Hi Jens,
this series contains various cleanups for how bios are allocated or
initialized plus related fallout.
Diffstat:
Documentation/filesystems/f2fs.rst | 1
block/bio.c | 167 ++++++++++++++++++-------------------
block/blk-crypto-fallback.c | 2
block/blk-flush.c | 17 +--
drivers/block/drbd/drbd_actlog.c | 2
drivers/block/drbd/drbd_bitmap.c | 2
drivers/block/drbd/drbd_int.h | 2
drivers/block/drbd/drbd_main.c | 13 --
drivers/block/drbd/drbd_req.c | 5 -
drivers/block/drbd/drbd_req.h | 12 --
drivers/block/drbd/drbd_worker.c | 5 -
drivers/md/dm-clone-target.c | 14 ---
drivers/md/dm-zoned-metadata.c | 6 -
drivers/md/md.c | 48 +++-------
drivers/md/md.h | 2
drivers/md/raid1.c | 2
drivers/md/raid10.c | 2
drivers/md/raid5-ppl.c | 2
drivers/md/raid5.c | 108 +++++++++--------------
drivers/nvme/target/io-cmd-bdev.c | 2
fs/block_dev.c | 2
fs/btrfs/volumes.c | 2
fs/exfat/file.c | 2
fs/ext4/fast_commit.c | 4
fs/ext4/fsync.c | 2
fs/ext4/ialloc.c | 2
fs/ext4/super.c | 2
fs/f2fs/data.c | 28 ------
fs/f2fs/f2fs.h | 2
fs/f2fs/segment.c | 12 --
fs/f2fs/super.c | 1
fs/fat/file.c | 2
fs/hfsplus/inode.c | 2
fs/hfsplus/super.c | 2
fs/jbd2/checkpoint.c | 2
fs/jbd2/commit.c | 4
fs/jbd2/recovery.c | 2
fs/libfs.c | 2
fs/nfs/blocklayout/blocklayout.c | 5 -
fs/nilfs2/segbuf.c | 4
fs/nilfs2/the_nilfs.h | 2
fs/ocfs2/file.c | 2
fs/reiserfs/file.c | 2
fs/xfs/xfs_super.c | 2
fs/zonefs/super.c | 4
include/linux/bio.h | 6 -
include/linux/blkdev.h | 4
include/linux/swap.h | 1
mm/page_io.c | 45 ++-------
mm/swapfile.c | 10 --
50 files changed, 213 insertions(+), 363 deletions(-)
Use bio_alloc instead of open coding it.
Signed-off-by: Christoph Hellwig <[email protected]>
---
fs/zonefs/super.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index bec47f2d074beb..faea2ed34b4a37 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -678,7 +678,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
if (!nr_pages)
return 0;
- bio = bio_alloc_bioset(GFP_NOFS, nr_pages, &fs_bio_set);
+ bio = bio_alloc(GFP_NOFS, nr_pages);
if (!bio)
return -ENOMEM;
--
2.29.2
Use bio_kmalloc instead of open coding it.
Signed-off-by: Christoph Hellwig <[email protected]>
---
fs/btrfs/volumes.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0a6de859eb2226..584ba093cf4966 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -421,7 +421,7 @@ static struct btrfs_device *__alloc_device(struct btrfs_fs_info *fs_info)
* Preallocate a bio that's always going to be used for flushing device
* barriers and matches the device lifespan
*/
- dev->flush_bio = bio_alloc_bioset(GFP_KERNEL, 0, NULL);
+ dev->flush_bio = bio_kmalloc(GFP_KERNEL, 0);
if (!dev->flush_bio) {
kfree(dev);
return ERR_PTR(-ENOMEM);
--
2.29.2
Use bio_kmalloc instead of open coding it.
Signed-off-by: Christoph Hellwig <[email protected]>
---
block/blk-crypto-fallback.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
index 50c225398e4d60..e8327c50d7c9f4 100644
--- a/block/blk-crypto-fallback.c
+++ b/block/blk-crypto-fallback.c
@@ -164,7 +164,7 @@ static struct bio *blk_crypto_clone_bio(struct bio *bio_src)
struct bio_vec bv;
struct bio *bio;
- bio = bio_alloc_bioset(GFP_NOIO, bio_segments(bio_src), NULL);
+ bio = bio_kmalloc(GFP_NOIO, bio_segments(bio_src));
if (!bio)
return NULL;
bio->bi_bdev = bio_src->bi_bdev;
--
2.29.2
There is no point in allocating memory for a synchronous flush.
Signed-off-by: Christoph Hellwig <[email protected]>
---
block/blk-flush.c | 17 ++++++-----------
drivers/md/dm-zoned-metadata.c | 6 +++---
drivers/md/raid5-ppl.c | 2 +-
drivers/nvme/target/io-cmd-bdev.c | 2 +-
fs/block_dev.c | 2 +-
fs/exfat/file.c | 2 +-
fs/ext4/fast_commit.c | 4 ++--
fs/ext4/fsync.c | 2 +-
fs/ext4/ialloc.c | 2 +-
fs/ext4/super.c | 2 +-
fs/fat/file.c | 2 +-
fs/hfsplus/inode.c | 2 +-
fs/hfsplus/super.c | 2 +-
fs/jbd2/checkpoint.c | 2 +-
fs/jbd2/commit.c | 4 ++--
fs/jbd2/recovery.c | 2 +-
fs/libfs.c | 2 +-
fs/nilfs2/the_nilfs.h | 2 +-
fs/ocfs2/file.c | 2 +-
fs/reiserfs/file.c | 2 +-
fs/xfs/xfs_super.c | 2 +-
fs/zonefs/super.c | 2 +-
include/linux/blkdev.h | 4 ++--
23 files changed, 33 insertions(+), 38 deletions(-)
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 76c1624cb06c05..7942ca6ed3211c 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -432,23 +432,18 @@ void blk_insert_flush(struct request *rq)
/**
* blkdev_issue_flush - queue a flush
* @bdev: blockdev to issue flush for
- * @gfp_mask: memory allocation flags (for bio_alloc)
*
* Description:
* Issue a flush for the block device in question.
*/
-int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask)
+int blkdev_issue_flush(struct block_device *bdev)
{
- struct bio *bio;
- int ret = 0;
+ struct bio bio;
- bio = bio_alloc(gfp_mask, 0);
- bio_set_dev(bio, bdev);
- bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
-
- ret = submit_bio_wait(bio);
- bio_put(bio);
- return ret;
+ bio_init(&bio, NULL, 0);
+ bio_set_dev(&bio, bdev);
+ bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+ return submit_bio_wait(&bio);
}
EXPORT_SYMBOL(blkdev_issue_flush);
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index b298fefb022eb9..039d17b2893849 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -819,7 +819,7 @@ static int dmz_write_sb(struct dmz_metadata *zmd, unsigned int set)
ret = dmz_rdwr_block(dev, REQ_OP_WRITE, zmd->sb[set].block,
mblk->page);
if (ret == 0)
- ret = blkdev_issue_flush(dev->bdev, GFP_NOIO);
+ ret = blkdev_issue_flush(dev->bdev);
return ret;
}
@@ -862,7 +862,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd,
/* Flush drive cache (this will also sync data) */
if (ret == 0)
- ret = blkdev_issue_flush(dev->bdev, GFP_NOIO);
+ ret = blkdev_issue_flush(dev->bdev);
return ret;
}
@@ -933,7 +933,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
/* If there are no dirty metadata blocks, just flush the device cache */
if (list_empty(&write_list)) {
- ret = blkdev_issue_flush(dev->bdev, GFP_NOIO);
+ ret = blkdev_issue_flush(dev->bdev);
goto err;
}
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index d0f540296fe91e..e8c118e05dfd46 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -1037,7 +1037,7 @@ static int ppl_recover(struct ppl_log *log, struct ppl_header *pplhdr,
}
/* flush the disk cache after recovery if necessary */
- ret = blkdev_issue_flush(rdev->bdev, GFP_KERNEL);
+ ret = blkdev_issue_flush(rdev->bdev);
out:
__free_page(page);
return ret;
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index 125dde3f410ee7..bf6e0ac9ad2890 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -333,7 +333,7 @@ static void nvmet_bdev_execute_flush(struct nvmet_req *req)
u16 nvmet_bdev_flush(struct nvmet_req *req)
{
- if (blkdev_issue_flush(req->ns->bdev, GFP_KERNEL))
+ if (blkdev_issue_flush(req->ns->bdev))
return NVME_SC_INTERNAL | NVME_SC_DNR;
return 0;
}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 6f5bd9950baf45..bc957ef7cebaae 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -681,7 +681,7 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
* i_mutex and doing so causes performance issues with concurrent
* O_SYNC writers to a block device.
*/
- error = blkdev_issue_flush(bdev, GFP_KERNEL);
+ error = blkdev_issue_flush(bdev);
if (error == -EOPNOTSUPP)
error = 0;
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index a92478eabfa4e4..183ffdf4d43c5f 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -361,7 +361,7 @@ int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
if (err)
return err;
- return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
+ return blkdev_issue_flush(inode->i_sb->s_bdev);
}
const struct file_operations exfat_file_operations = {
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 0a14a7c87bf82e..6e8208acfc62ac 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1076,7 +1076,7 @@ static int ext4_fc_perform_commit(journal_t *journal)
* flush before we start writing fast commit blocks.
