diff options
Diffstat (limited to 'block')
| -rw-r--r-- | block/Makefile | 2 | ||||
| -rw-r--r-- | block/badblocks.c | 585 | ||||
| -rw-r--r-- | block/bio-integrity.c | 13 | ||||
| -rw-r--r-- | block/bio.c | 4 | ||||
| -rw-r--r-- | block/blk-core.c | 43 | ||||
| -rw-r--r-- | block/blk-merge.c | 22 | ||||
| -rw-r--r-- | block/blk-mq-cpumap.c | 2 | ||||
| -rw-r--r-- | block/blk-mq-tag.c | 11 | ||||
| -rw-r--r-- | block/blk-mq.c | 44 | ||||
| -rw-r--r-- | block/blk-mq.h | 11 | ||||
| -rw-r--r-- | block/blk-timeout.c | 17 | ||||
| -rw-r--r-- | block/blk.h | 2 | ||||
| -rw-r--r-- | block/genhd.c | 32 | ||||
| -rw-r--r-- | block/ioctl.c | 71 |
14 files changed, 789 insertions, 70 deletions
diff --git a/block/Makefile b/block/Makefile index e850474..9eda232 100644 --- a/block/Makefile +++ b/block/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-lib.o blk-mq.o blk-mq-tag.o \ blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \ genhd.o scsi_ioctl.o partition-generic.o ioprio.o \ - partitions/ + badblocks.o partitions/ obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o diff --git a/block/badblocks.c b/block/badblocks.c new file mode 100644 index 0000000..7be53cb --- /dev/null +++ b/block/badblocks.c @@ -0,0 +1,585 @@ +/* + * Bad block management + * + * - Heavily based on MD badblocks code from Neil Brown + * + * Copyright (c) 2015, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/badblocks.h> +#include <linux/seqlock.h> +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/stddef.h> +#include <linux/types.h> +#include <linux/slab.h> + +/** + * badblocks_check() - check a given range for bad sectors + * @bb: the badblocks structure that holds all badblock information + * @s: sector (start) at which to check for badblocks + * @sectors: number of sectors to check for badblocks + * @first_bad: pointer to store location of the first badblock + * @bad_sectors: pointer to store number of badblocks after @first_bad + * + * We can record which blocks on each device are 'bad' and so just + * fail those blocks, or that stripe, rather than the whole device. + * Entries in the bad-block table are 64bits wide. This comprises: + * Length of bad-range, in sectors: 0-511 for lengths 1-512 + * Start of bad-range, sector offset, 54 bits (allows 8 exbibytes) + * A 'shift' can be set so that larger blocks are tracked and + * consequently larger devices can be covered. + * 'Acknowledged' flag - 1 bit. - the most significant bit. + * + * Locking of the bad-block table uses a seqlock so badblocks_check + * might need to retry if it is very unlucky. + * We will sometimes want to check for bad blocks in a bi_end_io function, + * so we use the write_seqlock_irq variant. + * + * When looking for a bad block we specify a range and want to + * know if any block in the range is bad. So we binary-search + * to the last range that starts at-or-before the given endpoint, + * (or "before the sector after the target range") + * then see if it ends after the given start. + * + * Return: + * 0: there are no known bad blocks in the range + * 1: there are known bad block which are all acknowledged + * -1: there are bad blocks which have not yet been acknowledged in metadata. + * plus the start/length of the first bad section we overlap. + */ +int badblocks_check(struct badblocks *bb, sector_t s, int sectors, + sector_t *first_bad, int *bad_sectors) +{ + int hi; + int lo; + u64 *p = bb->page; + int rv; + sector_t target = s + sectors; + unsigned seq; + + if (bb->shift > 0) { + /* round the start down, and the end up */ + s >>= bb->shift; + target += (1<<bb->shift) - 1; + target >>= bb->shift; + sectors = target - s; + } + /* 'target' is now the first block after the bad range */ + +retry: + seq = read_seqbegin(&bb->lock); + lo = 0; + rv = 0; + hi = bb->count; + + /* Binary search between lo and hi for 'target' + * i.e. for the last range that starts before 'target' + */ + /* INVARIANT: ranges before 'lo' and at-or-after 'hi' + * are known not to be the last range before target. + * VARIANT: hi-lo is the number of possible + * ranges, and decreases until it reaches 1 + */ + while (hi - lo > 1) { + int mid = (lo + hi) / 2; + sector_t a = BB_OFFSET(p[mid]); + + if (a < target) + /* This could still be the one, earlier