Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (106 commits)
  powerpc/p3060qds: Add support for P3060QDS board
  powerpc/83xx: Add shutdown request support to MCU handling on MPC8349 MITX
  powerpc/85xx: Make kexec to interate over online cpus
  powerpc/fsl_booke: Fix comment in head_fsl_booke.S
  powerpc/85xx: issue 15 EOI after core reset for FSL CoreNet devices
  powerpc/8xxx: Fix interrupt handling in MPC8xxx GPIO driver
  powerpc/85xx: Add 'fsl,pq3-gpio' compatiable for GPIO driver
  powerpc/86xx: Correct Gianfar support for GE boards
  powerpc/cpm: Clear muram before it is in use.
  drivers/virt: add ioctl for 32-bit compat on 64-bit to fsl-hv-manager
  powerpc/fsl_msi: add support for "msi-address-64" property
  powerpc/85xx: Setup secondary cores PIR with hard SMP id
  powerpc/fsl-booke: Fix settlbcam for 64-bit
  powerpc/85xx: Adding DCSR node to dtsi device trees
  powerpc/85xx: clean up FPGA device tree nodes for Freecsale QorIQ boards
  powerpc/85xx: fix PHYS_64BIT selection for P1022DS
  powerpc/fsl-booke: Fix setup_initial_memory_limit to not blindly map
  powerpc: respect mem= setting for early memory limit setup
  powerpc: Update corenet64_smp_defconfig
  powerpc: Update mpc85xx/corenet 32-bit defconfigs
  ...

Fix up trivial conflicts in:
 - arch/powerpc/configs/40x/hcu4_defconfig
	removed stale file, edited elsewhere
 - arch/powerpc/include/asm/udbg.h, arch/powerpc/kernel/udbg.c:
	added opal and gelic drivers vs added ePAPR driver
 - drivers/tty/serial/8250.c
	moved UPIO_TSI to powerpc vs removed UPIO_DWAPB support

51 files changed, 4180 insertions, 127 deletions

diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig
index b5d87067a58b..8f9c3e245cff 100644
--- a/arch/powerpc/platforms/40x/Kconfig
+++ b/arch/powerpc/platforms/40x/Kconfig
@@ -32,14 +32,6 @@ config EP405
 	help
 	  This option enables support for the EP405/EP405PC boards.
 
-config HCU4
-	bool "Hcu4"
-	depends on 40x
-	default n
-	select 405GPR
-	help
-	  This option enables support for the Nestal Maschinen HCU4 board.
-
 config HOTFOOT
         bool "Hotfoot"
 	depends on 40x
diff --git a/arch/powerpc/platforms/40x/Makefile b/arch/powerpc/platforms/40x/Makefile
index 56e89004c468..88c22de0c850 100644
--- a/arch/powerpc/platforms/40x/Makefile
+++ b/arch/powerpc/platforms/40x/Makefile
@@ -1,4 +1,3 @@
-obj-$(CONFIG_HCU4)				+= hcu4.o
 obj-$(CONFIG_WALNUT)				+= walnut.o
 obj-$(CONFIG_XILINX_VIRTEX_GENERIC_BOARD)	+= virtex.o
 obj-$(CONFIG_EP405)				+= ep405.o
diff --git a/arch/powerpc/platforms/40x/hcu4.c b/arch/powerpc/platforms/40x/hcu4.c
deleted file mode 100644
index 60b2afecab75..000000000000
--- a/arch/powerpc/platforms/40x/hcu4.c
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * Architecture- / platform-specific boot-time initialization code for
- * IBM PowerPC 4xx based boards. Adapted from original
- * code by Gary Thomas, Cort Dougan <cort@fsmlabs.com>, and Dan Malek
- * <dan@net4x.com>.
- *
- * Copyright(c) 1999-2000 Grant Erickson <grant@lcse.umn.edu>
- *
- * Rewritten and ported to the merged powerpc tree:
- * Copyright 2007 IBM Corporation
- * Josh Boyer <jwboyer@linux.vnet.ibm.com>
- *
- * 2002 (c) MontaVista, Software, Inc.  This file is licensed under
- * the terms of the GNU General Public License version 2.  This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-
-#include <linux/init.h>
-#include <linux/of_platform.h>
-
-#include <asm/machdep.h>
-#include <asm/prom.h>
-#include <asm/udbg.h>
-#include <asm/time.h>
-#include <asm/uic.h>
-#include <asm/ppc4xx.h>
-
-static __initdata struct of_device_id hcu4_of_bus[] = {
-	{ .compatible = "ibm,plb3", },
-	{ .compatible = "ibm,opb", },
-	{ .compatible = "ibm,ebc", },
-	{},
-};
-
-static int __init hcu4_device_probe(void)
-{
-	of_platform_bus_probe(NULL, hcu4_of_bus, NULL);
-	return 0;
-}
-machine_device_initcall(hcu4, hcu4_device_probe);
-
-static int __init hcu4_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "netstal,hcu4"))
-		return 0;
-
-	return 1;
-}
-
-define_machine(hcu4) {
-	.name			= "HCU4",
-	.probe			= hcu4_probe,
-	.progress		= udbg_progress,
-	.init_IRQ		= uic_init_tree,
-	.get_irq		= uic_get_irq,
-	.restart		= ppc4xx_reset_system,
-	.calibrate_decr		= generic_calibrate_decr,
-};
diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig
index 27b0651221d1..b3ebce1aec07 100644
--- a/arch/powerpc/platforms/512x/Kconfig
+++ b/arch/powerpc/platforms/512x/Kconfig
@@ -6,6 +6,7 @@ config PPC_MPC512x
 	select PPC_CLOCK
 	select PPC_PCI_CHOICE
 	select FSL_PCI if PCI
+	select ARCH_WANT_OPTIONAL_GPIOLIB
 
 config MPC5121_ADS
 	bool "Freescale MPC5121E ADS"
diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c
index 428c5e0a0e75..3661bcdc326a 100644
--- a/arch/powerpc/platforms/82xx/km82xx.c
+++ b/arch/powerpc/platforms/82xx/km82xx.c
@@ -49,6 +49,9 @@ struct cpm_pin {
 };
 
 static __initdata struct cpm_pin km82xx_pins[] = {
+	/* SMC1 */
+	{2, 4, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
+	{2, 5, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
 
 	/* SMC2 */
 	{0, 8, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
@@ -137,6 +140,7 @@ static void __init init_ioports(void)
 	}
 
 	cpm2_smc_clk_setup(CPM_CLK_SMC2, CPM_BRG8);
+	cpm2_smc_clk_setup(CPM_CLK_SMC1, CPM_BRG7);
 	cpm2_clk_setup(CPM_CLK_SCC1, CPM_CLK11, CPM_CLK_RX);
 	cpm2_clk_setup(CPM_CLK_SCC1, CPM_CLK11, CPM_CLK_TX);
 	cpm2_clk_setup(CPM_CLK_SCC3, CPM_CLK5, CPM_CLK_RTX);
diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig
index 73f4135f3a1a..670a033264c0 100644
--- a/arch/powerpc/platforms/83xx/Kconfig
+++ b/arch/powerpc/platforms/83xx/Kconfig
@@ -114,18 +114,21 @@ config KMETER1
 
 endif
 
-# used for usb
+# used for usb & gpio
 config PPC_MPC831x
 	bool
+	select ARCH_WANT_OPTIONAL_GPIOLIB
 
 # used for math-emu
 config PPC_MPC832x
 	bool
 
-# used for usb
+# used for usb & gpio
 config PPC_MPC834x
 	bool
+	select ARCH_WANT_OPTIONAL_GPIOLIB
 
-# used for usb
+# used for usb & gpio
 config PPC_MPC837x
 	bool
+	select ARCH_WANT_OPTIONAL_GPIOLIB
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index 70798ac911ef..ef6537b8ed33 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -21,6 +21,8 @@
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 #include <linux/slab.h>
+#include <linux/kthread.h>
+#include <linux/reboot.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 
@@ -30,6 +32,7 @@
  */
 #define MCU_REG_CTRL	0x20
 #define MCU_CTRL_POFF	0x40
+#define MCU_CTRL_BTN	0x80
 
 #define MCU_NUM_GPIO	2
 
@@ -42,13 +45,55 @@ struct mcu {
 
 static struct mcu *glob_mcu;
 
+struct task_struct *shutdown_thread;
+static int shutdown_thread_fn(void *data)
+{
+	int ret;
+	struct mcu *mcu = glob_mcu;
+
+	while (!kthread_should_stop()) {
+		ret = i2c_smbus_read_byte_data(mcu->client, MCU_REG_CTRL);
+		if (ret < 0)
+			pr_err("MCU status reg read failed.\n");
+		mcu->reg_ctrl = ret;
+
+
+		if (mcu->reg_ctrl & MCU_CTRL_BTN) {
+			i2c_smbus_write_byte_data(mcu->client, MCU_REG_CTRL,
+						  mcu->reg_ctrl & ~MCU_CTRL_BTN);
+
+			ctrl_alt_del();
+		}
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(HZ);
+	}
+
+	return 0;
+}
+
+static ssize_t show_status(struct device *d,
+			   struct device_attribute *attr, char *buf)
+{
+	int ret;
+	struct mcu *mcu = glob_mcu;
+
+	ret = i2c_smbus_read_byte_data(mcu->client, MCU_REG_CTRL);
+	if (ret < 0)
+		return -ENODEV;
+	mcu->reg_ctrl = ret;
+
+	return sprintf(buf, "%02x\n", ret);
+}
+static DEVICE_ATTR(status, S_IRUGO, show_status, NULL);
+
 static void mcu_power_off(void)
 {
 	struct mcu *mcu = glob_mcu;
 
 	pr_info("Sending power-off request to the MCU...\n");
 	mutex_lock(&mcu->lock);
-	i2c_smbus_write_byte_data(glob_mcu->client, MCU_REG_CTRL,
+	i2c_smbus_write_byte_data(mcu->client, MCU_REG_CTRL,
 				  mcu->reg_ctrl | MCU_CTRL_POFF);
 	mutex_unlock(&mcu->lock);
 }
@@ -130,6 +175,13 @@ static int __devinit mcu_probe(struct i2c_client *client,
 		dev_info(&client->dev, "will provide power-off service\n");
 	}
 
+	if (device_create_file(&client->dev, &dev_attr_status))
+		dev_err(&client->dev,
+			"couldn't create device file for status\n");
+
+	shutdown_thread = kthread_run(shutdown_thread_fn, NULL,
+				      "mcu-i2c-shdn");
+
 	return 0;
 err:
 	kfree(mcu);
@@ -141,6 +193,10 @@ static int __devexit mcu_remove(struct i2c_client *client)
 	struct mcu *mcu = i2c_get_clientdata(client);
 	int ret;
 
+	kthread_stop(shutdown_thread);
+
+	device_remove_file(&client->dev, &dev_attr_status);
+
 	if (glob_mcu == mcu) {
 		ppc_md.power_off = NULL;
 		glob_mcu = NULL;
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 12f5932dadc9..45023e26aea3 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -171,17 +171,18 @@ config SBC8560
 	help
 	  This option enables support for the Wind River SBC8560 board
 
-config P2040_RDB
-	bool "Freescale P2040 RDB"
+config P2041_RDB
+	bool "Freescale P2041 RDB"
 	select DEFAULT_UIMAGE
 	select PPC_E500MC
 	select PHYS_64BIT
 	select SWIOTLB
-	select MPC8xxx_GPIO
+	select ARCH_REQUIRE_GPIOLIB
+	select GPIO_MPC8XXX
 	select HAS_RAPIDIO
 	select PPC_EPAPR_HV_PIC
 	help
-	  This option enables support for the P2040 RDB board
+	  This option enables support for the P2041 RDB board
 
 config P3041_DS
 	bool "Freescale P3041 DS"
@@ -189,19 +190,33 @@ config P3041_DS
 	select PPC_E500MC
 	select PHYS_64BIT
 	select SWIOTLB
-	select MPC8xxx_GPIO
+	select ARCH_REQUIRE_GPIOLIB
+	select GPIO_MPC8XXX
 	select HAS_RAPIDIO
 	select PPC_EPAPR_HV_PIC
 	help
 	  This option enables support for the P3041 DS board
 
+config P3060_QDS
+	bool "Freescale P3060 QDS"
+	select DEFAULT_UIMAGE
+	select PPC_E500MC
+	select PHYS_64BIT
+	select SWIOTLB
+	select MPC8xxx_GPIO
+	select HAS_RAPIDIO
+	select PPC_EPAPR_HV_PIC
+	help
+	  This option enables support for the P3060 QDS board
+
 config P4080_DS
 	bool "Freescale P4080 DS"
 	select DEFAULT_UIMAGE
 	select PPC_E500MC
 	select PHYS_64BIT
 	select SWIOTLB
-	select MPC8xxx_GPIO
+	select ARCH_REQUIRE_GPIOLIB
+	select GPIO_MPC8XXX
 	select HAS_RAPIDIO
 	select PPC_EPAPR_HV_PIC
 	help
@@ -216,7 +231,8 @@ config P5020_DS
 	select PPC_E500MC
 	select PHYS_64BIT
 	select SWIOTLB
-	select MPC8xxx_GPIO
+	select ARCH_REQUIRE_GPIOLIB
+	select GPIO_MPC8XXX
 	select HAS_RAPIDIO
 	select PPC_EPAPR_HV_PIC
 	help
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index a971b32c5c0a..bc5acb95917a 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -13,8 +13,9 @@ obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o
 obj-$(CONFIG_P1010_RDB)   += p1010rdb.o
 obj-$(CONFIG_P1022_DS)    += p1022_ds.o
 obj-$(CONFIG_P1023_RDS)   += p1023_rds.o
-obj-$(CONFIG_P2040_RDB)   += p2040_rdb.o corenet_ds.o
+obj-$(CONFIG_P2041_RDB)   += p2041_rdb.o corenet_ds.o
 obj-$(CONFIG_P3041_DS)    += p3041_ds.o corenet_ds.o
+obj-$(CONFIG_P3060_QDS)   += p3060_qds.o corenet_ds.o
 obj-$(CONFIG_P4080_DS)    += p4080_ds.o corenet_ds.o
 obj-$(CONFIG_P5020_DS)    += p5020_ds.o corenet_ds.o
 obj-$(CONFIG_STX_GP3)	  += stx_gp3.o
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index c01c7277888c..fda15716fada 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -129,17 +129,20 @@ static void p1022ds_set_gamma_table(enum fsl_diu_monitor_port port,
  */
 static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port)
 {
-	struct device_node *pixis_node;
+	struct device_node *np;
 	void __iomem *pixis;
 	u8 __iomem *brdcfg1;
 
-	pixis_node = of_find_compatible_node(NULL, NULL, "fsl,p1022ds-pixis");
-	if (!pixis_node) {
+	np = of_find_compatible_node(NULL, NULL, "fsl,p1022ds-fpga");
+	if (!np)
+		/* older device trees used "fsl,p1022ds-pixis" */
+		np = of_find_compatible_node(NULL, NULL, "fsl,p1022ds-pixis");
+	if (!np) {
 		pr_err("p1022ds: missing ngPIXIS node\n");
 		return;
 	}
 
-	pixis = of_iomap(pixis_node, 0);
+	pixis = of_iomap(np, 0);
 	if (!pixis) {
 		pr_err("p1022ds: could not map ngPIXIS registers\n");
 		return;
diff --git a/arch/powerpc/platforms/85xx/p2040_rdb.c b/arch/powerpc/platforms/85xx/p2041_rdb.c
index 32b56ac73dfb..eda6ed5683e1 100644
--- a/arch/powerpc/platforms/85xx/p2040_rdb.c
+++ b/arch/powerpc/platforms/85xx/p2041_rdb.c
@@ -1,5 +1,5 @@
 /*
- * P2040 RDB Setup
+ * P2041 RDB Setup
  *
  * Copyright 2011 Freescale Semiconductor Inc.
  *
@@ -35,18 +35,18 @@
 /*
  * Called very early, device-tree isn't unflattened
  */
-static int __init p2040_rdb_probe(void)
+static int __init p2041_rdb_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
 #ifdef CONFIG_SMP
 	extern struct smp_ops_t smp_85xx_ops;
 #endif
 
-	if (of_flat_dt_is_compatible(root, "fsl,P2040RDB"))
+	if (of_flat_dt_is_compatible(root, "fsl,P2041RDB"))
 		return 1;
 
 	/* Check if we're running under the Freescale hypervisor */
-	if (of_flat_dt_is_compatible(root, "fsl,P2040RDB-hv")) {
+	if (of_flat_dt_is_compatible(root, "fsl,P2041RDB-hv")) {
 		ppc_md.init_IRQ = ehv_pic_init;
 		ppc_md.get_irq = ehv_pic_get_irq;
 		ppc_md.restart = fsl_hv_restart;
@@ -66,9 +66,9 @@ static int __init p2040_rdb_probe(void)
 	return 0;
 }
 
-define_machine(p2040_rdb) {
-	.name			= "P2040 RDB",
-	.probe			= p2040_rdb_probe,
+define_machine(p2041_rdb) {
+	.name			= "P2041 RDB",
+	.probe			= p2041_rdb_probe,
 	.setup_arch		= corenet_ds_setup_arch,
 	.init_IRQ		= corenet_ds_pic_init,
 #ifdef CONFIG_PCI
@@ -81,8 +81,8 @@ define_machine(p2040_rdb) {
 	.power_save		= e500_idle,
 };
 
-machine_device_initcall(p2040_rdb, corenet_ds_publish_devices);
+machine_device_initcall(p2041_rdb, corenet_ds_publish_devices);
 
 #ifdef CONFIG_SWIOTLB
-machine_arch_initcall(p2040_rdb, swiotlb_setup_bus_notifier);
+machine_arch_initcall(p2041_rdb, swiotlb_setup_bus_notifier);
 #endif
diff --git a/arch/powerpc/platforms/85xx/p3060_qds.c b/arch/powerpc/platforms/85xx/p3060_qds.c
new file mode 100644
index 000000000000..01dcf44871e9
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/p3060_qds.c
@@ -0,0 +1,77 @@
+/*
+ * P3060 QDS Setup
+ *
+ * Copyright 2011 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/phy.h>
+#include <asm/machdep.h>
+#include <asm/udbg.h>
+#include <asm/mpic.h>
+#include <linux/of_platform.h>
+#include <sysdev/fsl_soc.h>
+#include <sysdev/fsl_pci.h>
+#include <asm/ehv_pic.h>
+#include "corenet_ds.h"
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init p3060_qds_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+#ifdef CONFIG_SMP
+	extern struct smp_ops_t smp_85xx_ops;
+#endif
+
+	if (of_flat_dt_is_compatible(root, "fsl,P3060QDS"))
+		return 1;
+
+	/* Check if we're running under the Freescale hypervisor */
+	if (of_flat_dt_is_compatible(root, "fsl,P3060QDS-hv")) {
+		ppc_md.init_IRQ = ehv_pic_init;
+		ppc_md.get_irq = ehv_pic_get_irq;
+		ppc_md.restart = fsl_hv_restart;
+		ppc_md.power_off = fsl_hv_halt;
+		ppc_md.halt = fsl_hv_halt;
+#ifdef CONFIG_SMP
+		/*
+		 * Disable the timebase sync operations because we can't write
+		 * to the timebase registers under the hypervisor.
+		 */
+		smp_85xx_ops.give_timebase = NULL;
+		smp_85xx_ops.take_timebase = NULL;
+#endif
+		return 1;
+	}
+
+	return 0;
+}
+
+define_machine(p3060_qds) {
+	.name			= "P3060 QDS",
+	.probe			= p3060_qds_probe,
+	.setup_arch		= corenet_ds_setup_arch,
+	.init_IRQ		= corenet_ds_pic_init,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+	.get_irq		= mpic_get_coreint_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+	.power_save		= e500_idle,
+};
+
+machine_device_initcall(p3060_qds, declare_of_platform_devices);
+
+#ifdef CONFIG_SWIOTLB
+machine_arch_initcall(p3060_qds, swiotlb_setup_bus_notifier);
+#endif
diff --git a/arch/powerpc/platforms/85xx/sbc8560.c b/arch/powerpc/platforms/85xx/sbc8560.c
index 09ced7221750..cebd786dc334 100644
--- a/arch/powerpc/platforms/85xx/sbc8560.c
+++ b/arch/powerpc/platforms/85xx/sbc8560.c
@@ -283,7 +283,7 @@ static int __init sbc8560_bdrstcr_init(void)
 
 	of_address_to_resource(np, 0, &res);
 
-	printk(KERN_INFO "sbc8560: Found BRSTCR at i/o 0x%x\n", res.start);
+	printk(KERN_INFO "sbc8560: Found BRSTCR at %pR\n", &res);
 
 	brstcr = ioremap(res.start, resource_size(&res));
 	if(!brstcr)
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 5b9b901f6443..2df4785ffd4e 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -48,10 +48,11 @@ smp_85xx_kick_cpu(int nr)
 	const u64 *cpu_rel_addr;
 	__iomem u32 *bptr_vaddr;
 	struct device_node *np;
-	int n = 0;
+	int n = 0, hw_cpu = get_hard_smp_processor_id(nr);
 	int ioremappable;
 
-	WARN_ON (nr < 0 || nr >= NR_CPUS);
+	WARN_ON(nr < 0 || nr >= NR_CPUS);
+	WARN_ON(hw_cpu < 0 || hw_cpu >= NR_CPUS);
 
 	pr_debug("smp_85xx_kick_cpu: kick CPU #%d\n", nr);
 
@@ -79,7 +80,7 @@ smp_85xx_kick_cpu(int nr)
 
 	local_irq_save(flags);
 
-	out_be32(bptr_vaddr + BOOT_ENTRY_PIR, nr);
+	out_be32(bptr_vaddr + BOOT_ENTRY_PIR, hw_cpu);
 #ifdef CONFIG_PPC32
 	out_be32(bptr_vaddr + BOOT_ENTRY_ADDR_LOWER, __pa(__early_start));
 
@@ -88,7 +89,7 @@ smp_85xx_kick_cpu(int nr)
 				(ulong)(bptr_vaddr + SIZE_BOOT_ENTRY));
 
 	/* Wait a bit for the CPU to ack. */
-	while ((__secondary_hold_acknowledge != nr) && (++n < 1000))
+	while ((__secondary_hold_acknowledge != hw_cpu) && (++n < 1000))
 		mdelay(1);
 #else
 	smp_generic_kick_cpu(nr);
@@ -206,7 +207,7 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image)
 	if ( !timeout )
 		printk(KERN_ERR "Unable to bring down secondary cpu(s)");
 
-	for (i = 0; i < num_cpus; i++)
+	for_each_online_cpu(i)
 	{
 		if ( i == smp_processor_id() ) continue;
 		mpic_reset_core(i);
@@ -243,6 +244,7 @@ void __init mpc85xx_smp_init(void)
 		 * If left NULL, .message_pass defaults to
 		 * smp_muxed_ipi_message_pass
 		 */
+		smp_85xx_ops.message_pass = NULL;
 		smp_85xx_ops.cause_ipi = doorbell_cause_ipi;
 	}
 
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index a0b5638c5dc8..8d6599d54ea6 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -4,6 +4,7 @@ menuconfig PPC_86xx
 	depends on 6xx
 	select FSL_SOC
 	select ALTIVEC
+	select ARCH_WANT_OPTIONAL_GPIOLIB
 	help
 	  The Freescale E600 SoCs have 74xx cores.
 
