diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-02 15:29:19 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-02 15:29:19 -0700 |
| commit | 750a02ab8d3c49ca7d23102be90d3d1db19e2827 (patch) | |
| tree | 3c829af238b6598178c9ed859edb00bc8a280c05 /block | |
| parent | 1966391fa576e1fb2701be8bcca197d8f72737b7 (diff) | |
| parent | abb30460bda232f304f642510adc8c6576ea51ea (diff) | |
Merge tag 'for-5.8/block-2020-06-01' of git://git.kernel.dk/linux-block
Pull block updates from Jens Axboe:
"Core block changes that have been queued up for this release:
- Remove dead blk-throttle and blk-wbt code (Guoqing)
- Include pid in blktrace note traces (Jan)
- Don't spew I/O errors on wouldblock termination (me)
- Zone append addition (Johannes, Keith, Damien)
- IO accounting improvements (Konstantin, Christoph)
- blk-mq hardware map update improvements (Ming)
- Scheduler dispatch improvement (Salman)
- Inline block encryption support (Satya)
- Request map fixes and improvements (Weiping)
- blk-iocost tweaks (Tejun)
- Fix for timeout failing with error injection (Keith)
- Queue re-run fixes (Douglas)
- CPU hotplug improvements (Christoph)
- Queue entry/exit improvements (Christoph)
- Move DMA drain handling to the few drivers that use it (Christoph)
- Partition handling cleanups (Christoph)"
* tag 'for-5.8/block-2020-06-01' of git://git.kernel.dk/linux-block: (127 commits)
block: mark bio_wouldblock_error() bio with BIO_QUIET
blk-wbt: rename __wbt_update_limits to wbt_update_limits
blk-wbt: remove wbt_update_limits
blk-throttle: remove tg_drain_bios
blk-throttle: remove blk_throtl_drain
null_blk: force complete for timeout request
blk-mq: drain I/O when all CPUs in a hctx are offline
blk-mq: add blk_mq_all_tag_iter
blk-mq: open code __blk_mq_alloc_request in blk_mq_alloc_request_hctx
blk-mq: use BLK_MQ_NO_TAG in more places
blk-mq: rename BLK_MQ_TAG_FAIL to BLK_MQ_NO_TAG
blk-mq: move more request initialization to blk_mq_rq_ctx_init
blk-mq: simplify the blk_mq_get_request calling convention
blk-mq: remove the bio argument to ->prepare_request
nvme: force complete cancelled requests
blk-mq: blk-mq: provide forced completion method
block: fix a warning when blkdev.h is included for !CONFIG_BLOCK builds
block: blk-crypto-fallback: remove redundant initialization of variable err
block: reduce part_stat_lock() scope
block: use __this_cpu_add() instead of access by smp_processor_id()
...
Diffstat (limited to 'block')
36 files changed, 2879 insertions, 859 deletions
diff --git a/block/Kconfig b/block/Kconfig index 3bc76bb113a0..9382a4acefc3 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -146,6 +146,7 @@ config BLK_CGROUP_IOLATENCY config BLK_CGROUP_IOCOST bool "Enable support for cost model based cgroup IO controller" depends on BLK_CGROUP=y + select BLK_RQ_IO_DATA_LEN select BLK_RQ_ALLOC_TIME ---help--- Enabling this option enables the .weight interface for cost @@ -185,6 +186,23 @@ config BLK_SED_OPAL Enabling this option enables users to setup/unlock/lock Locking ranges for SED devices using the Opal protocol. +config BLK_INLINE_ENCRYPTION + bool "Enable inline encryption support in block layer" + help + Build the blk-crypto subsystem. Enabling this lets the + block layer handle encryption, so users can take + advantage of inline encryption hardware if present. + +config BLK_INLINE_ENCRYPTION_FALLBACK + bool "Enable crypto API fallback for blk-crypto" + depends on BLK_INLINE_ENCRYPTION + select CRYPTO + select CRYPTO_SKCIPHER + help + Enabling this lets the block layer handle inline encryption + by falling back to the kernel crypto API when inline + encryption hardware is not present. + menu "Partition Types" source "block/partitions/Kconfig" diff --git a/block/Makefile b/block/Makefile index 206b96e9387f..78719169fb2a 100644 --- a/block/Makefile +++ b/block/Makefile @@ -36,3 +36,5 @@ obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o obj-$(CONFIG_BLK_SED_OPAL) += sed-opal.o obj-$(CONFIG_BLK_PM) += blk-pm.o +obj-$(CONFIG_BLK_INLINE_ENCRYPTION) += keyslot-manager.o blk-crypto.o +obj-$(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) += blk-crypto-fallback.o diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 3d411716d7ee..50c8f034c01c 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -6073,7 +6073,7 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, * comments on bfq_init_rq for the reason behind this delayed * preparation. */ -static void bfq_prepare_request(struct request *rq, struct bio *bio) +static void bfq_prepare_request(struct request *rq) { /* * Regardless of whether we have an icq attached, we have to diff --git a/block/bio-integrity.c b/block/bio-integrity.c index bf62c25cde8f..3579ac0f6ec1 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -42,6 +42,9 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, struct bio_set *bs = bio->bi_pool; unsigned inline_vecs; + if (WARN_ON_ONCE(bio_has_crypt_ctx(bio))) + return ERR_PTR(-EOPNOTSUPP); + if (!bs || !mempool_initialized(&bs->bio_integrity_pool)) { bip = kmalloc(struct_size(bip, bip_inline_vecs, nr_vecs), gfp_mask); inline_vecs = nr_vecs; diff --git a/block/bio.c b/block/bio.c index 21cbaa6a1c20..5235da6434aa 100644 --- a/block/bio.c +++ b/block/bio.c @@ -18,6 +18,7 @@ #include <linux/blk-cgroup.h> #include <linux/highmem.h> #include <linux/sched/sysctl.h> +#include <linux/blk-crypto.h> #include <trace/events/block.h> #include "blk.h" @@ -237,6 +238,8 @@ void bio_uninit(struct bio *bio) if (bio_integrity(bio)) bio_integrity_free(bio); + + bio_crypt_free_ctx(bio); } EXPORT_SYMBOL(bio_uninit); @@ -708,6 +711,8 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs) __bio_clone_fast(b, bio); + bio_crypt_clone(b, bio, gfp_mask); + if (bio_integrity(bio)) { int ret; @@ -748,9 +753,14 @@ static inline bool page_is_mergeable(const struct bio_vec *bv, return true; } -static bool bio_try_merge_pc_page(struct request_queue *q, struct bio *bio, - struct page *page, unsigned len, unsigned offset, - bool *same_page) +/* + * Try to merge a page into a segment, while obeying the hardware segment + * size limit. This is not for normal read/write bios, but for passthrough + * or Zone Append operations that we can't split. + */ +static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio, + struct page *page, unsigned len, + unsigned offset, bool *same_page) { struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; unsigned long mask = queue_segment_boundary(q); @@ -765,38 +775,32 @@ static bool bio_try_merge_pc_page(struct request_queue *q, struct bio *bio, } /** - * __bio_add_pc_page - attempt to add page to passthrough bio - * @q: the target queue - * @bio: destination bio - * @page: page to add - * @len: vec entry length - * @offset: vec entry offset - * @same_page: return if the merge happen inside the same page - * - * Attempt to add a page to the bio_vec maplist. This can fail for a - * number of reasons, such as the bio being full or target block device - * limitations. The target block device must allow bio's up to PAGE_SIZE, - * so it is always possible to add a single page to an empty bio. + * bio_add_hw_page - attempt to add a page to a bio with hw constraints + * @q: the target queue + * @bio: destination bio + * @page: page to add + * @len: vec entry length + * @offset: vec entry offset + * @max_sectors: maximum number of sectors that can be added + * @same_page: return if the segment has been merged inside the same page * - * This should only be used by passthrough bios. + * Add a page to a bio while respecting the hardware max_sectors, max_segment + * and gap limitations. */ -int __bio_add_pc_page(struct request_queue *q, struct bio *bio, +int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, - bool *same_page) + unsigned int max_sectors, bool *same_page) { struct bio_vec *bvec; - /* - * cloned bio must not modify vec list - */ - if (unlikely(bio_flagged(bio, BIO_CLONED))) + if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return 0; - if (((bio->bi_iter.bi_size + len) >> 9) > queue_max_hw_sectors(q)) + if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors) return 0; if (bio->bi_vcnt > 0) { - if (bio_try_merge_pc_page(q, bio, page, len, offset, same_page)) + if (bio_try_merge_hw_seg(q, bio, page, len, offset, same_page)) return len; /* @@ -823,11 +827,27 @@ int __bio_add_pc_page(struct request_queue *q, struct bio *bio, return len; } +/** + * bio_add_pc_page - attempt to add page to passthrough bio + * @q: the target queue + * @bio: destination bio + * @page: page to add + * @len: vec entry length + * @offset: vec entry offset + * + * Attempt to add a page to the bio_vec maplist. This can fail for a + * number of reasons, such as the bio being full or target block device + * limitations. The target block device must allow bio's up to PAGE_SIZE, + * so it is always possible to add a single page to an empty bio. + * + * This should only be used by passthrough bios. + */ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { bool same_page = false; - return __bio_add_pc_page(q, bio, page, len, offset, &same_page); + return bio_add_hw_page(q, bio, page, len, offset, + queue_max_hw_sectors(q), &same_page); } EXPORT_SYMBOL(bio_add_pc_page); @@ -936,6 +956,7 @@ void bio_release_pages(struct bio *bio, bool mark_dirty) put_page(bvec->bv_page); } } +EXPORT_SYMBOL_GPL(bio_release_pages); static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter) { @@ -1010,6 +1031,50 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) return 0; } +static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter) +{ + unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; + unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt; + struct request_queue *q = bio->bi_disk->queue; + unsigned int max_append_sectors = queue_max_zone_append_sectors(q); + struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; + struct page **pages = (struct page **)bv; + ssize_t size, left; + unsigned len, i; + size_t offset; + + if (WARN_ON_ONCE(!max_append_sectors)) + return 0; + + /* + * Move page array up in the allocated memory for the bio vecs as far as + * possible so that we can start filling biovecs from the beginning + * without overwriting the temporary page array. + */ + BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2); + pages += entries_left * (PAGE_PTRS_PER_BVEC - 1); + + size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); + if (unlikely(size <= 0)) + return size ? size : -EFAULT; + + for (left = size, i = 0; left > 0; left -= len, i++) { + struct page *page = pages[i]; + bool same_page = false; + + len = min_t(size_t, PAGE_SIZE - offset, left); + if (bio_add_hw_page(q, bio, page, len, offset, + max_append_sectors, &same_page) != len) + return -EINVAL; + if (same_page) + put_page(page); + offset = 0; + } + + iov_iter_advance(iter, size); + return 0; +} + /** * bio_iov_iter_get_pages - add user or kernel pages to a bio * @bio: bio to add pages to @@ -1039,16 +1104,23 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) return -EINVAL; do { - if (is_bvec) - ret = __bio_iov_bvec_add_pages(bio, iter); - else - ret = __bio_iov_iter_get_pages(bio, iter); + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + if (WARN_ON_ONCE(is_bvec)) + return -EINVAL; + ret = __bio_iov_append_get_pages(bio, iter); + } else { + if (is_bvec) + ret = __bio_iov_bvec_add_pages(bio, iter); + else + ret = __bio_iov_iter_get_pages(bio, iter); + } } while (!ret && iov_iter_count(iter) && !bio_full(bio, 0)); if (is_bvec) bio_set_flag(bio, BIO_NO_PAGE_REF); return bio->bi_vcnt ? 0 : ret; } +EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); static void submit_bio_wait_endio(struct bio *bio) { @@ -1105,6 +1177,7 @@ void bio_advance(struct bio *bio, unsigned bytes) if (bio_integrity(bio)) bio_integrity_advance(bio, bytes); + bio_crypt_advance(bio, bytes); bio_advance_iter(bio, &bio->bi_iter, bytes); } EXPORT_SYMBOL(bio_advance); @@ -1303,55 +1376,6 @@ defer: schedule_work(&bio_dirty_work); } -void update_io_ticks(struct hd_struct *part, unsigned long now, bool end) -{ - unsigned long stamp; -again: - stamp = READ_ONCE(part->stamp); - if (unlikely(stamp != now)) { - if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) { - __part_stat_add(part, io_ticks, end ? now - stamp : 1); - } - } - if (part->partno) { - part = &part_to_disk(part)->part0; - goto again; - } -} - -void generic_start_io_acct(struct request_queue *q, int op, - unsigned long sectors, struct hd_struct *part) -{ - const int sgrp = op_stat_group(op); - - part_stat_lock(); - - update_io_ticks(part, jiffies, false); - part_stat_inc(part, ios[sgrp]); - part_stat_add(part, sectors[sgrp], sectors); - part_inc_in_flight(q, part, op_is_write(op)); - - part_stat_unlock(); -} -EXPORT_SYMBOL(generic_start_io_acct); - -void generic_end_io_acct(struct request_queue *q, int req_op, - struct hd_struct *part, unsigned long start_time) -{ - unsigned long now = jiffies; - unsigned long duration = now - start_time; - const int sgrp = op_stat_group(req_op); - - part_stat_lock(); - - update_io_ticks(part, now, true); - part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration)); - part_dec_in_flight(q, part, op_is_write(req_op)); - - part_stat_unlock(); -} -EXPORT_SYMBOL(generic_end_io_acct); - static inline bool bio_remaining_done(struct bio *bio) { /* @@ -1445,6 +1469,10 @@ struct bio *bio_split(struct bio *bio, int sectors, BUG_ON(sectors <= 0); BUG_ON(sectors >= bio_sectors(bio)); + /* Zone append commands cannot be split */ + if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND)) + return NULL; + split = bio_clone_fast(bio, gfp, bs); if (!split) return NULL; diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 930212c1a512..0ecc897b225c 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1530,6 +1530,10 @@ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now) { u64 old = atomic64_read(&blkg->delay_start); + /* negative use_delay means no scaling, see blkcg_set_delay() */ + if (atomic_read(&blkg->use_delay) < 0) + return; + /* * We only want to scale down every second. The idea here is that we * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain @@ -1717,6 +1721,8 @@ void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) */ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) { + if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) + return; blkcg_scale_delay(blkg, now); atomic64_add(delta, &blkg->delay_nsec); } diff --git a/block/blk-core.c b/block/blk-core.c index 38d7b1f16067..03252af8c82c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -39,6 +39,8 @@ #include <linux/debugfs.h> #include <linux/bpf.h> #include <linux/psi.h> +#include <linux/sched/sysctl.h> +#include <linux/blk-crypto.h> #define CREATE_TRACE_POINTS #include <trace/events/block.h> @@ -121,6 +123,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq) rq->start_time_ns = ktime_get_ns(); rq->part = NULL; refcount_set(&rq->ref, 1); + blk_crypto_rq_set_defaults(rq); } EXPORT_SYMBOL(blk_rq_init); @@ -136,6 +139,7 @@ static const char *const blk_op_name[] = { REQ_OP_NAME(ZONE_OPEN), REQ_OP_NAME(ZONE_CLOSE), REQ_OP_NAME(ZONE_FINISH), + REQ_OP_NAME(ZONE_APPEND), REQ_OP_NAME(WRITE_SAME), REQ_OP_NAME(WRITE_ZEROES), REQ_OP_NAME(SCSI_IN), @@ -241,6 +245,17 @@ static void req_bio_endio(struct request *rq, struct bio *bio, bio_advance(bio, nbytes); + if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) { + /* + * Partial zone append completions cannot be supported as the + * BIO fragments may end up not being written sequentially. + */ + if (bio->bi_iter.bi_size) + bio->bi_status = BLK_STS_IOERR; + else + bio->bi_iter.bi_sector = rq->__sector; + } + /* don't actually finish bio if it's part of flush sequence */ if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ)) bio_endio(bio); @@ -441,6 +456,23 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) } } +static inline int bio_queue_enter(struct bio *bio) +{ + struct request_queue *q = bio->bi_disk->queue; + bool nowait = bio->bi_opf & REQ_NOWAIT; + int ret; + + ret = blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0); + if (unlikely(ret)) { + if (nowait && !blk_queue_dying(q)) + bio_wouldblock_error(bio); + else + bio_io_error(bio); + } + + return ret; +} + void blk_queue_exit(struct request_queue *q) { percpu_ref_put(&q->q_usage_counter); @@ -485,7 +517,7 @@ struct request_queue *__blk_alloc_queue(int node_id) if (ret) goto fail_id; - q->backing_dev_info = bdi_alloc_node(GFP_KERNEL, node_id); + q->backing_dev_info = bdi_alloc(node_id); if (!q->backing_dev_info) goto fail_split; @@ -495,7 +527,6 @@ struct request_queue *__blk_alloc_queue(int node_id) q->backing_dev_info->ra_pages = VM_READAHEAD_PAGES; q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK; - q->backing_dev_info->name = "block"; q->node = node_id; timer_setup(&q->backing_dev_info->laptop_mode_wb_timer, @@ -606,6 +637,16 @@ void blk_put_request(struct request *req) } EXPORT_SYMBOL(blk_put_request); +static void blk_account_io_merge_bio(struct request *req) +{ + if (!blk_do_io_stat(req)) + return; + + part_stat_lock(); + part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); + part_stat_unlock(); +} + bool bio_attempt_back_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { @@ -624,7 +665,9 @@ bool bio_attempt_back_merge(struct request *req, struct bio *bio, req->biotail = bio; req->__data_len += bio->bi_iter.bi_size; - blk_account_io_start(req, false); + bio_crypt_free_ctx(bio); + + blk_account_io_merge_bio(req); return true; } @@ -648,7 +691,9 @@ bool bio_attempt_front_merge(struct request *req, struct bio *bio, req->__sector = bio->bi_iter.bi_sector; req->__data_len += bio->bi_iter.bi_size; - blk_account_io_start(req, false); + bio_crypt_do_front_merge(req, bio); + + blk_account_io_merge_bio(req); return true; } @@ -670,7 +715,7 @@ bool bio_attempt_discard_merge(struct request_queue *q, struct request *req, req->__data_len += bio->bi_iter.bi_size; req->nr_phys_segments = segments + 1; - blk_account_io_start(req, false); + blk_account_io_merge_bio(req); return true; no_merge: req_set_nomerge(q, req); @@ -872,6 +917,41 @@ out: return ret; } +/* + * Check write append to a zoned block device. + */ +static inline blk_status_t blk_check_zone_append(struct request_queue *q, + struct bio *bio) +{ + sector_t pos = bio->bi_iter.bi_sector; + int nr_sectors = bio_sectors(bio); + + /* Only applicable to zoned block devices */ + if (!blk_queue_is_zoned(q)) + return BLK_STS_NOTSUPP; + + /* The bio sector must point to the start of a sequential zone */ + if (pos & (blk_queue_zone_sectors(q) - 1) || + !blk_queue_zone_is_seq(q, pos)) + return BLK_STS_IOERR; + + /* + * Not allowed to cross zone boundaries. Otherwise, the BIO will be + * split and could result in non-contiguous sectors being written in + * different zones. + */ + if (nr_sectors > q->limits.chunk_sectors) + return BLK_STS_IOERR; + + /* Make sure the BIO is small enough and will not get split */ + if (nr_sectors > q->limits.max_zone_append_sectors) + return BLK_STS_IOERR; + + bio->bi_opf |= REQ_NOMERGE; + + return BLK_STS_OK; +} + static noinline_for_stack bool generic_make_request_checks(struct bio *bio) { @@ -941,6 +1021,11 @@ generic_make_request_checks(struct bio *bio) if (!q->limits.max_write_same_sectors) goto not_supported; break; + case REQ_OP_ZONE_APPEND: + status = blk_check_zone_append(q, bio); + if (status != BLK_STS_OK) + goto end_io; + break; case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: @@ -961,12 +1046,13 @@ generic_make_request_checks(struct bio *bio) } /* - * Various block parts want %current->io_context and lazy ioc - * allocation ends up trading a lot of pain for a small amount of - * memory. Just allocate it upfront. This may fail and block - * layer knows how to live with it. + * Various block parts want %current->io_context, so allocate it up + * front rather than dealing with lots of pain to allocate it only + * where needed. This may fail and the block layer knows how to live + * with it. */ - create_io_context(GFP_ATOMIC, q->node); + if (unlikely(!current->io_context)) + create_task_io_context(current, GFP_ATOMIC, q->node); if (!blkcg_bio_issue_check(q, bio)) return false; @@ -988,29 +1074,28 @@ end_io: return false; } +static blk_qc_t do_make_request(struct bio *bio) +{ + struct request_queue *q = bio->bi_disk->queue; + blk_qc_t ret = BLK_QC_T_NONE; + + if (blk_crypto_bio_prep(&bio)) { + if (!q->make_request_fn) + return blk_mq_make_request(q, bio); + ret = q->make_request_fn(q, bio); + } + blk_queue_exit(q); + return ret; +} + /** - * generic_make_request - hand a buffer to its device driver for I/O + * generic_make_request - re-submit a bio to the block device layer for I/O * @bio: The bio describing the location in memory and on the device. * - * generic_make_request() is used to make I/O requests