Merge tag 'for-5.17/block-2022-01-11' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Unify where the struct request handling code is located in the blk-mq
   code (Christoph)

 - Header cleanups (Christoph)

 - Clean up the io_context handling code (Christoph, me)

 - Get rid of ->rq_disk in struct request (Christoph)

 - Error handling fix for add_disk() (Christoph)

 - request allocation cleanusp (Christoph)

 - Documentation updates (Eric, Matthew)

 - Remove trivial crypto unregister helper (Eric)

 - Reduce shared tag overhead (John)

 - Reduce poll_stats memory overhead (me)

 - Known indirect function call for dio (me)

 - Use atomic references for struct request (me)

 - Support request list issue for block and NVMe (me)

 - Improve queue dispatch pinning (Ming)

 - Improve the direct list issue code (Keith)

 - BFQ improvements (Jan)

 - Direct completion helper and use it in mmc block (Sebastian)

 - Use raw spinlock for the blktrace code (Wander)

 - fsync error handling fix (Ye)

 - Various fixes and cleanups (Lukas, Randy, Yang, Tetsuo, Ming, me)

* tag 'for-5.17/block-2022-01-11' of git://git.kernel.dk/linux-block: (132 commits)
  MAINTAINERS: add entries for block layer documentation
  docs: block: remove queue-sysfs.rst
  docs: sysfs-block: document virt_boundary_mask
  docs: sysfs-block: document stable_writes
  docs: sysfs-block: fill in missing documentation from queue-sysfs.rst
  docs: sysfs-block: add contact for nomerges
  docs: sysfs-block: sort alphabetically
  docs: sysfs-block: move to stable directory
  block: don't protect submit_bio_checks by q_usage_counter
  block: fix old-style declaration
  nvme-pci: fix queue_rqs list splitting
  block: introduce rq_list_move
  block: introduce rq_list_for_each_safe macro
  block: move rq_list macros to blk-mq.h
  block: drop needless assignment in set_task_ioprio()
  block: remove unnecessary trailing '\'
  bio.h: fix kernel-doc warnings
  block: check minor range in device_add_disk()
  block: use "unsigned long" for blk_validate_block_size().
  block: fix error unwinding in device_add_disk
  ...

1 files changed, 37 insertions, 354 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 1378d084c770..97f8bc8d3a79 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -16,7 +16,6 @@
 #include <linux/module.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
-#include <linux/blk-mq.h>
 #include <linux/blk-pm.h>
 #include <linux/blk-integrity.h>
 #include <linux/highmem.h>
@@ -40,6 +39,7 @@
 #include <linux/debugfs.h>
 #include <linux/bpf.h>
 #include <linux/psi.h>
+#include <linux/part_stat.h>
 #include <linux/sched/sysctl.h>
 #include <linux/blk-crypto.h>
 
@@ -47,7 +47,6 @@
 #include <trace/events/block.h>
 
 #include "blk.h"
-#include "blk-mq.h"
 #include "blk-mq-sched.h"
 #include "blk-pm.h"
 #include "blk-throttle.h"
@@ -67,6 +66,7 @@ DEFINE_IDA(blk_queue_ida);
  * For queue allocation
  */
 struct kmem_cache *blk_requestq_cachep;
+struct kmem_cache *blk_requestq_srcu_cachep;
 
 /*
  * Controlling structure to kblockd
@@ -109,23 +109,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set);
 
-void blk_rq_init(struct request_queue *q, struct request *rq)
-{
-	memset(rq, 0, sizeof(*rq));
-
-	INIT_LIST_HEAD(&rq->queuelist);
-	rq->q = q;
-	rq->__sector = (sector_t) -1;
-	INIT_HLIST_NODE(&rq->hash);
-	RB_CLEAR_NODE(&rq->rb_node);
-	rq->tag = BLK_MQ_NO_TAG;
-	rq->internal_tag = BLK_MQ_NO_TAG;
-	rq->start_time_ns = ktime_get_ns();
-	rq->part = NULL;
-	blk_crypto_rq_set_defaults(rq);
-}
-EXPORT_SYMBOL(blk_rq_init);
-
 #define REQ_OP_NAME(name) [REQ_OP_##name] = #name
 static const char *const blk_op_name[] = {
 	REQ_OP_NAME(READ),
@@ -216,38 +199,15 @@ int blk_status_to_errno(blk_status_t status)
 }
 EXPORT_SYMBOL_GPL(blk_status_to_errno);
 
