added more kernel files for debugging

src/block/blk-mq.c

+/*
+ * Block multiqueue core code
+ *
+ * Copyright (C) 2013-2014 Jens Axboe
+ * Copyright (C) 2013-2014 Christoph Hellwig
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/backing-dev.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/kmemleak.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/smp.h>
+#include <linux/llist.h>
+#include <linux/list_sort.h>
+#include <linux/cpu.h>
+#include <linux/cache.h>
+#include <linux/sched/sysctl.h>
+#include <linux/sched/topology.h>
+#include <linux/sched/signal.h>
+#include <linux/delay.h>
+#include <linux/crash_dump.h>
+#include <linux/prefetch.h>
+
+#include <trace/events/block.h>
+
+#include <linux/blk-mq.h>
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-debugfs.h"
+#include "blk-mq-tag.h"
+#include "blk-stat.h"
+#include "blk-mq-sched.h"
+#include "blk-rq-qos.h"
+
+static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie);
+static void blk_mq_poll_stats_start(struct request_queue *q);
+static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
+
+static int blk_mq_poll_stats_bkt(const struct request *rq)
+{
+	int ddir, bytes, bucket;
+
+	ddir = rq_data_dir(rq);
+	bytes = blk_rq_bytes(rq);
+
+	bucket = ddir + 2*(ilog2(bytes) - 9);
+
+	if (bucket < 0)
+		return -1;
+	else if (bucket >= BLK_MQ_POLL_STATS_BKTS)
+		return ddir + BLK_MQ_POLL_STATS_BKTS - 2;
+
+	return bucket;
+}
+
+/*
+ * Check if any of the ctx's have pending work in this hardware queue
+ */
+static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
+{
+	return !list_empty_careful(&hctx->dispatch) ||
+		sbitmap_any_bit_set(&hctx->ctx_map) ||
+			blk_mq_sched_has_work(hctx);
+}
+
+/*
+ * Mark this ctx as having pending work in this hardware queue
+ */
+static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx,
+				     struct blk_mq_ctx *ctx)
+{
+	if (!sbitmap_test_bit(&hctx->ctx_map, ctx->index_hw))
+		sbitmap_set_bit(&hctx->ctx_map, ctx->index_hw);
+}
+
+static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
+				      struct blk_mq_ctx *ctx)
+{
+	sbitmap_clear_bit(&hctx->ctx_map, ctx->index_hw);
+}
+
+struct mq_inflight {
+	struct hd_struct *part;
+	unsigned int *inflight;
+};
+
+static void blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
+				  struct request *rq, void *priv,
+				  bool reserved)
+{
+	struct mq_inflight *mi = priv;
+
+	/*
+	 * index[0] counts the specific partition that was asked for. index[1]
+	 * counts the ones that are active on the whole device, so increment
+	 * that if mi->part is indeed a partition, and not a whole device.
+	 */
+	if (rq->part == mi->part)
+		mi->inflight[0]++;
+	if (mi->part->partno)
+		mi->inflight[1]++;
+}
+
+void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
+		      unsigned int inflight[2])
+{
+	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+
+	inflight[0] = inflight[1] = 0;
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
+}
+
+static void blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
+				     struct request *rq, void *priv,
+				     bool reserved)
+{
+	struct mq_inflight *mi = priv;
+
+	if (rq->part == mi->part)
+		mi->inflight[rq_data_dir(rq)]++;
+}
+
+void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+			 unsigned int inflight[2])
+{
+	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+
+	inflight[0] = inflight[1] = 0;
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
+}
+
+void blk_freeze_queue_start(struct request_queue *q)
+{
+	int freeze_depth;
+
+	freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
+	if (freeze_depth == 1) {
+		percpu_ref_kill(&q->q_usage_counter);
+		if (q->mq_ops)
+			blk_mq_run_hw_queues(q, false);
+	}
+}
+EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
+
+void blk_mq_freeze_queue_wait(struct request_queue *q)
+{
+	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
+}
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait);
+
+int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
+				     unsigned long timeout)
+{
+	return wait_event_timeout(q->mq_freeze_wq,
+					percpu_ref_is_zero(&q->q_usage_counter),
+					timeout);
+}
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout);
+
+/*
+ * Guarantee no request is in use, so we can change any data structure of
+ * the queue afterward.
+ */
+void blk_freeze_queue(struct request_queue *q)
+{
+	/*
+	 * In the !blk_mq case we are only calling this to kill the
+	 * q_usage_counter, otherwise this increases the freeze depth
+	 * and waits for it to return to zero.  For this reason there is
+	 * no blk_unfreeze_queue(), and blk_freeze_queue() is not
+	 * exported to drivers as the only user for unfreeze is blk_mq.
+	 */
+	blk_freeze_queue_start(q);
+	if (!q->mq_ops)
+		blk_drain_queue(q);
+	blk_mq_freeze_queue_wait(q);
+}
+
+void blk_mq_freeze_queue(struct request_queue *q)
+{
+	/*
+	 * ...just an alias to keep freeze and unfreeze actions balanced
+	 * in the blk_mq_* namespace
+	 */
+	blk_freeze_queue(q);
+}
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
+
+void blk_mq_unfreeze_queue(struct request_queue *q)
+{
+	int freeze_depth;
+
+	freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
+	WARN_ON_ONCE(freeze_depth < 0);
+	if (!freeze_depth) {
+		percpu_ref_reinit(&q->q_usage_counter);
+		wake_up_all(&q->mq_freeze_wq);
+	}
+}
+EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
+
+/*
+ * FIXME: replace the scsi_internal_device_*block_nowait() calls in the
+ * mpt3sas driver such that this function can be removed.
+ */
+void blk_mq_quiesce_queue_nowait(struct request_queue *q)
+{
+	blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q);
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
+
+/**
+ * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
+ * @q: request queue.
+ *
+ * Note: this function does not prevent that the struct request end_io()
+ * callback function is invoked. Once this function is returned, we make
+ * sure no dispatch can happen until the queue is unquiesced via
+ * blk_mq_unquiesce_queue().
+ */
+void blk_mq_quiesce_queue(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+	bool rcu = false;
+
+	blk_mq_quiesce_queue_nowait(q);
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (hctx->flags & BLK_MQ_F_BLOCKING)
+			synchronize_srcu(hctx->srcu);
+		else
+			rcu = true;
+	}
+	if (rcu)
+		synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
+
+/*
+ * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue()
+ * @q: request queue.
+ *
+ * This function recovers queue into the state before quiescing
+ * which is done by blk_mq_quiesce_queue.
+ */
+void blk_mq_unquiesce_queue(struct request_queue *q)
+{
+	blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
+
+	/* dispatch requests which are inserted during quiescing */
+	blk_mq_run_hw_queues(q, true);
+}
+EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
+
+void blk_mq_wake_waiters(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		if (blk_mq_hw_queue_mapped(hctx))
+			blk_mq_tag_wakeup_all(hctx->tags, true);
+}
+
+bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
+{
+	return blk_mq_has_free_tags(hctx->tags);
+}
+EXPORT_SYMBOL(blk_mq_can_queue);
+
+static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
+		unsigned int tag, unsigned int op)
+{
+	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+	struct request *rq = tags->static_rqs[tag];
+	req_flags_t rq_flags = 0;
+
+	if (data->flags & BLK_MQ_REQ_INTERNAL) {
+		rq->tag = -1;
+		rq->internal_tag = tag;
+	} else {
+		if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
+			rq_flags = RQF_MQ_INFLIGHT;
+			atomic_inc(&data->hctx->nr_active);
+		}
+		rq->tag = tag;
+		rq->internal_tag = -1;
+		data->hctx->tags->rqs[rq->tag] = rq;
+	}
+
+	/* csd/requeue_work/fifo_time is initialized before use */
+	rq->q = data->q;
+	rq->mq_ctx = data->ctx;
+	rq->rq_flags = rq_flags;
+	rq->cpu = -1;
+	rq->cmd_flags = op;
+	if (data->flags & BLK_MQ_REQ_PREEMPT)
+		rq->rq_flags |= RQF_PREEMPT;
+	if (blk_queue_io_stat(data->q))
+		rq->rq_flags |= RQF_IO_STAT;
+	INIT_LIST_HEAD(&rq->queuelist);
+	INIT_HLIST_NODE(&rq->hash);
+	RB_CLEAR_NODE(&rq->rb_node);
+	rq->rq_disk = NULL;
+	rq->part = NULL;
+	rq->start_time_ns = ktime_get_ns();
+	rq->io_start_time_ns = 0;
+	rq->nr_phys_segments = 0;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	rq->nr_integrity_segments = 0;
+#endif
+	rq->special = NULL;
+	/* tag was already set */
+	rq->extra_len = 0;
+	rq->__deadline = 0;
+
+	INIT_LIST_HEAD(&rq->timeout_list);
+	rq->timeout = 0;
+
+	rq->end_io = NULL;
+	rq->end_io_data = NULL;
+	rq->next_rq = NULL;
+
+#ifdef CONFIG_BLK_CGROUP
+	rq->rl = NULL;
+#endif
+
+	data->ctx->rq_dispatched[op_is_sync(op)]++;
+	refcount_set(&rq->ref, 1);
+	return rq;
+}
+
+static struct request *blk_mq_get_request(struct request_queue *q,
+		struct bio *bio, unsigned int op,
+		struct blk_mq_alloc_data *data)
+{
+	struct elevator_queue *e = q->elevator;
+	struct request *rq;
+	unsigned int tag;
+	bool put_ctx_on_error = false;
+
+	blk_queue_enter_live(q);
+	data->q = q;
+	if (likely(!data->ctx)) {
+		data->ctx = blk_mq_get_ctx(q);
+		put_ctx_on_error = true;
+	}
+	if (likely(!data->hctx))
+		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
+	if (op & REQ_NOWAIT)
+		data->flags |= BLK_MQ_REQ_NOWAIT;
+
+	if (e) {
+		data->flags |= BLK_MQ_REQ_INTERNAL;
+
+		/*
+		 * Flush requests are special and go directly to the
+		 * dispatch list. Don't include reserved tags in the
+		 * limiting, as it isn't useful.
+		 */
+		if (!op_is_flush(op) && e->type->ops.mq.limit_depth &&
+		    !(data->flags & BLK_MQ_REQ_RESERVED))
+			e->type->ops.mq.limit_depth(op, data);
+	} else {
+		blk_mq_tag_busy(data->hctx);
+	}
+
+	tag = blk_mq_get_tag(data);
+	if (tag == BLK_MQ_TAG_FAIL) {
+		if (put_ctx_on_error) {
+			blk_mq_put_ctx(data->ctx);
+			data->ctx = NULL;
+		}
+		blk_queue_exit(q);
+		return NULL;
+	}
+
+	rq = blk_mq_rq_ctx_init(data, tag, op);
+	if (!op_is_flush(op)) {
+		rq->elv.icq = NULL;
+		if (e && e->type->ops.mq.prepare_request) {
+			if (e->type->icq_cache && rq_ioc(bio))
+				blk_mq_sched_assign_ioc(rq, bio);
+
+			e->type->ops.mq.prepare_request(rq, bio);
+			rq->rq_flags |= RQF_ELVPRIV;
+		}
+	}
+	data->hctx->queued++;
+	return rq;
+}
+
+struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
+		blk_mq_req_flags_t flags)
+{
+	struct blk_mq_alloc_data alloc_data = { .flags = flags };
+	struct request *rq;
+	int ret;
+
+	ret = blk_queue_enter(q, flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	rq = blk_mq_get_request(q, NULL, op, &alloc_data);
+	blk_queue_exit(q);
+
+	if (!rq)
+		return ERR_PTR(-EWOULDBLOCK);
+
+	blk_mq_put_ctx(alloc_data.ctx);
+
+	rq->__data_len = 0;
+	rq->__sector = (sector_t) -1;
+	rq->bio = rq->biotail = NULL;
+	return rq;
+}
+EXPORT_SYMBOL(blk_mq_alloc_request);
+
+struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
+	unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx)
+{
+	struct blk_mq_alloc_data alloc_data = { .flags = flags };
+	struct request *rq;
+	unsigned int cpu;
+	int ret;
+
+	/*
+	 * If the tag allocator sleeps we could get an allocation for a
+	 * different hardware context.  No need to complicate the low level
+	 * allocator for this for the rare use case of a command tied to
+	 * a specific queue.
+	 */
+	if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)))
+		return ERR_PTR(-EINVAL);
+
+	if (hctx_idx >= q->nr_hw_queues)
+		return ERR_PTR(-EIO);
+
+	ret = blk_queue_enter(q, flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/*
+	 * Check if the hardware context is actually mapped to anything.
+	 * If not tell the caller that it should skip this queue.
+	 */
+	alloc_data.hctx = q->queue_hw_ctx[hctx_idx];
+	if (!blk_mq_hw_queue_mapped(alloc_data.hctx)) {
+		blk_queue_exit(q);
+		return ERR_PTR(-EXDEV);
+	}
+	cpu = cpumask_first_and(alloc_data.hctx->cpumask, cpu_online_mask);
+	alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
+
+	rq = blk_mq_get_request(q, NULL, op, &alloc_data);
+	blk_queue_exit(q);
+
+	if (!rq)
+		return ERR_PTR(-EWOULDBLOCK);
+
+	return rq;
+}
+EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
+
+static void __blk_mq_free_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+	const int sched_tag = rq->internal_tag;
+
+	if (rq->tag != -1)
+		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
+	if (sched_tag != -1)
+		blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
+	blk_mq_sched_restart(hctx);
+	blk_queue_exit(q);
+}
+
+void blk_mq_free_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+
+	if (rq->rq_flags & RQF_ELVPRIV) {
+		if (e && e->type->ops.mq.finish_request)
+			e->type->ops.mq.finish_request(rq);
+		if (rq->elv.icq) {
+			put_io_context(rq->elv.icq->ioc);
+			rq->elv.icq = NULL;
+		}
+	}
+
+	ctx->rq_completed[rq_is_sync(rq)]++;
+	if (rq->rq_flags & RQF_MQ_INFLIGHT)
+		atomic_dec(&hctx->nr_active);
+
+	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
+		laptop_io_completion(q->backing_dev_info);
+
+	rq_qos_done(q, rq);
+
+	if (blk_rq_rl(rq))
+		blk_put_rl(blk_rq_rl(rq));
+
+	WRITE_ONCE(rq->state, MQ_RQ_IDLE);
+	if (refcount_dec_and_test(&rq->ref))
+		__blk_mq_free_request(rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_free_request);
+
+inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
+{
+	u64 now = ktime_get_ns();
+
+	if (rq->rq_flags & RQF_STATS) {
+		blk_mq_poll_stats_start(rq->q);
+		blk_stat_add(rq, now);
+	}
+
+	blk_account_io_done(rq, now);
+
+	if (rq->end_io) {
+		rq_qos_done(rq->q, rq);
+		rq->end_io(rq, error);
+	} else {
+		if (unlikely(blk_bidi_rq(rq)))
+			blk_mq_free_request(rq->next_rq);
+		blk_mq_free_request(rq);
+	}
+}
+EXPORT_SYMBOL(__blk_mq_end_request);
+
+void blk_mq_end_request(struct request *rq, blk_status_t error)
+{
+	if (blk_update_request(rq, error, blk_rq_bytes(rq)))
+		BUG();
+	__blk_mq_end_request(rq, error);
+}
+EXPORT_SYMBOL(blk_mq_end_request);
+
+static void __blk_mq_complete_request_remote(void *data)
+{
+	struct request *rq = data;
+
+	rq->q->softirq_done_fn(rq);
+}
+
+static void __blk_mq_complete_request(struct request *rq)
+{
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	bool shared = false;
+	int cpu;
+
+	if (!blk_mq_mark_complete(rq))
+		return;
+	if (rq->internal_tag != -1)
+		blk_mq_sched_completed_request(rq);
+
+	if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {
+		rq->q->softirq_done_fn(rq);
+		return;
+	}
+
+	cpu = get_cpu();
+	if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags))
+		shared = cpus_share_cache(cpu, ctx->cpu);
+
+	if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {
+		rq->csd.func = __blk_mq_complete_request_remote;
+		rq->csd.info = rq;
+		rq->csd.flags = 0;
+		smp_call_function_single_async(ctx->cpu, &rq->csd);
+	} else {
+		rq->q->softirq_done_fn(rq);
+	}
+	put_cpu();
+}
+
+static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
+	__releases(hctx->srcu)
+{
+	if (!(hctx->flags & BLK_MQ_F_BLOCKING))
+		rcu_read_unlock();
+	else
+		srcu_read_unlock(hctx->srcu, srcu_idx);
+}
+
+static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx)
+	__acquires(hctx->srcu)
+{
+	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
+		/* shut up gcc false positive */
+		*srcu_idx = 0;
+		rcu_read_lock();
+	} else
+		*srcu_idx = srcu_read_lock(hctx->srcu);
+}
+
+/**
+ * blk_mq_complete_request - end I/O on a request
+ * @rq:		the request being processed
+ *
+ * Description:
+ *	Ends all I/O on a request. It does not handle partial completions.
+ *	The actual completion happens out-of-order, through a IPI handler.
+ **/
+void blk_mq_complete_request(struct request *rq)
+{
+	if (unlikely(blk_should_fake_timeout(rq->q)))
+		return;
+	__blk_mq_complete_request(rq);
+}
+EXPORT_SYMBOL(blk_mq_complete_request);
+
+int blk_mq_request_started(struct request *rq)
+{
+	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
+}
+EXPORT_SYMBOL_GPL(blk_mq_request_started);
+
+void blk_mq_start_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+
+	blk_mq_sched_started_request(rq);
+
+	trace_block_rq_issue(q, rq);
+
+	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
+		rq->io_start_time_ns = ktime_get_ns();
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+		rq->throtl_size = blk_rq_sectors(rq);
+#endif
+		rq->rq_flags |= RQF_STATS;
+		rq_qos_issue(q, rq);
+	}
+
+	WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);
+
+	blk_add_timer(rq);
+	WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);
+
+	if (q->dma_drain_size && blk_rq_bytes(rq)) {
+		/*
+		 * Make sure space for the drain appears.  We know we can do
+		 * this because max_hw_segments has been adjusted to be one
+		 * fewer than the device can handle.
+		 */
+		rq->nr_phys_segments++;
+	}
+}
+EXPORT_SYMBOL(blk_mq_start_request);
+
+static void __blk_mq_requeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+
+	blk_mq_put_driver_tag(rq);
+
+	trace_block_rq_requeue(q, rq);
+	rq_qos_requeue(q, rq);
+
+	if (blk_mq_request_started(rq)) {
+		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
+		rq->rq_flags &= ~RQF_TIMED_OUT;
+		if (q->dma_drain_size && blk_rq_bytes(rq))
+			rq->nr_phys_segments--;
+	}
+}
+
+void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
+{
+	__blk_mq_requeue_request(rq);
+
+	/* this request will be re-inserted to io scheduler queue */
+	blk_mq_sched_requeue_request(rq);
+
+	BUG_ON(blk_queued_rq(rq));
+	blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
+}
+EXPORT_SYMBOL(blk_mq_requeue_request);
+
+static void blk_mq_requeue_work(struct work_struct *work)
+{
+	struct request_queue *q =
+		container_of(work, struct request_queue, requeue_work.work);
+	LIST_HEAD(rq_list);
+	struct request *rq, *next;
+
+	spin_lock_irq(&q->requeue_lock);
+	list_splice_init(&q->requeue_list, &rq_list);
+	spin_unlock_irq(&q->requeue_lock);
+
+	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
+		if (!(rq->rq_flags & RQF_SOFTBARRIER))
+			continue;
+
+		rq->rq_flags &= ~RQF_SOFTBARRIER;
+		list_del_init(&rq->queuelist);
+		blk_mq_sched_insert_request(rq, true, false, false);
+	}
+
+	while (!list_empty(&rq_list)) {
+		rq = list_entry(rq_list.next, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		blk_mq_sched_insert_request(rq, false, false, false);
+	}
+
+	blk_mq_run_hw_queues(q, false);
+}
+
+void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
+				bool kick_requeue_list)
+{
+	struct request_queue *q = rq->q;
+	unsigned long flags;
+
+	/*
+	 * We abuse this flag that is otherwise used by the I/O scheduler to
+	 * request head insertion from the workqueue.
+	 */
+	BUG_ON(rq->rq_flags & RQF_SOFTBARRIER);
+
+	spin_lock_irqsave(&q->requeue_lock, flags);
+	if (at_head) {
+		rq->rq_flags |= RQF_SOFTBARRIER;
+		list_add(&rq->queuelist, &q->requeue_list);
+	} else {
+		list_add_tail(&rq->queuelist, &q->requeue_list);
+	}
+	spin_unlock_irqrestore(&q->requeue_lock, flags);
+
+	if (kick_requeue_list)
+		blk_mq_kick_requeue_list(q);
+}
+EXPORT_SYMBOL(blk_mq_add_to_requeue_list);
+
+void blk_mq_kick_requeue_list(struct request_queue *q)
+{
+	kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0);
+}
+EXPORT_SYMBOL(blk_mq_kick_requeue_list);
+
+void blk_mq_delay_kick_requeue_list(struct request_queue *q,
+				    unsigned long msecs)
+{
+	kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work,
+				    msecs_to_jiffies(msecs));
+}
+EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
+
+struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
+{
+	if (tag < tags->nr_tags) {
+		prefetch(tags->rqs[tag]);
+		return tags->rqs[tag];
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(blk_mq_tag_to_rq);
+
+static void blk_mq_rq_timed_out(struct request *req, bool reserved)
+{
+	req->rq_flags |= RQF_TIMED_OUT;
+	if (req->q->mq_ops->timeout) {
+		enum blk_eh_timer_return ret;
+
+		ret = req->q->mq_ops->timeout(req, reserved);
+		if (ret == BLK_EH_DONE)
+			return;
+		WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
+	}
+
+	blk_add_timer(req);
+}
+
+static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
+{
+	unsigned long deadline;
+
+	if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT)
+		return false;
+	if (rq->rq_flags & RQF_TIMED_OUT)
+		return false;
+
+	deadline = blk_rq_deadline(rq);
+	if (time_after_eq(jiffies, deadline))
+		return true;
+
+	if (*next == 0)
+		*next = deadline;
+	else if (time_after(*next, deadline))
+		*next = deadline;
+	return false;
+}
+
+static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
+		struct request *rq, void *priv, bool reserved)
+{
+	unsigned long *next = priv;
+
+	/*
+	 * Just do a quick check if it is expired before locking the request in
+	 * so we're not unnecessarilly synchronizing across CPUs.
+	 */
+	if (!blk_mq_req_expired(rq, next))
+		return;
+
+	/*
+	 * We have reason to believe the request may be expired. Take a
+	 * reference on the request to lock this request lifetime into its
+	 * currently allocated context to prevent it from being reallocated in
+	 * the event the completion by-passes this timeout handler.
+	 *
+	 * If the reference was already released, then the driver beat the
+	 * timeout handler to posting a natural completion.
+	 */
+	if (!refcount_inc_not_zero(&rq->ref))
+		return;
+
+	/*
+	 * The request is now locked and cannot be reallocated underneath the
+	 * timeout handler's processing. Re-verify this exact request is truly
+	 * expired; if it is not expired, then the request was completed and
+	 * reallocated as a new request.
+	 */
+	if (blk_mq_req_expired(rq, next))
+		blk_mq_rq_timed_out(rq, reserved);
+	if (refcount_dec_and_test(&rq->ref))
+		__blk_mq_free_request(rq);
+}
+
+static void blk_mq_timeout_work(struct work_struct *work)
+{
+	struct request_queue *q =
+		container_of(work, struct request_queue, timeout_work);
+	unsigned long next = 0;
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	/* A deadlock might occur if a request is stuck requiring a
+	 * timeout at the same time a queue freeze is waiting
+	 * completion, since the timeout code would not be able to
+	 * acquire the queue reference here.
+	 *
+	 * That's why we don't use blk_queue_enter here; instead, we use
+	 * percpu_ref_tryget directly, because we need to be able to
+	 * obtain a reference even in the short window between the queue
+	 * starting to freeze, by dropping the first reference in
+	 * blk_freeze_queue_start, and the moment the last request is
+	 * consumed, marked by the instant q_usage_counter reaches
+	 * zero.
+	 */
+	if (!percpu_ref_tryget(&q->q_usage_counter))
+		return;
+
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &next);
+
+	if (next != 0) {
+		mod_timer(&q->timeout, next);
+	} else {
+		/*
+		 * Request timeouts are handled as a forward rolling timer. If
+		 * we end up here it means that no requests are pending and
+		 * also that no request has been pending for a while. Mark
+		 * each hctx as idle.
+		 */
+		queue_for_each_hw_ctx(q, hctx, i) {
+			/* the hctx may be unmapped, so check it here */
+			if (blk_mq_hw_queue_mapped(hctx))
+				blk_mq_tag_idle(hctx);
+		}
+	}
+	blk_queue_exit(q);
+}
+
+struct flush_busy_ctx_data {
+	struct blk_mq_hw_ctx *hctx;
+	struct list_head *list;
+};
+
+static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data)
+{
+	struct flush_busy_ctx_data *flush_data = data;
+	struct blk_mq_hw_ctx *hctx = flush_data->hctx;
+	struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
+
+	spin_lock(&ctx->lock);
+	list_splice_tail_init(&ctx->rq_list, flush_data->list);
+	sbitmap_clear_bit(sb, bitnr);
+	spin_unlock(&ctx->lock);
+	return true;
+}
+
+/*
+ * Process software queues that have been marked busy, splicing them
+ * to the for-dispatch
+ */
+void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
+{
+	struct flush_busy_ctx_data data = {
+		.hctx = hctx,
+		.list = list,
+	};
+
+	sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data);
+}
+EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs);
+
+struct dispatch_rq_data {
+	struct blk_mq_hw_ctx *hctx;
+	struct request *rq;
+};
+
+static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr,
+		void *data)
+{
+	struct dispatch_rq_data *dispatch_data = data;
+	struct blk_mq_hw_ctx *hctx = dispatch_data->hctx;
+	struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
+
+	spin_lock(&ctx->lock);
+	if (!list_empty(&ctx->rq_list)) {
+		dispatch_data->rq = list_entry_rq(ctx->rq_list.next);
+		list_del_init(&dispatch_data->rq->queuelist);
+		if (list_empty(&ctx->rq_list))
+			sbitmap_clear_bit(sb, bitnr);
+	}
+	spin_unlock(&ctx->lock);
+
+	return !dispatch_data->rq;
+}
+
+struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
+					struct blk_mq_ctx *start)
+{
+	unsigned off = start ? start->index_hw : 0;
+	struct dispatch_rq_data data = {
+		.hctx = hctx,
+		.rq   = NULL,
+	};
+
+	__sbitmap_for_each_set(&hctx->ctx_map, off,
+			       dispatch_rq_from_ctx, &data);
+
+	return data.rq;
+}
+
+static inline unsigned int queued_to_index(unsigned int queued)
+{
+	if (!queued)
+		return 0;
+
+	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
+}
+
+bool blk_mq_get_driver_tag(struct request *rq)
+{
+	struct blk_mq_alloc_data data = {
+		.q = rq->q,
+		.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
+		.flags = BLK_MQ_REQ_NOWAIT,
+	};
+	bool shared;
+
+	if (rq->tag != -1)
+		goto done;
+
+	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
+		data.flags |= BLK_MQ_REQ_RESERVED;
+
+	shared = blk_mq_tag_busy(data.hctx);
+	rq->tag = blk_mq_get_tag(&data);
+	if (rq->tag >= 0) {
+		if (shared) {
+			rq->rq_flags |= RQF_MQ_INFLIGHT;
+			atomic_inc(&data.hctx->nr_active);
+		}
+		data.hctx->tags->rqs[rq->tag] = rq;
+	}
+
+done:
+	return rq->tag != -1;
+}
+
+static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
+				int flags, void *key)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
+
+	spin_lock(&hctx->dispatch_wait_lock);
+	list_del_init(&wait->entry);
+	spin_unlock(&hctx->dispatch_wait_lock);
+
+	blk_mq_run_hw_queue(hctx, true);
+	return 1;
+}
+
+/*
+ * Mark us waiting for a tag. For shared tags, this involves hooking us into
+ * the tag wakeups. For non-shared tags, we can simply mark us needing a
+ * restart. For both cases, take care to check the condition again after
+ * marking us as waiting.
+ */
+static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
+				 struct request *rq)
+{
+	struct wait_queue_head *wq;
+	wait_queue_entry_t *wait;
+	bool ret;
+
+	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) {
+		if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+			set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+
+		/*
+		 * It's possible that a tag was freed in the window between the
+		 * allocation failure and adding the hardware queue to the wait
+		 * queue.
+		 *
+		 * Don't clear RESTART here, someone else could have set it.
+		 * At most this will cost an extra queue run.
+		 */
+		return blk_mq_get_driver_tag(rq);
+	}
+
+	wait = &hctx->dispatch_wait;
+	if (!list_empty_careful(&wait->entry))
+		return false;
+
+	wq = &bt_wait_ptr(&hctx->tags->bitmap_tags, hctx)->wait;
+
+	spin_lock_irq(&wq->lock);
+	spin_lock(&hctx->dispatch_wait_lock);
+	if (!list_empty(&wait->entry)) {
+		spin_unlock(&hctx->dispatch_wait_lock);
+		spin_unlock_irq(&wq->lock);
+		return false;
+	}
+
+	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
+	__add_wait_queue(wq, wait);
+
+	/*
+	 * It's possible that a tag was freed in the window between the
+	 * allocation failure and adding the hardware queue to the wait
+	 * queue.
+	 */
+	ret = blk_mq_get_driver_tag(rq);
+	if (!ret) {
+		spin_unlock(&hctx->dispatch_wait_lock);
+		spin_unlock_irq(&wq->lock);
+		return false;
+	}
+
+	/*
+	 * We got a tag, remove ourselves from the wait queue to ensure
+	 * someone else gets the wakeup.
+	 */
+	list_del_init(&wait->entry);
+	spin_unlock(&hctx->dispatch_wait_lock);
+	spin_unlock_irq(&wq->lock);
+
+	return true;
+}
+
+#define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT  8
+#define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR  4
+/*
+ * Update dispatch busy with the Exponential Weighted Moving Average(EWMA):
+ * - EWMA is one simple way to compute running average value
+ * - weight(7/8 and 1/8) is applied so that it can decrease exponentially
+ * - take 4 as factor for avoiding to get too small(0) result, and this
+ *   factor doesn't matter because EWMA decreases exponentially
+ */
+static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)
+{
+	unsigned int ewma;
+
+	if (hctx->queue->elevator)
+		return;
+
+	ewma = hctx->dispatch_busy;
+
+	if (!ewma && !busy)
+		return;
+
+	ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1;
+	if (busy)
+		ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR;
+	ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT;
+
+	hctx->dispatch_busy = ewma;
+}
+
+#define BLK_MQ_RESOURCE_DELAY	3		/* ms units */
+
+/*
+ * Returns true if we did some work AND can potentially do more.
+ */
+bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
+			     bool got_budget)
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct request *rq, *nxt;
+	bool no_tag = false;
+	int errors, queued;
+	blk_status_t ret = BLK_STS_OK;
+
+	if (list_empty(list))
+		return false;
+
+	WARN_ON(!list_is_singular(list) && got_budget);
+
+	/*
+	 * Now process all the entries, sending them to the driver.
+	 */
+	errors = queued = 0;
+	do {
+		struct blk_mq_queue_data bd;
+
+		rq = list_first_entry(list, struct request, queuelist);
+
+		hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
+		if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
+			break;
+
+		if (!blk_mq_get_driver_tag(rq)) {
+			/*
+			 * The initial allocation attempt failed, so we need to
+			 * rerun the hardware queue when a tag is freed. The
+			 * waitqueue takes care of that. If the queue is run
+			 * before we add this entry back on the dispatch list,
+			 * we'll re-run it below.
+			 */
+			if (!blk_mq_mark_tag_wait(hctx, rq)) {
+				blk_mq_put_dispatch_budget(hctx);
+				/*
+				 * For non-shared tags, the RESTART check
+				 * will suffice.
+				 */
+				if (hctx->flags & BLK_MQ_F_TAG_SHARED)
+					no_tag = true;
+				break;
+			}
+		}
+
+		list_del_init(&rq->queuelist);
+
+		bd.rq = rq;
+
+		/*
+		 * Flag last if we have no more requests, or if we have more
+		 * but can't assign a driver tag to it.
+		 */
+		if (list_empty(list))
+			bd.last = true;
+		else {
+			nxt = list_first_entry(list, struct request, queuelist);
+			bd.last = !blk_mq_get_driver_tag(nxt);
+		}
+
+		ret = q->mq_ops->queue_rq(hctx, &bd);
+		if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
+			/*
+			 * If an I/O scheduler has been configured and we got a
+			 * driver tag for the next request already, free it
+			 * again.
+			 */
+			if (!list_empty(list)) {
+				nxt = list_first_entry(list, struct request, queuelist);
+				blk_mq_put_driver_tag(nxt);
+			}
+			list_add(&rq->queuelist, list);
+			__blk_mq_requeue_request(rq);
+			break;
+		}
+
+		if (unlikely(ret != BLK_STS_OK)) {
+			errors++;
+			blk_mq_end_request(rq, BLK_STS_IOERR);
+			continue;
+		}
+
+		queued++;
+	} while (!list_empty(list));
+
+	hctx->dispatched[queued_to_index(queued)]++;
+
+	/*
+	 * Any items that need requeuing? Stuff them into hctx->dispatch,
+	 * that is where we will continue on next queue run.
+	 */
+	if (!list_empty(list)) {
+		bool needs_restart;
+
+		spin_lock(&hctx->lock);
+		list_splice_init(list, &hctx->dispatch);
+		spin_unlock(&hctx->lock);
+
+		/*
+		 * If SCHED_RESTART was set by the caller of this function and
+		 * it is no longer set that means that it was cleared by another
+		 * thread and hence that a queue rerun is needed.
+		 *
+		 * If 'no_tag' is set, that means that we failed getting
+		 * a driver tag with an I/O scheduler attached. If our dispatch
+		 * waitqueue is no longer active, ensure that we run the queue
+		 * AFTER adding our entries back to the list.
+		 *
+		 * If no I/O scheduler has been configured it is possible that
+		 * the hardware queue got stopped and restarted before requests
+		 * were pushed back onto the dispatch list. Rerun the queue to
+		 * avoid starvation. Notes:
+		 * - blk_mq_run_hw_queue() checks whether or not a queue has
+		 *   been stopped before rerunning a queue.
+		 * - Some but not all block drivers stop a queue before
+		 *   returning BLK_STS_RESOURCE. Two exceptions are scsi-mq
+		 *   and dm-rq.
+		 *
+		 * If driver returns BLK_STS_RESOURCE and SCHED_RESTART
+		 * bit is set, run queue after a delay to avoid IO stalls
+		 * that could otherwise occur if the queue is idle.
+		 */
+		needs_restart = blk_mq_sched_needs_restart(hctx);
+		if (!needs_restart ||
+		    (no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
+			blk_mq_run_hw_queue(hctx, true);
+		else if (needs_restart && (ret == BLK_STS_RESOURCE))
+			blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
+
+		blk_mq_update_dispatch_busy(hctx, true);
+		return false;
+	} else
+		blk_mq_update_dispatch_busy(hctx, false);
+
+	/*
+	 * If the host/device is unable to accept more work, inform the
+	 * caller of that.
+	 */
+	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
+		return false;
+
+	return (queued + errors) != 0;
+}
+
+static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
+{
+	int srcu_idx;
+
+	/*
+	 * We should be running this queue from one of the CPUs that
+	 * are mapped to it.
+	 *
+	 * There are at least two related races now between setting
+	 * hctx->next_cpu from blk_mq_hctx_next_cpu() and running
+	 * __blk_mq_run_hw_queue():
+	 *
+	 * - hctx->next_cpu is found offline in blk_mq_hctx_next_cpu(),
+	 *   but later it becomes online, then this warning is harmless
+	 *   at all
+	 *
+	 * - hctx->next_cpu is found online in blk_mq_hctx_next_cpu(),
+	 *   but later it becomes offline, then the warning can't be
+	 *   triggered, and we depend on blk-mq timeout handler to
+	 *   handle dispatched requests to this hctx
+	 */
+	if (!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
+		cpu_online(hctx->next_cpu)) {
+		printk(KERN_WARNING "run queue from wrong CPU %d, hctx %s\n",
+			raw_smp_processor_id(),
+			cpumask_empty(hctx->cpumask) ? "inactive": "active");
+		dump_stack();
+	}
+	pr_debug("__blk_mq_run_hw_queue");
+	/*
+	 * We can't run the queue inline with ints disabled. Ensure that
+	 * we catch bad users of this early.
+	 */
+	WARN_ON_ONCE(in_interrupt());
+
+	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
+
+	hctx_lock(hctx, &srcu_idx);
+	blk_mq_sched_dispatch_requests(hctx);
+	hctx_unlock(hctx, srcu_idx);
+}
+
+static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
+{
+	int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
+
+	if (cpu >= nr_cpu_ids)
+		cpu = cpumask_first(hctx->cpumask);
+	return cpu;
+}
+
+/*
+ * It'd be great if the workqueue API had a way to pass
+ * in a mask and had some smarts for more clever placement.
+ * For now we just round-robin here, switching for every
+ * BLK_MQ_CPU_WORK_BATCH queued items.
+ */
+static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
+{
+	bool tried = false;
+	int next_cpu = hctx->next_cpu;
+
+	if (hctx->queue->nr_hw_queues == 1)
+		return WORK_CPU_UNBOUND;
+
+	if (--hctx->next_cpu_batch <= 0) {
+select_cpu:
+		next_cpu = cpumask_next_and(next_cpu, hctx->cpumask,
+				cpu_online_mask);
+		if (next_cpu >= nr_cpu_ids)
+			next_cpu = blk_mq_first_mapped_cpu(hctx);
+		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
+	}
+
+	/*
+	 * Do unbound schedule if we can't find a online CPU for this hctx,
+	 * and it should only happen in the path of handling CPU DEAD.
+	 */
+	if (!cpu_online(next_cpu)) {
+		if (!tried) {
+			tried = true;
+			goto select_cpu;
+		}
+
+		/*
+		 * Make sure to re-select CPU next time once after CPUs
+		 * in hctx->cpumask become online again.
+		 */
+		hctx->next_cpu = next_cpu;
+		hctx->next_cpu_batch = 1;
+		return WORK_CPU_UNBOUND;
+	}
+
+	hctx->next_cpu = next_cpu;
+	return next_cpu;
+}
+
+static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
+					unsigned long msecs)
+{
+	if (unlikely(blk_mq_hctx_stopped(hctx)))
+		return;
+
+	if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
+		int cpu = get_cpu();
+		if (cpumask_test_cpu(cpu, hctx->cpumask)) {
+			__blk_mq_run_hw_queue(hctx);
+			put_cpu();
+			return;
+		}
+
+		put_cpu();
+	}
+
+	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
+				    msecs_to_jiffies(msecs));
+}
+
+void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
+{
+	__blk_mq_delay_run_hw_queue(hctx, true, msecs);
+}
+EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
+
+bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+{
+	int srcu_idx;
+	bool need_run;
+
+	/*
+	 * When queue is quiesced, we may be switching io scheduler, or
+	 * updating nr_hw_queues, or other things, and we can't run queue
+	 * any more, even __blk_mq_hctx_has_pending() can't be called safely.
+	 *
+	 * And queue will be rerun in blk_mq_unquiesce_queue() if it is
+	 * quiesced.
+	 */
+	hctx_lock(hctx, &srcu_idx);
+	need_run = !blk_queue_quiesced(hctx->queue) &&
+		blk_mq_hctx_has_pending(hctx);
+	hctx_unlock(hctx, srcu_idx);
+
+	if (need_run) {
+		__blk_mq_delay_run_hw_queue(hctx, async, 0);
+		return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(blk_mq_run_hw_queue);
+
+void blk_mq_run_hw_queues(struct request_queue *q, bool async)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (blk_mq_hctx_stopped(hctx))
+			continue;
+
+		blk_mq_run_hw_queue(hctx, async);
+	}
+}
+EXPORT_SYMBOL(blk_mq_run_hw_queues);
+
+/**
+ * blk_mq_queue_stopped() - check whether one or more hctxs have been stopped
+ * @q: request queue.
+ *
+ * The caller is responsible for serializing this function against
+ * blk_mq_{start,stop}_hw_queue().
+ */
+bool blk_mq_queue_stopped(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		if (blk_mq_hctx_stopped(hctx))
+			return true;
+
+	return false;
+}
+EXPORT_SYMBOL(blk_mq_queue_stopped);
+
+/*
+ * This function is often used for pausing .queue_rq() by driver when
+ * there isn't enough resource or some conditions aren't satisfied, and
+ * BLK_STS_RESOURCE is usually returned.
+ *
+ * We do not guarantee that dispatch can be drained or blocked
+ * after blk_mq_stop_hw_queue() returns. Please use
+ * blk_mq_quiesce_queue() for that requirement.
+ */
+void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
+{
+	cancel_delayed_work(&hctx->run_work);
+
+	set_bit(BLK_MQ_S_STOPPED, &hctx->state);
+}
+EXPORT_SYMBOL(blk_mq_stop_hw_queue);
+
+/*
+ * This function is often used for pausing .queue_rq() by driver when
+ * there isn't enough resource or some conditions aren't satisfied, and
+ * BLK_STS_RESOURCE is usually returned.
+ *
+ * We do not guarantee that dispatch can be drained or blocked
+ * after blk_mq_stop_hw_queues() returns. Please use
+ * blk_mq_quiesce_queue() for that requirement.
+ */
+void blk_mq_stop_hw_queues(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_stop_hw_queue(hctx);
+}
+EXPORT_SYMBOL(blk_mq_stop_hw_queues);
+
+void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx)
+{
+	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+
+	blk_mq_run_hw_queue(hctx, false);
+}
+EXPORT_SYMBOL(blk_mq_start_hw_queue);
+
+void blk_mq_start_hw_queues(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_start_hw_queue(hctx);
+}
+EXPORT_SYMBOL(blk_mq_start_hw_queues);
+
+void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+{
+	if (!blk_mq_hctx_stopped(hctx))
+		return;
+
+	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+	blk_mq_run_hw_queue(hctx, async);
+}
+EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue);
+
+void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_start_stopped_hw_queue(hctx, async);
+}
+EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);
+
+static void blk_mq_run_work_fn(struct work_struct *work)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work);
+
+	/*
+	 * If we are stopped, don't run the queue.
+	 */
+	if (test_bit(BLK_MQ_S_STOPPED, &hctx->state))
+		return;
+
+	__blk_mq_run_hw_queue(hctx);
+}
+
+static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
+					    struct request *rq,
+					    bool at_head)
+{
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+
+	lockdep_assert_held(&ctx->lock);
+
+	trace_block_rq_insert(hctx->queue, rq);
+
+	if (at_head)
+		list_add(&rq->queuelist, &ctx->rq_list);
+	else
+		list_add_tail(&rq->queuelist, &ctx->rq_list);
+}
+
+void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+			     bool at_head)
+{
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+
+	lockdep_assert_held(&ctx->lock);
+
+	__blk_mq_insert_req_list(hctx, rq, at_head);
+	blk_mq_hctx_mark_pending(hctx, ctx);
+}
+
+/*
+ * Should only be used carefully, when the caller knows we want to
+ * bypass a potential IO scheduler on the target device.
+ */
+void blk_mq_request_bypass_insert(struct request *rq, bool run_queue)
+{
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu);
+
+	spin_lock(&hctx->lock);
+	list_add_tail(&rq->queuelist, &hctx->dispatch);
+	spin_unlock(&hctx->lock);
+
+	if (run_queue)
+		blk_mq_run_hw_queue(hctx, false);
+}
+
+void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+			    struct list_head *list)
+
+{
+	struct request *rq;
+
+	/*
+	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
+	 * offline now
+	 */
+	list_for_each_entry(rq, list, queuelist) {
+		BUG_ON(rq->mq_ctx != ctx);
+		trace_block_rq_insert(hctx->queue, rq);
+	}
+
+	spin_lock(&ctx->lock);
+	list_splice_tail_init(list, &ctx->rq_list);
+	blk_mq_hctx_mark_pending(hctx, ctx);
+	spin_unlock(&ctx->lock);
+}
+
+static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct request *rqa = container_of(a, struct request, queuelist);
+	struct request *rqb = container_of(b, struct request, queuelist);
+
+	return !(rqa->mq_ctx < rqb->mq_ctx ||
+		 (rqa->mq_ctx == rqb->mq_ctx &&
+		  blk_rq_pos(rqa) < blk_rq_pos(rqb)));
+}
+
+void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
+{
+	struct blk_mq_ctx *this_ctx;
+	struct request_queue *this_q;
+	struct request *rq;
+	LIST_HEAD(list);
+	LIST_HEAD(ctx_list);
+	unsigned int depth;
+
+	list_splice_init(&plug->mq_list, &list);
+
+	list_sort(NULL, &list, plug_ctx_cmp);
+
+	this_q = NULL;
+	this_ctx = NULL;
+	depth = 0;
+
+	while (!list_empty(&list)) {
+		rq = list_entry_rq(list.next);
+		list_del_init(&rq->queuelist);
+		BUG_ON(!rq->q);
+		if (rq->mq_ctx != this_ctx) {
+			if (this_ctx) {
+				trace_block_unplug(this_q, depth, !from_schedule);
+				blk_mq_sched_insert_requests(this_q, this_ctx,
+								&ctx_list,
+								from_schedule);
+			}
+
+			this_ctx = rq->mq_ctx;
+			this_q = rq->q;
+			depth = 0;
+		}
+
+		depth++;
+		list_add_tail(&rq->queuelist, &ctx_list);
+	}
+
+	/*
+	 * If 'this_ctx' is set, we know we have entries to complete
+	 * on 'ctx_list'. Do those.
+	 */
+	if (this_ctx) {
+		trace_block_unplug(this_q, depth, !from_schedule);
+		blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
+						from_schedule);
+	}
+}
+
+static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
+{
+	blk_init_request_from_bio(rq, bio);
+
+	blk_rq_set_rl(rq, blk_get_rl(rq->q, bio));
+
+	blk_account_io_start(rq, true);
+}
+
+static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
+{
+	if (rq->tag != -1)
+		return blk_tag_to_qc_t(rq->tag, hctx->queue_num, false);
+
+	return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
+}
+
+static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
+					    struct request *rq,
+					    blk_qc_t *cookie)
+{
+	struct request_queue *q = rq->q;
+	struct blk_mq_queue_data bd = {
+		.rq = rq,
+		.last = true,
+	};
+	blk_qc_t new_cookie;
+	blk_status_t ret;
+
+	new_cookie = request_to_qc_t(hctx, rq);
+
+	/*
+	 * For OK queue, we are done. For error, caller may kill it.
+	 * Any other error (busy), just add it to our list as we
+	 * previously would have done.
+	 */
+	ret = q->mq_ops->queue_rq(hctx, &bd);
+	switch (ret) {
+	case BLK_STS_OK:
+		blk_mq_update_dispatch_busy(hctx, false);
+		*cookie = new_cookie;
+		break;
+	case BLK_STS_RESOURCE:
+	case BLK_STS_DEV_RESOURCE:
+		blk_mq_update_dispatch_busy(hctx, true);
+		__blk_mq_requeue_request(rq);
+		break;
+	default:
+		blk_mq_update_dispatch_busy(hctx, false);
+		*cookie = BLK_QC_T_NONE;
+		break;
+	}
+
+	return ret;
+}
+
+static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+						struct request *rq,
+						blk_qc_t *cookie,
+						bool bypass_insert)
+{
+	struct request_queue *q = rq->q;
+	bool run_queue = true;
+
+	/*
+	 * RCU or SRCU read lock is needed before checking quiesced flag.
+	 *
+	 * When queue is stopped or quiesced, ignore 'bypass_insert' from
+	 * blk_mq_request_issue_directly(), and return BLK_STS_OK to caller,
+	 * and avoid driver to try to dispatch again.
+	 */
+	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) {
+		run_queue = false;
+		bypass_insert = false;
+		goto insert;
+	}
+
+	if (q->elevator && !bypass_insert)
+		goto insert;
+
+	if (!blk_mq_get_dispatch_budget(hctx))
+		goto insert;
+
+	if (!blk_mq_get_driver_tag(rq)) {
+		blk_mq_put_dispatch_budget(hctx);
+		goto insert;
+	}
+
+	return __blk_mq_issue_directly(hctx, rq, cookie);
+insert:
+	if (bypass_insert)
+		return BLK_STS_RESOURCE;
+
+	blk_mq_sched_insert_request(rq, false, run_queue, false);
+	return BLK_STS_OK;
+}
+
+static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+		struct request *rq, blk_qc_t *cookie)
+{
+	blk_status_t ret;
+	int srcu_idx;
+
+	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
+
+	hctx_lock(hctx, &srcu_idx);
+
+	ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false);
+	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
+		blk_mq_sched_insert_request(rq, false, true, false);
+	else if (ret != BLK_STS_OK)
+		blk_mq_end_request(rq, ret);
+
+	hctx_unlock(hctx, srcu_idx);
+}
+
+blk_status_t blk_mq_request_issue_directly(struct request *rq)
+{
+	blk_status_t ret;
+	int srcu_idx;
+	blk_qc_t unused_cookie;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu);
+
+	hctx_lock(hctx, &srcu_idx);
+	ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true);
+	hctx_unlock(hctx, srcu_idx);
+
+	return ret;
+}
+
+void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+		struct list_head *list)
+{
+	while (!list_empty(list)) {
+		blk_status_t ret;
+		struct request *rq = list_first_entry(list, struct request,
+				queuelist);
+
+		list_del_init(&rq->queuelist);
+		ret = blk_mq_request_issue_directly(rq);
+		if (ret != BLK_STS_OK) {
+			if (ret == BLK_STS_RESOURCE ||
+					ret == BLK_STS_DEV_RESOURCE) {
+				list_add(&rq->queuelist, list);
+				break;
+			}
+			blk_mq_end_request(rq, ret);
+		}
+	}
+}
+
+static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
+{
+	const int is_sync = op_is_sync(bio->bi_opf);
+	const int is_flush_fua = op_is_flush(bio->bi_opf);
+	struct blk_mq_alloc_data data = { .flags = 0 };
+	struct request *rq;
+	unsigned int request_count = 0;
+	struct blk_plug *plug;
+	struct request *same_queue_rq = NULL;
+	blk_qc_t cookie;
+
+	blk_queue_bounce(q, &bio);
+
+	blk_queue_split(q, &bio);
+
+	if (!bio_integrity_prep(bio))
+		return BLK_QC_T_NONE;
+
+	if (!is_flush_fua && !blk_queue_nomerges(q) &&
+	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
+		return BLK_QC_T_NONE;
+
+	if (blk_mq_sched_bio_merge(q, bio))
+		return BLK_QC_T_NONE;
+
+	rq_qos_throttle(q, bio, NULL);
+
+	trace_block_getrq(q, bio, bio->bi_opf);
+
+	rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
+	if (unlikely(!rq)) {
+		rq_qos_cleanup(q, bio);
+		if (bio->bi_opf & REQ_NOWAIT)
+			bio_wouldblock_error(bio);
+		return BLK_QC_T_NONE;
+	}
+
+	rq_qos_track(q, rq, bio);
+
+	cookie = request_to_qc_t(data.hctx, rq);
+
+	plug = current->plug;
+	if (unlikely(is_flush_fua)) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+
+		/* bypass scheduler for flush rq */
+		blk_insert_flush(rq);
+		blk_mq_run_hw_queue(data.hctx, true);
+	} else if (plug && q->nr_hw_queues == 1) {
+		struct request *last = NULL;
+
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+
+		/*
+		 * @request_count may become stale because of schedule
+		 * out, so check the list again.
+		 */
+		if (list_empty(&plug->mq_list))
+			request_count = 0;
+		else if (blk_queue_nomerges(q))
+			request_count = blk_plug_queued_count(q);
+
+		if (!request_count)
+			trace_block_plug(q);
+		else
+			last = list_entry_rq(plug->mq_list.prev);
+
+		if (request_count >= BLK_MAX_REQUEST_COUNT || (last &&
+		    blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
+			blk_flush_plug_list(plug, false);
+			trace_block_plug(q);
+		}
+
+		list_add_tail(&rq->queuelist, &plug->mq_list);
+	} else if (plug && !blk_queue_nomerges(q)) {
+		blk_mq_bio_to_request(rq, bio);
+
+		/*
+		 * We do limited plugging. If the bio can be merged, do that.
+		 * Otherwise the existing request in the plug list will be
+		 * issued. So the plug list will have one request at most
+		 * The plug list might get flushed before this. If that happens,
+		 * the plug list is empty, and same_queue_rq is invalid.
+		 */
+		if (list_empty(&plug->mq_list))
+			same_queue_rq = NULL;
+		if (same_queue_rq)
+			list_del_init(&same_queue_rq->queuelist);
+		list_add_tail(&rq->queuelist, &plug->mq_list);
+
+		blk_mq_put_ctx(data.ctx);
+
+		if (same_queue_rq) {
+			data.hctx = blk_mq_map_queue(q,
+					same_queue_rq->mq_ctx->cpu);
+			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
+					&cookie);
+		}
+	} else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
+			!data.hctx->dispatch_busy)) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
+	} else {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_sched_insert_request(rq, false, true, true);
+	}
+
+	return cookie;
+}
+
+void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx)
+{
+	struct page *page;
+
+	if (tags->rqs && set->ops->exit_request) {
+		int i;
+
+		for (i = 0; i < tags->nr_tags; i++) {
+			struct request *rq = tags->static_rqs[i];
+
+			if (!rq)
+				continue;
+			set->ops->exit_request(set, rq, hctx_idx);
+			tags->static_rqs[i] = NULL;
+		}
+	}
+
+	while (!list_empty(&tags->page_list)) {
+		page = list_first_entry(&tags->page_list, struct page, lru);
+		list_del_init(&page->lru);
+		/*
+		 * Remove kmemleak object previously allocated in
+		 * blk_mq_init_rq_map().
+		 */
+		kmemleak_free(page_address(page));
+		__free_pages(page, page->private);
+	}
+}
+
+void blk_mq_free_rq_map(struct blk_mq_tags *tags)
+{
+	kfree(tags->rqs);
+	tags->rqs = NULL;
+	kfree(tags->static_rqs);
+	tags->static_rqs = NULL;
+
+	blk_mq_free_tags(tags);
+}
+
+struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
+					unsigned int hctx_idx,
+					unsigned int nr_tags,
+					unsigned int reserved_tags)
+{
+	struct blk_mq_tags *tags;
+	int node;
+
+	node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx);
+	if (node == NUMA_NO_NODE)
+		node = set->numa_node;
+
+	tags = blk_mq_init_tags(nr_tags, reserved_tags, node,
+				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
+	if (!tags)
+		return NULL;
+
+	tags->rqs = kcalloc_node(nr_tags, sizeof(struct request *),
+				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
+				 node);
+	if (!tags->rqs) {
+		blk_mq_free_tags(tags);
+		return NULL;
+	}
+
+	tags->static_rqs = kcalloc_node(nr_tags, sizeof(struct request *),
+					GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
+					node);
+	if (!tags->static_rqs) {
+		kfree(tags->rqs);
+		blk_mq_free_tags(tags);
+		return NULL;
+	}
+
+	return tags;
+}
+
+static size_t order_to_size(unsigned int order)
+{
+	return (size_t)PAGE_SIZE << order;
+}
+
+static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
+			       unsigned int hctx_idx, int node)
+{
+	int ret;
+
+	if (set->ops->init_request) {
+		ret = set->ops->init_request(set, rq, hctx_idx, node);
+		if (ret)
+			return ret;
+	}
+
+	WRITE_ONCE(rq->state, MQ_RQ_IDLE);
+	return 0;
+}
+
+int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx, unsigned int depth)
+{
+	unsigned int i, j, entries_per_page, max_order = 4;
+	size_t rq_size, left;
+	int node;
+
+	node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx);
+	if (node == NUMA_NO_NODE)
+		node = set->numa_node;
+
+	INIT_LIST_HEAD(&tags->page_list);
+
+	/*
+	 * rq_size is the size of the request plus driver payload, rounded
+	 * to the cacheline size
+	 */
+	rq_size = round_up(sizeof(struct request) + set->cmd_size,
+				cache_line_size());
+	left = rq_size * depth;
+
+	for (i = 0; i < depth; ) {
+		int this_order = max_order;
+		struct page *page;
+		int to_do;
+		void *p;
+
+		while (this_order && left < order_to_size(this_order - 1))
+			this_order--;
+
+		do {
+			page = alloc_pages_node(node,
+				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
+				this_order);
+			if (page)
+				break;
+			if (!this_order--)
+				break;
+			if (order_to_size(this_order) < rq_size)
+				break;
+		} while (1);
+
+		if (!page)
+			goto fail;
+
+		page->private = this_order;
+		list_add_tail(&page->lru, &tags->page_list);
+
+		p = page_address(page);
+		/*
+		 * Allow kmemleak to scan these pages as they contain pointers
+		 * to additional allocations like via ops->init_request().
+		 */
+		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO);
+		entries_per_page = order_to_size(this_order) / rq_size;
+		to_do = min(entries_per_page, depth - i);
+		left -= to_do * rq_size;
+		for (j = 0; j < to_do; j++) {
+			struct request *rq = p;
+
+			tags->static_rqs[i] = rq;
+			if (blk_mq_init_request(set, rq, hctx_idx, node)) {
+				tags->static_rqs[i] = NULL;
+				goto fail;
+			}
+
+			p += rq_size;
+			i++;
+		}
+	}
+	return 0;
+
+fail:
+	blk_mq_free_rqs(set, tags, hctx_idx);
+	return -ENOMEM;
+}
+
+/*
+ * 'cpu' is going away. splice any existing rq_list entries from this
+ * software queue to the hw queue dispatch list, and ensure that it
+ * gets run.
+ */
+static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	LIST_HEAD(tmp);
+
+	hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);
+	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
+
+	spin_lock(&ctx->lock);
+	if (!list_empty(&ctx->rq_list)) {
+		list_splice_init(&ctx->rq_list, &tmp);
+		blk_mq_hctx_clear_pending(hctx, ctx);
+	}
+	spin_unlock(&ctx->lock);
+
+	if (list_empty(&tmp))
+		return 0;
+
+	spin_lock(&hctx->lock);
+	list_splice_tail_init(&tmp, &hctx->dispatch);
+	spin_unlock(&hctx->lock);
+
+	blk_mq_run_hw_queue(hctx, true);
+	return 0;
+}
+
+static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
+{
+	cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
+					    &hctx->cpuhp_dead);
+}
+
+/* hctx->ctxs will be freed in queue's release handler */
+static void blk_mq_exit_hctx(struct request_queue *q,
+		struct blk_mq_tag_set *set,
+		struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
+{
+	blk_mq_debugfs_unregister_hctx(hctx);
+
+	if (blk_mq_hw_queue_mapped(hctx))
+		blk_mq_tag_idle(hctx);
+
+	if (set->ops->exit_request)
+		set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
+
+	if (set->ops->exit_hctx)
+		set->ops->exit_hctx(hctx, hctx_idx);
+
+	if (hctx->flags & BLK_MQ_F_BLOCKING)
+		cleanup_srcu_struct(hctx->srcu);
+
+	blk_mq_remove_cpuhp(hctx);
+	blk_free_flush_queue(hctx->fq);
+	sbitmap_free(&hctx->ctx_map);
+}
+
+static void blk_mq_exit_hw_queues(struct request_queue *q,
+		struct blk_mq_tag_set *set, int nr_queue)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (i == nr_queue)
+			break;
+		blk_mq_exit_hctx(q, set, hctx, i);
+	}
+}
+
+static int blk_mq_init_hctx(struct request_queue *q,
+		struct blk_mq_tag_set *set,
+		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
+{
+	int node;
+
+	node = hctx->numa_node;
+	if (node == NUMA_NO_NODE)
+		node = hctx->numa_node = set->numa_node;
+
+	INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
+	spin_lock_init(&hctx->lock);
+	INIT_LIST_HEAD(&hctx->dispatch);
+	hctx->queue = q;
+	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
+
+	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
+
+	hctx->tags = set->tags[hctx_idx];
+
+	/*
+	 * Allocate space for all possible cpus to avoid allocation at
+	 * runtime
+	 */
+	hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *),
+					GFP_KERNEL, node);
+	if (!hctx->ctxs)
+		goto unregister_cpu_notifier;
+
+	if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8), GFP_KERNEL,
+			      node))
+		goto free_ctxs;
+
+	hctx->nr_ctx = 0;
+
+	spin_lock_init(&hctx->dispatch_wait_lock);
+	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
+	INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
+
+	if (set->ops->init_hctx &&
+	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
+		goto free_bitmap;
+
+	hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size);
+	if (!hctx->fq)
+		goto exit_hctx;
+
+	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, node))
+		goto free_fq;
+
+	if (hctx->flags & BLK_MQ_F_BLOCKING)
+		init_srcu_struct(hctx->srcu);
+
+	blk_mq_debugfs_register_hctx(q, hctx);
+
+	return 0;
+
+ free_fq:
+	kfree(hctx->fq);
+ exit_hctx:
+	if (set->ops->exit_hctx)
+		set->ops->exit_hctx(hctx, hctx_idx);
+ free_bitmap:
+	sbitmap_free(&hctx->ctx_map);
+ free_ctxs:
+	kfree(hctx->ctxs);
+ unregister_cpu_notifier:
+	blk_mq_remove_cpuhp(hctx);
+	return -1;
+}
+
+static void blk_mq_init_cpu_queues(struct request_queue *q,
+				   unsigned int nr_hw_queues)
+{
+	unsigned int i;
+
+	for_each_possible_cpu(i) {
+		struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i);
+		struct blk_mq_hw_ctx *hctx;
+
+		__ctx->cpu = i;
+		spin_lock_init(&__ctx->lock);
+		INIT_LIST_HEAD(&__ctx->rq_list);
+		__ctx->queue = q;
+
+		/*
+		 * Set local node, IFF we have more than one hw queue. If
+		 * not, we remain on the home node of the device
+		 */
+		hctx = blk_mq_map_queue(q, i);
+		if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE)
+			hctx->numa_node = local_memory_node(cpu_to_node(i));
+	}
+}
+
+static bool __blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, int hctx_idx)
+{
+	int ret = 0;
+
+	set->tags[hctx_idx] = blk_mq_alloc_rq_map(set, hctx_idx,
+					set->queue_depth, set->reserved_tags);
+	if (!set->tags[hctx_idx])
+		return false;
+
+	ret = blk_mq_alloc_rqs(set, set->tags[hctx_idx], hctx_idx,
+				set->queue_depth);
+	if (!ret)
+		return true;
+
+	blk_mq_free_rq_map(set->tags[hctx_idx]);
+	set->tags[hctx_idx] = NULL;
+	return false;
+}
+
+static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
+					 unsigned int hctx_idx)
+{
+	if (set->tags[hctx_idx]) {
+		blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx);
+		blk_mq_free_rq_map(set->tags[hctx_idx]);
+		set->tags[hctx_idx] = NULL;
+	}
+}
+
+static void blk_mq_map_swqueue(struct request_queue *q)
+{
+	unsigned int i, hctx_idx;
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	struct blk_mq_tag_set *set = q->tag_set;
+
+	/*
+	 * Avoid others reading imcomplete hctx->cpumask through sysfs
+	 */
+	mutex_lock(&q->sysfs_lock);
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		cpumask_clear(hctx->cpumask);
+		hctx->nr_ctx = 0;
+		hctx->dispatch_from = NULL;
+	}
+
+	/*
+	 * Map software to hardware queues.
+	 *
+	 * If the cpu isn't present, the cpu is mapped to first hctx.
+	 */
+	for_each_possible_cpu(i) {
+		hctx_idx = q->mq_map[i];
+		/* unmapped hw queue can be remapped after CPU topo changed */
+		if (!set->tags[hctx_idx] &&
+		    !__blk_mq_alloc_rq_map(set, hctx_idx)) {
+			/*
+			 * If tags initialization fail for some hctx,
+			 * that hctx won't be brought online.  In this
+			 * case, remap the current ctx to hctx[0] which
+			 * is guaranteed to always have tags allocated
+			 */
+			q->mq_map[i] = 0;
+		}
+
+		ctx = per_cpu_ptr(q->queue_ctx, i);
+		hctx = blk_mq_map_queue(q, i);
+
+		cpumask_set_cpu(i, hctx->cpumask);
+		ctx->index_hw = hctx->nr_ctx;
+		hctx->ctxs[hctx->nr_ctx++] = ctx;
+	}
+
+	mutex_unlock(&q->sysfs_lock);
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		/*
+		 * If no software queues are mapped to this hardware queue,
+		 * disable it and free the request entries.
+		 */
+		if (!hctx->nr_ctx) {
+			/* Never unmap queue 0.  We need it as a
+			 * fallback in case of a new remap fails
+			 * allocation
+			 */
+			if (i && set->tags[i])
+				blk_mq_free_map_and_requests(set, i);
+
+			hctx->tags = NULL;
+			continue;
+		}
+
+		hctx->tags = set->tags[i];
+		WARN_ON(!hctx->tags);
+
+		/*
+		 * Set the map size to the number of mapped software queues.
+		 * This is more accurate and more efficient than looping
+		 * over all possibly mapped software queues.
+		 */
+		sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx);
+
+		/*
+		 * Initialize batch roundrobin counts
+		 */
+		hctx->next_cpu = blk_mq_first_mapped_cpu(hctx);
+		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
+	}
+}
+
+/*
+ * Caller needs to ensure that we're either frozen/quiesced, or that
+ * the queue isn't live yet.
+ */
+static void queue_set_hctx_shared(struct request_queue *q, bool shared)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (shared)
+			hctx->flags |= BLK_MQ_F_TAG_SHARED;
+		else
+			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
+	}
+}
+
+static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set,
+					bool shared)
+{
+	struct request_queue *q;
+
+	lockdep_assert_held(&set->tag_list_lock);
+
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		blk_mq_freeze_queue(q);
+		queue_set_hctx_shared(q, shared);
+		blk_mq_unfreeze_queue(q);
+	}
+}
+
+static void blk_mq_del_queue_tag_set(struct request_queue *q)
+{
+	struct blk_mq_tag_set *set = q->tag_set;
+
+	mutex_lock(&set->tag_list_lock);
+	list_del_rcu(&q->tag_set_list);
+	if (list_is_singular(&set->tag_list)) {
+		/* just transitioned to unshared */
+		set->flags &= ~BLK_MQ_F_TAG_SHARED;
+		/* update existing queue */
+		blk_mq_update_tag_set_depth(set, false);
+	}
+	mutex_unlock(&set->tag_list_lock);
+	INIT_LIST_HEAD(&q->tag_set_list);
+}
+
+static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
+				     struct request_queue *q)
+{
+	q->tag_set = set;
+
+	mutex_lock(&set->tag_list_lock);
+
+	/*
+	 * Check to see if we're transitioning to shared (from 1 to 2 queues).
+	 */
+	if (!list_empty(&set->tag_list) &&
+	    !(set->flags & BLK_MQ_F_TAG_SHARED)) {
+		set->flags |= BLK_MQ_F_TAG_SHARED;
+		/* update existing queue */
+		blk_mq_update_tag_set_depth(set, true);
+	}
+	if (set->flags & BLK_MQ_F_TAG_SHARED)
+		queue_set_hctx_shared(q, true);
+	list_add_tail_rcu(&q->tag_set_list, &set->tag_list);
+
+	mutex_unlock(&set->tag_list_lock);
+}
+
+/*
+ * It is the actual release handler for mq, but we do it from
+ * request queue's release handler for avoiding use-after-free
+ * and headache because q->mq_kobj shouldn't have been introduced,
+ * but we can't group ctx/kctx kobj without it.
+ */
+void blk_mq_release(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	/* hctx kobj stays in hctx */
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (!hctx)
+			continue;
+		kobject_put(&hctx->kobj);
+	}
+
+	q->mq_map = NULL;
+
+	kfree(q->queue_hw_ctx);
+
+	/*
+	 * release .mq_kobj and sw queue's kobject now because
+	 * both share lifetime with request queue.
+	 */
+	blk_mq_sysfs_deinit(q);
+
+	free_percpu(q->queue_ctx);
+}
+
+struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
+{
+	struct request_queue *uninit_q, *q;
+
+	uninit_q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node, NULL);
+	if (!uninit_q)
+		return ERR_PTR(-ENOMEM);
+
+	q = blk_mq_init_allocated_queue(set, uninit_q);
+	if (IS_ERR(q))
+		blk_cleanup_queue(uninit_q);
+
+	return q;
+}
+EXPORT_SYMBOL(blk_mq_init_queue);
+
+static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
+{
+	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
+
+	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
+			   __alignof__(struct blk_mq_hw_ctx)) !=
+		     sizeof(struct blk_mq_hw_ctx));
+
+	if (tag_set->flags & BLK_MQ_F_BLOCKING)
+		hw_ctx_size += sizeof(struct srcu_struct);
+
+	return hw_ctx_size;
+}
+
+static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
+						struct request_queue *q)
+{
+	int i, j;
+	struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
+
+	blk_mq_sysfs_unregister(q);
+
+	/* protect against switching io scheduler  */
+	mutex_lock(&q->sysfs_lock);
+	for (i = 0; i < set->nr_hw_queues; i++) {
+		int node;
+
+		if (hctxs[i])
+			continue;
+
+		node = blk_mq_hw_queue_to_node(q->mq_map, i);
+		hctxs[i] = kzalloc_node(blk_mq_hw_ctx_size(set),
+					GFP_KERNEL, node);
+		if (!hctxs[i])
+			break;
+
+		if (!zalloc_cpumask_var_node(&hctxs[i]->cpumask, GFP_KERNEL,
+						node)) {
+			kfree(hctxs[i]);
+			hctxs[i] = NULL;
+			break;
+		}
+
+		atomic_set(&hctxs[i]->nr_active, 0);
+		hctxs[i]->numa_node = node;
+		hctxs[i]->queue_num = i;
+
+		if (blk_mq_init_hctx(q, set, hctxs[i], i)) {
+			free_cpumask_var(hctxs[i]->cpumask);
+			kfree(hctxs[i]);
+			hctxs[i] = NULL;
+			break;
+		}
+		blk_mq_hctx_kobj_init(hctxs[i]);
+	}
+	for (j = i; j < q->nr_hw_queues; j++) {
+		struct blk_mq_hw_ctx *hctx = hctxs[j];
+
+		if (hctx) {
+			if (hctx->tags)
+				blk_mq_free_map_and_requests(set, j);
+			blk_mq_exit_hctx(q, set, hctx, j);
+			kobject_put(&hctx->kobj);
+			hctxs[j] = NULL;
+
+		}
+	}
+	q->nr_hw_queues = i;
+	mutex_unlock(&q->sysfs_lock);
+	blk_mq_sysfs_register(q);
+}
+
+struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
+						  struct request_queue *q)
+{
+	/* mark the queue as mq asap */
+	q->mq_ops = set->ops;
+
+	q->poll_cb = blk_stat_alloc_callback(blk_mq_poll_stats_fn,
+					     blk_mq_poll_stats_bkt,
+					     BLK_MQ_POLL_STATS_BKTS, q);
+	if (!q->poll_cb)
+		goto err_exit;
+
+	q->queue_ctx = alloc_percpu(struct blk_mq_ctx);
+	if (!q->queue_ctx)
+		goto err_exit;
+
+	/* init q->mq_kobj and sw queues' kobjects */
+	blk_mq_sysfs_init(q);
+
+	q->queue_hw_ctx = kcalloc_node(nr_cpu_ids, sizeof(*(q->queue_hw_ctx)),
+						GFP_KERNEL, set->numa_node);
+	if (!q->queue_hw_ctx)
+		goto err_percpu;
+
+	q->mq_map = set->mq_map;
+
+	blk_mq_realloc_hw_ctxs(set, q);
+	if (!q->nr_hw_queues)
+		goto err_hctxs;
+
+	INIT_WORK(&q->timeout_work, blk_mq_timeout_work);
+	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
+
+	q->nr_queues = nr_cpu_ids;
+
+	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
+
+	if (!(set->flags & BLK_MQ_F_SG_MERGE))
+		queue_flag_set_unlocked(QUEUE_FLAG_NO_SG_MERGE, q);
+
+	q->sg_reserved_size = INT_MAX;
+
+	INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work);
+	INIT_LIST_HEAD(&q->requeue_list);
+	spin_lock_init(&q->requeue_lock);
+
+	blk_queue_make_request(q, blk_mq_make_request);
+	if (q->mq_ops->poll)
+		q->poll_fn = blk_mq_poll;
+
+	/*
+	 * Do this after blk_queue_make_request() overrides it...
+	 */
+	q->nr_requests = set->queue_depth;
+
+	/*
+	 * Default to classic polling
+	 */
+	q->poll_nsec = -1;
+
+	if (set->ops->complete)
+		blk_queue_softirq_done(q, set->ops->complete);
+
+	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
+	blk_mq_add_queue_tag_set(set, q);
+	blk_mq_map_swqueue(q);
+
+	if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
+		int ret;
+
+		ret = elevator_init_mq(q);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
+	return q;
+
+err_hctxs:
+	kfree(q->queue_hw_ctx);
+err_percpu:
+	free_percpu(q->queue_ctx);
+err_exit:
+	q->mq_ops = NULL;
+	return ERR_PTR(-ENOMEM);
+}
+EXPORT_SYMBOL(blk_mq_init_allocated_queue);
+
+void blk_mq_free_queue(struct request_queue *q)
+{
+	struct blk_mq_tag_set	*set = q->tag_set;
+
+	blk_mq_del_queue_tag_set(q);
+	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
+}
+
+/* Basically redo blk_mq_init_queue with queue frozen */
+static void blk_mq_queue_reinit(struct request_queue *q)
+{
+	WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
+
+	blk_mq_debugfs_unregister_hctxs(q);
+	blk_mq_sysfs_unregister(q);
+
+	/*
+	 * redo blk_mq_init_cpu_queues and blk_mq_init_hw_queues. FIXME: maybe
+	 * we should change hctx numa_node according to the new topology (this
+	 * involves freeing and re-allocating memory, worth doing?)
+	 */
+	blk_mq_map_swqueue(q);
+
+	blk_mq_sysfs_register(q);
+	blk_mq_debugfs_register_hctxs(q);
+}
+
+static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
+{
+	int i;
+
+	for (i = 0; i < set->nr_hw_queues; i++)
+		if (!__blk_mq_alloc_rq_map(set, i))
+			goto out_unwind;
+
+	return 0;
+
+out_unwind:
+	while (--i >= 0)
+		blk_mq_free_rq_map(set->tags[i]);
+
+	return -ENOMEM;
+}
+
+/*
+ * Allocate the request maps associated with this tag_set. Note that this
+ * may reduce the depth asked for, if memory is tight. set->queue_depth
+ * will be updated to reflect the allocated depth.
+ */
+static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
+{
+	unsigned int depth;
+	int err;
+
+	depth = set->queue_depth;
+	do {
+		err = __blk_mq_alloc_rq_maps(set);
+		if (!err)
+			break;
+
+		set->queue_depth >>= 1;
+		if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) {
+			err = -ENOMEM;
+			break;
+		}
+	} while (set->queue_depth);
+
+	if (!set->queue_depth || err) {
+		pr_err("blk-mq: failed to allocate request map\n");
+		return -ENOMEM;
+	}
+
+	if (depth != set->queue_depth)
+		pr_info("blk-mq: reduced tag depth (%u -> %u)\n",
+						depth, set->queue_depth);
+
+	return 0;
+}
+
+static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
+{
+	if (set->ops->map_queues) {
+		/*
+		 * transport .map_queues is usually done in the following
+		 * way:
+		 *
+		 * for (queue = 0; queue < set->nr_hw_queues; queue++) {
+		 * 	mask = get_cpu_mask(queue)
+		 * 	for_each_cpu(cpu, mask)
+		 * 		set->mq_map[cpu] = queue;
+		 * }
+		 *
+		 * When we need to remap, the table has to be cleared for
+		 * killing stale mapping since one CPU may not be mapped
+		 * to any hw queue.
+		 */
+		blk_mq_clear_mq_map(set);
+
+		return set->ops->map_queues(set);
+	} else
+		return blk_mq_map_queues(set);
+}
+
+/*
+ * Alloc a tag set to be associated with one or more request queues.
+ * May fail with EINVAL for various error conditions. May adjust the
+ * requested depth down, if it's too large. In that case, the set
+ * value will be stored in set->queue_depth.
+ */
+int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
+{
+	int ret;
+
+	BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS);
+
+	if (!set->nr_hw_queues)
+		return -EINVAL;
+	if (!set->queue_depth)
+		return -EINVAL;
+	if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN)
+		return -EINVAL;
+
+	if (!set->ops->queue_rq)
+		return -EINVAL;
+
+	if (!set->ops->get_budget ^ !set->ops->put_budget)
+		return -EINVAL;
+
+	if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
+		pr_info("blk-mq: reduced tag depth to %u\n",
+			BLK_MQ_MAX_DEPTH);
+		set->queue_depth = BLK_MQ_MAX_DEPTH;
+	}
+
+	/*
+	 * If a crashdump is active, then we are potentially in a very
+	 * memory constrained environment. Limit us to 1 queue and
+	 * 64 tags to prevent using too much memory.
+	 */
+	if (is_kdump_kernel()) {
+		set->nr_hw_queues = 1;
+		set->queue_depth = min(64U, set->queue_depth);
+	}
+	/*
+	 * There is no use for more h/w queues than cpus.
+	 */
+	if (set->nr_hw_queues > nr_cpu_ids)
+		set->nr_hw_queues = nr_cpu_ids;
+
+	set->tags = kcalloc_node(nr_cpu_ids, sizeof(struct blk_mq_tags *),
+				 GFP_KERNEL, set->numa_node);
+	if (!set->tags)
+		return -ENOMEM;
+
+	ret = -ENOMEM;
+	set->mq_map = kcalloc_node(nr_cpu_ids, sizeof(*set->mq_map),
+				   GFP_KERNEL, set->numa_node);
+	if (!set->mq_map)
+		goto out_free_tags;
+
+	ret = blk_mq_update_queue_map(set);
+	if (ret)
+		goto out_free_mq_map;
+
+	ret = blk_mq_alloc_rq_maps(set);
+	if (ret)
+		goto out_free_mq_map;
+
+	mutex_init(&set->tag_list_lock);
+	INIT_LIST_HEAD(&set->tag_list);
+
+	return 0;
+
+out_free_mq_map:
+	kfree(set->mq_map);
+	set->mq_map = NULL;
+out_free_tags:
+	kfree(set->tags);
+	set->tags = NULL;
+	return ret;
+}
+EXPORT_SYMBOL(blk_mq_alloc_tag_set);
+
+void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
+{
+	int i;
+
+	for (i = 0; i < nr_cpu_ids; i++)
+		blk_mq_free_map_and_requests(set, i);
+
+	kfree(set->mq_map);
+	set->mq_map = NULL;
+
+	kfree(set->tags);
+	set->tags = NULL;
+}
+EXPORT_SYMBOL(blk_mq_free_tag_set);
+
+int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
+{
+	struct blk_mq_tag_set *set = q->tag_set;
+	struct blk_mq_hw_ctx *hctx;
+	int i, ret;
+
+	if (!set)
+		return -EINVAL;
+
+	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue(q);
+
+	ret = 0;
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (!hctx->tags)
+			continue;
+		/*
+		 * If we're using an MQ scheduler, just update the scheduler
+		 * queue depth. This is similar to what the old code would do.
+		 */
+		if (!hctx->sched_tags) {
+			ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr,
+							false);
+		} else {
+			ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags,
+							nr, true);
+		}
+		if (ret)
+			break;
+	}
+
+	if (!ret)
+		q->nr_requests = nr;
+
+	blk_mq_unquiesce_queue(q);
+	blk_mq_unfreeze_queue(q);
+
+	return ret;
+}
+
+/*
+ * request_queue and elevator_type pair.
+ * It is just used by __blk_mq_update_nr_hw_queues to cache
+ * the elevator_type associated with a request_queue.
+ */
+struct blk_mq_qe_pair {
+	struct list_head node;
+	struct request_queue *q;
+	struct elevator_type *type;
+};
+
+/*
+ * Cache the elevator_type in qe pair list and switch the
+ * io scheduler to 'none'
+ */
+static bool blk_mq_elv_switch_none(struct list_head *head,
+		struct request_queue *q)
+{
+	struct blk_mq_qe_pair *qe;
+
+	if (!q->elevator)
+		return true;
+
+	qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY);
+	if (!qe)
+		return false;
+
+	INIT_LIST_HEAD(&qe->node);
+	qe->q = q;
+	qe->type = q->elevator->type;
+	list_add(&qe->node, head);
+
+	mutex_lock(&q->sysfs_lock);
+	/*
+	 * After elevator_switch_mq, the previous elevator_queue will be
+	 * released by elevator_release. The reference of the io scheduler
+	 * module get by elevator_get will also be put. So we need to get
+	 * a reference of the io scheduler module here to prevent it to be
+	 * removed.
+	 */
+	__module_get(qe->type->elevator_owner);
+	elevator_switch_mq(q, NULL);
+	mutex_unlock(&q->sysfs_lock);
+
+	return true;
+}
+
+static void blk_mq_elv_switch_back(struct list_head *head,
+		struct request_queue *q)
+{
+	struct blk_mq_qe_pair *qe;
+	struct elevator_type *t = NULL;
+
+	list_for_each_entry(qe, head, node)
+		if (qe->q == q) {
+			t = qe->type;
+			break;
+		}
+
+	if (!t)
+		return;
+
+	list_del(&qe->node);
+	kfree(qe);
+
+	mutex_lock(&q->sysfs_lock);
+	elevator_switch_mq(q, t);
+	mutex_unlock(&q->sysfs_lock);
+}
+
+static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
+							int nr_hw_queues)
+{
+	struct request_queue *q;
+	LIST_HEAD(head);
+
+	lockdep_assert_held(&set->tag_list_lock);
+
+	if (nr_hw_queues > nr_cpu_ids)
+		nr_hw_queues = nr_cpu_ids;
+	if (nr_hw_queues < 1 || nr_hw_queues == set->nr_hw_queues)
+		return;
+
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		blk_mq_freeze_queue(q);
+	/*
+	 * Sync with blk_mq_queue_tag_busy_iter.
+	 */
+	synchronize_rcu();
+	/*
+	 * Switch IO scheduler to 'none', cleaning up the data associated
+	 * with the previous scheduler. We will switch back once we are done
+	 * updating the new sw to hw queue mappings.
+	 */
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		if (!blk_mq_elv_switch_none(&head, q))
+			goto switch_back;
+
+	set->nr_hw_queues = nr_hw_queues;
+	blk_mq_update_queue_map(set);
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		blk_mq_realloc_hw_ctxs(set, q);
+		blk_mq_queue_reinit(q);
+	}
+
+switch_back:
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		blk_mq_elv_switch_back(&head, q);
+
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		blk_mq_unfreeze_queue(q);
+}
+
+void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
+{
+	mutex_lock(&set->tag_list_lock);
+	__blk_mq_update_nr_hw_queues(set, nr_hw_queues);
+	mutex_unlock(&set->tag_list_lock);
+}
+EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
+
+/* Enable polling stats and return whether they were already enabled. */
+static bool blk_poll_stats_enable(struct request_queue *q)
+{
+	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) ||
+	    blk_queue_flag_test_and_set(QUEUE_FLAG_POLL_STATS, q))
+		return true;
+	blk_stat_add_callback(q, q->poll_cb);
+	return false;
+}
+
+static void blk_mq_poll_stats_start(struct request_queue *q)
+{
+	/*
+	 * We don't arm the callback if polling stats are not enabled or the
+	 * callback is already active.
+	 */
+	if (!test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) ||
+	    blk_stat_is_active(q->poll_cb))
+		return;
+
+	blk_stat_activate_msecs(q->poll_cb, 100);
+}
+
+static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb)
+{
+	struct request_queue *q = cb->data;
+	int bucket;
+
+	for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS; bucket++) {
+		if (cb->stat[bucket].nr_samples)
+			q->poll_stat[bucket] = cb->stat[bucket];
+	}
+}
+
+static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
+				       struct blk_mq_hw_ctx *hctx,
+				       struct request *rq)
+{
+	unsigned long ret = 0;
+	int bucket;
+
+	/*
+	 * If stats collection isn't on, don't sleep but turn it on for
+	 * future users
+	 */
+	if (!blk_poll_stats_enable(q))
+		return 0;
+
+	/*
+	 * As an optimistic guess, use half of the mean service time
+	 * for this type of request. We can (and should) make this smarter.
+	 * For instance, if the completion latencies are tight, we can
+	 * get closer than just half the mean. This is especially
+	 * important on devices where the completion latencies are longer
+	 * than ~10 usec. We do use the stats for the relevant IO size
+	 * if available which does lead to better estimates.
+	 */
+	bucket = blk_mq_poll_stats_bkt(rq);
+	if (bucket < 0)
+		return ret;
+
+	if (q->poll_stat[bucket].nr_samples)
+		ret = (q->poll_stat[bucket].mean + 1) / 2;
+
+	return ret;
+}
+
+static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
+				     struct blk_mq_hw_ctx *hctx,
+				     struct request *rq)
+{
+	struct hrtimer_sleeper hs;
+	enum hrtimer_mode mode;
+	unsigned int nsecs;
+	ktime_t kt;
+
+	if (rq->rq_flags & RQF_MQ_POLL_SLEPT)
+		return false;
+
+	/*
+	 * poll_nsec can be:
+	 *
+	 * -1:	don't ever hybrid sleep
+	 *  0:	use half of prev avg
+	 * >0:	use this specific value
+	 */
+	if (q->poll_nsec == -1)
+		return false;
+	else if (q->poll_nsec > 0)
+		nsecs = q->poll_nsec;
+	else
+		nsecs = blk_mq_poll_nsecs(q, hctx, rq);
+
+	if (!nsecs)
+		return false;
+
+	rq->rq_flags |= RQF_MQ_POLL_SLEPT;
+
+	/*
+	 * This will be replaced with the stats tracking code, using
+	 * 'avg_completion_time / 2' as the pre-sleep target.
+	 */
+	kt = nsecs;
+
+	mode = HRTIMER_MODE_REL;
+	hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode);
+	hrtimer_set_expires(&hs.timer, kt);
+
+	hrtimer_init_sleeper(&hs, current);
+	do {
+		if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE)
+			break;
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		hrtimer_start_expires(&hs.timer, mode);
+		if (hs.task)
+			io_schedule();
+		hrtimer_cancel(&hs.timer);
+		mode = HRTIMER_MODE_ABS;
+	} while (hs.task && !signal_pending(current));
+
+	__set_current_state(TASK_RUNNING);
+	destroy_hrtimer_on_stack(&hs.timer);
+	return true;
+}
+
+static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq)
+{
+	struct request_queue *q = hctx->queue;
+	long state;
+
+	/*
+	 * If we sleep, have the caller restart the poll loop to reset
+	 * the state. Like for the other success return cases, the
+	 * caller is responsible for checking if the IO completed. If
+	 * the IO isn't complete, we'll get called again and will go
+	 * straight to the busy poll loop.
+	 */
+	if (blk_mq_poll_hybrid_sleep(q, hctx, rq))
+		return true;
+
+	hctx->poll_considered++;
+
+	state = current->state;
+	while (!need_resched()) {
+		int ret;
+
+		hctx->poll_invoked++;
+
+		ret = q->mq_ops->poll(hctx, rq->tag);
+		if (ret > 0) {
+			hctx->poll_success++;
+			set_current_state(TASK_RUNNING);
+			return true;
+		}
+
+		if (signal_pending_state(state, current))
+			set_current_state(TASK_RUNNING);
+
+		if (current->state == TASK_RUNNING)
+			return true;
+		if (ret < 0)
+			break;
+		cpu_relax();
+	}
+
+	__set_current_state(TASK_RUNNING);
+	return false;
+}
+
+static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct request *rq;
+
+	if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+		return false;
+
+	hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
+	if (!blk_qc_t_is_internal(cookie))
+		rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
+	else {
+		rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie));
+		/*
+		 * With scheduling, if the request has completed, we'll
+		 * get a NULL return here, as we clear the sched tag when
+		 * that happens. The request still remains valid, like always,
+		 * so we should be safe with just the NULL check.
+		 */
+		if (!rq)
+			return false;
+	}
+
+	return __blk_mq_poll(hctx, rq);
+}
+
+static int __init blk_mq_init(void)
+{
+	cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
+				blk_mq_hctx_notify_dead);
+	return 0;
+}
+subsys_initcall(blk_mq_init);