of block - * devices. It is passed a &struct bio, which describes the I/O that needs - * to be done. - * - * generic_make_request() does not return any status. The - * success/failure status of the request, along with notification of - * completion, is delivered asynchronously through the bio->bi_end_io - * function described (one day) else where. - * - * The caller of generic_make_request must make sure that bi_io_vec - * are set to describe the memory buffer, and that bi_dev and bi_sector are - * set to describe the device address, and the - * bi_end_io and optionally bi_private are set to describe how - * completion notification should be signaled. - * - * generic_make_request and the drivers it calls may use bi_next if this - * bio happens to be merged with someone else, and may resubmit the bio to - * a lower device by calling into generic_make_request recursively, which - * means the bio should NOT be touched after the call to ->make_request_fn. + * This is a version of submit_bio() that shall only be used for I/O that is + * resubmitted to lower level drivers by stacking block drivers. All file + * systems and other upper level users of the block layer should use + * submit_bio() instead. */ blk_qc_t generic_make_request(struct bio *bio) { @@ -1061,18 +1146,14 @@ blk_qc_t generic_make_request(struct bio *bio) current->bio_list = bio_list_on_stack; do { struct request_queue *q = bio->bi_disk->queue; - blk_mq_req_flags_t flags = bio->bi_opf & REQ_NOWAIT ? - BLK_MQ_REQ_NOWAIT : 0; - if (likely(blk_queue_enter(q, flags) == 0)) { + if (likely(bio_queue_enter(bio) == 0)) { struct bio_list lower, same; /* Create a fresh bio_list for all subordinate requests */ bio_list_on_stack[1] = bio_list_on_stack[0]; bio_list_init(&bio_list_on_stack[0]); - ret = q->make_request_fn(q, bio); - - blk_queue_exit(q); + ret = do_make_request(bio); /* sort new bios into those for a lower level * and those for the same level @@ -1088,12 +1169,6 @@ blk_qc_t generic_make_request(struct bio *bio) bio_list_merge(&bio_list_on_stack[0], &lower); bio_list_merge(&bio_list_on_stack[0], &same); bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); - } else { - if (unlikely(!blk_queue_dying(q) && - (bio->bi_opf & REQ_NOWAIT))) - bio_wouldblock_error(bio); - else - bio_io_error(bio); } bio = bio_list_pop(&bio_list_on_stack[0]); } while (bio); @@ -1110,30 +1185,25 @@ EXPORT_SYMBOL(generic_make_request); * * This function behaves like generic_make_request(), but does not protect * against recursion. Must only be used if the called driver is known - * to not call generic_make_request (or direct_make_request) again from - * its make_request function. (Calling direct_make_request again from - * a workqueue is perfectly fine as that doesn't recurse). + * to be blk-mq based. */ blk_qc_t direct_make_request(struct bio *bio) { struct request_queue *q = bio->bi_disk->queue; - bool nowait = bio->bi_opf & REQ_NOWAIT; - blk_qc_t ret; + if (WARN_ON_ONCE(q->make_request_fn)) { + bio_io_error(bio); + return BLK_QC_T_NONE; + } if (!generic_make_request_checks(bio)) return BLK_QC_T_NONE; - - if (unlikely(blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0))) { - if (nowait && !blk_queue_dying(q)) - bio_wouldblock_error(bio); - else - bio_io_error(bio); + if (unlikely(bio_queue_enter(bio))) + return BLK_QC_T_NONE; + if (!blk_crypto_bio_prep(&bio)) { + blk_queue_exit(q); return BLK_QC_T_NONE; } - - ret = q->make_request_fn(q, bio); - blk_queue_exit(q); - return ret; + return blk_mq_make_request(q, bio); } EXPORT_SYMBOL_GPL(direct_make_request); @@ -1141,17 +1211,17 @@ EXPORT_SYMBOL_GPL(direct_make_request); * submit_bio - submit a bio to the block device layer for I/O * @bio: The &struct bio which describes the I/O * - * submit_bio() is very similar in purpose to generic_make_request(), and - * uses that function to do most of the work. Both are fairly rough - * interfaces; @bio must be presetup and ready for I/O. + * submit_bio() is used to submit I/O requests to block devices. It is passed a + * fully set up &struct bio that describes the I/O that needs to be done. The + * bio will be send to the device described by the bi_disk and bi_partno fields. * + * The success/failure status of the request, along with notification of + * completion, is delivered asynchronously through the ->bi_end_io() callback + * in @bio. The bio must NOT be touched by thecaller until ->bi_end_io() has + * been called. */ blk_qc_t submit_bio(struct bio *bio) { - bool workingset_read = false; - unsigned long pflags; - blk_qc_t ret; - if (blkcg_punt_bio_submit(bio)) return BLK_QC_T_NONE; @@ -1170,8 +1240,6 @@ blk_qc_t submit_bio(struct bio *bio) if (op_is_write(bio_op(bio))) { count_vm_events(PGPGOUT, count); } else { - if (bio_flagged(bio, BIO_WORKINGSET)) - workingset_read = true; task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, count); } @@ -1187,20 +1255,24 @@ blk_qc_t submit_bio(struct bio *bio) } /* - * If we're reading data that is part of the userspace - * workingset, count submission time as memory stall. When the - * device is congested, or the submitting cgroup IO-throttled, - * submission can be a significant part of overall IO time. + * If we're reading data that is part of the userspace workingset, count + * submission time as memory stall. When the device is congested, or + * the submitting cgroup IO-throttled, submission can be a significant + * part of overall IO time. */ - if (workingset_read) - psi_memstall_enter(&pflags); - - ret = generic_make_request(bio); + if (unlikely(bio_op(bio) == REQ_OP_READ && + bio_flagged(bio, BIO_WORKINGSET))) { + unsigned long pflags; + blk_qc_t ret; - if (workingset_read) + psi_memstall_enter(&pflags); + ret = generic_make_request(bio); psi_memstall_leave(&pflags); - return ret; + return ret; + } + + return generic_make_request(bio); } EXPORT_SYMBOL(submit_bio); @@ -1261,8 +1333,11 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request * should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; + if (blk_crypto_insert_cloned_request(rq)) + return BLK_STS_IOERR; + if (blk_queue_io_stat(q)) - blk_account_io_start(rq, true); + blk_account_io_start(rq); /* * Since we have a scheduler attached on the top device, @@ -1314,7 +1389,22 @@ unsigned int blk_rq_err_bytes(const struct request *rq) } EXPORT_SYMBOL_GPL(blk_rq_err_bytes); -void blk_account_io_completion(struct request *req, unsigned int bytes) +static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end) +{ + unsigned long stamp; +again: + stamp = READ_ONCE(part->stamp); + if (unlikely(stamp != now)) { + if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) + __part_stat_add(part, io_ticks, end ? now - stamp : 1); + } + if (part->partno) { + part = &part_to_disk(part)->part0; + goto again; + } +} + +static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->part && blk_do_io_stat(req)) { const int sgrp = op_stat_group(req_op(req)); @@ -1345,48 +1435,57 @@ void blk_account_io_done(struct request *req, u64 now) update_io_ticks(part, jiffies, true); part_stat_inc(part, ios[sgrp]); part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); - part_dec_in_flight(req->q, part, rq_data_dir(req)); + part_stat_unlock(); hd_struct_put(part); - part_stat_unlock(); } } -void blk_account_io_start(struct request *rq, bool new_io) +void blk_account_io_start(struct request *rq) { - struct hd_struct *part; - int rw = rq_data_dir(rq); - if (!blk_do_io_stat(rq)) return; + rq->part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq)); + part_stat_lock(); + update_io_ticks(rq->part, jiffies, false); + part_stat_unlock(); +} - if (!new_io) { - part = rq->part; - part_stat_inc(part, merges[rw]); - } else { - part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq)); - if (!hd_struct_try_get(part)) { - /* - * The partition is already being removed, - * the request will be accounted on the disk only - * - * We take a reference on disk->part0 although that - * partition will never be deleted, so we can treat - * it as any other partition. - */ - part = &rq->rq_disk->part0; - hd_struct_get(part); - } - part_inc_in_flight(rq->q, part, rw); - rq->part = part; - } +unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, + unsigned int op) +{ + struct hd_struct *part = &disk->part0; + const int sgrp = op_stat_group(op); + unsigned long now = READ_ONCE(jiffies); + + part_stat_lock(); + update_io_ticks(part, now, false); + part_stat_inc(part, ios[sgrp]); + part_stat_add(part, sectors[sgrp], sectors); + part_stat_local_inc(part, in_flight[op_is_write(op)]); + part_stat_unlock(); - update_io_ticks(part, jiffies, false); + return now; +} +EXPORT_SYMBOL(disk_start_io_acct); + +void disk_end_io_acct(struct gendisk *disk, unsigned int op, + unsigned long start_time) +{ + struct hd_struct *part = &disk->part0; + const int sgrp = op_stat_group(op); + unsigned long now = READ_ONCE(jiffies); + unsigned long duration = now - start_time; + part_stat_lock(); + update_io_ticks(part, now, true); + part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration)); + part_stat_local_dec(part, in_flight[op_is_write(op)]); part_stat_unlock(); } +EXPORT_SYMBOL(disk_end_io_acct); /* * Steal bios from a request and add them to a bio list. @@ -1636,7 +1735,9 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, } rq->nr_phys_segments = rq_src->nr_phys_segments; rq->ioprio = rq_src->ioprio; - rq->extra_len = rq_src->extra_len; + + if (rq->bio) + blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask); return 0; @@ -1778,6 +1879,18 @@ void blk_finish_plug(struct blk_plug *plug) } EXPORT_SYMBOL(blk_finish_plug); +void blk_io_schedule(void) +{ + /* Prevent hang_check timer from firing at us during very long I/O */ + unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; + + if (timeout) + io_schedule_timeout(timeout); + else + io_schedule(); +} +EXPORT_SYMBOL_GPL(blk_io_schedule); + int __init blk_dev_init(void) { BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS)); diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c new file mode 100644 index 000000000000..6e49688a2d80 --- /dev/null +++ b/block/blk-crypto-fallback.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2019 Google LLC + */ + +/* + * Refer to Documentation/block/inline-encryption.rst for detailed explanation. + */ + +#define pr_fmt(fmt) "blk-crypto-fallback: " fmt + +#include <crypto/skcipher.h> +#include <linux/blk-cgroup.h> +#include <linux/blk-crypto.h> +#include <linux/blkdev.h> +#include <linux/crypto.h> +#include <linux/keyslot-manager.h> +#include <linux/mempool.h> +#include <linux/module.h> +#include <linux/random.h> + +#include "blk-crypto-internal.h" + +static unsigned int num_prealloc_bounce_pg = 32; +module_param(num_prealloc_bounce_pg, uint, 0); +MODULE_PARM_DESC(num_prealloc_bounce_pg, + "Number of preallocated bounce pages for the blk-crypto crypto API fallback"); + +static unsigned int blk_crypto_num_keyslots = 100; +module_param_named(num_keyslots, blk_crypto_num_keyslots, uint, 0); +MODULE_PARM_DESC(num_keyslots, + "Number of keyslots for the blk-crypto crypto API fallback"); + +static unsigned int num_prealloc_fallback_crypt_ctxs = 128; +module_param(num_prealloc_fallback_crypt_ctxs, uint, 0); +MODULE_PARM_DESC(num_prealloc_crypt_fallback_ctxs, + "Number of preallocated bio fallback crypto contexts for blk-crypto to use during crypto API fallback"); + +struct bio_fallback_crypt_ctx { + struct bio_crypt_ctx crypt_ctx; + /* + * Copy of the bvec_iter when this bio was submitted. + * We only want to en/decrypt the part of the bio as described by the + * bvec_iter upon submission because bio might be split before being + * resubmitted + */ + struct bvec_iter crypt_iter; + union { + struct { + struct work_struct work; + struct bio *bio; + }; + struct { + void *bi_private_orig; + bio_end_io_t *bi_end_io_orig; + }; + }; +}; + +static struct kmem_cache *bio_fallback_crypt_ctx_cache; +static mempool_t *bio_fallback_crypt_ctx_pool; + +/* + * Allocating a crypto tfm during I/O can deadlock, so we have to preallocate + * all of a mode's tfms when that mode starts being used. Since each mode may + * need all the keyslots at some point, each mode needs its own tfm for each + * keyslot; thus, a keyslot may contain tfms for multiple modes. However, to + * match the behavior of real inline encryption hardware (which only supports a + * single encryption context per keyslot), we only allow one tfm per keyslot to + * be used at a time - the rest of the unused tfms have their keys cleared. + */ +static DEFINE_MUTEX(tfms_init_lock); +static bool tfms_inited[BLK_ENCRYPTION_MODE_MAX]; + +static struct blk_crypto_keyslot { + enum blk_crypto_mode_num crypto_mode; + struct crypto_skcipher *tfms[BLK_ENCRYPTION_MODE_MAX]; +} *blk_crypto_keyslots; + +static struct blk_keyslot_manager blk_crypto_ksm; +static struct workqueue_struct *blk_crypto_wq; +static mempool_t *blk_crypto_bounce_page_pool; + +/* + * This is the key we set when evicting a keyslot. This *should* be the all 0's + * key, but AES-XTS rejects that key, so we use some random bytes instead. + */ +static u8 blank_key[BLK_CRYPTO_MAX_KEY_SIZE]; + +static void blk_crypto_evict_keyslot(unsigned int slot) +{ + struct blk_crypto_keyslot *slotp = &blk_crypto_keyslots[slot]; + enum blk_crypto_mode_num crypto_mode = slotp->crypto_mode; + int err; + + WARN_ON(slotp->crypto_mode == BLK_ENCRYPTION_MODE_INVALID); + + /* Clear the key in the skcipher */ + err = crypto_skcipher_setkey(slotp->tfms[crypto_mode], blank_key, + blk_crypto_modes[crypto_mode].keysize); + WARN_ON(err); + slotp->crypto_mode = BLK_ENCRYPTION_MODE_INVALID; +} + +static int blk_crypto_keyslot_program(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + unsigned int slot) +{ + struct blk_crypto_keyslot *slotp = &blk_crypto_keyslots[slot]; + const enum blk_crypto_mode_num crypto_mode = + key->crypto_cfg.crypto_mode; + int err; + + if (crypto_mode != slotp->crypto_mode && + slotp->crypto_mode != BLK_ENCRYPTION_MODE_INVALID) + blk_crypto_evict_keyslot(slot); + + slotp->crypto_mode = crypto_mode; + err = crypto_skcipher_setkey(slotp->tfms[crypto_mode], key->raw, + key->size); + if (err) { + blk_crypto_evict_keyslot(slot); + return err; + } + return 0; +} + +static int blk_crypto_keyslot_evict(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + unsigned int slot) +{ + blk_crypto_evict_keyslot(slot); + return 0; +} + +/* + * The crypto API fallback KSM ops - only used for a bio when it specifies a + * blk_crypto_key that was not supported by the device's inline encryption + * hardware. + */ +static const struct blk_ksm_ll_ops blk_crypto_ksm_ll_ops = { + .keyslot_program = blk_crypto_keyslot_program, + .keyslot_evict = blk_crypto_keyslot_evict, +}; + +static void blk_crypto_fallback_encrypt_endio(struct bio *enc_bio) +{ + struct bio *src_bio = enc_bio->bi_private; + int i; + + for (i = 0; i < enc_bio->bi_vcnt; i++) + mempool_free(enc_bio->bi_io_vec[i].bv_page, + blk_crypto_bounce_page_pool); + + src_bio->bi_status = enc_bio->bi_status; + + bio_put(enc_bio); + bio_endio(src_bio); +} + +static struct bio *blk_crypto_clone_bio(struct bio *bio_src) +{ + struct bvec_iter iter; + struct bio_vec bv; + struct bio *bio; + + bio = bio_alloc_bioset(GFP_NOIO, bio_segments(bio_src), NULL); + if (!bio) + return NULL; + bio->bi_disk = bio_src->bi_disk; + bio->bi_opf = bio_src->bi_opf; + bio->bi_ioprio = bio_src->bi_ioprio; + bio->bi_write_hint = bio_src->bi_write_hint; + bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; + bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; + + bio_for_each_segment(bv, bio_src, iter) + bio->bi_io_vec[bio->bi_vcnt++] = bv; + + bio_clone_blkg_association(bio, bio_src); + blkcg_bio_issue_init(bio); + + return bio; +} + +static bool blk_crypto_alloc_cipher_req(struct blk_ksm_keyslot *slot, + struct skcipher_request **ciph_req_ret, + struct crypto_wait *wait) +{ + struct skcipher_request *ciph_req; + const struct blk_crypto_keyslot *slotp; + int keyslot_idx = blk_ksm_get_slot_idx(slot); + + slotp = &blk_crypto_keyslots[keyslot_idx]; + ciph_req = skcipher_request_alloc(slotp->tfms[slotp->crypto_mode], + GFP_NOIO); + if (!ciph_req) + return false; + + skcipher_request_set_callback(ciph_req, + CRYPTO_TFM_REQ_MAY_BACKLOG | + CRYPTO_TFM_REQ_MAY_SLEEP, + crypto_req_done, wait); + *ciph_req_ret = ciph_req; + + return true; +} + +static bool blk_crypto_split_bio_if_needed(struct bio **bio_ptr) +{ + struct bio *bio = *bio_ptr; + unsigned int i = 0; + unsigned int num_sectors = 0; + struct bio_vec bv; + struct bvec_iter iter; + + bio_for_each_segment(bv, bio, iter) { + num_sectors += bv.bv_len >> SECTOR_SHIFT; + if (++i == BIO_MAX_PAGES) + break; + } + if (num_sectors < bio_sectors(bio)) { + struct bio *split_bio; + + split_bio = bio_split(bio, num_sectors, GFP_NOIO, NULL); + if (!split_bio) { + bio->bi_status = BLK_STS_RESOURCE; + return false; + } + bio_chain(split_bio, bio); + generic_make_request(bio); + *bio_ptr = split_bio; + } + + return true; +} + +union blk_crypto_iv { + __le64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; + u8 bytes[BLK_CRYPTO_MAX_IV_SIZE]; +}; + +static void blk_crypto_dun_to_iv(const u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], + union blk_crypto_iv *iv) +{ + int i; + + for (i = 0; i < BLK_CRYPTO_DUN_ARRAY_SIZE; i++) + iv->dun[i] = cpu_to_le64(dun[i]); +} + +/* + * The crypto API fallback's encryption routine. + * Allocate a bounce bio for encryption, encrypt the input bio using crypto API, + * and replace *bio_ptr with the bounce bio. May split input bio if it's too + * large. Returns true on success. Returns false and sets bio->bi_status on + * error. + */ +static bool blk_crypto_fallback_encrypt_bio(struct bio **bio_ptr) +{ + struct bio *src_bio, *enc_bio; + struct bio_crypt_ctx *bc; + struct blk_ksm_keyslot *slot; + int data_unit_size; + struct skcipher_request *ciph_req = NULL; + DECLARE_CRYPTO_WAIT(wait); + u64 curr_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; + struct scatterlist src, dst; + union blk_crypto_iv iv; + unsigned int i, j; + bool ret = false; + blk_status_t blk_st; + + /* Split the bio if it's too big for single page bvec */ + if (!blk_crypto_split_bio_if_needed(bio_ptr)) + return false; + + src_bio = *bio_ptr; + bc = src_bio->bi_crypt_context; + data_unit_size = bc->bc_key->crypto_cfg.data_unit_size; + + /* Allocate bounce bio for encryption */ + enc_bio = blk_crypto_clone_bio(src_bio); + if (!enc_bio) { + src_bio->bi_status = BLK_STS_RESOURCE; + return false; + } + + /* + * Use the crypto API fallback keyslot manager to get a crypto_skcipher + * for the algorithm and key specified for this bio. + */ + blk_st = blk_ksm_get_slot_for_key(&blk_crypto_ksm, bc->bc_key, &slot); + if (blk_st != BLK_STS_OK) { + src_bio->bi_status = blk_st; + goto out_put_enc_bio; + } + + /* and then allocate an skcipher_request for it */ + if (!blk_crypto_alloc_cipher_req(slot, &ciph_req, &wait)) { + src_bio->bi_status = BLK_STS_RESOURCE; + goto out_release_keyslot; + } + + memcpy(curr_dun, bc->bc_dun, sizeof(curr_dun)); + sg_init_table(&src, 1); + sg_init_table(&dst, 1); + + skcipher_request_set_crypt(ciph_req, &src, &dst, data_unit_size, + iv.bytes); + + /* Encrypt each page in the bounce bio */ + for (i = 0; i < enc_bio->bi_vcnt; i++) { + struct bio_vec *enc_bvec = &enc_bio->bi_io_vec[i]; + struct page *plaintext_page = enc_bvec->bv_page; + struct page *ciphertext_page = + mempool_alloc(blk_crypto_bounce_page_pool, GFP_NOIO); + + enc_bvec->bv_page = ciphertext_page; + + if (!ciphertext_page) { + src_bio->bi_status = BLK_STS_RESOURCE; + goto out_free_bounce_pages; + } + + sg_set_page(&src, plaintext_page, data_unit_size, + enc_bvec->bv_offset); + sg_set_page(&dst, ciphertext_page, data_unit_size, + enc_bvec->bv_offset); + + /* Encrypt each data unit in this page */ + for (j = 0; j < enc_bvec->bv_len; j += data_unit_size) { + blk_crypto_dun_to_iv(curr_dun, &iv); + if (crypto_wait_req(crypto_skcipher_encrypt(ciph_req), + &wait)) { + i++; + src_bio->bi_status = BLK_STS_IOERR; + goto out_free_bounce_pages; + } + bio_crypt_dun_increment(curr_dun, 1); + src.offset += data_unit_size; + dst.offset += data_unit_size; + } + } + + enc_bio->bi_private = src_bio; + enc_bio->bi_end_io = blk_crypto_fallback_encrypt_endio; + *bio_ptr = enc_bio; + ret = true; + + enc_bio = NULL; + goto out_free_ciph_req; + +out_free_bounce_pages: + while (i > 0) + mempool_free(enc_bio->bi_io_vec[--i].bv_page, + blk_crypto_bounce_page_pool); +out_free_ciph_req: + skcipher_request_free(ciph_req); +out_release_keyslot: + blk_ksm_put_slot(slot); +out_put_enc_bio: + if (enc_bio) + bio_put(enc_bio); + + return ret; +} + +/* + * The crypto API fallback's main decryption routine. + * Decrypts input bio in place, and calls bio_endio on the bio. + */ +static void blk_crypto_fallback_decrypt_bio(struct