Initial file dump from open source releaseHEADmaster

14 files changed, 3497 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
new file mode 100644
index 00000000..c24684c8
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -0,0 +1,22 @@
+config PPC_POWERNV
+	depends on PPC64 && PPC_BOOK3S
+	bool "IBM PowerNV (Non-Virtualized) platform support"
+	select PPC_NATIVE
+	select PPC_XICS
+	select PPC_ICP_NATIVE
+	select PPC_P7_NAP
+	select PPC_PCI_CHOICE if EMBEDDED
+	select EPAPR_BOOT
+	default y
+
+config POWERNV_MSI
+	bool "Support PCI MSI on PowerNV platform"
+	depends on PCI_MSI
+	default y
+
+config PPC_POWERNV_RTAS
+	depends on PPC_POWERNV
+	bool "Support for RTAS based PowerNV platforms such as BML"
+	default y
+	select PPC_ICS_RTAS
+	select PPC_RTAS
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
new file mode 100644
index 00000000..bcc3cb48
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -0,0 +1,5 @@
+obj-y			+= setup.o opal-takeover.o opal-wrappers.o opal.o
+obj-y			+= opal-rtc.o opal-nvram.o
+
+obj-$(CONFIG_SMP)	+= smp.o
+obj-$(CONFIG_PCI)	+= pci.o pci-p5ioc2.o pci-ioda.o
diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c
new file mode 100644
index 00000000..3f83e1ae
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-nvram.c
@@ -0,0 +1,88 @@
+/*
+ * PowerNV nvram code.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define DEBUG
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of.h>
+
+#include <asm/opal.h>
+#include <asm/machdep.h>
+
+static unsigned int nvram_size;
+
+static ssize_t opal_nvram_size(void)
+{
+	return nvram_size;
+}
+
+static ssize_t opal_nvram_read(char *buf, size_t count, loff_t *index)
+{
+	s64 rc;
+	int off;
+
+	if (*index >= nvram_size)
+		return 0;
+	off = *index;
+	if ((off + count) > nvram_size)
+		count = nvram_size - off;
+	rc = opal_read_nvram(__pa(buf), count, off);
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+	*index += count;
+	return count;
+}
+
+static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index)
+{
+	s64 rc = OPAL_BUSY;
+	int off;
+
+	if (*index >= nvram_size)
+		return 0;
+	off = *index;
+	if ((off + count) > nvram_size)
+		count = nvram_size - off;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_write_nvram(__pa(buf), count, off);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+	}
+	*index += count;
+	return count;
+}
+
+void __init opal_nvram_init(void)
+{
+	struct device_node *np;
+	const u32 *nbytes_p;
+
+	np = of_find_compatible_node(NULL, NULL, "ibm,opal-nvram");
+	if (np == NULL)
+		return;
+
+	nbytes_p = of_get_property(np, "#bytes", NULL);
+	if (!nbytes_p) {
+		of_node_put(np);
+		return;
+	}
+	nvram_size = *nbytes_p;
+
+	printk(KERN_INFO "OPAL nvram setup, %u bytes\n", nvram_size);
+	of_node_put(np);
+
+	ppc_md.nvram_read = opal_nvram_read;
+	ppc_md.nvram_write = opal_nvram_write;
+	ppc_md.nvram_size = opal_nvram_size;
+}
+
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
new file mode 100644
index 00000000..2aa7641a
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -0,0 +1,97 @@
+/*
+ * PowerNV Real Time Clock.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/time.h>
+#include <linux/bcd.h>
+#include <linux/rtc.h>
+#include <linux/delay.h>
+
+#include <asm/opal.h>
+#include <asm/firmware.h>
+
+static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm)
+{
+	tm->tm_year	= ((bcd2bin(y_m_d >> 24) * 100) +
+			   bcd2bin((y_m_d >> 16) & 0xff)) - 1900;
+	tm->tm_mon	= bcd2bin((y_m_d >> 8) & 0xff) - 1;
+	tm->tm_mday	= bcd2bin(y_m_d & 0xff);
+	tm->tm_hour	= bcd2bin((h_m_s_ms >> 56) & 0xff);
+	tm->tm_min	= bcd2bin((h_m_s_ms >> 48) & 0xff);
+	tm->tm_sec	= bcd2bin((h_m_s_ms >> 40) & 0xff);
+
+        GregorianDay(tm);
+}
+
+unsigned long __init opal_get_boot_time(void)
+{
+	struct rtc_time tm;
+	u32 y_m_d;
+	u64 h_m_s_ms;
+	long rc = OPAL_BUSY;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_read(&y_m_d, &h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
+	if (rc != OPAL_SUCCESS)
+		return 0;
+	opal_to_tm(y_m_d, h_m_s_ms, &tm);
+	return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+		      tm.tm_hour, tm.tm_min, tm.tm_sec);
+}
+
+void opal_get_rtc_time(struct rtc_time *tm)
+{
+	long rc = OPAL_BUSY;
+	u32 y_m_d;
+	u64 h_m_s_ms;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_read(&y_m_d, &h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
+	if (rc != OPAL_SUCCESS)
+		return;
+	opal_to_tm(y_m_d, h_m_s_ms, tm);
+}
+
+int opal_set_rtc_time(struct rtc_time *tm)
+{
+	long rc = OPAL_BUSY;
+	u32 y_m_d = 0;
+	u64 h_m_s_ms = 0;
+
+	y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24;
+	y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16;
+	y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8;
+	y_m_d |= ((u32)bin2bcd(tm->tm_mday));
+
+	h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56;
+	h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48;
+	h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_write(y_m_d, h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
+	return rc == OPAL_SUCCESS ? 0 : -EIO;
+}
diff --git a/arch/powerpc/platforms/powernv/opal-takeover.S b/arch/powerpc/platforms/powernv/opal-takeover.S
new file mode 100644
index 00000000..3cd26289
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-takeover.S
@@ -0,0 +1,138 @@
+/*
+ * PowerNV OPAL takeover assembly code, for use by prom_init.c
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/hvcall.h>
+#include <asm/asm-offsets.h>
+#include <asm/opal.h>
+
+#define H_HAL_TAKEOVER			0x5124
+#define H_HAL_TAKEOVER_QUERY_MAGIC	-1
+
+	.text
+_GLOBAL(opal_query_takeover)
+	mfcr	r0
+	stw	r0,8(r1)
+	std	r3,STK_PARAM(R3)(r1)
+	std	r4,STK_PARAM(R4)(r1)
+	li	r3,H_HAL_TAKEOVER
+	li	r4,H_HAL_TAKEOVER_QUERY_MAGIC
+	HVSC
+	ld	r10,STK_PARAM(R3)(r1)
+	std	r4,0(r10)
+	ld	r10,STK_PARAM(R4)(r1)
+	std	r5,0(r10)
+	lwz	r0,8(r1)
+	mtcrf	0xff,r0
+	blr
+
+_GLOBAL(opal_do_takeover)
+	mfcr	r0
+	stw	r0,8(r1)
+	mflr	r0
+	std	r0,16(r1)
+	bl	__opal_do_takeover
+	ld	r0,16(r1)
+	mtlr	r0
+	lwz	r0,8(r1)
+	mtcrf	0xff,r0
+	blr
+
+__opal_do_takeover:
+	ld	r4,0(r3)
+	ld	r5,0x8(r3)
+	ld	r6,0x10(r3)
+	ld	r7,0x18(r3)
+	ld	r8,0x20(r3)
+	ld	r9,0x28(r3)
+	ld	r10,0x30(r3)
+	ld	r11,0x38(r3)
+	li	r3,H_HAL_TAKEOVER
+	HVSC
+	blr
+
+	.globl opal_secondary_entry
+opal_secondary_entry:
+	mr	r31,r3
+	mfmsr	r11
+	li	r12,(MSR_SF | MSR_ISF)@highest
+	sldi	r12,r12,48
+	or	r11,r11,r12
+	mtmsrd	r11
+	isync
+	mfspr	r4,SPRN_PIR
+	std	r4,0(r3)
+1:	HMT_LOW
+	ld	r4,8(r3)
+	cmpli	cr0,r4,0
+	beq	1b
+	HMT_MEDIUM
+1:	addi	r3,r31,16
+	bl	__opal_do_takeover
+	b	1b
+
+_GLOBAL(opal_enter_rtas)
+	mflr	r0
+	std	r0,16(r1)
+        stdu	r1,-PROM_FRAME_SIZE(r1)	/* Save SP and create stack space */
+
+	/* Because PROM is running in 32b mode, it clobbers the high order half
+	 * of all registers that it saves.  We therefore save those registers
+	 * PROM might touch to the stack.  (r0, r3-r13 are caller saved)
+	*/
+	SAVE_GPR(2, r1)
+	SAVE_GPR(13, r1)
+	SAVE_8GPRS(14, r1)
+	SAVE_10GPRS(22, r1)
+	mfcr	r10
+	mfmsr	r11
+	std	r10,_CCR(r1)
+	std	r11,_MSR(r1)
+
+	/* Get the PROM entrypoint */
+	mtlr	r5
+
+	/* Switch MSR to 32 bits mode
+	 */
+        li      r12,1
+        rldicr  r12,r12,MSR_SF_LG,(63-MSR_SF_LG)
+        andc    r11,r11,r12
+        li      r12,1
+        rldicr  r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG)
+        andc    r11,r11,r12
+        mtmsrd  r11
+        isync
+
+	/* Enter RTAS here... */
+	blrl
+
+	/* Just make sure that r1 top 32 bits didn't get
+	 * corrupt by OF
+	 */
+	rldicl	r1,r1,0,32
+
+	/* Restore the MSR (back to 64 bits) */
+	ld	r0,_MSR(r1)
+	MTMSRD(r0)
+        isync
+
+	/* Restore other registers */
+	REST_GPR(2, r1)
+	REST_GPR(13, r1)
+	REST_8GPRS(14, r1)
+	REST_10GPRS(22, r1)
+	ld	r4,_CCR(r1)
+	mtcr	r4
+
+        addi	r1,r1,PROM_FRAME_SIZE
+	ld	r0,16(r1)
+	mtlr    r0
+	blr
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
new file mode 100644
index 00000000..6fabe92e
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -0,0 +1,110 @@
+/*
+ * PowerNV OPAL API wrappers
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/hvcall.h>
+#include <asm/asm-offsets.h>
+#include <asm/opal.h>
+
+/* TODO:
+ *
+ * - Trace irqs in/off (needs saving/restoring all args, argh...)
