1 files changed, 694 insertions, 95 deletions

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index de19edeaa7a7..468a0f23c7f2 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -36,41 +36,44 @@
 #include <asm/tce.h>
 #include <asm/xics.h>
 #include <asm/debug.h>
+#include <asm/firmware.h>
+#include <asm/pnv-pci.h>
+
+#include <misc/cxl.h>
 
 #include "powernv.h"
 #include "pci.h"
 
-#define define_pe_printk_level(func, kern_level)		\
-static int func(const struct pnv_ioda_pe *pe, const char *fmt, ...)	\
-{								\
-	struct va_format vaf;					\
-	va_list args;						\
-	char pfix[32];						\
-	int r;							\
-								\
-	va_start(args, fmt);					\
-								\
-	vaf.fmt = fmt;						\
-	vaf.va = &args;						\
-								\
-	if (pe->pdev)						\
-		strlcpy(pfix, dev_name(&pe->pdev->dev),		\
-			sizeof(pfix));				\
-	else							\
-		sprintf(pfix, "%04x:%02x     ",			\
-			pci_domain_nr(pe->pbus),		\
-			pe->pbus->number);			\
-	r = printk(kern_level "pci %s: [PE# %.3d] %pV",		\
-		   pfix, pe->pe_number, &vaf);			\
-								\
-	va_end(args);						\
-								\
-	return r;						\
-}								\
-
-define_pe_printk_level(pe_err, KERN_ERR);
-define_pe_printk_level(pe_warn, KERN_WARNING);
-define_pe_printk_level(pe_info, KERN_INFO);
+static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
+			    const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	char pfix[32];
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	if (pe->pdev)
+		strlcpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix));
+	else
+		sprintf(pfix, "%04x:%02x     ",
+			pci_domain_nr(pe->pbus), pe->pbus->number);
+
+	printk("%spci %s: [PE# %.3d] %pV",
+	       level, pfix, pe->pe_number, &vaf);
+
+	va_end(args);
+}
+
+#define pe_err(pe, fmt, ...)					\
+	pe_level_printk(pe, KERN_ERR, fmt, ##__VA_ARGS__)
+#define pe_warn(pe, fmt, ...)					\
+	pe_level_printk(pe, KERN_WARNING, fmt, ##__VA_ARGS__)
+#define pe_info(pe, fmt, ...)					\
+	pe_level_printk(pe, KERN_INFO, fmt, ##__VA_ARGS__)
 
 /*
  * stdcix is only supposed to be used in hypervisor real mode as per
@@ -82,6 +85,12 @@ static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr)
 		: : "r" (val), "r" (paddr) : "memory");
 }
 
+static inline bool pnv_pci_is_mem_pref_64(unsigned long flags)
+{
+	return ((flags & (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)) ==
+		(IORESOURCE_MEM_64 | IORESOURCE_PREFETCH));
+}
+
 static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
 	unsigned long pe;
@@ -106,6 +115,380 @@ static void pnv_ioda_free_pe(struct pnv_phb *phb, int pe)
 	clear_bit(pe, phb->ioda.pe_alloc);
 }
 
