diff options
Diffstat (limited to 'block')
-rw-r--r-- | block/Kconfig | 13 | ||||
-rw-r--r-- | block/bio.c | 9 | ||||
-rw-r--r-- | block/blk-cgroup.c | 9 | ||||
-rw-r--r-- | block/blk-core.c | 8 | ||||
-rw-r--r-- | block/blk-map.c | 91 | ||||
-rw-r--r-- | block/blk-merge.c | 8 | ||||
-rw-r--r-- | block/blk-mq.c | 6 | ||||
-rw-r--r-- | block/blk-sysfs.c | 5 | ||||
-rw-r--r-- | block/deadline-iosched.c | 3 | ||||
-rw-r--r-- | block/ioctl.c | 38 | ||||
-rw-r--r-- | block/partition-generic.c | 29 |
11 files changed, 128 insertions, 91 deletions
diff --git a/block/Kconfig b/block/Kconfig index 161491d..0363cd7 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -88,6 +88,19 @@ config BLK_DEV_INTEGRITY T10/SCSI Data Integrity Field or the T13/ATA External Path Protection. If in doubt, say N. +config BLK_DEV_DAX + bool "Block device DAX support" + depends on FS_DAX + depends on BROKEN + help + When DAX support is available (CONFIG_FS_DAX) raw block + devices can also support direct userspace access to the + storage capacity via MMAP(2) similar to a file on a + DAX-enabled filesystem. However, the DAX I/O-path disables + some standard I/O-statistics, and the MMAP(2) path has some + operational differences due to bypassing the page + cache. If in doubt, say N. + config BLK_DEV_THROTTLING bool "Block layer bio throttling support" depends on BLK_CGROUP=y diff --git a/block/bio.c b/block/bio.c index 0fde6e0..f124a0a 100644 --- a/block/bio.c +++ b/block/bio.c @@ -880,7 +880,7 @@ int submit_bio_wait(int rw, struct bio *bio) bio->bi_private = &ret; bio->bi_end_io = submit_bio_wait_endio; submit_bio(rw, bio); - wait_for_completion(&ret.event); + wait_for_completion_io(&ret.event); return ret.error; } @@ -1096,9 +1096,12 @@ int bio_uncopy_user(struct bio *bio) if (!bio_flagged(bio, BIO_NULL_MAPPED)) { /* * if we're in a workqueue, the request is orphaned, so - * don't copy into a random user address space, just free. + * don't copy into a random user address space, just free + * and return -EINTR so user space doesn't expect any data. */ - if (current->mm && bio_data_dir(bio) == READ) + if (!current->mm) + ret = -EINTR; + else if (bio_data_dir(bio) == READ) ret = bio_copy_to_iter(bio, bmd->iter); if (bmd->is_our_pages) bio_free_pages(bio); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5a37188..66e6f1a 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -788,6 +788,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, { struct gendisk *disk; struct blkcg_gq *blkg; + struct module *owner; unsigned int major, minor; int key_len, part, ret; char *body; @@ -804,7 +805,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, if (!disk) return -ENODEV; if (part) { + owner = disk->fops->owner; put_disk(disk); + module_put(owner); return -ENODEV; } @@ -820,7 +823,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, ret = PTR_ERR(blkg); rcu_read_unlock(); spin_unlock_irq(disk->queue->queue_lock); + owner = disk->fops->owner; put_disk(disk); + module_put(owner); /* * If queue was bypassing, we should retry. Do so after a * short msleep(). It isn't strictly necessary but queue @@ -851,9 +856,13 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep); void blkg_conf_finish(struct blkg_conf_ctx *ctx) __releases(ctx->disk->queue->queue_lock) __releases(rcu) { + struct module *owner; + spin_unlock_irq(ctx->disk->queue->queue_lock); rcu_read_unlock(); + owner = ctx->disk->fops->owner; put_disk(ctx->disk); + module_put(owner); } EXPORT_SYMBOL_GPL(blkg_conf_finish); diff --git a/block/blk-core.c b/block/blk-core.c index ab51685..45f4d7e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2198,7 +2198,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq) if (q->mq_ops) { if (blk_queue_io_stat(q)) blk_account_io_start(rq, true); - blk_mq_insert_request(rq, false, true, true); + blk_mq_insert_request(rq, false, true, false); return 0; } @@ -2455,14 +2455,16 @@ struct request *blk_peek_request(struct request_queue *q) rq = NULL; break; - } else if (ret == BLKPREP_KILL) { + } else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) { + int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO; + rq->cmd_flags |= REQ_QUIET; /* * Mark this