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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477
|
/*-------------------------------------------------------------------------
*
* heapfuncs.c
* Functions to investigate heap pages
*
* We check the input to these functions for corrupt pointers etc. that
* might cause crashes, but at the same time we try to print out as much
* information as possible, even if it's nonsense. That's because if a
* page is corrupt, we don't know why and how exactly it is corrupt, so we
* let the user judge it.
*
* These functions are restricted to superusers for the fear of introducing
* security holes if the input checking isn't as water-tight as it should be.
* You'd need to be superuser to obtain a raw page image anyway, so
* there's hardly any use case for using these without superuser-rights
* anyway.
*
* Copyright (c) 2007-2018, PostgreSQL Global Development Group
*
* IDENTIFICATION
* contrib/pageinspect/heapfuncs.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "pageinspect.h"
#include "access/htup_details.h"
#include "funcapi.h"
#include "catalog/pg_type.h"
#include "miscadmin.h"
#include "utils/array.h"
#include "utils/builtins.h"
#include "utils/rel.h"
/*
* bits_to_text
*
* Converts a bits8-array of 'len' bits to a human-readable
* c-string representation.
*/
static char *
bits_to_text(bits8 *bits, int len)
{
int i;
char *str;
str = palloc(len + 1);
for (i = 0; i < len; i++)
str[i] = (bits[(i / 8)] & (1 << (i % 8))) ? '1' : '0';
str[i] = '\0';
return str;
}
/*
* text_to_bits
*
* Converts a c-string representation of bits into a bits8-array. This is
* the reverse operation of previous routine.
*/
static bits8 *
text_to_bits(char *str, int len)
{
bits8 *bits;
int off = 0;
char byte = 0;
bits = palloc(len + 1);
while (off < len)
{
if (off % 8 == 0)
byte = 0;
if ((str[off] == '0') || (str[off] == '1'))
byte = byte | ((str[off] - '0') << off % 8);
else
ereport(ERROR,
(errcode(ERRCODE_DATA_CORRUPTED),
errmsg("illegal character '%c' in t_bits string", str[off])));
if (off % 8 == 7)
bits[off / 8] = byte;
off++;
}
return bits;
}
/*
* heap_page_items
*
* Allows inspection of line pointers and tuple headers of a heap page.
*/
PG_FUNCTION_INFO_V1(heap_page_items);
typedef struct heap_page_items_state
{
TupleDesc tupd;
Page page;
uint16 offset;
} heap_page_items_state;
Datum
heap_page_items(PG_FUNCTION_ARGS)
{
bytea *raw_page = PG_GETARG_BYTEA_P(0);
heap_page_items_state *inter_call_data = NULL;
FuncCallContext *fctx;
int raw_page_size;
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use raw page functions"))));
raw_page_size = VARSIZE(raw_page) - VARHDRSZ;
if (SRF_IS_FIRSTCALL())
{
TupleDesc tupdesc;
MemoryContext mctx;
if (raw_page_size < SizeOfPageHeaderData)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("input page too small (%d bytes)", raw_page_size)));
fctx = SRF_FIRSTCALL_INIT();
mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx);
inter_call_data = palloc(sizeof(heap_page_items_state));
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
inter_call_data->tupd = tupdesc;
inter_call_data->offset = FirstOffsetNumber;
inter_call_data->page = VARDATA(raw_page);
fctx->max_calls = PageGetMaxOffsetNumber(inter_call_data->page);
fctx->user_fctx = inter_call_data;
MemoryContextSwitchTo(mctx);
}
fctx = SRF_PERCALL_SETUP();
inter_call_data = fctx->user_fctx;
if (fctx->call_cntr < fctx->max_calls)
{
Page page = inter_call_data->page;
HeapTuple resultTuple;
Datum result;
ItemId id;
Datum values[14];
bool nulls[14];
uint16 lp_offset;
uint16 lp_flags;
uint16 lp_len;
memset(nulls, 0, sizeof(nulls));
/* Extract information from the line pointer */
id = PageGetItemId(page, inter_call_data->offset);
lp_offset = ItemIdGetOffset(id);
lp_flags = ItemIdGetFlags(id);
lp_len = ItemIdGetLength(id);
values[0] = UInt16GetDatum(inter_call_data->offset);
values[1] = UInt16GetDatum(lp_offset);
values[2] = UInt16GetDatum(lp_flags);
values[3] = UInt16GetDatum(lp_len);
/*
* We do just enough validity checking to make sure we don't reference
* data outside the page passed to us. The page could be corrupt in
* many other ways, but at least we won't crash.
