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

Pull powerpc updates from Benjamin Herrenschmidt:
 "Some highlights in addition to the usual batch of fixes:

   - 64TB address space support for 64-bit processes by Aneesh Kumar

   - Gavin Shan did a major cleanup & re-organization of our EEH support
     code (IBM fancy PCI error handling & recovery infrastructure) which
     paves the way for supporting different platform backends, along
     with some rework of the PCIe code for the PowerNV platform in order
     to remove home made resource allocations and instead use the
     generic code (which is possible after some small improvements to it
     done by Gavin).

   - Uprobes support by Ananth N Mavinakayanahalli

   - A pile of embedded updates from Freescale folks, including new SoC
     and board supports, more KVM stuff including preparing for 64-bit
     BookE KVM support, ePAPR 1.1 updates, etc..."

Fixup trivial conflicts in drivers/scsi/ipr.c

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (146 commits)
  powerpc/iommu: Fix multiple issues with IOMMU pools code
  powerpc: Fix VMX fix for memcpy case
  driver/mtd:IFC NAND:Initialise internal SRAM before any write
  powerpc/fsl-pci: use 'Header Type' to identify PCIE mode
  powerpc/eeh: Don't release eeh_mutex in eeh_phb_pe_get
  powerpc: Remove tlb batching hack for nighthawk
  powerpc: Set paca->data_offset = 0 for boot cpu
  powerpc/perf: Sample only if SIAR-Valid bit is set in P7+
  powerpc/fsl-pci: fix warning when CONFIG_SWIOTLB is disabled
  powerpc/mpc85xx: Update interrupt handling for IFC controller
  powerpc/85xx: Enable USB support in p1023rds_defconfig
  powerpc/smp: Do not disable IPI interrupts during suspend
  powerpc/eeh: Fix crash on converting OF node to edev
  powerpc/eeh: Lock module while handling EEH event
  powerpc/kprobe: Don't emulate store when kprobe stwu r1
  powerpc/kprobe: Complete kprobe and migrate exception frame
  powerpc/kprobe: Introduce a new thread flag
  powerpc: Remove unused __get_user64() and __put_user64()
  powerpc/eeh: Global mutex to protect PE tree
  powerpc/eeh: Remove EEH PE for normal PCI hotplug
  ...

64 files changed, 2184 insertions, 1845 deletions

diff --git a/arch/powerpc/platforms/44x/currituck.c b/arch/powerpc/platforms/44x/currituck.c
index 9f6c33d..6bd89a0 100644
--- a/arch/powerpc/platforms/44x/currituck.c
+++ b/arch/powerpc/platforms/44x/currituck.c
@@ -21,7 +21,6 @@
  */
 
 #include <linux/init.h>
-#include <linux/memblock.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/rtc.h>
@@ -159,13 +158,8 @@ static void __init ppc47x_setup_arch(void)
 
 	/* No need to check the DMA config as we /know/ our windows are all of
  	 * RAM.  Lets hope that doesn't change */
-#ifdef CONFIG_SWIOTLB
-	if ((memblock_end_of_DRAM() - 1) > 0xffffffff) {
-		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_dma_ops);
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
-	}
-#endif
+	swiotlb_detect_4g();
+
 	ppc47x_smp_init();
 }
 
diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig
index c169998..b62508b 100644
--- a/arch/powerpc/platforms/512x/Kconfig
+++ b/arch/powerpc/platforms/512x/Kconfig
@@ -2,6 +2,7 @@ config PPC_MPC512x
 	bool "512x-based boards"
 	depends on 6xx
 	select FSL_SOC
+	select FB_FSL_DIU
 	select IPIC
 	select PPC_CLOCK
 	select PPC_PCI_CHOICE
diff --git a/arch/powerpc/platforms/512x/clock.c b/arch/powerpc/platforms/512x/clock.c
index 1d8700f..9f771e0 100644
--- a/arch/powerpc/platforms/512x/clock.c
+++ b/arch/powerpc/platforms/512x/clock.c
@@ -54,14 +54,16 @@ static DEFINE_MUTEX(clocks_mutex);
 static struct clk *mpc5121_clk_get(struct device *dev, const char *id)
 {
 	struct clk *p, *clk = ERR_PTR(-ENOENT);
-	int dev_match = 0;
-	int id_match = 0;
+	int dev_match;
+	int id_match;
 
 	if (dev == NULL || id == NULL)
 		return clk;
 
 	mutex_lock(&clocks_mutex);
 	list_for_each_entry(p, &clocks, node) {
+		dev_match = id_match = 0;
+
 		if (dev == p->dev)
 			dev_match++;
 		if (strcmp(id, p->name) == 0)
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index cfe958e..1650e09 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -191,8 +191,6 @@ mpc512x_valid_monitor_port(enum fsl_diu_monitor_port port)
 
 static struct fsl_diu_shared_fb __attribute__ ((__aligned__(8))) diu_shared_fb;
 
-#if defined(CONFIG_FB_FSL_DIU) || \
-    defined(CONFIG_FB_FSL_DIU_MODULE)
 static inline void mpc512x_free_bootmem(struct page *page)
 {
 	__ClearPageReserved(page);
@@ -220,7 +218,6 @@ void mpc512x_release_bootmem(void)
 	}
 	diu_ops.release_bootmem	= NULL;
 }
-#endif
 
 /*
  * Check if DIU was pre-initialized. If so, perform steps
@@ -323,15 +320,12 @@ void __init mpc512x_setup_diu(void)
 		}
 	}
 
-#if defined(CONFIG_FB_FSL_DIU) || \
-    defined(CONFIG_FB_FSL_DIU_MODULE)
 	diu_ops.get_pixel_format	= mpc512x_get_pixel_format;
 	diu_ops.set_gamma_table		= mpc512x_set_gamma_table;
 	diu_ops.set_monitor_port	= mpc512x_set_monitor_port;
 	diu_ops.set_pixel_clock		= mpc512x_set_pixel_clock;
 	diu_ops.valid_monitor_port	= mpc512x_valid_monitor_port;
 	diu_ops.release_bootmem		= mpc512x_release_bootmem;
-#endif
 }
 
 void __init mpc512x_init_IRQ(void)
diff --git a/arch/powerpc/platforms/52xx/mpc5200_simple.c b/arch/powerpc/platforms/52xx/mpc5200_simple.c
index c0aa040..9cf3602 100644
--- a/arch/powerpc/platforms/52xx/mpc5200_simple.c
+++ b/arch/powerpc/platforms/52xx/mpc5200_simple.c
@@ -52,6 +52,7 @@ static void __init mpc5200_simple_setup_arch(void)
 static const char *board[] __initdata = {
 	"anonymous,a4m072",
 	"anon,charon",
+	"ifm,o2d",
 	"intercontrol,digsy-mtc",
 	"manroland,mucmc52",
 	"manroland,uc101",
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
index d61fb1c..2351f9e 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
@@ -170,7 +170,8 @@ static void mpc52xx_lpbfifo_kick(struct mpc52xx_lpbfifo_request *req)
 	out_be32(lpbfifo.regs + LPBFIFO_REG_CONTROL, bit_fields);
 
 	/* Kick it off */
-	out_8(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, 0x01);
+	if (!lpbfifo.req->defer_xfer_start)
+		out_8(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, 0x01);
 	if (dma)
 		bcom_enable(lpbfifo.bcom_cur_task);
 }
@@ -421,6 +422,38 @@ int mpc52xx_lpbfifo_submit(struct mpc52xx_lpbfifo_request *req)
 }
 EXPORT_SYMBOL(mpc52xx_lpbfifo_submit);
 
+int mpc52xx_lpbfifo_start_xfer(struct mpc52xx_lpbfifo_request *req)
+{
+	unsigned long flags;
+
+	if (!lpbfifo.regs)
+		return -ENODEV;
+
+	spin_lock_irqsave(&lpbfifo.lock, flags);
+
+	/*
+	 * If the req pointer is already set and a transfer was
+	 * started on submit, then this transfer is in progress
+	 */
+	if (lpbfifo.req && !lpbfifo.req->defer_xfer_start) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+		return -EBUSY;
+	}
+
+	/*
+	 * If the req was previously submitted but not
+	 * started, start it now
+	 */
+	if (lpbfifo.req && lpbfifo.req == req &&
+	    lpbfifo.req->defer_xfer_start) {
+		out_8(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, 0x01);
+	}
+
+	spin_unlock_irqrestore(&lpbfifo.lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL(mpc52xx_lpbfifo_start_xfer);
+
 void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req)
 {
 	unsigned long flags;
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 159c01e..02d02a0 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -104,6 +104,13 @@ config P1022_DS
 	help
 	  This option enables support for the Freescale P1022DS reference board.
 
+config P1022_RDK
+	bool "Freescale / iVeia P1022 RDK"
+	select DEFAULT_UIMAGE
+	help
+	  This option enables support for the Freescale / iVeia P1022RDK
+	  reference board.
+
 config P1023_RDS
 	bool "Freescale P1023 RDS"
 	select DEFAULT_UIMAGE
@@ -254,6 +261,20 @@ config P5020_DS
 	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
+	help
+	  This option enables support for the P5040 DS board
+
 config PPC_QEMU_E500
 	bool "QEMU generic e500 platform"
 	depends on EXPERIMENTAL
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index 3dfe811..76f679c 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -15,11 +15,13 @@ obj-$(CONFIG_MPC85xx_MDS) += mpc85xx_mds.o
 obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o
 obj-$(CONFIG_P1010_RDB)   += p1010rdb.o
 obj-$(CONFIG_P1022_DS)    += p1022_ds.o
+obj-$(CONFIG_P1022_RDK)   += p1022_rdk.o
 obj-$(CONFIG_P1023_RDS)   += p1023_rds.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_STX_GP3)	  += stx_gp3.o
 obj-$(CONFIG_TQM85xx)	  += tqm85xx.o
 obj-$(CONFIG_SBC8548)     += sbc8548.o
diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c
index 67dac22..d0861a0 100644
--- a/arch/powerpc/platforms/85xx/common.c
+++ b/arch/powerpc/platforms/85xx/common.c
@@ -27,6 +27,16 @@ static struct of_device_id __initdata mpc85xx_common_ids[] = {
 	{ .compatible = "fsl,mpc8548-guts", },
 	/* Probably unnecessary? */
 	{ .compatible = "gpio-leds", },
+	/* For all PCI controllers */
+	{ .compatible = "fsl,mpc8540-pci", },
+	{ .compatible = "fsl,mpc8548-pcie", },
+	{ .compatible = "fsl,p1022-pcie", },
+	{ .compatible = "fsl,p1010-pcie", },
+	{ .compatible = "fsl,p1023-pcie", },
+	{ .compatible = "fsl,p4080-pcie", },
+	{ .compatible = "fsl,qoriq-pcie-v2.4", },
+	{ .compatible = "fsl,qoriq-pcie-v2.3", },
+	{ .compatible = "fsl,qoriq-pcie-v2.2", },
 	{},
 };
 
diff --git a/arch/powerpc/platforms/85xx/corenet_ds.c b/arch/powerpc/platforms/85xx/corenet_ds.c
index 925b028..ed69c92 100644
--- a/arch/powerpc/platforms/85xx/corenet_ds.c
+++ b/arch/powerpc/platforms/85xx/corenet_ds.c
@@ -16,7 +16,6 @@
 #include <linux/kdev_t.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
-#include <linux/memblock.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
@@ -52,37 +51,16 @@ void __init corenet_ds_pic_init(void)
  */
 void __init corenet_ds_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-	struct pci_controller *hose;
-#endif
-	dma_addr_t max = 0xffffffff;
-
 	mpc85xx_smp_init();
 
-#ifdef CONFIG_PCI
-	for_each_node_by_type(np, "pci") {
-		if (of_device_is_compatible(np, "fsl,p4080-pcie") ||
-		    of_device_is_compatible(np, "fsl,qoriq-pcie-v2.2")) {
-			fsl_add_bridge(np, 0);
-			hose = pci_find_hose_for_OF_device(np);
-			max = min(max, hose->dma_window_base_cur +
-					hose->dma_window_size);
-		}
-	}
-
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PCI) && defined(CONFIG_PPC64)
 	pci_devs_phb_init();
 #endif
-#endif
 
-#ifdef CONFIG_SWIOTLB
-	if ((memblock_end_of_DRAM() - 1) > max) {
-		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_dma_ops);
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
-	}
-#endif
+	fsl_pci_assign_primary();
+
+	swiotlb_detect_4g();
+
 	pr_info("%s board from Freescale Semiconductor\n", ppc_md.name);
 }
 
@@ -99,6 +77,12 @@ static const struct of_device_id of_device_ids[] __devinitconst = {
 	{
 		.compatible	= "fsl,qoriq-pcie-v2.2",
 	},
+	{
+		.compatible	= "fsl,qoriq-pcie-v2.3",
+	},
+	{
+		.compatible	= "fsl,qoriq-pcie-v2.4",
+	},
 	/* The following two are for the Freescale hypervisor */
 	{
 		.name		= "hypervisor",
diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c
index b6a728b..e6285ae 100644
--- a/arch/powerpc/platforms/85xx/ge_imp3a.c
+++ b/arch/powerpc/platforms/85xx/ge_imp3a.c
@@ -22,7 +22,6 @@
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/of_platform.h>
-#include <linux/memblock.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
@@ -84,53 +83,39 @@ void __init ge_imp3a_pic_init(void)
 	of_node_put(cascade_node);
 }
 
-#ifdef CONFIG_PCI
-static int primary_phb_addr;
-#endif	/* CONFIG_PCI */
-
-/*
- * Setup the architecture
- */
-static void __init ge_imp3a_setup_arch(void)
+static void ge_imp3a_pci_assign_primary(void)
 {
-	struct device_node *regs;
 #ifdef CONFIG_PCI
 	struct device_node *np;
-	struct pci_controller *hose;
-#endif
-	dma_addr_t max = 0xffffffff;
+	struct resource rsrc;
 
-	if (ppc_md.progress)
-		ppc_md.progress("ge_imp3a_setup_arch()", 0);
-
-#ifdef CONFIG_PCI
 	for_each_node_by_type(np, "pci") {
 		if (of_device_is_compatible(np, "fsl,mpc8540-pci") ||
 		    of_device_is_compatible(np, "fsl,mpc8548-pcie") ||
 		    of_device_is_compatible(np, "fsl,p2020-pcie")) {
-			struct resource rsrc;
 			of_address_to_resource(np, 0, &rsrc);
-			if ((rsrc.start & 0xfffff) == primary_phb_addr)
-				fsl_add_bridge(np, 1);
-			else
-				fsl_add_bridge(np, 0);
-
-			hose = pci_find_hose_for_OF_device(np);
-			max = min(max, hose->dma_window_base_cur +
-					hose->dma_window_size);
+			if ((rsrc.start & 0xfffff) == 0x9000)
+				fsl_pci_primary = np;
 		}
 	}
 #endif
+}
+
+/*
+ * Setup the architecture
+ */
+static void __init ge_imp3a_setup_arch(void)
+{
+	struct device_node *regs;
+
+	if (ppc_md.progress)
+		ppc_md.progress("ge_imp3a_setup_arch()", 0);
 
 	mpc85xx_smp_init();
 
-#ifdef CONFIG_SWIOTLB
-	if ((memblock_end_of_DRAM() - 1) > max) {
-		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_dma_ops);
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
-	}
-#endif
+	ge_imp3a_pci_assign_primary();
+
+	swiotlb_detect_4g();
 
 	/* Remap basic board registers */
 	regs = of_find_compatible_node(NULL, NULL, "ge,imp3a-fpga-regs");
@@ -215,17 +200,10 @@ static int __init ge_imp3a_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
 
-	if (of_flat_dt_is_compatible(root, "ge,IMP3A")) {
-#ifdef CONFIG_PCI
-		primary_phb_addr = 0x9000;
-#endif
-		return 1;
-	}
-
-	return 0;
+	return of_flat_dt_is_compatible(root, "ge,IMP3A");
 }
 
-machine_device_initcall(ge_imp3a, mpc85xx_common_publish_devices);
+machine_arch_initcall(ge_imp3a, mpc85xx_common_publish_devices);
 
 machine_arch_initcall(ge_imp3a, swiotlb_setup_bus_notifier);
 
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index 767c7cf..15ce4b5 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -17,7 +17,6 @@
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/of_platform.h>
-#include <linux/memblock.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
@@ -46,46 +45,17 @@ void __init mpc8536_ds_pic_init(void)
  */
 static void __init mpc8536_ds_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-	struct pci_controller *hose;
-#endif
-	dma_addr_t max = 0xffffffff;
-
 	if (ppc_md.progress)
 		ppc_md.progress("mpc8536_ds_setup_arch()", 0);
 
-#ifdef CONFIG_PCI
-	for_each_node_by_type(np, "pci") {
-		if (of_device_is_compatible(np, "fsl,mpc8540-pci") ||
-		    of_device_is_compatible(np, "fsl,mpc8548-pcie")) {
-			struct resource rsrc;
-			of_address_to_resource(np, 0, &rsrc);
-			if ((rsrc.start & 0xfffff) == 0x8000)
-				fsl_add_bridge(np, 1);
-			else
-				fsl_add_bridge(np, 0);
-
-			hose = pci_find_hose_for_OF_device(np);
-			max = min(max, hose->dma_window_base_cur +
-					hose->dma_window_size);
-		}
-	}
-
-#endif
+	fsl_pci_assign_primary();
 
-#ifdef CONFIG_SWIOTLB
-	if ((memblock_end_of_DRAM() - 1) > max) {
-		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_dma_ops);
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
-	}
-#endif
+	swiotlb_detect_4g();
 
 	printk("MPC8536 DS board from Freescale Semiconductor\n");
 }
 
-machine_device_initcall(mpc8536_ds, mpc85xx_common_publish_devices);
+machine_arch_initcall(mpc8536_ds, mpc85xx_common_publish_devices);
 
 machine_arch_initcall(mpc8536_ds, swiotlb_setup_bus_notifier);
 
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
index 29ee8fc..7d12a19 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
@@ -137,10 +137,6 @@ static void __init init_ioports(void)
 
 static void __init mpc85xx_ads_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-#endif
-
 	if (ppc_md.progress)
 		ppc_md.progress("mpc85xx_ads_setup_arch()", 0);
 
@@ -150,11 +146,10 @@ static void __init mpc85xx_ads_setup_arch(void)
 #endif
 
 #ifdef CONFIG_PCI
-	for_each_compatible_node(np, "pci", "fsl,mpc8540-pci")
-		fsl_add_bridge(np, 1);
-
 	ppc_md.pci_exclude_device = mpc85xx_exclude_device;
 #endif
+
+	fsl_pci_assign_primary();
 }
 
 static void mpc85xx_ads_show_cpuinfo(struct seq_file *m)
@@ -173,7 +168,7 @@ static void mpc85xx_ads_show_cpuinfo(struct seq_file *m)
 	seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f));
 }
 
-machine_device_initcall(mpc85xx_ads, mpc85xx_common_publish_devices);
+machine_arch_initcall(mpc85xx_ads, mpc85xx_common_publish_devices);
 
 /*
  * Called very early, device-tree isn't unflattened
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
index 11156fb..c474505 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
@@ -276,6 +276,33 @@ machine_device_initcall(mpc85xx_cds, mpc85xx_cds_8259_attach);
 
 #endif /* CONFIG_PPC_I8259 */
 
+static void mpc85xx_cds_pci_assign_primary(void)
+{
+#ifdef CONFIG_PCI
+	struct device_node *np;
+
+	if (fsl_pci_primary)
+		return;
+
+	/*
+	 * MPC85xx_CDS has ISA bridge but unfortunately there is no
+	 * isa node in device tree. We now looking for i8259 node as
+	 * a workaround for such a broken device tree. This routine
+	 * is for complying to all device trees.
+	 */
+	np = of_find_node_by_name(NULL, "i8259");
+	while ((fsl_pci_primary = of_get_parent(np))) {
+		of_node_put(np);
+		np = fsl_pci_primary;
+
+		if ((of_device_is_compatible(np, "fsl,mpc8540-pci") ||
+		    of_device_is_compatible(np, "fsl,mpc8548-pcie")) &&
+		    of_device_is_available(np))
+			return;
+	}
+#endif
+}
+
 /*
  * Setup the architecture
  */
@@ -309,21 +336,12 @@ static void __init mpc85xx_cds_setup_arch(void)
 	}
 
 #ifdef CONFIG_PCI
-	for_each_node_by_type(np, "pci") {
-		if (of_device_is_compatible(np, "fsl,mpc8540-pci") ||
-		    of_device_is_compatible(np, "fsl,mpc8548-pcie")) {
-			struct resource rsrc;
-			of_address_to_resource(np, 0, &rsrc);
-			if ((rsrc.start & 0xfffff) == 0x8000)
-				fsl_add_bridge(np, 1);
-			else
-				fsl_add_bridge(np, 0);
-		}
-	}
-
 	ppc_md.pci_irq_fixup = mpc85xx_cds_pci_irq_fixup;
 	ppc_md.pci_exclude_device = mpc85xx_exclude_device;
 #endif
+
+	mpc85xx_cds_pci_assign_primary();
+	fsl_pci_assign_primary();
 }
 
 static void mpc85xx_cds_show_cpuinfo(struct seq_file *m)
@@ -355,7 +373,7 @@ static int __init mpc85xx_cds_probe(void)
         return of_flat_dt_is_compatible(root, "MPC85xxCDS");
 }
 
-machine_device_initcall(mpc85xx_cds, mpc85xx_common_publish_devices);
+machine_arch_initcall(mpc85xx_cds, mpc85xx_common_publish_devices);
 
 define_machine(mpc85xx_cds) {
 	.name		= "MPC85xx CDS",
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index 6d3265f..9ebb91e 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -20,7 +20,6 @@
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/of_platform.h>
-#include <linux/memblock.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
@@ -129,13 +128,11 @@ static int mpc85xx_exclude_device(struct pci_controller *hose,
 }
 #endif	/* CONFIG_PCI */
 
-static void __init mpc85xx_ds_pci_init(void)
+static void __init mpc85xx_ds_uli_init(void)
 {
 #ifdef CONFIG_PCI
 	struct device_node *node;
 
-	fsl_pci_init();
-
 	/* See if we have a ULI under the primary */
 
 	node = of_find_node_by_name(NULL, "uli1575");
@@ -159,7 +156,9 @@ static void __init mpc85xx_ds_setup_arch(void)
 	if (ppc_md.progress)
 		ppc_md.progress("mpc85xx_ds_setup_arch()", 0);
 
-	mpc85xx_ds_pci_init();
+	swiotlb_detect_4g();
+	fsl_pci_assign_primary();
+	mpc85xx_ds_uli_init();
 	mpc85xx_smp_init();
 
 	printk("MPC85xx DS board from Freescale Semiconductor\n");
@@ -175,9 +174,9 @@ static int __init mpc8544_ds_probe(void)
 	return !!of_flat_dt_is_compatible(root, "MPC8544DS");
 }
 
-machine_device_initcall(mpc8544_ds, mpc85xx_common_publish_devices);
-machine_device_initcall(mpc8572_ds, mpc85xx_common_publish_devices);
-machine_device_initcall(p2020_ds, mpc85xx_common_publish_devices);
+machine_arch_initcall(mpc8544_ds, mpc85xx_common_publish_devices);
+machine_arch_initcall(mpc8572_ds, mpc85xx_common_publish_devices);
+machine_arch_initcall(p2020_ds, mpc85xx_common_publish_devices);
 
 machine_arch_initcall(mpc8544_ds, swiotlb_setup_bus_notifier);
 machine_arch_initcall(mpc8572_ds, swiotlb_setup_bus_notifier);
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index 8e4b094..8498f73 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -327,44 +327,16 @@ static void __init mpc85xx_mds_qeic_init(void) { }
 
 static void __init mpc85xx_mds_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct pci_controller *hose;
-	struct device_node *np;
-#endif
-	dma_addr_t max = 0xffffffff;
-
 	if (ppc_md.progress)
 		ppc_md.progress("mpc85xx_mds_setup_arch()", 0);
 
-#ifdef CONFIG_PCI
-	for_each_node_by_type(np, "pci") {
-		if (of_device_is_compatible(np, "fsl,mpc8540-pci") ||
-		    of_device_is_compatible(np, "fsl,mpc8548-pcie")) {
-			struct resource rsrc;
-			of_address_to_resource(np, 0, &rsrc);
-			if ((rsrc.start & 0xfffff) == 0x8000)
-				fsl_add_bridge(np, 1);
-			else
-				fsl_add_bridge(np, 0);
-
-			hose = pci_find_hose_for_OF_device(np);
-			max = min(max, hose->dma_window_base_cur +
-					hose->dma_window_size);
-		}
-	}
-#endif
-
 	mpc85xx_smp_init();
 
 	mpc85xx_mds_qe_init();
 