work_struct *work) +{ + struct bio_fallback_crypt_ctx *f_ctx = + container_of(work, struct bio_fallback_crypt_ctx, work); + struct bio *bio = f_ctx->bio; + struct bio_crypt_ctx *bc = &f_ctx->crypt_ctx; + struct blk_ksm_keyslot *slot; + struct skcipher_request *ciph_req = NULL; + DECLARE_CRYPTO_WAIT(wait); + u64 curr_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; + union blk_crypto_iv iv; + struct scatterlist sg; + struct bio_vec bv; + struct bvec_iter iter; + const int data_unit_size = bc->bc_key->crypto_cfg.data_unit_size; + unsigned int i; + blk_status_t blk_st; + + /* + * Use the crypto API fallback keyslot manager to get a crypto_skcipher + * for the algorithm and key specified for this bio. + */ + blk_st = blk_ksm_get_slot_for_key(&blk_crypto_ksm, bc->bc_key, &slot); + if (blk_st != BLK_STS_OK) { + bio->bi_status = blk_st; + goto out_no_keyslot; + } + + /* and then allocate an skcipher_request for it */ + if (!blk_crypto_alloc_cipher_req(slot, &ciph_req, &wait)) { + bio->bi_status = BLK_STS_RESOURCE; + goto out; + } + + memcpy(curr_dun, bc->bc_dun, sizeof(curr_dun)); + sg_init_table(&sg, 1); + skcipher_request_set_crypt(ciph_req, &sg, &sg, data_unit_size, + iv.bytes); + + /* Decrypt each segment in the bio */ + __bio_for_each_segment(bv, bio, iter, f_ctx->crypt_iter) { + struct page *page = bv.bv_page; + + sg_set_page(&sg, page, data_unit_size, bv.bv_offset); + + /* Decrypt each data unit in the segment */ + for (i = 0; i < bv.bv_len; i += data_unit_size) { + blk_crypto_dun_to_iv(curr_dun, &iv); + if (crypto_wait_req(crypto_skcipher_decrypt(ciph_req), + &wait)) { + bio->bi_status = BLK_STS_IOERR; + goto out; + } + bio_crypt_dun_increment(curr_dun, 1); + sg.offset += data_unit_size; + } + } + +out: + skcipher_request_free(ciph_req); + blk_ksm_put_slot(slot); +out_no_keyslot: + mempool_free(f_ctx, bio_fallback_crypt_ctx_pool); + bio_endio(bio); +} + +/** + * blk_crypto_fallback_decrypt_endio - queue bio for fallback decryption + * + * @bio: the bio to queue + * + * Restore bi_private and bi_end_io, and queue the bio for decryption into a + * workqueue, since this function will be called from an atomic context. + */ +static void blk_crypto_fallback_decrypt_endio(struct bio *bio) +{ + struct bio_fallback_crypt_ctx *f_ctx = bio->bi_private; + + bio->bi_private = f_ctx->bi_private_orig; + bio->bi_end_io = f_ctx->bi_end_io_orig; + + /* If there was an IO error, don't queue for decrypt. */ + if (bio->bi_status) { + mempool_free(f_ctx, bio_fallback_crypt_ctx_pool); + bio_endio(bio); + return; + } + + INIT_WORK(&f_ctx->work, blk_crypto_fallback_decrypt_bio); + f_ctx->bio = bio; + queue_work(blk_crypto_wq, &f_ctx->work); +} + +/** + * blk_crypto_fallback_bio_prep - Prepare a bio to use fallback en/decryption + * + * @bio_ptr: pointer to the bio to prepare + * + * If bio is doing a WRITE operation, this splits the bio into two parts if it's + * too big (see blk_crypto_split_bio_if_needed). It then allocates a bounce bio + * for the first part, encrypts it, and update bio_ptr to point to the bounce + * bio. + * + * For a READ operation, we mark the bio for decryption by using bi_private and + * bi_end_io. + * + * In either case, this function will make the bio look like a regular bio (i.e. + * as if no encryption context was ever specified) for the purposes of the rest + * of the stack except for blk-integrity (blk-integrity and blk-crypto are not + * currently supported together). + * + * Return: true on success. Sets bio->bi_status and returns false on error. + */ +bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr) +{ + struct bio *bio = *bio_ptr; + struct bio_crypt_ctx *bc = bio->bi_crypt_context; + struct bio_fallback_crypt_ctx *f_ctx; + + if (WARN_ON_ONCE(!tfms_inited[bc->bc_key->crypto_cfg.crypto_mode])) { + /* User didn't call blk_crypto_start_using_key() first */ + bio->bi_status = BLK_STS_IOERR; + return false; + } + + if (!blk_ksm_crypto_cfg_supported(&blk_crypto_ksm, + &bc->bc_key->crypto_cfg)) { + bio->bi_status = BLK_STS_NOTSUPP; + return false; + } + + if (bio_data_dir(bio) == WRITE) + return blk_crypto_fallback_encrypt_bio(bio_ptr); + + /* + * bio READ case: Set up a f_ctx in the bio's bi_private and set the + * bi_end_io appropriately to trigger decryption when the bio is ended. + */ + f_ctx = mempool_alloc(bio_fallback_crypt_ctx_pool, GFP_NOIO); + f_ctx->crypt_ctx = *bc; + f_ctx->crypt_iter = bio->bi_iter; + f_ctx->bi_private_orig = bio->bi_private; + f_ctx->bi_end_io_orig = bio->bi_end_io; + bio->bi_private = (void *)f_ctx; + bio->bi_end_io = blk_crypto_fallback_decrypt_endio; + bio_crypt_free_ctx(bio); + + return true; +} + +int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key) +{ + return blk_ksm_evict_key(&blk_crypto_ksm, key); +} + +static bool blk_crypto_fallback_inited; +static int blk_crypto_fallback_init(void) +{ + int i; + int err; + + if (blk_crypto_fallback_inited) + return 0; + + prandom_bytes(blank_key, BLK_CRYPTO_MAX_KEY_SIZE); + + err = blk_ksm_init(&blk_crypto_ksm, blk_crypto_num_keyslots); + if (err) + goto out; + err = -ENOMEM; + + blk_crypto_ksm.ksm_ll_ops = blk_crypto_ksm_ll_ops; + blk_crypto_ksm.max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE; + + /* All blk-crypto modes have a crypto API fallback. */ + for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++) + blk_crypto_ksm.crypto_modes_supported[i] = 0xFFFFFFFF; + blk_crypto_ksm.crypto_modes_supported[BLK_ENCRYPTION_MODE_INVALID] = 0; + + blk_crypto_wq = alloc_workqueue("blk_crypto_wq", + WQ_UNBOUND | WQ_HIGHPRI | + WQ_MEM_RECLAIM, num_online_cpus()); + if (!blk_crypto_wq) + goto fail_free_ksm; + + blk_crypto_keyslots = kcalloc(blk_crypto_num_keyslots, + sizeof(blk_crypto_keyslots[0]), + GFP_KERNEL); + if (!blk_crypto_keyslots) + goto fail_free_wq; + + blk_crypto_bounce_page_pool = + mempool_create_page_pool(num_prealloc_bounce_pg, 0); + if (!blk_crypto_bounce_page_pool) + goto fail_free_keyslots; + + bio_fallback_crypt_ctx_cache = KMEM_CACHE(bio_fallback_crypt_ctx, 0); + if (!bio_fallback_crypt_ctx_cache) + goto fail_free_bounce_page_pool; + + bio_fallback_crypt_ctx_pool = + mempool_create_slab_pool(num_prealloc_fallback_crypt_ctxs, + bio_fallback_crypt_ctx_cache); + if (!bio_fallback_crypt_ctx_pool) + goto fail_free_crypt_ctx_cache; + + blk_crypto_fallback_inited = true; + + return 0; +fail_free_crypt_ctx_cache: + kmem_cache_destroy(bio_fallback_crypt_ctx_cache); +fail_free_bounce_page_pool: + mempool_destroy(blk_crypto_bounce_page_pool); +fail_free_keyslots: + kfree(blk_crypto_keyslots); +fail_free_wq: + destroy_workqueue(blk_crypto_wq); +fail_free_ksm: + blk_ksm_destroy(&blk_crypto_ksm); +out: + return err; +} + +/* + * Prepare blk-crypto-fallback for the specified crypto mode. + * Returns -ENOPKG if the needed crypto API support is missing. + */ +int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num) +{ + const char *cipher_str = blk_crypto_modes[mode_num].cipher_str; + struct blk_crypto_keyslot *slotp; + unsigned int i; + int err = 0; + + /* + * Fast path + * Ensure that updates to blk_crypto_keyslots[i].tfms[mode_num] + * for each i are visible before we try to access them. + */ + if (likely(smp_load_acquire(&tfms_inited[mode_num]))) + return 0; + + mutex_lock(&tfms_init_lock); + if (tfms_inited[mode_num]) + goto out; + + err = blk_crypto_fallback_init(); + if (err) + goto out; + + for (i = 0; i < blk_crypto_num_keyslots; i++) { + slotp = &blk_crypto_keyslots[i]; + slotp->tfms[mode_num] = crypto_alloc_skcipher(cipher_str, 0, 0); + if (IS_ERR(slotp->tfms[mode_num])) { + err = PTR_ERR(slotp->tfms[mode_num]); + if (err == -ENOENT) { + pr_warn_once("Missing crypto API support for \"%s\"\n", + cipher_str); + err = -ENOPKG; + } + slotp->tfms[mode_num] = NULL; + goto out_free_tfms; + } + + crypto_skcipher_set_flags(slotp->tfms[mode_num], + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); + } + + /* + * Ensure that updates to blk_crypto_keyslots[i].tfms[mode_num] + * for each i are visible before we set tfms_inited[mode_num]. + */ + smp_store_release(&tfms_inited[mode_num], true); + goto out; + +out_free_tfms: + for (i = 0; i < blk_crypto_num_keyslots; i++) { + slotp = &blk_crypto_keyslots[i]; + crypto_free_skcipher(slotp->tfms[mode_num]); + slotp->tfms[mode_num] = NULL; + } +out: + mutex_unlock(&tfms_init_lock); + return err; +} diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h new file mode 100644 index 000000000000..d2b0f565d83c --- /dev/null +++ b/block/blk-crypto-internal.h @@ -0,0 +1,201 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2019 Google LLC + */ + +#ifndef __LINUX_BLK_CRYPTO_INTERNAL_H +#define __LINUX_BLK_CRYPTO_INTERNAL_H + +#include <linux/bio.h> +#include <linux/blkdev.h> + +/* Represents a crypto mode supported by blk-crypto */ +struct blk_crypto_mode { + const char *cipher_str; /* crypto API name (for fallback case) */ + unsigned int keysize; /* key size in bytes */ + unsigned int ivsize; /* iv size in bytes */ +}; + +extern const struct blk_crypto_mode blk_crypto_modes[]; + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + +void bio_crypt_dun_increment(u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], + unsigned int inc); + +bool bio_crypt_rq_ctx_compatible(struct request *rq, struct bio *bio); + +bool bio_crypt_ctx_mergeable(struct bio_crypt_ctx *bc1, unsigned int bc1_bytes, + struct bio_crypt_ctx *bc2); + +static inline bool bio_crypt_ctx_back_mergeable(struct request *req, + struct bio *bio) +{ + return bio_crypt_ctx_mergeable(req->crypt_ctx, blk_rq_bytes(req), + bio->bi_crypt_context); +} + +static inline bool bio_crypt_ctx_front_mergeable(struct request *req, + struct bio *bio) +{ + return bio_crypt_ctx_mergeable(bio->bi_crypt_context, + bio->bi_iter.bi_size, req->crypt_ctx); +} + +static inline bool bio_crypt_ctx_merge_rq(struct request *req, + struct request *next) +{ + return bio_crypt_ctx_mergeable(req->crypt_ctx, blk_rq_bytes(req), + next->crypt_ctx); +} + +static inline void blk_crypto_rq_set_defaults(struct request *rq) +{ + rq->crypt_ctx = NULL; + rq->crypt_keyslot = NULL; +} + +static inline bool blk_crypto_rq_is_encrypted(struct request *rq) +{ + return rq->crypt_ctx; +} + +#else /* CONFIG_BLK_INLINE_ENCRYPTION */ + +static inline bool bio_crypt_rq_ctx_compatible(struct request *rq, + struct bio *bio) +{ + return true; +} + +static inline bool bio_crypt_ctx_front_mergeable(struct request *req, + struct bio *bio) +{ + return true; +} + +static inline bool bio_crypt_ctx_back_mergeable(struct request *req, + struct bio *bio) +{ + return true; +} + +static inline bool bio_crypt_ctx_merge_rq(struct request *req, + struct request *next) +{ + return true; +} + +static inline void blk_crypto_rq_set_defaults(struct request *rq) { } + +static inline bool blk_crypto_rq_is_encrypted(struct request *rq) +{ + return false; +} + +#endif /* CONFIG_BLK_INLINE_ENCRYPTION */ + +void __bio_crypt_advance(struct bio *bio, unsigned int bytes); +static inline void bio_crypt_advance(struct bio *bio, unsigned int bytes) +{ + if (bio_has_crypt_ctx(bio)) + __bio_crypt_advance(bio, bytes); +} + +void __bio_crypt_free_ctx(struct bio *bio); +static inline void bio_crypt_free_ctx(struct bio *bio) +{ + if (bio_has_crypt_ctx(bio)) + __bio_crypt_free_ctx(bio); +} + +static inline void bio_crypt_do_front_merge(struct request *rq, + struct bio *bio) +{ +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + if (bio_has_crypt_ctx(bio)) + memcpy(rq->crypt_ctx->bc_dun, bio->bi_crypt_context->bc_dun, + sizeof(rq->crypt_ctx->bc_dun)); +#endif +} + +bool __blk_crypto_bio_prep(struct bio **bio_ptr); +static inline bool blk_crypto_bio_prep(struct bio **bio_ptr) +{ + if (bio_has_crypt_ctx(*bio_ptr)) + return __blk_crypto_bio_prep(bio_ptr); + return true; +} + +blk_status_t __blk_crypto_init_request(struct request *rq); +static inline blk_status_t blk_crypto_init_request(struct request *rq) +{ + if (blk_crypto_rq_is_encrypted(rq)) + return __blk_crypto_init_request(rq); + return BLK_STS_OK; +} + +void __blk_crypto_free_request(struct request *rq); +static inline void blk_crypto_free_request(struct request *rq) +{ + if (blk_crypto_rq_is_encrypted(rq)) + __blk_crypto_free_request(rq); +} + +void __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, + gfp_t gfp_mask); +static inline void blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, + gfp_t gfp_mask) +{ + if (bio_has_crypt_ctx(bio)) + __blk_crypto_rq_bio_prep(rq, bio, gfp_mask); +} + +/** + * blk_crypto_insert_cloned_request - Prepare a cloned request to be inserted + * into a request queue. + * @rq: the request being queued + * + * Return: BLK_STS_OK on success, nonzero on error. + */ +static inline blk_status_t blk_crypto_insert_cloned_request(struct request *rq) +{ + + if (blk_crypto_rq_is_encrypted(rq)) + return blk_crypto_init_request(rq); + return BLK_STS_OK; +} + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK + +int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num); + +bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr); + +int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key); + +#else /* CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK */ + +static inline int +blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num) +{ + pr_warn_once("crypto API fallback is disabled\n"); + return -ENOPKG; +} + +static inline bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr) +{ + pr_warn_once("crypto API fallback disabled; failing request.\n"); + (*bio_ptr)->bi_status = BLK_STS_NOTSUPP; + return false; +} + +static inline int +blk_crypto_fallback_evict_key(const struct blk_crypto_key *key) +{ + return 0; +} + +#endif /* CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK */ + +#endif /* __LINUX_BLK_CRYPTO_INTERNAL_H */ diff --git a/block/blk-crypto.c b/block/blk-crypto.c new file mode 100644 index 000000000000..6533c9b36ab8 --- /dev/null +++ b/block/blk-crypto.c @@ -0,0 +1,404 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2019 Google LLC + */ + +/* + * Refer to Documentation/block/inline-encryption.rst for detailed explanation. + */ + +#define pr_fmt(fmt) "blk-crypto: " fmt + +#include <linux/bio.h> +#include <linux/blkdev.h> +#include <linux/keyslot-manager.h> +#include <linux/module.h> +#include <linux/slab.h> + +#include "blk-crypto-internal.h" + +const struct blk_crypto_mode blk_crypto_modes[] = { + [BLK_ENCRYPTION_MODE_AES_256_XTS] = { + .cipher_str = "xts(aes)", + .keysize = 64, + .ivsize = 16, + }, + [BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV] = { + .cipher_str = "essiv(cbc(aes),sha256)", + .keysize = 16, + .ivsize = 16, + }, + [BLK_ENCRYPTION_MODE_ADIANTUM] = { + .cipher_str = "adiantum(xchacha12,aes)", + .keysize = 32, + .ivsize = 32, + }, +}; + +/* + * This number needs to be at least (the number of threads doing IO + * concurrently) * (maximum recursive depth of a bio), so that we don't + * deadlock on crypt_ctx allocations. The default is chosen to be the same + * as the default number of post read contexts in both EXT4 and F2FS. + */ +static int num_prealloc_crypt_ctxs = 128; + +module_param(num_prealloc_crypt_ctxs, int, 0444); +MODULE_PARM_DESC(num_prealloc_crypt_ctxs, + "Number of bio crypto contexts to preallocate"); + +static struct kmem_cache *bio_crypt_ctx_cache; +static mempool_t *bio_crypt_ctx_pool; + +static int __init bio_crypt_ctx_init(void) +{ + size_t i; + + bio_crypt_ctx_cache = KMEM_CACHE(bio_crypt_ctx, 0); + if (!bio_crypt_ctx_cache) + goto out_no_mem; + + bio_crypt_ctx_pool = mempool_create_slab_pool(num_prealloc_crypt_ctxs, + bio_crypt_ctx_cache); + if (!bio_crypt_ctx_pool) + goto out_no_mem; + + /* This is assumed in various places. */ + BUILD_BUG_ON(BLK_ENCRYPTION_MODE_INVALID != 0); + + /* Sanity check that no algorithm exceeds the defined limits. */ + for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++) { + BUG_ON(blk_crypto_modes[i].keysize > BLK_CRYPTO_MAX_KEY_SIZE); + BUG_ON(blk_crypto_modes[i].ivsize > BLK_CRYPTO_MAX_IV_SIZE); + } + + return 0; +out_no_mem: + panic("Failed to allocate mem for bio crypt ctxs\n"); +} +subsys_initcall(bio_crypt_ctx_init); + +void bio_crypt_set_ctx(struct bio *bio, const struct blk_crypto_key *key, + const u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], gfp_t gfp_mask) +{ + struct bio_crypt_ctx *bc = mempool_alloc(bio_crypt_ctx_pool, gfp_mask); + + bc->bc_key = key; + memcpy(bc->bc_dun, dun, sizeof(bc->bc_dun)); + + bio->bi_crypt_context = bc; +} + +void __bio_crypt_free_ctx(struct bio *bio) +{ + mempool_free(bio->bi_crypt_context, bio_crypt_ctx_pool); + bio->bi_crypt_context = NULL; +} + +void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask) +{ + dst->bi_crypt_context = mempool_alloc(bio_crypt_ctx_pool, gfp_mask); + *dst->bi_crypt_context = *src->bi_crypt_context; +} +EXPORT_SYMBOL_GPL(__bio_crypt_clone); + +/* Increments @dun by @inc, treating @dun as a multi-limb integer. */ +void bio_crypt_dun_increment(u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], + unsigned int inc) +{ + int i; + + for (i = 0; inc && i < BLK_CRYPTO_DUN_ARRAY_SIZE; i++) { + dun[i] += inc; + /* + * If the addition in this limb overflowed, then we need to + * carry 1 into the next limb. Else the carry is 0. + */ + if (dun[i] < inc) + inc = 1; + else + inc = 0; + } +} + +void __bio_crypt_advance(struct bio *bio, unsigned int bytes) +{ + struct bio_crypt_ctx *bc = bio->bi_crypt_context; + + bio_crypt_dun_increment(bc->bc_dun, + bytes >> bc->bc_key->data_unit_size_bits); +} + +/* + * Returns true if @bc->bc_dun plus @bytes converted to data units is equal to + * @next_dun, treating the DUNs as multi-limb integers. + */ +bool bio_crypt_dun_is_contiguous(const struct bio_crypt_ctx *bc, + unsigned int bytes, + const u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]) +{ + int i; + unsigned int carry = bytes >> bc->bc_key->data_unit_size_bits; + + for (i = 0; i < BLK_CRYPTO_DUN_ARRAY_SIZE; i++) { + if (bc->bc_dun[i] + carry != next_dun[i]) + return false; + /* + * If the addition in this limb overflowed, then we need to + * carry 1 into the next limb. Else the carry is 0. + */ + if ((bc->bc_dun[i] + carry) < carry) + carry = 1; + else + carry = 0; + } + + /* If the DUN wrapped through 0, don't treat it as contiguous. */ + return carry == 0; +} + +/* + * Checks that two bio crypt contexts are compatible - i.e. that + * they are mergeable except for data_unit_num continuity. + */ +static bool bio_crypt_ctx_compatible(struct bio_crypt_ctx *bc1, + struct bio_crypt_ctx *bc2) +{ + if (!bc1) + return !bc2; + + return bc2 && bc1->bc_key == bc2->bc_key; +} + +bool bio_crypt_rq_ctx_compatible(struct request *rq, struct bio *bio) +{ + return bio_crypt_ctx_compatible(rq->crypt_ctx, bio->bi_crypt_context); +} + +/* + * Checks that two bio crypt contexts are compatible, and also + * that their data_unit_nums are continuous (and can hence be merged) + * in the order @bc1 followed by @bc2. + */ +bool bio_crypt_ctx_mergeable(struct bio_crypt_ctx *bc1, unsigned int bc1_bytes, + struct bio_crypt_ctx *bc2) +{ + if (!bio_crypt_ctx_compatible(bc1, bc2)) + return false; + + return !bc1 || bio_crypt_dun_is_contiguous(bc1, bc1_bytes, bc2->bc_dun); +} + +/* Check that all I/O segments are data unit aligned. */ +static bool bio_crypt_check_alignment(struct bio *bio) +{ + const unsigned int data_unit_size = + bio->bi_crypt_context->bc_key->crypto_cfg.data_unit_size; + struct bvec_iter iter; + struct bio_vec bv; + + bio_for_each_segment(bv, bio, iter) { + if (!IS_ALIGNED(bv.bv_len | bv.bv_offset, data_unit_size)) + return false; + } + + return true; +} + +blk_status_t __blk_crypto_init_request(struct request *rq) +{ + return blk_ksm_get_slot_for_key(rq->q->ksm, rq->crypt_ctx->bc_key, + &rq->crypt_keyslot); +} + +/** + * __blk_crypto_free_request - Uninitialize the crypto fields of a request. + * + * @rq: The request whose crypto fields to uninitialize. + * + * Completely uninitializes the crypto fields of a request. If a keyslot has + * been programmed into some inline encryption hardware, that keyslot is + * released. The rq->crypt_ctx is also freed. + */ +void __blk_crypto_free_request(struct request *rq) +{ + blk_ksm_put_slot(rq->crypt_keyslot); + mempool_free(rq->crypt_ctx, bio_crypt_ctx_pool); + blk_crypto_rq_set_defaults(rq); +} + +/** + * __blk_crypto_bio_prep - Prepare bio for inline encryption + * + * @bio_ptr: pointer to original bio pointer + * + * If the bio crypt context provided for the bio is supported by the underlying + * device's inline encryption hardware, do nothing. + * + * Otherwise, try to perform en/decryption for this bio by falling back to the + * kernel crypto API. When the crypto API fallback is used for encryption, + * blk-crypto may choose to split the bio into 2 - the first one that will + * continue to be processed and the second one that will be resubmitted via + * generic_make_request. A bounce