*/
if (journal->j_fs_dev != journal->j_dev)
- blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS);
+ blkdev_issue_flush(journal->j_fs_dev);
blk_start_plug(&plug);
if (sbi->s_fc_bytes == 0) {
@@ -1535,7 +1535,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
out:
iput(inode);
if (!ret)
- blkdev_issue_flush(sb->s_bdev, GFP_KERNEL);
+ blkdev_issue_flush(sb->s_bdev);
return 0;
}
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 113bfb023a4a09..027a7d7037a07b 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -174,7 +174,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
ret = ext4_fsync_journal(inode, datasync, &needs_barrier);
if (needs_barrier) {
- err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
+ err = blkdev_issue_flush(inode->i_sb->s_bdev);
if (!ret)
ret = err;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index b215c564bc318a..20f2fcb799f55f 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1583,7 +1583,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
if (ret < 0)
goto err_out;
if (barrier)
- blkdev_issue_flush(sb->s_bdev, GFP_NOFS);
+ blkdev_issue_flush(sb->s_bdev);
skip_zeroout:
ext4_lock_group(sb, group);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9a6f9875aa3499..fb5985102c1db7 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5709,7 +5709,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
needs_barrier = true;
if (needs_barrier) {
int err;
- err = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL);
+ err = blkdev_issue_flush(sb->s_bdev);
if (!ret)
ret = err;
}
diff --git a/fs/fat/file.c b/fs/fat/file.c
index f9ee27cf4d7c2f..5fee74f1ad611d 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -195,7 +195,7 @@ int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
if (err)
return err;
- return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
+ return blkdev_issue_flush(inode->i_sb->s_bdev);
}
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index e3da9e96b83578..ca464328b79cc5 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -340,7 +340,7 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
}
if (!test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags))
- blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
+ blkdev_issue_flush(inode->i_sb->s_bdev);
inode_unlock(inode);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 807119ae5adf73..b9e3db3f855f96 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -239,7 +239,7 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait)
mutex_unlock(&sbi->vh_mutex);
if (!test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags))
- blkdev_issue_flush(sb->s_bdev, GFP_KERNEL);
+ blkdev_issue_flush(sb->s_bdev);
return error;
}
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 472932b9e6bca9..63b526d44886d0 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -416,7 +416,7 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
* jbd2_cleanup_journal_tail() doesn't get called all that often.
*/
if (journal->j_flags & JBD2_BARRIER)
- blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS);
+ blkdev_issue_flush(journal->j_fs_dev);
return __jbd2_update_log_tail(journal, first_tid, blocknr);
}
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index b121d7d434c675..3cc4ab2ba7f4f2 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -825,7 +825,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
if (commit_transaction->t_need_data_flush &&
(journal->j_fs_dev != journal->j_dev) &&
(journal->j_flags & JBD2_BARRIER))
- blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS);
+ blkdev_issue_flush(journal->j_fs_dev);
/* Done it all: now write the commit record asynchronously. */
if (jbd2_has_feature_async_commit(journal)) {
@@ -932,7 +932,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
stats.run.rs_blocks_logged++;
if (jbd2_has_feature_async_commit(journal) &&
journal->j_flags & JBD2_BARRIER) {
- blkdev_issue_flush(journal->j_dev, GFP_NOFS);
+ blkdev_issue_flush(journal->j_dev);
}
if (err)
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index dc0694fcfcd123..69f18fe2092369 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -326,7 +326,7 @@ int jbd2_journal_recover(journal_t *journal)
err = err2;
/* Make sure all replayed data is on permanent storage */
if (journal->j_flags & JBD2_BARRIER) {
- err2 = blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL);
+ err2 = blkdev_issue_flush(journal->j_fs_dev);
if (!err)
err = err2;
}
diff --git a/fs/libfs.c b/fs/libfs.c
index d1c3bade9f30dd..8398a0efb401c6 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1117,7 +1117,7 @@ int generic_file_fsync(struct file *file, loff_t start, loff_t end,
err = __generic_file_fsync(file, start, end, datasync);
if (err)
return err;
- return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
+ return blkdev_issue_flush(inode->i_sb->s_bdev);
}
EXPORT_SYMBOL(generic_file_fsync);
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index b55cdeb4d16991..987c8ab02aeee6 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -375,7 +375,7 @@ static inline int nilfs_flush_device(struct the_nilfs *nilfs)
*/
smp_wmb();
- err = blkdev_issue_flush(nilfs->ns_bdev, GFP_KERNEL);
+ err = blkdev_issue_flush(nilfs->ns_bdev);
if (err != -EIO)
err = 0;
return err;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 85979e2214b39d..df6d709d2ae3b6 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -194,7 +194,7 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
needs_barrier = true;
err = jbd2_complete_transaction(journal, commit_tid);
if (needs_barrier) {
- ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
+ ret = blkdev_issue_flush(inode->i_sb->s_bdev);
if (!err)
err = ret;
}
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 0b641ae694f123..1db0254bc38b26 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -159,7 +159,7 @@ static int reiserfs_sync_file(struct file *filp, loff_t start, loff_t end,
barrier_done = reiserfs_commit_for_inode(inode);
reiserfs_write_unlock(inode->i_sb);
if (barrier_done != 1 && reiserfs_barrier_flush(inode->i_sb))
- blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
+ blkdev_issue_flush(inode->i_sb->s_bdev);
inode_unlock(inode);
if (barrier_done < 0)
return barrier_done;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 813be879a5e51d..c3e32789829f90 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -342,7 +342,7 @@ void
xfs_blkdev_issue_flush(
xfs_buftarg_t *buftarg)
{
- blkdev_issue_flush(buftarg->bt_bdev, GFP_NOFS);
+ blkdev_issue_flush(buftarg->bt_bdev);
}
STATIC void
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index faea2ed34b4a37..ab68e27bb322e0 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -541,7 +541,7 @@ static int zonefs_file_fsync(struct file *file, loff_t start, loff_t end,
if (ZONEFS_I(inode)->i_ztype == ZONEFS_ZTYPE_CNV)
ret = file_write_and_wait_range(file, start, end);
if (!ret)
- ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
+ ret = blkdev_issue_flush(inode->i_sb->s_bdev);
if (ret)
zonefs_io_error(inode, true);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 20f3706b6b2e68..09f7ac5507d146 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1288,7 +1288,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
!list_empty(&plug->cb_list));
}
-int blkdev_issue_flush(struct block_device *, gfp_t);
+int blkdev_issue_flush(struct block_device *bdev);
long nr_blockdev_pages(void);
#else /* CONFIG_BLOCK */
struct blk_plug {
@@ -1316,7 +1316,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
return false;
}
-static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask)
+static inline int blkdev_issue_flush(struct block_device *bdev)
{
return 0;
}
--
2.29.2
Use blkdev_issue_flush instead of open coding it.
Signed-off-by: Christoph Hellwig <[email protected]>
---
drivers/md/dm-clone-target.c | 14 +-------------
1 file changed, 1 insertion(+), 13 deletions(-)
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index bdb255edc20043..a90bdf9b2ca6bd 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -85,12 +85,6 @@ struct clone {
struct dm_clone_metadata *cmd;
- /*
- * bio used to flush the destination device, before committing the
- * metadata.
- */
- struct bio flush_bio;
-
/* Region hydration hash table */
struct hash_table_bucket *ht;
@@ -1155,11 +1149,7 @@ static int commit_metadata(struct clone *clone, bool *dest_dev_flushed)
goto out;
}
- bio_reset(&clone->flush_bio);
- bio_set_dev(&clone->flush_bio, clone->dest_dev->bdev);
- clone->flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
-
- r = submit_bio_wait(&clone->flush_bio);
+ r = blkdev_issue_flush(clone->dest_dev->bdev);
if (unlikely(r)) {
__metadata_operation_failed(clone, "flush destination device", r);
goto out;
@@ -1886,7 +1876,6 @@ static int clone_ctr(struct dm_target *ti, unsigned int argc, char **argv)
bio_list_init(&clone->deferred_flush_completions);
clone->hydration_offset = 0;
atomic_set(&clone->hydrations_in_flight, 0);
- bio_init(&clone->flush_bio, NULL, 0);
clone->wq = alloc_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM, 0);
if (!clone->wq) {
@@ -1958,7 +1947,6 @@ static void clone_dtr(struct dm_target *ti)
struct clone *clone = ti->private;
mutex_destroy(&clone->commit_lock);
- bio_uninit(&clone->flush_bio);
for (i = 0; i < clone->nr_ctr_args; i++)
kfree(clone->ctr_args[i]);
--
2.29.2
On 26/01/2021 16:01, Christoph Hellwig wrote:
> Use bio_alloc instead of open coding it.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> fs/zonefs/super.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
> index bec47f2d074beb..faea2ed34b4a37 100644
> --- a/fs/zonefs/super.c
> +++ b/fs/zonefs/super.c
> @@ -678,7 +678,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
> if (!nr_pages)
> return 0;
>
> - bio = bio_alloc_bioset(GFP_NOFS, nr_pages, &fs_bio_set);
> + bio = bio_alloc(GFP_NOFS, nr_pages);
> if (!bio)
> return -ENOMEM;
>
>
Whoopsie my bad,
Reviewed-by: Johannes Thumshirn <[email protected]>
Use the blkdev_issue_flush helper instead of duplicating it.
Signed-off-by: Christoph Hellwig <[email protected]>
---
fs/f2fs/data.c | 3 ++-
fs/f2fs/f2fs.h | 1 -
fs/f2fs/segment.c | 12 +-----------
3 files changed, 3 insertions(+), 13 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 8cbf0315975228..0cf0c605992431 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -56,7 +56,8 @@ static inline struct bio *__f2fs_bio_alloc(gfp_t gfp_mask,
return bio_alloc_bioset(gfp_mask, nr_iovecs, &f2fs_bioset);
}
-struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio)
+static struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages,
+ bool noio)
{
if (noio) {
/* No failure on bio allocation */
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index bb11759191dcc9..902bd3267c03e1 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3424,7 +3424,6 @@ void f2fs_destroy_checkpoint_caches(void);
*/
int __init f2fs_init_bioset(void);
void f2fs_destroy_bioset(void);
-struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio);
int f2fs_init_bio_entry_cache(void);
void f2fs_destroy_bio_entry_cache(void);
void f2fs_submit_bio(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index deca74cb17dfd8..c495f170ee400b 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -566,17 +566,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
static int __submit_flush_wait(struct f2fs_sb_info *sbi,
struct block_device *bdev)
{
- struct bio *bio;
- int ret;
-
- bio = f2fs_bio_alloc(sbi, 0, false);
- if (!bio)
- return -ENOMEM;
-
- bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
- bio_set_dev(bio, bdev);
- ret = submit_bio_wait(bio);
- bio_put(bio);
+ int ret = blkdev_issue_flush(bdev);
trace_f2fs_issue_flush(bdev, test_opt(sbi, NOBARRIER),
test_opt(sbi, FLUSH_MERGE), ret);
--
2.29.2
Sleeping bio allocations do not fail, which means that injecting an error
into sleeping bio allocations is a little silly.
