diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index e27e9ad6818e..150866b2a3fe 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -134,6 +134,7 @@ static inline int dma_supported(struct device *dev, u64 mask)
 }
 
 extern int dma_set_mask(struct device *dev, u64 dma_mask);
+extern int __dma_set_mask(struct device *dev, u64 dma_mask);
 
 #define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
 
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index f7a8036579b5..42632c7a2a4e 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -77,6 +77,7 @@ struct iommu_table {
 #ifdef CONFIG_IOMMU_API
 	struct iommu_group *it_group;
 #endif
+	void (*set_bypass)(struct iommu_table *tbl, bool enable);
 };
 
 /* Pure 2^n version of get_order */
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 4ee06fe15de4..d0e784e0ff48 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -8,6 +8,7 @@
 
 #ifdef __powerpc64__
 
+extern char __start_interrupts[];
 extern char __end_interrupts[];
 
 extern char __prom_init_toc_start[];
@@ -21,6 +22,17 @@ static inline int in_kernel_text(unsigned long addr)
 	return 0;
 }
 
+static inline int overlaps_interrupt_vector_text(unsigned long start,
+							unsigned long end)
+{
+	unsigned long real_start, real_end;
+	real_start = __start_interrupts - _stext;
+	real_end = __end_interrupts - _stext;
+
+	return start < (unsigned long)__va(real_end) &&
+		(unsigned long)__va(real_start) < end;
+}
+
 static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
 {
 	return start < (unsigned long)__init_end &&
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 8032b97ccdcb..ee78f6e49d64 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -191,12 +191,10 @@ EXPORT_SYMBOL(dma_direct_ops);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
 
-int dma_set_mask(struct device *dev, u64 dma_mask)
+int __dma_set_mask(struct device *dev, u64 dma_mask)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-	if (ppc_md.dma_set_mask)
-		return ppc_md.dma_set_mask(dev, dma_mask);
 	if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL))
 		return dma_ops->set_dma_mask(dev, dma_mask);
 	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
@@ -204,6 +202,12 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
 	*dev->dma_mask = dma_mask;
 	return 0;
 }
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (ppc_md.dma_set_mask)
+		return ppc_md.dma_set_mask(dev, dma_mask);
+	return __dma_set_mask(dev, dma_mask);
+}
 EXPORT_SYMBOL(dma_set_mask);
 
 u64 dma_get_required_mask(struct device *dev)
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 7bb30dca4e19..fdc679d309ec 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -362,9 +362,13 @@ static void *eeh_rmv_device(void *data, void *userdata)
 	 */
 	if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
 		return NULL;
+
 	driver = eeh_pcid_get(dev);
-	if (driver && driver->err_handler)
-		return NULL;
+	if (driver) {
+		eeh_pcid_put(dev);
+		if (driver->err_handler)
+			return NULL;
+	}
 
 	/* Remove it from PCI subsystem */
 	pr_debug("EEH: Removing %s without EEH sensitive driver\n",
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index d773dd440a45..88e3ec6e1d96 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1088,6 +1088,14 @@ int iommu_take_ownership(struct iommu_table *tbl)
 	memset(tbl->it_map, 0xff, sz);
 	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
 
+	/*
+	 * Disable iommu bypass, otherwise the user can DMA to all of
+	 * our physical memory via the bypass window instead of just
+	 * the pages that has been explicitly mapped into the iommu
+	 */
+	if (tbl->set_bypass)
+		tbl->set_bypass(tbl, false);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iommu_take_ownership);
@@ -1102,6 +1110,10 @@ void iommu_release_ownership(struct iommu_table *tbl)
 	/* Restore bit#0 set by iommu_init_table() */
 	if (tbl->it_offset == 0)
 		set_bit(0, tbl->it_map);
+
+	/* The kernel owns the device now, we can restore the iommu bypass */
+	if (tbl->set_bypass)
+		tbl->set_bypass(tbl, true);
 }
 EXPORT_SYMBOL_GPL(iommu_release_ownership);
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 9729b23bfb0a..1d0848bba049 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -559,8 +559,13 @@ void exc_lvl_ctx_init(void)
 #ifdef CONFIG_PPC64
 		cpu_nr = i;
 #else
+#ifdef CONFIG_SMP
 		cpu_nr = get_hard_smp_processor_id(i);
+#else
+		cpu_nr = 0;
 #endif
+#endif
+
 		memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE);
 		tp = critirq_ctx[cpu_nr];
 		tp->cpu = cpu_nr;
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index 75d4f7340da8..015ae55c1868 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -196,7 +196,9 @@ int overlaps_crashkernel(unsigned long start, unsigned long size)
 