-#ifdef CONFIG_SWIOTLB
-	if ((memblock_end_of_DRAM() - 1) > max) {
-		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_dma_ops);
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
-	}
-#endif
+	fsl_pci_assign_primary();
+
+	swiotlb_detect_4g();
 }
 
 
@@ -409,9 +381,9 @@ static int __init mpc85xx_publish_devices(void)
 	return mpc85xx_common_publish_devices();
 }
 
-machine_device_initcall(mpc8568_mds, mpc85xx_publish_devices);
-machine_device_initcall(mpc8569_mds, mpc85xx_publish_devices);
-machine_device_initcall(p1021_mds, mpc85xx_common_publish_devices);
+machine_arch_initcall(mpc8568_mds, mpc85xx_publish_devices);
+machine_arch_initcall(mpc8569_mds, mpc85xx_publish_devices);
+machine_arch_initcall(p1021_mds, mpc85xx_common_publish_devices);
 
 machine_arch_initcall(mpc8568_mds, swiotlb_setup_bus_notifier);
 machine_arch_initcall(mpc8569_mds, swiotlb_setup_bus_notifier);
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index 1910fdc..ede8771 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -86,23 +86,17 @@ void __init mpc85xx_rdb_pic_init(void)
  */
 static void __init mpc85xx_rdb_setup_arch(void)
 {
-#if defined(CONFIG_PCI) || defined(CONFIG_QUICC_ENGINE)
+#ifdef CONFIG_QUICC_ENGINE
 	struct device_node *np;
 #endif
 
 	if (ppc_md.progress)
 		ppc_md.progress("mpc85xx_rdb_setup_arch()", 0);
 
-#ifdef CONFIG_PCI
-	for_each_node_by_type(np, "pci") {
-		if (of_device_is_compatible(np, "fsl,mpc8548-pcie"))
-			fsl_add_bridge(np, 0);
-	}
-
-#endif
-
 	mpc85xx_smp_init();
 
+	fsl_pci_assign_primary();
+
 #ifdef CONFIG_QUICC_ENGINE
 	np = of_find_compatible_node(NULL, NULL, "fsl,qe");
 	if (!np) {
@@ -161,15 +155,15 @@ qe_fail:
 	printk(KERN_INFO "MPC85xx RDB board from Freescale Semiconductor\n");
 }
 
-machine_device_initcall(p2020_rdb, mpc85xx_common_publish_devices);
-machine_device_initcall(p2020_rdb_pc, mpc85xx_common_publish_devices);
-machine_device_initcall(p1020_mbg_pc, mpc85xx_common_publish_devices);
-machine_device_initcall(p1020_rdb, mpc85xx_common_publish_devices);
-machine_device_initcall(p1020_rdb_pc, mpc85xx_common_publish_devices);
-machine_device_initcall(p1020_utm_pc, mpc85xx_common_publish_devices);
-machine_device_initcall(p1021_rdb_pc, mpc85xx_common_publish_devices);
-machine_device_initcall(p1025_rdb, mpc85xx_common_publish_devices);
-machine_device_initcall(p1024_rdb, mpc85xx_common_publish_devices);
+machine_arch_initcall(p2020_rdb, mpc85xx_common_publish_devices);
+machine_arch_initcall(p2020_rdb_pc, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1020_mbg_pc, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1020_rdb, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1020_rdb_pc, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1020_utm_pc, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1021_rdb_pc, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1025_rdb, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1024_rdb, mpc85xx_common_publish_devices);
 
 /*
  * Called very early, device-tree isn't unflattened
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index dbaf443..0252961 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -46,25 +46,15 @@ void __init p1010_rdb_pic_init(void)
  */
 static void __init p1010_rdb_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-#endif
-
 	if (ppc_md.progress)
 		ppc_md.progress("p1010_rdb_setup_arch()", 0);
 
-#ifdef CONFIG_PCI
-	for_each_node_by_type(np, "pci") {
-		if (of_device_is_compatible(np, "fsl,p1010-pcie"))
-			fsl_add_bridge(np, 0);
-	}
-
-#endif
+	fsl_pci_assign_primary();
 
 	printk(KERN_INFO "P1010 RDB board from Freescale Semiconductor\n");
 }
 
-machine_device_initcall(p1010_rdb, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1010_rdb, mpc85xx_common_publish_devices);
 machine_arch_initcall(p1010_rdb, swiotlb_setup_bus_notifier);
 
 /*
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 3c732ac..848a3e9 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -18,7 +18,6 @@
 
 #include <linux/pci.h>
 #include <linux/of_platform.h>
-#include <linux/memblock.h>
 #include <asm/div64.h>
 #include <asm/mpic.h>
 #include <asm/swiotlb.h>
@@ -507,32 +506,9 @@ early_param("video", early_video_setup);
  */
 static void __init p1022_ds_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-#endif
-	dma_addr_t max = 0xffffffff;
-
 	if (ppc_md.progress)
 		ppc_md.progress("p1022_ds_setup_arch()", 0);
 
-#ifdef CONFIG_PCI
-	for_each_compatible_node(np, "pci", "fsl,p1022-pcie") {
-		struct resource rsrc;
-		struct pci_controller *hose;
-
-		of_address_to_resource(np, 0, &rsrc);
-
-		if ((rsrc.start & 0xfffff) == 0x8000)
-			fsl_add_bridge(np, 1);
-		else
-			fsl_add_bridge(np, 0);
-
-		hose = pci_find_hose_for_OF_device(np);
-		max = min(max, hose->dma_window_base_cur +
-			  hose->dma_window_size);
-	}
-#endif
-
 #if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
 	diu_ops.get_pixel_format	= p1022ds_get_pixel_format;
 	diu_ops.set_gamma_table		= p1022ds_set_gamma_table;
@@ -601,18 +577,14 @@ static void __init p1022_ds_setup_arch(void)
 
 	mpc85xx_smp_init();
 
-#ifdef CONFIG_SWIOTLB
-	if ((memblock_end_of_DRAM() - 1) > max) {
-		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_dma_ops);
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
-	}
-#endif
+	fsl_pci_assign_primary();
+
+	swiotlb_detect_4g();
 
 	pr_info("Freescale P1022 DS reference board\n");
 }
 
-machine_device_initcall(p1022_ds, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1022_ds, mpc85xx_common_publish_devices);
 
 machine_arch_initcall(p1022_ds, swiotlb_setup_bus_notifier);
 
diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c
new file mode 100644
index 0000000..55ffa1c
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/p1022_rdk.c
@@ -0,0 +1,167 @@
+/*
+ * P1022 RDK board specific routines
+ *
+ * Copyright 2012 Freescale Semiconductor, Inc.
+ *
+ * Author: Timur Tabi <timur@freescale.com>
+ *
+ * Based on p1022_ds.c
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include <linux/pci.h>
+#include <linux/of_platform.h>
+#include <asm/div64.h>
+#include <asm/mpic.h>
+#include <asm/swiotlb.h>
+
+#include <sysdev/fsl_soc.h>
+#include <sysdev/fsl_pci.h>
+#include <asm/udbg.h>
+#include <asm/fsl_guts.h>
+#include "smp.h"
+
+#include "mpc85xx.h"
+
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+
+/* DIU Pixel Clock bits of the CLKDVDR Global Utilities register */
+#define CLKDVDR_PXCKEN		0x80000000
+#define CLKDVDR_PXCKINV		0x10000000
+#define CLKDVDR_PXCKDLY		0x06000000
+#define CLKDVDR_PXCLK_MASK	0x00FF0000
+
+/**
+ * p1022rdk_set_monitor_port: switch the output to a different monitor port
+ */
+static void p1022rdk_set_monitor_port(enum fsl_diu_monitor_port port)
+{
+	if (port != FSL_DIU_PORT_DVI) {
+		pr_err("p1022rdk: unsupported monitor port %i\n", port);
+		return;
+	}
+}
+
+/**
+ * p1022rdk_set_pixel_clock: program the DIU's clock
+ *
+ * @pixclock: the wavelength, in picoseconds, of the clock
+ */
+void p1022rdk_set_pixel_clock(unsigned int pixclock)
+{
+	struct device_node *guts_np = NULL;
+	struct ccsr_guts __iomem *guts;
+	unsigned long freq;
+	u64 temp;
+	u32 pxclk;
+
+	/* Map the global utilities registers. */
+	guts_np = of_find_compatible_node(NULL, NULL, "fsl,p1022-guts");
+	if (!guts_np) {
+		pr_err("p1022rdk: missing global utilties device node\n");
+		return;
+	}
+
+	guts = of_iomap(guts_np, 0);
+	of_node_put(guts_np);
+	if (!guts) {
+		pr_err("p1022rdk: could not map global utilties device\n");
+		return;
+	}
+
+	/* Convert pixclock from a wavelength to a frequency */
+	temp = 1000000000000ULL;
+	do_div(temp, pixclock);
+	freq = temp;
+
+	/*
+	 * 'pxclk' is the ratio of the platform clock to the pixel clock.
+	 * This number is programmed into the CLKDVDR register, and the valid
+	 * range of values is 2-255.
+	 */
+	pxclk = DIV_ROUND_CLOSEST(fsl_get_sys_freq(), freq);
+	pxclk = clamp_t(u32, pxclk, 2, 255);
+
+	/* Disable the pixel clock, and set it to non-inverted and no delay */
+	clrbits32(&guts->clkdvdr,
+		  CLKDVDR_PXCKEN | CLKDVDR_PXCKDLY | CLKDVDR_PXCLK_MASK);
+
+	/* Enable the clock and set the pxclk */
+	setbits32(&guts->clkdvdr, CLKDVDR_PXCKEN | (pxclk << 16));
+
+	iounmap(guts);
+}
+
+/**
+ * p1022rdk_valid_monitor_port: set the monitor port for sysfs
+ */
+enum fsl_diu_monitor_port
+p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port)
+{
+	return FSL_DIU_PORT_DVI;
+}
+
+#endif
+
+void __init p1022_rdk_pic_init(void)
+{
+	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+		MPIC_SINGLE_DEST_CPU,
+		0, 256, " OpenPIC  ");
+	BUG_ON(mpic == NULL);
+	mpic_init(mpic);
+}
+
+/*
+ * Setup the architecture
+ */
+static void __init p1022_rdk_setup_arch(void)
+{
+	if (ppc_md.progress)
+		ppc_md.progress("p1022_rdk_setup_arch()", 0);
+
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+	diu_ops.set_monitor_port	= p1022rdk_set_monitor_port;
+	diu_ops.set_pixel_clock		= p1022rdk_set_pixel_clock;
+	diu_ops.valid_monitor_port	= p1022rdk_valid_monitor_port;
+#endif
+
+	mpc85xx_smp_init();
+
+	fsl_pci_assign_primary();
+
+	swiotlb_detect_4g();
+
+	pr_info("Freescale / iVeia P1022 RDK reference board\n");
+}
+
+machine_arch_initcall(p1022_rdk, mpc85xx_common_publish_devices);
+
+machine_arch_initcall(p1022_rdk, swiotlb_setup_bus_notifier);
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init p1022_rdk_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	return of_flat_dt_is_compatible(root, "fsl,p1022rdk");
+}
+
+define_machine(p1022_rdk) {
+	.name			= "P1022 RDK",
+	.probe			= p1022_rdk_probe,
+	.setup_arch		= p1022_rdk_setup_arch,
+	.init_IRQ		= p1022_rdk_pic_init,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+	.get_irq		= mpic_get_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
diff --git a/arch/powerpc/platforms/85xx/p1023_rds.c b/arch/powerpc/platforms/85xx/p1023_rds.c
index 2990e8b..9cc60a7 100644
--- a/arch/powerpc/platforms/85xx/p1023_rds.c
+++ b/arch/powerpc/platforms/85xx/p1023_rds.c
@@ -80,15 +80,12 @@ static void __init mpc85xx_rds_setup_arch(void)
 		}
 	}
 
-#ifdef CONFIG_PCI
-	for_each_compatible_node(np, "pci", "fsl,p1023-pcie")
-		fsl_add_bridge(np, 0);
-#endif
-
 	mpc85xx_smp_init();
+
+	fsl_pci_assign_primary();
 }
 
-machine_device_initcall(p1023_rds, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1023_rds, mpc85xx_common_publish_devices);
 
 static void __init mpc85xx_rds_pic_init(void)
 {
diff --git a/arch/powerpc/platforms/85xx/p2041_rdb.c b/arch/powerpc/platforms/85xx/p2041_rdb.c
index 6541fa2..000c089 100644
--- a/arch/powerpc/platforms/85xx/p2041_rdb.c
+++ b/arch/powerpc/platforms/85xx/p2041_rdb.c
@@ -80,7 +80,7 @@ define_machine(p2041_rdb) {
 	.power_save		= e500_idle,
 };
 
-machine_device_initcall(p2041_rdb, corenet_ds_publish_devices);
+machine_arch_initcall(p2041_rdb, corenet_ds_publish_devices);
 
 #ifdef CONFIG_SWIOTLB
 machine_arch_initcall(p2041_rdb, swiotlb_setup_bus_notifier);
diff --git a/arch/powerpc/platforms/85xx/p3041_ds.c b/arch/powerpc/platforms/85xx/p3041_ds.c
index f238efa..b3edc20 100644
--- a/arch/powerpc/platforms/85xx/p3041_ds.c
+++ b/arch/powerpc/platforms/85xx/p3041_ds.c
@@ -82,7 +82,7 @@ define_machine(p3041_ds) {
 	.power_save		= e500_idle,
 };
 
-machine_device_initcall(p3041_ds, corenet_ds_publish_devices);
+machine_arch_initcall(p3041_ds, corenet_ds_publish_devices);
 
 #ifdef CONFIG_SWIOTLB
 machine_arch_initcall(p3041_ds, swiotlb_setup_bus_notifier);
diff --git a/arch/powerpc/platforms/85xx/p4080_ds.c b/arch/powerpc/platforms/85xx/p4080_ds.c
index c92417d..54df106 100644
--- a/arch/powerpc/platforms/85xx/p4080_ds.c
+++ b/arch/powerpc/platforms/85xx/p4080_ds.c
@@ -81,7 +81,7 @@ define_machine(p4080_ds) {
 	.power_save		= e500_idle,
 };
 
-machine_device_initcall(p4080_ds, corenet_ds_publish_devices);
+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
index 17bef15..753a42c 100644
--- a/arch/powerpc/platforms/85xx/p5020_ds.c
+++ b/arch/powerpc/platforms/85xx/p5020_ds.c
@@ -91,7 +91,7 @@ define_machine(p5020_ds) {
 #endif
 };
 
-machine_device_initcall(p5020_ds, corenet_ds_publish_devices);
+machine_arch_initcall(p5020_ds, corenet_ds_publish_devices);
 
 #ifdef CONFIG_SWIOTLB
 machine_arch_initcall(p5020_ds, swiotlb_setup_bus_notifier);
diff --git a/arch/powerpc/platforms/85xx/p5040_ds.c b/arch/powerpc/platforms/85xx/p5040_ds.c
new file mode 100644
index 0000000..1138185
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/p5040_ds.c
@@ -0,0 +1,89 @@
+/*
+ * 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();
+#ifdef CONFIG_SMP
+	extern struct smp_ops_t smp_85xx_ops;
+#endif
+
+	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;
+#ifdef CONFIG_SMP
+		/*
+		 * Disable the timebase sync operations because we can't write
+		 * to the timebase registers under the hypervisor.
+		  */
+		smp_85xx_ops.give_timebase = NULL;
+		smp_85xx_ops.take_timebase = NULL;
+#endif
+		return 1;
+	}
+
+	return 0;
+}
+
+define_machine(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
+};
+
+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/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c
index 95a2e53..f6ea561 100644
--- a/arch/powerpc/platforms/85xx/qemu_e500.c
+++ b/arch/powerpc/platforms/85xx/qemu_e500.c
@@ -41,7 +41,8 @@ static void __init qemu_e500_setup_arch(void)
 {
 	ppc_md.progress("qemu_e500_setup_arch()", 0);
 
-	fsl_pci_init();
+	fsl_pci_assign_primary();
+	swiotlb_detect_4g();
 	mpc85xx_smp_init();
 }
 
@@ -55,7 +56,7 @@ static int __init qemu_e500_probe(void)
 	return !!of_flat_dt_is_compatible(root, "fsl,qemu-e500");
 }
 
-machine_device_initcall(qemu_e500, mpc85xx_common_publish_devices);
+machine_arch_initcall(qemu_e500, mpc85xx_common_publish_devices);
 
 define_machine(qemu_e500) {
 	.name			= "QEMU e500",
diff --git a/arch/powerpc/platforms/85xx/sbc8548.c b/arch/powerpc/platforms/85xx/sbc8548.c
index cd3a66b..f621218 100644
--- a/arch/powerpc/platforms/85xx/sbc8548.c
+++ b/arch/powerpc/platforms/85xx/sbc8548.c
@@ -88,26 +88,11 @@ static int __init sbc8548_hw_rev(void)
  */
 static void __init sbc8548_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-#endif
-
 	if (ppc_md.progress)
 		ppc_md.progress("sbc8548_setup_arch()", 0);
 
-#ifdef CONFIG_PCI
-	for_each_node_by_type(np, "pci") {
-		if (of_device_is_compatible(np, "fsl,mpc8540-pci") ||
-		    of_device_is_compatible(np, "fsl,mpc8548-pcie")) {
-			struct resource rsrc;
-			of_address_to_resource(np, 0, &rsrc);
-			if ((rsrc.start & 0xfffff) == 0x8000)
-				fsl_add_bridge(np, 1);
-			else
-				fsl_add_bridge(np, 0);
-		}
-	}
-#endif
+	fsl_pci_assign_primary();
+
 	sbc_rev = sbc8548_hw_rev();
 }
 
@@ -128,7 +113,7 @@ static void sbc8548_show_cpuinfo(struct seq_file *m)
 	seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f));
 }
 
-machine_device_initcall(sbc8548, mpc85xx_common_publish_devices);
+machine_arch_initcall(sbc8548, mpc85xx_common_publish_devices);
 
 /*
  * Called very early, device-tree isn't unflattened
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index ff42490..6fcfa12 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -2,7 +2,7 @@
  * Author: Andy Fleming <afleming@freescale.com>
  * 	   Kumar Gala <galak@kernel.crashing.org>
  *
- * Copyright 2006-2008, 2011 Freescale Semiconductor Inc.
+ * Copyright 2006-2008, 2011-2012 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
@@ -17,6 +17,7 @@
 #include <linux/of.h>
 #include <linux/kexec.h>
 #include <linux/highmem.h>
+#include <linux/cpu.h>
 
 #include <asm/machdep.h>
 #include <asm/pgtable.h>
@@ -24,33 +25,118 @@
 #include <asm/mpic.h>
 #include <asm/cacheflush.h>
 #include <asm/dbell.h>
+#include <asm/fsl_guts.h>
 
 #include <sysdev/fsl_soc.h>
 #include <sysdev/mpic.h>
 #include "smp.h"
 
-extern void __early_start(void);
-
-#define BOOT_ENTRY_ADDR_UPPER	0
-#define BOOT_ENTRY_ADDR_LOWER	1
-#define BOOT_ENTRY_R3_UPPER	2
-#define BOOT_ENTRY_R3_LOWER	3
-#define BOOT_ENTRY_RESV		4
-#define BOOT_ENTRY_PIR		5
-#define BOOT_ENTRY_R6_UPPER	6
-#define BOOT_ENTRY_R6_LOWER	7
-#define NUM_BOOT_ENTRY		8
-#define SIZE_BOOT_ENTRY		(NUM_BOOT_ENTRY * sizeof(u32))
-
-static int __init
-smp_85xx_kick_cpu(int nr)
+struct epapr_spin_table {
+	u32	addr_h;
+	u32	addr_l;
+	u32	r3_h;
+	u32	r3_l;
+	u32	reserved;
+	u32	pir;
+};
+
+static struct ccsr_guts __iomem *guts;
+static u64 timebase;
+static int tb_req;
+static int tb_valid;
+
+static void mpc85xx_timebase_freeze(int freeze)
+{
+	uint32_t mask;
+
+	mask = CCSR_GUTS_DEVDISR_TB0 | CCSR_GUTS_DEVDISR_TB1;
+	if (freeze)
+		setbits32(&guts->devdisr, mask);
+	else
+		clrbits32(&guts->devdisr, mask);
+
+	in_be32(&guts->devdisr);
+}
+
+static void mpc85xx_give_timebase(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	while (!tb_req)
+		barrier();
+	tb_req = 0;
+
+	mpc85xx_timebase_freeze(1);
+	timebase = get_tb();
+	mb();
+	tb_valid = 1;
+
+	while (tb_valid)
+		barrier();
+
+	mpc85xx_timebase_freeze(0);
+
+	local_irq_restore(flags);
+}
+
+static void mpc85xx_take_timebase(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	tb_req = 1;
+	while (!tb_valid)
+		barrier();
+
+	set_tb(timebase >> 32, timebase & 0xffffffff);
+	isync();
+	tb_valid = 0;
+
+	local_irq_restore(flags);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void __cpuinit smp_85xx_mach_cpu_die(void)
+{
+	unsigned int cpu = smp_processor_id();
+	u32 tmp;
+
+	local_irq_disable();
+	idle_task_exit();
+	generic_set_cpu_dead(cpu);
+	mb();
+
+	mtspr(SPRN_TCR, 0);
+
+	__flush_disable_L1();
+	tmp = (mfspr(SPRN_HID0) & ~(HID0_DOZE|HID0_SLEEP)) | HID0_NAP;
+	mtspr(SPRN_HID0, tmp);
+	isync();
+
+	/* Enter NAP mode. */
+	tmp = mfmsr();
+	tmp |= MSR_WE;
+	mb();
+	mtmsr(tmp);
+	isync();
+
+	while (1)
+		;
+}
+#endif
+
+static int __cpuinit smp_85xx_kick_cpu(int nr)
 {
 	unsigned long flags;
 	const u64 *cpu_rel_addr;
-	__iomem u32 *bptr_vaddr;
+	__iomem struct epapr_spin_table *spin_table;
 	struct device_node *np;
-	int n = 0, hw_cpu = get_hard_smp_processor_id(nr);
+	int hw_cpu = get_hard_smp_processor_id(nr);
 	int ioremappable;
+	int ret = 0;
 
 	WARN_ON(nr < 0 || nr >= NR_CPUS);
 	WARN_ON(hw_cpu < 0 || hw_cpu >= NR_CPUS);
@@ -75,46 +161,81 @@ smp_85xx_kick_cpu(int nr)
 
 	/* Map the spin table */
 	if (ioremappable)
-		bptr_vaddr = ioremap(*cpu_rel_addr, SIZE_BOOT_ENTRY);
+		spin_table = ioremap(*cpu_rel_addr,
+				sizeof(struct epapr_spin_table));
 	else
-		bptr_vaddr = phys_to_virt(*cpu_rel_addr);
+		spin_table = phys_to_virt(*cpu_rel_addr);
 
 	local_irq_save(flags);
-
-	out_be32(bptr_vaddr + BOOT_ENTRY_PIR, hw_cpu);
 #ifdef CONFIG_PPC32
-	out_be32(bptr_vaddr + BOOT_ENTRY_ADDR_LOWER, __pa(__early_start));
+#ifdef CONFIG_HOTPLUG_CPU
+	/* Corresponding to generic_set_cpu_dead() */
+	generic_set_cpu_up(nr);
+
+	if (system_state == SYSTEM_RUNNING) {
+		out_be32(&spin_table->addr_l, 0);
+
+		/*
+		 * We don't set the BPTR register here since it already points
+		 * to the boot page properly.
+		 */
+		mpic_reset_core(hw_cpu);
+
+		/* wait until core is ready... */
+		if (!spin_event_timeout(in_be32(&spin_table->addr_l) == 1,
+						10000, 100)) {
+			pr_err("%s: timeout waiting for core %d to reset\n",
+							__func__, hw_cpu);
+			ret = -ENOENT;
+			goto out;
+		}
+
+		/*  clear the acknowledge status */
+		__secondary_hold_acknowledge = -1;
+	}
+#endif
+	out_be32(&spin_table->pir, hw_cpu);
+	out_be32(&spin_table->addr_l, __pa(__early_start));
 
 	if (!ioremappable)
-		flush_dcache_range((ulong)bptr_vaddr,
-				(ulong)(bptr_vaddr + SIZE_BOOT_ENTRY));
+		flush_dcache_range((ulong)spin_table,
+			(ulong)spin_table + sizeof(struct epapr_spin_table));
 
