powerpc/pci: Delay populating pdn

The pdn (struct pci_dn) instances are allocated from memblock or
bootmem when creating PCI controller (hoses) in setup_arch(). PCI
hotplug, which will be supported by proceeding patches, releases
PCI device nodes and their corresponding pdn on unplugging event.
The memory chunks for pdn instances allocated from memblock or
bootmem are hard to reused after being released.

This delays creating pdn by pci_devs_phb_init() from setup_arch()
to core_initcall() so that they are allocated from slab. The memory
consumed by pdn can be released to system without problem during
PCI unplugging time. It indicates that pci_dn is unavailable in
setup_arch() and the the fixup on pdn (like AGP's) can't be carried
out that time. We have to do that in pcibios_root_bridge_prepare()
on maple/pasemi/powermac platforms where/when the pdn is available.
pcibios_root_bridge_prepare is called from subsys_initcall() which
is executed after core_initcall() so the code flow does not change.

At the mean while, the EEH device is created when pdn is populated,
meaning pdn and EEH device have same life cycle. In turn, we needn't
call eeh_dev_init() to create EEH device explicitly.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/eeh.h

@@ -274,7 +274,7 @@ void eeh_pe_restore_bars(struct eeh_pe *pe);
 const char *eeh_pe_loc_get(struct eeh_pe *pe);
 struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe);
 
-void *eeh_dev_init(struct pci_dn *pdn, void *data);
+struct eeh_dev *eeh_dev_init(struct pci_dn *pdn);
 void eeh_dev_phb_init_dynamic(struct pci_controller *phb);
 int eeh_init(void);
 int __init eeh_ops_register(struct eeh_ops *ops);

arch/powerpc/include/asm/ppc-pci.h

@@ -39,8 +39,6 @@ void *pci_traverse_device_nodes(struct device_node *start,
 void *traverse_pci_dn(struct pci_dn *root,
 		      void *(*fn)(struct pci_dn *, void *),
 		      void *data);
-
-extern void pci_devs_phb_init(void);
 extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
 
 /* From rtas_pci.h */

arch/powerpc/kernel/eeh_dev.c

@@ -44,14 +44,13 @@
 /**
  * eeh_dev_init - Create EEH device according to OF node
  * @pdn: PCI device node
- * @data: PHB
  *
  * It will create EEH device according to the given OF node. The function
  * might be called by PCI emunation, DR, PHB hotplug.
  */
-void *eeh_dev_init(struct pci_dn *pdn, void *data)
+struct eeh_dev *eeh_dev_init(struct pci_dn *pdn)
 {
-	struct pci_controller *phb = data;
+	struct pci_controller *phb = pdn->phb;
 	struct eeh_dev *edev;
 
 	/* Allocate EEH device */
@@ -69,7 +68,7 @@ void *eeh_dev_init(struct pci_dn *pdn, void *data)
 	INIT_LIST_HEAD(&edev->list);
 	INIT_LIST_HEAD(&edev->rmv_list);
 
-	return NULL;
+	return edev;
 }
 
 /**
@@ -81,16 +80,8 @@ void *eeh_dev_init(struct pci_dn *pdn, void *data)
  */
 void eeh_dev_phb_init_dynamic(struct pci_controller *phb)
 {
-	struct pci_dn *root = phb->pci_data;
-
 	/* EEH PE for PHB */
 	eeh_phb_pe_create(phb);
-
-	/* EEH device for PHB */
-	eeh_dev_init(root, phb);
-
-	/* EEH devices for children OF nodes */
-	traverse_pci_dn(root, eeh_dev_init, phb);
 }
 
 /**
@@ -106,8 +97,6 @@ static int __init eeh_dev_phb_init(void)
 	list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
 		eeh_dev_phb_init_dynamic(phb);
 
-	pr_info("EEH: devices created\n");
-
 	return 0;
 }
 

arch/powerpc/kernel/pci_dn.c

@@ -212,8 +212,7 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
 
 #ifdef CONFIG_EEH
 		/* Create the EEH device for the VF */
-		eeh_dev_init(pdn, pci_bus_to_host(pdev->bus));
-		edev = pdn_to_eeh_dev(pdn);
+		edev = eeh_dev_init(pdn);
 		BUG_ON(!edev);
 		edev->physfn = pdev;
 #endif /* CONFIG_EEH */
@@ -295,8 +294,11 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
 	const __be32 *regs;
 	struct device_node *parent;
 	struct pci_dn *pdn;
+#ifdef CONFIG_EEH
+	struct eeh_dev *edev;
+#endif
 
-	pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL);
+	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
 	if (pdn == NULL)
 		return NULL;
 	dn->data = pdn;
@@ -325,6 +327,15 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
 	/* Extended config space */
 	pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1);
 
+	/* Create EEH device */
+#ifdef CONFIG_EEH
+	edev = eeh_dev_init(pdn);
+	if (!edev) {
+		kfree(pdn);
+		return NULL;
+	}
+#endif
+
 	/* Attach to parent node */
 	INIT_LIST_HEAD(&pdn->child_list);
 	INIT_LIST_HEAD(&pdn->list);
@@ -510,15 +521,19 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb)
  * pci device found underneath.  This routine runs once,
  * early in the boot sequence.
  */
-void __init pci_devs_phb_init(void)
+static int __init pci_devs_phb_init(void)
 {
 	struct pci_controller *phb, *tmp;
 
 	/* This must be done first so the device nodes have valid pci info! */
 	list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
 		pci_devs_phb_init_dynamic(phb);
+
+	return 0;
 }
 
