diff options
Diffstat (limited to 'drivers/block')
30 files changed, 243 insertions, 421 deletions
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 52484bcdedb9..8a91fcac6f82 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -12,7 +12,6 @@ #include <linux/ioctl.h> #include <linux/slab.h> #include <linux/ratelimit.h> -#include <linux/genhd.h> #include <linux/netdevice.h> #include <linux/mutex.h> #include <linux/export.h> diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 6af111f568e4..384073ef2323 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -10,7 +10,6 @@ #include <linux/blk-mq.h> #include <linux/skbuff.h> #include <linux/netdevice.h> -#include <linux/genhd.h> #include <linux/moduleparam.h> #include <linux/workqueue.h> #include <linux/kthread.h> @@ -1019,9 +1018,9 @@ bvcpy(struct sk_buff *skb, struct bio *bio, struct bvec_iter iter, long cnt) iter.bi_size = cnt; __bio_for_each_segment(bv, bio, iter, iter) { - char *p = kmap_atomic(bv.bv_page) + bv.bv_offset; + char *p = bvec_kmap_local(&bv); skb_copy_bits(skb, soff, p, bv.bv_len); - kunmap_atomic(p); + kunmap_local(p); soff += bv.bv_len; } } diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index 72cf7603d51f..f5bcded3640d 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -138,15 +138,14 @@ static int _drbd_md_sync_page_io(struct drbd_device *device, op_flags |= REQ_FUA | REQ_PREFLUSH; op_flags |= REQ_SYNC; - bio = bio_alloc_bioset(GFP_NOIO, 1, &drbd_md_io_bio_set); - bio_set_dev(bio, bdev->md_bdev); + bio = bio_alloc_bioset(bdev->md_bdev, 1, op | op_flags, GFP_NOIO, + &drbd_md_io_bio_set); bio->bi_iter.bi_sector = sector; err = -EIO; if (bio_add_page(bio, device->md_io.page, size, 0) != size) goto out; bio->bi_private = device; bio->bi_end_io = drbd_md_endio; - bio_set_op_attrs(bio, op, op_flags); if (op != REQ_OP_WRITE && device->state.disk == D_DISKLESS && device->ldev == NULL) /* special case, drbd_md_read() during drbd_adm_attach(): no get_ldev */ diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index c1f816f896a8..df25eecf80af 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -976,12 +976,13 @@ static void drbd_bm_endio(struct bio *bio) static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_hold(local) { - struct bio *bio = bio_alloc_bioset(GFP_NOIO, 1, &drbd_md_io_bio_set); struct drbd_device *device = ctx->device; + unsigned int op = (ctx->flags & BM_AIO_READ) ? REQ_OP_READ : REQ_OP_WRITE; + struct bio *bio = bio_alloc_bioset(device->ldev->md_bdev, 1, op, + GFP_NOIO, &drbd_md_io_bio_set); struct drbd_bitmap *b = device->bitmap; struct page *page; unsigned int len; - unsigned int op = (ctx->flags & BM_AIO_READ) ? REQ_OP_READ : REQ_OP_WRITE; sector_t on_disk_sector = device->ldev->md.md_offset + device->ldev->md.bm_offset; @@ -1006,14 +1007,12 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho bm_store_page_idx(page, page_nr); } else page = b->bm_pages[page_nr]; - bio_set_dev(bio, device->ldev->md_bdev); bio->bi_iter.bi_sector = on_disk_sector; /* bio_add_page of a single page to an empty bio will always succeed, * according to api. Do we want to assert that? */ bio_add_page(bio, page, len, 0); bio->bi_private = ctx; bio->bi_end_io = drbd_bm_endio; - bio_set_op_attrs(bio, op, 0); if (drbd_insert_fault(device, (op == REQ_OP_WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD)) { bio_io_error(bio); diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index f27d5b0f9a0b..4b55e864a0a3 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -27,7 +27,6 @@ #include <linux/major.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> -#include <linux/genhd.h> #include <linux/idr.h> #include <linux/dynamic_debug.h> #include <net/tcp.h> @@ -638,9 +637,6 @@ enum { STATE_SENT, /* Do not change state/UUIDs while this is set */ CALLBACK_PENDING, /* Whether we have a call_usermodehelper(, UMH_WAIT_PROC) * pending, from drbd worker context. - * If set, bdi_write_congested() returns true, - * so shrink_page_list() would not recurse into, - * and potentially deadlock on, this drbd worker. */ DISCONNECT_SENT, diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 6df2539e215b..fa00cf2ea952 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1279,16 +1279,16 @@ static void one_flush_endio(struct bio *bio) static void submit_one_flush(struct drbd_device *device, struct issue_flush_context *ctx) { - struct bio *bio = bio_alloc(GFP_NOIO, 0); + struct bio *bio = bio_alloc(device->ldev->backing_bdev, 0, + REQ_OP_FLUSH | REQ_PREFLUSH, GFP_NOIO); struct one_flush_context *octx = kmalloc(sizeof(*octx), GFP_NOIO); - if (!bio || !octx) { - drbd_warn(device, "Could not allocate a bio, CANNOT ISSUE FLUSH\n"); + + if (!octx) { + drbd_warn(device, "Could not allocate a octx, CANNOT ISSUE FLUSH\n"); /* FIXME: what else can I do now? disconnecting or detaching * really does not help to improve the state of the world, either. */ - kfree(octx); - if (bio) - bio_put(bio); + bio_put(bio); ctx->error = -ENOMEM; put_ldev(device); @@ -1298,10 +1298,8 @@ static void submit_one_flush(struct drbd_device *device, struct issue_flush_cont octx->device = device; octx->ctx = ctx; - bio_set_dev(bio, device->ldev->backing_bdev); bio->bi_private = octx; bio->bi_end_io = one_flush_endio; - bio->bi_opf = REQ_OP_FLUSH | REQ_PREFLUSH; device->flush_jif = jiffies; set_bit(FLUSH_PENDING, &device->flags); @@ -1646,7 +1644,6 @@ int drbd_submit_peer_request(struct drbd_device *device, unsigned data_size = peer_req->i.size; unsigned n_bios = 0; unsigned nr_pages = (data_size + PAGE_SIZE -1) >> PAGE_SHIFT; - int err = -ENOMEM; /* TRIM/DISCARD: for now, always use the helper function * blkdev_issue_zeroout(..., discard=true). @@ -1687,15 +1684,10 @@ int drbd_submit_peer_request(struct drbd_device *device, * generated bio, but a bio allocated on behalf of the peer. */ next_bio: - bio = bio_alloc(GFP_NOIO, nr_pages); - if (!bio) { - drbd_err(device, "submit_ee: Allocation of a bio failed (nr_pages=%u)\n", nr_pages); - goto fail; - } + bio = bio_alloc(device->ldev->backing_bdev, nr_pages, op | op_flags, + GFP_NOIO); /* > peer_req->i.sector, unless this is the first bio */ bio->bi_iter.bi_sector = sector; - bio_set_dev(bio, device->ldev->backing_bdev); - bio_set_op_attrs(bio, op, op_flags); bio->bi_private = peer_req; bio->bi_end_io = drbd_peer_request_endio; @@ -1726,14 +1718,6 @@ next_bio: drbd_submit_bio_noacct(device, fault_type, bio); } while (bios); return 0; - -fail: - while (bios) { - bio = bios; - bios = bios->bi_next; - bio_put(bio); - } - return err; } static void drbd_remove_epoch_entry_interval(struct drbd_device *device, @@ -2033,10 +2017,10 @@ static