#include "dev-replace.h"
#include "rcu-string.h"
#include "zoned.h"
+#include "file-item.h"
static struct bio_set btrfs_bioset;
+static struct bio_set btrfs_repair_bioset;
+static mempool_t btrfs_failed_bio_pool;
+
+struct btrfs_failed_bio {
+ struct btrfs_bio *bbio;
+ int num_copies;
+ atomic_t repair_count;
+};
/*
* Initialize a btrfs_bio structure. This skips the embedded bio itself as it
* is already initialized by the block layer.
*/
static inline void btrfs_bio_init(struct btrfs_bio *bbio,
+ struct btrfs_inode *inode,
btrfs_bio_end_io_t end_io, void *private)
{
memset(bbio, 0, offsetof(struct btrfs_bio, bio));
+ bbio->inode = inode;
bbio->end_io = end_io;
bbio->private = private;
}
* a mempool.
*/
struct bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
+ struct btrfs_inode *inode,
btrfs_bio_end_io_t end_io, void *private)
{
struct bio *bio;
bio = bio_alloc_bioset(NULL, nr_vecs, opf, GFP_NOFS, &btrfs_bioset);
- btrfs_bio_init(btrfs_bio(bio), end_io, private);
+ btrfs_bio_init(btrfs_bio(bio), inode, end_io, private);
return bio;
}
struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size,
+ struct btrfs_inode *inode,
btrfs_bio_end_io_t end_io, void *private)
{
struct bio *bio;
bio = bio_alloc_clone(orig->bi_bdev, orig, GFP_NOFS, &btrfs_bioset);
bbio = btrfs_bio(bio);
- btrfs_bio_init(bbio, end_io, private);
+ btrfs_bio_init(bbio, inode, end_io, private);
bio_trim(bio, offset >> 9, size >> 9);
- bbio->iter = bio->bi_iter;
return bio;
}
+static int next_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
+{
+ if (cur_mirror == fbio->num_copies)
+ return cur_mirror + 1 - fbio->num_copies;
+ return cur_mirror + 1;
+}
+
+static int prev_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
+{
+ if (cur_mirror == 1)
+ return fbio->num_copies;
+ return cur_mirror - 1;
+}
+
+static void btrfs_repair_done(struct btrfs_failed_bio *fbio)
+{
+ if (atomic_dec_and_test(&fbio->repair_count)) {
+ fbio->bbio->end_io(fbio->bbio);
+ mempool_free(fbio, &btrfs_failed_bio_pool);
+ }
+}
+
+static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio,
+ struct btrfs_device *dev)
+{
+ struct btrfs_failed_bio *fbio = repair_bbio->private;
+ struct btrfs_inode *inode = repair_bbio->inode;
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
+ struct bio_vec *bv = bio_first_bvec_all(&repair_bbio->bio);
+ int mirror = repair_bbio->mirror_num;
+
+ if (repair_bbio->bio.bi_status ||
+ !btrfs_data_csum_ok(repair_bbio, dev, 0, bv)) {
+ bio_reset(&repair_bbio->bio, NULL, REQ_OP_READ);
+ repair_bbio->bio.bi_iter = repair_bbio->saved_iter;
+
+ mirror = next_repair_mirror(fbio, mirror);
+ if (mirror == fbio->bbio->mirror_num) {
+ btrfs_debug(fs_info, "no mirror left");
+ fbio->bbio->bio.bi_status = BLK_STS_IOERR;
+ goto done;
+ }
+
+ btrfs_submit_bio(fs_info, &repair_bbio->bio, mirror);
+ return;
+ }
+
+ do {
+ mirror = prev_repair_mirror(fbio, mirror);
+ btrfs_repair_io_failure(fs_info, btrfs_ino(inode),
+ repair_bbio->file_offset, fs_info->sectorsize,
+ repair_bbio->saved_iter.bi_sector << SECTOR_SHIFT,
+ bv->bv_page, bv->bv_offset, mirror);
+ } while (mirror != fbio->bbio->mirror_num);
+
+done:
+ btrfs_repair_done(fbio);
+ bio_put(&repair_bbio->bio);
+}
+
+/*
+ * Try to kick off a repair read to the next available mirror for a bad sector.