+core_initcall(pci_devs_phb_init);
+
 static void pci_dev_pdn_setup(struct pci_dev *pdev)
 {
 	struct pci_dn *pdn;

arch/powerpc/platforms/maple/pci.c

@@ -568,6 +568,26 @@ void maple_pci_irq_fixup(struct pci_dev *dev)
 	DBG(" <- maple_pci_irq_fixup\n");
 }
 
+static int maple_pci_root_bridge_prepare(struct pci_host_bridge *bridge)
+{
+	struct pci_controller *hose = pci_bus_to_host(bridge->bus);
+	struct device_node *np, *child;
+
+	if (hose != u3_agp)
+		return 0;
+
+	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
+	 * assume there is no P2P bridge on the AGP bus, which should be a
+	 * safe assumptions hopefully.
+	 */
+	np = hose->dn;
+	PCI_DN(np)->busno = 0xf0;
+	for_each_child_of_node(np, child)
+		PCI_DN(child)->busno = 0xf0;
+
+	return 0;
+}
+
 void __init maple_pci_init(void)
 {
 	struct device_node *np, *root;
@@ -605,19 +625,7 @@ void __init maple_pci_init(void)
 	if (ht && maple_add_bridge(ht) != 0)
 		of_node_put(ht);
 
-	/* Setup the linkage between OF nodes and PHBs */ 
-	pci_devs_phb_init();
-
-	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
-	 * assume there is no P2P bridge on the AGP bus, which should be a
-	 * safe assumptions hopefully.
-	 */
-	if (u3_agp) {
-		struct device_node *np = u3_agp->dn;
-		PCI_DN(np)->busno = 0xf0;
-		for (np = np->child; np; np = np->sibling)
-			PCI_DN(np)->busno = 0xf0;
-	}
+	ppc_md.pcibios_root_bridge_prepare = maple_pci_root_bridge_prepare;
 
 	/* Tell pci.c to not change any resource allocations.  */
 	pci_add_flags(PCI_PROBE_ONLY);

arch/powerpc/platforms/pasemi/pci.c

@@ -229,9 +229,6 @@ void __init pas_pci_init(void)
 			of_node_get(np);
 
 	of_node_put(root);
-
-	/* Setup the linkage between OF nodes and PHBs */
-	pci_devs_phb_init();
 }
 
 void __iomem *pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset)

arch/powerpc/platforms/powermac/pci.c

@@ -878,6 +878,29 @@ void pmac_pci_irq_fixup(struct pci_dev *dev)
 #endif /* CONFIG_PPC32 */
 }
 
+#ifdef CONFIG_PPC64
+static int pmac_pci_root_bridge_prepare(struct pci_host_bridge *bridge)
+{
+	struct pci_controller *hose = pci_bus_to_host(bridge->bus);
+	struct device_node *np, *child;
+
+	if (hose != u3_agp)
+		return 0;
+
+	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
+	 * assume there is no P2P bridge on the AGP bus, which should be a
+	 * safe assumptions for now. We should do something better in the
+	 * future though
+	 */
+	np = hose->dn;
+	PCI_DN(np)->busno = 0xf0;
+	for_each_child_of_node(np, child)
+		PCI_DN(child)->busno = 0xf0;
+
+	return 0;
+}
+#endif /* CONFIG_PPC64 */
+
 void __init pmac_pci_init(void)
 {
 	struct device_node *np, *root;
@@ -914,20 +937,7 @@ void __init pmac_pci_init(void)
 	if (ht && pmac_add_bridge(ht) != 0)
 		of_node_put(ht);
 
-	/* Setup the linkage between OF nodes and PHBs */
-	pci_devs_phb_init();
-
-	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
-	 * assume there is no P2P bridge on the AGP bus, which should be a
-	 * safe assumptions for now. We should do something better in the
-	 * future though
-	 */
-	if (u3_agp) {
-		struct device_node *np = u3_agp->dn;
-		PCI_DN(np)->busno = 0xf0;
-		for (np = np->child; np; np = np->sibling)
-			PCI_DN(np)->busno = 0xf0;
-	}
+	ppc_md.pcibios_root_bridge_prepare = pmac_pci_root_bridge_prepare;
 	/* pmac_check_ht_link(); */
 
 #else /* CONFIG_PPC64 */

arch/powerpc/platforms/powernv/pci.c

@@ -816,9 +816,6 @@ void __init pnv_pci_init(void)
 	for_each_compatible_node(np, NULL, "ibm,ioda2-npu-phb")
 		pnv_pci_init_npu_phb(np);
 
-	/* Setup the linkage between OF nodes and PHBs */
-	pci_devs_phb_init();
-
 	/* Configure IOMMU DMA hooks */
 	set_pci_dma_ops(&dma_iommu_ops);
 }

arch/powerpc/platforms/pseries/setup.c

@@ -195,11 +195,8 @@ static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long act
 	case OF_RECONFIG_ATTACH_NODE:
 		parent = of_get_parent(np);
 		pdn = parent ? PCI_DN(parent) : NULL;
-		if (pdn) {
-			/* Create pdn and EEH device */
+		if (pdn)
 			pci_add_device_node_info(pdn->phb, np);
-			eeh_dev_init(PCI_DN(np), pdn->phb);
-		}
 
 		of_node_put(parent);
 		break;
@@ -422,7 +419,6 @@ static void __init find_and_init_phbs(void)
 	}
 
 	of_node_put(root);
-	pci_devs_phb_init();
 
 	/*
 	 * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties