diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-08-05 23:31:51 -0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-08-05 23:31:51 -0400 |
commit | fff648da962992eeef607100e1df070de0173692 (patch) | |
tree | 300ed947c82f5934f31d322460d26d796fac7c1a | |
parent | 62e6e9bab3014e3931ffbc82de7a9d2fd94cb8cd (diff) | |
parent | abf545484d31b68777a85c5c8f5b4bcde08283eb (diff) | |
download | op-kernel-dev-fff648da962992eeef607100e1df070de0173692.zip op-kernel-dev-fff648da962992eeef607100e1df070de0173692.tar.gz |
Merge branch 'for-linus' of git://git.kernel.dk/linux-block
Pull block fixes from Jens Axboe:
"Here's the second round of block updates for this merge window.
It's a mix of fixes for changes that went in previously in this round,
and fixes in general. This pull request contains:
- Fixes for loop from Christoph
- A bdi vs gendisk lifetime fix from Dan, worth two cookies.
- A blk-mq timeout fix, when on frozen queues. From Gabriel.
- Writeback fix from Jan, ensuring that __writeback_single_inode()
does the right thing.
- Fix for bio->bi_rw usage in f2fs from me.
- Error path deadlock fix in blk-mq sysfs registration from me.
- Floppy O_ACCMODE fix from Jiri.
- Fix to the new bio op methods from Mike.
One more followup will be coming here, ensuring that we don't
propagate the block types outside of block. That, and a rename of
bio->bi_rw is coming right after -rc1 is cut.
- Various little fixes"
* 'for-linus' of git://git.kernel.dk/linux-block:
mm/block: convert rw_page users to bio op use
loop: make do_req_filebacked more robust
loop: don't try to use AIO for discards
blk-mq: fix deadlock in blk_mq_register_disk() error path
Include: blkdev: Removed duplicate 'struct request;' declaration.
Fixup direct bi_rw modifiers
block: fix bdi vs gendisk lifetime mismatch
blk-mq: Allow timeouts to run while queue is freezing
nbd: fix race in ioctl
block: fix use-after-free in seq file
f2fs: drop bio->bi_rw manual assignment
block: add missing group association in bio-cloning functions
blkcg: kill unused field nr_undestroyed_grps
writeback: Write dirty times for WB_SYNC_ALL writeback
floppy: fix open(O_ACCMODE) for ioctl-only open
-rw-r--r-- | block/bio.c | 15 | ||||
-rw-r--r-- | block/blk-mq-sysfs.c | 12 | ||||
-rw-r--r-- | block/blk-mq.c | 15 | ||||
-rw-r--r-- | block/blk-throttle.c | 5 | ||||
-rw-r--r-- | block/genhd.c | 3 | ||||
-rw-r--r-- | drivers/block/brd.c | 17 | ||||
-rw-r--r-- | drivers/block/floppy.c | 21 | ||||
-rw-r--r-- | drivers/block/loop.c | 67 | ||||
-rw-r--r-- | drivers/block/nbd.c | 12 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.c | 28 | ||||
-rw-r--r-- | drivers/nvdimm/btt.c | 18 | ||||
-rw-r--r-- | drivers/nvdimm/pmem.c | 12 | ||||
-rw-r--r-- | fs/block_dev.c | 7 | ||||
-rw-r--r-- | fs/btrfs/extent_io.c | 8 | ||||
-rw-r--r-- | fs/f2fs/data.c | 1 | ||||
-rw-r--r-- | fs/fs-writeback.c | 1 | ||||
-rw-r--r-- | fs/mpage.c | 2 | ||||
-rw-r--r-- | include/linux/backing-dev-defs.h | 1 | ||||
-rw-r--r-- | include/linux/backing-dev.h | 1 | ||||
-rw-r--r-- | include/linux/bio.h | 3 | ||||
-rw-r--r-- | include/linux/blk_types.h | 22 | ||||
-rw-r--r-- | include/linux/blkdev.h | 3 | ||||
-rw-r--r-- | include/linux/fs.h | 3 | ||||
-rw-r--r-- | include/linux/pagemap.h | 2 | ||||
-rw-r--r-- | mm/backing-dev.c | 19 | ||||
-rw-r--r-- | mm/filemap.c | 6 |
26 files changed, 168 insertions, 136 deletions
diff --git a/block/bio.c b/block/bio.c index 54ee384..3f76a38 100644 --- a/block/bio.c +++ b/block/bio.c @@ -583,6 +583,8 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) bio->bi_rw = bio_src->bi_rw; bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; + + bio_clone_blkcg_association(bio, bio_src); } EXPORT_SYMBOL(__bio_clone_fast); @@ -687,6 +689,8 @@ integrity_clone: } } + bio_clone_blkcg_association(bio, bio_src); + return bio; } EXPORT_SYMBOL(bio_clone_bioset); @@ -2004,6 +2008,17 @@ void bio_disassociate_task(struct bio *bio) } } +/** + * bio_clone_blkcg_association - clone blkcg association