }
}

inline uint8_t next() {
  return read_mem_u8(EIP++);
}

void dump_registers() {
  for (int i = 0;  i < NUM_INT_REGISTERS;  ++i) {
    if (i > 0) cerr << "; ";
    cerr << "  " << i << ": " << std::hex << std::setw(8) << std::setfill('_') << Reg[i].u;
  }
  cerr << " -- SF: " << SF << "; ZF: " << ZF << "; OF: " << OF << '\n';
}

//: start tracking supported opcodes
:(before "End Globals")
map</*op*/string, string> Name;
map</*op*/string, string> Name_0f;
map</*op*/string, string> Name_f3;
map</*op*/string, string> Name_f3_0f;
:(before "End One-time Setup")
init_op_names();
:(code)
void init_op_names() {
  put(Name, "f4", "halt (hlt)");
  // End Initialize Op Names
}

:(before "End Help Special-cases(key)")
if (key == "opcodes") {
  cerr << "Opcodes currently supported by SubX:\n";
  for (map<string, string>::iterator p = Name.begin();  p != Name.end();  ++p)
    cerr << "  " << p->first << ": " << p->second << '\n';
  for (map<string, string>::iterator p = Name_0f.begin();  p != Name_0f.end();  ++p)
    cerr << "  0f " << p->first << ": " << p->second << '\n';
  for (map<string, string>::iterator p = Name_f3.begin();  p != Name_f3.end();  ++p)
    cerr << "  f3 " << p->first << ": " << p->second << '\n';
  for (map<string, string>::iterator p = Name_f3_0f.begin();  p != Name_f3_0f.end();  ++p)
    cerr << "  f3 0f " << p->first << ": " << p->second << '\n';
  cerr << "Run `subx help instructions` for details on words like 'r32' and 'disp8'.\n"
          "For complete details on these instructions, consult the IA-32 manual (volume 2).\n"
          "There's various versions of it online, such as https://c9x.me/x86.\n"
          "The mnemonics in brackets will help you locate each instruction.\n";
  return 0;
}
:(before "End Help Contents")
cerr << "  opcodes\n";

:(before "End Includes")
#include <iomanip>
#define HEXBYTE  std::hex << std::setw(2) << std::setfill('0')
#define HEXWORD  std::hex << std::setw(8) << std::setfill('0')
// ugly that iostream doesn't print uint8_t as an integer
#define NUM(X) static_cast<int>(X)
#include <stdint.h>