715 files changed, 9645 insertions, 6523 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 5a1779c93940..1455579791ec 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -319,13 +319,6 @@ config ARCH_WANT_OLD_COMPAT_IPC
         select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
         bool
 
-config HAVE_VIRT_TO_BUS
-        bool
-        help
-          An architecture should select this if it implements the
-          deprecated interface virt_to_bus().  All new architectures
-          should probably not select this.
-
 config HAVE_ARCH_SECCOMP_FILTER
         bool
         help
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 5833aa441481..8a33ba01301f 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -9,7 +9,7 @@ config ALPHA
         select HAVE_PERF_EVENTS
         select HAVE_DMA_ATTRS
         select HAVE_GENERIC_HARDIRQS
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select GENERIC_IRQ_PROBE
         select AUTO_IRQ_AFFINITY if SMP
         select GENERIC_IRQ_SHOW
diff --git a/arch/alpha/Makefile b/arch/alpha/Makefile
index 4759fe751aa1..2cc3cc519c54 100644
--- a/arch/alpha/Makefile
+++ b/arch/alpha/Makefile
@@ -12,7 +12,7 @@ NM := $(NM) -B
 
 LDFLAGS_vmlinux := -static -N #-relax
 CHECKFLAGS      += -D__alpha__ -m64
-cflags-y        := -pipe -mno-fp-regs -ffixed-8 -msmall-data
+cflags-y        := -pipe -mno-fp-regs -ffixed-8
 cflags-y        += $(call cc-option, -fno-jump-tables)
 
 cpuflags-$(CONFIG_ALPHA_EV4)            := -mcpu=ev4
diff --git a/arch/alpha/include/asm/floppy.h b/arch/alpha/include/asm/floppy.h
index 46cefbd50e73..bae97eb19d26 100644
--- a/arch/alpha/include/asm/floppy.h
+++ b/arch/alpha/include/asm/floppy.h
@@ -26,7 +26,7 @@
 #define fd_disable_irq()        disable_irq(FLOPPY_IRQ)
 #define fd_cacheflush(addr,size) /* nothing */
 #define fd_request_irq()        request_irq(FLOPPY_IRQ, floppy_interrupt,\
-                                            IRQF_DISABLED, "floppy", NULL)
+                                            0, "floppy", NULL)
 #define fd_free_irq()           free_irq(FLOPPY_IRQ, NULL)
 
 #ifdef CONFIG_PCI
diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h
index 1f8c72959fb6..52cd2a4a3ff4 100644
--- a/arch/alpha/include/asm/thread_info.h
+++ b/arch/alpha/include/asm/thread_info.h
@@ -95,8 +95,6 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #define TS_POLLING              0x0010  /* idle task polling need_resched,
                                            skip sending interrupt */
 
-#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
-
 #ifndef __ASSEMBLY__
 #define HAVE_SET_RESTORE_SIGMASK        1
 static inline void set_restore_sigmask(void)
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index 2872accd2215..7b2be251c30f 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -117,13 +117,6 @@ handle_irq(int irq)
                 return;
         }
 
-        /*
-         * From here we must proceed with IPL_MAX. Note that we do not
-         * explicitly enable interrupts afterwards - some MILO PALcode
-         * (namely LX164 one) seems to have severe problems with RTI
-         * at IPL 0.
-         */
-        local_irq_disable();
         irq_enter();
         generic_handle_irq_desc(irq, desc);
         irq_exit();
diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c
index 772ddfdb71a8..f433fc11877a 100644
--- a/arch/alpha/kernel/irq_alpha.c
+++ b/arch/alpha/kernel/irq_alpha.c
@@ -45,6 +45,14 @@ do_entInt(unsigned long type, unsigned long vector,
           unsigned long la_ptr, struct pt_regs *regs)
 {
         struct pt_regs *old_regs;
+
+        /*
+         * Disable interrupts during IRQ handling.
+         * Note that there is no matching local_irq_enable() due to
+         * severe problems with RTI at IPL0 and some MILO PALcode
+         * (namely LX164).
+         */
+        local_irq_disable();
         switch (type) {
         case 0:
 #ifdef CONFIG_SMP
@@ -62,7 +70,6 @@ do_entInt(unsigned long type, unsigned long vector,
           {
                 long cpu;
 
-                local_irq_disable();
                 smp_percpu_timer_interrupt(regs);
                 cpu = smp_processor_id();
                 if (cpu != boot_cpuid) {
@@ -222,7 +229,6 @@ process_mcheck_info(unsigned long vector, unsigned long la_ptr,
 
 struct irqaction timer_irqaction = {
         .handler        = timer_interrupt,
-        .flags          = IRQF_DISABLED,
         .name           = "timer",
 };
 
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 63d27fb9b023..a3fd8a29ccac 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -46,25 +46,6 @@
 void (*pm_power_off)(void) = machine_power_off;
 EXPORT_SYMBOL(pm_power_off);
 
-void
-cpu_idle(void)
-{
-        current_thread_info()->status |= TS_POLLING;
-
-        while (1) {
-                /* FIXME -- EV6 and LCA45 know how to power down
-                   the CPU.  */
-
-                rcu_idle_enter();
-                while (!need_resched())
-                        cpu_relax();
-
-                rcu_idle_exit();
-                schedule_preempt_disabled();
-        }
-}
-
-
 struct halt_info {
         int mode;
         char *restart_cmd;
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 9603bc234b47..7b60834fb4b2 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -167,8 +167,7 @@ smp_callin(void)
               cpuid, current, current->active_mm));
 
         preempt_disable();
-        /* Do nothing.  */
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 /* Wait until hwrpb->txrdy is clear for cpu.  Return -1 on timeout.  */
diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 4d4c046f708d..1d4aabfcf9a1 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -185,9 +185,12 @@ nautilus_machine_check(unsigned long vector, unsigned long la_ptr)
         mb();
 }
 
-extern void free_reserved_mem(void *, void *);
 extern void pcibios_claim_one_bus(struct pci_bus *);
 
+static struct resource irongate_io = {
+        .name   = "Irongate PCI IO",
+        .flags  = IORESOURCE_IO,
+};
 static struct resource irongate_mem = {
         .name   = "Irongate PCI MEM",
         .flags  = IORESOURCE_MEM,
@@ -209,6 +212,7 @@ nautilus_init_pci(void)
 
         irongate = pci_get_bus_and_slot(0, 0);
         bus->self = irongate;
+        bus->resource[0] = &irongate_io;
         bus->resource[1] = &irongate_mem;
 
         pci_bus_size_bridges(bus);
@@ -234,8 +238,8 @@ nautilus_init_pci(void)
         if (pci_mem < memtop)
                 memtop = pci_mem;
         if (memtop > alpha_mv.min_mem_address) {
-                free_reserved_mem(__va(alpha_mv.min_mem_address),
-                                  __va(memtop));
+                free_reserved_area((unsigned long)__va(alpha_mv.min_mem_address),
+                                   (unsigned long)__va(memtop), 0, NULL);
                 printk("nautilus_init_pci: %ldk freed\n",
                         (memtop - alpha_mv.min_mem_address) >> 10);
         }
diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c
index 5cf4a481b8c5..a53cf03f49d5 100644
--- a/arch/alpha/kernel/sys_titan.c
+++ b/arch/alpha/kernel/sys_titan.c
@@ -280,15 +280,15 @@ titan_late_init(void)
          * all reported to the kernel as machine checks, so the handler
          * is a nop so it can be called to count the individual events.
          */
-        titan_request_irq(63+16, titan_intr_nop, IRQF_DISABLED,
+        titan_request_irq(63+16, titan_intr_nop, 0,
                     "CChip Error", NULL);
-        titan_request_irq(62+16, titan_intr_nop, IRQF_DISABLED,
+        titan_request_irq(62+16, titan_intr_nop, 0,
                     "PChip 0 H_Error", NULL);
-        titan_request_irq(61+16, titan_intr_nop, IRQF_DISABLED,
+        titan_request_irq(61+16, titan_intr_nop, 0,
                     "PChip 1 H_Error", NULL);
-        titan_request_irq(60+16, titan_intr_nop, IRQF_DISABLED,
+        titan_request_irq(60+16, titan_intr_nop, 0,
                     "PChip 0 C_Error", NULL);
-        titan_request_irq(59+16, titan_intr_nop, IRQF_DISABLED,
+        titan_request_irq(59+16, titan_intr_nop, 0,
                     "PChip 1 C_Error", NULL);
 
         /* 
@@ -348,9 +348,9 @@ privateer_init_pci(void)
          * Hook a couple of extra err interrupts that the
          * common titan code won't.
          */
-        titan_request_irq(53+16, titan_intr_nop, IRQF_DISABLED,
+        titan_request_irq(53+16, titan_intr_nop, 0,
                     "NMI", NULL);
-        titan_request_irq(50+16, titan_intr_nop, IRQF_DISABLED,
+        titan_request_irq(50+16, titan_intr_nop, 0,
                     "Temperature Warning", NULL);
 
         /*
diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c
index 1ad6ca74bed2..0ba85ee4a466 100644
--- a/arch/alpha/mm/init.c
+++ b/arch/alpha/mm/init.c
@@ -31,6 +31,7 @@
 #include <asm/console.h>
 #include <asm/tlb.h>
 #include <asm/setup.h>
+#include <asm/sections.h>
 
 extern void die_if_kernel(char *,struct pt_regs *,long);
 
@@ -281,8 +282,6 @@ printk_memory_info(void)
 {
         unsigned long codesize, reservedpages, datasize, initsize, tmp;
         extern int page_is_ram(unsigned long) __init;
-        extern char _text, _etext, _data, _edata;
-        extern char __init_begin, __init_end;
 
         /* printk all informations */
         reservedpages = 0;
@@ -318,32 +317,15 @@ mem_init(void)
 #endif /* CONFIG_DISCONTIGMEM */
 
 void
-free_reserved_mem(void *start, void *end)
-{
-        void *__start = start;
-        for (; __start < end; __start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(__start));
-                init_page_count(virt_to_page(__start));
-                free_page((long)__start);
-                totalram_pages++;
-        }
-}
-
-void
 free_initmem(void)
 {
-        extern char __init_begin, __init_end;
-
-        free_reserved_mem(&__init_begin, &__init_end);
-        printk ("Freeing unused kernel memory: %ldk freed\n",
-                (&__init_end - &__init_begin) >> 10);
+        free_initmem_default(0);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void
 free_initrd_mem(unsigned long start, unsigned long end)
 {
-        free_reserved_mem((void *)start, (void *)end);
-        printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
+        free_reserved_area(start, end, 0, "initrd");
 }
 #endif
diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c
index 3973ae395772..33885048fa36 100644
--- a/arch/alpha/mm/numa.c
+++ b/arch/alpha/mm/numa.c
@@ -17,6 +17,7 @@
 
 #include <asm/hwrpb.h>
 #include <asm/pgalloc.h>
+#include <asm/sections.h>
 
 pg_data_t node_data[MAX_NUMNODES];
 EXPORT_SYMBOL(node_data);
@@ -325,8 +326,6 @@ void __init mem_init(void)
 {
         unsigned long codesize, reservedpages, datasize, initsize, pfn;
         extern int page_is_ram(unsigned long) __init;
-        extern char _text, _etext, _data, _edata;
-        extern char __init_begin, __init_end;
         unsigned long nid, i;
         high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
 
diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h
index 31f77aec0823..45b8e0cea176 100644
--- a/arch/arc/include/asm/dma-mapping.h
+++ b/arch/arc/include/asm/dma-mapping.h
@@ -126,7 +126,7 @@ dma_map_sg(struct device *dev, struct scatterlist *sg,
         int i;
 
         for_each_sg(sg, s, nents, i)
-                sg->dma_address = dma_map_page(dev, sg_page(s), s->offset,
+                s->dma_address = dma_map_page(dev, sg_page(s), s->offset,
                                                s->length, dir);
 
         return nents;
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index f4c8d36ebecb..a26282857683 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -72,7 +72,4 @@ extern int elf_check_arch(const struct elf32_hdr *);
  */
 #define ELF_PLATFORM    (NULL)
 
-#define SET_PERSONALITY(ex) \
-        set_personality(PER_LINUX | (current->personality & (~PER_MASK)))
-
 #endif
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index 23daa326fc9b..eb2ae53187d9 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -415,7 +415,7 @@
  *-------------------------------------------------------------*/
 .macro SAVE_ALL_EXCEPTION   marker
 
-        st      \marker, [sp, 8]
+        st      \marker, [sp, 8]        /* orig_r8 */
         st      r0, [sp, 4]    /* orig_r0, needed only for sys calls */
 
         /* Restore r9 used to code the early prologue */
diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h
index ccd84806b62f..eac071668201 100644
--- a/arch/arc/include/asm/irqflags.h
+++ b/arch/arc/include/asm/irqflags.h
@@ -39,7 +39,7 @@ static inline long arch_local_irq_save(void)
         "       flag.nz %0              \n"
         : "=r"(temp), "=r"(flags)
         : "n"((STATUS_E1_MASK | STATUS_E2_MASK))
-        : "cc");
+        : "memory", "cc");
 
         return flags;
 }
@@ -53,7 +53,8 @@ static inline void arch_local_irq_restore(unsigned long flags)
         __asm__ __volatile__(
         "       flag %0                 \n"
         :
-        : "r"(flags));
+        : "r"(flags)
+        : "memory");
 }
 
 /*
@@ -73,7 +74,8 @@ static inline void arch_local_irq_disable(void)
         "       and %0, %0, %1          \n"
         "       flag %0                 \n"
         : "=&r"(temp)
-        : "n"(~(STATUS_E1_MASK | STATUS_E2_MASK)));
+        : "n"(~(STATUS_E1_MASK | STATUS_E2_MASK))
+        : "memory");
 }
 
 /*
@@ -85,7 +87,9 @@ static inline long arch_local_save_flags(void)
 
         __asm__ __volatile__(
         "       lr  %0, [status32]      \n"
-        : "=&r"(temp));
+        : "=&r"(temp)
+        :
+        : "memory");
 
         return temp;
 }
diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h
index f3c4934f0ca9..4930957ca3d3 100644
--- a/arch/arc/include/asm/kgdb.h
+++ b/arch/arc/include/asm/kgdb.h
@@ -13,7 +13,7 @@
 
 #ifdef CONFIG_KGDB
 
-#include <asm/user.h>
+#include <asm/ptrace.h>
 
 /* to ensure compatibility with Linux 2.6.35, we don't implement the get/set
  * register API yet */
@@ -53,9 +53,7 @@ enum arc700_linux_regnums {
 };
 
 #else
-static inline void kgdb_trap(struct pt_regs *regs, int param)
-{
-}
+#define kgdb_trap(regs, param)
 #endif
 
 #endif  /* __ARC_KGDB_H__ */
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 8ae783d20a81..6179de7e07c2 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -123,7 +123,7 @@ static inline long regs_return_value(struct pt_regs *regs)
 #define orig_r8_IS_SCALL                0x0001
 #define orig_r8_IS_SCALL_RESTARTED      0x0002
 #define orig_r8_IS_BRKPT                0x0004
-#define orig_r8_IS_EXCPN                0x0004
+#define orig_r8_IS_EXCPN                0x0008
 #define orig_r8_IS_IRQ1                 0x0010
 #define orig_r8_IS_IRQ2                 0x0020
 
diff --git a/arch/arc/include/asm/syscalls.h b/arch/arc/include/asm/syscalls.h
index e53a5340ba4f..dd785befe7fd 100644
--- a/arch/arc/include/asm/syscalls.h
+++ b/arch/arc/include/asm/syscalls.h
@@ -16,8 +16,6 @@
 #include <linux/types.h>
 
 int sys_clone_wrapper(int, int, int, int, int);
-int sys_fork_wrapper(void);
-int sys_vfork_wrapper(void);
 int sys_cacheflush(uint32_t, uint32_t uint32_t);
 int sys_arc_settls(void *);
 int sys_arc_gettls(void);
diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
index 6afa4f702075..30333cec0fef 100644
--- a/arch/arc/include/uapi/asm/ptrace.h
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -28,14 +28,14 @@
 */
 struct user_regs_struct {
 
-        struct scratch {
+        struct {
                 long pad;
                 long bta, lp_start, lp_end, lp_count;
                 long status32, ret, blink, fp, gp;
                 long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
                 long sp;
         } scratch;
-        struct callee {
+        struct {
                 long pad;
                 long r25, r24, r23, r22, r21, r20;
                 long r19, r18, r17, r16, r15, r14, r13;
diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c
index 2f390289a792..d14764ae2c60 100644
--- a/arch/arc/kernel/disasm.c
+++ b/arch/arc/kernel/disasm.c
@@ -535,4 +535,4 @@ int __kprobes disasm_next_pc(unsigned long pc, struct pt_regs *regs,
         return instr.is_branch;
 }
 
-#endif /* CONFIG_KGDB || CONFIG_MISALIGN_ACCESS || CONFIG_KPROBES */
+#endif /* CONFIG_KGDB || CONFIG_ARC_MISALIGN_ACCESS || CONFIG_KPROBES */
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index ef6800ba2f03..91eeab81f52d 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -452,7 +452,7 @@ tracesys:
         ; using ERET won't work since next-PC has already committed
         lr  r12, [efa]
         GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r11
-        st  r12, [r11, THREAD_FAULT_ADDR]
+        st  r12, [r11, THREAD_FAULT_ADDR]       ; thread.fault_address
 
         ; PRE Sys Call Ptrace hook
         mov r0, sp                      ; pt_regs needed
@@ -792,31 +792,6 @@ ARC_EXIT ret_from_fork
 
 ;################### Special Sys Call Wrappers ##########################
 
-; TBD: call do_fork directly from here
-ARC_ENTRY sys_fork_wrapper
-        SAVE_CALLEE_SAVED_USER
-        bl  @sys_fork
-        DISCARD_CALLEE_SAVED_USER
-
-        GET_CURR_THR_INFO_FLAGS   r10
-        btst r10, TIF_SYSCALL_TRACE
-        bnz  tracesys_exit
-
-        b ret_from_system_call
-ARC_EXIT sys_fork_wrapper
-
-ARC_ENTRY sys_vfork_wrapper
-        SAVE_CALLEE_SAVED_USER
-        bl  @sys_vfork
-        DISCARD_CALLEE_SAVED_USER
-
-        GET_CURR_THR_INFO_FLAGS   r10
-        btst r10, TIF_SYSCALL_TRACE
-        bnz  tracesys_exit
-
-        b ret_from_system_call
-ARC_EXIT sys_vfork_wrapper
-
 ARC_ENTRY sys_clone_wrapper
         SAVE_CALLEE_SAVED_USER
         bl  @sys_clone
diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c
index 2888ba5be47e..52bdc83c1495 100644
--- a/arch/arc/kernel/kgdb.c
+++ b/arch/arc/kernel/kgdb.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/kgdb.h>
+#include <linux/sched.h>
 #include <asm/disasm.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 0a7531d99294..cad66851e0c4 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -41,37 +41,12 @@ SYSCALL_DEFINE0(arc_gettls)
         return task_thread_info(current)->thr_ptr;
 }
 