+ *
+ * This primarily tries to recover good data to serve the actual read request,
+ * but also tries to write the good data back to the bad mirror(s) when a
+ * read succeeded to restore the redundancy.
+ */
+static struct btrfs_failed_bio *repair_one_sector(struct btrfs_bio *failed_bbio,
+ u32 bio_offset,
+ struct bio_vec *bv,
+ struct btrfs_failed_bio *fbio)
+{
+ struct btrfs_inode *inode = failed_bbio->inode;
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
+ const u32 sectorsize = fs_info->sectorsize;
+ const u64 logical = (failed_bbio->saved_iter.bi_sector << SECTOR_SHIFT);
+ struct btrfs_bio *repair_bbio;
+ struct bio *repair_bio;
+ int num_copies;
+ int mirror;
+
+ btrfs_debug(fs_info, "repair read error: read error at %llu",
+ failed_bbio->file_offset + bio_offset);
+
+ num_copies = btrfs_num_copies(fs_info, logical, sectorsize);
+ if (num_copies == 1) {
+ btrfs_debug(fs_info, "no copy to repair from");
+ failed_bbio->bio.bi_status = BLK_STS_IOERR;
+ return fbio;
+ }
+
+ if (!fbio) {
+ fbio = mempool_alloc(&btrfs_failed_bio_pool, GFP_NOFS);
+ fbio->bbio = failed_bbio;
+ fbio->num_copies = num_copies;
+ atomic_set(&fbio->repair_count, 1);
+ }
+
+ atomic_inc(&fbio->repair_count);
+
+ repair_bio = bio_alloc_bioset(NULL, 1, REQ_OP_READ, GFP_NOFS,
+ &btrfs_repair_bioset);
+ repair_bio->bi_iter.bi_sector = failed_bbio->saved_iter.bi_sector;
+ bio_add_page(repair_bio, bv->bv_page, bv->bv_len, bv->bv_offset);
+
+ repair_bbio = btrfs_bio(repair_bio);
+ btrfs_bio_init(repair_bbio, failed_bbio->inode, NULL, fbio);
+ repair_bbio->file_offset = failed_bbio->file_offset + bio_offset;
+
+ mirror = next_repair_mirror(fbio, failed_bbio->mirror_num);
+ btrfs_debug(fs_info, "submitting repair read to mirror %d", mirror);
+ btrfs_submit_bio(fs_info, repair_bio, mirror);
+ return fbio;
+}
+
+static void btrfs_check_read_bio(struct btrfs_bio *bbio, struct btrfs_device *dev)
+{
+ struct btrfs_inode *inode = bbio->inode;
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
+ u32 sectorsize = fs_info->sectorsize;
+ struct bvec_iter *iter = &bbio->saved_iter;
+ blk_status_t status = bbio->bio.bi_status;
+ struct btrfs_failed_bio *fbio = NULL;
+ u32 offset = 0;
+
+ /*
+ * Hand off repair bios to the repair code as there is no upper level
+ * submitter for them.
