diff mbox series

[v2,12/16] npu2-opencapi: Detect PHY reset errors

Message ID 20191009193811.15333-13-fbarrat@linux.ibm.com
State Accepted
Headers show
Series opencapi: enable card reset and link retraining | expand

Checks

Context Check Description
snowpatch_ozlabs/apply_patch success Successfully applied on branch master (1785745d5a7eaefd7d0c135f2a3b0f5d86aefec5)
snowpatch_ozlabs/snowpatch_job_snowpatch-skiboot success Test snowpatch/job/snowpatch-skiboot on branch master
snowpatch_ozlabs/snowpatch_job_snowpatch-skiboot-dco success Signed-off-by present

Commit Message

Frederic Barrat Oct. 9, 2019, 7:38 p.m. UTC 
PHY reset can fail! Though past problems are now fixed, let's handle
any future failure.

Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
---
Changelog:
v2:
 - log a message if we couldn't reset the PHY (Christophe, Andrew)


hw/npu2-hw-procedures.c | 13 ++++++++++---
 hw/npu2-opencapi.c      |  7 ++++++-
 include/npu2.h          |  2 +-
 3 files changed, 17 insertions(+), 5 deletions(-)

Comments

Christophe Lombard Oct. 14, 2019, 12:39 p.m. UTC | #1 
On 09/10/2019 21:38, Frederic Barrat wrote:
> PHY reset can fail! Though past problems are now fixed, let's handle
> any future failure.
> 
> Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
> ---

Reviewed-by: Christophe Lombard <clombard@linux.vnet.ibm.com>
diff mbox series

Patch

diff --git a/hw/npu2-hw-procedures.c b/hw/npu2-hw-procedures.c
index ad1627ae..8379cbbe 100644
--- a/hw/npu2-hw-procedures.c
+++ b/hw/npu2-hw-procedures.c
@@ -1041,10 +1041,17 @@  void npu2_opencapi_phy_init(struct npu2_dev *dev)
 	}
 }
 
-void npu2_opencapi_phy_reset(struct npu2_dev *dev)
+int npu2_opencapi_phy_reset(struct npu2_dev *dev)
 {
-	run_procedure(dev, 4); /* procedure_phy_reset */
-	run_procedure(dev, 6); /* procedure_phy_rx_dccal */
+	int rc;
+
+	rc = run_procedure(dev, 4); /* procedure_phy_reset */
+	if (rc != PROCEDURE_COMPLETE)
+		return -1;
+	rc = run_procedure(dev, 6); /* procedure_phy_rx_dccal */
+	if (rc != PROCEDURE_COMPLETE)
+		return -1;
+	return 0;
 }
 
 void npu2_opencapi_phy_prbs31(struct npu2_dev *dev)
diff --git a/hw/npu2-opencapi.c b/hw/npu2-opencapi.c
index ead6f5fa..140b8ef9 100644
--- a/hw/npu2-opencapi.c
+++ b/hw/npu2-opencapi.c
@@ -1187,6 +1187,7 @@  static int64_t npu2_opencapi_freset(struct pci_slot *slot)
 	struct npu2_dev *dev = phb_to_npu2_dev_ocapi(slot->phb);
 	uint32_t chip_id = dev->npu->chip_id;
 	uint8_t presence = 1;
+	int rc;
 
 	switch (slot->state) {
 	case OCAPI_SLOT_NORMAL:
@@ -1216,7 +1217,11 @@  static int64_t npu2_opencapi_freset(struct pci_slot *slot)
 		return pci_slot_set_sm_timeout(slot, msecs_to_tb(5));
 
 	case OCAPI_SLOT_FRESET_ASSERT_DELAY:
-		npu2_opencapi_phy_reset(dev);
+		rc = npu2_opencapi_phy_reset(dev);
+		if (rc) {
+			OCAPIERR(dev, "FRESET: couldn't reset PHY state\n");
+			return OPAL_HARDWARE;
+		}
 		deassert_odl_reset(chip_id, dev->brick_index);
 		deassert_adapter_reset(dev);
 		pci_slot_set_state(slot,
diff --git a/include/npu2.h b/include/npu2.h
index 6b1063da..6171cd3c 100644
--- a/include/npu2.h
+++ b/include/npu2.h
@@ -234,7 +234,7 @@  void npu2_clear_link_flag(struct npu2_dev *ndev, uint8_t flag);
 uint32_t reset_ntl(struct npu2_dev *ndev);
 extern int nv_zcal_nominal;
 void npu2_opencapi_phy_init(struct npu2_dev *dev);
-void npu2_opencapi_phy_reset(struct npu2_dev *dev);
+int npu2_opencapi_phy_reset(struct npu2_dev *dev);
 void npu2_opencapi_phy_prbs31(struct npu2_dev *dev);
 void npu2_opencapi_bump_ui_lane(struct npu2_dev *dev);
 int64_t npu2_freeze_status(struct phb *phb __unused,