bio will be allocated to encrypt the contents + * of the aforementioned "first one", and *bio_ptr will be updated to this + * bounce bio. + * + * Caller must ensure bio has bio_crypt_ctx. + * + * Return: true on success; false on error (and bio->bi_status will be set + * appropriately, and bio_endio() will have been called so bio + * submission should abort). + */ +bool __blk_crypto_bio_prep(struct bio **bio_ptr) +{ + struct bio *bio = *bio_ptr; + const struct blk_crypto_key *bc_key = bio->bi_crypt_context->bc_key; + + /* Error if bio has no data. */ + if (WARN_ON_ONCE(!bio_has_data(bio))) { + bio->bi_status = BLK_STS_IOERR; + goto fail; + } + + if (!bio_crypt_check_alignment(bio)) { + bio->bi_status = BLK_STS_IOERR; + goto fail; + } + + /* + * Success if device supports the encryption context, or if we succeeded + * in falling back to the crypto API. + */ + if (blk_ksm_crypto_cfg_supported(bio->bi_disk->queue->ksm, + &bc_key->crypto_cfg)) + return true; + + if (blk_crypto_fallback_bio_prep(bio_ptr)) + return true; +fail: + bio_endio(*bio_ptr); + return false; +} + +/** + * __blk_crypto_rq_bio_prep - Prepare a request's crypt_ctx when its first bio + * is inserted + * + * @rq: The request to prepare + * @bio: The first bio being inserted into the request + * @gfp_mask: gfp mask + */ +void __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, + gfp_t gfp_mask) +{ + if (!rq->crypt_ctx) + rq->crypt_ctx = mempool_alloc(bio_crypt_ctx_pool, gfp_mask); + *rq->crypt_ctx = *bio->bi_crypt_context; +} + +/** + * blk_crypto_init_key() - Prepare a key for use with blk-crypto + * @blk_key: Pointer to the blk_crypto_key to initialize. + * @raw_key: Pointer to the raw key. Must be the correct length for the chosen + * @crypto_mode; see blk_crypto_modes[]. + * @crypto_mode: identifier for the encryption algorithm to use + * @dun_bytes: number of bytes that will be used to specify the DUN when this + * key is used + * @data_unit_size: the data unit size to use for en/decryption + * + * Return: 0 on success, -errno on failure. The caller is responsible for + * zeroizing both blk_key and raw_key when done with them. + */ +int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, + enum blk_crypto_mode_num crypto_mode, + unsigned int dun_bytes, + unsigned int data_unit_size) +{ + const struct blk_crypto_mode *mode; + + memset(blk_key, 0, sizeof(*blk_key)); + + if (crypto_mode >= ARRAY_SIZE(blk_crypto_modes)) + return -EINVAL; + + mode = &blk_crypto_modes[crypto_mode]; + if (mode->keysize == 0) + return -EINVAL; + + if (dun_bytes == 0 || dun_bytes > BLK_CRYPTO_MAX_IV_SIZE) + return -EINVAL; + + if (!is_power_of_2(data_unit_size)) + return -EINVAL; + + blk_key->crypto_cfg.crypto_mode = crypto_mode; + blk_key->crypto_cfg.dun_bytes = dun_bytes; + blk_key->crypto_cfg.data_unit_size = data_unit_size; + blk_key->data_unit_size_bits = ilog2(data_unit_size); + blk_key->size = mode->keysize; + memcpy(blk_key->raw, raw_key, mode->keysize); + + return 0; +} + +/* + * Check if bios with @cfg can be en/decrypted by blk-crypto (i.e. either the + * request queue it's submitted to supports inline crypto, or the + * blk-crypto-fallback is enabled and supports the cfg). + */ +bool blk_crypto_config_supported(struct request_queue *q, + const struct blk_crypto_config *cfg) +{ + return IS_ENABLED(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) || + blk_ksm_crypto_cfg_supported(q->ksm, cfg); +} + +/** + * blk_crypto_start_using_key() - Start using a blk_crypto_key on a device + * @key: A key to use on the device + * @q: the request queue for the device + * + * Upper layers must call this function to ensure that either the hardware + * supports the key's crypto settings, or the crypto API fallback has transforms + * for the needed mode allocated and ready to go. This function may allocate + * an skcipher, and *should not* be called from the data path, since that might + * cause a deadlock + * + * Return: 0 on success; -ENOPKG if the hardware doesn't support the key and + * blk-crypto-fallback is either disabled or the needed algorithm + * is disabled in the crypto API; or another -errno code. + */ +int blk_crypto_start_using_key(const struct blk_crypto_key *key, + struct request_queue *q) +{ + if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg)) + return 0; + return blk_crypto_fallback_start_using_mode(key->crypto_cfg.crypto_mode); +} + +/** + * blk_crypto_evict_key() - Evict a key from any inline encryption hardware + * it may have been programmed into + * @q: The request queue who's associated inline encryption hardware this key + * might have been programmed into + * @key: The key to evict + * + * Upper layers (filesystems) must call this function to ensure that a key is + * evicted from any hardware that it might have been programmed into. The key + * must not be in use by any in-flight IO when this function is called. + * + * Return: 0 on success or if key is not present in the q's ksm, -err on error. + */ +int blk_crypto_evict_key(struct request_queue *q, + const struct blk_crypto_key *key) +{ + if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg)) + return blk_ksm_evict_key(q->ksm, key); + + /* + * If the request queue's associated inline encryption hardware didn't + * have support for the key, then the key might have been programmed + * into the fallback keyslot manager, so try to evict from there. + */ + return blk_crypto_fallback_evict_key(key); +} diff --git a/block/blk-exec.c b/block/blk-exec.c index e20a852ae432..85324d53d072 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -55,7 +55,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, rq->rq_disk = bd_disk; rq->end_io = done; - blk_account_io_start(rq, true); + blk_account_io_start(rq); /* * don't check dying flag for MQ because the request won't diff --git a/block/blk-flush.c b/block/blk-flush.c index c7f396e3d5e2..15ae0155ec07 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -258,7 +258,6 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) blk_flush_complete_seq(rq, fq, seq, error); } - fq->flush_queue_delayed = 0; spin_unlock_irqrestore(&fq->mq_flush_lock, flags); } @@ -433,41 +432,20 @@ void blk_insert_flush(struct request *rq) * blkdev_issue_flush - queue a flush * @bdev: blockdev to issue flush for * @gfp_mask: memory allocation flags (for bio_alloc) - * @error_sector: error sector * * Description: - * Issue a flush for the block device in question. Caller can supply - * room for storing the error offset in case of a flush error, if they - * wish to. + * Issue a flush for the block device in question. */ -int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, - sector_t *error_sector) +int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) { - struct request_queue *q; struct bio *bio; int ret = 0; - if (bdev->bd_disk == NULL) - return -ENXIO; - - q = bdev_get_queue(bdev); - if (!q) - return -ENXIO; - bio = bio_alloc(gfp_mask, 0); bio_set_dev(bio, bdev); bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; ret = submit_bio_wait(bio); - - /* - * The driver must store the error location in ->bi_sector, if - * it supports it. For non-stacked drivers, this should be - * copied from blk_rq_pos(rq). - */ - if (error_sector) - *error_sector = bio->bi_iter.bi_sector; - bio_put(bio); return ret; } diff --git a/block/blk-integrity.c b/block/blk-integrity.c index ff1070edbb40..c03705cbb9c9 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -409,6 +409,13 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template bi->tag_size = template->tag_size; disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + if (disk->queue->ksm) { + pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n"); + blk_ksm_unregister(disk->queue); + } +#endif } EXPORT_SYMBOL(blk_integrity_register); diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 7c1fe605d0d6..8ac4aad66ebc 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -260,6 +260,7 @@ enum { VTIME_PER_SEC_SHIFT = 37, VTIME_PER_SEC = 1LLU << VTIME_PER_SEC_SHIFT, VTIME_PER_USEC = VTIME_PER_SEC / USEC_PER_SEC, + VTIME_PER_NSEC = VTIME_PER_SEC / NSEC_PER_SEC, /* bound vrate adjustments within two orders of magnitude */ VRATE_MIN_PPM = 10000, /* 1% */ @@ -1206,14 +1207,14 @@ static enum hrtimer_restart iocg_waitq_timer_fn(struct hrtimer *timer) return HRTIMER_NORESTART; } -static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) +static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); u64 vtime = atomic64_read(&iocg->vtime); u64 vmargin = ioc->margin_us * now->vrate; u64 margin_ns = ioc->margin_us * NSEC_PER_USEC; - u64 expires, oexpires; + u64 delta_ns, expires, oexpires; u32 hw_inuse; lockdep_assert_held(&iocg->waitq.lock); @@ -1236,15 +1237,10 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) return false; /* use delay */ - if (cost) { - u64 cost_ns = DIV64_U64_ROUND_UP(cost * NSEC_PER_USEC, - now->vrate); - blkcg_add_delay(blkg, now->now_ns, cost_ns); - } - blkcg_use_delay(blkg); - - expires = now->now_ns + DIV64_U64_ROUND_UP(vtime - now->vnow, - now->vrate) * NSEC_PER_USEC; + delta_ns = DIV64_U64_ROUND_UP(vtime - now->vnow, + now->vrate) * NSEC_PER_USEC; + blkcg_set_delay(blkg, delta_ns); + expires = now->now_ns + delta_ns; /* if already active and close enough, don't bother */ oexpires = ktime_to_ns(hrtimer_get_softexpires(&iocg->delay_timer)); @@ -1265,7 +1261,7 @@ static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer) spin_lock_irqsave(&iocg->waitq.lock, flags); ioc_now(iocg->ioc, &now); - iocg_kick_delay(iocg, &now, 0); + iocg_kick_delay(iocg, &now); spin_unlock_irqrestore(&iocg->waitq.lock, flags); return HRTIMER_NORESTART; @@ -1383,7 +1379,7 @@ static void ioc_timer_fn(struct timer_list *timer) if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt) { /* might be oversleeping vtime / hweight changes, kick */ iocg_kick_waitq(iocg, &now); - iocg_kick_delay(iocg, &now, 0); + iocg_kick_delay(iocg, &now); } else if (iocg_is_idle(iocg)) { /* no waiter and idle, deactivate */ iocg->last_inuse = iocg->inuse; @@ -1543,19 +1539,39 @@ skip_surplus_transfers: if (rq_wait_pct > RQ_WAIT_BUSY_PCT || missed_ppm[READ] > ppm_rthr || missed_ppm[WRITE] > ppm_wthr) { + /* clearly missing QoS targets, slow down vrate */ ioc->busy_level = max(ioc->busy_level, 0); ioc->busy_level++; } else if (rq_wait_pct <= RQ_WAIT_BUSY_PCT * UNBUSY_THR_PCT / 100 && missed_ppm[READ] <= ppm_rthr * UNBUSY_THR_PCT / 100 && missed_ppm[WRITE] <= ppm_wthr * UNBUSY_THR_PCT / 100) { - /* take action iff there is contention */ - if (nr_shortages && !nr_lagging) { + /* QoS targets are being met with >25% margin */ + if (nr_shortages) { + /* + * We're throttling while the device has spare + * capacity. If vrate was being slowed down, stop. + */ ioc->busy_level = min(ioc->busy_level, 0); - /* redistribute surpluses first */ - if (!nr_surpluses) + + /* + * If there are IOs spanning multiple periods, wait + * them out before pushing the device harder. If + * there are surpluses, let redistribution work it + * out first. + */ + if (!nr_lagging && !nr_surpluses) ioc->busy_level--; + } else { + /* + * Nobody is being throttled and the users aren't + * issuing enough IOs to saturate the device. We + * simply don't know how close the device is to + * saturation. Coast. + */ + ioc->busy_level = 0; } } else { + /* inside the hysterisis margin, we're good */ ioc->busy_level = 0; } @@ -1678,6 +1694,31 @@ static u64 calc_vtime_cost(struct bio *bio, struct ioc_gq *iocg, bool is_merge) return cost; } +static void calc_size_vtime_cost_builtin(struct request *rq, struct ioc *ioc, + u64 *costp) +{ + unsigned int pages = blk_rq_stats_sectors(rq) >> IOC_SECT_TO_PAGE_SHIFT; + + switch (req_op(rq)) { + case REQ_OP_READ: + *costp = pages * ioc->params.lcoefs[LCOEF_RPAGE]; + break; + case REQ_OP_WRITE: + *costp = pages * ioc->params.lcoefs[LCOEF_WPAGE]; + break; + default: + *costp = 0; + } +} + +static u64 calc_size_vtime_cost(struct request *rq, struct ioc *ioc) +{ + u64 cost; + + calc_size_vtime_cost_builtin(rq, ioc, &cost); + return cost; +} + static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; @@ -1762,7 +1803,7 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) */ if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) { iocg->abs_vdebt += abs_cost; - if (iocg_kick_delay(iocg, &now, cost)) + if (iocg_kick_delay(iocg, &now)) blkcg_schedule_throttle(rqos->q, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); spin_unlock_irq(&iocg->waitq.lock); @@ -1850,7 +1891,7 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, spin_lock_irqsave(&iocg->waitq.lock, flags); if (likely(!list_empty(&iocg->active_list))) { iocg->abs_vdebt += abs_cost; - iocg_kick_delay(iocg, &now, cost); + iocg_kick_delay(iocg, &now); } else { iocg_commit_bio(iocg, bio, cost); } @@ -1868,7 +1909,7 @@ static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio) static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq) { struct ioc *ioc = rqos_to_ioc(rqos); - u64 on_q_ns, rq_wait_ns; + u64 on_q_ns, rq_wait_ns, size_nsec; int pidx, rw; if (!ioc->enabled || !rq->alloc_time_ns || !rq->start_time_ns) @@ -1889,8 +1930,10 @@ static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq) on_q_ns = ktime_get_ns() - rq->alloc_time_ns; rq_wait_ns = rq->start_time_ns - rq->alloc_time_ns; + size_nsec = div64_u64(calc_size_vtime_cost(rq, ioc), VTIME_PER_NSEC); - if (on_q_ns <= ioc->params.qos[pidx] * NSEC_PER_USEC) + if (on_q_ns <= size_nsec || + on_q_ns - size_nsec <= ioc->params.qos[pidx] * NSEC_PER_USEC) this_cpu_inc(ioc->pcpu_stat->missed[rw].nr_met); else this_cpu_inc(ioc->pcpu_stat->missed[rw].nr_missed); @@ -2297,6 +2340,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, spin_lock_irq(&ioc->lock); if (enable) { + blk_stat_enable_accounting(ioc->rqos.q); blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, ioc->rqos.q); ioc->enabled = true; } else { diff --git a/block/blk-map.c b/block/blk-map.c index b72c361911a4..6e804892d5ec 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -257,6 +257,7 @@ out_bmd: static struct bio *bio_map_user_iov(struct request_queue *q, struct iov_iter *iter, gfp_t gfp_mask) { + unsigned int max_sectors = queue_max_hw_sectors(q); int j; struct bio *bio; int ret; @@ -294,8 +295,8 @@ static struct bio *bio_map_user_iov(struct request_queue *q, if (n > bytes) n = bytes; - if (!__bio_add_pc_page(q, bio, page, n, offs, - &same_page)) { + if (!bio_add_hw_page(q, bio, page, n, offs, + max_sectors, &same_page)) { if (same_page) put_page(page); break; @@ -549,6 +550,7 @@ int blk_rq_append_bio(struct request *rq, struct bio **bio) rq->biotail->bi_next = *bio; rq->biotail = *bio; rq->__data_len += (*bio)->bi_iter.bi_size; + bio_crypt_free_ctx(*bio); } return 0; @@ -654,8 +656,6 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, bio = rq->bio; } while (iov_iter_count(&i)); - if (!bio_flagged(bio, BIO_USER_MAPPED)) - rq->rq_flags |= RQF_COPY_USER; return 0; unmap_rq: @@ -731,7 +731,6 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, { int reading = rq_data_dir(rq) == READ; unsigned long addr = (unsigned long) kbuf; - int do_copy = 0; struct bio *bio, *orig_bio; int ret; @@ -740,8 +739,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, if (!len || !kbuf) return -EINVAL; - do_copy = !blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf); - if (do_copy) + if (!blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf)) bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading); else bio = bio_map_kern(q, kbuf, len, gfp_mask); @@ -752,9 +750,6 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, bio->bi_opf &= ~REQ_OP_MASK; bio->bi_opf |= req_op(rq); - if (do_copy) - rq->rq_flags |= RQF_COPY_USER; - orig_bio = bio; ret = blk_rq_append_bio(rq, &bio); if (unlikely(ret)) { diff --git a/block/blk-merge.c b/block/blk-merge.c index 1534ed736363..f0b0bae075a0 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -336,16 +336,6 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio, /* there isn't chance to merge the splitted bio */ split->bi_opf |= REQ_NOMERGE; - /* - * Since we're recursing into make_request here, ensure - * that we mark this bio as already having entered the queue. - * If not, and the queue is going away, we can get stuck - * forever on waiting for the queue reference to drop. But - * that will never happen, as we're already holding a - * reference to it. - */ - bio_set_flag(*bio, BIO_QUEUE_ENTERED); - bio_chain(split, *bio); trace_block_split(q, split, (*bio)->bi_iter.bi_sector); generic_make_request(*bio); @@ -519,44 +509,20 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, * map a request to scatterlist, return number of sg entries setup. Caller * must make sure sg can hold rq->nr_phys_segments entries */ -int blk_rq_map_sg(struct request_queue *q, struct request *rq, - struct scatterlist *sglist) +int __blk_rq_map_sg(struct request_queue *q, struct request *rq, + struct scatterlist *sglist, struct scatterlist **last_sg) { - struct scatterlist *sg = NULL; int nsegs = 0; if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) - nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, &sg); + nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, last_sg); else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME) - nsegs = __blk_bvec_map_sg(bio_iovec(rq->bio), sglist, &sg); + nsegs = __blk_bvec_map_sg(bio_iovec(rq->bio), sglist, last_sg); else if (rq->bio) - nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg); - - if (unlikely(rq->rq_flags & RQF_COPY_USER) && - (blk_rq_bytes(rq) & q->dma_pad_mask)) { - unsigned int pad_len = - (q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1; - - sg->length += pad_len; - rq->extra_len += pad_len; - } + nsegs = __blk_bios_map_sg(q, rq->bio, sglist, last_sg); - if (q->dma_drain_size && q->dma_drain_needed(rq)) { - if (op_is_write(req_op(rq))) - memset(q->dma_drain_buffer, 0, q->dma_drain_size); - - sg_unmark_end(sg); - sg = sg_next(sg); - sg_set_page(sg, virt_to_page(q->dma_drain_buffer), - q->dma_drain_size, - ((unsigned long)q->dma_drain_buffer) & - (PAGE_SIZE - 1)); - nsegs++; - rq->extra_len += q->dma_drain_size; - } - - if (sg) - sg_mark_end(sg); + if (*last_sg) + sg_mark_end(*last_sg); /* * Something must have been wrong if the figured number of @@ -566,7 +532,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, return nsegs; } -EXPORT_SYMBOL(blk_rq_map_sg); +EXPORT_SYMBOL(__blk_rq_map_sg); static inline int ll_new_hw_segment(struct request *req, struct bio *bio, unsigned int nr_phys_segs) @@ -596,6 +562,8 @@ int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs) if (blk_integrity_rq(req) && integrity_req_gap_back_merge(req, bio)) return 0; + if (!bio_crypt_ctx_back_mergeable(req, bio)) + return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) { req_set_nomerge(req->q, req); @@ -612,6 +580,8 @@ int ll_front_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs if (blk_integrity_rq(req) && integrity_req_gap_front_merge(req, bio)) return 0; + if (!bio_crypt_ctx_front_mergeable(req, bio)) + return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) { req_set_nomerge(req->q, req); @@ -661,6 +631,9 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, if (blk_integrity_merge_rq(q, req, next) == false) return 0; + if (!bio_crypt_ctx_merge_rq(req, next)) + return 0; + /* Merge is OK... */ req->nr_phys_segments = total_phys_segments; return 1; @@ -696,20 +669,17 @@ void blk_rq_set_mixed_merge(struct request *rq) rq->rq_flags |= RQF_MIXED_MERGE; } -static void blk_account_io_merge(struct request *req) +static void blk_account_io_merge_request(struct request *req) { if (blk_do_io_stat(req)) { - struct hd_struct *part; - part_stat_lock(); - part = req->part; - - part_dec_in_flight(req->q, part, rq_data_dir(req)); - - hd_struct_put(part); + part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); part_stat_unlock(); + + hd_struct_put(req->part); } } + /* * Two cases of handling DISCARD merge: * If max_discard_segments > 1, the driver takes every bio @@ -821,7 +791,7 @@ static struct request *attempt_merge(struct request_queue *q, /* * 'next' is going away, so update stats accordingly */ - blk_account_io_merge(next); + blk_account_io_merge_request(next); /* * ownership of bio passed from next to req, return 'next' for @@ -885,6 +855,10 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) if (blk_integrity_merge_bio(rq->q, rq, bio) == false) return false; + /* Only merge if the crypt contexts are compatible */ + if (!bio_crypt_rq_ctx_compatible(rq, bio)) + return false; + /* must be using the same buffer */ if (req_op(rq) == REQ_OP_WRITE_SAME && !blk_write_same_mergeable(rq->bio, bio)) diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index b3f2ba483992..15df3a36e9fa 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -213,6 +213,7 @@ static const char *const