int recv_dless_read(struct drbd_peer_device *peer_device, struct drbd_req D_ASSERT(peer_device->device, sector == bio->bi_iter.bi_sector); bio_for_each_segment(bvec, bio, iter) { - void *mapped = kmap(bvec.bv_page) + bvec.bv_offset; + void *mapped = bvec_kmap_local(&bvec); expect = min_t(int, data_size, bvec.bv_len); err = drbd_recv_all_warn(peer_device->connection, mapped, expect); - kunmap(bvec.bv_page); + kunmap_local(mapped); if (err) return err; data_size -= expect; diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 3235532ae077..2f608525a879 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -30,7 +30,8 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio return NULL; memset(req, 0, sizeof(*req)); - req->private_bio = bio_clone_fast(bio_src, GFP_NOIO, &drbd_io_bio_set); + req->private_bio = bio_alloc_clone(device->ldev->backing_bdev, bio_src, + GFP_NOIO, &drbd_io_bio_set); req->private_bio->bi_private = req; req->private_bio->bi_end_io = drbd_request_endio; @@ -909,8 +910,7 @@ static bool remote_due_to_read_balancing(struct drbd_device *device, sector_t se switch (rbm) { case RB_CONGESTED_REMOTE: - return bdi_read_congested( - device->ldev->backing_bdev->bd_disk->bdi); + return 0; case RB_LEAST_PENDING: return atomic_read(&device->local_cnt) > atomic_read(&device->ap_pending_cnt) + atomic_read(&device->rs_pending_cnt); @@ -1151,8 +1151,6 @@ drbd_submit_req_private_bio(struct drbd_request *req) else type = DRBD_FAULT_DT_RD; - bio_set_dev(bio, device->ldev->backing_bdev); - /* State may have changed since we grabbed our reference on the * ->ldev member. Double check, and short-circuit to endio. * In case the last activity log transaction failed to get on diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 64563bfdf0da..1b48c8172a07 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -326,9 +326,9 @@ void drbd_csum_bio(struct crypto_shash *tfm, struct bio *bio, void *digest) bio_for_each_segment(bvec, bio, iter) { u8 *src; - src = kmap_atomic(bvec.bv_page); - crypto_shash_update(desc, src + bvec.bv_offset, bvec.bv_len); - kunmap_atomic(src); + src = bvec_kmap_local(&bvec); + crypto_shash_update(desc, src, bvec.bv_len); + kunmap_local(src); /* REQ_OP_WRITE_SAME has only one segment, * checksum the payload only once. */ @@ -1523,9 +1523,9 @@ int w_restart_disk_io(struct drbd_work *w, int cancel) if (bio_data_dir(req->master_bio) == WRITE && req->rq_state & RQ_IN_ACT_LOG) drbd_al_begin_io(device, &req->i); - req->private_bio = bio_clone_fast(req->master_bio, GFP_NOIO, + req->private_bio = bio_alloc_clone(device->ldev->backing_bdev, + req->master_bio, GFP_NOIO, &drbd_io_bio_set); - bio_set_dev(req->private_bio, device->ldev->backing_bdev); req->private_bio->bi_private = req; req->private_bio->bi_end_io = drbd_request_endio; submit_bio_noacct(req->private_bio); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index e611411a934c..8c647532e3ce 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -2485,11 +2485,9 @@ static void copy_buffer(int ssize, int max_sector, int max_sector_2) } if (CT(raw_cmd->cmd[COMMAND]) == FD_READ) - memcpy_to_page(bv.bv_page, bv.bv_offset, dma_buffer, - size); + memcpy_to_bvec(&bv, dma_buffer); else - memcpy_from_page(dma_buffer, bv.bv_page, bv.bv_offset, - size); + memcpy_from_bvec(dma_buffer, &bv); remaining -= size; dma_buffer += size; @@ -4129,15 +4127,13 @@ static int __floppy_read_block_0(struct block_device *bdev, int drive) cbdata.drive = drive; - bio_init(&bio, &bio_vec, 1); - bio_set_dev(&bio, bdev); + bio_init(&bio, bdev, &bio_vec, 1, REQ_OP_READ); bio_add_page(&bio, page, block_size(bdev), 0); bio.bi_iter.bi_sector = 0; bio.bi_flags |= (1 << BIO_QUIET); bio.bi_private = &cbdata; bio.bi_end_io = floppy_rb0_cb; - bio_set_op_attrs(&bio, REQ_OP_READ, 0); init_completion(&cbdata.complete); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 01cbbfc4e9e2..3e636a75c83a 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -79,12 +79,14 @@ #include <linux/ioprio.h> #include <linux/blk-cgroup.h> #include <linux/sched/mm.h> +#include <linux/statfs.h> #include "loop.h" #include <linux/uaccess.h> #define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ) +#define LOOP_DEFAULT_HW_Q_DEPTH (128) static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_ctl_mutex); @@ -308,12 +310,11 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, * a.k.a. discard/zerorange. */ struct file *file = lo->lo_backing_file; - struct request_queue *q = lo->lo_queue; int ret; mode |= FALLOC_FL_KEEP_SIZE; - if (!blk_queue_discard(q)) { + if (!blk_queue_discard(lo->lo_queue)) { ret = -EOPNOTSUPP; goto out; } @@ -327,8 +328,7 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, static int lo_req_flush(struct loop_device *lo, struct request *rq) { - struct file *file = lo->lo_backing_file; - int ret = vfs_fsync(file, 0); + int ret = vfs_fsync(lo->lo_backing_file, 0); if (unlikely(ret && ret != -EINVAL)) ret = -EIO; @@ -680,33 +680,33 @@ static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf) static ssize_t loop_attr_offset_show(struct loop_device *lo, char *buf) { - return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_offset); + return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_offset); } static ssize_t loop_attr_sizelimit_show(struct loop_device *lo, char *buf) { - return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit); + return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit); } static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf) { int autoclear = (lo->lo_flags & LO_FLAGS_AUTOCLEAR); - return sprintf(buf, "%s\n", autoclear ? "1" : "0"); + return sysfs_emit(buf, "%s\n", autoclear ? "1" : "0"); } static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf) { int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN); - return sprintf(buf, "%s\n", partscan ? "1" : "0"); + return sysfs_emit(buf, "%s\n", partscan ? "1" : "0"); } static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf) { int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO); - return sprintf(buf, "%s\n", dio ? "1" : "0"); + return sysfs_emit(buf, "%s\n", dio ? "1" : "0"); } LOOP_ATTR_RO(backing_file); @@ -774,8 +774,13 @@ static void loop_config_discard(struct loop_device *lo) granularity = 0; } else { + struct kstatfs sbuf; + max_discard_sectors = UINT_MAX >> 9; - granularity = inode->i_sb->s_blocksize; + if (!vfs_statfs(&file->f_path, &sbuf)) + granularity = sbuf.f_bsize; + else + max_discard_sectors = 0; } if (max_discard_sectors) { @@ -1082,7 +1087,7 @@ out_putf: return error; } -static void __loop_clr_fd(struct loop_device *lo) +static void __loop_clr_fd(struct