ranges + * could not. + */ + lo = mid; + else + /* This and later ranges are definitely out. */ + hi = mid; + } + /* 'lo' might be the last that started before target, but 'hi' isn't */ + if (hi > lo) { + /* need to check all range that end after 's' to see if + * any are unacknowledged. + */ + while (lo >= 0 && + BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) { + if (BB_OFFSET(p[lo]) < target) { + /* starts before the end, and finishes after + * the start, so they must overlap + */ + if (rv != -1 && BB_ACK(p[lo])) + rv = 1; + else + rv = -1; + *first_bad = BB_OFFSET(p[lo]); + *bad_sectors = BB_LEN(p[lo]); + } + lo--; + } + } + + if (read_seqretry(&bb->lock, seq)) + goto retry; + + return rv; +} +EXPORT_SYMBOL_GPL(badblocks_check); + +/** + * badblocks_set() - Add a range of bad blocks to the table. + * @bb: the badblocks structure that holds all badblock information + * @s: first sector to mark as bad + * @sectors: number of sectors to mark as bad + * @acknowledged: weather to mark the bad sectors as acknowledged + * + * This might extend the table, or might contract it if two adjacent ranges + * can be merged. We binary-search to find the 'insertion' point, then + * decide how best to handle it. + * + * Return: + * 0: success + * 1: failed to set badblocks (out of space) + */ +int badblocks_set(struct badblocks *bb, sector_t s, int sectors, + int acknowledged) +{ + u64 *p; + int lo, hi; + int rv = 0; + unsigned long flags; + + if (bb->shift < 0) + /* badblocks are disabled */ + return 0; + + if (bb->shift) { + /* round the start down, and the end up */ + sector_t next = s + sectors; + + s >>= bb->shift; + next += (1<<bb->shift) - 1; + next >>= bb->shift; + sectors = next - s; + } + + write_seqlock_irqsave(&bb->lock, flags); + + p = bb->page; + lo = 0; + hi = bb->count; + /* Find the last range that starts at-or-before 's' */ + while (hi - lo > 1) { + int mid = (lo + hi) / 2; + sector_t a = BB_OFFSET(p[mid]); + + if (a <= s) + lo = mid; + else + hi = mid; + } + if (hi > lo && BB_OFFSET(p[lo]) > s) + hi = lo; + + if (hi > lo) { + /* we found a range that might merge with the start + * of our new range + */ + sector_t a = BB_OFFSET(p[lo]); + sector_t e = a + BB_LEN(p[lo]); + int ack = BB_ACK(p[lo]); + + if (e >= s) { + /* Yes, we can merge with a previous range */ + if (s == a && s + sectors >= e) + /* new range covers old */ + ack = acknowledged; + else + ack = ack && acknowledged; + + if (e < s + sectors) + e = s + sectors; + if (e - a <= BB_MAX_LEN) { + p[lo] = BB_MAKE(a, e-a, ack); + s = e; + } else { + /* does not all fit in one range, + * make p[lo] maximal + */ + if (BB_LEN(p[lo]) != BB_MAX_LEN) + p[lo] = BB_MAKE(a, BB_MAX_LEN, ack); + s = a + BB_MAX_LEN; + } + sectors = e - s; + } + } + if (sectors && hi < bb->count) { + /* 'hi' points to the first range that starts after 's'. + * Maybe we can merge with the start of that range + */ + sector_t a = BB_OFFSET(p[hi]); + sector_t e = a + BB_LEN(p[hi]); + int ack = BB_ACK(p[hi]); + + if (a <= s + sectors) { + /* merging is possible */ + if (e <= s + sectors) { + /* full overlap */ + e = s + sectors; + ack = acknowledged; + } else + ack = ack && acknowledged; + + a = s; + if (e - a <= BB_MAX_LEN) { + p[hi] = BB_MAKE(a, e-a, ack); + s = e; + } else { + p[hi] = BB_MAKE(a, BB_MAX_LEN, ack); + s = a + BB_MAX_LEN; + } + sectors = e - s; + lo = hi; + hi++; + } + } + if (sectors == 0 && hi < bb->count) { + /* we might be able to combine lo and hi */ + /* Note: 's' is at the end of 'lo' */ + sector_t a = BB_OFFSET(p[hi]); + int lolen = BB_LEN(p[lo]); + int hilen = BB_LEN(p[hi]); + int newlen = lolen + hilen - (s - a); + + if (s >= a && newlen < BB_MAX_LEN) { + /* yes, we can combine them */ + int ack = BB_ACK(p[lo]) && BB_ACK(p[hi]); + + p[lo] = BB_MAKE(BB_OFFSET(p[lo]), newlen, ack); + memmove(p + hi, p + hi + 1, + (bb->count - hi - 1) * 8); + bb->count--; + } + } + while (sectors) { + /* didn't merge (it all). + * Need to add a range just before 'hi' + */ + if (bb->count >= MAX_BADBLOCKS) { + /* No room for more */ + rv = 1; + break; + } else { + int this_sectors = sectors; + + memmove(p + hi + 1, p + hi, + (bb->count - hi) * 8); + bb->count++; + + if (this_sectors > BB_MAX_LEN) + this_sectors = BB_MAX_LEN; + p[hi] = BB_MAKE(s, this_sectors, acknowledged); + sectors -= this_sectors; + s += this_sectors; + } + } + + bb->changed = 1; + if (!acknowledged) + bb->unacked_exist = 1; + write_sequnlock_irqrestore(&bb->lock, flags); + + return rv; +} +EXPORT_SYMBOL_GPL(badblocks_set); + +/** + * badblocks_clear() - Remove a range of bad blocks to the table. + * @bb: the badblocks structure that holds all badblock information + * @s: first sector to mark as bad + * @sectors: number of sectors to mark as bad + * + * This may involve extending the table if we spilt a region, + * but it must not fail. So if the table becomes full, we just + * drop the remove request. + * + * Return: + * 0: success + * 1: failed to clear badblocks + */ +int badblocks_clear(struct badblocks *bb, sector_t s, int sectors) +{ + u64 *p; + int lo, hi; + sector_t target = s + sectors; + int rv = 0; + + if (bb->shift > 0) { + /* When clearing we round the start up and the end down. + * This should not matter as the shift should align with + * the block size and no rounding should ever be needed. + * However it is better the think a block is bad when it + * isn't than to think a block is not bad when it is. + */ + s += (1<<bb->shift) - 1; + s >>= bb->shift; + target >>= bb->shift; + sectors = target - s; + } + + write_seqlock_irq(&bb->lock); + + p = bb->page; + lo = 0; + hi = bb->count; + /* Find the last range that starts before 'target' */ + while (hi - lo > 1) { + int mid = (lo + hi) / 2; + sector_t a = BB_OFFSET(p[mid]); + + if (a < target) + lo = mid; + else + hi = mid; + } + if (hi > lo) { + /* p[lo] is the last range that could overlap the + * current range. Earlier ranges could also overlap, + * but only this one can overlap the end of the range. + */ + if (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) { + /* Partial overlap, leave the tail of this range */ + int ack = BB_ACK(p[lo]); + sector_t a = BB_OFFSET(p[lo]); + sector_t end = a + BB_LEN(p[lo]); + + if (a < s) { + /* we need to split this range */ + if (bb->count >= MAX_BADBLOCKS) { + rv = -ENOSPC; + goto out; + } + memmove(p+lo+1, p+lo, (bb->count - lo) * 8); + bb->count++; + p[lo] = BB_MAKE(a, s-a, ack); + lo++; + } + p[lo] = BB_MAKE(target, end - target, ack); + /* there is no longer an overlap */ + hi = lo; + lo--; + } + while (lo >= 0 && + BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) { + /* This range does overlap */ + if (BB_OFFSET(p[lo]) < s) { + /* Keep the early parts of this range. */ + int ack = BB_ACK(p[lo]); + sector_t start = BB_OFFSET(p[lo]); + + p[lo] = BB_MAKE(start, s - start, ack); + /* now low doesn't overlap, so.. */ + break; + } + lo--; + } + /* 'lo' is strictly before, 'hi' is strictly after, + * anything between needs to be discarded + */ + if (hi - lo > 1) { + memmove(p+lo+1, p+hi, (bb->count - hi) * 8); + bb->count -= (hi - lo - 1); + } + } + + bb->changed = 1; +out: + write_sequnlock_irq(&bb->lock); + return rv; +} +EXPORT_SYMBOL_GPL(badblocks_clear); + +/** + * ack_all_badblocks() - Acknowledge all bad blocks in a list. + * @bb: the badblocks structure that holds all badblock information + * + * This only succeeds if ->changed is clear. It is used by + * in-kernel metadata updates + */ +void ack_all_badblocks(struct badblocks *bb) +{ + if (bb->page == NULL || bb->changed) + /* no point even trying */ + return; + write_seqlock_irq(&bb->lock); + + if (bb->changed == 0 && bb->unacked_exist) { + u64 *p = bb->page; + int i; + + for (i = 0; i < bb->count ; i++) { + if (!BB_ACK(p[i])) { + sector_t start = BB_OFFSET(p[i]); + int len = BB_LEN(p[i]); + + p[i] = BB_MAKE(start, len, 1); + } + } + bb->unacked_exist = 0; + } + write_sequnlock_irq(&bb->lock); +} +EXPORT_SYMBOL_GPL(ack_all_badblocks); + +/** + * badblocks_show() - sysfs access to bad-blocks list + * @bb: the badblocks structure that holds all badblock information + * @page: buffer received from sysfs + * @unack: weather to show unacknowledged badblocks + * + * Return: + * Length of returned data + */ +ssize_t badblocks_show(struct badblocks *bb, char *page, int unack) +{ + size_t len; + int i; + u64 *p = bb->page; + unsigned seq; + + if (bb->shift < 0) + return 0; + +retry: + seq = read_seqbegin(&bb->lock); + + len = 0; + i = 0; + + while (len < PAGE_SIZE && i < bb->count) { + sector_t s = BB_OFFSET(p[i]); + unsigned int length = BB_LEN(p[i]); + int ack = BB_ACK(p[i]); + + i++; + + if (unack && ack) + continue; + + len += snprintf(page+len, PAGE_SIZE-len, "%llu %u\n", + (unsigned long long)s << bb->shift, + length << bb->shift); + } + if (unack && len == 0) + bb->unacked_exist = 0; + + if (read_seqretry(&bb->lock, seq)) + goto retry; + + return len; +} +EXPORT_SYMBOL_GPL(badblocks_show); + +/** + * badblocks_store() - sysfs access to bad-blocks list + * @bb: the badblocks structure that holds all badblock information + * @page: buffer received from sysfs + * @len: length of data received from sysfs + * @unack: weather to show unacknowledged badblocks + * + * Return: + * Length of the buffer processed or -ve error. + */ +ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, + int unack) +{ + unsigned long long sector; + int length; + char newline; + + switch (sscanf(page, "%llu %d%c", §or, &length, &newline)) { + case 3: + if (newline != '\n') + return -EINVAL; + case 2: + if (length <= 0) + return -EINVAL; + break; + default: + return -EINVAL; + } + + if (badblocks_set(bb, sector, length, !unack)) + return -ENOSPC; + else + return len; +} +EXPORT_SYMBOL_GPL(badblocks_store); + +static int __badblocks_init(struct device *dev, struct badblocks *bb, + int enable) +{ + bb->dev = dev; + bb->count = 0; + if (enable) + bb->shift = 0; + else + bb->shift = -1; + if (dev) + bb->page = devm_kzalloc(dev, PAGE_SIZE, GFP_KERNEL); + else + bb->page = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!bb->page) { + bb->shift = -1; + return -ENOMEM; + } + seqlock_init(&bb->lock); + + return 0; +} + +/** + * badblocks_init() - initialize the badblocks structure + * @bb: the badblocks structure that holds all badblock information + * @enable: weather to enable badblocks accounting + * + * Return: + * 0: success + * -ve errno: on error + */ +int badblocks_init(struct badblocks *bb, int enable) +{ + return __badblocks_init(NULL, bb, enable); +} +EXPORT_SYMBOL_GPL(badblocks_init); + +int devm_init_badblocks(struct device *dev, struct badblocks *bb) +{ + if (!bb) + return -EINVAL; + return __badblocks_init(dev, bb, 1); +} +EXPORT_SYMBOL_GPL(devm_init_badblocks); + +/** + * badblocks_exit() - free the badblocks structure + * @bb: the badblocks structure that holds all badblock information + */ +void badblocks_exit(struct badblocks *bb) +{ + if (!bb) + return; + if (bb->dev) + devm_kfree(bb->dev, bb->page); + else + kfree(bb->page); + bb->page = NULL; +} +EXPORT_SYMBOL_GPL(badblocks_exit); diff --git a/block/bio-integrity.c b/block/bio-integrity.c index f6325d5..711e4d8d 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -66,7 +66,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, } if (unlikely(!bip)) - return NULL; + return ERR_PTR(-ENOMEM); memset(bip, 0, sizeof(*bip)); @@ -89,7 +89,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, return bip; err: mempool_free(bip, bs->bio_integrity_pool); - return NULL; + return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(bio_integrity_alloc); @@ -298,10 +298,10 @@ int bio_integrity_prep(struct bio *bio) /* Allocate bio integrity payload and integrity vectors */ bip = bio_integrity_alloc(bio, GFP_NOIO, nr_pages); - if (unlikely(bip == NULL)) { + if (IS_ERR(bip)) { printk(KERN_ERR "could not allocate data integrity bioset\n"); kfree(buf); - return -EIO; + return PTR_ERR(bip); } bip->bip_flags |= BIP_BLOCK_INTEGRITY; @@ -465,9 +465,8 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, BUG_ON(bip_src == NULL); bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt); - - if (bip == NULL) - return -EIO; + if (IS_ERR(bip)) + return PTR_ERR(bip); memcpy(bip->bip_vec, bip_src->bip_vec, bip_src->bip_vcnt * sizeof(struct bio_vec)); diff --git a/block/bio.c b/block/bio.c index 4f184d9..dbabd48 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1125,7 +1125,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q, int i, ret; int nr_pages = 0; unsigned int len = iter->count; - unsigned int offset = map_data ? map_data->offset & ~PAGE_MASK : 0; + unsigned int offset = map_data ? offset_in_page(map_data->offset) : 0; for (i = 0; i < iter->nr_segs; i++) { unsigned long uaddr; @@ -1304,7 +1304,7 @@ struct bio *bio_map_user_iov(struct request_queue *q, goto out_unmap; } - offset = uaddr & ~PAGE_MASK; + offset = offset_in_page(uaddr); for (j = cur_page; j < page_limit; j++) { unsigned int bytes = PAGE_SIZE - offset; diff --git a/block/blk-core.c b/block/blk-core.c index 3636be4..ab51685 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -51,7 +51,7 @@ DEFINE_IDA(blk_queue_ida); /* * For the allocated request tables */ -struct kmem_cache *request_cachep = NULL; +struct kmem_cache *request_cachep; /* * For queue allocation @@ -207,6 +207,22 @@ void blk_delay_queue(struct request_queue *q, unsigned long msecs) EXPORT_SYMBOL(blk_delay_queue); /** + * blk_start_queue_async - asynchronously restart a previously stopped queue + * @q: The &struct request_queue in question + * + * Description: + * blk_start_queue_async() will clear the stop flag on the queue, and + * ensure that the request_fn for the queue is run from an async + * context. + **/ +void blk_start_queue_async(struct request_queue *q) +{ + queue_flag_clear(QUEUE_FLAG_STOPPED, q); + blk_run_queue_async(q); +} +EXPORT_SYMBOL(blk_start_queue_async); + +/** * blk_start_queue - restart a previously stopped queue * @q: The &struct request_queue in question * @@ -630,7 +646,7 @@ struct request_queue *blk_alloc_queue(gfp_t gfp_mask) } EXPORT_SYMBOL(blk_alloc_queue); -int blk_queue_enter(struct request_queue *q, gfp_t gfp) +int blk_queue_enter(struct request_queue *q, bool nowait) { while (true) { int ret; @@ -638,7 +654,7 @@ int blk_queue_enter(struct request_queue *q, gfp_t gfp) if (percpu_ref_tryget_live(&q->q_usage_counter)) return 0; - if (!gfpflags_allow_blocking(gfp)) + if (nowait) return -EBUSY; ret = wait_event_interruptible(q->mq_freeze_wq, @@ -664,6 +680,13 @@ static void blk_queue_usage_counter_release(struct percpu_ref *ref) wake_up_all(&q->mq_freeze_wq); } +static void blk_rq_timed_out_timer(unsigned long data) +{ + struct request_queue *q = (struct request_queue *)data; + + kblockd_schedule_work(&q->timeout_work); +} + struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) { struct request_queue *q; @@ -825,6 +848,7 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, if (blk_init_rl(&q->root_rl, q, GFP_KERNEL)) goto fail; + INIT_WORK(&q->timeout_work, blk_timeout_work); q->request_fn = rfn; q->prep_rq_fn = NULL; q->unprep_rq_fn = NULL; @@ -1276,7 +1300,9 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw, struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask) { if (q->mq_ops) - return blk_mq_alloc_request(q, rw, gfp_mask, false); + return blk_mq_alloc_request(q, rw, + (gfp_mask & __GFP_DIRECT_RECLAIM) ? + 0 : BLK_MQ_REQ_NOWAIT); else return blk_old_get_request(q, rw, gfp_mask); } @@ -1689,8 +1715,6 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) struct request *req; unsigned int request_count = 0; - blk_queue_split(q, &bio, q->bio_split); - /* * low level driver can indicate that it wants pages above a * certain limit bounced to low memory (ie for highmem, or even @@ -1698,6 +1722,8 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) */ blk_queue_bounce(q, &bio); + blk_queue_split(q, &bio, q->bio_split); + if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { bio->bi_error = -EIO; bio_endio(bio); @@ -2044,8 +2070,7 @@ blk_qc_t generic_make_request(struct bio *bio) do { struct request_queue *q = bdev_get_queue(bio->bi_bdev); - if (likely(blk_queue_enter(q, __GFP_DIRECT_RECLAIM) == 0)) { - + if (likely(blk_queue_enter(q, false) == 0)) { ret = q->make_request_fn(q, bio); blk_queue_exit(q); @@ -3518,7 +3543,7 @@ int __init blk_dev_init(void) request_cachep = kmem_cache_create("blkdev_requests", sizeof(struct request), 0, SLAB_PANIC, NULL); - blk_requestq_cachep = kmem_cache_create("blkdev_queue", + blk_requestq_cachep = kmem_cache_create("request_queue", sizeof(struct request_queue), 0, SLAB_PANIC, NULL); return 0; diff --git a/block/blk-merge.c b/block/blk-merge.c index e01405a..1699df5 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -7,6 +7,8 @@ #include <linux/blkdev.h> #include <linux/scatterlist.h> +#include <trace/events/block.h> + #include "blk.h" static struct bio *blk_bio_discard_split(struct request_queue *q, @@ -81,9 +83,6 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *new = NULL; bio_for_each_segment(bv, bio, iter) { - if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q)) - goto split; - /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. @@ -91,6 +90,22 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) goto split; + if (sectors + (bv.bv_len >> 9) > + blk_max_size_offset(q, bio->bi_iter.bi_sector)) { + /* + * Consider this a new segment if we're splitting in + * the middle of this vector. + */ + if (nsegs < queue_max_segments(q) && + sectors < blk_max_size_offset(q, + bio->bi_iter.bi_sector)) { + nsegs++; + sectors = blk_max_size_offset(q, + bio->bi_iter.bi_sector); + } + goto split; + } + if (bvprvp && blk_queue_cluster(q)) { if (seg_size + bv.bv_len > queue_max_segment_size(q)) goto new_segment; @@ -162,6 +177,7 @@ void blk_queue_split(struct request_queue *q, struct bio **bio, split->bi_rw |= REQ_NOMERGE; bio_chain(split, *bio); + trace_block_split(q, split, (*bio)->bi_iter.bi_sector); generic_make_request(*bio); *bio = split; } diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index 8764c24..d0634bc 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -113,7 +113,7 @@ int blk_mq_hw_queue_to_node(unsigned int *mq_map, unsigned int index) for_each_possible_cpu(i) { if (index == mq_map[i]) - return cpu_to_node(i); + return local_memory_node(cpu_to_node(i)); } return NUMA_NO_NODE; diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index a07ca34..abdbb47 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -268,7 +268,7 @@ static int bt_get(struct blk_mq_alloc_data *data, if (tag != -1) return tag; - if (!gfpflags_allow_blocking(data->gfp)) + if (data->flags & BLK_MQ_REQ_NOWAIT) return -1; bs = bt_wait_ptr(bt, hctx); @@ -303,7 +303,7 @@ static int bt_get(struct blk_mq_alloc_data *data, data->ctx = blk_mq_get_ctx(data->q); data->hctx = data->q->mq_ops->map_queue(data->q, data->ctx->cpu); - if (data->reserved) { + if (data->flags & BLK_MQ_REQ_RESERVED) { bt = &data->hctx->tags->breserved_tags; } else { last_tag = &data->ctx->last_tag; @@ -349,10 +349,9 @@ static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_alloc_data *data) unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) { - if (!data->reserved) - return __blk_mq_get_tag(data); - - return __blk_mq_get_reserved_tag(data); + if (data->flags & BLK_MQ_REQ_RESERVED) + return __blk_mq_get_reserved_tag(data); + return __blk_mq_get_tag(data); } static struct bt_wait_state *bt_wake_ptr(struct blk_mq_bitmap_tags *bt) diff --git a/block/blk-mq.c b/block/blk-mq.c index 6d6f8fe..4c0622f 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -229,8 +229,8 @@ __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int rw) return NULL; } -struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, - bool reserved) +struct request *blk_mq_alloc_request(struct request_queue *q, int rw, + unsigned int flags) { struct blk_mq_ctx *ctx; struct blk_mq_hw_ctx *hctx; @@ -238,24 +238,22 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, struct blk_mq_alloc_data alloc_data; int ret; - ret = blk_queue_enter(q, gfp); + ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT); if (ret) return ERR_PTR(ret); ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_set_alloc_data(&alloc_data, q, gfp & ~__GFP_DIRECT_RECLAIM, - reserved, ctx, hctx); + blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw); - if (!rq && (gfp & __GFP_DIRECT_RECLAIM)) { + if (!rq && !(flags & BLK_MQ_REQ_NOWAIT)) { __blk_mq_run_hw_queue(hctx); blk_mq_put_ctx(ctx); ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_set_alloc_data(&alloc_data, q, gfp, reserved, ctx, - hctx); + blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw); ctx = alloc_data.ctx; } @@ -605,8 +603,6 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, blk_mq_complete_request(rq, -EIO); return; } - if (rq->cmd_flags & REQ_NO_TIMEOUT) - return; if (time_after_eq(jiffies, rq->deadline)) { if (!blk_mark_rq_complete(rq)) @@ -617,15 +613,19 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, } } -static void blk_mq_rq_timer(unsigned long priv) +static void blk_mq_timeout_work(struct work_struct *work) { - struct request_queue *q = (struct request_queue *)priv; + struct request_queue *q = + container_of(work, struct request_queue, timeout_work); struct blk_mq_timeout_data data = { .next = 