src/drivers/ata/ahci_elphel.c

@@ -34,7 +34,6 @@
 #include "ahci_elphel.h"
 #include "../elphel/exif393.h"
 #include "../elphel/jpeghead.h"
-
 #define DRV_NAME "elphel-ahci"
 /*
  * FPGA bitstream control address and bit mask. These are used to check whether
@@ -75,8 +74,8 @@ static int move_head(struct elphel_ahci_priv *dpriv);
 static size_t get_prev_slot(const struct elphel_ahci_priv *dpriv);
 static int is_cmdq_empty(const struct elphel_ahci_priv *dpriv);
 void process_queue(unsigned long data);
-static void set_flag(struct elphel_ahci_priv *drpiv, uint32_t flag);
-static void reset_flag(struct elphel_ahci_priv *dpriv, uint32_t flag);
+static void set_flag(struct elphel_ahci_priv *drpiv, u32 flag);
+static void reset_flag(struct elphel_ahci_priv *dpriv, u32 flag);
 static inline void reset_chunks(struct fvec *vects, int all);
 /* debug functions */
 static int check_chunks(struct fvec *vects);
@@ -235,7 +234,7 @@ static irqreturn_t elphel_irq_handler(int irq, void * dev_instance)
 	struct ata_port *port = host->ports[DEFAULT_PORT_NUM];
 	void __iomem *port_mmio = ahci_port_base(port);
 	struct elphel_ahci_priv *dpriv = hpriv->plat_data;
-	uint32_t irq_stat, host_irq_stat, serror;
+	u32 irq_stat, host_irq_stat, serror;
 
 	if (dpriv->flags & IRQ_SIMPLE) {
 
@@ -529,9 +528,14 @@ static void elphel_qc_prep(struct ata_queued_cmd *qc)
 
 	dev_dbg(ap->dev, "cmd = 0x%x, qc->tag = %u, ap->qc_active = %u, link->sactive = %u, link->active_tag = %u\n",
 			qc->tf.command, qc->tag, ap->qc_active, ap->link.sactive, ap->link.active_tag);
+	dev_dbg(ap->dev, "cmd = 0x%x, lba = %u, nob_lba = %u, nsect = %u, nob_nsect = %u\n",
+			qc->tf.command, qc->tf.lbal + (qc->tf.lbam << 8)+ (qc->tf.lbah << 16),
+			qc->tf.hob_lbal + (qc->tf.hob_lbam << 8)+ (qc->tf.hob_lbah << 16),
+			qc->tf.nsect, qc->tf.hob_nsect);
 
 	/* There is only one slot in controller thus we need to change tag*/
 	qc->tag = 0;
+//	dump_stack();// not controlled by debugfs
 
 	/*
 	 * Fill in command table information.  First, the header,
@@ -583,10 +587,22 @@ static void elphel_qc_prep(struct ata_queued_cmd *qc)
 
 	struct elphel_ahci_priv *dpriv = dev_get_dpriv(ap->dev);
 	set_dscope_tstamp(dpriv, TSTMP_CMD_SYS);
+
+	dev_dbg(ap->dev, "cmd = 0x%x, lba = %lu, nsect = %u\n",
+			qc->tf.command,
+			((long)(qc->tf.lbal + (qc->tf.lbam << 8)+ (qc->tf.lbah << 16))) +
+			(((long) (qc->tf.hob_lbal + (qc->tf.hob_lbam << 8)+ (qc->tf.hob_lbah << 16))) << 24),
+			qc->tf.nsect + (qc->tf.hob_nsect << 8));
+	//same
+	dev_dbg(ap->dev, "cmd = 0x%x, lba = %u, nob_lba = %u, nsect = %u, nob_nsect = %u\n",
+			((char *) (pp->cmd_tbl))[2],  ((char *) (pp->cmd_tbl))[4] + (((char *) (pp->cmd_tbl))[5] << 8)+ (((char *)(pp->cmd_tbl))[6] << 16),
+			((char *) (pp->cmd_tbl))[8] + (((char *)(pp->cmd_tbl))[9] << 8)+ (((char *)(pp->cmd_tbl))[10] << 16),
+			((char *) (pp->cmd_tbl))[12], ((char *) (pp->cmd_tbl))[13]);
+
 }
 
 /** Set flag @e flag in driver private structure. This function uses spin lock to access the flags variable. */
-static void set_flag(struct elphel_ahci_priv *dpriv, uint32_t flag)
+static void set_flag(struct elphel_ahci_priv *dpriv, u32 flag)
 {
 	unsigned long irq_flags;
 
@@ -596,7 +612,7 @@ static void set_flag(struct elphel_ahci_priv *dpriv, uint32_t flag)
 }
 
 /** Reset flag @e flag in driver private structure. This function uses spin lock to access the flags variable. */
-static void reset_flag(struct elphel_ahci_priv *dpriv, uint32_t flag)
+static void reset_flag(struct elphel_ahci_priv *dpriv, u32 flag)
 {
 	unsigned long irq_flags;
 
@@ -1564,7 +1580,7 @@ static void elphel_cmd_issue(struct ata_port *ap,///< device port for which the
 		                                         ///< ATA_CMD_WRITE or ATA_CMD_WRITE_EXT, other commands are not tested
 		                                         ///< @return None
 {
-	uint32_t opts;
+	u32 opts;
 	uint8_t *cmd_tbl;
 	unsigned int slot_num = 0;
 	struct ahci_port_priv *pp = ap->private_data;
@@ -1964,7 +1980,7 @@ static void dump_current_state(struct elphel_ahci_priv *dpriv)
 	struct ata_port *ap = host->ports[DEFAULT_PORT_NUM];
 	struct ata_link *link = &ap->link;
 	struct ahci_port_priv *pp = ap->private_data;
-	uint32_t *datascope_ptr;
+	u32 *datascope_ptr;
 
 	dev_dbg(dpriv->dev, "===== HBA memory dump ======\n");
 	dump_iomem(dpriv->dev, hpriv->mmio, 100, dpriv->base_addr);
@@ -1994,7 +2010,7 @@ static void set_dscope_tstamp(struct elphel_ahci_priv *dpriv, unsigned int cmd)
         struct ahci_host_priv *hpriv;
         struct ata_port *ap;
         void __iomem *port_mmio;
-        uint32_t data = 0;
+        u32 data = 0;
 
         host = dev_get_drvdata(dpriv->dev);
         hpriv = host->private_data;

src/drivers/ata/ahci_elphel.h

@@ -90,13 +90,13 @@ struct datascope {
     void __iomem *timestamp_reg;                 ///< register in vendor specific address range (PxVS) where timestamp can be written
     unsigned int cmd_cntr;                       ///< command counter, its value can be found in timestamp (2 bits only)
     unsigned int enable;                         ///< enable/disable timestamps
-    uint32_t reg_stat[REG_NUM];                  ///< buffer for registers' status, filled in in IRQ
+    u32 reg_stat[REG_NUM];                  ///< buffer for registers' status, filled in in IRQ
 };
 
 /** Data for error handler */
 struct error_handler {
-	uint32_t s_error;                            ///< the content of PxSERR register
-	uint32_t irq_stat;                           ///< the content of PxIS register
+	u32 s_error;                            ///< the content of PxSERR register
+	u32 irq_stat;                           ///< the content of PxIS register
 	wait_queue_head_t wait;                      ///< wait queue for delayed interrupts
 };
 

src/drivers/elphel/x393_videomem.c

@@ -648,7 +648,7 @@ int control_compressor_memory (int num_sensor,       ///< sensor port number (0.
    return 0;
 }
 
-/** Return number of rfames in videobuffer for the sensor port minus 1 (0 means single frame buffer) */
+/** Return number of frames in videobuffer for the sensor port minus 1 (0 means single frame buffer) */
 int frames_in_buffer_minus_one(int num_sensor) ///< sensor port number (0..3)
                                                ///< @return number of frames in buffer - 1 (<0 for disabled channels ?)
 {

