mirror of
https://github.com/MariaDB/server.git
synced 2025-01-31 02:51:44 +01:00
765a43605a
Problem was that bpage was referenced after it was already freed from LRU. Fixed by adding a new variable encrypted that is passed down to buf_page_check_corrupt() and used in buf_page_get_gen() to stop processing page read. This patch should also address following test failures and bugs: MDEV-12419: IMPORT should not look up tablespace in PageConverter::validate(). This is now removed. MDEV-10099: encryption.innodb_onlinealter_encryption fails sporadically in buildbot MDEV-11420: encryption.innodb_encryption-page-compression failed in buildbot MDEV-11222: encryption.encrypt_and_grep failed in buildbot on P8 Removed dict_table_t::is_encrypted and dict_table_t::ibd_file_missing and replaced these with dict_table_t::file_unreadable. Table ibd file is missing if fil_get_space(space_id) returns NULL and encrypted if not. Removed dict_table_t::is_corrupted field. Ported FilSpace class from 10.2 and using that on buf_page_check_corrupt(), buf_page_decrypt_after_read(), buf_page_encrypt_before_write(), buf_dblwr_process(), buf_read_page(), dict_stats_save_defrag_stats(). Added test cases when enrypted page could be read while doing redo log crash recovery. Also added test case for row compressed blobs. btr_cur_open_at_index_side_func(), btr_cur_open_at_rnd_pos_func(): Avoid referencing block that is NULL. buf_page_get_zip(): Issue error if page read fails. buf_page_get_gen(): Use dberr_t for error detection and do not reference bpage after we hare freed it. buf_mark_space_corrupt(): remove bpage from LRU also when it is encrypted. buf_page_check_corrupt(): @return DB_SUCCESS if page has been read and is not corrupted, DB_PAGE_CORRUPTED if page based on checksum check is corrupted, DB_DECRYPTION_FAILED if page post encryption checksum matches but after decryption normal page checksum does not match. In read case only DB_SUCCESS is possible. buf_page_io_complete(): use dberr_t for error handling. buf_flush_write_block_low(), buf_read_ahead_random(), buf_read_page_async(), buf_read_ahead_linear(), buf_read_ibuf_merge_pages(), buf_read_recv_pages(), fil_aio_wait(): Issue error if page read fails. btr_pcur_move_to_next_page(): Do not reference page if it is NULL. Introduced dict_table_t::is_readable() and dict_index_t::is_readable() that will return true if tablespace exists and pages read from tablespace are not corrupted or page decryption failed. Removed buf_page_t::key_version. After page decryption the key version is not removed from page frame. For unencrypted pages, old key_version is removed at buf_page_encrypt_before_write() dict_stats_update_transient_for_index(), dict_stats_update_transient() Do not continue if table decryption failed or table is corrupted. dict0stats.cc: Introduced a dict_stats_report_error function to avoid code duplication. fil_parse_write_crypt_data(): Check that key read from redo log entry is found from encryption plugin and if it is not, refuse to start. PageConverter::validate(): Removed access to fil_space_t as tablespace is not available during import. Fixed error code on innodb.innodb test. Merged test cased innodb-bad-key-change5 and innodb-bad-key-shutdown to innodb-bad-key-change2. Removed innodb-bad-key-change5 test. Decreased unnecessary complexity on some long lasting tests. Removed fil_inc_pending_ops(), fil_decr_pending_ops(), fil_get_first_space(), fil_get_next_space(), fil_get_first_space_safe(), fil_get_next_space_safe() functions. fil_space_verify_crypt_checksum(): Fixed bug found using ASAN where FIL_PAGE_END_LSN_OLD_CHECKSUM field was incorrectly accessed from row compressed tables. Fixed out of page frame bug for row compressed tables in fil_space_verify_crypt_checksum() found using ASAN. Incorrect function was called for compressed table. Added new tests for discard, rename table and drop (we should allow them even when page decryption fails). Alter table rename is not allowed. Added test for restart with innodb-force-recovery=1 when page read on redo-recovery cant be decrypted. Added test for corrupted table where both page data and FIL_PAGE_FILE_FLUSH_LSN_OR_KEY_VERSION is corrupted. Adjusted the test case innodb_bug14147491 so that it does not anymore expect crash. Instead table is just mostly not usable. fil0fil.h: fil_space_acquire_low is not visible function and fil_space_acquire and fil_space_acquire_silent are inline functions. FilSpace class uses fil_space_acquire_low directly. recv_apply_hashed_log_recs() does not return anything.