-static inline void arch_idle(void)
+void arch_cpu_idle(void)
 {
         /* sleep, but enable all interrupts before committing */
         __asm__("sleep 0x3");
 }
 
-void cpu_idle(void)
-{
-        /* Since we SLEEP in idle loop, TIF_POLLING_NRFLAG can't be set */
-
-        /* endless idle loop with no priority at all */
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-
-doze:
-                local_irq_disable();
-                if (!need_resched()) {
-                        arch_idle();
-                        goto doze;
-                } else {
-                        local_irq_enable();
-                }
-
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-
-                schedule_preempt_disabled();
-        }
-}
-
 asmlinkage void ret_from_fork(void);
 
 /* Layout of Child kernel mode stack as setup at the end of this function is
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index dc0f968dae0a..2d95ac07df7b 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -232,10 +232,8 @@ char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 
         n += scnprintf(buf + n, len - n, "\n");
 
-#ifdef _ASM_GENERIC_UNISTD_H
         n += scnprintf(buf + n, len - n,
-                       "OS ABI [v2]\t: asm-generic/{unistd,stat,fcntl}\n");
-#endif
+                       "OS ABI [v3]\t: no-legacy-syscalls\n");
 
         return buf;
 }
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 3af3e06dcf02..5c7fd603d216 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -141,7 +141,7 @@ void __cpuinit start_kernel_secondary(void)
 
         local_irq_enable();
         preempt_disable();
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 /*
diff --git a/arch/arc/kernel/sys.c b/arch/arc/kernel/sys.c
index f6bdd07583f3..9d6c1ca26af6 100644
--- a/arch/arc/kernel/sys.c
+++ b/arch/arc/kernel/sys.c
@@ -6,8 +6,6 @@
 #include <asm/syscalls.h>
 
 #define sys_clone       sys_clone_wrapper
-#define sys_fork        sys_fork_wrapper
-#define sys_vfork       sys_vfork_wrapper
 
 #undef __SYSCALL
 #define __SYSCALL(nr, call) [nr] = (call),
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index caf797de23fc..727d4794ea0f 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -144,37 +144,18 @@ void __init mem_init(void)
                 PAGES_TO_KB(reserved_pages));
 }
 
-static void __init free_init_pages(const char *what, unsigned long begin,
-                                   unsigned long end)
-{
-        unsigned long addr;
-
-        pr_info("Freeing %s: %ldk [%lx] to [%lx]\n",
-                what, TO_KB(end - begin), begin, end);
-
-        /* need to check that the page we free is not a partial page */
-        for (addr = begin; addr + PAGE_SIZE <= end; addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-}
-
 /*
  * free_initmem: Free all the __init memory.
  */
 void __init_refok free_initmem(void)
 {
-        free_init_pages("unused kernel memory",
-                        (unsigned long)__init_begin,
-                        (unsigned long)__init_end);
+        free_initmem_default(0);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-        free_init_pages("initrd memory", start, end);
+        free_reserved_area(start, end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/arc/plat-arcfpga/Kconfig b/arch/arc/plat-arcfpga/Kconfig
index b41e786cdbc0..295cefeb25d3 100644
--- a/arch/arc/plat-arcfpga/Kconfig
+++ b/arch/arc/plat-arcfpga/Kconfig
@@ -53,7 +53,7 @@ menuconfig ARC_HAS_BVCI_LAT_UNIT
         bool "BVCI Bus Latency Unit"
         depends on ARC_BOARD_ML509 || ARC_BOARD_ANGEL4
         help
-          IP to add artifical latency to BVCI Bus Based FPGA builds.
+          IP to add artificial latency to BVCI Bus Based FPGA builds.
           The default latency (even worst case) for FPGA is non-realistic
           (~10 SDRAM, ~5 SSRAM).
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 5b714695b01b..a39e3214ea3d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -15,6 +15,7 @@ config ARM
         select GENERIC_IRQ_SHOW
         select GENERIC_PCI_IOMAP
         select GENERIC_SMP_IDLE_THREAD
+        select GENERIC_IDLE_POLL_SETUP
         select GENERIC_STRNCPY_FROM_USER
         select GENERIC_STRNLEN_USER
         select HARDIRQS_SW_RESEND
@@ -49,7 +50,6 @@ config ARM
         select HAVE_REGS_AND_STACK_ACCESS_API
         select HAVE_SYSCALL_TRACEPOINTS
         select HAVE_UID16
-        select HAVE_VIRT_TO_BUS
         select KTIME_SCALAR
         select PERF_USE_VMALLOC
         select RTC_LIB
@@ -550,13 +550,14 @@ config ARCH_IXP4XX
         select GENERIC_CLOCKEVENTS
         select MIGHT_HAVE_PCI
         select NEED_MACH_IO_H
+        select USB_EHCI_BIG_ENDIAN_MMIO
+        select USB_EHCI_BIG_ENDIAN_DESC
         help
           Support for Intel's IXP4XX (XScale) family of processors.
 
 config ARCH_DOVE
         bool "Marvell Dove"
         select ARCH_REQUIRE_GPIOLIB
-        select COMMON_CLK_DOVE
         select CPU_V7
         select GENERIC_CLOCKEVENTS
         select MIGHT_HAVE_PCI
@@ -744,6 +745,7 @@ config ARCH_RPC
         select NEED_MACH_IO_H
         select NEED_MACH_MEMORY_H
         select NO_IOPORT
+        select VIRT_TO_BUS
         help
           On the Acorn Risc-PC, Linux can support the internal IDE disk and
           CD-ROM interface, serial and parallel port, and the floppy drive.
@@ -879,6 +881,7 @@ config ARCH_SHARK
         select ISA_DMA
         select NEED_MACH_MEMORY_H
         select PCI
+        select VIRT_TO_BUS
         select ZONE_DMA
         help
           Support for the StrongARM based Digital DNARD machine, also known
@@ -1006,12 +1009,12 @@ config ARCH_MULTI_V4_V5
         bool
 
 config ARCH_MULTI_V6
-        bool "ARMv6 based platforms (ARM11, Scorpion, ...)"
+        bool "ARMv6 based platforms (ARM11)"
         select ARCH_MULTI_V6_V7
         select CPU_V6
 
 config ARCH_MULTI_V7
-        bool "ARMv7 based platforms (Cortex-A, PJ4, Krait)"
+        bool "ARMv7 based platforms (Cortex-A, PJ4, Scorpion, Krait)"
         default y
         select ARCH_MULTI_V6_V7
         select ARCH_VEXPRESS
@@ -1183,9 +1186,9 @@ config ARM_NR_BANKS
         default 8
 
 config IWMMXT
-        bool "Enable iWMMXt support"
+        bool "Enable iWMMXt support" if !CPU_PJ4
         depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_PJ4
-        default y if PXA27x || PXA3xx || ARCH_MMP
+        default y if PXA27x || PXA3xx || ARCH_MMP || CPU_PJ4
         help
           Enable support for iWMMXt context switching at run time if
           running on a CPU that supports it.
@@ -1439,6 +1442,16 @@ config ARM_ERRATA_775420
          to deadlock. This workaround puts DSB before executing ISB if
          an abort may occur on cache maintenance.
 
+config ARM_ERRATA_798181
+        bool "ARM errata: TLBI/DSB failure on Cortex-A15"
+        depends on CPU_V7 && SMP
+        help
+          On Cortex-A15 (r0p0..r3p2) the TLBI*IS/DSB operations are not
+          adequately shooting down all use of the old entries. This
+          option enables the Linux kernel workaround for this erratum
+          which sends an IPI to the CPUs that are running the same ASID
+          as the one being invalidated.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
@@ -1462,10 +1475,6 @@ config ISA_DMA
         bool
         select ISA_DMA_API
 
-config ARCH_NO_VIRT_TO_BUS
-        def_bool y
-        depends on !ARCH_RPC && !ARCH_NETWINDER && !ARCH_SHARK
-
 # Select ISA DMA interface
 config ISA_DMA_API
         bool
@@ -1657,13 +1666,16 @@ config LOCAL_TIMERS
           accounting to be spread across the timer interval, preventing a
           "thundering herd" at every timer tick.
 
+# The GPIO number here must be sorted by descending number. In case of
+# a multiplatform kernel, we just want the highest value required by the
+# selected platforms.
 config ARCH_NR_GPIO
         int
         default 1024 if ARCH_SHMOBILE || ARCH_TEGRA
-        default 355 if ARCH_U8500
-        default 264 if MACH_H4700
         default 512 if SOC_OMAP5
+        default 355 if ARCH_U8500
         default 288 if ARCH_VT8500 || ARCH_SUNXI
+        default 264 if MACH_H4700
         default 0
         help
           Maximum number of GPIOs in the system.
@@ -1887,8 +1899,9 @@ config XEN_DOM0
 
 config XEN
         bool "Xen guest support on ARM (EXPERIMENTAL)"
-        depends on ARM && OF
+        depends on ARM && AEABI && OF
         depends on CPU_V7 && !CPU_V6
+        depends on !GENERIC_ATOMIC64
         help
           Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.
 
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index acddddac7ee4..9b31f4311ea2 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -492,9 +492,10 @@ config DEBUG_IMX_UART_PORT
                                                 DEBUG_IMX31_UART || \
                                                 DEBUG_IMX35_UART || \
                                                 DEBUG_IMX51_UART || \
-                                                DEBUG_IMX50_IMX53_UART || \
+                                                DEBUG_IMX53_UART || \
                                                 DEBUG_IMX6Q_UART
         default 1
+        depends on ARCH_MXC
         help
           Choose UART port on which kernel low-level debug messages
           should be output.
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 71768b8a1ab9..84aa2caf07ed 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -115,4 +115,4 @@ i:
         $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
         $(obj)/Image System.map "$(INSTALL_PATH)"
 
-subdir-     := bootp compressed
+subdir-     := bootp compressed dts
diff --git a/arch/arm/boot/dts/armada-370-mirabox.dts b/arch/arm/boot/dts/armada-370-mirabox.dts
index dd0c57dd9f30..3234875824dc 100644
--- a/arch/arm/boot/dts/armada-370-mirabox.dts
+++ b/arch/arm/boot/dts/armada-370-mirabox.dts
@@ -54,7 +54,7 @@
                 };
 
                 mvsdio@d00d4000 {
-                        pinctrl-0 = <&sdio_pins2>;
+                        pinctrl-0 = <&sdio_pins3>;
                         pinctrl-names = "default";
                         status = "okay";
                         /*
diff --git a/arch/arm/boot/dts/armada-370-rd.dts b/arch/arm/boot/dts/armada-370-rd.dts
index f8e4855bc9a5..070bba4f2585 100644
--- a/arch/arm/boot/dts/armada-370-rd.dts
+++ b/arch/arm/boot/dts/armada-370-rd.dts
@@ -64,5 +64,13 @@
                         status = "okay";
                         /* No CD or WP GPIOs */
                 };
+
+                usb@d0050000 {
+                        status = "okay";
+                };
+
+                usb@d0051000 {
+                        status = "okay";
+                };
         };
 };
diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 6f1acc75e155..5b708208b607 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -31,7 +31,6 @@
         mpic: interrupt-controller@d0020000 {
               compatible = "marvell,mpic";
               #interrupt-cells = <1>;
-              #address-cells = <1>;
               #size-cells = <1>;
               interrupt-controller;
         };
@@ -54,7 +53,7 @@
                                 reg = <0xd0012000 0x100>;
                                 reg-shift = <2>;
                                 interrupts = <41>;
-                                reg-io-width = <4>;
+                                reg-io-width = <1>;
                                 status = "disabled";
                 };
                 serial@d0012100 {
@@ -62,7 +61,7 @@
                                 reg = <0xd0012100 0x100>;
                                 reg-shift = <2>;
                                 interrupts = <42>;
-                                reg-io-width = <4>;
+                                reg-io-width = <1>;
                                 status = "disabled";
                 };
 
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index 8188d138020e..a195debb67d3 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -59,6 +59,12 @@
                                              "mpp50", "mpp51", "mpp52";
                               marvell,function = "sd0";
                         };
+
+                        sdio_pins3: sdio-pins3 {
+                              marvell,pins = "mpp48", "mpp49", "mpp50",
+                                             "mpp51", "mpp52", "mpp53";
+                              marvell,function = "sd0";
+                        };
                 };
 
                 gpio0: gpio@d0018100 {
diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
index 1443949c165e..ca00d8326c87 100644
--- a/arch/arm/boot/dts/armada-xp.dtsi
+++ b/arch/arm/boot/dts/armada-xp.dtsi
@@ -46,7 +46,7 @@
                                 reg = <0xd0012200 0x100>;
                                 reg-shift = <2>;
                                 interrupts = <43>;
-                                reg-io-width = <4>;
+                                reg-io-width = <1>;
                                 status = "disabled";
                 };
                 serial@d0012300 {
@@ -54,7 +54,7 @@
                                 reg = <0xd0012300 0x100>;
                                 reg-shift = <2>;
                                 interrupts = <44>;
-                                reg-io-width = <4>;
+                                reg-io-width = <1>;
                                 status = "disabled";
                 };
 
diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi
index cb7bcc51608d..39253b9aedd1 100644
--- a/arch/arm/boot/dts/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/at91sam9260.dtsi
@@ -322,6 +322,24 @@
                                         };
                                 };
 
+                                spi0 {
+                                        pinctrl_spi0: spi0-0 {
+                                                atmel,pins =
+                                                        <0 0 0x1 0x0    /* PA0 periph A SPI0_MISO pin */
+                                                         0 1 0x1 0x0    /* PA1 periph A SPI0_MOSI pin */
+                                                         0 2 0x1 0x0>;  /* PA2 periph A SPI0_SPCK pin */
+                                        };
+                                };
+
+                                spi1 {
+                                        pinctrl_spi1: spi1-0 {
+                                                atmel,pins =
+                                                        <1 0 0x1 0x0    /* PB0 periph A SPI1_MISO pin */
+                                                         1 1 0x1 0x0    /* PB1 periph A SPI1_MOSI pin */
+                                                         1 2 0x1 0x0>;  /* PB2 periph A SPI1_SPCK pin */
+                                        };
+                                };
+
                                 pioA: gpio@fffff400 {
                                         compatible = "atmel,at91rm9200-gpio";
                                         reg = <0xfffff400 0x200>;
@@ -471,6 +489,28 @@
                                 status = "disabled";
                         };
 
+                        spi0: spi@fffc8000 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "atmel,at91rm9200-spi";
+                                reg = <0xfffc8000 0x200>;
+                                interrupts = <12 4 3>;
+                                pinctrl-names = "default";
+                                pinctrl-0 = <&pinctrl_spi0>;
+                                status = "disabled";
+                        };
+
+                        spi1: spi@fffcc000 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "atmel,at91rm9200-spi";
+                                reg = <0xfffcc000 0x200>;
+                                interrupts = <13 4 3>;
+                                pinctrl-names = "default";
+                                pinctrl-0 = <&pinctrl_spi1>;
+                                status = "disabled";
+                        };
+
                         adc0: adc@fffe0000 {
                                 compatible = "atmel,at91sam9260-adc";
                                 reg = <0xfffe0000 0x100>;
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index 271d4de026e9..94b58ab2cc08 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -303,6 +303,24 @@
                                         };
                                 };
 
+                                spi0 {
+                                        pinctrl_spi0: spi0-0 {
+                                                atmel,pins =
+                                                        <0 0 0x2 0x0    /* PA0 periph B SPI0_MISO pin */
+                                                         0 1 0x2 0x0    /* PA1 periph B SPI0_MOSI pin */
+                                                         0 2 0x2 0x0>;  /* PA2 periph B SPI0_SPCK pin */
+                                        };
+                                };
+
+                                spi1 {
+                                        pinctrl_spi1: spi1-0 {
+                                                atmel,pins =
+                                                        <1 12 0x1 0x0   /* PB12 periph A SPI1_MISO pin */
+                                                         1 13 0x1 0x0   /* PB13 periph A SPI1_MOSI pin */
+                                                         1 14 0x1 0x0>; /* PB14 periph A SPI1_SPCK pin */
+                                        };
+                                };
+
                                 pioA: gpio@fffff200 {
                                         compatible = "atmel,at91rm9200-gpio";
                                         reg = <0xfffff200 0x200>;
@@ -462,6 +480,28 @@
                                 reg = <0xfffffd40 0x10>;
                                 status = "disabled";
                         };
+
+                        spi0: spi@fffa4000 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "atmel,at91rm9200-spi";
+                                reg = <0xfffa4000 0x200>;
+                                interrupts = <14 4 3>;
+                                pinctrl-names = "default";
+                                pinctrl-0 = <&pinctrl_spi0>;
+                                status = "disabled";
+                        };
+
+                        spi1: spi@fffa8000 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "atmel,at91rm9200-spi";
+                                reg = <0xfffa8000 0x200>;
+                                interrupts = <15 4 3>;
+                                pinctrl-names = "default";
+                                pinctrl-0 = <&pinctrl_spi1>;
+                                status = "disabled";
+                        };
                 };
 
                 nand0: nand@40000000 {
diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts
index 1eb08728f527..a14e424b2e81 100644
--- a/arch/arm/boot/dts/at91sam9263ek.dts
+++ b/arch/arm/boot/dts/at91sam9263ek.dts
@@ -79,6 +79,16 @@
                                         };
                                 };
                         };
+
+                        spi0: spi@fffa4000 {
+                                status = "okay";
+                                cs-gpios = <&pioA 5 0>, <0>, <0>, <0>;
+                                mtd_dataflash@0 {
+                                        compatible = "atmel,at45", "atmel,dataflash";
+                                        spi-max-frequency = <50000000>;
+                                        reg = <0>;
+                                };
+                        };
                 };
 
                 nand0: nand@40000000 {
diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
index da15e83e7f17..23d1f468f27f 100644
--- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
+++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
@@ -96,6 +96,16 @@
                                 status = "okay";
                                 pinctrl-0 = <&pinctrl_ssc0_tx>;
                         };
+
+                        spi0: spi@fffc8000 {
+                                status = "okay";
+                                cs-gpios = <0>, <&pioC 11 0>, <0>, <0>;
+                                mtd_dataflash@0 {
+                                        compatible = "atmel,at45", "atmel,dataflash";
+                                        spi-max-frequency = <50000000>;
+                                        reg = <1>;
+                                };
+                        };
                 };
 
                 nand0: nand@40000000 {
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index 6b1d4cab24c2..cfdf429578b5 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -322,6 +322,24 @@
                                         };
                                 };
 
