Initial import

9 files changed, 2631 insertions, 0 deletions

diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
new file mode 100644
index 000000000..805d8b291
--- /dev/null
+++ b/arch/s390/pci/Makefile
@@ -0,0 +1,6 @@
+#
+# Makefile for the s390 PCI subsystem.
+#
+
+obj-$(CONFIG_PCI)	+= pci.o pci_dma.o pci_clp.o pci_sysfs.o \
+			   pci_event.o pci_debug.o pci_insn.o pci_mmio.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
new file mode 100644
index 000000000..598f023cf
--- /dev/null
+++ b/arch/s390/pci/pci.c
@@ -0,0 +1,965 @@
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ *
+ * The System z PCI code is a rewrite from a prototype by
+ * the following people (Kudoz!):
+ *   Alexander Schmidt
+ *   Christoph Raisch
+ *   Hannes Hering
+ *   Hoang-Nam Nguyen
+ *   Jan-Bernd Themann
+ *   Stefan Roscher
+ *   Thomas Klein
+ */
+
+#define KMSG_COMPONENT "zpci"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/kernel_stat.h>
+#include <linux/seq_file.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+
+#include <asm/isc.h>
+#include <asm/airq.h>
+#include <asm/facility.h>
+#include <asm/pci_insn.h>
+#include <asm/pci_clp.h>
+#include <asm/pci_dma.h>
+
+#define DEBUG				/* enable pr_debug */
+
+#define	SIC_IRQ_MODE_ALL		0
+#define	SIC_IRQ_MODE_SINGLE		1
+
+#define ZPCI_NR_DMA_SPACES		1
+#define ZPCI_NR_DEVICES			CONFIG_PCI_NR_FUNCTIONS
+
+/* list of all detected zpci devices */
+static LIST_HEAD(zpci_list);
+static DEFINE_SPINLOCK(zpci_list_lock);
+
+static struct irq_chip zpci_irq_chip = {
+	.name = "zPCI",
+	.irq_unmask = pci_msi_unmask_irq,
+	.irq_mask = pci_msi_mask_irq,
+};
+
+static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
+static DEFINE_SPINLOCK(zpci_domain_lock);
+
+static struct airq_iv *zpci_aisb_iv;
+static struct airq_iv *zpci_aibv[ZPCI_NR_DEVICES];
+
+/* Adapter interrupt definitions */
+static void zpci_irq_handler(struct airq_struct *airq);
+
+static struct airq_struct zpci_airq = {
+	.handler = zpci_irq_handler,
+	.isc = PCI_ISC,
+};
+
+/* I/O Map */
+static DEFINE_SPINLOCK(zpci_iomap_lock);
+static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
+struct zpci_iomap_entry *zpci_iomap_start;
+EXPORT_SYMBOL_GPL(zpci_iomap_start);
+
+static struct kmem_cache *zdev_fmb_cache;
+
+struct zpci_dev *get_zdev(struct pci_dev *pdev)
+{
+	return (struct zpci_dev *) pdev->sysdata;
+}
+
+struct zpci_dev *get_zdev_by_fid(u32 fid)
+{
+	struct zpci_dev *tmp, *zdev = NULL;
+
+	spin_lock(&zpci_list_lock);
+	list_for_each_entry(tmp, &zpci_list, entry) {
+		if (tmp->fid == fid) {
+			zdev = tmp;
+			break;
+		}
+	}
+	spin_unlock(&zpci_list_lock);
+	return zdev;
+}
+
+static struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus)
+{
+	return (bus && bus->sysdata) ? (struct zpci_dev *) bus->sysdata : NULL;
+}
+
+int pci_domain_nr(struct pci_bus *bus)
+{
+	return ((struct zpci_dev *) bus->sysdata)->domain;
+}
+EXPORT_SYMBOL_GPL(pci_domain_nr);
+
+int pci_proc_domain(struct pci_bus *bus)
+{
+	return pci_domain_nr(bus);
+}
+EXPORT_SYMBOL_GPL(pci_proc_domain);
+
+/* Modify PCI: Register adapter interruptions */
+static int zpci_set_airq(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
+	struct zpci_fib fib = {0};
+
+	fib.isc = PCI_ISC;
+	fib.sum = 1;		/* enable summary notifications */
+	fib.noi = airq_iv_end(zdev->aibv);
+	fib.aibv = (unsigned long) zdev->aibv->vector;
+	fib.aibvo = 0;		/* each zdev has its own interrupt vector */
+	fib.aisb = (unsigned long) zpci_aisb_iv->vector + (zdev->aisb/64)*8;
+	fib.aisbo = zdev->aisb & 63;
+
+	return zpci_mod_fc(req, &fib);
+}
+
+struct mod_pci_args {
+	u64 base;
+	u64 limit;
+	u64 iota;
+	u64 fmb_addr;
+};
+
+static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args *args)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, dmaas, fn);
+	struct zpci_fib fib = {0};
+
+	fib.pba = args->base;
+	fib.pal = args->limit;
+	fib.iota = args->iota;
+	fib.fmb_addr = args->fmb_addr;
+
+	return zpci_mod_fc(req, &fib);
+}
+
+/* Modify PCI: Register I/O address translation parameters */
+int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
+		       u64 base, u64 limit, u64 iota)
+{
+	struct mod_pci_args args = { base, limit, iota, 0 };
+
+	WARN_ON_ONCE(iota & 0x3fff);
+	args.iota |= ZPCI_IOTA_RTTO_FLAG;
+	return mod_pci(zdev, ZPCI_MOD_FC_REG_IOAT, dmaas, &args);
+}
+
+/* Modify PCI: Unregister I/O address translation parameters */
+int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
+{
+	struct mod_pci_args args = { 0, 0, 0, 0 };
+
+	return mod_pci(zdev, ZPCI_MOD_FC_DEREG_IOAT, dmaas, &args);
+}
+
+/* Modify PCI: Unregister adapter interruptions */
+static int zpci_clear_airq(struct zpci_dev *zdev)
+{
+	struct mod_pci_args args = { 0, 0, 0, 0 };
+
+	return mod_pci(zdev, ZPCI_MOD_FC_DEREG_INT, 0, &args);
+}
+
+/* Modify PCI: Set PCI function measurement parameters */
+int zpci_fmb_enable_device(struct zpci_dev *zdev)
+{
+	struct mod_pci_args args = { 0, 0, 0, 0 };
+
+	if (zdev->fmb)
+		return -EINVAL;
+
+	zdev->fmb = kmem_cache_zalloc(zdev_fmb_cache, GFP_KERNEL);
+	if (!zdev->fmb)
+		return -ENOMEM;
+	WARN_ON((u64) zdev->fmb & 0xf);
+
+	/* reset software counters */
+	atomic64_set(&zdev->allocated_pages, 0);
+	atomic64_set(&zdev->mapped_pages, 0);
+	atomic64_set(&zdev->unmapped_pages, 0);
+
+	args.fmb_addr = virt_to_phys(zdev->fmb);
+	return mod_pci(zdev, ZPCI_MOD_FC_SET_MEASURE, 0, &args);
+}
+
+/* Modify PCI: Disable PCI function measurement */
+int zpci_fmb_disable_device(struct zpci_dev *zdev)
+{
+	struct mod_pci_args args = { 0, 0, 0, 0 };
+	int rc;
+
+	if (!zdev->fmb)
+		return -EINVAL;
+
+	/* Function measurement is disabled if fmb address is zero */
+	rc = mod_pci(zdev, ZPCI_MOD_FC_SET_MEASURE, 0, &args);
+
+	kmem_cache_free(zdev_fmb_cache, zdev->fmb);
+	zdev->fmb = NULL;
+	return rc;
+}
+
+#define ZPCI_PCIAS_CFGSPC	15
+
+static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, ZPCI_PCIAS_CFGSPC, len);
+	u64 data;
+	int rc;
+
+	rc = zpci_load(&data, req, offset);
+	if (!rc) {
+		data = data << ((8 - len) * 8);
+		data = le64_to_cpu(data);
+		*val = (u32) data;
+	} else
+		*val = 0xffffffff;
+	return rc;
+}
+
+static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, ZPCI_PCIAS_CFGSPC, len);
+	u64 data = val;
+	int rc;
+
+	data = cpu_to_le64(data);
+	data = data >> ((8 - len) * 8);
+	rc = zpci_store(data, req, offset);
+	return rc;
+}
+
+void pcibios_fixup_bus(struct pci_bus *bus)
+{
+}
+
+resource_size_t pcibios_align_resource(void *data, const struct resource *res,
+				       resource_size_t size,
+				       resource_size_t align)
+{
+	return 0;
+}
+
+/* combine single writes by using store-block insn */
+void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
+{
+       zpci_memcpy_toio(to, from, count);
+}
+
+/* Create a virtual mapping cookie for a PCI BAR */
+void __iomem *pci_iomap_range(struct pci_dev *pdev,
+			      int bar,
+			      unsigned long offset,
+			      unsigned long max)
+{
+	struct zpci_dev *zdev =	get_zdev(pdev);
+	u64 addr;
+	int idx;
+
+	if ((bar & 7) != bar)
+		return NULL;
+
+	idx = zdev->bars[bar].map_idx;
+	spin_lock(&zpci_iomap_lock);
+	if (zpci_iomap_start[idx].count++) {
+		BUG_ON(zpci_iomap_start[idx].fh != zdev->fh ||
+		       zpci_iomap_start[idx].bar != bar);
+	} else {
+		zpci_iomap_start[idx].fh = zdev->fh;
+		zpci_iomap_start[idx].bar = bar;
+	}
+	/* Detect overrun */
+	BUG_ON(!zpci_iomap_start[idx].count);
+	spin_unlock(&zpci_iomap_lock);
+