 	/* Wait a bit for the CPU to ack. */
-	while ((__secondary_hold_acknowledge != hw_cpu) && (++n < 1000))
-		mdelay(1);
+	if (!spin_event_timeout(__secondary_hold_acknowledge == hw_cpu,
+					10000, 100)) {
+		pr_err("%s: timeout waiting for core %d to ack\n",
+						__func__, hw_cpu);
+		ret = -ENOENT;
+		goto out;
+	}
+out:
 #else
 	smp_generic_kick_cpu(nr);
 
-	out_be64((u64 *)(bptr_vaddr + BOOT_ENTRY_ADDR_UPPER),
-		__pa((u64)*((unsigned long long *) generic_secondary_smp_init)));
+	out_be32(&spin_table->pir, hw_cpu);
+	out_be64((u64 *)(&spin_table->addr_h),
+	  __pa((u64)*((unsigned long long *)generic_secondary_smp_init)));
 
 	if (!ioremappable)
-		flush_dcache_range((ulong)bptr_vaddr,
-				(ulong)(bptr_vaddr + SIZE_BOOT_ENTRY));
+		flush_dcache_range((ulong)spin_table,
+			(ulong)spin_table + sizeof(struct epapr_spin_table));
 #endif
 
 	local_irq_restore(flags);
 
 	if (ioremappable)
-		iounmap(bptr_vaddr);
-
-	pr_debug("waited %d msecs for CPU #%d.\n", n, nr);
+		iounmap(spin_table);
 
-	return 0;
+	return ret;
 }
 
 struct smp_ops_t smp_85xx_ops = {
 	.kick_cpu = smp_85xx_kick_cpu,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable	= generic_cpu_disable,
+	.cpu_die	= generic_cpu_die,
+#endif
 #ifdef CONFIG_KEXEC
 	.give_timebase	= smp_generic_give_timebase,
 	.take_timebase	= smp_generic_take_timebase,
@@ -218,8 +339,7 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image)
 }
 #endif /* CONFIG_KEXEC */
 
-static void __init
-smp_85xx_setup_cpu(int cpu_nr)
+static void __cpuinit smp_85xx_setup_cpu(int cpu_nr)
 {
 	if (smp_85xx_ops.probe == smp_mpic_probe)
 		mpic_setup_this_cpu();
@@ -228,6 +348,16 @@ smp_85xx_setup_cpu(int cpu_nr)
 		doorbell_setup_this_cpu();
 }
 
+static const struct of_device_id mpc85xx_smp_guts_ids[] = {
+	{ .compatible = "fsl,mpc8572-guts", },
+	{ .compatible = "fsl,p1020-guts", },
+	{ .compatible = "fsl,p1021-guts", },
+	{ .compatible = "fsl,p1022-guts", },
+	{ .compatible = "fsl,p1023-guts", },
+	{ .compatible = "fsl,p2020-guts", },
+	{},
+};
+
 void __init mpc85xx_smp_init(void)
 {
 	struct device_node *np;
@@ -249,6 +379,22 @@ void __init mpc85xx_smp_init(void)
 		smp_85xx_ops.cause_ipi = doorbell_cause_ipi;
 	}
 
+	np = of_find_matching_node(NULL, mpc85xx_smp_guts_ids);
+	if (np) {
+		guts = of_iomap(np, 0);
+		of_node_put(np);
+		if (!guts) {
+			pr_err("%s: Could not map guts node address\n",
+								__func__);
+			return;
+		}
+		smp_85xx_ops.give_timebase = mpc85xx_give_timebase;
+		smp_85xx_ops.take_timebase = mpc85xx_take_timebase;
+#ifdef CONFIG_HOTPLUG_CPU
+		ppc_md.cpu_die = smp_85xx_mach_cpu_die;
+#endif
+	}
+
 	smp_ops = &smp_85xx_ops;
 
 #ifdef CONFIG_KEXEC
diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c
index b9c6daa..ae368e0 100644
--- a/arch/powerpc/platforms/85xx/socrates.c
+++ b/arch/powerpc/platforms/85xx/socrates.c
@@ -66,20 +66,13 @@ static void __init socrates_pic_init(void)
  */
 static void __init socrates_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-#endif
-
 	if (ppc_md.progress)
 		ppc_md.progress("socrates_setup_arch()", 0);
 
-#ifdef CONFIG_PCI
-	for_each_compatible_node(np, "pci", "fsl,mpc8540-pci")
-		fsl_add_bridge(np, 1);
-#endif
+	fsl_pci_assign_primary();
 }
 
-machine_device_initcall(socrates, mpc85xx_common_publish_devices);
+machine_arch_initcall(socrates, mpc85xx_common_publish_devices);
 
 /*
  * Called very early, device-tree isn't unflattened
diff --git a/arch/powerpc/platforms/85xx/stx_gp3.c b/arch/powerpc/platforms/85xx/stx_gp3.c
index e050800..6f4939b 100644
--- a/arch/powerpc/platforms/85xx/stx_gp3.c
+++ b/arch/powerpc/platforms/85xx/stx_gp3.c
@@ -60,21 +60,14 @@ static void __init stx_gp3_pic_init(void)
  */
 static void __init stx_gp3_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-#endif
-
 	if (ppc_md.progress)
 		ppc_md.progress("stx_gp3_setup_arch()", 0);
 
+	fsl_pci_assign_primary();
+
 #ifdef CONFIG_CPM2
 	cpm2_reset();
 #endif
-
-#ifdef CONFIG_PCI
-	for_each_compatible_node(np, "pci", "fsl,mpc8540-pci")
-		fsl_add_bridge(np, 1);
-#endif
 }
 
 static void stx_gp3_show_cpuinfo(struct seq_file *m)
@@ -93,7 +86,7 @@ static void stx_gp3_show_cpuinfo(struct seq_file *m)
 	seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f));
 }
 
-machine_device_initcall(stx_gp3, mpc85xx_common_publish_devices);
+machine_arch_initcall(stx_gp3, mpc85xx_common_publish_devices);
 
 /*
  * Called very early, device-tree isn't unflattened
diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c
index b62fa87..b4e58cd 100644
--- a/arch/powerpc/platforms/85xx/tqm85xx.c
+++ b/arch/powerpc/platforms/85xx/tqm85xx.c
@@ -59,10 +59,6 @@ static void __init tqm85xx_pic_init(void)
  */
 static void __init tqm85xx_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-#endif
-
 	if (ppc_md.progress)
 		ppc_md.progress("tqm85xx_setup_arch()", 0);
 
@@ -70,20 +66,7 @@ static void __init tqm85xx_setup_arch(void)
 	cpm2_reset();
 #endif
 
-#ifdef CONFIG_PCI
-	for_each_node_by_type(np, "pci") {
-		if (of_device_is_compatible(np, "fsl,mpc8540-pci") ||
-		    of_device_is_compatible(np, "fsl,mpc8548-pcie")) {
-			struct resource rsrc;
-			if (!of_address_to_resource(np, 0, &rsrc)) {
-				if ((rsrc.start & 0xfffff) == 0x8000)
-					fsl_add_bridge(np, 1);
-				else
-					fsl_add_bridge(np, 0);
-			}
-		}
-	}
-#endif
+	fsl_pci_assign_primary();
 }
 
 static void tqm85xx_show_cpuinfo(struct seq_file *m)
@@ -123,7 +106,7 @@ static void __devinit tqm85xx_ti1520_fixup(struct pci_dev *pdev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_1520,
 		tqm85xx_ti1520_fixup);
 
-machine_device_initcall(tqm85xx, mpc85xx_common_publish_devices);
+machine_arch_initcall(tqm85xx, mpc85xx_common_publish_devices);
 
 static const char * const board[] __initconst = {
 	"tqc,tqm8540",
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index 41c6875..dcbf7e4 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -111,18 +111,11 @@ static void xes_mpc85xx_fixups(void)
 	}
 }
 
-#ifdef CONFIG_PCI
-static int primary_phb_addr;
-#endif
-
 /*
  * Setup the architecture
  */
 static void __init xes_mpc85xx_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-#endif
 	struct device_node *root;
 	const char *model = "Unknown";
 
@@ -137,26 +130,14 @@ static void __init xes_mpc85xx_setup_arch(void)
 
 	xes_mpc85xx_fixups();
 
-#ifdef CONFIG_PCI
-	for_each_node_by_type(np, "pci") {
-		if (of_device_is_compatible(np, "fsl,mpc8540-pci") ||
-		    of_device_is_compatible(np, "fsl,mpc8548-pcie")) {
-			struct resource rsrc;
-			of_address_to_resource(np, 0, &rsrc);
-			if ((rsrc.start & 0xfffff) == primary_phb_addr)
-				fsl_add_bridge(np, 1);
-			else
-				fsl_add_bridge(np, 0);
-		}
-	}
-#endif
-
 	mpc85xx_smp_init();
+
+	fsl_pci_assign_primary();
 }
 
-machine_device_initcall(xes_mpc8572, mpc85xx_common_publish_devices);
-machine_device_initcall(xes_mpc8548, mpc85xx_common_publish_devices);
-machine_device_initcall(xes_mpc8540, mpc85xx_common_publish_devices);
+machine_arch_initcall(xes_mpc8572, mpc85xx_common_publish_devices);
+machine_arch_initcall(xes_mpc8548, mpc85xx_common_publish_devices);
+machine_arch_initcall(xes_mpc8540, mpc85xx_common_publish_devices);
 
 /*
  * Called very early, device-tree isn't unflattened
@@ -165,42 +146,21 @@ static int __init xes_mpc8572_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
 
-	if (of_flat_dt_is_compatible(root, "xes,MPC8572")) {
-#ifdef CONFIG_PCI
-		primary_phb_addr = 0x8000;
-#endif
-		return 1;
-	} else {
-		return 0;
-	}
+	return of_flat_dt_is_compatible(root, "xes,MPC8572");
 }
 
 static int __init xes_mpc8548_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
 
-	if (of_flat_dt_is_compatible(root, "xes,MPC8548")) {
-#ifdef CONFIG_PCI
-		primary_phb_addr = 0xb000;
-#endif
-		return 1;
-	} else {
-		return 0;
-	}
+	return of_flat_dt_is_compatible(root, "xes,MPC8548");
 }
 
 static int __init xes_mpc8540_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
 
-	if (of_flat_dt_is_compatible(root, "xes,MPC8540")) {
-#ifdef CONFIG_PCI
-		primary_phb_addr = 0xb000;
-#endif
-		return 1;
-	} else {
-		return 0;
-	}
+	return of_flat_dt_is_compatible(root, "xes,MPC8540");
 }
 
 define_machine(xes_mpc8572) {
diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c
index 563aafa8..bf53387 100644
--- a/arch/powerpc/platforms/86xx/gef_ppc9a.c
+++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c
@@ -73,13 +73,6 @@ static void __init gef_ppc9a_init_irq(void)
 static void __init gef_ppc9a_setup_arch(void)
 {
 	struct device_node *regs;
-#ifdef CONFIG_PCI
-	struct device_node *np;
-
-	for_each_compatible_node(np, "pci", "fsl,mpc8641-pcie") {
-		fsl_add_bridge(np, 1);
-	}
-#endif
 
 	printk(KERN_INFO "GE Intelligent Platforms PPC9A 6U VME SBC\n");
 
@@ -87,6 +80,8 @@ static void __init gef_ppc9a_setup_arch(void)
 	mpc86xx_smp_init();
 #endif
 
+	fsl_pci_assign_primary();
+
 	/* Remap basic board registers */
 	regs = of_find_compatible_node(NULL, NULL, "gef,ppc9a-fpga-regs");
 	if (regs) {
@@ -221,6 +216,7 @@ static long __init mpc86xx_time_init(void)
 static __initdata struct of_device_id of_bus_ids[] = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "gianfar", },
+	{ .compatible = "fsl,mpc8641-pcie", },
 	{},
 };
 
@@ -231,7 +227,7 @@ static int __init declare_of_platform_devices(void)
 
 	return 0;
 }
-machine_device_initcall(gef_ppc9a, declare_of_platform_devices);
+machine_arch_initcall(gef_ppc9a, declare_of_platform_devices);
 
 define_machine(gef_ppc9a) {
 	.name			= "GE PPC9A",
diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c
index cc6a91a..0b78513 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc310.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc310.c
@@ -73,20 +73,14 @@ static void __init gef_sbc310_init_irq(void)
 static void __init gef_sbc310_setup_arch(void)
 {
 	struct device_node *regs;
-#ifdef CONFIG_PCI
-	struct device_node *np;
-
-	for_each_compatible_node(np, "pci", "fsl,mpc8641-pcie") {
-		fsl_add_bridge(np, 1);
-	}
-#endif
-
 	printk(KERN_INFO "GE Intelligent Platforms SBC310 6U VPX SBC\n");
 
 #ifdef CONFIG_SMP
 	mpc86xx_smp_init();
 #endif
 
+	fsl_pci_assign_primary();
+
 	/* Remap basic board registers */
 	regs = of_find_compatible_node(NULL, NULL, "gef,fpga-regs");
 	if (regs) {
@@ -209,6 +203,7 @@ static long __init mpc86xx_time_init(void)
 static __initdata struct of_device_id of_bus_ids[] = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "gianfar", },
+	{ .compatible = "fsl,mpc8641-pcie", },
 	{},
 };
 
@@ -219,7 +214,7 @@ static int __init declare_of_platform_devices(void)
 
 	return 0;
 }
-machine_device_initcall(gef_sbc310, declare_of_platform_devices);
+machine_arch_initcall(gef_sbc310, declare_of_platform_devices);
 
 define_machine(gef_sbc310) {
 	.name			= "GE SBC310",
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index aead6b3..b9eb174 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -73,13 +73,6 @@ static void __init gef_sbc610_init_irq(void)
 static void __init gef_sbc610_setup_arch(void)
 {
 	struct device_node *regs;
-#ifdef CONFIG_PCI
-	struct device_node *np;
-
-	for_each_compatible_node(np, "pci", "fsl,mpc8641-pcie") {
-		fsl_add_bridge(np, 1);
-	}
-#endif
 
 	printk(KERN_INFO "GE Intelligent Platforms SBC610 6U VPX SBC\n");
 
@@ -87,6 +80,8 @@ static void __init gef_sbc610_setup_arch(void)
 	mpc86xx_smp_init();
 #endif
 
+	fsl_pci_assign_primary();
+
 	/* Remap basic board registers */
 	regs = of_find_compatible_node(NULL, NULL, "gef,fpga-regs");
 	if (regs) {
@@ -198,6 +193,7 @@ static long __init mpc86xx_time_init(void)
 static __initdata struct of_device_id of_bus_ids[] = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "gianfar", },
+	{ .compatible = "fsl,mpc8641-pcie", },
 	{},
 };
 
@@ -208,7 +204,7 @@ static int __init declare_of_platform_devices(void)
 
 	return 0;
 }
-machine_device_initcall(gef_sbc610, declare_of_platform_devices);
+machine_arch_initcall(gef_sbc610, declare_of_platform_devices);
 
 define_machine(gef_sbc610) {
 	.name			= "GE SBC610",
diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
index 62cd3c5..a817398 100644
--- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
+++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
@@ -91,6 +91,9 @@ static struct of_device_id __initdata mpc8610_ids[] = {
 	{ .compatible = "simple-bus", },
 	/* So that the DMA channel nodes can be probed individually: */
 	{ .compatible = "fsl,eloplus-dma", },
+	/* PCI controllers */
+	{ .compatible = "fsl,mpc8610-pci", },
+	{ .compatible = "fsl,mpc8641-pcie", },
 	{}
 };
 
@@ -107,7 +110,7 @@ static int __init mpc8610_declare_of_platform_devices(void)
 
 	return 0;
 }
-machine_device_initcall(mpc86xx_hpcd, mpc8610_declare_of_platform_devices);
+machine_arch_initcall(mpc86xx_hpcd, mpc8610_declare_of_platform_devices);
 
 #if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
 
@@ -278,25 +281,13 @@ mpc8610hpcd_valid_monitor_port(enum fsl_diu_monitor_port port)
 static void __init mpc86xx_hpcd_setup_arch(void)
 {
 	struct resource r;
-	struct device_node *np;
 	unsigned char *pixis;
 
 	if (ppc_md.progress)
 		ppc_md.progress("mpc86xx_hpcd_setup_arch()", 0);
 
-#ifdef CONFIG_PCI
-	for_each_node_by_type(np, "pci") {
-		if (of_device_is_compatible(np, "fsl,mpc8610-pci")
-		    || of_device_is_compatible(np, "fsl,mpc8641-pcie")) {
-			struct resource rsrc;
-			of_address_to_resource(np, 0, &rsrc);
-			if ((rsrc.start & 0xfffff) == 0xa000)
-				fsl_add_bridge(np, 1);
-			else
-				fsl_add_bridge(np, 0);
-		}
-        }
-#endif
+	fsl_pci_assign_primary();
+
 #if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
 	diu_ops.get_pixel_format	= mpc8610hpcd_get_pixel_format;
 	diu_ops.set_gamma_table		= mpc8610hpcd_set_gamma_table;
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index 817245b..e8bf3fa 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -19,7 +19,6 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include <linux/of_platform.h>
-#include <linux/memblock.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
@@ -51,15 +50,8 @@ extern int uli_exclude_device(struct pci_controller *hose,
 static int mpc86xx_exclude_device(struct pci_controller *hose,
 				   u_char bus, u_char devfn)
 {
-	struct device_node* node;	
-	struct resource rsrc;
-
-	node = hose->dn;
-	of_address_to_resource(node, 0, &rsrc);
-
-	if ((rsrc.start & 0xfffff) == 0x8000) {
+	if (hose->dn == fsl_pci_primary)
 		return uli_exclude_device(hose, bus, devfn);
-	}
 
 	return PCIBIOS_SUCCESSFUL;
 }
@@ -69,30 +61,11 @@ static int mpc86xx_exclude_device(struct pci_controller *hose,
 static void __init
 mpc86xx_hpcn_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-	struct pci_controller *hose;
-#endif
-	dma_addr_t max = 0xffffffff;
-
 	if (ppc_md.progress)
 		ppc_md.progress("mpc86xx_hpcn_setup_arch()", 0);
 
 #ifdef CONFIG_PCI
-	for_each_compatible_node(np, "pci", "fsl,mpc8641-pcie") {
-		struct resource rsrc;
-		of_address_to_resource(np, 0, &rsrc);
-		if ((rsrc.start & 0xfffff) == 0x8000)
-			fsl_add_bridge(np, 1);
-		else
-			fsl_add_bridge(np, 0);
-		hose = pci_find_hose_for_OF_device(np);
-		max = min(max, hose->dma_window_base_cur +
-			  hose->dma_window_size);
-	}
-
 	ppc_md.pci_exclude_device = mpc86xx_exclude_device;
-
 #endif
 
 	printk("MPC86xx HPCN board from Freescale Semiconductor\n");
@@ -101,13 +74,9 @@ mpc86xx_hpcn_setup_arch(void)
 	mpc86xx_smp_init();
 #endif
 
-#ifdef CONFIG_SWIOTLB
-	if ((memblock_end_of_DRAM() - 1) > max) {
-		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_dma_ops);
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
-	}
-#endif
+	fsl_pci_assign_primary();
+
+	swiotlb_detect_4g();
 }
 
 
@@ -162,6 +131,7 @@ static __initdata struct of_device_id of_bus_ids[] = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "fsl,srio", },
 	{ .compatible = "gianfar", },
+	{ .compatible = "fsl,mpc8641-pcie", },
 	{},
 };
 
@@ -171,7 +141,7 @@ static int __init declare_of_platform_devices(void)
 
 	return 0;
 }
-machine_device_initcall(mpc86xx_hpcn, declare_of_platform_devices);
+machine_arch_initcall(mpc86xx_hpcn, declare_of_platform_devices);
 machine_arch_initcall(mpc86xx_hpcn, swiotlb_setup_bus_notifier);
 
 define_machine(mpc86xx_hpcn) {
diff --git a/arch/powerpc/platforms/86xx/sbc8641d.c b/arch/powerpc/platforms/86xx/sbc8641d.c
index e7007d0..b47a8fd 100644
--- a/arch/powerpc/platforms/86xx/sbc8641d.c
+++ b/arch/powerpc/platforms/86xx/sbc8641d.c
@@ -38,23 +38,16 @@
 static void __init
 sbc8641_setup_arch(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
-#endif
-
 	if (ppc_md.progress)
 		ppc_md.progress("sbc8641_setup_arch()", 0);
 
-#ifdef CONFIG_PCI
-	for_each_compatible_node(np, "pci", "fsl,mpc8641-pcie")
-		fsl_add_bridge(np, 0);
-#endif
-
 	printk("SBC8641 board from Wind River\n");
 
 #ifdef CONFIG_SMP
 	mpc86xx_smp_init();
 #endif
+
+	fsl_pci_assign_primary();
 }
 
 
@@ -102,6 +95,7 @@ mpc86xx_time_init(void)
 static __initdata struct of_device_id of_bus_ids[] = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "gianfar", },
+	{ .compatible = "fsl,mpc8641-pcie", },
 	{},
 };
 
@@ -111,7 +105,7 @@ static int __init declare_of_platform_devices(void)
 
 	return 0;
 }
-machine_device_initcall(sbc8641, declare_of_platform_devices);
+machine_arch_initcall(sbc8641, declare_of_platform_devices);
 
 define_machine(sbc8641) {
 	.name			= "SBC8641D",
diff --git a/arch/powerpc/platforms/cell/beat.c b/arch/powerpc/platforms/cell/beat.c
index 852592b..affcf56 100644
--- a/arch/powerpc/platforms/cell/beat.c
+++ b/arch/powerpc/platforms/cell/beat.c
@@ -136,9 +136,9 @@ ssize_t beat_nvram_get_size(void)
 	return BEAT_NVRAM_SIZE;
 }
 
-int beat_set_xdabr(unsigned long dabr)
+int beat_set_xdabr(unsigned long dabr, unsigned long dabrx)
 {
-	if (beat_set_dabr(dabr, DABRX_KERNEL | DABRX_USER))
+	if (beat_set_dabr(dabr, dabrx))
 		return -1;
 	return 0;
 }
diff --git a/arch/powerpc/platforms/cell/beat.h b/arch/powerpc/platforms/cell/beat.h
index 32c8efc..bfcb8e3 100644
--- a/arch/powerpc/platforms/cell/beat.h
+++ b/arch/powerpc/platforms/cell/beat.h
@@ -32,7 +32,7 @@ void beat_get_rtc_time(struct rtc_time *);
 ssize_t beat_nvram_get_size(void);
 ssize_t beat_nvram_read(char *, size_t, loff_t *);
 ssize_t beat_nvram_write(char *, size_t, loff_t *);
-int beat_set_xdabr(unsigned long);
+int beat_set_xdabr(unsigned long, unsigned long);
 void beat_power_save(void);
 void beat_kexec_cpu_down(int, int);
 
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index 943c9d3..0f6f839 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -88,7 +88,7 @@ static inline unsigned int beat_read_mask(unsigned hpte_group)
 }
 
 static long beat_lpar_hpte_insert(unsigned long hpte_group,
-				  unsigned long va, unsigned long pa,
+				  unsigned long vpn, unsigned long pa,
 				  unsigned long rflags, unsigned long vflags,
 				  int psize, int ssize)
 {
@@ -103,7 +103,7 @@ static long beat_lpar_hpte_insert(unsigned long hpte_group,
 			"rflags=%lx, vflags=%lx, psize=%d)\n",
 		hpte_group, va, pa, rflags, vflags, psize);
 
-	hpte_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M) |
+	hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) |
 		vflags | HPTE_V_VALID;
 	hpte_r = hpte_encode_r(pa, psize) | rflags;
 
@@ -184,14 +184,14 @@ static void beat_lpar_hptab_clear(void)
  */
 static long beat_lpar_hpte_updatepp(unsigned long slot,
 				    unsigned long newpp,
-				    unsigned long va,
+				    unsigned long vpn,
 				    int psize, int ssize, int local)
 {
 	unsigned long lpar_rc;
 	u64 dummy0, dummy1;
 	unsigned long want_v;
 
-	want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M);
+	want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
 
 	DBG_LOW("    update: "
 		"avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ",
@@ -220,15 +220,15 @@ static long beat_lpar_hpte_updatepp(unsigned long slot,
 	return 0;
 }
 
-static long beat_lpar_hpte_find(unsigned long va, int psize)
+static long beat_lpar_hpte_find(unsigned long vpn, int psize)
 {
 	unsigned long hash;
 	unsigned long i, j;
 	long slot;
 	unsigned long want_v, hpte_v;
 