from src to dst bio + * @dst: destination bio + * @src: source bio + */ +void bio_clone_blkcg_association(struct bio *dst, struct bio *src) +{ + if (src->bi_css) + WARN_ON(bio_associate_blkcg(dst, src->bi_css)); +} + #endif /* CONFIG_BLK_CGROUP */ static void __init biovec_init_slabs(void) diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 4ea4dd8..fe822aa 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -380,15 +380,13 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx) return ret; } -void blk_mq_unregister_disk(struct gendisk *disk) +static void __blk_mq_unregister_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; int i, j; - blk_mq_disable_hotplug(); - queue_for_each_hw_ctx(q, hctx, i) { blk_mq_unregister_hctx(hctx); @@ -405,6 +403,12 @@ void blk_mq_unregister_disk(struct gendisk *disk) kobject_put(&disk_to_dev(disk)->kobj); q->mq_sysfs_init_done = false; +} + +void blk_mq_unregister_disk(struct gendisk *disk) +{ + blk_mq_disable_hotplug(); + __blk_mq_unregister_disk(disk); blk_mq_enable_hotplug(); } @@ -450,7 +454,7 @@ int blk_mq_register_disk(struct gendisk *disk) } if (ret) - blk_mq_unregister_disk(disk); + __blk_mq_unregister_disk(disk); else q->mq_sysfs_init_done = true; out: diff --git a/block/blk-mq.c b/block/blk-mq.c index 576e711..6a63da1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -672,7 +672,20 @@ static void blk_mq_timeout_work(struct work_struct *work) }; int i; - if (blk_queue_enter(q, true)) + /* A deadlock might occur if a request is stuck requiring a + * timeout at the same time a queue freeze is waiting + * completion, since the timeout code would not be able to + * acquire the queue reference here. + * + * That's why we don't use blk_queue_enter here; instead, we use + * percpu_ref_tryget directly, because we need to be able to + * obtain a reference even in the short window between the queue + * starting to freeze, by dropping the first reference in + * blk_mq_freeze_queue_start, and the moment the last request is + * consumed, marked by the instant q_usage_counter reaches + * zero. + */ + if (!percpu_ref_tryget(&q->q_usage_counter)) return; blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 47a3e54..c5494e4 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -145,11 +145,6 @@ struct throtl_data /* Total Number of queued bios on READ and WRITE lists */ unsigned int nr_queued[2]; - /* - * number of total undestroyed groups - */ - unsigned int nr_undestroyed_grps; - /* Work for dispatching throttled bios */ struct work_struct dispatch_work; }; diff --git a/block/genhd.c b/block/genhd.c index 3c9dede..fcd6d4f 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -614,7 +614,7 @@ void device_add_disk(struct device *parent, struct gendisk *disk) /* Register BDI before referencing it from bdev */ bdi = &disk->queue->backing_dev_info; - bdi_register_dev(bdi, disk_devt(disk)); + bdi_register_owner(bdi, disk_to_dev(disk)); blk_register_region(disk_devt(disk), disk->minors, NULL, exact_match, exact_lock, disk); @@ -856,6 +856,7 @@ static void disk_seqf_stop(struct seq_file *seqf, void *v) if (iter) { class_dev_iter_exit(iter); kfree(iter); + seqf->private = NULL; } } diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 3022dad..3439b28 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -300,20 +300,20 @@ static void copy_from_brd(void *dst, struct brd_device *brd, * Process a single bvec of a bio. */ static int brd_do_bvec(struct brd_device *brd, struct page *page, - unsigned int len, unsigned int off, int rw, + unsigned int len, unsigned int off, int op, sector_t sector) { void *mem; int err = 0; - if (rw != READ) { + if (op_is_write(op)) { err = copy_to_brd_setup(brd, sector, len); if (err) goto out; } mem = kmap_atomic(page); - if (rw == READ) { + if (!op_is_write(op)) { copy_from_brd(mem + off, brd, sector, len); flush_dcache_page(page); } else { @@ -330,7 +330,6 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio) { struct block_device *bdev = bio->bi_bdev; struct