Merge branch 'iov_iter' into for-next

18 files changed, 178 insertions, 112 deletions

diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index a6774560afe3..493e72f64b35 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -70,39 +70,39 @@
 #define CPU_UNKNOWN		(~((u32)0))
 
 /* Utility macros */
-#define SKIP_TO_NEXT_CPU(reg_entry)			\
-({							\
-	while (reg_entry->reg_id != REG_ID("CPUEND"))	\
-		reg_entry++;				\
-	reg_entry++;					\
+#define SKIP_TO_NEXT_CPU(reg_entry)					\
+({									\
+	while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND"))	\
+		reg_entry++;						\
+	reg_entry++;							\
 })
 
 /* Kernel Dump section info */
 struct fadump_section {
-	u32	request_flag;
-	u16	source_data_type;
-	u16	error_flags;
-	u64	source_address;
-	u64	source_len;
-	u64	bytes_dumped;
-	u64	destination_address;
+	__be32	request_flag;
+	__be16	source_data_type;
+	__be16	error_flags;
+	__be64	source_address;
+	__be64	source_len;
+	__be64	bytes_dumped;
+	__be64	destination_address;
 };
 
 /* ibm,configure-kernel-dump header. */
 struct fadump_section_header {
-	u32	dump_format_version;
-	u16	dump_num_sections;
-	u16	dump_status_flag;
-	u32	offset_first_dump_section;
+	__be32	dump_format_version;
+	__be16	dump_num_sections;
+	__be16	dump_status_flag;
+	__be32	offset_first_dump_section;
 
 	/* Fields for disk dump option. */
-	u32	dd_block_size;
-	u64	dd_block_offset;
-	u64	dd_num_blocks;
-	u32	dd_offset_disk_path;
+	__be32	dd_block_size;
+	__be64	dd_block_offset;
+	__be64	dd_num_blocks;
+	__be32	dd_offset_disk_path;
 
 	/* Maximum time allowed to prevent an automatic dump-reboot. */
-	u32	max_time_auto;
+	__be32	max_time_auto;
 };
 
 /*
@@ -174,15 +174,15 @@ static inline u64 str_to_u64(const char *str)
 
 /* Register save area header. */
 struct fadump_reg_save_area_header {
-	u64		magic_number;
-	u32		version;
-	u32		num_cpu_offset;
+	__be64		magic_number;
+	__be32		version;
+	__be32		num_cpu_offset;
 };
 
 /* Register entry. */
 struct fadump_reg_entry {
-	u64		reg_id;
-	u64		reg_value;
+	__be64		reg_id;
+	__be64		reg_value;
 };
 
 /* fadump crash info structure */
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 623f2971ce0e..766b77d527ac 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -71,7 +71,7 @@ pte_t *huge_pte_offset_and_shift(struct mm_struct *mm,
 
 void flush_dcache_icache_hugepage(struct page *page);
 
-#if defined(CONFIG_PPC_MM_SLICES) || defined(CONFIG_PPC_SUBPAGE_PROT)
+#if defined(CONFIG_PPC_MM_SLICES)
 int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 			   unsigned long len);
 #else
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 7d8a60068805..ce9577d693be 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -365,3 +365,4 @@ SYSCALL_SPU(renameat2)
 SYSCALL_SPU(seccomp)
 SYSCALL_SPU(getrandom)
 SYSCALL_SPU(memfd_create)
+SYSCALL_SPU(bpf)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 4e9af3fd43e7..e0da021caa00 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define __NR_syscalls		361
+#define __NR_syscalls		362
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 0688fc06e183..f55351f2e66e 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -383,5 +383,6 @@
 #define __NR_seccomp		358
 #define __NR_getrandom		359
 #define __NR_memfd_create	360
+#define __NR_bpf		361
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 5bbd1bc8c3b0..0905c8da90f1 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -659,7 +659,13 @@ _GLOBAL(ret_from_except_lite)
 3:
 #endif
 	bl	save_nvgprs
+	/*
+	 * Use a non volatile GPR to save and restore our thread_info flags
+	 * across the call to restore_interrupts.
+	 */
+	mr	r30,r4
 	bl	restore_interrupts
+	mr	r4,r30
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_notify_resume
 	b	ret_from_except
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 742694c1d852..26d091a1a54c 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -58,7 +58,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node,
 	const __be32 *sections;
 	int i, num_sections;
 	int size;
-	const int *token;
+	const __be32 *token;
 
