d/freebsd-skq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

nvme(4): Add bus_dmamap_sync() at the end of the request path

Browse Source 
Summary:
Some architectures, in this case powerpc64, need explicit synchronization
barriers vs device accesses.

Prior to this change, when running 'make buildworld -j72' on a 18-core
(72-thread) POWER9, I would see controller resets often.  With this change, I
don't see these resets messages, though another tester still does, for yet to be
determined reasons, so this may not be a complete fix.  Additionally, I see a
~5-10% speed up in buildworld times, likely due to not needing to reset the
controller.

Reviewed By: jimharris
Differential Revision: https://reviews.freebsd.org/D16570
This commit is contained in:
Justin Hibbits 2018-08-03 20:04:06 +00:00
parent bc0d7285f9
commit 2e0090af65
1 changed files with 18 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
sys/dev/nvme/nvme_qpair.c
View File

@ -401,9 +401,13 @@ nvme_qpair_complete_tracker(struct nvme_qpair *qpair, struct nvme_tracker *tr,
req->retries++;
nvme_qpair_submit_tracker(qpair, tr);
} else {
if (req->type != NVME_REQUEST_NULL)
if (req->type != NVME_REQUEST_NULL) {
bus_dmamap_sync(qpair->dma_tag_payload,
tr->payload_dma_map,
BUS_DMASYNC_POSTREAD | BUS_DMASYNC_POSTWRITE);
bus_dmamap_unload(qpair->dma_tag_payload,
tr->payload_dma_map);
}
nvme_free_request(req);
tr->req = NULL;
@ -487,6 +491,8 @@ nvme_qpair_process_completions(struct nvme_qpair *qpair)
*/
return (false);
bus_dmamap_sync(qpair->dma_tag, qpair->queuemem_map,
BUS_DMASYNC_POSTREAD | BUS_DMASYNC_POSTWRITE);
while (1) {
cpl = qpair->cpl[qpair->cq_head];
@ -828,7 +834,16 @@ nvme_qpair_submit_tracker(struct nvme_qpair *qpair, struct nvme_tracker *tr)
if (++qpair->sq_tail == qpair->num_entries)
qpair->sq_tail = 0;
bus_dmamap_sync(qpair->dma_tag, qpair->queuemem_map,
BUS_DMASYNC_PREREAD | BUS_DMASYNC_PREWRITE);
#ifndef __powerpc__
/*
* powerpc's bus_dmamap_sync() already includes a heavyweight sync, but
* no other archs do.
*/
wmb();
#endif
nvme_mmio_write_4(qpair->ctrlr, doorbell[qpair->id].sq_tdbl,
qpair->sq_tail);
@ -879,6 +894,8 @@ nvme_payload_map(void *arg, bus_dma_segment_t *seg, int nseg, int error)
tr->req->cmd.prp2 = 0;
}
bus_dmamap_sync(tr->qpair->dma_tag_payload, tr->payload_dma_map,
BUS_DMASYNC_PREREAD | BUS_DMASYNC_PREWRITE);
nvme_qpair_submit_tracker(tr->qpair, tr);
}