src/drivers/scsi/scsi_lib.c

+/*
+ * Copyright (C) 1999 Eric Youngdale
+ * Copyright (C) 2014 Christoph Hellwig
+ *
+ *  SCSI queueing library.
+ *      Initial versions: Eric Youngdale (eric@andante.org).
+ *                        Based upon conversations with large numbers
+ *                        of people at Linux Expo.
+ */
+
+#include <linux/bio.h>
+#include <linux/bitops.h>
+#include <linux/blkdev.h>
+#include <linux/completion.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/hardirq.h>
+#include <linux/scatterlist.h>
+#include <linux/blk-mq.h>
+#include <linux/ratelimit.h>
+#include <asm/unaligned.h>
+
+#include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_dbg.h>
+#include <scsi/scsi_device.h>
+#include <scsi/scsi_driver.h>
+#include <scsi/scsi_eh.h>
+#include <scsi/scsi_host.h>
+#include <scsi/scsi_transport.h> /* __scsi_init_queue() */
+#include <scsi/scsi_dh.h>
+
+#include <trace/events/scsi.h>
+
+#include "scsi_debugfs.h"
+#include "scsi_priv.h"
+#include "scsi_logging.h"
+
+static struct kmem_cache *scsi_sdb_cache;
+static struct kmem_cache *scsi_sense_cache;
+static struct kmem_cache *scsi_sense_isadma_cache;
+static DEFINE_MUTEX(scsi_sense_cache_mutex);
+
+static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd);
+
+static inline struct kmem_cache *
+scsi_select_sense_cache(bool unchecked_isa_dma)
+{
+	return unchecked_isa_dma ? scsi_sense_isadma_cache : scsi_sense_cache;
+}
+
+static void scsi_free_sense_buffer(bool unchecked_isa_dma,
+				   unsigned char *sense_buffer)
+{
+	kmem_cache_free(scsi_select_sense_cache(unchecked_isa_dma),
+			sense_buffer);
+}
+
+static unsigned char *scsi_alloc_sense_buffer(bool unchecked_isa_dma,
+	gfp_t gfp_mask, int numa_node)
+{
+	return kmem_cache_alloc_node(scsi_select_sense_cache(unchecked_isa_dma),
+				     gfp_mask, numa_node);
+}
+
+int scsi_init_sense_cache(struct Scsi_Host *shost)
+{
+	struct kmem_cache *cache;
+	int ret = 0;
+
+	cache = scsi_select_sense_cache(shost->unchecked_isa_dma);
+	if (cache)
+		return 0;
+
+	mutex_lock(&scsi_sense_cache_mutex);
+	if (shost->unchecked_isa_dma) {
+		scsi_sense_isadma_cache =
+			kmem_cache_create("scsi_sense_cache(DMA)",
+				SCSI_SENSE_BUFFERSIZE, 0,
+				SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA, NULL);
+		if (!scsi_sense_isadma_cache)
+			ret = -ENOMEM;
+	} else {
+		scsi_sense_cache =
+			kmem_cache_create_usercopy("scsi_sense_cache",
+				SCSI_SENSE_BUFFERSIZE, 0, SLAB_HWCACHE_ALIGN,
+				0, SCSI_SENSE_BUFFERSIZE, NULL);
+		if (!scsi_sense_cache)
+			ret = -ENOMEM;
+	}
+
+	mutex_unlock(&scsi_sense_cache_mutex);
+	return ret;
+}
+
+/*
+ * When to reinvoke queueing after a resource shortage. It's 3 msecs to
+ * not change behaviour from the previous unplug mechanism, experimentation
+ * may prove this needs changing.
+ */
+#define SCSI_QUEUE_DELAY	3
+
+static void
+scsi_set_blocked(struct scsi_cmnd *cmd, int reason)
+{
+	struct Scsi_Host *host = cmd->device->host;
+	struct scsi_device *device = cmd->device;
+	struct scsi_target *starget = scsi_target(device);
+
+	/*
+	 * Set the appropriate busy bit for the device/host.
+	 *
+	 * If the host/device isn't busy, assume that something actually
+	 * completed, and that we should be able to queue a command now.
+	 *
+	 * Note that the prior mid-layer assumption that any host could
+	 * always queue at least one command is now broken.  The mid-layer
+	 * will implement a user specifiable stall (see
+	 * scsi_host.max_host_blocked and scsi_device.max_device_blocked)
+	 * if a command is requeued with no other commands outstanding
+	 * either for the device or for the host.
+	 */
+	switch (reason) {
+	case SCSI_MLQUEUE_HOST_BUSY:
+		atomic_set(&host->host_blocked, host->max_host_blocked);
+		break;
+	case SCSI_MLQUEUE_DEVICE_BUSY:
+	case SCSI_MLQUEUE_EH_RETRY:
+		atomic_set(&device->device_blocked,
+			   device->max_device_blocked);
+		break;
+	case SCSI_MLQUEUE_TARGET_BUSY:
+		atomic_set(&starget->target_blocked,
+			   starget->max_target_blocked);
+		break;
+	}
+}
+
+static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd)
+{
+	struct scsi_device *sdev = cmd->device;
+
+	if (cmd->request->rq_flags & RQF_DONTPREP) {
+		cmd->request->rq_flags &= ~RQF_DONTPREP;
+		scsi_mq_uninit_cmd(cmd);
+	} else {
+		WARN_ON_ONCE(true);
+	}
+	blk_mq_requeue_request(cmd->request, true);
+	put_device(&sdev->sdev_gendev);
+}
+
+/**
+ * __scsi_queue_insert - private queue insertion
+ * @cmd: The SCSI command being requeued
+ * @reason:  The reason for the requeue
+ * @unbusy: Whether the queue should be unbusied
+ *
+ * This is a private queue insertion.  The public interface
+ * scsi_queue_insert() always assumes the queue should be unbusied
+ * because it's always called before the completion.  This function is
+ * for a requeue after completion, which should only occur in this
+ * file.
+ */
+static void __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, bool unbusy)
+{
+	struct scsi_device *device = cmd->device;
+	struct request_queue *q = device->request_queue;
+	unsigned long flags;
+
+	SCSI_LOG_MLQUEUE(1, scmd_printk(KERN_INFO, cmd,
+		"Inserting command %p into mlqueue\n", cmd));
+
+	scsi_set_blocked(cmd, reason);
+
+	/*
+	 * Decrement the counters, since these commands are no longer
+	 * active on the host/device.
+	 */
+	if (unbusy)
+		scsi_device_unbusy(device);
+
+	/*
+	 * Requeue this command.  It will go before all other commands
+	 * that are already in the queue. Schedule requeue work under
+	 * lock such that the kblockd_schedule_work() call happens
+	 * before blk_cleanup_queue() finishes.
+	 */
+	cmd->result = 0;
+	if (q->mq_ops) {
+		/*
+		 * Before a SCSI command is dispatched,
+		 * get_device(&sdev->sdev_gendev) is called and the host,
+		 * target and device busy counters are increased. Since
+		 * requeuing a request causes these actions to be repeated and
+		 * since scsi_device_unbusy() has already been called,
+		 * put_device(&device->sdev_gendev) must still be called. Call
+		 * put_device() after blk_mq_requeue_request() to avoid that
+		 * removal of the SCSI device can start before requeueing has
+		 * happened.
+		 */
+		blk_mq_requeue_request(cmd->request, true);
+		put_device(&device->sdev_gendev);
+		return;
+	}
+	spin_lock_irqsave(q->queue_lock, flags);
+	blk_requeue_request(q, cmd->request);
+	kblockd_schedule_work(&device->requeue_work);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+/*
+ * Function:    scsi_queue_insert()
+ *
+ * Purpose:     Insert a command in the midlevel queue.
+ *
+ * Arguments:   cmd    - command that we are adding to queue.
+ *              reason - why we are inserting command to queue.
+ *
+ * Lock status: Assumed that lock is not held upon entry.
+ *
+ * Returns:     Nothing.
+ *
+ * Notes:       We do this for one of two cases.  Either the host is busy
+ *              and it cannot accept any more commands for the time being,
+ *              or the device returned QUEUE_FULL and can accept no more
+ *              commands.
+ * Notes:       This could be called either from an interrupt context or a
+ *              normal process context.
+ */
+void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
+{
+	__scsi_queue_insert(cmd, reason, true);
+}
+
+
+/**
+ * __scsi_execute - insert request and wait for the result
+ * @sdev:	scsi device
+ * @cmd:	scsi command
+ * @data_direction: data direction
+ * @buffer:	data buffer
+ * @bufflen:	len of buffer
+ * @sense:	optional sense buffer
+ * @sshdr:	optional decoded sense header
+ * @timeout:	request timeout in seconds
+ * @retries:	number of times to retry request
+ * @flags:	flags for ->cmd_flags
+ * @rq_flags:	flags for ->rq_flags
+ * @resid:	optional residual length
+ *
+ * Returns the scsi_cmnd result field if a command was executed, or a negative
+ * Linux error code if we didn't get that far.
+ */
+int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+		 int data_direction, void *buffer, unsigned bufflen,
+		 unsigned char *sense, struct scsi_sense_hdr *sshdr,
+		 int timeout, int retries, u64 flags, req_flags_t rq_flags,
+		 int *resid)
+{
+	struct request *req;
+	struct scsi_request *rq;
+	int ret = DRIVER_ERROR << 24;
+
+	req = blk_get_request(sdev->request_queue,
+			data_direction == DMA_TO_DEVICE ?
+			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, BLK_MQ_REQ_PREEMPT);
+	if (IS_ERR(req))
+		return ret;
+	rq = scsi_req(req);
+
+	if (bufflen &&	blk_rq_map_kern(sdev->request_queue, req,
+					buffer, bufflen, GFP_NOIO))
+		goto out;
+
+	rq->cmd_len = COMMAND_SIZE(cmd[0]);
+	memcpy(rq->cmd, cmd, rq->cmd_len);
+	rq->retries = retries;
+	req->timeout = timeout;
+	req->cmd_flags |= flags;
+	req->rq_flags |= rq_flags | RQF_QUIET;
+
+	/*
+	 * head injection *required* here otherwise quiesce won't work
+	 */
+	blk_execute_rq(req->q, NULL, req, 1);
+
+	/*
+	 * Some devices (USB mass-storage in particular) may transfer
+	 * garbage data together with a residue indicating that the data
+	 * is invalid.  Prevent the garbage from being misinterpreted
+	 * and prevent security leaks by zeroing out the excess data.
+	 */
+	if (unlikely(rq->resid_len > 0 && rq->resid_len <= bufflen))
+		memset(buffer + (bufflen - rq->resid_len), 0, rq->resid_len);
+
+	if (resid)
+		*resid = rq->resid_len;
+	if (sense && rq->sense_len)
+		memcpy(sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
+	if (sshdr)
+		scsi_normalize_sense(rq->sense, rq->sense_len, sshdr);
+	ret = rq->result;
+ out:
+	blk_put_request(req);
+
+	return ret;
+}
+EXPORT_SYMBOL(__scsi_execute);
+
+/*
+ * Function:    scsi_init_cmd_errh()
+ *
+ * Purpose:     Initialize cmd fields related to error handling.
+ *
+ * Arguments:   cmd	- command that is ready to be queued.
+ *
+ * Notes:       This function has the job of initializing a number of
+ *              fields related to error handling.   Typically this will
+ *              be called once for each command, as required.
+ */
+static void scsi_init_cmd_errh(struct scsi_cmnd *cmd)
+{
+	cmd->serial_number = 0;
+	scsi_set_resid(cmd, 0);
+	memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
+	if (cmd->cmd_len == 0)
+		cmd->cmd_len = scsi_command_size(cmd->cmnd);
+}
+
+/*
+ * Decrement the host_busy counter and wake up the error handler if necessary.
+ * Avoid as follows that the error handler is not woken up if shost->host_busy
+ * == shost->host_failed: use call_rcu() in scsi_eh_scmd_add() in combination
+ * with an RCU read lock in this function to ensure that this function in its
+ * entirety either finishes before scsi_eh_scmd_add() increases the
+ * host_failed counter or that it notices the shost state change made by
+ * scsi_eh_scmd_add().
+ */
+static void scsi_dec_host_busy(struct Scsi_Host *shost)
+{
+	unsigned long flags;
+
+	rcu_read_lock();
+	atomic_dec(&shost->host_busy);
+	if (unlikely(scsi_host_in_recovery(shost))) {
+		spin_lock_irqsave(shost->host_lock, flags);
+		if (shost->host_failed || shost->host_eh_scheduled)
+			scsi_eh_wakeup(shost);
+		spin_unlock_irqrestore(shost->host_lock, flags);
+	}
+	rcu_read_unlock();
+}
+
+void scsi_device_unbusy(struct scsi_device *sdev)
+{
+	struct Scsi_Host *shost = sdev->host;
+	struct scsi_target *starget = scsi_target(sdev);
+
+	scsi_dec_host_busy(shost);
+
+	if (starget->can_queue > 0)
+		atomic_dec(&starget->target_busy);
+
+	atomic_dec(&sdev->device_busy);
+}
+
+static void scsi_kick_queue(struct request_queue *q)
+{
+	if (q->mq_ops)
+		blk_mq_run_hw_queues(q, false);
+	else
+		blk_run_queue(q);
+}
+
+/*
+ * Called for single_lun devices on IO completion. Clear starget_sdev_user,
+ * and call blk_run_queue for all the scsi_devices on the target -
+ * including current_sdev first.
+ *
+ * Called with *no* scsi locks held.
+ */
+static void scsi_single_lun_run(struct scsi_device *current_sdev)
+{
+	struct Scsi_Host *shost = current_sdev->host;
+	struct scsi_device *sdev, *tmp;
+	struct scsi_target *starget = scsi_target(current_sdev);
+	unsigned long flags;
+
+	spin_lock_irqsave(shost->host_lock, flags);
+	starget->starget_sdev_user = NULL;
+	spin_unlock_irqrestore(shost->host_lock, flags);
+
+	/*
+	 * Call blk_run_queue for all LUNs on the target, starting with
+	 * current_sdev. We race with others (to set starget_sdev_user),
+	 * but in most cases, we will be first. Ideally, each LU on the
+	 * target would get some limited time or requests on the target.
+	 */
+	scsi_kick_queue(current_sdev->request_queue);
+
+	spin_lock_irqsave(shost->host_lock, flags);
+	if (starget->starget_sdev_user)
+		goto out;
+	list_for_each_entry_safe(sdev, tmp, &starget->devices,
+			same_target_siblings) {
+		if (sdev == current_sdev)
+			continue;
+		if (scsi_device_get(sdev))
+			continue;
+
+		spin_unlock_irqrestore(shost->host_lock, flags);
+		scsi_kick_queue(sdev->request_queue);
+		spin_lock_irqsave(shost->host_lock, flags);
+	
+		scsi_device_put(sdev);
+	}
+ out:
+	spin_unlock_irqrestore(shost->host_lock, flags);
+}
+
+static inline bool scsi_device_is_busy(struct scsi_device *sdev)
+{
+	if (atomic_read(&sdev->device_busy) >= sdev->queue_depth)
+		return true;
+	if (atomic_read(&sdev->device_blocked) > 0)
+		return true;
+	return false;
+}
+
+static inline bool scsi_target_is_busy(struct scsi_target *starget)
+{
+	if (starget->can_queue > 0) {
+		if (atomic_read(&starget->target_busy) >= starget->can_queue)
+			return true;
+		if (atomic_read(&starget->target_blocked) > 0)
+			return true;
+	}
+	return false;
+}
+
+static inline bool scsi_host_is_busy(struct Scsi_Host *shost)
+{
+	if (shost->can_queue > 0 &&
+	    atomic_read(&shost->host_busy) >= shost->can_queue)
+		return true;
+	if (atomic_read(&shost->host_blocked) > 0)
+		return true;
+	if (shost->host_self_blocked)
+		return true;
+	return false;
+}
+
+static void scsi_starved_list_run(struct Scsi_Host *shost)
+{
+	LIST_HEAD(starved_list);
+	struct scsi_device *sdev;
+	unsigned long flags;
+
+	spin_lock_irqsave(shost->host_lock, flags);
+	list_splice_init(&shost->starved_list, &starved_list);
+
+	while (!list_empty(&starved_list)) {
+		struct request_queue *slq;
+
+		/*
+		 * As long as shost is accepting commands and we have
+		 * starved queues, call blk_run_queue. scsi_request_fn
+		 * drops the queue_lock and can add us back to the
+		 * starved_list.
+		 *
+		 * host_lock protects the starved_list and starved_entry.
+		 * scsi_request_fn must get the host_lock before checking
+		 * or modifying starved_list or starved_entry.
+		 */
+		if (scsi_host_is_busy(shost))
+			break;
+
+		sdev = list_entry(starved_list.next,
+				  struct scsi_device, starved_entry);
+		list_del_init(&sdev->starved_entry);
+		if (scsi_target_is_busy(scsi_target(sdev))) {
+			list_move_tail(&sdev->starved_entry,
+				       &shost->starved_list);
+			continue;
+		}
+
+		/*
+		 * Once we drop the host lock, a racing scsi_remove_device()
+		 * call may remove the sdev from the starved list and destroy
+		 * it and the queue.  Mitigate by taking a reference to the
+		 * queue and never touching the sdev again after we drop the
+		 * host lock.  Note: if __scsi_remove_device() invokes
+		 * blk_cleanup_queue() before the queue is run from this
+		 * function then blk_run_queue() will return immediately since
+		 * blk_cleanup_queue() marks the queue with QUEUE_FLAG_DYING.
+		 */
+		slq = sdev->request_queue;
+		if (!blk_get_queue(slq))
+			continue;
+		spin_unlock_irqrestore(shost->host_lock, flags);
+
+		scsi_kick_queue(slq);
+		blk_put_queue(slq);
+
+		spin_lock_irqsave(shost->host_lock, flags);
+	}
+	/* put any unprocessed entries back */
+	list_splice(&starved_list, &shost->starved_list);
+	spin_unlock_irqrestore(shost->host_lock, flags);
+}
+
+/*
+ * Function:   scsi_run_queue()
+ *
+ * Purpose:    Select a proper request queue to serve next
+ *
+ * Arguments:  q       - last request's queue
+ *
+ * Returns:     Nothing
+ *
+ * Notes:      The previous command was completely finished, start
+ *             a new one if possible.
+ */
+static void scsi_run_queue(struct request_queue *q)
+{
+	struct scsi_device *sdev = q->queuedata;
+
+	if (scsi_target(sdev)->single_lun)
+		scsi_single_lun_run(sdev);
+	if (!list_empty(&sdev->host->starved_list))
+		scsi_starved_list_run(sdev->host);
+
+	if (q->mq_ops)
+		blk_mq_run_hw_queues(q, false);
+	else
+		blk_run_queue(q);
+}
+
+void scsi_requeue_run_queue(struct work_struct *work)
+{
+	struct scsi_device *sdev;
+	struct request_queue *q;
+
+	sdev = container_of(work, struct scsi_device, requeue_work);
+	q = sdev->request_queue;
+	scsi_run_queue(q);
+}
+
+/*
+ * Function:	scsi_requeue_command()
+ *
+ * Purpose:	Handle post-processing of completed commands.
+ *
+ * Arguments:	q	- queue to operate on
+ *		cmd	- command that may need to be requeued.
+ *
+ * Returns:	Nothing
+ *
+ * Notes:	After command completion, there may be blocks left
+ *		over which weren't finished by the previous command
+ *		this can be for a number of reasons - the main one is
+ *		I/O errors in the middle of the request, in which case
+ *		we need to request the blocks that come after the bad
+ *		sector.
+ * Notes:	Upon return, cmd is a stale pointer.
+ */
+static void scsi_requeue_command(struct request_queue *q, struct scsi_cmnd *cmd)
+{
+	struct scsi_device *sdev = cmd->device;
+	struct request *req = cmd->request;
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	blk_unprep_request(req);
+	req->special = NULL;
+	scsi_put_command(cmd);
+	blk_requeue_request(q, req);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	scsi_run_queue(q);
+
+	put_device(&sdev->sdev_gendev);
+}
+
+void scsi_run_host_queues(struct Scsi_Host *shost)
+{
+	struct scsi_device *sdev;
+
+	shost_for_each_device(sdev, shost)
+		scsi_run_queue(sdev->request_queue);
+}
+
+static void scsi_uninit_cmd(struct scsi_cmnd *cmd)
+{
+	if (!blk_rq_is_passthrough(cmd->request)) {
+		struct scsi_driver *drv = scsi_cmd_to_driver(cmd);
+
+		if (drv->uninit_command)
+			drv->uninit_command(cmd);
+	}
+}
+
+static void scsi_mq_free_sgtables(struct scsi_cmnd *cmd)
+{
+	struct scsi_data_buffer *sdb;
+
+	if (cmd->sdb.table.nents)
+		sg_free_table_chained(&cmd->sdb.table, true);
+	if (cmd->request->next_rq) {
+		sdb = cmd->request->next_rq->special;
+		if (sdb)
+			sg_free_table_chained(&sdb->table, true);
+	}
+	if (scsi_prot_sg_count(cmd))
+		sg_free_table_chained(&cmd->prot_sdb->table, true);
+}
+
+static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd)
+{
+	scsi_mq_free_sgtables(cmd);
+	scsi_uninit_cmd(cmd);
+	scsi_del_cmd_from_list(cmd);
+}
+
+/*
+ * Function:    scsi_release_buffers()
+ *
+ * Purpose:     Free resources allocate for a scsi_command.
+ *
+ * Arguments:   cmd	- command that we are bailing.
+ *
+ * Lock status: Assumed that no lock is held upon entry.
+ *
+ * Returns:     Nothing
+ *
+ * Notes:       In the event that an upper level driver rejects a
+ *		command, we must release resources allocated during
+ *		the __init_io() function.  Primarily this would involve
+ *		the scatter-gather table.
+ */
+static void scsi_release_buffers(struct scsi_cmnd *cmd)
+{
+	if (cmd->sdb.table.nents)
+		sg_free_table_chained(&cmd->sdb.table, false);
+
+	memset(&cmd->sdb, 0, sizeof(cmd->sdb));
+
+	if (scsi_prot_sg_count(cmd))
+		sg_free_table_chained(&cmd->prot_sdb->table, false);
+}
+
+static void scsi_release_bidi_buffers(struct scsi_cmnd *cmd)
+{
+	struct scsi_data_buffer *bidi_sdb = cmd->request->next_rq->special;
+
+	sg_free_table_chained(&bidi_sdb->table, false);
+	kmem_cache_free(scsi_sdb_cache, bidi_sdb);
+	cmd->request->next_rq->special = NULL;
+}
+
+/* Returns false when no more bytes to process, true if there are more */
+static bool scsi_end_request(struct request *req, blk_status_t error,
+		unsigned int bytes, unsigned int bidi_bytes)
+{
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
+	struct scsi_device *sdev = cmd->device;
+	struct request_queue *q = sdev->request_queue;
+
+	if (blk_update_request(req, error, bytes))
+		return true;
+
+	/* Bidi request must be completed as a whole */
+	if (unlikely(bidi_bytes) &&
+	    blk_update_request(req->next_rq, error, bidi_bytes))
+		return true;
+
+	if (blk_queue_add_random(q))
+		add_disk_randomness(req->rq_disk);
+
+	if (!blk_rq_is_scsi(req)) {
+		WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED));
+		cmd->flags &= ~SCMD_INITIALIZED;
+		destroy_rcu_head(&cmd->rcu);
+	}
+
+	if (req->mq_ctx) {
+		/*
+		 * In the MQ case the command gets freed by __blk_mq_end_request,
+		 * so we have to do all cleanup that depends on it earlier.
+		 *
+		 * We also can't kick the queues from irq context, so we
+		 * will have to defer it to a workqueue.
+		 */
+		scsi_mq_uninit_cmd(cmd);
+
+		__blk_mq_end_request(req, error);
+
+		if (scsi_target(sdev)->single_lun ||
+		    !list_empty(&sdev->host->starved_list))
+			kblockd_schedule_work(&sdev->requeue_work);
+		else
+			blk_mq_run_hw_queues(q, true);
+	} else {
+		unsigned long flags;
+
+		if (bidi_bytes)
+			scsi_release_bidi_buffers(cmd);
+		scsi_release_buffers(cmd);
+		scsi_put_command(cmd);
+
+		spin_lock_irqsave(q->queue_lock, flags);
+		blk_finish_request(req, error);
+		spin_unlock_irqrestore(q->queue_lock, flags);
+
+		scsi_run_queue(q);
+	}
+
+	put_device(&sdev->sdev_gendev);
+	return false;
+}
+
+/**
+ * scsi_result_to_blk_status - translate a SCSI result code into blk_status_t
+ * @cmd:	SCSI command
+ * @result:	scsi error code
+ *
+ * Translate a SCSI result code into a blk_status_t value. May reset the host
+ * byte of @cmd->result.
+ */
+static blk_status_t scsi_result_to_blk_status(struct scsi_cmnd *cmd, int result)
+{
+	switch (host_byte(result)) {
+	case DID_OK:
+		/*
+		 * Also check the other bytes than the status byte in result
+		 * to handle the case when a SCSI LLD sets result to
+		 * DRIVER_SENSE << 24 without setting SAM_STAT_CHECK_CONDITION.
+		 */
+		if (scsi_status_is_good(result) && (result & ~0xff) == 0)
+			return BLK_STS_OK;
+		return BLK_STS_IOERR;
+	case DID_TRANSPORT_FAILFAST:
+		return BLK_STS_TRANSPORT;
+	case DID_TARGET_FAILURE:
+		set_host_byte(cmd, DID_OK);
+		return BLK_STS_TARGET;
+	case DID_NEXUS_FAILURE:
+		return BLK_STS_NEXUS;
+	case DID_ALLOC_FAILURE:
+		set_host_byte(cmd, DID_OK);
+		return BLK_STS_NOSPC;
+	case DID_MEDIUM_ERROR:
+		set_host_byte(cmd, DID_OK);
+		return BLK_STS_MEDIUM;
+	default:
+		return BLK_STS_IOERR;
+	}
+}
+
+/* Helper for scsi_io_completion() when "reprep" action required. */
+static void scsi_io_completion_reprep(struct scsi_cmnd *cmd,
+				      struct request_queue *q)
+{
+	/* A new command will be prepared and issued. */
+	if (q->mq_ops) {
+		scsi_mq_requeue_cmd(cmd);
+	} else {
+		/* Unprep request and put it back at head of the queue. */
+		scsi_release_buffers(cmd);
+		scsi_requeue_command(q, cmd);
+	}
+}
+
+/* Helper for scsi_io_completion() when special action required. */
+static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
+{
+	struct request_queue *q = cmd->device->request_queue;
+	struct request *req = cmd->request;
+	int level = 0;
+	enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
+	      ACTION_DELAYED_RETRY} action;
+	unsigned long wait_for = (cmd->allowed + 1) * req->timeout;
+	struct scsi_sense_hdr sshdr;
+	bool sense_valid;
+	bool sense_current = true;      /* false implies "deferred sense" */
+	blk_status_t blk_stat;
+
+	sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
+	if (sense_valid)
+		sense_current = !scsi_sense_is_deferred(&sshdr);
+
+	blk_stat = scsi_result_to_blk_status(cmd, result);
+
+	if (host_byte(result) == DID_RESET) {
+		/* Third party bus reset or reset for error recovery
+		 * reasons.  Just retry the command and see what
+		 * happens.
+		 */
+		action = ACTION_RETRY;
+	} else if (sense_valid && sense_current) {
+		switch (sshdr.sense_key) {
+		case UNIT_ATTENTION:
+			if (cmd->device->removable) {
+				/* Detected disc change.  Set a bit
+				 * and quietly refuse further access.
+				 */
+				cmd->device->changed = 1;
+				action = ACTION_FAIL;
+			} else {
+				/* Must have been a power glitch, or a
+				 * bus reset.  Could not have been a
+				 * media change, so we just retry the
+				 * command and see what happens.
+				 */
+				action = ACTION_RETRY;
+			}
+			break;
+		case ILLEGAL_REQUEST:
+			/* If we had an ILLEGAL REQUEST returned, then
+			 * we may have performed an unsupported
+			 * command.  The only thing this should be
+			 * would be a ten byte read where only a six
+			 * byte read was supported.  Also, on a system
+			 * where READ CAPACITY failed, we may have
+			 * read past the end of the disk.
+			 */
+			if ((cmd->device->use_10_for_rw &&
+			    sshdr.asc == 0x20 && sshdr.ascq == 0x00) &&
+			    (cmd->cmnd[0] == READ_10 ||
+			     cmd->cmnd[0] == WRITE_10)) {
+				/* This will issue a new 6-byte command. */
+				cmd->device->use_10_for_rw = 0;
+				action = ACTION_REPREP;
+			} else if (sshdr.asc == 0x10) /* DIX */ {
+				action = ACTION_FAIL;
+				blk_stat = BLK_STS_PROTECTION;
+			/* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */
+			} else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) {
+				action = ACTION_FAIL;
+				blk_stat = BLK_STS_TARGET;
+			} else
+				action = ACTION_FAIL;
+			break;
+		case ABORTED_COMMAND:
+			action = ACTION_FAIL;
+			if (sshdr.asc == 0x10) /* DIF */
+				blk_stat = BLK_STS_PROTECTION;
+			break;
+		case NOT_READY:
+			/* If the device is in the process of becoming
+			 * ready, or has a temporary blockage, retry.
+			 */
+			if (sshdr.asc == 0x04) {
+				switch (sshdr.ascq) {
+				case 0x01: /* becoming ready */
+				case 0x04: /* format in progress */
+				case 0x05: /* rebuild in progress */
+				case 0x06: /* recalculation in progress */
+				case 0x07: /* operation in progress */
+				case 0x08: /* Long write in progress */
+				case 0x09: /* self test in progress */
+				case 0x14: /* space allocation in progress */
+				case 0x1a: /* start stop unit in progress */
+				case 0x1b: /* sanitize in progress */
+				case 0x1d: /* configuration in progress */
+				case 0x24: /* depopulation in progress */
+					action = ACTION_DELAYED_RETRY;
+					break;
+				default:
+					action = ACTION_FAIL;
+					break;
+				}
+			} else
+				action = ACTION_FAIL;
+			break;
+		case VOLUME_OVERFLOW:
+			/* See SSC3rXX or current. */
+			action = ACTION_FAIL;
+			break;
+		default:
+			action = ACTION_FAIL;
+			break;
+		}
+	} else
+		action = ACTION_FAIL;
+
+	if (action != ACTION_FAIL &&
+	    time_before(cmd->jiffies_at_alloc + wait_for, jiffies))
+		action = ACTION_FAIL;
+
+	switch (action) {
+	case ACTION_FAIL:
+		/* Give up and fail the remainder of the request */
+		if (!(req->rq_flags & RQF_QUIET)) {
+			static DEFINE_RATELIMIT_STATE(_rs,
+					DEFAULT_RATELIMIT_INTERVAL,
+					DEFAULT_RATELIMIT_BURST);
+
+			if (unlikely(scsi_logging_level))
+				level =
+				     SCSI_LOG_LEVEL(SCSI_LOG_MLCOMPLETE_SHIFT,
+						    SCSI_LOG_MLCOMPLETE_BITS);
+
+			/*
+			 * if logging is enabled the failure will be printed
+			 * in scsi_log_completion(), so avoid duplicate messages
+			 */
+			if (!level && __ratelimit(&_rs)) {
+				scsi_print_result(cmd, NULL, FAILED);
+				if (driver_byte(result) == DRIVER_SENSE)
+					scsi_print_sense(cmd);
+				scsi_print_command(cmd);
+			}
+		}
+		if (!scsi_end_request(req, blk_stat, blk_rq_err_bytes(req), 0))
+			return;
+		/*FALLTHRU*/
+	case ACTION_REPREP:
+		scsi_io_completion_reprep(cmd, q);
+		break;
+	case ACTION_RETRY:
+		/* Retry the same command immediately */
+		__scsi_queue_insert(cmd, SCSI_MLQUEUE_EH_RETRY, false);
+		break;
+	case ACTION_DELAYED_RETRY:
+		/* Retry the same command after a delay */
+		__scsi_queue_insert(cmd, SCSI_MLQUEUE_DEVICE_BUSY, false);
+		break;
+	}
+}
+
+/*
+ * Helper for scsi_io_completion() when cmd->result is non-zero. Returns a
+ * new result that may suppress further error checking. Also modifies
+ * *blk_statp in some cases.
+ */
+static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result,
+					blk_status_t *blk_statp)
+{
+	bool sense_valid;
+	bool sense_current = true;	/* false implies "deferred sense" */
+	struct request *req = cmd->request;
+	struct scsi_sense_hdr sshdr;
+
+	sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
+	if (sense_valid)
+		sense_current = !scsi_sense_is_deferred(&sshdr);
+
+	if (blk_rq_is_passthrough(req)) {
+		if (sense_valid) {
+			/*
+			 * SG_IO wants current and deferred errors
+			 */
+			scsi_req(req)->sense_len =
+				min(8 + cmd->sense_buffer[7],
+				    SCSI_SENSE_BUFFERSIZE);
+		}
+		if (sense_current)
+			*blk_statp = scsi_result_to_blk_status(cmd, result);
+	} else if (blk_rq_bytes(req) == 0 && sense_current) {
+		/*
+		 * Flush commands do not transfers any data, and thus cannot use
+		 * good_bytes != blk_rq_bytes(req) as the signal for an error.
+		 * This sets *blk_statp explicitly for the problem case.
+		 */
+		*blk_statp = scsi_result_to_blk_status(cmd, result);
+	}
+	/*
+	 * Recovered errors need reporting, but they're always treated as
+	 * success, so fiddle the result code here.  For passthrough requests
+	 * we already took a copy of the original into sreq->result which
+	 * is what gets returned to the user
+	 */
+	if (sense_valid && (sshdr.sense_key == RECOVERED_ERROR)) {
+		bool do_print = true;
+		/*
+		 * if ATA PASS-THROUGH INFORMATION AVAILABLE [0x0, 0x1d]
+		 * skip print since caller wants ATA registers. Only occurs
+		 * on SCSI ATA PASS_THROUGH commands when CK_COND=1
+		 */
+		if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
+			do_print = false;
+		else if (req->rq_flags & RQF_QUIET)
+			do_print = false;
+		if (do_print)
+			scsi_print_sense(cmd);
+		result = 0;
+		/* for passthrough, *blk_statp may be set */
+		*blk_statp = BLK_STS_OK;
+	}
+	/*
+	 * Another corner case: the SCSI status byte is non-zero but 'good'.
+	 * Example: PRE-FETCH command returns SAM_STAT_CONDITION_MET when
+	 * it is able to fit nominated LBs in its cache (and SAM_STAT_GOOD
+	 * if it can't fit). Treat SAM_STAT_CONDITION_MET and the related
+	 * intermediate statuses (both obsolete in SAM-4) as good.
+	 */
+	if (status_byte(result) && scsi_status_is_good(result)) {
+		result = 0;
+		*blk_statp = BLK_STS_OK;
+	}
+	return result;
+}
+
+/*
+ * Function:    scsi_io_completion()
+ *
+ * Purpose:     Completion processing for block device I/O requests.
+ *
+ * Arguments:   cmd   - command that is finished.
+ *
+ * Lock status: Assumed that no lock is held upon entry.
+ *
+ * Returns:     Nothing
+ *
+ * Notes:       We will finish off the specified number of sectors.  If we
+ *		are done, the command block will be released and the queue
+ *		function will be goosed.  If we are not done then we have to
+ *		figure out what to do next:
+ *
+ *		a) We can call scsi_requeue_command().  The request
+ *		   will be unprepared and put back on the queue.  Then
+ *		   a new command will be created for it.  This should
+ *		   be used if we made forward progress, or if we want
+ *		   to switch from READ(10) to READ(6) for example.
+ *
+ *		b) We can call __scsi_queue_insert().  The request will
+ *		   be put back on the queue and retried using the same
+ *		   command as before, possibly after a delay.
+ *
+ *		c) We can call scsi_end_request() with blk_stat other than
+ *		   BLK_STS_OK, to fail the remainder of the request.
+ */
+void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
+{
+	int result = cmd->result;
+	struct request_queue *q = cmd->device->request_queue;
+	struct request *req = cmd->request;
+	blk_status_t blk_stat = BLK_STS_OK;
+
+	if (unlikely(result))	/* a nz result may or may not be an error */
+		result = scsi_io_completion_nz_result(cmd, result, &blk_stat);
+
+	if (unlikely(blk_rq_is_passthrough(req))) {
+		/*
+		 * scsi_result_to_blk_status may have reset the host_byte
+		 */
+		scsi_req(req)->result = cmd->result;
+		scsi_req(req)->resid_len = scsi_get_resid(cmd);
+
+		if (unlikely(scsi_bidi_cmnd(cmd))) {
+			/*
+			 * Bidi commands Must be complete as a whole,
+			 * both sides at once.
+			 */
+			scsi_req(req->next_rq)->resid_len = scsi_in(cmd)->resid;
+			if (scsi_end_request(req, BLK_STS_OK, blk_rq_bytes(req),
+					blk_rq_bytes(req->next_rq)))
+				WARN_ONCE(true,
+					  "Bidi command with remaining bytes");
+			return;
+		}
+	}
+
+	/* no bidi support yet, other than in pass-through */
+	if (unlikely(blk_bidi_rq(req))) {
+		WARN_ONCE(true, "Only support bidi command in passthrough");
+		scmd_printk(KERN_ERR, cmd, "Killing bidi command\n");
+		if (scsi_end_request(req, BLK_STS_IOERR, blk_rq_bytes(req),
+				     blk_rq_bytes(req->next_rq)))
+			WARN_ONCE(true, "Bidi command with remaining bytes");
+		return;
+	}
+
+	/*
+	 * Next deal with any sectors which we were able to correctly
+	 * handle.
+	 */
+	SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, cmd,
+		"%u sectors total, %d bytes done.\n",
+		blk_rq_sectors(req), good_bytes));
+
+	/*
+	 * Next deal with any sectors which we were able to correctly
+	 * handle. Failed, zero length commands always need to drop down
+	 * to retry code. Fast path should return in this block.
+	 */
+	if (likely(blk_rq_bytes(req) > 0 || blk_stat == BLK_STS_OK)) {
+		if (likely(!scsi_end_request(req, blk_stat, good_bytes, 0)))
+			return; /* no bytes remaining */
+	}
+
+	/* Kill remainder if no retries. */
+	if (unlikely(blk_stat && scsi_noretry_cmd(cmd))) {
+		if (scsi_end_request(req, blk_stat, blk_rq_bytes(req), 0))
+			WARN_ONCE(true,
+			    "Bytes remaining after failed, no-retry command");
+		return;
+	}
+
+	/*
+	 * If there had been no error, but we have leftover bytes in the
+	 * requeues just queue the command up again.
+	 */
+	if (likely(result == 0))
+		scsi_io_completion_reprep(cmd, q);
+	else
+		scsi_io_completion_action(cmd, result);
+}
+
+static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb)
+{
+	int count;
+
+	/*
+	 * If sg table allocation fails, requeue request later.
+	 */
+	if (unlikely(sg_alloc_table_chained(&sdb->table,
+			blk_rq_nr_phys_segments(req), sdb->table.sgl)))
+		return BLKPREP_DEFER;
+
+	/* 
+	 * Next, walk the list, and fill in the addresses and sizes of
+	 * each segment.
+	 */
+	count = blk_rq_map_sg(req->q, req, sdb->table.sgl);
+	BUG_ON(count > sdb->table.nents);
+	sdb->table.nents = count;
+	sdb->length = blk_rq_payload_bytes(req);
+	return BLKPREP_OK;
+}
+
+/*
+ * Function:    scsi_init_io()
+ *
+ * Purpose:     SCSI I/O initialize function.
+ *
+ * Arguments:   cmd   - Command descriptor we wish to initialize
+ *
+ * Returns:     0 on success
+ *		BLKPREP_DEFER if the failure is retryable
+ *		BLKPREP_KILL if the failure is fatal
+ */
+int scsi_init_io(struct scsi_cmnd *cmd)
+{
+	struct scsi_device *sdev = cmd->device;
+	struct request *rq = cmd->request;
+	bool is_mq = (rq->mq_ctx != NULL);
+	int error = BLKPREP_KILL;
+
+	if (WARN_ON_ONCE(!blk_rq_nr_phys_segments(rq)))
+		goto err_exit;
+
+	error = scsi_init_sgtable(rq, &cmd->sdb);
+	if (error)
+		goto err_exit;
+
+	if (blk_bidi_rq(rq)) {
+		if (!rq->q->mq_ops) {
+			struct scsi_data_buffer *bidi_sdb =
+				kmem_cache_zalloc(scsi_sdb_cache, GFP_ATOMIC);
+			if (!bidi_sdb) {
+				error = BLKPREP_DEFER;
+				goto err_exit;
+			}
+
+			rq->next_rq->special = bidi_sdb;
+		}
+
+		error = scsi_init_sgtable(rq->next_rq, rq->next_rq->special);
+		if (error)
+			goto err_exit;
+	}
+
+	if (blk_integrity_rq(rq)) {
+		struct scsi_data_buffer *prot_sdb = cmd->prot_sdb;
+		int ivecs, count;
+
+		if (prot_sdb == NULL) {
+			/*
+			 * This can happen if someone (e.g. multipath)
+			 * queues a command to a device on an adapter
+			 * that does not support DIX.
+			 */
+			WARN_ON_ONCE(1);
+			error = BLKPREP_KILL;
+			goto err_exit;
+		}
+
+		ivecs = blk_rq_count_integrity_sg(rq->q, rq->bio);
+
+		if (sg_alloc_table_chained(&prot_sdb->table, ivecs,
+				prot_sdb->table.sgl)) {
+			error = BLKPREP_DEFER;
+			goto err_exit;
+		}
+
+		count = blk_rq_map_integrity_sg(rq->q, rq->bio,
+						prot_sdb->table.sgl);
+		BUG_ON(unlikely(count > ivecs));
+		BUG_ON(unlikely(count > queue_max_integrity_segments(rq->q)));
+
+		cmd->prot_sdb = prot_sdb;
+		cmd->prot_sdb->table.nents = count;
+	}
+
+	return BLKPREP_OK;
+err_exit:
+	if (is_mq) {
+		scsi_mq_free_sgtables(cmd);
+	} else {
+		scsi_release_buffers(cmd);
+		cmd->request->special = NULL;
+		scsi_put_command(cmd);
+		put_device(&sdev->sdev_gendev);
+	}
+	return error;
+}
+EXPORT_SYMBOL(scsi_init_io);
+
+/**
+ * scsi_initialize_rq - initialize struct scsi_cmnd partially
+ * @rq: Request associated with the SCSI command to be initialized.
+ *
+ * This function initializes the members of struct scsi_cmnd that must be
+ * initialized before request processing starts and that won't be
+ * reinitialized if a SCSI command is requeued.
+ *
+ * Called from inside blk_get_request() for pass-through requests and from
+ * inside scsi_init_command() for filesystem requests.
+ */
+static void scsi_initialize_rq(struct request *rq)
+{
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+	scsi_req_init(&cmd->req);
+	init_rcu_head(&cmd->rcu);
+	cmd->jiffies_at_alloc = jiffies;
+	cmd->retries = 0;
+}
+
+/* Add a command to the list used by the aacraid and dpt_i2o drivers */
+void scsi_add_cmd_to_list(struct scsi_cmnd *cmd)
+{
+	struct scsi_device *sdev = cmd->device;
+	struct Scsi_Host *shost = sdev->host;
+	unsigned long flags;
+
+	if (shost->use_cmd_list) {
+		spin_lock_irqsave(&sdev->list_lock, flags);
+		list_add_tail(&cmd->list, &sdev->cmd_list);
+		spin_unlock_irqrestore(&sdev->list_lock, flags);
+	}
+}
+
+/* Remove a command from the list used by the aacraid and dpt_i2o drivers */
+void scsi_del_cmd_from_list(struct scsi_cmnd *cmd)
+{
+	struct scsi_device *sdev = cmd->device;
+	struct Scsi_Host *shost = sdev->host;
+	unsigned long flags;
+
+	if (shost->use_cmd_list) {
+		spin_lock_irqsave(&sdev->list_lock, flags);
+		BUG_ON(list_empty(&cmd->list));
+		list_del_init(&cmd->list);
+		spin_unlock_irqrestore(&sdev->list_lock, flags);
+	}
+}
+
+/* Called after a request has been started. */
+void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd)
+{
+	void *buf = cmd->sense_buffer;
+	void *prot = cmd->prot_sdb;
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
+	unsigned int flags = cmd->flags & SCMD_PRESERVED_FLAGS;
+	unsigned long jiffies_at_alloc;
+	int retries;
+
+	if (!blk_rq_is_scsi(rq) && !(flags & SCMD_INITIALIZED)) {
+		flags |= SCMD_INITIALIZED;
+		scsi_initialize_rq(rq);
+	}
+
+	jiffies_at_alloc = cmd->jiffies_at_alloc;
+	retries = cmd->retries;
+	/* zero out the cmd, except for the embedded scsi_request */
+	memset((char *)cmd + sizeof(cmd->req), 0,
+		sizeof(*cmd) - sizeof(cmd->req) + dev->host->hostt->cmd_size);
+
+	cmd->device = dev;
+	cmd->sense_buffer = buf;
+	cmd->prot_sdb = prot;
+	cmd->flags = flags;
+	INIT_DELAYED_WORK(&cmd->abort_work, scmd_eh_abort_handler);
+	cmd->jiffies_at_alloc = jiffies_at_alloc;
+	cmd->retries = retries;
+
+	scsi_add_cmd_to_list(cmd);
+}
+
+static int scsi_setup_scsi_cmnd(struct scsi_device *sdev, struct request *req)
+{
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
+
+	/*
+	 * Passthrough requests may transfer data, in which case they must
+	 * a bio attached to them.  Or they might contain a SCSI command
+	 * that does not transfer data, in which case they may optionally
+	 * submit a request without an attached bio.
+	 */
+	if (req->bio) {
+		int ret = scsi_init_io(cmd);
+		if (unlikely(ret))
+			return ret;
+	} else {
+		BUG_ON(blk_rq_bytes(req));
+
+		memset(&cmd->sdb, 0, sizeof(cmd->sdb));
+	}
+
+	cmd->cmd_len = scsi_req(req)->cmd_len;
+	cmd->cmnd = scsi_req(req)->cmd;
+	cmd->transfersize = blk_rq_bytes(req);
+	cmd->allowed = scsi_req(req)->retries;
+	return BLKPREP_OK;
+}
+
+/*
+ * Setup a normal block command.  These are simple request from filesystems
+ * that still need to be translated to SCSI CDBs from the ULD.
+ */
+static int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req)
+{
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
+
+	if (unlikely(sdev->handler && sdev->handler->prep_fn)) {
+		int ret = sdev->handler->prep_fn(sdev, req);
+		if (ret != BLKPREP_OK)
+			return ret;
+	}
+
+	cmd->cmnd = scsi_req(req)->cmd = scsi_req(req)->__cmd;
+	memset(cmd->cmnd, 0, BLK_MAX_CDB);
+	return scsi_cmd_to_driver(cmd)->init_command(cmd);
+}
+
+static int scsi_setup_cmnd(struct scsi_device *sdev, struct request *req)
+{
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
+
+	if (!blk_rq_bytes(req))
+		cmd->sc_data_direction = DMA_NONE;
+	else if (rq_data_dir(req) == WRITE)
+		cmd->sc_data_direction = DMA_TO_DEVICE;
+	else
+		cmd->sc_data_direction = DMA_FROM_DEVICE;
+
+	if (blk_rq_is_scsi(req))
+		return scsi_setup_scsi_cmnd(sdev, req);
+	else
+		return scsi_setup_fs_cmnd(sdev, req);
+}
+
+static int
+scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
+{
+	int ret = BLKPREP_OK;
+
+	/*
+	 * If the device is not in running state we will reject some
+	 * or all commands.
+	 */
+	if (unlikely(sdev->sdev_state != SDEV_RUNNING)) {
+		switch (sdev->sdev_state) {
+		case SDEV_OFFLINE:
+		case SDEV_TRANSPORT_OFFLINE:
+			/*
+			 * If the device is offline we refuse to process any
+			 * commands.  The device must be brought online
+			 * before trying any recovery commands.
+			 */
+			sdev_printk(KERN_ERR, sdev,
+				    "rejecting I/O to offline device\n");
+			ret = BLKPREP_KILL;
+			break;
+		case SDEV_DEL:
+			/*
+			 * If the device is fully deleted, we refuse to
+			 * process any commands as well.
+			 */
+			sdev_printk(KERN_ERR, sdev,
+				    "rejecting I/O to dead device\n");
+			ret = BLKPREP_KILL;
+			break;
+		case SDEV_BLOCK:
+		case SDEV_CREATED_BLOCK:
+			ret = BLKPREP_DEFER;
+			break;
+		case SDEV_QUIESCE:
+			/*
+			 * If the devices is blocked we defer normal commands.
+			 */
+			if (req && !(req->rq_flags & RQF_PREEMPT))
+				ret = BLKPREP_DEFER;
+			break;
+		default:
+			/*
+			 * For any other not fully online state we only allow
+			 * special commands.  In particular any user initiated
+			 * command is not allowed.
+			 */
+			if (req && !(req->rq_flags & RQF_PREEMPT))
+				ret = BLKPREP_KILL;
+			break;
+		}
+	}
+	return ret;
+}
+
+static int
+scsi_prep_return(struct request_queue *q, struct request *req, int ret)
+{
+	struct scsi_device *sdev = q->queuedata;
+
+	switch (ret) {
+	case BLKPREP_KILL:
+	case BLKPREP_INVALID:
+		scsi_req(req)->result = DID_NO_CONNECT << 16;
+		/* release the command and kill it */
+		if (req->special) {
+			struct scsi_cmnd *cmd = req->special;
+			scsi_release_buffers(cmd);
+			scsi_put_command(cmd);
+			put_device(&sdev->sdev_gendev);
+			req->special = NULL;
+		}
+		break;
+	case BLKPREP_DEFER:
+		/*
+		 * If we defer, the blk_peek_request() returns NULL, but the
+		 * queue must be restarted, so we schedule a callback to happen
+		 * shortly.
+		 */
+		if (atomic_read(&sdev->device_busy) == 0)
+			blk_delay_queue(q, SCSI_QUEUE_DELAY);
+		break;
+	default:
+		req->rq_flags |= RQF_DONTPREP;
+	}
+
+	return ret;
+}
+
+static int scsi_prep_fn(struct request_queue *q, struct request *req)
+{
+	struct scsi_device *sdev = q->queuedata;
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
+	int ret;
+
+	ret = scsi_prep_state_check(sdev, req);
+	if (ret != BLKPREP_OK)
+		goto out;
+
+	if (!req->special) {
+		/* Bail if we can't get a reference to the device */
+		if (unlikely(!get_device(&sdev->sdev_gendev))) {
+			ret = BLKPREP_DEFER;
+			goto out;
+		}
+
+		scsi_init_command(sdev, cmd);
+		req->special = cmd;
+	}
+
+	cmd->tag = req->tag;
+	cmd->request = req;
+	cmd->prot_op = SCSI_PROT_NORMAL;
+
+	ret = scsi_setup_cmnd(sdev, req);
+out:
+	return scsi_prep_return(q, req, ret);
+}
+
+static void scsi_unprep_fn(struct request_queue *q, struct request *req)
+{
+	scsi_uninit_cmd(blk_mq_rq_to_pdu(req));
+}
+
+/*
+ * scsi_dev_queue_ready: if we can send requests to sdev, return 1 else
+ * return 0.
+ *
+ * Called with the queue_lock held.
+ */
+static inline int scsi_dev_queue_ready(struct request_queue *q,
+				  struct scsi_device *sdev)
+{
+	unsigned int busy;
+
+	busy = atomic_inc_return(&sdev->device_busy) - 1;
+	if (atomic_read(&sdev->device_blocked)) {
+		if (busy)
+			goto out_dec;
+
+		/*
+		 * unblock after device_blocked iterates to zero
+		 */
+		if (atomic_dec_return(&sdev->device_blocked) > 0) {
+			/*
+			 * For the MQ case we take care of this in the caller.
+			 */
+			if (!q->mq_ops)
+				blk_delay_queue(q, SCSI_QUEUE_DELAY);
+			goto out_dec;
+		}
+		SCSI_LOG_MLQUEUE(3, sdev_printk(KERN_INFO, sdev,
+				   "unblocking device at zero depth\n"));
+	}
+
+	if (busy >= sdev->queue_depth)
+		goto out_dec;
+
+	return 1;
+out_dec:
+	atomic_dec(&sdev->device_busy);
+	return 0;
+}
+
+/*
+ * scsi_target_queue_ready: checks if there we can send commands to target
+ * @sdev: scsi device on starget to check.
+ */
+static inline int scsi_target_queue_ready(struct Scsi_Host *shost,
+					   struct scsi_device *sdev)
+{
+	struct scsi_target *starget = scsi_target(sdev);
+	unsigned int busy;
+
+	if (starget->single_lun) {
+		spin_lock_irq(shost->host_lock);
+		if (starget->starget_sdev_user &&
+		    starget->starget_sdev_user != sdev) {
+			spin_unlock_irq(shost->host_lock);
+			return 0;
+		}
+		starget->starget_sdev_user = sdev;
+		spin_unlock_irq(shost->host_lock);
+	}
+
+	if (starget->can_queue <= 0)
+		return 1;
+
+	busy = atomic_inc_return(&starget->target_busy) - 1;
+	if (atomic_read(&starget->target_blocked) > 0) {
+		if (busy)
+			goto starved;
+
+		/*
+		 * unblock after target_blocked iterates to zero
+		 */
+		if (atomic_dec_return(&starget->target_blocked) > 0)
+			goto out_dec;
+
+		SCSI_LOG_MLQUEUE(3, starget_printk(KERN_INFO, starget,
+				 "unblocking target at zero depth\n"));
+	}
+
+	if (busy >= starget->can_queue)
+		goto starved;
+
+	return 1;
+
+starved:
+	spin_lock_irq(shost->host_lock);
+	list_move_tail(&sdev->starved_entry, &shost->starved_list);
+	spin_unlock_irq(shost->host_lock);
+out_dec:
+	if (starget->can_queue > 0)
+		atomic_dec(&starget->target_busy);
+	return 0;
+}
+
+/*
+ * scsi_host_queue_ready: if we can send requests to shost, return 1 else
+ * return 0. We must end up running the queue again whenever 0 is
+ * returned, else IO can hang.
+ */
+static inline int scsi_host_queue_ready(struct request_queue *q,
+				   struct Scsi_Host *shost,
+				   struct scsi_device *sdev)
+{
+	unsigned int busy;
+
+	if (scsi_host_in_recovery(shost))
+		return 0;
+
+	busy = atomic_inc_return(&shost->host_busy) - 1;
+	if (atomic_read(&shost->host_blocked) > 0) {
+		if (busy)
+			goto starved;
+
+		/*
+		 * unblock after host_blocked iterates to zero
+		 */
+		if (atomic_dec_return(&shost->host_blocked) > 0)
+			goto out_dec;
+
+		SCSI_LOG_MLQUEUE(3,
+			shost_printk(KERN_INFO, shost,
+				     "unblocking host at zero depth\n"));
+	}
+
+	if (shost->can_queue > 0 && busy >= shost->can_queue)
+		goto starved;
+	if (shost->host_self_blocked)
+		goto starved;
+
+	/* We're OK to process the command, so we can't be starved */
+	if (!list_empty(&sdev->starved_entry)) {
+		spin_lock_irq(shost->host_lock);
+		if (!list_empty(&sdev->starved_entry))
+			list_del_init(&sdev->starved_entry);
+		spin_unlock_irq(shost->host_lock);
+	}
+
+	return 1;
+
+starved:
+	spin_lock_irq(shost->host_lock);
+	if (list_empty(&sdev->starved_entry))
+		list_add_tail(&sdev->starved_entry, &shost->starved_list);
+	spin_unlock_irq(shost->host_lock);
+out_dec:
+	scsi_dec_host_busy(shost);
+	return 0;
+}
+
+/*
+ * Busy state exporting function for request stacking drivers.
+ *
+ * For efficiency, no lock is taken to check the busy state of
+ * shost/starget/sdev, since the returned value is not guaranteed and
+ * may be changed after request stacking drivers call the function,
+ * regardless of taking lock or not.
+ *
+ * When scsi can't dispatch I/Os anymore and needs to kill I/Os scsi
+ * needs to return 'not busy'. Otherwise, request stacking drivers
+ * may hold requests forever.
+ */
+static int scsi_lld_busy(struct request_queue *q)
+{
+	struct scsi_device *sdev = q->queuedata;
+	struct Scsi_Host *shost;
+
+	if (blk_queue_dying(q))
+		return 0;
+
+	shost = sdev->host;
+
+	/*
+	 * Ignore host/starget busy state.
+	 * Since block layer does not have a concept of fairness across
+	 * multiple queues, congestion of host/starget needs to be handled
+	 * in SCSI layer.
+	 */
+	if (scsi_host_in_recovery(shost) || scsi_device_is_busy(sdev))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Kill a request for a dead device
+ */
+static void scsi_kill_request(struct request *req, struct request_queue *q)
+{
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
+	struct scsi_device *sdev;
+	struct scsi_target *starget;
+	struct Scsi_Host *shost;
+
+	blk_start_request(req);
+
+	scmd_printk(KERN_INFO, cmd, "killing request\n");
+
+	sdev = cmd->device;
+	starget = scsi_target(sdev);
+	shost = sdev->host;
+	scsi_init_cmd_errh(cmd);
+	cmd->result = DID_NO_CONNECT << 16;
+	atomic_inc(&cmd->device->iorequest_cnt);
+
+	/*
+	 * SCSI request completion path will do scsi_device_unbusy(),
+	 * bump busy counts.  To bump the counters, we need to dance
+	 * with the locks as normal issue path does.
+	 */
+	atomic_inc(&sdev->device_busy);
+	atomic_inc(&shost->host_busy);
+	if (starget->can_queue > 0)
+		atomic_inc(&starget->target_busy);
+
+	blk_complete_request(req);
+}
+
+static void scsi_softirq_done(struct request *rq)
+{
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+	unsigned long wait_for = (cmd->allowed + 1) * rq->timeout;
+	int disposition;
+
+	INIT_LIST_HEAD(&cmd->eh_entry);
+
+	atomic_inc(&cmd->device->iodone_cnt);
+	if (cmd->result)
+		atomic_inc(&cmd->device->ioerr_cnt);
+
+	disposition = scsi_decide_disposition(cmd);
+	if (disposition != SUCCESS &&
+	    time_before(cmd->jiffies_at_alloc + wait_for, jiffies)) {
+		sdev_printk(KERN_ERR, cmd->device,
+			    "timing out command, waited %lus\n",
+			    wait_for/HZ);
+		disposition = SUCCESS;
+	}
+
+	scsi_log_completion(cmd, disposition);
+
+	switch (disposition) {
+		case SUCCESS:
+			scsi_finish_command(cmd);
+			break;
+		case NEEDS_RETRY:
+			scsi_queue_insert(cmd, SCSI_MLQUEUE_EH_RETRY);
+			break;
+		case ADD_TO_MLQUEUE:
+			scsi_queue_insert(cmd, SCSI_MLQUEUE_DEVICE_BUSY);
+			break;
+		default:
+			scsi_eh_scmd_add(cmd);
+			break;
+	}
+}
+
+/**
+ * scsi_dispatch_command - Dispatch a command to the low-level driver.
+ * @cmd: command block we are dispatching.
+ *