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index b9ba86191aed..e4588721ef34 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -1,5 +1,6 @@
 menu "Platform support"
 
+source "arch/powerpc/platforms/powernv/Kconfig"
 source "arch/powerpc/platforms/pseries/Kconfig"
 source "arch/powerpc/platforms/iseries/Kconfig"
 source "arch/powerpc/platforms/chrp/Kconfig"
@@ -333,16 +334,6 @@ config OF_RTC
 
 source "arch/powerpc/sysdev/bestcomm/Kconfig"
 
-config MPC8xxx_GPIO
-	bool "MPC512x/MPC8xxx GPIO support"
-	depends on PPC_MPC512x || PPC_MPC831x || PPC_MPC834x || PPC_MPC837x || \
-		   FSL_SOC_BOOKE || PPC_86xx
-	select GENERIC_GPIO
-	select ARCH_REQUIRE_GPIOLIB
-	help
-	  Say Y here if you're going to use hardware that connects to the
-	  MPC512x/831x/834x/837x/8572/8610 GPIOs.
-
 config SIMPLE_GPIO
 	bool "Support for simple, memory-mapped GPIO controllers"
 	depends on PPC
@@ -355,7 +346,7 @@ config SIMPLE_GPIO
 	  on-board peripherals.
 
 config MCU_MPC8349EMITX
-	tristate "MPC8349E-mITX MCU driver"
+	bool "MPC8349E-mITX MCU driver"
 	depends on I2C && PPC_83xx
 	select GENERIC_GPIO
 	select ARCH_REQUIRE_GPIOLIB
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index e06e39589a09..a85990c886e9 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -69,6 +69,7 @@ config PPC_BOOK3S_64
 	bool "Server processors"
 	select PPC_FPU
 	select PPC_HAVE_PMU_SUPPORT
+	select SYS_SUPPORTS_HUGETLBFS
 
 config PPC_BOOK3E_64
 	bool "Embedded processors"
@@ -173,6 +174,7 @@ config BOOKE
 config FSL_BOOKE
 	bool
 	depends on (E200 || E500) && PPC32
+	select SYS_SUPPORTS_HUGETLBFS if PHYS_64BIT
 	default y
 
 # this is for common code between PPC32 & PPC64 FSL BOOKE
@@ -296,7 +298,7 @@ config PPC_BOOK3E_MMU
 
 config PPC_MM_SLICES
 	bool
-	default y if HUGETLB_PAGE || (PPC_STD_MMU_64 && PPC_64K_PAGES)
+	default y if (PPC64 && HUGETLB_PAGE) || (PPC_STD_MMU_64 && PPC_64K_PAGES)
 	default n
 
 config VIRT_CPU_ACCOUNTING
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index 73e2116cfeed..2635a22bade2 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_PPC_82xx)		+= 82xx/
 obj-$(CONFIG_PPC_83xx)		+= 83xx/
 obj-$(CONFIG_FSL_SOC_BOOKE)	+= 85xx/
 obj-$(CONFIG_PPC_86xx)		+= 86xx/
+obj-$(CONFIG_PPC_POWERNV)	+= powernv/
 obj-$(CONFIG_PPC_PSERIES)	+= pseries/
 obj-$(CONFIG_PPC_ISERIES)	+= iseries/
 obj-$(CONFIG_PPC_MAPLE)		+= maple/
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 26a067122a54..fc46fcac3921 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -1159,6 +1159,26 @@ static int __init setup_iommu_fixed(char *str)
 }
 __setup("iommu_fixed=", setup_iommu_fixed);
 
+static u64 cell_dma_get_required_mask(struct device *dev)
+{
+	struct dma_map_ops *dma_ops;
+
+	if (!dev->dma_mask)
+		return 0;
+
+	if (!iommu_fixed_disabled &&
+			cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR)
+		return DMA_BIT_MASK(64);
+
+	dma_ops = get_dma_ops(dev);
+	if (dma_ops->get_required_mask)
+		return dma_ops->get_required_mask(dev);
+
+	WARN_ONCE(1, "no get_required_mask in %p ops", dma_ops);
+
+	return DMA_BIT_MASK(64);
+}
+
 static int __init cell_iommu_init(void)
 {
 	struct device_node *np;
@@ -1175,6 +1195,7 @@ static int __init cell_iommu_init(void)
 
 	/* Setup various ppc_md. callbacks */
 	ppc_md.pci_dma_dev_setup = cell_pci_dma_dev_setup;
+	ppc_md.dma_get_required_mask = cell_dma_get_required_mask;
 	ppc_md.tce_build = tce_build_cell;
 	ppc_md.tce_free = tce_free_cell;
 
