// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Support PCI/PCIe on PowerNV platforms
 *
 * Copyright 2011 Benjamin Herrenschmidt, IBM Corp.
 */

#undef DEBUG

#include <linux/kernel.h>
#include <linux/pci.h>
#include <linux/crash_dump.h>
#include <linux/delay.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/memblock.h>
#include <linux/irq.h>
#include <linux/io.h>
#include <linux/msi.h>
#include <linux/iommu.h>
#include <linux/rculist.h>
#include <linux/sizes.h>

#include <asm/sections.h>
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/pci-bridge.h>
#include <asm/machdep.h>
#include <asm/msi_bitmap.h>
#include <asm/ppc-pci.h>
#include <asm/opal.h>
#include <asm/iommu.h>
#include <asm/tce.h>
#include <asm/xics.h>
#include <asm/debugfs.h>
#include <asm/firmware.h>
#include <asm/pnv-pci.h>
#include <asm/mmzone.h>

#include <misc/cxl-base.h>

#include "powernv.h"
#include "pci.h"
#include "../../../../drivers/pci/pci.h"

#define PNV_IODA1_M64_NUM       16      /* Number of M64 BARs   */
#define PNV_IODA1_M64_SEGS      8       /* Segments per M64 BAR */
#define PNV_IODA1_DMA32_SEGSIZE 0x10000000

static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK",
                                              "NPU_OCAPI" };

static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);

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->flags & PNV_IODA_PE_DEV)
                strlcpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix));
        else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
                sprintf(pfix, "%04x:%02x     ",
                        pci_domain_nr(pe->pbus), pe->pbus->number);
#ifdef CONFIG_PCI_IOV
        else if (pe->flags & PNV_IODA_PE_VF)
                sprintf(pfix, "%04x:%02x:%2x.%d",
                        pci_domain_nr(pe->parent_dev->bus),
                        (pe->rid & 0xff00) >> 8,
                        PCI_SLOT(pe->rid), PCI_FUNC(pe->rid));
#endif /* CONFIG_PCI_IOV*/

        printk("%spci %s: [PE# %.2x] %pV",
               level, pfix, pe->pe_number, &vaf);

        va_end(args);
}

static bool pnv_iommu_bypass_disabled __read_mostly;
static bool pci_reset_phbs __read_mostly;

static int __init iommu_setup(char *str)
{
        if (!str)
                return -EINVAL;

        while (*str) {
                if (!strncmp(str, "nobypass", 8)) {
                        pnv_iommu_bypass_disabled = true;
                        pr_info("PowerNV: IOMMU bypass window disabled.\n");
                        break;
                }
                str += strcspn(str, ",");
                if (*str == ',')
                        str++;
        }

        return 0;
}
early_param("iommu", iommu_setup);

static int __init pci_reset_phbs_setup(char *str)
{
        pci_reset_phbs = true;
        return 0;
}

early_param("ppc_pci_reset_phbs", pci_reset_phbs_setup);

static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r)
{
        /*
         * WARNING: We cannot rely on the resource flags. The Linux PCI
         * allocation code sometimes decides to put a 64-bit prefetchable
         * BAR in the 32-bit window, so we have to compare the addresses.
         *
         * For simplicity we only test resource start.
         */
        return (r->start >= phb->ioda.m64_base &&
                r->start < (phb->ioda.m64_base + phb->ioda.m64_size));
}

static inline bool pnv_pci_is_m64_flags(unsigned long resource_flags)
{
        unsigned long flags = (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH);

        return (resource_flags & flags) == flags;
}

static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no)
{
        s64 rc;

        phb->ioda.pe_array[pe_no].phb = phb;
        phb->ioda.pe_array[pe_no].pe_number = pe_no;

        /*
         * Clear the PE frozen state as it might be put into frozen state
         * in the last PCI remove path. It's not harmful to do so when the
         * PE is already in unfrozen state.
         */
        rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no,
                                       OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
        if (rc != OPAL_SUCCESS && rc != OPAL_UNSUPPORTED)
                pr_warn("%s: Error %lld unfreezing PHB#%x-PE#%x\n",
                        __func__, rc, phb->hose->global_number, pe_no);

        return &phb->ioda.pe_array[pe_no];
}

static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
{
        if (!(pe_no >= 0 && pe_no < phb->ioda.total_pe_num)) {
                pr_warn("%s: Invalid PE %x on PHB#%x\n",
                        __func__, pe_no, phb->hose->global_number);
                return;
        }

        if (test_and_set_bit(pe_no, phb->ioda.pe_alloc))
                pr_debug("%s: PE %x was reserved on PHB#%x\n",
                         __func__, pe_no, phb->hose->global_number);

        pnv_ioda_init_pe(phb, pe_no);
}

static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
{
        long pe;

        for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) {
                if (!test_and_set_bit(pe, phb->ioda.pe_alloc))
                        return pnv_ioda_init_pe(phb, pe);
        }

        return NULL;
}

static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
{
        struct pnv_phb *phb = pe->phb;
        unsigned int pe_num = pe->pe_number;

        WARN_ON(pe->pdev);
        WARN_ON(pe->npucomp); /* NPUs are not supposed to be freed */
        kfree(pe->npucomp);
        memset(pe, 0, sizeof(struct pnv_ioda_pe));
        clear_bit(pe_num, 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;
        }

        /*
         * 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 += (2 * phb->ioda.m64_segsize);
        else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1))
                r->end -= (2 * phb->ioda.m64_segsize);
        else
                pr_warn("  Cannot strip M64 segment for reserved PE#%x\n",
                        phb->ioda.reserved_pe_idx);

        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_ioda_reserve_dev_m64_pe(struct pci_dev *pdev,
                                         unsigned long *pe_bitmap)
{
        struct pci_controller *hose = pci_bus_to_host(pdev->bus);
        struct pnv_phb *phb = hose->private_data;
        struct resource *r;
        resource_size_t base, sgsz, start, end;
        int segno, i;

        base = phb->ioda.m64_base;
        sgsz = phb->ioda.m64_segsize;
        for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
                r = &pdev->resource[i];
                if (!r->parent || !pnv_pci_is_m64(phb, r))
                        continue;

                start = _ALIGN_DOWN(r->start - base, sgsz);
                end = _ALIGN_UP(r->end - base, sgsz);
                for (segno = start / sgsz; segno < end / sgsz; segno++) {
                        if (pe_bitmap)
                                set_bit(segno, pe_bitmap);
                        else
                                pnv_ioda_reserve_pe(phb, segno);
                }
        }
}

static int pnv_ioda1_init_m64(struct pnv_phb *phb)
{
        struct resource *r;
        int index;

        /*
         * There are 16 M64 BARs, each of which has 8 segments. So
         * there are as many M64 segments as the maximum number of
         * PEs, which is 128.
         */
        for (index = 0; index < PNV_IODA1_M64_NUM; index++) {
                unsigned long base, segsz = phb->ioda.m64_segsize;
                int64_t rc;

                base = phb->ioda.m64_base +
                       index * PNV_IODA1_M64_SEGS * segsz;
                rc = opal_pci_set_phb_mem_window(phb->opal_id,
                                OPAL_M64_WINDOW_TYPE, index, base, 0,
                                PNV_IODA1_M64_SEGS * segsz);
                if (rc != OPAL_SUCCESS) {
                        pr_warn("  Error %lld setting M64 PHB#%x-BAR#%d\n",
                                rc, phb->hose->global_number, index);
                        goto fail;
                }

                rc = opal_pci_phb_mmio_enable(phb->opal_id,
                                OPAL_M64_WINDOW_TYPE, index,
                                OPAL_ENABLE_M64_SPLIT);
                if (rc != OPAL_SUCCESS) {
                        pr_warn("  Error %lld enabling M64 PHB#%x-BAR#%d\n",
                                rc, phb->hose->global_number, index);
                        goto fail;
                }
        }

        /*
         * 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 += (2 * phb->ioda.m64_segsize);
        else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1))
                r->end -= (2 * phb->ioda.m64_segsize);
        else
                WARN(1, "Wrong reserved PE#%x on PHB#%x\n",
                     phb->ioda.reserved_pe_idx, phb->hose->global_number);

        return 0;

fail:
        for ( ; index >= 0; index--)
                opal_pci_phb_mmio_enable(phb->opal_id,
                        OPAL_M64_WINDOW_TYPE, index, OPAL_DISABLE_M64);

        return -EIO;
}

static void pnv_ioda_reserve_m64_pe(struct pci_bus *bus,
                                    unsigned long *pe_bitmap,
                                    bool all)
{
        struct pci_dev *pdev;

        list_for_each_entry(pdev, &bus->devices, bus_list) {
                pnv_ioda_reserve_dev_m64_pe(pdev, pe_bitmap);

                if (all && pdev->subordinate)
                        pnv_ioda_reserve_m64_pe(pdev->subordinate,
                                                pe_bitmap, all);
        }
}

static struct pnv_ioda_pe *pnv_ioda_pick_m64_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 *master_pe, *pe;
        unsigned long size, *pe_alloc;
        int i;

        /* Root bus shouldn't use M64 */
        if (pci_is_root_bus(bus))
                return NULL;

        /* Allocate bitmap */
        size = _ALIGN_UP(phb->ioda.total_pe_num / 8, sizeof(unsigned long));
        pe_alloc = kzalloc(size, GFP_KERNEL);
        if (!pe_alloc) {
                pr_warn("%s: Out of memory !\n",
                        __func__);
                return NULL;
        }

        /* Figure out reserved PE numbers by the PE */
        pnv_ioda_reserve_m64_pe(bus, pe_alloc, all);

        /*
         * 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_num)) {
                kfree(pe_alloc);
                return NULL;
        }

        /*
         * Figure out the master PE and put all slave PEs to master
         * PE's list to form compound PE.
         */
        master_pe = NULL;
        i = -1;
        while ((i = find_next_bit(pe_alloc, phb->ioda.total_pe_num, i + 1)) <
                phb->ioda.total_pe_num) {
                pe = &phb->ioda.pe_array[i];

                phb->ioda.m64_segmap[pe->pe_number] = pe->pe_number;
                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);
                }

                /*
                 * P7IOC supports M64DT, which helps mapping M64 segment
                 * to one particular PE#. However, PHB3 has fixed mapping
                 * between M64 segment and PE#. In order to have same logic
                 * for P7IOC and PHB3, we enforce fixed mapping between M64
                 * segment and PE# on P7IOC.
                 */
                if (phb->type == PNV_PHB_IODA1) {
                        int64_t rc;

