diff options
Diffstat (limited to 'drivers/md/dm-log-writes.c')
| -rw-r--r-- | drivers/md/dm-log-writes.c | 217 |
1 files changed, 202 insertions, 15 deletions
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 534a254eb977..189badbeddaf 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -10,9 +10,11 @@ #include <linux/init.h> #include <linux/blkdev.h> #include <linux/bio.h> +#include <linux/dax.h> #include <linux/slab.h> #include <linux/kthread.h> #include <linux/freezer.h> +#include <linux/uio.h> #define DM_MSG_PREFIX "log-writes" @@ -100,6 +102,7 @@ struct log_writes_c { struct dm_dev *logdev; u64 logged_entries; u32 sectorsize; + u32 sectorshift; atomic_t io_blocks; atomic_t pending_blocks; sector_t next_sector; @@ -128,6 +131,18 @@ struct per_bio_data { struct pending_block *block; }; +static inline sector_t bio_to_dev_sectors(struct log_writes_c *lc, + sector_t sectors) +{ + return sectors >> (lc->sectorshift - SECTOR_SHIFT); +} + +static inline sector_t dev_to_bio_sectors(struct log_writes_c *lc, + sector_t sectors) +{ + return sectors << (lc->sectorshift - SECTOR_SHIFT); +} + static void put_pending_block(struct log_writes_c *lc) { if (atomic_dec_and_test(&lc->pending_blocks)) { @@ -233,27 +248,108 @@ error: return -1; } +static int write_inline_data(struct log_writes_c *lc, void *entry, + size_t entrylen, void *data, size_t datalen, + sector_t sector) +{ + int num_pages, bio_pages, pg_datalen, pg_sectorlen, i; + struct page *page; + struct bio *bio; + size_t ret; + void *ptr; + + while (datalen) { + num_pages = ALIGN(datalen, PAGE_SIZE) >> PAGE_SHIFT; + bio_pages = min(num_pages, BIO_MAX_PAGES); + + atomic_inc(&lc->io_blocks); + + bio = bio_alloc(GFP_KERNEL, bio_pages); + if (!bio) { + DMERR("Couldn't alloc inline data bio"); + goto error; + } + + bio->bi_iter.bi_size = 0; + bio->bi_iter.bi_sector = sector; + bio_set_dev(bio, lc->logdev->bdev); + bio->bi_end_io = log_end_io; + bio->bi_private = lc; + bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + + for (i = 0; i < bio_pages; i++) { + pg_datalen = min_t(int, datalen, PAGE_SIZE); + pg_sectorlen = ALIGN(pg_datalen, lc->sectorsize); + + page = alloc_page(GFP_KERNEL); + if (!page) { + DMERR("Couldn't alloc inline data page"); + goto error_bio; + } + + ptr = kmap_atomic(page); + memcpy(ptr, data, pg_datalen); + if (pg_sectorlen > pg_datalen) + memset(ptr + pg_datalen, 0, pg_sectorlen - pg_datalen); + kunmap_atomic(ptr); + + ret = bio_add_page(bio, page, pg_sectorlen, 0); + if (ret != pg_sectorlen) { + DMERR("Couldn't add page of inline data"); + __free_page(page); + goto error_bio; + } + + datalen -= pg_datalen; + data += pg_datalen; + } + submit_bio(bio); + + sector += bio_pages * PAGE_SECTORS; + } + return 0; +error_bio: + bio_free_pages(bio); + bio_put(bio); +error: + put_io_block(lc); + return -1; +} + static int log_one_block(struct log_writes_c *lc, struct pending_block *block, sector_t sector) { struct bio *bio; struct log_write_entry entry; - size_t ret; + size_t metadatalen, ret; int i; entry.sector = cpu_to_le64(block->sector); entry.nr_sectors = cpu_to_le64(block->nr_sectors); entry.flags = cpu_to_le64(block->flags); entry.data_len = cpu_to_le64(block->datalen); + + metadatalen = (block->flags & LOG_MARK_FLAG) ? block->datalen : 0; if (write_metadata(lc, &entry, sizeof(entry), block->data, - block->datalen, sector)) { + metadatalen, sector)) { free_pending_block(lc, block); return -1; } + sector += dev_to_bio_sectors(lc, 1); + + if (block->datalen && metadatalen == 0) { + if (write_inline_data(lc, &entry, sizeof(entry), block->data, + block->datalen, sector)) { + free_pending_block(lc, block); + return -1; + } + /* we don't support both inline data & bio data */ + goto out; + } + if (!block->vec_cnt) goto out; - sector++; atomic_inc(&lc->io_blocks); bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt, BIO_MAX_PAGES)); @@ -354,10 +450,9 @@ static int log_writes_kthread(void *arg) goto next; sector = lc->next_sector; - if (block->flags & LOG_DISCARD_FLAG) - lc->next_sector++; - else - lc->next_sector += block->nr_sectors + 1; + if (!