+	addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48);
+	return (void __iomem *) addr + offset;
+}
+EXPORT_SYMBOL(pci_iomap_range);
+
+void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+	return pci_iomap_range(dev, bar, 0, maxlen);
+}
+EXPORT_SYMBOL(pci_iomap);
+
+void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
+{
+	unsigned int idx;
+
+	idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48;
+	spin_lock(&zpci_iomap_lock);
+	/* Detect underrun */
+	BUG_ON(!zpci_iomap_start[idx].count);
+	if (!--zpci_iomap_start[idx].count) {
+		zpci_iomap_start[idx].fh = 0;
+		zpci_iomap_start[idx].bar = 0;
+	}
+	spin_unlock(&zpci_iomap_lock);
+}
+EXPORT_SYMBOL(pci_iounmap);
+
+static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
+		    int size, u32 *val)
+{
+	struct zpci_dev *zdev = get_zdev_by_bus(bus);
+	int ret;
+
+	if (!zdev || devfn != ZPCI_DEVFN)
+		ret = -ENODEV;
+	else
+		ret = zpci_cfg_load(zdev, where, val, size);
+
+	return ret;
+}
+
+static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
+		     int size, u32 val)
+{
+	struct zpci_dev *zdev = get_zdev_by_bus(bus);
+	int ret;
+
+	if (!zdev || devfn != ZPCI_DEVFN)
+		ret = -ENODEV;
+	else
+		ret = zpci_cfg_store(zdev, where, val, size);
+
+	return ret;
+}
+
+static struct pci_ops pci_root_ops = {
+	.read = pci_read,
+	.write = pci_write,
+};
+
+static void zpci_irq_handler(struct airq_struct *airq)
+{
+	unsigned long si, ai;
+	struct airq_iv *aibv;
+	int irqs_on = 0;
+
+	inc_irq_stat(IRQIO_PCI);
+	for (si = 0;;) {
+		/* Scan adapter summary indicator bit vector */
+		si = airq_iv_scan(zpci_aisb_iv, si, airq_iv_end(zpci_aisb_iv));
+		if (si == -1UL) {
+			if (irqs_on++)
+				/* End of second scan with interrupts on. */
+				break;
+			/* First scan complete, reenable interrupts. */
+			zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+			si = 0;
+			continue;
+		}
+
+		/* Scan the adapter interrupt vector for this device. */
+		aibv = zpci_aibv[si];
+		for (ai = 0;;) {
+			ai = airq_iv_scan(aibv, ai, airq_iv_end(aibv));
+			if (ai == -1UL)
+				break;
+			inc_irq_stat(IRQIO_MSI);
+			airq_iv_lock(aibv, ai);
+			generic_handle_irq(airq_iv_get_data(aibv, ai));
+			airq_iv_unlock(aibv, ai);
+		}
+	}
+}
+
+int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+	unsigned int hwirq, msi_vecs;
+	unsigned long aisb;
+	struct msi_desc *msi;
+	struct msi_msg msg;
+	int rc, irq;
+
+	if (type == PCI_CAP_ID_MSI && nvec > 1)
+		return 1;
+	msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
+
+	/* Allocate adapter summary indicator bit */
+	rc = -EIO;
+	aisb = airq_iv_alloc_bit(zpci_aisb_iv);
+	if (aisb == -1UL)
+		goto out;
+	zdev->aisb = aisb;
+
+	/* Create adapter interrupt vector */
+	rc = -ENOMEM;
+	zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
+	if (!zdev->aibv)
+		goto out_si;
+
+	/* Wire up shortcut pointer */
+	zpci_aibv[aisb] = zdev->aibv;
+
+	/* Request MSI interrupts */
+	hwirq = 0;
+	list_for_each_entry(msi, &pdev->msi_list, list) {
+		rc = -EIO;
+		irq = irq_alloc_desc(0);	/* Alloc irq on node 0 */
+		if (irq < 0)
+			goto out_msi;
+		rc = irq_set_msi_desc(irq, msi);
+		if (rc)
+			goto out_msi;
+		irq_set_chip_and_handler(irq, &zpci_irq_chip,
+					 handle_simple_irq);
+		msg.data = hwirq;
+		msg.address_lo = zdev->msi_addr & 0xffffffff;
+		msg.address_hi = zdev->msi_addr >> 32;
+		pci_write_msi_msg(irq, &msg);
+		airq_iv_set_data(zdev->aibv, hwirq, irq);
+		hwirq++;
+	}
+
+	/* Enable adapter interrupts */
+	rc = zpci_set_airq(zdev);
+	if (rc)
+		goto out_msi;
+
+	return (msi_vecs == nvec) ? 0 : msi_vecs;
+
+out_msi:
+	list_for_each_entry(msi, &pdev->msi_list, list) {
+		if (hwirq-- == 0)
+			break;
+		irq_set_msi_desc(msi->irq, NULL);
+		irq_free_desc(msi->irq);
+		msi->msg.address_lo = 0;
+		msi->msg.address_hi = 0;
+		msi->msg.data = 0;
+		msi->irq = 0;
+	}
+	zpci_aibv[aisb] = NULL;
+	airq_iv_release(zdev->aibv);
+out_si:
+	airq_iv_free_bit(zpci_aisb_iv, aisb);
+out:
+	return rc;
+}
+
+void arch_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+	struct msi_desc *msi;
+	int rc;
+
+	/* Disable adapter interrupts */
+	rc = zpci_clear_airq(zdev);
+	if (rc)
+		return;
+
+	/* Release MSI interrupts */
+	list_for_each_entry(msi, &pdev->msi_list, list) {
+		if (msi->msi_attrib.is_msix)
+			__pci_msix_desc_mask_irq(msi, 1);
+		else
+			__pci_msi_desc_mask_irq(msi, 1, 1);
+		irq_set_msi_desc(msi->irq, NULL);
+		irq_free_desc(msi->irq);
+		msi->msg.address_lo = 0;
+		msi->msg.address_hi = 0;
+		msi->msg.data = 0;
+		msi->irq = 0;
+	}
+
+	zpci_aibv[zdev->aisb] = NULL;
+	airq_iv_release(zdev->aibv);
+	airq_iv_free_bit(zpci_aisb_iv, zdev->aisb);
+}
+
+static void zpci_map_resources(struct pci_dev *pdev)
+{
+	resource_size_t len;
+	int i;
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		len = pci_resource_len(pdev, i);
+		if (!len)
+			continue;
+		pdev->resource[i].start =
+			(resource_size_t __force) pci_iomap(pdev, i, 0);
+		pdev->resource[i].end = pdev->resource[i].start + len - 1;
+	}
+}
+
+static void zpci_unmap_resources(struct pci_dev *pdev)
+{
+	resource_size_t len;
+	int i;
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		len = pci_resource_len(pdev, i);
+		if (!len)
+			continue;
+		pci_iounmap(pdev, (void __iomem __force *)
+			    pdev->resource[i].start);
+	}
+}
+
+static int __init zpci_irq_init(void)
+{
+	int rc;
+
+	rc = register_adapter_interrupt(&zpci_airq);
+	if (rc)
+		goto out;
+	/* Set summary to 1 to be called every time for the ISC. */
+	*zpci_airq.lsi_ptr = 1;
+
+	rc = -ENOMEM;
+	zpci_aisb_iv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC);
+	if (!zpci_aisb_iv)
+		goto out_airq;
+
+	zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+	return 0;
+
+out_airq:
+	unregister_adapter_interrupt(&zpci_airq);
+out:
+	return rc;
+}
+
+static void zpci_irq_exit(void)
+{
+	airq_iv_release(zpci_aisb_iv);
+	unregister_adapter_interrupt(&zpci_airq);
+}
+
+static int zpci_alloc_iomap(struct zpci_dev *zdev)
+{
+	int entry;
+
+	spin_lock(&zpci_iomap_lock);
+	entry = find_first_zero_bit(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
+	if (entry == ZPCI_IOMAP_MAX_ENTRIES) {
+		spin_unlock(&zpci_iomap_lock);
+		return -ENOSPC;
+	}
+	set_bit(entry, zpci_iomap);
+	spin_unlock(&zpci_iomap_lock);
+	return entry;
+}
+
+static void zpci_free_iomap(struct zpci_dev *zdev, int entry)
+{
+	spin_lock(&zpci_iomap_lock);
+	memset(&zpci_iomap_start[entry], 0, sizeof(struct zpci_iomap_entry));
+	clear_bit(entry, zpci_iomap);
+	spin_unlock(&zpci_iomap_lock);
+}
+
+static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start,
+				    unsigned long size, unsigned long flags)
+{
+	struct resource *r;
+
+	r = kzalloc(sizeof(*r), GFP_KERNEL);
+	if (!r)
+		return NULL;
+
+	r->start = start;
+	r->end = r->start + size - 1;
+	r->flags = flags;
+	r->name = zdev->res_name;
+
+	if (request_resource(&iomem_resource, r)) {
+		kfree(r);
+		return NULL;
+	}
+	return r;
+}
+
+static int zpci_setup_bus_resources(struct zpci_dev *zdev,
+				    struct list_head *resources)
+{
+	unsigned long addr, size, flags;
+	struct resource *res;
+	int i, entry;
+
+	snprintf(zdev->res_name, sizeof(zdev->res_name),
+		 "PCI Bus %04x:%02x", zdev->domain, ZPCI_BUS_NR);
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		if (!zdev->bars[i].size)
+			continue;
+		entry = zpci_alloc_iomap(zdev);
+		if (entry < 0)
+			return entry;
+		zdev->bars[i].map_idx = entry;
+
+		/* only MMIO is supported */
+		flags = IORESOURCE_MEM;
+		if (zdev->bars[i].val & 8)