 /* Values we need to export to the second kernel via the device tree. */
 static phys_addr_t kernel_end;
+static phys_addr_t crashk_base;
 static phys_addr_t crashk_size;
+static unsigned long long mem_limit;
 
 static struct property kernel_end_prop = {
 	.name = "linux,kernel-end",
@@ -207,7 +209,7 @@ static struct property kernel_end_prop = {
 static struct property crashk_base_prop = {
 	.name = "linux,crashkernel-base",
 	.length = sizeof(phys_addr_t),
-	.value = &crashk_res.start,
+	.value = &crashk_base
 };
 
 static struct property crashk_size_prop = {
@@ -219,9 +221,11 @@ static struct property crashk_size_prop = {
 static struct property memory_limit_prop = {
 	.name = "linux,memory-limit",
 	.length = sizeof(unsigned long long),
-	.value = &memory_limit,
+	.value = &mem_limit,
 };
 
+#define cpu_to_be_ulong	__PASTE(cpu_to_be, BITS_PER_LONG)
+
 static void __init export_crashk_values(struct device_node *node)
 {
 	struct property *prop;
@@ -237,8 +241,9 @@ static void __init export_crashk_values(struct device_node *node)
 		of_remove_property(node, prop);
 
 	if (crashk_res.start != 0) {
+		crashk_base = cpu_to_be_ulong(crashk_res.start),
 		of_add_property(node, &crashk_base_prop);
-		crashk_size = resource_size(&crashk_res);
+		crashk_size = cpu_to_be_ulong(resource_size(&crashk_res));
 		of_add_property(node, &crashk_size_prop);
 	}
 
@@ -246,6 +251,7 @@ static void __init export_crashk_values(struct device_node *node)
 	 * memory_limit is required by the kexec-tools to limit the
 	 * crash regions to the actual memory used.
 	 */
+	mem_limit = cpu_to_be_ulong(memory_limit);
 	of_update_property(node, &memory_limit_prop);
 }
 
@@ -264,7 +270,7 @@ static int __init kexec_setup(void)
 		of_remove_property(node, prop);
 
 	/* information needed by userspace when using default_machine_kexec */
-	kernel_end = __pa(_end);
+	kernel_end = cpu_to_be_ulong(__pa(_end));
 	of_add_property(node, &kernel_end_prop);
 
 	export_crashk_values(node);
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index be4e6d648f60..59d229a2a3e0 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -369,6 +369,7 @@ void default_machine_kexec(struct kimage *image)
 
 /* Values we need to export to the second kernel via the device tree. */
 static unsigned long htab_base;
+static unsigned long htab_size;
 
 static struct property htab_base_prop = {
 	.name = "linux,htab-base",
@@ -379,7 +380,7 @@ static struct property htab_base_prop = {
 static struct property htab_size_prop = {
 	.name = "linux,htab-size",
 	.length = sizeof(unsigned long),
-	.value = &htab_size_bytes,
+	.value = &htab_size,
 };
 
 static int __init export_htab_values(void)
@@ -403,8 +404,9 @@ static int __init export_htab_values(void)
 	if (prop)
 		of_remove_property(node, prop);
 