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
new file mode 100644
index 000000000000..74fea5c21839
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -0,0 +1,16 @@
+config PPC_POWERNV
+	depends on PPC64 && PPC_BOOK3S
+	bool "IBM PowerNV (Non-Virtualized) platform support"
+	select PPC_NATIVE
+	select PPC_XICS
+	select PPC_ICP_NATIVE
+	select PPC_P7_NAP
+	select PPC_PCI_CHOICE if EMBEDDED
+	default y
+
+config PPC_POWERNV_RTAS
+	depends on PPC_POWERNV
+	bool "Support for RTAS based PowerNV platforms such as BML"
+	default y
+	select PPC_ICS_RTAS
+	select PPC_RTAS
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
new file mode 100644
index 000000000000..31853008b418
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -0,0 +1,5 @@
+obj-y			+= setup.o opal-takeover.o opal-wrappers.o opal.o
+obj-y			+= opal-rtc.o opal-nvram.o
+
+obj-$(CONFIG_SMP)	+= smp.o
+obj-$(CONFIG_PCI)	+= pci.o pci-p5ioc2.o
diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c
new file mode 100644
index 000000000000..3f83e1ae26ac
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-nvram.c
@@ -0,0 +1,88 @@
+/*
+ * PowerNV nvram code.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define DEBUG
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of.h>
+
+#include <asm/opal.h>
+#include <asm/machdep.h>
+
+static unsigned int nvram_size;
+
+static ssize_t opal_nvram_size(void)
+{
+	return nvram_size;
+}
+
+static ssize_t opal_nvram_read(char *buf, size_t count, loff_t *index)
+{
+	s64 rc;
+	int off;
+
+	if (*index >= nvram_size)
+		return 0;
+	off = *index;
+	if ((off + count) > nvram_size)
+		count = nvram_size - off;
+	rc = opal_read_nvram(__pa(buf), count, off);
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+	*index += count;
+	return count;
+}
+
+static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index)
+{
+	s64 rc = OPAL_BUSY;
+	int off;
+
+	if (*index >= nvram_size)
+		return 0;
+	off = *index;
+	if ((off + count) > nvram_size)
+		count = nvram_size - off;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_write_nvram(__pa(buf), count, off);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+	}
+	*index += count;
+	return count;
+}
+
+void __init opal_nvram_init(void)
+{
+	struct device_node *np;
+	const u32 *nbytes_p;
+
+	np = of_find_compatible_node(NULL, NULL, "ibm,opal-nvram");
+	if (np == NULL)
+		return;
+
+	nbytes_p = of_get_property(np, "#bytes", NULL);
+	if (!nbytes_p) {
+		of_node_put(np);
+		return;
+	}
+	nvram_size = *nbytes_p;
+
+	printk(KERN_INFO "OPAL nvram setup, %u bytes\n", nvram_size);
+	of_node_put(np);
+
+	ppc_md.nvram_read = opal_nvram_read;
+	ppc_md.nvram_write = opal_nvram_write;
+	ppc_md.nvram_size = opal_nvram_size;
+}
+
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
new file mode 100644
index 000000000000..2aa7641aac9b
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -0,0 +1,97 @@
+/*
+ * PowerNV Real Time Clock.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/time.h>
+#include <linux/bcd.h>
+#include <linux/rtc.h>
+#include <linux/delay.h>
+
+#include <asm/opal.h>
+#include <asm/firmware.h>
+
+static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm)
+{
+	tm->tm_year	= ((bcd2bin(y_m_d >> 24) * 100) +
+			   bcd2bin((y_m_d >> 16) & 0xff)) - 1900;
+	tm->tm_mon	= bcd2bin((y_m_d >> 8) & 0xff) - 1;
+	tm->tm_mday	= bcd2bin(y_m_d & 0xff);
+	tm->tm_hour	= bcd2bin((h_m_s_ms >> 56) & 0xff);
+	tm->tm_min	= bcd2bin((h_m_s_ms >> 48) & 0xff);
+	tm->tm_sec	= bcd2bin((h_m_s_ms >> 40) & 0xff);
+
+        GregorianDay(tm);
+}
+
+unsigned long __init opal_get_boot_time(void)
+{
+	struct rtc_time tm;
+	u32 y_m_d;
+	u64 h_m_s_ms;
+	long rc = OPAL_BUSY;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_read(&y_m_d, &h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
+	if (rc != OPAL_SUCCESS)
+		return 0;
+	opal_to_tm(y_m_d, h_m_s_ms, &tm);
+	return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+		      tm.tm_hour, tm.tm_min, tm.tm_sec);
+}
+
+void opal_get_rtc_time(struct rtc_time *tm)
+{
+	long rc = OPAL_BUSY;
+	u32 y_m_d;
+	u64 h_m_s_ms;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_read(&y_m_d, &h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
+	if (rc != OPAL_SUCCESS)
+		return;
+	opal_to_tm(y_m_d, h_m_s_ms, tm);
+}
+
+int opal_set_rtc_time(struct rtc_time *tm)
+{
+	long rc = OPAL_BUSY;
+	u32 y_m_d = 0;
+	u64 h_m_s_ms = 0;
+
+	y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24;
+	y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16;
+	y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8;
+	y_m_d |= ((u32)bin2bcd(tm->tm_mday));
+
+	h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56;
+	h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48;
+	h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_write(y_m_d, h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
+	return rc == OPAL_SUCCESS ? 0 : -EIO;
+}
diff --git a/arch/powerpc/platforms/powernv/opal-takeover.S b/arch/powerpc/platforms/powernv/opal-takeover.S
new file mode 100644
index 000000000000..77b48b2b9309
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-takeover.S
@@ -0,0 +1,140 @@
+/*
+ * PowerNV OPAL takeover assembly code, for use by prom_init.c
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/hvcall.h>
+#include <asm/asm-offsets.h>
+#include <asm/opal.h>
+
+#define STK_PARAM(i)	(48 + ((i)-3)*8)
+
+#define H_HAL_TAKEOVER			0x5124
+#define H_HAL_TAKEOVER_QUERY_MAGIC	-1
+
+	.text
+_GLOBAL(opal_query_takeover)
+	mfcr	r0
+	stw	r0,8(r1)
+	std	r3,STK_PARAM(r3)(r1)
+	std	r4,STK_PARAM(r4)(r1)
+	li	r3,H_HAL_TAKEOVER
+	li	r4,H_HAL_TAKEOVER_QUERY_MAGIC
+	HVSC
+	ld	r10,STK_PARAM(r3)(r1)
+	std	r4,0(r10)
+	ld	r10,STK_PARAM(r4)(r1)
+	std	r5,0(r10)
+	lwz	r0,8(r1)
+	mtcrf	0xff,r0
+	blr
+
+_GLOBAL(opal_do_takeover)
+	mfcr	r0
+	stw	r0,8(r1)
+	mflr	r0
+	std	r0,16(r1)
+	bl	__opal_do_takeover
+	ld	r0,16(r1)
+	mtlr	r0
+	lwz	r0,8(r1)
+	mtcrf	0xff,r0
+	blr
+
+__opal_do_takeover:
+	ld	r4,0(r3)
+	ld	r5,0x8(r3)
+	ld	r6,0x10(r3)
+	ld	r7,0x18(r3)
+	ld	r8,0x20(r3)
+	ld	r9,0x28(r3)
+	ld	r10,0x30(r3)
+	ld	r11,0x38(r3)
+	li	r3,H_HAL_TAKEOVER
+	HVSC
+	blr
+
+	.globl opal_secondary_entry
+opal_secondary_entry:
+	mr	r31,r3
+	mfmsr	r11
+	li	r12,(MSR_SF | MSR_ISF)@highest
+	sldi	r12,r12,48
+	or	r11,r11,r12
+	mtmsrd	r11
+	isync
+	mfspr	r4,SPRN_PIR
+	std	r4,0(r3)
+1:	HMT_LOW
+	ld	r4,8(r3)
+	cmpli	cr0,r4,0
+	beq	1b
+	HMT_MEDIUM
+1:	addi	r3,r31,16
+	bl	__opal_do_takeover
+	b	1b
+
+_GLOBAL(opal_enter_rtas)
+	mflr	r0
+	std	r0,16(r1)
+        stdu	r1,-PROM_FRAME_SIZE(r1)	/* Save SP and create stack space */
+
+	/* Because PROM is running in 32b mode, it clobbers the high order half
+	 * of all registers that it saves.  We therefore save those registers
+	 * PROM might touch to the stack.  (r0, r3-r13 are caller saved)
+	*/
+	SAVE_GPR(2, r1)
+	SAVE_GPR(13, r1)
+	SAVE_8GPRS(14, r1)
+	SAVE_10GPRS(22, r1)
+	mfcr	r10
+	mfmsr	r11
+	std	r10,_CCR(r1)
+	std	r11,_MSR(r1)
+
+	/* Get the PROM entrypoint */
+	mtlr	r5
+
+	/* Switch MSR to 32 bits mode
+	 */
+        li      r12,1
+        rldicr  r12,r12,MSR_SF_LG,(63-MSR_SF_LG)
+        andc    r11,r11,r12
+        li      r12,1
+        rldicr  r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG)
+        andc    r11,r11,r12
+        mtmsrd  r11
+        isync
+
+	/* Enter RTAS here... */
+	blrl
+
+	/* Just make sure that r1 top 32 bits didn't get
+	 * corrupt by OF
+	 */
+	rldicl	r1,r1,0,32
+
+	/* Restore the MSR (back to 64 bits) */
+	ld	r0,_MSR(r1)
+	MTMSRD(r0)
+        isync
+
+	/* Restore other registers */
+	REST_GPR(2, r1)
+	REST_GPR(13, r1)
+	REST_8GPRS(14, r1)
+	REST_10GPRS(22, r1)
+	ld	r4,_CCR(r1)
+	mtcr	r4
+
+        addi	r1,r1,PROM_FRAME_SIZE
+	ld	r0,16(r1)
+	mtlr    r0
+	blr
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
new file mode 100644
index 000000000000..4a3f46d8533e
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -0,0 +1,101 @@
+/*
+ * PowerNV OPAL API wrappers
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/hvcall.h>
+#include <asm/asm-offsets.h>
+#include <asm/opal.h>
+
+/* TODO:
+ *
+ * - Trace irqs in/off (needs saving/restoring all args, argh...)
+ * - Get r11 feed up by Dave so I can have better register usage
+ */
+#define OPAL_CALL(name, token)		\
+ _GLOBAL(name);				\
+	mflr	r0;			\
+	mfcr	r12;			\
+	std	r0,16(r1);		\
+	std	r12,8(r1);		\
+	std	r1,PACAR1(r13);		\
+	li	r0,0;			\
+	mfmsr	r12;			\
+	ori	r0,r0,MSR_EE;		\
+	std	r12,PACASAVEDMSR(r13);	\
+	andc	r12,r12,r0;		\
+	mtmsrd	r12,1;			\
+	LOAD_REG_ADDR(r0,.opal_return);	\
+	mtlr	r0;			\
+	li	r0,MSR_DR|MSR_IR;	\
+	andc	r12,r12,r0;		\
+	li	r0,token;		\
+	mtspr	SPRN_HSRR1,r12;		\
+	LOAD_REG_ADDR(r11,opal);	\
+	ld	r12,8(r11);		\
+	ld	r2,0(r11);		\
+	mtspr	SPRN_HSRR0,r12;		\
+	hrfid
+
+_STATIC(opal_return)
+	ld	r2,PACATOC(r13);
+	ld	r4,8(r1);
+	ld	r5,16(r1);
+	ld	r6,PACASAVEDMSR(r13);
+	mtspr	SPRN_SRR0,r5;
+	mtspr	SPRN_SRR1,r6;
+	mtcr	r4;
+	rfid
+
+OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
+OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
+OPAL_CALL(opal_console_write_buffer_space,	OPAL_CONSOLE_WRITE_BUFFER_SPACE);
+OPAL_CALL(opal_rtc_read,			OPAL_RTC_READ);
+OPAL_CALL(opal_rtc_write,			OPAL_RTC_WRITE);
+OPAL_CALL(opal_cec_power_down,			OPAL_CEC_POWER_DOWN);
+OPAL_CALL(opal_cec_reboot,			OPAL_CEC_REBOOT);
+OPAL_CALL(opal_read_nvram,			OPAL_READ_NVRAM);
+OPAL_CALL(opal_write_nvram,			OPAL_WRITE_NVRAM);
+OPAL_CALL(opal_handle_interrupt,		OPAL_HANDLE_INTERRUPT);
+OPAL_CALL(opal_poll_events,			OPAL_POLL_EVENTS);
+OPAL_CALL(opal_pci_set_hub_tce_memory,		OPAL_PCI_SET_HUB_TCE_MEMORY);
+OPAL_CALL(opal_pci_set_phb_tce_memory,		OPAL_PCI_SET_PHB_TCE_MEMORY);
+OPAL_CALL(opal_pci_config_read_byte,		OPAL_PCI_CONFIG_READ_BYTE);
+OPAL_CALL(opal_pci_config_read_half_word,	OPAL_PCI_CONFIG_READ_HALF_WORD);
+OPAL_CALL(opal_pci_config_read_word,		OPAL_PCI_CONFIG_READ_WORD);
+OPAL_CALL(opal_pci_config_write_byte,		OPAL_PCI_CONFIG_WRITE_BYTE);
+OPAL_CALL(opal_pci_config_write_half_word,	OPAL_PCI_CONFIG_WRITE_HALF_WORD);
+OPAL_CALL(opal_pci_config_write_word,		OPAL_PCI_CONFIG_WRITE_WORD);
+OPAL_CALL(opal_set_xive,			OPAL_SET_XIVE);
+OPAL_CALL(opal_get_xive,			OPAL_GET_XIVE);
+OPAL_CALL(opal_register_exception_handler,	OPAL_REGISTER_OPAL_EXCEPTION_HANDLER);
+OPAL_CALL(opal_pci_eeh_freeze_status,		OPAL_PCI_EEH_FREEZE_STATUS);
+OPAL_CALL(opal_pci_eeh_freeze_clear,		OPAL_PCI_EEH_FREEZE_CLEAR);
+OPAL_CALL(opal_pci_shpc,			OPAL_PCI_SHPC);
+OPAL_CALL(opal_pci_phb_mmio_enable,		OPAL_PCI_PHB_MMIO_ENABLE);
+OPAL_CALL(opal_pci_set_phb_mem_window,		OPAL_PCI_SET_PHB_MEM_WINDOW);
+OPAL_CALL(opal_pci_map_pe_mmio_window,		OPAL_PCI_MAP_PE_MMIO_WINDOW);
+OPAL_CALL(opal_pci_set_phb_table_memory,	OPAL_PCI_SET_PHB_TABLE_MEMORY);
+OPAL_CALL(opal_pci_set_pe,			OPAL_PCI_SET_PE);
+OPAL_CALL(opal_pci_set_peltv,			OPAL_PCI_SET_PELTV);
+OPAL_CALL(opal_pci_set_mve,			OPAL_PCI_SET_MVE);
+OPAL_CALL(opal_pci_set_mve_enable,		OPAL_PCI_SET_MVE_ENABLE);
+OPAL_CALL(opal_pci_get_xive_reissue,		OPAL_PCI_GET_XIVE_REISSUE);
+OPAL_CALL(opal_pci_set_xive_reissue,		OPAL_PCI_SET_XIVE_REISSUE);
+OPAL_CALL(opal_pci_set_xive_pe,			OPAL_PCI_SET_XIVE_PE);
+OPAL_CALL(opal_get_xive_source,			OPAL_GET_XIVE_SOURCE);
+OPAL_CALL(opal_get_msi_32,			OPAL_GET_MSI_32);
+OPAL_CALL(opal_get_msi_64,			OPAL_GET_MSI_64);
+OPAL_CALL(opal_start_cpu,			OPAL_START_CPU);
+OPAL_CALL(opal_query_cpu_status,		OPAL_QUERY_CPU_STATUS);
+OPAL_CALL(opal_write_oppanel,			OPAL_WRITE_OPPANEL);
+OPAL_CALL(opal_pci_map_pe_dma_window,		OPAL_PCI_MAP_PE_DMA_WINDOW);
+OPAL_CALL(opal_pci_map_pe_dma_window_real,	OPAL_PCI_MAP_PE_DMA_WINDOW_REAL);
+OPAL_CALL(opal_pci_reset,			OPAL_PCI_RESET);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
new file mode 100644
index 000000000000..aaa0dba49471
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -0,0 +1,322 @@
+/*
+ * PowerNV OPAL high level interfaces
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/types.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/interrupt.h>
+#include <asm/opal.h>
+#include <asm/firmware.h>
+
+#include "powernv.h"
+
+struct opal {
+	u64 base;
+	u64 entry;
+} opal;
+
+static struct device_node *opal_node;
+static DEFINE_SPINLOCK(opal_write_lock);
+extern u64 opal_mc_secondary_handler[];
+
+int __init early_init_dt_scan_opal(unsigned long node,
+				   const char *uname, int depth, void *data)
+{
+	const void *basep, *entryp;
+	unsigned long basesz, entrysz;
+	u64 glue;
+
+	if (depth != 1 || strcmp(uname, "ibm,opal") != 0)
+		return 0;
+
+	basep  = of_get_flat_dt_prop(node, "opal-base-address", &basesz);
+	entryp = of_get_flat_dt_prop(node, "opal-entry-address", &entrysz);
+
+	if (!basep || !entryp)
+		return 1;
+
+	opal.base = of_read_number(basep, basesz/4);
+	opal.entry = of_read_number(entryp, entrysz/4);
+
+	pr_debug("OPAL Base  = 0x%llx (basep=%p basesz=%ld)\n",
+		 opal.base, basep, basesz);
+	pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%ld)\n",
+		 opal.entry, entryp, entrysz);
+
+	powerpc_firmware_features |= FW_FEATURE_OPAL;
+	if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
+		powerpc_firmware_features |= FW_FEATURE_OPALv2;
+		printk("OPAL V2 detected !\n");
+	} else {
+		printk("OPAL V1 detected !\n");
+	}
+
+	/* Hookup some exception handlers. We use the fwnmi area at 0x7000
+	 * to provide the glue space to OPAL
+	 */
+	glue = 0x7000;
+	opal_register_exception_handler(OPAL_MACHINE_CHECK_HANDLER,
+					__pa(opal_mc_secondary_handler[0]),
+					glue);
+	glue += 128;
+	opal_register_exception_handler(OPAL_HYPERVISOR_MAINTENANCE_HANDLER,
+					0, glue);
+	glue += 128;
+	opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue);
+
+	return 1;
+}
+
+int opal_get_chars(uint32_t vtermno, char *buf, int count)
+{
+	s64 len, rc;
+	u64 evt;
+
+	if (!opal.entry)
+		return -ENODEV;
+	opal_poll_events(&evt);
+	if ((evt & OPAL_EVENT_CONSOLE_INPUT) == 0)
+		return 0;
+	len = count;
+	rc = opal_console_read(vtermno, &len, buf);
+	if (rc == OPAL_SUCCESS)
+		return len;
+	return 0;
+}
+
+int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
+{
+	int written = 0;
+	s64 len, rc;
+	unsigned long flags;
+	u64 evt;
+
+	if (!opal.entry)
+		return -ENODEV;
+
+	/* We want put_chars to be atomic to avoid mangling of hvsi
+	 * packets. To do that, we first test for room and return
+	 * -EAGAIN if there isn't enough.
+	 *
+	 * Unfortunately, opal_console_write_buffer_space() doesn't
+	 * appear to work on opal v1, so we just assume there is
+	 * enough room and be done with it
+	 */
+	spin_lock_irqsave(&opal_write_lock, flags);
+	if (firmware_has_feature(FW_FEATURE_OPALv2)) {
+		rc = opal_console_write_buffer_space(vtermno, &len);
+		if (rc || len < total_len) {
+			spin_unlock_irqrestore(&opal_write_lock, flags);
+			/* Closed -> drop characters */
+			if (rc)
+				return total_len;
+			opal_poll_events(&evt);
+			return -EAGAIN;
+		}
+	}
+
+	/* We still try to handle partial completions, though they
+	 * should no longer happen.
+	 */
+	rc = OPAL_BUSY;
+	while(total_len > 0 && (rc == OPAL_BUSY ||
+				rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) {
+		len = total_len;
+		rc = opal_console_write(vtermno, &len, data);
+		if (rc == OPAL_SUCCESS) {
+			total_len -= len;
+			data += len;
+			written += len;
+		}
+		/* This is a bit nasty but we need that for the console to
+		 * flush when there aren't any interrupts. We will clean
+		 * things a bit later to limit that to synchronous path
+		 * such as the kernel console and xmon/udbg
+		 */
+		do
+			opal_poll_events(&evt);
+		while(rc == OPAL_SUCCESS && (evt & OPAL_EVENT_CONSOLE_OUTPUT));
+	}
+	spin_unlock_irqrestore(&opal_write_lock, flags);
+	return written;
+}
+
+int opal_machine_check(struct pt_regs *regs)
+{
+	struct opal_machine_check_event *opal_evt = get_paca()->opal_mc_evt;
+	struct opal_machine_check_event evt;
+	const char *level, *sevstr, *subtype;
+	static const char *opal_mc_ue_types[] = {
+		"Indeterminate",
+		"Instruction fetch",
+		"Page table walk ifetch",
+		"Load/Store",
+		"Page table walk Load/Store",
+	};
+	static const char *opal_mc_slb_types[] = {
+		"Indeterminate",
+		"Parity",
+		"Multihit",
+	};
+	static const char *opal_mc_erat_types[] = {
+		"Indeterminate",
+		"Parity",
+		"Multihit",
+	};
+	static const char *opal_mc_tlb_types[] = {
+		"Indeterminate",
+		"Parity",
+		"Multihit",
+	};
+
+	/* Copy the event structure and release the original */
+	evt = *opal_evt;
+	opal_evt->in_use = 0;
+
+	/* Print things out */
+	if (evt.version != OpalMCE_V1) {
+		pr_err("Machine Check Exception, Unknown event version %d !\n",
+		       evt.version);
+		return 0;
+	}
+	switch(evt.severity) {
+	case OpalMCE_SEV_NO_ERROR:
+		level = KERN_INFO;
+		sevstr = "Harmless";
+		break;
+	case OpalMCE_SEV_WARNING:
+		level = KERN_WARNING;
+		sevstr = "";
+		break;
+	case OpalMCE_SEV_ERROR_SYNC:
+		level = KERN_ERR;
+		sevstr = "Severe";
+		break;
+	case OpalMCE_SEV_FATAL:
+	default:
+		level = KERN_ERR;
+		sevstr = "Fatal";
+		break;
+	}
+
+	printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
+	       evt.disposition == OpalMCE_DISPOSITION_RECOVERED ?
+	       "Recovered" : "[Not recovered");
+	printk("%s  Initiator: %s\n", level,
+	       evt.initiator == OpalMCE_INITIATOR_CPU ? "CPU" : "Unknown");
+	switch(evt.error_type) {
+	case OpalMCE_ERROR_TYPE_UE:
+		subtype = evt.u.ue_error.ue_error_type <
+			ARRAY_SIZE(opal_mc_ue_types) ?
+			opal_mc_ue_types[evt.u.ue_error.ue_error_type]
+			: "Unknown";
+		printk("%s  Error type: UE [%s]\n", level, subtype);
+		if (evt.u.ue_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt.u.ue_error.effective_address);
+		if (evt.u.ue_error.physical_address_provided)
+			printk("%s      Physial address: %016llx\n",
+			       level, evt.u.ue_error.physical_address);
+		break;
+	case OpalMCE_ERROR_TYPE_SLB:
+		subtype = evt.u.slb_error.slb_error_type <
+			ARRAY_SIZE(opal_mc_slb_types) ?
+			opal_mc_slb_types[evt.u.slb_error.slb_error_type]
+			: "Unknown";
+		printk("%s  Error type: SLB [%s]\n", level, subtype);
+		if (evt.u.slb_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt.u.slb_error.effective_address);
+		break;
+	case OpalMCE_ERROR_TYPE_ERAT:
+		subtype = evt.u.erat_error.erat_error_type <
+			ARRAY_SIZE(opal_mc_erat_types) ?
+			opal_mc_erat_types[evt.u.erat_error.erat_error_type]
+			: "Unknown";
+		printk("%s  Error type: ERAT [%s]\n", level, subtype);
+		if (evt.u.erat_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt.u.erat_error.effective_address);
+		break;
+	case OpalMCE_ERROR_TYPE_TLB:
+		subtype = evt.u.tlb_error.tlb_error_type <
+			ARRAY_SIZE(opal_mc_tlb_types) ?
+			opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type]
+			: "Unknown";
+		printk("%s  Error type: TLB [%s]\n", level, subtype);
+		if (evt.u.tlb_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt.u.tlb_error.effective_address);
+		break;
+	default:
+	case OpalMCE_ERROR_TYPE_UNKNOWN:
+		printk("%s  Error type: Unknown\n", level);
+		break;
+	}
+	return evt.severity == OpalMCE_SEV_FATAL ? 0 : 1;
+}
+
+static irqreturn_t opal_interrupt(int irq, void *data)
+{
+	uint64_t events;
+
+	opal_handle_interrupt(virq_to_hw(irq), &events);
+
+	/* XXX TODO: Do something with the events */
+
+	return IRQ_HANDLED;
+}
+
+static int __init opal_init(void)
+{
+	struct device_node *np, *consoles;
+	const u32 *irqs;
+	int rc, i, irqlen;
+
+	opal_node = of_find_node_by_path("/ibm,opal");
+	if (!opal_node) {
+		pr_warn("opal: Node not found\n");
+		return -ENODEV;
+	}
+	if (firmware_has_feature(FW_FEATURE_OPALv2))
+		consoles = of_find_node_by_path("/ibm,opal/consoles");
+	else
+		consoles = of_node_get(opal_node);
+
+	/* Register serial ports */
+	for_each_child_of_node(consoles, np) {
+		if (strcmp(np->name, "serial"))
+			continue;
+		of_platform_device_create(np, NULL, NULL);
+	}
+	of_node_put(consoles);
+
+	/* Find all OPAL interrupts and request them */
+	irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
+	pr_debug("opal: Found %d interrupts reserved for OPAL\n",
+		 irqs ? (irqlen / 4) : 0);
+	for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) {
+		unsigned int hwirq = be32_to_cpup(irqs);
+		unsigned int irq = irq_create_mapping(NULL, hwirq);
+		if (irq == NO_IRQ) {
+			pr_warning("opal: Failed to map irq 0x%x\n", hwirq);
+			continue;
+		}
+		rc = request_irq(irq, opal_interrupt, 0, "opal", NULL);
+		if (rc)
+			pr_warning("opal: Error %d requesting irq %d"
+				   " (0x%x)\n", rc, irq, hwirq);
+	}
+	return 0;
+}
+subsys_initcall(opal_init);
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
new file mode 100644
index 000000000000..4c80f7c77d56
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -0,0 +1,234 @@
+/*
+ * Support PCI/PCIe on PowerNV platforms
+ *
+ * Currently supports only P5IOC2
+ *
+ * Copyright 2011 Benjamin Herrenschmidt, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/msi.h>
+
+#include <asm/sections.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/opal.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+#include <asm/abs_addr.h>
+
+#include "powernv.h"
+#include "pci.h"
+
+/* For now, use a fixed amount of TCE memory for each p5ioc2
+ * hub, 16M will do
+ */
+#define P5IOC2_TCE_MEMORY	0x01000000
+
+#ifdef CONFIG_PCI_MSI
+static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
+				    unsigned int hwirq, unsigned int is_64,
+				    struct msi_msg *msg)
+{
+	if (WARN_ON(!is_64))
+		return -ENXIO;
+	msg->data = hwirq - phb->msi_base;
+	msg->address_hi = 0x10000000;
+	msg->address_lo = 0;
+
+	return 0;
+}
+
+static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb)
+{
+	unsigned int bmap_size;
+	const __be32 *prop = of_get_property(phb->hose->dn,
+					     "ibm,opal-msi-ranges", NULL);
+	if (!prop)
+		return;
+
+	/* Don't do MSI's on p5ioc2 PCI-X are they are not properly
+	 * verified in HW
+	 */
+	if (of_device_is_compatible(phb->hose->dn, "ibm,p5ioc2-pcix"))
+		return;
+	phb->msi_base = be32_to_cpup(prop);
+	phb->msi_count = be32_to_cpup(prop + 1);
+	bmap_size = BITS_TO_LONGS(phb->msi_count) * sizeof(unsigned long);
+	phb->msi_map = zalloc_maybe_bootmem(bmap_size, GFP_KERNEL);
+	if (!phb->msi_map) {
+		pr_err("PCI %d: Failed to allocate MSI bitmap !\n",
+		       phb->hose->global_number);
+		return;
+	}
+	phb->msi_setup = pnv_pci_p5ioc2_msi_setup;
+	phb->msi32_support = 0;
+	pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n",
+		phb->msi_count, phb->msi_base);
+}
+#else
+static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { }
+#endif /* CONFIG_PCI_MSI */
+
+static void __devinit pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
+						   struct pci_dev *pdev)
+{
+	if (phb->p5ioc2.iommu_table.it_map == NULL)
+		iommu_init_table(&phb->p5ioc2.iommu_table, phb->hose->node);
+
+	set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table);
+}
+
+static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np,
+					   void *tce_mem, u64 tce_size)
+{
+	struct pnv_phb *phb;
+	const u64 *prop64;
+	u64 phb_id;
+	int64_t rc;
+	static int primary = 1;
+
+	pr_info(" Initializing p5ioc2 PHB %s\n", np->full_name);
+
+	prop64 = of_get_property(np, "ibm,opal-phbid", NULL);
+	if (!prop64) {
+		pr_err("  Missing \"ibm,opal-phbid\" property !\n");
+		return;
+	}
+	phb_id = be64_to_cpup(prop64);
+	pr_devel("  PHB-ID  : 0x%016llx\n", phb_id);
+	pr_devel("  TCE AT  : 0x%016lx\n", __pa(tce_mem));
+	pr_devel("  TCE SZ  : 0x%016llx\n", tce_size);
+
+	rc = opal_pci_set_phb_tce_memory(phb_id, __pa(tce_mem), tce_size);
+	if (rc != OPAL_SUCCESS) {
+		pr_err("  Failed to set TCE memory, OPAL error %lld\n", rc);
+		return;
+	}
+
+	phb = alloc_bootmem(sizeof(struct pnv_phb));
+	if (phb) {
+		memset(phb, 0, sizeof(struct pnv_phb));
+		phb->hose = pcibios_alloc_controller(np);
+	}
+	if (!phb || !phb->hose) {
+		pr_err("  Failed to allocate PCI controller\n");
+		return;
+	}
+
+	spin_lock_init(&phb->lock);
+	phb->hose->first_busno = 0;
+	phb->hose->last_busno = 0xff;
+	phb->hose->private_data = phb;
+	phb->opal_id = phb_id;
+	phb->type = PNV_PHB_P5IOC2;
+
+	phb->regs = of_iomap(np, 0);
+
+	if (phb->regs == NULL)
+		pr_err("  Failed to map registers !\n");
+	else {
+		pr_devel("  P_BUID     = 0x%08x\n", in_be32(phb->regs + 0x100));