loop_device *lo, bool release) { struct file *filp; gfp_t gfp = lo->old_gfp_mask; @@ -1144,6 +1149,8 @@ static void __loop_clr_fd(struct loop_device *lo) /* let user-space know about this change */ kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); mapping_set_gfp_mask(filp->f_mapping, gfp); + /* This is safe: open() is still holding a reference. */ + module_put(THIS_MODULE); blk_mq_unfreeze_queue(lo->lo_queue); disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE); @@ -1151,52 +1158,44 @@ static void __loop_clr_fd(struct loop_device *lo) if (lo->lo_flags & LO_FLAGS_PARTSCAN) { int err; - mutex_lock(&lo->lo_disk->open_mutex); + /* + * open_mutex has been held already in release path, so don't + * acquire it if this function is called in such case. + * + * If the reread partition isn't from release path, lo_refcnt + * must be at least one and it can only become zero when the + * current holder is released. + */ + if (!release) + mutex_lock(&lo->lo_disk->open_mutex); err = bdev_disk_changed(lo->lo_disk, false); - mutex_unlock(&lo->lo_disk->open_mutex); + if (!release) + mutex_unlock(&lo->lo_disk->open_mutex); if (err) pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", __func__, lo->lo_number, err); /* Device is gone, no point in returning error */ } + /* + * lo->lo_state is set to Lo_unbound here after above partscan has + * finished. There cannot be anybody else entering __loop_clr_fd() as + * Lo_rundown state protects us from all the other places trying to + * change the 'lo' device. + */ lo->lo_flags = 0; if (!part_shift) lo->lo_disk->flags |= GENHD_FL_NO_PART; - - fput(filp); -} - -static void loop_rundown_completed(struct loop_device *lo) -{ mutex_lock(&lo->lo_mutex); lo->lo_state = Lo_unbound; mutex_unlock(&lo->lo_mutex); - module_put(THIS_MODULE); -} -static void loop_rundown_workfn(struct work_struct *work) -{ - struct loop_device *lo = container_of(work, struct loop_device, - rundown_work); - struct block_device *bdev = lo->lo_device; - struct gendisk *disk = lo->lo_disk; - - __loop_clr_fd(lo); - kobject_put(&bdev->bd_device.kobj); - module_put(disk->fops->owner); - loop_rundown_completed(lo); -} - -static void loop_schedule_rundown(struct loop_device *lo) -{ - struct block_device *bdev = lo->lo_device; - struct gendisk *disk = lo->lo_disk; - - __module_get(disk->fops->owner); - kobject_get(&bdev->bd_device.kobj); - INIT_WORK(&lo->rundown_work, loop_rundown_workfn); - queue_work(system_long_wq, &lo->rundown_work); + /* + * Need not hold lo_mutex to fput backing file. Calling fput holding + * lo_mutex triggers a circular lock dependency possibility warning as + * fput can take open_mutex which is usually taken before lo_mutex. + */ + fput(filp); } static int loop_clr_fd(struct loop_device *lo) @@ -1228,8 +1227,7 @@ static int loop_clr_fd(struct loop_device *lo) lo->lo_state = Lo_rundown; mutex_unlock(&lo->lo_mutex); - __loop_clr_fd(lo); - loop_rundown_completed(lo); + __loop_clr_fd(lo, false); return 0; } @@ -1262,7 +1260,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) { /* If any pages were dirtied after invalidate_bdev(), try again */ err = -EAGAIN; - pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", + pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n", __func__, lo->lo_number, lo->lo_file_name, lo->lo_device->bd_inode->i_mapping->nrpages); goto out_unfreeze; @@ -1482,7 +1480,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) /* invalidate_bdev should have truncated all the pages */ if (lo->lo_device->bd_inode->i_mapping->nrpages) { err = -EAGAIN; - pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", + pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n", __func__, lo->lo_number, lo->lo_file_name, lo->lo_device->bd_inode->i_mapping->nrpages); goto out_unfreeze; @@ -1754,7 +1752,7 @@ static void lo_release(struct gendisk *disk, fmode_t mode) * In autoclear mode, stop the loop thread * and remove configuration after last close. */ - loop_schedule_rundown(lo); + __loop_clr_fd(lo, true); return; } else if (lo->lo_state == Lo_bound) { /* @@ -1787,6 +1785,24 @@ module_param(max_loop, int, 0444); MODULE_PARM_DESC(max_loop, "Maximum number of loop devices"); module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device"); + +static int hw_queue_depth = LOOP_DEFAULT_HW_Q_DEPTH; + +static int loop_set_hw_queue_depth(const char *s, const struct kernel_param *p) +{ + int ret = kstrtoint(s, 10, &hw_queue_depth); + + return (ret || (hw_queue_depth < 1)) ? -EINVAL : 0; +} + +static const struct kernel_param_ops loop_hw_qdepth_param_ops = { + .set = loop_set_hw_queue_depth, + .get = param_get_int, +}; + +device_param_cb(hw_queue_depth, &loop_hw_qdepth_param_ops, &hw_queue_depth, 0444); +MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 128"); + MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR); @@ -1981,7 +1997,7 @@ static int loop_add(int i) lo->tag_set.ops = &loop_mq_ops; lo->tag_set.nr_hw_queues = 1; - lo->tag_set.queue_depth = 128; + lo->tag_set.queue_depth = hw_queue_depth; lo->tag_set.numa_node = NUMA_NO_NODE; lo->tag_set.cmd_size = sizeof(struct loop_cmd); lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING | @@ -2075,6 +2091,7 @@ static void loop_remove(struct loop_device *lo) del_gendisk(lo->lo_disk); blk_cleanup_disk(lo->lo_disk); blk_mq_free_tag_set(&lo->tag_set); + mutex_lock(&loop_ctl_mutex); idr_remove(&loop_index_idr, lo->lo_number); mutex_unlock(&loop_ctl_mutex); diff --git a/drivers/block/loop.h b/drivers/block/loop.h index 918a7a2dc025..082d4b6bfc6a 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -56,7 +56,6 @@ struct loop_device { struct gendisk *lo_disk; struct mutex lo_mutex; bool idr_visible; - struct work_struct rundown_work; }; struct loop_cmd { diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index e6005c232328..4fbaf0b4958b 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -19,7 +19,6 @@ #include <linux/compat.h> #include <linux/fs.h> #include <linux/module.h> -#include <linux/genhd.h> #include <linux/blkdev.h> #include <linux/blk-mq.h> #include <linux/bio.h> @@ -161,9 +160,7 @@ static bool mtip_check_surprise_removal(struct driver_data *dd) static struct mtip_cmd *mtip_cmd_from_tag(struct driver_data *dd, unsigned int tag) { - struct blk_mq_hw_ctx *hctx = dd->queue->queue_hw_ctx[0]; - - return blk_mq_rq_to_pdu(blk_mq_tag_to_rq(hctx->tags, tag)); + return blk_mq_rq_to_pdu(blk_mq_tag_to_rq(dd->tags.tags[0], tag)); } /* @@ -4112,7 +4109,7 @@ static void mtip_pci_remove(struct pci_dev *pdev) "Completion workers still active!