[PATCH v8 21/45] powerpc/powernv: Create PEs at PCI hot plugging time

[Gavin Shan <gwshan@linux.vnet.ibm.com>]

Currently, the PEs and their associated resources are assigned
in ppc_md.pcibios_fixup() except those used by SRIOV VFs. The
function is called for once after PCI probing and resources
assignment is completed. So it isn't hotplug friendly.

This creates PEs dynamically by ppc_md.pcibios_setup_bridge(), which
is called on the event during system bootup and PCI hotplug: updating
PCI bridge's windows after resource assignment/reassignment are done.
For partial hotplug case, where not all PCI devices belonging to the
PE are unplugged and plugged again, we just need unbinding/binding
the affected PCI devices with the corresponding PE without creating
new one.

As there is no upstream bridge for root bus that needs to be covered
by PE, we have to create PE for root bus in ppc_md.pcibios_setup_bridge()
before any other PEs can be created, as PE for root bus is the ancestor
to anyone else.

Also, the windows of root port or the upstream port of PCIe switch behind
root port are extended to be PHB's apertures to accommodate the additional
resources needed by newly plugged devices based on the fact: hotpluggable
slot is behind root port or downstream port of the PCIe switch behind
root port. The extension for those PCI brdiges' windows is done in
ppc_md.pcibios_setup_bridge() as well.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/pci-ioda.c | 294 +++++++++++++++++-------------
 arch/powerpc/platforms/powernv/pci.h      |   2 +
 2 files changed, 168 insertions(+), 128 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 565725b..d360607 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -197,14 +197,14 @@ static int pnv_ioda2_init_m64(struct pnv_phb *phb)
 	set_bit(phb->ioda.m64_bar_idx, &phb->ioda.m64_bar_alloc);
 
 	/*
-	 * Strip off the segment used by the reserved PE, which is
-	 * expected to be 0 or last one of PE capabicity.
+	 * Exclude the segments for reserved and root bus PE, which
+	 * are first or last two PEs.
 	 */
 	r = &phb->hose->mem_resources[1];
 	if (phb->ioda.reserved_pe_idx == 0)
-		r->start += phb->ioda.m64_segsize;
+		r->start += (2 * phb->ioda.m64_segsize);
 	else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1))
-		r->end -= phb->ioda.m64_segsize;
+		r->end -= (2 * phb->ioda.m64_segsize);
 	else
 		pr_warn("  Cannot strip M64 segment for reserved PE#%d\n",
 			phb->ioda.reserved_pe_idx);
@@ -284,14 +284,14 @@ static int pnv_ioda1_init_m64(struct pnv_phb *phb)
 	}
 
 	/*
-	 * Exclude the segment used by the reserved PE, which
-	 * is expected to be 0 or last supported PE#.
+	 * Exclude the segments for reserved and root bus PE, which
+	 * are first or last two PEs.
 	 */
 	r = &phb->hose->mem_resources[1];
 	if (phb->ioda.reserved_pe_idx == 0)
-		r->start += phb->ioda.m64_segsize;
+		r->start += (2 * phb->ioda.m64_segsize);
 	else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1))
-		r->end -= phb->ioda.m64_segsize;
+		r->end -= (2 * phb->ioda.m64_segsize);
 	else
 		pr_warn("  Cannot cut M64 segment for reserved PE#%d\n",
 			phb->ioda.reserved_pe_idx);
@@ -1022,6 +1022,15 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
 				pci_name(dev));
 			continue;
 		}
+
+		/*
+		 * In partial hotplug case, the PCI device might be still
+		 * associated with the PE and needn't be attached to the
+		 * PE again.
+		 */
+		if (pdn->pe_number != IODA_INVALID_PE)
+			continue;
+
 		pdn->pcidev = dev;
 		pdn->pe_number = pe->pe_number;
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
@@ -1040,9 +1049,26 @@ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 	struct pci_controller *hose = pci_bus_to_host(bus);
 	struct pnv_phb *phb = hose->private_data;
 	struct pnv_ioda_pe *pe = NULL;
+	int pe_num;
+
+	/*
+	 * In partial hotplug case, the PE instance might be still alive.
+	 * We should reuse it instead of allocating a new one.
+	 */
+	pe_num = phb->ioda.pe_rmap[bus->number << 8];
+	if (pe_num != IODA_INVALID_PE) {
+		pe = &phb->ioda.pe_array[pe_num];
+		pnv_ioda_setup_same_PE(bus, pe);
+		return NULL;
+	}
+
+	/* PE number for root bus should have been reserved */
+	if (pci_is_root_bus(bus) &&
+	    phb->ioda.root_pe_idx != IODA_INVALID_PE)
+		pe = &phb->ioda.pe_array[phb->ioda.root_pe_idx];
 
