Merge branch 'linus' into perfcounters/core

Conflicts:
	arch/x86/include/asm/kmap_types.h
	include/linux/mm.h

	include/asm-generic/kmap_types.h

Merge reason: We crossed changes with kmap_types.h cleanups in mainline.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

30 files changed, 1745 insertions, 1469 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index a2c683403c2..612b0c4dc26 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -36,7 +36,7 @@ obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   firmware.o nvram_64.o
 obj64-$(CONFIG_RELOCATABLE)	+= reloc_64.o
 obj-$(CONFIG_PPC64)		+= vdso64/
-obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
+obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
 obj-$(CONFIG_PPC_OF)		+= of_device.o of_platform.o prom_parse.o
 obj-$(CONFIG_PPC_CLOCK)		+= clock.o
@@ -82,6 +82,7 @@ obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_PPC_UDBG_16550)	+= legacy_serial.o udbg_16550.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
+obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
 
 pci64-$(CONFIG_PPC64)		+= pci_dn.o isa-bridge.o
 obj-$(CONFIG_PCI)		+= pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \
@@ -111,6 +112,7 @@ obj-y				+= ppc_save_regs.o
 endif
 
 extra-$(CONFIG_PPC_FPU)		+= fpu.o
+extra-$(CONFIG_ALTIVEC)		+= vector.o
 extra-$(CONFIG_PPC64)		+= entry_64.o
 
 extra-y				+= systbl_chk.i
@@ -123,6 +125,7 @@ PHONY += systbl_chk
 systbl_chk: $(src)/systbl_chk.sh $(obj)/systbl_chk.i
 	$(call cmd,systbl_chk)
 
+ifeq ($(CONFIG_PPC_OF_BOOT_TRAMPOLINE),y)
 $(obj)/built-in.o:		prom_init_check
 
 quiet_cmd_prom_init_check = CALL    $<
@@ -131,5 +134,6 @@ quiet_cmd_prom_init_check = CALL    $<
 PHONY += prom_init_check
 prom_init_check: $(src)/prom_init_check.sh $(obj)/prom_init.o
 	$(call cmd,prom_init_check)
+endif
 
 clean-files := vmlinux.lds
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 5ffcfaa77d6..a5b632e52fa 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -24,6 +24,7 @@
 #include <asm/system.h>
 #include <asm/cache.h>
 #include <asm/cputable.h>
+#include <asm/emulated_ops.h>
 
 struct aligninfo {
 	unsigned char len;
@@ -730,8 +731,10 @@ int fix_alignment(struct pt_regs *regs)
 	areg = dsisr & 0x1f;		/* register to update */
 
 #ifdef CONFIG_SPE
-	if ((instr >> 26) == 0x4)
+	if ((instr >> 26) == 0x4) {
+		PPC_WARN_EMULATED(spe);
 		return emulate_spe(regs, reg, instr);
+	}
 #endif
 
 	instr = (dsisr >> 10) & 0x7f;
@@ -783,23 +786,28 @@ int fix_alignment(struct pt_regs *regs)
 			flags |= SPLT;
 			nb = 8;
 		}
+		PPC_WARN_EMULATED(vsx);
 		return emulate_vsx(addr, reg, areg, regs, flags, nb);
 	}
 #endif
 	/* A size of 0 indicates an instruction we don't support, with
 	 * the exception of DCBZ which is handled as a special case here
 	 */
-	if (instr == DCBZ)
+	if (instr == DCBZ) {
+		PPC_WARN_EMULATED(dcbz);
 		return emulate_dcbz(regs, addr);
+	}
 	if (unlikely(nb == 0))
 		return 0;
 
 	/* Load/Store Multiple instructions are handled in their own
 	 * function
 	 */
-	if (flags & M)
+	if (flags & M) {
+		PPC_WARN_EMULATED(multiple);
 		return emulate_multiple(regs, addr, reg, nb,
 					flags, instr, swiz);
+	}
 
 	/* Verify the address of the operand */
 	if (unlikely(user_mode(regs) &&
@@ -816,8 +824,12 @@ int fix_alignment(struct pt_regs *regs)
 	}
 
 	/* Special case for 16-byte FP loads and stores */
-	if (nb == 16)
+	if (nb == 16) {
+		PPC_WARN_EMULATED(fp_pair);
 		return emulate_fp_pair(addr, reg, flags);
+	}
+
+	PPC_WARN_EMULATED(unaligned);
 