(block->flags & LOG_DISCARD_FLAG)) + lc->next_sector += dev_to_bio_sectors(lc, block->nr_sectors); + lc->next_sector += dev_to_bio_sectors(lc, 1); /* * Apparently the size of the device may not be known @@ -399,7 +494,7 @@ next: if (!try_to_freeze()) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop() && - !atomic_read(&lc->pending_blocks)) + list_empty(&lc->logging_blocks)) schedule(); __set_current_state(TASK_RUNNING); } @@ -435,7 +530,6 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv) INIT_LIST_HEAD(&lc->unflushed_blocks); INIT_LIST_HEAD(&lc->logging_blocks); init_waitqueue_head(&lc->wait); - lc->sectorsize = 1 << SECTOR_SHIFT; atomic_set(&lc->io_blocks, 0); atomic_set(&lc->pending_blocks, 0); @@ -455,6 +549,8 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } + lc->sectorsize = bdev_logical_block_size(lc->dev->bdev); + lc->sectorshift = ilog2(lc->sectorsize); lc->log_kthread = kthread_run(log_writes_kthread, lc, "log-write"); if (IS_ERR(lc->log_kthread)) { ret = PTR_ERR(lc->log_kthread); @@ -464,8 +560,12 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - /* We put the super at sector 0, start logging at sector 1 */ - lc->next_sector = 1; + /* + * next_sector is in 512b sectors to correspond to what bi_sector expects. + * The super starts at sector 0, and the next_sector is the next logical + * one based on the sectorsize of the device. + */ + lc->next_sector = lc->sectorsize >> SECTOR_SHIFT; lc->logging_enabled = true; lc->end_sector = logdev_last_sector(lc); lc->device_supports_discard = true; @@ -510,6 +610,51 @@ static int log_mark(struct log_writes_c *lc, char *data) return 0; } +static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes, + struct iov_iter *i) +{ + struct pending_block *block; + + if (!bytes) + return 0; + + block = kzalloc(sizeof(struct pending_block), GFP_KERNEL); + if (!block) { + DMERR("Error allocating dax pending block"); + return -ENOMEM; + } + + block->data = kzalloc(bytes, GFP_KERNEL); + if (!block->data) { + DMERR("Error allocating dax data space"); + kfree(block); + return -ENOMEM; + } + + /* write data provided via the iterator */ + if (!copy_from_iter(block->data, bytes, i)) { + DMERR("Error copying dax data"); + kfree(block->data); + kfree(block); + return -EIO; + } + + /* rewind the iterator so that the block driver can use it */ + iov_iter_revert(i, bytes); + + block->datalen = bytes; + block->sector = bio_to_dev_sectors(lc, sector); + block->nr_sectors = ALIGN(bytes, lc->sectorsize) >> lc->sectorshift; + + atomic_inc(&lc->pending_blocks); + spin_lock_irq(&lc->blocks_lock); + list_add_tail(&block->list, &lc->unflushed_blocks); + spin_unlock_irq(&lc->blocks_lock); + wake_up_process(lc->log_kthread); + + return 0; +} + static void log_writes_dtr(struct dm_target *ti) { struct log_writes_c *lc = ti->private; @@ -599,8 +744,8 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio) if (discard_bio) block->flags |= LOG_DISCARD_FLAG; - block->sector = bio->bi_iter.bi_sector; - block->nr_sectors = bio_sectors(bio); + block->sector = bio_to_dev_sectors(lc, bio->bi_iter.bi_sector); + block->nr_sectors = bio_to_dev_sectors(lc, bio_sectors(bio)); /* We don't need the data, just submit */ if (discard_bio) { @@ -767,14 +912,54 @@ static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limit if (!q || !blk_queue_discard(q)) { lc->device_supports_discard = false; - limits->discard_granularity = 1 << SECTOR_SHIFT; + limits->discard_granularity = lc->sectorsize; limits->max_discard_sectors = (UINT_MAX >> SECTOR_SHIFT); } + limits->logical_block_size = bdev_logical_block_size(lc->dev->bdev); + limits->physical_block_size = bdev_physical_block_size(lc->dev->bdev); + limits->io_min = limits->physical_block_size; +} + +static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, + long nr_pages, void **kaddr, pfn_t *pfn) +{ + struct log_writes_c *lc = ti->private; + sector_t sector = pgoff * PAGE_SECTORS; + int ret; + + ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages * PAGE_SIZE, &pgoff); + if (ret) + return ret; + return dax_direct_access(lc->dev->dax_dev, pgoff, nr_pages, kaddr, pfn); +} + +static size_t log_writes_dax_copy_from_iter(struct dm_target *ti, + pgoff_t pgoff, void *addr, size_t bytes, + struct iov_iter *i) +{ + struct log_writes_c *lc = ti->private; + sector_t sector = pgoff * PAGE_SECTORS; + int err; + + if (bdev_dax_pgoff(lc->dev->bdev, sector, ALIGN(bytes, PAGE_SIZE), &pgoff)) + return 0; + + /* Don't bother doing anything if logging has been disabled */ + if (!lc->logging_enabled) + goto dax_copy; + + err = log_dax(lc, sector, bytes, i); + if (err) { + DMWARN("Error %d logging DAX write", err); + return 0; + } +dax_copy: + return dax_copy_from_iter(lc->dev->dax_dev, pgoff, addr, bytes, i); } static struct target_type log_writes_target = { .name = "log-writes", - .version = {1, 0, 0}, + .version = {1, 1, 0}, .module = THIS_MODULE, .ctr = log_writes_ctr, .dtr = log_writes_dtr, @@ -785,6 +970,8 @@ static struct target_type log_writes_target = { .message = log_writes_message, .iterate_devices = log_writes_iterate_devices, .io_hints = log_writes_io_hints, + .direct_access = log_writes_dax_direct_access, + .dax_copy_from_iter = log_writes_dax_copy_from_iter, }; static int __init dm_log_writes_init(void) |