Merge remote-tracking branch 'linus/master' into merge

Conflicts: Documentation/hwmon/ina2xx arch/powerpc/Kconfig arch/powerpc/boot/dts/b4860emu.dts arch/powerpc/boot/dts/b4qds.dtsi arch/powerpc/boot/dts/fsl/b4si-post.dtsi arch/powerpc/boot/dts/fsl/qoriq-sec6.0-0.dtsi arch/powerpc/boot/dts/p1023rdb.dts arch/powerpc/boot/dts/t4240emu.dts arch/powerpc/boot/dts/t4240qds.dts arch/powerpc/configs/85xx/p1023_defconfig arch/powerpc/configs/corenet32_smp_defconfig arch/powerpc/configs/corenet64_smp_defconfig arch/powerpc/configs/mpc85xx_smp_defconfig arch/powerpc/include/asm/cputable.h arch/powerpc/include/asm/device.h arch/powerpc/include/asm/epapr_hcalls.h arch/powerpc/include/asm/kvm_host.h arch/powerpc/include/asm/mpic.h arch/powerpc/include/asm/pci.h arch/powerpc/include/asm/ppc-opcode.h arch/powerpc/include/asm/ppc_asm.h arch/powerpc/include/asm/reg_booke.h arch/powerpc/kernel/epapr_paravirt.c arch/powerpc/kernel/process.c arch/powerpc/kernel/prom.c arch/powerpc/kernel/setup-common.c arch/powerpc/kernel/setup_32.c arch/powerpc/kernel/setup_64.c arch/powerpc/kernel/smp.c arch/powerpc/kernel/swsusp_asm64.S arch/powerpc/kernel/swsusp_booke.S arch/powerpc/kvm/book3s_pr.c arch/powerpc/kvm/booke.c arch/powerpc/kvm/booke.h arch/powerpc/kvm/e500.c arch/powerpc/kvm/e500.h arch/powerpc/kvm/e500_emulate.c arch/powerpc/kvm/e500mc.c arch/powerpc/kvm/powerpc.c arch/powerpc/perf/e6500-pmu.c arch/powerpc/platforms/85xx/Kconfig arch/powerpc/platforms/85xx/Makefile arch/powerpc/platforms/85xx/b4_qds.c arch/powerpc/platforms/85xx/c293pcie.c arch/powerpc/platforms/85xx/corenet_ds.c arch/powerpc/platforms/85xx/corenet_ds.h arch/powerpc/platforms/85xx/p1023_rds.c arch/powerpc/platforms/85xx/p2041_rdb.c arch/powerpc/platforms/85xx/p3041_ds.c arch/powerpc/platforms/85xx/p4080_ds.c arch/powerpc/platforms/85xx/p5020_ds.c arch/powerpc/platforms/85xx/p5040_ds.c arch/powerpc/platforms/85xx/smp.c arch/powerpc/platforms/85xx/t4240_qds.c arch/powerpc/platforms/Kconfig arch/powerpc/sysdev/Makefile arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c arch/powerpc/sysdev/fsl_msi.c arch/powerpc/sysdev/fsl_pci.c arch/powerpc/sysdev/fsl_pci.h arch/powerpc/sysdev/fsl_soc.h arch/powerpc/sysdev/mpic.c arch/powerpc/sysdev/mpic_timer.c drivers/Kconfig drivers/clk/Kconfig drivers/clk/clk-ppc-corenet.c drivers/cpufreq/Kconfig.powerpc drivers/cpufreq/Makefile drivers/cpufreq/ppc-corenet-cpufreq.c drivers/crypto/caam/Kconfig drivers/crypto/caam/Makefile drivers/crypto/caam/ctrl.c drivers/crypto/caam/desc_constr.h drivers/crypto/caam/intern.h drivers/crypto/caam/jr.c drivers/crypto/caam/regs.h drivers/dma/fsldma.c drivers/hwmon/ina2xx.c drivers/iommu/Kconfig drivers/iommu/fsl_pamu.c drivers/iommu/fsl_pamu.h drivers/iommu/fsl_pamu_domain.c drivers/iommu/fsl_pamu_domain.h drivers/misc/Makefile drivers/mmc/card/block.c drivers/mmc/core/core.c drivers/mmc/host/sdhci-esdhc.h drivers/mmc/host/sdhci-pltfm.c drivers/mtd/nand/fsl_ifc_nand.c drivers/net/ethernet/freescale/gianfar.c drivers/net/ethernet/freescale/gianfar.h drivers/net/ethernet/freescale/gianfar_ethtool.c drivers/net/phy/at803x.c drivers/net/phy/phy_device.c drivers/net/phy/vitesse.c drivers/pci/msi.c drivers/staging/Kconfig drivers/staging/Makefile drivers/uio/Kconfig drivers/uio/Makefile drivers/uio/uio.c drivers/usb/host/ehci-fsl.c drivers/vfio/Kconfig drivers/vfio/Makefile include/crypto/algapi.h include/linux/iommu.h include/linux/mmc/sdhci.h include/linux/msi.h include/linux/netdev_features.h include/linux/phy.h include/linux/skbuff.h include/net/ip.h include/uapi/linux/vfio.h net/core/ethtool.c net/ipv4/route.c net/ipv6/route.c
author: Scott Wood <scottwood@freescale.com> 2013-12-14 01:15:24 (GMT)
committer: Scott Wood <scottwood@freescale.com> 2013-12-14 01:15:24 (GMT)
commit: b7c81aa3ab2ac2c140e278b6d0e9a0b95112cf0b (patch)
tree: 87828aaf5f82c7042bfc0307bc4ac499e10f93fb /arch/powerpc/platforms
parent: 22c782a4b14773fab7eab3c1db54ad7ad077e9b8 (diff)
parent: 78fd82238d0e5716578c326404184a27ba67fd6e (diff)
download: linux-fsl-qoriq-b7c81aa3ab2ac2c140e278b6d0e9a0b95112cf0b.tar.xz
129 files changed, 5094 insertions, 6467 deletions
diff --git a/arch/powerpc/platforms/44x/currituck.c b/arch/powerpc/platforms/44x/currituck.c
index ecd3890..7f1b71a 100644
--- a/arch/powerpc/platforms/44x/currituck.c
+++ b/arch/powerpc/platforms/44x/currituck.c
@@ -91,12 +91,12 @@ static void __init ppc47x_init_irq(void)
 }
 
 #ifdef CONFIG_SMP
-static void __cpuinit smp_ppc47x_setup_cpu(int cpu)
+static void smp_ppc47x_setup_cpu(int cpu)
 {
 	mpic_setup_this_cpu();
 }
 
-static int __cpuinit smp_ppc47x_kick_cpu(int cpu)
+static int smp_ppc47x_kick_cpu(int cpu)
 {
 	struct device_node *cpunode = of_get_cpu_node(cpu, NULL);
 	const u64 *spin_table_addr_prop;
@@ -176,13 +176,48 @@ static int __init ppc47x_probe(void)
 	return 1;
 }
 
+static int board_rev = -1;
+static int __init ppc47x_get_board_rev(void)
+{
+	u8 fpga_reg0;
+	void *fpga;
+	struct device_node *np;
+
+	np = of_find_compatible_node(NULL, NULL, "ibm,currituck-fpga");
+	if (!np)
+		goto fail;
+
+	fpga = of_iomap(np, 0);
+	of_node_put(np);
+	if (!fpga)
+		goto fail;
+
+	fpga_reg0 = ioread8(fpga);
+	board_rev = fpga_reg0 & 0x03;
+	pr_info("%s: Found board revision %d\n", __func__, board_rev);
+	iounmap(fpga);
+	return 0;
+
+fail:
+	pr_info("%s: Unable to find board revision\n", __func__);
+	return 0;
+}
+machine_arch_initcall(ppc47x, ppc47x_get_board_rev);
+
 /* Use USB controller should have been hardware swizzled but it wasn't :( */
 static void ppc47x_pci_irq_fixup(struct pci_dev *dev)
 {
 	if (dev->vendor == 0x1033 && (dev->device == 0x0035 ||
 	                              dev->device == 0x00e0)) {
-		dev->irq = irq_create_mapping(NULL, 47);
-		pr_info("%s: Mapping irq 47 %d\n", __func__, dev->irq);
+		if (board_rev == 0) {
+			dev->irq = irq_create_mapping(NULL, 47);
+			pr_info("%s: Mapping irq %d\n", __func__, dev->irq);
+		} else if (board_rev == 2) {
+			dev->irq = irq_create_mapping(NULL, 49);
+			pr_info("%s: Mapping irq %d\n", __func__, dev->irq);
+		} else {
+			pr_alert("%s: Unknown board revision\n", __func__);
+		}
 	}
 }
 
diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c
index a28a862..4241bc8 100644
--- a/arch/powerpc/platforms/44x/iss4xx.c
+++ b/arch/powerpc/platforms/44x/iss4xx.c
@@ -81,12 +81,12 @@ static void __init iss4xx_init_irq(void)
 }
 
 #ifdef CONFIG_SMP
-static void __cpuinit smp_iss4xx_setup_cpu(int cpu)
+static void smp_iss4xx_setup_cpu(int cpu)
 {
 	mpic_setup_this_cpu();
 }
 
-static int __cpuinit smp_iss4xx_kick_cpu(int cpu)
+static int smp_iss4xx_kick_cpu(int cpu)
 {
 	struct device_node *cpunode = of_get_cpu_node(cpu, NULL);
 	const u64 *spin_table_addr_prop;
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index 4cfa499..534574a 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -16,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/of_gpio.h>
-#include <linux/of_i2c.h>
 #include <linux/slab.h>
 #include <linux/export.h>
 
diff --git a/arch/powerpc/platforms/512x/clock.c b/arch/powerpc/platforms/512x/clock.c
index e504166..fd8a376 100644
--- a/arch/powerpc/platforms/512x/clock.c
+++ b/arch/powerpc/platforms/512x/clock.c
@@ -24,6 +24,7 @@
 #include <linux/mutex.h>
 #include <linux/io.h>
 
+#include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <asm/mpc5xxx.h>
 #include <asm/mpc5121.h>
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads.c b/arch/powerpc/platforms/512x/mpc5121_ads.c
index 0a134e0..3e90ece 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads.c
@@ -43,9 +43,7 @@ static void __init mpc5121_ads_setup_arch(void)
 		mpc83xx_add_bridge(np);
 #endif
 
-#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
-	mpc512x_setup_diu();
-#endif
+	mpc512x_setup_arch();
 }
 
 static void __init mpc5121_ads_init_IRQ(void)
@@ -69,7 +67,7 @@ define_machine(mpc5121_ads) {
 	.probe			= mpc5121_ads_probe,
 	.setup_arch		= mpc5121_ads_setup_arch,
 	.init			= mpc512x_init,
-	.init_early		= mpc512x_init_diu,
+	.init_early		= mpc512x_init_early,
 	.init_IRQ		= mpc5121_ads_init_IRQ,
 	.get_irq		= ipic_get_irq,
 	.calibrate_decr		= generic_calibrate_decr,
diff --git a/arch/powerpc/platforms/512x/mpc512x.h b/arch/powerpc/platforms/512x/mpc512x.h
index 0a8e600..cc97f02 100644
--- a/arch/powerpc/platforms/512x/mpc512x.h
+++ b/arch/powerpc/platforms/512x/mpc512x.h
@@ -12,18 +12,12 @@
 #ifndef __MPC512X_H__
 #define __MPC512X_H__
 extern void __init mpc512x_init_IRQ(void);
+extern void __init mpc512x_init_early(void);
 extern void __init mpc512x_init(void);
+extern void __init mpc512x_setup_arch(void);
 extern int __init mpc5121_clk_init(void);
-void __init mpc512x_declare_of_platform_devices(void);
 extern const char *mpc512x_select_psc_compat(void);
+extern const char *mpc512x_select_reset_compat(void);
 extern void mpc512x_restart(char *cmd);
 
-#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
-void mpc512x_init_diu(void);
-void mpc512x_setup_diu(void);
-#else
-#define mpc512x_init_diu NULL
-#define mpc512x_setup_diu NULL
-#endif
-
 #endif				/* __MPC512X_H__ */
diff --git a/arch/powerpc/platforms/512x/mpc512x_generic.c b/arch/powerpc/platforms/512x/mpc512x_generic.c
index 5fb919b..ce71408 100644
--- a/arch/powerpc/platforms/512x/mpc512x_generic.c
+++ b/arch/powerpc/platforms/512x/mpc512x_generic.c
@@ -45,8 +45,8 @@ define_machine(mpc512x_generic) {
 	.name			= "MPC512x generic",
 	.probe			= mpc512x_generic_probe,
 	.init			= mpc512x_init,
-	.init_early		= mpc512x_init_diu,
-	.setup_arch		= mpc512x_setup_diu,
+	.init_early		= mpc512x_init_early,
+	.setup_arch		= mpc512x_setup_arch,
 	.init_IRQ		= mpc512x_init_IRQ,
 	.get_irq		= ipic_get_irq,
 	.calibrate_decr		= generic_calibrate_decr,
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index 6eb94ab..36b5652 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -35,8 +35,10 @@ static struct mpc512x_reset_module __iomem *reset_module_base;
 static void __init mpc512x_restart_init(void)
 {
 	struct device_node *np;
+	const char *reset_compat;
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-reset");
+	reset_compat = mpc512x_select_reset_compat();
+	np = of_find_compatible_node(NULL, NULL, reset_compat);
 	if (!np)
 		return;
 
@@ -58,8 +60,6 @@ void mpc512x_restart(char *cmd)
 		;
 }
 
-#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
-
 struct fsl_diu_shared_fb {
 	u8		gamma[0x300];	/* 32-bit aligned! */
 	struct diu_ad	ad0;		/* 32-bit aligned! */
@@ -69,7 +69,7 @@ struct fsl_diu_shared_fb {
 };
 
 #define DIU_DIV_MASK	0x000000ff
-void mpc512x_set_pixel_clock(unsigned int pixclock)
+static void mpc512x_set_pixel_clock(unsigned int pixclock)
 {
 	unsigned long bestval, bestfreq, speed, busfreq;
 	unsigned long minpixclock, maxpixclock, pixval;
@@ -162,7 +162,7 @@ void mpc512x_set_pixel_clock(unsigned int pixclock)
 	iounmap(ccm);
 }
 
-enum fsl_diu_monitor_port
+static enum fsl_diu_monitor_port
 mpc512x_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
 	return FSL_DIU_PORT_DVI;
@@ -177,7 +177,7 @@ static inline void mpc512x_free_bootmem(struct page *page)
 	free_reserved_page(page);
 }
 
-void mpc512x_release_bootmem(void)
+static void mpc512x_release_bootmem(void)
 {
 	unsigned long addr = diu_shared_fb.fb_phys & PAGE_MASK;
 	unsigned long size = diu_shared_fb.fb_len;
@@ -203,7 +203,7 @@ void mpc512x_release_bootmem(void)
  * address range will be reserved in setup_arch() after bootmem
  * allocator is up.
  */
-void __init mpc512x_init_diu(void)
+static void __init mpc512x_init_diu(void)
 {
 	struct device_node *np;
 	struct diu __iomem *diu_reg;
@@ -272,7 +272,7 @@ out:
 	iounmap(diu_reg);
 }
 
-void __init mpc512x_setup_diu(void)
+static void __init mpc512x_setup_diu(void)
 {
 	int ret;
 
@@ -301,8 +301,6 @@ void __init mpc512x_setup_diu(void)
 	diu_ops.release_bootmem		= mpc512x_release_bootmem;
 }
 
-#endif
-
 void __init mpc512x_init_IRQ(void)
 {
 	struct device_node *np;
@@ -335,7 +333,7 @@ static struct of_device_id __initdata of_bus_ids[] = {
 	{},
 };
 
-void __init mpc512x_declare_of_platform_devices(void)
+static void __init mpc512x_declare_of_platform_devices(void)
 {
 	if (of_platform_bus_probe(NULL, of_bus_ids, NULL))
 		printk(KERN_ERR __FILE__ ": "
@@ -355,6 +353,17 @@ const char *mpc512x_select_psc_compat(void)
 	return NULL;
 }
 
+const char *mpc512x_select_reset_compat(void)
+{
+	if (of_machine_is_compatible("fsl,mpc5121"))
+		return "fsl,mpc5121-reset";
+
+	if (of_machine_is_compatible("fsl,mpc5125"))
+		return "fsl,mpc5125-reset";
+
+	return NULL;
+}
+
 static unsigned int __init get_fifo_size(struct device_node *np,
 					 char *prop_name)
 {
@@ -374,7 +383,7 @@ static unsigned int __init get_fifo_size(struct device_node *np,
 		    ((u32)(_base) + sizeof(struct mpc52xx_psc)))
 
 /* Init PSC FIFO space for TX and RX slices */
-void __init mpc512x_psc_fifo_init(void)
+static void __init mpc512x_psc_fifo_init(void)
 {
 	struct device_node *np;
 	void __iomem *psc;
@@ -436,14 +445,26 @@ void __init mpc512x_psc_fifo_init(void)
 	}
 }
 
+void __init mpc512x_init_early(void)
+{
+	mpc512x_restart_init();
+	if (IS_ENABLED(CONFIG_FB_FSL_DIU))
+		mpc512x_init_diu();
+}
+
 void __init mpc512x_init(void)
 {
 	mpc5121_clk_init();
 	mpc512x_declare_of_platform_devices();
-	mpc512x_restart_init();
 	mpc512x_psc_fifo_init();
 }
 
+void __init mpc512x_setup_arch(void)
+{
+	if (IS_ENABLED(CONFIG_FB_FSL_DIU))
+		mpc512x_setup_diu();
+}
+
 /**
  * mpc512x_cs_config - Setup chip select configuration
  * @cs: chip select number
diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c
index 0575e85..116f2325 100644
--- a/arch/powerpc/platforms/512x/pdm360ng.c
+++ b/arch/powerpc/platforms/512x/pdm360ng.c
@@ -14,6 +14,8 @@
 
 #include <linux/kernel.h>
 #include <linux/io.h>
+#include <linux/of_address.h>
+#include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 
 #include <asm/machdep.h>
@@ -119,9 +121,9 @@ static int __init pdm360ng_probe(void)
 define_machine(pdm360ng) {
 	.name			= "PDM360NG",
 	.probe			= pdm360ng_probe,
-	.setup_arch		= mpc512x_setup_diu,
+	.setup_arch		= mpc512x_setup_arch,
 	.init			= pdm360ng_init,
-	.init_early		= mpc512x_init_diu,
+	.init_early		= mpc512x_init_early,
 	.init_IRQ		= mpc512x_init_IRQ,
 	.get_irq		= ipic_get_irq,
 	.calibrate_decr		= generic_calibrate_decr,
diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig
index 90f4496..af54174 100644
--- a/arch/powerpc/platforms/52xx/Kconfig
+++ b/arch/powerpc/platforms/52xx/Kconfig
@@ -57,5 +57,5 @@ config PPC_MPC5200_BUGFIX
 
 config PPC_MPC5200_LPBFIFO
 	tristate "MPC5200 LocalPlus bus FIFO driver"
-	depends on PPC_MPC52xx
+	depends on PPC_MPC52xx && PPC_BESTCOMM
 	select PPC_BESTCOMM_GEN_BD
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index b89ef65..2898b73 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -340,7 +340,7 @@ static int mpc52xx_irqhost_map(struct irq_domain *h, unsigned int virq,
 {
 	int l1irq;
 	int l2irq;
-	struct irq_chip *irqchip;
+	struct irq_chip *uninitialized_var(irqchip);
 	void *hndlr;
 	int type;
 	u32 reg;
diff --git a/arch/powerpc/platforms/82xx/mpc8272_ads.c b/arch/powerpc/platforms/82xx/mpc8272_ads.c
index 30394b4..6a14cf5 100644
--- a/arch/powerpc/platforms/82xx/mpc8272_ads.c
+++ b/arch/powerpc/platforms/82xx/mpc8272_ads.c
@@ -16,6 +16,8 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/fsl_devices.h>
+#include <linux/of_address.h>
+#include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 #include <linux/io.h>
 
diff --git a/arch/powerpc/platforms/82xx/pq2fads.c b/arch/powerpc/platforms/82xx/pq2fads.c
index e1dceee..e5f82ec 100644
--- a/arch/powerpc/platforms/82xx/pq2fads.c
+++ b/arch/powerpc/platforms/82xx/pq2fads.c
@@ -15,6 +15,8 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/fsl_devices.h>
+#include <linux/of_address.h>
+#include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 
 #include <asm/io.h>
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index 624cb51..fd71cfd 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -204,7 +204,6 @@ static int mcu_remove(struct i2c_client *client)
 	ret = mcu_gpiochip_remove(mcu);
 	if (ret)
 		return ret;
-	i2c_set_clientdata(client, NULL);
 	kfree(mcu);
 	return 0;
 }
@@ -231,17 +230,7 @@ static struct i2c_driver mcu_driver = {
 	.id_table = mcu_ids,
 };
 
-static int __init mcu_init(void)
-{
-	return i2c_add_driver(&mcu_driver);
-}
-module_init(mcu_init);
-
-static void __exit mcu_exit(void)
-{
-	i2c_del_driver(&mcu_driver);
-}
-module_exit(mcu_exit);
+module_i2c_driver(mcu_driver);
 
 MODULE_DESCRIPTION("Power Management and GPIO expander driver for "
 		   "MPC8349E-mITX-compatible MCU");
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index 1d769a2..3d9716c 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -20,6 +20,8 @@
 #include <linux/freezer.h>
 #include <linux/suspend.h>
 #include <linux/fsl_devices.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/export.h>
 
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 60afff1..25d7580 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -42,7 +42,6 @@ config BSC9132_QDS
 config C293_PCIE
 	  bool "Freescale C293PCIE"
 	  select DEFAULT_UIMAGE
-	  select SWIOTLB
 	  help
 	  This option enables support for the C293PCIE board
 
@@ -132,10 +131,10 @@ config P1023_RDB
 	  This option enables support for the P1023 RDB board
 
 config P1023_RDS
-	bool "Freescale P1023 RDS"
+	bool "Freescale P1023 RDS/RDB"
 	select DEFAULT_UIMAGE
 	help
-	  This option enables support for the P1023 RDS board
+	  This option enables support for the P1023 RDS and RDB boards
 
 config TWR_P102x
 	bool "Freescale TWR-P102x"
@@ -238,96 +237,16 @@ config GE_IMP3A
 	  This board is a 3U CompactPCI Single Board Computer with a Freescale
 	  P2020 processor.
 
-config P2041_RDB
-	bool "Freescale P2041 RDB"
-	select DEFAULT_UIMAGE
-	select PPC_E500MC
-	select PHYS_64BIT
-	select SWIOTLB
-	select ARCH_REQUIRE_GPIOLIB
-	select GPIO_MPC8XXX
-	select HAS_RAPIDIO
-	select PPC_EPAPR_HV_PIC
-        select HAS_FSL_QBMAN
-	help
-	  This option enables support for the P2041 RDB board
-
-config P3041_DS
-	bool "Freescale P3041 DS"
-	select DEFAULT_UIMAGE
-	select PPC_E500MC
-	select PHYS_64BIT
-	select SWIOTLB
-	select ARCH_REQUIRE_GPIOLIB
-	select GPIO_MPC8XXX
-	select HAS_RAPIDIO
-	select PPC_EPAPR_HV_PIC
-        select HAS_FSL_QBMAN
-	select MDIO_BUS_MUX if FSL_DPAA_ETH
-	select MDIO_BUS_MUX_MMIOREG if FSL_DPAA_ETH
-	help
-	  This option enables support for the P3041 DS board
-
-config P4080_DS
-	bool "Freescale P4080 DS"
-	select DEFAULT_UIMAGE
-	select PPC_E500MC
-	select PHYS_64BIT
-	select SWIOTLB
-	select ARCH_REQUIRE_GPIOLIB
-	select GPIO_MPC8XXX
-	select HAS_RAPIDIO
-	select PPC_EPAPR_HV_PIC
-        select HAS_FSL_QBMAN
-	select MDIO_BUS_MUX if FSL_DPAA_ETH
-	select MDIO_BUS_MUX_GPIO
-	help
-	  This option enables support for the P4080 DS board
-
 config SGY_CTS1000
 	tristate "Servergy CTS-1000 support"
 	select GPIOLIB
 	select OF_GPIO
-	depends on P4080_DS
+	depends on CORENET_GENERIC
 	help
 	  Enable this to support functionality in Servergy's CTS-1000 systems.
 
 endif # PPC32
 
-config P5020_DS
-	bool "Freescale P5020 DS"
-	select DEFAULT_UIMAGE
-	select E500
-	select PPC_E500MC
-	select PHYS_64BIT
-	select SWIOTLB
-	select ARCH_REQUIRE_GPIOLIB
-	select GPIO_MPC8XXX
-	select HAS_RAPIDIO
-	select PPC_EPAPR_HV_PIC
-        select HAS_FSL_QBMAN
-	select MDIO_BUS_MUX if FSL_DPAA_ETH
-	select MDIO_BUS_MUX_MMIOREG if FSL_DPAA_ETH
-	help
-	  This option enables support for the P5020 DS board
-
-config P5040_DS
-	bool "Freescale P5040 DS"
-	select DEFAULT_UIMAGE
-	select E500
-	select PPC_E500MC
-	select PHYS_64BIT
-	select SWIOTLB
-	select ARCH_REQUIRE_GPIOLIB
-	select GPIO_MPC8XXX
-	select HAS_RAPIDIO
-	select PPC_EPAPR_HV_PIC
-        select HAS_FSL_QBMAN
-	select MDIO_BUS_MUX if FSL_DPAA_ETH
-	select MDIO_BUS_MUX_MMIOREG if FSL_DPAA_ETH
-	help
-	  This option enables support for the P5040 DS board
-
 config PPC_QEMU_E500
 	bool "QEMU generic e500 platform"
 	select DEFAULT_UIMAGE
@@ -343,10 +262,8 @@ config PPC_QEMU_E500
 	  unset based on the emulated CPU (or actual host CPU in the case
 	  of KVM).
 
-if PPC64
-
-config T4240_QDS
-	bool "Freescale T4240 QDS"
+config CORENET_GENERIC
+	bool "Freescale CoreNet Generic"
 	select DEFAULT_UIMAGE
 	select E500
 	select PPC_E500MC
@@ -360,28 +277,14 @@ config T4240_QDS
 	select MDIO_BUS_MUX if FSL_DPAA_ETH
 	select MDIO_BUS_MUX_MMIOREG if FSL_DPAA_ETH
 	help
-	  This option enables support for the T4240 QDS board
-
-config B4_QDS
-	bool "Freescale B4 QDS"
-	select DEFAULT_UIMAGE
-	select E500
-	select PPC_E500MC
-	select PHYS_64BIT
-	select SWIOTLB
-	select GPIOLIB
-	select ARCH_REQUIRE_GPIOLIB
-	select HAS_RAPIDIO
-	select PPC_EPAPR_HV_PIC
-	select MDIO_BUS_MUX if FSL_DPAA_ETH
-	select MDIO_BUS_MUX_MMIOREG if FSL_DPAA_ETH
-	help
-	  This option enables support for the B4 QDS board
-	  The B4 application development system B4 QDS is a complete
-	  debugging environment intended for engineers developing
-	  applications for the B4.
+	  This option enables support for the FSL CoreNet based boards.
+	  For 32bit kernel, the following boards are supported:
+	    P2041 RDB, P3041 DS and P4080 DS
+	  For 64bit kernel, the following boards are supported:
+	    T4240 QDS and B4 QDS
+	  The following boards are supported for both 32bit and 64bit kernel:
+	    P5020 DS and P5040 DS
 
-endif
 endif # FSL_SOC_BOOKE
 
 config TQM85xx
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index 05ed088..f385b5c 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -24,13 +24,7 @@ obj-$(CONFIG_P1022_DS)    += p1022_ds.o
 obj-$(CONFIG_P1022_RDK)   += p1022_rdk.o
 obj-$(CONFIG_P1023_RDS)   += p1023_rds.o
 obj-$(CONFIG_TWR_P102x)   += twr_p102x.o
-obj-$(CONFIG_P2041_RDB)   += p2041_rdb.o corenet_ds.o
-obj-$(CONFIG_P3041_DS)    += p3041_ds.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-$(CONFIG_P5040_DS)    += p5040_ds.o corenet_ds.o
-obj-$(CONFIG_T4240_QDS)   += t4240_qds.o corenet_ds.o
-obj-$(CONFIG_B4_QDS)	  += b4_qds.o corenet_ds.o
+obj-$(CONFIG_CORENET_GENERIC)   += corenet_generic.o
 obj-$(CONFIG_STX_GP3)	  += stx_gp3.o
 obj-$(CONFIG_TQM85xx)	  += tqm85xx.o
 obj-$(CONFIG_SBC8548)     += sbc8548.o
diff --git a/arch/powerpc/platforms/85xx/b4_qds.c b/arch/powerpc/platforms/85xx/b4_qds.c
deleted file mode 100644
index d4b6a2c..0000000
--- a/arch/powerpc/platforms/85xx/b4_qds.c
+++ /dev/null
@@ -1,92 +0,0 @@
-/*
- * B4 QDS Setup
- * Should apply for QDS platform of B4860 and it's personalities.
- * viz B4860/B4420/B4220QDS
- *
- * Copyright 2012 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/pci.h>
-#include <linux/kdev_t.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/phy.h>
-
-#include <asm/time.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <mm/mmu_decl.h>
-#include <asm/prom.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 b4_qds_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	if ((of_flat_dt_is_compatible(root, "fsl,B4860QDS")) ||
-		(of_flat_dt_is_compatible(root, "fsl,B4420QDS")) ||
-			(of_flat_dt_is_compatible(root, "fsl,B4220QDS")))
-		return 1;
-
-	/* Check if we're running under the Freescale hypervisor */
-	if ((of_flat_dt_is_compatible(root, "fsl,B4860QDS-hv")) ||
-		(of_flat_dt_is_compatible(root, "fsl,B4420QDS-hv")) ||
-			(of_flat_dt_is_compatible(root, "fsl,B4220QDS-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;
-		return 1;
-	}
-
-	return 0;
-}
-
-define_machine(b4_qds) {
-	.name			= "B4 QDS",
-	.probe			= b4_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
-/* coreint doesn't play nice with lazy EE, use legacy mpic for now */
-#ifdef CONFIG_PPC64
-	.get_irq		= mpic_get_irq,
-#else
-	.get_irq		= mpic_get_coreint_irq,
-#endif
-	.restart		= fsl_rstcr_restart,
-	.calibrate_decr		= generic_calibrate_decr,
-	.progress		= udbg_progress,
-#ifdef CONFIG_PPC64
-	.power_save		= book3e_idle,
-#else
-	.power_save		= e500_idle,
-#endif
-	.init_early             = corenet_ds_init_early,
-};
-
-machine_arch_initcall(b4_qds, corenet_ds_publish_devices);
-
-#ifdef CONFIG_SWIOTLB
-machine_arch_initcall(b4_qds, swiotlb_setup_bus_notifier);
-#endif
diff --git a/arch/powerpc/platforms/85xx/c293pcie.c b/arch/powerpc/platforms/85xx/c293pcie.c
index 75dda12..213d5b8 100644
--- a/arch/powerpc/platforms/85xx/c293pcie.c
+++ b/arch/powerpc/platforms/85xx/c293pcie.c
@@ -11,16 +11,10 @@
 
 #include <linux/stddef.h>
 #include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
+#include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 
-#include <asm/time.h>
 #include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <mm/mmu_decl.h>
-#include <asm/prom.h>
 #include <asm/udbg.h>
 #include <asm/mpic.h>
 
diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c
index f63c10d..d694407 100644
--- a/arch/powerpc/platforms/85xx/common.c
+++ b/arch/powerpc/platforms/85xx/common.c
@@ -5,6 +5,8 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+
+#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 
 #include <sysdev/cpm2_pic.h>
diff --git a/arch/powerpc/platforms/85xx/corenet_ds.h b/arch/powerpc/platforms/85xx/corenet_ds.h
deleted file mode 100644
index a5b63c6..0000000
--- a/arch/powerpc/platforms/85xx/corenet_ds.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Corenet based SoC DS Setup
- *
- * Copyright 2009 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 version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#ifndef CORENET_DS_H
-#define CORENET_DS_H
-
-extern void __init corenet_ds_pic_init(void);
-extern void __init corenet_ds_setup_arch(void);
-extern int __init corenet_ds_publish_devices(void);
-extern void __init corenet_ds_init_early(void);
-
-#endif
diff --git a/arch/powerpc/platforms/85xx/corenet_ds.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index 004ffb4..30a5c43 100644
--- a/arch/powerpc/platforms/85xx/corenet_ds.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -5,8 +5,8 @@
  *
  * Copyright 2009-2011 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
+ * 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.
  */
@@ -25,6 +25,7 @@
 #include <asm/prom.h>
 #include <asm/udbg.h>
 #include <asm/mpic.h>
+#include <asm/ehv_pic.h>
 
 #include <linux/of_platform.h>
 #include <sysdev/fsl_soc.h>
@@ -33,7 +34,7 @@
 
 #include <linux/fsl_usdpaa.h>
 
-void __init corenet_ds_pic_init(void)
+void __init corenet_gen_pic_init(void)
 {
 	struct mpic *mpic;
 	unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU |
@@ -51,16 +52,10 @@ void __init corenet_ds_pic_init(void)
 /*
  * Setup the architecture
  */
-void __init corenet_ds_setup_arch(void)
+void __init corenet_gen_setup_arch(void)
 {
 	mpc85xx_smp_init();
 
-#if defined(CONFIG_PCI) && defined(CONFIG_PPC64)
-	pci_devs_phb_init();
-#endif
-
-	fsl_pci_assign_primary();
-
 	swiotlb_detect_4g();
 
 	pr_info("%s board from Freescale Semiconductor\n", ppc_md.name);
@@ -68,7 +63,7 @@ void __init corenet_ds_setup_arch(void)
 
 static const struct of_device_id of_device_ids[] = {
 	{
-		.compatible	= "simple-bus",
+		.compatible	= "simple-bus"
 	},
 	{
 		.compatible	= "fsl,dpaa",
@@ -110,11 +105,60 @@ static const struct of_device_id of_device_ids[] = {
 	{}
 };
 
-int __init corenet_ds_publish_devices(void)
+int __init corenet_gen_publish_devices(void)
 {
 	return of_platform_bus_probe(NULL, of_device_ids, NULL);
 }
 
+static const char * const boards[] __initconst = {
+	"fsl,P2041RDB",
+	"fsl,P3041DS",
+	"fsl,P4080DS",
+	"fsl,P5020DS",
+	"fsl,P5040DS",
+	"fsl,T4240QDS",
+	"fsl,B4860QDS",
+	"fsl,B4420QDS",
+	"fsl,B4220QDS",
+	NULL
+};
+
+static const char * const hv_boards[] __initconst = {
+	"fsl,P2041RDB-hv",
+	"fsl,P3041DS-hv",
+	"fsl,P4080DS-hv",
+	"fsl,P5020DS-hv",
+	"fsl,P5040DS-hv",
+	"fsl,T4240QDS-hv",
+	"fsl,B4860QDS-hv",
+	"fsl,B4420QDS-hv",
+	"fsl,B4220QDS-hv",
+	NULL
+};
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init corenet_generic_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	if (of_flat_dt_match(root, boards))
+		return 1;
+
+	/* Check if we're running under the Freescale hypervisor */
+	if (of_flat_dt_match(root, hv_boards)) {
+		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;
+		return 1;
+	}
+
+	return 0;
+}
+
 /* Early setup is required for large chunks of contiguous (and coarsely-aligned)
  * memory. The following shoe-horns Q/Bman "init_early" calls into the
  * platform setup to let them parse their CCSR nodes early on. */
@@ -128,7 +172,7 @@ void __init bman_init_early(void);
 void __init pme2_init_early(void);
 #endif
 
-__init void corenet_ds_init_early(void)
+static __init void corenet_ds_init_early(void)
 {
 #ifdef CONFIG_FSL_QMAN_CONFIG
 	qman_init_early();
@@ -143,3 +187,29 @@ __init void corenet_ds_init_early(void)
 	fsl_usdpaa_init_early();
 #endif
 }
+
+define_machine(corenet_generic) {
+	.name			= "CoreNet Generic",
+	.probe			= corenet_generic_probe,
+	.setup_arch		= corenet_gen_setup_arch,
+	.init_IRQ		= corenet_gen_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,
+#ifdef CONFIG_PPC64
+	.power_save		= book3e_idle,
+#else
+	.power_save		= e500_idle,
+#endif
+	.init_early		= corenet_ds_init_early,
+};
+
+machine_arch_initcall(corenet_generic, corenet_gen_publish_devices);
+
+#ifdef CONFIG_SWIOTLB
+machine_arch_initcall(corenet_generic, swiotlb_setup_bus_notifier);
+#endif
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index 0252961..d6a3dd3 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -66,6 +66,8 @@ static int __init p1010_rdb_probe(void)
 
 	if (of_flat_dt_is_compatible(root, "fsl,P1010RDB"))
 		return 1;
+	if (of_flat_dt_is_compatible(root, "fsl,P1010RDB-PB"))
+		return 1;
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/85xx/p2041_rdb.c b/arch/powerpc/platforms/85xx/p2041_rdb.c
deleted file mode 100644
index 9ee8758..0000000
--- a/arch/powerpc/platforms/85xx/p2041_rdb.c
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * P2041 RDB 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/pci.h>
-#include <linux/kdev_t.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/phy.h>
-
-#include <asm/time.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <mm/mmu_decl.h>
-#include <asm/prom.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 p2041_rdb_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	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,P2041RDB-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;
-		return 1;
-	}
-
-	return 0;
-}
-
-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
-	.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,
-	.init_early		= corenet_ds_init_early,
-};
-
-machine_arch_initcall(p2041_rdb, corenet_ds_publish_devices);
-
-#ifdef CONFIG_SWIOTLB
-machine_arch_initcall(p2041_rdb, swiotlb_setup_bus_notifier);
-#endif
diff --git a/arch/powerpc/platforms/85xx/p3041_ds.c b/arch/powerpc/platforms/85xx/p3041_ds.c
deleted file mode 100644
index b8af7fb..0000000
--- a/arch/powerpc/platforms/85xx/p3041_ds.c
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * P3041 DS Setup
- *
- * Maintained by Kumar Gala (see MAINTAINERS for contact information)
- *
- * Copyright 2009-2010 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/pci.h>
-#include <linux/kdev_t.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/phy.h>
-
-#include <asm/time.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <mm/mmu_decl.h>
-#include <asm/prom.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 p3041_ds_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,P3041DS"))
-		return 1;
-
-	/* Check if we're running under the Freescale hypervisor */
-	if (of_flat_dt_is_compatible(root, "fsl,P3041DS-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;
-		return 1;
-	}
-
-	return 0;
-}
-
-define_machine(p3041_ds) {
-	.name			= "P3041 DS",
-	.probe			= p3041_ds_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,
-	.init_early		= corenet_ds_init_early,
-};
-
-machine_arch_initcall(p3041_ds, corenet_ds_publish_devices);
-
-#ifdef CONFIG_SWIOTLB
-machine_arch_initcall(p3041_ds, swiotlb_setup_bus_notifier);
-#endif
diff --git a/arch/powerpc/platforms/85xx/p4080_ds.c b/arch/powerpc/platforms/85xx/p4080_ds.c
deleted file mode 100644
index d83b8d0..0000000
--- a/arch/powerpc/platforms/85xx/p4080_ds.c
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * P4080 DS Setup
- *
- * Maintained by Kumar Gala (see MAINTAINERS for contact information)
- *
- * Copyright 2009 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/pci.h>
-#include <linux/kdev_t.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-
-#include <asm/time.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <mm/mmu_decl.h>
-#include <asm/prom.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 p4080_ds_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,P4080DS"))
-		return 1;
-
-	/* Check if we're running under the Freescale hypervisor */
-	if (of_flat_dt_is_compatible(root, "fsl,P4080DS-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;
-		return 1;
-	}
-
-	return 0;
-}
-
-define_machine(p4080_ds) {
-	.name			= "P4080 DS",
-	.probe			= p4080_ds_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,
-        .init_early             = corenet_ds_init_early,
-};
-
-machine_arch_initcall(p4080_ds, corenet_ds_publish_devices);
-#ifdef CONFIG_SWIOTLB
-machine_arch_initcall(p4080_ds, swiotlb_setup_bus_notifier);
-#endif
diff --git a/arch/powerpc/platforms/85xx/p5020_ds.c b/arch/powerpc/platforms/85xx/p5020_ds.c
deleted file mode 100644
index 6e1ed9f..0000000
--- a/arch/powerpc/platforms/85xx/p5020_ds.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * P5020 DS Setup
- *
- * Maintained by Kumar Gala (see MAINTAINERS for contact information)
- *
- * Copyright 2009-2010 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/pci.h>
-#include <linux/kdev_t.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/phy.h>
-
-#include <asm/time.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <mm/mmu_decl.h>
-#include <asm/prom.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 p5020_ds_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,P5020DS"))
-		return 1;
-
-	/* Check if we're running under the Freescale hypervisor */
-	if (of_flat_dt_is_compatible(root, "fsl,P5020DS-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;
-		return 1;
-	}
-
-	return 0;
-}
-
-define_machine(p5020_ds) {
-	.name			= "P5020 DS",
-	.probe			= p5020_ds_probe,
-	.setup_arch		= corenet_ds_setup_arch,
-	.init_IRQ		= corenet_ds_pic_init,
-#ifdef CONFIG_PCI
-	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
-#endif
-/* coreint doesn't play nice with lazy EE, use legacy mpic for now */
-#ifdef CONFIG_PPC64
-	.get_irq		= mpic_get_irq,
-#else
-	.get_irq		= mpic_get_coreint_irq,
-#endif
-	.restart		= fsl_rstcr_restart,
-	.calibrate_decr		= generic_calibrate_decr,
-	.progress		= udbg_progress,
-#ifdef CONFIG_PPC64
-	.power_save		= book3e_idle,
-#else
-	.power_save		= e500_idle,
-#endif
-	.init_early		= corenet_ds_init_early,
-};
-
-machine_arch_initcall(p5020_ds, corenet_ds_publish_devices);
-
-#ifdef CONFIG_SWIOTLB
-machine_arch_initcall(p5020_ds, swiotlb_setup_bus_notifier);
-#endif
diff --git a/arch/powerpc/platforms/85xx/p5040_ds.c b/arch/powerpc/platforms/85xx/p5040_ds.c
deleted file mode 100644
index 095806a..0000000
--- a/arch/powerpc/platforms/85xx/p5040_ds.c
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * P5040 DS Setup
- *
- * Copyright 2009-2010 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/pci.h>
-
-#include <asm/machdep.h>
-#include <asm/udbg.h>
-#include <asm/mpic.h>
-
-#include <linux/of_fdt.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 p5040_ds_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,P5040DS"))
-		return 1;
-
-	/* Check if we're running under the Freescale hypervisor */
-	if (of_flat_dt_is_compatible(root, "fsl,P5040DS-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;
-		return 1;
-	}
-
-	return 0;
-}
-
-define_machine(p5040_ds) {
-	.name			= "P5040 DS",
-	.probe			= p5040_ds_probe,
-	.setup_arch		= corenet_ds_setup_arch,
-	.init_IRQ		= corenet_ds_pic_init,
-#ifdef CONFIG_PCI
-	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
-#endif
-/* coreint doesn't play nice with lazy EE, use legacy mpic for now */
-#ifdef CONFIG_PPC64
-	.get_irq		= mpic_get_irq,
-#else
-	.get_irq		= mpic_get_coreint_irq,
-#endif
-	.restart		= fsl_rstcr_restart,
-	.calibrate_decr		= generic_calibrate_decr,
-	.progress		= udbg_progress,
-#ifdef CONFIG_PPC64
-	.power_save		= book3e_idle,
-#else
-	.power_save		= e500_idle,
-#endif
-	.init_early		= corenet_ds_init_early,
-};
-
-machine_arch_initcall(p5040_ds, corenet_ds_publish_devices);
-
-#ifdef CONFIG_SWIOTLB
-machine_arch_initcall(p5040_ds, swiotlb_setup_bus_notifier);
-#endif
diff --git a/arch/powerpc/platforms/85xx/ppa8548.c b/arch/powerpc/platforms/85xx/ppa8548.c
index 6a7704b..3daff7c 100644
--- a/arch/powerpc/platforms/85xx/ppa8548.c
+++ b/arch/powerpc/platforms/85xx/ppa8548.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/reboot.h>
 #include <linux/seq_file.h>
+#include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c
index 7179726..b9197ce 100644
--- a/arch/powerpc/platforms/85xx/sgy_cts1000.c
+++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/of_gpio.h>
+#include <linux/of_irq.h>
 #include <linux/workqueue.h>
 #include <linux/reboot.h>
 #include <linux/interrupt.h>
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 43cc5c9..1f50419 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/kexec.h>
 #include <linux/highmem.h>
 #include <linux/cpu.h>
@@ -144,11 +145,13 @@ static void __cpuinit mpc85xx_give_timebase(void)
 	{
 		u64 prev;
 
-		asm volatile("mftb %0" : "=r" (timebase));
+		asm volatile("mfspr %0, %1" : "=r" (timebase) :
+			     "i" (SPRN_TBRL));
 
 		do {
 			prev = timebase;
-			asm volatile("mftb %0" : "=r" (timebase));
+			asm volatile("mfspr %0, %1" : "=r" (timebase) :
+				     "i" (SPRN_TBRL));
 		} while (prev != timebase);
 	}
 #else
@@ -242,8 +245,7 @@ void platform_cpu_die(unsigned int cpu)
 	}
 }
 #else
-/* for e500v1 and e500v2 */
-static void __cpuinit smp_85xx_mach_cpu_die(void)
+static void smp_85xx_mach_cpu_die(void)
 {
 	unsigned int cpu = smp_processor_id();
 	u32 tmp;
@@ -286,7 +288,7 @@ static inline u32 read_spin_table_addr_l(void *spin_table)
 	return in_be32(&((struct epapr_spin_table *)spin_table)->addr_l);
 }
 
-static int __cpuinit smp_85xx_kick_cpu(int nr)
+static int smp_85xx_kick_cpu(int nr)
 {
 	unsigned long flags;
 	const u64 *cpu_rel_addr;
@@ -563,7 +565,7 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image)
 }
 #endif /* CONFIG_KEXEC */
 
-static void __cpuinit smp_85xx_setup_cpu(int cpu_nr)
+static void smp_85xx_setup_cpu(int cpu_nr)
 {
 	if (smp_85xx_ops.probe == smp_mpic_probe)
 		mpic_setup_this_cpu();
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index 3bbbf74..55a9682 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -9,6 +9,8 @@
  */
 
 #include <linux/irq.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/io.h>
 
diff --git a/arch/powerpc/platforms/85xx/t4240_qds.c b/arch/powerpc/platforms/85xx/t4240_qds.c
deleted file mode 100644
index c68baaa..0000000
--- a/arch/powerpc/platforms/85xx/t4240_qds.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * T4240 QDS Setup
- *
- * Maintained by Kumar Gala (see MAINTAINERS for contact information)
- *
- * Copyright 2012 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/pci.h>
-#include <linux/kdev_t.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/phy.h>
-
-#include <asm/time.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <mm/mmu_decl.h>
-#include <asm/prom.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 t4240_qds_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,T4240QDS"))
-		return 1;
-
-	/* Check if we're running under the Freescale hypervisor */
-	if (of_flat_dt_is_compatible(root, "fsl,T4240QDS-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;
-		return 1;
-	}
-
-	return 0;
-}
-
-define_machine(t4240_qds) {
-	.name			= "T4240 QDS",
-	.probe			= t4240_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
-/* coreint doesn't play nice with lazy EE, use legacy mpic for now */
-#ifdef CONFIG_PPC64
-	.get_irq		= mpic_get_irq,
-#else
-	.get_irq		= mpic_get_coreint_irq,
-#endif
-	.restart		= fsl_rstcr_restart,
-	.calibrate_decr		= generic_calibrate_decr,
-	.progress		= udbg_progress,
-#ifdef CONFIG_PPC64
-	.power_save		= book3e_idle,
-#else
-	.power_save		= e500_idle,
-#endif
-	.init_early		= corenet_ds_init_early,
-};
-
-machine_arch_initcall(t4240_qds, corenet_ds_publish_devices);
-
-#ifdef CONFIG_SWIOTLB
-machine_arch_initcall(t4240_qds, swiotlb_setup_bus_notifier);
-#endif
diff --git a/arch/powerpc/platforms/86xx/pic.c b/arch/powerpc/platforms/86xx/pic.c
index 9982f57..d5b98c0 100644
--- a/arch/powerpc/platforms/86xx/pic.c
+++ b/arch/powerpc/platforms/86xx/pic.c
@@ -10,6 +10,7 @@
 #include <linux/stddef.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
+#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 
 #include <asm/mpic.h>
diff --git a/arch/powerpc/platforms/8xx/ep88xc.c b/arch/powerpc/platforms/8xx/ep88xc.c
index 7d9ac60..e621666 100644
--- a/arch/powerpc/platforms/8xx/ep88xc.c
+++ b/arch/powerpc/platforms/8xx/ep88xc.c
@@ -10,6 +10,8 @@
  */
 
 #include <linux/init.h>
+#include <linux/of_address.h>
+#include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c
index 1e12108..587a282 100644
--- a/arch/powerpc/platforms/8xx/m8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/m8xx_setup.c
@@ -43,6 +43,7 @@ static irqreturn_t timebase_interrupt(int irq, void *dev)
 
 static struct irqaction tbint_irqaction = {
 	.handler = timebase_interrupt,
+	.flags = IRQF_NO_THREAD,
 	.name = "tbint",
 };
 
@@ -218,19 +219,12 @@ void mpc8xx_restart(char *cmd)
 
 static void cpm_cascade(unsigned int irq, struct irq_desc *desc)
 {
-	struct irq_chip *chip;
-	int cascade_irq;
-
-	if ((cascade_irq = cpm_get_irq()) >= 0) {
-		struct irq_desc *cdesc = irq_to_desc(cascade_irq);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	int cascade_irq = cpm_get_irq();
 
+	if (cascade_irq >= 0)
 		generic_handle_irq(cascade_irq);
 
-		chip = irq_desc_get_chip(cdesc);
-		chip->irq_eoi(&cdesc->irq_data);
-	}
-
-	chip = irq_desc_get_chip(desc);
 	chip->irq_eoi(&desc->irq_data);
 }
 
diff --git a/arch/powerpc/platforms/8xx/mpc86xads_setup.c b/arch/powerpc/platforms/8xx/mpc86xads_setup.c
index 866feff..6308464 100644
--- a/arch/powerpc/platforms/8xx/mpc86xads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc86xads_setup.c
@@ -15,6 +15,8 @@
  */
 
 #include <linux/init.h>
+#include <linux/of_address.h>
+#include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 
 #include <asm/io.h>
diff --git a/arch/powerpc/platforms/8xx/mpc885ads_setup.c b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
index 5d98398..c126258 100644
--- a/arch/powerpc/platforms/8xx/mpc885ads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
@@ -25,6 +25,8 @@
 #include <linux/fs_uart_pd.h>
 #include <linux/fsl_devices.h>
 #include <linux/mii.h>
+#include <linux/of_address.h>
+#include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 
 #include <asm/delay.h>
diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
index 8d21ab7..251aba8 100644
--- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
@@ -28,6 +28,7 @@
 #include <linux/fs_uart_pd.h>
 #include <linux/fsl_devices.h>
 #include <linux/mii.h>
+#include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 
 #include <asm/delay.h>
@@ -48,7 +49,7 @@ struct cpm_pin {
 	int port, pin, flags;
 };
 
-static struct __initdata cpm_pin tqm8xx_pins[] = {
+static struct cpm_pin tqm8xx_pins[] __initdata = {
 	/* SMC1 */
 	{CPM_PORTB, 24, CPM_PIN_INPUT}, /* RX */
 	{CPM_PORTB, 25, CPM_PIN_INPUT | CPM_PIN_SECONDARY}, /* TX */
@@ -63,7 +64,7 @@ static struct __initdata cpm_pin tqm8xx_pins[] = {
 	{CPM_PORTC, 11, CPM_PIN_INPUT | CPM_PIN_SECONDARY | CPM_PIN_GPIO},
 };
 
-static struct __initdata cpm_pin tqm8xx_fec_pins[] = {
+static struct cpm_pin tqm8xx_fec_pins[] __initdata = {
 	/* MII */
 	{CPM_PORTD, 3, CPM_PIN_OUTPUT},
 	{CPM_PORTD, 4, CPM_PIN_OUTPUT},
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index a1c5686..bf9c6d4 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -92,19 +92,19 @@ config MPIC_TIMER
 	default n
 	help
 	  The MPIC global timer is a hardware timer inside the
-	  Freescale PIC comply to Open-PIC standard. When the
-	  timer is timeout of the specified interval, the hardware
-	  timer generates an interrupt. The driver currently is
-	  only tested on fsl chip, but it can potentially support
-	  other global timers complying to Open-PIC standard.
+	  Freescale PIC complying with OpenPIC standard. When the
+	  specified interval times out, the hardware timer generates
+	  an interrupt. The driver currently is only tested on fsl
+	  chip, but it can potentially support other global timers
+	  complying with the OpenPIC standard.
 
 config FSL_MPIC_TIMER_WAKEUP
 	tristate "Freescale MPIC global timer wakeup driver"
-	depends on FSL_SOC &&  MPIC_TIMER
+	depends on FSL_SOC &&  MPIC_TIMER && PM
 	default n
 	help
-	  This is only for freescale powerpc platform. The driver
-	  provides a way to wake up the system by MPIC timer,
+	  The driver provides a way to wake up the system by MPIC
+	  timer.
 	  e.g. "echo 5 > /sys/devices/system/mpic/timer_wakeup"
 
 config PPC_EPAPR_HV_PIC
@@ -185,6 +185,11 @@ config IBMEBUS
 	help
 	  Bus device driver for GX bus based adapters.
 