brd_device *brd = bdev->bd_disk->private_data; - int rw; struct bio_vec bvec; sector_t sector; struct bvec_iter iter; @@ -347,14 +346,12 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio) goto out; } - rw = bio_data_dir(bio); - bio_for_each_segment(bvec, bio, iter) { unsigned int len = bvec.bv_len; int err; err = brd_do_bvec(brd, bvec.bv_page, len, - bvec.bv_offset, rw, sector); + bvec.bv_offset, bio_op(bio), sector); if (err) goto io_error; sector += len >> SECTOR_SHIFT; @@ -369,11 +366,11 @@ io_error: } static int brd_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, int rw) + struct page *page, int op) { struct brd_device *brd = bdev->bd_disk->private_data; - int err = brd_do_bvec(brd, page, PAGE_SIZE, 0, rw, sector); - page_endio(page, rw & WRITE, err); + int err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector); + page_endio(page, op, err); return err; } diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index c557057..b71a9c7 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3663,11 +3663,6 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) opened_bdev[drive] = bdev; - if (!(mode & (FMODE_READ|FMODE_WRITE))) { - res = -EINVAL; - goto out; - } - res = -ENXIO; if (!floppy_track_buffer) { @@ -3711,13 +3706,15 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) if (UFDCS->rawcmd == 1) UFDCS->rawcmd = 2; - UDRS->last_checked = 0; - clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); - check_disk_change(bdev); - if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) - goto out; - if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) - goto out; + if (mode & (FMODE_READ|FMODE_WRITE)) { + UDRS->last_checked = 0; + clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); + check_disk_change(bdev); + if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) + goto out; + if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) + goto out; + } res = -EROFS; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 075377e..c9f2107 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -510,14 +510,10 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, return 0; } - -static inline int lo_rw_simple(struct loop_device *lo, - struct request *rq, loff_t pos, bool rw) +static int do_req_filebacked(struct loop_device *lo, struct request *rq) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); - - if (cmd->use_aio) - return lo_rw_aio(lo, cmd, pos, rw); + loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset; /* * lo_write_simple and lo_read_simple should have been covered @@ -528,37 +524,30 @@ static inline int lo_rw_simple(struct loop_device *lo, * of the req at one time. And direct read IO doesn't need to * run flush_dcache_page(). */ - if (rw == WRITE) - return lo_write_simple(lo, rq, pos); - else - return lo_read_simple(lo, rq, pos); -} - -static int do_req_filebacked(struct loop_device *lo, struct request *rq) -{ - loff_t pos; - int ret; - - pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset; - - if (op_is_write(req_op(rq))) { - if (req_op(rq) == REQ_OP_FLUSH) - ret = lo_req_flush(lo, rq); - else if (req_op(rq) == REQ_OP_DISCARD) - ret = lo_discard(lo, rq, pos); - else if (lo->transfer) - ret = lo_write_transfer(lo, rq, pos); + switch (req_op(rq)) { + case REQ_OP_FLUSH: + return lo_req_flush(lo, rq); + case REQ_OP_DISCARD: + return lo_discard(lo, rq, pos); + case REQ_OP_WRITE: + if (lo->transfer) + return lo_write_transfer(lo, rq, pos); + else if (cmd->use_aio) + return lo_rw_aio(lo, cmd, pos, WRITE); else - ret = lo_rw_simple(lo, rq, pos, WRITE); - - } else { + return lo_write_simple(lo, rq, pos); + case REQ_OP_READ: if (lo->transfer) - ret = lo_read_transfer(lo, rq, pos); + return lo_read_transfer(lo, rq, pos); + else if (cmd->use_aio) + return lo_rw_aio(lo, cmd, pos, READ); else - ret = lo_rw_simple(lo, rq, pos, READ); + return lo_read_simple(lo, rq, pos); + default: + WARN_ON_ONCE(1); + return -EIO; + break; } - - return ret; } struct switch_request { @@ -1659,11 +1648,15 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx, if (lo->lo_state != Lo_bound) return -EIO; - if (lo->use_dio && (req_op(cmd->rq) != REQ_OP_FLUSH || - req_op(cmd->rq) == REQ_OP_DISCARD)) - cmd->use_aio = true; - else + switch (req_op(cmd->rq)) { + case REQ_OP_FLUSH: + case REQ_OP_DISCARD: cmd->use_aio = false; + break; + default: + cmd->use_aio = lo->use_dio; + break; + } queue_kthread_work(&lo->worker, &cmd->work); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 6f55b26..a9e3980 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -451,14 +451,9 @@ static int nbd_thread_recv(struct nbd_device *nbd, struct block_device *bdev) sk_set_memalloc(nbd->sock->sk); - nbd->task_recv = current; - ret = device_create_file(disk_to_dev(nbd->disk), &pid_attr); if (ret) { dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n"); - - nbd->task_recv = NULL; - return ret; } @@ -477,9 +472,6 @@ static int nbd_thread_recv(struct nbd_device *nbd, struct block_device *bdev) nbd_size_clear(nbd, bdev); device_remove_file(disk_to_dev(nbd->disk), &pid_attr); - - nbd->task_recv = NULL; - return ret; } @@ -788,6 +780,8 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, if (!nbd->sock) return -EINVAL; + /* We have to claim the device under the lock */ + nbd->task_recv = current; mutex_unlock(&nbd->tx_lock); nbd_parse_flags(nbd, bdev); @@ -796,6 +790,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, nbd_name(nbd)); if (IS_ERR(thread)) { mutex_lock(&nbd->tx_lock); + nbd->task_recv = NULL; return PTR_ERR(thread); } @@ -805,6 +800,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, kthread_stop(thread); mutex_lock(&nbd->tx_lock); + nbd->task_recv = NULL; sock_shutdown(nbd); nbd_clear_que(nbd); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 7454cf1..ca29649 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -843,15 +843,15 @@ static void zram_bio_discard(struct zram *zram, u32 index, } static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, - int offset, int rw) + int offset, int op) { unsigned long start_time = jiffies; int ret; - generic_start_io_acct(rw, bvec->bv_len >> SECTOR_SHIFT, + generic_start_io_acct(op, bvec->bv_len >> SECTOR_SHIFT, &zram->disk->part0); - if (rw == READ) { + if (!op_is_write(op)) { atomic64_inc(&zram->stats.num_reads); ret = zram_bvec_read(zram, bvec, index, offset); } else { @@ -859,10 +859,10 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, ret = zram_bvec_write(zram, bvec, index, offset); } - generic_end_io_acct(rw, &zram->disk->part0, start_time); + generic_end_io_acct(op, &zram->disk->part0, start_time); if (unlikely(ret)) { - if (rw == READ) + if (!op_is_write(op)) atomic64_inc(&zram->stats.failed_reads); else atomic64_inc(&zram->stats.failed_writes); @@ -873,7 +873,7 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, static void __zram_make_request(struct zram *zram, struct bio *bio) { - int offset, rw; + int offset; u32 index; struct bio_vec bvec; struct bvec_iter iter; @@ -888,7 +888,6 @@ static void __zram_make_request(struct zram *zram, struct bio *bio) return; } - rw = bio_data_dir(bio); bio_for_each_segment(bvec, bio, iter) { int max_transfer_size = PAGE_SIZE - offset; @@ -903,15 +902,18 @@ static void __zram_make_request(struct zram *zram, struct bio *bio) bv.bv_len = max_transfer_size; bv.bv_offset = bvec.bv_offset; - if (zram_bvec_rw(zram, &bv, index, offset, rw) < 0) + if (zram_bvec_rw(zram, &bv, index, offset, + bio_op(bio)) < 0) goto out; bv.bv_len = bvec.bv_len - max_transfer_size; bv.bv_offset += max_transfer_size; - if (zram_bvec_rw(zram, &bv, index + 1, 0, rw) < 0) + if (zram_bvec_rw(zram, &bv, index + 1, 0, + bio_op(bio)) < 0) goto out; } else - if (zram_bvec_rw(zram, &bvec, index, offset, rw) < 0) + if (zram_bvec_rw(zram, &bvec, index, offset, + bio_op(bio)) < 0) goto out; update_position(&index, &offset, &bvec); @@ -968,7 +970,7 @@ static void zram_slot_free_notify(struct block_device *bdev, } static int