s390: Add PCI bus support

This patch implements a pci bus for s390x together with infrastructure
to generate and handle hotplug events, to configure/unconfigure via
sclp instruction, to do iommu translations and provide s390 support for
MSI/MSI-X notification processing.

Signed-off-by: Frank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>

MAINTAINERS

@@ -538,6 +538,7 @@ S390 Virtio
 M: Alexander Graf <agraf@suse.de>
 S: Maintained
 F: hw/s390x/s390-*.c
+X: hw/s390x/*pci*.[hc]
 
 S390 Virtio-ccw
 M: Cornelia Huck <cornelia.huck@de.ibm.com>
@@ -548,6 +549,7 @@ F: hw/s390x/s390-virtio-ccw.c
 F: hw/s390x/css.[hc]
 F: hw/s390x/sclp*.[hc]
 F: hw/s390x/ipl*.[hc]
+F: hw/s390x/*pci*.[hc]
 F: include/hw/s390x/
 F: pc-bios/s390-ccw/
 T: git git://github.com/cohuck/qemu virtio-ccw-upstr

default-configs/s390x-softmmu.mak

@@ -1,3 +1,4 @@
+include pci.mak
 CONFIG_VIRTIO=y
 CONFIG_SCLPCONSOLE=y
 CONFIG_S390_FLIC=y

hw/s390x/Makefile.objs

@@ -8,3 +8,4 @@ obj-y += ipl.o
 obj-y += css.o
 obj-y += s390-virtio-ccw.o
 obj-y += virtio-ccw.o
+obj-y += s390-pci-bus.o

hw/s390x/css.c

@@ -1299,6 +1299,11 @@ void css_generate_chp_crws(uint8_t cssid, uint8_t chpid)
     /* TODO */
 }
 
+void css_generate_css_crws(uint8_t cssid)
+{
+    css_queue_crw(CRW_RSC_CSS, 0, 0, cssid);
+}
+
 int css_enable_mcsse(void)
 {
     trace_css_enable_facility("mcsse");

hw/s390x/css.h

@@ -101,6 +101,7 @@ void css_queue_crw(uint8_t rsc, uint8_t erc, int chain, uint16_t rsid);
 void css_generate_sch_crws(uint8_t cssid, uint8_t ssid, uint16_t schid,
                            int hotplugged, int add);
 void css_generate_chp_crws(uint8_t cssid, uint8_t chpid);
+void css_generate_css_crws(uint8_t cssid);
 void css_adapter_interrupt(uint8_t isc);
 
