// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * raid10.c : Multiple Devices driver for Linux
 *
 * Copyright (C) 2000-2004 Neil Brown
 *
 * RAID-10 support for md.
 *
 * Base on code in raid1.c.  See raid1.c for further copyright information.
 */

#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
#include <linux/raid/md_p.h>
#include <trace/events/block.h>
#include "md.h"
#include "raid10.h"
#include "raid0.h"
#include "md-bitmap.h"

/*
 * RAID10 provides a combination of RAID0 and RAID1 functionality.
 * The layout of data is defined by
 *    chunk_size
 *    raid_disks
 *    near_copies (stored in low byte of layout)
 *    far_copies (stored in second byte of layout)
 *    far_offset (stored in bit 16 of layout )
 *    use_far_sets (stored in bit 17 of layout )
 *    use_far_sets_bugfixed (stored in bit 18 of layout )
 *
 * The data to be stored is divided into chunks using chunksize.  Each device
 * is divided into far_copies sections.   In each section, chunks are laid out
 * in a style similar to raid0, but near_copies copies of each chunk is stored
 * (each on a different drive).  The starting device for each section is offset
 * near_copies from the starting device of the previous section.  Thus there
 * are (near_copies * far_copies) of each chunk, and each is on a different
 * drive.  near_copies and far_copies must be at least one, and their product
 * is at most raid_disks.
 *
 * If far_offset is true, then the far_copies are handled a bit differently.
 * The copies are still in different stripes, but instead of being very far
 * apart on disk, there are adjacent stripes.
 *
 * The far and offset algorithms are handled slightly differently if
 * 'use_far_sets' is true.  In this case, the array's devices are grouped into
 * sets that are (near_copies * far_copies) in size.  The far copied stripes
 * are still shifted by 'near_copies' devices, but this shifting stays confined
 * to the set rather than the entire array.  This is done to improve the number
 * of device combinations that can fail without causing the array to fail.
 * Example 'far' algorithm w/o 'use_far_sets' (each letter represents a chunk
 * on a device):
 *    A B C D    A B C D E
 *      ...         ...
 *    D A B C    E A B C D
 * Example 'far' algorithm w/ 'use_far_sets' enabled (sets illustrated w/ []'s):
 *    [A B] [C D]    [A B] [C D E]
 *    |...| |...|    |...| | ... |
 *    [B A] [D C]    [B A] [E C D]
 */

static void allow_barrier(struct r10conf *conf);
static void lower_barrier(struct r10conf *conf);
static int _enough(struct r10conf *conf, int previous, int ignore);
static int enough(struct r10conf *conf, int ignore);
static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
                                int *skipped);
static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
static void end_reshape_write(struct bio *bio);
static void end_reshape(struct r10conf *conf);

#define raid10_log(md, fmt, args...)                            \
        do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0)

#include "raid1-10.c"

/*
 * for resync bio, r10bio pointer can be retrieved from the per-bio
 * 'struct resync_pages'.
 */
static inline struct r10bio *get_resync_r10bio(struct bio *bio)
{
        return get_resync_pages(bio)->raid_bio;
}

static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
{
        struct r10conf *conf = data;
        int size = offsetof(struct r10bio, devs[conf->geo.raid_disks]);

        /* allocate a r10bio with room for raid_disks entries in the
         * bios array */
        return kzalloc(size, gfp_flags);
}

#define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
/* amount of memory to reserve for resync requests */
#define RESYNC_WINDOW (1024*1024)
/* maximum number of concurrent requests, memory permitting */
#define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE)
#define CLUSTER_RESYNC_WINDOW (32 * RESYNC_WINDOW)
#define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9)

/*
 * When performing a resync, we need to read and compare, so
 * we need as many pages are there are copies.
 * When performing a recovery, we need 2 bios, one for read,
 * one for write (we recover only one drive per r10buf)
 *
 */
static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
{
        struct r10conf *conf = data;
        struct r10bio *r10_bio;
        struct bio *bio;
        int j;
        int nalloc, nalloc_rp;
        struct resync_pages *rps;

        r10_bio = r10bio_pool_alloc(gfp_flags, conf);
        if (!r10_bio)
                return NULL;

        if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery) ||
            test_bit(MD_RECOVERY_RESHAPE, &conf->mddev->recovery))
                nalloc = conf->copies; /* resync */
        else
                nalloc = 2; /* recovery */

        /* allocate once for all bios */
        if (!conf->have_replacement)
                nalloc_rp = nalloc;
        else
                nalloc_rp = nalloc * 2;
        rps = kmalloc_array(nalloc_rp, sizeof(struct resync_pages), gfp_flags);
        if (!rps)
                goto out_free_r10bio;

        /*
         * Allocate bios.
         */
        for (j = nalloc ; j-- ; ) {
                bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
                if (!bio)
                        goto out_free_bio;
                r10_bio->devs[j].bio = bio;
                if (!conf->have_replacement)
                        continue;
                bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
                if (!bio)
                        goto out_free_bio;
                r10_bio->devs[j].repl_bio = bio;
        }
        /*
         * Allocate RESYNC_PAGES data pages and attach them
         * where needed.
         */
        for (j = 0; j < nalloc; j++) {
                struct bio *rbio = r10_bio->devs[j].repl_bio;
                struct resync_pages *rp, *rp_repl;

                rp = &rps[j];
                if (rbio)
                        rp_repl = &rps[nalloc + j];

                bio = r10_bio->devs[j].bio;

                if (!j || test_bit(MD_RECOVERY_SYNC,
                                   &conf->mddev->recovery)) {
                        if (resync_alloc_pages(rp, gfp_flags))
                                goto out_free_pages;
                } else {
                        memcpy(rp, &rps[0], sizeof(*rp));
                        resync_get_all_pages(rp);
                }

                rp->raid_bio = r10_bio;
                bio->bi_private = rp;
                if (rbio) {
                        memcpy(rp_repl, rp, sizeof(*rp));
                        rbio->bi_private = rp_repl;
                }
        }

        return r10_bio;

out_free_pages:
        while (--j >= 0)
                resync_free_pages(&rps[j]);

        j = 0;
out_free_bio:
        for ( ; j < nalloc; j++) {
                if (r10_bio->devs[j].bio)
                        bio_put(r10_bio->devs[j].bio);
                if (r10_bio->devs[j].repl_bio)
                        bio_put(r10_bio->devs[j].repl_bio);
        }
        kfree(rps);
out_free_r10bio:
        rbio_pool_free(r10_bio, conf);
        return NULL;
}

static void r10buf_pool_free(void *__r10_bio, void *data)
{
        struct r10conf *conf = data;
        struct r10bio *r10bio = __r10_bio;
        int j;
        struct resync_pages *rp = NULL;

        for (j = conf->copies; j--; ) {
                struct bio *bio = r10bio->devs[j].bio;

                if (bio) {
                        rp = get_resync_pages(bio);
                        resync_free_pages(rp);
                        bio_put(bio);
                }

                bio = r10bio->devs[j].repl_bio;
                if (bio)
                        bio_put(bio);
        }

        /* resync pages array stored in the 1st bio's .bi_private */
        kfree(rp);

        rbio_pool_free(r10bio, conf);
}

static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio)
{
        int i;

        for (i = 0; i < conf->geo.raid_disks; i++) {
                struct bio **bio = & r10_bio->devs[i].bio;
                if (!BIO_SPECIAL(*bio))
                        bio_put(*bio);
                *bio = NULL;
                bio = &r10_bio->devs[i].repl_bio;
                if (r10_bio->read_slot < 0 && !BIO_SPECIAL(*bio))
                        bio_put(*bio);
                *bio = NULL;
        }
}

static void free_r10bio(struct r10bio *r10_bio)
{
        struct r10conf *conf = r10_bio->mddev->private;

        put_all_bios(conf, r10_bio);
        mempool_free(r10_bio, &conf->r10bio_pool);
}

static void put_buf(struct r10bio *r10_bio)
{
        struct r10conf *conf = r10_bio->mddev->private;

        mempool_free(r10_bio, &conf->r10buf_pool);

        lower_barrier(conf);
}

static void reschedule_retry(struct r10bio *r10_bio)
{
        unsigned long flags;
        struct mddev *mddev = r10_bio->mddev;
        struct r10conf *conf = mddev->private;

        spin_lock_irqsave(&conf->device_lock, flags);
        list_add(&r10_bio->retry_list, &conf->retry_list);
        conf->nr_queued ++;
        spin_unlock_irqrestore(&conf->device_lock, flags);

        /* wake up frozen array... */
        wake_up(&conf->wait_barrier);

        md_wakeup_thread(mddev->thread);
}

/*
 * raid_end_bio_io() is called when we have finished servicing a mirrored
 * operation and are ready to return a success/failure code to the buffer
 * cache layer.
 */
static void raid_end_bio_io(struct r10bio *r10_bio)
{
        struct bio *bio = r10_bio->master_bio;
        struct r10conf *conf = r10_bio->mddev->private;

        if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
                bio->bi_status = BLK_STS_IOERR;

        if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
                bio_end_io_acct(bio, r10_bio->start_time);
        bio_endio(bio);
        /*
         * Wake up any possible resync thread that waits for the device
         * to go idle.
         */
        allow_barrier(conf);

        free_r10bio(r10_bio);
}

/*
 * Update disk head position estimator based on IRQ completion info.
 */
static inline void update_head_pos(int slot, struct r10bio *r10_bio)
{
        struct r10conf *conf = r10_bio->mddev->private;

        conf->mirrors[r10_bio->devs[slot].devnum].head_position =
                r10_bio->devs[slot].addr + (r10_bio->sectors);
}

/*
 * Find the disk number which triggered given bio
 */
static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
                         struct bio *bio, int *slotp, int *replp)
{
        int slot;
        int repl = 0;

        for (slot = 0; slot < conf->geo.raid_disks; slot++) {
                if (r10_bio->devs[slot].bio == bio)
                        break;
                if (r10_bio->devs[slot].repl_bio == bio) {
                        repl = 1;
                        break;
                }
        }

        update_head_pos(slot, r10_bio);

        if (slotp)
                *slotp = slot;
        if (replp)
                *replp = repl;
        return r10_bio->devs[slot].devnum;
}

static void raid10_end_read_request(struct bio *bio)
{
        int uptodate = !bio->bi_status;
        struct r10bio *r10_bio = bio->bi_private;
        int slot;
        struct md_rdev *rdev;
        struct r10conf *conf = r10_bio->mddev->private;

        slot = r10_bio->read_slot;
        rdev = r10_bio->devs[slot].rdev;
        /*
         * this branch is our 'one mirror IO has finished' event handler:
         */
        update_head_pos(slot, r10_bio);

        if (uptodate) {
                /*
                 * Set R10BIO_Uptodate in our master bio, so that
                 * we will return a good error code to the higher
                 * levels even if IO on some other mirrored buffer fails.
                 *
                 * The 'master' represents the composite IO operation to
                 * user-side. So if something waits for IO, then it will
                 * wait for the 'master' bio.
                 */
                set_bit(R10BIO_Uptodate, &r10_bio->state);
        } else {
                /* If all other devices that store this block have
                 * failed, we want to return the error upwards rather
                 * than fail the last device.  Here we redefine
                 * "uptodate" to mean "Don't want to retry"
                 */
                if (!_enough(conf, test_bit(R10BIO_Previous, &r10_bio->state),
                             rdev->raid_disk))
                        uptodate = 1;
        }
        if (uptodate) {
                raid_end_bio_io(r10_bio);
                rdev_dec_pending(rdev, conf->mddev);
        } else {
                /*
                 * oops, read error - keep the refcount on the rdev
                 */
                char b[BDEVNAME_SIZE];
                pr_err_ratelimited("md/raid10:%s: %s: rescheduling sector %llu\n",
                                   mdname(conf->mddev),
                                   bdevname(rdev->bdev, b),
                                   (unsigned long long)r10_bio->sector);
                set_bit(R10BIO_ReadError, &r10_bio->state);
                reschedule_retry(r10_bio);
        }
}

static void close_write(struct r10bio *r10_bio)
{
        /* clear the bitmap if all writes complete successfully */
        md_bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector,
                           r10_bio->sectors,
                           !test_bit(R10BIO_Degraded, &r10_bio->state),
                           0);
        md_write_end(r10_bio->mddev);
}

static void one_write_done(struct r10bio *r10_bio)
{
        if (atomic_dec_and_test(&r10_bio->remaining)) {
                if (test_bit(R10BIO_WriteError, &r10_bio->state))
                        reschedule_retry(r10_bio);
                else {
                        close_write(r10_bio);
                        if (test_bit(R10BIO_MadeGood, &r10_bio->state))
                                reschedule_retry(r10_bio);
                        else
                                raid_end_bio_io(r10_bio);
                }
        }
}

static void raid10_end_write_request(struct bio *bio)
{
        struct r10bio *r10_bio = bio->bi_private;
        int dev;
        int dec_rdev = 1;
        struct r10conf *conf = r10_bio->mddev->private;
        int slot, repl;
        struct md_rdev *rdev = NULL;
        struct bio *to_put = NULL;
        bool discard_error;

        discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;

        dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);

        if (repl)
                rdev = conf->mirrors[dev].replacement;
        if (!rdev) {
                smp_rmb();
                repl = 0;
                rdev = conf->mirrors[dev].rdev;
        }
        /*
         * this branch is our 'one mirror IO has finished' event handler:
         */
        if (bio->bi_status && !discard_error) {
                if (repl)
                        /* Never record new bad blocks to replacement,
                         * just fail it.
                         */
                        md_error(rdev->mddev, rdev);
                else {
                        set_bit(WriteErrorSeen, &rdev->flags);
                        if (!test_and_set_bit(WantReplacement, &rdev->flags))
                                set_bit(MD_RECOVERY_NEEDED,
                                        &rdev->mddev->recovery);

