powerpc/eeh: Aux PE data for error log

The patch allows PE (struct eeh_pe) instance to have auxillary data,
whose size is configurable on basis of platform. For PowerNV, the
auxillary data will be used to cache PHB diag-data for that PE
(frozen PE or fenced PHB). In turn, we can retrieve the diag-data
at any later points.

It's useful for the case of VFIO PCI devices where the error log
should be cached, and then be retrieved by the guest at later point.
Also, it can avoid PHB diag-data overwritting if another frozen PE
reported and the previous diag-data isn't fetched by guest.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

2 files changed, 31 insertions, 14 deletions

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 4909e5f3adda..f4d0259a63c3 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -239,20 +239,16 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
 	return ret;
 }
 
-static void ioda_eeh_phb_diag(struct pci_controller *hose)
+static void ioda_eeh_phb_diag(struct eeh_pe *pe)
 {
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pe->phb->private_data;
 	long rc;
 
-	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, pe->data,
 					 PNV_PCI_DIAG_BUF_SIZE);
-	if (rc != OPAL_SUCCESS) {
+	if (rc != OPAL_SUCCESS)
 		pr_warn("%s: Failed to get diag-data for PHB#%x (%ld)\n",
-			__func__, hose->global_number, rc);
-		return;
-	}
-
-	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
+			__func__, pe->phb->global_number, rc);
 }
 
 /**
@@ -323,7 +319,7 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
 			result |= EEH_STATE_DMA_ENABLED;
 		} else if (!(pe->state & EEH_PE_ISOLATED)) {
 			eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
-			ioda_eeh_phb_diag(hose);
+			ioda_eeh_phb_diag(pe);
 		}
 
 		return result;
@@ -373,7 +369,7 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
 	    (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) &&
 	    !(pe->state & EEH_PE_ISOLATED)) {
 		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
-		ioda_eeh_phb_diag(hose);
+		ioda_eeh_phb_diag(pe);
 	}
 
 	return result;
@@ -589,6 +585,24 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 }
 
 /**
+ * ioda_eeh_get_log - Retrieve error log
+ * @pe: frozen PE
+ * @severity: permanent or temporary error
+ * @drv_log: device driver log
+ * @len: length of device driver log
+ *
+ * Retrieve error log, which contains log from device driver
+ * and firmware.
+ */
+int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
+		     char *drv_log, unsigned long len)
+{
+	pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
+
+	return 0;
+}
+
+/**
  * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
  * @pe: EEH PE
  *
@@ -805,7 +819,8 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 					"detected, location: %s\n",
 					hose->global_number,
 					eeh_pe_loc_get(phb_pe));
-				ioda_eeh_phb_diag(hose);
+				ioda_eeh_phb_diag(phb_pe);
+				pnv_pci_dump_phb_diag_data(hose, phb_pe->data);
 				ret = EEH_NEXT_ERR_NONE;
 			}
 
@@ -853,7 +868,7 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 		    ret == EEH_NEXT_ERR_FENCED_PHB) &&
 		    !((*pe)->state & EEH_PE_ISOLATED)) {
 			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
-			ioda_eeh_phb_diag(hose);
+			ioda_eeh_phb_diag(*pe);
 		}
 
 		/*
@@ -899,6 +914,7 @@ struct pnv_eeh_ops ioda_eeh_ops = {
 	.set_option		= ioda_eeh_set_option,
 	.get_state		= ioda_eeh_get_state,
 	.reset			= ioda_eeh_reset,
+	.get_log		= ioda_eeh_get_log,
 	.configure_bridge	= ioda_eeh_configure_bridge,
 	.next_error		= ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 4a113f3c9171..fd7a16f855ed 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -326,7 +326,7 @@ static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
  * Retrieve the temporary or permanent error from the PE.
  */
 static int powernv_eeh_get_log(struct eeh_pe *pe, int severity,
-			char *drv_log, unsigned long len)
+			       char *drv_log, unsigned long len)
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
@@ -430,6 +430,7 @@ static int __init eeh_powernv_init(void)
 {
 	int ret = -EINVAL;
 
+	eeh_set_pe_aux_size(PNV_PCI_DIAG_BUF_SIZE);
 	ret = eeh_ops_register(&powernv_eeh_ops);
 	if (!ret)
 		pr_info("EEH: PowerNV platform initialized\n");