diff --git a/Documentation/block/null_blk.rst b/Documentation/block/null_blk.rst index edbbab2f12f8..4dd78f24d10a 100644 --- a/Documentation/block/null_blk.rst +++ b/Documentation/block/null_blk.rst @@ -72,6 +72,28 @@ submit_queues=[1..nr_cpus]: Default: 1 hw_queue_depth=[0..qdepth]: Default: 64 The hardware queue depth of the device. +memory_backed=[0/1]: Default: 0 + Whether or not to use a memory buffer to respond to IO requests + + = ============================================= + 0 Transfer no data in response to IO requests + 1 Use a memory buffer to respond to IO requests + = ============================================= + +discard=[0/1]: Default: 0 + Support discard operations (requires memory-backed null_blk device). + + = ===================================== + 0 Do not support discard operations + 1 Enable support for discard operations + = ===================================== + +cache_size=[Size in MB]: Default: 0 + Cache size in MB for memory-backed device. + +mbps=[Maximum bandwidth in MB/s]: Default: 0 (no limit) + Bandwidth limit for device performance. + Multi-queue specific parameters ------------------------------- diff --git a/MAINTAINERS b/MAINTAINERS index 1c42103d889a..a6c5c29e5a0b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14507,7 +14507,8 @@ S: Supported W: http://git.infradead.org/nvme.git T: git://git.infradead.org/nvme.git F: drivers/nvme/host/ -F: include/linux/nvme.h +F: drivers/nvme/common/ +F: include/linux/nvme* F: include/uapi/linux/nvme_ioctl.h NVM EXPRESS FC TRANSPORT DRIVERS @@ -18838,6 +18839,7 @@ SOFTWARE RAID (Multiple Disks) SUPPORT M: Song Liu L: linux-raid@vger.kernel.org S: Supported +Q: https://patchwork.kernel.org/project/linux-raid/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/song/md.git F: drivers/md/Kconfig F: drivers/md/Makefile diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 32929c89ba8a..3f5685c00e36 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -134,7 +134,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, iv = bip->bip_vec + bip->bip_vcnt; if (bip->bip_vcnt && - bvec_gap_to_prev(bdev_get_queue(bio->bi_bdev), + bvec_gap_to_prev(&bdev_get_queue(bio->bi_bdev)->limits, &bip->bip_vec[bip->bip_vcnt - 1], offset)) return 0; diff --git a/block/bio.c b/block/bio.c index 6f9f883f9a65..d6eb90d9b20b 100644 --- a/block/bio.c +++ b/block/bio.c @@ -965,7 +965,7 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio, * would create a gap, disallow it. */ bvec = &bio->bi_io_vec[bio->bi_vcnt - 1]; - if (bvec_gap_to_prev(q, bvec, offset)) + if (bvec_gap_to_prev(&q->limits, bvec, offset)) return 0; } @@ -1151,22 +1151,12 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) bio_set_flag(bio, BIO_CLONED); } -static void bio_put_pages(struct page **pages, size_t size, size_t off) -{ - size_t i, nr = DIV_ROUND_UP(size + (off & ~PAGE_MASK), PAGE_SIZE); - - for (i = 0; i < nr; i++) - put_page(pages[i]); -} - static int bio_iov_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { bool same_page = false; if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) { - if (WARN_ON_ONCE(bio_full(bio, len))) - return -EINVAL; __bio_add_page(bio, page, len, offset); return 0; } @@ -1209,8 +1199,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; ssize_t size, left; - unsigned len, i; + unsigned len, i = 0; size_t offset; + int ret = 0; /* * Move page array up in the allocated memory for the bio vecs as far as @@ -1227,32 +1218,40 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) * result to ensure the bio's total size is correct. The remainder of * the iov data will be picked up in the next bio iteration. */ - size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); - if (size > 0) + size = iov_iter_get_pages(iter, pages, UINT_MAX - bio->bi_iter.bi_size, + nr_pages, &offset); + if (size > 0) { + nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE); size = ALIGN_DOWN(size, bdev_logical_block_size(bio->bi_bdev)); - if (unlikely(size <= 0)) - return size ? size : -EFAULT; + } else + nr_pages = 0; + + if (unlikely(size <= 0)) { + ret = size ? size : -EFAULT; + goto out; + } for (left = size, i = 0; left > 0; left -= len, i++) { struct page *page = pages[i]; - int ret; len = min_t(size_t, PAGE_SIZE - offset, left); - if (bio_op(bio) == REQ_OP_ZONE_APPEND) + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { ret = bio_iov_add_zone_append_page(bio, page, len, offset); - else - ret = bio_iov_add_page(bio, page, len, offset); + if (ret) + break; + } else + bio_iov_add_page(bio, page, len, offset); - if (ret) { - bio_put_pages(pages + i, left, offset); - return ret; - } offset = 0; } - iov_iter_advance(iter, size); - return 0; + iov_iter_advance(iter, size - left); +out: + while (i < nr_pages) + put_page(pages[i++]); + + return ret; } /** diff --git a/block/blk-core.c b/block/blk-core.c index 3d286a256d3d..a0d1104c5590 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -377,7 +377,6 @@ static void blk_timeout_work(struct work_struct *work) struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu) { struct request_queue *q; - int ret; q = kmem_cache_alloc_node(blk_get_queue_kmem_cache(alloc_srcu), GFP_KERNEL | __GFP_ZERO, node_id); @@ -396,13 +395,9 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu) if (q->id < 0) goto fail_srcu; - ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, 0); - if (ret) - goto fail_id; - q->stats = blk_alloc_queue_stats(); if (!q->stats) - goto fail_split; + goto fail_id; q->node = node_id; @@ -439,8 +434,6 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu) fail_stats: blk_free_queue_stats(q->stats); -fail_split: - bioset_exit(&q->bio_split); fail_id: ida_free(&blk_queue_ida, q->id); fail_srcu: diff --git a/block/blk-merge.c b/block/blk-merge.c index 4c8a699754c9..ff04e9290715 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -82,7 +82,7 @@ static inline bool bio_will_gap(struct request_queue *q, bio_get_first_bvec(next, &nb); if (biovec_phys_mergeable(q, &pb, &nb)) return false; - return __bvec_gap_to_prev(q, &pb, nb.bv_offset); + return __bvec_gap_to_prev(&q->limits, &pb, nb.bv_offset); } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) @@ -95,23 +95,30 @@ static inline bool req_gap_front_merge(struct request *req, struct bio *bio) return bio_will_gap(req->q, NULL, bio, req->bio); } -static struct bio *blk_bio_discard_split(struct request_queue *q, - struct bio *bio, - struct bio_set *bs, - unsigned *nsegs) +/* + * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size + * is defined as 'unsigned int', meantime it has to be aligned to with the + * logical block size, which is the minimum accepted unit by hardware. + */ +static unsigned int bio_allowed_max_sectors(struct queue_limits *lim) +{ + return round_down(UINT_MAX, lim->logical_block_size) >> SECTOR_SHIFT; +} + +static struct bio *bio_split_discard(struct bio *bio, struct queue_limits *lim, + unsigned *nsegs, struct bio_set *bs) { unsigned int max_discard_sectors, granularity; - int alignment; sector_t tmp; unsigned split_sectors; *nsegs = 1; /* Zero-sector (unknown) and one-sector granularities are the same. */ - granularity = max(q->limits.discard_granularity >> 9, 1U); + granularity = max(lim->discard_granularity >> 9, 1U); - max_discard_sectors = min(q->limits.max_discard_sectors, - bio_allowed_max_sectors(q)); + max_discard_sectors = + min(lim->max_discard_sectors, bio_allowed_max_sectors(lim)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) { @@ -128,9 +135,8 @@ static struct bio *blk_bio_discard_split(struct request_queue *q, * If the next starting sector would be misaligned, stop the discard at * the previous aligned sector. */ - alignment = (q->limits.discard_alignment >> 9) % granularity; - - tmp = bio->bi_iter.bi_sector + split_sectors - alignment; + tmp = bio->bi_iter.bi_sector + split_sectors - + ((lim->discard_alignment >> 9) % granularity); tmp = sector_div(tmp, granularity); if (split_sectors > tmp) @@ -139,18 +145,15 @@ static struct bio *blk_bio_discard_split(struct request_queue *q, return bio_split(bio, split_sectors, GFP_NOIO, bs); } -static struct bio *blk_bio_write_zeroes_split(struct request_queue *q, - struct bio *bio, struct bio_set *bs, unsigned *nsegs) +static struct bio *bio_split_write_zeroes(struct bio *bio, + struct queue_limits *lim, unsigned *nsegs, struct bio_set *bs) { *nsegs = 0; - - if (!q->limits.max_write_zeroes_sectors) + if (!lim->max_write_zeroes_sectors) return NULL; - - if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors) + if (bio_sectors(bio) <= lim->max_write_zeroes_sectors) return NULL; - - return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs); + return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs); } /* @@ -161,17 +164,17 @@ static struct bio *blk_bio_write_zeroes_split(struct request_queue *q, * requests that are submitted to a block device if the start of a bio is not * aligned to a physical block boundary. */ -static inline unsigned get_max_io_size(struct request_queue *q, - struct bio *bio) +static inline unsigned get_max_io_size(struct bio *bio, + struct queue_limits *lim) { - unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT; - unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT; - unsigned max_sectors = queue_max_sectors(q), start, end; + unsigned pbs = lim->physical_block_size >> SECTOR_SHIFT; + unsigned lbs = lim->logical_block_size >> SECTOR_SHIFT; + unsigned max_sectors = lim->max_sectors, start, end; - if (q->limits.chunk_sectors) { + if (lim->chunk_sectors) { max_sectors = min(max_sectors, blk_chunk_sectors_left(bio->bi_iter.bi_sector, - q->limits.chunk_sectors)); + lim->chunk_sectors)); } start = bio->bi_iter.bi_sector & (pbs - 1); @@ -181,11 +184,10 @@ static inline unsigned get_max_io_size(struct request_queue *q, return max_sectors & ~(lbs - 1); } -static inline unsigned get_max_segment_size(const struct request_queue *q, - struct page *start_page, - unsigned long offset) +static inline unsigned get_max_segment_size(struct queue_limits *lim, + struct page *start_page, unsigned long offset) { - unsigned long mask = queue_segment_boundary(q); + unsigned long mask = lim->seg_boundary_mask; offset = mask & (page_to_phys(start_page) + offset); @@ -194,12 +196,12 @@ static inline unsigned get_max_segment_size(const struct request_queue *q, * on 32bit arch, use queue's max segment size when that happens. */ return min_not_zero(mask - offset + 1, - (unsigned long)queue_max_segment_size(q)); + (unsigned long)lim->max_segment_size); } /** * bvec_split_segs - verify whether or not a bvec should be split in the middle - * @q: [in] request queue associated with the bio associated with @bv + * @lim: [in] queue limits to split based on * @bv: [in] bvec to examine * @nsegs: [in,out] Number of segments in the bio being built. Incremented * by the number of segments from @bv that may be appended to that @@ -217,10 +219,9 @@ static inline unsigned get_max_segment_size(const struct request_queue *q, * *@nsegs segments and *@sectors sectors would make that bio unacceptable for * the block driver. */ -static bool bvec_split_segs(const struct request_queue *q, - const struct bio_vec *bv, unsigned *nsegs, - unsigned *bytes, unsigned max_segs, - unsigned max_bytes) +static bool bvec_split_segs(struct queue_limits *lim, const struct bio_vec *bv, + unsigned *nsegs, unsigned *bytes, unsigned max_segs, + unsigned max_bytes) { unsigned max_len = min(max_bytes, UINT_MAX) - *bytes; unsigned len = min(bv->bv_len, max_len); @@ -228,7 +229,7 @@ static bool bvec_split_segs(const struct request_queue *q, unsigned seg_size = 0; while (len && *nsegs < max_segs) { - seg_size = get_max_segment_size(q, bv->bv_page, + seg_size = get_max_segment_size(lim, bv->bv_page, bv->bv_offset + total_len); seg_size = min(seg_size, len); @@ -236,7 +237,7 @@ static bool bvec_split_segs(const struct request_queue *q, total_len += seg_size; len -= seg_size; - if ((bv->bv_offset + total_len) & queue_virt_boundary(q)) + if ((bv->bv_offset + total_len) & lim->virt_boundary_mask) break; } @@ -247,16 +248,17 @@ static bool bvec_split_segs(const struct request_queue *q, } /** - * blk_bio_segment_split - split a bio in two bios - * @q: [in] request queue pointer + * bio_split_rw - split a bio in two bios * @bio: [in] bio to be split - * @bs: [in] bio set to allocate the clone from + * @lim: [in] queue limits to split based on * @segs: [out] number of segments in the bio with the first half of the sectors + * @bs: [in] bio set to allocate the clone from + * @max_bytes: [in] maximum number of bytes per bio * * Clone @bio, update the bi_iter of the clone to represent the first sectors * of @bio and update @bio->bi_iter to represent the remaining sectors. The * following is guaranteed for the cloned bio: - * - That it has at most get_max_io_size(@q, @bio) sectors. + * - That it has at most @max_bytes worth of data * - That it has at most queue_max_segments(@q) segments. * * Except for discard requests the cloned bio will point at the bi_io_vec of @@ -265,33 +267,30 @@ static bool bvec_split_segs(const struct request_queue *q, * responsible for ensuring that @bs is only destroyed after processing of the * split bio has finished. */ -static struct bio *blk_bio_segment_split(struct request_queue *q, - struct bio *bio, - struct bio_set *bs, - unsigned *segs) +static struct bio *bio_split_rw(struct bio *bio, struct queue_limits *lim, + unsigned *segs, struct bio_set *bs, unsigned max_bytes) { struct bio_vec bv, bvprv, *bvprvp = NULL; struct bvec_iter iter; unsigned nsegs = 0, bytes = 0; - const unsigned max_bytes = get_max_io_size(q, bio) << 9; - const unsigned max_segs = queue_max_segments(q); bio_for_each_bvec(bv, bio, iter) { /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ - if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) + if (bvprvp && bvec_gap_to_prev(lim, bvprvp, bv.bv_offset)) goto split; - if (nsegs < max_segs && + if (nsegs < lim->max_segments && bytes + bv.bv_len <= max_bytes && bv.bv_offset + bv.bv_len <= PAGE_SIZE) { nsegs++; bytes += bv.bv_len; - } else if (bvec_split_segs(q, &bv, &nsegs, &bytes, max_segs, - max_bytes)) { - goto split; + } else { + if (bvec_split_segs(lim, &bv, &nsegs, &bytes, + lim->max_segments, max_bytes)) + goto split; } bvprv = bv; @@ -308,7 +307,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, * split size so that each bio is properly block size aligned, even if * we do not use the full hardware limits. */ - bytes = ALIGN_DOWN(bytes, queue_logical_block_size(q)); + bytes = ALIGN_DOWN(bytes, lim->logical_block_size); /* * Bio splitting may cause subtle trouble such as hang when doing sync @@ -320,34 +319,35 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, } /** - * __blk_queue_split - split a bio and submit the second half - * @q: [in] request_queue new bio is being queued at - * @bio: [in, out] bio to be split - * @nr_segs: [out] number of segments in the first bio + * __bio_split_to_limits - split a bio to fit the queue limits + * @bio: bio to be split + * @lim: queue limits to split based on + * @nr_segs: returns the number of segments in the returned bio * - * Split a bio into two bios, chain the two bios, submit the second half and - * store a pointer to the first half in *@bio. If the second bio is still too - * big it will be split by a recursive call to this function. Since this - * function may allocate a new bio from q->bio_split, it is the responsibility - * of the caller to ensure that q->bio_split is only released after processing - * of the split bio has finished. + * Check if @bio needs splitting based on the queue limits, and if so split off + * a bio fitting the limits from the beginning of @bio and return it. @bio is + * shortened to the remainder and re-submitted. + * + * The split bio is allocated from @q->bio_split, which is provided by the + * block layer. */ -void __blk_queue_split(struct request_queue *q, struct bio **bio, +struct bio *__bio_split_to_limits(struct bio *bio, struct queue_limits *lim, unsigned int *nr_segs) { - struct bio *split = NULL; + struct bio_set *bs = &bio->bi_bdev->bd_disk->bio_split; + struct bio *split; - switch (bio_op(*bio)) { + switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: - split = blk_bio_discard_split(q, *bio, &q->bio_split, nr_segs); + split = bio_split_discard(bio, lim, nr_segs, bs); break; case REQ_OP_WRITE_ZEROES: - split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split, - nr_segs); + split = bio_split_write_zeroes(bio, lim, nr_segs, bs); break; default: - split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs); + split = bio_split_rw(bio, lim, nr_segs, bs, + get_max_io_size(bio, lim) << SECTOR_SHIFT); break; } @@ -356,32 +356,35 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio, split->bi_opf |= REQ_NOMERGE; blkcg_bio_issue_init(split); - bio_chain(split, *bio); - trace_block_split(split, (*bio)->bi_iter.bi_sector); - submit_bio_noacct(*bio); - *bio = split; + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); + submit_bio_noacct(bio); + return split; } + return bio; } /** - * blk_queue_split - split a bio and submit the second half - * @bio: [in, out] bio to be split + * bio_split_to_limits - split a bio to fit the queue limits + * @bio: bio to be split * - * Split a bio into two bios, chains the two bios, submit the second half and - * store a pointer to the first half in *@bio. Since this function may allocate - * a new bio from q->bio_split, it is the responsibility of the caller to ensure - * that q->bio_split is only released after processing of the split bio has - * finished. + * Check if @bio needs splitting based on the queue limits of @bio->bi_bdev, and + * if so split off a bio fitting the limits from the beginning of @bio and + * return it. @bio is shortened to the remainder and re-submitted. + * + * The split bio is allocated from @q->bio_split, which is provided by the + * block layer. */ -void blk_queue_split(struct bio **bio) +struct bio *bio_split_to_limits(struct bio *bio) { - struct request_queue *q = bdev_get_queue((*bio)->bi_bdev); + struct queue_limits *lim = &bdev_get_queue(bio->bi_bdev)->limits; unsigned int nr_segs; - if (blk_may_split(q, *bio)) - __blk_queue_split(q, bio, &nr_segs); + if (bio_may_exceed_limits(bio, lim)) + return __bio_split_to_limits(bio, lim, &nr_segs); + return bio; } -EXPORT_SYMBOL(blk_queue_split); +EXPORT_SYMBOL(bio_split_to_limits); unsigned int blk_recalc_rq_segments(struct request *rq) { @@ -411,7 +414,7 @@ unsigned int blk_recalc_rq_segments(struct request *rq) } rq_for_each_bvec(bv, rq, iter) - bvec_split_segs(rq->q, &bv, &nr_phys_segs, &bytes, + bvec_split_segs(&rq->q->limits, &bv, &nr_phys_segs, &bytes, UINT_MAX, UINT_MAX); return nr_phys_segs; } @@ -442,8 +445,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q, while (nbytes > 0) { unsigned offset = bvec->bv_offset + total; - unsigned len = min(get_max_segment_size(q, bvec->bv_page, - offset), nbytes); + unsigned len = min(get_max_segment_size(&q->limits, + bvec->bv_page, offset), nbytes); struct page *page = bvec->bv_page; /* diff --git a/block/blk-mq.c b/block/blk-mq.c index 70177ee74295..5ee62b95f3e5 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2815,9 +2815,9 @@ void blk_mq_submit_bio(struct bio *bio) unsigned int nr_segs = 1; blk_status_t ret; - blk_queue_bounce(q, &bio); - if (blk_may_split(q, bio)) - __blk_queue_split(q, &bio, &nr_segs); + bio = blk_queue_bounce(bio, q); + if (bio_may_exceed_limits(bio, &q->limits)) + bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); if (!bio_integrity_prep(bio)) return; diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index c0303026752d..e1f009aba6fd 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -779,8 +779,6 @@ static void blk_release_queue(struct kobject *kobj) if (queue_is_mq(q)) blk_mq_release(q); - bioset_exit(&q->bio_split); - if (blk_queue_has_srcu(q)) cleanup_srcu_struct(q->srcu); diff --git a/block/blk.h b/block/blk.h index 1d83b1d41cd1..d7142c4d2fef 100644 --- a/block/blk.h +++ b/block/blk.h @@ -97,23 +97,23 @@ static inline bool biovec_phys_mergeable(struct request_queue *q, return true; } -static inline bool __bvec_gap_to_prev(struct request_queue *q, +static inline bool __bvec_gap_to_prev(struct queue_limits *lim, struct bio_vec *bprv, unsigned int offset) { - return (offset & queue_virt_boundary(q)) || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); + return (offset & lim->virt_boundary_mask) || + ((bprv->bv_offset + bprv->bv_len) & lim->virt_boundary_mask); } /* * Check if adding a bio_vec after bprv with offset would create a gap in * the SG list. Most drivers don't care about this, but some do. */ -static inline bool bvec_gap_to_prev(struct request_queue *q, +static inline bool bvec_gap_to_prev(struct queue_limits *lim, struct bio_vec *bprv, unsigned int offset) { - if (!queue_virt_boundary(q)) + if (!lim->virt_boundary_mask) return false; - return __bvec_gap_to_prev(q, bprv, offset); + return __bvec_gap_to_prev(lim, bprv, offset); } static inline bool rq_mergeable(struct request *rq) @@ -189,7 +189,8 @@ static inline bool integrity_req_gap_back_merge(struct request *req, struct bio_integrity_payload *bip = bio_integrity(req->bio); struct bio_integrity_payload *bip_next = bio_integrity(next); - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + return bvec_gap_to_prev(&req->q->limits, + &bip->bip_vec[bip->bip_vcnt - 1], bip_next->bip_vec[0].bv_offset); } @@ -199,7 +200,8 @@ static inline bool integrity_req_gap_front_merge(struct request *req, struct bio_integrity_payload *bip = bio_integrity(bio); struct bio_integrity_payload *bip_next = bio_integrity(req->bio); - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + return bvec_gap_to_prev(&req->q->limits, + &bip->bip_vec[bip->bip_vcnt - 1], bip_next->bip_vec[0].bv_offset); } @@ -288,7 +290,8 @@ ssize_t part_timeout_show(struct device *, struct device_attribute *, char *); ssize_t part_timeout_store(struct device *, struct device_attribute *, const char *, size_t); -static inline bool blk_may_split(struct request_queue *q, struct bio *bio) +static inline bool bio_may_exceed_limits(struct bio *bio, + struct queue_limits *lim) { switch (bio_op(bio)) { case REQ_OP_DISCARD: @@ -307,12 +310,12 @@ static inline bool blk_may_split(struct request_queue *q, struct bio *bio) * to the performance impact of cloned bios themselves the loop below * doesn't matter anyway. */ - return q->limits.chunk_sectors || bio->bi_vcnt != 1 || + return lim->chunk_sectors || bio->bi_vcnt != 1 || bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE; } -void __blk_queue_split(struct request_queue *q, struct bio **bio, - unsigned int *nr_segs); +struct bio *__bio_split_to_limits(struct bio *bio, struct queue_limits *lim, + unsigned int *nr_segs); int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs); bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, @@ -344,16 +347,6 @@ static inline void req_set_nomerge(struct request_queue *q, struct request *req) q->last_merge = NULL; } -/* - * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size - * is defined as 'unsigned int', meantime it has to aligned to with logical - * block size which is the minimum accepted unit by hardware. - */ -static inline unsigned int bio_allowed_max_sectors(struct request_queue *q) -{ - return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9; -} - /* * Internal io_context interface */ @@ -378,7 +371,7 @@ static inline void blk_throtl_bio_endio(struct bio *bio) { } static inline void blk_throtl_stat_add(struct request *rq, u64 time) { } #endif -void __blk_queue_bounce(struct request_queue *q, struct bio **bio); +struct bio *__blk_queue_bounce(struct bio *bio, struct request_queue *q); static inline bool blk_queue_may_bounce(struct request_queue *q) { @@ -387,10 +380,12 @@ static inline bool blk_queue_may_bounce(struct request_queue *q) max_low_pfn >= max_pfn; } -static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio) +static inline struct bio *blk_queue_bounce(struct bio *bio, + struct request_queue *q) { - if (unlikely(blk_queue_may_bounce(q) && bio_has_data(*bio))) - __blk_queue_bounce(q, bio); + if (unlikely(blk_queue_may_bounce(q) && bio_has_data(bio))) + return __blk_queue_bounce(bio, q); + return bio; } #ifdef CONFIG_BLK_CGROUP_IOLATENCY diff --git a/block/bounce.c b/block/bounce.c index c8f487af7be3..7cfcb242f9a1 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -199,24 +199,24 @@ static struct bio *bounce_clone_bio(struct bio *bio_src) return NULL; } -void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) +struct bio *__blk_queue_bounce(struct bio *bio_orig, struct request_queue *q) { struct bio *bio; - int rw = bio_data_dir(*bio_orig); + int rw = bio_data_dir(bio_orig); struct bio_vec *to, from; struct bvec_iter iter; unsigned i = 0, bytes = 0; bool bounce = false; int sectors; - bio_for_each_segment(from, *bio_orig, iter) { + bio_for_each_segment(from, bio_orig, iter) { if (i++ < BIO_MAX_VECS) bytes += from.bv_len; if (PageHighMem(from.bv_page)) bounce = true; } if (!bounce) - return; + return bio_orig; /* * Individual bvecs might not be logical block aligned. Round down @@ -225,13 +225,13 @@ void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) */ sectors = ALIGN_DOWN(bytes, queue_logical_block_size(q)) >> SECTOR_SHIFT; - if (sectors < bio_sectors(*bio_orig)) { - bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split); - bio_chain(bio, *bio_orig); - submit_bio_noacct(*bio_orig); - *bio_orig = bio; + if (sectors < bio_sectors(bio_orig)) { + bio = bio_split(bio_orig, sectors, GFP_NOIO, &bounce_bio_split); + bio_chain(bio, bio_orig); + submit_bio_noacct(bio_orig); + bio_orig = bio; } - bio = bounce_clone_bio(*bio_orig); + bio = bounce_clone_bio(bio_orig); /* * Bvec table can't be updated by bio_for_each_segment_all(), @@ -254,7 +254,7 @@ void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) to->bv_page = bounce_page; } - trace_block_bio_bounce(*bio_orig); + trace_block_bio_bounce(bio_orig); bio->bi_flags |= (1 << BIO_BOUNCED); @@ -263,6 +263,6 @@ void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) else bio->bi_end_io = bounce_end_io_write; - bio->bi_private = *bio_orig; - *bio_orig = bio; + bio->bi_private = bio_orig; + return bio; } diff --git a/block/genhd.c b/block/genhd.c index e1d5b10ac193..b901fea1d55a 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1151,6 +1151,7 @@ static void disk_release(struct device *dev) blk_mq_exit_queue(disk->queue); blkcg_exit_queue(disk->queue); + bioset_exit(&disk->bio_split); disk_release_events(disk); kfree(disk->random); @@ -1342,9 +1343,12 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, if (!disk) goto out_put_queue; + if (bioset_init(&disk->bio_split, BIO_POOL_SIZE, 0, 0)) + goto out_free_disk; + disk->bdi = bdi_alloc(node_id); if (!disk->bdi) - goto out_free_disk; + goto out_free_bioset; /* bdev_alloc() might need the queue, set before the first call */ disk->queue = q; @@ -1382,6 +1386,8 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, iput(disk->part0->bd_inode); out_free_bdi: bdi_put(disk->bdi); +out_free_bioset: + bioset_exit(&disk->bio_split); out_free_disk: kfree(disk); out_put_queue: diff --git a/crypto/kpp.c b/crypto/kpp.c index 7aa6ba4b60a4..678e871ce418 100644 --- a/crypto/kpp.c +++ b/crypto/kpp.c @@ -104,6 +104,12 @@ int crypto_grab_kpp(struct crypto_kpp_spawn *spawn, } EXPORT_SYMBOL_GPL(crypto_grab_kpp); +int crypto_has_kpp(const char *alg_name, u32 type, u32 mask) +{ + return crypto_type_has_alg(alg_name, &crypto_kpp_type, type, mask); +} +EXPORT_SYMBOL_GPL(crypto_has_kpp); + static void kpp_prepare_alg(struct kpp_alg *alg) { struct crypto_alg *base = &alg->base; diff --git a/crypto/shash.c b/crypto/shash.c index 0a0a50cb694f..4c88e63b3350 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -521,6 +521,12 @@ struct crypto_shash *crypto_alloc_shash(const char *alg_name, u32 type, } EXPORT_SYMBOL_GPL(crypto_alloc_shash); +int crypto_has_shash(const char *alg_name, u32 type, u32 mask) +{ + return crypto_type_has_alg(alg_name, &crypto_shash_type, type, mask); +} +EXPORT_SYMBOL_GPL(crypto_has_shash); + static int shash_prepare_alg(struct shash_alg *alg) { struct crypto_alg *base = &alg->base; diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index e19fcab016ba..db1b4b202646 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -248,15 +248,6 @@ config BLK_DEV_NBD If unsure, say N. -config BLK_DEV_SX8 - tristate "Promise SATA SX8 support" - depends on PCI - help - Saying Y or M here will enable support for the - Promise SATA SX8 controllers. - - Use devices /dev/sx8/$N and /dev/sx8/$Np$M. - config BLK_DEV_RAM tristate "RAM block device support" help diff --git a/drivers/block/Makefile b/drivers/block/Makefile index be631352567e..101612cba303 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -26,8 +26,6 @@ obj-$(CONFIG_SUNVDC) += sunvdc.o obj-$(CONFIG_BLK_DEV_NBD) += nbd.o obj-$(CONFIG_VIRTIO_BLK) += virtio_blk.o -obj-$(CONFIG_BLK_DEV_SX8) += sx8.o - obj-$(CONFIG_XEN_BLKDEV_FRONTEND) += xen-blkfront.o obj-$(CONFIG_XEN_BLKDEV_BACKEND) += xen-blkback/ obj-$(CONFIG_BLK_DEV_DRBD) += drbd/ diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index 603f6828dd79..7d9db33363de 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -974,25 +974,58 @@ static void drbd_bm_endio(struct bio *bio) } } +/* For the layout, see comment above drbd_md_set_sector_offsets(). */ +static inline sector_t drbd_md_last_bitmap_sector(struct drbd_backing_dev *bdev) +{ + switch (bdev->md.meta_dev_idx) { + case DRBD_MD_INDEX_INTERNAL: + case DRBD_MD_INDEX_FLEX_INT: + return bdev->md.md_offset + bdev->md.al_offset -1; + case DRBD_MD_INDEX_FLEX_EXT: + default: + return bdev->md.md_offset + bdev->md.md_size_sect -1; + } +} + static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_hold(local) { struct drbd_device *device = ctx->device; enum req_op op = ctx->flags & BM_AIO_READ ? REQ_OP_READ : REQ_OP_WRITE; - struct bio *bio = bio_alloc_bioset(device->ldev->md_bdev, 1, op, - GFP_NOIO, &drbd_md_io_bio_set); struct drbd_bitmap *b = device->bitmap; + struct bio *bio; struct page *page; + sector_t last_bm_sect; + sector_t first_bm_sect; + sector_t on_disk_sector; unsigned int len; - sector_t on_disk_sector = - device->ldev->md.md_offset + device->ldev->md.bm_offset; - on_disk_sector += ((sector_t)page_nr) << (PAGE_SHIFT-9); + first_bm_sect = device->ldev->md.md_offset + device->ldev->md.bm_offset; + on_disk_sector = first_bm_sect + (((sector_t)page_nr) << (PAGE_SHIFT-SECTOR_SHIFT)); /* this might happen with very small * flexible external meta data device, * or with PAGE_SIZE > 4k */ - len = min_t(unsigned int, PAGE_SIZE, - (drbd_md_last_sector(device->ldev) - on_disk_sector + 1)<<9); + last_bm_sect = drbd_md_last_bitmap_sector(device->ldev); + if (first_bm_sect <= on_disk_sector && last_bm_sect >= on_disk_sector) { + sector_t len_sect = last_bm_sect - on_disk_sector + 1; + if (len_sect < PAGE_SIZE/SECTOR_SIZE) + len = (unsigned int)len_sect*SECTOR_SIZE; + else + len = PAGE_SIZE; + } else { + if (__ratelimit(&drbd_ratelimit_state)) { + drbd_err(device, "Invalid offset during on-disk bitmap access: " + "page idx %u, sector %llu\n", page_nr, on_disk_sector); + } + ctx->error = -EIO; + bm_set_page_io_err(b->bm_pages[page_nr]); + if (atomic_dec_and_test(&ctx->in_flight)) { + ctx->done = 1; + wake_up(&device->misc_wait); + kref_put(&ctx->kref, &drbd_bm_aio_ctx_destroy); + } + return; + } /* serialize IO on this page */ bm_page_lock_io(device, page_nr); @@ -1007,6 +1040,8 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho bm_store_page_idx(page, page_nr); } else page = b->bm_pages[page_nr]; + bio = bio_alloc_bioset(device->ldev->md_bdev, 1, op, GFP_NOIO, + &drbd_md_io_bio_set); bio->bi_iter.bi_sector = on_disk_sector; /* bio_add_page of a single page to an empty bio will always succeed, * according to api. Do we want to assert that? */ diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 6d8dd14458c6..8f7f144e54f3 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -1608,7 +1608,7 @@ void drbd_submit_bio(struct bio *bio) { struct drbd_device *device = bio->bi_bdev->bd_disk->private_data; - blk_queue_split(&bio); + bio = bio_split_to_limits(bio); /* * what we "blindly" assume: diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index f5d098a148cb..2a709daefbc4 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -11,6 +11,8 @@ * (part of code stolen from loop.c) */ +#define pr_fmt(fmt) "nbd: " fmt + #include #include @@ -1950,7 +1952,7 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info) test_bit(NBD_DISCONNECT_REQUESTED, &nbd->flags)) || !refcount_inc_not_zero(&nbd->refs)) { mutex_unlock(&nbd_index_mutex); - pr_err("nbd: device at index %d is going down\n", + pr_err("device at index %d is going down\n", index); return -EINVAL; } @@ -1961,7 +1963,7 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info) if (!nbd) { nbd = nbd_dev_add(index, 2); if (IS_ERR(nbd)) { - pr_err("nbd: failed to add new device\n"); + pr_err("failed to add new device\n"); return PTR_ERR(nbd); } } diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 8b224ede2e33..c451c477978f 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -201,6 +201,22 @@ static bool g_use_per_node_hctx; module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444); MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false"); +static bool g_memory_backed; +module_param_named(memory_backed, g_memory_backed, bool, 0444); +MODULE_PARM_DESC(memory_backed, "Create a memory-backed block device. Default: false"); + +static bool g_discard; +module_param_named(discard, g_discard, bool, 0444); +MODULE_PARM_DESC(discard, "Support discard operations (requires memory-backed null_blk device). Default: false"); + +static unsigned long g_cache_size; +module_param_named(cache_size, g_cache_size, ulong, 0444); +MODULE_PARM_DESC(mbps, "Cache size in MiB for memory-backed device. Default: 0 (none)"); + +static unsigned int g_mbps; +module_param_named(mbps, g_mbps, uint, 0444); +MODULE_PARM_DESC(mbps, "Limit maximum bandwidth (in MiB/s). Default: 0 (no limit)"); + static bool g_zoned; module_param_named(zoned, g_zoned, bool, S_IRUGO); MODULE_PARM_DESC(zoned, "Make device as a host-managed zoned block device. Default: false"); @@ -409,6 +425,8 @@ NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL); NULLB_DEVICE_ATTR(zone_max_open, uint, NULL); NULLB_DEVICE_ATTR(zone_max_active, uint, NULL); NULLB_DEVICE_ATTR(virt_boundary, bool, NULL); +NULLB_DEVICE_ATTR(no_sched, bool, NULL); +NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL); static ssize_t nullb_device_power_show(struct config_item *item, char *page) { @@ -532,6 +550,8 @@ static struct configfs_attribute *nullb_device_attrs[] = { &nullb_device_attr_zone_max_open, &nullb_device_attr_zone_max_active, &nullb_device_attr_virt_boundary, + &nullb_device_attr_no_sched, + &nullb_device_attr_shared_tag_bitmap, NULL, }; @@ -588,7 +608,13 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item) static ssize_t memb_group_features_show(struct config_item *item, char *page) { return snprintf(page, PAGE_SIZE, - "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv,zone_max_open,zone_max_active,blocksize,max_sectors,virt_boundary\n"); + "badblocks,blocking,blocksize,cache_size," + "completion_nsec,discard,home_node,hw_queue_depth," + "irqmode,max_sectors,mbps,memory_backed,no_sched," + "poll_queues,power,queue_mode,shared_tag_bitmap,size," + "submit_queues,use_per_node_hctx,virt_boundary,zoned," + "zone_capacity,zone_max_active,zone_max_open," + "zone_nr_conv,zone_size\n"); } CONFIGFS_ATTR_RO(memb_group_, features); @@ -650,6 +676,10 @@ static struct nullb_device *null_alloc_dev(void) dev->irqmode = g_irqmode; dev->hw_queue_depth = g_hw_queue_depth; dev->blocking = g_blocking; + dev->memory_backed = g_memory_backed; + dev->discard = g_discard; + dev->cache_size = g_cache_size; + dev->mbps = g_mbps; dev->use_per_node_hctx = g_use_per_node_hctx; dev->zoned = g_zoned; dev->zone_size = g_zone_size; @@ -658,6 +688,8 @@ static struct nullb_device *null_alloc_dev(void) dev->zone_max_open = g_zone_max_open; dev->zone_max_active = g_zone_max_active; dev->virt_boundary = g_virt_boundary; + dev->no_sched = g_no_sched; + dev->shared_tag_bitmap = g_shared_tag_bitmap; return dev; } @@ -1655,7 +1687,7 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, static void cleanup_queue(struct nullb_queue *nq) { - kfree(nq->tag_map); + bitmap_free(nq->tag_map); kfree(nq->cmds); } @@ -1782,14 +1814,13 @@ static const struct block_device_operations null_rq_ops = { static int setup_commands(struct nullb_queue *nq) { struct nullb_cmd *cmd; - int i, tag_size; + int i; nq->cmds = kcalloc(nq->queue_depth, sizeof(*cmd), GFP_KERNEL); if (!nq->cmds) return -ENOMEM; - tag_size = ALIGN(nq->queue_depth, BITS_PER_LONG) / BITS_PER_LONG; - nq->tag_map = kcalloc(tag_size, sizeof(unsigned long), GFP_KERNEL); + nq->tag_map = bitmap_zalloc(nq->queue_depth, GFP_KERNEL); if (!nq->tag_map) { kfree(nq->cmds); return -ENOMEM; @@ -1866,31 +1897,48 @@ static int null_gendisk_register(struct nullb *nullb) static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set) { + unsigned int flags = BLK_MQ_F_SHOULD_MERGE; + int hw_queues, numa_node; + unsigned int queue_depth; int poll_queues; - set->ops = &null_mq_ops; - set->nr_hw_queues = nullb ? nullb->dev->submit_queues : - g_submit_queues; - poll_queues = nullb ? nullb->dev->poll_queues : g_poll_queues; - if (poll_queues) - set->nr_hw_queues += poll_queues; - set->queue_depth = nullb ? nullb->dev->hw_queue_depth : - g_hw_queue_depth; - set->numa_node = nullb ? nullb->dev->home_node : g_home_node; - set->cmd_size = sizeof(struct nullb_cmd); - set->flags = BLK_MQ_F_SHOULD_MERGE; - if (g_no_sched) - set->flags |= BLK_MQ_F_NO_SCHED; - if (g_shared_tag_bitmap) - set->flags |= BLK_MQ_F_TAG_HCTX_SHARED; - set->driver_data = nullb; - if (poll_queues) - set->nr_maps = 3; - else - set->nr_maps = 1; + if (nullb) { + hw_queues = nullb->dev->submit_queues; + poll_queues = nullb->dev->poll_queues; + queue_depth = nullb->dev->hw_queue_depth; + numa_node = nullb->dev->home_node; + if (nullb->dev->no_sched) + flags |= BLK_MQ_F_NO_SCHED; + if (nullb->dev->shared_tag_bitmap) + flags |= BLK_MQ_F_TAG_HCTX_SHARED; + if (nullb->dev->blocking) + flags |= BLK_MQ_F_BLOCKING; + } else { + hw_queues = g_submit_queues; + poll_queues = g_poll_queues; + queue_depth = g_hw_queue_depth; + numa_node = g_home_node; + if (g_no_sched) + flags |= BLK_MQ_F_NO_SCHED; + if (g_shared_tag_bitmap) + flags |= BLK_MQ_F_TAG_HCTX_SHARED; + if (g_blocking) + flags |= BLK_MQ_F_BLOCKING; + } - if ((nullb && nullb->dev->blocking) || g_blocking) - set->flags |= BLK_MQ_F_BLOCKING; + set->ops = &null_mq_ops; + set->cmd_size = sizeof(struct nullb_cmd); + set->flags = flags; + set->driver_data = nullb; + set->nr_hw_queues = hw_queues; + set->queue_depth = queue_depth; + set->numa_node = numa_node; + if (poll_queues) { + set->nr_hw_queues += poll_queues; + set->nr_maps = 3; + } else { + set->nr_maps = 1; + } return blk_mq_alloc_tag_set(set); } @@ -2042,8 +2090,13 @@ static int null_add_dev(struct nullb_device *dev) blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, nullb->q); mutex_lock(&lock); - nullb->index = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL); - dev->index = nullb->index; + rv = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL); + if (rv < 0) { + mutex_unlock(&lock); + goto out_cleanup_zone; + } + nullb->index = rv; + dev->index = rv; mutex_unlock(&lock); blk_queue_logical_block_size(nullb->q, dev->blocksize); @@ -2069,7 +2122,7 @@ static int null_add_dev(struct nullb_device *dev) rv = null_gendisk_register(nullb); if (rv) - goto out_cleanup_zone; + goto out_ida_free; mutex_lock(&lock); list_add_tail(&nullb->list, &nullb_list); @@ -2078,6 +2131,9 @@ static int null_add_dev(struct nullb_device *dev) pr_info("disk %s created\n", nullb->disk_name); return 0; + +out_ida_free: + ida_free(&nullb_indexes, nullb->index); out_cleanup_zone: null_free_zoned_dev(dev); out_cleanup_disk: diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h index 6fbf0a1b2622..94ff68052b1e 100644 --- a/drivers/block/null_blk/null_blk.h +++ b/drivers/block/null_blk/null_blk.h @@ -113,6 +113,8 @@ struct nullb_device { bool discard; /* if support discard */ bool zoned; /* if device is zoned */ bool virt_boundary; /* virtual boundary on/off for the device */ + bool no_sched; /* no IO scheduler for the device */ + bool shared_tag_bitmap; /* use hostwide shared tags */ }; struct nullb { diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 01a15dbd9cde..4cea3b08087e 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2399,7 +2399,7 @@ static void pkt_submit_bio(struct bio *bio) struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata; struct bio *split; - blk_queue_split(&bio); + bio = bio_split_to_limits(bio); pkt_dbg(2, pd, "start = %6llx stop = %6llx\n", (unsigned long long)bio->bi_iter.bi_sector, diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index d1e0fefec90b..e1d080f680ed 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -586,7 +586,7 @@ static void ps3vram_submit_bio(struct bio *bio) dev_dbg(&dev->core, "%s\n", __func__); - blk_queue_split(&bio); + bio = bio_split_to_limits(bio); spin_lock_irq(&priv->lock); busy = !bio_list_empty(&priv->list); diff --git a/drivers/block/rnbd/rnbd-clt-sysfs.c b/drivers/block/rnbd/rnbd-clt-sysfs.c index 2be5d87a3ca6..e7c7d9a68168 100644 --- a/drivers/block/rnbd/rnbd-clt-sysfs.c +++ b/drivers/block/rnbd/rnbd-clt-sysfs.c @@ -376,7 +376,7 @@ static ssize_t rnbd_clt_resize_dev_store(struct kobject *kobj, if (ret) return ret; - ret = rnbd_clt_resize_disk(dev, (size_t)sectors); + ret = rnbd_clt_resize_disk(dev, sectors); if (ret) return ret; diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index b8d9e2824d9c..04da33a22ef4 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -68,39 +68,18 @@ static inline bool rnbd_clt_get_dev(struct rnbd_clt_dev *dev) return refcount_inc_not_zero(&dev->refcount); } -static int rnbd_clt_set_dev_attr(struct rnbd_clt_dev *dev, - const struct rnbd_msg_open_rsp *rsp) +static void rnbd_clt_change_capacity(struct rnbd_clt_dev *dev, + sector_t new_nsectors) { - struct rnbd_clt_session *sess = dev->sess; + if (get_capacity(dev->gd) == new_nsectors) + return; - if (!rsp->logical_block_size) - return -EINVAL; - - dev->device_id = le32_to_cpu(rsp->device_id); - dev->nsectors = le64_to_cpu(rsp->nsectors); - dev->logical_block_size = le16_to_cpu(rsp->logical_block_size); - dev->physical_block_size = le16_to_cpu(rsp->physical_block_size); - dev->max_discard_sectors = le32_to_cpu(rsp->max_discard_sectors); - dev->discard_granularity = le32_to_cpu(rsp->discard_granularity); - dev->discard_alignment = le32_to_cpu(rsp->discard_alignment); - dev->secure_discard = le16_to_cpu(rsp->secure_discard); - dev->wc = !!