 #define CSS_IO_ADAPTER_VIRTIO 1

hw/s390x/s390-pci-bus.c

@@ -0,0 +1,591 @@
+/*
+ * s390 PCI BUS
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Frank Blaschka <frank.blaschka@de.ibm.com>
+ *            Hong Bo Li <lihbbj@cn.ibm.com>
+ *            Yi Min Zhao <zyimin@cn.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or (at
+ * your option) any later version. See the COPYING file in the top-level
+ * directory.
+ */
+
+#include "s390-pci-bus.h"
+#include <hw/pci/pci_bus.h>
+#include <hw/pci/msi.h>
+#include <qemu/error-report.h>
+
+/* #define DEBUG_S390PCI_BUS */
+#ifdef DEBUG_S390PCI_BUS
+#define DPRINTF(fmt, ...) \
+    do { fprintf(stderr, "S390pci-bus: " fmt, ## __VA_ARGS__); } while (0)
+#else
+#define DPRINTF(fmt, ...) \
+    do { } while (0)
+#endif
+
+int chsc_sei_nt2_get_event(void *res)
+{
+    ChscSeiNt2Res *nt2_res = (ChscSeiNt2Res *)res;
+    PciCcdfAvail *accdf;
+    PciCcdfErr *eccdf;
+    int rc = 1;
+    SeiContainer *sei_cont;
+    S390pciState *s = S390_PCI_HOST_BRIDGE(
+        object_resolve_path(TYPE_S390_PCI_HOST_BRIDGE, NULL));
+
+    if (!s) {
+        return rc;
+    }
+
+    sei_cont = QTAILQ_FIRST(&s->pending_sei);
+    if (sei_cont) {
+        QTAILQ_REMOVE(&s->pending_sei, sei_cont, link);
+        nt2_res->nt = 2;
+        nt2_res->cc = sei_cont->cc;
+        switch (sei_cont->cc) {
+        case 1: /* error event */
+            eccdf = (PciCcdfErr *)nt2_res->ccdf;
+            eccdf->fid = cpu_to_be32(sei_cont->fid);
+            eccdf->fh = cpu_to_be32(sei_cont->fh);
+            eccdf->e = cpu_to_be32(sei_cont->e);
+            eccdf->faddr = cpu_to_be64(sei_cont->faddr);
+            eccdf->pec = cpu_to_be16(sei_cont->pec);
+            break;
+        case 2: /* availability event */
+            accdf = (PciCcdfAvail *)nt2_res->ccdf;
+            accdf->fid = cpu_to_be32(sei_cont->fid);
+            accdf->fh = cpu_to_be32(sei_cont->fh);
+            accdf->pec = cpu_to_be16(sei_cont->pec);
+            break;
+        default:
+            abort();
+        }
+        g_free(sei_cont);
+        rc = 0;
+    }
+
+    return rc;
+}
+
+int chsc_sei_nt2_have_event(void)
+{
+    S390pciState *s = S390_PCI_HOST_BRIDGE(
+        object_resolve_path(TYPE_S390_PCI_HOST_BRIDGE, NULL));
+
+    if (!s) {
+        return 0;
+    }
+
+    return !QTAILQ_EMPTY(&s->pending_sei);
+}
+
+S390PCIBusDevice *s390_pci_find_dev_by_fid(uint32_t fid)
+{
+    S390PCIBusDevice *pbdev;
+    int i;
+    S390pciState *s = S390_PCI_HOST_BRIDGE(
+        object_resolve_path(TYPE_S390_PCI_HOST_BRIDGE, NULL));
+
+    if (!s) {
+        return NULL;
+    }
+
+    for (i = 0; i < PCI_SLOT_MAX; i++) {
+        pbdev = &s->pbdev[i];
+        if ((pbdev->fh != 0) && (pbdev->fid == fid)) {
+            return pbdev;
+        }
+    }
+
+    return NULL;
+}
+
+void s390_pci_sclp_configure(int configure, SCCB *sccb)
+{
+    PciCfgSccb *psccb = (PciCfgSccb *)sccb;
+    S390PCIBusDevice *pbdev = s390_pci_find_dev_by_fid(be32_to_cpu(psccb->aid));
+    uint16_t rc;
+
+    if (pbdev) {
+        if ((configure == 1 && pbdev->configured == true) ||
+            (configure == 0 && pbdev->configured == false)) {
+            rc = SCLP_RC_NO_ACTION_REQUIRED;
+        } else {
+            pbdev->configured = !pbdev->configured;
+            rc = SCLP_RC_NORMAL_COMPLETION;
+        }
+    } else {
+        DPRINTF("sclp config %d no dev found\n", configure);
+        rc = SCLP_RC_ADAPTER_ID_NOT_RECOGNIZED;
+    }
+
+    psccb->header.response_code = cpu_to_be16(rc);
+    return;
+}
+
+static uint32_t s390_pci_get_pfid(PCIDevice *pdev)
+{
+    return PCI_SLOT(pdev->devfn);
+}
+
+static uint32_t s390_pci_get_pfh(PCIDevice *pdev)
+{
+    return PCI_SLOT(pdev->devfn) | FH_VIRT;
+}
+
+S390PCIBusDevice *s390_pci_find_dev_by_idx(uint32_t idx)
+{
+    S390PCIBusDevice *pbdev;
+    int i;
+    int j = 0;
+    S390pciState *s = S390_PCI_HOST_BRIDGE(
+        object_resolve_path(TYPE_S390_PCI_HOST_BRIDGE, NULL));
+
+    if (!s) {
+        return NULL;
+    }
+
+    for (i = 0; i < PCI_SLOT_MAX; i++) {
+        pbdev = &s->pbdev[i];
+
+        if (pbdev->fh == 0) {
+            continue;
+        }
+
+        if (j == idx) {
+            return pbdev;
+        }
+        j++;
+    }
+
+    return NULL;
+}
+
+S390PCIBusDevice *s390_pci_find_dev_by_fh(uint32_t fh)
+{
+    S390PCIBusDevice *pbdev;
+    int i;
+    S390pciState *s = S390_PCI_HOST_BRIDGE(
+        object_resolve_path(TYPE_S390_PCI_HOST_BRIDGE, NULL));
+
+    if (!s) {
+        return NULL;
+    }
+
+    for (i = 0; i < PCI_SLOT_MAX; i++) {
+        pbdev = &s->pbdev[i];
+        if (pbdev->fh == fh) {
+            return pbdev;
+        }
+    }
+
+    return NULL;
+}
+
+static void s390_pci_generate_event(uint8_t cc, uint16_t pec, uint32_t fh,
+                                    uint32_t fid, uint64_t faddr, uint32_t e)
+{
+    SeiContainer *sei_cont = g_malloc0(sizeof(SeiContainer));
+    S390pciState *s = S390_PCI_HOST_BRIDGE(
+        object_resolve_path(TYPE_S390_PCI_HOST_BRIDGE, NULL));
+
+    if (!s) {
+        return;
+    }
+
+    sei_cont->fh = fh;
+    sei_cont->fid = fid;
+    sei_cont->cc = cc;
+    sei_cont->pec = pec;
+    sei_cont->faddr = faddr;
+    sei_cont->e = e;
+
+    QTAILQ_INSERT_TAIL(&s->pending_sei, sei_cont, link);
+    css_generate_css_crws(0);
+}
+
+static void s390_pci_generate_plug_event(uint16_t pec, uint32_t fh,
+                                         uint32_t fid)
+{
+    s390_pci_generate_event(2, pec, fh, fid, 0, 0);
+}
+
+static void s390_pci_generate_error_event(uint16_t pec, uint32_t fh,
+                                          uint32_t fid, uint64_t faddr,