-void blk_print_req_error(struct request *req, blk_status_t status)
+const char *blk_status_to_str(blk_status_t status)
 {
 	int idx = (__force int)status;
 
 	if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
-		return;
-
-	printk_ratelimited(KERN_ERR
-		"%s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x "
-		"phys_seg %u prio class %u\n",
-		blk_errors[idx].name,
-		req->rq_disk ? req->rq_disk->disk_name : "?",
-		blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)),
-		req->cmd_flags & ~REQ_OP_MASK,
-		req->nr_phys_segments,
-		IOPRIO_PRIO_CLASS(req->ioprio));
+		return "<null>";
+	return blk_errors[idx].name;
 }
 
-void blk_dump_rq_flags(struct request *rq, char *msg)
-{
-	printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg,
-		rq->rq_disk ? rq->rq_disk->disk_name : "?",
-		(unsigned long long) rq->cmd_flags);
-
-	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
-	       (unsigned long long)blk_rq_pos(rq),
-	       blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
-	printk(KERN_INFO "  bio %p, biotail %p, len %u\n",
-	       rq->bio, rq->biotail, blk_rq_bytes(rq));
-}
-EXPORT_SYMBOL(blk_dump_rq_flags);
-
 /**
  * blk_sync_queue - cancel any pending callbacks on a queue
  * @q: the queue
@@ -478,21 +438,27 @@ static void blk_timeout_work(struct work_struct *work)
 {
 }
 
-struct request_queue *blk_alloc_queue(int node_id)
+struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 {
 	struct request_queue *q;
 	int ret;
 
-	q = kmem_cache_alloc_node(blk_requestq_cachep,
-				GFP_KERNEL | __GFP_ZERO, node_id);
+	q = kmem_cache_alloc_node(blk_get_queue_kmem_cache(alloc_srcu),
+			GFP_KERNEL | __GFP_ZERO, node_id);
 	if (!q)
 		return NULL;
 
+	if (alloc_srcu) {
+		blk_queue_flag_set(QUEUE_FLAG_HAS_SRCU, q);
+		if (init_srcu_struct(q->srcu) != 0)
+			goto fail_q;
+	}
+
 	q->last_merge = NULL;
 
 	q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL);
 	if (q->id < 0)
-		goto fail_q;
+		goto fail_srcu;
 
 	ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, 0);
 	if (ret)
@@ -549,8 +515,11 @@ fail_split:
 	bioset_exit(&q->bio_split);
 fail_id:
 	ida_simple_remove(&blk_queue_ida, q->id);
+fail_srcu:
+	if (alloc_srcu)
+		cleanup_srcu_struct(q->srcu);
 fail_q:
-	kmem_cache_free(blk_requestq_cachep, q);
+	kmem_cache_free(blk_get_queue_kmem_cache(alloc_srcu), q);
 	return NULL;
 }
 
@@ -594,7 +563,7 @@ static int __init setup_fail_make_request(char *str)
 }
 __setup("fail_make_request=", setup_fail_make_request);
 
-static bool should_fail_request(struct block_device *part, unsigned int bytes)
+bool should_fail_request(struct block_device *part, unsigned int bytes)
 {
 	return part->bd_make_it_fail && should_fail(&fail_make_request, bytes);
 }
@@ -608,15 +577,6 @@ static int __init fail_make_request_debugfs(void)
 }
 
 late_initcall(fail_make_request_debugfs);
-
-#else /* CONFIG_FAIL_MAKE_REQUEST */
-
-static inline bool should_fail_request(struct block_device *part,
-					unsigned int bytes)
-{
-	return false;
-}
-
 #endif /* CONFIG_FAIL_MAKE_REQUEST */
 
 static inline bool bio_check_ro(struct bio *bio)
@@ -802,15 +762,6 @@ noinline_for_stack bool submit_bio_checks(struct bio *bio)
 		break;
 	}
 