+/* The default M64 BAR is shared by all PEs */
+static int pnv_ioda2_init_m64(struct pnv_phb *phb)
+{
+	const char *desc;
+	struct resource *r;
+	s64 rc;
+
+	/* Configure the default M64 BAR */
+	rc = opal_pci_set_phb_mem_window(phb->opal_id,
+					 OPAL_M64_WINDOW_TYPE,
+					 phb->ioda.m64_bar_idx,
+					 phb->ioda.m64_base,
+					 0, /* unused */
+					 phb->ioda.m64_size);
+	if (rc != OPAL_SUCCESS) {
+		desc = "configuring";
+		goto fail;
+	}
+
+	/* Enable the default M64 BAR */
+	rc = opal_pci_phb_mmio_enable(phb->opal_id,
+				      OPAL_M64_WINDOW_TYPE,
+				      phb->ioda.m64_bar_idx,
+				      OPAL_ENABLE_M64_SPLIT);
+	if (rc != OPAL_SUCCESS) {
+		desc = "enabling";
+		goto fail;
+	}
+
+	/* Mark the M64 BAR assigned */
+	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.
+	 */
+	r = &phb->hose->mem_resources[1];
+	if (phb->ioda.reserved_pe == 0)
+		r->start += phb->ioda.m64_segsize;
+	else if (phb->ioda.reserved_pe == (phb->ioda.total_pe - 1))
+		r->end -= phb->ioda.m64_segsize;
+	else
+		pr_warn("  Cannot strip M64 segment for reserved PE#%d\n",
+			phb->ioda.reserved_pe);
+
+	return 0;
+
+fail:
+	pr_warn("  Failure %lld %s M64 BAR#%d\n",
+		rc, desc, phb->ioda.m64_bar_idx);
+	opal_pci_phb_mmio_enable(phb->opal_id,
+				 OPAL_M64_WINDOW_TYPE,
+				 phb->ioda.m64_bar_idx,
+				 OPAL_DISABLE_M64);
+	return -EIO;
+}
+
+static void pnv_ioda2_alloc_m64_pe(struct pnv_phb *phb)
+{
+	resource_size_t sgsz = phb->ioda.m64_segsize;
+	struct pci_dev *pdev;
+	struct resource *r;
+	int base, step, i;
+
+	/*
+	 * Root bus always has full M64 range and root port has
+	 * M64 range used in reality. So we're checking root port
+	 * instead of root bus.
+	 */
+	list_for_each_entry(pdev, &phb->hose->bus->devices, bus_list) {
+		for (i = PCI_BRIDGE_RESOURCES;
+		     i <= PCI_BRIDGE_RESOURCE_END; i++) {
+			r = &pdev->resource[i];
+			if (!r->parent ||
+			    !pnv_pci_is_mem_pref_64(r->flags))
+				continue;
+
+			base = (r->start - phb->ioda.m64_base) / sgsz;
+			for (step = 0; step < resource_size(r) / sgsz; step++)
+				set_bit(base + step, phb->ioda.pe_alloc);
+		}
+	}
+}
+
+static int pnv_ioda2_pick_m64_pe(struct pnv_phb *phb,
+				 struct pci_bus *bus, int all)
+{
+	resource_size_t segsz = phb->ioda.m64_segsize;
+	struct pci_dev *pdev;
+	struct resource *r;
+	struct pnv_ioda_pe *master_pe, *pe;
+	unsigned long size, *pe_alloc;
+	bool found;
+	int start, i, j;
+
+	/* Root bus shouldn't use M64 */
+	if (pci_is_root_bus(bus))
+		return IODA_INVALID_PE;
+
+	/* We support only one M64 window on each bus */
+	found = false;
+	pci_bus_for_each_resource(bus, r, i) {
+		if (r && r->parent &&
+		    pnv_pci_is_mem_pref_64(r->flags)) {
+			found = true;
+			break;
+		}
+	}
+
+	/* No M64 window found ? */
+	if (!found)
+		return IODA_INVALID_PE;
+
+	/* Allocate bitmap */
+	size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
+	pe_alloc = kzalloc(size, GFP_KERNEL);
+	if (!pe_alloc) {
+		pr_warn("%s: Out of memory !\n",
+			__func__);
+		return IODA_INVALID_PE;
+	}
+
+	/*
+	 * Figure out reserved PE numbers by the PE
+	 * the its child PEs.
+	 */
+	start = (r->start - phb->ioda.m64_base) / segsz;
+	for (i = 0; i < resource_size(r) / segsz; i++)
+		set_bit(start + i, pe_alloc);
+
+	if (all)
+		goto done;
+
+	/*
+	 * If the PE doesn't cover all subordinate buses,
+	 * we need subtract from reserved PEs for children.