(rsp->cache_policy & RNBD_WRITEBACK); - dev->fua = !!(rsp->cache_policy & RNBD_FUA); - - dev->max_hw_sectors = sess->max_io_size / SECTOR_SIZE; - dev->max_segments = sess->max_segments; - - return 0; -} - -static int rnbd_clt_change_capacity(struct rnbd_clt_dev *dev, - size_t new_nsectors) -{ - rnbd_clt_info(dev, "Device size changed from %zu to %zu sectors\n", - dev->nsectors, new_nsectors); - dev->nsectors = new_nsectors; - set_capacity_and_notify(dev->gd, dev->nsectors); - return 0; + /* + * If the size changed, we need to revalidate it + */ + rnbd_clt_info(dev, "Device size changed from %llu to %llu sectors\n", + get_capacity(dev->gd), new_nsectors); + set_capacity_and_notify(dev->gd, new_nsectors); } static int process_msg_open_rsp(struct rnbd_clt_dev *dev, @@ -119,19 +98,16 @@ static int process_msg_open_rsp(struct rnbd_clt_dev *dev, if (dev->dev_state == DEV_STATE_MAPPED_DISCONNECTED) { u64 nsectors = le64_to_cpu(rsp->nsectors); - /* - * If the device was remapped and the size changed in the - * meantime we need to revalidate it - */ - if (dev->nsectors != nsectors) - rnbd_clt_change_capacity(dev, nsectors); + rnbd_clt_change_capacity(dev, nsectors); gd_kobj = &disk_to_dev(dev->gd)->kobj; kobject_uevent(gd_kobj, KOBJ_ONLINE); rnbd_clt_info(dev, "Device online, device remapped successfully\n"); } - err = rnbd_clt_set_dev_attr(dev, rsp); - if (err) + if (!rsp->logical_block_size) { + err = -EINVAL; goto out; + } + dev->device_id = le32_to_cpu(rsp->device_id); dev->dev_state = DEV_STATE_MAPPED; out: @@ -140,7 +116,7 @@ static int process_msg_open_rsp(struct rnbd_clt_dev *dev, return err; } -int rnbd_clt_resize_disk(struct rnbd_clt_dev *dev, size_t newsize) +int rnbd_clt_resize_disk(struct rnbd_clt_dev *dev, sector_t newsize) { int ret = 0; @@ -150,7 +126,7 @@ int rnbd_clt_resize_disk(struct rnbd_clt_dev *dev, size_t newsize) ret = -ENOENT; goto out; } - ret = rnbd_clt_change_capacity(dev, newsize); + rnbd_clt_change_capacity(dev, newsize); out: mutex_unlock(&dev->lock); @@ -507,6 +483,11 @@ static void msg_open_conf(struct work_struct *work) struct rnbd_msg_open_rsp *rsp = iu->buf; struct rnbd_clt_dev *dev = iu->dev; int errno = iu->errno; + bool from_map = false; + + /* INIT state is only triggered from rnbd_clt_map_device */ + if (dev->dev_state == DEV_STATE_INIT) + from_map = true; if (errno) { rnbd_clt_err(dev, @@ -523,7 +504,9 @@ static void msg_open_conf(struct work_struct *work) send_msg_close(dev, device_id, RTRS_PERMIT_NOWAIT); } } - kfree(rsp); + /* We free rsp in rnbd_clt_map_device for map scenario */ + if (!from_map) + kfree(rsp); wake_up_iu_comp(iu, errno); rnbd_put_iu(dev->sess, iu); rnbd_clt_put_dev(dev); @@ -942,7 +925,7 @@ static int rnbd_client_open(struct block_device *block_device, fmode_t mode) { struct rnbd_clt_dev *dev = block_device->bd_disk->private_data; - if (dev->read_only && (mode & FMODE_WRITE)) + if (get_disk_ro(dev->gd) && (mode & FMODE_WRITE)) return -EPERM; if (dev->dev_state == DEV_STATE_UNMAPPED || @@ -963,10 +946,10 @@ static int rnbd_client_getgeo(struct block_device *block_device, struct hd_geometry *geo) { u64 size; - struct rnbd_clt_dev *dev; + struct rnbd_clt_dev *dev = block_device->bd_disk->private_data; + struct queue_limits *limit = &dev->queue->limits; - dev = block_device->bd_disk->private_data; - size = dev->size * (dev->logical_block_size / SECTOR_SIZE); + size = dev->size * (limit->logical_block_size / SECTOR_SIZE); geo->cylinders = size >> 6; /* size/64 */ geo->heads = 4; geo->sectors = 16; @@ -1350,11 +1333,15 @@ static void rnbd_init_mq_hw_queues(struct rnbd_clt_dev *dev) } } -static void setup_request_queue(struct rnbd_clt_dev *dev) +static void setup_request_queue(struct rnbd_clt_dev *dev, + struct rnbd_msg_open_rsp *rsp) { - blk_queue_logical_block_size(dev->queue, dev->logical_block_size); - blk_queue_physical_block_size(dev->queue, dev->physical_block_size); - blk_queue_max_hw_sectors(dev->queue, dev->max_hw_sectors); + blk_queue_logical_block_size(dev->queue, + le16_to_cpu(rsp->logical_block_size)); + blk_queue_physical_block_size(dev->queue, + le16_to_cpu(rsp->physical_block_size)); + blk_queue_max_hw_sectors(dev->queue, + dev->sess->max_io_size / SECTOR_SIZE); /* * we don't support discards to "discontiguous" segments @@ -1362,21 +1349,27 @@ static void setup_request_queue(struct rnbd_clt_dev *dev) */ blk_queue_max_discard_segments(dev->queue, 1); - blk_queue_max_discard_sectors(dev->queue, dev->max_discard_sectors); - dev->queue->limits.discard_granularity = dev->discard_granularity; - dev->queue->limits.discard_alignment = dev->discard_alignment; - if (dev->secure_discard) + blk_queue_max_discard_sectors(dev->queue, + le32_to_cpu(rsp->max_discard_sectors)); + dev->queue->limits.discard_granularity = + le32_to_cpu(rsp->discard_granularity); + dev->queue->limits.discard_alignment = + le32_to_cpu(rsp->discard_alignment); + if (le16_to_cpu(rsp->secure_discard)) blk_queue_max_secure_erase_sectors(dev->queue, - dev->max_discard_sectors); + le32_to_cpu(rsp->max_discard_sectors)); blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue); blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue); - blk_queue_max_segments(dev->queue, dev->max_segments); + blk_queue_max_segments(dev->queue, dev->sess->max_segments); blk_queue_io_opt(dev->queue, dev->sess->max_io_size); blk_queue_virt_boundary(dev->queue, SZ_4K - 1); - blk_queue_write_cache(dev->queue, dev->wc, dev->fua); + blk_queue_write_cache(dev->queue, + !!(rsp->cache_policy & RNBD_WRITEBACK), + !!(rsp->cache_policy & RNBD_FUA)); } -static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) +static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, + struct rnbd_msg_open_rsp *rsp, int idx) { int err; @@ -1388,19 +1381,15 @@ static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) dev->gd->private_data = dev; snprintf(dev->gd->disk_name, sizeof(dev->gd->disk_name), "rnbd%d", idx); - pr_debug("disk_name=%s, capacity=%zu\n", + pr_debug("disk_name=%s, capacity=%llu\n", dev->gd->disk_name, - dev->nsectors * (dev->logical_block_size / SECTOR_SIZE) - ); + le64_to_cpu(rsp->nsectors) * + (le16_to_cpu(rsp->logical_block_size) / SECTOR_SIZE)); - set_capacity(dev->gd, dev->nsectors); + set_capacity(dev->gd, le64_to_cpu(rsp->nsectors)); - if (dev->access_mode == RNBD_ACCESS_RO) { - dev->read_only = true; + if (dev->access_mode == RNBD_ACCESS_RO) set_disk_ro(dev->gd, true); - } else { - dev->read_only = false; - } /* * Network device does not need rotational @@ -1413,11 +1402,13 @@ static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) return err; } -static int rnbd_client_setup_device(struct rnbd_clt_dev *dev) +static int rnbd_client_setup_device(struct rnbd_clt_dev *dev, + struct rnbd_msg_open_rsp *rsp) { int idx = dev->clt_device_id; - dev->size = dev->nsectors * dev->logical_block_size; + dev->size = le64_to_cpu(rsp->nsectors) * + le16_to_cpu(rsp->logical_block_size); dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, dev); if (IS_ERR(dev->gd)) @@ -1425,8 +1416,8 @@ static int rnbd_client_setup_device(struct rnbd_clt_dev *dev) dev->queue = dev->gd->queue; rnbd_init_mq_hw_queues(dev); - setup_request_queue(dev); - return rnbd_clt_setup_gen_disk(dev, idx); + setup_request_queue(dev, rsp); + return rnbd_clt_setup_gen_disk(dev, rsp, idx); } static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, @@ -1562,7 +1553,14 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname, { struct rnbd_clt_session *sess; struct rnbd_clt_dev *dev; - int ret; + int ret, errno; + struct rnbd_msg_open_rsp *rsp; + struct rnbd_msg_open msg; + struct rnbd_iu *iu; + struct kvec vec = { + .iov_base = &msg, + .iov_len = sizeof(msg) + }; if (exists_devpath(pathname, sessname)) return ERR_PTR(-EEXIST); @@ -1582,17 +1580,47 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname, ret = -EEXIST; goto put_dev; } - ret = send_msg_open(dev, RTRS_PERMIT_WAIT); + + rsp = kzalloc(sizeof(*rsp), GFP_KERNEL); + if (!rsp) { + ret = -ENOMEM; + goto del_dev; + } + + iu = rnbd_get_iu(sess, RTRS_ADMIN_CON, RTRS_PERMIT_WAIT); + if (!iu) { + ret = -ENOMEM; + kfree(rsp); + goto del_dev; + } + iu->buf = rsp; + iu->dev = dev; + sg_init_one(iu->sgt.sgl, rsp, sizeof(*rsp)); + + msg.hdr.type = cpu_to_le16(RNBD_MSG_OPEN); + msg.access_mode = dev->access_mode; + strscpy(msg.dev_name, dev->pathname, sizeof(msg.dev_name)); + + WARN_ON(!rnbd_clt_get_dev(dev)); + ret = send_usr_msg(sess->rtrs, READ, iu, + &vec, sizeof(*rsp), iu->sgt.sgl, 1, + msg_open_conf, &errno, RTRS_PERMIT_WAIT); + if (ret) { + rnbd_clt_put_dev(dev); + rnbd_put_iu(sess, iu); + } else { + ret = errno; + } if (ret) { rnbd_clt_err(dev, "map_device: failed, can't open remote device, err: %d\n", ret); - goto del_dev; + goto put_iu; } mutex_lock(&dev->lock); pr_debug("Opened remote device: session=%s, path='%s'\n", sess->sessname, pathname); - ret = rnbd_client_setup_device(dev); + ret = rnbd_client_setup_device(dev, rsp); if (ret) { rnbd_clt_err(dev, "map_device: Failed to configure device, err: %d\n", @@ -1602,21 +1630,30 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname, } rnbd_clt_info(dev, - "map_device: Device mapped as %s (nsectors: %zu, logical_block_size: %d, physical_block_size: %d, max_discard_sectors: %d, discard_granularity: %d, discard_alignment: %d, secure_discard: %d, max_segments: %d, max_hw_sectors: %d, wc: %d, fua: %d)\n", - dev->gd->disk_name, dev->nsectors, - dev->logical_block_size, dev->physical_block_size, - dev->max_discard_sectors, - dev->discard_granularity, dev->discard_alignment, - dev->secure_discard, dev->max_segments, - dev->max_hw_sectors, dev->wc, dev->fua); + "map_device: Device mapped as %s (nsectors: %llu, logical_block_size: %d, physical_block_size: %d, max_discard_sectors: %d, discard_granularity: %d, discard_alignment: %d, secure_discard: %d, max_segments: %d, max_hw_sectors: %d, wc: %d, fua: %d)\n", + dev->gd->disk_name, le64_to_cpu(rsp->nsectors), + le16_to_cpu(rsp->logical_block_size), + le16_to_cpu(rsp->physical_block_size), + le32_to_cpu(rsp->max_discard_sectors), + le32_to_cpu(rsp->discard_granularity), + le32_to_cpu(rsp->discard_alignment), + le16_to_cpu(rsp->secure_discard), + sess->max_segments, sess->max_io_size / SECTOR_SIZE, + !!(rsp->cache_policy & RNBD_WRITEBACK), + !!(rsp->cache_policy & RNBD_FUA)); mutex_unlock(&dev->lock); + kfree(rsp); + rnbd_put_iu(sess, iu); rnbd_clt_put_sess(sess); return dev; send_close: send_msg_close(dev, dev->device_id, RTRS_PERMIT_WAIT); +put_iu: + kfree(rsp); + rnbd_put_iu(sess, iu); del_dev: delete_dev(dev); put_dev: diff --git a/drivers/block/rnbd/rnbd-clt.h b/drivers/block/rnbd/rnbd-clt.h index 2e2e8c4a85c1..a48e040abe63 100644 --- a/drivers/block/rnbd/rnbd-clt.h +++ b/drivers/block/rnbd/rnbd-clt.h @@ -106,6 +106,7 @@ struct rnbd_queue { }; struct rnbd_clt_dev { + struct kobject kobj; struct rnbd_clt_session *sess; struct request_queue *queue; struct rnbd_queue *hw_queues; @@ -114,27 +115,14 @@ struct rnbd_clt_dev { u32 clt_device_id; struct mutex lock; enum rnbd_clt_dev_state dev_state; + refcount_t refcount; char *pathname; enum rnbd_access_mode access_mode; u32 nr_poll_queues; - bool read_only; - bool wc; - bool fua; - u32 max_hw_sectors; - u32 max_discard_sectors; - u32 discard_granularity; - u32 discard_alignment; - u16 secure_discard; - u16 physical_block_size; - u16 logical_block_size; - u16 max_segments; - size_t nsectors; u64 size; /* device size in bytes */ struct list_head list; struct gendisk *gd; - struct kobject kobj; char *blk_symlink_name; - refcount_t refcount; struct work_struct unmap_on_rmmod_work; }; @@ -150,7 +138,7 @@ int rnbd_clt_unmap_device(struct rnbd_clt_dev *dev, bool force, const struct attribute *sysfs_self); int rnbd_clt_remap_device(struct rnbd_clt_dev *dev); -int rnbd_clt_resize_disk(struct rnbd_clt_dev *dev, size_t newsize); +int rnbd_clt_resize_disk(struct rnbd_clt_dev *dev, sector_t newsize); /* rnbd-clt-sysfs.c */ diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index 0713014bf423..5e08da277ddf 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -224,7 +224,6 @@ void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id) wait_for_completion(&dc); /* wait for inflights to drop to zero */ rnbd_dev_close(sess_dev->rnbd_dev); - list_del(&sess_dev->sess_list); mutex_lock(&sess_dev->dev->lock); list_del(&sess_dev->dev_list); if (sess_dev->open_flags & FMODE_WRITE) @@ -239,14 +238,14 @@ void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id) static void destroy_sess(struct rnbd_srv_session *srv_sess) { - struct rnbd_srv_sess_dev *sess_dev, *tmp; + struct rnbd_srv_sess_dev *sess_dev; + unsigned long index; - if (list_empty(&srv_sess->sess_dev_list)) + if (xa_empty(&srv_sess->index_idr)) goto out; mutex_lock(&srv_sess->lock); - list_for_each_entry_safe(sess_dev, tmp, &srv_sess->sess_dev_list, - sess_list) + xa_for_each(&srv_sess->index_idr, index, sess_dev) rnbd_srv_destroy_dev_session_sysfs(sess_dev); mutex_unlock(&srv_sess->lock); @@ -281,7 +280,6 @@ static int create_sess(struct rtrs_srv_sess *rtrs) srv_sess->queue_depth = rtrs_srv_get_queue_depth(rtrs); xa_init_flags(&srv_sess->index_idr, XA_FLAGS_ALLOC); - INIT_LIST_HEAD(&srv_sess->sess_dev_list); mutex_init(&srv_sess->lock); mutex_lock(&sess_lock); list_add(&srv_sess->list, &sess_list); @@ -323,10 +321,11 @@ void rnbd_srv_sess_dev_force_close(struct rnbd_srv_sess_dev *sess_dev, { struct rnbd_srv_session *sess = sess_dev->sess; - sess_dev->keep_id = true; /* It is already started to close by client's close message. */ if (!mutex_trylock(&sess->lock)) return; + + sess_dev->keep_id = true; /* first remove sysfs itself to avoid deadlock */ sysfs_remove_file_self(&sess_dev->kobj, &attr->attr); rnbd_srv_destroy_dev_session_sysfs(sess_dev); @@ -666,11 +665,12 @@ static struct rnbd_srv_sess_dev * find_srv_sess_dev(struct rnbd_srv_session *srv_sess, const char *dev_name) { struct rnbd_srv_sess_dev *sess_dev; + unsigned long index; - if (list_empty(&srv_sess->sess_dev_list)) + if (xa_empty(&srv_sess->index_idr)) return NULL; - list_for_each_entry(sess_dev, &srv_sess->sess_dev_list, sess_list) + xa_for_each(&srv_sess->index_idr, index, sess_dev) if (!strcmp(sess_dev->pathname, dev_name)) return sess_dev; @@ -780,8 +780,6 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, list_add(&srv_sess_dev->dev_list, &srv_dev->sess_dev_list); mutex_unlock(&srv_dev->lock); - list_add(&srv_sess_dev->sess_list, &srv_sess->sess_dev_list); - rnbd_srv_info(srv_sess_dev, "Opened device '%s'\n", srv_dev->id); kfree(full_path); diff --git a/drivers/block/rnbd/rnbd-srv.h b/drivers/block/rnbd/rnbd-srv.h index 6926f9069dc4..081bceaf4ae9 100644 --- a/drivers/block/rnbd/rnbd-srv.h +++ b/drivers/block/rnbd/rnbd-srv.h @@ -25,8 +25,6 @@ struct rnbd_srv_session { int queue_depth; struct xarray index_idr; - /* List of struct rnbd_srv_sess_dev */ - struct list_head sess_dev_list; struct mutex lock; u8 ver; }; @@ -48,8 +46,6 @@ struct rnbd_srv_dev { struct rnbd_srv_sess_dev { /* Entry inside rnbd_srv_dev struct */ struct list_head dev_list; - /* Entry inside rnbd_srv_session struct */ - struct list_head sess_list; struct rnbd_dev *rnbd_dev; struct rnbd_srv_session *sess; struct rnbd_srv_dev *dev; diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c deleted file mode 100644 index 0e1a484cab0b..000000000000 --- a/drivers/block/sx8.c +++ /dev/null @@ -1,1582 +0,0 @@ -/* - * sx8.c: Driver for Promise SATA SX8 looks-like-I2O hardware - * - * Copyright 2004-2005 Red Hat, Inc. - * - * Author/maintainer: Jeff Garzik - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#if 0 -#define CARM_DEBUG -#define CARM_VERBOSE_DEBUG -#else -#undef CARM_DEBUG -#undef CARM_VERBOSE_DEBUG -#endif -#undef CARM_NDEBUG - -#define DRV_NAME "sx8" -#define DRV_VERSION "1.0" -#define PFX DRV_NAME ": " - -MODULE_AUTHOR("Jeff Garzik"); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Promise SATA SX8 block driver"); -MODULE_VERSION(DRV_VERSION); - -/* - * SX8 hardware has a single message queue for all ATA ports. - * When this driver was written, the hardware (firmware?) would - * corrupt data eventually, if more than one request was outstanding. - * As one can imagine, having 8 ports bottlenecking on a single - * command hurts performance. - * - * Based on user reports, later versions of the hardware (firmware?) - * seem to be able to survive with more than one command queued. - * - * Therefore, we default to the safe option -- 1 command -- but - * allow the user to increase this. - * - * SX8 should be able to support up to ~60 queued commands (CARM_MAX_REQ), - * but problems seem to occur when you exceed ~30, even on newer hardware. - */ -static int max_queue = 1; -module_param(max_queue, int, 0444); -MODULE_PARM_DESC(max_queue, "Maximum number of queued commands. (min==1, max==30, safe==1)"); - - -#define NEXT_RESP(idx) ((idx + 1) % RMSG_Q_LEN) - -/* 0xf is just arbitrary, non-zero noise; this is sorta like poisoning */ -#define TAG_ENCODE(tag) (((tag) << 16) | 0xf) -#define TAG_DECODE(tag) (((tag) >> 16) & 0x1f) -#define TAG_VALID(tag) ((((tag) & 0xf) == 0xf) && (TAG_DECODE(tag) < 32)) - -/* note: prints function name for you */ -#ifdef CARM_DEBUG -#define DPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#ifdef CARM_VERBOSE_DEBUG -#define VPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#else -#define VPRINTK(fmt, args...) -#endif /* CARM_VERBOSE_DEBUG */ -#else -#define DPRINTK(fmt, args...) -#define VPRINTK(fmt, args...) -#endif /* CARM_DEBUG */ - -#ifdef CARM_NDEBUG -#define assert(expr) -#else -#define assert(expr) \ - if(unlikely(!(expr))) { \ - printk(KERN_ERR "Assertion failed! %s,%s,%s,line=%d\n", \ - #expr, __FILE__, __func__, __LINE__); \ - } -#endif - -/* defines only for the constants which don't work well as enums */ -struct carm_host; - -enum { - /* adapter-wide limits */ - CARM_MAX_PORTS = 8, - CARM_SHM_SIZE = (4096 << 7), - CARM_MINORS_PER_MAJOR = 256 / CARM_MAX_PORTS, - CARM_MAX_WAIT_Q = CARM_MAX_PORTS + 1, - - /* command message queue limits */ - CARM_MAX_REQ = 64, /* max command msgs per host */ - CARM_MSG_LOW_WATER = (CARM_MAX_REQ / 4), /* refill mark */ - - /* S/G limits, host-wide and per-request */ - CARM_MAX_REQ_SG = 32, /* max s/g entries per request */ - CARM_MAX_HOST_SG = 600, /* max s/g entries per host */ - CARM_SG_LOW_WATER = (CARM_MAX_HOST_SG / 4), /* re-fill mark */ - - /* hardware registers */ - CARM_IHQP = 0x1c, - CARM_INT_STAT = 0x10, /* interrupt status */ - CARM_INT_MASK = 0x14, /* interrupt mask */ - CARM_HMUC = 0x18, /* host message unit control */ - RBUF_ADDR_LO = 0x20, /* response msg DMA buf low 32 bits */ - RBUF_ADDR_HI = 0x24, /* response msg DMA buf high 32 bits */ - RBUF_BYTE_SZ = 0x28, - CARM_RESP_IDX = 0x2c, - CARM_CMS0 = 0x30, /* command message size reg 0 */ - CARM_LMUC = 0x48, - CARM_HMPHA = 0x6c, - CARM_INITC = 0xb5, - - /* bits in CARM_INT_{STAT,MASK} */ - INT_RESERVED = 0xfffffff0, - INT_WATCHDOG = (1 << 3), /* watchdog timer */ - INT_Q_OVERFLOW = (1 << 2), /* cmd msg q overflow */ - INT_Q_AVAILABLE = (1 << 1), /* cmd msg q has free space */ - INT_RESPONSE = (1 << 0), /* response msg available */ - INT_ACK_MASK = INT_WATCHDOG | INT_Q_OVERFLOW, - INT_DEF_MASK = INT_RESERVED | INT_Q_OVERFLOW | - INT_RESPONSE, - - /* command messages, and related register bits */ - CARM_HAVE_RESP = 0x01, - CARM_MSG_READ = 1, - CARM_MSG_WRITE = 2, - CARM_MSG_VERIFY = 3, - CARM_MSG_GET_CAPACITY = 4, - CARM_MSG_FLUSH = 5, - CARM_MSG_IOCTL = 6, - CARM_MSG_ARRAY = 8, - CARM_MSG_MISC = 9, - CARM_CME = (1 << 2), - CARM_RME = (1 << 1), - CARM_WZBC = (1 << 0), - CARM_RMI = (1 << 0), - CARM_Q_FULL = (1 << 3), - CARM_MSG_SIZE = 288, - CARM_Q_LEN = 48, - - /* CARM_MSG_IOCTL messages */ - CARM_IOC_SCAN_CHAN = 5, /* scan channels for devices */ - CARM_IOC_GET_TCQ = 13, /* get tcq/ncq depth */ - CARM_IOC_SET_TCQ = 14, /* set tcq/ncq depth */ - - IOC_SCAN_CHAN_NODEV = 0x1f, - IOC_SCAN_CHAN_OFFSET = 0x40, - - /* CARM_MSG_ARRAY messages */ - CARM_ARRAY_INFO = 0, - - ARRAY_NO_EXIST = (1 << 31), - - /* response messages */ - RMSG_SZ = 8, /* sizeof(struct carm_response) */ - RMSG_Q_LEN = 48, /* resp. msg list length */ - RMSG_OK = 1, /* bit indicating msg was successful */ - /* length of entire resp. msg buffer */ - RBUF_LEN = RMSG_SZ * RMSG_Q_LEN, - - PDC_SHM_SIZE = (4096 << 7), /* length of entire h/w buffer */ - - /* CARM_MSG_MISC messages */ - MISC_GET_FW_VER = 2, - MISC_ALLOC_MEM = 3, - MISC_SET_TIME = 5, - - /* MISC_GET_FW_VER feature bits */ - FW_VER_4PORT = (1 << 2), /* 1=4 ports, 0=8 ports */ - FW_VER_NON_RAID = (1 << 1), /* 1=non-RAID firmware, 0=RAID */ - FW_VER_ZCR = (1 << 0), /* zero channel RAID (whatever that is) */ - - /* carm_host flags */ - FL_NON_RAID = FW_VER_NON_RAID, - FL_4PORT = FW_VER_4PORT, - FL_FW_VER_MASK = (FW_VER_NON_RAID | FW_VER_4PORT), - FL_DYN_MAJOR = (1 << 17), -}; - -enum { - CARM_SG_BOUNDARY = 0xffffUL, /* s/g segment boundary */ -}; - -enum scatter_gather_types { - SGT_32BIT = 0, - SGT_64BIT = 1, -}; - -enum host_states { - HST_INVALID, /* invalid state; never used */ - HST_ALLOC_BUF, /* setting up master SHM area */ - HST_ERROR, /* we never leave here */ - HST_PORT_SCAN, /* start dev scan */ - HST_DEV_SCAN_START, /* start per-device probe */ - HST_DEV_SCAN, /* continue per-device probe */ - HST_DEV_ACTIVATE, /* activate devices we found */ - HST_PROBE_FINISHED, /* probe is complete */ - HST_PROBE_START, /* initiate probe */ - HST_SYNC_TIME, /* tell firmware what time it is */ - HST_GET_FW_VER, /* get firmware version, adapter port cnt */ -}; - -#ifdef CARM_DEBUG -static const char *state_name[] = { - "HST_INVALID", - "HST_ALLOC_BUF", - "HST_ERROR", - "HST_PORT_SCAN", - "HST_DEV_SCAN_START", - "HST_DEV_SCAN", - "HST_DEV_ACTIVATE", - "HST_PROBE_FINISHED", - "HST_PROBE_START", - "HST_SYNC_TIME", - "HST_GET_FW_VER", -}; -#endif - -struct carm_port { - unsigned int port_no; - struct gendisk *disk; - struct carm_host *host; - - /* attached device characteristics */ - u64 capacity; - char name[41]; - u16 dev_geom_head; - u16 dev_geom_sect; - u16 dev_geom_cyl; -}; - -struct carm_request { - int n_elem; - unsigned int msg_type; - unsigned int msg_subtype; - unsigned int msg_bucket; - struct scatterlist sg[CARM_MAX_REQ_SG]; -}; - -struct carm_host { - unsigned long flags; - void __iomem *mmio; - void *shm; - dma_addr_t shm_dma; - - int major; - int id; - char name[32]; - - spinlock_t lock; - struct pci_dev *pdev; - unsigned int state; - u32 fw_ver; - - struct blk_mq_tag_set tag_set; - struct request_queue *oob_q; - unsigned int n_oob; - - unsigned int hw_sg_used; - - unsigned int resp_idx; - - unsigned int wait_q_prod; - unsigned int wait_q_cons; - struct request_queue *wait_q[CARM_MAX_WAIT_Q]; - - void *msg_base; - dma_addr_t msg_dma; - - int cur_scan_dev; - unsigned long dev_active; - unsigned long dev_present; - struct carm_port port[CARM_MAX_PORTS]; - - struct work_struct fsm_task; - - int probe_err; - struct completion probe_comp; -}; - -struct carm_response { - __le32 ret_handle; - __le32 status; -} __attribute__((packed)); - -struct carm_msg_sg { - __le32 start; - __le32 len; -} __attribute__((packed)); - -struct carm_msg_rw { - u8 type; - u8 id; - u8 sg_count; - u8 sg_type; - __le32 handle; - __le32 lba; - __le16 lba_count; - __le16 lba_high; - struct carm_msg_sg sg[32]; -} __attribute__((packed)); - -struct carm_msg_allocbuf { - u8 type; - u8 subtype; - u8 n_sg; - u8 sg_type; - __le32 handle; - __le32 addr; - __le32 len; - __le32 evt_pool; - __le32 n_evt; - __le32 rbuf_pool; - __le32 n_rbuf; - __le32 msg_pool; - __le32 n_msg; - struct carm_msg_sg sg[8]; -} __attribute__((packed)); - -struct carm_msg_ioctl { - u8 type; - u8 subtype; - u8 array_id; - u8 reserved1; - __le32 handle; - __le32 data_addr; - u32 reserved2; -} __attribute__((packed)); - -struct carm_msg_sync_time { - u8 type; - u8 subtype; - u16 reserved1; - __le32 handle; - u32 reserved2; - __le32 timestamp; -} __attribute__((packed)); - -struct carm_msg_get_fw_ver { - u8 type; - u8 subtype; - u16 reserved1; - __le32 handle; - __le32 data_addr; - u32 reserved2; -} __attribute__((packed)); - -struct carm_fw_ver { - __le32 version; - u8 features; - u8 reserved1; - u16 reserved2; -} __attribute__((packed)); - -struct carm_array_info { - __le32 size; - - __le16 size_hi; - __le16 stripe_size; - - __le32 mode; - - __le16 stripe_blk_sz; - __le16 reserved1; - - __le16 cyl; - __le16 head; - - __le16 sect; - u8 array_id; - u8 reserved2; - - char name[40]; - - __le32 array_status; - - /* device list continues beyond this point? */ -} __attribute__((packed)); - -static int carm_init_one (struct pci_dev *pdev, const struct pci_device_id *ent); -static void carm_remove_one (struct pci_dev *pdev); -static int carm_bdev_getgeo(struct block_device *bdev, struct hd_geometry *geo); - -static const struct pci_device_id carm_pci_tbl[] = { - { PCI_VENDOR_ID_PROMISE, 0x8000, PCI_ANY_ID, PCI_ANY_ID, 0, 0, }, - { PCI_VENDOR_ID_PROMISE, 0x8002, PCI_ANY_ID, PCI_ANY_ID, 0, 0, }, - { } /* terminate list */ -}; -MODULE_DEVICE_TABLE(pci, carm_pci_tbl); - -static struct pci_driver carm_driver = { - .name = DRV_NAME, - .id_table = carm_pci_tbl, - .probe = carm_init_one, - .remove = carm_remove_one, -}; - -static const struct block_device_operations carm_bd_ops = { - .owner = THIS_MODULE, - .getgeo = carm_bdev_getgeo, -}; - -static unsigned int carm_host_id; -static unsigned long carm_major_alloc; - - - -static int carm_bdev_getgeo(struct block_device *bdev, struct hd_geometry *geo) -{ - struct carm_port *port = bdev->bd_disk->private_data; - - geo->heads = (u8) port->dev_geom_head; - geo->sectors = (u8) port->dev_geom_sect; - geo->cylinders = port->dev_geom_cyl; - return 0; -} - -static const u32 msg_sizes[] = { 32, 64, 128, CARM_MSG_SIZE }; - -static inline int carm_lookup_bucket(u32 msg_size) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(msg_sizes); i++) - if (msg_size <= msg_sizes[i]) - return i; - - return -ENOENT; -} - -static void carm_init_buckets(void __iomem *mmio) -{ - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(msg_sizes); i++) - writel(msg_sizes[i], mmio + CARM_CMS0 + (4 * i)); -} - -static inline void *carm_ref_msg(struct carm_host *host, - unsigned int msg_idx) -{ - return host->msg_base + (msg_idx * CARM_MSG_SIZE); -} - -static inline dma_addr_t carm_ref_msg_dma(struct carm_host *host, - unsigned int msg_idx) -{ - return host->msg_dma + (msg_idx * CARM_MSG_SIZE); -} - -static int carm_send_msg(struct carm_host *host, - struct carm_request *crq, unsigned tag) -{ - void __iomem *mmio = host->mmio; - u32 msg = (u32) carm_ref_msg_dma(host, tag); - u32 cm_bucket = crq->msg_bucket; - u32 tmp; - int rc = 0; - - VPRINTK("ENTER\n"); - - tmp = readl(mmio + CARM_HMUC); - if (tmp & CARM_Q_FULL) { -#if 0 - tmp = readl(mmio + CARM_INT_MASK); - tmp |= INT_Q_AVAILABLE; - writel(tmp, mmio + CARM_INT_MASK); - readl(mmio + CARM_INT_MASK); /* flush */ -#endif - DPRINTK("host msg queue full\n"); - rc = -EBUSY; - } else { - writel(msg | (cm_bucket << 1), mmio + CARM_IHQP); - readl(mmio + CARM_IHQP); /* flush */ - } - - return rc; -} - -static int carm_array_info (struct carm_host *host, unsigned int array_idx) -{ - struct carm_msg_ioctl *ioc; - u32 msg_data; - dma_addr_t msg_dma; - struct carm_request *crq; - struct request *rq; - int rc; - - rq = blk_mq_alloc_request(host->oob_q, REQ_OP_DRV_OUT, 0); - if (IS_ERR(rq)) { - rc = -ENOMEM; - goto err_out; - } - crq = blk_mq_rq_to_pdu(rq); - - ioc = carm_ref_msg(host, rq->tag); - msg_dma = carm_ref_msg_dma(host, rq->tag); - msg_data = (u32) (msg_dma + sizeof(struct carm_array_info)); - - crq->msg_type = CARM_MSG_ARRAY; - crq->msg_subtype = CARM_ARRAY_INFO; - rc = carm_lookup_bucket(sizeof(struct carm_msg_ioctl) + - sizeof(struct carm_array_info)); - BUG_ON(rc < 0); - crq->msg_bucket = (u32) rc; - - memset(ioc, 0, sizeof(*ioc)); - ioc->type = CARM_MSG_ARRAY; - ioc->subtype = CARM_ARRAY_INFO; - ioc->array_id = (u8) array_idx; - ioc->handle = cpu_to_le32(TAG_ENCODE(rq->tag)); - ioc->data_addr = cpu_to_le32(msg_data); - - spin_lock_irq(&host->lock); - assert(host->state == HST_DEV_SCAN_START || - host->state == HST_DEV_SCAN); - spin_unlock_irq(&host->lock); - - DPRINTK("blk_execute_rq_nowait, tag == %u\n", rq->tag); - blk_execute_rq_nowait(rq, true); - - return 0; - -err_out: - spin_lock_irq(&host->lock); - host->state = HST_ERROR; - spin_unlock_irq(&host->lock); - return rc; -} - -typedef unsigned int (*carm_sspc_t)(struct carm_host *, unsigned int, void *); - -static int carm_send_special (struct carm_host *host, carm_sspc_t func) -{ - struct request *rq; - struct carm_request *crq; - struct carm_msg_ioctl *ioc; - void *mem; - unsigned int msg_size; - int rc; - - rq = blk_mq_alloc_request(host->oob_q, REQ_OP_DRV_OUT, 0); - if (IS_ERR(rq)) - return -ENOMEM; - crq = blk_mq_rq_to_pdu(rq); - - mem = carm_ref_msg(host, rq->tag); - - msg_size = func(host, rq->tag, mem); - - ioc = mem; - crq->msg_type = ioc->type; - crq->msg_subtype = ioc->subtype; - rc = carm_lookup_bucket(msg_size); - BUG_ON(rc < 0); - crq->msg_bucket = (u32) rc; - - DPRINTK("blk_execute_rq_nowait, tag == %u\n", rq->tag); - blk_execute_rq_nowait(rq, true); - - return 0; -} - -static unsigned int carm_fill_sync_time(struct carm_host *host, - unsigned int idx, void *mem) -{ - struct carm_msg_sync_time *st = mem; - - time64_t tv = ktime_get_real_seconds(); - - memset(st, 0, sizeof(*st)); - st->type = CARM_MSG_MISC; - st->subtype = MISC_SET_TIME; - st->handle = cpu_to_le32(TAG_ENCODE(idx)); - st->timestamp = cpu_to_le32(tv); - - return sizeof(struct carm_msg_sync_time); -} - -static unsigned int carm_fill_alloc_buf(struct carm_host *host, - unsigned int idx, void *mem) -{ - struct carm_msg_allocbuf *ab = mem; - - memset(ab, 0, sizeof(*ab)); - ab->type = CARM_MSG_MISC; - ab->subtype = MISC_ALLOC_MEM; - ab->handle = cpu_to_le32(TAG_ENCODE(idx)); - ab->n_sg = 1; - ab->sg_type = SGT_32BIT; - ab->addr = cpu_to_le32(host->shm_dma + (PDC_SHM_SIZE >> 1)); - ab->len = cpu_to_le32(PDC_SHM_SIZE >> 1); - ab->evt_pool = cpu_to_le32(host->shm_dma + (16 * 1024)); - ab->n_evt = cpu_to_le32(1024); - ab->rbuf_pool = cpu_to_le32(host->shm_dma); - ab->n_rbuf = cpu_to_le32(RMSG_Q_LEN); - ab->msg_pool = cpu_to_le32(host->shm_dma + RBUF_LEN); - ab->n_msg = cpu_to_le32(CARM_Q_LEN); - ab->sg[0].start = cpu_to_le32(host->shm_dma + (PDC_SHM_SIZE >> 1)); - ab->sg[0].len = cpu_to_le32(65536); - - return sizeof(struct carm_msg_allocbuf); -} - -static unsigned int carm_fill_scan_channels(struct carm_host *host, - unsigned int idx, void *mem) -{ - struct carm_msg_ioctl *ioc = mem; - u32 msg_data = (u32) (carm_ref_msg_dma(host, idx) + - IOC_SCAN_CHAN_OFFSET); - - memset(ioc, 0, sizeof(*ioc)); - ioc->type = CARM_MSG_IOCTL; - ioc->subtype = CARM_IOC_SCAN_CHAN; - ioc->handle = cpu_to_le32(TAG_ENCODE(idx)); - ioc->data_addr = cpu_to_le32(msg_data); - - /* fill output data area with "no device" default values */ - mem += IOC_SCAN_CHAN_OFFSET; - memset(mem, IOC_SCAN_CHAN_NODEV, CARM_MAX_PORTS); - - return IOC_SCAN_CHAN_OFFSET + CARM_MAX_PORTS; -} - -static unsigned int carm_fill_get_fw_ver(struct carm_host *host, - unsigned int idx, void *mem) -{ - struct carm_msg_get_fw_ver *ioc = mem; - u32 msg_data = (u32) (carm_ref_msg_dma(host, idx) + sizeof(*ioc)); - - memset(ioc, 0, sizeof(*ioc)); - ioc->type = CARM_MSG_MISC; - ioc->subtype = MISC_GET_FW_VER; - ioc->handle = cpu_to_le32(TAG_ENCODE(idx)); - ioc->data_addr = cpu_to_le32(msg_data); - - return sizeof(struct carm_msg_get_fw_ver) + - sizeof(struct carm_fw_ver); -} - -static inline void carm_push_q (struct carm_host *host, struct request_queue *q) -{ - unsigned int idx = host->wait_q_prod % CARM_MAX_WAIT_Q; - - blk_mq_stop_hw_queues(q); - VPRINTK("STOPPED QUEUE %p\n", q); - - host->wait_q[idx] = q; - host->wait_q_prod++; - BUG_ON(host->wait_q_prod == host->wait_q_cons); /* overrun */ -} - -static inline struct request_queue *carm_pop_q(struct carm_host *host) -{ - unsigned int idx; - - if (host->wait_q_prod == host->wait_q_cons) - return NULL; - - idx = host->wait_q_cons % CARM_MAX_WAIT_Q; - host->wait_q_cons++; - - return host->wait_q[idx]; -} - -static inline void carm_round_robin(struct carm_host *host) -{ - struct request_queue *q = carm_pop_q(host); - if (q) { - blk_mq_start_hw_queues(q); - VPRINTK("STARTED QUEUE %p\n", q); - } -} - -static inline enum dma_data_direction carm_rq_dir(struct request *rq) -{ - return op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; -} - -static blk_status_t carm_queue_rq(struct blk_mq_hw_ctx *hctx, - const struct blk_mq_queue_data *bd) -{ - struct request_queue *q = hctx->queue; - struct request *rq = bd->rq; - struct carm_port *port = q->queuedata; - struct carm_host *host = port->host; - struct carm_request *crq = blk_mq_rq_to_pdu(rq); - struct carm_msg_rw *msg; - struct scatterlist *sg; - int i, n_elem = 0, rc; - unsigned int msg_size; - u32 tmp; - - crq->n_elem = 0; - sg_init_table(crq->sg, CARM_MAX_REQ_SG); - - blk_mq_start_request(rq); - - spin_lock_irq(&host->lock); - if (req_op(rq) == REQ_OP_DRV_OUT) - goto send_msg; - - /* get scatterlist from block layer */ - sg = &crq->sg[0]; - n_elem = blk_rq_map_sg(q, rq, sg); - if (n_elem <= 0) - goto out_ioerr; - - /* map scatterlist to PCI bus addresses */ - n_elem = dma_map_sg(&host->pdev->dev, sg, n_elem, carm_rq_dir(rq)); - if (n_elem <= 0) - goto out_ioerr; - - /* obey global hardware limit on S/G entries */ - if (host->hw_sg_used >= CARM_MAX_HOST_SG - n_elem) - goto out_resource; - - crq->n_elem = n_elem; - host->hw_sg_used += n_elem; - - /* - * build read/write message - */ - - VPRINTK("build msg\n"); - msg = (struct carm_msg_rw *) carm_ref_msg(host, rq->tag); - - if (rq_data_dir(rq) == WRITE) { - msg->type = CARM_MSG_WRITE; - crq->msg_type = CARM_MSG_WRITE; - } else { - msg->type = CARM_MSG_READ; - crq->msg_type = CARM_MSG_READ; - } - - msg->id = port->port_no; - msg->sg_count = n_elem; - msg->sg_type = SGT_32BIT; - msg->handle = cpu_to_le32(TAG_ENCODE(rq->tag)); - msg->lba = cpu_to_le32(blk_rq_pos(rq) & 0xffffffff); - tmp = (blk_rq_pos(rq) >> 16) >> 16; - msg->lba_high = cpu_to_le16( (u16) tmp ); - msg->lba_count = cpu_to_le16(blk_rq_sectors(rq)); - - msg_size = sizeof(struct carm_msg_rw) - sizeof(msg->sg); - for (i = 0; i < n_elem; i++) { - struct carm_msg_sg *carm_sg = &msg->sg[i]; - carm_sg->start = cpu_to_le32(sg_dma_address(&crq->sg[i])); - carm_sg->len = cpu_to_le32(sg_dma_len(&crq->sg[i])); - msg_size += sizeof(struct carm_msg_sg); - } - - rc = carm_lookup_bucket(msg_size); - BUG_ON(rc < 0); - crq->msg_bucket = (u32) rc; -send_msg: - /* - * queue read/write message to hardware - */ - VPRINTK("send msg, tag == %u\n", rq->tag); - rc = carm_send_msg(host, crq, rq->tag); - if (rc) { - host->hw_sg_used -= n_elem; - goto out_resource; - } - - spin_unlock_irq(&host->lock); - return BLK_STS_OK; -out_resource: - dma_unmap_sg(&host->pdev->dev, &crq->sg[0], n_elem, carm_rq_dir(rq)); - carm_push_q(host, q); - spin_unlock_irq(&host->lock); - return BLK_STS_DEV_RESOURCE; -out_ioerr: - carm_round_robin(host); - spin_unlock_irq(&host->lock); - return BLK_STS_IOERR; -} - -static void carm_handle_array_info(struct carm_host *host, - struct carm_request *crq, u8 *mem, - blk_status_t error) -{ - struct carm_port *port; - u8 *msg_data = mem + sizeof(struct carm_array_info); - struct carm_array_info *desc = (struct carm_array_info *) msg_data; - u64 lo, hi; - int cur_port; - size_t slen; - - DPRINTK("ENTER\n"); - - if (error) - goto out; - if (le32_to_cpu(desc->array_status) & ARRAY_NO_EXIST) - goto out; - - cur_port = host->cur_scan_dev; - - /* should never occur */ - if ((cur_port < 0) || (cur_port >= CARM_MAX_PORTS)) { - printk(KERN_ERR PFX "BUG: cur_scan_dev==%d, array_id==%d\n", - cur_port, (int) desc->array_id); - goto out; - } - - port = &host->port[cur_port]; - - lo = (u64) le32_to_cpu(desc->size); - hi = (u64) le16_to_cpu(desc->size_hi); - - port->capacity = lo | (hi << 32); - port->dev_geom_head = le16_to_cpu(desc->head); - port->dev_geom_sect = le16_to_cpu(desc->sect); - port->dev_geom_cyl = le16_to_cpu(desc->cyl); - - host->dev_active |= (1 << cur_port); - - strncpy(port->name, desc->name, sizeof(port->name)); - port->name[sizeof(port->name) - 1] = 0; - slen = strlen(port->name); - while (slen && (port->name[slen - 1] == ' ')) { - port->name[slen - 1] = 0; - slen--; - } - - printk(KERN_INFO DRV_NAME "(%s): port %u device %Lu sectors\n", - pci_name(host->pdev), port->port_no, - (unsigned long long) port->capacity); - printk(KERN_INFO DRV_NAME "(%s): port %u device \"%s\"\n", - pci_name(host->pdev), port->port_no, port->name); - -out: - assert(host->state == HST_DEV_SCAN); - schedule_work(&host->fsm_task); -} - -static void carm_handle_scan_chan(struct carm_host *host, - struct carm_request *crq, u8 *mem, - blk_status_t error) -{ - u8 *msg_data = mem + IOC_SCAN_CHAN_OFFSET; - unsigned int i, dev_count = 0; - int new_state = HST_DEV_SCAN_START; - - DPRINTK("ENTER\n"); - - if (error) { - new_state = HST_ERROR; - goto out; - } - - /* TODO: scan and support non-disk devices */ - for (i = 0; i < 8; i++) - if (msg_data[i] == 0) { /* direct-access device (disk) */ - host->dev_present |= (1 << i); - dev_count++; - } - - printk(KERN_INFO DRV_NAME "(%s): found %u interesting devices\n", - pci_name(host->pdev), dev_count); - -out: - assert(host->state == HST_PORT_SCAN); - host->state = new_state; - schedule_work(&host->fsm_task); -} - -static void carm_handle_generic(struct carm_host *host, - struct carm_request *crq, blk_status_t error, - int cur_state, int next_state) -{ - DPRINTK("ENTER\n"); - - assert(host->state == cur_state); - if (error) - host->state = HST_ERROR; - else - host->state = next_state; - schedule_work(&host->fsm_task); -} - -static inline void carm_handle_resp(struct carm_host *host, - __le32 ret_handle_le, u32 status) -{ - u32 handle = le32_to_cpu(ret_handle_le); - unsigned int msg_idx; - struct request *rq; - struct carm_request *crq; - blk_status_t error = (status == RMSG_OK) ? 0 : BLK_STS_IOERR; - u8 *mem; - - VPRINTK("ENTER, handle == 0x%x\n", handle); - - if (unlikely(!TAG_VALID(handle))) { - printk(KERN_ERR DRV_NAME "(%s): BUG: invalid tag 0x%x\n", - pci_name(host->pdev), handle); - return; - } - - msg_idx = TAG_DECODE(handle); - VPRINTK("tag == %u\n", msg_idx); - - rq = blk_mq_tag_to_rq(host->tag_set.tags[0], msg_idx); - crq = blk_mq_rq_to_pdu(rq); - - /* fast path */ - if (likely(crq->msg_type == CARM_MSG_READ || - crq->msg_type == CARM_MSG_WRITE)) { - dma_unmap_sg(&host->pdev->dev, &crq->sg[0], crq->n_elem, - carm_rq_dir(rq)); - goto done; - } - - mem = carm_ref_msg(host, msg_idx); - - switch (crq->msg_type) { - case CARM_MSG_IOCTL: { - switch (crq->msg_subtype) { - case CARM_IOC_SCAN_CHAN: - carm_handle_scan_chan(host, crq, mem, error); - goto done; - default: - /* unknown / invalid response */ - goto err_out; - } - break; - } - - case CARM_MSG_MISC: { - switch (crq->msg_subtype) { - case MISC_ALLOC_MEM: - carm_handle_generic(host, crq, error, - HST_ALLOC_BUF, HST_SYNC_TIME); - goto done; - case MISC_SET_TIME: - carm_handle_generic(host, crq, error, - HST_SYNC_TIME, HST_GET_FW_VER); - goto done; - case MISC_GET_FW_VER: { - struct carm_fw_ver *ver = (struct carm_fw_ver *) - (mem + sizeof(struct carm_msg_get_fw_ver)); - if (!error) { - host->fw_ver = le32_to_cpu(ver->version); - host->flags |= (ver->features & FL_FW_VER_MASK); - } - carm_handle_generic(host, crq, error, - HST_GET_FW_VER, HST_PORT_SCAN); - goto done; - } - default: - /* unknown / invalid response */ - goto err_out; - } - break; - } - - case CARM_MSG_ARRAY: { - switch (crq->msg_subtype) { - case CARM_ARRAY_INFO: - carm_handle_array_info(host, crq, mem, error); - break; - default: - /* unknown / invalid response */ - goto err_out; - } - break; - } - - default: - /* unknown / invalid response */ - goto err_out; - } - - return; - -err_out: - printk(KERN_WARNING DRV_NAME "(%s): BUG: unhandled message type %d/%d\n", - pci_name(host->pdev), crq->msg_type, crq->msg_subtype); - error = BLK_STS_IOERR; -done: - host->hw_sg_used -= crq->n_elem; - blk_mq_end_request(blk_mq_rq_from_pdu(crq), error); - - if (host->hw_sg_used <= CARM_SG_LOW_WATER) - carm_round_robin(host); -} - -static inline void carm_handle_responses(struct carm_host *host) -{ - void __iomem *mmio = host->mmio; - struct carm_response *resp = (struct carm_response *) host->shm; - unsigned int work = 0; - unsigned int idx = host->resp_idx % RMSG_Q_LEN; - - while (1) { - u32 status = le32_to_cpu(resp[idx].status); - - if (status == 0xffffffff) { - VPRINTK("ending response on index %u\n", idx); - writel(idx << 3, mmio + CARM_RESP_IDX); - break; - } - - /* response to a message we sent */ - else if ((status & (1 << 31)) == 0) { - VPRINTK("handling msg response on index %u\n", idx); - carm_handle_resp(host, resp[idx].ret_handle, status); - resp[idx].status = cpu_to_le32(0xffffffff); - } - - /* asynchronous events the hardware throws our way */ - else if ((status & 0xff000000) == (1 << 31)) { - u8 *evt_type_ptr = (u8 *) &resp[idx]; - u8 evt_type = *evt_type_ptr; - printk(KERN_WARNING DRV_NAME "(%s): unhandled event type %d\n", - pci_name(host->pdev), (int) evt_type); - resp[idx].status = cpu_to_le32(0xffffffff); - } - - idx = NEXT_RESP(idx); - work++; - } - - VPRINTK("EXIT, work==%u\n", work); - host->resp_idx += work; -} - -static irqreturn_t carm_interrupt(int irq, void *__host) -{ - struct carm_host *host = __host; - void __iomem *mmio; - u32 mask; - int handled = 0; - unsigned long flags; - - if (!host) { - VPRINTK("no host\n"); - return IRQ_NONE; - } - - spin_lock_irqsave(&host->lock, flags); - - mmio = host->mmio; - - /* reading should also clear interrupts */ - mask = readl(mmio + CARM_INT_STAT); - - if (mask == 0 || mask == 0xffffffff) { - VPRINTK("no work, mask == 0x%x\n", mask); - goto out; - } - - if (mask & INT_ACK_MASK) - writel(mask, mmio + CARM_INT_STAT); - - if (unlikely(host->state == HST_INVALID)) { - VPRINTK("not initialized yet, mask = 0x%x\n", mask); - goto out; - } - - if (mask & CARM_HAVE_RESP) { - handled = 1; - carm_handle_responses(host); - } - -out: - spin_unlock_irqrestore(&host->lock, flags); - VPRINTK("EXIT\n"); - return IRQ_RETVAL(handled); -} - -static void carm_fsm_task (struct work_struct *work) -{ - struct carm_host *host = - container_of(work, struct carm_host, fsm_task); - unsigned long flags; - unsigned int state; - int rc, i, next_dev; - int reschedule = 0; - int new_state = HST_INVALID; - - spin_lock_irqsave(&host->lock, flags); - state = host->state; - spin_unlock_irqrestore(&host->lock, flags); - - DPRINTK("ENTER, state == %s\n", state_name[state]); - - switch (state) { - case HST_PROBE_START: - new_state = HST_ALLOC_BUF; - reschedule = 1; - break; - - case HST_ALLOC_BUF: - rc = carm_send_special(host, carm_fill_alloc_buf); - if (rc) { - new_state = HST_ERROR; - reschedule = 1; - } - break; - - case HST_SYNC_TIME: - rc = carm_send_special(host, carm_fill_sync_time); - if (rc) { - new_state = HST_ERROR; - reschedule = 1; - } - break; - - case HST_GET_FW_VER: - rc = carm_send_special(host, carm_fill_get_fw_ver); - if (rc) { - new_state = HST_ERROR; - reschedule = 1; - } - break; - - case HST_PORT_SCAN: - rc = carm_send_special(host, carm_fill_scan_channels); - if (rc) { - new_state = HST_ERROR; - reschedule = 1; - } - break; - - case HST_DEV_SCAN_START: - host->cur_scan_dev = -1; - new_state = HST_DEV_SCAN; - reschedule = 1; - break; - - case HST_DEV_SCAN: - next_dev = -1; - for (i = host->cur_scan_dev + 1; i < CARM_MAX_PORTS; i++) - if (host->dev_present & (1 << i)) { - next_dev = i; - break; - } - - if (next_dev >= 0) { - host->cur_scan_dev = next_dev; - rc = carm_array_info(host, next_dev); - if (rc) { - new_state = HST_ERROR; - reschedule = 1; - } - } else { - new_state = HST_DEV_ACTIVATE; - reschedule = 1; - } - break; - - case HST_DEV_ACTIVATE: { - int activated = 0; - for (i = 0; i < CARM_MAX_PORTS; i++) - if (host->dev_active & (1 << i)) { - struct carm_port *port = &host->port[i]; - struct gendisk *disk = port->disk; - - set_capacity(disk, port->capacity); - host->probe_err = add_disk(disk); - if (!host->probe_err) - activated++; - else - break; - } - - printk(KERN_INFO DRV_NAME "(%s): %d ports activated\n", - pci_name(host->pdev), activated); - - new_state = HST_PROBE_FINISHED; - reschedule = 1; - break; - } - case HST_PROBE_FINISHED: - complete(&host->probe_comp); - break; - case HST_ERROR: - /* FIXME: TODO */ - break; - - default: - /* should never occur */ - printk(KERN_ERR PFX "BUG: unknown state %d\n", state); - assert(0); - break; - } - - if (new_state != HST_INVALID) { - spin_lock_irqsave(&host->lock, flags); - host->state = new_state; - spin_unlock_irqrestore(&host->lock, flags); - } - if (reschedule) - schedule_work(&host->fsm_task); -} - -static int carm_init_wait(void __iomem *mmio, u32 bits, unsigned int test_bit) -{ - unsigned int i; - - for (i = 0; i < 50000; i++) { - u32 tmp = readl(mmio + CARM_LMUC); - udelay(100); - - if (test_bit) { - if ((tmp & bits) == bits) - return 0; - } else { - if ((tmp & bits) == 0) - return 0; - } - - cond_resched(); - } - - printk(KERN_ERR PFX "carm_init_wait timeout, bits == 0x%x, test_bit == %s\n", - bits, test_bit ? "yes" : "no"); - return -EBUSY; -} - -static void carm_init_responses(struct carm_host *host) -{ - void __iomem *mmio = host->mmio; - unsigned int i; - struct carm_response *resp = (struct carm_response *) host->shm; - - for (i = 0; i < RMSG_Q_LEN; i++) - resp[i].status = cpu_to_le32(0xffffffff); - - writel(0, mmio + CARM_RESP_IDX); -} - -static int carm_init_host(struct carm_host *host) -{ - void __iomem *mmio = host->mmio; - u32 tmp; - u8 tmp8; - int rc; - - DPRINTK("ENTER\n"); - - writel(0, mmio + CARM_INT_MASK); - - tmp8 = readb(mmio + CARM_INITC); - if (tmp8 & 0x01) { - tmp8 &= ~0x01; - writeb(tmp8, mmio + CARM_INITC); - readb(mmio + CARM_INITC); /* flush */ - - DPRINTK("snooze...