+ * - Get r11 feed up by Dave so I can have better register usage
+ */
+#define OPAL_CALL(name, token)		\
+ _GLOBAL(name);				\
+	mflr	r0;			\
+	mfcr	r12;			\
+	std	r0,16(r1);		\
+	std	r12,8(r1);		\
+	std	r1,PACAR1(r13);		\
+	li	r0,0;			\
+	mfmsr	r12;			\
+	ori	r0,r0,MSR_EE;		\
+	std	r12,PACASAVEDMSR(r13);	\
+	andc	r12,r12,r0;		\
+	mtmsrd	r12,1;			\
+	LOAD_REG_ADDR(r0,.opal_return);	\
+	mtlr	r0;			\
+	li	r0,MSR_DR|MSR_IR;	\
+	andc	r12,r12,r0;		\
+	li	r0,token;		\
+	mtspr	SPRN_HSRR1,r12;		\
+	LOAD_REG_ADDR(r11,opal);	\
+	ld	r12,8(r11);		\
+	ld	r2,0(r11);		\
+	mtspr	SPRN_HSRR0,r12;		\
+	hrfid
+
+_STATIC(opal_return)
+	ld	r2,PACATOC(r13);
+	ld	r4,8(r1);
+	ld	r5,16(r1);
+	ld	r6,PACASAVEDMSR(r13);
+	mtspr	SPRN_SRR0,r5;
+	mtspr	SPRN_SRR1,r6;
+	mtcr	r4;
+	rfid
+
+OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
+OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
+OPAL_CALL(opal_console_write_buffer_space,	OPAL_CONSOLE_WRITE_BUFFER_SPACE);
+OPAL_CALL(opal_rtc_read,			OPAL_RTC_READ);
+OPAL_CALL(opal_rtc_write,			OPAL_RTC_WRITE);
+OPAL_CALL(opal_cec_power_down,			OPAL_CEC_POWER_DOWN);
+OPAL_CALL(opal_cec_reboot,			OPAL_CEC_REBOOT);
+OPAL_CALL(opal_read_nvram,			OPAL_READ_NVRAM);
+OPAL_CALL(opal_write_nvram,			OPAL_WRITE_NVRAM);
+OPAL_CALL(opal_handle_interrupt,		OPAL_HANDLE_INTERRUPT);
+OPAL_CALL(opal_poll_events,			OPAL_POLL_EVENTS);
+OPAL_CALL(opal_pci_set_hub_tce_memory,		OPAL_PCI_SET_HUB_TCE_MEMORY);
+OPAL_CALL(opal_pci_set_phb_tce_memory,		OPAL_PCI_SET_PHB_TCE_MEMORY);
+OPAL_CALL(opal_pci_config_read_byte,		OPAL_PCI_CONFIG_READ_BYTE);
+OPAL_CALL(opal_pci_config_read_half_word,	OPAL_PCI_CONFIG_READ_HALF_WORD);
+OPAL_CALL(opal_pci_config_read_word,		OPAL_PCI_CONFIG_READ_WORD);
+OPAL_CALL(opal_pci_config_write_byte,		OPAL_PCI_CONFIG_WRITE_BYTE);
+OPAL_CALL(opal_pci_config_write_half_word,	OPAL_PCI_CONFIG_WRITE_HALF_WORD);
+OPAL_CALL(opal_pci_config_write_word,		OPAL_PCI_CONFIG_WRITE_WORD);
+OPAL_CALL(opal_set_xive,			OPAL_SET_XIVE);
+OPAL_CALL(opal_get_xive,			OPAL_GET_XIVE);
+OPAL_CALL(opal_register_exception_handler,	OPAL_REGISTER_OPAL_EXCEPTION_HANDLER);
+OPAL_CALL(opal_pci_eeh_freeze_status,		OPAL_PCI_EEH_FREEZE_STATUS);
+OPAL_CALL(opal_pci_eeh_freeze_clear,		OPAL_PCI_EEH_FREEZE_CLEAR);
+OPAL_CALL(opal_pci_shpc,			OPAL_PCI_SHPC);
+OPAL_CALL(opal_pci_phb_mmio_enable,		OPAL_PCI_PHB_MMIO_ENABLE);
+OPAL_CALL(opal_pci_set_phb_mem_window,		OPAL_PCI_SET_PHB_MEM_WINDOW);
+OPAL_CALL(opal_pci_map_pe_mmio_window,		OPAL_PCI_MAP_PE_MMIO_WINDOW);
+OPAL_CALL(opal_pci_set_phb_table_memory,	OPAL_PCI_SET_PHB_TABLE_MEMORY);
+OPAL_CALL(opal_pci_set_pe,			OPAL_PCI_SET_PE);
+OPAL_CALL(opal_pci_set_peltv,			OPAL_PCI_SET_PELTV);
+OPAL_CALL(opal_pci_set_mve,			OPAL_PCI_SET_MVE);
+OPAL_CALL(opal_pci_set_mve_enable,		OPAL_PCI_SET_MVE_ENABLE);
+OPAL_CALL(opal_pci_get_xive_reissue,		OPAL_PCI_GET_XIVE_REISSUE);
+OPAL_CALL(opal_pci_set_xive_reissue,		OPAL_PCI_SET_XIVE_REISSUE);
+OPAL_CALL(opal_pci_set_xive_pe,			OPAL_PCI_SET_XIVE_PE);
+OPAL_CALL(opal_get_xive_source,			OPAL_GET_XIVE_SOURCE);
+OPAL_CALL(opal_get_msi_32,			OPAL_GET_MSI_32);
+OPAL_CALL(opal_get_msi_64,			OPAL_GET_MSI_64);
+OPAL_CALL(opal_start_cpu,			OPAL_START_CPU);
+OPAL_CALL(opal_query_cpu_status,		OPAL_QUERY_CPU_STATUS);
+OPAL_CALL(opal_write_oppanel,			OPAL_WRITE_OPPANEL);
+OPAL_CALL(opal_pci_map_pe_dma_window,		OPAL_PCI_MAP_PE_DMA_WINDOW);
+OPAL_CALL(opal_pci_map_pe_dma_window_real,	OPAL_PCI_MAP_PE_DMA_WINDOW_REAL);
+OPAL_CALL(opal_pci_reset,			OPAL_PCI_RESET);
+OPAL_CALL(opal_pci_get_hub_diag_data,		OPAL_PCI_GET_HUB_DIAG_DATA);
+OPAL_CALL(opal_pci_get_phb_diag_data,		OPAL_PCI_GET_PHB_DIAG_DATA);
+OPAL_CALL(opal_pci_fence_phb,			OPAL_PCI_FENCE_PHB);
+OPAL_CALL(opal_pci_reinit,			OPAL_PCI_REINIT);
+OPAL_CALL(opal_pci_mask_pe_error,		OPAL_PCI_MASK_PE_ERROR);
+OPAL_CALL(opal_set_slot_led_status,		OPAL_SET_SLOT_LED_STATUS);
+OPAL_CALL(opal_get_epow_status,			OPAL_GET_EPOW_STATUS);
+OPAL_CALL(opal_set_system_attention_led,	OPAL_SET_SYSTEM_ATTENTION_LED);
+OPAL_CALL(opal_pci_msi_eoi,			OPAL_PCI_MSI_EOI);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
new file mode 100644
index 00000000..06620ea3
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -0,0 +1,361 @@
+/*
+ * PowerNV OPAL high level interfaces
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/types.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <asm/opal.h>
+#include <asm/firmware.h>
+
+#include "powernv.h"
+
+struct opal {
+	u64 base;
+	u64 entry;
+} opal;
+
+static struct device_node *opal_node;
+static DEFINE_SPINLOCK(opal_write_lock);
+extern u64 opal_mc_secondary_handler[];
+static unsigned int *opal_irqs;
+static unsigned int opal_irq_count;
+
+int __init early_init_dt_scan_opal(unsigned long node,
+				   const char *uname, int depth, void *data)
+{
+	const void *basep, *entryp, *sizep;
+	int basesz, entrysz, runtimesz;
+
+	if (depth != 1 || strcmp(uname, "ibm,opal") != 0)
+		return 0;
+
+	basep  = of_get_flat_dt_prop(node, "opal-base-address", &basesz);
+	entryp = of_get_flat_dt_prop(node, "opal-entry-address", &entrysz);
+
+	if (!basep || !entryp)
+		return 1;
+
+	opal.base = of_read_number(basep, basesz/4);
+	opal.entry = of_read_number(entryp, entrysz/4);
+
+	pr_debug("OPAL Base  = 0x%llx (basep=%p basesz=%d)\n",
+		 opal.base, basep, basesz);
+	pr_debug("OPAL Entry = 0x%llx (sizep=%p runtimesz=%d)\n",
+		 opal.size, sizep, runtimesz);
+
+	powerpc_firmware_features |= FW_FEATURE_OPAL;
+	if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
+		powerpc_firmware_features |= FW_FEATURE_OPALv2;
+		powerpc_firmware_features |= FW_FEATURE_OPALv3;
+		printk("OPAL V3 detected !\n");
+	} else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
+		powerpc_firmware_features |= FW_FEATURE_OPALv2;
+		printk("OPAL V2 detected !\n");
+	} else {
+		printk("OPAL V1 detected !\n");
+	}
+
+	return 1;
+}
+
+static int __init opal_register_exception_handlers(void)
+{
+	u64 glue;
+
+	if (!(powerpc_firmware_features & FW_FEATURE_OPAL))
+		return -ENODEV;
+
+	/* Hookup some exception handlers. We use the fwnmi area at 0x7000
+	 * to provide the glue space to OPAL
+	 */
+	glue = 0x7000;
+	opal_register_exception_handler(OPAL_MACHINE_CHECK_HANDLER,
+					__pa(opal_mc_secondary_handler[0]),
+					glue);
+	glue += 128;
+	opal_register_exception_handler(OPAL_HYPERVISOR_MAINTENANCE_HANDLER,
+					0, glue);
+	glue += 128;
+	opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue);
+
+	return 0;
+}
+
+early_initcall(opal_register_exception_handlers);
+
+int opal_get_chars(uint32_t vtermno, char *buf, int count)
+{
+	s64 len, rc;
+	u64 evt;
+
+	if (!opal.entry)
+		return -ENODEV;
+	opal_poll_events(&evt);
+	if ((evt & OPAL_EVENT_CONSOLE_INPUT) == 0)
+		return 0;
+	len = cpu_to_be64(count);
+	rc = opal_console_read(vtermno, &len, buf);
+	if (rc == OPAL_SUCCESS)
+		return len;
+	return 0;
+}
+
+int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
+{
+	int written = 0;
+	s64 len, rc;
+	unsigned long flags;
+	u64 evt;
+
+	if (!opal.entry)
+		return -ENODEV;
+
+	/* We want put_chars to be atomic to avoid mangling of hvsi
+	 * packets. To do that, we first test for room and return
+	 * -EAGAIN if there isn't enough.
+	 *
+	 * Unfortunately, opal_console_write_buffer_space() doesn't
+	 * appear to work on opal v1, so we just assume there is
+	 * enough room and be done with it
+	 */
+	spin_lock_irqsave(&opal_write_lock, flags);
+	if (firmware_has_feature(FW_FEATURE_OPALv2)) {
+		rc = opal_console_write_buffer_space(vtermno, &len);
+		if (rc || len < total_len) {
+			spin_unlock_irqrestore(&opal_write_lock, flags);
+			/* Closed -> drop characters */
+			if (rc)
+				return total_len;
+			opal_poll_events(&evt);
+			return -EAGAIN;
+		}
+	}
+
+	/* We still try to handle partial completions, though they
+	 * should no longer happen.
+	 */
+	rc = OPAL_BUSY;
+	while(total_len > 0 && (rc == OPAL_BUSY ||
+				rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) {
+		len = total_len;
+		rc = opal_console_write(vtermno, &len, data);
+
+		/* Closed or other error drop */
+		if (rc != OPAL_SUCCESS && rc != OPAL_BUSY &&
+		    rc != OPAL_BUSY_EVENT) {
+			written = total_len;
+			break;
+		}
+		if (rc == OPAL_SUCCESS) {
+			total_len -= len;
+			data += len;
+			written += len;
+		}
+		/* This is a bit nasty but we need that for the console to
+		 * flush when there aren't any interrupts. We will clean
+		 * things a bit later to limit that to synchronous path
+		 * such as the kernel console and xmon/udbg
+		 */
+		do
+			opal_poll_events(&evt);
+		while(rc == OPAL_SUCCESS && (evt & OPAL_EVENT_CONSOLE_OUTPUT));
+	}
+	spin_unlock_irqrestore(&opal_write_lock, flags);
+	return written;
+}
+
+int opal_machine_check(struct pt_regs *regs)
+{
+	struct opal_machine_check_event *opal_evt = get_paca()->opal_mc_evt;
+	struct opal_machine_check_event evt;
+	const char *level, *sevstr, *subtype;
+	static const char *opal_mc_ue_types[] = {
+		"Indeterminate",
+		"Instruction fetch",
+		"Page table walk ifetch",
+		"Load/Store",
+		"Page table walk Load/Store",
+	};
+	static const char *opal_mc_slb_types[] = {
+		"Indeterminate",
+		"Parity",
+		"Multihit",
+	};
+	static const char *opal_mc_erat_types[] = {
+		"Indeterminate",
+		"Parity",
+		"Multihit",
+	};
+	static const char *opal_mc_tlb_types[] = {
+		"Indeterminate",
+		"Parity",
+		"Multihit",
+	};
+
+	/* Copy the event structure and release the original */
+	evt = *opal_evt;
+	opal_evt->in_use = 0;
+
+	/* Print things out */
+	if (evt.version != OpalMCE_V1) {
+		pr_err("Machine Check Exception, Unknown event version %d !\n",
+		       evt.version);
+		return 0;
+	}
+	switch(evt.severity) {
+	case OpalMCE_SEV_NO_ERROR:
+		level = KERN_INFO;
+		sevstr = "Harmless";
+		break;
+	case OpalMCE_SEV_WARNING:
+		level = KERN_WARNING;
+		sevstr = "";
+		break;
+	case OpalMCE_SEV_ERROR_SYNC:
+		level = KERN_ERR;
+		sevstr = "Severe";
+		break;
+	case OpalMCE_SEV_FATAL:
+	default:
+		level = KERN_ERR;
+		sevstr = "Fatal";
+		break;
+	}
+
+	printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
+	       evt.disposition == OpalMCE_DISPOSITION_RECOVERED ?
+	       "Recovered" : "[Not recovered");
+	printk("%s  Initiator: %s\n", level,
+	       evt.initiator == OpalMCE_INITIATOR_CPU ? "CPU" : "Unknown");
+	switch(evt.error_type) {
+	case OpalMCE_ERROR_TYPE_UE:
+		subtype = evt.u.ue_error.ue_error_type <
+			ARRAY_SIZE(opal_mc_ue_types) ?
+			opal_mc_ue_types[evt.u.ue_error.ue_error_type]
+			: "Unknown";
+		printk("%s  Error type: UE [%s]\n", level, subtype);
+		if (evt.u.ue_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt.u.ue_error.effective_address);
+		if (evt.u.ue_error.physical_address_provided)
+			printk("%s      Physial address: %016llx\n",
+			       level, evt.u.ue_error.physical_address);
+		break;
+	case OpalMCE_ERROR_TYPE_SLB:
+		subtype = evt.u.slb_error.slb_error_type <
+			ARRAY_SIZE(opal_mc_slb_types) ?
+			opal_mc_slb_types[evt.u.slb_error.slb_error_type]
+			: "Unknown";
+		printk("%s  Error type: SLB [%s]\n", level, subtype);
+		if (evt.u.slb_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt.u.slb_error.effective_address);
+		break;
+	case OpalMCE_ERROR_TYPE_ERAT:
+		subtype = evt.u.erat_error.erat_error_type <
+			ARRAY_SIZE(opal_mc_erat_types) ?
+			opal_mc_erat_types[evt.u.erat_error.erat_error_type]
+			: "Unknown";
+		printk("%s  Error type: ERAT [%s]\n", level, subtype);
+		if (evt.u.erat_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt.u.erat_error.effective_address);
+		break;
+	case OpalMCE_ERROR_TYPE_TLB:
+		subtype = evt.u.tlb_error.tlb_error_type <
+			ARRAY_SIZE(opal_mc_tlb_types) ?