+	 */
+	list_for_each_entry(pdev, &bus->devices, bus_list) {
+		if (!pdev->subordinate)
+			continue;
+
+		pci_bus_for_each_resource(pdev->subordinate, r, i) {
+			if (!r || !r->parent ||
+			    !pnv_pci_is_mem_pref_64(r->flags))
+				continue;
+
+			start = (r->start - phb->ioda.m64_base) / segsz;
+			for (j = 0; j < resource_size(r) / segsz ; j++)
+				clear_bit(start + j, pe_alloc);
+                }
+        }
+
+	/*
+	 * the current bus might not own M64 window and that's all
+	 * contributed by its child buses. For the case, we needn't
+	 * pick M64 dependent PE#.
+	 */
+	if (bitmap_empty(pe_alloc, phb->ioda.total_pe)) {
+		kfree(pe_alloc);
+		return IODA_INVALID_PE;
+	}
+
+	/*
+	 * Figure out the master PE and put all slave PEs to master
+	 * PE's list to form compound PE.
+	 */
+done:
+	master_pe = NULL;
+	i = -1;
+	while ((i = find_next_bit(pe_alloc, phb->ioda.total_pe, i + 1)) <
+		phb->ioda.total_pe) {
+		pe = &phb->ioda.pe_array[i];
+		pe->phb = phb;
+		pe->pe_number = i;
+
+		if (!master_pe) {
+			pe->flags |= PNV_IODA_PE_MASTER;
+			INIT_LIST_HEAD(&pe->slaves);
+			master_pe = pe;
+		} else {
+			pe->flags |= PNV_IODA_PE_SLAVE;
+			pe->master = master_pe;
+			list_add_tail(&pe->list, &master_pe->slaves);
+		}
+	}
+
+	kfree(pe_alloc);
+	return master_pe->pe_number;
+}
+
+static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
+{
+	struct pci_controller *hose = phb->hose;
+	struct device_node *dn = hose->dn;
+	struct resource *res;
+	const u32 *r;
+	u64 pci_addr;
+
+	if (!firmware_has_feature(FW_FEATURE_OPALv3)) {
+		pr_info("  Firmware too old to support M64 window\n");
+		return;
+	}
+
+	r = of_get_property(dn, "ibm,opal-m64-window", NULL);
+	if (!r) {
+		pr_info("  No <ibm,opal-m64-window> on %s\n",
+			dn->full_name);
+		return;
+	}
+
+	/* FIXME: Support M64 for P7IOC */
+	if (phb->type != PNV_PHB_IODA2) {
+		pr_info("  Not support M64 window\n");
+		return;
+	}
+
+	res = &hose->mem_resources[1];
+	res->start = of_translate_address(dn, r + 2);
+	res->end = res->start + of_read_number(r + 4, 2) - 1;
+	res->flags = (IORESOURCE_MEM | IORESOURCE_MEM_64 | IORESOURCE_PREFETCH);
+	pci_addr = of_read_number(r, 2);
+	hose->mem_offset[1] = res->start - pci_addr;
+
+	phb->ioda.m64_size = resource_size(res);
+	phb->ioda.m64_segsize = phb->ioda.m64_size / phb->ioda.total_pe;
+	phb->ioda.m64_base = pci_addr;
+
+	/* Use last M64 BAR to cover M64 window */
+	phb->ioda.m64_bar_idx = 15;
+	phb->init_m64 = pnv_ioda2_init_m64;
+	phb->alloc_m64_pe = pnv_ioda2_alloc_m64_pe;
+	phb->pick_m64_pe = pnv_ioda2_pick_m64_pe;
+}
+
+static void pnv_ioda_freeze_pe(struct pnv_phb *phb, int pe_no)
+{
+	struct pnv_ioda_pe *pe = &phb->ioda.pe_array[pe_no];
+	struct pnv_ioda_pe *slave;
+	s64 rc;
+
+	/* Fetch master PE */
+	if (pe->flags & PNV_IODA_PE_SLAVE) {
+		pe = pe->master;
+		WARN_ON(!pe || !(pe->flags & PNV_IODA_PE_MASTER));
+		pe_no = pe->pe_number;
+	}
+
+	/* Freeze master PE */
+	rc = opal_pci_eeh_freeze_set(phb->opal_id,
+				     pe_no,
+				     OPAL_EEH_ACTION_SET_FREEZE_ALL);
+	if (rc != OPAL_SUCCESS) {
+		pr_warn("%s: Failure %lld freezing PHB#%x-PE#%x\n",
+			__func__, rc, phb->hose->global_number, pe_no);
+		return;
+	}
+
+	/* Freeze slave PEs */
+	if (!(pe->flags & PNV_IODA_PE_MASTER))
+		return;
+
+	list_for_each_entry(slave, &pe->slaves, list) {
+		rc = opal_pci_eeh_freeze_set(phb->opal_id,