335 lines
9.2 KiB
Text
335 lines
9.2 KiB
Text
/*****************************************************************************
|
|
|
|
Copyright (c) 1994, 2016, Oracle and/or its affiliates. All Rights Reserved.
|
|
Copyright (c) 2015, 2016, MariaDB Corporation.
|
|
|
|
This program is free software; you can redistribute it and/or modify it under
|
|
the terms of the GNU General Public License as published by the Free Software
|
|
Foundation; version 2 of the License.
|
|
|
|
This program is distributed in the hope that it will be useful, but WITHOUT
|
|
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
|
|
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
|
|
|
|
You should have received a copy of the GNU General Public License along with
|
|
this program; if not, write to the Free Software Foundation, Inc.,
|
|
51 Franklin Street, Suite 500, Boston, MA 02110-1335 USA
|
|
|
|
*****************************************************************************/
|
|
|
|
/**************************************************//**
|
|
@file include/btr0btr.ic
|
|
The B-tree
|
|
|
|
Created 6/2/1994 Heikki Tuuri
|
|
*******************************************************/
|
|
|
|
#include "mach0data.h"
|
|
#ifndef UNIV_HOTBACKUP
|
|
#include "mtr0mtr.h"
|
|
#include "mtr0log.h"
|
|
#include "page0zip.h"
|
|
|
|
#define BTR_MAX_NODE_LEVEL 50 /*!< Maximum B-tree page level
|
|
(not really a hard limit).
|
|
Used in debug assertions
|
|
in btr_page_set_level and
|
|
btr_page_get_level_low */
|
|
|
|
/**************************************************************//**
|
|
Gets a buffer page and declares its latching order level. */
|
|
UNIV_INLINE
|
|
buf_block_t*
|
|
btr_block_get_func(
|
|
/*===============*/
|
|
ulint space, /*!< in: space id */
|
|
ulint zip_size, /*!< in: compressed page size in bytes
|
|
or 0 for uncompressed pages */
|
|
ulint page_no, /*!< in: page number */
|
|
ulint mode, /*!< in: latch mode */
|
|
const char* file, /*!< in: file name */
|
|
ulint line, /*!< in: line where called */
|
|
dict_index_t* index, /*!< in: index tree, may be NULL
|
|
if it is not an insert buffer tree */
|
|
mtr_t* mtr) /*!< in/out: mtr */
|
|
{
|
|
buf_block_t* block;
|
|
dberr_t err;
|
|
|
|
block = buf_page_get_gen(space, zip_size, page_no, mode,
|
|
NULL, BUF_GET, file, line, mtr, &err);
|
|
|
|
if (err == DB_DECRYPTION_FAILED) {
|
|
if (index && index->table) {
|
|
index->table->file_unreadable = true;
|
|
}
|
|
}
|
|
|
|
if (block) {
|
|
if (mode != RW_NO_LATCH) {
|
|
|
|
buf_block_dbg_add_level(
|
|
block, index != NULL && dict_index_is_ibuf(index)
|
|
? SYNC_IBUF_TREE_NODE : SYNC_TREE_NODE);
|
|
}
|
|
}
|
|
|
|
return(block);
|
|
}
|
|
|
|
/**************************************************************//**
|
|
Sets the index id field of a page. */
|
|
UNIV_INLINE
|
|
void
|
|
btr_page_set_index_id(
|
|
/*==================*/
|
|
page_t* page, /*!< in: page to be created */
|
|
page_zip_des_t* page_zip,/*!< in: compressed page whose uncompressed
|
|
part will be updated, or NULL */
|
|
index_id_t id, /*!< in: index id */
|
|
mtr_t* mtr) /*!< in: mtr */
|
|
{
|
|
if (page_zip) {
|
|
mach_write_to_8(page + (PAGE_HEADER + PAGE_INDEX_ID), id);
|
|
page_zip_write_header(page_zip,
|
|
page + (PAGE_HEADER + PAGE_INDEX_ID),
|
|
8, mtr);
|
|
} else {
|
|
mlog_write_ull(page + (PAGE_HEADER + PAGE_INDEX_ID), id, mtr);
|
|
}
|
|
}
|
|
|
|
/** Gets a buffer page and declares its latching order level.