hctx_state_name[] = { HCTX_STATE_NAME(STOPPED), HCTX_STATE_NAME(TAG_ACTIVE), HCTX_STATE_NAME(SCHED_RESTART), + HCTX_STATE_NAME(INACTIVE), }; #undef HCTX_STATE_NAME @@ -239,6 +240,7 @@ static const char *const hctx_flag_name[] = { HCTX_FLAG_NAME(TAG_SHARED), HCTX_FLAG_NAME(BLOCKING), HCTX_FLAG_NAME(NO_SCHED), + HCTX_FLAG_NAME(STACKING), }; #undef HCTX_FLAG_NAME @@ -292,7 +294,6 @@ static const char *const rqf_name[] = { RQF_NAME(MQ_INFLIGHT), RQF_NAME(DONTPREP), RQF_NAME(PREEMPT), - RQF_NAME(COPY_USER), RQF_NAME(FAILED), RQF_NAME(QUIET), RQF_NAME(ELVPRIV), diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 74cedea56034..fdcc2c1dd178 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -80,16 +80,22 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) blk_mq_run_hw_queue(hctx, true); } +#define BLK_MQ_BUDGET_DELAY 3 /* ms units */ + /* * Only SCSI implements .get_budget and .put_budget, and SCSI restarts * its queue by itself in its completion handler, so we don't need to * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE. + * + * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to + * be run again. This is necessary to avoid starving flushes. */ -static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) +static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct elevator_queue *e = q->elevator; LIST_HEAD(rq_list); + int ret = 0; do { struct request *rq; @@ -97,12 +103,25 @@ static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) if (e->type->ops.has_work && !e->type->ops.has_work(hctx)) break; + if (!list_empty_careful(&hctx->dispatch)) { + ret = -EAGAIN; + break; + } + if (!blk_mq_get_dispatch_budget(hctx)) break; rq = e->type->ops.dispatch_request(hctx); if (!rq) { blk_mq_put_dispatch_budget(hctx); + /* + * We're releasing without dispatching. Holding the + * budget could have blocked any "hctx"s with the + * same queue and if we didn't dispatch then there's + * no guarantee anyone will kick the queue. Kick it + * ourselves. + */ + blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); break; } @@ -113,6 +132,8 @@ static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) */ list_add(&rq->queuelist, &rq_list); } while (blk_mq_dispatch_rq_list(q, &rq_list, true)); + + return ret; } static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx, @@ -130,16 +151,25 @@ static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx, * Only SCSI implements .get_budget and .put_budget, and SCSI restarts * its queue by itself in its completion handler, so we don't need to * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE. + * + * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to + * to be run again. This is necessary to avoid starving flushes. */ -static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) +static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; LIST_HEAD(rq_list); struct blk_mq_ctx *ctx = READ_ONCE(hctx->dispatch_from); + int ret = 0; do { struct request *rq; + if (!list_empty_careful(&hctx->dispatch)) { + ret = -EAGAIN; + break; + } + if (!sbitmap_any_bit_set(&hctx->ctx_map)) break; @@ -149,6 +179,14 @@ static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) rq = blk_mq_dequeue_from_ctx(hctx, ctx); if (!rq) { blk_mq_put_dispatch_budget(hctx); + /* + * We're releasing without dispatching. Holding the + * budget could have blocked any "hctx"s with the + * same queue and if we didn't dispatch then there's + * no guarantee anyone will kick the queue. Kick it + * ourselves. + */ + blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); break; } @@ -165,21 +203,17 @@ static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) } while (blk_mq_dispatch_rq_list(q, &rq_list, true)); WRITE_ONCE(hctx->dispatch_from, ctx); + return ret; } -void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) +static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct elevator_queue *e = q->elevator; const bool has_sched_dispatch = e && e->type->ops.dispatch_request; + int ret = 0; LIST_HEAD(rq_list); - /* RCU or SRCU read lock is needed before checking quiesced flag */ - if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q))) - return; - - hctx->run++; - /* * If we have previous entries on our dispatch list, grab them first for * more fair dispatch. @@ -208,19 +242,41 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) blk_mq_sched_mark_restart_hctx(hctx); if (blk_mq_dispatch_rq_list(q, &rq_list, false)) { if (has_sched_dispatch) - blk_mq_do_dispatch_sched(hctx); + ret = blk_mq_do_dispatch_sched(hctx); else - blk_mq_do_dispatch_ctx(hctx); + ret = blk_mq_do_dispatch_ctx(hctx); } } else if (has_sched_dispatch) { - blk_mq_do_dispatch_sched(hctx); + ret = blk_mq_do_dispatch_sched(hctx); } else if (hctx->dispatch_busy) { /* dequeue request one by one from sw queue if queue is busy */ - blk_mq_do_dispatch_ctx(hctx); + ret = blk_mq_do_dispatch_ctx(hctx); } else { blk_mq_flush_busy_ctxs(hctx, &rq_list); blk_mq_dispatch_rq_list(q, &rq_list, false); } + + return ret; +} + +void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) +{ + struct request_queue *q = hctx->queue; + + /* RCU or SRCU read lock is needed before checking quiesced flag */ + if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q))) + return; + + hctx->run++; + + /* + * A return of -EAGAIN is an indication that hctx->dispatch is not + * empty and we must run again in order to avoid starving flushes. + */ + if (__blk_mq_sched_dispatch_requests(hctx) == -EAGAIN) { + if (__blk_mq_sched_dispatch_requests(hctx) == -EAGAIN) + blk_mq_run_hw_queue(hctx, true); + } } bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 586c9d6e904a..96a39d0724a2 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -92,7 +92,7 @@ static int __blk_mq_get_tag(struct blk_mq_alloc_data *data, { if (!(data->flags & BLK_MQ_REQ_INTERNAL) && !hctx_may_queue(data->hctx, bt)) - return -1; + return BLK_MQ_NO_TAG; if (data->shallow_depth) return __sbitmap_queue_get_shallow(bt, data->shallow_depth); else @@ -111,7 +111,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) if (data->flags & BLK_MQ_REQ_RESERVED) { if (unlikely(!tags->nr_reserved_tags)) { WARN_ON_ONCE(1); - return BLK_MQ_TAG_FAIL; + return BLK_MQ_NO_TAG; } bt = &tags->breserved_tags; tag_offset = 0; @@ -121,11 +121,11 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) } tag = __blk_mq_get_tag(data, bt); - if (tag != -1) + if (tag != BLK_MQ_NO_TAG) goto found_tag; if (data->flags & BLK_MQ_REQ_NOWAIT) - return BLK_MQ_TAG_FAIL; + return BLK_MQ_NO_TAG; ws = bt_wait_ptr(bt, data->hctx); do { @@ -143,13 +143,13 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) * as running the queue may also have found completions. */ tag = __blk_mq_get_tag(data, bt); - if (tag != -1) + if (tag != BLK_MQ_NO_TAG) break; sbitmap_prepare_to_wait(bt, ws, &wait, TASK_UNINTERRUPTIBLE); tag = __blk_mq_get_tag(data, bt); - if (tag != -1) + if (tag != BLK_MQ_NO_TAG) break; bt_prev = bt; @@ -180,6 +180,14 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) sbitmap_finish_wait(bt, ws, &wait); found_tag: + /* + * Give up this allocation if the hctx is inactive. The caller will + * retry on an active hctx. + */ + if (unlikely(test_bit(BLK_MQ_S_INACTIVE, &data->hctx->state))) { + blk_mq_put_tag(tags, data->ctx, tag + tag_offset); + return BLK_MQ_NO_TAG; + } return tag + tag_offset; } @@ -256,14 +264,17 @@ struct bt_tags_iter_data { struct blk_mq_tags *tags; busy_tag_iter_fn *fn; void *data; - bool reserved; + unsigned int flags; }; +#define BT_TAG_ITER_RESERVED (1 << 0) +#define BT_TAG_ITER_STARTED (1 << 1) + static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_tags_iter_data *iter_data = data; struct blk_mq_tags *tags = iter_data->tags; - bool reserved = iter_data->reserved; + bool reserved = iter_data->flags & BT_TAG_ITER_RESERVED; struct request *rq; if (!reserved) @@ -274,10 +285,12 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * test and set the bit before assining ->rqs[]. */ rq = tags->rqs[bitnr]; - if (rq && blk_mq_request_started(rq)) - return iter_data->fn(rq, iter_data->data, reserved); - - return true; + if (!rq) + return true; + if ((iter_data->flags & BT_TAG_ITER_STARTED) && + !blk_mq_request_started(rq)) + return true; + return iter_data->fn(rq, iter_data->data, reserved); } /** @@ -290,39 +303,47 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * @reserved) where rq is a pointer to a request. Return true * to continue iterating tags, false to stop. * @data: Will be passed as second argument to @fn. - * @reserved: Indicates whether @bt is the breserved_tags member or the - * bitmap_tags member of struct blk_mq_tags. + * @flags: BT_TAG_ITER_* */ static void bt_tags_for_each(struct blk_mq_tags *tags, struct sbitmap_queue *bt, - busy_tag_iter_fn *fn, void *data, bool reserved) + busy_tag_iter_fn *fn, void *data, unsigned int flags) { struct bt_tags_iter_data iter_data = { .tags = tags, .fn = fn, .data = data, - .reserved = reserved, + .flags = flags, }; if (tags->rqs) sbitmap_for_each_set(&bt->sb, bt_tags_iter, &iter_data); } +static void __blk_mq_all_tag_iter(struct blk_mq_tags *tags, + busy_tag_iter_fn *fn, void *priv, unsigned int flags) +{ + WARN_ON_ONCE(flags & BT_TAG_ITER_RESERVED); + + if (tags->nr_reserved_tags) + bt_tags_for_each(tags, &tags->breserved_tags, fn, priv, + flags | BT_TAG_ITER_RESERVED); + bt_tags_for_each(tags, &tags->bitmap_tags, fn, priv, flags); +} + /** - * blk_mq_all_tag_busy_iter - iterate over all started requests in a tag map + * blk_mq_all_tag_iter - iterate over all requests in a tag map * @tags: Tag map to iterate over. - * @fn: Pointer to the function that will be called for each started + * @fn: Pointer to the function that will be called for each * request. @fn will be called as follows: @fn(rq, @priv, * reserved) where rq is a pointer to a request. 'reserved' * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. */ -static void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, - busy_tag_iter_fn *fn, void *priv) +void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, + void *priv) { - if (tags->nr_reserved_tags) - bt_tags_for_each(tags, &tags->breserved_tags, fn, priv, true); - bt_tags_for_each(tags, &tags->bitmap_tags, fn, priv, false); + return __blk_mq_all_tag_iter(tags, fn, priv, 0); } /** @@ -342,7 +363,8 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, for (i = 0; i < tagset->nr_hw_queues; i++) { if (tagset->tags && tagset->tags[i]) - blk_mq_all_tag_busy_iter(tagset->tags[i], fn, priv); + __blk_mq_all_tag_iter(tagset->tags[i], fn, priv, + BT_TAG_ITER_STARTED); } } EXPORT_SYMBOL(blk_mq_tagset_busy_iter); diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 2b8321efb682..d38e48f2a0a4 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -34,6 +34,8 @@ extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool); void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, void *priv); +void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, + void *priv); static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt, struct blk_mq_hw_ctx *hctx) @@ -44,9 +46,9 @@ static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt, } enum { - BLK_MQ_TAG_FAIL = -1U, + BLK_MQ_NO_TAG = -1U, BLK_MQ_TAG_MIN = 1, - BLK_MQ_TAG_MAX = BLK_MQ_TAG_FAIL - 1, + BLK_MQ_TAG_MAX = BLK_MQ_NO_TAG - 1, }; extern bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *); diff --git a/block/blk-mq.c b/block/blk-mq.c index a7785df2c944..9a36ac1c1fa1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -26,6 +26,7 @@ #include <linux/delay.h> #include <linux/crash_dump.h> #include <linux/prefetch.h> +#include <linux/blk-crypto.h> #include <trace/events/block.h> @@ -270,14 +271,14 @@ static inline bool blk_mq_need_time_stamp(struct request *rq) } static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, - unsigned int tag, unsigned int op, u64 alloc_time_ns) + unsigned int tag, u64 alloc_time_ns) { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct request *rq = tags->static_rqs[tag]; req_flags_t rq_flags = 0; if (data->flags & BLK_MQ_REQ_INTERNAL) { - rq->tag = -1; + rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = tag; } else { if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) { @@ -285,7 +286,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, atomic_inc(&data->hctx->nr_active); } rq->tag = tag; - rq->internal_tag = -1; + rq->internal_tag = BLK_MQ_NO_TAG; data->hctx->tags->rqs[rq->tag] = rq; } @@ -294,7 +295,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->mq_ctx = data->ctx; rq->mq_hctx = data->hctx; rq->rq_flags = rq_flags; - rq->cmd_flags = op; + rq->cmd_flags = data->cmd_flags; if (data->flags & BLK_MQ_REQ_PREEMPT) rq->rq_flags |= RQF_PREEMPT; if (blk_queue_io_stat(data->q)) @@ -317,8 +318,8 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, #if defined(CONFIG_BLK_DEV_INTEGRITY) rq->nr_integrity_segments = 0; #endif + blk_crypto_rq_set_defaults(rq); /* tag was already set */ - rq->extra_len = 0; WRITE_ONCE(rq->deadline, 0); rq->timeout = 0; @@ -326,35 +327,37 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->end_io = NULL; rq->end_io_data = NULL; - data->ctx->rq_dispatched[op_is_sync(op)]++; + data->ctx->rq_dispatched[op_is_sync(data->cmd_flags)]++; refcount_set(&rq->ref, 1); + + if (!op_is_flush(data->cmd_flags)) { + struct elevator_queue *e = data->q->elevator; + + rq->elv.icq = NULL; + if (e && e->type->ops.prepare_request) { + if (e->type->icq_cache) + blk_mq_sched_assign_ioc(rq); + + e->type->ops.prepare_request(rq); + rq->rq_flags |= RQF_ELVPRIV; + } + } + + data->hctx->queued++; return rq; } -static struct request *blk_mq_get_request(struct request_queue *q, - struct bio *bio, - struct blk_mq_alloc_data *data) +static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data) { + struct request_queue *q = data->q; struct elevator_queue *e = q->elevator; - struct request *rq; - unsigned int tag; - bool clear_ctx_on_error = false; u64 alloc_time_ns = 0; - - blk_queue_enter_live(q); + unsigned int tag; /* alloc_time includes depth and tag waits */ if (blk_queue_rq_alloc_time(q)) alloc_time_ns = ktime_get_ns(); - data->q = q; - if (likely(!data->ctx)) { - data->ctx = blk_mq_get_ctx(q); - clear_ctx_on_error = true; - } - if (likely(!data->hctx)) - data->hctx = blk_mq_map_queue(q, data->cmd_flags, - data->ctx); if (data->cmd_flags & REQ_NOWAIT) data->flags |= BLK_MQ_REQ_NOWAIT; @@ -370,37 +373,43 @@ static struct request *blk_mq_get_request(struct request_queue *q, e->type->ops.limit_depth && !(data->flags & BLK_MQ_REQ_RESERVED)) e->type->ops.limit_depth(data->cmd_flags, data); - } else { - blk_mq_tag_busy(data->hctx); } - tag = blk_mq_get_tag(data); - if (tag == BLK_MQ_TAG_FAIL) { - if (clear_ctx_on_error) - data->ctx = NULL; - blk_queue_exit(q); - return NULL; - } +retry: + data->ctx = blk_mq_get_ctx(q); + data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); + if (!(data->flags & BLK_MQ_REQ_INTERNAL)) + blk_mq_tag_busy(data->hctx); - rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags, alloc_time_ns); - if (!op_is_flush(data->cmd_flags)) { - rq->elv.icq = NULL; - if (e && e->type->ops.prepare_request) { - if (e->type->icq_cache) - blk_mq_sched_assign_ioc(rq); + /* + * Waiting allocations only fail because of an inactive hctx. In that + * case just retry the hctx assignment and tag allocation as CPU hotplug + * should have migrated us to an online CPU by now. + */ + tag = blk_mq_get_tag(data); + if (tag == BLK_MQ_NO_TAG) { + if (data->flags & BLK_MQ_REQ_NOWAIT) + return NULL; - e->type->ops.prepare_request(rq, bio); - rq->rq_flags |= RQF_ELVPRIV; - } + /* + * Give up the CPU and sleep for a random short time to ensure + * that thread using a realtime scheduling class are migrated + * off the the CPU, and thus off the hctx that is going away. + */ + msleep(3); + goto retry; } - data->hctx->queued++; - return rq; + return blk_mq_rq_ctx_init(data, tag, alloc_time_ns); } struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags) { - struct blk_mq_alloc_data alloc_data = { .flags = flags, .cmd_flags = op }; + struct blk_mq_alloc_data data = { + .q = q, + .flags = flags, + .cmd_flags = op, + }; struct request *rq; int ret; @@ -408,34 +417,43 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, if (ret) return ERR_PTR(ret); - rq = blk_mq_get_request(q, NULL, &alloc_data); - blk_queue_exit(q); - + rq = __blk_mq_alloc_request(&data); if (!rq) - return ERR_PTR(-EWOULDBLOCK); - + goto out_queue_exit; rq->__data_len = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; return rq; +out_queue_exit: + blk_queue_exit(q); + return ERR_PTR(-EWOULDBLOCK); } EXPORT_SYMBOL(blk_mq_alloc_request); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx) { - struct blk_mq_alloc_data alloc_data = { .flags = flags, .cmd_flags = op }; - struct request *rq; + struct blk_mq_alloc_data data = { + .q = q, + .flags = flags, + .cmd_flags = op, + }; + u64 alloc_time_ns = 0; unsigned int cpu; + unsigned int tag; int ret; + /* alloc_time includes depth and tag waits */ + if (blk_queue_rq_alloc_time(q)) + alloc_time_ns = ktime_get_ns(); + /* * If the tag allocator sleeps we could get an allocation for a * different hardware context. No need to complicate the low level * allocator for this for the rare use case of a command tied to * a specific queue. */ - if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT))) + if (WARN_ON_ONCE(!(flags & (BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED)))) return ERR_PTR(-EINVAL); if (hctx_idx >= q->nr_hw_queues) @@ -449,21 +467,27 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, * Check if the hardware context is actually mapped to anything. * If not tell the caller that it should skip this queue. */ - alloc_data.hctx = q->queue_hw_ctx[hctx_idx]; - if (!blk_mq_hw_queue_mapped(alloc_data.hctx)) { - blk_queue_exit(q); - return ERR_PTR(-EXDEV); - } - cpu = cpumask_first_and(alloc_data.hctx->cpumask, cpu_online_mask); - alloc_data.ctx = __blk_mq_get_ctx(q, cpu); - - rq = blk_mq_get_request(q, NULL, &alloc_data); - blk_queue_exit(q); + ret = -EXDEV; + data.hctx = q->queue_hw_ctx[hctx_idx]; + if (!blk_mq_hw_queue_mapped(data.hctx)) + goto out_queue_exit; + cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask); + data.ctx = __blk_mq_get_ctx(q, cpu); + + if (q->elevator) + data.flags |= BLK_MQ_REQ_INTERNAL; + else + blk_mq_tag_busy(data.hctx); - if (!rq) - return ERR_PTR(-EWOULDBLOCK); + ret = -EWOULDBLOCK; + tag = blk_mq_get_tag(&data); + if (tag == BLK_MQ_NO_TAG) + goto out_queue_exit; + return blk_mq_rq_ctx_init(&data, tag, alloc_time_ns); - return rq; +out_queue_exit: + blk_queue_exit(q); + return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); @@ -474,11 +498,12 @@ static void __blk_mq_free_request(struct request *rq) struct blk_mq_hw_ctx *hctx = rq->mq_hctx; const int sched_tag = rq->internal_tag; + blk_crypto_free_request(rq); blk_pm_mark_last_busy(rq); rq->mq_hctx = NULL; - if (rq->tag != -1) + if (rq->tag != BLK_MQ_NO_TAG) blk_mq_put_tag(hctx->tags, ctx, rq->tag); - if (sched_tag != -1) + if (sched_tag != BLK_MQ_NO_TAG) blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag); blk_mq_sched_restart(hctx); blk_queue_exit(q); @@ -527,7 +552,7 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error) blk_stat_add(rq, now); } - if (rq->internal_tag != -1) + if (rq->internal_tag != BLK_MQ_NO_TAG) blk_mq_sched_completed_request(rq, now); blk_account_io_done(rq, now); @@ -557,7 +582,17 @@ static void __blk_mq_complete_request_remote(void *data) q->mq_ops->complete(rq); } -static void __blk_mq_complete_request(struct request *rq) +/** + * blk_mq_force_complete_rq() - Force complete the request, bypassing any error + * injection that could drop the completion. + * @rq: Request to be force completed + * + * Drivers should use blk_mq_complete_request() to complete requests in their + * normal IO path. For timeout error recovery, drivers may call this forced + * completion routine after they've reclaimed timed out requests to bypass + * potentially subsequent fake timeouts. + */ +void blk_mq_force_complete_rq(struct request *rq) { struct blk_mq_ctx *ctx = rq->mq_ctx; struct request_queue *q = rq->q; @@ -603,6 +638,7 @@ static void __blk_mq_complete_request(struct request *rq) } put_cpu(); } +EXPORT_SYMBOL_GPL(blk_mq_force_complete_rq); static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx) __releases(hctx->srcu) @@ -636,7 +672,7 @@ bool blk_mq_complete_request(struct request *rq) { if (unlikely(blk_should_fake_timeout(rq->q))) return false; - __blk_mq_complete_request(rq); + blk_mq_force_complete_rq(rq); return true; } EXPORT_SYMBOL(blk_mq_complete_request); @@ -667,15 +703,6 @@ void blk_mq_start_request(struct request *rq) blk_add_timer(rq); WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT); - if (q->dma_drain_size && blk_rq_bytes(rq)) { - /* - * Make sure