+					     slave->pe_number,
+					     OPAL_EEH_ACTION_SET_FREEZE_ALL);
+		if (rc != OPAL_SUCCESS)
+			pr_warn("%s: Failure %lld freezing PHB#%x-PE#%x\n",
+				__func__, rc, phb->hose->global_number,
+				slave->pe_number);
+	}
+}
+
+static int pnv_ioda_unfreeze_pe(struct pnv_phb *phb, int pe_no, int opt)
+{
+	struct pnv_ioda_pe *pe, *slave;
+	s64 rc;
+
+	/* Find master PE */
+	pe = &phb->ioda.pe_array[pe_no];
+	if (pe->flags & PNV_IODA_PE_SLAVE) {
+		pe = pe->master;
+		WARN_ON(!pe || !(pe->flags & PNV_IODA_PE_MASTER));
+		pe_no = pe->pe_number;
+	}
+
+	/* Clear frozen state for master PE */
+	rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no, opt);
+	if (rc != OPAL_SUCCESS) {
+		pr_warn("%s: Failure %lld clear %d on PHB#%x-PE#%x\n",
+			__func__, rc, opt, phb->hose->global_number, pe_no);
+		return -EIO;
+	}
+
+	if (!(pe->flags & PNV_IODA_PE_MASTER))
+		return 0;
+
+	/* Clear frozen state for slave PEs */
+	list_for_each_entry(slave, &pe->slaves, list) {
+		rc = opal_pci_eeh_freeze_clear(phb->opal_id,
+					     slave->pe_number,
+					     opt);
+		if (rc != OPAL_SUCCESS) {
+			pr_warn("%s: Failure %lld clear %d on PHB#%x-PE#%x\n",
+				__func__, rc, opt, phb->hose->global_number,
+				slave->pe_number);
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+static int pnv_ioda_get_pe_state(struct pnv_phb *phb, int pe_no)
+{
+	struct pnv_ioda_pe *slave, *pe;
+	u8 fstate, state;
+	__be16 pcierr;
+	s64 rc;
+
+	/* Sanity check on PE number */
+	if (pe_no < 0 || pe_no >= phb->ioda.total_pe)
+		return OPAL_EEH_STOPPED_PERM_UNAVAIL;
+
+	/*
+	 * Fetch the master PE and the PE instance might be
+	 * not initialized yet.
+	 */
+	pe = &phb->ioda.pe_array[pe_no];
+	if (pe->flags & PNV_IODA_PE_SLAVE) {
+		pe = pe->master;
+		WARN_ON(!pe || !(pe->flags & PNV_IODA_PE_MASTER));
+		pe_no = pe->pe_number;
+	}
+
+	/* Check the master PE */
+	rc = opal_pci_eeh_freeze_status(phb->opal_id, pe_no,
+					&state, &pcierr, NULL);
+	if (rc != OPAL_SUCCESS) {
+		pr_warn("%s: Failure %lld getting "
+			"PHB#%x-PE#%x state\n",
+			__func__, rc,
+			phb->hose->global_number, pe_no);
+		return OPAL_EEH_STOPPED_TEMP_UNAVAIL;
+	}
+
+	/* Check the slave PE */
+	if (!(pe->flags & PNV_IODA_PE_MASTER))
+		return state;
+
+	list_for_each_entry(slave, &pe->slaves, list) {
+		rc = opal_pci_eeh_freeze_status(phb->opal_id,
+						slave->pe_number,
+						&fstate,
+						&pcierr,
+						NULL);
+		if (rc != OPAL_SUCCESS) {
+			pr_warn("%s: Failure %lld getting "
+				"PHB#%x-PE#%x state\n",
+				__func__, rc,
+				phb->hose->global_number, slave->pe_number);
+			return OPAL_EEH_STOPPED_TEMP_UNAVAIL;
+		}
+
+		/*
+		 * Override the result based on the ascending
+		 * priority.
+		 */
+		if (fstate > state)
+			state = fstate;
+	}
+
+	return state;
+}
+
 /* Currently those 2 are only used when MSIs are enabled, this will change
  * but in the meantime, we need to protect them to avoid warnings
  */
@@ -363,9 +746,16 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
 	struct pci_controller *hose = pci_bus_to_host(bus);
 	struct pnv_phb *phb = hose->private_data;
 	struct pnv_ioda_pe *pe;
-	int pe_num;
+	int pe_num = IODA_INVALID_PE;
+
+	/* Check if PE is determined by M64 */
+	if (phb->pick_m64_pe)
+		pe_num = phb->pick_m64_pe(phb, bus, all);
+
+	/* The PE number isn't pinned by M64 */
+	if (pe_num == IODA_INVALID_PE)
+		pe_num = pnv_ioda_alloc_pe(phb);
 