                        dec_rdev = 0;
                        if (test_bit(FailFast, &rdev->flags) &&
                            (bio->bi_opf & MD_FAILFAST)) {
                                md_error(rdev->mddev, rdev);
                        }

                        /*
                         * When the device is faulty, it is not necessary to
                         * handle write error.
                         */
                        if (!test_bit(Faulty, &rdev->flags))
                                set_bit(R10BIO_WriteError, &r10_bio->state);
                        else {
                                /* Fail the request */
                                set_bit(R10BIO_Degraded, &r10_bio->state);
                                r10_bio->devs[slot].bio = NULL;
                                to_put = bio;
                                dec_rdev = 1;
                        }
                }
        } else {
                /*
                 * Set R10BIO_Uptodate in our master bio, so that
                 * we will return a good error code for to the higher
                 * levels even if IO on some other mirrored buffer fails.
                 *
                 * The 'master' represents the composite IO operation to
                 * user-side. So if something waits for IO, then it will
                 * wait for the 'master' bio.
                 */
                sector_t first_bad;
                int bad_sectors;

                /*
                 * Do not set R10BIO_Uptodate if the current device is
                 * rebuilding or Faulty. This is because we cannot use
                 * such device for properly reading the data back (we could
                 * potentially use it, if the current write would have felt
                 * before rdev->recovery_offset, but for simplicity we don't
                 * check this here.
                 */
                if (test_bit(In_sync, &rdev->flags) &&
                    !test_bit(Faulty, &rdev->flags))
                        set_bit(R10BIO_Uptodate, &r10_bio->state);

                /* Maybe we can clear some bad blocks. */
                if (is_badblock(rdev,
                                r10_bio->devs[slot].addr,
                                r10_bio->sectors,
                                &first_bad, &bad_sectors) && !discard_error) {
                        bio_put(bio);
                        if (repl)
                                r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
                        else
                                r10_bio->devs[slot].bio = IO_MADE_GOOD;
                        dec_rdev = 0;
                        set_bit(R10BIO_MadeGood, &r10_bio->state);
                }
        }

        /*
         *
         * Let's see if all mirrored write operations have finished
         * already.
         */
        one_write_done(r10_bio);
        if (dec_rdev)
                rdev_dec_pending(rdev, conf->mddev);
        if (to_put)
                bio_put(to_put);
}

/*
 * RAID10 layout manager
 * As well as the chunksize and raid_disks count, there are two
 * parameters: near_copies and far_copies.
 * near_copies * far_copies must be <= raid_disks.
 * Normally one of these will be 1.
 * If both are 1, we get raid0.
 * If near_copies == raid_disks, we get raid1.
 *
 * Chunks are laid out in raid0 style with near_copies copies of the
 * first chunk, followed by near_copies copies of the next chunk and
 * so on.
 * If far_copies > 1, then after 1/far_copies of the array has been assigned
 * as described above, we start again with a device offset of near_copies.
 * So we effectively have another copy of the whole array further down all
 * the drives, but with blocks on different drives.
 * With this layout, and block is never stored twice on the one device.
 *
 * raid10_find_phys finds the sector offset of a given virtual sector
 * on each device that it is on.
 *
 * raid10_find_virt does the reverse mapping, from a device and a
 * sector offset to a virtual address
 */

static void __raid10_find_phys(struct geom *geo, struct r10bio *r10bio)
{
        int n,f;
        sector_t sector;
        sector_t chunk;
        sector_t stripe;
        int dev;
        int slot = 0;
        int last_far_set_start, last_far_set_size;

        last_far_set_start = (geo->raid_disks / geo->far_set_size) - 1;
        last_far_set_start *= geo->far_set_size;

        last_far_set_size = geo->far_set_size;
        last_far_set_size += (geo->raid_disks % geo->far_set_size);

        /* now calculate first sector/dev */
        chunk = r10bio->sector >> geo->chunk_shift;
        sector = r10bio->sector & geo->chunk_mask;

        chunk *= geo->near_copies;
        stripe = chunk;
        dev = sector_div(stripe, geo->raid_disks);
        if (geo->far_offset)
                stripe *= geo->far_copies;

        sector += stripe << geo->chunk_shift;

        /* and calculate all the others */
        for (n = 0; n < geo->near_copies; n++) {
                int d = dev;
                int set;
                sector_t s = sector;
                r10bio->devs[slot].devnum = d;
                r10bio->devs[slot].addr = s;
                slot++;

                for (f = 1; f < geo->far_copies; f++) {
                        set = d / geo->far_set_size;
                        d += geo->near_copies;

                        if ((geo->raid_disks % geo->far_set_size) &&
                            (d > last_far_set_start)) {
                                d -= last_far_set_start;
                                d %= last_far_set_size;
                                d += last_far_set_start;
                        } else {
                                d %= geo->far_set_size;
                                d += geo->far_set_size * set;
                        }
                        s += geo->stride;
                        r10bio->devs[slot].devnum = d;
                        r10bio->devs[slot].addr = s;
                        slot++;
                }
                dev++;
                if (dev >= geo->raid_disks) {
                        dev = 0;
                        sector += (geo->chunk_mask + 1);
                }
        }
}

static void raid10_find_phys(struct r10conf *conf, struct r10bio *r10bio)
{
        struct geom *geo = &conf->geo;

        if (conf->reshape_progress != MaxSector &&
            ((r10bio->sector >= conf->reshape_progress) !=
             conf->mddev->reshape_backwards)) {
                set_bit(R10BIO_Previous, &r10bio->state);
                geo = &conf->prev;
        } else
                clear_bit(R10BIO_Previous, &r10bio->state);

        __raid10_find_phys(geo, r10bio);
}

static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
{
        sector_t offset, chunk, vchunk;
        /* Never use conf->prev as this is only called during resync
         * or recovery, so reshape isn't happening
         */
        struct geom *geo = &conf->geo;
        int far_set_start = (dev / geo->far_set_size) * geo->far_set_size;
        int far_set_size = geo->far_set_size;
        int last_far_set_start;

        if (geo->raid_disks % geo->far_set_size) {
                last_far_set_start = (geo->raid_disks / geo->far_set_size) - 1;
                last_far_set_start *= geo->far_set_size;

                if (dev >= last_far_set_start) {
                        far_set_size = geo->far_set_size;
                        far_set_size += (geo->raid_disks % geo->far_set_size);
                        far_set_start = last_far_set_start;
                }
        }

        offset = sector & geo->chunk_mask;
        if (geo->far_offset) {
                int fc;
                chunk = sector >> geo->chunk_shift;
                fc = sector_div(chunk, geo->far_copies);
                dev -= fc * geo->near_copies;
                if (dev < far_set_start)
                        dev += far_set_size;
        } else {
                while (sector >= geo->stride) {
                        sector -= geo->stride;
                        if (dev < (geo->near_copies + far_set_start))
                                dev += far_set_size - geo->near_copies;
                        else
                                dev -= geo->near_copies;
                }
                chunk = sector >> geo->chunk_shift;
        }
        vchunk = chunk * geo->raid_disks + dev;
        sector_div(vchunk, geo->near_copies);
        return (vchunk << geo->chunk_shift) + offset;
}

/*
 * This routine returns the disk from which the requested read should
 * be done. There is a per-array 'next expected sequential IO' sector
 * number - if this matches on the next IO then we use the last disk.
 * There is also a per-disk 'last know head position' sector that is
 * maintained from IRQ contexts, both the normal and the resync IO
 * completion handlers update this position correctly. If there is no
 * perfect sequential match then we pick the disk whose head is closest.
 *
 * If there are 2 mirrors in the same 2 devices, performance degrades
 * because position is mirror, not device based.
 *
 * The rdev for the device selected will have nr_pending incremented.
 */

/*
 * FIXME: possibly should rethink readbalancing and do it differently
 * depending on near_copies / far_copies geometry.
 */
static struct md_rdev *read_balance(struct r10conf *conf,
                                    struct r10bio *r10_bio,
                                    int *max_sectors)
{
        const sector_t this_sector = r10_bio->sector;
        int disk, slot;
        int sectors = r10_bio->sectors;
        int best_good_sectors;
        sector_t new_distance, best_dist;
        struct md_rdev *best_dist_rdev, *best_pending_rdev, *rdev = NULL;
        int do_balance;
        int best_dist_slot, best_pending_slot;
        bool has_nonrot_disk = false;
        unsigned int min_pending;
        struct geom *geo = &conf->geo;

        raid10_find_phys(conf, r10_bio);
        rcu_read_lock();
        best_dist_slot = -1;
        min_pending = UINT_MAX;
        best_dist_rdev = NULL;
        best_pending_rdev = NULL;
        best_dist = MaxSector;
        best_good_sectors = 0;
        do_balance = 1;
        clear_bit(R10BIO_FailFast, &r10_bio->state);
        /*
         * Check if we can balance. We can balance on the whole
         * device if no resync is going on (recovery is ok), or below
         * the resync window. We take the first readable disk when
         * above the resync window.
         */
        if ((conf->mddev->recovery_cp < MaxSector
             && (this_sector + sectors >= conf->next_resync)) ||
            (mddev_is_clustered(conf->mddev) &&
             md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
                                            this_sector + sectors)))
                do_balance = 0;

        for (slot = 0; slot < conf->copies ; slot++) {
                sector_t first_bad;
                int bad_sectors;
                sector_t dev_sector;
                unsigned int pending;
                bool nonrot;

                if (r10_bio->devs[slot].bio == IO_BLOCKED)
                        continue;
                disk = r10_bio->devs[slot].devnum;
                rdev = rcu_dereference(conf->mirrors[disk].replacement);
                if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
                    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
                        rdev = rcu_dereference(conf->mirrors[disk].rdev);
                if (rdev == NULL ||
                    test_bit(Faulty, &rdev->flags))
                        continue;
                if (!test_bit(In_sync, &rdev->flags) &&
                    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
                        continue;

                dev_sector = r10_bio->devs[slot].addr;
                if (is_badblock(rdev, dev_sector, sectors,
                                &first_bad, &bad_sectors)) {
                        if (best_dist < MaxSector)
                                /* Already have a better slot */
                                continue;
                        if (first_bad <= dev_sector) {
                                /* Cannot read here.  If this is the
                                 * 'primary' device, then we must not read
                                 * beyond 'bad_sectors' from another device.
                                 */
                                bad_sectors -= (dev_sector - first_bad);
                                if (!do_balance && sectors > bad_sectors)
                                        sectors = bad_sectors;
                                if (best_good_sectors > sectors)
                                        best_good_sectors = sectors;
                        } else {
                                sector_t good_sectors =
                                        first_bad - dev_sector;
                                if (good_sectors > best_good_sectors) {
                                        best_good_sectors = good_sectors;
                                        best_dist_slot = slot;
                                        best_dist_rdev = rdev;
                                }
                                if (!do_balance)
                                        /* Must read from here */
                                        break;
                        }
                        continue;
                } else
                        best_good_sectors = sectors;

                if (!do_balance)
                        break;

                nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev));
                has_nonrot_disk |= nonrot;
                pending = atomic_read(&rdev->nr_pending);
                if (min_pending > pending && nonrot) {
                        min_pending = pending;
                        best_pending_slot = slot;
                        best_pending_rdev = rdev;
                }

                if (best_dist_slot >= 0)
                        /* At least 2 disks to choose from so failfast is OK */
                        set_bit(R10BIO_FailFast, &r10_bio->state);
                /* This optimisation is debatable, and completely destroys
                 * sequential read speed for 'far copies' arrays.  So only
                 * keep it for 'near' arrays, and review those later.
                 */
                if (geo->near_copies > 1 && !pending)
                        new_distance = 0;