 	if (depth != 1 || strcmp(uname, "rtas") != 0)
 		return 0;
@@ -72,7 +72,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node,
 		return 1;
 
 	fw_dump.fadump_supported = 1;
-	fw_dump.ibm_configure_kernel_dump = *token;
+	fw_dump.ibm_configure_kernel_dump = be32_to_cpu(*token);
 
 	/*
 	 * The 'ibm,kernel-dump' rtas node is present only if there is
@@ -147,11 +147,11 @@ static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
 	memset(fdm, 0, sizeof(struct fadump_mem_struct));
 	addr = addr & PAGE_MASK;
 
-	fdm->header.dump_format_version = 0x00000001;
-	fdm->header.dump_num_sections = 3;
+	fdm->header.dump_format_version = cpu_to_be32(0x00000001);
+	fdm->header.dump_num_sections = cpu_to_be16(3);
 	fdm->header.dump_status_flag = 0;
 	fdm->header.offset_first_dump_section =
-		(u32)offsetof(struct fadump_mem_struct, cpu_state_data);
+		cpu_to_be32((u32)offsetof(struct fadump_mem_struct, cpu_state_data));
 
 	/*
 	 * Fields for disk dump option.
@@ -167,27 +167,27 @@ static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
 
 	/* Kernel dump sections */
 	/* cpu state data section. */
-	fdm->cpu_state_data.request_flag = FADUMP_REQUEST_FLAG;
-	fdm->cpu_state_data.source_data_type = FADUMP_CPU_STATE_DATA;
+	fdm->cpu_state_data.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
+	fdm->cpu_state_data.source_data_type = cpu_to_be16(FADUMP_CPU_STATE_DATA);
 	fdm->cpu_state_data.source_address = 0;
-	fdm->cpu_state_data.source_len = fw_dump.cpu_state_data_size;
-	fdm->cpu_state_data.destination_address = addr;
+	fdm->cpu_state_data.source_len = cpu_to_be64(fw_dump.cpu_state_data_size);
+	fdm->cpu_state_data.destination_address = cpu_to_be64(addr);
 	addr += fw_dump.cpu_state_data_size;
 
 	/* hpte region section */
-	fdm->hpte_region.request_flag = FADUMP_REQUEST_FLAG;
-	fdm->hpte_region.source_data_type = FADUMP_HPTE_REGION;
+	fdm->hpte_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
+	fdm->hpte_region.source_data_type = cpu_to_be16(FADUMP_HPTE_REGION);
 	fdm->hpte_region.source_address = 0;
-	fdm->hpte_region.source_len = fw_dump.hpte_region_size;
-	fdm->hpte_region.destination_address = addr;
+	fdm->hpte_region.source_len = cpu_to_be64(fw_dump.hpte_region_size);
+	fdm->hpte_region.destination_address = cpu_to_be64(addr);
 	addr += fw_dump.hpte_region_size;
 
 	/* RMA region section */
-	fdm->rmr_region.request_flag = FADUMP_REQUEST_FLAG;
-	fdm->rmr_region.source_data_type = FADUMP_REAL_MODE_REGION;
-	fdm->rmr_region.source_address = RMA_START;
-	fdm->rmr_region.source_len = fw_dump.boot_memory_size;
-	fdm->rmr_region.destination_address = addr;
+	fdm->rmr_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
+	fdm->rmr_region.source_data_type = cpu_to_be16(FADUMP_REAL_MODE_REGION);
+	fdm->rmr_region.source_address = cpu_to_be64(RMA_START);
+	fdm->rmr_region.source_len = cpu_to_be64(fw_dump.boot_memory_size);
+	fdm->rmr_region.destination_address = cpu_to_be64(addr);
 	addr += fw_dump.boot_memory_size;
 
 	return addr;
@@ -272,7 +272,7 @@ int __init fadump_reserve_mem(void)
 	 * first kernel.
 	 */
 	if (fdm_active)
-		fw_dump.boot_memory_size = fdm_active->rmr_region.source_len;
+		fw_dump.boot_memory_size = be64_to_cpu(fdm_active->rmr_region.source_len);
 	else
 		fw_dump.boot_memory_size = fadump_calculate_reserve_size();
 