\n"); } - blk_set_queue_dying(dd->queue); + blk_mark_disk_dead(dd->disk); set_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag); /* Clean up the block layer. */ diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index 88f4206310e4..6816beb45352 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -15,7 +15,6 @@ #include <linux/rwsem.h> #include <linux/ata.h> #include <linux/interrupt.h> -#include <linux/genhd.h> /* Offset of Subsystem Device ID in pci confoguration space */ #define PCI_SUBSYSTEM_DEVICEID 0x2E diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 13004beb48ca..05b1120e6623 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -431,9 +431,10 @@ static ssize_t nullb_device_power_store(struct config_item *item, if (!dev->power && newp) { if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags)) return count; - if (null_add_dev(dev)) { + ret = null_add_dev(dev); + if (ret) { clear_bit(NULLB_DEV_FL_UP, &dev->flags); - return -ENOMEM; + return ret; } set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags); @@ -719,26 +720,25 @@ static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq) return NULL; } -static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, int can_wait) +static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, struct bio *bio) { struct nullb_cmd *cmd; DEFINE_WAIT(wait); - cmd = __alloc_cmd(nq); - if (cmd || !can_wait) - return cmd; - do { - prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE); + /* + * This avoids multiple return statements, multiple calls to + * __alloc_cmd() and a fast path call to prepare_to_wait(). + */ cmd = __alloc_cmd(nq); - if (cmd) - break; - + if (cmd) { + cmd->bio = bio; + return cmd; + } + prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE); io_schedule(); + finish_wait(&nq->wait, &wait); } while (1); - - finish_wait(&nq->wait, &wait); - return cmd; } static void end_cmd(struct nullb_cmd *cmd) @@ -777,24 +777,22 @@ static void null_complete_rq(struct request *rq) end_cmd(blk_mq_rq_to_pdu(rq)); } -static struct nullb_page *null_alloc_page(gfp_t gfp_flags) +static struct nullb_page *null_alloc_page(void) { struct nullb_page *t_page; - t_page = kmalloc(sizeof(struct nullb_page), gfp_flags); + t_page = kmalloc(sizeof(struct nullb_page), GFP_NOIO); if (!t_page) - goto out; + return NULL; - t_page->page = alloc_pages(gfp_flags, 0); - if (!t_page->page) - goto out_freepage; + t_page->page = alloc_pages(GFP_NOIO, 0); + if (!t_page->page) { + kfree(t_page); + return NULL; + } memset(t_page->bitmap, 0, sizeof(t_page->bitmap)); return t_page; -out_freepage: - kfree(t_page); -out: - return NULL; } static void null_free_page(struct nullb_page *t_page) @@ -932,7 +930,7 @@ static struct nullb_page *null_insert_page(struct nullb *nullb, spin_unlock_irq(&nullb->lock); - t_page = null_alloc_page(GFP_NOIO); + t_page = null_alloc_page(); if (!t_page) goto out_lock; @@ -1476,12 +1474,8 @@ static void null_submit_bio(struct bio *bio) sector_t nr_sectors = bio_sectors(bio); struct nullb *nullb = bio->bi_bdev->bd_disk->private_data; struct nullb_queue *nq = nullb_to_queue(nullb); - struct nullb_cmd *cmd; - - cmd = alloc_cmd(nq, 1); - cmd->bio = bio; - null_handle_cmd(cmd, sector, nr_sectors, bio_op(bio)); + null_handle_cmd(alloc_cmd(nq, bio), sector, nr_sectors, bio_op(bio)); } static bool should_timeout_request(struct request *rq) diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 2b6b70a39e76..e745fc29e55d 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1020,9 +1020,8 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) continue; bio = pkt->r_bios[f]; - bio_reset(bio); + bio_reset(bio, pd->bdev, REQ_OP_READ); bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9); - bio_set_dev(bio, pd->bdev); bio->bi_end_io = pkt_end_io_read; bio->bi_private = pkt; @@ -1034,7 +1033,6 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) BUG(); atomic_inc(&pkt->io_wait); - bio_set_op_attrs(bio, REQ_OP_READ, 0); pkt_queue_bio(pd, bio); frames_read++; } @@ -1235,9 +1233,8 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) { int f; - bio_reset(pkt->w_bio); + bio_reset(pkt->w_bio, pd->bdev, REQ_OP_WRITE); pkt->w_bio->bi_iter.bi_sector = pkt->sector; - bio_set_dev(pkt->w_bio, pd->bdev); pkt->w_bio->bi_end_io = pkt_end_io_packet_write; pkt->w_bio->bi_private = pkt; @@ -1270,7 +1267,6 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) /* Start the write request */ atomic_set(&pkt->io_wait, 1); - bio_set_op_attrs(pkt->w_bio, REQ_OP_WRITE, 0); pkt_queue_bio(pd, pkt->w_bio); } @@ -2298,12 +2294,12 @@ static void pkt_end_io_read_cloned(struct bio *bio) static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio) { - struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, &pkt_bio_set); + struct bio *cloned_bio = + bio_alloc_clone(pd->bdev, bio, GFP_NOIO, &pkt_bio_set); struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO); psd->pd = pd; psd->bio = bio; - bio_set_dev(cloned_bio, pd->bdev); cloned_bio->bi_private = psd; cloned_bio->bi_end_io = pkt_end_io_read_cloned; pd->stats.secs_r += bio_sectors(bio); @@ -2404,18 +2400,11 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) static void pkt_submit_bio(struct bio *bio) { - struct pktcdvd_device *pd; - char b[BDEVNAME_SIZE]; + struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata; struct bio *split; blk_queue_split(&bio); - pd = bio->bi_bdev->bd_disk->queue->queuedata; - if (!pd) { - pr_err("%s incorrect request queue\n", bio_devname(bio, b)); - goto end_io; - } - pkt_dbg(2, pd, "start = %6llx stop = %6llx\n", (unsigned long long)bio->bi_iter.bi_sector, (unsigned long long)bio_end_sector(bio)); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 4203cdab8abf..b844432bad20 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -7185,7 +7185,7 @@ static ssize_t do_rbd_remove(struct bus_type *bus, * IO to complete/fail. */ blk_mq_freeze_queue(rbd_dev->disk->queue); - blk_set_queue_dying(rbd_dev->disk->queue); + blk_mark_disk_dead(rbd_dev->disk); } del_gendisk(rbd_dev->disk); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index c08971de369f..2f378684b735 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -23,7 +23,6 @@ MODULE_LICENSE("GPL"); static int rnbd_client_major; static DEFINE_IDA(index_ida); -static DEFINE_MUTEX(ida_lock); static DEFINE_MUTEX(sess_lock); static LIST_HEAD(sess_list); @@ -55,9 +54,7 @@ static void rnbd_clt_put_dev(struct rnbd_clt_dev *dev) if (!refcount_dec_and_test(&dev->refcount)) return; - mutex_lock(&ida_lock); - ida_simple_remove(&index_ida, dev->clt_device_id); - mutex_unlock(&ida_lock); + ida_free(&index_ida, dev->clt_device_id); kfree(dev->hw_queues); kfree(dev->pathname); rnbd_clt_put_sess(dev->sess); @@ -87,7 +84,6 @@ static int rnbd_clt_set_dev_attr(struct rnbd_clt_dev *dev, dev->discard_granularity = le32_to_cpu(rsp->discard_granularity); dev->discard_alignment = le32_to_cpu(rsp->discard_alignment); dev->secure_discard = le16_to_cpu(rsp->secure_discard); - dev->rotational = rsp->rotational; dev->wc = !!