[PATCH v2 11/22] staging/rdma/hfi1: Fix port bounce issues with 0.22 DC firmware

ira.weiny at intel.com ira.weiny at intel.com
Tue Oct 20 02:11:26 UTC 2015


From: Easwar Hariharan <easwar.hariharan at intel.com>

The DC firmware overwrites the enable_lane_tx register and does not update it
on a host request to go to Poll. This causes an infinite loop through the LNI
state machine if a link width downgrade occurs. This patch re-sets the
enable_lane_tx register to all 4 lanes.

Reviewed-by: Dean Luick <dean.luick at intel.com>
Signed-off-by: Easwar Hariharan <easwar.hariharan at intel.com>
Signed-off-by: Ira Weiny <ira.weiny at intel.com>
---
 drivers/staging/rdma/hfi1/chip.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/staging/rdma/hfi1/chip.c b/drivers/staging/rdma/hfi1/chip.c
index 3c48294abd20..0be37e9430af 100644
--- a/drivers/staging/rdma/hfi1/chip.c
+++ b/drivers/staging/rdma/hfi1/chip.c
@@ -5417,6 +5417,8 @@ static int set_local_link_attributes(struct hfi1_pportdata *ppd)
 		if (ppd->link_speed_enabled & OPA_LINK_SPEED_12_5G)
 			ppd->local_tx_rate |= 1;
 	}
+
+	enable_lane_tx = 0xF; /* enable all four lanes */
 	ret = write_tx_settings(dd, enable_lane_tx, tx_polarity_inversion,
 		     rx_polarity_inversion, ppd->local_tx_rate);
 	if (ret != HCMD_SUCCESS)
-- 
1.8.2



More information about the devel mailing list