+			flags |= IORESOURCE_PREFETCH;
+		if (zdev->bars[i].val & 4)
+			flags |= IORESOURCE_MEM_64;
+
+		addr = ZPCI_IOMAP_ADDR_BASE + ((u64) entry << 48);
+
+		size = 1UL << zdev->bars[i].size;
+
+		res = __alloc_res(zdev, addr, size, flags);
+		if (!res) {
+			zpci_free_iomap(zdev, entry);
+			return -ENOMEM;
+		}
+		zdev->bars[i].res = res;
+		pci_add_resource(resources, res);
+	}
+
+	return 0;
+}
+
+static void zpci_cleanup_bus_resources(struct zpci_dev *zdev)
+{
+	int i;
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		if (!zdev->bars[i].size)
+			continue;
+
+		zpci_free_iomap(zdev, zdev->bars[i].map_idx);
+		release_resource(zdev->bars[i].res);
+		kfree(zdev->bars[i].res);
+	}
+}
+
+int pcibios_add_device(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+	struct resource *res;
+	int i;
+
+	zdev->pdev = pdev;
+	pdev->dev.groups = zpci_attr_groups;
+	zpci_map_resources(pdev);
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		res = &pdev->resource[i];
+		if (res->parent || !res->flags)
+			continue;
+		pci_claim_resource(pdev, i);
+	}
+
+	return 0;
+}
+
+void pcibios_release_device(struct pci_dev *pdev)
+{
+	zpci_unmap_resources(pdev);
+}
+
+int pcibios_enable_device(struct pci_dev *pdev, int mask)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+
+	zdev->pdev = pdev;
+	zpci_debug_init_device(zdev);
+	zpci_fmb_enable_device(zdev);
+
+	return pci_enable_resources(pdev, mask);
+}
+
+void pcibios_disable_device(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+
+	zpci_fmb_disable_device(zdev);
+	zpci_debug_exit_device(zdev);
+	zdev->pdev = NULL;
+}
+
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+static int zpci_restore(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct zpci_dev *zdev = get_zdev(pdev);
+	int ret = 0;
+
+	if (zdev->state != ZPCI_FN_STATE_ONLINE)
+		goto out;
+
+	ret = clp_enable_fh(zdev, ZPCI_NR_DMA_SPACES);
+	if (ret)
+		goto out;
+
+	zpci_map_resources(pdev);
+	zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET,
+			   zdev->start_dma + zdev->iommu_size - 1,
+			   (u64) zdev->dma_table);
+
+out:
+	return ret;
+}
+
+static int zpci_freeze(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct zpci_dev *zdev = get_zdev(pdev);
+
+	if (zdev->state != ZPCI_FN_STATE_ONLINE)
+		return 0;
+
+	zpci_unregister_ioat(zdev, 0);
+	zpci_unmap_resources(pdev);
+	return clp_disable_fh(zdev);
+}
+
+struct dev_pm_ops pcibios_pm_ops = {
+	.thaw_noirq = zpci_restore,
+	.freeze_noirq = zpci_freeze,
+	.restore_noirq = zpci_restore,
+	.poweroff_noirq = zpci_freeze,
+};
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
+
+static int zpci_alloc_domain(struct zpci_dev *zdev)
+{
+	spin_lock(&zpci_domain_lock);
+	zdev->domain = find_first_zero_bit(zpci_domain, ZPCI_NR_DEVICES);
+	if (zdev->domain == ZPCI_NR_DEVICES) {
+		spin_unlock(&zpci_domain_lock);
+		return -ENOSPC;
+	}
+	set_bit(zdev->domain, zpci_domain);
+	spin_unlock(&zpci_domain_lock);
+	return 0;
+}
+
+static void zpci_free_domain(struct zpci_dev *zdev)
+{
+	spin_lock(&zpci_domain_lock);
+	clear_bit(zdev->domain, zpci_domain);
+	spin_unlock(&zpci_domain_lock);
+}
+
+void pcibios_remove_bus(struct pci_bus *bus)
+{
+	struct zpci_dev *zdev = get_zdev_by_bus(bus);
+
+	zpci_exit_slot(zdev);
+	zpci_cleanup_bus_resources(zdev);
+	zpci_free_domain(zdev);
+
+	spin_lock(&zpci_list_lock);
+	list_del(&zdev->entry);
+	spin_unlock(&zpci_list_lock);
+
+	kfree(zdev);
+}
+
+static int zpci_scan_bus(struct zpci_dev *zdev)
+{
+	LIST_HEAD(resources);
+	int ret;
+
+	ret = zpci_setup_bus_resources(zdev, &resources);
+	if (ret)
+		return ret;
+
+	zdev->bus = pci_scan_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops,
+				      zdev, &resources);
+	if (!zdev->bus) {
+		zpci_cleanup_bus_resources(zdev);
+		return -EIO;
+	}
+	zdev->bus->max_bus_speed = zdev->max_bus_speed;
+	pci_bus_add_devices(zdev->bus);
+	return 0;
+}
+
+int zpci_enable_device(struct zpci_dev *zdev)
+{
+	int rc;
+
+	rc = clp_enable_fh(zdev, ZPCI_NR_DMA_SPACES);
+	if (rc)
+		goto out;
+
+	rc = zpci_dma_init_device(zdev);
+	if (rc)
+		goto out_dma;
+
+	zdev->state = ZPCI_FN_STATE_ONLINE;
+	return 0;
+
+out_dma:
+	clp_disable_fh(zdev);
+out:
+	return rc;
+}
+EXPORT_SYMBOL_GPL(zpci_enable_device);
+
+int zpci_disable_device(struct zpci_dev *zdev)
+{
+	zpci_dma_exit_device(zdev);
+	return clp_disable_fh(zdev);
+}
+EXPORT_SYMBOL_GPL(zpci_disable_device);
+
+int zpci_create_device(struct zpci_dev *zdev)
+{
+	int rc;
+
+	rc = zpci_alloc_domain(zdev);
+	if (rc)
+		goto out;
+
+	mutex_init(&zdev->lock);
+	if (zdev->state == ZPCI_FN_STATE_CONFIGURED) {
+		rc = zpci_enable_device(zdev);
+		if (rc)
+			goto out_free;
+	}
+	rc = zpci_scan_bus(zdev);
+	if (rc)
+		goto out_disable;
+
+	spin_lock(&zpci_list_lock);
+	list_add_tail(&zdev->entry, &zpci_list);
+	spin_unlock(&zpci_list_lock);
+
+	zpci_init_slot(zdev);
+
+	return 0;
+
+out_disable:
+	if (zdev->state == ZPCI_FN_STATE_ONLINE)
+		zpci_disable_device(zdev);
+out_free:
+	zpci_free_domain(zdev);
+out:
+	return rc;
+}
+
+void zpci_stop_device(struct zpci_dev *zdev)
+{
+	zpci_dma_exit_device(zdev);
+	/*
+	 * Note: SCLP disables fh via set-pci-fn so don't
+	 * do that here.
+	 */
+}
+EXPORT_SYMBOL_GPL(zpci_stop_device);
+
+static inline int barsize(u8 size)
+{
+	return (size) ? (1 << size) >> 10 : 0;
+}
+
+static int zpci_mem_init(void)
+{
+	zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb),
+				16, 0, NULL);
+	if (!zdev_fmb_cache)
+		goto error_zdev;
+
+	/* TODO: use realloc */
+	zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start),
+				   GFP_KERNEL);
+	if (!zpci_iomap_start)
+		goto error_iomap;
+	return 0;
+
+error_iomap:
+	kmem_cache_destroy(zdev_fmb_cache);
+error_zdev:
+	return -ENOMEM;
+}
+
+static void zpci_mem_exit(void)
+{
+	kfree(zpci_iomap_start);
+	kmem_cache_destroy(zdev_fmb_cache);
+}
+
+static unsigned int s390_pci_probe = 1;
+static unsigned int s390_pci_initialized;
+
+char * __init pcibios_setup(char *str)
+{
+	if (!strcmp(str, "off")) {
+		s390_pci_probe = 0;
+		return NULL;
+	}
+	return str;
+}
+
+bool zpci_is_enabled(void)
+{
+	return s390_pci_initialized;
+}
+
+static int __init pci_base_init(void)
+{
+	int rc;
+
+	if (!s390_pci_probe)
+		return 0;
+
+	if (!test_facility(69) || !test_facility(71) || !test_facility(72))
+		return 0;
+
+	rc = zpci_debug_init();
+	if (rc)
+		goto out;
+
+	rc = zpci_mem_init();
+	if (rc)
+		goto out_mem;
+
+	rc = zpci_irq_init();
+	if (rc)
+		goto out_irq;
+
+	rc = zpci_dma_init();
+	if (rc)
+		goto out_dma;
+
+	rc = clp_scan_pci_devices();
+	if (rc)
+		goto out_find;
+
+	s390_pci_initialized = 1;
+	return 0;
+
+out_find:
+	zpci_dma_exit();
+out_dma:
+	zpci_irq_exit();
+out_irq:
+	zpci_mem_exit();
+out_mem:
+	zpci_debug_exit();
+out:
+	return rc;
+}
+subsys_initcall_sync(pci_base_init);
+
+void zpci_rescan(void)
+{
+	if (zpci_is_enabled())
+		clp_rescan_pci_devices_simple();
+}
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
new file mode 100644
index 000000000..d6e411ed8
--- /dev/null
+++ b/arch/s390/pci/pci_clp.c
@@ -0,0 +1,393 @@
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#define KMSG_COMPONENT "zpci"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <asm/pci_debug.h>
+#include <asm/pci_clp.h>
+
+static inline void zpci_err_clp(unsigned int rsp, int rc)
+{
+	struct {
+		unsigned int rsp;
+		int rc;
+	} __packed data = {rsp, rc};
+
+	zpci_err_hex(&data, sizeof(data));
+}
+
+/*
+ * Call Logical Processor
+ * Retry logic is handled by the caller.
