-> sequential reads
   best_disk = disk;
   if (...)
    choose_next_idle = 1
    continue;

 for_each_rdev
 -> iterate next rdev
  if (pending == 0)
   best_disk = disk;
   -> choose the next idle disk
   break;

  if (choose_next_idle)
   -> keep using this rdev if there are no other idle disk
   continue

However, commit 2e52d449bcec ("md/raid1: add failfast handling for reads.")
remove the code:

-               /* If device is idle, use it */
-               if (pending == 0) {
-                       best_disk = disk;
-                       break;
-               }

Hence choose next idle will never work now, fix this problem by
following:

1) don't set best_disk in this case, read_balance() will choose the best
   disk after iterating all the disks;
2) add 'pending' so that other idle disk will be chosen;
3) set 'dist' to 0 so that if there is no other idle disk, and all disks
   are rotational, this disk will still be chosen;

Fixes: 2e52d449bcec ("md/raid1: add failfast handling for reads.")
Co-developed-by: Paul Luse <redacted>
Signed-off-by: Paul Luse <redacted>
Signed-off-by: Yu Kuai <redacted>
---
 drivers/md/raid1.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index c60ea58ae8c5..d0bc67e6d068 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c

@@ -604,7 +604,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
        unsigned int min_pending;
        struct md_rdev *rdev;
        int choose_first;
-       int choose_next_idle;

        /*
         * Check if we can balance. We can balance on the whole

@@ -619,7 +618,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
        best_pending_disk = -1;
        min_pending = UINT_MAX;
        best_good_sectors = 0;
-       choose_next_idle = 0;
        clear_bit(R1BIO_FailFast, &r1_bio->state);

        if ((conf->mddev->recovery_cp < this_sector + sectors) ||

@@ -712,7 +710,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
                        int opt_iosize = bdev_io_opt(rdev->bdev) >> 9;
                        struct raid1_info *mirror = &conf->mirrors[disk];

-                       best_disk = disk;
                        /*
                         * If buffered sequential IO size exceeds optimal
                         * iosize, check if there is idle disk. If yes, choose

@@ -731,15 +728,21 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
                            mirror->next_seq_sect > opt_iosize &&
                            mirror->next_seq_sect - opt_iosize >=
                            mirror->seq_start) {
-                               choose_next_idle = 1;
-                               continue;
+                               /*
+                                * Add 'pending' to avoid choosing this disk if
+                                * there is other idle disk.
+                                * Set 'dist' to 0, so that if there is no other
+                                * idle disk and all disks are rotational, this
+                                * disk will still be chosen.
+                                */
+                               pending++;
+                               dist = 0;