-	/*
-	 * Various block parts want %current->io_context, so allocate it up
-	 * front rather than dealing with lots of pain to allocate it only
-	 * where needed. This may fail and the block layer knows how to live
-	 * with it.
-	 */
-	if (unlikely(!current->io_context))
-		create_task_io_context(current, GFP_ATOMIC, q->node);
-
 	if (blk_throtl_bio(bio))
 		return false;
 
@@ -836,17 +787,21 @@ end_io:
 
 static void __submit_bio_fops(struct gendisk *disk, struct bio *bio)
 {
-	if (unlikely(bio_queue_enter(bio) != 0))
-		return;
-	if (submit_bio_checks(bio) && blk_crypto_bio_prep(&bio))
-		disk->fops->submit_bio(bio);
-	blk_queue_exit(disk->queue);
+	if (blk_crypto_bio_prep(&bio)) {
+		if (likely(bio_queue_enter(bio) == 0)) {
+			disk->fops->submit_bio(bio);
+			blk_queue_exit(disk->queue);
+		}
+	}
 }
 
 static void __submit_bio(struct bio *bio)
 {
 	struct gendisk *disk = bio->bi_bdev->bd_disk;
 
+	if (unlikely(!submit_bio_checks(bio)))
+		return;
+
 	if (!disk->fops->submit_bio)
 		blk_mq_submit_bio(bio);
 	else
@@ -1090,135 +1045,7 @@ int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
 }
 EXPORT_SYMBOL_GPL(iocb_bio_iopoll);
 
-/**
- * blk_cloned_rq_check_limits - Helper function to check a cloned request
- *                              for the new queue limits
- * @q:  the queue
- * @rq: the request being checked
- *
- * Description:
- *    @rq may have been made based on weaker limitations of upper-level queues
- *    in request stacking drivers, and it may violate the limitation of @q.
- *    Since the block layer and the underlying device driver trust @rq
- *    after it is inserted to @q, it should be checked against @q before
- *    the insertion using this generic function.
- *
- *    Request stacking drivers like request-based dm may change the queue
- *    limits when retrying requests on other queues. Those requests need
- *    to be checked against the new queue limits again during dispatch.
- */
-static blk_status_t blk_cloned_rq_check_limits(struct request_queue *q,
-				      struct request *rq)
-{
-	unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq));
-
-	if (blk_rq_sectors(rq) > max_sectors) {
-		/*
-		 * SCSI device does not have a good way to return if
-		 * Write Same/Zero is actually supported. If a device rejects
-		 * a non-read/write command (discard, write same,etc.) the
-		 * low-level device driver will set the relevant queue limit to
-		 * 0 to prevent blk-lib from issuing more of the offending
-		 * operations. Commands queued prior to the queue limit being
-		 * reset need to be completed with BLK_STS_NOTSUPP to avoid I/O
-		 * errors being propagated to upper layers.
-		 */
-		if (max_sectors == 0)
-			return BLK_STS_NOTSUPP;
-
-		printk(KERN_ERR "%s: over max size limit. (%u > %u)\n",
-			__func__, blk_rq_sectors(rq), max_sectors);
-		return BLK_STS_IOERR;
-	}
-
-	/*
-	 * The queue settings related to segment counting may differ from the
-	 * original queue.
-	 */
-	rq->nr_phys_segments = blk_recalc_rq_segments(rq);
-	if (rq->nr_phys_segments > queue_max_segments(q)) {
-		printk(KERN_ERR "%s: over max segments limit. (%hu > %hu)\n",
-			__func__, rq->nr_phys_segments, queue_max_segments(q));
-		return BLK_STS_IOERR;
-	}
-
-	return BLK_STS_OK;
-}
-
-/**
- * blk_insert_cloned_request - Helper for stacking drivers to submit a request
- * @q:  the queue to submit the request
- * @rq: the request being queued
- */
-blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq)
-{
-	blk_status_t ret;
-
-	ret = blk_cloned_rq_check_limits(q, rq);
-	if (ret != BLK_STS_OK)
-		return ret;
-
-	if (rq->rq_disk &&
-	    should_fail_request(rq->rq_disk->part0, blk_rq_bytes(rq)))
-		return BLK_STS_IOERR;
-
-	if (blk_crypto_insert_cloned_request(rq))
-		return BLK_STS_IOERR;
-
-	blk_account_io_start(rq);
-
-	/*
-	 * Since we have a scheduler attached on the top device,
-	 * bypass a potential scheduler on the bottom device for
-	 * insert.
-	 */
-	return blk_mq_request_issue_directly(rq, true);
-}
-EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
-
-/**
- * blk_rq_err_bytes - determine number of bytes till the next failure boundary
- * @rq: request to examine
- *
- * Description:
- *     A request could be merge of IOs which require different failure
- *     handling.  This function determines the number of bytes which
- *     can be failed from the beginning of the request without
- *     crossing into area which need to be retried further.
- *
- * Return:
- *     The number of bytes to fail.
- */
-unsigned int blk_rq_err_bytes(const struct request *rq)
-{
-	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
-	unsigned int bytes = 0;
-	struct bio *bio;
-
-	if (!(rq->rq_flags & RQF_MIXED_MERGE))
-		return blk_rq_bytes(rq);
-
-	/*
-	 * Currently the only 'mixing' which can happen is between
-	 * different fastfail types.  We can safely fail portions
-	 * which have all the failfast bits that the first one has -
-	 * the ones which are at least as eager to fail as the first
-	 * one.
-	 */
-	for (bio = rq->bio; bio; bio = bio->bi_next) {
-		if ((bio->bi_opf & ff) != ff)
-			break;
-		bytes += bio->bi_iter.bi_size;
-	}
-
-	/* this could lead to infinite loop */
-	BUG_ON(blk_rq_bytes(rq) && !bytes);
-	return bytes;
-}
-EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
-
-static void update_io_ticks(struct block_device *part, unsigned long now,
-		bool end)
+void update_io_ticks(struct block_device *part, unsigned long now, bool end)
 {
 	unsigned long stamp;
 again:
@@ -1233,30 +1060,6 @@ again:
 	}
 }
 