+                                          uint32_t e)
+{
+    s390_pci_generate_event(1, pec, fh, fid, faddr, e);
+}
+
+static void s390_pci_set_irq(void *opaque, int irq, int level)
+{
+    /* nothing to do */
+}
+
+static int s390_pci_map_irq(PCIDevice *pci_dev, int irq_num)
+{
+    /* nothing to do */
+    return 0;
+}
+
+static uint64_t s390_pci_get_table_origin(uint64_t iota)
+{
+    return iota & ~ZPCI_IOTA_RTTO_FLAG;
+}
+
+static unsigned int calc_rtx(dma_addr_t ptr)
+{
+    return ((unsigned long) ptr >> ZPCI_RT_SHIFT) & ZPCI_INDEX_MASK;
+}
+
+static unsigned int calc_sx(dma_addr_t ptr)
+{
+    return ((unsigned long) ptr >> ZPCI_ST_SHIFT) & ZPCI_INDEX_MASK;
+}
+
+static unsigned int calc_px(dma_addr_t ptr)
+{
+    return ((unsigned long) ptr >> PAGE_SHIFT) & ZPCI_PT_MASK;
+}
+
+static uint64_t get_rt_sto(uint64_t entry)
+{
+    return ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_RTX)
+                ? (entry & ZPCI_RTE_ADDR_MASK)
+                : 0;
+}
+
+static uint64_t get_st_pto(uint64_t entry)
+{
+    return ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_SX)
+            ? (entry & ZPCI_STE_ADDR_MASK)
+            : 0;
+}
+
+static uint64_t s390_guest_io_table_walk(uint64_t guest_iota,
+                                  uint64_t guest_dma_address)
+{
+    uint64_t sto_a, pto_a, px_a;
+    uint64_t sto, pto, pte;
+    uint32_t rtx, sx, px;
+
+    rtx = calc_rtx(guest_dma_address);
+    sx = calc_sx(guest_dma_address);
+    px = calc_px(guest_dma_address);
+
+    sto_a = guest_iota + rtx * sizeof(uint64_t);
+    sto = ldq_phys(&address_space_memory, sto_a);
+    sto = get_rt_sto(sto);
+    if (!sto) {
+        pte = 0;
+        goto out;
+    }
+
+    pto_a = sto + sx * sizeof(uint64_t);
+    pto = ldq_phys(&address_space_memory, pto_a);
+    pto = get_st_pto(pto);
+    if (!pto) {
+        pte = 0;
+        goto out;
+    }
+
+    px_a = pto + px * sizeof(uint64_t);
+    pte = ldq_phys(&address_space_memory, px_a);
+
+out:
+    return pte;
+}
+
+static IOMMUTLBEntry s390_translate_iommu(MemoryRegion *iommu, hwaddr addr,
+                                          bool is_write)
+{
+    uint64_t pte;
+    uint32_t flags;
+    S390PCIBusDevice *pbdev = container_of(iommu, S390PCIBusDevice, mr);
+    S390pciState *s = S390_PCI_HOST_BRIDGE(pci_device_root_bus(pbdev->pdev)
+                                           ->qbus.parent);
+    IOMMUTLBEntry ret = {
+        .target_as = &address_space_memory,
+        .iova = 0,
+        .translated_addr = 0,
+        .addr_mask = ~(hwaddr)0,
+        .perm = IOMMU_NONE,
+    };
+
+    DPRINTF("iommu trans addr 0x%" PRIx64 "\n", addr);
+
+    /* s390 does not have an APIC mapped to main storage so we use
+     * a separate AddressSpace only for msix notifications
+     */
+    if (addr == ZPCI_MSI_ADDR) {
+        ret.target_as = &s->msix_notify_as;
+        ret.iova = addr;
+        ret.translated_addr = addr;
+        ret.addr_mask = 0xfff;
+        ret.perm = IOMMU_RW;
+        return ret;
+    }
+
+    if (!pbdev->g_iota) {
+        pbdev->error_state = true;
+        pbdev->lgstg_blocked = true;
+        s390_pci_generate_error_event(ERR_EVENT_INVALAS, pbdev->fh, pbdev->fid,
+                                      addr, 0);
+        return ret;
+    }
+
+    if (addr < pbdev->pba || addr > pbdev->pal) {
+        pbdev->error_state = true;
+        pbdev->lgstg_blocked = true;
+        s390_pci_generate_error_event(ERR_EVENT_OORANGE, pbdev->fh, pbdev->fid,
+                                      addr, 0);
+        return ret;
+    }
+
+    pte = s390_guest_io_table_walk(s390_pci_get_table_origin(pbdev->g_iota),
+                                   addr);
+
+    if (!pte) {
+        pbdev->error_state = true;
+        pbdev->lgstg_blocked = true;
+        s390_pci_generate_error_event(ERR_EVENT_SERR, pbdev->fh, pbdev->fid,
+                                      addr, ERR_EVENT_Q_BIT);
+        return ret;
+    }
+
+    flags = pte & ZPCI_PTE_FLAG_MASK;
+    ret.iova = addr;
+    ret.translated_addr = pte & ZPCI_PTE_ADDR_MASK;
+    ret.addr_mask = 0xfff;
+
+    if (flags & ZPCI_PTE_INVALID) {
+        ret.perm = IOMMU_NONE;
+    } else {
+        ret.perm = IOMMU_RW;
+    }
+
+    return ret;
+}
+
+static const MemoryRegionIOMMUOps s390_iommu_ops = {
+    .translate = s390_translate_iommu,
+};
+
+static AddressSpace *s390_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn)
+{
+    S390pciState *s = opaque;
+
+    return &s->pbdev[PCI_SLOT(devfn)].as;
+}
+
+static uint8_t set_ind_atomic(uint64_t ind_loc, uint8_t to_be_set)
+{
+    uint8_t ind_old, ind_new;
+    hwaddr len = 1;
+    uint8_t *ind_addr;
+
+    ind_addr = cpu_physical_memory_map(ind_loc, &len, 1);
+    if (!ind_addr) {
+        s390_pci_generate_error_event(ERR_EVENT_AIRERR, 0, 0, 0, 0);
+        return -1;
+    }
+    do {
+        ind_old = *ind_addr;
+        ind_new = ind_old | to_be_set;
+    } while (atomic_cmpxchg(ind_addr, ind_old, ind_new) != ind_old);
+    cpu_physical_memory_unmap(ind_addr, len, 1, len);
+
+    return ind_old;
+}
+
+static void s390_msi_ctrl_write(void *opaque, hwaddr addr, uint64_t data,
+                                unsigned int size)
+{
+    S390PCIBusDevice *pbdev;
+    uint32_t io_int_word;
+    uint32_t fid = data >> ZPCI_MSI_VEC_BITS;
+    uint32_t vec = data & ZPCI_MSI_VEC_MASK;
+    uint64_t ind_bit;
+    uint32_t sum_bit;
+    uint32_t e = 0;
+
+    DPRINTF("write_msix data 0x%" PRIx64 " fid %d vec 0x%x\n", data, fid, vec);
+
+    pbdev = s390_pci_find_dev_by_fid(fid);
+    if (!pbdev) {
+        e |= (vec << ERR_EVENT_MVN_OFFSET);
+        s390_pci_generate_error_event(ERR_EVENT_NOMSI, 0, fid, addr, e);