+ */
+ if (bbio->bio.bi_pool == &btrfs_repair_bioset) {
+ btrfs_end_repair_bio(bbio, dev);
+ return;
+ }
+
+ /* Clear the I/O error. A failed repair will reset it. */
+ bbio->bio.bi_status = BLK_STS_OK;
+
+ while (iter->bi_size) {
+ struct bio_vec bv = bio_iter_iovec(&bbio->bio, *iter);
+
+ bv.bv_len = min(bv.bv_len, sectorsize);
+ if (status || !btrfs_data_csum_ok(bbio, dev, offset, &bv))
+ fbio = repair_one_sector(bbio, offset, &bv, fbio);
+
+ bio_advance_iter_single(&bbio->bio, iter, sectorsize);
+ offset += sectorsize;
+ }
+
+ if (bbio->csum != bbio->csum_inline)
+ kfree(bbio->csum);
+
+ if (fbio)
+ btrfs_repair_done(fbio);
+ else
+ bbio->end_io(bbio);
+}
+
static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev)
{
if (!dev || !dev->bdev)
{
struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, end_io_work);
- bbio->end_io(bbio);
+ /* Metadata reads are checked and repaired by the submitter. */
+ if (bbio->bio.bi_opf & REQ_META)
+ bbio->end_io(bbio);
+ else
+ btrfs_check_read_bio(bbio, bbio->bio.bi_private);
}
static void btrfs_simple_end_io(struct bio *bio)
{
- struct btrfs_fs_info *fs_info = bio->bi_private;
struct btrfs_bio *bbio = btrfs_bio(bio);
+ struct btrfs_device *dev = bio->bi_private;
+ struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info;
btrfs_bio_counter_dec(fs_info);
if (bio->bi_status)
- btrfs_log_dev_io_error(bio, bbio->device);
+ btrfs_log_dev_io_error(bio, dev);
if (bio_op(bio) == REQ_OP_READ) {
INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work);
queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work);
} else {
+ if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+ btrfs_record_physical_zoned(bbio);
bbio->end_io(bbio);
}
}
btrfs_bio_counter_dec(bioc->fs_info);
bbio->mirror_num = bioc->mirror_num;
- bbio->end_io(bbio);
+ if (bio_op(bio) == REQ_OP_READ && !(bbio->bio.bi_opf & REQ_META))
+ btrfs_check_read_bio(bbio, NULL);
+ else
+ bbio->end_io(bbio);
btrfs_put_bioc(bioc);
}
btrfs_submit_dev_bio(bioc->stripes[dev_nr].dev, bio);
}
+static void __btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc,
+ struct btrfs_io_stripe *smap, int mirror_num)
+{
+ /* Do not leak our private flag into the block layer. */
+ bio->bi_opf &= ~REQ_BTRFS_ONE_ORDERED;
+
+ if (!bioc) {
+ /* Single mirror read/write fast path. */
+ btrfs_bio(bio)->mirror_num = mirror_num;
+ bio->bi_iter.bi_sector = smap->physical >> SECTOR_SHIFT;
+ bio->bi_private = smap->dev;
+ bio->bi_end_io = btrfs_simple_end_io;
+ btrfs_submit_dev_bio(smap->dev, bio);
+ } else if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+ /* Parity RAID write or read recovery. */
+ bio->bi_private = bioc;
+ bio->bi_end_io = btrfs_raid56_end_io;
+ if (bio_op(bio) == REQ_OP_READ)
+ raid56_parity_recover(bio, bioc, mirror_num);
+ else
+ raid56_parity_write(bio, bioc);
+ } else {
+ /* Write to multiple mirrors. */
+ int total_devs = bioc->num_stripes;
+
+ bioc->orig_bio = bio;
+ for (int dev_nr = 0; dev_nr < total_devs; dev_nr++)
+ btrfs_submit_mirrored_bio(bioc, dev_nr);
+ }
+}
+
+static blk_status_t btrfs_bio_csum(struct btrfs_bio *bbio)
+{
+ if (bbio->bio.bi_opf & REQ_META)
+ return btree_csum_one_bio(&bbio->bio);
+ return btrfs_csum_one_bio(bbio);
+}
+
+/*
+ * Async submit bios are used to offload expensive checksumming onto the worker
+ * threads.
+ */
+struct async_submit_bio {
+ struct btrfs_bio *bbio;
+ struct btrfs_io_context *bioc;
+ struct btrfs_io_stripe smap;
+ int mirror_num;
+ struct btrfs_work work;
+};
+
+/*
+ * In order to insert checksums into the metadata in large chunks, we wait
+ * until bio submission time. All the pages in the bio are checksummed and
+ * sums are attached onto the ordered extent record.
+ *
+ * At IO completion time the csums attached on the ordered extent record are
+ * inserted into the btree.
+ */
+static void run_one_async_start(struct btrfs_work *work)
+{
+ struct async_submit_bio *async =
+ container_of(work, struct async_submit_bio, work);
+ blk_status_t ret;
+
+ ret = btrfs_bio_csum(async->bbio);
+ if (ret)
+ async->bbio->bio.bi_status = ret;
+}
+
+/*
+ * In order to insert checksums into the metadata in large chunks, we wait
+ * until bio submission time. All the pages in the bio are checksummed and
+ * sums are attached onto the ordered extent record.
