btrfs: fix async discard stall

Might happen that bg->discard_eligible_time was changed without
rescheduling, so btrfs_discard_workfn() wakes up earlier than that new
time, peek_discard_list() returns NULL, and all work halts and goes to
sleep without further rescheduling even there are block groups to
discard.

It happens pretty often, but not so visible from the userspace because
after some time it usually will be kicked off anyway by someone else
calling btrfs_discard_reschedule_work().

Fix it by continue rescheduling if block group discard lists are not
empty.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 1db966bf85b244fcf96cb67153053d62b149ca4c..36431d7e1334cb3a04d9d26e9ec7c6dc63775ada 100644 (file)
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -199,16 +199,15 @@ static struct btrfs_block_group *find_next_block_group(
 static struct btrfs_block_group *peek_discard_list(
                                        struct btrfs_discard_ctl *discard_ctl,
                                        enum btrfs_discard_state *discard_state,
-                                       int *discard_index)
+                                       int *discard_index, u64 now)
 {
        struct btrfs_block_group *block_group;
-       const u64 now = ktime_get_ns();
 
        spin_lock(&discard_ctl->lock);
 again:
        block_group = find_next_block_group(discard_ctl, now);
 
-       if (block_group && now > block_group->discard_eligible_time) {
+       if (block_group && now >= block_group->discard_eligible_time) {
                if (block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED &&
                    block_group->used != 0) {
                        if (btrfs_is_block_group_data_only(block_group))
@@ -222,12 +221,11 @@ again:
                        block_group->discard_state = BTRFS_DISCARD_EXTENTS;
                }
                discard_ctl->block_group = block_group;
+       }
+       if (block_group) {
                *discard_state = block_group->discard_state;
                *discard_index = block_group->discard_index;
-       } else {
-               block_group = NULL;
        }
-
        spin_unlock(&discard_ctl->lock);
 
        return block_group;
@@ -438,13 +436,18 @@ static void btrfs_discard_workfn(struct work_struct *work)
        int discard_index = 0;
        u64 trimmed = 0;
        u64 minlen = 0;
+       u64 now = ktime_get_ns();
 
        discard_ctl = container_of(work, struct btrfs_discard_ctl, work.work);
 
        block_group = peek_discard_list(discard_ctl, &discard_state,
-                                       &discard_index);
+                                       &discard_index, now);
        if (!block_group || !btrfs_run_discard_work(discard_ctl))
                return;
+       if (now < block_group->discard_eligible_time) {
+               btrfs_discard_schedule_work(discard_ctl, false);
+               return;
+       }
 
        /* Perform discarding */
        minlen = discard_minlen[discard_index];