+config EEH
+	bool
+	depends on (PPC_POWERNV || PPC_PSERIES) && PCI
+	default y
+
 config PPC_MPC106
 	bool
 	default n
@@ -197,65 +202,18 @@ config PPC_P7_NAP
 	bool
 	default n
 
-config PPC_INDIRECT_IO
-	bool
-	select GENERIC_IOMAP
-
 config PPC_INDIRECT_PIO
 	bool
-	select PPC_INDIRECT_IO
+	select GENERIC_IOMAP
 
 config PPC_INDIRECT_MMIO
 	bool
-	select PPC_INDIRECT_IO
 
 config PPC_IO_WORKAROUNDS
 	bool
 
 source "drivers/cpufreq/Kconfig"
 
-menu "CPU Frequency drivers"
-	depends on CPU_FREQ
-
-config CPU_FREQ_PMAC
-	bool "Support for Apple PowerBooks"
-	depends on ADB_PMU && PPC32
-	select CPU_FREQ_TABLE
-	help
-	  This adds support for frequency switching on Apple PowerBooks,
-	  this currently includes some models of iBook & Titanium
-	  PowerBook.
-
-config CPU_FREQ_PMAC64
-	bool "Support for some Apple G5s"
-	depends on PPC_PMAC && PPC64
-	select CPU_FREQ_TABLE
-	help
-	  This adds support for frequency switching on Apple iMac G5,
-	  and some of the more recent desktop G5 machines as well.
-
-config MPC85xx_CPUFREQ
-	bool "Support for Freescale MPC85xx CPU freq"
-	depends on PPC_85xx && PPC32 && !PPC_E500MC
-	default y
-	select CPU_FREQ_TABLE
-	help
-	  This adds support for dynamic frequency switching on
-	  Freescale MPC85xx by cpufreq interface. MPC8536 and P1022
-	  have a JOG feature, which provides a dynamic mechanism
-	  to lower or raise the CPU core clock at runtime.
-
-config PPC_PASEMI_CPUFREQ
-	bool "Support for PA Semi PWRficient"
-	depends on PPC_PASEMI
-	default y
-	select CPU_FREQ_TABLE
-	help
-	  This adds the support for frequency switching on PA Semi
-	  PWRficient processors.
-
-endmenu
-
 menu "CPUIdle driver"
 
 source "drivers/cpuidle/Kconfig"
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 57e32a3..226f871 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -71,6 +71,7 @@ config PPC_BOOK3S_64
 	select PPC_FPU
 	select PPC_HAVE_PMU_SUPPORT
 	select SYS_SUPPORTS_HUGETLBFS
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if PPC_64K_PAGES
 
 config PPC_BOOK3E_64
 	bool "Embedded processors"
@@ -92,21 +93,35 @@ choice
 
 config GENERIC_CPU
 	bool "Generic"
+	depends on !CPU_LITTLE_ENDIAN
 
 config CELL_CPU
 	bool "Cell Broadband Engine"
+	depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN
 
 config POWER4_CPU
 	bool "POWER4"
+	depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN
 
 config POWER5_CPU
 	bool "POWER5"
+	depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN
 
 config POWER6_CPU
 	bool "POWER6"
+	depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN
 
 config POWER7_CPU
 	bool "POWER7"
+	depends on PPC_BOOK3S_64
+
+config E5500_CPU
+	bool "Freescale e5500"
+	depends on E500
+
+config E6500_CPU
+	bool "Freescale e6500"
+	depends on E500
 
 endchoice
 
@@ -464,3 +479,28 @@ config PPC_DOORBELL
 	default n
 
 endmenu
+
+choice
+	prompt "Endianness selection"
+	default CPU_BIG_ENDIAN
+	help
+	  This option selects whether a big endian or little endian kernel will
+	  be built.
+
+config CPU_BIG_ENDIAN
+	bool "Build big endian kernel"
+	help
+	  Build a big endian kernel.
+
+	  If unsure, select this option.
+
+config CPU_LITTLE_ENDIAN
+	bool "Build little endian kernel"
+	help
+	  Build a little endian kernel.
+
+	  Note that if cross compiling a little endian kernel,
+	  CROSS_COMPILE must point to a toolchain capable of targeting
+	  little endian powerpc.
+
+endchoice
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index 246e1d8..c34ee4e 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -185,7 +185,8 @@ static void beat_lpar_hptab_clear(void)
 static long beat_lpar_hpte_updatepp(unsigned long slot,
 				    unsigned long newpp,
 				    unsigned long vpn,
-				    int psize, int ssize, int local)
+				    int psize, int apsize,
+				    int ssize, int local)
 {
 	unsigned long lpar_rc;
 	u64 dummy0, dummy1;
@@ -274,7 +275,8 @@ static void beat_lpar_hpte_updateboltedpp(unsigned long newpp,
 }
 
 static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
-					 int psize, int ssize, int local)
+				      int psize, int apsize,
+				      int ssize, int local)
 {
 	unsigned long want_v;
 	unsigned long lpar_rc;
@@ -364,9 +366,10 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
  * already zero.  For now I am paranoid.
  */
 static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
-				    unsigned long newpp,
-				    unsigned long vpn,
-				    int psize, int ssize, int local)
+				       unsigned long newpp,
+				       unsigned long vpn,
+				       int psize, int apsize,
+				       int ssize, int local)
 {
 	unsigned long lpar_rc;
 	unsigned long want_v;
@@ -394,7 +397,8 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
 }
 
 static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn,
-					 int psize, int ssize, int local)
+					 int psize, int apsize,
+					 int ssize, int local)
 {
 	unsigned long want_v;
 	unsigned long lpar_rc;
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index 8c6dc42..9e5dfbc 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -239,7 +239,7 @@ void __init beatic_init_IRQ(void)
 	ppc_md.get_irq = beatic_get_irq;
 
 	/* Allocate an irq host */
-	beatic_host = irq_domain_add_nomap(NULL, 0, &beatic_pic_host_ops, NULL);
+	beatic_host = irq_domain_add_nomap(NULL, ~0, &beatic_pic_host_ops, NULL);
 	BUG_ON(beatic_host == NULL);
 	irq_set_default_host(beatic_host);
 }
diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
index 14be2bd..4278acf 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
@@ -486,7 +486,6 @@ static __init int celleb_setup_pciex(struct device_node *node,
 				     struct pci_controller *phb)
 {
 	struct resource	r;
-	struct of_irq oirq;
 	int virq;
 
 	/* SMMIO registers; used inside this file */
@@ -507,12 +506,11 @@ static __init int celleb_setup_pciex(struct device_node *node,
 	phb->ops = &scc_pciex_pci_ops;
 
 	/* internal interrupt handler */
-	if (of_irq_map_one(node, 1, &oirq)) {
+	virq = irq_of_parse_and_map(node, 1);
+	if (!virq) {
 		pr_err("PCIEXC:Failed to map irq\n");
 		goto error;
 	}
-	virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
-				     oirq.size);
 	if (request_irq(virq, pciex_handle_internal_irq,
 			0, "pciex", (void *)phb)) {
 		pr_err("PCIEXC:Failed to request irq\n");
diff --git a/arch/powerpc/platforms/cell/celleb_scc_sio.c b/arch/powerpc/platforms/cell/celleb_scc_sio.c
index 9c339ec..c8eb571 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_sio.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_sio.c
@@ -45,7 +45,7 @@ static int __init txx9_serial_init(void)
 	struct device_node *node;
 	int i;
 	struct uart_port req;
-	struct of_irq irq;
+	struct of_phandle_args irq;
 	struct resource res;
 
 	for_each_compatible_node(node, "serial", "toshiba,sio-scc") {
@@ -53,7 +53,7 @@ static int __init txx9_serial_init(void)
 			if (!(txx9_serial_bitmap & (1<<i)))
 				continue;
 
-			if (of_irq_map_one(node, i, &irq))
+			if (of_irq_parse_one(node, i, &irq))
 				continue;
 			if (of_address_to_resource(node,
 				txx9_scc_tab[i].index, &res))
@@ -66,8 +66,7 @@ static int __init txx9_serial_init(void)
 #ifdef CONFIG_SERIAL_TXX9_CONSOLE
 			req.membase = ioremap(req.mapbase, 0x24);
 #endif
-			req.irq = irq_create_of_mapping(irq.controller,
-				irq.specifier, irq.size);
+			req.irq = irq_create_of_mapping(&irq);
 			req.flags |= UPF_IOREMAP | UPF_BUGGY_UART
 				/*HAVE_CTS_LINE*/;
 			req.uartclk = 83300000;
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 946306b..b535606 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -697,7 +697,7 @@ static int __init cell_iommu_get_window(struct device_node *np,
 					 unsigned long *base,
 					 unsigned long *size)
 {
-	const void *dma_window;
+	const __be32 *dma_window;
 	unsigned long index;
 
 	/* Use ibm,dma-window if available, else, hard code ! */
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 8e29944..1f72f4a 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -235,12 +235,9 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic)
 	/* First, we check whether we have a real "interrupts" in the device
 	 * tree in case the device-tree is ever fixed
 	 */
-	struct of_irq oirq;
-	if (of_irq_map_one(pic->host->of_node, 0, &oirq) == 0) {
-		virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
-					     oirq.size);
+	virq = irq_of_parse_and_map(pic->host->of_node, 0);
+	if (virq)
 		return virq;
-	}
 
 	/* Now do the horrible hacks */
 	tmp = of_get_property(pic->host->of_node, "#interrupt-cells", NULL);
diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c
index 2bb6977..c3327f3 100644
--- a/arch/powerpc/platforms/cell/spu_manage.c
+++ b/arch/powerpc/platforms/cell/spu_manage.c
@@ -177,21 +177,20 @@ out:
 
 static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
 {
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 	int ret;
 	int i;
 
 	for (i=0; i < 3; i++) {
-		ret = of_irq_map_one(np, i, &oirq);
+		ret = of_irq_parse_one(np, i, &oirq);
 		if (ret) {
 			pr_debug("spu_new: failed to get irq %d\n", i);
 			goto err;
 		}
 		ret = -EINVAL;
-		pr_debug("  irq %d no 0x%x on %s\n", i, oirq.specifier[0],
-			 oirq.controller->full_name);
-		spu->irqs[i] = irq_create_of_mapping(oirq.controller,
-					oirq.specifier, oirq.size);
+		pr_debug("  irq %d no 0x%x on %s\n", i, oirq.args[0],
+			 oirq.np->full_name);
+		spu->irqs[i] = irq_create_of_mapping(&oirq);
 		if (spu->irqs[i] == NO_IRQ) {
 			pr_debug("spu_new: failed to map it !\n");
 			goto err;
@@ -200,7 +199,7 @@ static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
 	return 0;
 
 err:
-	pr_debug("failed to map irq %x for spu %s\n", *oirq.specifier,
+	pr_debug("failed to map irq %x for spu %s\n", *oirq.args,
 		spu->name);
 	for (; i >= 0; i--) {
 		if (spu->irqs[i] != NO_IRQ)
diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c
index db4e638..3844f13 100644
--- a/arch/powerpc/platforms/cell/spu_syscalls.c
+++ b/arch/powerpc/platforms/cell/spu_syscalls.c
@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/syscalls.h>
 #include <linux/rcupdate.h>
+#include <linux/binfmts.h>
 
 #include <asm/spu.h>
 
@@ -126,7 +127,7 @@ int elf_coredump_extra_notes_size(void)
 	return ret;
 }
 
-int elf_coredump_extra_notes_write(struct file *file, loff_t *foffset)
+int elf_coredump_extra_notes_write(struct coredump_params *cprm)
 {
 	struct spufs_calls *calls;
 	int ret;
@@ -135,7 +136,7 @@ int elf_coredump_extra_notes_write(struct file *file, loff_t *foffset)
 	if (!calls)
 		return 0;
 
-	ret = calls->coredump_extra_notes_write(file, foffset);
+	ret = calls->coredump_extra_notes_write(cprm);
 
 	spufs_calls_put(calls);
 
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index c9500ea..be6212d 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -27,6 +27,8 @@
 #include <linux/gfp.h>
 #include <linux/list.h>
 #include <linux/syscalls.h>
+#include <linux/coredump.h>
+#include <linux/binfmts.h>
 
 #include <asm/uaccess.h>
 
@@ -48,44 +50,6 @@ static ssize_t do_coredump_read(int num, struct spu_context *ctx, void *buffer,
 	return ++ret; /* count trailing NULL */
 }
 
-/*
- * These are the only things you should do on a core-file: use only these
- * functions to write out all the necessary info.
- */
-static int spufs_dump_write(struct file *file, const void *addr, int nr, loff_t *foffset)
-{
-	unsigned long limit = rlimit(RLIMIT_CORE);
-	ssize_t written;
-
-	if (*foffset + nr > limit)
-		return -EIO;
-
-	written = file->f_op->write(file, addr, nr, &file->f_pos);
-	*foffset += written;
-
-	if (written != nr)
-		return -EIO;
-
-	return 0;
-}
-
-static int spufs_dump_align(struct file *file, char *buf, loff_t new_off,
-			    loff_t *foffset)
-{
-	int rc, size;
-
-	size = min((loff_t)PAGE_SIZE, new_off - *foffset);
-	memset(buf, 0, size);
-
-	rc = 0;
-	while (rc == 0 && new_off > *foffset) {
-		size = min((loff_t)PAGE_SIZE, new_off - *foffset);
-		rc = spufs_dump_write(file, buf, size, foffset);
-	}
-
-	return rc;
-}
-
 static int spufs_ctx_note_size(struct spu_context *ctx, int dfd)
 {
 	int i, sz, total = 0;
@@ -165,10 +129,10 @@ int spufs_coredump_extra_notes_size(void)
 }
 
 static int spufs_arch_write_note(struct spu_context *ctx, int i,
-				  struct file *file, int dfd, loff_t *foffset)
+				  struct coredump_params *cprm, int dfd)
 {
 	loff_t pos = 0;
-	int sz, rc, nread, total = 0;
+	int sz, rc, total = 0;
 	const int bufsz = PAGE_SIZE;
 	char *name;
 	char fullname[80], *buf;
@@ -186,42 +150,39 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i,
 	en.n_descsz = sz;
 	en.n_type = NT_SPU;
 
-	rc = spufs_dump_write(file, &en, sizeof(en), foffset);
-	if (rc)
-		goto out;
+	if (!dump_emit(cprm, &en, sizeof(en)))
+		goto Eio;
 
-	rc = spufs_dump_write(file, fullname, en.n_namesz, foffset);
-	if (rc)
-		goto out;
+	if (!dump_emit(cprm, fullname, en.n_namesz))
+		goto Eio;
 
-	rc = spufs_dump_align(file, buf, roundup(*foffset, 4), foffset);
-	if (rc)
-		goto out;
+	if (!dump_align(cprm, 4))
+		goto Eio;
 
 	do {
-		nread = do_coredump_read(i, ctx, buf, bufsz, &pos);
-		if (nread > 0) {
-			rc = spufs_dump_write(file, buf, nread, foffset);
-			if (rc)
-				goto out;
-			total += nread;
+		rc = do_coredump_read(i, ctx, buf, bufsz, &pos);
+		if (rc > 0) {
+			if (!dump_emit(cprm, buf, rc))
+				goto Eio;
+			total += rc;
 		}
-	} while (nread == bufsz && total < sz);
+	} while (rc == bufsz && total < sz);
 
-	if (nread < 0) {
-		rc = nread;
+	if (rc < 0)
 		goto out;
-	}
-
-	rc = spufs_dump_align(file, buf, roundup(*foffset - total + sz, 4),
-			      foffset);
 
+	if (!dump_skip(cprm,
+		       roundup(cprm->written - total + sz, 4) - cprm->written))
+		goto Eio;
 out:
 	free_page((unsigned long)buf);
 	return rc;
+Eio:
+	free_page((unsigned long)buf);
+	return -EIO;
 }
 
-int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset)
+int spufs_coredump_extra_notes_write(struct coredump_params *cprm)
 {
 	struct spu_context *ctx;
 	int fd, j, rc;
@@ -233,7 +194,7 @@ int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset)
 			return rc;
 
 		for (j = 0; spufs_coredump_read[j].name != NULL; j++) {
-			rc = spufs_arch_write_note(ctx, j, file, fd, foffset);
+			rc = spufs_arch_write_note(ctx, j, cprm, fd);
 			if (rc) {
 				spu_release_saved(ctx);
 				return rc;
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 35f77a4..87ba7cf 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -238,7 +238,7 @@ const struct file_operations spufs_context_fops = {
 	.release	= spufs_dir_close,
 	.llseek		= dcache_dir_lseek,
 	.read		= generic_read_dir,
-	.readdir	= dcache_readdir,
+	.iterate	= dcache_readdir,
 	.fsync		= noop_fsync,
 };
 EXPORT_SYMBOL_GPL(spufs_context_fops);
@@ -620,12 +620,16 @@ spufs_parse_options(struct super_block *sb, char *options, struct inode *root)
 		case Opt_uid:
 			if (match_int(&args[0], &option))
 				return 0;
-			root->i_uid = option;
+			root->i_uid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(root->i_uid))
+				return 0;
 			break;
 		case Opt_gid:
 			if (match_int(&args[0], &option))
 				return 0;
-			root->i_gid = option;
+			root->i_gid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(root->i_gid))
+				return 0;
 			break;
 		case Opt_mode:
 			if (match_octal(&args[0], &option))
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index 67852ad..0ba3c95 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -247,12 +247,13 @@ extern const struct spufs_tree_descr spufs_dir_debug_contents[];
 
 /* system call implementation */
 extern struct spufs_calls spufs_calls;
+struct coredump_params;
 long spufs_run_spu(struct spu_context *ctx, u32 *npc, u32 *status);
 long spufs_create(struct path *nd, struct dentry *dentry, unsigned int flags,
 			umode_t mode, struct file *filp);
 /* ELF coredump callbacks for writing SPU ELF notes */
 extern int spufs_coredump_extra_notes_size(void);
-extern int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset);
+extern int spufs_coredump_extra_notes_write(struct coredump_params *cprm);
 
 extern const struct file_operations spufs_context_fops;
 
diff --git a/arch/powerpc/platforms/chrp/nvram.c b/arch/powerpc/platforms/chrp/nvram.c
index d3ceff0..9ef8cc3 100644
--- a/arch/powerpc/platforms/chrp/nvram.c
+++ b/arch/powerpc/platforms/chrp/nvram.c
@@ -66,7 +66,7 @@ static void chrp_nvram_write(int addr, unsigned char val)
 void __init chrp_nvram_init(void)
 {
 	struct device_node *nvram;
-	const unsigned int *nbytes_p;
+	const __be32 *nbytes_p;
 	unsigned int proplen;
 
 	nvram = of_find_node_by_type(NULL, "nvram");
@@ -79,7 +79,7 @@ void __init chrp_nvram_init(void)
 		return;
 	}
 
-	nvram_size = *nbytes_p;
+	nvram_size = be32_to_cpup(nbytes_p);
 
 	printk(KERN_INFO "CHRP nvram contains %u bytes\n", nvram_size);
 	of_node_put(nvram);
diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
index 53d6eee0..4cde8e7 100644
--- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <asm/io.h>
 
 #include "flipper-pic.h"
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index 3006b51..6c03034 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -18,6 +18,8 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
 #include <asm/io.h>
 
 #include "hlwd-pic.h"
@@ -181,6 +183,7 @@ struct irq_domain *hlwd_pic_init(struct device_node *np)
 					   &hlwd_irq_domain_ops, io_base);
 	if (!irq_domain) {
 		pr_err("failed to allocate irq_domain\n");
+		iounmap(io_base);
 		return NULL;
 	}
 
diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c
index 92ac9b5..b97f6f3 100644
--- a/arch/powerpc/platforms/fsl_uli1575.c
+++ b/arch/powerpc/platforms/fsl_uli1575.c
@@ -321,8 +321,7 @@ static void hpcd_final_uli5288(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 	struct device_node *hosenode = hose ? hose->dn : NULL;
-	struct of_irq oirq;
-	int virq, pin = 2;
+	struct of_phandle_args oirq;
 	u32 laddr[3];
 
 	if (!machine_is(mpc86xx_hpcd))
@@ -331,12 +330,13 @@ static void hpcd_final_uli5288(struct pci_dev *dev)
 	if (!hosenode)
 		return;
 
+	oirq.np = hosenode;
+	oirq.args[0] = 2;
+	oirq.args_count = 1;
 	laddr[0] = (hose->first_busno << 16) | (PCI_DEVFN(31, 0) << 8);
 	laddr[1] = laddr[2] = 0;
-	of_irq_map_raw(hosenode, &pin, 1, laddr, &oirq);
-	virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
-				     oirq.size);
-	dev->irq = virq;
+	of_irq_parse_raw(laddr, &oirq);
+	dev->irq = irq_create_of_mapping(&oirq);
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x1575, hpcd_quirk_uli1575);
diff --git a/arch/powerpc/platforms/pasemi/Makefile b/arch/powerpc/platforms/pasemi/Makefile
index ce6d789..8e8d4ca 100644
--- a/arch/powerpc/platforms/pasemi/Makefile
+++ b/arch/powerpc/platforms/pasemi/Makefile
@@ -1,3 +1,2 @@
 obj-y	+= setup.o pci.o time.o idle.o powersave.o iommu.o dma_lib.o misc.o
 obj-$(CONFIG_PPC_PASEMI_MDIO)	+= gpio_mdio.o
-obj-$(CONFIG_PPC_PASEMI_CPUFREQ) += cpufreq.o
diff --git a/arch/powerpc/platforms/pasemi/cpufreq.c b/arch/powerpc/platforms/pasemi/cpufreq.c
deleted file mode 100644
index be1e795..0000000
--- a/arch/powerpc/platforms/pasemi/cpufreq.c
+++ /dev/null
@@ -1,330 +0,0 @@
-/*
- * Copyright (C) 2007 PA Semi, Inc
- *
- * Authors: Egor Martovetsky <egor@pasemi.com>
- *	    Olof Johansson <olof@lixom.net>
- *
- * Maintained by: Olof Johansson <olof@lixom.net>
- *
- * Based on arch/powerpc/platforms/cell/cbe_cpufreq.c:
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *
- * 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, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-
-#include <linux/cpufreq.h>
-#include <linux/timer.h>
-#include <linux/module.h>
-
-#include <asm/hw_irq.h>
-#include <asm/io.h>
-#include <asm/prom.h>
-#include <asm/time.h>
-#include <asm/smp.h>
-
-#define SDCASR_REG		0x0100
-#define SDCASR_REG_STRIDE	0x1000
-#define SDCPWR_CFGA0_REG	0x0100
-#define SDCPWR_PWST0_REG	0x0000
-#define SDCPWR_GIZTIME_REG	0x0440
-
-/* SDCPWR_GIZTIME_REG fields */
-#define SDCPWR_GIZTIME_GR	0x80000000
-#define SDCPWR_GIZTIME_LONGLOCK	0x000000ff
-
-/* Offset of ASR registers from SDC base */
-#define SDCASR_OFFSET		0x120000
-
-static void __iomem *sdcpwr_mapbase;
-static void __iomem *sdcasr_mapbase;
-
-static DEFINE_MUTEX(pas_switch_mutex);
-
-/* Current astate, is used when waking up from power savings on
- * one core, in case the other core has switched states during
- * the idle time.
- */
-static int current_astate;
-
-/* We support 5(A0-A4) power states excluding turbo(A5-A6) modes */
-static struct cpufreq_frequency_table pas_freqs[] = {
-	{0,	0},
-	{1,	0},
-	{2,	0},
-	{3,	0},
-	{4,	0},
-	{0,	CPUFREQ_TABLE_END},
-};
-
-static struct freq_attr *pas_cpu_freqs_attr[] = {
-	&cpufreq_freq_attr_scaling_available_freqs,
-	NULL,
-};
-
-/*
- * hardware specific functions
- */
-
-static int get_astate_freq(int astate)
-{
-	u32 ret;
-	ret = in_le32(sdcpwr_mapbase + SDCPWR_CFGA0_REG + (astate * 0x10));
-
-	return ret & 0x3f;
-}
-
-static int get_cur_astate(int cpu)
-{
-	u32 ret;
-
-	ret = in_le32(sdcpwr_mapbase + SDCPWR_PWST0_REG);
-	ret = (ret >> (cpu * 4)) & 0x7;
-
-	return ret;
-}
-
-static int get_gizmo_latency(void)
-{
-	u32 giztime, ret;
-
-	giztime = in_le32(sdcpwr_mapbase + SDCPWR_GIZTIME_REG);
-
-	/* just provide the upper bound */
-	if (giztime & SDCPWR_GIZTIME_GR)
-		ret = (giztime & SDCPWR_GIZTIME_LONGLOCK) * 128000;
-	else
-		ret = (giztime & SDCPWR_GIZTIME_LONGLOCK) * 1000;
-
-	return ret;
-}
-
-static void set_astate(int cpu, unsigned int astate)
-{
-	unsigned long flags;
-
-	/* Return if called before init has run */
-	if (unlikely(!sdcasr_mapbase))
-		return;
-
-	local_irq_save(flags);
-
-	out_le32(sdcasr_mapbase + SDCASR_REG + SDCASR_REG_STRIDE*cpu, astate);
-
-	local_irq_restore(flags);
-}
-
-int check_astate(void)
-{
-	return get_cur_astate(hard_smp_processor_id());
-}
-
-void restore_astate(int cpu)
-{
-	set_astate(cpu, current_astate);
-}
-
-/*
- * cpufreq functions
- */
-
-static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy)
-{
-	const u32 *max_freqp;
-	u32 max_freq;
-	int i, cur_astate;
-	struct resource res;
-	struct device_node *cpu, *dn;
-	int err = -ENODEV;
-
-	cpu = of_get_cpu_node(policy->cpu, NULL);
-
-	if (!cpu)
-		goto out;
-
-	dn = of_find_compatible_node(NULL, NULL, "1682m-sdc");
-	if (!dn)
-		dn = of_find_compatible_node(NULL, NULL,
-					     "pasemi,pwrficient-sdc");
-	if (!dn)
-		goto out;
-	err = of_address_to_resource(dn, 0, &res);
-	of_node_put(dn);
-	if (err)
-		goto out;
-	sdcasr_mapbase = ioremap(res.start + SDCASR_OFFSET, 0x2000);
-	if (!sdcasr_mapbase) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	dn = of_find_compatible_node(NULL, NULL, "1682m-gizmo");
-	if (!dn)
-		dn = of_find_compatible_node(NULL, NULL,
-					     "pasemi,pwrficient-gizmo");
-	if (!dn) {
-		err = -ENODEV;
-		goto out_unmap_sdcasr;
-	}
-	err = of_address_to_resource(dn, 0, &res);
-	of_node_put(dn);
-	if (err)
-		goto out_unmap_sdcasr;
-	sdcpwr_mapbase = ioremap(res.start, 0x1000);
-	if (!sdcpwr_mapbase) {
-		err = -EINVAL;
-		goto out_unmap_sdcasr;
-	}
-
-	pr_debug("init cpufreq on CPU %d\n", policy->cpu);
-
-	max_freqp = of_get_property(cpu, "clock-frequency", NULL);
-	if (!max_freqp) {
-		err = -EINVAL;
-		goto out_unmap_sdcpwr;
-	}
-
-	/* we need the freq in kHz */
-	max_freq = *max_freqp / 1000;
-
-	pr_debug("max clock-frequency is at %u kHz\n", max_freq);
-	pr_debug("initializing frequency table\n");
-
-	/* initialize frequency table */
-	for (i=0; pas_freqs[i].frequency!=CPUFREQ_TABLE_END; i++) {
-		pas_freqs[i].frequency = get_astate_freq(pas_freqs[i].index) * 100000;
-		pr_debug("%d: %d\n", i, pas_freqs[i].frequency);
-	}
-
-	policy->cpuinfo.transition_latency = get_gizmo_latency();
-
-	cur_astate = get_cur_astate(policy->cpu);
-	pr_debug("current astate is at %d\n",cur_astate);
-
-	policy->cur = pas_freqs[cur_astate].frequency;
-	cpumask_copy(policy->cpus, cpu_online_mask);
-
-	ppc_proc_freq = policy->cur * 1000ul;
-
-	cpufreq_frequency_table_get_attr(pas_freqs, policy->cpu);
-
-	/* this ensures that policy->cpuinfo_min and policy->cpuinfo_max
-	 * are set correctly
-	 */
-	return cpufreq_frequency_table_cpuinfo(policy, pas_freqs);
-
-out_unmap_sdcpwr:
-	iounmap(sdcpwr_mapbase);
-
-out_unmap_sdcasr:
-	iounmap(sdcasr_mapbase);
-out:
-	return err;
-}
-
-static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy)
-{
-	/*
-	 * We don't support CPU hotplug. Don't unmap after the system
-	 * has already made it to a running state.
-	 */
-	if (system_state != SYSTEM_BOOTING)
-		return 0;
-
-	if (sdcasr_mapbase)
-		iounmap(sdcasr_mapbase);
-	if (sdcpwr_mapbase)
-		iounmap(sdcpwr_mapbase);
-
-	cpufreq_frequency_table_put_attr(policy->cpu);
-	return 0;
-}
-
-static int pas_cpufreq_verify(struct cpufreq_policy *policy)
-{
-	return cpufreq_frequency_table_verify(policy, pas_freqs);
-}
-
-static int pas_cpufreq_target(struct cpufreq_policy *policy,
-			      unsigned int target_freq,
-			      unsigned int relation)
-{
-	struct cpufreq_freqs freqs;
-	int pas_astate_new;
-	int i;
-
-	cpufreq_frequency_table_target(policy,
-				       pas_freqs,
-				       target_freq,
-				       relation,
-				       &pas_astate_new);
-
-	freqs.old = policy->cur;
-	freqs.new = pas_freqs[pas_astate_new].frequency;
-
-	mutex_lock(&pas_switch_mutex);
-	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
-
-	pr_debug("setting frequency for cpu %d to %d kHz, 1/%d of max frequency\n",
-		 policy->cpu,
-		 pas_freqs[pas_astate_new].frequency,
-		 pas_freqs[pas_astate_new].index);
-
-	current_astate = pas_astate_new;
-
-	for_each_online_cpu(i)
-		set_astate(i, pas_astate_new);
-
-	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
-	mutex_unlock(&pas_switch_mutex);
-
-	ppc_proc_freq = freqs.new * 1000ul;
-	return 0;
-}
-
-static struct cpufreq_driver pas_cpufreq_driver = {
-	.name		= "pas-cpufreq",
-	.owner		= THIS_MODULE,
-	.flags		= CPUFREQ_CONST_LOOPS,
-	.init		= pas_cpufreq_cpu_init,
-	.exit		= pas_cpufreq_cpu_exit,
-	.verify		= pas_cpufreq_verify,
-	.target		= pas_cpufreq_target,
-	.attr		= pas_cpu_freqs_attr,
-};
-
-/*
- * module init and destoy
- */
-
-static int __init pas_cpufreq_init(void)
-{
-	if (!of_machine_is_compatible("PA6T-1682M") &&
-	    !of_machine_is_compatible("pasemi,pwrficient"))
-		return -ENODEV;
-
-	return cpufreq_register_driver(&pas_cpufreq_driver);
-}
-
-static void __exit pas_cpufreq_exit(void)
-{
-	cpufreq_unregister_driver(&pas_cpufreq_driver);
-}
-
-module_init(pas_cpufreq_init);
-module_exit(pas_cpufreq_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Egor Martovetsky <egor@pasemi.com>, Olof Johansson <olof@lixom.net>");
diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c
index 0237ab7..15adee5 100644
--- a/arch/powerpc/platforms/pasemi/gpio_mdio.c
+++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c
@@ -30,6 +30,7 @@
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/phy.h>
+#include <linux/of_address.h>
 #include <linux/of_mdio.h>
 #include <linux/of_platform.h>
 
diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile
index ea47df6..52c6ce1 100644
--- a/arch/powerpc/platforms/powermac/Makefile
+++ b/arch/powerpc/platforms/powermac/Makefile
@@ -9,8 +9,6 @@ obj-y				+= pic.o setup.o time.o feature.o pci.o \
 				   sleep.o low_i2c.o cache.o pfunc_core.o \
 				   pfunc_base.o udbg_scc.o udbg_adb.o
 obj-$(CONFIG_PMAC_BACKLIGHT)	+= backlight.o
-obj-$(CONFIG_CPU_FREQ_PMAC)	+= cpufreq_32.o
-obj-$(CONFIG_CPU_FREQ_PMAC64)	+= cpufreq_64.o
 # CONFIG_NVRAM is an arch. independent tristate symbol, for pmac32 we really
 # need this to be a bool.  Cheat here and pretend CONFIG_NVRAM=m is really
 # CONFIG_NVRAM=y
diff --git a/arch/powerpc/platforms/powermac/cpufreq_32.c b/arch/powerpc/platforms/powermac/cpufreq_32.c
deleted file mode 100644
index 3104fad..0000000
--- a/arch/powerpc/platforms/powermac/cpufreq_32.c
+++ /dev/null
@@ -1,721 +0,0 @@
-/*
- *  Copyright (C) 2002 - 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org>
- *  Copyright (C) 2004        John Steele Scott <toojays@toojays.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * TODO: Need a big cleanup here. Basically, we need to have different
- * cpufreq_driver structures for the different type of HW instead of the
- * current mess. We also need to better deal with the detection of the
- * type of machine.
- *
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/adb.h>
-#include <linux/pmu.h>
-#include <linux/cpufreq.h>
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/hardirq.h>
-#include <asm/prom.h>
-#include <asm/machdep.h>
-#include <asm/irq.h>
-#include <asm/pmac_feature.h>
-#include <asm/mmu_context.h>
-#include <asm/sections.h>
-#include <asm/cputable.h>
-#include <asm/time.h>
-#include <asm/mpic.h>
-#include <asm/keylargo.h>
-#include <asm/switch_to.h>
-
-/* WARNING !!! This will cause calibrate_delay() to be called,
- * but this is an __init function ! So you MUST go edit
- * init/main.c to make it non-init before enabling DEBUG_FREQ
- */
-#undef DEBUG_FREQ
-
-extern void low_choose_7447a_dfs(int dfs);
-extern void low_choose_750fx_pll(int pll);
-extern void low_sleep_handler(void);
-
-/*
- * Currently, PowerMac cpufreq supports only high & low frequencies
- * that are set by the firmware
- */
-static unsigned int low_freq;
-static unsigned int hi_freq;
-static unsigned int cur_freq;
-static unsigned int sleep_freq;
-static unsigned long transition_latency;
-
-/*
- * Different models uses different mechanisms to switch the frequency
- */
-static int (*set_speed_proc)(int low_speed);
-static unsigned int (*get_speed_proc)(void);
-
-/*
- * Some definitions used by the various speedprocs
- */
-static u32 voltage_gpio;
-static u32 frequency_gpio;
-static u32 slew_done_gpio;
-static int no_schedule;
-static int has_cpu_l2lve;
-static int is_pmu_based;
-
-/* There are only two frequency states for each processor. Values
- * are in kHz for the time being.
- */
-#define CPUFREQ_HIGH                  0
-#define CPUFREQ_LOW                   1
-
-static struct cpufreq_frequency_table pmac_cpu_freqs[] = {
-	{CPUFREQ_HIGH, 		0},
-	{CPUFREQ_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
-};
-
-static struct freq_attr* pmac_cpu_freqs_attr[] = {
-	&cpufreq_freq_attr_scaling_available_freqs,
-	NULL,
-};
-
-static inline void local_delay(unsigned long ms)
-{
-	if (no_schedule)
-		mdelay(ms);
-	else
-		msleep(ms);
-}
-
-#ifdef DEBUG_FREQ
-static inline void debug_calc_bogomips(void)
-{
-	/* This will cause a recalc of bogomips and display the
-	 * result. We backup/restore the value to avoid affecting the
-	 * core cpufreq framework's own calculation.
-	 */
-	unsigned long save_lpj = loops_per_jiffy;
-	calibrate_delay();
-	loops_per_jiffy = save_lpj;
-}
-#endif /* DEBUG_FREQ */
-
-/* Switch CPU speed under 750FX CPU control
- */
-static int cpu_750fx_cpu_speed(int low_speed)
-{
-	u32 hid2;
-
-	if (low_speed == 0) {
-		/* ramping up, set voltage first */
-		pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x05);
-		/* Make sure we sleep for at least 1ms */
-		local_delay(10);
-
-		/* tweak L2 for high voltage */
-		if (has_cpu_l2lve) {
-			hid2 = mfspr(SPRN_HID2);
-			hid2 &= ~0x2000;
-			mtspr(SPRN_HID2, hid2);
-		}
-	}
-#ifdef CONFIG_6xx
-	low_choose_750fx_pll(low_speed);
-#endif
-	if (low_speed == 1) {
-		/* tweak L2 for low voltage */
-		if (has_cpu_l2lve) {
-			hid2 = mfspr(SPRN_HID2);
-			hid2 |= 0x2000;
-			mtspr(SPRN_HID2, hid2);
-		}
-
-		/* ramping down, set voltage last */
-		pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x04);
-		local_delay(10);
-	}
-
-	return 0;
-}
-
-static unsigned int cpu_750fx_get_cpu_speed(void)
-{
-	if (mfspr(SPRN_HID1) & HID1_PS)
-		return low_freq;
-	else
-		return hi_freq;
-}
-
-/* Switch CPU speed using DFS */
-static int dfs_set_cpu_speed(int low_speed)
-{
-	if (low_speed == 0) {
-		/* ramping up, set voltage first */
-		pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x05);
-		/* Make sure we sleep for at least 1ms */
-		local_delay(1);
-	}
-
-	/* set frequency */
-#ifdef CONFIG_6xx
-	low_choose_7447a_dfs(low_speed);
-#endif
-	udelay(100);
-
-	if (low_speed == 1) {
-		/* ramping down, set voltage last */
-		pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x04);
-		local_delay(1);
-	}
-
-	return 0;
-}
-
-static unsigned int dfs_get_cpu_speed(void)
-{
-	if (mfspr(SPRN_HID1) & HID1_DFS)
-		return low_freq;
-	else
-		return hi_freq;
-}
-
-
-/* Switch CPU speed using slewing GPIOs
- */
-static int gpios_set_cpu_speed(int low_speed)
-{
-	int gpio, timeout = 0;
-
-	/* If ramping up, set voltage first */
-	if (low_speed == 0) {
-		pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x05);
-		/* Delay is way too big but it's ok, we schedule */
-		local_delay(10);
-	}
-
-	/* Set frequency */
-	gpio = 	pmac_call_feature(PMAC_FTR_READ_GPIO, NULL, frequency_gpio, 0);
-	if (low_speed == ((gpio & 0x01) == 0))
-		goto skip;
-
-	pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, frequency_gpio,
-			  low_speed ? 0x04 : 0x05);
-	udelay(200);
-	do {
-		if (++timeout > 100)
-			break;
-		local_delay(1);
-		gpio = pmac_call_feature(PMAC_FTR_READ_GPIO, NULL, slew_done_gpio, 0);
-	} while((gpio & 0x02) == 0);
- skip:
-	/* If ramping down, set voltage last */
-	if (low_speed == 1) {
-		pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x04);
-		/* Delay is way too big but it's ok, we schedule */
-		local_delay(10);
-	}
-
-#ifdef DEBUG_FREQ
-	debug_calc_bogomips();
-#endif
-
-	return 0;
-}
-
-/* Switch CPU speed under PMU control
- */
-static int pmu_set_cpu_speed(int low_speed)
-{
-	struct adb_request req;
-	unsigned long save_l2cr;
-	unsigned long save_l3cr;
-	unsigned int pic_prio;
-	unsigned long flags;
-
-	preempt_disable();
-
-#ifdef DEBUG_FREQ
-	printk(KERN_DEBUG "HID1, before: %x\n", mfspr(SPRN_HID1));
-#endif
-	pmu_suspend();
-
-	/* Disable all interrupt sources on openpic */
- 	pic_prio = mpic_cpu_get_priority();
-	mpic_cpu_set_priority(0xf);
-
-	/* Make sure the decrementer won't interrupt us */
-	asm volatile("mtdec %0" : : "r" (0x7fffffff));
-	/* Make sure any pending DEC interrupt occurring while we did
-	 * the above didn't re-enable the DEC */
-	mb();
-	asm volatile("mtdec %0" : : "r" (0x7fffffff));
-
-	/* We can now disable MSR_EE */
-	local_irq_save(flags);
-
-	/* Giveup the FPU & vec */
-	enable_kernel_fp();
-
-#ifdef CONFIG_ALTIVEC
-	if (cpu_has_feature(CPU_FTR_ALTIVEC))
-		enable_kernel_altivec();
-#endif /* CONFIG_ALTIVEC */
-
-	/* Save & disable L2 and L3 caches */
-	save_l3cr = _get_L3CR();	/* (returns -1 if not available) */
-	save_l2cr = _get_L2CR();	/* (returns -1 if not available) */
-
-	/* Send the new speed command. My assumption is that this command
-	 * will cause PLL_CFG[0..3] to be changed next time CPU goes to sleep
-	 */
-	pmu_request(&req, NULL, 6, PMU_CPU_SPEED, 'W', 'O', 'O', 'F', low_speed);
-	while (!req.complete)
-		pmu_poll();
-
-	/* Prepare the northbridge for the speed transition */
-	pmac_call_feature(PMAC_FTR_SLEEP_STATE,NULL,1,1);
-
-	/* Call low level code to backup CPU state and recover from
-	 * hardware reset
-	 */
-	low_sleep_handler();
-
-	/* Restore the northbridge */
-	pmac_call_feature(PMAC_FTR_SLEEP_STATE,NULL,1,0);
-
-	/* Restore L2 cache */
-	if (save_l2cr != 0xffffffff && (save_l2cr & L2CR_L2E) != 0)
- 		_set_L2CR(save_l2cr);
-	/* Restore L3 cache */
-	if (save_l3cr != 0xffffffff && (save_l3cr & L3CR_L3E) != 0)
- 		_set_L3CR(save_l3cr);
-
-	/* Restore userland MMU context */
-	switch_mmu_context(NULL, current->active_mm);
-
-#ifdef DEBUG_FREQ
-	printk(KERN_DEBUG "HID1, after: %x\n", mfspr(SPRN_HID1));
-#endif
-
-	/* Restore low level PMU operations */
-	pmu_unlock();
-
-	/*
-	 * Restore decrementer; we'll take a decrementer interrupt
-	 * as soon as interrupts are re-enabled and the generic
-	 * clockevents code will reprogram it with the right value.
-	 */
-	set_dec(1);
-
-	/* Restore interrupts */
- 	mpic_cpu_set_priority(pic_prio);
-
-	/* Let interrupts flow again ... */
-	local_irq_restore(flags);
-
-#ifdef DEBUG_FREQ
-	debug_calc_bogomips();
-#endif
-
-	pmu_resume();
-
-	preempt_enable();
-
-	return 0;
-}
-
-static int do_set_cpu_speed(struct cpufreq_policy *policy, int speed_mode,
-		int notify)
-{
-	struct cpufreq_freqs freqs;
-	unsigned long l3cr;
-	static unsigned long prev_l3cr;
-
-	freqs.old = cur_freq;
-	freqs.new = (speed_mode == CPUFREQ_HIGH) ? hi_freq : low_freq;
-
-	if (freqs.old == freqs.new)
-		return 0;
-
-	if (notify)
-		cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
-	if (speed_mode == CPUFREQ_LOW &&
-	    cpu_has_feature(CPU_FTR_L3CR)) {
-		l3cr = _get_L3CR();
-		if (l3cr & L3CR_L3E) {
-			prev_l3cr = l3cr;
-			_set_L3CR(0);
-		}
-	}
-	set_speed_proc(speed_mode == CPUFREQ_LOW);
-	if (speed_mode == CPUFREQ_HIGH &&
-	    cpu_has_feature(CPU_FTR_L3CR)) {
-		l3cr = _get_L3CR();
-		if ((prev_l3cr & L3CR_L3E) && l3cr != prev_l3cr)
-			_set_L3CR(prev_l3cr);
-	}
-	if (notify)
-		cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
-	cur_freq = (speed_mode == CPUFREQ_HIGH) ? hi_freq : low_freq;
-
-	return 0;
-}
-
-static unsigned int pmac_cpufreq_get_speed(unsigned int cpu)
-{
-	return cur_freq;
-}
-
-static int pmac_cpufreq_verify(struct cpufreq_policy *policy)
-{
-	return cpufreq_frequency_table_verify(policy, pmac_cpu_freqs);
-}
-
-static int pmac_cpufreq_target(	struct cpufreq_policy *policy,
-					unsigned int target_freq,
-					unsigned int relation)
-{
-	unsigned int    newstate = 0;
-	int		rc;
-
-	if (cpufreq_frequency_table_target(policy, pmac_cpu_freqs,
-			target_freq, relation, &newstate))
-		return -EINVAL;
-
-	rc = do_set_cpu_speed(policy, newstate, 1);
-
-	ppc_proc_freq = cur_freq * 1000ul;
-	return rc;
-}
-
-static int pmac_cpufreq_cpu_init(struct cpufreq_policy *policy)
-{
-	if (policy->cpu != 0)
-		return -ENODEV;
-
-	policy->cpuinfo.transition_latency	= transition_latency;
-	policy->cur = cur_freq;
-
-	cpufreq_frequency_table_get_attr(pmac_cpu_freqs, policy->cpu);
-	return cpufreq_frequency_table_cpuinfo(policy, pmac_cpu_freqs);
-}
-
-static u32 read_gpio(struct device_node *np)
-{
-	const u32 *reg = of_get_property(np, "reg", NULL);
-	u32 offset;
-
-	if (reg == NULL)
-		return 0;
-	/* That works for all keylargos but shall be fixed properly
-	 * some day... The problem is that it seems we can't rely
-	 * on the "reg" property of the GPIO nodes, they are either
-	 * relative to the base of KeyLargo or to the base of the
-	 * GPIO space, and the device-tree doesn't help.
-	 */
-	offset = *reg;
-	if (offset < KEYLARGO_GPIO_LEVELS0)
-		offset += KEYLARGO_GPIO_LEVELS0;
-	return offset;
-}
-
-static int pmac_cpufreq_suspend(struct cpufreq_policy *policy)
-{
-	/* Ok, this could be made a bit smarter, but let's be robust for now. We
-	 * always force a speed change to high speed before sleep, to make sure
-	 * we have appropriate voltage and/or bus speed for the wakeup process,
-	 * and to make sure our loops_per_jiffies are "good enough", that is will
-	 * not cause too short delays if we sleep in low speed and wake in high
-	 * speed..
-	 */
-	no_schedule = 1;
-	sleep_freq = cur_freq;
-	if (cur_freq == low_freq && !is_pmu_based)
-		do_set_cpu_speed(policy, CPUFREQ_HIGH, 0);
-	return 0;
-}
-
-static int pmac_cpufreq_resume(struct cpufreq_policy *policy)
-{
-	/* If we resume, first check if we have a get() function */
-	if (get_speed_proc)
-		cur_freq = get_speed_proc();
-	else
-		cur_freq = 0;
-
-	/* We don't, hrm... we don't really know our speed here, best
-	 * is that we force a switch to whatever it was, which is
-	 * probably high speed due to our suspend() routine
-	 */
-	do_set_cpu_speed(policy, sleep_freq == low_freq ?
-			 CPUFREQ_LOW : CPUFREQ_HIGH, 0);
-
-	ppc_proc_freq = cur_freq * 1000ul;
-
-	no_schedule = 0;
-	return 0;
-}
-
-static struct cpufreq_driver pmac_cpufreq_driver = {
-	.verify 	= pmac_cpufreq_verify,
-	.target 	= pmac_cpufreq_target,
-	.get		= pmac_cpufreq_get_speed,
-	.init		= pmac_cpufreq_cpu_init,
-	.suspend	= pmac_cpufreq_suspend,
-	.resume		= pmac_cpufreq_resume,
-	.flags		= CPUFREQ_PM_NO_WARN,
-	.attr		= pmac_cpu_freqs_attr,
-	.name		= "powermac",
-	.owner		= THIS_MODULE,
-};
-
-
-static int pmac_cpufreq_init_MacRISC3(struct device_node *cpunode)
-{
-	struct device_node *volt_gpio_np = of_find_node_by_name(NULL,
-								"voltage-gpio");
-	struct device_node *freq_gpio_np = of_find_node_by_name(NULL,
-								"frequency-gpio");
-	struct device_node *slew_done_gpio_np = of_find_node_by_name(NULL,
-								     "slewing-done");
-	const u32 *value;
-
-	/*
-	 * Check to see if it's GPIO driven or PMU only
-	 *
-	 * The way we extract the GPIO address is slightly hackish, but it
-	 * works well enough for now. We need to abstract the whole GPIO
-	 * stuff sooner or later anyway
-	 */
-
-	if (volt_gpio_np)
-		voltage_gpio = read_gpio(volt_gpio_np);
-	if (freq_gpio_np)
-		frequency_gpio = read_gpio(freq_gpio_np);
-	if (slew_done_gpio_np)
-		slew_done_gpio = read_gpio(slew_done_gpio_np);
-
-	/* If we use the frequency GPIOs, calculate the min/max speeds based
-	 * on the bus frequencies
-	 */
-	if (frequency_gpio && slew_done_gpio) {
-		int lenp, rc;
-		const u32 *freqs, *ratio;
-
-		freqs = of_get_property(cpunode, "bus-frequencies", &lenp);
-		lenp /= sizeof(u32);
-		if (freqs == NULL || lenp != 2) {
-			printk(KERN_ERR "cpufreq: bus-frequencies incorrect or missing\n");
-			return 1;
-		}
-		ratio = of_get_property(cpunode, "processor-to-bus-ratio*2",
-						NULL);
-		if (ratio == NULL) {
-			printk(KERN_ERR "cpufreq: processor-to-bus-ratio*2 missing\n");
-			return 1;
-		}
-
-		/* Get the min/max bus frequencies */
-		low_freq = min(freqs[0], freqs[1]);
-		hi_freq = max(freqs[0], freqs[1]);
-
-		/* Grrrr.. It _seems_ that the device-tree is lying on the low bus
-		 * frequency, it claims it to be around 84Mhz on some models while
-		 * it appears to be approx. 101Mhz on all. Let's hack around here...
-		 * fortunately, we don't need to be too precise
-		 */
-		if (low_freq < 98000000)
-			low_freq = 101000000;
-
-		/* Convert those to CPU core clocks */
-		low_freq = (low_freq * (*ratio)) / 2000;
-		hi_freq = (hi_freq * (*ratio)) / 2000;
-
-		/* Now we get the frequencies, we read the GPIO to see what is out current
-		 * speed
-		 */
-		rc = pmac_call_feature(PMAC_FTR_READ_GPIO, NULL, frequency_gpio, 0);
-		cur_freq = (rc & 0x01) ? hi_freq : low_freq;
-
-		set_speed_proc = gpios_set_cpu_speed;
-		return 1;
-	}
-
-	/* If we use the PMU, look for the min & max frequencies in the
-	 * device-tree
-	 */
-	value = of_get_property(cpunode, "min-clock-frequency", NULL);
-	if (!value)
-		return 1;
-	low_freq = (*value) / 1000;
-	/* The PowerBook G4 12" (PowerBook6,1) has an error in the device-tree
-	 * here */
-	if (low_freq < 100000)
-		low_freq *= 10;
-
-	value = of_get_property(cpunode, "max-clock-frequency", NULL);
-	if (!value)
-		return 1;
-	hi_freq = (*value) / 1000;
-	set_speed_proc = pmu_set_cpu_speed;
-	is_pmu_based = 1;
-
-	return 0;
-}
-
-static int pmac_cpufreq_init_7447A(struct device_node *cpunode)
-{
-	struct device_node *volt_gpio_np;
-
-	if (of_get_property(cpunode, "dynamic-power-step", NULL) == NULL)
-		return 1;
-
-	volt_gpio_np = of_find_node_by_name(NULL, "cpu-vcore-select");
-	if (volt_gpio_np)
-		voltage_gpio = read_gpio(volt_gpio_np);
-	if (!voltage_gpio){
-		printk(KERN_ERR "cpufreq: missing cpu-vcore-select gpio\n");
-		return 1;
-	}
-
-	/* OF only reports the high frequency */
-	hi_freq = cur_freq;
-	low_freq = cur_freq/2;
-
-	/* Read actual frequency from CPU */
-	cur_freq = dfs_get_cpu_speed();
-	set_speed_proc = dfs_set_cpu_speed;
-	get_speed_proc = dfs_get_cpu_speed;
-
-	return 0;
-}
-
-static int pmac_cpufreq_init_750FX(struct device_node *cpunode)
-{
-	struct device_node *volt_gpio_np;
-	u32 pvr;
-	const u32 *value;
-
-	if (of_get_property(cpunode, "dynamic-power-step", NULL) == NULL)
-		return 1;
-
-	hi_freq = cur_freq;
-	value = of_get_property(cpunode, "reduced-clock-frequency", NULL);
-	if (!value)
-		return 1;
-	low_freq = (*value) / 1000;
-
-	volt_gpio_np = of_find_node_by_name(NULL, "cpu-vcore-select");
-	if (volt_gpio_np)
-		voltage_gpio = read_gpio(volt_gpio_np);
-
-	pvr = mfspr(SPRN_PVR);
-	has_cpu_l2lve = !((pvr & 0xf00) == 0x100);
-
-	set_speed_proc = cpu_750fx_cpu_speed;
-	get_speed_proc = cpu_750fx_get_cpu_speed;
-	cur_freq = cpu_750fx_get_cpu_speed();
-
-	return 0;
-}
-
-/* Currently, we support the following machines:
- *
- *  - Titanium PowerBook 1Ghz (PMU based, 667Mhz & 1Ghz)
- *  - Titanium PowerBook 800 (PMU based, 667Mhz & 800Mhz)
- *  - Titanium PowerBook 400 (PMU based, 300Mhz & 400Mhz)
- *  - Titanium PowerBook 500 (PMU based, 300Mhz & 500Mhz)
- *  - iBook2 500/600 (PMU based, 400Mhz & 500/600Mhz)
- *  - iBook2 700 (CPU based, 400Mhz & 700Mhz, support low voltage)
- *  - Recent MacRISC3 laptops
- *  - All new machines with 7447A CPUs
- */
-static int __init pmac_cpufreq_setup(void)
-{
-	struct device_node	*cpunode;
-	const u32		*value;
-
-	if (strstr(cmd_line, "nocpufreq"))
-		return 0;
-
-	/* Assume only one CPU */
-	cpunode = of_find_node_by_type(NULL, "cpu");
-	if (!cpunode)
-		goto out;
-
-	/* Get current cpu clock freq */
-	value = of_get_property(cpunode, "clock-frequency", NULL);
-	if (!value)
-		goto out;
-	cur_freq = (*value) / 1000;
-	transition_latency = CPUFREQ_ETERNAL;
-
-	/*  Check for 7447A based MacRISC3 */
-	if (of_machine_is_compatible("MacRISC3") &&
-	    of_get_property(cpunode, "dynamic-power-step", NULL) &&
-	    PVR_VER(mfspr(SPRN_PVR)) == 0x8003) {
-		pmac_cpufreq_init_7447A(cpunode);
-		transition_latency = 8000000;
-	/* Check for other MacRISC3 machines */
-	} else if (of_machine_is_compatible("PowerBook3,4") ||
-		   of_machine_is_compatible("PowerBook3,5") ||
-		   of_machine_is_compatible("MacRISC3")) {
-		pmac_cpufreq_init_MacRISC3(cpunode);
-	/* Else check for iBook2 500/600 */
-	} else if (of_machine_is_compatible("PowerBook4,1")) {
-		hi_freq = cur_freq;
-		low_freq = 400000;
-		set_speed_proc = pmu_set_cpu_speed;
-		is_pmu_based = 1;
-	}
-	/* Else check for TiPb 550 */
-	else if (of_machine_is_compatible("PowerBook3,3") && cur_freq == 550000) {
-		hi_freq = cur_freq;
-		low_freq = 500000;
-		set_speed_proc = pmu_set_cpu_speed;
-		is_pmu_based = 1;
-	}
-	/* Else check for TiPb 400 & 500 */
-	else if (of_machine_is_compatible("PowerBook3,2")) {
-		/* We only know about the 400 MHz and the 500Mhz model
-		 * they both have 300 MHz as low frequency
-		 */
-		if (cur_freq < 350000 || cur_freq > 550000)
-			goto out;
-		hi_freq = cur_freq;
-		low_freq = 300000;
-		set_speed_proc = pmu_set_cpu_speed;
-		is_pmu_based = 1;
-	}
-	/* Else check for 750FX */
-	else if (PVR_VER(mfspr(SPRN_PVR)) == 0x7000)
-		pmac_cpufreq_init_750FX(cpunode);
-out:
-	of_node_put(cpunode);
-	if (set_speed_proc == NULL)
-		return -ENODEV;
-
-	pmac_cpu_freqs[CPUFREQ_LOW].frequency = low_freq;
-	pmac_cpu_freqs[CPUFREQ_HIGH].frequency = hi_freq;
-	ppc_proc_freq = cur_freq * 1000ul;
-
-	printk(KERN_INFO "Registering PowerMac CPU frequency driver\n");
-	printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Boot: %d Mhz\n",
-	       low_freq/1000, hi_freq/1000, cur_freq/1000);
-
-	return cpufreq_register_driver(&pmac_cpufreq_driver);
-}
-
-module_init(pmac_cpufreq_setup);
-
diff --git a/arch/powerpc/platforms/powermac/cpufreq_64.c b/arch/powerpc/platforms/powermac/cpufreq_64.c
deleted file mode 100644
index 7ba4234..0000000
--- a/arch/powerpc/platforms/powermac/cpufreq_64.c
+++ /dev/null
@@ -1,746 +0,0 @@
-/*
- *  Copyright (C) 2002 - 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org>
- *  and                       Markus Demleitner <msdemlei@cl.uni-heidelberg.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This driver adds basic cpufreq support for SMU & 970FX based G5 Macs,
- * that is iMac G5 and latest single CPU desktop.
- */
-
-#undef DEBUG
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/cpufreq.h>
-#include <linux/init.h>
-#include <linux/completion.h>
-#include <linux/mutex.h>
-#include <asm/prom.h>
-#include <asm/machdep.h>
-#include <asm/irq.h>
-#include <asm/sections.h>
-#include <asm/cputable.h>
-#include <asm/time.h>
-#include <asm/smu.h>
-#include <asm/pmac_pfunc.h>
-
-#define DBG(fmt...) pr_debug(fmt)
-
-/* see 970FX user manual */
-
-#define SCOM_PCR 0x0aa001			/* PCR scom addr */
-
-#define PCR_HILO_SELECT		0x80000000U	/* 1 = PCR, 0 = PCRH */
-#define PCR_SPEED_FULL		0x00000000U	/* 1:1 speed value */
-#define PCR_SPEED_HALF		0x00020000U	/* 1:2 speed value */
-#define PCR_SPEED_QUARTER	0x00040000U	/* 1:4 speed value */
-#define PCR_SPEED_MASK		0x000e0000U	/* speed mask */
-#define PCR_SPEED_SHIFT		17
-#define PCR_FREQ_REQ_VALID	0x00010000U	/* freq request valid */
-#define PCR_VOLT_REQ_VALID	0x00008000U	/* volt request valid */
-#define PCR_TARGET_TIME_MASK	0x00006000U	/* target time */
-#define PCR_STATLAT_MASK	0x00001f00U	/* STATLAT value */
-#define PCR_SNOOPLAT_MASK	0x000000f0U	/* SNOOPLAT value */
-#define PCR_SNOOPACC_MASK	0x0000000fU	/* SNOOPACC value */
-
-#define SCOM_PSR 0x408001			/* PSR scom addr */
-/* warning: PSR is a 64 bits register */
-#define PSR_CMD_RECEIVED	0x2000000000000000U   /* command received */
-#define PSR_CMD_COMPLETED	0x1000000000000000U   /* command completed */
-#define PSR_CUR_SPEED_MASK	0x0300000000000000U   /* current speed */
-#define PSR_CUR_SPEED_SHIFT	(56)
-
-/*
- * The G5 only supports two frequencies (Quarter speed is not supported)
- */
-#define CPUFREQ_HIGH                  0
-#define CPUFREQ_LOW                   1
-
-static struct cpufreq_frequency_table g5_cpu_freqs[] = {
-	{CPUFREQ_HIGH, 		0},
-	{CPUFREQ_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
-};
-
-static struct freq_attr* g5_cpu_freqs_attr[] = {
-	&cpufreq_freq_attr_scaling_available_freqs,
-	NULL,
-};
-
-/* Power mode data is an array of the 32 bits PCR values to use for
- * the various frequencies, retrieved from the device-tree
- */
-static int g5_pmode_cur;
-
-static void (*g5_switch_volt)(int speed_mode);
-static int (*g5_switch_freq)(int speed_mode);
-static int (*g5_query_freq)(void);
-
-static DEFINE_MUTEX(g5_switch_mutex);
-
-static unsigned long transition_latency;
-
-#ifdef CONFIG_PMAC_SMU
-
-static const u32 *g5_pmode_data;
-static int g5_pmode_max;
-
-static struct smu_sdbp_fvt *g5_fvt_table;	/* table of op. points */
-static int g5_fvt_count;			/* number of op. points */
-static int g5_fvt_cur;				/* current op. point */
-
-/*
- * SMU based voltage switching for Neo2 platforms
- */
-
-static void g5_smu_switch_volt(int speed_mode)
-{
-	struct smu_simple_cmd	cmd;
-
-	DECLARE_COMPLETION_ONSTACK(comp);
-	smu_queue_simple(&cmd, SMU_CMD_POWER_COMMAND, 8, smu_done_complete,
-			 &comp, 'V', 'S', 'L', 'E', 'W',
-			 0xff, g5_fvt_cur+1, speed_mode);
-	wait_for_completion(&comp);
-}
-
-/*
- * Platform function based voltage/vdnap switching for Neo2
- */
-
-static struct pmf_function *pfunc_set_vdnap0;
-static struct pmf_function *pfunc_vdnap0_complete;
-
-static void g5_vdnap_switch_volt(int speed_mode)
-{
-	struct pmf_args args;
-	u32 slew, done = 0;
-	unsigned long timeout;
-
-	slew = (speed_mode == CPUFREQ_LOW) ? 1 : 0;
-	args.count = 1;
-	args.u[0].p = &slew;
-
-	pmf_call_one(pfunc_set_vdnap0, &args);
-
-	/* It's an irq GPIO so we should be able to just block here,
-	 * I'll do that later after I've properly tested the IRQ code for
-	 * platform functions
-	 */
-	timeout = jiffies + HZ/10;
-	while(!time_after(jiffies, timeout)) {
-		args.count = 1;
-		args.u[0].p = &done;
-		pmf_call_one(pfunc_vdnap0_complete, &args);
-		if (done)
-			break;
-		msleep(1);
-	}
-	if (done == 0)
-		printk(KERN_WARNING "cpufreq: Timeout in clock slewing !\n");
-}
-
-
-/*
- * SCOM based frequency switching for 970FX rev3
- */
-static int g5_scom_switch_freq(int speed_mode)
-{
-	unsigned long flags;
-	int to;
-
-	/* If frequency is going up, first ramp up the voltage */
-	if (speed_mode < g5_pmode_cur)
-		g5_switch_volt(speed_mode);
-
-	local_irq_save(flags);
-
-	/* Clear PCR high */
-	scom970_write(SCOM_PCR, 0);
-	/* Clear PCR low */
-       	scom970_write(SCOM_PCR, PCR_HILO_SELECT | 0);
-	/* Set PCR low */
-	scom970_write(SCOM_PCR, PCR_HILO_SELECT |
-		      g5_pmode_data[speed_mode]);
-
-	/* Wait for completion */
-	for (to = 0; to < 10; to++) {
-		unsigned long psr = scom970_read(SCOM_PSR);
-
-		if ((psr & PSR_CMD_RECEIVED) == 0 &&
-		    (((psr >> PSR_CUR_SPEED_SHIFT) ^
-		      (g5_pmode_data[speed_mode] >> PCR_SPEED_SHIFT)) & 0x3)
-		    == 0)
-			break;
-		if (psr & PSR_CMD_COMPLETED)
-			break;
-		udelay(100);
-	}
-
-	local_irq_restore(flags);
-
-	/* If frequency is going down, last ramp the voltage */
-	if (speed_mode > g5_pmode_cur)
-		g5_switch_volt(speed_mode);
-
-	g5_pmode_cur = speed_mode;
-	ppc_proc_freq = g5_cpu_freqs[speed_mode].frequency * 1000ul;
-
-	return 0;
-}
-
-static int g5_scom_query_freq(void)
-{
-	unsigned long psr = scom970_read(SCOM_PSR);
-	int i;
-
-	for (i = 0; i <= g5_pmode_max; i++)
-		if ((((psr >> PSR_CUR_SPEED_SHIFT) ^
-		      (g5_pmode_data[i] >> PCR_SPEED_SHIFT)) & 0x3) == 0)
-			break;
-	return i;
-}
-
-/*
- * Fake voltage switching for platforms with missing support
- */
-
-static void g5_dummy_switch_volt(int speed_mode)
-{
-}
-
-#endif /* CONFIG_PMAC_SMU */
-
-/*
- * Platform function based voltage switching for PowerMac7,2 & 7,3
- */
-
-static struct pmf_function *pfunc_cpu0_volt_high;
-static struct pmf_function *pfunc_cpu0_volt_low;
-static struct pmf_function *pfunc_cpu1_volt_high;
-static struct pmf_function *pfunc_cpu1_volt_low;
-
-static void g5_pfunc_switch_volt(int speed_mode)
-{
-	if (speed_mode == CPUFREQ_HIGH) {
-		if (pfunc_cpu0_volt_high)
-			pmf_call_one(pfunc_cpu0_volt_high, NULL);
-		if (pfunc_cpu1_volt_high)
-			pmf_call_one(pfunc_cpu1_volt_high, NULL);
-	} else {
-		if (pfunc_cpu0_volt_low)
-			pmf_call_one(pfunc_cpu0_volt_low, NULL);
-		if (pfunc_cpu1_volt_low)
-			pmf_call_one(pfunc_cpu1_volt_low, NULL);
-	}
-	msleep(10); /* should be faster , to fix */
-}
-
-/*
- * Platform function based frequency switching for PowerMac7,2 & 7,3
- */
-
-static struct pmf_function *pfunc_cpu_setfreq_high;
-static struct pmf_function *pfunc_cpu_setfreq_low;
-static struct pmf_function *pfunc_cpu_getfreq;
-static struct pmf_function *pfunc_slewing_done;
-
-static int g5_pfunc_switch_freq(int speed_mode)
-{
-	struct pmf_args args;
-	u32 done = 0;
-	unsigned long timeout;
-	int rc;
-
-	DBG("g5_pfunc_switch_freq(%d)\n", speed_mode);
-
-	/* If frequency is going up, first ramp up the voltage */
-	if (speed_mode < g5_pmode_cur)
-		g5_switch_volt(speed_mode);
-
-	/* Do it */
-	if (speed_mode == CPUFREQ_HIGH)
-		rc = pmf_call_one(pfunc_cpu_setfreq_high, NULL);
-	else
-		rc = pmf_call_one(pfunc_cpu_setfreq_low, NULL);
-
-	if (rc)
-		printk(KERN_WARNING "cpufreq: pfunc switch error %d\n", rc);
-
-	/* It's an irq GPIO so we should be able to just block here,
-	 * I'll do that later after I've properly tested the IRQ code for
-	 * platform functions
-	 */
-	timeout = jiffies + HZ/10;
-	while(!time_after(jiffies, timeout)) {
-		args.count = 1;
-		args.u[0].p = &done;
-		pmf_call_one(pfunc_slewing_done, &args);
-		if (done)
-			break;
-		msleep(1);
-	}
-	if (done == 0)
-		printk(KERN_WARNING "cpufreq: Timeout in clock slewing !\n");
-
-	/* If frequency is going down, last ramp the voltage */
-	if (speed_mode > g5_pmode_cur)
-		g5_switch_volt(speed_mode);
-
-	g5_pmode_cur = speed_mode;
-	ppc_proc_freq = g5_cpu_freqs[speed_mode].frequency * 1000ul;
-
-	return 0;
-}
-
-static int g5_pfunc_query_freq(void)
-{
-	struct pmf_args args;
-	u32 val = 0;
-
-	args.count = 1;
-	args.u[0].p = &val;
-	pmf_call_one(pfunc_cpu_getfreq, &args);
-	return val ? CPUFREQ_HIGH : CPUFREQ_LOW;
-}
-
-
-/*
- * Common interface to the cpufreq core
- */
-
-static int g5_cpufreq_verify(struct cpufreq_policy *policy)
-{
-	return cpufreq_frequency_table_verify(policy, g5_cpu_freqs);
-}
-
-static int g5_cpufreq_target(struct cpufreq_policy *policy,
-	unsigned int target_freq, unsigned int relation)
-{
-	unsigned int newstate = 0;
-	struct cpufreq_freqs freqs;
-	int rc;
-
-	if (cpufreq_frequency_table_target(policy, g5_cpu_freqs,
-			target_freq, relation, &newstate))
-		return -EINVAL;
-
-	if (g5_pmode_cur == newstate)
-		return 0;
-
-	mutex_lock(&g5_switch_mutex);
-
-	freqs.old = g5_cpu_freqs[g5_pmode_cur].frequency;
-	freqs.new = g5_cpu_freqs[newstate].frequency;
-
-	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
-	rc = g5_switch_freq(newstate);
-	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
-
-	mutex_unlock(&g5_switch_mutex);
-
-	return rc;
-}
-
-static unsigned int g5_cpufreq_get_speed(unsigned int cpu)
-{
-	return g5_cpu_freqs[g5_pmode_cur].frequency;
-}
-
-static int g5_cpufreq_cpu_init(struct cpufreq_policy *policy)
-{
-	policy->cpuinfo.transition_latency = transition_latency;
-	policy->cur = g5_cpu_freqs[g5_query_freq()].frequency;
-	/* secondary CPUs are tied to the primary one by the
-	 * cpufreq core if in the secondary policy we tell it that
-	 * it actually must be one policy together with all others. */
-	cpumask_copy(policy->cpus, cpu_online_mask);
-	cpufreq_frequency_table_get_attr(g5_cpu_freqs, policy->cpu);
-
-	return cpufreq_frequency_table_cpuinfo(policy,
-		g5_cpu_freqs);
-}
-
-
-static struct cpufreq_driver g5_cpufreq_driver = {
-	.name		= "powermac",
-	.owner		= THIS_MODULE,
-	.flags		= CPUFREQ_CONST_LOOPS,
-	.init		= g5_cpufreq_cpu_init,
-	.verify		= g5_cpufreq_verify,
-	.target		= g5_cpufreq_target,
-	.get		= g5_cpufreq_get_speed,
-	.attr 		= g5_cpu_freqs_attr,
-};
-
-
-#ifdef CONFIG_PMAC_SMU
-
-static int __init g5_neo2_cpufreq_init(struct device_node *cpus)
-{
-	struct device_node *cpunode;
-	unsigned int psize, ssize;
-	unsigned long max_freq;
-	char *freq_method, *volt_method;
-	const u32 *valp;
-	u32 pvr_hi;
-	int use_volts_vdnap = 0;
-	int use_volts_smu = 0;
-	int rc = -ENODEV;
-
-	/* Check supported platforms */
-	if (of_machine_is_compatible("PowerMac8,1") ||
-	    of_machine_is_compatible("PowerMac8,2") ||
-	    of_machine_is_compatible("PowerMac9,1"))
-		use_volts_smu = 1;
-	else if (of_machine_is_compatible("PowerMac11,2"))
-		use_volts_vdnap = 1;
-	else
-		return -ENODEV;
-
-	/* Get first CPU node */
-	for (cpunode = NULL;
-	     (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) {
-		const u32 *reg = of_get_property(cpunode, "reg", NULL);
-		if (reg == NULL || (*reg) != 0)
-			continue;
-		if (!strcmp(cpunode->type, "cpu"))
-			break;
-	}
-	if (cpunode == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find any CPU 0 node\n");
-		return -ENODEV;
-	}
-
-	/* Check 970FX for now */
-	valp = of_get_property(cpunode, "cpu-version", NULL);
-	if (!valp) {
-		DBG("No cpu-version property !\n");
-		goto bail_noprops;
-	}
-	pvr_hi = (*valp) >> 16;
-	if (pvr_hi != 0x3c && pvr_hi != 0x44) {
-		printk(KERN_ERR "cpufreq: Unsupported CPU version\n");
-		goto bail_noprops;
-	}
-
-	/* Look for the powertune data in the device-tree */
-	g5_pmode_data = of_get_property(cpunode, "power-mode-data",&psize);
-	if (!g5_pmode_data) {
-		DBG("No power-mode-data !\n");
-		goto bail_noprops;
-	}
-	g5_pmode_max = psize / sizeof(u32) - 1;
-
-	if (use_volts_smu) {
-		const struct smu_sdbp_header *shdr;
-
-		/* Look for the FVT table */
-		shdr = smu_get_sdb_partition(SMU_SDB_FVT_ID, NULL);
-		if (!shdr)
-			goto bail_noprops;
-		g5_fvt_table = (struct smu_sdbp_fvt *)&shdr[1];
-		ssize = (shdr->len * sizeof(u32)) -
-			sizeof(struct smu_sdbp_header);
-		g5_fvt_count = ssize / sizeof(struct smu_sdbp_fvt);
-		g5_fvt_cur = 0;
-
-		/* Sanity checking */
-		if (g5_fvt_count < 1 || g5_pmode_max < 1)
-			goto bail_noprops;
-
-		g5_switch_volt = g5_smu_switch_volt;
-		volt_method = "SMU";
-	} else if (use_volts_vdnap) {
-		struct device_node *root;
-
-		root = of_find_node_by_path("/");
-		if (root == NULL) {
-			printk(KERN_ERR "cpufreq: Can't find root of "
-			       "device tree\n");
-			goto bail_noprops;
-		}
-		pfunc_set_vdnap0 = pmf_find_function(root, "set-vdnap0");
-		pfunc_vdnap0_complete =
-			pmf_find_function(root, "slewing-done");
-		if (pfunc_set_vdnap0 == NULL ||
-		    pfunc_vdnap0_complete == NULL) {
-			printk(KERN_ERR "cpufreq: Can't find required "
-			       "platform function\n");
-			goto bail_noprops;
-		}
-
-		g5_switch_volt = g5_vdnap_switch_volt;
-		volt_method = "GPIO";
-	} else {
-		g5_switch_volt = g5_dummy_switch_volt;
-		volt_method = "none";
-	}
-
-	/*
-	 * From what I see, clock-frequency is always the maximal frequency.
-	 * The current driver can not slew sysclk yet, so we really only deal
-	 * with powertune steps for now. We also only implement full freq and
-	 * half freq in this version. So far, I haven't yet seen a machine
-	 * supporting anything else.
-	 */
-	valp = of_get_property(cpunode, "clock-frequency", NULL);
-	if (!valp)
-		return -ENODEV;
-	max_freq = (*valp)/1000;
-	g5_cpu_freqs[0].frequency = max_freq;
-	g5_cpu_freqs[1].frequency = max_freq/2;
-
-	/* Set callbacks */
-	transition_latency = 12000;
-	g5_switch_freq = g5_scom_switch_freq;
-	g5_query_freq = g5_scom_query_freq;
-	freq_method = "SCOM";
-
-	/* Force apply current frequency to make sure everything is in
-	 * sync (voltage is right for example). Firmware may leave us with
-	 * a strange setting ...
-	 */
-	g5_switch_volt(CPUFREQ_HIGH);
-	msleep(10);
-	g5_pmode_cur = -1;
-	g5_switch_freq(g5_query_freq());
-
-	printk(KERN_INFO "Registering G5 CPU frequency driver\n");
-	printk(KERN_INFO "Frequency method: %s, Voltage method: %s\n",
-	       freq_method, volt_method);
-	printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n",
-		g5_cpu_freqs[1].frequency/1000,
-		g5_cpu_freqs[0].frequency/1000,
-		g5_cpu_freqs[g5_pmode_cur].frequency/1000);
-
-	rc = cpufreq_register_driver(&g5_cpufreq_driver);
-
-	/* We keep the CPU node on hold... hopefully, Apple G5 don't have
-	 * hotplug CPU with a dynamic device-tree ...
-	 */
-	return rc;
-
- bail_noprops:
-	of_node_put(cpunode);
-
-	return rc;
-}
-
-#endif /* CONFIG_PMAC_SMU */
-
-
-static int __init g5_pm72_cpufreq_init(struct device_node *cpus)
-{
-	struct device_node *cpuid = NULL, *hwclock = NULL, *cpunode = NULL;
-	const u8 *eeprom = NULL;
-	const u32 *valp;
-	u64 max_freq, min_freq, ih, il;
-	int has_volt = 1, rc = 0;
-
-	DBG("cpufreq: Initializing for PowerMac7,2, PowerMac7,3 and"
-	    " RackMac3,1...\n");
-
-	/* Get first CPU node */
-	for (cpunode = NULL;
-	     (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) {
-		if (!strcmp(cpunode->type, "cpu"))
-			break;
-	}
-	if (cpunode == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find any CPU node\n");
-		return -ENODEV;
-	}
-
-	/* Lookup the cpuid eeprom node */
-        cpuid = of_find_node_by_path("/u3@0,f8000000/i2c@f8001000/cpuid@a0");
-	if (cpuid != NULL)
-		eeprom = of_get_property(cpuid, "cpuid", NULL);
-	if (eeprom == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find cpuid EEPROM !\n");
-		rc = -ENODEV;
-		goto bail;
-	}
-
-	/* Lookup the i2c hwclock */
-	for (hwclock = NULL;
-	     (hwclock = of_find_node_by_name(hwclock, "i2c-hwclock")) != NULL;){
-		const char *loc = of_get_property(hwclock,
-				"hwctrl-location", NULL);
-		if (loc == NULL)
-			continue;
-		if (strcmp(loc, "CPU CLOCK"))
-			continue;
-		if (!of_get_property(hwclock, "platform-get-frequency", NULL))
-			continue;
-		break;
-	}
-	if (hwclock == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find i2c clock chip !\n");
-		rc = -ENODEV;
-		goto bail;
-	}
-
-	DBG("cpufreq: i2c clock chip found: %s\n", hwclock->full_name);
-
-	/* Now get all the platform functions */
-	pfunc_cpu_getfreq =
-		pmf_find_function(hwclock, "get-frequency");
-	pfunc_cpu_setfreq_high =
-		pmf_find_function(hwclock, "set-frequency-high");
-	pfunc_cpu_setfreq_low =
-		pmf_find_function(hwclock, "set-frequency-low");
-	pfunc_slewing_done =
-		pmf_find_function(hwclock, "slewing-done");
-	pfunc_cpu0_volt_high =
-		pmf_find_function(hwclock, "set-voltage-high-0");
-	pfunc_cpu0_volt_low =
-		pmf_find_function(hwclock, "set-voltage-low-0");
-	pfunc_cpu1_volt_high =
-		pmf_find_function(hwclock, "set-voltage-high-1");
-	pfunc_cpu1_volt_low =
-		pmf_find_function(hwclock, "set-voltage-low-1");
-
-	/* Check we have minimum requirements */
-	if (pfunc_cpu_getfreq == NULL || pfunc_cpu_setfreq_high == NULL ||
-	    pfunc_cpu_setfreq_low == NULL || pfunc_slewing_done == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find platform functions !\n");
-		rc = -ENODEV;
-		goto bail;
-	}
-
-	/* Check that we have complete sets */
-	if (pfunc_cpu0_volt_high == NULL || pfunc_cpu0_volt_low == NULL) {
-		pmf_put_function(pfunc_cpu0_volt_high);
-		pmf_put_function(pfunc_cpu0_volt_low);
-		pfunc_cpu0_volt_high = pfunc_cpu0_volt_low = NULL;
-		has_volt = 0;
-	}
-	if (!has_volt ||
-	    pfunc_cpu1_volt_high == NULL || pfunc_cpu1_volt_low == NULL) {
-		pmf_put_function(pfunc_cpu1_volt_high);
-		pmf_put_function(pfunc_cpu1_volt_low);
-		pfunc_cpu1_volt_high = pfunc_cpu1_volt_low = NULL;
-	}
-
-	/* Note: The device tree also contains a "platform-set-values"
-	 * function for which I haven't quite figured out the usage. It
-	 * might have to be called on init and/or wakeup, I'm not too sure
-	 * but things seem to work fine without it so far ...
-	 */
-
-	/* Get max frequency from device-tree */
-	valp = of_get_property(cpunode, "clock-frequency", NULL);
-	if (!valp) {
-		printk(KERN_ERR "cpufreq: Can't find CPU frequency !\n");
-		rc = -ENODEV;
-		goto bail;
-	}
-
-	max_freq = (*valp)/1000;
-
-	/* Now calculate reduced frequency by using the cpuid input freq
-	 * ratio. This requires 64 bits math unless we are willing to lose
-	 * some precision
-	 */
-	ih = *((u32 *)(eeprom + 0x10));
-	il = *((u32 *)(eeprom + 0x20));
-
-	/* Check for machines with no useful settings */
-	if (il == ih) {
-		printk(KERN_WARNING "cpufreq: No low frequency mode available"
-		       " on this model !\n");
-		rc = -ENODEV;
-		goto bail;
-	}
-
-	min_freq = 0;
-	if (ih != 0 && il != 0)
-		min_freq = (max_freq * il) / ih;
-
-	/* Sanity check */
-	if (min_freq >= max_freq || min_freq < 1000) {
-		printk(KERN_ERR "cpufreq: Can't calculate low frequency !\n");
-		rc = -ENXIO;
-		goto bail;
-	}
-	g5_cpu_freqs[0].frequency = max_freq;
-	g5_cpu_freqs[1].frequency = min_freq;
-
-	/* Set callbacks */
-	transition_latency = CPUFREQ_ETERNAL;
-	g5_switch_volt = g5_pfunc_switch_volt;
-	g5_switch_freq = g5_pfunc_switch_freq;
-	g5_query_freq = g5_pfunc_query_freq;
-
-	/* Force apply current frequency to make sure everything is in
-	 * sync (voltage is right for example). Firmware may leave us with
-	 * a strange setting ...
-	 */
-	g5_switch_volt(CPUFREQ_HIGH);
-	msleep(10);
-	g5_pmode_cur = -1;
-	g5_switch_freq(g5_query_freq());
-
-	printk(KERN_INFO "Registering G5 CPU frequency driver\n");
-	printk(KERN_INFO "Frequency method: i2c/pfunc, "
-	       "Voltage method: %s\n", has_volt ? "i2c/pfunc" : "none");
-	printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n",
-		g5_cpu_freqs[1].frequency/1000,
-		g5_cpu_freqs[0].frequency/1000,
-		g5_cpu_freqs[g5_pmode_cur].frequency/1000);
-
-	rc = cpufreq_register_driver(&g5_cpufreq_driver);
- bail:
-	if (rc != 0) {
-		pmf_put_function(pfunc_cpu_getfreq);
-		pmf_put_function(pfunc_cpu_setfreq_high);
-		pmf_put_function(pfunc_cpu_setfreq_low);
-		pmf_put_function(pfunc_slewing_done);
-		pmf_put_function(pfunc_cpu0_volt_high);
-		pmf_put_function(pfunc_cpu0_volt_low);
-		pmf_put_function(pfunc_cpu1_volt_high);
-		pmf_put_function(pfunc_cpu1_volt_low);
-	}
-	of_node_put(hwclock);
-	of_node_put(cpuid);
-	of_node_put(cpunode);
-
-	return rc;
-}
-
-static int __init g5_cpufreq_init(void)
-{
-	struct device_node *cpus;
-	int rc = 0;
-
-	cpus = of_find_node_by_path("/cpus");
-	if (cpus == NULL) {
-		DBG("No /cpus node !\n");
-		return -ENODEV;
-	}
-
-	if (of_machine_is_compatible("PowerMac7,2") ||
-	    of_machine_is_compatible("PowerMac7,3") ||
-	    of_machine_is_compatible("RackMac3,1"))
-		rc = g5_pm72_cpufreq_init(cpus);
-#ifdef CONFIG_PMAC_SMU
-	else
-		rc = g5_neo2_cpufreq_init(cpus);
-#endif /* CONFIG_PMAC_SMU */
-
-	of_node_put(cpus);
-	return rc;
-}
-
-module_init(g5_cpufreq_init);
-
-
-MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c
index fc536f2..7553b6a 100644
--- a/arch/powerpc/platforms/powermac/low_i2c.c
+++ b/arch/powerpc/platforms/powermac/low_i2c.c
@@ -452,7 +452,7 @@ static int kw_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize,
 	 */
 	if (use_irq) {
 		/* Clear completion */
-		INIT_COMPLETION(host->complete);
+		reinit_completion(&host->complete);
 		/* Ack stale interrupts */
 		kw_write_reg(reg_isr, kw_read_reg(reg_isr));
 		/* Arm timeout */
@@ -717,7 +717,7 @@ static int pmu_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize,
 			return -EINVAL;
 		}
 