                        rc = opal_pci_map_pe_mmio_window(phb->opal_id,
                                        pe->pe_number, OPAL_M64_WINDOW_TYPE,
                                        pe->pe_number / PNV_IODA1_M64_SEGS,
                                        pe->pe_number % PNV_IODA1_M64_SEGS);
                        if (rc != OPAL_SUCCESS)
                                pr_warn("%s: Error %lld mapping M64 for PHB#%x-PE#%x\n",
                                        __func__, rc, phb->hose->global_number,
                                        pe->pe_number);
                }
        }

        kfree(pe_alloc);
        return master_pe;
}

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;
        u32 m64_range[2], i;
        const __be32 *r;
        u64 pci_addr;

        if (phb->type != PNV_PHB_IODA1 && phb->type != PNV_PHB_IODA2) {
                pr_info("  Not support M64 window\n");
                return;
        }

        if (!firmware_has_feature(FW_FEATURE_OPAL)) {
                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 %pOF\n",
                        dn);
                return;
        }

        /*
         * Find the available M64 BAR range and pickup the last one for
         * covering the whole 64-bits space. We support only one range.
         */
        if (of_property_read_u32_array(dn, "ibm,opal-available-m64-ranges",
                                       m64_range, 2)) {
                /* In absence of the property, assume 0..15 */
                m64_range[0] = 0;
                m64_range[1] = 16;
        }
        /* We only support 64 bits in our allocator */
        if (m64_range[1] > 63) {
                pr_warn("%s: Limiting M64 range to 63 (from %d) on PHB#%x\n",
                        __func__, m64_range[1], phb->hose->global_number);
                m64_range[1] = 63;
        }
        /* Empty range, no m64 */
        if (m64_range[1] <= m64_range[0]) {
                pr_warn("%s: M64 empty, disabling M64 usage on PHB#%x\n",
                        __func__, phb->hose->global_number);
                return;
        }

        /* Configure M64 informations */
        res = &hose->mem_resources[1];
        res->name = dn->full_name;
        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_num;
        phb->ioda.m64_base = pci_addr;

        /* This lines up nicely with the display from processing OF ranges */
        pr_info(" MEM 0x%016llx..0x%016llx -> 0x%016llx (M64 #%d..%d)\n",
                res->start, res->end, pci_addr, m64_range[0],
                m64_range[0] + m64_range[1] - 1);

        /* Mark all M64 used up by default */
        phb->ioda.m64_bar_alloc = (unsigned long)-1;

        /* Use last M64 BAR to cover M64 window */
        m64_range[1]--;
        phb->ioda.m64_bar_idx = m64_range[0] + m64_range[1];

        pr_info(" Using M64 #%d as default window\n", phb->ioda.m64_bar_idx);

        /* Mark remaining ones free */
        for (i = m64_range[0]; i < m64_range[1]; i++)
                clear_bit(i, &phb->ioda.m64_bar_alloc);

        /*
         * Setup init functions for M64 based on IODA version, IODA3 uses
         * the IODA2 code.
         */
        if (phb->type == PNV_PHB_IODA1)
                phb->init_m64 = pnv_ioda1_init_m64;
        else
                phb->init_m64 = pnv_ioda2_init_m64;
}

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;
                if (WARN_ON(!pe || !(pe->flags & PNV_IODA_PE_MASTER)))
                        return;

                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 = 0, state;
        __be16 pcierr = 0;
        s64 rc;

        /* Sanity check on PE number */
        if (pe_no < 0 || pe_no >= phb->ioda.total_pe_num)
                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;
}

struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev)
{
        struct pci_controller *hose = pci_bus_to_host(dev->bus);
        struct pnv_phb *phb = hose->private_data;
        struct pci_dn *pdn = pci_get_pdn(dev);

        if (!pdn)
                return NULL;
        if (pdn->pe_number == IODA_INVALID_PE)
                return NULL;
        return &phb->ioda.pe_array[pdn->pe_number];
}

static int pnv_ioda_set_one_peltv(struct pnv_phb *phb,
                                  struct pnv_ioda_pe *parent,
                                  struct pnv_ioda_pe *child,
                                  bool is_add)
{
        const char *desc = is_add ? "adding" : "removing";
        uint8_t op = is_add ? OPAL_ADD_PE_TO_DOMAIN :
                              OPAL_REMOVE_PE_FROM_DOMAIN;
        struct pnv_ioda_pe *slave;
        long rc;

        /* Parent PE affects child PE */
        rc = opal_pci_set_peltv(phb->opal_id, parent->pe_number,
                                child->pe_number, op);
        if (rc != OPAL_SUCCESS) {
                pe_warn(child, "OPAL error %ld %s to parent PELTV\n",
                        rc, desc);
                return -ENXIO;
        }

        if (!(child->flags & PNV_IODA_PE_MASTER))
                return 0;

        /* Compound case: parent PE affects slave PEs */
        list_for_each_entry(slave, &child->slaves, list) {
                rc = opal_pci_set_peltv(phb->opal_id, parent->pe_number,
                                        slave->pe_number, op);
                if (rc != OPAL_SUCCESS) {
                        pe_warn(slave, "OPAL error %ld %s to parent PELTV\n",
                                rc, desc);
                        return -ENXIO;
                }
        }

        return 0;
}

static int pnv_ioda_set_peltv(struct pnv_phb *phb,
                              struct pnv_ioda_pe *pe,
                              bool is_add)
{
        struct pnv_ioda_pe *slave;
        struct pci_dev *pdev = NULL;
        int ret;

        /*
         * Clear PE frozen state. If it's master PE, we need
         * clear slave PE frozen state as well.
         */
        if (is_add) {
                opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
                                          OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
                if (pe->flags & PNV_IODA_PE_MASTER) {
                        list_for_each_entry(slave, &pe->slaves, list)
                                opal_pci_eeh_freeze_clear(phb->opal_id,
                                                          slave->pe_number,
                                                          OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
                }
        }

        /*
         * Associate PE in PELT. We need add the PE into the
         * corresponding PELT-V as well. Otherwise, the error
         * originated from the PE might contribute to other
         * PEs.
         */
        ret = pnv_ioda_set_one_peltv(phb, pe, pe, is_add);
        if (ret)
                return ret;

        /* For compound PEs, any one affects all of them */
        if (pe->flags & PNV_IODA_PE_MASTER) {
                list_for_each_entry(slave, &pe->slaves, list) {
                        ret = pnv_ioda_set_one_peltv(phb, slave, pe, is_add);
                        if (ret)
                                return ret;
                }
        }

        if (pe->flags & (PNV_IODA_PE_BUS_ALL | PNV_IODA_PE_BUS))
                pdev = pe->pbus->self;
        else if (pe->flags & PNV_IODA_PE_DEV)
                pdev = pe->pdev->bus->self;
#ifdef CONFIG_PCI_IOV
        else if (pe->flags & PNV_IODA_PE_VF)
                pdev = pe->parent_dev;
#endif /* CONFIG_PCI_IOV */
        while (pdev) {
                struct pci_dn *pdn = pci_get_pdn(pdev);
                struct pnv_ioda_pe *parent;

                if (pdn && pdn->pe_number != IODA_INVALID_PE) {
                        parent = &phb->ioda.pe_array[pdn->pe_number];
                        ret = pnv_ioda_set_one_peltv(phb, parent, pe, is_add);
                        if (ret)
                                return ret;
                }

                pdev = pdev->bus->self;
        }

        return 0;
}

static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
{
        struct pci_dev *parent;
        uint8_t bcomp, dcomp, fcomp;
        int64_t rc;
        long rid_end, rid;

        /* Currently, we just deconfigure VF PE. Bus PE will always there.*/
        if (pe->pbus) {
                int count;

                dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER;
                fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
                parent = pe->pbus->self;
                if (pe->flags & PNV_IODA_PE_BUS_ALL)
                        count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
                else
                        count = 1;

                switch(count) {
                case  1: bcomp = OpalPciBusAll;         break;
                case  2: bcomp = OpalPciBus7Bits;       break;
                case  4: bcomp = OpalPciBus6Bits;       break;
                case  8: bcomp = OpalPciBus5Bits;       break;
                case 16: bcomp = OpalPciBus4Bits;       break;
                case 32: bcomp = OpalPciBus3Bits;       break;
                default:
                        dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n",
                                count);
                        /* Do an exact match only */
                        bcomp = OpalPciBusAll;
                }
                rid_end = pe->rid + (count << 8);
        } else {
#ifdef CONFIG_PCI_IOV
                if (pe->flags & PNV_IODA_PE_VF)
                        parent = pe->parent_dev;
                else
#endif
                        parent = pe->pdev->bus->self;
                bcomp = OpalPciBusAll;
                dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER;
                fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER;
                rid_end = pe->rid + 1;
        }

        /* Clear the reverse map */
        for (rid = pe->rid; rid < rid_end; rid++)
                phb->ioda.pe_rmap[rid] = IODA_INVALID_PE;

        /* Release from all parents PELT-V */
        while (parent) {
                struct pci_dn *pdn = pci_get_pdn(parent);
                if (pdn && pdn->pe_number != IODA_INVALID_PE) {
                        rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
                                                pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
                        /* XXX What to do in case of error ? */
                }
                parent = parent->bus->self;
        }

        opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
                                  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);

        /* Disassociate PE in PELT */
        rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
                                pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
        if (rc)
                pe_warn(pe, "OPAL error %lld remove self from PELTV\n", rc);
        rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
                             bcomp, dcomp, fcomp, OPAL_UNMAP_PE);
        if (rc)
                pe_err(pe, "OPAL error %lld trying to setup PELT table\n", rc);

        pe->pbus = NULL;
        pe->pdev = NULL;
#ifdef CONFIG_PCI_IOV
        pe->parent_dev = NULL;
#endif

        return 0;
}

static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
{
        struct pci_dev *parent;
        uint8_t bcomp, dcomp, fcomp;
        long rc, rid_end, rid;

        /* Bus validation ? */
        if (pe->pbus) {
                int count;

                dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER;
                fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
                parent = pe->pbus->self;
                if (pe->flags & PNV_IODA_PE_BUS_ALL)
                        count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
                else
                        count = 1;

                switch(count) {
                case  1: bcomp = OpalPciBusAll;         break;
                case  2: bcomp = OpalPciBus7Bits;       break;
                case  4: bcomp = OpalPciBus6Bits;       break;
                case  8: bcomp = OpalPciBus5Bits;       break;
                case 16: bcomp = OpalPciBus4Bits;       break;
                case 32: bcomp = OpalPciBus3Bits;       break;
                default:
                        dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n",
                                count);
                        /* Do an exact match only */
                        bcomp = OpalPciBusAll;
                }
                rid_end = pe->rid + (count << 8);
        } else {
#ifdef CONFIG_PCI_IOV
                if (pe->flags & PNV_IODA_PE_VF)
                        parent = pe->parent_dev;
                else
#endif /* CONFIG_PCI_IOV */
                        parent = pe->pdev->bus->self;
                bcomp = OpalPciBusAll;
                dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER;
                fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER;
                rid_end = pe->rid + 1;
        }

        /*
         * Associate PE in PELT. We need add the PE into the
         * corresponding PELT-V as well. Otherwise, the error
         * originated from the PE might contribute to other
         * PEs.
         */
        rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
                             bcomp, dcomp, fcomp, OPAL_MAP_PE);
        if (rc) {
                pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc);
                return -ENXIO;
        }