+			opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type]
+			: "Unknown";
+		printk("%s  Error type: TLB [%s]\n", level, subtype);
+		if (evt.u.tlb_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt.u.tlb_error.effective_address);
+		break;
+	default:
+	case OpalMCE_ERROR_TYPE_UNKNOWN:
+		printk("%s  Error type: Unknown\n", level);
+		break;
+	}
+	return evt.severity == OpalMCE_SEV_FATAL ? 0 : 1;
+}
+
+static irqreturn_t opal_interrupt(int irq, void *data)
+{
+	uint64_t events;
+
+	opal_handle_interrupt(virq_to_hw(irq), &events);
+
+	/* XXX TODO: Do something with the events */
+
+	return IRQ_HANDLED;
+}
+
+static int __init opal_init(void)
+{
+	struct device_node *np, *consoles;
+	const u32 *irqs;
+	int rc, i, irqlen;
+
+	opal_node = of_find_node_by_path("/ibm,opal");
+	if (!opal_node) {
+		pr_warn("opal: Node not found\n");
+		return -ENODEV;
+	}
+	if (firmware_has_feature(FW_FEATURE_OPALv2))
+		consoles = of_find_node_by_path("/ibm,opal/consoles");
+	else
+		consoles = of_node_get(opal_node);
+
+	/* Register serial ports */
+	for_each_child_of_node(consoles, np) {
+		if (strcmp(np->name, "serial"))
+			continue;
+		of_platform_device_create(np, NULL, NULL);
+	}
+	of_node_put(consoles);
+
+	/* Find all OPAL interrupts and request them */
+	irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
+	pr_debug("opal: Found %d interrupts reserved for OPAL\n",
+		 irqs ? (irqlen / 4) : 0);
+	opal_irq_count = irqlen / 4;
+	opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL);
+	for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) {
+		unsigned int hwirq = be32_to_cpup(irqs);
+		unsigned int irq = irq_create_mapping(NULL, hwirq);
+		if (irq == NO_IRQ) {
+			pr_warning("opal: Failed to map irq 0x%x\n", hwirq);
+			continue;
+		}
+		rc = request_irq(irq, opal_interrupt, 0, "opal", NULL);
+		if (rc)
+			pr_warning("opal: Error %d requesting irq %d"
+				   " (0x%x)\n", rc, irq, hwirq);
+		opal_irqs[i] = irq;
+	}
+	return 0;
+}
+subsys_initcall(opal_init);
+
+void opal_shutdown(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < opal_irq_count; i++) {
+		if (opal_irqs[i])
+			free_irq(opal_irqs[i], 0);
+		opal_irqs[i] = 0;
+	}
+}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
new file mode 100644
index 00000000..b2bbb79b
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -0,0 +1,1270 @@
+/*
+ * Support PCI/PCIe on PowerNV platforms
+ *
+ * Copyright 2011 Benjamin Herrenschmidt, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/msi.h>
+
+#include <asm/sections.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/msi_bitmap.h>
+#include <asm/ppc-pci.h>
+#include <asm/opal.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+#include <asm/xics.h>
+
+#include "powernv.h"
+#include "pci.h"
+
+#define define_pe_printk_level(func, kern_level)		\
+static int func(const struct pnv_ioda_pe *pe, const char *fmt, ...)	\
+{								\
+	struct va_format vaf;					\
+	va_list args;						\
+	char pfix[32];						\
+	int r;							\
+								\
+	va_start(args, fmt);					\
+								\
+	vaf.fmt = fmt;						\
+	vaf.va = &args;						\
+								\
+	if (pe->pdev)						\
+		strlcpy(pfix, dev_name(&pe->pdev->dev),		\
+			sizeof(pfix));				\
+	else							\
+		sprintf(pfix, "%04x:%02x     ",			\
+			pci_domain_nr(pe->pbus),		\
+			pe->pbus->number);			\
+	r = printk(kern_level "pci %s: [PE# %.3d] %pV",		\
+		   pfix, pe->pe_number, &vaf);			\
+								\
+	va_end(args);						\
+								\
+	return r;						\
+}								\
+
+define_pe_printk_level(pe_err, KERN_ERR);
+define_pe_printk_level(pe_warn, KERN_WARNING);
+define_pe_printk_level(pe_info, KERN_INFO);
+
+static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
+{
+	unsigned long pe;
+
+	do {
+		pe = find_next_zero_bit(phb->ioda.pe_alloc,
+					phb->ioda.total_pe, 0);
+		if (pe >= phb->ioda.total_pe)
+			return IODA_INVALID_PE;
+	} while(test_and_set_bit(pe, phb->ioda.pe_alloc));
+
+	phb->ioda.pe_array[pe].phb = phb;
+	phb->ioda.pe_array[pe].pe_number = pe;
+	return pe;
+}
+
+static void pnv_ioda_free_pe(struct pnv_phb *phb, int pe)
+{
+	WARN_ON(phb->ioda.pe_array[pe].pdev);
+
+	memset(&phb->ioda.pe_array[pe], 0, sizeof(struct pnv_ioda_pe));
+	clear_bit(pe, phb->ioda.pe_alloc);
+}
+
+/* Currently those 2 are only used when MSIs are enabled, this will change
+ * but in the meantime, we need to protect them to avoid warnings
+ */
+#ifdef CONFIG_PCI_MSI
+static struct pnv_ioda_pe *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;
+	struct pci_dn *pdn = pci_get_pdn(dev);
+
+	if (!pdn)
+		return NULL;
+	if (pdn->pe_number == IODA_INVALID_PE)
+		return NULL;
+	return &phb->ioda.pe_array[pdn->pe_number];
+}
+#endif /* CONFIG_PCI_MSI */
+
+static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
+{
+	struct pci_dev *parent;
+	uint8_t bcomp, dcomp, fcomp;
+	long rc, rid_end, rid;
+
+	/* Bus validation ? */
+	if (pe->pbus) {
+		int count;
+
+		dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER;
+		fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
+		parent = pe->pbus->self;
+		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;
+		case  4: bcomp = OpalPciBus6Bits;	break;
+		case  8: bcomp = OpalPciBus5Bits;	break;
+		case 16: bcomp = OpalPciBus4Bits;	break;
+		case 32: bcomp = OpalPciBus3Bits;	break;
+		default:
+			pr_err("%s: Number of subordinate busses %d"
+			       " unsupported\n",
+			       pci_name(pe->pbus->self), count);
+			/* Do an exact match only */
+			bcomp = OpalPciBusAll;
+		}
+		rid_end = pe->rid + (count << 8);
+	} else {
+		parent = pe->pdev->bus->self;
+		bcomp = OpalPciBusAll;
+		dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER;
+		fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER;
+		rid_end = pe->rid + 1;
+	}
+
+	/*
+	 * Associate PE in PELT. We need add the PE into the
+	 * corresponding PELT-V as well. Otherwise, the error
+	 * originated from the PE might contribute to other
+	 * PEs.
+	 */
+	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
+			     bcomp, dcomp, fcomp, OPAL_MAP_PE);
+	if (rc) {
+		pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc);
+		return -ENXIO;
+	}
+
+	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
+				pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
+	if (rc)
+		pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc);
+	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
+				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+
+	/* Add to all parents PELT-V */
+	while (parent) {
+		struct pci_dn *pdn = pci_get_pdn(parent);
+		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
+			rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
+						pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
+			/* XXX What to do in case of error ? */
+		}
+		parent = parent->bus->self;
+	}
+	/* Setup reverse map */
+	for (rid = pe->rid; rid < rid_end; rid++)
+		phb->ioda.pe_rmap[rid] = pe->pe_number;
+
+	/* Setup one MVTs on IODA1 */
+	if (phb->type == PNV_PHB_IODA1) {
+		pe->mve_number = pe->pe_number;
+		rc = opal_pci_set_mve(phb->opal_id, pe->mve_number,
+				      pe->pe_number);
+		if (rc) {
+			pe_err(pe, "OPAL error %ld setting up MVE %d\n",
+			       rc, pe->mve_number);
+			pe->mve_number = -1;
+		} else {
+			rc = opal_pci_set_mve_enable(phb->opal_id,
+						     pe->mve_number, OPAL_ENABLE_MVE);
+			if (rc) {
+				pe_err(pe, "OPAL error %ld enabling MVE %d\n",
+				       rc, pe->mve_number);
+				pe->mve_number = -1;
+			}
+		}
+	} else if (phb->type == PNV_PHB_IODA2)
+		pe->mve_number = 0;
+
+	return 0;
+}
+
+static void pnv_ioda_link_pe_by_weight(struct pnv_phb *phb,
+				       struct pnv_ioda_pe *pe)
+{
+	struct pnv_ioda_pe *lpe;
+
+	list_for_each_entry(lpe, &phb->ioda.pe_dma_list, dma_link) {
+		if (lpe->dma_weight < pe->dma_weight) {
+			list_add_tail(&pe->dma_link, &lpe->dma_link);
+			return;
+		}
+	}
+	list_add_tail(&pe->dma_link, &phb->ioda.pe_dma_list);
+}
+
+static unsigned int pnv_ioda_dma_weight(struct pci_dev *dev)
+{
+	/* This is quite simplistic. The "base" weight of a device
+	 * is 10. 0 means no DMA is to be accounted for it.
+	 */
+
+	/* If it's a bridge, no DMA */
+	if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL)
+		return 0;
+
+	/* Reduce the weight of slow USB controllers */
+	if (dev->class == PCI_CLASS_SERIAL_USB_UHCI ||
+	    dev->class == PCI_CLASS_SERIAL_USB_OHCI ||
+	    dev->class == PCI_CLASS_SERIAL_USB_EHCI)
+		return 3;
+
+	/* Increase the weight of RAID (includes Obsidian) */
+	if ((dev->class >> 8) == PCI_CLASS_STORAGE_RAID)
+		return 15;
+
+	/* Default */
+	return 10;
+}
+
+#if 0
+static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(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 = pci_get_pdn(dev);
+	struct pnv_ioda_pe *pe;
+	int pe_num;
+
+	if (!pdn) {
+		pr_err("%s: Device tree node not associated properly\n",
+			   pci_name(dev));
+		return NULL;
+	}
+	if (pdn->pe_number != IODA_INVALID_PE)
+		return NULL;
+
+	/* PE#0 has been pre-set */
+	if (dev->bus->number == 0)
+		pe_num = 0;
+	else
+		pe_num = pnv_ioda_alloc_pe(phb);
+	if (pe_num == IODA_INVALID_PE) {
+		pr_warning("%s: Not enough PE# available, disabling device\n",
+			   pci_name(dev));
+		return NULL;
+	}
+
+	/* NOTE: We get only one ref to the pci_dev for the pdn, not for the
+	 * pointer in the PE data structure, both should be destroyed at the
+	 * same time. However, this needs to be looked at more closely again
+	 * once we actually start removing things (Hotplug, SR-IOV, ...)
+	 *
+	 * At some point we want to remove the PDN completely anyways
+	 */
+	pe = &phb->ioda.pe_array[pe_num];
+	pci_dev_get(dev);
+	pdn->pcidev = dev;
+	pdn->pe_number = pe_num;
+	pe->pdev = dev;
+	pe->pbus = NULL;
+	pe->tce32_seg = -1;
+	pe->mve_number = -1;
+	pe->rid = dev->bus->number << 8 | pdn->devfn;
+
+	pe_info(pe, "Associated device to PE\n");
+
+	if (pnv_ioda_configure_pe(phb, pe)) {
+		/* XXX What do we do here ? */
+		if (pe_num)
+			pnv_ioda_free_pe(phb, pe_num);
+		pdn->pe_number = IODA_INVALID_PE;
+		pe->pdev = NULL;
+		pci_dev_put(dev);
+		return NULL;
+	}
+
+	/* Assign a DMA weight to the device */
+	pe->dma_weight = pnv_ioda_dma_weight(dev);
+	if (pe->dma_weight != 0) {
+		phb->ioda.dma_weight += pe->dma_weight;
+		phb->ioda.dma_pe_count++;
+	}
+
+	/* Link the PE */
+	pnv_ioda_link_pe_by_weight(phb, pe);
+
+	return pe;
+}
+#endif /* Useful for SRIOV case */
+
+static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		struct pci_dn *pdn = pci_get_pdn(dev);
+
+		if (pdn == NULL) {
+			pr_warn("%s: No device node associated with device !\n",
+				pci_name(dev));
+			continue;
+		}
+		pci_dev_get(dev);
+		pdn->pcidev = dev;
+		pdn->pe_number = pe->pe_number;
+		pe->dma_weight += pnv_ioda_dma_weight(dev);
+		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
+			pnv_ioda_setup_same_PE(dev->subordinate, pe);
+	}
+}
+
+/*
+ * 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 pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pnv_ioda_pe *pe;
+	int pe_num;
+
+	pe_num = pnv_ioda_alloc_pe(phb);
+	if (pe_num == IODA_INVALID_PE) {
+		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];
+	pe->flags = (all ? PNV_IODA_PE_BUS_ALL : PNV_IODA_PE_BUS);
+	pe->pbus = bus;
+	pe->pdev = NULL;
+	pe->tce32_seg = -1;
+	pe->mve_number = -1;
+	pe->rid = bus->busn_res.start << 8;
+	pe->dma_weight = 0;
+
+	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 ? */
+		if (pe_num)
+			pnv_ioda_free_pe(phb, pe_num);
+		pe->pbus = NULL;
+		return;
+	}
+
+	/* 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
+	 */
+	if (pe->dma_weight != 0) {
+		phb->ioda.dma_weight += pe->dma_weight;
+		phb->ioda.dma_pe_count++;
+	}
+
+	/* Link the PE */
+	pnv_ioda_link_pe_by_weight(phb, pe);
+}
+
+static void pnv_ioda_setup_PEs(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	pnv_ioda_setup_bus_PE(bus, 0);
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		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 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);
+	}
+}
+
+static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	struct pnv_ioda_pe *pe;
+
+	/*
+	 * The function can be called while the PE#
+	 * hasn't been assigned. Do nothing for the
+	 * case.