Signed-off-by: Christoph Hellwig <[email protected]>
---
Documentation/filesystems/f2fs.rst | 1 -
fs/f2fs/data.c | 29 ++++-------------------------
fs/f2fs/f2fs.h | 1 -
fs/f2fs/super.c | 1 -
4 files changed, 4 insertions(+), 28 deletions(-)
diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index dae15c96e659e2..624f5f3ed93e86 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -179,7 +179,6 @@ fault_type=%d Support configuring fault injection type, should be
FAULT_KVMALLOC 0x000000002
FAULT_PAGE_ALLOC 0x000000004
FAULT_PAGE_GET 0x000000008
- FAULT_ALLOC_BIO 0x000000010
FAULT_ALLOC_NID 0x000000020
FAULT_ORPHAN 0x000000040
FAULT_BLOCK 0x000000080
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0cf0c605992431..9fb6be65592b1f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -50,28 +50,6 @@ void f2fs_destroy_bioset(void)
bioset_exit(&f2fs_bioset);
}
-static inline struct bio *__f2fs_bio_alloc(gfp_t gfp_mask,
- unsigned int nr_iovecs)
-{
- return bio_alloc_bioset(gfp_mask, nr_iovecs, &f2fs_bioset);
-}
-
-static struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages,
- bool noio)
-{
- if (noio) {
- /* No failure on bio allocation */
- return __f2fs_bio_alloc(GFP_NOIO, npages);
- }
-
- if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
- f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO);
- return NULL;
- }
-
- return __f2fs_bio_alloc(GFP_KERNEL, npages);
-}
-
static bool __is_cp_guaranteed(struct page *page)
{
struct address_space *mapping = page->mapping;
@@ -433,7 +411,7 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
struct f2fs_sb_info *sbi = fio->sbi;
struct bio *bio;
- bio = f2fs_bio_alloc(sbi, npages, true);
+ bio = bio_alloc_bioset(GFP_NOIO, npages, &f2fs_bioset);
f2fs_target_device(sbi, fio->new_blkaddr, bio);
if (is_read_io(fio->op)) {
@@ -1029,8 +1007,9 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
struct bio_post_read_ctx *ctx;
unsigned int post_read_steps = 0;
- bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES),
- for_write);
+ bio = bio_alloc_bioset(for_write ? GFP_NOIO : GFP_KERNEL,
+ min_t(int, nr_pages, BIO_MAX_PAGES),
+ &f2fs_bioset);
if (!bio)
return ERR_PTR(-ENOMEM);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 902bd3267c03e1..6c78365d80ceb5 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -43,7 +43,6 @@ enum {
FAULT_KVMALLOC,
FAULT_PAGE_ALLOC,
FAULT_PAGE_GET,
- FAULT_ALLOC_BIO,
FAULT_ALLOC_NID,
FAULT_ORPHAN,
FAULT_BLOCK,
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index b4a07fe62d1a58..3a312642907e86 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -45,7 +45,6 @@ const char *f2fs_fault_name[FAULT_MAX] = {
[FAULT_KVMALLOC] = "kvmalloc",
[FAULT_PAGE_ALLOC] = "page alloc",
[FAULT_PAGE_GET] = "page get",
- [FAULT_ALLOC_BIO] = "alloc bio",
[FAULT_ALLOC_NID] = "alloc nid",
[FAULT_ORPHAN] = "orphan",
[FAULT_BLOCK] = "no more block",
--
2.29.2
bio_kmalloc shares almost no logic with the bio_set based fast path
in bio_alloc_bioset. Split it into an entirely separate implementation.
Signed-off-by: Christoph Hellwig <[email protected]>
---
block/bio.c | 167 ++++++++++++++++++++++----------------------
include/linux/bio.h | 6 +-
2 files changed, 86 insertions(+), 87 deletions(-)
diff --git a/block/bio.c b/block/bio.c
index dfd7740a32300a..d4375619348c52 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -396,123 +396,101 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
* @nr_iovecs: number of iovecs to pre-allocate
* @bs: the bio_set to allocate from.
*
- * Description:
- * If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is
- * backed by the @bs's mempool.
+ * Allocate a bio from the mempools in @bs.
*
- * When @bs is not NULL, if %__GFP_DIRECT_RECLAIM is set then bio_alloc will
- * always be able to allocate a bio. This is due to the mempool guarantees.
- * To make this work, callers must never allocate more than 1 bio at a time
- * from this pool. Callers that need to allocate more than 1 bio must always
- * submit the previously allocated bio for IO before attempting to allocate
- * a new one. Failure to do so can cause deadlocks under memory pressure.
+ * If %__GFP_DIRECT_RECLAIM is set then bio_alloc will always be able to
+ * allocate a bio. This is due to the mempool guarantees. To make this work,
+ * callers must never allocate more than 1 bio at a time from the general pool.
+ * Callers that need to allocate more than 1 bio must always submit the
+ * previously allocated bio for IO before attempting to allocate a new one.
+ * Failure to do so can cause deadlocks under memory pressure.
*
- * Note that when running under submit_bio_noacct() (i.e. any block
- * driver), bios are not submitted until after you return - see the code in
- * submit_bio_noacct() that converts recursion into iteration, to prevent
- * stack overflows.
+ * Note that when running under submit_bio_noacct() (i.e. any block driver),
+ * bios are not submitted until after you return - see the code in
+ * submit_bio_noacct() that converts recursion into iteration, to prevent
+ * stack overflows.
*
- * This would normally mean allocating multiple bios under
- * submit_bio_noacct() would be susceptible to deadlocks, but we have
- * deadlock avoidance code that resubmits any blocked bios from a rescuer
- * thread.
+ * This would normally mean allocating multiple bios under submit_bio_noacct()
+ * would be susceptible to deadlocks, but we have
+ * deadlock avoidance code that resubmits any blocked bios from a rescuer
+ * thread.
*
- * However, we do not guarantee forward progress for allocations from other
- * mempools. Doing multiple allocations from the same mempool under
- * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad
- * for per bio allocations.
+ * However, we do not guarantee forward progress for allocations from other
+ * mempools. Doing multiple allocations from the same mempool under
+ * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad
+ * for per bio allocations.
*
- * RETURNS:
- * Pointer to new bio on success, NULL on failure.
+ * Returns: Pointer to new bio on success, NULL on failure.
*/
struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
struct bio_set *bs)
{
gfp_t saved_gfp = gfp_mask;
- unsigned front_pad;
- unsigned inline_vecs;
- struct bio_vec *bvl = NULL;
struct bio *bio;
void *p;
- if (!bs) {
- if (nr_iovecs > UIO_MAXIOV)
- return NULL;
-
- p = kmalloc(struct_size(bio, bi_inline_vecs, nr_iovecs), gfp_mask);
- front_pad = 0;
- inline_vecs = nr_iovecs;
- } else {
- /* should not use nobvec bioset for nr_iovecs > 0 */
- if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) &&
- nr_iovecs > 0))
- return NULL;
- /*
- * submit_bio_noacct() converts recursion to iteration; this
- * means if we're running beneath it, any bios we allocate and
- * submit will not be submitted (and thus freed) until after we
- * return.
- *
- * This exposes us to a potential deadlock if we allocate
- * multiple bios from the same bio_set() while running
- * underneath submit_bio_noacct(). If we were to allocate
- * multiple bios (say a stacking block driver that was splitting
- * bios), we would deadlock if we exhausted the mempool's
- * reserve.
- *
- * We solve this, and guarantee forward progress, with a rescuer
- * workqueue per bio_set. If we go to allocate and there are
- * bios on current->bio_list, we first try the allocation
- * without __GFP_DIRECT_RECLAIM; if that fails, we punt those
- * bios we would be blocking to the rescuer workqueue before
- * we retry with the original gfp_flags.
- */
-
- if (current->bio_list &&
- (!bio_list_empty(¤t->bio_list[0]) ||
- !bio_list_empty(¤t->bio_list[1])) &&
- bs->rescue_workqueue)
- gfp_mask &= ~__GFP_DIRECT_RECLAIM;
+ /* should not use nobvec bioset for nr_iovecs > 0 */
+ if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_iovecs > 0))
+ return NULL;
+ /*
+ * submit_bio_noacct() converts recursion to iteration; this means if
+ * we're running beneath it, any bios we allocate and submit will not be
+ * submitted (and thus freed) until after we return.
+ *
+ * This exposes us to a potential deadlock if we allocate multiple bios
+ * from the same bio_set() while running underneath submit_bio_noacct().
+ * If we were to allocate multiple bios (say a stacking block driver
+ * that was splitting bios), we would deadlock if we exhausted the
+ * mempool's reserve.
+ *
+ * We solve this, and guarantee forward progress, with a rescuer
+ * workqueue per bio_set. If we go to allocate and there are bios on
+ * current->bio_list, we first try the allocation without
+ * __GFP_DIRECT_RECLAIM; if that fails, we punt those bios we would be
+ * blocking to the rescuer workqueue before we retry with the original
+ * gfp_flags.
+ */
+ if (current->bio_list &&
+ (!bio_list_empty(¤t->bio_list[0]) ||
+ !bio_list_empty(¤t->bio_list[1])) &&
+ bs->rescue_workqueue)
+ gfp_mask &= ~__GFP_DIRECT_RECLAIM;
+
+ p = mempool_alloc(&bs->bio_pool, gfp_mask);
+ if (!p && gfp_mask != saved_gfp) {
+ punt_bios_to_rescuer(bs);
+ gfp_mask = saved_gfp;
p = mempool_alloc(&bs->bio_pool, gfp_mask);
- if (!p && gfp_mask != saved_gfp) {
- punt_bios_to_rescuer(bs);
- gfp_mask = saved_gfp;
- p = mempool_alloc(&bs->bio_pool, gfp_mask);
- }
-
- front_pad = bs->front_pad;
- inline_vecs = BIO_INLINE_VECS;
}
-
if (unlikely(!p))
return NULL;
- bio = p + front_pad;
- bio_init(bio, NULL, 0);
-
- if (nr_iovecs > inline_vecs) {
+ bio = p + bs->front_pad;
+ if (nr_iovecs > BIO_INLINE_VECS) {
unsigned long idx = 0;
+ struct bio_vec *bvl = NULL;
bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool);
if (!bvl && gfp_mask != saved_gfp) {
punt_bios_to_rescuer(bs);
gfp_mask = saved_gfp;
- bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool);
+ bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx,
+ &bs->bvec_pool);
}
if (unlikely(!bvl))
goto err_free;
bio->bi_flags |= idx << BVEC_POOL_OFFSET;
- bio->bi_max_vecs = bvec_nr_vecs(idx);
+ bio_init(bio, bvl, bvec_nr_vecs(idx));
} else if (nr_iovecs) {
- bvl = bio->bi_inline_vecs;
- bio->bi_max_vecs = inline_vecs;
+ bio_init(bio, bio->bi_inline_vecs, BIO_INLINE_VECS);
+ } else {
+ bio_init(bio, NULL, 0);
}
bio->bi_pool = bs;
- bio->bi_io_vec = bvl;
return bio;
err_free:
@@ -521,6 +499,31 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
}
EXPORT_SYMBOL(bio_alloc_bioset);
+/**
+ * bio_kmalloc - kmalloc a bio for I/O
+ * @gfp_mask: the GFP_* mask given to the slab allocator
+ * @nr_iovecs: number of iovecs to pre-allocate
+ *
+ * Use kmalloc to allocate and initialize a bio.
