* This file is released under the GPL.
*/
+#include "dm-bio-record.h"
+
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/device-mapper.h>
__u8 log2_blocks_per_bitmap_bit;
unsigned char mode;
- int suspending;
int failed;
struct crypto_shash *internal_hash;
+ struct dm_target *ti;
+
/* these variables are locked with endio_wait.lock */
struct rb_root in_progress;
struct list_head wait_list;
wait_queue_head_t endio_wait;
struct workqueue_struct *wait_wq;
+ struct workqueue_struct *offload_wq;
unsigned char commit_seq;
commit_id_t commit_ids[N_COMMIT_IDS];
struct completion *completion;
- struct gendisk *orig_bi_disk;
- u8 orig_bi_partno;
- bio_end_io_t *orig_bi_end_io;
- struct bio_integrity_payload *orig_bi_integrity;
- struct bvec_iter orig_bi_iter;
+ struct dm_bio_details bio_details;
};
struct journal_completion {
if (unlikely(((sector | n_sectors) & ((1 << ic->sb->log2_sectors_per_block) - 1)) != 0)) {
DMCRIT("invalid bitmap access (%llx,%llx,%d,%d,%d)",
- (unsigned long long)sector,
- (unsigned long long)n_sectors,
+ sector,
+ n_sectors,
ic->sb->log2_sectors_per_block,
ic->log2_blocks_per_bitmap_bit,
mode);
dio->range.logical_sector += dio->range.n_sectors;
bio_advance(bio, dio->range.n_sectors << SECTOR_SHIFT);
INIT_WORK(&dio->work, integrity_bio_wait);
- queue_work(ic->wait_wq, &dio->work);
+ queue_work(ic->offload_wq, &dio->work);
return;
}
do_endio_flush(ic, dio);
{
struct dm_integrity_io *dio = dm_per_bio_data(bio, sizeof(struct dm_integrity_io));
- bio->bi_iter = dio->orig_bi_iter;
- bio->bi_disk = dio->orig_bi_disk;
- bio->bi_partno = dio->orig_bi_partno;
- if (dio->orig_bi_integrity) {
- bio->bi_integrity = dio->orig_bi_integrity;
+ dm_bio_restore(&dio->bio_details, bio);
+ if (bio->bi_integrity)
bio->bi_opf |= REQ_INTEGRITY;
- }
- bio->bi_end_io = dio->orig_bi_end_io;
if (dio->completion)
complete(dio->completion);
struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
char *checksums;
unsigned extra_space = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0;
- char checksums_onstack[HASH_MAX_DIGESTSIZE];
+ char checksums_onstack[max((size_t)HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
unsigned sectors_to_process = dio->range.n_sectors;
sector_t sector = dio->range.logical_sector;
}
}
- __bio_for_each_segment(bv, bio, iter, dio->orig_bi_iter) {
+ __bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
unsigned pos;
char *mem, *checksums_ptr;
checksums_ptr - checksums, !dio->write ? TAG_CMP : TAG_WRITE);
if (unlikely(r)) {
if (r > 0) {
- DMERR_LIMIT("Checksum failed at sector 0x%llx",
- (unsigned long long)(sector - ((r + ic->tag_size - 1) / ic->tag_size)));
+ char b[BDEVNAME_SIZE];
+ DMERR_LIMIT("%s: Checksum failed at sector 0x%llx", bio_devname(bio, b),
+ (sector - ((r + ic->tag_size - 1) / ic->tag_size)));
r = -EILSEQ;
atomic64_inc(&ic->number_of_mismatches);
}
if (likely(checksums != checksums_onstack))
kfree(checksums);
} else {
- struct bio_integrity_payload *bip = dio->orig_bi_integrity;
+ struct bio_integrity_payload *bip = dio->bio_details.bi_integrity;
if (bip) {
struct bio_vec biv;
}
if (unlikely(dio->range.logical_sector + bio_sectors(bio) > ic->provided_data_sectors)) {
DMERR("Too big sector number: 0x%llx + 0x%x > 0x%llx",
- (unsigned long long)dio->range.logical_sector, bio_sectors(bio),
- (unsigned long long)ic->provided_data_sectors);
+ dio->range.logical_sector, bio_sectors(bio),
+ ic->provided_data_sectors);
return DM_MAPIO_KILL;
}
if (unlikely((dio->range.logical_sector | bio_sectors(bio)) & (unsigned)(ic->sectors_per_block - 1))) {
DMERR("Bio not aligned on %u sectors: 0x%llx, 0x%x",
ic->sectors_per_block,
