| 1 |
// SPDX-License-Identifier: GPL-2.0 |
| 2 |
#include <linux/fs.h> |
| 3 |
#include <linux/random.h> |
| 4 |
#include <linux/buffer_head.h> |
| 5 |
#include <linux/utsname.h> |
| 6 |
#include <linux/kthread.h> |
| 7 |
|
| 8 |
#include "ext4.h" |
| 9 |
|
| 10 |
/* Checksumming functions */ |
| 11 |
static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp) |
| 12 |
{ |
| 13 |
struct ext4_sb_info *sbi = EXT4_SB(sb); |
| 14 |
int offset = offsetof(struct mmp_struct, mmp_checksum); |
| 15 |
__u32 csum; |
| 16 |
|
| 17 |
csum = ext4_chksum(sbi->s_csum_seed, (char *)mmp, offset); |
| 18 |
|
| 19 |
return cpu_to_le32(csum); |
| 20 |
} |
| 21 |
|
| 22 |
static int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp) |
| 23 |
{ |
| 24 |
if (!ext4_has_feature_metadata_csum(sb)) |
| 25 |
return 1; |
| 26 |
|
| 27 |
return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp); |
| 28 |
} |
| 29 |
|
| 30 |
static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp) |
| 31 |
{ |
| 32 |
if (!ext4_has_feature_metadata_csum(sb)) |
| 33 |
return; |
| 34 |
|
| 35 |
mmp->mmp_checksum = ext4_mmp_csum(sb, mmp); |
| 36 |
} |
| 37 |
|
| 38 |
/* |
| 39 |
* Write the MMP block using REQ_SYNC to try to get the block on-disk |
| 40 |
* faster. |
| 41 |
*/ |
| 42 |
static int write_mmp_block_thawed(struct super_block *sb, |
| 43 |
struct buffer_head *bh) |
| 44 |
{ |
| 45 |
struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data); |
| 46 |
|
| 47 |
ext4_mmp_csum_set(sb, mmp); |
| 48 |
lock_buffer(bh); |
| 49 |
bh->b_end_io = end_buffer_write_sync; |
| 50 |
get_bh(bh); |
| 51 |
submit_bh(REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, bh); |
| 52 |
wait_on_buffer(bh); |
| 53 |
if (unlikely(!buffer_uptodate(bh))) |
| 54 |
return -EIO; |
| 55 |
return 0; |
| 56 |
} |
| 57 |
|
| 58 |
static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) |
| 59 |
{ |
| 60 |
/* |
| 61 |
* We protect against freezing so that we don't create dirty buffers |
| 62 |
* on frozen filesystem. |
| 63 |
*/ |
| 64 |
scoped_guard(super_write, sb) |
| 65 |
return write_mmp_block_thawed(sb, bh); |
| 66 |
} |
| 67 |
|
| 68 |
/* |
| 69 |
* Read the MMP block. It _must_ be read from disk and hence we clear the |
| 70 |
* uptodate flag on the buffer. |
| 71 |
*/ |
| 72 |
static int read_mmp_block(struct super_block *sb, struct buffer_head **bh, |
| 73 |
ext4_fsblk_t mmp_block) |
| 74 |
{ |
| 75 |
struct mmp_struct *mmp; |
| 76 |
int ret; |
| 77 |
|
| 78 |
if (*bh) |
| 79 |
clear_buffer_uptodate(*bh); |
| 80 |
|
| 81 |
/* This would be sb_bread(sb, mmp_block), except we need to be sure |
| 82 |
* that the MD RAID device cache has been bypassed, and that the read |
| 83 |
* is not blocked in the elevator. */ |
| 84 |
if (!*bh) { |
| 85 |
*bh = sb_getblk(sb, mmp_block); |
| 86 |
if (!*bh) { |
| 87 |
ret = -ENOMEM; |
| 88 |
goto warn_exit; |
| 89 |
} |
| 90 |
} |
| 91 |
|
| 92 |
lock_buffer(*bh); |
| 93 |
ret = ext4_read_bh(*bh, REQ_META | REQ_PRIO, NULL, false); |
| 94 |
if (ret) |
| 95 |
goto warn_exit; |
| 96 |
|
| 97 |
mmp = (struct mmp_struct *)((*bh)->b_data); |
| 98 |
if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC) { |
| 99 |
ret = -EFSCORRUPTED; |
| 100 |
goto warn_exit; |
| 101 |
} |
| 102 |
if (!ext4_mmp_csum_verify(sb, mmp)) { |
| 103 |
ret = -EFSBADCRC; |
| 104 |
goto warn_exit; |
| 105 |
} |
| 106 |
return 0; |
| 107 |
warn_exit: |
| 108 |
brelse(*bh); |
| 109 |
*bh = NULL; |
| 110 |