        /*
         * Configure PELTV. NPUs don't have a PELTV table so skip
         * configuration on them.
         */
        if (phb->type != PNV_PHB_NPU_NVLINK && phb->type != PNV_PHB_NPU_OCAPI)
                pnv_ioda_set_peltv(phb, pe, true);

        /* Setup reverse map */
        for (rid = pe->rid; rid < rid_end; rid++)
                phb->ioda.pe_rmap[rid] = pe->pe_number;

        /* Setup one MVTs on IODA1 */
        if (phb->type != PNV_PHB_IODA1) {
                pe->mve_number = 0;
                goto out;
        }

        pe->mve_number = pe->pe_number;
        rc = opal_pci_set_mve(phb->opal_id, pe->mve_number, pe->pe_number);
        if (rc != OPAL_SUCCESS) {
                pe_err(pe, "OPAL error %ld setting up MVE %x\n",
                       rc, pe->mve_number);
                pe->mve_number = -1;
        } else {
                rc = opal_pci_set_mve_enable(phb->opal_id,
                                             pe->mve_number, OPAL_ENABLE_MVE);
                if (rc) {
                        pe_err(pe, "OPAL error %ld enabling MVE %x\n",
                               rc, pe->mve_number);
                        pe->mve_number = -1;
                }
        }

out:
        return 0;
}

#ifdef CONFIG_PCI_IOV
static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset)
{
        struct pci_dn *pdn = pci_get_pdn(dev);
        int i;
        struct resource *res, res2;
        resource_size_t size;
        u16 num_vfs;

        if (!dev->is_physfn)
                return -EINVAL;

        /*
         * "offset" is in VFs.  The M64 windows are sized so that when they
         * are segmented, each segment is the same size as the IOV BAR.
         * Each segment is in a separate PE, and the high order bits of the
         * address are the PE number.  Therefore, each VF's BAR is in a
         * separate PE, and changing the IOV BAR start address changes the
         * range of PEs the VFs are in.
         */
        num_vfs = pdn->num_vfs;
        for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
                res = &dev->resource[i + PCI_IOV_RESOURCES];
                if (!res->flags || !res->parent)
                        continue;

                /*
                 * The actual IOV BAR range is determined by the start address
                 * and the actual size for num_vfs VFs BAR.  This check is to
                 * make sure that after shifting, the range will not overlap
                 * with another device.
                 */
                size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES);
                res2.flags = res->flags;
                res2.start = res->start + (size * offset);
                res2.end = res2.start + (size * num_vfs) - 1;

                if (res2.end > res->end) {
                        dev_err(&dev->dev, "VF BAR%d: %pR would extend past %pR (trying to enable %d VFs shifted by %d)\n",
                                i, &res2, res, num_vfs, offset);
                        return -EBUSY;
                }
        }

        /*
         * Since M64 BAR shares segments among all possible 256 PEs,
         * we have to shift the beginning of PF IOV BAR to make it start from
         * the segment which belongs to the PE number assigned to the first VF.
         * This creates a "hole" in the /proc/iomem which could be used for
         * allocating other resources so we reserve this area below and
         * release when IOV is released.
         */
        for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
                res = &dev->resource[i + PCI_IOV_RESOURCES];
                if (!res->flags || !res->parent)
                        continue;

                size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES);
                res2 = *res;
                res->start += size * offset;

                dev_info(&dev->dev, "VF BAR%d: %pR shifted to %pR (%sabling %d VFs shifted by %d)\n",
                         i, &res2, res, (offset > 0) ? "En" : "Dis",
                         num_vfs, offset);

                if (offset < 0) {
                        devm_release_resource(&dev->dev, &pdn->holes[i]);
                        memset(&pdn->holes[i], 0, sizeof(pdn->holes[i]));
                }

                pci_update_resource(dev, i + PCI_IOV_RESOURCES);

                if (offset > 0) {
                        pdn->holes[i].start = res2.start;
                        pdn->holes[i].end = res2.start + size * offset - 1;
                        pdn->holes[i].flags = IORESOURCE_BUS;
                        pdn->holes[i].name = "pnv_iov_reserved";
                        devm_request_resource(&dev->dev, res->parent,
                                        &pdn->holes[i]);
                }
        }
        return 0;
}
#endif /* CONFIG_PCI_IOV */

static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
{
        struct pci_controller *hose = pci_bus_to_host(dev->bus);
        struct pnv_phb *phb = hose->private_data;
        struct pci_dn *pdn = pci_get_pdn(dev);
        struct pnv_ioda_pe *pe;

        if (!pdn) {
                pr_err("%s: Device tree node not associated properly\n",
                           pci_name(dev));
                return NULL;
        }
        if (pdn->pe_number != IODA_INVALID_PE)
                return NULL;

        pe = pnv_ioda_alloc_pe(phb);
        if (!pe) {
                pr_warn("%s: Not enough PE# available, disabling device\n",
                        pci_name(dev));
                return NULL;
        }

        /* NOTE: We get only one ref to the pci_dev for the pdn, not for the
         * pointer in the PE data structure, both should be destroyed at the
         * same time. However, this needs to be looked at more closely again
         * once we actually start removing things (Hotplug, SR-IOV, ...)
         *
         * At some point we want to remove the PDN completely anyways
         */
        pci_dev_get(dev);
        pdn->pe_number = pe->pe_number;
        pe->flags = PNV_IODA_PE_DEV;
        pe->pdev = dev;
        pe->pbus = NULL;
        pe->mve_number = -1;
        pe->rid = dev->bus->number << 8 | pdn->devfn;

        pe_info(pe, "Associated device to PE\n");

        if (pnv_ioda_configure_pe(phb, pe)) {
                /* XXX What do we do here ? */
                pnv_ioda_free_pe(pe);
                pdn->pe_number = IODA_INVALID_PE;
                pe->pdev = NULL;
                pci_dev_put(dev);
                return NULL;
        }

        /* Put PE to the list */
        list_add_tail(&pe->list, &phb->ioda.pe_list);

        return pe;
}

static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
{
        struct pci_dev *dev;

        list_for_each_entry(dev, &bus->devices, bus_list) {
                struct pci_dn *pdn = pci_get_pdn(dev);

                if (pdn == NULL) {
                        pr_warn("%s: No device node associated with device !\n",
                                pci_name(dev));
                        continue;
                }

                /*
                 * In partial hotplug case, the PCI device might be still
                 * associated with the PE and needn't attach it to the PE
                 * again.
                 */
                if (pdn->pe_number != IODA_INVALID_PE)
                        continue;

                pe->device_count++;
                pdn->pe_number = pe->pe_number;
                if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
                        pnv_ioda_setup_same_PE(dev->subordinate, pe);
        }
}

/*
 * There're 2 types of PCI bus sensitive PEs: One that is compromised of
 * single PCI bus. Another one that contains the primary PCI bus and its
 * subordinate PCI devices and buses. The second type of PE is normally
 * orgiriated by PCIe-to-PCI bridge or PLX switch downstream ports.
 */
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;
        unsigned 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 (!pe)
                pe = pnv_ioda_pick_m64_pe(bus, all);

        /* The PE number isn't pinned by M64 */
        if (!pe)
                pe = pnv_ioda_alloc_pe(phb);

        if (!pe) {
                pr_warn("%s: Not enough PE# available for PCI bus %04x:%02x\n",
                        __func__, pci_domain_nr(bus), bus->number);
                return NULL;
        }

        pe->flags |= (all ? PNV_IODA_PE_BUS_ALL : PNV_IODA_PE_BUS);
        pe->pbus = bus;
        pe->pdev = NULL;
        pe->mve_number = -1;
        pe->rid = bus->busn_res.start << 8;

        if (all)
                pe_info(pe, "Secondary bus %pad..%pad associated with PE#%x\n",
                        &bus->busn_res.start, &bus->busn_res.end,
                        pe->pe_number);
        else
                pe_info(pe, "Secondary bus %pad associated with PE#%x\n",
                        &bus->busn_res.start, pe->pe_number);

        if (pnv_ioda_configure_pe(phb, pe)) {
                /* XXX What do we do here ? */
                pnv_ioda_free_pe(pe);
                pe->pbus = NULL;
                return NULL;
        }

        /* Associate it with all child devices */
        pnv_ioda_setup_same_PE(bus, pe);

        /* Put PE to the list */
        list_add_tail(&pe->list, &phb->ioda.pe_list);

        return pe;
}

static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
{
        int pe_num, found_pe = false, rc;
        long rid;
        struct pnv_ioda_pe *pe;
        struct pci_dev *gpu_pdev;
        struct pci_dn *npu_pdn;
        struct pci_controller *hose = pci_bus_to_host(npu_pdev->bus);
        struct pnv_phb *phb = hose->private_data;

        /*
         * Due to a hardware errata PE#0 on the NPU is reserved for
         * error handling. This means we only have three PEs remaining
         * which need to be assigned to four links, implying some
         * links must share PEs.
         *
         * To achieve this we assign PEs such that NPUs linking the
         * same GPU get assigned the same PE.
         */
        gpu_pdev = pnv_pci_get_gpu_dev(npu_pdev);
        for (pe_num = 0; pe_num < phb->ioda.total_pe_num; pe_num++) {
                pe = &phb->ioda.pe_array[pe_num];
                if (!pe->pdev)
                        continue;

                if (pnv_pci_get_gpu_dev(pe->pdev) == gpu_pdev) {
                        /*
                         * This device has the same peer GPU so should
                         * be assigned the same PE as the existing
                         * peer NPU.
                         */
                        dev_info(&npu_pdev->dev,
                                "Associating to existing PE %x\n", pe_num);
                        pci_dev_get(npu_pdev);
                        npu_pdn = pci_get_pdn(npu_pdev);
                        rid = npu_pdev->bus->number << 8 | npu_pdn->devfn;
                        npu_pdn->pe_number = pe_num;
                        phb->ioda.pe_rmap[rid] = pe->pe_number;

                        /* Map the PE to this link */
                        rc = opal_pci_set_pe(phb->opal_id, pe_num, rid,
                                        OpalPciBusAll,
                                        OPAL_COMPARE_RID_DEVICE_NUMBER,
                                        OPAL_COMPARE_RID_FUNCTION_NUMBER,
                                        OPAL_MAP_PE);
                        WARN_ON(rc != OPAL_SUCCESS);
                        found_pe = true;
                        break;
                }
        }

        if (!found_pe)
                /*
                 * Could not find an existing PE so allocate a new
                 * one.
                 */
                return pnv_ioda_setup_dev_PE(npu_pdev);
        else
                return pe;
}

static void pnv_ioda_setup_npu_PEs(struct pci_bus *bus)
{
        struct pci_dev *pdev;

        list_for_each_entry(pdev, &bus->devices, bus_list)
                pnv_ioda_setup_npu_PE(pdev);
}

static void pnv_pci_ioda_setup_PEs(void)
{
        struct pci_controller *hose;
        struct pnv_phb *phb;
        struct pci_bus *bus;
        struct pci_dev *pdev;
        struct pnv_ioda_pe *pe;

        list_for_each_entry(hose, &hose_list, list_node) {
                phb = hose->private_data;
                if (phb->type == PNV_PHB_NPU_NVLINK) {
                        /* PE#0 is needed for error reporting */
                        pnv_ioda_reserve_pe(phb, 0);
                        pnv_ioda_setup_npu_PEs(hose->bus);
                        if (phb->model == PNV_PHB_MODEL_NPU2)
                                WARN_ON_ONCE(pnv_npu2_init(hose));
                }
                if (phb->type == PNV_PHB_NPU_OCAPI) {
                        bus = hose->bus;
                        list_for_each_entry(pdev, &bus->devices, bus_list)
                                pnv_ioda_setup_dev_PE(pdev);
                }
        }
        list_for_each_entry(hose, &hose_list, list_node) {
                phb = hose->private_data;
                if (phb->type != PNV_PHB_IODA2)
                        continue;

                list_for_each_entry(pe, &phb->ioda.pe_list, list)
                        pnv_npu2_map_lpar(pe, MSR_DR | MSR_PR | MSR_HV);
        }
}

#ifdef CONFIG_PCI_IOV
static int pnv_pci_vf_release_m64(struct pci_dev *pdev, u16 num_vfs)
{
        struct pci_bus        *bus;
        struct pci_controller *hose;
        struct pnv_phb        *phb;
        struct pci_dn         *pdn;
        int                    i, j;
        int                    m64_bars;

        bus = pdev->bus;
        hose = pci_bus_to_host(bus);
        phb = hose->private_data;
        pdn = pci_get_pdn(pdev);

        if (pdn->m64_single_mode)
                m64_bars = num_vfs;
        else
                m64_bars = 1;

        for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
                for (j = 0; j < m64_bars; j++) {
                        if (pdn->m64_map[j][i] == IODA_INVALID_M64)
                                continue;
                        opal_pci_phb_mmio_enable(phb->opal_id,
                                OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 0);
                        clear_bit(pdn->m64_map[j][i], &phb->ioda.m64_bar_alloc);
                        pdn->m64_map[j][i] = IODA_INVALID_M64;
                }

        kfree(pdn->m64_map);
        return 0;
}

static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs)
{
        struct pci_bus        *bus;
        struct pci_controller *hose;
        struct pnv_phb        *phb;
        struct pci_dn         *pdn;
        unsigned int           win;
        struct resource       *res;
        int                    i, j;
        int64_t                rc;
        int                    total_vfs;
        resource_size_t        size, start;
        int                    pe_num;
        int                    m64_bars;

        bus = pdev->bus;
        hose = pci_bus_to_host(bus);
        phb = hose->private_data;
        pdn = pci_get_pdn(pdev);
        total_vfs = pci_sriov_get_totalvfs(pdev);

        if (pdn->m64_single_mode)
                m64_bars = num_vfs;
        else
                m64_bars = 1;

        pdn->m64_map = kmalloc_array(m64_bars,
                                     sizeof(*pdn->m64_map),
                                     GFP_KERNEL);
        if (!pdn->m64_map)
                return -ENOMEM;
        /* Initialize the m64_map to IODA_INVALID_M64 */
        for (i = 0; i < m64_bars ; i++)
                for (j = 0; j < PCI_SRIOV_NUM_BARS; j++)
                        pdn->m64_map[i][j] = IODA_INVALID_M64;


        for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
                res = &pdev->resource[i + PCI_IOV_RESOURCES];
                if (!res->flags || !res->parent)
                        continue;

                for (j = 0; j < m64_bars; j++) {
                        do {
                                win = find_next_zero_bit(&phb->ioda.m64_bar_alloc,
                                                phb->ioda.m64_bar_idx + 1, 0);

                                if (win >= phb->ioda.m64_bar_idx + 1)
                                        goto m64_failed;
                        } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc));

                        pdn->m64_map[j][i] = win;

                        if (pdn->m64_single_mode) {
                                size = pci_iov_resource_size(pdev,
                                                        PCI_IOV_RESOURCES + i);
                                start = res->start + size * j;
                        } else {
                                size = resource_size(res);
                                start = res->start;
                        }

                        /* Map the M64 here */
                        if (pdn->m64_single_mode) {
                                pe_num = pdn->pe_num_map[j];
                                rc = opal_pci_map_pe_mmio_window(phb->opal_id,
                                                pe_num, OPAL_M64_WINDOW_TYPE,
                                                pdn->m64_map[j][i], 0);
                        }

                        rc = opal_pci_set_phb_mem_window(phb->opal_id,
                                                 OPAL_M64_WINDOW_TYPE,
                                                 pdn->m64_map[j][i],
                                                 start,
                                                 0, /* unused */
                                                 size);


                        if (rc != OPAL_SUCCESS) {
                                dev_err(&pdev->dev, "Failed to map M64 window #%d: %lld\n",
                                        win, rc);
                                goto m64_failed;
                        }

                        if (pdn->m64_single_mode)
                                rc = opal_pci_phb_mmio_enable(phb->opal_id,
                                     OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 2);
                        else
                                rc = opal_pci_phb_mmio_enable(phb->opal_id,
                                     OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 1);

                        if (rc != OPAL_SUCCESS) {
                                dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n",
                                        win, rc);
                                goto m64_failed;
                        }
                }
        }
        return 0;

m64_failed:
        pnv_pci_vf_release_m64(pdev, num_vfs);
        return -EBUSY;
}

static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
                int num);

static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe)
{
        struct iommu_table    *tbl;
        int64_t               rc;

        tbl = pe->table_group.tables[0];
        rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0);
        if (rc)
                pe_warn(pe, "OPAL error %lld release DMA window\n", rc);

        pnv_pci_ioda2_set_bypass(pe, false);
        if (pe->table_group.group) {
                iommu_group_put(pe->table_group.group);
                BUG_ON(pe->table_group.group);
        }
        iommu_tce_table_put(tbl);
}

static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
{
        struct pci_bus        *bus;
        struct pci_controller *hose;
        struct pnv_phb        *phb;
        struct pnv_ioda_pe    *pe, *pe_n;
        struct pci_dn         *pdn;

        bus = pdev->bus;
        hose = pci_bus_to_host(bus);
        phb = hose->private_data;
        pdn = pci_get_pdn(pdev);

        if (!pdev->is_physfn)
                return;

        list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) {
                if (pe->parent_dev != pdev)
                        continue;

                pnv_pci_ioda2_release_dma_pe(pdev, pe);

                /* Remove from list */
                mutex_lock(&phb->ioda.pe_list_mutex);
                list_del(&pe->list);
                mutex_unlock(&phb->ioda.pe_list_mutex);

                pnv_ioda_deconfigure_pe(phb, pe);

                pnv_ioda_free_pe(pe);
        }
}

void pnv_pci_sriov_disable(struct pci_dev *pdev)
{
        struct pci_bus        *bus;
        struct pci_controller *hose;
        struct pnv_phb        *phb;
        struct pnv_ioda_pe    *pe;
        struct pci_dn         *pdn;
        u16                    num_vfs, i;

        bus = pdev->bus;
        hose = pci_bus_to_host(bus);
        phb = hose->private_data;
        pdn = pci_get_pdn(pdev);
        num_vfs = pdn->num_vfs;

        /* Release VF PEs */
        pnv_ioda_release_vf_PE(pdev);

        if (phb->type == PNV_PHB_IODA2) {
                if (!pdn->m64_single_mode)
                        pnv_pci_vf_resource_shift(pdev, -*pdn->pe_num_map);

                /* Release M64 windows */
                pnv_pci_vf_release_m64(pdev, num_vfs);

                /* Release PE numbers */
                if (pdn->m64_single_mode) {
                        for (i = 0; i < num_vfs; i++) {
                                if (pdn->pe_num_map[i] == IODA_INVALID_PE)
                                        continue;

                                pe = &phb->ioda.pe_array[pdn->pe_num_map[i]];
                                pnv_ioda_free_pe(pe);
                        }
                } else
                        bitmap_clear(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs);
                /* Releasing pe_num_map */
                kfree(pdn->pe_num_map);
        }
}

static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
                                       struct pnv_ioda_pe *pe);
#ifdef CONFIG_IOMMU_API
static void pnv_ioda_setup_bus_iommu_group(struct pnv_ioda_pe *pe,
                struct iommu_table_group *table_group, struct pci_bus *bus);

#endif
static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
{
        struct pci_bus        *bus;
        struct pci_controller *hose;
        struct pnv_phb        *phb;
        struct pnv_ioda_pe    *pe;
        int                    pe_num;
        u16                    vf_index;
        struct pci_dn         *pdn;

        bus = pdev->bus;
        hose = pci_bus_to_host(bus);
        phb = hose->private_data;
        pdn = pci_get_pdn(pdev);

        if (!pdev->is_physfn)
                return;

        /* Reserve PE for each VF */
        for (vf_index = 0; vf_index < num_vfs; vf_index++) {
                if (pdn->m64_single_mode)
                        pe_num = pdn->pe_num_map[vf_index];
                else
                        pe_num = *pdn->pe_num_map + vf_index;

                pe = &phb->ioda.pe_array[pe_num];
                pe->pe_number = pe_num;
                pe->phb = phb;
                pe->flags = PNV_IODA_PE_VF;
                pe->pbus = NULL;
                pe->parent_dev = pdev;
                pe->mve_number = -1;
                pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) |
                           pci_iov_virtfn_devfn(pdev, vf_index);

                pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%x\n",
                        hose->global_number, pdev->bus->number,
                        PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)),
                        PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num);

                if (pnv_ioda_configure_pe(phb, pe)) {
                        /* XXX What do we do here ? */
                        pnv_ioda_free_pe(pe);
                        pe->pdev = NULL;
                        continue;
                }

                /* Put PE to the list */
                mutex_lock(&phb->ioda.pe_list_mutex);
                list_add_tail(&pe->list, &phb->ioda.pe_list);
                mutex_unlock(&phb->ioda.pe_list_mutex);

                pnv_pci_ioda2_setup_dma_pe(phb, pe);
#ifdef CONFIG_IOMMU_API
                iommu_register_group(&pe->table_group,
                                pe->phb->hose->global_number, pe->pe_number);
                pnv_ioda_setup_bus_iommu_group(pe, &pe->table_group, NULL);
#endif
        }
}

int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
{
        struct pci_bus        *bus;
        struct pci_controller *hose;
        struct pnv_phb        *phb;
        struct pnv_ioda_pe    *pe;
        struct pci_dn         *pdn;
        int                    ret;
        u16                    i;

        bus = pdev->bus;
        hose = pci_bus_to_host(bus);
        phb = hose->private_data;
        pdn = pci_get_pdn(pdev);

        if (phb->type == PNV_PHB_IODA2) {
                if (!pdn->vfs_expanded) {
                        dev_info(&pdev->dev, "don't support this SRIOV device"
                                " with non 64bit-prefetchable IOV BAR\n");
                        return -ENOSPC;
                }