 	/* If we are loading, get the data from user space, else
 	 * get it from register values
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index e981d1ce191..561b6465231 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -122,8 +122,6 @@ int main(void)
 	DEFINE(PACAKSAVE, offsetof(struct paca_struct, kstack));
 	DEFINE(PACACURRENT, offsetof(struct paca_struct, __current));
 	DEFINE(PACASAVEDMSR, offsetof(struct paca_struct, saved_msr));
-	DEFINE(PACASTABREAL, offsetof(struct paca_struct, stab_real));
-	DEFINE(PACASTABVIRT, offsetof(struct paca_struct, stab_addr));
 	DEFINE(PACASTABRR, offsetof(struct paca_struct, stab_rr));
 	DEFINE(PACAR1, offsetof(struct paca_struct, saved_r1));
 	DEFINE(PACATOC, offsetof(struct paca_struct, kernel_toc));
@@ -132,35 +130,30 @@ int main(void)
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
 	DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_counter_pending));
-	DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
-	DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
 	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
-	DEFINE(PACAVMALLOCSLLP, offsetof(struct paca_struct, vmalloc_sllp));
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
 					    context.low_slices_psize));
 	DEFINE(PACAHIGHSLICEPSIZE, offsetof(struct paca_struct,
 					    context.high_slices_psize));
 	DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
+#endif /* CONFIG_PPC_MM_SLICES */
+#ifdef CONFIG_PPC_STD_MMU_64
+	DEFINE(PACASTABREAL, offsetof(struct paca_struct, stab_real));
+	DEFINE(PACASTABVIRT, offsetof(struct paca_struct, stab_addr));
+	DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
+	DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
+	DEFINE(PACAVMALLOCSLLP, offsetof(struct paca_struct, vmalloc_sllp));
+#ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(MMUPSIZESLLP, offsetof(struct mmu_psize_def, sllp));
 #else
 	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, context.sllp));
-
 #endif /* CONFIG_PPC_MM_SLICES */
 	DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
 	DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));
 	DEFINE(PACA_EXSLB, offsetof(struct paca_struct, exslb));
-	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
 	DEFINE(PACALPPACAPTR, offsetof(struct paca_struct, lppaca_ptr));
-	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
-	DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
-	DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
-	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
-	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
 	DEFINE(PACA_SLBSHADOWPTR, offsetof(struct paca_struct, slb_shadow_ptr));
-	DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset));
-	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
-
 	DEFINE(SLBSHADOW_STACKVSID,
 	       offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid));
 	DEFINE(SLBSHADOW_STACKESID,
@@ -170,6 +163,15 @@ int main(void)
 	DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int));
 	DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int));
 	DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area));
+#endif /* CONFIG_PPC_STD_MMU_64 */
+	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
+	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
+	DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
+	DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
+	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
+	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
+	DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset));
+	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
 #endif /* CONFIG_PPC64 */
 
