diff options
154 files changed, 1799 insertions, 2595 deletions
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index d09471aa7443..a789755c311d 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1483,8 +1483,7 @@ IO Interface Files ~~~~~~~~~~~~~~~~~~ io.stat - A read-only nested-keyed file which exists on non-root - cgroups. + A read-only nested-keyed file. Lines are keyed by $MAJ:$MIN device numbers and not ordered. The following nested keys are defined. diff --git a/Documentation/block/biodoc.rst b/Documentation/block/biodoc.rst index b964796ec9c7..afda5e30a82e 100644 --- a/Documentation/block/biodoc.rst +++ b/Documentation/block/biodoc.rst @@ -1036,7 +1036,7 @@ Now the generic block layer performs partition-remapping early and thus provides drivers with a sector number relative to whole device, rather than having to take partition number into account in order to arrive at the true sector number. The routine blk_partition_remap() is invoked by -generic_make_request even before invoking the queue specific make_request_fn, +submit_bio_noacct even before invoking the queue specific ->submit_bio, so the i/o scheduler also gets to operate on whole disk sector numbers. This should typically not require changes to block drivers, it just never gets to invoke its own partition sector offset calculations since all bios diff --git a/Documentation/block/writeback_cache_control.rst b/Documentation/block/writeback_cache_control.rst index 2c752c57c14c..b208488d0aae 100644 --- a/Documentation/block/writeback_cache_control.rst +++ b/Documentation/block/writeback_cache_control.rst @@ -47,7 +47,7 @@ the Forced Unit Access is implemented. The REQ_PREFLUSH and REQ_FUA flags may both be set on a single bio. -Implementation details for make_request_fn based block drivers +Implementation details for bio based block drivers -------------------------------------------------------------- These drivers will always see the REQ_PREFLUSH and REQ_FUA bits as they sit diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst index dde4f7f7fdbf..2de905810590 100644 --- a/Documentation/cdrom/cdrom-standard.rst +++ b/Documentation/cdrom/cdrom-standard.rst @@ -157,7 +157,6 @@ with the kernel as a block device by registering the following general cdrom_release, /∗ release ∗/ NULL, /∗ fsync ∗/ NULL, /∗ fasync ∗/ - cdrom_media_changed, /∗ media change ∗/ NULL /∗ revalidate ∗/ }; @@ -368,19 +367,6 @@ which may or may not be in the drive). If the drive is not a changer, :: - int media_changed(struct cdrom_device_info *cdi, int disc_nr) - -This function is very similar to the original function in $struct -file_operations*. It returns 1 if the medium of the device *cdi->dev* -has changed since the last call, and 0 otherwise. The parameter -*disc_nr* identifies a specific slot in a juke-box, it should be -ignored for single-disc drives. Note that by `re-routing` this -function through *cdrom_media_changed()*, we can implement separate -queues for the VFS and a new *ioctl()* function that can report device -changes to software (e. g., an auto-mounting daemon). - -:: - int tray_move(struct cdrom_device_info *cdi, int position) This function, if implemented, should control the tray movement. (No @@ -917,9 +903,7 @@ commands can be identified by the underscores in their names. maximum number of discs in the juke-box found in the *cdrom_dops*. `CDROM_MEDIA_CHANGED` Returns 1 if a disc has been changed since the last call. - Note that calls to *cdrom_media_changed* by the VFS are treated - by an independent queue, so both mechanisms will detect a - media change once. For juke-boxes, an extra argument *arg* + For juke-boxes, an extra argument *arg* specifies the slot for which the information is given. The special value *CDSL_CURRENT* requests that information about the currently selected slot be returned. diff --git a/Documentation/fault-injection/fault-injection.rst b/Documentation/fault-injection/fault-injection.rst index f51bb21d20e4..f850ad018b70 100644 --- a/Documentation/fault-injection/fault-injection.rst +++ b/Documentation/fault-injection/fault-injection.rst @@ -24,7 +24,7 @@ Available fault injection capabilities injects disk IO errors on devices permitted by setting /sys/block/<device>/make-it-fail or - /sys/block/<device>/<partition>/make-it-fail. (generic_make_request()) + /sys/block/<device>/<partition>/make-it-fail. (submit_bio_noacct()) - fail_mmc_request diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 318605de83f3..17bea12538c3 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -467,7 +467,6 @@ prototypes:: int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *); - int (*media_changed) (struct gendisk *); void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); @@ -483,14 +482,13 @@ release: yes ioctl: no compat_ioctl: no direct_access: no -media_changed: no unlock_native_capacity: no revalidate_disk: no getgeo: no swap_slot_free_notify: no (see below) ======================= =================== -media_changed, unlock_native_capacity and revalidate_disk are called only from +unlock_native_capacity and revalidate_disk are called only from check_disk_change(). swap_slot_free_notify is called with swap_lock and sometimes the page lock diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index 430a16283103..80ba765a8237 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -1453,7 +1453,7 @@ function-trace, we get a much larger output:: => __blk_run_queue_uncond => __blk_run_queue => blk_queue_bio - => generic_make_request + => submit_bio_noacct => submit_bio => submit_bh => __ext3_get_inode_loc @@ -1738,7 +1738,7 @@ tracers. => __blk_run_queue_uncond => __blk_run_queue => blk_queue_bio - => generic_make_request + => submit_bio_noacct => submit_bio => submit_bh => ext3_bread diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index c3a630440512..92d26c812441 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -59,9 +59,9 @@ struct nfhd_device { struct gendisk *disk; }; -static blk_qc_t nfhd_make_request(struct request_queue *queue, struct bio *bio) +static blk_qc_t nfhd_submit_bio(struct bio *bio) { - struct nfhd_device *dev = queue->queuedata; + struct nfhd_device *dev = bio->bi_disk->private_data; struct bio_vec bvec; struct bvec_iter iter; int dir, len, shift; @@ -93,6 +93,7 @@ static int nfhd_getgeo(struct block_device *bdev, struct hd_geometry *geo) static const struct block_device_operations nfhd_ops = { .owner = THIS_MODULE, + .submit_bio = nfhd_submit_bio, .getgeo = nfhd_getgeo, }; @@ -118,11 +119,10 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize) dev->bsize = bsize; dev->bshift = ffs(bsize) - 10; - dev->queue = blk_alloc_queue(nfhd_make_request, NUMA_NO_NODE); + dev->queue = blk_alloc_queue(NUMA_NO_NODE); if (dev->queue == NULL) goto free_dev; - dev->queue->queuedata = dev; blk_queue_logical_block_size(dev->queue, bsize); dev->disk = alloc_disk(16); diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index 49322b66cda9..3447556d276d 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -101,9 +101,9 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector, spin_unlock(&dev->lock); } -static blk_qc_t simdisk_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t simdisk_submit_bio(struct bio *bio) { - struct simdisk *dev = q->queuedata; + struct simdisk *dev = bio->bi_disk->private_data; struct bio_vec bvec; struct bvec_iter iter; sector_t sector = bio->bi_iter.bi_sector; @@ -127,8 +127,6 @@ static int simdisk_open(struct block_device *bdev, fmode_t mode) struct simdisk *dev = bdev->bd_disk->private_data; spin_lock(&dev->lock); - if (!dev->users) - check_disk_change(bdev); ++dev->users; spin_unlock(&dev->lock); return 0; @@ -144,6 +142,7 @@ static void simdisk_release(struct gendisk *disk, fmode_t mode) static const struct block_device_operations simdisk_ops = { .owner = THIS_MODULE, + .submit_bio = simdisk_submit_bio, .open = simdisk_open, .release = simdisk_release, }; @@ -267,14 +266,12 @@ static int __init simdisk_setup(struct simdisk *dev, int which, spin_lock_init(&dev->lock); dev->users = 0; - dev->queue = blk_alloc_queue(simdisk_make_request, NUMA_NO_NODE); + dev->queue = blk_alloc_queue(NUMA_NO_NODE); if (dev->queue == NULL) { pr_err("blk_alloc_queue failed\n"); goto out_alloc_queue; } - dev->queue->queuedata = dev; - dev->gd = alloc_disk(SIMDISK_MINORS); if (dev->gd == NULL) { pr_err("alloc_disk failed\n"); diff --git a/block/Makefile b/block/Makefile index 78719169fb2a..8d841f5f986f 100644 --- a/block/Makefile +++ b/block/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \ blk-flush.o blk-settings.o blk-ioc.o blk-map.o \ - blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \ + blk-exec.o blk-merge.o blk-timeout.o \ blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \ genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o diff --git a/block/bio.c b/block/bio.c index a7366c02c9b5..ef91782fd668 100644 --- a/block/bio.c +++ b/block/bio.c @@ -234,8 +234,12 @@ fallback: void bio_uninit(struct bio *bio) { - bio_disassociate_blkg(bio); - +#ifdef CONFIG_BLK_CGROUP + if (bio->bi_blkg) { + blkg_put(bio->bi_blkg); + bio->bi_blkg = NULL; + } +#endif if (bio_integrity(bio)) bio_integrity_free(bio); @@ -354,7 +358,7 @@ static void bio_alloc_rescue(struct work_struct *work) if (!bio) break; - generic_make_request(bio); + submit_bio_noacct(bio); } } @@ -412,19 +416,19 @@ static void punt_bios_to_rescuer(struct bio_set *bs) * 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 generic_make_request() (i.e. any block + * 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 - * generic_make_request() that converts recursion into iteration, to prevent + * submit_bio_noacct() that converts recursion into iteration, to prevent * stack overflows. * * This would normally mean allocating multiple bios under - * generic_make_request() would be susceptible to deadlocks, but we have + * 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 - * generic_make_request() should be avoided - instead, use bio_set's front_pad + * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad * for per bio allocations. * * RETURNS: @@ -444,9 +448,7 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs, if (nr_iovecs > UIO_MAXIOV) return NULL; - p = kmalloc(sizeof(struct bio) + - nr_iovecs * sizeof(struct bio_vec), - gfp_mask); + p = kmalloc(struct_size(bio, bi_inline_vecs, nr_iovecs), gfp_mask); front_pad = 0; inline_vecs = nr_iovecs; } else { @@ -455,14 +457,14 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs, nr_iovecs > 0)) return NULL; /* - * generic_make_request() converts recursion to iteration; this + * 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 generic_make_request(). If we were to allocate + * 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. @@ -1625,141 +1627,6 @@ int bioset_init_from_src(struct bio_set *bs, struct bio_set *src) } EXPORT_SYMBOL(bioset_init_from_src); -#ifdef CONFIG_BLK_CGROUP - -/** - * bio_disassociate_blkg - puts back the blkg reference if associated - * @bio: target bio - * - * Helper to disassociate the blkg from @bio if a blkg is associated. - */ -void bio_disassociate_blkg(struct bio *bio) -{ - if (bio->bi_blkg) { - blkg_put(bio->bi_blkg); - bio->bi_blkg = NULL; - } -} -EXPORT_SYMBOL_GPL(bio_disassociate_blkg); - -/** - * __bio_associate_blkg - associate a bio with the a blkg - * @bio: target bio - * @blkg: the blkg to associate - * - * This tries to associate @bio with the specified @blkg. Association failure - * is handled by walking up the blkg tree. Therefore, the blkg associated can - * be anything between @blkg and the root_blkg. This situation only happens - * when a cgroup is dying and then the remaining bios will spill to the closest - * alive blkg. - * - * A reference will be taken on the @blkg and will be released when @bio is - * freed. - */ -static void __bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) -{ - bio_disassociate_blkg(bio); - - bio->bi_blkg = blkg_tryget_closest(blkg); -} - -/** - * bio_associate_blkg_from_css - associate a bio with a specified css - * @bio: target bio - * @css: target css - * - * Associate @bio with the blkg found by combining the css's blkg and the - * request_queue of the @bio. This falls back to the queue's root_blkg if - * the association fails with the css. - */ -void bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ - struct request_queue *q = bio->bi_disk->queue; - struct blkcg_gq *blkg; - - rcu_read_lock(); - - if (!css || !css->parent) - blkg = q->root_blkg; - else - blkg = blkg_lookup_create(css_to_blkcg(css), q); - - __bio_associate_blkg(bio, blkg); - - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); - -#ifdef CONFIG_MEMCG -/** - * bio_associate_blkg_from_page - associate a bio with the page's blkg - * @bio: target bio - * @page: the page to lookup the blkcg from - * - * Associate @bio with the blkg from @page's owning memcg and the respective - * request_queue. If cgroup_e_css returns %NULL, fall back to the queue's - * root_blkg. - */ -void bio_associate_blkg_from_page(struct bio *bio, struct page *page) -{ - struct cgroup_subsys_state *css; - - if (!page->mem_cgroup) - return; - - rcu_read_lock(); - - css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys); - bio_associate_blkg_from_css(bio, css); - - rcu_read_unlock(); -} -#endif /* CONFIG_MEMCG */ - -/** - * bio_associate_blkg - associate a bio with a blkg - * @bio: target bio - * - * Associate @bio with the blkg found from the bio's css and request_queue. - * If one is not found, bio_lookup_blkg() creates the blkg. If a blkg is - * already associated, the css is reused and association redone as the - * request_queue may have changed. - */ -void bio_associate_blkg(struct bio *bio) -{ - struct cgroup_subsys_state *css; - - rcu_read_lock(); - - if (bio->bi_blkg) - css = &bio_blkcg(bio)->css; - else - css = blkcg_css(); - - bio_associate_blkg_from_css(bio, css); - - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(bio_associate_blkg); - -/** - * bio_clone_blkg_association - clone blkg association from src to dst bio - * @dst: destination bio - * @src: source bio - */ -void bio_clone_blkg_association(struct bio *dst, struct bio *src) -{ - rcu_read_lock(); - - if (src->bi_blkg) - __bio_associate_blkg(dst, src->bi_blkg); - - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(bio_clone_blkg_association); -#endif /* CONFIG_BLK_CGROUP */ - static void __init biovec_init_slabs(void) { int i; diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 0ecc897b225c..619a79b51068 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -95,9 +95,6 @@ static void __blkg_release(struct rcu_head *rcu) css_put(&blkg->blkcg->css); if (blkg->parent) blkg_put(blkg->parent); - - wb_congested_put(blkg->wb_congested); - blkg_free(blkg); } @@ -227,7 +224,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct blkcg_gq *new_blkg) { struct blkcg_gq *blkg; - struct bdi_writeback_congested *wb_congested; int i, ret; WARN_ON_ONCE(!rcu_read_lock_held()); @@ -245,31 +241,22 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, goto err_free_blkg; } - wb_congested = wb_congested_get_create(q->backing_dev_info, - blkcg->css.id, - GFP_NOWAIT | __GFP_NOWARN); - if (!wb_congested) { - ret = -ENOMEM; - goto err_put_css; - } - /* allocate */ if (!new_blkg) { new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!new_blkg)) { ret = -ENOMEM; - goto err_put_congested; + goto err_put_css; } } blkg = new_blkg; - blkg->wb_congested = wb_congested; /* link parent */ if (blkcg_parent(blkcg)) { blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false); if (WARN_ON_ONCE(!blkg->parent)) { ret = -ENODEV; - goto err_put_congested; + goto err_put_css; } blkg_get(blkg->parent); } @@ -306,8 +293,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, blkg_put(blkg); return ERR_PTR(ret); -err_put_congested: - wb_congested_put(wb_congested); err_put_css: css_put(&blkcg->css); err_free_blkg: @@ -316,30 +301,35 @@ err_free_blkg: } /** - * __blkg_lookup_create - lookup blkg, try to create one if not there + * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. If it doesn't exist, try to * create one. blkg creation is performed recursively from blkcg_root such * that all non-root blkg's have access to the parent blkg. This function - * should be called under RCU read lock and @q->queue_lock. + * should be called under RCU read lock and takes @q->queue_lock. * * Returns the blkg or the closest blkg if blkg_create() fails as it walks * down from root. */ -struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q) +static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, + struct request_queue *q) { struct blkcg_gq *blkg; + unsigned long flags; WARN_ON_ONCE(!rcu_read_lock_held()); - lockdep_assert_held(&q->queue_lock); - blkg = __blkg_lookup(blkcg, q, true); + blkg = blkg_lookup(blkcg, q); if (blkg) return blkg; + spin_lock_irqsave(&q->queue_lock, flags); + blkg = __blkg_lookup(blkcg, q, true); + if (blkg) + goto found; + /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. Returns the closest @@ -362,34 +352,16 @@ struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, } blkg = blkg_create(pos, q, NULL); - if (IS_ERR(blkg)) - return ret_blkg; + if (IS_ERR(blkg)) { + blkg = ret_blkg; + break; + } if (pos == blkcg) - return blkg; - } -} - -/** - * blkg_lookup_create - find or create a blkg - * @blkcg: target block cgroup - * @q: target request_queue - * - * This looks up or creates the blkg representing the unique pair - * of the blkcg and the request_queue. - */ -struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q) -{ - struct blkcg_gq *blkg = blkg_lookup(blkcg, q); - - if (unlikely(!blkg)) { - unsigned long flags; - - spin_lock_irqsave(&q->queue_lock, flags); - blkg = __blkg_lookup_create(blkcg, q); - spin_unlock_irqrestore(&q->queue_lock, flags); + break; } +found: + spin_unlock_irqrestore(&q->queue_lock, flags); return blkg; } @@ -739,12 +711,137 @@ void blkg_conf_finish(struct blkg_conf_ctx *ctx) } EXPORT_SYMBOL_GPL(blkg_conf_finish); +static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] = src->bytes[i]; + dst->ios[i] = src->ios[i]; + } +} + +static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] += src->bytes[i]; + dst->ios[i] += src->ios[i]; + } +} + +static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] -= src->bytes[i]; + dst->ios[i] -= src->ios[i]; + } +} + +static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) +{ + struct blkcg *blkcg = css_to_blkcg(css); + struct blkcg_gq *blkg; + + rcu_read_lock(); + + hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { + struct blkcg_gq *parent = blkg->parent; + struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu); + struct blkg_iostat cur, delta; + unsigned int seq; + + /* fetch the current per-cpu values */ + do { + seq = u64_stats_fetch_begin(&bisc->sync); + blkg_iostat_set(&cur, &bisc->cur); + } while (u64_stats_fetch_retry(&bisc->sync, seq)); + + /* propagate percpu delta to global */ + u64_stats_update_begin(&blkg->iostat.sync); + blkg_iostat_set(&delta, &cur); + blkg_iostat_sub(&delta, &bisc->last); + blkg_iostat_add(&blkg->iostat.cur, &delta); + blkg_iostat_add(&bisc->last, &delta); + u64_stats_update_end(&blkg->iostat.sync); + + /* propagate global delta to parent */ + if (parent) { + u64_stats_update_begin(&parent->iostat.sync); + blkg_iostat_set(&delta, &blkg->iostat.cur); + blkg_iostat_sub(&delta, &blkg->iostat.last); + blkg_iostat_add(&parent->iostat.cur, &delta); + blkg_iostat_add(&blkg->iostat.last, &delta); + u64_stats_update_end(&parent->iostat.sync); + } + } + + rcu_read_unlock(); +} + +/* + * The rstat algorithms intentionally don't handle the root cgroup to avoid + * incurring overhead when no cgroups are defined. For that reason, + * cgroup_rstat_flush in blkcg_print_stat does not actually fill out the + * iostat in the root cgroup's blkcg_gq. + * + * However, we would like to re-use the printing code between the root and + * non-root cgroups to the extent possible. For that reason, we simulate + * flushing the root cgroup's stats by explicitly filling in the iostat + * with disk level statistics. + */ +static void blkcg_fill_root_iostats(void) +{ + struct class_dev_iter iter; + struct device *dev; + + class_dev_iter_init(&iter, &block_class, NULL, &disk_type); + while ((dev = class_dev_iter_next(&iter))) { + struct gendisk *disk = dev_to_disk(dev); + struct hd_struct *part = disk_get_part(disk, 0); + struct blkcg_gq *blkg = blk_queue_root_blkg(disk->queue); + struct blkg_iostat tmp; + int cpu; + + memset(&tmp, 0, sizeof(tmp)); + for_each_possible_cpu(cpu) { + struct disk_stats *cpu_dkstats; + + cpu_dkstats = per_cpu_ptr(part->dkstats, cpu); + tmp.ios[BLKG_IOSTAT_READ] += + cpu_dkstats->ios[STAT_READ]; + tmp.ios[BLKG_IOSTAT_WRITE] += + cpu_dkstats->ios[STAT_WRITE]; + tmp.ios[BLKG_IOSTAT_DISCARD] += + cpu_dkstats->ios[STAT_DISCARD]; + // convert sectors to bytes + tmp.bytes[BLKG_IOSTAT_READ] += + cpu_dkstats->sectors[STAT_READ] << 9; + tmp.bytes[BLKG_IOSTAT_WRITE] += + cpu_dkstats->sectors[STAT_WRITE] << 9; + tmp.bytes[BLKG_IOSTAT_DISCARD] += + cpu_dkstats->sectors[STAT_DISCARD] << 9; + + u64_stats_update_begin(&blkg->iostat.sync); + blkg_iostat_set(&blkg->iostat.cur, &tmp); + u64_stats_update_end(&blkg->iostat.sync); + } + } +} + static int blkcg_print_stat(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; - cgroup_rstat_flush(blkcg->css.cgroup); + if (!seq_css(sf)->parent) + blkcg_fill_root_iostats(); + else + cgroup_rstat_flush(blkcg->css.cgroup); + rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { @@ -833,7 +930,6 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) static struct cftype blkcg_files[] = { { .name = "stat", - .flags = CFTYPE_NOT_ON_ROOT, .seq_show = blkcg_print_stat, }, { } /* terminate */ @@ -1025,7 +1121,7 @@ static int blkcg_css_online(struct cgroup_subsys_state *css) * blkcg_init_queue - initialize blkcg part of request queue * @q: request_queue to initialize * - * Called from __blk_alloc_queue(). Responsible for initializing blkcg + * Called from blk_alloc_queue(). Responsible for initializing blkcg * part of new request_queue @q. * * RETURNS: @@ -1114,77 +1210,6 @@ static int blkcg_can_attach(struct cgroup_taskset *tset) return ret; } -static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) -{ - int i; - - for (i = 0; i < BLKG_IOSTAT_NR; i++) { - dst->bytes[i] = src->bytes[i]; - dst->ios[i] = src->ios[i]; - } -} - -static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) -{ - int i; - - for (i = 0; i < BLKG_IOSTAT_NR; i++) { - dst->bytes[i] += src->bytes[i]; - dst->ios[i] += src->ios[i]; - } -} - -static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) -{ - int i; - - for (i = 0; i < BLKG_IOSTAT_NR; i++) { - dst->bytes[i] -= src->bytes[i]; - dst->ios[i] -= src->ios[i]; - } -} - -static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) -{ - struct blkcg *blkcg = css_to_blkcg(css); - struct blkcg_gq *blkg; - - rcu_read_lock(); - - hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { - struct blkcg_gq *parent = blkg->parent; - struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu); - struct blkg_iostat cur, delta; - unsigned seq; - - /* fetch the current per-cpu values */ - do { - seq = u64_stats_fetch_begin(&bisc->sync); - blkg_iostat_set(&cur, &bisc->cur); - } while (u64_stats_fetch_retry(&bisc->sync, seq)); - - /* propagate percpu delta to global */ - u64_stats_update_begin(&blkg->iostat.sync); - blkg_iostat_set(&delta, &cur); - blkg_iostat_sub(&delta, &bisc->last); - blkg_iostat_add(&blkg->iostat.cur, &delta); - blkg_iostat_add(&bisc->last, &delta); - u64_stats_update_end(&blkg->iostat.sync); - - /* propagate global delta to parent */ - if (parent) { - u64_stats_update_begin(&parent->iostat.sync); - blkg_iostat_set(&delta, &blkg->iostat.cur); - blkg_iostat_sub(&delta, &blkg->iostat.last); - blkg_iostat_add(&parent->iostat.cur, &delta); - blkg_iostat_add(&blkg->iostat.last, &delta); - u64_stats_update_end(&parent->iostat.sync); - } - } - - rcu_read_unlock(); -} - static void blkcg_bind(struct cgroup_subsys_state *root_css) { int i; @@ -1727,6 +1752,139 @@ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) atomic64_add(delta, &blkg->delay_nsec); } +/** + * blkg_tryget_closest - try and get a blkg ref on the closet blkg + * @bio: target bio + * @css: target css + * + * As the failure mode here is to walk up the blkg tree, this ensure that the + * blkg->parent pointers are always valid. This returns the blkg that it ended + * up taking a reference on or %NULL if no reference was taken. + */ +static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio, + struct cgroup_subsys_state *css) +{ + struct blkcg_gq *blkg, *ret_blkg = NULL; + + rcu_read_lock(); + blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_disk->queue); + while (blkg) { + if (blkg_tryget(blkg)) { + ret_blkg = blkg; + break; + } + blkg = blkg->parent; + } + rcu_read_unlock(); + + return ret_blkg; +} + +/** + * bio_associate_blkg_from_css - associate a bio with a specified css + * @bio: target bio + * @css: target css + * + * Associate @bio with the blkg found by combining the css's blkg and the + * request_queue of the @bio. An association failure is handled by walking up + * the blkg tree. Therefore, the blkg associated can be anything between @blkg + * and q->root_blkg. This situation only happens when a cgroup is dying and + * then the remaining bios will spill to the closest alive blkg. + * + * A reference will be taken on the blkg and will be released when @bio is + * freed. + */ +void bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css) +{ + if (bio->bi_blkg) + blkg_put(bio->bi_blkg); + + if (css && css->parent) { + bio->bi_blkg = blkg_tryget_closest(bio, css); + } else { + blkg_get(bio->bi_disk->queue->root_blkg); + bio->bi_blkg = bio->bi_disk->queue->root_blkg; + } +} +EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); + +/** + * bio_associate_blkg - associate a bio with a blkg + * @bio: target bio + * + * Associate @bio with the blkg found from the bio's css and request_queue. + * If one is not found, bio_lookup_blkg() creates the blkg. If a blkg is + * already associated, the css is reused and association redone as the + * request_queue may have changed. + */ +void bio_associate_blkg(struct bio *bio) +{ + struct cgroup_subsys_state *css; + + rcu_read_lock(); + + if (bio->bi_blkg) + css = &bio_blkcg(bio)->css; + else + css = blkcg_css(); + + bio_associate_blkg_from_css(bio, css); + + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(bio_associate_blkg); + +/** + * bio_clone_blkg_association - clone blkg association from src to dst bio + * @dst: destination bio + * @src: source bio + */ +void bio_clone_blkg_association(struct bio *dst, struct bio *src) +{ + if (src->bi_blkg) { + if (dst->bi_blkg) + blkg_put(dst->bi_blkg); + blkg_get(src->bi_blkg); + dst->bi_blkg = src->bi_blkg; + } +} +EXPORT_SYMBOL_GPL(bio_clone_blkg_association); + +static int blk_cgroup_io_type(struct bio *bio) +{ + if (op_is_discard(bio->bi_opf)) + return BLKG_IOSTAT_DISCARD; + if (op_is_write(bio->bi_opf)) + return BLKG_IOSTAT_WRITE; + return BLKG_IOSTAT_READ; +} + +void blk_cgroup_bio_start(struct bio *bio) +{ + int rwd = blk_cgroup_io_type(bio), cpu; + struct blkg_iostat_set *bis; + + cpu = get_cpu(); + bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); + u64_stats_update_begin(&bis->sync); + + /* + * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split + * bio and we would have already accounted for the size of the bio. + */ + if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { + bio_set_flag(bio, BIO_CGROUP_ACCT); + bis->cur.bytes[rwd] += bio->bi_iter.bi_size; + } + bis->cur.ios[rwd]++; + + u64_stats_update_end(&bis->sync); + if (cgroup_subsys_on_dfl(io_cgrp_subsys)) + cgroup_rstat_updated(bio->bi_blkg->blkcg->css.cgroup, cpu); + put_cpu(); +} + static int __init blkcg_init(void) { blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", diff --git a/block/blk-core.c b/block/blk-core.c index 03252af8c82c..93104c7470e8 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -51,9 +51,7 @@ #include "blk-pm.h" #include "blk-rq-qos.h" -#ifdef CONFIG_DEBUG_FS struct dentry *blk_debugfs_root; -#endif EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); @@ -285,7 +283,7 @@ EXPORT_SYMBOL(blk_dump_rq_flags); * A block device may call blk_sync_queue to ensure that any * such activity is cancelled, thus allowing it to release resources * that the callbacks might use. The caller must already have made sure - * that its ->make_request_fn will not re-add plugging prior to calling + * that its ->submit_bio will not re-add plugging prior to calling * this function. * * This function does not cancel any asynchronous activity arising @@ -321,6 +319,16 @@ void blk_clear_pm_only(struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_clear_pm_only); +/** + * blk_put_queue - decrement the request_queue refcount + * @q: the request_queue structure to decrement the refcount for + * + * Decrements the refcount of the request_queue kobject. When this reaches 0 + * we'll have blk_release_queue() called. + * + * Context: Any context, but the last reference must not be dropped from + * atomic context. + */ void blk_put_queue(struct request_queue *q) { kobject_put(&q->kobj); @@ -352,9 +360,14 @@ EXPORT_SYMBOL_GPL(blk_set_queue_dying); * * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and * put it. All future requests will be failed immediately with -ENODEV. + * + * Context: can sleep */ void blk_cleanup_queue(struct request_queue *q) { + /* cannot be called from atomic context */ + might_sleep(); + WARN_ON_ONCE(blk_queue_registered(q)); /* mark @q DYING, no new request or merges will be allowed afterwards */ @@ -497,7 +510,7 @@ static void blk_timeout_work(struct work_struct *work) { } -struct request_queue *__blk_alloc_queue(int node_id) +struct request_queue *blk_alloc_queue(int node_id) { struct request_queue *q; int ret; @@ -540,9 +553,7 @@ struct request_queue *__blk_alloc_queue(int node_id) kobject_init(&q->kobj, &blk_queue_ktype); -#ifdef CONFIG_BLK_DEV_IO_TRACE - mutex_init(&q->blk_trace_mutex); -#endif + mutex_init(&q->debugfs_mutex); mutex_init(&q->sysfs_lock); mutex_init(&q->sysfs_dir_lock); spin_lock_init(&q->queue_lock); @@ -564,6 +575,7 @@ struct request_queue *__blk_alloc_queue(int node_id) blk_queue_dma_alignment(q, 511); blk_set_default_limits(&q->limits); + q->nr_requests = BLKDEV_MAX_RQ; return q; @@ -581,23 +593,16 @@ fail_q: kmem_cache_free(blk_requestq_cachep, q); return NULL; } - -struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id) -{ - struct request_queue *q; - - if (WARN_ON_ONCE(!make_request)) - return NULL; - - q = __blk_alloc_queue(node_id); - if (!q) - return NULL; - q->make_request_fn = make_request; - q->nr_requests = BLKDEV_MAX_RQ; - return q; -} EXPORT_SYMBOL(blk_alloc_queue); +/** + * blk_get_queue - increment the request_queue refcount + * @q: the request_queue structure to increment the refcount for + * + * Increment the refcount of the request_queue kobject. + * + * Context: Any context. + */ bool blk_get_queue(struct request_queue *q) { if (likely(!blk_queue_dying(q))) { @@ -850,8 +855,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) return false; WARN_ONCE(1, - "generic_make_request: Trying to write " - "to read-only block-device %s (partno %d)\n", + "Trying to write to read-only block-device %s (partno %d)\n", bio_devname(bio, b), part->partno); /* Older lvm-tools actually trigger this */ return false; @@ -952,25 +956,13 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q, return BLK_STS_OK; } -static noinline_for_stack bool -generic_make_request_checks(struct bio *bio) +static noinline_for_stack bool submit_bio_checks(struct bio *bio) { - struct request_queue *q; - int nr_sectors = bio_sectors(bio); + struct request_queue *q = bio->bi_disk->queue; blk_status_t status = BLK_STS_IOERR; - char b[BDEVNAME_SIZE]; might_sleep(); - q = bio->bi_disk->queue; - if (unlikely(!q)) { - printk(KERN_ERR - "generic_make_request: Trying to access " - "nonexistent block-device %s (%Lu)\n", - bio_devname(bio, b), (long long)bio->bi_iter.bi_sector); - goto end_io; - } - /* * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue is not a request based queue. @@ -992,14 +984,13 @@ generic_make_request_checks(struct bio *bio) } /* - * Filter flush bio's early so that make_request based - * drivers without flush support don't have to worry - * about them. + * Filter flush bio's early so that bio based drivers without flush + * support don't have to worry about them. */ if (op_is_flush(bio->bi_opf) && !