space for the drain appears. We know we can do - * this because max_hw_segments has been adjusted to be one - * fewer than the device can handle. - */ - rq->nr_phys_segments++; - } - #ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE) q->integrity.profile->prepare_fn(rq); @@ -695,8 +722,6 @@ static void __blk_mq_requeue_request(struct request *rq) if (blk_mq_request_started(rq)) { WRITE_ONCE(rq->state, MQ_RQ_IDLE); rq->rq_flags &= ~RQF_TIMED_OUT; - if (q->dma_drain_size && blk_rq_bytes(rq)) - rq->nr_phys_segments--; } } @@ -1037,7 +1062,7 @@ bool blk_mq_get_driver_tag(struct request *rq) }; bool shared; - if (rq->tag != -1) + if (rq->tag != BLK_MQ_NO_TAG) return true; if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag)) @@ -1053,7 +1078,7 @@ bool blk_mq_get_driver_tag(struct request *rq) data.hctx->tags->rqs[rq->tag] = rq; } - return rq->tag != -1; + return rq->tag != BLK_MQ_NO_TAG; } static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, @@ -1195,6 +1220,19 @@ static void blk_mq_handle_dev_resource(struct request *rq, __blk_mq_requeue_request(rq); } +static void blk_mq_handle_zone_resource(struct request *rq, + struct list_head *zone_list) +{ + /* + * If we end up here it is because we cannot dispatch a request to a + * specific zone due to LLD level zone-write locking or other zone + * related resource not being available. In this case, set the request + * aside in zone_list for retrying it later. + */ + list_add(&rq->queuelist, zone_list); + __blk_mq_requeue_request(rq); +} + /* * Returns true if we did some work AND can potentially do more. */ @@ -1206,6 +1244,8 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, bool no_tag = false; int errors, queued; blk_status_t ret = BLK_STS_OK; + bool no_budget_avail = false; + LIST_HEAD(zone_list); if (list_empty(list)) return false; @@ -1224,6 +1264,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, hctx = rq->mq_hctx; if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) { blk_mq_put_driver_tag(rq); + no_budget_avail = true; break; } @@ -1266,6 +1307,16 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { blk_mq_handle_dev_resource(rq, list); break; + } else if (ret == BLK_STS_ZONE_RESOURCE) { + /* + * Move the request to zone_list and keep going through + * the dispatch list to find more requests the drive can + * accept. + */ + blk_mq_handle_zone_resource(rq, &zone_list); + if (list_empty(list)) + break; + continue; } if (unlikely(ret != BLK_STS_OK)) { @@ -1277,6 +1328,9 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, queued++; } while (!list_empty(list)); + if (!list_empty(&zone_list)) + list_splice_tail_init(&zone_list, list); + hctx->dispatched[queued_to_index(queued)]++; /* @@ -1320,13 +1374,15 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, * * If driver returns BLK_STS_RESOURCE and SCHED_RESTART * bit is set, run queue after a delay to avoid IO stalls - * that could otherwise occur if the queue is idle. + * that could otherwise occur if the queue is idle. We'll do + * similar if we couldn't get budget and SCHED_RESTART is set. */ needs_restart = blk_mq_sched_needs_restart(hctx); if (!needs_restart || (no_tag && list_empty_careful(&hctx->dispatch_wait.entry))) blk_mq_run_hw_queue(hctx, true); - else if (needs_restart && (ret == BLK_STS_RESOURCE)) + else if (needs_restart && (ret == BLK_STS_RESOURCE || + no_budget_avail)) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY); blk_mq_update_dispatch_busy(hctx, true); @@ -1542,6 +1598,25 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async) EXPORT_SYMBOL(blk_mq_run_hw_queues); /** + * blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously. + * @q: Pointer to the request queue to run. + * @msecs: Microseconds of delay to wait before running the queues. + */ +void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs) +{ + struct blk_mq_hw_ctx *hctx; + int i; + + queue_for_each_hw_ctx(q, hctx, i) { + if (blk_mq_hctx_stopped(hctx)) + continue; + + blk_mq_delay_run_hw_queue(hctx, msecs); + } +} +EXPORT_SYMBOL(blk_mq_delay_run_hw_queues); + +/** * blk_mq_queue_stopped() - check whether one or more hctxs have been stopped * @q: request queue. * @@ -1782,8 +1857,9 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, rq->__sector = bio->bi_iter.bi_sector; rq->write_hint = bio->bi_write_hint; blk_rq_bio_prep(rq, bio, nr_segs); + blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO); - blk_account_io_start(rq, true); + blk_account_io_start(rq); } static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, @@ -1973,39 +2049,42 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) * * Returns: Request queue cookie. */ -static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) +blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) { const int is_sync = op_is_sync(bio->bi_opf); const int is_flush_fua = op_is_flush(bio->bi_opf); - struct blk_mq_alloc_data data = { .flags = 0}; + struct blk_mq_alloc_data data = { + .q = q, + }; struct request *rq; struct blk_plug *plug; struct request *same_queue_rq = NULL; unsigned int nr_segs; blk_qc_t cookie; + blk_status_t ret; blk_queue_bounce(q, &bio); __blk_queue_split(q, &bio, &nr_segs); if (!bio_integrity_prep(bio)) - return BLK_QC_T_NONE; + goto queue_exit; if (!is_flush_fua && !blk_queue_nomerges(q) && blk_attempt_plug_merge(q, bio, nr_segs, &same_queue_rq)) - return BLK_QC_T_NONE; + goto queue_exit; if (blk_mq_sched_bio_merge(q, bio, nr_segs)) - return BLK_QC_T_NONE; + goto queue_exit; rq_qos_throttle(q, bio); data.cmd_flags = bio->bi_opf; - rq = blk_mq_get_request(q, bio, &data); + rq = __blk_mq_alloc_request(&data); if (unlikely(!rq)) { rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); - return BLK_QC_T_NONE; + goto queue_exit; } trace_block_getrq(q, bio, bio->bi_opf); @@ -2016,6 +2095,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_mq_bio_to_request(rq, bio, nr_segs); + ret = blk_crypto_init_request(rq); + if (ret != BLK_STS_OK) { + bio->bi_status = ret; + bio_endio(bio); + blk_mq_free_request(rq); + return BLK_QC_T_NONE; + } + plug = blk_mq_plug(q, bio); if (unlikely(is_flush_fua)) { /* Bypass scheduler for flush requests */ @@ -2084,7 +2171,11 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) } return cookie; +queue_exit: + blk_queue_exit(q); + return BLK_QC_T_NONE; } +EXPORT_SYMBOL_GPL(blk_mq_make_request); /* only for request based dm */ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) @@ -2260,6 +2351,86 @@ fail: return -ENOMEM; } +struct rq_iter_data { + struct blk_mq_hw_ctx *hctx; + bool has_rq; +}; + +static bool blk_mq_has_request(struct request *rq, void *data, bool reserved) +{ + struct rq_iter_data *iter_data = data; + + if (rq->mq_hctx != iter_data->hctx) + return true; + iter_data->has_rq = true; + return false; +} + +static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx) +{ + struct blk_mq_tags *tags = hctx->sched_tags ? + hctx->sched_tags : hctx->tags; + struct rq_iter_data data = { + .hctx = hctx, + }; + + blk_mq_all_tag_iter(tags, blk_mq_has_request, &data); + return data.has_rq; +} + +static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu, + struct blk_mq_hw_ctx *hctx) +{ + if (cpumask_next_and(-1, hctx->cpumask, cpu_online_mask) != cpu) + return false; + if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids) + return false; + return true; +} + +static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node) +{ + struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, + struct blk_mq_hw_ctx, cpuhp_online); + + if (!cpumask_test_cpu(cpu, hctx->cpumask) || + !blk_mq_last_cpu_in_hctx(cpu, hctx)) + return 0; + + /* + * Prevent new request from being allocated on the current hctx. + * + * The smp_mb__after_atomic() Pairs with the implied barrier in + * test_and_set_bit_lock in sbitmap_get(). Ensures the inactive flag is + * seen once we return from the tag allocator. + */ + set_bit(BLK_MQ_S_INACTIVE, &hctx->state); + smp_mb__after_atomic(); + + /* + * Try to grab a reference to the queue and wait for any outstanding + * requests. If we could not grab a reference the queue has been + * frozen and there are no requests. + */ + if (percpu_ref_tryget(&hctx->queue->q_usage_counter)) { + while (blk_mq_hctx_has_requests(hctx)) + msleep(5); + percpu_ref_put(&hctx->queue->q_usage_counter); + } + + return 0; +} + +static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node) +{ + struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, + struct blk_mq_hw_ctx, cpuhp_online); + + if (cpumask_test_cpu(cpu, hctx->cpumask)) + clear_bit(BLK_MQ_S_INACTIVE, &hctx->state); + return 0; +} + /* * 'cpu' is going away. splice any existing rq_list entries from this * software queue to the hw queue dispatch list, and ensure that it @@ -2273,6 +2444,9 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) enum hctx_type type; hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead); + if (!cpumask_test_cpu(cpu, hctx->cpumask)) + return 0; + ctx = __blk_mq_get_ctx(hctx->queue, cpu); type = hctx->type; @@ -2296,6 +2470,9 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) { + if (!(hctx->flags & BLK_MQ_F_STACKING)) + cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, + &hctx->cpuhp_online); cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); } @@ -2355,6 +2532,9 @@ static int blk_mq_init_hctx(struct request_queue *q, { hctx->queue_num = hctx_idx; + if (!(hctx->flags & BLK_MQ_F_STACKING)) + cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, + &hctx->cpuhp_online); cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); hctx->tags = set->tags[hctx_idx]; @@ -2473,7 +2653,8 @@ static void blk_mq_init_cpu_queues(struct request_queue *q, } } -static bool __blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, int hctx_idx) +static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set, + int hctx_idx) { int ret = 0; @@ -2521,18 +2702,6 @@ static void blk_mq_map_swqueue(struct request_queue *q) * If the cpu isn't present, the cpu is mapped to first hctx. */ for_each_possible_cpu(i) { - hctx_idx = set->map[HCTX_TYPE_DEFAULT].mq_map[i]; - /* unmapped hw queue can be remapped after CPU topo changed */ - if (!set->tags[hctx_idx] && - !__blk_mq_alloc_rq_map(set, hctx_idx)) { - /* - * If tags initialization fail for some hctx, - * that hctx won't be brought online. In this - * case, remap the current ctx to hctx[0] which - * is guaranteed to always have tags allocated - */ - set->map[HCTX_TYPE_DEFAULT].mq_map[i] = 0; - } ctx = per_cpu_ptr(q->queue_ctx, i); for (j = 0; j < set->nr_maps; j++) { @@ -2541,6 +2710,18 @@ static void blk_mq_map_swqueue(struct request_queue *q) HCTX_TYPE_DEFAULT, i); continue; } + hctx_idx = set->map[j].mq_map[i]; + /* unmapped hw queue can be remapped after CPU topo changed */ + if (!set->tags[hctx_idx] && + !__blk_mq_alloc_map_and_request(set, hctx_idx)) { + /* + * If tags initialization fail for some hctx, + * that hctx won't be brought online. In this + * case, remap the current ctx to hctx[0] which + * is guaranteed to always have tags allocated + */ + set->map[j].mq_map[i] = 0; + } hctx = blk_mq_map_queue_type(q, j, i); ctx->hctxs[j] = hctx; @@ -2944,7 +3125,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, INIT_LIST_HEAD(&q->requeue_list); spin_lock_init(&q->requeue_lock); - q->make_request_fn = blk_mq_make_request; q->nr_requests = set->queue_depth; /* @@ -2988,14 +3168,14 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) int i; for (i = 0; i < set->nr_hw_queues; i++) - if (!__blk_mq_alloc_rq_map(set, i)) + if (!__blk_mq_alloc_map_and_request(set, i)) goto out_unwind; return 0; out_unwind: while (--i >= 0) - blk_mq_free_rq_map(set->tags[i]); + blk_mq_free_map_and_requests(set, i); return -ENOMEM; } @@ -3005,7 +3185,7 @@ out_unwind: * may reduce the depth asked for, if memory is tight. set->queue_depth * will be updated to reflect the allocated depth. */ -static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) +static int blk_mq_alloc_map_and_requests(struct blk_mq_tag_set *set) { unsigned int depth; int err; @@ -3165,7 +3345,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) if (ret) goto out_free_mq_map; - ret = blk_mq_alloc_rq_maps(set); + ret = blk_mq_alloc_map_and_requests(set); if (ret) goto out_free_mq_map; @@ -3347,14 +3527,14 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, blk_mq_sysfs_unregister(q); } + prev_nr_hw_queues = set->nr_hw_queues; if (blk_mq_realloc_tag_set_tags(set, set->nr_hw_queues, nr_hw_queues) < 0) goto reregister; - prev_nr_hw_queues = set->nr_hw_queues; set->nr_hw_queues = nr_hw_queues; - blk_mq_update_queue_map(set); fallback: + blk_mq_update_queue_map(set); list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_realloc_hw_ctxs(set, q); if (q->nr_hw_queues != set->nr_hw_queues) { @@ -3609,6 +3789,9 @@ static int __init blk_mq_init(void) { cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); + cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online", + blk_mq_hctx_notify_online, + blk_mq_hctx_notify_offline); return 0; } subsys_initcall(blk_mq_init); diff --git a/block/blk-mq.h b/block/blk-mq.h index 10bfdfb494fa..a139b0631817 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -201,7 +201,7 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq) { blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag); - rq->tag = -1; + rq->tag = BLK_MQ_NO_TAG; if (rq->rq_flags & RQF_MQ_INFLIGHT) { rq->rq_flags &= ~RQF_MQ_INFLIGHT; @@ -211,7 +211,7 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, static inline void blk_mq_put_driver_tag(struct request *rq) { - if (rq->tag == -1 || rq->internal_tag == -1) + if (rq->tag == BLK_MQ_NO_TAG || rq->internal_tag == BLK_MQ_NO_TAG) return; __blk_mq_put_driver_tag(rq->mq_hctx, rq); diff --git a/block/blk-settings.c b/block/blk-settings.c index 14397b4c4b53..9a2c23cd9700 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -48,6 +48,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->chunk_sectors = 0; lim->max_write_same_sectors = 0; lim->max_write_zeroes_sectors = 0; + lim->max_zone_append_sectors = 0; lim->max_discard_sectors = 0; lim->max_hw_discard_sectors = 0; lim->discard_granularity = 0; @@ -83,6 +84,7 @@ void blk_set_stacking_limits(struct queue_limits *lim) lim->max_dev_sectors = UINT_MAX; lim->max_write_same_sectors = UINT_MAX; lim->max_write_zeroes_sectors = UINT_MAX; + lim->max_zone_append_sectors = UINT_MAX; } EXPORT_SYMBOL(blk_set_stacking_limits); @@ -222,6 +224,33 @@ void blk_queue_max_write_zeroes_sectors(struct request_queue *q, EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors); /** + * blk_queue_max_zone_append_sectors - set max sectors for a single zone append + * @q: the request queue for the device + * @max_zone_append_sectors: maximum number of sectors to write per command + **/ +void blk_queue_max_zone_append_sectors(struct request_queue *q, + unsigned int max_zone_append_sectors) +{ + unsigned int max_sectors; + + if (WARN_ON(!blk_queue_is_zoned(q))) + return; + + max_sectors = min(q->limits.max_hw_sectors, max_zone_append_sectors); + max_sectors = min(q->limits.chunk_sectors, max_sectors); + + /* + * Signal eventual driver bugs resulting in the max_zone_append sectors limit + * being 0 due to a 0 argument, the chunk_sectors limit (zone size) not set, + * or the max_hw_sectors limit not set. + */ + WARN_ON(!max_sectors); + + q->limits.max_zone_append_sectors = max_sectors; +} +EXPORT_SYMBOL_GPL(blk_queue_max_zone_append_sectors); + +/** * blk_queue_max_segments - set max hw segments for a request for this queue * @q: the request queue for the device * @max_segments: max number of segments @@ -470,6 +499,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, b->max_write_same_sectors); t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors, b->max_write_zeroes_sectors); + t->max_zone_append_sectors = min(t->max_zone_append_sectors, + b->max_zone_append_sectors); t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn); t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, @@ -652,43 +683,6 @@ void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask) EXPORT_SYMBOL(blk_queue_update_dma_pad); /** - * blk_queue_dma_drain - Set up a drain buffer for excess dma. - * @q: the request queue for the device - * @dma_drain_needed: fn which returns non-zero if drain is necessary - * @buf: physically contiguous buffer - * @size: size of the buffer in bytes - * - * Some devices have excess DMA problems and can't simply discard (or - * zero fill) the unwanted piece of the transfer. They have to have a - * real area of memory to transfer it into. The use case for this is - * ATAPI devices in DMA mode. If the packet command causes a transfer - * bigger than the transfer size some HBAs will lock up if there - * aren't DMA elements to contain the excess transfer. What this API - * does is adjust the queue so that the buf is always appended - * silently to the scatterlist. - * - * Note: This routine adjusts max_hw_segments to make room for appending - * the drain buffer. If you call blk_queue_max_segments() after calling - * this routine, you must set the limit to one fewer than your device - * can support otherwise there won't be room for the drain buffer. - */ -int blk_queue_dma_drain(struct request_queue *q, - dma_drain_needed_fn *dma_drain_needed, - void *buf, unsigned int size) -{ - if (queue_max_segments(q) < 2) - return -EINVAL; - /* make room for appending the drain */ - blk_queue_max_segments(q, queue_max_segments(q) - 1); - q->dma_drain_needed = dma_drain_needed; - q->dma_drain_buffer = buf; - q->dma_drain_size = size; - - return 0; -} -EXPORT_SYMBOL_GPL(blk_queue_dma_drain); - -/** * blk_queue_segment_boundary - set boundary rules for segment merging * @q: the request queue for the device * @mask: the memory boundary mask diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index fca9b158f4a0..02643e149d5e 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -218,6 +218,13 @@ static ssize_t queue_write_zeroes_max_show(struct request_queue *q, char *page) (unsigned long long)q->limits.max_write_zeroes_sectors << 9); } +static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page) +{ + unsigned long long max_sectors = q->limits.max_zone_append_sectors; + + return sprintf(page, "%llu\n", max_sectors << SECTOR_SHIFT); +} + static ssize_t queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) { @@ -639,6 +646,11 @@ static struct queue_sysfs_entry queue_write_zeroes_max_entry = { .show = queue_write_zeroes_max_show, }; +static struct queue_sysfs_entry queue_zone_append_max_entry = { + .attr = {.name = "zone_append_max_bytes", .mode = 0444 }, + .show = queue_zone_append_max_show, +}; + static struct queue_sysfs_entry queue_nonrot_entry = { .attr = {.name = "rotational", .mode = 0644 }, .show = queue_show_nonrot, @@ -749,6 +761,7 @@ static struct attribute *queue_attrs[] = { &queue_discard_zeroes_data_entry.attr, &queue_write_same_max_entry.attr, &queue_write_zeroes_max_entry.attr, + &queue_zone_append_max_entry.attr, &queue_nonrot_entry.attr, &queue_zoned_entry.attr, &queue_nr_zones_entry.attr, diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 98233c9c65a8..209fdd8939fb 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2358,69 +2358,6 @@ void blk_throtl_bio_endio(struct bio *bio) } #endif -/* - * Dispatch all bios from all children tg's queued on @parent_sq. On - * return, @parent_sq is guaranteed to not have any active children tg's - * and all bios from previously active tg's are on @parent_sq->bio_lists[]. - */ -static void tg_drain_bios(struct throtl_service_queue *parent_sq) -{ - struct throtl_grp *tg; - - while ((tg = throtl_rb_first(parent_sq))) { - struct throtl_service_queue *sq = &tg->service_queue; - struct bio *bio; - - throtl_dequeue_tg(tg); - - while ((bio = throtl_peek_queued(&sq->queued[READ]))) - tg_dispatch_one_bio(tg, bio_data_dir(bio)); - while ((bio = throtl_peek_queued(&sq->queued[WRITE]))) - tg_dispatch_one_bio(tg, bio_data_dir(bio)); - } -} - -/** - * blk_throtl_drain - drain throttled bios - * @q: request_queue to drain throttled bios for - * - * Dispatch all currently throttled bios on @q through ->make_request_fn(). - */ -void blk_throtl_drain(struct request_queue *q) - __releases(&q->queue_lock) __acquires(&q->queue_lock) -{ - struct throtl_data *td = q->td; - struct blkcg_gq *blkg; - struct cgroup_subsys_state *pos_css; - struct bio *bio; - int rw; - - rcu_read_lock(); - - /* - * Drain each tg while doing post-order walk on the blkg tree, so - * that all bios are propagated to td->service_queue. It'd be - * better to walk service_queue tree directly but blkg walk is - * easier. - */ - blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) - tg_drain_bios(&blkg_to_tg(blkg)->service_queue); - - /* finally, transfer bios from top-level tg's into the td */ - tg_drain_bios(&td->service_queue); - - rcu_read_unlock(); - spin_unlock_irq(&q->queue_lock); - - /* all bios now should be in td->service_queue, issue them */ - for (rw = READ; rw <= WRITE; rw++) - while ((bio = throtl_pop_queued(&td->service_queue.queued[rw], - NULL))) - generic_make_request(bio); - - spin_lock_irq(&q->queue_lock); -} - int blk_throtl_init(struct request_queue *q) { struct throtl_data *td; diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 9cb082f38b93..0fa615eefd52 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -405,7 +405,7 @@ static void wb_timer_fn(struct blk_stat_callback *cb) rwb_arm_timer(rwb); } -static void __wbt_update_limits(struct rq_wb *rwb) +static void wbt_update_limits(struct rq_wb *rwb) { struct rq_depth *rqd = &rwb->rq_depth; @@ -418,14 +418,6 @@ static void __wbt_update_limits(struct rq_wb *rwb) rwb_wake_all(rwb); } -void wbt_update_limits(struct request_queue *q) -{ - struct rq_qos *rqos = wbt_rq_qos(q); - if (!rqos) - return; - __wbt_update_limits(RQWB(rqos)); -} - u64 wbt_get_min_lat(struct request_queue *q) { struct rq_qos *rqos = wbt_rq_qos(q); @@ -441,7 +433,7 @@ void wbt_set_min_lat(struct request_queue *q, u64 val) return; RQWB(rqos)->min_lat_nsec = val; RQWB(rqos)->enable_state = WBT_STATE_ON_MANUAL; - __wbt_update_limits(RQWB(rqos)); + wbt_update_limits(RQWB(rqos)); } @@ -685,7 +677,7 @@ static int wbt_data_dir(const struct request *rq) static void wbt_queue_depth_changed(struct rq_qos *rqos) { RQWB(rqos)->rq_depth.queue_depth = blk_queue_depth(rqos->q); - __wbt_update_limits(RQWB(rqos)); + wbt_update_limits(RQWB(rqos)); } static void wbt_exit(struct rq_qos *rqos) @@ -843,7 +835,7 @@ int wbt_init(struct request_queue *q) rwb->enable_state = WBT_STATE_ON_DEFAULT; rwb->wc = 1; rwb->rq_depth.default_depth = RWB_DEF_DEPTH; - __wbt_update_limits(rwb); + wbt_update_limits(rwb); /* * Assign rwb and add the stats callback. diff --git a/block/blk-wbt.h b/block/blk-wbt.h index 8e4e37660971..16bdc85b8df9 100644 --- a/block/blk-wbt.h +++ b/block/blk-wbt.h @@ -88,7 +88,6 @@ static inline unsigned int wbt_inflight(struct rq_wb *rwb) #ifdef CONFIG_BLK_WBT int wbt_init(struct request_queue *); -void wbt_update_limits(struct request_queue *); void wbt_disable_default(struct request_queue *); void wbt_enable_default(struct request_queue *); @@ -108,9 +107,6 @@ static inline int wbt_init(struct request_queue *q) { return -EINVAL; } -static inline void wbt_update_limits(struct request_queue *q) -{ -} static inline void wbt_disable_default(struct request_queue *q) { } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index f87956e0dcaf..23831fa8701d 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -82,6 +82,20 @@ bool blk_req_needs_zone_write_lock(struct request *rq) } EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock); +bool blk_req_zone_write_trylock(struct request *rq) +{ + unsigned int zno = blk_rq_zone_no(rq); + + if (test_and_set_bit(zno, rq->q->seq_zones_wlock)) + return false; + + WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED); + rq->rq_flags |= RQF_ZONE_WRITE_LOCKED; + + return true; +} +EXPORT_SYMBOL_GPL(blk_req_zone_write_trylock); + void __blk_req_zone_write_lock(struct request *rq) { if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq), @@ -457,14 +471,19 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, /** * blk_revalidate_disk_zones - (re)allocate and initialize zone bitmaps * @disk: Target disk + * @update_driver_data: Callback to update driver data on the frozen disk * * Helper function for low-level device drivers to (re) allocate and initialize * a disk request queue zone bitmaps. This functions should normally be called * within the disk ->revalidate method for blk-mq based drivers. For BIO based * drivers only q->nr_zones needs to be updated so that the sysfs exposed value * is correct. + * If the @update_driver_data callback function is not NULL, the callback is + * executed with the device request queue frozen after all zones have been + * checked. */ -int blk_revalidate_disk_zones(struct gendisk *disk) +int blk_revalidate_disk_zones(struct gendisk *disk, + void (*update_driver_data)(struct gendisk *disk)) { struct request_queue *q = disk->queue; struct blk_revalidate_zone_args args = { @@ -498,6 +517,8 @@ int blk_revalidate_disk_zones(struct gendisk *disk) q->nr_zones = args.nr_zones; swap(q->seq_zones_wlock, args.seq_zones_wlock); swap(q->conv_zones_bitmap, args.conv_zones_bitmap); + if (update_driver_data) + update_driver_data(disk); ret = 0; } else { pr_warn("%s: failed to revalidate zones\n", disk->disk_name); diff --git a/block/blk.h b/block/blk.h index 0a94ec68af32..aa16e524dc35 100644 --- a/block/blk.h +++ b/block/blk.h @@ -5,7 +5,9 @@ #include <linux/idr.h> #include <linux/blk-mq.h> #include <linux/part_stat.h> +#include <linux/blk-crypto.h> #include <xen/xen.h> +#include "blk-crypto-internal.h" #include "blk-mq.h" #include "blk-mq-sched.h" @@ -17,7 +19,6 @@ extern struct dentry *blk_debugfs_root; #endif struct blk_flush_queue { - unsigned int flush_queue_delayed:1; unsigned int flush_pending_idx:1; unsigned int flush_running_idx:1; blk_status_t rq_status; @@ -62,17 +63,6 @@ void blk_free_flush_queue(struct blk_flush_queue *q); void blk_freeze_queue(struct request_queue *q); -static inline void blk_queue_enter_live(struct request_queue *q) -{ - /* - * Given that running in generic_make_request() context - * guarantees that a live reference against q_usage_counter has - * been established, further references under that same context - * need not check that the queue has been frozen (marked dead). - */ - percpu_ref_get(&q->q_usage_counter); -} - static inline bool biovec_phys_mergeable(struct request_queue *q, struct bio_vec *vec1, struct bio_vec *vec2) { @@ -195,8 +185,7 @@ bool bio_attempt_discard_merge(struct request_queue *q, struct request *req, bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **same_queue_rq); -void blk_account_io_start(struct request *req, bool new_io); -void blk_account_io_completion(struct request *req, unsigned int bytes); +void blk_account_io_start(struct request *req); void blk_account_io_done(struct request *req, u64 now); /* @@ -303,36 +292,14 @@ void ioc_clear_queue(struct request_queue *q); int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node); -/** - * create_io_context - try to create task->io_context - * @gfp_mask: allocation mask - * @node: allocation node - * - * If %current->io_context is %NULL, allocate a new io_context and install - * it. Returns the current %current->io_context which may be %NULL if - * allocation failed. - * - * Note that this function can't be called with IRQ disabled because - * task_lock which protects %current->io_context is IRQ-unsafe. - */ -static inline struct io_context *create_io_context(gfp_t gfp_mask, int node) -{ - WARN_ON_ONCE(irqs_disabled()); - if (unlikely(!current->io_context)) - create_task_io_context(current, gfp_mask, node); - return current->io_context; -} - /* * Internal throttling interface */ #ifdef CONFIG_BLK_DEV_THROTTLING -extern void blk_throtl_drain(struct request_queue *q); extern int blk_throtl_init(struct request_queue *q); extern void blk_throtl_exit(struct request_queue *q); extern void blk_throtl_register_queue(struct request_queue *q); #else /* CONFIG_BLK_DEV_THROTTLING */ -static inline void blk_throtl_drain(struct request_queue *q) { } static inline int blk_throtl_init(struct request_queue *q) { return 0; } static inline void blk_throtl_exit(struct request_queue *q) { } static inline void blk_throtl_register_queue(struct request_queue *q) { } @@ -375,11 +342,6 @@ void blk_queue_free_zone_bitmaps(struct request_queue *q); static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {} #endif -void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, - int rw); -void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, - int rw); -void update_io_ticks(struct hd_struct *part, unsigned long now, bool end); struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); int blk_alloc_devt(struct hd_struct *part, dev_t *devt); @@ -389,44 +351,32 @@ char *disk_name(struct gendisk *hd, int partno, char *buf); #define ADDPART_FLAG_NONE 0 #define ADDPART_FLAG_RAID 1 #define ADDPART_FLAG_WHOLEDISK 2 -struct hd_struct *__must_check add_partition(struct gendisk *disk, int partno, - sector_t start, sector_t len, int flags, - struct partition_meta_info *info); -void __delete_partition(struct percpu_ref *ref); -void delete_partition(struct gendisk *disk, int partno); +void delete_partition(struct gendisk *disk, struct hd_struct *part); +int bdev_add_partition(struct block_device *bdev, int partno, + sector_t start, sector_t length); +int bdev_del_partition(struct block_device *bdev, int partno); +int bdev_resize_partition(struct block_device *bdev, int partno, + sector_t start, sector_t length); int disk_expand_part_tbl(struct gendisk *disk, int target); +int hd_ref_init(struct hd_struct *part); -static inline int hd_ref_init(struct hd_struct *part) -{ - if (percpu_ref_init(&part->ref, __delete_partition, 0, - GFP_KERNEL)) - return -ENOMEM; - return 0; -} - -static inline void hd_struct_get(struct hd_struct *part) -{ - percpu_ref_get(&part->ref); -} - +/* no need to get/put refcount of part0 */ static inline int hd_struct_try_get(struct hd_struct *part) { - return percpu_ref_tryget_live(&part->ref); + if (part->partno) + return percpu_ref_tryget_live(&part->ref); + return 1; } static inline void hd_struct_put(struct hd_struct *part) { - percpu_ref_put(&part->ref); -} - -static inline void hd_struct_kill(struct hd_struct *part) -{ - percpu_ref_kill(&part->ref); + if (part->partno) + percpu_ref_put(&part->ref); } static inline void hd_free_part(struct hd_struct *part) { - free_part_stats(part); + free_percpu(part->dkstats); kfree(part->info); percpu_ref_exit(&part->ref); } @@ -484,8 +434,8 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) struct request_queue *__blk_alloc_queue(int node_id); -int __bio_add_pc_page(struct request_queue *q, struct bio *bio, +int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, - bool *same_page); + unsigned int max_sectors, bool *same_page); #endif /* BLK_INTERNAL_H */ diff --git a/block/bounce.c b/block/bounce.c index f8ed677a1bf7..c3aaed070124 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -267,6 +267,8 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask, break; } + bio_crypt_clone(bio, bio_src, gfp_mask); + if (bio_integrity(bio_src)) { int ret; diff --git a/block/genhd.c b/block/genhd.c index 06b642b23a07..1a7659327664 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -92,7 +92,6 @@ const char *bdevname(struct block_device *bdev, char *buf) } EXPORT_SYMBOL(bdevname); -#ifdef CONFIG_SMP static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat) { int cpu; @@ -112,44 +111,13 @@ static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat) stat->io_ticks += ptr->io_ticks; } } -#else /* CONFIG_SMP */ -static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat) -{ - memcpy(stat, &part->dkstats, sizeof(struct disk_stats)); -} -#endif /* CONFIG_SMP */ - -void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, int rw) -{ - if (queue_is_mq(q)) - return; - - part_stat_local_inc(part, in_flight[rw]); - if (part->partno) - part_stat_local_inc(&part_to_disk(part)->part0, in_flight[rw]); -} - -void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, int rw) -{ - if (queue_is_mq(q)) - return; - - part_stat_local_dec(part, in_flight[rw]); - if (part->partno) - part_stat_local_dec(&part_to_disk(part)->part0, in_flight[rw]); -} static unsigned int part_in_flight(struct request_queue *q, struct hd_struct *part) { + unsigned int inflight = 0; int cpu; - unsigned int inflight; - if (queue_is_mq(q)) { - return blk_mq_in_flight(q, part); - } - - inflight = 0; for_each_possible_cpu(cpu) { inflight += part_stat_local_read_cpu(part, in_flight[0], cpu) + part_stat_local_read_cpu(part, in_flight[1], cpu); @@ -165,11 +133,6 @@ static void part_in_flight_rw(struct request_queue *q, struct hd_struct *part, { int cpu; - if (queue_is_mq(q)) { - blk_mq_in_flight_rw(q, part, inflight); - return; - } - inflight[0] = 0; inflight[1] = 0; for_each_possible_cpu(cpu) { @@ -344,11 +307,13 @@ static inline int sector_in_part(struct hd_struct *part, sector_t sector) * primarily used for stats accounting. * * CONTEXT: - * RCU read locked. The returned partition pointer is valid only - * while preemption is disabled. + * RCU read locked. The returned partition pointer is always valid + * because its refcount is grabbed except for part0, which lifetime + * is same with the disk. * * RETURNS: * Found partition on success, part0 is returned if no partition matches + * or the matched partition is being deleted. */ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) { @@ -356,21 +321,33 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) struct hd_struct *part; int i; + rcu_read_lock(); ptbl = rcu_dereference(disk->part_tbl); part = rcu_dereference(ptbl->last_lookup); - if (part && sector_in_part(part, sector)) - return part; + if (part && sector_in_part(part, sector) && hd_struct_try_get(part)) + goto out_unlock; for (i = 1; i < ptbl->len; i++) { part = rcu_dereference(ptbl->part[i]); if (part && sector_in_part(part, sector)) { + /* + * only live partition can be cached for lookup, + * so use-after-free on cached & deleting partition + * can be avoided + */ + if (!hd_struct_try_get(part)) + break; rcu_assign_pointer(ptbl->last_lookup, part); - return part; + goto out_unlock; } } - return &disk->part0; + + part = &disk->part0; +out_unlock: + rcu_read_unlock(); + return part; } /** @@ -840,13 +817,15 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO; disk->flags |= GENHD_FL_NO_PART_SCAN; } else { + struct backing_dev_info *bdi = disk->queue->backing_dev_info; + struct device *dev = disk_to_dev(disk); int ret; /* Register BDI before referencing it from bdev */ - disk_to_dev(disk)->devt = devt; - ret = bdi_register_owner(disk->queue->backing_dev_info, - disk_to_dev(disk)); + dev->devt = devt; + ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt)); WARN_ON(ret); + bdi_set_owner(bdi, dev); blk_register_region(disk_devt(disk), disk->minors, NULL, exact_match, exact_lock, disk); } @@ -878,6 +857,25 @@ void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk) } EXPORT_SYMBOL(device_add_disk_no_queue_reg); +static void invalidate_partition(struct gendisk *disk, int partno) +{ + struct block_device *bdev; + + bdev = bdget_disk(disk, partno); + if (!bdev) + return; + + fsync_bdev(bdev); + __invalidate_device(bdev, true); + + /* + * Unhash the bdev inode for this device so that it gets evicted as soon + * as last inode reference is dropped. + */ + remove_inode_hash(bdev->bd_inode); + bdput(bdev); +} + void del_gendisk(struct gendisk *disk) { struct disk_part_iter piter; @@ -896,13 +894,11 @@ void del_gendisk(struct gendisk *disk) DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE); while ((part = disk_part_iter_next(&piter))) { invalidate_partition(disk, part->partno); - bdev_unhash_inode(part_devt(part)); - delete_partition(disk, part->partno); + delete_partition(disk, part); } disk_part_iter_exit(&piter); invalidate_partition(disk, 0); - bdev_unhash_inode(disk_devt(disk)); set_capacity(disk, 0); disk->flags &= ~GENHD_FL_UP; up_write(&disk->lookup_sem); @@ -1279,7 +1275,10 @@ ssize_t part_stat_show(struct device *dev, unsigned int inflight; part_stat_read_all(p, &stat); - inflight = part_in_flight(q, p); + if (queue_is_mq(q)) + inflight = blk_mq_in_flight(q, p); + else + inflight = part_in_flight(q, p); return sprintf(buf, "%8lu %8lu %8llu %8u " @@ -1318,7 +1317,11 @@ ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, struct request_queue *q = part_to_disk(p)->queue; unsigned int inflight[2]; - part_in_flight_rw(q, p, inflight); + if (queue_is_mq(q)) + blk_mq_in_flight_rw(q, p, inflight); + else + part_in_flight_rw(q, p, inflight); + return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]); } @@ -1573,7 +1576,10 @@ static int diskstats_show(struct seq_file *seqf, void *v) disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0); while ((hd = disk_part_iter_next(&piter))) { part_stat_read_all(hd, &stat); - inflight = part_in_flight(gp->queue, hd); + if (queue_is_mq(gp->queue)) + inflight = blk_mq_in_flight(gp->queue, hd); + else + inflight = part_in_flight(gp->queue, hd); seq_printf(seqf, "%4d %7d %s " "%lu %lu %lu %u " @@ -1680,14 +1686,15 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id); if (disk) { - if (!init_part_stats(&disk->part0)) { + disk->part0.dkstats = alloc_percpu(struct disk_stats); + if (!disk->part0.dkstats) { kfree(disk); return NULL; } init_rwsem(&disk->lookup_sem); disk->node_id = node_id; if (disk_expand_part_tbl(disk, 0)) { - free_part_stats(&disk->part0); + free_percpu(disk->part0.dkstats); kfree(disk); return NULL; } @@ -1703,7 +1710,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) * TODO: Ideally set_capacity() and get_capacity() should be * converted to make use of bd_mutex and sequence counters. */ - seqcount_init(&disk->part0.nr_sects_seq); + hd_sects_seq_init(&disk->part0); if (hd_ref_init(&disk->part0)) { hd_free_part(&disk->part0); kfree(disk); @@ -1806,20 +1813,6 @@ int bdev_read_only(struct block_device *bdev) EXPORT_SYMBOL(bdev_read_only); -int invalidate_partition(struct gendisk *disk, int partno) -{ - int res = 0; - struct block_device *bdev = bdget_disk(disk, partno); - if (bdev) { - fsync_bdev(bdev); - res = __invalidate_device(bdev, true); - bdput(bdev); - } - return res; -} - -EXPORT_SYMBOL(invalidate_partition); - /* * Disk events - monitor disk events like media change and eject request. */ diff --git a/block/ioctl.c b/block/ioctl.c index 6e827de1a4c4..bdb3bbb253d9 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -16,142 +16,44 @@ static int blkpg_do_ioctl(struct block_device *bdev, struct blkpg_partition __user *upart, int op) { - struct block_device *bdevp; - struct gendisk *disk; - struct hd_struct *part, *lpart; struct blkpg_partition p; - struct disk_part_iter piter; long long start, length; - int partno; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (copy_from_user(&p, upart, sizeof(struct blkpg_partition))) return -EFAULT; - disk = bdev->bd_disk; if (bdev != bdev->bd_contains) return -EINVAL; - partno = p.pno; - if (partno <= 0) + + if (p.pno <= 0) return -EINVAL; + + if (op == BLKPG_DEL_PARTITION) + return bdev_del_partition(bdev, p.pno); + + start = p.start >> SECTOR_SHIFT; + length = p.length >> SECTOR_SHIFT; + + /* check for fit in a hd_struct */ + if (sizeof(sector_t) < sizeof(long long)) { + long pstart = start, plength = length; + + if (pstart != start || plength != length || pstart < 0 || + plength < 0 || p.pno > 65535) + return -EINVAL; + } + switch (op) { - case BLKPG_ADD_PARTITION: - start = p.start >> 9; - length = p.length >> 9; - /* check for fit in a hd_struct */ - if (sizeof(sector_t) == sizeof(long) && - sizeof(long long) > sizeof(long)) { - long pstart = start, plength = length; - if (pstart != start || plength != length - || pstart < 0 || plength < 0 || partno > 65535) - return -EINVAL; - } - /* check if partition is aligned to blocksize */ - if (p.start & (bdev_logical_block_size(bdev) - 1)) - return -EINVAL; - - mutex_lock(&bdev->bd_mutex); - - /* overlap? */ - disk_part_iter_init(&piter, disk, - DISK_PITER_INCL_EMPTY); - while ((part = disk_part_iter_next(&piter))) { - if (!(start + length <= part->start_sect || - start >= part->start_sect + part->nr_sects)) { - disk_part_iter_exit(&piter); - mutex_unlock(&bdev->bd_mutex); - return -EBUSY; - } - } - disk_part_iter_exit(&piter); - - /* all seems OK */ - part = add_partition(disk, partno, start, length, - ADDPART_FLAG_NONE, NULL); - mutex_unlock(&bdev->bd_mutex); - return PTR_ERR_OR_ZERO(part); - case BLKPG_DEL_PARTITION: - part = disk_get_part(disk, partno); - if (!part) - return -ENXIO; - - bdevp = bdget(part_devt(part)); - disk_put_part(part); - if (!bdevp) - return -ENOMEM; - - mutex_lock(&bdevp->bd_mutex); - if (bdevp->bd_openers) { - mutex_unlock(&bdevp->bd_mutex); - bdput(bdevp); - return -EBUSY; - } - /* all seems OK */ - fsync_bdev(bdevp); - invalidate_bdev(bdevp); - - mutex_lock_nested(&bdev->bd_mutex, 1); - delete_partition(disk, partno); - mutex_unlock(&bdev->bd_mutex); - mutex_unlock(&bdevp->bd_mutex); - bdput(bdevp); - - return 0; - case BLKPG_RESIZE_PARTITION: - start = p.start >> 9; - /* new length of partition in bytes */ - length = p.length >> 9; - /* check for fit in a hd_struct */ - if (sizeof(sector_t) == sizeof(long) && - sizeof(long long) > sizeof(long)) { - long pstart = start, plength = length; - if (pstart != start || plength != length - || pstart < 0 || plength < 0) - return -EINVAL; - } - part = disk_get_part(disk, partno); - if (!part) - return -ENXIO; - bdevp = bdget(part_devt(part)); - if (!bdevp) { - disk_put_part(part); - return -ENOMEM; - } - mutex_lock(&bdevp->bd_mutex); - mutex_lock_nested(&bdev->bd_mutex, 1); - if (start != part->start_sect) { - mutex_unlock(&bdevp->bd_mutex); - mutex_unlock(&bdev->bd_mutex); - bdput(bdevp); - disk_put_part(part); - return -EINVAL; - } - /* overlap? */ - disk_part_iter_init(&piter, disk, - DISK_PITER_INCL_EMPTY); - while ((lpart = disk_part_iter_next(&piter))) { - if (lpart->partno != partno && - !