@@ -314,8 +314,8 @@ int __init fadump_reserve_mem(void)
 				(unsigned long)(base >> 20));
 
 		fw_dump.fadumphdr_addr =
-				fdm_active->rmr_region.destination_address +
-				fdm_active->rmr_region.source_len;
+				be64_to_cpu(fdm_active->rmr_region.destination_address) +
+				be64_to_cpu(fdm_active->rmr_region.source_len);
 		pr_debug("fadumphdr_addr = %p\n",
 				(void *) fw_dump.fadumphdr_addr);
 	} else {
@@ -472,9 +472,9 @@ fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
 {
 	memset(regs, 0, sizeof(struct pt_regs));
 
-	while (reg_entry->reg_id != REG_ID("CPUEND")) {
-		fadump_set_regval(regs, reg_entry->reg_id,
-					reg_entry->reg_value);
+	while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) {
+		fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id),
+					be64_to_cpu(reg_entry->reg_value));
 		reg_entry++;
 	}
 	reg_entry++;
@@ -603,20 +603,20 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
 	if (!fdm->cpu_state_data.bytes_dumped)
 		return -EINVAL;
 
-	addr = fdm->cpu_state_data.destination_address;
+	addr = be64_to_cpu(fdm->cpu_state_data.destination_address);
 	vaddr = __va(addr);
 
 	reg_header = vaddr;
-	if (reg_header->magic_number != REGSAVE_AREA_MAGIC) {
+	if (be64_to_cpu(reg_header->magic_number) != REGSAVE_AREA_MAGIC) {
 		printk(KERN_ERR "Unable to read register save area.\n");
 		return -ENOENT;
 	}
 	pr_debug("--------CPU State Data------------\n");
-	pr_debug("Magic Number: %llx\n", reg_header->magic_number);
-	pr_debug("NumCpuOffset: %x\n", reg_header->num_cpu_offset);
+	pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number));
+	pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset));
 
-	vaddr += reg_header->num_cpu_offset;
-	num_cpus = *((u32 *)(vaddr));
+	vaddr += be32_to_cpu(reg_header->num_cpu_offset);
+	num_cpus = be32_to_cpu(*((__be32 *)(vaddr)));
 	pr_debug("NumCpus     : %u\n", num_cpus);
 	vaddr += sizeof(u32);
 	reg_entry = (struct fadump_reg_entry *)vaddr;
@@ -639,13 +639,13 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
 		fdh = __va(fw_dump.fadumphdr_addr);
 
 	for (i = 0; i < num_cpus; i++) {
-		if (reg_entry->reg_id != REG_ID("CPUSTRT")) {
+		if (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUSTRT")) {
 			printk(KERN_ERR "Unable to read CPU state data\n");
 			rc = -ENOENT;
 			goto error_out;
 		}
 		/* Lower 4 bytes of reg_value contains logical cpu id */
-		cpu = reg_entry->reg_value & FADUMP_CPU_ID_MASK;
+		cpu = be64_to_cpu(reg_entry->reg_value) & FADUMP_CPU_ID_MASK;
 		if (fdh && !cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) {
 			SKIP_TO_NEXT_CPU(reg_entry);
 			continue;
@@ -692,7 +692,7 @@ static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
 		return -EINVAL;
 