+ *
+ * Returns: Pointer to new bio on success, NULL on failure.
+ */
+struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
+{
+ struct bio *bio;
+
+ if (nr_iovecs > UIO_MAXIOV)
+ return NULL;
+
+ bio = kmalloc(struct_size(bio, bi_inline_vecs, nr_iovecs), gfp_mask);
+ if (unlikely(!bio))
+ return NULL;
+ bio_init(bio, nr_iovecs ? bio->bi_inline_vecs : NULL, nr_iovecs);
+ bio->bi_pool = NULL;
+ return bio;
+}
+EXPORT_SYMBOL(bio_kmalloc);
+
void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start)
{
unsigned long flags;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 676870b2c88d80..c74857cf12528c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -408,6 +408,7 @@ extern int biovec_init_pool(mempool_t *pool, int pool_entries);
extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src);
extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *);
+struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs);
extern void bio_put(struct bio *);
extern void __bio_clone_fast(struct bio *, struct bio *);
@@ -420,11 +421,6 @@ static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set);
}
-static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
-{
- return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
-}
-
extern blk_qc_t submit_bio(struct bio *);
extern void bio_endio(struct bio *);
--
2.29.2
Given that drbd_md_io_bio_set is initialized during module initialization
and the module fails to load if the initialization fails there is no need
to fall back to plain bio_alloc.
Signed-off-by: Christoph Hellwig <[email protected]>
---
drivers/block/drbd/drbd_actlog.c | 2 +-
drivers/block/drbd/drbd_bitmap.c | 2 +-
drivers/block/drbd/drbd_int.h | 2 --
drivers/block/drbd/drbd_main.c | 13 -------------
4 files changed, 2 insertions(+), 17 deletions(-)
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 7227fc7ab8ed1e..72cf7603d51fc7 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -138,7 +138,7 @@ static int _drbd_md_sync_page_io(struct drbd_device *device,
op_flags |= REQ_FUA | REQ_PREFLUSH;
op_flags |= REQ_SYNC;
- bio = bio_alloc_drbd(GFP_NOIO);
+ bio = bio_alloc_bioset(GFP_NOIO, 1, &drbd_md_io_bio_set);
bio_set_dev(bio, bdev->md_bdev);
bio->bi_iter.bi_sector = sector;
err = -EIO;
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index df53dca5d02c7e..c1f816f896a89a 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -976,7 +976,7 @@ static void drbd_bm_endio(struct bio *bio)
static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_hold(local)
{
- struct bio *bio = bio_alloc_drbd(GFP_NOIO);
+ struct bio *bio = bio_alloc_bioset(GFP_NOIO, 1, &drbd_md_io_bio_set);
struct drbd_device *device = ctx->device;
struct drbd_bitmap *b = device->bitmap;
struct page *page;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index b2c93a29c251fd..02db50d7e4c668 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1422,8 +1422,6 @@ extern mempool_t drbd_md_io_page_pool;
/* We also need to make sure we get a bio
* when we need it for housekeeping purposes */
extern struct bio_set drbd_md_io_bio_set;
-/* to allocate from that set */
-extern struct bio *bio_alloc_drbd(gfp_t gfp_mask);
/* And a bio_set for cloning */
extern struct bio_set drbd_io_bio_set;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 1c8c18b2a25f33..788dd97e6026b8 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -138,19 +138,6 @@ static const struct block_device_operations drbd_ops = {
.release = drbd_release,
};
-struct bio *bio_alloc_drbd(gfp_t gfp_mask)
-{
- struct bio *bio;
-
- if (!bioset_initialized(&drbd_md_io_bio_set))
- return bio_alloc(gfp_mask, 1);
-
- bio = bio_alloc_bioset(gfp_mask, 1, &drbd_md_io_bio_set);
- if (!bio)
- return NULL;
- return bio;
-}
-
#ifdef __CHECKER__
/* When checking with sparse, and this is an inline function, sparse will
give tons of false positives. When this is a real functions sparse works.
--
2.29.2
On 1/26/21 9:52 AM, Christoph Hellwig wrote:
> Use bio_kmalloc instead of open coding it.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Josef Bacik <[email protected]>
yay I contributed,
Josef
Open code drbd_req_make_private_bio in the two callers to prepare
for further changes. Also don't bother to initialize bi_next as the
bio code already does that that.
Signed-off-by: Christoph Hellwig <[email protected]>
---
drivers/block/drbd/drbd_req.c | 5 ++++-
drivers/block/drbd/drbd_req.h | 12 ------------
drivers/block/drbd/drbd_worker.c | 5 ++++-
3 files changed, 8 insertions(+), 14 deletions(-)
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index ea0f31ab334361..9dbb660a7d7c8e 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -30,7 +30,10 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio
return NULL;
memset(req, 0, sizeof(*req));
- drbd_req_make_private_bio(req, bio_src);
+ req->private_bio = bio_clone_fast(bio_src, GFP_NOIO, &drbd_io_bio_set);
+ req->private_bio->bi_private = req;
+ req->private_bio->bi_end_io = drbd_request_endio;
+
req->rq_state = (bio_data_dir(bio_src) == WRITE ? RQ_WRITE : 0)
| (bio_op(bio_src) == REQ_OP_WRITE_SAME ? RQ_WSAME : 0)
| (bio_op(bio_src) == REQ_OP_WRITE_ZEROES ? RQ_ZEROES : 0)
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index 55bb0f8721faa3..511f39a08de453 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -256,18 +256,6 @@ enum drbd_req_state_bits {
#define MR_WRITE 1
#define MR_READ 2
-static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src)
-{
- struct bio *bio;
- bio = bio_clone_fast(bio_src, GFP_NOIO, &drbd_io_bio_set);
-
- req->private_bio = bio;
-
- bio->bi_private = req;
- bio->bi_end_io = drbd_request_endio;
- bio->bi_next = NULL;
-}
-
/* Short lived temporary struct on the stack.
* We could squirrel the error to be returned into
* bio->bi_iter.bi_size, or similar. But that would be too ugly. */
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 02044ab7f767d5..64563bfdf0da02 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1523,8 +1523,11 @@ int w_restart_disk_io(struct drbd_work *w, int cancel)
if (bio_data_dir(req->master_bio) == WRITE && req->rq_state & RQ_IN_ACT_LOG)
drbd_al_begin_io(device, &req->i);
- drbd_req_make_private_bio(req, req->master_bio);
+ req->private_bio = bio_clone_fast(req->master_bio, GFP_NOIO,
+ &drbd_io_bio_set);
bio_set_dev(req->private_bio, device->ldev->backing_bdev);
+ req->private_bio->bi_private = req;
+ req->private_bio->bi_end_io = drbd_request_endio;
submit_bio_noacct(req->private_bio);
return 0;
--
2.29.2
bio_alloc_mddev is never called with a NULL mddev, and ->bio_set is
initialized in md_run, so it always must be initialized as well. Just
open code the remaining call to bio_alloc_bioset.
Signed-off-by: Christoph Hellwig <[email protected]>
---
drivers/md/md.c | 12 +-----------
drivers/md/md.h | 2 --
drivers/md/raid1.c | 2 +-
drivers/md/raid10.c | 2 +-
4 files changed, 3 insertions(+), 15 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 7d1bb24add3107..e2b9dbb6e888f6 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -340,16 +340,6 @@ static int start_readonly;
*/
static bool create_on_open = true;
-struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
- struct mddev *mddev)
-{
- if (!mddev || !bioset_initialized(&mddev->bio_set))
- return bio_alloc(gfp_mask, nr_iovecs);
-
- return bio_alloc_bioset(gfp_mask, nr_iovecs, &mddev->bio_set);
-}
-EXPORT_SYMBOL_GPL(bio_alloc_mddev);
-
static struct bio *md_bio_alloc_sync(struct mddev *mddev)
{
if (!mddev || !bioset_initialized(&mddev->sync_set))
@@ -613,7 +603,7 @@ static void submit_flushes(struct work_struct *ws)
atomic_inc(&rdev->nr_pending);
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
- bi = bio_alloc_mddev(GFP_NOIO, 0, mddev);
+ bi = bio_alloc_bioset(GFP_NOIO, 0, &mddev->bio_set);
bi->bi_end_io = md_end_flush;
bi->bi_private = rdev;
bio_set_dev(bi, rdev->bdev);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index f13290ccc1c248..bcbba1b5ec4a71 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -742,8 +742,6 @@ extern void md_rdev_clear(struct md_rdev *rdev);
extern void md_handle_request(struct mddev *mddev, struct bio *bio);
extern void mddev_suspend(struct mddev *mddev);
extern void mddev_resume(struct mddev *mddev);
-extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
- struct mddev *mddev);
extern void md_reload_sb(struct mddev *mddev, int raid_disk);
extern void md_update_sb(struct mddev *mddev, int force);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 3b19141cdb4bc2..d2378765dc154f 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1104,7 +1104,7 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio,
int i = 0;
struct bio *behind_bio = NULL;
- behind_bio = bio_alloc_mddev(GFP_NOIO, vcnt, r1_bio->mddev);
+ behind_bio = bio_alloc_bioset(GFP_NOIO, vcnt, &r1_bio->mddev->bio_set);
if (!behind_bio)
return;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index be8f14afb6d143..e1eefbec15d444 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4531,7 +4531,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
return sectors_done;
}
- read_bio = bio_alloc_mddev(GFP_KERNEL, RESYNC_PAGES, mddev);
+ read_bio = bio_alloc_bioset(GFP_KERNEL, RESYNC_PAGES, &mddev->bio_set);
bio_set_dev(read_bio, rdev->bdev);
read_bio->bi_iter.bi_sector = (r10_bio->devs[r10_bio->read_slot].addr
--
2.29.2
Use an on-stack bio and biovec for the single page synchronous I/O.