+ * Return: nonzero return request was rejected and device's queue needs to be
+ * plugged.
+ */
+static int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
+{
+	struct Scsi_Host *host = cmd->device->host;
+	int rtn = 0;
+
+	atomic_inc(&cmd->device->iorequest_cnt);
+
+	/* check if the device is still usable */
+	if (unlikely(cmd->device->sdev_state == SDEV_DEL)) {
+		/* in SDEV_DEL we error all commands. DID_NO_CONNECT
+		 * returns an immediate error upwards, and signals
+		 * that the device is no longer present */
+		cmd->result = DID_NO_CONNECT << 16;
+		goto done;
+	}
+
+	/* Check to see if the scsi lld made this device blocked. */
+	if (unlikely(scsi_device_blocked(cmd->device))) {
+		/*
+		 * in blocked state, the command is just put back on
+		 * the device queue.  The suspend state has already
+		 * blocked the queue so future requests should not
+		 * occur until the device transitions out of the
+		 * suspend state.
+		 */
+		SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd,
+			"queuecommand : device blocked\n"));
+		return SCSI_MLQUEUE_DEVICE_BUSY;
+	}
+
+	/* Store the LUN value in cmnd, if needed. */
+	if (cmd->device->lun_in_cdb)
+		cmd->cmnd[1] = (cmd->cmnd[1] & 0x1f) |
+			       (cmd->device->lun << 5 & 0xe0);
+
+	scsi_log_send(cmd);
+
+	/*
+	 * Before we queue this command, check if the command
+	 * length exceeds what the host adapter can handle.
+	 */
+	if (cmd->cmd_len > cmd->device->host->max_cmd_len) {
+		SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd,
+			       "queuecommand : command too long. "
+			       "cdb_size=%d host->max_cmd_len=%d\n",
+			       cmd->cmd_len, cmd->device->host->max_cmd_len));
+		cmd->result = (DID_ABORT << 16);
+		goto done;
+	}
+
+	if (unlikely(host->shost_state == SHOST_DEL)) {
+		cmd->result = (DID_NO_CONNECT << 16);
+		goto done;
+
+	}
+
+	trace_scsi_dispatch_cmd_start(cmd);
+	rtn = host->hostt->queuecommand(host, cmd);
+	if (rtn) {
+		trace_scsi_dispatch_cmd_error(cmd, rtn);
+		if (rtn != SCSI_MLQUEUE_DEVICE_BUSY &&
+		    rtn != SCSI_MLQUEUE_TARGET_BUSY)
+			rtn = SCSI_MLQUEUE_HOST_BUSY;
+
+		SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd,
+			"queuecommand : request rejected\n"));
+	}
+
+	return rtn;
+ done:
+	cmd->scsi_done(cmd);
+	return 0;
+}
+
+/**
+ * scsi_done - Invoke completion on finished SCSI command.
+ * @cmd: The SCSI Command for which a low-level device driver (LLDD) gives
+ * ownership back to SCSI Core -- i.e. the LLDD has finished with it.
+ *
+ * Description: This function is the mid-level's (SCSI Core) interrupt routine,
+ * which regains ownership of the SCSI command (de facto) from a LLDD, and
+ * calls blk_complete_request() for further processing.
+ *
+ * This function is interrupt context safe.
+ */
+static void scsi_done(struct scsi_cmnd *cmd)
+{
+	trace_scsi_dispatch_cmd_done(cmd);
+	blk_complete_request(cmd->request);
+}
+
+/*
+ * Function:    scsi_request_fn()
+ *
+ * Purpose:     Main strategy routine for SCSI.
+ *
+ * Arguments:   q       - Pointer to actual queue.
+ *
+ * Returns:     Nothing
+ *
+ * Lock status: request queue lock assumed to be held when called.
+ *
+ * Note: See sd_zbc.c sd_zbc_write_lock_zone() for write order
+ * protection for ZBC disks.
+ */
+static void scsi_request_fn(struct request_queue *q)
+	__releases(q->queue_lock)
+	__acquires(q->queue_lock)
+{
+	struct scsi_device *sdev = q->queuedata;
+	struct Scsi_Host *shost;
+	struct scsi_cmnd *cmd;
+	struct request *req;
+
+	/*
+	 * To start with, we keep looping until the queue is empty, or until
+	 * the host is no longer able to accept any more requests.
+	 */
+	shost = sdev->host;
+	for (;;) {
+		int rtn;
+		/*
+		 * get next queueable request.  We do this early to make sure
+		 * that the request is fully prepared even if we cannot
+		 * accept it.
+		 */
+		req = blk_peek_request(q);
+		if (!req)
+			break;
+
+		if (unlikely(!scsi_device_online(sdev))) {
+			sdev_printk(KERN_ERR, sdev,
+				    "rejecting I/O to offline device\n");
+			scsi_kill_request(req, q);
+			continue;
+		}
+
+		if (!scsi_dev_queue_ready(q, sdev))
+			break;
+
+		/*
+		 * Remove the request from the request list.
+		 */
+		if (!(blk_queue_tagged(q) && !blk_queue_start_tag(q, req)))
+			blk_start_request(req);
+
+		spin_unlock_irq(q->queue_lock);
+		cmd = blk_mq_rq_to_pdu(req);
+		if (cmd != req->special) {
+			printk(KERN_CRIT "impossible request in %s.\n"
+					 "please mail a stack trace to "
+					 "linux-scsi@vger.kernel.org\n",
+					 __func__);
+			blk_dump_rq_flags(req, "foo");
+			BUG();
+		}
+
+		/*
+		 * We hit this when the driver is using a host wide
+		 * tag map. For device level tag maps the queue_depth check
+		 * in the device ready fn would prevent us from trying
+		 * to allocate a tag. Since the map is a shared host resource
+		 * we add the dev to the starved list so it eventually gets
+		 * a run when a tag is freed.
+		 */
+		if (blk_queue_tagged(q) && !(req->rq_flags & RQF_QUEUED)) {
+			spin_lock_irq(shost->host_lock);
+			if (list_empty(&sdev->starved_entry))
+				list_add_tail(&sdev->starved_entry,
+					      &shost->starved_list);
+			spin_unlock_irq(shost->host_lock);
+			goto not_ready;
+		}
+
+		if (!scsi_target_queue_ready(shost, sdev))
+			goto not_ready;
+
+		if (!scsi_host_queue_ready(q, shost, sdev))
+			goto host_not_ready;
+	
+		if (sdev->simple_tags)
+			cmd->flags |= SCMD_TAGGED;
+		else
+			cmd->flags &= ~SCMD_TAGGED;
+
+		/*
+		 * Finally, initialize any error handling parameters, and set up
+		 * the timers for timeouts.
+		 */
+		scsi_init_cmd_errh(cmd);
+
+		/*
+		 * Dispatch the command to the low-level driver.
+		 */
+		cmd->scsi_done = scsi_done;
+		rtn = scsi_dispatch_cmd(cmd);
+		if (rtn) {
+			scsi_queue_insert(cmd, rtn);
+			spin_lock_irq(q->queue_lock);
+			goto out_delay;
+		}
+		spin_lock_irq(q->queue_lock);
+	}
+
+	return;
+
+ host_not_ready:
+	if (scsi_target(sdev)->can_queue > 0)
+		atomic_dec(&scsi_target(sdev)->target_busy);
+ not_ready:
+	/*
+	 * lock q, handle tag, requeue req, and decrement device_busy. We
+	 * must return with queue_lock held.
+	 *
+	 * Decrementing device_busy without checking it is OK, as all such
+	 * cases (host limits or settings) should run the queue at some
+	 * later time.
+	 */
+	spin_lock_irq(q->queue_lock);
+	blk_requeue_request(q, req);
+	atomic_dec(&sdev->device_busy);
+out_delay:
+	if (!atomic_read(&sdev->device_busy) && !scsi_device_blocked(sdev))
+		blk_delay_queue(q, SCSI_QUEUE_DELAY);
+}
+
+static inline blk_status_t prep_to_mq(int ret)
+{
+	switch (ret) {
+	case BLKPREP_OK:
+		return BLK_STS_OK;
+	case BLKPREP_DEFER:
+		return BLK_STS_RESOURCE;
+	default:
+		return BLK_STS_IOERR;
+	}
+}
+
+/* Size in bytes of the sg-list stored in the scsi-mq command-private data. */
+static unsigned int scsi_mq_sgl_size(struct Scsi_Host *shost)
+{
+	return min_t(unsigned int, shost->sg_tablesize, SG_CHUNK_SIZE) *
+		sizeof(struct scatterlist);
+}
+
+static int scsi_mq_prep_fn(struct request *req)
+{
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
+	struct scsi_device *sdev = req->q->queuedata;
+	struct Scsi_Host *shost = sdev->host;
+	struct scatterlist *sg;
+
+	scsi_init_command(sdev, cmd);
+
+	req->special = cmd;
+
+	cmd->request = req;
+
+	cmd->tag = req->tag;
+	cmd->prot_op = SCSI_PROT_NORMAL;
+
+	sg = (void *)cmd + sizeof(struct scsi_cmnd) + shost->hostt->cmd_size;
+	cmd->sdb.table.sgl = sg;
+
+	if (scsi_host_get_prot(shost)) {
+		memset(cmd->prot_sdb, 0, sizeof(struct scsi_data_buffer));
+
+		cmd->prot_sdb->table.sgl =
+			(struct scatterlist *)(cmd->prot_sdb + 1);
+	}
+
+	if (blk_bidi_rq(req)) {
+		struct request *next_rq = req->next_rq;
+		struct scsi_data_buffer *bidi_sdb = blk_mq_rq_to_pdu(next_rq);
+
+		memset(bidi_sdb, 0, sizeof(struct scsi_data_buffer));
+		bidi_sdb->table.sgl =
+			(struct scatterlist *)(bidi_sdb + 1);
+
+		next_rq->special = bidi_sdb;
+	}
+
+	blk_mq_start_request(req);
+
+	return scsi_setup_cmnd(sdev, req);
+}
+
+static void scsi_mq_done(struct scsi_cmnd *cmd)
+{
+	trace_scsi_dispatch_cmd_done(cmd);
+	blk_mq_complete_request(cmd->request);
+}
+
+static void scsi_mq_put_budget(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	struct scsi_device *sdev = q->queuedata;
+
+	atomic_dec(&sdev->device_busy);
+	put_device(&sdev->sdev_gendev);
+}
+
+static bool scsi_mq_get_budget(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	struct scsi_device *sdev = q->queuedata;
+
+	if (!get_device(&sdev->sdev_gendev))
+		goto out;
+	if (!scsi_dev_queue_ready(q, sdev))
+		goto out_put_device;
+
+	return true;
+
+out_put_device:
+	put_device(&sdev->sdev_gendev);
+out:
+	if (atomic_read(&sdev->device_busy) == 0 && !scsi_device_blocked(sdev))
+		blk_mq_delay_run_hw_queue(hctx, SCSI_QUEUE_DELAY);
+	return false;
+}
+
+static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
+			 const struct blk_mq_queue_data *bd)
+{
+	struct request *req = bd->rq;
+	struct request_queue *q = req->q;
+	struct scsi_device *sdev = q->queuedata;
+	struct Scsi_Host *shost = sdev->host;
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
+	blk_status_t ret;
+	int reason;
+	pr_debug("scsi_queue_rq()");
+	ret = prep_to_mq(scsi_prep_state_check(sdev, req));
+	if (ret != BLK_STS_OK)
+		goto out_put_budget;
+
+	ret = BLK_STS_RESOURCE;
+	if (!scsi_target_queue_ready(shost, sdev))
+		goto out_put_budget;
+	if (!scsi_host_queue_ready(q, shost, sdev))
+		goto out_dec_target_busy;
+
+	if (!(req->rq_flags & RQF_DONTPREP)) {
+		ret = prep_to_mq(scsi_mq_prep_fn(req));
+		if (ret != BLK_STS_OK)
+			goto out_dec_host_busy;
+		req->rq_flags |= RQF_DONTPREP;
+	} else {
+		blk_mq_start_request(req);
+	}
+
+	if (sdev->simple_tags)
+		cmd->flags |= SCMD_TAGGED;
+	else
+		cmd->flags &= ~SCMD_TAGGED;
+
+	scsi_init_cmd_errh(cmd);
+	cmd->scsi_done = scsi_mq_done;
+
+	reason = scsi_dispatch_cmd(cmd);
+	if (reason) {
+		scsi_set_blocked(cmd, reason);
+		ret = BLK_STS_RESOURCE;
+		goto out_dec_host_busy;
+	}
+
+	return BLK_STS_OK;
+
+out_dec_host_busy:
+	scsi_dec_host_busy(shost);
+out_dec_target_busy:
+	if (scsi_target(sdev)->can_queue > 0)
+		atomic_dec(&scsi_target(sdev)->target_busy);
+out_put_budget:
+	scsi_mq_put_budget(hctx);
+	switch (ret) {
+	case BLK_STS_OK:
+		break;
+	case BLK_STS_RESOURCE:
+		if (atomic_read(&sdev->device_busy) ||
+		    scsi_device_blocked(sdev))
+			ret = BLK_STS_DEV_RESOURCE;
+		break;
+	default:
+		/*
+		 * Make sure to release all allocated ressources when
+		 * we hit an error, as we will never see this command
+		 * again.
+		 */
+		if (req->rq_flags & RQF_DONTPREP)
+			scsi_mq_uninit_cmd(cmd);
+		break;
+	}
+	return ret;
+}
+
+static enum blk_eh_timer_return scsi_timeout(struct request *req,
+		bool reserved)
+{
+	if (reserved)
+		return BLK_EH_RESET_TIMER;
+	return scsi_times_out(req);
+}
+
+static int scsi_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
+				unsigned int hctx_idx, unsigned int numa_node)
+{
+	struct Scsi_Host *shost = set->driver_data;
+	const bool unchecked_isa_dma = shost->unchecked_isa_dma;
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+	struct scatterlist *sg;
+
+	if (unchecked_isa_dma)
+		cmd->flags |= SCMD_UNCHECKED_ISA_DMA;
+	cmd->sense_buffer = scsi_alloc_sense_buffer(unchecked_isa_dma,
+						    GFP_KERNEL, numa_node);
+	if (!cmd->sense_buffer)
+		return -ENOMEM;
+	cmd->req.sense = cmd->sense_buffer;
+
+	if (scsi_host_get_prot(shost)) {
+		sg = (void *)cmd + sizeof(struct scsi_cmnd) +
+			shost->hostt->cmd_size;
+		cmd->prot_sdb = (void *)sg + scsi_mq_sgl_size(shost);
+	}
+
+	return 0;
+}
+
+static void scsi_mq_exit_request(struct blk_mq_tag_set *set, struct request *rq,
+				 unsigned int hctx_idx)
+{
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+	scsi_free_sense_buffer(cmd->flags & SCMD_UNCHECKED_ISA_DMA,
+			       cmd->sense_buffer);
+}
+
+static int scsi_map_queues(struct blk_mq_tag_set *set)
+{
+	struct Scsi_Host *shost = container_of(set, struct Scsi_Host, tag_set);
+
+	if (shost->hostt->map_queues)
+		return shost->hostt->map_queues(shost);
+	return blk_mq_map_queues(set);
+}
+
+void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
+{
+	struct device *dev = shost->dma_dev;
+
+	/*
+	 * this limit is imposed by hardware restrictions
+	 */
+	blk_queue_max_segments(q, min_t(unsigned short, shost->sg_tablesize,
+					SG_MAX_SEGMENTS));
+
+	if (scsi_host_prot_dma(shost)) {
+		shost->sg_prot_tablesize =
+			min_not_zero(shost->sg_prot_tablesize,
+				     (unsigned short)SCSI_MAX_PROT_SG_SEGMENTS);
+		BUG_ON(shost->sg_prot_tablesize < shost->sg_tablesize);
+		blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize);
+	}
+
+	blk_queue_max_hw_sectors(q, shost->max_sectors);
+	if (shost->unchecked_isa_dma)
+		blk_queue_bounce_limit(q, BLK_BOUNCE_ISA);
+	blk_queue_segment_boundary(q, shost->dma_boundary);
+	dma_set_seg_boundary(dev, shost->dma_boundary);
+
+	blk_queue_max_segment_size(q, dma_get_max_seg_size(dev));
+
+	if (!shost->use_clustering)
+		q->limits.cluster = 0;
+
+	/*
+	 * Set a reasonable default alignment:  The larger of 32-byte (dword),
+	 * which is a common minimum for HBAs, and the minimum DMA alignment,
+	 * which is set by the platform.
+	 *
+	 * Devices that require a bigger alignment can increase it later.
+	 */
+	blk_queue_dma_alignment(q, max(4, dma_get_cache_alignment()) - 1);
+}
+EXPORT_SYMBOL_GPL(__scsi_init_queue);
+
+static int scsi_old_init_rq(struct request_queue *q, struct request *rq,
+			    gfp_t gfp)
+{
+	struct Scsi_Host *shost = q->rq_alloc_data;
+	const bool unchecked_isa_dma = shost->unchecked_isa_dma;
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+	memset(cmd, 0, sizeof(*cmd));
+
+	if (unchecked_isa_dma)
+		cmd->flags |= SCMD_UNCHECKED_ISA_DMA;
+	cmd->sense_buffer = scsi_alloc_sense_buffer(unchecked_isa_dma, gfp,
+						    NUMA_NO_NODE);
+	if (!cmd->sense_buffer)
+		goto fail;
+	cmd->req.sense = cmd->sense_buffer;
+
+	if (scsi_host_get_prot(shost) >= SHOST_DIX_TYPE0_PROTECTION) {
+		cmd->prot_sdb = kmem_cache_zalloc(scsi_sdb_cache, gfp);
+		if (!cmd->prot_sdb)
+			goto fail_free_sense;
+	}
+
+	return 0;
+
+fail_free_sense:
+	scsi_free_sense_buffer(unchecked_isa_dma, cmd->sense_buffer);
+fail:
+	return -ENOMEM;
+}
+
+static void scsi_old_exit_rq(struct request_queue *q, struct request *rq)
+{
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+	if (cmd->prot_sdb)
+		kmem_cache_free(scsi_sdb_cache, cmd->prot_sdb);
+	scsi_free_sense_buffer(cmd->flags & SCMD_UNCHECKED_ISA_DMA,
+			       cmd->sense_buffer);
+}
+
+struct request_queue *scsi_old_alloc_queue(struct scsi_device *sdev)
+{
+	struct Scsi_Host *shost = sdev->host;
+	struct request_queue *q;
+
+	q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE, NULL);
+	if (!q)
+		return NULL;
+	q->cmd_size = sizeof(struct scsi_cmnd) + shost->hostt->cmd_size;
+	q->rq_alloc_data = shost;
+	q->request_fn = scsi_request_fn;
+	q->init_rq_fn = scsi_old_init_rq;
+	q->exit_rq_fn = scsi_old_exit_rq;
+	q->initialize_rq_fn = scsi_initialize_rq;
+
+	if (blk_init_allocated_queue(q) < 0) {
+		blk_cleanup_queue(q);
+		return NULL;
+	}
+
+	__scsi_init_queue(shost, q);
+	blk_queue_flag_set(QUEUE_FLAG_SCSI_PASSTHROUGH, q);
+	blk_queue_prep_rq(q, scsi_prep_fn);
+	blk_queue_unprep_rq(q, scsi_unprep_fn);
+	blk_queue_softirq_done(q, scsi_softirq_done);
+	blk_queue_rq_timed_out(q, scsi_times_out);
+	blk_queue_lld_busy(q, scsi_lld_busy);
+	return q;
+}
+
+static const struct blk_mq_ops scsi_mq_ops = {
+	.get_budget	= scsi_mq_get_budget,
+	.put_budget	= scsi_mq_put_budget,
+	.queue_rq	= scsi_queue_rq,
+	.complete	= scsi_softirq_done,
+	.timeout	= scsi_timeout,
+#ifdef CONFIG_BLK_DEBUG_FS
+	.show_rq	= scsi_show_rq,
+#endif
+	.init_request	= scsi_mq_init_request,
+	.exit_request	= scsi_mq_exit_request,
+	.initialize_rq_fn = scsi_initialize_rq,
+	.map_queues	= scsi_map_queues,
+};
+
+struct request_queue *scsi_mq_alloc_queue(struct scsi_device *sdev)
+{
+	sdev->request_queue = blk_mq_init_queue(&sdev->host->tag_set);
+	if (IS_ERR(sdev->request_queue))
+		return NULL;
+
+	sdev->request_queue->queuedata = sdev;
+	__scsi_init_queue(sdev->host, sdev->request_queue);
+	blk_queue_flag_set(QUEUE_FLAG_SCSI_PASSTHROUGH, sdev->request_queue);
+	return sdev->request_queue;
+}
+
+int scsi_mq_setup_tags(struct Scsi_Host *shost)
+{
+	unsigned int cmd_size, sgl_size;
+
+	sgl_size = scsi_mq_sgl_size(shost);
+	cmd_size = sizeof(struct scsi_cmnd) + shost->hostt->cmd_size + sgl_size;
+	if (scsi_host_get_prot(shost))
+		cmd_size += sizeof(struct scsi_data_buffer) + sgl_size;
+
+	memset(&shost->tag_set, 0, sizeof(shost->tag_set));
+	shost->tag_set.ops = &scsi_mq_ops;
+	shost->tag_set.nr_hw_queues = shost->nr_hw_queues ? : 1;
+	shost->tag_set.queue_depth = shost->can_queue;
+	shost->tag_set.cmd_size = cmd_size;
+	shost->tag_set.numa_node = NUMA_NO_NODE;
+	shost->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	shost->tag_set.flags |=
+		BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy);
+	shost->tag_set.driver_data = shost;
+
+	return blk_mq_alloc_tag_set(&shost->tag_set);
+}
+
+void scsi_mq_destroy_tags(struct Scsi_Host *shost)
+{
+	blk_mq_free_tag_set(&shost->tag_set);
+}
+
+/**
+ * scsi_device_from_queue - return sdev associated with a request_queue
+ * @q: The request queue to return the sdev from
+ *
+ * Return the sdev associated with a request queue or NULL if the
+ * request_queue does not reference a SCSI device.
+ */
+struct scsi_device *scsi_device_from_queue(struct request_queue *q)
+{
+	struct scsi_device *sdev = NULL;
+
+	if (q->mq_ops) {
+		if (q->mq_ops == &scsi_mq_ops)
+			sdev = q->queuedata;
+	} else if (q->request_fn == scsi_request_fn)
+		sdev = q->queuedata;
+	if (!sdev || !get_device(&sdev->sdev_gendev))
+		sdev = NULL;
+
+	return sdev;
+}
+EXPORT_SYMBOL_GPL(scsi_device_from_queue);
+
+/*
+ * Function:    scsi_block_requests()
+ *
+ * Purpose:     Utility function used by low-level drivers to prevent further
+ *		commands from being queued to the device.
+ *
+ * Arguments:   shost       - Host in question
+ *
+ * Returns:     Nothing
+ *
+ * Lock status: No locks are assumed held.
+ *
+ * Notes:       There is no timer nor any other means by which the requests
+ *		get unblocked other than the low-level driver calling
+ *		scsi_unblock_requests().
+ */
+void scsi_block_requests(struct Scsi_Host *shost)
+{
+	shost->host_self_blocked = 1;
+}
+EXPORT_SYMBOL(scsi_block_requests);
+
+/*
+ * Function:    scsi_unblock_requests()
+ *
+ * Purpose:     Utility function used by low-level drivers to allow further
+ *		commands from being queued to the device.
+ *
+ * Arguments:   shost       - Host in question
+ *
+ * Returns:     Nothing
+ *
+ * Lock status: No locks are assumed held.
+ *
+ * Notes:       There is no timer nor any other means by which the requests
+ *		get unblocked other than the low-level driver calling
+ *		scsi_unblock_requests().
+ *
+ *		This is done as an API function so that changes to the
+ *		internals of the scsi mid-layer won't require wholesale
+ *		changes to drivers that use this feature.
+ */
+void scsi_unblock_requests(struct Scsi_Host *shost)
+{
+	shost->host_self_blocked = 0;
+	scsi_run_host_queues(shost);
+}
+EXPORT_SYMBOL(scsi_unblock_requests);
+
+int __init scsi_init_queue(void)
+{
+	scsi_sdb_cache = kmem_cache_create("scsi_data_buffer",
+					   sizeof(struct scsi_data_buffer),
+					   0, 0, NULL);
+	if (!scsi_sdb_cache) {
+		printk(KERN_ERR "SCSI: can't init scsi sdb cache\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void scsi_exit_queue(void)
+{
+	kmem_cache_destroy(scsi_sense_cache);
+	kmem_cache_destroy(scsi_sense_isadma_cache);
+	kmem_cache_destroy(scsi_sdb_cache);
+}
+
+/**
+ *	scsi_mode_select - issue a mode select
+ *	@sdev:	SCSI device to be queried
+ *	@pf:	Page format bit (1 == standard, 0 == vendor specific)
+ *	@sp:	Save page bit (0 == don't save, 1 == save)
+ *	@modepage: mode page being requested
+ *	@buffer: request buffer (may not be smaller than eight bytes)
+ *	@len:	length of request buffer.
+ *	@timeout: command timeout
+ *	@retries: number of retries before failing
+ *	@data: returns a structure abstracting the mode header data
+ *	@sshdr: place to put sense data (or NULL if no sense to be collected).
+ *		must be SCSI_SENSE_BUFFERSIZE big.
+ *
+ *	Returns zero if successful; negative error number or scsi
+ *	status on error
+ *
+ */
+int
+scsi_mode_select(struct scsi_device *sdev, int pf, int sp, int modepage,
+		 unsigned char *buffer, int len, int timeout, int retries,
+		 struct scsi_mode_data *data, struct scsi_sense_hdr *sshdr)
+{
+	unsigned char cmd[10];
+	unsigned char *real_buffer;
+	int ret;
+
+	memset(cmd, 0, sizeof(cmd));
+	cmd[1] = (pf ? 0x10 : 0) | (sp ? 0x01 : 0);
+
+	if (sdev->use_10_for_ms) {
+		if (len > 65535)
+			return -EINVAL;
+		real_buffer = kmalloc(8 + len, GFP_KERNEL);
+		if (!real_buffer)
+			return -ENOMEM;
+		memcpy(real_buffer + 8, buffer, len);
+		len += 8;
+		real_buffer[0] = 0;
+		real_buffer[1] = 0;
+		real_buffer[2] = data->medium_type;
+		real_buffer[3] = data->device_specific;
+		real_buffer[4] = data->longlba ? 0x01 : 0;
+		real_buffer[5] = 0;
+		real_buffer[6] = data->block_descriptor_length >> 8;
+		real_buffer[7] = data->block_descriptor_length;
+
+		cmd[0] = MODE_SELECT_10;
+		cmd[7] = len >> 8;
+		cmd[8] = len;
+	} else {
+		if (len > 255 || data->block_descriptor_length > 255 ||
+		    data->longlba)
+			return -EINVAL;
+
+		real_buffer = kmalloc(4 + len, GFP_KERNEL);
+		if (!real_buffer)
+			return -ENOMEM;
+		memcpy(real_buffer + 4, buffer, len);
+		len += 4;
+		real_buffer[0] = 0;
+		real_buffer[1] = data->medium_type;
+		real_buffer[2] = data->device_specific;
+		real_buffer[3] = data->block_descriptor_length;
+		
+
+		cmd[0] = MODE_SELECT;
+		cmd[4] = len;
+	}
+
+	ret = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, real_buffer, len,
+			       sshdr, timeout, retries, NULL);
+	kfree(real_buffer);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(scsi_mode_select);
+
+/**
+ *	scsi_mode_sense - issue a mode sense, falling back from 10 to six bytes if necessary.
+ *	@sdev:	SCSI device to be queried
+ *	@dbd:	set if mode sense will allow block descriptors to be returned
+ *	@modepage: mode page being requested
+ *	@buffer: request buffer (may not be smaller than eight bytes)
+ *	@len:	length of request buffer.
+ *	@timeout: command timeout
+ *	@retries: number of retries before failing
+ *	@data: returns a structure abstracting the mode header data
+ *	@sshdr: place to put sense data (or NULL if no sense to be collected).
+ *		must be SCSI_SENSE_BUFFERSIZE big.
+ *
+ *	Returns zero if unsuccessful, or the header offset (either 4
+ *	or 8 depending on whether a six or ten byte command was
+ *	issued) if successful.
+ */
+int
+scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage,
+		  unsigned char *buffer, int len, int timeout, int retries,
+		  struct scsi_mode_data *data, struct scsi_sense_hdr *sshdr)
+{
+	unsigned char cmd[12];
+	int use_10_for_ms;
+	int header_length;
+	int result, retry_count = retries;
+	struct scsi_sense_hdr my_sshdr;
+
+	memset(data, 0, sizeof(*data));
+	memset(&cmd[0], 0, 12);
+	cmd[1] = dbd & 0x18;	/* allows DBD and LLBA bits */
+	cmd[2] = modepage;
+
+	/* caller might not be interested in sense, but we need it */
+	if (!sshdr)
+		sshdr = &my_sshdr;
+
+ retry:
+	use_10_for_ms = sdev->use_10_for_ms;
+
+	if (use_10_for_ms) {
+		if (len < 8)
+			len = 8;
+
+		cmd[0] = MODE_SENSE_10;
+		cmd[8] = len;
+		header_length = 8;
+	} else {
+		if (len < 4)
+			len = 4;
+
+		cmd[0] = MODE_SENSE;
+		cmd[4] = len;
+		header_length = 4;
+	}
+
+	memset(buffer, 0, len);
+
+	result = scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buffer, len,
+				  sshdr, timeout, retries, NULL);
+
+	/* This code looks awful: what it's doing is making sure an
+	 * ILLEGAL REQUEST sense return identifies the actual command
+	 * byte as the problem.  MODE_SENSE commands can return
+	 * ILLEGAL REQUEST if the code page isn't supported */
+
+	if (use_10_for_ms && !scsi_status_is_good(result) &&
+	    driver_byte(result) == DRIVER_SENSE) {
+		if (scsi_sense_valid(sshdr)) {
+			if ((sshdr->sense_key == ILLEGAL_REQUEST) &&
+			    (sshdr->asc == 0x20) && (sshdr->ascq == 0)) {
+				/* 
+				 * Invalid command operation code
+				 */
+				sdev->use_10_for_ms = 0;
+				goto retry;
+			}
+		}
+	}
+
+	if(scsi_status_is_good(result)) {
+		if (unlikely(buffer[0] == 0x86 && buffer[1] == 0x0b &&
+			     (modepage == 6 || modepage == 8))) {
+			/* Initio breakage? */
+			header_length = 0;
+			data->length = 13;
+			data->medium_type = 0;
+			data->device_specific = 0;
+			data->longlba = 0;
+			data->block_descriptor_length = 0;
+		} else if(use_10_for_ms) {
+			data->length = buffer[0]*256 + buffer[1] + 2;
+			data->medium_type = buffer[2];
+			data->device_specific = buffer[3];
+			data->longlba = buffer[4] & 0x01;
+			data->block_descriptor_length = buffer[6]*256
+				+ buffer[7];
+		} else {
+			data->length = buffer[0] + 1;
+			data->medium_type = buffer[1];
+			data->device_specific = buffer[2];
+			data->block_descriptor_length = buffer[3];
+		}
+		data->header_length = header_length;
+	} else if ((status_byte(result) == CHECK_CONDITION) &&
+		   scsi_sense_valid(sshdr) &&
+		   sshdr->sense_key == UNIT_ATTENTION && retry_count) {
+		retry_count--;
+		goto retry;
+	}
+
+	return result;
+}
+EXPORT_SYMBOL(scsi_mode_sense);
+
+/**
+ *	scsi_test_unit_ready - test if unit is ready
+ *	@sdev:	scsi device to change the state of.
+ *	@timeout: command timeout
+ *	@retries: number of retries before failing
+ *	@sshdr: outpout pointer for decoded sense information.
+ *
+ *	Returns zero if unsuccessful or an error if TUR failed.  For
+ *	removable media, UNIT_ATTENTION sets ->changed flag.
+ **/
+int
+scsi_test_unit_ready(struct scsi_device *sdev, int timeout, int retries,
+		     struct scsi_sense_hdr *sshdr)
+{
+	char cmd[] = {
+		TEST_UNIT_READY, 0, 0, 0, 0, 0,
+	};
+	int result;
+
+	/* try to eat the UNIT_ATTENTION if there are enough retries */
+	do {
+		result = scsi_execute_req(sdev, cmd, DMA_NONE, NULL, 0, sshdr,
+					  timeout, 1, NULL);
+		if (sdev->removable && scsi_sense_valid(sshdr) &&
+		    sshdr->sense_key == UNIT_ATTENTION)
+			sdev->changed = 1;
+	} while (scsi_sense_valid(sshdr) &&
+		 sshdr->sense_key == UNIT_ATTENTION && --retries);
+
+	return result;
+}
+EXPORT_SYMBOL(scsi_test_unit_ready);
+
+/**
+ *	scsi_device_set_state - Take the given device through the device state model.
+ *	@sdev:	scsi device to change the state of.
+ *	@state:	state to change to.
+ *
+ *	Returns zero if successful or an error if the requested
+ *	transition is illegal.
+ */
+int
+scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state)
+{
+	enum scsi_device_state oldstate = sdev->sdev_state;
+
+	if (state == oldstate)
+		return 0;
+
+	switch (state) {
+	case SDEV_CREATED:
+		switch (oldstate) {
+		case SDEV_CREATED_BLOCK:
+			break;
+		default:
+			goto illegal;
+		}
+		break;
+			
+	case SDEV_RUNNING:
+		switch (oldstate) {
+		case SDEV_CREATED:
+		case SDEV_OFFLINE:
+		case SDEV_TRANSPORT_OFFLINE:
+		case SDEV_QUIESCE:
+		case SDEV_BLOCK:
+			break;
+		default:
+			goto illegal;
+		}
+		break;
+
+	case SDEV_QUIESCE:
+		switch (oldstate) {
+		case SDEV_RUNNING:
+		case SDEV_OFFLINE:
+		case SDEV_TRANSPORT_OFFLINE:
+			break;
+		default:
+			goto illegal;
+		}
+		break;
+
+	case SDEV_OFFLINE:
+	case SDEV_TRANSPORT_OFFLINE:
+		switch (oldstate) {
+		case SDEV_CREATED:
+		case SDEV_RUNNING:
+		case SDEV_QUIESCE:
+		case SDEV_BLOCK:
+			break;
+		default:
+			goto illegal;
+		}
+		break;
+
+	case SDEV_BLOCK:
+		switch (oldstate) {
+		case SDEV_RUNNING:
+		case SDEV_CREATED_BLOCK:
+			break;
+		default:
+			goto illegal;
+		}
+		break;
+
+	case SDEV_CREATED_BLOCK:
+		switch (oldstate) {
+		case SDEV_CREATED:
+			break;
+		default:
+			goto illegal;
+		}
+		break;
+
+	case SDEV_CANCEL:
+		switch (oldstate) {
+		case SDEV_CREATED:
+		case SDEV_RUNNING:
+		case SDEV_QUIESCE:
+		case SDEV_OFFLINE:
+		case SDEV_TRANSPORT_OFFLINE:
+			break;
+		default:
+			goto illegal;
+		}
+		break;
+
+	case SDEV_DEL:
+		switch (oldstate) {
+		case SDEV_CREATED:
+		case SDEV_RUNNING:
+		case SDEV_OFFLINE:
+		case SDEV_TRANSPORT_OFFLINE:
+		case SDEV_CANCEL:
+		case SDEV_BLOCK:
+		case SDEV_CREATED_BLOCK:
+			break;
+		default:
+			goto illegal;
+		}
+		break;
+
+	}
+	sdev->sdev_state = state;
+	return 0;
+
+ illegal:
+	SCSI_LOG_ERROR_RECOVERY(1,
+				sdev_printk(KERN_ERR, sdev,
+					    "Illegal state transition %s->%s",
+					    scsi_device_state_name(oldstate),
+					    scsi_device_state_name(state))
+				);
+	return -EINVAL;
+}
+EXPORT_SYMBOL(scsi_device_set_state);
+
+/**
+ * 	sdev_evt_emit - emit a single SCSI device uevent
+ *	@sdev: associated SCSI device
+ *	@evt: event to emit
+ *
+ *	Send a single uevent (scsi_event) to the associated scsi_device.
+ */
+static void scsi_evt_emit(struct scsi_device *sdev, struct scsi_event *evt)
+{
+	int idx = 0;
+	char *envp[3];
+
+	switch (evt->evt_type) {
+	case SDEV_EVT_MEDIA_CHANGE:
+		envp[idx++] = "SDEV_MEDIA_CHANGE=1";
+		break;
+	case SDEV_EVT_INQUIRY_CHANGE_REPORTED:
+		scsi_rescan_device(&sdev->sdev_gendev);
+		envp[idx++] = "SDEV_UA=INQUIRY_DATA_HAS_CHANGED";
+		break;
+	case SDEV_EVT_CAPACITY_CHANGE_REPORTED:
+		envp[idx++] = "SDEV_UA=CAPACITY_DATA_HAS_CHANGED";
+		break;
+	case SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED:
+	       envp[idx++] = "SDEV_UA=THIN_PROVISIONING_SOFT_THRESHOLD_REACHED";
+		break;
+	case SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED:
+		envp[idx++] = "SDEV_UA=MODE_PARAMETERS_CHANGED";
+		break;
+	case SDEV_EVT_LUN_CHANGE_REPORTED:
+		envp[idx++] = "SDEV_UA=REPORTED_LUNS_DATA_HAS_CHANGED";
+		break;
+	case SDEV_EVT_ALUA_STATE_CHANGE_REPORTED:
+		envp[idx++] = "SDEV_UA=ASYMMETRIC_ACCESS_STATE_CHANGED";
+		break;
+	case SDEV_EVT_POWER_ON_RESET_OCCURRED:
+		envp[idx++] = "SDEV_UA=POWER_ON_RESET_OCCURRED";
+		break;
+	default:
+		/* do nothing */
+		break;
+	}
+
+	envp[idx++] = NULL;
+
+	kobject_uevent_env(&sdev->sdev_gendev.kobj, KOBJ_CHANGE, envp);
+}
+
+/**
+ * 	sdev_evt_thread - send a uevent for each scsi event
+ *	@work: work struct for scsi_device
+ *
+ *	Dispatch queued events to their associated scsi_device kobjects
+ *	as uevents.
+ */
+void scsi_evt_thread(struct work_struct *work)
+{
+	struct scsi_device *sdev;
+	enum scsi_device_event evt_type;
+	LIST_HEAD(event_list);
+
+	sdev = container_of(work, struct scsi_device, event_work);
+
+	for (evt_type = SDEV_EVT_FIRST; evt_type <= SDEV_EVT_LAST; evt_type++)
+		if (test_and_clear_bit(evt_type, sdev->pending_events))
+			sdev_evt_send_simple(sdev, evt_type, GFP_KERNEL);
+
+	while (1) {
+		struct scsi_event *evt;
+		struct list_head *this, *tmp;
+		unsigned long flags;
+
+		spin_lock_irqsave(&sdev->list_lock, flags);
+		list_splice_init(&sdev->event_list, &event_list);
+		spin_unlock_irqrestore(&sdev->list_lock, flags);
+
+		if (list_empty(&event_list))
+			break;
+
+		list_for_each_safe(this, tmp, &event_list) {
+			evt = list_entry(this, struct scsi_event, node);
+			list_del(&evt->node);
+			scsi_evt_emit(sdev, evt);
+			kfree(evt);
+		}
+	}
+}
+
+/**
+ * 	sdev_evt_send - send asserted event to uevent thread
+ *	@sdev: scsi_device event occurred on
+ *	@evt: event to send
+ *
+ *	Assert scsi device event asynchronously.
+ */
+void sdev_evt_send(struct scsi_device *sdev, struct scsi_event *evt)
+{
+	unsigned long flags;
+
+#if 0
+	/* FIXME: currently this check eliminates all media change events
+	 * for polled devices.  Need to update to discriminate between AN
+	 * and polled events */
+	if (!test_bit(evt->evt_type, sdev->supported_events)) {
+		kfree(evt);
+		return;
+	}
+#endif
+
+	spin_lock_irqsave(&sdev->list_lock, flags);
+	list_add_tail(&evt->node, &sdev->event_list);
+	schedule_work(&sdev->event_work);
+	spin_unlock_irqrestore(&sdev->list_lock, flags);
+}
+EXPORT_SYMBOL_GPL(sdev_evt_send);
+
+/**
+ * 	sdev_evt_alloc - allocate a new scsi event
+ *	@evt_type: type of event to allocate
+ *	@gfpflags: GFP flags for allocation
+ *
+ *	Allocates and returns a new scsi_event.
+ */
+struct scsi_event *sdev_evt_alloc(enum scsi_device_event evt_type,
+				  gfp_t gfpflags)
+{
+	struct scsi_event *evt = kzalloc(sizeof(struct scsi_event), gfpflags);
+	if (!evt)
+		return NULL;
+
+	evt->evt_type = evt_type;
+	INIT_LIST_HEAD(&evt->node);
+
+	/* evt_type-specific initialization, if any */
+	switch (evt_type) {
+	case SDEV_EVT_MEDIA_CHANGE:
+	case SDEV_EVT_INQUIRY_CHANGE_REPORTED:
+	case SDEV_EVT_CAPACITY_CHANGE_REPORTED:
+	case SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED:
+	case SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED:
+	case SDEV_EVT_LUN_CHANGE_REPORTED:
+	case SDEV_EVT_ALUA_STATE_CHANGE_REPORTED:
+	case SDEV_EVT_POWER_ON_RESET_OCCURRED:
+	default:
+		/* do nothing */
+		break;
+	}
+
+	return evt;
+}
+EXPORT_SYMBOL_GPL(sdev_evt_alloc);
+
+/**
+ * 	sdev_evt_send_simple - send asserted event to uevent thread
+ *	@sdev: scsi_device event occurred on
+ *	@evt_type: type of event to send
+ *	@gfpflags: GFP flags for allocation
+ *
+ *	Assert scsi device event asynchronously, given an event type.
+ */
+void sdev_evt_send_simple(struct scsi_device *sdev,
+			  enum scsi_device_event evt_type, gfp_t gfpflags)
+{
+	struct scsi_event *evt = sdev_evt_alloc(evt_type, gfpflags);
+	if (!evt) {
+		sdev_printk(KERN_ERR, sdev, "event %d eaten due to OOM\n",
+			    evt_type);
+		return;
+	}
+
+	sdev_evt_send(sdev, evt);
+}
+EXPORT_SYMBOL_GPL(sdev_evt_send_simple);
+
+/**
+ * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn()
+ * @sdev: SCSI device to count the number of scsi_request_fn() callers for.
+ */
+static int scsi_request_fn_active(struct scsi_device *sdev)
+{
+	struct request_queue *q = sdev->request_queue;
+	int request_fn_active;
+
+	WARN_ON_ONCE(sdev->host->use_blk_mq);
+
+	spin_lock_irq(q->queue_lock);
+	request_fn_active = q->request_fn_active;
+	spin_unlock_irq(q->queue_lock);
+
+	return request_fn_active;
+}
+
+/**
+ * scsi_wait_for_queuecommand() - wait for ongoing queuecommand() calls
+ * @sdev: SCSI device pointer.
+ *
+ * Wait until the ongoing shost->hostt->queuecommand() calls that are
+ * invoked from scsi_request_fn() have finished.
+ */
+static void scsi_wait_for_queuecommand(struct scsi_device *sdev)
+{
+	WARN_ON_ONCE(sdev->host->use_blk_mq);
+
+	while (scsi_request_fn_active(sdev))
+		msleep(20);
+}
+
+/**
+ *	scsi_device_quiesce - Block user issued commands.
+ *	@sdev:	scsi device to quiesce.
+ *
+ *	This works by trying to transition to the SDEV_QUIESCE state
+ *	(which must be a legal transition).  When the device is in this
+ *	state, only special requests will be accepted, all others will
+ *	be deferred.  Since special requests may also be requeued requests,
+ *	a successful return doesn't guarantee the device will be 
+ *	totally quiescent.
+ *
+ *	Must be called with user context, may sleep.
+ *
+ *	Returns zero if unsuccessful or an error if not.
+ */
+int
+scsi_device_quiesce(struct scsi_device *sdev)
+{
+	struct request_queue *q = sdev->request_queue;
+	int err;
+
+	/*
+	 * It is allowed to call scsi_device_quiesce() multiple times from
+	 * the same context but concurrent scsi_device_quiesce() calls are
+	 * not allowed.
+	 */
+	WARN_ON_ONCE(sdev->quiesced_by && sdev->quiesced_by != current);
+
+	blk_set_preempt_only(q);
+
+	blk_mq_freeze_queue(q);
+	/*
+	 * Ensure that the effect of blk_set_preempt_only() will be visible
+	 * for percpu_ref_tryget() callers that occur after the queue
+	 * unfreeze even if the queue was already frozen before this function
+	 * was called. See also https://lwn.net/Articles/573497/.
+	 */
+	synchronize_rcu();
+	blk_mq_unfreeze_queue(q);
+
+	mutex_lock(&sdev->state_mutex);
+	err = scsi_device_set_state(sdev, SDEV_QUIESCE);
+	if (err == 0)
+		sdev->quiesced_by = current;
+	else
+		blk_clear_preempt_only(q);
+	mutex_unlock(&sdev->state_mutex);
+
+	return err;
+}
+EXPORT_SYMBOL(scsi_device_quiesce);
+
+/**
+ *	scsi_device_resume - Restart user issued commands to a quiesced device.
+ *	@sdev:	scsi device to resume.
+ *
+ *	Moves the device from quiesced back to running and restarts the
+ *	queues.
+ *
+ *	Must be called with user context, may sleep.
+ */
+void scsi_device_resume(struct scsi_device *sdev)
+{
+	/* check if the device state was mutated prior to resume, and if
+	 * so assume the state is being managed elsewhere (for example
+	 * device deleted during suspend)
+	 */
+	mutex_lock(&sdev->state_mutex);
+	WARN_ON_ONCE(!sdev->quiesced_by);
+	sdev->quiesced_by = NULL;
+	blk_clear_preempt_only(sdev->request_queue);
+	if (sdev->sdev_state == SDEV_QUIESCE)
+		scsi_device_set_state(sdev, SDEV_RUNNING);
+	mutex_unlock(&sdev->state_mutex);
+}
+EXPORT_SYMBOL(scsi_device_resume);
+
+static void
+device_quiesce_fn(struct scsi_device *sdev, void *data)
+{
+	scsi_device_quiesce(sdev);
+}
+
+void
+scsi_target_quiesce(struct scsi_target *starget)
+{
+	starget_for_each_device(starget, NULL, device_quiesce_fn);
+}
+EXPORT_SYMBOL(scsi_target_quiesce);
+
+static void
+device_resume_fn(struct scsi_device *sdev, void *data)
+{
+	scsi_device_resume(sdev);
+}
+
+void
+scsi_target_resume(struct scsi_target *starget)
+{
+	starget_for_each_device(starget, NULL, device_resume_fn);
+}
+EXPORT_SYMBOL(scsi_target_resume);
+
+/**
+ * scsi_internal_device_block_nowait - try to transition to the SDEV_BLOCK state
+ * @sdev: device to block
+ *
+ * Pause SCSI command processing on the specified device. Does not sleep.
+ *
+ * Returns zero if successful or a negative error code upon failure.
+ *
+ * Notes:
+ * This routine transitions the device to the SDEV_BLOCK state (which must be
+ * a legal transition). When the device is in this state, command processing
+ * is paused until the device leaves the SDEV_BLOCK state. See also
+ * scsi_internal_device_unblock_nowait().
+ */
+int scsi_internal_device_block_nowait(struct scsi_device *sdev)
+{
+	struct request_queue *q = sdev->request_queue;
+	unsigned long flags;
+	int err = 0;
+
+	err = scsi_device_set_state(sdev, SDEV_BLOCK);
+	if (err) {
+		err = scsi_device_set_state(sdev, SDEV_CREATED_BLOCK);
+
+		if (err)
+			return err;
+	}
+
+	/* 
+	 * The device has transitioned to SDEV_BLOCK.  Stop the
+	 * block layer from calling the midlayer with this device's
+	 * request queue. 
+	 */
+	if (q->mq_ops) {
+		blk_mq_quiesce_queue_nowait(q);
+	} else {
+		spin_lock_irqsave(q->queue_lock, flags);
+		blk_stop_queue(q);
+		spin_unlock_irqrestore(q->queue_lock, flags);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(scsi_internal_device_block_nowait);
+
+/**
+ * scsi_internal_device_block - try to transition to the SDEV_BLOCK state
+ * @sdev: device to block
+ *
+ * Pause SCSI command processing on the specified device and wait until all
+ * ongoing scsi_request_fn() / scsi_queue_rq() calls have finished. May sleep.
+ *
+ * Returns zero if successful or a negative error code upon failure.
+ *
+ * Note:
+ * This routine transitions the device to the SDEV_BLOCK state (which must be
+ * a legal transition). When the device is in this state, command processing
+ * is paused until the device leaves the SDEV_BLOCK state. See also
+ * scsi_internal_device_unblock().
+ *
+ * To do: avoid that scsi_send_eh_cmnd() calls queuecommand() after
+ * scsi_internal_device_block() has blocked a SCSI device and also
+ * remove the rport mutex lock and unlock calls from srp_queuecommand().
+ */
+static int scsi_internal_device_block(struct scsi_device *sdev)
+{
+	struct request_queue *q = sdev->request_queue;
+	int err;
+
+	mutex_lock(&sdev->state_mutex);
+	err = scsi_internal_device_block_nowait(sdev);
+	if (err == 0) {
+		if (q->mq_ops)
+			blk_mq_quiesce_queue(q);
+		else
+			scsi_wait_for_queuecommand(sdev);
+	}
+	mutex_unlock(&sdev->state_mutex);
+
+	return err;
+}
+ 
+void scsi_start_queue(struct scsi_device *sdev)
+{
+	struct request_queue *q = sdev->request_queue;
+	unsigned long flags;
+
+	if (q->mq_ops) {
+		blk_mq_unquiesce_queue(q);
+	} else {
+		spin_lock_irqsave(q->queue_lock, flags);
+		blk_start_queue(q);
+		spin_unlock_irqrestore(q->queue_lock, flags);
+	}
+}
+
+/**
+ * scsi_internal_device_unblock_nowait - resume a device after a block request
+ * @sdev:	device to resume
+ * @new_state:	state to set the device to after unblocking
+ *
+ * Restart the device queue for a previously suspended SCSI device. Does not
+ * sleep.
+ *
+ * Returns zero if successful or a negative error code upon failure.
+ *
+ * Notes:
+ * This routine transitions the device to the SDEV_RUNNING state or to one of
+ * the offline states (which must be a legal transition) allowing the midlayer
+ * to goose the queue for this device.
+ */
+int scsi_internal_device_unblock_nowait(struct scsi_device *sdev,
+					enum scsi_device_state new_state)
+{
+	/*
+	 * Try to transition the scsi device to SDEV_RUNNING or one of the
+	 * offlined states and goose the device queue if successful.
+	 */
+	switch (sdev->sdev_state) {
+	case SDEV_BLOCK:
+	case SDEV_TRANSPORT_OFFLINE:
+		sdev->sdev_state = new_state;
+		break;
+	case SDEV_CREATED_BLOCK:
+		if (new_state == SDEV_TRANSPORT_OFFLINE ||
+		    new_state == SDEV_OFFLINE)
+			sdev->sdev_state = new_state;
+		else
+			sdev->sdev_state = SDEV_CREATED;
+		break;
+	case SDEV_CANCEL:
+	case SDEV_OFFLINE:
+		break;
+	default:
+		return -EINVAL;
+	}
+	scsi_start_queue(sdev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(scsi_internal_device_unblock_nowait);
+
+/**
+ * scsi_internal_device_unblock - resume a device after a block request
+ * @sdev:	device to resume
+ * @new_state:	state to set the device to after unblocking
+ *
+ * Restart the device queue for a previously suspended SCSI device. May sleep.
+ *
+ * Returns zero if successful or a negative error code upon failure.
+ *
+ * Notes:
+ * This routine transitions the device to the SDEV_RUNNING state or to one of
+ * the offline states (which must be a legal transition) allowing the midlayer
+ * to goose the queue for this device.
+ */
+static int scsi_internal_device_unblock(struct scsi_device *sdev,
+					enum scsi_device_state new_state)
+{
+	int ret;
+
+	mutex_lock(&sdev->state_mutex);
+	ret = scsi_internal_device_unblock_nowait(sdev, new_state);
+	mutex_unlock(&sdev->state_mutex);
+
+	return ret;
+}
+
+static void
+device_block(struct scsi_device *sdev, void *data)
+{
+	scsi_internal_device_block(sdev);
+}
+
+static int
+target_block(struct device *dev, void *data)
+{
+	if (scsi_is_target_device(dev))
+		starget_for_each_device(to_scsi_target(dev), NULL,
+					device_block);
+	return 0;
+}
+
+void
+scsi_target_block(struct device *dev)
+{
+	if (scsi_is_target_device(dev))
+		starget_for_each_device(to_scsi_target(dev), NULL,
+					device_block);
+	else
+		device_for_each_child(dev, NULL, target_block);
+}
+EXPORT_SYMBOL_GPL(scsi_target_block);
+
+static void
+device_unblock(struct scsi_device *sdev, void *data)
+{
+	scsi_internal_device_unblock(sdev, *(enum scsi_device_state *)data);
+}
+
+static int
+target_unblock(struct device *dev, void *data)
+{
+	if (scsi_is_target_device(dev))
+		starget_for_each_device(to_scsi_target(dev), data,
+					device_unblock);
+	return 0;
+}
+
+void
+scsi_target_unblock(struct device *dev, enum scsi_device_state new_state)
+{
+	if (scsi_is_target_device(dev))
+		starget_for_each_device(to_scsi_target(dev), &new_state,
+					device_unblock);
+	else
+		device_for_each_child(dev, &new_state, target_unblock);
+}
+EXPORT_SYMBOL_GPL(scsi_target_unblock);
+
+/**
+ * scsi_kmap_atomic_sg - find and atomically map an sg-elemnt
+ * @sgl:	scatter-gather list
+ * @sg_count:	number of segments in sg
+ * @offset:	offset in bytes into sg, on return offset into the mapped area
+ * @len:	bytes to map, on return number of bytes mapped
+ *
+ * Returns virtual address of the start of the mapped page
+ */
+void *scsi_kmap_atomic_sg(struct scatterlist *sgl, int sg_count,
+			  size_t *offset, size_t *len)
+{
+	int i;
+	size_t sg_len = 0, len_complete = 0;
+	struct scatterlist *sg;
+	struct page *page;
+
+	WARN_ON(!irqs_disabled());
+
+	for_each_sg(sgl, sg, sg_count, i) {
+		len_complete = sg_len; /* Complete sg-entries */
+		sg_len += sg->length;
+		if (sg_len > *offset)
+			break;
+	}
+
+	if (unlikely(i == sg_count)) {
+		printk(KERN_ERR "%s: Bytes in sg: %zu, requested offset %zu, "
+			"elements %d\n",
+		       __func__, sg_len, *offset, sg_count);
+		WARN_ON(1);
+		return NULL;
+	}
+
+	/* Offset starting from the beginning of first page in this sg-entry */
+	*offset = *offset - len_complete + sg->offset;
+
+	/* Assumption: contiguous pages can be accessed as "page + i" */
+	page = nth_page(sg_page(sg), (*offset >> PAGE_SHIFT));
+	*offset &= ~PAGE_MASK;
+
+	/* Bytes in this sg-entry from *offset to the end of the page */
+	sg_len = PAGE_SIZE - *offset;
+	if (*len > sg_len)
+		*len = sg_len;
+
+	return kmap_atomic(page);
+}
+EXPORT_SYMBOL(scsi_kmap_atomic_sg);
+
+/**
+ * scsi_kunmap_atomic_sg - atomically unmap a virtual address, previously mapped with scsi_kmap_atomic_sg
+ * @virt:	virtual address to be unmapped
+ */
+void scsi_kunmap_atomic_sg(void *virt)
+{
+	kunmap_atomic(virt);
+}
+EXPORT_SYMBOL(scsi_kunmap_atomic_sg);
+
+void sdev_disable_disk_events(struct scsi_device *sdev)
+{
+	atomic_inc(&sdev->disk_events_disable_depth);
+}
+EXPORT_SYMBOL(sdev_disable_disk_events);
+
+void sdev_enable_disk_events(struct scsi_device *sdev)
+{
+	if (WARN_ON_ONCE(atomic_read(&sdev->disk_events_disable_depth) <= 0))
+		return;
+	atomic_dec(&sdev->disk_events_disable_depth);
+}
+EXPORT_SYMBOL(sdev_enable_disk_events);
+
+/**
+ * scsi_vpd_lun_id - return a unique device identification
+ * @sdev: SCSI device
+ * @id:   buffer for the identification
+ * @id_len:  length of the buffer
+ *
+ * Copies a unique device identification into @id based
+ * on the information in the VPD page 0x83 of the device.
+ * The string will be formatted as a SCSI name string.
+ *
+ * Returns the length of the identification or error on failure.
+ * If the identifier is longer than the supplied buffer the actual
+ * identifier length is returned and the buffer is not zero-padded.
+ */
+int scsi_vpd_lun_id(struct scsi_device *sdev, char *id, size_t id_len)
+{
+	u8 cur_id_type = 0xff;
+	u8 cur_id_size = 0;
+	const unsigned char *d, *cur_id_str;
+	const struct scsi_vpd *vpd_pg83;
+	int id_size = -EINVAL;
+
+	rcu_read_lock();
+	vpd_pg83 = rcu_dereference(sdev->vpd_pg83);
+	if (!vpd_pg83) {
+		rcu_read_unlock();
+		return -ENXIO;
+	}
+
+	/*
+	 * Look for the correct descriptor.
+	 * Order of preference for lun descriptor:
+	 * - SCSI name string
+	 * - NAA IEEE Registered Extended
+	 * - EUI-64 based 16-byte
+	 * - EUI-64 based 12-byte
+	 * - NAA IEEE Registered
+	 * - NAA IEEE Extended
+	 * - T10 Vendor ID
+	 * as longer descriptors reduce the likelyhood
+	 * of identification clashes.
+	 */
+
+	/* The id string must be at least 20 bytes + terminating NULL byte */
+	if (id_len < 21) {
+		rcu_read_unlock();
+		return -EINVAL;
+	}
+
+	memset(id, 0, id_len);
+	d = vpd_pg83->data + 4;
+	while (d < vpd_pg83->data + vpd_pg83->len) {
+		/* Skip designators not referring to the LUN */
+		if ((d[1] & 0x30) != 0x00)
+			goto next_desig;
+
+		switch (d[1] & 0xf) {
+		case 0x1:
+			/* T10 Vendor ID */
+			if (cur_id_size > d[3])
+				break;
+			/* Prefer anything */
+			if (cur_id_type > 0x01 && cur_id_type != 0xff)
+				break;
+			cur_id_size = d[3];
+			if (cur_id_size + 4 > id_len)
+				cur_id_size = id_len - 4;
+			cur_id_str = d + 4;
+			cur_id_type = d[1] & 0xf;
+			id_size = snprintf(id, id_len, "t10.%*pE",
+					   cur_id_size, cur_id_str);
+			break;
+		case 0x2:
+			/* EUI-64 */
+			if (cur_id_size > d[3])
+				break;
+			/* Prefer NAA IEEE Registered Extended */
+			if (cur_id_type == 0x3 &&
+			    cur_id_size == d[3])
+				break;
+			cur_id_size = d[3];
+			cur_id_str = d + 4;
+			cur_id_type = d[1] & 0xf;
+			switch (cur_id_size) {
+			case 8:
+				id_size = snprintf(id, id_len,
+						   "eui.%8phN",
+						   cur_id_str);
+				break;
+			case 12:
+				id_size = snprintf(id, id_len,
+						   "eui.%12phN",
+						   cur_id_str);
+				break;
+			case 16:
+				id_size = snprintf(id, id_len,
+						   "eui.%16phN",
+						   cur_id_str);
+				break;
+			default:
+				cur_id_size = 0;
+				break;
+			}
+			break;
+		case 0x3:
+			/* NAA */
+			if (cur_id_size > d[3])
+				break;
+			cur_id_size = d[3];
+			cur_id_str = d + 4;
+			cur_id_type = d[1] & 0xf;
+			switch (cur_id_size) {
+			case 8:
+				id_size = snprintf(id, id_len,
+						   "naa.%8phN",
+						   cur_id_str);
+				break;
+			case 16:
+				id_size = snprintf(id, id_len,
+						   "naa.%16phN",
+						   cur_id_str);
+				break;
+			default:
+				cur_id_size = 0;
+				break;
+			}
+			break;
+		case 0x8:
+			/* SCSI name string */
+			if (cur_id_size + 4 > d[3])
+				break;
+			/* Prefer others for truncated descriptor */
+			if (cur_id_size && d[3] > id_len)
+				break;
+			cur_id_size = id_size = d[3];
+			cur_id_str = d + 4;
+			cur_id_type = d[1] & 0xf;
+			if (cur_id_size >= id_len)
+				cur_id_size = id_len - 1;
+			memcpy(id, cur_id_str, cur_id_size);
+			/* Decrease priority for truncated descriptor */
+			if (cur_id_size != id_size)
+				cur_id_size = 6;
+			break;
+		default:
+			break;
+		}
+next_desig:
+		d += d[3] + 4;
+	}
+	rcu_read_unlock();
+
+	return id_size;
+}
+EXPORT_SYMBOL(scsi_vpd_lun_id);
+
+/*
+ * scsi_vpd_tpg_id - return a target port group identifier
+ * @sdev: SCSI device
+ *
+ * Returns the Target Port Group identifier from the information
+ * froom VPD page 0x83 of the device.
+ *
+ * Returns the identifier or error on failure.
+ */
+int scsi_vpd_tpg_id(struct scsi_device *sdev, int *rel_id)
+{
+	const unsigned char *d;
+	const struct scsi_vpd *vpd_pg83;
+	int group_id = -EAGAIN, rel_port = -1;
+
+	rcu_read_lock();
+	vpd_pg83 = rcu_dereference(sdev->vpd_pg83);
+	if (!vpd_pg83) {
+		rcu_read_unlock();
+		return -ENXIO;
+	}
+
+	d = vpd_pg83->data + 4;
+	while (d < vpd_pg83->data + vpd_pg83->len) {
+		switch (d[1] & 0xf) {
+		case 0x4:
+			/* Relative target port */
+			rel_port = get_unaligned_be16(&d[6]);
+			break;
+		case 0x5:
+			/* Target port group */
+			group_id = get_unaligned_be16(&d[6]);
+			break;
+		default:
+			break;
+		}
+		d += d[3] + 4;
+	}
+	rcu_read_unlock();
+
+	if (group_id >= 0 && rel_id && rel_port != -1)
+		*rel_id = rel_port;
+
+	return group_id;
+}
+EXPORT_SYMBOL(scsi_vpd_tpg_id);