 	/* Check if the dump data is valid. */
-	if ((fdm_active->header.dump_status_flag == FADUMP_ERROR_FLAG) ||
+	if ((be16_to_cpu(fdm_active->header.dump_status_flag) == FADUMP_ERROR_FLAG) ||
 			(fdm_active->cpu_state_data.error_flags != 0) ||
 			(fdm_active->rmr_region.error_flags != 0)) {
 		printk(KERN_ERR "Dump taken by platform is not valid\n");
@@ -828,7 +828,7 @@ static void fadump_setup_crash_memory_ranges(void)
 static inline unsigned long fadump_relocate(unsigned long paddr)
 {
 	if (paddr > RMA_START && paddr < fw_dump.boot_memory_size)
-		return fdm.rmr_region.destination_address + paddr;
+		return be64_to_cpu(fdm.rmr_region.destination_address) + paddr;
 	else
 		return paddr;
 }
@@ -902,7 +902,7 @@ static int fadump_create_elfcore_headers(char *bufp)
 			 * to the specified destination_address. Hence set
 			 * the correct offset.
 			 */
-			phdr->p_offset = fdm.rmr_region.destination_address;
+			phdr->p_offset = be64_to_cpu(fdm.rmr_region.destination_address);
 		}
 
 		phdr->p_paddr = mbase;
@@ -951,7 +951,7 @@ static void register_fadump(void)
 
 	fadump_setup_crash_memory_ranges();
 
-	addr = fdm.rmr_region.destination_address + fdm.rmr_region.source_len;
+	addr = be64_to_cpu(fdm.rmr_region.destination_address) + be64_to_cpu(fdm.rmr_region.source_len);
 	/* Initialize fadump crash info header. */
 	addr = init_fadump_header(addr);
 	vaddr = __va(addr);
@@ -1023,7 +1023,7 @@ void fadump_cleanup(void)
 	/* Invalidate the registration only if dump is active. */
 	if (fw_dump.dump_active) {
 		init_fadump_mem_struct(&fdm,
-			fdm_active->cpu_state_data.destination_address);
+			be64_to_cpu(fdm_active->cpu_state_data.destination_address));
 		fadump_invalidate_dump(&fdm);
 	}
 }
@@ -1063,7 +1063,7 @@ static void fadump_invalidate_release_mem(void)
 		return;
 	}
 
-	destination_address = fdm_active->cpu_state_data.destination_address;
+	destination_address = be64_to_cpu(fdm_active->cpu_state_data.destination_address);
 	fadump_cleanup();
 	mutex_unlock(&fadump_mutex);
 
@@ -1183,31 +1183,31 @@ static int fadump_region_show(struct seq_file *m, void *private)
 	seq_printf(m,
 			"CPU : [%#016llx-%#016llx] %#llx bytes, "
 			"Dumped: %#llx\n",
-			fdm_ptr->cpu_state_data.destination_address,
-			fdm_ptr->cpu_state_data.destination_address +
-			fdm_ptr->cpu_state_data.source_len - 1,
-			fdm_ptr->cpu_state_data.source_len,
-			fdm_ptr->cpu_state_data.bytes_dumped);
+			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address),
+			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) +
+			be64_to_cpu(fdm_ptr->cpu_state_data.source_len) - 1,
+			be64_to_cpu(fdm_ptr->cpu_state_data.source_len),
+			be64_to_cpu(fdm_ptr->cpu_state_data.bytes_dumped));
 	seq_printf(m,
 			"HPTE: [%#016llx-%#016llx] %#llx bytes, "
 			"Dumped: %#llx\n",
-			fdm_ptr->hpte_region.destination_address,
-			fdm_ptr->hpte_region.destination_address +
-			fdm_ptr->hpte_region.source_len - 1,
-			fdm_ptr->hpte_region.source_len,
-			fdm_ptr->hpte_region.bytes_dumped);
+			be64_to_cpu(fdm_ptr->hpte_region.destination_address),
+			be64_to_cpu(fdm_ptr->hpte_region.destination_address) +
+			be64_to_cpu(fdm_ptr->hpte_region.source_len) - 1,
+			be64_to_cpu(fdm_ptr->hpte_region.source_len),
+			be64_to_cpu(fdm_ptr->hpte_region.bytes_dumped));
 	seq_printf(m,
 			"DUMP: [%#016llx-%#016llx] %#llx bytes, "
 			"Dumped: %#llx\n",
-			fdm_ptr->rmr_region.destination_address,
-			fdm_ptr->rmr_region.destination_address +
-			fdm_ptr->rmr_region.source_len - 1,
-			fdm_ptr->rmr_region.source_len,
-			fdm_ptr->rmr_region.bytes_dumped);
+			be64_to_cpu(fdm_ptr->rmr_region.destination_address),
+			be64_to_cpu(fdm_ptr->rmr_region.destination_address) +
+			be64_to_cpu(fdm_ptr->rmr_region.source_len) - 1,
+			be64_to_cpu(fdm_ptr->rmr_region.source_len),
+			be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped));
 