0, .next_set = 0, }; int i; + if (blk_queue_enter(q, true)) + return; + blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data); if (data.next_set) { @@ -640,6 +640,7 @@ static void blk_mq_rq_timer(unsigned long priv) blk_mq_tag_idle(hctx); } } + blk_queue_exit(q); } /* @@ -1175,8 +1176,7 @@ static struct request *blk_mq_map_request(struct request_queue *q, rw |= REQ_SYNC; trace_block_getrq(q, bio, rw); - blk_mq_set_alloc_data(&alloc_data, q, GFP_ATOMIC, false, ctx, - hctx); + blk_mq_set_alloc_data(&alloc_data, q, BLK_MQ_REQ_NOWAIT, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw); if (unlikely(!rq)) { __blk_mq_run_hw_queue(hctx); @@ -1185,8 +1185,7 @@ static struct request *blk_mq_map_request(struct request_queue *q, ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_set_alloc_data(&alloc_data, q, - __GFP_RECLAIM|__GFP_HIGH, false, ctx, hctx); + blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw); ctx = alloc_data.ctx; hctx = alloc_data.hctx; @@ -1794,7 +1793,7 @@ static void blk_mq_init_cpu_queues(struct request_queue *q, * not, we remain on the home node of the device */ if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE) - hctx->numa_node = cpu_to_node(i); + hctx->numa_node = local_memory_node(cpu_to_node(i)); } } @@ -1854,6 +1853,7 @@ static void blk_mq_map_swqueue(struct request_queue *q, hctx->tags = set->tags[i]; WARN_ON(!hctx->tags); + cpumask_copy(hctx->tags->cpumask, hctx->cpumask); /* * Set the map size to the number of mapped software queues. * This is more accurate and more efficient than looping @@ -1867,14 +1867,6 @@ static void blk_mq_map_swqueue(struct request_queue *q, hctx->next_cpu = cpumask_first(hctx->cpumask); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } - - queue_for_each_ctx(q, ctx, i) { - if (!cpumask_test_cpu(i, online_mask)) - continue; - - hctx = q->mq_ops->map_queue(q, i); - cpumask_set_cpu(i, hctx->tags->cpumask); - } } static void queue_set_hctx_shared(struct request_queue *q, bool shared) @@ -2019,7 +2011,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, hctxs[i]->queue_num = i; } - setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q); + INIT_WORK(&q->timeout_work, blk_mq_timeout_work); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); q->nr_queues = nr_cpu_ids; diff --git a/block/blk-mq.h b/block/blk-mq.h index 713820b..eaede8e 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -96,8 +96,7 @@ static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx) struct blk_mq_alloc_data { /* input parameter */ struct request_queue *q; - gfp_t gfp; - bool reserved; + unsigned int flags; /* input & output parameter */ struct blk_mq_ctx *ctx; @@ -105,13 +104,11 @@ struct blk_mq_alloc_data { }; static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data, - struct request_queue *q, gfp_t gfp, bool reserved, - struct blk_mq_ctx *ctx, - struct blk_mq_hw_ctx *hctx) + struct request_queue *q, unsigned int flags, + struct blk_mq_ctx *ctx, struct blk_mq_hw_ctx *hctx) { data->q = q; - data->gfp = gfp; - data->reserved = reserved; + data->flags = flags; data->ctx = ctx; data->hctx = hctx; } diff --git a/block/blk-timeout.c b/block/blk-timeout.c index aa40aa9..a30441a 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -127,13 +127,16 @@ static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout } } -void blk_rq_timed_out_timer(unsigned long data) +void blk_timeout_work(struct work_struct *work) { - struct request_queue *q = (struct request_queue *) data; + struct request_queue *q = + container_of(work, struct request_queue, timeout_work); unsigned long flags, next = 0; struct request *rq, *tmp; int next_set = 0; + if (blk_queue_enter(q, true)) + return; spin_lock_irqsave(q->queue_lock, flags); list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list) @@ -143,6 +146,7 @@ void blk_rq_timed_out_timer(unsigned long data) mod_timer(&q->timeout, round_jiffies_up(next)); spin_unlock_irqrestore(q->queue_lock, flags); + blk_queue_exit(q); } /** @@ -186,15 +190,13 @@ unsigned long blk_rq_timeout(unsigned long timeout) * Notes: * Each request has its own timer, and as it is added to the queue, we * set up the timer. When the request completes, we cancel the timer. + * Queue lock must be held for the non-mq case, mq case