Blame view
fs/ext4/mmp.c
10.1 KB
b24413180
|
1 |
// SPDX-License-Identifier: GPL-2.0 |
c5e06d101
|
2 3 4 5 6 7 8 |
#include <linux/fs.h> #include <linux/random.h> #include <linux/buffer_head.h> #include <linux/utsname.h> #include <linux/kthread.h> #include "ext4.h" |
5c359a47e
|
9 |
/* Checksumming functions */ |
171a7f21a
|
10 |
static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp) |
5c359a47e
|
11 12 13 14 15 16 17 18 19 |
{ struct ext4_sb_info *sbi = EXT4_SB(sb); int offset = offsetof(struct mmp_struct, mmp_checksum); __u32 csum; csum = ext4_chksum(sbi, sbi->s_csum_seed, (char *)mmp, offset); return cpu_to_le32(csum); } |
c197855ea
|
20 |
static int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp) |
5c359a47e
|
21 |
{ |
9aa5d32ba
|
22 |
if (!ext4_has_metadata_csum(sb)) |
5c359a47e
|
23 24 25 26 |
return 1; return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp); } |
c197855ea
|
27 |
static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp) |
5c359a47e
|
28 |
{ |
9aa5d32ba
|
29 |
if (!ext4_has_metadata_csum(sb)) |
5c359a47e
|
30 31 32 33 |
return; mmp->mmp_checksum = ext4_mmp_csum(sb, mmp); } |
c5e06d101
|
34 |
/* |
70fd76140
|
35 |
* Write the MMP block using REQ_SYNC to try to get the block on-disk |
c5e06d101
|
36 37 |
* faster. */ |
5c359a47e
|
38 |
static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) |
c5e06d101
|
39 |
{ |
5c359a47e
|
40 |
struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data); |
8e8ad8a57
|
41 42 43 44 45 |
/* * We protect against freezing so that we don't create dirty buffers * on frozen filesystem. */ sb_start_write(sb); |
5c359a47e
|
46 |
ext4_mmp_csum_set(sb, mmp); |
c5e06d101
|
47 48 49 |
lock_buffer(bh); bh->b_end_io = end_buffer_write_sync; get_bh(bh); |
70fd76140
|
50 |
submit_bh(REQ_OP_WRITE, REQ_SYNC | REQ_META | REQ_PRIO, bh); |
c5e06d101
|
51 |
wait_on_buffer(bh); |
8e8ad8a57
|
52 |
sb_end_write(sb); |
c5e06d101
|
53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
if (unlikely(!buffer_uptodate(bh))) return 1; return 0; } /* * Read the MMP block. It _must_ be read from disk and hence we clear the * uptodate flag on the buffer. */ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh, ext4_fsblk_t mmp_block) { struct mmp_struct *mmp; |
981044683
|
67 |
int ret; |
c5e06d101
|
68 69 70 71 72 73 74 |
if (*bh) clear_buffer_uptodate(*bh); /* This would be sb_bread(sb, mmp_block), except we need to be sure * that the MD RAID device cache has been bypassed, and that the read * is not blocked in the elevator. */ |
981044683
|
75 |
if (!*bh) { |
c5e06d101
|
76 |
*bh = sb_getblk(sb, mmp_block); |
981044683
|
77 78 79 |
if (!*bh) { ret = -ENOMEM; goto warn_exit; |
c5e06d101
|
80 81 |
} } |
981044683
|
82 83 84 85 |
get_bh(*bh); lock_buffer(*bh); (*bh)->b_end_io = end_buffer_read_sync; |
70fd76140
|
86 |
submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, *bh); |
981044683
|
87 88 |
wait_on_buffer(*bh); if (!buffer_uptodate(*bh)) { |
981044683
|
89 90 |
ret = -EIO; goto warn_exit; |
c5e06d101
|
91 |
} |
c5e06d101
|
92 |
mmp = (struct mmp_struct *)((*bh)->b_data); |
030468867
|
93 |
if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC) { |
6a797d273
|
94 |
ret = -EFSCORRUPTED; |
030468867
|
95 96 97 |
goto warn_exit; } if (!ext4_mmp_csum_verify(sb, mmp)) { |
6a797d273
|
98 |
ret = -EFSBADCRC; |
030468867
|
99 100 101 |
goto warn_exit; } return 0; |
981044683
|
102 |
warn_exit: |
030468867
|
103 104 |
brelse(*bh); *bh = NULL; |
981044683
|
105 106 107 |
ext4_warning(sb, "Error %d while reading MMP block %llu", ret, mmp_block); return ret; |
c5e06d101
|
108 109 110 111 112 113 114 115 |
} /* * Dump as much information as possible to help the admin. */ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp, const char *function, unsigned int line, const char *msg) { |
da0b5e40a
|
116 |
__ext4_warning(sb, function, line, "%s", msg); |
c5e06d101
|
117 |
__ext4_warning(sb, function, line, |
14c9ca058
|
118 119 120 121 |
"MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s", (unsigned long long)le64_to_cpu(mmp->mmp_time), (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename, (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname); |