Signed-off-by: Christoph Hellwig <[email protected]>
---
drivers/md/md.c | 26 +++++++++++++-------------
1 file changed, 13 insertions(+), 13 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index e2b9dbb6e888f6..6a27f52007c871 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1021,29 +1021,29 @@ int md_super_wait(struct mddev *mddev)
int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
struct page *page, int op, int op_flags, bool metadata_op)
{
- struct bio *bio = md_bio_alloc_sync(rdev->mddev);
- int ret;
+ struct bio bio;
+ struct bio_vec bvec;
+
+ bio_init(&bio, &bvec, 1);
if (metadata_op && rdev->meta_bdev)
- bio_set_dev(bio, rdev->meta_bdev);
+ bio_set_dev(&bio, rdev->meta_bdev);
else
- bio_set_dev(bio, rdev->bdev);
- bio_set_op_attrs(bio, op, op_flags);
+ bio_set_dev(&bio, rdev->bdev);
+ bio.bi_opf = op | op_flags;
if (metadata_op)
- bio->bi_iter.bi_sector = sector + rdev->sb_start;
+ bio.bi_iter.bi_sector = sector + rdev->sb_start;
else if (rdev->mddev->reshape_position != MaxSector &&
(rdev->mddev->reshape_backwards ==
(sector >= rdev->mddev->reshape_position)))
- bio->bi_iter.bi_sector = sector + rdev->new_data_offset;
+ bio.bi_iter.bi_sector = sector + rdev->new_data_offset;
else
- bio->bi_iter.bi_sector = sector + rdev->data_offset;
- bio_add_page(bio, page, size, 0);
+ bio.bi_iter.bi_sector = sector + rdev->data_offset;
+ bio_add_page(&bio, page, size, 0);
- submit_bio_wait(bio);
+ submit_bio_wait(&bio);
- ret = !bio->bi_status;
- bio_put(bio);
- return ret;
+ return !bio.bi_status;
}
EXPORT_SYMBOL_GPL(sync_page_io);
--
2.29.2
md_bio_alloc_sync is never called with a NULL mddev, and ->sync_set is
initialized in md_run, so it always must be initialized as well. Just
open code the remaining call to bio_alloc_bioset.
Signed-off-by: Christoph Hellwig <[email protected]>
---
drivers/md/md.c | 10 +---------
1 file changed, 1 insertion(+), 9 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 6a27f52007c871..399c81bddc1ae1 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -340,14 +340,6 @@ static int start_readonly;
*/
static bool create_on_open = true;
-static struct bio *md_bio_alloc_sync(struct mddev *mddev)
-{
- if (!mddev || !bioset_initialized(&mddev->sync_set))
- return bio_alloc(GFP_NOIO, 1);
-
- return bio_alloc_bioset(GFP_NOIO, 1, &mddev->sync_set);
-}
-
/*
* We have a system wide 'event count' that is incremented
* on any 'interesting' event, and readers of /proc/mdstat
@@ -989,7 +981,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
if (test_bit(Faulty, &rdev->flags))
return;
- bio = md_bio_alloc_sync(mddev);
+ bio = bio_alloc_bioset(GFP_NOIO, 1, &mddev->sync_set);
atomic_inc(&rdev->nr_pending);
--
2.29.2
Refactor raid5_read_one_chunk so that all simple checks are done
before allocating the bio.
Signed-off-by: Christoph Hellwig <[email protected]>
---
drivers/md/raid5.c | 108 +++++++++++++++++++--------------------------
1 file changed, 45 insertions(+), 63 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f411b9e5c332f4..a348b2adf2a9f9 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5393,90 +5393,72 @@ static void raid5_align_endio(struct bio *bi)
static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
{
struct r5conf *conf = mddev->private;
- int dd_idx;
- struct bio* align_bi;
+ struct bio *align_bio;
struct md_rdev *rdev;
- sector_t end_sector;
+ sector_t sector, end_sector, first_bad;
+ int bad_sectors, dd_idx;
if (!in_chunk_boundary(mddev, raid_bio)) {
pr_debug("%s: non aligned\n", __func__);
return 0;
}
- /*
- * use bio_clone_fast to make a copy of the bio
- */
- align_bi = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set);
- if (!align_bi)
- return 0;
- /*
- * set bi_end_io to a new function, and set bi_private to the
- * original bio.
- */
- align_bi->bi_end_io = raid5_align_endio;
- align_bi->bi_private = raid_bio;
- /*
- * compute position
- */
- align_bi->bi_iter.bi_sector =
- raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector,
- 0, &dd_idx, NULL);
- end_sector = bio_end_sector(align_bi);
+ sector = raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector, 0,
+ &dd_idx, NULL);
+ end_sector = bio_end_sector(raid_bio);
+
rcu_read_lock();
+ if (r5c_big_stripe_cached(conf, sector))
+ goto out_rcu_unlock;
+
rdev = rcu_dereference(conf->disks[dd_idx].replacement);
if (!rdev || test_bit(Faulty, &rdev->flags) ||
rdev->recovery_offset < end_sector) {
rdev = rcu_dereference(conf->disks[dd_idx].rdev);
- if (rdev &&
- (test_bit(Faulty, &rdev->flags) ||
+ if (!rdev)
+ goto out_rcu_unlock;
+ if (test_bit(Faulty, &rdev->flags) ||
!(test_bit(In_sync, &rdev->flags) ||
- rdev->recovery_offset >= end_sector)))
- rdev = NULL;
+ rdev->recovery_offset >= end_sector))
+ goto out_rcu_unlock;
}
- if (r5c_big_stripe_cached(conf, align_bi->bi_iter.bi_sector)) {
- rcu_read_unlock();
- bio_put(align_bi);
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
+
+ align_bio = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set);
+ bio_set_dev(align_bio, rdev->bdev);
+ align_bio->bi_end_io = raid5_align_endio;
+ align_bio->bi_private = raid_bio;
+ align_bio->bi_iter.bi_sector = sector;
+
+ raid_bio->bi_next = (void *)rdev;
+
+ if (is_badblock(rdev, sector, bio_sectors(align_bio), &first_bad,
+ &bad_sectors)) {
+ bio_put(align_bio);
+ rdev_dec_pending(rdev, mddev);
return 0;
}
- if (rdev) {
- sector_t first_bad;
- int bad_sectors;
-
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
- raid_bio->bi_next = (void*)rdev;
- bio_set_dev(align_bi, rdev->bdev);
-
- if (is_badblock(rdev, align_bi->bi_iter.bi_sector,
- bio_sectors(align_bi),
- &first_bad, &bad_sectors)) {
- bio_put(align_bi);
- rdev_dec_pending(rdev, mddev);
- return 0;
- }
+ /* No reshape active, so we can trust rdev->data_offset */
+ align_bio->bi_iter.bi_sector += rdev->data_offset;
- /* No reshape active, so we can trust rdev->data_offset */
- align_bi->bi_iter.bi_sector += rdev->data_offset;
+ spin_lock_irq(&conf->device_lock);
+ wait_event_lock_irq(conf->wait_for_quiescent, conf->quiesce == 0,
+ conf->device_lock);
+ atomic_inc(&conf->active_aligned_reads);
+ spin_unlock_irq(&conf->device_lock);
- spin_lock_irq(&conf->device_lock);
- wait_event_lock_irq(conf->wait_for_quiescent,
- conf->quiesce == 0,
- conf->device_lock);
- atomic_inc(&conf->active_aligned_reads);
- spin_unlock_irq(&conf->device_lock);
+ if (mddev->gendisk)
+ trace_block_bio_remap(align_bio, disk_devt(mddev->gendisk),
+ raid_bio->bi_iter.bi_sector);
+ submit_bio_noacct(align_bio);
+ return 1;
- if (mddev->gendisk)
- trace_block_bio_remap(align_bi, disk_devt(mddev->gendisk),
- raid_bio->bi_iter.bi_sector);
- submit_bio_noacct(align_bi);
- return 1;
- } else {
- rcu_read_unlock();
- bio_put(align_bi);
- return 0;
- }
+out_rcu_unlock:
+ rcu_read_unlock();
+ return 0;
}
static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
--
2.29.2
bio_alloc never returns NULL when it can sleep.
Signed-off-by: Christoph Hellwig <[email protected]>
---
fs/nfs/blocklayout/blocklayout.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 3be6836074ae92..1a96ce28efb026 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -123,11 +123,6 @@ bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector,
npg = min(npg, BIO_MAX_PAGES);
bio = bio_alloc(GFP_NOIO, npg);
- if (!bio && (current->flags & PF_MEMALLOC)) {
- while (!bio && (npg /= 2))
- bio = bio_alloc(GFP_NOIO, npg);
- }
-
if (bio) {
bio->bi_iter.bi_sector = disk_sector;
bio_set_dev(bio, bdev);
--
2.29.2
bio_alloc never returns NULL when it can sleep.
Signed-off-by: Christoph Hellwig <[email protected]>
---
fs/nilfs2/segbuf.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 1a8729eded8b14..1e75417bfe6e52 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -386,10 +386,6 @@ static struct bio *nilfs_alloc_seg_bio(struct the_nilfs *nilfs, sector_t start,
struct bio *bio;
bio = bio_alloc(GFP_NOIO, nr_vecs);
- if (bio == NULL) {
- while (!bio && (nr_vecs >>= 1))
- bio = bio_alloc(GFP_NOIO, nr_vecs);
- }
if (likely(bio)) {
bio_set_dev(bio, nilfs->ns_bdev);
bio->bi_iter.bi_sector =
--
2.29.2
Just reuse the block_device and sector from the swap_info structure,
just as used by the SWP_SYNCHRONOUS path. Also remove the checks for
NULL returns from bio_alloc as that can't happen for sleeping
allocations.