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) { bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA); - if (!nr_sectors) { + if (!bio_sectors(bio)) { status = BLK_STS_OK; goto end_io; } @@ -1054,8 +1045,13 @@ generic_make_request_checks(struct bio *bio) if (unlikely(!current->io_context)) create_task_io_context(current, GFP_ATOMIC, q->node); - if (!blkcg_bio_issue_check(q, bio)) + if (blk_throtl_bio(bio)) { + blkcg_bio_issue_init(bio); return false; + } + + blk_cgroup_bio_start(bio); + blkcg_bio_issue_init(bio); if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) { trace_block_bio_queue(q, bio); @@ -1074,138 +1070,144 @@ end_io: return false; } -static blk_qc_t do_make_request(struct bio *bio) +static blk_qc_t __submit_bio(struct bio *bio) { - struct request_queue *q = bio->bi_disk->queue; + struct gendisk *disk = bio->bi_disk; blk_qc_t ret = BLK_QC_T_NONE; if (blk_crypto_bio_prep(&bio)) { - if (!q->make_request_fn) - return blk_mq_make_request(q, bio); - ret = q->make_request_fn(q, bio); + if (!disk->fops->submit_bio) + return blk_mq_submit_bio(bio); + ret = disk->fops->submit_bio(bio); } - blk_queue_exit(q); + blk_queue_exit(disk->queue); return ret; } -/** - * generic_make_request - re-submit a bio to the block device layer for I/O - * @bio: The bio describing the location in memory and on the device. +/* + * The loop in this function may be a bit non-obvious, and so deserves some + * explanation: * - * This is a version of submit_bio() that shall only be used for I/O that is - * resubmitted to lower level drivers by stacking block drivers. All file - * systems and other upper level users of the block layer should use - * submit_bio() instead. + * - Before entering the loop, bio->bi_next is NULL (as all callers ensure + * that), so we have a list with a single bio. + * - We pretend that we have just taken it off a longer list, so we assign + * bio_list to a pointer to the bio_list_on_stack, thus initialising the + * bio_list of new bios to be added. ->submit_bio() may indeed add some more + * bios through a recursive call to submit_bio_noacct. If it did, we find a + * non-NULL value in bio_list and re-enter the loop from the top. + * - In this case we really did just take the bio of the top of the list (no + * pretending) and so remove it from bio_list, and call into ->submit_bio() + * again. + * + * bio_list_on_stack[0] contains bios submitted by the current ->submit_bio. + * bio_list_on_stack[1] contains bios that were submitted before the current + * ->submit_bio_bio, but that haven't been processed yet. */ -blk_qc_t generic_make_request(struct bio *bio) +static blk_qc_t __submit_bio_noacct(struct bio *bio) { - /* - * bio_list_on_stack[0] contains bios submitted by the current - * make_request_fn. - * bio_list_on_stack[1] contains bios that were submitted before - * the current make_request_fn, but that haven't been processed - * yet. - */ struct bio_list bio_list_on_stack[2]; blk_qc_t ret = BLK_QC_T_NONE; - if (!generic_make_request_checks(bio)) - goto out; - - /* - * We only want one ->make_request_fn to be active at a time, else - * stack usage with stacked devices could be a problem. So use - * current->bio_list to keep a list of requests submited by a - * make_request_fn function. current->bio_list is also used as a - * flag to say if generic_make_request is currently active in this - * task or not. If it is NULL, then no make_request is active. If - * it is non-NULL, then a make_request is active, and new requests - * should be added at the tail - */ - if (current->bio_list) { - bio_list_add(¤t->bio_list[0], bio); - goto out; - } - - /* following loop may be a bit non-obvious, and so deserves some - * explanation. - * Before entering the loop, bio->bi_next is NULL (as all callers - * ensure that) so we have a list with a single bio. - * We pretend that we have just taken it off a longer list, so - * we assign bio_list to a pointer to the bio_list_on_stack, - * thus initialising the bio_list of new bios to be - * added. ->make_request() may indeed add some more bios - * through a recursive call to generic_make_request. If it - * did, we find a non-NULL value in bio_list and re-enter the loop - * from the top. In this case we really did just take the bio - * of the top of the list (no pretending) and so remove it from - * bio_list, and call into ->make_request() again. - */ BUG_ON(bio->bi_next); + bio_list_init(&bio_list_on_stack[0]); current->bio_list = bio_list_on_stack; + do { struct request_queue *q = bio->bi_disk->queue; + struct bio_list lower, same; + + if (unlikely(bio_queue_enter(bio) != 0)) + continue; - if (likely(bio_queue_enter(bio) == 0)) { - struct bio_list lower, same; + /* + * Create a fresh bio_list for all subordinate requests. + */ + bio_list_on_stack[1] = bio_list_on_stack[0]; + bio_list_init(&bio_list_on_stack[0]); - /* Create a fresh bio_list for all subordinate requests */ - bio_list_on_stack[1] = bio_list_on_stack[0]; - bio_list_init(&bio_list_on_stack[0]); - ret = do_make_request(bio); + ret = __submit_bio(bio); - /* sort new bios into those for a lower level - * and those for the same level - */ - bio_list_init(&lower); - bio_list_init(&same); - while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL) - if (q == bio->bi_disk->queue) - bio_list_add(&same, bio); - else - bio_list_add(&lower, bio); - /* now assemble so we handle the lowest level first */ - bio_list_merge(&bio_list_on_stack[0], &lower); - bio_list_merge(&bio_list_on_stack[0], &same); - bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); + /* + * Sort new bios into those for a lower level and those for the + * same level. + */ + bio_list_init(&lower); + bio_list_init(&same); + while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL) + if (q == bio->bi_disk->queue) + bio_list_add(&same, bio); + else + bio_list_add(&lower, bio); + + /* + * Now assemble so we handle the lowest level first. + */ + bio_list_merge(&bio_list_on_stack[0], &lower); + bio_list_merge(&bio_list_on_stack[0], &same); + bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); + } while ((bio = bio_list_pop(&bio_list_on_stack[0]))); + + current->bio_list = NULL; + return ret; +} + +static blk_qc_t __submit_bio_noacct_mq(struct bio *bio) +{ + struct bio_list bio_list[2] = { }; + blk_qc_t ret = BLK_QC_T_NONE; + + current->bio_list = bio_list; + + do { + struct gendisk *disk = bio->bi_disk; + + if (unlikely(bio_queue_enter(bio) != 0)) + continue; + + if (!blk_crypto_bio_prep(&bio)) { + blk_queue_exit(disk->queue); + ret = BLK_QC_T_NONE; + continue; } - bio = bio_list_pop(&bio_list_on_stack[0]); - } while (bio); - current->bio_list = NULL; /* deactivate */ -out: + ret = blk_mq_submit_bio(bio); + } while ((bio = bio_list_pop(&bio_list[0]))); + + current->bio_list = NULL; return ret; } -EXPORT_SYMBOL(generic_make_request); /** - * direct_make_request - hand a buffer directly to its device driver for I/O + * submit_bio_noacct - re-submit a bio to the block device layer for I/O * @bio: The bio describing the location in memory and on the device. * - * This function behaves like generic_make_request(), but does not protect - * against recursion. Must only be used if the called driver is known - * to be blk-mq based. + * This is a version of submit_bio() that shall only be used for I/O that is + * resubmitted to lower level drivers by stacking block drivers. All file + * systems and other upper level users of the block layer should use + * submit_bio() instead. */ -blk_qc_t direct_make_request(struct bio *bio) +blk_qc_t submit_bio_noacct(struct bio *bio) { - struct request_queue *q = bio->bi_disk->queue; - - if (WARN_ON_ONCE(q->make_request_fn)) { - bio_io_error(bio); - return BLK_QC_T_NONE; - } - if (!generic_make_request_checks(bio)) - return BLK_QC_T_NONE; - if (unlikely(bio_queue_enter(bio))) + if (!submit_bio_checks(bio)) return BLK_QC_T_NONE; - if (!blk_crypto_bio_prep(&bio)) { - blk_queue_exit(q); + + /* + * We only want one ->submit_bio to be active at a time, else stack + * usage with stacked devices could be a problem. Use current->bio_list + * to collect a list of requests submited by a ->submit_bio method while + * it is active, and then process them after it returned. + */ + if (current->bio_list) { + bio_list_add(¤t->bio_list[0], bio); return BLK_QC_T_NONE; } - return blk_mq_make_request(q, bio); + + if (!bio->bi_disk->fops->submit_bio) + return __submit_bio_noacct_mq(bio); + return __submit_bio_noacct(bio); } -EXPORT_SYMBOL_GPL(direct_make_request); +EXPORT_SYMBOL(submit_bio_noacct); /** * submit_bio - submit a bio to the block device layer for I/O @@ -1266,13 +1268,13 @@ blk_qc_t submit_bio(struct bio *bio) blk_qc_t ret; psi_memstall_enter(&pflags); - ret = generic_make_request(bio); + ret = submit_bio_noacct(bio); psi_memstall_leave(&pflags); return ret; } - return generic_make_request(bio); + return submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); @@ -1908,9 +1910,7 @@ int __init blk_dev_init(void) blk_requestq_cachep = kmem_cache_create("request_queue", sizeof(struct request_queue), 0, SLAB_PANIC, NULL); -#ifdef CONFIG_DEBUG_FS blk_debugfs_root = debugfs_create_dir("block", NULL); -#endif return 0; } diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index 6e49688a2d80..c162b754efbd 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -228,7 +228,7 @@ static bool blk_crypto_split_bio_if_needed(struct bio **bio_ptr) return false; } bio_chain(split_bio, bio); - generic_make_request(bio); + submit_bio_noacct(bio); *bio_ptr = split_bio; } diff --git a/block/blk-crypto.c b/block/blk-crypto.c index 6533c9b36ab8..2d5e60023b08 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -239,7 +239,7 @@ void __blk_crypto_free_request(struct request *rq) * kernel crypto API. When the crypto API fallback is used for encryption, * blk-crypto may choose to split the bio into 2 - the first one that will * continue to be processed and the second one that will be resubmitted via - * generic_make_request. A bounce bio will be allocated to encrypt the contents + * submit_bio_noacct. A bounce bio will be allocated to encrypt the contents * of the aforementioned "first one", and *bio_ptr will be updated to this * bounce bio. * diff --git a/block/blk-flush.c b/block/blk-flush.c index 15ae0155ec07..6e1543c10493 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -219,7 +219,6 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) struct request *rq, *n; unsigned long flags = 0; struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx); - struct blk_mq_hw_ctx *hctx; blk_account_io_flush(flush_rq); @@ -235,13 +234,11 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) if (fq->rq_status != BLK_STS_OK) error = fq->rq_status; - hctx = flush_rq->mq_hctx; if (!q->elevator) { - blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq); - flush_rq->tag = -1; + flush_rq->tag = BLK_MQ_NO_TAG; } else { blk_mq_put_driver_tag(flush_rq); - flush_rq->internal_tag = -1; + flush_rq->internal_tag = BLK_MQ_NO_TAG; } running = &fq->flush_queue[fq->flush_running_idx]; @@ -286,13 +283,8 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending)) return; - /* C2 and C3 - * - * For blk-mq + scheduling, we can risk having all driver tags - * assigned to empty flushes, and we deadlock if we are expecting - * other requests to make progress. Don't defer for that case. - */ - if (!list_empty(&fq->flush_data_in_flight) && q->elevator && + /* C2 and C3 */ + if (!list_empty(&fq->flush_data_in_flight) && time_before(jiffies, fq->flush_pending_since + FLUSH_PENDING_TIMEOUT)) return; @@ -316,13 +308,10 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, flush_rq->mq_ctx = first_rq->mq_ctx; flush_rq->mq_hctx = first_rq->mq_hctx; - if (!q->elevator) { - fq->orig_rq = first_rq; + if (!q->elevator) flush_rq->tag = first_rq->tag; - blk_mq_tag_set_rq(flush_rq->mq_hctx, first_rq->tag, flush_rq); - } else { + else flush_rq->internal_tag = first_rq->internal_tag; - } flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH; flush_rq->cmd_flags |= (flags & REQ_DRV) | (flags & REQ_FAILFAST_MASK); diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 9df50fb507ca..57299f860d41 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -96,15 +96,7 @@ static void ioc_release_fn(struct work_struct *work) { struct io_context *ioc = container_of(work, struct io_context, release_work); - unsigned long flags; - - /* - * Exiting icq may call into put_io_context() through elevator - * which will trigger lockdep warning. The ioc's are guaranteed to - * be different, use a different locking subclass here. Use - * irqsave variant as there's no spin_lock_irq_nested(). - */ - spin_lock_irqsave_nested(&ioc->lock, flags, 1); + spin_lock_irq(&ioc->lock); while (!hlist_empty(&ioc->icq_list)) { struct io_cq *icq = hlist_entry(ioc->icq_list.first, @@ -115,13 +107,27 @@ static void ioc_release_fn(struct work_struct *work) ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); } else { - spin_unlock_irqrestore(&ioc->lock, flags); - cpu_relax(); - spin_lock_irqsave_nested(&ioc->lock, flags, 1); + /* Make sure q and icq cannot be freed. */ + rcu_read_lock(); + + /* Re-acquire the locks in the correct order. */ + spin_unlock(&ioc->lock); + spin_lock(&q->queue_lock); + spin_lock(&ioc->lock); + + /* + * The icq may have been destroyed when the ioc lock + * was released. + */ + if (!(icq->flags & ICQ_DESTROYED)) + ioc_destroy_icq(icq); + + spin_unlock(&q->queue_lock); + rcu_read_unlock(); } } - spin_unlock_irqrestore(&ioc->lock, flags); + spin_unlock_irq(&ioc->lock); kmem_cache_free(iocontext_cachep, ioc); } @@ -170,7 +176,6 @@ void put_io_context(struct io_context *ioc) */ void put_io_context_active(struct io_context *ioc) { - unsigned long flags; struct io_cq *icq; if (!atomic_dec_and_test(&ioc->active_ref)) { @@ -178,19 +183,14 @@ void put_io_context_active(struct io_context *ioc) return; } - /* - * Need ioc lock to walk icq_list and q lock to exit icq. Perform - * reverse double locking. Read comment in ioc_release_fn() for - * explanation on the nested locking annotation. - */ - spin_lock_irqsave_nested(&ioc->lock, flags, 1); + spin_lock_irq(&ioc->lock); hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) { if (icq->flags & ICQ_EXITED) continue; ioc_exit_icq(icq); } - spin_unlock_irqrestore(&ioc->lock, flags); + spin_unlock_irq(&ioc->lock); put_io_context(ioc); } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 8ac4aad66ebc..cea5ee9be639 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2045,8 +2045,7 @@ static struct blkg_policy_data *ioc_pd_alloc(gfp_t gfp, struct request_queue *q, int levels = blkcg->css.cgroup->level + 1; struct ioc_gq *iocg; - iocg = kzalloc_node(sizeof(*iocg) + levels * sizeof(iocg->ancestors[0]), - gfp, q->node); + iocg = kzalloc_node(struct_size(iocg, ancestors, levels), gfp, q->node); if (!iocg) return NULL; diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index c128d50cb410..f90429cf4edf 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -591,7 +591,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) struct rq_wait *rqw; struct iolatency_grp *iolat; u64 window_start; - u64 now = ktime_to_ns(ktime_get()); + u64 now; bool issue_as_root = bio_issue_as_root_blkg(bio); bool enabled = false; int inflight = 0; @@ -608,6 +608,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) if (!enabled) return; + now = ktime_to_ns(ktime_get()); while (blkg && blkg->parent) { iolat = blkg_to_lat(blkg); if (!iolat) { diff --git a/block/blk-lib.c b/block/blk-lib.c index 5f2c429d4378..019e09bb9c0e 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -29,7 +29,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, struct request_queue *q = bdev_get_queue(bdev); struct bio *bio = *biop; unsigned int op; - sector_t bs_mask; + sector_t bs_mask, part_offset = 0; if (!q) return -ENXIO; @@ -54,9 +54,34 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, if (!nr_sects) return -EINVAL; + /* In case the discard request is in a partition */ + if (bdev->bd_partno) + part_offset = bdev->bd_part->start_sect; + while (nr_sects) { - sector_t req_sects = min_t(sector_t, nr_sects, - bio_allowed_max_sectors(q)); + sector_t granularity_aligned_lba, req_sects; + sector_t sector_mapped = sector + part_offset; + + granularity_aligned_lba = round_up(sector_mapped, + q->limits.discard_granularity >> SECTOR_SHIFT); + + /* + * Check whether the discard bio starts at a discard_granularity + * aligned LBA, + * - If no: set (granularity_aligned_lba - sector_mapped) to + * bi_size of the first split bio, then the second bio will + * start at a discard_granularity aligned LBA on the device. + * - If yes: use bio_aligned_discard_max_sectors() as the max + * possible bi_size of the first split bio. Then when this bio + * is split in device drive, the split ones are very probably + * to be aligned to discard_granularity of the device's queue. + */ + if (granularity_aligned_lba == sector_mapped) + req_sects = min_t(sector_t, nr_sects, + bio_aligned_discard_max_sectors(q)); + else + req_sects = min_t(sector_t, nr_sects, + granularity_aligned_lba - sector_mapped); WARN_ON_ONCE((req_sects << 9) > UINT_MAX); diff --git a/block/blk-merge.c b/block/blk-merge.c index f0b0bae075a0..5196dc145270 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -283,20 +283,20 @@ split: /** * __blk_queue_split - split a bio and submit the second half - * @q: [in] request queue pointer * @bio: [in, out] bio to be split * @nr_segs: [out] number of segments in the first bio * * Split a bio into two bios, chain the two bios, submit the second half and * store a pointer to the first half in *@bio. If the second bio is still too * big it will be split by a recursive call to this function. Since this - * function may allocate a new bio from @q->bio_split, it is the responsibility - * of the caller to ensure that @q is only released after processing of the + * function may allocate a new bio from @bio->bi_disk->queue->bio_split, it is + * the responsibility of the caller to ensure that + * @bio->bi_disk->queue->bio_split is only released after processing of the * split bio has finished. */ -void __blk_queue_split(struct request_queue *q, struct bio **bio, - unsigned int *nr_segs) +void __blk_queue_split(struct bio **bio, unsigned int *nr_segs) { + struct request_queue *q = (*bio)->bi_disk->queue; struct bio *split = NULL; switch (bio_op(*bio)) { @@ -338,27 +338,26 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio, bio_chain(split, *bio); trace_block_split(q, split, (*bio)->bi_iter.bi_sector); - generic_make_request(*bio); + submit_bio_noacct(*bio); *bio = split; } } /** * blk_queue_split - split a bio and submit the second half - * @q: [in] request queue pointer * @bio: [in, out] bio to be split * * Split a bio into two bios, chains the two bios, submit the second half and * store a pointer to the first half in *@bio. Since this function may allocate - * a new bio from @q->bio_split, it is the responsibility of the caller to - * ensure that @q is only released after processing of the split bio has - * finished. + * a new bio from @bio->bi_disk->queue->bio_split, it is the responsibility of + * the caller to ensure that @bio->bi_disk->queue->bio_split is only released + * after processing of the split bio has finished. */ -void blk_queue_split(struct request_queue *q, struct bio **bio) +void blk_queue_split(struct bio **bio) { unsigned int nr_segs; - __blk_queue_split(q, bio, &nr_segs); + __blk_queue_split(bio, &nr_segs); } EXPORT_SYMBOL(blk_queue_split); @@ -793,6 +792,8 @@ static struct request *attempt_merge(struct request_queue *q, */ blk_account_io_merge_request(next); + trace_block_rq_merge(q, next); + /* * ownership of bio passed from next to req, return 'next' for * the caller to free diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index e0b2bc131bf5..3f09bcb8a6fd 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -404,8 +404,7 @@ static bool hctx_show_busy_rq(struct request *rq, void *data, bool reserved) const struct show_busy_params *params = data; if (rq->mq_hctx == params->hctx) - __blk_mq_debugfs_rq_show(params->m, - list_entry_rq(&rq->queuelist)); + __blk_mq_debugfs_rq_show(params->m, rq); return true; } @@ -827,9 +826,6 @@ void blk_mq_debugfs_register(struct request_queue *q) struct blk_mq_hw_ctx *hctx; int i; - q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent), - blk_debugfs_root); - debugfs_create_files(q->debugfs_dir, q, blk_mq_debugfs_queue_attrs); /* @@ -860,9 +856,7 @@ void blk_mq_debugfs_register(struct request_queue *q) void blk_mq_debugfs_unregister(struct request_queue *q) { - debugfs_remove_recursive(q->debugfs_dir); q->sched_debugfs_dir = NULL; - q->debugfs_dir = NULL; } static void blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx, diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index fdcc2c1dd178..b8db72cf1043 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -7,6 +7,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/blk-mq.h> +#include <linux/list_sort.h> #include <trace/events/block.h> @@ -80,6 +81,35 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) blk_mq_run_hw_queue(hctx, true); } +static int sched_rq_cmp(void *priv, struct list_head *a, struct list_head *b) +{ + struct request *rqa = container_of(a, struct request, queuelist); + struct request *rqb = container_of(b, struct request, queuelist); + + return rqa->mq_hctx > rqb->mq_hctx; +} + +static bool blk_mq_dispatch_hctx_list(struct list_head *rq_list) +{ + struct blk_mq_hw_ctx *hctx = + list_first_entry(rq_list, struct request, queuelist)->mq_hctx; + struct request *rq; + LIST_HEAD(hctx_list); + unsigned int count = 0; + + list_for_each_entry(rq, rq_list, queuelist) { + if (rq->mq_hctx != hctx) { + list_cut_before(&hctx_list, rq_list, &rq->queuelist); + goto dispatch; + } + count++; + } + list_splice_tail_init(rq_list, &hctx_list); + +dispatch: + return blk_mq_dispatch_rq_list(hctx, &hctx_list, count); +} + #define BLK_MQ_BUDGET_DELAY 3 /* ms units */ /* @@ -90,12 +120,20 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to * be run again. This is necessary to avoid starving flushes. */ -static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) +static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct elevator_queue *e = q->elevator; + bool multi_hctxs = false, run_queue = false; + bool dispatched = false, busy = false; + unsigned int max_dispatch; LIST_HEAD(rq_list); - int ret = 0; + int count = 0; + + if (hctx->dispatch_busy) + max_dispatch = 1; + else + max_dispatch = hctx->queue->nr_requests; do { struct request *rq; @@ -104,16 +142,16 @@ static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) break; if (!list_empty_careful(&hctx->dispatch)) { - ret = -EAGAIN; + busy = true; break; } - if (!blk_mq_get_dispatch_budget(hctx)) + if (!blk_mq_get_dispatch_budget(q)) break; rq = e->type->ops.dispatch_request(hctx); if (!rq) { - blk_mq_put_dispatch_budget(hctx); + blk_mq_put_dispatch_budget(q); /* * We're releasing without dispatching. Holding the * budget could have blocked any "hctx"s with the @@ -121,7 +159,7 @@ static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) * no guarantee anyone will kick the queue. Kick it * ourselves. */ - blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); + run_queue = true; break; } @@ -130,8 +168,42 @@ static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) * if this rq won't be queued to driver via .queue_rq() * in blk_mq_dispatch_rq_list(). */ - list_add(&rq->queuelist, &rq_list); - } while (blk_mq_dispatch_rq_list(q, &rq_list, true)); + list_add_tail(&rq->queuelist, &rq_list); + if (rq->mq_hctx != hctx) + multi_hctxs = true; + } while (++count < max_dispatch); + + if (!count) { + if (run_queue) + blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); + } else if (multi_hctxs) { + /* + * Requests from different hctx may be dequeued from some + * schedulers, such as bfq and deadline. + * + * Sort the requests in the list according to their hctx, + * dispatch batching requests from same hctx at a time. + */ + list_sort(NULL, &rq_list, sched_rq_cmp); + do { + dispatched |= blk_mq_dispatch_hctx_list(&rq_list); + } while (!list_empty(&rq_list)); + } else { + dispatched = blk_mq_dispatch_rq_list(hctx, &rq_list, count); + } + + if (busy) + return -EAGAIN; + return !!dispatched; +} + +static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) +{ + int ret; + + do { + ret = __blk_mq_do_dispatch_sched(hctx); + } while (ret == 1); return ret; } @@ -161,10 +233,9 @@ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) LIST_HEAD(rq_list); struct blk_mq_ctx *ctx = READ_ONCE(hctx->dispatch_from); int ret = 0; + struct request *rq; do { - struct request *rq; - if (!list_empty_careful(&hctx->dispatch)) { ret = -EAGAIN; break; @@ -173,12 +244,12 @@ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) if (!sbitmap_any_bit_set(&hctx->ctx_map)) break; - if (!blk_mq_get_dispatch_budget(hctx)) + if (!blk_mq_get_dispatch_budget(q)) break; rq = blk_mq_dequeue_from_ctx(hctx, ctx); if (!rq) { - blk_mq_put_dispatch_budget(hctx); + blk_mq_put_dispatch_budget(q); /* * We're releasing without dispatching. Holding the * budget could have blocked any "hctx"s with the @@ -200,7 +271,7 @@ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) /* round robin for fair dispatch */ ctx = blk_mq_next_ctx(hctx, rq->mq_ctx); - } while (blk_mq_dispatch_rq_list(q, &rq_list, true)); + } while (blk_mq_dispatch_rq_list(rq->mq_hctx, &rq_list, 1)); WRITE_ONCE(hctx->dispatch_from, ctx); return ret; @@ -240,7 +311,7 @@ static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) */ if (!list_empty(&rq_list)) { blk_mq_sched_mark_restart_hctx(hctx); - if (blk_mq_dispatch_rq_list(q, &rq_list, false)) { + if (blk_mq_dispatch_rq_list(hctx, &rq_list, 0)) { if (has_sched_dispatch) ret = blk_mq_do_dispatch_sched(hctx); else @@ -253,7 +324,7 @@ static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) ret = blk_mq_do_dispatch_ctx(hctx); } else { blk_mq_flush_busy_ctxs(hctx, &rq_list); - blk_mq_dispatch_rq_list(q, &rq_list, false); + blk_mq_dispatch_rq_list(hctx, &rq_list, 0); } return ret; diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index ae722f8b13fb..32d82e23b095 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -56,43 +56,12 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) blk_mq_tag_wakeup_all(tags, false); } -/* - * For shared tag users, we track the number of currently active users - * and attempt to provide a fair share of the tag depth for each of them. - */ -static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, - struct sbitmap_queue *bt) -{ - unsigned int depth, users; - - if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_SHARED)) - return true; - if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) - return true; - - /* - * Don't try dividing an ant - */ - if (bt->sb.depth == 1) - return true; - - users = atomic_read(&hctx->tags->active_queues); - if (!users) - return true; - - /* - * Allow at least some tags - */ - depth = max((bt->sb.depth + users - 1) / users, 4U); - return atomic_read(&hctx->nr_active) < depth; -} - static int __blk_mq_get_tag(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt) { - if (!(data->flags & BLK_MQ_REQ_INTERNAL) && - !hctx_may_queue(data->hctx, bt)) + if (!data->q->elevator && !hctx_may_queue(data->hctx, bt)) return BLK_MQ_NO_TAG; + if (data->shallow_depth) return __sbitmap_queue_get_shallow(bt, data->shallow_depth); else @@ -191,33 +160,6 @@ found_tag: return tag + tag_offset; } -bool __blk_mq_get_driver_tag(struct request *rq) -{ - struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags; - unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags; - bool shared = blk_mq_tag_busy(rq->mq_hctx); - int tag; - - if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) { - bt = &rq->mq_hctx->tags->breserved_tags; - tag_offset = 0; - } - - if (!hctx_may_queue(rq->mq_hctx, bt)) - return false; - tag = __sbitmap_queue_get(bt); - if (tag == BLK_MQ_NO_TAG) - return false; - - rq->tag = tag + tag_offset; - if (shared) { - rq->rq_flags |= RQF_MQ_INFLIGHT; - atomic_inc(&rq->mq_hctx->nr_active); - } - rq->mq_hctx->tags->rqs[rq->tag] = rq; - return true; -} - void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag) { diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 2e4ef51cdb32..b1acac518c4e 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -51,14 +51,6 @@ enum { BLK_MQ_TAG_MAX = BLK_MQ_NO_TAG - 1, }; -bool __blk_mq_get_driver_tag(struct request *rq); -static inline bool blk_mq_get_driver_tag(struct request *rq) -{ - if (rq->tag != BLK_MQ_NO_TAG) - return true; - return __blk_mq_get_driver_tag(rq); -} - extern bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *); extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *); @@ -79,15 +71,34 @@ static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) } /* - * This helper should only be used for flush request to share tag - * with the request cloned from, and both the two requests can't be - * in flight at the same time. The caller has to make sure the tag - * can't be freed. + * For shared tag users, we track the number of currently active users + * and attempt to provide a fair share of the tag depth for each of them. */ -static inline void blk_mq_tag_set_rq(struct blk_mq_hw_ctx *hctx, - unsigned int tag, struct request *rq) +static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, + struct sbitmap_queue *bt) { - hctx->tags->rqs[tag] = rq; + unsigned int depth, users; + + if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_SHARED)) + return true; + if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) + return true; + + /* + * Don't try dividing an ant + */ + if (bt->sb.depth == 1) + return true; + + users = atomic_read(&hctx->tags->active_queues); + if (!users) + return true; + + /* + * Allow at least some tags + */ + depth = max((bt->sb.depth + users - 1) / users, 4U); + return atomic_read(&hctx->nr_active) < depth; } static inline bool blk_mq_tag_is_reserved(struct blk_mq_tags *tags, diff --git a/block/blk-mq.c b/block/blk-mq.c index 4e0d173beaa3..667155f752f7 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -41,6 +41,8 @@ #include "blk-mq-sched.h" #include "blk-rq-qos.h" +static DEFINE_PER_CPU(struct list_head, blk_cpu_done); + static void blk_mq_poll_stats_start(struct request_queue *q); static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb); @@ -275,26 +277,20 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct request *rq = tags->static_rqs[tag]; - req_flags_t rq_flags = 0; - if (data->flags & BLK_MQ_REQ_INTERNAL) { + if (data->q->elevator) { rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = tag; } else { - if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) { - rq_flags = RQF_MQ_INFLIGHT; - atomic_inc(&data->hctx->nr_active); - } rq->tag = tag; rq->internal_tag = BLK_MQ_NO_TAG; - data->hctx->tags->rqs[rq->tag] = rq; } /* csd/requeue_work/fifo_time is initialized before use */ rq->q = data->q; rq->mq_ctx = data->ctx; rq->mq_hctx = data->hctx; - rq->rq_flags = rq_flags; + rq->rq_flags = 0; rq->cmd_flags = data->cmd_flags; if (data->flags & BLK_MQ_REQ_PREEMPT) rq->rq_flags |= RQF_PREEMPT; @@ -362,8 +358,6 @@ static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data) data->flags |= BLK_MQ_REQ_NOWAIT; if (e) { - data->flags |= BLK_MQ_REQ_INTERNAL; - /* * Flush requests are special and go directly to the * dispatch list. Don't include reserved tags in the @@ -378,7 +372,7 @@ static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data) retry: data->ctx = blk_mq_get_ctx(q); data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); - if (!(data->flags & BLK_MQ_REQ_INTERNAL)) + if (!e) blk_mq_tag_busy(data->hctx); /* @@ -474,9 +468,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask); data.ctx = __blk_mq_get_ctx(q, cpu); - if (q->elevator) - data.flags |= BLK_MQ_REQ_INTERNAL; - else + if (!q->elevator) blk_mq_tag_busy(data.hctx); ret = -EWOULDBLOCK; @@ -552,8 +544,7 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error) blk_stat_add(rq, now); } - if (rq->internal_tag != BLK_MQ_NO_TAG) - blk_mq_sched_completed_request(rq, now); + blk_mq_sched_completed_request(rq, now); blk_account_io_done(rq, now); @@ -574,71 +565,139 @@ void blk_mq_end_request(struct request *rq, blk_status_t error) } EXPORT_SYMBOL(blk_mq_end_request); -static void __blk_mq_complete_request_remote(void *data) +/* + * Softirq action handler - move entries to local list and loop over them + * while passing them to the queue registered handler. + */ +static __latent_entropy void blk_done_softirq(struct softirq_action *h) { - struct request *rq = data; - struct request_queue *q = rq->q; + struct list_head *cpu_list, local_list; - q->mq_ops->complete(rq); + local_irq_disable(); + cpu_list = this_cpu_ptr(&blk_cpu_done); + list_replace_init(cpu_list, &local_list); + local_irq_enable(); + + while (!list_empty(&local_list)) { + struct request *rq; + + rq = list_entry(local_list.next, struct request, ipi_list); + list_del_init(&rq->ipi_list); + rq->q->mq_ops->complete(rq); + } } -/** - * blk_mq_force_complete_rq() - Force complete the request, bypassing any error - * injection that could drop the completion. - * @rq: Request to be force completed - * - * Drivers should use blk_mq_complete_request() to complete requests in their - * normal IO path. For timeout error recovery, drivers may call this forced - * completion routine after they've reclaimed timed out requests to bypass - * potentially subsequent fake timeouts. - */ -void blk_mq_force_complete_rq(struct request *rq) +static void blk_mq_trigger_softirq(struct request *rq) { - struct blk_mq_ctx *ctx = rq->mq_ctx; - struct request_queue *q = rq->q; - bool shared = false; - int cpu; + struct list_head *list; + unsigned long flags; + + local_irq_save(flags); + list = this_cpu_ptr(&blk_cpu_done); + list_add_tail(&rq->ipi_list, list); + + /* + * If the list only contains our just added request, signal a raise of + * the softirq. If there are already entries there, someone already + * raised the irq but it hasn't run yet. + */ + if (list->next == &rq->ipi_list) + raise_softirq_irqoff(BLOCK_SOFTIRQ); + local_irq_restore(flags); +} + +static int blk_softirq_cpu_dead(unsigned int cpu) +{ + /* + * If a CPU goes away, splice its entries to the current CPU + * and trigger a run of the softirq + */ + local_irq_disable(); + list_splice_init(&per_cpu(blk_cpu_done, cpu), + this_cpu_ptr(&blk_cpu_done)); + raise_softirq_irqoff(BLOCK_SOFTIRQ); + local_irq_enable(); + + return 0; +} + + +static void __blk_mq_complete_request_remote(void *data) +{ + struct request *rq = data; - WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); /* - * Most of single queue controllers, there is only one irq vector - * for handling IO completion, and the only irq's affinity is set - * as all possible CPUs. On most of ARCHs, this affinity means the - * irq is handled on one specific CPU. + * For most of single queue controllers, there is only one irq vector + * for handling I/O completion, and the only irq's affinity is set + * to all possible CPUs. On most of ARCHs, this affinity means the irq + * is handled on one specific CPU. * - * So complete IO reqeust in softirq context in case of single queue - * for not degrading IO performance by irqsoff latency. + * So complete I/O requests in softirq context in case of single queue + * devices to avoid degrading I/O performance due to irqsoff latency. */ - if (q->nr_hw_queues == 1) { - __blk_complete_request(rq); - return; - } + if (rq->q->nr_hw_queues == 1) + blk_mq_trigger_softirq(rq); + else + rq->q->mq_ops->complete(rq); +} + +static inline bool blk_mq_complete_need_ipi(struct request *rq) +{ + int cpu = raw_smp_processor_id(); + + if (!IS_ENABLED(CONFIG_SMP) || + !test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) + return false; + + /* same CPU or cache domain? Complete locally */ + if (cpu == rq->mq_ctx->cpu || + (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) && + cpus_share_cache(cpu, rq->mq_ctx->cpu))) + return false; + + /* don't try to IPI to an offline CPU */ + return cpu_online(rq->mq_ctx->cpu); +} + +bool blk_mq_complete_request_remote(struct request *rq) +{ + WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); /* * For a polled request, always complete locallly, it's pointless * to redirect the completion. */ - if ((rq->cmd_flags & REQ_HIPRI) || - !test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags)) { - q->mq_ops->complete(rq); - return; - } - - cpu = get_cpu(); - if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) - shared = cpus_share_cache(cpu, ctx->cpu); + if (rq->cmd_flags & REQ_HIPRI) + return false; - if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) { + if (blk_mq_complete_need_ipi(rq)) { rq->csd.func = __blk_mq_complete_request_remote; rq->csd.info = rq; rq->csd.flags = 0; - smp_call_function_single_async(ctx->cpu, &rq->csd); + smp_call_function_single_async(rq->mq_ctx->cpu, &rq->csd); } else { - q->mq_ops->complete(rq); + if (rq->q->nr_hw_queues > 1) + return false; + blk_mq_trigger_softirq(rq); } - put_cpu(); + + return true; +} +EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote); + +/** + * blk_mq_complete_request - end I/O on a request + * @rq: the request being processed + * + * Description: + * Complete a request by scheduling the ->complete_rq operation. + **/ +void blk_mq_complete_request(struct request *rq) +{ + if (!blk_mq_complete_request_remote(rq)) + rq->q->mq_ops->complete(rq); } -EXPORT_SYMBOL_GPL(blk_mq_force_complete_rq); +EXPORT_SYMBOL(blk_mq_complete_request); static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx) __releases(hctx->srcu) @@ -661,23 +720,6 @@ static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx) } /** - * blk_mq_complete_request - end I/O on a request - * @rq: the request being processed - * - * Description: - * Ends all I/O on a request. It does not handle partial completions. - * The actual completion happens out-of-order, through a IPI handler. - **/ -bool blk_mq_complete_request(struct request *rq) -{ - if (unlikely(blk_should_fake_timeout(rq->q))) - return false; - blk_mq_force_complete_rq(rq); - return true; -} -EXPORT_SYMBOL(blk_mq_complete_request); - -/** * blk_mq_start_request - Start processing a request * @rq: Pointer to request to be started * @@ -1052,6 +1094,45 @@ static inline unsigned int queued_to_index(unsigned int queued) return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1); } +static bool __blk_mq_get_driver_tag(struct request *rq) +{ + struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags; + unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags; + int tag; + + blk_mq_tag_busy(rq->mq_hctx); + + if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) { + bt = &rq->mq_hctx->tags->breserved_tags; + tag_offset = 0; + } + + if (!hctx_may_queue(rq->mq_hctx, bt)) + return false; + tag = __sbitmap_queue_get(bt); + if (tag == BLK_MQ_NO_TAG) + return false; + + rq->tag = tag + tag_offset; + return true; +} + +static bool blk_mq_get_driver_tag(struct request *rq) +{ + struct blk_mq_hw_ctx *hctx = rq->mq_hctx; + + if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq)) + return false; + + if ((hctx->flags & BLK_MQ_F_TAG_SHARED) && + !