zram_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, int rw) + struct page *page, int op) { int offset, err = -EIO; u32 index; @@ -992,7 +994,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector, bv.bv_len = PAGE_SIZE; bv.bv_offset = 0; - err = zram_bvec_rw(zram, &bv, index, offset, rw); + err = zram_bvec_rw(zram, &bv, index, offset, op); put_zram: zram_meta_put(zram); out: @@ -1005,7 +1007,7 @@ out: * (e.g., SetPageError, set_page_dirty and extra works). */ if (err == 0) - page_endio(page, rw, 0); + page_endio(page, op, 0); return err; } diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 9dce03f..7cf3bdf 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1133,11 +1133,11 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip, static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip, struct page *page, unsigned int len, unsigned int off, - int rw, sector_t sector) + int op, sector_t sector) { int ret; - if (rw == READ) { + if (!op_is_write(op)) { ret = btt_read_pg(btt, bip, page, off, sector, len); flush_dcache_page(page); } else { @@ -1155,7 +1155,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio) struct bvec_iter iter; unsigned long start; struct bio_vec bvec; - int err = 0, rw; + int err = 0; bool do_acct; /* @@ -1170,7 +1170,6 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio) } do_acct = nd_iostat_start(bio, &start); - rw = bio_data_dir(bio); bio_for_each_segment(bvec, bio, iter) { unsigned int len = bvec.bv_len; @@ -1181,11 +1180,12 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio) BUG_ON(len % btt->sector_size); err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset, - rw, iter.bi_sector); + bio_op(bio), iter.bi_sector); if (err) { dev_info(&btt->nd_btt->dev, "io error in %s sector %lld, len %d,\n", - (rw == READ) ? "READ" : "WRITE", + (op_is_write(bio_op(bio))) ? "WRITE" : + "READ", (unsigned long long) iter.bi_sector, len); bio->bi_error = err; break; @@ -1200,12 +1200,12 @@ out: } static int btt_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, int rw) + struct page *page, int op) { struct btt *btt = bdev->bd_disk->private_data; - btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, rw, sector); - page_endio(page, rw & WRITE, 0); + btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, op, sector); + page_endio(page, op, 0); return 0; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index b511099..d64d924 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -67,7 +67,7 @@ static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset, } static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, - unsigned int len, unsigned int off, int rw, + unsigned int len, unsigned int off, int op, sector_t sector) { int rc = 0; @@ -79,7 +79,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) bad_pmem = true; - if (rw == READ) { + if (!op_is_write(op)) { if (unlikely(bad_pmem)) rc = -EIO; else { @@ -134,7 +134,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) do_acct = nd_iostat_start(bio, &start); bio_for_each_segment(bvec, bio, iter) { rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, - bvec.bv_offset, bio_data_dir(bio), + bvec.bv_offset, bio_op(bio), iter.bi_sector); if (rc) { bio->bi_error = rc; @@ -152,12 +152,12 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) } static int pmem_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, int rw) + struct page *page, int op) { struct pmem_device *pmem = bdev->bd_queue->queuedata; int rc; - rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, rw, sector); + rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, op, sector); /* * The ->rw_page interface is subtle and tricky. The core @@ -166,7 +166,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, * caused by double completion. */ if (rc == 0) - page_endio(page, rw & WRITE, 0); + page_endio(page, op, 0); return rc; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 2033a3f..d402899 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -416,7 +416,8 