doesn't care. */ void blk_add_timer(struct request *req) { struct request_queue *q = req->q; unsigned long expiry; - if (req->cmd_flags & REQ_NO_TIMEOUT) - return; - /* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */ if (!q->mq_ops && !q->rq_timed_out_fn) return; @@ -209,6 +211,11 @@ void blk_add_timer(struct request *req) req->timeout = q->rq_timeout; req->deadline = jiffies + req->timeout; + + /* + * Only the non-mq case needs to add the request to a protected list. + * For the mq case we simply scan the tag map. + */ if (!q->mq_ops) list_add_tail(&req->timeout_list, &req->q->timeout_list); diff --git a/block/blk.h b/block/blk.h index c43926d..70e4aee 100644 --- a/block/blk.h +++ b/block/blk.h @@ -93,7 +93,7 @@ static inline void blk_flush_integrity(void) } #endif -void blk_rq_timed_out_timer(unsigned long data); +void blk_timeout_work(struct work_struct *work); unsigned long blk_rq_timeout(unsigned long timeout); void blk_add_timer(struct request *req); void blk_delete_timer(struct request *); diff --git a/block/genhd.c b/block/genhd.c index e5cafa5..9f42526 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -20,6 +20,7 @@ #include <linux/idr.h> #include <linux/log2.h> #include <linux/pm_runtime.h> +#include <linux/badblocks.h> #include "blk.h" @@ -664,7 +665,6 @@ void del_gendisk(struct gendisk *disk) kobject_put(disk->part0.holder_dir); kobject_put(disk->slave_dir); - disk->driverfs_dev = NULL; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); @@ -672,6 +672,31 @@ void del_gendisk(struct gendisk *disk) } EXPORT_SYMBOL(del_gendisk); +/* sysfs access to bad-blocks list. */ +static ssize_t disk_badblocks_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (!disk->bb) + return sprintf(page, "\n"); + + return badblocks_show(disk->bb, page, 0); +} + +static ssize_t disk_badblocks_store(struct device *dev, + struct device_attribute *attr, + const char *page, size_t len) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (!disk->bb) + return -ENXIO; + + return badblocks_store(disk->bb, page, len, 0); +} + /** * get_gendisk - get partitioning information for a given device * @devt: device to get partitioning information for @@ -990,6 +1015,8 @@ static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show, static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); +static DEVICE_ATTR(badblocks, S_IRUGO | S_IWUSR, disk_badblocks_show, + disk_badblocks_store); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -1011,6 +1038,7 @@ static struct attribute *disk_attrs[] = { &dev_attr_capability.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, + &dev_attr_badblocks.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif @@ -1421,7 +1449,7 @@ static DEFINE_MUTEX(disk_events_mutex); static LIST_HEAD(disk_events); /* disable in-kernel polling by default */ -static unsigned long disk_events_dfl_poll_msecs = 0; +static unsigned long disk_events_dfl_poll_msecs; static unsigned long disk_events_poll_jiffies(struct gendisk *disk) { diff --git a/block/ioctl.c b/block/ioctl.c index 0918aed..77f5d177 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -4,6 +4,7 @@ #include <linux/gfp.h> #include <linux/blkpg.h> #include <linux/hdreg.h> +#include <linux/badblocks.h> #include <linux/backing-dev.h> #include <linux/fs.h> #include <linux/blktrace_api.h> @@ -406,6 +407,71 @@ static inline int is_unrecognized_ioctl(int ret) ret == -ENOIOCTLCMD; } +#ifdef CONFIG_FS_DAX +bool blkdev_dax_capable(struct block_device *bdev) +{ + struct gendisk *disk = bdev->bd_disk; + + if (!disk->fops->direct_access) + return false; + + /* + * If the partition is not aligned on a page boundary, we can't + * do dax I/O to it. + */ + if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) + || (bdev->bd_part->nr_sects % (PAGE_SIZE / 512))) + return false; + + /* + * If the device has known bad blocks, force all I/O through the + * driver / page cache. + * + * TODO: support finer grained dax error handling + */ + if (disk->bb && disk->bb->count) + return false; + + 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, unsigned cmd, unsigned long arg) { @@ -568,6 +634,11 @@ 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; case IOC_PR_REGISTER: return blkdev_pr_register(bdev, argp); case IOC_PR_RESERVE: |