+                                spi0 {
+                                        pinctrl_spi0: spi0-0 {
+                                                atmel,pins =
+                                                        <1 0 0x1 0x0    /* PB0 periph A SPI0_MISO pin */
+                                                         1 1 0x1 0x0    /* PB1 periph A SPI0_MOSI pin */
+                                                         1 2 0x1 0x0>;  /* PB2 periph A SPI0_SPCK pin */
+                                        };
+                                };
+
+                                spi1 {
+                                        pinctrl_spi1: spi1-0 {
+                                                atmel,pins =
+                                                        <1 14 0x1 0x0   /* PB14 periph A SPI1_MISO pin */
+                                                         1 15 0x1 0x0   /* PB15 periph A SPI1_MOSI pin */
+                                                         1 16 0x1 0x0>; /* PB16 periph A SPI1_SPCK pin */
+                                        };
+                                };
+
                                 pioA: gpio@fffff200 {
                                         compatible = "atmel,at91rm9200-gpio";
                                         reg = <0xfffff200 0x200>;
@@ -531,6 +549,28 @@
                                 reg = <0xfffffd40 0x10>;
                                 status = "disabled";
                         };
+
+                        spi0: spi@fffa4000 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "atmel,at91rm9200-spi";
+                                reg = <0xfffa4000 0x200>;
+                                interrupts = <14 4 3>;
+                                pinctrl-names = "default";
+                                pinctrl-0 = <&pinctrl_spi0>;
+                                status = "disabled";
+                        };
+
+                        spi1: spi@fffa8000 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "atmel,at91rm9200-spi";
+                                reg = <0xfffa8000 0x200>;
+                                interrupts = <15 4 3>;
+                                pinctrl-names = "default";
+                                pinctrl-0 = <&pinctrl_spi1>;
+                                status = "disabled";
+                        };
                 };
 
                 nand0: nand@40000000 {
diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts
index 20c31913c270..92c52a7d70bc 100644
--- a/arch/arm/boot/dts/at91sam9m10g45ek.dts
+++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts
@@ -102,6 +102,16 @@
                                         };
                                 };
                         };
+
+                        spi0: spi@fffa4000{
+                                status = "okay";
+                                cs-gpios = <&pioB 3 0>, <0>, <0>, <0>;
+                                mtd_dataflash@0 {
+                                        compatible = "atmel,at45", "atmel,dataflash";
+                                        spi-max-frequency = <13000000>;
+                                        reg = <0>;
+                                };
+                        };
                 };
 
                 nand0: nand@40000000 {
diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi
index 7750f98dd764..b2961f1ea51b 100644
--- a/arch/arm/boot/dts/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/at91sam9n12.dtsi
@@ -261,6 +261,24 @@
                                         };
                                 };
 
+                                spi0 {
+                                        pinctrl_spi0: spi0-0 {
+                                                atmel,pins =
+                                                        <0 11 0x1 0x0   /* PA11 periph A SPI0_MISO pin */
+                                                         0 12 0x1 0x0   /* PA12 periph A SPI0_MOSI pin */
+                                                         0 13 0x1 0x0>; /* PA13 periph A SPI0_SPCK pin */
+                                        };
+                                };
+
+                                spi1 {
+                                        pinctrl_spi1: spi1-0 {
+                                                atmel,pins =
+                                                        <0 21 0x2 0x0   /* PA21 periph B SPI1_MISO pin */
+                                                         0 22 0x2 0x0   /* PA22 periph B SPI1_MOSI pin */
+                                                         0 23 0x2 0x0>; /* PA23 periph B SPI1_SPCK pin */
+                                        };
+                                };
+
                                 pioA: gpio@fffff400 {
                                         compatible = "atmel,at91sam9x5-gpio", "atmel,at91rm9200-gpio";
                                         reg = <0xfffff400 0x200>;
@@ -373,6 +391,28 @@
                                 #size-cells = <0>;
                                 status = "disabled";
                         };
+
+                        spi0: spi@f0000000 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "atmel,at91rm9200-spi";
+                                reg = <0xf0000000 0x100>;
+                                interrupts = <13 4 3>;
+                                pinctrl-names = "default";
+                                pinctrl-0 = <&pinctrl_spi0>;
+                                status = "disabled";
+                        };
+
+                        spi1: spi@f0004000 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "atmel,at91rm9200-spi";
+                                reg = <0xf0004000 0x100>;
+                                interrupts = <14 4 3>;
+                                pinctrl-names = "default";
+                                pinctrl-0 = <&pinctrl_spi1>;
+                                status = "disabled";
+                        };
                 };
 
                 nand0: nand@40000000 {
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index d400f8de4387..34c842b1efb2 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -67,6 +67,16 @@
                                         };
                                 };
                         };
+
+                        spi0: spi@f0000000 {
+                                status = "okay";
+                                cs-gpios = <&pioA 14 0>, <0>, <0>, <0>;
+                                m25p80@0 {
+                                        compatible = "atmel,at25df321a";
+                                        spi-max-frequency = <50000000>;
+                                        reg = <0>;
+                                };
+                        };
                 };
 
                 nand0: nand@40000000 {
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index aa98e641931f..347b438d47fa 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -238,8 +238,32 @@
                                 nand {
                                         pinctrl_nand: nand-0 {
                                                 atmel,pins =
-                                                        <3 4 0x0 0x1    /* PD5 gpio RDY pin pull_up */
-                                                         3 5 0x0 0x1>;  /* PD4 gpio enable pin pull_up */
+                                                        <3 0 0x1 0x0    /* PD0 periph A Read Enable */
+                                                         3 1 0x1 0x0    /* PD1 periph A Write Enable */
+                                                         3 2 0x1 0x0    /* PD2 periph A Address Latch Enable */
+                                                         3 3 0x1 0x0    /* PD3 periph A Command Latch Enable */
+                                                         3 4 0x0 0x1    /* PD4 gpio Chip Enable pin pull_up */
+                                                         3 5 0x0 0x1    /* PD5 gpio RDY/BUSY pin pull_up */
+                                                         3 6 0x1 0x0    /* PD6 periph A Data bit 0 */
+                                                         3 7 0x1 0x0    /* PD7 periph A Data bit 1 */
+                                                         3 8 0x1 0x0    /* PD8 periph A Data bit 2 */
+                                                         3 9 0x1 0x0    /* PD9 periph A Data bit 3 */
+                                                         3 10 0x1 0x0   /* PD10 periph A Data bit 4 */
+                                                         3 11 0x1 0x0   /* PD11 periph A Data bit 5 */
+                                                         3 12 0x1 0x0   /* PD12 periph A Data bit 6 */
+                                                         3 13 0x1 0x0>; /* PD13 periph A Data bit 7 */
+                                        };
+
+                                        pinctrl_nand_16bits: nand_16bits-0 {
+                                                atmel,pins =
+                                                        <3 14 0x1 0x0   /* PD14 periph A Data bit 8 */
+                                                         3 15 0x1 0x0   /* PD15 periph A Data bit 9 */
+                                                         3 16 0x1 0x0   /* PD16 periph A Data bit 10 */
+                                                         3 17 0x1 0x0   /* PD17 periph A Data bit 11 */
+                                                         3 18 0x1 0x0   /* PD18 periph A Data bit 12 */
+                                                         3 19 0x1 0x0   /* PD19 periph A Data bit 13 */
+                                                         3 20 0x1 0x0   /* PD20 periph A Data bit 14 */
+                                                         3 21 0x1 0x0>; /* PD21 periph A Data bit 15 */
                                         };
                                 };
 
@@ -319,6 +343,24 @@
                                         };
                                 };
 
+                                spi0 {
+                                        pinctrl_spi0: spi0-0 {
+                                                atmel,pins =
+                                                        <0 11 0x1 0x0   /* PA11 periph A SPI0_MISO pin */
+                                                         0 12 0x1 0x0   /* PA12 periph A SPI0_MOSI pin */
+                                                         0 13 0x1 0x0>; /* PA13 periph A SPI0_SPCK pin */
+                                        };
+                                };
+
+                                spi1 {
+                                        pinctrl_spi1: spi1-0 {
+                                                atmel,pins =
+                                                        <0 21 0x2 0x0   /* PA21 periph B SPI1_MISO pin */
+                                                         0 22 0x2 0x0   /* PA22 periph B SPI1_MOSI pin */
+                                                         0 23 0x2 0x0>; /* PA23 periph B SPI1_SPCK pin */
+                                        };
+                                };
+
                                 pioA: gpio@fffff400 {
                                         compatible = "atmel,at91sam9x5-gpio", "atmel,at91rm9200-gpio";
                                         reg = <0xfffff400 0x200>;
@@ -505,6 +547,28 @@
                                         trigger-value = <0x6>;
                                 };
                         };
+
+                        spi0: spi@f0000000 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "atmel,at91rm9200-spi";
+                                reg = <0xf0000000 0x100>;
+                                interrupts = <13 4 3>;
+                                pinctrl-names = "default";
+                                pinctrl-0 = <&pinctrl_spi0>;
+                                status = "disabled";
+                        };
+
+                        spi1: spi@f0004000 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "atmel,at91rm9200-spi";
+                                reg = <0xf0004000 0x100>;
+                                interrupts = <14 4 3>;
+                                pinctrl-names = "default";
+                                pinctrl-0 = <&pinctrl_spi1>;
+                                status = "disabled";
+                        };
                 };
 
                 nand0: nand@40000000 {
diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi
index 8a7cf1d9cf5d..09f5e667ca7a 100644
--- a/arch/arm/boot/dts/at91sam9x5ek.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi
@@ -84,6 +84,16 @@
                                         };
                                 };
                         };
+
+                        spi0: spi@f0000000 {
+                                status = "okay";
+                                cs-gpios = <&pioA 14 0>, <0>, <0>, <0>;
+                                m25p80@0 {
+                                        compatible = "atmel,at25df321a";
+                                        spi-max-frequency = <50000000>;
+                                        reg = <0>;
+                                };
+                        };
                 };
 
                 usb0: ohci@00600000 {
diff --git a/arch/arm/boot/dts/bcm2835.dtsi b/arch/arm/boot/dts/bcm2835.dtsi
index 4bf2a8774aa7..7e0481e2441a 100644
--- a/arch/arm/boot/dts/bcm2835.dtsi
+++ b/arch/arm/boot/dts/bcm2835.dtsi
@@ -105,7 +105,7 @@
                         compatible = "fixed-clock";
                         reg = <1>;
                         #clock-cells = <0>;
-                        clock-frequency = <150000000>;
+                        clock-frequency = <250000000>;
                 };
         };
 };
diff --git a/arch/arm/boot/dts/dbx5x0.dtsi b/arch/arm/boot/dts/dbx5x0.dtsi
index 69140ba99f46..aaa63d0a8096 100644
--- a/arch/arm/boot/dts/dbx5x0.dtsi
+++ b/arch/arm/boot/dts/dbx5x0.dtsi
@@ -191,8 +191,8 @@
 
                 prcmu: prcmu@80157000 {
                         compatible = "stericsson,db8500-prcmu";
-                        reg = <0x80157000 0x1000>;
-                        reg-names = "prcmu";
+                        reg = <0x80157000 0x1000>, <0x801b0000 0x8000>, <0x801b8000 0x1000>;
+                        reg-names = "prcmu", "prcmu-tcpm", "prcmu-tcdm";
                         interrupts = <0 47 0x4>;
                         #address-cells = <1>;
                         #size-cells = <1>;
@@ -319,9 +319,8 @@
                                 };
                         };
 
-                        ab8500@5 {
+                        ab8500 {
                                 compatible = "stericsson,ab8500";
-                                reg = <5>; /* mailbox 5 is i2c */
                                 interrupt-parent = <&intc>;
                                 interrupts = <0 40 0x4>;
                                 interrupt-controller;
diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi
index 67dbe20868a2..f7509cafc377 100644
--- a/arch/arm/boot/dts/dove.dtsi
+++ b/arch/arm/boot/dts/dove.dtsi
@@ -197,6 +197,11 @@
                         status = "disabled";
                 };
 
+                rtc@d8500 {
+                        compatible = "marvell,orion-rtc";
+                        reg = <0xd8500 0x20>;
+                };
+
                 crypto: crypto@30000 {
                         compatible = "marvell,orion-crypto";
                         reg = <0x30000 0x10000>,
diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi
index e1347fceb5bc..1a62bcf18aa3 100644
--- a/arch/arm/boot/dts/exynos4.dtsi
+++ b/arch/arm/boot/dts/exynos4.dtsi
@@ -275,18 +275,27 @@
                         compatible = "arm,pl330", "arm,primecell";
                         reg = <0x12680000 0x1000>;
                         interrupts = <0 35 0>;
+                        #dma-cells = <1>;
+                        #dma-channels = <8>;
+                        #dma-requests = <32>;
                 };
 
                 pdma1: pdma@12690000 {
                         compatible = "arm,pl330", "arm,primecell";
                         reg = <0x12690000 0x1000>;
                         interrupts = <0 36 0>;
+                        #dma-cells = <1>;
+                        #dma-channels = <8>;
+                        #dma-requests = <32>;
                 };
 
                 mdma1: mdma@12850000 {
                         compatible = "arm,pl330", "arm,primecell";
                         reg = <0x12850000 0x1000>;
                         interrupts = <0 34 0>;
+                        #dma-cells = <1>;
+                        #dma-channels = <8>;
+                        #dma-requests = <1>;
                 };
         };
 };
diff --git a/arch/arm/boot/dts/exynos5440.dtsi b/arch/arm/boot/dts/exynos5440.dtsi
index 5f3562ad6746..9a99755920c0 100644
--- a/arch/arm/boot/dts/exynos5440.dtsi
+++ b/arch/arm/boot/dts/exynos5440.dtsi
@@ -142,12 +142,18 @@
                         compatible = "arm,pl330", "arm,primecell";
                         reg = <0x120000 0x1000>;
                         interrupts = <0 34 0>;
+                        #dma-cells = <1>;
+                        #dma-channels = <8>;
+                        #dma-requests = <32>;
                 };
 
                 pdma1: pdma@121B0000 {
                         compatible = "arm,pl330", "arm,primecell";
                         reg = <0x121000 0x1000>;
                         interrupts = <0 35 0>;
+                        #dma-cells = <1>;
+                        #dma-channels = <8>;
+                        #dma-requests = <32>;
                 };
         };
 
diff --git a/arch/arm/boot/dts/href.dtsi b/arch/arm/boot/dts/href.dtsi
index 592fb9dc35bd..379128eb9d98 100644
--- a/arch/arm/boot/dts/href.dtsi
+++ b/arch/arm/boot/dts/href.dtsi
@@ -221,7 +221,7 @@
                                 };
                         };
 
-                        ab8500@5 {
+                        ab8500 {
                                 ab8500-regulators {
                                         ab8500_ldo_aux1_reg: ab8500_ldo_aux1 {
                                                 regulator-name = "V-DISPLAY";
diff --git a/arch/arm/boot/dts/hrefv60plus.dts b/arch/arm/boot/dts/hrefv60plus.dts
index 55f4191a626e..2b587a74b813 100644
--- a/arch/arm/boot/dts/hrefv60plus.dts
+++ b/arch/arm/boot/dts/hrefv60plus.dts
@@ -158,7 +158,7 @@
                                 };
                         };
 
-                        ab8500@5 {
+                        ab8500 {
                                 ab8500-regulators {
                                         ab8500_ldo_aux1_reg: ab8500_ldo_aux1 {
                                                 regulator-name = "V-DISPLAY";
diff --git a/arch/arm/boot/dts/imx28-m28evk.dts b/arch/arm/boot/dts/imx28-m28evk.dts
index 6ce3d17c3a29..fd36e1cca104 100644
--- a/arch/arm/boot/dts/imx28-m28evk.dts
+++ b/arch/arm/boot/dts/imx28-m28evk.dts
@@ -152,7 +152,6 @@
                         i2c0: i2c@80058000 {
                                 pinctrl-names = "default";
                                 pinctrl-0 = <&i2c0_pins_a>;
-                                clock-frequency = <400000>;
                                 status = "okay";
 
                                 sgtl5000: codec@0a {
diff --git a/arch/arm/boot/dts/imx28-sps1.dts b/arch/arm/boot/dts/imx28-sps1.dts
index e6cde8aa7fff..6c6a5442800a 100644
--- a/arch/arm/boot/dts/imx28-sps1.dts
+++ b/arch/arm/boot/dts/imx28-sps1.dts
@@ -70,7 +70,6 @@
                         i2c0: i2c@80058000 {
                                 pinctrl-names = "default";
                                 pinctrl-0 = <&i2c0_pins_a>;
-                                clock-frequency = <400000>;
                                 status = "okay";
 
                                 rtc: rtc@51 {
diff --git a/arch/arm/boot/dts/imx53-mba53.dts b/arch/arm/boot/dts/imx53-mba53.dts
index e54fffd48369..468c0a1d48d9 100644
--- a/arch/arm/boot/dts/imx53-mba53.dts
+++ b/arch/arm/boot/dts/imx53-mba53.dts
@@ -42,10 +42,9 @@
                         fsl,pins = <689 0x10000         /* DISP1_DRDY   */
                                     482 0x10000         /* DISP1_HSYNC  */
                                     489 0x10000         /* DISP1_VSYNC  */
-                                    684 0x10000         /* DISP1_DAT_0  */
                                     515 0x10000         /* DISP1_DAT_22 */
                                     523 0x10000         /* DISP1_DAT_23 */
-                                    543 0x10000         /* DISP1_DAT_21 */
+                                    545 0x10000         /* DISP1_DAT_21 */
                                     553 0x10000         /* DISP1_DAT_20 */
                                     558 0x10000         /* DISP1_DAT_19 */
                                     564 0x10000         /* DISP1_DAT_18 */
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index 06ec460b4581..281a223591ff 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -91,6 +91,7 @@
                         compatible = "arm,cortex-a9-twd-timer";
                         reg = <0x00a00600 0x20>;
                         interrupts = <1 13 0xf01>;
+                        clocks = <&clks 15>;
                 };
 
                 L2: l2-cache@00a02000 {
diff --git a/arch/arm/boot/dts/kirkwood-dns320.dts b/arch/arm/boot/dts/kirkwood-dns320.dts
index 5bb0bf39d3b8..c9c44b2f62d7 100644
--- a/arch/arm/boot/dts/kirkwood-dns320.dts
+++ b/arch/arm/boot/dts/kirkwood-dns320.dts
@@ -42,12 +42,10 @@
 
         ocp@f1000000 {
                 serial@12000 {
-                        clock-frequency = <166666667>;
                         status = "okay";
                 };
 
                 serial@12100 {
-                        clock-frequency = <166666667>;
                         status = "okay";
                 };
         };
diff --git a/arch/arm/boot/dts/kirkwood-dns325.dts b/arch/arm/boot/dts/kirkwood-dns325.dts
index d430713ea9b9..e4e4930dc5cf 100644
--- a/arch/arm/boot/dts/kirkwood-dns325.dts
+++ b/arch/arm/boot/dts/kirkwood-dns325.dts
@@ -50,7 +50,6 @@
                         };
                 };
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "okay";
                 };
         };
diff --git a/arch/arm/boot/dts/kirkwood-dockstar.dts b/arch/arm/boot/dts/kirkwood-dockstar.dts
index 2e3dd34e21a5..0196cf6b0ef2 100644
--- a/arch/arm/boot/dts/kirkwood-dockstar.dts
+++ b/arch/arm/boot/dts/kirkwood-dockstar.dts
@@ -37,7 +37,6 @@
                         };
                 };
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "ok";
                 };
 
diff --git a/arch/arm/boot/dts/kirkwood-dreamplug.dts b/arch/arm/boot/dts/kirkwood-dreamplug.dts
index ef2d8c705709..289e51d86372 100644
--- a/arch/arm/boot/dts/kirkwood-dreamplug.dts
+++ b/arch/arm/boot/dts/kirkwood-dreamplug.dts
@@ -38,7 +38,6 @@
                         };
                 };
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "ok";
                 };
 
diff --git a/arch/arm/boot/dts/kirkwood-goflexnet.dts b/arch/arm/boot/dts/kirkwood-goflexnet.dts
index 1b133e0c566e..c3573be7b92c 100644
--- a/arch/arm/boot/dts/kirkwood-goflexnet.dts
+++ b/arch/arm/boot/dts/kirkwood-goflexnet.dts
@@ -73,11 +73,11 @@
                         };
                 };
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "ok";
                 };
 
                 nand@3000000 {
+                        chip-delay = <40>;
                         status = "okay";
 