 	/* Check if PE is determined by M64 */
-	if (phb->pick_m64_pe)
+	if (!pe && phb->pick_m64_pe)
 		pe = phb->pick_m64_pe(bus, all);
 
 	/* The PE number isn't pinned by M64 */
@@ -1154,30 +1180,6 @@ static void pnv_ioda_setup_npu_PEs(struct pci_bus *bus)
 		pnv_ioda_setup_npu_PE(pdev);
 }
 
-static void pnv_ioda_setup_PEs(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	pnv_ioda_setup_bus_PE(bus, false);
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		if (dev->subordinate) {
-			if (pci_pcie_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE)
-				pnv_ioda_setup_bus_PE(dev->subordinate, true);
-			else
-				pnv_ioda_setup_PEs(dev->subordinate);
-		}
-	}
-}
-
-/*
- * Configure PEs so that the downstream PCI buses and devices
- * could have their associated PE#. Unfortunately, we didn't
- * figure out the way to identify the PLX bridge yet. So we
- * simply put the PCI bus and the subordinate behind the root
- * port to PE# here. The game rule here is expected to be changed
- * as soon as we can detected PLX bridge correctly.
- */
 static void pnv_pci_ioda_setup_PEs(void)
 {
 	struct pci_controller *hose, *tmp;
@@ -1185,22 +1187,12 @@ static void pnv_pci_ioda_setup_PEs(void)
 
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
 		phb = hose->private_data;
+		if (phb->type != PNV_PHB_NPU)
+			continue;
 
-		/* M64 layout might affect PE allocation */
-		if (phb->reserve_m64_pe)
-			phb->reserve_m64_pe(hose->bus, NULL, true);
-
-		/*
-		 * On NPU PHB, we expect separate PEs for individual PCI
-		 * functions. PCI bus dependent PEs are required for the
-		 * remaining types of PHBs.
-		 */
-		if (phb->type == PNV_PHB_NPU) {
-			/* PE#0 is needed for error reporting */
-			pnv_ioda_reserve_pe(phb, 0);
-			pnv_ioda_setup_npu_PEs(hose->bus);
-		} else
-			pnv_ioda_setup_PEs(hose->bus);
+		/* PE#0 is needed for error reporting */
+		pnv_ioda_reserve_pe(phb, 0);
+		pnv_ioda_setup_npu_PEs(hose->bus);
 	}
 }
 
@@ -2552,8 +2544,13 @@ static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl)
 static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 				       struct pnv_ioda_pe *pe)
 {
+	unsigned int weight;
 	int64_t rc;
 
+	weight = pnv_pci_ioda_pe_dma_weight(pe);
+	if (!weight)
+		return;
+
 	/* TVE #1 is selected by PCI address bit 59 */
 	pe->tce_bypass_base = 1ull << 59;
 
@@ -2585,49 +2582,6 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 }
 
-static void pnv_ioda_setup_dma(struct pnv_phb *phb)
-{
-	struct pci_controller *hose = phb->hose;
-	struct pnv_ioda_pe *pe;
-	unsigned int weight;
-
-	/* If we have more PE# than segments available, hand out one
-	 * per PE until we run out and let the rest fail. If not,
-	 * then we assign at least one segment per PE, plus more based
-	 * on the amount of devices under that PE
-	 */
-	pr_info("PCI: Domain %04x has %ld available 32-bit DMA segments\n",
-		hose->global_number, phb->ioda.dma32_count);
-
-	pnv_pci_ioda_setup_opal_tce_kill(phb);
-
-	/* Walk our PE list and configure their DMA segments */
-	list_for_each_entry(pe, &phb->ioda.pe_list, list) {
-		weight = pnv_pci_ioda_pe_dma_weight(pe);
-		if (!weight)
-			continue;
-
-		/*
-		 * For IODA2 compliant PHB3, we needn't care about the weight.
-		 * The all available 32-bits DMA space will be assigned to
-		 * the specific PE.
-		 */
-		if (phb->type == PNV_PHB_IODA1) {
-			pnv_pci_ioda1_setup_dma_pe(phb, pe);
-		} else if (phb->type == PNV_PHB_IODA2) {
-			pe_info(pe, "Assign DMA32 space\n");
-			pnv_pci_ioda2_setup_dma_pe(phb, pe);
-		} else if (phb->type == PNV_PHB_NPU) {
-			/*
-			 * We initialise the DMA space for an NPU PHB
-			 * after setup of the PHB is complete as we
-			 * point the NPU TVT to the the same location
-			 * as the PHB3 TVT.
-			 */
-		}
-	}
-}
-
 #ifdef CONFIG_PCI_MSI
 static void pnv_ioda2_msi_eoi(struct irq_data *d)
 {
@@ -3087,39 +3041,6 @@ static void pnv_ioda_setup_pe_seg(struct pnv_ioda_pe *pe)
 	}
 }
 