-	pe_num = pnv_ioda_alloc_pe(phb);
 	if (pe_num == IODA_INVALID_PE) {
 		pr_warning("%s: Not enough PE# available for PCI bus %04x:%02x\n",
 			__func__, pci_domain_nr(bus), bus->number);
@@ -373,7 +763,7 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
 	}
 
 	pe = &phb->ioda.pe_array[pe_num];
-	pe->flags = (all ? PNV_IODA_PE_BUS_ALL : PNV_IODA_PE_BUS);
+	pe->flags |= (all ? PNV_IODA_PE_BUS_ALL : PNV_IODA_PE_BUS);
 	pe->pbus = bus;
 	pe->pdev = NULL;
 	pe->tce32_seg = -1;
@@ -441,8 +831,15 @@ static void pnv_ioda_setup_PEs(struct pci_bus *bus)
 static void pnv_pci_ioda_setup_PEs(void)
 {
 	struct pci_controller *hose, *tmp;
+	struct pnv_phb *phb;
 
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		phb = hose->private_data;
+
+		/* M64 layout might affect PE allocation */
+		if (phb->alloc_m64_pe)
+			phb->alloc_m64_pe(phb);
+
 		pnv_ioda_setup_PEs(hose->bus);
 	}
 }
@@ -462,7 +859,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
-	set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+	set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
 }
 
 static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
@@ -491,17 +888,48 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
 		set_dma_ops(&pdev->dev, &dma_iommu_ops);
 		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
 	}
+	*pdev->dev.dma_mask = dma_mask;
 	return 0;
 }
 
-static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
+static u64 pnv_pci_ioda_dma_get_required_mask(struct pnv_phb *phb,
+					      struct pci_dev *pdev)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	struct pnv_ioda_pe *pe;
+	u64 end, mask;
+
+	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
+		return 0;
+
+	pe = &phb->ioda.pe_array[pdn->pe_number];
+	if (!pe->tce_bypass_enabled)
+		return __dma_get_required_mask(&pdev->dev);
+
+
+	end = pe->tce_bypass_base + memblock_end_of_DRAM();
+	mask = 1ULL << (fls64(end) - 1);
+	mask += mask - 1;
+
+	return mask;
+}
+
+static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
+				   struct pci_bus *bus,
+				   bool add_to_iommu_group)
 {
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
-		set_iommu_table_base_and_group(&dev->dev, &pe->tce32_table);
+		if (add_to_iommu_group)
+			set_iommu_table_base_and_group(&dev->dev,
+						       &pe->tce32_table);
+		else
+			set_iommu_table_base(&dev->dev, &pe->tce32_table);
+
 		if (dev->subordinate)
-			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
+					       add_to_iommu_group);
 	}
 }
 
@@ -513,15 +941,16 @@ static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe,
 		(__be64 __iomem *)pe->tce_inval_reg_phys :
 		(__be64 __iomem *)tbl->it_index;
 	unsigned long start, end, inc;
+	const unsigned shift = tbl->it_page_shift;
 
 	start = __pa(startp);
 	end = __pa(endp);
 
 	/* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */
 	if (tbl->it_busno) {
-		start <<= 12;
-		end <<= 12;
-		inc = 128 << 12;
+		start <<= shift;
+		end <<= shift;
+		inc = 128ull << shift;
 		start |= tbl->it_busno;
 		end |= tbl->it_busno;
 	} else if (tbl->it_type & TCE_PCI_SWINV_PAIR) {
@@ -559,18 +988,19 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
 	__be64 __iomem *invalidate = rm ?
 		(__be64 __iomem *)pe->tce_inval_reg_phys :
 		(__be64 __iomem *)tbl->it_index;
+	const unsigned shift = tbl->it_page_shift;
 
 	/* We'll invalidate DMA address in PE scope */
-	start = 0x2ul << 60;
+	start = 0x2ull << 60;
 	start |= (pe->pe_number & 0xFF);
 	end = start;
 
 	/* Figure out the start, end and step */
 	inc = tbl->it_offset + (((u64)startp - tbl->it_base) / sizeof(u64));
-	start |= (inc << 12);
+	start |= (inc << shift);
 	inc = tbl->it_offset + (((u64)endp - tbl->it_base) / sizeof(u64));
-	end |= (inc << 12);
-	inc = (0x1ul << 12);
+	end |= (inc << shift);
+	inc = (0x1ull << shift);
 	mb();
 
 	while (start <= end) {
@@ -654,7 +1084,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	/* Setup linux iommu table */
 	tbl = &pe->tce32_table;
 	pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
-				  base << 28);
+				  base << 28, IOMMU_PAGE_SHIFT_4K);
 
