static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
unsigned int argc, char **argv,
struct dm_dev *dev)
{
enum sync sync = DEFAULTSYNC;
struct log_c *lc;
uint32_t region_size;
unsigned int region_count;
size_t bitset_size, buf_size;
int r;
char dummy;
if (argc < 1 || argc > 2) {
DMWARN("wrong number of arguments to dirty region log");
return -EINVAL;
}
if (argc > 1) {
if (!strcmp(argv[1], "sync"))
sync = FORCESYNC;
else if (!strcmp(argv[1], "nosync"))
sync = NOSYNC;
else {
DMWARN("unrecognised sync argument to "
"dirty region log: %s", argv[1]);
return -EINVAL;
}
}
if (sscanf(argv[0], "%u%c", ®ion_size, &dummy) != 1 ||
!_check_region_size(ti, region_size)) {
DMWARN("invalid region size %s", argv[0]);
return -EINVAL;
}
region_count = dm_sector_div_up(ti->len, region_size);
lc = kmalloc(sizeof(*lc), GFP_KERNEL);
if (!lc) {
DMWARN("couldn't allocate core log");
return -ENOMEM;
}
lc->ti = ti;
lc->touched_dirtied = 0;
lc->touched_cleaned = 0;
lc->flush_failed = 0;
lc->region_size = region_size;
lc->region_count = region_count;
lc->sync = sync;
/*
* Work out how many "unsigned long"s we need to hold the bitset.
*/
bitset_size = dm_round_up(region_count,
sizeof(*lc->clean_bits) << BYTE_SHIFT);
bitset_size >>= BYTE_SHIFT;
lc->bitset_uint32_count = bitset_size / sizeof(*lc->clean_bits);
/*
* Disk log?
*/
if (!dev) {
lc->clean_bits = vmalloc(bitset_size);
if (!lc->clean_bits) {
DMWARN("couldn't allocate clean bitset");
kfree(lc);
return -ENOMEM;
}
lc->disk_header = NULL;
} else {
lc->log_dev = dev;
lc->log_dev_failed = 0;
lc->log_dev_flush_failed = 0;
lc->header_location.bdev = lc->log_dev->bdev;
lc->header_location.sector = 0;
/*
* Buffer holds both header and bitset.
*/
buf_size =
dm_round_up((LOG_OFFSET << SECTOR_SHIFT) + bitset_size,
bdev_logical_block_size(lc->header_location.
bdev));
if (buf_size > i_size_read(dev->bdev->bd_inode)) {
DMWARN("log device %s too small: need %llu bytes",
dev->name, (unsigned long long)buf_size);
kfree(lc);
return -EINVAL;
}
lc->header_location.count = buf_size >> SECTOR_SHIFT;
lc->io_req.mem.type = DM_IO_VMA;
lc->io_req.notify.fn = NULL;
lc->io_req.client = dm_io_client_create();
if (IS_ERR(lc->io_req.client)) {
r = PTR_ERR(lc->io_req.client);
DMWARN("couldn't allocate disk io client");
kfree(lc);
return r;
}
lc->disk_header = vmalloc(buf_size);
if (!lc->disk_header) {
DMWARN("couldn't allocate disk log buffer");
dm_io_client_destroy(lc->io_req.client);
kfree(lc);
return -ENOMEM;
}
lc->io_req.mem.ptr.vma = lc->disk_header;
lc->clean_bits = (void *)lc->disk_header +
(LOG_OFFSET << SECTOR_SHIFT);
}
memset(lc->clean_bits, -1, bitset_size);
lc->sync_bits = vmalloc(bitset_size);
if (!lc->sync_bits) {
DMWARN("couldn't allocate sync bitset");
if (!dev)
vfree(lc->clean_bits);
else
dm_io_client_destroy(lc->io_req.client);
vfree(lc->disk_header);
kfree(lc);
return -ENOMEM;
}
memset(lc->sync_bits, (sync == NOSYNC) ? -1 : 0, bitset_size);
lc->sync_count = (sync == NOSYNC) ? region_count : 0;
lc->recovering_bits = vzalloc(bitset_size);
if (!lc->recovering_bits) {
DMWARN("couldn't allocate sync bitset");
vfree(lc->sync_bits);
if (!dev)
vfree(lc->clean_bits);
else
dm_io_client_destroy(lc->io_req.client);
vfree(lc->disk_header);
kfree(lc);
return -ENOMEM;
}
lc->sync_search = 0;
log->context = lc;
return 0;
}
/*
* userspace_ctr
*
* argv contains:
* <UUID> [integrated_flush] <other args>
* Where 'other args' are the userspace implementation-specific log
* arguments.