-static void pnv_pci_ioda_setup_seg(void)
-{
-	struct pci_controller *tmp, *hose;
-	struct pnv_phb *phb;
-	struct pnv_ioda_pe *pe;
-
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
-		phb = hose->private_data;
-
-		/* NPU PHB does not support IO or MMIO segmentation */
-		if (phb->type == PNV_PHB_NPU)
-			continue;
-
-		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
-			pnv_ioda_setup_pe_seg(pe);
-		}
-	}
-}
-
-static void pnv_pci_ioda_setup_DMA(void)
-{
-	struct pci_controller *hose, *tmp;
-	struct pnv_phb *phb;
-
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
-		pnv_ioda_setup_dma(hose->private_data);
-
-		/* Mark the PHB initialization done */
-		phb = hose->private_data;
-		phb->initialized = 1;
-	}
-}
-
 static void pnv_pci_ioda_create_dbgfs(void)
 {
 #ifdef CONFIG_DEBUG_FS
@@ -3130,6 +3051,9 @@ static void pnv_pci_ioda_create_dbgfs(void)
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
 		phb = hose->private_data;
 
+		/* Notify initialization of PHB done */
+		phb->initialized = 1;
+
 		sprintf(name, "PCI%04x", hose->global_number);
 		phb->dbgfs = debugfs_create_dir(name, powerpc_debugfs_root);
 		if (!phb->dbgfs)
@@ -3168,9 +3092,6 @@ static void pnv_npu_ioda_fixup(void)
 static void pnv_pci_ioda_fixup(void)
 {
 	pnv_pci_ioda_setup_PEs();
-	pnv_pci_ioda_setup_seg();
-	pnv_pci_ioda_setup_DMA();
-
 	pnv_pci_ioda_create_dbgfs();
 
 #ifdef CONFIG_EEH
@@ -3223,6 +3144,104 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
 	return phb->ioda.io_segsize;
 }
 