|
|
@param space tablespace identifier
|
|
@param zip_size compressed page size in bytes or 0 for uncompressed pages
|
|
@param page_no page number
|
|
@param mode latch mode
|
|
@param idx index tree, may be NULL if not the insert buffer tree
|
|
@param mtr mini-transaction handle
|
|
@return the uncompressed page frame */
|
|
UNIV_INLINE
|
|
page_t*
|
|
btr_page_get(
|
|
/*=========*/
|
|
ulint space,
|
|
ulint zip_size,
|
|
ulint root_page_no,
|
|
ulint mode,
|
|
dict_index_t* index,
|
|
mtr_t* mtr)
|
|
{
|
|
buf_block_t* block=NULL;
|
|
buf_frame_t* frame=NULL;
|
|
|
|
block = btr_block_get(space, zip_size, root_page_no, mode, index, mtr);
|
|
|
|
if (block) {
|
|
frame = buf_block_get_frame(block);
|
|
}
|
|
|
|
return ((page_t*)frame);
|
|
}
|
|
|
|
#endif /* !UNIV_HOTBACKUP */
|
|
|
|
/**************************************************************//**
|
|
Gets the index id field of a page.
|
|
@return index id */
|
|
UNIV_INLINE
|
|
index_id_t
|
|
btr_page_get_index_id(
|
|
/*==================*/
|
|
const page_t* page) /*!< in: index page */
|
|
{
|
|
return(mach_read_from_8(page + PAGE_HEADER + PAGE_INDEX_ID));
|
|
}
|
|
|
|
#ifndef UNIV_HOTBACKUP
|
|
/********************************************************//**
|
|
Gets the node level field in an index page.
|
|
@return level, leaf level == 0 */
|
|
UNIV_INLINE
|
|
ulint
|
|
btr_page_get_level_low(
|
|
/*===================*/
|
|
const page_t* page) /*!< in: index page */
|
|
{
|
|
ulint level;
|
|
|
|
ut_ad(page);
|
|
|
|
level = mach_read_from_2(page + PAGE_HEADER + PAGE_LEVEL);
|
|
|
|
ut_ad(level <= BTR_MAX_NODE_LEVEL);
|
|
|
|
return(level);
|
|
}
|
|
|
|
/********************************************************//**
|
|
Sets the node level field in an index page. */
|
|
UNIV_INLINE
|
|
void
|
|
btr_page_set_level(
|
|
/*===============*/
|
|
page_t* page, /*!< in: index page */
|
|
page_zip_des_t* page_zip,/*!< in: compressed page whose uncompressed
|
|
part will be updated, or NULL */
|
|
ulint level, /*!< in: level, leaf level == 0 */
|
|
mtr_t* mtr) /*!< in: mini-transaction handle */
|
|
{
|
|
ut_ad(page && mtr);
|
|
ut_ad(level <= BTR_MAX_NODE_LEVEL);
|
|
|
|
if (page_zip) {
|
|
mach_write_to_2(page + (PAGE_HEADER + PAGE_LEVEL), level);
|
|
page_zip_write_header(page_zip,
|
|
page + (PAGE_HEADER + PAGE_LEVEL),
|
|
2, mtr);
|
|
} else {
|
|
mlog_write_ulint(page + (PAGE_HEADER + PAGE_LEVEL), level,
|
|
MLOG_2BYTES, mtr);
|
|
}
|
|
}
|
|
|
|
/********************************************************//**
|
|
Gets the next index page number.
|
|
@return next page number */
|
|
UNIV_INLINE
|
|
ulint
|
|
btr_page_get_next(
|
|
/*==============*/
|
|
const page_t* page, /*!< in: index page */
|
|
mtr_t* mtr MY_ATTRIBUTE((unused)))
|
|
/*!< in: mini-transaction handle */
|
|
{
|
|
ut_ad(page != NULL);
|
|
ut_ad(mtr != NULL);
|
|
#ifndef UNIV_INNOCHECKSUM
|
|
ut_ad(mtr_memo_contains_page(mtr, page, MTR_MEMO_PAGE_X_FIX)
|
|
|| mtr_memo_contains_page(mtr, page, MTR_MEMO_PAGE_S_FIX));
|
|
#endif /* UNIV_INNOCHECKSUM */
|
|
return(mach_read_from_4(page + FIL_PAGE_NEXT));
|
|
}
|
|
|
|
/********************************************************//**
|
|
Sets the next index page field. */
|
|
UNIV_INLINE
|
|
void
|
|
btr_page_set_next(
|
|
/*==============*/
|
|
page_t* page, /*!< in: index page */
|
|
page_zip_des_t* page_zip,/*!< in: compressed page whose uncompressed
|
|
part will be updated, or NULL */
|
|
ulint next, /*!< in: next page number */
|
|
mtr_t* mtr) /*!< in: mini-transaction handle */
|
|
{
|
|
ut_ad(page != NULL);
|
|
ut_ad(mtr != NULL);
|
|
|
|
if (page_zip) {
|
|
mach_write_to_4(page + FIL_PAGE_NEXT, next);
|
|
page_zip_write_header(page_zip, page + FIL_PAGE_NEXT, 4, mtr);
|
|
} else {
|
|
mlog_write_ulint(page + FIL_PAGE_NEXT, next, MLOG_4BYTES, mtr);
|
|
}
|
|
}
|
|
|
|
/********************************************************//**
|
|
Gets the previous index page number.
