#define MIN_LOG2_INTERLEAVE_SECTORS 3
#define MAX_LOG2_INTERLEAVE_SECTORS 31
#define METADATA_WORKQUEUE_MAX_ACTIVE 16
+#define RECALC_SECTORS 8192
+#define RECALC_WRITE_SUPER 16
/*
* Warning - DEBUG_PRINT prints security-sensitive data to the log,
*/
#define SB_MAGIC "integrt"
-#define SB_VERSION 1
+#define SB_VERSION_1 1
+#define SB_VERSION_2 2
#define SB_SECTORS 8
#define MAX_SECTORS_PER_BLOCK 8
__u64 provided_data_sectors; /* userspace uses this value */
__u32 flags;
__u8 log2_sectors_per_block;
+ __u8 pad[3];
+ __u64 recalc_sector;
};
#define SB_FLAG_HAVE_JOURNAL_MAC 0x1
+#define SB_FLAG_RECALCULATING 0x2
#define JOURNAL_ENTRY_ROUNDUP 8
struct dm_integrity_c {
struct dm_dev *dev;
+ struct dm_dev *meta_dev;
unsigned tag_size;
__s8 log2_tag_size;
sector_t start;
unsigned short journal_section_sectors;
unsigned journal_sections;
unsigned journal_entries;
- sector_t device_sectors;
+ sector_t data_device_sectors;
+ sector_t meta_device_sectors;
unsigned initial_sectors;
unsigned metadata_run;
__s8 log2_metadata_run;
struct workqueue_struct *writer_wq;
struct work_struct writer_work;
+ struct workqueue_struct *recalc_wq;
+ struct work_struct recalc_work;
+ u8 *recalc_buffer;
+ u8 *recalc_tags;
+
struct bio_list flush_bio_list;
unsigned long autocommit_jiffies;
static void get_area_and_offset(struct dm_integrity_c *ic, sector_t data_sector,
sector_t *area, sector_t *offset)
{
- __u8 log2_interleave_sectors = ic->sb->log2_interleave_sectors;
-
- *area = data_sector >> log2_interleave_sectors;
- *offset = (unsigned)data_sector & ((1U << log2_interleave_sectors) - 1);
+ if (!ic->meta_dev) {
+ __u8 log2_interleave_sectors = ic->sb->log2_interleave_sectors;
+ *area = data_sector >> log2_interleave_sectors;
+ *offset = (unsigned)data_sector & ((1U << log2_interleave_sectors) - 1);
+ } else {
+ *area = 0;
+ *offset = data_sector;
+ }
}
#define sector_to_block(ic, n) \
{
sector_t result;
+ if (ic->meta_dev)
+ return offset;
+
result = area << ic->sb->log2_interleave_sectors;
if (likely(ic->log2_metadata_run >= 0))
result += (area + 1) << ic->log2_metadata_run;
*sec_ptr -= ic->journal_sections;
}
+static void sb_set_version(struct dm_integrity_c *ic)
+{
+ if (ic->meta_dev || ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))
+ ic->sb->version = SB_VERSION_2;
+ else
+ ic->sb->version = SB_VERSION_1;
+}
+
static int sync_rw_sb(struct dm_integrity_c *ic, int op, int op_flags)
{
struct dm_io_request io_req;
io_req.mem.ptr.addr = ic->sb;
io_req.notify.fn = NULL;
io_req.client = ic->io;
- io_loc.bdev = ic->dev->bdev;
+ io_loc.bdev = ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev;
io_loc.sector = ic->start;
io_loc.count = SB_SECTORS;
io_req.notify.fn = NULL;
}
io_req.client = ic->io;
- io_loc.bdev = ic->dev->bdev;
+ io_loc.bdev = ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev;
io_loc.sector = ic->start + SB_SECTORS + sector;
io_loc.count = n_sectors;
if (need_sync_io) {
wait_for_completion_io(&read_comp);
+ if (unlikely(ic->recalc_wq != NULL) &&
+ ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) &&
+ dio->range.logical_sector + dio->range.n_sectors > le64_to_cpu(ic->sb->recalc_sector))
+ goto skip_check;
if (likely(!bio->bi_status))
integrity_metadata(&dio->work);
else
+skip_check:
dec_in_flight(dio);
} else {
unsigned prev_free_sectors;
