lightnvm: pblk: simplify work_queue mempool

In pblk, we have a mempool to allocate a generic structure that we
pass along workqueues. This is heavily used in the GC path in order
to have enough inflight reads and fully utilize the GC bandwidth.

However, the current GC path copies data to the host memory and puts it
back into the write buffer. This requires a vmalloc allocation for the
data and a memory copy. Thus, guaranteeing the allocation by using a
mempool for the structure in itself does not give us much. Until we
implement support for vector copy to avoid moving data through the host,
just allocate the workqueue structure using kmalloc.

This allows us to have a much smaller mempool.

Reported-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 2 insertions, 2 deletions

diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index d82ca8bd8390..c73b17bca06b 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -198,8 +198,8 @@ static void pblk_end_io_write_meta(struct nvm_rq *rqd)
 
         sync = atomic_add_return(rqd->nr_ppas, &emeta->sync);
         if (sync == emeta->nr_entries)
-                pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws,
-                                                                pblk->close_wq);
+                pblk_gen_run_ws(pblk, line, NULL, pblk_line_close_ws,
+                                                GFP_ATOMIC, pblk->close_wq);
 
         bio_put(rqd->bio);
         nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);