-	hash = hpt_hash(va, mmu_psize_defs[psize].shift, MMU_SEGSIZE_256M);
-	want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M);
+	hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, MMU_SEGSIZE_256M);
+	want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
 
 	for (j = 0; j < 2; j++) {
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
@@ -255,14 +255,15 @@ static void beat_lpar_hpte_updateboltedpp(unsigned long newpp,
 					  unsigned long ea,
 					  int psize, int ssize)
 {
-	unsigned long lpar_rc, slot, vsid, va;
+	unsigned long vpn;
+	unsigned long lpar_rc, slot, vsid;
 	u64 dummy0, dummy1;
 
 	vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M);
-	va = (vsid << 28) | (ea & 0x0fffffff);
+	vpn = hpt_vpn(ea, vsid, MMU_SEGSIZE_256M);
 
 	raw_spin_lock(&beat_htab_lock);
-	slot = beat_lpar_hpte_find(va, psize);
+	slot = beat_lpar_hpte_find(vpn, psize);
 	BUG_ON(slot == -1);
 
 	lpar_rc = beat_write_htab_entry(0, slot, 0, newpp, 0, 7,
@@ -272,7 +273,7 @@ static void beat_lpar_hpte_updateboltedpp(unsigned long newpp,
 	BUG_ON(lpar_rc != 0);
 }
 
-static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
+static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
 					 int psize, int ssize, int local)
 {
 	unsigned long want_v;
@@ -282,7 +283,7 @@ static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
 
 	DBG_LOW("    inval : slot=%lx, va=%016lx, psize: %d, local: %d\n",
 		slot, va, psize, local);
-	want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M);
+	want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
 
 	raw_spin_lock_irqsave(&beat_htab_lock, flags);
 	dummy1 = beat_lpar_hpte_getword0(slot);
@@ -311,7 +312,7 @@ void __init hpte_init_beat(void)
 }
 
 static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
-				  unsigned long va, unsigned long pa,
+				  unsigned long vpn, unsigned long pa,
 				  unsigned long rflags, unsigned long vflags,
 				  int psize, int ssize)
 {
@@ -322,11 +323,11 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
 		return -1;
 
 	if (!(vflags & HPTE_V_BOLTED))
-		DBG_LOW("hpte_insert(group=%lx, va=%016lx, pa=%016lx, "
+		DBG_LOW("hpte_insert(group=%lx, vpn=%016lx, pa=%016lx, "
 			"rflags=%lx, vflags=%lx, psize=%d)\n",
-		hpte_group, va, pa, rflags, vflags, psize);
+		hpte_group, vpn, pa, rflags, vflags, psize);
 
-	hpte_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M) |
+	hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) |
 		vflags | HPTE_V_VALID;
 	hpte_r = hpte_encode_r(pa, psize) | rflags;
 
@@ -364,14 +365,14 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
  */
 static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
 				    unsigned long newpp,
-				    unsigned long va,
+				    unsigned long vpn,
 				    int psize, int ssize, int local)
 {
 	unsigned long lpar_rc;
 	unsigned long want_v;
 	unsigned long pss;
 
-	want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M);
+	want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
 	pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
 
 	DBG_LOW("    update: "
@@ -392,16 +393,16 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
 	return 0;
 }
 
-static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long va,
+static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn,
 					 int psize, int ssize, int local)
 {
 	unsigned long want_v;
 	unsigned long lpar_rc;
 	unsigned long pss;
 
-	DBG_LOW("    inval : slot=%lx, va=%016lx, psize: %d, local: %d\n",
-		slot, va, psize, local);
-	want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M);
+	DBG_LOW("    inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n",
+		slot, vpn, psize, local);
+	want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
 	pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
 
 	lpar_rc = beat_invalidate_htab_entry3(0, slot, want_v, pss);
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index 14943ef..7d2d036 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -19,12 +19,12 @@
 
 #undef DEBUG
 
+#include <linux/memblock.h>
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/pci.h>
 #include <asm/iommu.h>
 #include <asm/machdep.h>
-#include <asm/abs_addr.h>
 #include <asm/firmware.h>
 
 #define IOBMAP_PAGE_SHIFT	12
@@ -99,7 +99,7 @@ static int iobmap_build(struct iommu_table *tbl, long index,
 	ip = ((u32 *)tbl->it_base) + index;
 
 	while (npages--) {
-		rpn = virt_to_abs(uaddr) >> IOBMAP_PAGE_SHIFT;
+		rpn = __pa(uaddr) >> IOBMAP_PAGE_SHIFT;
 
 		*(ip++) = IOBMAP_L2E_V | rpn;
 		/* invalidate tlb, can be optimized more */
@@ -258,7 +258,7 @@ void __init alloc_iobmap_l2(void)
 	return;
 #endif
 	/* For 2G space, 8x64 pages (2^21 bytes) is max total l2 size */
-	iob_l2_base = (u32 *)abs_to_virt(memblock_alloc_base(1UL<<21, 1UL<<21, 0x80000000));
+	iob_l2_base = (u32 *)__va(memblock_alloc_base(1UL<<21, 1UL<<21, 0x80000000));
 
 	printk(KERN_INFO "IOBMAP L2 allocated at: %p\n", iob_l2_base);
 }
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 0e7eccc..471aa3c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -30,19 +30,10 @@
 #include <asm/opal.h>
 #include <asm/iommu.h>
 #include <asm/tce.h>
-#include <asm/abs_addr.h>
 
 #include "powernv.h"
 #include "pci.h"
 
-struct resource_wrap {
-	struct list_head	link;
-	resource_size_t		size;
-	resource_size_t		align;
-	struct pci_dev		*dev;	/* Set if it's a device */
-	struct pci_bus		*bus;	/* Set if it's a bridge */
-};
-
 static int __pe_printk(const char *level, const struct pnv_ioda_pe *pe,
 		       struct va_format *vaf)
 {
@@ -78,273 +69,6 @@ define_pe_printk_level(pe_err, KERN_ERR);
 define_pe_printk_level(pe_warn, KERN_WARNING);
 define_pe_printk_level(pe_info, KERN_INFO);
 
-
-/* Calculate resource usage & alignment requirement of a single
- * device. This will also assign all resources within the device
- * for a given type starting at 0 for the biggest one and then
- * assigning in decreasing order of size.
- */
-static void __devinit pnv_ioda_calc_dev(struct pci_dev *dev, unsigned int flags,
-					resource_size_t *size,
-					resource_size_t *align)
-{
-	resource_size_t start;
-	struct resource *r;
-	int i;
-
-	pr_devel("  -> CDR %s\n", pci_name(dev));
-
-	*size = *align = 0;
-
-	/* Clear the resources out and mark them all unset */
-	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
-		r = &dev->resource[i];
-		if (!(r->flags & flags))
-		    continue;
-		if (r->start) {
-			r->end -= r->start;
-			r->start = 0;
-		}
-		r->flags |= IORESOURCE_UNSET;
-	}
-
-	/* We currently keep all memory resources together, we
-	 * will handle prefetch & 64-bit separately in the future
-	 * but for now we stick everybody in M32
-	 */
-	start = 0;
-	for (;;) {
-		resource_size_t max_size = 0;
-		int max_no = -1;
-
-		/* Find next biggest resource */
-		for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
-			r = &dev->resource[i];
-			if (!(r->flags & IORESOURCE_UNSET) ||
-			    !(r->flags & flags))
-				continue;
-			if (resource_size(r) > max_size) {
-				max_size = resource_size(r);
-				max_no = i;
-			}
-		}
-		if (max_no < 0)
-			break;
-		r = &dev->resource[max_no];
-		if (max_size > *align)
-			*align = max_size;
-		*size += max_size;
-		r->start = start;
-		start += max_size;
-		r->end = r->start + max_size - 1;
-		r->flags &= ~IORESOURCE_UNSET;
-		pr_devel("  ->     R%d %016llx..%016llx\n",
-			 max_no, r->start, r->end);
-	}
-	pr_devel("  <- CDR %s size=%llx align=%llx\n",
-		 pci_name(dev), *size, *align);
-}
-
-/* Allocate a resource "wrap" for a given device or bridge and
- * insert it at the right position in the sorted list
- */
-static void __devinit pnv_ioda_add_wrap(struct list_head *list,
-					struct pci_bus *bus,
-					struct pci_dev *dev,
-					resource_size_t size,
-					resource_size_t align)
-{
-	struct resource_wrap *w1, *w = kzalloc(sizeof(*w), GFP_KERNEL);
-
-	w->size = size;
-	w->align = align;
-	w->dev = dev;
-	w->bus = bus;
-
-	list_for_each_entry(w1, list, link) {
-		if (w1->align < align) {
-			list_add_tail(&w->link, &w1->link);
-			return;
-		}
-	}
-	list_add_tail(&w->link, list);
-}
-
-/* Offset device resources of a given type */
-static void __devinit pnv_ioda_offset_dev(struct pci_dev *dev,
-					  unsigned int flags,
-					  resource_size_t offset)
-{
-	struct resource *r;
-	int i;
-
-	pr_devel("  -> ODR %s [%x] +%016llx\n", pci_name(dev), flags, offset);
-
-	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
-		r = &dev->resource[i];
-		if (r->flags & flags) {
-			dev->resource[i].start += offset;
-			dev->resource[i].end += offset;
-		}
-	}
-
-	pr_devel("  <- ODR %s [%x] +%016llx\n", pci_name(dev), flags, offset);
-}
-
-/* Offset bus resources (& all children) of a given type */
-static void __devinit pnv_ioda_offset_bus(struct pci_bus *bus,
-					  unsigned int flags,
-					  resource_size_t offset)
-{
-	struct resource *r;
-	struct pci_dev *dev;
-	struct pci_bus *cbus;
-	int i;
-
-	pr_devel("  -> OBR %s [%x] +%016llx\n",
-		 bus->self ? pci_name(bus->self) : "root", flags, offset);
-
-	pci_bus_for_each_resource(bus, r, i) {
-		if (r && (r->flags & flags)) {
-			r->start += offset;
-			r->end += offset;
-		}
-	}
-	list_for_each_entry(dev, &bus->devices, bus_list)
-		pnv_ioda_offset_dev(dev, flags, offset);
-	list_for_each_entry(cbus, &bus->children, node)
-		pnv_ioda_offset_bus(cbus, flags, offset);
-
-	pr_devel("  <- OBR %s [%x]\n",
-		 bus->self ? pci_name(bus->self) : "root", flags);
-}
-
-/* This is the guts of our IODA resource allocation. This is called
- * recursively for each bus in the system. It calculates all the
- * necessary size and requirements for children and assign them
- * resources such that:
- *
- *   - Each function fits in it's own contiguous set of IO/M32
- *     segment
- *
- *   - All segments behind a P2P bridge are contiguous and obey
- *     alignment constraints of those bridges
- */
-static void __devinit pnv_ioda_calc_bus(struct pci_bus *bus, unsigned int flags,
-					resource_size_t *size,
-					resource_size_t *align)
-{
-	struct pci_controller *hose = pci_bus_to_host(bus);
-	struct pnv_phb *phb = hose->private_data;
-	resource_size_t dev_size, dev_align, start;
-	resource_size_t min_align, min_balign;
-	struct pci_dev *cdev;
-	struct pci_bus *cbus;
-	struct list_head head;
-	struct resource_wrap *w;
-	unsigned int bres;
-
-	*size = *align = 0;
-
-	pr_devel("-> CBR %s [%x]\n",
-		 bus->self ? pci_name(bus->self) : "root", flags);
-
-	/* Calculate alignment requirements based on the type
-	 * of resource we are working on
-	 */
-	if (flags & IORESOURCE_IO) {
-		bres = 0;
-		min_align = phb->ioda.io_segsize;
-		min_balign = 0x1000;
-	} else {
-		bres = 1;
-		min_align = phb->ioda.m32_segsize;
-		min_balign = 0x100000;
-	}
-
-	/* Gather all our children resources ordered by alignment */
-	INIT_LIST_HEAD(&head);
-
-	/*   - Busses */
-	list_for_each_entry(cbus, &bus->children, node) {
-		pnv_ioda_calc_bus(cbus, flags, &dev_size, &dev_align);
-		pnv_ioda_add_wrap(&head, cbus, NULL, dev_size, dev_align);
-	}
-
-	/*   - Devices */
-	list_for_each_entry(cdev, &bus->devices, bus_list) {
-		pnv_ioda_calc_dev(cdev, flags, &dev_size, &dev_align);
-		/* Align them to segment size */
-		if (dev_align < min_align)
-			dev_align = min_align;
-		pnv_ioda_add_wrap(&head, NULL, cdev, dev_size, dev_align);
-	}
-	if (list_empty(&head))
-		goto empty;
-
-	/* Now we can do two things: assign offsets to them within that
-	 * level and get our total alignment & size requirements. The
-	 * assignment algorithm is going to be uber-trivial for now, we
-	 * can try to be smarter later at filling out holes.
-	 */
-	if (bus->self) {
-		/* No offset for downstream bridges */
-		start = 0;
-	} else {
-		/* Offset from the root */
-		if (flags & IORESOURCE_IO)
-			/* Don't hand out IO 0 */
-			start = hose->io_resource.start + 0x1000;
-		else
-			start = hose->mem_resources[0].start;
-	}
-	while(!list_empty(&head)) {
-		w = list_first_entry(&head, struct resource_wrap, link);
-		list_del(&w->link);
-		if (w->size) {
-			if (start) {
-				start = ALIGN(start, w->align);
-				if (w->dev)
-					pnv_ioda_offset_dev(w->dev,flags,start);
-				else if (w->bus)
-					pnv_ioda_offset_bus(w->bus,flags,start);
-			}
-			if (w->align > *align)
-				*align = w->align;
-		}
-		start += w->size;
-		kfree(w);
-	}
-	*size = start;
-
-	/* Align and setup bridge resources */
-	*align = max_t(resource_size_t, *align,
-		       max_t(resource_size_t, min_align, min_balign));
-	*size = ALIGN(*size,
-		      max_t(resource_size_t, min_align, min_balign));
- empty:
-	/* Only setup P2P's, not the PHB itself */
-	if (bus->self) {
-		struct resource *res = bus->resource[bres];
-
-		if (WARN_ON(res == NULL))
-			return;
-
-		/*
-		 * FIXME: We should probably export and call
-		 * pci_bridge_check_ranges() to properly re-initialize
-		 * the PCI portion of the flags here, and to detect
-		 * what the bridge actually supports.
-		 */
-		res->start = 0;
-		res->flags = (*size) ? flags : 0;
-		res->end = (*size) ? (*size - 1) : 0;
-	}
-
-	pr_devel("<- CBR %s [%x] *size=%016llx *align=%016llx\n",
-		 bus->self ? pci_name(bus->self) : "root", flags,*size,*align);
-}
-
 static struct pci_dn *pnv_ioda_get_pdn(struct pci_dev *dev)
 {
 	struct device_node *np;
@@ -355,172 +79,6 @@ static struct pci_dn *pnv_ioda_get_pdn(struct pci_dev *dev)
 	return PCI_DN(np);
 }
 
-static void __devinit pnv_ioda_setup_pe_segments(struct pci_dev *dev)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	struct pci_dn *pdn = pnv_ioda_get_pdn(dev);
-	unsigned int pe, i;
-	resource_size_t pos;
-	struct resource io_res;
-	struct resource m32_res;
-	struct pci_bus_region region;
-	int rc;
-
-	/* Anything not referenced in the device-tree gets PE#0 */
-	pe = pdn ? pdn->pe_number : 0;
-
-	/* Calculate the device min/max */
-	io_res.start = m32_res.start = (resource_size_t)-1;
-	io_res.end = m32_res.end = 0;
-	io_res.flags = IORESOURCE_IO;
-	m32_res.flags = IORESOURCE_MEM;
-
-	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
-		struct resource *r = NULL;
-		if (dev->resource[i].flags & IORESOURCE_IO)
-			r = &io_res;
-		if (dev->resource[i].flags & IORESOURCE_MEM)
-			r = &m32_res;
-		if (!r)
-			continue;
-		if (dev->resource[i].start < r->start)
-			r->start = dev->resource[i].start;
-		if (dev->resource[i].end > r->end)
-			r->end = dev->resource[i].end;
-	}
-
-	/* Setup IO segments */
-	if (io_res.start < io_res.end) {
-		pcibios_resource_to_bus(dev, &region, &io_res);
-		pos = region.start;
-		i = pos / phb->ioda.io_segsize;
-		while(i < phb->ioda.total_pe && pos <= region.end) {
-			if (phb->ioda.io_segmap[i]) {
-				pr_err("%s: Trying to use IO seg #%d which is"
-				       " already used by PE# %d\n",
-				       pci_name(dev), i,
-				       phb->ioda.io_segmap[i]);
-				/* XXX DO SOMETHING TO DISABLE DEVICE ? */
-				break;
-			}
-			phb->ioda.io_segmap[i] = pe;
-			rc = opal_pci_map_pe_mmio_window(phb->opal_id, pe,
-							 OPAL_IO_WINDOW_TYPE,
-							 0, i);
-			if (rc != OPAL_SUCCESS) {
-				pr_err("%s: OPAL error %d setting up mapping"
-				       " for IO seg# %d\n",
-				       pci_name(dev), rc, i);
-				/* XXX DO SOMETHING TO DISABLE DEVICE ? */
-				break;
-			}
-			pos += phb->ioda.io_segsize;
-			i++;
-		};
-	}
-
-	/* Setup M32 segments */
-	if (m32_res.start < m32_res.end) {
-		pcibios_resource_to_bus(dev, &region, &m32_res);
-		pos = region.start;
-		i = pos / phb->ioda.m32_segsize;
-		while(i < phb->ioda.total_pe && pos <= region.end) {
-			if (phb->ioda.m32_segmap[i]) {
-				pr_err("%s: Trying to use M32 seg #%d which is"
-				       " already used by PE# %d\n",
-				       pci_name(dev), i,
-				       phb->ioda.m32_segmap[i]);
-				/* XXX DO SOMETHING TO DISABLE DEVICE ? */
-				break;
-			}
-			phb->ioda.m32_segmap[i] = pe;
-			rc = opal_pci_map_pe_mmio_window(phb->opal_id, pe,
-							 OPAL_M32_WINDOW_TYPE,
-							 0, i);
-			if (rc != OPAL_SUCCESS) {
-				pr_err("%s: OPAL error %d setting up mapping"
-				       " for M32 seg# %d\n",
-				       pci_name(dev), rc, i);
-				/* XXX DO SOMETHING TO DISABLE DEVICE ? */
-				break;
-			}
-			pos += phb->ioda.m32_segsize;
-			i++;
-		}
-	}
-}
-
-/* Check if a resource still fits in the total IO or M32 range
- * for a given PHB
- */
-static int __devinit pnv_ioda_resource_fit(struct pci_controller *hose,
-					   struct resource *r)
-{
-	struct resource *bounds;
-
-	if (r->flags & IORESOURCE_IO)
-		bounds = &hose->io_resource;
-	else if (r->flags & IORESOURCE_MEM)
-		bounds = &hose->mem_resources[0];
-	else
-		return 1;
-
-	if (r->start >= bounds->start && r->end <= bounds->end)
-		return 1;
-	r->flags = 0;
-	return 0;
-}
-
-static void __devinit pnv_ioda_update_resources(struct pci_bus *bus)
-{
-	struct pci_controller *hose = pci_bus_to_host(bus);
-	struct pci_bus *cbus;
-	struct pci_dev *cdev;
-	unsigned int i;
-
-	/* We used to clear all device enables here. However it looks like
-	 * clearing MEM enable causes Obsidian (IPR SCS) to go bonkers,
-	 * and shoot fatal errors to the PHB which in turns fences itself
-	 * and we can't recover from that ... yet. So for now, let's leave
-	 * the enables as-is and hope for the best.
-	 */
-
-	/* Check if bus resources fit in our IO or M32 range */
-	for (i = 0; bus->self && (i < 2); i++) {
-		struct resource *r = bus->resource[i];
-		if (r && !pnv_ioda_resource_fit(hose, r))
-			pr_err("%s: Bus %d resource %d disabled, no room\n",
-			       pci_name(bus->self), bus->number, i);
-	}
-
-	/* Update self if it's not a PHB */
-	if (bus->self)
-		pci_setup_bridge(bus);
-
-	/* Update child devices */
-	list_for_each_entry(cdev, &bus->devices, bus_list) {
-		/* Check if resource fits, if not, disabled it */
-		for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
-			struct resource *r = &cdev->resource[i];
-			if (!pnv_ioda_resource_fit(hose, r))
-				pr_err("%s: Resource %d disabled, no room\n",
-				       pci_name(cdev), i);
-		}
-
-		/* Assign segments */
-		pnv_ioda_setup_pe_segments(cdev);
-
-		/* Update HW BARs */
-		for (i = 0; i <= PCI_ROM_RESOURCE; i++)
-			pci_update_resource(cdev, i);
-	}
-
-	/* Update child busses */
-	list_for_each_entry(cbus, &bus->children, node)
-		pnv_ioda_update_resources(cbus);
-}
-
 static int __devinit pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
 	unsigned long pe;
@@ -548,7 +106,7 @@ static void __devinit pnv_ioda_free_pe(struct pnv_phb *phb, int pe)
  * but in the meantime, we need to protect them to avoid warnings
  */
 #ifdef CONFIG_PCI_MSI
-static struct pnv_ioda_pe * __devinit __pnv_ioda_get_one_pe(struct pci_dev *dev)
+static struct pnv_ioda_pe * __devinit pnv_ioda_get_pe(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 	struct pnv_phb *phb = hose->private_data;
@@ -560,19 +118,6 @@ static struct pnv_ioda_pe * __devinit __pnv_ioda_get_one_pe(struct pci_dev *dev)
 		return NULL;
 	return &phb->ioda.pe_array[pdn->pe_number];
 }
-
-static struct pnv_ioda_pe * __devinit pnv_ioda_get_pe(struct pci_dev *dev)
-{
-	struct pnv_ioda_pe *pe = __pnv_ioda_get_one_pe(dev);
-
-	while (!pe && dev->bus->self) {
-		dev = dev->bus->self;
-		pe = __pnv_ioda_get_one_pe(dev);
-		if (pe)
-			pe = pe->bus_pe;
-	}
-	return pe;
-}
 #endif /* CONFIG_PCI_MSI */
 
 static int __devinit pnv_ioda_configure_pe(struct pnv_phb *phb,
@@ -589,7 +134,11 @@ static int __devinit pnv_ioda_configure_pe(struct pnv_phb *phb,
 		dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER;
 		fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
 		parent = pe->pbus->self;
-		count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
+		if (pe->flags & PNV_IODA_PE_BUS_ALL)
+			count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
+		else
+			count = 1;
+
 		switch(count) {
 		case  1: bcomp = OpalPciBusAll;		break;
 		case  2: bcomp = OpalPciBus7Bits;	break;
@@ -666,13 +215,13 @@ static void __devinit pnv_ioda_link_pe_by_weight(struct pnv_phb *phb,
 {
 	struct pnv_ioda_pe *lpe;
 
-	list_for_each_entry(lpe, &phb->ioda.pe_list, link) {
+	list_for_each_entry(lpe, &phb->ioda.pe_dma_list, dma_link) {
 		if (lpe->dma_weight < pe->dma_weight) {
-			list_add_tail(&pe->link, &lpe->link);
+			list_add_tail(&pe->dma_link, &lpe->dma_link);
 			return;
 		}
 	}
-	list_add_tail(&pe->link, &phb->ioda.pe_list);
+	list_add_tail(&pe->dma_link, &phb->ioda.pe_dma_list);
 }
 
 static unsigned int pnv_ioda_dma_weight(struct pci_dev *dev)
@@ -699,6 +248,7 @@ static unsigned int pnv_ioda_dma_weight(struct pci_dev *dev)
 	return 10;
 }
 
+#if 0
 static struct pnv_ioda_pe * __devinit pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
@@ -767,6 +317,7 @@ static struct pnv_ioda_pe * __devinit pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 
 	return pe;
 }
+#endif /* Useful for SRIOV case */
 
 static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
 {
@@ -784,34 +335,33 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
 		pdn->pcidev = dev;
 		pdn->pe_number = pe->pe_number;
 		pe->dma_weight += pnv_ioda_dma_weight(dev);
-		if (dev->subordinate)
+		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
 			pnv_ioda_setup_same_PE(dev->subordinate, pe);
 	}
 }
 