                /*
                 * When M64 BARs functions in Single PE mode, the number of VFs
                 * could be enabled must be less than the number of M64 BARs.
                 */
                if (pdn->m64_single_mode && num_vfs > phb->ioda.m64_bar_idx) {
                        dev_info(&pdev->dev, "Not enough M64 BAR for VFs\n");
                        return -EBUSY;
                }

                /* Allocating pe_num_map */
                if (pdn->m64_single_mode)
                        pdn->pe_num_map = kmalloc_array(num_vfs,
                                                        sizeof(*pdn->pe_num_map),
                                                        GFP_KERNEL);
                else
                        pdn->pe_num_map = kmalloc(sizeof(*pdn->pe_num_map), GFP_KERNEL);

                if (!pdn->pe_num_map)
                        return -ENOMEM;

                if (pdn->m64_single_mode)
                        for (i = 0; i < num_vfs; i++)
                                pdn->pe_num_map[i] = IODA_INVALID_PE;

                /* Calculate available PE for required VFs */
                if (pdn->m64_single_mode) {
                        for (i = 0; i < num_vfs; i++) {
                                pe = pnv_ioda_alloc_pe(phb);
                                if (!pe) {
                                        ret = -EBUSY;
                                        goto m64_failed;
                                }

                                pdn->pe_num_map[i] = pe->pe_number;
                        }
                } else {
                        mutex_lock(&phb->ioda.pe_alloc_mutex);
                        *pdn->pe_num_map = bitmap_find_next_zero_area(
                                phb->ioda.pe_alloc, phb->ioda.total_pe_num,
                                0, num_vfs, 0);
                        if (*pdn->pe_num_map >= phb->ioda.total_pe_num) {
                                mutex_unlock(&phb->ioda.pe_alloc_mutex);
                                dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs);
                                kfree(pdn->pe_num_map);
                                return -EBUSY;
                        }
                        bitmap_set(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs);
                        mutex_unlock(&phb->ioda.pe_alloc_mutex);
                }
                pdn->num_vfs = num_vfs;

                /* Assign M64 window accordingly */
                ret = pnv_pci_vf_assign_m64(pdev, num_vfs);
                if (ret) {
                        dev_info(&pdev->dev, "Not enough M64 window resources\n");
                        goto m64_failed;
                }

                /*
                 * When using one M64 BAR to map one IOV BAR, we need to shift
                 * the IOV BAR according to the PE# allocated to the VFs.
                 * Otherwise, the PE# for the VF will conflict with others.
                 */
                if (!pdn->m64_single_mode) {
                        ret = pnv_pci_vf_resource_shift(pdev, *pdn->pe_num_map);
                        if (ret)
                                goto m64_failed;
                }
        }

        /* Setup VF PEs */
        pnv_ioda_setup_vf_PE(pdev, num_vfs);

        return 0;

m64_failed:
        if (pdn->m64_single_mode) {
                for (i = 0; i < num_vfs; i++) {
                        if (pdn->pe_num_map[i] == IODA_INVALID_PE)
                                continue;

                        pe = &phb->ioda.pe_array[pdn->pe_num_map[i]];
                        pnv_ioda_free_pe(pe);
                }
        } else
                bitmap_clear(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs);

        /* Releasing pe_num_map */
        kfree(pdn->pe_num_map);

        return ret;
}

int pnv_pcibios_sriov_disable(struct pci_dev *pdev)
{
        pnv_pci_sriov_disable(pdev);

        /* Release PCI data */
        remove_dev_pci_data(pdev);
        return 0;
}

int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
{
        /* Allocate PCI data */
        add_dev_pci_data(pdev);

        return pnv_pci_sriov_enable(pdev, num_vfs);
}
#endif /* CONFIG_PCI_IOV */

static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
{
        struct pci_dn *pdn = pci_get_pdn(pdev);
        struct pnv_ioda_pe *pe;

        /*
         * The function can be called while the PE#
         * hasn't been assigned. Do nothing for the
         * case.
         */
        if (!pdn || pdn->pe_number == IODA_INVALID_PE)
                return;

        pe = &phb->ioda.pe_array[pdn->pe_number];
        WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
        pdev->dev.archdata.dma_offset = pe->tce_bypass_base;
        set_iommu_table_base(&pdev->dev, pe->table_group.tables[0]);
        /*
         * Note: iommu_add_device() will fail here as
         * for physical PE: the device is already added by now;
         * for virtual PE: sysfs entries are not ready yet and
         * tce_iommu_bus_notifier will add the device to a group later.
         */
}

/*
 * Reconfigure TVE#0 to be usable as 64-bit DMA space.
 *
 * The first 4GB of virtual memory for a PE is reserved for 32-bit accesses.
 * Devices can only access more than that if bit 59 of the PCI address is set
 * by hardware, which indicates TVE#1 should be used instead of TVE#0.
 * Many PCI devices are not capable of addressing that many bits, and as a
 * result are limited to the 4GB of virtual memory made available to 32-bit
 * devices in TVE#0.
 *
 * In order to work around this, reconfigure TVE#0 to be suitable for 64-bit
 * devices by configuring the virtual memory past the first 4GB inaccessible
 * by 64-bit DMAs.  This should only be used by devices that want more than
 * 4GB, and only on PEs that have no 32-bit devices.
 *
 * Currently this will only work on PHB3 (POWER8).
 */
static int pnv_pci_ioda_dma_64bit_bypass(struct pnv_ioda_pe *pe)
{
        u64 window_size, table_size, tce_count, addr;
        struct page *table_pages;
        u64 tce_order = 28; /* 256MB TCEs */
        __be64 *tces;
        s64 rc;

        /*
         * Window size needs to be a power of two, but needs to account for
         * shifting memory by the 4GB offset required to skip 32bit space.
         */
        window_size = roundup_pow_of_two(memory_hotplug_max() + (1ULL << 32));
        tce_count = window_size >> tce_order;
        table_size = tce_count << 3;

        if (table_size < PAGE_SIZE)
                table_size = PAGE_SIZE;

        table_pages = alloc_pages_node(pe->phb->hose->node, GFP_KERNEL,
                                       get_order(table_size));
        if (!table_pages)
                goto err;

        tces = page_address(table_pages);
        if (!tces)
                goto err;

        memset(tces, 0, table_size);

        for (addr = 0; addr < memory_hotplug_max(); addr += (1 << tce_order)) {
                tces[(addr + (1ULL << 32)) >> tce_order] =
                        cpu_to_be64(addr | TCE_PCI_READ | TCE_PCI_WRITE);
        }

        rc = opal_pci_map_pe_dma_window(pe->phb->opal_id,
                                        pe->pe_number,
                                        /* reconfigure window 0 */
                                        (pe->pe_number << 1) + 0,
                                        1,
                                        __pa(tces),
                                        table_size,
                                        1 << tce_order);
        if (rc == OPAL_SUCCESS) {
                pe_info(pe, "Using 64-bit DMA iommu bypass (through TVE#0)\n");
                return 0;
        }
err:
        pe_err(pe, "Error configuring 64-bit DMA bypass\n");
        return -EIO;
}

static bool pnv_pci_ioda_iommu_bypass_supported(struct pci_dev *pdev,
                u64 dma_mask)
{
        struct pci_controller *hose = pci_bus_to_host(pdev->bus);
        struct pnv_phb *phb = hose->private_data;
        struct pci_dn *pdn = pci_get_pdn(pdev);
        struct pnv_ioda_pe *pe;

        if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
                return false;

        pe = &phb->ioda.pe_array[pdn->pe_number];
        if (pe->tce_bypass_enabled) {
                u64 top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
                if (dma_mask >= top)
                        return true;
        }

        /*
         * If the device can't set the TCE bypass bit but still wants
         * to access 4GB or more, on PHB3 we can reconfigure TVE#0 to
         * bypass the 32-bit region and be usable for 64-bit DMAs.
         * The device needs to be able to address all of this space.
         */
        if (dma_mask >> 32 &&
            dma_mask > (memory_hotplug_max() + (1ULL << 32)) &&
            /* pe->pdev should be set if it's a single device, pe->pbus if not */
            (pe->device_count == 1 || !pe->pbus) &&
            phb->model == PNV_PHB_MODEL_PHB3) {
                /* Configure the bypass mode */
                s64 rc = pnv_pci_ioda_dma_64bit_bypass(pe);
                if (rc)
                        return false;
                /* 4GB offset bypasses 32-bit space */
                pdev->dev.archdata.dma_offset = (1ULL << 32);
                return true;
        }

        return false;
}

static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
{
        struct pci_dev *dev;

        list_for_each_entry(dev, &bus->devices, bus_list) {
                set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
                dev->dev.archdata.dma_offset = pe->tce_bypass_base;

                if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
                        pnv_ioda_setup_bus_dma(pe, dev->subordinate);
        }
}

static inline __be64 __iomem *pnv_ioda_get_inval_reg(struct pnv_phb *phb,
                                                     bool real_mode)
{
        return real_mode ? (__be64 __iomem *)(phb->regs_phys + 0x210) :
                (phb->regs + 0x210);
}

static void pnv_pci_p7ioc_tce_invalidate(struct iommu_table *tbl,
                unsigned long index, unsigned long npages, bool rm)
{
        struct iommu_table_group_link *tgl = list_first_entry_or_null(
                        &tbl->it_group_list, struct iommu_table_group_link,
                        next);
        struct pnv_ioda_pe *pe = container_of(tgl->table_group,
                        struct pnv_ioda_pe, table_group);
        __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm);
        unsigned long start, end, inc;

        start = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset);
        end = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset +
                        npages - 1);

        /* p7ioc-style invalidation, 2 TCEs per write */
        start |= (1ull << 63);
        end |= (1ull << 63);
        inc = 16;
        end |= inc - 1; /* round up end to be different than start */

        mb(); /* Ensure above stores are visible */
        while (start <= end) {
                if (rm)
                        __raw_rm_writeq_be(start, invalidate);
                else
                        __raw_writeq_be(start, invalidate);

                start += inc;
        }

        /*
         * The iommu layer will do another mb() for us on build()
         * and we don't care on free()
         */
}

static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
                long npages, unsigned long uaddr,
                enum dma_data_direction direction,
                unsigned long attrs)
{
        int ret = pnv_tce_build(tbl, index, npages, uaddr, direction,
                        attrs);

        if (!ret)
                pnv_pci_p7ioc_tce_invalidate(tbl, index, npages, false);

        return ret;
}

#ifdef CONFIG_IOMMU_API
static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
                unsigned long *hpa, enum dma_data_direction *direction)
{
        long ret = pnv_tce_xchg(tbl, index, hpa, direction, true);

        if (!ret)
                pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, false);

        return ret;
}

static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index,
                unsigned long *hpa, enum dma_data_direction *direction)
{
        long ret = pnv_tce_xchg(tbl, index, hpa, direction, false);

        if (!ret)
                pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true);

        return ret;
}
#endif

static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
                long npages)
{
        pnv_tce_free(tbl, index, npages);

        pnv_pci_p7ioc_tce_invalidate(tbl, index, npages, false);
}

static struct iommu_table_ops pnv_ioda1_iommu_ops = {
        .set = pnv_ioda1_tce_build,
#ifdef CONFIG_IOMMU_API
        .exchange = pnv_ioda1_tce_xchg,
        .exchange_rm = pnv_ioda1_tce_xchg_rm,
        .useraddrptr = pnv_tce_useraddrptr,
#endif
        .clear = pnv_ioda1_tce_free,
        .get = pnv_tce_get,
};