                         partition@0 {
diff --git a/arch/arm/boot/dts/kirkwood-ib62x0.dts b/arch/arm/boot/dts/kirkwood-ib62x0.dts
index 71902da33d63..5335b1aa8601 100644
--- a/arch/arm/boot/dts/kirkwood-ib62x0.dts
+++ b/arch/arm/boot/dts/kirkwood-ib62x0.dts
@@ -51,7 +51,6 @@
                         };
                 };
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "okay";
                 };
 
diff --git a/arch/arm/boot/dts/kirkwood-iconnect.dts b/arch/arm/boot/dts/kirkwood-iconnect.dts
index 504f16be8b54..12ccf74ac3c4 100644
--- a/arch/arm/boot/dts/kirkwood-iconnect.dts
+++ b/arch/arm/boot/dts/kirkwood-iconnect.dts
@@ -78,7 +78,6 @@
                         };
                 };
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "ok";
                 };
 
diff --git a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts
index 6cae4599c4b3..3694e94f6e99 100644
--- a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts
+++ b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts
@@ -96,11 +96,11 @@
                                 marvell,function = "gpio";
                         };
                         pmx_led_rebuild_brt_ctrl_1: pmx-led-rebuild-brt-ctrl-1 {
-                                marvell,pins = "mpp44";
+                                marvell,pins = "mpp46";
                                 marvell,function = "gpio";
                         };
                         pmx_led_rebuild_brt_ctrl_2: pmx-led-rebuild-brt-ctrl-2 {
-                                marvell,pins = "mpp45";
+                                marvell,pins = "mpp47";
                                 marvell,function = "gpio";
                         };
 
@@ -115,7 +115,6 @@
                 };
 
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "ok";
                 };
 
@@ -158,14 +157,14 @@
                         gpios = <&gpio0 16 0>;
                         linux,default-trigger = "default-on";
                 };
-                health_led1 {
+                rebuild_led {
+                        label = "status:white:rebuild_led";
+                        gpios = <&gpio1 4 0>;
+                };
+                health_led {
                         label = "status:red:health_led";
                         gpios = <&gpio1 5 0>;
                 };
-                health_led2 {
-                        label = "status:white:health_led";
-                        gpios = <&gpio1 4 0>;
-                };
                 backup_led {
                         label = "status:blue:backup_led";
                         gpios = <&gpio0 15 0>;
diff --git a/arch/arm/boot/dts/kirkwood-km_kirkwood.dts b/arch/arm/boot/dts/kirkwood-km_kirkwood.dts
index 8db3123ac80f..5bbd0542cdd3 100644
--- a/arch/arm/boot/dts/kirkwood-km_kirkwood.dts
+++ b/arch/arm/boot/dts/kirkwood-km_kirkwood.dts
@@ -34,7 +34,6 @@
                 };
 
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "ok";
                 };
 
diff --git a/arch/arm/boot/dts/kirkwood-lschlv2.dts b/arch/arm/boot/dts/kirkwood-lschlv2.dts
index 9510c9ea666c..9f55d95f35f5 100644
--- a/arch/arm/boot/dts/kirkwood-lschlv2.dts
+++ b/arch/arm/boot/dts/kirkwood-lschlv2.dts
@@ -13,7 +13,6 @@
 
         ocp@f1000000 {
                 serial@12000 {
-                        clock-frequency = <166666667>;
                         status = "okay";
                 };
         };
diff --git a/arch/arm/boot/dts/kirkwood-lsxhl.dts b/arch/arm/boot/dts/kirkwood-lsxhl.dts
index 739019c4cba9..5c84c118ed8d 100644
--- a/arch/arm/boot/dts/kirkwood-lsxhl.dts
+++ b/arch/arm/boot/dts/kirkwood-lsxhl.dts
@@ -13,7 +13,6 @@
 
         ocp@f1000000 {
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "okay";
                 };
         };
diff --git a/arch/arm/boot/dts/kirkwood-mplcec4.dts b/arch/arm/boot/dts/kirkwood-mplcec4.dts
index 662dfd81b1ce..758824118a9a 100644
--- a/arch/arm/boot/dts/kirkwood-mplcec4.dts
+++ b/arch/arm/boot/dts/kirkwood-mplcec4.dts
@@ -90,7 +90,6 @@
                 };
 
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "ok";
                 };
 
diff --git a/arch/arm/boot/dts/kirkwood-ns2-common.dtsi b/arch/arm/boot/dts/kirkwood-ns2-common.dtsi
index e8e7ecef1650..6affd924fe11 100644
--- a/arch/arm/boot/dts/kirkwood-ns2-common.dtsi
+++ b/arch/arm/boot/dts/kirkwood-ns2-common.dtsi
@@ -23,7 +23,6 @@
                 };
 
                 serial@12000 {
-                        clock-frequency = <166666667>;
                         status = "okay";
                 };
 
diff --git a/arch/arm/boot/dts/kirkwood-nsa310.dts b/arch/arm/boot/dts/kirkwood-nsa310.dts
index 3a178cf708d7..a7412b937a8a 100644
--- a/arch/arm/boot/dts/kirkwood-nsa310.dts
+++ b/arch/arm/boot/dts/kirkwood-nsa310.dts
@@ -117,7 +117,6 @@
                 };
 
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "ok";
                 };
 
diff --git a/arch/arm/boot/dts/kirkwood-openblocks_a6.dts b/arch/arm/boot/dts/kirkwood-openblocks_a6.dts
index ede7fe0d7a87..d27f7245f8e7 100644
--- a/arch/arm/boot/dts/kirkwood-openblocks_a6.dts
+++ b/arch/arm/boot/dts/kirkwood-openblocks_a6.dts
@@ -18,12 +18,10 @@
 
         ocp@f1000000 {
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "ok";
                 };
 
                 serial@12100 {
-                        clock-frequency = <200000000>;
                         status = "ok";
                 };
 
diff --git a/arch/arm/boot/dts/kirkwood-topkick.dts b/arch/arm/boot/dts/kirkwood-topkick.dts
index 842ff95d60df..66eb45b00b25 100644
--- a/arch/arm/boot/dts/kirkwood-topkick.dts
+++ b/arch/arm/boot/dts/kirkwood-topkick.dts
@@ -108,7 +108,6 @@
                 };
 
                 serial@12000 {
-                        clock-frequency = <200000000>;
                         status = "ok";
                 };
 
diff --git a/arch/arm/boot/dts/kirkwood.dtsi b/arch/arm/boot/dts/kirkwood.dtsi
index 2c738d9dc82a..fada7e6d24d8 100644
--- a/arch/arm/boot/dts/kirkwood.dtsi
+++ b/arch/arm/boot/dts/kirkwood.dtsi
@@ -38,6 +38,7 @@
                         interrupt-controller;
                         #interrupt-cells = <2>;
                         interrupts = <35>, <36>, <37>, <38>;
+                        clocks = <&gate_clk 7>;
                 };
 
                 gpio1: gpio@10140 {
@@ -49,6 +50,7 @@
                         interrupt-controller;
                         #interrupt-cells = <2>;
                         interrupts = <39>, <40>, <41>;
+                        clocks = <&gate_clk 7>;
                 };
 
                 serial@12000 {
@@ -57,7 +59,6 @@
                         reg-shift = <2>;
                         interrupts = <33>;
                         clocks = <&gate_clk 7>;
-                        /* set clock-frequency in board dts */
                         status = "disabled";
                 };
 
@@ -67,7 +68,6 @@
                         reg-shift = <2>;
                         interrupts = <34>;
                         clocks = <&gate_clk 7>;
-                        /* set clock-frequency in board dts */
                         status = "disabled";
                 };
 
@@ -75,6 +75,7 @@
                         compatible = "marvell,kirkwood-rtc", "marvell,orion-rtc";
                         reg = <0x10300 0x20>;
                         interrupts = <53>;
+                        clocks = <&gate_clk 7>;
                 };
 
                 spi@10600 {
diff --git a/arch/arm/boot/dts/msm8660-surf.dts b/arch/arm/boot/dts/msm8660-surf.dts
index 31f2157cd7d7..67f8670c4d6a 100644
--- a/arch/arm/boot/dts/msm8660-surf.dts
+++ b/arch/arm/boot/dts/msm8660-surf.dts
@@ -38,4 +38,10 @@
                       <0x19c00000 0x1000>;
                 interrupts = <0 195 0x0>;
         };
+
+        qcom,ssbi@500000 {
+                compatible = "qcom,ssbi";
+                reg = <0x500000 0x1000>;
+                qcom,controller-type = "pmic-arbiter";
+        };
 };
diff --git a/arch/arm/boot/dts/msm8960-cdp.dts b/arch/arm/boot/dts/msm8960-cdp.dts
index 9e621b5ad3dd..c9b09a813a4b 100644
--- a/arch/arm/boot/dts/msm8960-cdp.dts
+++ b/arch/arm/boot/dts/msm8960-cdp.dts
@@ -38,4 +38,10 @@
                       <0x16400000 0x1000>;
                 interrupts = <0 154 0x0>;
         };
+
+        qcom,ssbi@500000 {
+                compatible = "qcom,ssbi";
+                reg = <0x500000 0x1000>;
+                qcom,controller-type = "pmic-arbiter";
+        };
 };
diff --git a/arch/arm/boot/dts/orion5x-lacie-ethernet-disk-mini-v2.dts b/arch/arm/boot/dts/orion5x-lacie-ethernet-disk-mini-v2.dts
index 5a3a58b7e18f..0077fc8510b7 100644
--- a/arch/arm/boot/dts/orion5x-lacie-ethernet-disk-mini-v2.dts
+++ b/arch/arm/boot/dts/orion5x-lacie-ethernet-disk-mini-v2.dts
@@ -11,7 +11,7 @@
 
 / {
         model = "LaCie Ethernet Disk mini V2";
-        compatible = "lacie,ethernet-disk-mini-v2", "marvell-orion5x-88f5182", "marvell,orion5x";
+        compatible = "lacie,ethernet-disk-mini-v2", "marvell,orion5x-88f5182", "marvell,orion5x";
 
         memory {
                 reg = <0x00000000 0x4000000>; /* 64 MB */
diff --git a/arch/arm/boot/dts/orion5x.dtsi b/arch/arm/boot/dts/orion5x.dtsi
index 8aad00f81ed9..f7bec3b1ba32 100644
--- a/arch/arm/boot/dts/orion5x.dtsi
+++ b/arch/arm/boot/dts/orion5x.dtsi
@@ -13,6 +13,9 @@
         compatible = "marvell,orion5x";
         interrupt-parent = <&intc>;
 
+        aliases {
+                gpio0 = &gpio0;
+        };
         intc: interrupt-controller {
                 compatible = "marvell,orion-intc", "marvell,intc";
                 interrupt-controller;
@@ -32,7 +35,9 @@
                         #gpio-cells = <2>;
                         gpio-controller;
                         reg = <0x10100 0x40>;
-                        ngpio = <32>;
+                        ngpios = <32>;
+                        interrupt-controller;
+                        #interrupt-cells = <2>;
                         interrupts = <6>, <7>, <8>, <9>;
                 };
 
@@ -91,7 +96,7 @@
                         reg = <0x90000 0x10000>,
                               <0xf2200000 0x800>;
                         reg-names = "regs", "sram";
-                        interrupts = <22>;
+                        interrupts = <28>;
                         status = "okay";
                 };
         };
diff --git a/arch/arm/boot/dts/snowball.dts b/arch/arm/boot/dts/snowball.dts
index 27f31a5fa494..d3ec32f6b790 100644
--- a/arch/arm/boot/dts/snowball.dts
+++ b/arch/arm/boot/dts/snowball.dts
@@ -298,7 +298,7 @@
                                 };
                         };
 
-                        ab8500@5 {
+                        ab8500 {
                                 ab8500-regulators {
                                         ab8500_ldo_aux1_reg: ab8500_ldo_aux1 {
                                                 regulator-name = "V-DISPLAY";
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index 936d2306e7e1..7e8769bd5977 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/arch/arm/boot/dts/socfpga.dtsi
@@ -75,6 +75,9 @@
                                 compatible = "arm,pl330", "arm,primecell";
                                 reg = <0xffe01000 0x1000>;
                                 interrupts = <0 180 4>;
+                                #dma-cells = <1>;
+                                #dma-channels = <8>;
+                                #dma-requests = <32>;
                         };
                 };
 
diff --git a/arch/arm/boot/dts/spear1310.dtsi b/arch/arm/boot/dts/spear1310.dtsi
index 1513c1927cc8..122ae94076c8 100644
--- a/arch/arm/boot/dts/spear1310.dtsi
+++ b/arch/arm/boot/dts/spear1310.dtsi
@@ -89,7 +89,7 @@
                 pinmux: pinmux@e0700000 {
                         compatible = "st,spear1310-pinmux";
                         reg = <0xe0700000 0x1000>;
-                        #gpio-range-cells = <2>;
+                        #gpio-range-cells = <3>;
                 };
 
                 apb {
@@ -212,7 +212,7 @@
                                 interrupt-controller;
                                 gpio-controller;
                                 #gpio-cells = <2>;
-                                gpio-ranges = <&pinmux 0 246>;
+                                gpio-ranges = <&pinmux 0 0 246>;
                                 status = "disabled";
 
                                 st-plgpio,ngpio = <246>;
diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi
index 34da11aa6795..c511c4772efd 100644
--- a/arch/arm/boot/dts/spear1340.dtsi
+++ b/arch/arm/boot/dts/spear1340.dtsi
@@ -63,7 +63,7 @@
                 pinmux: pinmux@e0700000 {
                         compatible = "st,spear1340-pinmux";
                         reg = <0xe0700000 0x1000>;
-                        #gpio-range-cells = <2>;
+                        #gpio-range-cells = <3>;
                 };
 
                 pwm: pwm@e0180000 {
@@ -127,7 +127,7 @@
                                 interrupt-controller;
                                 gpio-controller;
                                 #gpio-cells = <2>;
-                                gpio-ranges = <&pinmux 0 252>;
+                                gpio-ranges = <&pinmux 0 0 252>;
                                 status = "disabled";
 
                                 st-plgpio,ngpio = <250>;
diff --git a/arch/arm/boot/dts/spear310.dtsi b/arch/arm/boot/dts/spear310.dtsi
index ab45b8c81982..95372080eea6 100644
--- a/arch/arm/boot/dts/spear310.dtsi
+++ b/arch/arm/boot/dts/spear310.dtsi
@@ -25,7 +25,7 @@
                 pinmux: pinmux@b4000000 {
                         compatible = "st,spear310-pinmux";
                         reg = <0xb4000000 0x1000>;
-                        #gpio-range-cells = <2>;
+                        #gpio-range-cells = <3>;
                 };
 
                 fsmc: flash@44000000 {
@@ -102,7 +102,7 @@
                                 interrupt-controller;
                                 gpio-controller;
                                 #gpio-cells = <2>;
-                                gpio-ranges = <&pinmux 0 102>;
+                                gpio-ranges = <&pinmux 0 0 102>;
                                 status = "disabled";
 
                                 st-plgpio,ngpio = <102>;
diff --git a/arch/arm/boot/dts/spear320.dtsi b/arch/arm/boot/dts/spear320.dtsi
index caa5520b1fd4..ffea342aeec9 100644
--- a/arch/arm/boot/dts/spear320.dtsi
+++ b/arch/arm/boot/dts/spear320.dtsi
@@ -24,7 +24,7 @@
                 pinmux: pinmux@b3000000 {
                         compatible = "st,spear320-pinmux";
                         reg = <0xb3000000 0x1000>;
-                        #gpio-range-cells = <2>;
+                        #gpio-range-cells = <3>;
                 };
 
                 clcd@90000000 {
@@ -130,7 +130,7 @@
                                 interrupt-controller;
                                 gpio-controller;
                                 #gpio-cells = <2>;
-                                gpio-ranges = <&pinmux 0 102>;
+                                gpio-ranges = <&pinmux 0 0 102>;
                                 status = "disabled";
 
                                 st-plgpio,ngpio = <102>;
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index 9a428931d042..3d3f64d2111a 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -118,6 +118,7 @@
                 compatible = "arm,cortex-a9-twd-timer";
                 reg = <0x50040600 0x20>;
                 interrupts = <1 13 0x304>;
+                clocks = <&tegra_car 132>;
         };
 
         intc: interrupt-controller {
@@ -384,7 +385,7 @@
 
         spi@7000d800 {
                 compatible = "nvidia,tegra20-slink";
-                reg = <0x7000d480 0x200>;
+                reg = <0x7000d800 0x200>;
                 interrupts = <0 83 0x04>;
                 nvidia,dma-request-selector = <&apbdma 17>;
                 #address-cells = <1>;
diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi
index 767803e1fd55..dbf46c272562 100644
--- a/arch/arm/boot/dts/tegra30.dtsi
+++ b/arch/arm/boot/dts/tegra30.dtsi
@@ -119,6 +119,7 @@
                 compatible = "arm,cortex-a9-twd-timer";
                 reg = <0x50040600 0x20>;
                 interrupts = <1 13 0xf04>;
+                clocks = <&tegra_car 214>;
         };
 
         intc: interrupt-controller {
@@ -371,7 +372,7 @@
 
         spi@7000d800 {
                 compatible = "nvidia,tegra30-slink", "nvidia,tegra20-slink";
-                reg = <0x7000d480 0x200>;
+                reg = <0x7000d800 0x200>;
                 interrupts = <0 83 0x04>;
                 nvidia,dma-request-selector = <&apbdma 17>;
                 #address-cells = <1>;
diff --git a/arch/arm/boot/dts/vt8500-bv07.dts b/arch/arm/boot/dts/vt8500-bv07.dts
index 567cf4e8ab84..877b33afa7ed 100644
--- a/arch/arm/boot/dts/vt8500-bv07.dts
+++ b/arch/arm/boot/dts/vt8500-bv07.dts
@@ -11,26 +11,22 @@
 