(rsp->cache_policy & RNBD_WRITEBACK); dev->fua = !!(rsp->cache_policy & RNBD_FUA); @@ -1262,9 +1258,9 @@ find_and_get_or_create_sess(const char *sessname, struct rtrs_clt_ops rtrs_ops; sess = find_or_create_sess(sessname, &first); - if (sess == ERR_PTR(-ENOMEM)) + if (sess == ERR_PTR(-ENOMEM)) { return ERR_PTR(-ENOMEM); - else if ((nr_poll_queues && !first) || (!nr_poll_queues && sess->nr_poll_queues)) { + } else if ((nr_poll_queues && !first) || (!nr_poll_queues && sess->nr_poll_queues)) { /* * A device MUST have its own session to use the polling-mode. * It must fail to map new device with the same session. @@ -1343,7 +1339,7 @@ static inline void rnbd_init_hw_queue(struct rnbd_clt_dev *dev, static void rnbd_init_mq_hw_queues(struct rnbd_clt_dev *dev) { - int i; + unsigned long i; struct blk_mq_hw_ctx *hctx; struct rnbd_queue *q; @@ -1410,8 +1406,10 @@ static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) dev->read_only = false; } - if (!dev->rotational) - blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue); + /* + * Network device does not need rotational + */ + blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue); err = add_disk(dev->gd); if (err) blk_cleanup_disk(dev->gd); @@ -1459,10 +1457,8 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, goto out_alloc; } - mutex_lock(&ida_lock); - ret = ida_simple_get(&index_ida, 0, 1 << (MINORBITS - RNBD_PART_BITS), - GFP_KERNEL); - mutex_unlock(&ida_lock); + ret = ida_alloc_max(&index_ida, 1 << (MINORBITS - RNBD_PART_BITS), + GFP_KERNEL); if (ret < 0) { pr_err("Failed to initialize device '%s' from session %s, allocating idr failed, err: %d\n", pathname, sess->sessname, ret); @@ -1610,13 +1606,13 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname, } rnbd_clt_info(dev, - "map_device: Device mapped as %s (nsectors: %zu, logical_block_size: %d, physical_block_size: %d, max_write_same_sectors: %d, max_discard_sectors: %d, discard_granularity: %d, discard_alignment: %d, secure_discard: %d, max_segments: %d, max_hw_sectors: %d, rotational: %d, wc: %d, fua: %d)\n", + "map_device: Device mapped as %s (nsectors: %zu, logical_block_size: %d, physical_block_size: %d, max_write_same_sectors: %d, max_discard_sectors: %d, discard_granularity: %d, discard_alignment: %d, secure_discard: %d, max_segments: %d, max_hw_sectors: %d, wc: %d, fua: %d)\n", dev->gd->disk_name, dev->nsectors, dev->logical_block_size, dev->physical_block_size, dev->max_write_same_sectors, dev->max_discard_sectors, dev->discard_granularity, dev->discard_alignment, dev->secure_discard, dev->max_segments, - dev->max_hw_sectors, dev->rotational, dev->wc, dev->fua); + dev->max_hw_sectors, dev->wc, dev->fua); mutex_unlock(&dev->lock); rnbd_clt_put_sess(sess); diff --git a/drivers/block/rnbd/rnbd-clt.h b/drivers/block/rnbd/rnbd-clt.h index 0c2cae7f39b9..62bf7c3fa63c 100644 --- a/drivers/block/rnbd/rnbd-clt.h +++ b/drivers/block/rnbd/rnbd-clt.h @@ -118,7 +118,6 @@ struct rnbd_clt_dev { enum rnbd_access_mode access_mode; u32 nr_poll_queues; bool read_only; - bool rotational; bool wc; bool fua; u32 max_hw_sectors; diff --git a/drivers/block/rnbd/rnbd-proto.h b/drivers/block/rnbd/rnbd-proto.h index de5d5a8df81d..c4a68b3a1cbe 100644 --- a/drivers/block/rnbd/rnbd-proto.h +++ b/drivers/block/rnbd/rnbd-proto.h @@ -128,7 +128,7 @@ enum rnbd_cache_policy { * @logical_block_size: logical block size device supports in bytes * @max_segments: max segments hardware support in one transfer * @secure_discard: supports secure discard - * @rotation: is a rotational disc? + * @obsolete_rotational: obsolete, not in used. * @cache_policy: support write-back caching or FUA? */ struct rnbd_msg_open_rsp { @@ -144,7 +144,7 @@ struct rnbd_msg_open_rsp { __le16 logical_block_size; __le16 max_segments; __le16 secure_discard; - u8 rotational; + u8 obsolete_rotational; u8 cache_policy; u8 reserved[10]; }; diff --git a/drivers/block/rnbd/rnbd-srv-dev.c b/drivers/block/rnbd/rnbd-srv-dev.c index b241a099aeae..c5d0a0391165 100644 --- a/drivers/block/rnbd/rnbd-srv-dev.c +++ b/drivers/block/rnbd/rnbd-srv-dev.c @@ -12,8 +12,7 @@ #include "rnbd-srv-dev.h" #include "rnbd-log.h" -struct rnbd_dev *rnbd_dev_open(const char *path, fmode_t flags, - struct bio_set *bs) +struct rnbd_dev *rnbd_dev_open(const char *path, fmode_t flags) { struct rnbd_dev *dev; int ret; @@ -30,7 +29,6 @@ struct rnbd_dev *rnbd_dev_open(const char *path, fmode_t flags, dev->blk_open_flags = flags; bdevname(dev->bdev, dev->name); - dev->ibd_bio_set = bs; return dev; @@ -44,60 +42,3 @@ void rnbd_dev_close(struct rnbd_dev *dev) blkdev_put(dev->bdev, dev->blk_open_flags); kfree(dev); } - -void rnbd_dev_bi_end_io(struct bio *bio) -{ - struct rnbd_dev_blk_io *io = bio->bi_private; - - rnbd_endio(io->priv, blk_status_to_errno(bio->bi_status)); - bio_put(bio); -} - -/** - * rnbd_bio_map_kern - map kernel address into bio - * @data: pointer to buffer to map - * @bs: bio_set to use. - * @len: length in bytes - * @gfp_mask: allocation flags for bio allocation - * - * Map the kernel address into a bio suitable for io to a block - * device. Returns an error pointer in case of error. - */ -struct bio *rnbd_bio_map_kern(void *data, struct bio_set *bs, - unsigned int len, gfp_t gfp_mask) -{ - unsigned long kaddr = (unsigned long)data; - unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; - unsigned long start = kaddr >> PAGE_SHIFT; - const int nr_pages = end - start; - int offset, i; - struct bio *bio; - - bio = bio_alloc_bioset(gfp_mask, nr_pages, bs); - if (!bio) - return ERR_PTR(-ENOMEM); - - offset = offset_in_page(kaddr); - for (i = 0; i < nr_pages; i++) { - unsigned int bytes = PAGE_SIZE - offset; - - if (len <= 0) - break; - - if (bytes > len) - bytes = len; - - if (bio_add_page(bio, virt_to_page(data), bytes, - offset) < bytes) { - /* we don't support partial mappings */ - bio_put(bio); - return ERR_PTR(-EINVAL); - } - - data += bytes; - len -= bytes; - offset = 0; - } - - return bio; -} diff --git a/drivers/block/rnbd/rnbd-srv-dev.h b/drivers/block/rnbd/rnbd-srv-dev.h index 0eb23850afb9..2c3df02b5e8e 100644 --- a/drivers/block/rnbd/rnbd-srv-dev.h +++ b/drivers/block/rnbd/rnbd-srv-dev.h @@ -14,25 +14,16 @@ struct rnbd_dev { struct block_device *bdev; - struct bio_set *ibd_bio_set; fmode_t blk_open_flags; char name[BDEVNAME_SIZE]; }; -struct