\n"); - msleep(5000); - } - - tmp = readl(mmio + CARM_HMUC); - if (tmp & CARM_CME) { - DPRINTK("CME bit present, waiting\n"); - rc = carm_init_wait(mmio, CARM_CME, 1); - if (rc) { - DPRINTK("EXIT, carm_init_wait 1 failed\n"); - return rc; - } - } - if (tmp & CARM_RME) { - DPRINTK("RME bit present, waiting\n"); - rc = carm_init_wait(mmio, CARM_RME, 1); - if (rc) { - DPRINTK("EXIT, carm_init_wait 2 failed\n"); - return rc; - } - } - - tmp &= ~(CARM_RME | CARM_CME); - writel(tmp, mmio + CARM_HMUC); - readl(mmio + CARM_HMUC); /* flush */ - - rc = carm_init_wait(mmio, CARM_RME | CARM_CME, 0); - if (rc) { - DPRINTK("EXIT, carm_init_wait 3 failed\n"); - return rc; - } - - carm_init_buckets(mmio); - - writel(host->shm_dma & 0xffffffff, mmio + RBUF_ADDR_LO); - writel((host->shm_dma >> 16) >> 16, mmio + RBUF_ADDR_HI); - writel(RBUF_LEN, mmio + RBUF_BYTE_SZ); - - tmp = readl(mmio + CARM_HMUC); - tmp |= (CARM_RME | CARM_CME | CARM_WZBC); - writel(tmp, mmio + CARM_HMUC); - readl(mmio + CARM_HMUC); /* flush */ - - rc = carm_init_wait(mmio, CARM_RME | CARM_CME, 1); - if (rc) { - DPRINTK("EXIT, carm_init_wait 4 failed\n"); - return rc; - } - - writel(0, mmio + CARM_HMPHA); - writel(INT_DEF_MASK, mmio + CARM_INT_MASK); - - carm_init_responses(host); - - /* start initialization, probing state machine */ - spin_lock_irq(&host->lock); - assert(host->state == HST_INVALID); - host->state = HST_PROBE_START; - spin_unlock_irq(&host->lock); - schedule_work(&host->fsm_task); - - DPRINTK("EXIT\n"); - return 0; -} - -static const struct blk_mq_ops carm_mq_ops = { - .queue_rq = carm_queue_rq, -}; - -static int carm_init_disk(struct carm_host *host, unsigned int port_no) -{ - struct carm_port *port = &host->port[port_no]; - struct gendisk *disk; - - port->host = host; - port->port_no = port_no; - - disk = blk_mq_alloc_disk(&host->tag_set, port); - if (IS_ERR(disk)) - return PTR_ERR(disk); - - port->disk = disk; - sprintf(disk->disk_name, DRV_NAME "/%u", - (unsigned int)host->id * CARM_MAX_PORTS + port_no); - disk->major = host->major; - disk->first_minor = port_no * CARM_MINORS_PER_MAJOR; - disk->minors = CARM_MINORS_PER_MAJOR; - disk->fops = &carm_bd_ops; - disk->private_data = port; - - blk_queue_max_segments(disk->queue, CARM_MAX_REQ_SG); - blk_queue_segment_boundary(disk->queue, CARM_SG_BOUNDARY); - return 0; -} - -static void carm_free_disk(struct carm_host *host, unsigned int port_no) -{ - struct carm_port *port = &host->port[port_no]; - struct gendisk *disk = port->disk; - - if (!disk) - return; - - if (host->state > HST_DEV_ACTIVATE) - del_gendisk(disk); - put_disk(disk); -} - -static int carm_init_shm(struct carm_host *host) -{ - host->shm = dma_alloc_coherent(&host->pdev->dev, CARM_SHM_SIZE, - &host->shm_dma, GFP_KERNEL); - if (!host->shm) - return -ENOMEM; - - host->msg_base = host->shm + RBUF_LEN; - host->msg_dma = host->shm_dma + RBUF_LEN; - - memset(host->shm, 0xff, RBUF_LEN); - memset(host->msg_base, 0, PDC_SHM_SIZE - RBUF_LEN); - - return 0; -} - -static int carm_init_one (struct pci_dev *pdev, const struct pci_device_id *ent) -{ - struct carm_host *host; - int rc; - struct request_queue *q; - unsigned int i; - - printk_once(KERN_DEBUG DRV_NAME " version " DRV_VERSION "\n"); - - rc = pci_enable_device(pdev); - if (rc) - return rc; - - rc = pci_request_regions(pdev, DRV_NAME); - if (rc) - goto err_out; - - rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); - if (rc) { - printk(KERN_ERR DRV_NAME "(%s): DMA mask failure\n", - pci_name(pdev)); - goto err_out_regions; - } - - host = kzalloc(sizeof(*host), GFP_KERNEL); - if (!host) { - rc = -ENOMEM; - goto err_out_regions; - } - - host->pdev = pdev; - spin_lock_init(&host->lock); - INIT_WORK(&host->fsm_task, carm_fsm_task); - init_completion(&host->probe_comp); - - host->mmio = ioremap(pci_resource_start(pdev, 0), - pci_resource_len(pdev, 0)); - if (!host->mmio) { - printk(KERN_ERR DRV_NAME "(%s): MMIO alloc failure\n", - pci_name(pdev)); - rc = -ENOMEM; - goto err_out_kfree; - } - - rc = carm_init_shm(host); - if (rc) { - printk(KERN_ERR DRV_NAME "(%s): DMA SHM alloc failure\n", - pci_name(pdev)); - goto err_out_iounmap; - } - - memset(&host->tag_set, 0, sizeof(host->tag_set)); - host->tag_set.ops = &carm_mq_ops; - host->tag_set.cmd_size = sizeof(struct carm_request); - host->tag_set.nr_hw_queues = 1; - host->tag_set.nr_maps = 1; - host->tag_set.queue_depth = max_queue; - host->tag_set.numa_node = NUMA_NO_NODE; - host->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; - - rc = blk_mq_alloc_tag_set(&host->tag_set); - if (rc) - goto err_out_dma_free; - - q = blk_mq_init_queue(&host->tag_set); - if (IS_ERR(q)) { - rc = PTR_ERR(q); - blk_mq_free_tag_set(&host->tag_set); - goto err_out_dma_free; - } - - host->oob_q = q; - q->queuedata = host; - - /* - * Figure out which major to use: 160, 161, or dynamic - */ - if (!test_and_set_bit(0, &carm_major_alloc)) - host->major = 160; - else if (!test_and_set_bit(1, &carm_major_alloc)) - host->major = 161; - else - host->flags |= FL_DYN_MAJOR; - - host->id = carm_host_id; - sprintf(host->name, DRV_NAME "%d", carm_host_id); - - rc = register_blkdev(host->major, host->name); - if (rc < 0) - goto err_out_free_majors; - if (host->flags & FL_DYN_MAJOR) - host->major = rc; - - for (i = 0; i < CARM_MAX_PORTS; i++) { - rc = carm_init_disk(host, i); - if (rc) - goto err_out_blkdev_disks; - } - - pci_set_master(pdev); - - rc = request_irq(pdev->irq, carm_interrupt, IRQF_SHARED, DRV_NAME, host); - if (rc) { - printk(KERN_ERR DRV_NAME "(%s): irq alloc failure\n", - pci_name(pdev)); - goto err_out_blkdev_disks; - } - - rc = carm_init_host(host); - if (rc) - goto err_out_free_irq; - - DPRINTK("waiting for probe_comp\n"); - host->probe_err = -ENODEV; - wait_for_completion(&host->probe_comp); - if (host->probe_err) { - rc = host->probe_err; - goto err_out_free_irq; - } - - printk(KERN_INFO "%s: pci %s, ports %d, io %llx, irq %u, major %d\n", - host->name, pci_name(pdev), (int) CARM_MAX_PORTS, - (unsigned long long)pci_resource_start(pdev, 0), - pdev->irq, host->major); - - carm_host_id++; - pci_set_drvdata(pdev, host); - return 0; - -err_out_free_irq: - free_irq(pdev->irq, host); -err_out_blkdev_disks: - for (i = 0; i < CARM_MAX_PORTS; i++) - carm_free_disk(host, i); - unregister_blkdev(host->major, host->name); -err_out_free_majors: - if (host->major == 160) - clear_bit(0, &carm_major_alloc); - else if (host->major == 161) - clear_bit(1, &carm_major_alloc); - blk_mq_destroy_queue(host->oob_q); - blk_mq_free_tag_set(&host->tag_set); -err_out_dma_free: - dma_free_coherent(&pdev->dev, CARM_SHM_SIZE, host->shm, host->shm_dma); -err_out_iounmap: - iounmap(host->mmio); -err_out_kfree: - kfree(host); -err_out_regions: - pci_release_regions(pdev); -err_out: - pci_disable_device(pdev); - return rc; -} - -static void carm_remove_one (struct pci_dev *pdev) -{ - struct carm_host *host = pci_get_drvdata(pdev); - unsigned int i; - - if (!host) { - printk(KERN_ERR PFX "BUG: no host data for PCI(%s)\n", - pci_name(pdev)); - return; - } - - free_irq(pdev->irq, host); - for (i = 0; i < CARM_MAX_PORTS; i++) - carm_free_disk(host, i); - unregister_blkdev(host->major, host->name); - if (host->major == 160) - clear_bit(0, &carm_major_alloc); - else if (host->major == 161) - clear_bit(1, &carm_major_alloc); - blk_mq_destroy_queue(host->oob_q); - blk_mq_free_tag_set(&host->tag_set); - dma_free_coherent(&pdev->dev, CARM_SHM_SIZE, host->shm, host->shm_dma); - iounmap(host->mmio); - kfree(host); - pci_release_regions(pdev); - pci_disable_device(pdev); -} - -module_pci_driver(carm_driver); diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 3f1906965ac8..2b7d1db5c4a7 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -47,7 +47,12 @@ #define UBLK_MINORS (1U << MINORBITS) /* All UBLK_F_* have to be included into UBLK_F_ALL */ -#define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_URING_CMD_COMP_IN_TASK) +#define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY \ + | UBLK_F_URING_CMD_COMP_IN_TASK \ + | UBLK_F_NEED_GET_DATA) + +/* All UBLK_PARAM_TYPE_* should be included here */ +#define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD) struct ublk_rq_data { struct callback_head work; @@ -86,6 +91,15 @@ struct ublk_uring_cmd_pdu { */ #define UBLK_IO_FLAG_ABORTED 0x04 +/* + * UBLK_IO_FLAG_NEED_GET_DATA is set because IO command requires + * get data buffer address from ublksrv. + * + * Then, bio data could be copied into this data buffer for a WRITE request + * after the IO command is issued again and UBLK_IO_FLAG_NEED_GET_DATA is unset. + */ +#define UBLK_IO_FLAG_NEED_GET_DATA 0x08 + struct ublk_io { /* userspace buffer address from io cmd */ __u64 addr; @@ -119,7 +133,6 @@ struct ublk_device { char *__queues; unsigned short queue_size; - unsigned short bs_shift; struct ublksrv_ctrl_dev_info dev_info; struct blk_mq_tag_set tag_set; @@ -137,6 +150,8 @@ struct ublk_device { spinlock_t mm_lock; struct mm_struct *mm; + struct ublk_params params; + struct completion completion; unsigned int nr_queues_ready; atomic_t nr_aborted_queues; @@ -149,6 +164,12 @@ struct ublk_device { struct work_struct stop_work; }; +/* header of ublk_params */ +struct ublk_params_header { + __u32 len; + __u32 types; +}; + static dev_t ublk_chr_devt; static struct class *ublk_chr_class; @@ -160,6 +181,90 @@ static DEFINE_MUTEX(ublk_ctl_mutex); static struct miscdevice ublk_misc; +static void ublk_dev_param_basic_apply(struct ublk_device *ub) +{ + struct request_queue *q = ub->ub_disk->queue; + const struct ublk_param_basic *p = &ub->params.basic; + + blk_queue_logical_block_size(q, 1 << p->logical_bs_shift); + blk_queue_physical_block_size(q, 1 << p->physical_bs_shift); + blk_queue_io_min(q, 1 << p->io_min_shift); + blk_queue_io_opt(q, 1 << p->io_opt_shift); + + blk_queue_write_cache(q, p->attrs & UBLK_ATTR_VOLATILE_CACHE, + p->attrs & UBLK_ATTR_FUA); + if (p->attrs & UBLK_ATTR_ROTATIONAL) + blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); + else + blk_queue_flag_set(QUEUE_FLAG_NONROT, q); + + blk_queue_max_hw_sectors(q, p->max_sectors); + blk_queue_chunk_sectors(q, p->chunk_sectors); + blk_queue_virt_boundary(q, p->virt_boundary_mask); + + if (p->attrs & UBLK_ATTR_READ_ONLY) + set_disk_ro(ub->ub_disk, true); + + set_capacity(ub->ub_disk, p->dev_sectors); +} + +static void ublk_dev_param_discard_apply(struct ublk_device *ub) +{ + struct request_queue *q = ub->ub_disk->queue; + const struct ublk_param_discard *p = &ub->params.discard; + + q->limits.discard_alignment = p->discard_alignment; + q->limits.discard_granularity = p->discard_granularity; + blk_queue_max_discard_sectors(q, p->max_discard_sectors); + blk_queue_max_write_zeroes_sectors(q, + p->max_write_zeroes_sectors); + blk_queue_max_discard_segments(q, p->max_discard_segments); +} + +static int ublk_validate_params(const struct ublk_device *ub) +{ + /* basic param is the only one which must be set */ + if (ub->params.types & UBLK_PARAM_TYPE_BASIC) { + const struct ublk_param_basic *p = &ub->params.basic; + + if (p->logical_bs_shift > PAGE_SHIFT) + return -EINVAL; + + if (p->logical_bs_shift > p->physical_bs_shift) + return -EINVAL; + + if (p->max_sectors > (ub->dev_info.max_io_buf_bytes >> 9)) + return -EINVAL; + } else + return -EINVAL; + + if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) { + const struct ublk_param_discard *p = &ub->params.discard; + + /* So far, only support single segment discard */ + if (p->max_discard_sectors && p->max_discard_segments != 1) + return -EINVAL; + + if (!p->discard_granularity) + return -EINVAL; + } + + return 0; +} + +static int ublk_apply_params(struct ublk_device *ub) +{ + if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC)) + return -EINVAL; + + ublk_dev_param_basic_apply(ub); + + if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) + ublk_dev_param_discard_apply(ub); + + return 0; +} + static inline bool ublk_can_use_task_work(const struct ublk_queue *ubq) { if (IS_BUILTIN(CONFIG_BLK_DEV_UBLK) && @@ -168,6 +273,13 @@ static inline bool ublk_can_use_task_work(const struct ublk_queue *ubq) return false; } +static inline bool ublk_need_get_data(const struct ublk_queue *ubq) +{ + if (ubq->flags & UBLK_F_NEED_GET_DATA) + return true; + return false; +} + static struct ublk_device *ublk_get_device(struct ublk_device *ub) { if (kobject_get_unless_zero(&ub->cdev_dev.kobj)) @@ -509,6 +621,21 @@ static void __ublk_fail_req(struct ublk_io *io, struct request *req) } } +static void ubq_complete_io_cmd(struct ublk_io *io, int res) +{ + /* mark this cmd owned by ublksrv */ + io->flags |= UBLK_IO_FLAG_OWNED_BY_SRV; + + /* + * clear ACTIVE since we are done with this sqe/cmd slot + * We can only accept io cmd in case of being not active. + */ + io->flags &= ~UBLK_IO_FLAG_ACTIVE; + + /* tell ublksrv one io request is coming */ + io_uring_cmd_done(io->cmd, res, 0); +} + #define UBLK_REQUEUE_DELAY_MS 3 static inline void __ublk_rq_task_work(struct request *req) @@ -531,6 +658,30 @@ static inline void __ublk_rq_task_work(struct request *req) return; } + if (ublk_need_get_data(ubq) && + (req_op(req) == REQ_OP_WRITE || + req_op(req) == REQ_OP_FLUSH)) { + /* + * We have not handled UBLK_IO_NEED_GET_DATA command yet, + * so immepdately pass UBLK_IO_RES_NEED_GET_DATA to ublksrv + * and notify it. + */ + if (!(io->flags & UBLK_IO_FLAG_NEED_GET_DATA)) { + io->flags |= UBLK_IO_FLAG_NEED_GET_DATA; + pr_devel("%s: need get data. op %d, qid %d tag %d io_flags %x\n", + __func__, io->cmd->cmd_op, ubq->q_id, + req->tag, io->flags); + ubq_complete_io_cmd(io, UBLK_IO_RES_NEED_GET_DATA); + return; + } + /* + * We have handled UBLK_IO_NEED_GET_DATA command, + * so clear UBLK_IO_FLAG_NEED_GET_DATA now and just + * do the copy work. + */ + io->flags &= ~UBLK_IO_FLAG_NEED_GET_DATA; + } + mapped_bytes = ublk_map_io(ubq, req, io); /* partially mapped, update io descriptor */ @@ -553,17 +704,7 @@ static inline void __ublk_rq_task_work(struct request *req) mapped_bytes >> 9; } - /* mark this cmd owned by ublksrv */ - io->flags |= UBLK_IO_FLAG_OWNED_BY_SRV; - - /* - * clear ACTIVE since we are done with this sqe/cmd slot - * We can only accept io cmd in case of being not active. - */ - io->flags &= ~UBLK_IO_FLAG_ACTIVE; - - /* tell ublksrv one io request is coming */ - io_uring_cmd_done(io->cmd, UBLK_IO_RES_OK, 0); + ubq_complete_io_cmd(io, UBLK_IO_RES_OK); } static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd) @@ -788,16 +929,27 @@ static void ublk_daemon_monitor_work(struct work_struct *work) UBLK_DAEMON_MONITOR_PERIOD); } +static inline bool ublk_queue_ready(struct ublk_queue *ubq) +{ + return ubq->nr_io_ready == ubq->q_depth; +} + static void ublk_cancel_queue(struct ublk_queue *ubq) { int i; + if (!ublk_queue_ready(ubq)) + return; + for (i = 0; i < ubq->q_depth; i++) { struct ublk_io *io = &ubq->ios[i]; if (io->flags & UBLK_IO_FLAG_ACTIVE) io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0); } + + /* all io commands are canceled */ + ubq->nr_io_ready = 0; } /* Cancel all pending commands, must be called after del_gendisk() returns */ @@ -818,19 +970,14 @@ static void ublk_stop_dev(struct ublk_device *ub) del_gendisk(ub->ub_disk); ub->dev_info.state = UBLK_S_DEV_DEAD; ub->dev_info.ublksrv_pid = -1; - ublk_cancel_dev(ub); put_disk(ub->ub_disk); ub->ub_disk = NULL; unlock: + ublk_cancel_dev(ub); mutex_unlock(&ub->mutex); cancel_delayed_work_sync(&ub->monitor_work); } -static inline bool ublk_queue_ready(struct ublk_queue *ubq) -{ - return ubq->nr_io_ready == ubq->q_depth; -} - /* device can only be started after all IOs are ready */ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) { @@ -846,6 +993,25 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) mutex_unlock(&ub->mutex); } +static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id, + int tag, struct io_uring_cmd *cmd) +{ + struct ublk_queue *ubq = ublk_get_queue(ub, q_id); + struct request *req = blk_mq_tag_to_rq(ub->tag_set.tags[q_id], tag); + + if (ublk_can_use_task_work(ubq)) { + struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); + + /* should not fail since we call it just in ubq->ubq_daemon */ + task_work_add(ubq->ubq_daemon, &data->work, TWA_SIGNAL_NO_IPI); + } else { + struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); + + pdu->req = req; + io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb); + } +} + static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { struct ublksrv_io_cmd *ub_cmd = (struct ublksrv_io_cmd *)cmd->cmd; @@ -884,6 +1050,14 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) goto out; } + /* + * ensure that the user issues UBLK_IO_NEED_GET_DATA + * iff the driver have set the UBLK_IO_FLAG_NEED_GET_DATA. + */ + if ((!!(io->flags & UBLK_IO_FLAG_NEED_GET_DATA)) + ^ (cmd_op == UBLK_IO_NEED_GET_DATA)) + goto out; + switch (cmd_op) { case UBLK_IO_FETCH_REQ: /* UBLK_IO_FETCH_REQ is only allowed before queue is setup */ @@ -917,6 +1091,14 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) io->cmd = cmd; ublk_commit_completion(ub, ub_cmd); break; + case UBLK_IO_NEED_GET_DATA: + if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)) + goto out; + io->addr = ub_cmd->addr; + io->cmd = cmd; + io->flags |= UBLK_IO_FLAG_ACTIVE; + ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag, cmd); + break; default: goto out; } @@ -1083,13 +1265,13 @@ static void ublk_stop_work_fn(struct work_struct *work) ublk_stop_dev(ub); } -/* align maximum I/O size to PAGE_SIZE */ +/* align max io buffer size with PAGE_SIZE */ static void ublk_align_max_io_size(struct ublk_device *ub) { - unsigned int max_rq_bytes = ub->dev_info.rq_max_blocks << ub->bs_shift; + unsigned int max_io_bytes = ub->dev_info.max_io_buf_bytes; - ub->dev_info.rq_max_blocks = - round_down(max_rq_bytes, PAGE_SIZE) >> ub->bs_shift; + ub->dev_info.max_io_buf_bytes = + round_down(max_io_bytes, PAGE_SIZE); } static int ublk_add_tag_set(struct ublk_device *ub) @@ -1132,7 +1314,6 @@ static int ublk_ctrl_start_dev(struct io_uring_cmd *cmd) { struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; int ublksrv_pid = (int)header->data[0]; - unsigned long dev_blocks = header->data[1]; struct ublk_device *ub; struct gendisk *disk; int ret = -EINVAL; @@ -1155,10 +1336,6 @@ static int ublk_ctrl_start_dev(struct io_uring_cmd *cmd) goto out_unlock; } - /* We may get disk size updated */ - if (dev_blocks) - ub->dev_info.dev_blocks = dev_blocks; - disk = blk_mq_alloc_disk(&ub->tag_set, ub); if (IS_ERR(disk)) { ret = PTR_ERR(disk); @@ -1168,27 +1345,28 @@ static int ublk_ctrl_start_dev(struct io_uring_cmd *cmd) disk->fops = &ub_fops; disk->private_data = ub; - blk_queue_logical_block_size(disk->queue, ub->dev_info.block_size); - blk_queue_physical_block_size(disk->queue, ub->dev_info.block_size); - blk_queue_io_min(disk->queue, ub->dev_info.block_size); - blk_queue_max_hw_sectors(disk->queue, - ub->dev_info.rq_max_blocks << (ub->bs_shift - 9)); - disk->queue->limits.discard_granularity = PAGE_SIZE; - blk_queue_max_discard_sectors(disk->queue, UINT_MAX >> 9); - blk_queue_max_write_zeroes_sectors(disk->queue, UINT_MAX >> 9); - - set_capacity(disk, ub->dev_info.dev_blocks << (ub->bs_shift - 9)); - ub->dev_info.ublksrv_pid = ublksrv_pid; ub->ub_disk = disk; + + ret = ublk_apply_params(ub); + if (ret) + goto out_put_disk; + get_device(&ub->cdev_dev); ret = add_disk(disk); if (ret) { - put_disk(disk); - goto out_unlock; + /* + * Has to drop the reference since ->free_disk won't be + * called in case of add_disk failure. + */ + ublk_put_device(ub); + goto out_put_disk; } set_bit(UB_STATE_USED, &ub->state); ub->dev_info.state = UBLK_S_DEV_LIVE; +out_put_disk: + if (ret) + put_disk(disk); out_unlock: mutex_unlock(&ub->mutex); ublk_put_device(ub); @@ -1250,9 +1428,8 @@ static inline void ublk_dump_dev_info(struct ublksrv_ctrl_dev_info *info) { pr_devel("%s: dev id %d flags %llx\n", __func__, info->dev_id, info->flags); - pr_devel("\t nr_hw_queues %d queue_depth %d block size %d dev_capacity %lld\n", - info->nr_hw_queues, info->queue_depth, - info->block_size, info->dev_blocks); + pr_devel("\t nr_hw_queues %d queue_depth %d\n", + info->nr_hw_queues, info->queue_depth); } static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) @@ -1312,7 +1489,6 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) /* We are not ready to support zero copy */ ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY; - ub->bs_shift = ilog2(ub->dev_info.block_size); ub->dev_info.nr_hw_queues = min_t(unsigned int, ub->dev_info.nr_hw_queues, nr_cpu_ids); ublk_align_max_io_size(ub); @@ -1436,6 +1612,82 @@ static int ublk_ctrl_get_dev_info(struct io_uring_cmd *cmd) return ret; } +static int ublk_ctrl_get_params(struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + void __user *argp = (void __user *)(unsigned long)header->addr; + struct ublk_params_header ph; + struct ublk_device *ub; + int ret; + + if (header->len <= sizeof(ph) || !header->addr) + return -EINVAL; + + if (copy_from_user(&ph, argp, sizeof(ph))) + return -EFAULT; + + if (ph.len > header->len || !ph.len) + return -EINVAL; + + if (ph.len > sizeof(struct ublk_params)) + ph.len = sizeof(struct ublk_params); + + ub = ublk_get_device_from_id(header->dev_id); + if (!ub) + return -EINVAL; + + mutex_lock(&ub->mutex); + if (copy_to_user(argp, &ub->params, ph.len)) + ret = -EFAULT; + else + ret = 0; + mutex_unlock(&ub->mutex); + + ublk_put_device(ub); + return ret; +} + +static int ublk_ctrl_set_params(struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + void __user *argp = (void __user *)(unsigned long)header->addr; + struct ublk_params_header ph; + struct ublk_device *ub; + int ret = -EFAULT; + + if (header->len <= sizeof(ph) || !header->addr) + return -EINVAL; + + if (copy_from_user(&ph, argp, sizeof(ph))) + return -EFAULT; + + if (ph.len > header->len || !ph.len || !ph.types) + return -EINVAL; + + if (ph.len > sizeof(struct ublk_params)) + ph.len = sizeof(struct ublk_params); + + ub = ublk_get_device_from_id(header->dev_id); + if (!ub) + return -EINVAL; + + /* parameters can only be changed when device isn't live */ + mutex_lock(&ub->mutex); + if (ub->dev_info.state == UBLK_S_DEV_LIVE) { + ret = -EACCES; + } else if (copy_from_user(&ub->params, argp, ph.len)) { + ret = -EFAULT; + } else { + /* clear all we don't support yet */ + ub->params.types &= UBLK_PARAM_TYPE_ALL; + ret = ublk_validate_params(ub); + } + mutex_unlock(&ub->mutex); + ublk_put_device(ub); + + return ret; +} + static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { @@ -1471,6 +1723,12 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, case UBLK_CMD_GET_QUEUE_AFFINITY: ret = ublk_ctrl_get_queue_affinity(cmd); break; + case UBLK_CMD_GET_PARAMS: + ret = ublk_ctrl_get_params(cmd); + break; + case UBLK_CMD_SET_PARAMS: + ret = ublk_ctrl_set_params(cmd); + break; default: break; } diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig index cf3e8096942a..529c9d04e9a4 100644 --- a/drivers/md/bcache/Kconfig +++ b/drivers/md/bcache/Kconfig @@ -29,7 +29,7 @@ config BCACHE_CLOSURES_DEBUG operations that get stuck. config BCACHE_ASYNC_REGISTRATION - bool "Asynchronous device registration (EXPERIMENTAL)" + bool "Asynchronous device registration" depends on BCACHE help Add a sysfs file /sys/fs/bcache/register_async. Writing registering diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 1ec17c32867f..c640be453313 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3728,6 +3728,7 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv, if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) { if (mddev->sync_thread) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); } } else if (decipher_sync_action(mddev, mddev->recovery) != st_idle) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 99642f69bfa7..28bd4a35b86b 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1016,7 +1016,7 @@ static void dm_wq_requeue_work(struct work_struct *work) while (io) { struct dm_io *next = io->next; - dm_io_rewind(io, &md->queue->bio_split); + dm_io_rewind(io, &md->disk->bio_split); io->next = NULL; __dm_io_complete(io, false); @@ -1181,7 +1181,7 @@ static sector_t max_io_len(struct dm_target *ti, sector_t sector) * Does the target need to split IO even further? * - varied (per target) IO splitting is a tenet of DM; this * explains why stacked chunk_sectors based splitting via - * blk_queue_split() isn't possible here. + * bio_split_to_limits() isn't possible here. */ if (!ti->max_io_len) return len; @@ -1751,10 +1751,10 @@ static void dm_split_and_process_bio(struct mapped_device *md, is_abnormal = is_abnormal_io(bio); if (unlikely(is_abnormal)) { /* - * Use blk_queue_split() for abnormal IO (e.g. discard, etc) + * Use bio_split_to_limits() for abnormal IO (e.g. discard, etc) * otherwise associated queue_limits won't be imposed. */ - blk_queue_split(&bio); + bio = bio_split_to_limits(bio); } init_clone_info(&ci, md, map, bio, is_abnormal); diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index 2cf973722f59..91836e6de326 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -125,7 +125,6 @@ static void __init md_setup_drive(struct md_setup_args *args) char *devname = args->device_names; dev_t devices[MD_SB_DISKS + 1], mdev; struct mdu_array_info_s ainfo = { }; - struct block_device *bdev; struct mddev *mddev; int err = 0, i; char name[16]; @@ -169,24 +168,16 @@ static void __init md_setup_drive(struct md_setup_args *args) pr_info("md: Loading %s: %s\n", name, args->device_names); - bdev = blkdev_get_by_dev(mdev, FMODE_READ, NULL); - if (IS_ERR(bdev)) { - pr_err("md: open failed - cannot start array %s\n", name); + mddev = md_alloc(mdev, name); + if (IS_ERR(mddev)) { + pr_err("md: md_alloc failed - cannot start array %s\n", name); return; } - err = -EIO; - if (WARN(bdev->bd_disk->fops != &md_fops, - "Opening block device %x resulted in non-md device\n", - mdev)) - goto out_blkdev_put; - - mddev = bdev->bd_disk->private_data; - err = mddev_lock(mddev); if (err) { pr_err("md: failed to lock array %s\n", name); - goto out_blkdev_put; + goto out_mddev_put; } if (!list_empty(&mddev->disks) || mddev->raid_disks) { @@ -230,8 +221,8 @@ static void __init md_setup_drive(struct md_setup_args *args) pr_warn("md: starting %s failed\n", name); out_unlock: mddev_unlock(mddev); -out_blkdev_put: - blkdev_put(bdev, FMODE_READ); +out_mddev_put: + mddev_put(mddev); } static int __init raid_setup(char *str) diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 37cbcce3cc66..742b2349fea3 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -40,7 +40,7 @@ struct resync_info { /* Lock the send communication. This is done through * bit manipulation as opposed to a mutex in order to - * accomodate lock and hold. See next comment. + * accommodate lock and hold. See next comment. */ #define MD_CLUSTER_SEND_LOCK 4 /* If cluster operations (such as adding a disk) must lock the @@ -689,7 +689,7 @@ static int lock_comm(struct md_cluster_info *cinfo, bool mddev_locked) /* * If resync thread run after raid1d thread, then process_metadata_update * could not continue if raid1d held reconfig_mutex (and raid1d is blocked - * since another node already got EX on Token and waitting the EX of Ack), + * since another node already got EX on Token and waiting the EX of Ack), * so let resync wake up thread in case flag is set. */ if (mddev_locked && !test_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, diff --git a/drivers/md/md.c b/drivers/md/md.c index 4df78e30b76a..afaf36b2f6ab 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -368,28 +368,6 @@ EXPORT_SYMBOL_GPL(md_new_event); static LIST_HEAD(all_mddevs); static DEFINE_SPINLOCK(all_mddevs_lock); -/* - * iterates through all used mddevs in the system. - * We take care to grab the all_mddevs_lock whenever navigating - * the list, and to always hold a refcount when unlocked. - * Any code which breaks out of this loop while own - * a reference to the current mddev and must mddev_put it. - */ -#define for_each_mddev(_mddev,_tmp) \ - \ - for (({ spin_lock(&all_mddevs_lock); \ - _tmp = all_mddevs.next; \ - _mddev = NULL;}); \ - ({ if (_tmp != &all_mddevs) \ - mddev_get(list_entry(_tmp, struct mddev, all_mddevs));\ - spin_unlock(&all_mddevs_lock); \ - if (_mddev) mddev_put(_mddev); \ - _mddev = list_entry(_tmp, struct mddev, all_mddevs); \ - _tmp != &all_mddevs;}); \ - ({ spin_lock(&all_mddevs_lock); \ - _tmp = _tmp->next;}) \ - ) - /* Rather than calling directly into the personality make_request function, * IO requests come here first so that we can check if the device is * being suspended pending a reconfiguration. @@ -464,7 +442,7 @@ static void md_submit_bio(struct bio *bio) return; } - blk_queue_split(&bio); + bio = bio_split_to_limits(bio); if (mddev->ro == 1 && unlikely(rw == WRITE)) { if (bio_sectors(bio) != 0) @@ -647,13 +625,17 @@ EXPORT_SYMBOL(md_flush_request); static inline struct mddev *mddev_get(struct mddev *mddev) { + lockdep_assert_held(&all_mddevs_lock); + + if (test_bit(MD_DELETED, &mddev->flags)) + return NULL; atomic_inc(&mddev->active); return mddev; } static void mddev_delayed_delete(struct work_struct *ws); -static void mddev_put(struct mddev *mddev) +void mddev_put(struct mddev *mddev) { if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock)) return; @@ -661,7 +643,7 @@ static void mddev_put(struct mddev *mddev) mddev->ctime == 0 && !mddev->hold_active) { /* Array is not configured at all, and not held active, * so destroy it */ - list_del_init(&mddev->all_mddevs); + set_bit(MD_DELETED, &mddev->flags); /* * Call queue_work inside the spinlock so that @@ -678,7 +660,6 @@ static void md_safemode_timeout(struct timer_list *t); void mddev_init(struct mddev *mddev) { - kobject_init(&mddev->kobj, &md_ktype); mutex_init(&mddev->open_mutex); mutex_init(&mddev->reconfig_mutex); mutex_init(&mddev->bitmap_info.mutex); @@ -733,22 +714,6 @@ static dev_t mddev_alloc_unit(void) return dev; } -static struct mddev *mddev_find(dev_t unit) -{ - struct mddev *mddev; - - if (MAJOR(unit) != MD_MAJOR) - unit &= ~((1 << MdpMinorShift) - 1); - - spin_lock(&all_mddevs_lock); - mddev = mddev_find_locked(unit); - if (mddev) - mddev_get(mddev); - spin_unlock(&all_mddevs_lock); - - return mddev; -} - static struct mddev *mddev_alloc(dev_t unit) { struct mddev *new; @@ -791,6 +756,15 @@ static struct mddev *mddev_alloc(dev_t unit) return ERR_PTR(error); } +static void mddev_free(struct mddev *mddev) +{ + spin_lock(&all_mddevs_lock); + list_del(&mddev->all_mddevs); + spin_unlock(&all_mddevs_lock); + + kfree(mddev); +} + static const struct attribute_group md_redundancy_group; void mddev_unlock(struct mddev *mddev) @@ -3335,14 +3309,35 @@ rdev_size_show(struct md_rdev *rdev, char *page) return sprintf(page, "%llu\n", (unsigned long long)rdev->sectors / 2); } -static int overlaps(sector_t s1, sector_t l1, sector_t s2, sector_t l2) +static int md_rdevs_overlap(struct md_rdev *a, struct md_rdev *b) { /* check if two start/length pairs overlap */ - if (s1+l1 <= s2) - return 0; - if (s2+l2 <= s1) - return 0; - return 1; + if (a->data_offset + a->sectors <= b->data_offset) + return false; + if (b->data_offset + b->sectors <= a->data_offset) + return false; + return true; +} + +static bool md_rdev_overlaps(struct md_rdev *rdev) +{ + struct mddev *mddev; + struct md_rdev *rdev2; + + spin_lock(&all_mddevs_lock); + list_for_each_entry(mddev, &all_mddevs, all_mddevs) { + if (test_bit(MD_DELETED, &mddev->flags)) + continue; + rdev_for_each(rdev2, mddev) { + if (rdev != rdev2 && rdev->bdev == rdev2->bdev && + md_rdevs_overlap(rdev, rdev2)) { + spin_unlock(&all_mddevs_lock); + return true; + } + } + } + spin_unlock(&all_mddevs_lock); + return false; } static int strict_blocks_to_sectors(const char *buf, sector_t *sectors) @@ -3394,46 +3389,21 @@ rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len) return -EINVAL; /* component must fit device */ rdev->sectors = sectors; - if (sectors > oldsectors && my_mddev->external) { - /* Need to check that all other rdevs with the same - * ->bdev do not overlap. 'rcu' is sufficient to walk - * the rdev lists safely. - * This check does not provide a hard guarantee, it - * just helps avoid dangerous mistakes. + + /* + * Check that all other rdevs with the same bdev do not overlap. This + * check does not provide a hard guarantee, it just helps avoid + * dangerous mistakes. + */ + if (sectors > oldsectors && my_mddev->external && + md_rdev_overlaps(rdev)) { + /* + * Someone else could have slipped in a size change here, but + * doing so is just silly. We put oldsectors back because we + * know it is safe, and trust userspace not to race with itself. */ - struct mddev *mddev; - int overlap = 0; - struct list_head *tmp; - - rcu_read_lock(); - for_each_mddev(mddev, tmp) { - struct md_rdev *rdev2; - - rdev_for_each(rdev2, mddev) - if (rdev->bdev == rdev2->bdev && - rdev != rdev2 && - overlaps(rdev->data_offset, rdev->sectors, - rdev2->data_offset, - rdev2->sectors)) { - overlap = 1; - break; - } - if (overlap) { - mddev_put(mddev); - break; - } - } - rcu_read_unlock(); - if (overlap) { - /* Someone else could have slipped in a size - * change here, but doing so is just silly. - * We put oldsectors back because we *know* it is - * safe, and trust userspace not to race with - * itself - */ - rdev->sectors = oldsectors; - return -EBUSY; - } + rdev->sectors = oldsectors; + return -EBUSY; } return len; } @@ -4830,6 +4800,19 @@ action_store(struct mddev *mddev, const char *page, size_t len) if (work_pending(&mddev->del_work)) flush_workqueue(md_misc_wq); if (mddev->sync_thread) { + sector_t save_rp = mddev->reshape_position; + + mddev_unlock(mddev); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(&mddev->sync_thread); + mddev_lock_nointr(mddev); + /* + * set RECOVERY_INTR again and restore reshape + * position in case others changed them after + * got lock, eg, reshape_position_store and + * md_check_recovery. + */ + mddev->reshape_position = save_rp; set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_reap_sync_thread(mddev); } @@ -5001,7 +4984,7 @@ static ssize_t sync_speed_show(struct mddev *mddev, char *page) { unsigned long resync, dt, db; - if (mddev->curr_resync == 0) + if (mddev->curr_resync == MD_RESYNC_NONE) return sprintf(page, "none\n"); resync = mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active); dt = (jiffies - mddev->resync_mark) / HZ; @@ -5020,8 +5003,8 @@ sync_completed_show(struct mddev *mddev, char *page) if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return sprintf(page, "none\n"); - if (mddev->curr_resync == 1 || - mddev->curr_resync == 2) + if (mddev->curr_resync == MD_RESYNC_YIELDED || + mddev->curr_resync == MD_RESYNC_DELAYED) return sprintf(page, "delayed\n"); if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) || @@ -5532,11 +5515,10 @@ md_attr_show(struct kobject *kobj, struct attribute *attr, char *page) if (!entry->show) return -EIO; spin_lock(&all_mddevs_lock); - if (list_empty(&mddev->all_mddevs)) { + if (!mddev_get(mddev)) { spin_unlock(&all_mddevs_lock); return -EBUSY; } - mddev_get(mddev); spin_unlock(&all_mddevs_lock); rv = entry->show(mddev, page); @@ -5557,18 +5539,17 @@ md_attr_store(struct kobject *kobj, struct attribute *attr, if (!capable(CAP_SYS_ADMIN)) return -EACCES; spin_lock(&all_mddevs_lock); - if (list_empty(&mddev->all_mddevs)) { + if (!mddev_get(mddev)) { spin_unlock(&all_mddevs_lock); return -EBUSY; } - mddev_get(mddev); spin_unlock(&all_mddevs_lock); rv = entry->store(mddev, page, length); mddev_put(mddev); return rv; } -static void md_free(struct kobject *ko) +static void md_kobj_release(struct kobject *ko) { struct mddev *mddev = container_of(ko, struct mddev, kobj); @@ -5577,15 +5558,8 @@ static void md_free(struct kobject *ko) if (mddev->sysfs_level) sysfs_put(mddev->sysfs_level); - if (mddev->gendisk) { - del_gendisk(mddev->gendisk); - put_disk(mddev->gendisk); - } - percpu_ref_exit(&mddev->writes_pending); - - bioset_exit(&mddev->bio_set); - bioset_exit(&mddev->sync_set); - kfree(mddev); + del_gendisk(mddev->gendisk); + put_disk(mddev->gendisk); } static const struct sysfs_ops md_sysfs_ops = { @@ -5593,7 +5567,7 @@ static const struct sysfs_ops md_sysfs_ops = { .store = md_attr_store, }; static struct kobj_type md_ktype = { - .release = md_free, + .release = md_kobj_release, .sysfs_ops = &md_sysfs_ops, .default_groups = md_attr_groups, }; @@ -5604,7 +5578,6 @@ static void mddev_delayed_delete(struct work_struct *ws) { struct mddev *mddev = container_of(ws, struct mddev, del_work); - kobject_del(&mddev->kobj); kobject_put(&mddev->kobj); } @@ -5623,7 +5596,7 @@ int mddev_init_writes_pending(struct mddev *mddev) } EXPORT_SYMBOL_GPL(mddev_init_writes_pending); -static int md_alloc(dev_t dev, char *name) +struct mddev *md_alloc(dev_t dev, char *name) { /* * If dev is zero, name is the name of a device to allocate with @@ -5651,8 +5624,8 @@ static int md_alloc(dev_t dev, char *name) mutex_lock(&disks_mutex); mddev = mddev_alloc(dev); if (IS_ERR(mddev)) { - mutex_unlock(&disks_mutex); - return PTR_ERR(mddev); + error = PTR_ERR(mddev); + goto out_unlock; } partitioned = (MAJOR(mddev->unit) != MD_MAJOR); @@ -5670,7 +5643,7 @@ static int md_alloc(dev_t dev, char *name) strcmp(mddev2->gendisk->disk_name, name) == 0) { spin_unlock(&all_mddevs_lock); error = -EEXIST; - goto out_unlock_disks_mutex; + goto out_free_mddev; } spin_unlock(&all_mddevs_lock); } @@ -5683,7 +5656,7 @@ static int md_alloc(dev_t dev, char *name) error = -ENOMEM; disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) - goto out_unlock_disks_mutex; + goto out_free_mddev; disk->major = MAJOR(mddev->unit); disk->first_minor = unit << shift; @@ -5704,25 +5677,45 @@ static int md_alloc(dev_t dev, char *name) mddev->gendisk = disk; error = add_disk(disk); if (error) - goto out_cleanup_disk; + goto out_put_disk; + kobject_init(&mddev->kobj, &md_ktype); error = kobject_add(&mddev->kobj, &disk_to_dev(disk)->kobj, "%s", "md"); - if (error) - goto out_del_gendisk; + if (error) { + /* + * The disk is already live at this point. Clear the hold flag + * and let mddev_put take care of the deletion, as it isn't any + * different from a normal close on last release now. + */ + mddev->hold_active = 0; + mutex_unlock(&disks_mutex); + mddev_put(mddev); + return ERR_PTR(error); + } kobject_uevent(&mddev->kobj, KOBJ_ADD); mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state"); mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level"); - goto out_unlock_disks_mutex; - -out_del_gendisk: - del_gendisk(disk); -out_cleanup_disk: - put_disk(disk); -out_unlock_disks_mutex: mutex_unlock(&disks_mutex); + return mddev; + +out_put_disk: + put_disk(disk); +out_free_mddev: + mddev_free(mddev); +out_unlock: + mutex_unlock(&disks_mutex); + return ERR_PTR(error); +} + +static int md_alloc_and_put(dev_t dev, char *name) +{ + struct mddev *mddev = md_alloc(dev, name); + + if (IS_ERR(mddev)) + return PTR_ERR(mddev); mddev_put(mddev); - return error; + return 0; } static void md_probe(dev_t dev) @@ -5730,7 +5723,7 @@ static void md_probe(dev_t dev) if (MAJOR(dev) == MD_MAJOR && MINOR(dev) >= 512) return; if (create_on_open) - md_alloc(dev, NULL); + md_alloc_and_put(dev, NULL); } static int add_named_array(const char *val, const struct kernel_param *kp) @@ -5752,12 +5745,12 @@ static int add_named_array(const char *val, const struct kernel_param *kp) return -E2BIG; strscpy(buf, val, len+1); if (strncmp(buf, "md_", 3) == 0) - return md_alloc(0, buf); + return md_alloc_and_put(0, buf); if (strncmp(buf, "md", 2) == 0 && isdigit(buf[2]) && kstrtoul(buf+2, 10, &devnum) == 0 && devnum <= MINORMASK) - return md_alloc(MKDEV(MD_MAJOR, devnum), NULL); + return md_alloc_and_put(MKDEV(MD_MAJOR, devnum), NULL); return -EINVAL; } @@ -6197,6 +6190,7 @@ static void __md_stop_writes(struct mddev *mddev) flush_workqueue(md_misc_wq); if (mddev->sync_thread) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); } @@ -6244,11 +6238,11 @@ static void mddev_detach(struct mddev *mddev) static void __md_stop(struct mddev *mddev) { struct md_personality *pers = mddev->pers; - md_bitmap_destroy(mddev); mddev_detach(mddev); /* Ensure ->event_work is done */ if (mddev->event_work.func) flush_workqueue(md_misc_wq); + md_bitmap_destroy(mddev); spin_lock(&mddev->lock); mddev->pers = NULL; spin_unlock(&mddev->lock); @@ -6497,9 +6491,8 @@ static void autorun_devices(int part) break; } - md_probe(dev); - mddev = mddev_find(dev); - if (!mddev) + mddev = md_alloc(dev, NULL); + if (IS_ERR(mddev)) break; if (mddev_lock(mddev)) @@ -7782,45 +7775,33 @@ static int md_set_read_only(struct block_device *bdev, bool ro) static int md_open(struct block_device *bdev, fmode_t mode) { - /* - * Succeed if we can lock the mddev, which confirms that - * it isn't being stopped right now. - */ - struct mddev *mddev = mddev_find(bdev->bd_dev); + struct mddev *mddev; int err; + spin_lock(&all_mddevs_lock); + mddev = mddev_get(bdev->bd_disk->private_data); + spin_unlock(&all_mddevs_lock); if (!mddev) return -ENODEV; - if (mddev->gendisk != bdev->bd_disk) { - /* we are racing with mddev_put which is discarding this - * bd_disk. - */ - mddev_put(mddev); - /* Wait until bdev->bd_disk is definitely gone */ - if (work_pending(&mddev->del_work)) - flush_workqueue(md_misc_wq); - return -EBUSY; - } - BUG_ON(mddev != bdev->bd_disk->private_data); - - if ((err = mutex_lock_interruptible(&mddev->open_mutex))) + err = mutex_lock_interruptible(&mddev->open_mutex); + if (err) goto out; - if (test_bit(MD_CLOSING, &mddev->flags)) { - mutex_unlock(&mddev->open_mutex); - err = -ENODEV; - goto out; - } + err = -ENODEV; + if (test_bit(MD_CLOSING, &mddev->flags)) + goto out_unlock; - err = 0; atomic_inc(&mddev->openers); mutex_unlock(&mddev->open_mutex); bdev_check_media_change(bdev); - out: - if (err) - mddev_put(mddev); + return 0; + +out_unlock: + mutex_unlock(&mddev->open_mutex); +out: + mddev_put(mddev); return err; } @@ -7844,6 +7825,17 @@ static unsigned int md_check_events(struct gendisk *disk, unsigned int clearing) return ret; } +static void md_free_disk(struct gendisk *disk) +{ + struct mddev *mddev = disk->private_data; + + percpu_ref_exit(&mddev->writes_pending); + bioset_exit(&mddev->bio_set); + bioset_exit(&mddev->sync_set); + + mddev_free(mddev); +} + const struct block_device_operations md_fops = { .owner = THIS_MODULE, @@ -7857,6 +7849,7 @@ const struct block_device_operations md_fops = .getgeo = md_getgeo, .check_events = md_check_events, .set_read_only = md_set_read_only, + .free_disk = md_free_disk, }; static int md_thread(void *arg) @@ -8018,16 +8011,26 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev) max_sectors = mddev->dev_sectors; resync = mddev->curr_resync; - if (resync <= 3) { + if (resync < MD_RESYNC_ACTIVE) { if (test_bit(MD_RECOVERY_DONE, &mddev->recovery)) /* Still cleaning up */ resync = max_sectors; - } else if (resync > max_sectors) + } else if (resync > max_sectors) { resync = max_sectors; - else + } else { resync -= atomic_read(&mddev->recovery_active); + if (resync < MD_RESYNC_ACTIVE) { + /* + * Resync has started, but the subtraction has + * yielded one of the special values. Force it + * to active to ensure the status reports an + * active resync. + */ + resync = MD_RESYNC_ACTIVE; + } + } - if (resync == 0) { + if (resync == MD_RESYNC_NONE) { if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery)) { struct md_rdev *rdev; @@ -8051,7 +8054,7 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev) } return 0; } - if (resync < 3) { + if (resync < MD_RESYNC_ACTIVE) { seq_printf(seq, "\tresync=DELAYED"); return 1; } @@ -8152,6 +8155,8 @@ static void *md_seq_start(struct seq_file *seq, loff_t *pos) if (!l--) { mddev = list_entry(tmp, struct mddev, all_mddevs); mddev_get(mddev); + if (!mddev_get(mddev)) + continue; spin_unlock(&all_mddevs_lock); return mddev; } @@ -8165,25 +8170,35 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct list_head *tmp; struct mddev *next_mddev, *mddev = v; + struct mddev *to_put = NULL; ++*pos; if (v == (void*)2) return NULL; spin_lock(&all_mddevs_lock); - if (v == (void*)1) + if (v == (void*)1) { tmp = all_mddevs.next; - else + } else { + to_put = mddev; + tmp = mddev->all_mddevs.next; + } + + for (;;) { + if (tmp == &all_mddevs) { + next_mddev = (void*)2; + *pos = 0x10000; + break; + } + next_mddev = list_entry(tmp, struct mddev, all_mddevs); + if (mddev_get(next_mddev)) + break; + mddev = next_mddev; tmp = mddev->all_mddevs.next; - if (tmp != &all_mddevs) - next_mddev = mddev_get(list_entry(tmp,struct mddev,all_mddevs)); - else { - next_mddev = (void*)2; - *pos = 0x10000; } spin_unlock(&all_mddevs_lock); - if (v != (void*)1) + if (to_put) mddev_put(mddev); return next_mddev; @@ -8682,7 +8697,6 @@ void md_do_sync(struct md_thread *thread) unsigned long update_time; sector_t mark_cnt[SYNC_MARKS]; int last_mark,m; - struct list_head *tmp; sector_t last_check; int skipped = 0; struct md_rdev *rdev; @@ -8729,13 +8743,7 @@ void md_do_sync(struct md_thread *thread) mddev->last_sync_action = action ?: desc; - /* we overload curr_resync somewhat here. - * 0 == not engaged in resync at all - * 2 == checking that there is no conflict with another sync - * 1 == like 2, but have yielded to allow conflicting resync to - * commence - * other == active in resync - this many blocks - * + /* * Before starting a resync we must have set curr_resync to * 2, and then checked that every "conflicting" array has curr_resync * less than ours. When we find one that is the same or higher @@ -8747,24 +8755,29 @@ void md_do_sync(struct md_thread *thread) do { int mddev2_minor = -1; - mddev->curr_resync = 2; + mddev->curr_resync = MD_RESYNC_DELAYED; try_again: if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) goto skip; - for_each_mddev(mddev2, tmp) { + spin_lock(&all_mddevs_lock); + list_for_each_entry(mddev2, &all_mddevs, all_mddevs) { + if (test_bit(MD_DELETED, &mddev2->flags)) + continue; if (mddev2 == mddev) continue; if (!mddev->parallel_resync && mddev2->curr_resync && match_mddev_units(mddev, mddev2)) { DEFINE_WAIT(wq); - if (mddev < mddev2 && mddev->curr_resync == 2) { + if (mddev < mddev2 && + mddev->curr_resync == MD_RESYNC_DELAYED) { /* arbitrarily yield */ - mddev->curr_resync = 1; + mddev->curr_resync = MD_RESYNC_YIELDED; wake_up(&resync_wait); } - if (mddev > mddev2 && mddev->curr_resync == 1) + if (mddev > mddev2 && + mddev->curr_resync == MD_RESYNC_YIELDED) /* no need to wait here, we can wait the next * time 'round when curr_resync == 2 */ @@ -8782,7 +8795,8 @@ void md_do_sync(struct md_thread *thread) desc, mdname(mddev), mdname(mddev2)); } - mddev_put(mddev2); + spin_unlock(&all_mddevs_lock); + if (signal_pending(current)) flush_signals(current); schedule(); @@ -8792,7 +8806,8 @@ void md_do_sync(struct md_thread *thread) finish_wait(&resync_wait, &wq); } } - } while (mddev->curr_resync < 2); + spin_unlock(&all_mddevs_lock); + } while (mddev->curr_resync < MD_RESYNC_DELAYED); j = 0; if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) { @@ -8876,7 +8891,7 @@ void md_do_sync(struct md_thread *thread) desc, mdname(mddev)); mddev->curr_resync = j; } else - mddev->curr_resync = 3; /* no longer delayed */ + mddev->curr_resync = MD_RESYNC_ACTIVE; /* no longer delayed */ mddev->curr_resync_completed = j; sysfs_notify_dirent_safe(mddev->sysfs_completed); md_new_event(); @@ -9011,14 +9026,14 @@ void md_do_sync(struct md_thread *thread) if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && !test_bit(MD_RECOVERY_INTR, &mddev->recovery) && - mddev->curr_resync > 3) { + mddev->curr_resync >= MD_RESYNC_ACTIVE) { mddev->curr_resync_completed = mddev->curr_resync; sysfs_notify_dirent_safe(mddev->sysfs_completed); } mddev->pers->sync_request(mddev, max_sectors, &skipped); if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) && - mddev->curr_resync > 3) { + mddev->curr_resync >= MD_RESYNC_ACTIVE) { if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) { if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { if (mddev->curr_resync >= mddev->recovery_cp) { @@ -9082,7 +9097,7 @@ void md_do_sync(struct md_thread *thread) } else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) mddev->resync_min = mddev->curr_resync_completed; set_bit(MD_RECOVERY_DONE, &mddev->recovery); - mddev->curr_resync = 0; + mddev->curr_resync = MD_RESYNC_NONE; spin_unlock(&mddev->lock); wake_up(&resync_wait); @@ -9303,6 +9318,7 @@ void md_check_recovery(struct mddev *mddev) * ->spare_active and clear saved_raid_disk */ set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); @@ -9338,6 +9354,7 @@ void md_check_recovery(struct mddev *mddev) goto unlock; } if (mddev->sync_thread) { + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); goto unlock; } @@ -9417,8 +9434,7 @@ void md_reap_sync_thread(struct mddev *mddev) sector_t old_dev_sectors = mddev->dev_sectors; bool is_reshaped = false; - /* resync has finished, collect result */ - md_unregister_thread(&mddev->sync_thread); + /* sync_thread should be unregistered, collect result */ if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && mddev->degraded != mddev->raid_disks) { @@ -9466,6 +9482,7 @@ void md_reap_sync_thread(struct mddev *mddev) wake_up(&resync_wait); /* flag recovery needed just to double check */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + sysfs_notify_dirent_safe(mddev->sysfs_completed); sysfs_notify_dirent_safe(mddev->sysfs_action); md_new_event(); if (mddev->event_work.func) @@ -9544,11 +9561,14 @@ EXPORT_SYMBOL_GPL(rdev_clear_badblocks); static int md_notify_reboot(struct notifier_block *this, unsigned long code, void *x) { - struct list_head *tmp; - struct mddev *mddev; + struct mddev *mddev, *n; int need_delay = 0; - for_each_mddev(mddev, tmp) { + spin_lock(&all_mddevs_lock); + list_for_each_entry_safe(mddev, n, &all_mddevs, all_mddevs) { + if (!mddev_get(mddev)) + continue; + spin_unlock(&all_mddevs_lock); if (mddev_trylock(mddev)) { if (mddev->pers) __md_stop_writes(mddev); @@ -9557,7 +9577,11 @@ static int md_notify_reboot(struct notifier_block *this, mddev_unlock(mddev); } need_delay = 1; + mddev_put(mddev); + spin_lock(&all_mddevs_lock); } + spin_unlock(&all_mddevs_lock); + /* * certain more exotic SCSI devices are known to be * volatile wrt too early system reboots. While the @@ -9876,8 +9900,7 @@ void md_autostart_arrays(int part) static __exit void md_exit(void) { - struct mddev *mddev; - struct list_head *tmp; + struct mddev *mddev, *n; int delay = 1; unregister_blkdev(MD_MAJOR,"md"); @@ -9897,17 +9920,24 @@ static __exit void md_exit(void) } remove_proc_entry("mdstat", NULL); - for_each_mddev(mddev, tmp) { + spin_lock(&all_mddevs_lock); + list_for_each_entry_safe(mddev, n, &all_mddevs, all_mddevs) { + if (!mddev_get(mddev)) + continue; + spin_unlock(&all_mddevs_lock); export_array(mddev); mddev->ctime = 0; mddev->hold_active = 0; /* - * for_each_mddev() will call mddev_put() at the end of each - * iteration. As the mddev is now fully clear, this will - * schedule the mddev for destruction by a workqueue, and the + * As the mddev is now fully clear, mddev_put will schedule + * the mddev for destruction by a workqueue, and the * destroy_workqueue() below will wait for that to complete. */ + mddev_put(mddev); + spin_lock(&all_mddevs_lock); } + spin_unlock(&all_mddevs_lock); + destroy_workqueue(md_rdev_misc_wq); destroy_workqueue(md_misc_wq); destroy_workqueue(md_wq); diff --git a/drivers/md/md.h b/drivers/md/md.h index b4f84b27bdef..b4e2d8b87b61 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -254,6 +254,7 @@ struct md_cluster_info; * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that * array is ready yet. * @MD_BROKEN: This is used to stop writes and mark array as failed. + * @MD_DELETED: This device is being deleted * * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */ @@ -270,6 +271,7 @@ enum mddev_flags { MD_UPDATING_SB, MD_NOT_READY, MD_BROKEN, + MD_DELETED, }; enum mddev_sb_flags { @@ -288,6 +290,21 @@ struct serial_info { sector_t _subtree_last; /* highest sector in subtree of rb node */ }; +/* + * mddev->curr_resync stores the current sector of the resync but + * also has some overloaded values. + */ +enum { + /* No resync in progress */ + MD_RESYNC_NONE = 0, + /* Yielded to allow another conflicting resync to commence */ + MD_RESYNC_YIELDED = 1, + /* Delayed to check that there is no conflict with another sync */ + MD_RESYNC_DELAYED = 2, + /* Any value greater than or equal to this is in an active resync */ + MD_RESYNC_ACTIVE = 3, +}; + struct mddev { void *private; struct md_personality *pers; @@ -750,6 +767,8 @@ extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); extern void mddev_init(struct mddev *mddev); +struct mddev *md_alloc(dev_t dev, char *name); +void mddev_put(struct mddev *mddev); extern int md_run(struct mddev *mddev); extern int md_start(struct mddev *mddev); extern void md_stop(struct mddev *mddev); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 26545950ca42..9117fcdee1be 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2167,9 +2167,12 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev) int err = 0; int number = rdev->raid_disk; struct md_rdev **rdevp; - struct raid10_info *p = conf->mirrors + number; + struct raid10_info *p; print_conf(conf); + if (unlikely(number >= mddev->raid_disks)) + return 0; + p = conf->mirrors + number; if (rdev == p->rdev) rdevp = &p->rdev; else if (rdev == p->replacement) diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 6f2dd73128b0..f4e1cc1ece43 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1590,18 +1590,13 @@ void r5l_quiesce(struct r5l_log *log, int quiesce) bool r5l_log_disk_error(struct r5conf *conf) { - struct r5l_log *log; - bool ret; - /* don't allow write if journal disk is missing */ - rcu_read_lock(); - log = rcu_dereference(conf->log); + struct r5l_log *log = conf->log; + /* don't allow write if journal disk is missing */ if (!log) - ret = test_bit(MD_HAS_JOURNAL, &conf->mddev->flags); + return test_bit(MD_HAS_JOURNAL, &conf->mddev->flags); else - ret = test_bit(Faulty, &log->rdev->flags); - rcu_read_unlock(); - return ret; + return test_bit(Faulty, &log->rdev->flags); } #define R5L_RECOVERY_PAGE_POOL_SIZE 256 @@ -2534,12 +2529,13 @@ static ssize_t r5c_journal_mode_show(struct mddev *mddev, char *page) struct r5conf *conf; int ret; - spin_lock(&mddev->lock); + ret = mddev_lock(mddev); + if (ret) + return ret; + conf = mddev->private; - if (!conf || !conf->log) { - spin_unlock(&mddev->lock); - return 0; - } + if (!conf || !conf->log) + goto out_unlock; switch (conf->log->r5c_journal_mode) { case R5C_JOURNAL_MODE_WRITE_THROUGH: @@ -2557,7 +2553,9 @@ static ssize_t r5c_journal_mode_show(struct mddev *mddev, char *page) default: ret = 0; } - spin_unlock(&mddev->lock); + +out_unlock: + mddev_unlock(mddev); return ret; } @@ -2639,7 +2637,7 @@ int r5c_try_caching_write(struct r5conf *conf, int i; struct r5dev *dev; int to_cache = 0; - void **pslot; + void __rcu **pslot; sector_t tree_index; int ret; uintptr_t refcount; @@ -2806,7 +2804,7 @@ void r5c_finish_stripe_write_out(struct r5conf *conf, int i; int do_wakeup = 0; sector_t tree_index; - void **pslot; + void __rcu **pslot; uintptr_t refcount; if (!log || !test_bit(R5_InJournal, &sh->dev[sh->pd_idx].flags)) @@ -3145,7 +3143,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) spin_lock_init(&log->stripe_in_journal_lock); atomic_set(&log->stripe_in_journal_count, 0); - rcu_assign_pointer(conf->log, log); + conf->log = log; set_bit(MD_HAS_JOURNAL, &conf->mddev->flags); return 0; @@ -3167,13 +3165,13 @@ void r5l_exit_log(struct r5conf *conf) { struct r5l_log *log = conf->log; - conf->log = NULL; - synchronize_rcu(); - /* Ensure disable_writeback_work wakes up and exits */ wake_up(&conf->mddev->sb_wait); flush_work(&log->disable_writeback_work); md_unregister_thread(&log->reclaim_thread); + + conf->log = NULL; + mempool_exit(&log->meta_pool); bioset_exit(&log->bs); mempool_exit(&log->io_pool); diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h index 43c714a8798c..c8332502669e 100644 --- a/drivers/md/raid5-log.h +++ b/drivers/md/raid5-log.h @@ -2,49 +2,46 @@ #ifndef _RAID5_LOG_H #define _RAID5_LOG_H -extern int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev); -extern void r5l_exit_log(struct r5conf *conf); -extern int r5l_write_stripe(struct r5l_log *log, struct stripe_head *head_sh); -extern void r5l_write_stripe_run(struct r5l_log *log); -extern void r5l_flush_stripe_to_raid(struct r5l_log *log); -extern void r5l_stripe_write_finished(struct stripe_head *sh); -extern int r5l_handle_flush_request(struct r5l_log *log, struct bio *bio); -extern void r5l_quiesce(struct r5l_log *log, int quiesce); -extern bool r5l_log_disk_error(struct r5conf *conf); -extern bool r5c_is_writeback(struct r5l_log *log); -extern int -r5c_try_caching_write(struct r5conf *conf, struct stripe_head *sh, - struct stripe_head_state *s, int disks); -extern void -r5c_finish_stripe_write_out(struct r5conf *conf, struct stripe_head *sh, - struct stripe_head_state *s); -extern void r5c_release_extra_page(struct stripe_head *sh); -extern void r5c_use_extra_page(struct stripe_head *sh); -extern void r5l_wake_reclaim(struct r5l_log *log, sector_t space); -extern void r5c_handle_cached_data_endio(struct r5conf *conf, - struct stripe_head *sh, int disks); -extern int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh); -extern void r5c_make_stripe_write_out(struct stripe_head *sh); -extern void r5c_flush_cache(struct r5conf *conf, int num); -extern void r5c_check_stripe_cache_usage(struct r5conf *conf); -extern void r5c_check_cached_full_stripe(struct r5conf *conf); +int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev); +void r5l_exit_log(struct r5conf *conf); +int r5l_write_stripe(struct r5l_log *log, struct stripe_head *head_sh); +void r5l_write_stripe_run(struct r5l_log *log); +void r5l_flush_stripe_to_raid(struct r5l_log *log); +void r5l_stripe_write_finished(struct stripe_head *sh); +int r5l_handle_flush_request(struct r5l_log *log, struct bio *bio); +void r5l_quiesce(struct r5l_log *log, int quiesce); +bool r5l_log_disk_error(struct r5conf *conf); +bool r5c_is_writeback(struct r5l_log *log); +int r5c_try_caching_write(struct r5conf *conf, struct stripe_head *sh, + struct stripe_head_state *s, int disks); +void r5c_finish_stripe_write_out(struct r5conf *conf, struct stripe_head *sh, + struct stripe_head_state *s); +void r5c_release_extra_page(struct stripe_head *sh); +void r5c_use_extra_page(struct stripe_head *sh); +void r5l_wake_reclaim(struct r5l_log *log, sector_t space); +void r5c_handle_cached_data_endio(struct r5conf *conf, + struct stripe_head *sh, int disks); +int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh); +void r5c_make_stripe_write_out(struct stripe_head *sh); +void r5c_flush_cache(struct r5conf *conf, int num); +void r5c_check_stripe_cache_usage(struct r5conf *conf); +void r5c_check_cached_full_stripe(struct r5conf *conf); extern struct md_sysfs_entry r5c_journal_mode; -extern void r5c_update_on_rdev_error(struct mddev *mddev, - struct md_rdev *rdev); -extern bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect); -extern int r5l_start(struct r5l_log *log); +void r5c_update_on_rdev_error(struct mddev *mddev, struct md_rdev *rdev); +bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect); +int r5l_start(struct r5l_log *log); -extern struct dma_async_tx_descriptor * +struct dma_async_tx_descriptor * ops_run_partial_parity(struct stripe_head *sh, struct raid5_percpu *percpu, struct dma_async_tx_descriptor *tx); -extern int ppl_init_log(struct r5conf *conf); -extern void ppl_exit_log(struct r5conf *conf); -extern int ppl_write_stripe(struct r5conf *conf, struct stripe_head *sh); -extern void ppl_write_stripe_run(struct r5conf *conf); -extern void ppl_stripe_write_finished(struct stripe_head *sh); -extern int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add); -extern void ppl_quiesce(struct r5conf *conf, int quiesce); -extern int ppl_handle_flush_request(struct r5l_log *log, struct bio *bio); +int ppl_init_log(struct r5conf *conf); +void ppl_exit_log(struct r5conf *conf); +int ppl_write_stripe(struct r5conf *conf, struct stripe_head *sh); +void ppl_write_stripe_run(struct r5conf *conf); +void ppl_stripe_write_finished(struct stripe_head *sh); +int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add); +void ppl_quiesce(struct r5conf *conf, int quiesce); +int ppl_handle_flush_request(struct bio *bio); extern struct md_sysfs_entry ppl_write_hint; static inline bool raid5_has_log(struct r5conf *conf) @@ -111,7 +108,7 @@ static inline int log_handle_flush_request(struct r5conf *conf, struct bio *bio) if (conf->log) ret = r5l_handle_flush_request(conf->log, bio); else if (raid5_has_ppl(conf)) - ret = ppl_handle_flush_request(conf->log, bio); + ret = ppl_handle_flush_request(bio); return ret; } diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 98988cb26295..31b9157bc9ae 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -679,7 +679,7 @@ void ppl_quiesce(struct r5conf *conf, int quiesce) } } -int ppl_handle_flush_request(struct r5l_log *log, struct bio *bio) +int ppl_handle_flush_request(struct bio *bio) { if (bio->bi_iter.bi_size == 0) { bio_endio(bio); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 5cabdbbac48b..860c45c10a57 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -61,6 +61,8 @@ #define cpu_to_group(cpu) cpu_to_node(cpu) #define ANY_GROUP NUMA_NO_NODE +#define RAID5_MAX_REQ_STRIPES 256 + static bool devices_handle_discard_safely = false; module_param(devices_handle_discard_safely, bool, 0644); MODULE_PARM_DESC(devices_handle_discard_safely, @@ -624,6 +626,49 @@ static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, return NULL; } +static struct stripe_head *find_get_stripe(struct r5conf *conf, + sector_t sector, short generation, int hash) +{ + int inc_empty_inactive_list_flag; + struct stripe_head *sh; + + sh = __find_stripe(conf, sector, generation); + if (!sh) + return NULL; + + if (atomic_inc_not_zero(&sh->count)) + return sh; + + /* + * Slow path. The reference count is zero which means the stripe must + * be on a list (sh->lru). Must remove the stripe from the list that + * references it with the device_lock held. + */ + + spin_lock(&conf->device_lock); + if (!atomic_read(&sh->count)) { + if (!test_bit(STRIPE_HANDLE, &sh->state)) + atomic_inc(&conf->active_stripes); + BUG_ON(list_empty(&sh->lru) && + !test_bit(STRIPE_EXPANDING, &sh->state)); + inc_empty_inactive_list_flag = 0; + if (!list_empty(conf->inactive_list + hash)) + inc_empty_inactive_list_flag = 1; + list_del_init(&sh->lru); + if (list_empty(conf->inactive_list + hash) && + inc_empty_inactive_list_flag) + atomic_inc(&conf->empty_inactive_list_nr); + if (sh->group) { + sh->group->stripes_cnt--; + sh->group = NULL; + } + } + atomic_inc(&sh->count); + spin_unlock(&conf->device_lock); + + return sh; +} + /* * Need to check if array has failed when deciding whether to: * - start an array @@ -710,80 +755,121 @@ static bool has_failed(struct r5conf *conf) return degraded > conf->max_degraded; } -struct stripe_head * -raid5_get_active_stripe(struct r5conf *conf, sector_t sector, - int previous, int noblock, int noquiesce) +enum stripe_result { + STRIPE_SUCCESS = 0, + STRIPE_RETRY, + STRIPE_SCHEDULE_AND_RETRY, + STRIPE_FAIL, +}; + +struct stripe_request_ctx { + /* a reference to the last stripe_head for batching */ + struct stripe_head *batch_last; + + /* first sector in the request */ + sector_t first_sector; + + /* last sector in the request */ + sector_t last_sector; + + /* + * bitmap to track stripe sectors that have been added to stripes + * add one to account for unaligned requests + */ + DECLARE_BITMAP(sectors_to_do, RAID5_MAX_REQ_STRIPES + 1); + + /* the request had REQ_PREFLUSH, cleared after the first stripe_head */ + bool do_flush; +}; + +/* + * Block until another thread clears R5_INACTIVE_BLOCKED or + * there are fewer than 3/4 the maximum number of active stripes + * and there is an inactive stripe available. + */ +static bool is_inactive_blocked(struct r5conf *conf, int hash) +{ + int active = atomic_read(&conf->active_stripes); + + if (list_empty(conf->inactive_list + hash)) + return false; + + if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) + return true; + + return active < (conf->max_nr_stripes * 3 / 4); +} + +static struct stripe_head *__raid5_get_active_stripe(struct r5conf *conf, + struct stripe_request_ctx *ctx, sector_t sector, + bool previous, bool noblock, bool noquiesce) { struct stripe_head *sh; int hash = stripe_hash_locks_hash(conf, sector); - int inc_empty_inactive_list_flag; pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector); spin_lock_irq(conf->hash_locks + hash); - do { - wait_event_lock_irq(conf->wait_for_quiescent, - conf->quiesce == 0 || noquiesce, - *(conf->hash_locks + hash)); - sh = __find_stripe(conf, sector, conf->generation - previous); - if (!sh) { - if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) { - sh = get_free_stripe(conf, hash); - if (!sh && !test_bit(R5_DID_ALLOC, - &conf->cache_state)) - set_bit(R5_ALLOC_MORE, - &conf->cache_state); - } - if (noblock && sh == NULL) - break; - - r5c_check_stripe_cache_usage(conf); - if (!sh) { - set_bit(R5_INACTIVE_BLOCKED, - &conf->cache_state); - r5l_wake_reclaim(conf->log, 0); - wait_event_lock_irq( - conf->wait_for_stripe, - !list_empty(conf->inactive_list + hash) && - (atomic_read(&conf->active_stripes) - < (conf->max_nr_stripes * 3 / 4) - || !test_bit(R5_INACTIVE_BLOCKED, - &conf->cache_state)), - *(conf->hash_locks + hash)); - clear_bit(R5_INACTIVE_BLOCKED, - &conf->cache_state); - } else { - init_stripe(sh, sector, previous); - atomic_inc(&sh->count); - } - } else if (!atomic_inc_not_zero(&sh->count)) { - spin_lock(&conf->device_lock); - if (!atomic_read(&sh->count)) { - if (!test_bit(STRIPE_HANDLE, &sh->state)) - atomic_inc(&conf->active_stripes); - BUG_ON(list_empty(&sh->lru) && - !test_bit(STRIPE_EXPANDING, &sh->state)); - inc_empty_inactive_list_flag = 0; - if (!list_empty(conf->inactive_list + hash)) - inc_empty_inactive_list_flag = 1; - list_del_init(&sh->lru); - if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag) - atomic_inc(&conf->empty_inactive_list_nr); - if (sh->group) { - sh->group->stripes_cnt--; - sh->group = NULL; - } - } - atomic_inc(&sh->count); - spin_unlock(&conf->device_lock); +retry: + if (!noquiesce && conf->quiesce) { + /* + * Must release the reference to batch_last before waiting, + * on quiesce, otherwise the batch_last will hold a reference + * to a stripe and raid5_quiesce() will deadlock waiting for + * active_stripes to go to zero. + */ + if (ctx && ctx->batch_last) { + raid5_release_stripe(ctx->batch_last); + ctx->batch_last = NULL; } - } while (sh == NULL); + wait_event_lock_irq(conf->wait_for_quiescent, !conf->quiesce, + *(conf->hash_locks + hash)); + } + + sh = find_get_stripe(conf, sector, conf->generation - previous, hash); + if (sh) + goto out; + + if (test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) + goto wait_for_stripe; + + sh = get_free_stripe(conf, hash); + if (sh) { + r5c_check_stripe_cache_usage(conf); + init_stripe(sh, sector, previous); + atomic_inc(&sh->count); + goto out; + } + + if (!test_bit(R5_DID_ALLOC, &conf->cache_state)) + set_bit(R5_ALLOC_MORE, &conf->cache_state); + +wait_for_stripe: + if (noblock) + goto out; + + set_bit(R5_INACTIVE_BLOCKED, &conf->cache_state); + r5l_wake_reclaim(conf->log, 0); + wait_event_lock_irq(conf->wait_for_stripe, + is_inactive_blocked(conf, hash), + *(conf->hash_locks + hash)); + clear_bit(R5_INACTIVE_BLOCKED, &conf->cache_state); + goto retry; + +out: spin_unlock_irq(conf->hash_locks + hash); return sh; } +struct stripe_head *raid5_get_active_stripe(struct r5conf *conf, + sector_t sector, bool previous, bool noblock, bool noquiesce) +{ + return __raid5_get_active_stripe(conf, NULL, sector, previous, noblock, + noquiesce); +} + static bool is_full_stripe_write(struct stripe_head *sh) { BUG_ON(sh->overwrite_disks > (sh->disks - sh->raid_conf->max_degraded)); @@ -824,13 +910,13 @@ static bool stripe_can_batch(struct stripe_head *sh) } /* we only do back search */ -static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh) +static void stripe_add_to_batch_list(struct r5conf *conf, + struct stripe_head *sh, struct stripe_head *last_sh) { struct stripe_head *head; sector_t head_sector, tmp_sec; int hash; int dd_idx; - int inc_empty_inactive_list_flag; /* Don't cross chunks, so stripe pd_idx/qd_idx is the same */ tmp_sec = sh->sector; @@ -838,36 +924,20 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh return; head_sector = sh->sector - RAID5_STRIPE_SECTORS(conf); - hash = stripe_hash_locks_hash(conf, head_sector); - spin_lock_irq(conf->hash_locks + hash); - head = __find_stripe(conf, head_sector, conf->generation); - if (head && !atomic_inc_not_zero(&head->count)) { - spin_lock(&conf->device_lock); - if (!atomic_read(&head->count)) { - if (!test_bit(STRIPE_HANDLE, &head->state)) - atomic_inc(&conf->active_stripes); - BUG_ON(list_empty(&head->lru) && - !test_bit(STRIPE_EXPANDING, &head->state)); - inc_empty_inactive_list_flag = 0; - if (!list_empty(conf->inactive_list + hash)) - inc_empty_inactive_list_flag = 1; - list_del_init(&head->lru); - if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag) - atomic_inc(&conf->empty_inactive_list_nr); - if (head->group) { - head->group->stripes_cnt--; - head->group = NULL; - } - } + if (last_sh && head_sector == last_sh->sector) { + head = last_sh; atomic_inc(&head->count); - spin_unlock(&conf->device_lock); + } else { + hash = stripe_hash_locks_hash(conf, head_sector); + spin_lock_irq(conf->hash_locks + hash); + head = find_get_stripe(conf, head_sector, conf->generation, + hash); + spin_unlock_irq(conf->hash_locks + hash); + if (!head) + return; + if (!stripe_can_batch(head)) + goto out; } - spin_unlock_irq(conf->hash_locks + hash); - - if (!head) - return; - if (!stripe_can_batch(head)) - goto out; lock_two_stripes(head, sh); /* clear_batch_ready clear the flag */ @@ -2882,10 +2952,10 @@ static void raid5_end_write_request(struct bio *bi) if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags)) clear_bit(R5_LOCKED, &sh->dev[i].flags); set_bit(STRIPE_HANDLE, &sh->state); - raid5_release_stripe(sh); if (sh->batch_head && sh != sh->batch_head) raid5_release_stripe(sh->batch_head); + raid5_release_stripe(sh); } static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) @@ -3413,39 +3483,32 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, s->locked, s->ops_request); } -/* - * Each stripe/dev can have one or more bion attached. - * toread/towrite point to the first in a chain. - * The bi_next chain must be in order. - */ -static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, - int forwrite, int previous) +static bool stripe_bio_overlaps(struct stripe_head *sh, struct bio *bi, + int dd_idx, int forwrite) { - struct bio **bip; struct r5conf *conf = sh->raid_conf; - int firstwrite=0; + struct bio **bip; - pr_debug("adding bi b#%llu to stripe s#%llu\n", - (unsigned long long)bi->bi_iter.bi_sector, - (unsigned long long)sh->sector); + pr_debug("checking bi b#%llu to stripe s#%llu\n", + bi->bi_iter.bi_sector, sh->sector); - spin_lock_irq(&sh->stripe_lock); /* Don't allow new IO added to stripes in batch list */ if (sh->batch_head) - goto overlap; - if (forwrite) { + return true; + + if (forwrite) bip = &sh->dev[dd_idx].towrite; - if (*bip == NULL) - firstwrite = 1; - } else + else bip = &sh->dev[dd_idx].toread; + while (*bip && (*bip)->bi_iter.bi_sector < bi->bi_iter.bi_sector) { if (bio_end_sector(*bip) > bi->bi_iter.bi_sector) - goto overlap; - bip = & (*bip)->bi_next; + return true; + bip = &(*bip)->bi_next; } + if (*bip && (*bip)->bi_iter.bi_sector < bio_end_sector(bi)) - goto overlap; + return true; if (forwrite && raid5_has_ppl(conf)) { /* @@ -3474,9 +3537,30 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, } if (first + conf->chunk_sectors * (count - 1) != last) - goto overlap; + return true; } + return false; +} + +static void __add_stripe_bio(struct stripe_head *sh, struct bio *bi, + int dd_idx, int forwrite, int previous) +{ + struct r5conf *conf = sh->raid_conf; + struct bio **bip; + int firstwrite = 0; + + if (forwrite) { + bip = &sh->dev[dd_idx].towrite; + if (!*bip) + firstwrite = 1; + } else { + bip = &sh->dev[dd_idx].toread; + } + + while (*bip && (*bip)->bi_iter.bi_sector < bi->bi_iter.bi_sector) + bip = &(*bip)->bi_next; + if (!forwrite || previous) clear_bit(STRIPE_BATCH_READY, &sh->state); @@ -3502,9 +3586,9 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, sh->overwrite_disks++; } - pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n", - (unsigned long long)(*bip)->bi_iter.bi_sector, - (unsigned long long)sh->sector, dd_idx); + pr_debug("added bi b#%llu to stripe s#%llu, disk %d, logical %llu\n", + (*bip)->bi_iter.bi_sector, sh->sector, dd_idx, + sh->dev[dd_idx].sector); if (conf->mddev->bitmap && firstwrite) { /* Cannot hold spinlock over bitmap_startwrite, @@ -3512,7 +3596,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, * we have added to the bitmap and set bm_seq. * So set STRIPE_BITMAP_PENDING to prevent * batching. - * If multiple add_stripe_bio() calls race here they + * If multiple __add_stripe_bio() calls race here they * much all set STRIPE_BITMAP_PENDING. So only the first one * to complete "bitmap_startwrite" gets to set * STRIPE_BIT_DELAY. This is important as once a stripe @@ -3530,16 +3614,27 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, set_bit(STRIPE_BIT_DELAY, &sh->state); } } - spin_unlock_irq(&sh->stripe_lock); +} - if (stripe_can_batch(sh)) - stripe_add_to_batch_list(conf, sh); - return 1; +/* + * Each stripe/dev can have one or more bios attached. + * toread/towrite point to the first in a chain. + * The bi_next chain must be in order. + */ +static bool add_stripe_bio(struct stripe_head *sh, struct bio *bi, + int dd_idx, int forwrite, int previous) +{ + spin_lock_irq(&sh->stripe_lock); - overlap: - set_bit(R5_Overlap, &sh->dev[dd_idx].flags); + if (stripe_bio_overlaps(sh, bi, dd_idx, forwrite)) { + set_bit(R5_Overlap, &sh->dev[dd_idx].flags); + spin_unlock_irq(&sh->stripe_lock); + return false; + } + + __add_stripe_bio(sh, bi, dd_idx, forwrite, previous); spin_unlock_irq(&sh->stripe_lock); - return 0; + return true; } static void end_reshape(struct r5conf *conf); @@ -5785,17 +5880,215 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) bio_endio(bi); } +static bool ahead_of_reshape(struct mddev *mddev, sector_t sector, + sector_t reshape_sector) +{ + return mddev->reshape_backwards ? sector < reshape_sector : + sector >= reshape_sector; +} + +static bool range_ahead_of_reshape(struct mddev *mddev, sector_t min, + sector_t max, sector_t reshape_sector) +{ + return mddev->reshape_backwards ? max < reshape_sector : + min >= reshape_sector; +} + +static bool stripe_ahead_of_reshape(struct mddev *mddev, struct r5conf *conf, + struct stripe_head *sh) +{ + sector_t max_sector = 0, min_sector = MaxSector; + bool ret = false; + int dd_idx; + + for (dd_idx = 0; dd_idx < sh->disks; dd_idx++) { + if (dd_idx == sh->pd_idx) + continue; + + min_sector = min(min_sector, sh->dev[dd_idx].sector); + max_sector = min(max_sector, sh->dev[dd_idx].sector); + } + + spin_lock_irq(&conf->device_lock); + + if (!range_ahead_of_reshape(mddev, min_sector, max_sector, + conf->reshape_progress)) + /* mismatch, need to try again */ + ret = true; + + spin_unlock_irq(&conf->device_lock); + + return ret; +} + +static int add_all_stripe_bios(struct r5conf *conf, + struct stripe_request_ctx *ctx, struct stripe_head *sh, + struct bio *bi, int forwrite, int previous) +{ + int dd_idx; + int ret = 1; + + spin_lock_irq(&sh->stripe_lock); + + for (dd_idx = 0; dd_idx < sh->disks; dd_idx++) { + struct r5dev *dev = &sh->dev[dd_idx]; + + if (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx) + continue; + + if (dev->sector < ctx->first_sector || + dev->sector >= ctx->last_sector) + continue; + + if (stripe_bio_overlaps(sh, bi, dd_idx, forwrite)) { + set_bit(R5_Overlap, &dev->flags); + ret = 0; + continue; + } + } + + if (!ret) + goto out; + + for (dd_idx = 0; dd_idx < sh->disks; dd_idx++) { + struct r5dev *dev = &sh->dev[dd_idx]; + + if (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx) + continue; + + if (dev->sector < ctx->first_sector || + dev->sector >= ctx->last_sector) + continue; + + __add_stripe_bio(sh, bi, dd_idx, forwrite, previous); + clear_bit((dev->sector - ctx->first_sector) >> + RAID5_STRIPE_SHIFT(conf), ctx->sectors_to_do); + } + +out: + spin_unlock_irq(&sh->stripe_lock); + return ret; +} + +static enum stripe_result make_stripe_request(struct mddev *mddev, + struct r5conf *conf, struct stripe_request_ctx *ctx, + sector_t logical_sector, struct bio *bi) +{ + const int rw = bio_data_dir(bi); + enum stripe_result ret; + struct stripe_head *sh; + sector_t new_sector; + int previous = 0; + int seq, dd_idx; + + seq = read_seqcount_begin(&conf->gen_lock); + + if (unlikely(conf->reshape_progress != MaxSector)) { + /* + * Spinlock is needed as reshape_progress may be + * 64bit on a 32bit platform, and so it might be + * possible to see a half-updated value + * Of course reshape_progress could change after + * the lock is dropped, so once we get a reference + * to the stripe that we think it is, we will have + * to check again. + */ + spin_lock_irq(&conf->device_lock); + if (ahead_of_reshape(mddev, logical_sector, + conf->reshape_progress)) { + previous = 1; + } else { + if (ahead_of_reshape(mddev, logical_sector, + conf->reshape_safe)) { + spin_unlock_irq(&conf->device_lock); + return STRIPE_SCHEDULE_AND_RETRY; + } + } + spin_unlock_irq(&conf->device_lock); + } + + new_sector = raid5_compute_sector(conf, logical_sector, previous, + &dd_idx, NULL); + pr_debug("raid456: %s, sector %llu logical %llu\n", __func__, + new_sector, logical_sector); + + sh = __raid5_get_active_stripe(conf, ctx, new_sector, previous, + (bi->bi_opf & REQ_RAHEAD), 0); + if (unlikely(!sh)) { + /* cannot get stripe, just give-up */ + bi->bi_status = BLK_STS_IOERR; + return STRIPE_FAIL; + } + + if (unlikely(previous) && + stripe_ahead_of_reshape(mddev, conf, sh)) { + /* + * Expansion moved on while waiting for a stripe. + * Expansion could still move past after this + * test, but as we are holding a reference to + * 'sh', we know that if that happens, + * STRIPE_EXPANDING will get set and the expansion + * won't proceed until we finish with the stripe. + */ + ret = STRIPE_SCHEDULE_AND_RETRY; + goto out_release; + } + + if (read_seqcount_retry(&conf->gen_lock, seq)) { + /* Might have got the wrong stripe_head by accident */ + ret = STRIPE_RETRY; + goto out_release; + } + + if (test_bit(STRIPE_EXPANDING, &sh->state) || + !add_all_stripe_bios(conf, ctx, sh, bi, rw, previous)) { + /* + * Stripe is busy expanding or add failed due to + * overlap. Flush everything and wait a while. + */ + md_wakeup_thread(mddev->thread); + ret = STRIPE_SCHEDULE_AND_RETRY; + goto out_release; + } + + if (stripe_can_batch(sh)) { + stripe_add_to_batch_list(conf, sh, ctx->batch_last); + if (ctx->batch_last) + raid5_release_stripe(ctx->batch_last); + atomic_inc(&sh->count); + ctx->batch_last = sh; + } + + if (ctx->do_flush) { + set_bit(STRIPE_R5C_PREFLUSH, &sh->state); + /* we only need flush for one stripe */ + ctx->do_flush = false; + } + + set_bit(STRIPE_HANDLE, &sh->state); + clear_bit(STRIPE_DELAYED, &sh->state); + if ((!sh->batch_head || sh == sh->batch_head) && + (bi->bi_opf & REQ_SYNC) && + !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + atomic_inc(&conf->preread_active_stripes); + + release_stripe_plug(mddev, sh); + return STRIPE_SUCCESS; + +out_release: + raid5_release_stripe(sh); + return ret; +} + static bool raid5_make_request(struct mddev *mddev, struct bio * bi) { + DEFINE_WAIT_FUNC(wait, woken_wake_function); struct r5conf *conf = mddev->private; - int dd_idx; - sector_t new_sector; - sector_t logical_sector, last_sector; - struct stripe_head *sh; + sector_t logical_sector; + struct stripe_request_ctx ctx = {}; const int rw = bio_data_dir(bi); - DEFINE_WAIT(w); - bool do_prepare; - bool do_flush = false; + enum stripe_result res; + int s, stripe_cnt; if (unlikely(bi->bi_opf & REQ_PREFLUSH)) { int ret = log_handle_flush_request(conf, bi); @@ -5811,7 +6104,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) * if r5l_handle_flush_request() didn't clear REQ_PREFLUSH, * we need to flush journal device */ - do_flush = bi->bi_opf & REQ_PREFLUSH; + ctx.do_flush = bi->bi_opf & REQ_PREFLUSH; } if (!md_write_start(mddev, bi)) @@ -5835,134 +6128,68 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) } logical_sector = bi->bi_iter.bi_sector & ~((sector_t)RAID5_STRIPE_SECTORS(conf)-1); - last_sector = bio_end_sector(bi); + ctx.first_sector = logical_sector; + ctx.last_sector = bio_end_sector(bi); bi->bi_next = NULL; + stripe_cnt = DIV_ROUND_UP_SECTOR_T(ctx.last_sector - logical_sector, + RAID5_STRIPE_SECTORS(conf)); + bitmap_set(ctx.sectors_to_do, 0, stripe_cnt); + + pr_debug("raid456: %s, logical %llu to %llu\n", __func__, + bi->bi_iter.bi_sector, ctx.last_sector); + /* Bail out if conflicts with reshape and REQ_NOWAIT is set */ if ((bi->bi_opf & REQ_NOWAIT) && (conf->reshape_progress != MaxSector) && - (mddev->reshape_backwards - ? (logical_sector > conf->reshape_progress && logical_sector <= conf->reshape_safe) - : (logical_sector >= conf->reshape_safe && logical_sector < conf->reshape_progress))) { + !ahead_of_reshape(mddev, logical_sector, conf->reshape_progress) && + ahead_of_reshape(mddev, logical_sector, conf->reshape_safe)) { bio_wouldblock_error(bi); if (rw == WRITE) md_write_end(mddev); return true; } md_account_bio(mddev, &bi); - prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); - for (; logical_sector < last_sector; logical_sector += RAID5_STRIPE_SECTORS(conf)) { - int previous; - int seq; - do_prepare = false; - retry: - seq = read_seqcount_begin(&conf->gen_lock); - previous = 0; - if (do_prepare) - prepare_to_wait(&conf->wait_for_overlap, &w, - TASK_UNINTERRUPTIBLE); - if (unlikely(conf->reshape_progress != MaxSector)) { - /* spinlock is needed as reshape_progress may be - * 64bit on a 32bit platform, and so it might be - * possible to see a half-updated value - * Of course reshape_progress could change after - * the lock is dropped, so once we get a reference - * to the stripe that we think it is, we will have - * to check again. - */ - spin_lock_irq(&conf->device_lock); - if (mddev->reshape_backwards - ? logical_sector < conf->reshape_progress - : logical_sector >= conf->reshape_progress) { - previous = 1; - } else { - if (mddev->reshape_backwards - ? logical_sector < conf->reshape_safe - : logical_sector >= conf->reshape_safe) { - spin_unlock_irq(&conf->device_lock); - schedule(); - do_prepare = true; - goto retry; - } - } - spin_unlock_irq(&conf->device_lock); - } - - new_sector = raid5_compute_sector(conf, logical_sector, - previous, - &dd_idx, NULL); - pr_debug("raid456: raid5_make_request, sector %llu logical %llu\n", - (unsigned long long)new_sector, - (unsigned long long)logical_sector); - - sh = raid5_get_active_stripe(conf, new_sector, previous, - (bi->bi_opf & REQ_RAHEAD), 0); - if (sh) { - if (unlikely(previous)) { - /* expansion might have moved on while waiting for a - * stripe, so we must do the range check again. - * Expansion could still move past after this - * test, but as we are holding a reference to - * 'sh', we know that if that happens, - * STRIPE_EXPANDING will get set and the expansion - * won't proceed until we finish with the stripe. - */ - int must_retry = 0; - spin_lock_irq(&conf->device_lock); - if (mddev->reshape_backwards - ? logical_sector >= conf->reshape_progress - : logical_sector < conf->reshape_progress) - /* mismatch, need to try again */ - must_retry = 1; - spin_unlock_irq(&conf->device_lock); - if (must_retry) { - raid5_release_stripe(sh); - schedule(); - do_prepare = true; - goto retry; - } - } - if (read_seqcount_retry(&conf->gen_lock, seq)) { - /* Might have got the wrong stripe_head - * by accident - */ - raid5_release_stripe(sh); - goto retry; - } - - if (test_bit(STRIPE_EXPANDING, &sh->state) || - !add_stripe_bio(sh, bi, dd_idx, rw, previous)) { - /* Stripe is busy expanding or - * add failed due to overlap. Flush everything - * and wait a while - */ - md_wakeup_thread(mddev->thread); - raid5_release_stripe(sh); - schedule(); - do_prepare = true; - goto retry; - } - if (do_flush) { - set_bit(STRIPE_R5C_PREFLUSH, &sh->state); - /* we only need flush for one stripe */ - do_flush = false; - } - - set_bit(STRIPE_HANDLE, &sh->state); - clear_bit(STRIPE_DELAYED, &sh->state); - if ((!sh->batch_head || sh == sh->batch_head) && - (bi->bi_opf & REQ_SYNC) && - !