 / {
         model = "Benign BV07 Netbook";
+};
 
-        /*
-         * Display node is based on Sascha Hauer's patch on dri-devel.
-         * Added a bpp property to calculate the size of the framebuffer
-         * until the binding is formalized.
-         */
-        display: display@0 {
-                modes {
-                        mode0: mode@0 {
-                                hactive = <800>;
-                                vactive = <480>;
-                                hback-porch = <88>;
-                                hfront-porch = <40>;
-                                hsync-len = <0>;
-                                vback-porch = <32>;
-                                vfront-porch = <11>;
-                                vsync-len = <1>;
-                                clock = <0>;    /* unused but required */
-                                bpp = <16>;     /* non-standard but required */
-                        };
+&fb {
+        bits-per-pixel = <16>;
+        display-timings {
+                native-mode = <&timing0>;
+                timing0: 800x480 {
+                        clock-frequency = <0>; /* unused but required */
+                        hactive = <800>;
+                        vactive = <480>;
+                        hfront-porch = <40>;
+                        hback-porch = <88>;
+                        hsync-len = <0>;
+                        vback-porch = <32>;
+                        vfront-porch = <11>;
+                        vsync-len = <1>;
                 };
         };
 };
diff --git a/arch/arm/boot/dts/vt8500.dtsi b/arch/arm/boot/dts/vt8500.dtsi
index cf31ced46602..68c8dc644383 100644
--- a/arch/arm/boot/dts/vt8500.dtsi
+++ b/arch/arm/boot/dts/vt8500.dtsi
@@ -98,12 +98,10 @@
                         interrupts = <43>;
                 };
 
-                fb@d800e400 {
+                fb: fb@d8050800 {
                         compatible = "via,vt8500-fb";
                         reg = <0xd800e400 0x400>;
                         interrupts = <12>;
-                        display = <&display>;
-                        default-mode = <&mode0>;
                 };
 
                 ge_rops@d8050400 {
diff --git a/arch/arm/boot/dts/wm8505-ref.dts b/arch/arm/boot/dts/wm8505-ref.dts
index fd4e248074c6..edd2cec3d37f 100644
--- a/arch/arm/boot/dts/wm8505-ref.dts
+++ b/arch/arm/boot/dts/wm8505-ref.dts
@@ -11,26 +11,22 @@
 
 / {
         model = "Wondermedia WM8505 Netbook";
+};
 
-        /*
-         * Display node is based on Sascha Hauer's patch on dri-devel.
-         * Added a bpp property to calculate the size of the framebuffer
-         * until the binding is formalized.
-         */
-        display: display@0 {
-                modes {
-                        mode0: mode@0 {
-                                hactive = <800>;
-                                vactive = <480>;
-                                hback-porch = <88>;
-                                hfront-porch = <40>;
-                                hsync-len = <0>;
-                                vback-porch = <32>;
-                                vfront-porch = <11>;
-                                vsync-len = <1>;
-                                clock = <0>;    /* unused but required */
-                                bpp = <32>;     /* non-standard but required */
-                        };
+&fb {
+        bits-per-pixel = <32>;
+        display-timings {
+                native-mode = <&timing0>;
+                timing0: 800x480 {
+                        clock-frequency = <0>; /* unused but required */
+                        hactive = <800>;
+                        vactive = <480>;
+                        hfront-porch = <40>;
+                        hback-porch = <88>;
+                        hsync-len = <0>;
+                        vback-porch = <32>;
+                        vfront-porch = <11>;
+                        vsync-len = <1>;
                 };
         };
 };
diff --git a/arch/arm/boot/dts/wm8505.dtsi b/arch/arm/boot/dts/wm8505.dtsi
index e74a1c0fb9a2..bcf668d31b28 100644
--- a/arch/arm/boot/dts/wm8505.dtsi
+++ b/arch/arm/boot/dts/wm8505.dtsi
@@ -128,11 +128,9 @@
                         interrupts = <0>;
                 };
 
-                fb@d8050800 {
+                fb: fb@d8050800 {
                         compatible = "wm,wm8505-fb";
                         reg = <0xd8050800 0x200>;
-                        display = <&display>;
-                        default-mode = <&mode0>;
                 };
 
                 ge_rops@d8050400 {
diff --git a/arch/arm/boot/dts/wm8650-mid.dts b/arch/arm/boot/dts/wm8650-mid.dts
index cefd938f842f..61671a0d9ede 100644
--- a/arch/arm/boot/dts/wm8650-mid.dts
+++ b/arch/arm/boot/dts/wm8650-mid.dts
@@ -11,26 +11,24 @@
 
 / {
         model = "Wondermedia WM8650-MID Tablet";
+};
+
+&fb {
+        bits-per-pixel = <16>;
 
-        /*
-         * Display node is based on Sascha Hauer's patch on dri-devel.
-         * Added a bpp property to calculate the size of the framebuffer
-         * until the binding is formalized.
-         */
-        display: display@0 {
-                modes {
-                        mode0: mode@0 {
-                                hactive = <800>;
-                                vactive = <480>;
-                                hback-porch = <88>;
-                                hfront-porch = <40>;
-                                hsync-len = <0>;
-                                vback-porch = <32>;
-                                vfront-porch = <11>;
-                                vsync-len = <1>;
-                                clock = <0>;    /* unused but required */
-                                bpp = <16>;     /* non-standard but required */
-                        };
+        display-timings {
+                native-mode = <&timing0>;
+                timing0: 800x480 {
+                        clock-frequency = <0>; /* unused but required */
+                        hactive = <800>;
+                        vactive = <480>;
+                        hfront-porch = <40>;
+                        hback-porch = <88>;
+                        hsync-len = <0>;
+                        vback-porch = <32>;
+                        vfront-porch = <11>;
+                        vsync-len = <1>;
                 };
         };
 };
+
diff --git a/arch/arm/boot/dts/wm8650.dtsi b/arch/arm/boot/dts/wm8650.dtsi
index db3c0a12e052..9313407bbc30 100644
--- a/arch/arm/boot/dts/wm8650.dtsi
+++ b/arch/arm/boot/dts/wm8650.dtsi
@@ -128,11 +128,9 @@
                         interrupts = <43>;
                 };
 
-                fb@d8050800 {
+                fb: fb@d8050800 {
                         compatible = "wm,wm8505-fb";
                         reg = <0xd8050800 0x200>;
-                        display = <&display>;
-                        default-mode = <&mode0>;
                 };
 
                 ge_rops@d8050400 {
diff --git a/arch/arm/boot/dts/wm8850-w70v2.dts b/arch/arm/boot/dts/wm8850-w70v2.dts
index fcc660c89540..32d22532cd6c 100644
--- a/arch/arm/boot/dts/wm8850-w70v2.dts
+++ b/arch/arm/boot/dts/wm8850-w70v2.dts
@@ -15,28 +15,6 @@
 / {
         model = "Wondermedia WM8850-W70v2 Tablet";
 
-        /*
-         * Display node is based on Sascha Hauer's patch on dri-devel.
-         * Added a bpp property to calculate the size of the framebuffer
-         * until the binding is formalized.
-         */
-        display: display@0 {
-                modes {
-                        mode0: mode@0 {
-                                hactive = <800>;
-                                vactive = <480>;
-                                hback-porch = <88>;
-                                hfront-porch = <40>;
-                                hsync-len = <0>;
-                                vback-porch = <32>;
-                                vfront-porch = <11>;
-                                vsync-len = <1>;
-                                clock = <0>;    /* unused but required */
-                                bpp = <16>;     /* non-standard but required */
-                        };
-                };
-        };
-
         backlight {
                 compatible = "pwm-backlight";
                 pwms = <&pwm 0 50000 1>;        /* duty inverted */
@@ -45,3 +23,21 @@
                 default-brightness-level = <5>;
         };
 };
+
+&fb {
+        bits-per-pixel = <16>;
+        display-timings {
+                native-mode = <&timing0>;
+                timing0: 800x480 {
+                        clock-frequency = <0>; /* unused but required */
+                        hactive = <800>;
+                        vactive = <480>;
+                        hfront-porch = <40>;
+                        hback-porch = <88>;
+                        hsync-len = <0>;
+                        vback-porch = <32>;
+                        vfront-porch = <11>;
+                        vsync-len = <1>;
+                };
+        };
+};
diff --git a/arch/arm/boot/dts/wm8850.dtsi b/arch/arm/boot/dts/wm8850.dtsi
index e8cbfdc87bba..7149cd13e3b9 100644
--- a/arch/arm/boot/dts/wm8850.dtsi
+++ b/arch/arm/boot/dts/wm8850.dtsi
@@ -135,11 +135,9 @@
                         };
                 };
 
-                fb@d8051700 {
+                fb: fb@d8051700 {
                         compatible = "wm,wm8505-fb";
                         reg = <0xd8051700 0x200>;
-                        display = <&display>;
-                        default-mode = <&mode0>;
                 };
 
                 ge_rops@d8050400 {
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index e36b01025321..088d6c11a0fa 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -188,6 +188,7 @@ CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_MXC=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_PHY=y
 CONFIG_USB_MXS_PHY=y
 CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
diff --git a/arch/arm/configs/lpc32xx_defconfig b/arch/arm/configs/lpc32xx_defconfig
index 92386b20bd09..afa7249fac6e 100644
--- a/arch/arm/configs/lpc32xx_defconfig
+++ b/arch/arm/configs/lpc32xx_defconfig
@@ -134,6 +134,7 @@ CONFIG_SND_DEBUG_VERBOSE=y
 # CONFIG_SND_SPI is not set
 CONFIG_SND_SOC=y
 CONFIG_USB=y
+CONFIG_USB_PHY=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_USB_GADGET=y
diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index fbbc5bb022d5..87924d671115 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -116,9 +116,11 @@ CONFIG_SND_SOC=y
 CONFIG_SND_MXS_SOC=y
 CONFIG_SND_SOC_MXS_SGTL5000=y
 CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_HOST=y
 CONFIG_USB_STORAGE=y
+CONFIG_USB_PHY=y
 CONFIG_USB_MXS_PHY=y
 CONFIG_MMC=y
 CONFIG_MMC_MXS=y
diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig
index 42eab9a2a0fd..7e0ebb64a7f9 100644
--- a/arch/arm/configs/omap1_defconfig
+++ b/arch/arm/configs/omap1_defconfig
@@ -195,6 +195,7 @@ CONFIG_SND_SOC=y
 CONFIG_SND_OMAP_SOC=y
 # CONFIG_USB_HID is not set
 CONFIG_USB=y
+CONFIG_USB_PHY=y
 CONFIG_USB_DEBUG=y
 CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DEVICE_CLASS is not set
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index b16bae2c9a60..bd07864f14a0 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -126,6 +126,8 @@ CONFIG_INPUT_MISC=y
 CONFIG_INPUT_TWL4030_PWRBUTTON=y
 CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=32
 CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index 720799fd3a81..dff714d886d5 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -24,7 +24,7 @@ extern struct arm_delay_ops {
         void (*delay)(unsigned long);
         void (*const_udelay)(unsigned long);
         void (*udelay)(unsigned long);
-        bool const_clock;
+        unsigned long ticks_per_jiffy;
 } arm_delay_ops;
 
 #define __delay(n)              arm_delay_ops.delay(n)
diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
index cca9f15704ed..ea289e1435e7 100644
--- a/arch/arm/include/asm/glue-cache.h
+++ b/arch/arm/include/asm/glue-cache.h
@@ -19,14 +19,6 @@
 #undef _CACHE
 #undef MULTI_CACHE
 
-#if defined(CONFIG_CPU_CACHE_V3)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE v3
-# endif
-#endif
-
 #if defined(CONFIG_CPU_CACHE_V4)
 # ifdef _CACHE
 #  define MULTI_CACHE 1
diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h
index 02fe2fbe2477..ed94b1a366ae 100644
--- a/arch/arm/include/asm/hardware/iop3xx.h
+++ b/arch/arm/include/asm/hardware/iop3xx.h
@@ -37,7 +37,7 @@ extern int iop3xx_get_init_atu(void);
  * IOP3XX processor registers
  */
 #define IOP3XX_PERIPHERAL_PHYS_BASE     0xffffe000
-#define IOP3XX_PERIPHERAL_VIRT_BASE     0xfeffe000
+#define IOP3XX_PERIPHERAL_VIRT_BASE     0xfedfe000
 #define IOP3XX_PERIPHERAL_SIZE          0x00002000
 #define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\
                                         IOP3XX_PERIPHERAL_SIZE - 1)
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
index 8c5e828f484d..91b99abe7a95 100644
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@@ -41,6 +41,13 @@ extern void kunmap_high(struct page *page);
 #endif
 #endif
 
+/*
+ * Needed to be able to broadcast the TLB invalidation for kmap.
+ */
+#ifdef CONFIG_ARM_ERRATA_798181
+#undef ARCH_NEEDS_KMAP_HIGH_GET
+#endif
+
 #ifdef ARCH_NEEDS_KMAP_HIGH_GET
 extern void *kmap_high_get(struct page *page);
 #else
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 863a6611323c..a7b85e0d0cc1 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -27,6 +27,8 @@ void __check_vmalloc_seq(struct mm_struct *mm);
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk);
 #define init_new_context(tsk,mm)        ({ atomic64_set(&mm->context.id, 0); 0; })
 
+DECLARE_PER_CPU(atomic64_t, active_asids);
+
 #else   /* !CONFIG_CPU_HAS_ASID */
 
 #ifdef CONFIG_MMU
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 6ef8afd1b64c..86b8fe398b95 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -111,7 +111,7 @@
 #define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */
 #define L_PTE_S2_MT_WRITEBACK    (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */
 #define L_PTE_S2_RDONLY          (_AT(pteval_t, 1) << 6)   /* HAP[1]   */
-#define L_PTE_S2_RDWR            (_AT(pteval_t, 2) << 6)   /* HAP[2:1] */
+#define L_PTE_S2_RDWR            (_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
 
 /*
  * Hyp-mode PL2 PTE definitions for LPAE.
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 80d6fc4dbe4a..9bcd262a9008 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -61,6 +61,15 @@ extern void __pgd_error(const char *file, int line, pgd_t);
 #define FIRST_USER_ADDRESS      PAGE_SIZE
 
 /*
+ * Use TASK_SIZE as the ceiling argument for free_pgtables() and
+ * free_pgd_range() to avoid freeing the modules pmd when LPAE is enabled (pmd
+ * page shared between user and kernel).
+ */
+#ifdef CONFIG_ARM_LPAE
+#define USER_PGTABLES_CEILING   TASK_SIZE
+#endif
+
+/*
  * The pgprot_* and protection_map entries will be fixed up in runtime
  * to include the cachable and bufferable bits based on memory policy,
  * as well as any architecture dependent bits like global/ASID and SMP
diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h
index 5a85f148b607..21a23e378bbe 100644
--- a/arch/arm/include/asm/system_misc.h
+++ b/arch/arm/include/asm/system_misc.h
@@ -21,9 +21,6 @@ extern void (*arm_pm_idle)(void);
 
 extern unsigned int user_debug;
 
-extern void disable_hlt(void);
-extern void enable_hlt(void);
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_ARM_SYSTEM_MISC_H */
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 4db8c8820f0d..ab865e65a84c 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -14,7 +14,6 @@
 
 #include <asm/glue.h>
 
-#define TLB_V3_PAGE     (1 << 0)
 #define TLB_V4_U_PAGE   (1 << 1)
 #define TLB_V4_D_PAGE   (1 << 2)
 #define TLB_V4_I_PAGE   (1 << 3)
@@ -22,7 +21,6 @@
 #define TLB_V6_D_PAGE   (1 << 5)
 #define TLB_V6_I_PAGE   (1 << 6)
 
-#define TLB_V3_FULL     (1 << 8)
 #define TLB_V4_U_FULL   (1 << 9)
 #define TLB_V4_D_FULL   (1 << 10)
 #define TLB_V4_I_FULL   (1 << 11)
@@ -52,7 +50,6 @@
  *      =============
  *
  *      We have the following to choose from:
- *        v3    - ARMv3
  *        v4    - ARMv4 without write buffer
  *        v4wb  - ARMv4 with write buffer without I TLB flush entry instruction
  *        v4wbi - ARMv4 with write buffer with I TLB flush entry instruction
@@ -330,7 +327,6 @@ static inline void local_flush_tlb_all(void)
         if (tlb_flag(TLB_WB))
                 dsb();
 
-        tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
         tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
         tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
         tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
@@ -351,9 +347,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
         if (tlb_flag(TLB_WB))
                 dsb();
 
-        if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
+        if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
                 if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
-                        tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
                         tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
                         tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
                         tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
@@ -385,9 +380,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
         if (tlb_flag(TLB_WB))
                 dsb();
 
-        if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
+        if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
             cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
-                tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr);
                 tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
                 tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr);
                 tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr);
@@ -418,7 +412,6 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
         if (tlb_flag(TLB_WB))
                 dsb();
 
-        tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr);
         tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
         tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
         tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);
@@ -450,6 +443,21 @@ static inline void local_flush_bp_all(void)
                 isb();
 }
 
+#ifdef CONFIG_ARM_ERRATA_798181
+static inline void dummy_flush_tlb_a15_erratum(void)
+{
+        /*
+         * Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0.
+         */
+        asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
+        dsb();
+}
+#else
+static inline void dummy_flush_tlb_a15_erratum(void)
+{
+}
+#endif
+
 /*
  *      flush_pmd_entry
  *
diff --git a/arch/arm/include/asm/xen/events.h b/arch/arm/include/asm/xen/events.h
index 5c27696de14f..8b1f37bfeeec 100644
--- a/arch/arm/include/asm/xen/events.h
+++ b/arch/arm/include/asm/xen/events.h
@@ -2,6 +2,7 @@
 #define _ASM_ARM_XEN_EVENTS_H
 
 #include <asm/ptrace.h>
+#include <asm/atomic.h>
 
 enum ipi_vector {
         XEN_PLACEHOLDER_VECTOR,
@@ -15,26 +16,8 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
         return raw_irqs_disabled_flags(regs->ARM_cpsr);
 }
 
-/*
- * We cannot use xchg because it does not support 8-byte
- * values. However it is safe to use {ldr,dtd}exd directly because all
- * platforms which Xen can run on support those instructions.
- */
-static inline xen_ulong_t xchg_xen_ulong(xen_ulong_t *ptr, xen_ulong_t val)
-{
-        xen_ulong_t oldval;
-        unsigned int tmp;
-
-        wmb();
-        asm volatile("@ xchg_xen_ulong\n"
-                "1:     ldrexd  %0, %H0, [%3]\n"
-                "       strexd  %1, %2, %H2, [%3]\n"
-                "       teq     %1, #0\n"
-                "       bne     1b"
-                : "=&r" (oldval), "=&r" (tmp)
-                : "r" (val), "r" (ptr)
-                : "memory", "cc");
-        return oldval;
-}
+#define xchg_xen_ulong(ptr, val) atomic64_xchg(container_of((ptr),      \
+                                                            atomic64_t, \
+                                                            counter), (val))
 