+		pr_devel("  P_IOSZ     = 0x%08x\n", in_be32(phb->regs + 0x1b0));
+		pr_devel("  P_IO_ST    = 0x%08x\n", in_be32(phb->regs + 0x1e0));
+		pr_devel("  P_MEM1_H   = 0x%08x\n", in_be32(phb->regs + 0x1a0));
+		pr_devel("  P_MEM1_L   = 0x%08x\n", in_be32(phb->regs + 0x190));
+		pr_devel("  P_MSZ1_L   = 0x%08x\n", in_be32(phb->regs + 0x1c0));
+		pr_devel("  P_MEM_ST   = 0x%08x\n", in_be32(phb->regs + 0x1d0));
+		pr_devel("  P_MEM2_H   = 0x%08x\n", in_be32(phb->regs + 0x2c0));
+		pr_devel("  P_MEM2_L   = 0x%08x\n", in_be32(phb->regs + 0x2b0));
+		pr_devel("  P_MSZ2_H   = 0x%08x\n", in_be32(phb->regs + 0x2d0));
+		pr_devel("  P_MSZ2_L   = 0x%08x\n", in_be32(phb->regs + 0x2e0));
+	}
+
+	/* Interpret the "ranges" property */
+	/* This also maps the I/O region and sets isa_io/mem_base */
+	pci_process_bridge_OF_ranges(phb->hose, np, primary);
+	primary = 0;
+
+	phb->hose->ops = &pnv_pci_ops;
+
+	/* Setup MSI support */
+	pnv_pci_init_p5ioc2_msis(phb);
+
+	/* Setup TCEs */
+	phb->dma_dev_setup = pnv_pci_p5ioc2_dma_dev_setup;
+	pnv_pci_setup_iommu_table(&phb->p5ioc2.iommu_table,
+				  tce_mem, tce_size, 0);
+}
+
+void __init pnv_pci_init_p5ioc2_hub(struct device_node *np)
+{
+	struct device_node *phbn;
+	const u64 *prop64;
+	u64 hub_id;
+	void *tce_mem;
+	uint64_t tce_per_phb;
+	int64_t rc;
+	int phb_count = 0;
+
+	pr_info("Probing p5ioc2 IO-Hub %s\n", np->full_name);
+
+	prop64 = of_get_property(np, "ibm,opal-hubid", NULL);
+	if (!prop64) {
+		pr_err(" Missing \"ibm,opal-hubid\" property !\n");
+		return;
+	}
+	hub_id = be64_to_cpup(prop64);
+	pr_info(" HUB-ID : 0x%016llx\n", hub_id);
+
+	/* Currently allocate 16M of TCE memory for every Hub
+	 *
+	 * XXX TODO: Make it chip local if possible
+	 */
+	tce_mem = __alloc_bootmem(P5IOC2_TCE_MEMORY, P5IOC2_TCE_MEMORY,
+				  __pa(MAX_DMA_ADDRESS));
+	if (!tce_mem) {
+		pr_err(" Failed to allocate TCE Memory !\n");
+		return;
+	}
+	pr_debug(" TCE    : 0x%016lx..0x%016lx\n",
+		__pa(tce_mem), __pa(tce_mem) + P5IOC2_TCE_MEMORY - 1);
+	rc = opal_pci_set_hub_tce_memory(hub_id, __pa(tce_mem),
+					P5IOC2_TCE_MEMORY);
+	if (rc != OPAL_SUCCESS) {
+		pr_err(" Failed to allocate TCE memory, OPAL error %lld\n", rc);
+		return;
+	}
+
+	/* Count child PHBs */
+	for_each_child_of_node(np, phbn) {
+		if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
+		    of_device_is_compatible(phbn, "ibm,p5ioc2-pciex"))
+			phb_count++;
+	}
+
+	/* Calculate how much TCE space we can give per PHB */
+	tce_per_phb = __rounddown_pow_of_two(P5IOC2_TCE_MEMORY / phb_count);
+	pr_info(" Allocating %lld MB of TCE memory per PHB\n",
+		tce_per_phb >> 20);
+
+	/* Initialize PHBs */
+	for_each_child_of_node(np, phbn) {
+		if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
+		    of_device_is_compatible(phbn, "ibm,p5ioc2-pciex")) {
+			pnv_pci_init_p5ioc2_phb(phbn, tce_mem, tce_per_phb);
+			tce_mem += tce_per_phb;
+		}
+	}
+}
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
new file mode 100644
index 000000000000..85bb66d7f933
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -0,0 +1,427 @@
+/*
+ * Support PCI/PCIe on PowerNV platforms
+ *
+ * Currently supports only P5IOC2
+ *
+ * Copyright 2011 Benjamin Herrenschmidt, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/msi.h>
+
+#include <asm/sections.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/opal.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+#include <asm/abs_addr.h>
+
+#include "powernv.h"
+#include "pci.h"
+
+/* Delay in usec */
+#define PCI_RESET_DELAY_US	3000000
+
+#define cfg_dbg(fmt...)	do { } while(0)
+//#define cfg_dbg(fmt...)	printk(fmt)
+
+#ifdef CONFIG_PCI_MSI
+static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	return (phb && phb->msi_map) ? 0 : -ENODEV;
+}
+
+static unsigned int pnv_get_one_msi(struct pnv_phb *phb)
+{
+	unsigned int id;
+
+	spin_lock(&phb->lock);
+	id = find_next_zero_bit(phb->msi_map, phb->msi_count, phb->msi_next);
+	if (id >= phb->msi_count && phb->msi_next)
+		id = find_next_zero_bit(phb->msi_map, phb->msi_count, 0);
+	if (id >= phb->msi_count) {
+		spin_unlock(&phb->lock);
+		return 0;
+	}
+	__set_bit(id, phb->msi_map);
+	spin_unlock(&phb->lock);
+	return id + phb->msi_base;
+}
+
+static void pnv_put_msi(struct pnv_phb *phb, unsigned int hwirq)
+{
+	unsigned int id;
+
+	if (WARN_ON(hwirq < phb->msi_base ||
+		    hwirq >= (phb->msi_base + phb->msi_count)))
+		return;
+	id = hwirq - phb->msi_base;
+	spin_lock(&phb->lock);
+	__clear_bit(id, phb->msi_map);
+	spin_unlock(&phb->lock);
+}
+
+static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct msi_desc *entry;
+	struct msi_msg msg;
+	unsigned int hwirq, virq;
+	int rc;
+
+	if (WARN_ON(!phb))
+		return -ENODEV;
+
+	list_for_each_entry(entry, &pdev->msi_list, list) {
+		if (!entry->msi_attrib.is_64 && !phb->msi32_support) {
+			pr_warn("%s: Supports only 64-bit MSIs\n",
+				pci_name(pdev));
+			return -ENXIO;
+		}
+		hwirq = pnv_get_one_msi(phb);
+		if (!hwirq) {
+			pr_warn("%s: Failed to find a free MSI\n",
+				pci_name(pdev));
+			return -ENOSPC;
+		}
+		virq = irq_create_mapping(NULL, hwirq);
+		if (virq == NO_IRQ) {
+			pr_warn("%s: Failed to map MSI to linux irq\n",
+				pci_name(pdev));
+			pnv_put_msi(phb, hwirq);
+			return -ENOMEM;
+		}
+		rc = phb->msi_setup(phb, pdev, hwirq, entry->msi_attrib.is_64,
+				    &msg);
+		if (rc) {
+			pr_warn("%s: Failed to setup MSI\n", pci_name(pdev));
+			irq_dispose_mapping(virq);
+			pnv_put_msi(phb, hwirq);
+			return rc;
+		}
+		irq_set_msi_desc(virq, entry);
+		write_msi_msg(virq, &msg);
+	}
+	return 0;
+}
+
+static void pnv_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct msi_desc *entry;
+
+	if (WARN_ON(!phb))
+		return;
+
+	list_for_each_entry(entry, &pdev->msi_list, list) {
+		if (entry->irq == NO_IRQ)
+			continue;
+		irq_set_msi_desc(entry->irq, NULL);
+		pnv_put_msi(phb, virq_to_hw(entry->irq));
+		irq_dispose_mapping(entry->irq);
+	}
+}
+#endif /* CONFIG_PCI_MSI */
+
+static void pnv_pci_config_check_eeh(struct pnv_phb *phb, struct pci_bus *bus,
+				     u32 bdfn)
+{
+	s64	rc;
+	u8	fstate;
+	u16	pcierr;
+	u32	pe_no;
+
+	/* Get PE# if we support IODA */
+	pe_no = phb->bdfn_to_pe ? phb->bdfn_to_pe(phb, bus, bdfn & 0xff) : 0;
+
+	/* Read freeze status */
+	rc = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, &fstate, &pcierr,
+					NULL);
+	if (rc) {
+		pr_warning("PCI %d: Failed to read EEH status for PE#%d,"
+			   " err %lld\n", phb->hose->global_number, pe_no, rc);
+		return;
+	}
+	cfg_dbg(" -> EEH check, bdfn=%04x PE%d fstate=%x\n",
+		bdfn, pe_no, fstate);
+	if (fstate != 0) {
+		rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no,
+					      OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+		if (rc) {
+			pr_warning("PCI %d: Failed to clear EEH freeze state"
+				   " for PE#%d, err %lld\n",
+				   phb->hose->global_number, pe_no, rc);
+		}
+	}
+}
+
+static int pnv_pci_read_config(struct pci_bus *bus,
+			       unsigned int devfn,
+			       int where, int size, u32 *val)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
+	u32 bdfn = (((uint64_t)bus->number) << 8) | devfn;
+	s64 rc;
+
+	if (hose == NULL)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	switch (size) {
+	case 1: {
+		u8 v8;
+		rc = opal_pci_config_read_byte(phb->opal_id, bdfn, where, &v8);
+		*val = (rc == OPAL_SUCCESS) ? v8 : 0xff;
+		break;
+	}
+	case 2: {
+		u16 v16;
+		rc = opal_pci_config_read_half_word(phb->opal_id, bdfn, where,
+						   &v16);
+		*val = (rc == OPAL_SUCCESS) ? v16 : 0xffff;
+		break;
+	}
+	case 4: {
+		u32 v32;
+		rc = opal_pci_config_read_word(phb->opal_id, bdfn, where, &v32);
+		*val = (rc == OPAL_SUCCESS) ? v32 : 0xffffffff;
+		break;
+	}
+	default:
+		return PCIBIOS_FUNC_NOT_SUPPORTED;
+	}
+	cfg_dbg("pnv_pci_read_config bus: %x devfn: %x +%x/%x -> %08x\n",
+		bus->number, devfn, where, size, *val);
+
+	/* Check if the PHB got frozen due to an error (no response) */
+	pnv_pci_config_check_eeh(phb, bus, bdfn);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int pnv_pci_write_config(struct pci_bus *bus,
+				unsigned int devfn,
+				int where, int size, u32 val)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
+	u32 bdfn = (((uint64_t)bus->number) << 8) | devfn;
+
+	if (hose == NULL)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	cfg_dbg("pnv_pci_write_config bus: %x devfn: %x +%x/%x -> %08x\n",
+		bus->number, devfn, where, size, val);
+	switch (size) {
+	case 1:
+		opal_pci_config_write_byte(phb->opal_id, bdfn, where, val);
+		break;
+	case 2:
+		opal_pci_config_write_half_word(phb->opal_id, bdfn, where, val);
+		break;
+	case 4:
+		opal_pci_config_write_word(phb->opal_id, bdfn, where, val);
+		break;
+	default:
+		return PCIBIOS_FUNC_NOT_SUPPORTED;
+	}
+	/* Check if the PHB got frozen due to an error (no response) */
+	pnv_pci_config_check_eeh(phb, bus, bdfn);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+struct pci_ops pnv_pci_ops = {
+	.read = pnv_pci_read_config,
+	.write = pnv_pci_write_config,
+};
+
+static int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
+			 unsigned long uaddr, enum dma_data_direction direction,
+			 struct dma_attrs *attrs)
+{
+	u64 proto_tce;
+	u64 *tcep;
+	u64 rpn;
+
+	proto_tce = TCE_PCI_READ; // Read allowed
+
+	if (direction != DMA_TO_DEVICE)
+		proto_tce |= TCE_PCI_WRITE;
+
+	tcep = ((u64 *)tbl->it_base) + index;
+
+	while (npages--) {
+		/* can't move this out since we might cross LMB boundary */
+		rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
+		*tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
+
+		uaddr += TCE_PAGE_SIZE;
+		tcep++;
+	}
+	return 0;
+}
+
+static void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
+{
+	u64 *tcep = ((u64 *)tbl->it_base) + index;
+
+	while (npages--)
+		*(tcep++) = 0;
+}
+
+void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
+			       void *tce_mem, u64 tce_size,
+			       u64 dma_offset)
+{
+	tbl->it_blocksize = 16;
+	tbl->it_base = (unsigned long)tce_mem;
+	tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT;
+	tbl->it_index = 0;
+	tbl->it_size = tce_size >> 3;
+	tbl->it_busno = 0;
+	tbl->it_type = TCE_PCI;
+}
+
+static struct iommu_table * __devinit
+pnv_pci_setup_bml_iommu(struct pci_controller *hose)
+{
+	struct iommu_table *tbl;
+	const __be64 *basep;
+	const __be32 *sizep;
+
+	basep = of_get_property(hose->dn, "linux,tce-base", NULL);
+	sizep = of_get_property(hose->dn, "linux,tce-size", NULL);
+	if (basep == NULL || sizep == NULL) {
+		pr_err("PCI: %s has missing tce entries !\n", hose->dn->full_name);
+		return NULL;
+	}
+	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, hose->node);
+	if (WARN_ON(!tbl))
+		return NULL;
+	pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)),
+				  be32_to_cpup(sizep), 0);
+	iommu_init_table(tbl, hose->node);
+	return tbl;
+}
+
+static void __devinit pnv_pci_dma_fallback_setup(struct pci_controller *hose,
+						 struct pci_dev *pdev)
+{
+	struct device_node *np = pci_bus_to_OF_node(hose->bus);
+	struct pci_dn *pdn;
+
+	if (np == NULL)
+		return;
+	pdn = PCI_DN(np);
+	if (!pdn->iommu_table)
+		pdn->iommu_table = pnv_pci_setup_bml_iommu(hose);
+	if (!pdn->iommu_table)
+		return;
+	set_iommu_table_base(&pdev->dev, pdn->iommu_table);
+}
+
+static void __devinit pnv_pci_dma_dev_setup(struct pci_dev *pdev)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	/* If we have no phb structure, try to setup a fallback based on
+	 * the device-tree (RTAS PCI for example)
+	 */
+	if (phb && phb->dma_dev_setup)
+		phb->dma_dev_setup(phb, pdev);
+	else
+		pnv_pci_dma_fallback_setup(hose, pdev);
+}
+
+static int pnv_pci_probe_mode(struct pci_bus *bus)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	const __be64 *tstamp;
+	u64 now, target;
+
+
+	/* We hijack this as a way to ensure we have waited long
+	 * enough since the reset was lifted on the PCI bus
+	 */
+	if (bus != hose->bus)
+		return PCI_PROBE_NORMAL;
+	tstamp = of_get_property(hose->dn, "reset-clear-timestamp", NULL);
+	if (!tstamp || !*tstamp)
+		return PCI_PROBE_NORMAL;
+
+	now = mftb() / tb_ticks_per_usec;
+	target = (be64_to_cpup(tstamp) / tb_ticks_per_usec)
+		+ PCI_RESET_DELAY_US;
+
+	pr_devel("pci %04d: Reset target: 0x%llx now: 0x%llx\n",
+		 hose->global_number, target, now);
+
+	if (now < target)
+		msleep((target - now + 999) / 1000);
+
+	return PCI_PROBE_NORMAL;
+}
+
+void __init pnv_pci_init(void)
+{
+	struct device_node *np;
+
+	pci_set_flags(PCI_CAN_SKIP_ISA_ALIGN);
+
+	/* We do not want to just probe */
+	pci_probe_only = 0;
+
+	/* OPAL absent, try POPAL first then RTAS detection of PHBs */
+	if (!firmware_has_feature(FW_FEATURE_OPAL)) {
+#ifdef CONFIG_PPC_POWERNV_RTAS
+		init_pci_config_tokens();
+		find_and_init_phbs();
+#endif /* CONFIG_PPC_POWERNV_RTAS */
+	} else {
+		/* OPAL is here, do our normal stuff */
+
+		/* Look for p5ioc2 IO-Hubs */
+		for_each_compatible_node(np, NULL, "ibm,p5ioc2")
+			pnv_pci_init_p5ioc2_hub(np);
+	}
+
+	/* Setup the linkage between OF nodes and PHBs */
+	pci_devs_phb_init();
+
+	/* Configure IOMMU DMA hooks */
+	ppc_md.pci_dma_dev_setup = pnv_pci_dma_dev_setup;
+	ppc_md.tce_build = pnv_tce_build;
+	ppc_md.tce_free = pnv_tce_free;
+	ppc_md.pci_probe_mode = pnv_pci_probe_mode;
+	set_pci_dma_ops(&dma_iommu_ops);
+
+	/* Configure MSIs */
+#ifdef CONFIG_PCI_MSI
+	ppc_md.msi_check_device = pnv_msi_check_device;
+	ppc_md.setup_msi_irqs = pnv_setup_msi_irqs;
+	ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs;
+#endif
+}
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
new file mode 100644
index 000000000000..d4dbc4950936
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -0,0 +1,48 @@
+#ifndef __POWERNV_PCI_H
+#define __POWERNV_PCI_H
+
+struct pci_dn;
+
+enum pnv_phb_type {
+	PNV_PHB_P5IOC2,
+	PNV_PHB_IODA1,
+	PNV_PHB_IODA2,
+};
+
+struct pnv_phb {
+	struct pci_controller	*hose;
+	enum pnv_phb_type	type;
+	u64			opal_id;
+	void __iomem		*regs;
+	spinlock_t		lock;
+
+#ifdef CONFIG_PCI_MSI
+	unsigned long		*msi_map;
+	unsigned int		msi_base;
+	unsigned int		msi_count;
+	unsigned int		msi_next;
+	unsigned int		msi32_support;
+#endif
+	int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev,
+			 unsigned int hwirq, unsigned int is_64,
+			 struct msi_msg *msg);
+	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
+	void (*fixup_phb)(struct pci_controller *hose);
+	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
+
+	union {
+		struct {
+			struct iommu_table iommu_table;
+		} p5ioc2;
+	};
+};
+
+extern struct pci_ops pnv_pci_ops;
+
+extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
+				      void *tce_mem, u64 tce_size,
+				      u64 dma_offset);
+extern void pnv_pci_init_p5ioc2_hub(struct device_node *np);
+
+
+#endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
new file mode 100644
index 000000000000..8a9df7f9667e
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -0,0 +1,16 @@
+#ifndef _POWERNV_H
+#define _POWERNV_H
+
+#ifdef CONFIG_SMP
+extern void pnv_smp_init(void);
+#else
+static inline void pnv_smp_init(void) { }
+#endif
+
+#ifdef CONFIG_PCI
+extern void pnv_pci_init(void);
+#else
+static inline void pnv_pci_init(void) { }
+#endif
+
+#endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
new file mode 100644
index 000000000000..467bd4ac6824
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -0,0 +1,196 @@
+/*
+ * PowerNV setup code.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/cpu.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/tty.h>
+#include <linux/reboot.h>
+#include <linux/init.h>
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/seq_file.h>
+#include <linux/of.h>
+#include <linux/interrupt.h>
+#include <linux/bug.h>
+
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+#include <asm/xics.h>
+#include <asm/rtas.h>
+#include <asm/opal.h>
+#include <asm/xics.h>
+
+#include "powernv.h"
+
+static void __init pnv_setup_arch(void)
+{
+	/* Initialize SMP */
+	pnv_smp_init();
+
+	/* Setup PCI */
+	pnv_pci_init();
+
+	/* Setup RTC and NVRAM callbacks */
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		opal_nvram_init();
+
+	/* Enable NAP mode */
+	powersave_nap = 1;
+
+	/* XXX PMCS */
+}
+
+static void __init pnv_init_early(void)
+{
+#ifdef CONFIG_HVC_OPAL
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		hvc_opal_init_early();
+	else
+#endif
+		add_preferred_console("hvc", 0, NULL);
+}
+
+static void __init pnv_init_IRQ(void)
+{
+	xics_init();
+
+	WARN_ON(!ppc_md.get_irq);
+}
+
+static void pnv_show_cpuinfo(struct seq_file *m)
+{
+	struct device_node *root;
+	const char *model = "";
+
+	root = of_find_node_by_path("/");
+	if (root)
+		model = of_get_property(root, "model", NULL);
+	seq_printf(m, "machine\t\t: PowerNV %s\n", model);
+	if (firmware_has_feature(FW_FEATURE_OPALv2))
+		seq_printf(m, "firmware\t: OPAL v2\n");
+	else if (firmware_has_feature(FW_FEATURE_OPAL))
+		seq_printf(m, "firmware\t: OPAL v1\n");
+	else
+		seq_printf(m, "firmware\t: BML\n");
+	of_node_put(root);
+}
+
+static void  __noreturn pnv_restart(char *cmd)
+{
+	long rc = OPAL_BUSY;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_cec_reboot();
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
+	for (;;)
+		opal_poll_events(NULL);
+}
+
+static void __noreturn pnv_power_off(void)
+{
+	long rc = OPAL_BUSY;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_cec_power_down(0);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
+	for (;;)
+		opal_poll_events(NULL);
+}
+
+static void __noreturn pnv_halt(void)
+{
+	pnv_power_off();
+}
+
+static void pnv_progress(char *s, unsigned short hex)
+{
+}
+
+#ifdef CONFIG_KEXEC
+static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
+{
+	xics_kexec_teardown_cpu(secondary);
+}
+#endif /* CONFIG_KEXEC */
+
+static void __init pnv_setup_machdep_opal(void)
+{
+	ppc_md.get_boot_time = opal_get_boot_time;
+	ppc_md.get_rtc_time = opal_get_rtc_time;
+	ppc_md.set_rtc_time = opal_set_rtc_time;
+	ppc_md.restart = pnv_restart;
+	ppc_md.power_off = pnv_power_off;
+	ppc_md.halt = pnv_halt;
+	ppc_md.machine_check_exception = opal_machine_check;
+}
+
+#ifdef CONFIG_PPC_POWERNV_RTAS
+static void __init pnv_setup_machdep_rtas(void)
+{
+	if (rtas_token("get-time-of-day") != RTAS_UNKNOWN_SERVICE) {
+		ppc_md.get_boot_time = rtas_get_boot_time;
+		ppc_md.get_rtc_time = rtas_get_rtc_time;
+		ppc_md.set_rtc_time = rtas_set_rtc_time;
+	}
+	ppc_md.restart = rtas_restart;
+	ppc_md.power_off = rtas_power_off;
+	ppc_md.halt = rtas_halt;
+}
+#endif /* CONFIG_PPC_POWERNV_RTAS */
+
+static int __init pnv_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	if (!of_flat_dt_is_compatible(root, "ibm,powernv"))
+		return 0;
+
+	hpte_init_native();
+
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		pnv_setup_machdep_opal();
+#ifdef CONFIG_PPC_POWERNV_RTAS
+	else if (rtas.base)
+		pnv_setup_machdep_rtas();
+#endif /* CONFIG_PPC_POWERNV_RTAS */
+
+	pr_debug("PowerNV detected !\n");
+
+	return 1;
+}
+
+define_machine(powernv) {
+	.name			= "PowerNV",
+	.probe			= pnv_probe,
+	.init_early		= pnv_init_early,
+	.setup_arch		= pnv_setup_arch,
+	.init_IRQ		= pnv_init_IRQ,
+	.show_cpuinfo		= pnv_show_cpuinfo,
+	.progress		= pnv_progress,
+	.power_save             = power7_idle,
+	.calibrate_decr		= generic_calibrate_decr,
+#ifdef CONFIG_KEXEC
+	.kexec_cpu_down		= pnv_kexec_cpu_down,
+#endif
+};
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
new file mode 100644
index 000000000000..e87736685243
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -0,0 +1,182 @@
+/*
+ * SMP support for PowerNV machines.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/cpu.h>
+
+#include <asm/irq.h>
+#include <asm/smp.h>
+#include <asm/paca.h>
+#include <asm/machdep.h>
+#include <asm/cputable.h>
+#include <asm/firmware.h>
+#include <asm/system.h>
+#include <asm/rtas.h>
+#include <asm/vdso_datapage.h>
+#include <asm/cputhreads.h>
+#include <asm/xics.h>
+#include <asm/opal.h>
+
+#include "powernv.h"
+
+#ifdef DEBUG
+#include <asm/udbg.h>
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+static void __cpuinit pnv_smp_setup_cpu(int cpu)
+{
+	if (cpu != boot_cpuid)
+		xics_setup_cpu();
+}
+
+static int pnv_smp_cpu_bootable(unsigned int nr)
+{
+	/* Special case - we inhibit secondary thread startup
+	 * during boot if the user requests it.
+	 */
+	if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) {
+		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
+			return 0;
+		if (smt_enabled_at_boot
+		    && cpu_thread_in_core(nr) >= smt_enabled_at_boot)
+			return 0;
+	}
+
+	return 1;
+}
+
+int __devinit pnv_smp_kick_cpu(int nr)
+{
+	unsigned int pcpu = get_hard_smp_processor_id(nr);
+	unsigned long start_here = __pa(*((unsigned long *)
+					  generic_secondary_smp_init));
+	long rc;
+
+	BUG_ON(nr < 0 || nr >= NR_CPUS);
+
+	/* On OPAL v2 the CPU are still spinning inside OPAL itself,
+	 * get them back now
+	 */
+	if (firmware_has_feature(FW_FEATURE_OPALv2)) {
+		pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu);
+		rc = opal_start_cpu(pcpu, start_here);
+		if (rc != OPAL_SUCCESS)
+			pr_warn("OPAL Error %ld starting CPU %d\n",
+				rc, nr);
+	}
+	return smp_generic_kick_cpu(nr);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static int pnv_smp_cpu_disable(void)
+{
+	int cpu = smp_processor_id();
+
+	/* This is identical to pSeries... might consolidate by
+	 * moving migrate_irqs_away to a ppc_md with default to
+	 * the generic fixup_irqs. --BenH.
+	 */
+	set_cpu_online(cpu, false);
+	vdso_data->processorCount--;
+	if (cpu == boot_cpuid)
+		boot_cpuid = cpumask_any(cpu_online_mask);
+	xics_migrate_irqs_away();
+	return 0;
+}
+
+static void pnv_smp_cpu_kill_self(void)
+{
+	unsigned int cpu;
+
+	/* If powersave_nap is enabled, use NAP mode, else just
+	 * spin aimlessly
+	 */
+	if (!powersave_nap) {
+		generic_mach_cpu_die();
+		return;
+	}
+
+	/* Standard hot unplug procedure */
+	local_irq_disable();
+	idle_task_exit();
+	current->active_mm = NULL; /* for sanity */
+	cpu = smp_processor_id();
+	DBG("CPU%d offline\n", cpu);
+	generic_set_cpu_dead(cpu);
+	smp_wmb();
+
+	/* We don't want to take decrementer interrupts while we are offline,
+	 * so clear LPCR:PECE1. We keep PECE2 enabled.
+	 */
+	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
+	while (!generic_check_cpu_restart(cpu)) {
+		power7_idle();
+		if (!generic_check_cpu_restart(cpu)) {
+			DBG("CPU%d Unexpected exit while offline !\n", cpu);
+			/* We may be getting an IPI, so we re-enable
+			 * interrupts to process it, it will be ignored
+			 * since we aren't online (hopefully)
+			 */
+			local_irq_enable();
+			local_irq_disable();
+		}
+	}
+	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1);
+	DBG("CPU%d coming online...\n", cpu);
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static struct smp_ops_t pnv_smp_ops = {
+	.message_pass	= smp_muxed_ipi_message_pass,
+	.cause_ipi	= NULL,	/* Filled at runtime by xics_smp_probe() */
+	.probe		= xics_smp_probe,
+	.kick_cpu	= pnv_smp_kick_cpu,
+	.setup_cpu	= pnv_smp_setup_cpu,
+	.cpu_bootable	= pnv_smp_cpu_bootable,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable	= pnv_smp_cpu_disable,
+	.cpu_die	= generic_cpu_die,
+#endif /* CONFIG_HOTPLUG_CPU */
+};
+
+/* This is called very early during platform setup_arch */
+void __init pnv_smp_init(void)
+{
+	smp_ops = &pnv_smp_ops;
+
+	/* XXX We don't yet have a proper entry point from HAL, for
+	 * now we rely on kexec-style entry from BML
+	 */
+
+#ifdef CONFIG_PPC_RTAS
+	/* Non-lpar has additional take/give timebase */
+	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
+		smp_ops->give_timebase = rtas_give_timebase;
+		smp_ops->take_timebase = rtas_take_timebase;
+	}
+#endif /* CONFIG_PPC_RTAS */
+
+#ifdef CONFIG_HOTPLUG_CPU
+	ppc_md.cpu_die	= pnv_smp_cpu_kill_self;
+#endif
+}
diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig
index dfe316b161a9..476d9d9b2405 100644
--- a/arch/powerpc/platforms/ps3/Kconfig
+++ b/arch/powerpc/platforms/ps3/Kconfig
@@ -148,4 +148,16 @@ config PS3_LPM
 	  profiling support of the Cell processor with programs like
 	  oprofile and perfmon2, then say Y or M, otherwise say N.
 