*
* Example:
* <UUID> [integrated_flush] clustered-disk <arg count> <log dev>
* <region_size> [[no]sync]
*
* This module strips off the <UUID> and uses it for identification
* purposes when communicating with userspace about a log.
*
* If integrated_flush is defined, the kernel combines flush
* and mark requests.
*
* The rest of the line, beginning with 'clustered-disk', is passed
* to the userspace ctr function.
*/
static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
unsigned argc, char **argv)
{
int r = 0;
int str_size;
char *ctr_str = NULL;
struct log_c *lc = NULL;
uint64_t rdata;
size_t rdata_size = sizeof(rdata);
char *devices_rdata = NULL;
size_t devices_rdata_size = DM_NAME_LEN;
if (argc < 3) {
DMWARN("Too few arguments to userspace dirty log");
return -EINVAL;
}
lc = kzalloc(sizeof(*lc), GFP_KERNEL);
if (!lc) {
DMWARN("Unable to allocate userspace log context.");
return -ENOMEM;
}
/* The ptr value is sufficient for local unique id */
lc->luid = (unsigned long)lc;
lc->ti = ti;
if (strlen(argv[0]) > (DM_UUID_LEN - 1)) {
DMWARN("UUID argument too long.");
kfree(lc);
return -EINVAL;
}
lc->usr_argc = argc;
strncpy(lc->uuid, argv[0], DM_UUID_LEN);
argc--;
argv++;
spin_lock_init(&lc->flush_lock);
INIT_LIST_HEAD(&lc->mark_list);
INIT_LIST_HEAD(&lc->clear_list);
if (!strcasecmp(argv[0], "integrated_flush")) {
lc->integrated_flush = 1;
argc--;
argv++;
}
str_size = build_constructor_string(ti, argc, argv, &ctr_str);
if (str_size < 0) {
kfree(lc);
return str_size;
}
devices_rdata = kzalloc(devices_rdata_size, GFP_KERNEL);
if (!devices_rdata) {
DMERR("Failed to allocate memory for device information");
r = -ENOMEM;
goto out;
}
lc->flush_entry_pool = mempool_create_slab_pool(FLUSH_ENTRY_POOL_SIZE,
_flush_entry_cache);
if (!lc->flush_entry_pool) {
DMERR("Failed to create flush_entry_pool");
r = -ENOMEM;
goto out;
}
/*
* Send table string and get back any opened device.
*/
r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_CTR,
ctr_str, str_size,
devices_rdata, &devices_rdata_size);
if (r < 0) {
if (r == -ESRCH)
DMERR("Userspace log server not found");
else
DMERR("Userspace log server failed to create log");
goto out;
}
/* Since the region size does not change, get it now */
rdata_size = sizeof(rdata);
r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_GET_REGION_SIZE,
NULL, 0, (char *)&rdata, &rdata_size);
if (r) {
DMERR("Failed to get region size of dirty log");
goto out;
}
lc->region_size = (uint32_t)rdata;
lc->region_count = dm_sector_div_up(ti->len, lc->region_size);
if (devices_rdata_size) {
if (devices_rdata[devices_rdata_size - 1] != '\0') {
DMERR("DM_ULOG_CTR device return string not properly terminated");
r = -EINVAL;
goto out;
}
r = dm_get_device(ti, devices_rdata,
dm_table_get_mode(ti->table), &lc->log_dev);
if (r)
DMERR("Failed to register %s with device-mapper",
devices_rdata);
}
if (lc->integrated_flush) {
lc->dmlog_wq = alloc_workqueue("dmlogd", WQ_MEM_RECLAIM, 0);
if (!lc->dmlog_wq) {
DMERR("couldn't start dmlogd");
r = -ENOMEM;
goto out;
}
INIT_DELAYED_WORK(&lc->flush_log_work, do_flush);
atomic_set(&lc->sched_flush, 0);
}
out:
kfree(devices_rdata);
if (r) {
if (lc->flush_entry_pool)
mempool_destroy(lc->flush_entry_pool);
kfree(lc);
kfree(ctr_str);
} else {
lc->usr_argv_str = ctr_str;
log->context = lc;
}
return r;
}
static int create_log_context(struct dirty_log *log, struct dm_target *ti,
unsigned int argc, char **argv,
struct dm_dev *dev)
{
enum sync sync = DEFAULTSYNC;
struct log_c *lc;
uint32_t region_size;