|
|
@return prev page number */
|
|
UNIV_INLINE
|
|
ulint
|
|
btr_page_get_prev(
|
|
/*==============*/
|
|
const page_t* page, /*!< in: index page */
|
|
mtr_t* mtr MY_ATTRIBUTE((unused))) /*!< in: mini-transaction handle */
|
|
{
|
|
ut_ad(page != NULL);
|
|
ut_ad(mtr != NULL);
|
|
|
|
return(mach_read_from_4(page + FIL_PAGE_PREV));
|
|
}
|
|
|
|
/********************************************************//**
|
|
Sets the previous index page field. */
|
|
UNIV_INLINE
|
|
void
|
|
btr_page_set_prev(
|
|
/*==============*/
|
|
page_t* page, /*!< in: index page */
|
|
page_zip_des_t* page_zip,/*!< in: compressed page whose uncompressed
|
|
part will be updated, or NULL */
|
|
ulint prev, /*!< in: previous page number */
|
|
mtr_t* mtr) /*!< in: mini-transaction handle */
|
|
{
|
|
ut_ad(page != NULL);
|
|
ut_ad(mtr != NULL);
|
|
|
|
if (page_zip) {
|
|
mach_write_to_4(page + FIL_PAGE_PREV, prev);
|
|
page_zip_write_header(page_zip, page + FIL_PAGE_PREV, 4, mtr);
|
|
} else {
|
|
mlog_write_ulint(page + FIL_PAGE_PREV, prev, MLOG_4BYTES, mtr);
|
|
}
|
|
}
|
|
|
|
/**************************************************************//**
|
|
Gets the child node file address in a node pointer.
|
|
NOTE: the offsets array must contain all offsets for the record since
|
|
we read the last field according to offsets and assume that it contains
|
|
the child page number. In other words offsets must have been retrieved
|
|
with rec_get_offsets(n_fields=ULINT_UNDEFINED).
|
|
@return child node address */
|
|
UNIV_INLINE
|
|
ulint
|
|
btr_node_ptr_get_child_page_no(
|
|
/*===========================*/
|
|
const rec_t* rec, /*!< in: node pointer record */
|
|
const ulint* offsets)/*!< in: array returned by rec_get_offsets() */
|
|
{
|
|
const byte* field;
|
|
ulint len;
|
|
ulint page_no;
|
|
|
|
ut_ad(!rec_offs_comp(offsets) || rec_get_node_ptr_flag(rec));
|
|
|
|
/* The child address is in the last field */
|
|
field = rec_get_nth_field(rec, offsets,
|
|
rec_offs_n_fields(offsets) - 1, &len);
|
|
|
|
ut_ad(len == 4);
|
|
|
|
page_no = mach_read_from_4(field);
|
|
|
|
if (page_no == 0) {
|
|
fprintf(stderr,
|
|
"InnoDB: a nonsensical page number 0"
|
|
" in a node ptr record at offset %lu\n",
|
|
(ulong) page_offset(rec));
|
|
buf_page_print(page_align(rec), 0, 0);
|
|
ut_ad(0);
|
|
}
|
|
|
|
return(page_no);
|
|
}
|
|
|
|
/**************************************************************//**
|
|
Releases the latches on a leaf page and bufferunfixes it. */
|
|
UNIV_INLINE
|
|
void
|
|
btr_leaf_page_release(
|
|
/*==================*/
|
|
buf_block_t* block, /*!< in: buffer block */
|
|
ulint latch_mode, /*!< in: BTR_SEARCH_LEAF or
|
|
BTR_MODIFY_LEAF */
|
|
mtr_t* mtr) /*!< in: mtr */
|
|
{
|
|
ut_ad(latch_mode == BTR_SEARCH_LEAF || latch_mode == BTR_MODIFY_LEAF);
|
|
ut_ad(!mtr_memo_contains(mtr, block, MTR_MEMO_MODIFY));
|
|
|
|
mtr_memo_release(mtr, block,
|
|
latch_mode == BTR_SEARCH_LEAF
|
|
? MTR_MEMO_PAGE_S_FIX
|
|
: MTR_MEMO_PAGE_X_FIX);
|
|
}
|
|
#endif /* !UNIV_HOTBACKUP */
|