#define PHB3_TCE_KILL_INVAL_ALL         PPC_BIT(0)
#define PHB3_TCE_KILL_INVAL_PE          PPC_BIT(1)
#define PHB3_TCE_KILL_INVAL_ONE         PPC_BIT(2)

static void pnv_pci_phb3_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
{
        __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(phb, rm);
        const unsigned long val = PHB3_TCE_KILL_INVAL_ALL;

        mb(); /* Ensure previous TCE table stores are visible */
        if (rm)
                __raw_rm_writeq_be(val, invalidate);
        else
                __raw_writeq_be(val, invalidate);
}

static inline void pnv_pci_phb3_tce_invalidate_pe(struct pnv_ioda_pe *pe)

{
        /* 01xb - invalidate TCEs that match the specified PE# */
        __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false);
        unsigned long val = PHB3_TCE_KILL_INVAL_PE | (pe->pe_number & 0xFF);

        mb(); /* Ensure above stores are visible */
        __raw_writeq_be(val, invalidate);
}

static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm,
                                        unsigned shift, unsigned long index,
                                        unsigned long npages)
{
        __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm);
        unsigned long start, end, inc;

        /* We'll invalidate DMA address in PE scope */
        start = PHB3_TCE_KILL_INVAL_ONE;
        start |= (pe->pe_number & 0xFF);
        end = start;

        /* Figure out the start, end and step */
        start |= (index << shift);
        end |= ((index + npages - 1) << shift);
        inc = (0x1ull << shift);
        mb();

        while (start <= end) {
                if (rm)
                        __raw_rm_writeq_be(start, invalidate);
                else
                        __raw_writeq_be(start, invalidate);
                start += inc;
        }
}

static inline void pnv_pci_ioda2_tce_invalidate_pe(struct pnv_ioda_pe *pe)
{
        struct pnv_phb *phb = pe->phb;

        if (phb->model == PNV_PHB_MODEL_PHB3 && phb->regs)
                pnv_pci_phb3_tce_invalidate_pe(pe);
        else
                opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL_PE,
                                  pe->pe_number, 0, 0, 0);
}

static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
                unsigned long index, unsigned long npages, bool rm)
{
        struct iommu_table_group_link *tgl;

        list_for_each_entry_lockless(tgl, &tbl->it_group_list, next) {
                struct pnv_ioda_pe *pe = container_of(tgl->table_group,
                                struct pnv_ioda_pe, table_group);
                struct pnv_phb *phb = pe->phb;
                unsigned int shift = tbl->it_page_shift;

                /*
                 * NVLink1 can use the TCE kill register directly as
                 * it's the same as PHB3. NVLink2 is different and
                 * should go via the OPAL call.
                 */
                if (phb->model == PNV_PHB_MODEL_NPU) {
                        /*
                         * The NVLink hardware does not support TCE kill
                         * per TCE entry so we have to invalidate
                         * the entire cache for it.
                         */
                        pnv_pci_phb3_tce_invalidate_entire(phb, rm);
                        continue;
                }
                if (phb->model == PNV_PHB_MODEL_PHB3 && phb->regs)
                        pnv_pci_phb3_tce_invalidate(pe, rm, shift,
                                                    index, npages);
                else
                        opal_pci_tce_kill(phb->opal_id,
                                          OPAL_PCI_TCE_KILL_PAGES,
                                          pe->pe_number, 1u << shift,
                                          index << shift, npages);
        }
}

void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
{
        if (phb->model == PNV_PHB_MODEL_NPU || phb->model == PNV_PHB_MODEL_PHB3)
                pnv_pci_phb3_tce_invalidate_entire(phb, rm);
        else
                opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL, 0, 0, 0, 0);
}

static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
                long npages, unsigned long uaddr,
                enum dma_data_direction direction,
                unsigned long attrs)
{
        int ret = pnv_tce_build(tbl, index, npages, uaddr, direction,
                        attrs);

        if (!ret)
                pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);

        return ret;
}

#ifdef CONFIG_IOMMU_API
static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
                unsigned long *hpa, enum dma_data_direction *direction)
{
        long ret = pnv_tce_xchg(tbl, index, hpa, direction, true);

        if (!ret)
                pnv_pci_ioda2_tce_invalidate(tbl, index, 1, false);

        return ret;
}

static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index,
                unsigned long *hpa, enum dma_data_direction *direction)
{
        long ret = pnv_tce_xchg(tbl, index, hpa, direction, false);

        if (!ret)
                pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true);

        return ret;
}
#endif

static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
                long npages)
{
        pnv_tce_free(tbl, index, npages);

        pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
}

static struct iommu_table_ops pnv_ioda2_iommu_ops = {
        .set = pnv_ioda2_tce_build,
#ifdef CONFIG_IOMMU_API
        .exchange = pnv_ioda2_tce_xchg,
        .exchange_rm = pnv_ioda2_tce_xchg_rm,
        .useraddrptr = pnv_tce_useraddrptr,
#endif
        .clear = pnv_ioda2_tce_free,
        .get = pnv_tce_get,
        .free = pnv_pci_ioda2_table_free_pages,
};

static int pnv_pci_ioda_dev_dma_weight(struct pci_dev *dev, void *data)
{
        unsigned int *weight = (unsigned int *)data;

        /* This is quite simplistic. The "base" weight of a device
         * is 10. 0 means no DMA is to be accounted for it.
         */
        if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL)
                return 0;

        if (dev->class == PCI_CLASS_SERIAL_USB_UHCI ||
            dev->class == PCI_CLASS_SERIAL_USB_OHCI ||
            dev->class == PCI_CLASS_SERIAL_USB_EHCI)
                *weight += 3;
        else if ((dev->class >> 8) == PCI_CLASS_STORAGE_RAID)
                *weight += 15;
        else
                *weight += 10;

        return 0;
}

static unsigned int pnv_pci_ioda_pe_dma_weight(struct pnv_ioda_pe *pe)
{
        unsigned int weight = 0;

        /* SRIOV VF has same DMA32 weight as its PF */
#ifdef CONFIG_PCI_IOV
        if ((pe->flags & PNV_IODA_PE_VF) && pe->parent_dev) {
                pnv_pci_ioda_dev_dma_weight(pe->parent_dev, &weight);
                return weight;
        }
#endif

        if ((pe->flags & PNV_IODA_PE_DEV) && pe->pdev) {
                pnv_pci_ioda_dev_dma_weight(pe->pdev, &weight);
        } else if ((pe->flags & PNV_IODA_PE_BUS) && pe->pbus) {
                struct pci_dev *pdev;

                list_for_each_entry(pdev, &pe->pbus->devices, bus_list)
                        pnv_pci_ioda_dev_dma_weight(pdev, &weight);
        } else if ((pe->flags & PNV_IODA_PE_BUS_ALL) && pe->pbus) {
                pci_walk_bus(pe->pbus, pnv_pci_ioda_dev_dma_weight, &weight);
        }

        return weight;
}

static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
                                       struct pnv_ioda_pe *pe)
{

        struct page *tce_mem = NULL;
        struct iommu_table *tbl;
        unsigned int weight, total_weight = 0;
        unsigned int tce32_segsz, base, segs, avail, i;
        int64_t rc;
        void *addr;

        /* XXX FIXME: Handle 64-bit only DMA devices */
        /* XXX FIXME: Provide 64-bit DMA facilities & non-4K TCE tables etc.. */
        /* XXX FIXME: Allocate multi-level tables on PHB3 */
        weight = pnv_pci_ioda_pe_dma_weight(pe);
        if (!weight)
                return;

        pci_walk_bus(phb->hose->bus, pnv_pci_ioda_dev_dma_weight,
                     &total_weight);
        segs = (weight * phb->ioda.dma32_count) / total_weight;
        if (!segs)
                segs = 1;

        /*
         * Allocate contiguous DMA32 segments. We begin with the expected
         * number of segments. With one more attempt, the number of DMA32
         * segments to be allocated is decreased by one until one segment
         * is allocated successfully.
         */
        do {
                for (base = 0; base <= phb->ioda.dma32_count - segs; base++) {
                        for (avail = 0, i = base; i < base + segs; i++) {
                                if (phb->ioda.dma32_segmap[i] ==
                                    IODA_INVALID_PE)
                                        avail++;
                        }

                        if (avail == segs)
                                goto found;
                }
        } while (--segs);

        if (!segs) {
                pe_warn(pe, "No available DMA32 segments\n");
                return;
        }

found:
        tbl = pnv_pci_table_alloc(phb->hose->node);
        if (WARN_ON(!tbl))
                return;

        iommu_register_group(&pe->table_group, phb->hose->global_number,
                        pe->pe_number);
        pnv_pci_link_table_and_group(phb->hose->node, 0, tbl, &pe->table_group);

        /* Grab a 32-bit TCE table */
        pe_info(pe, "DMA weight %d (%d), assigned (%d) %d DMA32 segments\n",
                weight, total_weight, base, segs);
        pe_info(pe, " Setting up 32-bit TCE table at %08x..%08x\n",
                base * PNV_IODA1_DMA32_SEGSIZE,
                (base + segs) * PNV_IODA1_DMA32_SEGSIZE - 1);

        /* XXX Currently, we allocate one big contiguous table for the
         * TCEs. We only really need one chunk per 256M of TCE space
         * (ie per segment) but that's an optimization for later, it
         * requires some added smarts with our get/put_tce implementation
         *
         * Each TCE page is 4KB in size and each TCE entry occupies 8
         * bytes
         */
        tce32_segsz = PNV_IODA1_DMA32_SEGSIZE >> (IOMMU_PAGE_SHIFT_4K - 3);
        tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL,
                                   get_order(tce32_segsz * segs));
        if (!tce_mem) {
                pe_err(pe, " Failed to allocate a 32-bit TCE memory\n");
                goto fail;
        }
        addr = page_address(tce_mem);
        memset(addr, 0, tce32_segsz * segs);

        /* Configure HW */
        for (i = 0; i < segs; i++) {
                rc = opal_pci_map_pe_dma_window(phb->opal_id,
                                              pe->pe_number,
                                              base + i, 1,
                                              __pa(addr) + tce32_segsz * i,
                                              tce32_segsz, IOMMU_PAGE_SIZE_4K);
                if (rc) {
                        pe_err(pe, " Failed to configure 32-bit TCE table, err %lld\n",
                               rc);
                        goto fail;
                }
        }