+ */
+static inline u8 clp_instr(void *data)
+{
+	struct { u8 _[CLP_BLK_SIZE]; } *req = data;
+	u64 ignored;
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rrf,0xb9a00000,%[ign],%[req],0x0,0x2\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [ign] "=d" (ignored), "+m" (*req)
+		: [req] "a" (req)
+		: "cc");
+	return cc;
+}
+
+static void *clp_alloc_block(gfp_t gfp_mask)
+{
+	return (void *) __get_free_pages(gfp_mask, get_order(CLP_BLK_SIZE));
+}
+
+static void clp_free_block(void *ptr)
+{
+	free_pages((unsigned long) ptr, get_order(CLP_BLK_SIZE));
+}
+
+static void clp_store_query_pci_fngrp(struct zpci_dev *zdev,
+				      struct clp_rsp_query_pci_grp *response)
+{
+	zdev->tlb_refresh = response->refresh;
+	zdev->dma_mask = response->dasm;
+	zdev->msi_addr = response->msia;
+	zdev->max_msi = response->noi;
+	zdev->fmb_update = response->mui;
+
+	switch (response->version) {
+	case 1:
+		zdev->max_bus_speed = PCIE_SPEED_5_0GT;
+		break;
+	default:
+		zdev->max_bus_speed = PCI_SPEED_UNKNOWN;
+		break;
+	}
+}
+
+static int clp_query_pci_fngrp(struct zpci_dev *zdev, u8 pfgid)
+{
+	struct clp_req_rsp_query_pci_grp *rrb;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	memset(rrb, 0, sizeof(*rrb));
+	rrb->request.hdr.len = sizeof(rrb->request);
+	rrb->request.hdr.cmd = CLP_QUERY_PCI_FNGRP;
+	rrb->response.hdr.len = sizeof(rrb->response);
+	rrb->request.pfgid = pfgid;
+
+	rc = clp_instr(rrb);
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK)
+		clp_store_query_pci_fngrp(zdev, &rrb->response);
+	else {
+		zpci_err("Q PCI FGRP:\n");
+		zpci_err_clp(rrb->response.hdr.rsp, rc);
+		rc = -EIO;
+	}
+	clp_free_block(rrb);
+	return rc;
+}
+
+static int clp_store_query_pci_fn(struct zpci_dev *zdev,
+				  struct clp_rsp_query_pci *response)
+{
+	int i;
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		zdev->bars[i].val = le32_to_cpu(response->bar[i]);
+		zdev->bars[i].size = response->bar_size[i];
+	}
+	zdev->start_dma = response->sdma;
+	zdev->end_dma = response->edma;
+	zdev->pchid = response->pchid;
+	zdev->pfgid = response->pfgid;
+	zdev->pft = response->pft;
+	zdev->vfn = response->vfn;
+	zdev->uid = response->uid;
+
+	memcpy(zdev->pfip, response->pfip, sizeof(zdev->pfip));
+	if (response->util_str_avail) {
+		memcpy(zdev->util_str, response->util_str,
+		       sizeof(zdev->util_str));
+	}
+
+	return 0;
+}
+
+static int clp_query_pci_fn(struct zpci_dev *zdev, u32 fh)
+{
+	struct clp_req_rsp_query_pci *rrb;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	memset(rrb, 0, sizeof(*rrb));
+	rrb->request.hdr.len = sizeof(rrb->request);
+	rrb->request.hdr.cmd = CLP_QUERY_PCI_FN;
+	rrb->response.hdr.len = sizeof(rrb->response);
+	rrb->request.fh = fh;
+
+	rc = clp_instr(rrb);
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
+		rc = clp_store_query_pci_fn(zdev, &rrb->response);
+		if (rc)
+			goto out;
+		if (rrb->response.pfgid)
+			rc = clp_query_pci_fngrp(zdev, rrb->response.pfgid);
+	} else {
+		zpci_err("Q PCI FN:\n");
+		zpci_err_clp(rrb->response.hdr.rsp, rc);
+		rc = -EIO;
+	}
+out:
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_add_pci_device(u32 fid, u32 fh, int configured)
+{
+	struct zpci_dev *zdev;
+	int rc;
+
+	zpci_dbg(3, "add fid:%x, fh:%x, c:%d\n", fid, fh, configured);
+	zdev = kzalloc(sizeof(*zdev), GFP_KERNEL);
+	if (!zdev)
+		return -ENOMEM;
+
+	zdev->fh = fh;
+	zdev->fid = fid;
+
+	/* Query function properties and update zdev */
+	rc = clp_query_pci_fn(zdev, fh);
+	if (rc)
+		goto error;
+
+	if (configured)
+		zdev->state = ZPCI_FN_STATE_CONFIGURED;
+	else
+		zdev->state = ZPCI_FN_STATE_STANDBY;
+
+	rc = zpci_create_device(zdev);
+	if (rc)
+		goto error;
+	return 0;
+
+error:
+	kfree(zdev);
+	return rc;
+}
+
+/*
+ * Enable/Disable a given PCI function defined by its function handle.
+ */
+static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
+{
+	struct clp_req_rsp_set_pci *rrb;
+	int rc, retries = 100;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	do {
+		memset(rrb, 0, sizeof(*rrb));
+		rrb->request.hdr.len = sizeof(rrb->request);
+		rrb->request.hdr.cmd = CLP_SET_PCI_FN;
+		rrb->response.hdr.len = sizeof(rrb->response);
+		rrb->request.fh = *fh;
+		rrb->request.oc = command;
+		rrb->request.ndas = nr_dma_as;
+
+		rc = clp_instr(rrb);
+		if (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY) {
+			retries--;
+			if (retries < 0)
+				break;
+			msleep(20);
+		}
+	} while (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY);
+
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK)
+		*fh = rrb->response.fh;
+	else {
+		zpci_err("Set PCI FN:\n");
+		zpci_err_clp(rrb->response.hdr.rsp, rc);
+		rc = -EIO;
+	}
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as)
+{
+	u32 fh = zdev->fh;
+	int rc;
+
+	rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
+	if (!rc)
+		/* Success -> store enabled handle in zdev */
+		zdev->fh = fh;
+
+	zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
+	return rc;
+}
+
+int clp_disable_fh(struct zpci_dev *zdev)
+{
+	u32 fh = zdev->fh;
+	int rc;
+
+	if (!zdev_enabled(zdev))
+		return 0;
+
+	rc = clp_set_pci_fn(&fh, 0, CLP_SET_DISABLE_PCI_FN);
+	if (!rc)
+		/* Success -> store disabled handle in zdev */
+		zdev->fh = fh;
+
+	zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
+	return rc;
+}
+
+static int clp_list_pci(struct clp_req_rsp_list_pci *rrb,
+			void (*cb)(struct clp_fh_list_entry *entry))
+{
+	u64 resume_token = 0;
+	int entries, i, rc;
+
+	do {
+		memset(rrb, 0, sizeof(*rrb));
+		rrb->request.hdr.len = sizeof(rrb->request);
+		rrb->request.hdr.cmd = CLP_LIST_PCI;
+		/* store as many entries as possible */
+		rrb->response.hdr.len = CLP_BLK_SIZE - LIST_PCI_HDR_LEN;
+		rrb->request.resume_token = resume_token;
+
+		/* Get PCI function handle list */
+		rc = clp_instr(rrb);
+		if (rc || rrb->response.hdr.rsp != CLP_RC_OK) {
+			zpci_err("List PCI FN:\n");
+			zpci_err_clp(rrb->response.hdr.rsp, rc);
+			rc = -EIO;
+			goto out;
+		}
+
+		WARN_ON_ONCE(rrb->response.entry_size !=
+			sizeof(struct clp_fh_list_entry));
+
+		entries = (rrb->response.hdr.len - LIST_PCI_HDR_LEN) /
+			rrb->response.entry_size;
+
+		resume_token = rrb->response.resume_token;
+		for (i = 0; i < entries; i++)
+			cb(&rrb->response.fh_list[i]);
+	} while (resume_token);
+out:
+	return rc;
+}
+
+static void __clp_add(struct clp_fh_list_entry *entry)
+{
+	if (!entry->vendor_id)
+		return;
+
+	clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
+}
+
+static void __clp_rescan(struct clp_fh_list_entry *entry)
+{
+	struct zpci_dev *zdev;
+
+	if (!entry->vendor_id)
+		return;
+
+	zdev = get_zdev_by_fid(entry->fid);
+	if (!zdev) {
+		clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
+		return;
+	}
+
+	if (!entry->config_state) {
+		/*
+		 * The handle is already disabled, that means no iota/irq freeing via
+		 * the firmware interfaces anymore. Need to free resources manually
+		 * (DMA memory, debug, sysfs)...