-static void __devinit pnv_ioda_setup_bus_PE(struct pci_dev *dev,
-					    struct pnv_ioda_pe *ppe)
+/*
+ * There're 2 types of PCI bus sensitive PEs: One that is compromised of
+ * single PCI bus. Another one that contains the primary PCI bus and its
+ * subordinate PCI devices and buses. The second type of PE is normally
+ * orgiriated by PCIe-to-PCI bridge or PLX switch downstream ports.
+ */
+static void __devinit pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
 {
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pci_controller *hose = pci_bus_to_host(bus);
 	struct pnv_phb *phb = hose->private_data;
-	struct pci_bus *bus = dev->subordinate;
 	struct pnv_ioda_pe *pe;
 	int pe_num;
 
-	if (!bus) {
-		pr_warning("%s: Bridge without a subordinate bus !\n",
-			   pci_name(dev));
-		return;
-	}
 	pe_num = pnv_ioda_alloc_pe(phb);
 	if (pe_num == IODA_INVALID_PE) {
-		pr_warning("%s: Not enough PE# available, disabling bus\n",
-			   pci_name(dev));
+		pr_warning("%s: Not enough PE# available for PCI bus %04x:%02x\n",
+			__func__, pci_domain_nr(bus), bus->number);
 		return;
 	}
 
 	pe = &phb->ioda.pe_array[pe_num];
-	ppe->bus_pe = pe;
+	pe->flags = (all ? PNV_IODA_PE_BUS_ALL : PNV_IODA_PE_BUS);
 	pe->pbus = bus;
 	pe->pdev = NULL;
 	pe->tce32_seg = -1;
@@ -819,8 +369,12 @@ static void __devinit pnv_ioda_setup_bus_PE(struct pci_dev *dev,
 	pe->rid = bus->busn_res.start << 8;
 	pe->dma_weight = 0;
 
-	pe_info(pe, "Secondary busses %pR associated with PE\n",
-		&bus->busn_res);
+	if (all)
+		pe_info(pe, "Secondary bus %d..%d associated with PE#%d\n",
+			bus->busn_res.start, bus->busn_res.end, pe_num);
+	else
+		pe_info(pe, "Secondary bus %d associated with PE#%d\n",
+			bus->busn_res.start, pe_num);
 
 	if (pnv_ioda_configure_pe(phb, pe)) {
 		/* XXX What do we do here ? */
@@ -833,6 +387,9 @@ static void __devinit pnv_ioda_setup_bus_PE(struct pci_dev *dev,
 	/* Associate it with all child devices */
 	pnv_ioda_setup_same_PE(bus, pe);
 
+	/* Put PE to the list */
+	list_add_tail(&pe->list, &phb->ioda.pe_list);
+
 	/* Account for one DMA PE if at least one DMA capable device exist
 	 * below the bridge
 	 */
@@ -848,17 +405,33 @@ static void __devinit pnv_ioda_setup_bus_PE(struct pci_dev *dev,
 static void __devinit pnv_ioda_setup_PEs(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
-	struct pnv_ioda_pe *pe;
+
+	pnv_ioda_setup_bus_PE(bus, 0);
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
-		pe = pnv_ioda_setup_dev_PE(dev);
-		if (pe == NULL)
-			continue;
-		/* Leaving the PCIe domain ... single PE# */
-		if (pci_pcie_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE)
-			pnv_ioda_setup_bus_PE(dev, pe);
-		else if (dev->subordinate)
-			pnv_ioda_setup_PEs(dev->subordinate);
+		if (dev->subordinate) {
+			if (pci_pcie_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE)
+				pnv_ioda_setup_bus_PE(dev->subordinate, 1);
+			else
+				pnv_ioda_setup_PEs(dev->subordinate);
+		}
+	}
+}
+
+/*
+ * Configure PEs so that the downstream PCI buses and devices
+ * could have their associated PE#. Unfortunately, we didn't
+ * figure out the way to identify the PLX bridge yet. So we
+ * simply put the PCI bus and the subordinate behind the root
+ * port to PE# here. The game rule here is expected to be changed
+ * as soon as we can detected PLX bridge correctly.
+ */
+static void __devinit pnv_pci_ioda_setup_PEs(void)
+{
+	struct pci_controller *hose, *tmp;
+
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		pnv_ioda_setup_PEs(hose->bus);
 	}
 }
 
@@ -1000,7 +573,7 @@ static void __devinit pnv_ioda_setup_dma(struct pnv_phb *phb)
 	remaining = phb->ioda.tce32_count;
 	tw = phb->ioda.dma_weight;
 	base = 0;
-	list_for_each_entry(pe, &phb->ioda.pe_list, link) {
+	list_for_each_entry(pe, &phb->ioda.pe_dma_list, dma_link) {
 		if (!pe->dma_weight)
 			continue;
 		if (!remaining) {
@@ -1109,36 +682,115 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb)
 static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { }
 #endif /* CONFIG_PCI_MSI */
 
-/* This is the starting point of our IODA specific resource
- * allocation process
+/*
+ * This function is supposed to be called on basis of PE from top
+ * to bottom style. So the the I/O or MMIO segment assigned to
+ * parent PE could be overrided by its child PEs if necessary.
  */
-static void __devinit pnv_pci_ioda_fixup_phb(struct pci_controller *hose)
+static void __devinit pnv_ioda_setup_pe_seg(struct pci_controller *hose,
+				struct pnv_ioda_pe *pe)
 {
-	resource_size_t size, align;
-	struct pci_bus *child;
+	struct pnv_phb *phb = hose->private_data;
+	struct pci_bus_region region;
+	struct resource *res;
+	int i, index;
+	int rc;
 
-	/* Associate PEs per functions */
-	pnv_ioda_setup_PEs(hose->bus);
+	/*
+	 * NOTE: We only care PCI bus based PE for now. For PCI
+	 * device based PE, for example SRIOV sensitive VF should
+	 * be figured out later.
+	 */
+	BUG_ON(!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)));
 
-	/* Calculate all resources */
-	pnv_ioda_calc_bus(hose->bus, IORESOURCE_IO, &size, &align);
-	pnv_ioda_calc_bus(hose->bus, IORESOURCE_MEM, &size, &align);
+	pci_bus_for_each_resource(pe->pbus, res, i) {
+		if (!res || !res->flags ||
+		    res->start > res->end)
+			continue;
 
-	/* Apply then to HW */
-	pnv_ioda_update_resources(hose->bus);
+		if (res->flags & IORESOURCE_IO) {
+			region.start = res->start - phb->ioda.io_pci_base;
+			region.end   = res->end - phb->ioda.io_pci_base;
+			index = region.start / phb->ioda.io_segsize;
+
+			while (index < phb->ioda.total_pe &&
+			       region.start <= region.end) {
+				phb->ioda.io_segmap[index] = pe->pe_number;
+				rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+					pe->pe_number, OPAL_IO_WINDOW_TYPE, 0, index);
+				if (rc != OPAL_SUCCESS) {
+					pr_err("%s: OPAL error %d when mapping IO "
+					       "segment #%d to PE#%d\n",
+					       __func__, rc, index, pe->pe_number);
+					break;
+				}
+
+				region.start += phb->ioda.io_segsize;
+				index++;
+			}
+		} else if (res->flags & IORESOURCE_MEM) {
+			region.start = res->start -
+				       hose->pci_mem_offset -
+				       phb->ioda.m32_pci_base;
+			region.end   = res->end -
+				       hose->pci_mem_offset -
+				       phb->ioda.m32_pci_base;
+			index = region.start / phb->ioda.m32_segsize;
+
+			while (index < phb->ioda.total_pe &&
+			       region.start <= region.end) {
+				phb->ioda.m32_segmap[index] = pe->pe_number;
+				rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+					pe->pe_number, OPAL_M32_WINDOW_TYPE, 0, index);
+				if (rc != OPAL_SUCCESS) {
+					pr_err("%s: OPAL error %d when mapping M32 "
+					       "segment#%d to PE#%d",
+					       __func__, rc, index, pe->pe_number);
+					break;
+				}
+
+				region.start += phb->ioda.m32_segsize;
+				index++;
+			}
+		}
+	}
+}
 
-	/* Setup DMA */
-	pnv_ioda_setup_dma(hose->private_data);
+static void __devinit pnv_pci_ioda_setup_seg(void)
+{
+	struct pci_controller *tmp, *hose;
+	struct pnv_phb *phb;
+	struct pnv_ioda_pe *pe;
 
-	/* Configure PCI Express settings */
-	list_for_each_entry(child, &hose->bus->children, node) {
-		struct pci_dev *self = child->self;
-		if (!self)
-			continue;
-		pcie_bus_configure_settings(child, self->pcie_mpss);
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		phb = hose->private_data;
+		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+			pnv_ioda_setup_pe_seg(hose, pe);
+		}
+	}
+}
+
+static void __devinit pnv_pci_ioda_setup_DMA(void)
+{
+	struct pci_controller *hose, *tmp;
+	struct pnv_phb *phb;
+
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		pnv_ioda_setup_dma(hose->private_data);
+
+		/* Mark the PHB initialization done */
+		phb = hose->private_data;
+		phb->initialized = 1;
 	}
 }
 
+static void __devinit pnv_pci_ioda_fixup(void)
+{
+	pnv_pci_ioda_setup_PEs();
+	pnv_pci_ioda_setup_seg();
+	pnv_pci_ioda_setup_DMA();
+}
+
 /*
  * Returns the alignment for I/O or memory windows for P2P
  * bridges. That actually depends on how PEs are segmented.
@@ -1182,10 +834,22 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
  */
 static int __devinit pnv_pci_enable_device_hook(struct pci_dev *dev)
 {
-	struct pci_dn *pdn = pnv_ioda_get_pdn(dev);
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pci_dn *pdn;
 
+	/* The function is probably called while the PEs have
+	 * not be created yet. For example, resource reassignment
+	 * during PCI probe period. We just skip the check if
+	 * PEs isn't ready.
+	 */
+	if (!phb->initialized)
+		return 0;
+
+	pdn = pnv_ioda_get_pdn(dev);
 	if (!pdn || pdn->pe_number == IODA_INVALID_PE)
 		return -EINVAL;
+
 	return 0;
 }
 
@@ -1276,9 +940,9 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np)
 	/* Allocate aux data & arrays */
 	size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
 	m32map_off = size;
-	size += phb->ioda.total_pe;
+	size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]);
 	iomap_off = size;
-	size += phb->ioda.total_pe;
+	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);
@@ -1289,6 +953,7 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np)
 	phb->ioda.pe_array = aux + pemap_off;
 	set_bit(0, phb->ioda.pe_alloc);
 
+	INIT_LIST_HEAD(&phb->ioda.pe_dma_list);
 	INIT_LIST_HEAD(&phb->ioda.pe_list);
 
 	/* Calculate how many 32-bit TCE segments we have */
@@ -1337,15 +1002,17 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np)
 	/* Setup MSI support */
 	pnv_pci_init_ioda_msis(phb);
 
-	/* We set both PCI_PROBE_ONLY and PCI_REASSIGN_ALL_RSRC. This is an
-	 * odd combination which essentially means that we skip all resource
-	 * fixups and assignments in the generic code, and do it all
-	 * ourselves here
+	/*
+	 * We pass the PCI probe flag PCI_REASSIGN_ALL_RSRC here
+	 * to let the PCI core do resource assignment. It's supposed
+	 * that the PCI core will do correct I/O and MMIO alignment
+	 * for the P2P bridge bars so that each PCI bus (excluding
+	 * the child P2P bridges) can form individual PE.
 	 */
-	ppc_md.pcibios_fixup_phb = pnv_pci_ioda_fixup_phb;
+	ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
 	ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook;
 	ppc_md.pcibios_window_alignment = pnv_pci_window_alignment;
-	pci_add_flags(PCI_PROBE_ONLY | PCI_REASSIGN_ALL_RSRC);
+	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 
 	/* Reset IODA tables to a clean state */
 	rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET);
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
index 2649677..6b4bef4 100644
--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -30,7 +30,6 @@
 #include <asm/opal.h>
 #include <asm/iommu.h>
 #include <asm/tce.h>
-#include <asm/abs_addr.h>
 
 #include "powernv.h"
 #include "pci.h"
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index be3cfc5..c01688a 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -30,7 +30,6 @@
 #include <asm/opal.h>
 #include <asm/iommu.h>
 #include <asm/tce.h>
-#include <asm/abs_addr.h>
 #include <asm/firmware.h>
 
 #include "powernv.h"
@@ -447,6 +446,11 @@ static void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
 		pnv_tce_invalidate(tbl, tces, tcep - 1);
 }
 
+static unsigned long pnv_tce_get(struct iommu_table *tbl, long index)
+{
+	return ((u64 *)tbl->it_base)[index - tbl->it_offset];
+}
+
 void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 			       void *tce_mem, u64 tce_size,
 			       u64 dma_offset)
@@ -597,6 +601,7 @@ void __init pnv_pci_init(void)
 	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_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 8bc4796..7cfb7c8 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -17,9 +17,14 @@ enum pnv_phb_model {
 };
 
 #define PNV_PCI_DIAG_BUF_SIZE	4096
+#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	*/
 
 /* Data associated with a PE, including IOMMU tracking etc.. */
 struct pnv_ioda_pe {
+	unsigned long		flags;
+
 	/* A PE can be associated with a single device or an
 	 * entire bus (& children). In the former case, pdev
 	 * is populated, in the later case, pbus is.
@@ -40,11 +45,6 @@ struct pnv_ioda_pe {
 	 */
 	unsigned int		dma_weight;
 
-	/* This is a PCI-E -> PCI-X bridge, this points to the
-	 * corresponding bus PE
-	 */
-	struct pnv_ioda_pe	*bus_pe;
-
 	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
 	int			tce32_seg;
 	int			tce32_segcount;
@@ -59,7 +59,8 @@ struct pnv_ioda_pe {
 	int			mve_number;
 
 	/* Link in list of PE#s */
-	struct list_head	link;
+	struct list_head	dma_link;
+	struct list_head	list;
 };
 
 struct pnv_phb {
@@ -68,6 +69,7 @@ struct pnv_phb {
 	enum pnv_phb_model	model;
 	u64			opal_id;
 	void __iomem		*regs;
+	int			initialized;
 	spinlock_t		lock;
 
 #ifdef CONFIG_PCI_MSI
@@ -107,6 +109,11 @@ struct pnv_phb {
 			unsigned int		*io_segmap;
 			struct pnv_ioda_pe	*pe_array;
 
+			/* Sorted list of used PE's based
+			 * on the sequence of creation
+			 */
+			struct list_head	pe_list;
+
 			/* Reverse map of PEs, will have to extend if
 			 * we are to support more than 256 PEs, indexed
 			 * bus { bus, devfn }
@@ -125,7 +132,7 @@ struct pnv_phb {
 			/* Sorted list of used PE's, sorted at
 			 * boot for resource allocation purposes
 			 */
-			struct list_head	pe_list;
+			struct list_head	pe_dma_list;
 		} ioda;
 	};
 
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index 3124cf7..d00d7b0 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -43,7 +43,7 @@ enum ps3_lpar_vas_id {
 
 static DEFINE_SPINLOCK(ps3_htab_lock);
 
-static long ps3_hpte_insert(unsigned long hpte_group, unsigned long va,
+static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 	unsigned long pa, unsigned long rflags, unsigned long vflags,
 	int psize, int ssize)
 {
@@ -61,7 +61,7 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long va,
 	 */
 	vflags &= ~HPTE_V_SECONDARY;
 
-	hpte_v = hpte_encode_v(va, psize, ssize) | vflags | HPTE_V_VALID;
+	hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
 	hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize) | rflags;
 
 	spin_lock_irqsave(&ps3_htab_lock, flags);
@@ -75,8 +75,8 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long va,
 
 	if (result) {
 		/* all entries bolted !*/
-		pr_info("%s:result=%d va=%lx pa=%lx ix=%lx v=%llx r=%llx\n",
-			__func__, result, va, pa, hpte_group, hpte_v, hpte_r);
+		pr_info("%s:result=%d vpn=%lx pa=%lx ix=%lx v=%llx r=%llx\n",
+			__func__, result, vpn, pa, hpte_group, hpte_v, hpte_r);
 		BUG();
 	}
 
@@ -107,7 +107,7 @@ static long ps3_hpte_remove(unsigned long hpte_group)
 }
 
 static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
-	unsigned long va, int psize, int ssize, int local)
+	unsigned long vpn, int psize, int ssize, int local)
 {
 	int result;
 	u64 hpte_v, want_v, hpte_rs;
@@ -115,7 +115,7 @@ static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	unsigned long flags;
 	long ret;
 
-	want_v = hpte_encode_v(va, psize, ssize);
+	want_v = hpte_encode_v(vpn, psize, ssize);
 
 	spin_lock_irqsave(&ps3_htab_lock, flags);
 
@@ -125,8 +125,8 @@ static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
 				       &hpte_rs);
 
 	if (result) {
-		pr_info("%s: res=%d read va=%lx slot=%lx psize=%d\n",
-			__func__, result, va, slot, psize);
+		pr_info("%s: res=%d read vpn=%lx slot=%lx psize=%d\n",
+			__func__, result, vpn, slot, psize);
 		BUG();
 	}
 
@@ -159,7 +159,7 @@ static void ps3_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	panic("ps3_hpte_updateboltedpp() not implemented");
 }
 
-static void ps3_hpte_invalidate(unsigned long slot, unsigned long va,
+static void ps3_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	int psize, int ssize, int local)
 {
 	unsigned long flags;
@@ -170,8 +170,8 @@ static void ps3_hpte_invalidate(unsigned long slot, unsigned long va,
 	result = lv1_write_htab_entry(PS3_LPAR_VAS_ID_CURRENT, slot, 0, 0);
 
 	if (result) {
-		pr_info("%s: res=%d va=%lx slot=%lx psize=%d\n",
-			__func__, result, va, slot, psize);
+		pr_info("%s: res=%d vpn=%lx slot=%lx psize=%d\n",
+			__func__, result, vpn, slot, psize);
 		BUG();
 	}
 
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 2d664c5..3f509f8 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -184,11 +184,15 @@ early_param("ps3flash", early_parse_ps3flash);
 #define prealloc_ps3flash_bounce_buffer()	do { } while (0)
 #endif
 
-static int ps3_set_dabr(unsigned long dabr)
+static int ps3_set_dabr(unsigned long dabr, unsigned long dabrx)
 {
-	enum {DABR_USER = 1, DABR_KERNEL = 2,};
+	/* Have to set at least one bit in the DABRX */
+	if (dabrx == 0 && dabr == 0)
+		dabrx = DABRX_USER;
+	/* hypervisor only allows us to set BTI, Kernel and user */
+	dabrx &= DABRX_BTI | DABRX_KERNEL | DABRX_USER;
 
-	return lv1_set_dabr(dabr, DABR_KERNEL | DABR_USER) ? -1 : 0;
+	return lv1_set_dabr(dabr, dabrx) ? -1 : 0;
 }
 
 static void __init ps3_setup_arch(void)
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index c222189..890622b 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -6,8 +6,9 @@ obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
 			   firmware.o power.o dlpar.o mobility.o
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_SCANLOG)	+= scanlog.o
-obj-$(CONFIG_EEH)	+= eeh.o eeh_dev.o eeh_cache.o eeh_driver.o \
-			   eeh_event.o eeh_sysfs.o eeh_pseries.o
+obj-$(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-$(CONFIG_KEXEC)	+= kexec.o
 obj-$(CONFIG_PCI)	+= pci.o pci_dlpar.o
 obj-$(CONFIG_PSERIES_MSI)	+= msi.o
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index ecd394c..9a04322 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -92,6 +92,20 @@ 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);
 
@@ -204,22 +218,12 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len)
 		}
 	}
 
-	/* Gather status on devices under the bridge */
-	if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) {
-		struct device_node *child;
-
-		for_each_child_of_node(dn, child) {
-			if (of_node_to_eeh_dev(child))
-				n += eeh_gather_pci_data(of_node_to_eeh_dev(child), buf+n, len-n);
-		}
-	}
-
 	return n;
 }
 
 /**
  * eeh_slot_error_detail - Generate combined log including driver log and error log
- * @edev: device to report error log for
+ * @pe: EEH PE
  * @severity: temporary or permanent error log
  *
  * This routine should be called to generate the combined log, which
@@ -227,17 +231,22 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len)
  * 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_dev *edev, int severity)
+void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 {
 	size_t loglen = 0;
-	pci_regs_buf[0] = 0;
+	struct eeh_dev *edev;
 
-	eeh_pci_enable(edev, EEH_OPT_THAW_MMIO);
-	eeh_ops->configure_bridge(eeh_dev_to_of_node(edev));
-	eeh_restore_bars(edev);
-	loglen = eeh_gather_pci_data(edev, pci_regs_buf, EEH_PCI_REGS_LOG_LEN);
+	eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+	eeh_ops->configure_bridge(pe);
+	eeh_pe_restore_bars(pe);
 
-	eeh_ops->get_log(eeh_dev_to_of_node(edev), severity, pci_regs_buf, loglen);
+	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);
 }
 
 /**
@@ -261,126 +270,8 @@ static inline unsigned long eeh_token_to_phys(unsigned long token)
 }
 
 /**
- * eeh_find_device_pe - Retrieve the PE for the given device
- * @dn: device node
- *
- * Return the PE under which this device lies
- */
-struct device_node *eeh_find_device_pe(struct device_node *dn)
-{
-	while (dn->parent && of_node_to_eeh_dev(dn->parent) &&
-	       (of_node_to_eeh_dev(dn->parent)->mode & EEH_MODE_SUPPORTED)) {
-		dn = dn->parent;
-	}
-	return dn;
-}
-
-/**
- * __eeh_mark_slot - Mark all child devices as failed
- * @parent: parent device
- * @mode_flag: failure flag
- *
- * Mark all devices that are children of this device as failed.
- * Mark the device driver too, so that it can see the failure
- * immediately; this is critical, since some drivers poll
- * status registers in interrupts ... If a driver is polling,
- * and the slot is frozen, then the driver can deadlock in
- * an interrupt context, which is bad.
- */
-static void __eeh_mark_slot(struct device_node *parent, int mode_flag)
-{
-	struct device_node *dn;
-
-	for_each_child_of_node(parent, dn) {
-		if (of_node_to_eeh_dev(dn)) {
-			/* Mark the pci device driver too */
-			struct pci_dev *dev = of_node_to_eeh_dev(dn)->pdev;
-
-			of_node_to_eeh_dev(dn)->mode |= mode_flag;
-
-			if (dev && dev->driver)
-				dev->error_state = pci_channel_io_frozen;
-
-			__eeh_mark_slot(dn, mode_flag);
-		}
-	}
-}
-
-/**
- * eeh_mark_slot - Mark the indicated device and its children as failed
- * @dn: parent device
- * @mode_flag: failure flag
- *
- * Mark the indicated device and its child devices as failed.
- * The device drivers are marked as failed as well.
- */
-void eeh_mark_slot(struct device_node *dn, int mode_flag)
-{
-	struct pci_dev *dev;
-	dn = eeh_find_device_pe(dn);
-
-	/* Back up one, since config addrs might be shared */
-	if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent))
-		dn = dn->parent;
-
-	of_node_to_eeh_dev(dn)->mode |= mode_flag;
-
-	/* Mark the pci device too */
-	dev = of_node_to_eeh_dev(dn)->pdev;
-	if (dev)
-		dev->error_state = pci_channel_io_frozen;
-
-	__eeh_mark_slot(dn, mode_flag);
-}
-
-/**
- * __eeh_clear_slot - Clear failure flag for the child devices
- * @parent: parent device
- * @mode_flag: flag to be cleared
- *
- * Clear failure flag for the child devices.
- */
-static void __eeh_clear_slot(struct device_node *parent, int mode_flag)
-{
-	struct device_node *dn;
-
-	for_each_child_of_node(parent, dn) {
-		if (of_node_to_eeh_dev(dn)) {
-			of_node_to_eeh_dev(dn)->mode &= ~mode_flag;
-			of_node_to_eeh_dev(dn)->check_count = 0;
-			__eeh_clear_slot(dn, mode_flag);
-		}
-	}
-}
-
-/**
- * eeh_clear_slot - Clear failure flag for the indicated device and its children
- * @dn: parent device
- * @mode_flag: flag to be cleared
- *
- * Clear failure flag for the indicated device and its children.
- */
-void eeh_clear_slot(struct device_node *dn, int mode_flag)
-{
-	unsigned long flags;
-	raw_spin_lock_irqsave(&confirm_error_lock, flags);
-	
-	dn = eeh_find_device_pe(dn);
-	
-	/* Back up one, since config addrs might be shared */
-	if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent))
-		dn = dn->parent;
-
-	of_node_to_eeh_dev(dn)->mode &= ~mode_flag;
-	of_node_to_eeh_dev(dn)->check_count = 0;
-	__eeh_clear_slot(dn, mode_flag);
-	raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
-}
-
-/**
- * eeh_dn_check_failure - Check if all 1's data is due to EEH slot freeze
- * @dn: device node
- * @dev: pci device, if known
+ * 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
@@ -392,11 +283,13 @@ void eeh_clear_slot(struct device_node *dn, int mode_flag)
  *
  * It is safe to call this routine in an interrupt context.
  */
-int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
+int eeh_dev_check_failure(struct eeh_dev *edev)
 {
 	int ret;
 	unsigned long flags;
-	struct eeh_dev *edev;
+	struct device_node *dn;
+	struct pci_dev *dev;
+	struct eeh_pe *pe;
 	int rc = 0;
 	const char *location;
 