                /* for far > 1 always use the lowest address */
                else if (geo->far_copies > 1)
                        new_distance = r10_bio->devs[slot].addr;
                else
                        new_distance = abs(r10_bio->devs[slot].addr -
                                           conf->mirrors[disk].head_position);

                if (new_distance < best_dist) {
                        best_dist = new_distance;
                        best_dist_slot = slot;
                        best_dist_rdev = rdev;
                }
        }
        if (slot >= conf->copies) {
                if (has_nonrot_disk) {
                        slot = best_pending_slot;
                        rdev = best_pending_rdev;
                } else {
                        slot = best_dist_slot;
                        rdev = best_dist_rdev;
                }
        }

        if (slot >= 0) {
                atomic_inc(&rdev->nr_pending);
                r10_bio->read_slot = slot;
        } else
                rdev = NULL;
        rcu_read_unlock();
        *max_sectors = best_good_sectors;

        return rdev;
}

static void flush_pending_writes(struct r10conf *conf)
{
        /* Any writes that have been queued but are awaiting
         * bitmap updates get flushed here.
         */
        spin_lock_irq(&conf->device_lock);

        if (conf->pending_bio_list.head) {
                struct blk_plug plug;
                struct bio *bio;

                bio = bio_list_get(&conf->pending_bio_list);
                conf->pending_count = 0;
                spin_unlock_irq(&conf->device_lock);

                /*
                 * As this is called in a wait_event() loop (see freeze_array),
                 * current->state might be TASK_UNINTERRUPTIBLE which will
                 * cause a warning when we prepare to wait again.  As it is
                 * rare that this path is taken, it is perfectly safe to force
                 * us to go around the wait_event() loop again, so the warning
                 * is a false-positive. Silence the warning by resetting
                 * thread state
                 */
                __set_current_state(TASK_RUNNING);

                blk_start_plug(&plug);
                /* flush any pending bitmap writes to disk
                 * before proceeding w/ I/O */
                md_bitmap_unplug(conf->mddev->bitmap);
                wake_up(&conf->wait_barrier);

                while (bio) { /* submit pending writes */
                        struct bio *next = bio->bi_next;
                        struct md_rdev *rdev = (void*)bio->bi_bdev;
                        bio->bi_next = NULL;
                        bio_set_dev(bio, rdev->bdev);
                        if (test_bit(Faulty, &rdev->flags)) {
                                bio_io_error(bio);
                        } else if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
                                            !blk_queue_discard(bio->bi_bdev->bd_disk->queue)))
                                /* Just ignore it */
                                bio_endio(bio);
                        else
                                submit_bio_noacct(bio);
                        bio = next;
                }
                blk_finish_plug(&plug);
        } else
                spin_unlock_irq(&conf->device_lock);
}

/* Barriers....
 * Sometimes we need to suspend IO while we do something else,
 * either some resync/recovery, or reconfigure the array.
 * To do this we raise a 'barrier'.
 * The 'barrier' is a counter that can be raised multiple times
 * to count how many activities are happening which preclude
 * normal IO.
 * We can only raise the barrier if there is no pending IO.
 * i.e. if nr_pending == 0.
 * We choose only to raise the barrier if no-one is waiting for the
 * barrier to go down.  This means that as soon as an IO request
 * is ready, no other operations which require a barrier will start
 * until the IO request has had a chance.
 *
 * So: regular IO calls 'wait_barrier'.  When that returns there
 *    is no backgroup IO happening,  It must arrange to call
 *    allow_barrier when it has finished its IO.
 * backgroup IO calls must call raise_barrier.  Once that returns
 *    there is no normal IO happeing.  It must arrange to call
 *    lower_barrier when the particular background IO completes.
 */

static void raise_barrier(struct r10conf *conf, int force)
{
        BUG_ON(force && !conf->barrier);
        spin_lock_irq(&conf->resync_lock);

        /* Wait until no block IO is waiting (unless 'force') */
        wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting,
                            conf->resync_lock);

        /* block any new IO from starting */
        conf->barrier++;

        /* Now wait for all pending IO to complete */
        wait_event_lock_irq(conf->wait_barrier,
                            !atomic_read(&conf->nr_pending) && conf->barrier < RESYNC_DEPTH,
                            conf->resync_lock);

        spin_unlock_irq(&conf->resync_lock);
}

static void lower_barrier(struct r10conf *conf)
{
        unsigned long flags;
        spin_lock_irqsave(&conf->resync_lock, flags);
        conf->barrier--;
        spin_unlock_irqrestore(&conf->resync_lock, flags);
        wake_up(&conf->wait_barrier);
}

static void wait_barrier(struct r10conf *conf)
{
        spin_lock_irq(&conf->resync_lock);
        if (conf->barrier) {
                struct bio_list *bio_list = current->bio_list;
                conf->nr_waiting++;
                /* Wait for the barrier to drop.
                 * However if there are already pending
                 * requests (preventing the barrier from
                 * rising completely), and the
                 * pre-process bio queue isn't empty,
                 * then don't wait, as we need to empty
                 * that queue to get the nr_pending
                 * count down.
                 */
                raid10_log(conf->mddev, "wait barrier");
                wait_event_lock_irq(conf->wait_barrier,
                                    !conf->barrier ||
                                    (atomic_read(&conf->nr_pending) &&
                                     bio_list &&
                                     (!bio_list_empty(&bio_list[0]) ||
                                      !bio_list_empty(&bio_list[1]))) ||
                                     /* move on if recovery thread is
                                      * blocked by us
                                      */
                                     (conf->mddev->thread->tsk == current &&
                                      test_bit(MD_RECOVERY_RUNNING,
                                               &conf->mddev->recovery) &&
                                      conf->nr_queued > 0),
                                    conf->resync_lock);
                conf->nr_waiting--;
                if (!conf->nr_waiting)
                        wake_up(&conf->wait_barrier);
        }
        atomic_inc(&conf->nr_pending);
        spin_unlock_irq(&conf->resync_lock);
}

static void allow_barrier(struct r10conf *conf)
{
        if ((atomic_dec_and_test(&conf->nr_pending)) ||
                        (conf->array_freeze_pending))
                wake_up(&conf->wait_barrier);
}

static void freeze_array(struct r10conf *conf, int extra)

{
        /* stop syncio and normal IO and wait for everything to
         * go quiet.
         * We increment barrier and nr_waiting, and then
         * wait until nr_pending match nr_queued+extra
         * This is called in the context of one normal IO request
         * that has failed. Thus any sync request that might be pending
         * will be blocked by nr_pending, and we need to wait for
         * pending IO requests to complete or be queued for re-try.
         * Thus the number queued (nr_queued) plus this request (extra)
         * must match the number of pending IOs (nr_pending) before
         * we continue.
         */
        spin_lock_irq(&conf->resync_lock);
        conf->array_freeze_pending++;
        conf->barrier++;
        conf->nr_waiting++;
        wait_event_lock_irq_cmd(conf->wait_barrier,
                                atomic_read(&conf->nr_pending) == conf->nr_queued+extra,
                                conf->resync_lock,
                                flush_pending_writes(conf));

        conf->array_freeze_pending--;
        spin_unlock_irq(&conf->resync_lock);
}

static void unfreeze_array(struct r10conf *conf)
{
        /* reverse the effect of the freeze */
        spin_lock_irq(&conf->resync_lock);
        conf->barrier--;
        conf->nr_waiting--;
        wake_up(&conf->wait_barrier);
        spin_unlock_irq(&conf->resync_lock);
}

static sector_t choose_data_offset(struct r10bio *r10_bio,
                                   struct md_rdev *rdev)
{
        if (!test_bit(MD_RECOVERY_RESHAPE, &rdev->mddev->recovery) ||
            test_bit(R10BIO_Previous, &r10_bio->state))
                return rdev->data_offset;
        else
                return rdev->new_data_offset;
}

struct raid10_plug_cb {
        struct blk_plug_cb      cb;
        struct bio_list         pending;
        int                     pending_cnt;
};

static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
{
        struct raid10_plug_cb *plug = container_of(cb, struct raid10_plug_cb,
                                                   cb);
        struct mddev *mddev = plug->cb.data;
        struct r10conf *conf = mddev->private;
        struct bio *bio;

        if (from_schedule || current->bio_list) {
                spin_lock_irq(&conf->device_lock);
                bio_list_merge(&conf->pending_bio_list, &plug->pending);
                conf->pending_count += plug->pending_cnt;
                spin_unlock_irq(&conf->device_lock);
                wake_up(&conf->wait_barrier);
                md_wakeup_thread(mddev->thread);
                kfree(plug);
                return;
        }

        /* we aren't scheduling, so we can do the write-out directly. */
        bio = bio_list_get(&plug->pending);
        md_bitmap_unplug(mddev->bitmap);
        wake_up(&conf->wait_barrier);

        while (bio) { /* submit pending writes */
                struct bio *next = bio->bi_next;
                struct md_rdev *rdev = (void*)bio->bi_bdev;
                bio->bi_next = NULL;
                bio_set_dev(bio, rdev->bdev);
                if (test_bit(Faulty, &rdev->flags)) {
                        bio_io_error(bio);
                } else if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
                                    !blk_queue_discard(bio->bi_bdev->bd_disk->queue)))
                        /* Just ignore it */
                        bio_endio(bio);
                else
                        submit_bio_noacct(bio);
                bio = next;
        }
        kfree(plug);
}

/*
 * 1. Register the new request and wait if the reconstruction thread has put
 * up a bar for new requests. Continue immediately if no resync is active
 * currently.
 * 2. If IO spans the reshape position.  Need to wait for reshape to pass.
 */
static void regular_request_wait(struct mddev *mddev, struct r10conf *conf,
                                 struct bio *bio, sector_t sectors)
{
        wait_barrier(conf);
        while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
            bio->bi_iter.bi_sector < conf->reshape_progress &&
            bio->bi_iter.bi_sector + sectors > conf->reshape_progress) {
                raid10_log(conf->mddev, "wait reshape");
                allow_barrier(conf);
                wait_event(conf->wait_barrier,
                           conf->reshape_progress <= bio->bi_iter.bi_sector ||
                           conf->reshape_progress >= bio->bi_iter.bi_sector +
                           sectors);
                wait_barrier(conf);
        }
}

static void raid10_read_request(struct mddev *mddev, struct bio *bio,
                                struct r10bio *r10_bio)
{
        struct r10conf *conf = mddev->private;
        struct bio *read_bio;
        const int op = bio_op(bio);
        const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
        int max_sectors;
        struct md_rdev *rdev;
        char b[BDEVNAME_SIZE];
        int slot = r10_bio->read_slot;
        struct md_rdev *err_rdev = NULL;
        gfp_t gfp = GFP_NOIO;

        if (slot >= 0 && r10_bio->devs[slot].rdev) {
                /*
                 * This is an error retry, but we cannot
                 * safely dereference the rdev in the r10_bio,
                 * we must use the one in conf.
                 * If it has already been disconnected (unlikely)
                 * we lose the device name in error messages.
                 */
                int disk;
                /*
                 * As we are blocking raid10, it is a little safer to
                 * use __GFP_HIGH.
                 */
                gfp = GFP_NOIO | __GFP_HIGH;