+/*
+ * We are updating root port or the upstream port of the
+ * bridge behind the root port with PHB's windows in order
+ * to accommodate the changes on required resources during
+ * PCI (slot) hotplug, which is connected to either root
+ * port or the downstream ports of PCIe switch behind the
+ * root port.
+ */
+static void pnv_pci_fixup_bridge_resources(struct pci_bus *bus,
+					   unsigned long type)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pci_dev *bridge = bus->self;
+	struct resource *r, *w;
+	int i;
+
+	/* Check if we need apply fixup to the bridge's windows */
+	if (!pci_is_root_bus(bridge->bus) &&
+	    !pci_is_root_bus(bridge->bus->self->bus))
+		return;
+
+	/* Fixup the resources */
+	for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) {
+		r = &bridge->resource[PCI_BRIDGE_RESOURCES + i];
+		if (!r->flags || !r->parent)
+			continue;
+
+		w = NULL;
+		if (r->flags & type & IORESOURCE_IO)
+			w = &hose->io_resource;
+		else if (pnv_pci_is_mem_pref_64(r->flags) &&
+			 (type & IORESOURCE_PREFETCH) &&
+			 phb->ioda.m64_segsize)
+			w = &hose->mem_resources[1];
+		else if (r->flags & type & IORESOURCE_MEM)
+			w = &hose->mem_resources[0];
+
+		r->start = w->start;
+		r->end = w->end;
+	}
+}
+
+static void pnv_pci_setup_bridge(struct pci_bus *bus,
+				 unsigned long type)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pci_dev *bridge = bus->self;
+	struct pnv_ioda_pe *pe;
+	bool all = (pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE);
+
+	 /* The PE for root bus should be realized before any one else */
+	if (!phb->ioda.root_pe_populated) {
+		pe = pnv_ioda_setup_bus_PE(phb->hose->bus, false);
+		if (pe) {
+			phb->ioda.root_pe_idx = pe->pe_number;
+			phb->ioda.root_pe_populated = true;
+		}
+	}
+
+	/* Extend bridge's windows if necessary */
+	pnv_pci_fixup_bridge_resources(bus, type);
+
+	/* Don't assign PE to PCI bus, which doesn't have subordinate devices */
+	if (list_empty(&bus->devices))
+		return;
+
+	/* Reserve PEs according to used M64 resources */
+	if (phb->reserve_m64_pe)
+		phb->reserve_m64_pe(bus, NULL, all);
+
+	/*
+	 * Assign PE. We might run here because of partial hotplug.
+	 * For the case, we just pick up the existing PE and should
+	 * not allocate resources again.
+	 */
+	pe = pnv_ioda_setup_bus_PE(bus, all);
+	if (!pe)
+		return;
+
+	/* Setup MMIO mapping */
+	pnv_ioda_setup_pe_seg(pe);
+
+	/* Setup DMA */
+	switch (phb->type) {
+	case PNV_PHB_IODA1:
+		pnv_pci_ioda1_setup_dma_pe(phb, pe);
+		break;
+	case PNV_PHB_IODA2:
+		pnv_pci_ioda2_setup_dma_pe(phb, pe);
+		break;
+	default:
+		pr_warn("%s: No DMA for PHB#%d (type %d)\n",
+			__func__, phb->hose->global_number, phb->type);
+	}
+}
+
 #ifdef CONFIG_PCI_IOV
 static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev,
 						      int resno)
@@ -3300,6 +3319,7 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 #endif
 	.enable_device_hook	= pnv_pci_enable_device_hook,
 	.window_alignment	= pnv_pci_window_alignment,
+	.setup_bridge		= pnv_pci_setup_bridge,
 	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
 	.dma_set_mask		= pnv_pci_ioda_dma_set_mask,
 	.dma_get_required_mask	= pnv_pci_ioda_dma_get_required_mask,
@@ -3388,6 +3408,9 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	if (phb->regs == NULL)
 		pr_err("  Failed to map registers !\n");
 
+	/* Initialize TCE kill register */
+	pnv_pci_ioda_setup_opal_tce_kill(phb);
+
 	/* Initialize more IODA stuff */
 	phb->ioda.total_pe_num = 1;
 	prop32 = of_get_property(np, "ibm,opal-num-pes", NULL);
@@ -3451,7 +3474,22 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 			phb->ioda.dma32_segmap[i] = IODA_INVALID_PE;
 	}
 	phb->ioda.pe_array = aux + pemap_off;
-	set_bit(phb->ioda.reserved_pe_idx, phb->ioda.pe_alloc);
+
+	/*
+	 * Choose PE number for root bus, which shouldn't have
+	 * M64 resources consumed by its child devices. To pick
+	 * the PE number adjacent to the reserved one if possible.
+	 */
+	pnv_ioda_reserve_pe(phb, phb->ioda.reserved_pe_idx);
+	if (phb->ioda.reserved_pe_idx == 0) {
+		phb->ioda.root_pe_idx = 1;
+		pnv_ioda_reserve_pe(phb, phb->ioda.root_pe_idx);
+	} else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1)) {
+		phb->ioda.root_pe_idx = phb->ioda.reserved_pe_idx - 1;
+		pnv_ioda_reserve_pe(phb, phb->ioda.root_pe_idx);
+	} else {
+		phb->ioda.root_pe_idx = IODA_INVALID_PE;
+	}
 
 	INIT_LIST_HEAD(&phb->ioda.pe_list);
 	mutex_init(&phb->ioda.pe_list_mutex);
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index ef9924a..01f2428 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -118,6 +118,8 @@ struct pnv_phb {
 		/* Global bridge info */
 		unsigned int		total_pe_num;
 		unsigned int		reserved_pe_idx;
+		unsigned int		root_pe_idx;
+		bool			root_pe_populated;
 
 		/* 32-bit MMIO window */
 		unsigned int		m32_size;
-- 
2.1.0