+        return;
+    }
+
+    ind_bit = pbdev->routes.adapter.ind_offset;
+    sum_bit = pbdev->routes.adapter.summary_offset;
+
+    set_ind_atomic(pbdev->routes.adapter.ind_addr + (ind_bit + vec) / 8,
+                   0x80 >> ((ind_bit + vec) % 8));
+    if (!set_ind_atomic(pbdev->routes.adapter.summary_addr + sum_bit / 8,
+                                       0x80 >> (sum_bit % 8))) {
+        io_int_word = (pbdev->isc << 27) | IO_INT_WORD_AI;
+        s390_io_interrupt(0, 0, 0, io_int_word);
+    }
+
+    return;
+}
+
+static uint64_t s390_msi_ctrl_read(void *opaque, hwaddr addr, unsigned size)
+{
+    return 0xffffffff;
+}
+
+static const MemoryRegionOps s390_msi_ctrl_ops = {
+    .write = s390_msi_ctrl_write,
+    .read = s390_msi_ctrl_read,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+};
+
+static void s390_pcihost_init_as(S390pciState *s)
+{
+    int i;
+
+    for (i = 0; i < PCI_SLOT_MAX; i++) {
+        memory_region_init_iommu(&s->pbdev[i].mr, OBJECT(s),
+                                 &s390_iommu_ops, "iommu-s390", UINT64_MAX);
+        address_space_init(&s->pbdev[i].as, &s->pbdev[i].mr, "iommu-pci");
+    }
+
+    memory_region_init_io(&s->msix_notify_mr, OBJECT(s),
+                          &s390_msi_ctrl_ops, s, "msix-s390", UINT64_MAX);
+    address_space_init(&s->msix_notify_as, &s->msix_notify_mr, "msix-pci");
+}
+
+static int s390_pcihost_init(SysBusDevice *dev)
+{
+    PCIBus *b;
+    BusState *bus;
+    PCIHostState *phb = PCI_HOST_BRIDGE(dev);
+    S390pciState *s = S390_PCI_HOST_BRIDGE(dev);
+
+    DPRINTF("host_init\n");
+
+    b = pci_register_bus(DEVICE(dev), NULL,
+                         s390_pci_set_irq, s390_pci_map_irq, NULL,
+                         get_system_memory(), get_system_io(), 0, 64,
+                         TYPE_PCI_BUS);
+    s390_pcihost_init_as(s);
+    pci_setup_iommu(b, s390_pci_dma_iommu, s);
+
+    bus = BUS(b);
+    qbus_set_hotplug_handler(bus, DEVICE(dev), NULL);
+    phb->bus = b;
+    QTAILQ_INIT(&s->pending_sei);
+    return 0;
+}
+
+static int s390_pcihost_setup_msix(S390PCIBusDevice *pbdev)
+{
+    uint8_t pos;
+    uint16_t ctrl;
+    uint32_t table, pba;
+
+    pos = pci_find_capability(pbdev->pdev, PCI_CAP_ID_MSIX);
+    if (!pos) {
+        pbdev->msix.available = false;
+        return 0;
+    }
+
+    ctrl = pci_host_config_read_common(pbdev->pdev, pos + PCI_CAP_FLAGS,
+             pci_config_size(pbdev->pdev), sizeof(ctrl));
+    table = pci_host_config_read_common(pbdev->pdev, pos + PCI_MSIX_TABLE,
+             pci_config_size(pbdev->pdev), sizeof(table));
+    pba = pci_host_config_read_common(pbdev->pdev, pos + PCI_MSIX_PBA,
+             pci_config_size(pbdev->pdev), sizeof(pba));
+
+    pbdev->msix.table_bar = table & PCI_MSIX_FLAGS_BIRMASK;
+    pbdev->msix.table_offset = table & ~PCI_MSIX_FLAGS_BIRMASK;
+    pbdev->msix.pba_bar = pba & PCI_MSIX_FLAGS_BIRMASK;
+    pbdev->msix.pba_offset = pba & ~PCI_MSIX_FLAGS_BIRMASK;
+    pbdev->msix.entries = (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1;
+    pbdev->msix.available = true;
+    return 0;
+}
+
+static void s390_pcihost_hot_plug(HotplugHandler *hotplug_dev,
+                                  DeviceState *dev, Error **errp)
+{
+    PCIDevice *pci_dev = PCI_DEVICE(dev);
+    S390PCIBusDevice *pbdev;
+    S390pciState *s = S390_PCI_HOST_BRIDGE(pci_device_root_bus(pci_dev)
+                                           ->qbus.parent);
+
+    pbdev = &s->pbdev[PCI_SLOT(pci_dev->devfn)];
+
+    pbdev->fid = s390_pci_get_pfid(pci_dev);
+    pbdev->pdev = pci_dev;
+    pbdev->configured = true;
+    pbdev->fh = s390_pci_get_pfh(pci_dev);
+
+    s390_pcihost_setup_msix(pbdev);
+
+    if (dev->hotplugged) {
+        s390_pci_generate_plug_event(HP_EVENT_RESERVED_TO_STANDBY,
+                                     pbdev->fh, pbdev->fid);
+        s390_pci_generate_plug_event(HP_EVENT_TO_CONFIGURED,
+                                     pbdev->fh, pbdev->fid);
+    }
+    return;
+}
+
+static void s390_pcihost_hot_unplug(HotplugHandler *hotplug_dev,
+                                    DeviceState *dev, Error **errp)
+{
+    PCIDevice *pci_dev = PCI_DEVICE(dev);
+    S390pciState *s = S390_PCI_HOST_BRIDGE(pci_device_root_bus(pci_dev)
+                                           ->qbus.parent);
+    S390PCIBusDevice *pbdev = &s->pbdev[PCI_SLOT(pci_dev->devfn)];
+
+    if (pbdev->configured) {
+        pbdev->configured = false;
+        s390_pci_generate_plug_event(HP_EVENT_CONFIGURED_TO_STBRES,
+                                     pbdev->fh, pbdev->fid);
+    }
+
+    s390_pci_generate_plug_event(HP_EVENT_STANDBY_TO_RESERVED,
+                                 pbdev->fh, pbdev->fid);
+    pbdev->fh = 0;
+    pbdev->fid = 0;
+    pbdev->pdev = NULL;
+    object_unparent(OBJECT(pci_dev));
+}
+
+static void s390_pcihost_class_init(ObjectClass *klass, void *data)
+{
+    SysBusDeviceClass *k = SYS_BUS_DEVICE_CLASS(klass);
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(klass);
+
+    dc->cannot_instantiate_with_device_add_yet = true;
+    k->init = s390_pcihost_init;
+    hc->plug = s390_pcihost_hot_plug;
+    hc->unplug = s390_pcihost_hot_unplug;
+    msi_supported = true;
+}
+
+static const TypeInfo s390_pcihost_info = {
+    .name          = TYPE_S390_PCI_HOST_BRIDGE,
+    .parent        = TYPE_PCI_HOST_BRIDGE,
+    .instance_size = sizeof(S390pciState),
+    .class_init    = s390_pcihost_class_init,
+    .interfaces = (InterfaceInfo[]) {
+        { TYPE_HOTPLUG_HANDLER },
+        { }
+    }
+};
+
+static void s390_pci_register_types(void)
+{
+    type_register_static(&s390_pcihost_info);
+}
+
+type_init(s390_pci_register_types)