c5e06d101
|
122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
} /* * kmmpd will update the MMP sequence every s_mmp_update_interval seconds */ static int kmmpd(void *data) { struct super_block *sb = ((struct mmpd_data *) data)->sb; struct buffer_head *bh = ((struct mmpd_data *) data)->bh; struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct mmp_struct *mmp; ext4_fsblk_t mmp_block; u32 seq = 0; unsigned long failed_writes = 0; int mmp_update_interval = le16_to_cpu(es->s_mmp_update_interval); unsigned mmp_check_interval; unsigned long last_update_time; unsigned long diff; int retval; mmp_block = le64_to_cpu(es->s_mmp_block); mmp = (struct mmp_struct *)(bh->b_data); |
af123b371
|
144 |
mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds()); |
c5e06d101
|
145 146 147 148 149 150 151 |
/* * Start with the higher mmp_check_interval and reduce it if * the MMP block is being updated on time. */ mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval, EXT4_MMP_MIN_CHECK_INTERVAL); mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval); |
14c9ca058
|
152 |
BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE); |
c5e06d101
|
153 |
bdevname(bh->b_bdev, mmp->mmp_bdevname); |
215fc6af7
|
154 |
memcpy(mmp->mmp_nodename, init_utsname()->nodename, |
c5e06d101
|
155 156 157 158 159 160 161 |
sizeof(mmp->mmp_nodename)); while (!kthread_should_stop()) { if (++seq > EXT4_MMP_SEQ_MAX) seq = 1; mmp->mmp_seq = cpu_to_le32(seq); |
af123b371
|
162 |
mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds()); |
c5e06d101
|
163 |
last_update_time = jiffies; |
5c359a47e
|
164 |
retval = write_mmp_block(sb, bh); |
c5e06d101
|
165 166 167 168 |
/* * Don't spew too many error messages. Print one every * (s_mmp_update_interval * 60) seconds. */ |
bdfc230f3
|
169 |
if (retval) { |
878520ac4
|
170 |
if ((failed_writes % 60) == 0) { |
54d3adbc2
|
171 172 |
ext4_error_err(sb, -retval, "Error writing to MMP block"); |
878520ac4
|
173 |
} |
c5e06d101
|
174 175 176 177 178 179 180 |
failed_writes++; } if (!(le32_to_cpu(es->s_feature_incompat) & EXT4_FEATURE_INCOMPAT_MMP)) { ext4_warning(sb, "kmmpd being stopped since MMP feature" " has been disabled."); |
030468867
|
181 |
goto exit_thread; |
c5e06d101
|
182 |
} |
2dca60d98
|
183 184 |
if (sb_rdonly(sb)) break; |
c5e06d101
|
185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 |
diff = jiffies - last_update_time; if (diff < mmp_update_interval * HZ) schedule_timeout_interruptible(mmp_update_interval * HZ - diff); /* * We need to make sure that more than mmp_check_interval * seconds have not passed since writing. If that has happened * we need to check if the MMP block is as we left it. */ diff = jiffies - last_update_time; if (diff > mmp_check_interval * HZ) { struct buffer_head *bh_check = NULL; struct mmp_struct *mmp_check; retval = read_mmp_block(sb, &bh_check, mmp_block); if (retval) { |
54d3adbc2
|
203 204 205 |
ext4_error_err(sb, -retval, "error reading MMP data: %d", retval); |
030468867
|
206 |
goto exit_thread; |
c5e06d101
|
207 208 209 210 211 212 213 214 215 216 |
} mmp_check = (struct mmp_struct *)(bh_check->b_data); if (mmp->mmp_seq != mmp_check->mmp_seq || memcmp(mmp->mmp_nodename, mmp_check->mmp_nodename, sizeof(mmp->mmp_nodename))) { dump_mmp_msg(sb, mmp_check, "Error while updating MMP info. " "The filesystem seems to have been" " multiply mounted."); |
54d3adbc2
|
217 |
ext4_error_err(sb, EBUSY, "abort"); |
030468867
|
218 219 220 |
put_bh(bh_check); retval = -EBUSY; goto exit_thread; |
c5e06d101
|
221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 |
} put_bh(bh_check); } /* * Adjust the mmp_check_interval depending on how much time * it took for the MMP block to be written. */ mmp_check_interval = max(min(EXT4_MMP_CHECK_MULT * diff / HZ, EXT4_MMP_MAX_CHECK_INTERVAL), EXT4_MMP_MIN_CHECK_INTERVAL); mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval); } /* * Unmount seems to be clean. */ mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN); |
af123b371
|
239 |
mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds()); |
c5e06d101
|
240 |
|
5c359a47e
|
241 |
retval = write_mmp_block(sb, bh); |
c5e06d101
|
242 |
|
030468867
|
243 244 |
exit_thread: EXT4_SB(sb)->s_mmp_tsk = NULL; |
c5e06d101
|
245 246 247 248 249 250 251 252 253 254 255 256 257 258 |
kfree(data); brelse(bh); return retval; } /* * Get a random new sequence number but make sure it is not greater than * EXT4_MMP_SEQ_MAX. */ static unsigned int mmp_new_seq(void) { u32 new_seq; do { |
dd1f723bf
|
259 |
new_seq = prandom_u32(); |
c5e06d101
|
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 |
} while (new_seq > EXT4_MMP_SEQ_MAX); return new_seq; } /* * Protect the filesystem from being mounted more than once. */ int ext4_multi_mount_protect(struct super_block *sb, ext4_fsblk_t mmp_block) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct buffer_head *bh = NULL; struct mmp_struct *mmp = NULL; struct mmpd_data *mmpd_data; u32 seq; unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval); unsigned int wait_time = 0; int retval; if (mmp_block < le32_to_cpu(es->s_first_data_block) || mmp_block >= ext4_blocks_count(es)) { ext4_warning(sb, "Invalid MMP block in superblock"); goto failed; } retval = read_mmp_block(sb, &bh, mmp_block); if (retval) goto failed; mmp = (struct mmp_struct *)(bh->b_data); if (mmp_check_interval < EXT4_MMP_MIN_CHECK_INTERVAL) mmp_check_interval = EXT4_MMP_MIN_CHECK_INTERVAL; /* * If check_interval in MMP block is larger, use that instead of * update_interval from the superblock. */ |
85d216501
|
299 300 |
if (le16_to_cpu(mmp->mmp_check_interval) > mmp_check_interval) mmp_check_interval = le16_to_cpu(mmp->mmp_check_interval); |
c5e06d101
|
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 |
seq = le32_to_cpu(mmp->mmp_seq); if (seq == EXT4_MMP_SEQ_CLEAN) goto skip; if (seq == EXT4_MMP_SEQ_FSCK) { dump_mmp_msg(sb, mmp, "fsck is running on the filesystem"); goto failed; } wait_time = min(mmp_check_interval * 2 + 1, mmp_check_interval + 60); /* Print MMP interval if more than 20 secs. */ if (wait_time > EXT4_MMP_MIN_CHECK_INTERVAL * 4) ext4_warning(sb, "MMP interval %u higher than expected, please" " wait. ", wait_time * 2); if (schedule_timeout_interruptible(HZ * wait_time) != 0) { ext4_warning(sb, "MMP startup interrupted, failing mount "); goto failed; } retval = read_mmp_block(sb, &bh, mmp_block); if (retval) goto failed; mmp = (struct mmp_struct *)(bh->b_data); if (seq != le32_to_cpu(mmp->mmp_seq)) { dump_mmp_msg(sb, mmp, "Device is already active on another node."); goto failed; } skip: /* * write a new random sequence number. */ |
f6f96fdb8
|
340 341 |
seq = mmp_new_seq(); mmp->mmp_seq = cpu_to_le32(seq); |
c5e06d101
|
342 |
|
5c359a47e
|
343 |
retval = write_mmp_block(sb, bh); |
c5e06d101
|
344 345 346 347 348 349 350 |
if (retval) goto failed; /* * wait for MMP interval and check mmp_seq. */ if (schedule_timeout_interruptible(HZ * wait_time) != 0) { |
8d2ae1cbe
|
351 |
ext4_warning(sb, "MMP startup interrupted, failing mount"); |
c5e06d101
|
352 353 354 355 356 357 358 359 360 361 362 363 |
goto failed; } retval = read_mmp_block(sb, &bh, mmp_block); if (retval) goto failed; mmp = (struct mmp_struct *)(bh->b_data); if (seq != le32_to_cpu(mmp->mmp_seq)) { dump_mmp_msg(sb, mmp, "Device is already active on another node."); goto failed; } |
d695a1bea
|
364 |
mmpd_data = kmalloc(sizeof(*mmpd_data), GFP_KERNEL); |
c5e06d101
|
365 366 367 368 369 370 371 372 373 374 |
if (!mmpd_data) { ext4_warning(sb, "not enough memory for mmpd_data"); goto failed; } mmpd_data->sb = sb; mmpd_data->bh = bh; /* * Start a kernel thread to update the MMP block periodically. */ |
14c9ca058
|
375 376 |
EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s", (int)sizeof(mmp->mmp_bdevname), |
c5e06d101
|
377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 |
bdevname(bh->b_bdev, mmp->mmp_bdevname)); if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) { EXT4_SB(sb)->s_mmp_tsk = NULL; kfree(mmpd_data); ext4_warning(sb, "Unable to create kmmpd thread for %s.", sb->s_id); goto failed; } return 0; failed: brelse(bh); return 1; } |