+		 */
+		zpci_stop_device(zdev);
+	}
+}
+
+static void __clp_update(struct clp_fh_list_entry *entry)
+{
+	struct zpci_dev *zdev;
+
+	if (!entry->vendor_id)
+		return;
+
+	zdev = get_zdev_by_fid(entry->fid);
+	if (!zdev)
+		return;
+
+	zdev->fh = entry->fh;
+}
+
+int clp_scan_pci_devices(void)
+{
+	struct clp_req_rsp_list_pci *rrb;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	rc = clp_list_pci(rrb, __clp_add);
+
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_rescan_pci_devices(void)
+{
+	struct clp_req_rsp_list_pci *rrb;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	rc = clp_list_pci(rrb, __clp_rescan);
+
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_rescan_pci_devices_simple(void)
+{
+	struct clp_req_rsp_list_pci *rrb;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_NOWAIT);
+	if (!rrb)
+		return -ENOMEM;
+
+	rc = clp_list_pci(rrb, __clp_update);
+
+	clp_free_block(rrb);
+	return rc;
+}
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
new file mode 100644
index 000000000..4129b0a5f
--- /dev/null
+++ b/arch/s390/pci/pci_debug.c
@@ -0,0 +1,177 @@
+/*
+ *  Copyright IBM Corp. 2012
+ *
+ *  Author(s):
+ *    Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#define KMSG_COMPONENT "zpci"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/export.h>
+#include <linux/pci.h>
+#include <asm/debug.h>
+
+#include <asm/pci_dma.h>
+
+static struct dentry *debugfs_root;
+debug_info_t *pci_debug_msg_id;
+EXPORT_SYMBOL_GPL(pci_debug_msg_id);
+debug_info_t *pci_debug_err_id;
+EXPORT_SYMBOL_GPL(pci_debug_err_id);
+
+static char *pci_perf_names[] = {
+	/* hardware counters */
+	"Load operations",
+	"Store operations",
+	"Store block operations",
+	"Refresh operations",
+	"DMA read bytes",
+	"DMA write bytes",
+};
+
+static char *pci_sw_names[] = {
+	"Allocated pages",
+	"Mapped pages",
+	"Unmapped pages",
+};
+
+static void pci_sw_counter_show(struct seq_file *m)
+{
+	struct zpci_dev *zdev = m->private;
+	atomic64_t *counter = &zdev->allocated_pages;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(pci_sw_names); i++, counter++)
+		seq_printf(m, "%26s:\t%llu\n", pci_sw_names[i],
+			   atomic64_read(counter));
+}
+
+static int pci_perf_show(struct seq_file *m, void *v)
+{
+	struct zpci_dev *zdev = m->private;
+	u64 *stat;
+	int i;
+
+	if (!zdev)
+		return 0;
+
+	mutex_lock(&zdev->lock);
+	if (!zdev->fmb) {
+		mutex_unlock(&zdev->lock);
+		seq_puts(m, "FMB statistics disabled\n");
+		return 0;
+	}
+
+	/* header */
+	seq_printf(m, "FMB @ %p\n", zdev->fmb);
+	seq_printf(m, "Update interval: %u ms\n", zdev->fmb_update);
+	seq_printf(m, "Samples: %u\n", zdev->fmb->samples);
+	seq_printf(m, "Last update TOD: %Lx\n", zdev->fmb->last_update);
+
+	/* hardware counters */
+	stat = (u64 *) &zdev->fmb->ld_ops;
+	for (i = 0; i < 4; i++)
+		seq_printf(m, "%26s:\t%llu\n",
+			   pci_perf_names[i], *(stat + i));
+	if (zdev->fmb->dma_valid)
+		for (i = 4; i < 6; i++)
+			seq_printf(m, "%26s:\t%llu\n",
+				   pci_perf_names[i], *(stat + i));
+
+	pci_sw_counter_show(m);
+	mutex_unlock(&zdev->lock);
+	return 0;
+}
+
+static ssize_t pci_perf_seq_write(struct file *file, const char __user *ubuf,
+				  size_t count, loff_t *off)
+{
+	struct zpci_dev *zdev = ((struct seq_file *) file->private_data)->private;
+	unsigned long val;
+	int rc;
+
+	if (!zdev)
+		return 0;
+
+	rc = kstrtoul_from_user(ubuf, count, 10, &val);
+	if (rc)
+		return rc;
+
+	mutex_lock(&zdev->lock);
+	switch (val) {
+	case 0:
+		rc = zpci_fmb_disable_device(zdev);
+		break;
+	case 1:
+		rc = zpci_fmb_enable_device(zdev);
+		break;
+	}
+	mutex_unlock(&zdev->lock);
+	return rc ? rc : count;
+}
+
+static int pci_perf_seq_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, pci_perf_show,
+			   file_inode(filp)->i_private);
+}
+
+static const struct file_operations debugfs_pci_perf_fops = {
+	.open	 = pci_perf_seq_open,
+	.read	 = seq_read,
+	.write	 = pci_perf_seq_write,
+	.llseek  = seq_lseek,
+	.release = single_release,
+};
+
+void zpci_debug_init_device(struct zpci_dev *zdev)
+{
+	zdev->debugfs_dev = debugfs_create_dir(dev_name(&zdev->pdev->dev),
+					       debugfs_root);
+	if (IS_ERR(zdev->debugfs_dev))
+		zdev->debugfs_dev = NULL;
+
+	zdev->debugfs_perf = debugfs_create_file("statistics",
+				S_IFREG | S_IRUGO | S_IWUSR,
+				zdev->debugfs_dev, zdev,
+				&debugfs_pci_perf_fops);
+	if (IS_ERR(zdev->debugfs_perf))
+		zdev->debugfs_perf = NULL;
+}
+
+void zpci_debug_exit_device(struct zpci_dev *zdev)
+{
+	debugfs_remove(zdev->debugfs_perf);
+	debugfs_remove(zdev->debugfs_dev);
+}
+
+int __init zpci_debug_init(void)
+{
+	/* event trace buffer */
+	pci_debug_msg_id = debug_register("pci_msg", 8, 1, 8 * sizeof(long));
+	if (!pci_debug_msg_id)
+		return -EINVAL;
+	debug_register_view(pci_debug_msg_id, &debug_sprintf_view);
+	debug_set_level(pci_debug_msg_id, 3);
+
+	/* error log */
+	pci_debug_err_id = debug_register("pci_error", 2, 1, 16);
+	if (!pci_debug_err_id)
+		return -EINVAL;
+	debug_register_view(pci_debug_err_id, &debug_hex_ascii_view);
+	debug_set_level(pci_debug_err_id, 6);
+
+	debugfs_root = debugfs_create_dir("pci", NULL);
+	return 0;
+}
+
+void zpci_debug_exit(void)
+{
+	debug_unregister(pci_debug_msg_id);
+	debug_unregister(pci_debug_err_id);
+	debugfs_remove(debugfs_root);
+}
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
new file mode 100644
index 000000000..6fd8d5836
--- /dev/null
+++ b/arch/s390/pci/pci_dma.c
@@ -0,0 +1,528 @@
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/iommu-helper.h>
+#include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
+#include <linux/pci.h>
+#include <asm/pci_dma.h>
+
+static struct kmem_cache *dma_region_table_cache;
+static struct kmem_cache *dma_page_table_cache;
+static int s390_iommu_strict;
+
+static int zpci_refresh_global(struct zpci_dev *zdev)
+{
+	return zpci_refresh_trans((u64) zdev->fh << 32, zdev->start_dma,
+				  zdev->iommu_pages * PAGE_SIZE);
+}
+
+static unsigned long *dma_alloc_cpu_table(void)
+{
+	unsigned long *table, *entry;
+
+	table = kmem_cache_alloc(dma_region_table_cache, GFP_ATOMIC);
+	if (!table)
+		return NULL;
+
+	for (entry = table; entry < table + ZPCI_TABLE_ENTRIES; entry++)
+		*entry = ZPCI_TABLE_INVALID | ZPCI_TABLE_PROTECTED;
+	return table;
+}
+
+static void dma_free_cpu_table(void *table)
+{
+	kmem_cache_free(dma_region_table_cache, table);
+}
+
+static unsigned long *dma_alloc_page_table(void)
+{
+	unsigned long *table, *entry;
+
+	table = kmem_cache_alloc(dma_page_table_cache, GFP_ATOMIC);
+	if (!table)
+		return NULL;
+
+	for (entry = table; entry < table + ZPCI_PT_ENTRIES; entry++)
+		*entry = ZPCI_PTE_INVALID | ZPCI_TABLE_PROTECTED;
+	return table;
+}
+
+static void dma_free_page_table(void *table)
+{
+	kmem_cache_free(dma_page_table_cache, table);
+}
+
+static unsigned long *dma_get_seg_table_origin(unsigned long *entry)
+{
+	unsigned long *sto;
+
+	if (reg_entry_isvalid(*entry))
+		sto = get_rt_sto(*entry);
+	else {
+		sto = dma_alloc_cpu_table();
+		if (!sto)
+			return NULL;
+
+		set_rt_sto(entry, sto);
+		validate_rt_entry(entry);
+		entry_clr_protected(entry);
+	}
+	return sto;
+}
+
+static unsigned long *dma_get_page_table_origin(unsigned long *entry)
+{
+	unsigned long *pto;
+
+	if (reg_entry_isvalid(*entry))
+		pto = get_st_pto(*entry);
+	else {
+		pto = dma_alloc_page_table();
+		if (!pto)
+			return NULL;
+		set_st_pto(entry, pto);
+		validate_st_entry(entry);
+		entry_clr_protected(entry);
+	}
+	return pto;
+}
+
+static unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr)
+{
+	unsigned long *sto, *pto;
+	unsigned int rtx, sx, px;
+
+	rtx = calc_rtx(dma_addr);
+	sto = dma_get_seg_table_origin(&rto[rtx]);
+	if (!sto)
+		return NULL;
+
+	sx = calc_sx(dma_addr);
+	pto = dma_get_page_table_origin(&sto[sx]);
+	if (!pto)
+		return NULL;
+
+	px = calc_px(dma_addr);
+	return &pto[px];
+}
+
+static void dma_update_cpu_trans(struct zpci_dev *zdev, void *page_addr,
+				 dma_addr_t dma_addr, int flags)
+{
+	unsigned long *entry;
+
+	entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr);
+	if (!entry) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	if (flags & ZPCI_PTE_INVALID) {
+		invalidate_pt_entry(entry);
+		return;
+	} else {
+		set_pt_pfaa(entry, page_addr);
+		validate_pt_entry(entry);
+	}
+
+	if (flags & ZPCI_TABLE_PROTECTED)
+		entry_set_protected(entry);
+	else
+		entry_clr_protected(entry);
+}
+
+static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
+			    dma_addr_t dma_addr, size_t size, int flags)
+{
+	unsigned int nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	u8 *page_addr = (u8 *) (pa & PAGE_MASK);
+	dma_addr_t start_dma_addr = dma_addr;
+	unsigned long irq_flags;
+	int i, rc = 0;
+
+	if (!nr_pages)
+		return -EINVAL;
+
+	spin_lock_irqsave(&zdev->dma_table_lock, irq_flags);
+	if (!zdev->dma_table)
+		goto no_refresh;
+
+	for (i = 0; i < nr_pages; i++) {
+		dma_update_cpu_trans(zdev, page_addr, dma_addr, flags);
+		page_addr += PAGE_SIZE;
+		dma_addr += PAGE_SIZE;
+	}
+
+	/*
+	 * With zdev->tlb_refresh == 0, rpcit is not required to establish new
+	 * translations when previously invalid translation-table entries are
+	 * validated. With lazy unmap, it also is skipped for previously valid
+	 * entries, but a global rpcit is then required before any address can
+	 * be re-used, i.e. after each iommu bitmap wrap-around.