ext4_warning(sb, "Error %d while reading MMP block %llu", |
| 111 |
ret, mmp_block); |
| 112 |
return ret; |
| 113 |
} |
| 114 |
|
| 115 |
/* |
| 116 |
* Dump as much information as possible to help the admin. |
| 117 |
*/ |
| 118 |
void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp, |
| 119 |
const char *function, unsigned int line, const char *msg) |
| 120 |
{ |
| 121 |
__ext4_warning(sb, function, line, "%s", msg); |
| 122 |
__ext4_warning(sb, function, line, |
| 123 |
"MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s", |
| 124 |
(unsigned long long)le64_to_cpu(mmp->mmp_time), |
| 125 |
(int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename, |
| 126 |
(int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname); |
| 127 |
} |
| 128 |
|
| 129 |
/* |
| 130 |
* kmmpd will update the MMP sequence every s_mmp_update_interval seconds |
| 131 |
*/ |
| 132 |
static int kmmpd(void *data) |
| 133 |
{ |
| 134 |
struct super_block *sb = data; |
| 135 |
struct ext4_super_block *es = EXT4_SB(sb)->s_es; |
| 136 |
struct buffer_head *bh = EXT4_SB(sb)->s_mmp_bh; |
| 137 |
struct mmp_struct *mmp; |
| 138 |
ext4_fsblk_t mmp_block; |
| 139 |
u32 seq = 0; |
| 140 |
unsigned long failed_writes = 0; |
| 141 |
int mmp_update_interval = le16_to_cpu(es->s_mmp_update_interval); |
| 142 |
unsigned mmp_check_interval; |
| 143 |
unsigned long last_update_time; |
| 144 |
unsigned long diff; |
| 145 |
int retval = 0; |
| 146 |
|
| 147 |
mmp_block = le64_to_cpu(es->s_mmp_block); |
| 148 |
mmp = (struct mmp_struct *)(bh->b_data); |
| 149 |
mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds()); |
| 150 |
/* |
| 151 |
* Start with the higher mmp_check_interval and reduce it if |
| 152 |
* the MMP block is being updated on time. |
| 153 |
*/ |
| 154 |
mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval, |
| 155 |
EXT4_MMP_MIN_CHECK_INTERVAL); |
| 156 |
mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval); |
| 157 |
|
| 158 |
memcpy(mmp->mmp_nodename, init_utsname()->nodename, |
| 159 |
sizeof(mmp->mmp_nodename)); |
| 160 |
|
| 161 |
while (!kthread_should_stop() && !ext4_emergency_state(sb)) { |
| 162 |
if (!ext4_has_feature_mmp(sb)) { |
| 163 |
ext4_warning(sb, "kmmpd being stopped since MMP feature" |
| 164 |
" has been disabled."); |
| 165 |
goto wait_to_exit; |
| 166 |
} |
| 167 |
if (++seq > EXT4_MMP_SEQ_MAX) |
| 168 |
seq = 1; |
| 169 |
|
| 170 |
mmp->mmp_seq = cpu_to_le32(seq); |
| 171 |
mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds()); |
| 172 |
last_update_time = jiffies; |
| 173 |
|
| 174 |
retval = write_mmp_block(sb, bh); |
| 175 |
/* |
| 176 |
* Don't spew too many error messages. Print one every |
| 177 |
* (s_mmp_update_interval * 60) seconds. |
| 178 |
*/ |
| 179 |
if (retval) { |
| 180 |
if ((failed_writes % 60) == 0) { |
| 181 |
ext4_error_err(sb, -retval, |
| 182 |
"Error writing to MMP block"); |
| 183 |
} |
| 184 |
failed_writes++; |
| 185 |
} |
| 186 |
|
| 187 |
diff = jiffies - last_update_time; |
| 188 |
if (diff < mmp_update_interval * HZ) |
| 189 |
schedule_timeout_interruptible(mmp_update_interval * |
| 190 |
HZ - diff); |
| 191 |
|
| 192 |
/* |
| 193 |
* We need to make sure that more than mmp_check_interval |
| 194 |
* seconds have not passed since writing. If that has happened |
| 195 |
* we need to check if the MMP block is as we left it. |
| 196 |
*/ |
| 197 |
diff = jiffies - last_update_time; |
| 198 |
if (diff > mmp_check_interval * HZ) { |