rnbd_dev_blk_io { - struct rnbd_dev *dev; - void *priv; - /* have to be last member for front_pad usage of bioset_init */ - struct bio bio; -}; - /** * rnbd_dev_open() - Open a device + * @path: path to open * @flags: open flags - * @bs: bio_set to use during block io, */ -struct rnbd_dev *rnbd_dev_open(const char *path, fmode_t flags, - struct bio_set *bs); +struct rnbd_dev *rnbd_dev_open(const char *path, fmode_t flags); /** * rnbd_dev_close() - Close a device @@ -41,11 +32,6 @@ void rnbd_dev_close(struct rnbd_dev *dev); void rnbd_endio(void *priv, int error); -void rnbd_dev_bi_end_io(struct bio *bio); - -struct bio *rnbd_bio_map_kern(void *data, struct bio_set *bs, - unsigned int len, gfp_t gfp_mask); - static inline int rnbd_dev_get_max_segs(const struct rnbd_dev *dev) { return queue_max_segments(bdev_get_queue(dev->bdev)); diff --git a/drivers/block/rnbd/rnbd-srv-sysfs.c b/drivers/block/rnbd/rnbd-srv-sysfs.c index 4db98e0e76f0..feaa76c5a342 100644 --- a/drivers/block/rnbd/rnbd-srv-sysfs.c +++ b/drivers/block/rnbd/rnbd-srv-sysfs.c @@ -13,7 +13,6 @@ #include <linux/kobject.h> #include <linux/sysfs.h> #include <linux/stat.h> -#include <linux/genhd.h> #include <linux/list.h> #include <linux/moduleparam.h> #include <linux/device.h> diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index 1ee808fc600c..6499efae5c43 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -114,6 +114,12 @@ rnbd_get_sess_dev(int dev_id, struct rnbd_srv_session *srv_sess) return sess_dev; } +static void rnbd_dev_bi_end_io(struct bio *bio) +{ + rnbd_endio(bio->bi_private, blk_status_to_errno(bio->bi_status)); + bio_put(bio); +} + static int process_rdma(struct rnbd_srv_session *srv_sess, struct rtrs_srv_op *id, void *data, u32 datalen, const void *usr, size_t usrlen) @@ -123,7 +129,6 @@ static int process_rdma(struct rnbd_srv_session *srv_sess, struct rnbd_srv_sess_dev *sess_dev; u32 dev_id; int err; - struct rnbd_dev_blk_io *io; struct bio *bio; short prio; @@ -144,33 +149,29 @@ static int process_rdma(struct rnbd_srv_session *srv_sess, priv->sess_dev = sess_dev; priv->id = id; - /* Generate bio with pages pointing to the rdma buffer */ - bio = rnbd_bio_map_kern(data, sess_dev->rnbd_dev->ibd_bio_set, datalen, GFP_KERNEL); - if (IS_ERR(bio)) { - err = PTR_ERR(bio); - rnbd_srv_err(sess_dev, "Failed to generate bio, err: %d\n", err); - goto sess_dev_put; + bio = bio_alloc(sess_dev->rnbd_dev->bdev, 1, + rnbd_to_bio_flags(le32_to_cpu(msg->rw)), GFP_KERNEL); + if (bio_add_page(bio, virt_to_page(data), datalen, + offset_in_page(data)) != datalen) { + rnbd_srv_err(sess_dev, "Failed to map data to bio\n"); + err = -EINVAL; + goto bio_put; } - io = container_of(bio, struct rnbd_dev_blk_io, bio); - io->dev = sess_dev->rnbd_dev; - io->priv = priv; - bio->bi_end_io = rnbd_dev_bi_end_io; - bio->bi_private = io; - bio->bi_opf = rnbd_to_bio_flags(le32_to_cpu(msg->rw)); + bio->bi_private = priv; bio->bi_iter.bi_sector = le64_to_cpu(msg->sector); bio->bi_iter.bi_size = le32_to_cpu(msg->bi_size); prio = srv_sess->ver < RNBD_PROTO_VER_MAJOR || usrlen < sizeof(*msg) ? 0 : le16_to_cpu(msg->prio); bio_set_prio(bio, prio); - bio_set_dev(bio, sess_dev->rnbd_dev->bdev); submit_bio(bio); return 0; -sess_dev_put: +bio_put: + bio_put(bio); rnbd_put_sess_dev(sess_dev); err: kfree(priv); @@ -251,7 +252,6 @@ static void destroy_sess(struct rnbd_srv_session *srv_sess) out: xa_destroy(&srv_sess->index_idr); - bioset_exit(&srv_sess->sess_bio_set); pr_info("RTRS Session %s disconnected\n", srv_sess->sessname); @@ -280,16 +280,6 @@ static int create_sess(struct rtrs_srv_sess *rtrs) return -ENOMEM; srv_sess->queue_depth = rtrs_srv_get_queue_depth(rtrs); - err = bioset_init(&srv_sess->sess_bio_set, srv_sess->queue_depth, - offsetof(struct rnbd_dev_blk_io, bio), - BIOSET_NEED_BVECS); - if (err) { - pr_err("Allocating srv_session for path %s failed\n", - pathname); - kfree(srv_sess); - return err; - } - xa_init_flags(&srv_sess->index_idr, XA_FLAGS_ALLOC); INIT_LIST_HEAD(&srv_sess->sess_dev_list); mutex_init(&srv_sess->lock); @@ -568,7 +558,6 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, cpu_to_le32(rnbd_dev_get_discard_alignment(rnbd_dev)); rsp->secure_discard = cpu_to_le16(rnbd_dev_get_secure_discard(rnbd_dev)); - rsp->rotational = !blk_queue_nonrot(q); rsp->cache_policy = 0; if (test_bit(QUEUE_FLAG_WC, &q->queue_flags)) rsp->cache_policy |= RNBD_WRITEBACK; @@ -738,8 +727,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, goto reject; } - rnbd_dev = rnbd_dev_open(full_path, open_flags, - &srv_sess->sess_bio_set); + rnbd_dev = rnbd_dev_open(full_path, open_flags); if (IS_ERR(rnbd_dev)) { pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %ld\n", full_path, srv_sess->sessname, PTR_ERR(rnbd_dev)); diff --git a/drivers/block/rnbd/rnbd-srv.h b/drivers/block/rnbd/rnbd-srv.h index e5604bce123a..be2ae486d407 100644 --- a/drivers/block/rnbd/rnbd-srv.h +++ b/drivers/block/rnbd/rnbd-srv.h @@ -23,7 +23,6 @@ struct rnbd_srv_session { struct rtrs_srv_sess *rtrs; char sessname[NAME_MAX]; int queue_depth; - struct bio_set sess_bio_set; struct xarray index_idr; /* List of struct rnbd_srv_sess_dev */ diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 146d85d80e0e..dd0a1a6fed29 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -9,7 +9,6 @@ #include <linux/types.h> #include <linux/blk-mq.h> #include <linux/hdreg.h> -#include <linux/genhd.h> #include <linux/cdrom.h> #include <linux/slab.h> #include <linux/spinlock.h> diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index c443cd64fc9b..a8bcf3f664af 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -69,16 +69,6 @@ struct virtio_blk { /* Process context for config space updates */ struct work_struct config_work; - /* - * Tracks references from block_device_operations open/release and - * virtio_driver probe/remove so this object can be freed once no - * longer in use. - */ - refcount_t refs; - - /* What host tells us, plus 2 for header & tailer. */ - unsigned int sg_elems; - /* Ida index - used to track minor number allocations. */ int index; @@ -322,8 +312,6 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, blk_status_t status; int err; - BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems); - status = virtblk_setup_cmd(vblk->vdev, req, vbr); if (unlikely(status)) return status; @@ -391,43 +379,6 @@ out: return err; } -static void virtblk_get(struct virtio_blk *vblk) -{ - refcount_inc(&vblk->refs); -} - -static void virtblk_put(struct virtio_blk *vblk) -{ - if (refcount_dec_and_test(&vblk->refs)) { - ida_simple_remove(&vd_index_ida, vblk->index); - mutex_destroy(&vblk->vdev_mutex); - kfree(vblk); - } -} - -static