+	 */
+	if (!zdev->tlb_refresh &&
+			(!s390_iommu_strict ||
+			((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)))
+		goto no_refresh;
+
+	rc = zpci_refresh_trans((u64) zdev->fh << 32, start_dma_addr,
+				nr_pages * PAGE_SIZE);
+
+no_refresh:
+	spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags);
+	return rc;
+}
+
+static void dma_free_seg_table(unsigned long entry)
+{
+	unsigned long *sto = get_rt_sto(entry);
+	int sx;
+
+	for (sx = 0; sx < ZPCI_TABLE_ENTRIES; sx++)
+		if (reg_entry_isvalid(sto[sx]))
+			dma_free_page_table(get_st_pto(sto[sx]));
+
+	dma_free_cpu_table(sto);
+}
+
+static void dma_cleanup_tables(struct zpci_dev *zdev)
+{
+	unsigned long *table;
+	int rtx;
+
+	if (!zdev || !zdev->dma_table)
+		return;
+
+	table = zdev->dma_table;
+	for (rtx = 0; rtx < ZPCI_TABLE_ENTRIES; rtx++)
+		if (reg_entry_isvalid(table[rtx]))
+			dma_free_seg_table(table[rtx]);
+
+	dma_free_cpu_table(table);
+	zdev->dma_table = NULL;
+}
+
+static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev,
+				       unsigned long start, int size)
+{
+	unsigned long boundary_size;
+
+	boundary_size = ALIGN(dma_get_seg_boundary(&zdev->pdev->dev) + 1,
+			      PAGE_SIZE) >> PAGE_SHIFT;
+	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
+				start, size, 0, boundary_size, 0);
+}
+
+static unsigned long dma_alloc_iommu(struct zpci_dev *zdev, int size)
+{
+	unsigned long offset, flags;
+	int wrap = 0;
+
+	spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags);
+	offset = __dma_alloc_iommu(zdev, zdev->next_bit, size);
+	if (offset == -1) {
+		/* wrap-around */
+		offset = __dma_alloc_iommu(zdev, 0, size);
+		wrap = 1;
+	}
+
+	if (offset != -1) {
+		zdev->next_bit = offset + size;
+		if (!zdev->tlb_refresh && !s390_iommu_strict && wrap)
+			/* global flush after wrap-around with lazy unmap */
+			zpci_refresh_global(zdev);
+	}
+	spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
+	return offset;
+}
+
+static void dma_free_iommu(struct zpci_dev *zdev, unsigned long offset, int size)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags);
+	if (!zdev->iommu_bitmap)
+		goto out;
+	bitmap_clear(zdev->iommu_bitmap, offset, size);
+	/*
+	 * Lazy flush for unmap: need to move next_bit to avoid address re-use
+	 * until wrap-around.
+	 */
+	if (!s390_iommu_strict && offset >= zdev->next_bit)
+		zdev->next_bit = offset + size;
+out:
+	spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
+}
+
+int dma_set_mask(struct device *dev, u64 mask)
+{
+	if (!dev->dma_mask || !dma_supported(dev, mask))
+		return -EIO;
+
+	*dev->dma_mask = mask;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dma_set_mask);
+
+static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
+				     unsigned long offset, size_t size,
+				     enum dma_data_direction direction,
+				     struct dma_attrs *attrs)
+{
+	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+	unsigned long nr_pages, iommu_page_index;
+	unsigned long pa = page_to_phys(page) + offset;
+	int flags = ZPCI_PTE_VALID;
+	dma_addr_t dma_addr;
+
+	/* This rounds up number of pages based on size and offset */
+	nr_pages = iommu_num_pages(pa, size, PAGE_SIZE);
+	iommu_page_index = dma_alloc_iommu(zdev, nr_pages);
+	if (iommu_page_index == -1)
+		goto out_err;
+
+	/* Use rounded up size */
+	size = nr_pages * PAGE_SIZE;
+
+	dma_addr = zdev->start_dma + iommu_page_index * PAGE_SIZE;
+	if (dma_addr + size > zdev->end_dma)
+		goto out_free;
+
+	if (direction == DMA_NONE || direction == DMA_TO_DEVICE)
+		flags |= ZPCI_TABLE_PROTECTED;
+
+	if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) {
+		atomic64_add(nr_pages, &zdev->mapped_pages);
+		return dma_addr + (offset & ~PAGE_MASK);
+	}
+
+out_free:
+	dma_free_iommu(zdev, iommu_page_index, nr_pages);
+out_err:
+	zpci_err("map error:\n");
+	zpci_err_hex(&pa, sizeof(pa));
+	return DMA_ERROR_CODE;
+}
+
+static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
+				 size_t size, enum dma_data_direction direction,
+				 struct dma_attrs *attrs)
+{
+	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+	unsigned long iommu_page_index;
+	int npages;
+
+	npages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
+	dma_addr = dma_addr & PAGE_MASK;
+	if (dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE,
+			     ZPCI_TABLE_PROTECTED | ZPCI_PTE_INVALID)) {
+		zpci_err("unmap error:\n");
+		zpci_err_hex(&dma_addr, sizeof(dma_addr));
+	}
+
+	atomic64_add(npages, &zdev->unmapped_pages);
+	iommu_page_index = (dma_addr - zdev->start_dma) >> PAGE_SHIFT;
+	dma_free_iommu(zdev, iommu_page_index, npages);
+}
+
+static void *s390_dma_alloc(struct device *dev, size_t size,
+			    dma_addr_t *dma_handle, gfp_t flag,
+			    struct dma_attrs *attrs)
+{
+	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+	struct page *page;
+	unsigned long pa;
+	dma_addr_t map;
+
+	size = PAGE_ALIGN(size);
+	page = alloc_pages(flag, get_order(size));
+	if (!page)
+		return NULL;
+
+	pa = page_to_phys(page);
+	memset((void *) pa, 0, size);
+
+	map = s390_dma_map_pages(dev, page, pa % PAGE_SIZE,
+				 size, DMA_BIDIRECTIONAL, NULL);
+	if (dma_mapping_error(dev, map)) {
+		free_pages(pa, get_order(size));
+		return NULL;
+	}
+
+	atomic64_add(size / PAGE_SIZE, &zdev->allocated_pages);
+	if (dma_handle)
+		*dma_handle = map;
+	return (void *) pa;
+}
+
+static void s390_dma_free(struct device *dev, size_t size,
+			  void *pa, dma_addr_t dma_handle,
+			  struct dma_attrs *attrs)
+{
+	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+
+	size = PAGE_ALIGN(size);
+	atomic64_sub(size / PAGE_SIZE, &zdev->allocated_pages);
+	s390_dma_unmap_pages(dev, dma_handle, size, DMA_BIDIRECTIONAL, NULL);
+	free_pages((unsigned long) pa, get_order(size));
+}
+
+static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
+			   int nr_elements, enum dma_data_direction dir,
+			   struct dma_attrs *attrs)
+{
+	int mapped_elements = 0;
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nr_elements, i) {
+		struct page *page = sg_page(s);
+		s->dma_address = s390_dma_map_pages(dev, page, s->offset,
+						    s->length, dir, NULL);
+		if (!dma_mapping_error(dev, s->dma_address)) {
+			s->dma_length = s->length;
+			mapped_elements++;
+		} else
+			goto unmap;
+	}
+out:
+	return mapped_elements;
+
+unmap:
+	for_each_sg(sg, s, mapped_elements, i) {
+		if (s->dma_address)
+			s390_dma_unmap_pages(dev, s->dma_address, s->dma_length,
+					     dir, NULL);
+		s->dma_address = 0;
+		s->dma_length = 0;
+	}
+	mapped_elements = 0;
+	goto out;
+}
+
+static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+			      int nr_elements, enum dma_data_direction dir,
+			      struct dma_attrs *attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nr_elements, i) {
+		s390_dma_unmap_pages(dev, s->dma_address, s->dma_length, dir, NULL);
+		s->dma_address = 0;
+		s->dma_length = 0;
+	}
+}
+
+int zpci_dma_init_device(struct zpci_dev *zdev)
+{
+	int rc;
+
+	spin_lock_init(&zdev->iommu_bitmap_lock);
+	spin_lock_init(&zdev->dma_table_lock);
+
+	zdev->dma_table = dma_alloc_cpu_table();
+	if (!zdev->dma_table) {
+		rc = -ENOMEM;
+		goto out_clean;
+	}
+
+	zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET;
+	zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
+	zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
+	if (!zdev->iommu_bitmap) {
+		rc = -ENOMEM;
+		goto out_reg;
+	}
+
+	rc = zpci_register_ioat(zdev,
+				0,
+				zdev->start_dma + PAGE_OFFSET,