+ *
+ * At IO completion time the csums attached on the ordered extent record are
+ * inserted into the tree.
+ */
+static void run_one_async_done(struct btrfs_work *work)
+{
+ struct async_submit_bio *async =
+ container_of(work, struct async_submit_bio, work);
+ struct bio *bio = &async->bbio->bio;
+
+ /* If an error occurred we just want to clean up the bio and move on. */
+ if (bio->bi_status) {
+ btrfs_bio_end_io(async->bbio, bio->bi_status);
+ return;
+ }
+
+ /*
+ * All of the bios that pass through here are from async helpers.
+ * Use REQ_CGROUP_PUNT to issue them from the owning cgroup's context.
+ * This changes nothing when cgroups aren't in use.
+ */
+ bio->bi_opf |= REQ_CGROUP_PUNT;
+ __btrfs_submit_bio(bio, async->bioc, &async->smap, async->mirror_num);
+}
+
+static void run_one_async_free(struct btrfs_work *work)
+{
+ kfree(container_of(work, struct async_submit_bio, work));
+}
+
+static bool should_async_write(struct btrfs_bio *bbio)
+{
+ /*
+ * If the I/O is not issued by fsync and friends, (->sync_writers != 0),
+ * then try to defer the submission to a workqueue to parallelize the
+ * checksum calculation.
+ */
+ if (atomic_read(&bbio->inode->sync_writers))
+ return false;
+
+ /*
+ * Submit metadata writes synchronously if the checksum implementation
+ * is fast, or we are on a zoned device that wants I/O to be submitted
+ * in order.
+ */
+ if (bbio->bio.bi_opf & REQ_META) {
+ struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info;
+
+ if (btrfs_is_zoned(fs_info))
+ return false;
+ if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags))
+ return false;
+ }
+
+ return true;
+}
+
+/*
+ * Submit bio to an async queue.
+ *
+ * Return true if the work has been succesfuly submitted, else false.
+ */
+static bool btrfs_wq_submit_bio(struct btrfs_bio *bbio,
+ struct btrfs_io_context *bioc,
+ struct btrfs_io_stripe *smap, int mirror_num)
+{
+ struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info;
+ struct async_submit_bio *async;
+
+ async = kmalloc(sizeof(*async), GFP_NOFS);
+ if (!async)
+ return false;
+
+ async->bbio = bbio;
+ async->bioc = bioc;
+ async->smap = *smap;
+ async->mirror_num = mirror_num;
+
+ btrfs_init_work(&async->work, run_one_async_start, run_one_async_done,
+ run_one_async_free);
+ if (op_is_sync(bbio->bio.bi_opf))
+ btrfs_queue_work(fs_info->hipri_workers, &async->work);
+ else
+ btrfs_queue_work(fs_info->workers, &async->work);
+ return true;
+}
+
void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror_num)
{
+ struct btrfs_bio *bbio = btrfs_bio(bio);
u64 logical = bio->bi_iter.bi_sector << 9;
u64 length = bio->bi_iter.bi_size;
u64 map_length = length;
struct btrfs_io_context *bioc = NULL;
struct btrfs_io_stripe smap;
- int ret;
+ blk_status_t ret;
+ int error;
btrfs_bio_counter_inc_blocked(fs_info);
- ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
- &bioc, &smap, &mirror_num, 1);
- if (ret) {
- btrfs_bio_counter_dec(fs_info);
- btrfs_bio_end_io(btrfs_bio(bio), errno_to_blk_status(ret));
- return;
+ error = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
+ &bioc, &smap, &mirror_num, 1);
+ if (error) {
+ ret = errno_to_blk_status(error);
+ goto fail;
}
if (map_length < length) {
BUG();
}
- if (!bioc) {
- /* Single mirror read/write fast path */
- btrfs_bio(bio)->mirror_num = mirror_num;
- btrfs_bio(bio)->device = smap.dev;
- bio->bi_iter.bi_sector = smap.physical >> SECTOR_SHIFT;
- bio->bi_private = fs_info;
- bio->bi_end_io = btrfs_simple_end_io;
- btrfs_submit_dev_bio(smap.dev, bio);
- } else if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
- /* Parity RAID write or read recovery */
- bio->bi_private = bioc;
- bio->bi_end_io = btrfs_raid56_end_io;
- if (bio_op(bio) == REQ_OP_READ)
- raid56_parity_recover(bio, bioc, mirror_num);
- else
- raid56_parity_write(bio, bioc);
- } else {
- /* Write to multiple mirrors */
- int total_devs = bioc->num_stripes;
- int dev_nr;
+ /*
+ * Save the iter for the end_io handler and preload the checksums for
+ * data reads.