Signed-off-by: Christoph Hellwig <[email protected]>
---
include/linux/swap.h | 1 -
mm/page_io.c | 45 +++++++++++++-------------------------------
mm/swapfile.c | 10 ----------
3 files changed, 13 insertions(+), 43 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 596bc2f4d9b03e..3f1f7ae0fbe9e1 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -468,7 +468,6 @@ extern int free_swap_and_cache(swp_entry_t);
int swap_type_of(dev_t device, sector_t offset);
int find_first_swap(dev_t *device);
extern unsigned int count_swap_pages(int, int);
-extern sector_t map_swap_page(struct page *, struct block_device **);
extern sector_t swapdev_block(int, pgoff_t);
extern int page_swapcount(struct page *);
extern int __swap_count(swp_entry_t entry);
diff --git a/mm/page_io.c b/mm/page_io.c
index a75f35464a4e73..92f7941c6d018b 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -26,25 +26,6 @@
#include <linux/uio.h>
#include <linux/sched/task.h>
-static struct bio *get_swap_bio(gfp_t gfp_flags,
- struct page *page, bio_end_io_t end_io)
-{
- struct bio *bio;
-
- bio = bio_alloc(gfp_flags, 1);
- if (bio) {
- struct block_device *bdev;
-
- bio->bi_iter.bi_sector = map_swap_page(page, &bdev);
- bio_set_dev(bio, bdev);
- bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
- bio->bi_end_io = end_io;
-
- bio_add_page(bio, page, thp_size(page), 0);
- }
- return bio;
-}
-
void end_swap_bio_write(struct bio *bio)
{
struct page *page = bio_first_page_all(bio);
@@ -361,13 +342,13 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
return 0;
}
- bio = get_swap_bio(GFP_NOIO, page, end_write_func);
- if (bio == NULL) {
- set_page_dirty(page);
- unlock_page(page);
- return -ENOMEM;
- }
+ bio = bio_alloc(GFP_NOIO, 1);
+ bio_set_dev(bio, sis->bdev);
+ bio->bi_iter.bi_sector = swap_page_sector(page);
bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc);
+ bio->bi_end_io = end_write_func;
+ bio_add_page(bio, page, thp_size(page), 0);
+
bio_associate_blkg_from_page(bio, page);
count_swpout_vm_event(page);
set_page_writeback(page);
@@ -427,18 +408,18 @@ int swap_readpage(struct page *page, bool synchronous)
}
ret = 0;
- bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
- if (bio == NULL) {
- unlock_page(page);
- ret = -ENOMEM;
- goto out;
- }
+ bio = bio_alloc(GFP_KERNEL, 1);
+ bio_set_dev(bio, sis->bdev);
+ bio->bi_opf = REQ_OP_READ;
+ bio->bi_iter.bi_sector = swap_page_sector(page);
+ bio->bi_end_io = end_swap_bio_read;
+ bio_add_page(bio, page, thp_size(page), 0);
+
disk = bio->bi_bdev->bd_disk;
/*
* Keep this task valid during swap readpage because the oom killer may
* attempt to access it in the page fault retry time check.
*/
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
if (synchronous) {
bio->bi_opf |= REQ_HIPRI;
get_task_struct(current);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 9fffc5af29d1b9..bfa9e8b0c2ef61 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2301,16 +2301,6 @@ static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev)
return se->start_block + (offset - se->start_page);
}
-/*
- * Returns the page offset into bdev for the specified page's swap entry.
- */
-sector_t map_swap_page(struct page *page, struct block_device **bdev)
-{
- swp_entry_t entry;
- entry.val = page_private(page);
- return map_swap_entry(entry, bdev);
-}
-
/*
* Free all of a swapdev's extent information
*/
--
2.29.2
On 1/26/21 7:01 AM, Christoph Hellwig wrote:
> Use bio_alloc instead of open coding it.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
Ha Ha I was going send out a patch for this :P.
Reviewed-by: Chaitanya Kulkarni <[email protected]>
On 1/26/21 7:04 AM, Christoph Hellwig wrote:
> Use bio_kmalloc instead of open coding it.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
Looks good.
Reviewed-by: Chaitanya Kulkarni <[email protected]>
On 1/26/21 7:27 AM, Christoph Hellwig wrote:
> bio_alloc never returns NULL when it can sleep.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
Looks good.
Reviewed-by: Chaitanya Kulkarni <[email protected]>
On Tue, Jan 26, 2021 at 03:52:33PM +0100, Christoph Hellwig wrote:
> Use bio_kmalloc instead of open coding it.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> block/blk-crypto-fallback.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
> index 50c225398e4d60..e8327c50d7c9f4 100644
> --- a/block/blk-crypto-fallback.c
> +++ b/block/blk-crypto-fallback.c
> @@ -164,7 +164,7 @@ static struct bio *blk_crypto_clone_bio(struct bio *bio_src)
> struct bio_vec bv;
> struct bio *bio;
>
> - bio = bio_alloc_bioset(GFP_NOIO, bio_segments(bio_src), NULL);
> + bio = bio_kmalloc(GFP_NOIO, bio_segments(bio_src));
> if (!bio)
> return NULL;
> bio->bi_bdev = bio_src->bi_bdev;
> --
Looks good,
Reviewed-by: Eric Biggers <[email protected]>
On 1/26/21 7:07 AM, Christoph Hellwig wrote:
> There is no point in allocating memory for a synchronous flush.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
True, looks good.
Reviewed-by: Chaitanya Kulkarni <[email protected]>
On Tue, Jan 26, 2021 at 7:19 AM Christoph Hellwig <[email protected]> wrote:
>
> Refactor raid5_read_one_chunk so that all simple checks are done
> before allocating the bio.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Song Liu <[email protected]>
Thanks for the clean-up!
> ---
> drivers/md/raid5.c | 108 +++++++++++++++++++--------------------------
> 1 file changed, 45 insertions(+), 63 deletions(-)
>
> diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
> index f411b9e5c332f4..a348b2adf2a9f9 100644
> --- a/drivers/md/raid5.c
> +++ b/drivers/md/raid5.c
> @@ -5393,90 +5393,72 @@ static void raid5_align_endio(struct bio *bi)
> static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
> {
> struct r5conf *conf = mddev->private;
> - int dd_idx;
> - struct bio* align_bi;
> + struct bio *align_bio;
> struct md_rdev *rdev;
> - sector_t end_sector;
> + sector_t sector, end_sector, first_bad;
> + int bad_sectors, dd_idx;
>
> if (!in_chunk_boundary(mddev, raid_bio)) {
> pr_debug("%s: non aligned\n", __func__);
> return 0;
> }
> - /*
> - * use bio_clone_fast to make a copy of the bio
> - */
> - align_bi = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set);
> - if (!align_bi)
> - return 0;
> - /*
> - * set bi_end_io to a new function, and set bi_private to the
> - * original bio.
> - */
> - align_bi->bi_end_io = raid5_align_endio;
> - align_bi->bi_private = raid_bio;
> - /*
> - * compute position
> - */
> - align_bi->bi_iter.bi_sector =
> - raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector,
> - 0, &dd_idx, NULL);
>
> - end_sector = bio_end_sector(align_bi);
> + sector = raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector, 0,
> + &dd_idx, NULL);
> + end_sector = bio_end_sector(raid_bio);
> +
> rcu_read_lock();
> + if (r5c_big_stripe_cached(conf, sector))
> + goto out_rcu_unlock;
> +
> rdev = rcu_dereference(conf->disks[dd_idx].replacement);
> if (!rdev || test_bit(Faulty, &rdev->flags) ||
> rdev->recovery_offset < end_sector) {
> rdev = rcu_dereference(conf->disks[dd_idx].rdev);
> - if (rdev &&
> - (test_bit(Faulty, &rdev->flags) ||
> + if (!rdev)
> + goto out_rcu_unlock;
> + if (test_bit(Faulty, &rdev->flags) ||
> !(test_bit(In_sync, &rdev->flags) ||
> - rdev->recovery_offset >= end_sector)))
> - rdev = NULL;
> + rdev->recovery_offset >= end_sector))
> + goto out_rcu_unlock;
> }
>
> - if (r5c_big_stripe_cached(conf, align_bi->bi_iter.bi_sector)) {
> - rcu_read_unlock();
> - bio_put(align_bi);
> + atomic_inc(&rdev->nr_pending);
> + rcu_read_unlock();
> +
> + align_bio = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set);
> + bio_set_dev(align_bio, rdev->bdev);
> + align_bio->bi_end_io = raid5_align_endio;
> + align_bio->bi_private = raid_bio;
> + align_bio->bi_iter.bi_sector = sector;
> +
> + raid_bio->bi_next = (void *)rdev;
> +
> + if (is_badblock(rdev, sector, bio_sectors(align_bio), &first_bad,
> + &bad_sectors)) {
> + bio_put(align_bio);
> + rdev_dec_pending(rdev, mddev);
> return 0;
> }
>
> - if (rdev) {
> - sector_t first_bad;
> - int bad_sectors;
> -
> - atomic_inc(&rdev->nr_pending);
> - rcu_read_unlock();
> - raid_bio->bi_next = (void*)rdev;
> - bio_set_dev(align_bi, rdev->bdev);
> -
> - if (is_badblock(rdev, align_bi->bi_iter.bi_sector,
> - bio_sectors(align_bi),
> - &first_bad, &bad_sectors)) {
> - bio_put(align_bi);
> - rdev_dec_pending(rdev, mddev);
> - return 0;
> - }
> + /* No reshape active, so we can trust rdev->data_offset */
> + align_bio->bi_iter.bi_sector += rdev->data_offset;
>
> - /* No reshape active, so we can trust rdev->data_offset */
> - align_bi->bi_iter.bi_sector += rdev->data_offset;
> + spin_lock_irq(&conf->device_lock);
> + wait_event_lock_irq(conf->wait_for_quiescent, conf->quiesce == 0,
> + conf->device_lock);
> + atomic_inc(&conf->active_aligned_reads);
> + spin_unlock_irq(&conf->device_lock);
>
> - spin_lock_irq(&conf->device_lock);
> - wait_event_lock_irq(conf->wait_for_quiescent,
> - conf->quiesce == 0,
> - conf->device_lock);
> - atomic_inc(&conf->active_aligned_reads);
> - spin_unlock_irq(&conf->device_lock);
> + if (mddev->gendisk)
> + trace_block_bio_remap(align_bio, disk_devt(mddev->gendisk),
> + raid_bio->bi_iter.bi_sector);
> + submit_bio_noacct(align_bio);
> + return 1;
>
> - if (mddev->gendisk)
> - trace_block_bio_remap(align_bi, disk_devt(mddev->gendisk),
> - raid_bio->bi_iter.bi_sector);
> - submit_bio_noacct(align_bi);
> - return 1;
> - } else {
> - rcu_read_unlock();
> - bio_put(align_bi);
> - return 0;
> - }
> +out_rcu_unlock:
> + rcu_read_unlock();
> + return 0;
> }
>
> static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
> --
> 2.29.2
>
On Tue, Jan 26, 2021 at 7:17 AM Christoph Hellwig <[email protected]> wrote:
>
> md_bio_alloc_sync is never called with a NULL mddev, and ->sync_set is
> initialized in md_run, so it always must be initialized as well. Just