 	/* OPAL variant of P7IOC SW invalidated TCEs */
 	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
@@ -677,7 +1107,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	if (pe->pdev)
 		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
 	else
-		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
 
 	return;
  fail:
@@ -713,11 +1143,15 @@ static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
 						     0);
 
 		/*
-		 * We might want to reset the DMA ops of all devices on
-		 * this PE. However in theory, that shouldn't be necessary
-		 * as this is used for VFIO/KVM pass-through and the device
-		 * hasn't yet been returned to its kernel driver
+		 * EEH needs the mapping between IOMMU table and group
+		 * of those VFIO/KVM pass-through devices. We can postpone
+		 * resetting DMA ops until the DMA mask is configured in
+		 * host side.
 		 */
+		if (pe->pdev)
+			set_iommu_table_base(&pe->pdev->dev, tbl);
+		else
+			pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
 	}
 	if (rc)
 		pe_err(pe, "OPAL error %lld configuring bypass window\n", rc);
@@ -784,7 +1218,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 
 	/* Setup linux iommu table */
 	tbl = &pe->tce32_table;
-	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0);
+	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0,
+			IOMMU_PAGE_SHIFT_4K);
 
 	/* OPAL variant of PHB3 invalidated TCEs */
 	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
@@ -805,7 +1240,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	if (pe->pdev)
 		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
 	else
-		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
 
 	/* Also create a bypass window */
 	pnv_pci_ioda2_setup_bypass_pe(phb, pe);
@@ -895,14 +1330,186 @@ static void pnv_ioda2_msi_eoi(struct irq_data *d)
 	icp_native_eoi(d);
 }
 
+
+static void set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
+{
+	struct irq_data *idata;
+	struct irq_chip *ichip;
+
+	if (phb->type != PNV_PHB_IODA2)
+		return;
+
+	if (!phb->ioda.irq_chip_init) {
+		/*
+		 * First time we setup an MSI IRQ, we need to setup the
+		 * corresponding IRQ chip to route correctly.
+		 */
+		idata = irq_get_irq_data(virq);
+		ichip = irq_data_get_irq_chip(idata);
+		phb->ioda.irq_chip_init = 1;
+		phb->ioda.irq_chip = *ichip;
+		phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
+	}
+	irq_set_chip(virq, &phb->ioda.irq_chip);
+}
+
+#ifdef CONFIG_CXL_BASE
+
+struct device_node *pnv_pci_to_phb_node(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+
+	return hose->dn;
+}
+EXPORT_SYMBOL(pnv_pci_to_phb_node);
+
+int pnv_phb_to_cxl(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pnv_ioda_pe *pe;
+	int rc;
+
+	pe = pnv_ioda_get_pe(dev);
+	if (!pe)
+		return -ENODEV;
+
+	pe_info(pe, "Switching PHB to CXL\n");
+
+	rc = opal_pci_set_phb_cxl_mode(phb->opal_id, 1, pe->pe_number);
+	if (rc)
+		dev_err(&dev->dev, "opal_pci_set_phb_cxl_mode failed: %i\n", rc);
+
+	return rc;
+}
+EXPORT_SYMBOL(pnv_phb_to_cxl);
+
+/* Find PHB for cxl dev and allocate MSI hwirqs?
+ * Returns the absolute hardware IRQ number
+ */
+int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, num);
+
+	if (hwirq < 0) {
+		dev_warn(&dev->dev, "Failed to find a free MSI\n");
+		return -ENOSPC;
+	}
+
+	return phb->msi_base + hwirq;
+}
+EXPORT_SYMBOL(pnv_cxl_alloc_hwirqs);
+
+void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, num);
+}
+EXPORT_SYMBOL(pnv_cxl_release_hwirqs);
+
+void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
+				  struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int i, hwirq;
+
+	for (i = 1; i < CXL_IRQ_RANGES; i++) {
+		if (!irqs->range[i])
+			continue;
+		pr_devel("cxl release irq range 0x%x: offset: 0x%lx  limit: %ld\n",
+			 i, irqs->offset[i],
+			 irqs->range[i]);
+		hwirq = irqs->offset[i] - phb->msi_base;
+		msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq,
+				       irqs->range[i]);
+	}
+}
+EXPORT_SYMBOL(pnv_cxl_release_hwirq_ranges);
+
+int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
+			       struct pci_dev *dev, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int i, hwirq, try;
+
+	memset(irqs, 0, sizeof(struct cxl_irq_ranges));
+
+	/* 0 is reserved for the multiplexed PSL DSI interrupt */
+	for (i = 1; i < CXL_IRQ_RANGES && num; i++) {
+		try = num;
+		while (try) {
+			hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, try);
+			if (hwirq >= 0)
+				break;
+			try /= 2;
+		}
+		if (!try)
+			goto fail;
+
+		irqs->offset[i] = phb->msi_base + hwirq;
+		irqs->range[i] = try;
+		pr_devel("cxl alloc irq range 0x%x: offset: 0x%lx  limit: %li\n",
+			 i, irqs->offset[i], irqs->range[i]);
+		num -= try;
+	}
+	if (num)
+		goto fail;
+
+	return 0;
+fail:
+	pnv_cxl_release_hwirq_ranges(irqs, dev);
+	return -ENOSPC;
+}
+EXPORT_SYMBOL(pnv_cxl_alloc_hwirq_ranges);
+
+int pnv_cxl_get_irq_count(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	return phb->msi_bmp.irq_count;
+}
+EXPORT_SYMBOL(pnv_cxl_get_irq_count);
+
+int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
+			   unsigned int virq)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	unsigned int xive_num = hwirq - phb->msi_base;
+	struct pnv_ioda_pe *pe;
+	int rc;
+
+	if (!(pe = pnv_ioda_get_pe(dev)))
+		return -ENODEV;
+
+	/* Assign XIVE to PE */
+	rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
+	if (rc) {
+		pe_warn(pe, "%s: OPAL error %d setting msi_base 0x%x "
+			"hwirq 0x%x XIVE 0x%x PE\n",
+			pci_name(dev), rc, phb->msi_base, hwirq, xive_num);
+		return -EIO;
+	}
+	set_msi_irq_chip(phb, virq);
+
+	return 0;
+}
+EXPORT_SYMBOL(pnv_cxl_ioda_msi_setup);
+#endif
+
 static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 				  unsigned int hwirq, unsigned int virq,
 				  unsigned int is_64, struct msi_msg *msg)
 {
 	struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
 	struct pci_dn *pdn = pci_get_pdn(dev);
-	struct irq_data *idata;
-	struct irq_chip *ichip;
 	unsigned int xive_num = hwirq - phb->msi_base;
 	__be32 data;
 	int rc;
@@ -954,22 +1561,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 	}
 	msg->data = be32_to_cpu(data);
 