src/fs/block_dev.c

+/*
+ *  linux/fs/block_dev.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2001  Andrea Arcangeli <andrea@suse.de> SuSE
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/fcntl.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/major.h>
+#include <linux/device_cgroup.h>
+#include <linux/highmem.h>
+#include <linux/blkdev.h>
+#include <linux/backing-dev.h>
+#include <linux/module.h>
+#include <linux/blkpg.h>
+#include <linux/magic.h>
+#include <linux/dax.h>
+#include <linux/buffer_head.h>
+#include <linux/swap.h>
+#include <linux/pagevec.h>
+#include <linux/writeback.h>
+#include <linux/mpage.h>
+#include <linux/mount.h>
+#include <linux/uio.h>
+#include <linux/namei.h>
+#include <linux/log2.h>
+#include <linux/cleancache.h>
+#include <linux/dax.h>
+#include <linux/badblocks.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/falloc.h>
+#include <linux/uaccess.h>
+#include "internal.h"
+
+struct bdev_inode {
+	struct block_device bdev;
+	struct inode vfs_inode;
+};
+
+static const struct address_space_operations def_blk_aops;
+
+static inline struct bdev_inode *BDEV_I(struct inode *inode)
+{
+	return container_of(inode, struct bdev_inode, vfs_inode);
+}
+
+struct block_device *I_BDEV(struct inode *inode)
+{
+	return &BDEV_I(inode)->bdev;
+}
+EXPORT_SYMBOL(I_BDEV);
+
+static void bdev_write_inode(struct block_device *bdev)
+{
+	struct inode *inode = bdev->bd_inode;
+	int ret;
+
+	spin_lock(&inode->i_lock);
+	while (inode->i_state & I_DIRTY) {
+		spin_unlock(&inode->i_lock);
+		ret = write_inode_now(inode, true);
+		if (ret) {
+			char name[BDEVNAME_SIZE];
+			pr_warn_ratelimited("VFS: Dirty inode writeback failed "
+					    "for block device %s (err=%d).\n",
+					    bdevname(bdev, name), ret);
+		}
+		spin_lock(&inode->i_lock);
+	}
+	spin_unlock(&inode->i_lock);
+}
+
+/* Kill _all_ buffers and pagecache , dirty or not.. */
+void kill_bdev(struct block_device *bdev)
+{
+	struct address_space *mapping = bdev->bd_inode->i_mapping;
+
+	if (mapping->nrpages == 0 && mapping->nrexceptional == 0)
+		return;
+
+	invalidate_bh_lrus();
+	truncate_inode_pages(mapping, 0);
+}	
+EXPORT_SYMBOL(kill_bdev);
+
+/* Invalidate clean unused buffers and pagecache. */
+void invalidate_bdev(struct block_device *bdev)
+{
+	struct address_space *mapping = bdev->bd_inode->i_mapping;
+
+	if (mapping->nrpages) {
+		invalidate_bh_lrus();
+		lru_add_drain_all();	/* make sure all lru add caches are flushed */
+		invalidate_mapping_pages(mapping, 0, -1);
+	}
+	/* 99% of the time, we don't need to flush the cleancache on the bdev.
+	 * But, for the strange corners, lets be cautious
+	 */
+	cleancache_invalidate_inode(mapping);
+}
+EXPORT_SYMBOL(invalidate_bdev);
+
+int set_blocksize(struct block_device *bdev, int size)
+{
+	/* Size must be a power of two, and between 512 and PAGE_SIZE */
+	if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
+		return -EINVAL;
+
+	/* Size cannot be smaller than the size supported by the device */
+	if (size < bdev_logical_block_size(bdev))
+		return -EINVAL;
+
+	/* Don't change the size if it is same as current */
+	if (bdev->bd_block_size != size) {
+		sync_blockdev(bdev);
+		bdev->bd_block_size = size;
+		bdev->bd_inode->i_blkbits = blksize_bits(size);
+		kill_bdev(bdev);
+	}
+	return 0;
+}
+
+EXPORT_SYMBOL(set_blocksize);
+
+int sb_set_blocksize(struct super_block *sb, int size)
+{
+	if (set_blocksize(sb->s_bdev, size))
+		return 0;
+	/* If we get here, we know size is power of two
+	 * and it's value is between 512 and PAGE_SIZE */
+	sb->s_blocksize = size;
+	sb->s_blocksize_bits = blksize_bits(size);
+	return sb->s_blocksize;
+}
+
+EXPORT_SYMBOL(sb_set_blocksize);
+
+int sb_min_blocksize(struct super_block *sb, int size)
+{
+	int minsize = bdev_logical_block_size(sb->s_bdev);
+	if (size < minsize)
+		size = minsize;
+	return sb_set_blocksize(sb, size);
+}
+
+EXPORT_SYMBOL(sb_min_blocksize);
+
+static int
+blkdev_get_block(struct inode *inode, sector_t iblock,
+		struct buffer_head *bh, int create)
+{
+	bh->b_bdev = I_BDEV(inode);
+	bh->b_blocknr = iblock;
+	set_buffer_mapped(bh);
+	return 0;
+}
+
+static struct inode *bdev_file_inode(struct file *file)
+{
+	return file->f_mapping->host;
+}
+
+static unsigned int dio_bio_write_op(struct kiocb *iocb)
+{
+	unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
+
+	/* avoid the need for a I/O completion work item */
+	if (iocb->ki_flags & IOCB_DSYNC)
+		op |= REQ_FUA;
+	return op;
+}
+
+#define DIO_INLINE_BIO_VECS 4
+
+static void blkdev_bio_end_io_simple(struct bio *bio)
+{
+	struct task_struct *waiter = bio->bi_private;
+
+	WRITE_ONCE(bio->bi_private, NULL);
+	wake_up_process(waiter);
+}
+
+static ssize_t
+__blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
+		int nr_pages)
+{
+	struct file *file = iocb->ki_filp;
+	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
+	struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs, *bvec;
+	loff_t pos = iocb->ki_pos;
+	bool should_dirty = false;
+	struct bio bio;
+	ssize_t ret;
+	blk_qc_t qc;
+	int i;
+
+	if ((pos | iov_iter_alignment(iter)) &
+	    (bdev_logical_block_size(bdev) - 1))
+		return -EINVAL;
+
+	if (nr_pages <= DIO_INLINE_BIO_VECS)
+		vecs = inline_vecs;
+	else {
+		vecs = kmalloc_array(nr_pages, sizeof(struct bio_vec),
+				     GFP_KERNEL);
+		if (!vecs)
+			return -ENOMEM;
+	}
+
+	bio_init(&bio, vecs, nr_pages);
+	bio_set_dev(&bio, bdev);
+	bio.bi_iter.bi_sector = pos >> 9;
+	bio.bi_write_hint = iocb->ki_hint;
+	bio.bi_private = current;
+	bio.bi_end_io = blkdev_bio_end_io_simple;
+	bio.bi_ioprio = iocb->ki_ioprio;
+
+	ret = bio_iov_iter_get_pages(&bio, iter);
+	if (unlikely(ret))
+		goto out;
+	ret = bio.bi_iter.bi_size;
+
+	if (iov_iter_rw(iter) == READ) {
+		bio.bi_opf = REQ_OP_READ;
+		if (iter_is_iovec(iter))
+			should_dirty = true;
+	} else {
+		bio.bi_opf = dio_bio_write_op(iocb);
+		task_io_account_write(ret);
+	}
+
+	qc = submit_bio(&bio);
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (!READ_ONCE(bio.bi_private))
+			break;
+		if (!(iocb->ki_flags & IOCB_HIPRI) ||
+		    !blk_poll(bdev_get_queue(bdev), qc))
+			io_schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+
+	bio_for_each_segment_all(bvec, &bio, i) {
+		if (should_dirty && !PageCompound(bvec->bv_page))
+			set_page_dirty_lock(bvec->bv_page);
+		put_page(bvec->bv_page);
+	}
+
+	if (unlikely(bio.bi_status))
+		ret = blk_status_to_errno(bio.bi_status);
+
+out:
+	if (vecs != inline_vecs)
+		kfree(vecs);
+
+	bio_uninit(&bio);
+
+	return ret;
+}
+
+struct blkdev_dio {
+	union {
+		struct kiocb		*iocb;
+		struct task_struct	*waiter;
+	};
+	size_t			size;
+	atomic_t		ref;
+	bool			multi_bio : 1;
+	bool			should_dirty : 1;
+	bool			is_sync : 1;
+	struct bio		bio;
+};
+
+static struct bio_set blkdev_dio_pool;
+
+static void blkdev_bio_end_io(struct bio *bio)
+{
+	struct blkdev_dio *dio = bio->bi_private;
+	bool should_dirty = dio->should_dirty;
+
+	if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) {
+		if (bio->bi_status && !dio->bio.bi_status)
+			dio->bio.bi_status = bio->bi_status;
+	} else {
+		if (!dio->is_sync) {
+			struct kiocb *iocb = dio->iocb;
+			ssize_t ret;
+
+			if (likely(!dio->bio.bi_status)) {
+				ret = dio->size;
+				iocb->ki_pos += ret;
+			} else {
+				ret = blk_status_to_errno(dio->bio.bi_status);
+			}
+
+			dio->iocb->ki_complete(iocb, ret, 0);
+			bio_put(&dio->bio);
+		} else {
+			struct task_struct *waiter = dio->waiter;
+
+			WRITE_ONCE(dio->waiter, NULL);
+			wake_up_process(waiter);
+		}
+	}
+
+	if (should_dirty) {
+		bio_check_pages_dirty(bio);
+	} else {
+		struct bio_vec *bvec;
+		int i;
+
+		bio_for_each_segment_all(bvec, bio, i)
+			put_page(bvec->bv_page);
+		bio_put(bio);
+	}
+}
+
+static ssize_t
+__blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = bdev_file_inode(file);
+	struct block_device *bdev = I_BDEV(inode);
+	struct blk_plug plug;
+	struct blkdev_dio *dio;
+	struct bio *bio;
+	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
+	loff_t pos = iocb->ki_pos;
+	blk_qc_t qc = BLK_QC_T_NONE;
+	int ret = 0;
+
+	if ((pos | iov_iter_alignment(iter)) &
+	    (bdev_logical_block_size(bdev) - 1))
+		return -EINVAL;
+
+	bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool);
+	bio_get(bio); /* extra ref for the completion handler */
+
+	dio = container_of(bio, struct blkdev_dio, bio);
+	dio->is_sync = is_sync = is_sync_kiocb(iocb);
+	if (dio->is_sync)
+		dio->waiter = current;
+	else
+		dio->iocb = iocb;
+
+	dio->size = 0;
+	dio->multi_bio = false;
+	dio->should_dirty = is_read && (iter->type == ITER_IOVEC);
+
+	blk_start_plug(&plug);
+	for (;;) {
+		bio_set_dev(bio, bdev);
+		bio->bi_iter.bi_sector = pos >> 9;
+		bio->bi_write_hint = iocb->ki_hint;
+		bio->bi_private = dio;
+		bio->bi_end_io = blkdev_bio_end_io;
+		bio->bi_ioprio = iocb->ki_ioprio;
+
+		ret = bio_iov_iter_get_pages(bio, iter);
+		if (unlikely(ret)) {
+			bio->bi_status = BLK_STS_IOERR;
+			bio_endio(bio);
+			break;
+		}
+
+		if (is_read) {
+			bio->bi_opf = REQ_OP_READ;
+			if (dio->should_dirty)
+				bio_set_pages_dirty(bio);
+		} else {
+			bio->bi_opf = dio_bio_write_op(iocb);
+			task_io_account_write(bio->bi_iter.bi_size);
+		}
+
+		dio->size += bio->bi_iter.bi_size;
+		pos += bio->bi_iter.bi_size;
+
+		nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES);
+		if (!nr_pages) {
+			qc = submit_bio(bio);
+			break;
+		}
+
+		if (!dio->multi_bio) {
+			dio->multi_bio = true;
+			atomic_set(&dio->ref, 2);
+		} else {
+			atomic_inc(&dio->ref);
+		}
+
+		submit_bio(bio);
+		bio = bio_alloc(GFP_KERNEL, nr_pages);
+	}
+	blk_finish_plug(&plug);
+
+	if (!is_sync)
+		return -EIOCBQUEUED;
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (!READ_ONCE(dio->waiter))
+			break;
+
+		if (!(iocb->ki_flags & IOCB_HIPRI) ||
+		    !blk_poll(bdev_get_queue(bdev), qc))
+			io_schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+
+	if (!ret)
+		ret = blk_status_to_errno(dio->bio.bi_status);
+	if (likely(!ret))
+		ret = dio->size;
+
+	bio_put(&dio->bio);
+	return ret;
+}
+
+static ssize_t
+blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+{
+	int nr_pages;
+
+	nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES + 1);
+	if (!nr_pages)
+		return 0;
+	if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_PAGES)
+		return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
+
+	return __blkdev_direct_IO(iocb, iter, min(nr_pages, BIO_MAX_PAGES));
+}
+
+static __init int blkdev_init(void)
+{
+	return bioset_init(&blkdev_dio_pool, 4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS);
+}
+module_init(blkdev_init);
+
+int __sync_blockdev(struct block_device *bdev, int wait)
+{
+	if (!bdev)
+		return 0;
+	if (!wait)
+		return filemap_flush(bdev->bd_inode->i_mapping);
+	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
+}
+
+/*
+ * Write out and wait upon all the dirty data associated with a block
+ * device via its mapping.  Does not take the superblock lock.
+ */
+int sync_blockdev(struct block_device *bdev)
+{
+	return __sync_blockdev(bdev, 1);
+}
+EXPORT_SYMBOL(sync_blockdev);
+
+/*
+ * Write out and wait upon all dirty data associated with this
+ * device.   Filesystem data as well as the underlying block
+ * device.  Takes the superblock lock.
+ */
+int fsync_bdev(struct block_device *bdev)
+{
+	struct super_block *sb = get_super(bdev);
+	if (sb) {
+		int res = sync_filesystem(sb);
+		drop_super(sb);
+		return res;
+	}
+	return sync_blockdev(bdev);
+}
+EXPORT_SYMBOL(fsync_bdev);
+
+/**
+ * freeze_bdev  --  lock a filesystem and force it into a consistent state
+ * @bdev:	blockdevice to lock
+ *
+ * If a superblock is found on this device, we take the s_umount semaphore
+ * on it to make sure nobody unmounts until the snapshot creation is done.
+ * The reference counter (bd_fsfreeze_count) guarantees that only the last
+ * unfreeze process can unfreeze the frozen filesystem actually when multiple
+ * freeze requests arrive simultaneously. It counts up in freeze_bdev() and
+ * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze
+ * actually.
+ */
+struct super_block *freeze_bdev(struct block_device *bdev)
+{
+	struct super_block *sb;
+	int error = 0;
+
+	mutex_lock(&bdev->bd_fsfreeze_mutex);
+	if (++bdev->bd_fsfreeze_count > 1) {
+		/*
+		 * We don't even need to grab a reference - the first call
+		 * to freeze_bdev grab an active reference and only the last
+		 * thaw_bdev drops it.
+		 */
+		sb = get_super(bdev);
+		if (sb)
+			drop_super(sb);
+		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		return sb;
+	}
+
+	sb = get_active_super(bdev);
+	if (!sb)
+		goto out;
+	if (sb->s_op->freeze_super)
+		error = sb->s_op->freeze_super(sb);
+	else
+		error = freeze_super(sb);
+	if (error) {
+		deactivate_super(sb);
+		bdev->bd_fsfreeze_count--;
+		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		return ERR_PTR(error);
+	}
+	deactivate_super(sb);
+ out:
+	sync_blockdev(bdev);
+	mutex_unlock(&bdev->bd_fsfreeze_mutex);
+	return sb;	/* thaw_bdev releases s->s_umount */
+}
+EXPORT_SYMBOL(freeze_bdev);
+
+/**
+ * thaw_bdev  -- unlock filesystem
+ * @bdev:	blockdevice to unlock
+ * @sb:		associated superblock
+ *
+ * Unlocks the filesystem and marks it writeable again after freeze_bdev().
+ */
+int thaw_bdev(struct block_device *bdev, struct super_block *sb)
+{
+	int error = -EINVAL;
+
+	mutex_lock(&bdev->bd_fsfreeze_mutex);
+	if (!bdev->bd_fsfreeze_count)
+		goto out;
+
+	error = 0;
+	if (--bdev->bd_fsfreeze_count > 0)
+		goto out;
+
+	if (!sb)
+		goto out;
+
+	if (sb->s_op->thaw_super)
+		error = sb->s_op->thaw_super(sb);
+	else
+		error = thaw_super(sb);
+	if (error)
+		bdev->bd_fsfreeze_count++;
+out:
+	mutex_unlock(&bdev->bd_fsfreeze_mutex);
+	return error;
+}
+EXPORT_SYMBOL(thaw_bdev);
+
+static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
+{
+	return block_write_full_page(page, blkdev_get_block, wbc);
+}
+
+static int blkdev_readpage(struct file * file, struct page * page)
+{
+	return block_read_full_page(page, blkdev_get_block);
+}
+
+static int blkdev_readpages(struct file *file, struct address_space *mapping,
+			struct list_head *pages, unsigned nr_pages)
+{
+	return mpage_readpages(mapping, pages, nr_pages, blkdev_get_block);
+}
+
+static int blkdev_write_begin(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata)
+{
+	return block_write_begin(mapping, pos, len, flags, pagep,
+				 blkdev_get_block);
+}
+
+static int blkdev_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
+{
+	int ret;
+	ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+	unlock_page(page);
+	put_page(page);
+
+	return ret;
+}
+
+/*
+ * private llseek:
+ * for a block special file file_inode(file)->i_size is zero
+ * so we compute the size by hand (just as in block_read/write above)
+ */
+static loff_t block_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *bd_inode = bdev_file_inode(file);
+	loff_t retval;
+
+	inode_lock(bd_inode);
+	retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode));
+	inode_unlock(bd_inode);
+	return retval;
+}
+	
+int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
+{
+	struct inode *bd_inode = bdev_file_inode(filp);
+	struct block_device *bdev = I_BDEV(bd_inode);
+	int error;
+	
+	error = file_write_and_wait_range(filp, start, end);
+	if (error)
+		return error;
+
+	/*
+	 * There is no need to serialise calls to blkdev_issue_flush with
+	 * i_mutex and doing so causes performance issues with concurrent
+	 * O_SYNC writers to a block device.
+	 */
+	error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL);
+	if (error == -EOPNOTSUPP)
+		error = 0;
+
+	return error;
+}
+EXPORT_SYMBOL(blkdev_fsync);
+
+/**
+ * bdev_read_page() - Start reading a page from a block device
+ * @bdev: The device to read the page from
+ * @sector: The offset on the device to read the page to (need not be aligned)
+ * @page: The page to read
+ *
+ * On entry, the page should be locked.  It will be unlocked when the page
+ * has been read.  If the block driver implements rw_page synchronously,
+ * that will be true on exit from this function, but it need not be.
+ *
+ * Errors returned by this function are usually "soft", eg out of memory, or
+ * queue full; callers should try a different route to read this page rather
+ * than propagate an error back up the stack.
+ *
+ * Return: negative errno if an error occurs, 0 if submission was successful.
+ */
+int bdev_read_page(struct block_device *bdev, sector_t sector,
+			struct page *page)
+{
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+	int result = -EOPNOTSUPP;
+
+	if (!ops->rw_page || bdev_get_integrity(bdev))
+		return result;
+
+	result = blk_queue_enter(bdev->bd_queue, 0);
+	if (result)
+		return result;
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_READ);
+	blk_queue_exit(bdev->bd_queue);
+	return result;
+}
+EXPORT_SYMBOL_GPL(bdev_read_page);
+
+/**
+ * bdev_write_page() - Start writing a page to a block device
+ * @bdev: The device to write the page to
+ * @sector: The offset on the device to write the page to (need not be aligned)
+ * @page: The page to write
+ * @wbc: The writeback_control for the write
+ *
+ * On entry, the page should be locked and not currently under writeback.
+ * On exit, if the write started successfully, the page will be unlocked and
+ * under writeback.  If the write failed already (eg the driver failed to
+ * queue the page to the device), the page will still be locked.  If the
+ * caller is a ->writepage implementation, it will need to unlock the page.
+ *
+ * Errors returned by this function are usually "soft", eg out of memory, or
+ * queue full; callers should try a different route to write this page rather
+ * than propagate an error back up the stack.
+ *
+ * Return: negative errno if an error occurs, 0 if submission was successful.
+ */
+int bdev_write_page(struct block_device *bdev, sector_t sector,
+			struct page *page, struct writeback_control *wbc)
+{
+	int result;
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+
+	if (!ops->rw_page || bdev_get_integrity(bdev))
+		return -EOPNOTSUPP;
+	result = blk_queue_enter(bdev->bd_queue, 0);
+	if (result)
+		return result;
+
+	set_page_writeback(page);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_WRITE);
+	if (result) {
+		end_page_writeback(page);
+	} else {
+		clean_page_buffers(page);
+		unlock_page(page);
+	}
+	blk_queue_exit(bdev->bd_queue);
+	return result;
+}
+EXPORT_SYMBOL_GPL(bdev_write_page);
+
+/*
+ * pseudo-fs
+ */
+
+static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
+static struct kmem_cache * bdev_cachep __read_mostly;
+
+static struct inode *bdev_alloc_inode(struct super_block *sb)
+{
+	struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
+	if (!ei)
+		return NULL;
+	return &ei->vfs_inode;
+}
+
+static void bdev_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	struct bdev_inode *bdi = BDEV_I(inode);
+
+	kmem_cache_free(bdev_cachep, bdi);
+}
+
+static void bdev_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, bdev_i_callback);
+}
+
+static void init_once(void *foo)
+{
+	struct bdev_inode *ei = (struct bdev_inode *) foo;
+	struct block_device *bdev = &ei->bdev;
+
+	memset(bdev, 0, sizeof(*bdev));
+	mutex_init(&bdev->bd_mutex);
+	INIT_LIST_HEAD(&bdev->bd_list);
+#ifdef CONFIG_SYSFS
+	INIT_LIST_HEAD(&bdev->bd_holder_disks);
+#endif
+	bdev->bd_bdi = &noop_backing_dev_info;
+	inode_init_once(&ei->vfs_inode);
+	/* Initialize mutex for freeze. */
+	mutex_init(&bdev->bd_fsfreeze_mutex);
+}
+
+static void bdev_evict_inode(struct inode *inode)
+{
+	struct block_device *bdev = &BDEV_I(inode)->bdev;
+	truncate_inode_pages_final(&inode->i_data);
+	invalidate_inode_buffers(inode); /* is it needed here? */
+	clear_inode(inode);
+	spin_lock(&bdev_lock);
+	list_del_init(&bdev->bd_list);
+	spin_unlock(&bdev_lock);
+	/* Detach inode from wb early as bdi_put() may free bdi->wb */
+	inode_detach_wb(inode);
+	if (bdev->bd_bdi != &noop_backing_dev_info) {
+		bdi_put(bdev->bd_bdi);
+		bdev->bd_bdi = &noop_backing_dev_info;
+	}
+}
+
+static const struct super_operations bdev_sops = {
+	.statfs = simple_statfs,
+	.alloc_inode = bdev_alloc_inode,
+	.destroy_inode = bdev_destroy_inode,
+	.drop_inode = generic_delete_inode,
+	.evict_inode = bdev_evict_inode,
+};
+
+static struct dentry *bd_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data)
+{
+	struct dentry *dent;
+	dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
+	if (!IS_ERR(dent))
+		dent->d_sb->s_iflags |= SB_I_CGROUPWB;
+	return dent;
+}
+
+static struct file_system_type bd_type = {
+	.name		= "bdev",
+	.mount		= bd_mount,
+	.kill_sb	= kill_anon_super,
+};
+
+struct super_block *blockdev_superblock __read_mostly;
+EXPORT_SYMBOL_GPL(blockdev_superblock);
+
+void __init bdev_cache_init(void)
+{
+	int err;
+	static struct vfsmount *bd_mnt;
+
+	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
+			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
+				SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC),
+			init_once);
+	err = register_filesystem(&bd_type);
+	if (err)
+		panic("Cannot register bdev pseudo-fs");
+	bd_mnt = kern_mount(&bd_type);
+	if (IS_ERR(bd_mnt))
+		panic("Cannot create bdev pseudo-fs");
+	blockdev_superblock = bd_mnt->mnt_sb;   /* For writeback */
+}
+
+/*
+ * Most likely _very_ bad one - but then it's hardly critical for small
+ * /dev and can be fixed when somebody will need really large one.
+ * Keep in mind that it will be fed through icache hash function too.
+ */
+static inline unsigned long hash(dev_t dev)
+{
+	return MAJOR(dev)+MINOR(dev);
+}
+
+static int bdev_test(struct inode *inode, void *data)
+{
+	return BDEV_I(inode)->bdev.bd_dev == *(dev_t *)data;
+}
+
+static int bdev_set(struct inode *inode, void *data)
+{
+	BDEV_I(inode)->bdev.bd_dev = *(dev_t *)data;
+	return 0;
+}
+
+static LIST_HEAD(all_bdevs);
+
+/*
+ * If there is a bdev inode for this device, unhash it so that it gets evicted
+ * as soon as last inode reference is dropped.
+ */
+void bdev_unhash_inode(dev_t dev)
+{
+	struct inode *inode;
+
+	inode = ilookup5(blockdev_superblock, hash(dev), bdev_test, &dev);
+	if (inode) {
+		remove_inode_hash(inode);
+		iput(inode);
+	}
+}
+
+struct block_device *bdget(dev_t dev)
+{
+	struct block_device *bdev;
+	struct inode *inode;
+
+	inode = iget5_locked(blockdev_superblock, hash(dev),
+			bdev_test, bdev_set, &dev);
+
+	if (!inode)
+		return NULL;
+
+	bdev = &BDEV_I(inode)->bdev;
+
+	if (inode->i_state & I_NEW) {
+		bdev->bd_contains = NULL;
+		bdev->bd_super = NULL;
+		bdev->bd_inode = inode;
+		bdev->bd_block_size = i_blocksize(inode);
+		bdev->bd_part_count = 0;
+		bdev->bd_invalidated = 0;
+		inode->i_mode = S_IFBLK;
+		inode->i_rdev = dev;
+		inode->i_bdev = bdev;
+		inode->i_data.a_ops = &def_blk_aops;
+		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
+		spin_lock(&bdev_lock);
+		list_add(&bdev->bd_list, &all_bdevs);
+		spin_unlock(&bdev_lock);
+		unlock_new_inode(inode);
+	}
+	return bdev;
+}
+
+EXPORT_SYMBOL(bdget);
+
+/**
+ * bdgrab -- Grab a reference to an already referenced block device
+ * @bdev:	Block device to grab a reference to.
+ */
+struct block_device *bdgrab(struct block_device *bdev)
+{
+	ihold(bdev->bd_inode);
+	return bdev;
+}
+EXPORT_SYMBOL(bdgrab);
+
+long nr_blockdev_pages(void)
+{
+	struct block_device *bdev;
+	long ret = 0;
+	spin_lock(&bdev_lock);
+	list_for_each_entry(bdev, &all_bdevs, bd_list) {
+		ret += bdev->bd_inode->i_mapping->nrpages;
+	}
+	spin_unlock(&bdev_lock);
+	return ret;
+}
+
+void bdput(struct block_device *bdev)
+{
+	iput(bdev->bd_inode);
+}
+
+EXPORT_SYMBOL(bdput);
+ 
+static struct block_device *bd_acquire(struct inode *inode)
+{
+	struct block_device *bdev;
+
+	spin_lock(&bdev_lock);
+	bdev = inode->i_bdev;
+	if (bdev && !inode_unhashed(bdev->bd_inode)) {
+		bdgrab(bdev);
+		spin_unlock(&bdev_lock);
+		return bdev;
+	}
+	spin_unlock(&bdev_lock);
+
+	/*
+	 * i_bdev references block device inode that was already shut down
+	 * (corresponding device got removed).  Remove the reference and look
+	 * up block device inode again just in case new device got
+	 * reestablished under the same device number.
+	 */
+	if (bdev)
+		bd_forget(inode);
+
+	bdev = bdget(inode->i_rdev);
+	if (bdev) {
+		spin_lock(&bdev_lock);
+		if (!inode->i_bdev) {
+			/*
+			 * We take an additional reference to bd_inode,
+			 * and it's released in clear_inode() of inode.
+			 * So, we can access it via ->i_mapping always
+			 * without igrab().
+			 */
+			bdgrab(bdev);
+			inode->i_bdev = bdev;
+			inode->i_mapping = bdev->bd_inode->i_mapping;
+		}
+		spin_unlock(&bdev_lock);
+	}
+	return bdev;
+}
+
+/* Call when you free inode */
+
+void bd_forget(struct inode *inode)
+{
+	struct block_device *bdev = NULL;
+
+	spin_lock(&bdev_lock);
+	if (!sb_is_blkdev_sb(inode->i_sb))
+		bdev = inode->i_bdev;
+	inode->i_bdev = NULL;
+	inode->i_mapping = &inode->i_data;
+	spin_unlock(&bdev_lock);
+
+	if (bdev)
+		bdput(bdev);
+}
+
+/**
+ * bd_may_claim - test whether a block device can be claimed
+ * @bdev: block device of interest
+ * @whole: whole block device containing @bdev, may equal @bdev
+ * @holder: holder trying to claim @bdev
+ *
+ * Test whether @bdev can be claimed by @holder.
+ *
+ * CONTEXT:
+ * spin_lock(&bdev_lock).
+ *
+ * RETURNS:
+ * %true if @bdev can be claimed, %false otherwise.
+ */
+static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
+			 void *holder)
+{
+	if (bdev->bd_holder == holder)
+		return true;	 /* already a holder */
+	else if (bdev->bd_holder != NULL)
+		return false; 	 /* held by someone else */
+	else if (whole == bdev)
+		return true;  	 /* is a whole device which isn't held */
+
+	else if (whole->bd_holder == bd_may_claim)
+		return true; 	 /* is a partition of a device that is being partitioned */
+	else if (whole->bd_holder != NULL)
+		return false;	 /* is a partition of a held device */
+	else
+		return true;	 /* is a partition of an un-held device */
+}
+
+/**
+ * bd_prepare_to_claim - prepare to claim a block device
+ * @bdev: block device of interest
+ * @whole: the whole device containing @bdev, may equal @bdev
+ * @holder: holder trying to claim @bdev
+ *
+ * Prepare to claim @bdev.  This function fails if @bdev is already
+ * claimed by another holder and waits if another claiming is in
+ * progress.  This function doesn't actually claim.  On successful
+ * return, the caller has ownership of bd_claiming and bd_holder[s].
+ *
+ * CONTEXT:
+ * spin_lock(&bdev_lock).  Might release bdev_lock, sleep and regrab
+ * it multiple times.
+ *
+ * RETURNS:
+ * 0 if @bdev can be claimed, -EBUSY otherwise.
+ */
+static int bd_prepare_to_claim(struct block_device *bdev,
+			       struct block_device *whole, void *holder)
+{
+retry:
+	/* if someone else claimed, fail */
+	if (!bd_may_claim(bdev, whole, holder))
+		return -EBUSY;
+
+	/* if claiming is already in progress, wait for it to finish */
+	if (whole->bd_claiming) {
+		wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0);
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
+		spin_unlock(&bdev_lock);
+		schedule();
+		finish_wait(wq, &wait);
+		spin_lock(&bdev_lock);
+		goto retry;
+	}
+
+	/* yay, all mine */
+	return 0;
+}
+
+static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno)
+{
+	struct gendisk *disk = get_gendisk(bdev->bd_dev, partno);
+
+	if (!disk)
+		return NULL;
+	/*
+	 * Now that we hold gendisk reference we make sure bdev we looked up is
+	 * not stale. If it is, it means device got removed and created before
+	 * we looked up gendisk and we fail open in such case. Associating
+	 * unhashed bdev with newly created gendisk could lead to two bdevs
+	 * (and thus two independent caches) being associated with one device
+	 * which is bad.
+	 */
+	if (inode_unhashed(bdev->bd_inode)) {
+		put_disk_and_module(disk);
+		return NULL;
+	}
+	return disk;
+}
+
+/**
+ * bd_start_claiming - start claiming a block device
+ * @bdev: block device of interest
+ * @holder: holder trying to claim @bdev
+ *
+ * @bdev is about to be opened exclusively.  Check @bdev can be opened
+ * exclusively and mark that an exclusive open is in progress.  Each
+ * successful call to this function must be matched with a call to
+ * either bd_finish_claiming() or bd_abort_claiming() (which do not
+ * fail).
+ *
+ * This function is used to gain exclusive access to the block device
+ * without actually causing other exclusive open attempts to fail. It
+ * should be used when the open sequence itself requires exclusive
+ * access but may subsequently fail.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * Pointer to the block device containing @bdev on success, ERR_PTR()
+ * value on failure.
+ */
+static struct block_device *bd_start_claiming(struct block_device *bdev,
+					      void *holder)
+{
+	struct gendisk *disk;
+	struct block_device *whole;
+	int partno, err;
+
+	might_sleep();
+
+	/*
+	 * @bdev might not have been initialized properly yet, look up
+	 * and grab the outer block device the hard way.
+	 */
+	disk = bdev_get_gendisk(bdev, &partno);
+	if (!disk)
+		return ERR_PTR(-ENXIO);
+
+	/*
+	 * Normally, @bdev should equal what's returned from bdget_disk()
+	 * if partno is 0; however, some drivers (floppy) use multiple
+	 * bdev's for the same physical device and @bdev may be one of the
+	 * aliases.  Keep @bdev if partno is 0.  This means claimer
+	 * tracking is broken for those devices but it has always been that
+	 * way.
+	 */
+	if (partno)
+		whole = bdget_disk(disk, 0);
+	else
+		whole = bdgrab(bdev);
+
+	put_disk_and_module(disk);
+	if (!whole)
+		return ERR_PTR(-ENOMEM);
+
+	/* prepare to claim, if successful, mark claiming in progress */
+	spin_lock(&bdev_lock);
+
+	err = bd_prepare_to_claim(bdev, whole, holder);
+	if (err == 0) {
+		whole->bd_claiming = holder;
+		spin_unlock(&bdev_lock);
+		return whole;
+	} else {
+		spin_unlock(&bdev_lock);
+		bdput(whole);
+		return ERR_PTR(err);
+	}
+}
+
+#ifdef CONFIG_SYSFS
+struct bd_holder_disk {
+	struct list_head	list;
+	struct gendisk		*disk;
+	int			refcnt;
+};
+
+static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev,
+						  struct gendisk *disk)
+{
+	struct bd_holder_disk *holder;
+
+	list_for_each_entry(holder, &bdev->bd_holder_disks, list)
+		if (holder->disk == disk)
+			return holder;
+	return NULL;
+}
+
+static int add_symlink(struct kobject *from, struct kobject *to)
+{
+	return sysfs_create_link(from, to, kobject_name(to));
+}
+
+static void del_symlink(struct kobject *from, struct kobject *to)
+{
+	sysfs_remove_link(from, kobject_name(to));
+}
+
+/**
+ * bd_link_disk_holder - create symlinks between holding disk and slave bdev
+ * @bdev: the claimed slave bdev
+ * @disk: the holding disk
+ *
+ * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT.
+ *
+ * This functions creates the following sysfs symlinks.
+ *
+ * - from "slaves" directory of the holder @disk to the claimed @bdev
+ * - from "holders" directory of the @bdev to the holder @disk
+ *
+ * For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is
+ * passed to bd_link_disk_holder(), then:
+ *
+ *   /sys/block/dm-0/slaves/sda --> /sys/block/sda
+ *   /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
+ *
+ * The caller must have claimed @bdev before calling this function and
+ * ensure that both @bdev and @disk are valid during the creation and
+ * lifetime of these symlinks.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
+{
+	struct bd_holder_disk *holder;
+	int ret = 0;
+
+	mutex_lock(&bdev->bd_mutex);
+
+	WARN_ON_ONCE(!bdev->bd_holder);
+
+	/* FIXME: remove the following once add_disk() handles errors */
+	if (WARN_ON(!disk->slave_dir || !bdev->bd_part->holder_dir))
+		goto out_unlock;
+
+	holder = bd_find_holder_disk(bdev, disk);
+	if (holder) {
+		holder->refcnt++;
+		goto out_unlock;
+	}
+
+	holder = kzalloc(sizeof(*holder), GFP_KERNEL);
+	if (!holder) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	INIT_LIST_HEAD(&holder->list);
+	holder->disk = disk;
+	holder->refcnt = 1;
+
+	ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+	if (ret)
+		goto out_free;
+
+	ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
+	if (ret)
+		goto out_del;
+	/*
+	 * bdev could be deleted beneath us which would implicitly destroy
+	 * the holder directory.  Hold on to it.
+	 */
+	kobject_get(bdev->bd_part->holder_dir);
+
+	list_add(&holder->list, &bdev->bd_holder_disks);
+	goto out_unlock;
+
+out_del:
+	del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+out_free:
+	kfree(holder);
+out_unlock:
+	mutex_unlock(&bdev->bd_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(bd_link_disk_holder);
+
+/**
+ * bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder()
+ * @bdev: the calimed slave bdev
+ * @disk: the holding disk
+ *
+ * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT.
+ *
+ * CONTEXT:
+ * Might sleep.
+ */
+void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
+{
+	struct bd_holder_disk *holder;
+
+	mutex_lock(&bdev->bd_mutex);
+
+	holder = bd_find_holder_disk(bdev, disk);
+
+	if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
+		del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+		del_symlink(bdev->bd_part->holder_dir,
+			    &disk_to_dev(disk)->kobj);
+		kobject_put(bdev->bd_part->holder_dir);
+		list_del_init(&holder->list);
+		kfree(holder);
+	}
+
+	mutex_unlock(&bdev->bd_mutex);
+}
+EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
+#endif
+
+/**
+ * flush_disk - invalidates all buffer-cache entries on a disk
+ *
+ * @bdev:      struct block device to be flushed
+ * @kill_dirty: flag to guide handling of dirty inodes
+ *
+ * Invalidates all buffer-cache entries on a disk. It should be called
+ * when a disk has been changed -- either by a media change or online
+ * resize.
+ */
+static void flush_disk(struct block_device *bdev, bool kill_dirty)
+{
+	if (__invalidate_device(bdev, kill_dirty)) {
+		printk(KERN_WARNING "VFS: busy inodes on changed media or "
+		       "resized disk %s\n",
+		       bdev->bd_disk ? bdev->bd_disk->disk_name : "");
+	}
+
+	if (!bdev->bd_disk)
+		return;
+	if (disk_part_scan_enabled(bdev->bd_disk))
+		bdev->bd_invalidated = 1;
+}
+
+/**
+ * check_disk_size_change - checks for disk size change and adjusts bdev size.
+ * @disk: struct gendisk to check
+ * @bdev: struct bdev to adjust.
+ * @verbose: if %true log a message about a size change if there is any
+ *
+ * This routine checks to see if the bdev size does not match the disk size
+ * and adjusts it if it differs. When shrinking the bdev size, its all caches
+ * are freed.
+ */
+void check_disk_size_change(struct gendisk *disk, struct block_device *bdev,
+		bool verbose)
+{
+	loff_t disk_size, bdev_size;
+
+	disk_size = (loff_t)get_capacity(disk) << 9;
+	bdev_size = i_size_read(bdev->bd_inode);
+	if (disk_size != bdev_size) {
+		if (verbose) {
+			printk(KERN_INFO
+			       "%s: detected capacity change from %lld to %lld\n",
+			       disk->disk_name, bdev_size, disk_size);
+		}
+		i_size_write(bdev->bd_inode, disk_size);
+		if (bdev_size > disk_size)
+			flush_disk(bdev, false);
+	}
+}
+
+/**
+ * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
+ * @disk: struct gendisk to be revalidated
+ *
+ * This routine is a wrapper for lower-level driver's revalidate_disk
+ * call-backs.  It is used to do common pre and post operations needed
+ * for all revalidate_disk operations.
+ */
+int revalidate_disk(struct gendisk *disk)
+{
+	struct block_device *bdev;
+	int ret = 0;
+
+	if (disk->fops->revalidate_disk)
+		ret = disk->fops->revalidate_disk(disk);
+	bdev = bdget_disk(disk, 0);
+	if (!bdev)
+		return ret;
+
+	mutex_lock(&bdev->bd_mutex);
+	check_disk_size_change(disk, bdev, ret == 0);
+	bdev->bd_invalidated = 0;
+	mutex_unlock(&bdev->bd_mutex);
+	bdput(bdev);
+	return ret;
+}
+EXPORT_SYMBOL(revalidate_disk);
+
+/*
+ * This routine checks whether a removable media has been changed,
+ * and invalidates all buffer-cache-entries in that case. This
+ * is a relatively slow routine, so we have to try to minimize using
+ * it. Thus it is called only upon a 'mount' or 'open'. This
+ * is the best way of combining speed and utility, I think.
+ * People changing diskettes in the middle of an operation deserve
+ * to lose :-)
+ */
+int check_disk_change(struct block_device *bdev)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	const struct block_device_operations *bdops = disk->fops;
+	unsigned int events;
+
+	events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE |
+				   DISK_EVENT_EJECT_REQUEST);
+	if (!(events & DISK_EVENT_MEDIA_CHANGE))
+		return 0;
+
+	flush_disk(bdev, true);
+	if (bdops->revalidate_disk)
+		bdops->revalidate_disk(bdev->bd_disk);
+	return 1;
+}
+
+EXPORT_SYMBOL(check_disk_change);
+
+void bd_set_size(struct block_device *bdev, loff_t size)
+{
+	unsigned bsize = bdev_logical_block_size(bdev);
+
+	inode_lock(bdev->bd_inode);
+	i_size_write(bdev->bd_inode, size);
+	inode_unlock(bdev->bd_inode);
+	while (bsize < PAGE_SIZE) {
+		if (size & bsize)
+			break;
+		bsize <<= 1;
+	}
+	bdev->bd_block_size = bsize;
+	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
+}
+EXPORT_SYMBOL(bd_set_size);
+
+static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
+
+/*
+ * bd_mutex locking:
+ *
+ *  mutex_lock(part->bd_mutex)
+ *    mutex_lock_nested(whole->bd_mutex, 1)
+ */
+
+static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
+{
+	struct gendisk *disk;
+	int ret;
+	int partno;
+	int perm = 0;
+	bool first_open = false;
+
+	if (mode & FMODE_READ)
+		perm |= MAY_READ;
+	if (mode & FMODE_WRITE)
+		perm |= MAY_WRITE;
+	/*
+	 * hooks: /n/, see "layering violations".
+	 */
+	if (!for_part) {
+		ret = devcgroup_inode_permission(bdev->bd_inode, perm);
+		if (ret != 0) {
+			bdput(bdev);
+			return ret;
+		}
+	}
+
+ restart:
+
+	ret = -ENXIO;
+	disk = bdev_get_gendisk(bdev, &partno);
+	if (!disk)
+		goto out;
+
+	disk_block_events(disk);
+	mutex_lock_nested(&bdev->bd_mutex, for_part);
+	if (!bdev->bd_openers) {
+		first_open = true;
+		bdev->bd_disk = disk;
+		bdev->bd_queue = disk->queue;
+		bdev->bd_contains = bdev;
+		bdev->bd_partno = partno;
+
+		if (!partno) {
+			ret = -ENXIO;
+			bdev->bd_part = disk_get_part(disk, partno);
+			if (!bdev->bd_part)
+				goto out_clear;
+
+			ret = 0;
+			if (disk->fops->open) {
+				ret = disk->fops->open(bdev, mode);
+				if (ret == -ERESTARTSYS) {
+					/* Lost a race with 'disk' being
+					 * deleted, try again.
+					 * See md.c
+					 */
+					disk_put_part(bdev->bd_part);
+					bdev->bd_part = NULL;
+					bdev->bd_disk = NULL;
+					bdev->bd_queue = NULL;
+					mutex_unlock(&bdev->bd_mutex);
+					disk_unblock_events(disk);
+					put_disk_and_module(disk);
+					goto restart;
+				}
+			}
+
+			if (!ret)
+				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
+
+			/*
+			 * If the device is invalidated, rescan partition
+			 * if open succeeded or failed with -ENOMEDIUM.
+			 * The latter is necessary to prevent ghost
+			 * partitions on a removed medium.
+			 */
+			if (bdev->bd_invalidated) {
+				if (!ret)
+					rescan_partitions(disk, bdev);
+				else if (ret == -ENOMEDIUM)
+					invalidate_partitions(disk, bdev);
+			}
+
+			if (ret)
+				goto out_clear;
+		} else {
+			struct block_device *whole;
+			whole = bdget_disk(disk, 0);
+			ret = -ENOMEM;
+			if (!whole)
+				goto out_clear;
+			BUG_ON(for_part);
+			ret = __blkdev_get(whole, mode, 1);
+			if (ret)
+				goto out_clear;
+			bdev->bd_contains = whole;
+			bdev->bd_part = disk_get_part(disk, partno);
+			if (!(disk->flags & GENHD_FL_UP) ||
+			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
+				ret = -ENXIO;
+				goto out_clear;
+			}
+			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
+		}
+
+		if (bdev->bd_bdi == &noop_backing_dev_info)
+			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
+	} else {
+		if (bdev->bd_contains == bdev) {
+			ret = 0;
+			if (bdev->bd_disk->fops->open)
+				ret = bdev->bd_disk->fops->open(bdev, mode);
+			/* the same as first opener case, read comment there */
+			if (bdev->bd_invalidated) {
+				if (!ret)
+					rescan_partitions(bdev->bd_disk, bdev);
+				else if (ret == -ENOMEDIUM)
+					invalidate_partitions(bdev->bd_disk, bdev);
+			}
+			if (ret)
+				goto out_unlock_bdev;
+		}
+	}
+	bdev->bd_openers++;
+	if (for_part)
+		bdev->bd_part_count++;
+	mutex_unlock(&bdev->bd_mutex);
+	disk_unblock_events(disk);
+	/* only one opener holds refs to the module and disk */
+	if (!first_open)
+		put_disk_and_module(disk);
+	return 0;
+
+ out_clear:
+	disk_put_part(bdev->bd_part);
+	bdev->bd_disk = NULL;
+	bdev->bd_part = NULL;
+	bdev->bd_queue = NULL;
+	if (bdev != bdev->bd_contains)
+		__blkdev_put(bdev->bd_contains, mode, 1);
+	bdev->bd_contains = NULL;
+ out_unlock_bdev:
+	mutex_unlock(&bdev->bd_mutex);
+	disk_unblock_events(disk);
+	put_disk_and_module(disk);
+ out:
+	bdput(bdev);
+
+	return ret;
+}
+
+/**
+ * blkdev_get - open a block device
+ * @bdev: block_device to open
+ * @mode: FMODE_* mask
+ * @holder: exclusive holder identifier
+ *
+ * Open @bdev with @mode.  If @mode includes %FMODE_EXCL, @bdev is
+ * open with exclusive access.  Specifying %FMODE_EXCL with %NULL
+ * @holder is invalid.  Exclusive opens may nest for the same @holder.
+ *
+ * On success, the reference count of @bdev is unchanged.  On failure,
+ * @bdev is put.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
+{
+	struct block_device *whole = NULL;
+	int res;
+
+	WARN_ON_ONCE((mode & FMODE_EXCL) && !holder);
+
+	if ((mode & FMODE_EXCL) && holder) {
+		whole = bd_start_claiming(bdev, holder);
+		if (IS_ERR(whole)) {
+			bdput(bdev);
+			return PTR_ERR(whole);
+		}
+	}
+
+	res = __blkdev_get(bdev, mode, 0);
+
+	if (whole) {
+		struct gendisk *disk = whole->bd_disk;
+
+		/* finish claiming */
+		mutex_lock(&bdev->bd_mutex);
+		spin_lock(&bdev_lock);
+
+		if (!res) {
+			BUG_ON(!bd_may_claim(bdev, whole, holder));
+			/*
+			 * Note that for a whole device bd_holders
+			 * will be incremented twice, and bd_holder
+			 * will be set to bd_may_claim before being
+			 * set to holder
+			 */
+			whole->bd_holders++;
+			whole->bd_holder = bd_may_claim;
+			bdev->bd_holders++;
+			bdev->bd_holder = holder;
+		}
+
+		/* tell others that we're done */
+		BUG_ON(whole->bd_claiming != holder);
+		whole->bd_claiming = NULL;
+		wake_up_bit(&whole->bd_claiming, 0);
+
+		spin_unlock(&bdev_lock);
+
+		/*
+		 * Block event polling for write claims if requested.  Any
+		 * write holder makes the write_holder state stick until
+		 * all are released.  This is good enough and tracking
+		 * individual writeable reference is too fragile given the
+		 * way @mode is used in blkdev_get/put().
+		 */
+		if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder &&
+		    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
+			bdev->bd_write_holder = true;
+			disk_block_events(disk);
+		}
+
+		mutex_unlock(&bdev->bd_mutex);
+		bdput(whole);
+	}
+
+	return res;
+}
+EXPORT_SYMBOL(blkdev_get);
+
+/**
+ * blkdev_get_by_path - open a block device by name
+ * @path: path to the block device to open
+ * @mode: FMODE_* mask
+ * @holder: exclusive holder identifier
+ *
+ * Open the blockdevice described by the device file at @path.  @mode
+ * and @holder are identical to blkdev_get().
+ *
+ * On success, the returned block_device has reference count of one.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * Pointer to block_device on success, ERR_PTR(-errno) on failure.
+ */
+struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
+					void *holder)
+{
+	struct block_device *bdev;
+	int err;
+
+	bdev = lookup_bdev(path);
+	if (IS_ERR(bdev))
+		return bdev;
+
+	err = blkdev_get(bdev, mode, holder);
+	if (err)
+		return ERR_PTR(err);
+
+	if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) {
+		blkdev_put(bdev, mode);
+		return ERR_PTR(-EACCES);
+	}
+
+	return bdev;
+}
+EXPORT_SYMBOL(blkdev_get_by_path);
+
+/**
+ * blkdev_get_by_dev - open a block device by device number
+ * @dev: device number of block device to open
+ * @mode: FMODE_* mask
+ * @holder: exclusive holder identifier
+ *
+ * Open the blockdevice described by device number @dev.  @mode and
+ * @holder are identical to blkdev_get().
+ *
+ * Use it ONLY if you really do not have anything better - i.e. when
+ * you are behind a truly sucky interface and all you are given is a
+ * device number.  _Never_ to be used for internal purposes.  If you
+ * ever need it - reconsider your API.
+ *
+ * On success, the returned block_device has reference count of one.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * Pointer to block_device on success, ERR_PTR(-errno) on failure.
+ */
+struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
+{
+	struct block_device *bdev;
+	int err;
+
+	bdev = bdget(dev);
+	if (!bdev)
+		return ERR_PTR(-ENOMEM);
+
+	err = blkdev_get(bdev, mode, holder);
+	if (err)
+		return ERR_PTR(err);
+
+	return bdev;
+}
+EXPORT_SYMBOL(blkdev_get_by_dev);
+
+static int blkdev_open(struct inode * inode, struct file * filp)
+{
+	struct block_device *bdev;
+
+	/*
+	 * Preserve backwards compatibility and allow large file access
+	 * even if userspace doesn't ask for it explicitly. Some mkfs
+	 * binary needs it. We might want to drop this workaround
+	 * during an unstable branch.
+	 */
+	filp->f_flags |= O_LARGEFILE;
+
+	filp->f_mode |= FMODE_NOWAIT;
+
+	if (filp->f_flags & O_NDELAY)
+		filp->f_mode |= FMODE_NDELAY;
+	if (filp->f_flags & O_EXCL)
+		filp->f_mode |= FMODE_EXCL;
+	if ((filp->f_flags & O_ACCMODE) == 3)
+		filp->f_mode |= FMODE_WRITE_IOCTL;
+
+	bdev = bd_acquire(inode);
+	if (bdev == NULL)
+		return -ENOMEM;
+
+	filp->f_mapping = bdev->bd_inode->i_mapping;
+	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
+
+	return blkdev_get(bdev, filp->f_mode, filp);
+}
+
+static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	struct block_device *victim = NULL;
+
+	mutex_lock_nested(&bdev->bd_mutex, for_part);
+	if (for_part)
+		bdev->bd_part_count--;
+
+	if (!--bdev->bd_openers) {
+		WARN_ON_ONCE(bdev->bd_holders);
+		sync_blockdev(bdev);
+		kill_bdev(bdev);
+
+		bdev_write_inode(bdev);
+	}
+	if (bdev->bd_contains == bdev) {
+		if (disk->fops->release)
+			disk->fops->release(disk, mode);
+	}
+	if (!bdev->bd_openers) {
+		disk_put_part(bdev->bd_part);
+		bdev->bd_part = NULL;
+		bdev->bd_disk = NULL;
+		if (bdev != bdev->bd_contains)
+			victim = bdev->bd_contains;
+		bdev->bd_contains = NULL;
+
+		put_disk_and_module(disk);
+	}
+	mutex_unlock(&bdev->bd_mutex);
+	bdput(bdev);
+	if (victim)
+		__blkdev_put(victim, mode, 1);
+}
+
+void blkdev_put(struct block_device *bdev, fmode_t mode)
+{
+	mutex_lock(&bdev->bd_mutex);
+
+	if (mode & FMODE_EXCL) {
+		bool bdev_free;
+
+		/*
+		 * Release a claim on the device.  The holder fields
+		 * are protected with bdev_lock.  bd_mutex is to
+		 * synchronize disk_holder unlinking.
+		 */
+		spin_lock(&bdev_lock);
+
+		WARN_ON_ONCE(--bdev->bd_holders < 0);
+		WARN_ON_ONCE(--bdev->bd_contains->bd_holders < 0);
+
+		/* bd_contains might point to self, check in a separate step */
+		if ((bdev_free = !bdev->bd_holders))
+			bdev->bd_holder = NULL;
+		if (!bdev->bd_contains->bd_holders)
+			bdev->bd_contains->bd_holder = NULL;
+
+		spin_unlock(&bdev_lock);
+
+		/*
+		 * If this was the last claim, remove holder link and
+		 * unblock evpoll if it was a write holder.
+		 */
+		if (bdev_free && bdev->bd_write_holder) {
+			disk_unblock_events(bdev->bd_disk);
+			bdev->bd_write_holder = false;
+		}
+	}
+
+	/*
+	 * Trigger event checking and tell drivers to flush MEDIA_CHANGE
+	 * event.  This is to ensure detection of media removal commanded
+	 * from userland - e.g. eject(1).
+	 */
+	disk_flush_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE);
+
+	mutex_unlock(&bdev->bd_mutex);
+
+	__blkdev_put(bdev, mode, 0);
+}
+EXPORT_SYMBOL(blkdev_put);
+
+static int blkdev_close(struct inode * inode, struct file * filp)
+{
+	struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
+	blkdev_put(bdev, filp->f_mode);
+	return 0;
+}
+
+static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
+{
+	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
+	fmode_t mode = file->f_mode;
+
+	/*
+	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
+	 * to updated it before every ioctl.
+	 */
+	if (file->f_flags & O_NDELAY)
+		mode |= FMODE_NDELAY;
+	else
+		mode &= ~FMODE_NDELAY;
+
+	return blkdev_ioctl(bdev, mode, cmd, arg);
+}
+
+/*
+ * Write data to the block device.  Only intended for the block device itself
+ * and the raw driver which basically is a fake block device.
+ *
+ * Does not take i_mutex for the write and thus is not for general purpose
+ * use.
+ */
+ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *bd_inode = bdev_file_inode(file);
+	loff_t size = i_size_read(bd_inode);
+	struct blk_plug plug;
+	ssize_t ret;
+	pr_debug("pos=%llu, size=%llu", iocb->ki_pos, size);
+
+	if (bdev_read_only(I_BDEV(bd_inode)))
+		return -EPERM;
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	if (iocb->ki_pos >= size)
+		return -ENOSPC;
+	if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+	iov_iter_truncate(from, size - iocb->ki_pos);
+	blk_start_plug(&plug);
+//	pr_debug("after blk_start_plug()");
+	ret = __generic_file_write_iter(iocb, from);
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+//	pr_debug("before blk_finish_plug()");
+	blk_finish_plug(&plug);
+//	pr_debug("after blk_finish_plug()");
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_write_iter);
+
+ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *bd_inode = bdev_file_inode(file);
+	loff_t size = i_size_read(bd_inode);
+	loff_t pos = iocb->ki_pos;
+	pr_debug("pos=%llu, size=%llu", pos, size);
+	if (pos >= size)
+		return 0;
+
+	size -= pos;
+	iov_iter_truncate(to, size);
+	return generic_file_read_iter(iocb, to);
+}
+EXPORT_SYMBOL_GPL(blkdev_read_iter);
+
+/*
+ * Try to release a page associated with block device when the system
+ * is under memory pressure.
+ */
+static int blkdev_releasepage(struct page *page, gfp_t wait)
+{
+	struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super;
+
+	if (super && super->s_op->bdev_try_to_free_page)
+		return super->s_op->bdev_try_to_free_page(super, page, wait);
+
+	return try_to_free_buffers(page);
+}
+
+static int blkdev_writepages(struct address_space *mapping,
+			     struct writeback_control *wbc)
+{
+	return generic_writepages(mapping, wbc);
+}
+
+static const struct address_space_operations def_blk_aops = {
+	.readpage	= blkdev_readpage,
+	.readpages	= blkdev_readpages,
+	.writepage	= blkdev_writepage,
+	.write_begin	= blkdev_write_begin,
+	.write_end	= blkdev_write_end,
+	.writepages	= blkdev_writepages,
+	.releasepage	= blkdev_releasepage,
+	.direct_IO	= blkdev_direct_IO,
+	.is_dirty_writeback = buffer_check_dirty_writeback,
+};
+
+#define	BLKDEV_FALLOC_FL_SUPPORTED					\
+		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
+		 FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE)
+
+static long blkdev_fallocate(struct file *file, int mode, loff_t start,
+			     loff_t len)
+{
+	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
+	struct address_space *mapping;
+	loff_t end = start + len - 1;
+	loff_t isize;
+	int error;
+
+	/* Fail if we don't recognize the flags. */
+	if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED)
+		return -EOPNOTSUPP;
+
+	/* Don't go off the end of the device. */
+	isize = i_size_read(bdev->bd_inode);
+	if (start >= isize)
+		return -EINVAL;
+	if (end >= isize) {
+		if (mode & FALLOC_FL_KEEP_SIZE) {
+			len = isize - start;
+			end = start + len - 1;
+		} else
+			return -EINVAL;
+	}
+
+	/*
+	 * Don't allow IO that isn't aligned to logical block size.
+	 */
+	if ((start | len) & (bdev_logical_block_size(bdev) - 1))
+		return -EINVAL;
+
+	/* Invalidate the page cache, including dirty pages. */
+	mapping = bdev->bd_inode->i_mapping;
+	truncate_inode_pages_range(mapping, start, end);
+
+	switch (mode) {
+	case FALLOC_FL_ZERO_RANGE:
+	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
+		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
+					    GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
+		break;
+	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
+		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
+					     GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
+		break;
+	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
+		error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
+					     GFP_KERNEL, 0);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	if (error)
+		return error;
+
+	/*
+	 * Invalidate again; if someone wandered in and dirtied a page,
+	 * the caller will be given -EBUSY.  The third argument is
+	 * inclusive, so the rounding here is safe.
+	 */
+	return invalidate_inode_pages2_range(mapping,
+					     start >> PAGE_SHIFT,
+					     end >> PAGE_SHIFT);
+}
+
+const struct file_operations def_blk_fops = {
+	.open		= blkdev_open,
+	.release	= blkdev_close,
+	.llseek		= block_llseek,
+	.read_iter	= blkdev_read_iter,
+	.write_iter	= blkdev_write_iter,
+	.mmap		= generic_file_mmap,
+	.fsync		= blkdev_fsync,
+	.unlocked_ioctl	= block_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= compat_blkdev_ioctl,
+#endif
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
+	.fallocate	= blkdev_fallocate,
+};
+
+int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)
+{
+	int res;
+	mm_segment_t old_fs = get_fs();
+	set_fs(KERNEL_DS);
+	res = blkdev_ioctl(bdev, 0, cmd, arg);
+	set_fs(old_fs);
+	return res;
+}
+
+EXPORT_SYMBOL(ioctl_by_bdev);
+
+/**
+ * lookup_bdev  - lookup a struct block_device by name
+ * @pathname:	special file representing the block device
+ *
+ * Get a reference to the blockdevice at @pathname in the current
+ * namespace if possible and return it.  Return ERR_PTR(error)
+ * otherwise.
+ */
+struct block_device *lookup_bdev(const char *pathname)
+{
+	struct block_device *bdev;
+	struct inode *inode;
+	struct path path;
+	int error;
+
+	if (!pathname || !*pathname)
+		return ERR_PTR(-EINVAL);
+
+	error = kern_path(pathname, LOOKUP_FOLLOW, &path);
+	if (error)
+		return ERR_PTR(error);
+
+	inode = d_backing_inode(path.dentry);
+	error = -ENOTBLK;
+	if (!S_ISBLK(inode->i_mode))
+		goto fail;
+	error = -EACCES;
+	if (!may_open_dev(&path))
+		goto fail;
+	error = -ENOMEM;
+	bdev = bd_acquire(inode);
+	if (!bdev)
+		goto fail;
+out:
+	path_put(&path);
+	return bdev;
+fail:
+	bdev = ERR_PTR(error);
+	goto out;
+}
+EXPORT_SYMBOL(lookup_bdev);
+
+int __invalidate_device(struct block_device *bdev, bool kill_dirty)
+{
+	struct super_block *sb = get_super(bdev);
+	int res = 0;
+
+	if (sb) {
+		/*
+		 * no need to lock the super, get_super holds the
+		 * read mutex so the filesystem cannot go away
+		 * under us (->put_super runs with the write lock
+		 * hold).
+		 */
+		shrink_dcache_sb(sb);
+		res = invalidate_inodes(sb, kill_dirty);
+		drop_super(sb);
+	}
+	invalidate_bdev(bdev);
+	return res;
+}
+EXPORT_SYMBOL(__invalidate_device);
+
+void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
+{
+	struct inode *inode, *old_inode = NULL;
+
+	spin_lock(&blockdev_superblock->s_inode_list_lock);
+	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
+		struct address_space *mapping = inode->i_mapping;
+		struct block_device *bdev;
+
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) ||
+		    mapping->nrpages == 0) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+		__iget(inode);
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&blockdev_superblock->s_inode_list_lock);
+		/*
+		 * We hold a reference to 'inode' so it couldn't have been
+		 * removed from s_inodes list while we dropped the
+		 * s_inode_list_lock  We cannot iput the inode now as we can
+		 * be holding the last reference and we cannot iput it under
+		 * s_inode_list_lock. So we keep the reference and iput it
+		 * later.
+		 */
+		iput(old_inode);
+		old_inode = inode;
+		bdev = I_BDEV(inode);
+
+		mutex_lock(&bdev->bd_mutex);
+		if (bdev->bd_openers)
+			func(bdev, arg);
+		mutex_unlock(&bdev->bd_mutex);
+
+		spin_lock(&blockdev_superblock->s_inode_list_lock);
+	}
+	spin_unlock(&blockdev_superblock->s_inode_list_lock);
+	iput(old_inode);
+}