-		INIT_COMPLETION(comp);
+		reinit_completion(&comp);
 		req->data[0] = PMU_I2C_CMD;
 		req->reply[0] = 0xff;
 		req->nbytes = sizeof(struct pmu_i2c_hdr) + 1;
@@ -748,7 +748,7 @@ static int pmu_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize,
 
 		hdr->bus = PMU_I2C_BUS_STATUS;
 
-		INIT_COMPLETION(comp);
+		reinit_completion(&comp);
 		req->data[0] = PMU_I2C_CMD;
 		req->reply[0] = 0xff;
 		req->nbytes = 2;
diff --git a/arch/powerpc/platforms/powermac/pfunc_base.c b/arch/powerpc/platforms/powermac/pfunc_base.c
index f5e3cda..e49d07f 100644
--- a/arch/powerpc/platforms/powermac/pfunc_base.c
+++ b/arch/powerpc/platforms/powermac/pfunc_base.c
@@ -4,6 +4,7 @@
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
+#include <linux/of_irq.h>
 
 #include <asm/pmac_feature.h>
 #include <asm/pmac_pfunc.h>
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 31036b5..4c24bf6 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -393,8 +393,8 @@ static void __init pmac_pic_probe_oldstyle(void)
 #endif
 }
 
-int of_irq_map_oldworld(struct device_node *device, int index,
-			struct of_irq *out_irq)
+int of_irq_parse_oldworld(struct device_node *device, int index,
+			struct of_phandle_args *out_irq)
 {
 	const u32 *ints = NULL;
 	int intlen;
@@ -422,9 +422,9 @@ int of_irq_map_oldworld(struct device_node *device, int index,
 	if (index >= intlen)
 		return -EINVAL;
 
-	out_irq->controller = NULL;
-	out_irq->specifier[0] = ints[index];
-	out_irq->size = 1;
+	out_irq->np = NULL;
+	out_irq->args[0] = ints[index];
+	out_irq->args_count = 1;
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index bdb738a..5cbd4d6 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -192,7 +192,7 @@ static int psurge_secondary_ipi_init(void)
 {
 	int rc = -ENOMEM;
 
-	psurge_host = irq_domain_add_nomap(NULL, 0, &psurge_host_ops, NULL);
+	psurge_host = irq_domain_add_nomap(NULL, ~0, &psurge_host_ops, NULL);
 
 	if (psurge_host)
 		psurge_secondary_virq = irq_create_direct_mapping(psurge_host);
@@ -885,7 +885,7 @@ static int smp_core99_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata smp_core99_cpu_nb = {
+static struct notifier_block smp_core99_cpu_nb = {
 	.notifier_call	= smp_core99_cpu_notify,
 };
 #endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index c24684c..9fced3f 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -7,6 +7,10 @@ config PPC_POWERNV
 	select PPC_P7_NAP
 	select PPC_PCI_CHOICE if EMBEDDED
 	select EPAPR_BOOT
+	select PPC_INDIRECT_PIO
+	select PPC_UDBG_16550
+	select PPC_SCOM
+	select ARCH_RANDOM
 	default y
 
 config POWERNV_MSI
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index bcc3cb4..873fa13 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,5 +1,8 @@
 obj-y			+= setup.o opal-takeover.o opal-wrappers.o opal.o
-obj-y			+= opal-rtc.o opal-nvram.o
+obj-y			+= opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
+obj-y			+= rng.o
 