-	/*
-	 * Change the IRQ chip for the MSI interrupts on PHB3.
-	 * The corresponding IRQ chip should be populated for
-	 * the first time.
-	 */
-	if (phb->type == PNV_PHB_IODA2) {
-		if (!phb->ioda.irq_chip_init) {
-			idata = irq_get_irq_data(virq);
-			ichip = irq_data_get_irq_chip(idata);
-			phb->ioda.irq_chip_init = 1;
-			phb->ioda.irq_chip = *ichip;
-			phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
-		}
-
-		irq_set_chip(virq, &phb->ioda.irq_chip);
-	}
+	set_msi_irq_chip(phb, virq);
 
 	pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d),"
 		 " address=%x_%08x data=%x PE# %d\n",
@@ -1055,9 +1647,6 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose,
 				index++;
 			}
 		} else if (res->flags & IORESOURCE_MEM) {
-			/* WARNING: Assumes M32 is mem region 0 in PHB. We need to
-			 * harden that algorithm when we start supporting M64
-			 */
 			region.start = res->start -
 				       hose->mem_offset[0] -
 				       phb->ioda.m32_pci_base;
@@ -1141,9 +1730,8 @@ static void pnv_pci_ioda_fixup(void)
 	pnv_pci_ioda_create_dbgfs();
 
 #ifdef CONFIG_EEH
-	eeh_probe_mode_set(EEH_PROBE_MODE_DEV);
-	eeh_addr_cache_build();
 	eeh_init();
+	eeh_addr_cache_build();
 #endif
 }
 
@@ -1178,7 +1766,10 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
 		bridge = bridge->bus->self;
 	}
 
-	/* We need support prefetchable memory window later */
+	/* We fail back to M32 if M64 isn't supported */
+	if (phb->ioda.m64_segsize &&
+	    pnv_pci_is_mem_pref_64(type))
+		return phb->ioda.m64_segsize;
 	if (type & IORESOURCE_MEM)
 		return phb->ioda.m32_segsize;
 