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, result = blk_queue_enter(bdev->bd_queue, false); if (result) return result; - result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ); + result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, + REQ_OP_READ); blk_queue_exit(bdev->bd_queue); return result; } @@ -445,7 +446,6 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, struct page *page, struct writeback_control *wbc) { int result; - int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE; const struct block_device_operations *ops = bdev->bd_disk->fops; if (!ops->rw_page || bdev_get_integrity(bdev)) @@ -455,7 +455,8 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, return result; set_page_writeback(page); - result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw); + result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, + REQ_OP_WRITE); if (result) end_page_writeback(page); else diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 80d9283..44fe66b 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2049,7 +2049,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, return -EIO; } bio->bi_bdev = dev->bdev; - bio->bi_rw = WRITE_SYNC; + bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_SYNC); bio_add_page(bio, page, length, pg_offset); if (btrfsic_submit_bio_wait(bio)) { @@ -2697,12 +2697,6 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask) btrfs_bio->csum = NULL; btrfs_bio->csum_allocated = NULL; btrfs_bio->end_io = NULL; - -#ifdef CONFIG_BLK_CGROUP - /* FIXME, put this into bio_clone_bioset */ - if (bio->bi_css) - bio_associate_blkcg(new, bio->bi_css); -#endif } return new; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index e262427..d64d2a5 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -245,7 +245,6 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) bio_put(bio); return -EFAULT; } - bio->bi_rw = fio->op_flags; bio_set_op_attrs(bio, fio->op, fio->op_flags); __submit_bio(fio->sbi, bio, fio->type); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 56c8fda..4d09d44 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1327,6 +1327,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) dirty = inode->i_state & I_DIRTY; if (inode->i_state & I_DIRTY_TIME) { if ((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) || + wbc->sync_mode == WB_SYNC_ALL || unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) || unlikely(time_after(jiffies, (inode->dirtied_time_when + @@ -50,7 +50,7 @@ static void mpage_end_io(struct bio *bio) bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - page_endio(page, bio_data_dir(bio), bio->bi_error); + page_endio(page, bio_op(bio), bio->bi_error); } bio_put(bio); diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 3f10307..c357f27 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -163,6 +163,7 @@ struct backing_dev_info { wait_queue_head_t wb_waitq; struct device *dev; + struct device *owner; struct timer_list laptop_mode_wb_timer; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 491a917..43b93a9 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -24,6 +24,7 @@ __printf(3, 4) int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); +int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); diff --git a/include/linux/bio.h b/include/linux/bio.h index 583c108..e09a889 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -470,11 +470,14 @@ extern unsigned int bvec_nr_vecs(unsigned short idx); int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_current(struct bio *bio); void bio_disassociate_task(struct bio *bio); +void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { return 0; } static inline int bio_associate_current(struct bio *bio) { return -ENOENT; } static inline void bio_disassociate_task(struct bio *bio) { } +static inline void bio_clone_blkcg_association(struct bio *dst, + struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f254eb2..14b28ff 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -18,6 +18,17 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); typedef void (bio_destructor_t) (struct bio *); +enum req_op { + REQ_OP_READ, + REQ_OP_WRITE, + REQ_OP_DISCARD, /* request to discard sectors */ + REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ + REQ_OP_WRITE_SAME, /* write same block many times */ + REQ_OP_FLUSH, /* request for cache flush */ +}; + +#define REQ_OP_BITS 3 + #ifdef CONFIG_BLOCK /* * main unit of I/O for the block layer and lower layers (ie drivers and @@ -228,17 +239,6 @@ enum rq_flag_bits { #define REQ_HASHED (1ULL << __REQ_HASHED) #define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) -enum req_op { - REQ_OP_READ, - REQ_OP_WRITE, - REQ_OP_DISCARD, /* request to discard sectors */ - REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ - REQ_OP_WRITE_SAME, /* write same block many times */ - REQ_OP_FLUSH, /* request for cache flush */ -}; - -#define REQ_OP_BITS 3 - typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U #define BLK_QC_T_SHIFT 16 diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index adf3307..ccd68c0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -47,7 +47,6 @@ struct pr_ops; */ #define BLKCG_MAX_POLS 2 -struct request; typedef void (rq_end_io_fn)(struct request *, int); #define BLK_RL_SYNCFULL (1U << 0) @@ -1673,7 +1672,7 @@ struct blk_dax_ctl { struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); - int (*rw_page)(struct block_device *, sector_t, struct page *, int rw); + int (*rw_page)(struct block_device *, sector_t, struct page *, int op); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); long (*direct_access)(struct block_device *, sector_t, void **, pfn_t *, diff --git a/include/linux/fs.h b/include/linux/fs.h index f3f0b4c8..498255e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2480,12 +2480,13 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); -#ifdef CONFIG_BLOCK static inline bool op_is_write(unsigned int op) { return op == REQ_OP_READ ? false : true; } +#ifdef CONFIG_BLOCK + /* * return data direction, READ or WRITE */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 81363b8..4578637 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -510,7 +510,7 @@ static inline void wait_on_page_writeback(struct page *page) extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); -void page_endio(struct page *page, int rw, int err); +void page_endio(struct page *page, int op, int err); /* * Add an arbitrary waiter to a page's wait queue diff --git a/mm/backing-dev.c b/mm/backing-dev.c index efe2377..8fde443 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -825,6 +825,20 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) } EXPORT_SYMBOL(bdi_register_dev); +int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner) +{ + int rc; + + rc = bdi_register(bdi, NULL, "%u:%u", MAJOR(owner->devt), + MINOR(owner->devt)); + if (rc) + return rc; + bdi->owner = owner; + get_device(owner); + return 0; +} +EXPORT_SYMBOL(bdi_register_owner); + /* * Remove bdi from bdi_list, and ensure that it is no longer visible */ @@ -849,6 +863,11 @@ void bdi_unregister(struct backing_dev_info *bdi) device_unregister(bdi->dev); bdi->dev = NULL; } + + if (bdi->owner) { + put_device(bdi->owner); + bdi->owner = NULL; + } } void bdi_exit(struct backing_dev_info *bdi) diff --git a/mm/filemap.c b/mm/filemap.c index 3083ded..daef091 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -887,9 +887,9 @@ EXPORT_SYMBOL(end_page_writeback); * After completing I/O on a page, call this routine to update the page * flags appropriately */ -void page_endio(struct page *page, int rw, int err) +void page_endio(struct page *page, int op, int err) { - if (rw == READ) { + if (!op_is_write(op)) { if (!err) { SetPageUptodate(page); } else { @@ -897,7 +897,7 @@ void page_endio(struct page *page, int rw, int err) SetPageError(page); } unlock_page(page); - } else { /* rw == WRITE */ + } else { if (err) { SetPageError(page); if (page->mapping) |