 	/* RTAS */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 3e33fb933d9..4a24a2fc457 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -427,7 +427,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER7 (architected)",
 		.cpu_features		= CPU_FTRS_POWER7,
 		.cpu_user_features	= COMMON_USER_POWER7,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE |
+			MMU_FTR_TLBIE_206,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.machine_check		= machine_check_generic,
@@ -441,7 +442,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER7 (raw)",
 		.cpu_features		= CPU_FTRS_POWER7,
 		.cpu_user_features	= COMMON_USER_POWER7,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE |
+			MMU_FTR_TLBIE_206,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
new file mode 100644
index 00000000000..68ccf11e4f1
--- /dev/null
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -0,0 +1,163 @@
+/*
+ * Contains routines needed to support swiotlb for ppc.
+ *
+ * Copyright (C) 2009 Becky Bruce, Freescale Semiconductor
+ *
+ * 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/dma-mapping.h>
+#include <linux/pfn.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pci.h>
+
+#include <asm/machdep.h>
+#include <asm/swiotlb.h>
+#include <asm/dma.h>
+#include <asm/abs_addr.h>
+
+int swiotlb __read_mostly;
+unsigned int ppc_swiotlb_enable;
+
+void *swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t addr)
+{
+	unsigned long pfn = PFN_DOWN(swiotlb_bus_to_phys(hwdev, addr));
+	void *pageaddr = page_address(pfn_to_page(pfn));
+
+	if (pageaddr != NULL)
+		return pageaddr + (addr % PAGE_SIZE);
+	return NULL;
+}
+
+dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
+{
+	return paddr + get_dma_direct_offset(hwdev);
+}
+
+phys_addr_t swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
+
+{
+	return baddr - get_dma_direct_offset(hwdev);
+}
+
+/*
+ * Determine if an address needs bounce buffering via swiotlb.
+ * Going forward I expect the swiotlb code to generalize on using
+ * a dma_ops->addr_needs_map, and this function will move from here to the
+ * generic swiotlb code.
+ */
+int
+swiotlb_arch_address_needs_mapping(struct device *hwdev, dma_addr_t addr,
+				   size_t size)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(hwdev);
+
+	BUG_ON(!dma_ops);
+	return dma_ops->addr_needs_map(hwdev, addr, size);
+}
+
+/*
+ * Determine if an address is reachable by a pci device, or if we must bounce.
+ */
+static int
+swiotlb_pci_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
+{
+	u64 mask = dma_get_mask(hwdev);
+	dma_addr_t max;
+	struct pci_controller *hose;
+	struct pci_dev *pdev = to_pci_dev(hwdev);
+
+	hose = pci_bus_to_host(pdev->bus);
+	max = hose->dma_window_base_cur + hose->dma_window_size;
+
+	/* check that we're within mapped pci window space */
+	if ((addr + size > max) | (addr < hose->dma_window_base_cur))
+		return 1;
+
+	return !is_buffer_dma_capable(mask, addr, size);
+}
+
+static int
+swiotlb_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
+{
+	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
+}
+
+
+/*
+ * At the moment, all platforms that use this code only require
+ * swiotlb to be used if we're operating on HIGHMEM.  Since
+ * we don't ever call anything other than map_sg, unmap_sg,
+ * map_page, and unmap_page on highmem, use normal dma_ops
+ * for everything else.
+ */
+struct dma_mapping_ops swiotlb_dma_ops = {
+	.alloc_coherent = dma_direct_alloc_coherent,
+	.free_coherent = dma_direct_free_coherent,
+	.map_sg = swiotlb_map_sg_attrs,
+	.unmap_sg = swiotlb_unmap_sg_attrs,
+	.dma_supported = swiotlb_dma_supported,
+	.map_page = swiotlb_map_page,
+	.unmap_page = swiotlb_unmap_page,
+	.addr_needs_map = swiotlb_addr_needs_map,
+	.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
+	.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
+	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = swiotlb_sync_sg_for_device
+};
+
+struct dma_mapping_ops swiotlb_pci_dma_ops = {
+	.alloc_coherent = dma_direct_alloc_coherent,
+	.free_coherent = dma_direct_free_coherent,
+	.map_sg = swiotlb_map_sg_attrs,
+	.unmap_sg = swiotlb_unmap_sg_attrs,
+	.dma_supported = swiotlb_dma_supported,
+	.map_page = swiotlb_map_page,
+	.unmap_page = swiotlb_unmap_page,
+	.addr_needs_map = swiotlb_pci_addr_needs_map,
+	.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
+	.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
+	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = swiotlb_sync_sg_for_device
+};
+
+static int ppc_swiotlb_bus_notify(struct notifier_block *nb,
+				  unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	/* We are only intereted in device addition */
+	if (action != BUS_NOTIFY_ADD_DEVICE)
+		return 0;
+
+	/* May need to bounce if the device can't address all of DRAM */
+	if (dma_get_mask(dev) < lmb_end_of_DRAM())
+		set_dma_ops(dev, &swiotlb_dma_ops);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block ppc_swiotlb_plat_bus_notifier = {
+	.notifier_call = ppc_swiotlb_bus_notify,
+	.priority = 0,
+};
+
+static struct notifier_block ppc_swiotlb_of_bus_notifier = {
+	.notifier_call = ppc_swiotlb_bus_notify,
+	.priority = 0,
+};
+
+int __init swiotlb_setup_bus_notifier(void)
+{
+	bus_register_notifier(&platform_bus_type,
+			      &ppc_swiotlb_plat_bus_notifier);
+	bus_register_notifier(&of_platform_bus_type,
+			      &ppc_swiotlb_of_bus_notifier);
+
+	return 0;
+}
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 6b02793dc75..20a60d661ba 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -19,7 +19,7 @@
  * default the offset is PCI_DRAM_OFFSET.
  */
 