+ */
+ if (bio_op(bio) == REQ_OP_READ && !(bio->bi_opf & REQ_META)) {
+ bbio->saved_iter = bio->bi_iter;
+ ret = btrfs_lookup_bio_sums(bbio);
+ if (ret)
+ goto fail;
+ }
- bioc->orig_bio = bio;
- for (dev_nr = 0; dev_nr < total_devs; dev_nr++)
- btrfs_submit_mirrored_bio(bioc, dev_nr);
+ if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
+ if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+ ret = btrfs_extract_ordered_extent(btrfs_bio(bio));
+ if (ret)
+ goto fail;
+ }
+
+ /*
+ * Csum items for reloc roots have already been cloned at this
+ * point, so they are handled as part of the no-checksum case.
+ */
+ if (!(bbio->inode->flags & BTRFS_INODE_NODATASUM) &&
+ !test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state) &&
+ !btrfs_is_data_reloc_root(bbio->inode->root)) {
+ if (should_async_write(bbio) &&
+ btrfs_wq_submit_bio(bbio, bioc, &smap, mirror_num))
+ return;
+
+ ret = btrfs_bio_csum(bbio);
+ if (ret)
+ goto fail;
+ }
}
+
+ __btrfs_submit_bio(bio, bioc, &smap, mirror_num);
+ return;
+
+fail:
+ btrfs_bio_counter_dec(fs_info);
+ btrfs_bio_end_io(bbio, ret);
}
/*
* RAID setup. Here we only want to write the one bad copy, so we do the
* mapping ourselves and submit the bio directly.
*
- * The I/O is issued sychronously to block the repair read completion from
+ * The I/O is issued synchronously to block the repair read completion from
* freeing the bio.
*/
int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
&map_length, &bioc, mirror_num);
if (ret)
goto out_counter_dec;
- BUG_ON(mirror_num != bioc->mirror_num);
+ /*
+ * This happens when dev-replace is also running, and the
+ * mirror_num indicates the dev-replace target.
+ *
+ * In this case, we don't need to do anything, as the read
+ * error just means the replace progress hasn't reached our
+ * read range, and later replace routine would handle it well.
+ */
+ if (mirror_num != bioc->mirror_num)
+ goto out_counter_dec;
}
sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
offsetof(struct btrfs_bio, bio),
BIOSET_NEED_BVECS))
return -ENOMEM;
+ if (bioset_init(&btrfs_repair_bioset, BIO_POOL_SIZE,
+ offsetof(struct btrfs_bio, bio),
+ BIOSET_NEED_BVECS))
+ goto out_free_bioset;
+ if (mempool_init_kmalloc_pool(&btrfs_failed_bio_pool, BIO_POOL_SIZE,
+ sizeof(struct btrfs_failed_bio)))
+ goto out_free_repair_bioset;
return 0;
+
+out_free_repair_bioset:
+ bioset_exit(&btrfs_repair_bioset);
+out_free_bioset:
+ bioset_exit(&btrfs_bioset);
+ return -ENOMEM;
}
void __cold btrfs_bioset_exit(void)
{
+ mempool_exit(&btrfs_failed_bio_pool);
+ bioset_exit(&btrfs_repair_bioset);
bioset_exit(&btrfs_bioset);
}