-	htab_base = __pa(htab_address);
+	htab_base = cpu_to_be64(__pa(htab_address));
 	of_add_property(node, &htab_base_prop);
+	htab_size = cpu_to_be64(htab_size_bytes);
 	of_add_property(node, &htab_size_prop);
 
 	of_node_put(node);
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index b47a0e1ab001..1482327cfeba 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -69,8 +69,8 @@ _GLOBAL(relocate)
 	 * R_PPC64_RELATIVE ones.
 	 */
 	mtctr	r8
-5:	lwz	r0,12(9)	/* ELF64_R_TYPE(reloc->r_info) */
-	cmpwi	r0,R_PPC64_RELATIVE
+5:	ld	r0,8(9)		/* ELF64_R_TYPE(reloc->r_info) */
+	cmpdi	r0,R_PPC64_RELATIVE
 	bne	6f
 	ld	r6,0(r9)	/* reloc->r_offset */
 	ld	r0,16(r9)	/* reloc->r_addend */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 2b0da27eaee4..04cc4fcca78b 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -247,7 +247,12 @@ static void __init exc_lvl_early_init(void)
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
 	 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */
 	for_each_possible_cpu(i) {
+#ifdef CONFIG_SMP
 		hw_cpu = get_hard_smp_processor_id(i);
+#else
+		hw_cpu = 0;
+#endif
+
 		critirq_ctx[hw_cpu] = (struct thread_info *)
 			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 #ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index de6881259aef..d766d6ee33fe 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -207,6 +207,20 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		if (overlaps_kernel_text(vaddr, vaddr + step))
 			tprot &= ~HPTE_R_N;
 
+		/*
+		 * If relocatable, check if it overlaps interrupt vectors that
+		 * are copied down to real 0. For relocatable kernel
+		 * (e.g. kdump case) we copy interrupt vectors down to real
+		 * address 0. Mark that region as executable. This is
+		 * because on p8 system with relocation on exception feature
+		 * enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence
+		 * in order to execute the interrupt handlers in virtual
+		 * mode the vector region need to be marked as executable.
+		 */
+		if ((PHYSICAL_START > MEMORY_START) &&
+			overlaps_interrupt_vector_text(vaddr, vaddr + step))
+				tprot &= ~HPTE_R_N;
+
 		hash = hpt_hash(vpn, shift, ssize);
 		hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 29b89e863d7c..67cf22083f4c 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1147,6 +1147,9 @@ static void power_pmu_enable(struct pmu *pmu)
 	mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
 
 	mb();
+	if (cpuhw->bhrb_users)
+		ppmu->config_bhrb(cpuhw->bhrb_filter);
+
 	write_mmcr0(cpuhw, mmcr0);
 
 	/*
@@ -1158,8 +1161,6 @@ static void power_pmu_enable(struct pmu *pmu)
 	}
 
  out:
-	if (cpuhw->bhrb_users)
-		ppmu->config_bhrb(cpuhw->bhrb_filter);
 
 	local_irq_restore(flags);
 }
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index a3f7abd2f13f..96cee20dcd34 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -25,6 +25,37 @@
 #define PM_BRU_FIN			0x10068
 #define PM_BR_MPRED_CMPL		0x400f6
 
+/* All L1 D cache load references counted at finish, gated by reject */
+#define PM_LD_REF_L1			0x100ee
+/* Load Missed L1 */
+#define PM_LD_MISS_L1			0x3e054
+/* Store Missed L1 */
+#define PM_ST_MISS_L1			0x300f0
+/* L1 cache data prefetches */
+#define PM_L1_PREF			0x0d8b8
+/* Instruction fetches from L1 */
+#define PM_INST_FROM_L1			0x04080
+/* Demand iCache Miss */
+#define PM_L1_ICACHE_MISS		0x200fd
+/* Instruction Demand sectors wriittent into IL1 */
+#define PM_L1_DEMAND_WRITE		0x0408c
+/* Instruction prefetch written into IL1 */
+#define PM_IC_PREF_WRITE		0x0408e
+/* The data cache was reloaded from local core's L3 due to a demand load */
+#define PM_DATA_FROM_L3			0x4c042
+/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */
+#define PM_DATA_FROM_L3MISS		0x300fe
+/* All successful D-side store dispatches for this thread */
+#define PM_L2_ST			0x17080
+/* All successful D-side store dispatches for this thread that were L2 Miss */
+#define PM_L2_ST_MISS			0x17082
+/* Total HW L3 prefetches(Load+store) */
+#define PM_L3_PREF_ALL			0x4e052
+/* Data PTEG reload */
+#define PM_DTLB_MISS			0x300fc
+/* ITLB Reloaded */
+#define PM_ITLB_MISS			0x400fc
+
 