hw/s390x/s390-pci-bus.h

@@ -0,0 +1,251 @@
+/*
+ * s390 PCI BUS definitions
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Frank Blaschka <frank.blaschka@de.ibm.com>
+ *            Hong Bo Li <lihbbj@cn.ibm.com>
+ *            Yi Min Zhao <zyimin@cn.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or (at
+ * your option) any later version. See the COPYING file in the top-level
+ * directory.
+ */
+
+#ifndef HW_S390_PCI_BUS_H
+#define HW_S390_PCI_BUS_H
+
+#include <hw/pci/pci.h>
+#include <hw/pci/pci_host.h>
+#include "hw/s390x/sclp.h"
+#include "hw/s390x/s390_flic.h"
+#include "hw/s390x/css.h"
+
+#define TYPE_S390_PCI_HOST_BRIDGE "s390-pcihost"
+#define FH_VIRT 0x00ff0000
+#define ENABLE_BIT_OFFSET 31
+#define S390_PCIPT_ADAPTER 2
+
+#define S390_PCI_HOST_BRIDGE(obj) \
+    OBJECT_CHECK(S390pciState, (obj), TYPE_S390_PCI_HOST_BRIDGE)
+
+#define HP_EVENT_TO_CONFIGURED        0x0301
+#define HP_EVENT_RESERVED_TO_STANDBY  0x0302
+#define HP_EVENT_CONFIGURED_TO_STBRES 0x0304
+#define HP_EVENT_STANDBY_TO_RESERVED  0x0308
+
+#define ERR_EVENT_INVALAS 0x1
+#define ERR_EVENT_OORANGE 0x2
+#define ERR_EVENT_INVALTF 0x3
+#define ERR_EVENT_TPROTE  0x4
+#define ERR_EVENT_APROTE  0x5
+#define ERR_EVENT_KEYE    0x6
+#define ERR_EVENT_INVALTE 0x7
+#define ERR_EVENT_INVALTL 0x8
+#define ERR_EVENT_TT      0x9
+#define ERR_EVENT_INVALMS 0xa
+#define ERR_EVENT_SERR    0xb
+#define ERR_EVENT_NOMSI   0x10
+#define ERR_EVENT_INVALBV 0x11
+#define ERR_EVENT_AIBV    0x12
+#define ERR_EVENT_AIRERR  0x13
+#define ERR_EVENT_FMBA    0x2a
+#define ERR_EVENT_FMBUP   0x2b
+#define ERR_EVENT_FMBPRO  0x2c
+#define ERR_EVENT_CCONF   0x30
+#define ERR_EVENT_SERVAC  0x3a
+#define ERR_EVENT_PERMERR 0x3b
+
+#define ERR_EVENT_Q_BIT 0x2
+#define ERR_EVENT_MVN_OFFSET 16
+
+#define ZPCI_MSI_VEC_BITS 11
+#define ZPCI_MSI_VEC_MASK 0x7ff
+
+#define ZPCI_MSI_ADDR  0xfe00000000000000ULL
+#define ZPCI_SDMA_ADDR 0x100000000ULL
+#define ZPCI_EDMA_ADDR 0x1ffffffffffffffULL
+
+#define PAGE_SHIFT      12
+#define PAGE_MASK       (~(PAGE_SIZE-1))
+#define PAGE_DEFAULT_ACC        0
+#define PAGE_DEFAULT_KEY        (PAGE_DEFAULT_ACC << 4)
+
+/* I/O Translation Anchor (IOTA) */
+enum ZpciIoatDtype {
+    ZPCI_IOTA_STO = 0,
+    ZPCI_IOTA_RTTO = 1,
+    ZPCI_IOTA_RSTO = 2,
+    ZPCI_IOTA_RFTO = 3,
+    ZPCI_IOTA_PFAA = 4,
+    ZPCI_IOTA_IOPFAA = 5,
+    ZPCI_IOTA_IOPTO = 7
+};
+
+#define ZPCI_IOTA_IOT_ENABLED           0x800ULL
+#define ZPCI_IOTA_DT_ST                 (ZPCI_IOTA_STO  << 2)
+#define ZPCI_IOTA_DT_RT                 (ZPCI_IOTA_RTTO << 2)
+#define ZPCI_IOTA_DT_RS                 (ZPCI_IOTA_RSTO << 2)
+#define ZPCI_IOTA_DT_RF                 (ZPCI_IOTA_RFTO << 2)
+#define ZPCI_IOTA_DT_PF                 (ZPCI_IOTA_PFAA << 2)
+#define ZPCI_IOTA_FS_4K                 0
+#define ZPCI_IOTA_FS_1M                 1
+#define ZPCI_IOTA_FS_2G                 2
+#define ZPCI_KEY                        (PAGE_DEFAULT_KEY << 5)
+
+#define ZPCI_IOTA_STO_FLAG  (ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_ST)
+#define ZPCI_IOTA_RTTO_FLAG (ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RT)
+#define ZPCI_IOTA_RSTO_FLAG (ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RS)
+#define ZPCI_IOTA_RFTO_FLAG (ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RF)
+#define ZPCI_IOTA_RFAA_FLAG (ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY |\
+                             ZPCI_IOTA_DT_PF | ZPCI_IOTA_FS_2G)
+
+/* I/O Region and segment tables */
+#define ZPCI_INDEX_MASK         0x7ffULL
+
+#define ZPCI_TABLE_TYPE_MASK    0xc
+#define ZPCI_TABLE_TYPE_RFX     0xc
+#define ZPCI_TABLE_TYPE_RSX     0x8
+#define ZPCI_TABLE_TYPE_RTX     0x4
+#define ZPCI_TABLE_TYPE_SX      0x0
+
+#define ZPCI_TABLE_LEN_RFX      0x3
+#define ZPCI_TABLE_LEN_RSX      0x3
+#define ZPCI_TABLE_LEN_RTX      0x3
+