*/
if (ItemIdHasStorage(id) &&
lp_len >= MinHeapTupleSize &&
lp_offset == MAXALIGN(lp_offset) &&
lp_offset + lp_len <= raw_page_size)
{
HeapTupleHeader tuphdr;
bytea *tuple_data_bytea;
int tuple_data_len;
/* Extract information from the tuple header */
tuphdr = (HeapTupleHeader) PageGetItem(page, id);
values[4] = UInt32GetDatum(HeapTupleHeaderGetRawXmin(tuphdr));
values[5] = UInt32GetDatum(HeapTupleHeaderGetRawXmax(tuphdr));
/* shared with xvac */
values[6] = UInt32GetDatum(HeapTupleHeaderGetRawCommandId(tuphdr));
values[7] = PointerGetDatum(&tuphdr->t_ctid);
values[8] = UInt32GetDatum(tuphdr->t_infomask2);
values[9] = UInt32GetDatum(tuphdr->t_infomask);
values[10] = UInt8GetDatum(tuphdr->t_hoff);
/* Copy raw tuple data into bytea attribute */
tuple_data_len = lp_len - tuphdr->t_hoff;
tuple_data_bytea = (bytea *) palloc(tuple_data_len + VARHDRSZ);
SET_VARSIZE(tuple_data_bytea, tuple_data_len + VARHDRSZ);
memcpy(VARDATA(tuple_data_bytea), (char *) tuphdr + tuphdr->t_hoff,
tuple_data_len);
values[13] = PointerGetDatum(tuple_data_bytea);
/*
* We already checked that the item is completely within the raw
* page passed to us, with the length given in the line pointer.
* Let's check that t_hoff doesn't point over lp_len, before using
* it to access t_bits and oid.
*/
if (tuphdr->t_hoff >= SizeofHeapTupleHeader &&
tuphdr->t_hoff <= lp_len &&
tuphdr->t_hoff == MAXALIGN(tuphdr->t_hoff))
{
if (tuphdr->t_infomask & HEAP_HASNULL)
{
int bits_len;
bits_len =
BITMAPLEN(HeapTupleHeaderGetNatts(tuphdr)) * BITS_PER_BYTE;
values[11] = CStringGetTextDatum(
bits_to_text(tuphdr->t_bits, bits_len));
}
else
nulls[11] = true;
if (tuphdr->t_infomask & HEAP_HASOID)
values[12] = HeapTupleHeaderGetOid(tuphdr);
else
nulls[12] = true;
}
else
{
nulls[11] = true;
nulls[12] = true;
}
}
else
{
/*
* The line pointer is not used, or it's invalid. Set the rest of
* the fields to NULL
*/
int i;
for (i = 4; i <= 13; i++)
nulls[i] = true;
}
/* Build and return the result tuple. */
resultTuple = heap_form_tuple(inter_call_data->tupd, values, nulls);
result = HeapTupleGetDatum(resultTuple);
inter_call_data->offset++;
SRF_RETURN_NEXT(fctx, result);
}
else
SRF_RETURN_DONE(fctx);
}
/*
* tuple_data_split_internal
*
* Split raw tuple data taken directly from a page into an array of bytea
* elements. This routine does a lookup on NULL values and creates array
* elements accordingly. This is a reimplementation of nocachegetattr()
* in heaptuple.c simplified for educational purposes.
*/
static Datum
tuple_data_split_internal(Oid relid, char *tupdata,
uint16 tupdata_len, uint16 t_infomask,
uint16 t_infomask2, bits8 *t_bits,
bool do_detoast)
{
ArrayBuildState *raw_attrs;
int nattrs;
int i;
int off = 0;
Relation rel;
TupleDesc tupdesc;
/* Get tuple descriptor from relation OID */
rel = relation_open(relid, AccessShareLock);
tupdesc = RelationGetDescr(rel);
raw_attrs = initArrayResult(BYTEAOID, CurrentMemoryContext, false);
nattrs = tupdesc->natts;
if (nattrs < (t_infomask2 & HEAP_NATTS_MASK))
ereport(ERROR,
(errcode(ERRCODE_DATA_CORRUPTED),
errmsg("number of attributes in tuple header is greater than number of attributes in tuple descriptor")));
for (i = 0; i < nattrs; i++)
{
Form_pg_attribute attr;
bool is_null;
bytea *attr_data = NULL;
attr = TupleDescAttr(tupdesc, i);
/*
* Tuple header can specify less attributes than tuple descriptor as
* ALTER TABLE ADD COLUMN without DEFAULT keyword does not actually
* change tuples in pages, so attributes with numbers greater than
* (t_infomask2 & HEAP_NATTS_MASK) should be treated as NULL.
