From 9b1ebce6a1fded90d4a1c6c57dc6262dac4c4c14 Mon Sep 17 00:00:00 2001 From: Su Hui Date: Tue, 11 Jun 2024 15:37:00 +0800 Subject: block: sed-opal: avoid possible wrong address reference in read_sed_opal_key() Clang static checker (scan-build) warning: block/sed-opal.c:line 317, column 3 Value stored to 'ret' is never read. Fix this problem by returning the error code when keyring_search() failed. Otherwise, 'key' will have a wrong value when 'kerf' stores the error code. Fixes: 3bfeb6125664 ("block: sed-opal: keyring support for SED keys") Signed-off-by: Su Hui Link: https://lore.kernel.org/r/20240611073659.429582-1-suhui@nfschina.com Signed-off-by: Jens Axboe --- block/sed-opal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block') diff --git a/block/sed-opal.c b/block/sed-opal.c index 14fe0fef811c..598fd3e7fcc8 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -314,7 +314,7 @@ static int read_sed_opal_key(const char *key_name, u_char *buffer, int buflen) &key_type_user, key_name, true); if (IS_ERR(kref)) - ret = PTR_ERR(kref); + return PTR_ERR(kref); key = key_ref_to_ptr(kref); down_read(&key->sem); -- cgit v1.2.3 From 1933192a91be0a570663a3c6310c46e4ce3b2baa Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 7 Jun 2024 09:21:26 +0900 Subject: block: Optimize disk zone resource cleanup For zoned block devices using zone write plugging, an rcu_barrier() call is needed in disk_free_zone_resources() to synchronize freeing of zone write plugs and the destrution of the mempool used to allocate the plugs. The barrier call does slow down a little teardown of zoned block devices but should not affect teardown of regular block devices or zoned block devices that do not use zone write plugging (e.g. zoned DM devices that do not require zone append emulation). Modify disk_free_zone_resources() to return early if we do not have a mempool to start with, that is, if the device does not use zone write plugging. This avoids the costly rcu_barrier() and speeds up disk teardown. Reported-by: Mikulas Patocka Fixes: dd291d77cc90 ("block: Introduce zone write plugging") Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Tested-by: Mikulas Patocka Reviewed-by: Niklas Cassel Link: https://lore.kernel.org/r/20240607002126.104227-1-dlemoal@kernel.org Signed-off-by: Jens Axboe --- block/blk-zoned.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'block') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 52abebf56027..08d7dfe8bd93 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -1552,6 +1552,9 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk) void disk_free_zone_resources(struct gendisk *disk) { + if (!disk->zone_wplugs_pool) + return; + cancel_work_sync(&disk->zone_wplugs_work); if (disk->zone_wplugs_wq) { -- cgit v1.2.3 From d0321c812d89c5910d8da8e4b10c891c6b96ff70 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Sat, 8 Jun 2024 22:31:15 +0800 Subject: block: fix request.queuelist usage in flush Friedrich Weber reported a kernel crash problem and bisected to commit 81ada09cc25e ("blk-flush: reuse rq queuelist in flush state machine"). The root cause is that we use "list_move_tail(&rq->queuelist, pending)" in the PREFLUSH/POSTFLUSH sequences. But rq->queuelist.next == xxx since it's popped out from plug->cached_rq in __blk_mq_alloc_requests_batch(). We don't initialize its queuelist just for this first request, although the queuelist of all later popped requests will be initialized. Fix it by changing to use "list_add_tail(&rq->queuelist, pending)" so rq->queuelist doesn't need to be initialized. It should be ok since rq can't be on any list when PREFLUSH or POSTFLUSH, has no move actually. Please note the commit 81ada09cc25e ("blk-flush: reuse rq queuelist in flush state machine") also has another requirement that no drivers would touch rq->queuelist after blk_mq_end_request() since we will reuse it to add rq to the post-flush pending list in POSTFLUSH. If this is not true, we will have to revert that commit IMHO. This updated version adds "list_del_init(&rq->queuelist)" in flush rq callback since the dm layer may submit request of a weird invalid format (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH), which causes double list_add if without this "list_del_init(&rq->queuelist)". The weird invalid format problem should be fixed in dm layer. Reported-by: Friedrich Weber Closes: https://lore.kernel.org/lkml/14b89dfb-505c-49f7-aebb-01c54451db40@proxmox.com/ Closes: https://lore.kernel.org/lkml/c9d03ff7-27c5-4ebd-b3f6-5a90d96f35ba@proxmox.com/ Fixes: 81ada09cc25e ("blk-flush: reuse rq queuelist in flush state machine") Cc: Christoph Hellwig Cc: ming.lei@redhat.com Cc: bvanassche@acm.org Tested-by: Friedrich Weber Signed-off-by: Chengming Zhou Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240608143115.972486-1-chengming.zhou@linux.dev Signed-off-by: Jens Axboe --- block/blk-flush.