/* the following test is not needed, but it tests the replay code */
- if (READ_ONCE(ic->suspending))
+ if (READ_ONCE(ic->suspending) && !ic->meta_dev)
return;
spin_lock_irq(&ic->endio_wait.lock);
spin_unlock_irq(&ic->endio_wait.lock);
}
+static void recalc_write_super(struct dm_integrity_c *ic)
+{
+ int r;
+
+ dm_integrity_flush_buffers(ic);
+ if (dm_integrity_failed(ic))
+ return;
+
+ sb_set_version(ic);
+ r = sync_rw_sb(ic, REQ_OP_WRITE, 0);
+ if (unlikely(r))
+ dm_integrity_io_error(ic, "writing superblock", r);
+}
+
+static void integrity_recalc(struct work_struct *w)
+{
+ struct dm_integrity_c *ic = container_of(w, struct dm_integrity_c, recalc_work);
+ struct dm_integrity_range range;
+ struct dm_io_request io_req;
+ struct dm_io_region io_loc;
+ sector_t area, offset;
+ sector_t metadata_block;
+ unsigned metadata_offset;
+ __u8 *t;
+ unsigned i;
+ int r;
+ unsigned super_counter = 0;
+
+ spin_lock_irq(&ic->endio_wait.lock);
+
+next_chunk:
+
+ if (unlikely(READ_ONCE(ic->suspending)))
+ goto unlock_ret;
+
+ range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
+ if (unlikely(range.logical_sector >= ic->provided_data_sectors))
+ goto unlock_ret;
+
+ get_area_and_offset(ic, range.logical_sector, &area, &offset);
+ range.n_sectors = min((sector_t)RECALC_SECTORS, ic->provided_data_sectors - range.logical_sector);
+ if (!ic->meta_dev)
+ range.n_sectors = min(range.n_sectors, (1U << ic->sb->log2_interleave_sectors) - (unsigned)offset);
+
+ if (unlikely(!add_new_range(ic, &range, true)))
+ wait_and_add_new_range(ic, &range);
+
+ spin_unlock_irq(&ic->endio_wait.lock);
+
+ if (unlikely(++super_counter == RECALC_WRITE_SUPER)) {
+ recalc_write_super(ic);
+ super_counter = 0;
+ }
+
+ if (unlikely(dm_integrity_failed(ic)))
+ goto err;
+
+ io_req.bi_op = REQ_OP_READ;
+ io_req.bi_op_flags = 0;
+ io_req.mem.type = DM_IO_VMA;
+ io_req.mem.ptr.addr = ic->recalc_buffer;
+ io_req.notify.fn = NULL;
+ io_req.client = ic->io;
+ io_loc.bdev = ic->dev->bdev;
+ io_loc.sector = get_data_sector(ic, area, offset);
+ io_loc.count = range.n_sectors;
+
+ r = dm_io(&io_req, 1, &io_loc, NULL);
+ if (unlikely(r)) {
+ dm_integrity_io_error(ic, "reading data", r);
+ goto err;
+ }
+
+ t = ic->recalc_tags;
+ for (i = 0; i < range.n_sectors; i += ic->sectors_per_block) {
+ integrity_sector_checksum(ic, range.logical_sector + i, ic->recalc_buffer + (i << SECTOR_SHIFT), t);
+ t += ic->tag_size;
+ }
+
+ metadata_block = get_metadata_sector_and_offset(ic, area, offset, &metadata_offset);
+
+ r = dm_integrity_rw_tag(ic, ic->recalc_tags, &metadata_block, &metadata_offset, t - ic->recalc_tags, TAG_WRITE);
+ if (unlikely(r)) {
+ dm_integrity_io_error(ic, "writing tags", r);
+ goto err;
+ }
+
+ spin_lock_irq(&ic->endio_wait.lock);
+ remove_range_unlocked(ic, &range);
+ ic->sb->recalc_sector = cpu_to_le64(range.logical_sector + range.n_sectors);
+ goto next_chunk;
+
+err:
+ remove_range(ic, &range);
+ return;
+
+unlock_ret:
+ spin_unlock_irq(&ic->endio_wait.lock);
+
+ recalc_write_super(ic);
+}
+
static void init_journal(struct dm_integrity_c *ic, unsigned start_section,
unsigned n_sections, unsigned char commit_seq)
{
WRITE_ONCE(ic->suspending, 1);
+ if (ic->recalc_wq)
+ drain_workqueue(ic->recalc_wq);
+
queue_work(ic->commit_wq, &ic->commit_work);
drain_workqueue(ic->commit_wq);