@@ -405,23 +298,23 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
 	if (!eeh_subsystem_enabled)
 		return 0;
 
-	if (!dn) {
+	if (!edev) {
 		eeh_stats.no_dn++;
 		return 0;
 	}
-	dn = eeh_find_device_pe(dn);
-	edev = of_node_to_eeh_dev(dn);
+	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 (!(edev->mode & EEH_MODE_SUPPORTED) ||
-	    edev->mode & EEH_MODE_NOCHECK) {
+	if (!pe) {
 		eeh_stats.ignored_check++;
-		pr_debug("EEH: Ignored check (%x) for %s %s\n",
-			edev->mode, eeh_pci_name(dev), dn->full_name);
+		pr_debug("EEH: Ignored check for %s %s\n",
+			eeh_pci_name(dev), dn->full_name);
 		return 0;
 	}
 
-	if (!edev->config_addr && !edev->pe_config_addr) {
+	if (!pe->addr && !pe->config_addr) {
 		eeh_stats.no_cfg_addr++;
 		return 0;
 	}
@@ -434,13 +327,13 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
 	 */
 	raw_spin_lock_irqsave(&confirm_error_lock, flags);
 	rc = 1;
-	if (edev->mode & EEH_MODE_ISOLATED) {
-		edev->check_count++;
-		if (edev->check_count % EEH_MAX_FAILS == 0) {
+	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",
-				edev->check_count, location,
+				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));
@@ -456,7 +349,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
 	 * function zero of a multi-function device.
 	 * In any case they must share a common PHB.
 	 */
-	ret = eeh_ops->get_state(dn, NULL);
+	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.
@@ -469,7 +362,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
 	    (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) ==
 	    (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) {
 		eeh_stats.false_positives++;
-		edev->false_positives ++;
+		pe->false_positives++;
 		rc = 0;
 		goto dn_unlock;
 	}
@@ -480,10 +373,10 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
 	 * with other functions on this device, and functions under
 	 * bridges.
 	 */
-	eeh_mark_slot(dn, EEH_MODE_ISOLATED);
+	eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 	raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
 
-	eeh_send_failure_event(edev);
+	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
@@ -497,7 +390,7 @@ dn_unlock:
 	return rc;
 }
 
-EXPORT_SYMBOL_GPL(eeh_dn_check_failure);
+EXPORT_SYMBOL_GPL(eeh_dev_check_failure);
 
 /**
  * eeh_check_failure - Check if all 1's data is due to EEH slot freeze
@@ -514,21 +407,19 @@ EXPORT_SYMBOL_GPL(eeh_dn_check_failure);
 unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
 {
 	unsigned long addr;
-	struct pci_dev *dev;
-	struct device_node *dn;
+	struct eeh_dev *edev;
 
 	/* Finding the phys addr + pci device; this is pretty quick. */
 	addr = eeh_token_to_phys((unsigned long __force) token);
-	dev = pci_addr_cache_get_device(addr);
-	if (!dev) {
+	edev = eeh_addr_cache_get_dev(addr);
+	if (!edev) {
 		eeh_stats.no_device++;
 		return val;
 	}
 
-	dn = pci_device_to_OF_node(dev);
-	eeh_dn_check_failure(dn, dev);
+	eeh_dev_check_failure(edev);
 
-	pci_dev_put(dev);
+	pci_dev_put(eeh_dev_to_pci_dev(edev));
 	return val;
 }
 
@@ -537,23 +428,22 @@ EXPORT_SYMBOL(eeh_check_failure);
 
 /**
  * eeh_pci_enable - Enable MMIO or DMA transfers for this slot
- * @edev: pci device node
+ * @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_dev *edev, int function)
+int eeh_pci_enable(struct eeh_pe *pe, int function)
 {
 	int rc;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
 
-	rc = eeh_ops->set_option(dn, function);
+	rc = eeh_ops->set_option(pe, function);
 	if (rc)
-		printk(KERN_WARNING "EEH: Unexpected state change %d, err=%d dn=%s\n",
-		        function, rc, dn->full_name);
+		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(dn, PCI_BUS_RESET_WAIT_MSEC);
+	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;
@@ -571,17 +461,24 @@ int eeh_pci_enable(struct eeh_dev *edev, int function)
  */
 int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
 {
-	struct device_node *dn = pci_device_to_OF_node(dev);
+	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(dn, EEH_RESET_DEACTIVATE);
+		eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
 		break;
 	case pcie_hot_reset:
-		eeh_ops->reset(dn, EEH_RESET_HOT);
+		eeh_ops->reset(pe, EEH_RESET_HOT);
 		break;
 	case pcie_warm_reset:
-		eeh_ops->reset(dn, EEH_RESET_FUNDAMENTAL);
+		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
 		break;
 	default:
 		return -EINVAL;
@@ -591,66 +488,37 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
 }
 
 /**
- * __eeh_set_pe_freset - Check the required reset for child devices
- * @parent: parent device
- * @freset: return value
- *
- * Each device might have its preferred reset type: fundamental or
- * hot reset. The routine is used to collect the information from
- * the child devices so that they could be reset accordingly.
- */
-void __eeh_set_pe_freset(struct device_node *parent, unsigned int *freset)
-{
-	struct device_node *dn;
-
-	for_each_child_of_node(parent, dn) {
-		if (of_node_to_eeh_dev(dn)) {
-			struct pci_dev *dev = of_node_to_eeh_dev(dn)->pdev;
-
-			if (dev && dev->driver)
-				*freset |= dev->needs_freset;
-
-			__eeh_set_pe_freset(dn, freset);
-		}
-	}
-}
-
-/**
- * eeh_set_pe_freset - Check the required reset for the indicated device and its children
- * @dn: parent device
- * @freset: return value
+ * 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.
  */
-void eeh_set_pe_freset(struct device_node *dn, unsigned int *freset)
+static void *eeh_set_dev_freset(void *data, void *flag)
 {
 	struct pci_dev *dev;
-	dn = eeh_find_device_pe(dn);
-
-	/* Back up one, since config addrs might be shared */
-	if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent))
-		dn = dn->parent;
+	unsigned int *freset = (unsigned int *)flag;
+	struct eeh_dev *edev = (struct eeh_dev *)data;
 
-	dev = of_node_to_eeh_dev(dn)->pdev;
+	dev = eeh_dev_to_pci_dev(edev);
 	if (dev)
 		*freset |= dev->needs_freset;
 
-	__eeh_set_pe_freset(dn, freset);
+	return NULL;
 }
 
 /**
  * eeh_reset_pe_once - Assert the pci #RST line for 1/4 second
- * @edev: pci device node to be reset.
+ * @pe: EEH PE
  *
  * Assert the PCI #RST line for 1/4 second.
  */
-static void eeh_reset_pe_once(struct eeh_dev *edev)
+static void eeh_reset_pe_once(struct eeh_pe *pe)
 {
 	unsigned int freset = 0;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
 
 	/* Determine type of EEH reset required for
 	 * Partitionable Endpoint, a hot-reset (1)
@@ -658,12 +526,12 @@ static void eeh_reset_pe_once(struct eeh_dev *edev)
 	 * A fundamental reset required by any device under
 	 * Partitionable Endpoint trumps hot-reset.
   	 */
-	eeh_set_pe_freset(dn, &freset);
+	eeh_pe_dev_traverse(pe, eeh_set_dev_freset, &freset);
 
 	if (freset)
-		eeh_ops->reset(dn, EEH_RESET_FUNDAMENTAL);
+		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
 	else
-		eeh_ops->reset(dn, EEH_RESET_HOT);
+		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'.
@@ -675,9 +543,9 @@ static void eeh_reset_pe_once(struct eeh_dev *edev)
 	 * pci slot reset line is dropped. Make sure we don't miss
 	 * these, and clear the flag now.
 	 */
-	eeh_clear_slot(dn, EEH_MODE_ISOLATED);
+	eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
 
-	eeh_ops->reset(dn, EEH_RESET_DEACTIVATE);
+	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
@@ -689,116 +557,36 @@ static void eeh_reset_pe_once(struct eeh_dev *edev)
 
 /**
  * eeh_reset_pe - Reset the indicated PE
- * @edev: PCI device associated EEH device
+ * @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_dev *edev)
+int eeh_reset_pe(struct eeh_pe *pe)
 {
 	int i, rc;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
 
 	/* Take three shots at resetting the bus */
 	for (i=0; i<3; i++) {
-		eeh_reset_pe_once(edev);
+		eeh_reset_pe_once(pe);
 
-		rc = eeh_ops->wait_state(dn, PCI_BUS_RESET_WAIT_MSEC);
+		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) {
-			printk(KERN_ERR "EEH: unrecoverable slot failure %s\n",
-			       dn->full_name);
+			pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
+				__func__, pe->phb->global_number, pe->addr);
 			return -1;
 		}
-		printk(KERN_ERR "EEH: bus reset %d failed on slot %s, rc=%d\n",
-		       i+1, dn->full_name, rc);
+		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;
 }
 
-/** Save and restore of PCI BARs
- *
- * Although firmware will set up BARs during boot, it doesn't
- * set up device BAR's after a device reset, although it will,
- * if requested, set up bridge configuration. Thus, we need to
- * configure the PCI devices ourselves.  
- */
-
-/**
- * eeh_restore_one_device_bars - Restore the Base Address Registers for one device
- * @edev: PCI device associated EEH device
- *
- * 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 inline void eeh_restore_one_device_bars(struct eeh_dev *edev)
-{
-	int i;
-	u32 cmd;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
-
-	if (!edev->phb)
-		return;
-
-	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);
-}
-
-/**
- * eeh_restore_bars - Restore the PCI config space info
- * @edev: EEH device
- *
- * This routine performs a recursive walk to the children
- * of this device as well.
- */
-void eeh_restore_bars(struct eeh_dev *edev)
-{
-	struct device_node *dn;
-	if (!edev)
-		return;
-	
-	if ((edev->mode & EEH_MODE_SUPPORTED) && !IS_BRIDGE(edev->class_code))
-		eeh_restore_one_device_bars(edev);
-
-	for_each_child_of_node(eeh_dev_to_of_node(edev), dn)
-		eeh_restore_bars(of_node_to_eeh_dev(dn));
-}
-
 /**
  * eeh_save_bars - Save device bars
  * @edev: PCI device associated EEH device
@@ -808,7 +596,7 @@ void eeh_restore_bars(struct eeh_dev *edev)
  * PCI devices are added individually; but, for the restore,
  * an entire slot is reset at a time.
  */
-static void eeh_save_bars(struct eeh_dev *edev)
+void eeh_save_bars(struct eeh_dev *edev)
 {
 	int i;
 	struct device_node *dn;
@@ -822,102 +610,6 @@ static void eeh_save_bars(struct eeh_dev *edev)
 }
 
 /**
- * eeh_early_enable - Early enable EEH on the indicated device
- * @dn: device node
- * @data: BUID
- *
- * Enable EEH functionality on the specified PCI device. The function
- * is expected to be called before real PCI probing is done. However,
- * the PHBs have been initialized at this point.
- */
-static void *eeh_early_enable(struct device_node *dn, void *data)
-{
-	int ret;
-	const u32 *class_code = of_get_property(dn, "class-code", NULL);
-	const u32 *vendor_id = of_get_property(dn, "vendor-id", NULL);
-	const u32 *device_id = of_get_property(dn, "device-id", NULL);
-	const u32 *regs;
-	int enable;
-	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
-
-	edev->class_code = 0;
-	edev->mode = 0;
-	edev->check_count = 0;
-	edev->freeze_count = 0;
-	edev->false_positives = 0;
-
-	if (!of_device_is_available(dn))
-		return NULL;
-
-	/* Ignore bad nodes. */
-	if (!class_code || !vendor_id || !device_id)
-		return NULL;
-
-	/* There is nothing to check on PCI to ISA bridges */
-	if (dn->type && !strcmp(dn->type, "isa")) {
-		edev->mode |= EEH_MODE_NOCHECK;
-		return NULL;
-	}
-	edev->class_code = *class_code;
-
-	/* Ok... see if this device supports EEH.  Some do, some don't,
-	 * and the only way to find out is to check each and every one.
-	 */
-	regs = of_get_property(dn, "reg", NULL);
-	if (regs) {
-		/* First register entry is addr (00BBSS00)  */
-		/* Try to enable eeh */
-		ret = eeh_ops->set_option(dn, EEH_OPT_ENABLE);
-
-		enable = 0;
-		if (ret == 0) {
-			edev->config_addr = regs[0];
-
-			/* If the newer, better, ibm,get-config-addr-info is supported, 
-			 * then use that instead.
-			 */
-			edev->pe_config_addr = eeh_ops->get_pe_addr(dn);
-
-			/* Some older systems (Power4) allow the
-			 * ibm,set-eeh-option call to succeed even on nodes
-			 * where EEH is not supported. Verify support
-			 * explicitly.
-			 */
-			ret = eeh_ops->get_state(dn, NULL);
-			if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT)
-				enable = 1;
-		}
-
-		if (enable) {
-			eeh_subsystem_enabled = 1;
-			edev->mode |= EEH_MODE_SUPPORTED;
-
-			pr_debug("EEH: %s: eeh enabled, config=%x pe_config=%x\n",
-				 dn->full_name, edev->config_addr,
-				 edev->pe_config_addr);
-		} else {
-
-			/* This device doesn't support EEH, but it may have an
-			 * EEH parent, in which case we mark it as supported.
-			 */
-			if (dn->parent && of_node_to_eeh_dev(dn->parent) &&
-			    (of_node_to_eeh_dev(dn->parent)->mode & EEH_MODE_SUPPORTED)) {
-				/* Parent supports EEH. */
-				edev->mode |= EEH_MODE_SUPPORTED;
-				edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr;
-				return NULL;
-			}
-		}
-	} else {
-		printk(KERN_WARNING "EEH: %s: unable to get reg property.\n",
-		       dn->full_name);
-	}
-
-	eeh_save_bars(edev);
-	return NULL;
-}
-
-/**
  * eeh_ops_register - Register platform dependent EEH operations
  * @ops: platform dependent EEH operations
  *
@@ -982,7 +674,7 @@ int __exit eeh_ops_unregister(const char *name)
  * Even if force-off is set, the EEH hardware is still enabled, so that
  * newer systems can boot.
  */
-void __init eeh_init(void)
+static int __init eeh_init(void)
 {
 	struct pci_controller *hose, *tmp;
 	struct device_node *phb;
@@ -992,27 +684,34 @@ void __init eeh_init(void)
 	if (!eeh_ops) {
 		pr_warning("%s: Platform EEH operation not found\n",
 			__func__);
-		return;
+		return -EEXIST;
 	} else if ((ret = eeh_ops->init())) {
 		pr_warning("%s: Failed to call platform init function (%d)\n",
 			__func__, ret);
-		return;
+		return ret;
 	}
 
 	raw_spin_lock_init(&confirm_error_lock);
 
 	/* Enable EEH for all adapters */
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
-		phb = hose->dn;
-		traverse_pci_devices(phb, eeh_early_enable, NULL);
+	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)
-		printk(KERN_INFO "EEH: PCI Enhanced I/O Error Handling Enabled\n");
+		pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
 	else
-		printk(KERN_WARNING "EEH: No capable adapters found\n");
+		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
@@ -1029,7 +728,7 @@ static void eeh_add_device_early(struct device_node *dn)
 {
 	struct pci_controller *phb;
 
-	if (!dn || !of_node_to_eeh_dev(dn))
+	if (!of_node_to_eeh_dev(dn))
 		return;
 	phb = of_node_to_eeh_dev(dn)->phb;
 
@@ -1037,7 +736,8 @@ static void eeh_add_device_early(struct device_node *dn)
 	if (NULL == phb || 0 == phb->buid)
 		return;
 
-	eeh_early_enable(dn, NULL);
+	/* FIXME: hotplug support on POWERNV */
+	eeh_ops->of_probe(dn, NULL);
 }
 
 /**
@@ -1087,7 +787,7 @@ static void eeh_add_device_late(struct pci_dev *dev)
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
 
-	pci_addr_cache_insert_device(dev);
+	eeh_addr_cache_insert_dev(dev);
 	eeh_sysfs_add_device(dev);
 }
 
@@ -1117,6 +817,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
 /**
  * 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
@@ -1124,7 +825,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
  * 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)
+static void eeh_remove_device(struct pci_dev *dev, int purge_pe)
 {
 	struct eeh_dev *edev;
 
@@ -1143,28 +844,30 @@ static void eeh_remove_device(struct pci_dev *dev)
 	dev->dev.archdata.edev = NULL;
 	pci_dev_put(dev);
 
-	pci_addr_cache_remove_device(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)
+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);
+	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);
+			 eeh_remove_bus_device(child, purge_pe);
 	}
 }
 EXPORT_SYMBOL_GPL(eeh_remove_bus_device);
diff --git a/arch/powerpc/platforms/pseries/eeh_cache.c b/arch/powerpc/platforms/pseries/eeh_cache.c
index e5ae1c6..5a4c879 100644
--- a/arch/powerpc/platforms/pseries/eeh_cache.c
+++ b/arch/powerpc/platforms/pseries/eeh_cache.c
@@ -50,6 +50,7 @@ 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;
 };
@@ -59,7 +60,7 @@ static struct pci_io_addr_cache {
 	spinlock_t piar_lock;
 } pci_io_addr_cache_root;
 
-static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr)
+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;
 
@@ -74,7 +75,7 @@ static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr)
 				n = n->rb_right;
 			} else {
 				pci_dev_get(piar->pcidev);
-				return piar->pcidev;
+				return piar->edev;
 			}
 		}
 	}
@@ -83,7 +84,7 @@ static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr)
 }
 
 /**
- * pci_addr_cache_get_device - Get device, given only address
+ * 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
@@ -92,15 +93,15 @@ static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr)
  * from zero (that is, they do *not* have pci_io_addr added in).
  * It is safe to call this function within an interrupt.
  */
-struct pci_dev *pci_addr_cache_get_device(unsigned long addr)
+struct eeh_dev *eeh_addr_cache_get_dev(unsigned long addr)
 {
-	struct pci_dev *dev;
+	struct eeh_dev *edev;
 	unsigned long flags;
 
 	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
-	dev = __pci_addr_cache_get_device(addr);
+	edev = __eeh_addr_cache_get_device(addr);
 	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
-	return dev;
+	return edev;
 }
 
 #ifdef DEBUG
@@ -108,7 +109,7 @@ struct pci_dev *pci_addr_cache_get_device(unsigned long addr)
  * Handy-dandy debug print routine, does nothing more
  * than print out the contents of our addr cache.
  */
-static void pci_addr_cache_print(struct pci_io_addr_cache *cache)
+static void eeh_addr_cache_print(struct pci_io_addr_cache *cache)
 {
 	struct rb_node *n;
 	int cnt = 0;
@@ -117,7 +118,7 @@ static void pci_addr_cache_print(struct pci_io_addr_cache *cache)
 	while (n) {
 		struct pci_io_addr_range *piar;
 		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
-		printk(KERN_DEBUG "PCI: %s addr range %d [%lx-%lx]: %s\n",
+		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++;
@@ -128,7 +129,7 @@ static void pci_addr_cache_print(struct pci_io_addr_cache *cache)
 
 /* Insert address range into the rb tree. */
 static struct pci_io_addr_range *
-pci_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
+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;
@@ -146,23 +147,24 @@ pci_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
 		} else {
 			if (dev != piar->pcidev ||
 			    alo != piar->addr_lo || ahi != piar->addr_hi) {
-				printk(KERN_WARNING "PIAR: overlapping address range\n");
+				pr_warning("PIAR: overlapping address range\n");
 			}
 			return piar;
 		}
 	}
-	piar = kmalloc(sizeof(struct pci_io_addr_range), GFP_ATOMIC);
+	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
-	printk(KERN_DEBUG "PIAR: insert range=[%lx:%lx] dev=%s\n",
+	pr_debug("PIAR: insert range=[%lx:%lx] dev=%s\n",
 	                  alo, ahi, pci_name(dev));
 #endif
 
@@ -172,7 +174,7 @@ pci_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
 	return piar;
 }
 
-static void __pci_addr_cache_insert_device(struct pci_dev *dev)
+static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
 {
 	struct device_node *dn;
 	struct eeh_dev *edev;
@@ -180,7 +182,7 @@ static void __pci_addr_cache_insert_device(struct pci_dev *dev)
 
 	dn = pci_device_to_OF_node(dev);
 	if (!dn) {
-		printk(KERN_WARNING "PCI: no pci dn found for dev=%s\n", pci_name(dev));
+		pr_warning("PCI: no pci dn found for dev=%s\n", pci_name(dev));
 		return;
 	}
 
@@ -192,8 +194,7 @@ static void __pci_addr_cache_insert_device(struct pci_dev *dev)
 	}
 
 	/* Skip any devices for which EEH is not enabled. */
-	if (!(edev->mode & EEH_MODE_SUPPORTED) ||
-	    edev->mode & EEH_MODE_NOCHECK) {
+	if (!edev->pe) {
 #ifdef DEBUG
 		pr_info("PCI: skip building address cache for=%s - %s\n",
 			pci_name(dev), dn->full_name);
@@ -212,19 +213,19 @@ static void __pci_addr_cache_insert_device(struct pci_dev *dev)
 			continue;
 		if (start == 0 || ~start == 0 || end == 0 || ~end == 0)
 			 continue;
-		pci_addr_cache_insert(dev, start, end, flags);
+		eeh_addr_cache_insert(dev, start, end, flags);
 	}
 }
 
 /**
- * pci_addr_cache_insert_device - Add a device to the address cache
+ * 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 pci_addr_cache_insert_device(struct pci_dev *dev)
+void eeh_addr_cache_insert_dev(struct pci_dev *dev)
 {
 	unsigned long flags;
 
@@ -233,11 +234,11 @@ void pci_addr_cache_insert_device(struct pci_dev *dev)
 		return;
 
 	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
-	__pci_addr_cache_insert_device(dev);
+	__eeh_addr_cache_insert_dev(dev);
 	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
 }
 
-static inline void __pci_addr_cache_remove_device(struct pci_dev *dev)
+static inline void __eeh_addr_cache_rmv_dev(struct pci_dev *dev)
 {
 	struct rb_node *n;
 
@@ -258,7 +259,7 @@ restart:
 }
 
 /**
- * pci_addr_cache_remove_device - remove pci device from addr cache
+ * eeh_addr_cache_rmv_dev - remove pci device from addr cache
  * @dev: device to remove
  *
  * Remove a device from the addr-cache tree.
@@ -266,17 +267,17 @@ restart:
  * the tree multiple times (once per resource).
  * But so what; device removal doesn't need to be that fast.
  */
-void pci_addr_cache_remove_device(struct pci_dev *dev)
+void eeh_addr_cache_rmv_dev(struct pci_dev *dev)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
-	__pci_addr_cache_remove_device(dev);
+	__eeh_addr_cache_rmv_dev(dev);
 	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
 }
 
 /**
- * pci_addr_cache_build - Build a cache of I/O addresses
+ * 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.
@@ -284,7 +285,7 @@ void pci_addr_cache_remove_device(struct pci_dev *dev)
  * Must be run late in boot process, after the pci controllers
  * have been scanned for devices (after all device resources are known).
  */
-void __init pci_addr_cache_build(void)
+void __init eeh_addr_cache_build(void)
 {
 	struct device_node *dn;
 	struct eeh_dev *edev;
@@ -293,7 +294,7 @@ void __init pci_addr_cache_build(void)
 	spin_lock_init(&pci_io_addr_cache_root.piar_lock);
 
 	for_each_pci_dev(dev) {
-		pci_addr_cache_insert_device(dev);
+		eeh_addr_cache_insert_dev(dev);
 
 		dn = pci_device_to_OF_node(dev);
 		if (!dn)
@@ -312,7 +313,7 @@ void __init pci_addr_cache_build(void)
 