src/fs/buffer.c

+/*
+ *  linux/fs/buffer.c
+ *
+ *  Copyright (C) 1991, 1992, 2002  Linus Torvalds
+ */
+
+/*
+ * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95
+ *
+ * Removed a lot of unnecessary code and simplified things now that
+ * the buffer cache isn't our primary cache - Andrew Tridgell 12/96
+ *
+ * Speed up hash, lru, and free list operations.  Use gfp() for allocating
+ * hash table, use SLAB cache for buffer heads. SMP threading.  -DaveM
+ *
+ * Added 32k buffer block sizes - these are required older ARM systems. - RMK
+ *
+ * async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de>
+ */
+// elphel 06/03/23 was incorrectly calling ATA_DMA_READ with wrong LBA (did not fit in 28 bits)
+#define SKIP_DEPRECATED 1
+#include <linux/kernel.h>
+#include <linux/sched/signal.h>
+#include <linux/syscalls.h>
+#include <linux/fs.h>
+#include <linux/iomap.h>
+#include <linux/mm.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <linux/capability.h>
+#include <linux/blkdev.h>
+#include <linux/file.h>
+#include <linux/quotaops.h>
+#include <linux/highmem.h>
+#include <linux/export.h>
+#include <linux/backing-dev.h>
+#include <linux/writeback.h>
+#include <linux/hash.h>
+#include <linux/suspend.h>
+#include <linux/buffer_head.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/bio.h>
+#include <linux/cpu.h>
+#include <linux/bitops.h>
+#include <linux/mpage.h>
+#include <linux/bit_spinlock.h>
+#include <linux/pagevec.h>
+#include <linux/sched/mm.h>
+#include <trace/events/block.h>
+
+static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
+static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
+			 enum rw_hint hint, struct writeback_control *wbc);
+#define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
+inline void touch_buffer(struct buffer_head *bh)
+{
+	trace_block_touch_buffer(bh);
+	mark_page_accessed(bh->b_page);
+}
+EXPORT_SYMBOL(touch_buffer);
+
+void __lock_buffer(struct buffer_head *bh)
+{
+	wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(__lock_buffer);
+
+void unlock_buffer(struct buffer_head *bh)
+{
+	clear_bit_unlock(BH_Lock, &bh->b_state);
+	smp_mb__after_atomic();
+	wake_up_bit(&bh->b_state, BH_Lock);
+}
+EXPORT_SYMBOL(unlock_buffer);
+
+/*
+ * Returns if the page has dirty or writeback buffers. If all the buffers
+ * are unlocked and clean then the PageDirty information is stale. If
+ * any of the pages are locked, it is assumed they are locked for IO.
+ */
+void buffer_check_dirty_writeback(struct page *page,
+				     bool *dirty, bool *writeback)
+{
+	struct buffer_head *head, *bh;
+	*dirty = false;
+	*writeback = false;
+
+	BUG_ON(!PageLocked(page));
+
+	if (!page_has_buffers(page))
+		return;
+
+	if (PageWriteback(page))
+		*writeback = true;
+
+	head = page_buffers(page);
+	bh = head;
+	do {
+		if (buffer_locked(bh))
+			*writeback = true;
+
+		if (buffer_dirty(bh))
+			*dirty = true;
+
+		bh = bh->b_this_page;
+	} while (bh != head);
+}
+EXPORT_SYMBOL(buffer_check_dirty_writeback);
+
+/*
+ * Block until a buffer comes unlocked.  This doesn't stop it
+ * from becoming locked again - you have to lock it yourself
+ * if you want to preserve its state.
+ */
+void __wait_on_buffer(struct buffer_head * bh)
+{
+	wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(__wait_on_buffer);
+
+static void
+__clear_page_buffers(struct page *page)
+{
+	ClearPagePrivate(page);
+	set_page_private(page, 0);
+	put_page(page);
+}
+
+static void buffer_io_error(struct buffer_head *bh, char *msg)
+{
+	if (!test_bit(BH_Quiet, &bh->b_state))
+		printk_ratelimited(KERN_ERR
+			"Buffer I/O error on dev %pg, logical block %llu%s\n",
+			bh->b_bdev, (unsigned long long)bh->b_blocknr, msg);
+}
+
+/*
+ * End-of-IO handler helper function which does not touch the bh after
+ * unlocking it.
+ * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but
+ * a race there is benign: unlock_buffer() only use the bh's address for
+ * hashing after unlocking the buffer, so it doesn't actually touch the bh
+ * itself.
+ */
+static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate)
+{
+	if (uptodate) {
+		set_buffer_uptodate(bh);
+	} else {
+		/* This happens, due to failed read-ahead attempts. */
+		clear_buffer_uptodate(bh);
+	}
+	unlock_buffer(bh);
+}
+
+/*
+ * Default synchronous end-of-IO handler..  Just mark it up-to-date and
+ * unlock the buffer. This is what ll_rw_block uses too.
+ */
+void end_buffer_read_sync(struct buffer_head *bh, int uptodate)
+{
+	__end_buffer_read_notouch(bh, uptodate);
+	put_bh(bh);
+}
+EXPORT_SYMBOL(end_buffer_read_sync);
+
+void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
+{
+	if (uptodate) {
+		set_buffer_uptodate(bh);
+	} else {
+		buffer_io_error(bh, ", lost sync page write");
+		mark_buffer_write_io_error(bh);
+		clear_buffer_uptodate(bh);
+	}
+	unlock_buffer(bh);
+	put_bh(bh);
+}
+EXPORT_SYMBOL(end_buffer_write_sync);
+
+/*
+ * Various filesystems appear to want __find_get_block to be non-blocking.
+ * But it's the page lock which protects the buffers.  To get around this,
+ * we get exclusion from try_to_free_buffers with the blockdev mapping's
+ * private_lock.
+ *
+ * Hack idea: for the blockdev mapping, private_lock contention
+ * may be quite high.  This code could TryLock the page, and if that
+ * succeeds, there is no need to take private_lock.
+ */
+static struct buffer_head *
+__find_get_block_slow(struct block_device *bdev, sector_t block)
+{
+	struct inode *bd_inode = bdev->bd_inode;
+	struct address_space *bd_mapping = bd_inode->i_mapping;
+	struct buffer_head *ret = NULL;
+	pgoff_t index;
+	struct buffer_head *bh;
+	struct buffer_head *head;
+	struct page *page;
+	int all_mapped = 1;
+
+	index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
+	page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED);
+	if (!page)
+		goto out;
+
+	spin_lock(&bd_mapping->private_lock);
+	if (!page_has_buffers(page))
+		goto out_unlock;
+	head = page_buffers(page);
+	bh = head;
+	do {
+		if (!buffer_mapped(bh))
+			all_mapped = 0;
+		else if (bh->b_blocknr == block) {
+			ret = bh;
+			get_bh(bh);
+			goto out_unlock;
+		}
+		bh = bh->b_this_page;
+	} while (bh != head);
+
+	/* we might be here because some of the buffers on this page are
+	 * not mapped.  This is due to various races between
+	 * file io on the block device and getblk.  It gets dealt with
+	 * elsewhere, don't buffer_error if we had some unmapped buffers
+	 */
+	if (all_mapped) {
+		printk("__find_get_block_slow() failed. "
+			"block=%llu, b_blocknr=%llu\n",
+			(unsigned long long)block,
+			(unsigned long long)bh->b_blocknr);
+		printk("b_state=0x%08lx, b_size=%zu\n",
+			bh->b_state, bh->b_size);
+		printk("device %pg blocksize: %d\n", bdev,
+			1 << bd_inode->i_blkbits);
+	}
+out_unlock:
+	spin_unlock(&bd_mapping->private_lock);
+	put_page(page);
+out:
+	return ret;
+}
+
+/*
+ * I/O completion handler for block_read_full_page() - pages
+ * which come unlocked at the end of I/O.
+ */
+static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
+{
+	unsigned long flags;
+	struct buffer_head *first;
+	struct buffer_head *tmp;
+	struct page *page;
+	int page_uptodate = 1;
+
+	BUG_ON(!buffer_async_read(bh));
+
+	page = bh->b_page;
+	if (uptodate) {
+		set_buffer_uptodate(bh);
+	} else {
+		clear_buffer_uptodate(bh);
+		buffer_io_error(bh, ", async page read");
+		SetPageError(page);
+	}
+
+	/*
+	 * Be _very_ careful from here on. Bad things can happen if
+	 * two buffer heads end IO at almost the same time and both
+	 * decide that the page is now completely done.
+	 */
+	first = page_buffers(page);
+	local_irq_save(flags);
+	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+	clear_buffer_async_read(bh);
+	unlock_buffer(bh);
+	tmp = bh;
+	do {
+		if (!buffer_uptodate(tmp))
+			page_uptodate = 0;
+		if (buffer_async_read(tmp)) {
+			BUG_ON(!buffer_locked(tmp));
+			goto still_busy;
+		}
+		tmp = tmp->b_this_page;
+	} while (tmp != bh);
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
+
+	/*
+	 * If none of the buffers had errors and they are all
+	 * uptodate then we can set the page uptodate.
+	 */
+	if (page_uptodate && !PageError(page))
+		SetPageUptodate(page);
+	unlock_page(page);
+	return;
+
+still_busy:
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
+	return;
+}
+
+/*
+ * Completion handler for block_write_full_page() - pages which are unlocked
+ * during I/O, and which have PageWriteback cleared upon I/O completion.
+ */
+void end_buffer_async_write(struct buffer_head *bh, int uptodate)
+{
+	unsigned long flags;
+	struct buffer_head *first;
+	struct buffer_head *tmp;
+	struct page *page;
+
+	BUG_ON(!buffer_async_write(bh));
+
+	page = bh->b_page;
+	if (uptodate) {
+		set_buffer_uptodate(bh);
+	} else {
+		buffer_io_error(bh, ", lost async page write");
+		mark_buffer_write_io_error(bh);
+		clear_buffer_uptodate(bh);
+		SetPageError(page);
+	}
+
+	first = page_buffers(page);
+	local_irq_save(flags);
+	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+
+	clear_buffer_async_write(bh);
+	unlock_buffer(bh);
+	tmp = bh->b_this_page;
+	while (tmp != bh) {
+		if (buffer_async_write(tmp)) {
+			BUG_ON(!buffer_locked(tmp));
+			goto still_busy;
+		}
+		tmp = tmp->b_this_page;
+	}
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
+	end_page_writeback(page);
+	return;
+
+still_busy:
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
+	return;
+}
+EXPORT_SYMBOL(end_buffer_async_write);
+
+/*
+ * If a page's buffers are under async readin (end_buffer_async_read
+ * completion) then there is a possibility that another thread of
+ * control could lock one of the buffers after it has completed
+ * but while some of the other buffers have not completed.  This
+ * locked buffer would confuse end_buffer_async_read() into not unlocking
+ * the page.  So the absence of BH_Async_Read tells end_buffer_async_read()
+ * that this buffer is not under async I/O.
+ *
+ * The page comes unlocked when it has no locked buffer_async buffers
+ * left.
+ *
+ * PageLocked prevents anyone starting new async I/O reads any of
+ * the buffers.
+ *
+ * PageWriteback is used to prevent simultaneous writeout of the same
+ * page.
+ *
+ * PageLocked prevents anyone from starting writeback of a page which is
+ * under read I/O (PageWriteback is only ever set against a locked page).
+ */
+static void mark_buffer_async_read(struct buffer_head *bh)
+{
+	bh->b_end_io = end_buffer_async_read;
+	set_buffer_async_read(bh);
+}
+
+static void mark_buffer_async_write_endio(struct buffer_head *bh,
+					  bh_end_io_t *handler)
+{
+	bh->b_end_io = handler;
+	set_buffer_async_write(bh);
+}
+
+void mark_buffer_async_write(struct buffer_head *bh)
+{
+	mark_buffer_async_write_endio(bh, end_buffer_async_write);
+}
+EXPORT_SYMBOL(mark_buffer_async_write);
+
+
+/*
+ * fs/buffer.c contains helper functions for buffer-backed address space's
+ * fsync functions.  A common requirement for buffer-based filesystems is
+ * that certain data from the backing blockdev needs to be written out for
+ * a successful fsync().  For example, ext2 indirect blocks need to be
+ * written back and waited upon before fsync() returns.
+ *
+ * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(),
+ * inode_has_buffers() and invalidate_inode_buffers() are provided for the
+ * management of a list of dependent buffers at ->i_mapping->private_list.
+ *
+ * Locking is a little subtle: try_to_free_buffers() will remove buffers
+ * from their controlling inode's queue when they are being freed.  But
+ * try_to_free_buffers() will be operating against the *blockdev* mapping
+ * at the time, not against the S_ISREG file which depends on those buffers.
+ * So the locking for private_list is via the private_lock in the address_space
+ * which backs the buffers.  Which is different from the address_space 
+ * against which the buffers are listed.  So for a particular address_space,
+ * mapping->private_lock does *not* protect mapping->private_list!  In fact,
+ * mapping->private_list will always be protected by the backing blockdev's
+ * ->private_lock.
+ *
+ * Which introduces a requirement: all buffers on an address_space's
+ * ->private_list must be from the same address_space: the blockdev's.
+ *
+ * address_spaces which do not place buffers at ->private_list via these
+ * utility functions are free to use private_lock and private_list for
+ * whatever they want.  The only requirement is that list_empty(private_list)
+ * be true at clear_inode() time.
+ *
+ * FIXME: clear_inode should not call invalidate_inode_buffers().  The
+ * filesystems should do that.  invalidate_inode_buffers() should just go
+ * BUG_ON(!list_empty).
+ *
+ * FIXME: mark_buffer_dirty_inode() is a data-plane operation.  It should
+ * take an address_space, not an inode.  And it should be called
+ * mark_buffer_dirty_fsync() to clearly define why those buffers are being
+ * queued up.
+ *
+ * FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the
+ * list if it is already on a list.  Because if the buffer is on a list,
+ * it *must* already be on the right one.  If not, the filesystem is being
+ * silly.  This will save a ton of locking.  But first we have to ensure
+ * that buffers are taken *off* the old inode's list when they are freed
+ * (presumably in truncate).  That requires careful auditing of all
+ * filesystems (do it inside bforget()).  It could also be done by bringing
+ * b_inode back.
+ */
+
+/*
+ * The buffer's backing address_space's private_lock must be held
+ */
+static void __remove_assoc_queue(struct buffer_head *bh)
+{
+	list_del_init(&bh->b_assoc_buffers);
+	WARN_ON(!bh->b_assoc_map);
+	bh->b_assoc_map = NULL;
+}
+
+int inode_has_buffers(struct inode *inode)
+{
+	return !list_empty(&inode->i_data.private_list);
+}
+
+/*
+ * osync is designed to support O_SYNC io.  It waits synchronously for
+ * all already-submitted IO to complete, but does not queue any new
+ * writes to the disk.
+ *
+ * To do O_SYNC writes, just queue the buffer writes with ll_rw_block as
+ * you dirty the buffers, and then use osync_inode_buffers to wait for
+ * completion.  Any other dirty buffers which are not yet queued for
+ * write will not be flushed to disk by the osync.
+ */
+static int osync_buffers_list(spinlock_t *lock, struct list_head *list)
+{
+	struct buffer_head *bh;
+	struct list_head *p;
+	int err = 0;
+
+	spin_lock(lock);
+repeat:
+	list_for_each_prev(p, list) {
+		bh = BH_ENTRY(p);
+		if (buffer_locked(bh)) {
+			get_bh(bh);
+			spin_unlock(lock);
+			wait_on_buffer(bh);
+			if (!buffer_uptodate(bh))
+				err = -EIO;
+			brelse(bh);
+			spin_lock(lock);
+			goto repeat;
+		}
+	}
+	spin_unlock(lock);
+	return err;
+}
+
+void emergency_thaw_bdev(struct super_block *sb)
+{
+	while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
+		printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev);
+}
+
+/**
+ * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers
+ * @mapping: the mapping which wants those buffers written
+ *
+ * Starts I/O against the buffers at mapping->private_list, and waits upon
+ * that I/O.
+ *
+ * Basically, this is a convenience function for fsync().
+ * @mapping is a file or directory which needs those buffers to be written for
+ * a successful fsync().
+ */
+int sync_mapping_buffers(struct address_space *mapping)
+{
+	struct address_space *buffer_mapping = mapping->private_data;
+
+	if (buffer_mapping == NULL || list_empty(&mapping->private_list))
+		return 0;
+
+	return fsync_buffers_list(&buffer_mapping->private_lock,
+					&mapping->private_list);
+}
+EXPORT_SYMBOL(sync_mapping_buffers);
+
+/*
+ * Called when we've recently written block `bblock', and it is known that
+ * `bblock' was for a buffer_boundary() buffer.  This means that the block at
+ * `bblock + 1' is probably a dirty indirect block.  Hunt it down and, if it's
+ * dirty, schedule it for IO.  So that indirects merge nicely with their data.
+ */
+void write_boundary_block(struct block_device *bdev,
+			sector_t bblock, unsigned blocksize)
+{
+	struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
+	if (bh) {
+		if (buffer_dirty(bh))
+			ll_rw_block(REQ_OP_WRITE, 0, 1, &bh);
+		put_bh(bh);
+	}
+}
+
+void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct address_space *buffer_mapping = bh->b_page->mapping;
+
+	mark_buffer_dirty(bh);
+	if (!mapping->private_data) {
+		mapping->private_data = buffer_mapping;
+	} else {
+		BUG_ON(mapping->private_data != buffer_mapping);
+	}
+	if (!bh->b_assoc_map) {
+		spin_lock(&buffer_mapping->private_lock);
+		list_move_tail(&bh->b_assoc_buffers,
+				&mapping->private_list);
+		bh->b_assoc_map = mapping;
+		spin_unlock(&buffer_mapping->private_lock);
+	}
+}
+EXPORT_SYMBOL(mark_buffer_dirty_inode);
+
+/*
+ * Mark the page dirty, and set it dirty in the radix tree, and mark the inode
+ * dirty.
+ *
+ * If warn is true, then emit a warning if the page is not uptodate and has
+ * not been truncated.
+ *
+ * The caller must hold lock_page_memcg().
+ */
+void __set_page_dirty(struct page *page, struct address_space *mapping,
+			     int warn)
+{
+	unsigned long flags;
+
+	xa_lock_irqsave(&mapping->i_pages, flags);
+	if (page->mapping) {	/* Race with truncate? */
+		WARN_ON_ONCE(warn && !PageUptodate(page));
+		account_page_dirtied(page, mapping);
+		radix_tree_tag_set(&mapping->i_pages,
+				page_index(page), PAGECACHE_TAG_DIRTY);
+	}
+	xa_unlock_irqrestore(&mapping->i_pages, flags);
+}
+EXPORT_SYMBOL_GPL(__set_page_dirty);
+
+/*
+ * Add a page to the dirty page list.
+ *
+ * It is a sad fact of life that this function is called from several places
+ * deeply under spinlocking.  It may not sleep.
+ *
+ * If the page has buffers, the uptodate buffers are set dirty, to preserve
+ * dirty-state coherency between the page and the buffers.  It the page does
+ * not have buffers then when they are later attached they will all be set
+ * dirty.
+ *
+ * The buffers are dirtied before the page is dirtied.  There's a small race
+ * window in which a writepage caller may see the page cleanness but not the
+ * buffer dirtiness.  That's fine.  If this code were to set the page dirty
+ * before the buffers, a concurrent writepage caller could clear the page dirty
+ * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean
+ * page on the dirty page list.
+ *
+ * We use private_lock to lock against try_to_free_buffers while using the
+ * page's buffer list.  Also use this to protect against clean buffers being
+ * added to the page after it was set dirty.
+ *
+ * FIXME: may need to call ->reservepage here as well.  That's rather up to the
+ * address_space though.
+ */
+int __set_page_dirty_buffers(struct page *page)
+{
+	int newly_dirty;
+	struct address_space *mapping = page_mapping(page);
+
+	if (unlikely(!mapping))
+		return !TestSetPageDirty(page);
+
+	spin_lock(&mapping->private_lock);
+	if (page_has_buffers(page)) {
+		struct buffer_head *head = page_buffers(page);
+		struct buffer_head *bh = head;
+
+		do {
+			set_buffer_dirty(bh);
+			bh = bh->b_this_page;
+		} while (bh != head);
+	}
+	/*
+	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * synchronized with per-memcg dirty page counters.
+	 */
+	lock_page_memcg(page);
+	newly_dirty = !TestSetPageDirty(page);
+	spin_unlock(&mapping->private_lock);
+
+	if (newly_dirty)
+		__set_page_dirty(page, mapping, 1);
+
+	unlock_page_memcg(page);
+
+	if (newly_dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+
+	return newly_dirty;
+}
+EXPORT_SYMBOL(__set_page_dirty_buffers);
+
+/*
+ * Write out and wait upon a list of buffers.
+ *
+ * We have conflicting pressures: we want to make sure that all
+ * initially dirty buffers get waited on, but that any subsequently
+ * dirtied buffers don't.  After all, we don't want fsync to last
+ * forever if somebody is actively writing to the file.
+ *
+ * Do this in two main stages: first we copy dirty buffers to a
+ * temporary inode list, queueing the writes as we go.  Then we clean
+ * up, waiting for those writes to complete.
+ * 
+ * During this second stage, any subsequent updates to the file may end
+ * up refiling the buffer on the original inode's dirty list again, so
+ * there is a chance we will end up with a buffer queued for write but
+ * not yet completed on that list.  So, as a final cleanup we go through
+ * the osync code to catch these locked, dirty buffers without requeuing
+ * any newly dirty buffers for write.
+ */
+static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
+{
+	struct buffer_head *bh;
+	struct list_head tmp;
+	struct address_space *mapping;
+	int err = 0, err2;
+	struct blk_plug plug;
+
+	INIT_LIST_HEAD(&tmp);
+	blk_start_plug(&plug);
+
+	spin_lock(lock);
+	while (!list_empty(list)) {
+		bh = BH_ENTRY(list->next);
+		mapping = bh->b_assoc_map;
+		__remove_assoc_queue(bh);
+		/* Avoid race with mark_buffer_dirty_inode() which does
+		 * a lockless check and we rely on seeing the dirty bit */
+		smp_mb();
+		if (buffer_dirty(bh) || buffer_locked(bh)) {
+			list_add(&bh->b_assoc_buffers, &tmp);
+			bh->b_assoc_map = mapping;
+			if (buffer_dirty(bh)) {
+				get_bh(bh);
+				spin_unlock(lock);
+				/*
+				 * Ensure any pending I/O completes so that
+				 * write_dirty_buffer() actually writes the
+				 * current contents - it is a noop if I/O is
+				 * still in flight on potentially older
+				 * contents.
+				 */
+				write_dirty_buffer(bh, REQ_SYNC);
+
+				/*
+				 * Kick off IO for the previous mapping. Note
+				 * that we will not run the very last mapping,
+				 * wait_on_buffer() will do that for us
+				 * through sync_buffer().
+				 */
+				brelse(bh);
+				spin_lock(lock);
+			}
+		}
+	}
+
+	spin_unlock(lock);
+	blk_finish_plug(&plug);
+	spin_lock(lock);
+
+	while (!list_empty(&tmp)) {
+		bh = BH_ENTRY(tmp.prev);
+		get_bh(bh);
+		mapping = bh->b_assoc_map;
+		__remove_assoc_queue(bh);
+		/* Avoid race with mark_buffer_dirty_inode() which does
+		 * a lockless check and we rely on seeing the dirty bit */
+		smp_mb();
+		if (buffer_dirty(bh)) {
+			list_add(&bh->b_assoc_buffers,
+				 &mapping->private_list);
+			bh->b_assoc_map = mapping;
+		}
+		spin_unlock(lock);
+		wait_on_buffer(bh);
+		if (!buffer_uptodate(bh))
+			err = -EIO;
+		brelse(bh);
+		spin_lock(lock);
+	}
+	
+	spin_unlock(lock);
+	err2 = osync_buffers_list(lock, list);
+	if (err)
+		return err;
+	else
+		return err2;
+}
+
+/*
+ * Invalidate any and all dirty buffers on a given inode.  We are
+ * probably unmounting the fs, but that doesn't mean we have already
+ * done a sync().  Just drop the buffers from the inode list.
+ *
+ * NOTE: we take the inode's blockdev's mapping's private_lock.  Which
+ * assumes that all the buffers are against the blockdev.  Not true
+ * for reiserfs.
+ */
+void invalidate_inode_buffers(struct inode *inode)
+{
+	if (inode_has_buffers(inode)) {
+		struct address_space *mapping = &inode->i_data;
+		struct list_head *list = &mapping->private_list;
+		struct address_space *buffer_mapping = mapping->private_data;
+
+		spin_lock(&buffer_mapping->private_lock);
+		while (!list_empty(list))
+			__remove_assoc_queue(BH_ENTRY(list->next));
+		spin_unlock(&buffer_mapping->private_lock);
+	}
+}
+EXPORT_SYMBOL(invalidate_inode_buffers);
+
+/*
+ * Remove any clean buffers from the inode's buffer list.  This is called
+ * when we're trying to free the inode itself.  Those buffers can pin it.
+ *
+ * Returns true if all buffers were removed.
+ */
+int remove_inode_buffers(struct inode *inode)
+{
+	int ret = 1;
+
+	if (inode_has_buffers(inode)) {
+		struct address_space *mapping = &inode->i_data;
+		struct list_head *list = &mapping->private_list;
+		struct address_space *buffer_mapping = mapping->private_data;
+
+		spin_lock(&buffer_mapping->private_lock);
+		while (!list_empty(list)) {
+			struct buffer_head *bh = BH_ENTRY(list->next);
+			if (buffer_dirty(bh)) {
+				ret = 0;
+				break;
+			}
+			__remove_assoc_queue(bh);
+		}
+		spin_unlock(&buffer_mapping->private_lock);
+	}
+	return ret;
+}
+
+/*
+ * Create the appropriate buffers when given a page for data area and
+ * the size of each buffer.. Use the bh->b_this_page linked list to
+ * follow the buffers created.  Return NULL if unable to create more
+ * buffers.
+ *
+ * The retry flag is used to differentiate async IO (paging, swapping)
+ * which may not fail from ordinary buffer allocations.
+ */
+struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
+		bool retry)
+{
+	struct buffer_head *bh, *head;
+	gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT;
+	long offset;
+	struct mem_cgroup *memcg;
+
+	if (retry)
+		gfp |= __GFP_NOFAIL;
+
+	memcg = get_mem_cgroup_from_page(page);
+	memalloc_use_memcg(memcg);
+
+	head = NULL;
+	offset = PAGE_SIZE;
+	while ((offset -= size) >= 0) {
+		bh = alloc_buffer_head(gfp);
+		if (!bh)
+			goto no_grow;
+
+		bh->b_this_page = head;
+		bh->b_blocknr = -1;
+		head = bh;
+
+		bh->b_size = size;
+
+		/* Link the buffer to its page */
+		set_bh_page(bh, page, offset);
+	}
+out:
+	memalloc_unuse_memcg();
+	mem_cgroup_put(memcg);
+	return head;
+/*
+ * In case anything failed, we just free everything we got.
+ */
+no_grow:
+	if (head) {
+		do {
+			bh = head;
+			head = head->b_this_page;
+			free_buffer_head(bh);
+		} while (head);
+	}
+
+	goto out;
+}
+EXPORT_SYMBOL_GPL(alloc_page_buffers);
+
+static inline void
+link_dev_buffers(struct page *page, struct buffer_head *head)
+{
+	struct buffer_head *bh, *tail;
+
+	bh = head;
+	do {
+		tail = bh;
+		bh = bh->b_this_page;
+	} while (bh);
+	tail->b_this_page = head;
+	attach_page_buffers(page, head);
+}
+
+static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size)
+{
+	sector_t retval = ~((sector_t)0);
+	loff_t sz = i_size_read(bdev->bd_inode);
+
+	if (sz) {
+		unsigned int sizebits = blksize_bits(size);
+		retval = (sz >> sizebits);
+	}
+	return retval;
+}
+
+/*
+ * Initialise the state of a blockdev page's buffers.
+ */ 
+static sector_t
+init_page_buffers(struct page *page, struct block_device *bdev,
+			sector_t block, int size)
+{
+	struct buffer_head *head = page_buffers(page);
+	struct buffer_head *bh = head;
+	int uptodate = PageUptodate(page);
+	sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size);
+
+	do {
+		if (!buffer_mapped(bh)) {
+			bh->b_end_io = NULL;
+			bh->b_private = NULL;
+			bh->b_bdev = bdev;
+			bh->b_blocknr = block;
+			if (uptodate)
+				set_buffer_uptodate(bh);
+			if (block < end_block)
+				set_buffer_mapped(bh);
+		}
+		block++;
+		bh = bh->b_this_page;
+	} while (bh != head);
+
+	/*
+	 * Caller needs to validate requested block against end of device.
+	 */
+	return end_block;
+}
+
+/*
+ * Create the page-cache page that contains the requested block.
+ *
+ * This is used purely for blockdev mappings.
+ */
+static int
+grow_dev_page(struct block_device *bdev, sector_t block,
+	      pgoff_t index, int size, int sizebits, gfp_t gfp)
+{
+	struct inode *inode = bdev->bd_inode;
+	struct page *page;
+	struct buffer_head *bh;
+	sector_t end_block;
+	int ret = 0;		/* Will call free_more_memory() */
+	gfp_t gfp_mask;
+
+	gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp;
+
+	/*
+	 * XXX: __getblk_slow() can not really deal with failure and
+	 * will endlessly loop on improvised global reclaim.  Prefer
+	 * looping in the allocator rather than here, at least that
+	 * code knows what it's doing.
+	 */
+	gfp_mask |= __GFP_NOFAIL;
+
+	page = find_or_create_page(inode->i_mapping, index, gfp_mask);
+
+	BUG_ON(!PageLocked(page));
+
+	if (page_has_buffers(page)) {
+		bh = page_buffers(page);
+		if (bh->b_size == size) {
+			end_block = init_page_buffers(page, bdev,
+						(sector_t)index << sizebits,
+						size);
+			goto done;
+		}
+		if (!try_to_free_buffers(page))
+			goto failed;
+	}
+
+	/*
+	 * Allocate some buffers for this page
+	 */
+	bh = alloc_page_buffers(page, size, true);
+
+	/*
+	 * Link the page to the buffers and initialise them.  Take the
+	 * lock to be atomic wrt __find_get_block(), which does not
+	 * run under the page lock.
+	 */
+	spin_lock(&inode->i_mapping->private_lock);
+	link_dev_buffers(page, bh);
+	end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits,
+			size);
+	spin_unlock(&inode->i_mapping->private_lock);
+done:
+	ret = (block < end_block) ? 1 : -ENXIO;
+failed:
+	unlock_page(page);
+	put_page(page);
+	return ret;
+}
+
+/*
+ * Create buffers for the specified block device block's page.  If
+ * that page was dirty, the buffers are set dirty also.
+ */
+static int
+grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp)
+{
+	pgoff_t index;
+	int sizebits;
+
+	sizebits = -1;
+	do {
+		sizebits++;
+	} while ((size << sizebits) < PAGE_SIZE);
+
+	index = block >> sizebits;
+
+	/*
+	 * Check for a block which wants to lie outside our maximum possible
+	 * pagecache index.  (this comparison is done using sector_t types).
+	 */
+	if (unlikely(index != block >> sizebits)) {
+		printk(KERN_ERR "%s: requested out-of-range block %llu for "
+			"device %pg\n",
+			__func__, (unsigned long long)block,
+			bdev);
+		return -EIO;
+	}
+
+	/* Create a page with the proper size buffers.. */
+	return grow_dev_page(bdev, block, index, size, sizebits, gfp);
+}
+
+static struct buffer_head *
+__getblk_slow(struct block_device *bdev, sector_t block,
+	     unsigned size, gfp_t gfp)
+{
+	/* Size must be multiple of hard sectorsize */
+	if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
+			(size < 512 || size > PAGE_SIZE))) {
+		printk(KERN_ERR "getblk(): invalid block size %d requested\n",
+					size);
+		printk(KERN_ERR "logical block size: %d\n",
+					bdev_logical_block_size(bdev));
+
+		dump_stack();
+		return NULL;
+	}
+
+	for (;;) {
+		struct buffer_head *bh;
+		int ret;
+
+		bh = __find_get_block(bdev, block, size);
+		if (bh)
+			return bh;
+
+		ret = grow_buffers(bdev, block, size, gfp);
+		if (ret < 0)
+			return NULL;
+	}
+}
+
+/*
+ * The relationship between dirty buffers and dirty pages:
+ *
+ * Whenever a page has any dirty buffers, the page's dirty bit is set, and
+ * the page is tagged dirty in its radix tree.
+ *
+ * At all times, the dirtiness of the buffers represents the dirtiness of
+ * subsections of the page.  If the page has buffers, the page dirty bit is
+ * merely a hint about the true dirty state.
+ *
+ * When a page is set dirty in its entirety, all its buffers are marked dirty
+ * (if the page has buffers).
+ *
+ * When a buffer is marked dirty, its page is dirtied, but the page's other
+ * buffers are not.
+ *
+ * Also.  When blockdev buffers are explicitly read with bread(), they
+ * individually become uptodate.  But their backing page remains not
+ * uptodate - even if all of its buffers are uptodate.  A subsequent
+ * block_read_full_page() against that page will discover all the uptodate
+ * buffers, will set the page uptodate and will perform no I/O.
+ */
+
+/**
+ * mark_buffer_dirty - mark a buffer_head as needing writeout
+ * @bh: the buffer_head to mark dirty
+ *
+ * mark_buffer_dirty() will set the dirty bit against the buffer, then set its
+ * backing page dirty, then tag the page as dirty in its address_space's radix
+ * tree and then attach the address_space's inode to its superblock's dirty
+ * inode list.
+ *
+ * mark_buffer_dirty() is atomic.  It takes bh->b_page->mapping->private_lock,
+ * i_pages lock and mapping->host->i_lock.
+ */
+void mark_buffer_dirty(struct buffer_head *bh)
+{
+	WARN_ON_ONCE(!buffer_uptodate(bh));
+
+	trace_block_dirty_buffer(bh);
+
+	/*
+	 * Very *carefully* optimize the it-is-already-dirty case.
+	 *
+	 * Don't let the final "is it dirty" escape to before we
+	 * perhaps modified the buffer.
+	 */
+	if (buffer_dirty(bh)) {
+		smp_mb();
+		if (buffer_dirty(bh))
+			return;
+	}
+
+	if (!test_set_buffer_dirty(bh)) {
+		struct page *page = bh->b_page;
+		struct address_space *mapping = NULL;
+
+		lock_page_memcg(page);
+		if (!TestSetPageDirty(page)) {
+			mapping = page_mapping(page);
+			if (mapping)
+				__set_page_dirty(page, mapping, 0);
+		}
+		unlock_page_memcg(page);
+		if (mapping)
+			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+	}
+}
+EXPORT_SYMBOL(mark_buffer_dirty);
+
+void mark_buffer_write_io_error(struct buffer_head *bh)
+{
+	set_buffer_write_io_error(bh);
+	/* FIXME: do we need to set this in both places? */
+	if (bh->b_page && bh->b_page->mapping)
+		mapping_set_error(bh->b_page->mapping, -EIO);
+	if (bh->b_assoc_map)
+		mapping_set_error(bh->b_assoc_map, -EIO);
+}
+EXPORT_SYMBOL(mark_buffer_write_io_error);
+
+/*
+ * Decrement a buffer_head's reference count.  If all buffers against a page
+ * have zero reference count, are clean and unlocked, and if the page is clean
+ * and unlocked then try_to_free_buffers() may strip the buffers from the page
+ * in preparation for freeing it (sometimes, rarely, buffers are removed from
+ * a page but it ends up not being freed, and buffers may later be reattached).
+ */
+void __brelse(struct buffer_head * buf)
+{
+	if (atomic_read(&buf->b_count)) {
+		put_bh(buf);
+		return;
+	}
+	WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n");
+}
+EXPORT_SYMBOL(__brelse);
+
+/*
+ * bforget() is like brelse(), except it discards any
+ * potentially dirty data.
+ */
+void __bforget(struct buffer_head *bh)
+{
+	clear_buffer_dirty(bh);
+	if (bh->b_assoc_map) {
+		struct address_space *buffer_mapping = bh->b_page->mapping;
+
+		spin_lock(&buffer_mapping->private_lock);
+		list_del_init(&bh->b_assoc_buffers);
+		bh->b_assoc_map = NULL;
+		spin_unlock(&buffer_mapping->private_lock);
+	}
+	__brelse(bh);
+}
+EXPORT_SYMBOL(__bforget);
+
+static struct buffer_head *__bread_slow(struct buffer_head *bh)
+{
+	lock_buffer(bh);
+	if (buffer_uptodate(bh)) {
+		unlock_buffer(bh);
+		return bh;
+	} else {
+		get_bh(bh);
+		bh->b_end_io = end_buffer_read_sync;
+		submit_bh(REQ_OP_READ, 0, bh);
+		wait_on_buffer(bh);
+		if (buffer_uptodate(bh))
+			return bh;
+	}
+	brelse(bh);
+	return NULL;
+}
+
+/*
+ * Per-cpu buffer LRU implementation.  To reduce the cost of __find_get_block().
+ * The bhs[] array is sorted - newest buffer is at bhs[0].  Buffers have their
+ * refcount elevated by one when they're in an LRU.  A buffer can only appear
+ * once in a particular CPU's LRU.  A single buffer can be present in multiple
+ * CPU's LRUs at the same time.
+ *
+ * This is a transparent caching front-end to sb_bread(), sb_getblk() and
+ * sb_find_get_block().
+ *
+ * The LRUs themselves only need locking against invalidate_bh_lrus.  We use
+ * a local interrupt disable for that.
+ */
+
+#define BH_LRU_SIZE	16
+
+struct bh_lru {
+	struct buffer_head *bhs[BH_LRU_SIZE];
+};
+
+static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }};
+
+#ifdef CONFIG_SMP
+#define bh_lru_lock()	local_irq_disable()
+#define bh_lru_unlock()	local_irq_enable()
+#else
+#define bh_lru_lock()	preempt_disable()
+#define bh_lru_unlock()	preempt_enable()
+#endif
+
+static inline void check_irqs_on(void)
+{
+#ifdef irqs_disabled
+	BUG_ON(irqs_disabled());
+#endif
+}
+
+/*
+ * Install a buffer_head into this cpu's LRU.  If not already in the LRU, it is
+ * inserted at the front, and the buffer_head at the back if any is evicted.
+ * Or, if already in the LRU it is moved to the front.
+ */
+static void bh_lru_install(struct buffer_head *bh)
+{
+	struct buffer_head *evictee = bh;
+	struct bh_lru *b;
+	int i;
+
+	check_irqs_on();
+	bh_lru_lock();
+
+	b = this_cpu_ptr(&bh_lrus);
+	for (i = 0; i < BH_LRU_SIZE; i++) {
+		swap(evictee, b->bhs[i]);
+		if (evictee == bh) {
+			bh_lru_unlock();
+			return;
+		}
+	}
+
+	get_bh(bh);
+	bh_lru_unlock();
+	brelse(evictee);
+}
+
+/*
+ * Look up the bh in this cpu's LRU.  If it's there, move it to the head.
+ */
+static struct buffer_head *
+lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
+{
+	struct buffer_head *ret = NULL;
+	unsigned int i;
+
+	check_irqs_on();
+	bh_lru_lock();
+	for (i = 0; i < BH_LRU_SIZE; i++) {
+		struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]);
+
+		if (bh && bh->b_blocknr == block && bh->b_bdev == bdev &&
+		    bh->b_size == size) {
+			if (i) {
+				while (i) {
+					__this_cpu_write(bh_lrus.bhs[i],
+						__this_cpu_read(bh_lrus.bhs[i - 1]));
+					i--;
+				}
+				__this_cpu_write(bh_lrus.bhs[0], bh);
+			}
+			get_bh(bh);
+			ret = bh;
+			break;
+		}
+	}
+	bh_lru_unlock();
+	return ret;
+}
+
+/*
+ * Perform a pagecache lookup for the matching buffer.  If it's there, refresh
+ * it in the LRU and mark it as accessed.  If it is not present then return
+ * NULL
+ */
+struct buffer_head *
+__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
+{
+	struct buffer_head *bh = lookup_bh_lru(bdev, block, size);
+
+	if (bh == NULL) {
+		/* __find_get_block_slow will mark the page accessed */
+		bh = __find_get_block_slow(bdev, block);
+		if (bh)
+			bh_lru_install(bh);
+	} else
+		touch_buffer(bh);
+
+	return bh;
+}
+EXPORT_SYMBOL(__find_get_block);
+
+/*
+ * __getblk_gfp() will locate (and, if necessary, create) the buffer_head
+ * which corresponds to the passed block_device, block and size. The
+ * returned buffer has its reference count incremented.
+ *
+ * __getblk_gfp() will lock up the machine if grow_dev_page's
+ * try_to_free_buffers() attempt is failing.  FIXME, perhaps?
+ */
+struct buffer_head *
+__getblk_gfp(struct block_device *bdev, sector_t block,
+	     unsigned size, gfp_t gfp)
+{
+	struct buffer_head *bh = __find_get_block(bdev, block, size);
+
+	might_sleep();
+	if (bh == NULL)
+		bh = __getblk_slow(bdev, block, size, gfp);
+	return bh;
+}
+EXPORT_SYMBOL(__getblk_gfp);
+
+/*
+ * Do async read-ahead on a buffer..
+ */
+void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
+{
+	struct buffer_head *bh = __getblk(bdev, block, size);
+	if (likely(bh)) {
+		ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
+		brelse(bh);
+	}
+}
+EXPORT_SYMBOL(__breadahead);
+
+/**
+ *  __bread_gfp() - reads a specified block and returns the bh
+ *  @bdev: the block_device to read from
+ *  @block: number of block
+ *  @size: size (in bytes) to read
+ *  @gfp: page allocation flag
+ *
+ *  Reads a specified block, and returns buffer head that contains it.
+ *  The page cache can be allocated from non-movable area
+ *  not to prevent page migration if you set gfp to zero.
+ *  It returns NULL if the block was unreadable.
+ */
+struct buffer_head *
+__bread_gfp(struct block_device *bdev, sector_t block,
+		   unsigned size, gfp_t gfp)
+{
+	struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
+
+	if (likely(bh) && !buffer_uptodate(bh))
+		bh = __bread_slow(bh);
+	return bh;
+}
+EXPORT_SYMBOL(__bread_gfp);
+
+/*
+ * invalidate_bh_lrus() is called rarely - but not only at unmount.
+ * This doesn't race because it runs in each cpu either in irq
+ * or with preempt disabled.
+ */
+static void invalidate_bh_lru(void *arg)
+{
+	struct bh_lru *b = &get_cpu_var(bh_lrus);
+	int i;
+
+	for (i = 0; i < BH_LRU_SIZE; i++) {
+		brelse(b->bhs[i]);
+		b->bhs[i] = NULL;
+	}
+	put_cpu_var(bh_lrus);
+}
+
+static bool has_bh_in_lru(int cpu, void *dummy)
+{
+	struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
+	int i;
+	
+	for (i = 0; i < BH_LRU_SIZE; i++) {
+		if (b->bhs[i])
+			return 1;
+	}
+
+	return 0;
+}
+
+void invalidate_bh_lrus(void)
+{
+	on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1, GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
+
+void set_bh_page(struct buffer_head *bh,
+		struct page *page, unsigned long offset)
+{
+	bh->b_page = page;
+	BUG_ON(offset >= PAGE_SIZE);
+	if (PageHighMem(page))
+		/*
+		 * This catches illegal uses and preserves the offset:
+		 */
+		bh->b_data = (char *)(0 + offset);
+	else
+		bh->b_data = page_address(page) + offset;
+}
+EXPORT_SYMBOL(set_bh_page);
+
+/*
+ * Called when truncating a buffer on a page completely.
+ */
+
+/* Bits that are cleared during an invalidate */
+#define BUFFER_FLAGS_DISCARD \
+	(1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \
+	 1 << BH_Delay | 1 << BH_Unwritten)
+
+static void discard_buffer(struct buffer_head * bh)
+{
+	unsigned long b_state, b_state_old;
+
+	lock_buffer(bh);
+	clear_buffer_dirty(bh);
+	bh->b_bdev = NULL;
+	b_state = bh->b_state;
+	for (;;) {
+		b_state_old = cmpxchg(&bh->b_state, b_state,
+				      (b_state & ~BUFFER_FLAGS_DISCARD));
+		if (b_state_old == b_state)
+			break;
+		b_state = b_state_old;
+	}
+	unlock_buffer(bh);
+}
+
+/**
+ * block_invalidatepage - invalidate part or all of a buffer-backed page
+ *
+ * @page: the page which is affected
+ * @offset: start of the range to invalidate
+ * @length: length of the range to invalidate
+ *
+ * block_invalidatepage() is called when all or part of the page has become
+ * invalidated by a truncate operation.
+ *
+ * block_invalidatepage() does not have to release all buffers, but it must
+ * ensure that no dirty buffer is left outside @offset and that no I/O
+ * is underway against any of the blocks which are outside the truncation
+ * point.  Because the caller is about to free (and possibly reuse) those
+ * blocks on-disk.
+ */
+void block_invalidatepage(struct page *page, unsigned int offset,
+			  unsigned int length)
+{
+	struct buffer_head *head, *bh, *next;
+	unsigned int curr_off = 0;
+	unsigned int stop = length + offset;
+
+	BUG_ON(!PageLocked(page));
+	if (!page_has_buffers(page))
+		goto out;
+
+	/*
+	 * Check for overflow
+	 */
+	BUG_ON(stop > PAGE_SIZE || stop < length);
+
+	head = page_buffers(page);
+	bh = head;
+	do {
+		unsigned int next_off = curr_off + bh->b_size;
+		next = bh->b_this_page;
+
+		/*
+		 * Are we still fully in range ?
+		 */
+		if (next_off > stop)
+			goto out;
+
+		/*
+		 * is this block fully invalidated?
+		 */
+		if (offset <= curr_off)
+			discard_buffer(bh);
+		curr_off = next_off;
+		bh = next;
+	} while (bh != head);
+
+	/*
+	 * We release buffers only if the entire page is being invalidated.
+	 * The get_block cached value has been unconditionally invalidated,
+	 * so real IO is not possible anymore.
+	 */
+	if (length == PAGE_SIZE)
+		try_to_release_page(page, 0);
+out:
+	return;
+}
+EXPORT_SYMBOL(block_invalidatepage);
+
+
+/*
+ * We attach and possibly dirty the buffers atomically wrt
+ * __set_page_dirty_buffers() via private_lock.  try_to_free_buffers
+ * is already excluded via the page lock.
+ */
+void create_empty_buffers(struct page *page,
+			unsigned long blocksize, unsigned long b_state)
+{
+	struct buffer_head *bh, *head, *tail;
+
+	head = alloc_page_buffers(page, blocksize, true);
+	bh = head;
+	do {
+		bh->b_state |= b_state;
+		tail = bh;
+		bh = bh->b_this_page;
+	} while (bh);
+	tail->b_this_page = head;
+
+	spin_lock(&page->mapping->private_lock);
+	if (PageUptodate(page) || PageDirty(page)) {
+		bh = head;
+		do {
+			if (PageDirty(page))
+				set_buffer_dirty(bh);
+			if (PageUptodate(page))
+				set_buffer_uptodate(bh);
+			bh = bh->b_this_page;
+		} while (bh != head);
+	}
+	attach_page_buffers(page, head);
+	spin_unlock(&page->mapping->private_lock);
+}
+EXPORT_SYMBOL(create_empty_buffers);
+
+/**
+ * clean_bdev_aliases: clean a range of buffers in block device
+ * @bdev: Block device to clean buffers in
+ * @block: Start of a range of blocks to clean
+ * @len: Number of blocks to clean
+ *
+ * We are taking a range of blocks for data and we don't want writeback of any
+ * buffer-cache aliases starting from return from this function and until the
+ * moment when something will explicitly mark the buffer dirty (hopefully that
+ * will not happen until we will free that block ;-) We don't even need to mark
+ * it not-uptodate - nobody can expect anything from a newly allocated buffer
+ * anyway. We used to use unmap_buffer() for such invalidation, but that was
+ * wrong. We definitely don't want to mark the alias unmapped, for example - it
+ * would confuse anyone who might pick it with bread() afterwards...
+ *
+ * Also..  Note that bforget() doesn't lock the buffer.  So there can be
+ * writeout I/O going on against recently-freed buffers.  We don't wait on that
+ * I/O in bforget() - it's more efficient to wait on the I/O only if we really
+ * need to.  That happens here.
+ */
+void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
+{
+	struct inode *bd_inode = bdev->bd_inode;
+	struct address_space *bd_mapping = bd_inode->i_mapping;
+	struct pagevec pvec;
+	pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
+	pgoff_t end;
+	int i, count;
+	struct buffer_head *bh;
+	struct buffer_head *head;
+
+	end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits);
+	pagevec_init(&pvec);
+	while (pagevec_lookup_range(&pvec, bd_mapping, &index, end)) {
+		count = pagevec_count(&pvec);
+		for (i = 0; i < count; i++) {
+			struct page *page = pvec.pages[i];
+
+			if (!page_has_buffers(page))
+				continue;
+			/*
+			 * We use page lock instead of bd_mapping->private_lock
+			 * to pin buffers here since we can afford to sleep and
+			 * it scales better than a global spinlock lock.
+			 */
+			lock_page(page);
+			/* Recheck when the page is locked which pins bhs */
+			if (!page_has_buffers(page))
+				goto unlock_page;
+			head = page_buffers(page);
+			bh = head;
+			do {
+				if (!buffer_mapped(bh) || (bh->b_blocknr < block))
+					goto next;
+				if (bh->b_blocknr >= block + len)
+					break;
+				clear_buffer_dirty(bh);
+				wait_on_buffer(bh);
+				clear_buffer_req(bh);
+next:
+				bh = bh->b_this_page;
+			} while (bh != head);
+unlock_page:
+			unlock_page(page);
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+		/* End of range already reached? */
+		if (index > end || !index)
+			break;
+	}
+}
+EXPORT_SYMBOL(clean_bdev_aliases);
+
+/*
+ * Size is a power-of-two in the range 512..PAGE_SIZE,
+ * and the case we care about most is PAGE_SIZE.
+ *
+ * So this *could* possibly be written with those
+ * constraints in mind (relevant mostly if some
+ * architecture has a slow bit-scan instruction)
+ */
+static inline int block_size_bits(unsigned int blocksize)
+{
+	return ilog2(blocksize);
+}
+
+static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state)
+{
+	BUG_ON(!PageLocked(page));
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, 1 << READ_ONCE(inode->i_blkbits),
+				     b_state);
+	return page_buffers(page);
+}
+
+/*
+ * NOTE! All mapped/uptodate combinations are valid:
+ *
+ *	Mapped	Uptodate	Meaning
+ *
+ *	No	No		"unknown" - must do get_block()
+ *	No	Yes		"hole" - zero-filled
+ *	Yes	No		"allocated" - allocated on disk, not read in
+ *	Yes	Yes		"valid" - allocated and up-to-date in memory.
+ *
+ * "Dirty" is valid only with the last case (mapped+uptodate).
+ */
+
+/*
+ * While block_write_full_page is writing back the dirty buffers under
+ * the page lock, whoever dirtied the buffers may decide to clean them
+ * again at any time.  We handle that by only looking at the buffer
+ * state inside lock_buffer().
+ *
+ * If block_write_full_page() is called for regular writeback
+ * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a
+ * locked buffer.   This only can happen if someone has written the buffer
+ * directly, with submit_bh().  At the address_space level PageWriteback
+ * prevents this contention from occurring.
+ *
+ * If block_write_full_page() is called with wbc->sync_mode ==
+ * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this
+ * causes the writes to be flagged as synchronous writes.
+ */
+int __block_write_full_page(struct inode *inode, struct page *page,
+			get_block_t *get_block, struct writeback_control *wbc,
+			bh_end_io_t *handler)
+{
+	int err;
+	sector_t block;
+	sector_t last_block;
+	struct buffer_head *bh, *head;
+	unsigned int blocksize, bbits;
+	int nr_underway = 0;
+	int write_flags = wbc_to_write_flags(wbc);
+
+	head = create_page_buffers(page, inode,
+					(1 << BH_Dirty)|(1 << BH_Uptodate));
+
+	/*
+	 * Be very careful.  We have no exclusion from __set_page_dirty_buffers
+	 * here, and the (potentially unmapped) buffers may become dirty at
+	 * any time.  If a buffer becomes dirty here after we've inspected it
+	 * then we just miss that fact, and the page stays dirty.
+	 *
+	 * Buffers outside i_size may be dirtied by __set_page_dirty_buffers;
+	 * handle that here by just cleaning them.
+	 */
+
+	bh = head;
+	blocksize = bh->b_size;
+	bbits = block_size_bits(blocksize);
+
+	block = (sector_t)page->index << (PAGE_SHIFT - bbits);
+	last_block = (i_size_read(inode) - 1) >> bbits;
+
+	/*
+	 * Get all the dirty buffers mapped to disk addresses and
+	 * handle any aliases from the underlying blockdev's mapping.
+	 */
+	do {
+		if (block > last_block) {
+			/*
+			 * mapped buffers outside i_size will occur, because
+			 * this page can be outside i_size when there is a
+			 * truncate in progress.
+			 */
+			/*
+			 * The buffer was zeroed by block_write_full_page()
+			 */
+			clear_buffer_dirty(bh);
+			set_buffer_uptodate(bh);
+		} else if ((!buffer_mapped(bh) || buffer_delay(bh)) &&
+			   buffer_dirty(bh)) {
+			WARN_ON(bh->b_size != blocksize);
+			err = get_block(inode, block, bh, 1);
+			if (err)
+				goto recover;
+			clear_buffer_delay(bh);
+			if (buffer_new(bh)) {
+				/* blockdev mappings never come here */
+				clear_buffer_new(bh);
+				clean_bdev_bh_alias(bh);
+			}
+		}
+		bh = bh->b_this_page;
+		block++;
+	} while (bh != head);
+
+	do {
+		if (!buffer_mapped(bh))
+			continue;
+		/*
+		 * If it's a fully non-blocking write attempt and we cannot
+		 * lock the buffer then redirty the page.  Note that this can
+		 * potentially cause a busy-wait loop from writeback threads
+		 * and kswapd activity, but those code paths have their own
+		 * higher-level throttling.
+		 */
+		if (wbc->sync_mode != WB_SYNC_NONE) {
+			lock_buffer(bh);
+		} else if (!trylock_buffer(bh)) {
+			redirty_page_for_writepage(wbc, page);
+			continue;
+		}
+		if (test_clear_buffer_dirty(bh)) {
+			mark_buffer_async_write_endio(bh, handler);
+		} else {
+			unlock_buffer(bh);
+		}
+	} while ((bh = bh->b_this_page) != head);
+
+	/*
+	 * The page and its buffers are protected by PageWriteback(), so we can
+	 * drop the bh refcounts early.
+	 */
+	BUG_ON(PageWriteback(page));
+	set_page_writeback(page);
+
+	do {
+		struct buffer_head *next = bh->b_this_page;
+		if (buffer_async_write(bh)) {
+			submit_bh_wbc(REQ_OP_WRITE, write_flags, bh,
+					inode->i_write_hint, wbc);
+			nr_underway++;
+		}
+		bh = next;
+	} while (bh != head);
+	unlock_page(page);
+
+	err = 0;
+done:
+	if (nr_underway == 0) {
+		/*
+		 * The page was marked dirty, but the buffers were
+		 * clean.  Someone wrote them back by hand with
+		 * ll_rw_block/submit_bh.  A rare case.
+		 */
+		end_page_writeback(page);
+
+		/*
+		 * The page and buffer_heads can be released at any time from
+		 * here on.
+		 */
+	}
+	return err;
+
+recover:
+	/*
+	 * ENOSPC, or some other error.  We may already have added some
+	 * blocks to the file, so we need to write these out to avoid
+	 * exposing stale data.
+	 * The page is currently locked and not marked for writeback
+	 */
+	bh = head;
+	/* Recovery: lock and submit the mapped buffers */
+	do {
+		if (buffer_mapped(bh) && buffer_dirty(bh) &&
+		    !buffer_delay(bh)) {
+			lock_buffer(bh);
+			mark_buffer_async_write_endio(bh, handler);
+		} else {
+			/*
+			 * The buffer may have been set dirty during
+			 * attachment to a dirty page.
+			 */
+			clear_buffer_dirty(bh);
+		}
+	} while ((bh = bh->b_this_page) != head);
+	SetPageError(page);
+	BUG_ON(PageWriteback(page));
+	mapping_set_error(page->mapping, err);
+	set_page_writeback(page);
+	do {
+		struct buffer_head *next = bh->b_this_page;
+		if (buffer_async_write(bh)) {
+			clear_buffer_dirty(bh);
+			submit_bh_wbc(REQ_OP_WRITE, write_flags, bh,
+					inode->i_write_hint, wbc);
+			nr_underway++;
+		}
+		bh = next;
+	} while (bh != head);
+	unlock_page(page);
+	goto done;
+}
+EXPORT_SYMBOL(__block_write_full_page);
+
+/*
+ * If a page has any new buffers, zero them out here, and mark them uptodate
+ * and dirty so they'll be written out (in order to prevent uninitialised
+ * block data from leaking). And clear the new bit.
+ */
+void page_zero_new_buffers(struct page *page, unsigned from, unsigned to)
+{
+	unsigned int block_start, block_end;
+	struct buffer_head *head, *bh;
+
+	BUG_ON(!PageLocked(page));
+	if (!page_has_buffers(page))
+		return;
+
+	bh = head = page_buffers(page);
+	block_start = 0;
+	do {
+		block_end = block_start + bh->b_size;
+
+		if (buffer_new(bh)) {
+			if (block_end > from && block_start < to) {
+				if (!PageUptodate(page)) {
+					unsigned start, size;
+
+					start = max(from, block_start);
+					size = min(to, block_end) - start;
+
+					zero_user(page, start, size);
+					set_buffer_uptodate(bh);
+				}
+
+				clear_buffer_new(bh);
+				mark_buffer_dirty(bh);
+			}
+		}
+
+		block_start = block_end;
+		bh = bh->b_this_page;
+	} while (bh != head);
+}
+EXPORT_SYMBOL(page_zero_new_buffers);
+
+static void
+iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
+		struct iomap *iomap)
+{
+	loff_t offset = block << inode->i_blkbits;
+
+	bh->b_bdev = iomap->bdev;
+
+	/*
+	 * Block points to offset in file we need to map, iomap contains
+	 * the offset at which the map starts. If the map ends before the
+	 * current block, then do not map the buffer and let the caller
+	 * handle it.
+	 */
+	BUG_ON(offset >= iomap->offset + iomap->length);
+
+	switch (iomap->type) {
+	case IOMAP_HOLE:
+		/*
+		 * If the buffer is not up to date or beyond the current EOF,
+		 * we need to mark it as new to ensure sub-block zeroing is
+		 * executed if necessary.
+		 */
+		if (!buffer_uptodate(bh) ||
+		    (offset >= i_size_read(inode)))
+			set_buffer_new(bh);
+		break;
+	case IOMAP_DELALLOC:
+		if (!buffer_uptodate(bh) ||
+		    (offset >= i_size_read(inode)))
+			set_buffer_new(bh);
+		set_buffer_uptodate(bh);
+		set_buffer_mapped(bh);
+		set_buffer_delay(bh);
+		break;
+	case IOMAP_UNWRITTEN:
+		/*
+		 * For unwritten regions, we always need to ensure that regions
+		 * in the block we are not writing to are zeroed. Mark the
+		 * buffer as new to ensure this.
+		 */
+		set_buffer_new(bh);
+		set_buffer_unwritten(bh);
+		/* FALLTHRU */
+	case IOMAP_MAPPED:
+		if ((iomap->flags & IOMAP_F_NEW) ||
+		    offset >= i_size_read(inode))
+			set_buffer_new(bh);
+		bh->b_blocknr = (iomap->addr + offset - iomap->offset) >>
+				inode->i_blkbits;
+		set_buffer_mapped(bh);
+		break;
+	}
+}
+
+int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
+		get_block_t *get_block, struct iomap *iomap)
+{
+	unsigned from = pos & (PAGE_SIZE - 1);
+	unsigned to = from + len;
+	struct inode *inode = page->mapping->host;
+	unsigned block_start, block_end;
+	sector_t block;
+	int err = 0;
+	unsigned blocksize, bbits;
+	struct buffer_head *bh, *head, *wait[2], **wait_bh=wait;
+
+	BUG_ON(!PageLocked(page));
+	BUG_ON(from > PAGE_SIZE);
+	BUG_ON(to > PAGE_SIZE);
+	BUG_ON(from > to);
+
+	head = create_page_buffers(page, inode, 0);
+	blocksize = head->b_size;
+	bbits = block_size_bits(blocksize);
+
+	block = (sector_t)page->index << (PAGE_SHIFT - bbits);
+
+	for(bh = head, block_start = 0; bh != head || !block_start;
+	    block++, block_start=block_end, bh = bh->b_this_page) {
+		block_end = block_start + blocksize;
+		if (block_end <= from || block_start >= to) {
+			if (PageUptodate(page)) {
+				if (!buffer_uptodate(bh))
+					set_buffer_uptodate(bh);
+			}
+			continue;
+		}
+		if (buffer_new(bh))
+			clear_buffer_new(bh);
+		if (!buffer_mapped(bh)) {
+			WARN_ON(bh->b_size != blocksize);
+			if (get_block) {
+				err = get_block(inode, block, bh, 1);
+				if (err)
+					break;
+			} else {
+				iomap_to_bh(inode, block, bh, iomap);
+			}
+
+			if (buffer_new(bh)) {
+				clean_bdev_bh_alias(bh);
+				if (PageUptodate(page)) {
+					clear_buffer_new(bh);
+					set_buffer_uptodate(bh);
+					mark_buffer_dirty(bh);
+					continue;
+				}
+				if (block_end > to || block_start < from)
+					zero_user_segments(page,
+						to, block_end,
+						block_start, from);
+				continue;
+			}
+		}
+		if (PageUptodate(page)) {
+			if (!buffer_uptodate(bh))
+				set_buffer_uptodate(bh);
+			continue; 
+		}
+		if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
+		    !buffer_unwritten(bh) &&
+		     (block_start < from || block_end > to)) {
+#ifdef SKIP_DEPRECATED
+			pr_debug("Skipping DEPRECATED call");
+#else
+			pr_debug("will ll_rw_block() (DEPRECATED)");
+			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+			*wait_bh++=bh;
+			pr_debug("done DEPRECATED ll_rw_block()");
+#endif
+		}
+	}
+	/*
+	 * If we issued read requests - let them complete.
+	 */
+	while(wait_bh > wait) {
+		wait_on_buffer(*--wait_bh);
+		if (!buffer_uptodate(*wait_bh))
+			err = -EIO;
+	}
+	if (unlikely(err))
+		page_zero_new_buffers(page, from, to);
+	return err;
+}
+
+int __block_write_begin(struct page *page, loff_t pos, unsigned len,
+		get_block_t *get_block)
+{
+	return __block_write_begin_int(page, pos, len, get_block, NULL);
+}
+EXPORT_SYMBOL(__block_write_begin);
+
+static int __block_commit_write(struct inode *inode, struct page *page,
+		unsigned from, unsigned to)
+{
+	unsigned block_start, block_end;
+	int partial = 0;
+	unsigned blocksize;
+	struct buffer_head *bh, *head;
+
+	bh = head = page_buffers(page);
+	blocksize = bh->b_size;
+
+	block_start = 0;
+	do {
+		block_end = block_start + blocksize;
+		if (block_end <= from || block_start >= to) {
+			if (!buffer_uptodate(bh))
+				partial = 1;
+		} else {
+			set_buffer_uptodate(bh);
+			mark_buffer_dirty(bh);
+		}
+		clear_buffer_new(bh);
+
+		block_start = block_end;
+		bh = bh->b_this_page;
+	} while (bh != head);
+
+	/*
+	 * If this is a partial write which happened to make all buffers
+	 * uptodate then we can optimize away a bogus readpage() for
+	 * the next read(). Here we 'discover' whether the page went
+	 * uptodate as a result of this (potentially partial) write.
+	 */
+	if (!partial)
+		SetPageUptodate(page);
+	return 0;
+}
+
+/*
+ * block_write_begin takes care of the basic task of block allocation and
+ * bringing partial write blocks uptodate first.
+ *
+ * The filesystem needs to handle block truncation upon failure.
+ */
+int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
+		unsigned flags, struct page **pagep, get_block_t *get_block)
+{
+	pgoff_t index = pos >> PAGE_SHIFT;
+	struct page *page;
+	int status;
+	if (len < 4096) {
+		pr_debug("pos = %llu, len=%u < 4096", pos,len); // each 4096 bytes, first is aligned to page, last - whatever remains
+	}
+	page = grab_cache_page_write_begin(mapping, index, flags);
+	if (!page)
+		return -ENOMEM;
+
+	status = __block_write_begin(page, pos, len, get_block);
+	if (unlikely(status)) {
+		unlock_page(page);
+		put_page(page);
+		page = NULL;
+	}
+	*pagep = page;
+	return status;
+}
+EXPORT_SYMBOL(block_write_begin);
+
+int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
+		struct page *page)
+{
+	loff_t old_size = inode->i_size;
+	bool i_size_changed = false;
+
+	/*
+	 * No need to use i_size_read() here, the i_size cannot change under us
+	 * because we hold i_rwsem.
+	 *
+	 * But it's important to update i_size while still holding page lock:
+	 * page writeout could otherwise come in and zero beyond i_size.
+	 */
+	if (pos + copied > inode->i_size) {
+		i_size_write(inode, pos + copied);
+		i_size_changed = true;
+	}
+
+	unlock_page(page);
+	put_page(page);
+
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
+	/*
+	 * Don't mark the inode dirty under page lock. First, it unnecessarily
+	 * makes the holding time of page lock longer. Second, it forces lock
+	 * ordering of page lock and transaction start for journaling
+	 * filesystems.
+	 */
+	if (i_size_changed) {
+		pr_debug("mark_inode_dirty");
+		mark_inode_dirty(inode);
+	}
+	pr_debug("copied=%u", copied);
+	return copied;
+}
+
+int block_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
+{
+	struct inode *inode = mapping->host;
+	unsigned start;
+
+	start = pos & (PAGE_SIZE - 1);
+
+	if (unlikely(copied < len)) {
+		/*
+		 * The buffers that were written will now be uptodate, so we
+		 * don't have to worry about a readpage reading them and
+		 * overwriting a partial write. However if we have encountered
+		 * a short write and only partially written into a buffer, it
+		 * will not be marked uptodate, so a readpage might come in and
+		 * destroy our partial write.
+		 *
+		 * Do the simplest thing, and just treat any short write to a
+		 * non uptodate page as a zero-length write, and force the
+		 * caller to redo the whole thing.
+		 */
+		if (!PageUptodate(page))
+			copied = 0;
+
+		page_zero_new_buffers(page, start+copied, start+len);
+	}
+	flush_dcache_page(page);
+
+	/* This could be a short (even 0-length) commit */
+	__block_commit_write(inode, page, start, start+copied);
+
+	return copied;
+}
+EXPORT_SYMBOL(block_write_end);
+
+int generic_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
+{
+	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+	return __generic_write_end(mapping->host, pos, copied, page);
+}
+EXPORT_SYMBOL(generic_write_end);
+
+/*
+ * block_is_partially_uptodate checks whether buffers within a page are
+ * uptodate or not.
+ *
+ * Returns true if all buffers which correspond to a file portion
+ * we want to read are uptodate.
+ */
+int block_is_partially_uptodate(struct page *page, unsigned long from,
+					unsigned long count)
+{
+	unsigned block_start, block_end, blocksize;
+	unsigned to;
+	struct buffer_head *bh, *head;
+	int ret = 1;
+
+	if (!page_has_buffers(page))
+		return 0;
+
+	head = page_buffers(page);
+	blocksize = head->b_size;
+	to = min_t(unsigned, PAGE_SIZE - from, count);
+	to = from + to;
+	if (from < blocksize && to > PAGE_SIZE - blocksize)
+		return 0;
+
+	bh = head;
+	block_start = 0;
+	do {
+		block_end = block_start + blocksize;
+		if (block_end > from && block_start < to) {
+			if (!buffer_uptodate(bh)) {
+				ret = 0;
+				break;
+			}
+			if (block_end >= to)
+				break;
+		}
+		block_start = block_end;
+		bh = bh->b_this_page;
+	} while (bh != head);
+
+	return ret;
+}
+EXPORT_SYMBOL(block_is_partially_uptodate);
+
+/*
+ * Generic "read page" function for block devices that have the normal
+ * get_block functionality. This is most of the block device filesystems.
+ * Reads the page asynchronously --- the unlock_buffer() and
+ * set/clear_buffer_uptodate() functions propagate buffer state into the
+ * page struct once IO has completed.
+ */
+int block_read_full_page(struct page *page, get_block_t *get_block)
+{
+	struct inode *inode = page->mapping->host;
+	sector_t iblock, lblock;
+	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
+	unsigned int blocksize, bbits;
+	int nr, i;
+	int fully_mapped = 1;
+
+	head = create_page_buffers(page, inode, 0);
+	blocksize = head->b_size;
+	bbits = block_size_bits(blocksize);
+
+	iblock = (sector_t)page->index << (PAGE_SHIFT - bbits);
+	lblock = (i_size_read(inode)+blocksize-1) >> bbits;
+	bh = head;
+	nr = 0;
+	i = 0;
+
+	do {
+		if (buffer_uptodate(bh))
+			continue;
+
+		if (!buffer_mapped(bh)) {
+			int err = 0;
+
+			fully_mapped = 0;
+			if (iblock < lblock) {
+				WARN_ON(bh->b_size != blocksize);
+				err = get_block(inode, iblock, bh, 0);
+				if (err)
+					SetPageError(page);
+			}
+			if (!buffer_mapped(bh)) {
+				zero_user(page, i * blocksize, blocksize);
+				if (!err)
+					set_buffer_uptodate(bh);
+				continue;
+			}
+			/*
+			 * get_block() might have updated the buffer
+			 * synchronously
+			 */
+			if (buffer_uptodate(bh))
+				continue;
+		}
+		arr[nr++] = bh;
+	} while (i++, iblock++, (bh = bh->b_this_page) != head);
+
+	if (fully_mapped)
+		SetPageMappedToDisk(page);
+
+	if (!nr) {
+		/*
+		 * All buffers are uptodate - we can set the page uptodate
+		 * as well. But not if get_block() returned an error.
+		 */
+		if (!PageError(page))
+			SetPageUptodate(page);
+		unlock_page(page);
+		return 0;
+	}
+
+	/* Stage two: lock the buffers */
+	for (i = 0; i < nr; i++) {
+		bh = arr[i];
+		lock_buffer(bh);
+		mark_buffer_async_read(bh);
+	}
+
+	/*
+	 * Stage 3: start the IO.  Check for uptodateness
+	 * inside the buffer lock in case another process reading
+	 * the underlying blockdev brought it uptodate (the sct fix).
+	 */
+	for (i = 0; i < nr; i++) {
+		bh = arr[i];
+		if (buffer_uptodate(bh))
+			end_buffer_async_read(bh, 1);
+		else
+			submit_bh(REQ_OP_READ, 0, bh);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(block_read_full_page);
+
+/* utility function for filesystems that need to do work on expanding
+ * truncates.  Uses filesystem pagecache writes to allow the filesystem to
+ * deal with the hole.  
+ */
+int generic_cont_expand_simple(struct inode *inode, loff_t size)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct page *page;
+	void *fsdata;
+	int err;
+
+	err = inode_newsize_ok(inode, size);
+	if (err)
+		goto out;
+
+	err = pagecache_write_begin(NULL, mapping, size, 0,
+				    AOP_FLAG_CONT_EXPAND, &page, &fsdata);
+	if (err)
+		goto out;
+
+	err = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata);
+	BUG_ON(err > 0);
+
+out:
+	return err;
+}
+EXPORT_SYMBOL(generic_cont_expand_simple);
+
+static int cont_expand_zero(struct file *file, struct address_space *mapping,
+			    loff_t pos, loff_t *bytes)
+{
+	struct inode *inode = mapping->host;
+	unsigned int blocksize = i_blocksize(inode);
+	struct page *page;
+	void *fsdata;
+	pgoff_t index, curidx;
+	loff_t curpos;
+	unsigned zerofrom, offset, len;
+	int err = 0;
+
+	index = pos >> PAGE_SHIFT;
+	offset = pos & ~PAGE_MASK;
+
+	while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) {
+		zerofrom = curpos & ~PAGE_MASK;
+		if (zerofrom & (blocksize-1)) {
+			*bytes |= (blocksize-1);
+			(*bytes)++;
+		}
+		len = PAGE_SIZE - zerofrom;
+
+		err = pagecache_write_begin(file, mapping, curpos, len, 0,
+					    &page, &fsdata);
+		if (err)
+			goto out;
+		zero_user(page, zerofrom, len);
+		err = pagecache_write_end(file, mapping, curpos, len, len,
+						page, fsdata);
+		if (err < 0)
+			goto out;
+		BUG_ON(err != len);
+		err = 0;
+
+		balance_dirty_pages_ratelimited(mapping);
+
+		if (unlikely(fatal_signal_pending(current))) {
+			err = -EINTR;
+			goto out;
+		}
+	}
+
+	/* page covers the boundary, find the boundary offset */
+	if (index == curidx) {
+		zerofrom = curpos & ~PAGE_MASK;
+		/* if we will expand the thing last block will be filled */
+		if (offset <= zerofrom) {
+			goto out;
+		}
+		if (zerofrom & (blocksize-1)) {
+			*bytes |= (blocksize-1);
+			(*bytes)++;
+		}
+		len = offset - zerofrom;
+
+		err = pagecache_write_begin(file, mapping, curpos, len, 0,
+					    &page, &fsdata);
+		if (err)
+			goto out;
+		zero_user(page, zerofrom, len);
+		err = pagecache_write_end(file, mapping, curpos, len, len,
+						page, fsdata);
+		if (err < 0)
+			goto out;
+		BUG_ON(err != len);
+		err = 0;
+	}
+out:
+	return err;
+}
+
+/*
+ * For moronic filesystems that do not allow holes in file.
+ * We may have to extend the file.
+ */
+int cont_write_begin(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata,
+			get_block_t *get_block, loff_t *bytes)
+{
+	struct inode *inode = mapping->host;
+	unsigned int blocksize = i_blocksize(inode);
+	unsigned int zerofrom;
+	int err;
+
+	err = cont_expand_zero(file, mapping, pos, bytes);
+	if (err)
+		return err;
+
+	zerofrom = *bytes & ~PAGE_MASK;
+	if (pos+len > *bytes && zerofrom & (blocksize-1)) {
+		*bytes |= (blocksize-1);
+		(*bytes)++;
+	}
+
+	return block_write_begin(mapping, pos, len, flags, pagep, get_block);
+}
+EXPORT_SYMBOL(cont_write_begin);
+
+int block_commit_write(struct page *page, unsigned from, unsigned to)
+{
+	struct inode *inode = page->mapping->host;
+	__block_commit_write(inode,page,from,to);
+	return 0;
+}
+EXPORT_SYMBOL(block_commit_write);
+
+/*
+ * block_page_mkwrite() is not allowed to change the file size as it gets
+ * called from a page fault handler when a page is first dirtied. Hence we must
+ * be careful to check for EOF conditions here. We set the page up correctly
+ * for a written page which means we get ENOSPC checking when writing into
+ * holes and correct delalloc and unwritten extent mapping on filesystems that
+ * support these features.
+ *
+ * We are not allowed to take the i_mutex here so we have to play games to
+ * protect against truncate races as the page could now be beyond EOF.  Because
+ * truncate writes the inode size before removing pages, once we have the
+ * page lock we can determine safely if the page is beyond EOF. If it is not
+ * beyond EOF, then the page is guaranteed safe against truncation until we
+ * unlock the page.
+ *
+ * Direct callers of this function should protect against filesystem freezing
+ * using sb_start_pagefault() - sb_end_pagefault() functions.
+ */
+int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+			 get_block_t get_block)
+{
+	struct page *page = vmf->page;
+	struct inode *inode = file_inode(vma->vm_file);
+	unsigned long end;
+	loff_t size;
+	int ret;
+
+	lock_page(page);
+	size = i_size_read(inode);
+	if ((page->mapping != inode->i_mapping) ||
+	    (page_offset(page) > size)) {
+		/* We overload EFAULT to mean page got truncated */
+		ret = -EFAULT;
+		goto out_unlock;
+	}
+
+	/* page is wholly or partially inside EOF */
+	if (((page->index + 1) << PAGE_SHIFT) > size)
+		end = size & ~PAGE_MASK;
+	else
+		end = PAGE_SIZE;
+
+	ret = __block_write_begin(page, 0, end, get_block);
+	if (!ret)
+		ret = block_commit_write(page, 0, end);
+
+	if (unlikely(ret < 0))
+		goto out_unlock;
+	set_page_dirty(page);
+	wait_for_stable_page(page);
+	return 0;
+out_unlock:
+	unlock_page(page);
+	return ret;
+}
+EXPORT_SYMBOL(block_page_mkwrite);
+
+/*
+ * nobh_write_begin()'s prereads are special: the buffer_heads are freed
+ * immediately, while under the page lock.  So it needs a special end_io
+ * handler which does not touch the bh after unlocking it.
+ */
+static void end_buffer_read_nobh(struct buffer_head *bh, int uptodate)
+{
+	__end_buffer_read_notouch(bh, uptodate);
+}
+
+/*
+ * Attach the singly-linked list of buffers created by nobh_write_begin, to
+ * the page (converting it to circular linked list and taking care of page
+ * dirty races).
+ */
+static void attach_nobh_buffers(struct page *page, struct buffer_head *head)
+{
+	struct buffer_head *bh;
+
+	BUG_ON(!PageLocked(page));
+
+	spin_lock(&page->mapping->private_lock);
+	bh = head;
+	do {
+		if (PageDirty(page))
+			set_buffer_dirty(bh);
+		if (!bh->b_this_page)
+			bh->b_this_page = head;
+		bh = bh->b_this_page;
+	} while (bh != head);
+	attach_page_buffers(page, head);
+	spin_unlock(&page->mapping->private_lock);
+}
+
+/*
+ * On entry, the page is fully not uptodate.
+ * On exit the page is fully uptodate in the areas outside (from,to)
+ * The filesystem needs to handle block truncation upon failure.
+ */
+int nobh_write_begin(struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata,
+			get_block_t *get_block)
+{
+	struct inode *inode = mapping->host;
+	const unsigned blkbits = inode->i_blkbits;
+	const unsigned blocksize = 1 << blkbits;
+	struct buffer_head *head, *bh;
+	struct page *page;
+	pgoff_t index;
+	unsigned from, to;
+	unsigned block_in_page;
+	unsigned block_start, block_end;
+	sector_t block_in_file;
+	int nr_reads = 0;
+	int ret = 0;
+	int is_mapped_to_disk = 1;
+
+	index = pos >> PAGE_SHIFT;
+	from = pos & (PAGE_SIZE - 1);
+	to = from + len;
+
+	page = grab_cache_page_write_begin(mapping, index, flags);
+	if (!page)
+		return -ENOMEM;
+	*pagep = page;
+	*fsdata = NULL;
+
+	if (page_has_buffers(page)) {
+		ret = __block_write_begin(page, pos, len, get_block);
+		if (unlikely(ret))
+			goto out_release;
+		return ret;
+	}
+
+	if (PageMappedToDisk(page))
+		return 0;
+
+	/*
+	 * Allocate buffers so that we can keep track of state, and potentially
+	 * attach them to the page if an error occurs. In the common case of
+	 * no error, they will just be freed again without ever being attached
+	 * to the page (which is all OK, because we're under the page lock).
+	 *
+	 * Be careful: the buffer linked list is a NULL terminated one, rather
+	 * than the circular one we're used to.
+	 */
+	head = alloc_page_buffers(page, blocksize, false);
+	if (!head) {
+		ret = -ENOMEM;
+		goto out_release;
+	}
+
+	block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits);
+
+	/*
+	 * We loop across all blocks in the page, whether or not they are
+	 * part of the affected region.  This is so we can discover if the
+	 * page is fully mapped-to-disk.
+	 */
+	for (block_start = 0, block_in_page = 0, bh = head;
+		  block_start < PAGE_SIZE;
+		  block_in_page++, block_start += blocksize, bh = bh->b_this_page) {
+		int create;
+
+		block_end = block_start + blocksize;
+		bh->b_state = 0;
+		create = 1;
+		if (block_start >= to)
+			create = 0;
+		ret = get_block(inode, block_in_file + block_in_page,
+					bh, create);
+		if (ret)
+			goto failed;
+		if (!buffer_mapped(bh))
+			is_mapped_to_disk = 0;
+		if (buffer_new(bh))
+			clean_bdev_bh_alias(bh);
+		if (PageUptodate(page)) {
+			set_buffer_uptodate(bh);
+			continue;
+		}
+		if (buffer_new(bh) || !buffer_mapped(bh)) {
+			zero_user_segments(page, block_start, from,
+							to, block_end);
+			continue;
+		}
+		if (buffer_uptodate(bh))
+			continue;	/* reiserfs does this */
+		if (block_start < from || block_end > to) {
+			lock_buffer(bh);
+			bh->b_end_io = end_buffer_read_nobh;
+			submit_bh(REQ_OP_READ, 0, bh);
+			nr_reads++;
+		}
+	}
+
+	if (nr_reads) {
+		/*
+		 * The page is locked, so these buffers are protected from
+		 * any VM or truncate activity.  Hence we don't need to care
+		 * for the buffer_head refcounts.
+		 */
+		for (bh = head; bh; bh = bh->b_this_page) {
+			wait_on_buffer(bh);
+			if (!buffer_uptodate(bh))
+				ret = -EIO;
+		}
+		if (ret)
+			goto failed;
+	}
+
+	if (is_mapped_to_disk)
+		SetPageMappedToDisk(page);
+
+	*fsdata = head; /* to be released by nobh_write_end */
+
+	return 0;
+
+failed:
+	BUG_ON(!ret);
+	/*
+	 * Error recovery is a bit difficult. We need to zero out blocks that
+	 * were newly allocated, and dirty them to ensure they get written out.
+	 * Buffers need to be attached to the page at this point, otherwise
+	 * the handling of potential IO errors during writeout would be hard
+	 * (could try doing synchronous writeout, but what if that fails too?)
+	 */
+	attach_nobh_buffers(page, head);
+	page_zero_new_buffers(page, from, to);
+
+out_release:
+	unlock_page(page);
+	put_page(page);
+	*pagep = NULL;
+
+	return ret;
+}
+EXPORT_SYMBOL(nobh_write_begin);
+
+int nobh_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
+{
+	struct inode *inode = page->mapping->host;
+	struct buffer_head *head = fsdata;
+	struct buffer_head *bh;
+	BUG_ON(fsdata != NULL && page_has_buffers(page));
+
+	if (unlikely(copied < len) && head)
+		attach_nobh_buffers(page, head);
+	if (page_has_buffers(page))
+		return generic_write_end(file, mapping, pos, len,
+					copied, page, fsdata);
+
+	SetPageUptodate(page);
+	set_page_dirty(page);
+	if (pos+copied > inode->i_size) {
+		i_size_write(inode, pos+copied);
+		mark_inode_dirty(inode);
+	}
+
+	unlock_page(page);
+	put_page(page);
+
+	while (head) {
+		bh = head;
+		head = head->b_this_page;
+		free_buffer_head(bh);
+	}
+
+	return copied;
+}
+EXPORT_SYMBOL(nobh_write_end);
+
+/*
+ * nobh_writepage() - based on block_full_write_page() except
+ * that it tries to operate without attaching bufferheads to
+ * the page.
+ */
+int nobh_writepage(struct page *page, get_block_t *get_block,
+			struct writeback_control *wbc)
+{
+	struct inode * const inode = page->mapping->host;
+	loff_t i_size = i_size_read(inode);
+	const pgoff_t end_index = i_size >> PAGE_SHIFT;
+	unsigned offset;
+	int ret;
+
+	/* Is the page fully inside i_size? */
+	if (page->index < end_index)
+		goto out;
+
+	/* Is the page fully outside i_size? (truncate in progress) */
+	offset = i_size & (PAGE_SIZE-1);
+	if (page->index >= end_index+1 || !offset) {
+		/*
+		 * The page may have dirty, unmapped buffers.  For example,
+		 * they may have been added in ext3_writepage().  Make them
+		 * freeable here, so the page does not leak.
+		 */
+#if 0
+		/* Not really sure about this  - do we need this ? */
+		if (page->mapping->a_ops->invalidatepage)
+			page->mapping->a_ops->invalidatepage(page, offset);
+#endif
+		unlock_page(page);
+		return 0; /* don't care */
+	}
+
+	/*
+	 * The page straddles i_size.  It must be zeroed out on each and every
+	 * writepage invocation because it may be mmapped.  "A file is mapped
+	 * in multiples of the page size.  For a file that is not a multiple of
+	 * the  page size, the remaining memory is zeroed when mapped, and
+	 * writes to that region are not written out to the file."
+	 */
+	zero_user_segment(page, offset, PAGE_SIZE);
+out:
+	ret = mpage_writepage(page, get_block, wbc);
+	if (ret == -EAGAIN)
+		ret = __block_write_full_page(inode, page, get_block, wbc,
+					      end_buffer_async_write);
+	return ret;
+}
+EXPORT_SYMBOL(nobh_writepage);
+
+int nobh_truncate_page(struct address_space *mapping,
+			loff_t from, get_block_t *get_block)
+{
+	pgoff_t index = from >> PAGE_SHIFT;
+	unsigned offset = from & (PAGE_SIZE-1);
+	unsigned blocksize;
+	sector_t iblock;
+	unsigned length, pos;
+	struct inode *inode = mapping->host;
+	struct page *page;
+	struct buffer_head map_bh;
+	int err;
+
+	blocksize = i_blocksize(inode);
+	length = offset & (blocksize - 1);
+
+	/* Block boundary? Nothing to do */
+	if (!length)
+		return 0;
+
+	length = blocksize - length;
+	iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits);
+
+	page = grab_cache_page(mapping, index);
+	err = -ENOMEM;
+	if (!page)
+		goto out;
+
+	if (page_has_buffers(page)) {
+has_buffers:
+		unlock_page(page);
+		put_page(page);
+		return block_truncate_page(mapping, from, get_block);
+	}
+
+	/* Find the buffer that contains "offset" */
+	pos = blocksize;
+	while (offset >= pos) {
+		iblock++;
+		pos += blocksize;
+	}
+
+	map_bh.b_size = blocksize;
+	map_bh.b_state = 0;
+	err = get_block(inode, iblock, &map_bh, 0);
+	if (err)
+		goto unlock;
+	/* unmapped? It's a hole - nothing to do */
+	if (!buffer_mapped(&map_bh))
+		goto unlock;
+
+	/* Ok, it's mapped. Make sure it's up-to-date */
+	if (!PageUptodate(page)) {
+		err = mapping->a_ops->readpage(NULL, page);
+		if (err) {
+			put_page(page);
+			goto out;
+		}
+		lock_page(page);
+		if (!PageUptodate(page)) {
+			err = -EIO;
+			goto unlock;
+		}
+		if (page_has_buffers(page))
+			goto has_buffers;
+	}
+	zero_user(page, offset, length);
+	set_page_dirty(page);
+	err = 0;
+
+unlock:
+	unlock_page(page);
+	put_page(page);
+out:
+	return err;
+}
+EXPORT_SYMBOL(nobh_truncate_page);
+
+int block_truncate_page(struct address_space *mapping,
+			loff_t from, get_block_t *get_block)
+{
+	pgoff_t index = from >> PAGE_SHIFT;
+	unsigned offset = from & (PAGE_SIZE-1);
+	unsigned blocksize;
+	sector_t iblock;
+	unsigned length, pos;
+	struct inode *inode = mapping->host;
+	struct page *page;
+	struct buffer_head *bh;
+	int err;
+
+	blocksize = i_blocksize(inode);
+	length = offset & (blocksize - 1);
+
+	/* Block boundary? Nothing to do */
+	if (!length)
+		return 0;
+
+	length = blocksize - length;
+	iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits);
+	
+	page = grab_cache_page(mapping, index);
+	err = -ENOMEM;
+	if (!page)
+		goto out;
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, blocksize, 0);
+
+	/* Find the buffer that contains "offset" */
+	bh = page_buffers(page);
+	pos = blocksize;
+	while (offset >= pos) {
+		bh = bh->b_this_page;
+		iblock++;
+		pos += blocksize;
+	}
+
+	err = 0;
+	if (!buffer_mapped(bh)) {
+		WARN_ON(bh->b_size != blocksize);
+		err = get_block(inode, iblock, bh, 0);
+		if (err)
+			goto unlock;
+		/* unmapped? It's a hole - nothing to do */
+		if (!buffer_mapped(bh))
+			goto unlock;
+	}
+
+	/* Ok, it's mapped. Make sure it's up-to-date */
+	if (PageUptodate(page))
+		set_buffer_uptodate(bh);
+
+	if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
+		err = -EIO;
+		ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+		wait_on_buffer(bh);
+		/* Uhhuh. Read error. Complain and punt. */
+		if (!buffer_uptodate(bh))
+			goto unlock;
+	}
+
+	zero_user(page, offset, length);
+	mark_buffer_dirty(bh);
+	err = 0;
+
+unlock:
+	unlock_page(page);
+	put_page(page);
+out:
+	return err;
+}
+EXPORT_SYMBOL(block_truncate_page);
+
+/*
+ * The generic ->writepage function for buffer-backed address_spaces
+ */
+int block_write_full_page(struct page *page, get_block_t *get_block,
+			struct writeback_control *wbc)
+{
+	struct inode * const inode = page->mapping->host;
+	loff_t i_size = i_size_read(inode);
+	const pgoff_t end_index = i_size >> PAGE_SHIFT;
+	unsigned offset;
+
+	/* Is the page fully inside i_size? */
+	if (page->index < end_index)
+		return __block_write_full_page(inode, page, get_block, wbc,
+					       end_buffer_async_write);
+
+	/* Is the page fully outside i_size? (truncate in progress) */
+	offset = i_size & (PAGE_SIZE-1);
+	if (page->index >= end_index+1 || !offset) {
+		/*
+		 * The page may have dirty, unmapped buffers.  For example,
+		 * they may have been added in ext3_writepage().  Make them
+		 * freeable here, so the page does not leak.
+		 */
+		do_invalidatepage(page, 0, PAGE_SIZE);
+		unlock_page(page);
+		return 0; /* don't care */
+	}
+
+	/*
+	 * The page straddles i_size.  It must be zeroed out on each and every
+	 * writepage invocation because it may be mmapped.  "A file is mapped
+	 * in multiples of the page size.  For a file that is not a multiple of
+	 * the  page size, the remaining memory is zeroed when mapped, and
+	 * writes to that region are not written out to the file."
+	 */
+	zero_user_segment(page, offset, PAGE_SIZE);
+	return __block_write_full_page(inode, page, get_block, wbc,
+							end_buffer_async_write);
+}
+EXPORT_SYMBOL(block_write_full_page);
+
+sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
+			    get_block_t *get_block)
+{
+	struct inode *inode = mapping->host;
+	struct buffer_head tmp = {
+		.b_size = i_blocksize(inode),
+	};
+
+	get_block(inode, block, &tmp, 0);
+	return tmp.b_blocknr;
+}
+EXPORT_SYMBOL(generic_block_bmap);
+
+static void end_bio_bh_io_sync(struct bio *bio)
+{
+	struct buffer_head *bh = bio->bi_private;
+
+	if (unlikely(bio_flagged(bio, BIO_QUIET)))
+		set_bit(BH_Quiet, &bh->b_state);
+
+	bh->b_end_io(bh, !bio->bi_status);
+	bio_put(bio);
+}
+
+/*
+ * This allows us to do IO even on the odd last sectors
+ * of a device, even if the block size is some multiple
+ * of the physical sector size.
+ *
+ * We'll just truncate the bio to the size of the device,
+ * and clear the end of the buffer head manually.
+ *
+ * Truly out-of-range accesses will turn into actual IO
+ * errors, this only handles the "we need to be able to
+ * do IO at the final sector" case.
+ */
+void guard_bio_eod(int op, struct bio *bio)
+{
+	sector_t maxsector;
+	struct bio_vec *bvec = bio_last_bvec_all(bio);
+	unsigned truncated_bytes;
+	struct hd_struct *part;
+
+	rcu_read_lock();
+	part = __disk_get_part(bio->bi_disk, bio->bi_partno);
+	if (part)
+		maxsector = part_nr_sects_read(part);
+	else
+		maxsector = get_capacity(bio->bi_disk);
+	rcu_read_unlock();
+
+	if (!maxsector)
+		return;
+
+	/*
+	 * If the *whole* IO is past the end of the device,
+	 * let it through, and the IO layer will turn it into
+	 * an EIO.
+	 */
+	if (unlikely(bio->bi_iter.bi_sector >= maxsector))
+		return;
+
+	maxsector -= bio->bi_iter.bi_sector;
+	if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
+		return;
+
+	/* Uhhuh. We've got a bio that straddles the device size! */
+	truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
+
+	/* Truncate the bio.. */
+	bio->bi_iter.bi_size -= truncated_bytes;
+	bvec->bv_len -= truncated_bytes;
+
+	/* ..and clear the end of the buffer for reads */
+	if (op == REQ_OP_READ) {
+		zero_user(bvec->bv_page, bvec->bv_offset + bvec->bv_len,
+				truncated_bytes);
+	}
+}
+
+static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
+			 enum rw_hint write_hint, struct writeback_control *wbc)
+{
+	struct bio *bio;
+
+	BUG_ON(!buffer_locked(bh));
+	BUG_ON(!buffer_mapped(bh));
+	BUG_ON(!bh->b_end_io);
+	BUG_ON(buffer_delay(bh));
+	BUG_ON(buffer_unwritten(bh));
+
+	/*
+	 * Only clear out a write error when rewriting
+	 */
+	if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE))
+		clear_buffer_write_io_error(bh);
+
+	/*
+	 * from here on down, it's all bio -- do the initial mapping,
+	 * submit_bio -> generic_make_request may further map this bio around
+	 */
+	bio = bio_alloc(GFP_NOIO, 1);
+
+	if (wbc) {
+		wbc_init_bio(wbc, bio);
+		wbc_account_io(wbc, bh->b_page, bh->b_size);
+	}
+
+	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+	bio_set_dev(bio, bh->b_bdev);
+	bio->bi_write_hint = write_hint;
+
+	bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+	BUG_ON(bio->bi_iter.bi_size != bh->b_size);
+
+	bio->bi_end_io = end_bio_bh_io_sync;
+	bio->bi_private = bh;
+
+	/* Take care of bh's that straddle the end of the device */
+	guard_bio_eod(op, bio);
+
+	if (buffer_meta(bh))
+		op_flags |= REQ_META;
+	if (buffer_prio(bh))
+		op_flags |= REQ_PRIO;
+	bio_set_op_attrs(bio, op, op_flags);
+
+	submit_bio(bio);
+	return 0;
+}
+
+int submit_bh(int op, int op_flags, struct buffer_head *bh)
+{
+	return submit_bh_wbc(op, op_flags, bh, 0, NULL);
+}
+EXPORT_SYMBOL(submit_bh);
+
+/**
+ * ll_rw_block: low-level access to block devices (DEPRECATED)
+ * @op: whether to %READ or %WRITE
+ * @op_flags: req_flag_bits
+ * @nr: number of &struct buffer_heads in the array
+ * @bhs: array of pointers to &struct buffer_head
+ *
+ * ll_rw_block() takes an array of pointers to &struct buffer_heads, and
+ * requests an I/O operation on them, either a %REQ_OP_READ or a %REQ_OP_WRITE.
+ * @op_flags contains flags modifying the detailed I/O behavior, most notably
+ * %REQ_RAHEAD.
+ *
+ * This function drops any buffer that it cannot get a lock on (with the
+ * BH_Lock state bit), any buffer that appears to be clean when doing a write
+ * request, and any buffer that appears to be up-to-date when doing read
+ * request.  Further it marks as clean buffers that are processed for
+ * writing (the buffer cache won't assume that they are actually clean
+ * until the buffer gets unlocked).
+ *
+ * ll_rw_block sets b_end_io to simple completion handler that marks
+ * the buffer up-to-date (if appropriate), unlocks the buffer and wakes
+ * any waiters. 
+ *
+ * All of the buffers must be for the same device, and must also be a
+ * multiple of the current approved size for the device.
+ */
+void ll_rw_block(int op, int op_flags,  int nr, struct buffer_head *bhs[])
+{
+	int i;
+	pr_debug("DEPRECATED: op=%d, nr=%d, op_flags=0x%x", op, nr, op_flags);
+
+	for (i = 0; i < nr; i++) {
+		struct buffer_head *bh = bhs[i];
+
+		if (!trylock_buffer(bh))
+			continue;
+		if (op == WRITE) {
+			if (test_clear_buffer_dirty(bh)) {
+				bh->b_end_io = end_buffer_write_sync;
+				get_bh(bh);
+				submit_bh(op, op_flags, bh);
+				continue;
+			}
+		} else {
+			if (!buffer_uptodate(bh)) {
+				bh->b_end_io = end_buffer_read_sync;
+				get_bh(bh);
+				submit_bh(op, op_flags, bh);
+				continue;
+			}
+		}
+		unlock_buffer(bh);
+	}
+}
+EXPORT_SYMBOL(ll_rw_block);
+
+void write_dirty_buffer(struct buffer_head *bh, int op_flags)
+{
+	lock_buffer(bh);
+	if (!test_clear_buffer_dirty(bh)) {
+		unlock_buffer(bh);
+		return;
+	}
+	bh->b_end_io = end_buffer_write_sync;
+	get_bh(bh);
+	submit_bh(REQ_OP_WRITE, op_flags, bh);
+}
+EXPORT_SYMBOL(write_dirty_buffer);
+
+/*
+ * For a data-integrity writeout, we need to wait upon any in-progress I/O
+ * and then start new I/O and then wait upon it.  The caller must have a ref on
+ * the buffer_head.
+ */
+int __sync_dirty_buffer(struct buffer_head *bh, int op_flags)
+{
+	int ret = 0;
+
+	WARN_ON(atomic_read(&bh->b_count) < 1);
+	lock_buffer(bh);
+	if (test_clear_buffer_dirty(bh)) {
+		get_bh(bh);
+		bh->b_end_io = end_buffer_write_sync;
+		ret = submit_bh(REQ_OP_WRITE, op_flags, bh);
+		wait_on_buffer(bh);
+		if (!ret && !buffer_uptodate(bh))
+			ret = -EIO;
+	} else {
+		unlock_buffer(bh);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(__sync_dirty_buffer);
+
+int sync_dirty_buffer(struct buffer_head *bh)
+{
+	return __sync_dirty_buffer(bh, REQ_SYNC);
+}
+EXPORT_SYMBOL(sync_dirty_buffer);
+
+/*
+ * try_to_free_buffers() checks if all the buffers on this particular page
+ * are unused, and releases them if so.
+ *
+ * Exclusion against try_to_free_buffers may be obtained by either
+ * locking the page or by holding its mapping's private_lock.
+ *
+ * If the page is dirty but all the buffers are clean then we need to
+ * be sure to mark the page clean as well.  This is because the page
+ * may be against a block device, and a later reattachment of buffers
+ * to a dirty page will set *all* buffers dirty.  Which would corrupt
+ * filesystem data on the same device.
+ *
+ * The same applies to regular filesystem pages: if all the buffers are
+ * clean then we set the page clean and proceed.  To do that, we require
+ * total exclusion from __set_page_dirty_buffers().  That is obtained with
+ * private_lock.
+ *
+ * try_to_free_buffers() is non-blocking.
+ */
+static inline int buffer_busy(struct buffer_head *bh)
+{
+	return atomic_read(&bh->b_count) |
+		(bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock)));
+}
+
+static int
+drop_buffers(struct page *page, struct buffer_head **buffers_to_free)
+{
+	struct buffer_head *head = page_buffers(page);
+	struct buffer_head *bh;
+
+	bh = head;
+	do {
+		if (buffer_busy(bh))
+			goto failed;
+		bh = bh->b_this_page;
+	} while (bh != head);
+
+	do {
+		struct buffer_head *next = bh->b_this_page;
+
+		if (bh->b_assoc_map)
+			__remove_assoc_queue(bh);
+		bh = next;
+	} while (bh != head);
+	*buffers_to_free = head;
+	__clear_page_buffers(page);
+	return 1;
+failed:
+	return 0;
+}
+
+int try_to_free_buffers(struct page *page)
+{
+	struct address_space * const mapping = page->mapping;
+	struct buffer_head *buffers_to_free = NULL;
+	int ret = 0;
+
+	BUG_ON(!PageLocked(page));
+	if (PageWriteback(page))
+		return 0;
+
+	if (mapping == NULL) {		/* can this still happen? */
+		ret = drop_buffers(page, &buffers_to_free);
+		goto out;
+	}
+
+	spin_lock(&mapping->private_lock);
+	ret = drop_buffers(page, &buffers_to_free);
+
+	/*
+	 * If the filesystem writes its buffers by hand (eg ext3)
+	 * then we can have clean buffers against a dirty page.  We
+	 * clean the page here; otherwise the VM will never notice
+	 * that the filesystem did any IO at all.
+	 *
+	 * Also, during truncate, discard_buffer will have marked all
+	 * the page's buffers clean.  We discover that here and clean
+	 * the page also.
+	 *
+	 * private_lock must be held over this entire operation in order
+	 * to synchronise against __set_page_dirty_buffers and prevent the
+	 * dirty bit from being lost.
+	 */
+	if (ret)
+		cancel_dirty_page(page);
+	spin_unlock(&mapping->private_lock);
+out:
+	if (buffers_to_free) {
+		struct buffer_head *bh = buffers_to_free;
+
+		do {
+			struct buffer_head *next = bh->b_this_page;
+			free_buffer_head(bh);
+			bh = next;
+		} while (bh != buffers_to_free);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(try_to_free_buffers);
+
+/*
+ * There are no bdflush tunables left.  But distributions are
+ * still running obsolete flush daemons, so we terminate them here.
+ *
+ * Use of bdflush() is deprecated and will be removed in a future kernel.
+ * The `flush-X' kernel threads fully replace bdflush daemons and this call.
+ */
+SYSCALL_DEFINE2(bdflush, int, func, long, data)
+{
+	static int msg_count;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (msg_count < 5) {
+		msg_count++;
+		printk(KERN_INFO
+			"warning: process `%s' used the obsolete bdflush"
+			" system call\n", current->comm);
+		printk(KERN_INFO "Fix your initscripts?\n");
+	}
+
+	if (func == 1)
+		do_exit(0);
+	return 0;
+}
+
+/*
+ * Buffer-head allocation
+ */
+static struct kmem_cache *bh_cachep __read_mostly;
+
+/*
+ * Once the number of bh's in the machine exceeds this level, we start
+ * stripping them in writeback.
+ */
+static unsigned long max_buffer_heads;
+
+int buffer_heads_over_limit;
+
+struct bh_accounting {
+	int nr;			/* Number of live bh's */
+	int ratelimit;		/* Limit cacheline bouncing */
+};
+
+static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0};
+
+static void recalc_bh_state(void)
+{
+	int i;
+	int tot = 0;
+
+	if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096)
+		return;
+	__this_cpu_write(bh_accounting.ratelimit, 0);
+	for_each_online_cpu(i)
+		tot += per_cpu(bh_accounting, i).nr;
+	buffer_heads_over_limit = (tot > max_buffer_heads);
+}
+
+struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
+{
+	struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
+	if (ret) {
+		INIT_LIST_HEAD(&ret->b_assoc_buffers);
+		preempt_disable();
+		__this_cpu_inc(bh_accounting.nr);
+		recalc_bh_state();
+		preempt_enable();
+	}
+	return ret;
+}
+EXPORT_SYMBOL(alloc_buffer_head);
+
+void free_buffer_head(struct buffer_head *bh)
+{
+	BUG_ON(!list_empty(&bh->b_assoc_buffers));
+	kmem_cache_free(bh_cachep, bh);
+	preempt_disable();
+	__this_cpu_dec(bh_accounting.nr);
+	recalc_bh_state();
+	preempt_enable();
+}
+EXPORT_SYMBOL(free_buffer_head);
+
+static int buffer_exit_cpu_dead(unsigned int cpu)
+{
+	int i;
+	struct bh_lru *b = &per_cpu(bh_lrus, cpu);
+
+	for (i = 0; i < BH_LRU_SIZE; i++) {
+		brelse(b->bhs[i]);
+		b->bhs[i] = NULL;
+	}
+	this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr);
+	per_cpu(bh_accounting, cpu).nr = 0;
+	return 0;
+}
+
+/**
+ * bh_uptodate_or_lock - Test whether the buffer is uptodate
+ * @bh: struct buffer_head
+ *
+ * Return true if the buffer is up-to-date and false,
+ * with the buffer locked, if not.
+ */
+int bh_uptodate_or_lock(struct buffer_head *bh)
+{
+	if (!buffer_uptodate(bh)) {
+		lock_buffer(bh);
+		if (!buffer_uptodate(bh))
+			return 0;
+		unlock_buffer(bh);
+	}
+	return 1;
+}
+EXPORT_SYMBOL(bh_uptodate_or_lock);
+
+/**
+ * bh_submit_read - Submit a locked buffer for reading
+ * @bh: struct buffer_head
+ *
+ * Returns zero on success and -EIO on error.
+ */
+int bh_submit_read(struct buffer_head *bh)
+{
+	BUG_ON(!buffer_locked(bh));
+
+	if (buffer_uptodate(bh)) {
+		unlock_buffer(bh);
+		return 0;
+	}
+
+	get_bh(bh);
+	bh->b_end_io = end_buffer_read_sync;
+	submit_bh(REQ_OP_READ, 0, bh);
+	wait_on_buffer(bh);
+	if (buffer_uptodate(bh))
+		return 0;
+	return -EIO;
+}
+EXPORT_SYMBOL(bh_submit_read);
+
+void __init buffer_init(void)
+{
+	unsigned long nrpages;
+	int ret;
+
+	bh_cachep = kmem_cache_create("buffer_head",
+			sizeof(struct buffer_head), 0,
+				(SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
+				SLAB_MEM_SPREAD),
+				NULL);
+
+	/*
+	 * Limit the bh occupancy to 10% of ZONE_NORMAL
+	 */
+	nrpages = (nr_free_buffer_pages() * 10) / 100;
+	max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head));
+	ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead",
+					NULL, buffer_exit_cpu_dead);
+	WARN_ON(ret < 0);
+}