 /*
  * Raw event encoding for POWER8:
@@ -557,6 +588,8 @@ static int power8_generic_events[] = {
 	[PERF_COUNT_HW_INSTRUCTIONS] =			PM_INST_CMPL,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PM_BRU_FIN,
 	[PERF_COUNT_HW_BRANCH_MISSES] =			PM_BR_MPRED_CMPL,
+	[PERF_COUNT_HW_CACHE_REFERENCES] =		PM_LD_REF_L1,
+	[PERF_COUNT_HW_CACHE_MISSES] =			PM_LD_MISS_L1,
 };
 
 static u64 power8_bhrb_filter_map(u64 branch_sample_type)
@@ -596,6 +629,116 @@ static void power8_config_bhrb(u64 pmu_bhrb_filter)
 	mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter));
 }
 
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[ C(L1D) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_LD_REF_L1,
+			[ C(RESULT_MISS)   ] = PM_LD_MISS_L1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ST_MISS_L1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_PREF,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(L1I) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_INST_FROM_L1,
+			[ C(RESULT_MISS)   ] = PM_L1_ICACHE_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_DEMAND_WRITE,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_IC_PREF_WRITE,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(LL) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_DATA_FROM_L3,
+			[ C(RESULT_MISS)   ] = PM_DATA_FROM_L3MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L2_ST,
+			[ C(RESULT_MISS)   ] = PM_L2_ST_MISS,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(DTLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_DTLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(ITLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ITLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(BPU) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_BRU_FIN,
+			[ C(RESULT_MISS)   ] = PM_BR_MPRED_CMPL,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(NODE) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+};
+
+#undef C
+
 static struct power_pmu power8_pmu = {
 	.name			= "POWER8",
 	.n_counter		= 6,
@@ -611,6 +754,7 @@ static struct power_pmu power8_pmu = {
 	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
+	.cache_events		= &power8_cache_events,
 	.attr_groups		= power8_pmu_attr_groups,
 	.bhrb_nr		= 32,
 };
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 7d6dcc6d5fa9..3b2b4fb3585b 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -21,6 +21,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>
+#include <linux/memblock.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -460,9 +461,39 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 		return;
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
+	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
 	set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
 }
 
+static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
+				     struct pci_dev *pdev, u64 dma_mask)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	struct pnv_ioda_pe *pe;
+	uint64_t top;
+	bool bypass = false;
+
+	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
+		return -ENODEV;;
+
+	pe = &phb->ioda.pe_array[pdn->pe_number];
+	if (pe->tce_bypass_enabled) {
+		top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
+		bypass = (dma_mask >= top);
+	}
+
+	if (bypass) {
+		dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n");
+		set_dma_ops(&pdev->dev, &dma_direct_ops);
+		set_dma_offset(&pdev->dev, pe->tce_bypass_base);
+	} else {
+		dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
+		set_dma_ops(&pdev->dev, &dma_iommu_ops);
+		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+	}
+	return 0;
+}
+
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 {
 	struct pci_dev *dev;
@@ -657,6 +688,56 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 		__free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
 }
 