+config PS3GELIC_UDBG
+	bool "PS3 udbg output via UDP broadcasts on Ethernet"
+	depends on PPC_PS3
+	help
+	  Enables udbg early debugging output by sending broadcast UDP
+	  via the Ethernet port (UDP port number 18194).
+
+	  This driver uses a trivial implementation and is independent
+	  from the main network driver.
+
+	  If in doubt, say N here.
+
 endmenu
diff --git a/arch/powerpc/platforms/ps3/Makefile b/arch/powerpc/platforms/ps3/Makefile
index ac1bdf844eca..02b9e636dab7 100644
--- a/arch/powerpc/platforms/ps3/Makefile
+++ b/arch/powerpc/platforms/ps3/Makefile
@@ -2,6 +2,7 @@ obj-y += setup.o mm.o time.o hvcall.o htab.o repository.o
 obj-y += interrupt.o exports.o os-area.o
 obj-y += system-bus.o
 
+obj-$(CONFIG_PS3GELIC_UDBG) += gelic_udbg.o
 obj-$(CONFIG_SMP) += smp.o
 obj-$(CONFIG_SPU_BASE) += spu.o
 obj-y += device-init.o
diff --git a/arch/powerpc/platforms/ps3/gelic_udbg.c b/arch/powerpc/platforms/ps3/gelic_udbg.c
new file mode 100644
index 000000000000..20b46a19a48f
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/gelic_udbg.c
@@ -0,0 +1,273 @@
+/*
+ * udbg debug output routine via GELIC UDP broadcasts
+ *
+ * Copyright (C) 2007 Sony Computer Entertainment Inc.
+ * Copyright 2006, 2007 Sony Corporation
+ * Copyright (C) 2010 Hector Martin <hector@marcansoft.com>
+ * Copyright (C) 2011 Andre Heider <a.heider@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ */
+
+#include <asm/io.h>
+#include <asm/udbg.h>
+#include <asm/lv1call.h>
+
+#define GELIC_BUS_ID 1
+#define GELIC_DEVICE_ID 0
+#define GELIC_DEBUG_PORT 18194
+#define GELIC_MAX_MESSAGE_SIZE 1000
+
+#define GELIC_LV1_GET_MAC_ADDRESS 1
+#define GELIC_LV1_GET_VLAN_ID 4
+#define GELIC_LV1_VLAN_TX_ETHERNET_0 2
+
+#define GELIC_DESCR_DMA_STAT_MASK 0xf0000000
+#define GELIC_DESCR_DMA_CARDOWNED 0xa0000000
+
+#define GELIC_DESCR_TX_DMA_IKE 0x00080000
+#define GELIC_DESCR_TX_DMA_NO_CHKSUM 0x00000000
+#define GELIC_DESCR_TX_DMA_FRAME_TAIL 0x00040000
+
+#define GELIC_DESCR_DMA_CMD_NO_CHKSUM (GELIC_DESCR_DMA_CARDOWNED | \
+				       GELIC_DESCR_TX_DMA_IKE | \
+				       GELIC_DESCR_TX_DMA_NO_CHKSUM)
+
+static u64 bus_addr;
+
+struct gelic_descr {
+	/* as defined by the hardware */
+	__be32 buf_addr;
+	__be32 buf_size;
+	__be32 next_descr_addr;
+	__be32 dmac_cmd_status;
+	__be32 result_size;
+	__be32 valid_size;	/* all zeroes for tx */
+	__be32 data_status;
+	__be32 data_error;	/* all zeroes for tx */
+} __attribute__((aligned(32)));
+
+struct debug_block {
+	struct gelic_descr descr;
+	u8 pkt[1520];
+} __packed;
+
+struct ethhdr {
+	u8 dest[6];
+	u8 src[6];
+	u16 type;
+} __packed;
+
+struct vlantag {
+	u16 vlan;
+	u16 subtype;
+} __packed;
+
+struct iphdr {
+	u8 ver_len;
+	u8 dscp_ecn;
+	u16 total_length;
+	u16 ident;
+	u16 frag_off_flags;
+	u8 ttl;
+	u8 proto;
+	u16 checksum;
+	u32 src;
+	u32 dest;
+} __packed;
+
+struct udphdr {
+	u16 src;
+	u16 dest;
+	u16 len;
+	u16 checksum;
+} __packed;
+
+static __iomem struct ethhdr *h_eth;
+static __iomem struct vlantag *h_vlan;
+static __iomem struct iphdr *h_ip;
+static __iomem struct udphdr *h_udp;
+
+static __iomem char *pmsg;
+static __iomem char *pmsgc;
+
+static __iomem struct debug_block dbg __attribute__((aligned(32)));
+
+static int header_size;
+
+static void map_dma_mem(int bus_id, int dev_id, void *start, size_t len,
+			u64 *real_bus_addr)
+{
+	s64 result;
+	u64 real_addr = ((u64)start) & 0x0fffffffffffffffUL;
+	u64 real_end = real_addr + len;
+	u64 map_start = real_addr & ~0xfff;
+	u64 map_end = (real_end + 0xfff) & ~0xfff;
+	u64 bus_addr = 0;
+
+	u64 flags = 0xf800000000000000UL;
+
+	result = lv1_allocate_device_dma_region(bus_id, dev_id,
+						map_end - map_start, 12, 0,
+						&bus_addr);
+	if (result)
+		lv1_panic(0);
+
+	result = lv1_map_device_dma_region(bus_id, dev_id, map_start,
+					   bus_addr, map_end - map_start,
+					   flags);
+	if (result)
+		lv1_panic(0);
+
+	*real_bus_addr = bus_addr + real_addr - map_start;
+}
+
+static int unmap_dma_mem(int bus_id, int dev_id, u64 bus_addr, size_t len)
+{
+	s64 result;
+	u64 real_bus_addr;
+
+	real_bus_addr = bus_addr & ~0xfff;
+	len += bus_addr - real_bus_addr;
+	len = (len + 0xfff) & ~0xfff;
+
+	result = lv1_unmap_device_dma_region(bus_id, dev_id, real_bus_addr,
+					     len);
+	if (result)
+		return result;
+
+	return lv1_free_device_dma_region(bus_id, dev_id, real_bus_addr);
+}
+
+static void gelic_debug_init(void)
+{
+	s64 result;
+	u64 v2;
+	u64 mac;
+	u64 vlan_id;
+
+	result = lv1_open_device(GELIC_BUS_ID, GELIC_DEVICE_ID, 0);
+	if (result)
+		lv1_panic(0);
+
+	map_dma_mem(GELIC_BUS_ID, GELIC_DEVICE_ID, &dbg, sizeof(dbg),
+		    &bus_addr);
+
+	memset(&dbg, 0, sizeof(dbg));
+
+	dbg.descr.buf_addr = bus_addr + offsetof(struct debug_block, pkt);
+
+	wmb();
+
+	result = lv1_net_control(GELIC_BUS_ID, GELIC_DEVICE_ID,
+				 GELIC_LV1_GET_MAC_ADDRESS, 0, 0, 0,
+				 &mac, &v2);
+	if (result)
+		lv1_panic(0);
+
+	mac <<= 16;
+
+	h_eth = (struct ethhdr *)dbg.pkt;
+
+	memset(&h_eth->dest, 0xff, 6);
+	memcpy(&h_eth->src, &mac, 6);
+
+	header_size = sizeof(struct ethhdr);
+
+	result = lv1_net_control(GELIC_BUS_ID, GELIC_DEVICE_ID,
+				 GELIC_LV1_GET_VLAN_ID,
+				 GELIC_LV1_VLAN_TX_ETHERNET_0, 0, 0,
+				 &vlan_id, &v2);
+	if (!result) {
+		h_eth->type = 0x8100;
+
+		header_size += sizeof(struct vlantag);
+		h_vlan = (struct vlantag *)(h_eth + 1);
+		h_vlan->vlan = vlan_id;
+		h_vlan->subtype = 0x0800;
+		h_ip = (struct iphdr *)(h_vlan + 1);
+	} else {
+		h_eth->type = 0x0800;
+		h_ip = (struct iphdr *)(h_eth + 1);
+	}
+
+	header_size += sizeof(struct iphdr);
+	h_ip->ver_len = 0x45;
+	h_ip->ttl = 10;
+	h_ip->proto = 0x11;
+	h_ip->src = 0x00000000;
+	h_ip->dest = 0xffffffff;
+
+	header_size += sizeof(struct udphdr);
+	h_udp = (struct udphdr *)(h_ip + 1);
+	h_udp->src = GELIC_DEBUG_PORT;
+	h_udp->dest = GELIC_DEBUG_PORT;
+
+	pmsgc = pmsg = (char *)(h_udp + 1);
+}
+
+static void gelic_debug_shutdown(void)
+{
+	if (bus_addr)
+		unmap_dma_mem(GELIC_BUS_ID, GELIC_DEVICE_ID,
+			      bus_addr, sizeof(dbg));
+	lv1_close_device(GELIC_BUS_ID, GELIC_DEVICE_ID);
+}
+
+static void gelic_sendbuf(int msgsize)
+{
+	u16 *p;
+	u32 sum;
+	int i;
+
+	dbg.descr.buf_size = header_size + msgsize;
+	h_ip->total_length = msgsize + sizeof(struct udphdr) +
+			     sizeof(struct iphdr);
+	h_udp->len = msgsize + sizeof(struct udphdr);
+
+	h_ip->checksum = 0;
+	sum = 0;
+	p = (u16 *)h_ip;
+	for (i = 0; i < 5; i++)
+		sum += *p++;
+	h_ip->checksum = ~(sum + (sum >> 16));
+
+	dbg.descr.dmac_cmd_status = GELIC_DESCR_DMA_CMD_NO_CHKSUM |
+				    GELIC_DESCR_TX_DMA_FRAME_TAIL;
+	dbg.descr.result_size = 0;
+	dbg.descr.data_status = 0;
+
+	wmb();
+
+	lv1_net_start_tx_dma(GELIC_BUS_ID, GELIC_DEVICE_ID, bus_addr, 0);
+
+	while ((dbg.descr.dmac_cmd_status & GELIC_DESCR_DMA_STAT_MASK) ==
+	       GELIC_DESCR_DMA_CARDOWNED)
+		cpu_relax();
+}
+
+static void ps3gelic_udbg_putc(char ch)
+{
+	*pmsgc++ = ch;
+	if (ch == '\n' || (pmsgc-pmsg) >= GELIC_MAX_MESSAGE_SIZE) {
+		gelic_sendbuf(pmsgc-pmsg);
+		pmsgc = pmsg;
+	}
+}
+
+void __init udbg_init_ps3gelic(void)
+{
+	gelic_debug_init();
+	udbg_putc = ps3gelic_udbg_putc;
+}
+
+void udbg_shutdown_ps3gelic(void)
+{
+	udbg_putc = NULL;
+	gelic_debug_shutdown();
+}
+EXPORT_SYMBOL(udbg_shutdown_ps3gelic);
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 23083c397528..688141c76e03 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -695,12 +695,18 @@ static int ps3_dma_supported(struct device *_dev, u64 mask)
 	return mask >= DMA_BIT_MASK(32);
 }
 
+static u64 ps3_dma_get_required_mask(struct device *_dev)
+{
+	return DMA_BIT_MASK(32);
+}
+
 static struct dma_map_ops ps3_sb_dma_ops = {
 	.alloc_coherent = ps3_alloc_coherent,
 	.free_coherent = ps3_free_coherent,
 	.map_sg = ps3_sb_map_sg,
 	.unmap_sg = ps3_sb_unmap_sg,
 	.dma_supported = ps3_dma_supported,
+	.get_required_mask = ps3_dma_get_required_mask,
 	.map_page = ps3_sb_map_page,
 	.unmap_page = ps3_unmap_page,
 };
@@ -711,6 +717,7 @@ static struct dma_map_ops ps3_ioc0_dma_ops = {
 	.map_sg = ps3_ioc0_map_sg,
 	.unmap_sg = ps3_ioc0_unmap_sg,
 	.dma_supported = ps3_dma_supported,
+	.get_required_mask = ps3_dma_get_required_mask,
 	.map_page = ps3_ioc0_map_page,
 	.unmap_page = ps3_unmap_page,
 };
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 05cf4769b88c..c81f6bb9c10f 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -15,6 +15,7 @@ config PPC_PSERIES
 	select PPC_UDBG_16550
 	select PPC_NATIVE
 	select PPC_PCI_CHOICE if EXPERT
+	select ZLIB_DEFLATE
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index e9be25bc571b..0f1b706506ed 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -112,6 +112,7 @@ void dlpar_free_cc_nodes(struct device_node *dn)
 	dlpar_free_one_cc_node(dn);
 }
 
+#define COMPLETE	0
 #define NEXT_SIBLING    1
 #define NEXT_CHILD      2
 #define NEXT_PROPERTY   3
@@ -158,6 +159,9 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 		spin_unlock(&rtas_data_buf_lock);
 
 		switch (rc) {
+		case COMPLETE:
+			break;
+
 		case NEXT_SIBLING:
 			dn = dlpar_parse_cc_node(ccwa);
 			if (!dn)
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index ada6e07532ec..d42f37d8a440 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -1338,7 +1338,7 @@ static const struct file_operations proc_eeh_operations = {
 static int __init eeh_init_proc(void)
 {
 	if (machine_is(pseries))
-		proc_create("ppc64/eeh", 0, NULL, &proc_eeh_operations);
+		proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
 	return 0;
 }
 __initcall(eeh_init_proc);
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 01faab9456ca..5905a3b9f7e6 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -939,14 +939,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	if (ret) {
 		dev_info(&dev->dev, "failed to map direct window for %s: %d\n",
 			 dn->full_name, ret);
-		goto out_clear_window;
+		goto out_free_window;
 	}
 
 	ret = prom_add_property(pdn, win64);
 	if (ret) {
 		dev_err(&dev->dev, "unable to add dma window property for %s: %d",
 			 pdn->full_name, ret);
-		goto out_clear_window;
+		goto out_free_window;
 	}
 
 	window->device = pdn;
@@ -958,6 +958,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	dma_addr = of_read_number(&create.addr_hi, 2);
 	goto out_unlock;
 
+out_free_window:
+	kfree(window);
+
 out_clear_window:
 	remove_ddw(pdn);
 
@@ -1077,12 +1080,38 @@ check_mask:
 	return 0;
 }
 
+static u64 dma_get_required_mask_pSeriesLP(struct device *dev)
+{
+	if (!dev->dma_mask)
+		return 0;
+
+	if (!disable_ddw && dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+		struct device_node *dn;
+
+		dn = pci_device_to_OF_node(pdev);
+
+		/* search upwards for ibm,dma-window */
+		for (; dn && PCI_DN(dn) && !PCI_DN(dn)->iommu_table;
+				dn = dn->parent)
+			if (of_get_property(dn, "ibm,dma-window", NULL))
+				break;
+		/* if there is a ibm,ddw-applicable property require 64 bits */
+		if (dn && PCI_DN(dn) &&
+				of_get_property(dn, "ibm,ddw-applicable", NULL))
+			return DMA_BIT_MASK(64);
+	}
+
+	return dma_iommu_ops.get_required_mask(dev);
+}
+
 #else  /* CONFIG_PCI */
 #define pci_dma_bus_setup_pSeries	NULL
 #define pci_dma_dev_setup_pSeries	NULL
 #define pci_dma_bus_setup_pSeriesLP	NULL
 #define pci_dma_dev_setup_pSeriesLP	NULL
 #define dma_set_mask_pSeriesLP		NULL
+#define dma_get_required_mask_pSeriesLP	NULL
 #endif /* !CONFIG_PCI */
 
 static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
@@ -1186,6 +1215,7 @@ void iommu_init_early_pSeries(void)
 		ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
 		ppc_md.dma_set_mask = dma_set_mask_pSeriesLP;
+		ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP;
 	} else {
 		ppc_md.tce_build = tce_build_pSeries;
 		ppc_md.tce_free  = tce_free_pSeries;
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 00cc3a094885..a76b22844d18 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -18,6 +18,8 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/kmsg_dump.h>
+#include <linux/ctype.h>
+#include <linux/zlib.h>
 #include <asm/uaccess.h>
 #include <asm/nvram.h>
 #include <asm/rtas.h>
@@ -78,8 +80,41 @@ static struct kmsg_dumper nvram_kmsg_dumper = {
 #define NVRAM_RTAS_READ_TIMEOUT 5		/* seconds */
 static unsigned long last_unread_rtas_event;	/* timestamp */
 
-/* We preallocate oops_buf during init to avoid kmalloc during oops/panic. */
-static char *oops_buf;
+/*
+ * For capturing and compressing an oops or panic report...
+
+ * big_oops_buf[] holds the uncompressed text we're capturing.
+ *
+ * oops_buf[] holds the compressed text, preceded by a prefix.
+ * The prefix is just a u16 holding the length of the compressed* text.
+ * (*Or uncompressed, if compression fails.)  oops_buf[] gets written
+ * to NVRAM.
+ *
+ * oops_len points to the prefix.  oops_data points to the compressed text.
+ *
+ * +- oops_buf
+ * |		+- oops_data
+ * v		v
+ * +------------+-----------------------------------------------+
+ * | length	| text                                          |
+ * | (2 bytes)	| (oops_data_sz bytes)                          |
+ * +------------+-----------------------------------------------+
+ * ^
+ * +- oops_len
+ *
+ * We preallocate these buffers during init to avoid kmalloc during oops/panic.
+ */
+static size_t big_oops_buf_sz;
+static char *big_oops_buf, *oops_buf;
+static u16 *oops_len;
+static char *oops_data;
+static size_t oops_data_sz;
+
+/* Compression parameters */
+#define COMPR_LEVEL 6
+#define WINDOW_BITS 12
+#define MEM_LEVEL 4
+static struct z_stream_s stream;
 
 static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index)
 {
@@ -387,11 +422,44 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
 						sizeof(rtas_log_partition));
 	}
 	oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL);
+	if (!oops_buf) {
+		pr_err("nvram: No memory for %s partition\n",
+						oops_log_partition.name);
+		return;
+	}
+	oops_len = (u16*) oops_buf;
+	oops_data = oops_buf + sizeof(u16);
+	oops_data_sz = oops_log_partition.size - sizeof(u16);
+
+	/*
+	 * Figure compression (preceded by elimination of each line's <n>
+	 * severity prefix) will reduce the oops/panic report to at most
+	 * 45% of its original size.
+	 */
+	big_oops_buf_sz = (oops_data_sz * 100) / 45;
+	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
+	if (big_oops_buf) {
+		stream.workspace = kmalloc(zlib_deflate_workspacesize(
+				WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
+		if (!stream.workspace) {
+			pr_err("nvram: No memory for compression workspace; "
+				"skipping compression of %s partition data\n",
+				oops_log_partition.name);
+			kfree(big_oops_buf);
+			big_oops_buf = NULL;
+		}
+	} else {
+		pr_err("No memory for uncompressed %s data; "
+			"skipping compression\n", oops_log_partition.name);
+		stream.workspace = NULL;
+	}
+
 	rc = kmsg_dump_register(&nvram_kmsg_dumper);
 	if (rc != 0) {
 		pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc);
 		kfree(oops_buf);
-		return;
+		kfree(big_oops_buf);
+		kfree(stream.workspace);
 	}
 }
 
@@ -473,7 +541,83 @@ static int clobbering_unread_rtas_event(void)
 						NVRAM_RTAS_READ_TIMEOUT);
 }
 
-/* our kmsg_dump callback */
+/* Squeeze out each line's <n> severity prefix. */
+static size_t elide_severities(char *buf, size_t len)
+{
+	char *in, *out, *buf_end = buf + len;
+	/* Assume a <n> at the very beginning marks the start of a line. */
+	int newline = 1;
+
+	in = out = buf;
+	while (in < buf_end) {
+		if (newline && in+3 <= buf_end &&
+				*in == '<' && isdigit(in[1]) && in[2] == '>') {
+			in += 3;
+			newline = 0;
+		} else {
+			newline = (*in == '\n');
+			*out++ = *in++;
+		}
+	}
+	return out - buf;
+}
+
+/* Derived from logfs_compress() */
+static int nvram_compress(const void *in, void *out, size_t inlen,
+							size_t outlen)
+{
+	int err, ret;
+
+	ret = -EIO;
+	err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS,
+						MEM_LEVEL, Z_DEFAULT_STRATEGY);
+	if (err != Z_OK)
+		goto error;
+
+	stream.next_in = in;
+	stream.avail_in = inlen;
+	stream.total_in = 0;
+	stream.next_out = out;
+	stream.avail_out = outlen;
+	stream.total_out = 0;
+
+	err = zlib_deflate(&stream, Z_FINISH);
+	if (err != Z_STREAM_END)
+		goto error;
+
+	err = zlib_deflateEnd(&stream);
+	if (err != Z_OK)
+		goto error;
+
+	if (stream.total_out >= stream.total_in)
+		goto error;
+
+	ret = stream.total_out;
+error:
+	return ret;
+}
+
+/* Compress the text from big_oops_buf into oops_buf. */
+static int zip_oops(size_t text_len)
+{
+	int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len,
+								oops_data_sz);
+	if (zipped_len < 0) {
+		pr_err("nvram: compression failed; returned %d\n", zipped_len);
+		pr_err("nvram: logging uncompressed oops/panic report\n");
+		return -1;
+	}
+	*oops_len = (u16) zipped_len;
+	return 0;
+}
+
+/*
+ * This is our kmsg_dump callback, called after an oops or panic report
+ * has been written to the printk buffer.  We want to capture as much
+ * of the printk buffer as possible.  First, capture as much as we can
+ * that we think will compress sufficiently to fit in the lnx,oops-log
+ * partition.  If that's too much, go back and capture uncompressed text.
+ */
 static void oops_to_nvram(struct kmsg_dumper *dumper,
 		enum kmsg_dump_reason reason,
 		const char *old_msgs, unsigned long old_len,
@@ -482,6 +626,8 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
 	static unsigned int oops_count = 0;
 	static bool panicking = false;
 	size_t text_len;
+	unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ;
+	int rc = -1;
 
 	switch (reason) {
 	case KMSG_DUMP_RESTART:
@@ -509,8 +655,19 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
 	if (clobbering_unread_rtas_event())
 		return;
 