request as started so we don't trigger * any debug logic in the end I/O path. */ blk_start_request(rq); - __blk_end_request_all(rq, -EIO); + __blk_end_request_all(rq, err); } else { printk(KERN_ERR "%s: bad return=%d\n", __func__, ret); break; diff --git a/block/blk-map.c b/block/blk-map.c index f565e11..a54f054 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -57,6 +57,49 @@ static int __blk_rq_unmap_user(struct bio *bio) return ret; } +static int __blk_rq_map_user_iov(struct request *rq, + struct rq_map_data *map_data, struct iov_iter *iter, + gfp_t gfp_mask, bool copy) +{ + struct request_queue *q = rq->q; + struct bio *bio, *orig_bio; + int ret; + + if (copy) + bio = bio_copy_user_iov(q, map_data, iter, gfp_mask); + else + bio = bio_map_user_iov(q, iter, gfp_mask); + + if (IS_ERR(bio)) + return PTR_ERR(bio); + + if (map_data && map_data->null_mapped) + bio_set_flag(bio, BIO_NULL_MAPPED); + + iov_iter_advance(iter, bio->bi_iter.bi_size); + if (map_data) + map_data->offset += bio->bi_iter.bi_size; + + orig_bio = bio; + blk_queue_bounce(q, &bio); + + /* + * We link the bounce buffer in and could have to traverse it + * later so we have to get a ref to prevent it from being freed + */ + bio_get(bio); + + ret = blk_rq_append_bio(q, rq, bio); + if (ret) { + bio_endio(bio); + __blk_rq_unmap_user(orig_bio); + bio_put(bio); + return ret; + } + + return 0; +} + /** * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage * @q: request queue where request should be inserted @@ -82,10 +125,11 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, const struct iov_iter *iter, gfp_t gfp_mask) { - struct bio *bio; - int unaligned = 0; - struct iov_iter i; struct iovec iov, prv = {.iov_base = NULL, .iov_len = 0}; + bool copy = (q->dma_pad_mask & iter->count) || map_data; + struct bio *bio = NULL; + struct iov_iter i; + int ret; if (!iter || !iter->count) return -EINVAL; @@ -101,42 +145,29 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, */ if ((uaddr & queue_dma_alignment(q)) || iovec_gap_to_prv(q, &prv, &iov)) - unaligned = 1; + copy = true; prv.iov_base = iov.iov_base; prv.iov_len = iov.iov_len; } - if (unaligned || (q->dma_pad_mask & iter->count) || map_data) - bio = bio_copy_user_iov(q, map_data, iter, gfp_mask); - else - bio = bio_map_user_iov(q, iter, gfp_mask); - - if (IS_ERR(bio)) - return PTR_ERR(bio); - - if (map_data && map_data->null_mapped) - bio_set_flag(bio, BIO_NULL_MAPPED); - - if (bio->bi_iter.bi_size != iter->count) { - /* - * Grab an extra reference to this bio, as bio_unmap_user() - * expects to be able to drop it twice as it happens on the - * normal IO completion path - */ - bio_get(bio); - bio_endio(bio); - __blk_rq_unmap_user(bio); - return -EINVAL; - } + i = *iter; + do { + ret =__blk_rq_map_user_iov(rq, map_data, &i, gfp_mask, copy); + if (ret) + goto unmap_rq; + if (!bio) + bio = rq->bio; + } while (iov_iter_count(&i)); if (!bio_flagged(bio, BIO_USER_MAPPED)) rq->cmd_flags |= REQ_COPY_USER; - - blk_queue_bounce(q, &bio); - bio_get(bio); - blk_rq_bio_prep(q, rq, bio); return 0; + +unmap_rq: + __blk_rq_unmap_user(bio); + rq->bio = NULL; + return -EINVAL; } EXPORT_SYMBOL(blk_rq_map_user_iov); diff --git a/block/blk-merge.c b/block/blk-merge.c index 888a7fe..2613531 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -304,7 +304,6 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, struct bio *nxt) { struct bio_vec end_bv = { NULL }, nxt_bv; - struct bvec_iter iter; if (!blk_queue_cluster(q)) return 0; @@ -316,11 +315,8 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, if (!bio_has_data(bio)) return 1; - bio_for_each_segment(end_bv, bio, iter) - if (end_bv.bv_len == iter.bi_size) - break; - - nxt_bv = bio_iovec(nxt); + bio_get_last_bvec(bio, &end_bv); + bio_get_first_bvec(nxt, &nxt_bv); if (!BIOVEC_PHYS_MERGEABLE(&end_bv, &nxt_bv)) return 0; diff --git a/block/blk-mq.c b/block/blk-mq.c index 261b6fe..050f7a1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -602,8 +602,10 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, * If a request wasn't started before the queue was * marked dying, kill it here or it'll go unnoticed. */ - if (unlikely(blk_queue_dying(rq->q))) - blk_mq_complete_request(rq, -EIO); + if (unlikely(blk_queue_dying(rq->q))) { + rq->errors = -EIO; + blk_mq_end_request(rq, rq->errors); + } return; } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index e140cc4..dd937630 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -147,10 +147,9 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page) { - unsigned long long val; - val = q->limits.max_hw_discard_sectors << 9; - return sprintf(page, "%llu\n", val); + return sprintf(page, "%llu\n", + (unsigned long long)q->limits.max_hw_discard_sectors << 9); } static ssize_t queue_discard_max_show(struct request_queue *q, char *page) diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c index a753df2..d0dd788 100644 --- a/block/deadline-iosched.c +++ b/block/deadline-iosched.c @@ -39,7 +39,6 @@ struct deadline_data { */ struct request *next_rq[2]; unsigned int batching; /* number of sequential requests made */ - sector_t last_sector; /* head position */ unsigned int starved; /* times reads have starved writes */ /* @@ -210,8 +209,6 @@ deadline_move_request(struct deadline_data *dd, struct request *rq) dd->next_rq[WRITE] = NULL; dd->next_rq[data_dir] = deadline_latter_request(rq); - dd->last_sector = rq_end_sector(rq); - /* * take it off the sort and fifo list, move * to dispatch queue diff --git a/block/ioctl.c b/block/ioctl.c index 77f5d177..d8996bb 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -434,42 +434,6 @@ bool blkdev_dax_capable(struct block_device *bdev) return true; } - -static int blkdev_daxset(struct block_device *bdev, unsigned long argp) -{ - unsigned long arg; - int rc = 0; - - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - - if (get_user(arg, (int __user *)(argp))) - return -EFAULT; - arg = !!arg; - if (arg == !!(bdev->bd_inode->i_flags & S_DAX)) - return 0; - - if (arg) - arg = S_DAX; - - if (arg && !blkdev_dax_capable(bdev)) - return -ENOTTY; - - inode_lock(bdev->bd_inode); - if (bdev->bd_map_count == 0) - inode_set_flags(bdev->bd_inode, arg, S_DAX); - else - rc = -EBUSY; - inode_unlock(bdev->bd_inode); - return rc; -} -#else -static int blkdev_daxset(struct block_device *bdev, int arg) -{ - if (arg) - return -ENOTTY; - return 0; -} #endif static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, @@ -634,8 +598,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKTRACESETUP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); - case BLKDAXSET: - return blkdev_daxset(bdev, arg); case BLKDAXGET: return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX)); break; diff --git a/block/partition-generic.c b/block/partition-generic.c index 746935a..5d87019 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -16,6 +16,7 @@ #include <linux/kmod.h> #include <linux/ctype.h> #include <linux/genhd.h> +#include <linux/dax.h> #include <linux/blktrace_api.h> #include "partitions/check.h" @@ -216,10 +217,21 @@ static void part_release(struct device *dev) kfree(p); } +static int part_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + struct hd_struct *part = dev_to_part(dev); + + add_uevent_var(env, "PARTN=%u", part->partno); + if (part->info && part->info->volname[0]) + add_uevent_var(env, "PARTNAME=%s", part->info->volname); + return 0; +} + struct device_type part_type = { .name = "partition", .groups = part_attr_groups, .release = part_release, + .uevent = part_uevent, }; static void delete_partition_rcu_cb(struct rcu_head *head) @@ -550,13 +562,24 @@ int invalidate_partitions(struct gendisk *disk, struct block_device *bdev) return 0; } -unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) +static struct page *read_pagecache_sector(struct block_device *bdev, sector_t n) { struct address_space *mapping = bdev->bd_inode->i_mapping; + + return read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)), + NULL); +} + +unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) +{ struct page *page; - page = read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)), - NULL); + /* don't populate page cache for dax capable devices */ + if (IS_DAX(bdev->bd_inode)) + page = read_dax_sector(bdev, n); + else + page = read_pagecache_sector(bdev, n); + if (!IS_ERR(page)) { if (PageError(page)) goto fail; |