+static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
+{
+	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
+					      tce32_table);
+	uint16_t window_id = (pe->pe_number << 1 ) + 1;
+	int64_t rc;
+
+	pe_info(pe, "%sabling 64-bit DMA bypass\n", enable ? "En" : "Dis");
+	if (enable) {
+		phys_addr_t top = memblock_end_of_DRAM();
+
+		top = roundup_pow_of_two(top);
+		rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+						     pe->pe_number,
+						     window_id,
+						     pe->tce_bypass_base,
+						     top);
+	} else {
+		rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+						     pe->pe_number,
+						     window_id,
+						     pe->tce_bypass_base,
+						     0);
+
+		/*
+		 * We might want to reset the DMA ops of all devices on
+		 * this PE. However in theory, that shouldn't be necessary
+		 * as this is used for VFIO/KVM pass-through and the device
+		 * hasn't yet been returned to its kernel driver
+		 */
+	}
+	if (rc)
+		pe_err(pe, "OPAL error %lld configuring bypass window\n", rc);
+	else
+		pe->tce_bypass_enabled = enable;
+}
+
+static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
+					  struct pnv_ioda_pe *pe)
+{
+	/* TVE #1 is selected by PCI address bit 59 */
+	pe->tce_bypass_base = 1ull << 59;
+
+	/* Install set_bypass callback for VFIO */
+	pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
+
+	/* Enable bypass by default */
+	pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
+}
+
 static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 				       struct pnv_ioda_pe *pe)
 {
@@ -727,6 +808,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	else
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
+	/* Also create a bypass window */
+	pnv_pci_ioda2_setup_bypass_pe(phb, pe);
 	return;
 fail:
 	if (pe->tce32_seg >= 0)
@@ -1286,6 +1369,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
+	phb->dma_set_mask = pnv_pci_ioda_dma_set_mask;
 
 	/* Setup shutdown function for kexec */
 	phb->shutdown = pnv_pci_ioda_shutdown;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b555ebc57ef5..95633d79ef5d 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -634,6 +634,16 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 		pnv_pci_dma_fallback_setup(hose, pdev);
 }
 
+int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	if (phb && phb->dma_set_mask)
+		return phb->dma_set_mask(phb, pdev, dma_mask);
+	return __dma_set_mask(&pdev->dev, dma_mask);
+}
+
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 13f1942a9a5f..cde169442775 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -54,7 +54,9 @@ struct pnv_ioda_pe {
 	struct iommu_table	tce32_table;
 	phys_addr_t		tce_inval_reg_phys;
 
-	/* XXX TODO: Add support for additional 64-bit iommus */
+	/* 64-bit TCE bypass region */
+	bool			tce_bypass_enabled;
+	uint64_t		tce_bypass_base;
 
 	/* MSIs. MVE index is identical for for 32 and 64 bit MSI
 	 * and -1 if not supported. (It's actually identical to the
@@ -113,6 +115,8 @@ struct pnv_phb {
 			 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);
+	int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev,
+			    u64 dma_mask);
 	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);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index de6819be1f95..0051e108ef0f 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -7,12 +7,20 @@ extern void pnv_smp_init(void);
 static inline void pnv_smp_init(void) { }
 #endif
 
+struct pci_dev;
+
 #ifdef CONFIG_PCI
 extern void pnv_pci_init(void);
 extern void pnv_pci_shutdown(void);
+extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask);
 #else
 static inline void pnv_pci_init(void) { }
 static inline void pnv_pci_shutdown(void) { }
+
+static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+	return -ENODEV;
+}
 #endif
 
 extern void pnv_lpc_init(void);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 21166f65c97c..110f4fbd319f 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -27,6 +27,7 @@
 #include <linux/interrupt.h>
 #include <linux/bug.h>
 #include <linux/cpuidle.h>
+#include <linux/pci.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
@@ -141,6 +142,13 @@ static void pnv_progress(char *s, unsigned short hex)
 {
 }
 
+static int pnv_dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (dev_is_pci(dev))
+		return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask);
+	return __dma_set_mask(dev, dma_mask);
+}
+
 static void pnv_shutdown(void)
 {
 	/* Let the PCI code clear up IODA tables */
@@ -238,6 +246,7 @@ define_machine(powernv) {
 	.machine_shutdown	= pnv_shutdown,
 	.power_save             = powernv_idle,
 	.calibrate_decr		= generic_calibrate_decr,
+	.dma_set_mask		= pnv_dma_set_mask,
 #ifdef CONFIG_KEXEC
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
 #endif
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 37300f6ee244..80b1d57c306a 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -20,6 +20,7 @@ config PPC_PSERIES
 	select PPC_DOORBELL
 	select HAVE_CONTEXT_TRACKING
 	select HOTPLUG_CPU if SMP
+	select ARCH_RANDOM
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 8e639d7cbda7..972df0ffd4dc 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -430,8 +430,7 @@ static void pSeries_machine_kexec(struct kimage *image)
 {
 	long rc;
 