 #ifdef DEBUG
 	/* Verify tree built up above, echo back the list of addrs. */
-	pci_addr_cache_print(&pci_io_addr_cache_root);
+	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
index c4507d0..6644234 100644
--- a/arch/powerpc/platforms/pseries/eeh_dev.c
+++ b/arch/powerpc/platforms/pseries/eeh_dev.c
@@ -55,7 +55,7 @@ void * __devinit eeh_dev_init(struct device_node *dn, void *data)
 	struct eeh_dev *edev;
 
 	/* Allocate EEH device */
-	edev = zalloc_maybe_bootmem(sizeof(*edev), GFP_KERNEL);
+	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
 	if (!edev) {
 		pr_warning("%s: out of memory\n", __func__);
 		return NULL;
@@ -65,6 +65,7 @@ void * __devinit eeh_dev_init(struct device_node *dn, void *data)
 	PCI_DN(dn)->edev = edev;
 	edev->dn  = dn;
 	edev->phb = phb;
+	INIT_LIST_HEAD(&edev->list);
 
 	return NULL;
 }
@@ -80,6 +81,9 @@ void __devinit 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);
 
@@ -93,10 +97,16 @@ void __devinit eeh_dev_phb_init_dynamic(struct pci_controller *phb)
  * Scan all the existing PHBs and create EEH devices for their OF
  * nodes and their children OF nodes
  */
-void __init eeh_dev_phb_init(void)
+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
index baf92cd..a3fefb6 100644
--- a/arch/powerpc/platforms/pseries/eeh_driver.c
+++ b/arch/powerpc/platforms/pseries/eeh_driver.c
@@ -25,6 +25,7 @@
 #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>
@@ -47,6 +48,41 @@ static inline const char *eeh_pcid_name(struct pci_dev *pdev)
 	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)
 {
@@ -93,7 +129,7 @@ static void eeh_disable_irq(struct pci_dev *dev)
 	if (!irq_has_action(dev->irq))
 		return;
 
-	edev->mode |= EEH_MODE_IRQ_DISABLED;
+	edev->mode |= EEH_DEV_IRQ_DISABLED;
 	disable_irq_nosync(dev->irq);
 }
 
@@ -108,36 +144,44 @@ static void eeh_enable_irq(struct pci_dev *dev)
 {
 	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
 
-	if ((edev->mode) & EEH_MODE_IRQ_DISABLED) {
-		edev->mode &= ~EEH_MODE_IRQ_DISABLED;
+	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
- * @dev: PCI device
+ * @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 int eeh_report_error(struct pci_dev *dev, void *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 = dev->driver;
+	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;
 
-	if (!driver)
-		return 0;
+	driver = eeh_pcid_get(dev);
+	if (!driver) return NULL;
 
 	eeh_disable_irq(dev);
 
 	if (!driver->err_handler ||
-	    !driver->err_handler->error_detected)
-		return 0;
+	    !driver->err_handler->error_detected) {
+		eeh_pcid_put(dev);
+		return NULL;
+	}
 
 	rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen);
 
@@ -145,27 +189,34 @@ static int eeh_report_error(struct pci_dev *dev, void *userdata)
 	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
 	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
 
-	return 0;
+	eeh_pcid_put(dev);
+	return NULL;
 }
 
 /**
  * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled
- * @dev: PCI device
+ * @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 int eeh_report_mmio_enabled(struct pci_dev *dev, void *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 = dev->driver;
+	struct pci_driver *driver;
 
-	if (!driver ||
-	    !driver->err_handler ||
-	    !driver->err_handler->mmio_enabled)
-		return 0;
+	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);
 
@@ -173,12 +224,13 @@ static int eeh_report_mmio_enabled(struct pci_dev *dev, void *userdata)
 	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
 	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
 
-	return 0;
+	eeh_pcid_put(dev);
+	return NULL;
 }
 
 /**
  * eeh_report_reset - Tell device that slot has been reset
- * @dev: PCI device
+ * @data: eeh device
  * @userdata: return value
  *
  * This routine must be called while EEH tries to reset particular
@@ -186,21 +238,26 @@ static int eeh_report_mmio_enabled(struct pci_dev *dev, void *userdata)
  * some actions, usually to save data the driver needs so that the
  * driver can work again while the device is recovered.
  */
-static int eeh_report_reset(struct pci_dev *dev, void *userdata)
+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 = dev->driver;
-
-	if (!driver)
-		return 0;
+	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)
-		return 0;
+	    !driver->err_handler->slot_reset) {
+		eeh_pcid_put(dev);
+		return NULL;
+	}
 
 	rc = driver->err_handler->slot_reset(dev);
 	if ((*res == PCI_ERS_RESULT_NONE) ||
@@ -208,109 +265,115 @@ static int eeh_report_reset(struct pci_dev *dev, void *userdata)
 	if (*res == PCI_ERS_RESULT_DISCONNECT &&
 	     rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
 
-	return 0;
+	eeh_pcid_put(dev);
+	return NULL;
 }
 
 /**
  * eeh_report_resume - Tell device to resume normal operations
- * @dev: PCI device
+ * @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 int eeh_report_resume(struct pci_dev *dev, void *userdata)
+static void *eeh_report_resume(void *data, void *userdata)
 {
-	struct pci_driver *driver = dev->driver;
+	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;
 
-	if (!driver)
-		return 0;
+	driver = eeh_pcid_get(dev);
+	if (!driver) return NULL;
 
 	eeh_enable_irq(dev);
 
 	if (!driver->err_handler ||
-	    !driver->err_handler->resume)
-		return 0;
+	    !driver->err_handler->resume) {
+		eeh_pcid_put(dev);
+		return NULL;
+	}
 
 	driver->err_handler->resume(dev);
 
-	return 0;
+	eeh_pcid_put(dev);
+	return NULL;
 }
 
 /**
  * eeh_report_failure - Tell device driver that device is dead.
- * @dev: PCI device
+ * @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 int eeh_report_failure(struct pci_dev *dev, void *userdata)
+static void *eeh_report_failure(void *data, void *userdata)
 {
-	struct pci_driver *driver = dev->driver;
+	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;
 
-	if (!driver)
-		return 0;
+	driver = eeh_pcid_get(dev);
+	if (!driver) return NULL;
 
 	eeh_disable_irq(dev);
 
 	if (!driver->err_handler ||
-	    !driver->err_handler->error_detected)
-		return 0;
+	    !driver->err_handler->error_detected) {
+		eeh_pcid_put(dev);
+		return NULL;
+	}
 
 	driver->err_handler->error_detected(dev, pci_channel_io_perm_failure);
 
-	return 0;
+	eeh_pcid_put(dev);
+	return NULL;
 }
 
 /**
  * eeh_reset_device - Perform actual reset of a pci slot
- * @edev: PE associated EEH device
+ * @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_dev *edev, struct pci_bus *bus)
+static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 {
-	struct device_node *dn;
 	int cnt, rc;
 
 	/* pcibios will clear the counter; save the value */
-	cnt = edev->freeze_count;
+	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);
+		__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(edev);
+	rc = eeh_reset_pe(pe);
 	if (rc)
 		return rc;
 
-	/* Walk over all functions on this device. */
-	dn = eeh_dev_to_of_node(edev);
-	if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent))
-		dn = dn->parent->child;
-
-	while (dn) {
-		struct eeh_dev *pedev = of_node_to_eeh_dev(dn);
-
-		/* On Power4, always true because eeh_pe_config_addr=0 */
-		if (edev->pe_config_addr == pedev->pe_config_addr) {
-			eeh_ops->configure_bridge(dn);
-			eeh_restore_bars(pedev);
- 		}
-		dn = dn->sibling;
-	}
+	/* 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, 
@@ -322,7 +385,7 @@ static int eeh_reset_device(struct eeh_dev *edev, struct pci_bus *bus)
 		ssleep(5);
 		pcibios_add_pci_devices(bus);
 	}
-	edev->freeze_count = cnt;
+	pe->freeze_count = cnt;
 
 	return 0;
 }
@@ -334,7 +397,7 @@ static int eeh_reset_device(struct eeh_dev *edev, struct pci_bus *bus)
 
 /**
  * eeh_handle_event - Reset a PCI device after hard lockup.
- * @event: EEH event
+ * @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
@@ -349,69 +412,24 @@ static int eeh_reset_device(struct eeh_dev *edev, struct pci_bus *bus)
  * drivers (which cause a second set of hotplug events to go out to
  * userspace).
  */
-struct eeh_dev *handle_eeh_events(struct eeh_event *event)
+void eeh_handle_event(struct eeh_pe *pe)
 {
-	struct device_node *frozen_dn;
-	struct eeh_dev *frozen_edev;
 	struct pci_bus *frozen_bus;
 	int rc = 0;
 	enum pci_ers_result result = PCI_ERS_RESULT_NONE;
-	const char *location, *pci_str, *drv_str, *bus_pci_str, *bus_drv_str;
-
-	frozen_dn = eeh_find_device_pe(eeh_dev_to_of_node(event->edev));
-	if (!frozen_dn) {
-		location = of_get_property(eeh_dev_to_of_node(event->edev), "ibm,loc-code", NULL);
-		location = location ? location : "unknown";
-		printk(KERN_ERR "EEH: Error: Cannot find partition endpoint "
-		                "for location=%s pci addr=%s\n",
-			location, eeh_pci_name(eeh_dev_to_pci_dev(event->edev)));
-		return NULL;
-	}
-
-	frozen_bus = pcibios_find_pci_bus(frozen_dn);
-	location = of_get_property(frozen_dn, "ibm,loc-code", NULL);
-	location = location ? location : "unknown";
-
-	/* There are two different styles for coming up with the PE.
-	 * In the old style, it was the highest EEH-capable device
-	 * which was always an EADS pci bridge.  In the new style,
-	 * there might not be any EADS bridges, and even when there are,
-	 * the firmware marks them as "EEH incapable". So another
-	 * two-step is needed to find the pci bus..
-	 */
-	if (!frozen_bus)
-		frozen_bus = pcibios_find_pci_bus(frozen_dn->parent);
 
+	frozen_bus = eeh_pe_bus_get(pe);
 	if (!frozen_bus) {
-		printk(KERN_ERR "EEH: Cannot find PCI bus "
-		        "for location=%s dn=%s\n",
-		        location, frozen_dn->full_name);
-		return NULL;
+		pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
+			__func__, pe->phb->global_number, pe->addr);
+		return;
 	}
 
-	frozen_edev = of_node_to_eeh_dev(frozen_dn);
-	frozen_edev->freeze_count++;
-	pci_str = eeh_pci_name(eeh_dev_to_pci_dev(event->edev));
-	drv_str = eeh_pcid_name(eeh_dev_to_pci_dev(event->edev));
-
-	if (frozen_edev->freeze_count > EEH_MAX_ALLOWED_FREEZES)
+	pe->freeze_count++;
+	if (pe->freeze_count > EEH_MAX_ALLOWED_FREEZES)
 		goto excess_failures;
-
-	printk(KERN_WARNING
-	   "EEH: This PCI device has failed %d times in the last hour:\n",
-		frozen_edev->freeze_count);
-
-	if (frozen_edev->pdev) {
-		bus_pci_str = pci_name(frozen_edev->pdev);
-		bus_drv_str = eeh_pcid_name(frozen_edev->pdev);
-		printk(KERN_WARNING
-			"EEH: Bus location=%s driver=%s pci addr=%s\n",
-			location, bus_drv_str, bus_pci_str);
-	}
-
-	printk(KERN_WARNING
-		"EEH: Device location=%s driver=%s pci addr=%s\n",
-		location, drv_str, pci_str);
+	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
@@ -419,12 +437,12 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event)
 	 * status ... if any child can't handle the reset, then the entire
 	 * slot is dlpar removed and added.
 	 */
-	pci_walk_bus(frozen_bus, eeh_report_error, &result);
+	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(eeh_dev_to_of_node(frozen_edev), MAX_WAIT_FOR_RECOVERY*1000);
+	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;
@@ -434,14 +452,14 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event)
 	 * don't post the error log until after all dev drivers
 	 * have been informed.
 	 */
-	eeh_slot_error_detail(frozen_edev, EEH_LOG_TEMP);
+	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(frozen_edev, frozen_bus);
+		rc = eeh_reset_device(pe, frozen_bus);
 		if (rc) {
 			printk(KERN_WARNING "EEH: Unable to reset, rc=%d\n", rc);
 			goto hard_fail;
@@ -450,7 +468,7 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event)
 
 	/* If all devices reported they can proceed, then re-enable MMIO */
 	if (result == PCI_ERS_RESULT_CAN_RECOVER) {
-		rc = eeh_pci_enable(frozen_edev, EEH_OPT_THAW_MMIO);
+		rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
 
 		if (rc < 0)
 			goto hard_fail;
@@ -458,13 +476,13 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event)
 			result = PCI_ERS_RESULT_NEED_RESET;
 		} else {
 			result = PCI_ERS_RESULT_NONE;
-			pci_walk_bus(frozen_bus, eeh_report_mmio_enabled, &result);
+			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(frozen_edev, EEH_OPT_THAW_DMA);
+		rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
 
 		if (rc < 0)
 			goto hard_fail;
@@ -482,13 +500,13 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event)
 
 	/* If any device called out for a reset, then reset the slot */
 	if (result == PCI_ERS_RESULT_NEED_RESET) {
-		rc = eeh_reset_device(frozen_edev, NULL);
+		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;
-		pci_walk_bus(frozen_bus, eeh_report_reset, &result);
+		eeh_pe_dev_traverse(pe, eeh_report_reset, &result);
 	}
 
 	/* All devices should claim they have recovered by now. */
@@ -499,9 +517,9 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event)
 	}
 
 	/* Tell all device drivers that they can resume operations */
-	pci_walk_bus(frozen_bus, eeh_report_resume, NULL);
+	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
 
-	return frozen_edev;
+	return;
 	
 excess_failures:
 	/*
@@ -509,30 +527,26 @@ excess_failures:
 	 * are due to poorly seated PCI cards. Only 10% or so are
 	 * due to actual, failed cards.
 	 */
-	printk(KERN_ERR
-	   "EEH: PCI device at location=%s driver=%s pci addr=%s\n"
-		"has failed %d times in the last hour "
-		"and has been permanently disabled.\n"
-		"Please try reseating this device or replacing it.\n",
-		location, drv_str, pci_str, frozen_edev->freeze_count);
+	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:
-	printk(KERN_ERR
-	   "EEH: Unable to recover from failure of PCI device "
-	   "at location=%s driver=%s pci addr=%s\n"
-	   "Please try reseating this device or replacing it.\n",
-		location, drv_str, pci_str);
+	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(frozen_edev, EEH_LOG_PERM);
+	eeh_slot_error_detail(pe, EEH_LOG_PERM);
 
 	/* Notify all devices that they're about to go down. */
-	pci_walk_bus(frozen_bus, eeh_report_failure, NULL);
+	eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
 
 	/* Shut down the device drivers for good. */
-	pcibios_remove_pci_devices(frozen_bus);
-
-	return NULL;
+	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
index fb50631..51faaac 100644
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -57,7 +57,7 @@ static int eeh_event_handler(void * dummy)
 {
 	unsigned long flags;
 	struct eeh_event *event;
-	struct eeh_dev *edev;
+	struct eeh_pe *pe;
 
 	set_task_comm(current, "eehd");
 
@@ -76,28 +76,23 @@ static int eeh_event_handler(void * dummy)
 
 	/* Serialize processing of EEH events */
 	mutex_lock(&eeh_event_mutex);
-	edev = event->edev;
-	eeh_mark_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING);
-
-	printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n",
-	       eeh_pci_name(edev->pdev));
+	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 */
-	edev = handle_eeh_events(event);
-
-	if (edev) {
-		eeh_clear_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING);
-		pci_dev_put(edev->pdev);
-	}
+	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 (edev && edev->freeze_count>0) {
+	if (pe && pe->freeze_count > 0) {
 		msleep_interruptible(3600*1000);
-		if (edev->freeze_count>0)
-			edev->freeze_count--;
+		if (pe->freeze_count > 0)
+			pe->freeze_count--;
 
 	}
 
@@ -119,36 +114,23 @@ static void eeh_thread_launcher(struct work_struct *dummy)
 
 /**
  * eeh_send_failure_event - Generate a PCI error event
- * @edev: EEH device
+ * @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_dev *edev)
+int eeh_send_failure_event(struct eeh_pe *pe)
 {
 	unsigned long flags;
 	struct eeh_event *event;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
-	const char *location;
-
-	if (!mem_init_done) {
-		printk(KERN_ERR "EEH: event during early boot not handled\n");
-		location = of_get_property(dn, "ibm,loc-code", NULL);
-		printk(KERN_ERR "EEH: device node = %s\n", dn->full_name);
-		printk(KERN_ERR "EEH: PCI location = %s\n", location);
-		return 1;
-	}
-	event = kmalloc(sizeof(*event), GFP_ATOMIC);
-	if (event == NULL) {
-		printk(KERN_ERR "EEH: out of memory, event not handled\n");
-		return 1;
- 	}
-
-	if (edev->pdev)
-		pci_dev_get(edev->pdev);
 
-	event->edev = edev;
+	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);
diff --git a/arch/powerpc/platforms/pseries/eeh_pe.c b/arch/powerpc/platforms/pseries/eeh_pe.c
new file mode 100644
index 0000000..797cd18
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/eeh_pe.c
@@ -0,0 +1,652 @@
+/*
+ * 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 __devinit 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 (!(pe->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) {
+		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 c33360ec..19506f9 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -129,27 +129,117 @@ static int pseries_eeh_init(void)
 		eeh_error_buf_size = RTAS_ERROR_LOG_MAX;
 	}
 
+	/* Set EEH probe mode */
+	eeh_probe_mode_set(EEH_PROBE_MODE_DEVTREE);
+
 	return 0;
 }
 
 /**
+ * pseries_eeh_of_probe - EEH probe on the given device
+ * @dn: OF node
+ * @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.
+ */
+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;
+	int enable = 0;
+	int ret;
+
+	/* Retrieve OF node and eeh device */
+	edev = of_node_to_eeh_dev(dn);
+	if (!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);
+
+	/* Skip for bad OF node or PCI-ISA bridge */
+	if (!class_code || !vendor_id || !device_id)
+		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;
+
+	/* Retrieve the device address */
+	regs = of_get_property(dn, "reg", NULL);
+	if (!regs) {
+		pr_warning("%s: OF node property %s::reg not found\n",
+			__func__, dn->full_name);
+		return NULL;
+	}
+
+	/* Initialize the fake PE */
+	memset(&pe, 0, sizeof(struct eeh_pe));
+	pe.phb = edev->phb;
+	pe.config_addr = regs[0];
+
+	/* Enable EEH on the device */
+	ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE);
+	if (!ret) {
+		edev->config_addr = regs[0];
+		/* Retrieve PE address */
+		edev->pe_config_addr = eeh_ops->get_pe_addr(&pe);
+		pe.addr = edev->pe_config_addr;
+
+		/* Some older systems (Power4) allow the ibm,set-eeh-option
+		 * call to succeed even on nodes where EEH is not supported.
+		 * Verify support explicitly.
+		 */
+		ret = eeh_ops->get_state(&pe, NULL);
+		if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT)
+			enable = 1;
+
+		if (enable) {
+			eeh_subsystem_enabled = 1;
+			eeh_add_to_parent_pe(edev);
+
+			pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n",
+				__func__, dn->full_name, pe.phb->global_number,
+				pe.addr, pe.config_addr);
+		} else if (dn->parent && of_node_to_eeh_dev(dn->parent) &&
+			   (of_node_to_eeh_dev(dn->parent))->pe) {
+			/* This device doesn't support EEH, but it may have an
+			 * EEH parent, in which case we mark it as supported.
+			 */
+			edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr;
+			edev->pe_config_addr = of_node_to_eeh_dev(dn->parent)->pe_config_addr;
+			eeh_add_to_parent_pe(edev);
+		}
+	}
+
+	/* Save memory bars */
+	eeh_save_bars(edev);
+
+	return NULL;
+}
+
+/**
  * pseries_eeh_set_option - Initialize EEH or MMIO/DMA reenable
- * @dn: device node
+ * @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 pseries_eeh_set_option(struct device_node *dn, int option)
+static int pseries_eeh_set_option(struct eeh_pe *pe, int option)
 {
 	int ret = 0;
-	struct eeh_dev *edev;
-	const u32 *reg;
 	int config_addr;
 
-	edev = of_node_to_eeh_dev(dn);
-
 	/*
 	 * When we're enabling or disabling EEH functioality on
 	 * the particular PE, the PE config address is possibly
@@ -159,15 +249,11 @@ static int pseries_eeh_set_option(struct device_node *dn, int option)
 	switch (option) {
 	case EEH_OPT_DISABLE:
 	case EEH_OPT_ENABLE:
-		reg = of_get_property(dn, "reg", NULL);
-		config_addr = reg[0];
-		break;
-
 	case EEH_OPT_THAW_MMIO:
 	case EEH_OPT_THAW_DMA:
-		config_addr = edev->config_addr;
-		if (edev->pe_config_addr)
-			config_addr = edev->pe_config_addr;
+		config_addr = pe->config_addr;
+		if (pe->addr)
+			config_addr = pe->addr;
 		break;
 
 	default:
@@ -177,15 +263,15 @@ static int pseries_eeh_set_option(struct device_node *dn, int option)
 	}
 
 	ret = rtas_call(ibm_set_eeh_option, 4, 1, NULL,
-			config_addr, BUID_HI(edev->phb->buid),
-			BUID_LO(edev->phb->buid), option);
+			config_addr, BUID_HI(pe->phb->buid),
+			BUID_LO(pe->phb->buid), option);
 
 	return ret;
 }
 
 /**
  * pseries_eeh_get_pe_addr - Retrieve PE address
- * @dn: device node
+ * @pe: EEH PE
  *
  * Retrieve the assocated PE address. Actually, there're 2 RTAS
  * function calls dedicated for the purpose. We need implement
@@ -196,14 +282,11 @@ static int pseries_eeh_set_option(struct device_node *dn, int option)
  * It's notable that zero'ed return value means invalid PE config
  * address.
  */
-static int pseries_eeh_get_pe_addr(struct device_node *dn)
+static int pseries_eeh_get_pe_addr(struct eeh_pe *pe)
 {
-	struct eeh_dev *edev;
 	int ret = 0;
 	int rets[3];
 
-	edev = of_node_to_eeh_dev(dn);
-
 	if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) {
 		/*
 		 * First of all, we need to make sure there has one PE
@@ -211,18 +294,18 @@ static int pseries_eeh_get_pe_addr(struct device_node *dn)
 		 * meaningless.
 		 */
 		ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets,
-				edev->config_addr, BUID_HI(edev->phb->buid),
-				BUID_LO(edev->phb->buid), 1);
+				pe->config_addr, BUID_HI(pe->phb->buid),
+				BUID_LO(pe->phb->buid), 1);
 		if (ret || (rets[0] == 0))
 			return 0;
 
 		/* Retrieve the associated PE config address */
 		ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets,
-				edev->config_addr, BUID_HI(edev->phb->buid),
-				BUID_LO(edev->phb->buid), 0);
+				pe->config_addr, BUID_HI(pe->phb->buid),
+				BUID_LO(pe->phb->buid), 0);
 		if (ret) {
-			pr_warning("%s: Failed to get PE address for %s\n",
-				__func__, dn->full_name);
+			pr_warning("%s: Failed to get address for PHB#%d-PE#%x\n",
+				__func__, pe->phb->global_number, pe->config_addr);
 			return 0;
 		}
 
@@ -231,11 +314,11 @@ static int pseries_eeh_get_pe_addr(struct device_node *dn)
 
 	if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) {
 		ret = rtas_call(ibm_get_config_addr_info, 4, 2, rets,
-				edev->config_addr, BUID_HI(edev->phb->buid),
-				BUID_LO(edev->phb->buid), 0);
+				pe->config_addr, BUID_HI(pe->phb->buid),
+				BUID_LO(pe->phb->buid), 0);
 		if (ret) {
-			pr_warning("%s: Failed to get PE address for %s\n",
-				__func__, dn->full_name);
+			pr_warning("%s: Failed to get address for PHB#%d-PE#%x\n",
+				__func__, pe->phb->global_number, pe->config_addr);
 			return 0;
 		}
 
@@ -247,7 +330,7 @@ static int pseries_eeh_get_pe_addr(struct device_node *dn)
 