-static unsigned long get_dma_direct_offset(struct device *dev)
+unsigned long get_dma_direct_offset(struct device *dev)
 {
 	if (dev)
 		return (unsigned long)dev->archdata.dma_data;
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
new file mode 100644
index 00000000000..eb898112e57
--- /dev/null
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -0,0 +1,978 @@
+/*
+ * This file contains the 64-bit "server" PowerPC variant
+ * of the low level exception handling including exception
+ * vectors, exception return, part of the slb and stab
+ * handling and other fixed offset specific things.
+ *
+ * This file is meant to be #included from head_64.S due to
+ * position dependant assembly.
+ *
+ * Most of this originates from head_64.S and thus has the same
+ * copyright history.
+ *
+ */
+
+/*
+ * We layout physical memory as follows:
+ * 0x0000 - 0x00ff : Secondary processor spin code
+ * 0x0100 - 0x2fff : pSeries Interrupt prologs
+ * 0x3000 - 0x5fff : interrupt support, iSeries and common interrupt prologs
+ * 0x6000 - 0x6fff : Initial (CPU0) segment table
+ * 0x7000 - 0x7fff : FWNMI data area
+ * 0x8000 -        : Early init and support code
+ */
+
+
+/*
+ *   SPRG Usage
+ *
+ *   Register	Definition
+ *
+ *   SPRG0	reserved for hypervisor
+ *   SPRG1	temp - used to save gpr
+ *   SPRG2	temp - used to save gpr
+ *   SPRG3	virt addr of paca
+ */
+
+/*
+ * This is the start of the interrupt handlers for pSeries
+ * This code runs with relocation off.
+ * Code from here to __end_interrupts gets copied down to real
+ * address 0x100 when we are running a relocatable kernel.
+ * Therefore any relative branches in this section must only
+ * branch to labels in this section.
+ */
+	. = 0x100
+	.globl __start_interrupts
+__start_interrupts:
+
+	STD_EXCEPTION_PSERIES(0x100, system_reset)
+
+	. = 0x200
+_machine_check_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13		/* save r13 */
+	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
+
+	. = 0x300
+	.globl data_access_pSeries
+data_access_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13
+BEGIN_FTR_SECTION
+	mtspr	SPRN_SPRG2,r12
+	mfspr	r13,SPRN_DAR
+	mfspr	r12,SPRN_DSISR
+	srdi	r13,r13,60
+	rlwimi	r13,r12,16,0x20
+	mfcr	r12
+	cmpwi	r13,0x2c
+	beq	do_stab_bolted_pSeries
+	mtcrf	0x80,r12
+	mfspr	r12,SPRN_SPRG2
+END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common)
+
+	. = 0x380
+	.globl data_access_slb_pSeries
+data_access_slb_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13
+	mfspr	r13,SPRN_SPRG3		/* get paca address into r13 */
+	std	r3,PACA_EXSLB+EX_R3(r13)
+	mfspr	r3,SPRN_DAR
+	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
+	mfcr	r9
+#ifdef __DISABLED__
+	/* Keep that around for when we re-implement dynamic VSIDs */
+	cmpdi	r3,0
+	bge	slb_miss_user_pseries
+#endif /* __DISABLED__ */
+	std	r10,PACA_EXSLB+EX_R10(r13)
+	std	r11,PACA_EXSLB+EX_R11(r13)
+	std	r12,PACA_EXSLB+EX_R12(r13)
+	mfspr	r10,SPRN_SPRG1
+	std	r10,PACA_EXSLB+EX_R13(r13)
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+#ifndef CONFIG_RELOCATABLE
+	b	.slb_miss_realmode
+#else
+	/*
+	 * We can't just use a direct branch to .slb_miss_realmode