src/fs/read_write.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/read_write.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/sched/xacct.h>
+#include <linux/fcntl.h>
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/fsnotify.h>
+#include <linux/security.h>
+#include <linux/export.h>
+#include <linux/syscalls.h>
+#include <linux/pagemap.h>
+#include <linux/splice.h>
+#include <linux/compat.h>
+#include <linux/mount.h>
+#include <linux/fs.h>
+#include "internal.h"
+
+#include <linux/uaccess.h>
+#include <asm/unistd.h>
+
+const struct file_operations generic_ro_fops = {
+	.llseek		= generic_file_llseek,
+	.read_iter	= generic_file_read_iter,
+	.mmap		= generic_file_readonly_mmap,
+	.splice_read	= generic_file_splice_read,
+};
+
+EXPORT_SYMBOL(generic_ro_fops);
+
+static inline bool unsigned_offsets(struct file *file)
+{
+	return file->f_mode & FMODE_UNSIGNED_OFFSET;
+}
+
+/**
+ * vfs_setpos - update the file offset for lseek
+ * @file:	file structure in question
+ * @offset:	file offset to seek to
+ * @maxsize:	maximum file size
+ *
+ * This is a low-level filesystem helper for updating the file offset to
+ * the value specified by @offset if the given offset is valid and it is
+ * not equal to the current file offset.
+ *
+ * Return the specified offset on success and -EINVAL on invalid offset.
+ */
+loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize)
+{
+	if (offset < 0 && !unsigned_offsets(file))
+		return -EINVAL;
+	if (offset > maxsize)
+		return -EINVAL;
+
+	if (offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+	return offset;
+}
+EXPORT_SYMBOL(vfs_setpos);
+
+/**
+ * generic_file_llseek_size - generic llseek implementation for regular files
+ * @file:	file structure to seek on
+ * @offset:	file offset to seek to
+ * @whence:	type of seek
+ * @size:	max size of this file in file system
+ * @eof:	offset used for SEEK_END position
+ *
+ * This is a variant of generic_file_llseek that allows passing in a custom
+ * maximum file size and a custom EOF position, for e.g. hashed directories
+ *
+ * Synchronization:
+ * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms)
+ * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes.
+ * read/writes behave like SEEK_SET against seeks.
+ */
+loff_t
+generic_file_llseek_size(struct file *file, loff_t offset, int whence,
+		loff_t maxsize, loff_t eof)
+{
+	switch (whence) {
+	case SEEK_END:
+		offset += eof;
+		break;
+	case SEEK_CUR:
+		/*
+		 * Here we special-case the lseek(fd, 0, SEEK_CUR)
+		 * position-querying operation.  Avoid rewriting the "same"
+		 * f_pos value back to the file because a concurrent read(),
+		 * write() or lseek() might have altered it
+		 */
+		if (offset == 0)
+			return file->f_pos;
+		/*
+		 * f_lock protects against read/modify/write race with other
+		 * SEEK_CURs. Note that parallel writes and reads behave
+		 * like SEEK_SET.
+		 */
+		spin_lock(&file->f_lock);
+		offset = vfs_setpos(file, file->f_pos + offset, maxsize);
+		spin_unlock(&file->f_lock);
+		return offset;
+	case SEEK_DATA:
+		/*
+		 * In the generic case the entire file is data, so as long as
+		 * offset isn't at the end of the file then the offset is data.
+		 */
+		if ((unsigned long long)offset >= eof)
+			return -ENXIO;
+		break;
+	case SEEK_HOLE:
+		/*
+		 * There is a virtual hole at the end of the file, so as long as
+		 * offset isn't i_size or larger, return i_size.
+		 */
+		if ((unsigned long long)offset >= eof)
+			return -ENXIO;
+		offset = eof;
+		break;
+	}
+
+	return vfs_setpos(file, offset, maxsize);
+}
+EXPORT_SYMBOL(generic_file_llseek_size);
+
+/**
+ * generic_file_llseek - generic llseek implementation for regular files
+ * @file:	file structure to seek on
+ * @offset:	file offset to seek to
+ * @whence:	type of seek
+ *
+ * This is a generic implemenation of ->llseek useable for all normal local
+ * filesystems.  It just updates the file offset to the value specified by
+ * @offset and @whence.
+ */
+loff_t generic_file_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file->f_mapping->host;
+
+	return generic_file_llseek_size(file, offset, whence,
+					inode->i_sb->s_maxbytes,
+					i_size_read(inode));
+}
+EXPORT_SYMBOL(generic_file_llseek);
+
+/**
+ * fixed_size_llseek - llseek implementation for fixed-sized devices
+ * @file:	file structure to seek on
+ * @offset:	file offset to seek to
+ * @whence:	type of seek
+ * @size:	size of the file
+ *
+ */
+loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size)
+{
+	switch (whence) {
+	case SEEK_SET: case SEEK_CUR: case SEEK_END:
+		return generic_file_llseek_size(file, offset, whence,
+						size, size);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL(fixed_size_llseek);
+
+/**
+ * no_seek_end_llseek - llseek implementation for fixed-sized devices
+ * @file:	file structure to seek on
+ * @offset:	file offset to seek to
+ * @whence:	type of seek
+ *
+ */
+loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence)
+{
+	switch (whence) {
+	case SEEK_SET: case SEEK_CUR:
+		return generic_file_llseek_size(file, offset, whence,
+						OFFSET_MAX, 0);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL(no_seek_end_llseek);
+
+/**
+ * no_seek_end_llseek_size - llseek implementation for fixed-sized devices
+ * @file:	file structure to seek on
+ * @offset:	file offset to seek to
+ * @whence:	type of seek
+ * @size:	maximal offset allowed
+ *
+ */
+loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size)
+{
+	switch (whence) {
+	case SEEK_SET: case SEEK_CUR:
+		return generic_file_llseek_size(file, offset, whence,
+						size, 0);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL(no_seek_end_llseek_size);
+
+/**
+ * noop_llseek - No Operation Performed llseek implementation
+ * @file:	file structure to seek on
+ * @offset:	file offset to seek to
+ * @whence:	type of seek
+ *
+ * This is an implementation of ->llseek useable for the rare special case when
+ * userspace expects the seek to succeed but the (device) file is actually not
+ * able to perform the seek. In this case you use noop_llseek() instead of
+ * falling back to the default implementation of ->llseek.
+ */
+loff_t noop_llseek(struct file *file, loff_t offset, int whence)
+{
+	return file->f_pos;
+}
+EXPORT_SYMBOL(noop_llseek);
+
+loff_t no_llseek(struct file *file, loff_t offset, int whence)
+{
+	return -ESPIPE;
+}
+EXPORT_SYMBOL(no_llseek);
+
+loff_t default_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file_inode(file);
+	loff_t retval;
+
+	inode_lock(inode);
+	switch (whence) {
+		case SEEK_END:
+			offset += i_size_read(inode);
+			break;
+		case SEEK_CUR:
+			if (offset == 0) {
+				retval = file->f_pos;
+				goto out;
+			}
+			offset += file->f_pos;
+			break;
+		case SEEK_DATA:
+			/*
+			 * In the generic case the entire file is data, so as
+			 * long as offset isn't at the end of the file then the
+			 * offset is data.
+			 */
+			if (offset >= inode->i_size) {
+				retval = -ENXIO;
+				goto out;
+			}
+			break;
+		case SEEK_HOLE:
+			/*
+			 * There is a virtual hole at the end of the file, so
+			 * as long as offset isn't i_size or larger, return
+			 * i_size.
+			 */
+			if (offset >= inode->i_size) {
+				retval = -ENXIO;
+				goto out;
+			}
+			offset = inode->i_size;
+			break;
+	}
+	retval = -EINVAL;
+	if (offset >= 0 || unsigned_offsets(file)) {
+		if (offset != file->f_pos) {
+			file->f_pos = offset;
+			file->f_version = 0;
+		}
+		retval = offset;
+	}
+out:
+	inode_unlock(inode);
+	return retval;
+}
+EXPORT_SYMBOL(default_llseek);
+
+loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
+{
+	loff_t (*fn)(struct file *, loff_t, int);
+
+	fn = no_llseek;
+	if (file->f_mode & FMODE_LSEEK) {
+		if (file->f_op->llseek)
+			fn = file->f_op->llseek;
+	}
+	return fn(file, offset, whence);
+}
+EXPORT_SYMBOL(vfs_llseek);
+
+off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence)
+{
+	off_t retval;
+	struct fd f = fdget_pos(fd);
+	if (!f.file)
+		return -EBADF;
+
+	retval = -EINVAL;
+	if (whence <= SEEK_MAX) {
+		loff_t res = vfs_llseek(f.file, offset, whence);
+		retval = res;
+		if (res != (loff_t)retval)
+			retval = -EOVERFLOW;	/* LFS: should only happen on 32 bit platforms */
+	}
+	fdput_pos(f);
+	return retval;
+}
+
+SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
+{
+	return ksys_lseek(fd, offset, whence);
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence)
+{
+	return ksys_lseek(fd, offset, whence);
+}
+#endif
+
+#ifdef __ARCH_WANT_SYS_LLSEEK
+SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
+		unsigned long, offset_low, loff_t __user *, result,
+		unsigned int, whence)
+{
+	int retval;
+	struct fd f = fdget_pos(fd);
+	loff_t offset;
+
+	if (!f.file)
+		return -EBADF;
+
+	retval = -EINVAL;
+	if (whence > SEEK_MAX)
+		goto out_putf;
+
+	offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low,
+			whence);
+
+	retval = (int)offset;
+	if (offset >= 0) {
+		retval = -EFAULT;
+		if (!copy_to_user(result, &offset, sizeof(offset)))
+			retval = 0;
+	}
+out_putf:
+	fdput_pos(f);
+	return retval;
+}
+#endif
+
+int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count)
+{
+	struct inode *inode;
+	loff_t pos;
+	int retval = -EINVAL;
+
+	inode = file_inode(file);
+	if (unlikely((ssize_t) count < 0))
+		return retval;
+	pos = *ppos;
+	if (unlikely(pos < 0)) {
+		if (!unsigned_offsets(file))
+			return retval;
+		if (count >= -pos) /* both values are in 0..LLONG_MAX */
+			return -EOVERFLOW;
+	} else if (unlikely((loff_t) (pos + count) < 0)) {
+		if (!unsigned_offsets(file))
+			return retval;
+	}
+
+	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
+		retval = locks_mandatory_area(inode, file, pos, pos + count - 1,
+				read_write == READ ? F_RDLCK : F_WRLCK);
+		if (retval < 0)
+			return retval;
+	}
+	return security_file_permission(file,
+				read_write == READ ? MAY_READ : MAY_WRITE);
+}
+
+static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
+{
+	struct iovec iov = { .iov_base = buf, .iov_len = len };
+	struct kiocb kiocb;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	init_sync_kiocb(&kiocb, filp);
+	kiocb.ki_pos = *ppos;
+	iov_iter_init(&iter, READ, &iov, 1, len);
+
+	ret = call_read_iter(filp, &kiocb, &iter);
+	BUG_ON(ret == -EIOCBQUEUED);
+	*ppos = kiocb.ki_pos;
+	return ret;
+}
+
+ssize_t __vfs_read(struct file *file, char __user *buf, size_t count,
+		   loff_t *pos)
+{
+	if (file->f_op->read)
+		return file->f_op->read(file, buf, count, pos);
+	else if (file->f_op->read_iter)
+		return new_sync_read(file, buf, count, pos);
+	else
+		return -EINVAL;
+}
+
+ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
+{
+	mm_segment_t old_fs;
+	ssize_t result;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	/* The cast to a user pointer is valid due to the set_fs() */
+	result = vfs_read(file, (void __user *)buf, count, pos);
+	set_fs(old_fs);
+	return result;
+}
+EXPORT_SYMBOL(kernel_read);
+
+ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
+{
+	ssize_t ret;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!(file->f_mode & FMODE_CAN_READ))
+		return -EINVAL;
+	if (unlikely(!access_ok(VERIFY_WRITE, buf, count)))
+		return -EFAULT;
+
+	ret = rw_verify_area(READ, file, pos, count);
+	if (!ret) {
+		if (count > MAX_RW_COUNT)
+			count =  MAX_RW_COUNT;
+		ret = __vfs_read(file, buf, count, pos);
+		if (ret > 0) {
+			fsnotify_access(file);
+			add_rchar(current, ret);
+		}
+		inc_syscr(current);
+	}
+
+	return ret;
+}
+
+static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
+{
+	struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
+	struct kiocb kiocb;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	init_sync_kiocb(&kiocb, filp);
+	kiocb.ki_pos = *ppos;
+	iov_iter_init(&iter, WRITE, &iov, 1, len);
+
+	ret = call_write_iter(filp, &kiocb, &iter);
+	BUG_ON(ret == -EIOCBQUEUED);
+	if (ret > 0)
+		*ppos = kiocb.ki_pos;
+	return ret;
+}
+
+ssize_t __vfs_write(struct file *file, const char __user *p, size_t count,
+		    loff_t *pos)
+{
+	if (file->f_op->write)
+		return file->f_op->write(file, p, count, pos);
+	else if (file->f_op->write_iter)
+		return new_sync_write(file, p, count, pos);
+	else
+		return -EINVAL;
+}
+
+ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
+{
+	mm_segment_t old_fs;
+	const char __user *p;
+	ssize_t ret;
+
+	if (!(file->f_mode & FMODE_CAN_WRITE))
+		return -EINVAL;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	p = (__force const char __user *)buf;
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
+	ret = __vfs_write(file, p, count, pos);
+	set_fs(old_fs);
+	if (ret > 0) {
+		fsnotify_modify(file);
+		add_wchar(current, ret);
+	}
+	inc_syscw(current);
+	return ret;
+}
+EXPORT_SYMBOL(__kernel_write);
+
+ssize_t kernel_write(struct file *file, const void *buf, size_t count,
+			    loff_t *pos)
+{
+	mm_segment_t old_fs;
+	ssize_t res;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	/* The cast to a user pointer is valid due to the set_fs() */
+	res = vfs_write(file, (__force const char __user *)buf, count, pos);
+	set_fs(old_fs);
+
+	return res;
+}
+EXPORT_SYMBOL(kernel_write);
+
+ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
+{
+	ssize_t ret;
+
+	if (!(file->f_mode & FMODE_WRITE))
+		return -EBADF;
+	if (!(file->f_mode & FMODE_CAN_WRITE))
+		return -EINVAL;
+	if (unlikely(!access_ok(VERIFY_READ, buf, count)))
+		return -EFAULT;
+
+	ret = rw_verify_area(WRITE, file, pos, count);
+	if (!ret) {
+		if (count > MAX_RW_COUNT)
+			count =  MAX_RW_COUNT;
+		file_start_write(file);
+		ret = __vfs_write(file, buf, count, pos);
+		if (ret > 0) {
+			fsnotify_modify(file);
+			add_wchar(current, ret);
+		}
+		inc_syscw(current);
+		file_end_write(file);
+	}
+
+	return ret;
+}
+
+static inline loff_t file_pos_read(struct file *file)
+{
+	return file->f_pos;
+}
+
+static inline void file_pos_write(struct file *file, loff_t pos)
+{
+	file->f_pos = pos;
+}
+
+ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count)
+{
+	struct fd f = fdget_pos(fd);
+	ssize_t ret = -EBADF;
+
+	if (f.file) {
+		loff_t pos = file_pos_read(f.file);
+		ret = vfs_read(f.file, buf, count, &pos);
+		if (ret >= 0)
+			file_pos_write(f.file, pos);
+		fdput_pos(f);
+	}
+	return ret;
+}
+
+SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
+{
+	return ksys_read(fd, buf, count);
+}
+
+ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count)
+{
+	struct fd f = fdget_pos(fd);
+	ssize_t ret = -EBADF;
+
+	if (f.file) {
+		loff_t pos = file_pos_read(f.file);
+		ret = vfs_write(f.file, buf, count, &pos);
+		if (ret >= 0)
+			file_pos_write(f.file, pos);
+		fdput_pos(f);
+	}
+
+	return ret;
+}
+
+SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
+		size_t, count)
+{
+	return ksys_write(fd, buf, count);
+}
+
+ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count,
+		     loff_t pos)
+{
+	struct fd f;
+	ssize_t ret = -EBADF;
+
+	if (pos < 0)
+		return -EINVAL;
+
+	f = fdget(fd);
+	if (f.file) {
+		ret = -ESPIPE;
+		if (f.file->f_mode & FMODE_PREAD)
+			ret = vfs_read(f.file, buf, count, &pos);
+		fdput(f);
+	}
+
+	return ret;
+}
+
+SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf,
+			size_t, count, loff_t, pos)
+{
+	return ksys_pread64(fd, buf, count, pos);
+}
+
+ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf,
+		      size_t count, loff_t pos)
+{
+	struct fd f;
+	ssize_t ret = -EBADF;
+
+	if (pos < 0)
+		return -EINVAL;
+
+	f = fdget(fd);
+	if (f.file) {
+		ret = -ESPIPE;
+		if (f.file->f_mode & FMODE_PWRITE)  
+			ret = vfs_write(f.file, buf, count, &pos);
+		fdput(f);
+	}
+
+	return ret;
+}
+
+SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf,
+			 size_t, count, loff_t, pos)
+{
+	return ksys_pwrite64(fd, buf, count, pos);
+}
+
+static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
+		loff_t *ppos, int type, rwf_t flags)
+{
+	struct kiocb kiocb;
+	ssize_t ret;
+	pr_debug("pos=%llu, flags=0x%x, type=%s", *ppos, flags, type?"WRITE":"READ");
+	init_sync_kiocb(&kiocb, filp);
+	ret = kiocb_set_rw_flags(&kiocb, flags);
+	if (ret)
+		return ret;
+	kiocb.ki_pos = *ppos;
+
+	if (type == READ)
+		ret = call_read_iter(filp, &kiocb, iter);
+	else
+		ret = call_write_iter(filp, &kiocb, iter);
+	BUG_ON(ret == -EIOCBQUEUED);
+	*ppos = kiocb.ki_pos;
+	return ret;
+}
+
+/* Do it by hand, with file-ops */
+static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
+		loff_t *ppos, int type, rwf_t flags)
+{
+	ssize_t ret = 0;
+	pr_debug("do_loop_readv_writev()");
+	if (flags & ~RWF_HIPRI)
+		return -EOPNOTSUPP;
+
+	while (iov_iter_count(iter)) {
+		struct iovec iovec = iov_iter_iovec(iter);
+		ssize_t nr;
+
+		if (type == READ) {
+			nr = filp->f_op->read(filp, iovec.iov_base,
+					      iovec.iov_len, ppos);
+		} else {
+			nr = filp->f_op->write(filp, iovec.iov_base,
+					       iovec.iov_len, ppos);
+		}
+
+		if (nr < 0) {
+			if (!ret)
+				ret = nr;
+			break;
+		}
+		ret += nr;
+		if (nr != iovec.iov_len)
+			break;
+		iov_iter_advance(iter, nr);
+	}
+
+	return ret;
+}
+
+/* A write operation does a read from user space and vice versa */
+#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
+
+/**
+ * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace
+ *     into the kernel and check that it is valid.
+ *
+ * @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE.
+ * @uvector: Pointer to the userspace array.
+ * @nr_segs: Number of elements in userspace array.
+ * @fast_segs: Number of elements in @fast_pointer.
+ * @fast_pointer: Pointer to (usually small on-stack) kernel array.
+ * @ret_pointer: (output parameter) Pointer to a variable that will point to
+ *     either @fast_pointer, a newly allocated kernel array, or NULL,
+ *     depending on which array was used.
+ *
+ * This function copies an array of &struct iovec of @nr_segs from
+ * userspace into the kernel and checks that each element is valid (e.g.
+ * it does not point to a kernel address or cause overflow by being too
+ * large, etc.).
+ *
+ * As an optimization, the caller may provide a pointer to a small
+ * on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long
+ * (the size of this array, or 0 if unused, should be given in @fast_segs).
+ *
+ * @ret_pointer will always point to the array that was used, so the
+ * caller must take care not to call kfree() on it e.g. in case the
+ * @fast_pointer array was used and it was allocated on the stack.
+ *
+ * Return: The total number of bytes covered by the iovec array on success
+ *   or a negative error code on error.
+ */
+ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
+			      unsigned long nr_segs, unsigned long fast_segs,
+			      struct iovec *fast_pointer,
+			      struct iovec **ret_pointer)
+{
+	unsigned long seg;
+	ssize_t ret;
+	struct iovec *iov = fast_pointer;
+
+	/*
+	 * SuS says "The readv() function *may* fail if the iovcnt argument
+	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
+	 * traditionally returned zero for zero segments, so...
+	 */
+	if (nr_segs == 0) {
+		ret = 0;
+		goto out;
+	}
+
+	/*
+	 * First get the "struct iovec" from user memory and
+	 * verify all the pointers
+	 */
+	if (nr_segs > UIO_MAXIOV) {
+		ret = -EINVAL;
+		goto out;
+	}
+	if (nr_segs > fast_segs) {
+		iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
+		if (iov == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
+	}
+	if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	/*
+	 * According to the Single Unix Specification we should return EINVAL
+	 * if an element length is < 0 when cast to ssize_t or if the
+	 * total length would overflow the ssize_t return value of the
+	 * system call.
+	 *
+	 * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
+	 * overflow case.
+	 */
+	ret = 0;
+	for (seg = 0; seg < nr_segs; seg++) {
+		void __user *buf = iov[seg].iov_base;
+		ssize_t len = (ssize_t)iov[seg].iov_len;
+
+		/* see if we we're about to use an invalid len or if
+		 * it's about to overflow ssize_t */
+		if (len < 0) {
+			ret = -EINVAL;
+			goto out;
+		}
+		if (type >= 0
+		    && unlikely(!access_ok(vrfy_dir(type), buf, len))) {
+			ret = -EFAULT;
+			goto out;
+		}
+		if (len > MAX_RW_COUNT - ret) {
+			len = MAX_RW_COUNT - ret;
+			iov[seg].iov_len = len;
+		}
+		ret += len;
+	}
+out:
+	*ret_pointer = iov;
+	return ret;
+}
+
+#ifdef CONFIG_COMPAT
+ssize_t compat_rw_copy_check_uvector(int type,
+		const struct compat_iovec __user *uvector, unsigned long nr_segs,
+		unsigned long fast_segs, struct iovec *fast_pointer,
+		struct iovec **ret_pointer)
+{
+	compat_ssize_t tot_len;
+	struct iovec *iov = *ret_pointer = fast_pointer;
+	ssize_t ret = 0;
+	int seg;
+
+	/*
+	 * SuS says "The readv() function *may* fail if the iovcnt argument
+	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
+	 * traditionally returned zero for zero segments, so...
+	 */
+	if (nr_segs == 0)
+		goto out;
+
+	ret = -EINVAL;
+	if (nr_segs > UIO_MAXIOV)
+		goto out;
+	if (nr_segs > fast_segs) {
+		ret = -ENOMEM;
+		iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
+		if (iov == NULL)
+			goto out;
+	}
+	*ret_pointer = iov;
+
+	ret = -EFAULT;
+	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
+		goto out;
+
+	/*
+	 * Single unix specification:
+	 * We should -EINVAL if an element length is not >= 0 and fitting an
+	 * ssize_t.
+	 *
+	 * In Linux, the total length is limited to MAX_RW_COUNT, there is
+	 * no overflow possibility.
+	 */
+	tot_len = 0;
+	ret = -EINVAL;
+	for (seg = 0; seg < nr_segs; seg++) {
+		compat_uptr_t buf;
+		compat_ssize_t len;
+
+		if (__get_user(len, &uvector->iov_len) ||
+		   __get_user(buf, &uvector->iov_base)) {
+			ret = -EFAULT;
+			goto out;
+		}
+		if (len < 0)	/* size_t not fitting in compat_ssize_t .. */
+			goto out;
+		if (type >= 0 &&
+		    !access_ok(vrfy_dir(type), compat_ptr(buf), len)) {
+			ret = -EFAULT;
+			goto out;
+		}
+		if (len > MAX_RW_COUNT - tot_len)
+			len = MAX_RW_COUNT - tot_len;
+		tot_len += len;
+		iov->iov_base = compat_ptr(buf);
+		iov->iov_len = (compat_size_t) len;
+		uvector++;
+		iov++;
+	}
+	ret = tot_len;
+
+out:
+	return ret;
+}
+#endif
+
+static ssize_t do_iter_read(struct file *file, struct iov_iter *iter,
+		loff_t *pos, rwf_t flags)
+{
+	size_t tot_len;
+	ssize_t ret = 0;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!(file->f_mode & FMODE_CAN_READ))
+		return -EINVAL;
+
+	tot_len = iov_iter_count(iter);
+	if (!tot_len)
+		goto out;
+	ret = rw_verify_area(READ, file, pos, tot_len);
+	if (ret < 0)
+		return ret;
+
+	if (file->f_op->read_iter)
+		ret = do_iter_readv_writev(file, iter, pos, READ, flags);
+	else
+		ret = do_loop_readv_writev(file, iter, pos, READ, flags);
+out:
+	if (ret >= 0)
+		fsnotify_access(file);
+	return ret;
+}
+
+ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
+		rwf_t flags)
+{
+	if (!file->f_op->read_iter)
+		return -EINVAL;
+	return do_iter_read(file, iter, ppos, flags);
+}
+EXPORT_SYMBOL(vfs_iter_read);
+
+static ssize_t do_iter_write(struct file *file, struct iov_iter *iter,
+		loff_t *pos, rwf_t flags)
+{
+	size_t tot_len;
+	ssize_t ret = 0;
+//	char dbg_buf[128]; //	dentry_path_raw(file->f_path.dentry, dbg_buf, sizeof(dbg_buf));
+	if (!strncmp(file->f_path.dentry->d_name.name, "sda2", 4)) {
+		pr_debug("do_iter_write(), fname (only sda2) = %s", file->f_path.dentry->d_name.name); // dbg_buf);
+	}
+	if (!(file->f_mode & FMODE_WRITE))
+		return -EBADF;
+	if (!(file->f_mode & FMODE_CAN_WRITE))
+		return -EINVAL;
+	tot_len = iov_iter_count(iter);
+	if (!tot_len)
+		return 0;
+	ret = rw_verify_area(WRITE, file, pos, tot_len);
+	if (ret < 0)
+		return ret;
+
+	if (file->f_op->write_iter)
+		ret = do_iter_readv_writev(file, iter, pos, WRITE, flags);
+	else
+		ret = do_loop_readv_writev(file, iter, pos, WRITE, flags);
+	if (ret > 0)
+		fsnotify_modify(file);
+	return ret;
+}
+
+ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
+		rwf_t flags)
+{
+	if (!file->f_op->write_iter)
+		return -EINVAL;
+	return do_iter_write(file, iter, ppos, flags);
+}
+EXPORT_SYMBOL(vfs_iter_write);
+
+ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
+		  unsigned long vlen, loff_t *pos, rwf_t flags)
+{
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret >= 0) {
+		ret = do_iter_read(file, &iter, pos, flags);
+		kfree(iov);
+	}
+
+	return ret;
+}
+
+static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
+		   unsigned long vlen, loff_t *pos, rwf_t flags)
+{
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	ret = import_iovec(WRITE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret >= 0) {
+		file_start_write(file);
+		ret = do_iter_write(file, &iter, pos, flags);
+		file_end_write(file);
+		kfree(iov);
+	}
+	return ret;
+}
+
+static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec,
+			unsigned long vlen, rwf_t flags)
+{
+	struct fd f = fdget_pos(fd);
+	ssize_t ret = -EBADF;
+
+	if (f.file) {
+		loff_t pos = file_pos_read(f.file);
+		ret = vfs_readv(f.file, vec, vlen, &pos, flags);
+		if (ret >= 0)
+			file_pos_write(f.file, pos);
+		fdput_pos(f);
+	}
+
+	if (ret > 0)
+		add_rchar(current, ret);
+	inc_syscr(current);
+	return ret;
+}
+
+static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec,
+			 unsigned long vlen, rwf_t flags)
+{
+	struct fd f = fdget_pos(fd);
+	ssize_t ret = -EBADF;
+
+	if (f.file) {
+		loff_t pos = file_pos_read(f.file);
+		ret = vfs_writev(f.file, vec, vlen, &pos, flags);
+		if (ret >= 0)
+			file_pos_write(f.file, pos);
+		fdput_pos(f);
+	}
+
+	if (ret > 0)
+		add_wchar(current, ret);
+	inc_syscw(current);
+	return ret;
+}
+
+static inline loff_t pos_from_hilo(unsigned long high, unsigned long low)
+{
+#define HALF_LONG_BITS (BITS_PER_LONG / 2)
+	return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low;
+}
+
+static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec,
+			 unsigned long vlen, loff_t pos, rwf_t flags)
+{
+	struct fd f;
+	ssize_t ret = -EBADF;
+
+	if (pos < 0)
+		return -EINVAL;
+
+	f = fdget(fd);
+	if (f.file) {
+		ret = -ESPIPE;
+		if (f.file->f_mode & FMODE_PREAD)
+			ret = vfs_readv(f.file, vec, vlen, &pos, flags);
+		fdput(f);
+	}
+
+	if (ret > 0)
+		add_rchar(current, ret);
+	inc_syscr(current);
+	return ret;
+}
+
+static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec,
+			  unsigned long vlen, loff_t pos, rwf_t flags)
+{
+	struct fd f;
+	ssize_t ret = -EBADF;
+
+	if (pos < 0)
+		return -EINVAL;
+
+	f = fdget(fd);
+	if (f.file) {
+		ret = -ESPIPE;
+		if (f.file->f_mode & FMODE_PWRITE)
+			ret = vfs_writev(f.file, vec, vlen, &pos, flags);
+		fdput(f);
+	}
+
+	if (ret > 0)
+		add_wchar(current, ret);
+	inc_syscw(current);
+	return ret;
+}
+
+SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen)
+{
+	return do_readv(fd, vec, vlen, 0);
+}
+
+SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen)
+{
+	return do_writev(fd, vec, vlen, 0);
+}
+
+SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	return do_preadv(fd, vec, vlen, pos, 0);
+}
+
+SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
+		rwf_t, flags)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	if (pos == -1)
+		return do_readv(fd, vec, vlen, flags);
+
+	return do_preadv(fd, vec, vlen, pos, flags);
+}
+
+SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	return do_pwritev(fd, vec, vlen, pos, 0);
+}
+
+SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
+		rwf_t, flags)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	if (pos == -1)
+		return do_writev(fd, vec, vlen, flags);
+
+	return do_pwritev(fd, vec, vlen, pos, flags);
+}
+
+#ifdef CONFIG_COMPAT
+static size_t compat_readv(struct file *file,
+			   const struct compat_iovec __user *vec,
+			   unsigned long vlen, loff_t *pos, rwf_t flags)
+{
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	ret = compat_import_iovec(READ, vec, vlen, UIO_FASTIOV, &iov, &iter);
+	if (ret >= 0) {
+		ret = do_iter_read(file, &iter, pos, flags);
+		kfree(iov);
+	}
+	if (ret > 0)
+		add_rchar(current, ret);
+	inc_syscr(current);
+	return ret;
+}
+
+static size_t do_compat_readv(compat_ulong_t fd,
+				 const struct compat_iovec __user *vec,
+				 compat_ulong_t vlen, rwf_t flags)
+{
+	struct fd f = fdget_pos(fd);
+	ssize_t ret;
+	loff_t pos;
+
+	if (!f.file)
+		return -EBADF;
+	pos = f.file->f_pos;
+	ret = compat_readv(f.file, vec, vlen, &pos, flags);
+	if (ret >= 0)
+		f.file->f_pos = pos;
+	fdput_pos(f);
+	return ret;
+
+}
+
+COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
+		const struct compat_iovec __user *,vec,
+		compat_ulong_t, vlen)
+{
+	return do_compat_readv(fd, vec, vlen, 0);
+}
+
+static long do_compat_preadv64(unsigned long fd,
+				  const struct compat_iovec __user *vec,
+				  unsigned long vlen, loff_t pos, rwf_t flags)
+{
+	struct fd f;
+	ssize_t ret;
+
+	if (pos < 0)
+		return -EINVAL;
+	f = fdget(fd);
+	if (!f.file)
+		return -EBADF;
+	ret = -ESPIPE;
+	if (f.file->f_mode & FMODE_PREAD)
+		ret = compat_readv(f.file, vec, vlen, &pos, flags);
+	fdput(f);
+	return ret;
+}
+
+#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
+COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
+		const struct compat_iovec __user *,vec,
+		unsigned long, vlen, loff_t, pos)
+{
+	return do_compat_preadv64(fd, vec, vlen, pos, 0);
+}
+#endif
+
+COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
+		const struct compat_iovec __user *,vec,
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+	return do_compat_preadv64(fd, vec, vlen, pos, 0);
+}
+
+#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
+COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd,
+		const struct compat_iovec __user *,vec,
+		unsigned long, vlen, loff_t, pos, rwf_t, flags)
+{
+	return do_compat_preadv64(fd, vec, vlen, pos, flags);
+}
+#endif
+
+COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
+		const struct compat_iovec __user *,vec,
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
+		rwf_t, flags)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+	if (pos == -1)
+		return do_compat_readv(fd, vec, vlen, flags);
+
+	return do_compat_preadv64(fd, vec, vlen, pos, flags);
+}
+
+static size_t compat_writev(struct file *file,
+			    const struct compat_iovec __user *vec,
+			    unsigned long vlen, loff_t *pos, rwf_t flags)
+{
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	ret = compat_import_iovec(WRITE, vec, vlen, UIO_FASTIOV, &iov, &iter);
+	if (ret >= 0) {
+		file_start_write(file);
+		ret = do_iter_write(file, &iter, pos, flags);
+		file_end_write(file);
+		kfree(iov);
+	}
+	if (ret > 0)
+		add_wchar(current, ret);
+	inc_syscw(current);
+	return ret;
+}
+
+static size_t do_compat_writev(compat_ulong_t fd,
+				  const struct compat_iovec __user* vec,
+				  compat_ulong_t vlen, rwf_t flags)
+{
+	struct fd f = fdget_pos(fd);
+	ssize_t ret;
+	loff_t pos;
+
+	if (!f.file)
+		return -EBADF;
+	pos = f.file->f_pos;
+	ret = compat_writev(f.file, vec, vlen, &pos, flags);
+	if (ret >= 0)
+		f.file->f_pos = pos;
+	fdput_pos(f);
+	return ret;
+}
+
+COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
+		const struct compat_iovec __user *, vec,
+		compat_ulong_t, vlen)
+{
+	return do_compat_writev(fd, vec, vlen, 0);
+}
+
+static long do_compat_pwritev64(unsigned long fd,
+				   const struct compat_iovec __user *vec,
+				   unsigned long vlen, loff_t pos, rwf_t flags)
+{
+	struct fd f;
+	ssize_t ret;
+
+	if (pos < 0)
+		return -EINVAL;
+	f = fdget(fd);
+	if (!f.file)
+		return -EBADF;
+	ret = -ESPIPE;
+	if (f.file->f_mode & FMODE_PWRITE)
+		ret = compat_writev(f.file, vec, vlen, &pos, flags);
+	fdput(f);
+	return ret;
+}
+
+#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
+COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
+		const struct compat_iovec __user *,vec,
+		unsigned long, vlen, loff_t, pos)
+{
+	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
+}
+#endif
+
+COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
+		const struct compat_iovec __user *,vec,
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
+}
+
+#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2
+COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd,
+		const struct compat_iovec __user *,vec,
+		unsigned long, vlen, loff_t, pos, rwf_t, flags)
+{
+	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
+}
+#endif
+
+COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
+		const struct compat_iovec __user *,vec,
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+	if (pos == -1)
+		return do_compat_writev(fd, vec, vlen, flags);
+
+	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
+}
+
+#endif
+
+static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
+		  	   size_t count, loff_t max)
+{
+	struct fd in, out;
+	struct inode *in_inode, *out_inode;
+	loff_t pos;
+	loff_t out_pos;
+	ssize_t retval;
+	int fl;
+
+	/*
+	 * Get input file, and verify that it is ok..
+	 */
+	retval = -EBADF;
+	in = fdget(in_fd);
+	if (!in.file)
+		goto out;
+	if (!(in.file->f_mode & FMODE_READ))
+		goto fput_in;
+	retval = -ESPIPE;
+	if (!ppos) {
+		pos = in.file->f_pos;
+	} else {
+		pos = *ppos;
+		if (!(in.file->f_mode & FMODE_PREAD))
+			goto fput_in;
+	}
+	retval = rw_verify_area(READ, in.file, &pos, count);
+	if (retval < 0)
+		goto fput_in;
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
+
+	/*
+	 * Get output file, and verify that it is ok..
+	 */
+	retval = -EBADF;
+	out = fdget(out_fd);
+	if (!out.file)
+		goto fput_in;
+	if (!(out.file->f_mode & FMODE_WRITE))
+		goto fput_out;
+	retval = -EINVAL;
+	in_inode = file_inode(in.file);
+	out_inode = file_inode(out.file);
+	out_pos = out.file->f_pos;
+	retval = rw_verify_area(WRITE, out.file, &out_pos, count);
+	if (retval < 0)
+		goto fput_out;
+
+	if (!max)
+		max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
+
+	if (unlikely(pos + count > max)) {
+		retval = -EOVERFLOW;
+		if (pos >= max)
+			goto fput_out;
+		count = max - pos;
+	}
+
+	fl = 0;
+#if 0
+	/*
+	 * We need to debate whether we can enable this or not. The
+	 * man page documents EAGAIN return for the output at least,
+	 * and the application is arguably buggy if it doesn't expect
+	 * EAGAIN on a non-blocking file descriptor.
+	 */
+	if (in.file->f_flags & O_NONBLOCK)
+		fl = SPLICE_F_NONBLOCK;
+#endif
+	file_start_write(out.file);
+	retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl);
+	file_end_write(out.file);
+
+	if (retval > 0) {
+		add_rchar(current, retval);
+		add_wchar(current, retval);
+		fsnotify_access(in.file);
+		fsnotify_modify(out.file);
+		out.file->f_pos = out_pos;
+		if (ppos)
+			*ppos = pos;
+		else
+			in.file->f_pos = pos;
+	}
+
+	inc_syscr(current);
+	inc_syscw(current);
+	if (pos > max)
+		retval = -EOVERFLOW;
+
+fput_out:
+	fdput(out);
+fput_in:
+	fdput(in);
+out:
+	return retval;
+}
+
+SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count)
+{
+	loff_t pos;
+	off_t off;
+	ssize_t ret;
+
+	if (offset) {
+		if (unlikely(get_user(off, offset)))
+			return -EFAULT;
+		pos = off;
+		ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS);
+		if (unlikely(put_user(pos, offset)))
+			return -EFAULT;
+		return ret;
+	}
+
+	return do_sendfile(out_fd, in_fd, NULL, count, 0);
+}
+
+SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count)
+{
+	loff_t pos;
+	ssize_t ret;
+
+	if (offset) {
+		if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t))))
+			return -EFAULT;
+		ret = do_sendfile(out_fd, in_fd, &pos, count, 0);
+		if (unlikely(put_user(pos, offset)))
+			return -EFAULT;
+		return ret;
+	}
+
+	return do_sendfile(out_fd, in_fd, NULL, count, 0);
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd,
+		compat_off_t __user *, offset, compat_size_t, count)
+{
+	loff_t pos;
+	off_t off;
+	ssize_t ret;
+
+	if (offset) {
+		if (unlikely(get_user(off, offset)))
+			return -EFAULT;
+		pos = off;
+		ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS);
+		if (unlikely(put_user(pos, offset)))
+			return -EFAULT;
+		return ret;
+	}
+
+	return do_sendfile(out_fd, in_fd, NULL, count, 0);
+}
+
+COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
+		compat_loff_t __user *, offset, compat_size_t, count)
+{
+	loff_t pos;
+	ssize_t ret;
+
+	if (offset) {
+		if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t))))
+			return -EFAULT;
+		ret = do_sendfile(out_fd, in_fd, &pos, count, 0);
+		if (unlikely(put_user(pos, offset)))
+			return -EFAULT;
+		return ret;
+	}
+
+	return do_sendfile(out_fd, in_fd, NULL, count, 0);
+}
+#endif
+
+/*
+ * copy_file_range() differs from regular file read and write in that it
+ * specifically allows return partial success.  When it does so is up to
+ * the copy_file_range method.
+ */
+ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
+			    struct file *file_out, loff_t pos_out,
+			    size_t len, unsigned int flags)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	ssize_t ret;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	ret = rw_verify_area(READ, file_in, &pos_in, len);
+	if (unlikely(ret))
+		return ret;
+
+	ret = rw_verify_area(WRITE, file_out, &pos_out, len);
+	if (unlikely(ret))
+		return ret;
+
+	if (!(file_in->f_mode & FMODE_READ) ||
+	    !(file_out->f_mode & FMODE_WRITE) ||
+	    (file_out->f_flags & O_APPEND))
+		return -EBADF;
+
+	/* this could be relaxed once a method supports cross-fs copies */
+	if (inode_in->i_sb != inode_out->i_sb)
+		return -EXDEV;
+
+	if (len == 0)
+		return 0;
+
+	file_start_write(file_out);
+
+	/*
+	 * Try cloning first, this is supported by more file systems, and
+	 * more efficient if both clone and copy are supported (e.g. NFS).
+	 */
+	if (file_in->f_op->clone_file_range) {
+		ret = file_in->f_op->clone_file_range(file_in, pos_in,
+				file_out, pos_out, len);
+		if (ret == 0) {
+			ret = len;
+			goto done;
+		}
+	}
+
+	if (file_out->f_op->copy_file_range) {
+		ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out,
+						      pos_out, len, flags);
+		if (ret != -EOPNOTSUPP)
+			goto done;
+	}
+
+	ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out,
+			len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
+
+done:
+	if (ret > 0) {
+		fsnotify_access(file_in);
+		add_rchar(current, ret);
+		fsnotify_modify(file_out);
+		add_wchar(current, ret);
+	}
+
+	inc_syscr(current);
+	inc_syscw(current);
+
+	file_end_write(file_out);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_copy_file_range);
+
+SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in,
+		int, fd_out, loff_t __user *, off_out,
+		size_t, len, unsigned int, flags)
+{
+	loff_t pos_in;
+	loff_t pos_out;
+	struct fd f_in;
+	struct fd f_out;
+	ssize_t ret = -EBADF;
+
+	f_in = fdget(fd_in);
+	if (!f_in.file)
+		goto out2;
+
+	f_out = fdget(fd_out);
+	if (!f_out.file)
+		goto out1;
+
+	ret = -EFAULT;
+	if (off_in) {
+		if (copy_from_user(&pos_in, off_in, sizeof(loff_t)))
+			goto out;
+	} else {
+		pos_in = f_in.file->f_pos;
+	}
+
+	if (off_out) {
+		if (copy_from_user(&pos_out, off_out, sizeof(loff_t)))
+			goto out;
+	} else {
+		pos_out = f_out.file->f_pos;
+	}
+
+	ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len,
+				  flags);
+	if (ret > 0) {
+		pos_in += ret;
+		pos_out += ret;
+
+		if (off_in) {
+			if (copy_to_user(off_in, &pos_in, sizeof(loff_t)))
+				ret = -EFAULT;
+		} else {
+			f_in.file->f_pos = pos_in;
+		}
+
+		if (off_out) {
+			if (copy_to_user(off_out, &pos_out, sizeof(loff_t)))
+				ret = -EFAULT;
+		} else {
+			f_out.file->f_pos = pos_out;
+		}
+	}
+
+out:
+	fdput(f_out);
+out1:
+	fdput(f_in);
+out2:
+	return ret;
+}
+
+static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write)
+{
+	struct inode *inode = file_inode(file);
+
+	if (unlikely(pos < 0))
+		return -EINVAL;
+
+	 if (unlikely((loff_t) (pos + len) < 0))
+		return -EINVAL;
+
+	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
+		loff_t end = len ? pos + len - 1 : OFFSET_MAX;
+		int retval;
+
+		retval = locks_mandatory_area(inode, file, pos, end,
+				write ? F_WRLCK : F_RDLCK);
+		if (retval < 0)
+			return retval;
+	}
+
+	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
+}
+
+/*
+ * Check that the two inodes are eligible for cloning, the ranges make
+ * sense, and then flush all dirty data.  Caller must ensure that the
+ * inodes have been locked against any other modifications.
+ *
+ * Returns: 0 for "nothing to clone", 1 for "something to clone", or
+ * the usual negative error code.
+ */
+int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
+			       struct inode *inode_out, loff_t pos_out,
+			       u64 *len, bool is_dedupe)
+{
+	loff_t bs = inode_out->i_sb->s_blocksize;
+	loff_t blen;
+	loff_t isize;
+	bool same_inode = (inode_in == inode_out);
+	int ret;
+
+	/* Don't touch certain kinds of inodes */
+	if (IS_IMMUTABLE(inode_out))
+		return -EPERM;
+
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		return -ETXTBSY;
+
+	/* Don't reflink dirs, pipes, sockets... */
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	/* Are we going all the way to the end? */
+	isize = i_size_read(inode_in);
+	if (isize == 0)
+		return 0;
+
+	/* Zero length dedupe exits immediately; reflink goes to EOF. */
+	if (*len == 0) {
+		if (is_dedupe || pos_in == isize)
+			return 0;
+		if (pos_in > isize)
+			return -EINVAL;
+		*len = isize - pos_in;
+	}
+
+	/* Ensure offsets don't wrap and the input is inside i_size */
+	if (pos_in + *len < pos_in || pos_out + *len < pos_out ||
+	    pos_in + *len > isize)
+		return -EINVAL;
+
+	/* Don't allow dedupe past EOF in the dest file */
+	if (is_dedupe) {
+		loff_t	disize;
+
+		disize = i_size_read(inode_out);
+		if (pos_out >= disize || pos_out + *len > disize)
+			return -EINVAL;
+	}
+
+	/* If we're linking to EOF, continue to the block boundary. */
+	if (pos_in + *len == isize)
+		blen = ALIGN(isize, bs) - pos_in;
+	else
+		blen = *len;
+
+	/* Only reflink if we're aligned to block boundaries */
+	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
+	    !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
+		return -EINVAL;
+
+	/* Don't allow overlapped reflink within the same file */
+	if (same_inode) {
+		if (pos_out + blen > pos_in && pos_out < pos_in + blen)
+			return -EINVAL;
+	}
+
+	/* Wait for the completion of any pending IOs on both files */
+	inode_dio_wait(inode_in);
+	if (!same_inode)
+		inode_dio_wait(inode_out);
+
+	ret = filemap_write_and_wait_range(inode_in->i_mapping,
+			pos_in, pos_in + *len - 1);
+	if (ret)
+		return ret;
+
+	ret = filemap_write_and_wait_range(inode_out->i_mapping,
+			pos_out, pos_out + *len - 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Check that the extents are the same.
+	 */
+	if (is_dedupe) {
+		bool		is_same = false;
+
+		ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
+				inode_out, pos_out, *len, &is_same);
+		if (ret)
+			return ret;
+		if (!is_same)
+			return -EBADE;
+	}
+
+	return 1;
+}
+EXPORT_SYMBOL(vfs_clone_file_prep_inodes);
+
+int do_clone_file_range(struct file *file_in, loff_t pos_in,
+			struct file *file_out, loff_t pos_out, u64 len)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	int ret;
+
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	/*
+	 * FICLONE/FICLONERANGE ioctls enforce that src and dest files are on
+	 * the same mount. Practically, they only need to be on the same file
+	 * system.
+	 */
+	if (inode_in->i_sb != inode_out->i_sb)
+		return -EXDEV;
+
+	if (!(file_in->f_mode & FMODE_READ) ||
+	    !(file_out->f_mode & FMODE_WRITE) ||
+	    (file_out->f_flags & O_APPEND))
+		return -EBADF;
+
+	if (!file_in->f_op->clone_file_range)
+		return -EOPNOTSUPP;
+
+	ret = clone_verify_area(file_in, pos_in, len, false);
+	if (ret)
+		return ret;
+
+	ret = clone_verify_area(file_out, pos_out, len, true);
+	if (ret)
+		return ret;
+
+	if (pos_in + len > i_size_read(inode_in))
+		return -EINVAL;
+
+	ret = file_in->f_op->clone_file_range(file_in, pos_in,
+			file_out, pos_out, len);
+	if (!ret) {
+		fsnotify_access(file_in);
+		fsnotify_modify(file_out);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(do_clone_file_range);
+
+int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+			 struct file *file_out, loff_t pos_out, u64 len)
+{
+	int ret;
+
+	file_start_write(file_out);
+	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len);
+	file_end_write(file_out);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_clone_file_range);
+
+/*
+ * Read a page's worth of file data into the page cache.  Return the page
+ * locked.
+ */
+static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
+{
+	struct address_space *mapping;
+	struct page *page;
+	pgoff_t n;
+
+	n = offset >> PAGE_SHIFT;
+	mapping = inode->i_mapping;
+	page = read_mapping_page(mapping, n, NULL);
+	if (IS_ERR(page))
+		return page;
+	if (!PageUptodate(page)) {
+		put_page(page);
+		return ERR_PTR(-EIO);
+	}
+	lock_page(page);
+	return page;
+}
+
+/*
+ * Compare extents of two files to see if they are the same.
+ * Caller must have locked both inodes to prevent write races.
+ */
+int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+				  struct inode *dest, loff_t destoff,
+				  loff_t len, bool *is_same)
+{
+	loff_t src_poff;
+	loff_t dest_poff;
+	void *src_addr;
+	void *dest_addr;
+	struct page *src_page;
+	struct page *dest_page;
+	loff_t cmp_len;
+	bool same;
+	int error;
+
+	error = -EINVAL;
+	same = true;
+	while (len) {
+		src_poff = srcoff & (PAGE_SIZE - 1);
+		dest_poff = destoff & (PAGE_SIZE - 1);
+		cmp_len = min(PAGE_SIZE - src_poff,
+			      PAGE_SIZE - dest_poff);
+		cmp_len = min(cmp_len, len);
+		if (cmp_len <= 0)
+			goto out_error;
+
+		src_page = vfs_dedupe_get_page(src, srcoff);
+		if (IS_ERR(src_page)) {
+			error = PTR_ERR(src_page);
+			goto out_error;
+		}
+		dest_page = vfs_dedupe_get_page(dest, destoff);
+		if (IS_ERR(dest_page)) {
+			error = PTR_ERR(dest_page);
+			unlock_page(src_page);
+			put_page(src_page);
+			goto out_error;
+		}
+		src_addr = kmap_atomic(src_page);
+		dest_addr = kmap_atomic(dest_page);
+
+		flush_dcache_page(src_page);
+		flush_dcache_page(dest_page);
+
+		if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
+			same = false;
+
+		kunmap_atomic(dest_addr);
+		kunmap_atomic(src_addr);
+		unlock_page(dest_page);
+		unlock_page(src_page);
+		put_page(dest_page);
+		put_page(src_page);
+
+		if (!same)
+			break;
+
+		srcoff += cmp_len;
+		destoff += cmp_len;
+		len -= cmp_len;
+	}
+
+	*is_same = same;
+	return 0;
+
+out_error:
+	return error;
+}
+EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
+
+int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
+			      struct file *dst_file, loff_t dst_pos, u64 len)
+{
+	s64 ret;
+
+	ret = mnt_want_write_file(dst_file);
+	if (ret)
+		return ret;
+
+	ret = clone_verify_area(dst_file, dst_pos, len, true);
+	if (ret < 0)
+		goto out_drop_write;
+
+	ret = -EINVAL;
+	if (!(capable(CAP_SYS_ADMIN) || (dst_file->f_mode & FMODE_WRITE)))
+		goto out_drop_write;
+
+	ret = -EXDEV;
+	if (src_file->f_path.mnt != dst_file->f_path.mnt)
+		goto out_drop_write;
+
+	ret = -EISDIR;
+	if (S_ISDIR(file_inode(dst_file)->i_mode))
+		goto out_drop_write;
+
+	ret = -EINVAL;
+	if (!dst_file->f_op->dedupe_file_range)
+		goto out_drop_write;
+
+	ret = dst_file->f_op->dedupe_file_range(src_file, src_pos,
+						dst_file, dst_pos, len);
+out_drop_write:
+	mnt_drop_write_file(dst_file);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_dedupe_file_range_one);
+
+int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
+{
+	struct file_dedupe_range_info *info;
+	struct inode *src = file_inode(file);
+	u64 off;
+	u64 len;
+	int i;
+	int ret;
+	u16 count = same->dest_count;
+	int deduped;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EINVAL;
+
+	if (same->reserved1 || same->reserved2)
+		return -EINVAL;
+
+	off = same->src_offset;
+	len = same->src_length;
+
+	ret = -EISDIR;
+	if (S_ISDIR(src->i_mode))
+		goto out;
+
+	ret = -EINVAL;
+	if (!S_ISREG(src->i_mode))
+		goto out;
+
+	ret = clone_verify_area(file, off, len, false);
+	if (ret < 0)
+		goto out;
+	ret = 0;
+
+	if (off + len > i_size_read(src))
+		return -EINVAL;
+
+	/* Arbitrary 1G limit on a single dedupe request, can be raised. */
+	len = min_t(u64, len, 1 << 30);
+
+	/* pre-format output fields to sane values */
+	for (i = 0; i < count; i++) {
+		same->info[i].bytes_deduped = 0ULL;
+		same->info[i].status = FILE_DEDUPE_RANGE_SAME;
+	}
+
+	for (i = 0, info = same->info; i < count; i++, info++) {
+		struct fd dst_fd = fdget(info->dest_fd);
+		struct file *dst_file = dst_fd.file;
+
+		if (!dst_file) {
+			info->status = -EBADF;
+			goto next_loop;
+		}
+
+		if (info->reserved) {
+			info->status = -EINVAL;
+			goto next_fdput;
+		}
+
+		deduped = vfs_dedupe_file_range_one(file, off, dst_file,
+						    info->dest_offset, len);
+		if (deduped == -EBADE)
+			info->status = FILE_DEDUPE_RANGE_DIFFERS;
+		else if (deduped < 0)
+			info->status = deduped;
+		else
+			info->bytes_deduped = len;
+
+next_fdput:
+		fdput(dst_fd);
+next_loop:
+		if (fatal_signal_pending(current))
+			goto out;
+	}
+
+out:
+	return ret;
+}
+EXPORT_SYMBOL(vfs_dedupe_file_range);