+	 */
+	if (!pdn || pdn->pe_number == IODA_INVALID_PE)
+		return;
+
+	pe = &phb->ioda.pe_array[pdn->pe_number];
+	set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+}
+
+static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		set_iommu_table_base(&dev->dev, &pe->tce32_table);
+		if (dev->subordinate)
+			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+	}
+}
+
+static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
+					 u64 *startp, u64 *endp)
+{
+	u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index;
+	unsigned long start, end, inc;
+
+	start = __pa(startp);
+	end = __pa(endp);
+
+	/* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */
+	if (tbl->it_busno) {
+		start <<= 12;
+		end <<= 12;
+		inc = 128 << 12;
+		start |= tbl->it_busno;
+		end |= tbl->it_busno;
+	} else if (tbl->it_type & TCE_PCI_SWINV_PAIR) {
+		/* p7ioc-style invalidation, 2 TCEs per write */
+		start |= (1ull << 63);
+		end |= (1ull << 63);
+		inc = 16;
+        } else {
+		/* Default (older HW) */
+                inc = 128;
+	}
+
+        end |= inc - 1;	/* round up end to be different than start */
+
+        mb(); /* Ensure above stores are visible */
+        while (start <= end) {
+                __raw_writeq(start, invalidate);
+                start += inc;
+        }
+
+	/*
+	 * The iommu layer will do another mb() for us on build()
+	 * and we don't care on free()
+	 */
+}
+
+static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
+					 struct iommu_table *tbl,
+					 u64 *startp, u64 *endp)
+{
+	unsigned long start, end, inc;
+	u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index;
+
+	/* We'll invalidate DMA address in PE scope */
+	start = 0x2ul << 60;
+	start |= (pe->pe_number & 0xFF);
+	end = start;
+
+	/* Figure out the start, end and step */
+	inc = tbl->it_offset + (((u64)startp - tbl->it_base) / sizeof(u64));
+	start |= (inc << 12);
+	inc = tbl->it_offset + (((u64)endp - tbl->it_base) / sizeof(u64));
+	end |= (inc << 12);
+	inc = (0x1ul << 12);
+	mb();
+
+	while (start <= end) {
+		__raw_writeq(start, invalidate);
+		start += inc;
+	}
+}
+
+void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
+				 u64 *startp, u64 *endp)
+{
+	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
+					      tce32_table);
+	struct pnv_phb *phb = pe->phb;
+
+	if (phb->type == PNV_PHB_IODA1)
+		pnv_pci_ioda1_tce_invalidate(tbl, startp, endp);
+	else
+		pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp);
+}
+
+static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
+				      struct pnv_ioda_pe *pe, unsigned int base,
+				      unsigned int segs)
+{
+
+	struct page *tce_mem = NULL;
+	const __be64 *swinvp;
+	struct iommu_table *tbl;
+	unsigned int i;
+	int64_t rc;
+	void *addr;
+
+	/* 256M DMA window, 4K TCE pages, 8 bytes TCE */
+#define TCE32_TABLE_SIZE	((0x10000000 / 0x1000) * 8)
+
+	/* XXX FIXME: Handle 64-bit only DMA devices */
+	/* XXX FIXME: Provide 64-bit DMA facilities & non-4K TCE tables etc.. */
+	/* XXX FIXME: Allocate multi-level tables on PHB3 */
+
+	/* We shouldn't already have a 32-bit DMA associated */
+	if (WARN_ON(pe->tce32_seg >= 0))
+		return;
+
+	/* Grab a 32-bit TCE table */
+	pe->tce32_seg = base;
+	pe_info(pe, " Setting up 32-bit TCE table at %08x..%08x\n",
+		(base << 28), ((base + segs) << 28) - 1);
+
+	/* XXX Currently, we allocate one big contiguous table for the
+	 * TCEs. We only really need one chunk per 256M of TCE space
+	 * (ie per segment) but that's an optimization for later, it
+	 * requires some added smarts with our get/put_tce implementation
+	 */
+	tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL,
+				   get_order(TCE32_TABLE_SIZE * segs));
+	if (!tce_mem) {
+		pe_err(pe, " Failed to allocate a 32-bit TCE memory\n");
+		goto fail;
+	}
+	addr = page_address(tce_mem);
+	memset(addr, 0, TCE32_TABLE_SIZE * segs);
+
+	/* Configure HW */
+	for (i = 0; i < segs; i++) {
+		rc = opal_pci_map_pe_dma_window(phb->opal_id,
+					      pe->pe_number,
+					      base + i, 1,
+					      __pa(addr) + TCE32_TABLE_SIZE * i,
+					      TCE32_TABLE_SIZE, 0x1000);
+		if (rc) {
+			pe_err(pe, " Failed to configure 32-bit TCE table,"
+			       " err %ld\n", rc);
+			goto fail;
+		}
+	}
+
+	/* Setup linux iommu table */
+	tbl = &pe->tce32_table;
+	pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
+				  base << 28);
+
+	/* OPAL variant of P7IOC SW invalidated TCEs */
+	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
+	if (swinvp) {
+		/* We need a couple more fields -- an address and a data
+		 * to or.  Since the bus is only printed out on table free
+		 * errors, and on the first pass the data will be a relative
+		 * bus number, print that out instead.
+		 */
+		tbl->it_busno = 0;
+		tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8);
+		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE |
+			       TCE_PCI_SWINV_PAIR;
+	}
+	iommu_init_table(tbl, phb->hose->node);
+
+	if (pe->pdev)
+		set_iommu_table_base(&pe->pdev->dev, tbl);
+	else
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+
+	return;
+ fail:
+	/* XXX Failure: Try to fallback to 64-bit only ? */
+	if (pe->tce32_seg >= 0)
+		pe->tce32_seg = -1;
+	if (tce_mem)
+		__free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
+}
+
+static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
+				       struct pnv_ioda_pe *pe)
+{
+	struct page *tce_mem = NULL;
+	void *addr;
+	const __be64 *swinvp;
+	struct iommu_table *tbl;
+	unsigned int tce_table_size, end;
+	int64_t rc;
+
+	/* We shouldn't already have a 32-bit DMA associated */
+	if (WARN_ON(pe->tce32_seg >= 0))
+		return;
+
+	/* The PE will reserve all possible 32-bits space */
+	pe->tce32_seg = 0;
+	end = (1 << ilog2(phb->ioda.m32_pci_base));
+	tce_table_size = (end / 0x1000) * 8;
+	pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n",
+		end);
+
+	/* Allocate TCE table */
+	tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL,
+				   get_order(tce_table_size));
+	if (!tce_mem) {
+		pe_err(pe, "Failed to allocate a 32-bit TCE memory\n");
+		goto fail;
+	}
+	addr = page_address(tce_mem);
+	memset(addr, 0, tce_table_size);
+
+	/*
+	 * Map TCE table through TVT. The TVE index is the PE number
+	 * shifted by 1 bit for 32-bits DMA space.
+	 */
+	rc = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
+					pe->pe_number << 1, 1, __pa(addr),
+					tce_table_size, 0x1000);
+	if (rc) {
+		pe_err(pe, "Failed to configure 32-bit TCE table,"
+		       " err %ld\n", rc);
+		goto fail;
+	}
+
+	/* Setup linux iommu table */
+	tbl = &pe->tce32_table;
+	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0);
+
+	/* OPAL variant of PHB3 invalidated TCEs */
+	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
+	if (swinvp) {
+		/* We need a couple more fields -- an address and a data
+		 * to or.  Since the bus is only printed out on table free
+		 * errors, and on the first pass the data will be a relative
+		 * bus number, print that out instead.
+		 */
+		tbl->it_busno = 0;
+		tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8);
+		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
+	}
+	iommu_init_table(tbl, phb->hose->node);
+
+	if (pe->pdev)
+		set_iommu_table_base(&pe->pdev->dev, tbl);
+	else
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+
+	return;
+fail:
+	if (pe->tce32_seg >= 0)
+		pe->tce32_seg = -1;
+	if (tce_mem)
+		__free_pages(tce_mem, get_order(tce_table_size));
+}
+
+static void pnv_ioda_setup_dma(struct pnv_phb *phb)
+{
+	struct pci_controller *hose = phb->hose;
+	unsigned int residual, remaining, segs, tw, base;
+	struct pnv_ioda_pe *pe;
+
+	/* If we have more PE# than segments available, hand out one
+	 * per PE until we run out and let the rest fail. If not,
+	 * then we assign at least one segment per PE, plus more based
+	 * on the amount of devices under that PE
+	 */
+	if (phb->ioda.dma_pe_count > phb->ioda.tce32_count)
+		residual = 0;
+	else
+		residual = phb->ioda.tce32_count -
+			phb->ioda.dma_pe_count;
+
+	pr_info("PCI: Domain %04x has %ld available 32-bit DMA segments\n",
+		hose->global_number, phb->ioda.tce32_count);
+	pr_info("PCI: %d PE# for a total weight of %d\n",
+		phb->ioda.dma_pe_count, phb->ioda.dma_weight);
+
+	/* Walk our PE list and configure their DMA segments, hand them
+	 * out one base segment plus any residual segments based on
+	 * weight
+	 */
+	remaining = phb->ioda.tce32_count;
+	tw = phb->ioda.dma_weight;
+	base = 0;
+	list_for_each_entry(pe, &phb->ioda.pe_dma_list, dma_link) {
+		if (!pe->dma_weight)
+			continue;
+		if (!remaining) {
+			pe_warn(pe, "No DMA32 resources available\n");
+			continue;
+		}
+		segs = 1;
+		if (residual) {
+			segs += ((pe->dma_weight * residual)  + (tw / 2)) / tw;
+			if (segs > remaining)
+				segs = remaining;
+		}
+
+		/*
+		 * For IODA2 compliant PHB3, we needn't care about the weight.
+		 * The all available 32-bits DMA space will be assigned to
+		 * the specific PE.
+		 */
+		if (phb->type == PNV_PHB_IODA1) {
+			pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n",
+				pe->dma_weight, segs);
+			pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs);
+		} else {
+			pe_info(pe, "Assign DMA32 space\n");
+			segs = 0;
+			pnv_pci_ioda2_setup_dma_pe(phb, pe);
+		}
+
+		remaining -= segs;
+		base += segs;
+	}
+}
+
+#ifdef CONFIG_PCI_MSI
+static void pnv_ioda2_msi_eoi(struct irq_data *d)
+{
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+	struct irq_chip *chip = irq_data_get_irq_chip(d);
+	struct pnv_phb *phb = container_of(chip, struct pnv_phb,
+					   ioda.irq_chip);
+	int64_t rc;
+
+	rc = opal_pci_msi_eoi(phb->opal_id, hw_irq);
+	WARN_ON_ONCE(rc);
+
+	icp_native_eoi(d);
+}
+
+static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
+				  unsigned int hwirq, unsigned int virq,
+				  unsigned int is_64, struct msi_msg *msg)
+{
+	struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
+	struct irq_data *idata;
+	struct irq_chip *ichip;
+	unsigned int xive_num = hwirq - phb->msi_base;
+	uint64_t addr64;
+	uint32_t addr32, data;
+	int rc;
+
+	/* No PE assigned ? bail out ... no MSI for you ! */
+	if (pe == NULL)
+		return -ENXIO;
+
+	/* Check if we have an MVE */
+	if (pe->mve_number < 0)
+		return -ENXIO;
+
+	/* Force 32-bit MSI on some broken devices */
+	if (dev->no_64bit_msi)
+		is_64 = 0;
+
+	/* Assign XIVE to PE */
+	rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
+	if (rc) {
+		pr_warn("%s: OPAL error %d setting XIVE %d PE\n",
+			pci_name(dev), rc, xive_num);
+		return -EIO;
+	}
+
+	if (is_64) {
+		rc = opal_get_msi_64(phb->opal_id, pe->mve_number, xive_num, 1,
+				     &addr64, &data);
+		if (rc) {
+			pr_warn("%s: OPAL error %d getting 64-bit MSI data\n",
+				pci_name(dev), rc);
+			return -EIO;
+		}
+		msg->address_hi = addr64 >> 32;
+		msg->address_lo = addr64 & 0xfffffffful;
+	} else {
+		rc = opal_get_msi_32(phb->opal_id, pe->mve_number, xive_num, 1,
+				     &addr32, &data);
+		if (rc) {
+			pr_warn("%s: OPAL error %d getting 32-bit MSI data\n",
+				pci_name(dev), rc);
+			return -EIO;
+		}
+		msg->address_hi = 0;
+		msg->address_lo = addr32;
+	}
+	msg->data = data;
+
+	/*
+	 * Change the IRQ chip for the MSI interrupts on PHB3.
+	 * The corresponding IRQ chip should be populated for
+	 * the first time.
