powerpc/eeh: Probe mode support

While EEH module is installed, PCI devices is checked one by one
to see if it supports eeh. On different platforms, the PCI devices
are referred through different ways when the EEH module is loaded.
For example, on pSeries platform, that is done by OF node. However,
we would do that by real PCI devices (struct pci_dev) on PowerNV
platform in future. So we needs some mechanism to differentiate
those cases by classifying them to probe modes, either from OF
nodes or real PCI devices.

The patch implements the support to eeh probe mode. Also, the
EEH on pSeries has set it into EEH_PROBE_MODE_DEVTREE. That means
the probe will be done based on OF nodes on pSeries platform.

In addition, On pSeries platform, it's done by OF nodes. The patch
moves the the probe function from EEH core to platform dependent
backend and some cleanup applied.

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

4 files changed, 140 insertions, 109 deletions

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 792d2d7..895fd0d 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -129,6 +129,8 @@ static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
 struct eeh_ops {
 	char *name;
 	int (*init)(void);
+	void* (*of_probe)(struct device_node *dn, void *flag);
+	void* (*dev_probe)(struct pci_dev *dev, void *flag);
 	int (*set_option)(struct eeh_pe *pe, int option);
 	int (*get_pe_addr)(struct eeh_pe *pe);
 	int (*get_state)(struct eeh_pe *pe, int *state);
@@ -143,6 +145,25 @@ struct eeh_ops {
 extern struct eeh_ops *eeh_ops;
 extern int eeh_subsystem_enabled;
 extern struct mutex eeh_mutex;
+extern int eeh_probe_mode;
+
+#define EEH_PROBE_MODE_DEV	(1<<0)	/* From PCI device	*/
+#define EEH_PROBE_MODE_DEVTREE	(1<<1)	/* From device tree	*/
+
+static inline void eeh_probe_mode_set(int flag)
+{
+	eeh_probe_mode = flag;
+}
+
+static inline int eeh_probe_mode_devtree(void)
+{
+	return (eeh_probe_mode == EEH_PROBE_MODE_DEVTREE);
+}
+
+static inline int eeh_probe_mode_dev(void)
+{
+	return (eeh_probe_mode == EEH_PROBE_MODE_DEV);
+}
 
 static inline void eeh_lock(void)
 {
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index 2a80f08..56d55c7 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -54,6 +54,7 @@ struct pci_dev *pci_addr_cache_get_device(unsigned long addr);
 void eeh_slot_error_detail(struct eeh_pe *pe, int severity);
 int eeh_pci_enable(struct eeh_pe *pe, int function);
 int eeh_reset_pe(struct eeh_pe *);
+void eeh_save_bars(struct eeh_dev *edev);
 int rtas_write_config(struct pci_dn *, int where, int size, u32 val);
 int rtas_read_config(struct pci_dn *, int where, int size, u32 *val);
 void eeh_pe_state_mark(struct eeh_pe *pe, int state);
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 6d43230..4bdc278 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -92,6 +92,17 @@ struct eeh_ops *eeh_ops = NULL;
 int eeh_subsystem_enabled;
 EXPORT_SYMBOL(eeh_subsystem_enabled);
 
+/*
+ * EEH probe mode support. The intention is to support multiple
+ * platforms for EEH. Some platforms like pSeries do PCI emunation
+ * based on device tree. However, other platforms like powernv probe
+ * PCI devices from hardware. The flag is used to distinguish that.
+ * In addition, struct eeh_ops::probe would be invoked for particular
+ * OF node or PCI device so that the corresponding PE would be created
+ * there.
+ */
+int eeh_probe_mode;
+
 /* Global EEH mutex */
 DEFINE_MUTEX(eeh_mutex);
 
@@ -590,7 +601,7 @@ int eeh_reset_pe(struct eeh_pe *pe)
  * PCI devices are added individually; but, for the restore,
  * an entire slot is reset at a time.
  */
-static void eeh_save_bars(struct eeh_dev *edev)
+void eeh_save_bars(struct eeh_dev *edev)
 {
 	int i;
 	struct device_node *dn;
@@ -604,108 +615,6 @@ static void eeh_save_bars(struct eeh_dev *edev)
 }
 