-	text_len = capture_last_msgs(old_msgs, old_len, new_msgs, new_len,
-					oops_buf, oops_log_partition.size);
+	if (big_oops_buf) {
+		text_len = capture_last_msgs(old_msgs, old_len,
+			new_msgs, new_len, big_oops_buf, big_oops_buf_sz);
+		text_len = elide_severities(big_oops_buf, text_len);
+		rc = zip_oops(text_len);
+	}
+	if (rc != 0) {
+		text_len = capture_last_msgs(old_msgs, old_len,
+				new_msgs, new_len, oops_data, oops_data_sz);
+		err_type = ERR_TYPE_KERNEL_PANIC;
+		*oops_len = (u16) text_len;
+	}
+
 	(void) nvram_write_os_partition(&oops_log_partition, oops_buf,
-		(int) text_len, ERR_TYPE_KERNEL_PANIC, ++oops_count);
+		(int) (sizeof(*oops_len) + *oops_len), err_type, ++oops_count);
 }
diff --git a/arch/powerpc/platforms/wsp/Kconfig b/arch/powerpc/platforms/wsp/Kconfig
index c3c48eb62cc1..f4fb837873fb 100644
--- a/arch/powerpc/platforms/wsp/Kconfig
+++ b/arch/powerpc/platforms/wsp/Kconfig
@@ -1,5 +1,12 @@
 config PPC_WSP
 	bool
+	select PPC_A2
+	select PPC_SCOM
+	select PPC_XICS
+	select PPC_ICP_NATIVE
+	select PCI
+	select PPC_IO_WORKAROUNDS if PCI
+	select PPC_INDIRECT_PIO if PCI
 	default n
 
 menu "WSP platform selection"
@@ -7,13 +14,9 @@ menu "WSP platform selection"
 
 config PPC_PSR2
 	bool "PSR-2 platform"
-	select PPC_A2
 	select GENERIC_TBSYNC
-	select PPC_SCOM
 	select EPAPR_BOOT
 	select PPC_WSP
-	select PPC_XICS
-	select PPC_ICP_NATIVE
 	default y
 
 endmenu
diff --git a/arch/powerpc/platforms/wsp/Makefile b/arch/powerpc/platforms/wsp/Makefile
index 095be73d6cd4..a1486b436f02 100644
--- a/arch/powerpc/platforms/wsp/Makefile
+++ b/arch/powerpc/platforms/wsp/Makefile
@@ -4,3 +4,5 @@ obj-y				+= setup.o ics.o
 obj-$(CONFIG_PPC_PSR2)		+= psr2.o opb_pic.o
 obj-$(CONFIG_PPC_WSP)		+= scom_wsp.o
 obj-$(CONFIG_SMP)		+= smp.o scom_smp.o
+obj-$(CONFIG_PCI)		+= wsp_pci.o
+obj-$(CONFIG_PCI_MSI)		+= msi.o
\ No newline at end of file
diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c
index e53bd9e7b125..576874392543 100644
--- a/arch/powerpc/platforms/wsp/ics.c
+++ b/arch/powerpc/platforms/wsp/ics.c
@@ -710,3 +710,51 @@ void __init wsp_init_irq(void)
 	/* We need to patch our irq chip's EOI to point to the right ICP */
 	wsp_irq_chip.irq_eoi = icp_ops->eoi;
 }
+
+#ifdef CONFIG_PCI_MSI
+static void wsp_ics_msi_unmask_irq(struct irq_data *d)
+{
+	wsp_chip_unmask_irq(d);
+	unmask_msi_irq(d);
+}
+
+static unsigned int wsp_ics_msi_startup(struct irq_data *d)
+{
+	wsp_ics_msi_unmask_irq(d);
+	return 0;
+}
+
+static void wsp_ics_msi_mask_irq(struct irq_data *d)
+{
+	mask_msi_irq(d);
+	wsp_chip_mask_irq(d);
+}
+
+/*
+ * we do it this way because we reassinge default EOI handling in
+ * irq_init() above
+ */
+static void wsp_ics_eoi(struct irq_data *data)
+{
+	wsp_irq_chip.irq_eoi(data);
+}
+
+static struct irq_chip wsp_ics_msi = {
+	.name = "WSP ICS MSI",
+	.irq_startup = wsp_ics_msi_startup,
+	.irq_mask = wsp_ics_msi_mask_irq,
+	.irq_unmask = wsp_ics_msi_unmask_irq,
+	.irq_eoi = wsp_ics_eoi,
+	.irq_set_affinity = wsp_chip_set_affinity
+};
+
+void wsp_ics_set_msi_chip(unsigned int irq)
+{
+	irq_set_chip(irq, &wsp_ics_msi);
+}
+
+void wsp_ics_set_std_chip(unsigned int irq)
+{
+	irq_set_chip(irq, &wsp_irq_chip);
+}
+#endif /* CONFIG_PCI_MSI */
diff --git a/arch/powerpc/platforms/wsp/ics.h b/arch/powerpc/platforms/wsp/ics.h
index e34d53102640..07b644e0cf97 100644
--- a/arch/powerpc/platforms/wsp/ics.h
+++ b/arch/powerpc/platforms/wsp/ics.h
@@ -17,4 +17,9 @@ extern void wsp_init_irq(void);
 extern int wsp_ics_alloc_irq(struct device_node *dn, int num);
 extern void wsp_ics_free_irq(struct device_node *dn, unsigned int irq);
 
+#ifdef CONFIG_PCI_MSI
+extern void wsp_ics_set_msi_chip(unsigned int irq);
+extern void wsp_ics_set_std_chip(unsigned int irq);
+#endif /* CONFIG_PCI_MSI */
+
 #endif /* __ICS_H */
diff --git a/arch/powerpc/platforms/wsp/msi.c b/arch/powerpc/platforms/wsp/msi.c
new file mode 100644
index 000000000000..380882f27add
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/msi.c
@@ -0,0 +1,102 @@
+/*
+ * Copyright 2011 Michael Ellerman, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+
+#include "msi.h"
+#include "ics.h"
+#include "wsp_pci.h"
+
+/* Magic addresses for 32 & 64-bit MSIs with hardcoded MVE 0 */
+#define MSI_ADDR_32		0xFFFF0000ul
+#define MSI_ADDR_64		0x1000000000000000ul
+
+int wsp_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	struct pci_controller *phb;
+	struct msi_desc *entry;
+	struct msi_msg msg;
+	unsigned int virq;
+	int hwirq;
+
+	phb = pci_bus_to_host(dev->bus);
+	if (!phb)
+		return -ENOENT;
+
+	entry = list_first_entry(&dev->msi_list, struct msi_desc, list);
+	if (entry->msi_attrib.is_64) {
+		msg.address_lo = 0;
+		msg.address_hi = MSI_ADDR_64 >> 32;
+	} else {
+		msg.address_lo = MSI_ADDR_32;
+		msg.address_hi = 0;
+	}
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		hwirq = wsp_ics_alloc_irq(phb->dn, 1);
+		if (hwirq < 0) {
+			dev_warn(&dev->dev, "wsp_msi: hwirq alloc failed!\n");
+			return hwirq;
+		}
+
+		virq = irq_create_mapping(NULL, hwirq);
+		if (virq == NO_IRQ) {
+			dev_warn(&dev->dev, "wsp_msi: virq alloc failed!\n");
+			return -1;
+		}
+
+		dev_dbg(&dev->dev, "wsp_msi: allocated irq %#x/%#x\n",
+			hwirq, virq);
+
+		wsp_ics_set_msi_chip(virq);
+		irq_set_msi_desc(virq, entry);
+		msg.data = hwirq & XIVE_ADDR_MASK;
+		write_msi_msg(virq, &msg);
+	}
+
+	return 0;
+}
+
+void wsp_teardown_msi_irqs(struct pci_dev *dev)
+{
+	struct pci_controller *phb;
+	struct msi_desc *entry;
+	int hwirq;
+
+	phb = pci_bus_to_host(dev->bus);
+
+	dev_dbg(&dev->dev, "wsp_msi: tearing down msi irqs\n");
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		if (entry->irq == NO_IRQ)
+			continue;
+
+		irq_set_msi_desc(entry->irq, NULL);
+		wsp_ics_set_std_chip(entry->irq);
+
+		hwirq = virq_to_hw(entry->irq);
+		/* In this order to avoid racing with irq_create_mapping() */
+		irq_dispose_mapping(entry->irq);
+		wsp_ics_free_irq(phb->dn, hwirq);
+	}
+}
+
+void wsp_setup_phb_msi(struct pci_controller *phb)
+{
+	/* Create a single MVE at offset 0 that matches everything */
+	out_be64(phb->cfg_data + PCIE_REG_IODA_ADDR, PCIE_REG_IODA_AD_TBL_MVT);
+	out_be64(phb->cfg_data + PCIE_REG_IODA_DATA0, 1ull << 63);
+
+	ppc_md.setup_msi_irqs = wsp_setup_msi_irqs;
+	ppc_md.teardown_msi_irqs = wsp_teardown_msi_irqs;
+}
diff --git a/arch/powerpc/platforms/wsp/msi.h b/arch/powerpc/platforms/wsp/msi.h
new file mode 100644
index 000000000000..0ab27b71b24d
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/msi.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright 2011 Michael Ellerman, IBM Corp.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __WSP_MSI_H
+#define __WSP_MSI_H
+
+#ifdef CONFIG_PCI_MSI
+extern void wsp_setup_phb_msi(struct pci_controller *phb);
+#else
+static inline void wsp_setup_phb_msi(struct pci_controller *phb) { }
+#endif
+
+#endif /* __WSP_MSI_H */
diff --git a/arch/powerpc/platforms/wsp/psr2.c b/arch/powerpc/platforms/wsp/psr2.c
index 40f28916ff6c..166f2e4b4bee 100644
--- a/arch/powerpc/platforms/wsp/psr2.c
+++ b/arch/powerpc/platforms/wsp/psr2.c
@@ -63,6 +63,10 @@ static void __init psr2_setup_arch(void)
 #ifdef CONFIG_SMP
 	a2_setup_smp();
 #endif
+#ifdef CONFIG_PCI
+	wsp_setup_pci();
+#endif
+
 }
 
 static int __init psr2_probe(void)
diff --git a/arch/powerpc/platforms/wsp/wsp.h b/arch/powerpc/platforms/wsp/wsp.h
index 7c3e087fd2f2..33479818f62a 100644
--- a/arch/powerpc/platforms/wsp/wsp.h
+++ b/arch/powerpc/platforms/wsp/wsp.h
@@ -3,6 +3,9 @@
 
 #include <asm/wsp.h>
 
+/* Devtree compatible strings for major devices */
+#define PCIE_COMPATIBLE     "ibm,wsp-pciex"
+
 extern void wsp_setup_pci(void);
 extern void scom_init_wsp(void);
 