- (unsigned long long)dio->range.logical_sector, bio_sectors(bio));
+ dio->range.logical_sector, bio_sectors(bio));
return DM_MAPIO_KILL;
}
} while (++s < ic->sectors_per_block);
#ifdef INTERNAL_VERIFY
if (ic->internal_hash) {
- char checksums_onstack[max(HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
+ char checksums_onstack[max((size_t)HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
integrity_sector_checksum(ic, logical_sector, mem + bv.bv_offset, checksums_onstack);
if (unlikely(memcmp(checksums_onstack, journal_entry_tag(ic, je), ic->tag_size))) {
DMERR_LIMIT("Checksum failed when reading from journal, at sector 0x%llx",
- (unsigned long long)logical_sector);
+ logical_sector);
}
}
#endif
if (need_sync_io && from_map) {
INIT_WORK(&dio->work, integrity_bio_wait);
- queue_work(ic->metadata_wq, &dio->work);
+ queue_work(ic->offload_wq, &dio->work);
return;
}
} else
dio->completion = NULL;
- dio->orig_bi_iter = bio->bi_iter;
-
- dio->orig_bi_disk = bio->bi_disk;
- dio->orig_bi_partno = bio->bi_partno;
+ dm_bio_record(&dio->bio_details, bio);
bio_set_dev(bio, ic->dev->bdev);
-
- dio->orig_bi_integrity = bio_integrity(bio);
bio->bi_integrity = NULL;
bio->bi_opf &= ~REQ_INTEGRITY;
-
- dio->orig_bi_end_io = bio->bi_end_io;
bio->bi_end_io = integrity_end_io;
-
bio->bi_iter.bi_size = dio->range.n_sectors << SECTOR_SHIFT;
+
generic_make_request(bio);
if (need_sync_io) {
sec &= ~(sector_t)(ic->sectors_per_block - 1);
}
}
+ if (unlikely(sec >= ic->provided_data_sectors))
+ continue;
get_area_and_offset(ic, sec, &area, &offset);
restore_last_bytes(ic, access_journal_data(ic, i, j), je);
for (k = j + 1; k < ic->journal_section_entries; k++) {
break;
BUG_ON(unlikely(journal_entry_is_inprogress(je2)) && !from_replay);
sec2 = journal_entry_get_sector(je2);
+ if (unlikely(sec2 >= ic->provided_data_sectors))
+ break;
get_area_and_offset(ic, sec2, &area2, &offset2);
if (area2 != area || offset2 != offset + ((k - j) << ic->sb->log2_sectors_per_block))
break;
unsigned prev_free_sectors;
/* the following test is not needed, but it tests the replay code */
- if (READ_ONCE(ic->suspending) && !ic->meta_dev)
+ if (unlikely(dm_suspended(ic->ti)) && !ic->meta_dev)
return;
spin_lock_irq(&ic->endio_wait.lock);
next_chunk:
- if (unlikely(READ_ONCE(ic->suspending)))
+ if (unlikely(dm_suspended(ic->ti)))
goto unlock_ret;
range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
get_area_and_offset(ic, logical_sector, &area, &offset);
}
- DEBUG_print("recalculating: %lx, %lx\n", logical_sector, n_sectors);
+ DEBUG_print("recalculating: %llx, %llx\n", logical_sector, n_sectors);
if (unlikely(++super_counter == RECALC_WRITE_SUPER)) {
recalc_write_super(ic);
dio->range.n_sectors, BITMAP_OP_TEST_ALL_SET)) {
remove_range(ic, &dio->range);
INIT_WORK(&dio->work, integrity_bio_wait);
- queue_work(ic->wait_wq, &dio->work);
+ queue_work(ic->offload_wq, &dio->work);
} else {
block_bitmap_op(ic, ic->journal, dio->range.logical_sector,
dio->range.n_sectors, BITMAP_OP_SET);
remove_range(ic, &dio->range);
INIT_WORK(&dio->work, integrity_bio_wait);
- queue_work(ic->wait_wq, &dio->work);
+ queue_work(ic->offload_wq, &dio->work);
}
queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, ic->bitmap_flush_interval);
del_timer_sync(&ic->autocommit_timer);
- WRITE_ONCE(ic->suspending, 1);
-
if (ic->recalc_wq)
drain_workqueue(ic->recalc_wq);
#endif
}
- WRITE_ONCE(ic->suspending, 0);
-
BUG_ON(!RB_EMPTY_ROOT(&ic->in_progress));
ic->journal_uptodate = true;
static void dm_integrity_resume(struct dm_target *ti)
{
struct dm_integrity_c *ic = (struct dm_integrity_c *)ti->private;
+ __u64 old_provided_data_sectors = le64_to_cpu(ic->sb->provided_data_sectors);