-	if (firmware_has_feature(FW_FEATURE_SET_MODE) &&
-	    (image->type != KEXEC_TYPE_CRASH)) {
+	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
 		rc = pSeries_disable_reloc_on_exc();
 		if (rc != H_SUCCESS)
 			pr_warning("Warning: Failed to disable relocation on "
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 0e166ed4cd16..8209744b2829 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -886,25 +886,25 @@ int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 
 	/* Default: read HW settings */
 	if (flow_type == IRQ_TYPE_DEFAULT) {
-		switch(vold & (MPIC_INFO(VECPRI_POLARITY_MASK) |
-			       MPIC_INFO(VECPRI_SENSE_MASK))) {
-			case MPIC_INFO(VECPRI_SENSE_EDGE) |
-			     MPIC_INFO(VECPRI_POLARITY_POSITIVE):
-				flow_type = IRQ_TYPE_EDGE_RISING;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_EDGE) |
-			     MPIC_INFO(VECPRI_POLARITY_NEGATIVE):
-				flow_type = IRQ_TYPE_EDGE_FALLING;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_LEVEL) |
-			     MPIC_INFO(VECPRI_POLARITY_POSITIVE):
-				flow_type = IRQ_TYPE_LEVEL_HIGH;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_LEVEL) |
-			     MPIC_INFO(VECPRI_POLARITY_NEGATIVE):
-				flow_type = IRQ_TYPE_LEVEL_LOW;
-				break;
-		}
+		int vold_ps;
+
+		vold_ps = vold & (MPIC_INFO(VECPRI_POLARITY_MASK) |
+				  MPIC_INFO(VECPRI_SENSE_MASK));
+
+		if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) |
+				MPIC_INFO(VECPRI_POLARITY_POSITIVE)))
+			flow_type = IRQ_TYPE_EDGE_RISING;
+		else if	(vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) |
+				     MPIC_INFO(VECPRI_POLARITY_NEGATIVE)))
+			flow_type = IRQ_TYPE_EDGE_FALLING;
+		else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) |
+				     MPIC_INFO(VECPRI_POLARITY_POSITIVE)))
+			flow_type = IRQ_TYPE_LEVEL_HIGH;
+		else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) |
+				     MPIC_INFO(VECPRI_POLARITY_NEGATIVE)))
+			flow_type = IRQ_TYPE_LEVEL_LOW;
+		else
+			WARN_ONCE(1, "mpic: unknown IRQ type %d\n", vold);
 	}
 
 	/* Apply to irq desc */
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index a90731b3d44a..b07909850f77 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -309,16 +309,23 @@ static void get_output_lock(void)
 
 	if (xmon_speaker == me)
 		return;
+
 	for (;;) {
-		if (xmon_speaker == 0) {
-			last_speaker = cmpxchg(&xmon_speaker, 0, me);
-			if (last_speaker == 0)
-				return;
-		}
-		timeout = 10000000;
+		last_speaker = cmpxchg(&xmon_speaker, 0, me);
+		if (last_speaker == 0)
+			return;
+
+		/*
+		 * Wait a full second for the lock, we might be on a slow
+		 * console, but check every 100us.
+		 */
+		timeout = 10000;
 		while (xmon_speaker == last_speaker) {
-			if (--timeout > 0)
+			if (--timeout > 0) {
+				udelay(100);
 				continue;
+			}
+
 			/* hostile takeover */
 			prev = cmpxchg(&xmon_speaker, last_speaker, me);
 			if (prev == last_speaker)
@@ -397,7 +404,6 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 	}
 
 	xmon_fault_jmp[cpu] = recurse_jmp;
-	cpumask_set_cpu(cpu, &cpus_in_xmon);
 
 	bp = NULL;
 	if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT))
@@ -419,6 +425,8 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 		release_output_lock();
 	}
 
+	cpumask_set_cpu(cpu, &cpus_in_xmon);
+
  waiting:
 	secondary = 1;
 	while (secondary && !xmon_gate) {
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index 6c4c000671c5..1e5481d88a26 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -158,6 +158,15 @@ static inline unsigned long nx842_get_scatterlist_size(
 	return sl->entry_nr * sizeof(struct nx842_slentry);
 }
 