                rcu_read_lock();
                disk = r10_bio->devs[slot].devnum;
                err_rdev = rcu_dereference(conf->mirrors[disk].rdev);
                if (err_rdev)
                        bdevname(err_rdev->bdev, b);
                else {
                        strcpy(b, "???");
                        /* This never gets dereferenced */
                        err_rdev = r10_bio->devs[slot].rdev;
                }
                rcu_read_unlock();
        }

        regular_request_wait(mddev, conf, bio, r10_bio->sectors);
        rdev = read_balance(conf, r10_bio, &max_sectors);
        if (!rdev) {
                if (err_rdev) {
                        pr_crit_ratelimited("md/raid10:%s: %s: unrecoverable I/O read error for block %llu\n",
                                            mdname(mddev), b,
                                            (unsigned long long)r10_bio->sector);
                }
                raid_end_bio_io(r10_bio);
                return;
        }
        if (err_rdev)
                pr_err_ratelimited("md/raid10:%s: %s: redirecting sector %llu to another mirror\n",
                                   mdname(mddev),
                                   bdevname(rdev->bdev, b),
                                   (unsigned long long)r10_bio->sector);
        if (max_sectors < bio_sectors(bio)) {
                struct bio *split = bio_split(bio, max_sectors,
                                              gfp, &conf->bio_split);
                bio_chain(split, bio);
                allow_barrier(conf);
                submit_bio_noacct(bio);
                wait_barrier(conf);
                bio = split;
                r10_bio->master_bio = bio;
                r10_bio->sectors = max_sectors;
        }
        slot = r10_bio->read_slot;

        if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
                r10_bio->start_time = bio_start_io_acct(bio);
        read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set);

        r10_bio->devs[slot].bio = read_bio;
        r10_bio->devs[slot].rdev = rdev;

        read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr +
                choose_data_offset(r10_bio, rdev);
        bio_set_dev(read_bio, rdev->bdev);
        read_bio->bi_end_io = raid10_end_read_request;
        bio_set_op_attrs(read_bio, op, do_sync);
        if (test_bit(FailFast, &rdev->flags) &&
            test_bit(R10BIO_FailFast, &r10_bio->state))
                read_bio->bi_opf |= MD_FAILFAST;
        read_bio->bi_private = r10_bio;

        if (mddev->gendisk)
                trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
                                      r10_bio->sector);
        submit_bio_noacct(read_bio);
        return;
}

static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
                                  struct bio *bio, bool replacement,
                                  int n_copy)
{
        const int op = bio_op(bio);
        const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
        const unsigned long do_fua = (bio->bi_opf & REQ_FUA);
        unsigned long flags;
        struct blk_plug_cb *cb;
        struct raid10_plug_cb *plug = NULL;
        struct r10conf *conf = mddev->private;
        struct md_rdev *rdev;
        int devnum = r10_bio->devs[n_copy].devnum;
        struct bio *mbio;

        if (replacement) {
                rdev = conf->mirrors[devnum].replacement;
                if (rdev == NULL) {
                        /* Replacement just got moved to main 'rdev' */
                        smp_mb();
                        rdev = conf->mirrors[devnum].rdev;
                }
        } else
                rdev = conf->mirrors[devnum].rdev;

        mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
        if (replacement)
                r10_bio->devs[n_copy].repl_bio = mbio;
        else
                r10_bio->devs[n_copy].bio = mbio;

        mbio->bi_iter.bi_sector = (r10_bio->devs[n_copy].addr +
                                   choose_data_offset(r10_bio, rdev));
        bio_set_dev(mbio, rdev->bdev);
        mbio->bi_end_io = raid10_end_write_request;
        bio_set_op_attrs(mbio, op, do_sync | do_fua);
        if (!replacement && test_bit(FailFast,
                                     &conf->mirrors[devnum].rdev->flags)
                         && enough(conf, devnum))
                mbio->bi_opf |= MD_FAILFAST;
        mbio->bi_private = r10_bio;

        if (conf->mddev->gendisk)
                trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk),
                                      r10_bio->sector);
        /* flush_pending_writes() needs access to the rdev so...*/
        mbio->bi_bdev = (void *)rdev;

        atomic_inc(&r10_bio->remaining);

        cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug));
        if (cb)
                plug = container_of(cb, struct raid10_plug_cb, cb);
        else
                plug = NULL;
        if (plug) {
                bio_list_add(&plug->pending, mbio);
                plug->pending_cnt++;
        } else {
                spin_lock_irqsave(&conf->device_lock, flags);
                bio_list_add(&conf->pending_bio_list, mbio);
                conf->pending_count++;
                spin_unlock_irqrestore(&conf->device_lock, flags);
                md_wakeup_thread(mddev->thread);
        }
}

static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
{
        int i;
        struct r10conf *conf = mddev->private;
        struct md_rdev *blocked_rdev;

retry_wait:
        blocked_rdev = NULL;
        rcu_read_lock();
        for (i = 0; i < conf->copies; i++) {
                struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
                struct md_rdev *rrdev = rcu_dereference(
                        conf->mirrors[i].replacement);
                if (rdev == rrdev)
                        rrdev = NULL;
                if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
                        atomic_inc(&rdev->nr_pending);
                        blocked_rdev = rdev;
                        break;
                }
                if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) {
                        atomic_inc(&rrdev->nr_pending);
                        blocked_rdev = rrdev;
                        break;
                }

                if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
                        sector_t first_bad;
                        sector_t dev_sector = r10_bio->devs[i].addr;
                        int bad_sectors;
                        int is_bad;

                        /*
                         * Discard request doesn't care the write result
                         * so it doesn't need to wait blocked disk here.
                         */
                        if (!r10_bio->sectors)
                                continue;

                        is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors,
                                             &first_bad, &bad_sectors);
                        if (is_bad < 0) {
                                /*
                                 * Mustn't write here until the bad block
                                 * is acknowledged
                                 */
                                atomic_inc(&rdev->nr_pending);
                                set_bit(BlockedBadBlocks, &rdev->flags);
                                blocked_rdev = rdev;
                                break;
                        }
                }
        }
        rcu_read_unlock();

        if (unlikely(blocked_rdev)) {
                /* Have to wait for this device to get unblocked, then retry */
                allow_barrier(conf);
                raid10_log(conf->mddev, "%s wait rdev %d blocked",
                                __func__, blocked_rdev->raid_disk);
                md_wait_for_blocked_rdev(blocked_rdev, mddev);
                wait_barrier(conf);
                goto retry_wait;
        }
}

static void raid10_write_request(struct mddev *mddev, struct bio *bio,
                                 struct r10bio *r10_bio)
{
        struct r10conf *conf = mddev->private;
        int i;
        sector_t sectors;
        int max_sectors;

        if ((mddev_is_clustered(mddev) &&
             md_cluster_ops->area_resyncing(mddev, WRITE,
                                            bio->bi_iter.bi_sector,
                                            bio_end_sector(bio)))) {
                DEFINE_WAIT(w);
                for (;;) {
                        prepare_to_wait(&conf->wait_barrier,
                                        &w, TASK_IDLE);
                        if (!md_cluster_ops->area_resyncing(mddev, WRITE,
                                 bio->bi_iter.bi_sector, bio_end_sector(bio)))
                                break;
                        schedule();
                }
                finish_wait(&conf->wait_barrier, &w);
        }

        sectors = r10_bio->sectors;
        regular_request_wait(mddev, conf, bio, sectors);
        if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
            (mddev->reshape_backwards
             ? (bio->bi_iter.bi_sector < conf->reshape_safe &&
                bio->bi_iter.bi_sector + sectors > conf->reshape_progress)
             : (bio->bi_iter.bi_sector + sectors > conf->reshape_safe &&
                bio->bi_iter.bi_sector < conf->reshape_progress))) {
                /* Need to update reshape_position in metadata */
                mddev->reshape_position = conf->reshape_progress;
                set_mask_bits(&mddev->sb_flags, 0,
                              BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
                md_wakeup_thread(mddev->thread);
                raid10_log(conf->mddev, "wait reshape metadata");
                wait_event(mddev->sb_wait,
                           !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));

                conf->reshape_safe = mddev->reshape_position;
        }

        if (conf->pending_count >= max_queued_requests) {
                md_wakeup_thread(mddev->thread);
                raid10_log(mddev, "wait queued");
                wait_event(conf->wait_barrier,
                           conf->pending_count < max_queued_requests);
        }
        /* first select target devices under rcu_lock and
         * inc refcount on their rdev.  Record them by setting
         * bios[x] to bio
         * If there are known/acknowledged bad blocks on any device
         * on which we have seen a write error, we want to avoid
         * writing to those blocks.  This potentially requires several
         * writes to write around the bad blocks.  Each set of writes
         * gets its own r10_bio with a set of bios attached.
         */

        r10_bio->read_slot = -1; /* make sure repl_bio gets freed */
        raid10_find_phys(conf, r10_bio);

        wait_blocked_dev(mddev, r10_bio);

        rcu_read_lock();
        max_sectors = r10_bio->sectors;

        for (i = 0;  i < conf->copies; i++) {
                int d = r10_bio->devs[i].devnum;
                struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev);
                struct md_rdev *rrdev = rcu_dereference(
                        conf->mirrors[d].replacement);
                if (rdev == rrdev)
                        rrdev = NULL;
                if (rdev && (test_bit(Faulty, &rdev->flags)))
                        rdev = NULL;
                if (rrdev && (test_bit(Faulty, &rrdev->flags)))
                        rrdev = NULL;

                r10_bio->devs[i].bio = NULL;
                r10_bio->devs[i].repl_bio = NULL;

                if (!rdev && !rrdev) {
                        set_bit(R10BIO_Degraded, &r10_bio->state);
                        continue;
                }
                if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
                        sector_t first_bad;
                        sector_t dev_sector = r10_bio->devs[i].addr;
                        int bad_sectors;
                        int is_bad;

                        is_bad = is_badblock(rdev, dev_sector, max_sectors,
                                             &first_bad, &bad_sectors);
                        if (is_bad && first_bad <= dev_sector) {
                                /* Cannot write here at all */
                                bad_sectors -= (dev_sector - first_bad);
                                if (bad_sectors < max_sectors)
                                        /* Mustn't write more than bad_sectors
                                         * to other devices yet
                                         */
                                        max_sectors = bad_sectors;
                                /* We don't set R10BIO_Degraded as that
                                 * only applies if the disk is missing,
                                 * so it might be re-added, and we want to
                                 * know to recover this chunk.
                                 * In this case the device is here, and the
                                 * fact that this chunk is not in-sync is
                                 * recorded in the bad block log.
                                 */
                                continue;
                        }
                        if (is_bad) {
                                int good_sectors = first_bad - dev_sector;
                                if (good_sectors < max_sectors)
                                        max_sectors = good_sectors;
                        }
                }
                if (rdev) {
                        r10_bio->devs[i].bio = bio;
                        atomic_inc(&rdev->nr_pending);
                }
                if (rrdev) {
                        r10_bio->devs[i].repl_bio = bio;
                        atomic_inc(&rrdev->nr_pending);
                }
        }
        rcu_read_unlock();

        if (max_sectors < r10_bio->sectors)
                r10_bio->sectors = max_sectors;

        if (r10_bio->sectors < bio_sectors(bio)) {
                struct bio *split = bio_split(bio, r10_bio->sectors,
                                              GFP_NOIO, &conf->bio_split);
                bio_chain(split, bio);
                allow_barrier(conf);
                submit_bio_noacct(bio);
                wait_barrier(conf);
                bio = split;
                r10_bio->master_bio = bio;
        }

        if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
                r10_bio->start_time = bio_start_io_acct(bio);
        atomic_set(&r10_bio->remaining, 1);
        md_bitmap_startwrite(mddev->bitmap, r10_bio->sector, r10_bio->sectors, 0);

        for (i = 0; i < conf->copies; i++) {
                if (r10_bio->devs[i].bio)
                        raid10_write_one_disk(mddev, r10_bio, bio, false, i);
                if (r10_bio->devs[i].repl_bio)
                        raid10_write_one_disk(mddev, r10_bio, bio, true, i);
        }
        one_write_done(r10_bio);
}

static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
{
        struct r10conf *conf = mddev->private;
        struct r10bio *r10_bio;

        r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);

        r10_bio->master_bio = bio;
        r10_bio->sectors = sectors;

        r10_bio->mddev = mddev;
        r10_bio->sector = bio->bi_iter.bi_sector;
        r10_bio->state = 0;
        r10_bio->read_slot = -1;
        memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) *
                        conf->geo.raid_disks);

        if (bio_data_dir(bio) == READ)
                raid10_read_request(mddev, bio, r10_bio);
        else
                raid10_write_request(mddev, bio, r10_bio);
}

static void raid_end_discard_bio(struct r10bio *r10bio)
{
        struct r10conf *conf = r10bio->mddev->private;
        struct r10bio *first_r10bio;

        while (atomic_dec_and_test(&r10bio->remaining)) {

                allow_barrier(conf);

                if (!test_bit(R10BIO_Discard, &r10bio->state)) {
                        first_r10bio = (struct r10bio *)r10bio->master_bio;
                        free_r10bio(r10bio);
                        r10bio = first_r10bio;
                } else {
                        md_write_end(r10bio->mddev);
                        bio_endio(r10bio->master_bio);
                        free_r10bio(r10bio);
                        break;
                }
        }
}

static void raid10_end_discard_request(struct bio *bio)
{
        struct r10bio *r10_bio = bio->bi_private;
        struct r10conf *conf = r10_bio->mddev->private;
        struct md_rdev *rdev = NULL;
        int dev;
        int slot, repl;