int r;
+
DEBUG_print("resume\n");
+ if (ic->provided_data_sectors != old_provided_data_sectors) {
+ if (ic->provided_data_sectors > old_provided_data_sectors &&
+ ic->mode == 'B' &&
+ ic->sb->log2_blocks_per_bitmap_bit == ic->log2_blocks_per_bitmap_bit) {
+ rw_journal_sectors(ic, REQ_OP_READ, 0, 0,
+ ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);
+ block_bitmap_op(ic, ic->journal, old_provided_data_sectors,
+ ic->provided_data_sectors - old_provided_data_sectors, BITMAP_OP_SET);
+ rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, 0,
+ ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);
+ }
+
+ ic->sb->provided_data_sectors = cpu_to_le64(ic->provided_data_sectors);
+ r = sync_rw_sb(ic, REQ_OP_WRITE, REQ_FUA);
+ if (unlikely(r))
+ dm_integrity_io_error(ic, "writing superblock", r);
+ }
+
if (ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP)) {
DEBUG_print("resume dirty_bitmap\n");
rw_journal_sectors(ic, REQ_OP_READ, 0, 0,
DEBUG_print("testing recalc: %x\n", ic->sb->flags);
if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
__u64 recalc_pos = le64_to_cpu(ic->sb->recalc_sector);
- DEBUG_print("recalc pos: %lx / %lx\n", (long)recalc_pos, ic->provided_data_sectors);
+ DEBUG_print("recalc pos: %llx / %llx\n", recalc_pos, ic->provided_data_sectors);
if (recalc_pos < ic->provided_data_sectors) {
queue_work(ic->recalc_wq, &ic->recalc_work);
} else if (recalc_pos > ic->provided_data_sectors) {
switch (type) {
case STATUSTYPE_INFO:
DMEMIT("%llu %llu",
- (unsigned long long)atomic64_read(&ic->number_of_mismatches),
- (unsigned long long)ic->provided_data_sectors);
+ atomic64_read(&ic->number_of_mismatches),
+ ic->provided_data_sectors);
if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))
- DMEMIT(" %llu", (unsigned long long)le64_to_cpu(ic->sb->recalc_sector));
+ DMEMIT(" %llu", le64_to_cpu(ic->sb->recalc_sector));
else
DMEMIT(" -");
break;
arg_count += !!ic->journal_crypt_alg.alg_string;
arg_count += !!ic->journal_mac_alg.alg_string;
arg_count += (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0;
- DMEMIT("%s %llu %u %c %u", ic->dev->name, (unsigned long long)ic->start,
+ DMEMIT("%s %llu %u %c %u", ic->dev->name, ic->start,
ic->tag_size, ic->mode, arg_count);
if (ic->meta_dev)
DMEMIT(" meta_device:%s", ic->meta_dev->name);
if (ic->sectors_per_block != 1)
DMEMIT(" block_size:%u", ic->sectors_per_block << SECTOR_SHIFT);
- if (ic->recalculate_flag)
+ if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))
DMEMIT(" recalculate");
DMEMIT(" journal_sectors:%u", ic->initial_sectors - SB_SECTORS);
DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors);
DMEMIT(" commit_time:%u", ic->autocommit_msec);
}
if (ic->mode == 'B') {
- DMEMIT(" sectors_per_bit:%llu", (unsigned long long)ic->sectors_per_block << ic->log2_blocks_per_bitmap_bit);
+ DMEMIT(" sectors_per_bit:%llu", (sector_t)ic->sectors_per_block << ic->log2_blocks_per_bitmap_bit);
DMEMIT(" bitmap_flush_interval:%u", jiffies_to_msecs(ic->bitmap_flush_interval));
}
if ((ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0)
return 0;
}
+static void get_provided_data_sectors(struct dm_integrity_c *ic)
+{
+ if (!ic->meta_dev) {
+ int test_bit;
+ ic->provided_data_sectors = 0;
+ for (test_bit = fls64(ic->meta_device_sectors) - 1; test_bit >= 3; test_bit--) {
+ __u64 prev_data_sectors = ic->provided_data_sectors;
+
+ ic->provided_data_sectors |= (sector_t)1 << test_bit;
+ if (calculate_device_limits(ic))
+ ic->provided_data_sectors = prev_data_sectors;
+ }
+ } else {
+ ic->provided_data_sectors = ic->data_device_sectors;
+ ic->provided_data_sectors &= ~(sector_t)(ic->sectors_per_block - 1);