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c
new file mode 100644
index 000000000000..e0262cd0e2d3
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/wsp_pci.c
@@ -0,0 +1,1133 @@
+/*
+ * Copyright 2010 Ben Herrenschmidt, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define DEBUG
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/debugfs.h>
+
+#include <asm/sections.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/iommu.h>
+#include <asm/io-workarounds.h>
+
+#include "wsp.h"
+#include "wsp_pci.h"
+#include "msi.h"
+
+
+/* Max number of TVTs for one table. Only 32-bit tables can use
+ * multiple TVTs and so the max currently supported is thus 8
+ * since only 2G of DMA space is supported
+ */
+#define MAX_TABLE_TVT_COUNT		8
+
+struct wsp_dma_table {
+	struct list_head	link;
+	struct iommu_table	table;
+	struct wsp_phb	*phb;
+	struct page		*tces[MAX_TABLE_TVT_COUNT];
+};
+
+/* We support DMA regions from 0...2G in 32bit space (no support for
+ * 64-bit DMA just yet). Each device gets a separate TCE table (TVT
+ * entry) with validation enabled (though not supported by SimiCS
+ * just yet).
+ *
+ * To simplify things, we divide this 2G space into N regions based
+ * on the constant below which could be turned into a tunable eventually
+ *
+ * We then assign dynamically those regions to devices as they show up.
+ *
+ * We use a bitmap as an allocator for these.
+ *
+ * Tables are allocated/created dynamically as devices are discovered,
+ * multiple TVT entries are used if needed
+ *
+ * When 64-bit DMA support is added we should simply use a separate set
+ * of larger regions (the HW supports 64 TVT entries). We can
+ * additionally create a bypass region in 64-bit space for performances
+ * though that would have a cost in term of security.
+ *
+ * If you set NUM_DMA32_REGIONS to 1, then a single table is shared
+ * for all devices and bus/dev/fn validation is disabled
+ *
+ * Note that a DMA32 region cannot be smaller than 256M so the max
+ * supported here for now is 8. We don't yet support sharing regions
+ * between multiple devices so the max number of devices supported
+ * is MAX_TABLE_TVT_COUNT.
+ */
+#define NUM_DMA32_REGIONS	1
+
+struct wsp_phb {
+	struct pci_controller	*hose;
+
+	/* Lock controlling access to the list of dma tables.
+	 * It does -not- protect against dma_* operations on
+	 * those tables, those should be stopped before an entry
+	 * is removed from the list.
+	 *
+	 * The lock is also used for error handling operations
+	 */
+	spinlock_t		lock;
+	struct list_head	dma_tables;
+	unsigned long		dma32_map;
+	unsigned long		dma32_base;
+	unsigned int		dma32_num_regions;
+	unsigned long		dma32_region_size;
+
+	/* Debugfs stuff */
+	struct dentry		*ddir;
+
+	struct list_head	all;
+};
+static LIST_HEAD(wsp_phbs);
+
+//#define cfg_debug(fmt...)	pr_debug(fmt)
+#define cfg_debug(fmt...)
+
+
+static int wsp_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
+				  int offset, int len, u32 *val)
+{
+	struct pci_controller *hose;
+	int suboff;
+	u64 addr;
+
+	hose = pci_bus_to_host(bus);
+	if (hose == NULL)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	if (offset >= 0x1000)
+		return  PCIBIOS_BAD_REGISTER_NUMBER;
+	addr = PCIE_REG_CA_ENABLE |
+		((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT |
+		((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT |
+		((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT;
+	suboff = offset & 3;
+
+	/*
+	 * Note: the caller has already checked that offset is
+	 * suitably aligned and that len is 1, 2 or 4.
+	 */
+
+	switch (len) {
+	case 1:
+		addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+		*val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA)
+			>> (suboff << 3)) & 0xff;
+		cfg_debug("read 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n",
+			  bus->number, devfn >> 3, devfn & 7,
+			  offset, suboff, addr, *val);
+		break;
+	case 2:
+		addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+		*val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA)
+			>> (suboff << 3)) & 0xffff;
+		cfg_debug("read 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n",
+			  bus->number, devfn >> 3, devfn & 7,
+			  offset, suboff, addr, *val);
+		break;
+	default:
+		addr |= 0xful << PCIE_REG_CA_BE_SHIFT;
+		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+		*val = in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA);
+		cfg_debug("read 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n",
+			  bus->number, devfn >> 3, devfn & 7,
+			  offset, suboff, addr, *val);
+		break;
+	}
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int wsp_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
+				   int offset, int len, u32 val)
+{
+	struct pci_controller *hose;
+	int suboff;
+	u64 addr;
+
+	hose = pci_bus_to_host(bus);
+	if (hose == NULL)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	if (offset >= 0x1000)
+		return  PCIBIOS_BAD_REGISTER_NUMBER;
+	addr = PCIE_REG_CA_ENABLE |
+		((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT |
+		((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT |
+		((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT;
+	suboff = offset & 3;
+
+	/*
+	 * Note: the caller has already checked that offset is
+	 * suitably aligned and that len is 1, 2 or 4.
+	 */
+	switch (len) {
+	case 1:
+		addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+		val <<= suboff << 3;
+		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+		out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
+		cfg_debug("write 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n",
+			  bus->number, devfn >> 3, devfn & 7,
+			  offset, suboff, addr, val);
+		break;
+	case 2:
+		addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+		val <<= suboff << 3;
+		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+		out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
+		cfg_debug("write 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n",
+			  bus->number, devfn >> 3, devfn & 7,
+			  offset, suboff, addr, val);
+		break;
+	default:
+		addr |= 0xful << PCIE_REG_CA_BE_SHIFT;
+		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+		out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
+		cfg_debug("write 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n",
+			  bus->number, devfn >> 3, devfn & 7,
+			  offset, suboff, addr, val);
+		break;
+	}
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops wsp_pcie_pci_ops =
+{
+	.read = wsp_pcie_read_config,
+	.write = wsp_pcie_write_config,
+};
+
+#define TCE_SHIFT		12
+#define TCE_PAGE_SIZE		(1 << TCE_SHIFT)
+#define TCE_PCI_WRITE		0x2		 /* write from PCI allowed */
+#define TCE_PCI_READ		0x1	 	 /* read from PCI allowed */
+#define TCE_RPN_MASK		0x3fffffffffful  /* 42-bit RPN (4K pages) */
+#define TCE_RPN_SHIFT		12
+
+//#define dma_debug(fmt...)	pr_debug(fmt)
+#define dma_debug(fmt...)
+
+static int tce_build_wsp(struct iommu_table *tbl, long index, long npages,
+			   unsigned long uaddr, enum dma_data_direction direction,
+			   struct dma_attrs *attrs)
+{
+	struct wsp_dma_table *ptbl = container_of(tbl,
+						    struct wsp_dma_table,
+						    table);
+	u64 proto_tce;
+	u64 *tcep;
+	u64 rpn;
+
+	proto_tce = TCE_PCI_READ;
+#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+	proto_tce |= TCE_PCI_WRITE;
+#else
+	if (direction != DMA_TO_DEVICE)
+		proto_tce |= TCE_PCI_WRITE;
+#endif
+
+	/* XXX Make this faster by factoring out the page address for
+	 * within a TCE table
+	 */
+	while (npages--) {
+		/* We don't use it->base as the table can be scattered */
+		tcep = (u64 *)page_address(ptbl->tces[index >> 16]);
+		tcep += (index & 0xffff);
+
+		/* can't move this out since we might cross LMB boundary */
+		rpn = __pa(uaddr) >> TCE_SHIFT;
+		*tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
+
+		dma_debug("[DMA] TCE %p set to 0x%016llx (dma addr: 0x%lx)\n",
+			  tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT);
+
+		uaddr += TCE_PAGE_SIZE;
+		index++;
+	}
+	return 0;
+}
+
+static void tce_free_wsp(struct iommu_table *tbl, long index, long npages)
+{
+	struct wsp_dma_table *ptbl = container_of(tbl,
+						    struct wsp_dma_table,
+						    table);
+#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+	struct pci_controller *hose = ptbl->phb->hose;
+#endif
+	u64 *tcep;
+
+	/* XXX Make this faster by factoring out the page address for
+	 * within a TCE table. Also use line-kill option to kill multiple
+	 * TCEs at once
+	 */
+	while (npages--) {
+		/* We don't use it->base as the table can be scattered */
+		tcep = (u64 *)page_address(ptbl->tces[index >> 16]);
+		tcep += (index & 0xffff);
+		dma_debug("[DMA] TCE %p cleared\n", tcep);
+		*tcep = 0;
+#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+		/* Don't write there since it would pollute other MMIO accesses */
+		out_be64(hose->cfg_data + PCIE_REG_TCE_KILL,
+			 PCIE_REG_TCEKILL_SINGLE | PCIE_REG_TCEKILL_PS_4K |
+			 (__pa(tcep) & PCIE_REG_TCEKILL_ADDR_MASK));
+#endif
+		index++;
+	}
+}
+
+static struct wsp_dma_table *wsp_pci_create_dma32_table(struct wsp_phb *phb,
+							    unsigned int region,
+							    struct pci_dev *validate)
+{
+	struct pci_controller *hose = phb->hose;
+	unsigned long size = phb->dma32_region_size;
+	unsigned long addr = phb->dma32_region_size * region + phb->dma32_base;
+	struct wsp_dma_table *tbl;
+	int tvts_per_table, i, tvt, nid;
+	unsigned long flags;
+
+	nid = of_node_to_nid(phb->hose->dn);
+
+	/* Calculate how many TVTs are needed */
+	tvts_per_table = size / 0x10000000;
+	if (tvts_per_table == 0)
+		tvts_per_table = 1;
+
+	/* Calculate the base TVT index. We know all tables have the same
+	 * size so we just do a simple multiply here
+	 */
+	tvt = region * tvts_per_table;
+
+	pr_debug("         Region : %d\n", region);
+	pr_debug("      DMA range : 0x%08lx..0x%08lx\n", addr, addr + size - 1);
+	pr_debug(" Number of TVTs : %d\n", tvts_per_table);
+	pr_debug("       Base TVT : %d\n", tvt);
+	pr_debug("         Node   : %d\n", nid);
+
+	tbl = kzalloc_node(sizeof(struct wsp_dma_table), GFP_KERNEL, nid);
+	if (!tbl)
+		return ERR_PTR(-ENOMEM);
+	tbl->phb = phb;
+
+	/* Create as many TVTs as needed, each represents 256M at most */
+	for (i = 0; i < tvts_per_table; i++) {
+		u64 tvt_data1, tvt_data0;
+
+		/* Allocate table. We use a 4K TCE size for now always so
+		 * one table is always 8 * (258M / 4K) == 512K
+		 */
+		tbl->tces[i] = alloc_pages_node(nid, GFP_KERNEL, get_order(0x80000));
+		if (tbl->tces[i] == NULL)
+			goto fail;
+		memset(page_address(tbl->tces[i]), 0, 0x80000);
+
+		pr_debug(" TCE table %d at : %p\n", i, page_address(tbl->tces[i]));
+
+		/* Table size. We currently set it to be the whole 256M region */
+		tvt_data0 = 2ull << IODA_TVT0_TCE_TABLE_SIZE_SHIFT;
+		/* IO page size set to 4K */
+		tvt_data1 = 1ull << IODA_TVT1_IO_PAGE_SIZE_SHIFT;
+		/* Shift in the address */
+		tvt_data0 |= __pa(page_address(tbl->tces[i])) << IODA_TVT0_TTA_SHIFT;
+
+		/* Validation stuff. We only validate fully bus/dev/fn for now
+		 * one day maybe we can group devices but that isn't the case
+		 * at the moment
+		 */
+		if (validate) {
+			tvt_data0 |= IODA_TVT0_BUSNUM_VALID_MASK;
+			tvt_data0 |= validate->bus->number;
+			tvt_data1 |= IODA_TVT1_DEVNUM_VALID;
+			tvt_data1 |= ((u64)PCI_SLOT(validate->devfn))
+				<< IODA_TVT1_DEVNUM_VALUE_SHIFT;
+			tvt_data1 |= IODA_TVT1_FUNCNUM_VALID;
+			tvt_data1 |= ((u64)PCI_FUNC(validate->devfn))
+				<< IODA_TVT1_FUNCNUM_VALUE_SHIFT;
+		}
+
+		/* XX PE number is always 0 for now */
+
+		/* Program the values using the PHB lock */
+		spin_lock_irqsave(&phb->lock, flags);
+		out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR,
+			 (tvt + i) | PCIE_REG_IODA_AD_TBL_TVT);
+		out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, tvt_data1);
+		out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, tvt_data0);
+		spin_unlock_irqrestore(&phb->lock, flags);
+	}
+
+	/* Init bits and pieces */
+	tbl->table.it_blocksize = 16;
+	tbl->table.it_offset = addr >> IOMMU_PAGE_SHIFT;
+	tbl->table.it_size = size >> IOMMU_PAGE_SHIFT;
+
+	/*
+	 * It's already blank but we clear it anyway.
+	 * Consider an aditiona interface that makes cleaing optional
+	 */
+	iommu_init_table(&tbl->table, nid);
+
+	list_add(&tbl->link, &phb->dma_tables);
+	return tbl;
+
+ fail:
+	pr_debug("  Failed to allocate a 256M TCE table !\n");
+	for (i = 0; i < tvts_per_table; i++)
+		if (tbl->tces[i])
+			__free_pages(tbl->tces[i], get_order(0x80000));
+	kfree(tbl);
+	return ERR_PTR(-ENOMEM);
+}
+
+static void __devinit wsp_pci_dma_dev_setup(struct pci_dev *pdev)
+{
+	struct dev_archdata *archdata = &pdev->dev.archdata;
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct wsp_phb *phb = hose->private_data;
+	struct wsp_dma_table *table = NULL;
+	unsigned long flags;
+	int i;
+
+	/* Don't assign an iommu table to a bridge */
+	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+		return;
+
+	pr_debug("%s: Setting up DMA...\n", pci_name(pdev));
+
+	spin_lock_irqsave(&phb->lock, flags);
+
+	/* If only one region, check if it already exist */
+	if (phb->dma32_num_regions == 1) {
+		spin_unlock_irqrestore(&phb->lock, flags);
+		if (list_empty(&phb->dma_tables))
+			table = wsp_pci_create_dma32_table(phb, 0, NULL);
+		else
+			table = list_first_entry(&phb->dma_tables,
+						 struct wsp_dma_table,
+						 link);
+	} else {
+		/* else find a free region */
+		for (i = 0; i < phb->dma32_num_regions && !table; i++) {
+			if (__test_and_set_bit(i, &phb->dma32_map))
+				continue;
+			spin_unlock_irqrestore(&phb->lock, flags);
+			table = wsp_pci_create_dma32_table(phb, i, pdev);
+		}
+	}
+
+	/* Check if we got an error */
+	if (IS_ERR(table)) {
+		pr_err("%s: Failed to create DMA table, err %ld !\n",
+		       pci_name(pdev), PTR_ERR(table));
+		return;
+	}
+
+	/* Or a valid table */
+	if (table) {
+		pr_info("%s: Setup iommu: 32-bit DMA region 0x%08lx..0x%08lx\n",
+			pci_name(pdev),
+			table->table.it_offset << IOMMU_PAGE_SHIFT,
+			(table->table.it_offset << IOMMU_PAGE_SHIFT)
+			+ phb->dma32_region_size - 1);
+		archdata->dma_data.iommu_table_base = &table->table;
+		return;
+	}
+
+	/* Or no room */
+	spin_unlock_irqrestore(&phb->lock, flags);
+	pr_err("%s: Out of DMA space !\n", pci_name(pdev));
+}
+
+static void __init wsp_pcie_configure_hw(struct pci_controller *hose)
+{
+	u64 val;
+	int i;
+
+#define DUMP_REG(x) \
+	pr_debug("%-30s : 0x%016llx\n", #x, in_be64(hose->cfg_data + x))
+
+#ifdef CONFIG_WSP_DD1_WORKAROUND_BAD_PCIE_CLASS
+	/* WSP DD1 has a bogus class code by default in the PCI-E
+	 * root complex's built-in P2P bridge */
+	val = in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1);
+	pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", val);
+	out_be64(hose->cfg_data + PCIE_REG_SYS_CFG1,
+		 (val & ~PCIE_REG_SYS_CFG1_CLASS_CODE) | (PCI_CLASS_BRIDGE_PCI << 8));
+	pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1));
+#endif /* CONFIG_WSP_DD1_WORKAROUND_BAD_PCIE_CLASS */
+
+#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+	/* XXX Disable TCE caching, it doesn't work on DD1 */
+	out_be64(hose->cfg_data + 0xe50,
+		 in_be64(hose->cfg_data + 0xe50) | (3ull << 62));
+	printk("PCI-E DEBUG CONTROL 5 = 0x%llx\n", in_be64(hose->cfg_data + 0xe50));
+#endif
+
+	/* Configure M32A and IO. IO is hard wired to be 1M for now */
+	out_be64(hose->cfg_data + PCIE_REG_IO_BASE_ADDR, hose->io_base_phys);
+	out_be64(hose->cfg_data + PCIE_REG_IO_BASE_MASK,
+		 (~(hose->io_resource.end - hose->io_resource.start)) &
+		 0x3fffffff000ul);
+	out_be64(hose->cfg_data + PCIE_REG_IO_START_ADDR, 0 | 1);
+
+	out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_ADDR,
+		 hose->mem_resources[0].start);
+	printk("Want to write to M32A_BASE_MASK : 0x%llx\n",
+		 (~(hose->mem_resources[0].end -
+		    hose->mem_resources[0].start)) & 0x3ffffff0000ul);
+	out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_MASK,
+		 (~(hose->mem_resources[0].end -
+		    hose->mem_resources[0].start)) & 0x3ffffff0000ul);
+	out_be64(hose->cfg_data + PCIE_REG_M32A_START_ADDR,
+		 (hose->mem_resources[0].start - hose->pci_mem_offset) | 1);
+
+	/* Clear all TVT entries
+	 *
+	 * XX Might get TVT count from device-tree
+	 */
+	for (i = 0; i < IODA_TVT_COUNT; i++) {
+		out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR,
+			 PCIE_REG_IODA_AD_TBL_TVT | i);
+		out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, 0);
+		out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, 0);
+	}
+
+	/* Kill the TCE cache */
+	out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG,
+		 in_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG) |
+		 PCIE_REG_PHBC_64B_TCE_EN);
+
+	/* Enable 32 & 64-bit MSIs, IO space and M32A */
+	val = PCIE_REG_PHBC_32BIT_MSI_EN |
+	      PCIE_REG_PHBC_IO_EN |
+	      PCIE_REG_PHBC_64BIT_MSI_EN |
+	      PCIE_REG_PHBC_M32A_EN;
+	if (iommu_is_off)
+		val |= PCIE_REG_PHBC_DMA_XLATE_BYPASS;
+	pr_debug("Will write config: 0x%llx\n", val);
+	out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG, val);
+
+	/* Enable error reporting */
+	out_be64(hose->cfg_data + 0xe00,
+		 in_be64(hose->cfg_data + 0xe00) | 0x0008000000000000ull);
+
+	/* Mask an error that's generated when doing config space probe
+	 *
+	 * XXX Maybe we should only mask it around config space cycles... that or
+	 * ignore it when we know we had a config space cycle recently ?
+	 */
+	out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS_MASK, 0x8000000000000000ull);
+	out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS_MASK, 0x8000000000000000ull);
+
+	/* Enable UTL errors, for now, all of them got to UTL irq 1
+	 *
+	 * We similarily mask one UTL error caused apparently during normal
+	 * probing. We also mask the link up error
+	 */
+	out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_ERR_SEV, 0);
+	out_be64(hose->cfg_data + PCIE_UTL_RC_ERR_SEVERITY, 0);
+	out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_ERROR_SEV, 0);
+	out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_IRQ_EN, 0xffffffff00000000ull);
+	out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_IRQ_EN, 0xff5fffff00000000ull);
+	out_be64(hose->cfg_data + PCIE_UTL_EP_ERR_IRQ_EN, 0xffffffff00000000ull);
+
+	DUMP_REG(PCIE_REG_IO_BASE_ADDR);
+	DUMP_REG(PCIE_REG_IO_BASE_MASK);
+	DUMP_REG(PCIE_REG_IO_START_ADDR);
+	DUMP_REG(PCIE_REG_M32A_BASE_ADDR);
+	DUMP_REG(PCIE_REG_M32A_BASE_MASK);
+	DUMP_REG(PCIE_REG_M32A_START_ADDR);
+	DUMP_REG(PCIE_REG_M32B_BASE_ADDR);
+	DUMP_REG(PCIE_REG_M32B_BASE_MASK);
+	DUMP_REG(PCIE_REG_M32B_START_ADDR);
+	DUMP_REG(PCIE_REG_M64_BASE_ADDR);
+	DUMP_REG(PCIE_REG_M64_BASE_MASK);
+	DUMP_REG(PCIE_REG_M64_START_ADDR);
+	DUMP_REG(PCIE_REG_PHB_CONFIG);
+}
+
+static void wsp_pci_wait_io_idle(struct wsp_phb *phb, unsigned long port)
+{
+	u64 val;
+	int i;
+
+	for (i = 0; i < 10000; i++) {
+		val = in_be64(phb->hose->cfg_data + 0xe08);
+		if ((val & 0x1900000000000000ull) == 0x0100000000000000ull)
+			return;
+		udelay(1);
+	}
+	pr_warning("PCI IO timeout on domain %d port 0x%lx\n",
+		   phb->hose->global_number, port);
+}
+
+#define DEF_PCI_AC_RET_pio(name, ret, at, al, aa)		\
+static ret wsp_pci_##name at					\
+{								\
+	struct iowa_bus *bus;					\
+	struct wsp_phb *phb;					\
+	unsigned long flags;					\
+	ret rval;						\
+	bus = iowa_pio_find_bus(aa);				\
+	WARN_ON(!bus);						\
+	phb = bus->private;					\
+	spin_lock_irqsave(&phb->lock, flags);			\
+	wsp_pci_wait_io_idle(phb, aa);				\
+	rval = __do_##name al;					\
+	spin_unlock_irqrestore(&phb->lock, flags);		\
+	return rval;						\
+}
+
+#define DEF_PCI_AC_NORET_pio(name, at, al, aa)			\
+static void wsp_pci_##name at					\
+{								\
+	struct iowa_bus *bus;					\
+	struct wsp_phb *phb;					\
+	unsigned long flags;					\
+	bus = iowa_pio_find_bus(aa);				\
+	WARN_ON(!bus);						\
+	phb = bus->private;					\
+	spin_lock_irqsave(&phb->lock, flags);			\
+	wsp_pci_wait_io_idle(phb, aa);				\
+	__do_##name al;						\
+	spin_unlock_irqrestore(&phb->lock, flags);		\
+}
+
+#define DEF_PCI_AC_RET_mem(name, ret, at, al, aa)
+#define DEF_PCI_AC_NORET_mem(name, at, al, aa)
+
+#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)		\
+	DEF_PCI_AC_RET_##space(name, ret, at, al, aa)
+
+#define DEF_PCI_AC_NORET(name, at, al, space, aa)		\
+	DEF_PCI_AC_NORET_##space(name, at, al, aa)		\
+
+
+#include <asm/io-defs.h>
+
+#undef DEF_PCI_AC_RET
+#undef DEF_PCI_AC_NORET
+
+static struct ppc_pci_io wsp_pci_iops = {
+	.inb = wsp_pci_inb,
+	.inw = wsp_pci_inw,
+	.inl = wsp_pci_inl,
+	.outb = wsp_pci_outb,
+	.outw = wsp_pci_outw,
+	.outl = wsp_pci_outl,
+	.insb = wsp_pci_insb,
+	.insw = wsp_pci_insw,
+	.insl = wsp_pci_insl,
+	.outsb = wsp_pci_outsb,
+	.outsw = wsp_pci_outsw,
+	.outsl = wsp_pci_outsl,
+};
+
+static int __init wsp_setup_one_phb(struct device_node *np)
+{
+	struct pci_controller *hose;
+	struct wsp_phb *phb;
+
+	pr_info("PCI: Setting up PCIe host bridge 0x%s\n", np->full_name);
+
+	phb = zalloc_maybe_bootmem(sizeof(struct wsp_phb), GFP_KERNEL);
+	if (!phb)
+		return -ENOMEM;
+	hose = pcibios_alloc_controller(np);
+	if (!hose) {
+		/* Can't really free the phb */
+		return -ENOMEM;
+	}
+	hose->private_data = phb;
+	phb->hose = hose;
+
+	INIT_LIST_HEAD(&phb->dma_tables);
+	spin_lock_init(&phb->lock);
+
+	/* XXX Use bus-range property ? */
+	hose->first_busno = 0;
+	hose->last_busno = 0xff;
+
+	/* We use cfg_data as the address for the whole bridge MMIO space
+	 */
+	hose->cfg_data = of_iomap(hose->dn, 0);
+
+	pr_debug("PCIe registers mapped at 0x%p\n", hose->cfg_data);
+
+	/* Get the ranges of the device-tree */
+	pci_process_bridge_OF_ranges(hose, np, 0);
+
+	/* XXX Force re-assigning of everything for now */
+	pci_add_flags(PCI_REASSIGN_ALL_BUS | PCI_REASSIGN_ALL_RSRC |
+		      PCI_ENABLE_PROC_DOMAINS);
+	pci_probe_only = 0;
+
+	/* Calculate how the TCE space is divided */
+	phb->dma32_base		= 0;
+	phb->dma32_num_regions	= NUM_DMA32_REGIONS;
+	if (phb->dma32_num_regions > MAX_TABLE_TVT_COUNT) {
+		pr_warning("IOMMU: Clamped to %d DMA32 regions\n",
+			   MAX_TABLE_TVT_COUNT);
+		phb->dma32_num_regions = MAX_TABLE_TVT_COUNT;
+	}
+	phb->dma32_region_size	= 0x80000000 / phb->dma32_num_regions;
+