-void __blk_account_io_done(struct request *req, u64 now)
-{
-	const int sgrp = op_stat_group(req_op(req));
-
-	part_stat_lock();
-	update_io_ticks(req->part, jiffies, true);
-	part_stat_inc(req->part, ios[sgrp]);
-	part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
-	part_stat_unlock();
-}
-
-void __blk_account_io_start(struct request *rq)
-{
-	/* passthrough requests can hold bios that do not have ->bi_bdev set */
-	if (rq->bio && rq->bio->bi_bdev)
-		rq->part = rq->bio->bi_bdev;
-	else
-		rq->part = rq->rq_disk->part0;
-
-	part_stat_lock();
-	update_io_ticks(rq->part, jiffies, false);
-	part_stat_unlock();
-}
-
 static unsigned long __part_start_io_acct(struct block_device *part,
 					  unsigned int sectors, unsigned int op)
 {
@@ -1320,46 +1123,6 @@ void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 }
 EXPORT_SYMBOL(disk_end_io_acct);
 
-/*
- * Steal bios from a request and add them to a bio list.
- * The request must not have been partially completed before.
- */
-void blk_steal_bios(struct bio_list *list, struct request *rq)
-{
-	if (rq->bio) {
-		if (list->tail)
-			list->tail->bi_next = rq->bio;
-		else
-			list->head = rq->bio;
-		list->tail = rq->biotail;
-
-		rq->bio = NULL;
-		rq->biotail = NULL;
-	}
-
-	rq->__data_len = 0;
-}
-EXPORT_SYMBOL_GPL(blk_steal_bios);
-
-#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-/**
- * rq_flush_dcache_pages - Helper function to flush all pages in a request
- * @rq: the request to be flushed
- *
- * Description:
- *     Flush all pages in @rq.
- */
-void rq_flush_dcache_pages(struct request *rq)
-{
-	struct req_iterator iter;
-	struct bio_vec bvec;
-
-	rq_for_each_segment(bvec, rq, iter)
-		flush_dcache_page(bvec.bv_page);
-}
-EXPORT_SYMBOL_GPL(rq_flush_dcache_pages);
-#endif
-
 /**
  * blk_lld_busy - Check if underlying low-level drivers of a device are busy
  * @q : the queue of the device being checked
@@ -1388,93 +1151,6 @@ int blk_lld_busy(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_lld_busy);
 