        /* Setup DMA32 segment mapping */
        for (i = base; i < base + segs; i++)
                phb->ioda.dma32_segmap[i] = pe->pe_number;

        /* Setup linux iommu table */
        pnv_pci_setup_iommu_table(tbl, addr, tce32_segsz * segs,
                                  base * PNV_IODA1_DMA32_SEGSIZE,
                                  IOMMU_PAGE_SHIFT_4K);

        tbl->it_ops = &pnv_ioda1_iommu_ops;
        pe->table_group.tce32_start = tbl->it_offset << tbl->it_page_shift;
        pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift;
        iommu_init_table(tbl, phb->hose->node);

        if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
                pnv_ioda_setup_bus_dma(pe, pe->pbus);

        return;
 fail:
        /* XXX Failure: Try to fallback to 64-bit only ? */
        if (tce_mem)
                __free_pages(tce_mem, get_order(tce32_segsz * segs));
        if (tbl) {
                pnv_pci_unlink_table_and_group(tbl, &pe->table_group);
                iommu_tce_table_put(tbl);
        }
}

static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
                int num, struct iommu_table *tbl)
{
        struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
                        table_group);
        struct pnv_phb *phb = pe->phb;
        int64_t rc;
        const unsigned long size = tbl->it_indirect_levels ?
                        tbl->it_level_size : tbl->it_size;
        const __u64 start_addr = tbl->it_offset << tbl->it_page_shift;
        const __u64 win_size = tbl->it_size << tbl->it_page_shift;

        pe_info(pe, "Setting up window#%d %llx..%llx pg=%lx\n",
                num, start_addr, start_addr + win_size - 1,
                IOMMU_PAGE_SIZE(tbl));

        /*
         * Map TCE table through TVT. The TVE index is the PE number
         * shifted by 1 bit for 32-bits DMA space.
         */
        rc = opal_pci_map_pe_dma_window(phb->opal_id,
                        pe->pe_number,
                        (pe->pe_number << 1) + num,
                        tbl->it_indirect_levels + 1,
                        __pa(tbl->it_base),
                        size << 3,
                        IOMMU_PAGE_SIZE(tbl));
        if (rc) {
                pe_err(pe, "Failed to configure TCE table, err %lld\n", rc);
                return rc;
        }

        pnv_pci_link_table_and_group(phb->hose->node, num,
                        tbl, &pe->table_group);
        pnv_pci_ioda2_tce_invalidate_pe(pe);

        return 0;
}

static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
{
        uint16_t window_id = (pe->pe_number << 1 ) + 1;
        int64_t rc;

        pe_info(pe, "%sabling 64-bit DMA bypass\n", enable ? "En" : "Dis");
        if (enable) {
                phys_addr_t top = memblock_end_of_DRAM();

                top = roundup_pow_of_two(top);
                rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
                                                     pe->pe_number,
                                                     window_id,
                                                     pe->tce_bypass_base,
                                                     top);
        } else {
                rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
                                                     pe->pe_number,
                                                     window_id,
                                                     pe->tce_bypass_base,
                                                     0);
        }
        if (rc)
                pe_err(pe, "OPAL error %lld configuring bypass window\n", rc);
        else
                pe->tce_bypass_enabled = enable;
}

static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
                int num, __u32 page_shift, __u64 window_size, __u32 levels,
                bool alloc_userspace_copy, struct iommu_table **ptbl)
{
        struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
                        table_group);
        int nid = pe->phb->hose->node;
        __u64 bus_offset = num ? pe->tce_bypass_base : table_group->tce32_start;
        long ret;
        struct iommu_table *tbl;

        tbl = pnv_pci_table_alloc(nid);
        if (!tbl)
                return -ENOMEM;

        tbl->it_ops = &pnv_ioda2_iommu_ops;

        ret = pnv_pci_ioda2_table_alloc_pages(nid,
                        bus_offset, page_shift, window_size,
                        levels, alloc_userspace_copy, tbl);
        if (ret) {
                iommu_tce_table_put(tbl);
                return ret;
        }

        *ptbl = tbl;

        return 0;
}

static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
{
        struct iommu_table *tbl = NULL;
        long rc;

        /*
         * crashkernel= specifies the kdump kernel's maximum memory at
         * some offset and there is no guaranteed the result is a power
         * of 2, which will cause errors later.
         */
        const u64 max_memory = __rounddown_pow_of_two(memory_hotplug_max());

        /*
         * In memory constrained environments, e.g. kdump kernel, the
         * DMA window can be larger than available memory, which will
         * cause errors later.
         */
        const u64 window_size = min((u64)pe->table_group.tce32_size, max_memory);

        rc = pnv_pci_ioda2_create_table(&pe->table_group, 0,
                        IOMMU_PAGE_SHIFT_4K,
                        window_size,
                        POWERNV_IOMMU_DEFAULT_LEVELS, false, &tbl);
        if (rc) {
                pe_err(pe, "Failed to create 32-bit TCE table, err %ld",
                                rc);
                return rc;
        }

        iommu_init_table(tbl, pe->phb->hose->node);

        rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl);
        if (rc) {
                pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
                                rc);
                iommu_tce_table_put(tbl);
                return rc;
        }

        if (!pnv_iommu_bypass_disabled)
                pnv_pci_ioda2_set_bypass(pe, true);

        /*
         * Set table base for the case of IOMMU DMA use. Usually this is done
         * from dma_dev_setup() which is not called when a device is returned
         * from VFIO so do it here.
         */
        if (pe->pdev)
                set_iommu_table_base(&pe->pdev->dev, tbl);

        return 0;
}

#if defined(CONFIG_IOMMU_API) || defined(CONFIG_PCI_IOV)
static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
                int num)
{
        struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
                        table_group);
        struct pnv_phb *phb = pe->phb;
        long ret;

        pe_info(pe, "Removing DMA window #%d\n", num);

        ret = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
                        (pe->pe_number << 1) + num,
                        0/* levels */, 0/* table address */,
                        0/* table size */, 0/* page size */);
        if (ret)
                pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
        else
                pnv_pci_ioda2_tce_invalidate_pe(pe);

        pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);

        return ret;
}
#endif

#ifdef CONFIG_IOMMU_API
unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
                __u64 window_size, __u32 levels)
{
        unsigned long bytes = 0;
        const unsigned window_shift = ilog2(window_size);
        unsigned entries_shift = window_shift - page_shift;
        unsigned table_shift = entries_shift + 3;
        unsigned long tce_table_size = max(0x1000UL, 1UL << table_shift);
        unsigned long direct_table_size;

        if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS) ||
                        !is_power_of_2(window_size))
                return 0;

        /* Calculate a direct table size from window_size and levels */
        entries_shift = (entries_shift + levels - 1) / levels;
        table_shift = entries_shift + 3;
        table_shift = max_t(unsigned, table_shift, PAGE_SHIFT);
        direct_table_size =  1UL << table_shift;

        for ( ; levels; --levels) {
                bytes += _ALIGN_UP(tce_table_size, direct_table_size);

                tce_table_size /= direct_table_size;
                tce_table_size <<= 3;
                tce_table_size = max_t(unsigned long,
                                tce_table_size, direct_table_size);
        }

        return bytes + bytes; /* one for HW table, one for userspace copy */
}

static long pnv_pci_ioda2_create_table_userspace(
                struct iommu_table_group *table_group,
                int num, __u32 page_shift, __u64 window_size, __u32 levels,
                struct iommu_table **ptbl)
{
        long ret = pnv_pci_ioda2_create_table(table_group,
                        num, page_shift, window_size, levels, true, ptbl);

        if (!ret)
                (*ptbl)->it_allocated_size = pnv_pci_ioda2_get_table_size(
                                page_shift, window_size, levels);
        return ret;
}

static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
{
        struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
                                                table_group);
        /* Store @tbl as pnv_pci_ioda2_unset_window() resets it */
        struct iommu_table *tbl = pe->table_group.tables[0];

        pnv_pci_ioda2_set_bypass(pe, false);
        pnv_pci_ioda2_unset_window(&pe->table_group, 0);
        if (pe->pbus)
                pnv_ioda_setup_bus_dma(pe, pe->pbus);
        else if (pe->pdev)
                set_iommu_table_base(&pe->pdev->dev, NULL);
        iommu_tce_table_put(tbl);
}

static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
{
        struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
                                                table_group);

        pnv_pci_ioda2_setup_default_config(pe);
        if (pe->pbus)
                pnv_ioda_setup_bus_dma(pe, pe->pbus);
}

static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
        .get_table_size = pnv_pci_ioda2_get_table_size,
        .create_table = pnv_pci_ioda2_create_table_userspace,
        .set_window = pnv_pci_ioda2_set_window,
        .unset_window = pnv_pci_ioda2_unset_window,
        .take_ownership = pnv_ioda2_take_ownership,
        .release_ownership = pnv_ioda2_release_ownership,
};

static void pnv_ioda_setup_bus_iommu_group_add_devices(struct pnv_ioda_pe *pe,
                struct iommu_table_group *table_group,
                struct pci_bus *bus)
{
        struct pci_dev *dev;

        list_for_each_entry(dev, &bus->devices, bus_list) {
                iommu_add_device(table_group, &dev->dev);

                if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
                        pnv_ioda_setup_bus_iommu_group_add_devices(pe,
                                        table_group, dev->subordinate);
        }
}

static void pnv_ioda_setup_bus_iommu_group(struct pnv_ioda_pe *pe,
                struct iommu_table_group *table_group, struct pci_bus *bus)
{

        if (pe->flags & PNV_IODA_PE_DEV)
                iommu_add_device(table_group, &pe->pdev->dev);

        if ((pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) || bus)
                pnv_ioda_setup_bus_iommu_group_add_devices(pe, table_group,
                                bus);
}

static unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb);

static void pnv_pci_ioda_setup_iommu_api(void)
{
        struct pci_controller *hose;
        struct pnv_phb *phb;
        struct pnv_ioda_pe *pe;

        /*
         * There are 4 types of PEs:
         * - PNV_IODA_PE_BUS: a downstream port with an adapter,
         *   created from pnv_pci_setup_bridge();
         * - PNV_IODA_PE_BUS_ALL: a PCI-PCIX bridge with devices behind it,
         *   created from pnv_pci_setup_bridge();
         * - PNV_IODA_PE_VF: a SRIOV virtual function,
         *   created from pnv_pcibios_sriov_enable();
         * - PNV_IODA_PE_DEV: an NPU or OCAPI device,
         *   created from pnv_pci_ioda_fixup().
         *
         * Normally a PE is represented by an IOMMU group, however for
         * devices with side channels the groups need to be more strict.
         */
        list_for_each_entry(hose, &hose_list, list_node) {
                phb = hose->private_data;

                if (phb->type == PNV_PHB_NPU_NVLINK ||
                    phb->type == PNV_PHB_NPU_OCAPI)
                        continue;

                list_for_each_entry(pe, &phb->ioda.pe_list, list) {
                        struct iommu_table_group *table_group;