| 199 |
struct buffer_head *bh_check = NULL; |
| 200 |
struct mmp_struct *mmp_check; |
| 201 |
|
| 202 |
retval = read_mmp_block(sb, &bh_check, mmp_block); |
| 203 |
if (retval) { |
| 204 |
ext4_error_err(sb, -retval, |
| 205 |
"error reading MMP data: %d", |
| 206 |
retval); |
| 207 |
goto wait_to_exit; |
| 208 |
} |
| 209 |
|
| 210 |
mmp_check = (struct mmp_struct *)(bh_check->b_data); |
| 211 |
if (mmp->mmp_seq != mmp_check->mmp_seq || |
| 212 |
memcmp(mmp->mmp_nodename, mmp_check->mmp_nodename, |
| 213 |
sizeof(mmp->mmp_nodename))) { |
| 214 |
dump_mmp_msg(sb, mmp_check, |
| 215 |
"Error while updating MMP info. " |
| 216 |
"The filesystem seems to have been" |
| 217 |
" multiply mounted."); |
| 218 |
ext4_error_err(sb, EBUSY, "abort"); |
| 219 |
put_bh(bh_check); |
| 220 |
retval = -EBUSY; |
| 221 |
goto wait_to_exit; |
| 222 |
} |
| 223 |
put_bh(bh_check); |
| 224 |
} |
| 225 |
|
| 226 |
/* |
| 227 |
* Adjust the mmp_check_interval depending on how much time |
| 228 |
* it took for the MMP block to be written. |
| 229 |
*/ |
| 230 |
mmp_check_interval = clamp(EXT4_MMP_CHECK_MULT * diff / HZ, |
| 231 |
EXT4_MMP_MIN_CHECK_INTERVAL, |
| 232 |
EXT4_MMP_MAX_CHECK_INTERVAL); |
| 233 |
mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval); |
| 234 |
} |
| 235 |
|
| 236 |
/* |
| 237 |
* Unmount seems to be clean. |
| 238 |
*/ |
| 239 |
mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN); |
| 240 |
mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds()); |
| 241 |
|
| 242 |
retval = write_mmp_block(sb, bh); |
| 243 |
|
| 244 |
wait_to_exit: |
| 245 |
while (!kthread_should_stop()) { |
| 246 |
set_current_state(TASK_INTERRUPTIBLE); |
| 247 |
if (!kthread_should_stop()) |
| 248 |
schedule(); |
| 249 |
} |
| 250 |
set_current_state(TASK_RUNNING); |
| 251 |
return retval; |
| 252 |
} |
| 253 |
|
| 254 |
void ext4_stop_mmpd(struct ext4_sb_info *sbi) |
| 255 |
{ |
| 256 |
if (sbi->s_mmp_tsk) { |
| 257 |
kthread_stop(sbi->s_mmp_tsk); |
| 258 |
brelse(sbi->s_mmp_bh); |
| 259 |
sbi->s_mmp_tsk = NULL; |
| 260 |
} |
| 261 |
} |
| 262 |
|
| 263 |
/* |
| 264 |
* Get a random new sequence number but make sure it is not greater than |
| 265 |
* EXT4_MMP_SEQ_MAX. |
| 266 |
*/ |
| 267 |
static unsigned int mmp_new_seq(void) |
| 268 |
{ |
| 269 |
return get_random_u32_below(EXT4_MMP_SEQ_MAX + 1); |
| 270 |
} |
| 271 |
|
| 272 |
/* |
| 273 |
* Protect the filesystem from being mounted more than once. |
| 274 |
*/ |
| 275 |
int ext4_multi_mount_protect(struct super_block *sb, |
| 276 |
ext4_fsblk_t mmp_block) |
| 277 |
{ |
| 278 |
struct ext4_super_block *es = EXT4_SB(sb)->s_es; |
| 279 |
struct buffer_head *bh = NULL; |
| 280 |
struct mmp_struct *mmp = NULL; |
| 281 |
u32 seq; |
| 282 |
unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval); |
| 283 |
unsigned int wait_time = 0; |
| 284 |
int retval; |
| 285 |
|
| 286 |
if (mmp_block < le32_to_cpu(es->s_first_data_block) || |
| 287 |
mmp_block >= ext4_blocks_count(es)) { |
| 288 |
ext4_warning(sb, "Invalid MMP block in superblock"); |
| 289 |
retval = -EINVAL; |
| 290 |
goto failed; |
| 291 |
} |
| 292 |
|
| 293 |
retval = read_mmp_block(sb, &bh, mmp_block); |
| 294 |
if (retval) |
| 295 |
goto failed; |
| 296 |
|
| 297 |
mmp = (struct mmp_struct *)(bh->b_data); |
| 298 |
|
| 299 |
if (mmp_check_interval < EXT4_MMP_MIN_CHECK_INTERVAL) |
| 300 |
mmp_check_interval = EXT4_MMP_MIN_CHECK_INTERVAL; |
| 301 |
|
| 302 |
/* |
| 303 |