if (ic->mode == 'J') {
+ if (ic->meta_dev)
+ queue_work(ic->writer_wq, &ic->writer_work);
drain_workqueue(ic->writer_wq);
dm_integrity_flush_buffers(ic);
}
struct dm_integrity_c *ic = (struct dm_integrity_c *)ti->private;
replay_journal(ic);
+
+ if (ic->recalc_wq && ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
+ __u64 recalc_pos = le64_to_cpu(ic->sb->recalc_sector);
+ if (recalc_pos < ic->provided_data_sectors) {
+ queue_work(ic->recalc_wq, &ic->recalc_work);
+ } else if (recalc_pos > ic->provided_data_sectors) {
+ ic->sb->recalc_sector = cpu_to_le64(ic->provided_data_sectors);
+ recalc_write_super(ic);
+ }
+ }
}
static void dm_integrity_status(struct dm_target *ti, status_type_t type,
DMEMIT("%llu %llu",
(unsigned long long)atomic64_read(&ic->number_of_mismatches),
(unsigned long long)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));
+ else
+ DMEMIT(" -");
break;
case STATUSTYPE_TABLE: {
watermark_percentage += ic->journal_entries / 2;
do_div(watermark_percentage, ic->journal_entries);
arg_count = 5;
+ arg_count += !!ic->meta_dev;
arg_count += ic->sectors_per_block != 1;
+ arg_count += !!(ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING));
arg_count += !!ic->internal_hash_alg.alg_string;
arg_count += !!ic->journal_crypt_alg.alg_string;
arg_count += !!ic->journal_mac_alg.alg_string;
DMEMIT("%s %llu %u %c %u", ic->dev->name, (unsigned long long)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->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(" buffer_sectors:%u", 1U << ic->log2_buffer_sectors);
DMEMIT(" journal_watermark:%u", (unsigned)watermark_percentage);
DMEMIT(" commit_time:%u", ic->autocommit_msec);
- if (ic->sectors_per_block != 1)
- DMEMIT(" block_size:%u", ic->sectors_per_block << SECTOR_SHIFT);
#define EMIT_ALG(a, n) \
do { \
{
struct dm_integrity_c *ic = ti->private;
- return fn(ti, ic->dev, ic->start + ic->initial_sectors + ic->metadata_run, ti->len, data);
+ if (!ic->meta_dev)
+ return fn(ti, ic->dev, ic->start + ic->initial_sectors + ic->metadata_run, ti->len, data);
+ else
+ return fn(ti, ic->dev, 0, ti->len, data);
}
static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *limits)
static int calculate_device_limits(struct dm_integrity_c *ic)
{
__u64 initial_sectors;
- sector_t last_sector, last_area, last_offset;
calculate_journal_section_size(ic);
initial_sectors = SB_SECTORS + (__u64)ic->journal_section_sectors * ic->journal_sections;
- if (initial_sectors + METADATA_PADDING_SECTORS >= ic->device_sectors || initial_sectors > UINT_MAX)
+ if (initial_sectors + METADATA_PADDING_SECTORS >= ic->meta_device_sectors || initial_sectors > UINT_MAX)
return -EINVAL;
ic->initial_sectors = initial_sectors;
- ic->metadata_run = roundup((__u64)ic->tag_size << (ic->sb->log2_interleave_sectors - ic->sb->log2_sectors_per_block),
- (__u64)(1 << SECTOR_SHIFT << METADATA_PADDING_SECTORS)) >> SECTOR_SHIFT;
- if (!(ic->metadata_run & (ic->metadata_run - 1)))
- ic->log2_metadata_run = __ffs(ic->metadata_run);
- else
- ic->log2_metadata_run = -1;
+ if (!ic->meta_dev) {
+ sector_t last_sector, last_area, last_offset;
- get_area_and_offset(ic, ic->provided_data_sectors - 1, &last_area, &last_offset);
- last_sector = get_data_sector(ic, last_area, last_offset);
+ ic->metadata_run = roundup((__u64)ic->tag_size << (ic->sb->log2_interleave_sectors - ic->sb->log2_sectors_per_block),