 #endif /* _ASM_ARM_XEN_EVENTS_H */
diff --git a/arch/arm/kernel/early_printk.c b/arch/arm/kernel/early_printk.c
index 85aa2b292692..43076536965c 100644
--- a/arch/arm/kernel/early_printk.c
+++ b/arch/arm/kernel/early_printk.c
@@ -29,28 +29,17 @@ static void early_console_write(struct console *con, const char *s, unsigned n)
         early_write(s, n);
 }
 
-static struct console early_console = {
+static struct console early_console_dev = {
         .name =         "earlycon",
         .write =        early_console_write,
         .flags =        CON_PRINTBUFFER | CON_BOOT,
         .index =        -1,
 };
 
-asmlinkage void early_printk(const char *fmt, ...)
-{
-        char buf[512];
-        int n;
-        va_list ap;
-
-        va_start(ap, fmt);
-        n = vscnprintf(buf, sizeof(buf), fmt, ap);
-        early_write(buf, n);
-        va_end(ap);
-}
-
 static int __init setup_early_printk(char *buf)
 {
-        register_console(&early_console);
+        early_console = &early_console_dev;
+        register_console(&early_console_dev);
         return 0;
 }
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 3248cde504ed..fefd7f971437 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -276,7 +276,13 @@ ENDPROC(ftrace_graph_caller_old)
  */
 
 .macro mcount_enter
+/*
+ * This pad compensates for the push {lr} at the call site.  Note that we are
+ * unable to unwind through a function which does not otherwise save its lr.
+ */
+ UNWIND(.pad    #4)
         stmdb   sp!, {r0-r3, lr}
+ UNWIND(.save   {r0-r3, lr})
 .endm
 
 .macro mcount_get_lr reg
@@ -289,6 +295,7 @@ ENDPROC(ftrace_graph_caller_old)
 .endm
 
 ENTRY(__gnu_mcount_nc)
+UNWIND(.fnstart)
 #ifdef CONFIG_DYNAMIC_FTRACE
         mov     ip, lr
         ldmia   sp!, {lr}
@@ -296,17 +303,22 @@ ENTRY(__gnu_mcount_nc)
 #else
         __mcount
 #endif
+UNWIND(.fnend)
 ENDPROC(__gnu_mcount_nc)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(ftrace_caller)
+UNWIND(.fnstart)
         __ftrace_caller
+UNWIND(.fnend)
 ENDPROC(ftrace_caller)
 #endif
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 ENTRY(ftrace_graph_caller)
+UNWIND(.fnstart)
         __ftrace_graph_caller
+UNWIND(.fnend)
 ENDPROC(ftrace_graph_caller)
 #endif
 
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index e0eb9a1cae77..8bac553fe213 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -267,7 +267,7 @@ __create_page_tables:
         addne   r6, r6, #1 << SECTION_SHIFT
         strne   r6, [r3]
 
-#if defined(CONFIG_LPAE) && defined(CONFIG_CPU_ENDIAN_BE8)
+#if defined(CONFIG_ARM_LPAE) && defined(CONFIG_CPU_ENDIAN_BE8)
         sub     r4, r4, #4                      @ Fixup page table pointer
                                                 @ for 64-bit descriptors
 #endif
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 96093b75ab90..1fd749ee4a1b 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -966,7 +966,7 @@ static void reset_ctrl_regs(void *unused)
         }
 
         if (err) {
-                pr_warning("CPU %d debug is powered down!\n", cpu);
+                pr_warn_once("CPU %d debug is powered down!\n", cpu);
                 cpumask_or(&debug_err_mask, &debug_err_mask, cpumask_of(cpu));
                 return;
         }
@@ -987,7 +987,7 @@ clear_vcr:
         isb();
 
         if (cpumask_intersects(&debug_err_mask, cpumask_of(cpu))) {
-                pr_warning("CPU %d failed to disable vector catch\n", cpu);
+                pr_warn_once("CPU %d failed to disable vector catch\n", cpu);
                 return;
         }
 
@@ -1007,7 +1007,7 @@ clear_vcr:
         }
 
         if (cpumask_intersects(&debug_err_mask, cpumask_of(cpu))) {
-                pr_warning("CPU %d failed to clear debug register pairs\n", cpu);
+                pr_warn_once("CPU %d failed to clear debug register pairs\n", cpu);
                 return;
         }
 
@@ -1043,7 +1043,7 @@ static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action,
         return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata dbg_cpu_pm_nb = {
+static struct notifier_block dbg_cpu_pm_nb = {
         .notifier_call = dbg_cpu_pm_notify,
 };
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 146157dfe27c..8c3094d0f7b7 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -253,7 +253,10 @@ validate_event(struct pmu_hw_events *hw_events,
         struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
         struct pmu *leader_pmu = event->group_leader->pmu;
 
-        if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
+        if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+                return 1;
+
+        if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
                 return 1;
 
         return armpmu->get_event_idx(hw_events, event) >= 0;
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 047d3e40e470..c9a5e2ce8aa9 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -57,38 +57,6 @@ static const char *isa_modes[] = {
   "ARM" , "Thumb" , "Jazelle", "ThumbEE"
 };
 
-static volatile int hlt_counter;
-
-void disable_hlt(void)
-{
-        hlt_counter++;
-}
-
-EXPORT_SYMBOL(disable_hlt);
-
-void enable_hlt(void)
-{
-        hlt_counter--;
-        BUG_ON(hlt_counter < 0);
-}
-
-EXPORT_SYMBOL(enable_hlt);
-
-static int __init nohlt_setup(char *__unused)
-{
-        hlt_counter = 1;
-        return 1;
-}
-
-static int __init hlt_setup(char *__unused)
-{
-        hlt_counter = 0;
-        return 1;
-}
-
-__setup("nohlt", nohlt_setup);
-__setup("hlt", hlt_setup);
-
 extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
 typedef void (*phys_reset_t)(unsigned long);
 
@@ -172,54 +140,38 @@ static void default_idle(void)
         local_irq_enable();
 }
 
-/*
- * The idle thread.
- * We always respect 'hlt_counter' to prevent low power idle.
- */
-void cpu_idle(void)
+void arch_cpu_idle_prepare(void)
 {
         local_fiq_enable();
+}
 
-        /* endless idle loop with no priority at all */
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                ledtrig_cpu(CPU_LED_IDLE_START);
-                while (!need_resched()) {
-#ifdef CONFIG_HOTPLUG_CPU
-                        if (cpu_is_offline(smp_processor_id()))
-                                cpu_die();
+void arch_cpu_idle_enter(void)
+{
+        ledtrig_cpu(CPU_LED_IDLE_START);
+#ifdef CONFIG_PL310_ERRATA_769419
+        wmb();
 #endif
+}
 
-                        /*
-                         * We need to disable interrupts here
-                         * to ensure we don't miss a wakeup call.
-                         */
-                        local_irq_disable();
-#ifdef CONFIG_PL310_ERRATA_769419
-                        wmb();
+void arch_cpu_idle_exit(void)
+{
+        ledtrig_cpu(CPU_LED_IDLE_END);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+void arch_cpu_idle_dead(void)
+{
+        cpu_die();
+}
 #endif
-                        if (hlt_counter) {
-                                local_irq_enable();
-                                cpu_relax();
-                        } else if (!need_resched()) {
-                                stop_critical_timings();
-                                if (cpuidle_idle_call())
-                                        default_idle();
-                                start_critical_timings();
-                                /*
-                                 * default_idle functions must always
-                                 * return with IRQs enabled.
-                                 */
-                                WARN_ON(irqs_disabled());
-                        } else
-                                local_irq_enable();
-                }
-                ledtrig_cpu(CPU_LED_IDLE_END);
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                schedule_preempt_disabled();
-        }
+
+/*
+ * Called from the core idle loop.
+ */
+void arch_cpu_idle(void)
+{
+        if (cpuidle_idle_call())
+                default_idle();
 }
 
 static char reboot_mode = 'h';
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index bd6f56b9ec21..59d2adb764a9 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -45,12 +45,12 @@ static u32 notrace jiffy_sched_clock_read(void)
 
 static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
 
-static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 {
         return (cyc * mult) >> shift;
 }
 
-static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask)
+static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
 {
         u64 epoch_ns;
         u32 epoch_cyc;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 3f6cbb2e3eda..234e339196c0 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -56,7 +56,6 @@
 #include <asm/virt.h>
 
 #include "atags.h"
-#include "tcm.h"
 
 
 #if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE)
@@ -353,6 +352,23 @@ void __init early_print(const char *str, ...)
         printk("%s", buf);
 }
 
+static void __init cpuid_init_hwcaps(void)
+{
+        unsigned int divide_instrs;
+
+        if (cpu_architecture() < CPU_ARCH_ARMv7)
+                return;
+
+        divide_instrs = (read_cpuid_ext(CPUID_EXT_ISAR0) & 0x0f000000) >> 24;
+
+        switch (divide_instrs) {
+        case 2:
+                elf_hwcap |= HWCAP_IDIVA;
+        case 1:
+                elf_hwcap |= HWCAP_IDIVT;
+        }
+}
+
 static void __init feat_v6_fixup(void)
 {
         int id = read_cpuid_id();
@@ -483,8 +499,11 @@ static void __init setup_processor(void)
         snprintf(elf_platform, ELF_PLATFORM_SIZE, "%s%c",
                  list->elf_name, ENDIANNESS);
         elf_hwcap = list->elf_hwcap;
+
+        cpuid_init_hwcaps();
+
 #ifndef CONFIG_ARM_THUMB
-        elf_hwcap &= ~HWCAP_THUMB;
+        elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT);
 #endif
 
         feat_v6_fixup();
@@ -524,7 +543,7 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
         size -= start & ~PAGE_MASK;
         bank->start = PAGE_ALIGN(start);
 
-#ifndef CONFIG_LPAE
+#ifndef CONFIG_ARM_LPAE
         if (bank->start + size < bank->start) {
                 printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in "
                         "32-bit physical address space\n", (long long)start);
@@ -778,8 +797,6 @@ void __init setup_arch(char **cmdline_p)
 
         reserve_crashkernel();
 
-        tcm_init();
-
 #ifdef CONFIG_MULTI_IRQ_HANDLER
         handle_arch_irq = mdesc->handle_irq;
 #endif
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 31644f1978d5..4619177bcfe6 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -336,7 +336,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
         /*
          * OK, it's off to the idle thread for us
          */
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
@@ -480,7 +480,7 @@ static void __cpuinit broadcast_timer_setup(struct clock_event_device *evt)
         evt->features   = CLOCK_EVT_FEAT_ONESHOT |
                           CLOCK_EVT_FEAT_PERIODIC |
                           CLOCK_EVT_FEAT_DUMMY;
-        evt->rating     = 400;
+        evt->rating     = 100;
         evt->mult       = 1;
         evt->set_mode   = broadcast_timer_set_mode;
 
@@ -673,9 +673,6 @@ static int cpufreq_callback(struct notifier_block *nb,
         if (freq->flags & CPUFREQ_CONST_LOOPS)
                 return NOTIFY_OK;
 
-        if (arm_delay_ops.const_clock)
-                return NOTIFY_OK;
-
         if (!per_cpu(l_p_j_ref, cpu)) {
                 per_cpu(l_p_j_ref, cpu) =
                         per_cpu(cpu_data, cpu).loops_per_jiffy;
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index bd0300531399..e82e1d248772 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -12,6 +12,7 @@
 
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
 
 /**********************************************************************/
 
@@ -69,12 +70,72 @@ static inline void ipi_flush_bp_all(void *ignored)
         local_flush_bp_all();
 }
 
+#ifdef CONFIG_ARM_ERRATA_798181
+static int erratum_a15_798181(void)
+{
+        unsigned int midr = read_cpuid_id();
+
+        /* Cortex-A15 r0p0..r3p2 affected */
+        if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2)
+                return 0;
+        return 1;
+}
+#else
+static int erratum_a15_798181(void)
+{
+        return 0;
+}
+#endif
+
+static void ipi_flush_tlb_a15_erratum(void *arg)
+{
+        dmb();
+}
+
+static void broadcast_tlb_a15_erratum(void)
+{
+        if (!erratum_a15_798181())
+                return;
+
+        dummy_flush_tlb_a15_erratum();
+        smp_call_function_many(cpu_online_mask, ipi_flush_tlb_a15_erratum,
+                               NULL, 1);
+}
+
+static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
+{
+        int cpu;
+        cpumask_t mask = { CPU_BITS_NONE };
+
+        if (!erratum_a15_798181())
+                return;
+
+        dummy_flush_tlb_a15_erratum();
+        for_each_online_cpu(cpu) {
+                if (cpu == smp_processor_id())
+                        continue;
+                /*
+                 * We only need to send an IPI if the other CPUs are running
+                 * the same ASID as the one being invalidated. There is no
+                 * need for locking around the active_asids check since the
+                 * switch_mm() function has at least one dmb() (as required by
+                 * this workaround) in case a context switch happens on
+                 * another CPU after the condition below.
+                 */
+                if (atomic64_read(&mm->context.id) ==
+                    atomic64_read(&per_cpu(active_asids, cpu)))
+                        cpumask_set_cpu(cpu, &mask);
+        }
+        smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1);
+}
+
 void flush_tlb_all(void)
 {
         if (tlb_ops_need_broadcast())
                 on_each_cpu(ipi_flush_tlb_all, NULL, 1);
         else
                 local_flush_tlb_all();
+        broadcast_tlb_a15_erratum();
 }
 
 void flush_tlb_mm(struct mm_struct *mm)
@@ -83,6 +144,7 @@ void flush_tlb_mm(struct mm_struct *mm)
                 on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1);
         else
                 local_flush_tlb_mm(mm);
+        broadcast_tlb_mm_a15_erratum(mm);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
@@ -95,6 +157,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
                                         &ta, 1);
         } else
                 local_flush_tlb_page(vma, uaddr);
+        broadcast_tlb_mm_a15_erratum(vma->vm_mm);
 }
 
 void flush_tlb_kernel_page(unsigned long kaddr)
@@ -105,6 +168,7 @@ void flush_tlb_kernel_page(unsigned long kaddr)
                 on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
         } else
                 local_flush_tlb_kernel_page(kaddr);
+        broadcast_tlb_a15_erratum();
 }
 
 void flush_tlb_range(struct vm_area_struct *vma,
@@ -119,6 +183,7 @@ void flush_tlb_range(struct vm_area_struct *vma,
                                         &ta, 1);
         } else
                 local_flush_tlb_range(vma, start, end);
+        broadcast_tlb_mm_a15_erratum(vma->vm_mm);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
@@ -130,6 +195,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
                 on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
         } else
                 local_flush_tlb_kernel_range(start, end);
+        broadcast_tlb_a15_erratum();
 }
 
 void flush_bp_all(void)
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
index 30ae6bb4a310..f50f19e5c138 100644
--- a/arch/arm/kernel/tcm.c
+++ b/arch/arm/kernel/tcm.c
@@ -17,7 +17,6 @@
 #include <asm/mach/map.h>
 #include <asm/memory.h>
 #include <asm/system_info.h>
-#include "tcm.h"
 
 static struct gen_pool *tcm_pool;
 static bool dtcm_present;
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 79282ebcd939..f10316b4ecdc 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -100,7 +100,7 @@ static void __init parse_dt_topology(void)
         int alloc_size, cpu = 0;
 
         alloc_size = nr_cpu_ids * sizeof(struct cpu_capacity);
-        cpu_capacity = (struct cpu_capacity *)kzalloc(alloc_size, GFP_NOWAIT);
+        cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
 
         while ((cn = of_find_node_by_type(cn, "cpu"))) {
                 const u32 *rate, *reg;
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 5a936988eb24..842098d78f58 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -201,6 +201,7 @@ int kvm_dev_ioctl_check_extension(long ext)
                 break;
         case KVM_CAP_ARM_SET_DEVICE_ADDR:
                 r = 1;
+                break;
         case KVM_CAP_NR_VCPUS:
                 r = num_online_cpus();
                 break;
@@ -613,7 +614,7 @@ static int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
                 if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers)
                     || !arm_exit_handlers[hsr_ec]) {
-                        kvm_err("Unkown exception class: %#08lx, "
+                        kvm_err("Unknown exception class: %#08lx, "
                                 "hsr: %#08x\n", hsr_ec,
                                 (unsigned int)vcpu->arch.hsr);
                         BUG();
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 4ea9a982269c..7bed7556077a 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -79,11 +79,11 @@ static bool access_dcsw(struct kvm_vcpu *vcpu,
         u32 val;
         int cpu;
 
-        cpu = get_cpu();
-
         if (!p->is_write)
                 return read_from_write_only(vcpu, p);
 
+        cpu = get_cpu();
+
         cpumask_setall(&vcpu->arch.require_dcache_flush);
         cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush);
 
diff --git a/arch/arm/kvm/vgic.c b/arch/arm/kvm/vgic.c
index c9a17316e9fe..0e4cfe123b38 100644
--- a/arch/arm/kvm/vgic.c
+++ b/arch/arm/kvm/vgic.c
@@ -883,8 +883,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
                           lr, irq, vgic_cpu->vgic_lr[lr]);
                 BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
                 vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT;
-
-                goto out;
+                return true;
         }
 
         /* Try to use another LR for this interrupt */
@@ -898,7 +897,6 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
         vgic_cpu->vgic_irq_lr_map[irq] = lr;
         set_bit(lr, vgic_cpu->lr_used);
 
-out:
         if (!vgic_irq_is_edge(vcpu, irq))
                 vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI;
 
@@ -1018,21 +1016,6 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 
         kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr);
 
-        /*
-         * We do not need to take the distributor lock here, since the only
-         * action we perform is clearing the irq_active_bit for an EOIed
-         * level interrupt.  There is a potential race with
-         * the queuing of an interrupt in __kvm_vgic_flush_hwstate(), where we
-         * check if the interrupt is already active. Two possibilities:
-         *
-         * - The queuing is occurring on the same vcpu: cannot happen,
-         *   as we're already in the context of this vcpu, and
-         *   executing the handler
-         * - The interrupt has been migrated to another vcpu, and we
-         *   ignore this interrupt for this run. Big deal. It is still
-         *   pending though, and will get considered when this vcpu
-         *   exits.
-         */
         if (vgic_cpu->vgic_misr & GICH_MISR_EOI) {
                 /*
                  * Some level interrupts have been EOIed. Clear their
@@ -1054,6 +1037,13 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
                         } else {
                                 vgic_cpu_irq_clear(vcpu, irq);
                         }
+
+                        /*
+                         * Despite being EOIed, the LR may not have
+                         * been marked as empty.
+                         */
+                        set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr);
+                        vgic_cpu->vgic_lr[lr] &= ~GICH_LR_ACTIVE_BIT;
                 }
         }
 