+	 */
+	if (phb->type == PNV_PHB_IODA2) {
+		if (!phb->ioda.irq_chip_init) {
+			idata = irq_get_irq_data(virq);
+			ichip = irq_data_get_irq_chip(idata);
+			phb->ioda.irq_chip_init = 1;
+			phb->ioda.irq_chip = *ichip;
+			phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
+		}
+
+		irq_set_chip(virq, &phb->ioda.irq_chip);
+	}
+
+	pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d),"
+		 " address=%x_%08x data=%x PE# %d\n",
+		 pci_name(dev), is_64 ? "64" : "32", hwirq, xive_num,
+		 msg->address_hi, msg->address_lo, data, pe->pe_number);
+
+	return 0;
+}
+
+static void pnv_pci_init_ioda_msis(struct pnv_phb *phb)
+{
+	unsigned int count;
+	const __be32 *prop = of_get_property(phb->hose->dn,
+					     "ibm,opal-msi-ranges", NULL);
+	if (!prop) {
+		/* BML Fallback */
+		prop = of_get_property(phb->hose->dn, "msi-ranges", NULL);
+	}
+	if (!prop)
+		return;
+
+	phb->msi_base = be32_to_cpup(prop);
+	count = be32_to_cpup(prop + 1);
+	if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) {
+		pr_err("PCI %d: Failed to allocate MSI bitmap !\n",
+		       phb->hose->global_number);
+		return;
+	}
+
+	phb->msi_setup = pnv_pci_ioda_msi_setup;
+	phb->msi32_support = 1;
+	pr_info("  Allocated bitmap for %d MSIs (base IRQ 0x%x)\n",
+		count, phb->msi_base);
+}
+#else
+static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { }
+#endif /* CONFIG_PCI_MSI */
+
+/*
+ * 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 pnv_ioda_setup_pe_seg(struct pci_controller *hose,
+				  struct pnv_ioda_pe *pe)
+{
+	struct pnv_phb *phb = hose->private_data;
+	struct pci_bus_region region;
+	struct resource *res;
+	int i, index;
+	int rc;
+
+	/*
+	 * 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)));
+
+	pci_bus_for_each_resource(pe->pbus, res, i) {
+		if (!res || !res->flags ||
+		    res->start > res->end)
+			continue;
+
+		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) {
+			/* WARNING: Assumes M32 is mem region 0 in PHB. We need to
+			 * harden that algorithm when we start supporting M64
+			 */
+			region.start = res->start -
+				       hose->mem_offset[0] -
+				       phb->ioda.m32_pci_base;
+			region.end   = res->end -
+				       hose->mem_offset[0] -
+				       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++;
+			}
+		}
+	}
+}
+
+static void pnv_pci_ioda_setup_seg(void)
+{
+	struct pci_controller *tmp, *hose;
+	struct pnv_phb *phb;
+	struct pnv_ioda_pe *pe;
+
+	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 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 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.
+ * For now, we return I/O or M32 segment size for PE sensitive
+ * P2P bridges. Otherwise, the default values (4KiB for I/O,
+ * 1MiB for memory) will be returned.
+ *
+ * The current PCI bus might be put into one PE, which was
+ * create against the parent PCI bridge. For that case, we
+ * needn't enlarge the alignment so that we can save some
+ * resources.
+ */
+static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
+						unsigned long type)
+{
+	struct pci_dev *bridge;
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
+	int num_pci_bridges = 0;
+
+	bridge = bus->self;
+	while (bridge) {
+		if (pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE) {
+			num_pci_bridges++;
+			if (num_pci_bridges >= 2)
+				return 1;
+		}
+
+		bridge = bridge->bus->self;
+	}
+
+	/* We need support prefetchable memory window later */
+	if (type & IORESOURCE_MEM)
+		return phb->ioda.m32_segsize;
+
+	return phb->ioda.io_segsize;
+}
+
+/* Prevent enabling devices for which we couldn't properly
+ * assign a PE
+ */
+static int pnv_pci_enable_device_hook(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;
+
+	/* 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 = pci_get_pdn(dev);
+	if (!pdn || pdn->pe_number == IODA_INVALID_PE)
+		return -EINVAL;
+
+	return 0;
+}
+
+static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
+			       u32 devfn)
+{
+	return phb->ioda.pe_rmap[(bus->number << 8) | devfn];
+}
+
+static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
+{
+	opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET,
+		       OPAL_ASSERT_RESET);
+}
+
+void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
+{
+	struct pci_controller *hose;
+	static int primary = 1;
+	struct pnv_phb *phb;
+	unsigned long size, m32map_off, iomap_off, pemap_off;
+	const u64 *prop64;
+	const u32 *prop32;
+	u64 phb_id;
+	void *aux;
+	long rc;
+
+	pr_info(" Initializing IODA%d OPAL PHB %s\n", ioda_type, np->full_name);
+
+	prop64 = of_get_property(np, "ibm,opal-phbid", NULL);
+	if (!prop64) {
+		pr_err("  Missing \"ibm,opal-phbid\" property !\n");
+		return;
+	}
+	phb_id = be64_to_cpup(prop64);
+	pr_debug("  PHB-ID  : 0x%016llx\n", phb_id);
+
+	phb = alloc_bootmem(sizeof(struct pnv_phb));
+	if (phb) {
+		memset(phb, 0, sizeof(struct pnv_phb));
+		phb->hose = hose = pcibios_alloc_controller(np);
+	}
+	if (!phb || !phb->hose) {
+		pr_err("PCI: Failed to allocate PCI controller for %s\n",
+		       np->full_name);
+		return;
+	}
+
+	spin_lock_init(&phb->lock);
+	/* XXX Use device-tree */
+	hose->first_busno = 0;
+	hose->last_busno = 0xff;
+	hose->private_data = phb;
+	phb->opal_id = phb_id;
+	phb->type = ioda_type;
+
+	/* Detect specific models for error handling */
+	if (of_device_is_compatible(np, "ibm,p7ioc-pciex"))
+		phb->model = PNV_PHB_MODEL_P7IOC;
+	else if (of_device_is_compatible(np, "ibm,power8-pciex"))
+		phb->model = PNV_PHB_MODEL_PHB3;
+	else
+		phb->model = PNV_PHB_MODEL_UNKNOWN;
+
+	/* Parse 32-bit and IO ranges (if any) */
+	pci_process_bridge_OF_ranges(phb->hose, np, primary);
+	primary = 0;
+
+	/* Get registers */
+	phb->regs = of_iomap(np, 0);
+	if (phb->regs == NULL)
+		pr_err("  Failed to map registers !\n");
+
+	/* Initialize more IODA stuff */
+	prop32 = of_get_property(np, "ibm,opal-num-pes", NULL);
+	if (!prop32)
+		phb->ioda.total_pe = 1;
+	else
+		phb->ioda.total_pe = *prop32;
+
+	phb->ioda.m32_size = resource_size(&hose->mem_resources[0]);
+	/* FW Has already off top 64k of M32 space (MSI space) */
+	phb->ioda.m32_size += 0x10000;
+
+	phb->ioda.m32_segsize = phb->ioda.m32_size / phb->ioda.total_pe;
+	phb->ioda.m32_pci_base = hose->mem_resources[0].start - hose->mem_offset[0];
+	phb->ioda.io_size = hose->pci_io_size;
+	phb->ioda.io_segsize = phb->ioda.io_size / phb->ioda.total_pe;
+	phb->ioda.io_pci_base = 0; /* XXX calculate this ? */
+
+	/* Allocate aux data & arrays
+	 *
+	 * XXX TODO: Don't allocate io segmap on PHB3
+	 */
+	size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
+	m32map_off = size;
+	size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]);
+	iomap_off = size;
+	size += phb->ioda.total_pe * sizeof(phb->ioda.io_segmap[0]);
+	pemap_off = size;
+	size += phb->ioda.total_pe * sizeof(struct pnv_ioda_pe);
+	aux = alloc_bootmem(size);
+	memset(aux, 0, size);
+	phb->ioda.pe_alloc = aux;
+	phb->ioda.m32_segmap = aux + m32map_off;
+	phb->ioda.io_segmap = aux + iomap_off;
+	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 */
+	phb->ioda.tce32_count = phb->ioda.m32_pci_base >> 28;
+
+	/* Clear unusable m64 */
+	hose->mem_resources[1].flags = 0;
+	hose->mem_resources[1].start = 0;
+	hose->mem_resources[1].end = 0;
+	hose->mem_resources[2].flags = 0;
+	hose->mem_resources[2].start = 0;
+	hose->mem_resources[2].end = 0;
+
+#if 0 /* We should really do that ... */
+	rc = opal_pci_set_phb_mem_window(opal->phb_id,
+					 window_type,
+					 window_num,
+					 starting_real_address,
+					 starting_pci_address,
+					 segment_size);
+#endif
+
+	pr_info("  %d PE's M32: 0x%x [segment=0x%x] IO: 0x%x [segment=0x%x]\n",
+		phb->ioda.total_pe,
+		phb->ioda.m32_size, phb->ioda.m32_segsize,
+		phb->ioda.io_size, phb->ioda.io_segsize);
+
+	phb->hose->ops = &pnv_pci_ops;
+
+	/* Setup RID -> PE mapping function */
+	phb->bdfn_to_pe = pnv_ioda_bdfn_to_pe;
+
+	/* Setup TCEs */
+	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
+
+	/* Setup shutdown function for kexec */
+	phb->shutdown = pnv_pci_ioda_shutdown;
+
+	/* Setup MSI support */
+	pnv_pci_init_ioda_msis(phb);
+
+	/*
+	 * 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 = 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_REASSIGN_ALL_RSRC);
+
+	/* Reset IODA tables to a clean state */
+	rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET);
+	if (rc)
+		pr_warning("  OPAL Error %ld performing IODA table reset !\n", rc);
+
+	/*
+	 * On IODA1 map everything to PE#0, on IODA2 we assume the IODA reset
+	 * has cleared the RTT which has the same effect
+	 */
+	if (ioda_type == PNV_PHB_IODA1)
+		opal_pci_set_pe(phb_id, 0, 0, 7, 1, 1 , OPAL_MAP_PE);
+}
+
+void pnv_pci_init_ioda2_phb(struct device_node *np)
+{
+	pnv_pci_init_ioda_phb(np, PNV_PHB_IODA2);
+}
+
+void __init pnv_pci_init_ioda_hub(struct device_node *np)
+{
+	struct device_node *phbn;
+	const u64 *prop64;
+	u64 hub_id;
+
+	pr_info("Probing IODA IO-Hub %s\n", np->full_name);
+
+	prop64 = of_get_property(np, "ibm,opal-hubid", NULL);
+	if (!prop64) {
+		pr_err(" Missing \"ibm,opal-hubid\" property !\n");
+		return;
+	}
+	hub_id = be64_to_cpup(prop64);
+	pr_devel(" HUB-ID : 0x%016llx\n", hub_id);
+
+	/* Count child PHBs */
+	for_each_child_of_node(np, phbn) {
+		/* Look for IODA1 PHBs */
+		if (of_device_is_compatible(phbn, "ibm,ioda-phb"))
+			pnv_pci_init_ioda_phb(phbn, PNV_PHB_IODA1);
+	}
+}
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
new file mode 100644
index 00000000..92b37a01
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -0,0 +1,233 @@
+/*
+ * Support PCI/PCIe on PowerNV platforms
+ *
+ * Currently supports only P5IOC2
+ *
+ * Copyright 2011 Benjamin Herrenschmidt, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/msi.h>
+
+#include <asm/sections.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/msi_bitmap.h>
+#include <asm/ppc-pci.h>
+#include <asm/opal.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+
+#include "powernv.h"
+#include "pci.h"
+
+/* For now, use a fixed amount of TCE memory for each p5ioc2
+ * hub, 16M will do
+ */
+#define P5IOC2_TCE_MEMORY	0x01000000
+
+#ifdef CONFIG_PCI_MSI
+static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
+				    unsigned int hwirq, unsigned int virq,
+				    unsigned int is_64, struct msi_msg *msg)
+{
+	if (WARN_ON(!is_64))
+		return -ENXIO;
+	msg->data = hwirq - phb->msi_base;
+	msg->address_hi = 0x10000000;
+	msg->address_lo = 0;
+
+	return 0;
+}
+
+static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb)
+{
+	unsigned int count;
+	const __be32 *prop = of_get_property(phb->hose->dn,
+					     "ibm,opal-msi-ranges", NULL);
+	if (!prop)
+		return;
+
+	/* Don't do MSI's on p5ioc2 PCI-X are they are not properly
+	 * verified in HW
+	 */
+	if (of_device_is_compatible(phb->hose->dn, "ibm,p5ioc2-pcix"))