        /*
         * We don't care the return value of discard bio
         */
        if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
                set_bit(R10BIO_Uptodate, &r10_bio->state);

        dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
        if (repl)
                rdev = conf->mirrors[dev].replacement;
        if (!rdev) {
                /*
                 * raid10_remove_disk uses smp_mb to make sure rdev is set to
                 * replacement before setting replacement to NULL. It can read
                 * rdev first without barrier protect even replacment is NULL
                 */
                smp_rmb();
                rdev = conf->mirrors[dev].rdev;
        }

        raid_end_discard_bio(r10_bio);
        rdev_dec_pending(rdev, conf->mddev);
}

/*
 * There are some limitations to handle discard bio
 * 1st, the discard size is bigger than stripe_size*2.
 * 2st, if the discard bio spans reshape progress, we use the old way to
 * handle discard bio
 */
static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
{
        struct r10conf *conf = mddev->private;
        struct geom *geo = &conf->geo;
        int far_copies = geo->far_copies;
        bool first_copy = true;
        struct r10bio *r10_bio, *first_r10bio;
        struct bio *split;
        int disk;
        sector_t chunk;
        unsigned int stripe_size;
        unsigned int stripe_data_disks;
        sector_t split_size;
        sector_t bio_start, bio_end;
        sector_t first_stripe_index, last_stripe_index;
        sector_t start_disk_offset;
        unsigned int start_disk_index;
        sector_t end_disk_offset;
        unsigned int end_disk_index;
        unsigned int remainder;

        if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
                return -EAGAIN;

        wait_barrier(conf);

        /*
         * Check reshape again to avoid reshape happens after checking
         * MD_RECOVERY_RESHAPE and before wait_barrier
         */
        if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
                goto out;

        if (geo->near_copies)
                stripe_data_disks = geo->raid_disks / geo->near_copies +
                                        geo->raid_disks % geo->near_copies;
        else
                stripe_data_disks = geo->raid_disks;

        stripe_size = stripe_data_disks << geo->chunk_shift;

        bio_start = bio->bi_iter.bi_sector;
        bio_end = bio_end_sector(bio);

        /*
         * Maybe one discard bio is smaller than strip size or across one
         * stripe and discard region is larger than one stripe size. For far
         * offset layout, if the discard region is not aligned with stripe
         * size, there is hole when we submit discard bio to member disk.
         * For simplicity, we only handle discard bio which discard region
         * is bigger than stripe_size * 2
         */
        if (bio_sectors(bio) < stripe_size*2)
                goto out;

        /*
         * Keep bio aligned with strip size.
         */
        div_u64_rem(bio_start, stripe_size, &remainder);
        if (remainder) {
                split_size = stripe_size - remainder;
                split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split);
                bio_chain(split, bio);
                allow_barrier(conf);
                /* Resend the fist split part */
                submit_bio_noacct(split);
                wait_barrier(conf);
        }
        div_u64_rem(bio_end, stripe_size, &remainder);
        if (remainder) {
                split_size = bio_sectors(bio) - remainder;
                split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split);
                bio_chain(split, bio);
                allow_barrier(conf);
                /* Resend the second split part */
                submit_bio_noacct(bio);
                bio = split;
                wait_barrier(conf);
        }

        bio_start = bio->bi_iter.bi_sector;
        bio_end = bio_end_sector(bio);

        /*
         * Raid10 uses chunk as the unit to store data. It's similar like raid0.
         * One stripe contains the chunks from all member disk (one chunk from
         * one disk at the same HBA address). For layout detail, see 'man md 4'
         */
        chunk = bio_start >> geo->chunk_shift;
        chunk *= geo->near_copies;
        first_stripe_index = chunk;
        start_disk_index = sector_div(first_stripe_index, geo->raid_disks);
        if (geo->far_offset)
                first_stripe_index *= geo->far_copies;
        start_disk_offset = (bio_start & geo->chunk_mask) +
                                (first_stripe_index << geo->chunk_shift);

        chunk = bio_end >> geo->chunk_shift;
        chunk *= geo->near_copies;
        last_stripe_index = chunk;
        end_disk_index = sector_div(last_stripe_index, geo->raid_disks);
        if (geo->far_offset)
                last_stripe_index *= geo->far_copies;
        end_disk_offset = (bio_end & geo->chunk_mask) +
                                (last_stripe_index << geo->chunk_shift);

retry_discard:
        r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);
        r10_bio->mddev = mddev;
        r10_bio->state = 0;
        r10_bio->sectors = 0;
        memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * geo->raid_disks);
        wait_blocked_dev(mddev, r10_bio);

        /*
         * For far layout it needs more than one r10bio to cover all regions.
         * Inspired by raid10_sync_request, we can use the first r10bio->master_bio
         * to record the discard bio. Other r10bio->master_bio record the first
         * r10bio. The first r10bio only release after all other r10bios finish.
         * The discard bio returns only first r10bio finishes
         */
        if (first_copy) {
                r10_bio->master_bio = bio;
                set_bit(R10BIO_Discard, &r10_bio->state);
                first_copy = false;
                first_r10bio = r10_bio;
        } else
                r10_bio->master_bio = (struct bio *)first_r10bio;

        /*
         * first select target devices under rcu_lock and
         * inc refcount on their rdev.  Record them by setting
         * bios[x] to bio
         */
        rcu_read_lock();
        for (disk = 0; disk < geo->raid_disks; disk++) {
                struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev);
                struct md_rdev *rrdev = rcu_dereference(
                        conf->mirrors[disk].replacement);

                r10_bio->devs[disk].bio = NULL;
                r10_bio->devs[disk].repl_bio = NULL;

                if (rdev && (test_bit(Faulty, &rdev->flags)))
                        rdev = NULL;
                if (rrdev && (test_bit(Faulty, &rrdev->flags)))
                        rrdev = NULL;
                if (!rdev && !rrdev)
                        continue;

                if (rdev) {
                        r10_bio->devs[disk].bio = bio;
                        atomic_inc(&rdev->nr_pending);
                }
                if (rrdev) {
                        r10_bio->devs[disk].repl_bio = bio;
                        atomic_inc(&rrdev->nr_pending);
                }
        }
        rcu_read_unlock();

        atomic_set(&r10_bio->remaining, 1);
        for (disk = 0; disk < geo->raid_disks; disk++) {
                sector_t dev_start, dev_end;
                struct bio *mbio, *rbio = NULL;

                /*
                 * Now start to calculate the start and end address for each disk.
                 * The space between dev_start and dev_end is the discard region.
                 *
                 * For dev_start, it needs to consider three conditions:
                 * 1st, the disk is before start_disk, you can imagine the disk in
                 * the next stripe. So the dev_start is the start address of next
                 * stripe.
                 * 2st, the disk is after start_disk, it means the disk is at the
                 * same stripe of first disk
                 * 3st, the first disk itself, we can use start_disk_offset directly
                 */
                if (disk < start_disk_index)
                        dev_start = (first_stripe_index + 1) * mddev->chunk_sectors;
                else if (disk > start_disk_index)
                        dev_start = first_stripe_index * mddev->chunk_sectors;
                else
                        dev_start = start_disk_offset;

                if (disk < end_disk_index)
                        dev_end = (last_stripe_index + 1) * mddev->chunk_sectors;
                else if (disk > end_disk_index)
                        dev_end = last_stripe_index * mddev->chunk_sectors;
                else
                        dev_end = end_disk_offset;

                /*
                 * It only handles discard bio which size is >= stripe size, so
                 * dev_end > dev_start all the time.
                 * It doesn't need to use rcu lock to get rdev here. We already
                 * add rdev->nr_pending in the first loop.
                 */
                if (r10_bio->devs[disk].bio) {
                        struct md_rdev *rdev = conf->mirrors[disk].rdev;
                        mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
                        mbio->bi_end_io = raid10_end_discard_request;
                        mbio->bi_private = r10_bio;
                        r10_bio->devs[disk].bio = mbio;
                        r10_bio->devs[disk].devnum = disk;
                        atomic_inc(&r10_bio->remaining);
                        md_submit_discard_bio(mddev, rdev, mbio,
                                        dev_start + choose_data_offset(r10_bio, rdev),
                                        dev_end - dev_start);
                        bio_endio(mbio);
                }
                if (r10_bio->devs[disk].repl_bio) {
                        struct md_rdev *rrdev = conf->mirrors[disk].replacement;
                        rbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
                        rbio->bi_end_io = raid10_end_discard_request;
                        rbio->bi_private = r10_bio;
                        r10_bio->devs[disk].repl_bio = rbio;
                        r10_bio->devs[disk].devnum = disk;
                        atomic_inc(&r10_bio->remaining);
                        md_submit_discard_bio(mddev, rrdev, rbio,
                                        dev_start + choose_data_offset(r10_bio, rrdev),
                                        dev_end - dev_start);
                        bio_endio(rbio);
                }
        }

        if (!geo->far_offset && --far_copies) {
                first_stripe_index += geo->stride >> geo->chunk_shift;
                start_disk_offset += geo->stride;
                last_stripe_index += geo->stride >> geo->chunk_shift;
                end_disk_offset += geo->stride;
                atomic_inc(&first_r10bio->remaining);
                raid_end_discard_bio(r10_bio);
                wait_barrier(conf);
                goto retry_discard;
        }

        raid_end_discard_bio(r10_bio);

        return 0;
out:
        allow_barrier(conf);
        return -EAGAIN;
}

static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
{
        struct r10conf *conf = mddev->private;
        sector_t chunk_mask = (conf->geo.chunk_mask & conf->prev.chunk_mask);
        int chunk_sects = chunk_mask + 1;
        int sectors = bio_sectors(bio);

        if (unlikely(bio->bi_opf & REQ_PREFLUSH)
            && md_flush_request(mddev, bio))
                return true;

        if (!md_write_start(mddev, bio))
                return false;

        if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
                if (!raid10_handle_discard(mddev, bio))
                        return true;

        /*
         * If this request crosses a chunk boundary, we need to split
         * it.
         */
        if (unlikely((bio->bi_iter.bi_sector & chunk_mask) +
                     sectors > chunk_sects
                     && (conf->geo.near_copies < conf->geo.raid_disks
                         || conf->prev.near_copies <
                         conf->prev.raid_disks)))
                sectors = chunk_sects -
                        (bio->bi_iter.bi_sector &
                         (chunk_sects - 1));
        __make_request(mddev, bio, sectors);

        /* In case raid10d snuck in to freeze_array */
        wake_up(&conf->wait_barrier);
        return true;
}

static void raid10_status(struct seq_file *seq, struct mddev *mddev)
{
        struct r10conf *conf = mddev->private;
        int i;

        if (conf->geo.near_copies < conf->geo.raid_disks)
                seq_printf(seq, " %dK chunks", mddev->chunk_sectors / 2);
        if (conf->geo.near_copies > 1)
                seq_printf(seq, " %d near-copies", conf->geo.near_copies);
        if (conf->geo.far_copies > 1) {
                if (conf->geo.far_offset)
                        seq_printf(seq, " %d offset-copies", conf->geo.far_copies);
                else
                        seq_printf(seq, " %d far-copies", conf->geo.far_copies);
                if (conf->geo.far_set_size != conf->geo.raid_disks)
                        seq_printf(seq, " %d devices per set", conf->geo.far_set_size);
        }
        seq_printf(seq, " [%d/%d] [", conf->geo.raid_disks,
                                        conf->geo.raid_disks - mddev->degraded);
        rcu_read_lock();
        for (i = 0; i < conf->geo.raid_disks; i++) {
                struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
                seq_printf(seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
        }
        rcu_read_unlock();
        seq_printf(seq, "]");
}