int virtblk_open(struct block_device *bd, fmode_t mode) -{ - struct virtio_blk *vblk = bd->bd_disk->private_data; - int ret = 0; - - mutex_lock(&vblk->vdev_mutex); - - if (vblk->vdev) - virtblk_get(vblk); - else - ret = -ENXIO; - - mutex_unlock(&vblk->vdev_mutex); - return ret; -} - -static void virtblk_release(struct gendisk *disk, fmode_t mode) -{ - struct virtio_blk *vblk = disk->private_data; - - virtblk_put(vblk); -} - /* We provide getgeo only to please some old bootloader/partitioning tools */ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) { @@ -460,11 +411,19 @@ out: return ret; } +static void virtblk_free_disk(struct gendisk *disk) +{ + struct virtio_blk *vblk = disk->private_data; + + ida_simple_remove(&vd_index_ida, vblk->index); + mutex_destroy(&vblk->vdev_mutex); + kfree(vblk); +} + static const struct block_device_operations virtblk_fops = { - .owner = THIS_MODULE, - .open = virtblk_open, - .release = virtblk_release, - .getgeo = virtblk_getgeo, + .owner = THIS_MODULE, + .getgeo = virtblk_getgeo, + .free_disk = virtblk_free_disk, }; static int index_to_minor(int index) @@ -783,20 +742,15 @@ static int virtblk_probe(struct virtio_device *vdev) /* Prevent integer overflows and honor max vq size */ sg_elems = min_t(u32, sg_elems, VIRTIO_BLK_MAX_SG_ELEMS - 2); - /* We need extra sg elements at head and tail. */ - sg_elems += 2; vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL); if (!vblk) { err = -ENOMEM; goto out_free_index; } - /* This reference is dropped in virtblk_remove(). */ - refcount_set(&vblk->refs, 1); mutex_init(&vblk->vdev_mutex); vblk->vdev = vdev; - vblk->sg_elems = sg_elems; INIT_WORK(&vblk->config_work, virtblk_config_changed_work); @@ -853,7 +807,7 @@ static int virtblk_probe(struct virtio_device *vdev) set_disk_ro(vblk->disk, 1); /* We can handle whatever the host told us to handle. */ - blk_queue_max_segments(q, vblk->sg_elems-2); + blk_queue_max_segments(q, sg_elems); /* No real sector limit. */ blk_queue_max_hw_sectors(q, -1U); @@ -925,9 +879,15 @@ static int virtblk_probe(struct virtio_device *vdev) virtio_cread(vdev, struct virtio_blk_config, max_discard_seg, &v); + + /* + * max_discard_seg == 0 is out of spec but we always + * handled it. + */ + if (!v) + v = sg_elems; blk_queue_max_discard_segments(q, - min_not_zero(v, - MAX_DISCARD_SEGMENTS)); + min(v, MAX_DISCARD_SEGMENTS)); blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } @@ -970,7 +930,7 @@ static void virtblk_remove(struct virtio_device *vdev) flush_work(&vblk->config_work); del_gendisk(vblk->disk); - blk_cleanup_disk(vblk->disk); + blk_cleanup_queue(vblk->disk->queue); blk_mq_free_tag_set(&vblk->tag_set); mutex_lock(&vblk->vdev_mutex); @@ -986,7 +946,7 @@ static void virtblk_remove(struct virtio_device *vdev) mutex_unlock(&vblk->vdev_mutex); - virtblk_put(vblk); + put_disk(vblk->disk); } #ifdef CONFIG_PM_SLEEP @@ -1060,7 +1020,7 @@ static struct virtio_driver virtio_blk = { #endif }; -static int __init init(void) +static int __init virtio_blk_init(void) { int error; @@ -1086,14 +1046,14 @@ out_destroy_workqueue: return error; } -static void __exit fini(void) +static void __exit virtio_blk_fini(void) { unregister_virtio_driver(&virtio_blk); unregister_blkdev(major, "virtblk"); destroy_workqueue(virtblk_wq); } -module_init(init); -module_exit(fini); +module_init(virtio_blk_init); +module_exit(virtio_blk_fini); MODULE_DEVICE_TABLE(virtio, id_table); MODULE_DESCRIPTION("Virtio block driver"); diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 14e452896d04..d1e26461a64e 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -1326,16 +1326,13 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring, pages[i]->page, seg[i].nsec << 9, seg[i].offset) == 0)) { - bio = bio_alloc(GFP_KERNEL, bio_max_segs(nseg - i)); - if (unlikely(bio == NULL)) - goto fail_put_bio; - + bio = bio_alloc(preq.bdev, bio_max_segs(nseg - i), + operation | operation_flags, + GFP_KERNEL); biolist[nbio++] = bio; - bio_set_dev(bio, preq.bdev); bio->bi_private = pending_req; bio->bi_end_io = end_block_io_op; bio->bi_iter.bi_sector = preq.sector_number; - bio_set_op_attrs(bio, operation, operation_flags); } preq.sector_number += seg[i].nsec; @@ -1345,15 +1342,11 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring, if (!bio) { BUG_ON(operation_flags != REQ_PREFLUSH); - bio = bio_alloc(GFP_KERNEL, 0); - if (unlikely(bio == NULL)) - goto fail_put_bio; - + bio = bio_alloc(preq.bdev, 0, operation | operation_flags, + GFP_KERNEL); biolist[nbio++] = bio; - bio_set_dev(bio, preq.bdev); bio->bi_private = pending_req; bio->bi_end_io = end_block_io_op; - bio_set_op_attrs(bio, operation, operation_flags); } atomic_set(&pending_req->pendcnt, nbio); @@ -1381,14 +1374,6 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring, free_req(ring, pending_req); msleep(1); /* back off a bit */ return -EIO; - - fail_put_bio: - for (i = 0; i < nbio; i++) - bio_put(biolist[i]); - atomic_set(&pending_req->pendcnt, 1); - __end_block_io_op(pending_req, BLK_STS_RESOURCE); - msleep(1); /* back off a bit */ - return -EIO; } diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 62125fd4af4a..f09040435e2e 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -10,6 +10,7 @@ #include <linux/module.h> #include <linux/kthread.h> +#include <linux/pagemap.h> #include <xen/events.h> #include <xen/grant_table.h> #include "common.h" diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index ccd0dd0c6b83..85fc550508cc 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1288,7 +1288,8 @@ free_shadow: rinfo->ring_ref[i] = GRANT_INVALID_REF; } } - free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE)); + free_pages_exact(rinfo->ring.sring, + info->nr_ring_pages * XEN_PAGE_SIZE); rinfo->ring.sring = NULL; if (rinfo->irq) @@ -1372,9 +1373,15 @@ static int blkif_get_final_status(enum blk_req_status s1, return BLKIF_RSP_OKAY; } -static bool blkif_completion(unsigned long *id, - struct blkfront_ring_info *rinfo, - struct blkif_response *bret) +/* + * Return values: + * 1 response processed. + * 0 missing further responses. + * -1 error while processing. + */ +static int blkif_completion(unsigned long *id, + struct blkfront_ring_info *rinfo, + struct blkif_response *bret) { int i = 0; struct scatterlist *sg; @@ -1397,7 +1404,7 @@ static bool blkif_completion(unsigned long *id, /* Wait the second response if not yet here. */ if (s2->status < REQ_DONE) - return false; + return 0; bret->status = blkif_get_final_status(s->status, s2->status); @@ -1448,42 +1455,43 @@ static bool blkif_completion(unsigned long *id, } /* Add the persistent grant