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_PCI)	+= pci.o pci-p5ioc2.o pci-ioda.o
+obj-$(CONFIG_EEH)	+= eeh-ioda.o eeh-powernv.o
+obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
new file mode 100644
index 0000000..02245ce
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -0,0 +1,1017 @@
+/*
+ * The file intends to implement the functions needed by EEH, which is
+ * built on IODA compliant chip. Actually, lots of functions related
+ * to EEH would be built based on the OPAL APIs.
+ *
+ * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013.
+ *
+ * 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/bootmem.h>
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/msi.h>
+#include <linux/notifier.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/io.h>
+#include <asm/iommu.h>
+#include <asm/msi_bitmap.h>
+#include <asm/opal.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+#include <asm/tce.h>
+
+#include "powernv.h"
+#include "pci.h"
+
+static char *hub_diag = NULL;
+static int ioda_eeh_nb_init = 0;
+
+static int ioda_eeh_event(struct notifier_block *nb,
+			  unsigned long events, void *change)
+{
+	uint64_t changed_evts = (uint64_t)change;
+
+	/* We simply send special EEH event */
+	if ((changed_evts & OPAL_EVENT_PCI_ERROR) &&
+	    (events & OPAL_EVENT_PCI_ERROR))
+		eeh_send_failure_event(NULL);
+
+	return 0;
+}
+
+static struct notifier_block ioda_eeh_nb = {
+	.notifier_call	= ioda_eeh_event,
+	.next		= NULL,
+	.priority	= 0
+};
+
+#ifdef CONFIG_DEBUG_FS
+static int ioda_eeh_dbgfs_set(void *data, int offset, u64 val)
+{
+	struct pci_controller *hose = data;
+	struct pnv_phb *phb = hose->private_data;
+
+	out_be64(phb->regs + offset, val);
+	return 0;
+}
+
+static int ioda_eeh_dbgfs_get(void *data, int offset, u64 *val)
+{
+	struct pci_controller *hose = data;
+	struct pnv_phb *phb = hose->private_data;
+
+	*val = in_be64(phb->regs + offset);
+	return 0;
+}
+
+static int ioda_eeh_outb_dbgfs_set(void *data, u64 val)
+{
+	return ioda_eeh_dbgfs_set(data, 0xD10, val);
+}
+
+static int ioda_eeh_outb_dbgfs_get(void *data, u64 *val)
+{
+	return ioda_eeh_dbgfs_get(data, 0xD10, val);
+}
+
+static int ioda_eeh_inbA_dbgfs_set(void *data, u64 val)
+{
+	return ioda_eeh_dbgfs_set(data, 0xD90, val);
+}
+
+static int ioda_eeh_inbA_dbgfs_get(void *data, u64 *val)
+{
+	return ioda_eeh_dbgfs_get(data, 0xD90, val);
+}
+
+static int ioda_eeh_inbB_dbgfs_set(void *data, u64 val)
+{
+	return ioda_eeh_dbgfs_set(data, 0xE10, val);
+}
+
+static int ioda_eeh_inbB_dbgfs_get(void *data, u64 *val)
+{
+	return ioda_eeh_dbgfs_get(data, 0xE10, val);
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_outb_dbgfs_ops, ioda_eeh_outb_dbgfs_get,
+			ioda_eeh_outb_dbgfs_set, "0x%llx\n");
+DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbA_dbgfs_ops, ioda_eeh_inbA_dbgfs_get,
+			ioda_eeh_inbA_dbgfs_set, "0x%llx\n");
+DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get,
+			ioda_eeh_inbB_dbgfs_set, "0x%llx\n");
+#endif /* CONFIG_DEBUG_FS */
+
+/**
+ * ioda_eeh_post_init - Chip dependent post initialization
+ * @hose: PCI controller
+ *
+ * The function will be called after eeh PEs and devices
+ * have been built. That means the EEH is ready to supply
+ * service with I/O cache.
+ */
+static int ioda_eeh_post_init(struct pci_controller *hose)
+{
+	struct pnv_phb *phb = hose->private_data;
+	int ret;
+
+	/* Register OPAL event notifier */
+	if (!ioda_eeh_nb_init) {
+		ret = opal_notifier_register(&ioda_eeh_nb);
+		if (ret) {
+			pr_err("%s: Can't register OPAL event notifier (%d)\n",
+			       __func__, ret);
+			return ret;
+		}
+
+		ioda_eeh_nb_init = 1;
+	}
+
+	/* We needn't HUB diag-data on PHB3 */
+	if (phb->type == PNV_PHB_IODA1 && !hub_diag) {
+		hub_diag = (char *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+		if (!hub_diag) {
+			pr_err("%s: Out of memory !\n", __func__);
+			return -ENOMEM;
+		}
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	if (phb->dbgfs) {
+		debugfs_create_file("err_injct_outbound", 0600,
+				    phb->dbgfs, hose,
+				    &ioda_eeh_outb_dbgfs_ops);
+		debugfs_create_file("err_injct_inboundA", 0600,
+				    phb->dbgfs, hose,
+				    &ioda_eeh_inbA_dbgfs_ops);
+		debugfs_create_file("err_injct_inboundB", 0600,
+				    phb->dbgfs, hose,
+				    &ioda_eeh_inbB_dbgfs_ops);
+	}
+#endif
+
+	phb->eeh_state |= PNV_EEH_STATE_ENABLED;
+
+	return 0;
+}
+
+/**
+ * ioda_eeh_set_option - Set EEH operation or I/O setting
+ * @pe: EEH PE
+ * @option: options
+ *
+ * Enable or disable EEH option for the indicated PE. The
+ * function also can be used to enable I/O or DMA for the
+ * PE.
+ */
+static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
+{
+	s64 ret;
+	u32 pe_no;
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+
+	/* Check on PE number */
+	if (pe->addr < 0 || pe->addr >= phb->ioda.total_pe) {
+		pr_err("%s: PE address %x out of range [0, %x] "
+		       "on PHB#%x\n",
+			__func__, pe->addr, phb->ioda.total_pe,
+			hose->global_number);
+		return -EINVAL;
+	}
+
+	pe_no = pe->addr;
+	switch (option) {
+	case EEH_OPT_DISABLE:
+		ret = -EEXIST;
+		break;
+	case EEH_OPT_ENABLE:
+		ret = 0;
+		break;
+	case EEH_OPT_THAW_MMIO:
+		ret = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no,
+				OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO);
+		if (ret) {
+			pr_warning("%s: Failed to enable MMIO for "
+				   "PHB#%x-PE#%x, err=%lld\n",
+				__func__, hose->global_number, pe_no, ret);
+			return -EIO;
+		}
+
+		break;
+	case EEH_OPT_THAW_DMA:
+		ret = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no,
+				OPAL_EEH_ACTION_CLEAR_FREEZE_DMA);
+		if (ret) {
+			pr_warning("%s: Failed to enable DMA for "
+				   "PHB#%x-PE#%x, err=%lld\n",
+				__func__, hose->global_number, pe_no, ret);
+			return -EIO;
+		}
+
+		break;
+	default:
+		pr_warning("%s: Invalid option %d\n", __func__, option);
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+/**
+ * ioda_eeh_get_state - Retrieve the state of PE
+ * @pe: EEH PE
+ *
+ * The PE's state should be retrieved from the PEEV, PEST
+ * IODA tables. Since the OPAL has exported the function
+ * to do it, it'd better to use that.
+ */
+static int ioda_eeh_get_state(struct eeh_pe *pe)
+{
+	s64 ret = 0;
+	u8 fstate;
+	u16 pcierr;
+	u32 pe_no;
+	int result;
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+
+	/*
+	 * Sanity check on PE address. The PHB PE address should
+	 * be zero.
+	 */
+	if (pe->addr < 0 || pe->addr >= phb->ioda.total_pe) {
+		pr_err("%s: PE address %x out of range [0, %x] "
+		       "on PHB#%x\n",
+		       __func__, pe->addr, phb->ioda.total_pe,
+		       hose->global_number);
+		return EEH_STATE_NOT_SUPPORT;
+	}
+
+	/* Retrieve PE status through OPAL */
+	pe_no = pe->addr;
+	ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no,
+			&fstate, &pcierr, NULL);
+	if (ret) {
+		pr_err("%s: Failed to get EEH status on "
+		       "PHB#%x-PE#%x\n, err=%lld\n",
+		       __func__, hose->global_number, pe_no, ret);
+		return EEH_STATE_NOT_SUPPORT;
+	}
+
+	/* Check PHB status */
+	if (pe->type & EEH_PE_PHB) {
+		result = 0;
+		result &= ~EEH_STATE_RESET_ACTIVE;
+
+		if (pcierr != OPAL_EEH_PHB_ERROR) {
+			result |= EEH_STATE_MMIO_ACTIVE;
+			result |= EEH_STATE_DMA_ACTIVE;
+			result |= EEH_STATE_MMIO_ENABLED;
+			result |= EEH_STATE_DMA_ENABLED;
+		}
+
+		return result;
+	}
+
+	/* Parse result out */
+	result = 0;
+	switch (fstate) {
+	case OPAL_EEH_STOPPED_NOT_FROZEN:
+		result &= ~EEH_STATE_RESET_ACTIVE;
+		result |= EEH_STATE_MMIO_ACTIVE;
+		result |= EEH_STATE_DMA_ACTIVE;
+		result |= EEH_STATE_MMIO_ENABLED;
+		result |= EEH_STATE_DMA_ENABLED;
+		break;
+	case OPAL_EEH_STOPPED_MMIO_FREEZE:
+		result &= ~EEH_STATE_RESET_ACTIVE;
+		result |= EEH_STATE_DMA_ACTIVE;
+		result |= EEH_STATE_DMA_ENABLED;
+		break;
+	case OPAL_EEH_STOPPED_DMA_FREEZE:
+		result &= ~EEH_STATE_RESET_ACTIVE;
+		result |= EEH_STATE_MMIO_ACTIVE;
+		result |= EEH_STATE_MMIO_ENABLED;
+		break;
+	case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE:
+		result &= ~EEH_STATE_RESET_ACTIVE;
+		break;
+	case OPAL_EEH_STOPPED_RESET:
+		result |= EEH_STATE_RESET_ACTIVE;
+		break;
+	case OPAL_EEH_STOPPED_TEMP_UNAVAIL:
+		result |= EEH_STATE_UNAVAILABLE;
+		break;
+	case OPAL_EEH_STOPPED_PERM_UNAVAIL:
+		result |= EEH_STATE_NOT_SUPPORT;
+		break;
+	default:
+		pr_warning("%s: Unexpected EEH status 0x%x "
+			   "on PHB#%x-PE#%x\n",
+			   __func__, fstate, hose->global_number, pe_no);
+	}
+
+	return result;
+}
+
+static int ioda_eeh_pe_clear(struct eeh_pe *pe)
+{
+	struct pci_controller *hose;
+	struct pnv_phb *phb;
+	u32 pe_no;
+	u8 fstate;
+	u16 pcierr;
+	s64 ret;
+
+	pe_no = pe->addr;
+	hose = pe->phb;
+	phb = pe->phb->private_data;
+
+	/* Clear the EEH error on the PE */
+	ret = opal_pci_eeh_freeze_clear(phb->opal_id,
+			pe_no, OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+	if (ret) {
+		pr_err("%s: Failed to clear EEH error for "
+		       "PHB#%x-PE#%x, err=%lld\n",
+		       __func__, hose->global_number, pe_no, ret);
+		return -EIO;
+	}
+
+	/*
+	 * Read the PE state back and verify that the frozen
+	 * state has been removed.
+	 */
+	ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no,
+			&fstate, &pcierr, NULL);
+	if (ret) {
+		pr_err("%s: Failed to get EEH status on "
+		       "PHB#%x-PE#%x\n, err=%lld\n",
+		       __func__, hose->global_number, pe_no, ret);
+		return -EIO;
+	}
+
+	if (fstate != OPAL_EEH_STOPPED_NOT_FROZEN) {
+		pr_err("%s: Frozen state not cleared on "
+		       "PHB#%x-PE#%x, sts=%x\n",
+		       __func__, hose->global_number, pe_no, fstate);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static s64 ioda_eeh_phb_poll(struct pnv_phb *phb)
+{
+	s64 rc = OPAL_HARDWARE;
+
+	while (1) {
+		rc = opal_pci_poll(phb->opal_id);
+		if (rc <= 0)
+			break;
+
+		msleep(rc);
+	}
+
+	return rc;
+}
+
+static int ioda_eeh_phb_reset(struct pci_controller *hose, int option)
+{
+	struct pnv_phb *phb = hose->private_data;
+	s64 rc = OPAL_HARDWARE;
+
+	pr_debug("%s: Reset PHB#%x, option=%d\n",
+		 __func__, hose->global_number, option);
+
+	/* Issue PHB complete reset request */
+	if (option == EEH_RESET_FUNDAMENTAL ||
+	    option == EEH_RESET_HOT)
+		rc = opal_pci_reset(phb->opal_id,
+				OPAL_PHB_COMPLETE,
+				OPAL_ASSERT_RESET);
+	else if (option == EEH_RESET_DEACTIVATE)
+		rc = opal_pci_reset(phb->opal_id,
+				OPAL_PHB_COMPLETE,
+				OPAL_DEASSERT_RESET);
+	if (rc < 0)
+		goto out;
+
+	/*
+	 * Poll state of the PHB until the request is done
+	 * successfully.
+	 */
+	rc = ioda_eeh_phb_poll(phb);
+out:
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+
+	return 0;
+}
+
+static int ioda_eeh_root_reset(struct pci_controller *hose, int option)
+{
+	struct pnv_phb *phb = hose->private_data;
+	s64 rc = OPAL_SUCCESS;
+
+	pr_debug("%s: Reset PHB#%x, option=%d\n",
+		 __func__, hose->global_number, option);
+
+	/*
+	 * During the reset deassert time, we needn't care
+	 * the reset scope because the firmware does nothing
+	 * for fundamental or hot reset during deassert phase.
+	 */
+	if (option == EEH_RESET_FUNDAMENTAL)
+		rc = opal_pci_reset(phb->opal_id,
+				OPAL_PCI_FUNDAMENTAL_RESET,
+				OPAL_ASSERT_RESET);
+	else if (option == EEH_RESET_HOT)
+		rc = opal_pci_reset(phb->opal_id,
+				OPAL_PCI_HOT_RESET,
+				OPAL_ASSERT_RESET);
+	else if (option == EEH_RESET_DEACTIVATE)
+		rc = opal_pci_reset(phb->opal_id,
+				OPAL_PCI_HOT_RESET,
+				OPAL_DEASSERT_RESET);
+	if (rc < 0)
+		goto out;
+
+	/* Poll state of the PHB until the request is done */
+	rc = ioda_eeh_phb_poll(phb);
+out:
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+
+	return 0;
+}
+
+static int ioda_eeh_bridge_reset(struct pci_controller *hose,
+		struct pci_dev *dev, int option)
+{
+	u16 ctrl;
+
+	pr_debug("%s: Reset device %04x:%02x:%02x.%01x with option %d\n",
+		 __func__, hose->global_number, dev->bus->number,
+		 PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn), option);
+
+	switch (option) {
+	case EEH_RESET_FUNDAMENTAL:
+	case EEH_RESET_HOT:
+		pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl);
+		ctrl |= PCI_BRIDGE_CTL_BUS_RESET;
+		pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl);
+		break;
+	case EEH_RESET_DEACTIVATE:
+		pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl);
+		ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET;
+		pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl);
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ * ioda_eeh_reset - Reset the indicated PE
+ * @pe: EEH PE
+ * @option: reset option
+ *
+ * Do reset on the indicated PE. For PCI bus sensitive PE,
+ * we need to reset the parent p2p bridge. The PHB has to
+ * be reinitialized if the p2p bridge is root bridge. For
+ * PCI device sensitive PE, we will try to reset the device
+ * through FLR. For now, we don't have OPAL APIs to do HARD
+ * reset yet, so all reset would be SOFT (HOT) reset.
+ */
+static int ioda_eeh_reset(struct eeh_pe *pe, int option)
+{
+	struct pci_controller *hose = pe->phb;
+	struct eeh_dev *edev;
+	struct pci_dev *dev;
+	int ret;
+
+	/*
+	 * Anyway, we have to clear the problematic state for the
+	 * corresponding PE. However, we needn't do it if the PE
+	 * is PHB associated. That means the PHB is having fatal
+	 * errors and it needs reset. Further more, the AIB interface
+	 * isn't reliable any more.
+	 */
+	if (!(pe->type & EEH_PE_PHB) &&
+	    (option == EEH_RESET_HOT ||
+	    option == EEH_RESET_FUNDAMENTAL)) {
+		ret = ioda_eeh_pe_clear(pe);
+		if (ret)
+			return -EIO;
+	}
+
+	/*
+	 * The rules applied to reset, either fundamental or hot reset:
+	 *
+	 * We always reset the direct upstream bridge of the PE. If the
+	 * direct upstream bridge isn't root bridge, we always take hot
+	 * reset no matter what option (fundamental or hot) is. Otherwise,
+	 * we should do the reset according to the required option.
+	 */
+	if (pe->type & EEH_PE_PHB) {
+		ret = ioda_eeh_phb_reset(hose, option);
+	} else {
+		if (pe->type & EEH_PE_DEVICE) {
+			/*
+			 * If it's device PE, we didn't refer to the parent
+			 * PCI bus yet. So we have to figure it out indirectly.
+			 */
+			edev = list_first_entry(&pe->edevs,
+					struct eeh_dev, list);
+			dev = eeh_dev_to_pci_dev(edev);
+			dev = dev->bus->self;
+		} else {
+			/*
+			 * If it's bus PE, the parent PCI bus is already there
+			 * and just pick it up.
+			 */
+			dev = pe->bus->self;
+		}
+
+		/*
+		 * Do reset based on the fact that the direct upstream bridge
+		 * is root bridge (port) or not.
+		 */
+		if (dev->bus->number == 0)
+			ret = ioda_eeh_root_reset(hose, option);
+		else
+			ret = ioda_eeh_bridge_reset(hose, dev, option);
+	}
+
+	return ret;
+}
+
+/**
+ * ioda_eeh_get_log - Retrieve error log
+ * @pe: EEH PE
+ * @severity: Severity level of the log
+ * @drv_log: buffer to store the log
+ * @len: space of the log buffer
+ *
+ * The function is used to retrieve error log from P7IOC.
+ */
+static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
+			    char *drv_log, unsigned long len)
+{
+	s64 ret;
+	unsigned long flags;
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+
+	spin_lock_irqsave(&phb->lock, flags);
+
+	ret = opal_pci_get_phb_diag_data2(phb->opal_id,
+			phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
+	if (ret) {
+		spin_unlock_irqrestore(&phb->lock, flags);
+		pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n",
+			   __func__, hose->global_number, pe->addr, ret);
+		return -EIO;
+	}
+
+	/*
+	 * FIXME: We probably need log the error in somewhere.
+	 * Lets make it up in future.
+	 */
+	/* pr_info("%s", phb->diag.blob); */
+
+	spin_unlock_irqrestore(&phb->lock, flags);
+
+	return 0;
+}
+
+/**
+ * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
+ * @pe: EEH PE
+ *
+ * For particular PE, it might have included PCI bridges. In order
+ * to make the PE work properly, those PCI bridges should be configured
+ * correctly. However, we need do nothing on P7IOC since the reset
+ * function will do everything that should be covered by the function.
+ */
+static int ioda_eeh_configure_bridge(struct eeh_pe *pe)
+{
+	return 0;
+}
+
+static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data)
+{
+	/* GEM */
+	pr_info("  GEM XFIR:        %016llx\n", data->gemXfir);
+	pr_info("  GEM RFIR:        %016llx\n", data->gemRfir);
+	pr_info("  GEM RIRQFIR:     %016llx\n", data->gemRirqfir);
+	pr_info("  GEM Mask:        %016llx\n", data->gemMask);
+	pr_info("  GEM RWOF:        %016llx\n", data->gemRwof);
+
+	/* LEM */
+	pr_info("  LEM FIR:         %016llx\n", data->lemFir);
+	pr_info("  LEM Error Mask:  %016llx\n", data->lemErrMask);
+	pr_info("  LEM Action 0:    %016llx\n", data->lemAction0);
+	pr_info("  LEM Action 1:    %016llx\n", data->lemAction1);
+	pr_info("  LEM WOF:         %016llx\n", data->lemWof);
+}
+
+static void ioda_eeh_hub_diag(struct pci_controller *hose)
+{
+	struct pnv_phb *phb = hose->private_data;
+	struct OpalIoP7IOCErrorData *data;
+	long rc;
+
+	data = (struct OpalIoP7IOCErrorData *)ioda_eeh_hub_diag;
+	rc = opal_pci_get_hub_diag_data(phb->hub_id, data, PAGE_SIZE);
+	if (rc != OPAL_SUCCESS) {
+		pr_warning("%s: Failed to get HUB#%llx diag-data (%ld)\n",
+			   __func__, phb->hub_id, rc);
+		return;
+	}
+
+	switch (data->type) {
+	case OPAL_P7IOC_DIAG_TYPE_RGC:
+		pr_info("P7IOC diag-data for RGC\n\n");
+		ioda_eeh_hub_diag_common(data);
+		pr_info("  RGC Status:      %016llx\n", data->rgc.rgcStatus);
+		pr_info("  RGC LDCP:        %016llx\n", data->rgc.rgcLdcp);
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_BI:
+		pr_info("P7IOC diag-data for BI %s\n\n",
+			data->bi.biDownbound ? "Downbound" : "Upbound");
+		ioda_eeh_hub_diag_common(data);
+		pr_info("  BI LDCP 0:       %016llx\n", data->bi.biLdcp0);
+		pr_info("  BI LDCP 1:       %016llx\n", data->bi.biLdcp1);
+		pr_info("  BI LDCP 2:       %016llx\n", data->bi.biLdcp2);
+		pr_info("  BI Fence Status: %016llx\n", data->bi.biFenceStatus);
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_CI:
+		pr_info("P7IOC diag-data for CI Port %d\\nn",
+			data->ci.ciPort);
+		ioda_eeh_hub_diag_common(data);
+		pr_info("  CI Port Status:  %016llx\n", data->ci.ciPortStatus);
+		pr_info("  CI Port LDCP:    %016llx\n", data->ci.ciPortLdcp);
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_MISC:
+		pr_info("P7IOC diag-data for MISC\n\n");
+		ioda_eeh_hub_diag_common(data);
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_I2C:
+		pr_info("P7IOC diag-data for I2C\n\n");
+		ioda_eeh_hub_diag_common(data);
+		break;
+	default:
+		pr_warning("%s: Invalid type of HUB#%llx diag-data (%d)\n",
+			   __func__, phb->hub_id, data->type);
+	}
+}
+
+static void ioda_eeh_p7ioc_phb_diag(struct pci_controller *hose,
+				    struct OpalIoPhbErrorCommon *common)
+{
+	struct OpalIoP7IOCPhbErrorData *data;
+	int i;
+
+	data = (struct OpalIoP7IOCPhbErrorData *)common;
+
+	pr_info("P7IOC PHB#%x Diag-data (Version: %d)\n\n",
+		hose->global_number, common->version);
+
+	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
+
+	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
+	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
+	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
+
+	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
+	pr_info("  slotStatus:           %08x\n", data->slotStatus);
+	pr_info("  linkStatus:           %08x\n", data->linkStatus);
+	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
+	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
+
+	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
+	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
+	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
+	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
+	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
+	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
+	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
+	pr_info("  sourceId:             %08x\n", data->sourceId);
+
+	pr_info("  errorClass:           %016llx\n", data->errorClass);
+	pr_info("  correlator:           %016llx\n", data->correlator);
+	pr_info("  p7iocPlssr:           %016llx\n", data->p7iocPlssr);
+	pr_info("  p7iocCsr:             %016llx\n", data->p7iocCsr);
+	pr_info("  lemFir:               %016llx\n", data->lemFir);
+	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
+	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
+	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
+	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
+	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
+	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
+	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
+	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
+	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
+	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
+	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
+	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
+	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
+	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
+	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
+	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
+	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
+	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+
+	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
+		if ((data->pestA[i] >> 63) == 0 &&
+		    (data->pestB[i] >> 63) == 0)
+			continue;
+
+		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
+		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+	}
+}
+
+static void ioda_eeh_phb3_phb_diag(struct pci_controller *hose,
+				    struct OpalIoPhbErrorCommon *common)
+{
+	struct OpalIoPhb3ErrorData *data;
+	int i;
+
+	data = (struct OpalIoPhb3ErrorData*)common;
+	pr_info("PHB3 PHB#%x Diag-data (Version: %d)\n\n",
+		hose->global_number, common->version);
+
+	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
+
+	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
+	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
+	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
+
+	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
+	pr_info("  slotStatus:           %08x\n", data->slotStatus);
+	pr_info("  linkStatus:           %08x\n", data->linkStatus);
+	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
+	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
+
+	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
+	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
+	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
+	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
+	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
+	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
+	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
+	pr_info("  sourceId:             %08x\n", data->sourceId);
+	pr_info("  errorClass:           %016llx\n", data->errorClass);
+	pr_info("  correlator:           %016llx\n", data->correlator);
+	pr_info("  nFir:                 %016llx\n", data->nFir);
+	pr_info("  nFirMask:             %016llx\n", data->nFirMask);
+	pr_info("  nFirWOF:              %016llx\n", data->nFirWOF);
+	pr_info("  PhbPlssr:             %016llx\n", data->phbPlssr);
+	pr_info("  PhbCsr:               %016llx\n", data->phbCsr);
+	pr_info("  lemFir:               %016llx\n", data->lemFir);
+	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
+	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
+	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
+	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
+	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
+	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
+	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
+	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
+	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
+	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
+	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
+	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
+	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
+	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
+	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
+	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
+	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
+	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+
+	for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
+		if ((data->pestA[i] >> 63) == 0 &&
+		    (data->pestB[i] >> 63) == 0)
+			continue;
+
+		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
+		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+	}
+}
+
+static void ioda_eeh_phb_diag(struct pci_controller *hose)
+{
+	struct pnv_phb *phb = hose->private_data;
+	struct OpalIoPhbErrorCommon *common;
+	long rc;
+
+	common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, common, PAGE_SIZE);
+	if (rc != OPAL_SUCCESS) {
+		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
+			    __func__, hose->global_number, rc);
+		return;
+	}
+
+	switch (common->ioType) {
+	case OPAL_PHB_ERROR_DATA_TYPE_P7IOC:
+		ioda_eeh_p7ioc_phb_diag(hose, common);
+		break;
+	case OPAL_PHB_ERROR_DATA_TYPE_PHB3:
+		ioda_eeh_phb3_phb_diag(hose, common);
+		break;
+	default:
+		pr_warning("%s: Unrecognized I/O chip %d\n",
+			   __func__, common->ioType);
+	}
+}
+
+static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
+			       struct eeh_pe **pe)
+{
+	struct eeh_pe *phb_pe;
+
+	phb_pe = eeh_phb_pe_get(hose);
+	if (!phb_pe) {
+		pr_warning("%s Can't find PE for PHB#%d\n",
+			   __func__, hose->global_number);
+		return -EEXIST;
+	}
+
+	*pe = phb_pe;
+	return 0;
+}
+
+static int ioda_eeh_get_pe(struct pci_controller *hose,
+			   u16 pe_no, struct eeh_pe **pe)
+{
+	struct eeh_pe *phb_pe, *dev_pe;
+	struct eeh_dev dev;
+
+	/* Find the PHB PE */
+	if (ioda_eeh_get_phb_pe(hose, &phb_pe))
+		return -EEXIST;
+
+	/* Find the PE according to PE# */
+	memset(&dev, 0, sizeof(struct eeh_dev));
+	dev.phb = hose;
+	dev.pe_config_addr = pe_no;
+	dev_pe = eeh_pe_get(&dev);
+	if (!dev_pe) {
+		pr_warning("%s: Can't find PE for PHB#%x - PE#%x\n",
+			   __func__, hose->global_number, pe_no);
+		return -EEXIST;
+	}
+
+	*pe = dev_pe;
+	return 0;
+}
+
+/**
+ * ioda_eeh_next_error - Retrieve next error for EEH core to handle
+ * @pe: The affected PE
+ *
+ * The function is expected to be called by EEH core while it gets
+ * special EEH event (without binding PE). The function calls to
+ * OPAL APIs for next error to handle. The informational error is
+ * handled internally by platform. However, the dead IOC, dead PHB,
+ * fenced PHB and frozen PE should be handled by EEH core eventually.
+ */
+static int ioda_eeh_next_error(struct eeh_pe **pe)
+{
+	struct pci_controller *hose, *tmp;
+	struct pnv_phb *phb;
+	u64 frozen_pe_no;
+	u16 err_type, severity;
+	long rc;
+	int ret = 1;
+
+	/*
+	 * While running here, it's safe to purge the event queue.
+	 * And we should keep the cached OPAL notifier event sychronized
+	 * between the kernel and firmware.
+	 */
+	eeh_remove_event(NULL);
+	opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
+
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		/*
+		 * If the subordinate PCI buses of the PHB has been
+		 * removed, we needn't take care of it any more.
+		 */
+		phb = hose->private_data;
+		if (phb->eeh_state & PNV_EEH_STATE_REMOVED)
+			continue;
+
+		rc = opal_pci_next_error(phb->opal_id,
+				&frozen_pe_no, &err_type, &severity);
+
+		/* If OPAL API returns error, we needn't proceed */
+		if (rc != OPAL_SUCCESS) {
+			pr_devel("%s: Invalid return value on "
+				 "PHB#%x (0x%lx) from opal_pci_next_error",
+				 __func__, hose->global_number, rc);
+			continue;
+		}
+
+		/* If the PHB doesn't have error, stop processing */
+		if (err_type == OPAL_EEH_NO_ERROR ||
+		    severity == OPAL_EEH_SEV_NO_ERROR) {
+			pr_devel("%s: No error found on PHB#%x\n",
+				 __func__, hose->global_number);
+			continue;
+		}
+
+		/*
+		 * Processing the error. We're expecting the error with
+		 * highest priority reported upon multiple errors on the
+		 * specific PHB.
+		 */
+		pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n",
+			 __func__, err_type, severity,
+			 frozen_pe_no, hose->global_number);
+		switch (err_type) {
+		case OPAL_EEH_IOC_ERROR:
+			if (severity == OPAL_EEH_SEV_IOC_DEAD) {
+				list_for_each_entry_safe(hose, tmp,
+						&hose_list, list_node) {
+					phb = hose->private_data;
+					phb->eeh_state |= PNV_EEH_STATE_REMOVED;
+				}
+
+				pr_err("EEH: dead IOC detected\n");
+				ret = 4;
+				goto out;
+			} else if (severity == OPAL_EEH_SEV_INF) {
+				pr_info("EEH: IOC informative error "
+					"detected\n");
+				ioda_eeh_hub_diag(hose);
+			}
+
+			break;
+		case OPAL_EEH_PHB_ERROR:
+			if (severity == OPAL_EEH_SEV_PHB_DEAD) {
+				if (ioda_eeh_get_phb_pe(hose, pe))
+					break;
+
+				pr_err("EEH: dead PHB#%x detected\n",
+					hose->global_number);
+				phb->eeh_state |= PNV_EEH_STATE_REMOVED;
+				ret = 3;
+				goto out;
+			} else if (severity == OPAL_EEH_SEV_PHB_FENCED) {
+				if (ioda_eeh_get_phb_pe(hose, pe))
+					break;
+
+				pr_err("EEH: fenced PHB#%x detected\n",
+					hose->global_number);
+				ret = 2;
+				goto out;
+			} else if (severity == OPAL_EEH_SEV_INF) {
+				pr_info("EEH: PHB#%x informative error "
+					"detected\n",
+					hose->global_number);
+				ioda_eeh_phb_diag(hose);
+			}
+
+			break;
+		case OPAL_EEH_PE_ERROR:
+			if (ioda_eeh_get_pe(hose, frozen_pe_no, pe))
+				break;
+
+			pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
+				(*pe)->addr, (*pe)->phb->global_number);
+			ret = 1;
+			goto out;
+		}
+	}
+
+	ret = 0;
+out:
+	return ret;
+}
+
+struct pnv_eeh_ops ioda_eeh_ops = {
+	.post_init		= ioda_eeh_post_init,
+	.set_option		= ioda_eeh_set_option,
+	.get_state		= ioda_eeh_get_state,
+	.reset			= ioda_eeh_reset,
+	.get_log		= ioda_eeh_get_log,
+	.configure_bridge	= ioda_eeh_configure_bridge,
+	.next_error		= ioda_eeh_next_error
+};
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
new file mode 100644
index 0000000..73b9814
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -0,0 +1,387 @@
+/*
+ * The file intends to implement the platform dependent EEH operations on
+ * powernv platform. Actually, the powernv was created in order to fully
+ * hypervisor support.
+ *
+ * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013.
+ *
+ * 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/atomic.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/pci.h>
+#include <linux/proc_fs.h>
+#include <linux/rbtree.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/firmware.h>
+#include <asm/io.h>
+#include <asm/iommu.h>
+#include <asm/machdep.h>
+#include <asm/msi_bitmap.h>
+#include <asm/opal.h>
+#include <asm/ppc-pci.h>
+
+#include "powernv.h"
+#include "pci.h"
+
+/**
+ * powernv_eeh_init - EEH platform dependent initialization
+ *
+ * EEH platform dependent initialization on powernv
+ */
+static int powernv_eeh_init(void)
+{
+	/* We require OPALv3 */
+	if (!firmware_has_feature(FW_FEATURE_OPALv3)) {
+		pr_warning("%s: OPALv3 is required !\n", __func__);
+		return -EINVAL;
+	}
+
+	/* Set EEH probe mode */
+	eeh_probe_mode_set(EEH_PROBE_MODE_DEV);
+
+	return 0;
+}
+
+/**
+ * powernv_eeh_post_init - EEH platform dependent post initialization
+ *
+ * EEH platform dependent post initialization on powernv. When
+ * the function is called, the EEH PEs and devices should have
+ * been built. If the I/O cache staff has been built, EEH is
+ * ready to supply service.
+ */
+static int powernv_eeh_post_init(void)
+{
+	struct pci_controller *hose;
+	struct pnv_phb *phb;
+	int ret = 0;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		phb = hose->private_data;
+
+		if (phb->eeh_ops && phb->eeh_ops->post_init) {
+			ret = phb->eeh_ops->post_init(hose);
+			if (ret)
+				break;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_dev_probe - Do probe on PCI device
+ * @dev: PCI device
+ * @flag: unused
+ *
+ * When EEH module is installed during system boot, all PCI devices
+ * are checked one by one to see if it supports EEH. The function
+ * is introduced for the purpose. By default, EEH has been enabled
+ * on all PCI devices. That's to say, we only need do necessary
+ * initialization on the corresponding eeh device and create PE
+ * accordingly.
+ *
+ * It's notable that's unsafe to retrieve the EEH device through
+ * the corresponding PCI device. During the PCI device hotplug, which
+ * was possiblly triggered by EEH core, the binding between EEH device
+ * and the PCI device isn't built yet.
+ */
+static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct device_node *dn = pci_device_to_OF_node(dev);
+	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+
+	/*
+	 * When probing the root bridge, which doesn't have any
+	 * subordinate PCI devices. We don't have OF node for
+	 * the root bridge. So it's not reasonable to continue
+	 * the probing.
+	 */
+	if (!dn || !edev || edev->pe)
+		return 0;
+
+	/* Skip for PCI-ISA bridge */
+	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
+		return 0;
+
+	/* Initialize eeh device */
+	edev->class_code = dev->class;
+	edev->mode	&= 0xFFFFFF00;
+	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+		edev->mode |= EEH_DEV_BRIDGE;
+	if (pci_is_pcie(dev)) {
+		edev->pcie_cap = pci_pcie_cap(dev);
+
+		if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+			edev->mode |= EEH_DEV_ROOT_PORT;
+		else if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM)
+			edev->mode |= EEH_DEV_DS_PORT;
+	}
+
+	edev->config_addr	= ((dev->bus->number << 8) | dev->devfn);
+	edev->pe_config_addr	= phb->bdfn_to_pe(phb, dev->bus, dev->devfn & 0xff);
+
+	/* Create PE */
+	eeh_add_to_parent_pe(edev);
+
+	/*
+	 * Enable EEH explicitly so that we will do EEH check
+	 * while accessing I/O stuff
+	 */
+	eeh_subsystem_enabled = 1;
+
+	/* Save memory bars */
+	eeh_save_bars(edev);
+
+	return 0;
+}
+
+/**
+ * powernv_eeh_set_option - Initialize EEH or MMIO/DMA reenable
+ * @pe: EEH PE
+ * @option: operation to be issued
+ *
+ * The function is used to control the EEH functionality globally.
+ * Currently, following options are support according to PAPR:
+ * Enable EEH, Disable EEH, Enable MMIO and Enable DMA
+ */
+static int powernv_eeh_set_option(struct eeh_pe *pe, int option)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = -EEXIST;
+
+	/*
+	 * What we need do is pass it down for hardware
+	 * implementation to handle it.
+	 */
+	if (phb->eeh_ops && phb->eeh_ops->set_option)
+		ret = phb->eeh_ops->set_option(pe, option);
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_get_pe_addr - Retrieve PE address
+ * @pe: EEH PE
+ *
+ * Retrieve the PE address according to the given tranditional
+ * PCI BDF (Bus/Device/Function) address.
+ */
+static int powernv_eeh_get_pe_addr(struct eeh_pe *pe)
+{
+	return pe->addr;
+}
+
+/**
+ * powernv_eeh_get_state - Retrieve PE state
+ * @pe: EEH PE
+ * @delay: delay while PE state is temporarily unavailable
+ *
+ * Retrieve the state of the specified PE. For IODA-compitable
+ * platform, it should be retrieved from IODA table. Therefore,
+ * we prefer passing down to hardware implementation to handle
+ * it.
+ */
+static int powernv_eeh_get_state(struct eeh_pe *pe, int *delay)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = EEH_STATE_NOT_SUPPORT;
+
+	if (phb->eeh_ops && phb->eeh_ops->get_state) {
+		ret = phb->eeh_ops->get_state(pe);
+
+		/*
+		 * If the PE state is temporarily unavailable,
+		 * to inform the EEH core delay for default
+		 * period (1 second)
+		 */
+		if (delay) {
+			*delay = 0;
+			if (ret & EEH_STATE_UNAVAILABLE)
+				*delay = 1000;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_reset - Reset the specified PE
+ * @pe: EEH PE
+ * @option: reset option
+ *
+ * Reset the specified PE
+ */
+static int powernv_eeh_reset(struct eeh_pe *pe, int option)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = -EEXIST;
+
+	if (phb->eeh_ops && phb->eeh_ops->reset)
+		ret = phb->eeh_ops->reset(pe, option);
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_wait_state - Wait for PE state
+ * @pe: EEH PE
+ * @max_wait: maximal period in microsecond
+ *
+ * Wait for the state of associated PE. It might take some time
+ * to retrieve the PE's state.
+ */
+static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
+{
+	int ret;
+	int mwait;
+
+	while (1) {
+		ret = powernv_eeh_get_state(pe, &mwait);
+
+		/*
+		 * If the PE's state is temporarily unavailable,
+		 * we have to wait for the specified time. Otherwise,
+		 * the PE's state will be returned immediately.
+		 */
+		if (ret != EEH_STATE_UNAVAILABLE)
+			return ret;
+
+		max_wait -= mwait;
+		if (max_wait <= 0) {
+			pr_warning("%s: Timeout getting PE#%x's state (%d)\n",
+				   __func__, pe->addr, max_wait);
+			return EEH_STATE_NOT_SUPPORT;
+		}
+
+		msleep(mwait);
+	}
+
+	return EEH_STATE_NOT_SUPPORT;
+}
+
+/**
+ * powernv_eeh_get_log - Retrieve error log
+ * @pe: EEH PE
+ * @severity: temporary or permanent error log
+ * @drv_log: driver log to be combined with retrieved error log
+ * @len: length of driver log
+ *
+ * Retrieve the temporary or permanent error from the PE.
+ */
+static int powernv_eeh_get_log(struct eeh_pe *pe, int severity,
+			char *drv_log, unsigned long len)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = -EEXIST;
+
+	if (phb->eeh_ops && phb->eeh_ops->get_log)
+		ret = phb->eeh_ops->get_log(pe, severity, drv_log, len);
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_configure_bridge - Configure PCI bridges in the indicated PE
+ * @pe: EEH PE
+ *
+ * The function will be called to reconfigure the bridges included
+ * in the specified PE so that the mulfunctional PE would be recovered
+ * again.
+ */
+static int powernv_eeh_configure_bridge(struct eeh_pe *pe)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = 0;
+
+	if (phb->eeh_ops && phb->eeh_ops->configure_bridge)
+		ret = phb->eeh_ops->configure_bridge(pe);
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_next_error - Retrieve next EEH error to handle
+ * @pe: Affected PE
+ *
+ * Using OPAL API, to retrieve next EEH error for EEH core to handle
+ */
+static int powernv_eeh_next_error(struct eeh_pe **pe)
+{
+	struct pci_controller *hose;
+	struct pnv_phb *phb = NULL;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		phb = hose->private_data;
+		break;
+	}
+
+	if (phb && phb->eeh_ops->next_error)
+		return phb->eeh_ops->next_error(pe);
+
+	return -EEXIST;
+}
+
+static struct eeh_ops powernv_eeh_ops = {
+	.name                   = "powernv",
+	.init                   = powernv_eeh_init,
+	.post_init              = powernv_eeh_post_init,
+	.of_probe               = NULL,
+	.dev_probe              = powernv_eeh_dev_probe,
+	.set_option             = powernv_eeh_set_option,
+	.get_pe_addr            = powernv_eeh_get_pe_addr,
+	.get_state              = powernv_eeh_get_state,
+	.reset                  = powernv_eeh_reset,
+	.wait_state             = powernv_eeh_wait_state,
+	.get_log                = powernv_eeh_get_log,
+	.configure_bridge       = powernv_eeh_configure_bridge,
+	.read_config            = pnv_pci_cfg_read,
+	.write_config           = pnv_pci_cfg_write,
+	.next_error		= powernv_eeh_next_error
+};
+
+/**
+ * eeh_powernv_init - Register platform dependent EEH operations
+ *
+ * EEH initialization on powernv platform. This function should be
+ * called before any EEH related functions.
+ */
+static int __init eeh_powernv_init(void)
+{
+	int ret = -EINVAL;
+
+	if (!machine_is(powernv))
+		return ret;
+
+	ret = eeh_ops_register(&powernv_eeh_ops);
+	if (!ret)
+		pr_info("EEH: PowerNV platform initialized\n");
+	else
+		pr_info("EEH: Failed to initialize PowerNV platform (%d)\n", ret);
+
+	return ret;
+}
+
+early_initcall(eeh_powernv_init);
diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
new file mode 100644
index 0000000..6ffa6b1
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -0,0 +1,667 @@
+/*
+ * PowerNV OPAL Firmware Update Interface
+ *
+ * Copyright 2013 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/reboot.h>
+#include <linux/init.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/pagemap.h>
+
+#include <asm/opal.h>
+
+/* FLASH status codes */
+#define FLASH_NO_OP		-1099	/* No operation initiated by user */
+#define FLASH_NO_AUTH		-9002	/* Not a service authority partition */
+
+/* Validate image status values */
+#define VALIDATE_IMG_READY	-1001	/* Image ready for validation */
+#define VALIDATE_IMG_INCOMPLETE	-1002	/* User copied < VALIDATE_BUF_SIZE */
+
+/* Manage image status values */
+#define MANAGE_ACTIVE_ERR	-9001	/* Cannot overwrite active img */
+
+/* Flash image status values */
+#define FLASH_IMG_READY		0	/* Img ready for flash on reboot */
+#define FLASH_INVALID_IMG	-1003	/* Flash image shorter than expected */
+#define FLASH_IMG_NULL_DATA	-1004	/* Bad data in sg list entry */
+#define FLASH_IMG_BAD_LEN	-1005	/* Bad length in sg list entry */
+
+/* Manage operation tokens */
+#define FLASH_REJECT_TMP_SIDE	0	/* Reject temporary fw image */
+#define FLASH_COMMIT_TMP_SIDE	1	/* Commit temporary fw image */
+
+/* Update tokens */
+#define FLASH_UPDATE_CANCEL	0	/* Cancel update request */
+#define FLASH_UPDATE_INIT	1	/* Initiate update */
+
+/* Validate image update result tokens */
+#define VALIDATE_TMP_UPDATE	0     /* T side will be updated */
+#define VALIDATE_FLASH_AUTH	1     /* Partition does not have authority */
+#define VALIDATE_INVALID_IMG	2     /* Candidate image is not valid */
+#define VALIDATE_CUR_UNKNOWN	3     /* Current fixpack level is unknown */
+/*
+ * Current T side will be committed to P side before being replace with new
+ * image, and the new image is downlevel from current image
+ */
+#define VALIDATE_TMP_COMMIT_DL	4
+/*
+ * Current T side will be committed to P side before being replaced with new
+ * image
+ */
+#define VALIDATE_TMP_COMMIT	5
+/*
+ * T side will be updated with a downlevel image
+ */
+#define VALIDATE_TMP_UPDATE_DL	6
+/*
+ * The candidate image's release date is later than the system's firmware
+ * service entitlement date - service warranty period has expired
+ */
+#define VALIDATE_OUT_OF_WRNTY	7
+
+/* Validate buffer size */
+#define VALIDATE_BUF_SIZE	4096
+
+/* XXX: Assume candidate image size is <= 256MB */
+#define MAX_IMAGE_SIZE	0x10000000
+
+/* Flash sg list version */
+#define SG_LIST_VERSION (1UL)
+
+/* Image status */
+enum {
+	IMAGE_INVALID,
+	IMAGE_LOADING,
+	IMAGE_READY,
+};
+
+/* Candidate image data */
+struct image_data_t {
+	int		status;
+	void		*data;
+	uint32_t	size;
+};
+
+/* Candidate image header */
+struct image_header_t {
+	uint16_t	magic;
+	uint16_t	version;
+	uint32_t	size;
+};
+
+/* Scatter/gather entry */
+struct opal_sg_entry {
+	void	*data;
+	long	length;
+};
+
+/* We calculate number of entries based on PAGE_SIZE */
+#define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry))
+
+/*
+ * This struct is very similar but not identical to that
+ * needed by the opal flash update. All we need to do for
+ * opal is rewrite num_entries into a version/length and
+ * translate the pointers to absolute.
+ */
+struct opal_sg_list {
+	unsigned long num_entries;
+	struct opal_sg_list *next;
+	struct opal_sg_entry entry[SG_ENTRIES_PER_NODE];
+};
+
+struct validate_flash_t {
+	int		status;		/* Return status */
+	void		*buf;		/* Candiate image buffer */
+	uint32_t	buf_size;	/* Image size */
+	uint32_t	result;		/* Update results token */
+};
+
+struct manage_flash_t {
+	int status;		/* Return status */
+};
+
+struct update_flash_t {
+	int status;		/* Return status */
+};
+
+static struct image_header_t	image_header;
+static struct image_data_t	image_data;
+static struct validate_flash_t	validate_flash_data;
+static struct manage_flash_t	manage_flash_data;
+static struct update_flash_t	update_flash_data;
+
+static DEFINE_MUTEX(image_data_mutex);
+
+/*
+ * Validate candidate image
+ */
+static inline void opal_flash_validate(void)
+{
+	struct validate_flash_t *args_buf = &validate_flash_data;
+
+	args_buf->status = opal_validate_flash(__pa(args_buf->buf),
+					       &(args_buf->buf_size),
+					       &(args_buf->result));
+}
+
+/*
+ * Validate output format:
+ *     validate result token
+ *     current image version details
+ *     new image version details
+ */
+static ssize_t validate_show(struct kobject *kobj,
+			     struct kobj_attribute *attr, char *buf)
+{
+	struct validate_flash_t *args_buf = &validate_flash_data;
+	int len;
+
+	/* Candidate image is not validated */
+	if (args_buf->status < VALIDATE_TMP_UPDATE) {
+		len = sprintf(buf, "%d\n", args_buf->status);
+		goto out;
+	}
+
+	/* Result token */
+	len = sprintf(buf, "%d\n", args_buf->result);
+
+	/* Current and candidate image version details */
+	if ((args_buf->result != VALIDATE_TMP_UPDATE) &&
+	    (args_buf->result < VALIDATE_CUR_UNKNOWN))
+		goto out;
+
+	if (args_buf->buf_size > (VALIDATE_BUF_SIZE - len)) {
+		memcpy(buf + len, args_buf->buf, VALIDATE_BUF_SIZE - len);
+		len = VALIDATE_BUF_SIZE;
+	} else {
+		memcpy(buf + len, args_buf->buf, args_buf->buf_size);
+		len += args_buf->buf_size;
+	}
+out:
+	/* Set status to default */
+	args_buf->status = FLASH_NO_OP;
+	return len;
+}
+
+/*
+ * Validate candidate firmware image
+ *
+ * Note:
+ *   We are only interested in first 4K bytes of the
+ *   candidate image.
+ */
+static ssize_t validate_store(struct kobject *kobj,
+			      struct kobj_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct validate_flash_t *args_buf = &validate_flash_data;
+
+	if (buf[0] != '1')
+		return -EINVAL;
+
+	mutex_lock(&image_data_mutex);
+
+	if (image_data.status != IMAGE_READY ||
+	    image_data.size < VALIDATE_BUF_SIZE) {
+		args_buf->result = VALIDATE_INVALID_IMG;
+		args_buf->status = VALIDATE_IMG_INCOMPLETE;
+		goto out;
+	}
+
+	/* Copy first 4k bytes of candidate image */
+	memcpy(args_buf->buf, image_data.data, VALIDATE_BUF_SIZE);
+
+	args_buf->status = VALIDATE_IMG_READY;
+	args_buf->buf_size = VALIDATE_BUF_SIZE;
+
+	/* Validate candidate image */
+	opal_flash_validate();
+
+out:
+	mutex_unlock(&image_data_mutex);
+	return count;
+}
+
+/*
+ * Manage flash routine
+ */
+static inline void opal_flash_manage(uint8_t op)
+{
+	struct manage_flash_t *const args_buf = &manage_flash_data;
+
+	args_buf->status = opal_manage_flash(op);
+}
+
+/*
+ * Show manage flash status
+ */
+static ssize_t manage_show(struct kobject *kobj,
+			   struct kobj_attribute *attr, char *buf)
+{
+	struct manage_flash_t *const args_buf = &manage_flash_data;
+	int rc;
+
+	rc = sprintf(buf, "%d\n", args_buf->status);
+	/* Set status to default*/
+	args_buf->status = FLASH_NO_OP;
+	return rc;
+}
+
+/*
+ * Manage operations:
+ *   0 - Reject
+ *   1 - Commit
+ */
+static ssize_t manage_store(struct kobject *kobj,
+			    struct kobj_attribute *attr,
+			    const char *buf, size_t count)
+{
+	uint8_t op;
+	switch (buf[0]) {
+	case '0':
+		op = FLASH_REJECT_TMP_SIDE;
+		break;
+	case '1':
+		op = FLASH_COMMIT_TMP_SIDE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* commit/reject temporary image */
+	opal_flash_manage(op);
+	return count;
+}
+
+/*
+ * Free sg list
+ */
+static void free_sg_list(struct opal_sg_list *list)
+{
+	struct opal_sg_list *sg1;
+	while (list) {
+		sg1 = list->next;
+		kfree(list);
+		list = sg1;
+	}
+	list = NULL;
+}
+
+/*
+ * Build candidate image scatter gather list
+ *
+ * list format:
+ *   -----------------------------------
+ *  |  VER (8) | Entry length in bytes  |
+ *   -----------------------------------
+ *  |  Pointer to next entry            |
+ *   -----------------------------------
+ *  |  Address of memory area 1         |
+ *   -----------------------------------
+ *  |  Length of memory area 1          |
+ *   -----------------------------------
+ *  |   .........                       |
+ *   -----------------------------------
+ *  |   .........                       |
+ *   -----------------------------------
+ *  |  Address of memory area N         |
+ *   -----------------------------------
+ *  |  Length of memory area N          |
+ *   -----------------------------------
+ */
+static struct opal_sg_list *image_data_to_sglist(void)
+{
+	struct opal_sg_list *sg1, *list = NULL;
+	void *addr;
+	int size;
+
+	addr = image_data.data;
+	size = image_data.size;
+
+	sg1 = kzalloc((sizeof(struct opal_sg_list)), GFP_KERNEL);
+	if (!sg1)
+		return NULL;
+
+	list = sg1;
+	sg1->num_entries = 0;
+	while (size > 0) {
+		/* Translate virtual address to physical address */
+		sg1->entry[sg1->num_entries].data =
+			(void *)(vmalloc_to_pfn(addr) << PAGE_SHIFT);
+
+		if (size > PAGE_SIZE)
+			sg1->entry[sg1->num_entries].length = PAGE_SIZE;
+		else
+			sg1->entry[sg1->num_entries].length = size;
+
+		sg1->num_entries++;
+		if (sg1->num_entries >= SG_ENTRIES_PER_NODE) {
+			sg1->next = kzalloc((sizeof(struct opal_sg_list)),
+					    GFP_KERNEL);
+			if (!sg1->next) {
+				pr_err("%s : Failed to allocate memory\n",
+				       __func__);
+				goto nomem;
+			}
+
+			sg1 = sg1->next;
+			sg1->num_entries = 0;
+		}
+		addr += PAGE_SIZE;
+		size -= PAGE_SIZE;
+	}
+	return list;
+nomem:
+	free_sg_list(list);
+	return NULL;
+}
+
+/*
+ * OPAL update flash
+ */
+static int opal_flash_update(int op)
+{
+	struct opal_sg_list *sg, *list, *next;
+	unsigned long addr;
+	int64_t rc = OPAL_PARAMETER;
+
+	if (op == FLASH_UPDATE_CANCEL) {
+		pr_alert("FLASH: Image update cancelled\n");
+		addr = '\0';
+		goto flash;
+	}
+
+	list = image_data_to_sglist();
+	if (!list)
+		goto invalid_img;
+
+	/* First entry address */
+	addr = __pa(list);
+
+	/* Translate sg list address to absolute */
+	for (sg = list; sg; sg = next) {
+		next = sg->next;
+		/* Don't translate NULL pointer for last entry */
+		if (sg->next)
+			sg->next = (struct opal_sg_list *)__pa(sg->next);
+		else
+			sg->next = NULL;
+
+		/* Make num_entries into the version/length field */
+		sg->num_entries = (SG_LIST_VERSION << 56) |
+			(sg->num_entries * sizeof(struct opal_sg_entry) + 16);
+	}
+
+	pr_alert("FLASH: Image is %u bytes\n", image_data.size);
+	pr_alert("FLASH: Image update requested\n");
+	pr_alert("FLASH: Image will be updated during system reboot\n");
+	pr_alert("FLASH: This will take several minutes. Do not power off!\n");
+
+flash:
+	rc = opal_update_flash(addr);
+
+invalid_img:
+	return rc;
+}
+
+/*
+ * Show candidate image status
+ */
+static ssize_t update_show(struct kobject *kobj,
+			   struct kobj_attribute *attr, char *buf)
+{
+	struct update_flash_t *const args_buf = &update_flash_data;
+	return sprintf(buf, "%d\n", args_buf->status);
+}
+
+/*
+ * Set update image flag
+ *  1 - Flash new image
+ *  0 - Cancel flash request
+ */
+static ssize_t update_store(struct kobject *kobj,
+			    struct kobj_attribute *attr,
+			    const char *buf, size_t count)
+{
+	struct update_flash_t *const args_buf = &update_flash_data;
+	int rc = count;
+
+	mutex_lock(&image_data_mutex);
+
+	switch (buf[0]) {
+	case '0':
+		if (args_buf->status == FLASH_IMG_READY)
+			opal_flash_update(FLASH_UPDATE_CANCEL);
+		args_buf->status = FLASH_NO_OP;
+		break;
+	case '1':
+		/* Image is loaded? */
+		if (image_data.status == IMAGE_READY)
+			args_buf->status =
+				opal_flash_update(FLASH_UPDATE_INIT);
+		else
+			args_buf->status = FLASH_INVALID_IMG;
+		break;
+	default:
+		rc = -EINVAL;
+	}
+
+	mutex_unlock(&image_data_mutex);
+	return rc;
+}
+
+/*
+ * Free image buffer
+ */
+static void free_image_buf(void)
+{
+	void *addr;
+	int size;
+
+	addr = image_data.data;
+	size = PAGE_ALIGN(image_data.size);
+	while (size > 0) {
+		ClearPageReserved(vmalloc_to_page(addr));
+		addr += PAGE_SIZE;
+		size -= PAGE_SIZE;
+	}
+	vfree(image_data.data);
+	image_data.data = NULL;
+	image_data.status = IMAGE_INVALID;
+}
+
+/*
+ * Allocate image buffer.
+ */
+static int alloc_image_buf(char *buffer, size_t count)
+{
+	void *addr;
+	int size;
+
+	if (count < sizeof(struct image_header_t)) {
+		pr_warn("FLASH: Invalid candidate image\n");
+		return -EINVAL;
+	}
+
+	memcpy(&image_header, (void *)buffer, sizeof(struct image_header_t));
+	image_data.size = be32_to_cpu(image_header.size);
+	pr_debug("FLASH: Candiate image size = %u\n", image_data.size);
+
+	if (image_data.size > MAX_IMAGE_SIZE) {
+		pr_warn("FLASH: Too large image\n");
+		return -EINVAL;
+	}
+	if (image_data.size < VALIDATE_BUF_SIZE) {
+		pr_warn("FLASH: Image is shorter than expected\n");
+		return -EINVAL;
+	}
+
+	image_data.data = vzalloc(PAGE_ALIGN(image_data.size));
+	if (!image_data.data) {
+		pr_err("%s : Failed to allocate memory\n", __func__);
+		return -ENOMEM;
+	}
+
+	/* Pin memory */
+	addr = image_data.data;
+	size = PAGE_ALIGN(image_data.size);
+	while (size > 0) {
+		SetPageReserved(vmalloc_to_page(addr));
+		addr += PAGE_SIZE;
+		size -= PAGE_SIZE;
+	}
+
+	image_data.status = IMAGE_LOADING;
+	return 0;
+}
+
+/*
+ * Copy candidate image
+ *
+ * Parse candidate image header to get total image size
+ * and pre-allocate required memory.
+ */
+static ssize_t image_data_write(struct file *filp, struct kobject *kobj,
+				struct bin_attribute *bin_attr,
+				char *buffer, loff_t pos, size_t count)
+{
+	int rc;
+
+	mutex_lock(&image_data_mutex);
+
+	/* New image ? */
+	if (pos == 0) {
+		/* Free memory, if already allocated */
+		if (image_data.data)
+			free_image_buf();
+
+		/* Cancel outstanding image update request */
+		if (update_flash_data.status == FLASH_IMG_READY)
+			opal_flash_update(FLASH_UPDATE_CANCEL);
+
+		/* Allocate memory */
+		rc = alloc_image_buf(buffer, count);
+		if (rc)
+			goto out;
+	}
+
+	if (image_data.status != IMAGE_LOADING) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	if ((pos + count) > image_data.size) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	memcpy(image_data.data + pos, (void *)buffer, count);
+	rc = count;
+
+	/* Set image status */
+	if ((pos + count) == image_data.size) {
+		pr_debug("FLASH: Candidate image loaded....\n");
+		image_data.status = IMAGE_READY;
+	}
+
+out:
+	mutex_unlock(&image_data_mutex);
+	return rc;
+}
+
+/*
+ * sysfs interface :
+ *  OPAL uses below sysfs files for code update.
+ *  We create these files under /sys/firmware/opal.
+ *
+ *   image		: Interface to load candidate firmware image
+ *   validate_flash	: Validate firmware image
+ *   manage_flash	: Commit/Reject firmware image
+ *   update_flash	: Flash new firmware image
+ *
+ */
+static struct bin_attribute image_data_attr = {
+	.attr = {.name = "image", .mode = 0200},
+	.size = MAX_IMAGE_SIZE,	/* Limit image size */
+	.write = image_data_write,
+};
+
+static struct kobj_attribute validate_attribute =
+	__ATTR(validate_flash, 0600, validate_show, validate_store);
+
+static struct kobj_attribute manage_attribute =
+	__ATTR(manage_flash, 0600, manage_show, manage_store);
+
+static struct kobj_attribute update_attribute =
+	__ATTR(update_flash, 0600, update_show, update_store);
+
+static struct attribute *image_op_attrs[] = {
+	&validate_attribute.attr,
+	&manage_attribute.attr,
+	&update_attribute.attr,
+	NULL	/* need to NULL terminate the list of attributes */
+};
+
+static struct attribute_group image_op_attr_group = {
+	.attrs = image_op_attrs,
+};
+
+void __init opal_flash_init(void)
+{
+	int ret;
+
+	/* Allocate validate image buffer */
+	validate_flash_data.buf = kzalloc(VALIDATE_BUF_SIZE, GFP_KERNEL);
+	if (!validate_flash_data.buf) {
+		pr_err("%s : Failed to allocate memory\n", __func__);
+		return;
+	}
+
+	/* Make sure /sys/firmware/opal directory is created */
+	if (!opal_kobj) {
+		pr_warn("FLASH: opal kobject is not available\n");
+		goto nokobj;
+	}
+
+	/* Create the sysfs files */
+	ret = sysfs_create_group(opal_kobj, &image_op_attr_group);
+	if (ret) {
+		pr_warn("FLASH: Failed to create sysfs files\n");
+		goto nokobj;
+	}
+
+	ret = sysfs_create_bin_file(opal_kobj, &image_data_attr);
+	if (ret) {
+		pr_warn("FLASH: Failed to create sysfs files\n");
+		goto nosysfs_file;
+	}
+
+	/* Set default status */
+	validate_flash_data.status = FLASH_NO_OP;
+	manage_flash_data.status = FLASH_NO_OP;
+	update_flash_data.status = FLASH_NO_OP;
+	image_data.status = IMAGE_INVALID;
+	return;
+
+nosysfs_file:
+	sysfs_remove_group(opal_kobj, &image_op_attr_group);
+
+nokobj:
+	kfree(validate_flash_data.buf);
+	return;
+}
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
new file mode 100644
index 0000000..e7e59e4
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -0,0 +1,204 @@
+/*
+ * PowerNV LPC bus handling.
+ *
+ * Copyright 2013 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/of.h>
+#include <linux/bug.h>
+
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+#include <asm/xics.h>
+#include <asm/opal.h>
+#include <asm/prom.h>
+
+static int opal_lpc_chip_id = -1;
+
+static u8 opal_lpc_inb(unsigned long port)
+{
+	int64_t rc;
+	uint32_t data;
+
+	if (opal_lpc_chip_id < 0 || port > 0xffff)
+		return 0xff;
+	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 1);
+	return rc ? 0xff : data;
+}
+
+static __le16 __opal_lpc_inw(unsigned long port)
+{
+	int64_t rc;
+	uint32_t data;
+
+	if (opal_lpc_chip_id < 0 || port > 0xfffe)
+		return 0xffff;
+	if (port & 1)
+		return (__le16)opal_lpc_inb(port) << 8 | opal_lpc_inb(port + 1);
+	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 2);
+	return rc ? 0xffff : data;
+}
+static u16 opal_lpc_inw(unsigned long port)
+{
+	return le16_to_cpu(__opal_lpc_inw(port));
+}
+
+static __le32 __opal_lpc_inl(unsigned long port)
+{
+	int64_t rc;
+	uint32_t data;
+
+	if (opal_lpc_chip_id < 0 || port > 0xfffc)
+		return 0xffffffff;
+	if (port & 3)
+		return (__le32)opal_lpc_inb(port    ) << 24 |
+		       (__le32)opal_lpc_inb(port + 1) << 16 |
+		       (__le32)opal_lpc_inb(port + 2) <<  8 |
+			       opal_lpc_inb(port + 3);
+	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 4);
+	return rc ? 0xffffffff : data;
+}
+
+static u32 opal_lpc_inl(unsigned long port)
+{
+	return le32_to_cpu(__opal_lpc_inl(port));
+}
+
+static void opal_lpc_outb(u8 val, unsigned long port)
+{
+	if (opal_lpc_chip_id < 0 || port > 0xffff)
+		return;
+	opal_lpc_write(opal_lpc_chip_id, OPAL_LPC_IO, port, val, 1);
+}
+
+static void __opal_lpc_outw(__le16 val, unsigned long port)
+{
+	if (opal_lpc_chip_id < 0 || port > 0xfffe)
+		return;
+	if (port & 1) {
+		opal_lpc_outb(val >> 8, port);
+		opal_lpc_outb(val     , port + 1);
+		return;
+	}
+	opal_lpc_write(opal_lpc_chip_id, OPAL_LPC_IO, port, val, 2);
+}
+
+static void opal_lpc_outw(u16 val, unsigned long port)
+{
+	__opal_lpc_outw(cpu_to_le16(val), port);
+}
+
+static void __opal_lpc_outl(__le32 val, unsigned long port)
+{
+	if (opal_lpc_chip_id < 0 || port > 0xfffc)
+		return;
+	if (port & 3) {
+		opal_lpc_outb(val >> 24, port);
+		opal_lpc_outb(val >> 16, port + 1);
+		opal_lpc_outb(val >>  8, port + 2);
+		opal_lpc_outb(val      , port + 3);
+		return;
+	}
+	opal_lpc_write(opal_lpc_chip_id, OPAL_LPC_IO, port, val, 4);
+}
+
+static void opal_lpc_outl(u32 val, unsigned long port)
+{
+	__opal_lpc_outl(cpu_to_le32(val), port);
+}
+
+static void opal_lpc_insb(unsigned long p, void *b, unsigned long c)
+{
+	u8 *ptr = b;
+
+	while(c--)
+		*(ptr++) = opal_lpc_inb(p);
+}
+
+static void opal_lpc_insw(unsigned long p, void *b, unsigned long c)
+{
+	__le16 *ptr = b;
+
+	while(c--)
+		*(ptr++) = __opal_lpc_inw(p);
+}
+
+static void opal_lpc_insl(unsigned long p, void *b, unsigned long c)
+{
+	__le32 *ptr = b;
+
+	while(c--)
+		*(ptr++) = __opal_lpc_inl(p);
+}
+
+static void opal_lpc_outsb(unsigned long p, const void *b, unsigned long c)
+{
+	const u8 *ptr = b;
+
+	while(c--)
+		opal_lpc_outb(*(ptr++), p);
+}
+
+static void opal_lpc_outsw(unsigned long p, const void *b, unsigned long c)
+{
+	const __le16 *ptr = b;
+
+	while(c--)
+		__opal_lpc_outw(*(ptr++), p);
+}
+
+static void opal_lpc_outsl(unsigned long p, const void *b, unsigned long c)
+{
+	const __le32 *ptr = b;
+
+	while(c--)
+		__opal_lpc_outl(*(ptr++), p);
+}
+
+static const struct ppc_pci_io opal_lpc_io = {
+	.inb	= opal_lpc_inb,
+	.inw	= opal_lpc_inw,
+	.inl	= opal_lpc_inl,
+	.outb	= opal_lpc_outb,
+	.outw	= opal_lpc_outw,
+	.outl	= opal_lpc_outl,
+	.insb	= opal_lpc_insb,
+	.insw	= opal_lpc_insw,
+	.insl	= opal_lpc_insl,
+	.outsb	= opal_lpc_outsb,
+	.outsw	= opal_lpc_outsw,
+	.outsl	= opal_lpc_outsl,
+};
+
+void opal_lpc_init(void)
+{
+	struct device_node *np;
+
+	/*
+	 * Look for a Power8 LPC bus tagged as "primary",
+	 * we currently support only one though the OPAL APIs
+	 * support any number.
+	 */
+	for_each_compatible_node(np, NULL, "ibm,power8-lpc") {
+		if (!of_device_is_available(np))
+			continue;
+		if (!of_get_property(np, "primary", NULL))
+			continue;
+		opal_lpc_chip_id = of_get_ibm_chip_id(np);
+		break;
+	}
+	if (opal_lpc_chip_id < 0)
+		return;
+
+	/* Setup special IO ops */
+	ppc_pci_io = opal_lpc_io;
+	isa_io_special = true;
+
+	pr_info("OPAL: Power8 LPC bus found, chip ID %d\n", opal_lpc_chip_id);
+}
diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c
index 3f83e1a..acd9f7e 100644
--- a/arch/powerpc/platforms/powernv/opal-nvram.c
+++ b/arch/powerpc/platforms/powernv/opal-nvram.c
@@ -65,7 +65,7 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index)
 void __init opal_nvram_init(void)
 {
 	struct device_node *np;
-	const u32 *nbytes_p;
+	const __be32 *nbytes_p;
 
 	np = of_find_compatible_node(NULL, NULL, "ibm,opal-nvram");
 	if (np == NULL)
@@ -76,7 +76,7 @@ void __init opal_nvram_init(void)
 		of_node_put(np);
 		return;
 	}
-	nvram_size = *nbytes_p;
+	nvram_size = be32_to_cpup(nbytes_p);
 
 	printk(KERN_INFO "OPAL nvram setup, %u bytes\n", nvram_size);
 	of_node_put(np);
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index 2aa7641..7d07c7e 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -37,10 +37,12 @@ unsigned long __init opal_get_boot_time(void)
 	struct rtc_time tm;
 	u32 y_m_d;
 	u64 h_m_s_ms;
+	__be32 __y_m_d;
+	__be64 __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);
+		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
 		if (rc == OPAL_BUSY_EVENT)
 			opal_poll_events(NULL);
 		else
@@ -48,6 +50,8 @@ unsigned long __init opal_get_boot_time(void)
 	}
 	if (rc != OPAL_SUCCESS)
 		return 0;
+	y_m_d = be32_to_cpu(__y_m_d);
+	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
 	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);
@@ -58,9 +62,11 @@ void opal_get_rtc_time(struct rtc_time *tm)
 	long rc = OPAL_BUSY;
 	u32 y_m_d;
 	u64 h_m_s_ms;
+	__be32 __y_m_d;
+	__be64 __h_m_s_ms;
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-		rc = opal_rtc_read(&y_m_d, &h_m_s_ms);
+		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
 		if (rc == OPAL_BUSY_EVENT)
 			opal_poll_events(NULL);
 		else
@@ -68,6 +74,8 @@ void opal_get_rtc_time(struct rtc_time *tm)
 	}
 	if (rc != OPAL_SUCCESS)
 		return;
+	y_m_d = be32_to_cpu(__y_m_d);
+	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
 	opal_to_tm(y_m_d, h_m_s_ms, tm);
 }
 
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 6fabe92..e780650 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -24,7 +24,7 @@
 	mflr	r0;			\
 	mfcr	r12;			\
 	std	r0,16(r1);		\
-	std	r12,8(r1);		\
+	stw	r12,8(r1);		\
 	std	r1,PACAR1(r13);		\
 	li	r0,0;			\
 	mfmsr	r12;			\
@@ -34,7 +34,7 @@
 	mtmsrd	r12,1;			\
 	LOAD_REG_ADDR(r0,.opal_return);	\
 	mtlr	r0;			\
-	li	r0,MSR_DR|MSR_IR;	\
+	li	r0,MSR_DR|MSR_IR|MSR_LE;\
 	andc	r12,r12,r0;		\
 	li	r0,token;		\
 	mtspr	SPRN_HSRR1,r12;		\
@@ -45,8 +45,15 @@
 	hrfid
 
 _STATIC(opal_return)
+	/*
+	 * Fixup endian on OPAL return... we should be able to simplify
+	 * this by instead converting the below trampoline to a set of
+	 * bytes (always BE) since MSR:LE will end up fixed up as a side
+	 * effect of the rfid.
+	 */
+	FIXUP_ENDIAN
 	ld	r2,PACATOC(r13);
-	ld	r4,8(r1);
+	lwz	r4,8(r1);
 	ld	r5,16(r1);
 	ld	r6,PACASAVEDMSR(r13);
 	mtspr	SPRN_SRR0,r5;
@@ -107,4 +114,15 @@ OPAL_CALL(opal_pci_mask_pe_error,		OPAL_PCI_MASK_PE_ERROR);
 OPAL_CALL(opal_set_slot_led_status,		OPAL_SET_SLOT_LED_STATUS);
 OPAL_CALL(opal_get_epow_status,			OPAL_GET_EPOW_STATUS);
 OPAL_CALL(opal_set_system_attention_led,	OPAL_SET_SYSTEM_ATTENTION_LED);
+OPAL_CALL(opal_pci_next_error,			OPAL_PCI_NEXT_ERROR);
+OPAL_CALL(opal_pci_poll,			OPAL_PCI_POLL);
 OPAL_CALL(opal_pci_msi_eoi,			OPAL_PCI_MSI_EOI);
+OPAL_CALL(opal_pci_get_phb_diag_data2,		OPAL_PCI_GET_PHB_DIAG_DATA2);
+OPAL_CALL(opal_xscom_read,			OPAL_XSCOM_READ);
+OPAL_CALL(opal_xscom_write,			OPAL_XSCOM_WRITE);
+OPAL_CALL(opal_lpc_read,			OPAL_LPC_READ);
+OPAL_CALL(opal_lpc_write,			OPAL_LPC_WRITE);
+OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
+OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
+OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
+OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
new file mode 100644
index 0000000..4d99a8f
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -0,0 +1,128 @@
+/*
+ * PowerNV LPC bus handling.
+ *
+ * Copyright 2013 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/of.h>
+#include <linux/bug.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+#include <asm/opal.h>
+#include <asm/scom.h>
+
+/*
+ * We could probably fit that inside the scom_map_t
+ * which is a void* after all but it's really too ugly
+ * so let's kmalloc it for now
+ */
+struct opal_scom_map {
+	uint32_t chip;
+	uint64_t addr;
+};
+
+static scom_map_t opal_scom_map(struct device_node *dev, u64 reg, u64 count)
+{
+	struct opal_scom_map *m;
+	const __be32 *gcid;
+
+	if (!of_get_property(dev, "scom-controller", NULL)) {
+		pr_err("%s: device %s is not a SCOM controller\n",
+			__func__, dev->full_name);
+		return SCOM_MAP_INVALID;
+	}
+	gcid = of_get_property(dev, "ibm,chip-id", NULL);
+	if (!gcid) {
+		pr_err("%s: device %s has no ibm,chip-id\n",
+			__func__, dev->full_name);
+		return SCOM_MAP_INVALID;
+	}
+	m = kmalloc(sizeof(struct opal_scom_map), GFP_KERNEL);
+	if (!m)
+		return NULL;
+	m->chip = be32_to_cpup(gcid);
+	m->addr = reg;
+
+	return (scom_map_t)m;
+}
+
+static void opal_scom_unmap(scom_map_t map)
+{
+	kfree(map);
+}
+
+static int opal_xscom_err_xlate(int64_t rc)
+{
+	switch(rc) {
+	case 0:
+		return 0;
+	/* Add more translations if necessary */
+	default:
+		return -EIO;
+	}
+}
+
+static u64 opal_scom_unmangle(u64 reg)
+{
+	/*
+	 * XSCOM indirect addresses have the top bit set. Additionally
+	 * the reset of the top 3 nibbles is always 0.
+	 *
+	 * Because the debugfs interface uses signed offsets and shifts
+	 * the address left by 3, we basically cannot use the top 4 bits
+	 * of the 64-bit address, and thus cannot use the indirect bit.
+	 *
+	 * To deal with that, we support the indirect bit being in bit
+	 * 4 (IBM notation) instead of bit 0 in this API, we do the
+	 * conversion here. To leave room for further xscom address
+	 * expansion, we only clear out the top byte
+	 *
+	 */
+	if (reg & (1ull << 59))
+		reg = (reg & ~(0xffull << 56)) | (1ull << 63);
+	return reg;
+}
+
+static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
+{
+	struct opal_scom_map *m = map;
+	int64_t rc;
+
+	reg = opal_scom_unmangle(reg);
+	rc = opal_xscom_read(m->chip, m->addr + reg, (uint64_t *)__pa(value));
+	return opal_xscom_err_xlate(rc);
+}
+
+static int opal_scom_write(scom_map_t map, u64 reg, u64 value)
+{
+	struct opal_scom_map *m = map;
+	int64_t rc;
+
+	reg = opal_scom_unmangle(reg);
+	rc = opal_xscom_write(m->chip, m->addr + reg, value);
+	return opal_xscom_err_xlate(rc);
+}
+
+static const struct scom_controller opal_scom_controller = {
+	.map	= opal_scom_map,
+	.unmap	= opal_scom_unmap,
+	.read	= opal_scom_read,
+	.write	= opal_scom_write
+};
+
+static int opal_xscom_init(void)
+{
+	if (firmware_has_feature(FW_FEATURE_OPALv3))
+		scom_init(&opal_scom_controller);
+	return 0;
+}
+arch_initcall(opal_xscom_init);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 628c564..1c798cd 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -13,14 +13,20 @@
 
 #include <linux/types.h>
 #include <linux/of.h>
+#include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 #include <linux/interrupt.h>
+#include <linux/notifier.h>
 #include <linux/slab.h>
+#include <linux/kobject.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
 
 #include "powernv.h"
 
+/* /sys/firmware/opal */
+struct kobject *opal_kobj;
+
 struct opal {
 	u64 base;
 	u64 entry;
@@ -31,6 +37,10 @@ static DEFINE_SPINLOCK(opal_write_lock);
 extern u64 opal_mc_secondary_handler[];
 static unsigned int *opal_irqs;
 static unsigned int opal_irq_count;
+static ATOMIC_NOTIFIER_HEAD(opal_notifier_head);
+static DEFINE_SPINLOCK(opal_notifier_lock);
+static uint64_t last_notified_mask = 0x0ul;
+static atomic_t opal_notifier_hold = ATOMIC_INIT(0);
 
 int __init early_init_dt_scan_opal(unsigned long node,
 				   const char *uname, int depth, void *data)
@@ -72,6 +82,7 @@ int __init early_init_dt_scan_opal(unsigned long node,
 
 static int __init opal_register_exception_handlers(void)
 {
+#ifdef __BIG_ENDIAN__
 	u64 glue;
 
 	if (!(powerpc_firmware_features & FW_FEATURE_OPAL))
@@ -89,35 +100,99 @@ static int __init opal_register_exception_handlers(void)
 					0, glue);
 	glue += 128;
 	opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue);
+#endif
 
 	return 0;
 }
 
 early_initcall(opal_register_exception_handlers);
 
+int opal_notifier_register(struct notifier_block *nb)
+{
+	if (!nb) {
+		pr_warning("%s: Invalid argument (%p)\n",
+			   __func__, nb);
+		return -EINVAL;
+	}
+
+	atomic_notifier_chain_register(&opal_notifier_head, nb);
+	return 0;
+}
+
+static void opal_do_notifier(uint64_t events)
+{
+	unsigned long flags;
+	uint64_t changed_mask;
+
+	if (atomic_read(&opal_notifier_hold))
+		return;
+
+	spin_lock_irqsave(&opal_notifier_lock, flags);
+	changed_mask = last_notified_mask ^ events;
+	last_notified_mask = events;
+	spin_unlock_irqrestore(&opal_notifier_lock, flags);
+
+	/*
+	 * We feed with the event bits and changed bits for
+	 * enough information to the callback.
+	 */
+	atomic_notifier_call_chain(&opal_notifier_head,
+				   events, (void *)changed_mask);
+}
+
+void opal_notifier_update_evt(uint64_t evt_mask,
+			      uint64_t evt_val)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&opal_notifier_lock, flags);
+	last_notified_mask &= ~evt_mask;
+	last_notified_mask |= evt_val;
+	spin_unlock_irqrestore(&opal_notifier_lock, flags);
+}
+
+void opal_notifier_enable(void)
+{
+	int64_t rc;
+	uint64_t evt = 0;
+
+	atomic_set(&opal_notifier_hold, 0);
+
+	/* Process pending events */
+	rc = opal_poll_events(&evt);
+	if (rc == OPAL_SUCCESS && evt)
+		opal_do_notifier(evt);
+}
+
+void opal_notifier_disable(void)
+{
+	atomic_set(&opal_notifier_hold, 1);
+}
+
 int opal_get_chars(uint32_t vtermno, char *buf, int count)
 {
-	s64 len, rc;
-	u64 evt;
+	s64 rc;
+	__be64 evt, len;
 
 	if (!opal.entry)
 		return -ENODEV;
 	opal_poll_events(&evt);
-	if ((evt & OPAL_EVENT_CONSOLE_INPUT) == 0)
+	if ((be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_INPUT) == 0)
 		return 0;
-	len = count;
-	rc = opal_console_read(vtermno, &len, buf);
+	len = cpu_to_be64(count);
+	rc = opal_console_read(vtermno, &len, buf);	
 	if (rc == OPAL_SUCCESS)
-		return len;
+		return be64_to_cpu(len);
 	return 0;
 }
 
 int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 {
 	int written = 0;
+	__be64 olen;
 	s64 len, rc;
 	unsigned long flags;
-	u64 evt;
+	__be64 evt;
 
 	if (!opal.entry)
 		return -ENODEV;
@@ -132,13 +207,14 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 	 */
 	spin_lock_irqsave(&opal_write_lock, flags);
 	if (firmware_has_feature(FW_FEATURE_OPALv2)) {
-		rc = opal_console_write_buffer_space(vtermno, &len);
+		rc = opal_console_write_buffer_space(vtermno, &olen);
+		len = be64_to_cpu(olen);
 		if (rc || len < total_len) {
 			spin_unlock_irqrestore(&opal_write_lock, flags);
 			/* Closed -> drop characters */
 			if (rc)
 				return total_len;
-			opal_poll_events(&evt);
+			opal_poll_events(NULL);
 			return -EAGAIN;
 		}
 	}
@@ -149,8 +225,9 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 	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);
+		olen = cpu_to_be64(total_len);
+		rc = opal_console_write(vtermno, &olen, data);
+		len = be64_to_cpu(olen);
 
 		/* Closed or other error drop */
 		if (rc != OPAL_SUCCESS && rc != OPAL_BUSY &&
@@ -170,7 +247,8 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 		 */
 		do
 			opal_poll_events(&evt);
-		while(rc == OPAL_SUCCESS && (evt & OPAL_EVENT_CONSOLE_OUTPUT));
+		while(rc == OPAL_SUCCESS &&
+			(be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT));
 	}
 	spin_unlock_irqrestore(&opal_write_lock, flags);
 	return written;
@@ -293,19 +371,30 @@ int opal_machine_check(struct pt_regs *regs)
 
 static irqreturn_t opal_interrupt(int irq, void *data)
 {
-	uint64_t events;
+	__be64 events;
 
 	opal_handle_interrupt(virq_to_hw(irq), &events);
 
-	/* XXX TODO: Do something with the events */
+	opal_do_notifier(events);
 
 	return IRQ_HANDLED;
 }
 
+static int opal_sysfs_init(void)
+{
+	opal_kobj = kobject_create_and_add("opal", firmware_kobj);
+	if (!opal_kobj) {
+		pr_warn("kobject_create_and_add opal failed\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static int __init opal_init(void)
 {
 	struct device_node *np, *consoles;
-	const u32 *irqs;
+	const __be32 *irqs;
 	int rc, i, irqlen;
 
 	opal_node = of_find_node_by_path("/ibm,opal");
@@ -313,18 +402,20 @@ static int __init opal_init(void)
 		pr_warn("opal: Node not found\n");
 		return -ENODEV;
 	}
+
+	/* Register OPAL consoles if any ports */
 	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);
+	if (consoles) {
+		for_each_child_of_node(consoles, np) {
+			if (strcmp(np->name, "serial"))
+				continue;
+			of_platform_device_create(np, NULL, NULL);
+		}
+		of_node_put(consoles);
 	}
-	of_node_put(consoles);
 
 	/* Find all OPAL interrupts and request them */
 	irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
@@ -345,6 +436,14 @@ static int __init opal_init(void)
 				   " (0x%x)\n", rc, irq, hwirq);
 		opal_irqs[i] = irq;
 	}
+
+	/* Create "opal" kobject under /sys/firmware */
+	rc = opal_sysfs_init();
+	if (rc == 0) {
+		/* Setup code update interface */
+		opal_flash_init();
+	}
+
 	return 0;
 }
 subsys_initcall(opal_init);
@@ -355,7 +454,7 @@ void opal_shutdown(void)
 
 	for (i = 0; i < opal_irq_count; i++) {
 		if (opal_irqs[i])
-			free_irq(opal_irqs[i], 0);
+			free_irq(opal_irqs[i], NULL);
 		opal_irqs[i] = 0;
 	}
 }
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 9c9d15e..084cdfa 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -13,6 +13,7 @@
 
 #include <linux/kernel.h>
 #include <linux/pci.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/string.h>
 #include <linux/init.h>
@@ -32,6 +33,7 @@
 #include <asm/iommu.h>
 #include <asm/tce.h>
 #include <asm/xics.h>
+#include <asm/debug.h>
 
 #include "powernv.h"
 #include "pci.h"
@@ -68,6 +70,16 @@ define_pe_printk_level(pe_err, KERN_ERR);
 define_pe_printk_level(pe_warn, KERN_WARNING);
 define_pe_printk_level(pe_info, KERN_INFO);
 
+/*
+ * stdcix is only supposed to be used in hypervisor real mode as per
+ * the architecture spec
+ */
+static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr)
+{
+	__asm__ __volatile__("stdcix %0,0,%1"
+		: : "r" (val), "r" (paddr) : "memory");
+}
+
 static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
 	unsigned long pe;
@@ -151,13 +163,23 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		rid_end = pe->rid + 1;
 	}
 
-	/* Associate PE in PELT */
+	/*
+	 * Associate PE in PELT. We need add the PE into the
+	 * corresponding PELT-V as well. Otherwise, the error
+	 * originated from the PE might contribute to other
+	 * PEs.
+	 */
 	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
 			     bcomp, dcomp, fcomp, OPAL_MAP_PE);
 	if (rc) {
 		pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc);
 		return -ENXIO;
 	}
+
+	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
+				pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
+	if (rc)
+		pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc);
 	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
 				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
 
@@ -441,10 +463,24 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 	set_iommu_table_base(&pdev->dev, &pe->tce32_table);
 }
 
-static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
-					 u64 *startp, u64 *endp)
+static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 {
-	u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index;
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		set_iommu_table_base(&dev->dev, &pe->tce32_table);
+		if (dev->subordinate)
+			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+	}
+}
+
+static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe,
+					 struct iommu_table *tbl,
+					 __be64 *startp, __be64 *endp, bool rm)
+{
+	__be64 __iomem *invalidate = rm ?
+		(__be64 __iomem *)pe->tce_inval_reg_phys :
+		(__be64 __iomem *)tbl->it_index;
 	unsigned long start, end, inc;
 
 	start = __pa(startp);
@@ -471,7 +507,10 @@ static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
 
         mb(); /* Ensure above stores are visible */
         while (start <= end) {
-                __raw_writeq(start, invalidate);
+		if (rm)
+			__raw_rm_writeq(cpu_to_be64(start), invalidate);
+		else
+			__raw_writeq(cpu_to_be64(start), invalidate);
                 start += inc;
         }
 
@@ -483,10 +522,12 @@ static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
 
 static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
 					 struct iommu_table *tbl,
-					 u64 *startp, u64 *endp)
+					 __be64 *startp, __be64 *endp, bool rm)
 {
 	unsigned long start, end, inc;
-	u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index;
+	__be64 __iomem *invalidate = rm ?
+		(__be64 __iomem *)pe->tce_inval_reg_phys :
+		(__be64 __iomem *)tbl->it_index;
 
 	/* We'll invalidate DMA address in PE scope */
 	start = 0x2ul << 60;
@@ -502,22 +543,25 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
 	mb();
 
 	while (start <= end) {
-		__raw_writeq(start, invalidate);
+		if (rm)
+			__raw_rm_writeq(cpu_to_be64(start), invalidate);
+		else
+			__raw_writeq(cpu_to_be64(start), invalidate);
 		start += inc;
 	}
 }
 
 void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
-				 u64 *startp, u64 *endp)
+				 __be64 *startp, __be64 *endp, bool rm)
 {
 	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
 					      tce32_table);
 	struct pnv_phb *phb = pe->phb;
 
 	if (phb->type == PNV_PHB_IODA1)
-		pnv_pci_ioda1_tce_invalidate(tbl, startp, endp);
+		pnv_pci_ioda1_tce_invalidate(pe, tbl, startp, endp, rm);
 	else
-		pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp);
+		pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp, rm);
 }
 
 static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
@@ -590,11 +634,19 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 		 * bus number, print that out instead.
 		 */
 		tbl->it_busno = 0;
-		tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8);
+		pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
+		tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
+				8);
 		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE |
 			       TCE_PCI_SWINV_PAIR;
 	}
 	iommu_init_table(tbl, phb->hose->node);
+	iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number);
+
+	if (pe->pdev)
+		set_iommu_table_base(&pe->pdev->dev, tbl);
+	else
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
 	return;
  fail:
@@ -662,11 +714,18 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 		 * bus number, print that out instead.
 		 */
 		tbl->it_busno = 0;
-		tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8);
+		pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
+		tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
+				8);
 		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
 	}
 	iommu_init_table(tbl, phb->hose->node);
 