+	 * because the distance from here to there depends on where
+	 * the kernel ends up being put.
+	 */
+	mfctr	r11
+	ld	r10,PACAKBASE(r13)
+	LOAD_HANDLER(r10, .slb_miss_realmode)
+	mtctr	r10
+	bctr
+#endif
+
+	STD_EXCEPTION_PSERIES(0x400, instruction_access)
+
+	. = 0x480
+	.globl instruction_access_slb_pSeries
+instruction_access_slb_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13
+	mfspr	r13,SPRN_SPRG3		/* get paca address into r13 */
+	std	r3,PACA_EXSLB+EX_R3(r13)
+	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
+	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
+	mfcr	r9
+#ifdef __DISABLED__
+	/* Keep that around for when we re-implement dynamic VSIDs */
+	cmpdi	r3,0
+	bge	slb_miss_user_pseries
+#endif /* __DISABLED__ */
+	std	r10,PACA_EXSLB+EX_R10(r13)
+	std	r11,PACA_EXSLB+EX_R11(r13)
+	std	r12,PACA_EXSLB+EX_R12(r13)
+	mfspr	r10,SPRN_SPRG1
+	std	r10,PACA_EXSLB+EX_R13(r13)
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+#ifndef CONFIG_RELOCATABLE
+	b	.slb_miss_realmode
+#else
+	mfctr	r11
+	ld	r10,PACAKBASE(r13)
+	LOAD_HANDLER(r10, .slb_miss_realmode)
+	mtctr	r10
+	bctr
+#endif
+
+	MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt)
+	STD_EXCEPTION_PSERIES(0x600, alignment)
+	STD_EXCEPTION_PSERIES(0x700, program_check)
+	STD_EXCEPTION_PSERIES(0x800, fp_unavailable)
+	MASKABLE_EXCEPTION_PSERIES(0x900, decrementer)
+	STD_EXCEPTION_PSERIES(0xa00, trap_0a)
+	STD_EXCEPTION_PSERIES(0xb00, trap_0b)
+
+	. = 0xc00
+	.globl	system_call_pSeries
+system_call_pSeries:
+	HMT_MEDIUM
+BEGIN_FTR_SECTION
+	cmpdi	r0,0x1ebe
+	beq-	1f
+END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
+	mr	r9,r13
+	mfspr	r13,SPRN_SPRG3
+	mfspr	r11,SPRN_SRR0
+	ld	r12,PACAKBASE(r13)
+	ld	r10,PACAKMSR(r13)
+	LOAD_HANDLER(r12, system_call_entry)
+	mtspr	SPRN_SRR0,r12
+	mfspr	r12,SPRN_SRR1
+	mtspr	SPRN_SRR1,r10
+	rfid
+	b	.	/* prevent speculative execution */
+
+/* Fast LE/BE switch system call */
+1:	mfspr	r12,SPRN_SRR1
+	xori	r12,r12,MSR_LE
+	mtspr	SPRN_SRR1,r12
+	rfid		/* return to userspace */
+	b	.
+
+	STD_EXCEPTION_PSERIES(0xd00, single_step)
+	STD_EXCEPTION_PSERIES(0xe00, trap_0e)
+
+	/* We need to deal with the Altivec unavailable exception
+	 * here which is at 0xf20, thus in the middle of the
+	 * prolog code of the PerformanceMonitor one. A little
+	 * trickery is thus necessary
+	 */
+	. = 0xf00
+	b	performance_monitor_pSeries
+
+	. = 0xf20
+	b	altivec_unavailable_pSeries
+
+	. = 0xf40
+	b	vsx_unavailable_pSeries
+
+#ifdef CONFIG_CBE_RAS
+	HSTD_EXCEPTION_PSERIES(0x1200, cbe_system_error)
+#endif /* CONFIG_CBE_RAS */
+	STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint)
+#ifdef CONFIG_CBE_RAS
+	HSTD_EXCEPTION_PSERIES(0x1600, cbe_maintenance)
+#endif /* CONFIG_CBE_RAS */
+	STD_EXCEPTION_PSERIES(0x1700, altivec_assist)
+#ifdef CONFIG_CBE_RAS
+	HSTD_EXCEPTION_PSERIES(0x1800, cbe_thermal)
+#endif /* CONFIG_CBE_RAS */
+
+	. = 0x3000
+
+/*** pSeries interrupt support ***/
+
+	/* moved from 0xf00 */
+	STD_EXCEPTION_PSERIES(., performance_monitor)
+	STD_EXCEPTION_PSERIES(., altivec_unavailable)
+	STD_EXCEPTION_PSERIES(., vsx_unavailable)