-/**
- * blk_rq_unprep_clone - Helper function to free all bios in a cloned request
- * @rq: the clone request to be cleaned up
- *
- * Description:
- *     Free all bios in @rq for a cloned request.
- */
-void blk_rq_unprep_clone(struct request *rq)
-{
-	struct bio *bio;
-
-	while ((bio = rq->bio) != NULL) {
-		rq->bio = bio->bi_next;
-
-		bio_put(bio);
-	}
-}
-EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
-
-/**
- * blk_rq_prep_clone - Helper function to setup clone request
- * @rq: the request to be setup
- * @rq_src: original request to be cloned
- * @bs: bio_set that bios for clone are allocated from
- * @gfp_mask: memory allocation mask for bio
- * @bio_ctr: setup function to be called for each clone bio.
- *           Returns %0 for success, non %0 for failure.
- * @data: private data to be passed to @bio_ctr
- *
- * Description:
- *     Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
- *     Also, pages which the original bios are pointing to are not copied
- *     and the cloned bios just point same pages.
- *     So cloned bios must be completed before original bios, which means
- *     the caller must complete @rq before @rq_src.
- */
-int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
-		      struct bio_set *bs, gfp_t gfp_mask,
-		      int (*bio_ctr)(struct bio *, struct bio *, void *),
-		      void *data)
-{
-	struct bio *bio, *bio_src;
-
-	if (!bs)
-		bs = &fs_bio_set;
-
-	__rq_for_each_bio(bio_src, rq_src) {
-		bio = bio_clone_fast(bio_src, gfp_mask, bs);
-		if (!bio)
-			goto free_and_out;
-
-		if (bio_ctr && bio_ctr(bio, bio_src, data))
-			goto free_and_out;
-
-		if (rq->bio) {
-			rq->biotail->bi_next = bio;
-			rq->biotail = bio;
-		} else {
-			rq->bio = rq->biotail = bio;
-		}
-		bio = NULL;
-	}
-
-	/* Copy attributes of the original request to the clone request. */
-	rq->__sector = blk_rq_pos(rq_src);
-	rq->__data_len = blk_rq_bytes(rq_src);
-	if (rq_src->rq_flags & RQF_SPECIAL_PAYLOAD) {
-		rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
-		rq->special_vec = rq_src->special_vec;
-	}
-	rq->nr_phys_segments = rq_src->nr_phys_segments;
-	rq->ioprio = rq_src->ioprio;
-
-	if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0)
-		goto free_and_out;
-
-	return 0;
-
-free_and_out:
-	if (bio)
-		bio_put(bio);
-	blk_rq_unprep_clone(rq);
-
-	return -ENOMEM;
-}
-EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
-
 int kblockd_schedule_work(struct work_struct *work)
 {
 	return queue_work(kblockd_workqueue, work);
@@ -1639,6 +1315,9 @@ int __init blk_dev_init(void)
 			sizeof_field(struct request, cmd_flags));
 	BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *
 			sizeof_field(struct bio, bi_opf));
+	BUILD_BUG_ON(ALIGN(offsetof(struct request_queue, srcu),
+			   __alignof__(struct request_queue)) !=
+		     sizeof(struct request_queue));
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",
@@ -1649,6 +1328,10 @@ int __init blk_dev_init(void)
 	blk_requestq_cachep = kmem_cache_create("request_queue",
 			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
 
+	blk_requestq_srcu_cachep = kmem_cache_create("request_queue_srcu",
+			sizeof(struct request_queue) +
+			sizeof(struct srcu_struct), 0, SLAB_PANIC, NULL);
+
 	blk_debugfs_root = debugfs_create_dir("block", NULL);
 
 	return 0;