+		return;
+	phb->msi_base = be32_to_cpup(prop);
+	count = be32_to_cpup(prop + 1);
+	if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) {
+		pr_err("PCI %d: Failed to allocate MSI bitmap !\n",
+		       phb->hose->global_number);
+		return;
+	}
+	phb->msi_setup = pnv_pci_p5ioc2_msi_setup;
+	phb->msi32_support = 0;
+	pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n",
+		count, phb->msi_base);
+}
+#else
+static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { }
+#endif /* CONFIG_PCI_MSI */
+
+static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
+					 struct pci_dev *pdev)
+{
+	if (phb->p5ioc2.iommu_table.it_map == NULL)
+		iommu_init_table(&phb->p5ioc2.iommu_table, phb->hose->node);
+
+	set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table);
+}
+
+static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np,
+					   void *tce_mem, u64 tce_size)
+{
+	struct pnv_phb *phb;
+	const u64 *prop64;
+	u64 phb_id;
+	int64_t rc;
+	static int primary = 1;
+
+	pr_info(" Initializing p5ioc2 PHB %s\n", np->full_name);
+
+	prop64 = of_get_property(np, "ibm,opal-phbid", NULL);
+	if (!prop64) {
+		pr_err("  Missing \"ibm,opal-phbid\" property !\n");
+		return;
+	}
+	phb_id = be64_to_cpup(prop64);
+	pr_devel("  PHB-ID  : 0x%016llx\n", phb_id);
+	pr_devel("  TCE AT  : 0x%016lx\n", __pa(tce_mem));
+	pr_devel("  TCE SZ  : 0x%016llx\n", tce_size);
+
+	rc = opal_pci_set_phb_tce_memory(phb_id, __pa(tce_mem), tce_size);
+	if (rc != OPAL_SUCCESS) {
+		pr_err("  Failed to set TCE memory, OPAL error %lld\n", rc);
+		return;
+	}
+
+	phb = alloc_bootmem(sizeof(struct pnv_phb));
+	if (phb) {
+		memset(phb, 0, sizeof(struct pnv_phb));
+		phb->hose = pcibios_alloc_controller(np);
+	}
+	if (!phb || !phb->hose) {
+		pr_err("  Failed to allocate PCI controller\n");
+		return;
+	}
+
+	spin_lock_init(&phb->lock);
+	phb->hose->first_busno = 0;
+	phb->hose->last_busno = 0xff;
+	phb->hose->private_data = phb;
+	phb->opal_id = phb_id;
+	phb->type = PNV_PHB_P5IOC2;
+	phb->model = PNV_PHB_MODEL_P5IOC2;
+
+	phb->regs = of_iomap(np, 0);
+
+	if (phb->regs == NULL)
+		pr_err("  Failed to map registers !\n");
+	else {
+		pr_devel("  P_BUID     = 0x%08x\n", in_be32(phb->regs + 0x100));
+		pr_devel("  P_IOSZ     = 0x%08x\n", in_be32(phb->regs + 0x1b0));
+		pr_devel("  P_IO_ST    = 0x%08x\n", in_be32(phb->regs + 0x1e0));
+		pr_devel("  P_MEM1_H   = 0x%08x\n", in_be32(phb->regs + 0x1a0));
+		pr_devel("  P_MEM1_L   = 0x%08x\n", in_be32(phb->regs + 0x190));
+		pr_devel("  P_MSZ1_L   = 0x%08x\n", in_be32(phb->regs + 0x1c0));
+		pr_devel("  P_MEM_ST   = 0x%08x\n", in_be32(phb->regs + 0x1d0));
+		pr_devel("  P_MEM2_H   = 0x%08x\n", in_be32(phb->regs + 0x2c0));
+		pr_devel("  P_MEM2_L   = 0x%08x\n", in_be32(phb->regs + 0x2b0));
+		pr_devel("  P_MSZ2_H   = 0x%08x\n", in_be32(phb->regs + 0x2d0));
+		pr_devel("  P_MSZ2_L   = 0x%08x\n", in_be32(phb->regs + 0x2e0));
+	}
+
+	/* Interpret the "ranges" property */
+	/* This also maps the I/O region and sets isa_io/mem_base */
+	pci_process_bridge_OF_ranges(phb->hose, np, primary);
+	primary = 0;
+
+	phb->hose->ops = &pnv_pci_ops;
+
+	/* Setup MSI support */
+	pnv_pci_init_p5ioc2_msis(phb);
+
+	/* Setup TCEs */
+	phb->dma_dev_setup = pnv_pci_p5ioc2_dma_dev_setup;
+	pnv_pci_setup_iommu_table(&phb->p5ioc2.iommu_table,
+				  tce_mem, tce_size, 0);
+}
+
+void __init pnv_pci_init_p5ioc2_hub(struct device_node *np)
+{
+	struct device_node *phbn;
+	const u64 *prop64;
+	u64 hub_id;
+	void *tce_mem;
+	uint64_t tce_per_phb;
+	int64_t rc;
+	int phb_count = 0;
+
+	pr_info("Probing p5ioc2 IO-Hub %s\n", np->full_name);
+
+	prop64 = of_get_property(np, "ibm,opal-hubid", NULL);
+	if (!prop64) {
+		pr_err(" Missing \"ibm,opal-hubid\" property !\n");
+		return;
+	}
+	hub_id = be64_to_cpup(prop64);
+	pr_info(" HUB-ID : 0x%016llx\n", hub_id);
+
+	/* Currently allocate 16M of TCE memory for every Hub
+	 *
+	 * XXX TODO: Make it chip local if possible
+	 */
+	tce_mem = __alloc_bootmem(P5IOC2_TCE_MEMORY, P5IOC2_TCE_MEMORY,
+				  __pa(MAX_DMA_ADDRESS));
+	if (!tce_mem) {
+		pr_err(" Failed to allocate TCE Memory !\n");
+		return;
+	}
+	pr_debug(" TCE    : 0x%016lx..0x%016lx\n",
+		__pa(tce_mem), __pa(tce_mem) + P5IOC2_TCE_MEMORY - 1);
+	rc = opal_pci_set_hub_tce_memory(hub_id, __pa(tce_mem),
+					P5IOC2_TCE_MEMORY);
+	if (rc != OPAL_SUCCESS) {
+		pr_err(" Failed to allocate TCE memory, OPAL error %lld\n", rc);
+		return;
+	}
+
+	/* Count child PHBs */
+	for_each_child_of_node(np, phbn) {
+		if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
+		    of_device_is_compatible(phbn, "ibm,p5ioc2-pciex"))
+			phb_count++;
+	}
+
+	/* Calculate how much TCE space we can give per PHB */
+	tce_per_phb = __rounddown_pow_of_two(P5IOC2_TCE_MEMORY / phb_count);
+	pr_info(" Allocating %lld MB of TCE memory per PHB\n",
+		tce_per_phb >> 20);
+
+	/* Initialize PHBs */
+	for_each_child_of_node(np, phbn) {
+		if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
+		    of_device_is_compatible(phbn, "ibm,p5ioc2-pciex")) {
+			pnv_pci_init_p5ioc2_phb(phbn, tce_mem, tce_per_phb);
+			tce_mem += tce_per_phb;
+		}
+	}
+}
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
new file mode 100644
index 00000000..8ee842ce
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -0,0 +1,558 @@
+
+/*
+ * Support PCI/PCIe on PowerNV platforms
+ *
+ * Currently supports only P5IOC2
+ *
+ * Copyright 2011 Benjamin Herrenschmidt, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/msi.h>
+
+#include <asm/sections.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/msi_bitmap.h>
+#include <asm/ppc-pci.h>
+#include <asm/opal.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+#include <asm/firmware.h>
+
+#include "powernv.h"
+#include "pci.h"
+
+/* Delay in usec */
+#define PCI_RESET_DELAY_US	3000000
+
+#define cfg_dbg(fmt...)	do { } while(0)
+//#define cfg_dbg(fmt...)	printk(fmt)
+
+#ifdef CONFIG_PCI_MSI
+static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	if (pdev->no_64bit_msi && !phb->msi32_support)
+		return -ENODEV;
+
+	return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV;
+}
+
+static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct msi_desc *entry;
+	struct msi_msg msg;
+	int hwirq;
+	unsigned int virq;
+	int rc;
+
+	if (WARN_ON(!phb))
+		return -ENODEV;
+
+	list_for_each_entry(entry, &pdev->msi_list, list) {
+		if (!entry->msi_attrib.is_64 && !phb->msi32_support) {
+			pr_warn("%s: Supports only 64-bit MSIs\n",
+				pci_name(pdev));
+			return -ENXIO;
+		}
+		hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, 1);
+		if (hwirq < 0) {
+			pr_warn("%s: Failed to find a free MSI\n",
+				pci_name(pdev));
+			return -ENOSPC;
+		}
+		virq = irq_create_mapping(NULL, phb->msi_base + hwirq);
+		if (virq == NO_IRQ) {
+			pr_warn("%s: Failed to map MSI to linux irq\n",
+				pci_name(pdev));
+			msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1);
+			return -ENOMEM;
+		}
+		rc = phb->msi_setup(phb, pdev, phb->msi_base + hwirq,
+				    virq, entry->msi_attrib.is_64, &msg);
+		if (rc) {
+			pr_warn("%s: Failed to setup MSI\n", pci_name(pdev));
+			irq_dispose_mapping(virq);
+			msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1);
+			return rc;
+		}
+		irq_set_msi_desc(virq, entry);
+		write_msi_msg(virq, &msg);
+	}
+	return 0;
+}
+
+static void pnv_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct msi_desc *entry;
+
+	if (WARN_ON(!phb))
+		return;
+
+	list_for_each_entry(entry, &pdev->msi_list, list) {
+		if (entry->irq == NO_IRQ)
+			continue;
+		irq_set_msi_desc(entry->irq, NULL);
+		msi_bitmap_free_hwirqs(&phb->msi_bmp,
+			virq_to_hw(entry->irq) - phb->msi_base, 1);
+		irq_dispose_mapping(entry->irq);
+	}
+}
+#endif /* CONFIG_PCI_MSI */
+
+static void pnv_pci_dump_p7ioc_diag_data(struct pnv_phb *phb)
+{
+	struct OpalIoP7IOCPhbErrorData *data = &phb->diag.p7ioc;
+	int i;
+
+	pr_info("PHB %d diagnostic data:\n", phb->hose->global_number);
+
+	pr_info("  brdgCtl              = 0x%08x\n", data->brdgCtl);
+
+	pr_info("  portStatusReg        = 0x%08x\n", data->portStatusReg);
+	pr_info("  rootCmplxStatus      = 0x%08x\n", data->rootCmplxStatus);
+	pr_info("  busAgentStatus       = 0x%08x\n", data->busAgentStatus);
+
+	pr_info("  deviceStatus         = 0x%08x\n", data->deviceStatus);
+	pr_info("  slotStatus           = 0x%08x\n", data->slotStatus);
+	pr_info("  linkStatus           = 0x%08x\n", data->linkStatus);
+	pr_info("  devCmdStatus         = 0x%08x\n", data->devCmdStatus);
+	pr_info("  devSecStatus         = 0x%08x\n", data->devSecStatus);
+
+	pr_info("  rootErrorStatus      = 0x%08x\n", data->rootErrorStatus);
+	pr_info("  uncorrErrorStatus    = 0x%08x\n", data->uncorrErrorStatus);
+	pr_info("  corrErrorStatus      = 0x%08x\n", data->corrErrorStatus);
+	pr_info("  tlpHdr1              = 0x%08x\n", data->tlpHdr1);
+	pr_info("  tlpHdr2              = 0x%08x\n", data->tlpHdr2);
+	pr_info("  tlpHdr3              = 0x%08x\n", data->tlpHdr3);
+	pr_info("  tlpHdr4              = 0x%08x\n", data->tlpHdr4);
+	pr_info("  sourceId             = 0x%08x\n", data->sourceId);
+
+	pr_info("  errorClass           = 0x%016llx\n", data->errorClass);
+	pr_info("  correlator           = 0x%016llx\n", data->correlator);
+
+	pr_info("  p7iocPlssr           = 0x%016llx\n", data->p7iocPlssr);
+	pr_info("  p7iocCsr             = 0x%016llx\n", data->p7iocCsr);
+	pr_info("  lemFir               = 0x%016llx\n", data->lemFir);
+	pr_info("  lemErrorMask         = 0x%016llx\n", data->lemErrorMask);
+	pr_info("  lemWOF               = 0x%016llx\n", data->lemWOF);
+	pr_info("  phbErrorStatus       = 0x%016llx\n", data->phbErrorStatus);
+	pr_info("  phbFirstErrorStatus  = 0x%016llx\n", data->phbFirstErrorStatus);
+	pr_info("  phbErrorLog0         = 0x%016llx\n", data->phbErrorLog0);
+	pr_info("  phbErrorLog1         = 0x%016llx\n", data->phbErrorLog1);
+	pr_info("  mmioErrorStatus      = 0x%016llx\n", data->mmioErrorStatus);
+	pr_info("  mmioFirstErrorStatus = 0x%016llx\n", data->mmioFirstErrorStatus);
+	pr_info("  mmioErrorLog0        = 0x%016llx\n", data->mmioErrorLog0);
+	pr_info("  mmioErrorLog1        = 0x%016llx\n", data->mmioErrorLog1);
+	pr_info("  dma0ErrorStatus      = 0x%016llx\n", data->dma0ErrorStatus);
+	pr_info("  dma0FirstErrorStatus = 0x%016llx\n", data->dma0FirstErrorStatus);
+	pr_info("  dma0ErrorLog0        = 0x%016llx\n", data->dma0ErrorLog0);
+	pr_info("  dma0ErrorLog1        = 0x%016llx\n", data->dma0ErrorLog1);
+	pr_info("  dma1ErrorStatus      = 0x%016llx\n", data->dma1ErrorStatus);
+	pr_info("  dma1FirstErrorStatus = 0x%016llx\n", data->dma1FirstErrorStatus);
+	pr_info("  dma1ErrorLog0        = 0x%016llx\n", data->dma1ErrorLog0);
+	pr_info("  dma1ErrorLog1        = 0x%016llx\n", data->dma1ErrorLog1);
+
+	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
