[ Upstream commit f972775b1cc0441ae22c9f8d06dd16b118463632 ]
Once an SDMA engine is taken down due to a link failure, any waiting QPs that do not have outstanding descriptors in the ring will stay on the dmawait list as long as the port is down.
Since there is no timer running, they will stay there for a long time.
The fix is to wake up all iowaits linked to dmawait. The send engine will build and post packets that get flushed back.
Fixes: 7724105686e7 ("IB/hfi1: add driver files") Reviewed-by: Kaike Wan kaike.wan@intel.com Signed-off-by: Mike Marciniszyn mike.marciniszyn@intel.com Signed-off-by: Dennis Dalessandro dennis.dalessandro@intel.com Signed-off-by: Doug Ledford dledford@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/hfi1/sdma.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 70828de7436b..28b66bd70b74 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -405,6 +405,7 @@ static void sdma_flush(struct sdma_engine *sde) struct sdma_txreq *txp, *txp_next; LIST_HEAD(flushlist); unsigned long flags; + uint seq;
/* flush from head to tail */ sdma_flush_descq(sde); @@ -415,6 +416,22 @@ static void sdma_flush(struct sdma_engine *sde) /* flush from flush list */ list_for_each_entry_safe(txp, txp_next, &flushlist, list) complete_tx(sde, txp, SDMA_TXREQ_S_ABORTED); + /* wakeup QPs orphaned on the dmawait list */ + do { + struct iowait *w, *nw; + + seq = read_seqbegin(&sde->waitlock); + if (!list_empty(&sde->dmawait)) { + write_seqlock(&sde->waitlock); + list_for_each_entry_safe(w, nw, &sde->dmawait, list) { + if (w->wakeup) { + w->wakeup(w, SDMA_AVAIL_REASON); + list_del_init(&w->list); + } + } + write_sequnlock(&sde->waitlock); + } + } while (read_seqretry(&sde->waitlock, seq)); }
/*