 	if (!fdm_active ||
 		(fw_dump.reserve_dump_area_start ==
-		fdm_ptr->cpu_state_data.destination_address))
+		be64_to_cpu(fdm_ptr->cpu_state_data.destination_address)))
 		goto out;
 
 	/* Dump is active. Show reserved memory region. */
@@ -1215,10 +1215,10 @@ static int fadump_region_show(struct seq_file *m, void *private)
 			"    : [%#016llx-%#016llx] %#llx bytes, "
 			"Dumped: %#llx\n",
 			(unsigned long long)fw_dump.reserve_dump_area_start,
-			fdm_ptr->cpu_state_data.destination_address - 1,
-			fdm_ptr->cpu_state_data.destination_address -
+			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - 1,
+			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) -
 			fw_dump.reserve_dump_area_start,
-			fdm_ptr->cpu_state_data.destination_address -
+			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) -
 			fw_dump.reserve_dump_area_start);
 out:
 	if (fdm_active)
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 0f9939e693df..5a236f082c78 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -99,8 +99,6 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 	u64 vsid;
 	int psize, ssize;
 
-	slb->esid = (ea & ESID_MASK) | SLB_ESID_V;
-
 	switch (REGION_ID(ea)) {
 	case USER_REGION_ID:
 		pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
@@ -133,6 +131,7 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 	vsid |= mmu_psize_defs[psize].sllp |
 		((ssize == MMU_SEGSIZE_1T) ? SLB_VSID_B_1T : 0);
 
+	slb->esid = (ea & (ssize == MMU_SEGSIZE_1T ? ESID_MASK_1T : ESID_MASK)) | SLB_ESID_V;
 	slb->vsid = vsid;
 
 	return 0;
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index cad68ff8eca5..415a51b028b9 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -103,7 +103,7 @@ unsigned long __max_low_memory = MAX_LOW_MEM;
 /*
  * Check for command-line options that affect what MMU_init will do.
  */
-void MMU_setup(void)
+void __init MMU_setup(void)
 {
 	/* Check for nobats option (used in mapin_ram). */
 	if (strstr(boot_command_line, "nobats")) {
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index e5236c24dc07..b9d1dfdbe5bb 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1509,11 +1509,14 @@ static int update_cpu_topology(void *data)
 	cpu = smp_processor_id();
 
 	for (update = data; update; update = update->next) {
+		int new_nid = update->new_nid;
 		if (cpu != update->cpu)
 			continue;
 
-		unmap_cpu_from_node(update->cpu);
-		map_cpu_to_node(update->cpu, update->new_nid);
+		unmap_cpu_from_node(cpu);
+		map_cpu_to_node(cpu, new_nid);
+		set_cpu_numa_node(cpu, new_nid);
+		set_cpu_numa_mem(cpu, local_memory_node(new_nid));
 		vdso_getcpu_init();
 	}
 
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 8d7bda94d196..ded0ea1afde4 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -682,6 +682,7 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 	slice_convert(mm, mask, psize);
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
 /*
  * is_hugepage_only_range() is used by generic code to verify whether
  * a normal mmap mapping (non hugetlbfs) is valid on a given area.
@@ -726,4 +727,4 @@ int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 #endif
 	return !slice_check_fit(mask, available);
 }
-
+#endif
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 6c8710dd90c9..dba34088da28 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -417,11 +417,6 @@ static int h_24x7_event_add(struct perf_event *event, int flags)
 	return 0;
 }
 