+				zdev->start_dma + zdev->iommu_size - 1,
+				(u64) zdev->dma_table);
+	if (rc)
+		goto out_reg;
+	return 0;
+
+out_reg:
+	dma_free_cpu_table(zdev->dma_table);
+out_clean:
+	return rc;
+}
+
+void zpci_dma_exit_device(struct zpci_dev *zdev)
+{
+	zpci_unregister_ioat(zdev, 0);
+	dma_cleanup_tables(zdev);
+	vfree(zdev->iommu_bitmap);
+	zdev->iommu_bitmap = NULL;
+	zdev->next_bit = 0;
+}
+
+static int __init dma_alloc_cpu_table_caches(void)
+{
+	dma_region_table_cache = kmem_cache_create("PCI_DMA_region_tables",
+					ZPCI_TABLE_SIZE, ZPCI_TABLE_ALIGN,
+					0, NULL);
+	if (!dma_region_table_cache)
+		return -ENOMEM;
+
+	dma_page_table_cache = kmem_cache_create("PCI_DMA_page_tables",
+					ZPCI_PT_SIZE, ZPCI_PT_ALIGN,
+					0, NULL);
+	if (!dma_page_table_cache) {
+		kmem_cache_destroy(dma_region_table_cache);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+int __init zpci_dma_init(void)
+{
+	return dma_alloc_cpu_table_caches();
+}
+
+void zpci_dma_exit(void)
+{
+	kmem_cache_destroy(dma_page_table_cache);
+	kmem_cache_destroy(dma_region_table_cache);
+}
+
+#define PREALLOC_DMA_DEBUG_ENTRIES	(1 << 16)
+
+static int __init dma_debug_do_init(void)
+{
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+	return 0;
+}
+fs_initcall(dma_debug_do_init);
+
+struct dma_map_ops s390_dma_ops = {
+	.alloc		= s390_dma_alloc,
+	.free		= s390_dma_free,
+	.map_sg		= s390_dma_map_sg,
+	.unmap_sg	= s390_dma_unmap_sg,
+	.map_page	= s390_dma_map_pages,
+	.unmap_page	= s390_dma_unmap_pages,
+	/* if we support direct DMA this must be conditional */
+	.is_phys	= 0,
+	/* dma_supported is unconditionally true without a callback */
+};
+EXPORT_SYMBOL_GPL(s390_dma_ops);
+
+static int __init s390_iommu_setup(char *str)
+{
+	if (!strncmp(str, "strict", 6))
+		s390_iommu_strict = 1;
+	return 0;
+}
+
+__setup("s390_iommu=", s390_iommu_setup);
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
new file mode 100644
index 000000000..460fdb21c
--- /dev/null
+++ b/arch/s390/pci/pci_event.c
@@ -0,0 +1,136 @@
+/*
+ *  Copyright IBM Corp. 2012
+ *
+ *  Author(s):
+ *    Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#define KMSG_COMPONENT "zpci"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <asm/pci_debug.h>
+#include <asm/sclp.h>
+
+/* Content Code Description for PCI Function Error */
+struct zpci_ccdf_err {
+	u32 reserved1;
+	u32 fh;				/* function handle */
+	u32 fid;			/* function id */
+	u32 ett		:  4;		/* expected table type */
+	u32 mvn		: 12;		/* MSI vector number */
+	u32 dmaas	:  8;		/* DMA address space */
+	u32		:  6;
+	u32 q		:  1;		/* event qualifier */
+	u32 rw		:  1;		/* read/write */
+	u64 faddr;			/* failing address */
+	u32 reserved3;
+	u16 reserved4;
+	u16 pec;			/* PCI event code */
+} __packed;
+
+/* Content Code Description for PCI Function Availability */
+struct zpci_ccdf_avail {
+	u32 reserved1;
+	u32 fh;				/* function handle */
+	u32 fid;			/* function id */
+	u32 reserved2;
+	u32 reserved3;
+	u32 reserved4;
+	u32 reserved5;
+	u16 reserved6;
+	u16 pec;			/* PCI event code */
+} __packed;
+
+static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
+{
+	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
+
+	zpci_err("error CCDF:\n");
+	zpci_err_hex(ccdf, sizeof(*ccdf));
+
+	if (!zdev)
+		return;
+
+	pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n",
+	       pci_name(zdev->pdev), ccdf->pec, ccdf->fid);
+}
+
+void zpci_event_error(void *data)
+{
+	if (zpci_is_enabled())
+		__zpci_event_error(data);
+}
+
+static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
+{
+	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
+	struct pci_dev *pdev = zdev ? zdev->pdev : NULL;
+	int ret;
+
+	pr_info("%s: Event 0x%x reconfigured PCI function 0x%x\n",
+		pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid);
+	zpci_err("avail CCDF:\n");
+	zpci_err_hex(ccdf, sizeof(*ccdf));
+
+	switch (ccdf->pec) {
+	case 0x0301: /* Standby -> Configured */
+		if (!zdev || zdev->state != ZPCI_FN_STATE_STANDBY)
+			break;
+		zdev->state = ZPCI_FN_STATE_CONFIGURED;
+		zdev->fh = ccdf->fh;
+		ret = zpci_enable_device(zdev);
+		if (ret)
+			break;
+		pci_rescan_bus(zdev->bus);
+		break;
+	case 0x0302: /* Reserved -> Standby */
+		if (!zdev)
+			clp_add_pci_device(ccdf->fid, ccdf->fh, 0);
+		break;
+	case 0x0303: /* Deconfiguration requested */
+		if (pdev)
+			pci_stop_and_remove_bus_device(pdev);
+
+		ret = zpci_disable_device(zdev);
+		if (ret)
+			break;
+
+		ret = sclp_pci_deconfigure(zdev->fid);
+		zpci_dbg(3, "deconf fid:%x, rc:%d\n", zdev->fid, ret);
+		if (!ret)
+			zdev->state = ZPCI_FN_STATE_STANDBY;
+
+		break;
+	case 0x0304: /* Configured -> Standby */
+		if (pdev) {
+			/* Give the driver a hint that the function is
+			 * already unusable. */
+			pdev->error_state = pci_channel_io_perm_failure;
+			pci_stop_and_remove_bus_device(pdev);
+		}
+
+		zdev->fh = ccdf->fh;
+		zpci_disable_device(zdev);
+		zdev->state = ZPCI_FN_STATE_STANDBY;
+		break;
+	case 0x0306: /* 0x308 or 0x302 for multiple devices */
+		clp_rescan_pci_devices();
+		break;
+	case 0x0308: /* Standby -> Reserved */
+		if (!zdev)
+			break;
+		pci_stop_root_bus(zdev->bus);
+		pci_remove_root_bus(zdev->bus);
+		break;
+	default:
+		break;
+	}
+}
+
+void zpci_event_availability(void *data)
+{
+	if (zpci_is_enabled())
+		__zpci_event_availability(data);
+}
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
new file mode 100644
index 000000000..85267c058
--- /dev/null
+++ b/arch/s390/pci/pci_insn.c
@@ -0,0 +1,202 @@
+/*
+ * s390 specific pci instructions
+ *
+ * Copyright IBM Corp. 2013
+ */
+
+#include <linux/export.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <asm/pci_insn.h>
+#include <asm/processor.h>
+
+#define ZPCI_INSN_BUSY_DELAY	1	/* 1 microsecond */
+
+/* Modify PCI Function Controls */
+static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status)
+{
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rxy,0xe300000000d0,%[req],%[fib]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib)
+		: : "cc");
+	*status = req >> 24 & 0xff;
+	return cc;
+}
+
+int zpci_mod_fc(u64 req, struct zpci_fib *fib)
+{
+	u8 cc, status;
+
+	do {
+		cc = __mpcifc(req, fib, &status);
+		if (cc == 2)
+			msleep(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d\n",
+			     __func__, cc, status);
+	return (cc) ? -EIO : 0;
+}
+
+/* Refresh PCI Translations */
+static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status)
+{
+	register u64 __addr asm("2") = addr;
+	register u64 __range asm("3") = range;
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rre,0xb9d30000,%[fn],%[addr]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [fn] "+d" (fn)
+		: [addr] "d" (__addr), "d" (__range)
+		: "cc");
+	*status = fn >> 24 & 0xff;
+	return cc;
+}
+
+int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
+{
+	u8 cc, status;
+
+	do {
+		cc = __rpcit(fn, addr, range, &status);
+		if (cc == 2)
+			udelay(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  dma_addr: %Lx  size: %Lx\n",
+			    __func__, cc, status, addr, range);
+	return (cc) ? -EIO : 0;
+}
+
+/* Set Interruption Controls */
+void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc)
+{
+	asm volatile (
+		"	.insn	rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n"
+		: : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused));
+}
+
+/* PCI Load */
+static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
+{
+	register u64 __req asm("2") = req;
+	register u64 __offset asm("3") = offset;
