powerpc/eeh: Block PCI-CFG access during PE reset

We've observed multiple PE reset failures because of PCI-CFG
access during that period. Potentially, some device drivers
can't support EEH very well and they can't put the device to
motionless state before PE reset. So those device drivers might
produce PCI-CFG accesses during PE reset. Also, we could have
PCI-CFG access from user space (e.g. "lspci"). Since access to
frozen PE should return 0xFF's, we can block PCI-CFG access
during the period of PE reset so that we won't get recrusive EEH
errors.

The patch adds flag EEH_PE_RESET, which is kept during PE reset.
The PowerNV/pSeries PCI-CFG accessors reuse the flag to block
PCI-CFG accordingly.

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

1 files changed, 50 insertions, 16 deletions

diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index 7d4c717..c168337 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -80,10 +80,6 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
 	if (ret)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	if (returnval == EEH_IO_ERROR_VALUE(size) &&
-	    eeh_dev_check_failure(of_node_to_eeh_dev(pdn->node)))
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
 	return PCIBIOS_SUCCESSFUL;
 }
 
@@ -92,18 +88,39 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 				int where, int size, u32 *val)
 {
 	struct device_node *busdn, *dn;
-
-	busdn = pci_bus_to_OF_node(bus);
+	struct pci_dn *pdn;
+	bool found = false;
+#ifdef CONFIG_EEH
+	struct eeh_dev *edev;
+#endif
+	int ret;
 
 	/* Search only direct children of the bus */
+	*val = 0xFFFFFFFF;
+	busdn = pci_bus_to_OF_node(bus);
 	for (dn = busdn->child; dn; dn = dn->sibling) {
-		struct pci_dn *pdn = PCI_DN(dn);
+		pdn = PCI_DN(dn);
 		if (pdn && pdn->devfn == devfn
-		    && of_device_is_available(dn))
-			return rtas_read_config(pdn, where, size, val);
+		    && of_device_is_available(dn)) {
+			found = true;
+			break;
+		}
 	}
 
-	return PCIBIOS_DEVICE_NOT_FOUND;
+	if (!found)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+#ifdef CONFIG_EEH
+	edev = of_node_to_eeh_dev(dn);
+	if (edev && edev->pe && edev->pe->state & EEH_PE_RESET)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+#endif
+
+	ret = rtas_read_config(pdn, where, size, val);
+	if (*val == EEH_IO_ERROR_VALUE(size) &&
+	    eeh_dev_check_failure(of_node_to_eeh_dev(dn)))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	return ret;
 }
 
 int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
@@ -136,17 +153,34 @@ static int rtas_pci_write_config(struct pci_bus *bus,
 				 int where, int size, u32 val)
 {
 	struct device_node *busdn, *dn;
-
-	busdn = pci_bus_to_OF_node(bus);
+	struct pci_dn *pdn;
+	bool found = false;
+#ifdef CONFIG_EEH
+	struct eeh_dev *edev;
+#endif
+	int ret;
 
 	/* Search only direct children of the bus */
+	busdn = pci_bus_to_OF_node(bus);
 	for (dn = busdn->child; dn; dn = dn->sibling) {
-		struct pci_dn *pdn = PCI_DN(dn);
+		pdn = PCI_DN(dn);
 		if (pdn && pdn->devfn == devfn
-		    && of_device_is_available(dn))
-			return rtas_write_config(pdn, where, size, val);
+		    && of_device_is_available(dn)) {
+			found = true;
+			break;
+		}
 	}
-	return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (!found)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+#ifdef CONFIG_EEH
+	edev = of_node_to_eeh_dev(dn);
+	if (edev && edev->pe && (edev->pe->state & EEH_PE_RESET))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+#endif
+	ret = rtas_write_config(pdn, where, size, val);
+
+	return ret;
 }
 
 static struct pci_ops rtas_pci_ops = {