*/
if (i >= (t_infomask2 & HEAP_NATTS_MASK))
is_null = true;
else
is_null = (t_infomask & HEAP_HASNULL) && att_isnull(i, t_bits);
if (!is_null)
{
int len;
if (attr->attlen == -1)
{
off = att_align_pointer(off, attr->attalign, -1,
tupdata + off);
/*
* As VARSIZE_ANY throws an exception if it can't properly
* detect the type of external storage in macros VARTAG_SIZE,
* this check is repeated to have a nicer error handling.
*/
if (VARATT_IS_EXTERNAL(tupdata + off) &&
!VARATT_IS_EXTERNAL_ONDISK(tupdata + off) &&
!VARATT_IS_EXTERNAL_INDIRECT(tupdata + off))
ereport(ERROR,
(errcode(ERRCODE_DATA_CORRUPTED),
errmsg("first byte of varlena attribute is incorrect for attribute %d", i)));
len = VARSIZE_ANY(tupdata + off);
}
else
{
off = att_align_nominal(off, attr->attalign);
len = attr->attlen;
}
if (tupdata_len < off + len)
ereport(ERROR,
(errcode(ERRCODE_DATA_CORRUPTED),
errmsg("unexpected end of tuple data")));
if (attr->attlen == -1 && do_detoast)
attr_data = DatumGetByteaPCopy(tupdata + off);
else
{
attr_data = (bytea *) palloc(len + VARHDRSZ);
SET_VARSIZE(attr_data, len + VARHDRSZ);
memcpy(VARDATA(attr_data), tupdata + off, len);
}
off = att_addlength_pointer(off, attr->attlen,
tupdata + off);
}
raw_attrs = accumArrayResult(raw_attrs, PointerGetDatum(attr_data),
is_null, BYTEAOID, CurrentMemoryContext);
if (attr_data)
pfree(attr_data);
}
if (tupdata_len != off)
ereport(ERROR,
(errcode(ERRCODE_DATA_CORRUPTED),
errmsg("end of tuple reached without looking at all its data")));
relation_close(rel, AccessShareLock);
return makeArrayResult(raw_attrs, CurrentMemoryContext);
}
/*
* tuple_data_split
*
* Split raw tuple data taken directly from page into distinct elements
* taking into account null values.
*/
PG_FUNCTION_INFO_V1(tuple_data_split);
Datum
tuple_data_split(PG_FUNCTION_ARGS)
{
Oid relid;
bytea *raw_data;
uint16 t_infomask;
uint16 t_infomask2;
char *t_bits_str;
bool do_detoast = false;
bits8 *t_bits = NULL;
Datum res;
relid = PG_GETARG_OID(0);
raw_data = PG_ARGISNULL(1) ? NULL : PG_GETARG_BYTEA_P(1);
t_infomask = PG_GETARG_INT16(2);
t_infomask2 = PG_GETARG_INT16(3);
t_bits_str = PG_ARGISNULL(4) ? NULL :
text_to_cstring(PG_GETARG_TEXT_PP(4));
if (PG_NARGS() >= 6)
do_detoast = PG_GETARG_BOOL(5);
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("must be superuser to use raw page functions")));
if (!raw_data)
PG_RETURN_NULL();
/*
* Convert t_bits string back to the bits8 array as represented in the
* tuple header.
*/
if (t_infomask & HEAP_HASNULL)
{
int bits_str_len;
int bits_len;
bits_len = BITMAPLEN(t_infomask2 & HEAP_NATTS_MASK) * BITS_PER_BYTE;
if (!t_bits_str)
ereport(ERROR,
(errcode(ERRCODE_DATA_CORRUPTED),
errmsg("argument of t_bits is null, but it is expected to be null and %d character long",
bits_len)));
bits_str_len = strlen(t_bits_str);
if (bits_len != bits_str_len)
ereport(ERROR,
(errcode(ERRCODE_DATA_CORRUPTED),
errmsg("unexpected length of t_bits %u, expected %d",
bits_str_len, bits_len)));
/* do the conversion */
t_bits = text_to_bits(t_bits_str, bits_str_len);
}
else
{
if (t_bits_str)
ereport(ERROR,
(errcode(ERRCODE_DATA_CORRUPTED),
errmsg("t_bits string is expected to be NULL, but instead it is %zu bytes length",
strlen(t_bits_str))));
}
/* Split tuple data */
res = tuple_data_split_internal(relid, (char *) raw_data + VARHDRSZ,
VARSIZE(raw_data) - VARHDRSZ,
t_infomask, t_infomask2, t_bits,
do_detoast);
if (t_bits)
pfree(t_bits);
PG_RETURN_ARRAYTYPE_P(res);
}
|