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) - atomic_inc(&conf->preread_active_stripes); - release_stripe_plug(mddev, sh); - } else { - /* cannot get stripe for read-ahead, just give-up */ - bi->bi_status = BLK_STS_IOERR; + add_wait_queue(&conf->wait_for_overlap, &wait); + while (1) { + res = make_stripe_request(mddev, conf, &ctx, logical_sector, + bi); + if (res == STRIPE_FAIL) break; + + if (res == STRIPE_RETRY) + continue; + + if (res == STRIPE_SCHEDULE_AND_RETRY) { + /* + * Must release the reference to batch_last before + * scheduling and waiting for work to be done, + * otherwise the batch_last stripe head could prevent + * raid5_activate_delayed() from making progress + * and thus deadlocking. + */ + if (ctx.batch_last) { + raid5_release_stripe(ctx.batch_last); + ctx.batch_last = NULL; + } + + wait_woken(&wait, TASK_UNINTERRUPTIBLE, + MAX_SCHEDULE_TIMEOUT); + continue; } + + s = find_first_bit(ctx.sectors_to_do, stripe_cnt); + if (s == stripe_cnt) + break; + + logical_sector = ctx.first_sector + + (s << RAID5_STRIPE_SHIFT(conf)); } - finish_wait(&conf->wait_for_overlap, &w); + remove_wait_queue(&conf->wait_for_overlap, &wait); + + if (ctx.batch_last) + raid5_release_stripe(ctx.batch_last); if (rw == WRITE) md_write_end(mddev); @@ -7815,7 +8042,15 @@ static int raid5_run(struct mddev *mddev) mddev->queue->limits.discard_granularity < stripe) blk_queue_max_discard_sectors(mddev->queue, 0); - blk_queue_max_hw_sectors(mddev->queue, UINT_MAX); + /* + * Requests require having a bitmap for each stripe. + * Limit the max sectors based on this. + */ + blk_queue_max_hw_sectors(mddev->queue, + RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf)); + + /* No restrictions on the number of segments in the request */ + blk_queue_max_segments(mddev->queue, USHRT_MAX); } if (log_init(conf, journal_dev, raid5_has_ppl(conf))) @@ -8066,8 +8301,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) * find the disk ... but prefer rdev->saved_raid_disk * if possible. */ - if (rdev->saved_raid_disk >= 0 && - rdev->saved_raid_disk >= first && + if (rdev->saved_raid_disk >= first && rdev->saved_raid_disk <= last && conf->disks[rdev->saved_raid_disk].rdev == NULL) first = rdev->saved_raid_disk; @@ -8704,8 +8938,11 @@ static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf) err = log_init(conf, NULL, true); if (!err) { err = resize_stripes(conf, conf->pool_size); - if (err) + if (err) { + mddev_suspend(mddev); log_exit(conf); + mddev_resume(mddev); + } } } else err = -EINVAL; diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 638d29863503..a5082bed83c8 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -812,7 +812,7 @@ extern sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector, struct stripe_head *sh); extern struct stripe_head * raid5_get_active_stripe(struct r5conf *conf, sector_t sector, - int previous, int noblock, int noquiesce); + bool previous, bool noblock, bool noquiesce); extern int raid5_calc_degraded(struct r5conf *conf); extern int r5c_journal_mode_set(struct mddev *mddev, int journal_mode); #endif diff --git a/drivers/nvme/Kconfig b/drivers/nvme/Kconfig index 87ae409a32b9..656e46d938da 100644 --- a/drivers/nvme/Kconfig +++ b/drivers/nvme/Kconfig @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only menu "NVME Support" +source "drivers/nvme/common/Kconfig" source "drivers/nvme/host/Kconfig" source "drivers/nvme/target/Kconfig" diff --git a/drivers/nvme/Makefile b/drivers/nvme/Makefile index fb42c44609a8..eedca8c72098 100644 --- a/drivers/nvme/Makefile +++ b/drivers/nvme/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_NVME_COMMON) += common/ obj-y += host/ obj-y += target/ diff --git a/drivers/nvme/common/Kconfig b/drivers/nvme/common/Kconfig new file mode 100644 index 000000000000..4514f44362dd --- /dev/null +++ b/drivers/nvme/common/Kconfig @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config NVME_COMMON + tristate diff --git a/drivers/nvme/common/Makefile b/drivers/nvme/common/Makefile new file mode 100644 index 000000000000..720c625b8a52 --- /dev/null +++ b/drivers/nvme/common/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +ccflags-y += -I$(src) + +obj-$(CONFIG_NVME_COMMON) += nvme-common.o + +nvme-common-y += auth.o diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c new file mode 100644 index 000000000000..04bd28f17dcc --- /dev/null +++ b/drivers/nvme/common/auth.c @@ -0,0 +1,483 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020 Hannes Reinecke, SUSE Linux + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static u32 nvme_dhchap_seqnum; +static DEFINE_MUTEX(nvme_dhchap_mutex); + +u32 nvme_auth_get_seqnum(void) +{ + u32 seqnum; + + mutex_lock(&nvme_dhchap_mutex); + if (!nvme_dhchap_seqnum) + nvme_dhchap_seqnum = prandom_u32(); + else { + nvme_dhchap_seqnum++; + if (!nvme_dhchap_seqnum) + nvme_dhchap_seqnum++; + } + seqnum = nvme_dhchap_seqnum; + mutex_unlock(&nvme_dhchap_mutex); + return seqnum; +} +EXPORT_SYMBOL_GPL(nvme_auth_get_seqnum); + +static struct nvme_auth_dhgroup_map { + const char name[16]; + const char kpp[16]; +} dhgroup_map[] = { + [NVME_AUTH_DHGROUP_NULL] = { + .name = "null", .kpp = "null" }, + [NVME_AUTH_DHGROUP_2048] = { + .name = "ffdhe2048", .kpp = "ffdhe2048(dh)" }, + [NVME_AUTH_DHGROUP_3072] = { + .name = "ffdhe3072", .kpp = "ffdhe3072(dh)" }, + [NVME_AUTH_DHGROUP_4096] = { + .name = "ffdhe4096", .kpp = "ffdhe4096(dh)" }, + [NVME_AUTH_DHGROUP_6144] = { + .name = "ffdhe6144", .kpp = "ffdhe6144(dh)" }, + [NVME_AUTH_DHGROUP_8192] = { + .name = "ffdhe8192", .kpp = "ffdhe8192(dh)" }, +}; + +const char *nvme_auth_dhgroup_name(u8 dhgroup_id) +{ + if (dhgroup_id >= ARRAY_SIZE(dhgroup_map)) + return NULL; + return dhgroup_map[dhgroup_id].name; +} +EXPORT_SYMBOL_GPL(nvme_auth_dhgroup_name); + +const char *nvme_auth_dhgroup_kpp(u8 dhgroup_id) +{ + if (dhgroup_id >= ARRAY_SIZE(dhgroup_map)) + return NULL; + return dhgroup_map[dhgroup_id].kpp; +} +EXPORT_SYMBOL_GPL(nvme_auth_dhgroup_kpp); + +u8 nvme_auth_dhgroup_id(const char *dhgroup_name) +{ + int i; + + if (!dhgroup_name || !strlen(dhgroup_name)) + return NVME_AUTH_DHGROUP_INVALID; + for (i = 0; i < ARRAY_SIZE(dhgroup_map); i++) { + if (!strlen(dhgroup_map[i].name)) + continue; + if (!strncmp(dhgroup_map[i].name, dhgroup_name, + strlen(dhgroup_map[i].name))) + return i; + } + return NVME_AUTH_DHGROUP_INVALID; +} +EXPORT_SYMBOL_GPL(nvme_auth_dhgroup_id); + +static struct nvme_dhchap_hash_map { + int len; + const char hmac[15]; + const char digest[8]; +} hash_map[] = { + [NVME_AUTH_HASH_SHA256] = { + .len = 32, + .hmac = "hmac(sha256)", + .digest = "sha256", + }, + [NVME_AUTH_HASH_SHA384] = { + .len = 48, + .hmac = "hmac(sha384)", + .digest = "sha384", + }, + [NVME_AUTH_HASH_SHA512] = { + .len = 64, + .hmac = "hmac(sha512)", + .digest = "sha512", + }, +}; + +const char *nvme_auth_hmac_name(u8 hmac_id) +{ + if (hmac_id >= ARRAY_SIZE(hash_map)) + return NULL; + return hash_map[hmac_id].hmac; +} +EXPORT_SYMBOL_GPL(nvme_auth_hmac_name); + +const char *nvme_auth_digest_name(u8 hmac_id) +{ + if (hmac_id >= ARRAY_SIZE(hash_map)) + return NULL; + return hash_map[hmac_id].digest; +} +EXPORT_SYMBOL_GPL(nvme_auth_digest_name); + +u8 nvme_auth_hmac_id(const char *hmac_name) +{ + int i; + + if (!hmac_name || !strlen(hmac_name)) + return NVME_AUTH_HASH_INVALID; + + for (i = 0; i < ARRAY_SIZE(hash_map); i++) { + if (!strlen(hash_map[i].hmac)) + continue; + if (!strncmp(hash_map[i].hmac, hmac_name, + strlen(hash_map[i].hmac))) + return i; + } + return NVME_AUTH_HASH_INVALID; +} +EXPORT_SYMBOL_GPL(nvme_auth_hmac_id); + +size_t nvme_auth_hmac_hash_len(u8 hmac_id) +{ + if (hmac_id >= ARRAY_SIZE(hash_map)) + return 0; + return hash_map[hmac_id].len; +} +EXPORT_SYMBOL_GPL(nvme_auth_hmac_hash_len); + +struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret, + u8 key_hash) +{ + struct nvme_dhchap_key *key; + unsigned char *p; + u32 crc; + int ret, key_len; + size_t allocated_len = strlen(secret); + + /* Secret might be affixed with a ':' */ + p = strrchr(secret, ':'); + if (p) + allocated_len = p - secret; + key = kzalloc(sizeof(*key), GFP_KERNEL); + if (!key) + return ERR_PTR(-ENOMEM); + key->key = kzalloc(allocated_len, GFP_KERNEL); + if (!key->key) { + ret = -ENOMEM; + goto out_free_key; + } + + key_len = base64_decode(secret, allocated_len, key->key); + if (key_len < 0) { + pr_debug("base64 key decoding error %d\n", + key_len); + ret = key_len; + goto out_free_secret; + } + + if (key_len != 36 && key_len != 52 && + key_len != 68) { + pr_err("Invalid key len %d\n", key_len); + ret = -EINVAL; + goto out_free_secret; + } + + if (key_hash > 0 && + (key_len - 4) != nvme_auth_hmac_hash_len(key_hash)) { + pr_err("Mismatched key len %d for %s\n", key_len, + nvme_auth_hmac_name(key_hash)); + ret = -EINVAL; + goto out_free_secret; + } + + /* The last four bytes is the CRC in little-endian format */ + key_len -= 4; + /* + * The linux implementation doesn't do pre- and post-increments, + * so we have to do it manually. + */ + crc = ~crc32(~0, key->key, key_len); + + if (get_unaligned_le32(key->key + key_len) != crc) { + pr_err("key crc mismatch (key %08x, crc %08x)\n", + get_unaligned_le32(key->key + key_len), crc); + ret = -EKEYREJECTED; + goto out_free_secret; + } + key->len = key_len; + key->hash = key_hash; + return key; +out_free_secret: + kfree_sensitive(key->key); +out_free_key: + kfree(key); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(nvme_auth_extract_key); + +void nvme_auth_free_key(struct nvme_dhchap_key *key) +{ + if (!key) + return; + kfree_sensitive(key->key); + kfree(key); +} +EXPORT_SYMBOL_GPL(nvme_auth_free_key); + +u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn) +{ + const char *hmac_name; + struct crypto_shash *key_tfm; + struct shash_desc *shash; + u8 *transformed_key; + int ret; + + if (!key || !key->key) { + pr_warn("No key specified\n"); + return ERR_PTR(-ENOKEY); + } + if (key->hash == 0) { + transformed_key = kmemdup(key->key, key->len, GFP_KERNEL); + return transformed_key ? transformed_key : ERR_PTR(-ENOMEM); + } + hmac_name = nvme_auth_hmac_name(key->hash); + if (!hmac_name) { + pr_warn("Invalid key hash id %d\n", key->hash); + return ERR_PTR(-EINVAL); + } + + key_tfm = crypto_alloc_shash(hmac_name, 0, 0); + if (IS_ERR(key_tfm)) + return (u8 *)key_tfm; + + shash = kmalloc(sizeof(struct shash_desc) + + crypto_shash_descsize(key_tfm), + GFP_KERNEL); + if (!shash) { + ret = -ENOMEM; + goto out_free_key; + } + + transformed_key = kzalloc(crypto_shash_digestsize(key_tfm), GFP_KERNEL); + if (!transformed_key) { + ret = -ENOMEM; + goto out_free_shash; + } + + shash->tfm = key_tfm; + ret = crypto_shash_setkey(key_tfm, key->key, key->len); + if (ret < 0) + goto out_free_transformed_key; + ret = crypto_shash_init(shash); + if (ret < 0) + goto out_free_transformed_key; + ret = crypto_shash_update(shash, nqn, strlen(nqn)); + if (ret < 0) + goto out_free_transformed_key; + ret = crypto_shash_update(shash, "NVMe-over-Fabrics", 17); + if (ret < 0) + goto out_free_transformed_key; + ret = crypto_shash_final(shash, transformed_key); + if (ret < 0) + goto out_free_transformed_key; + + kfree(shash); + crypto_free_shash(key_tfm); + + return transformed_key; + +out_free_transformed_key: + kfree_sensitive(transformed_key); +out_free_shash: + kfree(shash); +out_free_key: + crypto_free_shash(key_tfm); + + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(nvme_auth_transform_key); + +static int nvme_auth_hash_skey(int hmac_id, u8 *skey, size_t skey_len, u8 *hkey) +{ + const char *digest_name; + struct crypto_shash *tfm; + int ret; + + digest_name = nvme_auth_digest_name(hmac_id); + if (!digest_name) { + pr_debug("%s: failed to get digest for %d\n", __func__, + hmac_id); + return -EINVAL; + } + tfm = crypto_alloc_shash(digest_name, 0, 0); + if (IS_ERR(tfm)) + return -ENOMEM; + + ret = crypto_shash_tfm_digest(tfm, skey, skey_len, hkey); + if (ret < 0) + pr_debug("%s: Failed to hash digest len %zu\n", __func__, + skey_len); + + crypto_free_shash(tfm); + return ret; +} + +int nvme_auth_augmented_challenge(u8 hmac_id, u8 *skey, size_t skey_len, + u8 *challenge, u8 *aug, size_t hlen) +{ + struct crypto_shash *tfm; + struct shash_desc *desc; + u8 *hashed_key; + const char *hmac_name; + int ret; + + hashed_key = kmalloc(hlen, GFP_KERNEL); + if (!hashed_key) + return -ENOMEM; + + ret = nvme_auth_hash_skey(hmac_id, skey, + skey_len, hashed_key); + if (ret < 0) + goto out_free_key; + + hmac_name = nvme_auth_hmac_name(hmac_id); + if (!hmac_name) { + pr_warn("%s: invalid hash algorithm %d\n", + __func__, hmac_id); + ret = -EINVAL; + goto out_free_key; + } + + tfm = crypto_alloc_shash(hmac_name, 0, 0); + if (IS_ERR(tfm)) { + ret = PTR_ERR(tfm); + goto out_free_key; + } + + desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm), + GFP_KERNEL); + if (!desc) { + ret = -ENOMEM; + goto out_free_hash; + } + desc->tfm = tfm; + + ret = crypto_shash_setkey(tfm, hashed_key, hlen); + if (ret) + goto out_free_desc; + + ret = crypto_shash_init(desc); + if (ret) + goto out_free_desc; + + ret = crypto_shash_update(desc, challenge, hlen); + if (ret) + goto out_free_desc; + + ret = crypto_shash_final(desc, aug); +out_free_desc: + kfree_sensitive(desc); +out_free_hash: + crypto_free_shash(tfm); +out_free_key: + kfree_sensitive(hashed_key); + return ret; +} +EXPORT_SYMBOL_GPL(nvme_auth_augmented_challenge); + +int nvme_auth_gen_privkey(struct crypto_kpp *dh_tfm, u8 dh_gid) +{ + int ret; + + ret = crypto_kpp_set_secret(dh_tfm, NULL, 0); + if (ret) + pr_debug("failed to set private key, error %d\n", ret); + + return ret; +} +EXPORT_SYMBOL_GPL(nvme_auth_gen_privkey); + +int nvme_auth_gen_pubkey(struct crypto_kpp *dh_tfm, + u8 *host_key, size_t host_key_len) +{ + struct kpp_request *req; + struct crypto_wait wait; + struct scatterlist dst; + int ret; + + req = kpp_request_alloc(dh_tfm, GFP_KERNEL); + if (!req) + return -ENOMEM; + + crypto_init_wait(&wait); + kpp_request_set_input(req, NULL, 0); + sg_init_one(&dst, host_key, host_key_len); + kpp_request_set_output(req, &dst, host_key_len); + kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + crypto_req_done, &wait); + + ret = crypto_wait_req(crypto_kpp_generate_public_key(req), &wait); + kpp_request_free(req); + return ret; +} +EXPORT_SYMBOL_GPL(nvme_auth_gen_pubkey); + +int nvme_auth_gen_shared_secret(struct crypto_kpp *dh_tfm, + u8 *ctrl_key, size_t ctrl_key_len, + u8 *sess_key, size_t sess_key_len) +{ + struct kpp_request *req; + struct crypto_wait wait; + struct scatterlist src, dst; + int ret; + + req = kpp_request_alloc(dh_tfm, GFP_KERNEL); + if (!req) + return -ENOMEM; + + crypto_init_wait(&wait); + sg_init_one(&src, ctrl_key, ctrl_key_len); + kpp_request_set_input(req, &src, ctrl_key_len); + sg_init_one(&dst, sess_key, sess_key_len); + kpp_request_set_output(req, &dst, sess_key_len); + kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + crypto_req_done, &wait); + + ret = crypto_wait_req(crypto_kpp_compute_shared_secret(req), &wait); + + kpp_request_free(req); + return ret; +} +EXPORT_SYMBOL_GPL(nvme_auth_gen_shared_secret); + +int nvme_auth_generate_key(u8 *secret, struct nvme_dhchap_key **ret_key) +{ + struct nvme_dhchap_key *key; + u8 key_hash; + + if (!secret) { + *ret_key = NULL; + return 0; + } + + if (sscanf(secret, "DHHC-1:%hhd:%*s:", &key_hash) != 1) + return -EINVAL; + + /* Pass in the secret without the 'DHHC-1:XX:' prefix */ + key = nvme_auth_extract_key(secret + 10, key_hash); + if (IS_ERR(key)) { + *ret_key = NULL; + return PTR_ERR(key); + } + + *ret_key = key; + return 0; +} +EXPORT_SYMBOL_GPL(nvme_auth_generate_key); + +MODULE_LICENSE("GPL v2"); diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 877d2ec4ea9f..2f6a7f8c94e8 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -92,6 +92,21 @@ config NVME_TCP If unsure, say N. +config NVME_AUTH + bool "NVM Express over Fabrics In-Band Authentication" + depends on NVME_CORE + select NVME_COMMON + select CRYPTO + select CRYPTO_HMAC + select CRYPTO_SHA256 + select CRYPTO_SHA512 + select CRYPTO_DH + select CRYPTO_DH_RFC7919_GROUPS + help + This provides support for NVMe over Fabrics In-Band Authentication. + + If unsure, say N. + config NVME_APPLE tristate "Apple ANS2 NVM Express host driver" depends on OF && BLOCK diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile index a36ae1612059..e27202d22c7d 100644 --- a/drivers/nvme/host/Makefile +++ b/drivers/nvme/host/Makefile @@ -10,12 +10,14 @@ obj-$(CONFIG_NVME_FC) += nvme-fc.o obj-$(CONFIG_NVME_TCP) += nvme-tcp.o obj-$(CONFIG_NVME_APPLE) += nvme-apple.o -nvme-core-y := core.o ioctl.o constants.o +nvme-core-y += core.o ioctl.o +nvme-core-$(CONFIG_NVME_VERBOSE_ERRORS) += constants.o nvme-core-$(CONFIG_TRACING) += trace.o nvme-core-$(CONFIG_NVME_MULTIPATH) += multipath.o nvme-core-$(CONFIG_BLK_DEV_ZONED) += zns.o nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS) += fault_inject.o nvme-core-$(CONFIG_NVME_HWMON) += hwmon.o +nvme-core-$(CONFIG_NVME_AUTH) += auth.o nvme-y += pci.o diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index 5c352d5d8ee6..5fc5ea196b40 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -845,11 +845,8 @@ static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown) apple_nvme_handle_cq(&anv->adminq, true); spin_unlock_irqrestore(&anv->lock, flags); - blk_mq_tagset_busy_iter(&anv->tagset, nvme_cancel_request, &anv->ctrl); - blk_mq_tagset_busy_iter(&anv->admin_tagset, nvme_cancel_request, - &anv->ctrl); - blk_mq_tagset_wait_completed_request(&anv->tagset); - blk_mq_tagset_wait_completed_request(&anv->admin_tagset); + nvme_cancel_tagset(&anv->ctrl); + nvme_cancel_admin_tagset(&anv->ctrl); /* * The driver will not be starting up queues again if shutting down so @@ -1222,6 +1219,11 @@ static void apple_nvme_async_probe(void *data, async_cookie_t cookie) nvme_put_ctrl(&anv->ctrl); } +static void devm_apple_nvme_put_tag_set(void *data) +{ + blk_mq_free_tag_set(data); +} + static int apple_nvme_alloc_tagsets(struct apple_nvme *anv) { int ret; @@ -1238,8 +1240,7 @@ static int apple_nvme_alloc_tagsets(struct apple_nvme *anv) ret = blk_mq_alloc_tag_set(&anv->admin_tagset); if (ret) return ret; - ret = devm_add_action_or_reset(anv->dev, - (void (*)(void *))blk_mq_free_tag_set, + ret = devm_add_action_or_reset(anv->dev, devm_apple_nvme_put_tag_set, &anv->admin_tagset); if (ret) return ret; @@ -1263,8 +1264,8 @@ static int apple_nvme_alloc_tagsets(struct apple_nvme *anv) ret = blk_mq_alloc_tag_set(&anv->tagset); if (ret) return ret; - ret = devm_add_action_or_reset( - anv->dev, (void (*)(void *))blk_mq_free_tag_set, &anv->tagset); + ret = devm_add_action_or_reset(anv->dev, devm_apple_nvme_put_tag_set, + &anv->tagset); if (ret) return ret; @@ -1365,6 +1366,11 @@ static int apple_nvme_attach_genpd(struct apple_nvme *anv) return 0; } +static void devm_apple_nvme_mempool_destroy(void *data) +{ + mempool_destroy(data); +} + static int apple_nvme_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1462,8 +1468,8 @@ static int apple_nvme_probe(struct platform_device *pdev) ret = -ENOMEM; goto put_dev; } - ret = devm_add_action_or_reset( - anv->dev, (void (*)(void *))mempool_destroy, anv->iod_mempool); + ret = devm_add_action_or_reset(anv->dev, + devm_apple_nvme_mempool_destroy, anv->iod_mempool); if (ret) goto put_dev; diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c new file mode 100644 index 000000000000..c8a6db7c4498 --- /dev/null +++ b/drivers/nvme/host/auth.c @@ -0,0 +1,1017 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020 Hannes Reinecke, SUSE Linux + */ + +#include +#include +#include +#include +#include +#include +#include "nvme.h" +#include "fabrics.h" +#include + +struct nvme_dhchap_queue_context { + struct list_head entry; + struct work_struct auth_work; + struct nvme_ctrl *ctrl; + struct crypto_shash *shash_tfm; + struct crypto_kpp *dh_tfm; + void *buf; + size_t buf_size; + int qid; + int error; + u32 s1; + u32 s2; + u16 transaction; + u8 status; + u8 hash_id; + size_t hash_len; + u8 dhgroup_id; + u8 c1[64]; + u8 c2[64]; + u8 response[64]; + u8 *host_response; + u8 *ctrl_key; + int ctrl_key_len; + u8 *host_key; + int host_key_len; + u8 *sess_key; + int sess_key_len; +}; + +#define nvme_auth_flags_from_qid(qid) \ + (qid == 0) ? 0 : BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED +#define nvme_auth_queue_from_qid(ctrl, qid) \ + (qid == 0) ? (ctrl)->fabrics_q : (ctrl)->connect_q + +static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid, + void *data, size_t data_len, bool auth_send) +{ + struct nvme_command cmd = {}; + blk_mq_req_flags_t flags = nvme_auth_flags_from_qid(qid); + struct request_queue *q = nvme_auth_queue_from_qid(ctrl, qid); + int ret; + + cmd.auth_common.opcode = nvme_fabrics_command; + cmd.auth_common.secp = NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER; + cmd.auth_common.spsp0 = 0x01; + cmd.auth_common.spsp1 = 0x01; + if (auth_send) { + cmd.auth_send.fctype = nvme_fabrics_type_auth_send; + cmd.auth_send.tl = cpu_to_le32(data_len); + } else { + cmd.auth_receive.fctype = nvme_fabrics_type_auth_receive; + cmd.auth_receive.al = cpu_to_le32(data_len); + } + + ret = __nvme_submit_sync_cmd(q, &cmd, NULL, data, data_len, + qid == 0 ? NVME_QID_ANY : qid, + 0, flags); + if (ret > 0) + dev_warn(ctrl->device, + "qid %d auth_send failed with status %d\n", qid, ret); + else if (ret < 0) + dev_err(ctrl->device, + "qid %d auth_send failed with error %d\n", qid, ret); + return ret; +} + +static int nvme_auth_receive_validate(struct nvme_ctrl *ctrl, int qid, + struct nvmf_auth_dhchap_failure_data *data, + u16 transaction, u8 expected_msg) +{ + dev_dbg(ctrl->device, "%s: qid %d auth_type %d auth_id %x\n", + __func__, qid, data->auth_type, data->auth_id); + + if (data->auth_type == NVME_AUTH_COMMON_MESSAGES && + data->auth_id == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) { + return data->rescode_exp; + } + if (data->auth_type != NVME_AUTH_DHCHAP_MESSAGES || + data->auth_id != expected_msg) { + dev_warn(ctrl->device, + "qid %d invalid message %02x/%02x\n", + qid, data->auth_type, data->auth_id); + return NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE; + } + if (le16_to_cpu(data->t_id) != transaction) { + dev_warn(ctrl->device, + "qid %d invalid transaction ID %d\n", + qid, le16_to_cpu(data->t_id)); + return NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE; + } + return 0; +} + +static int nvme_auth_set_dhchap_negotiate_data(struct nvme_ctrl *ctrl, + struct nvme_dhchap_queue_context *chap) +{ + struct nvmf_auth_dhchap_negotiate_data *data = chap->buf; + size_t size = sizeof(*data) + sizeof(union nvmf_auth_protocol); + + if (chap->buf_size < size) { + chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; + return -EINVAL; + } + memset((u8 *)chap->buf, 0, size); + data->auth_type = NVME_AUTH_COMMON_MESSAGES; + data->auth_id = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE; + data->t_id = cpu_to_le16(chap->transaction); + data->sc_c = 0; /* No secure channel concatenation */ + data->napd = 1; + data->auth_protocol[0].dhchap.authid = NVME_AUTH_DHCHAP_AUTH_ID; + data->auth_protocol[0].dhchap.halen = 3; + data->auth_protocol[0].dhchap.dhlen = 6; + data->auth_protocol[0].dhchap.idlist[0] = NVME_AUTH_HASH_SHA256; + data->auth_protocol[0].dhchap.idlist[1] = NVME_AUTH_HASH_SHA384; + data->auth_protocol[0].dhchap.idlist[2] = NVME_AUTH_HASH_SHA512; + data->auth_protocol[0].dhchap.idlist[30] = NVME_AUTH_DHGROUP_NULL; + data->auth_protocol[0].dhchap.idlist[31] = NVME_AUTH_DHGROUP_2048; + data->auth_protocol[0].dhchap.idlist[32] = NVME_AUTH_DHGROUP_3072; + data->auth_protocol[0].dhchap.idlist[33] = NVME_AUTH_DHGROUP_4096; + data->auth_protocol[0].dhchap.idlist[34] = NVME_AUTH_DHGROUP_6144; + data->auth_protocol[0].dhchap.idlist[35] = NVME_AUTH_DHGROUP_8192; + + return size; +} + +static int nvme_auth_process_dhchap_challenge(struct nvme_ctrl *ctrl, + struct nvme_dhchap_queue_context *chap) +{ + struct nvmf_auth_dhchap_challenge_data *data = chap->buf; + u16 dhvlen = le16_to_cpu(data->dhvlen); + size_t size = sizeof(*data) + data->hl + dhvlen; + const char *gid_name = nvme_auth_dhgroup_name(data->dhgid); + const char *hmac_name, *kpp_name; + + if (chap->buf_size < size) { + chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; + return NVME_SC_INVALID_FIELD; + } + + hmac_name = nvme_auth_hmac_name(data->hashid); + if (!hmac_name) { + dev_warn(ctrl->device, + "qid %d: invalid HASH ID %d\n", + chap->qid, data->hashid); + chap->status = NVME_AUTH_DHCHAP_FAILURE_HASH_UNUSABLE; + return NVME_SC_INVALID_FIELD; + } + + if (chap->hash_id == data->hashid && chap->shash_tfm && + !strcmp(crypto_shash_alg_name(chap->shash_tfm), hmac_name) && + crypto_shash_digestsize(chap->shash_tfm) == data->hl) { + dev_dbg(ctrl->device, + "qid %d: reuse existing hash %s\n", + chap->qid, hmac_name); + goto select_kpp; + } + + /* Reset if hash cannot be reused */ + if (chap->shash_tfm) { + crypto_free_shash(chap->shash_tfm); + chap->hash_id = 0; + chap->hash_len = 0; + } + chap->shash_tfm = crypto_alloc_shash(hmac_name, 0, + CRYPTO_ALG_ALLOCATES_MEMORY); + if (IS_ERR(chap->shash_tfm)) { + dev_warn(ctrl->device, + "qid %d: failed to allocate hash %s, error %ld\n", + chap->qid, hmac_name, PTR_ERR(chap->shash_tfm)); + chap->shash_tfm = NULL; + chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED; + return NVME_SC_AUTH_REQUIRED; + } + + if (crypto_shash_digestsize(chap->shash_tfm) != data->hl) { + dev_warn(ctrl->device, + "qid %d: invalid hash length %d\n", + chap->qid, data->hl); + crypto_free_shash(chap->shash_tfm); + chap->shash_tfm = NULL; + chap->status = NVME_AUTH_DHCHAP_FAILURE_HASH_UNUSABLE; + return NVME_SC_AUTH_REQUIRED; + } + + /* Reset host response if the hash had been changed */ + if (chap->hash_id != data->hashid) { + kfree(chap->host_response); + chap->host_response = NULL; + } + + chap->hash_id = data->hashid; + chap->hash_len = data->hl; + dev_dbg(ctrl->device, "qid %d: selected hash %s\n", + chap->qid, hmac_name); + +select_kpp: + kpp_name = nvme_auth_dhgroup_kpp(data->dhgid); + if (!kpp_name) { + dev_warn(ctrl->device, + "qid %d: invalid DH group id %d\n", + chap->qid, data->dhgid); + chap->status = NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE; + /* Leave previous dh_tfm intact */ + return NVME_SC_AUTH_REQUIRED; + } + + /* Clear host and controller key to avoid accidental reuse */ + kfree_sensitive(chap->host_key); + chap->host_key = NULL; + chap->host_key_len = 0; + kfree_sensitive(chap->ctrl_key); + chap->ctrl_key = NULL; + chap->ctrl_key_len = 0; + + if (chap->dhgroup_id == data->dhgid && + (data->dhgid == NVME_AUTH_DHGROUP_NULL || chap->dh_tfm)) { + dev_dbg(ctrl->device, + "qid %d: reuse existing DH group %s\n", + chap->qid, gid_name); + goto skip_kpp; + } + + /* Reset dh_tfm if it can't be reused */ + if (chap->dh_tfm) { + crypto_free_kpp(chap->dh_tfm); + chap->dh_tfm = NULL; + } + + if (data->dhgid != NVME_AUTH_DHGROUP_NULL) { + if (dhvlen == 0) { + dev_warn(ctrl->device, + "qid %d: empty DH value\n", + chap->qid); + chap->status = NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE; + return NVME_SC_INVALID_FIELD; + } + + chap->dh_tfm = crypto_alloc_kpp(kpp_name, 0, 0); + if (IS_ERR(chap->dh_tfm)) { + int ret = PTR_ERR(chap->dh_tfm); + + dev_warn(ctrl->device, + "qid %d: error %d initializing DH group %s\n", + chap->qid, ret, gid_name); + chap->status = NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE; + chap->dh_tfm = NULL; + return NVME_SC_AUTH_REQUIRED; + } + dev_dbg(ctrl->device, "qid %d: selected DH group %s\n", + chap->qid, gid_name); + } else if (dhvlen != 0) { + dev_warn(ctrl->device, + "qid %d: invalid DH value for NULL DH\n", + chap->qid); + chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; + return NVME_SC_INVALID_FIELD; + } + chap->dhgroup_id = data->dhgid; + +skip_kpp: + chap->s1 = le32_to_cpu(data->seqnum); + memcpy(chap->c1, data->cval, chap->hash_len); + if (dhvlen) { + chap->ctrl_key = kmalloc(dhvlen, GFP_KERNEL); + if (!chap->ctrl_key) { + chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED; + return NVME_SC_AUTH_REQUIRED; + } + chap->ctrl_key_len = dhvlen; + memcpy(chap->ctrl_key, data->cval + chap->hash_len, + dhvlen); + dev_dbg(ctrl->device, "ctrl public key %*ph\n", + (int)chap->ctrl_key_len, chap->ctrl_key); + } + + return 0; +} + +static int nvme_auth_set_dhchap_reply_data(struct nvme_ctrl *ctrl, + struct nvme_dhchap_queue_context *chap) +{ + struct nvmf_auth_dhchap_reply_data *data = chap->buf; + size_t size = sizeof(*data); + + size += 2 * chap->hash_len; + + if (chap->host_key_len) + size += chap->host_key_len; + + if (chap->buf_size < size) { + chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; + return -EINVAL; + } + + memset(chap->buf, 0, size); + data->auth_type = NVME_AUTH_DHCHAP_MESSAGES; + data->auth_id = NVME_AUTH_DHCHAP_MESSAGE_REPLY; + data->t_id = cpu_to_le16(chap->transaction); + data->hl = chap->hash_len; + data->dhvlen = cpu_to_le16(chap->host_key_len); + memcpy(data->rval, chap->response, chap->hash_len); + if (ctrl->ctrl_key) { + get_random_bytes(chap->c2, chap->hash_len); + data->cvalid = 1; + chap->s2 = nvme_auth_get_seqnum(); + memcpy(data->rval + chap->hash_len, chap->c2, + chap->hash_len); + dev_dbg(ctrl->device, "%s: qid %d ctrl challenge %*ph\n", + __func__, chap->qid, (int)chap->hash_len, chap->c2); + } else { + memset(chap->c2, 0, chap->hash_len); + chap->s2 = 0; + } + data->seqnum = cpu_to_le32(chap->s2); + if (chap->host_key_len) { + dev_dbg(ctrl->device, "%s: qid %d host public key %*ph\n", + __func__, chap->qid, + chap->host_key_len, chap->host_key); + memcpy(data->rval + 2 * chap->hash_len, chap->host_key, + chap->host_key_len); + } + + return size; +} + +static int nvme_auth_process_dhchap_success1(struct nvme_ctrl *ctrl, + struct nvme_dhchap_queue_context *chap) +{ + struct nvmf_auth_dhchap_success1_data *data = chap->buf; + size_t size = sizeof(*data); + + if (ctrl->ctrl_key) + size += chap->hash_len; + + if (chap->buf_size < size) { + chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; + return NVME_SC_INVALID_FIELD; + } + + if (data->hl != chap->hash_len) { + dev_warn(ctrl->device, + "qid %d: invalid hash length %u\n", + chap->qid, data->hl); + chap->status = NVME_AUTH_DHCHAP_FAILURE_HASH_UNUSABLE; + return NVME_SC_INVALID_FIELD; + } + + /* Just print out information for the admin queue */ + if (chap->qid == 0) + dev_info(ctrl->device, + "qid 0: authenticated with hash %s dhgroup %s\n", + nvme_auth_hmac_name(chap->hash_id), + nvme_auth_dhgroup_name(chap->dhgroup_id)); + + if (!data->rvalid) + return 0; + + /* Validate controller response */ + if (memcmp(chap->response, data->rval, data->hl)) { + dev_dbg(ctrl->device, "%s: qid %d ctrl response %*ph\n", + __func__, chap->qid, (int)chap->hash_len, data->rval); + dev_dbg(ctrl->device, "%s: qid %d host response %*ph\n", + __func__, chap->qid, (int)chap->hash_len, + chap->response); + dev_warn(ctrl->device, + "qid %d: controller authentication failed\n", + chap->qid); + chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED; + return NVME_SC_AUTH_REQUIRED; + } + + /* Just print out information for the admin queue */ + if (chap->qid == 0) + dev_info(ctrl->device, + "qid 0: controller authenticated\n"); + return 0; +} + +static int nvme_auth_set_dhchap_success2_data(struct nvme_ctrl *ctrl, + struct nvme_dhchap_queue_context *chap) +{ + struct nvmf_auth_dhchap_success2_data *data = chap->buf; + size_t size = sizeof(*data); + + memset(chap->buf, 0, size); + data->auth_type = NVME_AUTH_DHCHAP_MESSAGES; + data->auth_id = NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2; + data->t_id = cpu_to_le16(chap->transaction); + + return size; +} + +static int nvme_auth_set_dhchap_failure2_data(struct nvme_ctrl *ctrl, + struct nvme_dhchap_queue_context *chap) +{ + struct nvmf_auth_dhchap_failure_data *data = chap->buf; + size_t size = sizeof(*data); + + memset(chap->buf, 0, size); + data->auth_type = NVME_AUTH_COMMON_MESSAGES; + data->auth_id = NVME_AUTH_DHCHAP_MESSAGE_FAILURE2; + data->t_id = cpu_to_le16(chap->transaction); + data->rescode = NVME_AUTH_DHCHAP_FAILURE_REASON_FAILED; + data->rescode_exp = chap->status; + + return size; +} + +static int nvme_auth_dhchap_setup_host_response(struct nvme_ctrl *ctrl, + struct nvme_dhchap_queue_context *chap) +{ + SHASH_DESC_ON_STACK(shash, chap->shash_tfm); + u8 buf[4], *challenge = chap->c1; + int ret; + + dev_dbg(ctrl->device, "%s: qid %d host response seq %u transaction %d\n", + __func__, chap->qid, chap->s1, chap->transaction); + + if (!chap->host_response) { + chap->host_response = nvme_auth_transform_key(ctrl->host_key, + ctrl->opts->host->nqn); + if (IS_ERR(chap->host_response)) { + ret = PTR_ERR(chap->host_response); + chap->host_response = NULL; + return ret; + } + } else { + dev_dbg(ctrl->device, "%s: qid %d re-using host response\n", + __func__, chap->qid); + } + + ret = crypto_shash_setkey(chap->shash_tfm, + chap->host_response, ctrl->host_key->len); + if (ret) { + dev_warn(ctrl->device, "qid %d: failed to set key, error %d\n", + chap->qid, ret); + goto out; + } + + if (chap->dh_tfm) { + challenge = kmalloc(chap->hash_len, GFP_KERNEL); + if (!challenge) { + ret = -ENOMEM; + goto out; + } + ret = nvme_auth_augmented_challenge(chap->hash_id, + chap->sess_key, + chap->sess_key_len, + chap->c1, challenge, + chap->hash_len); + if (ret) + goto out; + } + + shash->tfm = chap->shash_tfm; + ret = crypto_shash_init(shash); + if (ret) + goto out; + ret = crypto_shash_update(shash, challenge, chap->hash_len); + if (ret) + goto out; + put_unaligned_le32(chap->s1, buf); + ret = crypto_shash_update(shash, buf, 4); + if (ret) + goto out; + put_unaligned_le16(chap->transaction, buf); + ret = crypto_shash_update(shash, buf, 2); + if (ret) + goto out; + memset(buf, 0, sizeof(buf)); + ret = crypto_shash_update(shash, buf, 1); + if (ret) + goto out; + ret = crypto_shash_update(shash, "HostHost", 8); + if (ret) + goto out; + ret = crypto_shash_update(shash, ctrl->opts->host->nqn, + strlen(ctrl->opts->host->nqn)); + if (ret) + goto out; + ret = crypto_shash_update(shash, buf, 1); + if (ret) + goto out; + ret = crypto_shash_update(shash, ctrl->opts->subsysnqn, + strlen(ctrl->opts->subsysnqn)); + if (ret) + goto out; + ret = crypto_shash_final(shash, chap->response); +out: + if (challenge != chap->c1) + kfree(challenge); + return ret; +} + +static int nvme_auth_dhchap_setup_ctrl_response(struct nvme_ctrl *ctrl, + struct nvme_dhchap_queue_context *chap) +{ + SHASH_DESC_ON_STACK(shash, chap->shash_tfm); + u8 *ctrl_response; + u8 buf[4], *challenge = chap->c2; + int ret; + + ctrl_response = nvme_auth_transform_key(ctrl->ctrl_key, + ctrl->opts->subsysnqn); + if (IS_ERR(ctrl_response)) { + ret = PTR_ERR(ctrl_response); + return ret; + } + ret = crypto_shash_setkey(chap->shash_tfm, + ctrl_response, ctrl->ctrl_key->len); + if (ret) { + dev_warn(ctrl->device, "qid %d: failed to set key, error %d\n", + chap->qid, ret); + goto out; + } + + if (chap->dh_tfm) { + challenge = kmalloc(chap->hash_len, GFP_KERNEL); + if (!challenge) { + ret = -ENOMEM; + goto out; + } + ret = nvme_auth_augmented_challenge(chap->hash_id, + chap->sess_key, + chap->sess_key_len, + chap->c2, challenge, + chap->hash_len); + if (ret) + goto out; + } + dev_dbg(ctrl->device, "%s: qid %d ctrl response seq %u transaction %d\n", + __func__, chap->qid, chap->s2, chap->transaction); + dev_dbg(ctrl->device, "%s: qid %d challenge %*ph\n", + __func__, chap->qid, (int)chap->hash_len, challenge); + dev_dbg(ctrl->device, "%s: qid %d subsysnqn %s\n", + __func__, chap->qid, ctrl->opts->subsysnqn); + dev_dbg(ctrl->device, "%s: qid %d hostnqn %s\n", + __func__, chap->qid, ctrl->opts->host->nqn); + shash->tfm = chap->shash_tfm; + ret = crypto_shash_init(shash); + if (ret) + goto out; + ret = crypto_shash_update(shash, challenge, chap->hash_len); + if (ret) + goto out; + put_unaligned_le32(chap->s2, buf); + ret = crypto_shash_update(shash, buf, 4); + if (ret) + goto out; + put_unaligned_le16(chap->transaction, buf); + ret = crypto_shash_update(shash, buf, 2); + if (ret) + goto out; + memset(buf, 0, 4); + ret = crypto_shash_update(shash, buf, 1); + if (ret) + goto out; + ret = crypto_shash_update(shash, "Controller", 10); + if (ret) + goto out; + ret = crypto_shash_update(shash, ctrl->opts->subsysnqn, + strlen(ctrl->opts->subsysnqn)); + if (ret) + goto out; + ret = crypto_shash_update(shash, buf, 1); + if (ret) + goto out; + ret = crypto_shash_update(shash, ctrl->opts->host->nqn, + strlen(ctrl->opts->host->nqn)); + if (ret) + goto out; + ret = crypto_shash_final(shash, chap->response); +out: + if (challenge != chap->c2) + kfree(challenge); + kfree(ctrl_response); + return ret; +} + +static int nvme_auth_dhchap_exponential(struct nvme_ctrl *ctrl, + struct nvme_dhchap_queue_context *chap) +{ + int ret; + + if (chap->host_key && chap->host_key_len) { + dev_dbg(ctrl->device, + "qid %d: reusing host key\n", chap->qid); + goto gen_sesskey; + } + ret = nvme_auth_gen_privkey(chap->dh_tfm, chap->dhgroup_id); + if (ret < 0) { + chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; + return ret; + } + + chap->host_key_len = crypto_kpp_maxsize(chap->dh_tfm); + + chap->host_key = kzalloc(chap->host_key_len, GFP_KERNEL); + if (!chap->host_key) { + chap->host_key_len = 0; + chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED; + return -ENOMEM; + } + ret = nvme_auth_gen_pubkey(chap->dh_tfm, + chap->host_key, chap->host_key_len); + if (ret) { + dev_dbg(ctrl->device, + "failed to generate public key, error %d\n", ret); + kfree(chap->host_key); + chap->host_key = NULL; + chap->host_key_len = 0; + chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; + return ret; + } + +gen_sesskey: + chap->sess_key_len = chap->host_key_len; + chap->sess_key = kmalloc(chap->sess_key_len, GFP_KERNEL); + if (!chap->sess_key) { + chap->sess_key_len = 0; + chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED; + return -ENOMEM; + } + + ret = nvme_auth_gen_shared_secret(chap->dh_tfm, + chap->ctrl_key, chap->ctrl_key_len, + chap->sess_key, chap->sess_key_len); + if (ret) { + dev_dbg(ctrl->device, + "failed to generate shared secret, error %d\n", ret); + kfree_sensitive(chap->sess_key); + chap->sess_key = NULL; + chap->sess_key_len = 0; + chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; + return ret; + } + dev_dbg(ctrl->device, "shared secret %*ph\n", + (int)chap->sess_key_len, chap->sess_key); + return 0; +} + +static void __nvme_auth_reset(struct nvme_dhchap_queue_context *chap) +{ + kfree_sensitive(chap->host_response); + chap->host_response = NULL; + kfree_sensitive(chap->host_key); + chap->host_key = NULL; + chap->host_key_len = 0; + kfree_sensitive(chap->ctrl_key); + chap->ctrl_key = NULL; + chap->ctrl_key_len = 0; + kfree_sensitive(chap->sess_key); + chap->sess_key = NULL; + chap->sess_key_len = 0; + chap->status = 0; + chap->error = 0; + chap->s1 = 0; + chap->s2 = 0; + chap->transaction = 0; + memset(chap->c1, 0, sizeof(chap->c1)); + memset(chap->c2, 0, sizeof(chap->c2)); +} + +static void __nvme_auth_free(struct nvme_dhchap_queue_context *chap) +{ + __nvme_auth_reset(chap); + if (chap->shash_tfm) + crypto_free_shash(chap->shash_tfm); + if (chap->dh_tfm) + crypto_free_kpp(chap->dh_tfm); + kfree_sensitive(chap->ctrl_key); + kfree_sensitive(chap->host_key); + kfree_sensitive(chap->sess_key); + kfree_sensitive(chap->host_response); + kfree(chap->buf); + kfree(chap); +} + +static void __nvme_auth_work(struct work_struct *work) +{ + struct nvme_dhchap_queue_context *chap = + container_of(work, struct nvme_dhchap_queue_context, auth_work); + struct nvme_ctrl *ctrl = chap->ctrl; + size_t tl; + int ret = 0; + + chap->transaction = ctrl->transaction++; + + /* DH-HMAC-CHAP Step 1: send negotiate */ + dev_dbg(ctrl->device, "%s: qid %d send negotiate\n", + __func__, chap->qid); + ret = nvme_auth_set_dhchap_negotiate_data(ctrl, chap); + if (ret < 0) { + chap->error = ret; + return; + } + tl = ret; + ret = nvme_auth_submit(ctrl, chap->qid, chap->buf, tl, true); + if (ret) { + chap->error = ret; + return; + } + + /* DH-HMAC-CHAP Step 2: receive challenge */ + dev_dbg(ctrl->device, "%s: qid %d receive challenge\n", + __func__, chap->qid); + + memset(chap->buf, 0, chap->buf_size); + ret = nvme_auth_submit(ctrl, chap->qid, chap->buf, chap->buf_size, false); + if (ret) { + dev_warn(ctrl->device, + "qid %d failed to receive challenge, %s %d\n", + chap->qid, ret < 0 ? "error" : "nvme status", ret); + chap->error = ret; + return; + } + ret = nvme_auth_receive_validate(ctrl, chap->qid, chap->buf, chap->transaction, + NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE); + if (ret) { + chap->status = ret; + chap->error = NVME_SC_AUTH_REQUIRED; + return; + } + + ret = nvme_auth_process_dhchap_challenge(ctrl, chap); + if (ret) { + /* Invalid challenge parameters */ + chap->error = ret; + goto fail2; + } + + if (chap->ctrl_key_len) { + dev_dbg(ctrl->device, + "%s: qid %d DH exponential\n", + __func__, chap->qid); + ret = nvme_auth_dhchap_exponential(ctrl, chap); + if (ret) { + chap->error = ret; + goto fail2; + } + } + + dev_dbg(ctrl->device, "%s: qid %d host response\n", + __func__, chap->qid); + ret = nvme_auth_dhchap_setup_host_response(ctrl, chap); + if (ret) { + chap->error = ret; + goto fail2; + } + + /* DH-HMAC-CHAP Step 3: send reply */ + dev_dbg(ctrl->device, "%s: qid %d send reply\n", + __func__, chap->qid); + ret = nvme_auth_set_dhchap_reply_data(ctrl, chap); + if (ret < 0) { + chap->error = ret; + goto fail2; + } + + tl = ret; + ret = nvme_auth_submit(ctrl, chap->qid, chap->buf, tl, true); + if (ret) { + chap->error = ret; + goto fail2; + } + + /* DH-HMAC-CHAP Step 4: receive success1 */ + dev_dbg(ctrl->device, "%s: qid %d receive success1\n", + __func__, chap->qid); + + memset(chap->buf, 0, chap->buf_size); + ret = nvme_auth_submit(ctrl, chap->qid, chap->buf, chap->buf_size, false); + if (ret) { + dev_warn(ctrl->device, + "qid %d failed to receive success1, %s %d\n", + chap->qid, ret < 0 ? "error" : "nvme status", ret); + chap->error = ret; + return; + } + ret = nvme_auth_receive_validate(ctrl, chap->qid, + chap->buf, chap->transaction, + NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1); + if (ret) { + chap->status = ret; + chap->error = NVME_SC_AUTH_REQUIRED; + return; + } + + if (ctrl->ctrl_key) { + dev_dbg(ctrl->device, + "%s: qid %d controller response\n", + __func__, chap->qid); + ret = nvme_auth_dhchap_setup_ctrl_response(ctrl, chap); + if (ret) { + chap->error = ret; + goto fail2; + } + } + + ret = nvme_auth_process_dhchap_success1(ctrl, chap); + if (ret) { + /* Controller authentication failed */ + chap->error = NVME_SC_AUTH_REQUIRED; + goto fail2; + } + + if (ctrl->ctrl_key) { + /* DH-HMAC-CHAP Step 5: send success2 */ + dev_dbg(ctrl->device, "%s: qid %d send success2\n", + __func__, chap->qid); + tl = nvme_auth_set_dhchap_success2_data(ctrl, chap); + ret = nvme_auth_submit(ctrl, chap->qid, chap->buf, tl, true); + if (ret) + chap->error = ret; + } + if (!ret) { + chap->error = 0; + return; + } + +fail2: + dev_dbg(ctrl->device, "%s: qid %d send failure2, status %x\n", + __func__, chap->qid, chap->status); + tl = nvme_auth_set_dhchap_failure2_data(ctrl, chap); + ret = nvme_auth_submit(ctrl, chap->qid, chap->buf, tl, true); + /* + * only update error if send failure2 failed and no other + * error had been set during authentication. + */ + if (ret && !chap->error) + chap->error = ret; +} + +int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid) +{ + struct nvme_dhchap_queue_context *chap; + + if (!ctrl->host_key) { + dev_warn(ctrl->device, "qid %d: no key\n", qid); + return -ENOKEY; + } + + if (ctrl->opts->dhchap_ctrl_secret && !ctrl->ctrl_key) { + dev_warn(ctrl->device, "qid %d: invalid ctrl key\n", qid); + return -ENOKEY; + } + + mutex_lock(&ctrl->dhchap_auth_mutex); + /* Check if the context is already queued */ + list_for_each_entry(chap, &ctrl->dhchap_auth_list, entry) { + WARN_ON(!chap->buf); + if (chap->qid == qid) { + dev_dbg(ctrl->device, "qid %d: re-using context\n", qid); + mutex_unlock(&ctrl->dhchap_auth_mutex); + flush_work(&chap->auth_work); + __nvme_auth_reset(chap); + queue_work(nvme_wq, &chap->auth_work); + return 0; + } + } + chap = kzalloc(sizeof(*chap), GFP_KERNEL); + if (!chap) { + mutex_unlock(&ctrl->dhchap_auth_mutex); + return -ENOMEM; + } + chap->qid = (qid == NVME_QID_ANY) ? 