+static inline unsigned long nx842_get_pa(void *addr)
+{
+	if (is_vmalloc_addr(addr))
+		return page_to_phys(vmalloc_to_page(addr))
+		       + offset_in_page(addr);
+	else
+		return __pa(addr);
+}
+
 static int nx842_build_scatterlist(unsigned long buf, int len,
 			struct nx842_scatterlist *sl)
 {
@@ -168,7 +177,7 @@ static int nx842_build_scatterlist(unsigned long buf, int len,
 
 	entry = sl->entries;
 	while (len) {
-		entry->ptr = __pa(buf);
+		entry->ptr = nx842_get_pa((void *)buf);
 		nextpage = ALIGN(buf + 1, NX842_HW_PAGE_SIZE);
 		if (nextpage < buf + len) {
 			/* we aren't at the end yet */
@@ -370,8 +379,8 @@ int nx842_compress(const unsigned char *in, unsigned int inlen,
 	op.flags = NX842_OP_COMPRESS;
 	csbcpb = &workmem->csbcpb;
 	memset(csbcpb, 0, sizeof(*csbcpb));
-	op.csbcpb = __pa(csbcpb);
-	op.out = __pa(slout.entries);
+	op.csbcpb = nx842_get_pa(csbcpb);
+	op.out = nx842_get_pa(slout.entries);
 
 	for (i = 0; i < hdr->blocks_nr; i++) {
 		/*
@@ -401,13 +410,13 @@ int nx842_compress(const unsigned char *in, unsigned int inlen,
 		 */
 		if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) {
 			/* Create direct DDE */
-			op.in = __pa(inbuf);
+			op.in = nx842_get_pa((void *)inbuf);
 			op.inlen = max_sync_size;
 
 		} else {
 			/* Create indirect DDE (scatterlist) */
 			nx842_build_scatterlist(inbuf, max_sync_size, &slin);
-			op.in = __pa(slin.entries);
+			op.in = nx842_get_pa(slin.entries);
 			op.inlen = -nx842_get_scatterlist_size(&slin);
 		}
 
@@ -565,7 +574,7 @@ int nx842_decompress(const unsigned char *in, unsigned int inlen,
 	op.flags = NX842_OP_DECOMPRESS;
 	csbcpb = &workmem->csbcpb;
 	memset(csbcpb, 0, sizeof(*csbcpb));
-	op.csbcpb = __pa(csbcpb);
+	op.csbcpb = nx842_get_pa(csbcpb);
 
 	/*
 	 * max_sync_size may have changed since compression,
@@ -597,12 +606,12 @@ int nx842_decompress(const unsigned char *in, unsigned int inlen,
 		if (likely((inbuf & NX842_HW_PAGE_MASK) ==
 			((inbuf + hdr->sizes[i] - 1) & NX842_HW_PAGE_MASK))) {
 			/* Create direct DDE */
-			op.in = __pa(inbuf);
+			op.in = nx842_get_pa((void *)inbuf);
 			op.inlen = hdr->sizes[i];
 		} else {
 			/* Create indirect DDE (scatterlist) */
 			nx842_build_scatterlist(inbuf, hdr->sizes[i] , &slin);
-			op.in = __pa(slin.entries);
+			op.in = nx842_get_pa(slin.entries);
 			op.inlen = -nx842_get_scatterlist_size(&slin);
 		}
 
@@ -613,12 +622,12 @@ int nx842_decompress(const unsigned char *in, unsigned int inlen,
 		 */
 		if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) {
 			/* Create direct DDE */
-			op.out = __pa(outbuf);
+			op.out = nx842_get_pa((void *)outbuf);
 			op.outlen = max_sync_size;
 		} else {
 			/* Create indirect DDE (scatterlist) */
 			nx842_build_scatterlist(outbuf, max_sync_size, &slout);
-			op.out = __pa(slout.entries);
+			op.out = nx842_get_pa(slout.entries);
 			op.outlen = -nx842_get_scatterlist_size(&slout);
 		}