+	int cc = -ENXIO;
+	u64 __data;
+
+	asm volatile (
+		"	.insn	rre,0xb9d20000,%[data],%[req]\n"
+		"0:	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), [data] "=d" (__data), [req] "+d" (__req)
+		:  "d" (__offset)
+		: "cc");
+	*status = __req >> 24 & 0xff;
+	if (!cc)
+		*data = __data;
+
+	return cc;
+}
+
+int zpci_load(u64 *data, u64 req, u64 offset)
+{
+	u8 status;
+	int cc;
+
+	do {
+		cc = __pcilg(data, req, offset, &status);
+		if (cc == 2)
+			udelay(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+			    __func__, cc, status, req, offset);
+	return (cc > 0) ? -EIO : cc;
+}
+EXPORT_SYMBOL_GPL(zpci_load);
+
+/* PCI Store */
+static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status)
+{
+	register u64 __req asm("2") = req;
+	register u64 __offset asm("3") = offset;
+	int cc = -ENXIO;
+
+	asm volatile (
+		"	.insn	rre,0xb9d00000,%[data],%[req]\n"
+		"0:	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), [req] "+d" (__req)
+		: "d" (__offset), [data] "d" (data)
+		: "cc");
+	*status = __req >> 24 & 0xff;
+	return cc;
+}
+
+int zpci_store(u64 data, u64 req, u64 offset)
+{
+	u8 status;
+	int cc;
+
+	do {
+		cc = __pcistg(data, req, offset, &status);
+		if (cc == 2)
+			udelay(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+			__func__, cc, status, req, offset);
+	return (cc > 0) ? -EIO : cc;
+}
+EXPORT_SYMBOL_GPL(zpci_store);
+
+/* PCI Store Block */
+static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
+{
+	int cc = -ENXIO;
+
+	asm volatile (
+		"	.insn	rsy,0xeb00000000d0,%[req],%[offset],%[data]\n"
+		"0:	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), [req] "+d" (req)
+		: [offset] "d" (offset), [data] "Q" (*data)
+		: "cc");
+	*status = req >> 24 & 0xff;
+	return cc;
+}
+
+int zpci_store_block(const u64 *data, u64 req, u64 offset)
+{
+	u8 status;
+	int cc;
+
+	do {
+		cc = __pcistb(data, req, offset, &status);
+		if (cc == 2)
+			udelay(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+			    __func__, cc, status, req, offset);
+	return (cc > 0) ? -EIO : cc;
+}
+EXPORT_SYMBOL_GPL(zpci_store_block);
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
new file mode 100644
index 000000000..b1bb2b723
--- /dev/null
+++ b/arch/s390/pci/pci_mmio.c
@@ -0,0 +1,114 @@
+/*
+ * Access to PCI I/O memory from user space programs.
+ *
+ * Copyright IBM Corp. 2014
+ * Author(s): Alexey Ishchuk <aishchuk@linux.vnet.ibm.com>
+ */
+#include <linux/kernel.h>
+#include <linux/syscalls.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/errno.h>
+#include <linux/pci.h>
+
+static long get_pfn(unsigned long user_addr, unsigned long access,
+		    unsigned long *pfn)
+{
+	struct vm_area_struct *vma;
+	long ret;
+
+	down_read(&current->mm->mmap_sem);
+	ret = -EINVAL;
+	vma = find_vma(current->mm, user_addr);
+	if (!vma)
+		goto out;
+	ret = -EACCES;
+	if (!(vma->vm_flags & access))
+		goto out;
+	ret = follow_pfn(vma, user_addr, pfn);
+out:
+	up_read(&current->mm->mmap_sem);
+	return ret;
+}
+
+SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
+		const void __user *, user_buffer, size_t, length)
+{
+	u8 local_buf[64];
+	void __iomem *io_addr;
+	void *buf;
+	unsigned long pfn;
+	long ret;
+
+	if (!zpci_is_enabled())
+		return -ENODEV;
+
+	if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length)
+		return -EINVAL;
+	if (length > 64) {
+		buf = kmalloc(length, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+	} else
+		buf = local_buf;
+
+	ret = get_pfn(mmio_addr, VM_WRITE, &pfn);
+	if (ret)
+		goto out;
+	io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK));
+
+	ret = -EFAULT;
+	if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE)
+		goto out;
+
+	if (copy_from_user(buf, user_buffer, length))
+		goto out;
+
+	ret = zpci_memcpy_toio(io_addr, buf, length);
+out:
+	if (buf != local_buf)
+		kfree(buf);
+	return ret;
+}
+
+SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
+		void __user *, user_buffer, size_t, length)
+{
+	u8 local_buf[64];
+	void __iomem *io_addr;
+	void *buf;
+	unsigned long pfn;
+	long ret;
+
+	if (!zpci_is_enabled())
+		return -ENODEV;
+
+	if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length)
+		return -EINVAL;
+	if (length > 64) {
+		buf = kmalloc(length, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+	} else
+		buf = local_buf;
+
+	ret = get_pfn(mmio_addr, VM_READ, &pfn);
+	if (ret)
+		goto out;
+	io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK));
+
+	if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) {
+		ret = -EFAULT;
+		goto out;
+	}
+	ret = zpci_memcpy_fromio(buf, io_addr, length);
+	if (ret)
+		goto out;
+	if (copy_to_user(user_buffer, buf, length))
+		ret = -EFAULT;
+
+out:
+	if (buf != local_buf)
+		kfree(buf);
+	return ret;
+}
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
new file mode 100644
index 000000000..fa3ce891e
--- /dev/null
+++ b/arch/s390/pci/pci_sysfs.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#define KMSG_COMPONENT "zpci"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/stat.h>
+#include <linux/pci.h>
+
+#define zpci_attr(name, fmt, member)					\
+static ssize_t name##_show(struct device *dev,				\
+			   struct device_attribute *attr, char *buf)	\
+{									\
+	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));		\
+									\
+	return sprintf(buf, fmt, zdev->member);				\
+}									\
+static DEVICE_ATTR_RO(name)
+
+zpci_attr(function_id, "0x%08x\n", fid);
+zpci_attr(function_handle, "0x%08x\n", fh);
+zpci_attr(pchid, "0x%04x\n", pchid);
+zpci_attr(pfgid, "0x%02x\n", pfgid);
+zpci_attr(vfn, "0x%04x\n", vfn);
+zpci_attr(pft, "0x%02x\n", pft);
+zpci_attr(uid, "0x%x\n", uid);
+zpci_attr(segment0, "0x%02x\n", pfip[0]);
+zpci_attr(segment1, "0x%02x\n", pfip[1]);
+zpci_attr(segment2, "0x%02x\n", pfip[2]);
+zpci_attr(segment3, "0x%02x\n", pfip[3]);
+
+static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct zpci_dev *zdev = get_zdev(pdev);
+	int ret;
+
+	if (!device_remove_file_self(dev, attr))
+		return count;
+
+	pci_stop_and_remove_bus_device(pdev);
+	ret = zpci_disable_device(zdev);
+	if (ret)
+		return ret;
+
+	ret = zpci_enable_device(zdev);
+	if (ret)
+		return ret;
+
+	pci_rescan_bus(zdev->bus);
+	return count;
+}
+static DEVICE_ATTR_WO(recover);
+
+static ssize_t util_string_read(struct file *filp, struct kobject *kobj,
+				struct bin_attribute *attr, char *buf,
+				loff_t off, size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct zpci_dev *zdev = get_zdev(pdev);
+
+	return memory_read_from_buffer(buf, count, &off, zdev->util_str,
+				       sizeof(zdev->util_str));
+}
+static BIN_ATTR_RO(util_string, CLP_UTIL_STR_LEN);
+static struct bin_attribute *zpci_bin_attrs[] = {
+	&bin_attr_util_string,
+	NULL,
+};
+
+static struct attribute *zpci_dev_attrs[] = {
+	&dev_attr_function_id.attr,
+	&dev_attr_function_handle.attr,
+	&dev_attr_pchid.attr,
+	&dev_attr_pfgid.attr,
+	&dev_attr_pft.attr,
+	&dev_attr_vfn.attr,
+	&dev_attr_uid.attr,
+	&dev_attr_recover.attr,
+	NULL,
+};
+static struct attribute_group zpci_attr_group = {
+	.attrs = zpci_dev_attrs,
+	.bin_attrs = zpci_bin_attrs,
+};
+
+static struct attribute *pfip_attrs[] = {
+	&dev_attr_segment0.attr,
+	&dev_attr_segment1.attr,
+	&dev_attr_segment2.attr,
+	&dev_attr_segment3.attr,
+	NULL,
+};
+static struct attribute_group pfip_attr_group = {
+	.name = "pfip",
+	.attrs = pfip_attrs,
+};
+
+const struct attribute_group *zpci_attr_groups[] = {
+	&zpci_attr_group,
+	&pfip_attr_group,
+	NULL,
+};