0 : qid; + chap->ctrl = ctrl; + + /* + * Allocate a large enough buffer for the entire negotiation: + * 4k should be enough to ffdhe8192. + */ + chap->buf_size = 4096; + chap->buf = kzalloc(chap->buf_size, GFP_KERNEL); + if (!chap->buf) { + mutex_unlock(&ctrl->dhchap_auth_mutex); + kfree(chap); + return -ENOMEM; + } + + INIT_WORK(&chap->auth_work, __nvme_auth_work); + list_add(&chap->entry, &ctrl->dhchap_auth_list); + mutex_unlock(&ctrl->dhchap_auth_mutex); + queue_work(nvme_wq, &chap->auth_work); + return 0; +} +EXPORT_SYMBOL_GPL(nvme_auth_negotiate); + +int nvme_auth_wait(struct nvme_ctrl *ctrl, int qid) +{ + struct nvme_dhchap_queue_context *chap; + int ret; + + mutex_lock(&ctrl->dhchap_auth_mutex); + list_for_each_entry(chap, &ctrl->dhchap_auth_list, entry) { + if (chap->qid != qid) + continue; + mutex_unlock(&ctrl->dhchap_auth_mutex); + flush_work(&chap->auth_work); + ret = chap->error; + return ret; + } + mutex_unlock(&ctrl->dhchap_auth_mutex); + return -ENXIO; +} +EXPORT_SYMBOL_GPL(nvme_auth_wait); + +void nvme_auth_reset(struct nvme_ctrl *ctrl) +{ + struct nvme_dhchap_queue_context *chap; + + mutex_lock(&ctrl->dhchap_auth_mutex); + list_for_each_entry(chap, &ctrl->dhchap_auth_list, entry) { + mutex_unlock(&ctrl->dhchap_auth_mutex); + flush_work(&chap->auth_work); + __nvme_auth_reset(chap); + } + mutex_unlock(&ctrl->dhchap_auth_mutex); +} +EXPORT_SYMBOL_GPL(nvme_auth_reset); + +static void nvme_dhchap_auth_work(struct work_struct *work) +{ + struct nvme_ctrl *ctrl = + container_of(work, struct nvme_ctrl, dhchap_auth_work); + int ret, q; + + /* Authenticate admin queue first */ + ret = nvme_auth_negotiate(ctrl, 0); + if (ret) { + dev_warn(ctrl->device, + "qid 0: error %d setting up authentication\n", ret); + return; + } + ret = nvme_auth_wait(ctrl, 0); + if (ret) { + dev_warn(ctrl->device, + "qid 0: authentication failed\n"); + return; + } + + for (q = 1; q < ctrl->queue_count; q++) { + ret = nvme_auth_negotiate(ctrl, q); + if (ret) { + dev_warn(ctrl->device, + "qid %d: error %d setting up authentication\n", + q, ret); + break; + } + } + + /* + * Failure is a soft-state; credentials remain valid until + * the controller terminates the connection. + */ +} + +void nvme_auth_init_ctrl(struct nvme_ctrl *ctrl) +{ + INIT_LIST_HEAD(&ctrl->dhchap_auth_list); + INIT_WORK(&ctrl->dhchap_auth_work, nvme_dhchap_auth_work); + mutex_init(&ctrl->dhchap_auth_mutex); + if (!ctrl->opts) + return; + nvme_auth_generate_key(ctrl->opts->dhchap_secret, &ctrl->host_key); + nvme_auth_generate_key(ctrl->opts->dhchap_ctrl_secret, &ctrl->ctrl_key); +} +EXPORT_SYMBOL_GPL(nvme_auth_init_ctrl); + +void nvme_auth_stop(struct nvme_ctrl *ctrl) +{ + struct nvme_dhchap_queue_context *chap = NULL, *tmp; + + cancel_work_sync(&ctrl->dhchap_auth_work); + mutex_lock(&ctrl->dhchap_auth_mutex); + list_for_each_entry_safe(chap, tmp, &ctrl->dhchap_auth_list, entry) + cancel_work_sync(&chap->auth_work); + mutex_unlock(&ctrl->dhchap_auth_mutex); +} +EXPORT_SYMBOL_GPL(nvme_auth_stop); + +void nvme_auth_free(struct nvme_ctrl *ctrl) +{ + struct nvme_dhchap_queue_context *chap = NULL, *tmp; + + mutex_lock(&ctrl->dhchap_auth_mutex); + list_for_each_entry_safe(chap, tmp, &ctrl->dhchap_auth_list, entry) { + list_del_init(&chap->entry); + flush_work(&chap->auth_work); + __nvme_auth_free(chap); + } + mutex_unlock(&ctrl->dhchap_auth_mutex); + if (ctrl->host_key) { + nvme_auth_free_key(ctrl->host_key); + ctrl->host_key = NULL; + } + if (ctrl->ctrl_key) { + nvme_auth_free_key(ctrl->ctrl_key); + ctrl->ctrl_key = NULL; + } +} +EXPORT_SYMBOL_GPL(nvme_auth_free); diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c index 4910543f00ff..e958d5015585 100644 --- a/drivers/nvme/host/constants.c +++ b/drivers/nvme/host/constants.c @@ -6,7 +6,6 @@ #include "nvme.h" -#ifdef CONFIG_NVME_VERBOSE_ERRORS static const char * const nvme_ops[] = { [nvme_cmd_flush] = "Flush", [nvme_cmd_write] = "Write", @@ -178,6 +177,7 @@ const unsigned char *nvme_get_opcode_str(u8 opcode) return nvme_ops[opcode]; return "Unknown"; } +EXPORT_SYMBOL_GPL(nvme_get_opcode_str); const unsigned char *nvme_get_admin_opcode_str(u8 opcode) { @@ -185,4 +185,3 @@ const unsigned char *nvme_get_admin_opcode_str(u8 opcode) return nvme_admin_ops[opcode]; return "Unknown"; } -#endif /* CONFIG_NVME_VERBOSE_ERRORS */ diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 2533b88e66d5..2429b11eb9a8 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -24,12 +24,22 @@ #include "nvme.h" #include "fabrics.h" +#include #define CREATE_TRACE_POINTS #include "trace.h" #define NVME_MINORS (1U << MINORBITS) +struct nvme_ns_info { + struct nvme_ns_ids ids; + u32 nsid; + __le32 anagrpid; + bool is_shared; + bool is_readonly; + bool is_ready; +}; + unsigned int admin_timeout = 60; module_param(admin_timeout, uint, 0644); MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin commands"); @@ -330,6 +340,7 @@ enum nvme_disposition { COMPLETE, RETRY, FAILOVER, + AUTHENTICATE, }; static inline enum nvme_disposition nvme_decide_disposition(struct request *req) @@ -337,6 +348,9 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req) if (likely(nvme_req(req)->status == 0)) return COMPLETE; + if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED) + return AUTHENTICATE; + if (blk_noretry_request(req) || (nvme_req(req)->status & NVME_SC_DNR) || nvme_req(req)->retries >= nvme_max_retries) @@ -375,11 +389,13 @@ static inline void nvme_end_req(struct request *req) void nvme_complete_rq(struct request *req) { + struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; + trace_nvme_complete_rq(req); nvme_cleanup_cmd(req); - if (nvme_req(req)->ctrl->kas) - nvme_req(req)->ctrl->comp_seen = true; + if (ctrl->kas) + ctrl->comp_seen = true; switch (nvme_decide_disposition(req)) { case COMPLETE: @@ -391,6 +407,14 @@ void nvme_complete_rq(struct request *req) case FAILOVER: nvme_failover_req(req); return; + case AUTHENTICATE: +#ifdef CONFIG_NVME_AUTH + queue_work(nvme_wq, &ctrl->dhchap_auth_work); + nvme_retry_req(req); +#else + nvme_end_req(req); +#endif + return; } } EXPORT_SYMBOL_GPL(nvme_complete_rq); @@ -702,7 +726,9 @@ bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq, switch (ctrl->state) { case NVME_CTRL_CONNECTING: if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) && - req->cmd->fabrics.fctype == nvme_fabrics_type_connect) + (req->cmd->fabrics.fctype == nvme_fabrics_type_connect || + req->cmd->fabrics.fctype == nvme_fabrics_type_auth_send || + req->cmd->fabrics.fctype == nvme_fabrics_type_auth_receive)) return true; break; default: @@ -990,8 +1016,7 @@ static int nvme_execute_rq(struct request *rq, bool at_head) */ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, union nvme_result *result, void *buffer, unsigned bufflen, - unsigned timeout, int qid, int at_head, - blk_mq_req_flags_t flags) + int qid, int at_head, blk_mq_req_flags_t flags) { struct request *req; int ret; @@ -1000,15 +1025,12 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags); else req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags, - qid ? qid - 1 : 0); + qid - 1); if (IS_ERR(req)) return PTR_ERR(req); nvme_init_request(req, cmd); - if (timeout) - req->timeout = timeout; - if (buffer && bufflen) { ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL); if (ret) @@ -1028,7 +1050,7 @@ EXPORT_SYMBOL_GPL(__nvme_submit_sync_cmd); int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, void *buffer, unsigned bufflen) { - return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, 0, + return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, NVME_QID_ANY, 0, 0); } EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd); @@ -1329,8 +1351,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, } } -static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, - struct nvme_ns_ids *ids) +static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, + struct nvme_ns_info *info) { struct nvme_command c = { }; bool csi_seen = false; @@ -1343,7 +1365,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, return 0; c.identify.opcode = nvme_admin_identify; - c.identify.nsid = cpu_to_le32(nsid); + c.identify.nsid = cpu_to_le32(info->nsid); c.identify.cns = NVME_ID_CNS_NS_DESC_LIST; data = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL); @@ -1355,7 +1377,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, if (status) { dev_warn(ctrl->device, "Identify Descriptors failed (nsid=%u, status=0x%x)\n", - nsid, status); + info->nsid, status); goto free_data; } @@ -1365,7 +1387,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, if (cur->nidl == 0) break; - len = nvme_process_ns_desc(ctrl, ids, cur, &csi_seen); + len = nvme_process_ns_desc(ctrl, &info->ids, cur, &csi_seen); if (len < 0) break; @@ -1374,7 +1396,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, if (nvme_multi_css(ctrl) && !csi_seen) { dev_warn(ctrl->device, "Command set not reported for nsid:%d\n", - nsid); + info->nsid); status = -EINVAL; } @@ -1384,7 +1406,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, } static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, - struct nvme_ns_ids *ids, struct nvme_id_ns **id) + struct nvme_id_ns **id) { struct nvme_command c = { }; int error; @@ -1407,20 +1429,6 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, error = NVME_SC_INVALID_NS | NVME_SC_DNR; if ((*id)->ncap == 0) /* namespace not allocated or attached */ goto out_free_id; - - - if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) { - dev_info(ctrl->device, - "Ignoring bogus Namespace Identifiers\n"); - } else { - if (ctrl->vs >= NVME_VS(1, 1, 0) && - !memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) - memcpy(ids->eui64, (*id)->eui64, sizeof(ids->eui64)); - if (ctrl->vs >= NVME_VS(1, 2, 0) && - !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) - memcpy(ids->nguid, (*id)->nguid, sizeof(ids->nguid)); - } - return 0; out_free_id: @@ -1428,30 +1436,59 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, return error; } -static int nvme_identify_ns_cs_indep(struct nvme_ctrl *ctrl, unsigned nsid, - struct nvme_id_ns_cs_indep **id) +static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl, + struct nvme_ns_info *info) { + struct nvme_ns_ids *ids = &info->ids; + struct nvme_id_ns *id; + int ret; + + ret = nvme_identify_ns(ctrl, info->nsid, &id); + if (ret) + return ret; + info->anagrpid = id->anagrpid; + info->is_shared = id->nmic & NVME_NS_NMIC_SHARED; + info->is_readonly = id->nsattr & NVME_NS_ATTR_RO; + info->is_ready = true; + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) { + dev_info(ctrl->device, + "Ignoring bogus Namespace Identifiers\n"); + } else { + if (ctrl->vs >= NVME_VS(1, 1, 0) && + !memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) + memcpy(ids->eui64, id->eui64, sizeof(ids->eui64)); + if (ctrl->vs >= NVME_VS(1, 2, 0) && + !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + memcpy(ids->nguid, id->nguid, sizeof(ids->nguid)); + } + kfree(id); + return 0; +} + +static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl, + struct nvme_ns_info *info) +{ + struct nvme_id_ns_cs_indep *id; struct nvme_command c = { .identify.opcode = nvme_admin_identify, - .identify.nsid = cpu_to_le32(nsid), + .identify.nsid = cpu_to_le32(info->nsid), .identify.cns = NVME_ID_CNS_NS_CS_INDEP, }; int ret; - *id = kmalloc(sizeof(**id), GFP_KERNEL); - if (!*id) + id = kmalloc(sizeof(*id), GFP_KERNEL); + if (!id) return -ENOMEM; - ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, *id, sizeof(**id)); - if (ret) { - dev_warn(ctrl->device, - "Identify namespace (CS independent) failed (%d)\n", - ret); - kfree(*id); - return ret; + ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id)); + if (!ret) { + info->anagrpid = id->anagrpid; + info->is_shared = id->nmic & NVME_NS_NMIC_SHARED; + info->is_readonly = id->nsattr & NVME_NS_ATTR_RO; + info->is_ready = id->nstat & NVME_NSTAT_NRDY; } - - return 0; + kfree(id); + return ret; } static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, @@ -1466,7 +1503,7 @@ static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, c.features.dword11 = cpu_to_le32(dword11); ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res, - buffer, buflen, 0, NVME_QID_ANY, 0, 0); + buffer, buflen, NVME_QID_ANY, 0, 0); if (ret >= 0 && result) *result = le32_to_cpu(res.u32); return ret; @@ -1875,6 +1912,11 @@ static void nvme_update_disk_info(struct gendisk *disk, ns->ctrl->max_zeroes_sectors); } +static bool nvme_ns_is_readonly(struct nvme_ns *ns, struct nvme_ns_info *info) +{ + return info->is_readonly || test_bit(NVME_NS_FORCE_RO, &ns->flags); +} + static inline bool nvme_first_scan(struct gendisk *disk) { /* nvme_alloc_ns() scans the disk prior to adding it */ @@ -1912,12 +1954,44 @@ static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id) blk_queue_chunk_sectors(ns->queue, iob); } -static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id) +static int nvme_update_ns_info_generic(struct nvme_ns *ns, + struct nvme_ns_info *info) { - unsigned lbaf = nvme_lbaf_index(id->flbas); + blk_mq_freeze_queue(ns->disk->queue); + nvme_set_queue_limits(ns->ctrl, ns->queue); + set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info)); + blk_mq_unfreeze_queue(ns->disk->queue); + + if (nvme_ns_head_multipath(ns->head)) { + blk_mq_freeze_queue(ns->head->disk->queue); + set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info)); + nvme_mpath_revalidate_paths(ns); + blk_stack_limits(&ns->head->disk->queue->limits, + &ns->queue->limits, 0); + ns->head->disk->flags |= GENHD_FL_HIDDEN; + blk_mq_unfreeze_queue(ns->head->disk->queue); + } + + /* Hide the block-interface for these devices */ + ns->disk->flags |= GENHD_FL_HIDDEN; + set_bit(NVME_NS_READY, &ns->flags); + + return 0; +} + +static int nvme_update_ns_info_block(struct nvme_ns *ns, + struct nvme_ns_info *info) +{ + struct nvme_id_ns *id; + unsigned lbaf; int ret; + ret = nvme_identify_ns(ns->ctrl, info->nsid, &id); + if (ret) + return ret; + blk_mq_freeze_queue(ns->disk->queue); + lbaf = nvme_lbaf_index(id->flbas); ns->lba_shift = id->lbaf[lbaf].ds; nvme_set_queue_limits(ns->ctrl, ns->queue); @@ -1927,36 +2001,35 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id) if (ns->head->ids.csi == NVME_CSI_ZNS) { ret = nvme_update_zone_info(ns, lbaf); - if (ret) - goto out_unfreeze; + if (ret) { + blk_mq_unfreeze_queue(ns->disk->queue); + goto out; + } } - set_disk_ro(ns->disk, (id->nsattr & NVME_NS_ATTR_RO) || - test_bit(NVME_NS_FORCE_RO, &ns->flags)); + set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info)); set_bit(NVME_NS_READY, &ns->flags); blk_mq_unfreeze_queue(ns->disk->queue); if (blk_queue_is_zoned(ns->queue)) { ret = nvme_revalidate_zones(ns); if (ret && !nvme_first_scan(ns->disk)) - return ret; + goto out; } if (nvme_ns_head_multipath(ns->head)) { blk_mq_freeze_queue(ns->head->disk->queue); nvme_update_disk_info(ns->head->disk, ns, id); - set_disk_ro(ns->head->disk, - (id->nsattr & NVME_NS_ATTR_RO) || - test_bit(NVME_NS_FORCE_RO, &ns->flags)); + set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info)); nvme_mpath_revalidate_paths(ns); blk_stack_limits(&ns->head->disk->queue->limits, &ns->queue->limits, 0); disk_update_readahead(ns->head->disk); blk_mq_unfreeze_queue(ns->head->disk->queue); } - return 0; -out_unfreeze: + ret = 0; +out: /* * If probing fails due an unsupported feature, hide the block device, * but still allow other access. @@ -1966,10 +2039,31 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id) set_bit(NVME_NS_READY, &ns->flags); ret = 0; } - blk_mq_unfreeze_queue(ns->disk->queue); + kfree(id); return ret; } +static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) +{ + switch (info->ids.csi) { + case NVME_CSI_ZNS: + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) { + dev_info(ns->ctrl->device, + "block device for nsid %u not supported without CONFIG_BLK_DEV_ZONED\n", + info->nsid); + return nvme_update_ns_info_generic(ns, info); + } + return nvme_update_ns_info_block(ns, info); + case NVME_CSI_NVM: + return nvme_update_ns_info_block(ns, info); + default: + dev_info(ns->ctrl->device, + "block device for nsid %u not supported (csi %u)\n", + info->nsid, info->ids.csi); + return nvme_update_ns_info_generic(ns, info); + } +} + static char nvme_pr_type(enum pr_type type) { switch (type) { @@ -2103,7 +2197,7 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len, cmd.common.cdw10 = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8); cmd.common.cdw11 = cpu_to_le32(len); - return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len, 0, + return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len, NVME_QID_ANY, 1, 0); } EXPORT_SYMBOL_GPL(nvme_sec_submit); @@ -2123,6 +2217,7 @@ static int nvme_report_zones(struct gendisk *disk, sector_t sector, static const struct block_device_operations nvme_bdev_ops = { .owner = THIS_MODULE, .ioctl = nvme_ioctl, + .compat_ioctl = blkdev_compat_ptr_ioctl, .open = nvme_open, .release = nvme_release, .getgeo = nvme_getgeo, @@ -3613,6 +3708,108 @@ static ssize_t dctype_show(struct device *dev, } static DEVICE_ATTR_RO(dctype); +#ifdef CONFIG_NVME_AUTH +static ssize_t nvme_ctrl_dhchap_secret_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + + if (!opts->dhchap_secret) + return sysfs_emit(buf, "none\n"); + return sysfs_emit(buf, "%s\n", opts->dhchap_secret); +} + +static ssize_t nvme_ctrl_dhchap_secret_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + char *dhchap_secret; + + if (!ctrl->opts->dhchap_secret) + return -EINVAL; + if (count < 7) + return -EINVAL; + if (memcmp(buf, "DHHC-1:", 7)) + return -EINVAL; + + dhchap_secret = kzalloc(count + 1, GFP_KERNEL); + if (!dhchap_secret) + return -ENOMEM; + memcpy(dhchap_secret, buf, count); + nvme_auth_stop(ctrl); + if (strcmp(dhchap_secret, opts->dhchap_secret)) { + int ret; + + ret = nvme_auth_generate_key(dhchap_secret, &ctrl->host_key); + if (ret) + return ret; + kfree(opts->dhchap_secret); + opts->dhchap_secret = dhchap_secret; + /* Key has changed; re-authentication with new key */ + nvme_auth_reset(ctrl); + } + /* Start re-authentication */ + dev_info(ctrl->device, "re-authenticating controller\n"); + queue_work(nvme_wq, &ctrl->dhchap_auth_work); + + return count; +} +static DEVICE_ATTR(dhchap_secret, S_IRUGO | S_IWUSR, + nvme_ctrl_dhchap_secret_show, nvme_ctrl_dhchap_secret_store); + +static ssize_t nvme_ctrl_dhchap_ctrl_secret_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + + if (!opts->dhchap_ctrl_secret) + return sysfs_emit(buf, "none\n"); + return sysfs_emit(buf, "%s\n", opts->dhchap_ctrl_secret); +} + +static ssize_t nvme_ctrl_dhchap_ctrl_secret_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + char *dhchap_secret; + + if (!ctrl->opts->dhchap_ctrl_secret) + return -EINVAL; + if (count < 7) + return -EINVAL; + if (memcmp(buf, "DHHC-1:", 7)) + return -EINVAL; + + dhchap_secret = kzalloc(count + 1, GFP_KERNEL); + if (!dhchap_secret) + return -ENOMEM; + memcpy(dhchap_secret, buf, count); + nvme_auth_stop(ctrl); + if (strcmp(dhchap_secret, opts->dhchap_ctrl_secret)) { + int ret; + + ret = nvme_auth_generate_key(dhchap_secret, &ctrl->ctrl_key); + if (ret) + return ret; + kfree(opts->dhchap_ctrl_secret); + opts->dhchap_ctrl_secret = dhchap_secret; + /* Key has changed; re-authentication with new key */ + nvme_auth_reset(ctrl); + } + /* Start re-authentication */ + dev_info(ctrl->device, "re-authenticating controller\n"); + queue_work(nvme_wq, &ctrl->dhchap_auth_work); + + return count; +} +static DEVICE_ATTR(dhchap_ctrl_secret, S_IRUGO | S_IWUSR, + nvme_ctrl_dhchap_ctrl_secret_show, nvme_ctrl_dhchap_ctrl_secret_store); +#endif + static struct attribute *nvme_dev_attrs[] = { &dev_attr_reset_controller.attr, &dev_attr_rescan_controller.attr, @@ -3636,6 +3833,10 @@ static struct attribute *nvme_dev_attrs[] = { &dev_attr_kato.attr, &dev_attr_cntrltype.attr, &dev_attr_dctype.attr, +#ifdef CONFIG_NVME_AUTH + &dev_attr_dhchap_secret.attr, + &dev_attr_dhchap_ctrl_secret.attr, +#endif NULL }; @@ -3659,6 +3860,12 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj, return 0; if (a == &dev_attr_fast_io_fail_tmo.attr && !ctrl->opts) return 0; +#ifdef CONFIG_NVME_AUTH + if (a == &dev_attr_dhchap_secret.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_dhchap_ctrl_secret.attr && !ctrl->opts) + return 0; +#endif return a->mode; } @@ -3786,7 +3993,7 @@ static int nvme_add_ns_cdev(struct nvme_ns *ns) } static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, - unsigned nsid, struct nvme_ns_ids *ids, bool is_shared) + struct nvme_ns_info *info) { struct nvme_ns_head *head; size_t size = sizeof(*head); @@ -3808,9 +4015,9 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, if (ret) goto out_ida_remove; head->subsys = ctrl->subsys; - head->ns_id = nsid; - head->ids = *ids; - head->shared = is_shared; + head->ns_id = info->nsid; + head->ids = info->ids; + head->shared = info->is_shared; kref_init(&head->ref); if (head->ids.csi) { @@ -3867,54 +4074,54 @@ static int nvme_global_check_duplicate_ids(struct nvme_subsystem *this, return ret; } -static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid, - struct nvme_ns_ids *ids, bool is_shared) +static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) { struct nvme_ctrl *ctrl = ns->ctrl; struct nvme_ns_head *head = NULL; int ret; - ret = nvme_global_check_duplicate_ids(ctrl->subsys, ids); + ret = nvme_global_check_duplicate_ids(ctrl->subsys, &info->ids); if (ret) { dev_err(ctrl->device, - "globally duplicate IDs for nsid %d\n", nsid); + "globally duplicate IDs for nsid %d\n", info->nsid); nvme_print_device_info(ctrl); return ret; } mutex_lock(&ctrl->subsys->lock); - head = nvme_find_ns_head(ctrl, nsid); + head = nvme_find_ns_head(ctrl, info->nsid); if (!head) { - ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, ids); + ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, &info->ids); if (ret) { dev_err(ctrl->device, "duplicate IDs in subsystem for nsid %d\n", - nsid); + info->nsid); goto out_unlock; } - head = nvme_alloc_ns_head(ctrl, nsid, ids, is_shared); + head = nvme_alloc_ns_head(ctrl, info); if (IS_ERR(head)) { ret = PTR_ERR(head); goto out_unlock; } } else { ret = -EINVAL; - if (!is_shared || !head->shared) { + if (!info->is_shared || !head->shared) { dev_err(ctrl->device, - "Duplicate unshared namespace %d\n", nsid); + "Duplicate unshared namespace %d\n", + info->nsid); goto out_put_ns_head; } - if (!nvme_ns_ids_equal(&head->ids, ids)) { + if (!nvme_ns_ids_equal(&head->ids, &info->ids)) { dev_err(ctrl->device, "IDs don't match for shared namespace %d\n", - nsid); + info->nsid); goto out_put_ns_head; } if (!multipath && !list_empty(&head->list)) { dev_warn(ctrl->device, "Found shared namespace %d, but multipathing not supported.\n", - nsid); + info->nsid); dev_warn_once(ctrl->device, "Support for shared namespaces without CONFIG_NVME_MULTIPATH is deprecated and will be removed in Linux 6.0\n."); } @@ -3968,20 +4175,15 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns) list_add(&ns->list, &ns->ctrl->namespaces); } -static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, - struct nvme_ns_ids *ids) +static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) { struct nvme_ns *ns; struct gendisk *disk; - struct nvme_id_ns *id; int node = ctrl->numa_node; - if (nvme_identify_ns(ctrl, nsid, ids, &id)) - return; - ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node); if (!ns) - goto out_free_id; + return; disk = blk_mq_alloc_disk(ctrl->tagset, ns); if (IS_ERR(disk)) @@ -4002,7 +4204,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, ns->ctrl = ctrl; kref_init(&ns->kref); - if (nvme_init_ns_head(ns, nsid, ids, id->nmic & NVME_NS_NMIC_SHARED)) + if (nvme_init_ns_head(ns, info)) goto out_cleanup_disk; /* @@ -4028,7 +4230,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, ns->head->instance); } - if (nvme_update_ns_info(ns, id)) + if (nvme_update_ns_info(ns, info)) goto out_unlink_ns; down_write(&ctrl->namespaces_rwsem); @@ -4042,9 +4244,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, if (!nvme_ns_head_multipath(ns->head)) nvme_add_ns_cdev(ns); - nvme_mpath_add_disk(ns, id); + nvme_mpath_add_disk(ns, info->anagrpid); nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name); - kfree(id); return; @@ -4064,8 +4265,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, put_disk(disk); out_free_ns: kfree(ns); - out_free_id: - kfree(id); } static void nvme_ns_remove(struct nvme_ns *ns) @@ -4123,29 +4322,21 @@ static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid) } } -static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_ids *ids) +static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_info *info) { - struct nvme_id_ns *id; int ret = NVME_SC_INVALID_NS | NVME_SC_DNR; if (test_bit(NVME_NS_DEAD, &ns->flags)) goto out; - ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, ids, &id); - if (ret) - goto out; - ret = NVME_SC_INVALID_NS | NVME_SC_DNR; - if (!nvme_ns_ids_equal(&ns->head->ids, ids)) { + if (!nvme_ns_ids_equal(&ns->head->ids, &info->ids)) { dev_err(ns->ctrl->device, "identifiers changed for nsid %d\n", ns->head->ns_id); - goto out_free_id; + goto out; } - ret = nvme_update_ns_info(ns, id); - -out_free_id: - kfree(id); + ret = nvme_update_ns_info(ns, info); out: /* * Only remove the namespace if we got a fatal error back from the @@ -4157,59 +4348,47 @@ static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_ids *ids) nvme_ns_remove(ns); } -static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) +static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid) { - struct nvme_ns_ids ids = { }; - struct nvme_id_ns_cs_indep *id; + struct nvme_ns_info info = { .nsid = nsid }; struct nvme_ns *ns; - bool ready = true; - if (nvme_identify_ns_descs(ctrl, nsid, &ids)) + if (nvme_identify_ns_descs(ctrl, &info)) return; - /* - * Check if the namespace is ready. If not ignore it, we will get an - * AEN once it becomes ready and restart the scan. - */ - if ((ctrl->cap & NVME_CAP_CRMS_CRIMS) && - !nvme_identify_ns_cs_indep(ctrl, nsid, &id)) { - ready = id->nstat & NVME_NSTAT_NRDY; - kfree(id); + if (info.ids.csi != NVME_CSI_NVM && !nvme_multi_css(ctrl)) { + dev_warn(ctrl->device, + "command set not reported for nsid: %d\n", nsid); + return; } - if (!ready) + /* + * If available try to use the Command Set Idependent Identify Namespace + * data structure to find all the generic information that is needed to + * set up a namespace. If not fall back to the legacy version. + */ + if ((ctrl->cap & NVME_CAP_CRMS_CRIMS) || + (info.ids.csi != NVME_CSI_NVM && info.ids.csi != NVME_CSI_ZNS)) { + if (nvme_ns_info_from_id_cs_indep(ctrl, &info)) + return; + } else { + if (nvme_ns_info_from_identify(ctrl, &info)) + return; + } + + /* + * Ignore the namespace if it is not ready. We will get an AEN once it + * becomes ready and restart the scan. + */ + if (!info.is_ready) return; ns = nvme_find_get_ns(ctrl, nsid); if (ns) { - nvme_validate_ns(ns, &ids); + nvme_validate_ns(ns, &info); nvme_put_ns(ns); - return; - } - - switch (ids.csi) { - case NVME_CSI_NVM: - nvme_alloc_ns(ctrl, nsid, &ids); - break; - case NVME_CSI_ZNS: - if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) { - dev_warn(ctrl->device, - "nsid %u not supported without CONFIG_BLK_DEV_ZONED\n", - nsid); - break; - } - if (!nvme_multi_css(ctrl)) { - dev_warn(ctrl->device, - "command set not reported for nsid: %d\n", - nsid); - break; - } - nvme_alloc_ns(ctrl, nsid, &ids); - break; - default: - dev_warn(ctrl->device, "unknown csi %u for nsid %u\n", - ids.csi, nsid); - break; + } else { + nvme_alloc_ns(ctrl, &info); } } @@ -4265,7 +4444,7 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl) if (!nsid) /* end of the list? */ goto out; - nvme_validate_or_alloc_ns(ctrl, nsid); + nvme_scan_ns(ctrl, nsid); while (++prev < nsid) nvme_ns_remove_by_nsid(ctrl, prev); } @@ -4288,7 +4467,7 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl) kfree(id); for (i = 1; i <= nn; i++) - nvme_validate_or_alloc_ns(ctrl, i); + nvme_scan_ns(ctrl, i); nvme_remove_invalid_namespaces(ctrl, nn); } @@ -4525,9 +4704,19 @@ static void nvme_fw_act_work(struct work_struct *work) nvme_get_fw_slot_info(ctrl); } +static u32 nvme_aer_type(u32 result) +{ + return result & 0x7; +} + +static u32 nvme_aer_subtype(u32 result) +{ + return (result & 0xff00) >> 8; +} + static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) { - u32 aer_notice_type = (result & 0xff00) >> 8; + u32 aer_notice_type = nvme_aer_subtype(result); trace_nvme_async_event(ctrl, aer_notice_type); @@ -4542,8 +4731,10 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) * recovery actions from interfering with the controller's * firmware activation. */ - if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) + if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) { + nvme_auth_stop(ctrl); queue_work(nvme_wq, &ctrl->fw_act_work); + } break; #ifdef CONFIG_NVME_MULTIPATH case NVME_AER_NOTICE_ANA: @@ -4560,11 +4751,19 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) } } +static void nvme_handle_aer_persistent_error(struct nvme_ctrl *ctrl) +{ + trace_nvme_async_event(ctrl, NVME_AER_ERROR); + dev_warn(ctrl->device, "resetting controller due to AER\n"); + nvme_reset_ctrl(ctrl); +} + void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, volatile union nvme_result *res) { u32 result = le32_to_cpu(res->u32); - u32 aer_type = result & 0x07; + u32 aer_type = nvme_aer_type(result); + u32 aer_subtype = nvme_aer_subtype(result); if (le16_to_cpu(status) >> 1 != NVME_SC_SUCCESS) return; @@ -4574,6 +4773,15 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, nvme_handle_aen_notice(ctrl, result); break; case NVME_AER_ERROR: + /* + * For a persistent internal error, don't run async_event_work + * to submit a new AER. The controller reset will do it. + */ + if (aer_subtype == NVME_AER_ERROR_PERSIST_INT_ERR) { + nvme_handle_aer_persistent_error(ctrl); + return; + } + fallthrough; case NVME_AER_SMART: case NVME_AER_CSS: case NVME_AER_VS: @@ -4590,6 +4798,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event); void nvme_stop_ctrl(struct nvme_ctrl *ctrl) { nvme_mpath_stop(ctrl); + nvme_auth_stop(ctrl); nvme_stop_keep_alive(ctrl); nvme_stop_failfast_work(ctrl); flush_work(&ctrl->async_event_work); @@ -4649,6 +4858,8 @@ static void nvme_free_ctrl(struct device *dev) nvme_free_cels(ctrl); nvme_mpath_uninit(ctrl); + nvme_auth_stop(ctrl); + nvme_auth_free(ctrl); __free_page(ctrl->discard_page); if (subsys) { @@ -4739,6 +4950,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device)); nvme_mpath_init_ctrl(ctrl); + nvme_auth_init_ctrl(ctrl); return 0; out_free_name: diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index ee79a6d639b4..5207a2348257 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -152,7 +152,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val) cmd.prop_get.fctype = nvme_fabrics_type_property_get; cmd.prop_get.offset = cpu_to_le32(off); - ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, 0, + ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, NVME_QID_ANY, 0, 0); if (ret >= 0) @@ -198,7 +198,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val) cmd.prop_get.attrib = 1; cmd.prop_get.offset = cpu_to_le32(off); - ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, 0, + ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, NVME_QID_ANY, 0, 0); if (ret >= 0) @@ -243,7 +243,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val) cmd.prop_set.offset = cpu_to_le32(off); cmd.prop_set.value = cpu_to_le64(val); - ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0, 0, + ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0, NVME_QID_ANY, 0, 0); if (unlikely(ret)) dev_err(ctrl->device, @@ -331,6 +331,10 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, dev_err(ctrl->device, "Connect command failed: host path error\n"); break; + case NVME_SC_AUTH_REQUIRED: + dev_err(ctrl->device, + "Connect command failed: authentication required\n"); + break; default: dev_err(ctrl->device, "Connect command failed, error wo/DNR bit: %d\n", @@ -365,6 +369,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) union nvme_result res; struct nvmf_connect_data *data; int ret; + u32 result; cmd.connect.opcode = nvme_fabrics_command; cmd.connect.fctype = nvme_fabrics_type_connect; @@ -389,7 +394,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, - data, sizeof(*data), 0, NVME_QID_ANY, 1, + data, sizeof(*data), NVME_QID_ANY, 1, BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT); if (ret) { nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32), @@ -397,8 +402,25 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) goto out_free_data; } - ctrl->cntlid = le16_to_cpu(res.u16); - + result = le32_to_cpu(res.u32); + ctrl->cntlid = result & 0xFFFF; + if ((result >> 16) & 0x3) { + /* Authentication required */ + ret = nvme_auth_negotiate(ctrl, 0); + if (ret) { + dev_warn(ctrl->device, + "qid 0: authentication setup failed\n"); + ret = NVME_SC_AUTH_REQUIRED; + goto out_free_data; + } + ret = nvme_auth_wait(ctrl, 0); + if (ret) + dev_warn(ctrl->device, + "qid 0: authentication failed\n"); + else + dev_info(ctrl->device, + "qid 0: authenticated\n"); + } out_free_data: kfree(data); return ret; @@ -431,6 +453,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) struct nvmf_connect_data *data; union nvme_result res; int ret; + u32 result; cmd.connect.opcode = nvme_fabrics_command; cmd.connect.fctype = nvme_fabrics_type_connect; @@ -450,12 +473,27 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &res, - data, sizeof(*data), 0, qid, 1, + data, sizeof(*data), qid, 1, BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT); if (ret) { nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32), &cmd, data); } + result = le32_to_cpu(res.u32); + if ((result >> 16) & 2) { + /* Authentication required */ + ret = nvme_auth_negotiate(ctrl, qid); + if (ret) { + dev_warn(ctrl->device, + "qid %d: authentication setup failed\n", qid); + ret = NVME_SC_AUTH_REQUIRED; + } else { + ret = nvme_auth_wait(ctrl, qid); + if (ret) + dev_warn(ctrl->device, + "qid %u: authentication failed\n", qid); + } + } kfree(data); return ret; } @@ -548,6 +586,8 @@ static const match_table_t opt_tokens = { { NVMF_OPT_TOS, "tos=%d" }, { NVMF_OPT_FAIL_FAST_TMO, "fast_io_fail_tmo=%d" }, { NVMF_OPT_DISCOVERY, "discovery" }, + { NVMF_OPT_DHCHAP_SECRET, "dhchap_secret=%s" }, + { NVMF_OPT_DHCHAP_CTRL_SECRET, "dhchap_ctrl_secret=%s" }, { NVMF_OPT_ERR, NULL } }; @@ -829,6 +869,34 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, case NVMF_OPT_DISCOVERY: opts->discovery_nqn = true; break; + case NVMF_OPT_DHCHAP_SECRET: + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + if (strlen(p) < 11 || strncmp(p, "DHHC-1:", 7)) { + pr_err("Invalid DH-CHAP secret %s\n", p); + ret = -EINVAL; + goto out; + } + kfree(opts->dhchap_secret); + opts->dhchap_secret = p; + break; + case NVMF_OPT_DHCHAP_CTRL_SECRET: + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + if (strlen(p) < 11 || strncmp(p, "DHHC-1:", 7)) { + pr_err("Invalid DH-CHAP secret %s\n", p); + ret = -EINVAL; + goto out; + } + kfree(opts->dhchap_ctrl_secret); + opts->dhchap_ctrl_secret = p; + break; default: pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n", p); @@ -947,6 +1015,8 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts) kfree(opts->subsysnqn); kfree(opts->host_traddr); kfree(opts->host_iface); + kfree(opts->dhchap_secret); + kfree(opts->dhchap_ctrl_secret); kfree(opts); } EXPORT_SYMBOL_GPL(nvmf_free_options); @@ -956,7 +1026,8 @@ EXPORT_SYMBOL_GPL(nvmf_free_options); NVMF_OPT_KATO | NVMF_OPT_HOSTNQN | \ NVMF_OPT_HOST_ID | NVMF_OPT_DUP_CONNECT |\ NVMF_OPT_DISABLE_SQFLOW | NVMF_OPT_DISCOVERY |\ - NVMF_OPT_FAIL_FAST_TMO) + NVMF_OPT_FAIL_FAST_TMO | NVMF_OPT_DHCHAP_SECRET |\ + NVMF_OPT_DHCHAP_CTRL_SECRET) static struct nvme_ctrl * nvmf_create_ctrl(struct device *dev, const char *buf) @@ -1192,7 +1263,14 @@ static void __exit nvmf_exit(void) BUILD_BUG_ON(sizeof(struct nvmf_connect_command) != 64); BUILD_BUG_ON(sizeof(struct nvmf_property_get_command) != 64); BUILD_BUG_ON(sizeof(struct nvmf_property_set_command) != 64); + BUILD_BUG_ON(sizeof(struct nvmf_auth_send_command) != 64); + BUILD_BUG_ON(sizeof(struct nvmf_auth_receive_command) != 64); BUILD_BUG_ON(sizeof(struct nvmf_connect_data) != 1024); + BUILD_BUG_ON(sizeof(struct nvmf_auth_dhchap_negotiate_data) != 8); + BUILD_BUG_ON(sizeof(struct nvmf_auth_dhchap_challenge_data) != 16); + BUILD_BUG_ON(sizeof(struct nvmf_auth_dhchap_reply_data) != 16); + BUILD_BUG_ON(sizeof(struct nvmf_auth_dhchap_success1_data) != 16); + BUILD_BUG_ON(sizeof(struct nvmf_auth_dhchap_success2_data) != 16); } MODULE_LICENSE("GPL v2"); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 46d6e194ac2b..a6e22116e139 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -68,6 +68,8 @@ enum { NVMF_OPT_FAIL_FAST_TMO = 1 << 20, NVMF_OPT_HOST_IFACE = 1 << 21, NVMF_OPT_DISCOVERY = 1 << 22, + NVMF_OPT_DHCHAP_SECRET = 1 << 23, + NVMF_OPT_DHCHAP_CTRL_SECRET = 1 << 24, }; /** @@ -97,6 +99,9 @@ enum { * @max_reconnects: maximum number of allowed reconnect attempts before removing * the controller, (-1) means reconnect forever, zero means remove * immediately; + * @dhchap_secret: DH-HMAC-CHAP secret + * @dhchap_ctrl_secret: DH-HMAC-CHAP controller secret for bi-directional + * authentication * @disable_sqflow: disable controller sq flow control * @hdr_digest: generate/verify header digest (TCP) * @data_digest: generate/verify data digest (TCP) @@ -121,6 +126,8 @@ struct nvmf_ctrl_options { unsigned int kato; struct nvmf_host *host; int max_reconnects; + char *dhchap_secret; + char *dhchap_ctrl_secret; bool disable_sqflow; bool hdr_digest; bool data_digest; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index f26640ccb955..6ef497c75a16 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -346,7 +346,7 @@ static void nvme_ns_head_submit_bio(struct bio *bio) * different queue via blk_steal_bios(), so we need to use the bio_split * pool from the original queue to allocate the bvecs from. */ - blk_queue_split(&bio); + bio = bio_split_to_limits(bio); srcu_idx = srcu_read_lock(&head->srcu); ns = nvme_find_path(head); @@ -408,6 +408,7 @@ const struct block_device_operations nvme_ns_head_ops = { .open = nvme_ns_head_open, .release = nvme_ns_head_release, .ioctl = nvme_ns_head_ioctl, + .compat_ioctl = blkdev_compat_ptr_ioctl, .getgeo = nvme_getgeo, .report_zones = nvme_ns_head_report_zones, .pr_ops = &nvme_pr_ops, @@ -800,16 +801,16 @@ static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl, return -ENXIO; /* just break out of the loop */ } -void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id) +void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid) { if (nvme_ctrl_use_ana(ns->ctrl)) { struct nvme_ana_group_desc desc = { - .grpid = id->anagrpid, + .grpid = anagrpid, .state = 0, }; mutex_lock(&ns->ctrl->ana_lock); - ns->ana_grpid = le32_to_cpu(id->anagrpid); + ns->ana_grpid = le32_to_cpu(anagrpid); nvme_parse_ana_log(ns->ctrl, &desc, nvme_lookup_ana_group_desc); mutex_unlock(&ns->ctrl->ana_lock); if (desc.state) { diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 7e0a925bf3be..bdc0ff7ed9ab 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -140,7 +140,7 @@ enum nvme_quirks { NVME_QUIRK_DMA_ADDRESS_BITS_48 = (1 << 16), /* - * The controller requires the command_id value be be limited, so skip + * The controller requires the command_id value be limited, so skip * encoding the generation sequence number. */ NVME_QUIRK_SKIP_CID_GEN = (1 << 17), @@ -328,6 +328,15 @@ struct nvme_ctrl { struct work_struct ana_work; #endif +#ifdef CONFIG_NVME_AUTH + struct work_struct dhchap_auth_work; + struct list_head dhchap_auth_list; + struct mutex dhchap_auth_mutex; + struct nvme_dhchap_key *host_key; + struct nvme_dhchap_key *ctrl_key; + u16 transaction; +#endif + /* Power saving configuration */ u64 ps_max_latency_us; bool apst_enabled; @@ -781,7 +790,7 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, void *buf, unsigned bufflen); int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, union nvme_result *result, void *buffer, unsigned bufflen, - unsigned timeout, int qid, int at_head, + int qid, int at_head, blk_mq_req_flags_t flags); int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, @@ -837,7 +846,7 @@ void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys); void nvme_failover_req(struct request *req); void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); -void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id); +void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid); void nvme_mpath_remove_disk(struct nvme_ns_head *head); int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id); void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl); @@ -879,8 +888,7 @@ static inline int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, { return 0; } -static inline void nvme_mpath_add_disk(struct nvme_ns *ns, - struct nvme_id_ns *id) +static inline void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid) { } static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head) @@ -992,6 +1000,27 @@ static inline bool nvme_ctrl_sgl_supported(struct nvme_ctrl *ctrl) return ctrl->sgls & ((1 << 0) | (1 << 1)); } +#ifdef CONFIG_NVME_AUTH +void nvme_auth_init_ctrl(struct nvme_ctrl *ctrl); +void nvme_auth_stop(struct nvme_ctrl *ctrl); +int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid); +int nvme_auth_wait(struct nvme_ctrl *ctrl, int qid); +void nvme_auth_reset(struct nvme_ctrl *ctrl); +void nvme_auth_free(struct nvme_ctrl *ctrl); +#else +static inline void nvme_auth_init_ctrl(struct nvme_ctrl *ctrl) {}; +static inline void nvme_auth_stop(struct nvme_ctrl *ctrl) {}; +static inline int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid) +{ + return -EPROTONOSUPPORT; +} +static inline int nvme_auth_wait(struct nvme_ctrl *ctrl, int qid) +{ + return NVME_SC_AUTH_REQUIRED; +} +static inline void nvme_auth_free(struct nvme_ctrl *ctrl) {}; +#endif + u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); int nvme_execute_passthru_rq(struct request *rq); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 7e7d4802ac6b..71a4f26ba476 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -670,7 +670,6 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); if (!prp_list) { - iod->first_dma = dma_addr; iod->npages = -1; return BLK_STS_RESOURCE; } @@ -1435,8 +1434,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) cmd.abort.sqid = cpu_to_le16(nvmeq->qid); dev_warn(nvmeq->dev->ctrl.device, - "I/O %d QID %d timeout, aborting\n", - req->tag, nvmeq->qid); + "I/O %d (%s) QID %d timeout, aborting\n", + req->tag, + nvme_get_opcode_str(nvme_req(req)->cmd->common.opcode), + nvmeq->qid); abort_req = blk_mq_alloc_request(dev->ctrl.admin_q, nvme_req_op(&cmd), BLK_MQ_REQ_NOWAIT); @@ -1765,37 +1766,35 @@ static void nvme_dev_remove_admin(struct nvme_dev *dev) } } -static int nvme_alloc_admin_tags(struct nvme_dev *dev) +static int nvme_pci_alloc_admin_tag_set(struct nvme_dev *dev) { - if (!dev->ctrl.admin_q) { - dev->admin_tagset.ops = &nvme_mq_admin_ops; - dev->admin_tagset.nr_hw_queues = 1; + struct blk_mq_tag_set *set = &dev->admin_tagset; - dev->admin_tagset.queue_depth = NVME_AQ_MQ_TAG_DEPTH; - dev->admin_tagset.timeout = NVME_ADMIN_TIMEOUT; - dev->admin_tagset.numa_node = dev->ctrl.numa_node; - dev->admin_tagset.cmd_size = sizeof(struct nvme_iod); - dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED; - dev->admin_tagset.driver_data = dev; + set->ops = &nvme_mq_admin_ops; + set->nr_hw_queues = 1; - if (blk_mq_alloc_tag_set(&dev->admin_tagset)) - return -ENOMEM; - dev->ctrl.admin_tagset = &dev->admin_tagset; + set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; + set->timeout = NVME_ADMIN_TIMEOUT; + set->numa_node = dev->ctrl.numa_node; + set->cmd_size = sizeof(struct nvme_iod); + set->flags = BLK_MQ_F_NO_SCHED; + set->driver_data = dev; - dev->ctrl.admin_q = blk_mq_init_queue(&dev->admin_tagset); - if (IS_ERR(dev->ctrl.admin_q)) { - blk_mq_free_tag_set(&dev->admin_tagset); - dev->ctrl.admin_q = NULL; - return -ENOMEM; - } - if (!blk_get_queue(dev->ctrl.admin_q)) { - nvme_dev_remove_admin(dev); - dev->ctrl.admin_q = NULL; - return -ENODEV; - } - } else - nvme_start_admin_queue(&dev->ctrl); + if (blk_mq_alloc_tag_set(set)) + return -ENOMEM; + dev->ctrl.admin_tagset = set; + dev->ctrl.admin_q = blk_mq_init_queue(set); + if (IS_ERR(dev->ctrl.admin_q)) { + blk_mq_free_tag_set(set); + dev->ctrl.admin_q = NULL; + return -ENOMEM; + } + if (!blk_get_queue(dev->ctrl.admin_q)) { + nvme_dev_remove_admin(dev); + dev->ctrl.admin_q = NULL; + return -ENODEV; + } return 0; } @@ -2534,47 +2533,45 @@ static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode) return true; } -static void nvme_dev_add(struct nvme_dev *dev) +static void nvme_pci_alloc_tag_set(struct nvme_dev *dev) { + struct blk_mq_tag_set * set = &dev->tagset; int ret; - if (!dev->ctrl.tagset) { - dev->tagset.ops = &nvme_mq_ops; - dev->tagset.nr_hw_queues = dev->online_queues - 1; - dev->tagset.nr_maps = 2; /* default + read */ - if (dev->io_queues[HCTX_TYPE_POLL]) - dev->tagset.nr_maps++; - dev->tagset.timeout = NVME_IO_TIMEOUT; - dev->tagset.numa_node = dev->ctrl.numa_node; - dev->tagset.queue_depth = min_t(unsigned int, dev->q_depth, - BLK_MQ_MAX_DEPTH) - 1; - dev->tagset.cmd_size = sizeof(struct nvme_iod); - dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE; - dev->tagset.driver_data = dev; + set->ops = &nvme_mq_ops; + set->nr_hw_queues = dev->online_queues - 1; + set->nr_maps = 2; /* default + read */ + if (dev->io_queues[HCTX_TYPE_POLL]) + set->nr_maps++; + set->timeout = NVME_IO_TIMEOUT; + set->numa_node = dev->ctrl.numa_node; + set->queue_depth = min_t(unsigned, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1; + set->cmd_size = sizeof(struct nvme_iod); + set->flags = BLK_MQ_F_SHOULD_MERGE; + set->driver_data = dev; - /* - * Some Apple controllers requires tags to be unique - * across admin and IO queue, so reserve the first 32 - * tags of the IO queue. - */ - if (dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS) - dev->tagset.reserved_tags = NVME_AQ_DEPTH; + /* + * Some Apple controllers requires tags to be unique + * across admin and IO queue, so reserve the first 32 + * tags of the IO queue. + */ + if (dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS) + set->reserved_tags = NVME_AQ_DEPTH; - ret = blk_mq_alloc_tag_set(&dev->tagset); - if (ret) { - dev_warn(dev->ctrl.device, - "IO queues tagset allocation failed %d\n", ret); - return; - } - dev->ctrl.tagset = &dev->tagset; - } else { - blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1); - - /* Free previously allocated queues that are no longer usable */ - nvme_free_queues(dev, dev->online_queues); + ret = blk_mq_alloc_tag_set(set); + if (ret) { + dev_warn(dev->ctrl.device, + "IO queues tagset allocation failed %d\n", ret); + return; } + dev->ctrl.tagset = set; +} - nvme_dbbuf_set(dev); +static void nvme_pci_update_nr_queues(struct nvme_dev *dev) +{ + blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1); + /* free previously allocated queues that are no longer usable */ + nvme_free_queues(dev, dev->online_queues); } static int nvme_pci_enable(struct nvme_dev *dev) @@ -2725,10 +2722,8 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_pci_disable(dev); nvme_reap_pending_cqes(dev); - blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl); - blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl); - blk_mq_tagset_wait_completed_request(&dev->tagset); - blk_mq_tagset_wait_completed_request(&dev->admin_tagset); + nvme_cancel_tagset(&dev->ctrl); + nvme_cancel_admin_tagset(&dev->ctrl); /* * The driver will not be starting up queues again if shutting down so @@ -2842,9 +2837,13 @@ static void nvme_reset_work(struct work_struct *work) if (result) goto out_unlock; - result = nvme_alloc_admin_tags(dev); - if (result) - goto out_unlock; + if (!dev->ctrl.admin_q) { + result = nvme_pci_alloc_admin_tag_set(dev); + if (result) + goto out_unlock; + } else { + nvme_start_admin_queue(&dev->ctrl); + } /* * Limit the max command size to prevent iod->sg allocations going @@ -2923,7 +2922,11 @@ static void nvme_reset_work(struct work_struct *work) } else { nvme_start_queues(&dev->ctrl); nvme_wait_freeze(&dev->ctrl); - nvme_dev_add(dev); + if (!dev->ctrl.tagset) + nvme_pci_alloc_tag_set(dev); + else + nvme_pci_update_nr_queues(dev); + nvme_dbbuf_set(dev); nvme_unfreeze(&dev->ctrl); } diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 4665aebd944d..3100643be299 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -29,7 +29,7 @@ #include "fabrics.h" -#define NVME_RDMA_CONNECT_TIMEOUT_MS 3000 /* 3 second */ +#define NVME_RDMA_CM_TIMEOUT_MS 3000 /* 3 second */ #define NVME_RDMA_MAX_SEGMENTS 256 @@ -248,12 +248,9 @@ static int nvme_rdma_wait_for_cm(struct nvme_rdma_queue *queue) { int ret; - ret = wait_for_completion_interruptible_timeout(&queue->cm_done, - msecs_to_jiffies(NVME_RDMA_CONNECT_TIMEOUT_MS) + 1); - if (ret < 0) + ret = wait_for_completion_interruptible(&queue->cm_done); + if (ret) return ret; - if (ret == 0) - return -ETIMEDOUT; WARN_ON_ONCE(queue->cm_error > 0); return queue->cm_error; } @@ -612,7 +609,7 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, queue->cm_error = -ETIMEDOUT; ret = rdma_resolve_addr(queue->cm_id, src_addr, (struct sockaddr *)&ctrl->addr, - NVME_RDMA_CONNECT_TIMEOUT_MS); + NVME_RDMA_CM_TIMEOUT_MS); if (ret) { dev_info(ctrl->ctrl.device, "rdma_resolve_addr failed (%d).\n", ret); @@ -790,50 +787,54 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl) return ret; } -static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl, - bool admin) +static int nvme_rdma_alloc_admin_tag_set(struct nvme_ctrl *nctrl) { struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); - struct blk_mq_tag_set *set; + struct blk_mq_tag_set *set = &ctrl->admin_tag_set; int ret; - if (admin) { - set = &ctrl->admin_tag_set; - memset(set, 0, sizeof(*set)); - set->ops = &nvme_rdma_admin_mq_ops; - set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; - set->reserved_tags = NVMF_RESERVED_TAGS; - set->numa_node = nctrl->numa_node; - set->cmd_size = sizeof(struct nvme_rdma_request) + - NVME_RDMA_DATA_SGL_SIZE; - set->driver_data = ctrl; - set->nr_hw_queues = 1; - set->timeout = NVME_ADMIN_TIMEOUT; - set->flags = BLK_MQ_F_NO_SCHED; - } else { - set = &ctrl->tag_set; - memset(set, 0, sizeof(*set)); - set->ops = &nvme_rdma_mq_ops; - set->queue_depth = nctrl->sqsize + 1; - set->reserved_tags = NVMF_RESERVED_TAGS; - set->numa_node = nctrl->numa_node; - set->flags = BLK_MQ_F_SHOULD_MERGE; - set->cmd_size = sizeof(struct nvme_rdma_request) + - NVME_RDMA_DATA_SGL_SIZE; - if (nctrl->max_integrity_segments) - set->cmd_size += sizeof(struct nvme_rdma_sgl) + - NVME_RDMA_METADATA_SGL_SIZE; - set->driver_data = ctrl; - set->nr_hw_queues = nctrl->queue_count - 1; - set->timeout = NVME_IO_TIMEOUT; - set->nr_maps = nctrl->opts->nr_poll_queues ? HCTX_MAX_TYPES : 2; - } - + memset(set, 0, sizeof(*set)); + set->ops = &nvme_rdma_admin_mq_ops; + set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; + set->reserved_tags = NVMF_RESERVED_TAGS; + set->numa_node = nctrl->numa_node; + set->cmd_size = sizeof(struct nvme_rdma_request) + + NVME_RDMA_DATA_SGL_SIZE; + set->driver_data = ctrl; + set->nr_hw_queues = 1; + set->timeout = NVME_ADMIN_TIMEOUT; + set->flags = BLK_MQ_F_NO_SCHED; ret = blk_mq_alloc_tag_set(set); - if (ret) - return ERR_PTR(ret); + if (!ret) + ctrl->ctrl.admin_tagset = set; + return ret; +} - return set; +static int nvme_rdma_alloc_tag_set(struct nvme_ctrl *nctrl) +{ + struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); + struct blk_mq_tag_set *set = &ctrl->tag_set; + int ret; + + memset(set, 0, sizeof(*set)); + set->ops = &nvme_rdma_mq_ops; + set->queue_depth = nctrl->sqsize + 1; + set->reserved_tags = NVMF_RESERVED_TAGS; + set->numa_node = nctrl->numa_node; + set->flags = BLK_MQ_F_SHOULD_MERGE; + set->cmd_size = sizeof(struct nvme_rdma_request) + + NVME_RDMA_DATA_SGL_SIZE; + if (nctrl->max_integrity_segments) + set->cmd_size += sizeof(struct nvme_rdma_sgl) + + NVME_RDMA_METADATA_SGL_SIZE; + set->driver_data = ctrl; + set->nr_hw_queues = nctrl->queue_count - 1; + set->timeout = NVME_IO_TIMEOUT; + set->nr_maps = nctrl->opts->nr_poll_queues ? HCTX_MAX_TYPES : 2; + ret = blk_mq_alloc_tag_set(set); + if (!ret) + ctrl->ctrl.tagset = set; + return ret; } static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl, @@ -885,11 +886,9 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, goto out_free_queue; if (new) { - ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true); - if (IS_ERR(ctrl->ctrl.admin_tagset)) { - error = PTR_ERR(ctrl->ctrl.admin_tagset); + error = nvme_rdma_alloc_admin_tag_set(&ctrl->ctrl); + if (error) goto out_free_async_qe; - } ctrl->ctrl.fabrics_q = blk_mq_init_queue(&ctrl->admin_tag_set); if (IS_ERR(ctrl->ctrl.fabrics_q)) { @@ -972,11 +971,9 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) return ret; if (new) { - ctrl->ctrl.tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, false); - if (IS_ERR(ctrl->ctrl.tagset)) { - ret = PTR_ERR(ctrl->ctrl.tagset); + ret = nvme_rdma_alloc_tag_set(&ctrl->ctrl); + if (ret) goto out_free_io_queues; - } ret = nvme_ctrl_init_connect_q(&(ctrl->ctrl)); if (ret) @@ -1205,6 +1202,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, err_work); + nvme_auth_stop(&ctrl->ctrl); nvme_stop_keep_alive(&ctrl->ctrl); flush_work(&ctrl->ctrl.async_event_work); nvme_rdma_teardown_io_queues(ctrl, false); @@ -1894,7 +1892,7 @@ static int nvme_rdma_addr_resolved(struct nvme_rdma_queue *queue) if (ctrl->opts->tos >= 0) rdma_set_service_type(queue->cm_id, ctrl->opts->tos); - ret = rdma_resolve_route(queue->cm_id, NVME_RDMA_CONNECT_TIMEOUT_MS); + ret = rdma_resolve_route(queue->cm_id, NVME_RDMA_CM_TIMEOUT_MS); if (ret) { dev_err(ctrl->device, "rdma_resolve_route failed (%d).\n", queue->cm_error); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index b95ee85053e3..e82dcfcda29b 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -209,9 +209,11 @@ static inline u8 nvme_tcp_ddgst_len(struct nvme_tcp_queue *queue) return queue->data_digest ? NVME_TCP_DIGEST_LENGTH : 0; } -static inline size_t nvme_tcp_inline_data_size(struct nvme_tcp_queue *queue) +static inline size_t nvme_tcp_inline_data_size(struct nvme_tcp_request *req) { - return queue->cmnd_capsule_len - sizeof(struct nvme_command); + if (nvme_is_fabrics(req->req.cmd)) + return NVME_TCP_ADMIN_CCSZ; + return req->queue->cmnd_capsule_len - sizeof(struct nvme_command); } static inline bool nvme_tcp_async_req(struct nvme_tcp_request *req) @@ -229,7 +231,7 @@ static inline bool nvme_tcp_has_inline_data(struct nvme_tcp_request *req) rq = blk_mq_rq_from_pdu(req); return rq_data_dir(rq) == WRITE && req->data_len && - req->data_len <= nvme_tcp_inline_data_size(req->queue); + req->data_len <= nvme_tcp_inline_data_size(req); } static inline struct page *nvme_tcp_req_cur_page(struct nvme_tcp_request *req) @@ -1685,45 +1687,49 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx) return ret; } -static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, - bool admin) +static int nvme_tcp_alloc_admin_tag_set(struct nvme_ctrl *nctrl) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); - struct blk_mq_tag_set *set; + struct blk_mq_tag_set *set = &ctrl->admin_tag_set; int ret; - if (admin) { - set = &ctrl->admin_tag_set; - memset(set, 0, sizeof(*set)); - set->ops = &nvme_tcp_admin_mq_ops; - set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; - set->reserved_tags = NVMF_RESERVED_TAGS; - set->numa_node = nctrl->numa_node; - set->flags = BLK_MQ_F_BLOCKING; - set->cmd_size = sizeof(struct nvme_tcp_request); - set->driver_data = ctrl; - set->nr_hw_queues = 1; - set->timeout = NVME_ADMIN_TIMEOUT; - } else { - set = &ctrl->tag_set; - memset(set, 0, sizeof(*set)); - set->ops = &nvme_tcp_mq_ops; - set->queue_depth = nctrl->sqsize + 1; - set->reserved_tags = NVMF_RESERVED_TAGS; - set->numa_node = nctrl->numa_node; - set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING; - set->cmd_size = sizeof(struct nvme_tcp_request); - set->driver_data = ctrl; - set->nr_hw_queues = nctrl->queue_count - 1; - set->timeout = NVME_IO_TIMEOUT; - set->nr_maps = nctrl->opts->nr_poll_queues ? HCTX_MAX_TYPES : 2; - } - + memset(set, 0, sizeof(*set)); + set->ops = &nvme_tcp_admin_mq_ops; + set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; + set->reserved_tags = NVMF_RESERVED_TAGS; + set->numa_node = nctrl->numa_node; + set->flags = BLK_MQ_F_BLOCKING; + set->cmd_size = sizeof(struct nvme_tcp_request); + set->driver_data = ctrl; + set->nr_hw_queues = 1; + set->timeout = NVME_ADMIN_TIMEOUT; ret = blk_mq_alloc_tag_set(set); - if (ret) - return ERR_PTR(ret); + if (!ret) + nctrl->admin_tagset = set; + return ret; +} - return set; +static int nvme_tcp_alloc_tag_set(struct nvme_ctrl *nctrl) +{ + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + struct blk_mq_tag_set *set = &ctrl->tag_set; + int ret; + + memset(set, 0, sizeof(*set)); + set->ops = &nvme_tcp_mq_ops; + set->queue_depth = nctrl->sqsize + 1; + set->reserved_tags = NVMF_RESERVED_TAGS; + set->numa_node = nctrl->numa_node; + set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING; + set->cmd_size = sizeof(struct nvme_tcp_request); + set->driver_data = ctrl; + set->nr_hw_queues = nctrl->queue_count - 1; + set->timeout = NVME_IO_TIMEOUT; + set->nr_maps = nctrl->opts->nr_poll_queues ? HCTX_MAX_TYPES : 2; + ret = blk_mq_alloc_tag_set(set); + if (!ret) + nctrl->tagset = set; + return ret; } static void nvme_tcp_free_admin_queue(struct nvme_ctrl *ctrl) @@ -1899,11 +1905,9 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) return ret; if (new) { - ctrl->tagset = nvme_tcp_alloc_tagset(ctrl, false); - if (IS_ERR(ctrl->tagset)) { - ret = PTR_ERR(ctrl->tagset); + ret = nvme_tcp_alloc_tag_set(ctrl); + if (ret) goto out_free_io_queues; - } ret = nvme_ctrl_init_connect_q(ctrl); if (ret) @@ -1968,11 +1972,9 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new) return error; if (new) { - ctrl->admin_tagset = nvme_tcp_alloc_tagset(ctrl, true); - if (IS_ERR(ctrl->admin_tagset)) { - error = PTR_ERR(ctrl->admin_tagset); + error = nvme_tcp_alloc_admin_tag_set(ctrl); + if (error) goto out_free_queue; - } ctrl->fabrics_q = blk_mq_init_queue(ctrl->admin_tagset); if (IS_ERR(ctrl->fabrics_q)) { @@ -2173,6 +2175,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work) struct nvme_tcp_ctrl, err_work); struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl; + nvme_auth_stop(ctrl); nvme_stop_keep_alive(ctrl); flush_work(&ctrl->async_event_work); nvme_tcp_teardown_io_queues(ctrl, false); @@ -2371,7 +2374,7 @@ static blk_status_t nvme_tcp_map_data(struct nvme_tcp_queue *queue, if (!blk_rq_nr_phys_segments(rq)) nvme_tcp_set_sg_null(c); else if (rq_data_dir(rq) == WRITE && - req->data_len <= nvme_tcp_inline_data_size(queue)) + req->data_len <= nvme_tcp_inline_data_size(req)) nvme_tcp_set_sg_inline(queue, c, req->data_len); else nvme_tcp_set_sg_host_data(c, req->data_len); @@ -2406,7 +2409,7 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns, nvme_tcp_init_iter(req, rq_data_dir(rq)); if (rq_data_dir(rq) == WRITE && - req->data_len <= nvme_tcp_inline_data_size(queue)) + req->data_len <= nvme_tcp_inline_data_size(req)) req->pdu_len = req->data_len; pdu->hdr.type = nvme_tcp_cmd; diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c index 2a89c5aa0790..1c36fcedea20 100644 --- a/drivers/nvme/host/trace.c +++ b/drivers/nvme/host/trace.c @@ -287,6 +287,34 @@ static const char *nvme_trace_fabrics_property_get(struct trace_seq *p, u8 *spc) return ret; } +static const char *nvme_trace_fabrics_auth_send(struct trace_seq *p, u8 *spc) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 spsp0 = spc[1]; + u8 spsp1 = spc[2]; + u8 secp = spc[3]; + u32 tl = get_unaligned_le32(spc + 4); + + trace_seq_printf(p, "spsp0=%02x, spsp1=%02x, secp=%02x, tl=%u", + spsp0, spsp1, secp, tl); + trace_seq_putc(p, 0); + return ret; +} + +static const char *nvme_trace_fabrics_auth_receive(struct trace_seq *p, u8 *spc) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 spsp0 = spc[1]; + u8 spsp1 = spc[2]; + u8 secp = spc[3]; + u32 al = get_unaligned_le32(spc + 4); + + trace_seq_printf(p, "spsp0=%02x, spsp1=%02x, secp=%02x, al=%u", + spsp0, spsp1, secp, al); + trace_seq_putc(p, 0); + return ret; +} + static const char *nvme_trace_fabrics_common(struct trace_seq *p, u8 *spc) { const char *ret = trace_seq_buffer_ptr(p); @@ -306,6 +334,10 @@ const char *nvme_trace_parse_fabrics_cmd(struct trace_seq *p, return nvme_trace_fabrics_connect(p, spc); case nvme_fabrics_type_property_get: return nvme_trace_fabrics_property_get(p, spc); + case nvme_fabrics_type_auth_send: + return nvme_trace_fabrics_auth_send(p, spc); + case nvme_fabrics_type_auth_receive: + return nvme_trace_fabrics_auth_receive(p, spc); default: return nvme_trace_fabrics_common(p, spc); } diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h index 37c7f4c89f92..6f0eaf6a1528 100644 --- a/drivers/nvme/host/trace.h +++ b/drivers/nvme/host/trace.h @@ -98,7 +98,7 @@ TRACE_EVENT(nvme_complete_rq, TP_fast_assign( __entry->ctrl_id = nvme_req(req)->ctrl->instance; __entry->qid = nvme_req_qid(req); - __entry->cid = req->tag; + __entry->cid = nvme_req(req)->cmd->common.command_id; __entry->result = le64_to_cpu(nvme_req(req)->result.u64); __entry->retries = nvme_req(req)->retries; __entry->flags = nvme_req(req)->flags; diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig index 973561c93888..79fc64035ee3 100644 --- a/drivers/nvme/target/Kconfig +++ b/drivers/nvme/target/Kconfig @@ -83,3 +83,18 @@ config NVME_TARGET_TCP devices over TCP. If unsure, say N. + +config NVME_TARGET_AUTH + bool "NVMe over Fabrics In-band Authentication support" + depends on NVME_TARGET + select NVME_COMMON + select CRYPTO + select CRYPTO_HMAC + select CRYPTO_SHA256 + select CRYPTO_SHA512 + select CRYPTO_DH + select CRYPTO_DH_RFC7919_GROUPS + help + This enables support for NVMe over Fabrics In-band Authentication + + If unsure, say N. diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile index 9837e580fa7e..c66820102493 100644 --- a/drivers/nvme/target/Makefile +++ b/drivers/nvme/target/Makefile @@ -13,6 +13,7 @@ nvmet-y += core.o configfs.o admin-cmd.o fabrics-cmd.o \ discovery.o io-cmd-file.o io-cmd-bdev.o nvmet-$(CONFIG_NVME_TARGET_PASSTHRU) += passthru.o nvmet-$(CONFIG_BLK_DEV_ZONED) += zns.o +nvmet-$(CONFIG_NVME_TARGET_AUTH) += fabrics-cmd-auth.o auth.o nvme-loop-y += loop.o nvmet-rdma-y += rdma.o nvmet-fc-y += fc.o diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 397daaf51f1b..fc8a957fad0a 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -1017,7 +1017,9 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) u16 ret; if (nvme_is_fabrics(cmd)) - return nvmet_parse_fabrics_cmd(req); + return nvmet_parse_fabrics_admin_cmd(req); + if (unlikely(!nvmet_check_auth_status(req))) + return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR; if (nvmet_is_disc_subsys(nvmet_req_subsys(req))) return nvmet_parse_discovery_cmd(req); diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c new file mode 100644 index 000000000000..cf690df34775 --- /dev/null +++ b/drivers/nvme/target/auth.c @@ -0,0 +1,525 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVMe over Fabrics DH-HMAC-CHAP authentication. + * Copyright (c) 2020 Hannes Reinecke, SUSE Software Solutions. + * All rights reserved. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "nvmet.h" + +int nvmet_auth_set_key(struct nvmet_host *host, const char *secret, + bool set_ctrl) +{ + unsigned char key_hash; + char *dhchap_secret; + + if (sscanf(secret, "DHHC-1:%hhd:%*s", &key_hash) != 1) + return -EINVAL; + if (key_hash > 3) { + pr_warn("Invalid DH-HMAC-CHAP hash id %d\n", + key_hash); + return -EINVAL; + } + if (key_hash > 0) { + /* Validate selected hash algorithm */ + const char *hmac = nvme_auth_hmac_name(key_hash); + + if (!crypto_has_shash(hmac, 0, 0)) { + pr_err("DH-HMAC-CHAP hash %s unsupported\n", hmac); + return -ENOTSUPP; + } + } + dhchap_secret = kstrdup(secret, GFP_KERNEL); + if (!dhchap_secret) + return -ENOMEM; + if (set_ctrl) { + host->dhchap_ctrl_secret = strim(dhchap_secret); + host->dhchap_ctrl_key_hash = key_hash; + } else { + host->dhchap_secret = strim(dhchap_secret); + host->dhchap_key_hash = key_hash; + } + return 0; +} + +int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id) +{ + const char *dhgroup_kpp; + int ret = 0; + + pr_debug("%s: ctrl %d selecting dhgroup %d\n", + __func__, ctrl->cntlid, dhgroup_id); + + if (ctrl->dh_tfm) { + if (ctrl->dh_gid == dhgroup_id) { + pr_debug("%s: ctrl %d reuse existing DH group %d\n", + __func__, ctrl->cntlid, dhgroup_id); + return 0; + } + crypto_free_kpp(ctrl->dh_tfm); + ctrl->dh_tfm = NULL; + ctrl->dh_gid = 0; + } + + if (dhgroup_id == NVME_AUTH_DHGROUP_NULL) + return 0; + + dhgroup_kpp = nvme_auth_dhgroup_kpp(dhgroup_id); + if (!dhgroup_kpp) { + pr_debug("%s: ctrl %d invalid DH group %d\n", + __func__, ctrl->cntlid, dhgroup_id); + return -EINVAL; + } + ctrl->dh_tfm = crypto_alloc_kpp(dhgroup_kpp, 0, 0); + if (IS_ERR(ctrl->dh_tfm)) { + pr_debug("%s: ctrl %d failed to setup DH group %d, err %ld\n", + __func__, ctrl->cntlid, dhgroup_id, + PTR_ERR(ctrl->dh_tfm)); + ret = PTR_ERR(ctrl->dh_tfm); + ctrl->dh_tfm = NULL; + ctrl->dh_gid = 0; + } else { + ctrl->dh_gid = dhgroup_id; + pr_debug("%s: ctrl %d setup DH group %d\n", + __func__, ctrl->cntlid, ctrl->dh_gid); + ret = nvme_auth_gen_privkey(ctrl->dh_tfm, ctrl->dh_gid); + if (ret < 0) { + pr_debug("%s: ctrl %d failed to generate private key, err %d\n", + __func__, ctrl->cntlid, ret); + kfree_sensitive(ctrl->dh_key); + return ret; + } + ctrl->dh_keysize = crypto_kpp_maxsize(ctrl->dh_tfm); + kfree_sensitive(ctrl->dh_key); + ctrl->dh_key = kzalloc(ctrl->dh_keysize, GFP_KERNEL); + if (!ctrl->dh_key) { + pr_warn("ctrl %d failed to allocate public key\n", + ctrl->cntlid); + return -ENOMEM; + } + ret = nvme_auth_gen_pubkey(ctrl->dh_tfm, ctrl->dh_key, + ctrl->dh_keysize); + if (ret < 0) { + pr_warn("ctrl %d failed to generate public key\n", + ctrl->cntlid); + kfree(ctrl->dh_key); + ctrl->dh_key = NULL; + } + } + + return ret; +} + +int nvmet_setup_auth(struct nvmet_ctrl *ctrl) +{ + int ret = 0; + struct nvmet_host_link *p; + struct nvmet_host *host = NULL; + const char *hash_name; + + down_read(&nvmet_config_sem); + if (nvmet_is_disc_subsys(ctrl->subsys)) + goto out_unlock; + + if (ctrl->subsys->allow_any_host) + goto out_unlock; + + list_for_each_entry(p, &ctrl->subsys->hosts, entry) { + pr_debug("check %s\n", nvmet_host_name(p->host)); + if (strcmp(nvmet_host_name(p->host), ctrl->hostnqn)) + continue; + host = p->host; + break; + } + if (!host) { + pr_debug("host %s not found\n", ctrl->hostnqn); + ret = -EPERM; + goto out_unlock; + } + + ret = nvmet_setup_dhgroup(ctrl, host->dhchap_dhgroup_id); + if (ret < 0) + pr_warn("Failed to setup DH group"); + + if (!host->dhchap_secret) { + pr_debug("No authentication provided\n"); + goto out_unlock; + } + + if (host->dhchap_hash_id == ctrl->shash_id) { + pr_debug("Re-use existing hash ID %d\n", + ctrl->shash_id); + } else { + hash_name = nvme_auth_hmac_name(host->dhchap_hash_id); + if (!hash_name) { + pr_warn("Hash ID %d invalid\n", host->dhchap_hash_id); + ret = -EINVAL; + goto out_unlock; + } + ctrl->shash_id = host->dhchap_hash_id; + } + + /* Skip the 'DHHC-1:XX:' prefix */ + nvme_auth_free_key(ctrl->host_key); + ctrl->host_key = nvme_auth_extract_key(host->dhchap_secret + 10, + host->dhchap_key_hash); + if (IS_ERR(ctrl->host_key)) { + ret = PTR_ERR(ctrl->host_key); + ctrl->host_key = NULL; + goto out_free_hash; + } + pr_debug("%s: using hash %s key %*ph\n", __func__, + ctrl->host_key->hash > 0 ? + nvme_auth_hmac_name(ctrl->host_key->hash) : "none", + (int)ctrl->host_key->len, ctrl->host_key->key); + + nvme_auth_free_key(ctrl->ctrl_key); + if (!host->dhchap_ctrl_secret) { + ctrl->ctrl_key = NULL; + goto out_unlock; + } + + ctrl->ctrl_key = nvme_auth_extract_key(host->dhchap_ctrl_secret + 10, + host->dhchap_ctrl_key_hash); + if (IS_ERR(ctrl->ctrl_key)) { + ret = PTR_ERR(ctrl->ctrl_key); + ctrl->ctrl_key = NULL; + } + pr_debug("%s: using ctrl hash %s key %*ph\n", __func__, + ctrl->ctrl_key->hash > 0 ? + nvme_auth_hmac_name(ctrl->ctrl_key->hash) : "none", + (int)ctrl->ctrl_key->len, ctrl->ctrl_key->key); + +out_free_hash: + if (ret) { + if (ctrl->host_key) { + nvme_auth_free_key(ctrl->host_key); + ctrl->host_key = NULL; + } + ctrl->shash_id = 0; + } +out_unlock: + up_read(&nvmet_config_sem); + + return ret; +} + +void nvmet_auth_sq_free(struct nvmet_sq *sq) +{ + cancel_delayed_work(&sq->auth_expired_work); + kfree(sq->dhchap_c1); + sq->dhchap_c1 = NULL; + kfree(sq->dhchap_c2); + sq->dhchap_c2 = NULL; + kfree(sq->dhchap_skey); + sq->dhchap_skey = NULL; +} + +void nvmet_destroy_auth(struct nvmet_ctrl *ctrl) +{ + ctrl->shash_id = 0; + + if (ctrl->dh_tfm) { + crypto_free_kpp(ctrl->dh_tfm); + ctrl->dh_tfm = NULL; + ctrl->dh_gid = 0; + } + kfree_sensitive(ctrl->dh_key); + ctrl->dh_key = NULL; + + if (ctrl->host_key) { + nvme_auth_free_key(ctrl->host_key); + ctrl->host_key = NULL; + } + if (ctrl->ctrl_key) { + nvme_auth_free_key(ctrl->ctrl_key); + ctrl->ctrl_key = NULL; + } +} + +bool nvmet_check_auth_status(struct nvmet_req *req) +{ + if (req->sq->ctrl->host_key && + !req->sq->authenticated) + return false; + return true; +} + +int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, + unsigned int shash_len) +{ + struct crypto_shash *shash_tfm; + struct shash_desc *shash; + struct nvmet_ctrl *ctrl = req->sq->ctrl; + const char *hash_name; + u8 *challenge = req->sq->dhchap_c1, *host_response; + u8 buf[4]; + int ret; + + hash_name = nvme_auth_hmac_name(ctrl->shash_id); + if (!hash_name) { + pr_warn("Hash ID %d invalid\n", ctrl->shash_id); + return -EINVAL; + } + + shash_tfm = crypto_alloc_shash(hash_name, 0, 0); + if (IS_ERR(shash_tfm)) { + pr_err("failed to allocate shash %s\n", hash_name); + return PTR_ERR(shash_tfm); + } + + if (shash_len != crypto_shash_digestsize(shash_tfm)) { + pr_debug("%s: hash len mismatch (len %d digest %d)\n", + __func__, shash_len, + crypto_shash_digestsize(shash_tfm)); + ret = -EINVAL; + goto out_free_tfm; + } + + host_response = nvme_auth_transform_key(ctrl->host_key, ctrl->hostnqn); + if (IS_ERR(host_response)) { + ret = PTR_ERR(host_response); + goto out_free_tfm; + } + + ret = crypto_shash_setkey(shash_tfm, host_response, + ctrl->host_key->len); + if (ret) + goto out_free_response; + + if (ctrl->dh_gid != NVME_AUTH_DHGROUP_NULL) { + challenge = kmalloc(shash_len, GFP_KERNEL); + if (!challenge) { + ret = -ENOMEM; + goto out_free_response; + } + ret = nvme_auth_augmented_challenge(ctrl->shash_id, + req->sq->dhchap_skey, + req->sq->dhchap_skey_len, + req->sq->dhchap_c1, + challenge, shash_len); + if (ret) + goto out_free_response; + } + + pr_debug("ctrl %d qid %d host response seq %u transaction %d\n", + ctrl->cntlid, req->sq->qid, req->sq->dhchap_s1, + req->sq->dhchap_tid); + + shash = kzalloc(sizeof(*shash) + crypto_shash_descsize(shash_tfm), + GFP_KERNEL); + if (!shash) { + ret = -ENOMEM; + goto out_free_response; + } + shash->tfm = shash_tfm; + ret = crypto_shash_init(shash); + if (ret) + goto out; + ret = crypto_shash_update(shash, challenge, shash_len); + if (ret) + goto out; + put_unaligned_le32(req->sq->dhchap_s1, buf); + ret = crypto_shash_update(shash, buf, 4); + if (ret) + goto out; + put_unaligned_le16(req->sq->dhchap_tid, buf); + ret = crypto_shash_update(shash, buf, 2); + if (ret) + goto out; + memset(buf, 0, 4); + ret = crypto_shash_update(shash, buf, 1); + if (ret) + goto out; + ret = crypto_shash_update(shash, "HostHost", 8); + if (ret) + goto out; + ret = crypto_shash_update(shash, ctrl->hostnqn, strlen(ctrl->hostnqn)); + if (ret) + goto out; + ret = crypto_shash_update(shash, buf, 1); + if (ret) + goto out; + ret = crypto_shash_update(shash, ctrl->subsysnqn, + strlen(ctrl->subsysnqn)); + if (ret) + goto out; + ret = crypto_shash_final(shash, response); +out: + if (challenge != req->sq->dhchap_c1) + kfree(challenge); + kfree(shash); +out_free_response: + kfree_sensitive(host_response); +out_free_tfm: + crypto_free_shash(shash_tfm); + return 0; +} + +int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response, + unsigned int shash_len) +{ + struct crypto_shash *shash_tfm; + struct shash_desc *shash; + struct nvmet_ctrl *ctrl = req->sq->ctrl; + const char *hash_name; + u8 *challenge = req->sq->dhchap_c2, *ctrl_response; + u8 buf[4]; + int ret; + + hash_name = nvme_auth_hmac_name(ctrl->shash_id); + if (!hash_name) { + pr_warn("Hash ID %d invalid\n", ctrl->shash_id); + return -EINVAL; + } + + shash_tfm = crypto_alloc_shash(hash_name, 0, 0); + if (IS_ERR(shash_tfm)) { + pr_err("failed to allocate shash %s\n", hash_name); + return PTR_ERR(shash_tfm); + } + + if (shash_len != crypto_shash_digestsize(shash_tfm)) { + pr_debug("%s: hash len mismatch (len %d digest %d)\n", + __func__, shash_len, + crypto_shash_digestsize(shash_tfm)); + ret = -EINVAL; + goto out_free_tfm; + } + + ctrl_response = nvme_auth_transform_key(ctrl->ctrl_key, + ctrl->subsysnqn); + if (IS_ERR(ctrl_response)) { + ret = PTR_ERR(ctrl_response); + goto out_free_tfm; + } + + ret = crypto_shash_setkey(shash_tfm, ctrl_response, + ctrl->ctrl_key->len); + if (ret) + goto out_free_response; + + if (ctrl->dh_gid != NVME_AUTH_DHGROUP_NULL) { + challenge = kmalloc(shash_len, GFP_KERNEL); + if (!challenge) { + ret = -ENOMEM; + goto out_free_response; + } + ret = nvme_auth_augmented_challenge(ctrl->shash_id, + req->sq->dhchap_skey, + req->sq->dhchap_skey_len, + req->sq->dhchap_c2, + challenge, shash_len); + if (ret) + goto out_free_response; + } + + shash = kzalloc(sizeof(*shash) + crypto_shash_descsize(shash_tfm), + GFP_KERNEL); + if (!shash) { + ret = -ENOMEM; + goto out_free_response; + } + shash->tfm = shash_tfm; + + ret = crypto_shash_init(shash); + if (ret) + goto out; + ret = crypto_shash_update(shash, challenge, shash_len); + if (ret) + goto out; + put_unaligned_le32(req->sq->dhchap_s2, buf); + ret = crypto_shash_update(shash, buf, 4); + if (ret) + goto out; + put_unaligned_le16(req->sq->dhchap_tid, buf); + ret = crypto_shash_update(shash, buf, 2); + if (ret) + goto out; + memset(buf, 0, 4); + ret = crypto_shash_update(shash, buf, 1); + if (ret) + goto out; + ret = crypto_shash_update(shash, "Controller", 10); + if (ret) + goto out; + ret = crypto_shash_update(shash, ctrl->subsysnqn, + strlen(ctrl->subsysnqn)); + if (ret) + goto out; + ret = crypto_shash_update(shash, buf, 1); + if (ret) + goto out; + ret = crypto_shash_update(shash, ctrl->hostnqn, strlen(ctrl->hostnqn)); + if (ret) + goto out; + ret = crypto_shash_final(shash, response); +out: + if (challenge != req->sq->dhchap_c2) + kfree(challenge); + kfree(shash); +out_free_response: + kfree_sensitive(ctrl_response); +out_free_tfm: + crypto_free_shash(shash_tfm); + return 0; +} + +int nvmet_auth_ctrl_exponential(struct nvmet_req *req, + u8 *buf, int buf_size) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + int ret = 0; + + if (!ctrl->dh_key) { + pr_warn("ctrl %d no DH public key!\n", ctrl->cntlid); + return -ENOKEY; + } + if (buf_size != ctrl->dh_keysize) { + pr_warn("ctrl %d DH public key size mismatch, need %zu is %d\n", + ctrl->cntlid, ctrl->dh_keysize, buf_size); + ret = -EINVAL; + } else { + memcpy(buf, ctrl->dh_key, buf_size); + pr_debug("%s: ctrl %d public key %*ph\n", __func__, + ctrl->cntlid, (int)buf_size, buf); + } + + return ret; +} + +int nvmet_auth_ctrl_sesskey(struct nvmet_req *req, + u8 *pkey, int pkey_size) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + int ret; + + req->sq->dhchap_skey_len = ctrl->dh_keysize; + req->sq->dhchap_skey = kzalloc(req->sq->dhchap_skey_len, GFP_KERNEL); + if (!req->sq->dhchap_skey) + return -ENOMEM; + ret = nvme_auth_gen_shared_secret(ctrl->dh_tfm, + pkey, pkey_size, + req->sq->dhchap_skey, + req->sq->dhchap_skey_len); + if (ret) + pr_debug("failed to compute shared secret, err %d\n", ret); + else + pr_debug("%s: shared secret %*ph\n", __func__, + (int)req->sq->dhchap_skey_len, + req->sq->dhchap_skey); + + return ret; +} diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index ff77c3d2354f..2bcd60758919 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -11,6 +11,11 @@ #include #include #include +#ifdef CONFIG_NVME_TARGET_AUTH +#include +#endif +#include +#include #include "nvmet.h" @@ -1680,10 +1685,133 @@ static const struct config_item_type nvmet_ports_type = { static struct config_group nvmet_subsystems_group; static struct config_group nvmet_ports_group; +#ifdef CONFIG_NVME_TARGET_AUTH +static ssize_t nvmet_host_dhchap_key_show(struct config_item *item, + char *page) +{ + u8 *dhchap_secret = to_host(item)->dhchap_secret; + + if (!dhchap_secret) + return sprintf(page, "\n"); + return sprintf(page, "%s\n", dhchap_secret); +} + +static ssize_t nvmet_host_dhchap_key_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_host *host = to_host(item); + int ret; + + ret = nvmet_auth_set_key(host, page, false); + /* + * Re-authentication is a soft state, so keep the + * current authentication valid until the host + * requests re-authentication. + */ + return ret < 0 ? ret : count; +} + +CONFIGFS_ATTR(nvmet_host_, dhchap_key); + +static ssize_t nvmet_host_dhchap_ctrl_key_show(struct config_item *item, + char *page) +{ + u8 *dhchap_secret = to_host(item)->dhchap_ctrl_secret; + + if (!dhchap_secret) + return sprintf(page, "\n"); + return sprintf(page, "%s\n", dhchap_secret); +} + +static ssize_t nvmet_host_dhchap_ctrl_key_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_host *host = to_host(item); + int ret; + + ret = nvmet_auth_set_key(host, page, true); + /* + * Re-authentication is a soft state, so keep the + * current authentication valid until the host + * requests re-authentication. + */ + return ret < 0 ? ret : count; +} + +CONFIGFS_ATTR(nvmet_host_, dhchap_ctrl_key); + +static ssize_t nvmet_host_dhchap_hash_show(struct config_item *item, + char *page) +{ + struct nvmet_host *host = to_host(item); + const char *hash_name = nvme_auth_hmac_name(host->dhchap_hash_id); + + return sprintf(page, "%s\n", hash_name ? hash_name : "none"); +} + +static ssize_t nvmet_host_dhchap_hash_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_host *host = to_host(item); + u8 hmac_id; + + hmac_id = nvme_auth_hmac_id(page); + if (hmac_id == NVME_AUTH_HASH_INVALID) + return -EINVAL; + if (!crypto_has_shash(nvme_auth_hmac_name(hmac_id), 0, 0)) + return -ENOTSUPP; + host->dhchap_hash_id = hmac_id; + return count; +} + +CONFIGFS_ATTR(nvmet_host_, dhchap_hash); + +static ssize_t nvmet_host_dhchap_dhgroup_show(struct config_item *item, + char *page) +{ + struct nvmet_host *host = to_host(item); + const char *dhgroup = nvme_auth_dhgroup_name(host->dhchap_dhgroup_id); + + return sprintf(page, "%s\n", dhgroup ? dhgroup : "none"); +} + +static ssize_t nvmet_host_dhchap_dhgroup_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_host *host = to_host(item); + int dhgroup_id; + + dhgroup_id = nvme_auth_dhgroup_id(page); + if (dhgroup_id == NVME_AUTH_DHGROUP_INVALID) + return -EINVAL; + if (dhgroup_id != NVME_AUTH_DHGROUP_NULL) { + const char *kpp = nvme_auth_dhgroup_kpp(dhgroup_id); + + if (!crypto_has_kpp(kpp, 0, 0)) + return -EINVAL; + } + host->dhchap_dhgroup_id = dhgroup_id; + return count; +} + +CONFIGFS_ATTR(nvmet_host_, dhchap_dhgroup); + +static struct configfs_attribute *nvmet_host_attrs[] = { + &nvmet_host_attr_dhchap_key, + &nvmet_host_attr_dhchap_ctrl_key, + &nvmet_host_attr_dhchap_hash, + &nvmet_host_attr_dhchap_dhgroup, + NULL, +}; +#endif /* CONFIG_NVME_TARGET_AUTH */ + static void nvmet_host_release(struct config_item *item) { struct nvmet_host *host = to_host(item); +#ifdef CONFIG_NVME_TARGET_AUTH + kfree(host->dhchap_secret); +#endif kfree(host); } @@ -1693,6 +1821,9 @@ static struct configfs_item_operations nvmet_host_item_ops = { static const struct config_item_type nvmet_host_type = { .ct_item_ops = &nvmet_host_item_ops, +#ifdef CONFIG_NVME_TARGET_AUTH + .ct_attrs = nvmet_host_attrs, +#endif .ct_owner = THIS_MODULE, }; @@ -1705,6 +1836,11 @@ static struct config_group *nvmet_hosts_make_group(struct config_group *group, if (!host) return ERR_PTR(-ENOMEM); +#ifdef CONFIG_NVME_TARGET_AUTH + /* Default to SHA256 */ + host->dhchap_hash_id = NVME_AUTH_HASH_SHA256; +#endif + config_group_init_type_name(&host->group, name, &nvmet_host_type); return &host->group; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index c27660a660d9..a1345790005f 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -795,6 +795,7 @@ void nvmet_sq_destroy(struct nvmet_sq *sq) wait_for_completion(&sq->confirm_done); wait_for_completion(&sq->free_done); percpu_ref_exit(&sq->ref); + nvmet_auth_sq_free(sq); if (ctrl) { /* @@ -865,8 +866,15 @@ static inline u16 nvmet_io_cmd_check_access(struct nvmet_req *req) static u16 nvmet_parse_io_cmd(struct nvmet_req *req) { + struct nvme_command *cmd = req->cmd; u16 ret; + if (nvme_is_fabrics(cmd)) + return nvmet_parse_fabrics_io_cmd(req); + + if (unlikely(!nvmet_check_auth_status(req))) + return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR; + ret = nvmet_check_ctrl_status(req); if (unlikely(ret)) return ret; @@ -1271,6 +1279,11 @@ u16 nvmet_check_ctrl_status(struct nvmet_req *req) req->cmd->common.opcode, req->sq->qid); return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR; } + + if (unlikely(!nvmet_check_auth_status(req))) { + pr_warn("qid %d not authenticated\n", req->sq->qid); + return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR; + } return 0; } @@ -1467,6 +1480,8 @@ static void nvmet_ctrl_free(struct kref *ref) flush_work(&ctrl->async_event_work); cancel_work_sync(&ctrl->fatal_err_work); + nvmet_destroy_auth(ctrl); + ida_free(&cntlid_ida, ctrl->cntlid); nvmet_async_events_free(ctrl); diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c new file mode 100644 index 000000000000..c851814d6cb0 --- /dev/null +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -0,0 +1,544 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVMe over Fabrics DH-HMAC-CHAP authentication command handling. + * Copyright (c) 2020 Hannes Reinecke, SUSE Software Solutions. + * All rights reserved. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include +#include +#include +#include +#include +#include "nvmet.h" + +static void nvmet_auth_expired_work(struct work_struct *work) +{ + struct nvmet_sq *sq = container_of(to_delayed_work(work), + struct nvmet_sq, auth_expired_work); + + pr_debug("%s: ctrl %d qid %d transaction %u expired, resetting\n", + __func__, sq->ctrl->cntlid, sq->qid, sq->dhchap_tid); + sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE; + sq->dhchap_tid = -1; +} + +void nvmet_init_auth(struct nvmet_ctrl *ctrl, struct nvmet_req *req) +{ + u32 result = le32_to_cpu(req->cqe->result.u32); + + /* Initialize in-band authentication */ + INIT_DELAYED_WORK(&req->sq->auth_expired_work, + nvmet_auth_expired_work); + req->sq->authenticated = false; + req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE; + result |= (u32)NVME_CONNECT_AUTHREQ_ATR << 16; + req->cqe->result.u32 = cpu_to_le32(result); +} + +static u16 nvmet_auth_negotiate(struct nvmet_req *req, void *d) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmf_auth_dhchap_negotiate_data *data = d; + int i, hash_id = 0, fallback_hash_id = 0, dhgid, fallback_dhgid; + + pr_debug("%s: ctrl %d qid %d: data sc_d %d napd %d authid %d halen %d dhlen %d\n", + __func__, ctrl->cntlid, req->sq->qid, + data->sc_c, data->napd, data->auth_protocol[0].dhchap.authid, + data->auth_protocol[0].dhchap.halen, + data->auth_protocol[0].dhchap.dhlen); + req->sq->dhchap_tid = le16_to_cpu(data->t_id); + if (data->sc_c) + return NVME_AUTH_DHCHAP_FAILURE_CONCAT_MISMATCH; + + if (data->napd != 1) + return NVME_AUTH_DHCHAP_FAILURE_HASH_UNUSABLE; + + if (data->auth_protocol[0].dhchap.authid != + NVME_AUTH_DHCHAP_AUTH_ID) + return NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; + + for (i = 0; i < data->auth_protocol[0].dhchap.halen; i++) { + u8 host_hmac_id = data->auth_protocol[0].dhchap.idlist[i]; + + if (!fallback_hash_id && + crypto_has_shash(nvme_auth_hmac_name(host_hmac_id), 0, 0)) + fallback_hash_id = host_hmac_id; + if (ctrl->shash_id != host_hmac_id) + continue; + hash_id = ctrl->shash_id; + break; + } + if (hash_id == 0) { + if (fallback_hash_id == 0) { + pr_debug("%s: ctrl %d qid %d: no usable hash found\n", + __func__, ctrl->cntlid, req->sq->qid); + return NVME_AUTH_DHCHAP_FAILURE_HASH_UNUSABLE; + } + pr_debug("%s: ctrl %d qid %d: no usable hash found, falling back to %s\n", + __func__, ctrl->cntlid, req->sq->qid, + nvme_auth_hmac_name(fallback_hash_id)); + ctrl->shash_id = fallback_hash_id; + } + + dhgid = -1; + fallback_dhgid = -1; + for (i = 0; i < data->auth_protocol[0].dhchap.dhlen; i++) { + int tmp_dhgid = data->auth_protocol[0].dhchap.idlist[i + 30]; + + if (tmp_dhgid != ctrl->dh_gid) { + dhgid = tmp_dhgid; + break; + } + if (fallback_dhgid < 0) { + const char *kpp = nvme_auth_dhgroup_kpp(tmp_dhgid); + + if (crypto_has_kpp(kpp, 0, 0)) + fallback_dhgid = tmp_dhgid; + } + } + if (dhgid < 0) { + if (fallback_dhgid < 0) { + pr_debug("%s: ctrl %d qid %d: no usable DH group found\n", + __func__, ctrl->cntlid, req->sq->qid); + return NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE; + } + pr_debug("%s: ctrl %d qid %d: configured DH group %s not found\n", + __func__, ctrl->cntlid, req->sq->qid, + nvme_auth_dhgroup_name(fallback_dhgid)); + ctrl->dh_gid = fallback_dhgid; + } + pr_debug("%s: ctrl %d qid %d: selected DH group %s (%d)\n", + __func__, ctrl->cntlid, req->sq->qid, + nvme_auth_dhgroup_name(ctrl->dh_gid), ctrl->dh_gid); + return 0; +} + +static u16 nvmet_auth_reply(struct nvmet_req *req, void *d) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmf_auth_dhchap_reply_data *data = d; + u16 dhvlen = le16_to_cpu(data->dhvlen); + u8 *response; + + pr_debug("%s: ctrl %d qid %d: data hl %d cvalid %d dhvlen %u\n", + __func__, ctrl->cntlid, req->sq->qid, + data->hl, data->cvalid, dhvlen); + + if (dhvlen) { + if (!ctrl->dh_tfm) + return NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; + if (nvmet_auth_ctrl_sesskey(req, data->rval + 2 * data->hl, + dhvlen) < 0) + return NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE; + } + + response = kmalloc(data->hl, GFP_KERNEL); + if (!response) + return NVME_AUTH_DHCHAP_FAILURE_FAILED; + + if (!ctrl->host_key) { + pr_warn("ctrl %d qid %d no host key\n", + ctrl->cntlid, req->sq->qid); + kfree(response); + return NVME_AUTH_DHCHAP_FAILURE_FAILED; + } + if (nvmet_auth_host_hash(req, response, data->hl) < 0) { + pr_debug("ctrl %d qid %d host hash failed\n", + ctrl->cntlid, req->sq->qid); + kfree(response); + return NVME_AUTH_DHCHAP_FAILURE_FAILED; + } + + if (memcmp(data->rval, response, data->hl)) { + pr_info("ctrl %d qid %d host response mismatch\n", + ctrl->cntlid, req->sq->qid); + kfree(response); + return NVME_AUTH_DHCHAP_FAILURE_FAILED; + } + kfree(response); + pr_debug("%s: ctrl %d qid %d host authenticated\n", + __func__, ctrl->cntlid, req->sq->qid); + if (data->cvalid) { + req->sq->dhchap_c2 = kmalloc(data->hl, GFP_KERNEL); + if (!req->sq->dhchap_c2) + return NVME_AUTH_DHCHAP_FAILURE_FAILED; + memcpy(req->sq->dhchap_c2, data->rval + data->hl, data->hl); + + pr_debug("%s: ctrl %d qid %d challenge %*ph\n", + __func__, ctrl->cntlid, req->sq->qid, data->hl, + req->sq->dhchap_c2); + req->sq->dhchap_s2 = le32_to_cpu(data->seqnum); + } else { + req->sq->authenticated = true; + req->sq->dhchap_c2 = NULL; + } + + return 0; +} + +static u16 nvmet_auth_failure2(struct nvmet_req *req, void *d) +{ + struct nvmf_auth_dhchap_failure_data *data = d; + + return data->rescode_exp; +} + +void nvmet_execute_auth_send(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmf_auth_dhchap_success2_data *data; + void *d; + u32 tl; + u16 status = 0; + + if (req->cmd->auth_send.secp != NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER) { + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + req->error_loc = + offsetof(struct nvmf_auth_send_command, secp); + goto done; + } + if (req->cmd->auth_send.spsp0 != 0x01) { + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + req->error_loc = + offsetof(struct nvmf_auth_send_command, spsp0); + goto done; + } + if (req->cmd->auth_send.spsp1 != 0x01) { + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + req->error_loc = + offsetof(struct nvmf_auth_send_command, spsp1); + goto done; + } + tl = le32_to_cpu(req->cmd->auth_send.tl); + if (!tl) { + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + req->error_loc = + offsetof(struct nvmf_auth_send_command, tl); + goto done; + } + if (!nvmet_check_transfer_len(req, tl)) { + pr_debug("%s: transfer length mismatch (%u)\n", __func__, tl); + return; + } + + d = kmalloc(tl, GFP_KERNEL); + if (!d) { + status = NVME_SC_INTERNAL; + goto done; + } + + status = nvmet_copy_from_sgl(req, 0, d, tl); + if (status) { + kfree(d); + goto done; + } + + data = d; + pr_debug("%s: ctrl %d qid %d type %d id %d step %x\n", __func__, + ctrl->cntlid, req->sq->qid, data->auth_type, data->auth_id, + req->sq->dhchap_step); + if (data->auth_type != NVME_AUTH_COMMON_MESSAGES && + data->auth_type != NVME_AUTH_DHCHAP_MESSAGES) + goto done_failure1; + if (data->auth_type == NVME_AUTH_COMMON_MESSAGES) { + if (data->auth_id == NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE) { + /* Restart negotiation */ + pr_debug("%s: ctrl %d qid %d reset negotiation\n", __func__, + ctrl->cntlid, req->sq->qid); + if (!req->sq->qid) { + if (nvmet_setup_auth(ctrl) < 0) { + status = NVME_SC_INTERNAL; + pr_err("ctrl %d qid 0 failed to setup" + "re-authentication", + ctrl->cntlid); + goto done_failure1; + } + } + req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE; + } else if (data->auth_id != req->sq->dhchap_step) + goto done_failure1; + /* Validate negotiation parameters */ + status = nvmet_auth_negotiate(req, d); + if (status == 0) + req->sq->dhchap_step = + NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE; + else { + req->sq->dhchap_step = + NVME_AUTH_DHCHAP_MESSAGE_FAILURE1; + req->sq->dhchap_status = status; + status = 0; + } + goto done_kfree; + } + if (data->auth_id != req->sq->dhchap_step) { + pr_debug("%s: ctrl %d qid %d step mismatch (%d != %d)\n", + __func__, ctrl->cntlid, req->sq->qid, + data->auth_id, req->sq->dhchap_step); + goto done_failure1; + } + if (le16_to_cpu(data->t_id) != req->sq->dhchap_tid) { + pr_debug("%s: ctrl %d qid %d invalid transaction %d (expected %d)\n", + __func__, ctrl->cntlid, req->sq->qid, + le16_to_cpu(data->t_id), + req->sq->dhchap_tid); + req->sq->dhchap_step = + NVME_AUTH_DHCHAP_MESSAGE_FAILURE1; + req->sq->dhchap_status = + NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; + goto done_kfree; + } + + switch (data->auth_id) { + case NVME_AUTH_DHCHAP_MESSAGE_REPLY: + status = nvmet_auth_reply(req, d); + if (status == 0) + req->sq->dhchap_step = + NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1; + else { + req->sq->dhchap_step = + NVME_AUTH_DHCHAP_MESSAGE_FAILURE1; + req->sq->dhchap_status = status; + status = 0; + } + goto done_kfree; + break; + case NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2: + req->sq->authenticated = true; + pr_debug("%s: ctrl %d qid %d ctrl authenticated\n", + __func__, ctrl->cntlid, req->sq->qid); + goto done_kfree; + break; + case NVME_AUTH_DHCHAP_MESSAGE_FAILURE2: + status = nvmet_auth_failure2(req, d); + if (status) { + pr_warn("ctrl %d qid %d: authentication failed (%d)\n", + ctrl->cntlid, req->sq->qid, status); + req->sq->dhchap_status = status; + req->sq->authenticated = false; + status = 0; + } + goto done_kfree; + break; + default: + req->sq->dhchap_status = + NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE; + req->sq->dhchap_step = + NVME_AUTH_DHCHAP_MESSAGE_FAILURE2; + req->sq->authenticated = false; + goto done_kfree; + break; + } +done_failure1: + req->sq->dhchap_status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE; + req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_FAILURE2; + +done_kfree: + kfree(d); +done: + pr_debug("%s: ctrl %d qid %d dhchap status %x step %x\n", __func__, + ctrl->cntlid, req->sq->qid, + req->sq->dhchap_status, req->sq->dhchap_step); + if (status) + pr_debug("%s: ctrl %d qid %d nvme status %x error loc %d\n", + __func__, ctrl->cntlid, req->sq->qid, + status, req->error_loc); + req->cqe->result.u64 = 0; + nvmet_req_complete(req, status); + if (req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2 && + req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) { + unsigned long auth_expire_secs = ctrl->kato ? ctrl->kato : 120; + + mod_delayed_work(system_wq, &req->sq->auth_expired_work, + auth_expire_secs * HZ); + return; + } + /* Final states, clear up variables */ + nvmet_auth_sq_free(req->sq); + if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) + nvmet_ctrl_fatal_error(ctrl); +} + +static int nvmet_auth_challenge(struct nvmet_req *req, void *d, int al) +{ + struct nvmf_auth_dhchap_challenge_data *data = d; + struct nvmet_ctrl *ctrl = req->sq->ctrl; + int ret = 0; + int hash_len = nvme_auth_hmac_hash_len(ctrl->shash_id); + int data_size = sizeof(*d) + hash_len; + + if (ctrl->dh_tfm) + data_size += ctrl->dh_keysize; + if (al < data_size) { + pr_debug("%s: buffer too small (al %d need %d)\n", __func__, + al, data_size); + return -EINVAL; + } + memset(data, 0, data_size); + req->sq->dhchap_s1 = nvme_auth_get_seqnum(); + data->auth_type = NVME_AUTH_DHCHAP_MESSAGES; + data->auth_id = NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE; + data->t_id = cpu_to_le16(req->sq->dhchap_tid); + data->hashid = ctrl->shash_id; + data->hl = hash_len; + data->seqnum = cpu_to_le32(req->sq->dhchap_s1); + req->sq->dhchap_c1 = kmalloc(data->hl, GFP_KERNEL); + if (!req->sq->dhchap_c1) + return -ENOMEM; + get_random_bytes(req->sq->dhchap_c1, data->hl); + memcpy(data->cval, req->sq->dhchap_c1, data->hl); + if (ctrl->dh_tfm) { + data->dhgid = ctrl->dh_gid; + data->dhvlen = cpu_to_le16(ctrl->dh_keysize); + ret = nvmet_auth_ctrl_exponential(req, data->cval + data->hl, + ctrl->dh_keysize); + } + pr_debug("%s: ctrl %d qid %d seq %d transaction %d hl %d dhvlen %zu\n", + __func__, ctrl->cntlid, req->sq->qid, req->sq->dhchap_s1, + req->sq->dhchap_tid, data->hl, ctrl->dh_keysize); + return ret; +} + +static int nvmet_auth_success1(struct nvmet_req *req, void *d, int al) +{ + struct nvmf_auth_dhchap_success1_data *data = d; + struct nvmet_ctrl *ctrl = req->sq->ctrl; + int hash_len = nvme_auth_hmac_hash_len(ctrl->shash_id); + + WARN_ON(al < sizeof(*data)); + memset(data, 0, sizeof(*data)); + data->auth_type = NVME_AUTH_DHCHAP_MESSAGES; + data->auth_id = NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1; + data->t_id = cpu_to_le16(req->sq->dhchap_tid); + data->hl = hash_len; + if (req->sq->dhchap_c2) { + if (!ctrl->ctrl_key) { + pr_warn("ctrl %d qid %d no ctrl key\n", + ctrl->cntlid, req->sq->qid); + return NVME_AUTH_DHCHAP_FAILURE_FAILED; + } + if (nvmet_auth_ctrl_hash(req, data->rval, data->hl)) + return NVME_AUTH_DHCHAP_FAILURE_HASH_UNUSABLE; + data->rvalid = 1; + pr_debug("ctrl %d qid %d response %*ph\n", + ctrl->cntlid, req->sq->qid, data->hl, data->rval); + } + return 0; +} + +static void nvmet_auth_failure1(struct nvmet_req *req, void *d, int al) +{ + struct nvmf_auth_dhchap_failure_data *data = d; + + WARN_ON(al < sizeof(*data)); + data->auth_type = NVME_AUTH_COMMON_MESSAGES; + data->auth_id = NVME_AUTH_DHCHAP_MESSAGE_FAILURE1; + data->t_id = cpu_to_le16(req->sq->dhchap_tid); + data->rescode = NVME_AUTH_DHCHAP_FAILURE_REASON_FAILED; + data->rescode_exp = req->sq->dhchap_status; +} + +void nvmet_execute_auth_receive(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + void *d; + u32 al; + u16 status = 0; + + if (req->cmd->auth_receive.secp != NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER) { + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + req->error_loc = + offsetof(struct nvmf_auth_receive_command, secp); + goto done; + } + if (req->cmd->auth_receive.spsp0 != 0x01) { + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + req->error_loc = + offsetof(struct nvmf_auth_receive_command, spsp0); + goto done; + } + if (req->cmd->auth_receive.spsp1 != 0x01) { + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + req->error_loc = + offsetof(struct nvmf_auth_receive_command, spsp1); + goto done; + } + al = le32_to_cpu(req->cmd->auth_receive.al); + if (!al) { + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + req->error_loc = + offsetof(struct nvmf_auth_receive_command, al); + goto done; + } + if (!nvmet_check_transfer_len(req, al)) { + pr_debug("%s: transfer length mismatch (%u)\n", __func__, al); + return; + } + + d = kmalloc(al, GFP_KERNEL); + if (!d) { + status = NVME_SC_INTERNAL; + goto done; + } + pr_debug("%s: ctrl %d qid %d step %x\n", __func__, + ctrl->cntlid, req->sq->qid, req->sq->dhchap_step); + switch (req->sq->dhchap_step) { + case NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE: + if (nvmet_auth_challenge(req, d, al) < 0) { + pr_warn("ctrl %d qid %d: challenge error (%d)\n", + ctrl->cntlid, req->sq->qid, status); + status = NVME_SC_INTERNAL; + break; + } + if (status) { + req->sq->dhchap_status = status; + nvmet_auth_failure1(req, d, al); + pr_warn("ctrl %d qid %d: challenge status (%x)\n", + ctrl->cntlid, req->sq->qid, + req->sq->dhchap_status); + status = 0; + break; + } + req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_REPLY; + break; + case NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1: + status = nvmet_auth_success1(req, d, al); + if (status) { + req->sq->dhchap_status = status; + req->sq->authenticated = false; + nvmet_auth_failure1(req, d, al); + pr_warn("ctrl %d qid %d: success1 status (%x)\n", + ctrl->cntlid, req->sq->qid, + req->sq->dhchap_status); + break; + } + req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2; + break; + case NVME_AUTH_DHCHAP_MESSAGE_FAILURE1: + req->sq->authenticated = false; + nvmet_auth_failure1(req, d, al); + pr_warn("ctrl %d qid %d failure1 (%x)\n", + ctrl->cntlid, req->sq->qid, req->sq->dhchap_status); + break; + default: + pr_warn("ctrl %d qid %d unhandled step (%d)\n", + ctrl->cntlid, req->sq->qid, req->sq->dhchap_step); + req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_FAILURE1; + req->sq->dhchap_status = NVME_AUTH_DHCHAP_FAILURE_FAILED; + nvmet_auth_failure1(req, d, al); + status = 0; + break; + } + + status = nvmet_copy_to_sgl(req, 0, d, al); + kfree(d); +done: + req->cqe->result.u64 = 0; + nvmet_req_complete(req, status); + if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2) + nvmet_auth_sq_free(req->sq); + else if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) { + nvmet_auth_sq_free(req->sq); + nvmet_ctrl_fatal_error(ctrl); + } +} diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 70fb587e9413..f91a56180d3d 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -82,7 +82,7 @@ static void nvmet_execute_prop_get(struct nvmet_req *req) nvmet_req_complete(req, status); } -u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req) +u16 nvmet_parse_fabrics_admin_cmd(struct nvmet_req *req) { struct nvme_command *cmd = req->cmd; @@ -93,6 +93,37 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req) case nvme_fabrics_type_property_get: req->execute = nvmet_execute_prop_get; break; +#ifdef CONFIG_NVME_TARGET_AUTH + case nvme_fabrics_type_auth_send: + req->execute = nvmet_execute_auth_send; + break; + case nvme_fabrics_type_auth_receive: + req->execute = nvmet_execute_auth_receive; + break; +#endif + default: + pr_debug("received unknown capsule type 0x%x\n", + cmd->fabrics.fctype); + req->error_loc = offsetof(struct nvmf_common_command, fctype); + return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + } + + return 0; +} + +u16 nvmet_parse_fabrics_io_cmd(struct nvmet_req *req) +{ + struct nvme_command *cmd = req->cmd; + + switch (cmd->fabrics.fctype) { +#ifdef CONFIG_NVME_TARGET_AUTH + case nvme_fabrics_type_auth_send: + req->execute = nvmet_execute_auth_send; + break; + case nvme_fabrics_type_auth_receive: + req->execute = nvmet_execute_auth_receive; + break; +#endif default: pr_debug("received unknown capsule type 0x%x\n", cmd->fabrics.fctype); @@ -173,6 +204,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) struct nvmf_connect_data *d; struct nvmet_ctrl *ctrl = NULL; u16 status = 0; + int ret; if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data))) return; @@ -215,18 +247,32 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) uuid_copy(&ctrl->hostid, &d->hostid); + ret = nvmet_setup_auth(ctrl); + if (ret < 0) { + pr_err("Failed to setup authentication, error %d\n", ret); + nvmet_ctrl_put(ctrl); + if (ret == -EPERM) + status = (NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR); + else + status = NVME_SC_INTERNAL; + goto out; + } + status = nvmet_install_queue(ctrl, req); if (status) { nvmet_ctrl_put(ctrl); goto out; } - pr_info("creating %s controller %d for subsystem %s for NQN %s%s.\n", + pr_info("creating %s controller %d for subsystem %s for NQN %s%s%s.\n", nvmet_is_disc_subsys(ctrl->subsys) ? "discovery" : "nvm", ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn, - ctrl->pi_support ? " T10-PI is enabled" : ""); + ctrl->pi_support ? " T10-PI is enabled" : "", + nvmet_has_auth(ctrl) ? " with DH-HMAC-CHAP" : ""); req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid); + if (nvmet_has_auth(ctrl)) + nvmet_init_auth(ctrl, req); out: kfree(d); complete: @@ -286,6 +332,9 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid); pr_debug("adding queue %d to ctrl %d.\n", qid, ctrl->cntlid); + req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid); + if (nvmet_has_auth(ctrl)) + nvmet_init_auth(ctrl, req); out: kfree(d); diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 0f5c77e22a0a..9750a7fca268 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -424,9 +424,7 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl) { if (ctrl->ctrl.queue_count > 1) { nvme_stop_queues(&ctrl->ctrl); - blk_mq_tagset_busy_iter(&ctrl->tag_set, - nvme_cancel_request, &ctrl->ctrl); - blk_mq_tagset_wait_completed_request(&ctrl->tag_set); + nvme_cancel_tagset(&ctrl->ctrl); nvme_loop_destroy_io_queues(ctrl); } @@ -434,9 +432,7 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl) if (ctrl->ctrl.state == NVME_CTRL_LIVE) nvme_shutdown_ctrl(&ctrl->ctrl); - blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, - nvme_cancel_request, &ctrl->ctrl); - blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set); + nvme_cancel_admin_tagset(&ctrl->ctrl); nvme_loop_destroy_admin_queue(ctrl); } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 2b3e5719f24e..6ffeeb0a1c49 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -108,6 +108,19 @@ struct nvmet_sq { u16 size; u32 sqhd; bool sqhd_disabled; +#ifdef CONFIG_NVME_TARGET_AUTH + struct delayed_work auth_expired_work; + bool authenticated; + u16 dhchap_tid; + u16 dhchap_status; + int dhchap_step; + u8 *dhchap_c1; + u8 *dhchap_c2; + u32 dhchap_s1; + u32 dhchap_s2; + u8 *dhchap_skey; + int dhchap_skey_len; +#endif struct completion free_done; struct completion confirm_done; }; @@ -209,6 +222,15 @@ struct nvmet_ctrl { u64 err_counter; struct nvme_error_slot slots[NVMET_ERROR_LOG_SLOTS]; bool pi_support; +#ifdef CONFIG_NVME_TARGET_AUTH + struct nvme_dhchap_key *host_key; + struct nvme_dhchap_key *ctrl_key; + u8 shash_id; + struct crypto_kpp *dh_tfm; + u8 dh_gid; + u8 *dh_key; + size_t dh_keysize; +#endif }; struct nvmet_subsys { @@ -271,6 +293,12 @@ static inline struct nvmet_subsys *namespaces_to_subsys( struct nvmet_host { struct config_group group; + u8 *dhchap_secret; + u8 *dhchap_ctrl_secret; + u8 dhchap_key_hash; + u8 dhchap_ctrl_key_hash; + u8 dhchap_hash_id; + u8 dhchap_dhgroup_id; }; static inline struct nvmet_host *to_host(struct config_item *item) @@ -420,7 +448,8 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req); u16 nvmet_bdev_zns_parse_io_cmd(struct nvmet_req *req); u16 nvmet_parse_admin_cmd(struct nvmet_req *req); u16 nvmet_parse_discovery_cmd(struct nvmet_req *req); -u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req); +u16 nvmet_parse_fabrics_admin_cmd(struct nvmet_req *req); +u16 nvmet_parse_fabrics_io_cmd(struct nvmet_req *req); bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, struct nvmet_sq *sq, const struct nvmet_fabrics_ops *ops); @@ -668,4 +697,48 @@ static inline void nvmet_req_bio_put(struct nvmet_req *req, struct bio *bio) bio_put(bio); } +#ifdef CONFIG_NVME_TARGET_AUTH +void nvmet_execute_auth_send(struct nvmet_req *req); +void nvmet_execute_auth_receive(struct nvmet_req *req); +int nvmet_auth_set_key(struct nvmet_host *host, const char *secret, + bool set_ctrl); +int nvmet_auth_set_host_hash(struct nvmet_host *host, const char *hash); +int nvmet_setup_auth(struct nvmet_ctrl *ctrl); +void nvmet_init_auth(struct nvmet_ctrl *ctrl, struct nvmet_req *req); +void nvmet_destroy_auth(struct nvmet_ctrl *ctrl); +void nvmet_auth_sq_free(struct nvmet_sq *sq); +int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id); +bool nvmet_check_auth_status(struct nvmet_req *req); +int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, + unsigned int hash_len); +int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response, + unsigned int hash_len); +static inline bool nvmet_has_auth(struct nvmet_ctrl *ctrl) +{ + return ctrl->host_key != NULL; +} +int nvmet_auth_ctrl_exponential(struct nvmet_req *req, + u8 *buf, int buf_size); +int nvmet_auth_ctrl_sesskey(struct nvmet_req *req, + u8 *buf, int buf_size); +#else +static inline int nvmet_setup_auth(struct nvmet_ctrl *ctrl) +{ + return 0; +} +static inline void nvmet_init_auth(struct nvmet_ctrl *ctrl, + struct nvmet_req *req) {}; +static inline void nvmet_destroy_auth(struct nvmet_ctrl *ctrl) {}; +static inline void nvmet_auth_sq_free(struct nvmet_sq *sq) {}; +static inline bool nvmet_check_auth_status(struct nvmet_req *req) +{ + return true; +} +static inline bool nvmet_has_auth(struct nvmet_ctrl *ctrl) +{ + return false; +} +static inline const char *nvmet_dhchap_dhgroup_name(u8 dhgid) { return NULL; } +#endif + #endif /* _NVMET_H */ diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 0a9542599ad1..dc3b4dc8fe08 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1839,7 +1839,8 @@ static int __init nvmet_tcp_init(void) { int ret; - nvmet_tcp_wq = alloc_workqueue("nvmet_tcp_wq", WQ_HIGHPRI, 0); + nvmet_tcp_wq = alloc_workqueue("nvmet_tcp_wq", + WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); if (!nvmet_tcp_wq) return -ENOMEM; diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 4df8bf6505fc..ea82821599f6 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1725,7 +1725,7 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, dasd_put_device(device); } - /* check for for attention message */ + /* check for attention message */ if (scsw_dstat(&irb->scsw) & DEV_STAT_ATTENTION) { device = dasd_device_from_cdev_locked(cdev); if (!IS_ERR(device)) { diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index e9edf3b6ed7c..94ee59864971 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -639,6 +639,7 @@ static void dasd_diag_setup_blk_queue(struct dasd_block *block) /* With page sized segments each segment can be translated into one idaw/tidaw */ blk_queue_max_segment_size(q, PAGE_SIZE); blk_queue_segment_boundary(q, PAGE_SIZE - 1); + blk_queue_dma_alignment(q, PAGE_SIZE - 1); } static int dasd_diag_pe_handler(struct dasd_device *device, diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 836838f7d686..3cc93e2e4e15 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -6626,6 +6626,7 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block) /* With page sized segments each segment can be translated into one idaw/tidaw */ blk_queue_max_segment_size(q, PAGE_SIZE); blk_queue_segment_boundary(q, PAGE_SIZE - 1); + blk_queue_dma_alignment(q, PAGE_SIZE - 1); } static struct ccw_driver dasd_eckd_driver = { diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 4d8d1759775a..5187705bd0f3 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -863,7 +863,7 @@ dcssblk_submit_bio(struct bio *bio) unsigned long source_addr; unsigned long bytes_done; - blk_queue_split(&bio); + bio = bio_split_to_limits(bio); bytes_done = 0; dev_info = bio->bi_bdev->bd_disk->private_data; diff --git a/include/crypto/hash.h b/include/crypto/hash.h index f140e4643949..f5841992dc9b 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -718,6 +718,8 @@ static inline void ahash_request_set_crypt(struct ahash_request *req, struct crypto_shash *crypto_alloc_shash(const char *alg_name, u32 type, u32 mask); +int crypto_has_shash(const char *alg_name, u32 type, u32 mask); + static inline struct crypto_tfm *crypto_shash_tfm(struct crypto_shash *tfm) { return &tfm->base; diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h index cccceadc164b..24d01e9877c1 100644 --- a/include/crypto/kpp.h +++ b/include/crypto/kpp.h @@ -104,6 +104,8 @@ struct kpp_alg { */ struct crypto_kpp *crypto_alloc_kpp(const char *alg_name, u32 type, u32 mask); +int crypto_has_kpp(const char *alg_name, u32 type, u32 mask); + static inline struct crypto_tfm *crypto_kpp_tfm(struct crypto_kpp *tfm) { return &tfm->base; diff --git a/include/linux/base64.h b/include/linux/base64.h new file mode 100644 index 000000000000..660d4cb1ef31 --- /dev/null +++ b/include/linux/base64.h @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * base64 encoding, lifted from fs/crypto/fname.c. + */ + +#ifndef _LINUX_BASE64_H +#define _LINUX_BASE64_H + +#include + +#define BASE64_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3) + +int base64_encode(const u8 *src, int len, char *dst); +int base64_decode(const char *src, int len, u8 *dst); + +#endif /* _LINUX_BASE64_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dccdf1551c62..84b13fdd34a7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -140,6 +140,8 @@ struct gendisk { struct request_queue *queue; void *private_data; + struct bio_set bio_split; + int flags; unsigned long state; #define GD_NEED_PART_SCAN 0 @@ -531,7 +533,6 @@ struct request_queue { struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; - struct bio_set bio_split; struct dentry *debugfs_dir; struct dentry *sched_debugfs_dir; @@ -864,9 +865,9 @@ void blk_request_module(dev_t devt); extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); void submit_bio_noacct(struct bio *bio); +struct bio *bio_split_to_limits(struct bio *bio); extern int blk_lld_busy(struct request_queue *q); -extern void blk_queue_split(struct bio **); extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h new file mode 100644 index 000000000000..dcb8030062dd --- /dev/null +++ b/include/linux/nvme-auth.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 Hannes Reinecke, SUSE Software Solutions + */ + +#ifndef _NVME_AUTH_H +#define _NVME_AUTH_H + +#include + +struct nvme_dhchap_key { + u8 *key; + size_t len; + u8 hash; +}; + +u32 nvme_auth_get_seqnum(void); +const char *nvme_auth_dhgroup_name(u8 dhgroup_id); +const char *nvme_auth_dhgroup_kpp(u8 dhgroup_id); +u8 nvme_auth_dhgroup_id(const char *dhgroup_name); + +const char *nvme_auth_hmac_name(u8 hmac_id); +const char *nvme_auth_digest_name(u8 hmac_id); +size_t nvme_auth_hmac_hash_len(u8 hmac_id); +u8 nvme_auth_hmac_id(const char *hmac_name); + +struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret, + u8 key_hash); +void nvme_auth_free_key(struct nvme_dhchap_key *key); +u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn); +int nvme_auth_generate_key(u8 *secret, struct nvme_dhchap_key **ret_key); +int nvme_auth_augmented_challenge(u8 hmac_id, u8 *skey, size_t skey_len, + u8 *challenge, u8 *aug, size_t hlen); +int nvme_auth_gen_privkey(struct crypto_kpp *dh_tfm, u8 dh_gid); +int nvme_auth_gen_pubkey(struct crypto_kpp *dh_tfm, + u8 *host_key, size_t host_key_len); +int nvme_auth_gen_shared_secret(struct crypto_kpp *dh_tfm, + u8 *ctrl_key, size_t ctrl_key_len, + u8 *sess_key, size_t sess_key_len); + +#endif /* _NVME_AUTH_H */ diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 07cfc922f8e4..ae53d74f3696 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -19,6 +19,7 @@ #define NVMF_TRSVCID_SIZE 32 #define NVMF_TRADDR_SIZE 256 #define NVMF_TSAS_SIZE 256 +#define NVMF_AUTH_HASH_LEN 64 #define NVME_DISC_SUBSYS_NAME "nqn.2014-08.org.nvmexpress.discovery" @@ -711,6 +712,10 @@ enum { NVME_AER_VS = 7, }; +enum { + NVME_AER_ERROR_PERSIST_INT_ERR = 0x03, +}; + enum { NVME_AER_NOTICE_NS_CHANGED = 0x00, NVME_AER_NOTICE_FW_ACT_STARTING = 0x01, @@ -1369,6 +1374,8 @@ enum nvmf_capsule_command { nvme_fabrics_type_property_set = 0x00, nvme_fabrics_type_connect = 0x01, nvme_fabrics_type_property_get = 0x04, + nvme_fabrics_type_auth_send = 0x05, + nvme_fabrics_type_auth_receive = 0x06, }; #define nvme_fabrics_type_name(type) { type, #type } @@ -1376,7 +1383,9 @@ enum nvmf_capsule_command { __print_symbolic(type, \ nvme_fabrics_type_name(nvme_fabrics_type_property_set), \ nvme_fabrics_type_name(nvme_fabrics_type_connect), \ - nvme_fabrics_type_name(nvme_fabrics_type_property_get)) + nvme_fabrics_type_name(nvme_fabrics_type_property_get), \ + nvme_fabrics_type_name(nvme_fabrics_type_auth_send), \ + nvme_fabrics_type_name(nvme_fabrics_type_auth_receive)) /* * If not fabrics command, fctype will be ignored. @@ -1472,6 +1481,11 @@ struct nvmf_connect_command { __u8 resv4[12]; }; +enum { + NVME_CONNECT_AUTHREQ_ASCR = (1 << 2), + NVME_CONNECT_AUTHREQ_ATR = (1 << 1), +}; + struct nvmf_connect_data { uuid_t hostid; __le16 cntlid; @@ -1506,6 +1520,200 @@ struct nvmf_property_get_command { __u8 resv4[16]; }; +struct nvmf_auth_common_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[19]; + union nvme_data_ptr dptr; + __u8 resv3; + __u8 spsp0; + __u8 spsp1; + __u8 secp; + __le32 al_tl; + __u8 resv4[16]; +}; + +struct nvmf_auth_send_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[19]; + union nvme_data_ptr dptr; + __u8 resv3; + __u8 spsp0; + __u8 spsp1; + __u8 secp; + __le32 tl; + __u8 resv4[16]; +}; + +struct nvmf_auth_receive_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[19]; + union nvme_data_ptr dptr; + __u8 resv3; + __u8 spsp0; + __u8 spsp1; + __u8 secp; + __le32 al; + __u8 resv4[16]; +}; + +/* Value for secp */ +enum { + NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER = 0xe9, +}; + +/* Defined value for auth_type */ +enum { + NVME_AUTH_COMMON_MESSAGES = 0x00, + NVME_AUTH_DHCHAP_MESSAGES = 0x01, +}; + +/* Defined messages for auth_id */ +enum { + NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE = 0x00, + NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE = 0x01, + NVME_AUTH_DHCHAP_MESSAGE_REPLY = 0x02, + NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1 = 0x03, + NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2 = 0x04, + NVME_AUTH_DHCHAP_MESSAGE_FAILURE2 = 0xf0, + NVME_AUTH_DHCHAP_MESSAGE_FAILURE1 = 0xf1, +}; + +struct nvmf_auth_dhchap_protocol_descriptor { + __u8 authid; + __u8 rsvd; + __u8 halen; + __u8 dhlen; + __u8 idlist[60]; +}; + +enum { + NVME_AUTH_DHCHAP_AUTH_ID = 0x01, +}; + +/* Defined hash functions for DH-HMAC-CHAP authentication */ +enum { + NVME_AUTH_HASH_SHA256 = 0x01, + NVME_AUTH_HASH_SHA384 = 0x02, + NVME_AUTH_HASH_SHA512 = 0x03, + NVME_AUTH_HASH_INVALID = 0xff, +}; + +/* Defined Diffie-Hellman group identifiers for DH-HMAC-CHAP authentication */ +enum { + NVME_AUTH_DHGROUP_NULL = 0x00, + NVME_AUTH_DHGROUP_2048 = 0x01, + NVME_AUTH_DHGROUP_3072 = 0x02, + NVME_AUTH_DHGROUP_4096 = 0x03, + NVME_AUTH_DHGROUP_6144 = 0x04, + NVME_AUTH_DHGROUP_8192 = 0x05, + NVME_AUTH_DHGROUP_INVALID = 0xff, +}; + +union nvmf_auth_protocol { + struct nvmf_auth_dhchap_protocol_descriptor dhchap; +}; + +struct nvmf_auth_dhchap_negotiate_data { + __u8 auth_type; + __u8 auth_id; + __le16 rsvd; + __le16 t_id; + __u8 sc_c; + __u8 napd; + union nvmf_auth_protocol auth_protocol[]; +}; + +struct nvmf_auth_dhchap_challenge_data { + __u8 auth_type; + __u8 auth_id; + __u16 rsvd1; + __le16 t_id; + __u8 hl; + __u8 rsvd2; + __u8 hashid; + __u8 dhgid; + __le16 dhvlen; + __le32 seqnum; + /* 'hl' bytes of challenge value */ + __u8 cval[]; + /* followed by 'dhvlen' bytes of DH value */ +}; + +struct nvmf_auth_dhchap_reply_data { + __u8 auth_type; + __u8 auth_id; + __le16 rsvd1; + __le16 t_id; + __u8 hl; + __u8 rsvd2; + __u8 cvalid; + __u8 rsvd3; + __le16 dhvlen; + __le32 seqnum; + /* 'hl' bytes of response data */ + __u8 rval[]; + /* followed by 'hl' bytes of Challenge value */ + /* followed by 'dhvlen' bytes of DH value */ +}; + +enum { + NVME_AUTH_DHCHAP_RESPONSE_VALID = (1 << 0), +}; + +struct nvmf_auth_dhchap_success1_data { + __u8 auth_type; + __u8 auth_id; + __le16 rsvd1; + __le16 t_id; + __u8 hl; + __u8 rsvd2; + __u8 rvalid; + __u8 rsvd3[7]; + /* 'hl' bytes of response value if 'rvalid' is set */ + __u8 rval[]; +}; + +struct nvmf_auth_dhchap_success2_data { + __u8 auth_type; + __u8 auth_id; + __le16 rsvd1; + __le16 t_id; + __u8 rsvd2[10]; +}; + +struct nvmf_auth_dhchap_failure_data { + __u8 auth_type; + __u8 auth_id; + __le16 rsvd1; + __le16 t_id; + __u8 rescode; + __u8 rescode_exp; +}; + +enum { + NVME_AUTH_DHCHAP_FAILURE_REASON_FAILED = 0x01, +}; + +enum { + NVME_AUTH_DHCHAP_FAILURE_FAILED = 0x01, + NVME_AUTH_DHCHAP_FAILURE_NOT_USABLE = 0x02, + NVME_AUTH_DHCHAP_FAILURE_CONCAT_MISMATCH = 0x03, + NVME_AUTH_DHCHAP_FAILURE_HASH_UNUSABLE = 0x04, + NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE = 0x05, + NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD = 0x06, + NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE = 0x07, +}; + + struct nvme_dbbuf { __u8 opcode; __u8 flags; @@ -1549,6 +1757,9 @@ struct nvme_command { struct nvmf_connect_command connect; struct nvmf_property_set_command prop_set; struct nvmf_property_get_command prop_get; + struct nvmf_auth_common_command auth_common; + struct nvmf_auth_send_command auth_send; + struct nvmf_auth_receive_command auth_receive; struct nvme_dbbuf dbbuf; struct nvme_directive_cmd directive; }; diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index ca33092354ab..677edaab2b66 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -15,6 +15,8 @@ #define UBLK_CMD_DEL_DEV 0x05 #define UBLK_CMD_START_DEV 0x06 #define UBLK_CMD_STOP_DEV 0x07 +#define UBLK_CMD_SET_PARAMS 0x08 +#define UBLK_CMD_GET_PARAMS 0x09 /* * IO commands, issued by ublk server, and handled by ublk driver. @@ -28,12 +30,21 @@ * this IO request, request's handling result is committed to ublk * driver, meantime FETCH_REQ is piggyback, and FETCH_REQ has to be * handled before completing io request. + * + * NEED_GET_DATA: only used for write requests to set io addr and copy data + * When NEED_GET_DATA is set, ublksrv has to issue UBLK_IO_NEED_GET_DATA + * command after ublk driver returns UBLK_IO_RES_NEED_GET_DATA. + * + * It is only used if ublksrv set UBLK_F_NEED_GET_DATA flag + * while starting a ublk device. */ #define UBLK_IO_FETCH_REQ 0x20 #define UBLK_IO_COMMIT_AND_FETCH_REQ 0x21 +#define UBLK_IO_NEED_GET_DATA 0x22 /* only ABORT means that no re-fetch */ #define UBLK_IO_RES_OK 0 +#define UBLK_IO_RES_NEED_GET_DATA 1 #define UBLK_IO_RES_ABORT (-ENODEV) #define UBLKSRV_CMD_BUF_OFFSET 0 @@ -54,6 +65,15 @@ */ #define UBLK_F_URING_CMD_COMP_IN_TASK (1ULL << 1) +/* + * User should issue io cmd again for write requests to + * set io buffer address and copy data from bio vectors + * to the userspace io buffer. + * + * In this mode, task_work is not used. + */ +#define UBLK_F_NEED_GET_DATA (1UL << 2) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 @@ -78,22 +98,23 @@ struct ublksrv_ctrl_cmd { struct ublksrv_ctrl_dev_info { __u16 nr_hw_queues; __u16 queue_depth; - __u16 block_size; __u16 state; + __u16 pad0; - __u32 rq_max_blocks; + __u32 max_io_buf_bytes; __u32 dev_id; - __u64 dev_blocks; - __s32 ublksrv_pid; - __s32 reserved0; + __u32 pad1; + __u64 flags; - __u64 flags_reserved; /* For ublksrv internal use, invisible to ublk driver */ __u64 ublksrv_flags; - __u64 reserved1[9]; + + __u64 reserved0; + __u64 reserved1; + __u64 reserved2; }; #define UBLK_IO_OP_READ 0 @@ -158,4 +179,49 @@ struct ublksrv_io_cmd { __u64 addr; }; +struct ublk_param_basic { +#define UBLK_ATTR_READ_ONLY (1 << 0) +#define UBLK_ATTR_ROTATIONAL (1 << 1) +#define UBLK_ATTR_VOLATILE_CACHE (1 << 2) +#define UBLK_ATTR_FUA (1 << 3) + __u32 attrs; + __u8 logical_bs_shift; + __u8 physical_bs_shift; + __u8 io_opt_shift; + __u8 io_min_shift; + + __u32 max_sectors; + __u32 chunk_sectors; + + __u64 dev_sectors; + __u64 virt_boundary_mask; +}; + +struct ublk_param_discard { + __u32 discard_alignment; + + __u32 discard_granularity; + __u32 max_discard_sectors; + + __u32 max_write_zeroes_sectors; + __u16 max_discard_segments; + __u16 reserved0; +}; + +struct ublk_params { + /* + * Total length of parameters, userspace has to set 'len' for both + * SET_PARAMS and GET_PARAMS command, and driver may update len + * if two sides use different version of 'ublk_params', same with + * 'types' fields. + */ + __u32 len; +#define UBLK_PARAM_TYPE_BASIC (1 << 0) +#define UBLK_PARAM_TYPE_DISCARD (1 << 1) + __u32 types; /* types of parameter included */ + + struct ublk_param_basic basic; + struct ublk_param_discard discard; +}; + #endif diff --git a/lib/Makefile b/lib/Makefile index 67482f5ec0e8..441795bf5d33 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -46,7 +46,7 @@ obj-y += bcd.o sort.o parser.o debug_locks.o random32.o \ bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \ list_sort.o uuid.o iov_iter.o clz_ctz.o \ bsearch.o find_bit.o llist.o memweight.o kfifo.o \ - percpu-refcount.o rhashtable.o \ + percpu-refcount.o rhashtable.o base64.o \ once.o refcount.o usercopy.o errseq.o bucket_locks.o \ generic-radix-tree.o obj-$(CONFIG_STRING_SELFTEST) += test_string.o diff --git a/lib/base64.c b/lib/base64.c new file mode 100644 index 000000000000..b736a7a431c5 --- /dev/null +++ b/lib/base64.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * base64.c - RFC4648-compliant base64 encoding + * + * Copyright (c) 2020 Hannes Reinecke, SUSE + * + * Based on the base64url routines from fs/crypto/fname.c + * (which are using the URL-safe base64 encoding), + * modified to use the standard coding table from RFC4648 section 4. + */ + +#include +#include +#include +#include +#include + +static const char base64_table[65] = + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"; + +/** + * base64_encode() - base64-encode some binary data + * @src: the binary data to encode + * @srclen: the length of @src in bytes + * @dst: (output) the base64-encoded string. Not NUL-terminated. + * + * Encodes data using base64 encoding, i.e. the "Base 64 Encoding" specified + * by RFC 4648, including the '='-padding. + * + * Return: the length of the resulting base64-encoded string in bytes. + */ +int base64_encode(const u8 *src, int srclen, char *dst) +{ + u32 ac = 0; + int bits = 0; + int i; + char *cp = dst; + + for (i = 0; i < srclen; i++) { + ac = (ac << 8) | src[i]; + bits += 8; + do { + bits -= 6; + *cp++ = base64_table[(ac >> bits) & 0x3f]; + } while (bits >= 6); + } + if (bits) { + *cp++ = base64_table[(ac << (6 - bits)) & 0x3f]; + bits -= 6; + } + while (bits < 0) { + *cp++ = '='; + bits += 2; + } + return cp - dst; +} +EXPORT_SYMBOL_GPL(base64_encode); + +/** + * base64_decode() - base64-decode a string + * @src: the string to decode. Doesn't need to be NUL-terminated. + * @srclen: the length of @src in bytes + * @dst: (output) the decoded binary data + * + * Decodes a string using base64 encoding, i.e. the "Base 64 Encoding" + * specified by RFC 4648, including the '='-padding. + * + * This implementation hasn't been optimized for performance. + * + * Return: the length of the resulting decoded binary data in bytes, + * or -1 if the string isn't a valid base64 string. + */ +int base64_decode(const char *src, int srclen, u8 *dst) +{ + u32 ac = 0; + int bits = 0; + int i; + u8 *bp = dst; + + for (i = 0; i < srclen; i++) { + const char *p = strchr(base64_table, src[i]); + + if (src[i] == '=') { + ac = (ac << 6); + bits += 6; + if (bits >= 8) + bits -= 8; + continue; + } + if (p == NULL || src[i] == 0) + return -1; + ac = (ac << 6) | (p - base64_table); + bits += 6; + if (bits >= 8) { + bits -= 8; + *bp++ = (u8)(ac >> bits); + } + } + if (ac & ((1 << bits) - 1)) + return -1; + return bp - dst; +} +EXPORT_SYMBOL_GPL(base64_decode);