(rq->rq_flags & RQF_MQ_INFLIGHT)) { + rq->rq_flags |= RQF_MQ_INFLIGHT; + atomic_inc(&hctx->nr_active); + } + hctx->tags->rqs[rq->tag] = rq; + return true; +} + static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, int flags, void *key) { @@ -1204,25 +1285,70 @@ static void blk_mq_handle_zone_resource(struct request *rq, __blk_mq_requeue_request(rq); } +enum prep_dispatch { + PREP_DISPATCH_OK, + PREP_DISPATCH_NO_TAG, + PREP_DISPATCH_NO_BUDGET, +}; + +static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq, + bool need_budget) +{ + struct blk_mq_hw_ctx *hctx = rq->mq_hctx; + + if (need_budget && !blk_mq_get_dispatch_budget(rq->q)) { + blk_mq_put_driver_tag(rq); + return PREP_DISPATCH_NO_BUDGET; + } + + if (!blk_mq_get_driver_tag(rq)) { + /* + * The initial allocation attempt failed, so we need to + * rerun the hardware queue when a tag is freed. The + * waitqueue takes care of that. If the queue is run + * before we add this entry back on the dispatch list, + * we'll re-run it below. + */ + if (!blk_mq_mark_tag_wait(hctx, rq)) { + /* + * All budgets not got from this function will be put + * together during handling partial dispatch + */ + if (need_budget) + blk_mq_put_dispatch_budget(rq->q); + return PREP_DISPATCH_NO_TAG; + } + } + + return PREP_DISPATCH_OK; +} + +/* release all allocated budgets before calling to blk_mq_dispatch_rq_list */ +static void blk_mq_release_budgets(struct request_queue *q, + unsigned int nr_budgets) +{ + int i; + + for (i = 0; i < nr_budgets; i++) + blk_mq_put_dispatch_budget(q); +} + /* * Returns true if we did some work AND can potentially do more. */ -bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, - bool got_budget) +bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, + unsigned int nr_budgets) { - struct blk_mq_hw_ctx *hctx; + enum prep_dispatch prep; + struct request_queue *q = hctx->queue; struct request *rq, *nxt; - bool no_tag = false; int errors, queued; blk_status_t ret = BLK_STS_OK; - bool no_budget_avail = false; LIST_HEAD(zone_list); if (list_empty(list)) return false; - WARN_ON(!list_is_singular(list) && got_budget); - /* * Now process all the entries, sending them to the driver. */ @@ -1232,32 +1358,10 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, rq = list_first_entry(list, struct request, queuelist); - hctx = rq->mq_hctx; - if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) { - blk_mq_put_driver_tag(rq); - no_budget_avail = true; + WARN_ON_ONCE(hctx != rq->mq_hctx); + prep = blk_mq_prep_dispatch_rq(rq, !nr_budgets); + if (prep != PREP_DISPATCH_OK) break; - } - - if (!blk_mq_get_driver_tag(rq)) { - /* - * The initial allocation attempt failed, so we need to - * rerun the hardware queue when a tag is freed. The - * waitqueue takes care of that. If the queue is run - * before we add this entry back on the dispatch list, - * we'll re-run it below. - */ - if (!blk_mq_mark_tag_wait(hctx, rq)) { - blk_mq_put_dispatch_budget(hctx); - /* - * For non-shared tags, the RESTART check - * will suffice. - */ - if (hctx->flags & BLK_MQ_F_TAG_SHARED) - no_tag = true; - break; - } - } list_del_init(&rq->queuelist); @@ -1274,31 +1378,35 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, bd.last = !blk_mq_get_driver_tag(nxt); } + /* + * once the request is queued to lld, no need to cover the + * budget any more + */ + if (nr_budgets) + nr_budgets--; ret = q->mq_ops->queue_rq(hctx, &bd); - if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { - blk_mq_handle_dev_resource(rq, list); + switch (ret) { + case BLK_STS_OK: + queued++; break; - } else if (ret == BLK_STS_ZONE_RESOURCE) { + case BLK_STS_RESOURCE: + case BLK_STS_DEV_RESOURCE: + blk_mq_handle_dev_resource(rq, list); + goto out; + case BLK_STS_ZONE_RESOURCE: /* * Move the request to zone_list and keep going through * the dispatch list to find more requests the drive can * accept. */ blk_mq_handle_zone_resource(rq, &zone_list); - if (list_empty(list)) - break; - continue; - } - - if (unlikely(ret != BLK_STS_OK)) { + break; + default: errors++; blk_mq_end_request(rq, BLK_STS_IOERR); - continue; } - - queued++; } while (!list_empty(list)); - +out: if (!list_empty(&zone_list)) list_splice_tail_init(&zone_list, list); @@ -1310,6 +1418,12 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, */ if (!list_empty(list)) { bool needs_restart; + /* For non-shared tags, the RESTART check will suffice */ + bool no_tag = prep == PREP_DISPATCH_NO_TAG && + (hctx->flags & BLK_MQ_F_TAG_SHARED); + bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET; + + blk_mq_release_budgets(q, nr_budgets); /* * If we didn't flush the entire list, we could have told @@ -1361,13 +1475,6 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, } else blk_mq_update_dispatch_busy(hctx, false); - /* - * If the host/device is unable to accept more work, inform the - * caller of that. - */ - if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) - return false; - return (queued + errors) != 0; } @@ -1896,11 +2003,11 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, if (q->elevator && !bypass_insert) goto insert; - if (!blk_mq_get_dispatch_budget(hctx)) + if (!blk_mq_get_dispatch_budget(q)) goto insert; if (!blk_mq_get_driver_tag(rq)) { - blk_mq_put_dispatch_budget(hctx); + blk_mq_put_dispatch_budget(q); goto insert; } @@ -2005,8 +2112,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) } /** - * blk_mq_make_request - Create and send a request to block device. - * @q: Request queue pointer. + * blk_mq_submit_bio - Create and send a request to block device. * @bio: Bio pointer. * * Builds up a request structure from @q and @bio and send to the device. The @@ -2020,8 +2126,9 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) * * Returns: Request queue cookie. */ -blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) +blk_qc_t blk_mq_submit_bio(struct bio *bio) { + struct request_queue *q = bio->bi_disk->queue; const int is_sync = op_is_sync(bio->bi_opf); const int is_flush_fua = op_is_flush(bio->bi_opf); struct blk_mq_alloc_data data = { @@ -2035,7 +2142,7 @@ blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_status_t ret; blk_queue_bounce(q, &bio); - __blk_queue_split(q, &bio, &nr_segs); + __blk_queue_split(&bio, &nr_segs); if (!bio_integrity_prep(bio)) goto queue_exit; @@ -2146,7 +2253,7 @@ queue_exit: blk_queue_exit(q); return BLK_QC_T_NONE; } -EXPORT_SYMBOL_GPL(blk_mq_make_request); /* only for request based dm */ +EXPORT_SYMBOL_GPL(blk_mq_submit_bio); /* only for request based dm */ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) @@ -2886,7 +2993,7 @@ struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, { struct request_queue *uninit_q, *q; - uninit_q = __blk_alloc_queue(set->numa_node); + uninit_q = blk_alloc_queue(set->numa_node); if (!uninit_q) return ERR_PTR(-ENOMEM); uninit_q->queuedata = queuedata; @@ -3760,6 +3867,15 @@ EXPORT_SYMBOL(blk_mq_rq_cpu); static int __init blk_mq_init(void) { + int i; + + for_each_possible_cpu(i) + INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i)); + open_softirq(BLOCK_SOFTIRQ, blk_done_softirq); + + cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD, + "block/softirq:dead", NULL, + blk_softirq_cpu_dead); cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online", diff --git a/block/blk-mq.h b/block/blk-mq.h index b3ce0f3a2ad2..863a2f3346d4 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -40,7 +40,8 @@ struct blk_mq_ctx { void blk_mq_exit_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); -bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool); +bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *, + unsigned int); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, bool kick_requeue_list); void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); @@ -159,7 +160,7 @@ struct blk_mq_alloc_data { static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data) { - if (data->flags & BLK_MQ_REQ_INTERNAL) + if (data->q->elevator) return data->hctx->sched_tags; return data->hctx->tags; @@ -179,20 +180,16 @@ unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part); void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]); -static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx) +static inline void blk_mq_put_dispatch_budget(struct request_queue *q) { - struct request_queue *q = hctx->queue; - if (q->mq_ops->put_budget) - q->mq_ops->put_budget(hctx); + q->mq_ops->put_budget(q); } -static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx) +static inline bool blk_mq_get_dispatch_budget(struct request_queue *q) { - struct request_queue *q = hctx->queue; - if (q->mq_ops->get_budget) - return q->mq_ops->get_budget(hctx); + return q->mq_ops->get_budget(q); return true; } diff --git a/block/blk-softirq.c b/block/blk-softirq.c deleted file mode 100644 index 6e7ec87d49fa..000000000000 --- a/block/blk-softirq.c +++ /dev/null @@ -1,156 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Functions related to softirq rq completions - */ -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/bio.h> -#include <linux/blkdev.h> -#include <linux/interrupt.h> -#include <linux/cpu.h> -#include <linux/sched.h> -#include <linux/sched/topology.h> - -#include "blk.h" - -static DEFINE_PER_CPU(struct list_head, blk_cpu_done); - -/* - * Softirq action handler - move entries to local list and loop over them - * while passing them to the queue registered handler. - */ -static __latent_entropy void blk_done_softirq(struct softirq_action *h) -{ - struct list_head *cpu_list, local_list; - - local_irq_disable(); - cpu_list = this_cpu_ptr(&blk_cpu_done); - list_replace_init(cpu_list, &local_list); - local_irq_enable(); - - while (!list_empty(&local_list)) { - struct request *rq; - - rq = list_entry(local_list.next, struct request, ipi_list); - list_del_init(&rq->ipi_list); - rq->q->mq_ops->complete(rq); - } -} - -#ifdef CONFIG_SMP -static void trigger_softirq(void *data) -{ - struct request *rq = data; - struct list_head *list; - - list = this_cpu_ptr(&blk_cpu_done); - list_add_tail(&rq->ipi_list, list); - - if (list->next == &rq->ipi_list) - raise_softirq_irqoff(BLOCK_SOFTIRQ); -} - -/* - * Setup and invoke a run of 'trigger_softirq' on the given cpu. - */ -static int raise_blk_irq(int cpu, struct request *rq) -{ - if (cpu_online(cpu)) { - call_single_data_t *data = &rq->csd; - - data->func = trigger_softirq; - data->info = rq; - data->flags = 0; - - smp_call_function_single_async(cpu, data); - return 0; - } - - return 1; -} -#else /* CONFIG_SMP */ -static int raise_blk_irq(int cpu, struct request *rq) -{ - return 1; -} -#endif - -static int blk_softirq_cpu_dead(unsigned int cpu) -{ - /* - * If a CPU goes away, splice its entries to the current CPU - * and trigger a run of the softirq - */ - local_irq_disable(); - list_splice_init(&per_cpu(blk_cpu_done, cpu), - this_cpu_ptr(&blk_cpu_done)); - raise_softirq_irqoff(BLOCK_SOFTIRQ); - local_irq_enable(); - - return 0; -} - -void __blk_complete_request(struct request *req) -{ - struct request_queue *q = req->q; - int cpu, ccpu = req->mq_ctx->cpu; - unsigned long flags; - bool shared = false; - - BUG_ON(!q->mq_ops->complete); - - local_irq_save(flags); - cpu = smp_processor_id(); - - /* - * Select completion CPU - */ - if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && ccpu != -1) { - if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) - shared = cpus_share_cache(cpu, ccpu); - } else - ccpu = cpu; - - /* - * If current CPU and requested CPU share a cache, run the softirq on - * the current CPU. One might concern this is just like - * QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is - * running in interrupt handler, and currently I/O controller doesn't - * support multiple interrupts, so current CPU is unique actually. This - * avoids IPI sending from current CPU to the first CPU of a group. - */ - if (ccpu == cpu || shared) { - struct list_head *list; -do_local: - list = this_cpu_ptr(&blk_cpu_done); - list_add_tail(&req->ipi_list, list); - - /* - * if the list only contains our just added request, - * signal a raise of the softirq. If there are already - * entries there, someone already raised the irq but it - * hasn't run yet. - */ - if (list->next == &req->ipi_list) - raise_softirq_irqoff(BLOCK_SOFTIRQ); - } else if (raise_blk_irq(ccpu, req)) - goto do_local; - - local_irq_restore(flags); -} - -static __init int blk_softirq_init(void) -{ - int i; - - for_each_possible_cpu(i) - INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i)); - - open_softirq(BLOCK_SOFTIRQ, blk_done_softirq); - cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD, - "block/softirq:dead", NULL, - blk_softirq_cpu_dead); - return 0; -} -subsys_initcall(blk_softirq_init); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 02643e149d5e..be67952e7be2 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -11,6 +11,7 @@ #include <linux/blktrace_api.h> #include <linux/blk-mq.h> #include <linux/blk-cgroup.h> +#include <linux/debugfs.h> #include "blk.h" #include "blk-mq.h" @@ -873,22 +874,32 @@ static void blk_exit_queue(struct request_queue *q) bdi_put(q->backing_dev_info); } - /** - * __blk_release_queue - release a request queue - * @work: pointer to the release_work member of the request queue to be released + * blk_release_queue - releases all allocated resources of the request_queue + * @kobj: pointer to a kobject, whose container is a request_queue + * + * This function releases all allocated resources of the request queue. + * + * The struct request_queue refcount is incremented with blk_get_queue() and + * decremented with blk_put_queue(). Once the refcount reaches 0 this function + * is called. + * + * For drivers that have a request_queue on a gendisk and added with + * __device_add_disk() the refcount to request_queue will reach 0 with + * the last put_disk() called by the driver. For drivers which don't use + * __device_add_disk() this happens with blk_cleanup_queue(). + * + * Drivers exist which depend on the release of the request_queue to be + * synchronous, it should not be deferred. * - * Description: - * This function is called when a block device is being unregistered. The - * process of releasing a request queue starts with blk_cleanup_queue, which - * set the appropriate flags and then calls blk_put_queue, that decrements - * the reference counter of the request queue. Once the reference counter - * of the request queue reaches zero, blk_release_queue is called to release - * all allocated resources of the request queue. + * Context: can sleep */ -static void __blk_release_queue(struct work_struct *work) +static void blk_release_queue(struct kobject *kobj) { - struct request_queue *q = container_of(work, typeof(*q), release_work); + struct request_queue *q = + container_of(kobj, struct request_queue, kobj); + + might_sleep(); if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags)) blk_stat_remove_callback(q, q->poll_cb); @@ -907,6 +918,9 @@ static void __blk_release_queue(struct work_struct *work) blk_mq_release(q); blk_trace_shutdown(q); + mutex_lock(&q->debugfs_mutex); + debugfs_remove_recursive(q->debugfs_dir); + mutex_unlock(&q->debugfs_mutex); if (queue_is_mq(q)) blk_mq_debugfs_unregister(q); @@ -917,15 +931,6 @@ static void __blk_release_queue(struct work_struct *work) call_rcu(&q->rcu_head, blk_free_queue_rcu); } -static void blk_release_queue(struct kobject *kobj) -{ - struct request_queue *q = - container_of(kobj, struct request_queue, kobj); - - INIT_WORK(&q->release_work, __blk_release_queue); - schedule_work(&q->release_work); -} - static const struct sysfs_ops queue_sysfs_ops = { .show = queue_attr_show, .store = queue_attr_store, @@ -988,6 +993,11 @@ int blk_register_queue(struct gendisk *disk) goto unlock; } + mutex_lock(&q->debugfs_mutex); + q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent), + blk_debugfs_root); + mutex_unlock(&q->debugfs_mutex); + if (queue_is_mq(q)) { __blk_mq_register_dev(dev, q); blk_mq_debugfs_register(q); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 209fdd8939fb..fee3325edf27 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1339,8 +1339,8 @@ static void blk_throtl_dispatch_work_fn(struct work_struct *work) if (!bio_list_empty(&bio_list_on_stack)) { blk_start_plug(&plug); - while((bio = bio_list_pop(&bio_list_on_stack))) - generic_make_request(bio); + while ((bio = bio_list_pop(&bio_list_on_stack))) + submit_bio_noacct(bio); blk_finish_plug(&plug); } } @@ -2158,17 +2158,18 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td) } #endif -bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, - struct bio *bio) +bool blk_throtl_bio(struct bio *bio) { + struct request_queue *q = bio->bi_disk->queue; + struct blkcg_gq *blkg = bio->bi_blkg; struct throtl_qnode *qn = NULL; - struct throtl_grp *tg = blkg_to_tg(blkg ?: q->root_blkg); + struct throtl_grp *tg = blkg_to_tg(blkg); struct throtl_service_queue *sq; bool rw = bio_data_dir(bio); bool throttled = false; struct throtl_data *td = tg->td; - WARN_ON_ONCE(!rcu_read_lock_held()); + rcu_read_lock(); /* see throtl_charge_bio() */ if (bio_flagged(bio, BIO_THROTTLED)) @@ -2273,6 +2274,7 @@ out: if (throttled || !td->track_bio_latency) bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY; #endif + rcu_read_unlock(); return throttled; } diff --git a/block/blk-timeout.c b/block/blk-timeout.c index 8aa68fae96ad..4c1fc3417460 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -20,13 +20,11 @@ static int __init setup_fail_io_timeout(char *str) } __setup("fail_io_timeout=", setup_fail_io_timeout); -int blk_should_fake_timeout(struct request_queue *q) +bool __blk_should_fake_timeout(struct request_queue *q) { - if (!test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags)) - return 0; - return should_fail(&fail_io_timeout, 1); } +EXPORT_SYMBOL_GPL(__blk_should_fake_timeout); static int __init fail_io_timeout_debugfs(void) { @@ -90,11 +88,29 @@ void blk_abort_request(struct request *req) } EXPORT_SYMBOL_GPL(blk_abort_request); +static unsigned long blk_timeout_mask __read_mostly; + +static int __init blk_timeout_init(void) +{ + blk_timeout_mask = roundup_pow_of_two(HZ) - 1; + return 0; +} + +late_initcall(blk_timeout_init); + +/* + * Just a rough estimate, we don't care about specific values for timeouts. + */ +static inline unsigned long blk_round_jiffies(unsigned long j) +{ + return (j + blk_timeout_mask) + 1; +} + unsigned long blk_rq_timeout(unsigned long timeout) { unsigned long maxt; - maxt = round_jiffies_up(jiffies + BLK_MAX_TIMEOUT); + maxt = blk_round_jiffies(jiffies + BLK_MAX_TIMEOUT); if (time_after(timeout, maxt)) timeout = maxt; @@ -131,7 +147,7 @@ void blk_add_timer(struct request *req) * than an existing one, modify the timer. Round up to next nearest * second. */ - expiry = blk_rq_timeout(round_jiffies_up(expiry)); + expiry = blk_rq_timeout(blk_round_jiffies(expiry)); if (!timer_pending(&q->timeout) || time_before(expiry, q->timeout.expires)) { diff --git a/block/blk.h b/block/blk.h index b5d1f0fc6547..49e2928a1632 100644 --- a/block/blk.h +++ b/block/blk.h @@ -14,9 +14,7 @@ /* Max future timer expiry for timeouts */ #define BLK_MAX_TIMEOUT (5 * HZ) -#ifdef CONFIG_DEBUG_FS extern struct dentry *blk_debugfs_root; -#endif struct blk_flush_queue { unsigned int flush_pending_idx:1; @@ -27,11 +25,6 @@ struct blk_flush_queue { struct list_head flush_data_in_flight; struct request *flush_rq; - /* - * flush_rq shares tag with this rq, both can't be active - * at the same time - */ - struct request *orig_rq; struct lock_class_key key; spinlock_t mq_flush_lock; }; @@ -223,21 +216,11 @@ ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf); ssize_t part_fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); - -#ifdef CONFIG_FAIL_IO_TIMEOUT -int blk_should_fake_timeout(struct request_queue *); ssize_t part_timeout_show(struct device *, struct device_attribute *, char *); ssize_t part_timeout_store(struct device *, struct device_attribute *, const char *, size_t); -#else -static inline int blk_should_fake_timeout(struct request_queue *q) -{ - return 0; -} -#endif -void __blk_queue_split(struct request_queue *q, struct bio **bio, - unsigned int *nr_segs); +void __blk_queue_split(struct bio **bio, unsigned int *nr_segs); int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs); int ll_front_merge_fn(struct request *req, struct bio *bio, @@ -282,6 +265,20 @@ static inline unsigned int bio_allowed_max_sectors(struct request_queue *q) } /* + * The max bio size which is aligned to q->limits.discard_granularity. This + * is a hint to split large discard bio in generic block layer, then if device + * driver needs to split the discard bio into smaller ones, their bi_size can + * be very probably and easily aligned to discard_granularity of the device's + * queue. + */ +static inline unsigned int bio_aligned_discard_max_sectors( + struct request_queue *q) +{ + return round_down(UINT_MAX, q->limits.discard_granularity) >> + SECTOR_SHIFT; +} + +/* * Internal io_context interface */ void get_io_context(struct io_context *ioc); @@ -299,10 +296,12 @@ int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node); extern int blk_throtl_init(struct request_queue *q); extern void blk_throtl_exit(struct request_queue *q); extern void blk_throtl_register_queue(struct request_queue *q); +bool blk_throtl_bio(struct bio *bio); #else /* CONFIG_BLK_DEV_THROTTLING */ static inline int blk_throtl_init(struct request_queue *q) { return 0; } static inline void blk_throtl_exit(struct request_queue *q) { } static inline void blk_throtl_register_queue(struct request_queue *q) { } +static inline bool blk_throtl_bio(struct bio *bio) { return false; } #endif /* CONFIG_BLK_DEV_THROTTLING */ #ifdef CONFIG_BLK_DEV_THROTTLING_LOW extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page); @@ -434,8 +433,6 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) #endif } -struct request_queue *__blk_alloc_queue(int node_id); - int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page); diff --git a/block/bounce.c b/block/bounce.c index c3aaed070124..431be88a0240 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -309,7 +309,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, if (!passthrough && sectors < bio_sectors(*bio_orig)) { bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split); bio_chain(bio, *bio_orig); - generic_make_request(*bio_orig); + submit_bio_noacct(*bio_orig); *bio_orig = bio; } bio = bounce_clone_bio(*bio_orig, GFP_NOIO, passthrough ? NULL : diff --git a/block/bsg-lib.c b/block/bsg-lib.c index 6cbb7926534c..fb7b347f8010 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -181,9 +181,12 @@ EXPORT_SYMBOL_GPL(bsg_job_get); void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len) { + struct request *rq = blk_mq_rq_from_pdu(job); + job->result = result; job->reply_payload_rcv_len = reply_payload_rcv_len; - blk_mq_complete_request(blk_mq_rq_from_pdu(job)); + if (likely(!blk_should_fake_timeout(rq->q))) + blk_mq_complete_request(rq); } EXPORT_SYMBOL_GPL(bsg_job_done); diff --git a/block/genhd.c b/block/genhd.c index 1a7659327664..8b1e9f48957c 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -38,8 +38,6 @@ static struct kobject *block_depr; static DEFINE_SPINLOCK(ext_devt_lock); static DEFINE_IDR(ext_devt_idr); -static const struct device_type disk_type; - static void disk_check_events(struct disk_events *ev, unsigned int *clearing_ptr); static void disk_alloc_events(struct gendisk *disk); @@ -876,11 +874,32 @@ static void invalidate_partition(struct gendisk *disk, int partno) bdput(bdev); } +/** + * del_gendisk - remove the gendisk + * @disk: the struct gendisk to remove + * + * Removes the gendisk and all its associated resources. This deletes the + * partitions associated with the gendisk, and unregisters the associated + * request_queue. + * + * This is the counter to the respective __device_add_disk() call. + * + * The final removal of the struct gendisk happens when its refcount reaches 0 + * with put_disk(), which should be called after del_gendisk(), if + * __device_add_disk() was used. + * + * Drivers exist which depend on the release of the gendisk to be synchronous, + * it should not be deferred. + * + * Context: can sleep + */ void del_gendisk(struct gendisk *disk) { struct disk_part_iter piter; struct hd_struct *part; + might_sleep(); + blk_integrity_del(disk); disk_del_events(disk); @@ -971,11 +990,15 @@ static ssize_t disk_badblocks_store(struct device *dev, * * This function gets the structure containing partitioning * information for the given device @devt. + * + * Context: can sleep */ struct gendisk *get_gendisk(dev_t devt, int *partno) { struct gendisk *disk = NULL; + might_sleep(); + if (MAJOR(devt) != BLOCK_EXT_MAJOR) { struct kobject *kobj; @@ -1514,10 +1537,31 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno) return 0; } +/** + * disk_release - releases all allocated resources of the gendisk + * @dev: the device representing this disk + * + * This function releases all allocated resources of the gendisk. + * + * The struct gendisk refcount is incremented with get_gendisk() or + * get_disk_and_module(), and its refcount is decremented with + * put_disk_and_module() or put_disk(). Once the refcount reaches 0 this + * function is called. + * + * Drivers which used __device_add_disk() have a gendisk with a request_queue + * assigned. Since the request_queue sits on top of the gendisk for these + * drivers we also call blk_put_queue() for them, and we expect the + * request_queue refcount to reach 0 at this point, and so the request_queue + * will also be freed prior to the disk. + * + * Context: can sleep + */ static void disk_release(struct device *dev) { struct gendisk *disk = dev_to_disk(dev); + might_sleep(); + blk_free_devt(dev->devt); disk_release_events(disk); kfree(disk->random); @@ -1541,7 +1585,7 @@ static char *block_devnode(struct device *dev, umode_t *mode, return NULL; } -static const struct device_type disk_type = { +const struct device_type disk_type = { .name = "disk", .groups = disk_attr_groups, .release = disk_release, @@ -1727,6 +1771,15 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) } EXPORT_SYMBOL(__alloc_disk_node); +/** + * get_disk_and_module - increments the gendisk and gendisk fops module refcount + * @disk: the struct gendisk to to increment the refcount for + * + * This increments the refcount for the struct gendisk, and the gendisk's + * fops module owner. + * + * Context: Any context. + */ struct kobject *get_disk_and_module(struct gendisk *disk) { struct module *owner; @@ -1747,6 +1800,16 @@ struct kobject *get_disk_and_module(struct gendisk *disk) } EXPORT_SYMBOL(get_disk_and_module); +/** + * put_disk - decrements the gendisk refcount + * @disk: the struct gendisk to to decrement the refcount for + * + * This decrements the refcount for the struct gendisk. When this reaches 0 + * we'll have disk_release() called. + * + * Context: Any context, but the last reference must not be dropped from + * atomic context. + */ void put_disk(struct gendisk *disk) { if (disk) @@ -1754,9 +1817,15 @@ void put_disk(struct gendisk *disk) } EXPORT_SYMBOL(put_disk); -/* +/** + * put_disk_and_module - decrements the module and gendisk refcount + * @disk: the struct gendisk to to decrement the refcount for + * * This is a counterpart of get_disk_and_module() and thus also of * get_gendisk(). + * + * Context: Any context, but the last reference must not be dropped from + * atomic context. */ void put_disk_and_module(struct gendisk *disk) { @@ -1985,18 +2054,12 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask) */ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) { - const struct block_device_operations *bdops = disk->fops; struct disk_events *ev = disk->ev; unsigned int pending; unsigned int clearing = mask; - if (!ev) { - /* for drivers still using the old ->media_changed method */ - if ((mask & DISK_EVENT_MEDIA_CHANGE) && - bdops->media_changed && bdops->media_changed(disk)) - return DISK_EVENT_MEDIA_CHANGE; + if (!ev) return 0; - } disk_block_events(disk); diff --git a/block/partitions/core.c b/block/partitions/core.c index 78951e33b2d7..e62a98a8eeb7 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -619,8 +619,6 @@ int blk_drop_partitions(struct block_device *bdev) struct disk_part_iter piter; struct hd_struct *part; - if (!disk_part_scan_enabled(bdev->bd_disk)) - return 0; if (bdev->bd_part_count) return -EBUSY; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 2fb25c348d53..2723a70eb855 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -282,7 +282,7 @@ out: return err; } -static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t brd_submit_bio(struct bio *bio) { struct brd_device *brd = bio->bi_disk->private_data; struct bio_vec bvec; @@ -330,6 +330,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector, static const struct block_device_operations brd_fops = { .owner = THIS_MODULE, + .submit_bio = brd_submit_bio, .rw_page = brd_rw_page, }; @@ -381,7 +382,7 @@ static struct brd_device *brd_alloc(int i) spin_lock_init(&brd->brd_lock); INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC); - brd->brd_queue = blk_alloc_queue(brd_make_request, NUMA_NO_NODE); + brd->brd_queue = blk_alloc_queue(NUMA_NO_NODE); if (!brd->brd_queue) goto out_free_dev; diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 33d0831c99b6..fe6cb99eb917 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1451,7 +1451,7 @@ extern void conn_free_crypto(struct drbd_connection *connection); /* drbd_req */ extern void do_submit(struct work_struct *ws); extern void __drbd_make_request(struct drbd_device *, struct bio *, unsigned long); -extern blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio); +extern blk_qc_t drbd_submit_bio(struct bio *bio); extern int drbd_read_remote(struct drbd_device *device, struct drbd_request *req); extern int is_valid_ar_handle(struct drbd_request *, sector_t); @@ -1576,12 +1576,12 @@ void drbd_set_my_capacity(struct drbd_device *device, sector_t size); /* * used to submit our private bio */ -static inline void drbd_generic_make_request(struct drbd_device *device, +static inline void drbd_submit_bio_noacct(struct drbd_device *device, int fault_type, struct bio *bio) { __release(local); if (!bio->bi_disk) { - drbd_err(device, "drbd_generic_make_request: bio->bi_disk == NULL\n"); + drbd_err(device, "drbd_submit_bio_noacct: bio->bi_disk == NULL\n"); bio->bi_status = BLK_STS_IOERR; bio_endio(bio); return; @@ -1590,7 +1590,7 @@ static inline void drbd_generic_make_request(struct drbd_device *device, if (drbd_insert_fault(device, fault_type)) bio_io_error(bio); else - generic_make_request(bio); + submit_bio_noacct(bio); } void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backing_dev *bdev, diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 45fbd526c453..cb687ccdbd96 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -132,9 +132,10 @@ wait_queue_head_t drbd_pp_wait; DEFINE_RATELIMIT_STATE(drbd_ratelimit_state, 5 * HZ, 5); static const struct block_device_operations drbd_ops = { - .owner = THIS_MODULE, - .open = drbd_open, - .release = drbd_release, + .owner = THIS_MODULE, + .submit_bio = drbd_submit_bio, + .open = drbd_open, + .release = drbd_release, }; struct bio *bio_alloc_drbd(gfp_t gfp_mask) @@ -2324,7 +2325,7 @@ static void do_retry(struct work_struct *ws) * workqueues instead. */ - /* We are not just doing generic_make_request(), + /* We are not just doing submit_bio_noacct(), * as we want to keep the start_time information. */ inc_ap_bio(device); __drbd_make_request(device, bio, start_jif); @@ -2414,62 +2415,6 @@ static void drbd_cleanup(void) pr_info("module cleanup done.