src/mm/filemap.c

+/*
+ *	linux/mm/filemap.c
+ *
+ * Copyright (C) 1994-1999  Linus Torvalds
+ */
+
+/*
+ * This file handles the generic file mmap semantics used by
+ * most "normal" filesystems (but you don't /have/ to use this:
+ * the NFS filesystem used to do this differently, for example)
+ */
+#include <linux/export.h>
+#include <linux/compiler.h>
+#include <linux/dax.h>
+#include <linux/fs.h>
+#include <linux/sched/signal.h>
+#include <linux/uaccess.h>
+#include <linux/capability.h>
+#include <linux/kernel_stat.h>
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/mman.h>
+#include <linux/pagemap.h>
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/hash.h>
+#include <linux/writeback.h>
+#include <linux/backing-dev.h>
+#include <linux/pagevec.h>
+#include <linux/blkdev.h>
+#include <linux/security.h>
+#include <linux/cpuset.h>
+#include <linux/hugetlb.h>
+#include <linux/memcontrol.h>
+#include <linux/cleancache.h>
+#include <linux/shmem_fs.h>
+#include <linux/rmap.h>
+#include "internal.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/filemap.h>
+
+/*
+ * FIXME: remove all knowledge of the buffer layer from the core VM
+ */
+#include <linux/buffer_head.h> /* for try_to_free_buffers */
+
+#include <asm/mman.h>
+
+/*
+ * Shared mappings implemented 30.11.1994. It's not fully working yet,
+ * though.
+ *
+ * Shared mappings now work. 15.8.1995  Bruno.
+ *
+ * finished 'unifying' the page and buffer cache and SMP-threaded the
+ * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com>
+ *
+ * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de>
+ */
+
+/*
+ * Lock ordering:
+ *
+ *  ->i_mmap_rwsem		(truncate_pagecache)
+ *    ->private_lock		(__free_pte->__set_page_dirty_buffers)
+ *      ->swap_lock		(exclusive_swap_page, others)
+ *        ->i_pages lock
+ *
+ *  ->i_mutex
+ *    ->i_mmap_rwsem		(truncate->unmap_mapping_range)
+ *
+ *  ->mmap_sem
+ *    ->i_mmap_rwsem
+ *      ->page_table_lock or pte_lock	(various, mainly in memory.c)
+ *        ->i_pages lock	(arch-dependent flush_dcache_mmap_lock)
+ *
+ *  ->mmap_sem
+ *    ->lock_page		(access_process_vm)
+ *
+ *  ->i_mutex			(generic_perform_write)
+ *    ->mmap_sem		(fault_in_pages_readable->do_page_fault)
+ *
+ *  bdi->wb.list_lock
+ *    sb_lock			(fs/fs-writeback.c)
+ *    ->i_pages lock		(__sync_single_inode)
+ *
+ *  ->i_mmap_rwsem
+ *    ->anon_vma.lock		(vma_adjust)
+ *
+ *  ->anon_vma.lock
+ *    ->page_table_lock or pte_lock	(anon_vma_prepare and various)
+ *
+ *  ->page_table_lock or pte_lock
+ *    ->swap_lock		(try_to_unmap_one)
+ *    ->private_lock		(try_to_unmap_one)
+ *    ->i_pages lock		(try_to_unmap_one)
+ *    ->zone_lru_lock(zone)	(follow_page->mark_page_accessed)
+ *    ->zone_lru_lock(zone)	(check_pte_range->isolate_lru_page)
+ *    ->private_lock		(page_remove_rmap->set_page_dirty)
+ *    ->i_pages lock		(page_remove_rmap->set_page_dirty)
+ *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
+ *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
+ *    ->memcg->move_lock	(page_remove_rmap->lock_page_memcg)
+ *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty)
+ *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
+ *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
+ *
+ * ->i_mmap_rwsem
+ *   ->tasklist_lock            (memory_failure, collect_procs_ao)
+ */
+
+static int page_cache_tree_insert(struct address_space *mapping,
+				  struct page *page, void **shadowp)
+{
+	struct radix_tree_node *node;
+	void **slot;
+	int error;
+
+	error = __radix_tree_create(&mapping->i_pages, page->index, 0,
+				    &node, &slot);
+	if (error)
+		return error;
+	if (*slot) {
+		void *p;
+
+		p = radix_tree_deref_slot_protected(slot,
+						    &mapping->i_pages.xa_lock);
+		if (!radix_tree_exceptional_entry(p))
+			return -EEXIST;
+
+		mapping->nrexceptional--;
+		if (shadowp)
+			*shadowp = p;
+	}
+	__radix_tree_replace(&mapping->i_pages, node, slot, page,
+			     workingset_lookup_update(mapping));
+	mapping->nrpages++;
+	return 0;
+}
+
+static void page_cache_tree_delete(struct address_space *mapping,
+				   struct page *page, void *shadow)
+{
+	int i, nr;
+
+	/* hugetlb pages are represented by one entry in the radix tree */
+	nr = PageHuge(page) ? 1 : hpage_nr_pages(page);
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(PageTail(page), page);
+	VM_BUG_ON_PAGE(nr != 1 && shadow, page);
+
+	for (i = 0; i < nr; i++) {
+		struct radix_tree_node *node;
+		void **slot;
+
+		__radix_tree_lookup(&mapping->i_pages, page->index + i,
+				    &node, &slot);
+
+		VM_BUG_ON_PAGE(!node && nr != 1, page);
+
+		radix_tree_clear_tags(&mapping->i_pages, node, slot);
+		__radix_tree_replace(&mapping->i_pages, node, slot, shadow,
+				workingset_lookup_update(mapping));
+	}
+
+	page->mapping = NULL;
+	/* Leave page->index set: truncation lookup relies upon it */
+
+	if (shadow) {
+		mapping->nrexceptional += nr;
+		/*
+		 * Make sure the nrexceptional update is committed before
+		 * the nrpages update so that final truncate racing
+		 * with reclaim does not see both counters 0 at the
+		 * same time and miss a shadow entry.
+		 */
+		smp_wmb();
+	}
+	mapping->nrpages -= nr;
+}
+
+static void unaccount_page_cache_page(struct address_space *mapping,
+				      struct page *page)
+{
+	int nr;
+
+	/*
+	 * if we're uptodate, flush out into the cleancache, otherwise
+	 * invalidate any existing cleancache entries.  We can't leave
+	 * stale data around in the cleancache once our page is gone
+	 */
+	if (PageUptodate(page) && PageMappedToDisk(page))
+		cleancache_put_page(page);
+	else
+		cleancache_invalidate_page(mapping, page);
+
+	VM_BUG_ON_PAGE(PageTail(page), page);
+	VM_BUG_ON_PAGE(page_mapped(page), page);
+	if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) {
+		int mapcount;
+
+		pr_alert("BUG: Bad page cache in process %s  pfn:%05lx\n",
+			 current->comm, page_to_pfn(page));
+		dump_page(page, "still mapped when deleted");
+		dump_stack();
+		add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
+
+		mapcount = page_mapcount(page);
+		if (mapping_exiting(mapping) &&
+		    page_count(page) >= mapcount + 2) {
+			/*
+			 * All vmas have already been torn down, so it's
+			 * a good bet that actually the page is unmapped,
+			 * and we'd prefer not to leak it: if we're wrong,
+			 * some other bad page check should catch it later.
+			 */
+			page_mapcount_reset(page);
+			page_ref_sub(page, mapcount);
+		}
+	}
+
+	/* hugetlb pages do not participate in page cache accounting. */
+	if (PageHuge(page))
+		return;
+
+	nr = hpage_nr_pages(page);
+
+	__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
+	if (PageSwapBacked(page)) {
+		__mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr);
+		if (PageTransHuge(page))
+			__dec_node_page_state(page, NR_SHMEM_THPS);
+	} else {
+		VM_BUG_ON_PAGE(PageTransHuge(page), page);
+	}
+
+	/*
+	 * At this point page must be either written or cleaned by
+	 * truncate.  Dirty page here signals a bug and loss of
+	 * unwritten data.
+	 *
+	 * This fixes dirty accounting after removing the page entirely
+	 * but leaves PageDirty set: it has no effect for truncated
+	 * page and anyway will be cleared before returning page into
+	 * buddy allocator.
+	 */
+	if (WARN_ON_ONCE(PageDirty(page)))
+		account_page_cleaned(page, mapping, inode_to_wb(mapping->host));
+}
+
+/*
+ * Delete a page from the page cache and free it. Caller has to make
+ * sure the page is locked and that nobody else uses it - or that usage
+ * is safe.  The caller must hold the i_pages lock.
+ */
+void __delete_from_page_cache(struct page *page, void *shadow)
+{
+	struct address_space *mapping = page->mapping;
+
+	trace_mm_filemap_delete_from_page_cache(page);
+
+	unaccount_page_cache_page(mapping, page);
+	page_cache_tree_delete(mapping, page, shadow);
+}
+
+static void page_cache_free_page(struct address_space *mapping,
+				struct page *page)
+{
+	void (*freepage)(struct page *);
+
+	freepage = mapping->a_ops->freepage;
+	if (freepage)
+		freepage(page);
+
+	if (PageTransHuge(page) && !PageHuge(page)) {
+		page_ref_sub(page, HPAGE_PMD_NR);
+		VM_BUG_ON_PAGE(page_count(page) <= 0, page);
+	} else {
+		put_page(page);
+	}
+}
+
+/**
+ * delete_from_page_cache - delete page from page cache
+ * @page: the page which the kernel is trying to remove from page cache
+ *
+ * This must be called only on pages that have been verified to be in the page
+ * cache and locked.  It will never put the page into the free list, the caller
+ * has a reference on the page.
+ */
+void delete_from_page_cache(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+	unsigned long flags;
+
+	BUG_ON(!PageLocked(page));
+	xa_lock_irqsave(&mapping->i_pages, flags);
+	__delete_from_page_cache(page, NULL);
+	xa_unlock_irqrestore(&mapping->i_pages, flags);
+
+	page_cache_free_page(mapping, page);
+}
+EXPORT_SYMBOL(delete_from_page_cache);
+
+/*
+ * page_cache_tree_delete_batch - delete several pages from page cache
+ * @mapping: the mapping to which pages belong
+ * @pvec: pagevec with pages to delete
+ *
+ * The function walks over mapping->i_pages and removes pages passed in @pvec
+ * from the mapping. The function expects @pvec to be sorted by page index.
+ * It tolerates holes in @pvec (mapping entries at those indices are not
+ * modified). The function expects only THP head pages to be present in the
+ * @pvec and takes care to delete all corresponding tail pages from the
+ * mapping as well.
+ *
+ * The function expects the i_pages lock to be held.
+ */
+static void
+page_cache_tree_delete_batch(struct address_space *mapping,
+			     struct pagevec *pvec)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	int total_pages = 0;
+	int i = 0, tail_pages = 0;
+	struct page *page;
+	pgoff_t start;
+
+	start = pvec->pages[0]->index;
+	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
+		if (i >= pagevec_count(pvec) && !tail_pages)
+			break;
+		page = radix_tree_deref_slot_protected(slot,
+						       &mapping->i_pages.xa_lock);
+		if (radix_tree_exceptional_entry(page))
+			continue;
+		if (!tail_pages) {
+			/*
+			 * Some page got inserted in our range? Skip it. We
+			 * have our pages locked so they are protected from
+			 * being removed.
+			 */
+			if (page != pvec->pages[i])
+				continue;
+			WARN_ON_ONCE(!PageLocked(page));
+			if (PageTransHuge(page) && !PageHuge(page))
+				tail_pages = HPAGE_PMD_NR - 1;
+			page->mapping = NULL;
+			/*
+			 * Leave page->index set: truncation lookup relies
+			 * upon it
+			 */
+			i++;
+		} else {
+			tail_pages--;
+		}
+		radix_tree_clear_tags(&mapping->i_pages, iter.node, slot);
+		__radix_tree_replace(&mapping->i_pages, iter.node, slot, NULL,
+				workingset_lookup_update(mapping));
+		total_pages++;
+	}
+	mapping->nrpages -= total_pages;
+}
+
+void delete_from_page_cache_batch(struct address_space *mapping,
+				  struct pagevec *pvec)
+{
+	int i;
+	unsigned long flags;
+
+	if (!pagevec_count(pvec))
+		return;
+
+	xa_lock_irqsave(&mapping->i_pages, flags);
+	for (i = 0; i < pagevec_count(pvec); i++) {
+		trace_mm_filemap_delete_from_page_cache(pvec->pages[i]);
+
+		unaccount_page_cache_page(mapping, pvec->pages[i]);
+	}
+	page_cache_tree_delete_batch(mapping, pvec);
+	xa_unlock_irqrestore(&mapping->i_pages, flags);
+
+	for (i = 0; i < pagevec_count(pvec); i++)
+		page_cache_free_page(mapping, pvec->pages[i]);
+}
+
+int filemap_check_errors(struct address_space *mapping)
+{
+	int ret = 0;
+	/* Check for outstanding write errors */
+	if (test_bit(AS_ENOSPC, &mapping->flags) &&
+	    test_and_clear_bit(AS_ENOSPC, &mapping->flags))
+		ret = -ENOSPC;
+	if (test_bit(AS_EIO, &mapping->flags) &&
+	    test_and_clear_bit(AS_EIO, &mapping->flags))
+		ret = -EIO;
+	return ret;
+}
+EXPORT_SYMBOL(filemap_check_errors);
+
+static int filemap_check_and_keep_errors(struct address_space *mapping)
+{
+	/* Check for outstanding write errors */
+	if (test_bit(AS_EIO, &mapping->flags))
+		return -EIO;
+	if (test_bit(AS_ENOSPC, &mapping->flags))
+		return -ENOSPC;
+	return 0;
+}
+
+/**
+ * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
+ * @mapping:	address space structure to write
+ * @start:	offset in bytes where the range starts
+ * @end:	offset in bytes where the range ends (inclusive)
+ * @sync_mode:	enable synchronous operation
+ *
+ * Start writeback against all of a mapping's dirty pages that lie
+ * within the byte offsets <start, end> inclusive.
+ *
+ * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
+ * opposed to a regular memory cleansing writeback.  The difference between
+ * these two operations is that if a dirty page/buffer is encountered, it must
+ * be waited upon, and not just skipped over.
+ */
+int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
+				loff_t end, int sync_mode)
+{
+	int ret;
+	struct writeback_control wbc = {
+		.sync_mode = sync_mode,
+		.nr_to_write = LONG_MAX,
+		.range_start = start,
+		.range_end = end,
+	};
+
+	if (!mapping_cap_writeback_dirty(mapping))
+		return 0;
+
+	wbc_attach_fdatawrite_inode(&wbc, mapping->host);
+	ret = do_writepages(mapping, &wbc);
+	wbc_detach_inode(&wbc);
+	return ret;
+}
+
+static inline int __filemap_fdatawrite(struct address_space *mapping,
+	int sync_mode)
+{
+	return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);
+}
+
+int filemap_fdatawrite(struct address_space *mapping)
+{
+	return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
+}
+EXPORT_SYMBOL(filemap_fdatawrite);
+
+int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
+				loff_t end)
+{
+	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
+}
+EXPORT_SYMBOL(filemap_fdatawrite_range);
+
+/**
+ * filemap_flush - mostly a non-blocking flush
+ * @mapping:	target address_space
+ *
+ * This is a mostly non-blocking flush.  Not suitable for data-integrity
+ * purposes - I/O may not be started against all dirty pages.
+ */
+int filemap_flush(struct address_space *mapping)
+{
+	return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
+}
+EXPORT_SYMBOL(filemap_flush);
+
+/**
+ * filemap_range_has_page - check if a page exists in range.
+ * @mapping:           address space within which to check
+ * @start_byte:        offset in bytes where the range starts
+ * @end_byte:          offset in bytes where the range ends (inclusive)
+ *
+ * Find at least one page in the range supplied, usually used to check if
+ * direct writing in this range will trigger a writeback.
+ */
+bool filemap_range_has_page(struct address_space *mapping,
+			   loff_t start_byte, loff_t end_byte)
+{
+	pgoff_t index = start_byte >> PAGE_SHIFT;
+	pgoff_t end = end_byte >> PAGE_SHIFT;
+	struct page *page;
+
+	if (end_byte < start_byte)
+		return false;
+
+	if (mapping->nrpages == 0)
+		return false;
+
+	if (!find_get_pages_range(mapping, &index, end, 1, &page))
+		return false;
+	put_page(page);
+	return true;
+}
+EXPORT_SYMBOL(filemap_range_has_page);
+
+static void __filemap_fdatawait_range(struct address_space *mapping,
+				     loff_t start_byte, loff_t end_byte)
+{
+	pgoff_t index = start_byte >> PAGE_SHIFT;
+	pgoff_t end = end_byte >> PAGE_SHIFT;
+	struct pagevec pvec;
+	int nr_pages;
+
+	if (end_byte < start_byte)
+		return;
+
+	pagevec_init(&pvec);
+	while (index <= end) {
+		unsigned i;
+
+		nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index,
+				end, PAGECACHE_TAG_WRITEBACK);
+		if (!nr_pages)
+			break;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			wait_on_page_writeback(page);
+			ClearPageError(page);
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+}
+
+/**
+ * filemap_fdatawait_range - wait for writeback to complete
+ * @mapping:		address space structure to wait for
+ * @start_byte:		offset in bytes where the range starts
+ * @end_byte:		offset in bytes where the range ends (inclusive)
+ *
+ * Walk the list of under-writeback pages of the given address space
+ * in the given range and wait for all of them.  Check error status of
+ * the address space and return it.
+ *
+ * Since the error status of the address space is cleared by this function,
+ * callers are responsible for checking the return value and handling and/or
+ * reporting the error.
+ */
+int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
+			    loff_t end_byte)
+{
+	__filemap_fdatawait_range(mapping, start_byte, end_byte);
+	return filemap_check_errors(mapping);
+}
+EXPORT_SYMBOL(filemap_fdatawait_range);
+
+/**
+ * file_fdatawait_range - wait for writeback to complete
+ * @file:		file pointing to address space structure to wait for
+ * @start_byte:		offset in bytes where the range starts
+ * @end_byte:		offset in bytes where the range ends (inclusive)
+ *
+ * Walk the list of under-writeback pages of the address space that file
+ * refers to, in the given range and wait for all of them.  Check error
+ * status of the address space vs. the file->f_wb_err cursor and return it.
+ *
+ * Since the error status of the file is advanced by this function,
+ * callers are responsible for checking the return value and handling and/or
+ * reporting the error.
+ */
+int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte)
+{
+	struct address_space *mapping = file->f_mapping;
+
+	__filemap_fdatawait_range(mapping, start_byte, end_byte);
+	return file_check_and_advance_wb_err(file);
+}
+EXPORT_SYMBOL(file_fdatawait_range);
+
+/**
+ * filemap_fdatawait_keep_errors - wait for writeback without clearing errors
+ * @mapping: address space structure to wait for
+ *
+ * Walk the list of under-writeback pages of the given address space
+ * and wait for all of them.  Unlike filemap_fdatawait(), this function
+ * does not clear error status of the address space.
+ *
+ * Use this function if callers don't handle errors themselves.  Expected
+ * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
+ * fsfreeze(8)
+ */
+int filemap_fdatawait_keep_errors(struct address_space *mapping)
+{
+	__filemap_fdatawait_range(mapping, 0, LLONG_MAX);
+	return filemap_check_and_keep_errors(mapping);
+}
+EXPORT_SYMBOL(filemap_fdatawait_keep_errors);
+
+static bool mapping_needs_writeback(struct address_space *mapping)
+{
+	return (!dax_mapping(mapping) && mapping->nrpages) ||
+	    (dax_mapping(mapping) && mapping->nrexceptional);
+}
+
+int filemap_write_and_wait(struct address_space *mapping)
+{
+	int err = 0;
+
+	if (mapping_needs_writeback(mapping)) {
+		err = filemap_fdatawrite(mapping);
+		/*
+		 * Even if the above returned error, the pages may be
+		 * written partially (e.g. -ENOSPC), so we wait for it.
+		 * But the -EIO is special case, it may indicate the worst
+		 * thing (e.g. bug) happened, so we avoid waiting for it.
+		 */
+		if (err != -EIO) {
+			int err2 = filemap_fdatawait(mapping);
+			if (!err)
+				err = err2;
+		} else {
+			/* Clear any previously stored errors */
+			filemap_check_errors(mapping);
+		}
+	} else {
+		err = filemap_check_errors(mapping);
+	}
+	return err;
+}
+EXPORT_SYMBOL(filemap_write_and_wait);
+
+/**
+ * filemap_write_and_wait_range - write out & wait on a file range
+ * @mapping:	the address_space for the pages
+ * @lstart:	offset in bytes where the range starts
+ * @lend:	offset in bytes where the range ends (inclusive)
+ *
+ * Write out and wait upon file offsets lstart->lend, inclusive.
+ *
+ * Note that @lend is inclusive (describes the last byte to be written) so
+ * that this function can be used to write to the very end-of-file (end = -1).
+ */
+int filemap_write_and_wait_range(struct address_space *mapping,
+				 loff_t lstart, loff_t lend)
+{
+	int err = 0;
+
+	if (mapping_needs_writeback(mapping)) {
+		err = __filemap_fdatawrite_range(mapping, lstart, lend,
+						 WB_SYNC_ALL);
+		/* See comment of filemap_write_and_wait() */
+		if (err != -EIO) {
+			int err2 = filemap_fdatawait_range(mapping,
+						lstart, lend);
+			if (!err)
+				err = err2;
+		} else {
+			/* Clear any previously stored errors */
+			filemap_check_errors(mapping);
+		}
+	} else {
+		err = filemap_check_errors(mapping);
+	}
+	return err;
+}
+EXPORT_SYMBOL(filemap_write_and_wait_range);
+
+void __filemap_set_wb_err(struct address_space *mapping, int err)
+{
+	errseq_t eseq = errseq_set(&mapping->wb_err, err);
+
+	trace_filemap_set_wb_err(mapping, eseq);
+}
+EXPORT_SYMBOL(__filemap_set_wb_err);
+
+/**
+ * file_check_and_advance_wb_err - report wb error (if any) that was previously
+ * 				   and advance wb_err to current one
+ * @file: struct file on which the error is being reported
+ *
+ * When userland calls fsync (or something like nfsd does the equivalent), we
+ * want to report any writeback errors that occurred since the last fsync (or
+ * since the file was opened if there haven't been any).
+ *
+ * Grab the wb_err from the mapping. If it matches what we have in the file,
+ * then just quickly return 0. The file is all caught up.
+ *
+ * If it doesn't match, then take the mapping value, set the "seen" flag in
+ * it and try to swap it into place. If it works, or another task beat us
+ * to it with the new value, then update the f_wb_err and return the error
+ * portion. The error at this point must be reported via proper channels
+ * (a'la fsync, or NFS COMMIT operation, etc.).
+ *
+ * While we handle mapping->wb_err with atomic operations, the f_wb_err
+ * value is protected by the f_lock since we must ensure that it reflects
+ * the latest value swapped in for this file descriptor.
+ */
+int file_check_and_advance_wb_err(struct file *file)
+{
+	int err = 0;
+	errseq_t old = READ_ONCE(file->f_wb_err);
+	struct address_space *mapping = file->f_mapping;
+
+	/* Locklessly handle the common case where nothing has changed */
+	if (errseq_check(&mapping->wb_err, old)) {
+		/* Something changed, must use slow path */
+		spin_lock(&file->f_lock);
+		old = file->f_wb_err;
+		err = errseq_check_and_advance(&mapping->wb_err,
+						&file->f_wb_err);
+		trace_file_check_and_advance_wb_err(file, old);
+		spin_unlock(&file->f_lock);
+	}
+
+	/*
+	 * We're mostly using this function as a drop in replacement for
+	 * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect
+	 * that the legacy code would have had on these flags.
+	 */
+	clear_bit(AS_EIO, &mapping->flags);
+	clear_bit(AS_ENOSPC, &mapping->flags);
+	return err;
+}
+EXPORT_SYMBOL(file_check_and_advance_wb_err);
+
+/**
+ * file_write_and_wait_range - write out & wait on a file range
+ * @file:	file pointing to address_space with pages
+ * @lstart:	offset in bytes where the range starts
+ * @lend:	offset in bytes where the range ends (inclusive)
+ *
+ * Write out and wait upon file offsets lstart->lend, inclusive.
+ *
+ * Note that @lend is inclusive (describes the last byte to be written) so
+ * that this function can be used to write to the very end-of-file (end = -1).
+ *
+ * After writing out and waiting on the data, we check and advance the
+ * f_wb_err cursor to the latest value, and return any errors detected there.
+ */
+int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
+{
+	int err = 0, err2;
+	struct address_space *mapping = file->f_mapping;
+
+	if (mapping_needs_writeback(mapping)) {
+		err = __filemap_fdatawrite_range(mapping, lstart, lend,
+						 WB_SYNC_ALL);
+		/* See comment of filemap_write_and_wait() */
+		if (err != -EIO)
+			__filemap_fdatawait_range(mapping, lstart, lend);
+	}
+	err2 = file_check_and_advance_wb_err(file);
+	if (!err)
+		err = err2;
+	return err;
+}
+EXPORT_SYMBOL(file_write_and_wait_range);
+
+/**
+ * replace_page_cache_page - replace a pagecache page with a new one
+ * @old:	page to be replaced
+ * @new:	page to replace with
+ * @gfp_mask:	allocation mode
+ *
+ * This function replaces a page in the pagecache with a new one.  On
+ * success it acquires the pagecache reference for the new page and
+ * drops it for the old page.  Both the old and new pages must be
+ * locked.  This function does not add the new page to the LRU, the
+ * caller must do that.
+ *
+ * The remove + add is atomic.  The only way this function can fail is
+ * memory allocation failure.
+ */
+int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
+{
+	int error;
+
+	VM_BUG_ON_PAGE(!PageLocked(old), old);
+	VM_BUG_ON_PAGE(!PageLocked(new), new);
+	VM_BUG_ON_PAGE(new->mapping, new);
+
+	error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
+	if (!error) {
+		struct address_space *mapping = old->mapping;
+		void (*freepage)(struct page *);
+		unsigned long flags;
+
+		pgoff_t offset = old->index;
+		freepage = mapping->a_ops->freepage;
+
+		get_page(new);
+		new->mapping = mapping;
+		new->index = offset;
+
+		xa_lock_irqsave(&mapping->i_pages, flags);
+		__delete_from_page_cache(old, NULL);
+		error = page_cache_tree_insert(mapping, new, NULL);
+		BUG_ON(error);
+
+		/*
+		 * hugetlb pages do not participate in page cache accounting.
+		 */
+		if (!PageHuge(new))
+			__inc_node_page_state(new, NR_FILE_PAGES);
+		if (PageSwapBacked(new))
+			__inc_node_page_state(new, NR_SHMEM);
+		xa_unlock_irqrestore(&mapping->i_pages, flags);
+		mem_cgroup_migrate(old, new);
+		radix_tree_preload_end();
+		if (freepage)
+			freepage(old);
+		put_page(old);
+	}
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(replace_page_cache_page);
+
+static int __add_to_page_cache_locked(struct page *page,
+				      struct address_space *mapping,
+				      pgoff_t offset, gfp_t gfp_mask,
+				      void **shadowp)
+{
+	int huge = PageHuge(page);
+	struct mem_cgroup *memcg;
+	int error;
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(PageSwapBacked(page), page);
+
+	if (!huge) {
+		error = mem_cgroup_try_charge(page, current->mm,
+					      gfp_mask, &memcg, false);
+		if (error)
+			return error;
+	}
+
+	error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
+	if (error) {
+		if (!huge)
+			mem_cgroup_cancel_charge(page, memcg, false);
+		return error;
+	}
+
+	get_page(page);
+	page->mapping = mapping;
+	page->index = offset;
+
+	xa_lock_irq(&mapping->i_pages);
+	error = page_cache_tree_insert(mapping, page, shadowp);
+	radix_tree_preload_end();
+	if (unlikely(error))
+		goto err_insert;
+
+	/* hugetlb pages do not participate in page cache accounting. */
+	if (!huge)
+		__inc_node_page_state(page, NR_FILE_PAGES);
+	xa_unlock_irq(&mapping->i_pages);
+	if (!huge)
+		mem_cgroup_commit_charge(page, memcg, false, false);
+	trace_mm_filemap_add_to_page_cache(page);
+	return 0;
+err_insert:
+	page->mapping = NULL;
+	/* Leave page->index set: truncation relies upon it */
+	xa_unlock_irq(&mapping->i_pages);
+	if (!huge)
+		mem_cgroup_cancel_charge(page, memcg, false);
+	put_page(page);
+	return error;
+}
+
+/**
+ * add_to_page_cache_locked - add a locked page to the pagecache
+ * @page:	page to add
+ * @mapping:	the page's address_space
+ * @offset:	page index
+ * @gfp_mask:	page allocation mode
+ *
+ * This function is used to add a page to the pagecache. It must be locked.
+ * This function does not add the page to the LRU.  The caller must do that.
+ */
+int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
+		pgoff_t offset, gfp_t gfp_mask)
+{
+	return __add_to_page_cache_locked(page, mapping, offset,
+					  gfp_mask, NULL);
+}
+EXPORT_SYMBOL(add_to_page_cache_locked);
+
+int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
+				pgoff_t offset, gfp_t gfp_mask)
+{
+	void *shadow = NULL;
+	int ret;
+
+	__SetPageLocked(page);
+	ret = __add_to_page_cache_locked(page, mapping, offset,
+					 gfp_mask, &shadow);
+	if (unlikely(ret))
+		__ClearPageLocked(page);
+	else {
+		/*
+		 * The page might have been evicted from cache only
+		 * recently, in which case it should be activated like
+		 * any other repeatedly accessed page.
+		 * The exception is pages getting rewritten; evicting other
+		 * data from the working set, only to cache data that will
+		 * get overwritten with something else, is a waste of memory.
+		 */
+		if (!(gfp_mask & __GFP_WRITE) &&
+		    shadow && workingset_refault(shadow)) {
+			SetPageActive(page);
+			workingset_activation(page);
+		} else
+			ClearPageActive(page);
+		lru_cache_add(page);
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
+
+#ifdef CONFIG_NUMA
+struct page *__page_cache_alloc(gfp_t gfp)
+{
+	int n;
+	struct page *page;
+
+	if (cpuset_do_page_mem_spread()) {
+		unsigned int cpuset_mems_cookie;
+		do {
+			cpuset_mems_cookie = read_mems_allowed_begin();
+			n = cpuset_mem_spread_node();
+			page = __alloc_pages_node(n, gfp, 0);
+		} while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
+
+		return page;
+	}
+	return alloc_pages(gfp, 0);
+}
+EXPORT_SYMBOL(__page_cache_alloc);
+#endif
+
+/*
+ * In order to wait for pages to become available there must be
+ * waitqueues associated with pages. By using a hash table of
+ * waitqueues where the bucket discipline is to maintain all
+ * waiters on the same queue and wake all when any of the pages
+ * become available, and for the woken contexts to check to be
+ * sure the appropriate page became available, this saves space
+ * at a cost of "thundering herd" phenomena during rare hash
+ * collisions.
+ */
+#define PAGE_WAIT_TABLE_BITS 8
+#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
+static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
+
+static wait_queue_head_t *page_waitqueue(struct page *page)
+{
+	return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)];
+}
+
+void __init pagecache_init(void)
+{
+	int i;
+
+	for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
+		init_waitqueue_head(&page_wait_table[i]);
+
+	page_writeback_init();
+}
+
+/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */
+struct wait_page_key {
+	struct page *page;
+	int bit_nr;
+	int page_match;
+};
+
+struct wait_page_queue {
+	struct page *page;
+	int bit_nr;
+	wait_queue_entry_t wait;
+};
+
+static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
+{
+	struct wait_page_key *key = arg;
+	struct wait_page_queue *wait_page
+		= container_of(wait, struct wait_page_queue, wait);
+
+	if (wait_page->page != key->page)
+	       return 0;
+	key->page_match = 1;
+
+	if (wait_page->bit_nr != key->bit_nr)
+		return 0;
+
+	/* Stop walking if it's locked */
+	if (test_bit(key->bit_nr, &key->page->flags))
+		return -1;
+
+	return autoremove_wake_function(wait, mode, sync, key);
+}
+
+static void wake_up_page_bit(struct page *page, int bit_nr)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	struct wait_page_key key;
+	unsigned long flags;
+	wait_queue_entry_t bookmark;
+
+	key.page = page;
+	key.bit_nr = bit_nr;
+	key.page_match = 0;
+
+	bookmark.flags = 0;
+	bookmark.private = NULL;
+	bookmark.func = NULL;
+	INIT_LIST_HEAD(&bookmark.entry);
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark);
+
+	while (bookmark.flags & WQ_FLAG_BOOKMARK) {
+		/*
+		 * Take a breather from holding the lock,
+		 * allow pages that finish wake up asynchronously
+		 * to acquire the lock and remove themselves
+		 * from wait queue
+		 */
+		spin_unlock_irqrestore(&q->lock, flags);
+		cpu_relax();
+		spin_lock_irqsave(&q->lock, flags);
+		__wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark);
+	}
+
+	/*
+	 * It is possible for other pages to have collided on the waitqueue
+	 * hash, so in that case check for a page match. That prevents a long-
+	 * term waiter
+	 *
+	 * It is still possible to miss a case here, when we woke page waiters
+	 * and removed them from the waitqueue, but there are still other
+	 * page waiters.
+	 */
+	if (!waitqueue_active(q) || !key.page_match) {
+		ClearPageWaiters(page);
+		/*
+		 * It's possible to miss clearing Waiters here, when we woke
+		 * our page waiters, but the hashed waitqueue has waiters for
+		 * other pages on it.
+		 *
+		 * That's okay, it's a rare case. The next waker will clear it.
+		 */
+	}
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+
+static void wake_up_page(struct page *page, int bit)
+{
+	if (!PageWaiters(page))
+		return;
+	wake_up_page_bit(page, bit);
+}
+
+static inline int wait_on_page_bit_common(wait_queue_head_t *q,
+		struct page *page, int bit_nr, int state, bool lock)
+{
+	struct wait_page_queue wait_page;
+	wait_queue_entry_t *wait = &wait_page.wait;
+	int ret = 0;
+
+	init_wait(wait);
+	wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0;
+	wait->func = wake_page_function;
+	wait_page.page = page;
+	wait_page.bit_nr = bit_nr;
+
+	for (;;) {
+		spin_lock_irq(&q->lock);
+
+		if (likely(list_empty(&wait->entry))) {
+			__add_wait_queue_entry_tail(q, wait);
+			SetPageWaiters(page);
+		}
+
+		set_current_state(state);
+
+		spin_unlock_irq(&q->lock);
+
+		if (likely(test_bit(bit_nr, &page->flags))) {
+			io_schedule();
+		}
+
+		if (lock) {
+			if (!test_and_set_bit_lock(bit_nr, &page->flags))
+				break;
+		} else {
+			if (!test_bit(bit_nr, &page->flags))
+				break;
+		}
+
+		if (unlikely(signal_pending_state(state, current))) {
+			ret = -EINTR;
+			break;
+		}
+	}
+
+	finish_wait(q, wait);
+
+	/*
+	 * A signal could leave PageWaiters set. Clearing it here if
+	 * !waitqueue_active would be possible (by open-coding finish_wait),
+	 * but still fail to catch it in the case of wait hash collision. We
+	 * already can fail to clear wait hash collision cases, so don't
+	 * bother with signals either.
+	 */
+
+	return ret;
+}
+
+void wait_on_page_bit(struct page *page, int bit_nr)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, false);
+}
+EXPORT_SYMBOL(wait_on_page_bit);
+
+int wait_on_page_bit_killable(struct page *page, int bit_nr)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, false);
+}
+EXPORT_SYMBOL(wait_on_page_bit_killable);
+
+/**
+ * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
+ * @page: Page defining the wait queue of interest
+ * @waiter: Waiter to add to the queue
+ *
+ * Add an arbitrary @waiter to the wait queue for the nominated @page.
+ */
+void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue_entry_tail(q, waiter);
+	SetPageWaiters(page);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(add_page_wait_queue);
+
+#ifndef clear_bit_unlock_is_negative_byte
+
+/*
+ * PG_waiters is the high bit in the same byte as PG_lock.
+ *
+ * On x86 (and on many other architectures), we can clear PG_lock and
+ * test the sign bit at the same time. But if the architecture does
+ * not support that special operation, we just do this all by hand
+ * instead.
+ *
+ * The read of PG_waiters has to be after (or concurrently with) PG_locked
+ * being cleared, but a memory barrier should be unneccssary since it is
+ * in the same byte as PG_locked.
+ */
+static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
+{
+	clear_bit_unlock(nr, mem);
+	/* smp_mb__after_atomic(); */
+	return test_bit(PG_waiters, mem);
+}
+
+#endif
+
+/**
+ * unlock_page - unlock a locked page
+ * @page: the page
+ *
+ * Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
+ * Also wakes sleepers in wait_on_page_writeback() because the wakeup
+ * mechanism between PageLocked pages and PageWriteback pages is shared.
+ * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
+ *
+ * Note that this depends on PG_waiters being the sign bit in the byte
+ * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
+ * clear the PG_locked bit and test PG_waiters at the same time fairly
+ * portably (architectures that do LL/SC can test any bit, while x86 can
+ * test the sign bit).
+ */
+void unlock_page(struct page *page)
+{
+	BUILD_BUG_ON(PG_waiters != 7);
+	page = compound_head(page);
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
+		wake_up_page_bit(page, PG_locked);
+}
+EXPORT_SYMBOL(unlock_page);
+
+/**
+ * end_page_writeback - end writeback against a page
+ * @page: the page
+ */
+void end_page_writeback(struct page *page)
+{
+	/*
+	 * TestClearPageReclaim could be used here but it is an atomic
+	 * operation and overkill in this particular case. Failing to
+	 * shuffle a page marked for immediate reclaim is too mild to
+	 * justify taking an atomic operation penalty at the end of
+	 * ever page writeback.
+	 */
+	if (PageReclaim(page)) {
+		ClearPageReclaim(page);
+		rotate_reclaimable_page(page);
+	}
+
+	if (!test_clear_page_writeback(page))
+		BUG();
+
+	smp_mb__after_atomic();
+	wake_up_page(page, PG_writeback);
+}
+EXPORT_SYMBOL(end_page_writeback);
+
+/*
+ * After completing I/O on a page, call this routine to update the page
+ * flags appropriately
+ */
+void page_endio(struct page *page, bool is_write, int err)
+{
+	if (!is_write) {
+		if (!err) {
+			SetPageUptodate(page);
+		} else {
+			ClearPageUptodate(page);
+			SetPageError(page);
+		}
+		unlock_page(page);
+	} else {
+		if (err) {
+			struct address_space *mapping;
+
+			SetPageError(page);
+			mapping = page_mapping(page);
+			if (mapping)
+				mapping_set_error(mapping, err);
+		}
+		end_page_writeback(page);
+	}
+}
+EXPORT_SYMBOL_GPL(page_endio);
+
+/**
+ * __lock_page - get a lock on the page, assuming we need to sleep to get it
+ * @__page: the page to lock
+ */
+void __lock_page(struct page *__page)
+{
+	struct page *page = compound_head(__page);
+	wait_queue_head_t *q = page_waitqueue(page);
+	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, true);
+}
+EXPORT_SYMBOL(__lock_page);
+
+int __lock_page_killable(struct page *__page)
+{
+	struct page *page = compound_head(__page);
+	wait_queue_head_t *q = page_waitqueue(page);
+	return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, true);
+}
+EXPORT_SYMBOL_GPL(__lock_page_killable);
+
+/*
+ * Return values:
+ * 1 - page is locked; mmap_sem is still held.
+ * 0 - page is not locked.
+ *     mmap_sem has been released (up_read()), unless flags had both
+ *     FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in
+ *     which case mmap_sem is still held.
+ *
+ * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1
+ * with the page locked and the mmap_sem unperturbed.
+ */
+int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
+			 unsigned int flags)
+{
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		/*
+		 * CAUTION! In this case, mmap_sem is not released
+		 * even though return 0.
+		 */
+		if (flags & FAULT_FLAG_RETRY_NOWAIT)
+			return 0;
+
+		up_read(&mm->mmap_sem);
+		if (flags & FAULT_FLAG_KILLABLE)
+			wait_on_page_locked_killable(page);
+		else
+			wait_on_page_locked(page);
+		return 0;
+	} else {
+		if (flags & FAULT_FLAG_KILLABLE) {
+			int ret;
+
+			ret = __lock_page_killable(page);
+			if (ret) {
+				up_read(&mm->mmap_sem);
+				return 0;
+			}
+		} else
+			__lock_page(page);
+		return 1;
+	}
+}
+
+/**
+ * page_cache_next_hole - find the next hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
+ * lowest indexed hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'return - index >=
+ * max_scan' will be true). In rare cases of index wrap-around, 0 will
+ * be returned.
+ *
+ * page_cache_next_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 5, then subsequently a hole is created at
+ * index 10, page_cache_next_hole covering both indexes may return 10
+ * if called under rcu_read_lock.
+ */
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		struct page *page;
+
+		page = radix_tree_lookup(&mapping->i_pages, index);
+		if (!page || radix_tree_exceptional_entry(page))
+			break;
+		index++;
+		if (index == 0)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(page_cache_next_hole);
+
+/**
+ * page_cache_prev_hole - find the prev hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search backwards in the range [max(index-max_scan+1, 0), index] for
+ * the first hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'index - return >=
+ * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
+ * will be returned.
+ *
+ * page_cache_prev_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 10, then subsequently a hole is created at
+ * index 5, page_cache_prev_hole covering both indexes may return 5 if
+ * called under rcu_read_lock.
+ */
+pgoff_t page_cache_prev_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		struct page *page;
+
+		page = radix_tree_lookup(&mapping->i_pages, index);
+		if (!page || radix_tree_exceptional_entry(page))
+			break;
+		index--;
+		if (index == ULONG_MAX)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(page_cache_prev_hole);
+
+/**
+ * find_get_entry - find and get a page cache entry
+ * @mapping: the address_space to search
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned with an increased refcount.
+ *
+ * If the slot holds a shadow entry of a previously evicted page, or a
+ * swap entry from shmem/tmpfs, it is returned.
+ *
+ * Otherwise, %NULL is returned.
+ */
+struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
+{
+	void **pagep;
+	struct page *head, *page;
+
+	rcu_read_lock();
+repeat:
+	page = NULL;
+	pagep = radix_tree_lookup_slot(&mapping->i_pages, offset);
+	if (pagep) {
+		page = radix_tree_deref_slot(pagep);
+		if (unlikely(!page))
+			goto out;
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page))
+				goto repeat;
+			/*
+			 * A shadow entry of a recently evicted page,
+			 * or a swap entry from shmem/tmpfs.  Return
+			 * it without attempting to raise page count.
+			 */
+			goto out;
+		}
+
+		head = compound_head(page);
+		if (!page_cache_get_speculative(head))
+			goto repeat;
+
+		/* The page was split under us? */
+		if (compound_head(page) != head) {
+			put_page(head);
+			goto repeat;
+		}
+
+		/*
+		 * Has the page moved?
+		 * This is part of the lockless pagecache protocol. See
+		 * include/linux/pagemap.h for details.
+		 */
+		if (unlikely(page != *pagep)) {
+			put_page(head);
+			goto repeat;
+		}
+	}
+out:
+	rcu_read_unlock();
+
+	return page;
+}
+EXPORT_SYMBOL(find_get_entry);
+
+/**
+ * find_lock_entry - locate, pin and lock a page cache entry
+ * @mapping: the address_space to search
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the slot holds a shadow entry of a previously evicted page, or a
+ * swap entry from shmem/tmpfs, it is returned.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_entry() may sleep.
+ */
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
+{
+	struct page *page;
+
+repeat:
+	page = find_get_entry(mapping, offset);
+	if (page && !radix_tree_exception(page)) {
+		lock_page(page);
+		/* Has the page been truncated? */
+		if (unlikely(page_mapping(page) != mapping)) {
+			unlock_page(page);
+			put_page(page);
+			goto repeat;
+		}
+		VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
+	}
+	return page;
+}
+EXPORT_SYMBOL(find_lock_entry);
+
+/**
+ * pagecache_get_page - find and get a page reference
+ * @mapping: the address_space to search
+ * @offset: the page index
+ * @fgp_flags: PCG flags
+ * @gfp_mask: gfp mask to use for the page cache data page allocation
+ *
+ * Looks up the page cache slot at @mapping & @offset.
+ *
+ * PCG flags modify how the page is returned.
+ *
+ * @fgp_flags can be:
+ *
+ * - FGP_ACCESSED: the page will be marked accessed
+ * - FGP_LOCK: Page is return locked
+ * - FGP_CREAT: If page is not present then a new page is allocated using
+ *   @gfp_mask and added to the page cache and the VM's LRU
+ *   list. The page is returned locked and with an increased
+ *   refcount. Otherwise, NULL is returned.
+ *
+ * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
+ * if the GFP flags specified for FGP_CREAT are atomic.
+ *
+ * If there is a page cache page, it is returned with an increased refcount.
+ */
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
+	int fgp_flags, gfp_t gfp_mask)
+{
+	struct page *page;
+
+repeat:
+	page = find_get_entry(mapping, offset);
+	if (radix_tree_exceptional_entry(page))
+		page = NULL;
+	if (!page)
+		goto no_page;
+
+	if (fgp_flags & FGP_LOCK) {
+		if (fgp_flags & FGP_NOWAIT) {
+			if (!trylock_page(page)) {
+				put_page(page);
+				return NULL;
+			}
+		} else {
+			lock_page(page);
+		}
+
+		/* Has the page been truncated? */
+		if (unlikely(page->mapping != mapping)) {
+			unlock_page(page);
+			put_page(page);
+			goto repeat;
+		}
+		VM_BUG_ON_PAGE(page->index != offset, page);
+	}
+
+	if (page && (fgp_flags & FGP_ACCESSED))
+		mark_page_accessed(page);
+
+no_page:
+	if (!page && (fgp_flags & FGP_CREAT)) {
+		int err;
+		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
+			gfp_mask |= __GFP_WRITE;
+		if (fgp_flags & FGP_NOFS)
+			gfp_mask &= ~__GFP_FS;
+
+		page = __page_cache_alloc(gfp_mask);
+		if (!page)
+			return NULL;
+
+		if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK)))
+			fgp_flags |= FGP_LOCK;
+
+		/* Init accessed so avoid atomic mark_page_accessed later */
+		if (fgp_flags & FGP_ACCESSED)
+			__SetPageReferenced(page);
+
+		err = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
+		if (unlikely(err)) {
+			put_page(page);
+			page = NULL;
+			if (err == -EEXIST)
+				goto repeat;
+		}
+	}
+
+	return page;
+}
+EXPORT_SYMBOL(pagecache_get_page);
+
+/**
+ * find_get_entries - gang pagecache lookup
+ * @mapping:	The address_space to search
+ * @start:	The starting page cache index
+ * @nr_entries:	The maximum number of entries
+ * @entries:	Where the resulting entries are placed
+ * @indices:	The cache indices corresponding to the entries in @entries
+ *
+ * find_get_entries() will search for and return a group of up to
+ * @nr_entries entries in the mapping.  The entries are placed at
+ * @entries.  find_get_entries() takes a reference against any actual
+ * pages it returns.
+ *
+ * The search returns a group of mapping-contiguous page cache entries
+ * with ascending indexes.  There may be holes in the indices due to
+ * not-present pages.
+ *
+ * Any shadow entries of evicted pages, or swap entries from
+ * shmem/tmpfs, are included in the returned array.
+ *
+ * find_get_entries() returns the number of pages and shadow entries
+ * which were found.
+ */
+unsigned find_get_entries(struct address_space *mapping,
+			  pgoff_t start, unsigned int nr_entries,
+			  struct page **entries, pgoff_t *indices)
+{
+	void **slot;
+	unsigned int ret = 0;
+	struct radix_tree_iter iter;
+
+	if (!nr_entries)
+		return 0;
+
+	rcu_read_lock();
+	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
+		struct page *head, *page;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			continue;
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page)) {
+				slot = radix_tree_iter_retry(&iter);
+				continue;
+			}
+			/*
+			 * A shadow entry of a recently evicted page, a swap
+			 * entry from shmem/tmpfs or a DAX entry.  Return it
+			 * without attempting to raise page count.
+			 */
+			goto export;
+		}
+
+		head = compound_head(page);
+		if (!page_cache_get_speculative(head))
+			goto repeat;
+
+		/* The page was split under us? */
+		if (compound_head(page) != head) {
+			put_page(head);
+			goto repeat;
+		}
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			put_page(head);
+			goto repeat;
+		}
+export:
+		indices[ret] = iter.index;
+		entries[ret] = page;
+		if (++ret == nr_entries)
+			break;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * find_get_pages_range - gang pagecache lookup
+ * @mapping:	The address_space to search
+ * @start:	The starting page index
+ * @end:	The final page index (inclusive)
+ * @nr_pages:	The maximum number of pages
+ * @pages:	Where the resulting pages are placed
+ *
+ * find_get_pages_range() will search for and return a group of up to @nr_pages
+ * pages in the mapping starting at index @start and up to index @end
+ * (inclusive).  The pages are placed at @pages.  find_get_pages_range() takes
+ * a reference against the returned pages.
+ *
+ * The search returns a group of mapping-contiguous pages with ascending
+ * indexes.  There may be holes in the indices due to not-present pages.
+ * We also update @start to index the next page for the traversal.
+ *
+ * find_get_pages_range() returns the number of pages which were found. If this
+ * number is smaller than @nr_pages, the end of specified range has been
+ * reached.
+ */
+unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
+			      pgoff_t end, unsigned int nr_pages,
+			      struct page **pages)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned ret = 0;
+
+	if (unlikely(!nr_pages))
+		return 0;
+
+	rcu_read_lock();
+	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, *start) {
+		struct page *head, *page;
+
+		if (iter.index > end)
+			break;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			continue;
+
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page)) {
+				slot = radix_tree_iter_retry(&iter);
+				continue;
+			}
+			/*
+			 * A shadow entry of a recently evicted page,
+			 * or a swap entry from shmem/tmpfs.  Skip
+			 * over it.
+			 */
+			continue;
+		}
+
+		head = compound_head(page);
+		if (!page_cache_get_speculative(head))
+			goto repeat;
+
+		/* The page was split under us? */
+		if (compound_head(page) != head) {
+			put_page(head);
+			goto repeat;
+		}
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			put_page(head);
+			goto repeat;
+		}
+
+		pages[ret] = page;
+		if (++ret == nr_pages) {
+			*start = pages[ret - 1]->index + 1;
+			goto out;
+		}
+	}
+
+	/*
+	 * We come here when there is no page beyond @end. We take care to not
+	 * overflow the index @start as it confuses some of the callers. This
+	 * breaks the iteration when there is page at index -1 but that is
+	 * already broken anyway.
+	 */
+	if (end == (pgoff_t)-1)
+		*start = (pgoff_t)-1;
+	else
+		*start = end + 1;
+out:
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/**
+ * find_get_pages_contig - gang contiguous pagecache lookup
+ * @mapping:	The address_space to search
+ * @index:	The starting page index
+ * @nr_pages:	The maximum number of pages
+ * @pages:	Where the resulting pages are placed
+ *
+ * find_get_pages_contig() works exactly like find_get_pages(), except
+ * that the returned number of pages are guaranteed to be contiguous.
+ *
+ * find_get_pages_contig() returns the number of pages which were found.
+ */
+unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
+			       unsigned int nr_pages, struct page **pages)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int ret = 0;
+
+	if (unlikely(!nr_pages))
+		return 0;
+
+	rcu_read_lock();
+	radix_tree_for_each_contig(slot, &mapping->i_pages, &iter, index) {
+		struct page *head, *page;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		/* The hole, there no reason to continue */
+		if (unlikely(!page))
+			break;
+
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page)) {
+				slot = radix_tree_iter_retry(&iter);
+				continue;
+			}
+			/*
+			 * A shadow entry of a recently evicted page,
+			 * or a swap entry from shmem/tmpfs.  Stop
+			 * looking for contiguous pages.
+			 */
+			break;
+		}
+
+		head = compound_head(page);
+		if (!page_cache_get_speculative(head))
+			goto repeat;
+
+		/* The page was split under us? */
+		if (compound_head(page) != head) {
+			put_page(head);
+			goto repeat;
+		}
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			put_page(head);
+			goto repeat;
+		}
+
+		/*
+		 * must check mapping and index after taking the ref.
+		 * otherwise we can get both false positives and false
+		 * negatives, which is just confusing to the caller.
+		 */
+		if (page->mapping == NULL || page_to_pgoff(page) != iter.index) {
+			put_page(page);
+			break;
+		}
+
+		pages[ret] = page;
+		if (++ret == nr_pages)
+			break;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL(find_get_pages_contig);
+
+/**
+ * find_get_pages_range_tag - find and return pages in given range matching @tag
+ * @mapping:	the address_space to search
+ * @index:	the starting page index
+ * @end:	The final page index (inclusive)
+ * @tag:	the tag index
+ * @nr_pages:	the maximum number of pages
+ * @pages:	where the resulting pages are placed
+ *
+ * Like find_get_pages, except we only return pages which are tagged with
+ * @tag.   We update @index to index the next page for the traversal.
+ */
+unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
+			pgoff_t end, int tag, unsigned int nr_pages,
+			struct page **pages)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned ret = 0;
+
+	if (unlikely(!nr_pages))
+		return 0;
+
+	rcu_read_lock();
+	radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, *index, tag) {
+		struct page *head, *page;
+
+		if (iter.index > end)
+			break;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			continue;
+
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page)) {
+				slot = radix_tree_iter_retry(&iter);
+				continue;
+			}
+			/*
+			 * A shadow entry of a recently evicted page.
+			 *
+			 * Those entries should never be tagged, but
+			 * this tree walk is lockless and the tags are
+			 * looked up in bulk, one radix tree node at a
+			 * time, so there is a sizable window for page
+			 * reclaim to evict a page we saw tagged.
+			 *
+			 * Skip over it.
+			 */
+			continue;
+		}
+
+		head = compound_head(page);
+		if (!page_cache_get_speculative(head))
+			goto repeat;
+
+		/* The page was split under us? */
+		if (compound_head(page) != head) {
+			put_page(head);
+			goto repeat;
+		}
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			put_page(head);
+			goto repeat;
+		}
+
+		pages[ret] = page;
+		if (++ret == nr_pages) {
+			*index = pages[ret - 1]->index + 1;
+			goto out;
+		}
+	}
+
+	/*
+	 * We come here when we got at @end. We take care to not overflow the
+	 * index @index as it confuses some of the callers. This breaks the
+	 * iteration when there is page at index -1 but that is already broken
+	 * anyway.
+	 */
+	if (end == (pgoff_t)-1)
+		*index = (pgoff_t)-1;
+	else
+		*index = end + 1;
+out:
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(find_get_pages_range_tag);
+
+/**
+ * find_get_entries_tag - find and return entries that match @tag
+ * @mapping:	the address_space to search
+ * @start:	the starting page cache index
+ * @tag:	the tag index
+ * @nr_entries:	the maximum number of entries
+ * @entries:	where the resulting entries are placed
+ * @indices:	the cache indices corresponding to the entries in @entries
+ *
+ * Like find_get_entries, except we only return entries which are tagged with
+ * @tag.
+ */
+unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
+			int tag, unsigned int nr_entries,
+			struct page **entries, pgoff_t *indices)
+{
+	void **slot;
+	unsigned int ret = 0;
+	struct radix_tree_iter iter;
+
+	if (!nr_entries)
+		return 0;
+
+	rcu_read_lock();
+	radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start, tag) {
+		struct page *head, *page;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			continue;
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page)) {
+				slot = radix_tree_iter_retry(&iter);
+				continue;
+			}
+
+			/*
+			 * A shadow entry of a recently evicted page, a swap
+			 * entry from shmem/tmpfs or a DAX entry.  Return it
+			 * without attempting to raise page count.
+			 */
+			goto export;
+		}
+
+		head = compound_head(page);
+		if (!page_cache_get_speculative(head))
+			goto repeat;
+
+		/* The page was split under us? */
+		if (compound_head(page) != head) {
+			put_page(head);
+			goto repeat;
+		}
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			put_page(head);
+			goto repeat;
+		}
+export:
+		indices[ret] = iter.index;
+		entries[ret] = page;
+		if (++ret == nr_entries)
+			break;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL(find_get_entries_tag);
+
+/*
+ * CD/DVDs are error prone. When a medium error occurs, the driver may fail
+ * a _large_ part of the i/o request. Imagine the worst scenario:
+ *
+ *      ---R__________________________________________B__________
+ *         ^ reading here                             ^ bad block(assume 4k)
+ *
+ * read(R) => miss => readahead(R...B) => media error => frustrating retries
+ * => failing the whole request => read(R) => read(R+1) =>
+ * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) =>
+ * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) =>
+ * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ......
+ *
+ * It is going insane. Fix it by quickly scaling down the readahead size.
+ */
+static void shrink_readahead_size_eio(struct file *filp,
+					struct file_ra_state *ra)
+{
+	ra->ra_pages /= 4;
+}
+
+/**
+ * generic_file_buffered_read - generic file read routine
+ * @iocb:	the iocb to read
+ * @iter:	data destination
+ * @written:	already copied
+ *
+ * This is a generic file read routine, and uses the
+ * mapping->a_ops->readpage() function for the actual low-level stuff.
+ *
+ * This is really ugly. But the goto's actually try to clarify some
+ * of the logic when it comes to error handling etc.
+ */
+static ssize_t generic_file_buffered_read(struct kiocb *iocb,
+		struct iov_iter *iter, ssize_t written)
+{
+	struct file *filp = iocb->ki_filp;
+	struct address_space *mapping = filp->f_mapping;
+	struct inode *inode = mapping->host;
+	struct file_ra_state *ra = &filp->f_ra;
+	loff_t *ppos = &iocb->ki_pos;
+	pgoff_t index;
+	pgoff_t last_index;
+	pgoff_t prev_index;
+	unsigned long offset;      /* offset into pagecache page */
+	unsigned int prev_offset;
+	int error = 0;
+
+	if (unlikely(*ppos >= inode->i_sb->s_maxbytes))
+		return 0;
+	iov_iter_truncate(iter, inode->i_sb->s_maxbytes);
+
+	index = *ppos >> PAGE_SHIFT;
+	prev_index = ra->prev_pos >> PAGE_SHIFT;
+	prev_offset = ra->prev_pos & (PAGE_SIZE-1);
+	last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT;
+	offset = *ppos & ~PAGE_MASK;
+
+	for (;;) {
+		struct page *page;
+		pgoff_t end_index;
+		loff_t isize;
+		unsigned long nr, ret;
+
+		cond_resched();
+find_page:
+		if (fatal_signal_pending(current)) {
+			error = -EINTR;
+			goto out;
+		}
+
+		page = find_get_page(mapping, index);
+		if (!page) {
+			if (iocb->ki_flags & IOCB_NOWAIT)
+				goto would_block;
+			page_cache_sync_readahead(mapping,
+					ra, filp,
+					index, last_index - index);
+			page = find_get_page(mapping, index);
+			if (unlikely(page == NULL))
+				goto no_cached_page;
+		}
+		if (PageReadahead(page)) {
+			page_cache_async_readahead(mapping,
+					ra, filp, page,
+					index, last_index - index);
+		}
+		if (!PageUptodate(page)) {
+			if (iocb->ki_flags & IOCB_NOWAIT) {
+				put_page(page);
+				goto would_block;
+			}
+
+			/*
+			 * See comment in do_read_cache_page on why
+			 * wait_on_page_locked is used to avoid unnecessarily
+			 * serialisations and why it's safe.
+			 */
+			error = wait_on_page_locked_killable(page);
+			if (unlikely(error))
+				goto readpage_error;
+			if (PageUptodate(page))
+				goto page_ok;
+
+			if (inode->i_blkbits == PAGE_SHIFT ||
+					!mapping->a_ops->is_partially_uptodate)
+				goto page_not_up_to_date;
+			/* pipes can't handle partially uptodate pages */
+			if (unlikely(iter->type & ITER_PIPE))
+				goto page_not_up_to_date;
+			if (!trylock_page(page))
+				goto page_not_up_to_date;
+			/* Did it get truncated before we got the lock? */
+			if (!page->mapping)
+				goto page_not_up_to_date_locked;
+			if (!mapping->a_ops->is_partially_uptodate(page,
+							offset, iter->count))
+				goto page_not_up_to_date_locked;
+			unlock_page(page);
+		}
+page_ok:
+		/*
+		 * i_size must be checked after we know the page is Uptodate.
+		 *
+		 * Checking i_size after the check allows us to calculate
+		 * the correct value for "nr", which means the zero-filled
+		 * part of the page is not copied back to userspace (unless
+		 * another truncate extends the file - this is desired though).
+		 */
+
+		isize = i_size_read(inode);
+		end_index = (isize - 1) >> PAGE_SHIFT;
+		if (unlikely(!isize || index > end_index)) {
+			put_page(page);
+			goto out;
+		}
+
+		/* nr is the maximum number of bytes to copy from this page */
+		nr = PAGE_SIZE;
+		if (index == end_index) {
+			nr = ((isize - 1) & ~PAGE_MASK) + 1;
+			if (nr <= offset) {
+				put_page(page);
+				goto out;
+			}
+		}
+		nr = nr - offset;
+
+		/* If users can be writing to this page using arbitrary
+		 * virtual addresses, take care about potential aliasing
+		 * before reading the page on the kernel side.
+		 */
+		if (mapping_writably_mapped(mapping))
+			flush_dcache_page(page);
+
+		/*
+		 * When a sequential read accesses a page several times,
+		 * only mark it as accessed the first time.
+		 */
+		if (prev_index != index || offset != prev_offset)
+			mark_page_accessed(page);
+		prev_index = index;
+
+		/*
+		 * Ok, we have the page, and it's up-to-date, so
+		 * now we can copy it to user space...
+		 */
+
+		ret = copy_page_to_iter(page, offset, nr, iter);
+		offset += ret;
+		index += offset >> PAGE_SHIFT;
+		offset &= ~PAGE_MASK;
+		prev_offset = offset;
+
+		put_page(page);
+		written += ret;
+		if (!iov_iter_count(iter))
+			goto out;
+		if (ret < nr) {
+			error = -EFAULT;
+			goto out;
+		}
+		continue;
+
+page_not_up_to_date:
+		/* Get exclusive access to the page ... */
+		error = lock_page_killable(page);
+		if (unlikely(error))
+			goto readpage_error;
+
+page_not_up_to_date_locked:
+		/* Did it get truncated before we got the lock? */
+		if (!page->mapping) {
+			unlock_page(page);
+			put_page(page);
+			continue;
+		}
+
+		/* Did somebody else fill it already? */
+		if (PageUptodate(page)) {
+			unlock_page(page);
+			goto page_ok;
+		}
+
+readpage:
+		/*
+		 * A previous I/O error may have been due to temporary
+		 * failures, eg. multipath errors.
+		 * PG_error will be set again if readpage fails.
+		 */
+		ClearPageError(page);
+		/* Start the actual read. The read will unlock the page. */
+		error = mapping->a_ops->readpage(filp, page);
+
+		if (unlikely(error)) {
+			if (error == AOP_TRUNCATED_PAGE) {
+				put_page(page);
+				error = 0;
+				goto find_page;
+			}
+			goto readpage_error;
+		}
+
+		if (!PageUptodate(page)) {
+			error = lock_page_killable(page);
+			if (unlikely(error))
+				goto readpage_error;
+			if (!PageUptodate(page)) {
+				if (page->mapping == NULL) {
+					/*
+					 * invalidate_mapping_pages got it
+					 */
+					unlock_page(page);
+					put_page(page);
+					goto find_page;
+				}
+				unlock_page(page);
+				shrink_readahead_size_eio(filp, ra);
+				error = -EIO;
+				goto readpage_error;
+			}
+			unlock_page(page);
+		}
+
+		goto page_ok;
+
+readpage_error:
+		/* UHHUH! A synchronous read error occurred. Report it */
+		put_page(page);
+		goto out;
+
+no_cached_page:
+		/*
+		 * Ok, it wasn't cached, so we need to create a new
+		 * page..
+		 */
+		page = page_cache_alloc(mapping);
+		if (!page) {
+			error = -ENOMEM;
+			goto out;
+		}
+		error = add_to_page_cache_lru(page, mapping, index,
+				mapping_gfp_constraint(mapping, GFP_KERNEL));
+		if (error) {
+			put_page(page);
+			if (error == -EEXIST) {
+				error = 0;
+				goto find_page;
+			}
+			goto out;
+		}
+		goto readpage;
+	}
+
+would_block:
+	error = -EAGAIN;
+out:
+	ra->prev_pos = prev_index;
+	ra->prev_pos <<= PAGE_SHIFT;
+	ra->prev_pos |= prev_offset;
+
+	*ppos = ((loff_t)index << PAGE_SHIFT) + offset;
+	file_accessed(filp);
+	return written ? written : error;
+}
+
+/**
+ * generic_file_read_iter - generic filesystem read routine
+ * @iocb:	kernel I/O control block
+ * @iter:	destination for the data read
+ *
+ * This is the "read_iter()" routine for all filesystems
+ * that can use the page cache directly.
+ */
+ssize_t
+generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	size_t count = iov_iter_count(iter);
+	ssize_t retval = 0;
+
+	if (!count)
+		goto out; /* skip atime */
+
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		struct file *file = iocb->ki_filp;
+		struct address_space *mapping = file->f_mapping;
+		struct inode *inode = mapping->host;
+		loff_t size;
+
+		size = i_size_read(inode);
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			if (filemap_range_has_page(mapping, iocb->ki_pos,
+						   iocb->ki_pos + count - 1))
+				return -EAGAIN;
+		} else {
+			retval = filemap_write_and_wait_range(mapping,
+						iocb->ki_pos,
+					        iocb->ki_pos + count - 1);
+			if (retval < 0)
+				goto out;
+		}
+
+		file_accessed(file);
+
+		retval = mapping->a_ops->direct_IO(iocb, iter);
+		if (retval >= 0) {
+			iocb->ki_pos += retval;
+			count -= retval;
+		}
+		iov_iter_revert(iter, count - iov_iter_count(iter));
+
+		/*
+		 * Btrfs can have a short DIO read if we encounter
+		 * compressed extents, so if there was an error, or if
+		 * we've already read everything we wanted to, or if
+		 * there was a short read because we hit EOF, go ahead
+		 * and return.  Otherwise fallthrough to buffered io for
+		 * the rest of the read.  Buffered reads will not work for
+		 * DAX files, so don't bother trying.
+		 */
+		if (retval < 0 || !count || iocb->ki_pos >= size ||
+		    IS_DAX(inode))
+			goto out;
+	}
+
+	retval = generic_file_buffered_read(iocb, iter, retval);
+out:
+	return retval;
+}
+EXPORT_SYMBOL(generic_file_read_iter);
+
+#ifdef CONFIG_MMU
+/**
+ * page_cache_read - adds requested page to the page cache if not already there
+ * @file:	file to read
+ * @offset:	page index
+ * @gfp_mask:	memory allocation flags
+ *
+ * This adds the requested page to the page cache if it isn't already there,
+ * and schedules an I/O to read in its contents from disk.
+ */
+static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
+{
+	struct address_space *mapping = file->f_mapping;
+	struct page *page;
+	int ret;
+
+	do {
+		page = __page_cache_alloc(gfp_mask);
+		if (!page)
+			return -ENOMEM;
+
+		ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
+		if (ret == 0)
+			ret = mapping->a_ops->readpage(file, page);
+		else if (ret == -EEXIST)
+			ret = 0; /* losing race to add is OK */
+
+		put_page(page);
+
+	} while (ret == AOP_TRUNCATED_PAGE);
+
+	return ret;
+}
+
+#define MMAP_LOTSAMISS  (100)
+
+/*
+ * Synchronous readahead happens when we don't even find
+ * a page in the page cache at all.
+ */
+static void do_sync_mmap_readahead(struct vm_area_struct *vma,
+				   struct file_ra_state *ra,
+				   struct file *file,
+				   pgoff_t offset)
+{
+	struct address_space *mapping = file->f_mapping;
+
+	/* If we don't want any read-ahead, don't bother */
+	if (vma->vm_flags & VM_RAND_READ)
+		return;
+	if (!ra->ra_pages)
+		return;
+
+	if (vma->vm_flags & VM_SEQ_READ) {
+		page_cache_sync_readahead(mapping, ra, file, offset,
+					  ra->ra_pages);
+		return;
+	}
+
+	/* Avoid banging the cache line if not needed */
+	if (ra->mmap_miss < MMAP_LOTSAMISS * 10)
+		ra->mmap_miss++;
+
+	/*
+	 * Do we miss much more than hit in this file? If so,
+	 * stop bothering with read-ahead. It will only hurt.
+	 */
+	if (ra->mmap_miss > MMAP_LOTSAMISS)
+		return;
+
+	/*
+	 * mmap read-around
+	 */
+	ra->start = max_t(long, 0, offset - ra->ra_pages / 2);
+	ra->size = ra->ra_pages;
+	ra->async_size = ra->ra_pages / 4;
+	ra_submit(ra, mapping, file);
+}
+
+/*
+ * Asynchronous readahead happens when we find the page and PG_readahead,
+ * so we want to possibly extend the readahead further..
+ */
+static void do_async_mmap_readahead(struct vm_area_struct *vma,
+				    struct file_ra_state *ra,
+				    struct file *file,
+				    struct page *page,
+				    pgoff_t offset)
+{
+	struct address_space *mapping = file->f_mapping;
+
+	/* If we don't want any read-ahead, don't bother */
+	if (vma->vm_flags & VM_RAND_READ)
+		return;
+	if (ra->mmap_miss > 0)
+		ra->mmap_miss--;
+	if (PageReadahead(page))
+		page_cache_async_readahead(mapping, ra, file,
+					   page, offset, ra->ra_pages);
+}
+
+/**
+ * filemap_fault - read in file data for page fault handling
+ * @vmf:	struct vm_fault containing details of the fault
+ *
+ * filemap_fault() is invoked via the vma operations vector for a
+ * mapped memory region to read in file data during a page fault.
+ *
+ * The goto's are kind of ugly, but this streamlines the normal case of having
+ * it in the page cache, and handles the special cases reasonably without
+ * having a lot of duplicated code.
+ *
+ * vma->vm_mm->mmap_sem must be held on entry.
+ *
+ * If our return value has VM_FAULT_RETRY set, it's because
+ * lock_page_or_retry() returned 0.
+ * The mmap_sem has usually been released in this case.
+ * See __lock_page_or_retry() for the exception.
+ *
+ * If our return value does not have VM_FAULT_RETRY set, the mmap_sem
+ * has not been released.
+ *
+ * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set.
+ */
+vm_fault_t filemap_fault(struct vm_fault *vmf)
+{
+	int error;
+	struct file *file = vmf->vma->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	struct file_ra_state *ra = &file->f_ra;
+	struct inode *inode = mapping->host;
+	pgoff_t offset = vmf->pgoff;
+	pgoff_t max_off;
+	struct page *page;
+	vm_fault_t ret = 0;
+
+	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+	if (unlikely(offset >= max_off))
+		return VM_FAULT_SIGBUS;
+
+	/*
+	 * Do we have something in the page cache already?
+	 */
+	page = find_get_page(mapping, offset);
+	if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
+		/*
+		 * We found the page, so try async readahead before
+		 * waiting for the lock.
+		 */
+		do_async_mmap_readahead(vmf->vma, ra, file, page, offset);
+	} else if (!page) {
+		/* No page in the page cache at all */
+		do_sync_mmap_readahead(vmf->vma, ra, file, offset);
+		count_vm_event(PGMAJFAULT);
+		count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
+		ret = VM_FAULT_MAJOR;
+retry_find:
+		page = find_get_page(mapping, offset);
+		if (!page)
+			goto no_cached_page;
+	}
+
+	if (!lock_page_or_retry(page, vmf->vma->vm_mm, vmf->flags)) {
+		put_page(page);
+		return ret | VM_FAULT_RETRY;
+	}
+
+	/* Did it get truncated? */
+	if (unlikely(page->mapping != mapping)) {
+		unlock_page(page);
+		put_page(page);
+		goto retry_find;
+	}
+	VM_BUG_ON_PAGE(page->index != offset, page);
+
+	/*
+	 * We have a locked page in the page cache, now we need to check
+	 * that it's up-to-date. If not, it is going to be due to an error.
+	 */
+	if (unlikely(!PageUptodate(page)))
+		goto page_not_uptodate;
+
+	/*
+	 * Found the page and have a reference on it.
+	 * We must recheck i_size under page lock.
+	 */
+	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+	if (unlikely(offset >= max_off)) {
+		unlock_page(page);
+		put_page(page);
+		return VM_FAULT_SIGBUS;
+	}
+
+	vmf->page = page;
+	return ret | VM_FAULT_LOCKED;
+
+no_cached_page:
+	/*
+	 * We're only likely to ever get here if MADV_RANDOM is in
+	 * effect.
+	 */
+	error = page_cache_read(file, offset, vmf->gfp_mask);
+
+	/*
+	 * The page we want has now been added to the page cache.
+	 * In the unlikely event that someone removed it in the
+	 * meantime, we'll just come back here and read it again.
+	 */
+	if (error >= 0)
+		goto retry_find;
+
+	/*
+	 * An error return from page_cache_read can result if the
+	 * system is low on memory, or a problem occurs while trying
+	 * to schedule I/O.
+	 */
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM;
+	return VM_FAULT_SIGBUS;
+
+page_not_uptodate:
+	/*
+	 * Umm, take care of errors if the page isn't up-to-date.
+	 * Try to re-read it _once_. We do this synchronously,
+	 * because there really aren't any performance issues here
+	 * and we need to check for errors.
+	 */
+	ClearPageError(page);
+	error = mapping->a_ops->readpage(file, page);
+	if (!error) {
+		wait_on_page_locked(page);
+		if (!PageUptodate(page))
+			error = -EIO;
+	}
+	put_page(page);
+
+	if (!error || error == AOP_TRUNCATED_PAGE)
+		goto retry_find;
+
+	/* Things didn't work out. Return zero to tell the mm layer so. */
+	shrink_readahead_size_eio(file, ra);
+	return VM_FAULT_SIGBUS;
+}
+EXPORT_SYMBOL(filemap_fault);
+
+void filemap_map_pages(struct vm_fault *vmf,
+		pgoff_t start_pgoff, pgoff_t end_pgoff)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	struct file *file = vmf->vma->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	pgoff_t last_pgoff = start_pgoff;
+	unsigned long max_idx;
+	struct page *head, *page;
+
+	rcu_read_lock();
+	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start_pgoff) {
+		if (iter.index > end_pgoff)
+			break;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			goto next;
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page)) {
+				slot = radix_tree_iter_retry(&iter);
+				continue;
+			}
+			goto next;
+		}
+
+		head = compound_head(page);
+		if (!page_cache_get_speculative(head))
+			goto repeat;
+
+		/* The page was split under us? */
+		if (compound_head(page) != head) {
+			put_page(head);
+			goto repeat;
+		}
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			put_page(head);
+			goto repeat;
+		}
+
+		if (!PageUptodate(page) ||
+				PageReadahead(page) ||
+				PageHWPoison(page))
+			goto skip;
+		if (!trylock_page(page))
+			goto skip;
+
+		if (page->mapping != mapping || !PageUptodate(page))
+			goto unlock;
+
+		max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
+		if (page->index >= max_idx)
+			goto unlock;
+
+		if (file->f_ra.mmap_miss > 0)
+			file->f_ra.mmap_miss--;
+
+		vmf->address += (iter.index - last_pgoff) << PAGE_SHIFT;
+		if (vmf->pte)
+			vmf->pte += iter.index - last_pgoff;
+		last_pgoff = iter.index;
+		if (alloc_set_pte(vmf, NULL, page))
+			goto unlock;
+		unlock_page(page);
+		goto next;
+unlock:
+		unlock_page(page);
+skip:
+		put_page(page);
+next:
+		/* Huge page is mapped? No need to proceed. */
+		if (pmd_trans_huge(*vmf->pmd))
+			break;
+		if (iter.index == end_pgoff)
+			break;
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(filemap_map_pages);
+
+vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
+{
+	struct page *page = vmf->page;
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	vm_fault_t ret = VM_FAULT_LOCKED;
+
+	sb_start_pagefault(inode->i_sb);
+	file_update_time(vmf->vma->vm_file);
+	lock_page(page);
+	if (page->mapping != inode->i_mapping) {
+		unlock_page(page);
+		ret = VM_FAULT_NOPAGE;
+		goto out;
+	}
+	/*
+	 * We mark the page dirty already here so that when freeze is in
+	 * progress, we are guaranteed that writeback during freezing will
+	 * see the dirty page and writeprotect it again.
+	 */
+	set_page_dirty(page);
+	wait_for_stable_page(page);
+out:
+	sb_end_pagefault(inode->i_sb);
+	return ret;
+}
+
+const struct vm_operations_struct generic_file_vm_ops = {
+	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
+	.page_mkwrite	= filemap_page_mkwrite,
+};
+
+/* This is used for a general mmap of a disk file */
+
+int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
+{
+	struct address_space *mapping = file->f_mapping;
+
+	if (!mapping->a_ops->readpage)
+		return -ENOEXEC;
+	file_accessed(file);
+	vma->vm_ops = &generic_file_vm_ops;
+	return 0;
+}
+
+/*
+ * This is for filesystems which do not implement ->writepage.
+ */
+int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
+		return -EINVAL;
+	return generic_file_mmap(file, vma);
+}
+#else
+int filemap_page_mkwrite(struct vm_fault *vmf)
+{
+	return -ENOSYS;
+}
+int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
+{
+	return -ENOSYS;
+}
+int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_MMU */
+
+EXPORT_SYMBOL(filemap_page_mkwrite);
+EXPORT_SYMBOL(generic_file_mmap);
+EXPORT_SYMBOL(generic_file_readonly_mmap);
+
+static struct page *wait_on_page_read(struct page *page)
+{
+	if (!IS_ERR(page)) {
+		wait_on_page_locked(page);
+		if (!PageUptodate(page)) {
+			put_page(page);
+			page = ERR_PTR(-EIO);
+		}
+	}
+	return page;
+}
+
+static struct page *do_read_cache_page(struct address_space *mapping,
+				pgoff_t index,
+				int (*filler)(void *, struct page *),
+				void *data,
+				gfp_t gfp)
+{
+	struct page *page;
+	int err;
+repeat:
+	page = find_get_page(mapping, index);
+	if (!page) {
+		page = __page_cache_alloc(gfp);
+		if (!page)
+			return ERR_PTR(-ENOMEM);
+		err = add_to_page_cache_lru(page, mapping, index, gfp);
+		if (unlikely(err)) {
+			put_page(page);
+			if (err == -EEXIST)
+				goto repeat;
+			/* Presumably ENOMEM for radix tree node */
+			return ERR_PTR(err);
+		}
+
+filler:
+		err = filler(data, page);
+		if (err < 0) {
+			put_page(page);
+			return ERR_PTR(err);
+		}
+
+		page = wait_on_page_read(page);
+		if (IS_ERR(page))
+			return page;
+		goto out;
+	}
+	if (PageUptodate(page))
+		goto out;
+
+	/*
+	 * Page is not up to date and may be locked due one of the following
+	 * case a: Page is being filled and the page lock is held
+	 * case b: Read/write error clearing the page uptodate status
+	 * case c: Truncation in progress (page locked)
+	 * case d: Reclaim in progress
+	 *
+	 * Case a, the page will be up to date when the page is unlocked.
+	 *    There is no need to serialise on the page lock here as the page
+	 *    is pinned so the lock gives no additional protection. Even if the
+	 *    the page is truncated, the data is still valid if PageUptodate as
+	 *    it's a race vs truncate race.
+	 * Case b, the page will not be up to date
+	 * Case c, the page may be truncated but in itself, the data may still
+	 *    be valid after IO completes as it's a read vs truncate race. The
+	 *    operation must restart if the page is not uptodate on unlock but
+	 *    otherwise serialising on page lock to stabilise the mapping gives
+	 *    no additional guarantees to the caller as the page lock is
+	 *    released before return.
+	 * Case d, similar to truncation. If reclaim holds the page lock, it
+	 *    will be a race with remove_mapping that determines if the mapping
+	 *    is valid on unlock but otherwise the data is valid and there is
+	 *    no need to serialise with page lock.
+	 *
+	 * As the page lock gives no additional guarantee, we optimistically
+	 * wait on the page to be unlocked and check if it's up to date and
+	 * use the page if it is. Otherwise, the page lock is required to
+	 * distinguish between the different cases. The motivation is that we
+	 * avoid spurious serialisations and wakeups when multiple processes
+	 * wait on the same page for IO to complete.
+	 */
+	wait_on_page_locked(page);
+	if (PageUptodate(page))
+		goto out;
+
+	/* Distinguish between all the cases under the safety of the lock */
+	lock_page(page);
+
+	/* Case c or d, restart the operation */
+	if (!page->mapping) {
+		unlock_page(page);
+		put_page(page);
+		goto repeat;
+	}
+
+	/* Someone else locked and filled the page in a very small window */
+	if (PageUptodate(page)) {
+		unlock_page(page);
+		goto out;
+	}
+	goto filler;
+
+out:
+	mark_page_accessed(page);
+	return page;
+}
+
+/**
+ * read_cache_page - read into page cache, fill it if needed
+ * @mapping:	the page's address_space
+ * @index:	the page index
+ * @filler:	function to perform the read
+ * @data:	first arg to filler(data, page) function, often left as NULL
+ *
+ * Read into the page cache. If a page already exists, and PageUptodate() is
+ * not set, try to fill the page and wait for it to become unlocked.
+ *
+ * If the page does not get brought uptodate, return -EIO.
+ */
+struct page *read_cache_page(struct address_space *mapping,
+				pgoff_t index,
+				int (*filler)(void *, struct page *),
+				void *data)
+{
+	return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
+}
+EXPORT_SYMBOL(read_cache_page);
+
+/**
+ * read_cache_page_gfp - read into page cache, using specified page allocation flags.
+ * @mapping:	the page's address_space
+ * @index:	the page index
+ * @gfp:	the page allocator flags to use if allocating
+ *
+ * This is the same as "read_mapping_page(mapping, index, NULL)", but with
+ * any new page allocations done using the specified allocation flags.
+ *
+ * If the page does not get brought uptodate, return -EIO.
+ */
+struct page *read_cache_page_gfp(struct address_space *mapping,
+				pgoff_t index,
+				gfp_t gfp)
+{
+	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
+
+	return do_read_cache_page(mapping, index, filler, NULL, gfp);
+}
+EXPORT_SYMBOL(read_cache_page_gfp);
+
+/*
+ * Performs necessary checks before doing a write
+ *
+ * Can adjust writing position or amount of bytes to write.
+ * Returns appropriate error code that caller should return or
+ * zero in case that write should be allowed.
+ */
+inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	unsigned long limit = rlimit(RLIMIT_FSIZE);
+	loff_t pos;
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	/* FIXME: this is for backwards compatibility with 2.4 */
+	if (iocb->ki_flags & IOCB_APPEND)
+		iocb->ki_pos = i_size_read(inode);
+
+	pos = iocb->ki_pos;
+
+	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+		return -EINVAL;
+
+	if (limit != RLIM_INFINITY) {
+		if (iocb->ki_pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		iov_iter_truncate(from, limit - (unsigned long)pos);
+	}
+
+	/*
+	 * LFS rule
+	 */
+	if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS &&
+				!(file->f_flags & O_LARGEFILE))) {
+		if (pos >= MAX_NON_LFS)
+			return -EFBIG;
+		iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos);
+	}
+
+	/*
+	 * Are we about to exceed the fs block limit ?
+	 *
+	 * If we have written data it becomes a short write.  If we have
+	 * exceeded without writing data we send a signal and return EFBIG.
+	 * Linus frestrict idea will clean these up nicely..
+	 */
+	if (unlikely(pos >= inode->i_sb->s_maxbytes))
+		return -EFBIG;
+
+	iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos);
+	return iov_iter_count(from);
+}
+EXPORT_SYMBOL(generic_write_checks);
+
+int pagecache_write_begin(struct file *file, struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned flags,
+				struct page **pagep, void **fsdata)
+{
+	const struct address_space_operations *aops = mapping->a_ops;
+
+	return aops->write_begin(file, mapping, pos, len, flags,
+							pagep, fsdata);
+}
+EXPORT_SYMBOL(pagecache_write_begin);
+
+int pagecache_write_end(struct file *file, struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned copied,
+				struct page *page, void *fsdata)
+{
+	const struct address_space_operations *aops = mapping->a_ops;
+
+	return aops->write_end(file, mapping, pos, len, copied, page, fsdata);
+}
+EXPORT_SYMBOL(pagecache_write_end);
+
+ssize_t
+generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file	*file = iocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
+	struct inode	*inode = mapping->host;
+	loff_t		pos = iocb->ki_pos;
+	ssize_t		written;
+	size_t		write_len;
+	pgoff_t		end;
+	pr_debug("generic_file_direct_write()");
+	write_len = iov_iter_count(from);
+	end = (pos + write_len - 1) >> PAGE_SHIFT;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		/* If there are pages to writeback, return */
+		if (filemap_range_has_page(inode->i_mapping, pos,
+					   pos + iov_iter_count(from)))
+			return -EAGAIN;
+	} else {
+		written = filemap_write_and_wait_range(mapping, pos,
+							pos + write_len - 1);
+		if (written)
+			goto out;
+	}
+
+	/*
+	 * After a write we want buffered reads to be sure to go to disk to get
+	 * the new data.  We invalidate clean cached page from the region we're
+	 * about to write.  We do this *before* the write so that we can return
+	 * without clobbering -EIOCBQUEUED from ->direct_IO().
+	 */
+	written = invalidate_inode_pages2_range(mapping,
+					pos >> PAGE_SHIFT, end);
+	/*
+	 * If a page can not be invalidated, return 0 to fall back
+	 * to buffered write.
+	 */
+	if (written) {
+		if (written == -EBUSY)
+			return 0;
+		goto out;
+	}
+
+	written = mapping->a_ops->direct_IO(iocb, from);
+
+	/*
+	 * Finally, try again to invalidate clean pages which might have been
+	 * cached by non-direct readahead, or faulted in by get_user_pages()
+	 * if the source of the write was an mmap'ed region of the file
+	 * we're writing.  Either one is a pretty crazy thing to do,
+	 * so we don't support it 100%.  If this invalidation
+	 * fails, tough, the write still worked...
+	 *
+	 * Most of the time we do not need this since dio_complete() will do
+	 * the invalidation for us. However there are some file systems that
+	 * do not end up with dio_complete() being called, so let's not break
+	 * them by removing it completely
+	 */
+	if (mapping->nrpages)
+		invalidate_inode_pages2_range(mapping,
+					pos >> PAGE_SHIFT, end);
+
+	if (written > 0) {
+		pos += written;
+		write_len -= written;
+		if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
+			i_size_write(inode, pos);
+			mark_inode_dirty(inode);
+		}
+		iocb->ki_pos = pos;
+	}
+	iov_iter_revert(from, write_len - iov_iter_count(from));
+out:
+	return written;
+}
+EXPORT_SYMBOL(generic_file_direct_write);
+
+/*
+ * Find or create a page at the given pagecache position. Return the locked
+ * page. This function is specifically for buffered writes.
+ */
+struct page *grab_cache_page_write_begin(struct address_space *mapping,
+					pgoff_t index, unsigned flags)
+{
+	struct page *page;
+	int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT;
+
+	if (flags & AOP_FLAG_NOFS)
+		fgp_flags |= FGP_NOFS;
+
+	page = pagecache_get_page(mapping, index, fgp_flags,
+			mapping_gfp_mask(mapping));
+	if (page)
+		wait_for_stable_page(page);
+
+	return page;
+}
+EXPORT_SYMBOL(grab_cache_page_write_begin);
+
+ssize_t generic_perform_write(struct file *file,
+				struct iov_iter *i, loff_t pos)
+{
+	struct address_space *mapping = file->f_mapping;
+	const struct address_space_operations *a_ops = mapping->a_ops;
+	long status = 0;
+	ssize_t written = 0;
+	unsigned int flags = 0;
+	if (!strncmp(file->f_path.dentry->d_name.name, "sda2", 4)) {
+		pr_debug("start");
+	}
+	do {
+		struct page *page;
+		unsigned long offset;	/* Offset into pagecache page */
+		unsigned long bytes;	/* Bytes to write to page */
+		size_t copied;		/* Bytes copied from user */
+		void *fsdata;
+
+		offset = (pos & (PAGE_SIZE - 1));
+		bytes = min_t(unsigned long, PAGE_SIZE - offset,
+						iov_iter_count(i));
+
+again:
+		/*
+		 * Bring in the user page that we will copy from _first_.
+		 * Otherwise there's a nasty deadlock on copying from the
+		 * same page as we're writing to, without it being marked
+		 * up-to-date.
+		 *
+		 * Not only is this an optimisation, but it is also required
+		 * to check that the address is actually valid, when atomic
+		 * usercopies are used, below.
+		 */
+		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+			status = -EFAULT;
+			break;
+		}
+
+		if (fatal_signal_pending(current)) {
+			status = -EINTR;
+			break;
+		}
+
+		status = a_ops->write_begin(file, mapping, pos, bytes, flags, // -> buffer:block_write_begin:2070
+						&page, &fsdata);
+		pr_debug("status = 0x%lx", status);
+		if (unlikely(status < 0))
+			break;
+		if (mapping_writably_mapped(mapping))
+			flush_dcache_page(page);
+
+		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
+		flush_dcache_page(page);
+		if ((!strncmp(file->f_path.dentry->d_name.name, "sda2", 4)) &&(copied < 4096)) {
+			pr_debug("copied = %u < 4096, iov_iter_count(i)=%u",copied, iov_iter_count(i)); // after last - reads wrong with cmd = 0xc8
+		}
+
+		status = a_ops->write_end(file, mapping, pos, bytes, copied,
+						page, fsdata);
+		if (unlikely(status < 0))
+			break;
+		copied = status;
+
+		cond_resched();
+
+		iov_iter_advance(i, copied);
+
+		if (unlikely(copied == 0)) {
+			/*
+			 * If we were unable to copy any data at all, we must
+			 * fall back to a single segment length write.
+			 *
+			 * If we didn't fallback here, we could livelock
+			 * because not all segments in the iov can be copied at
+			 * once without a pagefault.
+			 */
+			bytes = min_t(unsigned long, PAGE_SIZE - offset,
+						iov_iter_single_seg_count(i));
+			goto again;
+		}
+		pos += copied;
+		written += copied;
+		pr_debug("balance_dirty_pages_ratelimited()");
+		balance_dirty_pages_ratelimited(mapping);
+	} while (iov_iter_count(i));
+
+	return written ? written : status;
+}
+EXPORT_SYMBOL(generic_perform_write);
+
+/**
+ * __generic_file_write_iter - write data to a file
+ * @iocb:	IO state structure (file, offset, etc.)
+ * @from:	iov_iter with data to write
+ *
+ * This function does all the work needed for actually writing data to a
+ * file. It does all basic checks, removes SUID from the file, updates
+ * modification times and calls proper subroutines depending on whether we
+ * do direct IO or a standard buffered write.
+ *
+ * It expects i_mutex to be grabbed unless we work on a block device or similar
+ * object which does not need locking at all.
+ *
+ * This function does *not* take care of syncing data in case of O_SYNC write.
+ * A caller has to handle it. This is mainly due to the fact that we want to
+ * avoid syncing under i_mutex.
+ */
+ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct address_space * mapping = file->f_mapping;
+	struct inode 	*inode = mapping->host;
+	ssize_t		written = 0;
+	ssize_t		err;
+	ssize_t		status;
+
+	/* We can write back this queue in page reclaim */
+	current->backing_dev_info = inode_to_bdi(inode);
+	err = file_remove_privs(file);
+	if (err)
+		goto out;
+
+	err = file_update_time(file);
+	if (err)
+		goto out;
+	if (!strncmp(file->f_path.dentry->d_name.name, "sda2", 4)) {
+		pr_debug("iocb->ki_flags=0x%x", iocb->ki_flags);
+	}
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		loff_t pos, endbyte;
+		pr_debug("using IOCB_DIRECT");
+		written = generic_file_direct_write(iocb, from);
+		/*
+		 * If the write stopped short of completing, fall back to
+		 * buffered writes.  Some filesystems do this for writes to
+		 * holes, for example.  For DAX files, a buffered write will
+		 * not succeed (even if it did, DAX does not handle dirty
+		 * page-cache pages correctly).
+		 */
+		if (written < 0 || !iov_iter_count(from) || IS_DAX(inode))
+			goto out;
+
+		status = generic_perform_write(file, from, pos = iocb->ki_pos);
+		/*
+		 * If generic_perform_write() returned a synchronous error
+		 * then we want to return the number of bytes which were
+		 * direct-written, or the error code if that was zero.  Note
+		 * that this differs from normal direct-io semantics, which
+		 * will return -EFOO even if some bytes were written.
+		 */
+		if (unlikely(status < 0)) {
+			err = status;
+			goto out;
+		}
+		/*
+		 * We need to ensure that the page cache pages are written to
+		 * disk and invalidated to preserve the expected O_DIRECT
+		 * semantics.
+		 */
+		endbyte = pos + status - 1;
+		err = filemap_write_and_wait_range(mapping, pos, endbyte);
+		if (err == 0) {
+			iocb->ki_pos = endbyte + 1;
+			written += status;
+			invalidate_mapping_pages(mapping,
+						 pos >> PAGE_SHIFT,
+						 endbyte >> PAGE_SHIFT);
+		} else {
+			/*
+			 * We don't know how much we wrote, so just return
+			 * the number of bytes which were direct-written
+			 */
+		}
+	} else {
+		pr_debug("NOT using IOCB_DIRECT");
+		written = generic_perform_write(file, from, iocb->ki_pos);
+		if (likely(written > 0))
+			iocb->ki_pos += written;
+	}
+out:
+	current->backing_dev_info = NULL;
+	pr_debug("__generic_file_write_iter() -> %d", written);
+	if (!strncmp(file->f_path.dentry->d_name.name, "sda2", 4)) { //if (written > 511){
+		pr_debug("__generic_file_write_iter() -> %d", written);
+	}
+	return written ? written : err;
+}
+EXPORT_SYMBOL(__generic_file_write_iter);
+
+/**
+ * generic_file_write_iter - write data to a file
+ * @iocb:	IO state structure
+ * @from:	iov_iter with data to write
+ *
+ * This is a wrapper around __generic_file_write_iter() to be used by most
+ * filesystems. It takes care of syncing the file in case of O_SYNC file
+ * and acquires i_mutex as needed.
+ */
+ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	ssize_t ret;
+
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret > 0)
+		ret = __generic_file_write_iter(iocb, from);
+	inode_unlock(inode);
+
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+	return ret;
+}
+EXPORT_SYMBOL(generic_file_write_iter);
+
+/**
+ * try_to_release_page() - release old fs-specific metadata on a page
+ *
+ * @page: the page which the kernel is trying to free
+ * @gfp_mask: memory allocation flags (and I/O mode)
+ *
+ * The address_space is to try to release any data against the page
+ * (presumably at page->private).  If the release was successful, return '1'.
+ * Otherwise return zero.
+ *
+ * This may also be called if PG_fscache is set on a page, indicating that the
+ * page is known to the local caching routines.
+ *
+ * The @gfp_mask argument specifies whether I/O may be performed to release
+ * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS).
+ *
+ */
+int try_to_release_page(struct page *page, gfp_t gfp_mask)
+{
+	struct address_space * const mapping = page->mapping;
+
+	BUG_ON(!PageLocked(page));
+	if (PageWriteback(page))
+		return 0;
+
+	if (mapping && mapping->a_ops->releasepage)
+		return mapping->a_ops->releasepage(page, gfp_mask);
+	return try_to_free_buffers(page);
+}
+
+EXPORT_SYMBOL(try_to_release_page);