+ (__u64)(1 << SECTOR_SHIFT << METADATA_PADDING_SECTORS)) >> SECTOR_SHIFT;
+ if (!(ic->metadata_run & (ic->metadata_run - 1)))
+ ic->log2_metadata_run = __ffs(ic->metadata_run);
+ else
+ ic->log2_metadata_run = -1;
- if (last_sector < ic->start || last_sector >= ic->device_sectors)
- return -EINVAL;
+ get_area_and_offset(ic, ic->provided_data_sectors - 1, &last_area, &last_offset);
+ last_sector = get_data_sector(ic, last_area, last_offset);
+ if (last_sector < ic->start || last_sector >= ic->meta_device_sectors)
+ return -EINVAL;
+ } else {
+ __u64 meta_size = ic->provided_data_sectors * ic->tag_size;
+ meta_size = (meta_size + ((1U << (ic->log2_buffer_sectors + SECTOR_SHIFT)) - 1))
+ >> (ic->log2_buffer_sectors + SECTOR_SHIFT);
+ meta_size <<= ic->log2_buffer_sectors;
+ if (ic->initial_sectors + meta_size < ic->initial_sectors ||
+ ic->initial_sectors + meta_size > ic->meta_device_sectors)
+ return -EINVAL;
+ ic->metadata_run = 1;
+ ic->log2_metadata_run = 0;
+ }
return 0;
}
memset(ic->sb, 0, SB_SECTORS << SECTOR_SHIFT);
memcpy(ic->sb->magic, SB_MAGIC, 8);
- ic->sb->version = SB_VERSION;
ic->sb->integrity_tag_size = cpu_to_le16(ic->tag_size);
ic->sb->log2_sectors_per_block = __ffs(ic->sectors_per_block);
if (ic->journal_mac_alg.alg_string)
journal_sections = journal_sectors / ic->journal_section_sectors;
if (!journal_sections)
journal_sections = 1;
- ic->sb->journal_sections = cpu_to_le32(journal_sections);
-
- if (!interleave_sectors)
- interleave_sectors = DEFAULT_INTERLEAVE_SECTORS;
- ic->sb->log2_interleave_sectors = __fls(interleave_sectors);
- 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->device_sectors) - 1; test_bit >= 3; test_bit--) {
- __u64 prev_data_sectors = ic->provided_data_sectors;
+ if (!ic->meta_dev) {
+ ic->sb->journal_sections = cpu_to_le32(journal_sections);
+ if (!interleave_sectors)
+ interleave_sectors = DEFAULT_INTERLEAVE_SECTORS;
+ ic->sb->log2_interleave_sectors = __fls(interleave_sectors);
+ 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;
+ }
+ 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);
+
+try_smaller_buffer:
+ ic->sb->journal_sections = cpu_to_le32(0);
+ for (test_bit = fls(journal_sections) - 1; test_bit >= 0; test_bit--) {
+ __u32 prev_journal_sections = le32_to_cpu(ic->sb->journal_sections);
+ __u32 test_journal_sections = prev_journal_sections | (1U << test_bit);
+ if (test_journal_sections > journal_sections)
+ continue;
+ ic->sb->journal_sections = cpu_to_le32(test_journal_sections);
+ if (calculate_device_limits(ic))
+ ic->sb->journal_sections = cpu_to_le32(prev_journal_sections);
- ic->provided_data_sectors |= (sector_t)1 << test_bit;
- if (calculate_device_limits(ic))
- ic->provided_data_sectors = prev_data_sectors;
+ }
+ if (!le32_to_cpu(ic->sb->journal_sections)) {
+ if (ic->log2_buffer_sectors > 3) {
+ ic->log2_buffer_sectors--;
+ goto try_smaller_buffer;
+ }
+ return -EINVAL;
+ }
}
- if (!ic->provided_data_sectors)
- return -EINVAL;
-
ic->sb->provided_data_sectors = cpu_to_le64(ic->provided_data_sectors);
+ sb_set_version(ic);
+
return 0;
}
{0, 9, "Invalid number of feature args"},
};
unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec;
+ bool recalculate;
bool should_write_sb;
__u64 threshold;
unsigned long long start;
goto bad;
}