+	if (pe->pdev)
+		set_iommu_table_base(&pe->pdev->dev, tbl);
+	else
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+
 	return;
 fail:
 	if (pe->tce32_seg >= 0)
@@ -762,8 +821,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 	struct irq_data *idata;
 	struct irq_chip *ichip;
 	unsigned int xive_num = hwirq - phb->msi_base;
-	uint64_t addr64;
-	uint32_t addr32, data;
+	__be32 data;
 	int rc;
 
 	/* No PE assigned ? bail out ... no MSI for you ! */
@@ -787,6 +845,8 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 	}
 
 	if (is_64) {
+		__be64 addr64;
+
 		rc = opal_get_msi_64(phb->opal_id, pe->mve_number, xive_num, 1,
 				     &addr64, &data);
 		if (rc) {
@@ -794,9 +854,11 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 				pci_name(dev), rc);
 			return -EIO;
 		}
-		msg->address_hi = addr64 >> 32;
-		msg->address_lo = addr64 & 0xfffffffful;
+		msg->address_hi = be64_to_cpu(addr64) >> 32;
+		msg->address_lo = be64_to_cpu(addr64) & 0xfffffffful;
 	} else {
+		__be32 addr32;
+
 		rc = opal_get_msi_32(phb->opal_id, pe->mve_number, xive_num, 1,
 				     &addr32, &data);
 		if (rc) {
@@ -805,9 +867,9 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 			return -EIO;
 		}
 		msg->address_hi = 0;
-		msg->address_lo = addr32;
+		msg->address_lo = be32_to_cpu(addr32);
 	}
-	msg->data = data;
+	msg->data = be32_to_cpu(data);
 
 	/*
 	 * Change the IRQ chip for the MSI interrupts on PHB3.
@@ -968,11 +1030,38 @@ static void pnv_pci_ioda_setup_DMA(void)
 	}
 }
 
+static void pnv_pci_ioda_create_dbgfs(void)
+{
+#ifdef CONFIG_DEBUG_FS
+	struct pci_controller *hose, *tmp;
+	struct pnv_phb *phb;
+	char name[16];
+
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		phb = hose->private_data;
+
+		sprintf(name, "PCI%04x", hose->global_number);
+		phb->dbgfs = debugfs_create_dir(name, powerpc_debugfs_root);
+		if (!phb->dbgfs)
+			pr_warning("%s: Error on creating debugfs on PHB#%x\n",
+				__func__, hose->global_number);
+	}
+#endif /* CONFIG_DEBUG_FS */
+}
+
 static void pnv_pci_ioda_fixup(void)
 {
 	pnv_pci_ioda_setup_PEs();
 	pnv_pci_ioda_setup_seg();
 	pnv_pci_ioda_setup_DMA();
+
+	pnv_pci_ioda_create_dbgfs();
+
+#ifdef CONFIG_EEH
+	eeh_probe_mode_set(EEH_PROBE_MODE_DEV);
+	eeh_addr_cache_build();
+	eeh_init();
+#endif
 }
 
 /*
@@ -1049,19 +1138,20 @@ static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
 		       OPAL_ASSERT_RESET);
 }
 
-void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
+void __init pnv_pci_init_ioda_phb(struct device_node *np,
+				  u64 hub_id, int ioda_type)
 {
 	struct pci_controller *hose;
-	static int primary = 1;
 	struct pnv_phb *phb;
 	unsigned long size, m32map_off, iomap_off, pemap_off;
-	const u64 *prop64;
-	const u32 *prop32;
+	const __be64 *prop64;
+	const __be32 *prop32;
+	int len;
 	u64 phb_id;
 	void *aux;
 	long rc;
 
-	pr_info(" Initializing IODA%d OPAL PHB %s\n", ioda_type, np->full_name);
+	pr_info("Initializing IODA%d OPAL PHB %s\n", ioda_type, np->full_name);
 
 	prop64 = of_get_property(np, "ibm,opal-phbid", NULL);
 	if (!prop64) {
@@ -1072,21 +1162,33 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 	pr_debug("  PHB-ID  : 0x%016llx\n", phb_id);
 
 	phb = alloc_bootmem(sizeof(struct pnv_phb));
-	if (phb) {
-		memset(phb, 0, sizeof(struct pnv_phb));
-		phb->hose = hose = pcibios_alloc_controller(np);
+	if (!phb) {
+		pr_err("  Out of memory !\n");
+		return;
 	}
-	if (!phb || !phb->hose) {
-		pr_err("PCI: Failed to allocate PCI controller for %s\n",
+
+	/* Allocate PCI controller */
+	memset(phb, 0, sizeof(struct pnv_phb));
+	phb->hose = hose = pcibios_alloc_controller(np);
+	if (!phb->hose) {
+		pr_err("  Can't allocate PCI controller for %s\n",
 		       np->full_name);
+		free_bootmem((unsigned long)phb, sizeof(struct pnv_phb));
 		return;
 	}
 
 	spin_lock_init(&phb->lock);
-	/* XXX Use device-tree */
-	hose->first_busno = 0;
-	hose->last_busno = 0xff;
+	prop32 = of_get_property(np, "bus-range", &len);
+	if (prop32 && len == 8) {
+		hose->first_busno = be32_to_cpu(prop32[0]);
+		hose->last_busno = be32_to_cpu(prop32[1]);
+	} else {
+		pr_warn("  Broken <bus-range> on %s\n", np->full_name);
+		hose->first_busno = 0;
+		hose->last_busno = 0xff;
+	}
 	hose->private_data = phb;
+	phb->hub_id = hub_id;
 	phb->opal_id = phb_id;
 	phb->type = ioda_type;
 
@@ -1099,8 +1201,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 		phb->model = PNV_PHB_MODEL_UNKNOWN;
 
 	/* Parse 32-bit and IO ranges (if any) */
-	pci_process_bridge_OF_ranges(phb->hose, np, primary);
-	primary = 0;
+	pci_process_bridge_OF_ranges(hose, np, !hose->global_number);
 
 	/* Get registers */
 	phb->regs = of_iomap(np, 0);
@@ -1108,12 +1209,13 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 		pr_err("  Failed to map registers !\n");
 
 	/* Initialize more IODA stuff */
+	phb->ioda.total_pe = 1;
 	prop32 = of_get_property(np, "ibm,opal-num-pes", NULL);
-	if (!prop32)
-		phb->ioda.total_pe = 1;
-	else
-		phb->ioda.total_pe = *prop32;
-
+	if (prop32)
+		phb->ioda.total_pe = be32_to_cpup(prop32);
+	prop32 = of_get_property(np, "ibm,opal-reserved-pe", NULL);
+	if (prop32)
+		phb->ioda.reserved_pe = be32_to_cpup(prop32);
 	phb->ioda.m32_size = resource_size(&hose->mem_resources[0]);
 	/* FW Has already off top 64k of M32 space (MSI space) */
 	phb->ioda.m32_size += 0x10000;
@@ -1124,24 +1226,25 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 	phb->ioda.io_segsize = phb->ioda.io_size / phb->ioda.total_pe;
 	phb->ioda.io_pci_base = 0; /* XXX calculate this ? */
 
-	/* Allocate aux data & arrays
-	 *
-	 * XXX TODO: Don't allocate io segmap on PHB3
-	 */
+	/* Allocate aux data & arrays. We don't have IO ports on PHB3 */
 	size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
 	m32map_off = size;
 	size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]);
 	iomap_off = size;
-	size += phb->ioda.total_pe * sizeof(phb->ioda.io_segmap[0]);
+	if (phb->type == PNV_PHB_IODA1) {
+		iomap_off = size;
+		size += phb->ioda.total_pe * sizeof(phb->ioda.io_segmap[0]);
+	}
 	pemap_off = size;
 	size += phb->ioda.total_pe * sizeof(struct pnv_ioda_pe);
 	aux = alloc_bootmem(size);
 	memset(aux, 0, size);
 	phb->ioda.pe_alloc = aux;
 	phb->ioda.m32_segmap = aux + m32map_off;
-	phb->ioda.io_segmap = aux + iomap_off;
+	if (phb->type == PNV_PHB_IODA1)
+		phb->ioda.io_segmap = aux + iomap_off;
 	phb->ioda.pe_array = aux + pemap_off;
-	set_bit(0, phb->ioda.pe_alloc);
+	set_bit(phb->ioda.reserved_pe, phb->ioda.pe_alloc);
 
 	INIT_LIST_HEAD(&phb->ioda.pe_dma_list);
 	INIT_LIST_HEAD(&phb->ioda.pe_list);
@@ -1166,12 +1269,17 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 					 segment_size);
 #endif
 
-	pr_info("  %d PE's M32: 0x%x [segment=0x%x] IO: 0x%x [segment=0x%x]\n",
+	pr_info("  %d (%d) PE's M32: 0x%x [segment=0x%x]"
+		" IO: 0x%x [segment=0x%x]\n",
 		phb->ioda.total_pe,
+		phb->ioda.reserved_pe,
 		phb->ioda.m32_size, phb->ioda.m32_segsize,
 		phb->ioda.io_size, phb->ioda.io_segsize);
 
 	phb->hose->ops = &pnv_pci_ops;
+#ifdef CONFIG_EEH
+	phb->eeh_ops = &ioda_eeh_ops;
+#endif
 
 	/* Setup RID -> PE mapping function */
 	phb->bdfn_to_pe = pnv_ioda_bdfn_to_pe;
@@ -1201,24 +1309,17 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 	rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET);
 	if (rc)
 		pr_warning("  OPAL Error %ld performing IODA table reset !\n", rc);
-
-	/*
-	 * On IODA1 map everything to PE#0, on IODA2 we assume the IODA reset
-	 * has cleared the RTT which has the same effect
-	 */
-	if (ioda_type == PNV_PHB_IODA1)
-		opal_pci_set_pe(phb_id, 0, 0, 7, 1, 1 , OPAL_MAP_PE);
 }
 
-void pnv_pci_init_ioda2_phb(struct device_node *np)
+void __init pnv_pci_init_ioda2_phb(struct device_node *np)
 {
-	pnv_pci_init_ioda_phb(np, PNV_PHB_IODA2);
+	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_IODA2);
 }
 
 void __init pnv_pci_init_ioda_hub(struct device_node *np)
 {
 	struct device_node *phbn;
-	const u64 *prop64;
+	const __be64 *prop64;
 	u64 hub_id;
 
 	pr_info("Probing IODA IO-Hub %s\n", np->full_name);
@@ -1235,6 +1336,6 @@ void __init pnv_pci_init_ioda_hub(struct device_node *np)
 	for_each_child_of_node(np, phbn) {
 		/* Look for IODA1 PHBs */
 		if (of_device_is_compatible(phbn, "ibm,ioda-phb"))
-			pnv_pci_init_ioda_phb(phbn, PNV_PHB_IODA1);
+			pnv_pci_init_ioda_phb(phbn, hub_id, PNV_PHB_IODA1);
 	}
 }
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
index 92b37a0..f8b4bd8 100644
--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -86,17 +86,20 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { }
 static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
 					 struct pci_dev *pdev)
 {
-	if (phb->p5ioc2.iommu_table.it_map == NULL)
+	if (phb->p5ioc2.iommu_table.it_map == NULL) {
 		iommu_init_table(&phb->p5ioc2.iommu_table, phb->hose->node);
+		iommu_register_group(&phb->p5ioc2.iommu_table,
+				pci_domain_nr(phb->hose->bus), phb->opal_id);
+	}
 
 	set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table);
 }
 
-static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np,
+static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
 					   void *tce_mem, u64 tce_size)
 {
 	struct pnv_phb *phb;
-	const u64 *prop64;
+	const __be64 *prop64;
 	u64 phb_id;
 	int64_t rc;
 	static int primary = 1;
@@ -133,6 +136,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np,
 	phb->hose->first_busno = 0;
 	phb->hose->last_busno = 0xff;
 	phb->hose->private_data = phb;
+	phb->hub_id = hub_id;
 	phb->opal_id = phb_id;
 	phb->type = PNV_PHB_P5IOC2;
 	phb->model = PNV_PHB_MODEL_P5IOC2;
@@ -174,7 +178,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np,
 void __init pnv_pci_init_p5ioc2_hub(struct device_node *np)
 {
 	struct device_node *phbn;
-	const u64 *prop64;
+	const __be64 *prop64;
 	u64 hub_id;
 	void *tce_mem;
 	uint64_t tce_per_phb;
@@ -226,7 +230,8 @@ void __init pnv_pci_init_p5ioc2_hub(struct device_node *np)
 	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);
+			pnv_pci_init_p5ioc2_phb(phbn, hub_id,
+					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
index 277343c..4eb33a9 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -20,6 +20,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>
+#include <linux/iommu.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -32,6 +33,8 @@
 #include <asm/iommu.h>
 #include <asm/tce.h>
 #include <asm/firmware.h>
+#include <asm/eeh_event.h>
+#include <asm/eeh.h>
 
 #include "powernv.h"
 #include "pci.h"
@@ -202,7 +205,8 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no)
 
 	spin_lock_irqsave(&phb->lock, flags);
 
-	rc = opal_pci_get_phb_diag_data(phb->opal_id, phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+					 PNV_PCI_DIAG_BUF_SIZE);
 	has_diag = (rc == OPAL_SUCCESS);
 
 	rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no,
@@ -227,43 +231,54 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no)
 	spin_unlock_irqrestore(&phb->lock, flags);
 }
 
-static void pnv_pci_config_check_eeh(struct pnv_phb *phb, struct pci_bus *bus,
-				     u32 bdfn)
+static void pnv_pci_config_check_eeh(struct pnv_phb *phb,
+				     struct device_node *dn)
 {
 	s64	rc;
 	u8	fstate;
-	u16	pcierr;
+	__be16	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;
+	/*
+	 * Get the PE#. During the PCI probe stage, we might not
+	 * setup that yet. So all ER errors should be mapped to
+	 * reserved PE.
+	 */
+	pe_no = PCI_DN(dn)->pe_number;
+	if (pe_no == IODA_INVALID_PE) {
+		if (phb->type == PNV_PHB_P5IOC2)
+			pe_no = 0;
+		else
+			pe_no = phb->ioda.reserved_pe;
+	}
 
 	/* 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);
+		pr_warning("%s: Can't read EEH status (PE#%d) for "
+			   "%s, err %lld\n",
+			   __func__, pe_no, dn->full_name, rc);
 		return;
 	}
-	cfg_dbg(" -> EEH check, bdfn=%04x PE%d fstate=%x\n",
-		bdfn, pe_no, fstate);
+	cfg_dbg(" -> EEH check, bdfn=%04x PE#%d fstate=%x\n",
+		(PCI_DN(dn)->busno << 8) | (PCI_DN(dn)->devfn),
+		pe_no, fstate);
 	if (fstate != 0)
 		pnv_pci_handle_eeh_config(phb, pe_no);
 }
 
-static int pnv_pci_read_config(struct pci_bus *bus,
-			       unsigned int devfn,
-			       int where, int size, u32 *val)
+int pnv_pci_cfg_read(struct device_node *dn,
+		     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;
+	struct pci_dn *pdn = PCI_DN(dn);
+	struct pnv_phb *phb = pdn->phb->private_data;
+	u32 bdfn = (pdn->busno << 8) | pdn->devfn;
+#ifdef CONFIG_EEH
+	struct eeh_pe *phb_pe = NULL;
+#endif
 	s64 rc;
 
-	if (hose == NULL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
 	switch (size) {
 	case 1: {
 		u8 v8;
@@ -272,43 +287,58 @@ static int pnv_pci_read_config(struct pci_bus *bus,
 		break;
 	}
 	case 2: {
-		u16 v16;
+		__be16 v16;
 		rc = opal_pci_config_read_half_word(phb->opal_id, bdfn, where,
 						   &v16);
-		*val = (rc == OPAL_SUCCESS) ? v16 : 0xffff;
+		*val = (rc == OPAL_SUCCESS) ? be16_to_cpu(v16) : 0xffff;
 		break;
 	}
 	case 4: {
-		u32 v32;
+		__be32 v32;
 		rc = opal_pci_config_read_word(phb->opal_id, bdfn, where, &v32);
-		*val = (rc == OPAL_SUCCESS) ? v32 : 0xffffffff;
+		*val = (rc == OPAL_SUCCESS) ? be32_to_cpu(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);
+	cfg_dbg("%s: bus: %x devfn: %x +%x/%x -> %08x\n",
+		__func__, pdn->busno, pdn->devfn, where, size, *val);
+
+	/*
+	 * Check if the specified PE has been put into frozen
+	 * state. On the other hand, we needn't do that while
+	 * the PHB has been put into frozen state because of
+	 * PHB-fatal errors.
+	 */
+#ifdef CONFIG_EEH
+	phb_pe = eeh_phb_pe_get(pdn->phb);
+	if (phb_pe && (phb_pe->state & EEH_PE_ISOLATED))
+		return PCIBIOS_SUCCESSFUL;
+
+	if (phb->eeh_state & PNV_EEH_STATE_ENABLED) {
+		if (*val == EEH_IO_ERROR_VALUE(size) &&
+		    eeh_dev_check_failure(of_node_to_eeh_dev(dn)))
+			return PCIBIOS_DEVICE_NOT_FOUND;
+	} else {
+		pnv_pci_config_check_eeh(phb, dn);
+	}
+#else
+	pnv_pci_config_check_eeh(phb, dn);
+#endif
 
 	return PCIBIOS_SUCCESSFUL;
 }
 
-static int pnv_pci_write_config(struct pci_bus *bus,
-				unsigned int devfn,
-				int where, int size, u32 val)
+int pnv_pci_cfg_write(struct device_node *dn,
+		      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;
+	struct pci_dn *pdn = PCI_DN(dn);
+	struct pnv_phb *phb = pdn->phb->private_data;
+	u32 bdfn = (pdn->busno << 8) | pdn->devfn;
 
-	cfg_dbg("pnv_pci_write_config bus: %x devfn: %x +%x/%x -> %08x\n",
-		bus->number, devfn, where, size, val);
+	cfg_dbg("%s: bus: %x devfn: %x +%x/%x -> %08x\n",
+		pdn->busno, pdn->devfn, where, size, val);
 	switch (size) {
 	case 1:
 		opal_pci_config_write_byte(phb->opal_id, bdfn, where, val);
@@ -322,23 +352,63 @@ static int pnv_pci_write_config(struct pci_bus *bus,
 	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);
+#ifdef CONFIG_EEH
+	if (!(phb->eeh_state & PNV_EEH_STATE_ENABLED))
+		pnv_pci_config_check_eeh(phb, dn);
+#else
+	pnv_pci_config_check_eeh(phb, dn);
+#endif
 
 	return PCIBIOS_SUCCESSFUL;
 }
 
+static int pnv_pci_read_config(struct pci_bus *bus,
+			       unsigned int devfn,
+			       int where, int size, u32 *val)
+{
+	struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
+	struct pci_dn *pdn;
+
+	for (dn = busdn->child; dn; dn = dn->sibling) {
+		pdn = PCI_DN(dn);
+		if (pdn && pdn->devfn == devfn)
+			return pnv_pci_cfg_read(dn, where, size, val);
+	}
+
+	*val = 0xFFFFFFFF;
+	return PCIBIOS_DEVICE_NOT_FOUND;
+
+}
+
+static int pnv_pci_write_config(struct pci_bus *bus,
+				unsigned int devfn,
+				int where, int size, u32 val)
+{
+	struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
+	struct pci_dn *pdn;
+
+	for (dn = busdn->child; dn; dn = dn->sibling) {
+		pdn = PCI_DN(dn);
+		if (pdn && pdn->devfn == devfn)
+			return pnv_pci_cfg_write(dn, where, size, val);
+	}
+
+	return PCIBIOS_DEVICE_NOT_FOUND;
+}
+
 struct pci_ops pnv_pci_ops = {
-	.read = pnv_pci_read_config,
+	.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)
+			 struct dma_attrs *attrs, bool rm)
 {
 	u64 proto_tce;
-	u64 *tcep, *tces;
+	__be64 *tcep, *tces;
 	u64 rpn;
 
 	proto_tce = TCE_PCI_READ; // Read allowed
@@ -346,33 +416,48 @@ static int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
 	if (direction != DMA_TO_DEVICE)
 		proto_tce |= TCE_PCI_WRITE;
 
-	tces = tcep = ((u64 *)tbl->it_base) + index - tbl->it_offset;
+	tces = tcep = ((__be64 *)tbl->it_base) + index - tbl->it_offset;
 	rpn = __pa(uaddr) >> TCE_SHIFT;
 
 	while (npages--)
-		*(tcep++) = proto_tce | (rpn++ << TCE_RPN_SHIFT);
+		*(tcep++) = cpu_to_be64(proto_tce | (rpn++ << TCE_RPN_SHIFT));
 
 	/* Some implementations won't cache invalid TCEs and thus may not
 	 * need that flush. We'll probably turn it_type into a bit mask
 	 * of flags if that becomes the case
 	 */
 	if (tbl->it_type & TCE_PCI_SWINV_CREATE)
-		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1);
+		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm);
 
 	return 0;
 }
 
-static void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
+static int pnv_tce_build_vm(struct iommu_table *tbl, long index, long npages,
+			    unsigned long uaddr,
+			    enum dma_data_direction direction,
+			    struct dma_attrs *attrs)
 {
-	u64 *tcep, *tces;
+	return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs,
+			false);
+}
 
-	tces = tcep = ((u64 *)tbl->it_base) + index - tbl->it_offset;
+static void pnv_tce_free(struct iommu_table *tbl, long index, long npages,
+		bool rm)
+{
+	__be64 *tcep, *tces;
+
+	tces = tcep = ((__be64 *)tbl->it_base) + index - tbl->it_offset;
 
 	while (npages--)
-		*(tcep++) = 0;
+		*(tcep++) = cpu_to_be64(0);
 
 	if (tbl->it_type & TCE_PCI_SWINV_FREE)
-		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1);
+		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm);
+}
+
+static void pnv_tce_free_vm(struct iommu_table *tbl, long index, long npages)
+{
+	pnv_tce_free(tbl, index, npages, false);
 }
 
 static unsigned long pnv_tce_get(struct iommu_table *tbl, long index)
@@ -380,6 +465,19 @@ static unsigned long pnv_tce_get(struct iommu_table *tbl, long index)
 	return ((u64 *)tbl->it_base)[index - tbl->it_offset];
 }
 
+static int pnv_tce_build_rm(struct iommu_table *tbl, long index, long npages,
+			    unsigned long uaddr,
+			    enum dma_data_direction direction,
+			    struct dma_attrs *attrs)
+{
+	return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs, true);
+}
+
+static void pnv_tce_free_rm(struct iommu_table *tbl, long index, long npages)
+{
+	pnv_tce_free(tbl, index, npages, true);
+}
+
 void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 			       void *tce_mem, u64 tce_size,
 			       u64 dma_offset)
@@ -412,13 +510,14 @@ static struct iommu_table *pnv_pci_setup_bml_iommu(struct pci_controller *hose)
 	pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)),
 				  be32_to_cpup(sizep), 0);
 	iommu_init_table(tbl, hose->node);
+	iommu_register_group(tbl, pci_domain_nr(hose->bus), 0);
 
 	/* Deal with SW invalidated TCEs when needed (BML way) */
 	swinvp = of_get_property(hose->dn, "linux,tce-sw-invalidate-info",
 				 NULL);
 	if (swinvp) {
-		tbl->it_busno = swinvp[1];
-		tbl->it_index = (unsigned long)ioremap(swinvp[0], 8);
+		tbl->it_busno = be64_to_cpu(swinvp[1]);
+		tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8);
 		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
 	}
 	return tbl;
@@ -543,8 +642,10 @@ void __init pnv_pci_init(void)
 
 	/* 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.tce_build = pnv_tce_build_vm;
+	ppc_md.tce_free = pnv_tce_free_vm;
+	ppc_md.tce_build_rm = pnv_tce_build_rm;
+	ppc_md.tce_free_rm = pnv_tce_free_rm;
 	ppc_md.tce_get = pnv_tce_get;
 	ppc_md.pci_probe_mode = pnv_pci_probe_mode;
 	set_pci_dma_ops(&dma_iommu_ops);
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 25d76c4..911c24e 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -17,7 +17,7 @@ enum pnv_phb_model {
 	PNV_PHB_MODEL_PHB3,
 };
 
-#define PNV_PCI_DIAG_BUF_SIZE	4096
+#define PNV_PCI_DIAG_BUF_SIZE	8192
 #define PNV_IODA_PE_DEV		(1 << 0)	/* PE has single PCI device	*/
 #define PNV_IODA_PE_BUS		(1 << 1)	/* PE has primary PCI bus	*/
 #define PNV_IODA_PE_BUS_ALL	(1 << 2)	/* PE has subordinate buses	*/
@@ -52,6 +52,7 @@ struct pnv_ioda_pe {
 	int			tce32_seg;
 	int			tce32_segcount;
 	struct iommu_table	tce32_table;
+	phys_addr_t		tce_inval_reg_phys;
 
 	/* XXX TODO: Add support for additional 64-bit iommus */
 
@@ -66,15 +67,43 @@ struct pnv_ioda_pe {
 	struct list_head	list;
 };
 
+/* IOC dependent EEH operations */
+#ifdef CONFIG_EEH
+struct pnv_eeh_ops {
+	int (*post_init)(struct pci_controller *hose);
+	int (*set_option)(struct eeh_pe *pe, int option);
+	int (*get_state)(struct eeh_pe *pe);
+	int (*reset)(struct eeh_pe *pe, int option);
+	int (*get_log)(struct eeh_pe *pe, int severity,
+		       char *drv_log, unsigned long len);
+	int (*configure_bridge)(struct eeh_pe *pe);
+	int (*next_error)(struct eeh_pe **pe);
+};
+
+#define PNV_EEH_STATE_ENABLED	(1 << 0)	/* EEH enabled	*/
+#define PNV_EEH_STATE_REMOVED	(1 << 1)	/* PHB removed	*/
+
+#endif /* CONFIG_EEH */
+
 struct pnv_phb {
 	struct pci_controller	*hose;
 	enum pnv_phb_type	type;
 	enum pnv_phb_model	model;
+	u64			hub_id;
 	u64			opal_id;
 	void __iomem		*regs;
 	int			initialized;
 	spinlock_t		lock;
 
+#ifdef CONFIG_EEH
+	struct pnv_eeh_ops	*eeh_ops;
+	int			eeh_state;
+#endif
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry		*dbgfs;
+#endif
+
 #ifdef CONFIG_PCI_MSI
 	unsigned int		msi_base;
 	unsigned int		msi32_support;
@@ -96,6 +125,7 @@ struct pnv_phb {
 		struct {
 			/* Global bridge info */
 			unsigned int		total_pe;
+			unsigned int		reserved_pe;
 			unsigned int		m32_size;
 			unsigned int		m32_segsize;
 			unsigned int		m32_pci_base;
@@ -150,7 +180,14 @@ struct pnv_phb {
 };
 
 extern struct pci_ops pnv_pci_ops;
+#ifdef CONFIG_EEH
+extern struct pnv_eeh_ops ioda_eeh_ops;
+#endif
 
+int pnv_pci_cfg_read(struct device_node *dn,
+		     int where, int size, u32 *val);
+int pnv_pci_cfg_write(struct device_node *dn,
+		      int where, int size, u32 val);
 extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 				      void *tce_mem, u64 tce_size,
 				      u64 dma_offset);
@@ -158,6 +195,6 @@ extern void pnv_pci_init_p5ioc2_hub(struct device_node *np);
 extern void pnv_pci_init_ioda_hub(struct device_node *np);
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
-					u64 *startp, u64 *endp);
+					__be64 *startp, __be64 *endp, bool rm);
 
 #endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index a1c6f83..de6819b 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -15,4 +15,6 @@ static inline void pnv_pci_init(void) { }
 static inline void pnv_pci_shutdown(void) { }
 #endif
 
+extern void pnv_lpc_init(void);
+
 #endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c
new file mode 100644
index 0000000..1cb160d
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/rng.c
@@ -0,0 +1,126 @@
+/*
+ * Copyright 2013, Michael Ellerman, 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 pr_fmt(fmt)	"powernv-rng: " fmt
+
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <asm/archrandom.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/machdep.h>
+#include <asm/smp.h>
+
+
+struct powernv_rng {
+	void __iomem *regs;
+	unsigned long mask;
+};
+
+static DEFINE_PER_CPU(struct powernv_rng *, powernv_rng);
+
+
+static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val)
+{
+	unsigned long parity;
+
+	/* Calculate the parity of the value */
+	asm ("popcntd %0,%1" : "=r" (parity) : "r" (val));
+
+	/* xor our value with the previous mask */
+	val ^= rng->mask;
+
+	/* update the mask based on the parity of this value */
+	rng->mask = (rng->mask << 1) | (parity & 1);
+
+	return val;
+}
+
+int powernv_get_random_long(unsigned long *v)
+{
+	struct powernv_rng *rng;
+
+	rng = get_cpu_var(powernv_rng);
+
+	*v = rng_whiten(rng, in_be64(rng->regs));
+
+	put_cpu_var(rng);
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(powernv_get_random_long);
+
+static __init void rng_init_per_cpu(struct powernv_rng *rng,
+				    struct device_node *dn)
+{
+	int chip_id, cpu;
+
+	chip_id = of_get_ibm_chip_id(dn);
+	if (chip_id == -1)
+		pr_warn("No ibm,chip-id found for %s.\n", dn->full_name);
+
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(powernv_rng, cpu) == NULL ||
+		    cpu_to_chip_id(cpu) == chip_id) {
+			per_cpu(powernv_rng, cpu) = rng;
+		}
+	}
+}
+
+static __init int rng_create(struct device_node *dn)
+{
+	struct powernv_rng *rng;
+	unsigned long val;
+
+	rng = kzalloc(sizeof(*rng), GFP_KERNEL);
+	if (!rng)
+		return -ENOMEM;
+
+	rng->regs = of_iomap(dn, 0);
+	if (!rng->regs) {
+		kfree(rng);
+		return -ENXIO;
+	}
+
+	val = in_be64(rng->regs);
+	rng->mask = val;
+
+	rng_init_per_cpu(rng, dn);
+
+	pr_info_once("Registering arch random hook.\n");
+
+	ppc_md.get_random_long = powernv_get_random_long;
+
+	return 0;
+}
+
+static __init int rng_init(void)
+{
+	struct device_node *dn;
+	int rc;
+
+	for_each_compatible_node(dn, NULL, "ibm,power-rng") {
+		rc = rng_create(dn);
+		if (rc) {
+			pr_err("Failed creating rng for %s (%d).\n",
+				dn->full_name, rc);
+			continue;
+		}
+
+		/* Create devices for hwrng driver */
+		of_platform_device_create(dn, NULL, NULL);
+	}
+
+	return 0;
+}
+subsys_initcall(rng_init);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index d4459bf..19884b2 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -23,6 +23,7 @@
 #include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/of.h>
+#include <linux/of_fdt.h>
 #include <linux/interrupt.h>
 #include <linux/bug.h>
 
@@ -31,6 +32,7 @@
 #include <asm/xics.h>
 #include <asm/rtas.h>
 #include <asm/opal.h>
+#include <asm/kexec.h>
 
 #include "powernv.h"
 
@@ -54,6 +56,12 @@ static void __init pnv_setup_arch(void)
 
 static void __init pnv_init_early(void)
 {
+	/*
+	 * Initialize the LPC bus now so that legacy serial
+	 * ports can be found on it
+	 */
+	opal_lpc_init();
+
 #ifdef CONFIG_HVC_OPAL
 	if (firmware_has_feature(FW_FEATURE_OPAL))
 		hvc_opal_init_early();
@@ -93,6 +101,8 @@ static void  __noreturn pnv_restart(char *cmd)
 {
 	long rc = OPAL_BUSY;
 
+	opal_notifier_disable();
+
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_cec_reboot();
 		if (rc == OPAL_BUSY_EVENT)
@@ -108,6 +118,8 @@ static void __noreturn pnv_power_off(void)
 {
 	long rc = OPAL_BUSY;
 
+	opal_notifier_disable();
+
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_cec_power_down(0);
 		if (rc == OPAL_BUSY_EVENT)
@@ -143,6 +155,16 @@ static void pnv_shutdown(void)
 static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 {
 	xics_kexec_teardown_cpu(secondary);
+
+	/* Return secondary CPUs to firmware on OPAL v3 */
+	if (firmware_has_feature(FW_FEATURE_OPALv3) && secondary) {
+		mb();
+		get_paca()->kexec_state = KEXEC_STATE_REAL_MODE;
+		mb();
+
+		/* Return the CPU to OPAL */
+		opal_return_cpu();
+	}
 }
 #endif /* CONFIG_KEXEC */
 
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 8cbaa59..908672b 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -40,7 +40,7 @@
 #define DBG(fmt...)
 #endif
 
-static void __cpuinit pnv_smp_setup_cpu(int cpu)
+static void pnv_smp_setup_cpu(int cpu)
 {
 	if (cpu != boot_cpuid)
 		xics_setup_cpu();
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index 177a2f7..3e270e3 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -109,7 +109,8 @@ static long ps3_hpte_remove(unsigned long hpte_group)
 }
 
 static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
-	unsigned long vpn, int psize, int ssize, int local)
+			      unsigned long vpn, int psize, int apsize,
+			      int ssize, int local)
 {
 	int result;
 	u64 hpte_v, want_v, hpte_rs;
@@ -162,7 +163,7 @@ static void ps3_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 }
 
 static void ps3_hpte_invalidate(unsigned long slot, unsigned long vpn,
-	int psize, int ssize, int local)
+				int psize, int apsize, int ssize, int local)
 {
 	unsigned long flags;
 	int result;
diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c
index cba1e6b..ce73ce8 100644
--- a/arch/powerpc/platforms/ps3/time.c
+++ b/arch/powerpc/platforms/ps3/time.c
@@ -90,7 +90,7 @@ static int __init ps3_rtc_init(void)
 
 	pdev = platform_device_register_simple("rtc-ps3", -1, NULL, 0);
 
-	return PTR_RET(pdev);
+	return PTR_ERR_OR_ZERO(pdev);
 }
 
 module_init(ps3_rtc_init);
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 4459eff..62b4f80 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -19,7 +19,6 @@ config PPC_PSERIES
 	select ZLIB_DEFLATE
 	select PPC_DOORBELL
 	select HAVE_CONTEXT_TRACKING
-	select HOTPLUG if SMP
 	select HOTPLUG_CPU if SMP
 	default y
 
@@ -33,11 +32,6 @@ config PPC_SPLPAR
 	  processors, that is, which share physical processors between
 	  two or more partitions.
 
-config EEH
-	bool
-	depends on PPC_PSERIES && PCI
-	default y
-
 config PSERIES_MSI
        bool
        depends on PCI_MSI && EEH
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 53866e5..fbccac9 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -3,12 +3,10 @@ ccflags-$(CONFIG_PPC_PSERIES_DEBUG)	+= -DDEBUG
 
 obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
 			   setup.o iommu.o event_sources.o ras.o \
-			   firmware.o power.o dlpar.o mobility.o
+			   firmware.o power.o dlpar.o mobility.o rng.o
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_SCANLOG)	+= scanlog.o
-obj-$(CONFIG_EEH)	+= eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
-			   eeh_driver.o eeh_event.o eeh_sysfs.o \
-			   eeh_pseries.o
+obj-$(CONFIG_EEH)	+= eeh_pseries.o
 obj-$(CONFIG_KEXEC)	+= kexec.o
 obj-$(CONFIG_PCI)	+= pci.o pci_dlpar.o
 obj-$(CONFIG_PSERIES_MSI)	+= msi.o
@@ -24,6 +22,7 @@ obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_DTL)		+= dtl.o
 obj-$(CONFIG_IO_EVENT_IRQ)	+= io_event_irq.o
 obj-$(CONFIG_PSERIES_IDLE)	+= processor_idle.o
+obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 
 ifeq ($(CONFIG_PPC_PSERIES),y)
 obj-$(CONFIG_SUSPEND)		+= suspend.o
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index c638535..1e561be 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -40,8 +40,7 @@
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>
 #include <linux/memory.h>
-
-#include "plpar_wrappers.h"
+#include <asm/plpar_wrappers.h>
 
 #define CMM_DRIVER_VERSION	"1.0.0"
 #define CMM_DEFAULT_DELAY	1
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index a1a7b9a..a8fe5aa 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -63,26 +63,32 @@ static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa)
 	return prop;
 }
 
-static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa)
+static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa,
+					       const char *path)
 {
 	struct device_node *dn;
 	char *name;
 
+	/* If parent node path is "/" advance path to NULL terminator to
+	 * prevent double leading slashs in full_name.
+	 */
+	if (!path[1])
+		path++;
+
 	dn = kzalloc(sizeof(*dn), GFP_KERNEL);
 	if (!dn)
 		return NULL;
 
-	/* The configure connector reported name does not contain a
-	 * preceding '/', so we allocate a buffer large enough to
-	 * prepend this to the full_name.
-	 */
 	name = (char *)ccwa + ccwa->name_offset;
-	dn->full_name = kasprintf(GFP_KERNEL, "/%s", name);
+	dn->full_name = kasprintf(GFP_KERNEL, "%s/%s", path, name);
 	if (!dn->full_name) {
 		kfree(dn);
 		return NULL;
 	}
 
+	of_node_set_flag(dn, OF_DYNAMIC);
+	kref_init(&dn->kref);
+
 	return dn;
 }
 
@@ -120,7 +126,8 @@ void dlpar_free_cc_nodes(struct device_node *dn)
 #define CALL_AGAIN	-2
 #define ERR_CFG_USE     -9003
 
-struct device_node *dlpar_configure_connector(u32 drc_index)
+struct device_node *dlpar_configure_connector(u32 drc_index,
+					      struct device_node *parent)
 {
 	struct device_node *dn;
 	struct device_node *first_dn = NULL;
@@ -129,6 +136,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 	struct property *last_property = NULL;
 	struct cc_workarea *ccwa;
 	char *data_buf;
+	const char *parent_path = parent->full_name;
 	int cc_token;
 	int rc = -1;
 
@@ -162,7 +170,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 			break;
 
 		case NEXT_SIBLING:
-			dn = dlpar_parse_cc_node(ccwa);
+			dn = dlpar_parse_cc_node(ccwa, parent_path);
 			if (!dn)
 				goto cc_error;
 
@@ -172,13 +180,17 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 			break;
 
 		case NEXT_CHILD:
-			dn = dlpar_parse_cc_node(ccwa);
+			if (first_dn)
+				parent_path = last_dn->full_name;
+
+			dn = dlpar_parse_cc_node(ccwa, parent_path);
 			if (!dn)
 				goto cc_error;
 
-			if (!first_dn)
+			if (!first_dn) {
+				dn->parent = parent;
 				first_dn = dn;
-			else {
+			} else {
 				dn->parent = last_dn;
 				if (last_dn)
 					last_dn->child = dn;
@@ -202,6 +214,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 
 		case PREV_PARENT:
 			last_dn = last_dn->parent;
+			parent_path = last_dn->parent->full_name;
 			break;
 
 		case CALL_AGAIN:
@@ -256,8 +269,6 @@ int dlpar_attach_node(struct device_node *dn)
 {
 	int rc;
 
-	of_node_set_flag(dn, OF_DYNAMIC);
-	kref_init(&dn->kref);
 	dn->parent = derive_parent(dn->full_name);
 	if (!dn->parent)
 		return -ENOMEM;
@@ -275,8 +286,15 @@ int dlpar_attach_node(struct device_node *dn)
 
 int dlpar_detach_node(struct device_node *dn)
 {
+	struct device_node *child;
 	int rc;
 
+	child = of_get_next_child(dn, NULL);
+	while (child) {
+		dlpar_detach_node(child);
+		child = of_get_next_child(dn, child);
+	}
+
 	rc = of_detach_node(dn);
 	if (rc)
 		return rc;
@@ -382,57 +400,42 @@ out:
 
 static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 {
-	struct device_node *dn;
+	struct device_node *dn, *parent;
 	unsigned long drc_index;
-	char *cpu_name;
 	int rc;
 
-	cpu_hotplug_driver_lock();
 	rc = strict_strtoul(buf, 0, &drc_index);
-	if (rc) {
-		rc = -EINVAL;
-		goto out;
-	}
+	if (rc)
+		return -EINVAL;
 
-	dn = dlpar_configure_connector(drc_index);
-	if (!dn) {
-		rc = -EINVAL;
-		goto out;
-	}
+	parent = of_find_node_by_path("/cpus");
+	if (!parent)
+		return -ENODEV;
 
-	/* configure-connector reports cpus as living in the base
-	 * directory of the device tree.  CPUs actually live in the
-	 * cpus directory so we need to fixup the full_name.
-	 */
-	cpu_name = kasprintf(GFP_KERNEL, "/cpus%s", dn->full_name);
-	if (!cpu_name) {
-		dlpar_free_cc_nodes(dn);
-		rc = -ENOMEM;
-		goto out;
-	}
+	dn = dlpar_configure_connector(drc_index, parent);
+	if (!dn)
+		return -EINVAL;
 
-	kfree(dn->full_name);
-	dn->full_name = cpu_name;
+	of_node_put(parent);
 
 	rc = dlpar_acquire_drc(drc_index);
 	if (rc) {
 		dlpar_free_cc_nodes(dn);
-		rc = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	rc = dlpar_attach_node(dn);
 	if (rc) {
 		dlpar_release_drc(drc_index);
 		dlpar_free_cc_nodes(dn);
-		goto out;
+		return rc;
 	}
 
 	rc = dlpar_online_cpu(dn);
-out:
-	cpu_hotplug_driver_unlock();
+	if (rc)
+		return rc;
 
-	return rc ? rc : count;
+	return count;
 }
 
 static int dlpar_offline_cpu(struct device_node *dn)
@@ -505,30 +508,27 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count)
 		return -EINVAL;
 	}
 
-	cpu_hotplug_driver_lock();
 	rc = dlpar_offline_cpu(dn);
 	if (rc) {
 		of_node_put(dn);
-		rc = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	rc = dlpar_release_drc(*drc_index);
 	if (rc) {
 		of_node_put(dn);
-		goto out;
+		return rc;
 	}
 
 	rc = dlpar_detach_node(dn);
 	if (rc) {
 		dlpar_acquire_drc(*drc_index);
-		goto out;
+		return rc;
 	}
 
 	of_node_put(dn);
-out:
-	cpu_hotplug_driver_unlock();
-	return rc ? rc : count;
+
+	return count;
 }
 
 static int __init pseries_dlpar_init(void)
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 0cc0ac0..5db66f1 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -29,8 +29,7 @@
 #include <asm/firmware.h>
 #include <asm/lppaca.h>
 #include <asm/debug.h>
-
-#include "plpar_wrappers.h"
+#include <asm/plpar_wrappers.h>
 
 struct dtl {
 	struct dtl_entry	*buf;
@@ -87,7 +86,7 @@ static void consume_dtle(struct dtl_entry *dtle, u64 index)
 	barrier();
 
 	/* check for hypervisor ring buffer overflow, ignore this entry if so */
-	if (index + N_DISPATCH_LOG < vpa->dtl_idx)
+	if (index + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx))
 		return;
 