(start + length <= lpart->start_sect || - start >= lpart->start_sect + lpart->nr_sects) - ) { - disk_part_iter_exit(&piter); - mutex_unlock(&bdevp->bd_mutex); - mutex_unlock(&bdev->bd_mutex); - bdput(bdevp); - disk_put_part(part); - return -EBUSY; - } - } - disk_part_iter_exit(&piter); - part_nr_sects_write(part, (sector_t)length); - i_size_write(bdevp->bd_inode, p.length); - mutex_unlock(&bdevp->bd_mutex); - mutex_unlock(&bdev->bd_mutex); - bdput(bdevp); - disk_put_part(part); - return 0; - default: + case BLKPG_ADD_PARTITION: + /* check if partition is aligned to blocksize */ + if (p.start & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; + return bdev_add_partition(bdev, p.pno, start, length); + case BLKPG_RESIZE_PARTITION: + return bdev_resize_partition(bdev, p.pno, start, length); + default: + return -EINVAL; } } @@ -302,12 +204,12 @@ static int put_u64(u64 __user *argp, u64 val) } #ifdef CONFIG_COMPAT -static int compat_put_long(compat_long_t *argp, long val) +static int compat_put_long(compat_long_t __user *argp, long val) { return put_user(val, argp); } -static int compat_put_ulong(compat_ulong_t *argp, compat_ulong_t val) +static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val) { return put_user(val, argp); } diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c new file mode 100644 index 000000000000..c2ef41b3147b --- /dev/null +++ b/block/keyslot-manager.c @@ -0,0 +1,397 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2019 Google LLC + */ + +/** + * DOC: The Keyslot Manager + * + * Many devices with inline encryption support have a limited number of "slots" + * into which encryption contexts may be programmed, and requests can be tagged + * with a slot number to specify the key to use for en/decryption. + * + * As the number of slots is limited, and programming keys is expensive on + * many inline encryption hardware, we don't want to program the same key into + * multiple slots - if multiple requests are using the same key, we want to + * program just one slot with that key and use that slot for all requests. + * + * The keyslot manager manages these keyslots appropriately, and also acts as + * an abstraction between the inline encryption hardware and the upper layers. + * + * Lower layer devices will set up a keyslot manager in their request queue + * and tell it how to perform device specific operations like programming/ + * evicting keys from keyslots. + * + * Upper layers will call blk_ksm_get_slot_for_key() to program a + * key into some slot in the inline encryption hardware. + */ + +#define pr_fmt(fmt) "blk-crypto: " fmt + +#include <linux/keyslot-manager.h> +#include <linux/atomic.h> +#include <linux/mutex.h> +#include <linux/pm_runtime.h> +#include <linux/wait.h> +#include <linux/blkdev.h> + +struct blk_ksm_keyslot { + atomic_t slot_refs; + struct list_head idle_slot_node; + struct hlist_node hash_node; + const struct blk_crypto_key *key; + struct blk_keyslot_manager *ksm; +}; + +static inline void blk_ksm_hw_enter(struct blk_keyslot_manager *ksm) +{ + /* + * Calling into the driver requires ksm->lock held and the device + * resumed. But we must resume the device first, since that can acquire + * and release ksm->lock via blk_ksm_reprogram_all_keys(). + */ + if (ksm->dev) + pm_runtime_get_sync(ksm->dev); + down_write(&ksm->lock); +} + +static inline void blk_ksm_hw_exit(struct blk_keyslot_manager *ksm) +{ + up_write(&ksm->lock); + if (ksm->dev) + pm_runtime_put_sync(ksm->dev); +} + +/** + * blk_ksm_init() - Initialize a keyslot manager + * @ksm: The keyslot_manager to initialize. + * @num_slots: The number of key slots to manage. + * + * Allocate memory for keyslots and initialize a keyslot manager. Called by + * e.g. storage drivers to set up a keyslot manager in their request_queue. + * + * Return: 0 on success, or else a negative error code. + */ +int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots) +{ + unsigned int slot; + unsigned int i; + unsigned int slot_hashtable_size; + + memset(ksm, 0, sizeof(*ksm)); + + if (num_slots == 0) + return -EINVAL; + + ksm->slots = kvcalloc(num_slots, sizeof(ksm->slots[0]), GFP_KERNEL); + if (!ksm->slots) + return -ENOMEM; + + ksm->num_slots = num_slots; + + init_rwsem(&ksm->lock); + + init_waitqueue_head(&ksm->idle_slots_wait_queue); + INIT_LIST_HEAD(&ksm->idle_slots); + + for (slot = 0; slot < num_slots; slot++) { + ksm->slots[slot].ksm = ksm; + list_add_tail(&ksm->slots[slot].idle_slot_node, + &ksm->idle_slots); + } + + spin_lock_init(&ksm->idle_slots_lock); + + slot_hashtable_size = roundup_pow_of_two(num_slots); + ksm->log_slot_ht_size = ilog2(slot_hashtable_size); + ksm->slot_hashtable = kvmalloc_array(slot_hashtable_size, + sizeof(ksm->slot_hashtable[0]), + GFP_KERNEL); + if (!ksm->slot_hashtable) + goto err_destroy_ksm; + for (i = 0; i < slot_hashtable_size; i++) + INIT_HLIST_HEAD(&ksm->slot_hashtable[i]); + + return 0; + +err_destroy_ksm: + blk_ksm_destroy(ksm); + return -ENOMEM; +} +EXPORT_SYMBOL_GPL(blk_ksm_init); + +static inline struct hlist_head * +blk_ksm_hash_bucket_for_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key) +{ + return &ksm->slot_hashtable[hash_ptr(key, ksm->log_slot_ht_size)]; +} + +static void blk_ksm_remove_slot_from_lru_list(struct blk_ksm_keyslot *slot) +{ + struct blk_keyslot_manager *ksm = slot->ksm; + unsigned long flags; + + spin_lock_irqsave(&ksm->idle_slots_lock, flags); + list_del(&slot->idle_slot_node); + spin_unlock_irqrestore(&ksm->idle_slots_lock, flags); +} + +static struct blk_ksm_keyslot *blk_ksm_find_keyslot( + struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key) +{ + const struct hlist_head *head = blk_ksm_hash_bucket_for_key(ksm, key); + struct blk_ksm_keyslot *slotp; + + hlist_for_each_entry(slotp, head, hash_node) { + if (slotp->key == key) + return slotp; + } + return NULL; +} + +static struct blk_ksm_keyslot *blk_ksm_find_and_grab_keyslot( + struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key) +{ + struct blk_ksm_keyslot *slot; + + slot = blk_ksm_find_keyslot(ksm, key); + if (!slot) + return NULL; + if (atomic_inc_return(&slot->slot_refs) == 1) { + /* Took first reference to this slot; remove it from LRU list */ + blk_ksm_remove_slot_from_lru_list(slot); + } + return slot; +} + +unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot) +{ + return slot - slot->ksm->slots; +} +EXPORT_SYMBOL_GPL(blk_ksm_get_slot_idx); + +/** + * blk_ksm_get_slot_for_key() - Program a key into a keyslot. + * @ksm: The keyslot manager to program the key into. + * @key: Pointer to the key object to program, including the raw key, crypto + * mode, and data unit size. + * @slot_ptr: A pointer to return the pointer of the allocated keyslot. + * + * Get a keyslot that's been programmed with the specified key. If one already + * exists, return it with incremented refcount. Otherwise, wait for a keyslot + * to become idle and program it. + * + * Context: Process context. Takes and releases ksm->lock. + * Return: BLK_STS_OK on success (and keyslot is set to the pointer of the + * allocated keyslot), or some other blk_status_t otherwise (and + * keyslot is set to NULL). + */ +blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + struct blk_ksm_keyslot **slot_ptr) +{ + struct blk_ksm_keyslot *slot; + int slot_idx; + int err; + + *slot_ptr = NULL; + down_read(&ksm->lock); + slot = blk_ksm_find_and_grab_keyslot(ksm, key); + up_read(&ksm->lock); + if (slot) + goto success; + + for (;;) { + blk_ksm_hw_enter(ksm); + slot = blk_ksm_find_and_grab_keyslot(ksm, key); + if (slot) { + blk_ksm_hw_exit(ksm); + goto success; + } + + /* + * If we're here, that means there wasn't a slot that was + * already programmed with the key. So try to program it. + */ + if (!list_empty(&ksm->idle_slots)) + break; + + blk_ksm_hw_exit(ksm); + wait_event(ksm->idle_slots_wait_queue, + !list_empty(&ksm->idle_slots)); + } + + slot = list_first_entry(&ksm->idle_slots, struct blk_ksm_keyslot, + idle_slot_node); + slot_idx = blk_ksm_get_slot_idx(slot); + + err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot_idx); + if (err) { + wake_up(&ksm->idle_slots_wait_queue); + blk_ksm_hw_exit(ksm); + return errno_to_blk_status(err); + } + + /* Move this slot to the hash list for the new key. */ + if (slot->key) + hlist_del(&slot->hash_node); + slot->key = key; + hlist_add_head(&slot->hash_node, blk_ksm_hash_bucket_for_key(ksm, key)); + + atomic_set(&slot->slot_refs, 1); + + blk_ksm_remove_slot_from_lru_list(slot); + + blk_ksm_hw_exit(ksm); +success: + *slot_ptr = slot; + return BLK_STS_OK; +} + +/** + * blk_ksm_put_slot() - Release a reference to a slot + * @slot: The keyslot to release the reference of. + * + * Context: Any context. + */ +void blk_ksm_put_slot(struct blk_ksm_keyslot *slot) +{ + struct blk_keyslot_manager *ksm; + unsigned long flags; + + if (!slot) + return; + + ksm = slot->ksm; + + if (atomic_dec_and_lock_irqsave(&slot->slot_refs, + &ksm->idle_slots_lock, flags)) { + list_add_tail(&slot->idle_slot_node, &ksm->idle_slots); + spin_unlock_irqrestore(&ksm->idle_slots_lock, flags); + wake_up(&ksm->idle_slots_wait_queue); + } +} + +/** + * blk_ksm_crypto_cfg_supported() - Find out if a crypto configuration is + * supported by a ksm. + * @ksm: The keyslot manager to check + * @cfg: The crypto configuration to check for. + * + * Checks for crypto_mode/data unit size/dun bytes support. + * + * Return: Whether or not this ksm supports the specified crypto config. + */ +bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm, + const struct blk_crypto_config *cfg) +{ + if (!ksm) + return false; + if (!(ksm->crypto_modes_supported[cfg->crypto_mode] & + cfg->data_unit_size)) + return false; + if (ksm->max_dun_bytes_supported < cfg->dun_bytes) + return false; + return true; +} + +/** + * blk_ksm_evict_key() - Evict a key from the lower layer device. + * @ksm: The keyslot manager to evict from + * @key: The key to evict + * + * Find the keyslot that the specified key was programmed into, and evict that + * slot from the lower layer device. The slot must not be in use by any + * in-flight IO when this function is called. + * + * Context: Process context. Takes and releases ksm->lock. + * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY + * if the keyslot is still in use, or another -errno value on other + * error. + */ +int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key) +{ + struct blk_ksm_keyslot *slot; + int err = 0; + + blk_ksm_hw_enter(ksm); + slot = blk_ksm_find_keyslot(ksm, key); + if (!slot) + goto out_unlock; + + if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) { + err = -EBUSY; + goto out_unlock; + } + err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, + blk_ksm_get_slot_idx(slot)); + if (err) + goto out_unlock; + + hlist_del(&slot->hash_node); + slot->key = NULL; + err = 0; +out_unlock: + blk_ksm_hw_exit(ksm); + return err; +} + +/** + * blk_ksm_reprogram_all_keys() - Re-program all keyslots. + * @ksm: The keyslot manager + * + * Re-program all keyslots that are supposed to have a key programmed. This is + * intended only for use by drivers for hardware that loses its keys on reset. + * + * Context: Process context. Takes and releases ksm->lock. + */ +void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm) +{ + unsigned int slot; + + /* This is for device initialization, so don't resume the device */ + down_write(&ksm->lock); + for (slot = 0; slot < ksm->num_slots; slot++) { + const struct blk_crypto_key *key = ksm->slots[slot].key; + int err; + + if (!key) + continue; + + err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot); + WARN_ON(err); + } + up_write(&ksm->lock); +} +EXPORT_SYMBOL_GPL(blk_ksm_reprogram_all_keys); + +void blk_ksm_destroy(struct blk_keyslot_manager *ksm) +{ + if (!ksm) + return; + kvfree(ksm->slot_hashtable); + memzero_explicit(ksm->slots, sizeof(ksm->slots[0]) * ksm->num_slots); + kvfree(ksm->slots); + memzero_explicit(ksm, sizeof(*ksm)); +} +EXPORT_SYMBOL_GPL(blk_ksm_destroy); + +bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q) +{ + if (blk_integrity_queue_supports_integrity(q)) { + pr_warn("Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n"); + return false; + } + q->ksm = ksm; + return true; +} +EXPORT_SYMBOL_GPL(blk_ksm_register); + +void blk_ksm_unregister(struct request_queue *q) +{ + q->ksm = NULL; +} diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 34dcea0ef637..a38c5ab103d1 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -579,7 +579,7 @@ static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio, return merged; } -static void kyber_prepare_request(struct request *rq, struct bio *bio) +static void kyber_prepare_request(struct request *rq) { rq_set_domain_token(rq, -1); } diff --git a/block/mq-deadline.c b/block/mq-deadline.c index b490f47fd553..b57470e154c8 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -541,7 +541,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, * Nothing to do here. This is defined only to ensure that .finish_request * method is called upon request completion. */ -static void dd_prepare_request(struct request *rq, struct bio *bio) +static void dd_prepare_request(struct request *rq) { } diff --git a/block/partitions/core.c b/block/partitions/core.c index 9ef48a8cff86..78951e33b2d7 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -274,10 +274,10 @@ struct device_type part_type = { .uevent = part_uevent, }; -static void delete_partition_work_fn(struct work_struct *work) +static void hd_struct_free_work(struct work_struct *work) { - struct hd_struct *part = container_of(to_rcu_work(work), struct hd_struct, - rcu_work); + struct hd_struct *part = + container_of(to_rcu_work(work), struct hd_struct, rcu_work); part->start_sect = 0; part->nr_sects = 0; @@ -285,32 +285,42 @@ static void delete_partition_work_fn(struct work_struct *work) put_device(part_to_dev(part)); } -void __delete_partition(struct percpu_ref *ref) +static void hd_struct_free(struct percpu_ref *ref) { struct hd_struct *part = container_of(ref, struct hd_struct, ref); - INIT_RCU_WORK(&part->rcu_work, delete_partition_work_fn); + struct gendisk *disk = part_to_disk(part); + struct disk_part_tbl *ptbl = + rcu_dereference_protected(disk->part_tbl, 1); + + rcu_assign_pointer(ptbl->last_lookup, NULL); + put_device(disk_to_dev(disk)); + + INIT_RCU_WORK(&part->rcu_work, hd_struct_free_work); queue_rcu_work(system_wq, &part->rcu_work); } +int hd_ref_init(struct hd_struct *part) +{ + if (percpu_ref_init(&part->ref, hd_struct_free, 0, GFP_KERNEL)) + return -ENOMEM; + return 0; +} + /* * Must be called either with bd_mutex held, before a disk can be opened or * after all disk users are gone. */ -void delete_partition(struct gendisk *disk, int partno) +void delete_partition(struct gendisk *disk, struct hd_struct *part) { struct disk_part_tbl *ptbl = rcu_dereference_protected(disk->part_tbl, 1); - struct hd_struct *part; - - if (partno >= ptbl->len) - return; - - part = rcu_dereference_protected(ptbl->part[partno], 1); - if (!part) - return; - rcu_assign_pointer(ptbl->part[partno], NULL); - rcu_assign_pointer(ptbl->last_lookup, NULL); + /* + * ->part_tbl is referenced in this part's release handler, so + * we have to hold the disk device + */ + get_device(disk_to_dev(part_to_disk(part))); + rcu_assign_pointer(ptbl->part[part->partno], NULL); kobject_put(part->holder_dir); device_del(part_to_dev(part)); @@ -321,7 +331,7 @@ void delete_partition(struct gendisk *disk, int partno) * "in-use" until we really free the gendisk. */ blk_invalidate_devt(part_devt(part)); - hd_struct_kill(part); + percpu_ref_kill(&part->ref); } static ssize_t whole_disk_show(struct device *dev, @@ -335,7 +345,7 @@ static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); * Must be called either with bd_mutex held, before a disk can be opened or * after all disk users are gone. */ -struct hd_struct *add_partition(struct gendisk *disk, int partno, +static struct hd_struct *add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, struct partition_meta_info *info) { @@ -377,12 +387,13 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, if (!p) return ERR_PTR(-EBUSY); - if (!init_part_stats(p)) { + p->dkstats = alloc_percpu(struct disk_stats); + if (!p->dkstats) { err = -ENOMEM; goto out_free; } - seqcount_init(&p->nr_sects_seq); + hd_sects_seq_init(p); pdev = part_to_dev(p); p->start_sect = start; @@ -458,7 +469,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, out_free_info: kfree(p->info); out_free_stats: - free_part_stats(p); + free_percpu(p->dkstats); out_free: kfree(p); return ERR_PTR(err); @@ -472,6 +483,121 @@ out_put: return ERR_PTR(err); } +static bool partition_overlaps(struct gendisk *disk, sector_t start, + sector_t length, int skip_partno) +{ + struct disk_part_iter piter; + struct hd_struct *part; + bool overlap = false; + + disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY); + while ((part = disk_part_iter_next(&piter))) { + if (part->partno == skip_partno || + start >= part->start_sect + part->nr_sects || + start + length <= part->start_sect) + continue; + overlap = true; + break; + } + + disk_part_iter_exit(&piter); + return overlap; +} + +int bdev_add_partition(struct block_device *bdev, int partno, + sector_t start, sector_t length) +{ + struct hd_struct *part; + + mutex_lock(&bdev->bd_mutex); + if (partition_overlaps(bdev->bd_disk, start, length, -1)) { + mutex_unlock(&bdev->bd_mutex); + return -EBUSY; + } + + part = add_partition(bdev->bd_disk, partno, start, length, + ADDPART_FLAG_NONE, NULL); + mutex_unlock(&bdev->bd_mutex); + return PTR_ERR_OR_ZERO(part); +} + +int bdev_del_partition(struct block_device *bdev, int partno) +{ + struct block_device *bdevp; + struct hd_struct *part; + int ret = 0; + + part = disk_get_part(bdev->bd_disk, partno); + if (!part) + return -ENXIO; + + ret = -ENOMEM; + bdevp = bdget(part_devt(part)); + if (!bdevp) + goto out_put_part; + + mutex_lock(&bdevp->bd_mutex); + + ret = -EBUSY; + if (bdevp->bd_openers) + goto out_unlock; + + sync_blockdev(bdevp); + invalidate_bdev(bdevp); + + mutex_lock_nested(&bdev->bd_mutex, 1); + delete_partition(bdev->bd_disk, part); + mutex_unlock(&bdev->bd_mutex); + + ret = 0; +out_unlock: + mutex_unlock(&bdevp->bd_mutex); + bdput(bdevp); +out_put_part: + disk_put_part(part); + return ret; +} + +int bdev_resize_partition(struct block_device *bdev, int partno, + sector_t start, sector_t length) +{ + struct block_device *bdevp; + struct hd_struct *part; + int ret = 0; + + part = disk_get_part(bdev->bd_disk, partno); + if (!part) + return -ENXIO; + + ret = -ENOMEM; + bdevp = bdget(part_devt(part)); + if (!bdevp) + goto out_put_part; + + mutex_lock(&bdevp->bd_mutex); + mutex_lock_nested(&bdev->bd_mutex, 1); + + ret = -EINVAL; + if (start != part->start_sect) + goto out_unlock; + + ret = -EBUSY; + if (partition_overlaps(bdev->bd_disk, start, length, partno)) + goto out_unlock; + + part_nr_sects_write(part, (sector_t)length); + i_size_write(bdevp->bd_inode, length << SECTOR_SHIFT); + + ret = 0; +out_unlock: + mutex_unlock(&bdevp->bd_mutex); + mutex_unlock(&bdev->bd_mutex); + bdput(bdevp); +out_put_part: + disk_put_part(part); + return ret; +} + static bool disk_unlock_native_capacity(struct gendisk *disk) { const struct block_device_operations *bdops = disk->fops; @@ -488,27 +614,30 @@ static bool disk_unlock_native_capacity(struct gendisk *disk) } } -int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev) +int blk_drop_partitions(struct block_device *bdev) { struct disk_part_iter piter; struct hd_struct *part; - int res; - if (!disk_part_scan_enabled(disk)) + if (!disk_part_scan_enabled(bdev->bd_disk)) return 0; if (bdev->bd_part_count) return -EBUSY; - res = invalidate_partition(disk, 0); - if (res) - return res; - disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY); + sync_blockdev(bdev); + invalidate_bdev(bdev); + + disk_part_iter_init(&piter, bdev->bd_disk, DISK_PITER_INCL_EMPTY); while ((part = disk_part_iter_next(&piter))) - delete_partition(disk, part->partno); + delete_partition(bdev->bd_disk, part); disk_part_iter_exit(&piter); return 0; } +#ifdef CONFIG_S390 +/* for historic reasons in the DASD driver */ +EXPORT_SYMBOL_GPL(blk_drop_partitions); +#endif static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev, struct parsed_partitions *state, int p) |