+
+/*
+ * An interrupt came in while soft-disabled; clear EE in SRR1,
+ * clear paca->hard_enabled and return.
+ */
+masked_interrupt:
+	stb	r10,PACAHARDIRQEN(r13)
+	mtcrf	0x80,r9
+	ld	r9,PACA_EXGEN+EX_R9(r13)
+	mfspr	r10,SPRN_SRR1
+	rldicl	r10,r10,48,1		/* clear MSR_EE */
+	rotldi	r10,r10,16
+	mtspr	SPRN_SRR1,r10
+	ld	r10,PACA_EXGEN+EX_R10(r13)
+	mfspr	r13,SPRN_SPRG1
+	rfid
+	b	.
+
+	.align	7
+do_stab_bolted_pSeries:
+	mtcrf	0x80,r12
+	mfspr	r12,SPRN_SPRG2
+	EXCEPTION_PROLOG_PSERIES(PACA_EXSLB, .do_stab_bolted)
+
+#ifdef CONFIG_PPC_PSERIES
+/*
+ * Vectors for the FWNMI option.  Share common code.
+ */
+	.globl system_reset_fwnmi
+      .align 7
+system_reset_fwnmi:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13		/* save r13 */
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common)
+
+	.globl machine_check_fwnmi
+      .align 7
+machine_check_fwnmi:
+	HMT_MEDIUM
+	mtspr	SPRN_SPRG1,r13		/* save r13 */
+	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
+
+#endif /* CONFIG_PPC_PSERIES */
+
+#ifdef __DISABLED__
+/*
+ * This is used for when the SLB miss handler has to go virtual,
+ * which doesn't happen for now anymore but will once we re-implement
+ * dynamic VSIDs for shared page tables
+ */
+slb_miss_user_pseries:
+	std	r10,PACA_EXGEN+EX_R10(r13)
+	std	r11,PACA_EXGEN+EX_R11(r13)
+	std	r12,PACA_EXGEN+EX_R12(r13)
+	mfspr	r10,SPRG1
+	ld	r11,PACA_EXSLB+EX_R9(r13)
+	ld	r12,PACA_EXSLB+EX_R3(r13)
+	std	r10,PACA_EXGEN+EX_R13(r13)
+	std	r11,PACA_EXGEN+EX_R9(r13)
+	std	r12,PACA_EXGEN+EX_R3(r13)
+	clrrdi	r12,r13,32
+	mfmsr	r10
+	mfspr	r11,SRR0			/* save SRR0 */
+	ori	r12,r12,slb_miss_user_common@l	/* virt addr of handler */
+	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI
+	mtspr	SRR0,r12
+	mfspr	r12,SRR1			/* and SRR1 */
+	mtspr	SRR1,r10
+	rfid
+	b	.				/* prevent spec. execution */
+#endif /* __DISABLED__ */
+
+	.align	7
+	.globl	__end_interrupts
+__end_interrupts:
+
+/*
+ * Code from here down to __end_handlers is invoked from the
+ * exception prologs above.  Because the prologs assemble the
+ * addresses of these handlers using the LOAD_HANDLER macro,
+ * which uses an addi instruction, these handlers must be in
+ * the first 32k of the kernel image.
+ */
+
+/*** Common interrupt handlers ***/
+
+	STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception)
+
+	/*
+	 * Machine check is different because we use a different
+	 * save area: PACA_EXMC instead of PACA_EXGEN.
+	 */
+	.align	7
+	.globl machine_check_common
+machine_check_common:
+	EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
+	FINISH_NAP
+	DISABLE_INTS
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.machine_check_exception
+	b	.ret_from_except
+
+	STD_EXCEPTION_COMMON_LITE(0x900, decrementer, .timer_interrupt)
+	STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
+	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
+	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
+	STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
+	STD_EXCEPTION_COMMON_IDLE(0xf00, performance_monitor, .performance_monitor_exception)
+	STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