 	++wp;
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
deleted file mode 100644
index 6b73d6c..0000000
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ /dev/null
@@ -1,942 +0,0 @@
-/*
- * Copyright IBM Corporation 2001, 2005, 2006
- * Copyright Dave Engebretsen & Todd Inglett 2001
- * Copyright Linas Vepstas 2005, 2006
- * Copyright 2001-2012 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
- * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com>
- */
-
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/pci.h>
-#include <linux/proc_fs.h>
-#include <linux/rbtree.h>
-#include <linux/seq_file.h>
-#include <linux/spinlock.h>
-#include <linux/export.h>
-#include <linux/of.h>
-
-#include <linux/atomic.h>
-#include <asm/eeh.h>
-#include <asm/eeh_event.h>
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/ppc-pci.h>
-#include <asm/rtas.h>
-
-
-/** Overview:
- *  EEH, or "Extended Error Handling" is a PCI bridge technology for
- *  dealing with PCI bus errors that can't be dealt with within the
- *  usual PCI framework, except by check-stopping the CPU.  Systems
- *  that are designed for high-availability/reliability cannot afford
- *  to crash due to a "mere" PCI error, thus the need for EEH.
- *  An EEH-capable bridge operates by converting a detected error
- *  into a "slot freeze", taking the PCI adapter off-line, making
- *  the slot behave, from the OS'es point of view, as if the slot
- *  were "empty": all reads return 0xff's and all writes are silently
- *  ignored.  EEH slot isolation events can be triggered by parity
- *  errors on the address or data busses (e.g. during posted writes),
- *  which in turn might be caused by low voltage on the bus, dust,
- *  vibration, humidity, radioactivity or plain-old failed hardware.
- *
- *  Note, however, that one of the leading causes of EEH slot
- *  freeze events are buggy device drivers, buggy device microcode,
- *  or buggy device hardware.  This is because any attempt by the
- *  device to bus-master data to a memory address that is not
- *  assigned to the device will trigger a slot freeze.   (The idea
- *  is to prevent devices-gone-wild from corrupting system memory).
- *  Buggy hardware/drivers will have a miserable time co-existing
- *  with EEH.
- *
- *  Ideally, a PCI device driver, when suspecting that an isolation
- *  event has occurred (e.g. by reading 0xff's), will then ask EEH
- *  whether this is the case, and then take appropriate steps to
- *  reset the PCI slot, the PCI device, and then resume operations.
- *  However, until that day,  the checking is done here, with the
- *  eeh_check_failure() routine embedded in the MMIO macros.  If
- *  the slot is found to be isolated, an "EEH Event" is synthesized
- *  and sent out for processing.
- */
-
-/* If a device driver keeps reading an MMIO register in an interrupt
- * handler after a slot isolation event, it might be broken.
- * This sets the threshold for how many read attempts we allow
- * before printing an error message.
- */
-#define EEH_MAX_FAILS	2100000
-
-/* Time to wait for a PCI slot to report status, in milliseconds */
-#define PCI_BUS_RESET_WAIT_MSEC (60*1000)
-
-/* Platform dependent EEH operations */
-struct eeh_ops *eeh_ops = NULL;
-
-int eeh_subsystem_enabled;
-EXPORT_SYMBOL(eeh_subsystem_enabled);
-
-/*
- * EEH probe mode support. The intention is to support multiple
- * platforms for EEH. Some platforms like pSeries do PCI emunation
- * based on device tree. However, other platforms like powernv probe
- * PCI devices from hardware. The flag is used to distinguish that.
- * In addition, struct eeh_ops::probe would be invoked for particular
- * OF node or PCI device so that the corresponding PE would be created
- * there.
- */
-int eeh_probe_mode;
-
-/* Global EEH mutex */
-DEFINE_MUTEX(eeh_mutex);
-
-/* Lock to avoid races due to multiple reports of an error */
-static DEFINE_RAW_SPINLOCK(confirm_error_lock);
-
-/* Buffer for reporting pci register dumps. Its here in BSS, and
- * not dynamically alloced, so that it ends up in RMO where RTAS
- * can access it.
- */
-#define EEH_PCI_REGS_LOG_LEN 4096
-static unsigned char pci_regs_buf[EEH_PCI_REGS_LOG_LEN];
-
-/*
- * The struct is used to maintain the EEH global statistic
- * information. Besides, the EEH global statistics will be
- * exported to user space through procfs
- */
-struct eeh_stats {
-	u64 no_device;		/* PCI device not found		*/
-	u64 no_dn;		/* OF node not found		*/
-	u64 no_cfg_addr;	/* Config address not found	*/
-	u64 ignored_check;	/* EEH check skipped		*/
-	u64 total_mmio_ffs;	/* Total EEH checks		*/
-	u64 false_positives;	/* Unnecessary EEH checks	*/
-	u64 slot_resets;	/* PE reset			*/
-};
-
-static struct eeh_stats eeh_stats;
-
-#define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE)
-
-/**
- * eeh_gather_pci_data - Copy assorted PCI config space registers to buff
- * @edev: device to report data for
- * @buf: point to buffer in which to log
- * @len: amount of room in buffer
- *
- * This routine captures assorted PCI configuration space data,
- * and puts them into a buffer for RTAS error logging.
- */
-static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len)
-{
-	struct device_node *dn = eeh_dev_to_of_node(edev);
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	u32 cfg;
-	int cap, i;
-	int n = 0;
-
-	n += scnprintf(buf+n, len-n, "%s\n", dn->full_name);
-	printk(KERN_WARNING "EEH: of node=%s\n", dn->full_name);
-
-	eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg);
-	n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg);
-	printk(KERN_WARNING "EEH: PCI device/vendor: %08x\n", cfg);
-
-	eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg);
-	n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg);
-	printk(KERN_WARNING "EEH: PCI cmd/status register: %08x\n", cfg);
-
-	if (!dev) {
-		printk(KERN_WARNING "EEH: no PCI device for this of node\n");
-		return n;
-	}
-
-	/* Gather bridge-specific registers */
-	if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) {
-		eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg);
-		n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg);
-		printk(KERN_WARNING "EEH: Bridge secondary status: %04x\n", cfg);
-
-		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg);
-		n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg);
-		printk(KERN_WARNING "EEH: Bridge control: %04x\n", cfg);
-	}
-
-	/* Dump out the PCI-X command and status regs */
-	cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
-	if (cap) {
-		eeh_ops->read_config(dn, cap, 4, &cfg);
-		n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg);
-		printk(KERN_WARNING "EEH: PCI-X cmd: %08x\n", cfg);
-
-		eeh_ops->read_config(dn, cap+4, 4, &cfg);
-		n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg);
-		printk(KERN_WARNING "EEH: PCI-X status: %08x\n", cfg);
-	}
-
-	/* If PCI-E capable, dump PCI-E cap 10, and the AER */
-	cap = pci_find_capability(dev, PCI_CAP_ID_EXP);
-	if (cap) {
-		n += scnprintf(buf+n, len-n, "pci-e cap10:\n");
-		printk(KERN_WARNING
-		       "EEH: PCI-E capabilities and status follow:\n");
-
-		for (i=0; i<=8; i++) {
-			eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
-			n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
-			printk(KERN_WARNING "EEH: PCI-E %02x: %08x\n", i, cfg);
-		}
-
-		cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
-		if (cap) {
-			n += scnprintf(buf+n, len-n, "pci-e AER:\n");
-			printk(KERN_WARNING
-			       "EEH: PCI-E AER capability register set follows:\n");
-
-			for (i=0; i<14; i++) {
-				eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
-				n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
-				printk(KERN_WARNING "EEH: PCI-E AER %02x: %08x\n", i, cfg);
-			}
-		}
-	}
-
-	return n;
-}
-
-/**
- * eeh_slot_error_detail - Generate combined log including driver log and error log
- * @pe: EEH PE
- * @severity: temporary or permanent error log
- *
- * This routine should be called to generate the combined log, which
- * is comprised of driver log and error log. The driver log is figured
- * out from the config space of the corresponding PCI device, while
- * the error log is fetched through platform dependent function call.
- */
-void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
-{
-	size_t loglen = 0;
-	struct eeh_dev *edev;
-
-	eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
-	eeh_ops->configure_bridge(pe);
-	eeh_pe_restore_bars(pe);
-
-	pci_regs_buf[0] = 0;
-	eeh_pe_for_each_dev(pe, edev) {
-		loglen += eeh_gather_pci_data(edev, pci_regs_buf,
-				EEH_PCI_REGS_LOG_LEN);
-        }
-
-	eeh_ops->get_log(pe, severity, pci_regs_buf, loglen);
-}
-
-/**
- * eeh_token_to_phys - Convert EEH address token to phys address
- * @token: I/O token, should be address in the form 0xA....
- *
- * This routine should be called to convert virtual I/O address
- * to physical one.
- */
-static inline unsigned long eeh_token_to_phys(unsigned long token)
-{
-	pte_t *ptep;
-	unsigned long pa;
-
-	ptep = find_linux_pte(init_mm.pgd, token);
-	if (!ptep)
-		return token;
-	pa = pte_pfn(*ptep) << PAGE_SHIFT;
-
-	return pa | (token & (PAGE_SIZE-1));
-}
-
-/**
- * eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze
- * @edev: eeh device
- *
- * Check for an EEH failure for the given device node.  Call this
- * routine if the result of a read was all 0xff's and you want to
- * find out if this is due to an EEH slot freeze.  This routine
- * will query firmware for the EEH status.
- *
- * Returns 0 if there has not been an EEH error; otherwise returns
- * a non-zero value and queues up a slot isolation event notification.
- *
- * It is safe to call this routine in an interrupt context.
- */
-int eeh_dev_check_failure(struct eeh_dev *edev)
-{
-	int ret;
-	unsigned long flags;
-	struct device_node *dn;
-	struct pci_dev *dev;
-	struct eeh_pe *pe;
-	int rc = 0;
-	const char *location;
-
-	eeh_stats.total_mmio_ffs++;
-
-	if (!eeh_subsystem_enabled)
-		return 0;
-
-	if (!edev) {
-		eeh_stats.no_dn++;
-		return 0;
-	}
-	dn = eeh_dev_to_of_node(edev);
-	dev = eeh_dev_to_pci_dev(edev);
-	pe = edev->pe;
-
-	/* Access to IO BARs might get this far and still not want checking. */
-	if (!pe) {
-		eeh_stats.ignored_check++;
-		pr_debug("EEH: Ignored check for %s %s\n",
-			eeh_pci_name(dev), dn->full_name);
-		return 0;
-	}
-
-	if (!pe->addr && !pe->config_addr) {
-		eeh_stats.no_cfg_addr++;
-		return 0;
-	}
-
-	/* If we already have a pending isolation event for this
-	 * slot, we know it's bad already, we don't need to check.
-	 * Do this checking under a lock; as multiple PCI devices
-	 * in one slot might report errors simultaneously, and we
-	 * only want one error recovery routine running.
-	 */
-	raw_spin_lock_irqsave(&confirm_error_lock, flags);
-	rc = 1;
-	if (pe->state & EEH_PE_ISOLATED) {
-		pe->check_count++;
-		if (pe->check_count % EEH_MAX_FAILS == 0) {
-			location = of_get_property(dn, "ibm,loc-code", NULL);
-			printk(KERN_ERR "EEH: %d reads ignored for recovering device at "
-				"location=%s driver=%s pci addr=%s\n",
-				pe->check_count, location,
-				eeh_driver_name(dev), eeh_pci_name(dev));
-			printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n",
-				eeh_driver_name(dev));
-			dump_stack();
-		}
-		goto dn_unlock;
-	}
-
-	/*
-	 * Now test for an EEH failure.  This is VERY expensive.
-	 * Note that the eeh_config_addr may be a parent device
-	 * in the case of a device behind a bridge, or it may be
-	 * function zero of a multi-function device.
-	 * In any case they must share a common PHB.
-	 */
-	ret = eeh_ops->get_state(pe, NULL);
-
-	/* Note that config-io to empty slots may fail;
-	 * they are empty when they don't have children.
-	 * We will punt with the following conditions: Failure to get
-	 * PE's state, EEH not support and Permanently unavailable
-	 * state, PE is in good state.
-	 */
-	if ((ret < 0) ||
-	    (ret == EEH_STATE_NOT_SUPPORT) ||
-	    (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) ==
-	    (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) {
-		eeh_stats.false_positives++;
-		pe->false_positives++;
-		rc = 0;
-		goto dn_unlock;
-	}
-
-	eeh_stats.slot_resets++;
- 
-	/* Avoid repeated reports of this failure, including problems
-	 * with other functions on this device, and functions under
-	 * bridges.
-	 */
-	eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
-	raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
-
-	eeh_send_failure_event(pe);
-
-	/* Most EEH events are due to device driver bugs.  Having
-	 * a stack trace will help the device-driver authors figure
-	 * out what happened.  So print that out.
-	 */
-	WARN(1, "EEH: failure detected\n");
-	return 1;
-
-dn_unlock:
-	raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
-	return rc;
-}
-
-EXPORT_SYMBOL_GPL(eeh_dev_check_failure);
-
-/**
- * eeh_check_failure - Check if all 1's data is due to EEH slot freeze
- * @token: I/O token, should be address in the form 0xA....
- * @val: value, should be all 1's (XXX why do we need this arg??)
- *
- * Check for an EEH failure at the given token address.  Call this
- * routine if the result of a read was all 0xff's and you want to
- * find out if this is due to an EEH slot freeze event.  This routine
- * will query firmware for the EEH status.
- *
- * Note this routine is safe to call in an interrupt context.
- */
-unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
-{
-	unsigned long addr;
-	struct eeh_dev *edev;
-
-	/* Finding the phys addr + pci device; this is pretty quick. */
-	addr = eeh_token_to_phys((unsigned long __force) token);
-	edev = eeh_addr_cache_get_dev(addr);
-	if (!edev) {
-		eeh_stats.no_device++;
-		return val;
-	}
-
-	eeh_dev_check_failure(edev);
-
-	pci_dev_put(eeh_dev_to_pci_dev(edev));
-	return val;
-}
-
-EXPORT_SYMBOL(eeh_check_failure);
-
-
-/**
- * eeh_pci_enable - Enable MMIO or DMA transfers for this slot
- * @pe: EEH PE
- *
- * This routine should be called to reenable frozen MMIO or DMA
- * so that it would work correctly again. It's useful while doing
- * recovery or log collection on the indicated device.
- */
-int eeh_pci_enable(struct eeh_pe *pe, int function)
-{
-	int rc;
-
-	rc = eeh_ops->set_option(pe, function);
-	if (rc)
-		pr_warning("%s: Unexpected state change %d on PHB#%d-PE#%x, err=%d\n",
-			__func__, function, pe->phb->global_number, pe->addr, rc);
-
-	rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-	if (rc > 0 && (rc & EEH_STATE_MMIO_ENABLED) &&
-	   (function == EEH_OPT_THAW_MMIO))
-		return 0;
-
-	return rc;
-}
-
-/**
- * pcibios_set_pcie_slot_reset - Set PCI-E reset state
- * @dev: pci device struct
- * @state: reset state to enter
- *
- * Return value:
- * 	0 if success
- */
-int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
-{
-	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
-	struct eeh_pe *pe = edev->pe;
-
-	if (!pe) {
-		pr_err("%s: No PE found on PCI device %s\n",
-			__func__, pci_name(dev));
-		return -EINVAL;
-	}
-
-	switch (state) {
-	case pcie_deassert_reset:
-		eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
-		break;
-	case pcie_hot_reset:
-		eeh_ops->reset(pe, EEH_RESET_HOT);
-		break;
-	case pcie_warm_reset:
-		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
-		break;
-	default:
-		return -EINVAL;
-	};
-
-	return 0;
-}
-
-/**
- * eeh_set_pe_freset - Check the required reset for the indicated device
- * @data: EEH device
- * @flag: return value
- *
- * Each device might have its preferred reset type: fundamental or
- * hot reset. The routine is used to collected the information for
- * the indicated device and its children so that the bunch of the
- * devices could be reset properly.
- */
-static void *eeh_set_dev_freset(void *data, void *flag)
-{
-	struct pci_dev *dev;
-	unsigned int *freset = (unsigned int *)flag;
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-
-	dev = eeh_dev_to_pci_dev(edev);
-	if (dev)
-		*freset |= dev->needs_freset;
-
-	return NULL;
-}
-
-/**
- * eeh_reset_pe_once - Assert the pci #RST line for 1/4 second
- * @pe: EEH PE
- *
- * Assert the PCI #RST line for 1/4 second.
- */
-static void eeh_reset_pe_once(struct eeh_pe *pe)
-{
-	unsigned int freset = 0;
-
-	/* Determine type of EEH reset required for
-	 * Partitionable Endpoint, a hot-reset (1)
-	 * or a fundamental reset (3).
-	 * A fundamental reset required by any device under
-	 * Partitionable Endpoint trumps hot-reset.
-  	 */
-	eeh_pe_dev_traverse(pe, eeh_set_dev_freset, &freset);
-
-	if (freset)
-		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
-	else
-		eeh_ops->reset(pe, EEH_RESET_HOT);
-
-	/* The PCI bus requires that the reset be held high for at least
-	 * a 100 milliseconds. We wait a bit longer 'just in case'.
-	 */
-#define PCI_BUS_RST_HOLD_TIME_MSEC 250
-	msleep(PCI_BUS_RST_HOLD_TIME_MSEC);
-	
-	/* We might get hit with another EEH freeze as soon as the 
-	 * pci slot reset line is dropped. Make sure we don't miss
-	 * these, and clear the flag now.
-	 */
-	eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
-
-	eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
-
-	/* After a PCI slot has been reset, the PCI Express spec requires
-	 * a 1.5 second idle time for the bus to stabilize, before starting
-	 * up traffic.
-	 */
-#define PCI_BUS_SETTLE_TIME_MSEC 1800
-	msleep(PCI_BUS_SETTLE_TIME_MSEC);
-}
-
-/**
- * eeh_reset_pe - Reset the indicated PE
- * @pe: EEH PE
- *
- * This routine should be called to reset indicated device, including
- * PE. A PE might include multiple PCI devices and sometimes PCI bridges
- * might be involved as well.
- */
-int eeh_reset_pe(struct eeh_pe *pe)
-{
-	int i, rc;
-
-	/* Take three shots at resetting the bus */
-	for (i=0; i<3; i++) {
-		eeh_reset_pe_once(pe);
-
-		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-		if (rc == (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE))
-			return 0;
-
-		if (rc < 0) {
-			pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
-				__func__, pe->phb->global_number, pe->addr);
-			return -1;
-		}
-		pr_err("EEH: bus reset %d failed on PHB#%d-PE#%x, rc=%d\n",
-			i+1, pe->phb->global_number, pe->addr, rc);
-	}
-
-	return -1;
-}
-
-/**
- * eeh_save_bars - Save device bars
- * @edev: PCI device associated EEH device
- *
- * Save the values of the device bars. Unlike the restore
- * routine, this routine is *not* recursive. This is because
- * PCI devices are added individually; but, for the restore,
- * an entire slot is reset at a time.
- */
-void eeh_save_bars(struct eeh_dev *edev)
-{
-	int i;
-	struct device_node *dn;
-
-	if (!edev)
-		return;
-	dn = eeh_dev_to_of_node(edev);
-	
-	for (i = 0; i < 16; i++)
-		eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]);
-}
-
-/**
- * eeh_ops_register - Register platform dependent EEH operations
- * @ops: platform dependent EEH operations
- *
- * Register the platform dependent EEH operation callback
- * functions. The platform should call this function before
- * any other EEH operations.
- */
-int __init eeh_ops_register(struct eeh_ops *ops)
-{
-	if (!ops->name) {
-		pr_warning("%s: Invalid EEH ops name for %p\n",
-			__func__, ops);
-		return -EINVAL;
-	}
-
-	if (eeh_ops && eeh_ops != ops) {
-		pr_warning("%s: EEH ops of platform %s already existing (%s)\n",
-			__func__, eeh_ops->name, ops->name);
-		return -EEXIST;
-	}
-
-	eeh_ops = ops;
-
-	return 0;
-}
-
-/**
- * eeh_ops_unregister - Unreigster platform dependent EEH operations
- * @name: name of EEH platform operations
- *
- * Unregister the platform dependent EEH operation callback
- * functions.
- */
-int __exit eeh_ops_unregister(const char *name)
-{
-	if (!name || !strlen(name)) {
-		pr_warning("%s: Invalid EEH ops name\n",
-			__func__);
-		return -EINVAL;
-	}
-
-	if (eeh_ops && !strcmp(eeh_ops->name, name)) {
-		eeh_ops = NULL;
-		return 0;
-	}
-
-	return -EEXIST;
-}
-
-/**
- * eeh_init - EEH initialization
- *
- * Initialize EEH by trying to enable it for all of the adapters in the system.
- * As a side effect we can determine here if eeh is supported at all.
- * Note that we leave EEH on so failed config cycles won't cause a machine
- * check.  If a user turns off EEH for a particular adapter they are really
- * telling Linux to ignore errors.  Some hardware (e.g. POWER5) won't
- * grant access to a slot if EEH isn't enabled, and so we always enable
- * EEH for all slots/all devices.
- *
- * The eeh-force-off option disables EEH checking globally, for all slots.
- * Even if force-off is set, the EEH hardware is still enabled, so that
- * newer systems can boot.
- */
-static int __init eeh_init(void)
-{
-	struct pci_controller *hose, *tmp;
-	struct device_node *phb;
-	int ret;
-
-	/* call platform initialization function */
-	if (!eeh_ops) {
-		pr_warning("%s: Platform EEH operation not found\n",
-			__func__);
-		return -EEXIST;
-	} else if ((ret = eeh_ops->init())) {
-		pr_warning("%s: Failed to call platform init function (%d)\n",
-			__func__, ret);
-		return ret;
-	}
-
-	raw_spin_lock_init(&confirm_error_lock);
-
-	/* Enable EEH for all adapters */
-	if (eeh_probe_mode_devtree()) {
-		list_for_each_entry_safe(hose, tmp,
-			&hose_list, list_node) {
-			phb = hose->dn;
-			traverse_pci_devices(phb, eeh_ops->of_probe, NULL);
-		}
-	}
-
-	if (eeh_subsystem_enabled)
-		pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
-	else
-		pr_warning("EEH: No capable adapters found\n");
-
-	return ret;
-}
-
-core_initcall_sync(eeh_init);
-
-/**
- * eeh_add_device_early - Enable EEH for the indicated device_node
- * @dn: device node for which to set up EEH
- *
- * This routine must be used to perform EEH initialization for PCI
- * devices that were added after system boot (e.g. hotplug, dlpar).
- * This routine must be called before any i/o is performed to the
- * adapter (inluding any config-space i/o).
- * Whether this actually enables EEH or not for this device depends
- * on the CEC architecture, type of the device, on earlier boot
- * command-line arguments & etc.
- */
-static void eeh_add_device_early(struct device_node *dn)
-{
-	struct pci_controller *phb;
-
-	if (!of_node_to_eeh_dev(dn))
-		return;
-	phb = of_node_to_eeh_dev(dn)->phb;
-
-	/* USB Bus children of PCI devices will not have BUID's */
-	if (NULL == phb || 0 == phb->buid)
-		return;
-
-	/* FIXME: hotplug support on POWERNV */
-	eeh_ops->of_probe(dn, NULL);
-}
-
-/**
- * eeh_add_device_tree_early - Enable EEH for the indicated device
- * @dn: device node
- *
- * This routine must be used to perform EEH initialization for the
- * indicated PCI device that was added after system boot (e.g.
- * hotplug, dlpar).
- */
-void eeh_add_device_tree_early(struct device_node *dn)
-{
-	struct device_node *sib;
-
-	for_each_child_of_node(dn, sib)
-		eeh_add_device_tree_early(sib);
-	eeh_add_device_early(dn);
-}
-EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
-
-/**
- * eeh_add_device_late - Perform EEH initialization for the indicated pci device
- * @dev: pci device for which to set up EEH
- *
- * This routine must be used to complete EEH initialization for PCI
- * devices that were added after system boot (e.g. hotplug, dlpar).
- */
-static void eeh_add_device_late(struct pci_dev *dev)
-{
-	struct device_node *dn;
-	struct eeh_dev *edev;
-
-	if (!dev || !eeh_subsystem_enabled)
-		return;
-
-	pr_debug("EEH: Adding device %s\n", pci_name(dev));
-
-	dn = pci_device_to_OF_node(dev);
-	edev = of_node_to_eeh_dev(dn);
-	if (edev->pdev == dev) {
-		pr_debug("EEH: Already referenced !\n");
-		return;
-	}
-	WARN_ON(edev->pdev);
-
-	pci_dev_get(dev);
-	edev->pdev = dev;
-	dev->dev.archdata.edev = edev;
-
-	eeh_addr_cache_insert_dev(dev);
-}
-
-/**
- * eeh_add_device_tree_late - Perform EEH initialization for the indicated PCI bus
- * @bus: PCI bus
- *
- * This routine must be used to perform EEH initialization for PCI
- * devices which are attached to the indicated PCI bus. The PCI bus
- * is added after system boot through hotplug or dlpar.
- */
-void eeh_add_device_tree_late(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
- 		eeh_add_device_late(dev);
- 		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
- 			struct pci_bus *subbus = dev->subordinate;
- 			if (subbus)
- 				eeh_add_device_tree_late(subbus);
- 		}
-	}
-}
-EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
-
-/**
- * eeh_add_sysfs_files - Add EEH sysfs files for the indicated PCI bus
- * @bus: PCI bus
- *
- * This routine must be used to add EEH sysfs files for PCI
- * devices which are attached to the indicated PCI bus. The PCI bus
- * is added after system boot through hotplug or dlpar.
- */
-void eeh_add_sysfs_files(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		eeh_sysfs_add_device(dev);
-		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-			struct pci_bus *subbus = dev->subordinate;
-			if (subbus)
-				eeh_add_sysfs_files(subbus);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(eeh_add_sysfs_files);
-
-/**
- * eeh_remove_device - Undo EEH setup for the indicated pci device
- * @dev: pci device to be removed
- * @purge_pe: remove the PE or not
- *
- * This routine should be called when a device is removed from
- * a running system (e.g. by hotplug or dlpar).  It unregisters
- * the PCI device from the EEH subsystem.  I/O errors affecting
- * this device will no longer be detected after this call; thus,
- * i/o errors affecting this slot may leave this device unusable.
- */
-static void eeh_remove_device(struct pci_dev *dev, int purge_pe)
-{
-	struct eeh_dev *edev;
-
-	if (!dev || !eeh_subsystem_enabled)
-		return;
-	edev = pci_dev_to_eeh_dev(dev);
-
-	/* Unregister the device with the EEH/PCI address search system */
-	pr_debug("EEH: Removing device %s\n", pci_name(dev));
-
-	if (!edev || !edev->pdev) {
-		pr_debug("EEH: Not referenced !\n");
-		return;
-	}
-	edev->pdev = NULL;
-	dev->dev.archdata.edev = NULL;
-	pci_dev_put(dev);
-
-	eeh_rmv_from_parent_pe(edev, purge_pe);
-	eeh_addr_cache_rmv_dev(dev);
-	eeh_sysfs_remove_device(dev);
-}
-
-/**
- * eeh_remove_bus_device - Undo EEH setup for the indicated PCI device
- * @dev: PCI device
- * @purge_pe: remove the corresponding PE or not
- *
- * This routine must be called when a device is removed from the
- * running system through hotplug or dlpar. The corresponding
- * PCI address cache will be removed.
- */
-void eeh_remove_bus_device(struct pci_dev *dev, int purge_pe)
-{
-	struct pci_bus *bus = dev->subordinate;
-	struct pci_dev *child, *tmp;
-
-	eeh_remove_device(dev, purge_pe);
-
-	if (bus && dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-		list_for_each_entry_safe(child, tmp, &bus->devices, bus_list)
-			 eeh_remove_bus_device(child, purge_pe);
-	}
-}
-EXPORT_SYMBOL_GPL(eeh_remove_bus_device);
-
-static int proc_eeh_show(struct seq_file *m, void *v)
-{
-	if (0 == eeh_subsystem_enabled) {
-		seq_printf(m, "EEH Subsystem is globally disabled\n");
-		seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs);
-	} else {
-		seq_printf(m, "EEH Subsystem is enabled\n");
-		seq_printf(m,
-				"no device=%llu\n"
-				"no device node=%llu\n"
-				"no config address=%llu\n"
-				"check not wanted=%llu\n"
-				"eeh_total_mmio_ffs=%llu\n"
-				"eeh_false_positives=%llu\n"
-				"eeh_slot_resets=%llu\n",
-				eeh_stats.no_device,
-				eeh_stats.no_dn,
-				eeh_stats.no_cfg_addr,
-				eeh_stats.ignored_check,
-				eeh_stats.total_mmio_ffs,
-				eeh_stats.false_positives,
-				eeh_stats.slot_resets);
-	}
-
-	return 0;
-}
-
-static int proc_eeh_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_eeh_show, NULL);
-}
-
-static const struct file_operations proc_eeh_operations = {
-	.open      = proc_eeh_open,
-	.read      = seq_read,
-	.llseek    = seq_lseek,
-	.release   = single_release,
-};
-
-static int __init eeh_init_proc(void)
-{
-	if (machine_is(pseries))
-		proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
-	return 0;
-}
-__initcall(eeh_init_proc);
diff --git a/arch/powerpc/platforms/pseries/eeh_cache.c b/arch/powerpc/platforms/pseries/eeh_cache.c
deleted file mode 100644
index 5ce3ba7..0000000
--- a/arch/powerpc/platforms/pseries/eeh_cache.c
+++ /dev/null
@@ -1,319 +0,0 @@
-/*
- * PCI address cache; allows the lookup of PCI devices based on I/O address
- *
- * Copyright IBM Corporation 2004
- * Copyright Linas Vepstas <linas@austin.ibm.com> 2004
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#include <linux/list.h>
-#include <linux/pci.h>
-#include <linux/rbtree.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/atomic.h>
-#include <asm/pci-bridge.h>
-#include <asm/ppc-pci.h>
-
-
-/**
- * The pci address cache subsystem.  This subsystem places
- * PCI device address resources into a red-black tree, sorted
- * according to the address range, so that given only an i/o
- * address, the corresponding PCI device can be **quickly**
- * found. It is safe to perform an address lookup in an interrupt
- * context; this ability is an important feature.
- *
- * Currently, the only customer of this code is the EEH subsystem;
- * thus, this code has been somewhat tailored to suit EEH better.
- * In particular, the cache does *not* hold the addresses of devices
- * for which EEH is not enabled.
- *
- * (Implementation Note: The RB tree seems to be better/faster
- * than any hash algo I could think of for this problem, even
- * with the penalty of slow pointer chases for d-cache misses).
- */
-struct pci_io_addr_range {
-	struct rb_node rb_node;
-	unsigned long addr_lo;
-	unsigned long addr_hi;
-	struct eeh_dev *edev;
-	struct pci_dev *pcidev;
-	unsigned int flags;
-};
-
-static struct pci_io_addr_cache {
-	struct rb_root rb_root;
-	spinlock_t piar_lock;
-} pci_io_addr_cache_root;
-
-static inline struct eeh_dev *__eeh_addr_cache_get_device(unsigned long addr)
-{
-	struct rb_node *n = pci_io_addr_cache_root.rb_root.rb_node;
-
-	while (n) {
-		struct pci_io_addr_range *piar;
-		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
-
-		if (addr < piar->addr_lo) {
-			n = n->rb_left;
-		} else {
-			if (addr > piar->addr_hi) {
-				n = n->rb_right;
-			} else {
-				pci_dev_get(piar->pcidev);
-				return piar->edev;
-			}
-		}
-	}
-
-	return NULL;
-}
-
-/**
- * eeh_addr_cache_get_dev - Get device, given only address
- * @addr: mmio (PIO) phys address or i/o port number
- *
- * Given an mmio phys address, or a port number, find a pci device
- * that implements this address.  Be sure to pci_dev_put the device
- * when finished.  I/O port numbers are assumed to be offset
- * from zero (that is, they do *not* have pci_io_addr added in).
- * It is safe to call this function within an interrupt.
- */
-struct eeh_dev *eeh_addr_cache_get_dev(unsigned long addr)
-{
-	struct eeh_dev *edev;
-	unsigned long flags;
-
-	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
-	edev = __eeh_addr_cache_get_device(addr);
-	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
-	return edev;
-}
-
-#ifdef DEBUG
-/*
- * Handy-dandy debug print routine, does nothing more
- * than print out the contents of our addr cache.
- */
-static void eeh_addr_cache_print(struct pci_io_addr_cache *cache)
-{
-	struct rb_node *n;
-	int cnt = 0;
-
-	n = rb_first(&cache->rb_root);
-	while (n) {
-		struct pci_io_addr_range *piar;
-		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
-		pr_debug("PCI: %s addr range %d [%lx-%lx]: %s\n",
-		       (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", cnt,
-		       piar->addr_lo, piar->addr_hi, pci_name(piar->pcidev));
-		cnt++;
-		n = rb_next(n);
-	}
-}
-#endif
-
-/* Insert address range into the rb tree. */
-static struct pci_io_addr_range *
-eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
-		      unsigned long ahi, unsigned int flags)
-{
-	struct rb_node **p = &pci_io_addr_cache_root.rb_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct pci_io_addr_range *piar;
-
-	/* Walk tree, find a place to insert into tree */
-	while (*p) {
-		parent = *p;
-		piar = rb_entry(parent, struct pci_io_addr_range, rb_node);
-		if (ahi < piar->addr_lo) {
-			p = &parent->rb_left;
-		} else if (alo > piar->addr_hi) {
-			p = &parent->rb_right;
-		} else {
-			if (dev != piar->pcidev ||
-			    alo != piar->addr_lo || ahi != piar->addr_hi) {
-				pr_warning("PIAR: overlapping address range\n");
-			}
-			return piar;
-		}
-	}
-	piar = kzalloc(sizeof(struct pci_io_addr_range), GFP_ATOMIC);
-	if (!piar)
-		return NULL;
-
-	pci_dev_get(dev);
-	piar->addr_lo = alo;
-	piar->addr_hi = ahi;
-	piar->edev = pci_dev_to_eeh_dev(dev);
-	piar->pcidev = dev;
-	piar->flags = flags;
-
-#ifdef DEBUG
-	pr_debug("PIAR: insert range=[%lx:%lx] dev=%s\n",
-	                  alo, ahi, pci_name(dev));
-#endif
-
-	rb_link_node(&piar->rb_node, parent, p);
-	rb_insert_color(&piar->rb_node, &pci_io_addr_cache_root.rb_root);
-
-	return piar;
-}
-
-static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
-{
-	struct device_node *dn;
-	struct eeh_dev *edev;
-	int i;
-
-	dn = pci_device_to_OF_node(dev);
-	if (!dn) {
-		pr_warning("PCI: no pci dn found for dev=%s\n", pci_name(dev));
-		return;
-	}
-
-	edev = of_node_to_eeh_dev(dn);
-	if (!edev) {
-		pr_warning("PCI: no EEH dev found for dn=%s\n",
-			dn->full_name);
-		return;
-	}
-
-	/* Skip any devices for which EEH is not enabled. */
-	if (!edev->pe) {
-#ifdef DEBUG
-		pr_info("PCI: skip building address cache for=%s - %s\n",
-			pci_name(dev), dn->full_name);
-#endif
-		return;
-	}
-
-	/* Walk resources on this device, poke them into the tree */
-	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
-		unsigned long start = pci_resource_start(dev,i);
-		unsigned long end = pci_resource_end(dev,i);
-		unsigned int flags = pci_resource_flags(dev,i);
-
-		/* We are interested only bus addresses, not dma or other stuff */
-		if (0 == (flags & (IORESOURCE_IO | IORESOURCE_MEM)))
-			continue;
-		if (start == 0 || ~start == 0 || end == 0 || ~end == 0)
-			 continue;
-		eeh_addr_cache_insert(dev, start, end, flags);
-	}
-}
-
-/**
- * eeh_addr_cache_insert_dev - Add a device to the address cache
- * @dev: PCI device whose I/O addresses we are interested in.
- *
- * In order to support the fast lookup of devices based on addresses,
- * we maintain a cache of devices that can be quickly searched.
- * This routine adds a device to that cache.
- */
-void eeh_addr_cache_insert_dev(struct pci_dev *dev)
-{
-	unsigned long flags;
-
-	/* Ignore PCI bridges */
-	if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE)
-		return;
-
-	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
-	__eeh_addr_cache_insert_dev(dev);
-	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
-}
-
-static inline void __eeh_addr_cache_rmv_dev(struct pci_dev *dev)
-{
-	struct rb_node *n;
-
-restart:
-	n = rb_first(&pci_io_addr_cache_root.rb_root);
-	while (n) {
-		struct pci_io_addr_range *piar;
-		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
-
-		if (piar->pcidev == dev) {
-			rb_erase(n, &pci_io_addr_cache_root.rb_root);
-			pci_dev_put(piar->pcidev);
-			kfree(piar);
-			goto restart;
-		}
-		n = rb_next(n);
-	}
-}
-
-/**
- * eeh_addr_cache_rmv_dev - remove pci device from addr cache
- * @dev: device to remove
- *
- * Remove a device from the addr-cache tree.
- * This is potentially expensive, since it will walk
- * the tree multiple times (once per resource).
- * But so what; device removal doesn't need to be that fast.
- */
-void eeh_addr_cache_rmv_dev(struct pci_dev *dev)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
-	__eeh_addr_cache_rmv_dev(dev);
-	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
-}
-
-/**
- * eeh_addr_cache_build - Build a cache of I/O addresses
- *
- * Build a cache of pci i/o addresses.  This cache will be used to
- * find the pci device that corresponds to a given address.
- * This routine scans all pci busses to build the cache.
- * Must be run late in boot process, after the pci controllers
- * have been scanned for devices (after all device resources are known).
- */
-void __init eeh_addr_cache_build(void)
-{
-	struct device_node *dn;
-	struct eeh_dev *edev;
-	struct pci_dev *dev = NULL;
-
-	spin_lock_init(&pci_io_addr_cache_root.piar_lock);
-
-	for_each_pci_dev(dev) {
-		dn = pci_device_to_OF_node(dev);
-		if (!dn)
-			continue;
-
-		edev = of_node_to_eeh_dev(dn);
-		if (!edev)
-			continue;
-
-		pci_dev_get(dev);  /* matching put is in eeh_remove_device() */
-		dev->dev.archdata.edev = edev;
-		edev->pdev = dev;
-
-		eeh_addr_cache_insert_dev(dev);
-
-		eeh_sysfs_add_device(dev);
-	}
-
-#ifdef DEBUG
-	/* Verify tree built up above, echo back the list of addrs. */
-	eeh_addr_cache_print(&pci_io_addr_cache_root);
-#endif
-}
-
diff --git a/arch/powerpc/platforms/pseries/eeh_dev.c b/arch/powerpc/platforms/pseries/eeh_dev.c
deleted file mode 100644
index 1efa28f..0000000
--- a/arch/powerpc/platforms/pseries/eeh_dev.c
+++ /dev/null
@@ -1,112 +0,0 @@
-/*
- * The file intends to implement dynamic creation of EEH device, which will
- * be bound with OF node and PCI device simutaneously. The EEH devices would
- * be foundamental information for EEH core components to work proerly. Besides,
- * We have to support multiple situations where dynamic creation of EEH device
- * is required:
- *
- * 1) Before PCI emunation starts, we need create EEH devices according to the
- *    PCI sensitive OF nodes.
- * 2) When PCI emunation is done, we need do the binding between PCI device and
- *    the associated EEH device.
- * 3) DR (Dynamic Reconfiguration) would create PCI sensitive OF node. EEH device
- *    will be created while PCI sensitive OF node is detected from DR.
- * 4) PCI hotplug needs redoing the binding between PCI device and EEH device. If
- *    PHB is newly inserted, we also need create EEH devices accordingly.
- *
- * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#include <linux/export.h>
-#include <linux/gfp.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/string.h>
-
-#include <asm/pci-bridge.h>
-#include <asm/ppc-pci.h>
-
-/**
- * eeh_dev_init - Create EEH device according to OF node
- * @dn: device node
- * @data: PHB
- *
- * It will create EEH device according to the given OF node. The function
- * might be called by PCI emunation, DR, PHB hotplug.
- */
-void *eeh_dev_init(struct device_node *dn, void *data)
-{
-	struct pci_controller *phb = data;
-	struct eeh_dev *edev;
-
-	/* Allocate EEH device */
-	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
-	if (!edev) {
-		pr_warning("%s: out of memory\n", __func__);
-		return NULL;
-	}
-
-	/* Associate EEH device with OF node */
-	PCI_DN(dn)->edev = edev;
-	edev->dn  = dn;
-	edev->phb = phb;
-	INIT_LIST_HEAD(&edev->list);
-
-	return NULL;
-}
-
-/**
- * eeh_dev_phb_init_dynamic - Create EEH devices for devices included in PHB
- * @phb: PHB
- *
- * Scan the PHB OF node and its child association, then create the
- * EEH devices accordingly
- */
-void eeh_dev_phb_init_dynamic(struct pci_controller *phb)
-{
-	struct device_node *dn = phb->dn;
-
-	/* EEH PE for PHB */
-	eeh_phb_pe_create(phb);
-
-	/* EEH device for PHB */
-	eeh_dev_init(dn, phb);
-
-	/* EEH devices for children OF nodes */
-	traverse_pci_devices(dn, eeh_dev_init, phb);
-}
-
-/**
- * eeh_dev_phb_init - Create EEH devices for devices included in existing PHBs
- *
- * Scan all the existing PHBs and create EEH devices for their OF
- * nodes and their children OF nodes
- */
-static int __init eeh_dev_phb_init(void)
-{
-	struct pci_controller *phb, *tmp;
-
-	list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
-		eeh_dev_phb_init_dynamic(phb);
-
-	pr_info("EEH: devices created\n");
-
-	return 0;
-}
-
-core_initcall(eeh_dev_phb_init);
diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c
deleted file mode 100644
index a3fefb6..0000000
--- a/arch/powerpc/platforms/pseries/eeh_driver.c
+++ /dev/null
@@ -1,552 +0,0 @@
-/*
- * PCI Error Recovery Driver for RPA-compliant PPC64 platform.
- * Copyright IBM Corp. 2004 2005
- * Copyright Linas Vepstas <linas@linas.org> 2004, 2005
- *
- * All rights reserved.
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
- */
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <asm/eeh.h>
-#include <asm/eeh_event.h>
-#include <asm/ppc-pci.h>
-#include <asm/pci-bridge.h>
-#include <asm/prom.h>
-#include <asm/rtas.h>
-
-/**
- * eeh_pcid_name - Retrieve name of PCI device driver
- * @pdev: PCI device
- *
- * This routine is used to retrieve the name of PCI device driver
- * if that's valid.
- */
-static inline const char *eeh_pcid_name(struct pci_dev *pdev)
-{
-	if (pdev && pdev->dev.driver)
-		return pdev->dev.driver->name;
-	return "";
-}
-
-/**
- * eeh_pcid_get - Get the PCI device driver
- * @pdev: PCI device
- *
- * The function is used to retrieve the PCI device driver for
- * the indicated PCI device. Besides, we will increase the reference
- * of the PCI device driver to prevent that being unloaded on
- * the fly. Otherwise, kernel crash would be seen.
- */
-static inline struct pci_driver *eeh_pcid_get(struct pci_dev *pdev)
-{
-	if (!pdev || !pdev->driver)
-		return NULL;
-
-	if (!try_module_get(pdev->driver->driver.owner))
-		return NULL;
-
-	return pdev->driver;
-}
-
-/**
- * eeh_pcid_put - Dereference on the PCI device driver
- * @pdev: PCI device
- *
- * The function is called to do dereference on the PCI device
- * driver of the indicated PCI device.
- */
-static inline void eeh_pcid_put(struct pci_dev *pdev)
-{
-	if (!pdev || !pdev->driver)
-		return;
-
-	module_put(pdev->driver->driver.owner);
-}
-
-#if 0
-static void print_device_node_tree(struct pci_dn *pdn, int dent)
-{
-	int i;
-	struct device_node *pc;
-
-	if (!pdn)
-		return;
-	for (i = 0; i < dent; i++)
-		printk(" ");
-	printk("dn=%s mode=%x \tcfg_addr=%x pe_addr=%x \tfull=%s\n",
-		pdn->node->name, pdn->eeh_mode, pdn->eeh_config_addr,
-		pdn->eeh_pe_config_addr, pdn->node->full_name);
-	dent += 3;
-	pc = pdn->node->child;
-	while (pc) {
-		print_device_node_tree(PCI_DN(pc), dent);
-		pc = pc->sibling;
-	}
-}
-#endif
-
-/**
- * eeh_disable_irq - Disable interrupt for the recovering device
- * @dev: PCI device
- *
- * This routine must be called when reporting temporary or permanent
- * error to the particular PCI device to disable interrupt of that
- * device. If the device has enabled MSI or MSI-X interrupt, we needn't
- * do real work because EEH should freeze DMA transfers for those PCI
- * devices encountering EEH errors, which includes MSI or MSI-X.
- */
-static void eeh_disable_irq(struct pci_dev *dev)
-{
-	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
-
-	/* Don't disable MSI and MSI-X interrupts. They are
-	 * effectively disabled by the DMA Stopped state
-	 * when an EEH error occurs.
-	 */
-	if (dev->msi_enabled || dev->msix_enabled)
-		return;
-
-	if (!irq_has_action(dev->irq))
-		return;
-
-	edev->mode |= EEH_DEV_IRQ_DISABLED;
-	disable_irq_nosync(dev->irq);
-}
-
-/**
- * eeh_enable_irq - Enable interrupt for the recovering device
- * @dev: PCI device
- *
- * This routine must be called to enable interrupt while failed
- * device could be resumed.
- */
-static void eeh_enable_irq(struct pci_dev *dev)
-{
-	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
-
-	if ((edev->mode) & EEH_DEV_IRQ_DISABLED) {
-		edev->mode &= ~EEH_DEV_IRQ_DISABLED;
-		enable_irq(dev->irq);
-	}
-}
-
-/**
- * eeh_report_error - Report pci error to each device driver
- * @data: eeh device
- * @userdata: return value
- * 
- * Report an EEH error to each device driver, collect up and 
- * merge the device driver responses. Cumulative response 
- * passed back in "userdata".
- */
-static void *eeh_report_error(void *data, void *userdata)
-{
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	enum pci_ers_result rc, *res = userdata;
-	struct pci_driver *driver;
-
-	/* We might not have the associated PCI device,
-	 * then we should continue for next one.
-	 */
-	if (!dev) return NULL;
-	dev->error_state = pci_channel_io_frozen;
-
-	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
-
-	eeh_disable_irq(dev);
-
-	if (!driver->err_handler ||
-	    !driver->err_handler->error_detected) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
-
-	rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen);
-
-	/* A driver that needs a reset trumps all others */
-	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
-	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
-
-	eeh_pcid_put(dev);
-	return NULL;
-}
-
-/**
- * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled
- * @data: eeh device
- * @userdata: return value
- *
- * Tells each device driver that IO ports, MMIO and config space I/O
- * are now enabled. Collects up and merges the device driver responses.
- * Cumulative response passed back in "userdata".
- */
-static void *eeh_report_mmio_enabled(void *data, void *userdata)
-{
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	enum pci_ers_result rc, *res = userdata;
-	struct pci_driver *driver;
-
-	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
-
-	if (!driver->err_handler ||
-	    !driver->err_handler->mmio_enabled) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
-
-	rc = driver->err_handler->mmio_enabled(dev);
-
-	/* A driver that needs a reset trumps all others */
-	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
-	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
-
-	eeh_pcid_put(dev);
-	return NULL;
-}
-
-/**
- * eeh_report_reset - Tell device that slot has been reset
- * @data: eeh device
- * @userdata: return value
- *
- * This routine must be called while EEH tries to reset particular
- * PCI device so that the associated PCI device driver could take
- * some actions, usually to save data the driver needs so that the
- * driver can work again while the device is recovered.
- */
-static void *eeh_report_reset(void *data, void *userdata)
-{
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	enum pci_ers_result rc, *res = userdata;
-	struct pci_driver *driver;
-
-	if (!dev) return NULL;
-	dev->error_state = pci_channel_io_normal;
-
-	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
-
-	eeh_enable_irq(dev);
-
-	if (!driver->err_handler ||
-	    !driver->err_handler->slot_reset) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
-
-	rc = driver->err_handler->slot_reset(dev);
-	if ((*res == PCI_ERS_RESULT_NONE) ||
-	    (*res == PCI_ERS_RESULT_RECOVERED)) *res = rc;
-	if (*res == PCI_ERS_RESULT_DISCONNECT &&
-	     rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
-
-	eeh_pcid_put(dev);
-	return NULL;
-}
-
-/**
- * eeh_report_resume - Tell device to resume normal operations
- * @data: eeh device
- * @userdata: return value
- *
- * This routine must be called to notify the device driver that it
- * could resume so that the device driver can do some initialization
- * to make the recovered device work again.
- */
-static void *eeh_report_resume(void *data, void *userdata)
-{
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	struct pci_driver *driver;
-
-	if (!dev) return NULL;
-	dev->error_state = pci_channel_io_normal;
-
-	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
-
-	eeh_enable_irq(dev);
-
-	if (!driver->err_handler ||
-	    !driver->err_handler->resume) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
-
-	driver->err_handler->resume(dev);
-
-	eeh_pcid_put(dev);
-	return NULL;
-}
-
-/**
- * eeh_report_failure - Tell device driver that device is dead.
- * @data: eeh device
- * @userdata: return value
- *
- * This informs the device driver that the device is permanently
- * dead, and that no further recovery attempts will be made on it.
- */
-static void *eeh_report_failure(void *data, void *userdata)
-{
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	struct pci_driver *driver;
-
-	if (!dev) return NULL;
-	dev->error_state = pci_channel_io_perm_failure;
-
-	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
-
-	eeh_disable_irq(dev);
-
-	if (!driver->err_handler ||
-	    !driver->err_handler->error_detected) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
-
-	driver->err_handler->error_detected(dev, pci_channel_io_perm_failure);
-
-	eeh_pcid_put(dev);
-	return NULL;
-}
-
-/**
- * eeh_reset_device - Perform actual reset of a pci slot
- * @pe: EEH PE
- * @bus: PCI bus corresponding to the isolcated slot
- *
- * This routine must be called to do reset on the indicated PE.
- * During the reset, udev might be invoked because those affected
- * PCI devices will be removed and then added.
- */
-static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
-{
-	int cnt, rc;
-
-	/* pcibios will clear the counter; save the value */
-	cnt = pe->freeze_count;
-
-	/*
-	 * We don't remove the corresponding PE instances because
-	 * we need the information afterwords. The attached EEH
-	 * devices are expected to be attached soon when calling
-	 * into pcibios_add_pci_devices().
-	 */
-	if (bus)
-		__pcibios_remove_pci_devices(bus, 0);
-
-	/* Reset the pci controller. (Asserts RST#; resets config space).
-	 * Reconfigure bridges and devices. Don't try to bring the system
-	 * up if the reset failed for some reason.
-	 */
-	rc = eeh_reset_pe(pe);
-	if (rc)
-		return rc;
-
-	/* Restore PE */
-	eeh_ops->configure_bridge(pe);
-	eeh_pe_restore_bars(pe);
-
-	/* Give the system 5 seconds to finish running the user-space
-	 * hotplug shutdown scripts, e.g. ifdown for ethernet.  Yes, 
-	 * this is a hack, but if we don't do this, and try to bring 
-	 * the device up before the scripts have taken it down, 
-	 * potentially weird things happen.
-	 */
-	if (bus) {
-		ssleep(5);
-		pcibios_add_pci_devices(bus);
-	}
-	pe->freeze_count = cnt;
-
-	return 0;
-}
-
-/* The longest amount of time to wait for a pci device
- * to come back on line, in seconds.
- */
-#define MAX_WAIT_FOR_RECOVERY 150
-
-/**
- * eeh_handle_event - Reset a PCI device after hard lockup.
- * @pe: EEH PE
- *
- * While PHB detects address or data parity errors on particular PCI
- * slot, the associated PE will be frozen. Besides, DMA's occurring
- * to wild addresses (which usually happen due to bugs in device
- * drivers or in PCI adapter firmware) can cause EEH error. #SERR,
- * #PERR or other misc PCI-related errors also can trigger EEH errors.
- *
- * Recovery process consists of unplugging the device driver (which
- * generated hotplug events to userspace), then issuing a PCI #RST to
- * the device, then reconfiguring the PCI config space for all bridges
- * & devices under this slot, and then finally restarting the device
- * drivers (which cause a second set of hotplug events to go out to
- * userspace).
- */
-void eeh_handle_event(struct eeh_pe *pe)
-{
-	struct pci_bus *frozen_bus;
-	int rc = 0;
-	enum pci_ers_result result = PCI_ERS_RESULT_NONE;
-
-	frozen_bus = eeh_pe_bus_get(pe);
-	if (!frozen_bus) {
-		pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
-			__func__, pe->phb->global_number, pe->addr);
-		return;
-	}
-
-	pe->freeze_count++;
-	if (pe->freeze_count > EEH_MAX_ALLOWED_FREEZES)
-		goto excess_failures;
-	pr_warning("EEH: This PCI device has failed %d times in the last hour\n",
-		pe->freeze_count);
-
-	/* Walk the various device drivers attached to this slot through
-	 * a reset sequence, giving each an opportunity to do what it needs
-	 * to accomplish the reset.  Each child gets a report of the
-	 * status ... if any child can't handle the reset, then the entire
-	 * slot is dlpar removed and added.
-	 */
-	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
-
-	/* Get the current PCI slot state. This can take a long time,
-	 * sometimes over 3 seconds for certain systems.
-	 */
-	rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
-	if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
-		printk(KERN_WARNING "EEH: Permanent failure\n");
-		goto hard_fail;
-	}
-
-	/* Since rtas may enable MMIO when posting the error log,
-	 * don't post the error log until after all dev drivers
-	 * have been informed.
-	 */
-	eeh_slot_error_detail(pe, EEH_LOG_TEMP);
-
-	/* If all device drivers were EEH-unaware, then shut
-	 * down all of the device drivers, and hope they
-	 * go down willingly, without panicing the system.
-	 */
-	if (result == PCI_ERS_RESULT_NONE) {
-		rc = eeh_reset_device(pe, frozen_bus);
-		if (rc) {
-			printk(KERN_WARNING "EEH: Unable to reset, rc=%d\n", rc);
-			goto hard_fail;
-		}
-	}
-
-	/* If all devices reported they can proceed, then re-enable MMIO */
-	if (result == PCI_ERS_RESULT_CAN_RECOVER) {
-		rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
-
-		if (rc < 0)
-			goto hard_fail;
-		if (rc) {
-			result = PCI_ERS_RESULT_NEED_RESET;
-		} else {
-			result = PCI_ERS_RESULT_NONE;
-			eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result);
-		}
-	}
-
-	/* If all devices reported they can proceed, then re-enable DMA */
-	if (result == PCI_ERS_RESULT_CAN_RECOVER) {
-		rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
-
-		if (rc < 0)
-			goto hard_fail;
-		if (rc)
-			result = PCI_ERS_RESULT_NEED_RESET;
-		else
-			result = PCI_ERS_RESULT_RECOVERED;
-	}
-
-	/* If any device has a hard failure, then shut off everything. */
-	if (result == PCI_ERS_RESULT_DISCONNECT) {
-		printk(KERN_WARNING "EEH: Device driver gave up\n");
-		goto hard_fail;
-	}
-
-	/* If any device called out for a reset, then reset the slot */
-	if (result == PCI_ERS_RESULT_NEED_RESET) {
-		rc = eeh_reset_device(pe, NULL);
-		if (rc) {
-			printk(KERN_WARNING "EEH: Cannot reset, rc=%d\n", rc);
-			goto hard_fail;
-		}
-		result = PCI_ERS_RESULT_NONE;
-		eeh_pe_dev_traverse(pe, eeh_report_reset, &result);
-	}
-
-	/* All devices should claim they have recovered by now. */
-	if ((result != PCI_ERS_RESULT_RECOVERED) &&
-	    (result != PCI_ERS_RESULT_NONE)) {
-		printk(KERN_WARNING "EEH: Not recovered\n");
-		goto hard_fail;
-	}
-
-	/* Tell all device drivers that they can resume operations */
-	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
-
-	return;
-	
-excess_failures:
-	/*
-	 * About 90% of all real-life EEH failures in the field
-	 * are due to poorly seated PCI cards. Only 10% or so are
-	 * due to actual, failed cards.
-	 */
-	pr_err("EEH: PHB#%d-PE#%x has failed %d times in the\n"
-	       "last hour and has been permanently disabled.\n"
-	       "Please try reseating or replacing it.\n",
-		pe->phb->global_number, pe->addr,
-		pe->freeze_count);
-	goto perm_error;
-
-hard_fail:
-	pr_err("EEH: Unable to recover from failure from PHB#%d-PE#%x.\n"
-	       "Please try reseating or replacing it\n",
-		pe->phb->global_number, pe->addr);
-
-perm_error:
-	eeh_slot_error_detail(pe, EEH_LOG_PERM);
-
-	/* Notify all devices that they're about to go down. */
-	eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
-
-	/* Shut down the device drivers for good. */
-	if (frozen_bus)
-		pcibios_remove_pci_devices(frozen_bus);
-}
-
diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
deleted file mode 100644
index 185bedd..0000000
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ /dev/null
@@ -1,142 +0,0 @@
-/*
- * 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
- * Copyright (c) 2005 Linas Vepstas <linas@linas.org>
- */
-
-#include <linux/delay.h>
-#include <linux/list.h>
-#include <linux/mutex.h>
-#include <linux/sched.h>
-#include <linux/pci.h>
-#include <linux/slab.h>
-#include <linux/workqueue.h>
-#include <linux/kthread.h>
-#include <asm/eeh_event.h>
-#include <asm/ppc-pci.h>
-
-/** Overview:
- *  EEH error states may be detected within exception handlers;
- *  however, the recovery processing needs to occur asynchronously
- *  in a normal kernel context and not an interrupt context.
- *  This pair of routines creates an event and queues it onto a
- *  work-queue, where a worker thread can drive recovery.
- */
-
-/* EEH event workqueue setup. */
-static DEFINE_SPINLOCK(eeh_eventlist_lock);
-LIST_HEAD(eeh_eventlist);
-static void eeh_thread_launcher(struct work_struct *);
-DECLARE_WORK(eeh_event_wq, eeh_thread_launcher);
-
-/* Serialize reset sequences for a given pci device */
-DEFINE_MUTEX(eeh_event_mutex);
-
-/**
- * eeh_event_handler - Dispatch EEH events.
- * @dummy - unused
- *
- * The detection of a frozen slot can occur inside an interrupt,
- * where it can be hard to do anything about it.  The goal of this
- * routine is to pull these detection events out of the context
- * of the interrupt handler, and re-dispatch them for processing
- * at a later time in a normal context.
- */
-static int eeh_event_handler(void * dummy)
-{
-	unsigned long flags;
-	struct eeh_event *event;
-	struct eeh_pe *pe;
-
-	spin_lock_irqsave(&eeh_eventlist_lock, flags);
-	event = NULL;
-
-	/* Unqueue the event, get ready to process. */
-	if (!list_empty(&eeh_eventlist)) {
-		event = list_entry(eeh_eventlist.next, struct eeh_event, list);
-		list_del(&event->list);
-	}
-	spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
-
-	if (event == NULL)
-		return 0;
-
-	/* Serialize processing of EEH events */
-	mutex_lock(&eeh_event_mutex);
-	pe = event->pe;
-	eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
-	pr_info("EEH: Detected PCI bus error on PHB#%d-PE#%x\n",
-		pe->phb->global_number, pe->addr);
-
-	set_current_state(TASK_INTERRUPTIBLE);	/* Don't add to load average */
-	eeh_handle_event(pe);
-	eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
-
-	kfree(event);
-	mutex_unlock(&eeh_event_mutex);
-
-	/* If there are no new errors after an hour, clear the counter. */
-	if (pe && pe->freeze_count > 0) {
-		msleep_interruptible(3600*1000);
-		if (pe->freeze_count > 0)
-			pe->freeze_count--;
-
-	}
-
-	return 0;
-}
-
-/**
- * eeh_thread_launcher - Start kernel thread to handle EEH events
- * @dummy - unused
- *
- * This routine is called to start the kernel thread for processing
- * EEH event.
- */
-static void eeh_thread_launcher(struct work_struct *dummy)
-{
-	if (IS_ERR(kthread_run(eeh_event_handler, NULL, "eehd")))
-		printk(KERN_ERR "Failed to start EEH daemon\n");
-}
-
-/**
- * eeh_send_failure_event - Generate a PCI error event
- * @pe: EEH PE
- *
- * This routine can be called within an interrupt context;
- * the actual event will be delivered in a normal context
- * (from a workqueue).
- */
-int eeh_send_failure_event(struct eeh_pe *pe)
-{
-	unsigned long flags;
-	struct eeh_event *event;
-
-	event = kzalloc(sizeof(*event), GFP_ATOMIC);
-	if (!event) {
-		pr_err("EEH: out of memory, event not handled\n");
-		return -ENOMEM;
-	}
-	event->pe = pe;
-
-	/* We may or may not be called in an interrupt context */
-	spin_lock_irqsave(&eeh_eventlist_lock, flags);
-	list_add(&event->list, &eeh_eventlist);
-	spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
-
-	schedule_work(&eeh_event_wq);
-
-	return 0;
-}
diff --git a/arch/powerpc/platforms/pseries/eeh_pe.c b/arch/powerpc/platforms/pseries/eeh_pe.c
deleted file mode 100644
index 9d4a9e8..0000000
--- a/arch/powerpc/platforms/pseries/eeh_pe.c
+++ /dev/null
@@ -1,653 +0,0 @@
-/*
- * The file intends to implement PE based on the information from
- * platforms. Basically, there have 3 types of PEs: PHB/Bus/Device.
- * All the PEs should be organized as hierarchy tree. The first level
- * of the tree will be associated to existing PHBs since the particular
- * PE is only meaningful in one PHB domain.
- *
- * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#include <linux/export.h>
-#include <linux/gfp.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/string.h>
-
-#include <asm/pci-bridge.h>
-#include <asm/ppc-pci.h>
-
-static LIST_HEAD(eeh_phb_pe);
-
-/**
- * eeh_pe_alloc - Allocate PE
- * @phb: PCI controller
- * @type: PE type
- *
- * Allocate PE instance dynamically.
- */
-static struct eeh_pe *eeh_pe_alloc(struct pci_controller *phb, int type)
-{
-	struct eeh_pe *pe;
-
-	/* Allocate PHB PE */
-	pe = kzalloc(sizeof(struct eeh_pe), GFP_KERNEL);
-	if (!pe) return NULL;
-
-	/* Initialize PHB PE */
-	pe->type = type;
-	pe->phb = phb;
-	INIT_LIST_HEAD(&pe->child_list);
-	INIT_LIST_HEAD(&pe->child);
-	INIT_LIST_HEAD(&pe->edevs);
-
-	return pe;
-}
-
-/**
- * eeh_phb_pe_create - Create PHB PE
- * @phb: PCI controller
- *
- * The function should be called while the PHB is detected during
- * system boot or PCI hotplug in order to create PHB PE.
- */
-int eeh_phb_pe_create(struct pci_controller *phb)
-{
-	struct eeh_pe *pe;
-
-	/* Allocate PHB PE */
-	pe = eeh_pe_alloc(phb, EEH_PE_PHB);
-	if (!pe) {
-		pr_err("%s: out of memory!\n", __func__);
-		return -ENOMEM;
-	}
-
-	/* Put it into the list */
-	eeh_lock();
-	list_add_tail(&pe->child, &eeh_phb_pe);
-	eeh_unlock();
-
-	pr_debug("EEH: Add PE for PHB#%d\n", phb->global_number);
-
-	return 0;
-}
-
-/**
- * eeh_phb_pe_get - Retrieve PHB PE based on the given PHB
- * @phb: PCI controller
- *
- * The overall PEs form hierarchy tree. The first layer of the
- * hierarchy tree is composed of PHB PEs. The function is used
- * to retrieve the corresponding PHB PE according to the given PHB.
- */
-static struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb)
-{
-	struct eeh_pe *pe;
-
-	list_for_each_entry(pe, &eeh_phb_pe, child) {
-		/*
-		 * Actually, we needn't check the type since
-		 * the PE for PHB has been determined when that
-		 * was created.
-		 */
-		if ((pe->type & EEH_PE_PHB) && pe->phb == phb)
-			return pe;
-	}
-
-	return NULL;
-}
-
-/**
- * eeh_pe_next - Retrieve the next PE in the tree
- * @pe: current PE
- * @root: root PE
- *
- * The function is used to retrieve the next PE in the
- * hierarchy PE tree.
- */
-static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe,
-				  struct eeh_pe *root)
-{
-	struct list_head *next = pe->child_list.next;
-
-	if (next == &pe->child_list) {
-		while (1) {
-			if (pe == root)
-				return NULL;
-			next = pe->child.next;
-			if (next != &pe->parent->child_list)
-				break;
-			pe = pe->parent;
-		}
-	}
-
-	return list_entry(next, struct eeh_pe, child);
-}
-
-/**
- * eeh_pe_traverse - Traverse PEs in the specified PHB
- * @root: root PE
- * @fn: callback
- * @flag: extra parameter to callback
- *
- * The function is used to traverse the specified PE and its
- * child PEs. The traversing is to be terminated once the
- * callback returns something other than NULL, or no more PEs
- * to be traversed.
- */
-static void *eeh_pe_traverse(struct eeh_pe *root,
-			eeh_traverse_func fn, void *flag)
-{
-	struct eeh_pe *pe;
-	void *ret;
-
-	for (pe = root; pe; pe = eeh_pe_next(pe, root)) {
-		ret = fn(pe, flag);
-		if (ret) return ret;
-	}
-
-	return NULL;
-}
-
-/**
- * eeh_pe_dev_traverse - Traverse the devices from the PE
- * @root: EEH PE
- * @fn: function callback
- * @flag: extra parameter to callback
- *
- * The function is used to traverse the devices of the specified
- * PE and its child PEs.
- */
-void *eeh_pe_dev_traverse(struct eeh_pe *root,
-		eeh_traverse_func fn, void *flag)
-{
-	struct eeh_pe *pe;
-	struct eeh_dev *edev;
-	void *ret;
-
-	if (!root) {
-		pr_warning("%s: Invalid PE %p\n", __func__, root);
-		return NULL;
-	}
-
-	eeh_lock();
-
-	/* Traverse root PE */
-	for (pe = root; pe; pe = eeh_pe_next(pe, root)) {
-		eeh_pe_for_each_dev(pe, edev) {
-			ret = fn(edev, flag);
-			if (ret) {
-				eeh_unlock();
-				return ret;
-			}
-		}
-	}
-
-	eeh_unlock();
-
-	return NULL;
-}
-
-/**
- * __eeh_pe_get - Check the PE address
- * @data: EEH PE
- * @flag: EEH device
- *
- * For one particular PE, it can be identified by PE address
- * or tranditional BDF address. BDF address is composed of
- * Bus/Device/Function number. The extra data referred by flag
- * indicates which type of address should be used.
- */
-static void *__eeh_pe_get(void *data, void *flag)
-{
-	struct eeh_pe *pe = (struct eeh_pe *)data;
-	struct eeh_dev *edev = (struct eeh_dev *)flag;
-
-	/* Unexpected PHB PE */
-	if (pe->type & EEH_PE_PHB)
-		return NULL;
-
-	/* We prefer PE address */
-	if (edev->pe_config_addr &&
-	   (edev->pe_config_addr == pe->addr))
-		return pe;
-
-	/* Try BDF address */
-	if (edev->pe_config_addr &&
-	   (edev->config_addr == pe->config_addr))
-		return pe;
-
-	return NULL;
-}
-
-/**
- * eeh_pe_get - Search PE based on the given address
- * @edev: EEH device
- *
- * Search the corresponding PE based on the specified address which
- * is included in the eeh device. The function is used to check if
- * the associated PE has been created against the PE address. It's
- * notable that the PE address has 2 format: traditional PE address
- * which is composed of PCI bus/device/function number, or unified
- * PE address.
- */
-static struct eeh_pe *eeh_pe_get(struct eeh_dev *edev)
-{
-	struct eeh_pe *root = eeh_phb_pe_get(edev->phb);
-	struct eeh_pe *pe;
-
-	pe = eeh_pe_traverse(root, __eeh_pe_get, edev);
-
-	return pe;
-}
-
-/**
- * eeh_pe_get_parent - Retrieve the parent PE
- * @edev: EEH device
- *
- * The whole PEs existing in the system are organized as hierarchy
- * tree. The function is used to retrieve the parent PE according
- * to the parent EEH device.
- */
-static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev)
-{
-	struct device_node *dn;
-	struct eeh_dev *parent;
-
-	/*
-	 * It might have the case for the indirect parent
-	 * EEH device already having associated PE, but
-	 * the direct parent EEH device doesn't have yet.
-	 */
-	dn = edev->dn->parent;
-	while (dn) {
-		/* We're poking out of PCI territory */
-		if (!PCI_DN(dn)) return NULL;
-
-		parent = of_node_to_eeh_dev(dn);
-		/* We're poking out of PCI territory */
-		if (!parent) return NULL;
-
-		if (parent->pe)
-			return parent->pe;
-
-		dn = dn->parent;
-	}
-
-	return NULL;
-}
-
-/**
- * eeh_add_to_parent_pe - Add EEH device to parent PE
- * @edev: EEH device
- *
- * Add EEH device to the parent PE. If the parent PE already
- * exists, the PE type will be changed to EEH_PE_BUS. Otherwise,
- * we have to create new PE to hold the EEH device and the new
- * PE will be linked to its parent PE as well.
- */
-int eeh_add_to_parent_pe(struct eeh_dev *edev)
-{
-	struct eeh_pe *pe, *parent;
-
-	eeh_lock();
-
-	/*
-	 * Search the PE has been existing or not according
-	 * to the PE address. If that has been existing, the
-	 * PE should be composed of PCI bus and its subordinate
-	 * components.
-	 */
-	pe = eeh_pe_get(edev);
-	if (pe && !(pe->type & EEH_PE_INVALID)) {
-		if (!edev->pe_config_addr) {
-			eeh_unlock();
-			pr_err("%s: PE with addr 0x%x already exists\n",
-				__func__, edev->config_addr);
-			return -EEXIST;
-		}
-
-		/* Mark the PE as type of PCI bus */
-		pe->type = EEH_PE_BUS;
-		edev->pe = pe;
-
-		/* Put the edev to PE */
-		list_add_tail(&edev->list, &pe->edevs);
-		eeh_unlock();
-		pr_debug("EEH: Add %s to Bus PE#%x\n",
-			edev->dn->full_name, pe->addr);
-
-		return 0;
-	} else if (pe && (pe->type & EEH_PE_INVALID)) {
-		list_add_tail(&edev->list, &pe->edevs);
-		edev->pe = pe;
-		/*
-		 * We're running to here because of PCI hotplug caused by
-		 * EEH recovery. We need clear EEH_PE_INVALID until the top.
-		 */
-		parent = pe;
-		while (parent) {
-			if (!(parent->type & EEH_PE_INVALID))
-				break;
-			parent->type &= ~EEH_PE_INVALID;
-			parent = parent->parent;
-		}
-		eeh_unlock();
-		pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
-			edev->dn->full_name, pe->addr, pe->parent->addr);
-
-		return 0;
-	}
-
-	/* Create a new EEH PE */
-	pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE);
-	if (!pe) {
-		eeh_unlock();
-		pr_err("%s: out of memory!\n", __func__);
-		return -ENOMEM;
-	}
-	pe->addr	= edev->pe_config_addr;
-	pe->config_addr	= edev->config_addr;
-
-	/*
-	 * Put the new EEH PE into hierarchy tree. If the parent
-	 * can't be found, the newly created PE will be attached
-	 * to PHB directly. Otherwise, we have to associate the
-	 * PE with its parent.
-	 */
-	parent = eeh_pe_get_parent(edev);
-	if (!parent) {
-		parent = eeh_phb_pe_get(edev->phb);
-		if (!parent) {
-			eeh_unlock();
-			pr_err("%s: No PHB PE is found (PHB Domain=%d)\n",
-				__func__, edev->phb->global_number);
-			edev->pe = NULL;
-			kfree(pe);
-			return -EEXIST;
-		}
-	}
-	pe->parent = parent;
-
-	/*
-	 * Put the newly created PE into the child list and
-	 * link the EEH device accordingly.
-	 */
-	list_add_tail(&pe->child, &parent->child_list);
-	list_add_tail(&edev->list, &pe->edevs);
-	edev->pe = pe;
-	eeh_unlock();
-	pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
-		edev->dn->full_name, pe->addr, pe->parent->addr);
-
-	return 0;
-}
-
-/**
- * eeh_rmv_from_parent_pe - Remove one EEH device from the associated PE
- * @edev: EEH device
- * @purge_pe: remove PE or not
- *
- * The PE hierarchy tree might be changed when doing PCI hotplug.
- * Also, the PCI devices or buses could be removed from the system
- * during EEH recovery. So we have to call the function remove the
- * corresponding PE accordingly if necessary.
- */
-int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe)
-{
-	struct eeh_pe *pe, *parent, *child;
-	int cnt;
-
-	if (!edev->pe) {
-		pr_warning("%s: No PE found for EEH device %s\n",
-			__func__, edev->dn->full_name);
-		return -EEXIST;
-	}
-
-	eeh_lock();
-
-	/* Remove the EEH device */
-	pe = edev->pe;
-	edev->pe = NULL;
-	list_del(&edev->list);
-
-	/*
-	 * Check if the parent PE includes any EEH devices.
-	 * If not, we should delete that. Also, we should
-	 * delete the parent PE if it doesn't have associated
-	 * child PEs and EEH devices.
-	 */
-	while (1) {
-		parent = pe->parent;
-		if (pe->type & EEH_PE_PHB)
-			break;
-
-		if (purge_pe) {
-			if (list_empty(&pe->edevs) &&
-			    list_empty(&pe->child_list)) {
-				list_del(&pe->child);
-				kfree(pe);
-			} else {
-				break;
-			}
-		} else {
-			if (list_empty(&pe->edevs)) {
-				cnt = 0;
-				list_for_each_entry(child, &pe->child_list, child) {
-					if (!(child->type & EEH_PE_INVALID)) {
-						cnt++;
-						break;
-					}
-				}
-
-				if (!cnt)
-					pe->type |= EEH_PE_INVALID;
-				else
-					break;
-			}
-		}
-
-		pe = parent;
-	}
-
-	eeh_unlock();
-
-	return 0;
-}
-
-/**
- * __eeh_pe_state_mark - Mark the state for the PE
- * @data: EEH PE
- * @flag: state
- *
- * The function is used to mark the indicated state for the given
- * PE. Also, the associated PCI devices will be put into IO frozen
- * state as well.
- */
-static void *__eeh_pe_state_mark(void *data, void *flag)
-{
-	struct eeh_pe *pe = (struct eeh_pe *)data;
-	int state = *((int *)flag);
-	struct eeh_dev *tmp;
-	struct pci_dev *pdev;
-
-	/*
-	 * Mark the PE with the indicated state. Also,
-	 * the associated PCI device will be put into
-	 * I/O frozen state to avoid I/O accesses from
-	 * the PCI device driver.
-	 */
-	pe->state |= state;
-	eeh_pe_for_each_dev(pe, tmp) {
-		pdev = eeh_dev_to_pci_dev(tmp);
-		if (pdev)
-			pdev->error_state = pci_channel_io_frozen;
-	}
-
-	return NULL;
-}
-
-/**
- * eeh_pe_state_mark - Mark specified state for PE and its associated device
- * @pe: EEH PE
- *
- * EEH error affects the current PE and its child PEs. The function
- * is used to mark appropriate state for the affected PEs and the
- * associated devices.
- */
-void eeh_pe_state_mark(struct eeh_pe *pe, int state)
-{
-	eeh_lock();
-	eeh_pe_traverse(pe, __eeh_pe_state_mark, &state);
-	eeh_unlock();
-}
-
-/**
- * __eeh_pe_state_clear - Clear state for the PE
- * @data: EEH PE
- * @flag: state
- *
- * The function is used to clear the indicated state from the
- * given PE. Besides, we also clear the check count of the PE
- * as well.
- */
-static void *__eeh_pe_state_clear(void *data, void *flag)
-{
-	struct eeh_pe *pe = (struct eeh_pe *)data;
-	int state = *((int *)flag);
-
-	pe->state &= ~state;
-	pe->check_count = 0;
-
-	return NULL;
-}
-
-/**
- * eeh_pe_state_clear - Clear state for the PE and its children
- * @pe: PE
- * @state: state to be cleared
- *
- * When the PE and its children has been recovered from error,
- * we need clear the error state for that. The function is used
- * for the purpose.
- */
-void eeh_pe_state_clear(struct eeh_pe *pe, int state)
-{
-	eeh_lock();
-	eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
-	eeh_unlock();
-}
-
-/**
- * eeh_restore_one_device_bars - Restore the Base Address Registers for one device
- * @data: EEH device
- * @flag: Unused
- *
- * Loads the PCI configuration space base address registers,
- * the expansion ROM base address, the latency timer, and etc.
- * from the saved values in the device node.
- */
-static void *eeh_restore_one_device_bars(void *data, void *flag)
-{
-	int i;
-	u32 cmd;
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
-
-	for (i = 4; i < 10; i++)
-		eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
-	/* 12 == Expansion ROM Address */
-	eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]);
-
-#define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF))
-#define SAVED_BYTE(OFF) (((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
-
-	eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
-		SAVED_BYTE(PCI_CACHE_LINE_SIZE));
-	eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1,
-		SAVED_BYTE(PCI_LATENCY_TIMER));
-
-	/* max latency, min grant, interrupt pin and line */
-	eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]);
-
-	/*
-	 * Restore PERR & SERR bits, some devices require it,
-	 * don't touch the other command bits
-	 */
-	eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd);
-	if (edev->config_space[1] & PCI_COMMAND_PARITY)
-		cmd |= PCI_COMMAND_PARITY;
-	else
-		cmd &= ~PCI_COMMAND_PARITY;
-	if (edev->config_space[1] & PCI_COMMAND_SERR)
-		cmd |= PCI_COMMAND_SERR;
-	else
-		cmd &= ~PCI_COMMAND_SERR;
-	eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd);
-
-	return NULL;
-}
-
-/**
- * eeh_pe_restore_bars - Restore the PCI config space info
- * @pe: EEH PE
- *
- * This routine performs a recursive walk to the children
- * of this device as well.
- */
-void eeh_pe_restore_bars(struct eeh_pe *pe)
-{
-	/*
-	 * We needn't take the EEH lock since eeh_pe_dev_traverse()
-	 * will take that.
-	 */
-	eeh_pe_dev_traverse(pe, eeh_restore_one_device_bars, NULL);
-}
-
-/**
- * eeh_pe_bus_get - Retrieve PCI bus according to the given PE
- * @pe: EEH PE
- *
- * Retrieve the PCI bus according to the given PE. Basically,
- * there're 3 types of PEs: PHB/Bus/Device. For PHB PE, the
- * primary PCI bus will be retrieved. The parent bus will be
- * returned for BUS PE. However, we don't have associated PCI
- * bus for DEVICE PE.
- */
-struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
-{
-	struct pci_bus *bus = NULL;
-	struct eeh_dev *edev;
-	struct pci_dev *pdev;
-
-	eeh_lock();
-
-	if (pe->type & EEH_PE_PHB) {
-		bus = pe->phb->bus;
-	} else if (pe->type & EEH_PE_BUS ||
-		   pe->type & EEH_PE_DEVICE) {
-		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
-		pdev = eeh_dev_to_pci_dev(edev);
-		if (pdev)
-			bus = pdev->bus;
-	}
-
-	eeh_unlock();
-
-	return bus;
-}
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index b456b15..ccb633e 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -133,6 +133,48 @@ static int pseries_eeh_init(void)
 	return 0;
 }
 