+	BUG_ON(!is_power_of_2(phb->dma32_region_size));
+
+	/* Setup config ops */
+	hose->ops = &wsp_pcie_pci_ops;
+
+	/* Configure the HW */
+	wsp_pcie_configure_hw(hose);
+
+	/* Instanciate IO workarounds */
+	iowa_register_bus(hose, &wsp_pci_iops, NULL, phb);
+#ifdef CONFIG_PCI_MSI
+	wsp_setup_phb_msi(hose);
+#endif
+
+	/* Add to global list */
+	list_add(&phb->all, &wsp_phbs);
+
+	return 0;
+}
+
+void __init wsp_setup_pci(void)
+{
+	struct device_node *np;
+	int rc;
+
+	/* Find host bridges */
+	for_each_compatible_node(np, "pciex", PCIE_COMPATIBLE) {
+		rc = wsp_setup_one_phb(np);
+		if (rc)
+			pr_err("Failed to setup PCIe bridge %s, rc=%d\n",
+			       np->full_name, rc);
+	}
+
+	/* Establish device-tree linkage */
+	pci_devs_phb_init();
+
+	/* Set DMA ops to use TCEs */
+	if (iommu_is_off) {
+		pr_info("PCI-E: Disabled TCEs, using direct DMA\n");
+		set_pci_dma_ops(&dma_direct_ops);
+	} else {
+		ppc_md.pci_dma_dev_setup = wsp_pci_dma_dev_setup;
+		ppc_md.tce_build = tce_build_wsp;
+		ppc_md.tce_free = tce_free_wsp;
+		set_pci_dma_ops(&dma_iommu_ops);
+	}
+}
+
+#define err_debug(fmt...)	pr_debug(fmt)
+//#define err_debug(fmt...)
+
+static int __init wsp_pci_get_err_irq_no_dt(struct device_node *np)
+{
+	const u32 *prop;
+	int hw_irq;
+
+	/* Ok, no interrupts property, let's try to find our child P2P */
+	np = of_get_next_child(np, NULL);
+	if (np == NULL)
+		return 0;
+
+	/* Grab it's interrupt map */
+	prop = of_get_property(np, "interrupt-map", NULL);
+	if (prop == NULL)
+		return 0;
+
+	/* Grab one of the interrupts in there, keep the low 4 bits */
+	hw_irq = prop[5] & 0xf;
+
+	/* 0..4 for PHB 0 and 5..9 for PHB 1 */
+	if (hw_irq < 5)
+		hw_irq = 4;
+	else
+		hw_irq = 9;
+	hw_irq |= prop[5] & ~0xf;
+
+	err_debug("PCI: Using 0x%x as error IRQ for %s\n",
+		  hw_irq, np->parent->full_name);
+	return irq_create_mapping(NULL, hw_irq);
+}
+
+static const struct {
+	u32 offset;
+	const char *name;
+} wsp_pci_regs[] = {
+#define DREG(x) { PCIE_REG_##x, #x }
+#define DUTL(x) { PCIE_UTL_##x, "UTL_" #x }
+	/* Architected registers except CONFIG_ and IODA
+         * to avoid side effects
+	 */
+	DREG(DMA_CHAN_STATUS),
+	DREG(CPU_LOADSTORE_STATUS),
+	DREG(LOCK0),
+	DREG(LOCK1),
+	DREG(PHB_CONFIG),
+	DREG(IO_BASE_ADDR),
+	DREG(IO_BASE_MASK),
+	DREG(IO_START_ADDR),
+	DREG(M32A_BASE_ADDR),
+	DREG(M32A_BASE_MASK),
+	DREG(M32A_START_ADDR),
+	DREG(M32B_BASE_ADDR),
+	DREG(M32B_BASE_MASK),
+	DREG(M32B_START_ADDR),
+	DREG(M64_BASE_ADDR),
+	DREG(M64_BASE_MASK),
+	DREG(M64_START_ADDR),
+	DREG(TCE_KILL),
+	DREG(LOCK2),
+	DREG(PHB_GEN_CAP),
+	DREG(PHB_TCE_CAP),
+	DREG(PHB_IRQ_CAP),
+	DREG(PHB_EEH_CAP),
+	DREG(PAPR_ERR_INJ_CONTROL),
+	DREG(PAPR_ERR_INJ_ADDR),
+	DREG(PAPR_ERR_INJ_MASK),
+
+	/* UTL core regs */
+	DUTL(SYS_BUS_CONTROL),
+	DUTL(STATUS),
+	DUTL(SYS_BUS_AGENT_STATUS),
+	DUTL(SYS_BUS_AGENT_ERR_SEV),
+	DUTL(SYS_BUS_AGENT_IRQ_EN),
+	DUTL(SYS_BUS_BURST_SZ_CONF),
+	DUTL(REVISION_ID),
+	DUTL(OUT_POST_HDR_BUF_ALLOC),
+	DUTL(OUT_POST_DAT_BUF_ALLOC),
+	DUTL(IN_POST_HDR_BUF_ALLOC),
+	DUTL(IN_POST_DAT_BUF_ALLOC),
+	DUTL(OUT_NP_BUF_ALLOC),
+	DUTL(IN_NP_BUF_ALLOC),
+	DUTL(PCIE_TAGS_ALLOC),
+	DUTL(GBIF_READ_TAGS_ALLOC),
+
+	DUTL(PCIE_PORT_CONTROL),
+	DUTL(PCIE_PORT_STATUS),
+	DUTL(PCIE_PORT_ERROR_SEV),
+	DUTL(PCIE_PORT_IRQ_EN),
+	DUTL(RC_STATUS),
+	DUTL(RC_ERR_SEVERITY),
+	DUTL(RC_IRQ_EN),
+	DUTL(EP_STATUS),
+	DUTL(EP_ERR_SEVERITY),
+	DUTL(EP_ERR_IRQ_EN),
+	DUTL(PCI_PM_CTRL1),
+	DUTL(PCI_PM_CTRL2),
+
+	/* PCIe stack regs */
+	DREG(SYSTEM_CONFIG1),
+	DREG(SYSTEM_CONFIG2),
+	DREG(EP_SYSTEM_CONFIG),
+	DREG(EP_FLR),
+	DREG(EP_BAR_CONFIG),
+	DREG(LINK_CONFIG),
+	DREG(PM_CONFIG),
+	DREG(DLP_CONTROL),
+	DREG(DLP_STATUS),
+	DREG(ERR_REPORT_CONTROL),
+	DREG(SLOT_CONTROL1),
+	DREG(SLOT_CONTROL2),
+	DREG(UTL_CONFIG),
+	DREG(BUFFERS_CONFIG),
+	DREG(ERROR_INJECT),
+	DREG(SRIOV_CONFIG),
+	DREG(PF0_SRIOV_STATUS),
+	DREG(PF1_SRIOV_STATUS),
+	DREG(PORT_NUMBER),
+	DREG(POR_SYSTEM_CONFIG),
+
+	/* Internal logic regs */
+	DREG(PHB_VERSION),
+	DREG(RESET),
+	DREG(PHB_CONTROL),
+	DREG(PHB_TIMEOUT_CONTROL1),
+	DREG(PHB_QUIESCE_DMA),
+	DREG(PHB_DMA_READ_TAG_ACTV),
+	DREG(PHB_TCE_READ_TAG_ACTV),
+
+	/* FIR registers */
+	DREG(LEM_FIR_ACCUM),
+	DREG(LEM_FIR_AND_MASK),
+	DREG(LEM_FIR_OR_MASK),
+	DREG(LEM_ACTION0),
+	DREG(LEM_ACTION1),
+	DREG(LEM_ERROR_MASK),
+	DREG(LEM_ERROR_AND_MASK),
+	DREG(LEM_ERROR_OR_MASK),
+
+	/* Error traps registers */
+	DREG(PHB_ERR_STATUS),
+	DREG(PHB_ERR_STATUS),
+	DREG(PHB_ERR1_STATUS),
+	DREG(PHB_ERR_INJECT),
+	DREG(PHB_ERR_LEM_ENABLE),
+	DREG(PHB_ERR_IRQ_ENABLE),
+	DREG(PHB_ERR_FREEZE_ENABLE),
+	DREG(PHB_ERR_SIDE_ENABLE),
+	DREG(PHB_ERR_LOG_0),
+	DREG(PHB_ERR_LOG_1),
+	DREG(PHB_ERR_STATUS_MASK),
+	DREG(PHB_ERR1_STATUS_MASK),
+	DREG(MMIO_ERR_STATUS),
+	DREG(MMIO_ERR1_STATUS),
+	DREG(MMIO_ERR_INJECT),
+	DREG(MMIO_ERR_LEM_ENABLE),
+	DREG(MMIO_ERR_IRQ_ENABLE),
+	DREG(MMIO_ERR_FREEZE_ENABLE),
+	DREG(MMIO_ERR_SIDE_ENABLE),
+	DREG(MMIO_ERR_LOG_0),
+	DREG(MMIO_ERR_LOG_1),
+	DREG(MMIO_ERR_STATUS_MASK),
+	DREG(MMIO_ERR1_STATUS_MASK),
+	DREG(DMA_ERR_STATUS),
+	DREG(DMA_ERR1_STATUS),
+	DREG(DMA_ERR_INJECT),
+	DREG(DMA_ERR_LEM_ENABLE),
+	DREG(DMA_ERR_IRQ_ENABLE),
+	DREG(DMA_ERR_FREEZE_ENABLE),
+	DREG(DMA_ERR_SIDE_ENABLE),
+	DREG(DMA_ERR_LOG_0),
+	DREG(DMA_ERR_LOG_1),
+	DREG(DMA_ERR_STATUS_MASK),
+	DREG(DMA_ERR1_STATUS_MASK),
+
+	/* Debug and Trace registers */
+	DREG(PHB_DEBUG_CONTROL0),
+	DREG(PHB_DEBUG_STATUS0),
+	DREG(PHB_DEBUG_CONTROL1),
+	DREG(PHB_DEBUG_STATUS1),
+	DREG(PHB_DEBUG_CONTROL2),
+	DREG(PHB_DEBUG_STATUS2),
+	DREG(PHB_DEBUG_CONTROL3),
+	DREG(PHB_DEBUG_STATUS3),
+	DREG(PHB_DEBUG_CONTROL4),
+	DREG(PHB_DEBUG_STATUS4),
+	DREG(PHB_DEBUG_CONTROL5),
+	DREG(PHB_DEBUG_STATUS5),
+
+	/* Don't seem to exist ...
+	DREG(PHB_DEBUG_CONTROL6),
+	DREG(PHB_DEBUG_STATUS6),
+	*/
+};
+
+static int wsp_pci_regs_show(struct seq_file *m, void *private)
+{
+	struct wsp_phb *phb = m->private;
+	struct pci_controller *hose = phb->hose;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) {
+		/* Skip write-only regs */
+		if (wsp_pci_regs[i].offset == 0xc08 ||
+		    wsp_pci_regs[i].offset == 0xc10 ||
+		    wsp_pci_regs[i].offset == 0xc38 ||
+		    wsp_pci_regs[i].offset == 0xc40)
+			continue;
+		seq_printf(m, "0x%03x: 0x%016llx %s\n",
+			   wsp_pci_regs[i].offset,
+			   in_be64(hose->cfg_data + wsp_pci_regs[i].offset),
+			   wsp_pci_regs[i].name);
+	}
+	return 0;
+}
+
+static int wsp_pci_regs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wsp_pci_regs_show, inode->i_private);
+}
+
+static const struct file_operations wsp_pci_regs_fops = {
+	.open = wsp_pci_regs_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int wsp_pci_reg_set(void *data, u64 val)
+{
+	out_be64((void __iomem *)data, val);
+	return 0;
+}
+
+static int wsp_pci_reg_get(void *data, u64 *val)
+{
+	*val = in_be64((void __iomem *)data);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(wsp_pci_reg_fops, wsp_pci_reg_get, wsp_pci_reg_set, "0x%llx\n");
+
+static irqreturn_t wsp_pci_err_irq(int irq, void *dev_id)
+{
+	struct wsp_phb *phb = dev_id;
+	struct pci_controller *hose = phb->hose;
+	irqreturn_t handled = IRQ_NONE;
+	struct wsp_pcie_err_log_data ed;
+
+	pr_err("PCI: Error interrupt on %s (PHB %d)\n",
+	       hose->dn->full_name, hose->global_number);
+ again:
+	memset(&ed, 0, sizeof(ed));
+
+	/* Read and clear UTL errors */
+	ed.utl_sys_err = in_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS);
+	if (ed.utl_sys_err)
+		out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS, ed.utl_sys_err);
+	ed.utl_port_err = in_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS);
+	if (ed.utl_port_err)
+		out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS, ed.utl_port_err);
+	ed.utl_rc_err = in_be64(hose->cfg_data + PCIE_UTL_RC_STATUS);
+	if (ed.utl_rc_err)
+		out_be64(hose->cfg_data + PCIE_UTL_RC_STATUS, ed.utl_rc_err);
+
+	/* Read and clear main trap errors */
+	ed.phb_err = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS);
+	if (ed.phb_err) {
+		ed.phb_err1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS);
+		ed.phb_log0 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_0);
+		ed.phb_log1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_1);
+		out_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS, 0);
+		out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS, 0);
+	}
+	ed.mmio_err = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS);
+	if (ed.mmio_err) {
+		ed.mmio_err1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS);
+		ed.mmio_log0 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_0);
+		ed.mmio_log1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_1);
+		out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS, 0);
+		out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS, 0);
+	}
+	ed.dma_err = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS);
+	if (ed.dma_err) {
+		ed.dma_err1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS);
+		ed.dma_log0 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_0);
+		ed.dma_log1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_1);
+		out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS, 0);
+		out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS, 0);
+	}
+
+	/* Now print things out */
+	if (ed.phb_err) {
+		pr_err("   PHB Error Status      : 0x%016llx\n", ed.phb_err);
+		pr_err("   PHB First Error Status: 0x%016llx\n", ed.phb_err1);
+		pr_err("   PHB Error Log 0       : 0x%016llx\n", ed.phb_log0);
+		pr_err("   PHB Error Log 1       : 0x%016llx\n", ed.phb_log1);
+	}
+	if (ed.mmio_err) {
+		pr_err("  MMIO Error Status      : 0x%016llx\n", ed.mmio_err);
+		pr_err("  MMIO First Error Status: 0x%016llx\n", ed.mmio_err1);
+		pr_err("  MMIO Error Log 0       : 0x%016llx\n", ed.mmio_log0);
+		pr_err("  MMIO Error Log 1       : 0x%016llx\n", ed.mmio_log1);
+	}
+	if (ed.dma_err) {
+		pr_err("   DMA Error Status      : 0x%016llx\n", ed.dma_err);
+		pr_err("   DMA First Error Status: 0x%016llx\n", ed.dma_err1);
+		pr_err("   DMA Error Log 0       : 0x%016llx\n", ed.dma_log0);
+		pr_err("   DMA Error Log 1       : 0x%016llx\n", ed.dma_log1);
+	}
+	if (ed.utl_sys_err)
+		pr_err("   UTL Sys Error Status  : 0x%016llx\n", ed.utl_sys_err);
+	if (ed.utl_port_err)
+		pr_err("   UTL Port Error Status : 0x%016llx\n", ed.utl_port_err);
+	if (ed.utl_rc_err)
+		pr_err("   UTL RC Error Status   : 0x%016llx\n", ed.utl_rc_err);
+
+	/* Interrupts are caused by the error traps. If we had any error there
+	 * we loop again in case the UTL buffered some new stuff between
+	 * going there and going to the traps
+	 */
+	if (ed.dma_err || ed.mmio_err || ed.phb_err) {
+		handled = IRQ_HANDLED;
+		goto again;
+	}
+	return handled;
+}
+
+static void __init wsp_setup_pci_err_reporting(struct wsp_phb *phb)
+{
+	struct pci_controller *hose = phb->hose;
+	int err_irq, i, rc;
+	char fname[16];
+
+	/* Create a debugfs file for that PHB */
+	sprintf(fname, "phb%d", phb->hose->global_number);
+	phb->ddir = debugfs_create_dir(fname, powerpc_debugfs_root);
+
+	/* Some useful debug output */
+	if (phb->ddir) {
+		struct dentry *d = debugfs_create_dir("regs", phb->ddir);
+		char tmp[64];
+
+		for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) {
+			sprintf(tmp, "%03x_%s", wsp_pci_regs[i].offset,
+				wsp_pci_regs[i].name);
+			debugfs_create_file(tmp, 0600, d,
+					    hose->cfg_data + wsp_pci_regs[i].offset,
+					    &wsp_pci_reg_fops);
+		}
+		debugfs_create_file("all_regs", 0600, phb->ddir, phb, &wsp_pci_regs_fops);
+	}
+
+	/* Find the IRQ number for that PHB */
+	err_irq = irq_of_parse_and_map(hose->dn, 0);
+	if (err_irq == 0)
+		/* XXX Error IRQ lacking from device-tree */
+		err_irq = wsp_pci_get_err_irq_no_dt(hose->dn);
+	if (err_irq == 0) {
+		pr_err("PCI: Failed to fetch error interrupt for %s\n",
+		       hose->dn->full_name);
+		return;
+	}
+	/* Request it */
+	rc = request_irq(err_irq, wsp_pci_err_irq, 0, "wsp_pci error", phb);
+	if (rc) {
+		pr_err("PCI: Failed to request interrupt for %s\n",
+		       hose->dn->full_name);
+	}
+	/* Enable interrupts for all errors for now */
+	out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
+	out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
+	out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
+}
+
+/*
+ * This is called later to hookup with the error interrupt
+ */
+static int __init wsp_setup_pci_late(void)
+{
+	struct wsp_phb *phb;
+
+	list_for_each_entry(phb, &wsp_phbs, all)
+		wsp_setup_pci_err_reporting(phb);
+
+	return 0;
+}
+arch_initcall(wsp_setup_pci_late);
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.h b/arch/powerpc/platforms/wsp/wsp_pci.h
new file mode 100644
index 000000000000..52e9bd95250d
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/wsp_pci.h
@@ -0,0 +1,268 @@
+/*
+ * Copyright 2010 Ben Herrenschmidt, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __WSP_PCI_H
+#define __WSP_PCI_H
+
+/* Architected registers */
+#define PCIE_REG_DMA_CHAN_STATUS	0x110
+#define PCIE_REG_CPU_LOADSTORE_STATUS	0x120
+
+#define PCIE_REG_CONFIG_DATA		0x130
+#define PCIE_REG_LOCK0			0x138
+#define PCIE_REG_CONFIG_ADDRESS		0x140
+#define   PCIE_REG_CA_ENABLE			0x8000000000000000ull
+#define	  PCIE_REG_CA_BUS_MASK			0x0ff0000000000000ull
+#define   PCIE_REG_CA_BUS_SHIFT			(20+32)
+#define   PCIE_REG_CA_DEV_MASK			0x000f800000000000ull
+#define   PCIE_REG_CA_DEV_SHIFT			(15+32)
+#define   PCIE_REG_CA_FUNC_MASK			0x0000700000000000ull
+#define   PCIE_REG_CA_FUNC_SHIFT		(12+32)
+#define   PCIE_REG_CA_REG_MASK			0x00000fff00000000ull
+#define   PCIE_REG_CA_REG_SHIFT			( 0+32)
+#define   PCIE_REG_CA_BE_MASK			0x00000000f0000000ull
+#define   PCIE_REG_CA_BE_SHIFT			(   28)
+#define PCIE_REG_LOCK1			0x148
+
+#define PCIE_REG_PHB_CONFIG		0x160
+#define   PCIE_REG_PHBC_64B_TCE_EN		0x2000000000000000ull
+#define   PCIE_REG_PHBC_MMIO_DMA_FREEZE_EN	0x1000000000000000ull
+#define   PCIE_REG_PHBC_32BIT_MSI_EN		0x0080000000000000ull
+#define   PCIE_REG_PHBC_M64_EN			0x0040000000000000ull
+#define   PCIE_REG_PHBC_IO_EN			0x0008000000000000ull
+#define   PCIE_REG_PHBC_64BIT_MSI_EN		0x0002000000000000ull
+#define   PCIE_REG_PHBC_M32A_EN			0x0000800000000000ull
+#define   PCIE_REG_PHBC_M32B_EN			0x0000400000000000ull
+#define   PCIE_REG_PHBC_MSI_PE_VALIDATE		0x0000200000000000ull
+#define   PCIE_REG_PHBC_DMA_XLATE_BYPASS	0x0000100000000000ull
+
+#define PCIE_REG_IO_BASE_ADDR		0x170
+#define PCIE_REG_IO_BASE_MASK		0x178
+#define PCIE_REG_IO_START_ADDR		0x180
+
+#define PCIE_REG_M32A_BASE_ADDR		0x190
+#define PCIE_REG_M32A_BASE_MASK		0x198
+#define PCIE_REG_M32A_START_ADDR	0x1a0
+
+#define PCIE_REG_M32B_BASE_ADDR		0x1b0
+#define PCIE_REG_M32B_BASE_MASK		0x1b8
+#define PCIE_REG_M32B_START_ADDR	0x1c0
+
+#define PCIE_REG_M64_BASE_ADDR		0x1e0
+#define PCIE_REG_M64_BASE_MASK		0x1e8
+#define PCIE_REG_M64_START_ADDR		0x1f0
+
+#define PCIE_REG_TCE_KILL		0x210
+#define   PCIE_REG_TCEKILL_SINGLE	0x8000000000000000ull
+#define   PCIE_REG_TCEKILL_ADDR_MASK	0x000003fffffffff8ull
+#define   PCIE_REG_TCEKILL_PS_4K	0
+#define   PCIE_REG_TCEKILL_PS_64K	1
+#define   PCIE_REG_TCEKILL_PS_16M	2
+#define   PCIE_REG_TCEKILL_PS_16G	3
+
+#define PCIE_REG_IODA_ADDR		0x220
+#define   PCIE_REG_IODA_AD_AUTOINC	0x8000000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_MVT	0x0005000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_PELT	0x0006000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_PESTA	0x0007000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_PESTB	0x0008000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_TVT	0x0009000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_TCE	0x000a000000000000ull
+#define PCIE_REG_IODA_DATA0		0x228
+#define PCIE_REG_IODA_DATA1		0x230
+
+#define PCIE_REG_LOCK2			0x240
+
+#define PCIE_REG_PHB_GEN_CAP		0x250
+#define PCIE_REG_PHB_TCE_CAP		0x258
+#define PCIE_REG_PHB_IRQ_CAP		0x260
+#define PCIE_REG_PHB_EEH_CAP		0x268
+
+#define PCIE_REG_PAPR_ERR_INJ_CONTROL	0x2b0
+#define PCIE_REG_PAPR_ERR_INJ_ADDR	0x2b8
+#define PCIE_REG_PAPR_ERR_INJ_MASK	0x2c0
+
+
+#define PCIE_REG_SYS_CFG1		0x600
+#define   PCIE_REG_SYS_CFG1_CLASS_CODE	0x0000000000ffffffull
+
+#define IODA_TVT0_TTA_MASK		0x000fffffffff0000ull
+#define IODA_TVT0_TTA_SHIFT		4
+#define IODA_TVT0_BUSNUM_VALID_MASK	0x000000000000e000ull
+#define IODA_TVT0_TCE_TABLE_SIZE_MASK	0x0000000000001f00ull
+#define IODA_TVT0_TCE_TABLE_SIZE_SHIFT	8
+#define IODA_TVT0_BUSNUM_VALUE_MASK	0x00000000000000ffull
+#define IODA_TVT0_BUSNUM_VALID_SHIFT	0
+#define IODA_TVT1_DEVNUM_VALID		0x2000000000000000ull
+#define IODA_TVT1_DEVNUM_VALUE_MASK	0x1f00000000000000ull
+#define IODA_TVT1_DEVNUM_VALUE_SHIFT	56
+#define IODA_TVT1_FUNCNUM_VALID		0x0008000000000000ull
+#define IODA_TVT1_FUNCNUM_VALUE_MASK	0x0007000000000000ull
+#define IODA_TVT1_FUNCNUM_VALUE_SHIFT	48
+#define IODA_TVT1_IO_PAGE_SIZE_MASK	0x00001f0000000000ull
+#define IODA_TVT1_IO_PAGE_SIZE_SHIFT	40
+#define IODA_TVT1_PE_NUMBER_MASK	0x000000000000003full
+#define IODA_TVT1_PE_NUMBER_SHIFT	0
+
+#define IODA_TVT_COUNT			64
+
+/* UTL Core registers */
+#define PCIE_UTL_SYS_BUS_CONTROL	0x400
+#define PCIE_UTL_STATUS			0x408
+#define PCIE_UTL_SYS_BUS_AGENT_STATUS	0x410
+#define PCIE_UTL_SYS_BUS_AGENT_ERR_SEV	0x418
+#define PCIE_UTL_SYS_BUS_AGENT_IRQ_EN	0x420
+#define PCIE_UTL_SYS_BUS_BURST_SZ_CONF	0x440
+#define PCIE_UTL_REVISION_ID		0x448
+
+#define PCIE_UTL_OUT_POST_HDR_BUF_ALLOC	0x4c0
+#define PCIE_UTL_OUT_POST_DAT_BUF_ALLOC	0x4d0
+#define PCIE_UTL_IN_POST_HDR_BUF_ALLOC	0x4e0
+#define PCIE_UTL_IN_POST_DAT_BUF_ALLOC	0x4f0
+#define PCIE_UTL_OUT_NP_BUF_ALLOC	0x500
+#define PCIE_UTL_IN_NP_BUF_ALLOC	0x510
+#define PCIE_UTL_PCIE_TAGS_ALLOC	0x520
+#define PCIE_UTL_GBIF_READ_TAGS_ALLOC	0x530
+
+#define PCIE_UTL_PCIE_PORT_CONTROL	0x540
+#define PCIE_UTL_PCIE_PORT_STATUS	0x548
+#define PCIE_UTL_PCIE_PORT_ERROR_SEV	0x550
+#define PCIE_UTL_PCIE_PORT_IRQ_EN	0x558
+#define PCIE_UTL_RC_STATUS		0x560
+#define PCIE_UTL_RC_ERR_SEVERITY	0x568
+#define PCIE_UTL_RC_IRQ_EN		0x570
+#define PCIE_UTL_EP_STATUS		0x578
+#define PCIE_UTL_EP_ERR_SEVERITY	0x580
+#define PCIE_UTL_EP_ERR_IRQ_EN		0x588
+
+#define PCIE_UTL_PCI_PM_CTRL1		0x590
+#define PCIE_UTL_PCI_PM_CTRL2		0x598
+
+/* PCIe stack registers */
+#define PCIE_REG_SYSTEM_CONFIG1		0x600
+#define PCIE_REG_SYSTEM_CONFIG2		0x608
+#define PCIE_REG_EP_SYSTEM_CONFIG	0x618
+#define PCIE_REG_EP_FLR			0x620
+#define PCIE_REG_EP_BAR_CONFIG		0x628
+#define PCIE_REG_LINK_CONFIG		0x630
+#define PCIE_REG_PM_CONFIG		0x640
+#define PCIE_REG_DLP_CONTROL		0x650
+#define PCIE_REG_DLP_STATUS		0x658
+#define PCIE_REG_ERR_REPORT_CONTROL	0x660
+#define PCIE_REG_SLOT_CONTROL1		0x670
+#define PCIE_REG_SLOT_CONTROL2		0x678
+#define PCIE_REG_UTL_CONFIG		0x680
+#define PCIE_REG_BUFFERS_CONFIG		0x690
+#define PCIE_REG_ERROR_INJECT		0x698
+#define PCIE_REG_SRIOV_CONFIG		0x6a0
+#define PCIE_REG_PF0_SRIOV_STATUS	0x6a8
+#define PCIE_REG_PF1_SRIOV_STATUS	0x6b0
+#define PCIE_REG_PORT_NUMBER		0x700
+#define PCIE_REG_POR_SYSTEM_CONFIG	0x708
+
+/* PHB internal logic registers */
+#define PCIE_REG_PHB_VERSION		0x800
+#define PCIE_REG_RESET			0x808
+#define PCIE_REG_PHB_CONTROL		0x810
+#define PCIE_REG_PHB_TIMEOUT_CONTROL1	0x878
+#define PCIE_REG_PHB_QUIESCE_DMA	0x888
+#define PCIE_REG_PHB_DMA_READ_TAG_ACTV	0x900
+#define PCIE_REG_PHB_TCE_READ_TAG_ACTV	0x908
+
+/* FIR registers */
+#define PCIE_REG_LEM_FIR_ACCUM		0xc00
+#define PCIE_REG_LEM_FIR_AND_MASK	0xc08
+#define PCIE_REG_LEM_FIR_OR_MASK	0xc10
+#define PCIE_REG_LEM_ACTION0		0xc18
+#define PCIE_REG_LEM_ACTION1		0xc20
+#define PCIE_REG_LEM_ERROR_MASK		0xc30
+#define PCIE_REG_LEM_ERROR_AND_MASK	0xc38
+#define PCIE_REG_LEM_ERROR_OR_MASK	0xc40
+
+/* PHB Error registers */
+#define PCIE_REG_PHB_ERR_STATUS		0xc80
+#define PCIE_REG_PHB_ERR1_STATUS	0xc88
+#define PCIE_REG_PHB_ERR_INJECT		0xc90
+#define PCIE_REG_PHB_ERR_LEM_ENABLE	0xc98
+#define PCIE_REG_PHB_ERR_IRQ_ENABLE	0xca0
+#define PCIE_REG_PHB_ERR_FREEZE_ENABLE	0xca8
+#define PCIE_REG_PHB_ERR_SIDE_ENABLE	0xcb8
+#define PCIE_REG_PHB_ERR_LOG_0		0xcc0
+#define PCIE_REG_PHB_ERR_LOG_1		0xcc8
+#define PCIE_REG_PHB_ERR_STATUS_MASK	0xcd0
+#define PCIE_REG_PHB_ERR1_STATUS_MASK	0xcd8
+
+#define PCIE_REG_MMIO_ERR_STATUS	0xd00
+#define PCIE_REG_MMIO_ERR1_STATUS	0xd08
+#define PCIE_REG_MMIO_ERR_INJECT	0xd10
+#define PCIE_REG_MMIO_ERR_LEM_ENABLE	0xd18
+#define PCIE_REG_MMIO_ERR_IRQ_ENABLE	0xd20
+#define PCIE_REG_MMIO_ERR_FREEZE_ENABLE	0xd28
+#define PCIE_REG_MMIO_ERR_SIDE_ENABLE	0xd38
+#define PCIE_REG_MMIO_ERR_LOG_0		0xd40
+#define PCIE_REG_MMIO_ERR_LOG_1		0xd48
+#define PCIE_REG_MMIO_ERR_STATUS_MASK	0xd50
+#define PCIE_REG_MMIO_ERR1_STATUS_MASK	0xd58
+
+#define PCIE_REG_DMA_ERR_STATUS		0xd80
+#define PCIE_REG_DMA_ERR1_STATUS	0xd88
+#define PCIE_REG_DMA_ERR_INJECT		0xd90
+#define PCIE_REG_DMA_ERR_LEM_ENABLE	0xd98
+#define PCIE_REG_DMA_ERR_IRQ_ENABLE	0xda0
+#define PCIE_REG_DMA_ERR_FREEZE_ENABLE	0xda8
+#define PCIE_REG_DMA_ERR_SIDE_ENABLE	0xdb8
+#define PCIE_REG_DMA_ERR_LOG_0		0xdc0
+#define PCIE_REG_DMA_ERR_LOG_1		0xdc8
+#define PCIE_REG_DMA_ERR_STATUS_MASK	0xdd0
+#define PCIE_REG_DMA_ERR1_STATUS_MASK	0xdd8
+
+/* Shortcuts for access to the above using the PHB definitions
+ * with an offset
+ */
+#define PCIE_REG_ERR_PHB_OFFSET		0x0
+#define PCIE_REG_ERR_MMIO_OFFSET	0x80
+#define PCIE_REG_ERR_DMA_OFFSET		0x100
+
+/* Debug and Trace registers */
+#define PCIE_REG_PHB_DEBUG_CONTROL0	0xe00
+#define PCIE_REG_PHB_DEBUG_STATUS0	0xe08
+#define PCIE_REG_PHB_DEBUG_CONTROL1	0xe10
+#define PCIE_REG_PHB_DEBUG_STATUS1	0xe18
+#define PCIE_REG_PHB_DEBUG_CONTROL2	0xe20
+#define PCIE_REG_PHB_DEBUG_STATUS2	0xe28
+#define PCIE_REG_PHB_DEBUG_CONTROL3	0xe30
+#define PCIE_REG_PHB_DEBUG_STATUS3	0xe38
+#define PCIE_REG_PHB_DEBUG_CONTROL4	0xe40
+#define PCIE_REG_PHB_DEBUG_STATUS4	0xe48
+#define PCIE_REG_PHB_DEBUG_CONTROL5	0xe50
+#define PCIE_REG_PHB_DEBUG_STATUS5	0xe58
+#define PCIE_REG_PHB_DEBUG_CONTROL6	0xe60
+#define PCIE_REG_PHB_DEBUG_STATUS6	0xe68
+
+/* Definition for PCIe errors */
+struct wsp_pcie_err_log_data {
+	__u64	phb_err;
+	__u64	phb_err1;
+	__u64	phb_log0;
+	__u64	phb_log1;
+	__u64	mmio_err;
+	__u64	mmio_err1;
+	__u64	mmio_log0;
+	__u64	mmio_log1;
+	__u64	dma_err;
+	__u64	dma_err1;
+	__u64	dma_log0;
+	__u64	dma_log1;
+	__u64	utl_sys_err;
+	__u64	utl_port_err;
+	__u64	utl_rc_err;
+	__u64	unused;
+};
+
+#endif /* __WSP_PCI_H */