unsigned int region_count;
size_t bitset_size, buf_size;
if (argc < 1 || argc > 2) {
DMWARN("wrong number of arguments to mirror log");
return -EINVAL;
}
if (argc > 1) {
if (!strcmp(argv[1], "sync"))
sync = FORCESYNC;
else if (!strcmp(argv[1], "nosync"))
sync = NOSYNC;
else {
DMWARN("unrecognised sync argument to mirror log: %s",
argv[1]);
return -EINVAL;
}
}
if (sscanf(argv[0], "%u", ®ion_size) != 1) {
DMWARN("invalid region size string");
return -EINVAL;
}
region_count = dm_sector_div_up(ti->len, region_size);
lc = kmalloc(sizeof(*lc), GFP_KERNEL);
if (!lc) {
DMWARN("couldn't allocate core log");
return -ENOMEM;
}
lc->ti = ti;
lc->touched = 0;
lc->region_size = region_size;
lc->region_count = region_count;
lc->sync = sync;
/*
* Work out how many "unsigned long"s we need to hold the bitset.
*/
bitset_size = dm_round_up(region_count,
sizeof(*lc->clean_bits) << BYTE_SHIFT);
bitset_size >>= BYTE_SHIFT;
lc->bitset_uint32_count = bitset_size / sizeof(*lc->clean_bits);
/*
* Disk log?
*/
if (!dev) {
lc->clean_bits = vmalloc(bitset_size);
if (!lc->clean_bits) {
DMWARN("couldn't allocate clean bitset");
kfree(lc);
return -ENOMEM;
}
lc->disk_header = NULL;
} else {
lc->log_dev = dev;
lc->header_location.bdev = lc->log_dev->bdev;
lc->header_location.sector = 0;
/*
* Buffer holds both header and bitset.
*/
buf_size = dm_round_up((LOG_OFFSET << SECTOR_SHIFT) +
bitset_size, ti->limits.hardsect_size);
lc->header_location.count = buf_size >> SECTOR_SHIFT;
lc->disk_header = vmalloc(buf_size);
if (!lc->disk_header) {
DMWARN("couldn't allocate disk log buffer");
kfree(lc);
return -ENOMEM;
}
lc->clean_bits = (void *)lc->disk_header +
(LOG_OFFSET << SECTOR_SHIFT);
}
memset(lc->clean_bits, -1, bitset_size);
lc->sync_bits = vmalloc(bitset_size);
if (!lc->sync_bits) {
DMWARN("couldn't allocate sync bitset");
if (!dev)
vfree(lc->clean_bits);
vfree(lc->disk_header);
kfree(lc);
return -ENOMEM;
}
memset(lc->sync_bits, (sync == NOSYNC) ? -1 : 0, bitset_size);
lc->sync_count = (sync == NOSYNC) ? region_count : 0;
lc->recovering_bits = vmalloc(bitset_size);
if (!lc->recovering_bits) {
DMWARN("couldn't allocate sync bitset");
vfree(lc->sync_bits);
if (!dev)
vfree(lc->clean_bits);
vfree(lc->disk_header);
kfree(lc);
return -ENOMEM;
}
memset(lc->recovering_bits, 0, bitset_size);
lc->sync_search = 0;
log->context = lc;
return 0;
}
static int core_ctr(struct dirty_log *log, struct dm_target *ti,
unsigned int argc, char **argv)
{
enum sync sync = DEFAULTSYNC;
int failure_response = DMLOG_IOERR_IGNORE;
struct log_c *lc;
uint32_t region_size;
unsigned int region_count;
size_t bitset_size;
unsigned i;
if (argc < 1 || argc > 3) {
DMWARN("wrong number of arguments to mirror log");
return -EINVAL;
}
for (i = 1; i < argc; i++) {
if (!strcmp(argv[i], "sync"))
sync = FORCESYNC;
else if (!strcmp(argv[i], "nosync"))
sync = NOSYNC;
else if (!strcmp(argv[i], "block_on_error"))
failure_response = DMLOG_IOERR_BLOCK;
else {
DMWARN("unrecognised sync argument to mirror log: %s",
argv[i]);
return -EINVAL;
}
}
if (sscanf(argv[0], "%u", ®ion_size) != 1) {
DMWARN("invalid region size string");
return -EINVAL;
}
region_count = dm_sector_div_up(ti->len, region_size);
lc = kmalloc(sizeof(*lc), GFP_KERNEL);
if (!lc) {
DMWARN("couldn't allocate core log");
return -ENOMEM;
}
lc->ti = ti;
lc->touched = 0;
lc->region_size = region_size;
lc->region_count = region_count;
lc->sync = sync;
lc->failure_response = failure_response;
/*
* Work out how many "unsigned long"s we need to hold the bitset.