+ }
+}
+
static int initialize_superblock(struct dm_integrity_c *ic, unsigned journal_sectors, unsigned interleave_sectors)
{
unsigned journal_sections;
ic->sb->log2_interleave_sectors = max((__u8)MIN_LOG2_INTERLEAVE_SECTORS, ic->sb->log2_interleave_sectors);
ic->sb->log2_interleave_sectors = min((__u8)MAX_LOG2_INTERLEAVE_SECTORS, ic->sb->log2_interleave_sectors);
- ic->provided_data_sectors = 0;
- for (test_bit = fls64(ic->meta_device_sectors) - 1; test_bit >= 3; test_bit--) {
- __u64 prev_data_sectors = ic->provided_data_sectors;
-
- ic->provided_data_sectors |= (sector_t)1 << test_bit;
- if (calculate_device_limits(ic))
- ic->provided_data_sectors = prev_data_sectors;
- }
+ get_provided_data_sectors(ic);
if (!ic->provided_data_sectors)
return -EINVAL;
} else {
ic->sb->log2_interleave_sectors = 0;
- ic->provided_data_sectors = ic->data_device_sectors;
- ic->provided_data_sectors &= ~(sector_t)(ic->sectors_per_block - 1);
+
+ get_provided_data_sectors(ic);
+ if (!ic->provided_data_sectors)
+ return -EINVAL;
try_smaller_buffer:
ic->sb->journal_sections = cpu_to_le32(0);
}
ti->private = ic;
ti->per_io_data_size = sizeof(struct dm_integrity_io);
+ ic->ti = ti;
ic->in_progress = RB_ROOT;
INIT_LIST_HEAD(&ic->wait_list);
goto bad;
}
+ ic->offload_wq = alloc_workqueue("dm-integrity-offload", WQ_MEM_RECLAIM,
+ METADATA_WORKQUEUE_MAX_ACTIVE);
+ if (!ic->offload_wq) {
+ ti->error = "Cannot allocate workqueue";
+ r = -ENOMEM;
+ goto bad;
+ }
+
ic->commit_wq = alloc_workqueue("dm-integrity-commit", WQ_MEM_RECLAIM, 1);
if (!ic->commit_wq) {
ti->error = "Cannot allocate workqueue";
goto bad;
}
}
- ic->provided_data_sectors = le64_to_cpu(ic->sb->provided_data_sectors);
- if (ic->provided_data_sectors != le64_to_cpu(ic->sb->provided_data_sectors)) {
- /* test for overflow */
+ if (!!(ic->sb->flags & cpu_to_le32(SB_FLAG_HAVE_JOURNAL_MAC)) != !!ic->journal_mac_alg.alg_string) {
r = -EINVAL;
- ti->error = "The superblock has 64-bit device size, but the kernel was compiled with 32-bit sectors";
+ ti->error = "Journal mac mismatch";
goto bad;
}
- if (!!(ic->sb->flags & cpu_to_le32(SB_FLAG_HAVE_JOURNAL_MAC)) != !!ic->journal_mac_alg.alg_string) {
+
+ get_provided_data_sectors(ic);
+ if (!ic->provided_data_sectors) {
r = -EINVAL;
- ti->error = "Journal mac mismatch";
+ ti->error = "The device is too small";
goto bad;
}
DEBUG_print(" initial_sectors 0x%x\n", ic->initial_sectors);
DEBUG_print(" metadata_run 0x%x\n", ic->metadata_run);
DEBUG_print(" log2_metadata_run %d\n", ic->log2_metadata_run);
- DEBUG_print(" provided_data_sectors 0x%llx (%llu)\n", (unsigned long long)ic->provided_data_sectors,
- (unsigned long long)ic->provided_data_sectors);
+ DEBUG_print(" provided_data_sectors 0x%llx (%llu)\n", ic->provided_data_sectors, ic->provided_data_sectors);
DEBUG_print(" log2_buffer_sectors %u\n", ic->log2_buffer_sectors);
- DEBUG_print(" bits_in_journal %llu\n", (unsigned long long)bits_in_journal);
+ DEBUG_print(" bits_in_journal %llu\n", bits_in_journal);
if (ic->recalculate_flag && !(ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))) {
ic->sb->flags |= cpu_to_le32(SB_FLAG_RECALCULATING);
destroy_workqueue(ic->metadata_wq);
if (ic->wait_wq)
destroy_workqueue(ic->wait_wq);
+ if (ic->offload_wq)
+ destroy_workqueue(ic->offload_wq);
if (ic->commit_wq)
destroy_workqueue(ic->commit_wq);
if (ic->writer_wq)
static struct target_type integrity_target = {
.name = "integrity",
- .version = {1, 4, 0},
+ .version = {1, 6, 0},
.module = THIS_MODULE,
.features = DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY,
.ctr = dm_integrity_ctr,
projects / linux-2.6-microblaze.git / blobdiff