+#define ZPCI_TABLE_OFFSET_MASK  0xc0
+#define ZPCI_TABLE_SIZE         0x4000
+#define ZPCI_TABLE_ALIGN        ZPCI_TABLE_SIZE
+#define ZPCI_TABLE_ENTRY_SIZE   (sizeof(unsigned long))
+#define ZPCI_TABLE_ENTRIES      (ZPCI_TABLE_SIZE / ZPCI_TABLE_ENTRY_SIZE)
+
+#define ZPCI_TABLE_BITS         11
+#define ZPCI_PT_BITS            8
+#define ZPCI_ST_SHIFT           (ZPCI_PT_BITS + PAGE_SHIFT)
+#define ZPCI_RT_SHIFT           (ZPCI_ST_SHIFT + ZPCI_TABLE_BITS)
+
+#define ZPCI_RTE_FLAG_MASK      0x3fffULL
+#define ZPCI_RTE_ADDR_MASK      (~ZPCI_RTE_FLAG_MASK)
+#define ZPCI_STE_FLAG_MASK      0x7ffULL
+#define ZPCI_STE_ADDR_MASK      (~ZPCI_STE_FLAG_MASK)
+
+/* I/O Page tables */
+#define ZPCI_PTE_VALID_MASK             0x400
+#define ZPCI_PTE_INVALID                0x400
+#define ZPCI_PTE_VALID                  0x000
+#define ZPCI_PT_SIZE                    0x800
+#define ZPCI_PT_ALIGN                   ZPCI_PT_SIZE
+#define ZPCI_PT_ENTRIES                 (ZPCI_PT_SIZE / ZPCI_TABLE_ENTRY_SIZE)
+#define ZPCI_PT_MASK                    (ZPCI_PT_ENTRIES - 1)
+
+#define ZPCI_PTE_FLAG_MASK              0xfffULL
+#define ZPCI_PTE_ADDR_MASK              (~ZPCI_PTE_FLAG_MASK)
+
+/* Shared bits */
+#define ZPCI_TABLE_VALID                0x00
+#define ZPCI_TABLE_INVALID              0x20
+#define ZPCI_TABLE_PROTECTED            0x200
+#define ZPCI_TABLE_UNPROTECTED          0x000
+
+#define ZPCI_TABLE_VALID_MASK           0x20
+#define ZPCI_TABLE_PROT_MASK            0x200
+
+typedef struct SeiContainer {
+    QTAILQ_ENTRY(SeiContainer) link;
+    uint32_t fid;
+    uint32_t fh;
+    uint8_t cc;
+    uint16_t pec;
+    uint64_t faddr;
+    uint32_t e;
+} SeiContainer;
+
+typedef struct PciCcdfErr {
+    uint32_t reserved1;
+    uint32_t fh;
+    uint32_t fid;
+    uint32_t e;
+    uint64_t faddr;
+    uint32_t reserved3;
+    uint16_t reserved4;
+    uint16_t pec;
+} QEMU_PACKED PciCcdfErr;
+
+typedef struct PciCcdfAvail {
+    uint32_t reserved1;
+    uint32_t fh;
+    uint32_t fid;
+    uint32_t reserved2;
+    uint32_t reserved3;
+    uint32_t reserved4;
+    uint32_t reserved5;
+    uint16_t reserved6;
+    uint16_t pec;
+} QEMU_PACKED PciCcdfAvail;
+
+typedef struct ChscSeiNt2Res {
+    uint16_t length;
+    uint16_t code;
+    uint16_t reserved1;
+    uint8_t reserved2;
+    uint8_t nt;
+    uint8_t flags;
+    uint8_t reserved3;
+    uint8_t reserved4;
+    uint8_t cc;
+    uint32_t reserved5[13];
+    uint8_t ccdf[4016];
+} QEMU_PACKED ChscSeiNt2Res;
+
+typedef struct PciCfgSccb {
+        SCCBHeader header;
+        uint8_t atype;
+        uint8_t reserved1;
+        uint16_t reserved2;
+        uint32_t aid;
+} QEMU_PACKED PciCfgSccb;
+
+typedef struct S390MsixInfo {
+    bool available;
+    uint8_t table_bar;
+    uint8_t pba_bar;
+    uint16_t entries;
+    uint32_t table_offset;
+    uint32_t pba_offset;
+} S390MsixInfo;
+
+typedef struct S390PCIBusDevice {
+    PCIDevice *pdev;
+    bool configured;
+    bool error_state;
+    bool lgstg_blocked;
+    uint32_t fh;
+    uint32_t fid;
+    uint64_t g_iota;
+    uint64_t pba;
+    uint64_t pal;
+    uint64_t fmb_addr;
+    uint8_t isc;
+    uint16_t noi;
+    uint8_t sum;
+    S390MsixInfo msix;
+    AdapterRoutes routes;
+    AddressSpace as;
+    MemoryRegion mr;
+} S390PCIBusDevice;
+
+typedef struct S390pciState {
+    PCIHostState parent_obj;
+    S390PCIBusDevice pbdev[PCI_SLOT_MAX];
+    AddressSpace msix_notify_as;
+    MemoryRegion msix_notify_mr;
+    QTAILQ_HEAD(, SeiContainer) pending_sei;
+} S390pciState;
+
+int chsc_sei_nt2_get_event(void *res);
+int chsc_sei_nt2_have_event(void);
+void s390_pci_sclp_configure(int configure, SCCB *sccb);
+S390PCIBusDevice *s390_pci_find_dev_by_idx(uint32_t idx);
+S390PCIBusDevice *s390_pci_find_dev_by_fh(uint32_t fh);
+S390PCIBusDevice *s390_pci_find_dev_by_fid(uint32_t fid);
+
+#endif