+static int pseries_eeh_cap_start(struct device_node *dn)
+{
+	struct pci_dn *pdn = PCI_DN(dn);
+	u32 status;
+
+	if (!pdn)
+		return 0;
+
+	rtas_read_config(pdn, PCI_STATUS, 2, &status);
+	if (!(status & PCI_STATUS_CAP_LIST))
+		return 0;
+
+	return PCI_CAPABILITY_LIST;
+}
+
+
+static int pseries_eeh_find_cap(struct device_node *dn, int cap)
+{
+	struct pci_dn *pdn = PCI_DN(dn);
+	int pos = pseries_eeh_cap_start(dn);
+	int cnt = 48;	/* Maximal number of capabilities */
+	u32 id;
+
+	if (!pos)
+		return 0;
+
+        while (cnt--) {
+		rtas_read_config(pdn, pos, 1, &pos);
+		if (pos < 0x40)
+			break;
+		pos &= ~3;
+		rtas_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
+		if (id == 0xff)
+			break;
+		if (id == cap)
+			return pos;
+		pos += PCI_CAP_LIST_NEXT;
+	}
+
+	return 0;
+}
+
 /**
  * pseries_eeh_of_probe - EEH probe on the given device
  * @dn: OF node
@@ -146,30 +188,52 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 {
 	struct eeh_dev *edev;
 	struct eeh_pe pe;
-	const u32 *class_code, *vendor_id, *device_id;
-	const u32 *regs;
+	struct pci_dn *pdn = PCI_DN(dn);
+	const __be32 *classp, *vendorp, *devicep;
+	u32 class_code;
+	const __be32 *regs;
+	u32 pcie_flags;
 	int enable = 0;
 	int ret;
 
 	/* Retrieve OF node and eeh device */
 	edev = of_node_to_eeh_dev(dn);
-	if (!of_device_is_available(dn))
+	if (edev->pe || !of_device_is_available(dn))
 		return NULL;
 
 	/* Retrieve class/vendor/device IDs */
-	class_code = of_get_property(dn, "class-code", NULL);
-	vendor_id  = of_get_property(dn, "vendor-id", NULL);
-	device_id  = of_get_property(dn, "device-id", NULL);
+	classp = of_get_property(dn, "class-code", NULL);
+	vendorp = of_get_property(dn, "vendor-id", NULL);
+	devicep = of_get_property(dn, "device-id", NULL);
 
 	/* Skip for bad OF node or PCI-ISA bridge */
-	if (!class_code || !vendor_id || !device_id)
+	if (!classp || !vendorp || !devicep)
 		return NULL;
 	if (dn->type && !strcmp(dn->type, "isa"))
 		return NULL;
 
-	/* Update class code and mode of eeh device */
-	edev->class_code = *class_code;
-	edev->mode = 0;
+	class_code = of_read_number(classp, 1);
+
+	/*
+	 * Update class code and mode of eeh device. We need
+	 * correctly reflects that current device is root port
+	 * or PCIe switch downstream port.
+	 */
+	edev->class_code = class_code;
+	edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP);
+	edev->mode &= 0xFFFFFF00;
+	if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
+		edev->mode |= EEH_DEV_BRIDGE;
+		if (edev->pcie_cap) {
+			rtas_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
+					 2, &pcie_flags);
+			pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4;
+			if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT)
+				edev->mode |= EEH_DEV_ROOT_PORT;
+			else if (pcie_flags == PCI_EXP_TYPE_DOWNSTREAM)
+				edev->mode |= EEH_DEV_DS_PORT;
+		}
+	}
 
 	/* Retrieve the device address */
 	regs = of_get_property(dn, "reg", NULL);
@@ -182,12 +246,12 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 	/* Initialize the fake PE */
 	memset(&pe, 0, sizeof(struct eeh_pe));
 	pe.phb = edev->phb;
-	pe.config_addr = regs[0];
+	pe.config_addr = of_read_number(regs, 1);
 
 	/* Enable EEH on the device */
 	ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE);
 	if (!ret) {
-		edev->config_addr = regs[0];
+		edev->config_addr = of_read_number(regs, 1);
 		/* Retrieve PE address */
 		edev->pe_config_addr = eeh_ops->get_pe_addr(&pe);
 		pe.addr = edev->pe_config_addr;
diff --git a/arch/powerpc/platforms/pseries/eeh_sysfs.c b/arch/powerpc/platforms/pseries/eeh_sysfs.c
deleted file mode 100644
index d377083..0000000
--- a/arch/powerpc/platforms/pseries/eeh_sysfs.c
+++ /dev/null
@@ -1,75 +0,0 @@
-/*
- * Sysfs entries for PCI Error Recovery for PAPR-compliant platform.
- * Copyright IBM Corporation 2007
- * Copyright Linas Vepstas <linas@austin.ibm.com> 2007
- *
- * All rights reserved.
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
- */
-#include <linux/pci.h>
-#include <linux/stat.h>
-#include <asm/ppc-pci.h>
-#include <asm/pci-bridge.h>
-
-/**
- * EEH_SHOW_ATTR -- Create sysfs entry for eeh statistic
- * @_name: name of file in sysfs directory
- * @_memb: name of member in struct pci_dn to access
- * @_format: printf format for display
- *
- * All of the attributes look very similar, so just
- * auto-gen a cut-n-paste routine to display them.
- */
-#define EEH_SHOW_ATTR(_name,_memb,_format)               \
-static ssize_t eeh_show_##_name(struct device *dev,      \
-		struct device_attribute *attr, char *buf)          \
-{                                                        \
-	struct pci_dev *pdev = to_pci_dev(dev);               \
-	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);      \
-	                                                      \
-	if (!edev)                                            \
-		return 0;                                     \
-	                                                      \
-	return sprintf(buf, _format "\n", edev->_memb);       \
-}                                                        \
-static DEVICE_ATTR(_name, S_IRUGO, eeh_show_##_name, NULL);
-
-EEH_SHOW_ATTR(eeh_mode,            mode,            "0x%x");
-EEH_SHOW_ATTR(eeh_config_addr,     config_addr,     "0x%x");
-EEH_SHOW_ATTR(eeh_pe_config_addr,  pe_config_addr,  "0x%x");
-
-void eeh_sysfs_add_device(struct pci_dev *pdev)
-{
-	int rc=0;
-
-	rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode);
-	rc += device_create_file(&pdev->dev, &dev_attr_eeh_config_addr);
-	rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
-
-	if (rc)
-		printk(KERN_WARNING "EEH: Unable to create sysfs entries\n");
-}
-
-void eeh_sysfs_remove_device(struct pci_dev *pdev)
-{
-	device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
-	device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr);
-	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
-}
-
diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c
index 2605c31..18380e8 100644
--- a/arch/powerpc/platforms/pseries/event_sources.c
+++ b/arch/powerpc/platforms/pseries/event_sources.c
@@ -25,7 +25,7 @@ void request_event_sources_irqs(struct device_node *np,
 				const char *name)
 {
 	int i, index, count = 0;
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 	const u32 *opicprop;
 	unsigned int opicplen;
 	unsigned int virqs[16];
@@ -55,13 +55,11 @@ void request_event_sources_irqs(struct device_node *np,
 	/* Else use normal interrupt tree parsing */
 	else {
 		/* First try to do a proper OF tree parsing */
-		for (index = 0; of_irq_map_one(np, index, &oirq) == 0;
+		for (index = 0; of_irq_parse_one(np, index, &oirq) == 0;
 		     index++) {
 			if (count > 15)
 				break;
-			virqs[count] = irq_create_of_mapping(oirq.controller,
-							    oirq.specifier,
-							    oirq.size);
+			virqs[count] = irq_create_of_mapping(&oirq);
 			if (virqs[count] == NO_IRQ) {
 				pr_err("event-sources: Unable to allocate "
 				       "interrupt number for %s\n",
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 217ca5c..82789e7 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -30,7 +30,8 @@
 #include <asm/machdep.h>
 #include <asm/vdso_datapage.h>
 #include <asm/xics.h>
-#include "plpar_wrappers.h"
+#include <asm/plpar_wrappers.h>
+
 #include "offline_states.h"
 
 /* This version can't take the spinlock, because it never returns */
@@ -123,7 +124,7 @@ static void pseries_mach_cpu_die(void)
 		cede_latency_hint = 2;
 
 		get_lppaca()->idle = 1;
-		if (!get_lppaca()->shared_proc)
+		if (!lppaca_shared_proc(get_lppaca()))
 			get_lppaca()->donate_dedicated_cpu = 1;
 
 		while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
@@ -137,7 +138,7 @@ static void pseries_mach_cpu_die(void)
 
 		local_irq_disable();
 
-		if (!get_lppaca()->shared_proc)
+		if (!lppaca_shared_proc(get_lppaca()))
 			get_lppaca()->donate_dedicated_cpu = 0;
 		get_lppaca()->idle = 0;
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 9a432de..9590dbb 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -10,12 +10,14 @@
  */
 
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/memblock.h>
 #include <linux/vmalloc.h>
 #include <linux/memory.h>
 
 #include <asm/firmware.h>
 #include <asm/machdep.h>
+#include <asm/prom.h>
 #include <asm/sparsemem.h>
 
 static unsigned long get_memblock_size(void)
diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c
index b344f94..849b29b 100644
--- a/arch/powerpc/platforms/pseries/hvconsole.c
+++ b/arch/powerpc/platforms/pseries/hvconsole.c
@@ -28,7 +28,7 @@
 #include <linux/errno.h>
 #include <asm/hvcall.h>
 #include <asm/hvconsole.h>
-#include "plpar_wrappers.h"
+#include <asm/plpar_wrappers.h>
 
 /**
  * hvc_get_chars - retrieve characters from firmware for denoted vterm adatper
@@ -40,10 +40,16 @@
  */
 int hvc_get_chars(uint32_t vtermno, char *buf, int count)
 {
-	unsigned long got;
+	long ret;
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	unsigned long *lbuf = (unsigned long *)buf;
+
+	ret = plpar_hcall(H_GET_TERM_CHAR, retbuf, vtermno);
+	lbuf[0] = be64_to_cpu(retbuf[1]);
+	lbuf[1] = be64_to_cpu(retbuf[2]);
 
-	if (plpar_get_term_char(vtermno, &got, buf) == H_SUCCESS)
-		return got;
+	if (ret == H_SUCCESS)
+		return retbuf[0];
 
 	return 0;
 }
@@ -69,8 +75,9 @@ int hvc_put_chars(uint32_t vtermno, const char *buf, int count)
 	if (count > MAX_VIO_PUT_CHARS)
 		count = MAX_VIO_PUT_CHARS;
 
-	ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count, lbuf[0],
-				 lbuf[1]);
+	ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count,
+				 cpu_to_be64(lbuf[0]),
+				 cpu_to_be64(lbuf[1]));
 	if (ret == H_SUCCESS)
 		return count;
 	if (ret == H_BUSY)
diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c
index ef9d9d8..5ea88d1 100644
--- a/arch/powerpc/platforms/pseries/io_event_irq.c
+++ b/arch/powerpc/platforms/pseries/io_event_irq.c
@@ -115,7 +115,7 @@ static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog)
  *   by scope or event type alone. For example, Torrent ISR route change
  *   event is reported with scope 0x00 (Not Applicatable) rather than
  *   0x3B (Torrent-hub). It is better to let the clients to identify
- *   who owns the the event.
+ *   who owns the event.
  */
 
 static irqreturn_t ioei_interrupt(int irq, void *dev_id)
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 86ae364..f253361 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -48,12 +48,11 @@
 #include <asm/ppc-pci.h>
 #include <asm/udbg.h>
 #include <asm/mmzone.h>
-
-#include "plpar_wrappers.h"
+#include <asm/plpar_wrappers.h>
 
 
 static void tce_invalidate_pSeries_sw(struct iommu_table *tbl,
-				      u64 *startp, u64 *endp)
+				      __be64 *startp, __be64 *endp)
 {
 	u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index;
 	unsigned long start, end, inc;
@@ -87,7 +86,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
 			      struct dma_attrs *attrs)
 {
 	u64 proto_tce;
-	u64 *tcep, *tces;
+	__be64 *tcep, *tces;
 	u64 rpn;
 
 	proto_tce = TCE_PCI_READ; // Read allowed
@@ -95,12 +94,12 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
 	if (direction != DMA_TO_DEVICE)
 		proto_tce |= TCE_PCI_WRITE;
 
-	tces = tcep = ((u64 *)tbl->it_base) + index;
+	tces = tcep = ((__be64 *)tbl->it_base) + index;
 
 	while (npages--) {
 		/* can't move this out since we might cross MEMBLOCK boundary */
 		rpn = __pa(uaddr) >> TCE_SHIFT;
-		*tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
+		*tcep = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT);
 
 		uaddr += TCE_PAGE_SIZE;
 		tcep++;
@@ -114,9 +113,9 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
 
 static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
 {
-	u64 *tcep, *tces;
+	__be64 *tcep, *tces;
 
-	tces = tcep = ((u64 *)tbl->it_base) + index;
+	tces = tcep = ((__be64 *)tbl->it_base) + index;
 
 	while (npages--)
 		*(tcep++) = 0;
@@ -127,11 +126,11 @@ static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
 
 static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
 {
-	u64 *tcep;
+	__be64 *tcep;
 
-	tcep = ((u64 *)tbl->it_base) + index;
+	tcep = ((__be64 *)tbl->it_base) + index;
 
-	return *tcep;
+	return be64_to_cpu(*tcep);
 }
 
 static void tce_free_pSeriesLP(struct iommu_table*, long, long);
@@ -178,7 +177,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	return ret;
 }
 
-static DEFINE_PER_CPU(u64 *, tce_page);
+static DEFINE_PER_CPU(__be64 *, tce_page);
 
 static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				     long npages, unsigned long uaddr,
@@ -187,7 +186,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 {
 	u64 rc = 0;
 	u64 proto_tce;
-	u64 *tcep;
+	__be64 *tcep;
 	u64 rpn;
 	long l, limit;
 	long tcenum_start = tcenum, npages_start = npages;
@@ -207,7 +206,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	 * from iommu_alloc{,_sg}()
 	 */
 	if (!tcep) {
-		tcep = (u64 *)__get_free_page(GFP_ATOMIC);
+		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
 		/* If allocation fails, fall back to the loop implementation */
 		if (!tcep) {
 			local_irq_restore(flags);
@@ -231,7 +230,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		limit = min_t(long, npages, 4096/TCE_ENTRY_SIZE);
 
 		for (l = 0; l < limit; l++) {
-			tcep[l] = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
+			tcep[l] = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT);
 			rpn++;
 		}
 
@@ -330,16 +329,16 @@ struct direct_window {
 
 /* Dynamic DMA Window support */
 struct ddw_query_response {
-	u32 windows_available;
-	u32 largest_available_block;
-	u32 page_size;
-	u32 migration_capable;
+	__be32 windows_available;
+	__be32 largest_available_block;
+	__be32 page_size;
+	__be32 migration_capable;
 };
 
 struct ddw_create_response {
-	u32 liobn;
-	u32 addr_hi;
-	u32 addr_lo;
+	__be32 liobn;
+	__be32 addr_hi;
+	__be32 addr_lo;
 };
 
 static LIST_HEAD(direct_window_list);
@@ -393,7 +392,8 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 					unsigned long num_pfn, const void *arg)
 {
 	const struct dynamic_dma_window_prop *maprange = arg;
-	u64 *tcep, tce_size, num_tce, dma_offset, next, proto_tce, liobn;
+	u64 tce_size, num_tce, dma_offset, next, proto_tce, liobn;
+	__be64 *tcep;
 	u32 tce_shift;
 	u64 rc = 0;
 	long l, limit;
@@ -402,7 +402,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 	tcep = __get_cpu_var(tce_page);
 
 	if (!tcep) {
-		tcep = (u64 *)__get_free_page(GFP_ATOMIC);
+		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
 		if (!tcep) {
 			local_irq_enable();
 			return -ENOMEM;
@@ -436,7 +436,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 		dma_offset = next + be64_to_cpu(maprange->dma_base);
 
 		for (l = 0; l < limit; l++) {
-			tcep[l] = proto_tce | next;
+			tcep[l] = cpu_to_be64(proto_tce | next);
 			next += tce_size;
 		}
 
@@ -530,7 +530,7 @@ static void iommu_table_setparms(struct pci_controller *phb,
 static void iommu_table_setparms_lpar(struct pci_controller *phb,
 				      struct device_node *dn,
 				      struct iommu_table *tbl,
-				      const void *dma_window)
+				      const __be32 *dma_window)
 {
 	unsigned long offset, size;
 
@@ -614,6 +614,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 
 	iommu_table_setparms(pci->phb, dn, tbl);
 	pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
+	iommu_register_group(tbl, pci_domain_nr(bus), 0);
 
 	/* Divide the rest (1.75GB) among the children */
 	pci->phb->dma_window_size = 0x80000000ul;
@@ -629,7 +630,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	struct iommu_table *tbl;
 	struct device_node *dn, *pdn;
 	struct pci_dn *ppci;
-	const void *dma_window = NULL;
+	const __be32 *dma_window = NULL;
 
 	dn = pci_bus_to_OF_node(bus);
 
@@ -658,6 +659,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 				   ppci->phb->node);
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
 		ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node);
+		iommu_register_group(tbl, pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->iommu_table);
 	}
 }
@@ -684,6 +686,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 				   phb->node);
 		iommu_table_setparms(phb, dn, tbl);
 		PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node);
+		iommu_register_group(tbl, pci_domain_nr(phb->bus), 0);
 		set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table);
 		return;
 	}
@@ -778,7 +781,7 @@ static u64 find_existing_ddw(struct device_node *pdn)
 	list_for_each_entry(window, &direct_window_list, list) {
 		if (window->device == pdn) {
 			direct64 = window->prop;
-			dma_addr = direct64->dma_base;
+			dma_addr = be64_to_cpu(direct64->dma_base);
 			break;
 		}
 	}
@@ -1043,11 +1046,11 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		dev_dbg(&dev->dev, "no free dynamic windows");
 		goto out_restore_window;
 	}
-	if (query.page_size & 4) {
+	if (be32_to_cpu(query.page_size) & 4) {
 		page_shift = 24; /* 16MB */
-	} else if (query.page_size & 2) {
+	} else if (be32_to_cpu(query.page_size) & 2) {
 		page_shift = 16; /* 64kB */
-	} else if (query.page_size & 1) {
+	} else if (be32_to_cpu(query.page_size) & 1) {
 		page_shift = 12; /* 4kB */
 	} else {
 		dev_dbg(&dev->dev, "no supported direct page size in mask %x",
@@ -1057,7 +1060,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	/* verify the window * number of ptes will map the partition */
 	/* check largest block * page size > max memory hotplug addr */
 	max_addr = memory_hotplug_max();
-	if (query.largest_available_block < (max_addr >> page_shift)) {
+	if (be32_to_cpu(query.largest_available_block) < (max_addr >> page_shift)) {
 		dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u "
 			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
 			  1ULL << page_shift);
@@ -1083,7 +1086,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	if (ret != 0)
 		goto out_free_prop;
 
-	ddwprop->liobn = cpu_to_be32(create.liobn);
+	ddwprop->liobn = create.liobn;
 	ddwprop->dma_base = cpu_to_be64(of_read_number(&create.addr_hi, 2));
 	ddwprop->tce_shift = cpu_to_be32(page_shift);
 	ddwprop->window_shift = cpu_to_be32(len);
@@ -1149,7 +1152,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 {
 	struct device_node *pdn, *dn;
 	struct iommu_table *tbl;
-	const void *dma_window = NULL;
+	const __be32 *dma_window = NULL;
 	struct pci_dn *pci;
 
 	pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev));
@@ -1184,6 +1187,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 				   pci->phb->node);
 		iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
 		pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
+		iommu_register_group(tbl, pci_domain_nr(pci->phb->bus), 0);
 		pr_debug("  created table: %p\n", pci->iommu_table);
 	} else {
 		pr_debug("  found DMA window, table: %p\n", pci->iommu_table);
@@ -1197,7 +1201,7 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
 	bool ddw_enabled = false;
 	struct device_node *pdn, *dn;
 	struct pci_dev *pdev;
-	const void *dma_window = NULL;
+	const __be32 *dma_window = NULL;
 	u64 dma_offset;
 
 	if (!dev->dma_mask)
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index 7d94bdc..13fa95b3 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -17,9 +17,9 @@
 #include <asm/mpic.h>
 #include <asm/xics.h>
 #include <asm/smp.h>
+#include <asm/plpar_wrappers.h>
 
 #include "pseries.h"
-#include "plpar_wrappers.h"
 
 static void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 {
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 6d62072..4fca3de 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -41,10 +41,17 @@
 #include <asm/smp.h>
 #include <asm/trace.h>
 #include <asm/firmware.h>
+#include <asm/plpar_wrappers.h>
 
-#include "plpar_wrappers.h"
 #include "pseries.h"
 
+/* Flag bits for H_BULK_REMOVE */
+#define HBR_REQUEST	0x4000000000000000UL
+#define HBR_RESPONSE	0x8000000000000000UL
+#define HBR_END		0xc000000000000000UL
+#define HBR_AVPN	0x0200000000000000UL
+#define HBR_ANDCOND	0x0100000000000000UL
+
 
 /* in hvCall.S */
 EXPORT_SYMBOL(plpar_hcall);
@@ -61,9 +68,18 @@ void vpa_init(int cpu)
 	struct paca_struct *pp;
 	struct dtl_entry *dtl;
 
+	/*
+	 * The spec says it "may be problematic" if CPU x registers the VPA of
+	 * CPU y. We should never do that, but wail if we ever do.
+	 */
+	WARN_ON(cpu != smp_processor_id());
+
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		lppaca_of(cpu).vmxregs_in_use = 1;
 
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		lppaca_of(cpu).ebb_regs_in_use = 1;
+
 	addr = __pa(&lppaca_of(cpu));
 	ret = register_vpa(hwcpu, addr);
 
@@ -96,7 +112,7 @@ void vpa_init(int cpu)
 		lppaca_of(cpu).dtl_idx = 0;
 
 		/* hypervisor reads buffer length from this field */
-		dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
+		dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
 		ret = register_dtl(hwcpu, __pa(dtl));
 		if (ret)
 			pr_err("WARNING: DTL registration of cpu %d (hw %d) "
@@ -136,7 +152,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 	flags = 0;
 
 	/* Make pHyp happy */
-	if ((rflags & _PAGE_NO_CACHE) & !(rflags & _PAGE_WRITETHRU))
+	if ((rflags & _PAGE_NO_CACHE) && !(rflags & _PAGE_WRITETHRU))
 		hpte_r &= ~_PAGE_COHERENT;
 	if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N))
 		flags |= H_COALESCE_CAND;
@@ -229,6 +245,23 @@ static void pSeries_lpar_hptab_clear(void)
 					&(ptes[j].pteh), &(ptes[j].ptel));
 		}
 	}
+
+#ifdef __LITTLE_ENDIAN__
+	/* Reset exceptions to big endian */
+	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
+		long rc;
+
+		rc = pseries_big_endian_exceptions();
+		/*
+		 * At this point it is unlikely panic() will get anything
+		 * out to the user, but at least this will stop us from
+		 * continuing on further and creating an even more
+		 * difficult to debug situation.
+		 */
+		if (rc)
+			panic("Could not enable big endian exceptions");
+	}
+#endif
 }
 
 /*
@@ -240,7 +273,8 @@ static void pSeries_lpar_hptab_clear(void)
 static long pSeries_lpar_hpte_updatepp(unsigned long slot,
 				       unsigned long newpp,
 				       unsigned long vpn,
-				       int psize, int ssize, int local)
+				       int psize, int apsize,
+				       int ssize, int local)
 {
 	unsigned long lpar_rc;
 	unsigned long flags = (newpp & 7) | H_AVPN;
@@ -328,7 +362,8 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
 }
 
 static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
-					 int psize, int ssize, int local)
+					 int psize, int apsize,
+					 int ssize, int local)
 {
 	unsigned long want_v;
 	unsigned long lpar_rc;
@@ -345,6 +380,113 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	BUG_ON(lpar_rc != H_SUCCESS);
 }
 
+/*
+ * Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need
+ * to make sure that we avoid bouncing the hypervisor tlbie lock.
+ */
+#define PPC64_HUGE_HPTE_BATCH 12
+
+static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
+					     unsigned long *vpn, int count,
+					     int psize, int ssize)
+{
+	unsigned long param[8];
+	int i = 0, pix = 0, rc;
+	unsigned long flags = 0;
+	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+
+	if (lock_tlbie)
+		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
+
+	for (i = 0; i < count; i++) {
+
+		if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
+			pSeries_lpar_hpte_invalidate(slot[i], vpn[i], psize, 0,
+						     ssize, 0);
+		} else {
+			param[pix] = HBR_REQUEST | HBR_AVPN | slot[i];
+			param[pix+1] = hpte_encode_avpn(vpn[i], psize, ssize);
+			pix += 2;
+			if (pix == 8) {
+				rc = plpar_hcall9(H_BULK_REMOVE, param,
+						  param[0], param[1], param[2],
+						  param[3], param[4], param[5],
+						  param[6], param[7]);
+				BUG_ON(rc != H_SUCCESS);
+				pix = 0;
+			}
+		}
+	}
+	if (pix) {
+		param[pix] = HBR_END;
+		rc = plpar_hcall9(H_BULK_REMOVE, param, param[0], param[1],
+				  param[2], param[3], param[4], param[5],
+				  param[6], param[7]);
+		BUG_ON(rc != H_SUCCESS);
+	}
+
+	if (lock_tlbie)
+		spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
+}
+
+static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm,
+				       unsigned char *hpte_slot_array,
+				       unsigned long addr, int psize)
+{
+	int ssize = 0, i, index = 0;
+	unsigned long s_addr = addr;
+	unsigned int max_hpte_count, valid;
+	unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH];
+	unsigned long slot_array[PPC64_HUGE_HPTE_BATCH];
+	unsigned long shift, hidx, vpn = 0, vsid, hash, slot;
+
+	shift = mmu_psize_defs[psize].shift;
+	max_hpte_count = 1U << (PMD_SHIFT - shift);
+
+	for (i = 0; i < max_hpte_count; i++) {
+		valid = hpte_valid(hpte_slot_array, i);
+		if (!valid)
+			continue;
+		hidx =  hpte_hash_index(hpte_slot_array, i);
+
+		/* get the vpn */
+		addr = s_addr + (i * (1ul << shift));
+		if (!is_kernel_addr(addr)) {
+			ssize = user_segment_size(addr);
+			vsid = get_vsid(mm->context.id, addr, ssize);
+			WARN_ON(vsid == 0);
+		} else {
+			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+			ssize = mmu_kernel_ssize;
+		}
+
+		vpn = hpt_vpn(addr, vsid, ssize);
+		hash = hpt_hash(vpn, shift, ssize);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+
+		slot_array[index] = slot;
+		vpn_array[index] = vpn;
+		if (index == PPC64_HUGE_HPTE_BATCH - 1) {
+			/*
+			 * Now do a bluk invalidate
+			 */
+			__pSeries_lpar_hugepage_invalidate(slot_array,
+							   vpn_array,
+							   PPC64_HUGE_HPTE_BATCH,
+							   psize, ssize);
+			index = 0;
+		} else
+			index++;
+	}
+	if (index)
+		__pSeries_lpar_hugepage_invalidate(slot_array, vpn_array,
+						   index, psize, ssize);
+}
+
 static void pSeries_lpar_hpte_removebolted(unsigned long ea,
 					   int psize, int ssize)
 {
@@ -356,17 +498,12 @@ static void pSeries_lpar_hpte_removebolted(unsigned long ea,
 
 	slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
 	BUG_ON(slot == -1);
-
-	pSeries_lpar_hpte_invalidate(slot, vpn, psize, ssize, 0);
+	/*
+	 * lpar doesn't use the passed actual page size
+	 */
+	pSeries_lpar_hpte_invalidate(slot, vpn, psize, 0, ssize, 0);
 }
 
-/* Flag bits for H_BULK_REMOVE */
-#define HBR_REQUEST	0x4000000000000000UL
-#define HBR_RESPONSE	0x8000000000000000UL
-#define HBR_END		0xc000000000000000UL
-#define HBR_AVPN	0x0200000000000000UL
-#define HBR_ANDCOND	0x0100000000000000UL
-
 /*
  * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
  * lock.
@@ -400,8 +537,11 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
 			slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 			slot += hidx & _PTEIDX_GROUP_IX;
 			if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
+				/*
+				 * lpar doesn't use the passed actual page size
+				 */
 				pSeries_lpar_hpte_invalidate(slot, vpn, psize,
-							     ssize, local);
+							     0, ssize, local);
 			} else {
 				param[pix] = HBR_REQUEST | HBR_AVPN | slot;
 				param[pix+1] = hpte_encode_avpn(vpn, psize,
@@ -452,6 +592,7 @@ void __init hpte_init_lpar(void)
 	ppc_md.hpte_removebolted = pSeries_lpar_hpte_removebolted;
 	ppc_md.flush_hash_range	= pSeries_lpar_flush_hash_range;
 	ppc_md.hpte_clear_all   = pSeries_lpar_hptab_clear;
+	ppc_md.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
 }
 
 #ifdef CONFIG_PPC_SMLPAR
@@ -606,7 +747,7 @@ int h_get_mpp(struct hvcall_mpp_data *mpp_data)
 
 	mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff;
 	mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff;
-	mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffff;
+	mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffffUL;
 
 	mpp_data->pool_size = retbuf[4];
 	mpp_data->loan_request = retbuf[5];
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
new file mode 100644
index 0000000..e738007
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -0,0 +1,710 @@
+/*
+ * PowerPC64 LPAR Configuration Information Driver
+ *
+ * Dave Engebretsen engebret@us.ibm.com
+ *    Copyright (c) 2003 Dave Engebretsen
+ * Will Schmidt willschm@us.ibm.com
+ *    SPLPAR updates, Copyright (c) 2003 Will Schmidt IBM Corporation.
+ *    seq_file updates, Copyright (c) 2004 Will Schmidt IBM Corporation.
+ * Nathan Lynch nathanl@austin.ibm.com
+ *    Added lparcfg_write, Copyright (C) 2004 Nathan Lynch 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.
+ *
+ * This driver creates a proc file at /proc/ppc64/lparcfg which contains
+ * keyword - value pairs that specify the configuration of the partition.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <asm/uaccess.h>
+#include <asm/lppaca.h>
+#include <asm/hvcall.h>
+#include <asm/firmware.h>
+#include <asm/rtas.h>
+#include <asm/time.h>
+#include <asm/prom.h>
+#include <asm/vdso_datapage.h>
+#include <asm/vio.h>
+#include <asm/mmu.h>
+#include <asm/machdep.h>
+
+
+/*
+ * This isn't a module but we expose that to userspace
+ * via /proc so leave the definitions here
+ */
+#define MODULE_VERS "1.9"
+#define MODULE_NAME "lparcfg"
+
+/* #define LPARCFG_DEBUG */
+
+/*
+ * Track sum of all purrs across all processors. This is used to further
+ * calculate usage values by different applications
+ */
+static unsigned long get_purr(void)
+{
+	unsigned long sum_purr = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct cpu_usage *cu;
+
+		cu = &per_cpu(cpu_usage_array, cpu);
+		sum_purr += cu->current_tb;
+	}
+	return sum_purr;
+}
+
+/*
+ * Methods used to fetch LPAR data when running on a pSeries platform.
+ */
+
+struct hvcall_ppp_data {
+	u64	entitlement;
+	u64	unallocated_entitlement;
+	u16	group_num;
+	u16	pool_num;
+	u8	capped;
+	u8	weight;
+	u8	unallocated_weight;
+	u16	active_procs_in_pool;
+	u16	active_system_procs;
+	u16	phys_platform_procs;
+	u32	max_proc_cap_avail;
+	u32	entitled_proc_cap_avail;
+};
+
+/*
+ * H_GET_PPP hcall returns info in 4 parms.
+ *  entitled_capacity,unallocated_capacity,
+ *  aggregation, resource_capability).
+ *
+ *  R4 = Entitled Processor Capacity Percentage.
+ *  R5 = Unallocated Processor Capacity Percentage.
+ *  R6 (AABBCCDDEEFFGGHH).
+ *      XXXX - reserved (0)
+ *          XXXX - reserved (0)
+ *              XXXX - Group Number
+ *                  XXXX - Pool Number.
+ *  R7 (IIJJKKLLMMNNOOPP).
+ *      XX - reserved. (0)
+ *        XX - bit 0-6 reserved (0).   bit 7 is Capped indicator.
+ *          XX - variable processor Capacity Weight
+ *            XX - Unallocated Variable Processor Capacity Weight.
+ *              XXXX - Active processors in Physical Processor Pool.
+ *                  XXXX  - Processors active on platform.
+ *  R8 (QQQQRRRRRRSSSSSS). if ibm,partition-performance-parameters-level >= 1
+ *	XXXX - Physical platform procs allocated to virtualization.
+ *	    XXXXXX - Max procs capacity % available to the partitions pool.
+ *	          XXXXXX - Entitled procs capacity % available to the
+ *			   partitions pool.
+ */
+static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data)
+{
+	unsigned long rc;
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+	rc = plpar_hcall9(H_GET_PPP, retbuf);
+
+	ppp_data->entitlement = retbuf[0];
+	ppp_data->unallocated_entitlement = retbuf[1];
+
+	ppp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff;
+	ppp_data->pool_num = retbuf[2] & 0xffff;
+
+	ppp_data->capped = (retbuf[3] >> 6 * 8) & 0x01;
+	ppp_data->weight = (retbuf[3] >> 5 * 8) & 0xff;
+	ppp_data->unallocated_weight = (retbuf[3] >> 4 * 8) & 0xff;
+	ppp_data->active_procs_in_pool = (retbuf[3] >> 2 * 8) & 0xffff;
+	ppp_data->active_system_procs = retbuf[3] & 0xffff;
+
+	ppp_data->phys_platform_procs = retbuf[4] >> 6 * 8;
+	ppp_data->max_proc_cap_avail = (retbuf[4] >> 3 * 8) & 0xffffff;
+	ppp_data->entitled_proc_cap_avail = retbuf[4] & 0xffffff;
+
+	return rc;
+}
+
+static unsigned h_pic(unsigned long *pool_idle_time,
+		      unsigned long *num_procs)
+{
+	unsigned long rc;
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+	rc = plpar_hcall(H_PIC, retbuf);
+
+	*pool_idle_time = retbuf[0];
+	*num_procs = retbuf[1];
+
+	return rc;
+}
+
+/*
+ * parse_ppp_data
+ * Parse out the data returned from h_get_ppp and h_pic
+ */
+static void parse_ppp_data(struct seq_file *m)
+{
+	struct hvcall_ppp_data ppp_data;
+	struct device_node *root;
+	const int *perf_level;
+	int rc;
+
+	rc = h_get_ppp(&ppp_data);
+	if (rc)
+		return;
+
+	seq_printf(m, "partition_entitled_capacity=%lld\n",
+	           ppp_data.entitlement);
+	seq_printf(m, "group=%d\n", ppp_data.group_num);
+	seq_printf(m, "system_active_processors=%d\n",
+	           ppp_data.active_system_procs);
+
+	/* pool related entries are appropriate for shared configs */
+	if (lppaca_shared_proc(get_lppaca())) {
+		unsigned long pool_idle_time, pool_procs;
+
+		seq_printf(m, "pool=%d\n", ppp_data.pool_num);
+
+		/* report pool_capacity in percentage */
+		seq_printf(m, "pool_capacity=%d\n",
+			   ppp_data.active_procs_in_pool * 100);
+
+		h_pic(&pool_idle_time, &pool_procs);
+		seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time);
+		seq_printf(m, "pool_num_procs=%ld\n", pool_procs);
+	}
+
+	seq_printf(m, "unallocated_capacity_weight=%d\n",
+		   ppp_data.unallocated_weight);
+	seq_printf(m, "capacity_weight=%d\n", ppp_data.weight);
+	seq_printf(m, "capped=%d\n", ppp_data.capped);
+	seq_printf(m, "unallocated_capacity=%lld\n",
+		   ppp_data.unallocated_entitlement);
+
+	/* The last bits of information returned from h_get_ppp are only
+	 * valid if the ibm,partition-performance-parameters-level
+	 * property is >= 1.
+	 */
+	root = of_find_node_by_path("/");
+	if (root) {
+		perf_level = of_get_property(root,
+				"ibm,partition-performance-parameters-level",
+					     NULL);
+		if (perf_level && (*perf_level >= 1)) {
+			seq_printf(m,
+			    "physical_procs_allocated_to_virtualization=%d\n",
+				   ppp_data.phys_platform_procs);
+			seq_printf(m, "max_proc_capacity_available=%d\n",
+				   ppp_data.max_proc_cap_avail);
+			seq_printf(m, "entitled_proc_capacity_available=%d\n",
+				   ppp_data.entitled_proc_cap_avail);
+		}
+
+		of_node_put(root);
+	}
+}
+
+/**
+ * parse_mpp_data
+ * Parse out data returned from h_get_mpp
+ */
+static void parse_mpp_data(struct seq_file *m)
+{
+	struct hvcall_mpp_data mpp_data;
+	int rc;
+
+	rc = h_get_mpp(&mpp_data);
+	if (rc)
+		return;
+
+	seq_printf(m, "entitled_memory=%ld\n", mpp_data.entitled_mem);
+
+	if (mpp_data.mapped_mem != -1)
+		seq_printf(m, "mapped_entitled_memory=%ld\n",
+		           mpp_data.mapped_mem);
+
+	seq_printf(m, "entitled_memory_group_number=%d\n", mpp_data.group_num);
+	seq_printf(m, "entitled_memory_pool_number=%d\n", mpp_data.pool_num);
+
+	seq_printf(m, "entitled_memory_weight=%d\n", mpp_data.mem_weight);
+	seq_printf(m, "unallocated_entitled_memory_weight=%d\n",
+	           mpp_data.unallocated_mem_weight);
+	seq_printf(m, "unallocated_io_mapping_entitlement=%ld\n",
+	           mpp_data.unallocated_entitlement);
+
+	if (mpp_data.pool_size != -1)
+		seq_printf(m, "entitled_memory_pool_size=%ld bytes\n",
+		           mpp_data.pool_size);
+
+	seq_printf(m, "entitled_memory_loan_request=%ld\n",
+	           mpp_data.loan_request);
+
+	seq_printf(m, "backing_memory=%ld bytes\n", mpp_data.backing_mem);
+}
+
+/**
+ * parse_mpp_x_data
+ * Parse out data returned from h_get_mpp_x
+ */
+static void parse_mpp_x_data(struct seq_file *m)
+{
+	struct hvcall_mpp_x_data mpp_x_data;
+
+	if (!firmware_has_feature(FW_FEATURE_XCMO))
+		return;
+	if (h_get_mpp_x(&mpp_x_data))
+		return;
+
+	seq_printf(m, "coalesced_bytes=%ld\n", mpp_x_data.coalesced_bytes);
+
+	if (mpp_x_data.pool_coalesced_bytes)
+		seq_printf(m, "pool_coalesced_bytes=%ld\n",
+			   mpp_x_data.pool_coalesced_bytes);
+	if (mpp_x_data.pool_purr_cycles)
+		seq_printf(m, "coalesce_pool_purr=%ld\n", mpp_x_data.pool_purr_cycles);
+	if (mpp_x_data.pool_spurr_cycles)
+		seq_printf(m, "coalesce_pool_spurr=%ld\n", mpp_x_data.pool_spurr_cycles);
+}
+
+#define SPLPAR_CHARACTERISTICS_TOKEN 20
+#define SPLPAR_MAXLENGTH 1026*(sizeof(char))
+
+/*
+ * parse_system_parameter_string()
+ * Retrieve the potential_processors, max_entitled_capacity and friends
+ * through the get-system-parameter rtas call.  Replace keyword strings as
+ * necessary.
+ */
+static void parse_system_parameter_string(struct seq_file *m)
+{
+	int call_status;
+
+	unsigned char *local_buffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
+	if (!local_buffer) {
+		printk(KERN_ERR "%s %s kmalloc failure at line %d\n",
+		       __FILE__, __func__, __LINE__);
+		return;
+	}
+
+	spin_lock(&rtas_data_buf_lock);
+	memset(rtas_data_buf, 0, SPLPAR_MAXLENGTH);
+	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+				NULL,
+				SPLPAR_CHARACTERISTICS_TOKEN,
+				__pa(rtas_data_buf),
+				RTAS_DATA_BUF_SIZE);
+	memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH);
+	local_buffer[SPLPAR_MAXLENGTH - 1] = '\0';
+	spin_unlock(&rtas_data_buf_lock);
+
+	if (call_status != 0) {
+		printk(KERN_INFO
+		       "%s %s Error calling get-system-parameter (0x%x)\n",
+		       __FILE__, __func__, call_status);
+	} else {
+		int splpar_strlen;
+		int idx, w_idx;
+		char *workbuffer = kzalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
+		if (!workbuffer) {
+			printk(KERN_ERR "%s %s kmalloc failure at line %d\n",
+			       __FILE__, __func__, __LINE__);
+			kfree(local_buffer);
+			return;
+		}
+#ifdef LPARCFG_DEBUG
+		printk(KERN_INFO "success calling get-system-parameter\n");
+#endif
+		splpar_strlen = local_buffer[0] * 256 + local_buffer[1];
+		local_buffer += 2;	/* step over strlen value */
+
+		w_idx = 0;
+		idx = 0;
+		while ((*local_buffer) && (idx < splpar_strlen)) {
+			workbuffer[w_idx++] = local_buffer[idx++];
+			if ((local_buffer[idx] == ',')
+			    || (local_buffer[idx] == '\0')) {
+				workbuffer[w_idx] = '\0';
+				if (w_idx) {
+					/* avoid the empty string */
+					seq_printf(m, "%s\n", workbuffer);
+				}
+				memset(workbuffer, 0, SPLPAR_MAXLENGTH);
+				idx++;	/* skip the comma */
+				w_idx = 0;
+			} else if (local_buffer[idx] == '=') {
+				/* code here to replace workbuffer contents
+				   with different keyword strings */
+				if (0 == strcmp(workbuffer, "MaxEntCap")) {
+					strcpy(workbuffer,
+					       "partition_max_entitled_capacity");
+					w_idx = strlen(workbuffer);
+				}
+				if (0 == strcmp(workbuffer, "MaxPlatProcs")) {
+					strcpy(workbuffer,
+					       "system_potential_processors");
+					w_idx = strlen(workbuffer);
+				}
+			}
+		}
+		kfree(workbuffer);
+		local_buffer -= 2;	/* back up over strlen value */
+	}
+	kfree(local_buffer);
+}
+
+/* Return the number of processors in the system.
+ * This function reads through the device tree and counts
+ * the virtual processors, this does not include threads.
+ */
+static int lparcfg_count_active_processors(void)
+{
+	struct device_node *cpus_dn = NULL;
+	int count = 0;
+
+	while ((cpus_dn = of_find_node_by_type(cpus_dn, "cpu"))) {
+#ifdef LPARCFG_DEBUG
+		printk(KERN_ERR "cpus_dn %p\n", cpus_dn);
+#endif
+		count++;
+	}
+	return count;
+}
+
+static void pseries_cmo_data(struct seq_file *m)
+{
+	int cpu;
+	unsigned long cmo_faults = 0;
+	unsigned long cmo_fault_time = 0;
+
+	seq_printf(m, "cmo_enabled=%d\n", firmware_has_feature(FW_FEATURE_CMO));
+
+	if (!firmware_has_feature(FW_FEATURE_CMO))
+		return;
+
+	for_each_possible_cpu(cpu) {
+		cmo_faults += be64_to_cpu(lppaca_of(cpu).cmo_faults);
+		cmo_fault_time += be64_to_cpu(lppaca_of(cpu).cmo_fault_time);
+	}
+
+	seq_printf(m, "cmo_faults=%lu\n", cmo_faults);
+	seq_printf(m, "cmo_fault_time_usec=%lu\n",
+		   cmo_fault_time / tb_ticks_per_usec);
+	seq_printf(m, "cmo_primary_psp=%d\n", cmo_get_primary_psp());
+	seq_printf(m, "cmo_secondary_psp=%d\n", cmo_get_secondary_psp());
+	seq_printf(m, "cmo_page_size=%lu\n", cmo_get_page_size());
+}
+
+static void splpar_dispatch_data(struct seq_file *m)
+{
+	int cpu;
+	unsigned long dispatches = 0;
+	unsigned long dispatch_dispersions = 0;
+
+	for_each_possible_cpu(cpu) {
+		dispatches += be32_to_cpu(lppaca_of(cpu).yield_count);
+		dispatch_dispersions +=
+			be32_to_cpu(lppaca_of(cpu).dispersion_count);
+	}
+
+	seq_printf(m, "dispatches=%lu\n", dispatches);
+	seq_printf(m, "dispatch_dispersions=%lu\n", dispatch_dispersions);
+}
+
+static void parse_em_data(struct seq_file *m)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+	if (firmware_has_feature(FW_FEATURE_LPAR) &&
+	    plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
+		seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]);
+}
+
+static int pseries_lparcfg_data(struct seq_file *m, void *v)
+{
+	int partition_potential_processors;
+	int partition_active_processors;
+	struct device_node *rtas_node;
+	const int *lrdrp = NULL;
+
+	rtas_node = of_find_node_by_path("/rtas");
+	if (rtas_node)
+		lrdrp = of_get_property(rtas_node, "ibm,lrdr-capacity", NULL);
+
+	if (lrdrp == NULL) {
+		partition_potential_processors = vdso_data->processorCount;
+	} else {
+		partition_potential_processors = *(lrdrp + 4);
+	}
+	of_node_put(rtas_node);
+
+	partition_active_processors = lparcfg_count_active_processors();
+
+	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		/* this call handles the ibm,get-system-parameter contents */
+		parse_system_parameter_string(m);
+		parse_ppp_data(m);
+		parse_mpp_data(m);
+		parse_mpp_x_data(m);
+		pseries_cmo_data(m);
+		splpar_dispatch_data(m);
+
+		seq_printf(m, "purr=%ld\n", get_purr());
+	} else {		/* non SPLPAR case */
+
+		seq_printf(m, "system_active_processors=%d\n",
+			   partition_potential_processors);
+
+		seq_printf(m, "system_potential_processors=%d\n",
+			   partition_potential_processors);
+
+		seq_printf(m, "partition_max_entitled_capacity=%d\n",
+			   partition_potential_processors * 100);
+
+		seq_printf(m, "partition_entitled_capacity=%d\n",
+			   partition_active_processors * 100);
+	}
+
+	seq_printf(m, "partition_active_processors=%d\n",
+		   partition_active_processors);
+
+	seq_printf(m, "partition_potential_processors=%d\n",
+		   partition_potential_processors);
+
+	seq_printf(m, "shared_processor_mode=%d\n",
+		   lppaca_shared_proc(get_lppaca()));
+
+	seq_printf(m, "slb_size=%d\n", mmu_slb_size);
+
+	parse_em_data(m);
+
+	return 0;
+}
+
+static ssize_t update_ppp(u64 *entitlement, u8 *weight)
+{
+	struct hvcall_ppp_data ppp_data;
+	u8 new_weight;
+	u64 new_entitled;
+	ssize_t retval;
+
+	/* Get our current parameters */
+	retval = h_get_ppp(&ppp_data);
+	if (retval)
+		return retval;
+
+	if (entitlement) {
+		new_weight = ppp_data.weight;
+		new_entitled = *entitlement;
+	} else if (weight) {
+		new_weight = *weight;
+		new_entitled = ppp_data.entitlement;
+	} else
+		return -EINVAL;
+
+	pr_debug("%s: current_entitled = %llu, current_weight = %u\n",
+		 __func__, ppp_data.entitlement, ppp_data.weight);
+
+	pr_debug("%s: new_entitled = %llu, new_weight = %u\n",
+		 __func__, new_entitled, new_weight);
+
+	retval = plpar_hcall_norets(H_SET_PPP, new_entitled, new_weight);
+	return retval;
+}
+
+/**
+ * update_mpp
+ *
+ * Update the memory entitlement and weight for the partition.  Caller must
+ * specify either a new entitlement or weight, not both, to be updated
+ * since the h_set_mpp call takes both entitlement and weight as parameters.
+ */
+static ssize_t update_mpp(u64 *entitlement, u8 *weight)
+{
+	struct hvcall_mpp_data mpp_data;
+	u64 new_entitled;
+	u8 new_weight;
+	ssize_t rc;
+
+	if (entitlement) {
+		/* Check with vio to ensure the new memory entitlement
+		 * can be handled.
+		 */
+		rc = vio_cmo_entitlement_update(*entitlement);
+		if (rc)
+			return rc;
+	}
+
+	rc = h_get_mpp(&mpp_data);
+	if (rc)
+		return rc;
+
+	if (entitlement) {
+		new_weight = mpp_data.mem_weight;
+		new_entitled = *entitlement;
+	} else if (weight) {
+		new_weight = *weight;
+		new_entitled = mpp_data.entitled_mem;
+	} else
+		return -EINVAL;
+
+	pr_debug("%s: current_entitled = %lu, current_weight = %u\n",
+	         __func__, mpp_data.entitled_mem, mpp_data.mem_weight);
+
+	pr_debug("%s: new_entitled = %llu, new_weight = %u\n",
+		 __func__, new_entitled, new_weight);
+
+	rc = plpar_hcall_norets(H_SET_MPP, new_entitled, new_weight);
+	return rc;
+}
+
+/*
+ * Interface for changing system parameters (variable capacity weight
+ * and entitled capacity).  Format of input is "param_name=value";
+ * anything after value is ignored.  Valid parameters at this time are
+ * "partition_entitled_capacity" and "capacity_weight".  We use
+ * H_SET_PPP to alter parameters.
+ *
+ * This function should be invoked only on systems with
+ * FW_FEATURE_SPLPAR.
+ */
+static ssize_t lparcfg_write(struct file *file, const char __user * buf,
+			     size_t count, loff_t * off)
+{
+	int kbuf_sz = 64;
+	char kbuf[kbuf_sz];
+	char *tmp;
+	u64 new_entitled, *new_entitled_ptr = &new_entitled;
+	u8 new_weight, *new_weight_ptr = &new_weight;
+	ssize_t retval;
+
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+		return -EINVAL;
+
+	if (count > kbuf_sz)
+		return -EINVAL;
+
+	if (copy_from_user(kbuf, buf, count))
+		return -EFAULT;
+
+	kbuf[count - 1] = '\0';
+	tmp = strchr(kbuf, '=');
+	if (!tmp)
+		return -EINVAL;
+
+	*tmp++ = '\0';
+
+	if (!strcmp(kbuf, "partition_entitled_capacity")) {
+		char *endp;
+		*new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10);
+		if (endp == tmp)
+			return -EINVAL;
+
+		retval = update_ppp(new_entitled_ptr, NULL);
+	} else if (!strcmp(kbuf, "capacity_weight")) {
+		char *endp;
+		*new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);
+		if (endp == tmp)
+			return -EINVAL;
+
+		retval = update_ppp(NULL, new_weight_ptr);
+	} else if (!strcmp(kbuf, "entitled_memory")) {
+		char *endp;
+		*new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10);
+		if (endp == tmp)
+			return -EINVAL;
+
+		retval = update_mpp(new_entitled_ptr, NULL);
+	} else if (!strcmp(kbuf, "entitled_memory_weight")) {
+		char *endp;
+		*new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);
+		if (endp == tmp)
+			return -EINVAL;
+
+		retval = update_mpp(NULL, new_weight_ptr);
+	} else
+		return -EINVAL;
+
+	if (retval == H_SUCCESS || retval == H_CONSTRAINED) {
+		retval = count;
+	} else if (retval == H_BUSY) {
+		retval = -EBUSY;
+	} else if (retval == H_HARDWARE) {
+		retval = -EIO;
+	} else if (retval == H_PARAMETER) {
+		retval = -EINVAL;
+	}
+
+	return retval;
+}
+
+static int lparcfg_data(struct seq_file *m, void *v)
+{
+	struct device_node *rootdn;
+	const char *model = "";
+	const char *system_id = "";
+	const char *tmp;
+	const unsigned int *lp_index_ptr;
+	unsigned int lp_index = 0;
+
+	seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS);
+
+	rootdn = of_find_node_by_path("/");
+	if (rootdn) {
+		tmp = of_get_property(rootdn, "model", NULL);
+		if (tmp)
+			model = tmp;
+		tmp = of_get_property(rootdn, "system-id", NULL);
+		if (tmp)
+			system_id = tmp;
+		lp_index_ptr = of_get_property(rootdn, "ibm,partition-no",
+					NULL);
+		if (lp_index_ptr)
+			lp_index = *lp_index_ptr;
+		of_node_put(rootdn);
+	}
+	seq_printf(m, "serial_number=%s\n", system_id);
+	seq_printf(m, "system_type=%s\n", model);
+	seq_printf(m, "partition_id=%d\n", (int)lp_index);
+
+	return pseries_lparcfg_data(m, v);
+}
+
+static int lparcfg_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, lparcfg_data, NULL);
+}
+
+static const struct file_operations lparcfg_fops = {
+	.read		= seq_read,
+	.write		= lparcfg_write,
+	.open		= lparcfg_open,
+	.release	= single_release,
+	.llseek		= seq_lseek,
+};
+
+static int __init lparcfg_init(void)
+{
+	umode_t mode = S_IRUSR | S_IRGRP | S_IROTH;
+
+	/* Allow writing if we have FW_FEATURE_SPLPAR */
+	if (firmware_has_feature(FW_FEATURE_SPLPAR))
+		mode |= S_IWUSR;
+
+	if (!proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops)) {
+		printk(KERN_ERR "Failed to create powerpc/lparcfg\n");
+		return -EIO;
+	}
+	return 0;
+}
+machine_device_initcall(pseries, lparcfg_init);
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 3d01eee..cde4e0a 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -28,7 +28,7 @@ struct update_props_workarea {
 	u32 state;
 	u64 reserved;
 	u32 nprops;
-};
+} __packed;
 