> open code the remaining call to bio_alloc_bioset.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Song Liu <[email protected]>
> ---
> drivers/md/md.c | 10 +---------
> 1 file changed, 1 insertion(+), 9 deletions(-)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 6a27f52007c871..399c81bddc1ae1 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -340,14 +340,6 @@ static int start_readonly;
> */
> static bool create_on_open = true;
>
> -static struct bio *md_bio_alloc_sync(struct mddev *mddev)
> -{
> - if (!mddev || !bioset_initialized(&mddev->sync_set))
> - return bio_alloc(GFP_NOIO, 1);
> -
> - return bio_alloc_bioset(GFP_NOIO, 1, &mddev->sync_set);
> -}
> -
> /*
> * We have a system wide 'event count' that is incremented
> * on any 'interesting' event, and readers of /proc/mdstat
> @@ -989,7 +981,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
> if (test_bit(Faulty, &rdev->flags))
> return;
>
> - bio = md_bio_alloc_sync(mddev);
> + bio = bio_alloc_bioset(GFP_NOIO, 1, &mddev->sync_set);
>
> atomic_inc(&rdev->nr_pending);
>
> --
> 2.29.2
>
On Tue, Jan 26, 2021 at 7:12 AM Christoph Hellwig <[email protected]> wrote:
>
> bio_alloc_mddev is never called with a NULL mddev, and ->bio_set is
> initialized in md_run, so it always must be initialized as well. Just
> open code the remaining call to bio_alloc_bioset.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Song Liu <[email protected]>
> ---
> drivers/md/md.c | 12 +-----------
> drivers/md/md.h | 2 --
> drivers/md/raid1.c | 2 +-
> drivers/md/raid10.c | 2 +-
> 4 files changed, 3 insertions(+), 15 deletions(-)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 7d1bb24add3107..e2b9dbb6e888f6 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -340,16 +340,6 @@ static int start_readonly;
> */
> static bool create_on_open = true;
>
> -struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
> - struct mddev *mddev)
> -{
> - if (!mddev || !bioset_initialized(&mddev->bio_set))
> - return bio_alloc(gfp_mask, nr_iovecs);
> -
> - return bio_alloc_bioset(gfp_mask, nr_iovecs, &mddev->bio_set);
> -}
> -EXPORT_SYMBOL_GPL(bio_alloc_mddev);
> -
> static struct bio *md_bio_alloc_sync(struct mddev *mddev)
> {
> if (!mddev || !bioset_initialized(&mddev->sync_set))
> @@ -613,7 +603,7 @@ static void submit_flushes(struct work_struct *ws)
> atomic_inc(&rdev->nr_pending);
> atomic_inc(&rdev->nr_pending);
> rcu_read_unlock();
> - bi = bio_alloc_mddev(GFP_NOIO, 0, mddev);
> + bi = bio_alloc_bioset(GFP_NOIO, 0, &mddev->bio_set);
> bi->bi_end_io = md_end_flush;
> bi->bi_private = rdev;
> bio_set_dev(bi, rdev->bdev);
> diff --git a/drivers/md/md.h b/drivers/md/md.h
> index f13290ccc1c248..bcbba1b5ec4a71 100644
> --- a/drivers/md/md.h
> +++ b/drivers/md/md.h
> @@ -742,8 +742,6 @@ extern void md_rdev_clear(struct md_rdev *rdev);
> extern void md_handle_request(struct mddev *mddev, struct bio *bio);
> extern void mddev_suspend(struct mddev *mddev);
> extern void mddev_resume(struct mddev *mddev);
> -extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
> - struct mddev *mddev);
>
> extern void md_reload_sb(struct mddev *mddev, int raid_disk);
> extern void md_update_sb(struct mddev *mddev, int force);
> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
> index 3b19141cdb4bc2..d2378765dc154f 100644
> --- a/drivers/md/raid1.c
> +++ b/drivers/md/raid1.c
> @@ -1104,7 +1104,7 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio,
> int i = 0;
> struct bio *behind_bio = NULL;
>
> - behind_bio = bio_alloc_mddev(GFP_NOIO, vcnt, r1_bio->mddev);
> + behind_bio = bio_alloc_bioset(GFP_NOIO, vcnt, &r1_bio->mddev->bio_set);
> if (!behind_bio)
> return;
>
> diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
> index be8f14afb6d143..e1eefbec15d444 100644
> --- a/drivers/md/raid10.c
> +++ b/drivers/md/raid10.c
> @@ -4531,7 +4531,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
> return sectors_done;
> }
>
> - read_bio = bio_alloc_mddev(GFP_KERNEL, RESYNC_PAGES, mddev);
> + read_bio = bio_alloc_bioset(GFP_KERNEL, RESYNC_PAGES, &mddev->bio_set);
>
> bio_set_dev(read_bio, rdev->bdev);
> read_bio->bi_iter.bi_sector = (r10_bio->devs[r10_bio->read_slot].addr
> --
> 2.29.2
>
On Tue, Jan 26, 2021 at 7:14 AM Christoph Hellwig <[email protected]> wrote:
>
> Use an on-stack bio and biovec for the single page synchronous I/O.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Song Liu <[email protected]>
> ---
> drivers/md/md.c | 26 +++++++++++++-------------
> 1 file changed, 13 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index e2b9dbb6e888f6..6a27f52007c871 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -1021,29 +1021,29 @@ int md_super_wait(struct mddev *mddev)
> int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
> struct page *page, int op, int op_flags, bool metadata_op)
> {
> - struct bio *bio = md_bio_alloc_sync(rdev->mddev);
> - int ret;
> + struct bio bio;
> + struct bio_vec bvec;
> +
> + bio_init(&bio, &bvec, 1);
>
> if (metadata_op && rdev->meta_bdev)
> - bio_set_dev(bio, rdev->meta_bdev);
> + bio_set_dev(&bio, rdev->meta_bdev);
> else
> - bio_set_dev(bio, rdev->bdev);
> - bio_set_op_attrs(bio, op, op_flags);
> + bio_set_dev(&bio, rdev->bdev);
> + bio.bi_opf = op | op_flags;
> if (metadata_op)
> - bio->bi_iter.bi_sector = sector + rdev->sb_start;
> + bio.bi_iter.bi_sector = sector + rdev->sb_start;
> else if (rdev->mddev->reshape_position != MaxSector &&
> (rdev->mddev->reshape_backwards ==
> (sector >= rdev->mddev->reshape_position)))
> - bio->bi_iter.bi_sector = sector + rdev->new_data_offset;
> + bio.bi_iter.bi_sector = sector + rdev->new_data_offset;
> else
> - bio->bi_iter.bi_sector = sector + rdev->data_offset;
> - bio_add_page(bio, page, size, 0);
> + bio.bi_iter.bi_sector = sector + rdev->data_offset;
> + bio_add_page(&bio, page, size, 0);
>
> - submit_bio_wait(bio);
> + submit_bio_wait(&bio);
>
> - ret = !bio->bi_status;
> - bio_put(bio);
> - return ret;
> + return !bio.bi_status;
> }
> EXPORT_SYMBOL_GPL(sync_page_io);
>
> --
> 2.29.2
>
On 1/26/21 7:52 AM, Christoph Hellwig wrote:
> Hi Jens,
>
> this series contains various cleanups for how bios are allocated or
> initialized plus related fallout.
Applied, thanks.
--
Jens Axboe
On 01/26, Christoph Hellwig wrote:
> Sleeping bio allocations do not fail, which means that injecting an error
> into sleeping bio allocations is a little silly.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
Already merged tho.
Acked-by: Jaegeuk Kim <[email protected]>
> ---
> Documentation/filesystems/f2fs.rst | 1 -
> fs/f2fs/data.c | 29 ++++-------------------------
> fs/f2fs/f2fs.h | 1 -
> fs/f2fs/super.c | 1 -
> 4 files changed, 4 insertions(+), 28 deletions(-)
>
> diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
> index dae15c96e659e2..624f5f3ed93e86 100644
> --- a/Documentation/filesystems/f2fs.rst
> +++ b/Documentation/filesystems/f2fs.rst
> @@ -179,7 +179,6 @@ fault_type=%d Support configuring fault injection type, should be
> FAULT_KVMALLOC 0x000000002
> FAULT_PAGE_ALLOC 0x000000004
> FAULT_PAGE_GET 0x000000008
> - FAULT_ALLOC_BIO 0x000000010
> FAULT_ALLOC_NID 0x000000020
> FAULT_ORPHAN 0x000000040
> FAULT_BLOCK 0x000000080
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index 0cf0c605992431..9fb6be65592b1f 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -50,28 +50,6 @@ void f2fs_destroy_bioset(void)
> bioset_exit(&f2fs_bioset);
> }
>
> -static inline struct bio *__f2fs_bio_alloc(gfp_t gfp_mask,
> - unsigned int nr_iovecs)
> -{
> - return bio_alloc_bioset(gfp_mask, nr_iovecs, &f2fs_bioset);
> -}
> -
> -static struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages,
> - bool noio)
> -{
> - if (noio) {
> - /* No failure on bio allocation */
> - return __f2fs_bio_alloc(GFP_NOIO, npages);
> - }
> -
> - if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
> - f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO);
> - return NULL;
> - }
> -
> - return __f2fs_bio_alloc(GFP_KERNEL, npages);
> -}
> -
> static bool __is_cp_guaranteed(struct page *page)
> {
> struct address_space *mapping = page->mapping;
> @@ -433,7 +411,7 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
> struct f2fs_sb_info *sbi = fio->sbi;
> struct bio *bio;
>
> - bio = f2fs_bio_alloc(sbi, npages, true);
> + bio = bio_alloc_bioset(GFP_NOIO, npages, &f2fs_bioset);
>
> f2fs_target_device(sbi, fio->new_blkaddr, bio);
> if (is_read_io(fio->op)) {
> @@ -1029,8 +1007,9 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
> struct bio_post_read_ctx *ctx;
> unsigned int post_read_steps = 0;
>
> - bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES),
> - for_write);
> + bio = bio_alloc_bioset(for_write ? GFP_NOIO : GFP_KERNEL,
> + min_t(int, nr_pages, BIO_MAX_PAGES),
> + &f2fs_bioset);
> if (!bio)
> return ERR_PTR(-ENOMEM);
>
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index 902bd3267c03e1..6c78365d80ceb5 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -43,7 +43,6 @@ enum {
> FAULT_KVMALLOC,
> FAULT_PAGE_ALLOC,
> FAULT_PAGE_GET,
> - FAULT_ALLOC_BIO,
> FAULT_ALLOC_NID,
> FAULT_ORPHAN,
> FAULT_BLOCK,
> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
> index b4a07fe62d1a58..3a312642907e86 100644
> --- a/fs/f2fs/super.c
> +++ b/fs/f2fs/super.c
> @@ -45,7 +45,6 @@ const char *f2fs_fault_name[FAULT_MAX] = {
> [FAULT_KVMALLOC] = "kvmalloc",
> [FAULT_PAGE_ALLOC] = "page alloc",
> [FAULT_PAGE_GET] = "page get",
> - [FAULT_ALLOC_BIO] = "alloc bio",
> [FAULT_ALLOC_NID] = "alloc nid",
> [FAULT_ORPHAN] = "orphan",
> [FAULT_BLOCK] = "no more block",
> --
> 2.29.2
On 2021/1/26 22:52, Christoph Hellwig wrote:
> Use the blkdev_issue_flush helper instead of duplicating it.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Chao Yu <[email protected]>
Thanks,
On 2021/1/26 22:52, Christoph Hellwig wrote:
> Sleeping bio allocations do not fail, which means that injecting an error
> into sleeping bio allocations is a little silly.