hw/s390x/s390-virtio-ccw.c

@@ -18,6 +18,7 @@
 #include "css.h"
 #include "virtio-ccw.h"
 #include "qemu/config-file.h"
+#include "s390-pci-bus.h"
 
 #define TYPE_S390_CCW_MACHINE               "s390-ccw-machine"
 
@@ -91,6 +92,7 @@ static void ccw_init(MachineState *machine)
     uint8_t *storage_keys;
     int ret;
     VirtualCssBus *css_bus;
+    DeviceState *dev;
     QemuOpts *opts = qemu_opts_find(qemu_find_opts("memory"), NULL);
     ram_addr_t pad_size = 0;
     ram_addr_t maxmem = qemu_opt_get_size(opts, "maxmem", my_ram_size);
@@ -127,6 +129,11 @@ static void ccw_init(MachineState *machine)
                       machine->initrd_filename, "s390-ccw.img");
     s390_flic_init();
 
+    dev = qdev_create(NULL, TYPE_S390_PCI_HOST_BRIDGE);
+    object_property_add_child(qdev_get_machine(), TYPE_S390_PCI_HOST_BRIDGE,
+                              OBJECT(dev), NULL);
+    qdev_init_nofail(dev);
+
     /* register hypercalls */
     virtio_ccw_register_hcalls();
 

hw/s390x/sclp.c

@@ -20,6 +20,7 @@
 #include "qemu/config-file.h"
 #include "hw/s390x/sclp.h"
 #include "hw/s390x/event-facility.h"
+#include "hw/s390x/s390-pci-bus.h"
 
 static inline SCLPEventFacility *get_event_facility(void)
 {
@@ -62,7 +63,8 @@ static void read_SCP_info(SCCB *sccb)
         read_info->entries[i].type = 0;
     }
 