-static int h_24x7_event_idx(struct perf_event *event)
-{
-	return 0;
-}
-
 static struct pmu h_24x7_pmu = {
 	.task_ctx_nr = perf_invalid_context,
 
@@ -433,7 +428,6 @@ static struct pmu h_24x7_pmu = {
 	.start       = h_24x7_event_start,
 	.stop        = h_24x7_event_stop,
 	.read        = h_24x7_event_update,
-	.event_idx   = h_24x7_event_idx,
 };
 
 static int hv_24x7_init(void)
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 15fc76c93022..a051fe946c63 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -246,11 +246,6 @@ static int h_gpci_event_init(struct perf_event *event)
 	return 0;
 }
 
-static int h_gpci_event_idx(struct perf_event *event)
-{
-	return 0;
-}
-
 static struct pmu h_gpci_pmu = {
 	.task_ctx_nr = perf_invalid_context,
 
@@ -262,7 +257,6 @@ static struct pmu h_gpci_pmu = {
 	.start       = h_gpci_event_start,
 	.stop        = h_gpci_event_stop,
 	.read        = h_gpci_event_update,
-	.event_idx   = h_gpci_event_idx,
 };
 
 static int hv_gpci_init(void)
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index dd2c285ad170..e4169d68cb32 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -191,7 +191,6 @@ static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf,
 {
 	struct lpc_debugfs_entry *lpc = filp->private_data;
 	u32 data, pos, len, todo;
-	__be32 bedata;
 	int rc;
 
 	if (!access_ok(VERIFY_WRITE, ubuf, count))
@@ -214,18 +213,57 @@ static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf,
 				len = 2;
 		}
 		rc = opal_lpc_read(opal_lpc_chip_id, lpc->lpc_type, pos,
-				   &bedata, len);
+				   &data, len);
 		if (rc)
 			return -ENXIO;
-		data = be32_to_cpu(bedata);
+
+		/*
+		 * Now there is some trickery with the data returned by OPAL
+		 * as it's the desired data right justified in a 32-bit BE
+		 * word.
+		 *
+		 * This is a very bad interface and I'm to blame for it :-(
+		 *
+		 * So we can't just apply a 32-bit swap to what comes from OPAL,
+		 * because user space expects the *bytes* to be in their proper
+		 * respective positions (ie, LPC position).
+		 *
+		 * So what we really want to do here is to shift data right
+		 * appropriately on a LE kernel.
+		 *
+		 * IE. If the LPC transaction has bytes B0, B1, B2 and B3 in that
+		 * order, we have in memory written to by OPAL at the "data"
+		 * pointer:
+		 *
+		 *               Bytes:      OPAL "data"   LE "data"
+		 *   32-bit:   B0 B1 B2 B3   B0B1B2B3      B3B2B1B0
+		 *   16-bit:   B0 B1         0000B0B1      B1B00000
+		 *    8-bit:   B0            000000B0      B0000000
+		 *
+		 * So a BE kernel will have the leftmost of the above in the MSB
+		 * and rightmost in the LSB and can just then "cast" the u32 "data"
+		 * down to the appropriate quantity and write it.
+		 *
+		 * However, an LE kernel can't. It doesn't need to swap because a
+		 * load from data followed by a store to user are going to preserve
+		 * the byte ordering which is the wire byte order which is what the
+		 * user wants, but in order to "crop" to the right size, we need to
+		 * shift right first.
+		 */
 		switch(len) {
 		case 4:
 			rc = __put_user((u32)data, (u32 __user *)ubuf);
 			break;
 		case 2:
+#ifdef __LITTLE_ENDIAN__
+			data >>= 16;
+#endif
 			rc = __put_user((u16)data, (u16 __user *)ubuf);
 			break;
 		default:
+#ifdef __LITTLE_ENDIAN__
+			data >>= 24;
+#endif
 			rc = __put_user((u8)data, (u8 __user *)ubuf);
 			break;
 		}
@@ -265,12 +303,31 @@ static ssize_t lpc_debug_write(struct file *filp, const char __user *ubuf,
 			else if (todo > 1 && (pos & 1) == 0)
 				len = 2;
 		}
+
+		/*
+		 * Similarly to the read case, we have some trickery here but
+		 * it's different to handle. We need to pass the value to OPAL in
+		 * a register whose layout depends on the access size. We want
+		 * to reproduce the memory layout of the user, however we aren't
+		 * doing a load from user and a store to another memory location
+		 * which would achieve that. Here we pass the value to OPAL via
+		 * a register which is expected to contain the "BE" interpretation
+		 * of the byte sequence. IE: for a 32-bit access, byte 0 should be
+		 * in the MSB. So here we *do* need to byteswap on LE.
+		 *
+		 *           User bytes:    LE "data"  OPAL "data"
+		 *  32-bit:  B0 B1 B2 B3    B3B2B1B0   B0B1B2B3
+		 *  16-bit:  B0 B1          0000B1B0   0000B0B1
+		 *   8-bit:  B0             000000B0   000000B0
+		 */
 		switch(len) {
 		case 4:
 			rc = __get_user(data, (u32 __user *)ubuf);
+			data = cpu_to_be32(data);
 			break;
 		case 2:
 			rc = __get_user(data, (u16 __user *)ubuf);
+			data = cpu_to_be16(data);
 			break;
 		default:
 			rc = __get_user(data, (u8 __user *)ubuf);
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index e9e2450c1fdd..feb549aa3eea 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -58,7 +58,7 @@ END_FTR_SECTION(0, 1);						\
  */
 