/* check if there are enough drives for
 * every block to appear on atleast one.
 * Don't consider the device numbered 'ignore'
 * as we might be about to remove it.
 */
static int _enough(struct r10conf *conf, int previous, int ignore)
{
        int first = 0;
        int has_enough = 0;
        int disks, ncopies;
        if (previous) {
                disks = conf->prev.raid_disks;
                ncopies = conf->prev.near_copies;
        } else {
                disks = conf->geo.raid_disks;
                ncopies = conf->geo.near_copies;
        }

        rcu_read_lock();
        do {
                int n = conf->copies;
                int cnt = 0;
                int this = first;
                while (n--) {
                        struct md_rdev *rdev;
                        if (this != ignore &&
                            (rdev = rcu_dereference(conf->mirrors[this].rdev)) &&
                            test_bit(In_sync, &rdev->flags))
                                cnt++;
                        this = (this+1) % disks;
                }
                if (cnt == 0)
                        goto out;
                first = (first + ncopies) % disks;
        } while (first != 0);
        has_enough = 1;
out:
        rcu_read_unlock();
        return has_enough;
}

static int enough(struct r10conf *conf, int ignore)
{
        /* when calling 'enough', both 'prev' and 'geo' must
         * be stable.
         * This is ensured if ->reconfig_mutex or ->device_lock
         * is held.
         */
        return _enough(conf, 0, ignore) &&
                _enough(conf, 1, ignore);
}

static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
{
        char b[BDEVNAME_SIZE];
        struct r10conf *conf = mddev->private;
        unsigned long flags;

        /*
         * If it is not operational, then we have already marked it as dead
         * else if it is the last working disks with "fail_last_dev == false",
         * ignore the error, let the next level up know.
         * else mark the drive as failed
         */
        spin_lock_irqsave(&conf->device_lock, flags);
        if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
            && !enough(conf, rdev->raid_disk)) {
                /*
                 * Don't fail the drive, just return an IO error.
                 */
                spin_unlock_irqrestore(&conf->device_lock, flags);
                return;
        }
        if (test_and_clear_bit(In_sync, &rdev->flags))
                mddev->degraded++;
        /*
         * If recovery is running, make sure it aborts.
         */
        set_bit(MD_RECOVERY_INTR, &mddev->recovery);
        set_bit(Blocked, &rdev->flags);
        set_bit(Faulty, &rdev->flags);
        set_mask_bits(&mddev->sb_flags, 0,
                      BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
        spin_unlock_irqrestore(&conf->device_lock, flags);
        pr_crit("md/raid10:%s: Disk failure on %s, disabling device.\n"
                "md/raid10:%s: Operation continuing on %d devices.\n",
                mdname(mddev), bdevname(rdev->bdev, b),
                mdname(mddev), conf->geo.raid_disks - mddev->degraded);
}

static void print_conf(struct r10conf *conf)
{
        int i;
        struct md_rdev *rdev;

        pr_debug("RAID10 conf printout:\n");
        if (!conf) {
                pr_debug("(!conf)\n");
                return;
        }
        pr_debug(" --- wd:%d rd:%d\n", conf->geo.raid_disks - conf->mddev->degraded,
                 conf->geo.raid_disks);

        /* This is only called with ->reconfix_mutex held, so
         * rcu protection of rdev is not needed */

        for (i = 0; i < conf->geo.raid_disks; i++) {
                char b[BDEVNAME_SIZE];
                rdev = conf->mirrors[i].rdev;
                if (rdev)
                        pr_debug(" disk %d, wo:%d, o:%d, dev:%s\n",
                                 i, !test_bit(In_sync, &rdev->flags),
                                 !test_bit(Faulty, &rdev->flags),
                                 bdevname(rdev->bdev,b));
        }
}

static void close_sync(struct r10conf *conf)
{
        wait_barrier(conf);
        allow_barrier(conf);

        mempool_exit(&conf->r10buf_pool);
}

static int raid10_spare_active(struct mddev *mddev)
{
        int i;
        struct r10conf *conf = mddev->private;
        struct raid10_info *tmp;
        int count = 0;
        unsigned long flags;

        /*
         * Find all non-in_sync disks within the RAID10 configuration
         * and mark them in_sync
         */
        for (i = 0; i < conf->geo.raid_disks; i++) {
                tmp = conf->mirrors + i;
                if (tmp->replacement
                    && tmp->replacement->recovery_offset == MaxSector
                    && !test_bit(Faulty, &tmp->replacement->flags)
                    && !test_and_set_bit(In_sync, &tmp->replacement->flags)) {
                        /* Replacement has just become active */
                        if (!tmp->rdev
                            || !test_and_clear_bit(In_sync, &tmp->rdev->flags))
                                count++;
                        if (tmp->rdev) {
                                /* Replaced device not technically faulty,
                                 * but we need to be sure it gets removed
                                 * and never re-added.
                                 */
                                set_bit(Faulty, &tmp->rdev->flags);
                                sysfs_notify_dirent_safe(
                                        tmp->rdev->sysfs_state);
                        }
                        sysfs_notify_dirent_safe(tmp->replacement->sysfs_state);
                } else if (tmp->rdev
                           && tmp->rdev->recovery_offset == MaxSector
                           && !test_bit(Faulty, &tmp->rdev->flags)
                           && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
                        count++;
                        sysfs_notify_dirent_safe(tmp->rdev->sysfs_state);
                }
        }
        spin_lock_irqsave(&conf->device_lock, flags);
        mddev->degraded -= count;
        spin_unlock_irqrestore(&conf->device_lock, flags);

        print_conf(conf);
        return count;
}

static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
{
        struct r10conf *conf = mddev->private;
        int err = -EEXIST;
        int mirror;
        int first = 0;
        int last = conf->geo.raid_disks - 1;

        if (mddev->recovery_cp < MaxSector)
                /* only hot-add to in-sync arrays, as recovery is
                 * very different from resync
                 */
                return -EBUSY;
        if (rdev->saved_raid_disk < 0 && !_enough(conf, 1, -1))
                return -EINVAL;

        if (md_integrity_add_rdev(rdev, mddev))
                return -ENXIO;

        if (rdev->raid_disk >= 0)
                first = last = rdev->raid_disk;

        if (rdev->saved_raid_disk >= first &&
            rdev->saved_raid_disk < conf->geo.raid_disks &&
            conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
                mirror = rdev->saved_raid_disk;
        else
                mirror = first;
        for ( ; mirror <= last ; mirror++) {
                struct raid10_info *p = &conf->mirrors[mirror];
                if (p->recovery_disabled == mddev->recovery_disabled)
                        continue;
                if (p->rdev) {
                        if (!test_bit(WantReplacement, &p->rdev->flags) ||
                            p->replacement != NULL)
                                continue;
                        clear_bit(In_sync, &rdev->flags);
                        set_bit(Replacement, &rdev->flags);
                        rdev->raid_disk = mirror;
                        err = 0;
                        if (mddev->gendisk)
                                disk_stack_limits(mddev->gendisk, rdev->bdev,
                                                  rdev->data_offset << 9);
                        conf->fullsync = 1;
                        rcu_assign_pointer(p->replacement, rdev);
                        break;
                }

                if (mddev->gendisk)
                        disk_stack_limits(mddev->gendisk, rdev->bdev,
                                          rdev->data_offset << 9);

                p->head_position = 0;
                p->recovery_disabled = mddev->recovery_disabled - 1;
                rdev->raid_disk = mirror;
                err = 0;
                if (rdev->saved_raid_disk != mirror)
                        conf->fullsync = 1;
                rcu_assign_pointer(p->rdev, rdev);
                break;
        }
        if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
                blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue);

        print_conf(conf);
        return err;
}

static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
{
        struct r10conf *conf = mddev->private;
        int err = 0;
        int number = rdev->raid_disk;
        struct md_rdev **rdevp;
        struct raid10_info *p = conf->mirrors + number;

        print_conf(conf);
        if (rdev == p->rdev)
                rdevp = &p->rdev;
        else if (rdev == p->replacement)
                rdevp = &p->replacement;
        else
                return 0;

        if (test_bit(In_sync, &rdev->flags) ||
            atomic_read(&rdev->nr_pending)) {
                err = -EBUSY;
                goto abort;
        }
        /* Only remove non-faulty devices if recovery
         * is not possible.
         */
        if (!test_bit(Faulty, &rdev->flags) &&
            mddev->recovery_disabled != p->recovery_disabled &&
            (!p->replacement || p->replacement == rdev) &&
            number < conf->geo.raid_disks &&
            enough(conf, -1)) {
                err = -EBUSY;
                goto abort;
        }
        *rdevp = NULL;
        if (!test_bit(RemoveSynchronized, &rdev->flags)) {
                synchronize_rcu();
                if (atomic_read(&rdev->nr_pending)) {
                        /* lost the race, try later */
                        err = -EBUSY;
                        *rdevp = rdev;
                        goto abort;
                }
        }
        if (p->replacement) {
                /* We must have just cleared 'rdev' */
                p->rdev = p->replacement;
                clear_bit(Replacement, &p->replacement->flags);
                smp_mb(); /* Make sure other CPUs may see both as identical
                           * but will never see neither -- if they are careful.
                           */
                p->replacement = NULL;
        }

        clear_bit(WantReplacement, &rdev->flags);
        err = md_integrity_register(mddev);

abort:

        print_conf(conf);
        return err;
}

static void __end_sync_read(struct r10bio *r10_bio, struct bio *bio, int d)
{
        struct r10conf *conf = r10_bio->mddev->private;

        if (!bio->bi_status)
                set_bit(R10BIO_Uptodate, &r10_bio->state);
        else
                /* The write handler will notice the lack of
                 * R10BIO_Uptodate and record any errors etc
                 */
                atomic_add(r10_bio->sectors,
                           &conf->mirrors[d].rdev->corrected_errors);

        /* for reconstruct, we always reschedule after a read.
         * for resync, only after all reads
         */
        rdev_dec_pending(conf->mirrors[d].rdev, conf->mddev);
        if (test_bit(R10BIO_IsRecover, &r10_bio->state) ||
            atomic_dec_and_test(&r10_bio->remaining)) {
                /* we have read all the blocks,
                 * do the comparison in process context in raid10d
                 */
                reschedule_retry(r10_bio);
        }
}

static void end_sync_read(struct bio *bio)
{
        struct r10bio *r10_bio = get_resync_r10bio(bio);
        struct r10conf *conf = r10_bio->mddev->private;
        int d = find_bio_disk(conf, r10_bio, bio, NULL, NULL);

        __end_sync_read(r10_bio, bio, d);
}

static void end_reshape_read(struct bio *bio)
{
        /* reshape read bio isn't allocated from r10buf_pool */
        struct r10bio *r10_bio = bio->bi_private;