-    read_info->facilities = cpu_to_be64(SCLP_HAS_CPU_INFO);
+    read_info->facilities = cpu_to_be64(SCLP_HAS_CPU_INFO |
+                                        SCLP_HAS_PCI_RECONFIG);
 
     /*
      * The storage increment size is a multiple of 1M and is a power of 2.
@@ -350,6 +352,12 @@ static void sclp_execute(SCCB *sccb, uint32_t code)
     case SCLP_UNASSIGN_STORAGE:
         unassign_storage(sccb);
         break;
+    case SCLP_CMDW_CONFIGURE_PCI:
+        s390_pci_sclp_configure(1, sccb);
+        break;
+    case SCLP_CMDW_DECONFIGURE_PCI:
+        s390_pci_sclp_configure(0, sccb);
+        break;
     default:
         efc->command_handler(ef, sccb, code);
         break;

include/hw/s390x/sclp.h

@@ -43,14 +43,22 @@
 #define SCLP_CMDW_CONFIGURE_CPU                 0x00110001
 #define SCLP_CMDW_DECONFIGURE_CPU               0x00100001
 
+/* SCLP PCI codes */
+#define SCLP_HAS_PCI_RECONFIG                   0x0000000040000000ULL
+#define SCLP_CMDW_CONFIGURE_PCI                 0x001a0001
+#define SCLP_CMDW_DECONFIGURE_PCI               0x001b0001
+#define SCLP_RECONFIG_PCI_ATPYE                 2
+
 /* SCLP response codes */
 #define SCLP_RC_NORMAL_READ_COMPLETION          0x0010
 #define SCLP_RC_NORMAL_COMPLETION               0x0020
 #define SCLP_RC_SCCB_BOUNDARY_VIOLATION         0x0100
+#define SCLP_RC_NO_ACTION_REQUIRED              0x0120
 #define SCLP_RC_INVALID_SCLP_COMMAND            0x01f0
 #define SCLP_RC_CONTAINED_EQUIPMENT_CHECK       0x0340
 #define SCLP_RC_INSUFFICIENT_SCCB_LENGTH        0x0300
 #define SCLP_RC_STANDBY_READ_COMPLETION         0x0410
+#define SCLP_RC_ADAPTER_ID_NOT_RECOGNIZED       0x09f0
 #define SCLP_RC_INVALID_FUNCTION                0x40f0
 #define SCLP_RC_NO_EVENT_BUFFERS_STORED         0x60f0
 #define SCLP_RC_INVALID_SELECTION_MASK          0x70f0

target-s390x/ioinst.c

@@ -14,6 +14,7 @@
 #include "cpu.h"
 #include "ioinst.h"
 #include "trace.h"
+#include "hw/s390x/s390-pci-bus.h"
 
 int ioinst_disassemble_sch_ident(uint32_t value, int *m, int *cssid, int *ssid,
                                  int *schid)
@@ -398,6 +399,7 @@ typedef struct ChscResp {
 #define CHSC_SCPD 0x0002
 #define CHSC_SCSC 0x0010
 #define CHSC_SDA  0x0031
+#define CHSC_SEI  0x000e
 
 #define CHSC_SCPD_0_M 0x20000000
 #define CHSC_SCPD_0_C 0x10000000
@@ -566,6 +568,53 @@ out:
     res->param = 0;
 }
 
+static int chsc_sei_nt0_get_event(void *res)
+{
+    /* no events yet */
+    return 1;
+}
+
+static int chsc_sei_nt0_have_event(void)
+{
+    /* no events yet */
+    return 0;
+}
+
+#define CHSC_SEI_NT0    (1ULL << 63)
+#define CHSC_SEI_NT2    (1ULL << 61)
+static void ioinst_handle_chsc_sei(ChscReq *req, ChscResp *res)
+{
+    uint64_t selection_mask = ldq_p(&req->param1);
+    uint8_t *res_flags = (uint8_t *)res->data;
+    int have_event = 0;
+    int have_more = 0;
+
+    /* regarding architecture nt0 can not be masked */
+    have_event = !chsc_sei_nt0_get_event(res);
+    have_more = chsc_sei_nt0_have_event();
+
+    if (selection_mask & CHSC_SEI_NT2) {
+        if (!have_event) {
+            have_event = !chsc_sei_nt2_get_event(res);
+        }
+
+        if (!have_more) {
+            have_more = chsc_sei_nt2_have_event();
+        }
+    }
+
+    if (have_event) {
+        res->code = cpu_to_be16(0x0001);
+        if (have_more) {
+            (*res_flags) |= 0x80;
+        } else {
+            (*res_flags) &= ~0x80;
+        }
+    } else {
+        res->code = cpu_to_be16(0x0004);
+    }
+}
+
 static void ioinst_handle_chsc_unimplemented(ChscResp *res)
 {
     res->len = cpu_to_be16(CHSC_MIN_RESP_LEN);
@@ -617,6 +666,9 @@ void ioinst_handle_chsc(S390CPU *cpu, uint32_t ipb)
     case CHSC_SDA:
         ioinst_handle_chsc_sda(req, res);
         break;
+    case CHSC_SEI:
+        ioinst_handle_chsc_sei(req, res);
+        break;
     default:
         ioinst_handle_chsc_unimplemented(res);
         break;

target-s390x/ioinst.h

@@ -204,6 +204,7 @@ typedef struct CRW {
 
 #define CRW_RSC_SUBCH 0x3
 #define CRW_RSC_CHP   0x4
+#define CRW_RSC_CSS   0xb
 
 /* I/O interruption code */
 typedef struct IOIntCode {