+		if ((data->pestA[i] >> 63) == 0 &&
+		    (data->pestB[i] >> 63) == 0)
+			continue;
+		pr_info("  PE[%3d] PESTA        = 0x%016llx\n", i, data->pestA[i]);
+		pr_info("          PESTB        = 0x%016llx\n", data->pestB[i]);
+	}
+}
+
+static void pnv_pci_dump_phb_diag_data(struct pnv_phb *phb)
+{
+	switch(phb->model) {
+	case PNV_PHB_MODEL_P7IOC:
+		pnv_pci_dump_p7ioc_diag_data(phb);
+		break;
+	default:
+		pr_warning("PCI %d: Can't decode this PHB diag data\n",
+			   phb->hose->global_number);
+	}
+}
+
+static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no)
+{
+	unsigned long flags, rc;
+	int has_diag;
+
+	spin_lock_irqsave(&phb->lock, flags);
+
+	rc = opal_pci_get_phb_diag_data(phb->opal_id, phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
+	has_diag = (rc == OPAL_SUCCESS);
+
+	rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no,
+				       OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+	if (rc) {
+		pr_warning("PCI %d: Failed to clear EEH freeze state"
+			   " for PE#%d, err %ld\n",
+			   phb->hose->global_number, pe_no, rc);
+
+		/* For now, let's only display the diag buffer when we fail to clear
+		 * the EEH status. We'll do more sensible things later when we have
+		 * proper EEH support. We need to make sure we don't pollute ourselves
+		 * with the normal errors generated when probing empty slots
+		 */
+		if (has_diag)
+			pnv_pci_dump_phb_diag_data(phb);
+		else
+			pr_warning("PCI %d: No diag data available\n",
+				   phb->hose->global_number);
+	}
+
+	spin_unlock_irqrestore(&phb->lock, flags);
+}
+
+static void pnv_pci_config_check_eeh(struct pnv_phb *phb, struct pci_bus *bus,
+				     u32 bdfn)
+{
+	s64	rc;
+	u8	fstate;
+	u16	pcierr;
+	u32	pe_no;
+
+	/* Get PE# if we support IODA */
+	pe_no = phb->bdfn_to_pe ? phb->bdfn_to_pe(phb, bus, bdfn & 0xff) : 0;
+
+	/* Read freeze status */
+	rc = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, &fstate, &pcierr,
+					NULL);
+	if (rc) {
+		pr_warning("PCI %d: Failed to read EEH status for PE#%d,"
+			   " err %lld\n", phb->hose->global_number, pe_no, rc);
+		return;
+	}
+	cfg_dbg(" -> EEH check, bdfn=%04x PE%d fstate=%x\n",
+		bdfn, pe_no, fstate);
+	if (fstate != 0)
+		pnv_pci_handle_eeh_config(phb, pe_no);
+}
+
+static int pnv_pci_read_config(struct pci_bus *bus,
+			       unsigned int devfn,
+			       int where, int size, u32 *val)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
+	u32 bdfn = (((uint64_t)bus->number) << 8) | devfn;
+	s64 rc;
+
+	if (hose == NULL)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	switch (size) {
+	case 1: {
+		u8 v8;
+		rc = opal_pci_config_read_byte(phb->opal_id, bdfn, where, &v8);
+		*val = (rc == OPAL_SUCCESS) ? v8 : 0xff;
+		break;
+	}
+	case 2: {
+		u16 v16;
+		rc = opal_pci_config_read_half_word(phb->opal_id, bdfn, where,
+						   &v16);
+		*val = (rc == OPAL_SUCCESS) ? v16 : 0xffff;
+		break;
+	}
+	case 4: {
+		u32 v32;
+		rc = opal_pci_config_read_word(phb->opal_id, bdfn, where, &v32);
+		*val = (rc == OPAL_SUCCESS) ? v32 : 0xffffffff;
+		break;
+	}
+	default:
+		return PCIBIOS_FUNC_NOT_SUPPORTED;
+	}
+	cfg_dbg("pnv_pci_read_config bus: %x devfn: %x +%x/%x -> %08x\n",
+		bus->number, devfn, where, size, *val);
+
+	/* Check if the PHB got frozen due to an error (no response) */
+	pnv_pci_config_check_eeh(phb, bus, bdfn);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int pnv_pci_write_config(struct pci_bus *bus,
+				unsigned int devfn,
+				int where, int size, u32 val)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
+	u32 bdfn = (((uint64_t)bus->number) << 8) | devfn;
+
+	if (hose == NULL)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	cfg_dbg("pnv_pci_write_config bus: %x devfn: %x +%x/%x -> %08x\n",
+		bus->number, devfn, where, size, val);
+	switch (size) {
+	case 1:
+		opal_pci_config_write_byte(phb->opal_id, bdfn, where, val);
+		break;
+	case 2:
+		opal_pci_config_write_half_word(phb->opal_id, bdfn, where, val);
+		break;
+	case 4:
+		opal_pci_config_write_word(phb->opal_id, bdfn, where, val);
+		break;
+	default:
+		return PCIBIOS_FUNC_NOT_SUPPORTED;
+	}
+	/* Check if the PHB got frozen due to an error (no response) */
+	pnv_pci_config_check_eeh(phb, bus, bdfn);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+struct pci_ops pnv_pci_ops = {
+	.read = pnv_pci_read_config,
+	.write = pnv_pci_write_config,
+};
+
+static int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
+			 unsigned long uaddr, enum dma_data_direction direction,
+			 struct dma_attrs *attrs)
+{
+	u64 proto_tce;
+	u64 *tcep, *tces;
+	u64 rpn;
+
+	proto_tce = TCE_PCI_READ; // Read allowed
+
+	if (direction != DMA_TO_DEVICE)
+		proto_tce |= TCE_PCI_WRITE;
+
+	tces = tcep = ((u64 *)tbl->it_base) + index - tbl->it_offset;
+	rpn = __pa(uaddr) >> TCE_SHIFT;
+
+	while (npages--)
+		*(tcep++) = proto_tce | (rpn++ << TCE_RPN_SHIFT);
+
+	/* Some implementations won't cache invalid TCEs and thus may not
+	 * need that flush. We'll probably turn it_type into a bit mask
+	 * of flags if that becomes the case
+	 */
+	if (tbl->it_type & TCE_PCI_SWINV_CREATE)
+		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1);
+
+	return 0;
+}
+
+static void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
+{
+	u64 *tcep, *tces;
+
+	tces = tcep = ((u64 *)tbl->it_base) + index - tbl->it_offset;
+
+	while (npages--)
+		*(tcep++) = 0;
+
+	if (tbl->it_type & TCE_PCI_SWINV_FREE)
+		pnv_pci_ioda_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)
+{
+	tbl->it_blocksize = 16;
+	tbl->it_base = (unsigned long)tce_mem;
+	tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT;
+	tbl->it_index = 0;
+	tbl->it_size = tce_size >> 3;
+	tbl->it_busno = 0;
+	tbl->it_type = TCE_PCI;
+}
+
+static struct iommu_table *pnv_pci_setup_bml_iommu(struct pci_controller *hose)
+{
+	struct iommu_table *tbl;
+	const __be64 *basep, *swinvp;
+	const __be32 *sizep;
+
+	basep = of_get_property(hose->dn, "linux,tce-base", NULL);
+	sizep = of_get_property(hose->dn, "linux,tce-size", NULL);
+	if (basep == NULL || sizep == NULL) {
+		pr_err("PCI: %s has missing tce entries !\n",
+		       hose->dn->full_name);
+		return NULL;
+	}
+	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, hose->node);
+	if (WARN_ON(!tbl))
+		return NULL;
+	pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)),
+				  be32_to_cpup(sizep), 0);
+	iommu_init_table(tbl, hose->node);
+
+	/* Deal with SW invalidated TCEs when needed (BML way) */
+	swinvp = of_get_property(hose->dn, "linux,tce-sw-invalidate-info",
+				 NULL);
+	if (swinvp) {
+		tbl->it_busno = swinvp[1];
+		tbl->it_index = (unsigned long)ioremap(swinvp[0], 8);
+		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
+	}
+	return tbl;
+}
+
+static void pnv_pci_dma_fallback_setup(struct pci_controller *hose,
+				       struct pci_dev *pdev)
+{
+	struct device_node *np = pci_bus_to_OF_node(hose->bus);
+	struct pci_dn *pdn;
+
+	if (np == NULL)
+		return;
+	pdn = PCI_DN(np);
+	if (!pdn->iommu_table)
+		pdn->iommu_table = pnv_pci_setup_bml_iommu(hose);
+	if (!pdn->iommu_table)
+		return;
+	set_iommu_table_base(&pdev->dev, pdn->iommu_table);
+}
+
+static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	/* If we have no phb structure, try to setup a fallback based on
+	 * the device-tree (RTAS PCI for example)
+	 */
+	if (phb && phb->dma_dev_setup)
+		phb->dma_dev_setup(phb, pdev);
+	else
+		pnv_pci_dma_fallback_setup(hose, pdev);
+}
+
+void pnv_pci_shutdown(void)
+{
+	struct pci_controller *hose;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		struct pnv_phb *phb = hose->private_data;
+
+		if (phb && phb->shutdown)
+			phb->shutdown(phb);
+	}
+}
+
+/* Fixup wrong class code in p7ioc and p8 root complex */
+static void pnv_p7ioc_rc_quirk(struct pci_dev *dev)
+{
+	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM, 0x3b9, pnv_p7ioc_rc_quirk);
+
+static int pnv_pci_probe_mode(struct pci_bus *bus)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	const __be64 *tstamp;
+	u64 now, target;
+
+
+	/* We hijack this as a way to ensure we have waited long
+	 * enough since the reset was lifted on the PCI bus
+	 */
+	if (bus != hose->bus)
+		return PCI_PROBE_NORMAL;
+	tstamp = of_get_property(hose->dn, "reset-clear-timestamp", NULL);
+	if (!tstamp || !*tstamp)
+		return PCI_PROBE_NORMAL;
+
+	now = mftb() / tb_ticks_per_usec;
+	target = (be64_to_cpup(tstamp) / tb_ticks_per_usec)
+		+ PCI_RESET_DELAY_US;
+
+	pr_devel("pci %04d: Reset target: 0x%llx now: 0x%llx\n",
+		 hose->global_number, target, now);
+
+	if (now < target)
+		msleep((target - now + 999) / 1000);
+
+	return PCI_PROBE_NORMAL;
+}
+
+void __init pnv_pci_init(void)
+{
+	struct device_node *np;
+
+	pci_add_flags(PCI_CAN_SKIP_ISA_ALIGN);
+
+	/* OPAL absent, try POPAL first then RTAS detection of PHBs */
+	if (!firmware_has_feature(FW_FEATURE_OPAL)) {
+#ifdef CONFIG_PPC_POWERNV_RTAS
+		init_pci_config_tokens();
+		find_and_init_phbs();
+#endif /* CONFIG_PPC_POWERNV_RTAS */
+	}
+	/* OPAL is here, do our normal stuff */
+	else {
+		int found_ioda = 0;
+
+		/* Look for IODA IO-Hubs. We don't support mixing IODA
+		 * and p5ioc2 due to the need to change some global
+		 * probing flags
+		 */
+		for_each_compatible_node(np, NULL, "ibm,ioda-hub") {
+			pnv_pci_init_ioda_hub(np);
+			found_ioda = 1;
+		}
+
+		/* Look for p5ioc2 IO-Hubs */
+		if (!found_ioda)
+			for_each_compatible_node(np, NULL, "ibm,p5ioc2")
+				pnv_pci_init_p5ioc2_hub(np);
+
+		/* Look for ioda2 built-in PHB3's */
+		for_each_compatible_node(np, NULL, "ibm,ioda2-phb")
+			pnv_pci_init_ioda2_phb(np);
+	}
+
+	/* Setup the linkage between OF nodes and PHBs */
+	pci_devs_phb_init();
+
+	/* Configure IOMMU DMA hooks */
+	ppc_md.pci_dma_dev_setup = pnv_pci_dma_dev_setup;
+	ppc_md.tce_build = pnv_tce_build;
+	ppc_md.tce_free = pnv_tce_free;
+	ppc_md.tce_get = pnv_tce_get;
+	ppc_md.pci_probe_mode = pnv_pci_probe_mode;
+	set_pci_dma_ops(&dma_iommu_ops);
+
+	/* Configure MSIs */
+#ifdef CONFIG_PCI_MSI
+	ppc_md.msi_check_device = pnv_msi_check_device;
+	ppc_md.setup_msi_irqs = pnv_setup_msi_irqs;
+	ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs;
+#endif
+}
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
new file mode 100644
index 00000000..25d76c4d
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -0,0 +1,163 @@
+#ifndef __POWERNV_PCI_H
+#define __POWERNV_PCI_H
+
+struct pci_dn;
+
+enum pnv_phb_type {
+	PNV_PHB_P5IOC2	= 0,
+	PNV_PHB_IODA1	= 1,
+	PNV_PHB_IODA2	= 2,
+};
+
+/* Precise PHB model for error management */
+enum pnv_phb_model {
+	PNV_PHB_MODEL_UNKNOWN,
+	PNV_PHB_MODEL_P5IOC2,
+	PNV_PHB_MODEL_P7IOC,
+	PNV_PHB_MODEL_PHB3,
+};
+
+#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_phb;
+struct pnv_ioda_pe {
+	unsigned long		flags;
+	struct pnv_phb		*phb;
+
+	/* 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.