*/
bitset_size = dm_round_up(region_count,
sizeof(uint32_t) << BYTE_SHIFT);
bitset_size >>= BYTE_SHIFT;
lc->bitset_uint32_count = bitset_size / sizeof(uint32_t);
lc->clean_bits = vmalloc(bitset_size);
if (!lc->clean_bits) {
DMWARN("couldn't allocate clean bitset");
kfree(lc);
return -ENOMEM;
}
memset(lc->clean_bits, -1, bitset_size);
lc->sync_bits = vmalloc(bitset_size);
if (!lc->sync_bits) {
DMWARN("couldn't allocate sync bitset");
vfree(lc->clean_bits);
kfree(lc);
return -ENOMEM;
}
memset(lc->sync_bits, (sync == NOSYNC) ? -1 : 0, bitset_size);
lc->sync_count = (sync == NOSYNC) ? region_count : 0;
lc->recovering_bits = vmalloc(bitset_size);
if (!lc->recovering_bits) {
DMWARN("couldn't allocate recovering bitset");
vfree(lc->sync_bits);
vfree(lc->clean_bits);
kfree(lc);
return -ENOMEM;
}
memset(lc->recovering_bits, 0, bitset_size);
lc->sync_search = 0;
log->context = lc;
return 0;
}
/*
* userspace_ctr
*
* argv contains:
* <UUID> <other args>
* Where 'other args' is the userspace implementation specific log
* arguments. An example might be:
* <UUID> clustered_disk <arg count> <log dev> <region_size> [[no]sync]
*
* So, this module will strip off the <UUID> for identification purposes
* when communicating with userspace about a log; but will pass on everything
* else.
*/
static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
unsigned argc, char **argv)
{
int r = 0;
int str_size;
char *ctr_str = NULL;
struct log_c *lc = NULL;
uint64_t rdata;
size_t rdata_size = sizeof(rdata);
if (argc < 3) {
DMWARN("Too few arguments to userspace dirty log");
return -EINVAL;
}
lc = kmalloc(sizeof(*lc), GFP_KERNEL);
if (!lc) {
DMWARN("Unable to allocate userspace log context.");
return -ENOMEM;
}
/* The ptr value is sufficient for local unique id */
lc->luid = (unsigned long)lc;
lc->ti = ti;
if (strlen(argv[0]) > (DM_UUID_LEN - 1)) {
DMWARN("UUID argument too long.");
kfree(lc);
return -EINVAL;
}
strncpy(lc->uuid, argv[0], DM_UUID_LEN);
spin_lock_init(&lc->flush_lock);
INIT_LIST_HEAD(&lc->mark_list);
INIT_LIST_HEAD(&lc->clear_list);
str_size = build_constructor_string(ti, argc - 1, argv + 1, &ctr_str);
if (str_size < 0) {
kfree(lc);
return str_size;
}
/* Send table string */
r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_CTR,
ctr_str, str_size, NULL, NULL);
if (r < 0) {
if (r == -ESRCH)
DMERR("Userspace log server not found");
else
DMERR("Userspace log server failed to create log");
goto out;
}
/* Since the region size does not change, get it now */
rdata_size = sizeof(rdata);
r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_GET_REGION_SIZE,
NULL, 0, (char *)&rdata, &rdata_size);
if (r) {
DMERR("Failed to get region size of dirty log");
goto out;
}
lc->region_size = (uint32_t)rdata;
lc->region_count = dm_sector_div_up(ti->len, lc->region_size);
out:
if (r) {
kfree(lc);
kfree(ctr_str);
} else {
lc->usr_argv_str = ctr_str;
lc->usr_argc = argc;
log->context = lc;
}
return r;
}