 /**
  * pseries_eeh_get_state - Retrieve PE state
- * @dn: PE associated device node
+ * @pe: EEH PE
  * @state: return value
  *
  * Retrieve the state of the specified PE. On RTAS compliant
@@ -258,30 +341,28 @@ static int pseries_eeh_get_pe_addr(struct device_node *dn)
  * RTAS calls for the purpose, we need to try the new one and back
  * to the old one if the new one couldn't work properly.
  */
-static int pseries_eeh_get_state(struct device_node *dn, int *state)
+static int pseries_eeh_get_state(struct eeh_pe *pe, int *state)
 {
-	struct eeh_dev *edev;
 	int config_addr;
 	int ret;
 	int rets[4];
 	int result;
 
 	/* Figure out PE config address if possible */
-	edev = of_node_to_eeh_dev(dn);
-	config_addr = edev->config_addr;
-	if (edev->pe_config_addr)
-		config_addr = edev->pe_config_addr;
+	config_addr = pe->config_addr;
+	if (pe->addr)
+		config_addr = pe->addr;
 
 	if (ibm_read_slot_reset_state2 != RTAS_UNKNOWN_SERVICE) {
 		ret = rtas_call(ibm_read_slot_reset_state2, 3, 4, rets,
-				config_addr, BUID_HI(edev->phb->buid),
-				BUID_LO(edev->phb->buid));
+				config_addr, BUID_HI(pe->phb->buid),
+				BUID_LO(pe->phb->buid));
 	} else if (ibm_read_slot_reset_state != RTAS_UNKNOWN_SERVICE) {
 		/* Fake PE unavailable info */
 		rets[2] = 0;
 		ret = rtas_call(ibm_read_slot_reset_state, 3, 3, rets,
-				config_addr, BUID_HI(edev->phb->buid),
-				BUID_LO(edev->phb->buid));
+				config_addr, BUID_HI(pe->phb->buid),
+				BUID_LO(pe->phb->buid));
 	} else {
 		return EEH_STATE_NOT_SUPPORT;
 	}
@@ -333,34 +414,32 @@ static int pseries_eeh_get_state(struct device_node *dn, int *state)
 
 /**
  * pseries_eeh_reset - Reset the specified PE
- * @dn: PE associated device node
+ * @pe: EEH PE
  * @option: reset option
  *
  * Reset the specified PE
  */
-static int pseries_eeh_reset(struct device_node *dn, int option)
+static int pseries_eeh_reset(struct eeh_pe *pe, int option)
 {
-	struct eeh_dev *edev;
 	int config_addr;
 	int ret;
 
 	/* Figure out PE address */
-	edev = of_node_to_eeh_dev(dn);
-	config_addr = edev->config_addr;
-	if (edev->pe_config_addr)
-		config_addr = edev->pe_config_addr;
+	config_addr = pe->config_addr;
+	if (pe->addr)
+		config_addr = pe->addr;
 
 	/* Reset PE through RTAS call */
 	ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
-			config_addr, BUID_HI(edev->phb->buid),
-			BUID_LO(edev->phb->buid), option);
+			config_addr, BUID_HI(pe->phb->buid),
+			BUID_LO(pe->phb->buid), option);
 
 	/* If fundamental-reset not supported, try hot-reset */
 	if (option == EEH_RESET_FUNDAMENTAL &&
 	    ret == -8) {
 		ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
-				config_addr, BUID_HI(edev->phb->buid),
-				BUID_LO(edev->phb->buid), EEH_RESET_HOT);
+				config_addr, BUID_HI(pe->phb->buid),
+				BUID_LO(pe->phb->buid), EEH_RESET_HOT);
 	}
 
 	return ret;
@@ -368,13 +447,13 @@ static int pseries_eeh_reset(struct device_node *dn, int option)
 
 /**
  * pseries_eeh_wait_state - Wait for PE state
- * @dn: PE associated device node
+ * @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 pseries_eeh_wait_state(struct device_node *dn, int max_wait)
+static int pseries_eeh_wait_state(struct eeh_pe *pe, int max_wait)
 {
 	int ret;
 	int mwait;
@@ -391,7 +470,7 @@ static int pseries_eeh_wait_state(struct device_node *dn, int max_wait)
 #define EEH_STATE_MAX_WAIT_TIME	(300 * 1000)
 
 	while (1) {
-		ret = pseries_eeh_get_state(dn, &mwait);
+		ret = pseries_eeh_get_state(pe, &mwait);
 
 		/*
 		 * If the PE's state is temporarily unavailable,
@@ -426,7 +505,7 @@ static int pseries_eeh_wait_state(struct device_node *dn, int max_wait)
 
 /**
  * pseries_eeh_get_log - Retrieve error log
- * @dn: device node
+ * @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
@@ -435,24 +514,22 @@ static int pseries_eeh_wait_state(struct device_node *dn, int max_wait)
  * Actually, the error will be retrieved through the dedicated
  * RTAS call.
  */
-static int pseries_eeh_get_log(struct device_node *dn, int severity, char *drv_log, unsigned long len)
+static int pseries_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len)
 {
-	struct eeh_dev *edev;
 	int config_addr;
 	unsigned long flags;
 	int ret;
 
-	edev = of_node_to_eeh_dev(dn);
 	spin_lock_irqsave(&slot_errbuf_lock, flags);
 	memset(slot_errbuf, 0, eeh_error_buf_size);
 
 	/* Figure out the PE address */
-	config_addr = edev->config_addr;
-	if (edev->pe_config_addr)
-		config_addr = edev->pe_config_addr;
+	config_addr = pe->config_addr;
+	if (pe->addr)
+		config_addr = pe->addr;
 
 	ret = rtas_call(ibm_slot_error_detail, 8, 1, NULL, config_addr,
-			BUID_HI(edev->phb->buid), BUID_LO(edev->phb->buid),
+			BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid),
 			virt_to_phys(drv_log), len,
 			virt_to_phys(slot_errbuf), eeh_error_buf_size,
 			severity);
@@ -465,40 +542,38 @@ static int pseries_eeh_get_log(struct device_node *dn, int severity, char *drv_l
 
 /**
  * pseries_eeh_configure_bridge - Configure PCI bridges in the indicated PE
- * @dn: PE associated device node
+ * @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 pseries_eeh_configure_bridge(struct device_node *dn)
+static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
 {
-	struct eeh_dev *edev;
 	int config_addr;
 	int ret;
 
 	/* Figure out the PE address */
-	edev = of_node_to_eeh_dev(dn);
-	config_addr = edev->config_addr;
-	if (edev->pe_config_addr)
-		config_addr = edev->pe_config_addr;
+	config_addr = pe->config_addr;
+	if (pe->addr)
+		config_addr = pe->addr;
 
 	/* Use new configure-pe function, if supported */
 	if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
 		ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
-				config_addr, BUID_HI(edev->phb->buid),
-				BUID_LO(edev->phb->buid));
+				config_addr, BUID_HI(pe->phb->buid),
+				BUID_LO(pe->phb->buid));
 	} else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
 		ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
-				config_addr, BUID_HI(edev->phb->buid),
-				BUID_LO(edev->phb->buid));
+				config_addr, BUID_HI(pe->phb->buid),
+				BUID_LO(pe->phb->buid));
 	} else {
 		return -EFAULT;
 	}
 
 	if (ret)
-		pr_warning("%s: Unable to configure bridge %d for %s\n",
-			__func__, ret, dn->full_name);
+		pr_warning("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
+			__func__, pe->phb->global_number, pe->addr, ret);
 
 	return ret;
 }
@@ -542,6 +617,8 @@ static int pseries_eeh_write_config(struct device_node *dn, int where, int size,
 static struct eeh_ops pseries_eeh_ops = {
 	.name			= "pseries",
 	.init			= pseries_eeh_init,
+	.of_probe		= pseries_eeh_of_probe,
+	.dev_probe		= NULL,
 	.set_option		= pseries_eeh_set_option,
 	.get_pe_addr		= pseries_eeh_get_pe_addr,
 	.get_state		= pseries_eeh_get_state,
@@ -559,7 +636,21 @@ static struct eeh_ops pseries_eeh_ops = {
  * EEH initialization on pseries platform. This function should be
  * called before any EEH related functions.
  */
-int __init eeh_pseries_init(void)
+static int __init eeh_pseries_init(void)
 {
-	return eeh_ops_register(&pseries_eeh_ops);
+	int ret = -EINVAL;
+
+	if (!machine_is(pseries))
+		return ret;
+
+	ret = eeh_ops_register(&pseries_eeh_ops);
+	if (!ret)
+		pr_info("EEH: pSeries platform initialized\n");
+	else
+		pr_info("EEH: pSeries platform initialization failure (%d)\n",
+			ret);
+
+	return ret;
 }
+
+early_initcall(eeh_pseries_init);
diff --git a/arch/powerpc/platforms/pseries/eeh_sysfs.c b/arch/powerpc/platforms/pseries/eeh_sysfs.c
index 243b351..d377083 100644
--- a/arch/powerpc/platforms/pseries/eeh_sysfs.c
+++ b/arch/powerpc/platforms/pseries/eeh_sysfs.c
@@ -53,9 +53,6 @@ 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");
-EEH_SHOW_ATTR(eeh_check_count,     check_count,     "%d"  );
-EEH_SHOW_ATTR(eeh_freeze_count,    freeze_count,    "%d"  );
-EEH_SHOW_ATTR(eeh_false_positives, false_positives, "%d"  );
 
 void eeh_sysfs_add_device(struct pci_dev *pdev)
 {
@@ -64,9 +61,6 @@ void eeh_sysfs_add_device(struct pci_dev *pdev)
 	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);
-	rc += device_create_file(&pdev->dev, &dev_attr_eeh_check_count);
-	rc += device_create_file(&pdev->dev, &dev_attr_eeh_false_positives);
-	rc += device_create_file(&pdev->dev, &dev_attr_eeh_freeze_count);
 
 	if (rc)
 		printk(KERN_WARNING "EEH: Unable to create sysfs entries\n");
@@ -77,8 +71,5 @@ 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);
-	device_remove_file(&pdev->dev, &dev_attr_eeh_check_count);
-	device_remove_file(&pdev->dev, &dev_attr_eeh_false_positives);
-	device_remove_file(&pdev->dev, &dev_attr_eeh_freeze_count);
 }
 
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index bca220f..6153eea 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -28,6 +28,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/memblock.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>	/* for show_stack */
 #include <linux/string.h>
@@ -41,7 +42,6 @@
 #include <asm/iommu.h>
 #include <asm/pci-bridge.h>
 #include <asm/machdep.h>
-#include <asm/abs_addr.h>
 #include <asm/pSeries_reconfig.h>
 #include <asm/firmware.h>
 #include <asm/tce.h>
@@ -99,7 +99,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
 
 	while (npages--) {
 		/* can't move this out since we might cross MEMBLOCK boundary */
-		rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
+		rpn = __pa(uaddr) >> TCE_SHIFT;
 		*tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
 
 		uaddr += TCE_PAGE_SIZE;
@@ -148,7 +148,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	int ret = 0;
 	long tcenum_start = tcenum, npages_start = npages;
 
-	rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
+	rpn = __pa(uaddr) >> TCE_SHIFT;
 	proto_tce = TCE_PCI_READ;
 	if (direction != DMA_TO_DEVICE)
 		proto_tce |= TCE_PCI_WRITE;
@@ -217,7 +217,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		__get_cpu_var(tce_page) = tcep;
 	}
 
-	rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
+	rpn = __pa(uaddr) >> TCE_SHIFT;
 	proto_tce = TCE_PCI_READ;
 	if (direction != DMA_TO_DEVICE)
 		proto_tce |= TCE_PCI_WRITE;
@@ -237,7 +237,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 
 		rc = plpar_tce_put_indirect((u64)tbl->it_index,
 					    (u64)tcenum << 12,
-					    (u64)virt_to_abs(tcep),
+					    (u64)__pa(tcep),
 					    limit);
 
 		npages -= limit;
@@ -441,7 +441,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 
 		rc = plpar_tce_put_indirect(liobn,
 					    dma_offset,
-					    (u64)virt_to_abs(tcep),
+					    (u64)__pa(tcep),
 					    limit);
 
 		num_tce -= limit;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 5f3ef87..0da39fe 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -31,7 +31,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/machdep.h>
-#include <asm/abs_addr.h>
 #include <asm/mmu_context.h>
 #include <asm/iommu.h>
 #include <asm/tlbflush.h>
@@ -108,9 +107,9 @@ void vpa_init(int cpu)
 }
 
 static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
- 			      unsigned long va, unsigned long pa,
- 			      unsigned long rflags, unsigned long vflags,
-			      int psize, int ssize)
+				     unsigned long vpn, unsigned long pa,
+				     unsigned long rflags, unsigned long vflags,
+				     int psize, int ssize)
 {
 	unsigned long lpar_rc;
 	unsigned long flags;
@@ -118,11 +117,11 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 	unsigned long hpte_v, hpte_r;
 
 	if (!(vflags & HPTE_V_BOLTED))
-		pr_devel("hpte_insert(group=%lx, va=%016lx, pa=%016lx, "
-			 "rflags=%lx, vflags=%lx, psize=%d)\n",
-			 hpte_group, va, pa, rflags, vflags, psize);
+		pr_devel("hpte_insert(group=%lx, vpn=%016lx, "
+			 "pa=%016lx, rflags=%lx, vflags=%lx, psize=%d)\n",
+			 hpte_group, vpn,  pa, rflags, vflags, psize);
 
-	hpte_v = hpte_encode_v(va, psize, ssize) | vflags | HPTE_V_VALID;
+	hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
 	hpte_r = hpte_encode_r(pa, psize) | rflags;
 
 	if (!(vflags & HPTE_V_BOLTED))
@@ -227,22 +226,6 @@ static void pSeries_lpar_hptab_clear(void)
 }
 
 /*
- * This computes the AVPN and B fields of the first dword of a HPTE,
- * for use when we want to match an existing PTE.  The bottom 7 bits
- * of the returned value are zero.
- */
-static inline unsigned long hpte_encode_avpn(unsigned long va, int psize,
-					     int ssize)
-{
-	unsigned long v;
-
-	v = (va >> 23) & ~(mmu_psize_defs[psize].avpnm);
-	v <<= HPTE_V_AVPN_SHIFT;
-	v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
-	return v;
-}
-
-/*
  * NOTE: for updatepp ops we are fortunate that the linux "newpp" bits and
  * the low 3 bits of flags happen to line up.  So no transform is needed.
  * We can probably optimize here and assume the high bits of newpp are
@@ -250,14 +233,14 @@ static inline unsigned long hpte_encode_avpn(unsigned long va, int psize,
  */
 static long pSeries_lpar_hpte_updatepp(unsigned long slot,
 				       unsigned long newpp,
-				       unsigned long va,
+				       unsigned long vpn,
 				       int psize, int ssize, int local)
 {
 	unsigned long lpar_rc;
 	unsigned long flags = (newpp & 7) | H_AVPN;
 	unsigned long want_v;
 
-	want_v = hpte_encode_avpn(va, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
 	pr_devel("    update: avpnv=%016lx, hash=%016lx, f=%lx, psize: %d ...",
 		 want_v, slot, flags, psize);
@@ -295,15 +278,15 @@ static unsigned long pSeries_lpar_hpte_getword0(unsigned long slot)
 	return dword0;
 }
 
-static long pSeries_lpar_hpte_find(unsigned long va, int psize, int ssize)
+static long pSeries_lpar_hpte_find(unsigned long vpn, int psize, int ssize)
 {
 	unsigned long hash;
 	unsigned long i;
 	long slot;
 	unsigned long want_v, hpte_v;
 
-	hash = hpt_hash(va, mmu_psize_defs[psize].shift, ssize);
-	want_v = hpte_encode_avpn(va, psize, ssize);
+	hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
+	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
 	/* Bolted entries are always in the primary group */
 	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
@@ -323,12 +306,13 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
 					     unsigned long ea,
 					     int psize, int ssize)
 {
-	unsigned long lpar_rc, slot, vsid, va, flags;
+	unsigned long vpn;
+	unsigned long lpar_rc, slot, vsid, flags;
 
 	vsid = get_kernel_vsid(ea, ssize);
-	va = hpt_va(ea, vsid, ssize);
+	vpn = hpt_vpn(ea, vsid, ssize);
 
-	slot = pSeries_lpar_hpte_find(va, psize, ssize);
+	slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
 	BUG_ON(slot == -1);
 
 	flags = newpp & 7;
@@ -337,17 +321,17 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
 	BUG_ON(lpar_rc != H_SUCCESS);
 }
 
-static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
+static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
 					 int psize, int ssize, int local)
 {
 	unsigned long want_v;
 	unsigned long lpar_rc;
 	unsigned long dummy1, dummy2;
 
-	pr_devel("    inval : slot=%lx, va=%016lx, psize: %d, local: %d\n",
-		 slot, va, psize, local);
+	pr_devel("    inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n",
+		 slot, vpn, psize, local);
 
-	want_v = hpte_encode_avpn(va, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, psize, ssize);
 	lpar_rc = plpar_pte_remove(H_AVPN, slot, want_v, &dummy1, &dummy2);
 	if (lpar_rc == H_NOT_FOUND)
 		return;
@@ -358,15 +342,16 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
 static void pSeries_lpar_hpte_removebolted(unsigned long ea,
 					   int psize, int ssize)
 {
-	unsigned long slot, vsid, va;
+	unsigned long vpn;
+	unsigned long slot, vsid;
 
 	vsid = get_kernel_vsid(ea, ssize);
-	va = hpt_va(ea, vsid, ssize);
+	vpn = hpt_vpn(ea, vsid, ssize);
 
-	slot = pSeries_lpar_hpte_find(va, psize, ssize);
+	slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
 	BUG_ON(slot == -1);
 
-	pSeries_lpar_hpte_invalidate(slot, va, psize, ssize, 0);
+	pSeries_lpar_hpte_invalidate(slot, vpn, psize, ssize, 0);
 }
 
 /* Flag bits for H_BULK_REMOVE */
@@ -382,12 +367,12 @@ static void pSeries_lpar_hpte_removebolted(unsigned long ea,
  */
 static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
 {
+	unsigned long vpn;
 	unsigned long i, pix, rc;
 	unsigned long flags = 0;
 	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 	unsigned long param[9];
-	unsigned long va;
 	unsigned long hash, index, shift, hidx, slot;
 	real_pte_t pte;
 	int psize, ssize;
@@ -399,21 +384,21 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
 	ssize = batch->ssize;
 	pix = 0;
 	for (i = 0; i < number; i++) {
-		va = batch->vaddr[i];
+		vpn = batch->vpn[i];
 		pte = batch->pte[i];
-		pte_iterate_hashed_subpages(pte, psize, va, index, shift) {
-			hash = hpt_hash(va, shift, ssize);
+		pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
+			hash = hpt_hash(vpn, shift, ssize);
 			hidx = __rpte_to_hidx(pte, index);
 			if (hidx & _PTEIDX_SECONDARY)
 				hash = ~hash;
 			slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 			slot += hidx & _PTEIDX_GROUP_IX;
 			if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
-				pSeries_lpar_hpte_invalidate(slot, va, psize,
+				pSeries_lpar_hpte_invalidate(slot, vpn, psize,
 							     ssize, local);
 			} else {
 				param[pix] = HBR_REQUEST | HBR_AVPN | slot;
-				param[pix+1] = hpte_encode_avpn(va, psize,
+				param[pix+1] = hpte_encode_avpn(vpn, psize,
 								ssize);
 				pix += 2;
 				if (pix == 8) {
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 109fdb7..d19f497 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -210,6 +210,7 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total)
 static struct device_node *find_pe_dn(struct pci_dev *dev, int *total)
 {
 	struct device_node *dn;
+	struct eeh_dev *edev;
 
 	/* Found our PE and assume 8 at that point. */
 
@@ -217,7 +218,10 @@ static struct device_node *find_pe_dn(struct pci_dev *dev, int *total)
 	if (!dn)
 		return NULL;
 
-	dn = eeh_find_device_pe(dn);
+	/* Get the top level device in the PE */
+	edev = of_node_to_eeh_dev(dn);
+	edev = list_first_entry(&edev->pe->edevs, struct eeh_dev, list);
+	dn = eeh_dev_to_of_node(edev);
 	if (!dn)
 		return NULL;
 
@@ -387,12 +391,13 @@ static int check_msix_entries(struct pci_dev *pdev)
 	return 0;
 }
 
-static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
 {
 	struct pci_dn *pdn;
 	int hwirq, virq, i, rc;
 	struct msi_desc *entry;
 	struct msi_msg msg;
+	int nvec = nvec_in;
 
 	pdn = get_pdn(pdev);
 	if (!pdn)
@@ -402,10 +407,23 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		return -EINVAL;
 
 	/*
+	 * Firmware currently refuse any non power of two allocation
+	 * so we round up if the quota will allow it.
+	 */
+	if (type == PCI_CAP_ID_MSIX) {
+		int m = roundup_pow_of_two(nvec);
+		int quota = msi_quota_for_device(pdev, m);
+
+		if (quota >= m)
+			nvec = m;
+	}
+
+	/*
 	 * Try the new more explicit firmware interface, if that fails fall
 	 * back to the old interface. The old interface is known to never
 	 * return MSI-Xs.
 	 */
+again:
 	if (type == PCI_CAP_ID_MSI) {
 		rc = rtas_change_msi(pdn, RTAS_CHANGE_MSI_FN, nvec);
 
@@ -417,6 +435,10 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		rc = rtas_change_msi(pdn, RTAS_CHANGE_MSIX_FN, nvec);
 
 	if (rc != nvec) {
+		if (nvec != nvec_in) {
+			nvec = nvec_in;
+			goto again;
+		}
 		pr_debug("rtas_msi: rtas_change_msi() failed\n");
 		return rc;
 	}
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 2c6ded2..56b864d 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -73,7 +73,7 @@ void __init pSeries_final_fixup(void)
 {
 	pSeries_request_regions();
 
-	pci_addr_cache_build();
+	eeh_addr_cache_build();
 }
 
 /*
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 3ccebc8..261a577 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -65,27 +65,43 @@ 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
+ * __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)
+void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe)
 {
- 	struct pci_dev *dev, *tmp;
+	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);
+		__pcibios_remove_pci_devices(child_bus, purge_pe);
 
 	pr_debug("PCI: Removing devices on bus %04x:%02x\n",
-		 pci_domain_nr(bus),  bus->number);
+		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);
- 		pci_stop_and_remove_bus_device(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);
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 51ecac9..e3cb7ae 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -388,10 +388,8 @@ static void __init pSeries_setup_arch(void)
 
 	/* Find and initialize PCI host bridges */
 	init_pci_config_tokens();
-	eeh_pseries_init();
 	find_and_init_phbs();
 	pSeries_reconfig_notifier_register(&pci_dn_reconfig_nb);
-	eeh_init();
 
 	pSeries_nvram_init();
 
@@ -416,16 +414,20 @@ static int __init pSeries_init_panel(void)
 }
 machine_arch_initcall(pseries, pSeries_init_panel);
 
-static int pseries_set_dabr(unsigned long dabr)
+static int pseries_set_dabr(unsigned long dabr, unsigned long dabrx)
 {
 	return plpar_hcall_norets(H_SET_DABR, dabr);
 }
 
-static int pseries_set_xdabr(unsigned long dabr)
+static int pseries_set_xdabr(unsigned long dabr, unsigned long dabrx)
 {
-	/* We want to catch accesses from kernel and userspace */
-	return plpar_hcall_norets(H_SET_XDABR, dabr,
-			H_DABRX_KERNEL | H_DABRX_USER);
+	/* Have to set at least one bit in the DABRX according to PAPR */
+	if (dabrx == 0 && dabr == 0)
+		dabrx = DABRX_USER;
+	/* PAPR says we can only set kernel and user bits */
+	dabrx &= DABRX_KERNEL | DABRX_USER;
+
+	return plpar_hcall_norets(H_SET_XDABR, dabr, dabrx);
 }
 
 #define CMO_CHARACTERISTICS_TOKEN 44
@@ -529,10 +531,10 @@ static void __init pSeries_init_early(void)
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		hvc_vio_init_early();
 #endif
-	if (firmware_has_feature(FW_FEATURE_DABR))
-		ppc_md.set_dabr = pseries_set_dabr;
-	else if (firmware_has_feature(FW_FEATURE_XDABR))
+	if (firmware_has_feature(FW_FEATURE_XDABR))
 		ppc_md.set_dabr = pseries_set_xdabr;
+	else if (firmware_has_feature(FW_FEATURE_DABR))
+		ppc_md.set_dabr = pseries_set_dabr;
 
 	pSeries_cmo_feature_init();
 	iommu_init_early_pSeries();