- ic->device_sectors = i_size_read(ic->dev->bdev->bd_inode) >> SECTOR_SHIFT;
- journal_sectors = min((sector_t)DEFAULT_MAX_JOURNAL_SECTORS,
- ic->device_sectors >> DEFAULT_JOURNAL_SIZE_FACTOR);
+ journal_sectors = 0;
interleave_sectors = DEFAULT_INTERLEAVE_SECTORS;
buffer_sectors = DEFAULT_BUFFER_SECTORS;
journal_watermark = DEFAULT_JOURNAL_WATERMARK;
sync_msec = DEFAULT_SYNC_MSEC;
+ recalculate = false;
ic->sectors_per_block = 1;
as.argc = argc - DIRECT_ARGUMENTS;
goto bad;
}
if (sscanf(opt_string, "journal_sectors:%u%c", &val, &dummy) == 1)
- journal_sectors = val;
+ journal_sectors = val ? val : 1;
else if (sscanf(opt_string, "interleave_sectors:%u%c", &val, &dummy) == 1)
interleave_sectors = val;
else if (sscanf(opt_string, "buffer_sectors:%u%c", &val, &dummy) == 1)
journal_watermark = val;
else if (sscanf(opt_string, "commit_time:%u%c", &val, &dummy) == 1)
sync_msec = val;
- else if (sscanf(opt_string, "block_size:%u%c", &val, &dummy) == 1) {
+ else if (!memcmp(opt_string, "meta_device:", strlen("meta_device:"))) {
+ if (ic->meta_dev) {
+ dm_put_device(ti, ic->meta_dev);
+ ic->meta_dev = NULL;
+ }
+ r = dm_get_device(ti, strchr(opt_string, ':') + 1, dm_table_get_mode(ti->table), &ic->meta_dev);
+ if (r) {
+ ti->error = "Device lookup failed";
+ goto bad;
+ }
+ } else if (sscanf(opt_string, "block_size:%u%c", &val, &dummy) == 1) {
if (val < 1 << SECTOR_SHIFT ||
val > MAX_SECTORS_PER_BLOCK << SECTOR_SHIFT ||
(val & (val -1))) {
"Invalid journal_mac argument");
if (r)
goto bad;
+ } else if (!strcmp(opt_string, "recalculate")) {
+ recalculate = true;
} else {
r = -EINVAL;
ti->error = "Invalid argument";
}
}
+ ic->data_device_sectors = i_size_read(ic->dev->bdev->bd_inode) >> SECTOR_SHIFT;
+ if (!ic->meta_dev)
+ ic->meta_device_sectors = ic->data_device_sectors;
+ else
+ ic->meta_device_sectors = i_size_read(ic->meta_dev->bdev->bd_inode) >> SECTOR_SHIFT;
+
+ if (!journal_sectors) {
+ journal_sectors = min((sector_t)DEFAULT_MAX_JOURNAL_SECTORS,
+ ic->data_device_sectors >> DEFAULT_JOURNAL_SIZE_FACTOR);
+ }
+
+ if (!buffer_sectors)
+ buffer_sectors = 1;
+ ic->log2_buffer_sectors = min((int)__fls(buffer_sectors), 31 - SECTOR_SHIFT);
+
r = get_mac(&ic->internal_hash, &ic->internal_hash_alg, &ti->error,
"Invalid internal hash", "Error setting internal hash key");
if (r)
should_write_sb = true;
}
- if (ic->sb->version != SB_VERSION) {
+ if (!ic->sb->version || ic->sb->version > SB_VERSION_2) {
r = -EINVAL;
ti->error = "Unknown version";
goto bad;
goto bad;
}
/* make sure that ti->max_io_len doesn't overflow */
- if (ic->sb->log2_interleave_sectors < MIN_LOG2_INTERLEAVE_SECTORS ||
- ic->sb->log2_interleave_sectors > MAX_LOG2_INTERLEAVE_SECTORS) {
- r = -EINVAL;
- ti->error = "Invalid interleave_sectors in the superblock";
- goto bad;
+ if (!ic->meta_dev) {
+ if (ic->sb->log2_interleave_sectors < MIN_LOG2_INTERLEAVE_SECTORS ||
+ ic->sb->log2_interleave_sectors > MAX_LOG2_INTERLEAVE_SECTORS) {
+ r = -EINVAL;
+ ti->error = "Invalid interleave_sectors in the superblock";
+ goto bad;
+ }
+ } else {
+ if (ic->sb->log2_interleave_sectors) {
+ r = -EINVAL;
+ ti->error = "Invalid interleave_sectors in the superblock";
+ 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)) {
ti->error = "Journal mac mismatch";
goto bad;
}
+
+try_smaller_buffer:
r = calculate_device_limits(ic);