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-flush.c b/block/blk-flush.c index c17cf8ed8113..cca4f9131f79 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -185,7 +185,7 @@ static void blk_flush_complete_seq(struct request *rq, /* queue for flush */ if (list_empty(pending)) fq->flush_pending_since = jiffies; - list_move_tail(&rq->queuelist, pending); + list_add_tail(&rq->queuelist, pending); break; case REQ_FSEQ_DATA: @@ -263,6 +263,7 @@ static enum rq_end_io_ret flush_end_io(struct request *flush_rq, unsigned int seq = blk_flush_cur_seq(rq); BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH); + list_del_init(&rq->queuelist); blk_flush_complete_seq(rq, fq, seq, error); } -- cgit v1.2.3 From e038ee6189842e9662d2fc59d09dbcf48350cf99 Mon Sep 17 00:00:00 2001 From: Anuj Gupta Date: Mon, 10 Jun 2024 16:41:44 +0530 Subject: block: unmap and free user mapped integrity via submitter The user mapped intergity is copied back and unpinned by bio_integrity_free which is a low-level routine. Do it via the submitter rather than doing it in the low-level block layer code, to split the submitter side from the consumer side of the bio. Signed-off-by: Anuj Gupta Signed-off-by: Kanchan Joshi Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20240610111144.14647-1-anuj20.g@samsung.com Signed-off-by: Jens Axboe --- block/bio-integrity.c | 26 ++++++++++++++++++++++++-- drivers/nvme/host/ioctl.c | 15 +++++++++++---- include/linux/bio.h | 4 ++++ 3 files changed, 39 insertions(+), 6 deletions(-) (limited to 'block') diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 2e3e8e04961e..8b528e12136f 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -144,16 +144,38 @@ void bio_integrity_free(struct bio *bio) struct bio_integrity_payload *bip = bio_integrity(bio); struct bio_set *bs = bio->bi_pool; + if (bip->bip_flags & BIP_INTEGRITY_USER) + return; if (bip->bip_flags & BIP_BLOCK_INTEGRITY) kfree(bvec_virt(bip->bip_vec)); - else if (bip->bip_flags & BIP_INTEGRITY_USER) - bio_integrity_unmap_user(bip); __bio_integrity_free(bs, bip); bio->bi_integrity = NULL; bio->bi_opf &= ~REQ_INTEGRITY; } +/** + * bio_integrity_unmap_free_user - Unmap and free bio user integrity payload + * @bio: bio containing bip to be unmapped and freed + * + * Description: Used to unmap and free the user mapped integrity portion of a + * bio. Submitter attaching the user integrity buffer is responsible for + * unmapping and freeing it during completion. + */ +void bio_integrity_unmap_free_user(struct bio *bio) +{ + struct bio_integrity_payload *bip = bio_integrity(bio); + struct bio_set *bs = bio->bi_pool; + + if (WARN_ON_ONCE(!(bip->bip_flags & BIP_INTEGRITY_USER))) + return; + bio_integrity_unmap_user(bip); + __bio_integrity_free(bs, bip); + bio->bi_integrity = NULL; + bio->bi_opf &= ~REQ_INTEGRITY; +} +EXPORT_SYMBOL(bio_integrity_unmap_free_user); + /** * bio_integrity_add_page - Attach integrity metadata * @bio: bio to update diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 9d9d2a127c4e..8b69427a4476 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -111,6 +111,13 @@ static struct request *nvme_alloc_user_request(struct request_queue *q, return req; } +static void nvme_unmap_bio(struct bio *bio) +{ + if (bio_integrity(bio)) + bio_integrity_unmap_free_user(bio); + blk_rq_unmap_user(bio); +} + static int nvme_map_user_request(struct request *req, u64 ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags) @@ -157,7 +164,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, out_unmap: if (bio) - blk_rq_unmap_user(bio); + nvme_unmap_bio(bio); out: blk_mq_free_request(req); return ret; @@ -195,7 +202,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, if (result) *result = le64_to_cpu(nvme_req(req)->result.u64); if (bio) - blk_rq_unmap_user(bio); + nvme_unmap_bio(bio); blk_mq_free_request(req); if (effects) @@ -406,7 +413,7 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd, struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); if (pdu->bio) - blk_rq_unmap_user(pdu->bio); + nvme_unmap_bio(pdu->bio); io_uring_cmd_done(ioucmd, pdu->status, pdu->result, issue_flags); } @@ -432,7 +439,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, */ if (blk_rq_is_poll(req)) { if (pdu->bio) - blk_rq_unmap_user(pdu->bio); + nvme_unmap_bio(pdu->bio); io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status); } else { io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); diff --git a/include/linux/bio.h b/include/linux/bio.h index d5379548d684..818e93612947 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -731,6 +731,7 @@ static inline bool bioset_initialized(struct bio_set *bs) bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed); +void bio_integrity_unmap_free_user(struct bio *bio); extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); extern bool bio_integrity_prep(struct bio *); @@ -807,6 +808,9 @@ static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf, { return -EINVAL; } +static inline void bio_integrity_unmap_free_user(struct bio *bio) +{ +} #endif /* CONFIG_BLK_DEV_INTEGRITY */ -- cgit v1.2.3