* If check_interval in MMP block is larger, use that instead of |
| 304 |
* update_interval from the superblock. |
| 305 |
*/ |
| 306 |
if (le16_to_cpu(mmp->mmp_check_interval) > mmp_check_interval) |
| 307 |
mmp_check_interval = le16_to_cpu(mmp->mmp_check_interval); |
| 308 |
|
| 309 |
seq = le32_to_cpu(mmp->mmp_seq); |
| 310 |
if (seq == EXT4_MMP_SEQ_CLEAN) |
| 311 |
goto skip; |
| 312 |
|
| 313 |
if (seq == EXT4_MMP_SEQ_FSCK) { |
| 314 |
dump_mmp_msg(sb, mmp, "fsck is running on the filesystem"); |
| 315 |
retval = -EBUSY; |
| 316 |
goto failed; |
| 317 |
} |
| 318 |
|
| 319 |
wait_time = min(mmp_check_interval * 2 + 1, |
| 320 |
mmp_check_interval + 60); |
| 321 |
|
| 322 |
/* Print MMP interval if more than 20 secs. */ |
| 323 |
if (wait_time > EXT4_MMP_MIN_CHECK_INTERVAL * 4) |
| 324 |
ext4_warning(sb, "MMP interval %u higher than expected, please" |
| 325 |
" wait.\n", wait_time * 2); |
| 326 |
|
| 327 |
if (schedule_timeout_interruptible(HZ * wait_time) != 0) { |
| 328 |
ext4_warning(sb, "MMP startup interrupted, failing mount\n"); |
| 329 |
retval = -ETIMEDOUT; |
| 330 |
goto failed; |
| 331 |
} |
| 332 |
|
| 333 |
retval = read_mmp_block(sb, &bh, mmp_block); |
| 334 |
if (retval) |
| 335 |
goto failed; |
| 336 |
mmp = (struct mmp_struct *)(bh->b_data); |
| 337 |
if (seq != le32_to_cpu(mmp->mmp_seq)) { |
| 338 |
dump_mmp_msg(sb, mmp, |
| 339 |
"Device is already active on another node."); |
| 340 |
retval = -EBUSY; |
| 341 |
goto failed; |
| 342 |
} |
| 343 |
|
| 344 |
skip: |
| 345 |
/* |
| 346 |
* write a new random sequence number. |
| 347 |
*/ |
| 348 |
seq = mmp_new_seq(); |
| 349 |
mmp->mmp_seq = cpu_to_le32(seq); |
| 350 |
|
| 351 |
/* |
| 352 |
* On mount / remount we are protected against fs freezing (by s_umount |
| 353 |
* semaphore) and grabbing freeze protection upsets lockdep |
| 354 |
*/ |
| 355 |
retval = write_mmp_block_thawed(sb, bh); |
| 356 |
if (retval) |
| 357 |
goto failed; |
| 358 |
|
| 359 |
/* |
| 360 |
* wait for MMP interval and check mmp_seq. |
| 361 |
*/ |
| 362 |
if (schedule_timeout_interruptible(HZ * wait_time) != 0) { |
| 363 |
ext4_warning(sb, "MMP startup interrupted, failing mount"); |
| 364 |
retval = -ETIMEDOUT; |
| 365 |
goto failed; |
| 366 |
} |
| 367 |
|
| 368 |
retval = read_mmp_block(sb, &bh, mmp_block); |
| 369 |
if (retval) |
| 370 |
goto failed; |
| 371 |
mmp = (struct mmp_struct *)(bh->b_data); |
| 372 |
if (seq != le32_to_cpu(mmp->mmp_seq)) { |
| 373 |
dump_mmp_msg(sb, mmp, |
| 374 |
"Device is already active on another node."); |
| 375 |
retval = -EBUSY; |
| 376 |
goto failed; |
| 377 |
} |
| 378 |
|
| 379 |
EXT4_SB(sb)->s_mmp_bh = bh; |
| 380 |
|
| 381 |
BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE); |
| 382 |
snprintf(mmp->mmp_bdevname, sizeof(mmp->mmp_bdevname), |
| 383 |
"%pg", bh->b_bdev); |
| 384 |
|
| 385 |
/* |
| 386 |
* Start a kernel thread to update the MMP block periodically. |
| 387 |
*/ |
| 388 |
EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, sb, "kmmpd-%.*s", |
| 389 |
(int)sizeof(mmp->mmp_bdevname), |
| 390 |
mmp->mmp_bdevname); |
| 391 |
if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) { |
| 392 |
EXT4_SB(sb)->s_mmp_tsk = NULL; |
| 393 |
ext4_warning(sb, "Unable to create kmmpd thread for %s.", |
| 394 |
sb->s_id); |
| 395 |
retval = -ENOMEM; |
| 396 |
goto failed; |
| 397 |
} |
| 398 |
|
| 399 |
return 0; |
| 400 |
|
| 401 |
failed: |
| 402 |
brelse(bh); |
| 403 |
return retval; |
| 404 |
} |