                        table_group = pnv_try_setup_npu_table_group(pe);
                        if (!table_group) {
                                if (!pnv_pci_ioda_pe_dma_weight(pe))
                                        continue;

                                table_group = &pe->table_group;
                                iommu_register_group(&pe->table_group,
                                                pe->phb->hose->global_number,
                                                pe->pe_number);
                        }
                        pnv_ioda_setup_bus_iommu_group(pe, table_group,
                                        pe->pbus);
                }
        }

        /*
         * Now we have all PHBs discovered, time to add NPU devices to
         * the corresponding IOMMU groups.
         */
        list_for_each_entry(hose, &hose_list, list_node) {
                unsigned long  pgsizes;

                phb = hose->private_data;

                if (phb->type != PNV_PHB_NPU_NVLINK)
                        continue;

                pgsizes = pnv_ioda_parse_tce_sizes(phb);
                list_for_each_entry(pe, &phb->ioda.pe_list, list) {
                        /*
                         * IODA2 bridges get this set up from
                         * pci_controller_ops::setup_bridge but NPU bridges
                         * do not have this hook defined so we do it here.
                         */
                        pe->table_group.pgsizes = pgsizes;
                        pnv_npu_compound_attach(pe);
                }
        }
}
#else /* !CONFIG_IOMMU_API */
static void pnv_pci_ioda_setup_iommu_api(void) { };
#endif

static unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb)
{
        struct pci_controller *hose = phb->hose;
        struct device_node *dn = hose->dn;
        unsigned long mask = 0;
        int i, rc, count;
        u32 val;

        count = of_property_count_u32_elems(dn, "ibm,supported-tce-sizes");
        if (count <= 0) {
                mask = SZ_4K | SZ_64K;
                /* Add 16M for POWER8 by default */
                if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
                                !cpu_has_feature(CPU_FTR_ARCH_300))
                        mask |= SZ_16M | SZ_256M;
                return mask;
        }

        for (i = 0; i < count; i++) {
                rc = of_property_read_u32_index(dn, "ibm,supported-tce-sizes",
                                                i, &val);
                if (rc == 0)
                        mask |= 1ULL << val;
        }

        return mask;
}

static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
                                       struct pnv_ioda_pe *pe)
{
        int64_t rc;

        if (!pnv_pci_ioda_pe_dma_weight(pe))
                return;

        /* TVE #1 is selected by PCI address bit 59 */
        pe->tce_bypass_base = 1ull << 59;

        /* The PE will reserve all possible 32-bits space */
        pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n",
                phb->ioda.m32_pci_base);

        /* Setup linux iommu table */
        pe->table_group.tce32_start = 0;
        pe->table_group.tce32_size = phb->ioda.m32_pci_base;
        pe->table_group.max_dynamic_windows_supported =
                        IOMMU_TABLE_GROUP_MAX_TABLES;
        pe->table_group.max_levels = POWERNV_IOMMU_MAX_LEVELS;
        pe->table_group.pgsizes = pnv_ioda_parse_tce_sizes(phb);
#ifdef CONFIG_IOMMU_API
        pe->table_group.ops = &pnv_pci_ioda2_ops;
#endif

        rc = pnv_pci_ioda2_setup_default_config(pe);
        if (rc)
                return;

        if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
                pnv_ioda_setup_bus_dma(pe, pe->pbus);
}

int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq)
{
        struct pnv_phb *phb = container_of(chip, struct pnv_phb,
                                           ioda.irq_chip);

        return opal_pci_msi_eoi(phb->opal_id, hw_irq);
}

static void pnv_ioda2_msi_eoi(struct irq_data *d)
{
        int64_t rc;
        unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
        struct irq_chip *chip = irq_data_get_irq_chip(d);

        rc = pnv_opal_pci_msi_eoi(chip, hw_irq);
        WARN_ON_ONCE(rc);

        icp_native_eoi(d);
}


void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
{
        struct irq_data *idata;
        struct irq_chip *ichip;

        /* The MSI EOI OPAL call is only needed on PHB3 */
        if (phb->model != PNV_PHB_MODEL_PHB3)
                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);
}

/*
 * Returns true iff chip is something that we could call
 * pnv_opal_pci_msi_eoi for.
 */
bool is_pnv_opal_msi(struct irq_chip *chip)
{
        return chip->irq_eoi == pnv_ioda2_msi_eoi;
}
EXPORT_SYMBOL_GPL(is_pnv_opal_msi);

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);
        unsigned int xive_num = hwirq - phb->msi_base;
        __be32 data;
        int rc;

        /* No PE assigned ? bail out ... no MSI for you ! */
        if (pe == NULL)
                return -ENXIO;

        /* Check if we have an MVE */
        if (pe->mve_number < 0)
                return -ENXIO;

        /* Force 32-bit MSI on some broken devices */
        if (dev->no_64bit_msi)
                is_64 = 0;

        /* Assign XIVE to PE */
        rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
        if (rc) {
                pr_warn("%s: OPAL error %d setting XIVE %d PE\n",
                        pci_name(dev), rc, xive_num);
                return -EIO;
        }

        if (is_64) {
                __be64 addr64;

                rc = opal_get_msi_64(phb->opal_id, pe->mve_number, xive_num, 1,
                                     &addr64, &data);
                if (rc) {
                        pr_warn("%s: OPAL error %d getting 64-bit MSI data\n",
                                pci_name(dev), rc);
                        return -EIO;
                }
                msg->address_hi = be64_to_cpu(addr64) >> 32;
                msg->address_lo = be64_to_cpu(addr64) & 0xfffffffful;
        } else {
                __be32 addr32;

                rc = opal_get_msi_32(phb->opal_id, pe->mve_number, xive_num, 1,
                                     &addr32, &data);
                if (rc) {
                        pr_warn("%s: OPAL error %d getting 32-bit MSI data\n",
                                pci_name(dev), rc);
                        return -EIO;
                }
                msg->address_hi = 0;
                msg->address_lo = be32_to_cpu(addr32);
        }
        msg->data = be32_to_cpu(data);

        pnv_set_msi_irq_chip(phb, virq);

        pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d),"
                 " address=%x_%08x data=%x PE# %x\n",
                 pci_name(dev), is_64 ? "64" : "32", hwirq, xive_num,
                 msg->address_hi, msg->address_lo, data, pe->pe_number);

        return 0;
}

static void pnv_pci_init_ioda_msis(struct pnv_phb *phb)
{
        unsigned int count;
        const __be32 *prop = of_get_property(phb->hose->dn,
                                             "ibm,opal-msi-ranges", NULL);
        if (!prop) {
                /* BML Fallback */
                prop = of_get_property(phb->hose->dn, "msi-ranges", NULL);
        }
        if (!prop)
                return;

        phb->msi_base = be32_to_cpup(prop);
        count = be32_to_cpup(prop + 1);
        if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) {
                pr_err("PCI %d: Failed to allocate MSI bitmap !\n",
                       phb->hose->global_number);
                return;
        }

        phb->msi_setup = pnv_pci_ioda_msi_setup;
        phb->msi32_support = 1;
        pr_info("  Allocated bitmap for %d MSIs (base IRQ 0x%x)\n",
                count, phb->msi_base);
}

#ifdef CONFIG_PCI_IOV
static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
{
        struct pci_controller *hose = pci_bus_to_host(pdev->bus);
        struct pnv_phb *phb = hose->private_data;
        const resource_size_t gate = phb->ioda.m64_segsize >> 2;
        struct resource *res;
        int i;
        resource_size_t size, total_vf_bar_sz;
        struct pci_dn *pdn;
        int mul, total_vfs;

        if (!pdev->is_physfn || pci_dev_is_added(pdev))
                return;

        pdn = pci_get_pdn(pdev);
        pdn->vfs_expanded = 0;
        pdn->m64_single_mode = false;

        total_vfs = pci_sriov_get_totalvfs(pdev);
        mul = phb->ioda.total_pe_num;
        total_vf_bar_sz = 0;

        for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
                res = &pdev->resource[i + PCI_IOV_RESOURCES];
                if (!res->flags || res->parent)
                        continue;
                if (!pnv_pci_is_m64_flags(res->flags)) {
                        dev_warn(&pdev->dev, "Don't support SR-IOV with"
                                        " non M64 VF BAR%d: %pR. \n",
                                 i, res);
                        goto truncate_iov;
                }

                total_vf_bar_sz += pci_iov_resource_size(pdev,
                                i + PCI_IOV_RESOURCES);

                /*
                 * If bigger than quarter of M64 segment size, just round up
                 * power of two.
                 *
                 * Generally, one M64 BAR maps one IOV BAR. To avoid conflict
                 * with other devices, IOV BAR size is expanded to be
                 * (total_pe * VF_BAR_size).  When VF_BAR_size is half of M64
                 * segment size , the expanded size would equal to half of the
                 * whole M64 space size, which will exhaust the M64 Space and
                 * limit the system flexibility.  This is a design decision to
                 * set the boundary to quarter of the M64 segment size.
                 */
                if (total_vf_bar_sz > gate) {
                        mul = roundup_pow_of_two(total_vfs);
                        dev_info(&pdev->dev,
                                "VF BAR Total IOV size %llx > %llx, roundup to %d VFs\n",
                                total_vf_bar_sz, gate, mul);
                        pdn->m64_single_mode = true;
                        break;
                }
        }

        for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
                res = &pdev->resource[i + PCI_IOV_RESOURCES];
                if (!res->flags || res->parent)
                        continue;

                size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES);
                /*
                 * On PHB3, the minimum size alignment of M64 BAR in single
                 * mode is 32MB.
                 */
                if (pdn->m64_single_mode && (size < SZ_32M))
                        goto truncate_iov;
                dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res);
                res->end = res->start + size * mul - 1;
                dev_dbg(&pdev->dev, "                       %pR\n", res);
                dev_info(&pdev->dev, "VF BAR%d: %pR (expanded to %d VFs for PE alignment)",
                         i, res, mul);
        }
        pdn->vfs_expanded = mul;

        return;

truncate_iov:
        /* To save MMIO space, IOV BAR is truncated. */
        for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
                res = &pdev->resource[i + PCI_IOV_RESOURCES];
                res->flags = 0;
                res->end = res->start - 1;
        }
}
#endif /* CONFIG_PCI_IOV */

static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
                                  struct resource *res)
{
        struct pnv_phb *phb = pe->phb;
        struct pci_bus_region region;
        int index;
        int64_t rc;

        if (!res || !res->flags || res->start > res->end)
                return;

        if (res->flags & IORESOURCE_IO) {
                region.start = res->start - phb->ioda.io_pci_base;
                region.end   = res->end - phb->ioda.io_pci_base;
                index = region.start / phb->ioda.io_segsize;

                while (index < phb->ioda.total_pe_num &&
                       region.start <= region.end) {
                        phb->ioda.io_segmap[index] = pe->pe_number;
                        rc = opal_pci_map_pe_mmio_window(phb->opal_id,