+	 */
+	struct pci_dev		*pdev;
+	struct pci_bus		*pbus;
+
+	/* Effective RID (device RID for a device PE and base bus
+	 * RID with devfn 0 for a bus PE)
+	 */
+	unsigned int		rid;
+
+	/* PE number */
+	unsigned int		pe_number;
+
+	/* "Weight" assigned to the PE for the sake of DMA resource
+	 * allocations
+	 */
+	unsigned int		dma_weight;
+
+	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
+	int			tce32_seg;
+	int			tce32_segcount;
+	struct iommu_table	tce32_table;
+
+	/* XXX TODO: Add support for additional 64-bit iommus */
+
+	/* MSIs. MVE index is identical for for 32 and 64 bit MSI
+	 * and -1 if not supported. (It's actually identical to the
+	 * PE number)
+	 */
+	int			mve_number;
+
+	/* Link in list of PE#s */
+	struct list_head	dma_link;
+	struct list_head	list;
+};
+
+struct pnv_phb {
+	struct pci_controller	*hose;
+	enum pnv_phb_type	type;
+	enum pnv_phb_model	model;
+	u64			opal_id;
+	void __iomem		*regs;
+	int			initialized;
+	spinlock_t		lock;
+
+#ifdef CONFIG_PCI_MSI
+	unsigned int		msi_base;
+	unsigned int		msi32_support;
+	struct msi_bitmap	msi_bmp;
+#endif
+	int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev,
+			 unsigned int hwirq, unsigned int virq,
+			 unsigned int is_64, struct msi_msg *msg);
+	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
+	void (*fixup_phb)(struct pci_controller *hose);
+	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
+	void (*shutdown)(struct pnv_phb *phb);
+
+	union {
+		struct {
+			struct iommu_table iommu_table;
+		} p5ioc2;
+
+		struct {
+			/* Global bridge info */
+			unsigned int		total_pe;
+			unsigned int		m32_size;
+			unsigned int		m32_segsize;
+			unsigned int		m32_pci_base;
+			unsigned int		io_size;
+			unsigned int		io_segsize;
+			unsigned int		io_pci_base;
+
+			/* PE allocation bitmap */
+			unsigned long		*pe_alloc;
+
+			/* M32 & IO segment maps */
+			unsigned int		*m32_segmap;
+			unsigned int		*io_segmap;
+			struct pnv_ioda_pe	*pe_array;
+
+			/* IRQ chip */
+			int			irq_chip_init;
+			struct irq_chip		irq_chip;
+
+			/* 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 }
+			 */
+			unsigned char		pe_rmap[0x10000];
+
+			/* 32-bit TCE tables allocation */
+			unsigned long		tce32_count;
+
+			/* Total "weight" for the sake of DMA resources
+			 * allocation
+			 */
+			unsigned int		dma_weight;
+			unsigned int		dma_pe_count;
+
+			/* Sorted list of used PE's, sorted at
+			 * boot for resource allocation purposes
+			 */
+			struct list_head	pe_dma_list;
+		} ioda;
+	};
+
+	/* PHB status structure */
+	union {
+		unsigned char			blob[PNV_PCI_DIAG_BUF_SIZE];
+		struct OpalIoP7IOCPhbErrorData	p7ioc;
+	} diag;
+};
+
+extern struct pci_ops pnv_pci_ops;
+
+extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
+				      void *tce_mem, u64 tce_size,
+				      u64 dma_offset);
+extern void pnv_pci_init_p5ioc2_hub(struct device_node *np);
+extern void pnv_pci_init_ioda_hub(struct device_node *np);
+extern void pnv_pci_init_ioda2_phb(struct device_node *np);
+extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
+					u64 *startp, u64 *endp);
+
+#endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
new file mode 100644
index 00000000..a1c6f83f
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -0,0 +1,18 @@
+#ifndef _POWERNV_H
+#define _POWERNV_H
+
+#ifdef CONFIG_SMP
+extern void pnv_smp_init(void);
+#else
+static inline void pnv_smp_init(void) { }
+#endif
+
+#ifdef CONFIG_PCI
+extern void pnv_pci_init(void);
+extern void pnv_pci_shutdown(void);
+#else
+static inline void pnv_pci_init(void) { }
+static inline void pnv_pci_shutdown(void) { }
+#endif
+
+#endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
new file mode 100644
index 00000000..d4459bfc
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -0,0 +1,209 @@
+/*
+ * PowerNV setup code.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/cpu.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/tty.h>
+#include <linux/reboot.h>
+#include <linux/init.h>
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/seq_file.h>
+#include <linux/of.h>
+#include <linux/interrupt.h>
+#include <linux/bug.h>
+
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+#include <asm/xics.h>
+#include <asm/rtas.h>
+#include <asm/opal.h>
+
+#include "powernv.h"
+
+static void __init pnv_setup_arch(void)
+{
+	/* Initialize SMP */
+	pnv_smp_init();
+
+	/* Setup PCI */
+	pnv_pci_init();
+
+	/* Setup RTC and NVRAM callbacks */
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		opal_nvram_init();
+
+	/* Enable NAP mode */
+	powersave_nap = 1;
+
+	/* XXX PMCS */
+}
+
+static void __init pnv_init_early(void)
+{
+#ifdef CONFIG_HVC_OPAL
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		hvc_opal_init_early();
+	else
+#endif
+		add_preferred_console("hvc", 0, NULL);
+}
+
+static void __init pnv_init_IRQ(void)
+{
+	xics_init();
+
+	WARN_ON(!ppc_md.get_irq);
+}
+
+static void pnv_show_cpuinfo(struct seq_file *m)
+{
+	struct device_node *root;
+	const char *model = "";
+
+	root = of_find_node_by_path("/");
+	if (root)
+		model = of_get_property(root, "model", NULL);
+	seq_printf(m, "machine\t\t: PowerNV %s\n", model);
+	if (firmware_has_feature(FW_FEATURE_OPALv3))
+		seq_printf(m, "firmware\t: OPAL v3\n");
+	else if (firmware_has_feature(FW_FEATURE_OPALv2))
+		seq_printf(m, "firmware\t: OPAL v2\n");
+	else if (firmware_has_feature(FW_FEATURE_OPAL))
+		seq_printf(m, "firmware\t: OPAL v1\n");
+	else
+		seq_printf(m, "firmware\t: BML\n");
+	of_node_put(root);
+}
+
+static void  __noreturn pnv_restart(char *cmd)
+{
+	long rc = OPAL_BUSY;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_cec_reboot();
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
+	for (;;)
+		opal_poll_events(NULL);
+}
+
+static void __noreturn pnv_power_off(void)
+{
+	long rc = OPAL_BUSY;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_cec_power_down(0);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
+	for (;;)
+		opal_poll_events(NULL);
+}
+
+static void __noreturn pnv_halt(void)
+{
+	pnv_power_off();
+}
+
+static void pnv_progress(char *s, unsigned short hex)
+{
+}
+
+static void pnv_shutdown(void)
+{
+	/* Let the PCI code clear up IODA tables */
+	pnv_pci_shutdown();
+
+	/* And unregister all OPAL interrupts so they don't fire
+	 * up while we kexec
+	 */
+	opal_shutdown();
+}
+
+#ifdef CONFIG_KEXEC
+static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
+{
+	xics_kexec_teardown_cpu(secondary);
+}
+#endif /* CONFIG_KEXEC */
+
+static void __init pnv_setup_machdep_opal(void)
+{
+	ppc_md.get_boot_time = opal_get_boot_time;
+	ppc_md.get_rtc_time = opal_get_rtc_time;
+	ppc_md.set_rtc_time = opal_set_rtc_time;
+	ppc_md.restart = pnv_restart;
+	ppc_md.power_off = pnv_power_off;
+	ppc_md.halt = pnv_halt;
+	ppc_md.machine_check_exception = opal_machine_check;
+}
+
+#ifdef CONFIG_PPC_POWERNV_RTAS
+static void __init pnv_setup_machdep_rtas(void)
+{
+	if (rtas_token("get-time-of-day") != RTAS_UNKNOWN_SERVICE) {
+		ppc_md.get_boot_time = rtas_get_boot_time;
+		ppc_md.get_rtc_time = rtas_get_rtc_time;
+		ppc_md.set_rtc_time = rtas_set_rtc_time;
+	}
+	ppc_md.restart = rtas_restart;
+	ppc_md.power_off = rtas_power_off;
+	ppc_md.halt = rtas_halt;
+}
+#endif /* CONFIG_PPC_POWERNV_RTAS */
+
+static int __init pnv_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	if (!of_flat_dt_is_compatible(root, "ibm,powernv"))
+		return 0;
+
+	hpte_init_native();
+
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		pnv_setup_machdep_opal();
+#ifdef CONFIG_PPC_POWERNV_RTAS
+	else if (rtas.base)
+		pnv_setup_machdep_rtas();
+#endif /* CONFIG_PPC_POWERNV_RTAS */
+
+	pr_debug("PowerNV detected !\n");
+
+	return 1;
+}
+
+define_machine(powernv) {
+	.name			= "PowerNV",
+	.probe			= pnv_probe,
+	.init_early		= pnv_init_early,
+	.setup_arch		= pnv_setup_arch,
+	.init_IRQ		= pnv_init_IRQ,
+	.show_cpuinfo		= pnv_show_cpuinfo,
+	.progress		= pnv_progress,
+	.machine_shutdown	= pnv_shutdown,
+	.power_save             = power7_idle,
+	.calibrate_decr		= generic_calibrate_decr,
+#ifdef CONFIG_KEXEC
+	.kexec_cpu_down		= pnv_kexec_cpu_down,
+#endif
+};
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
new file mode 100644
index 00000000..88c9459c
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -0,0 +1,225 @@
+/*
+ * SMP support for PowerNV machines.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/cpu.h>
+
+#include <asm/irq.h>
+#include <asm/smp.h>
+#include <asm/paca.h>
+#include <asm/machdep.h>
+#include <asm/cputable.h>
+#include <asm/firmware.h>
+#include <asm/rtas.h>
+#include <asm/vdso_datapage.h>
+#include <asm/cputhreads.h>
+#include <asm/xics.h>
+#include <asm/opal.h>
+
+#include "powernv.h"
+
+#ifdef DEBUG
+#include <asm/udbg.h>
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+static void __cpuinit pnv_smp_setup_cpu(int cpu)
+{
+	if (cpu != boot_cpuid)
+		xics_setup_cpu();
+}
+
+static int pnv_smp_cpu_bootable(unsigned int nr)
+{
+	/* Special case - we inhibit secondary thread startup
+	 * during boot if the user requests it.
+	 */
+	if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) {
+		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
+			return 0;
+		if (smt_enabled_at_boot
+		    && cpu_thread_in_core(nr) >= smt_enabled_at_boot)
+			return 0;
+	}
+
+	return 1;
+}
+
+int pnv_smp_kick_cpu(int nr)
+{
+	unsigned int pcpu = get_hard_smp_processor_id(nr);
+	unsigned long start_here = __pa(*((unsigned long *)
+					  generic_secondary_smp_init));
+	long rc;
+
+	BUG_ON(nr < 0 || nr >= NR_CPUS);
+
+	/*
+	 * If we already started or OPALv2 is not supported, we just
+	 * kick the CPU via the PACA
+	 */
+	if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPALv2))
+		goto kick;
+
+	/*
+	 * At this point, the CPU can either be spinning on the way in
+	 * from kexec or be inside OPAL waiting to be started for the
+	 * first time. OPAL v3 allows us to query OPAL to know if it
+	 * has the CPUs, so we do that
+	 */
+	if (firmware_has_feature(FW_FEATURE_OPALv3)) {
+		uint8_t status;
+
+		rc = opal_query_cpu_status(pcpu, &status);
+		if (rc != OPAL_SUCCESS) {
+			pr_warn("OPAL Error %ld querying CPU %d state\n",
+				rc, nr);
+			return -ENODEV;
+		}
+
+		/*
+		 * Already started, just kick it, probably coming from
+		 * kexec and spinning
+		 */
+		if (status == OPAL_THREAD_STARTED)
+			goto kick;
+
+		/*
+		 * Available/inactive, let's kick it
+		 */
+		if (status == OPAL_THREAD_INACTIVE) {
+			pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n",
+				 nr, pcpu);
+			rc = opal_start_cpu(pcpu, start_here);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("OPAL Error %ld starting CPU %d\n",
+					rc, nr);
+				return -ENODEV;
+			}
+		} else {
+			/*
+			 * An unavailable CPU (or any other unknown status)
+			 * shouldn't be started. It should also
+			 * not be in the possible map but currently it can
+			 * happen
+			 */
+			pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable"
+				 " (status %d)...\n", nr, pcpu, status);
+			return -ENODEV;
+		}
+	} else {
+		/*
+		 * On OPAL v2, we just kick it and hope for the best,
+		 * we must not test the error from opal_start_cpu() or
+		 * we would fail to get CPUs from kexec.
+		 */
+		opal_start_cpu(pcpu, start_here);
+	}
+ kick:
+	return smp_generic_kick_cpu(nr);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static int pnv_smp_cpu_disable(void)
+{
+	int cpu = smp_processor_id();
+
+	/* This is identical to pSeries... might consolidate by
+	 * moving migrate_irqs_away to a ppc_md with default to
+	 * the generic fixup_irqs. --BenH.
+	 */
+	set_cpu_online(cpu, false);
+	vdso_data->processorCount--;
+	if (cpu == boot_cpuid)
+		boot_cpuid = cpumask_any(cpu_online_mask);
+	xics_migrate_irqs_away();
+	return 0;
+}
+
+static void pnv_smp_cpu_kill_self(void)
+{
+	unsigned int cpu;
+
+	/* Standard hot unplug procedure */
+	local_irq_disable();
+	idle_task_exit();
+	current->active_mm = NULL; /* for sanity */
+	cpu = smp_processor_id();
+	DBG("CPU%d offline\n", cpu);
+	generic_set_cpu_dead(cpu);
+	smp_wmb();
+
+	/* We don't want to take decrementer interrupts while we are offline,
+	 * so clear LPCR:PECE1. We keep PECE2 enabled.
+	 */
+	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
+	while (!generic_check_cpu_restart(cpu)) {
+		power7_nap();
+		if (!generic_check_cpu_restart(cpu)) {
+			DBG("CPU%d Unexpected exit while offline !\n", cpu);
+			/* We may be getting an IPI, so we re-enable
+			 * interrupts to process it, it will be ignored
+			 * since we aren't online (hopefully)
+			 */
+			local_irq_enable();
+			local_irq_disable();
+		}
+	}
+	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1);
+	DBG("CPU%d coming online...\n", cpu);
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static struct smp_ops_t pnv_smp_ops = {
+	.message_pass	= smp_muxed_ipi_message_pass,
+	.cause_ipi	= NULL,	/* Filled at runtime by xics_smp_probe() */
+	.probe		= xics_smp_probe,
+	.kick_cpu	= pnv_smp_kick_cpu,
+	.setup_cpu	= pnv_smp_setup_cpu,
+	.cpu_bootable	= pnv_smp_cpu_bootable,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable	= pnv_smp_cpu_disable,
+	.cpu_die	= generic_cpu_die,
+#endif /* CONFIG_HOTPLUG_CPU */
+};
+
+/* This is called very early during platform setup_arch */
+void __init pnv_smp_init(void)
+{
+	smp_ops = &pnv_smp_ops;
+
+	/* XXX We don't yet have a proper entry point from HAL, for
+	 * now we rely on kexec-style entry from BML
+	 */
+
+#ifdef CONFIG_PPC_RTAS
+	/* Non-lpar has additional take/give timebase */
+	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
+		smp_ops->give_timebase = rtas_give_timebase;
+		smp_ops->take_timebase = rtas_take_timebase;
+	}
+#endif /* CONFIG_PPC_RTAS */
+
+#ifdef CONFIG_HOTPLUG_CPU
+	ppc_md.cpu_die	= pnv_smp_cpu_kill_self;
+#endif
+}