>
> Signed-off-by: Christoph Hellwig<[email protected]>
Acked-by: Chao Yu <[email protected]>
Thanks,
On Tue, Jan 26, 2021 at 03:52:34PM +0100, Christoph Hellwig wrote:
> bio_kmalloc shares almost no logic with the bio_set based fast path
> in bio_alloc_bioset. Split it into an entirely separate implementation.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> block/bio.c | 167 ++++++++++++++++++++++----------------------
> include/linux/bio.h | 6 +-
> 2 files changed, 86 insertions(+), 87 deletions(-)
This patch causes current linux-next to OOM for me when running xfstests
after about ten minutes. Haven't looked into why yet, this is just the
results of a git bisect.
The qemu command line is:
qemu-system-x86_64 -nodefaults -nographic -cpu host -machine accel=kvm,nvdimm -m 2G,slots=8,maxmem=1T -smp 6 -kernel /home/willy/kernel/folio/.build_test_kernel-x86_64/kpgk/vmlinuz -append console=hvc0 root=/dev/sda rw log_buf_len=8M ktest.dir=/home/willy/kernel/ktest ktest.env=/tmp/build-test-kernel-nJO6QgxOmo/env quiet systemd.show_status=0 systemd.log-target=journal crashkernel=128M no_console_suspend -device virtio-serial -chardev stdio,id=console -device virtconsole,chardev=console -serial unix:/tmp/build-test-kernel-nJO6QgxOmo/vm-kgdb,server,nowait -monitor unix:/tmp/build-test-kernel-nJO6QgxOmo/vm-mon,server,nowait -gdb unix:/tmp/build-test-kernel-nJO6QgxOmo/vm-gdb,server,nowait -device virtio-rng-pci -virtfs local,path=/,mount_tag=host,security_model=none -device virtio-scsi-pci,id=hba -nic user,model=virtio,hostfwd=tcp:127.0.0.1:24674-:22 -drive if=none,format=raw,id=disk0,file=/var/lib/ktest/root.amd64,snapshot=on -device scsi-hd,bus=hba.0,drive=disk0 -drive if=none,format=raw,id=disk1,file=/tmp/build-test-kernel-nJO6QgxOmo/dev-1,cache=unsafe -device scsi-hd,bus=hba.0,drive=disk1 -drive if=none,format=raw,id=disk2,file=/tmp/build-test-kernel-nJO6QgxOmo/dev-2,cache=unsafe -device scsi-hd,bus=hba.0,drive=disk2 -drive if=none,format=raw,id=disk3,file=/tmp/build-test-kernel-nJO6QgxOmo/dev-3,cache=unsafe -device scsi-hd,bus=hba.0,drive=disk3
Hi Christoph,
I tried with latest for-5.12/block branch, and got below issue when
trying to create raid1 array.
[ 80.605832] BUG: kernel NULL pointer dereference, address:
0000000000000018
[ 80.606159] #PF: supervisor read access in kernel mode
[ 80.606159] #PF: error_code(0x0000) - not-present page
[ 80.606159] PGD 0 P4D 0
[ 80.606159] Oops: 0000 [#1] SMP NOPTI
[ 80.606159] CPU: 1 PID: 207 Comm: mdadm Not tainted 5.11.0-rc5+ #37
[ 80.606159] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS 1.10.2-1ubuntu1 04/01/2014
[ 80.606159] RIP: 0010:bdev_read_only+0x0/0x30
[ 80.606159] Code: 89 df 5b 5d e9 71 21 e7 ff 81 e6 ff ff 0f 00 48 c7
c7 40 99 d9 9e e8 0f e5 04 00 eb a0 0f 1f 00 66 2e 0f 1f 84 00 00 00 00
00 <80> 7f 18 00 b8 01 00 00 00 75 11 48 8b 97 60 03 00 00 48 8b 4a 40
[ 80.606159] RSP: 0018:ffffb14f405dfd38 EFLAGS: 00000246
[ 80.606159] RAX: 0000000000000000 RBX: ffff9b0e0863b018 RCX:
ffff9b0e01edc000
[ 80.606159] RDX: ffff9b0e01b54c00 RSI: ffff9b0e0863b000 RDI:
0000000000000000
[ 80.606159] RBP: ffff9b0e01272200 R08: 0000000000000000 R09:
0000000000000000
[ 80.606159] R10: ffffee978004da40 R11: 0000000000000cc0 R12:
ffff9b0e0863b000
[ 80.606159] R13: ffff9b0e01f2cc00 R14: ffff9b0e0863b000 R15:
0000000000000000
[ 80.606159] FS: 00007f522ec65740(0000) GS:ffff9b0e7bc80000(0000)
knlGS:0000000000000000
[ 80.606159] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 80.606159] CR2: 0000000000000018 CR3: 0000000001364000 CR4:
00000000000006e0
[ 80.606159] Call Trace:
[ 80.606159] bind_rdev_to_array+0x2f7/0x380
[ 80.606159] ? cred_has_capability+0x80/0x120
[ 80.606159] md_add_new_disk+0x204/0x630
[ 80.606159] ? security_capable+0x33/0x50
[ 80.606159] md_ioctl+0xee7/0x1690
[ 80.606159] ? selinux_file_ioctl+0x143/0x200
[ 80.606159] blkdev_ioctl+0x1ff/0x240
[ 80.606159] block_ioctl+0x34/0x40
[ 80.606159] __x64_sys_ioctl+0x89/0xc0
[ 80.606159] do_syscall_64+0x33/0x40
[ 80.606159] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 80.606159] RIP: 0033:0x7f522e564317
[ 80.606159] Code: b3 66 90 48 8b 05 71 4b 2d 00 64 c7 00 26 00 00 00
48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f
05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 41 4b 2d 00 f7 d8 64 89 01 48
[ 80.606159] RSP: 002b:00007ffc3abd96f8 EFLAGS: 00000246 ORIG_RAX:
0000000000000010
[ 80.606159] RAX: ffffffffffffffda RBX: 00005653ee690350 RCX:
00007f522e564317
[ 80.606159] RDX: 00005653ee694058 RSI: 0000000040140921 RDI:
0000000000000004
[ 80.606159] RBP: 00005653ee690410 R08: 00007f522e839db0 R09:
0000000000000000
[ 80.606159] R10: 00005653ee690010 R11: 0000000000000246 R12:
0000000000000000
[ 80.606159] R13: 0000000000000000 R14: 0000000000000000 R15:
00005653ee694010
[ 80.606159] Modules linked in:
[ 80.606159] CR2: 0000000000000018
[ 80.622996] ---[ end trace 22144b856a3c1001 ]---
[ 80.623285] RIP: 0010:bdev_read_only+0x0/0x30
[ 80.623501] Code: 89 df 5b 5d e9 71 21 e7 ff 81 e6 ff ff 0f 00 48 c7
c7 40 99 d9 9e e8 0f e5 04 00 eb a0 0f 1f 00 66 2e 0f 1f 84 00 00 00 00
00 <80> 7f 18 00 b8 01 00 00 00 75 11 48 8b 97 60 03 00 00 48 8b 4a 40
[ 80.624544] RSP: 0018:ffffb14f405dfd38 EFLAGS: 00000246
[ 80.624788] RAX: 0000000000000000 RBX: ffff9b0e0863b018 RCX:
ffff9b0e01edc000
[ 80.625136] RDX: ffff9b0e01b54c00 RSI: ffff9b0e0863b000 RDI:
0000000000000000
[ 80.625449] RBP: ffff9b0e01272200 R08: 0000000000000000 R09:
0000000000000000
[ 80.625761] R10: ffffee978004da40 R11: 0000000000000cc0 R12:
ffff9b0e0863b000
[ 80.626112] R13: ffff9b0e01f2cc00 R14: ffff9b0e0863b000 R15:
0000000000000000
[ 80.626429] FS: 00007f522ec65740(0000) GS:ffff9b0e7bc80000(0000)
knlGS:0000000000000000
[ 80.626784] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 80.627035] CR2: 0000000000000018 CR3: 0000000001364000 CR4:
00000000000006e0
Killed
Thanks,
Guoqing
On Sat, Jan 30, 2021 at 03:56:46AM +0000, Matthew Wilcox wrote:
> On Tue, Jan 26, 2021 at 03:52:34PM +0100, Christoph Hellwig wrote:
> > bio_kmalloc shares almost no logic with the bio_set based fast path
> > in bio_alloc_bioset. Split it into an entirely separate implementation.
> >
> > Signed-off-by: Christoph Hellwig <[email protected]>
> > ---
> > block/bio.c | 167 ++++++++++++++++++++++----------------------
> > include/linux/bio.h | 6 +-
> > 2 files changed, 86 insertions(+), 87 deletions(-)
>
> This patch causes current linux-next to OOM for me when running xfstests
> after about ten minutes. Haven't looked into why yet, this is just the
> results of a git bisect.
I've run tests on linux-next all weekend and could not reproduce
the issue. Can you share your .config?