into the list of free grants */ for (i = 0; i < num_grant; i++) { - if (gnttab_query_foreign_access(s->grants_used[i]->gref)) { + if (!gnttab_try_end_foreign_access(s->grants_used[i]->gref)) { /* * If the grant is still mapped by the backend (the * backend has chosen to make this grant persistent) * we add it at the head of the list, so it will be * reused first. */ - if (!info->feature_persistent) - pr_alert_ratelimited("backed has not unmapped grant: %u\n", - s->grants_used[i]->gref); + if (!info->feature_persistent) { + pr_alert("backed has not unmapped grant: %u\n", + s->grants_used[i]->gref); + return -1; + } list_add(&s->grants_used[i]->node, &rinfo->grants); rinfo->persistent_gnts_c++; } else { /* - * If the grant is not mapped by the backend we end the - * foreign access and add it to the tail of the list, - * so it will not be picked again unless we run out of - * persistent grants. + * If the grant is not mapped by the backend we add it + * to the tail of the list, so it will not be picked + * again unless we run out of persistent grants. */ - gnttab_end_foreign_access(s->grants_used[i]->gref, 0, 0UL); s->grants_used[i]->gref = GRANT_INVALID_REF; list_add_tail(&s->grants_used[i]->node, &rinfo->grants); } } if (s->req.operation == BLKIF_OP_INDIRECT) { for (i = 0; i < INDIRECT_GREFS(num_grant); i++) { - if (gnttab_query_foreign_access(s->indirect_grants[i]->gref)) { - if (!info->feature_persistent) - pr_alert_ratelimited("backed has not unmapped grant: %u\n", - s->indirect_grants[i]->gref); + if (!gnttab_try_end_foreign_access(s->indirect_grants[i]->gref)) { + if (!info->feature_persistent) { + pr_alert("backed has not unmapped grant: %u\n", + s->indirect_grants[i]->gref); + return -1; + } list_add(&s->indirect_grants[i]->node, &rinfo->grants); rinfo->persistent_gnts_c++; } else { struct page *indirect_page; - gnttab_end_foreign_access(s->indirect_grants[i]->gref, 0, 0UL); /* * Add the used indirect page back to the list of * available pages for indirect grefs. @@ -1498,7 +1506,7 @@ static bool blkif_completion(unsigned long *id, } } - return true; + return 1; } static irqreturn_t blkif_interrupt(int irq, void *dev_id) @@ -1564,12 +1572,17 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) } if (bret.operation != BLKIF_OP_DISCARD) { + int ret; + /* * We may need to wait for an extra response if the * I/O request is split in 2 */ - if (!blkif_completion(&id, rinfo, &bret)) + ret = blkif_completion(&id, rinfo, &bret); + if (!ret) continue; + if (unlikely(ret < 0)) + goto err; } if (add_id_to_freelist(rinfo, id)) { @@ -1676,8 +1689,7 @@ static int setup_blkring(struct xenbus_device *dev, for (i = 0; i < info->nr_ring_pages; i++) rinfo->ring_ref[i] = GRANT_INVALID_REF; - sring = (struct blkif_sring *)__get_free_pages(GFP_NOIO | __GFP_HIGH, - get_order(ring_size)); + sring = alloc_pages_exact(ring_size, GFP_NOIO); if (!sring) { xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring"); return -ENOMEM; @@ -1687,7 +1699,7 @@ static int setup_blkring(struct xenbus_device *dev, err = xenbus_grant_ring(dev, rinfo->ring.sring, info->nr_ring_pages, gref); if (err < 0) { - free_pages((unsigned long)sring, get_order(ring_size)); + free_pages_exact(sring, ring_size); rinfo->ring.sring = NULL; goto fail; } @@ -2126,7 +2138,7 @@ static void blkfront_closing(struct blkfront_info *info) /* No more blkif_request(). */ blk_mq_stop_hw_queues(info->rq); - blk_set_queue_dying(info->rq); + blk_mark_disk_dead(info->gd); set_capacity(info->gd, 0); for_each_rinfo(info, rinfo, i) { @@ -2521,6 +2533,7 @@ static void purge_persistent_grants(struct blkfront_info *info) for_each_rinfo(info, rinfo, i) { struct grant *gnt_list_entry, *tmp; + LIST_HEAD(grants); spin_lock_irqsave(&rinfo->ring_lock, flags); @@ -2532,16 +2545,17 @@ static void purge_persistent_grants(struct blkfront_info *info) list_for_each_entry_safe(gnt_list_entry, tmp, &rinfo->grants, node) { if (gnt_list_entry->gref == GRANT_INVALID_REF || - gnttab_query_foreign_access(gnt_list_entry->gref)) + !gnttab_try_end_foreign_access(gnt_list_entry->gref)) continue; list_del(&gnt_list_entry->node); - gnttab_end_foreign_access(gnt_list_entry->gref, 0, 0UL); rinfo->persistent_gnts_c--; gnt_list_entry->gref = GRANT_INVALID_REF; - list_add_tail(&gnt_list_entry->node, &rinfo->grants); + list_add_tail(&gnt_list_entry->node, &grants); } + list_splice_tail(&grants, &rinfo->grants); + spin_unlock_irqrestore(&rinfo->ring_lock, flags); } } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index cb253d80d72b..e9474b02012d 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -22,7 +22,6 @@ #include <linux/blkdev.h> #include <linux/buffer_head.h> #include <linux/device.h> -#include <linux/genhd.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/backing-dev.h> @@ -617,24 +616,21 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, { struct bio *bio; - bio = bio_alloc(GFP_NOIO, 1); + bio = bio_alloc(zram->bdev, 1, parent ? parent->bi_opf : REQ_OP_READ, + GFP_NOIO); if (!bio) return -ENOMEM; bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); - bio_set_dev(bio, zram->bdev); if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) { bio_put(bio); return -EIO; } - if (!parent) { - bio->bi_opf = REQ_OP_READ; + if (!parent) bio->bi_end_io = zram_page_end_io; - } else { - bio->bi_opf = parent->bi_opf; + else bio_chain(bio, parent); - } submit_bio(bio); return 1; @@ -747,10 +743,9 @@ static ssize_t writeback_store(struct device *dev, continue; } - bio_init(&bio, &bio_vec, 1); - bio_set_dev(&bio, zram->bdev); + bio_init(&bio, zram->bdev, &bio_vec, 1, + REQ_OP_WRITE | REQ_SYNC); bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9); - bio.bi_opf = REQ_OP_WRITE | REQ_SYNC; bio_add_page(&bio, bvec.bv_page, bvec.bv_len, bvec.bv_offset); @@ -1336,12 +1331,10 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, goto out; if (is_partial_io(bvec)) { - void *dst = kmap_atomic(bvec->bv_page); void *src = kmap_atomic(page); - memcpy(dst + bvec->bv_offset, src + offset, bvec->bv_len); + memcpy_to_bvec(bvec, src + offset); kunmap_atomic(src); - kunmap_atomic(dst); } out: if (is_partial_io(bvec)) @@ -1472,7 +1465,6 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, { int ret; struct page *page = NULL; - void *src; struct bio_vec vec; vec = *bvec; @@ -1490,11 +1482,9 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, if (ret) goto out; - src = kmap_atomic(bvec->bv_page); dst = kmap_atomic(page); - memcpy(dst + offset, src + bvec->bv_offset, bvec->bv_len); + memcpy_from_bvec(dst + offset, bvec); kunmap_atomic(dst); - kunmap_atomic(src); vec.bv_page = page; vec.bv_len = PAGE_SIZE; |