if (r) {
+ if (ic->meta_dev) {
+ if (ic->log2_buffer_sectors > 3) {
+ ic->log2_buffer_sectors--;
+ goto try_smaller_buffer;
+ }
+ }
ti->error = "The device is too small";
goto bad;
}
+ if (!ic->meta_dev)
+ ic->log2_buffer_sectors = min(ic->log2_buffer_sectors, (__u8)__ffs(ic->metadata_run));
+
if (ti->len > ic->provided_data_sectors) {
r = -EINVAL;
ti->error = "Not enough provided sectors for requested mapping size";
goto bad;
}
- if (!buffer_sectors)
- buffer_sectors = 1;
- ic->log2_buffer_sectors = min3((int)__fls(buffer_sectors), (int)__ffs(ic->metadata_run), 31 - SECTOR_SHIFT);
threshold = (__u64)ic->journal_entries * (100 - journal_watermark);
threshold += 50;
(unsigned long long)ic->provided_data_sectors);
DEBUG_print(" log2_buffer_sectors %u\n", ic->log2_buffer_sectors);
- ic->bufio = dm_bufio_client_create(ic->dev->bdev, 1U << (SECTOR_SHIFT + ic->log2_buffer_sectors),
- 1, 0, NULL, NULL);
+ if (recalculate && !(ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))) {
+ ic->sb->flags |= cpu_to_le32(SB_FLAG_RECALCULATING);
+ ic->sb->recalc_sector = cpu_to_le64(0);
+ }
+
+ if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
+ if (!ic->internal_hash) {
+ r = -EINVAL;
+ ti->error = "Recalculate is only valid with internal hash";
+ goto bad;
+ }
+ ic->recalc_wq = alloc_workqueue("dm-intergrity-recalc", WQ_MEM_RECLAIM, 1);
+ if (!ic->recalc_wq ) {
+ ti->error = "Cannot allocate workqueue";
+ r = -ENOMEM;
+ goto bad;
+ }
+ INIT_WORK(&ic->recalc_work, integrity_recalc);
+ ic->recalc_buffer = vmalloc(RECALC_SECTORS << SECTOR_SHIFT);
+ if (!ic->recalc_buffer) {
+ ti->error = "Cannot allocate buffer for recalculating";
+ r = -ENOMEM;
+ goto bad;
+ }
+ ic->recalc_tags = kvmalloc((RECALC_SECTORS >> ic->sb->log2_sectors_per_block) * ic->tag_size, GFP_KERNEL);
+ if (!ic->recalc_tags) {
+ ti->error = "Cannot allocate tags for recalculating";
+ r = -ENOMEM;
+ goto bad;
+ }
+ }
+
+ ic->bufio = dm_bufio_client_create(ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev,
+ 1U << (SECTOR_SHIFT + ic->log2_buffer_sectors), 1, 0, NULL, NULL);
if (IS_ERR(ic->bufio)) {
r = PTR_ERR(ic->bufio);
ti->error = "Cannot initialize dm-bufio";
ic->just_formatted = true;
}
- r = dm_set_target_max_io_len(ti, 1U << ic->sb->log2_interleave_sectors);
- if (r)
- goto bad;
+ if (!ic->meta_dev) {
+ r = dm_set_target_max_io_len(ti, 1U << ic->sb->log2_interleave_sectors);
+ if (r)
+ goto bad;
+ }
if (!ic->internal_hash)
dm_integrity_set(ti, ic);
destroy_workqueue(ic->commit_wq);
if (ic->writer_wq)
destroy_workqueue(ic->writer_wq);
+ if (ic->recalc_wq)
+ destroy_workqueue(ic->recalc_wq);
+ if (ic->recalc_buffer)
+ vfree(ic->recalc_buffer);
+ if (ic->recalc_tags)
+ kvfree(ic->recalc_tags);
if (ic->bufio)
dm_bufio_client_destroy(ic->bufio);
mempool_exit(&ic->journal_io_mempool);
dm_io_client_destroy(ic->io);
if (ic->dev)
dm_put_device(ti, ic->dev);
+ if (ic->meta_dev)
+ dm_put_device(ti, ic->meta_dev);
dm_integrity_free_page_list(ic, ic->journal);
dm_integrity_free_page_list(ic, ic->journal_io);
dm_integrity_free_page_list(ic, ic->journal_xor);
static struct target_type integrity_target = {
.name = "integrity",
- .version = {1, 1, 0},
+ .version = {1, 2, 0},
.module = THIS_MODULE,
.features = DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY,
.ctr = dm_integrity_ctr,