        __end_sync_read(r10_bio, bio, r10_bio->read_slot);
}

static void end_sync_request(struct r10bio *r10_bio)
{
        struct mddev *mddev = r10_bio->mddev;

        while (atomic_dec_and_test(&r10_bio->remaining)) {
                if (r10_bio->master_bio == NULL) {
                        /* the primary of several recovery bios */
                        sector_t s = r10_bio->sectors;
                        if (test_bit(R10BIO_MadeGood, &r10_bio->state) ||
                            test_bit(R10BIO_WriteError, &r10_bio->state))
                                reschedule_retry(r10_bio);
                        else
                                put_buf(r10_bio);
                        md_done_sync(mddev, s, 1);
                        break;
                } else {
                        struct r10bio *r10_bio2 = (struct r10bio *)r10_bio->master_bio;
                        if (test_bit(R10BIO_MadeGood, &r10_bio->state) ||
                            test_bit(R10BIO_WriteError, &r10_bio->state))
                                reschedule_retry(r10_bio);
                        else
                                put_buf(r10_bio);
                        r10_bio = r10_bio2;
                }
        }
}

static void end_sync_write(struct bio *bio)
{
        struct r10bio *r10_bio = get_resync_r10bio(bio);
        struct mddev *mddev = r10_bio->mddev;
        struct r10conf *conf = mddev->private;
        int d;
        sector_t first_bad;
        int bad_sectors;
        int slot;
        int repl;
        struct md_rdev *rdev = NULL;

        d = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
        if (repl)
                rdev = conf->mirrors[d].replacement;
        else
                rdev = conf->mirrors[d].rdev;

        if (bio->bi_status) {
                if (repl)
                        md_error(mddev, rdev);
                else {
                        set_bit(WriteErrorSeen, &rdev->flags);
                        if (!test_and_set_bit(WantReplacement, &rdev->flags))
                                set_bit(MD_RECOVERY_NEEDED,
                                        &rdev->mddev->recovery);
                        set_bit(R10BIO_WriteError, &r10_bio->state);
                }
        } else if (is_badblock(rdev,
                             r10_bio->devs[slot].addr,
                             r10_bio->sectors,
                             &first_bad, &bad_sectors))
                set_bit(R10BIO_MadeGood, &r10_bio->state);

        rdev_dec_pending(rdev, mddev);

        end_sync_request(r10_bio);
}

/*
 * Note: sync and recover and handled very differently for raid10
 * This code is for resync.
 * For resync, we read through virtual addresses and read all blocks.
 * If there is any error, we schedule a write.  The lowest numbered
 * drive is authoritative.
 * However requests come for physical address, so we need to map.
 * For every physical address there are raid_disks/copies virtual addresses,
 * which is always are least one, but is not necessarly an integer.
 * This means that a physical address can span multiple chunks, so we may
 * have to submit multiple io requests for a single sync request.
 */
/*
 * We check if all blocks are in-sync and only write to blocks that
 * aren't in sync
 */
static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
{
        struct r10conf *conf = mddev->private;
        int i, first;
        struct bio *tbio, *fbio;
        int vcnt;
        struct page **tpages, **fpages;

        atomic_set(&r10_bio->remaining, 1);

        /* find the first device with a block */
        for (i=0; i<conf->copies; i++)
                if (!r10_bio->devs[i].bio->bi_status)
                        break;

        if (i == conf->copies)
                goto done;

        first = i;
        fbio = r10_bio->devs[i].bio;
        fbio->bi_iter.bi_size = r10_bio->sectors << 9;
        fbio->bi_iter.bi_idx = 0;
        fpages = get_resync_pages(fbio)->pages;

        vcnt = (r10_bio->sectors + (PAGE_SIZE >> 9) - 1) >> (PAGE_SHIFT - 9);
        /* now find blocks with errors */
        for (i=0 ; i < conf->copies ; i++) {
                int  j, d;
                struct md_rdev *rdev;
                struct resync_pages *rp;

                tbio = r10_bio->devs[i].bio;

                if (tbio->bi_end_io != end_sync_read)
                        continue;
                if (i == first)
                        continue;

                tpages = get_resync_pages(tbio)->pages;
                d = r10_bio->devs[i].devnum;
                rdev = conf->mirrors[d].rdev;
                if (!r10_bio->devs[i].bio->bi_status) {
                        /* We know that the bi_io_vec layout is the same for
                         * both 'first' and 'i', so we just compare them.
                         * All vec entries are PAGE_SIZE;
                         */
                        int sectors = r10_bio->sectors;
                        for (j = 0; j < vcnt; j++) {
                                int len = PAGE_SIZE;
                                if (sectors < (len / 512))
                                        len = sectors * 512;
                                if (memcmp(page_address(fpages[j]),
                                           page_address(tpages[j]),
                                           len))
                                        break;
                                sectors -= len/512;
                        }
                        if (j == vcnt)
                                continue;
                        atomic64_add(r10_bio->sectors, &mddev->resync_mismatches);
                        if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
                                /* Don't fix anything. */
                                continue;
                } else if (test_bit(FailFast, &rdev->flags)) {
                        /* Just give up on this device */
                        md_error(rdev->mddev, rdev);
                        continue;
                }
                /* Ok, we need to write this bio, either to correct an
                 * inconsistency or to correct an unreadable block.
                 * First we need to fixup bv_offset, bv_len and
                 * bi_vecs, as the read request might have corrupted these
                 */
                rp = get_resync_pages(tbio);
                bio_reset(tbio);

                md_bio_reset_resync_pages(tbio, rp, fbio->bi_iter.bi_size);

                rp->raid_bio = r10_bio;
                tbio->bi_private = rp;
                tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
                tbio->bi_end_io = end_sync_write;
                bio_set_op_attrs(tbio, REQ_OP_WRITE, 0);

                bio_copy_data(tbio, fbio);

                atomic_inc(&conf->mirrors[d].rdev->nr_pending);
                atomic_inc(&r10_bio->remaining);
                md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(tbio));

                if (test_bit(FailFast, &conf->mirrors[d].rdev->flags))
                        tbio->bi_opf |= MD_FAILFAST;
                tbio->bi_iter.bi_sector += conf->mirrors[d].rdev->data_offset;
                bio_set_dev(tbio, conf->mirrors[d].rdev->bdev);
                submit_bio_noacct(tbio);
        }

        /* Now write out to any replacement devices
         * that are active
         */
        for (i = 0; i < conf->copies; i++) {
                int d;

                tbio = r10_bio->devs[i].repl_bio;
                if (!tbio || !tbio->bi_end_io)
                        continue;
                if (r10_bio->devs[i].bio->bi_end_io != end_sync_write
                    && r10_bio->devs[i].bio != fbio)
                        bio_copy_data(tbio, fbio);
                d = r10_bio->devs[i].devnum;
                atomic_inc(&r10_bio->remaining);
                md_sync_acct(conf->mirrors[d].replacement->bdev,
                             bio_sectors(tbio));
                submit_bio_noacct(tbio);
        }

done:
        if (atomic_dec_and_test(&r10_bio->remaining)) {
                md_done_sync(mddev, r10_bio->sectors, 1);
                put_buf(r10_bio);
        }
}

/*
 * Now for the recovery code.
 * Recovery happens across physical sectors.
 * We recover all non-is_sync drives by finding the virtual address of
 * each, and then choose a working drive that also has that virt address.
 * There is a separate r10_bio for each non-in_sync drive.
 * Only the first two slots are in use. The first for reading,
 * The second for writing.
 *
 */
static void fix_recovery_read_error(struct r10bio *r10_bio)
{
        /* We got a read error during recovery.
         * We repeat the read in smaller page-sized sections.
         * If a read succeeds, write it to the new device or record
         * a bad block if we cannot.
         * If a read fails, record a bad block on both old and
         * new devices.
         */
        struct mddev *mddev = r10_bio->mddev;
        struct r10conf *conf = mddev->private;
        struct bio *bio = r10_bio->devs[0].bio;
        sector_t sect = 0;
        int sectors = r10_bio->sectors;
        int idx = 0;
        int dr = r10_bio->devs[0].devnum;
        int dw = r10_bio->devs[1].devnum;
        struct page **pages = get_resync_pages(bio)->pages;

        while (sectors) {
                int s = sectors;
                struct md_rdev *rdev;
                sector_t addr;
                int ok;

                if (s > (PAGE_SIZE>>9))
                        s = PAGE_SIZE >> 9;

                rdev = conf->mirrors[dr].rdev;
                addr = r10_bio->devs[0].addr + sect,
                ok = sync_page_io(rdev,
                                  addr,
                                  s << 9,
                                  pages[idx],
                                  REQ_OP_READ, 0, false);
                if (ok) {
                        rdev = conf->mirrors[dw].rdev;
                        addr = r10_bio->devs[1].addr + sect;
                        ok = sync_page_io(rdev,
                                          addr,
                                          s << 9,
                                          pages[idx],
                                          REQ_OP_WRITE, 0, false);
                        if (!ok) {
                                set_bit(WriteErrorSeen, &rdev->flags);
                                if (!test_and_set_bit(WantReplacement,
                                                      &rdev->flags))
                                        set_bit(MD_RECOVERY_NEEDED,
                                                &rdev->mddev->recovery);
                        }
                }
                if (!ok) {
                        /* We don't worry if we cannot set a bad block -
                         * it really is bad so there is no loss in not
                         * recording it yet
                         */
                        rdev_set_badblocks(rdev, addr, s, 0);

                        if (rdev != conf->mirrors[dw].rdev) {
                                /* need bad block on destination too */
                                struct md_rdev *rdev2 = conf->mirrors[dw].rdev;
                                addr = r10_bio->devs[1].addr + sect;
                                ok = rdev_set_badblocks(rdev2, addr, s, 0);
                                if (!ok) {
                                        /* just abort the recovery */
                                        pr_notice("md/raid10:%s: recovery aborted due to read error\n",
                                                  mdname(mddev));

                                        conf->mirrors[dw].recovery_disabled
                                                = mddev->recovery_disabled;
                                        set_bit(MD_RECOVERY_INTR,
                                                &mddev->recovery);
                                        break;
                                }
                        }
                }

                sectors -= s;
                sect += s;
                idx++;
        }
}

static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
{
        struct r10conf *conf = mddev->private;
        int d;
        struct bio *wbio, *wbio2;

        if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) {
                fix_recovery_read_error(r10_bio);
                end_sync_request(r10_bio);
                return;
        }

        /*
         * share the pages with the first bio
         * and submit the write request
         */
        d = r10_bio->devs[1].devnum;
        wbio = r10_bio->devs[1].bio;
        wbio2 = r10_bio->devs[1].repl_bio;
        /* Need to test wbio2->bi_end_io before we call
         * submit_bio_noacct as if the former is NULL,
         * the latter is free to free wbio2.
         */
        if (wbio2 && !wbio2->bi_end_io)
                wbio2 = NULL;
        if (wbio->bi_end_io) {
                atomic_inc(&conf->mirrors[d].rdev->nr_pending);
                md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
                submit_bio_noacct(wbio);
        }
        if (wbio2) {
                atomic_inc(&conf->mirrors[d].replacement->nr_pending);
                md_sync_acct(conf->mirrors[d].replacement->bdev,
                             bio_sectors(wbio2));
                submit_bio_noacct(wbio2);
        }
}

/*
 * Used by fix_read_error() to decay the per rdev read_errors.
 * We halve the read error count for every hour that has elapsed
 * since the last recorded read error.
 *
 */
static void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev)
{
        long cur_time_mon;
        unsigned long hours_since_last;
        unsigned int read_errors = atomic_read(&rdev->read_errors);

        cur_time_mon = ktime_get_seconds();

        if (rdev->last_read_error == 0) {
                /* first time we've seen a read error */
                rdev->last_read_error = cur_time_mon;
                return;
        }

        hours_since_last = (long)(cur_time_mon -
                            rdev->last_read_error) / 3600;

        rdev->last_read_error = cur_time_mon;

        /*
         * if hours_since_last is > the number of bits in read_errors
         * just set read errors to 0. We do this to avoid
         * overflowing the shift of read_errors by hours_since_last.
         */
        if (hours_since_last >= 8 * sizeof(read_errors))
                atomic_set(&rdev->read_errors, 0);
        else
                atomic_set(&rdev->read_errors, read_errors >> hours_since_last);
}

static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector,
                            int sectors, struct page *page, int rw)
{
        sector_t first_bad;
        int bad_sectors;

        if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors)
            && (rw == READ || test_bit(WriteErrorSeen, &rdev->flags)))
                return -1;
        if (sync_page_io(rdev, sector, sectors << 9, page, rw, 0, false))
                /* success */
                return 1;
        if (rw == WRITE) {
                set_bit(WriteErrorSeen, &rdev->flags);
                if (!test_and_set_bit(WantReplacement, &rdev->flags))
                        set_bit(MD_RECOVERY_NEEDED,
                                &rdev->mddev->recovery);
        }
        /* need to record an error - either for the block or the device */
        if (!rdev_set_badblocks(rdev, sector, sectors, 0))
                md_error(rdev->mddev, rdev);
        return 0;
}