+#ifdef CONFIG_ALTIVEC
+	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception)
+#else
+	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception)
+#endif
+#ifdef CONFIG_CBE_RAS
+	STD_EXCEPTION_COMMON(0x1200, cbe_system_error, .cbe_system_error_exception)
+	STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, .cbe_maintenance_exception)
+	STD_EXCEPTION_COMMON(0x1800, cbe_thermal, .cbe_thermal_exception)
+#endif /* CONFIG_CBE_RAS */
+
+	.align	7
+system_call_entry:
+	b	system_call_common
+
+/*
+ * Here we have detected that the kernel stack pointer is bad.
+ * R9 contains the saved CR, r13 points to the paca,
+ * r10 contains the (bad) kernel stack pointer,
+ * r11 and r12 contain the saved SRR0 and SRR1.
+ * We switch to using an emergency stack, save the registers there,
+ * and call kernel_bad_stack(), which panics.
+ */
+bad_stack:
+	ld	r1,PACAEMERGSP(r13)
+	subi	r1,r1,64+INT_FRAME_SIZE
+	std	r9,_CCR(r1)
+	std	r10,GPR1(r1)
+	std	r11,_NIP(r1)
+	std	r12,_MSR(r1)
+	mfspr	r11,SPRN_DAR
+	mfspr	r12,SPRN_DSISR
+	std	r11,_DAR(r1)
+	std	r12,_DSISR(r1)
+	mflr	r10
+	mfctr	r11
+	mfxer	r12
+	std	r10,_LINK(r1)
+	std	r11,_CTR(r1)
+	std	r12,_XER(r1)
+	SAVE_GPR(0,r1)
+	SAVE_GPR(2,r1)
+	SAVE_4GPRS(3,r1)
+	SAVE_2GPRS(7,r1)
+	SAVE_10GPRS(12,r1)
+	SAVE_10GPRS(22,r1)
+	lhz	r12,PACA_TRAP_SAVE(r13)
+	std	r12,_TRAP(r1)
+	addi	r11,r1,INT_FRAME_SIZE
+	std	r11,0(r1)
+	li	r12,0
+	std	r12,0(r11)
+	ld	r2,PACATOC(r13)
+1:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.kernel_bad_stack
+	b	1b
+
+/*
+ * Here r13 points to the paca, r9 contains the saved CR,
+ * SRR0 and SRR1 are saved in r11 and r12,
+ * r9 - r13 are saved in paca->exgen.
+ */
+	.align	7
+	.globl data_access_common
+data_access_common:
+	mfspr	r10,SPRN_DAR
+	std	r10,PACA_EXGEN+EX_DAR(r13)
+	mfspr	r10,SPRN_DSISR
+	stw	r10,PACA_EXGEN+EX_DSISR(r13)
+	EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN)
+	ld	r3,PACA_EXGEN+EX_DAR(r13)
+	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
+	li	r5,0x300
+	b	.do_hash_page	 	/* Try to handle as hpte fault */
+
+	.align	7
+	.globl instruction_access_common
+instruction_access_common:
+	EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN)
+	ld	r3,_NIP(r1)
+	andis.	r4,r12,0x5820
+	li	r5,0x400
+	b	.do_hash_page		/* Try to handle as hpte fault */
+
+/*
+ * Here is the common SLB miss user that is used when going to virtual
+ * mode for SLB misses, that is currently not used
+ */
+#ifdef __DISABLED__
+	.align	7
+	.globl	slb_miss_user_common
+slb_miss_user_common:
+	mflr	r10
+	std	r3,PACA_EXGEN+EX_DAR(r13)
+	stw	r9,PACA_EXGEN+EX_CCR(r13)
+	std	r10,PACA_EXGEN+EX_LR(r13)
+	std	r11,PACA_EXGEN+EX_SRR0(r13)
+	bl	.slb_allocate_user
+
+	ld	r10,PACA_EXGEN+EX_LR(r13)
+	ld	r3,PACA_EXGEN+EX_R3(r13)
+	lwz	r9,PACA_EXGEN+EX_CCR(r13)
+	ld	r11,PACA_EXGEN+EX_SRR0(r13)
+	mtlr	r10
+	beq-	slb_miss_fault
+
+	andi.	r10,r12,MSR_RI		/* check for unrecoverable exception */
+	beq-	unrecov_user_slb
+	mfmsr	r10
+
+.machine push
+.machine "power4"
+	mtcrf	0x80,r9
+.machine pop
+
+	clrrdi	r10,r10,2		/* clear RI before setting SRR0/1 */
+	mtmsrd	r10,1
+
+	mtspr	SRR0,r11
+	mtspr	SRR1,r12
+