@@ -1217,12 +1808,12 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
 
 static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
 {
-	opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET,
+	opal_pci_reset(phb->opal_id, OPAL_RESET_PCI_IODA_TABLE,
 		       OPAL_ASSERT_RESET);
 }
 
-void __init pnv_pci_init_ioda_phb(struct device_node *np,
-				  u64 hub_id, int ioda_type)
+static void __init pnv_pci_init_ioda_phb(struct device_node *np,
+					 u64 hub_id, int ioda_type)
 {
 	struct pci_controller *hose;
 	struct pnv_phb *phb;
@@ -1299,6 +1890,10 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	prop32 = of_get_property(np, "ibm,opal-reserved-pe", NULL);
 	if (prop32)
 		phb->ioda.reserved_pe = be32_to_cpup(prop32);
+
+	/* Parse 64-bit MMIO range */
+	pnv_ioda_parse_m64_window(phb);
+
 	phb->ioda.m32_size = resource_size(&hose->mem_resources[0]);
 	/* FW Has already off top 64k of M32 space (MSI space) */
 	phb->ioda.m32_size += 0x10000;
@@ -1334,14 +1929,6 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	/* Calculate how many 32-bit TCE segments we have */
 	phb->ioda.tce32_count = phb->ioda.m32_pci_base >> 28;
 
-	/* Clear unusable m64 */
-	hose->mem_resources[1].flags = 0;
-	hose->mem_resources[1].start = 0;
-	hose->mem_resources[1].end = 0;
-	hose->mem_resources[2].flags = 0;
-	hose->mem_resources[2].start = 0;
-	hose->mem_resources[2].end = 0;
-
 #if 0 /* We should really do that ... */
 	rc = opal_pci_set_phb_mem_window(opal->phb_id,
 					 window_type,
@@ -1351,14 +1938,21 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 					 segment_size);
 #endif
 
-	pr_info("  %d (%d) PE's M32: 0x%x [segment=0x%x]"
-		" IO: 0x%x [segment=0x%x]\n",
-		phb->ioda.total_pe,
-		phb->ioda.reserved_pe,
-		phb->ioda.m32_size, phb->ioda.m32_segsize,
-		phb->ioda.io_size, phb->ioda.io_segsize);
+	pr_info("  %03d (%03d) PE's M32: 0x%x [segment=0x%x]\n",
+		phb->ioda.total_pe, phb->ioda.reserved_pe,
+		phb->ioda.m32_size, phb->ioda.m32_segsize);
+	if (phb->ioda.m64_size)
+		pr_info("                 M64: 0x%lx [segment=0x%lx]\n",
+			phb->ioda.m64_size, phb->ioda.m64_segsize);
+	if (phb->ioda.io_size)
+		pr_info("                  IO: 0x%x [segment=0x%x]\n",
+			phb->ioda.io_size, phb->ioda.io_segsize);
+
 
 	phb->hose->ops = &pnv_pci_ops;
+	phb->get_pe_state = pnv_ioda_get_pe_state;
+	phb->freeze_pe = pnv_ioda_freeze_pe;
+	phb->unfreeze_pe = pnv_ioda_unfreeze_pe;
 #ifdef CONFIG_EEH
 	phb->eeh_ops = &ioda_eeh_ops;
 #endif
@@ -1369,6 +1963,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
 	phb->dma_set_mask = pnv_pci_ioda_dma_set_mask;
+	phb->dma_get_required_mask = pnv_pci_ioda_dma_get_required_mask;
 
 	/* Setup shutdown function for kexec */
 	phb->shutdown = pnv_pci_ioda_shutdown;
@@ -1390,7 +1985,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 
 	/* Reset IODA tables to a clean state */
-	rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET);
+	rc = opal_pci_reset(phb_id, OPAL_RESET_PCI_IODA_TABLE, OPAL_ASSERT_RESET);
 	if (rc)
 		pr_warning("  OPAL Error %ld performing IODA table reset !\n", rc);
 
@@ -1404,6 +1999,10 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		ioda_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL);
 		ioda_eeh_phb_reset(hose, OPAL_DEASSERT_RESET);
 	}
+
+	/* Configure M64 window */
+	if (phb->init_m64 && phb->init_m64(phb))
+		hose->mem_resources[1].flags = 0;
 }
 
 void __init pnv_pci_init_ioda2_phb(struct device_node *np)