/*
 * This is a kernel thread which:
 *
 *      1.      Retries failed read operations on working mirrors.
 *      2.      Updates the raid superblock when problems encounter.
 *      3.      Performs writes following reads for array synchronising.
 */

static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10bio *r10_bio)
{
        int sect = 0; /* Offset from r10_bio->sector */
        int sectors = r10_bio->sectors;
        struct md_rdev *rdev;
        int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
        int d = r10_bio->devs[r10_bio->read_slot].devnum;

        /* still own a reference to this rdev, so it cannot
         * have been cleared recently.
         */
        rdev = conf->mirrors[d].rdev;

        if (test_bit(Faulty, &rdev->flags))
                /* drive has already been failed, just ignore any
                   more fix_read_error() attempts */
                return;

        check_decay_read_errors(mddev, rdev);
        atomic_inc(&rdev->read_errors);
        if (atomic_read(&rdev->read_errors) > max_read_errors) {
                char b[BDEVNAME_SIZE];
                bdevname(rdev->bdev, b);

                pr_notice("md/raid10:%s: %s: Raid device exceeded read_error threshold [cur %d:max %d]\n",
                          mdname(mddev), b,
                          atomic_read(&rdev->read_errors), max_read_errors);
                pr_notice("md/raid10:%s: %s: Failing raid device\n",
                          mdname(mddev), b);
                md_error(mddev, rdev);
                r10_bio->devs[r10_bio->read_slot].bio = IO_BLOCKED;
                return;
        }

        while(sectors) {
                int s = sectors;
                int sl = r10_bio->read_slot;
                int success = 0;
                int start;

                if (s > (PAGE_SIZE>>9))
                        s = PAGE_SIZE >> 9;

                rcu_read_lock();
                do {
                        sector_t first_bad;
                        int bad_sectors;

                        d = r10_bio->devs[sl].devnum;
                        rdev = rcu_dereference(conf->mirrors[d].rdev);
                        if (rdev &&
                            test_bit(In_sync, &rdev->flags) &&
                            !test_bit(Faulty, &rdev->flags) &&
                            is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
                                        &first_bad, &bad_sectors) == 0) {
                                atomic_inc(&rdev->nr_pending);
                                rcu_read_unlock();
                                success = sync_page_io(rdev,
                                                       r10_bio->devs[sl].addr +
                                                       sect,
                                                       s<<9,
                                                       conf->tmppage,
                                                       REQ_OP_READ, 0, false);
                                rdev_dec_pending(rdev, mddev);
                                rcu_read_lock();
                                if (success)
                                        break;
                        }
                        sl++;
                        if (sl == conf->copies)
                                sl = 0;
                } while (!success && sl != r10_bio->read_slot);
                rcu_read_unlock();

                if (!success) {
                        /* Cannot read from anywhere, just mark the block
                         * as bad on the first device to discourage future
                         * reads.
                         */
                        int dn = r10_bio->devs[r10_bio->read_slot].devnum;
                        rdev = conf->mirrors[dn].rdev;

                        if (!rdev_set_badblocks(
                                    rdev,
                                    r10_bio->devs[r10_bio->read_slot].addr
                                    + sect,
                                    s, 0)) {
                                md_error(mddev, rdev);
                                r10_bio->devs[r10_bio->read_slot].bio
                                        = IO_BLOCKED;
                        }
                        break;
                }

                start = sl;
                /* write it back and re-read */
                rcu_read_lock();
                while (sl != r10_bio->read_slot) {
                        char b[BDEVNAME_SIZE];

                        if (sl==0)
                                sl = conf->copies;
                        sl--;
                        d = r10_bio->devs[sl].devnum;
                        rdev = rcu_dereference(conf->mirrors[d].rdev);
                        if (!rdev ||
                            test_bit(Faulty, &rdev->flags) ||
                            !test_bit(In_sync, &rdev->flags))
                                continue;

                        atomic_inc(&rdev->nr_pending);
                        rcu_read_unlock();
                        if (r10_sync_page_io(rdev,
                                             r10_bio->devs[sl].addr +
                                             sect,
                                             s, conf->tmppage, WRITE)
                            == 0) {
                                /* Well, this device is dead */
                                pr_notice("md/raid10:%s: read correction write failed (%d sectors at %llu on %s)\n",
                                          mdname(mddev), s,
                                          (unsigned long long)(
                                                  sect +
                                                  choose_data_offset(r10_bio,
                                                                     rdev)),
                                          bdevname(rdev->bdev, b));
                                pr_notice("md/raid10:%s: %s: failing drive\n",
                                          mdname(mddev),
                                          bdevname(rdev->bdev, b));
                        }
                        rdev_dec_pending(rdev, mddev);
                        rcu_read_lock();
                }
                sl = start;
                while (sl != r10_bio->read_slot) {
                        char b[BDEVNAME_SIZE];

                        if (sl==0)
                                sl = conf->copies;
                        sl--;
                        d = r10_bio->devs[sl].devnum;
                        rdev = rcu_dereference(conf->mirrors[d].rdev);
                        if (!rdev ||
                            test_bit(Faulty, &rdev->flags) ||
                            !test_bit(In_sync, &rdev->flags))
                                continue;

                        atomic_inc(&rdev->nr_pending);
                        rcu_read_unlock();
                        switch (r10_sync_page_io(rdev,
                                             r10_bio->devs[sl].addr +
                                             sect,
                                             s, conf->tmppage,
                                                 READ)) {
                        case 0:
                                /* Well, this device is dead */
                                pr_notice("md/raid10:%s: unable to read back corrected sectors (%d sectors at %llu on %s)\n",
                                       mdname(mddev), s,
                                       (unsigned long long)(
                                               sect +
                                               choose_data_offset(r10_bio, rdev)),
                                       bdevname(rdev->bdev, b));
                                pr_notice("md/raid10:%s: %s: failing drive\n",
                                       mdname(mddev),
                                       bdevname(rdev->bdev, b));
                                break;
                        case 1:
                                pr_info("md/raid10:%s: read error corrected (%d sectors at %llu on %s)\n",
                                       mdname(mddev), s,
                                       (unsigned long long)(
                                               sect +
                                               choose_data_offset(r10_bio, rdev)),
                                       bdevname(rdev->bdev, b));
                                atomic_add(s, &rdev->corrected_errors);
                        }

                        rdev_dec_pending(rdev, mddev);
                        rcu_read_lock();
                }
                rcu_read_unlock();

                sectors -= s;
                sect += s;
        }
}

static int narrow_write_error(struct r10bio *r10_bio, int i)
{
        struct bio *bio = r10_bio->master_bio;
        struct mddev *mddev = r10_bio->mddev;
        struct r10conf *conf = mddev->private;
        struct md_rdev *rdev = conf->mirrors[r10_bio->devs[i].devnum].rdev;
        /* bio has the data to be written to slot 'i' where
         * we just recently had a write error.
         * We repeatedly clone the bio and trim down to one block,
         * then try the write.  Where the write fails we record
         * a bad block.
         * It is conceivable that the bio doesn't exactly align with
         * blocks.  We must handle this.
         *
         * We currently own a reference to the rdev.
         */

        int block_sectors;
        sector_t sector;
        int sectors;
        int sect_to_write = r10_bio->sectors;
        int ok = 1;

        if (rdev->badblocks.shift < 0)
                return 0;

        block_sectors = roundup(1 << rdev->badblocks.shift,
                                bdev_logical_block_size(rdev->bdev) >> 9);
        sector = r10_bio->sector;
        sectors = ((r10_bio->sector + block_sectors)
                   & ~(sector_t)(block_sectors - 1))
                - sector;

        while (sect_to_write) {
                struct bio *wbio;
                sector_t wsector;
                if (sectors > sect_to_write)
                        sectors = sect_to_write;
                /* Write at 'sector' for 'sectors' */
                wbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
                bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors);
                wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector);
                wbio->bi_iter.bi_sector = wsector +
                                   choose_data_offset(r10_bio, rdev);
                bio_set_dev(wbio, rdev->bdev);
                bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);

                if (submit_bio_wait(wbio) < 0)
                        /* Failure! */
                        ok = rdev_set_badblocks(rdev, wsector,
                                                sectors, 0)
                                && ok;

                bio_put(wbio);
                sect_to_write -= sectors;
                sector += sectors;
                sectors = block_sectors;
        }
        return ok;
}

static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
{
        int slot = r10_bio->read_slot;
        struct bio *bio;
        struct r10conf *conf = mddev->private;
        struct md_rdev *rdev = r10_bio->devs[slot].rdev;

        /* we got a read error. Maybe the drive is bad.  Maybe just
         * the block and we can fix it.
         * We freeze all other IO, and try reading the block from
         * other devices.  When we find one, we re-write
         * and check it that fixes the read error.
         * This is all done synchronously while the array is
         * frozen.
         */
        bio = r10_bio->devs[slot].bio;
        bio_put(bio);
        r10_bio->devs[slot].bio = NULL;

        if (mddev->ro)
                r10_bio->devs[slot].bio = IO_BLOCKED;
        else if (!test_bit(FailFast, &rdev->flags)) {
                freeze_array(conf, 1);
                fix_read_error(conf, mddev, r10_bio);
                unfreeze_array(conf);
        } else
                md_error(mddev, rdev);

        rdev_dec_pending(rdev, mddev);
        allow_barrier(conf);
        r10_bio->state = 0;
        raid10_read_request(mddev, r10_bio->master_bio, r10_bio);
}

static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
{
        /* Some sort of write request has finished and it
         * succeeded in writing where we thought there was a
         * bad block.  So forget the bad block.
         * Or possibly if failed and we need to record
         * a bad block.
         */
        int m;
        struct md_rdev *rdev;

        if (test_bit(R10BIO_IsSync, &r10_bio->state) ||
            test_bit(R10BIO_IsRecover, &r10_bio->state)) {
                for (m = 0; m < conf->copies; m++) {
                        int dev = r10_bio->devs[m].devnum;
                        rdev = conf->mirrors[dev].rdev;
                        if (r10_bio->devs[m].bio == NULL ||
                                r10_bio->devs[m].bio->bi_end_io == NULL)
                                continue;
                        if (!r10_bio->devs[m].bio->bi_status) {
                                rdev_clear_badblocks(
                                        rdev,
                                        r10_bio->devs[m].addr,
                                        r10_bio->sectors, 0);
                        } else {
                                if (!rdev_set_badblocks(
                                            rdev,
                                            r10_bio->devs[m].addr,
                                            r10_bio->sectors, 0))
                                        md_error(conf->mddev, rdev);
                        }
                        rdev = conf->mirrors[dev].replacement;
                        if (r10_bio->devs[m].repl_bio == NULL ||
                                r10_bio->devs[m].repl_bio->bi_end_io == NULL)
                                continue;

                        if (!r10_bio->devs[m].repl_bio->bi_status) {
                                rdev_clear_badblocks(
                                        rdev,
                                        r10_bio->devs[m].addr,
                                        r10_bio->sectors, 0);
                        } else {
                                if (!rdev_set_badblocks(
                                            rdev,
                                            r10_bio->devs[m].addr,
                                            r10_bio->sectors, 0))
                                        md_error(conf->mddev, rdev);
                        }
                }
                put_buf(r10_bio);
        } else {
                bool fail = false;
                for (m = 0; m < conf->copies; m++) {
                        int dev = r10_bio->devs[m].devnum;
                        struct bio *bio = r10_bio->devs[m].bio;
                        rdev = conf->mirrors[dev].rdev;
                        if (bio == IO_MADE_GOOD) {
                                rdev_clear_badblocks(
                                        rdev,
                                        r10_bio->devs[m].addr,
                                        r10_bio->sectors, 0);
                                rdev_dec_pending(rdev, conf->mddev);
                        } else if (bio != NULL && bio->bi_status) {
                                fail = true;
                                if (!narrow_write_error(r10_bio, m)) {
                                        md_error(conf->mddev, rdev);
                                        set_bit(R10BIO_Degraded,
                                                &r10_bio->state);
                                }
                                rdev_dec_pending(rdev, conf->mddev);
                        }
                        bio = r10_bio->devs[m].repl_bio;
                        rdev = conf->mirrors[dev].replacement;
                        if (rdev && bio == IO_MADE_GOOD) {
                                rdev_clear_badblocks(
                                        rdev,
                                        r10_bio->devs[m].addr,