 #define NODE_ACTION_MASK	0xff000000
 #define NODE_COUNT_MASK		0x00ffffff
@@ -62,6 +62,7 @@ static int delete_dt_node(u32 phandle)
 		return -ENOENT;
 
 	dlpar_detach_node(dn);
+	of_node_put(dn);
 	return 0;
 }
 
@@ -119,7 +120,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop,
 
 	if (!more) {
 		of_update_property(dn, new_prop);
-		new_prop = NULL;
+		*prop = NULL;
 	}
 
 	return 0;
@@ -130,7 +131,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 	struct update_props_workarea *upwa;
 	struct device_node *dn;
 	struct property *prop = NULL;
-	int i, rc;
+	int i, rc, rtas_rc;
 	char *prop_data;
 	char *rtas_buf;
 	int update_properties_token;
@@ -154,25 +155,26 @@ static int update_dt_node(u32 phandle, s32 scope)
 	upwa->phandle = phandle;
 
 	do {
-		rc = mobility_rtas_call(update_properties_token, rtas_buf,
+		rtas_rc = mobility_rtas_call(update_properties_token, rtas_buf,
 					scope);
-		if (rc < 0)
+		if (rtas_rc < 0)
 			break;
 
 		prop_data = rtas_buf + sizeof(*upwa);
 
-		/* The first element of the buffer is the path of the node
-		 * being updated in the form of a 8 byte string length
-		 * followed by the string. Skip past this to get to the
-		 * properties being updated.
+		/* On the first call to ibm,update-properties for a node the
+		 * the first property value descriptor contains an empty
+		 * property name, the property value length encoded as u32,
+		 * and the property value is the node path being updated.
 		 */
-		vd = *prop_data++;
-		prop_data += vd;
+		if (*prop_data == 0) {
+			prop_data++;
+			vd = *(u32 *)prop_data;
+			prop_data += vd + sizeof(vd);
+			upwa->nprops--;
+		}
 
-		/* The path we skipped over is counted as one of the elements
-		 * returned so start counting at one.
-		 */
-		for (i = 1; i < upwa->nprops; i++) {
+		for (i = 0; i < upwa->nprops; i++) {
 			char *prop_name;
 
 			prop_name = prop_data;
@@ -202,7 +204,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 				prop_data += vd;
 			}
 		}
-	} while (rc == 1);
+	} while (rtas_rc == 1);
 
 	of_node_put(dn);
 	kfree(rtas_buf);
@@ -215,17 +217,14 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index)
 	struct device_node *parent_dn;
 	int rc;
 
-	dn = dlpar_configure_connector(drc_index);
-	if (!dn)
+	parent_dn = of_find_node_by_phandle(parent_phandle);
+	if (!parent_dn)
 		return -ENOENT;
 
-	parent_dn = of_find_node_by_phandle(parent_phandle);
-	if (!parent_dn) {
-		dlpar_free_cc_nodes(dn);
+	dn = dlpar_configure_connector(drc_index, parent_dn);
+	if (!dn)
 		return -ENOENT;
-	}
 
-	dn->parent = parent_dn;
 	rc = dlpar_attach_node(dn);
 	if (rc)
 		dlpar_free_cc_nodes(dn);
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 8733a86..7bfaf58 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -18,6 +18,7 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/kmsg_dump.h>
+#include <linux/pstore.h>
 #include <linux/ctype.h>
 #include <linux/zlib.h>
 #include <asm/uaccess.h>
@@ -29,6 +30,13 @@
 /* Max bytes to read/write in one go */
 #define NVRW_CNT 0x20
 
+/*
+ * Set oops header version to distinguish between old and new format header.
+ * lnx,oops-log partition max size is 4000, header version > 4000 will
+ * help in identifying new header.
+ */
+#define OOPS_HDR_VERSION 5000
+
 static unsigned int nvram_size;
 static int nvram_fetch, nvram_store;
 static char nvram_buf[NVRW_CNT];	/* assume this is in the first 4GB */
@@ -45,20 +53,23 @@ struct nvram_os_partition {
 	int min_size;	/* minimum acceptable size (0 means req_size) */
 	long size;	/* size of data portion (excluding err_log_info) */
 	long index;	/* offset of data portion of partition */
+	bool os_partition; /* partition initialized by OS, not FW */
 };
 
 static struct nvram_os_partition rtas_log_partition = {
 	.name = "ibm,rtas-log",
 	.req_size = 2079,
 	.min_size = 1055,
-	.index = -1
+	.index = -1,
+	.os_partition = true
 };
 
 static struct nvram_os_partition oops_log_partition = {
 	.name = "lnx,oops-log",
 	.req_size = 4000,
 	.min_size = 2000,
-	.index = -1
+	.index = -1,
+	.os_partition = true
 };
 
 static const char *pseries_nvram_os_partitions[] = {
@@ -67,6 +78,12 @@ static const char *pseries_nvram_os_partitions[] = {
 	NULL
 };
 
+struct oops_log_info {
+	u16 version;
+	u16 report_length;
+	u64 timestamp;
+} __attribute__((packed));
+
 static void oops_to_nvram(struct kmsg_dumper *dumper,
 			  enum kmsg_dump_reason reason);
 
@@ -83,28 +100,28 @@ static unsigned long last_unread_rtas_event;	/* timestamp */
 
  * 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_buf[] holds the compressed text, preceded by a oops header.
+ * oops header has u16 holding the version of oops header (to differentiate
+ * between old and new format header) followed by u16 holding the length of
+ * the compressed* text (*Or uncompressed, if compression fails.) and u64
+ * holding the timestamp. oops_buf[] gets written to NVRAM.
  *
- * oops_len points to the prefix.  oops_data points to the compressed text.
+ * oops_log_info points to the header. oops_data points to the compressed text.
  *
  * +- oops_buf
- * |		+- oops_data
- * v		v
- * +------------+-----------------------------------------------+
- * | length	| text                                          |
- * | (2 bytes)	| (oops_data_sz bytes)                          |
- * +------------+-----------------------------------------------+
+ * |                                   +- oops_data
+ * v                                   v
+ * +-----------+-----------+-----------+------------------------+
+ * | version   | length    | timestamp | text                   |
+ * | (2 bytes) | (2 bytes) | (8 bytes) | (oops_data_sz bytes)   |
+ * +-----------+-----------+-----------+------------------------+
  * ^
- * +- oops_len
+ * +- oops_log_info
  *
  * 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;
 
@@ -114,6 +131,30 @@ static size_t oops_data_sz;
 #define MEM_LEVEL 4
 static struct z_stream_s stream;
 
+#ifdef CONFIG_PSTORE
+static struct nvram_os_partition of_config_partition = {
+	.name = "of-config",
+	.index = -1,
+	.os_partition = false
+};
+
+static struct nvram_os_partition common_partition = {
+	.name = "common",
+	.index = -1,
+	.os_partition = false
+};
+
+static enum pstore_type_id nvram_type_ids[] = {
+	PSTORE_TYPE_DMESG,
+	PSTORE_TYPE_PPC_RTAS,
+	PSTORE_TYPE_PPC_OF,
+	PSTORE_TYPE_PPC_COMMON,
+	-1
+};
+static int read_type;
+static unsigned long last_rtas_event;
+#endif
+
 static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index)
 {
 	unsigned int i;
@@ -275,48 +316,72 @@ int nvram_write_error_log(char * buff, int length,
 {
 	int rc = nvram_write_os_partition(&rtas_log_partition, buff, length,
 						err_type, error_log_cnt);
-	if (!rc)
+	if (!rc) {
 		last_unread_rtas_event = get_seconds();
+#ifdef CONFIG_PSTORE
+		last_rtas_event = get_seconds();
+#endif
+	}
+
 	return rc;
 }
 
-/* nvram_read_error_log
+/* nvram_read_partition
  *
- * Reads nvram for error log for at most 'length'
+ * Reads nvram partition for at most 'length'
  */
-int nvram_read_error_log(char * buff, int length,
-                         unsigned int * err_type, unsigned int * error_log_cnt)
+int nvram_read_partition(struct nvram_os_partition *part, char *buff,
+			int length, unsigned int *err_type,
+			unsigned int *error_log_cnt)
 {
 	int rc;
 	loff_t tmp_index;
 	struct err_log_info info;
 	
-	if (rtas_log_partition.index == -1)
+	if (part->index == -1)
 		return -1;
 
-	if (length > rtas_log_partition.size)
-		length = rtas_log_partition.size;
+	if (length > part->size)
+		length = part->size;
 
-	tmp_index = rtas_log_partition.index;
+	tmp_index = part->index;
 
-	rc = ppc_md.nvram_read((char *)&info, sizeof(struct err_log_info), &tmp_index);
-	if (rc <= 0) {
-		printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc);
-		return rc;
+	if (part->os_partition) {
+		rc = ppc_md.nvram_read((char *)&info,
+					sizeof(struct err_log_info),
+					&tmp_index);
+		if (rc <= 0) {
+			pr_err("%s: Failed nvram_read (%d)\n", __FUNCTION__,
+									rc);
+			return rc;
+		}
 	}
 
 	rc = ppc_md.nvram_read(buff, length, &tmp_index);
 	if (rc <= 0) {
-		printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc);
+		pr_err("%s: Failed nvram_read (%d)\n", __FUNCTION__, rc);
 		return rc;
 	}
 
-	*error_log_cnt = info.seq_num;
-	*err_type = info.error_type;
+	if (part->os_partition) {
+		*error_log_cnt = info.seq_num;
+		*err_type = info.error_type;
+	}
 
 	return 0;
 }
 
+/* nvram_read_error_log
+ *
+ * Reads nvram for error log for at most 'length'
+ */
+int nvram_read_error_log(char *buff, int length,
+			unsigned int *err_type, unsigned int *error_log_cnt)
+{
+	return nvram_read_partition(&rtas_log_partition, buff, length,
+						err_type, error_log_cnt);
+}
+
 /* This doesn't actually zero anything, but it sets the event_logged
  * word to tell that this event is safely in syslog.
  */
@@ -364,9 +429,6 @@ static int __init pseries_nvram_init_os_partition(struct nvram_os_partition
 	loff_t p;
 	int size;
 
-	/* Scan nvram for partitions */
-	nvram_scan_partitions();
-
 	/* Look for ours */
 	p = nvram_find_partition(part->name, NVRAM_SIG_OS, &size);
 
@@ -405,6 +467,267 @@ static int __init pseries_nvram_init_os_partition(struct nvram_os_partition
 	return 0;
 }
 
+/*
+ * Are we using the ibm,rtas-log for oops/panic reports?  And if so,
+ * would logging this oops/panic overwrite an RTAS event that rtas_errd
+ * hasn't had a chance to read and process?  Return 1 if so, else 0.
+ *
+ * We assume that if rtas_errd hasn't read the RTAS event in
+ * NVRAM_RTAS_READ_TIMEOUT seconds, it's probably not going to.
+ */
+static int clobbering_unread_rtas_event(void)
+{
+	return (oops_log_partition.index == rtas_log_partition.index
+		&& last_unread_rtas_event
+		&& get_seconds() - last_unread_rtas_event <=
+						NVRAM_RTAS_READ_TIMEOUT);
+}
+
+/* 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)
+{
+	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
+	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_hdr->version = OOPS_HDR_VERSION;
+	oops_hdr->report_length = (u16) zipped_len;
+	oops_hdr->timestamp = get_seconds();
+	return 0;
+}
+
+#ifdef CONFIG_PSTORE
+static int nvram_pstore_open(struct pstore_info *psi)
+{
+	/* Reset the iterator to start reading partitions again */
+	read_type = -1;
+	return 0;
+}
+
+/**
+ * nvram_pstore_write - pstore write callback for nvram
+ * @type:               Type of message logged
+ * @reason:             reason behind dump (oops/panic)
+ * @id:                 identifier to indicate the write performed
+ * @part:               pstore writes data to registered buffer in parts,
+ *                      part number will indicate the same.
+ * @count:              Indicates oops count
+ * @compressed:         Flag to indicate the log is compressed
+ * @size:               number of bytes written to the registered buffer
+ * @psi:                registered pstore_info structure
+ *
+ * Called by pstore_dump() when an oops or panic report is logged in the
+ * printk buffer.
+ * Returns 0 on successful write.
+ */
+static int nvram_pstore_write(enum pstore_type_id type,
+				enum kmsg_dump_reason reason,
+				u64 *id, unsigned int part, int count,
+				bool compressed, size_t size,
+				struct pstore_info *psi)
+{
+	int rc;
+	unsigned int err_type = ERR_TYPE_KERNEL_PANIC;
+	struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf;
+
+	/* part 1 has the recent messages from printk buffer */
+	if (part > 1 || type != PSTORE_TYPE_DMESG ||
+				clobbering_unread_rtas_event())
+		return -1;
+
+	oops_hdr->version = OOPS_HDR_VERSION;
+	oops_hdr->report_length = (u16) size;
+	oops_hdr->timestamp = get_seconds();
+
+	if (compressed)
+		err_type = ERR_TYPE_KERNEL_PANIC_GZ;
+
+	rc = nvram_write_os_partition(&oops_log_partition, oops_buf,
+		(int) (sizeof(*oops_hdr) + size), err_type, count);
+
+	if (rc != 0)
+		return rc;
+
+	*id = part;
+	return 0;
+}
+
+/*
+ * Reads the oops/panic report, rtas, of-config and common partition.
+ * Returns the length of the data we read from each partition.
+ * Returns 0 if we've been called before.
+ */
+static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
+				int *count, struct timespec *time, char **buf,
+				bool *compressed, struct pstore_info *psi)
+{
+	struct oops_log_info *oops_hdr;
+	unsigned int err_type, id_no, size = 0;
+	struct nvram_os_partition *part = NULL;
+	char *buff = NULL;
+	int sig = 0;
+	loff_t p;
+
+	read_type++;
+
+	switch (nvram_type_ids[read_type]) {
+	case PSTORE_TYPE_DMESG:
+		part = &oops_log_partition;
+		*type = PSTORE_TYPE_DMESG;
+		break;
+	case PSTORE_TYPE_PPC_RTAS:
+		part = &rtas_log_partition;
+		*type = PSTORE_TYPE_PPC_RTAS;
+		time->tv_sec = last_rtas_event;
+		time->tv_nsec = 0;
+		break;
+	case PSTORE_TYPE_PPC_OF:
+		sig = NVRAM_SIG_OF;
+		part = &of_config_partition;
+		*type = PSTORE_TYPE_PPC_OF;
+		*id = PSTORE_TYPE_PPC_OF;
+		time->tv_sec = 0;
+		time->tv_nsec = 0;
+		break;
+	case PSTORE_TYPE_PPC_COMMON:
+		sig = NVRAM_SIG_SYS;
+		part = &common_partition;
+		*type = PSTORE_TYPE_PPC_COMMON;
+		*id = PSTORE_TYPE_PPC_COMMON;
+		time->tv_sec = 0;
+		time->tv_nsec = 0;
+		break;
+	default:
+		return 0;
+	}
+
+	if (!part->os_partition) {
+		p = nvram_find_partition(part->name, sig, &size);
+		if (p <= 0) {
+			pr_err("nvram: Failed to find partition %s, "
+				"err %d\n", part->name, (int)p);
+			return 0;
+		}
+		part->index = p;
+		part->size = size;
+	}
+
+	buff = kmalloc(part->size, GFP_KERNEL);
+
+	if (!buff)
+		return -ENOMEM;
+
+	if (nvram_read_partition(part, buff, part->size, &err_type, &id_no)) {
+		kfree(buff);
+		return 0;
+	}
+
+	*count = 0;
+
+	if (part->os_partition)
+		*id = id_no;
+
+	if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
+		size_t length, hdr_size;
+
+		oops_hdr = (struct oops_log_info *)buff;
+		if (oops_hdr->version < OOPS_HDR_VERSION) {
+			/* Old format oops header had 2-byte record size */
+			hdr_size = sizeof(u16);
+			length = oops_hdr->version;
+			time->tv_sec = 0;
+			time->tv_nsec = 0;
+		} else {
+			hdr_size = sizeof(*oops_hdr);
+			length = oops_hdr->report_length;
+			time->tv_sec = oops_hdr->timestamp;
+			time->tv_nsec = 0;
+		}
+		*buf = kmalloc(length, GFP_KERNEL);
+		if (*buf == NULL)
+			return -ENOMEM;
+		memcpy(*buf, buff + hdr_size, length);
+		kfree(buff);
+
+		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
+			*compressed = true;
+		else
+			*compressed = false;
+		return length;
+	}
+
+	*buf = buff;
+	return part->size;
+}
+
+static struct pstore_info nvram_pstore_info = {
+	.owner = THIS_MODULE,
+	.name = "nvram",
+	.open = nvram_pstore_open,
+	.read = nvram_pstore_read,
+	.write = nvram_pstore_write,
+};
+
+static int nvram_pstore_init(void)
+{
+	int rc = 0;
+
+	nvram_pstore_info.buf = oops_data;
+	nvram_pstore_info.bufsize = oops_data_sz;
+
+	rc = pstore_register(&nvram_pstore_info);
+	if (rc != 0)
+		pr_err("nvram: pstore_register() failed, defaults to "
+				"kmsg_dump; returned %d\n", rc);
+
+	return rc;
+}
+#else
+static int nvram_pstore_init(void)
+{
+	return -1;
+}
+#endif
+
 static void __init nvram_init_oops_partition(int rtas_partition_exists)
 {
 	int rc;
@@ -425,9 +748,13 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
 						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);
+	oops_data = oops_buf + sizeof(struct oops_log_info);
+	oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info);
+
+	rc = nvram_pstore_init();
+
+	if (!rc)
+		return;
 
 	/*
 	 * Figure compression (preceded by elimination of each line's <n>
@@ -437,8 +764,8 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
 	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);
+		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",
@@ -465,6 +792,9 @@ static int __init pseries_nvram_init_log_partitions(void)
 {
 	int rc;
 
+	/* Scan nvram for partitions */
+	nvram_scan_partitions();
+
 	rc = pseries_nvram_init_os_partition(&rtas_log_partition);
 	nvram_init_oops_partition(rc == 0);
 	return 0;
@@ -474,7 +804,7 @@ machine_arch_initcall(pseries, pseries_nvram_init_log_partitions);
 int __init pSeries_nvram_init(void)
 {
 	struct device_node *nvram;
-	const unsigned int *nbytes_p;
+	const __be32 *nbytes_p;
 	unsigned int proplen;
 
 	nvram = of_find_node_by_type(NULL, "nvram");
@@ -487,7 +817,7 @@ int __init pSeries_nvram_init(void)
 		return -EIO;
 	}
 
-	nvram_size = *nbytes_p;
+	nvram_size = be32_to_cpup(nbytes_p);
 
 	nvram_fetch = rtas_token("nvram-fetch");
 	nvram_store = rtas_token("nvram-store");
@@ -501,70 +831,6 @@ int __init pSeries_nvram_init(void)
 	return 0;
 }
 
-/*
- * Are we using the ibm,rtas-log for oops/panic reports?  And if so,
- * would logging this oops/panic overwrite an RTAS event that rtas_errd
- * hasn't had a chance to read and process?  Return 1 if so, else 0.
- *
- * We assume that if rtas_errd hasn't read the RTAS event in
- * NVRAM_RTAS_READ_TIMEOUT seconds, it's probably not going to.
- */
-static int clobbering_unread_rtas_event(void)
-{
-	return (oops_log_partition.index == rtas_log_partition.index
-		&& last_unread_rtas_event
-		&& get_seconds() - last_unread_rtas_event <=
-						NVRAM_RTAS_READ_TIMEOUT);
-}
-
-/* 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
@@ -576,6 +842,7 @@ static int zip_oops(size_t text_len)
 static void oops_to_nvram(struct kmsg_dumper *dumper,
 			  enum kmsg_dump_reason reason)
 {
+	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
 	static unsigned int oops_count = 0;
 	static bool panicking = false;
 	static DEFINE_SPINLOCK(lock);
@@ -619,14 +886,17 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
 	}
 	if (rc != 0) {
 		kmsg_dump_rewind(dumper);
-		kmsg_dump_get_buffer(dumper, true,
+		kmsg_dump_get_buffer(dumper, false,
 				     oops_data, oops_data_sz, &text_len);
 		err_type = ERR_TYPE_KERNEL_PANIC;
-		*oops_len = (u16) text_len;
+		oops_hdr->version = OOPS_HDR_VERSION;
+		oops_hdr->report_length = (u16) text_len;
+		oops_hdr->timestamp = get_seconds();
 	}
 
 	(void) nvram_write_os_partition(&oops_log_partition, oops_buf,
-		(int) (sizeof(*oops_len) + *oops_len), err_type, ++oops_count);
+		(int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type,
+		++oops_count);
 
 	spin_unlock_irqrestore(&lock, flags);
 }
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index c91b22b..efe6137 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -64,91 +64,6 @@ pcibios_find_pci_bus(struct device_node *dn)
 }
 EXPORT_SYMBOL_GPL(pcibios_find_pci_bus);
 
-/**
- * __pcibios_remove_pci_devices - remove all devices under this bus
- * @bus: the indicated PCI bus
- * @purge_pe: destroy the PE on removal of PCI devices
- *
- * Remove all of the PCI devices under this bus both from the
- * linux pci device tree, and from the powerpc EEH address cache.
- * By default, the corresponding PE will be destroied during the
- * normal PCI hotplug path. For PCI hotplug during EEH recovery,
- * the corresponding PE won't be destroied and deallocated.
- */
-void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe)
-{
-	struct pci_dev *dev, *tmp;
-	struct pci_bus *child_bus;
-
-	/* First go down child busses */
-	list_for_each_entry(child_bus, &bus->children, node)
-		__pcibios_remove_pci_devices(child_bus, purge_pe);
-
-	pr_debug("PCI: Removing devices on bus %04x:%02x\n",
-		pci_domain_nr(bus),  bus->number);
-	list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) {
-		pr_debug("     * Removing %s...\n", pci_name(dev));
-		eeh_remove_bus_device(dev, purge_pe);
-		pci_stop_and_remove_bus_device(dev);
-	}
-}
-
-/**
- * pcibios_remove_pci_devices - remove all devices under this bus
- *
- * Remove all of the PCI devices under this bus both from the
- * linux pci device tree, and from the powerpc EEH address cache.
- */
-void pcibios_remove_pci_devices(struct pci_bus *bus)
-{
-	__pcibios_remove_pci_devices(bus, 1);
-}
-EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
-
-/**
- * pcibios_add_pci_devices - adds new pci devices to bus
- *
- * This routine will find and fixup new pci devices under
- * the indicated bus. This routine presumes that there
- * might already be some devices under this bridge, so
- * it carefully tries to add only new devices.  (And that
- * is how this routine differs from other, similar pcibios
- * routines.)
- */
-void pcibios_add_pci_devices(struct pci_bus * bus)
-{
-	int slotno, num, mode, pass, max;
-	struct pci_dev *dev;
-	struct device_node *dn = pci_bus_to_OF_node(bus);
-
-	eeh_add_device_tree_early(dn);
-
-	mode = PCI_PROBE_NORMAL;
-	if (ppc_md.pci_probe_mode)
-		mode = ppc_md.pci_probe_mode(bus);
-
-	if (mode == PCI_PROBE_DEVTREE) {
-		/* use ofdt-based probe */
-		of_rescan_bus(dn, bus);
-	} else if (mode == PCI_PROBE_NORMAL) {
-		/* use legacy probe */
-		slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
-		num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
-		if (!num)
-			return;
-		pcibios_setup_bus_devices(bus);
-		max = bus->busn_res.start;
-		for (pass=0; pass < 2; pass++)
-			list_for_each_entry(dev, &bus->devices, bus_list) {
-			if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
-			    dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
-				max = pci_scan_bridge(bus, dev, max, pass);
-		}
-	}
-	pcibios_finish_adding_to_bus(bus);
-}
-EXPORT_SYMBOL_GPL(pcibios_add_pci_devices);
-
 struct pci_controller *init_phb_dynamic(struct device_node *dn)
 {
 	struct pci_controller *phb;
diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h
deleted file mode 100644
index f35787b..0000000
--- a/arch/powerpc/platforms/pseries/plpar_wrappers.h
+++ /dev/null
@@ -1,324 +0,0 @@
-#ifndef _PSERIES_PLPAR_WRAPPERS_H
-#define _PSERIES_PLPAR_WRAPPERS_H
-
-#include <linux/string.h>
-#include <linux/irqflags.h>
-
-#include <asm/hvcall.h>
-#include <asm/paca.h>
-#include <asm/page.h>
-
-/* Get state of physical CPU from query_cpu_stopped */
-int smp_query_cpu_stopped(unsigned int pcpu);
-#define QCSS_STOPPED 0
-#define QCSS_STOPPING 1
-#define QCSS_NOT_STOPPED 2
-#define QCSS_HARDWARE_ERROR -1
-#define QCSS_HARDWARE_BUSY -2
-
-static inline long poll_pending(void)
-{
-	return plpar_hcall_norets(H_POLL_PENDING);
-}
-
-static inline u8 get_cede_latency_hint(void)
-{
-	return get_lppaca()->cede_latency_hint;
-}
-
-static inline void set_cede_latency_hint(u8 latency_hint)
-{
-	get_lppaca()->cede_latency_hint = latency_hint;
-}
-
-static inline long cede_processor(void)
-{
-	return plpar_hcall_norets(H_CEDE);
-}
-
-static inline long extended_cede_processor(unsigned long latency_hint)
-{
-	long rc;
-	u8 old_latency_hint = get_cede_latency_hint();
-
-	set_cede_latency_hint(latency_hint);
-
-	rc = cede_processor();
-#ifdef CONFIG_TRACE_IRQFLAGS
-		/* Ensure that H_CEDE returns with IRQs on */
-		if (WARN_ON(!(mfmsr() & MSR_EE)))
-			__hard_irq_enable();
-#endif
-
-	set_cede_latency_hint(old_latency_hint);
-
-	return rc;
-}
-
-static inline long vpa_call(unsigned long flags, unsigned long cpu,
-		unsigned long vpa)
-{
-	flags = flags << H_VPA_FUNC_SHIFT;
-
-	return plpar_hcall_norets(H_REGISTER_VPA, flags, cpu, vpa);
-}
-
-static inline long unregister_vpa(unsigned long cpu)
-{
-	return vpa_call(H_VPA_DEREG_VPA, cpu, 0);
-}
-
-static inline long register_vpa(unsigned long cpu, unsigned long vpa)
-{
-	return vpa_call(H_VPA_REG_VPA, cpu, vpa);
-}
-
-static inline long unregister_slb_shadow(unsigned long cpu)
-{
-	return vpa_call(H_VPA_DEREG_SLB, cpu, 0);
-}
-
-static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa)
-{
-	return vpa_call(H_VPA_REG_SLB, cpu, vpa);
-}
-
-static inline long unregister_dtl(unsigned long cpu)
-{
-	return vpa_call(H_VPA_DEREG_DTL, cpu, 0);
-}
-
-static inline long register_dtl(unsigned long cpu, unsigned long vpa)
-{
-	return vpa_call(H_VPA_REG_DTL, cpu, vpa);
-}
-
-static inline long plpar_page_set_loaned(unsigned long vpa)
-{
-	unsigned long cmo_page_sz = cmo_get_page_size();
-	long rc = 0;
-	int i;
-
-	for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz)
-		rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, vpa + i, 0);
-
-	for (i -= cmo_page_sz; rc && i != 0; i -= cmo_page_sz)
-		plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE,
-				   vpa + i - cmo_page_sz, 0);
-
-	return rc;
-}
-
-static inline long plpar_page_set_active(unsigned long vpa)
-{
-	unsigned long cmo_page_sz = cmo_get_page_size();
-	long rc = 0;
-	int i;
-
-	for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz)
-		rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, vpa + i, 0);
-
-	for (i -= cmo_page_sz; rc && i != 0; i -= cmo_page_sz)
-		plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED,
-				   vpa + i - cmo_page_sz, 0);
-
-	return rc;
-}
-
-extern void vpa_init(int cpu);
-
-static inline long plpar_pte_enter(unsigned long flags,
-		unsigned long hpte_group, unsigned long hpte_v,
-		unsigned long hpte_r, unsigned long *slot)
-{
-	long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-	rc = plpar_hcall(H_ENTER, retbuf, flags, hpte_group, hpte_v, hpte_r);
-
-	*slot = retbuf[0];
-
-	return rc;
-}
-
-static inline long plpar_pte_remove(unsigned long flags, unsigned long ptex,
-		unsigned long avpn, unsigned long *old_pteh_ret,
-		unsigned long *old_ptel_ret)
-{
-	long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-	rc = plpar_hcall(H_REMOVE, retbuf, flags, ptex, avpn);
-
-	*old_pteh_ret = retbuf[0];
-	*old_ptel_ret = retbuf[1];
-
-	return rc;
-}
-
-/* plpar_pte_remove_raw can be called in real mode. It calls plpar_hcall_raw */
-static inline long plpar_pte_remove_raw(unsigned long flags, unsigned long ptex,
-		unsigned long avpn, unsigned long *old_pteh_ret,
-		unsigned long *old_ptel_ret)
-{
-	long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-	rc = plpar_hcall_raw(H_REMOVE, retbuf, flags, ptex, avpn);
-
-	*old_pteh_ret = retbuf[0];
-	*old_ptel_ret = retbuf[1];
-
-	return rc;
-}
-
-static inline long plpar_pte_read(unsigned long flags, unsigned long ptex,
-		unsigned long *old_pteh_ret, unsigned long *old_ptel_ret)
-{
-	long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-	rc = plpar_hcall(H_READ, retbuf, flags, ptex);
-
-	*old_pteh_ret = retbuf[0];
-	*old_ptel_ret = retbuf[1];
-
-	return rc;
-}
-
-/* plpar_pte_read_raw can be called in real mode. It calls plpar_hcall_raw */
-static inline long plpar_pte_read_raw(unsigned long flags, unsigned long ptex,
-		unsigned long *old_pteh_ret, unsigned long *old_ptel_ret)
-{
-	long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-	rc = plpar_hcall_raw(H_READ, retbuf, flags, ptex);
-
-	*old_pteh_ret = retbuf[0];
-	*old_ptel_ret = retbuf[1];
-
-	return rc;
-}
-
-/*
- * plpar_pte_read_4_raw can be called in real mode.
- * ptes must be 8*sizeof(unsigned long)
- */
-static inline long plpar_pte_read_4_raw(unsigned long flags, unsigned long ptex,
-					unsigned long *ptes)
-
-{
-	long rc;
-	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
-
-	rc = plpar_hcall9_raw(H_READ, retbuf, flags | H_READ_4, ptex);
-
-	memcpy(ptes, retbuf, 8*sizeof(unsigned long));
-
-	return rc;
-}
-
-static inline long plpar_pte_protect(unsigned long flags, unsigned long ptex,
-		unsigned long avpn)
-{
-	return plpar_hcall_norets(H_PROTECT, flags, ptex, avpn);
-}
-
-static inline long plpar_tce_get(unsigned long liobn, unsigned long ioba,
-		unsigned long *tce_ret)
-{
-	long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-	rc = plpar_hcall(H_GET_TCE, retbuf, liobn, ioba);
-
-	*tce_ret = retbuf[0];
-
-	return rc;
-}
-
-static inline long plpar_tce_put(unsigned long liobn, unsigned long ioba,
-		unsigned long tceval)
-{
-	return plpar_hcall_norets(H_PUT_TCE, liobn, ioba, tceval);
-}
-
-static inline long plpar_tce_put_indirect(unsigned long liobn,
-		unsigned long ioba, unsigned long page, unsigned long count)
-{
-	return plpar_hcall_norets(H_PUT_TCE_INDIRECT, liobn, ioba, page, count);
-}
-
-static inline long plpar_tce_stuff(unsigned long liobn, unsigned long ioba,
-		unsigned long tceval, unsigned long count)
-{
-	return plpar_hcall_norets(H_STUFF_TCE, liobn, ioba, tceval, count);
-}
-
-static inline long plpar_get_term_char(unsigned long termno,
-		unsigned long *len_ret, char *buf_ret)
-{
-	long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-	unsigned long *lbuf = (unsigned long *)buf_ret;	/* TODO: alignment? */
-
-	rc = plpar_hcall(H_GET_TERM_CHAR, retbuf, termno);
-
-	*len_ret = retbuf[0];
-	lbuf[0] = retbuf[1];
-	lbuf[1] = retbuf[2];
-
-	return rc;
-}
-
-static inline long plpar_put_term_char(unsigned long termno, unsigned long len,
-		const char *buffer)
-{
-	unsigned long *lbuf = (unsigned long *)buffer;	/* TODO: alignment? */
-	return plpar_hcall_norets(H_PUT_TERM_CHAR, termno, len, lbuf[0],
-			lbuf[1]);
-}
-
-/* Set various resource mode parameters */
-static inline long plpar_set_mode(unsigned long mflags, unsigned long resource,
-		unsigned long value1, unsigned long value2)
-{
-	return plpar_hcall_norets(H_SET_MODE, mflags, resource, value1, value2);
-}
-
-/*
- * Enable relocation on exceptions on this partition
- *
- * Note: this call has a partition wide scope and can take a while to complete.
- * If it returns H_LONG_BUSY_* it should be retried periodically until it
- * returns H_SUCCESS.
- */
-static inline long enable_reloc_on_exceptions(void)
-{
-	/* mflags = 3: Exceptions at 0xC000000000004000 */
-	return plpar_set_mode(3, 3, 0, 0);
-}
-
-/*
- * Disable relocation on exceptions on this partition
- *
- * Note: this call has a partition wide scope and can take a while to complete.
- * If it returns H_LONG_BUSY_* it should be retried periodically until it
- * returns H_SUCCESS.
- */
-static inline long disable_reloc_on_exceptions(void) {
-	return plpar_set_mode(0, 3, 0, 0);
-}
-
-static inline long plapr_set_ciabr(unsigned long ciabr)
-{
-	return plpar_set_mode(0, 1, ciabr, 0);
-}
-
-static inline long plapr_set_watchpoint0(unsigned long dawr0, unsigned long dawrx0)
-{
-	return plpar_set_mode(0, 2, dawr0, dawrx0);
-}
-
-#endif /* _PSERIES_PLPAR_WRAPPERS_H */
diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c
index 4644efa0..a166e38 100644
--- a/arch/powerpc/platforms/pseries/processor_idle.c
+++ b/arch/powerpc/platforms/pseries/processor_idle.c
@@ -18,9 +18,7 @@
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/runlatch.h>
-
-#include "plpar_wrappers.h"
-#include "pseries.h"
+#include <asm/plpar_wrappers.h>
 
 struct cpuidle_driver pseries_idle_driver = {
 	.name             = "pseries_idle",
@@ -45,7 +43,11 @@ static inline void idle_loop_prolog(unsigned long *in_purr)
 
 static inline void idle_loop_epilog(unsigned long in_purr)
 {
-	get_lppaca()->wait_state_cycles += mfspr(SPRN_PURR) - in_purr;
+	u64 wait_cycles;
+
+	wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
+	wait_cycles += mfspr(SPRN_PURR) - in_purr;
+	get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
 	get_lppaca()->idle = 0;
 }
 
@@ -308,7 +310,7 @@ static int pseries_idle_probe(void)
 		return -EPERM;
 	}
 
-	if (get_lppaca()->shared_proc)
+	if (lppaca_shared_proc(get_lppaca()))
 		cpuidle_state_table = shared_states;
 	else
 		cpuidle_state_table = dedicated_states;
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index c2a3a25..9921953 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -56,13 +56,10 @@ extern void hvc_vio_init_early(void);
 /* Dynamic logical Partitioning/Mobility */
 extern void dlpar_free_cc_nodes(struct device_node *);
 extern void dlpar_free_cc_property(struct property *);
-extern struct device_node *dlpar_configure_connector(u32);
+extern struct device_node *dlpar_configure_connector(u32, struct device_node *);
 extern int dlpar_attach_node(struct device_node *);
 extern int dlpar_detach_node(struct device_node *);
 
-/* Snooze Delay, pseries_idle */
-DECLARE_PER_CPU(long, smt_snooze_delay);
-
 /* PCI root bridge prepare function override for pseries */
 struct pci_host_bridge;
 int pseries_root_bridge_prepare(struct pci_host_bridge *bridge);
diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c
index a91e6da..9276779 100644
--- a/arch/powerpc/platforms/pseries/pseries_energy.c
+++ b/arch/powerpc/platforms/pseries/pseries_energy.c
@@ -108,8 +108,8 @@ err:
  * energy consumption.
  */
 
-#define FLAGS_MODE1	0x004E200000080E01
-#define FLAGS_MODE2	0x004E200000080401
+#define FLAGS_MODE1	0x004E200000080E01UL
+#define FLAGS_MODE2	0x004E200000080401UL
 #define FLAGS_ACTIVATE  0x100
 
 static ssize_t get_best_energy_list(char *page, int activate)
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index c4dfccd..721c058 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -83,7 +83,7 @@ static void handle_system_shutdown(char event_modifier)
 	switch (event_modifier) {
 	case EPOW_SHUTDOWN_NORMAL:
 		pr_emerg("Firmware initiated power off");
-		orderly_poweroff(1);
+		orderly_poweroff(true);
 		break;
 
 	case EPOW_SHUTDOWN_ON_UPS:
@@ -95,13 +95,13 @@ static void handle_system_shutdown(char event_modifier)
 		pr_emerg("Loss of system critical functions reported by "
 			"firmware");
 		pr_emerg("Check RTAS error log for details");
-		orderly_poweroff(1);
+		orderly_poweroff(true);
 		break;
 
 	case EPOW_SHUTDOWN_AMBIENT_TEMPERATURE_TOO_HIGH:
 		pr_emerg("Ambient temperature too high reported by firmware");
 		pr_emerg("Check RTAS error log for details");
-		orderly_poweroff(1);
+		orderly_poweroff(true);
 		break;
 
 	default:
@@ -162,7 +162,7 @@ void rtas_parse_epow_errlog(struct rtas_error_log *log)
 
 	case EPOW_SYSTEM_HALT:
 		pr_emerg("Firmware initiated power off");
-		orderly_poweroff(1);
+		orderly_poweroff(true);
 		break;
 
 	case EPOW_MAIN_ENCLOSURE:
@@ -287,6 +287,9 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs)
 	unsigned long *savep;
 	struct rtas_error_log *h, *errhdr = NULL;
 
+	/* Mask top two bits */
+	regs->gpr[3] &= ~(0x3UL << 62);
+
 	if (!VALID_FWNMI_BUFFER(regs->gpr[3])) {
 		printk(KERN_ERR "FWNMI: corrupt r3 0x%016lx\n", regs->gpr[3]);
 		return NULL;
diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c
new file mode 100644
index 0000000..72a1027
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/rng.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2013, Michael Ellerman, 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 pr_fmt(fmt)	"pseries-rng: " fmt
+
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <asm/archrandom.h>
+#include <asm/machdep.h>
+#include <asm/plpar_wrappers.h>
+
+
+static int pseries_get_random_long(unsigned long *v)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+	if (plpar_hcall(H_RANDOM, retbuf) == H_SUCCESS) {
+		*v = retbuf[0];
+		return 1;
+	}
+
+	return 0;
+}
+
+static __init int rng_init(void)
+{
+	struct device_node *dn;
+
+	dn = of_find_compatible_node(NULL, NULL, "ibm,random");
+	if (!dn)
+		return -ENODEV;
+
+	pr_info("Registering arch random hook.\n");
+
+	ppc_md.get_random_long = pseries_get_random_long;
+
+	return 0;
+}
+subsys_initcall(rng_init);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index c11c823..c1f1908 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -66,8 +66,8 @@
 #include <asm/firmware.h>
 #include <asm/eeh.h>
 #include <asm/reg.h>
+#include <asm/plpar_wrappers.h>
 
-#include "plpar_wrappers.h"
 #include "pseries.h"
 
 int CMO_PrPSP = -1;
@@ -183,7 +183,7 @@ static void __init pseries_mpic_init_IRQ(void)
 	np = of_find_node_by_path("/");
 	naddr = of_n_addr_cells(np);
 	opprop = of_get_property(np, "platform-open-pic", &opplen);
-	if (opprop != 0) {
+	if (opprop != NULL) {
 		openpic_addr = of_read_number(opprop, naddr);
 		printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr);
 	}
@@ -323,7 +323,7 @@ static int alloc_dispatch_logs(void)
 	get_paca()->lppaca_ptr->dtl_idx = 0;
 
 	/* hypervisor reads buffer length from this field */
-	dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
+	dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
 	ret = register_dtl(hard_smp_processor_id(), __pa(dtl));
 	if (ret)
 		pr_err("WARNING: DTL registration of cpu %d (hw %d) failed "
@@ -354,7 +354,7 @@ static int alloc_dispatch_log_kmem_cache(void)
 }
 early_initcall(alloc_dispatch_log_kmem_cache);
 
-static void pSeries_idle(void)
+static void pseries_lpar_idle(void)
 {
 	/* This would call on the cpuidle framework, and the back-end pseries
 	 * driver to  go to idle states
@@ -362,10 +362,22 @@ static void pSeries_idle(void)
 	if (cpuidle_idle_call()) {
 		/* On error, execute default handler
 		 * to go into low thread priority and possibly
-		 * low power mode.
+		 * low power mode by cedeing processor to hypervisor
 		 */
-		HMT_low();
-		HMT_very_low();
+
+		/* Indicate to hypervisor that we are idle. */
+		get_lppaca()->idle = 1;
+
+		/*
+		 * Yield the processor to the hypervisor.  We return if
+		 * an external interrupt occurs (which are driven prior
+		 * to returning here) or if a prod occurs from another
+		 * processor. When returning here, external interrupts
+		 * are enabled.
+		 */
+		cede_processor();
+
+		get_lppaca()->idle = 0;
 	}
 }
 
@@ -430,6 +442,32 @@ static void pSeries_machine_kexec(struct kimage *image)
 }
 #endif
 
+#ifdef __LITTLE_ENDIAN__
+long pseries_big_endian_exceptions(void)
+{
+	long rc;
+
+	while (1) {
+		rc = enable_big_endian_exceptions();
+		if (!H_IS_LONG_BUSY(rc))
+			return rc;
+		mdelay(get_longbusy_msecs(rc));
+	}
+}
+
+static long pseries_little_endian_exceptions(void)
+{
+	long rc;
+
+	while (1) {
+		rc = enable_little_endian_exceptions();
+		if (!H_IS_LONG_BUSY(rc))
+			return rc;
+		mdelay(get_longbusy_msecs(rc));
+	}
+}
+#endif
+
 static void __init pSeries_setup_arch(void)
 {
 	panic_timeout = 10;
@@ -456,15 +494,14 @@ static void __init pSeries_setup_arch(void)
 
 	pSeries_nvram_init();
 
-	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		vpa_init(boot_cpuid);
-		ppc_md.power_save = pSeries_idle;
-	}
-
-	if (firmware_has_feature(FW_FEATURE_LPAR))
+		ppc_md.power_save = pseries_lpar_idle;
 		ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
-	else
+	} else {
+		/* No special idle routine */
 		ppc_md.enable_pmcs = power4_enable_pmcs;
+	}
 
 	ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
 
@@ -687,6 +724,22 @@ static int __init pSeries_probe(void)
 	/* Now try to figure out if we are running on LPAR */
 	of_scan_flat_dt(pseries_probe_fw_features, NULL);
 
+#ifdef __LITTLE_ENDIAN__
+	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
+		long rc;
+		/*
+		 * Tell the hypervisor that we want our exceptions to
+		 * be taken in little endian mode. If this fails we don't
+		 * want to use BUG() because it will trigger an exception.
+		 */
+		rc = pseries_little_endian_exceptions();
+		if (rc) {
+			ppc_md.progress("H_SET_MODE LE exception fail", 0);
+			panic("Could not enable little endian exceptions");
+		}
+	}
+#endif
+
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		hpte_init_lpar();
 	else
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index ca2d1f6..24f58cb 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -43,8 +43,8 @@
 #include <asm/cputhreads.h>
 #include <asm/xics.h>
 #include <asm/dbell.h>
+#include <asm/plpar_wrappers.h>
 
-#include "plpar_wrappers.h"
 #include "pseries.h"
 #include "offline_states.h"
 
@@ -233,18 +233,24 @@ static void __init smp_init_pseries(void)
 
 	alloc_bootmem_cpumask_var(&of_spin_mask);
 
-	/* Mark threads which are still spinning in hold loops. */
-	if (cpu_has_feature(CPU_FTR_SMT)) {
-		for_each_present_cpu(i) { 
-			if (cpu_thread_in_core(i) == 0)
-				cpumask_set_cpu(i, of_spin_mask);
-		}
-	} else {
-		cpumask_copy(of_spin_mask, cpu_present_mask);
+	/*
+	 * Mark threads which are still spinning in hold loops
+	 *
+	 * We know prom_init will not have started them if RTAS supports
+	 * query-cpu-stopped-state.
+	 */
+	if (rtas_token("query-cpu-stopped-state") == RTAS_UNKNOWN_SERVICE) {
+		if (cpu_has_feature(CPU_FTR_SMT)) {
+			for_each_present_cpu(i) {
+				if (cpu_thread_in_core(i) == 0)
+					cpumask_set_cpu(i, of_spin_mask);
+			}
+		} else
+			cpumask_copy(of_spin_mask, cpu_present_mask);
+
+		cpumask_clear_cpu(boot_cpuid, of_spin_mask);
 	}
 
-	cpumask_clear_cpu(boot_cpuid, of_spin_mask);
-
 	/* Non-lpar has additional take/give timebase */
 	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
 		smp_ops->give_timebase = rtas_give_timebase;
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 5f997e7..16a2552 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -106,7 +106,7 @@ static int pseries_prepare_late(void)
 	atomic_set(&suspend_data.done, 0);
 	atomic_set(&suspend_data.error, 0);
 	suspend_data.complete = &suspend_work;
-	INIT_COMPLETION(suspend_work);
+	reinit_completion(&suspend_work);
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/wsp/chroma.c b/arch/powerpc/platforms/wsp/chroma.c
index 8ef53bc..aaa46b3 100644
--- a/arch/powerpc/platforms/wsp/chroma.c
+++ b/arch/powerpc/platforms/wsp/chroma.c
@@ -15,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/smp.h>
 #include <linux/time.h>
+#include <linux/of_fdt.h>
 
 #include <asm/machdep.h>
 #include <asm/udbg.h>
diff --git a/arch/powerpc/platforms/wsp/h8.c b/arch/powerpc/platforms/wsp/h8.c
index d18e6cc..a3c87f3 100644
--- a/arch/powerpc/platforms/wsp/h8.c
+++ b/arch/powerpc/platforms/wsp/h8.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/io.h>
+#include <linux/of_address.h>
 
 #include "wsp.h"
 
diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c
index 2d3b1dd..9cd92e6 100644
--- a/arch/powerpc/platforms/wsp/ics.c
+++ b/arch/powerpc/platforms/wsp/ics.c
@@ -18,6 +18,8 @@
 #include <linux/smp.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c
index cb565bf..3f67298 100644
--- a/arch/powerpc/platforms/wsp/opb_pic.c
+++ b/arch/powerpc/platforms/wsp/opb_pic.c
@@ -15,6 +15,8 @@
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/time.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
 
 #include <asm/reg_a2.h>
 #include <asm/irq.h>
diff --git a/arch/powerpc/platforms/wsp/psr2.c b/arch/powerpc/platforms/wsp/psr2.c
index 508ec82..a87b414 100644
--- a/arch/powerpc/platforms/wsp/psr2.c
+++ b/arch/powerpc/platforms/wsp/psr2.c
@@ -15,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/smp.h>
 #include <linux/time.h>
+#include <linux/of_fdt.h>
 
 #include <asm/machdep.h>
 #include <asm/udbg.h>
diff --git a/arch/powerpc/platforms/wsp/scom_smp.c b/arch/powerpc/platforms/wsp/scom_smp.c
index b56b70a..268bc89 100644
--- a/arch/powerpc/platforms/wsp/scom_smp.c
+++ b/arch/powerpc/platforms/wsp/scom_smp.c
@@ -116,7 +116,14 @@ static int a2_scom_ram(scom_map_t scom, int thread, u32 insn, int extmask)
 
 	scom_write(scom, SCOM_RAMIC, cmd);
 
-	while (!((val = scom_read(scom, SCOM_RAMC)) & mask)) {
+	for (;;) {
+		if (scom_read(scom, SCOM_RAMC, &val) != 0) {
+			pr_err("SCOM error on instruction 0x%08x, thread %d\n",
+			       insn, thread);
+			return -1;
+		}
+		if (val & mask)
+			break;
 		pr_devel("Waiting on RAMC = 0x%llx\n", val);
 		if (++n == 3) {
 			pr_err("RAMC timeout on instruction 0x%08x, thread %d\n",
@@ -151,9 +158,7 @@ static int a2_scom_getgpr(scom_map_t scom, int thread, int gpr, int alt,
 	if (rc)
 		return rc;
 
-	*out_gpr = scom_read(scom, SCOM_RAMD);
-
-	return 0;
+	return scom_read(scom, SCOM_RAMD, out_gpr);
 }
 
 static int a2_scom_getspr(scom_map_t scom, int thread, int spr, u64 *out_spr)
@@ -353,7 +358,10 @@ int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, struct device_node *np)
 
 	pr_devel("Bringing up CPU%d using SCOM...\n", lcpu);
 
-	pccr0 = scom_read(scom, SCOM_PCCR0);
+	if (scom_read(scom, SCOM_PCCR0, &pccr0) != 0) {
+		printk(KERN_ERR "XSCOM failure readng PCCR0 on CPU%d\n", lcpu);
+		return -1;
+	}
 	scom_write(scom, SCOM_PCCR0, pccr0 | SCOM_PCCR0_ENABLE_DEBUG |
 				     SCOM_PCCR0_ENABLE_RAM);
 
diff --git a/arch/powerpc/platforms/wsp/scom_wsp.c b/arch/powerpc/platforms/wsp/scom_wsp.c
index 4052e22..6538b4d 100644
--- a/arch/powerpc/platforms/wsp/scom_wsp.c
+++ b/arch/powerpc/platforms/wsp/scom_wsp.c
@@ -14,6 +14,7 @@
 #include <linux/of.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
+#include <linux/of_address.h>
 
 #include <asm/cputhreads.h>
 #include <asm/reg_a2.h>
@@ -50,18 +51,22 @@ static void wsp_scom_unmap(scom_map_t map)
 	iounmap((void *)map);
 }
 
-static u64 wsp_scom_read(scom_map_t map, u32 reg)
+static int wsp_scom_read(scom_map_t map, u64 reg, u64 *value)
 {
 	u64 __iomem *addr = (u64 __iomem *)map;
 
-	return in_be64(addr + reg);
+	*value = in_be64(addr + reg);
+
+	return 0;
 }
 
-static void wsp_scom_write(scom_map_t map, u32 reg, u64 value)
+static int wsp_scom_write(scom_map_t map, u64 reg, u64 value)
 {
 	u64 __iomem *addr = (u64 __iomem *)map;
 
-	return out_be64(addr + reg, value);
+	out_be64(addr + reg, value);
+
+	return 0;
 }
 
 static const struct scom_controller wsp_scom_controller = {
diff --git a/arch/powerpc/platforms/wsp/wsp.c b/arch/powerpc/platforms/wsp/wsp.c
index d25cc96..58cd1f0 100644
--- a/arch/powerpc/platforms/wsp/wsp.c
+++ b/arch/powerpc/platforms/wsp/wsp.c
@@ -13,6 +13,7 @@
 #include <linux/smp.h>
 #include <linux/delay.h>
 #include <linux/time.h>
+#include <linux/of_address.h>
 
 #include <asm/scom.h>
 
@@ -89,6 +90,7 @@ void wsp_halt(void)
 	struct device_node *dn;
 	struct device_node *mine;
 	struct device_node *me;
+	int rc;
 
 	me = of_get_cpu_node(smp_processor_id(), NULL);
 	mine = scom_find_parent(me);
@@ -101,15 +103,15 @@ void wsp_halt(void)
 
 		/* read-modify-write it so the HW probe does not get
 		 * confused */
-		val = scom_read(m, 0);
-		val |= 1;
-		scom_write(m, 0, val);
+		rc = scom_read(m, 0, &val);
+		if (rc == 0)
+			scom_write(m, 0, val | 1);
 		scom_unmap(m);
 	}
 	m = scom_map(mine, 0, 1);
-	val = scom_read(m, 0);
-	val |= 1;
-	scom_write(m, 0, val);
+	rc = scom_read(m, 0, &val);
+	if (rc == 0)
+		scom_write(m, 0, val | 1);
 	/* should never return */
 	scom_unmap(m);
 }
author	Scott Wood <scottwood@freescale.com>	2013-12-14 01:15:24 (GMT)
committer	Scott Wood <scottwood@freescale.com>	2013-12-14 01:15:24 (GMT)
commit	b7c81aa3ab2ac2c140e278b6d0e9a0b95112cf0b (patch)
tree	87828aaf5f82c7042bfc0307bc4ac499e10f93fb /arch/powerpc/platforms
parent	22c782a4b14773fab7eab3c1db54ad7ad077e9b8 (diff)
parent	78fd82238d0e5716578c326404184a27ba67fd6e (diff)
download	linux-fsl-qoriq-b7c81aa3ab2ac2c140e278b6d0e9a0b95112cf0b.tar.xz