aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAlexey Kardashevskiy <aik@ozlabs.ru>2019-05-29 16:58:59 +1000
committerStewart Smith <stewart@linux.ibm.com>2019-06-03 10:28:57 +1000
commitd496bb141c978a6dc8a106b3d92e5fc1ad0f8663 (patch)
tree5da14ca8321145e59ef1bcf91a8962e02502eabf
parent6c0a6612f4920438e19d68e0c7146a5ef5fec877 (diff)
downloadskiboot-d496bb141c978a6dc8a106b3d92e5fc1ad0f8663.zip
skiboot-d496bb141c978a6dc8a106b3d92e5fc1ad0f8663.tar.gz
skiboot-d496bb141c978a6dc8a106b3d92e5fc1ad0f8663.tar.bz2
npu2: Clear fence state for a brick being reset
Resetting a GPU before resetting an NVLink leads to occasional HMIs which fence some bricks and prevent the "reset_ntl" procedure from succeeding at the "reset_ntl_release" step - the host system requires reboot; there may be other cases like this as well. This adds clearing of the fence bit in NPU.MISC.FENCE_STATE for the NVLink which we are about to reset. Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Signed-off-by: Stewart Smith <stewart@linux.ibm.com>
-rw-r--r--hw/npu2-hw-procedures.c8
1 files changed, 8 insertions, 0 deletions
diff --git a/hw/npu2-hw-procedures.c b/hw/npu2-hw-procedures.c
index e1f5e8d..0779dde 100644
--- a/hw/npu2-hw-procedures.c
+++ b/hw/npu2-hw-procedures.c
@@ -283,6 +283,14 @@ uint32_t reset_ntl(struct npu2_dev *ndev)
phy_write_lane(ndev, &NPU2_PHY_TX_LANE_PDWN, lane, 0);
}
+ /* Clear fence state for the brick */
+ val = npu2_read(ndev->npu, NPU2_MISC_FENCE_STATE);
+ if (val & PPC_BIT(ndev->brick_index)) {
+ NPU2DEVINF(ndev, "Clearing brick fence\n");
+ val = PPC_BIT(ndev->brick_index);
+ npu2_write(ndev->npu, NPU2_MISC_FENCE_STATE, val);
+ }
+
/* Write PRI */
val = SETFIELD(PPC_BITMASK(0,1), 0ull, obus_brick_index(ndev));
npu2_write_mask(ndev->npu, NPU2_NTL_PRI_CFG(ndev), val, -1ULL);