@@ -1064,9 +1054,8 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Sync back the VGIC state after a guest run. We do not really touch
- * the distributor here (the irq_pending_on_cpu bit is safe to set),
- * so there is no need for taking its lock.
+ * Sync back the VGIC state after a guest run. The distributor lock is
+ * needed so we don't get preempted in the middle of the state processing.
  */
 static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
@@ -1112,10 +1101,14 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
+        struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
         if (!irqchip_in_kernel(vcpu->kvm))
                 return;
 
+        spin_lock(&dist->lock);
         __kvm_vgic_sync_hwstate(vcpu);
+        spin_unlock(&dist->lock);
 }
 
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
index 6b93f6a1a3c7..64dbfa57204a 100644
--- a/arch/arm/lib/delay.c
+++ b/arch/arm/lib/delay.c
@@ -58,7 +58,7 @@ static void __timer_delay(unsigned long cycles)
 static void __timer_const_udelay(unsigned long xloops)
 {
         unsigned long long loops = xloops;
-        loops *= loops_per_jiffy;
+        loops *= arm_delay_ops.ticks_per_jiffy;
         __timer_delay(loops >> UDELAY_SHIFT);
 }
 
@@ -73,11 +73,13 @@ void __init register_current_timer_delay(const struct delay_timer *timer)
                 pr_info("Switching to timer-based delay loop\n");
                 delay_timer                     = timer;
                 lpj_fine                        = timer->freq / HZ;
-                loops_per_jiffy                 = lpj_fine;
+
+                /* cpufreq may scale loops_per_jiffy, so keep a private copy */
+                arm_delay_ops.ticks_per_jiffy   = lpj_fine;
                 arm_delay_ops.delay             = __timer_delay;
                 arm_delay_ops.const_udelay      = __timer_const_udelay;
                 arm_delay_ops.udelay            = __timer_udelay;
-                arm_delay_ops.const_clock       = true;
+
                 delay_calibrated                = true;
         } else {
                 pr_info("Ignoring duplicate/late registration of read_current_timer delay\n");
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index d912e7397ecc..94b0650ea98f 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -14,31 +14,15 @@
 
         .text
         .align  5
-        .word   0
-
-1:      subs    r2, r2, #4              @ 1 do we have enough
-        blt     5f                      @ 1 bytes to align with?
-        cmp     r3, #2                  @ 1
-        strltb  r1, [ip], #1            @ 1
-        strleb  r1, [ip], #1            @ 1
-        strb    r1, [ip], #1            @ 1
-        add     r2, r2, r3              @ 1 (r2 = r2 - (4 - r3))
-/*
- * The pointer is now aligned and the length is adjusted.  Try doing the
- * memset again.
- */
 
 ENTRY(memset)
-/*
- * Preserve the contents of r0 for the return value.
- */
-        mov     ip, r0
-        ands    r3, ip, #3              @ 1 unaligned?
-        bne     1b                      @ 1
+        ands    r3, r0, #3              @ 1 unaligned?
+        mov     ip, r0                  @ preserve r0 as return value
+        bne     6f                      @ 1
 /*
  * we know that the pointer in ip is aligned to a word boundary.
  */
-        orr     r1, r1, r1, lsl #8
+1:      orr     r1, r1, r1, lsl #8
         orr     r1, r1, r1, lsl #16
         mov     r3, r1
         cmp     r2, #16
@@ -127,4 +111,13 @@ ENTRY(memset)
         tst     r2, #1
         strneb  r1, [ip], #1
         mov     pc, lr
+
+6:      subs    r2, r2, #4              @ 1 do we have enough
+        blt     5b                      @ 1 bytes to align with?
+        cmp     r3, #2                  @ 1
+        strltb  r1, [ip], #1            @ 1
+        strleb  r1, [ip], #1            @ 1
+        strb    r1, [ip], #1            @ 1
+        add     r2, r2, r3              @ 1 (r2 = r2 - (4 - r3))
+        b       1b
 ENDPROC(memset)
diff --git a/arch/arm/mach-at91/at91sam9260.c b/arch/arm/mach-at91/at91sam9260.c
index b67cd5374117..44199bc2c665 100644
--- a/arch/arm/mach-at91/at91sam9260.c
+++ b/arch/arm/mach-at91/at91sam9260.c
@@ -232,6 +232,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
         CLKDEV_CON_DEV_ID("t2_clk", "fffdc000.timer", &tc5_clk),
         CLKDEV_CON_DEV_ID("hclk", "500000.ohci", &ohci_clk),
         CLKDEV_CON_DEV_ID("mci_clk", "fffa8000.mmc", &mmc_clk),
+        CLKDEV_CON_DEV_ID("spi_clk", "fffc8000.spi", &spi0_clk),
+        CLKDEV_CON_DEV_ID("spi_clk", "fffcc000.spi", &spi1_clk),
         /* fake hclk clock */
         CLKDEV_CON_DEV_ID("hclk", "at91_ohci", &ohci_clk),
         CLKDEV_CON_ID("pioA", &pioA_clk),
diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c
index d3addee43d8d..2ec5efea3f03 100644
--- a/arch/arm/mach-at91/at91sam9g45.c
+++ b/arch/arm/mach-at91/at91sam9g45.c
@@ -262,6 +262,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
         CLKDEV_CON_DEV_ID("mci_clk", "fffd0000.mmc", &mmc1_clk),
         CLKDEV_CON_DEV_ID(NULL, "fff84000.i2c", &twi0_clk),
         CLKDEV_CON_DEV_ID(NULL, "fff88000.i2c", &twi1_clk),
+        CLKDEV_CON_DEV_ID("spi_clk", "fffa4000.spi", &spi0_clk),
+        CLKDEV_CON_DEV_ID("spi_clk", "fffa8000.spi", &spi1_clk),
         /* fake hclk clock */
         CLKDEV_CON_DEV_ID("hclk", "at91_ohci", &uhphs_clk),
         CLKDEV_CON_DEV_ID(NULL, "fffff200.gpio", &pioA_clk),
diff --git a/arch/arm/mach-at91/at91sam9n12.c b/arch/arm/mach-at91/at91sam9n12.c
index 5dfc8fd87103..ccd078355eed 100644
--- a/arch/arm/mach-at91/at91sam9n12.c
+++ b/arch/arm/mach-at91/at91sam9n12.c
@@ -172,6 +172,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
         CLKDEV_CON_DEV_ID("dma_clk", "ffffec00.dma-controller", &dma_clk),
         CLKDEV_CON_DEV_ID(NULL, "f8010000.i2c", &twi0_clk),
         CLKDEV_CON_DEV_ID(NULL, "f8014000.i2c", &twi1_clk),
+        CLKDEV_CON_DEV_ID("spi_clk", "f0000000.spi", &spi0_clk),
+        CLKDEV_CON_DEV_ID("spi_clk", "f0004000.spi", &spi1_clk),
         CLKDEV_CON_DEV_ID(NULL, "fffff400.gpio", &pioAB_clk),
         CLKDEV_CON_DEV_ID(NULL, "fffff600.gpio", &pioAB_clk),
         CLKDEV_CON_DEV_ID(NULL, "fffff800.gpio", &pioCD_clk),
diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c
index 44a9a62dcc13..a200d8a17123 100644
--- a/arch/arm/mach-at91/at91sam9x5.c
+++ b/arch/arm/mach-at91/at91sam9x5.c
@@ -237,6 +237,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
         CLKDEV_CON_DEV_ID(NULL, "f8010000.i2c", &twi0_clk),
         CLKDEV_CON_DEV_ID(NULL, "f8014000.i2c", &twi1_clk),
         CLKDEV_CON_DEV_ID(NULL, "f8018000.i2c", &twi2_clk),
+        CLKDEV_CON_DEV_ID("spi_clk", "f0000000.spi", &spi0_clk),
+        CLKDEV_CON_DEV_ID("spi_clk", "f0004000.spi", &spi1_clk),
         CLKDEV_CON_DEV_ID(NULL, "fffff400.gpio", &pioAB_clk),
         CLKDEV_CON_DEV_ID(NULL, "fffff600.gpio", &pioAB_clk),
         CLKDEV_CON_DEV_ID(NULL, "fffff800.gpio", &pioCD_clk),
diff --git a/arch/arm/mach-at91/board-foxg20.c b/arch/arm/mach-at91/board-foxg20.c
index 2ea7059b840b..c20a870ea9c9 100644
--- a/arch/arm/mach-at91/board-foxg20.c
+++ b/arch/arm/mach-at91/board-foxg20.c
@@ -176,6 +176,7 @@ static struct w1_gpio_platform_data w1_gpio_pdata = {
         /* If you choose to use a pin other than PB16 it needs to be 3.3V */
         .pin            = AT91_PIN_PB16,
         .is_open_drain  = 1,
+        .ext_pullup_enable_pin  = -EINVAL,
 };
 
 static struct platform_device w1_device = {
diff --git a/arch/arm/mach-at91/board-stamp9g20.c b/arch/arm/mach-at91/board-stamp9g20.c
index a033b8df9fb2..869cbecf00b7 100644
--- a/arch/arm/mach-at91/board-stamp9g20.c
+++ b/arch/arm/mach-at91/board-stamp9g20.c
@@ -188,6 +188,7 @@ static struct spi_board_info portuxg20_spi_devices[] = {
 static struct w1_gpio_platform_data w1_gpio_pdata = {
         .pin            = AT91_PIN_PA29,
         .is_open_drain  = 1,
+        .ext_pullup_enable_pin  = -EINVAL,
 };
 
 static struct platform_device w1_device = {
diff --git a/arch/arm/mach-at91/include/mach/gpio.h b/arch/arm/mach-at91/include/mach/gpio.h
index eed465ab0dd7..5fc23771c154 100644
--- a/arch/arm/mach-at91/include/mach/gpio.h
+++ b/arch/arm/mach-at91/include/mach/gpio.h
@@ -209,6 +209,14 @@ extern int at91_get_gpio_value(unsigned pin);
 extern void at91_gpio_suspend(void);
 extern void at91_gpio_resume(void);
 
+#ifdef CONFIG_PINCTRL_AT91
+extern void at91_pinctrl_gpio_suspend(void);
+extern void at91_pinctrl_gpio_resume(void);
+#else
+static inline void at91_pinctrl_gpio_suspend(void) {}
+static inline void at91_pinctrl_gpio_resume(void) {}
+#endif
+
 #endif  /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm/mach-at91/irq.c b/arch/arm/mach-at91/irq.c
index 8e210262aeee..e0ca59171022 100644
--- a/arch/arm/mach-at91/irq.c
+++ b/arch/arm/mach-at91/irq.c
@@ -92,23 +92,21 @@ static int at91_aic_set_wake(struct irq_data *d, unsigned value)
 
 void at91_irq_suspend(void)
 {
-        int i = 0, bit;
+        int bit = -1;
 
         if (has_aic5()) {
                 /* disable enabled irqs */
-                while ((bit = find_next_bit(backups, n_irqs, i)) < n_irqs) {
+                while ((bit = find_next_bit(backups, n_irqs, bit + 1)) < n_irqs) {
                         at91_aic_write(AT91_AIC5_SSR,
                                        bit & AT91_AIC5_INTSEL_MSK);
                         at91_aic_write(AT91_AIC5_IDCR, 1);
-                        i = bit;
                 }
                 /* enable wakeup irqs */
-                i = 0;
-                while ((bit = find_next_bit(wakeups, n_irqs, i)) < n_irqs) {
+                bit = -1;
+                while ((bit = find_next_bit(wakeups, n_irqs, bit + 1)) < n_irqs) {
                         at91_aic_write(AT91_AIC5_SSR,
                                        bit & AT91_AIC5_INTSEL_MSK);
                         at91_aic_write(AT91_AIC5_IECR, 1);
-                        i = bit;
                 }
         } else {
                 at91_aic_write(AT91_AIC_IDCR, *backups);
@@ -118,23 +116,21 @@ void at91_irq_suspend(void)
 
 void at91_irq_resume(void)
 {
-        int i = 0, bit;
+        int bit = -1;
 
         if (has_aic5()) {
                 /* disable wakeup irqs */
-                while ((bit = find_next_bit(wakeups, n_irqs, i)) < n_irqs) {
+                while ((bit = find_next_bit(wakeups, n_irqs, bit + 1)) < n_irqs) {
                         at91_aic_write(AT91_AIC5_SSR,
                                        bit & AT91_AIC5_INTSEL_MSK);
                         at91_aic_write(AT91_AIC5_IDCR, 1);
-                        i = bit;
                 }
                 /* enable irqs disabled for suspend */
-                i = 0;
-                while ((bit = find_next_bit(backups, n_irqs, i)) < n_irqs) {
+                bit = -1;
+                while ((bit = find_next_bit(backups, n_irqs, bit + 1)) < n_irqs) {
                         at91_aic_write(AT91_AIC5_SSR,
                                        bit & AT91_AIC5_INTSEL_MSK);
                         at91_aic_write(AT91_AIC5_IECR, 1);
-                        i = bit;
                 }
         } else {
                 at91_aic_write(AT91_AIC_IDCR, *wakeups);
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index adb6db888a1f..73f1f250403a 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -201,7 +201,10 @@ extern u32 at91_slow_clock_sz;
 
 static int at91_pm_enter(suspend_state_t state)
 {
-        at91_gpio_suspend();
+        if (of_have_populated_dt())
+                at91_pinctrl_gpio_suspend();
+        else
+                at91_gpio_suspend();
         at91_irq_suspend();
 
         pr_debug("AT91: PM - wake mask %08x, pm state %d\n",
@@ -286,7 +289,10 @@ static int at91_pm_enter(suspend_state_t state)
 error:
         target_state = PM_SUSPEND_ON;
         at91_irq_resume();
-        at91_gpio_resume();
+        if (of_have_populated_dt())
+                at91_pinctrl_gpio_resume();
+        else
+                at91_gpio_resume();
         return 0;
 }
 
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index bf02471d7e7c..f11289519c39 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -6,6 +6,7 @@ config ARCH_BCM
         select ARM_ERRATA_764369 if SMP
         select ARM_GIC
         select CPU_V7
+        select CLKSRC_OF
         select GENERIC_CLOCKEVENTS
         select GENERIC_TIME
         select GPIO_BCM
diff --git a/arch/arm/mach-bcm/board_bcm.c b/arch/arm/mach-bcm/board_bcm.c
index f0f9abafad29..259593540477 100644
--- a/arch/arm/mach-bcm/board_bcm.c
+++ b/arch/arm/mach-bcm/board_bcm.c
@@ -16,14 +16,11 @@
 #include <linux/device.h>
 #include <linux/platform_device.h>
 #include <linux/irqchip.h>
+#include <linux/clocksource.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 
-static void timer_init(void)
-{
-}
-
 
 static void __init board_init(void)
 {
@@ -35,7 +32,7 @@ static const char * const bcm11351_dt_compat[] = { "bcm,bcm11351", NULL, };
 
 DT_MACHINE_START(BCM11351_DT, "Broadcom Application Processor")
         .init_irq = irqchip_init,
-        .init_time = timer_init,
+        .init_time = clocksource_of_init,
         .init_machine = board_init,
         .dt_compat = bcm11351_dt_compat,
 MACHINE_END
diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c
index e698f26cc0cb..52e4bb5cf12d 100644
--- a/arch/arm/mach-cns3xxx/core.c
+++ b/arch/arm/mach-cns3xxx/core.c
@@ -22,19 +22,9 @@
 
 static struct map_desc cns3xxx_io_desc[] __initdata = {
         {
-                .virtual        = CNS3XXX_TC11MP_TWD_BASE_VIRT,
-                .pfn            = __phys_to_pfn(CNS3XXX_TC11MP_TWD_BASE),
-                .length         = SZ_4K,
-                .type           = MT_DEVICE,
-        }, {
-                .virtual        = CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT,
-                .pfn            = __phys_to_pfn(CNS3XXX_TC11MP_GIC_CPU_BASE),
-                .length         = SZ_4K,
-                .type           = MT_DEVICE,
-        }, {
-                .virtual        = CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT,
-                .pfn            = __phys_to_pfn(CNS3XXX_TC11MP_GIC_DIST_BASE),
-                .length         = SZ_4K,
+                .virtual        = CNS3XXX_TC11MP_SCU_BASE_VIRT,
+                .pfn            = __phys_to_pfn(CNS3XXX_TC11MP_SCU_BASE),
+                .length         = SZ_8K,
                 .type           = MT_DEVICE,
         }, {
                 .virtual        = CNS3XXX_TIMER1_2_3_BASE_VIRT,
diff --git a/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h b/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h
index 191c8e57f289..b1021aafa481 100644
--- a/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h
+++ b/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h
@@ -94,10 +94,10 @@
 #define RTC_INTR_STS_OFFSET                     0x34
 
 #define CNS3XXX_MISC_BASE                       0x76000000      /* Misc Control */
-#define CNS3XXX_MISC_BASE_VIRT                  0xFFF07000      /* Misc Control */
+#define CNS3XXX_MISC_BASE_VIRT                  0xFB000000      /* Misc Control */
 
 #define CNS3XXX_PM_BASE                         0x77000000      /* Power Management Control */
-#define CNS3XXX_PM_BASE_VIRT                    0xFFF08000
+#define CNS3XXX_PM_BASE_VIRT                    0xFB001000
 
 #define PM_CLK_GATE_OFFSET                      0x00
 #define PM_SOFT_RST_OFFSET                      0x04
@@ -109,7 +109,7 @@
 #define PM_PLL_HM_PD_OFFSET                     0x1C
 
 #define CNS3XXX_UART0_BASE                      0x78000000      /* UART 0 */
-#define CNS3XXX_UART0_BASE_VIRT                 0xFFF09000
+#define CNS3XXX_UART0_BASE_VIRT                 0xFB002000
 
 #define CNS3XXX_UART1_BASE                      0x78400000      /* UART 1 */
 #define CNS3XXX_UART1_BASE_VIRT                 0xFFF0A000
@@ -130,7 +130,7 @@
 #define CNS3XXX_I2S_BASE_VIRT                   0xFFF10000
 
 #define CNS3XXX_TIMER1_2_3_BASE                 0x7C800000      /* Timer */
-#define CNS3XXX_TIMER1_2_3_BASE_VIRT            0xFFF10800
+#define CNS3XXX_TIMER1_2_3_BASE_VIRT            0xFB003000
 
 #define TIMER1_COUNTER_OFFSET                   0x00
 #define TIMER1_AUTO_RELOAD_OFFSET               0x04
@@ -227,16 +227,16 @@
  * Testchip peripheral and fpga gic regions
  */
 #define CNS3XXX_TC11MP_SCU_BASE                 0x90000000      /* IRQ, Test chip */
-#define CNS3XXX_TC11MP_SCU_BASE_VIRT            0xFF000000
+#define CNS3XXX_TC11MP_SCU_BASE_VIRT            0xFB004000
 
 #define CNS3XXX_TC11MP_GIC_CPU_BASE             0x90000100      /* Test chip interrupt controller CPU interface */
-#define CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT        0xFF000100
+#define CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT        (CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x100)
 