 /**
- * eeh_early_enable - Early enable EEH on the indicated device
- * @dn: device node
- * @data: BUID
- *
- * Enable EEH functionality on the specified PCI device. The function
- * is expected to be called before real PCI probing is done. However,
- * the PHBs have been initialized at this point.
- */
-static void *eeh_early_enable(struct device_node *dn, void *data)
-{
-	int ret;
-	const u32 *class_code = of_get_property(dn, "class-code", NULL);
-	const u32 *vendor_id = of_get_property(dn, "vendor-id", NULL);
-	const u32 *device_id = of_get_property(dn, "device-id", NULL);
-	const u32 *regs;
-	int enable;
-	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
-	struct eeh_pe pe;
-
-	edev->class_code = 0;
-	edev->mode = 0;
-
-	if (!of_device_is_available(dn))
-		return NULL;
-
-	/* Ignore bad nodes. */
-	if (!class_code || !vendor_id || !device_id)
-		return NULL;
-
-	/* There is nothing to check on PCI to ISA bridges */
-	if (dn->type && !strcmp(dn->type, "isa"))
-		return NULL;
-	edev->class_code = *class_code;
-
-	/* Ok... see if this device supports EEH.  Some do, some don't,
-	 * and the only way to find out is to check each and every one.
-	 */
-	regs = of_get_property(dn, "reg", NULL);
-	if (regs) {
-		/* Initialize the fake PE */
-		memset(&pe, 0, sizeof(struct eeh_pe));
-		pe.phb = edev->phb;
-		pe.config_addr = regs[0];
-
-		/* First register entry is addr (00BBSS00)  */
-		/* Try to enable eeh */
-		ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE);
-
-		enable = 0;
-		if (ret == 0) {
-			edev->config_addr = regs[0];
-
-			/* If the newer, better, ibm,get-config-addr-info is supported, 
-			 * then use that instead.
-			 */
-			edev->pe_config_addr = eeh_ops->get_pe_addr(&pe);
-			pe.addr = edev->pe_config_addr;
-
-			/* Some older systems (Power4) allow the
-			 * ibm,set-eeh-option call to succeed even on nodes
-			 * where EEH is not supported. Verify support
-			 * explicitly.
-			 */
-			ret = eeh_ops->get_state(&pe, NULL);
-			if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT)
-				enable = 1;
-		}
-
-		if (enable) {
-			eeh_subsystem_enabled = 1;
-
-			eeh_add_to_parent_pe(edev);
-
-			pr_debug("EEH: %s: eeh enabled, config=%x pe_config=%x\n",
-				 dn->full_name, edev->config_addr,
-				 edev->pe_config_addr);
-		} else {
-
-			/* This device doesn't support EEH, but it may have an
-			 * EEH parent, in which case we mark it as supported.
-			 */
-			if (dn->parent && of_node_to_eeh_dev(dn->parent) &&
-			    of_node_to_eeh_dev(dn->parent)->pe) {
-				/* Parent supports EEH. */
-				edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr;
-				edev->pe_config_addr = of_node_to_eeh_dev(dn->parent)->pe_config_addr;
-
-				eeh_add_to_parent_pe(edev);
-
-				return NULL;
-			}
-		}
-	} else {
-		printk(KERN_WARNING "EEH: %s: unable to get reg property.\n",
-		       dn->full_name);
-	}
-
-	eeh_save_bars(edev);
-	return NULL;
-}
-
-/**
  * eeh_ops_register - Register platform dependent EEH operations
  * @ops: platform dependent EEH operations
  *
@@ -790,15 +699,18 @@ static int __init eeh_init(void)
 	raw_spin_lock_init(&confirm_error_lock);
 
 	/* Enable EEH for all adapters */
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
-		phb = hose->dn;
-		traverse_pci_devices(phb, eeh_early_enable, NULL);
+	if (eeh_probe_mode_devtree()) {
+		list_for_each_entry_safe(hose, tmp,
+			&hose_list, list_node) {
+			phb = hose->dn;
+			traverse_pci_devices(phb, eeh_ops->of_probe, NULL);
+		}
 	}
 
 	if (eeh_subsystem_enabled)
-		printk(KERN_INFO "EEH: PCI Enhanced I/O Error Handling Enabled\n");
+		pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
 	else
-		printk(KERN_WARNING "EEH: No capable adapters found\n");
+		pr_warning("EEH: No capable adapters found\n");
 
 	return ret;
 }
@@ -829,7 +741,8 @@ static void eeh_add_device_early(struct device_node *dn)
 	if (NULL == phb || 0 == phb->buid)
 		return;
 