 #define OPAL_CALL(name, token)		\
- _GLOBAL(name);				\
+ _GLOBAL_TOC(name);			\
 	mflr	r0;			\
 	std	r0,16(r1);		\
 	li	r0,token;		\
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 6ad83bd11fe2..c22bb1b4beb8 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -382,7 +382,7 @@ static int dlpar_online_cpu(struct device_node *dn)
 			BUG_ON(get_cpu_current_state(cpu)
 					!= CPU_STATE_OFFLINE);
 			cpu_maps_update_done();
-			rc = cpu_up(cpu);
+			rc = device_online(get_cpu_device(cpu));
 			if (rc)
 				goto out;
 			cpu_maps_update_begin();
@@ -467,7 +467,7 @@ static int dlpar_offline_cpu(struct device_node *dn)
 			if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
 				set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
 				cpu_maps_update_done();
-				rc = cpu_down(cpu);
+				rc = device_offline(get_cpu_device(cpu));
 				if (rc)
 					goto out;
 				cpu_maps_update_begin();
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 8c509d5397c6..f6880d2a40fb 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -43,6 +43,7 @@
 #include <asm/trace.h>
 #include <asm/firmware.h>
 #include <asm/plpar_wrappers.h>
+#include <asm/fadump.h>
 
 #include "pseries.h"
 
@@ -247,8 +248,17 @@ static void pSeries_lpar_hptab_clear(void)
 	}
 
 #ifdef __LITTLE_ENDIAN__
-	/* Reset exceptions to big endian */
-	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
+	/*
+	 * Reset exceptions to big endian.
+	 *
+	 * FIXME this is a hack for kexec, we need to reset the exception
+	 * endian before starting the new kernel and this is a convenient place
+	 * to do it.
+	 *
+	 * This is also called on boot when a fadump happens. In that case we
+	 * must not change the exception endian mode.
+	 */
+	if (firmware_has_feature(FW_FEATURE_SET_MODE) && !is_fadump_active()) {
 		long rc;
 
 		rc = pseries_big_endian_exceptions();
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index de40b48b460e..da08ed088157 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -361,7 +361,7 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 	cascade_data->virq = virt_msir;
 	msi->cascade_array[irq_index] = cascade_data;
 
-	ret = request_irq(virt_msir, fsl_msi_cascade, 0,
+	ret = request_irq(virt_msir, fsl_msi_cascade, IRQF_NO_THREAD,
 			  "fsl-msi-cascade", cascade_data);
 	if (ret) {
 		dev_err(&dev->dev, "failed to request_irq(%d), ret = %d\n",