\n"); } -/** - * drbd_congested() - Callback for the flusher thread - * @congested_data: User data - * @bdi_bits: Bits the BDI flusher thread is currently interested in - * - * Returns 1<<WB_async_congested and/or 1<<WB_sync_congested if we are congested. - */ -static int drbd_congested(void *congested_data, int bdi_bits) -{ - struct drbd_device *device = congested_data; - struct request_queue *q; - char reason = '-'; - int r = 0; - - if (!may_inc_ap_bio(device)) { - /* DRBD has frozen IO */ - r = bdi_bits; - reason = 'd'; - goto out; - } - - if (test_bit(CALLBACK_PENDING, &first_peer_device(device)->connection->flags)) { - r |= (1 << WB_async_congested); - /* Without good local data, we would need to read from remote, - * and that would need the worker thread as well, which is - * currently blocked waiting for that usermode helper to - * finish. - */ - if (!get_ldev_if_state(device, D_UP_TO_DATE)) - r |= (1 << WB_sync_congested); - else - put_ldev(device); - r &= bdi_bits; - reason = 'c'; - goto out; - } - - if (get_ldev(device)) { - q = bdev_get_queue(device->ldev->backing_bdev); - r = bdi_congested(q->backing_dev_info, bdi_bits); - put_ldev(device); - if (r) - reason = 'b'; - } - - if (bdi_bits & (1 << WB_async_congested) && - test_bit(NET_CONGESTED, &first_peer_device(device)->connection->flags)) { - r |= (1 << WB_async_congested); - reason = reason == 'b' ? 'a' : 'n'; - } - -out: - device->congestion_reason = reason; - return r; -} - static void drbd_init_workqueue(struct drbd_work_queue* wq) { spin_lock_init(&wq->q_lock); @@ -2801,11 +2746,10 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_init_set_defaults(device); - q = blk_alloc_queue(drbd_make_request, NUMA_NO_NODE); + q = blk_alloc_queue(NUMA_NO_NODE); if (!q) goto out_no_q; device->rq_queue = q; - q->queuedata = device; disk = alloc_disk(1); if (!disk) @@ -2825,9 +2769,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig /* we have no partitions. we contain only ourselves. */ device->this_bdev->bd_contains = device->this_bdev; - q->backing_dev_info->congested_fn = drbd_congested; - q->backing_dev_info->congested_data = device; - blk_queue_write_cache(q, true, true); /* Setting the max_hw_sectors to an odd value of 8kibyte here This triggers a max_bio_size message upon first attach or connect */ diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c index 1c41cd9982a2..3c0193de2498 100644 --- a/drivers/block/drbd/drbd_proc.c +++ b/drivers/block/drbd/drbd_proc.c @@ -265,7 +265,6 @@ int drbd_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%2d: cs:Unconfigured\n", i); } else { /* reset device->congestion_reason */ - bdi_rw_congested(device->rq_queue->backing_dev_info); nc = rcu_dereference(first_peer_device(device)->connection->net_conf); wp = nc ? nc->wire_protocol - DRBD_PROT_A + 'A' : ' '; diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 3a3f2b6a821f..c74f561b4eab 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1723,7 +1723,7 @@ next_bio: bios = bios->bi_next; bio->bi_next = NULL; - drbd_generic_make_request(device, fault_type, bio); + drbd_submit_bio_noacct(device, fault_type, bio); } while (bios); return 0; diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index c80a2f1c3c2a..674be09b2da9 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -1164,7 +1164,7 @@ drbd_submit_req_private_bio(struct drbd_request *req) else if (bio_op(bio) == REQ_OP_DISCARD) drbd_process_discard_or_zeroes_req(req, EE_TRIM); else - generic_make_request(bio); + submit_bio_noacct(bio); put_ldev(device); } else bio_io_error(bio); @@ -1593,12 +1593,12 @@ void do_submit(struct work_struct *ws) } } -blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio) +blk_qc_t drbd_submit_bio(struct bio *bio) { - struct drbd_device *device = (struct drbd_device *) q->queuedata; + struct drbd_device *device = bio->bi_disk->private_data; unsigned long start_jif; - blk_queue_split(q, &bio); + blk_queue_split(&bio); start_jif = jiffies; diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 2b89c9f2ca70..7c903de5c4e1 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1525,7 +1525,7 @@ int w_restart_disk_io(struct drbd_work *w, int cancel) drbd_req_make_private_bio(req, req->master_bio); bio_set_dev(req->private_bio, device->ldev->backing_bdev); - generic_make_request(req->private_bio); + submit_bio_noacct(req->private_bio); return 0; } diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 3e9db22db2a8..09079aee8dc4 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4205,7 +4205,6 @@ static int __floppy_read_block_0(struct block_device *bdev, int drive) struct bio_vec bio_vec; struct page *page; struct rb0_cbdata cbdata; - size_t size; page = alloc_page(GFP_NOIO); if (!page) { @@ -4213,15 +4212,11 @@ static int __floppy_read_block_0(struct block_device *bdev, int drive) return -ENOMEM; } - size = bdev->bd_block_size; - if (!size) - size = 1024; - cbdata.drive = drive; bio_init(&bio, &bio_vec, 1); bio_set_dev(&bio, bdev); - bio_add_page(&bio, page, size, 0); + bio_add_page(&bio, page, block_size(bdev), 0); bio.bi_iter.bi_sector = 0; bio.bi_flags |= (1 << BIO_QUIET); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 475e1a738560..d18160146226 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -509,7 +509,8 @@ static void lo_rw_aio_do_completion(struct loop_cmd *cmd) return; kfree(cmd->bvec); cmd->bvec = NULL; - blk_mq_complete_request(rq); + if (likely(!blk_should_fake_timeout(rq->q))) + blk_mq_complete_request(rq); } static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2) @@ -1089,11 +1090,10 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, * here to avoid changing device under exclusive owner. */ if (!(mode & FMODE_EXCL)) { - claimed_bdev = bd_start_claiming(bdev, loop_configure); - if (IS_ERR(claimed_bdev)) { - error = PTR_ERR(claimed_bdev); + claimed_bdev = bdev->bd_contains; + error = bd_prepare_to_claim(bdev, claimed_bdev, loop_configure); + if (error) goto out_putf; - } } error = mutex_lock_killable(&loop_ctl_mutex); @@ -2048,7 +2048,8 @@ static void loop_handle_cmd(struct loop_cmd *cmd) cmd->ret = ret; else cmd->ret = ret ? -EIO : 0; - blk_mq_complete_request(rq); + if (likely(!blk_should_fake_timeout(rq->q))) + blk_mq_complete_request(rq); } } @@ -2402,6 +2403,8 @@ static void __exit loop_exit(void) range = max_loop ? max_loop << part_shift : 1UL << MINORBITS; + mutex_lock(&loop_ctl_mutex); + idr_for_each(&loop_index_idr, &loop_exit_cb, NULL); idr_destroy(&loop_index_idr); @@ -2409,6 +2412,8 @@ static void __exit loop_exit(void) unregister_blkdev(LOOP_MAJOR, "loop"); misc_deregister(&loop_misc); + + mutex_unlock(&loop_ctl_mutex); } module_init(loop_init); diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index f6bafa9a68b9..153e2cdecb4d 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -492,7 +492,8 @@ static void mtip_complete_command(struct mtip_cmd *cmd, blk_status_t status) struct request *req = blk_mq_rq_from_pdu(cmd); cmd->status = status; - blk_mq_complete_request(req); + if (likely(!blk_should_fake_timeout(req->q))) + blk_mq_complete_request(req); } /* diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index ce7e9f223b20..3ff4054d6834 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -784,6 +784,7 @@ static void recv_work(struct work_struct *work) struct nbd_device *nbd = args->nbd; struct nbd_config *config = nbd->config; struct nbd_cmd *cmd; + struct request *rq; while (1) { cmd = nbd_read_stat(nbd, args->index); @@ -796,7 +797,9 @@ static void recv_work(struct work_struct *work) break; } - blk_mq_complete_request(blk_mq_rq_from_pdu(cmd)); + rq = blk_mq_rq_from_pdu(cmd); + if (likely(!blk_should_fake_timeout(rq->q))) + blk_mq_complete_request(rq); } atomic_dec(&config->recv_threads); wake_up(&config->recv_wq); diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 87b31f9ca362..907c6858aec0 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1283,7 +1283,8 @@ static inline void nullb_complete_cmd(struct nullb_cmd *cmd) case NULL_IRQ_SOFTIRQ: switch (cmd->nq->dev->queue_mode) { case NULL_Q_MQ: - blk_mq_complete_request(cmd->rq); + if (likely(!blk_should_fake_timeout(cmd->rq->q))) + blk_mq_complete_request(cmd->rq); break; case NULL_Q_BIO: /* @@ -1387,11 +1388,11 @@ static struct nullb_queue *nullb_to_queue(struct nullb *nullb) return &nullb->queues[index]; } -static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio) +static blk_qc_t null_submit_bio(struct bio *bio) { sector_t sector = bio->bi_iter.bi_sector; sector_t nr_sectors = bio_sectors(bio); - struct nullb *nullb = q->queuedata; + struct nullb *nullb = bio->bi_disk->private_data; struct nullb_queue *nq = nullb_to_queue(nullb); struct nullb_cmd *cmd; @@ -1423,7 +1424,7 @@ static bool should_requeue_request(struct request *rq) static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res) { pr_info("rq %p timed out\n", rq); - blk_mq_force_complete_rq(rq); + blk_mq_complete_request(rq); return BLK_EH_DONE; } @@ -1574,7 +1575,13 @@ static void null_config_discard(struct nullb *nullb) blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q); } -static const struct block_device_operations null_ops = { +static const struct block_device_operations null_bio_ops = { + .owner = THIS_MODULE, + .submit_bio = null_submit_bio, + .report_zones = null_report_zones, +}; + +static const struct block_device_operations null_rq_ops = { .owner = THIS_MODULE, .report_zones = null_report_zones, }; @@ -1646,7 +1653,10 @@ static int null_gendisk_register(struct nullb *nullb) disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO; disk->major = null_major; disk->first_minor = nullb->index; - disk->fops = &null_ops; + if (queue_is_mq(nullb->q)) + disk->fops = &null_rq_ops; + else + disk->fops = &null_bio_ops; disk->private_data = nullb; disk->queue = nullb->q; strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); @@ -1791,7 +1801,7 @@ static int null_add_dev(struct nullb_device *dev) goto out_cleanup_tags; } } else if (dev->queue_mode == NULL_Q_BIO) { - nullb->q = blk_alloc_queue(null_queue_bio, dev->home_node); + nullb->q = blk_alloc_queue(dev->home_node); if (!nullb->q) { rv = -ENOMEM; goto out_cleanup_queues; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 27a33adc41e4..4becc1efe775 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -36,7 +36,7 @@ * block device, assembling the pieces to full packets and queuing them to the * packet I/O scheduler. * - * At the top layer there is a custom make_request_fn function that forwards + * At the top layer there is a custom ->submit_bio function that forwards * read requests directly to the iosched queue and puts write requests in the * unaligned write queue. A kernel thread performs the necessary read * gathering to convert the unaligned writes to aligned writes and then feeds @@ -913,7 +913,7 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) } atomic_inc(&pd->cdrw.pending_bios); - generic_make_request(bio); + submit_bio_noacct(bio); } } @@ -2428,15 +2428,15 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) } } -static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t pkt_submit_bio(struct bio *bio) { struct pktcdvd_device *pd; char b[BDEVNAME_SIZE]; struct bio *split; - blk_queue_split(q, &bio); + blk_queue_split(&bio); - pd = q->queuedata; + pd = bio->bi_disk->queue->queuedata; if (!pd) { pr_err("%s incorrect request queue\n", bio_devname(bio, b)); goto end_io; @@ -2480,7 +2480,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio) split = bio; } - pkt_make_request_write(q, split); + pkt_make_request_write(bio->bi_disk->queue, split); } while (split != bio); return BLK_QC_T_NONE; @@ -2685,6 +2685,7 @@ static char *pkt_devnode(struct gendisk *disk, umode_t *mode) static const struct block_device_operations pktcdvd_ops = { .owner = THIS_MODULE, + .submit_bio = pkt_submit_bio, .open = pkt_open, .release = pkt_close, .ioctl = pkt_ioctl, @@ -2749,7 +2750,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) disk->flags = GENHD_FL_REMOVABLE; strcpy(disk->disk_name, pd->name); disk->private_data = pd; - disk->queue = blk_alloc_queue(pkt_make_request, NUMA_NO_NODE); + disk->queue = blk_alloc_queue(NUMA_NO_NODE); if (!disk->queue) goto out_mem2; diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index 821d4d8b1d76..1088798c8dd0 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -90,12 +90,6 @@ struct ps3vram_priv { static int ps3vram_major; - -static const struct block_device_operations ps3vram_fops = { - .owner = THIS_MODULE, -}; - - #define DMA_NOTIFIER_HANDLE_BASE 0x66604200 /* first DMA notifier handle */ #define DMA_NOTIFIER_OFFSET_BASE 0x1000 /* first DMA notifier offset */ #define DMA_NOTIFIER_SIZE 0x40 @@ -585,15 +579,15 @@ out: return next; } -static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t ps3vram_submit_bio(struct bio *bio) { - struct ps3_system_bus_device *dev = q->queuedata; + struct ps3_system_bus_device *dev = bio->bi_disk->private_data; struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev); int busy; dev_dbg(&dev->core, "%s\n", __func__); - blk_queue_split(q, &bio); + blk_queue_split(&bio); spin_lock_irq(&priv->lock); busy = !bio_list_empty(&priv->list); @@ -610,6 +604,11 @@ static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio) return BLK_QC_T_NONE; } +static const struct block_device_operations ps3vram_fops = { + .owner = THIS_MODULE, + .submit_bio = ps3vram_submit_bio, +}; + static int ps3vram_probe(struct ps3_system_bus_device *dev) { struct ps3vram_priv *priv; @@ -737,7 +736,7 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) ps3vram_proc_init(dev); - queue = blk_alloc_queue(ps3vram_make_request, NUMA_NO_NODE); + queue = blk_alloc_queue(NUMA_NO_NODE); if (!queue) { dev_err(&dev->core, "blk_alloc_queue failed\n"); error = -ENOMEM; @@ -745,7 +744,6 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) } priv->queue = queue; - queue->queuedata = dev; blk_queue_max_segments(queue, BLK_MAX_SEGMENTS); blk_queue_max_segment_size(queue, BLK_MAX_SEGMENT_SIZE); blk_queue_max_hw_sectors(queue, BLK_SAFE_MAX_SECTORS); diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c index 3ba07ab30c84..edacefff6e35 100644 --- a/drivers/block/rsxx/dev.c +++ b/drivers/block/rsxx/dev.c @@ -50,6 +50,8 @@ struct rsxx_bio_meta { static struct kmem_cache *bio_meta_pool; +static blk_qc_t rsxx_submit_bio(struct bio *bio); + /*----------------- Block Device Operations -----------------*/ static int rsxx_blkdev_ioctl(struct block_device *bdev, fmode_t mode, @@ -92,6 +94,7 @@ static int rsxx_getgeo(struct block_device *bdev, struct hd_geometry *geo) static const struct block_device_operations rsxx_fops = { .owner = THIS_MODULE, + .submit_bio = rsxx_submit_bio, .getgeo = rsxx_getgeo, .ioctl = rsxx_blkdev_ioctl, }; @@ -117,13 +120,13 @@ static void bio_dma_done_cb(struct rsxx_cardinfo *card, } } -static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t rsxx_submit_bio(struct bio *bio) { - struct rsxx_cardinfo *card = q->queuedata; + struct rsxx_cardinfo *card = bio->bi_disk->private_data; struct rsxx_bio_meta *bio_meta; blk_status_t st = BLK_STS_IOERR; - blk_queue_split(q, &bio); + blk_queue_split(&bio); might_sleep(); @@ -233,7 +236,7 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card) return -ENOMEM; } - card->queue = blk_alloc_queue(rsxx_make_request, NUMA_NO_NODE); + card->queue = blk_alloc_queue(NUMA_NO_NODE); if (!card->queue) { dev_err(CARD_TO_DEV(card), "Failed queue alloc\n"); unregister_blkdev(card->major, DRIVER_NAME); @@ -267,8 +270,6 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card) card->queue->limits.discard_alignment = RSXX_HW_BLK_SIZE; } - card->queue->queuedata = card; - snprintf(card->gendisk->disk_name, sizeof(card->gendisk->disk_name), "rsxx%d", card->disk_id); card->gendisk->major = card->major; @@ -289,7 +290,6 @@ void rsxx_destroy_dev(struct rsxx_cardinfo *card) card->gendisk = NULL; blk_cleanup_queue(card->queue); - card->queue->queuedata = NULL; unregister_blkdev(card->major, DRIVER_NAME); } diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index 51569c199a6c..3a476dc1d14f 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -1417,7 +1417,8 @@ static void skd_resolve_req_exception(struct skd_device *skdev, case SKD_CHECK_STATUS_REPORT_GOOD: case SKD_CHECK_STATUS_REPORT_SMART_ALERT: skreq->status = BLK_STS_OK; - blk_mq_complete_request(req); + if (likely(!blk_should_fake_timeout(req->q))) + blk_mq_complete_request(req); break; case SKD_CHECK_STATUS_BUSY_IMMINENT: @@ -1440,7 +1441,8 @@ static void skd_resolve_req_exception(struct skd_device *skdev, case SKD_CHECK_STATUS_REPORT_ERROR: default: skreq->status = BLK_STS_IOERR; - blk_mq_complete_request(req); + if (likely(!blk_should_fake_timeout(req->q))) + blk_mq_complete_request(req); break; } } @@ -1560,7 +1562,8 @@ static int skd_isr_completion_posted(struct skd_device *skdev, */ if (likely(cmp_status == SAM_STAT_GOOD)) { skreq->status = BLK_STS_OK; - blk_mq_complete_request(rq); + if (likely(!blk_should_fake_timeout(rq->q))) + blk_mq_complete_request(rq); } else { skd_resolve_req_exception(skdev, skreq, rq); } diff --git a/drivers/block/umem.c b/drivers/block/umem.c index 1e2aa5ae2796..2b95d7b33b91 100644 --- a/drivers/block/umem.c +++ b/drivers/block/umem.c @@ -519,14 +519,15 @@ static int mm_check_plugged(struct cardinfo *card) return !!blk_check_plugged(mm_unplug, card, sizeof(struct blk_plug_cb)); } -static blk_qc_t mm_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t mm_submit_bio(struct bio *bio) { - struct cardinfo *card = q->queuedata; + struct cardinfo *card = bio->bi_disk->private_data; + pr_debug("mm_make_request %llu %u\n", (unsigned long long)bio->bi_iter.bi_sector, bio->bi_iter.bi_size); - blk_queue_split(q, &bio); + blk_queue_split(&bio); spin_lock_irq(&card->lock); *card->biotail = bio; @@ -778,6 +779,7 @@ static int mm_getgeo(struct block_device *bdev, struct hd_geometry *geo) static const struct block_device_operations mm_fops = { .owner = THIS_MODULE, + .submit_bio = mm_submit_bio, .getgeo = mm_getgeo, .revalidate_disk = mm_revalidate, }; @@ -885,10 +887,9 @@ static int mm_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) card->biotail = &card->bio; spin_lock_init(&card->lock); - card->queue = blk_alloc_queue(mm_make_request, NUMA_NO_NODE); + card->queue = blk_alloc_queue(NUMA_NO_NODE); if (!card->queue) goto failed_alloc; - card->queue->queuedata = card; tasklet_init(&card->tasklet, process_page, (unsigned long)card); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 980df853ee49..63b213e00b37 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -171,7 +171,8 @@ static void virtblk_done(struct virtqueue *vq) while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) { struct request *req = blk_mq_rq_from_pdu(vbr); - blk_mq_complete_request(req); + if (likely(!blk_should_fake_timeout(req->q))) + blk_mq_complete_request(req); req_done = true; } if (unlikely(virtqueue_is_broken(vq))) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 3b889ea950c2..3bb3dd8da9b0 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1655,7 +1655,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) BUG(); } - blk_mq_complete_request(req); + if (likely(!blk_should_fake_timeout(req->q))) + blk_mq_complete_request(req); } rinfo->ring.rsp_cons = i; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 270dd810be54..9100ac36670a 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -793,9 +793,9 @@ static void zram_sync_read(struct work_struct *work) } /* - * Block layer want one ->make_request_fn to be active at a time - * so if we use chained IO with parent IO in same context, - * it's a deadlock. To avoid, it, it uses worker thread context. + * Block layer want one ->submit_bio to be active at a time, so if we use + * chained IO with parent IO in same context, it's a deadlock. To avoid that, + * use a worker thread context. */ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, unsigned long entry, struct bio *bio) @@ -1584,9 +1584,9 @@ static void __zram_make_request(struct zram *zram, struct bio *bio) /* * Handler function for all zram I/O requests. */ -static blk_qc_t zram_make_request(struct request_queue *queue, struct bio *bio) +static blk_qc_t zram_submit_bio(struct bio *bio) { - struct zram *zram = queue->queuedata; + struct zram *zram = bio->bi_disk->private_data; if (!valid_io_request(zram, bio->bi_iter.bi_sector, bio->bi_iter.bi_size)) { @@ -1813,6 +1813,7 @@ static int zram_open(struct block_device *bdev, fmode_t mode) static const struct block_device_operations zram_devops = { .open = zram_open, + .submit_bio = zram_submit_bio, .swap_slot_free_notify = zram_slot_free_notify, .rw_page = zram_rw_page, .owner = THIS_MODULE @@ -1891,7 +1892,7 @@ static int zram_add(void) #ifdef CONFIG_ZRAM_WRITEBACK spin_lock_init(&zram->wb_limit_lock); #endif - queue = blk_alloc_queue(zram_make_request, NUMA_NO_NODE); + queue = blk_alloc_queue(NUMA_NO_NODE); if (!queue) { pr_err("Error allocating disk queue for device %d\n", device_id); @@ -1912,7 +1913,6 @@ static int zram_add(void) zram->disk->first_minor = device_id; zram->disk->fops = &zram_devops; zram->disk->queue = queue; - zram->disk->queue->queuedata = zram; zram->disk->private_data = zram; snprintf(zram->disk->disk_name, 16, "zram%d", device_id); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index d82b3b7658bd..0c271b9e3c5b 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -605,7 +605,7 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi) disk->cdi = cdi; ENSURE(cdo, drive_status, CDC_DRIVE_STATUS); - if (cdo->check_events == NULL && cdo->media_changed == NULL) + if (cdo->check_events == NULL) WARN_ON_ONCE(cdo->capability & (CDC_MEDIA_CHANGED | CDC_SELECT_DISC)); ENSURE(cdo, tray_move, CDC_CLOSE_TRAY | CDC_OPEN_TRAY); ENSURE(cdo, lock_door, CDC_LOCK); @@ -1419,8 +1419,6 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot) if (cdi->ops->check_events) cdi->ops->check_events(cdi, 0, slot); - else - cdi->ops->media_changed(cdi, slot); if (slot == CDSL_NONE) { /* set media changed bits, on both queues */ @@ -1517,13 +1515,10 @@ int media_changed(struct cdrom_device_info *cdi, int queue) return ret; /* changed since last call? */ - if (cdi->ops->check_events) { - BUG_ON(!queue); /* shouldn't be called from VFS path */ - cdrom_update_events(cdi, DISK_EVENT_MEDIA_CHANGE); - changed = cdi->ioctl_events & DISK_EVENT_MEDIA_CHANGE; - cdi->ioctl_events = 0; - } else - changed = cdi->ops->media_changed(cdi, CDSL_CURRENT); + BUG_ON(!queue); /* shouldn't be called from VFS path */ + cdrom_update_events(cdi, DISK_EVENT_MEDIA_CHANGE); + changed = cdi->ioctl_events & DISK_EVENT_MEDIA_CHANGE; + cdi->ioctl_events = 0; if (changed) { cdi->mc_flags = 0x3; /* set bit on both queues */ @@ -1535,18 +1530,6 @@ int media_changed(struct cdrom_device_info *cdi, int queue) return ret; } -int cdrom_media_changed(struct cdrom_device_info *cdi) -{ - /* This talks to the VFS, which doesn't like errors - just 1 or 0. - * Returning "0" is always safe (media hasn't been changed). Do that - * if the low-level cdrom driver dosn't support media changed. */ - if (cdi == NULL || cdi->ops->media_changed == NULL) - return 0; - if (!CDROM_CAN(CDC_MEDIA_CHANGED)) - return 0; - return media_changed(cdi, 0); -} - /* Requests to the low-level drivers will /always/ be done in the following format convention: @@ -3464,7 +3447,6 @@ EXPORT_SYMBOL(unregister_cdrom); EXPORT_SYMBOL(cdrom_open); EXPORT_SYMBOL(cdrom_release); EXPORT_SYMBOL(cdrom_ioctl); -EXPORT_SYMBOL(cdrom_media_changed); EXPORT_SYMBOL(cdrom_number_of_slots); EXPORT_SYMBOL(cdrom_mode_select); EXPORT_SYMBOL(cdrom_mode_sense); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 8e32345be0f7..f50828526331 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -59,7 +59,7 @@ EXPORT_SYMBOL(bdev_dax_pgoff); #if IS_ENABLED(CONFIG_FS_DAX) struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) { - if (!blk_queue_dax(bdev->bd_queue)) + if (!blk_queue_dax(bdev->bd_disk->queue)) return NULL; return dax_get_by_host(bdev->bd_disk->disk_name); } diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index db38a68abb6c..fe78bf0fdce5 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -236,10 +236,6 @@ err_dev: return tgt_dev; } -static const struct block_device_operations nvm_fops = { - .owner = THIS_MODULE, -}; - static struct nvm_tgt_type *__nvm_find_target_type(const char *name) { struct nvm_tgt_type *tt; @@ -380,7 +376,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) goto err_dev; } - tqueue = blk_alloc_queue(tt->make_rq, dev->q->node); + tqueue = blk_alloc_queue(dev->q->node); if (!tqueue) { ret = -ENOMEM; goto err_disk; @@ -390,7 +386,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) tdisk->flags = GENHD_FL_EXT_DEVT; tdisk->major = 0; tdisk->first_minor = 0; - tdisk->fops = &nvm_fops; + tdisk->fops = tt->bops; tdisk->queue = tqueue; targetdata = tt->init(tgt_dev, tdisk, create->flags); diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c index 6e677ff62cc9..b6246f73895c 100644 --- a/drivers/lightnvm/pblk-init.c +++ b/drivers/lightnvm/pblk-init.c @@ -47,9 +47,9 @@ static struct pblk_global_caches pblk_caches = { struct bio_set pblk_bio_set; -static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio) +static blk_qc_t pblk_submit_bio(struct bio *bio) { - struct pblk *pblk = q->queuedata; + struct pblk *pblk = bio->bi_disk->queue->queuedata; if (bio_op(bio) == REQ_OP_DISCARD) { pblk_discard(pblk, bio); @@ -63,7 +63,7 @@ static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio) * constraint. Writes can be of arbitrary size. */ if (bio_data_dir(bio) == READ) { - blk_queue_split(q, &bio); + blk_queue_split(&bio); pblk_submit_read(pblk, bio); } else { /* Prevent deadlock in the case of a modest LUN configuration @@ -71,7 +71,7 @@ static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio) * leaves at least 256KB available for user I/O. */ if (pblk_get_secs(bio) > pblk_rl_max_io(&pblk->rl)) - blk_queue_split(q, &bio); + blk_queue_split(&bio); pblk_write_to_cache(pblk, bio, PBLK_IOTYPE_USER); } @@ -79,6 +79,12 @@ static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio) return BLK_QC_T_NONE; } +static const struct block_device_operations pblk_bops = { + .owner = THIS_MODULE, + .submit_bio = pblk_submit_bio, +}; + + static size_t pblk_trans_map_size(struct pblk *pblk) { int entry_size = 8; @@ -1280,7 +1286,7 @@ static struct nvm_tgt_type tt_pblk = { .name = "pblk", .version = {1, 0, 0}, - .make_rq = pblk_make_rq, + .bops = &pblk_bops, .capacity = pblk_capacity, .init = pblk_init, diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c index 140927ebf41e..c28537a489bc 100644 --- a/drivers/lightnvm/pblk-read.c +++ b/drivers/lightnvm/pblk-read.c @@ -320,7 +320,7 @@ split_retry: split_bio = bio_split(bio, nr_secs * NR_PHY_IN_LOG, GFP_KERNEL, &pblk_bio_set); bio_chain(split_bio, bio); - generic_make_request(bio); + submit_bio_noacct(bio); /* New bio contains first N sectors of the previous one, so * we can continue to use existing rqd, but we need to shrink diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 221e0191b687..3c708e8b5e2d 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -929,7 +929,7 @@ static inline void closure_bio_submit(struct cache_set *c, bio_endio(bio); return; } - generic_make_request(bio); + submit_bio_noacct(bio); } /* diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 6548a601edf0..d5c51e332046 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -959,7 +959,7 @@ err: * bch_btree_node_get - find a btree node in the cache and lock it, reading it * in from disk if necessary. * - * If IO is necessary and running under generic_make_request, returns -EAGAIN. + * If IO is necessary and running under submit_bio_noacct, returns -EAGAIN. * * The btree node will have either a read or a write lock held, depending on * level and op->lock. diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 7acf024e99f3..a190bf47076d 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1115,7 +1115,7 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio) !blk_queue_discard(bdev_get_queue(dc->bdev))) bio->bi_end_io(bio); else - generic_make_request(bio); + submit_bio_noacct(bio); } static void quit_max_writeback_rate(struct cache_set *c, @@ -1158,7 +1158,7 @@ static void quit_max_writeback_rate(struct cache_set *c, /* Cached devices - read & write stuff */ -blk_qc_t cached_dev_make_request(struct request_queue *q, struct bio *bio) +blk_qc_t cached_dev_submit_bio(struct bio *bio) { struct search *s; struct bcache_device *d = bio->bi_disk->private_data; @@ -1197,7 +1197,7 @@ blk_qc_t cached_dev_make_request(struct request_queue *q, struct bio *bio) if (!bio->bi_iter.bi_size) { /* * can't call bch_journal_meta from under - * generic_make_request + * submit_bio_noacct */ continue_at_nobarrier(&s->cl, cached_dev_nodata, @@ -1228,36 +1228,8 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); } -static int cached_dev_congested(void *data, int bits) -{ - struct bcache_device *d = data; - struct cached_dev *dc = container_of(d, struct cached_dev, disk); - struct request_queue *q = bdev_get_queue(dc->bdev); - int ret = 0; - - if (bdi_congested(q->backing_dev_info, bits)) - return 1; - - if (cached_dev_get(dc)) { - unsigned int i; - struct cache *ca; - - for_each_cache(ca, d->c, i) { - q = bdev_get_queue(ca->bdev); - ret |= bdi_congested(q->backing_dev_info, bits); - } - - cached_dev_put(dc); - } - - return ret; -} - void bch_cached_dev_request_init(struct cached_dev *dc) { - struct gendisk *g = dc->disk.disk; - - g->queue->backing_dev_info->congested_fn = cached_dev_congested; dc->disk.cache_miss = cached_dev_cache_miss; dc->disk.ioctl = cached_dev_ioctl; } @@ -1291,7 +1263,7 @@ static void flash_dev_nodata(struct closure *cl) continue_at(cl, search_free, NULL); } -blk_qc_t flash_dev_make_request(struct request_queue *q, struct bio *bio) +blk_qc_t flash_dev_submit_bio(struct bio *bio) { struct search *s; struct closure *cl; @@ -1311,8 +1283,7 @@ blk_qc_t flash_dev_make_request(struct request_queue *q, struct bio *bio) if (!bio->bi_iter.bi_size) { /* - * can't call bch_journal_meta from under - * generic_make_request + * can't call bch_journal_meta from under submit_bio_noacct */ continue_at_nobarrier(&s->cl, flash_dev_nodata, @@ -1342,27 +1313,8 @@ static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode, return -ENOTTY; } -static int flash_dev_congested(void *data, int bits) -{ - struct bcache_device *d = data; - struct request_queue *q; - struct cache *ca; - unsigned int i; - int ret = 0; - - for_each_cache(ca, d->c, i) { - q = bdev_get_queue(ca->bdev); - ret |= bdi_congested(q->backing_dev_info, bits); - } - - return ret; -} - void bch_flash_dev_request_init(struct bcache_device *d) { - struct gendisk *g = d->disk; - - g->queue->backing_dev_info->congested_fn = flash_dev_congested; d->cache_miss = flash_dev_cache_miss; d->ioctl = flash_dev_ioctl; } diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index bb005c93dd72..82b38366a95d 100644 --- a/drivers/md/bcache/request.h +++ b/drivers/md/bcache/request.h @@ -37,10 +37,10 @@ unsigned int bch_get_congested(const struct cache_set *c); void bch_data_insert(struct closure *cl); void bch_cached_dev_request_init(struct cached_dev *dc); -blk_qc_t cached_dev_make_request(struct request_queue *q, struct bio *bio); +blk_qc_t cached_dev_submit_bio(struct bio *bio); void bch_flash_dev_request_init(struct bcache_device *d); -blk_qc_t flash_dev_make_request(struct request_queue *q, struct bio *bio); +blk_qc_t flash_dev_submit_bio(struct bio *bio); extern struct kmem_cache *bch_search_cache; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 2014016f9a60..9e45faa054b6 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -680,7 +680,16 @@ static int ioctl_dev(struct block_device *b, fmode_t mode, return d->ioctl(d, mode, cmd, arg); } -static const struct block_device_operations bcache_ops = { +static const struct block_device_operations bcache_cached_ops = { + .submit_bio = cached_dev_submit_bio, + .open = open_dev, + .release = release_dev, + .ioctl = ioctl_dev, + .owner = THIS_MODULE, +}; + +static const struct block_device_operations bcache_flash_ops = { + .submit_bio = flash_dev_submit_bio, .open = open_dev, .release = release_dev, .ioctl = ioctl_dev, @@ -820,8 +829,8 @@ static void bcache_device_free(struct bcache_device *d) } static int bcache_device_init(struct bcache_device *d, unsigned int block_size, - sector_t sectors, make_request_fn make_request_fn, - struct block_device *cached_bdev) + sector_t sectors, struct block_device *cached_bdev, + const struct block_device_operations *ops) { struct request_queue *q; const size_t max_stripes = min_t(size_t, INT_MAX, @@ -868,16 +877,14 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, d->disk->major = bcache_major; d->disk->first_minor = idx_to_first_minor(idx); - d->disk->fops = &bcache_ops; + d->disk->fops = ops; d->disk->private_data = d; - q = blk_alloc_queue(make_request_fn, NUMA_NO_NODE); + q = blk_alloc_queue(NUMA_NO_NODE); if (!q) return -ENOMEM; d->disk->queue = q; - q->queuedata = d; - q->backing_dev_info->congested_data = d; q->limits.max_hw_sectors = UINT_MAX; q->limits.max_sectors = UINT_MAX; q->limits.max_segment_size = UINT_MAX; @@ -1356,7 +1363,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) ret = bcache_device_init(&dc->disk, block_size, dc->bdev->bd_part->nr_sects - dc->sb.data_offset, - cached_dev_make_request, dc->bdev); + dc->bdev, &bcache_cached_ops); if (ret) return ret; @@ -1469,7 +1476,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u) kobject_init(&d->kobj, &bch_flash_dev_ktype); if (bcache_device_init(d, block_bytes(c), u->sectors, - flash_dev_make_request, NULL)) + NULL, &bcache_flash_ops)) goto err; bcache_device_attach(d, c, u - c->uuids); diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index d3bb355819a4..96c93802ee4d 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -421,8 +421,6 @@ struct cache { struct rw_semaphore quiesce_lock; - struct dm_target_callbacks callbacks; - /* * origin_blocks entries, discarded if set. */ @@ -886,7 +884,7 @@ static void accounted_complete(struct cache *cache, struct bio *bio) static void accounted_request(struct cache *cache, struct bio *bio) { accounted_begin(cache, bio); - generic_make_request(bio); + submit_bio_noacct(bio); } static void issue_op(struct bio *bio, void *context) @@ -1792,7 +1790,7 @@ static bool process_bio(struct cache *cache, struct bio *bio) bool commit_needed; if (map_bio(cache, bio, get_bio_block(cache, bio), &commit_needed) == DM_MAPIO_REMAPPED) - generic_make_request(bio); + submit_bio_noacct(bio); return commit_needed; } @@ -1858,7 +1856,7 @@ static bool process_discard_bio(struct cache *cache, struct bio *bio) if (cache->features.discard_passdown) { remap_to_origin(cache, bio); - generic_make_request(bio); + submit_bio_noacct(bio); } else bio_endio(bio); @@ -2423,20 +2421,6 @@ static void set_cache_size(struct cache *cache, dm_cblock_t size) cache->cache_size = size; } -static int is_congested(struct dm_dev *dev, int bdi_bits) -{ - struct request_queue *q = bdev_get_queue(dev->bdev); - return bdi_congested(q->backing_dev_info, bdi_bits); -} - -static int cache_is_congested(struct dm_target_callbacks *cb, int bdi_bits) -{ - struct cache *cache = container_of(cb, struct cache, callbacks); - - return is_congested(cache->origin_dev, bdi_bits) || - is_congested(cache->cache_dev, bdi_bits); -} - #define DEFAULT_MIGRATION_THRESHOLD 2048 static int cache_create(struct cache_args *ca, struct cache **result) @@ -2471,9 +2455,6 @@ static int cache_create(struct cache_args *ca, struct cache **result) goto bad; } - cache->callbacks.congested_fn = cache_is_congested; - dm_table_add_target_callbacks(ti->table, &cache->callbacks); - cache->metadata_dev = ca->metadata_dev; cache->origin_dev = ca->origin_dev; cache->cache_dev = ca->cache_dev; diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 5ce96ddf1ce1..bdb255edc200 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -68,7 +68,6 @@ struct hash_table_bucket; struct clone { struct dm_target *ti; - struct dm_target_callbacks callbacks; struct dm_dev *metadata_dev; struct dm_dev *dest_dev; @@ -330,7 +329,7 @@ static void submit_bios(struct bio_list *bios) blk_start_plug(&plug); while ((bio = bio_list_pop(bios))) - generic_make_request(bio); + submit_bio_noacct(bio); blk_finish_plug(&plug); } @@ -346,7 +345,7 @@ static void submit_bios(struct bio_list *bios) static void issue_bio(struct clone *clone, struct bio *bio) { if (!bio_triggers_commit(clone, bio)) { - generic_make_request(bio); + submit_bio_noacct(bio); return; } @@ -473,7 +472,7 @@ static void complete_discard_bio(struct clone *clone, struct bio *bio, bool succ bio_region_range(clone, bio, &rs, &nr_regions); trim_bio(bio, region_to_sector(clone, rs), nr_regions << clone->region_shift); - generic_make_request(bio); + submit_bio_noacct(bio); } else bio_endio(bio); } @@ -865,7 +864,7 @@ static void hydration_overwrite(struct dm_clone_region_hydration *hd, struct bio bio->bi_private = hd; atomic_inc(&hd->clone->hydrations_in_flight); - generic_make_request(bio); + submit_bio_noacct(bio); } /* @@ -1281,7 +1280,7 @@ static void process_deferred_flush_bios(struct clone *clone) */ bio_endio(bio); } else { - generic_make_request(bio); + submit_bio_noacct(bio); } } } @@ -1518,18 +1517,6 @@ error: DMEMIT("Error"); } -static int clone_is_congested(struct dm_target_callbacks *cb, int bdi_bits) -{ - struct request_queue *dest_q, *source_q; - struct clone *clone = container_of(cb, struct clone, callbacks); - - source_q = bdev_get_queue(clone->source_dev->bdev); - dest_q = bdev_get_queue(clone->dest_dev->bdev); - - return (bdi_congested(dest_q->backing_dev_info, bdi_bits) | - bdi_congested(source_q->backing_dev_info, bdi_bits)); -} - static sector_t get_dev_size(struct dm_dev *dev) { return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT; @@ -1930,8 +1917,6 @@ static int clone_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto out_with_mempool; mutex_init(&clone->commit_lock); - clone->callbacks.congested_fn = clone_is_congested; - dm_table_add_target_callbacks(ti->table, &clone->callbacks); /* Enable flushes */ ti->num_flush_bios = 1; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 000ddfab5ba0..ad324abb8c49 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1789,7 +1789,7 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) return 1; } - generic_make_request(clone); + submit_bio_noacct(clone); return 0; } @@ -1815,7 +1815,7 @@ static void kcryptd_io_write(struct dm_crypt_io *io) { struct bio *clone = io->ctx.bio_out; - generic_make_request(clone); + submit_bio_noacct(clone); } #define crypt_io_from_node(node) rb_entry((node), struct dm_crypt_io, rb_node) @@ -1893,7 +1893,7 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async) clone->bi_iter.bi_sector = cc->start + io->sector; if (likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) { - generic_make_request(clone); + submit_bio_noacct(clone); return; } diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index f496213f8b67..2628a832787b 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -72,7 +72,7 @@ static void flush_bios(struct bio *bio) while (bio) { n = bio->bi_next; bio->bi_next = NULL; - generic_make_request(bio); + submit_bio_noacct(bio); bio = n; } } diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index bdb84b8e7162..b24e3839bb3a 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -1137,7 +1137,6 @@ static int metadata_get_stats(struct era_metadata *md, void *ptr) struct era { struct dm_target *ti; - struct dm_target_callbacks callbacks; struct dm_dev *metadata_dev; struct dm_dev *origin_dev; @@ -1265,7 +1264,7 @@ static void process_deferred_bios(struct era *era) bio_io_error(bio); else while ((bio = bio_list_pop(&marked_bios))) - generic_make_request(bio); + submit_bio_noacct(bio); } static void process_rpc_calls(struct era *era) @@ -1375,18 +1374,6 @@ static void stop_worker(struct era *era) /*---------------------------------------------------------------- * Target methods *--------------------------------------------------------------*/ -static int dev_is_congested(struct dm_dev *dev, int bdi_bits) -{ - struct request_queue *q = bdev_get_queue(dev->bdev); - return bdi_congested(q->backing_dev_info, bdi_bits); -} - -static int era_is_congested(struct dm_target_callbacks *cb, int bdi_bits) -{ - struct era *era = container_of(cb, struct era, callbacks); - return dev_is_congested(era->origin_dev, bdi_bits); -} - static void era_destroy(struct era *era) { if (era->md) @@ -1514,8 +1501,6 @@ static int era_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->flush_supported = true; ti->num_discard_bios = 1; - era->callbacks.congested_fn = era_is_congested; - dm_table_add_target_callbacks(ti->table, &era->callbacks); return 0; } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 81dc5ff08909..ae866e469e1b 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -2115,12 +2115,12 @@ offload_to_thread: dio->in_flight = (atomic_t)ATOMIC_INIT(1); dio->completion = NULL; - generic_make_request(bio); + submit_bio_noacct(bio); return; } - generic_make_request(bio); + submit_bio_noacct(bio); if (need_sync_io) { wait_for_completion_io(&read_comp); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 78cff42d987e..73bb23de6336 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -677,7 +677,7 @@ static void process_queued_bios(struct work_struct *work) bio_endio(bio); break; case DM_MAPIO_REMAPPED: - generic_make_request(bio); + submit_bio_noacct(bio); break; case DM_MAPIO_SUBMITTED: break; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 10e8b2fe787b..d9e270957e18 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -242,7 +242,6 @@ struct raid_set { struct mddev md; struct raid_type *raid_type; - struct dm_target_callbacks callbacks; sector_t array_sectors; sector_t dev_sectors; @@ -1705,13 +1704,6 @@ static void do_table_event(struct work_struct *ws) dm_table_event(rs->ti->table); } -static int raid_is_congested(struct dm_target_callbacks *cb, int bits) -{ - struct raid_set *rs = container_of(cb, struct raid_set, callbacks); - - return mddev_congested(&rs->md, bits); -} - /* * Make sure a valid takover (level switch) is being requested on @rs * @@ -3248,9 +3240,6 @@ size_check: goto bad_md_start; } - rs->callbacks.congested_fn = raid_is_congested; - dm_table_add_target_callbacks(ti->table, &rs->callbacks); - /* If raid4/5/6 journal mode explicitly requested (only possible with journal dev) -> set it */ if (test_bit(__CTR_FLAG_JOURNAL_MODE, &rs->ctr_flags)) { r = r5c_journal_mode_set(&rs->md, rs->journal_dev.mode); @@ -3310,7 +3299,6 @@ static void raid_dtr(struct dm_target *ti) { struct raid_set *rs = ti->private; - list_del_init(&rs->callbacks.list); md_stop(&rs->md); raid_set_free(rs); } diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 2f655d9f4200..fa09bc4e4c54 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -779,7 +779,7 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes) wakeup_mirrord(ms); } else { map_bio(get_default_mirror(ms), bio); - generic_make_request(bio); + submit_bio_noacct(bio); } } } diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 85e0daabad49..7ce387a1cc6a 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -284,7 +284,8 @@ static void dm_complete_request(struct request *rq, blk_status_t error) struct dm_rq_target_io *tio = tio_from_request(rq); tio->error = error; - blk_mq_complete_request(rq); + if (likely(!blk_should_fake_timeout(rq->q))) + blk_mq_complete_request(rq); } /* diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 963d3774c93e..2d1d4a4c399c 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -252,7 +252,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int op, /* * Issue the synchronous I/O from a different thread - * to avoid generic_make_request recursion. + * to avoid submit_bio_noacct recursion. */ INIT_WORK_ONSTACK(&req.work, do_metadata); queue_work(ps->metadata_wq, &req.work); diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 6b11a266299f..4668b2cd98f4 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1568,7 +1568,7 @@ static void flush_bios(struct bio *bio) while (bio) { n = bio->bi_next; bio->bi_next = NULL; - generic_make_request(bio); + submit_bio_noacct(bio); bio = n; } } @@ -1588,7 +1588,7 @@ static void retry_origin_bios(struct dm_snapshot *s, struct bio *bio) bio->bi_next = NULL; r = do_origin(s->origin, bio, false); if (r == DM_MAPIO_REMAPPED) - generic_make_request(bio); + submit_bio_noacct(bio); bio = n; } } @@ -1829,7 +1829,7 @@ static void start_full_bio(struct dm_snap_pending_exception *pe, bio->bi_end_io = full_bio_end_io; bio->bi_private = callback_data; - generic_make_request(bio); + submit_bio_noacct(bio); } static struct dm_snap_pending_exception * diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 8277b959e00b..0ea5b7367179 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -64,8 +64,6 @@ struct dm_table { void *event_context; struct dm_md_mempools *mempools; - - struct list_head target_callbacks; }; /* @@ -190,7 +188,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode, return -ENOMEM; INIT_LIST_HEAD(&t->devices); - INIT_LIST_HEAD(&t->target_callbacks); if (!num_targets) num_targets = KEYS_PER_NODE; @@ -361,7 +358,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, * This upgrades the mode on an already open dm_dev, being * careful to leave things as they were if we fail to reopen the * device and not to touch the existing bdev field in case - * it is accessed concurrently inside dm_table_any_congested(). + * it is accessed concurrently. */ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, struct mapped_device *md) @@ -2052,38 +2049,6 @@ int dm_table_resume_targets(struct dm_table *t) return 0; } -void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb) -{ - list_add(&cb->list, &t->target_callbacks); -} -EXPORT_SYMBOL_GPL(dm_table_add_target_callbacks); - -int dm_table_any_congested(struct dm_table *t, int bdi_bits) -{ - struct dm_dev_internal *dd; - struct list_head *devices = dm_table_get_devices(t); - struct dm_target_callbacks *cb; - int r = 0; - - list_for_each_entry(dd, devices, list) { - struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev); - char b[BDEVNAME_SIZE]; - - if (likely(q)) - r |= bdi_congested(q->backing_dev_info, bdi_bits); - else - DMWARN_LIMIT("%s: any_congested: nonexistent device %s", - dm_device_name(t->md), - bdevname(dd->dm_dev->bdev, b)); - } - - list_for_each_entry(cb, &t->target_callbacks, list) - if (cb->congested_fn) - r |= cb->congested_fn(cb, bdi_bits); - - return r; -} - struct mapped_device *dm_table_get_md(struct dm_table *t) { return t->md; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index fa8d5464c1fb..fff4c50df74d 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -326,7 +326,6 @@ struct pool_c { struct pool *pool; struct dm_dev *data_dev; struct dm_dev *metadata_dev; - struct dm_target_callbacks callbacks; dm_block_t low_water_blocks; struct pool_features requested_pf; /* Features requested during table load */ @@ -758,7 +757,7 @@ static void issue(struct thin_c *tc, struct bio *bio) struct pool *pool = tc->pool; if (!bio_triggers_commit(tc, bio)) { - generic_make_request(bio); + submit_bio_noacct(bio); return; } @@ -2394,7 +2393,7 @@ static void process_deferred_bios(struct pool *pool) if (bio->bi_opf & REQ_PREFLUSH) bio_endio(bio); else - generic_make_request(bio); + submit_bio_noacct(bio); } } @@ -2796,18 +2795,6 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) } } -static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits) -{ - struct pool_c *pt = container_of(cb, struct pool_c, callbacks); - struct request_queue *q; - - if (get_pool_mode(pt->pool) == PM_OUT_OF_DATA_SPACE) - return 1; - - q = bdev_get_queue(pt->data_dev->bdev); - return bdi_congested(q->backing_dev_info, bdi_bits); -} - static void requeue_bios(struct pool *pool) { struct thin_c *tc; @@ -3420,9 +3407,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) dm_pool_register_pre_commit_callback(pool->pmd, metadata_pre_commit_callback, pool); - pt->callbacks.congested_fn = pool_is_congested; - dm_table_add_target_callbacks(ti->table, &pt->callbacks); - mutex_unlock(&dm_thin_pool_table.mutex); return 0; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index eec9f252e935..75fa4d9b7617 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -681,7 +681,7 @@ static int verity_map(struct dm_target *ti, struct bio *bio) verity_submit_prefetch(v, io); - generic_make_request(bio); + submit_bio_noacct(bio); return DM_MAPIO_SUBMITTED; } diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 5358894bb9fd..8aa306ebc2ab 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -1244,7 +1244,7 @@ static int writecache_flush_thread(void *data) bio_end_sector(bio)); wc_unlock(wc); bio_set_dev(bio, wc->dev->bdev); - generic_make_request(bio); + submit_bio_noacct(bio); } else { writecache_flush(wc); wc_unlock(wc); diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 42aa5139df7c..697f9de37355 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -140,7 +140,7 @@ static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone, bio_advance(bio, clone->bi_iter.bi_size); refcount_inc(&bioctx->ref); - generic_make_request(clone); + submit_bio_noacct(clone); if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone)) zone->wp_block += nr_blocks; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 52449afd58eb..b2b07d954547 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1272,7 +1272,6 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) sector_t sector; struct bio *clone = &tio->clone; struct dm_io *io = tio->io; - struct mapped_device *md = io->md; struct dm_target *ti = tio->ti; blk_qc_t ret = BLK_QC_T_NONE; @@ -1294,10 +1293,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) /* the bio has been remapped so dispatch it */ trace_block_bio_remap(clone->bi_disk->queue, clone, bio_dev(io->orig_bio), sector); - if (md->type == DM_TYPE_NVME_BIO_BASED) - ret = direct_make_request(clone); - else - ret = generic_make_request(clone); + ret = submit_bio_noacct(clone); break; case DM_MAPIO_KILL: free_tio(tio); @@ -1644,7 +1640,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, error = __split_and_process_non_flush(&ci); if (current->bio_list && ci.sector_count && !error) { /* - * Remainder must be passed to generic_make_request() + * Remainder must be passed to submit_bio_noacct() * so that it gets handled *after* bios already submitted * have been completely processed. * We take a clone of the original to store in @@ -1669,7 +1665,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, bio_chain(b, bio); trace_block_split(md->queue, b, bio->bi_iter.bi_sector); - ret = generic_make_request(bio); + ret = submit_bio_noacct(bio); break; } } @@ -1737,7 +1733,7 @@ static void dm_queue_split(struct mapped_device *md, struct dm_target *ti, struc bio_chain(split, *bio); trace_block_split(md->queue, split, (*bio)->bi_iter.bi_sector); - generic_make_request(*bio); + submit_bio_noacct(*bio); *bio = split; } } @@ -1762,13 +1758,13 @@ static blk_qc_t dm_process_bio(struct mapped_device *md, } /* - * If in ->make_request_fn we need to use blk_queue_split(), otherwise + * If in ->queue_bio we need to use blk_queue_split(), otherwise * queue_limits for abnormal requests (e.g. discard, writesame, etc) * won't be imposed. */ if (current->bio_list) { if (is_abnormal_io(bio)) - blk_queue_split(md->queue, &bio); + blk_queue_split(&bio); else dm_queue_split(md, ti, &bio); } @@ -1779,9 +1775,9 @@ static blk_qc_t dm_process_bio(struct mapped_device *md, return __split_and_process_bio(md, map, bio); } -static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t dm_submit_bio(struct bio *bio) { - struct mapped_device *md = q->queuedata; + struct mapped_device *md = bio->bi_disk->private_data; blk_qc_t ret = BLK_QC_T_NONE; int srcu_idx; struct dm_table *map; @@ -1790,12 +1786,12 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio) /* * We are called with a live reference on q_usage_counter, but * that one will be released as soon as we return. Grab an - * extra one as blk_mq_make_request expects to be able to - * consume a reference (which lives until the request is freed - * in case a request is allocated). + * extra one as blk_mq_submit_bio expects to be able to consume + * a reference (which lives until the request is freed in case a + * request is allocated). */ - percpu_ref_get(&q->q_usage_counter); - return blk_mq_make_request(q, bio); + percpu_ref_get(&bio->bi_disk->queue->q_usage_counter); + return blk_mq_submit_bio(bio); } map = dm_get_live_table(md, &srcu_idx); @@ -1817,31 +1813,6 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio) return ret; } -static int dm_any_congested(void *congested_data, int bdi_bits) -{ - int r = bdi_bits; - struct mapped_device *md = congested_data; - struct dm_table *map; - - if (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) { - if (dm_request_based(md)) { - /* - * With request-based DM we only need to check the - * top-level queue for congestion. - */ - struct backing_dev_info *bdi = md->queue->backing_dev_info; - r = bdi->wb.congested->state & bdi_bits; - } else { - map = dm_get_live_table_fast(md); - if (map) - r = dm_table_any_congested(map, bdi_bits); - dm_put_live_table_fast(md); - } - } - - return r; -} - /*----------------------------------------------------------------- * An IDR is used to keep track of allocated minor numbers. *---------------------------------------------------------------*/ @@ -1980,14 +1951,13 @@ static struct mapped_device *alloc_dev(int minor) spin_lock_init(&md->uevent_lock); /* - * default to bio-based required ->make_request_fn until DM - * table is loaded and md->type established. If request-based - * table is loaded: blk-mq will override accordingly. + * default to bio-based until DM table is loaded and md->type + * established. If request-based table is loaded: blk-mq will + * override accordingly. */ - md->queue = blk_alloc_queue(dm_make_request, numa_node_id); + md->queue = blk_alloc_queue(numa_node_id); if (!md->queue) goto bad; - md->queue->queuedata = md; md->disk = alloc_disk_node(1, md->numa_node_id); if (!md->disk) @@ -2281,12 +2251,6 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md) } EXPORT_SYMBOL_GPL(dm_get_queue_limits); -static void dm_init_congested_fn(struct mapped_device *md) -{ - md->queue->backing_dev_info->congested_data = md; - md->queue->backing_dev_info->congested_fn = dm_any_congested; -} - /* * Setup the DM device's queue based on md's type */ @@ -2303,12 +2267,10 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t) DMERR("Cannot initialize queue for request-based dm-mq mapped device"); return r; } - dm_init_congested_fn(md); break; case DM_TYPE_BIO_BASED: case DM_TYPE_DAX_BIO_BASED: case DM_TYPE_NVME_BIO_BASED: - dm_init_congested_fn(md); break; case DM_TYPE_NONE: WARN_ON_ONCE(true); @@ -2529,7 +2491,7 @@ static void dm_wq_work(struct work_struct *work) break; if (dm_request_based(md)) - (void) generic_make_request(c); + (void) submit_bio_noacct(c); else (void) dm_process_bio(md, map, c); } @@ -3269,6 +3231,7 @@ static const struct pr_ops dm_pr_ops = { }; static const struct block_device_operations dm_blk_dops = { + .submit_bio = dm_submit_bio, .open = dm_blk_open, .release = dm_blk_close, .ioctl = dm_blk_ioctl, diff --git a/drivers/md/dm.h b/drivers/md/dm.h index d7c4f6606b5f..4f5fe664d05a 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -63,7 +63,6 @@ void dm_table_presuspend_targets(struct dm_table *t); void dm_table_presuspend_undo_targets(struct dm_table *t); void dm_table_postsuspend_targets(struct dm_table *t); int dm_table_resume_targets(struct dm_table *t); -int dm_table_any_congested(struct dm_table *t, int bdi_bits); enum dm_queue_mode dm_table_get_type(struct dm_table *t); struct target_type *dm_table_get_immutable_target_type(struct dm_table *t); struct dm_target *dm_table_get_immutable_target(struct dm_table *t); diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c index 50ad4ba86f0e..fda4cb3f936f 100644 --- a/drivers/md/md-faulty.c +++ b/drivers/md/md-faulty.c @@ -169,7 +169,7 @@ static bool faulty_make_request(struct mddev *mddev, struct bio *bio) if (bio_data_dir(bio) == WRITE) { /* write request */ if (atomic_read(&conf->counters[WriteAll])) { - /* special case - don't decrement, don't generic_make_request, + /* special case - don't decrement, don't submit_bio_noacct, * just fail immediately */ bio_io_error(bio); @@ -214,7 +214,7 @@ static bool faulty_make_request(struct mddev *mddev, struct bio *bio) } else bio_set_dev(bio, conf->rdev->bdev); - generic_make_request(bio); + submit_bio_noacct(bio); return true; } diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 26c75c0199fa..c2ae9125c4c3 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -46,29 +46,6 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector) return conf->disks + lo; } -/* - * In linear_congested() conf->raid_disks is used as a copy of - * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks - * and conf->disks[] are created in linear_conf(), they are always - * consitent with each other, but mddev->raid_disks does not. - */ -static int linear_congested(struct mddev *mddev, int bits) -{ - struct linear_conf *conf; - int i, ret = 0; - - rcu_read_lock(); - conf = rcu_dereference(mddev->private); - - for (i = 0; i < conf->raid_disks && !ret ; i++) { - struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev); - ret |= bdi_congested(q->backing_dev_info, bits); - } - - rcu_read_unlock(); - return ret; -} - static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks) { struct linear_conf *conf; @@ -267,7 +244,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) struct bio *split = bio_split(bio, end_sector - bio_sector, GFP_NOIO, &mddev->bio_set); bio_chain(split, bio); - generic_make_request(bio); + submit_bio_noacct(bio); bio = split; } @@ -286,7 +263,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) bio_sector); mddev_check_writesame(mddev, bio); mddev_check_write_zeroes(mddev, bio); - generic_make_request(bio); + submit_bio_noacct(bio); } return true; @@ -322,7 +299,6 @@ static struct md_personality linear_personality = .hot_add_disk = linear_add, .size = linear_size, .quiesce = linear_quiesce, - .congested = linear_congested, }; static int __init linear_init (void) diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index 152f9e65a226..776bbe542db5 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -131,7 +131,7 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio) mp_bh->bio.bi_private = mp_bh; mddev_check_writesame(mddev, &mp_bh->bio); mddev_check_write_zeroes(mddev, &mp_bh->bio); - generic_make_request(&mp_bh->bio); + submit_bio_noacct(&mp_bh->bio); return true; } @@ -151,28 +151,6 @@ static void multipath_status(struct seq_file *seq, struct mddev *mddev) seq_putc(seq, ']'); } -static int multipath_congested(struct mddev *mddev, int bits) -{ - struct mpconf *conf = mddev->private; - int i, ret = 0; - - rcu_read_lock(); - for (i = 0; i < mddev->raid_disks ; i++) { - struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags)) { - struct request_queue *q = bdev_get_queue(rdev->bdev); - - ret |= bdi_congested(q->backing_dev_info, bits); - /* Just like multipath_map, we just check the - * first available device - */ - break; - } - } - rcu_read_unlock(); - return ret; -} - /* * Careful, this can execute in IRQ contexts as well! */ @@ -348,7 +326,7 @@ static void multipathd(struct md_thread *thread) bio->bi_opf |= REQ_FAILFAST_TRANSPORT; bio->bi_end_io = multipath_end_request; bio->bi_private = mp_bh; - generic_make_request(bio); + submit_bio_noacct(bio); } } spin_unlock_irqrestore(&conf->device_lock, flags); @@ -478,7 +456,6 @@ static struct md_personality multipath_personality = .hot_add_disk = multipath_add_disk, .hot_remove_disk= multipath_remove_disk, .size = multipath_size, - .congested = multipath_congested, }; static int __init multipath_init (void) diff --git a/drivers/md/md.c b/drivers/md/md.c index f567f536b529..96b28f6d025c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -199,7 +199,7 @@ static int rdevs_init_serial(struct mddev *mddev) static int rdev_need_serial(struct md_rdev *rdev) { return (rdev && rdev->mddev->bitmap_info.max_write_behind > 0 && - rdev->bdev->bd_queue->nr_hw_queues != 1 && + rdev->bdev->bd_disk->queue->nr_hw_queues != 1 && test_bit(WriteMostly, &rdev->flags)); } @@ -463,7 +463,7 @@ check_suspended: } EXPORT_SYMBOL(md_handle_request); -static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t md_submit_bio(struct bio *bio) { const int rw = bio_data_dir(bio); const int sgrp = op_stat_group(bio_op(bio)); @@ -475,7 +475,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) return BLK_QC_T_NONE; } - blk_queue_split(q, &bio); + blk_queue_split(&bio); if (mddev == NULL || mddev->pers == NULL) { bio_io_error(bio); @@ -549,26 +549,6 @@ void mddev_resume(struct mddev *mddev) } EXPORT_SYMBOL_GPL(mddev_resume); -int mddev_congested(struct mddev *mddev, int bits) -{ - struct md_personality *pers = mddev->pers; - int ret = 0; - - rcu_read_lock(); - if (mddev->suspended) - ret = 1; - else if (pers && pers->congested) - ret = pers->congested(mddev, bits); - rcu_read_unlock(); - return ret; -} -EXPORT_SYMBOL_GPL(mddev_congested); -static int md_congested(void *data, int bits) -{ - struct mddev *mddev = data; - return mddev_congested(mddev, bits); -} - /* * Generic flush handling for md */ @@ -5641,7 +5621,7 @@ static int md_alloc(dev_t dev, char *name) mddev->hold_active = UNTIL_STOP; error = -ENOMEM; - mddev->queue = blk_alloc_queue(md_make_request, NUMA_NO_NODE); + mddev->queue = blk_alloc_queue(NUMA_NO_NODE); if (!mddev->queue) goto abort; @@ -5670,6 +5650,7 @@ static int md_alloc(dev_t dev, char *name) * remove it now. */ disk->flags |= GENHD_FL_EXT_DEVT; + disk->events |= DISK_EVENT_MEDIA_CHANGE; mddev->gendisk = disk; /* As soon as we call add_disk(), another thread could get * through to md_open, so make sure it doesn't get too far @@ -5964,8 +5945,6 @@ int md_run(struct mddev *mddev) blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue); else blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue); - mddev->queue->backing_dev_info->congested_data = mddev; - mddev->queue->backing_dev_info->congested_fn = md_congested; } if (pers->sync_request) { if (mddev->kobj.sd && @@ -6350,7 +6329,6 @@ static int do_md_stop(struct mddev *mddev, int mode, __md_stop_writes(mddev); __md_stop(mddev); - mddev->queue->backing_dev_info->congested_fn = NULL; /* tell userspace to handle 'inactive' */ sysfs_notify_dirent_safe(mddev->sysfs_state); @@ -7806,23 +7784,21 @@ static void md_release(struct gendisk *disk, fmode_t mode) mddev_put(mddev); } -static int md_media_changed(struct gendisk *disk) -{ - struct mddev *mddev = disk->private_data; - - return mddev->changed; -} - -static int md_revalidate(struct gendisk *disk) +static unsigned int md_check_events(struct gendisk *disk, unsigned int clearing) { struct mddev *mddev = disk->private_data; + unsigned int ret = 0; + if (mddev->changed) + ret = DISK_EVENT_MEDIA_CHANGE; mddev->changed = 0; - return 0; + return ret; } + static const struct block_device_operations md_fops = { .owner = THIS_MODULE, + .submit_bio = md_submit_bio, .open = md_open, .release = md_release, .ioctl = md_ioctl, @@ -7830,8 +7806,7 @@ static const struct block_device_operations md_fops = .compat_ioctl = md_compat_ioctl, #endif .getgeo = md_getgeo, - .media_changed = md_media_changed, - .revalidate_disk= md_revalidate, + .check_events = md_check_events, }; static int md_thread(void *arg) diff --git a/drivers/md/md.h b/drivers/md/md.h index 612814d07d35..e2f1ad9afc48 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -597,9 +597,6 @@ struct md_personality * array. */ void *(*takeover) (struct mddev *mddev); - /* congested implements bdi.congested_fn(). - * Will not be called while array is 'suspended' */ - int (*congested)(struct mddev *mddev, int bits); /* Changes the consistency policy of an active array. */ int (*change_consistency_policy)(struct mddev *mddev, const char *buf); }; @@ -710,7 +707,6 @@ extern void md_done_sync(struct mddev *mddev, int blocks, int ok); extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); -extern int mddev_congested(struct mddev *mddev, int bits); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 322386ff5d22..f54a449f97aa 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -29,21 +29,6 @@ module_param(default_layout, int, 0644); (1L << MD_HAS_PPL) | \ (1L << MD_HAS_MULTIPLE_PPLS)) -static int raid0_congested(struct mddev *mddev, int bits) -{ - struct r0conf *conf = mddev->private; - struct md_rdev **devlist = conf->devlist; - int raid_disks = conf->strip_zone[0].nb_dev; - int i, ret = 0; - - for (i = 0; i < raid_disks && !ret ; i++) { - struct request_queue *q = bdev_get_queue(devlist[i]->bdev); - - ret |= bdi_congested(q->backing_dev_info, bits); - } - return ret; -} - /* * inform the user of the raid configuration */ @@ -495,7 +480,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO, &mddev->bio_set); bio_chain(split, bio); - generic_make_request(bio); + submit_bio_noacct(bio); bio = split; end = zone->zone_end; } else @@ -559,7 +544,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) trace_block_bio_remap(bdev_get_queue(rdev->bdev), discard_bio, disk_devt(mddev->gendisk), bio->bi_iter.bi_sector); - generic_make_request(discard_bio); + submit_bio_noacct(discard_bio); } bio_endio(bio); } @@ -600,7 +585,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) struct bio *split = bio_split(bio, sectors, GFP_NOIO, &mddev->bio_set); bio_chain(split, bio); - generic_make_request(bio); + submit_bio_noacct(bio); bio = split; } @@ -633,7 +618,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) disk_devt(mddev->gendisk), bio_sector); mddev_check_writesame(mddev, bio); mddev_check_write_zeroes(mddev, bio); - generic_make_request(bio); + submit_bio_noacct(bio); return true; } @@ -818,7 +803,6 @@ static struct md_personality raid0_personality= .size = raid0_size, .takeover = raid0_takeover, .quiesce = raid0_quiesce, - .congested = raid0_congested, }; static int __init raid0_init (void) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index dcd27f3da84e..960d854c07f8 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -786,36 +786,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect return best_disk; } -static int raid1_congested(struct mddev *mddev, int bits) -{ - struct r1conf *conf = mddev->private; - int i, ret = 0; - - if ((bits & (1 << WB_async_congested)) && - conf->pending_count >= max_queued_requests) - return 1; - - rcu_read_lock(); - for (i = 0; i < conf->raid_disks * 2; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags)) { - struct request_queue *q = bdev_get_queue(rdev->bdev); - - BUG_ON(!q); - - /* Note the '|| 1' - when read_balance prefers - * non-congested targets, it can be removed - */ - if ((bits & (1 << WB_async_congested)) || 1) - ret |= bdi_congested(q->backing_dev_info, bits); - else - ret &= bdi_congested(q->backing_dev_info, bits); - } - } - rcu_read_unlock(); - return ret; -} - static void flush_bio_list(struct r1conf *conf, struct bio *bio) { /* flush any pending bitmap writes to disk before proceeding w/ I/O */ @@ -834,7 +804,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio) /* Just ignore it */ bio_endio(bio); else - generic_make_request(bio); + submit_bio_noacct(bio); bio = next; cond_resched(); } @@ -1312,7 +1282,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, struct bio *split = bio_split(bio, max_sectors, gfp, &conf->bio_split); bio_chain(split, bio); - generic_make_request(bio); + submit_bio_noacct(bio); bio = split; r1_bio->master_bio = bio; r1_bio->sectors = max_sectors; @@ -1338,7 +1308,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, trace_block_bio_remap(read_bio->bi_disk->queue, read_bio, disk_devt(mddev->gendisk), r1_bio->sector); - generic_make_request(read_bio); + submit_bio_noacct(read_bio); } static void raid1_write_request(struct mddev *mddev, struct bio *bio, @@ -1483,7 +1453,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, struct bio *split = bio_split(bio, max_sectors, GFP_NOIO, &conf->bio_split); bio_chain(split, bio); - generic_make_request(bio); + submit_bio_noacct(bio); bio = split; r1_bio->master_bio = bio; r1_bio->sectors = max_sectors; @@ -2240,7 +2210,7 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) atomic_inc(&r1_bio->remaining); md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio)); - generic_make_request(wbio); + submit_bio_noacct(wbio); } put_sync_write_buf(r1_bio, 1); @@ -2926,7 +2896,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, md_sync_acct_bio(bio, nr_sectors); if (read_targets == 1) bio->bi_opf &= ~MD_FAILFAST; - generic_make_request(bio); + submit_bio_noacct(bio); } } } else { @@ -2935,7 +2905,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, md_sync_acct_bio(bio, nr_sectors); if (read_targets == 1) bio->bi_opf &= ~MD_FAILFAST; - generic_make_request(bio); + submit_bio_noacct(bio); } return nr_sectors; } @@ -3396,7 +3366,6 @@ static struct md_personality raid1_personality = .check_reshape = raid1_reshape, .quiesce = raid1_quiesce, .takeover = raid1_takeover, - .congested = raid1_congested, }; static int __init raid_init(void) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index ec136e44aef7..353288bc4cb7 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -848,31 +848,6 @@ static struct md_rdev *read_balance(struct r10conf *conf, return rdev; } -static int raid10_congested(struct mddev *mddev, int bits) -{ - struct r10conf *conf = mddev->private; - int i, ret = 0; - - if ((bits & (1 << WB_async_congested)) && - conf->pending_count >= max_queued_requests) - return 1; - - rcu_read_lock(); - for (i = 0; - (i < conf->geo.raid_disks || i < conf->prev.raid_disks) - && ret == 0; - i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags)) { - struct request_queue *q = bdev_get_queue(rdev->bdev); - - ret |= bdi_congested(q->backing_dev_info, bits); - } - } - rcu_read_unlock(); - return ret; -} - static void flush_pending_writes(struct r10conf *conf) { /* Any writes that have been queued but are awaiting @@ -917,7 +892,7 @@ static void flush_pending_writes(struct r10conf *conf) /* Just ignore it */ bio_endio(bio); else - generic_make_request(bio); + submit_bio_noacct(bio); bio = next; } blk_finish_plug(&plug); @@ -1102,7 +1077,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) /* Just ignore it */ bio_endio(bio); else - generic_make_request(bio); + submit_bio_noacct(bio); bio = next; } kfree(plug); @@ -1194,7 +1169,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, gfp, &conf->bio_split); bio_chain(split, bio); allow_barrier(conf); - generic_make_request(bio); + submit_bio_noacct(bio); wait_barrier(conf); bio = split; r10_bio->master_bio = bio; @@ -1221,7 +1196,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, trace_block_bio_remap(read_bio->bi_disk->queue, read_bio, disk_devt(mddev->gendisk), r10_bio->sector); - generic_make_request(read_bio); + submit_bio_noacct(read_bio); return; } @@ -1479,7 +1454,7 @@ retry_write: GFP_NOIO, &conf->bio_split); bio_chain(split, bio); allow_barrier(conf); - generic_make_request(bio); + submit_bio_noacct(bio); wait_barrier(conf); bio = split; r10_bio->master_bio = bio; @@ -2099,7 +2074,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) tbio->bi_opf |= MD_FAILFAST; tbio->bi_iter.bi_sector += conf->mirrors[d].rdev->data_offset; bio_set_dev(tbio, conf->mirrors[d].rdev->bdev); - generic_make_request(tbio); + submit_bio_noacct(tbio); } /* Now write out to any replacement devices @@ -2118,7 +2093,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) atomic_inc(&r10_bio->remaining); md_sync_acct(conf->mirrors[d].replacement->bdev, bio_sectors(tbio)); - generic_make_request(tbio); + submit_bio_noacct(tbio); } done: @@ -2241,7 +2216,7 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio) wbio = r10_bio->devs[1].bio; wbio2 = r10_bio->devs[1].repl_bio; /* Need to test wbio2->bi_end_io before we call - * generic_make_request as if the former is NULL, + * submit_bio_noacct as if the former is NULL, * the latter is free to free wbio2. */ if (wbio2 && !wbio2->bi_end_io) @@ -2249,13 +2224,13 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio) if (wbio->bi_end_io) { atomic_inc(&conf->mirrors[d].rdev->nr_pending); md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio)); - generic_make_request(wbio); + submit_bio_noacct(wbio); } if (wbio2) { atomic_inc(&conf->mirrors[d].replacement->nr_pending); md_sync_acct(conf->mirrors[d].replacement->bdev, bio_sectors(wbio2)); - generic_make_request(wbio2); + submit_bio_noacct(wbio2); } } @@ -2889,7 +2864,7 @@ static void raid10_set_cluster_sync_high(struct r10conf *conf) * a number of r10_bio structures, one for each out-of-sync device. * As we setup these structures, we collect all bio's together into a list * which we then process collectively to add pages, and then process again - * to pass to generic_make_request. + * to pass to submit_bio_noacct. * * The r10_bio structures are linked using a borrowed master_bio pointer. * This link is counted in ->remaining. When the r10_bio that points to NULL @@ -3496,7 +3471,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, if (bio->bi_end_io == end_sync_read) { md_sync_acct_bio(bio, nr_sectors); bio->bi_status = 0; - generic_make_request(bio); + submit_bio_noacct(bio); } } @@ -4654,7 +4629,7 @@ read_more: md_sync_acct_bio(read_bio, r10_bio->sectors); atomic_inc(&r10_bio->remaining); read_bio->bi_next = NULL; - generic_make_request(read_bio); + submit_bio_noacct(read_bio); sectors_done += nr_sectors; if (sector_nr <= last) goto read_more; @@ -4717,7 +4692,7 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio) md_sync_acct_bio(b, r10_bio->sectors); atomic_inc(&r10_bio->remaining); b->bi_next = NULL; - generic_make_request(b); + submit_bio_noacct(b); } end_reshape_request(r10_bio); } @@ -4929,7 +4904,6 @@ static struct md_personality raid10_personality = .start_reshape = raid10_start_reshape, .finish_reshape = raid10_finish_reshape, .update_reshape_pos = raid10_update_reshape_pos, - .congested = raid10_congested, }; static int __init raid_init(void) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index ab8067f9ce8c..774ea893d47e 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -873,7 +873,7 @@ static void dispatch_bio_list(struct bio_list *tmp) struct bio *bio; while ((bio = bio_list_pop(tmp))) - generic_make_request(bio); + submit_bio_noacct(bio); } static int cmp_stripe(void *priv, struct list_head *a, struct list_head *b) @@ -1151,7 +1151,7 @@ again: if (should_defer && op_is_write(op)) bio_list_add(&pending_bios, bi); else - generic_make_request(bi); + submit_bio_noacct(bi); } if (rrdev) { if (s->syncing || s->expanding || s->expanded @@ -1201,7 +1201,7 @@ again: if (should_defer && op_is_write(op)) bio_list_add(&pending_bios, rbi); else - generic_make_request(rbi); + submit_bio_noacct(rbi); } if (!rdev && !rrdev) { if (op_is_write(op)) @@ -5099,28 +5099,6 @@ static void activate_bit_delay(struct r5conf *conf, } } -static int raid5_congested(struct mddev *mddev, int bits) -{ - struct r5conf *conf = mddev->private; - - /* No difference between reads and writes. Just check - * how busy the stripe_cache is - */ - - if (test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) - return 1; - - /* Also checks whether there is pressure on r5cache log space */ - if (test_bit(R5C_LOG_TIGHT, &conf->cache_state)) - return 1; - if (conf->quiesce) - return 1; - if (atomic_read(&conf->empty_inactive_list_nr)) - return 1; - - return 0; -} - static int in_chunk_boundary(struct mddev *mddev, struct bio *bio) { struct r5conf *conf = mddev->private; @@ -5289,7 +5267,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) trace_block_bio_remap(align_bi->bi_disk->queue, align_bi, disk_devt(mddev->gendisk), raid_bio->bi_iter.bi_sector); - generic_make_request(align_bi); + submit_bio_noacct(align_bi); return 1; } else { rcu_read_unlock(); @@ -5309,7 +5287,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio) struct r5conf *conf = mddev->private; split = bio_split(raid_bio, sectors, GFP_NOIO, &conf->bio_split); bio_chain(split, raid_bio); - generic_make_request(raid_bio); + submit_bio_noacct(raid_bio); raid_bio = split; } @@ -8427,7 +8405,6 @@ static struct md_personality raid6_personality = .finish_reshape = raid5_finish_reshape, .quiesce = raid5_quiesce, .takeover = raid6_takeover, - .congested = raid5_congested, .change_consistency_policy = raid5_change_consistency_policy, }; static struct md_personality raid5_personality = @@ -8452,7 +8429,6 @@ static struct md_personality raid5_personality = .finish_reshape = raid5_finish_reshape, .quiesce = raid5_quiesce, .takeover = raid5_takeover, - .congested = raid5_congested, .change_consistency_policy = raid5_change_consistency_policy, }; @@ -8478,7 +8454,6 @@ static struct md_personality raid4_personality = .finish_reshape = raid5_finish_reshape, .quiesce = raid5_quiesce, .takeover = raid4_takeover, - .congested = raid5_congested, .change_consistency_policy = raid5_change_consistency_policy, }; diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 7896952de1ac..fa313b634135 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -312,10 +312,7 @@ static int mmc_blk_open(struct block_device *bdev, fmode_t mode) mutex_lock(&block_mutex); if (md) { - if (md->usage == 2) - check_disk_change(bdev); ret = 0; - if ((mode & FMODE_WRITE) && md->read_only) { mmc_blk_put(md); ret = -EROFS; @@ -1446,7 +1443,7 @@ static void mmc_blk_cqe_req_done(struct mmc_request *mrq) */ if (mq->in_recovery) mmc_blk_cqe_complete_rq(mq, req); - else + else if (likely(!blk_should_fake_timeout(req->q))) blk_mq_complete_request(req); } @@ -1926,7 +1923,7 @@ static void mmc_blk_hsq_req_done(struct mmc_request *mrq) */ if (mq->in_recovery) mmc_blk_cqe_complete_rq(mq, req); - else + else if (likely(!blk_should_fake_timeout(req->q))) blk_mq_complete_request(req); } @@ -1936,7 +1933,7 @@ void mmc_blk_mq_complete(struct request *req) if (mq->use_cqe) mmc_blk_cqe_complete_rq(mq, req); - else + else if (likely(!blk_should_fake_timeout(req->q))) mmc_blk_mq_complete_rq(mq, req); } @@ -1988,7 +1985,7 @@ static void mmc_blk_mq_post_req(struct mmc_queue *mq, struct request *req) */ if (mq->in_recovery) mmc_blk_mq_complete_rq(mq, req); - else + else if (likely(!blk_should_fake_timeout(req->q))) blk_mq_complete_request(req); mmc_blk_mq_dec_in_flight(mq, req); diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c index 39030a324d7f..1f718381a045 100644 --- a/drivers/nvdimm/blk.c +++ b/drivers/nvdimm/blk.c @@ -162,7 +162,7 @@ static int nsblk_do_bvec(struct nd_namespace_blk *nsblk, return err; } -static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t nd_blk_submit_bio(struct bio *bio) { struct bio_integrity_payload *bip; struct nd_namespace_blk *nsblk = bio->bi_disk->private_data; @@ -225,6 +225,7 @@ static int nsblk_rw_bytes(struct nd_namespace_common *ndns, static const struct block_device_operations nd_blk_fops = { .owner = THIS_MODULE, + .submit_bio = nd_blk_submit_bio, .revalidate_disk = nvdimm_revalidate_disk, }; @@ -250,7 +251,7 @@ static int nsblk_attach_disk(struct nd_namespace_blk *nsblk) internal_nlba = div_u64(nsblk->size, nsblk_internal_lbasize(nsblk)); available_disk_size = internal_nlba * nsblk_sector_size(nsblk); - q = blk_alloc_queue(nd_blk_make_request, NUMA_NO_NODE); + q = blk_alloc_queue(NUMA_NO_NODE); if (!q) return -ENOMEM; if (devm_add_action_or_reset(dev, nd_blk_release_queue, q)) diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 48e9d169b6f9..412d21d8f643 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1439,7 +1439,7 @@ static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip, return ret; } -static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t btt_submit_bio(struct bio *bio) { struct bio_integrity_payload *bip = bio_integrity(bio); struct btt *btt = bio->bi_disk->private_data; @@ -1512,6 +1512,7 @@ static int btt_getgeo(struct block_device *bd, struct hd_geometry *geo) static const struct block_device_operations btt_fops = { .owner = THIS_MODULE, + .submit_bio = btt_submit_bio, .rw_page = btt_rw_page, .getgeo = btt_getgeo, .revalidate_disk = nvdimm_revalidate_disk, @@ -1523,7 +1524,7 @@ static int btt_blk_init(struct btt *btt) struct nd_namespace_common *ndns = nd_btt->ndns; /* create a new disk and request queue for btt */ - btt->btt_queue = blk_alloc_queue(btt_make_request, NUMA_NO_NODE); + btt->btt_queue = blk_alloc_queue(NUMA_NO_NODE); if (!btt->btt_queue) return -ENOMEM; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index d25e66fd942d..94790e6e0e4c 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -189,7 +189,7 @@ static blk_status_t pmem_do_write(struct pmem_device *pmem, return rc; } -static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t pmem_submit_bio(struct bio *bio) { int ret = 0; blk_status_t rc = 0; @@ -281,6 +281,7 @@ __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff, static const struct block_device_operations pmem_fops = { .owner = THIS_MODULE, + .submit_bio = pmem_submit_bio, .rw_page = pmem_rw_page, .revalidate_disk = nvdimm_revalidate_disk, }; @@ -423,7 +424,7 @@ static int pmem_attach_disk(struct device *dev, return -EBUSY; } - q = blk_alloc_queue(pmem_make_request, dev_to_node(dev)); + q = blk_alloc_queue(dev_to_node(dev)); if (!q) return -ENOMEM; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index add040168e67..71c2c1bf3cc1 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -304,7 +304,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved) return true; nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD; - blk_mq_force_complete_rq(req); + blk_mq_complete_request(req); return true; } EXPORT_SYMBOL_GPL(nvme_cancel_request); @@ -2184,6 +2184,7 @@ static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode) const struct block_device_operations nvme_ns_head_ops = { .owner = THIS_MODULE, + .submit_bio = nvme_ns_head_submit_bio, .open = nvme_ns_head_open, .release = nvme_ns_head_release, .ioctl = nvme_ioctl, diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index e999a8c4b7e8..6aa30bb5a762 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -227,6 +227,7 @@ static DECLARE_COMPLETION(nvme_fc_unload_proceed); */ static struct device *fc_udev_device; +static void nvme_fc_complete_rq(struct request *rq); /* *********************** FC-NVME Port Management ************************ */ @@ -2033,7 +2034,8 @@ done: } __nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate); - nvme_end_request(rq, status, result); + if (!nvme_end_request(rq, status, result)) + nvme_fc_complete_rq(rq); check_error: if (terminate_assoc) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 66509472fe06..5a37a595411e 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -291,8 +291,7 @@ static bool nvme_available_path(struct nvme_ns_head *head) return false; } -static blk_qc_t nvme_ns_head_make_request(struct request_queue *q, - struct bio *bio) +blk_qc_t nvme_ns_head_submit_bio(struct bio *bio) { struct nvme_ns_head *head = bio->bi_disk->private_data; struct device *dev = disk_to_dev(head->disk); @@ -301,12 +300,11 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q, int srcu_idx; /* - * The namespace might be going away and the bio might - * be moved to a different queue via blk_steal_bios(), - * so we need to use the bio_split pool from the original - * queue to allocate the bvecs from. + * The namespace might be going away and the bio might be moved to a + * different queue via blk_steal_bios(), so we need to use the bio_split + * pool from the original queue to allocate the bvecs from. */ - blk_queue_split(q, &bio); + blk_queue_split(&bio); srcu_idx = srcu_read_lock(&head->srcu); ns = nvme_find_path(head); @@ -316,7 +314,7 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q, trace_block_bio_remap(bio->bi_disk->queue, bio, disk_devt(ns->head->disk), bio->bi_iter.bi_sector); - ret = direct_make_request(bio); + ret = submit_bio_noacct(bio); } else if (nvme_available_path(head)) { dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n"); @@ -353,7 +351,7 @@ static void nvme_requeue_work(struct work_struct *work) * path. */ bio->bi_disk = head->disk; - generic_make_request(bio); + submit_bio_noacct(bio); } } @@ -375,7 +373,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || !multipath) return 0; - q = blk_alloc_queue(nvme_ns_head_make_request, ctrl->numa_node); + q = blk_alloc_queue(ctrl->numa_node); if (!q) goto out; blk_queue_flag_set(QUEUE_FLAG_NONROT, q); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 1de3f9b827aa..26099eaf1b1c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -474,7 +474,7 @@ static inline u32 nvme_bytes_to_numd(size_t len) return (len >> 2) - 1; } -static inline void nvme_end_request(struct request *req, __le16 status, +static inline bool nvme_end_request(struct request *req, __le16 status, union nvme_result result) { struct nvme_request *rq = nvme_req(req); @@ -483,7 +483,9 @@ static inline void nvme_end_request(struct request *req, __le16 status, rq->result = result; /* inject error when permitted by fault injection framework */ nvme_should_fail(req); - blk_mq_complete_request(req); + if (unlikely(blk_should_fake_timeout(req->q))) + return true; + return blk_mq_complete_request_remote(req); } static inline void nvme_get_ctrl(struct nvme_ctrl *ctrl) @@ -586,6 +588,7 @@ void nvme_mpath_stop(struct nvme_ctrl *ctrl); bool nvme_mpath_clear_current_path(struct nvme_ns *ns); void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl); struct nvme_ns *nvme_find_path(struct nvme_ns_head *head); +blk_qc_t nvme_ns_head_submit_bio(struct bio *bio); static inline void nvme_mpath_check_last_path(struct nvme_ns *ns) { diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b1d18f0633c7..74a2e2e00794 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -963,7 +963,8 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id); trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail); - nvme_end_request(req, cqe->status, cqe->result); + if (!nvme_end_request(req, cqe->status, cqe->result)) + nvme_pci_complete_rq(req); } static inline void nvme_update_cq_head(struct nvme_queue *nvmeq) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 13506a87a444..e881f879ac63 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -149,6 +149,7 @@ MODULE_PARM_DESC(register_always, static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event); static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc); +static void nvme_rdma_complete_rq(struct request *rq); static const struct blk_mq_ops nvme_rdma_mq_ops; static const struct blk_mq_ops nvme_rdma_admin_mq_ops; @@ -1149,6 +1150,16 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl) queue_work(nvme_reset_wq, &ctrl->err_work); } +static void nvme_rdma_end_request(struct nvme_rdma_request *req) +{ + struct request *rq = blk_mq_rq_from_pdu(req); + + if (!refcount_dec_and_test(&req->ref)) + return; + if (!nvme_end_request(rq, req->status, req->result)) + nvme_rdma_complete_rq(rq); +} + static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc, const char *op) { @@ -1173,16 +1184,11 @@ static void nvme_rdma_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc) { struct nvme_rdma_request *req = container_of(wc->wr_cqe, struct nvme_rdma_request, reg_cqe); - struct request *rq = blk_mq_rq_from_pdu(req); - if (unlikely(wc->status != IB_WC_SUCCESS)) { + if (unlikely(wc->status != IB_WC_SUCCESS)) nvme_rdma_wr_error(cq, wc, "LOCAL_INV"); - return; - } - - if (refcount_dec_and_test(&req->ref)) - nvme_end_request(rq, req->status, req->result); - + else + nvme_rdma_end_request(req); } static int nvme_rdma_inv_rkey(struct nvme_rdma_queue *queue, @@ -1547,15 +1553,11 @@ static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc) container_of(wc->wr_cqe, struct nvme_rdma_qe, cqe); struct nvme_rdma_request *req = container_of(qe, struct nvme_rdma_request, sqe); - struct request *rq = blk_mq_rq_from_pdu(req); - if (unlikely(wc->status != IB_WC_SUCCESS)) { + if (unlikely(wc->status != IB_WC_SUCCESS)) nvme_rdma_wr_error(cq, wc, "SEND"); - return; - } - - if (refcount_dec_and_test(&req->ref)) - nvme_end_request(rq, req->status, req->result); + else + nvme_rdma_end_request(req); } static int nvme_rdma_post_send(struct nvme_rdma_queue *queue, @@ -1697,8 +1699,7 @@ static void nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue, return; } - if (refcount_dec_and_test(&req->ref)) - nvme_end_request(rq, req->status, req->result); + nvme_rdma_end_request(req); } static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 79ef2b8e2b3c..7006aca89456 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -464,7 +464,8 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue, return -EINVAL; } - nvme_end_request(rq, cqe->status, cqe->result); + if (!nvme_end_request(rq, cqe->status, cqe->result)) + nvme_complete_rq(rq); queue->nr_cqe++; return 0; @@ -654,7 +655,8 @@ static inline void nvme_tcp_end_request(struct request *rq, u16 status) { union nvme_result res = {}; - nvme_end_request(rq, cpu_to_le16(status << 1), res); + if (!nvme_end_request(rq, cpu_to_le16(status << 1), res)) + nvme_complete_rq(rq); } static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb, diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 6e2f623e472e..6816507fba58 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -467,7 +467,7 @@ static int nvmet_p2pmem_ns_enable(struct nvmet_ns *ns) return -EINVAL; } - if (!blk_queue_pci_p2pdma(ns->bdev->bd_queue)) { + if (!blk_queue_pci_p2pdma(ns->bdev->bd_disk->queue)) { pr_err("peer-to-peer DMA is not supported by the driver of %s\n", ns->device_path); return -EINVAL; diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 6344e73c9354..8a0d4fe7bc18 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -116,7 +116,8 @@ static void nvme_loop_queue_response(struct nvmet_req *req) return; } - nvme_end_request(rq, cqe->status, cqe->result); + if (!nvme_end_request(rq, cqe->status, cqe->result)) + nvme_loop_complete_rq(rq); } } diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index cf87eb27879f..eb17fea8075c 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2802,7 +2802,7 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr) blk_update_request(req, BLK_STS_OK, blk_rq_bytes(req) - proc_bytes); blk_mq_requeue_request(req, true); - } else { + } else if (likely(!blk_should_fake_timeout(req->q))) { blk_mq_complete_request(req); } } diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 384edffe5cb4..299e77ec2c41 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -31,8 +31,7 @@ static int dcssblk_open(struct block_device *bdev, fmode_t mode); static void dcssblk_release(struct gendisk *disk, fmode_t mode); -static blk_qc_t dcssblk_make_request(struct request_queue *q, - struct bio *bio); +static blk_qc_t dcssblk_submit_bio(struct bio *bio); static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); @@ -41,6 +40,7 @@ static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0"; static int dcssblk_major; static const struct block_device_operations dcssblk_devops = { .owner = THIS_MODULE, + .submit_bio = dcssblk_submit_bio, .open = dcssblk_open, .release = dcssblk_release, }; @@ -651,8 +651,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char } dev_info->gd->major = dcssblk_major; dev_info->gd->fops = &dcssblk_devops; - dev_info->dcssblk_queue = - blk_alloc_queue(dcssblk_make_request, NUMA_NO_NODE); + dev_info->dcssblk_queue = blk_alloc_queue(NUMA_NO_NODE); dev_info->gd->queue = dev_info->dcssblk_queue; dev_info->gd->private_data = dev_info; blk_queue_logical_block_size(dev_info->dcssblk_queue, 4096); @@ -833,7 +832,6 @@ dcssblk_open(struct block_device *bdev, fmode_t mode) goto out; } atomic_inc(&dev_info->use_count); - bdev->bd_block_size = 4096; rc = 0; out: return rc; @@ -868,7 +866,7 @@ dcssblk_release(struct gendisk *disk, fmode_t mode) } static blk_qc_t -dcssblk_make_request(struct request_queue *q, struct bio *bio) +dcssblk_submit_bio(struct bio *bio) { struct dcssblk_dev_info *dev_info; struct bio_vec bvec; @@ -878,7 +876,7 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio) unsigned long source_addr; unsigned long bytes_done; - blk_queue_split(q, &bio); + blk_queue_split(&bio); bytes_done = 0; dev_info = bio->bi_disk->private_data; diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c index e01889394c84..a4f6f2e62b1d 100644 --- a/drivers/s390/block/scm_blk.c +++ b/drivers/s390/block/scm_blk.c @@ -256,7 +256,8 @@ static void scm_request_finish(struct scm_request *scmrq) for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) { error = blk_mq_rq_to_pdu(scmrq->request[i]); *error = scmrq->error; - blk_mq_complete_request(scmrq->request[i]); + if (likely(!blk_should_fake_timeout(scmrq->request[i]->q))) + blk_mq_complete_request(scmrq->request[i]); } atomic_dec(&bdev->queued_reqs); diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c index 45a04daec89e..c2536f7767b3 100644 --- a/drivers/s390/block/xpram.c +++ b/drivers/s390/block/xpram.c @@ -182,7 +182,7 @@ static unsigned long xpram_highest_page_index(void) /* * Block device make request function. */ -static blk_qc_t xpram_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t xpram_submit_bio(struct bio *bio) { xpram_device_t *xdev = bio->bi_disk->private_data; struct bio_vec bvec; @@ -191,7 +191,7 @@ static blk_qc_t xpram_make_request(struct request_queue *q, struct bio *bio) unsigned long page_addr; unsigned long bytes; - blk_queue_split(q, &bio); + blk_queue_split(&bio); if ((bio->bi_iter.bi_sector & 7) != 0 || (bio->bi_iter.bi_size & 4095) != 0) @@ -250,6 +250,7 @@ static int xpram_getgeo(struct block_device *bdev, struct hd_geometry *geo) static const struct block_device_operations xpram_devops = { .owner = THIS_MODULE, + .submit_bio = xpram_submit_bio, .getgeo = xpram_getgeo, }; @@ -343,8 +344,7 @@ static int __init xpram_setup_blkdev(void) xpram_disks[i] = alloc_disk(1); if (!xpram_disks[i]) goto out; - xpram_queues[i] = blk_alloc_queue(xpram_make_request, - NUMA_NO_NODE); + xpram_queues[i] = blk_alloc_queue(NUMA_NO_NODE); if (!xpram_queues[i]) { put_disk(xpram_disks[i]); goto out; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0ba7a65e7c8d..534b85e87c80 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1589,31 +1589,23 @@ static blk_status_t scsi_mq_prep_fn(struct request *req) static void scsi_mq_done(struct scsi_cmnd *cmd) { + if (unlikely(blk_should_fake_timeout(cmd->request->q))) + return; if (unlikely(test_and_set_bit(SCMD_STATE_COMPLETE, &cmd->state))) return; trace_scsi_dispatch_cmd_done(cmd); - - /* - * If the block layer didn't complete the request due to a timeout - * injection, scsi must clear its internal completed state so that the - * timeout handler will see it needs to escalate its own error - * recovery. - */ - if (unlikely(!blk_mq_complete_request(cmd->request))) - clear_bit(SCMD_STATE_COMPLETE, &cmd->state); + blk_mq_complete_request(cmd->request); } -static void scsi_mq_put_budget(struct blk_mq_hw_ctx *hctx) +static void scsi_mq_put_budget(struct request_queue *q) { - struct request_queue *q = hctx->queue; struct scsi_device *sdev = q->queuedata; atomic_dec(&sdev->device_busy); } -static bool scsi_mq_get_budget(struct blk_mq_hw_ctx *hctx) +static bool scsi_mq_get_budget(struct request_queue *q) { - struct request_queue *q = hctx->queue; struct scsi_device *sdev = q->queuedata; return scsi_dev_queue_ready(q, sdev); @@ -1680,7 +1672,7 @@ out_dec_target_busy: if (scsi_target(sdev)->can_queue > 0) atomic_dec(&scsi_target(sdev)->target_busy); out_put_budget: - scsi_mq_put_budget(hctx); + scsi_mq_put_budget(q); switch (ret) { case BLK_STS_OK: break; diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 7c95afa905a0..a8e39b2cdd55 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -403,7 +403,6 @@ static const struct sysrq_key_op sysrq_moom_op = { .enable_mask = SYSRQ_ENABLE_SIGNAL, }; -#ifdef CONFIG_BLOCK static void sysrq_handle_thaw(int key) { emergency_thaw_all(); @@ -414,7 +413,6 @@ static const struct sysrq_key_op sysrq_thaw_op = { .action_msg = "Emergency Thaw of all frozen filesystems", .enable_mask = SYSRQ_ENABLE_SIGNAL, }; -#endif static void sysrq_handle_kill(int key) { diff --git a/fs/adfs/super.c b/fs/adfs/super.c index a3cc8ecb50da..d553bb5bc17a 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -12,6 +12,7 @@ #include <linux/slab.h> #include <linux/statfs.h> #include <linux/user_namespace.h> +#include <linux/blkdev.h> #include "adfs.h" #include "dir_f.h" #include "dir_fplus.h" diff --git a/fs/affs/file.c b/fs/affs/file.c index a85817f54483..a26a0f96c119 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -14,6 +14,7 @@ */ #include <linux/uio.h> +#include <linux/blkdev.h> #include "affs.h" static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext); diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 64cdf4d8e424..2482032021ca 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -22,6 +22,7 @@ #include <linux/cred.h> #include <linux/exportfs.h> #include <linux/seq_file.h> +#include <linux/blkdev.h> #include "befs.h" #include "btree.h" diff --git a/fs/block_dev.c b/fs/block_dev.c index 0ae656e022fd..3f94a06a0946 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -105,16 +105,7 @@ EXPORT_SYMBOL(invalidate_bdev); static void set_init_blocksize(struct block_device *bdev) { - unsigned bsize = bdev_logical_block_size(bdev); - loff_t size = i_size_read(bdev->bd_inode); - - while (bsize < PAGE_SIZE) { - if (size & bsize) - break; - bsize <<= 1; - } - bdev->bd_block_size = bsize; - bdev->bd_inode->i_blkbits = blksize_bits(bsize); + bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev)); } int set_blocksize(struct block_device *bdev, int size) @@ -128,9 +119,8 @@ int set_blocksize(struct block_device *bdev, int size) return -EINVAL; /* Don't change the size if it is same as current */ - if (bdev->bd_block_size != size) { + if (bdev->bd_inode->i_blkbits != blksize_bits(size)) { sync_blockdev(bdev); - bdev->bd_block_size = size; bdev->bd_inode->i_blkbits = blksize_bits(size); kill_bdev(bdev); } @@ -703,12 +693,12 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, if (!ops->rw_page || bdev_get_integrity(bdev)) return result; - result = blk_queue_enter(bdev->bd_queue, 0); + result = blk_queue_enter(bdev->bd_disk->queue, 0); if (result) return result; result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, REQ_OP_READ); - blk_queue_exit(bdev->bd_queue); + blk_queue_exit(bdev->bd_disk->queue); return result; } @@ -739,7 +729,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, if (!ops->rw_page || bdev_get_integrity(bdev)) return -EOPNOTSUPP; - result = blk_queue_enter(bdev->bd_queue, 0); + result = blk_queue_enter(bdev->bd_disk->queue, 0); if (result) return result; @@ -752,7 +742,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, clean_page_buffers(page); unlock_page(page); } - blk_queue_exit(bdev->bd_queue); + blk_queue_exit(bdev->bd_disk->queue); return result; } @@ -783,7 +773,6 @@ static void init_once(void *foo) memset(bdev, 0, sizeof(*bdev)); mutex_init(&bdev->bd_mutex); - INIT_LIST_HEAD(&bdev->bd_list); #ifdef CONFIG_SYSFS INIT_LIST_HEAD(&bdev->bd_holder_disks); #endif @@ -799,9 +788,6 @@ static void bdev_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); /* is it needed here? */ clear_inode(inode); - spin_lock(&bdev_lock); - list_del_init(&bdev->bd_list); - spin_unlock(&bdev_lock); /* Detach inode from wb early as bdi_put() may free bdi->wb */ inode_detach_wb(inode); if (bdev->bd_bdi != &noop_backing_dev_info) { @@ -876,8 +862,6 @@ static int bdev_set(struct inode *inode, void *data) return 0; } -static LIST_HEAD(all_bdevs); - struct block_device *bdget(dev_t dev) { struct block_device *bdev; @@ -895,7 +879,6 @@ struct block_device *bdget(dev_t dev) bdev->bd_contains = NULL; bdev->bd_super = NULL; bdev->bd_inode = inode; - bdev->bd_block_size = i_blocksize(inode); bdev->bd_part_count = 0; bdev->bd_invalidated = 0; inode->i_mode = S_IFBLK; @@ -903,9 +886,6 @@ struct block_device *bdget(dev_t dev) inode->i_bdev = bdev; inode->i_data.a_ops = &def_blk_aops; mapping_set_gfp_mask(&inode->i_data, GFP_USER); - spin_lock(&bdev_lock); - list_add(&bdev->bd_list, &all_bdevs); - spin_unlock(&bdev_lock); unlock_new_inode(inode); } return bdev; @@ -926,13 +906,14 @@ EXPORT_SYMBOL(bdgrab); long nr_blockdev_pages(void) { - struct block_device *bdev; + struct inode *inode; long ret = 0; - spin_lock(&bdev_lock); - list_for_each_entry(bdev, &all_bdevs, bd_list) { - ret += bdev->bd_inode->i_mapping->nrpages; - } - spin_unlock(&bdev_lock); + + spin_lock(&blockdev_superblock->s_inode_list_lock); + list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) + ret += inode->i_mapping->nrpages; + spin_unlock(&blockdev_superblock->s_inode_list_lock); + return ret; } @@ -1034,30 +1015,28 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, } /** - * bd_prepare_to_claim - prepare to claim a block device + * bd_prepare_to_claim - claim a block device * @bdev: block device of interest * @whole: the whole device containing @bdev, may equal @bdev * @holder: holder trying to claim @bdev * - * Prepare to claim @bdev. This function fails if @bdev is already - * claimed by another holder and waits if another claiming is in - * progress. This function doesn't actually claim. On successful - * return, the caller has ownership of bd_claiming and bd_holder[s]. - * - * CONTEXT: - * spin_lock(&bdev_lock). Might release bdev_lock, sleep and regrab - * it multiple times. + * Claim @bdev. This function fails if @bdev is already claimed by another + * holder and waits if another claiming is in progress. return, the caller + * has ownership of bd_claiming and bd_holder[s]. * * RETURNS: * 0 if @bdev can be claimed, -EBUSY otherwise. */ -static int bd_prepare_to_claim(struct block_device *bdev, - struct block_device *whole, void *holder) +int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, + void *holder) { retry: + spin_lock(&bdev_lock); /* if someone else claimed, fail */ - if (!bd_may_claim(bdev, whole, holder)) + if (!bd_may_claim(bdev, whole, holder)) { + spin_unlock(&bdev_lock); return -EBUSY; + } /* if claiming is already in progress, wait for it to finish */ if (whole->bd_claiming) { @@ -1068,13 +1047,15 @@ retry: spin_unlock(&bdev_lock); schedule(); finish_wait(wq, &wait); - spin_lock(&bdev_lock); goto retry; } /* yay, all mine */ + whole->bd_claiming = holder; + spin_unlock(&bdev_lock); return 0; } +EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno) { @@ -1097,78 +1078,6 @@ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno) return disk; } -/** - * bd_start_claiming - start claiming a block device - * @bdev: block device of interest - * @holder: holder trying to claim @bdev - * - * @bdev is about to be opened exclusively. Check @bdev can be opened - * exclusively and mark that an exclusive open is in progress. Each - * successful call to this function must be matched with a call to - * either bd_finish_claiming() or bd_abort_claiming() (which do not - * fail). - * - * This function is used to gain exclusive access to the block device - * without actually causing other exclusive open attempts to fail. It - * should be used when the open sequence itself requires exclusive - * access but may subsequently fail. - * - * CONTEXT: - * Might sleep. - * - * RETURNS: - * Pointer to the block device containing @bdev on success, ERR_PTR() - * value on failure. - */ -struct block_device *bd_start_claiming(struct block_device *bdev, void *holder) -{ - struct gendisk *disk; - struct block_device *whole; - int partno, err; - - might_sleep(); - - /* - * @bdev might not have been initialized properly yet, look up - * and grab the outer block device the hard way. - */ - disk = bdev_get_gendisk(bdev, &partno); - if (!disk) - return ERR_PTR(-ENXIO); - - /* - * Normally, @bdev should equal what's returned from bdget_disk() - * if partno is 0; however, some drivers (floppy) use multiple - * bdev's for the same physical device and @bdev may be one of the - * aliases. Keep @bdev if partno is 0. This means claimer - * tracking is broken for those devices but it has always been that - * way. - */ - if (partno) - whole = bdget_disk(disk, 0); - else - whole = bdgrab(bdev); - - put_disk_and_module(disk); - if (!whole) - return ERR_PTR(-ENOMEM); - - /* prepare to claim, if successful, mark claiming in progress */ - spin_lock(&bdev_lock); - - err = bd_prepare_to_claim(bdev, whole, holder); - if (err == 0) { - whole->bd_claiming = holder; - spin_unlock(&bdev_lock); - return whole; - } else { - spin_unlock(&bdev_lock); - bdput(whole); - return ERR_PTR(err); - } -} -EXPORT_SYMBOL(bd_start_claiming); - static void bd_clear_claiming(struct block_device *whole, void *holder) { lockdep_assert_held(&bdev_lock); @@ -1181,14 +1090,14 @@ static void bd_clear_claiming(struct block_device *whole, void *holder) /** * bd_finish_claiming - finish claiming of a block device * @bdev: block device of interest - * @whole: whole block device (returned from bd_start_claiming()) + * @whole: whole block device * @holder: holder that has claimed @bdev * * Finish exclusive open of a block device. Mark the device as exlusively * open by the holder and wake up all waiters for exclusive open to finish. */ -void bd_finish_claiming(struct block_device *bdev, struct block_device *whole, - void *holder) +static void bd_finish_claiming(struct block_device *bdev, + struct block_device *whole, void *holder) { spin_lock(&bdev_lock); BUG_ON(!bd_may_claim(bdev, whole, holder)); @@ -1203,12 +1112,11 @@ void bd_finish_claiming(struct block_device *bdev, struct block_device *whole, bd_clear_claiming(whole, holder); spin_unlock(&bdev_lock); } -EXPORT_SYMBOL(bd_finish_claiming); /** * bd_abort_claiming - abort claiming of a block device * @bdev: block device of interest - * @whole: whole block device (returned from bd_start_claiming()) + * @whole: whole block device * @holder: holder that has claimed @bdev * * Abort claiming of a block device when the exclusive open failed. This can be @@ -1368,26 +1276,6 @@ EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); #endif /** - * flush_disk - invalidates all buffer-cache entries on a disk - * - * @bdev: struct block device to be flushed - * @kill_dirty: flag to guide handling of dirty inodes - * - * Invalidates all buffer-cache entries on a disk. It should be called - * when a disk has been changed -- either by a media change or online - * resize. - */ -static void flush_disk(struct block_device *bdev, bool kill_dirty) -{ - if (__invalidate_device(bdev, kill_dirty)) { - printk(KERN_WARNING "VFS: busy inodes on changed media or " - "resized disk %s\n", - bdev->bd_disk ? bdev->bd_disk->disk_name : ""); - } - bdev->bd_invalidated = 1; -} - -/** * check_disk_size_change - checks for disk size change and adjusts bdev size. * @disk: struct gendisk to check * @bdev: struct bdev to adjust. @@ -1411,8 +1299,9 @@ static void check_disk_size_change(struct gendisk *disk, disk->disk_name, bdev_size, disk_size); } i_size_write(bdev->bd_inode, disk_size); - if (bdev_size > disk_size) - flush_disk(bdev, false); + if (bdev_size > disk_size && __invalidate_device(bdev, false)) + pr_warn("VFS: busy inodes on resized disk %s\n", + disk->disk_name); } bdev->bd_invalidated = 0; } @@ -1471,7 +1360,10 @@ int check_disk_change(struct block_device *bdev) if (!(events & DISK_EVENT_MEDIA_CHANGE)) return 0; - flush_disk(bdev, true); + if (__invalidate_device(bdev, true)) + pr_warn("VFS: busy inodes on changed media %s\n", + disk->disk_name); + bdev->bd_invalidated = 1; if (bdops->revalidate_disk) bdops->revalidate_disk(bdev->bd_disk); return 1; @@ -1547,13 +1439,15 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed); * mutex_lock_nested(whole->bd_mutex, 1) */ -static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) +static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder, + int for_part) { + struct block_device *whole = NULL, *claiming = NULL; struct gendisk *disk; int ret; int partno; int perm = 0; - bool first_open = false; + bool first_open = false, unblock_events = true, need_restart; if (mode & FMODE_READ) perm |= MAY_READ; @@ -1569,18 +1463,36 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } restart: - + need_restart = false; ret = -ENXIO; disk = bdev_get_gendisk(bdev, &partno); if (!disk) goto out; + if (partno) { + whole = bdget_disk(disk, 0); + if (!whole) { + ret = -ENOMEM; + goto out_put_disk; + } + } + + if (!for_part && (mode & FMODE_EXCL)) { + WARN_ON_ONCE(!holder); + if (whole) + claiming = whole; + else + claiming = bdev; + ret = bd_prepare_to_claim(bdev, claiming, holder); + if (ret) + goto out_put_whole; + } + disk_block_events(disk); mutex_lock_nested(&bdev->bd_mutex, for_part); if (!bdev->bd_openers) { first_open = true; bdev->bd_disk = disk; - bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; bdev->bd_partno = partno; @@ -1593,20 +1505,12 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) ret = 0; if (disk->fops->open) { ret = disk->fops->open(bdev, mode); - if (ret == -ERESTARTSYS) { - /* Lost a race with 'disk' being - * deleted, try again. - * See md.c - */ - disk_put_part(bdev->bd_part); - bdev->bd_part = NULL; - bdev->bd_disk = NULL; - bdev->bd_queue = NULL; - mutex_unlock(&bdev->bd_mutex); - disk_unblock_events(disk); - put_disk_and_module(disk); - goto restart; - } + /* + * If we lost a race with 'disk' being deleted, + * try again. See md.c + */ + if (ret == -ERESTARTSYS) + need_restart = true; } if (!ret) { @@ -1627,18 +1531,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (ret) goto out_clear; } else { - struct block_device *whole; - whole = bdget_disk(disk, 0); - ret = -ENOMEM; - if (!whole) - goto out_clear; BUG_ON(for_part); - ret = __blkdev_get(whole, mode, 1); - if (ret) { - bdput(whole); + ret = __blkdev_get(whole, mode, NULL, 1); + if (ret) goto out_clear; - } - bdev->bd_contains = whole; + bdev->bd_contains = bdgrab(whole); bdev->bd_part = disk_get_part(disk, partno); if (!(disk->flags & GENHD_FL_UP) || !bdev->bd_part || !bdev->bd_part->nr_sects) { @@ -1667,27 +1564,52 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_openers++; if (for_part) bdev->bd_part_count++; + if (claiming) + bd_finish_claiming(bdev, claiming, holder); + + /* + * Block event polling for write claims if requested. Any write holder + * makes the write_holder state stick until all are released. This is + * good enough and tracking individual writeable reference is too + * fragile given the way @mode is used in blkdev_get/put(). + */ + if (claiming && (mode & FMODE_WRITE) && !bdev->bd_write_holder && + (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) { + bdev->bd_write_holder = true; + unblock_events = false; + } mutex_unlock(&bdev->bd_mutex); - disk_unblock_events(disk); + + if (unblock_events) + disk_unblock_events(disk); + /* only one opener holds refs to the module and disk */ if (!first_open) put_disk_and_module(disk); + if (whole) + bdput(whole); return 0; out_clear: disk_put_part(bdev->bd_part); bdev->bd_disk = NULL; bdev->bd_part = NULL; - bdev->bd_queue = NULL; if (bdev != bdev->bd_contains) __blkdev_put(bdev->bd_contains, mode, 1); bdev->bd_contains = NULL; out_unlock_bdev: + if (claiming) + bd_abort_claiming(bdev, claiming, holder); mutex_unlock(&bdev->bd_mutex); disk_unblock_events(disk); + out_put_whole: + if (whole) + bdput(whole); + out_put_disk: put_disk_and_module(disk); + if (need_restart) + goto restart; out: - return ret; } @@ -1712,50 +1634,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) */ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) { - struct block_device *whole = NULL; int res; - WARN_ON_ONCE((mode & FMODE_EXCL) && !holder); - - if ((mode & FMODE_EXCL) && holder) { - whole = bd_start_claiming(bdev, holder); - if (IS_ERR(whole)) { - bdput(bdev); - return PTR_ERR(whole); - } - } - - res = __blkdev_get(bdev, mode, 0); - - if (whole) { - struct gendisk *disk = whole->bd_disk; - - /* finish claiming */ - mutex_lock(&bdev->bd_mutex); - if (!res) - bd_finish_claiming(bdev, whole, holder); - else - bd_abort_claiming(bdev, whole, holder); - /* - * Block event polling for write claims if requested. Any - * write holder makes the write_holder state stick until - * all are released. This is good enough and tracking - * individual writeable reference is too fragile given the - * way @mode is used in blkdev_get/put(). - */ - if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder && - (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) { - bdev->bd_write_holder = true; - disk_block_events(disk); - } - - mutex_unlock(&bdev->bd_mutex); - bdput(whole); - } - + res =__blkdev_get(bdev, mode, holder, 0); if (res) bdput(bdev); - return res; } EXPORT_SYMBOL(blkdev_get); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b1a148058773..ad157b55d7f5 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1616,27 +1616,6 @@ fail: return ERR_PTR(ret); } -static int btrfs_congested_fn(void *congested_data, int bdi_bits) -{ - struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; - int ret = 0; - struct btrfs_device *device; - struct backing_dev_info *bdi; - - rcu_read_lock(); - list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) { - if (!device->bdev) - continue; - bdi = device->bdev->bd_bdi; - if (bdi_congested(bdi, bdi_bits)) { - ret = 1; - break; - } - } - rcu_read_unlock(); - return ret; -} - /* * called by the kthread helper functions to finally call the bio end_io * functions. This is where read checksum verification actually happens @@ -3053,8 +3032,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_sb_buffer; } - sb->s_bdi->congested_fn = btrfs_congested_fn; - sb->s_bdi->congested_data = fs_info; sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK; sb->s_bdi->ra_pages = VM_READAHEAD_PAGES; sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super); diff --git a/fs/buffer.c b/fs/buffer.c index 64fe82ec65ff..2725ebbcfdc2 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3040,12 +3040,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); - /* - * from here on down, it's all bio -- do the initial mapping, - * submit_bio -> generic_make_request may further map this bio around - */ bio = bio_alloc(GFP_NOIO, 1); - bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; diff --git a/fs/direct-io.c b/fs/direct-io.c index 6d5370eac2a8..183299892465 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1387,8 +1387,8 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, * Attempt to prefetch the pieces we likely need later. */ prefetch(&bdev->bd_disk->part_tbl); - prefetch(bdev->bd_queue); - prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES); + prefetch(bdev->bd_disk->queue); + prefetch((char *)bdev->bd_disk->queue + SMP_CACHE_BYTES); return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block, end_io, submit_io, flags); diff --git a/fs/efs/super.c b/fs/efs/super.c index 4a6ebff2af76..a4a945d0ac6a 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -13,6 +13,7 @@ #include <linux/slab.h> #include <linux/buffer_head.h> #include <linux/vfs.h> +#include <linux/blkdev.h> #include "efs.h" #include <linux/efs_vh.h> diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 2f224b98ee94..f35a37c65e5f 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -17,6 +17,7 @@ #include <linux/cred.h> #include <linux/uio.h> #include <linux/xattr.h> +#include <linux/blkdev.h> #include "hfs_fs.h" #include "btree.h" diff --git a/fs/internal.h b/fs/internal.h index 9b863a7bd708..969988d3d397 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -23,7 +23,9 @@ struct user_namespace; extern void __init bdev_cache_init(void); extern int __sync_blockdev(struct block_device *bdev, int wait); - +void iterate_bdevs(void (*)(struct block_device *, void *), void *); +void emergency_thaw_bdev(struct super_block *sb); +void bd_forget(struct inode *inode); #else static inline void bdev_cache_init(void) { @@ -33,7 +35,18 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait) { return 0; } -#endif +static inline void iterate_bdevs(void (*f)(struct block_device *, void *), + void *arg) +{ +} +static inline int emergency_thaw_bdev(struct super_block *sb) +{ + return 0; +} +static inline void bd_forget(struct inode *inode) +{ +} +#endif /* CONFIG_BLOCK */ /* * buffer.c diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index d634561f871a..78f5c96c76f3 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -612,9 +612,6 @@ static bool rootdir_empty(struct super_block *sb, unsigned long block) /* * Initialize the superblock and read the root inode. - * - * Note: a check_disk_change() has been done immediately prior - * to this call, so we don't need to check again. */ static int isofs_fill_super(struct super_block *s, void *data, int silent) { diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index eb8b9e233d73..2935d4c776ec 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -36,6 +36,7 @@ #include <linux/fs.h> #include <linux/buffer_head.h> +#include <linux/blkdev.h> #include "jfs_incore.h" #include "jfs_filsys.h" diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c index 66acea9d878b..bde787c354fc 100644 --- a/fs/jfs/resize.c +++ b/fs/jfs/resize.c @@ -6,6 +6,7 @@ #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/quotaops.h> +#include <linux/blkdev.h> #include "jfs_incore.h" #include "jfs_filsys.h" #include "jfs_metapage.h" diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index 3c4811469ae8..a87d4391e6b5 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -8,6 +8,7 @@ #include <linux/buffer_head.h> #include <linux/slab.h> +#include <linux/blkdev.h> #include "dir.h" #include "aops.h" diff --git a/fs/proc/devices.c b/fs/proc/devices.c index 37d38697eaf8..837971e74109 100644 --- a/fs/proc/devices.c +++ b/fs/proc/devices.c @@ -3,6 +3,7 @@ #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/blkdev.h> static int devinfo_show(struct seq_file *f, void *v) { diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 7b4bac91146b..bb02989d92b6 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -78,6 +78,7 @@ #include <linux/namei.h> #include <linux/capability.h> #include <linux/quotaops.h> +#include <linux/blkdev.h> #include "../internal.h" /* ugh */ #include <linux/uaccess.h> diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c index ff336513c254..155b82870333 100644 --- a/fs/reiserfs/procfs.c +++ b/fs/reiserfs/procfs.c @@ -15,6 +15,7 @@ #include "reiserfs.h" #include <linux/init.h> #include <linux/proc_fs.h> +#include <linux/blkdev.h> /* * LOCKING: diff --git a/fs/xfs/xfs_pwork.c b/fs/xfs/xfs_pwork.c index 4bcc3e61056c..b03333f1c84a 100644 --- a/fs/xfs/xfs_pwork.c +++ b/fs/xfs/xfs_pwork.c @@ -132,5 +132,5 @@ xfs_pwork_guess_datadev_parallelism( * For now we'll go with the most conservative setting possible, * which is two threads for an SSD and 1 thread everywhere else. */ - return blk_queue_nonrot(btp->bt_bdev->bd_queue) ? 2 : 1; + return blk_queue_nonrot(btp->bt_bdev->bd_disk->queue) ? 2 : 1; } diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 90a7e844a098..fff9367a6348 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -33,8 +33,6 @@ enum wb_congested_state { WB_sync_congested, /* The sync queue is getting full */ }; -typedef int (congested_fn)(void *, int); - enum wb_stat_item { WB_RECLAIMABLE, WB_WRITEBACK, @@ -88,26 +86,6 @@ struct wb_completion { struct wb_completion cmpl = WB_COMPLETION_INIT(bdi) /* - * For cgroup writeback, multiple wb's may map to the same blkcg. Those - * wb's can operate mostly independently but should share the congested - * state. To facilitate such sharing, the congested state is tracked using - * the following struct which is created on demand, indexed by blkcg ID on - * its bdi, and refcounted. - */ -struct bdi_writeback_congested { - unsigned long state; /* WB_[a]sync_congested flags */ - refcount_t refcnt; /* nr of attached wb's and blkg */ - -#ifdef CONFIG_CGROUP_WRITEBACK - struct backing_dev_info *__bdi; /* the associated bdi, set to NULL - * on bdi unregistration. For memcg-wb - * internal use only! */ - int blkcg_id; /* ID of the associated blkcg */ - struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */ -#endif -}; - -/* * Each wb (bdi_writeback) can perform writeback operations, is measured * and throttled, independently. Without cgroup writeback, each bdi * (bdi_writeback) is served by its embedded bdi->wb. @@ -140,7 +118,7 @@ struct bdi_writeback { struct percpu_counter stat[NR_WB_STAT_ITEMS]; - struct bdi_writeback_congested *congested; + unsigned long congested; /* WB_[a]sync_congested flags */ unsigned long bw_time_stamp; /* last time write bw is updated */ unsigned long dirtied_stamp; @@ -190,8 +168,6 @@ struct backing_dev_info { struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long io_pages; /* max allowed IO size */ - congested_fn *congested_fn; /* Function pointer if device is md/dm */ - void *congested_data; /* Pointer to aux data for congested func */ struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ @@ -208,11 +184,8 @@ struct backing_dev_info { struct list_head wb_list; /* list of all wbs */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ - struct rb_root cgwb_congested_tree; /* their congested states */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ -#else - struct bdi_writeback_congested *wb_congested; #endif wait_queue_head_t wb_waitq; @@ -232,18 +205,8 @@ enum { BLK_RW_SYNC = 1, }; -void clear_wb_congested(struct bdi_writeback_congested *congested, int sync); -void set_wb_congested(struct bdi_writeback_congested *congested, int sync); - -static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync) -{ - clear_wb_congested(bdi->wb.congested, sync); -} - -static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) -{ - set_wb_congested(bdi->wb.congested, sync); -} +void clear_bdi_congested(struct backing_dev_info *bdi, int sync); +void set_bdi_congested(struct backing_dev_info *bdi, int sync); struct wb_lock_cookie { bool locked; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 6b3504bf7a42..0b06b2d26c9a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -169,11 +169,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) { - struct backing_dev_info *bdi = wb->bdi; - - if (bdi->congested_fn) - return bdi->congested_fn(bdi->congested_data, cong_bits); - return wb->congested->state & cong_bits; + return wb->congested & cong_bits; } long congestion_wait(int sync, long timeout); @@ -224,9 +220,6 @@ static inline int bdi_sched_wait(void *word) #ifdef CONFIG_CGROUP_WRITEBACK -struct bdi_writeback_congested * -wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp); -void wb_congested_put(struct bdi_writeback_congested *congested); struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css); struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, @@ -404,19 +397,6 @@ static inline bool inode_cgwb_enabled(struct inode *inode) return false; } -static inline struct bdi_writeback_congested * -wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) -{ - refcount_inc(&bdi->wb_congested->refcnt); - return bdi->wb_congested; -} - -static inline void wb_congested_put(struct bdi_writeback_congested *congested) -{ - if (refcount_dec_and_test(&congested->refcnt)) - kfree(congested); -} - static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { return &bdi->wb; diff --git a/include/linux/bio.h b/include/linux/bio.h index 91676d4b2dfe..c6d765382926 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -8,8 +8,6 @@ #include <linux/highmem.h> #include <linux/mempool.h> #include <linux/ioprio.h> - -#ifdef CONFIG_BLOCK /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include <linux/blk_types.h> @@ -491,21 +489,12 @@ do { \ #define bio_dev(bio) \ disk_devt((bio)->bi_disk) -#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -void bio_associate_blkg_from_page(struct bio *bio, struct page *page); -#else -static inline void bio_associate_blkg_from_page(struct bio *bio, - struct page *page) { } -#endif - #ifdef CONFIG_BLK_CGROUP -void bio_disassociate_blkg(struct bio *bio); void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ -static inline void bio_disassociate_blkg(struct bio *bio) { } static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) @@ -824,5 +813,4 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } -#endif /* CONFIG_BLOCK */ #endif /* __LINUX_BIO_H */ diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index a57ebe2f00ab..c8fc9792ac77 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -109,12 +109,6 @@ struct blkcg_gq { struct hlist_node blkcg_node; struct blkcg *blkcg; - /* - * Each blkg gets congested separately and the congestion state is - * propagated to the matching bdi_writeback_congested. - */ - struct bdi_writeback_congested *wb_congested; - /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; @@ -183,10 +177,6 @@ extern bool blkcg_debug_stats; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); -struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q); -struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q); int blkcg_init_queue(struct request_queue *q); void blkcg_exit_queue(struct request_queue *q); @@ -481,32 +471,6 @@ static inline bool blkg_tryget(struct blkcg_gq *blkg) } /** - * blkg_tryget_closest - try and get a blkg ref on the closet blkg - * @blkg: blkg to get - * - * This needs to be called rcu protected. As the failure mode here is to walk - * up the blkg tree, this ensure that the blkg->parent pointers are always - * valid. This returns the blkg that it ended up taking a reference on or %NULL - * if no reference was taken. - */ -static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) -{ - struct blkcg_gq *ret_blkg = NULL; - - WARN_ON_ONCE(!rcu_read_lock_held()); - - while (blkg) { - if (blkg_tryget(blkg)) { - ret_blkg = blkg; - break; - } - blkg = blkg->parent; - } - - return ret_blkg; -} - -/** * blkg_put - put a blkg reference * @blkg: blkg to put */ @@ -547,14 +511,6 @@ static inline void blkg_put(struct blkcg_gq *blkg) if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) -#ifdef CONFIG_BLK_DEV_THROTTLING -extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, - struct bio *bio); -#else -static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, - struct bio *bio) { return false; } -#endif - bool __blkcg_punt_bio_submit(struct bio *bio); static inline bool blkcg_punt_bio_submit(struct bio *bio) @@ -570,65 +526,6 @@ static inline void blkcg_bio_issue_init(struct bio *bio) bio_issue_init(&bio->bi_issue, bio_sectors(bio)); } -static inline bool blkcg_bio_issue_check(struct request_queue *q, - struct bio *bio) -{ - struct blkcg_gq *blkg; - bool throtl = false; - - rcu_read_lock(); - - if (!bio->bi_blkg) { - char b[BDEVNAME_SIZE]; - - WARN_ONCE(1, - "no blkg associated for bio on block-device: %s\n", - bio_devname(bio, b)); - bio_associate_blkg(bio); - } - - blkg = bio->bi_blkg; - - throtl = blk_throtl_bio(q, blkg, bio); - - if (!throtl) { - struct blkg_iostat_set *bis; - int rwd, cpu; - - if (op_is_discard(bio->bi_opf)) - rwd = BLKG_IOSTAT_DISCARD; - else if (op_is_write(bio->bi_opf)) - rwd = BLKG_IOSTAT_WRITE; - else - rwd = BLKG_IOSTAT_READ; - - cpu = get_cpu(); - bis = per_cpu_ptr(blkg->iostat_cpu, cpu); - u64_stats_update_begin(&bis->sync); - - /* - * If the bio is flagged with BIO_CGROUP_ACCT it means this is a - * split bio and we would have already accounted for the size of - * the bio. - */ - if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { - bio_set_flag(bio, BIO_CGROUP_ACCT); - bis->cur.bytes[rwd] += bio->bi_iter.bi_size; - } - bis->cur.ios[rwd]++; - - u64_stats_update_end(&bis->sync); - if (cgroup_subsys_on_dfl(io_cgrp_subsys)) - cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu); - put_cpu(); - } - - blkcg_bio_issue_init(bio); - - rcu_read_unlock(); - return !throtl; -} - static inline void blkcg_use_delay(struct blkcg_gq *blkg) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) @@ -702,6 +599,7 @@ static inline void blkcg_clear_delay(struct blkcg_gq *blkg) atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); } +void blk_cgroup_bio_start(struct bio *bio); void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); @@ -755,8 +653,7 @@ static inline void blkg_put(struct blkcg_gq *blkg) { } static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; } static inline void blkcg_bio_issue_init(struct bio *bio) { } -static inline bool blkcg_bio_issue_check(struct request_queue *q, - struct bio *bio) { return true; } +static inline void blk_cgroup_bio_start(struct bio *bio) { } #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d6fcae17da5a..23230c1d031e 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -270,8 +270,8 @@ struct blk_mq_queue_data { typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); typedef void (commit_rqs_fn)(struct blk_mq_hw_ctx *); -typedef bool (get_budget_fn)(struct blk_mq_hw_ctx *); -typedef void (put_budget_fn)(struct blk_mq_hw_ctx *); +typedef bool (get_budget_fn)(struct request_queue *); +typedef void (put_budget_fn)(struct request_queue *); typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int); typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int); @@ -447,8 +447,6 @@ enum { BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), /* allocate from reserved pool */ BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1), - /* allocate internal/sched tag */ - BLK_MQ_REQ_INTERNAL = (__force blk_mq_req_flags_t)(1 << 2), /* set RQF_PREEMPT */ BLK_MQ_REQ_PREEMPT = (__force blk_mq_req_flags_t)(1 << 3), }; @@ -503,8 +501,8 @@ void __blk_mq_end_request(struct request *rq, blk_status_t error); void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); -bool blk_mq_complete_request(struct request *rq); -void blk_mq_force_complete_rq(struct request *rq); +void blk_mq_complete_request(struct request *rq); +bool blk_mq_complete_request_remote(struct request *rq); bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs); bool blk_mq_queue_stopped(struct request_queue *q); @@ -537,6 +535,15 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); +bool __blk_should_fake_timeout(struct request_queue *q); +static inline bool blk_should_fake_timeout(struct request_queue *q) +{ + if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) && + test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags)) + return __blk_should_fake_timeout(q); + return false; +} + /** * blk_mq_rq_from_pdu - cast a PDU to a request * @pdu: the PDU (Protocol Data Unit) to be casted @@ -589,6 +596,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq) rq->q->mq_ops->cleanup_rq(rq); } -blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio); +blk_qc_t blk_mq_submit_bio(struct bio *bio); #endif diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index ccb895f911b1..4ecf4fed171f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -14,12 +14,39 @@ struct bio_set; struct bio; struct bio_integrity_payload; struct page; -struct block_device; struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; +struct block_device { + dev_t bd_dev; /* not a kdev_t - it's a search key */ + int bd_openers; + struct inode * bd_inode; /* will die */ + struct super_block * bd_super; + struct mutex bd_mutex; /* open/close mutex */ + void * bd_claiming; + void * bd_holder; + int bd_holders; + bool bd_write_holder; +#ifdef CONFIG_SYSFS + struct list_head bd_holder_disks; +#endif + struct block_device * bd_contains; + u8 bd_partno; + struct hd_struct * bd_part; + /* number of times partitions within this device have been opened. */ + unsigned bd_part_count; + int bd_invalidated; + struct gendisk * bd_disk; + struct backing_dev_info *bd_bdi; + + /* The counter of freeze processes */ + int bd_fsfreeze_count; + /* Mutex for freeze */ + struct mutex bd_fsfreeze_mutex; +} __randomize_layout; + /* * Block error status values. See block/blk-core:blk_errors for the details. * Alpha cannot write a byte atomically, so we need to use 32-bit value. @@ -300,12 +327,8 @@ enum req_opf { REQ_OP_DISCARD = 3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, - /* reset a zone write pointer */ - REQ_OP_ZONE_RESET = 6, /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, - /* reset all the zone present on the device */ - REQ_OP_ZONE_RESET_ALL = 8, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 9, /* Open a zone */ @@ -316,6 +339,10 @@ enum req_opf { REQ_OP_ZONE_FINISH = 12, /* write data at the current zone write pointer */ REQ_OP_ZONE_APPEND = 13, + /* reset a zone write pointer */ + REQ_OP_ZONE_RESET = 15, + /* reset all the zone present on the device */ + REQ_OP_ZONE_RESET_ALL = 17, /* SCSI passthrough using struct scsi_request */ REQ_OP_SCSI_IN = 32, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 57241417ff2f..9ab06ea26894 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -4,9 +4,6 @@ #include <linux/sched.h> #include <linux/sched/clock.h> - -#ifdef CONFIG_BLOCK - #include <linux/major.h> #include <linux/genhd.h> #include <linux/list.h> @@ -289,8 +286,6 @@ static inline unsigned short req_get_ioprio(struct request *req) struct blk_queue_ctx; -typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); - struct bio_vec; enum blk_eh_timer_return { @@ -401,8 +396,6 @@ struct request_queue { struct blk_queue_stats *stats; struct rq_qos *rq_qos; - make_request_fn *make_request_fn; - const struct blk_mq_ops *mq_ops; /* sw queues */ @@ -528,9 +521,9 @@ struct request_queue { unsigned int sg_timeout; unsigned int sg_reserved_size; int node; + struct mutex debugfs_mutex; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; - struct mutex blk_trace_mutex; #endif /* * for flush operations @@ -574,8 +567,9 @@ struct request_queue { struct list_head tag_set_list; struct bio_set bio_split; -#ifdef CONFIG_BLK_DEBUG_FS struct dentry *debugfs_dir; + +#ifdef CONFIG_BLK_DEBUG_FS struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; #endif @@ -584,8 +578,6 @@ struct request_queue { size_t cmd_size; - struct work_struct release_work; - #define BLK_MAX_WRITE_HINTS 5 u64 write_hints[BLK_MAX_WRITE_HINTS]; }; @@ -861,8 +853,7 @@ static inline void rq_flush_dcache_pages(struct request *rq) extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); -extern blk_qc_t generic_make_request(struct bio *bio); -extern blk_qc_t direct_make_request(struct bio *bio); +blk_qc_t submit_bio_noacct(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern struct request *blk_get_request(struct request_queue *, unsigned int op, @@ -876,7 +867,7 @@ extern void blk_rq_unprep_clone(struct request *rq); extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern int blk_rq_append_bio(struct request *rq, struct bio **bio); -extern void blk_queue_split(struct request_queue *, struct bio **); +extern void blk_queue_split(struct bio **); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, unsigned int, void __user *); @@ -1079,7 +1070,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq); extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); /* @@ -1166,13 +1156,13 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, return __blk_rq_map_sg(q, rq, sglist, &last_sg); } extern void blk_dump_rq_flags(struct request *, char *); -extern long nr_blockdev_pages(void); bool __must_check blk_get_queue(struct request_queue *); -struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id); +struct request_queue *blk_alloc_queue(int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); +#ifdef CONFIG_BLOCK /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests @@ -1232,9 +1222,47 @@ 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); +long nr_blockdev_pages(void); +#else /* CONFIG_BLOCK */ +struct blk_plug { +}; + +static inline void blk_start_plug(struct blk_plug *plug) +{ +} + +static inline void blk_finish_plug(struct blk_plug *plug) +{ +} + +static inline void blk_flush_plug(struct task_struct *task) +{ +} + +static inline void blk_schedule_flush_plug(struct task_struct *task) +{ +} + + +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) +{ + return 0; +} + +static inline long nr_blockdev_pages(void) +{ + return 0; +} +#endif /* CONFIG_BLOCK */ + extern void blk_io_schedule(void); -int blkdev_issue_flush(struct block_device *, gfp_t); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); @@ -1516,7 +1544,7 @@ static inline unsigned int blksize_bits(unsigned int size) static inline unsigned int block_size(struct block_device *bdev) { - return bdev->bd_block_size; + return 1 << bdev->bd_inode->i_blkbits; } int kblockd_schedule_work(struct work_struct *work); @@ -1746,6 +1774,7 @@ static inline void blk_ksm_unregister(struct request_queue *q) { } struct block_device_operations { + blk_qc_t (*submit_bio) (struct bio *bio); int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); @@ -1753,8 +1782,6 @@ struct block_device_operations { int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); - /* ->media_changed() is DEPRECATED, use ->check_events() instead */ - int (*media_changed) (struct gendisk *); void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); @@ -1834,52 +1861,6 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq) } #endif /* CONFIG_BLK_DEV_ZONED */ -#else /* CONFIG_BLOCK */ - -struct block_device; - -/* - * stubs for when the block layer is configured out - */ -#define buffer_heads_over_limit 0 - -static inline long nr_blockdev_pages(void) -{ - return 0; -} - -struct blk_plug { -}; - -static inline void blk_start_plug(struct blk_plug *plug) -{ -} - -static inline void blk_finish_plug(struct blk_plug *plug) -{ -} - -static inline void blk_flush_plug(struct task_struct *task) -{ -} - -static inline void blk_schedule_flush_plug(struct task_struct *task) -{ -} - - -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) -{ - return 0; -} - -#endif /* CONFIG_BLOCK */ - static inline void blk_wake_io_task(struct task_struct *waiter) { /* @@ -1893,7 +1874,6 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -#ifdef CONFIG_BLOCK unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op); void disk_end_io_acct(struct gendisk *disk, unsigned int op, @@ -1919,6 +1899,53 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time); } -#endif /* CONFIG_BLOCK */ +int bdev_read_only(struct block_device *bdev); +int set_blocksize(struct block_device *bdev, int size); + +const char *bdevname(struct block_device *bdev, char *buffer); +struct block_device *lookup_bdev(const char *); + +void blkdev_show(struct seq_file *seqf, off_t offset); + +#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ +#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ +#ifdef CONFIG_BLOCK +#define BLKDEV_MAJOR_MAX 512 +#else +#define BLKDEV_MAJOR_MAX 0 +#endif + +int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); +struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, + void *holder); +struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); +int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, + void *holder); +void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, + void *holder); +void blkdev_put(struct block_device *bdev, fmode_t mode); + +struct block_device *I_BDEV(struct inode *inode); +struct block_device *bdget(dev_t); +struct block_device *bdgrab(struct block_device *bdev); +void bdput(struct block_device *); + +#ifdef CONFIG_BLOCK +void invalidate_bdev(struct block_device *bdev); +int sync_blockdev(struct block_device *bdev); +#else +static inline void invalidate_bdev(struct block_device *bdev) +{ +} +static inline int sync_blockdev(struct block_device *bdev) +{ + return 0; +} #endif +int fsync_bdev(struct block_device *bdev); + +struct super_block *freeze_bdev(struct block_device *bdev); +int thaw_bdev(struct block_device *bdev, struct super_block *sb); + +#endif /* _LINUX_BLKDEV_H */ diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 22fb11e2d2e0..6b47f94378c5 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -406,6 +406,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } +#define buffer_heads_over_limit 0 #endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 8543fa59da72..f48d0a31deae 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -73,7 +73,6 @@ struct cdrom_device_ops { int (*drive_status) (struct cdrom_device_info *, int); unsigned int (*check_events) (struct cdrom_device_info *cdi, unsigned int clearing, int slot); - int (*media_changed) (struct cdrom_device_info *, int); int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); int (*select_speed) (struct cdrom_device_info *, int); @@ -107,7 +106,6 @@ extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi, unsigned int clearing); -extern int cdrom_media_changed(struct cdrom_device_info *); extern int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi); extern void unregister_cdrom(struct cdrom_device_info *cdi); diff --git a/include/linux/dasd_mod.h b/include/linux/dasd_mod.h index d39abad2ff6e..14e6cf8c6267 100644 --- a/include/linux/dasd_mod.h +++ b/include/linux/dasd_mod.h @@ -4,6 +4,8 @@ #include <asm/dasd.h> +struct gendisk; + extern int dasd_biodasdinfo(struct gendisk *disk, dasd_information2_t *info); #endif diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 8750f2dc5613..d5306d9c29c4 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -322,12 +322,6 @@ struct dm_target { bool discards_supported:1; }; -/* Each target can link one of these into the table */ -struct dm_target_callbacks { - struct list_head list; - int (*congested_fn) (struct dm_target_callbacks *, int); -}; - void *dm_per_bio_data(struct bio *bio, size_t data_size); struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size); unsigned dm_bio_get_target_bio_nr(const struct bio *bio); @@ -478,11 +472,6 @@ int dm_table_add_target(struct dm_table *t, const char *type, sector_t start, sector_t len, char *params); /* - * Target_ctr should call this if it needs to add any callbacks. - */ -void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb); - -/* * Target can use this to set the table's type. * Can only ever be called from a target's ctr. * Useful for "hybrid" target (supports both bio-based diff --git a/include/linux/fs.h b/include/linux/fs.h index f5abba86107d..41cd993ec0f6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -471,45 +471,6 @@ struct address_space { * must be enforced here for CRIS, to let the least significant bit * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. */ -struct request_queue; - -struct block_device { - dev_t bd_dev; /* not a kdev_t - it's a search key */ - int bd_openers; - struct inode * bd_inode; /* will die */ - struct super_block * bd_super; - struct mutex bd_mutex; /* open/close mutex */ - void * bd_claiming; - void * bd_holder; - int bd_holders; - bool bd_write_holder; -#ifdef CONFIG_SYSFS - struct list_head bd_holder_disks; -#endif - struct block_device * bd_contains; - unsigned bd_block_size; - u8 bd_partno; - struct hd_struct * bd_part; - /* number of times partitions within this device have been opened. */ - unsigned bd_part_count; - int bd_invalidated; - struct gendisk * bd_disk; - struct request_queue * bd_queue; - struct backing_dev_info *bd_bdi; - struct list_head bd_list; - /* - * Private data. You must have bd_claim'ed the block_device - * to use this. NOTE: bd_claim allows an owner to claim - * the same device multiple times, the owner must take special - * care to not mess up bd_private for that case. - */ - unsigned long bd_private; - - /* The counter of freeze processes */ - int bd_fsfreeze_count; - /* Mutex for freeze */ - struct mutex bd_fsfreeze_mutex; -} __randomize_layout; /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 @@ -908,8 +869,6 @@ static inline unsigned imajor(const struct inode *inode) return MAJOR(inode->i_rdev); } -extern struct block_device *I_BDEV(struct inode *inode); - struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ @@ -1775,14 +1734,6 @@ struct dir_context { loff_t pos; }; -struct block_device_operations; - -/* These macros are for out of kernel modules to test that - * the kernel supports the unlocked_ioctl and compat_ioctl - * fields in struct file_operations. */ -#define HAVE_COMPAT_IOCTL 1 -#define HAVE_UNLOCKED_IOCTL 1 - /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. @@ -2264,18 +2215,9 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) -#ifdef CONFIG_BLOCK extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); -#else -static inline struct dentry *mount_bdev(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int)) -{ - return ERR_PTR(-ENODEV); -} -#endif extern struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -2284,14 +2226,7 @@ extern struct dentry *mount_nodev(struct file_system_type *fs_type, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void generic_shutdown_super(struct super_block *sb); -#ifdef CONFIG_BLOCK void kill_block_super(struct super_block *sb); -#else -static inline void kill_block_super(struct super_block *sb) -{ - BUG(); -} -#endif void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); @@ -2581,93 +2516,16 @@ extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) -#ifdef CONFIG_BLOCK -extern int register_blkdev(unsigned int, const char *); -extern void unregister_blkdev(unsigned int, const char *); -extern struct block_device *bdget(dev_t); -extern struct block_device *bdgrab(struct block_device *bdev); -extern void bd_set_size(struct block_device *, loff_t size); -extern void bd_forget(struct inode *inode); -extern void bdput(struct block_device *); -extern void invalidate_bdev(struct block_device *); -extern void iterate_bdevs(void (*)(struct block_device *, void *), void *); -extern int sync_blockdev(struct block_device *bdev); -extern struct super_block *freeze_bdev(struct block_device *); -extern void emergency_thaw_all(void); -extern void emergency_thaw_bdev(struct super_block *sb); -extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); -extern int fsync_bdev(struct block_device *); - extern struct super_block *blockdev_superblock; - static inline bool sb_is_blkdev_sb(struct super_block *sb) { - return sb == blockdev_superblock; -} -#else -static inline void bd_forget(struct inode *inode) {} -static inline int sync_blockdev(struct block_device *bdev) { return 0; } -static inline void invalidate_bdev(struct block_device *bdev) {} - -static inline struct super_block *freeze_bdev(struct block_device *sb) -{ - return NULL; -} - -static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) -{ - return 0; + return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } -static inline int emergency_thaw_bdev(struct super_block *sb) -{ - return 0; -} - -static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) -{ -} - -static inline bool sb_is_blkdev_sb(struct super_block *sb) -{ - return false; -} -#endif +void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; -#ifdef CONFIG_BLOCK -extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); -extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); -extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); -extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, - void *holder); -extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, - void *holder); -extern struct block_device *bd_start_claiming(struct block_device *bdev, - void *holder); -extern void bd_finish_claiming(struct block_device *bdev, - struct block_device *whole, void *holder); -extern void bd_abort_claiming(struct block_device *bdev, - struct block_device *whole, void *holder); -extern void blkdev_put(struct block_device *bdev, fmode_t mode); - -#ifdef CONFIG_SYSFS -extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); -extern void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk); -#else -static inline int bd_link_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ - return 0; -} -static inline void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ -} -#endif -#endif /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 @@ -2698,31 +2556,12 @@ static inline void unregister_chrdev(unsigned int major, const char *name) __unregister_chrdev(major, 0, 256, name); } -/* fs/block_dev.c */ -#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ -#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ - -#ifdef CONFIG_BLOCK -#define BLKDEV_MAJOR_MAX 512 -extern const char *bdevname(struct block_device *bdev, char *buffer); -extern struct block_device *lookup_bdev(const char *); -extern void blkdev_show(struct seq_file *,off_t); - -#else -#define BLKDEV_MAJOR_MAX 0 -#endif - extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); -#ifdef CONFIG_BLOCK -extern int revalidate_disk(struct gendisk *); -extern int check_disk_change(struct block_device *); -extern int __invalidate_device(struct block_device *, bool); -#endif unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); @@ -3123,10 +2962,6 @@ static inline void remove_inode_hash(struct inode *inode) extern void inode_sb_list_add(struct inode *inode); -#ifdef CONFIG_BLOCK -extern int bdev_read_only(struct block_device *); -#endif -extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 392aad5e29a2..4ab853461dff 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -19,13 +19,12 @@ #include <linux/blk_types.h> #include <asm/local.h> -#ifdef CONFIG_BLOCK - #define dev_to_disk(device) container_of((device), struct gendisk, part0.__dev) #define dev_to_part(device) container_of((device), struct hd_struct, __dev) #define disk_to_dev(disk) (&(disk)->part0.__dev) #define part_to_dev(part) (&((part)->__dev)) +extern const struct device_type disk_type; extern struct device_type part_type; extern struct class block_class; @@ -337,12 +336,9 @@ static inline void set_capacity(struct gendisk *disk, sector_t size) disk->part0.nr_sects = size; } -extern dev_t blk_lookup_devt(const char *name, int partno); - int bdev_disk_changed(struct block_device *bdev, bool invalidate); int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); int blk_drop_partitions(struct block_device *bdev); -extern void printk_all_partitions(void); extern struct gendisk *__alloc_disk_node(int minors, int node_id); extern struct kobject *get_disk_and_module(struct gendisk *disk); @@ -373,10 +369,40 @@ extern void blk_unregister_region(dev_t devt, unsigned long range); #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) -#else /* CONFIG_BLOCK */ +int register_blkdev(unsigned int major, const char *name); +void unregister_blkdev(unsigned int major, const char *name); -static inline void printk_all_partitions(void) { } +int revalidate_disk(struct gendisk *disk); +int check_disk_change(struct block_device *bdev); +int __invalidate_device(struct block_device *bdev, bool kill_dirty); +void bd_set_size(struct block_device *bdev, loff_t size); +/* for drivers/char/raw.c: */ +int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); +long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); + +#ifdef CONFIG_SYSFS +int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); +void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); +#else +static inline int bd_link_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ + return 0; +} +static inline void bd_unlink_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ +} +#endif /* CONFIG_SYSFS */ + +#ifdef CONFIG_BLOCK +void printk_all_partitions(void); +dev_t blk_lookup_devt(const char *name, int partno); +#else /* CONFIG_BLOCK */ +static inline void printk_all_partitions(void) +{ +} static inline dev_t blk_lookup_devt(const char *name, int partno) { dev_t devt = MKDEV(0, 0); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d56128df2aff..4aaa29772bb0 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -27,6 +27,7 @@ #include <linux/timer.h> #include <linux/slab.h> #include <linux/bit_spinlock.h> +#include <linux/blkdev.h> #include <crypto/hash.h> #endif diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index ee8ec2e68055..1db223710b28 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -631,7 +631,6 @@ static inline int nvm_next_ppa_in_chk(struct nvm_tgt_dev *dev, return last; } -typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, int flags); @@ -650,7 +649,7 @@ struct nvm_tgt_type { int flags; /* target entry points */ - nvm_tgt_make_rq_fn *make_rq; + const struct block_device_operations *bops; nvm_tgt_capacity_fn *capacity; /* module-specific init/teardown */ diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 93b114226af8..34d64ca306b1 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -212,6 +212,21 @@ DEFINE_EVENT(block_rq, block_rq_issue, ); /** + * block_rq_merge - merge request with another one in the elevator + * @q: queue holding operation + * @rq: block IO operation operation request + * + * Called when block operation request @rq from queue @q is merged to another + * request queued in the elevator. + */ +DEFINE_EVENT(block_rq, block_rq_merge, + + TP_PROTO(struct request_queue *q, struct request *rq), + + TP_ARGS(q, rq) +); + +/** * block_bio_bounce - used bounce buffer when processing block operation * @q: queue holding the block operation * @bio: block operation diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index b6397a186ce9..d51175cedfca 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -64,7 +64,6 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) raw_spin_unlock_irqrestore(cpu_lock, flags); } -EXPORT_SYMBOL_GPL(cgroup_rstat_updated); /** * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 5ef0484513ec..7ba62d68885a 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -348,7 +348,7 @@ static int __blk_trace_remove(struct request_queue *q) struct blk_trace *bt; bt = rcu_replace_pointer(q->blk_trace, NULL, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); if (!bt) return -EINVAL; @@ -362,9 +362,9 @@ int blk_trace_remove(struct request_queue *q) { int ret; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); ret = __blk_trace_remove(q); - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); return ret; } @@ -483,12 +483,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct dentry *dir = NULL; int ret; + lockdep_assert_held(&q->debugfs_mutex); + if (!buts->buf_size || !buts->buf_nr) return -EINVAL; - if (!blk_debugfs_root) - return -ENOENT; - strncpy(buts->name, name, BLKTRACE_BDEV_SIZE); buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0'; @@ -503,7 +502,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, * we can be. */ if (rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex))) { + lockdep_is_held(&q->debugfs_mutex))) { pr_warn("Concurrent blktraces are not allowed on %s\n", buts->name); return -EBUSY; @@ -522,12 +521,29 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!bt->msg_data) goto err; - ret = -ENOENT; - - dir = debugfs_lookup(buts->name, blk_debugfs_root); - if (!dir) + /* + * When tracing the whole disk reuse the existing debugfs directory + * created by the block layer on init. For partitions block devices, + * and scsi-generic block devices we create a temporary new debugfs + * directory that will be removed once the trace ends. + */ + if (bdev && bdev == bdev->bd_contains) + dir = q->debugfs_dir; + else bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root); + /* + * As blktrace relies on debugfs for its interface the debugfs directory + * is required, contrary to the usual mantra of not checking for debugfs + * files or directories. + */ + if (IS_ERR_OR_NULL(dir)) { + pr_warn("debugfs_dir not present for %s so skipping\n", + buts->name); + ret = -ENOENT; + goto err; + } + bt->dev = dev; atomic_set(&bt->dropped, 0); INIT_LIST_HEAD(&bt->running_list); @@ -563,8 +579,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, ret = 0; err: - if (dir && !bt->dir) - dput(dir); if (ret) blk_trace_free(bt); return ret; @@ -597,9 +611,9 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, { int ret; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); ret = __blk_trace_setup(q, name, dev, bdev, arg); - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); return ret; } @@ -645,7 +659,7 @@ static int __blk_trace_startstop(struct request_queue *q, int start) struct blk_trace *bt; bt = rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); if (bt == NULL) return -EINVAL; @@ -685,9 +699,9 @@ int blk_trace_startstop(struct request_queue *q, int start) { int ret; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); ret = __blk_trace_startstop(q, start); - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); return ret; } @@ -716,7 +730,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) if (!q) return -ENXIO; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); switch (cmd) { case BLKTRACESETUP: @@ -743,7 +757,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) break; } - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); return ret; } @@ -754,14 +768,14 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) **/ void blk_trace_shutdown(struct request_queue *q) { - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); if (rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex))) { + lockdep_is_held(&q->debugfs_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); } #ifdef CONFIG_BLK_CGROUP @@ -846,6 +860,13 @@ static void blk_add_trace_rq_issue(void *ignore, blk_trace_request_get_cgid(q, rq)); } +static void blk_add_trace_rq_merge(void *ignore, + struct request_queue *q, struct request *rq) +{ + blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE, + blk_trace_request_get_cgid(q, rq)); +} + static void blk_add_trace_rq_requeue(void *ignore, struct request_queue *q, struct request *rq) @@ -1130,6 +1151,8 @@ static void blk_register_tracepoints(void) WARN_ON(ret); ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); WARN_ON(ret); + ret = register_trace_block_rq_merge(blk_add_trace_rq_merge, NULL); + WARN_ON(ret); ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); WARN_ON(ret); ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); @@ -1176,6 +1199,7 @@ static void blk_unregister_tracepoints(void) unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); + unregister_trace_block_rq_merge(blk_add_trace_rq_merge, NULL); unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); @@ -1642,7 +1666,7 @@ static int blk_trace_remove_queue(struct request_queue *q) struct blk_trace *bt; bt = rcu_replace_pointer(q->blk_trace, NULL, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); if (bt == NULL) return -EINVAL; @@ -1817,10 +1841,10 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); bt = rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; @@ -1838,7 +1862,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, ret = sprintf(buf, "%llu\n", bt->end_lba); out_unlock_bdev: - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); out_bdput: bdput(bdev); out: @@ -1881,10 +1905,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); bt = rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); if (attr == &dev_attr_enable) { if (!!value == !!bt) { ret = 0; @@ -1901,7 +1925,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, if (bt == NULL) { ret = blk_trace_setup_queue(q, bdev); bt = rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); } if (ret == 0) { @@ -1916,7 +1940,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } out_unlock_bdev: - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); out_bdput: bdput(bdev); out: diff --git a/lib/sbitmap.c b/lib/sbitmap.c index af88d1346dd7..267aa7709416 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -292,8 +292,11 @@ void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m) for (i = 0; i < sb->map_nr; i++) { unsigned long word = READ_ONCE(sb->map[i].word); + unsigned long cleared = READ_ONCE(sb->map[i].cleared); unsigned int word_bits = READ_ONCE(sb->map[i].depth); + word &= ~cleared; + while (word_bits > 0) { unsigned int bits = min(8 - byte_bits, word_bits); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index d382272bcc31..8e8b00627bb2 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -281,7 +281,7 @@ void wb_wakeup_delayed(struct bdi_writeback *wb) #define INIT_BW (100 << (20 - PAGE_SHIFT)) static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, - int blkcg_id, gfp_t gfp) + gfp_t gfp) { int i, err; @@ -308,15 +308,9 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, INIT_DELAYED_WORK(&wb->dwork, wb_workfn); wb->dirty_sleep = jiffies; - wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp); - if (!wb->congested) { - err = -ENOMEM; - goto out_put_bdi; - } - err = fprop_local_init_percpu(&wb->completions, gfp); if (err) - goto out_put_cong; + goto out_put_bdi; for (i = 0; i < NR_WB_STAT_ITEMS; i++) { err = percpu_counter_init(&wb->stat[i], 0, gfp); @@ -330,8 +324,6 @@ out_destroy_stat: while (i--) percpu_counter_destroy(&wb->stat[i]); fprop_local_destroy_percpu(&wb->completions); -out_put_cong: - wb_congested_put(wb->congested); out_put_bdi: if (wb != &bdi->wb) bdi_put(bdi); @@ -374,7 +366,6 @@ static void wb_exit(struct bdi_writeback *wb) percpu_counter_destroy(&wb->stat[i]); fprop_local_destroy_percpu(&wb->completions); - wb_congested_put(wb->congested); if (wb != &wb->bdi->wb) bdi_put(wb->bdi); } @@ -384,99 +375,12 @@ static void wb_exit(struct bdi_writeback *wb) #include <linux/memcontrol.h> /* - * cgwb_lock protects bdi->cgwb_tree, bdi->cgwb_congested_tree, - * blkcg->cgwb_list, and memcg->cgwb_list. bdi->cgwb_tree is also RCU - * protected. + * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, and memcg->cgwb_list. + * bdi->cgwb_tree is also RCU protected. */ static DEFINE_SPINLOCK(cgwb_lock); static struct workqueue_struct *cgwb_release_wq; -/** - * wb_congested_get_create - get or create a wb_congested - * @bdi: associated bdi - * @blkcg_id: ID of the associated blkcg - * @gfp: allocation mask - * - * Look up the wb_congested for @blkcg_id on @bdi. If missing, create one. - * The returned wb_congested has its reference count incremented. Returns - * NULL on failure. - */ -struct bdi_writeback_congested * -wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) -{ - struct bdi_writeback_congested *new_congested = NULL, *congested; - struct rb_node **node, *parent; - unsigned long flags; -retry: - spin_lock_irqsave(&cgwb_lock, flags); - - node = &bdi->cgwb_congested_tree.rb_node; - parent = NULL; - - while (*node != NULL) { - parent = *node; - congested = rb_entry(parent, struct bdi_writeback_congested, - rb_node); - if (congested->blkcg_id < blkcg_id) - node = &parent->rb_left; - else if (congested->blkcg_id > blkcg_id) - node = &parent->rb_right; - else - goto found; - } - - if (new_congested) { - /* !found and storage for new one already allocated, insert */ - congested = new_congested; - rb_link_node(&congested->rb_node, parent, node); - rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree); - spin_unlock_irqrestore(&cgwb_lock, flags); - return congested; - } - - spin_unlock_irqrestore(&cgwb_lock, flags); - - /* allocate storage for new one and retry */ - new_congested = kzalloc(sizeof(*new_congested), gfp); - if (!new_congested) - return NULL; - - refcount_set(&new_congested->refcnt, 1); - new_congested->__bdi = bdi; - new_congested->blkcg_id = blkcg_id; - goto retry; - -found: - refcount_inc(&congested->refcnt); - spin_unlock_irqrestore(&cgwb_lock, flags); - kfree(new_congested); - return congested; -} - -/** - * wb_congested_put - put a wb_congested - * @congested: wb_congested to put - * - * Put @congested and destroy it if the refcnt reaches zero. - */ -void wb_congested_put(struct bdi_writeback_congested *congested) -{ - unsigned long flags; - - if (!refcount_dec_and_lock_irqsave(&congested->refcnt, &cgwb_lock, &flags)) - return; - - /* bdi might already have been destroyed leaving @congested unlinked */ - if (congested->__bdi) { - rb_erase(&congested->rb_node, - &congested->__bdi->cgwb_congested_tree); - congested->__bdi = NULL; - } - - spin_unlock_irqrestore(&cgwb_lock, flags); - kfree(congested); -} - static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, @@ -558,7 +462,7 @@ static int cgwb_create(struct backing_dev_info *bdi, goto out_put; } - ret = wb_init(wb, bdi, blkcg_css->id, gfp); + ret = wb_init(wb, bdi, gfp); if (ret) goto err_free; @@ -696,11 +600,10 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) int ret; INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); - bdi->cgwb_congested_tree = RB_ROOT; mutex_init(&bdi->cgwb_release_mutex); init_rwsem(&bdi->wb_switch_rwsem); - ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); + ret = wb_init(&bdi->wb, bdi, GFP_KERNEL); if (!ret) { bdi->wb.memcg_css = &root_mem_cgroup->css; bdi->wb.blkcg_css = blkcg_root_css; @@ -769,21 +672,6 @@ void wb_blkcg_offline(struct blkcg *blkcg) spin_unlock_irq(&cgwb_lock); } -static void cgwb_bdi_exit(struct backing_dev_info *bdi) -{ - struct rb_node *rbn; - - spin_lock_irq(&cgwb_lock); - while ((rbn = rb_first(&bdi->cgwb_congested_tree))) { - struct bdi_writeback_congested *congested = - rb_entry(rbn, struct bdi_writeback_congested, rb_node); - - rb_erase(rbn, &bdi->cgwb_congested_tree); - congested->__bdi = NULL; /* mark @congested unlinked */ - } - spin_unlock_irq(&cgwb_lock); -} - static void cgwb_bdi_register(struct backing_dev_info *bdi) { spin_lock_irq(&cgwb_lock); @@ -810,29 +698,11 @@ subsys_initcall(cgwb_init); static int cgwb_bdi_init(struct backing_dev_info *bdi) { - int err; - - bdi->wb_congested = kzalloc(sizeof(*bdi->wb_congested), GFP_KERNEL); - if (!bdi->wb_congested) - return -ENOMEM; - - refcount_set(&bdi->wb_congested->refcnt, 1); - - err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); - if (err) { - wb_congested_put(bdi->wb_congested); - return err; - } - return 0; + return wb_init(&bdi->wb, bdi, GFP_KERNEL); } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { } -static void cgwb_bdi_exit(struct backing_dev_info *bdi) -{ - wb_congested_put(bdi->wb_congested); -} - static void cgwb_bdi_register(struct backing_dev_info *bdi) { list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); @@ -1023,7 +893,6 @@ static void release_bdi(struct kref *ref) bdi_unregister(bdi); WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); - cgwb_bdi_exit(bdi); kfree(bdi); } @@ -1047,29 +916,29 @@ static wait_queue_head_t congestion_wqh[2] = { }; static atomic_t nr_wb_congested[2]; -void clear_wb_congested(struct bdi_writeback_congested *congested, int sync) +void clear_bdi_congested(struct backing_dev_info *bdi, int sync) { wait_queue_head_t *wqh = &congestion_wqh[sync]; enum wb_congested_state bit; bit = sync ? WB_sync_congested : WB_async_congested; - if (test_and_clear_bit(bit, &congested->state)) + if (test_and_clear_bit(bit, &bdi->wb.congested)) atomic_dec(&nr_wb_congested[sync]); smp_mb__after_atomic(); if (waitqueue_active(wqh)) wake_up(wqh); } -EXPORT_SYMBOL(clear_wb_congested); +EXPORT_SYMBOL(clear_bdi_congested); -void set_wb_congested(struct bdi_writeback_congested *congested, int sync) +void set_bdi_congested(struct backing_dev_info *bdi, int sync) { enum wb_congested_state bit; bit = sync ? WB_sync_congested : WB_async_congested; - if (!test_and_set_bit(bit, &congested->state)) + if (!test_and_set_bit(bit, &bdi->wb.congested)) atomic_inc(&nr_wb_congested[sync]); } -EXPORT_SYMBOL(set_wb_congested); +EXPORT_SYMBOL(set_bdi_congested); /** * congestion_wait - wait for a backing_dev to become uncongested diff --git a/mm/page_io.c b/mm/page_io.c index e8726f3e3820..ccda76790088 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -277,6 +277,23 @@ static inline void count_swpout_vm_event(struct page *page) count_vm_events(PSWPOUT, hpage_nr_pages(page)); } +#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) +static void bio_associate_blkg_from_page(struct bio *bio, struct page *page) +{ + struct cgroup_subsys_state *css; + + if (!page->mem_cgroup) + return; + + rcu_read_lock(); + css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys); + bio_associate_blkg_from_css(bio, css); + rcu_read_unlock(); +} +#else +#define bio_associate_blkg_from_page(bio, page) do { } while (0) +#endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */ + int __swap_writepage(struct page *page, struct writeback_control *wbc, bio_end_io_t end_write_func) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 987276c557d1..6c26916e95fd 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2929,7 +2929,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ - if (blk_queue_is_zoned(p->bdev->bd_queue)) + if (blk_queue_is_zoned(p->bdev->bd_disk->queue)) return -EINVAL; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c index ee5cb944f4ad..670a1aebb8a1 100644 --- a/security/loadpin/loadpin.c +++ b/security/loadpin/loadpin.c @@ -13,6 +13,7 @@ #include <linux/fs.h> #include <linux/lsm_hooks.h> #include <linux/mount.h> +#include <linux/blkdev.h> #include <linux/path.h> #include <linux/sched.h> /* current */ #include <linux/string_helpers.h> |