-	eeh_early_enable(dn, NULL);
+	/* FIXME: hotplug support on POWERNV */
+	eeh_ops->of_probe(dn, NULL);
 }
 
 /**
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index fdeef77..19506f9 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -129,10 +129,104 @@ static int pseries_eeh_init(void)
 		eeh_error_buf_size = RTAS_ERROR_LOG_MAX;
 	}
 
+	/* Set EEH probe mode */
+	eeh_probe_mode_set(EEH_PROBE_MODE_DEVTREE);
+
 	return 0;
 }
 
 /**
+ * pseries_eeh_of_probe - EEH probe on the given device
+ * @dn: OF node
+ * @flag: Unused
+ *
+ * When EEH module is installed during system boot, all PCI devices
+ * are checked one by one to see if it supports EEH. The function
+ * is introduced for the purpose.
+ */
+static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
+{
+	struct eeh_dev *edev;
+	struct eeh_pe pe;
+	const u32 *class_code, *vendor_id, *device_id;
+	const u32 *regs;
+	int enable = 0;
+	int ret;
+
+	/* Retrieve OF node and eeh device */
+	edev = of_node_to_eeh_dev(dn);
+	if (!of_device_is_available(dn))
+		return NULL;
+
+	/* Retrieve class/vendor/device IDs */
+	class_code = of_get_property(dn, "class-code", NULL);
+	vendor_id  = of_get_property(dn, "vendor-id", NULL);
+	device_id  = of_get_property(dn, "device-id", NULL);
+
+	/* Skip for bad OF node or PCI-ISA bridge */
+	if (!class_code || !vendor_id || !device_id)
+		return NULL;
+	if (dn->type && !strcmp(dn->type, "isa"))
+		return NULL;
+
+	/* Update class code and mode of eeh device */
+	edev->class_code = *class_code;
+	edev->mode = 0;
+
+	/* Retrieve the device address */
+	regs = of_get_property(dn, "reg", NULL);
+	if (!regs) {
+		pr_warning("%s: OF node property %s::reg not found\n",
+			__func__, dn->full_name);
+		return NULL;
+	}
+
+	/* Initialize the fake PE */
+	memset(&pe, 0, sizeof(struct eeh_pe));
+	pe.phb = edev->phb;
+	pe.config_addr = regs[0];
+
+	/* Enable EEH on the device */
+	ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE);
+	if (!ret) {
+		edev->config_addr = regs[0];
+		/* Retrieve PE address */
+		edev->pe_config_addr = eeh_ops->get_pe_addr(&pe);
+		pe.addr = edev->pe_config_addr;
+
+		/* Some older systems (Power4) allow the ibm,set-eeh-option
+		 * call to succeed even on nodes where EEH is not supported.
+		 * Verify support explicitly.
+		 */
+		ret = eeh_ops->get_state(&pe, NULL);
+		if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT)
+			enable = 1;
+
+		if (enable) {
+			eeh_subsystem_enabled = 1;
+			eeh_add_to_parent_pe(edev);
+
+			pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n",
+				__func__, dn->full_name, pe.phb->global_number,
+				pe.addr, pe.config_addr);
+		} else if (dn->parent && of_node_to_eeh_dev(dn->parent) &&
+			   (of_node_to_eeh_dev(dn->parent))->pe) {
+			/* This device doesn't support EEH, but it may have an
+			 * EEH parent, in which case we mark it as supported.
+			 */
+			edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr;
+			edev->pe_config_addr = of_node_to_eeh_dev(dn->parent)->pe_config_addr;
+			eeh_add_to_parent_pe(edev);
+		}
+	}
+
+	/* Save memory bars */
+	eeh_save_bars(edev);
+
+	return NULL;
+}
+
+/**
  * pseries_eeh_set_option - Initialize EEH or MMIO/DMA reenable
  * @pe: EEH PE
  * @option: operation to be issued
@@ -523,6 +617,8 @@ static int pseries_eeh_write_config(struct device_node *dn, int where, int size,
 static struct eeh_ops pseries_eeh_ops = {
 	.name			= "pseries",
 	.init			= pseries_eeh_init,
+	.of_probe		= pseries_eeh_of_probe,
+	.dev_probe		= NULL,
 	.set_option		= pseries_eeh_set_option,
 	.get_pe_addr		= pseries_eeh_get_pe_addr,
 	.get_state		= pseries_eeh_get_state,