 #define CNS3XXX_TC11MP_TWD_BASE                 0x90000600
-#define CNS3XXX_TC11MP_TWD_BASE_VIRT            0xFF000600
+#define CNS3XXX_TC11MP_TWD_BASE_VIRT            (CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x600)
 
 #define CNS3XXX_TC11MP_GIC_DIST_BASE            0x90001000      /* Test chip interrupt controller distributor */
-#define CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT       0xFF001000
+#define CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT       (CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x1000)
 
 #define CNS3XXX_TC11MP_L220_BASE                0x92002000      /* L220 registers */
 #define CNS3XXX_TC11MP_L220_BASE_VIRT           0xFF002000
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index 147b8e1a4407..886481c12173 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -242,6 +242,73 @@ static struct vpfe_config vpfe_cfg = {
         .ccdc = "DM355 CCDC",
 };
 
+/* venc standards timings */
+static struct vpbe_enc_mode_info dm355evm_enc_preset_timing[] = {
+        {
+                .name           = "ntsc",
+                .timings_type   = VPBE_ENC_STD,
+                .std_id         = V4L2_STD_NTSC,
+                .interlaced     = 1,
+                .xres           = 720,
+                .yres           = 480,
+                .aspect         = {11, 10},
+                .fps            = {30000, 1001},
+                .left_margin    = 0x79,
+                .upper_margin   = 0x10,
+        },
+        {
+                .name           = "pal",
+                .timings_type   = VPBE_ENC_STD,
+                .std_id         = V4L2_STD_PAL,
+                .interlaced     = 1,
+                .xres           = 720,
+                .yres           = 576,
+                .aspect         = {54, 59},
+                .fps            = {25, 1},
+                .left_margin    = 0x7E,
+                .upper_margin   = 0x16
+        },
+};
+
+#define VENC_STD_ALL    (V4L2_STD_NTSC | V4L2_STD_PAL)
+
+/*
+ * The outputs available from VPBE + ecnoders. Keep the
+ * the order same as that of encoders. First those from venc followed by that
+ * from encoders. Index in the output refers to index on a particular encoder.
+ * Driver uses this index to pass it to encoder when it supports more than
+ * one output. Application uses index of the array to set an output.
+ */
+static struct vpbe_output dm355evm_vpbe_outputs[] = {
+        {
+                .output         = {
+                        .index          = 0,
+                        .name           = "Composite",
+                        .type           = V4L2_OUTPUT_TYPE_ANALOG,
+                        .std            = VENC_STD_ALL,
+                        .capabilities   = V4L2_OUT_CAP_STD,
+                },
+                .subdev_name    = DM355_VPBE_VENC_SUBDEV_NAME,
+                .default_mode   = "ntsc",
+                .num_modes      = ARRAY_SIZE(dm355evm_enc_preset_timing),
+                .modes          = dm355evm_enc_preset_timing,
+                .if_params      = V4L2_MBUS_FMT_FIXED,
+        },
+};
+
+static struct vpbe_config dm355evm_display_cfg = {
+        .module_name    = "dm355-vpbe-display",
+        .i2c_adapter_id = 1,
+        .osd            = {
+                .module_name    = DM355_VPBE_OSD_SUBDEV_NAME,
+        },
+        .venc           = {
+                .module_name    = DM355_VPBE_VENC_SUBDEV_NAME,
+        },
+        .num_outputs    = ARRAY_SIZE(dm355evm_vpbe_outputs),
+        .outputs        = dm355evm_vpbe_outputs,
+};
+
 static struct platform_device *davinci_evm_devices[] __initdata = {
         &dm355evm_dm9000,
         &davinci_nand_device,
@@ -253,8 +320,6 @@ static struct davinci_uart_config uart_config __initdata = {
 
 static void __init dm355_evm_map_io(void)
 {
-        /* setup input configuration for VPFE input devices */
-        dm355_set_vpfe_config(&vpfe_cfg);
         dm355_init();
 }
 
@@ -344,6 +409,8 @@ static __init void dm355_evm_init(void)
         davinci_setup_mmc(0, &dm355evm_mmc_config);
         davinci_setup_mmc(1, &dm355evm_mmc_config);
 
+        dm355_init_video(&vpfe_cfg, &dm355evm_display_cfg);
+
         dm355_init_spi0(BIT(0), dm355_evm_spi_info,
                         ARRAY_SIZE(dm355_evm_spi_info));
 
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index c2d4958a0cb6..2a6674356585 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -27,6 +27,7 @@
 #include <linux/input.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/eeprom.h>
+#include <linux/v4l2-dv-timings.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -39,6 +40,7 @@
 #include <linux/platform_data/mtd-davinci.h>
 #include <linux/platform_data/keyscan-davinci.h>
 
+#include <media/ths7303.h>
 #include <media/tvp514x.h>
 
 #include "davinci.h"
@@ -374,6 +376,166 @@ static struct vpfe_config vpfe_cfg = {
         .ccdc = "ISIF",
 };
 
+/* venc standards timings */
+static struct vpbe_enc_mode_info dm365evm_enc_std_timing[] = {
+        {
+                .name           = "ntsc",
+                .timings_type   = VPBE_ENC_STD,
+                .std_id         = V4L2_STD_NTSC,
+                .interlaced     = 1,
+                .xres           = 720,
+                .yres           = 480,
+                .aspect         = {11, 10},
+                .fps            = {30000, 1001},
+                .left_margin    = 0x79,
+                .upper_margin   = 0x10,
+        },
+        {
+                .name           = "pal",
+                .timings_type   = VPBE_ENC_STD,
+                .std_id         = V4L2_STD_PAL,
+                .interlaced     = 1,
+                .xres           = 720,
+                .yres           = 576,
+                .aspect         = {54, 59},
+                .fps            = {25, 1},
+                .left_margin    = 0x7E,
+                .upper_margin   = 0x16,
+        },
+};
+
+/* venc dv timings */
+static struct vpbe_enc_mode_info dm365evm_enc_preset_timing[] = {
+        {
+                .name           = "480p59_94",
+                .timings_type   = VPBE_ENC_DV_TIMINGS,
+                .dv_timings     = V4L2_DV_BT_CEA_720X480P59_94,
+                .interlaced     = 0,
+                .xres           = 720,
+                .yres           = 480,
+                .aspect         = {1, 1},
+                .fps            = {5994, 100},
+                .left_margin    = 0x8F,
+                .upper_margin   = 0x2D,
+        },
+        {
+                .name           = "576p50",
+                .timings_type   = VPBE_ENC_DV_TIMINGS,
+                .dv_timings     = V4L2_DV_BT_CEA_720X576P50,
+                .interlaced     = 0,
+                .xres           = 720,
+                .yres           = 576,
+                .aspect         = {1, 1},
+                .fps            = {50, 1},
+                .left_margin    = 0x8C,
+                .upper_margin   = 0x36,
+        },
+        {
+                .name           = "720p60",
+                .timings_type   = VPBE_ENC_DV_TIMINGS,
+                .dv_timings     = V4L2_DV_BT_CEA_1280X720P60,
+                .interlaced     = 0,
+                .xres           = 1280,
+                .yres           = 720,
+                .aspect         = {1, 1},
+                .fps            = {60, 1},
+                .left_margin    = 0x117,
+                .right_margin   = 70,
+                .upper_margin   = 38,
+                .lower_margin   = 3,
+                .hsync_len      = 80,
+                .vsync_len      = 5,
+        },
+        {
+                .name           = "1080i60",
+                .timings_type   = VPBE_ENC_DV_TIMINGS,
+                .dv_timings     = V4L2_DV_BT_CEA_1920X1080I60,
+                .interlaced     = 1,
+                .xres           = 1920,
+                .yres           = 1080,
+                .aspect         = {1, 1},
+                .fps            = {30, 1},
+                .left_margin    = 0xc9,
+                .right_margin   = 80,
+                .upper_margin   = 30,
+                .lower_margin   = 3,
+                .hsync_len      = 88,
+                .vsync_len      = 5,
+        },
+};
+
+#define VENC_STD_ALL    (V4L2_STD_NTSC | V4L2_STD_PAL)
+
+/*
+ * The outputs available from VPBE + ecnoders. Keep the
+ * the order same as that of encoders. First those from venc followed by that
+ * from encoders. Index in the output refers to index on a particular
+ * encoder.Driver uses this index to pass it to encoder when it supports more
+ * than one output. Application uses index of the array to set an output.
+ */
+static struct vpbe_output dm365evm_vpbe_outputs[] = {
+        {
+                .output         = {
+                        .index          = 0,
+                        .name           = "Composite",
+                        .type           = V4L2_OUTPUT_TYPE_ANALOG,
+                        .std            = VENC_STD_ALL,
+                        .capabilities   = V4L2_OUT_CAP_STD,
+                },
+                .subdev_name    = DM365_VPBE_VENC_SUBDEV_NAME,
+                .default_mode   = "ntsc",
+                .num_modes      = ARRAY_SIZE(dm365evm_enc_std_timing),
+                .modes          = dm365evm_enc_std_timing,
+                .if_params      = V4L2_MBUS_FMT_FIXED,
+        },
+        {
+                .output         = {
+                        .index          = 1,
+                        .name           = "Component",
+                        .type           = V4L2_OUTPUT_TYPE_ANALOG,
+                        .capabilities   = V4L2_OUT_CAP_DV_TIMINGS,
+                },
+                .subdev_name    = DM365_VPBE_VENC_SUBDEV_NAME,
+                .default_mode   = "480p59_94",
+                .num_modes      = ARRAY_SIZE(dm365evm_enc_preset_timing),
+                .modes          = dm365evm_enc_preset_timing,
+                .if_params      = V4L2_MBUS_FMT_FIXED,
+        },
+};
+
+/*
+ * Amplifiers on the board
+ */
+struct ths7303_platform_data ths7303_pdata = {
+        .ch_1 = 3,
+        .ch_2 = 3,
+        .ch_3 = 3,
+        .init_enable = 1,
+};
+
+static struct amp_config_info vpbe_amp = {
+        .module_name    = "ths7303",
+        .is_i2c         = 1,
+        .board_info     = {
+                I2C_BOARD_INFO("ths7303", 0x2c),
+                .platform_data = &ths7303_pdata,
+        }
+};
+
+static struct vpbe_config dm365evm_display_cfg = {
+        .module_name    = "dm365-vpbe-display",
+        .i2c_adapter_id = 1,
+        .amp            = &vpbe_amp,
+        .osd            = {
+                .module_name    = DM365_VPBE_OSD_SUBDEV_NAME,
+        },
+        .venc           = {
+                .module_name    = DM365_VPBE_VENC_SUBDEV_NAME,
+        },
+        .num_outputs    = ARRAY_SIZE(dm365evm_vpbe_outputs),
+        .outputs        = dm365evm_vpbe_outputs,
+};
+
 static void __init evm_init_i2c(void)
 {
         davinci_init_i2c(&i2c_pdata);
@@ -564,8 +726,6 @@ static struct davinci_uart_config uart_config __initdata = {
 
 static void __init dm365_evm_map_io(void)
 {
-        /* setup input configuration for VPFE input devices */
-        dm365_set_vpfe_config(&vpfe_cfg);
         dm365_init();
 }
 
@@ -597,6 +757,8 @@ static __init void dm365_evm_init(void)
 
         davinci_setup_mmc(0, &dm365evm_mmc_config);
 
+        dm365_init_video(&vpfe_cfg, &dm365evm_display_cfg);
+
         /* maybe setup mmc1/etc ... _after_ mmc0 */
         evm_init_cpld();
 
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index 71735e7797cc..745280d4144c 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -622,7 +622,7 @@ static struct vpbe_enc_mode_info dm644xevm_enc_std_timing[] = {
         {
                 .name           = "ntsc",
                 .timings_type   = VPBE_ENC_STD,
-                .std_id         = V4L2_STD_525_60,
+                .std_id         = V4L2_STD_NTSC,
                 .interlaced     = 1,
                 .xres           = 720,
                 .yres           = 480,
@@ -634,7 +634,7 @@ static struct vpbe_enc_mode_info dm644xevm_enc_std_timing[] = {
         {
                 .name           = "pal",
                 .timings_type   = VPBE_ENC_STD,
-                .std_id         = V4L2_STD_625_50,
+                .std_id         = V4L2_STD_PAL,
                 .interlaced     = 1,
                 .xres           = 720,
                 .yres           = 576,
@@ -649,7 +649,7 @@ static struct vpbe_enc_mode_info dm644xevm_enc_std_timing[] = {
 static struct vpbe_enc_mode_info dm644xevm_enc_preset_timing[] = {
         {
                 .name           = "480p59_94",
-                .timings_type   = VPBE_ENC_CUSTOM_TIMINGS,
+                .timings_type   = VPBE_ENC_DV_TIMINGS,
                 .dv_timings     = V4L2_DV_BT_CEA_720X480P59_94,
                 .interlaced     = 0,
                 .xres           = 720,
@@ -661,7 +661,7 @@ static struct vpbe_enc_mode_info dm644xevm_enc_preset_timing[] = {
         },
         {
                 .name           = "576p50",
-                .timings_type   = VPBE_ENC_CUSTOM_TIMINGS,
+                .timings_type   = VPBE_ENC_DV_TIMINGS,
                 .dv_timings     = V4L2_DV_BT_CEA_720X576P50,
                 .interlaced     = 0,
                 .xres           = 720,
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index de7adff324dc..fc4871ac1c2c 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -514,7 +514,7 @@ static const struct vpif_output dm6467_ch0_outputs[] = {
                         .index = 1,
                         .name = "Component",
                         .type = V4L2_OUTPUT_TYPE_ANALOG,
-                        .capabilities = V4L2_OUT_CAP_CUSTOM_TIMINGS,
+                        .capabilities = V4L2_OUT_CAP_DV_TIMINGS,
                 },
                 .subdev_name = "adv7343",
                 .output_route = ADV7343_COMPONENT_ID,
diff --git a/arch/arm/mach-davinci/davinci.h b/arch/arm/mach-davinci/davinci.h
index 12d544befcfa..1ab3df423dac 100644
--- a/arch/arm/mach-davinci/davinci.h
+++ b/arch/arm/mach-davinci/davinci.h
@@ -36,12 +36,19 @@
 #include <media/davinci/vpbe_osd.h>
 
 #define DAVINCI_SYSTEM_MODULE_BASE      0x01c40000
+#define SYSMOD_VDAC_CONFIG              0x2c
 #define SYSMOD_VIDCLKCTL                0x38
 #define SYSMOD_VPSS_CLKCTL              0x44
 #define SYSMOD_VDD3P3VPWDN              0x48
 #define SYSMOD_VSCLKDIS                 0x6c
 #define SYSMOD_PUPDCTL1                 0x7c
 
+/* VPSS CLKCTL bit definitions */
+#define VPSS_MUXSEL_EXTCLK_ENABLE       BIT(1)
+#define VPSS_VENCCLKEN_ENABLE           BIT(3)
+#define VPSS_DACCLKEN_ENABLE            BIT(4)
+#define VPSS_PLLC2SYSCLK5_ENABLE        BIT(5)
+
 extern void __iomem *davinci_sysmod_base;
 #define DAVINCI_SYSMOD_VIRT(x)  (davinci_sysmod_base + (x))
 void davinci_map_sysmod(void);
@@ -74,7 +81,7 @@ void __init dm355_init(void);
 void dm355_init_spi0(unsigned chipselect_mask,
                 const struct spi_board_info *info, unsigned len);
 void __init dm355_init_asp1(u32 evt_enable, struct snd_platform_data *pdata);
-void dm355_set_vpfe_config(struct vpfe_config *cfg);
+int dm355_init_video(struct vpfe_config *, struct vpbe_config *);
 
 /* DM365 function declarations */
 void __init dm365_init(void);
@@ -84,7 +91,7 @@ void __init dm365_init_ks(struct davinci_ks_platform_data *pdata);
 void __init dm365_init_rtc(void);
 void dm365_init_spi0(unsigned chipselect_mask,
                         const struct spi_board_info *info, unsigned len);
-void dm365_set_vpfe_config(struct vpfe_config *cfg);
+int dm365_init_video(struct vpfe_config *, struct vpbe_config *);
 
 /* DM644x function declarations */
 void __init dm644x_init(void);
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index b49c3b77d55e..bf9a9d4ad9f5 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -35,6 +35,8 @@
 #include "asp.h"
 
 #define DM355_UART2_BASE        (IO_PHYS + 0x206000)
+#define DM355_OSD_BASE          (IO_PHYS + 0x70200)
+#define DM355_VENC_BASE         (IO_PHYS + 0x70400)
 
 /*
  * Device specific clocks
@@ -345,8 +347,8 @@ static struct clk_lookup dm355_clks[] = {
         CLK(NULL, "pll1_aux", &pll1_aux_clk),
         CLK(NULL, "pll1_sysclkbp", &pll1_sysclkbp),
         CLK(NULL, "vpss_dac", &vpss_dac_clk),
-        CLK(NULL, "vpss_master", &vpss_master_clk),
-        CLK(NULL, "vpss_slave", &vpss_slave_clk),
+        CLK("vpss", "master", &vpss_master_clk),
+        CLK("vpss", "slave", &vpss_slave_clk),
         CLK(NULL, "clkout1", &clkout1_clk),
         CLK(NULL, "clkout2", &clkout2_clk),
         CLK(NULL, "pll2", &pll2_clk),
@@ -744,11 +746,146 @@ static struct platform_device vpfe_capture_dev = {
         },
 };
 
-void dm355_set_vpfe_config(struct vpfe_config *cfg)
+static struct resource dm355_osd_resources[] = {
+        {
+                .start  = DM355_OSD_BASE,
+                .end    = DM355_OSD_BASE + 0x17f,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device dm355_osd_dev = {
+        .name           = DM355_VPBE_OSD_SUBDEV_NAME,
+        .id             = -1,
+        .num_resources  = ARRAY_SIZE(dm355_osd_resources),
+        .resource       = dm355_osd_resources,
+        .dev            = {
+                .dma_mask               = &vpfe_capture_dma_mask,
+                .coherent_dma_mask      = DMA_BIT_MASK(32),
+        },
+};
+
+static struct resource dm355_venc_resources[] = {
+        {
+                .start  = IRQ_VENCINT,
+                .end    = IRQ_VENCINT,
+                .flags  = IORESOURCE_IRQ,
+        },
+        /* venc registers io space */
+        {
+                .start  = DM355_VENC_BASE,
+                .end    = DM355_VENC_BASE + 0x17f,
+                .flags  = IORESOURCE_MEM,
+        },
+        /* VDAC config register io space */
+        {
+                .start  = DAVINCI_SYSTEM_MODULE_BASE + SYSMOD_VDAC_CONFIG,
+                .end    = DAVINCI_SYSTEM_MODULE_BASE + SYSMOD_VDAC_CONFIG + 3,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct resource dm355_v4l2_disp_resources[] = {
+        {
+                .start  = IRQ_VENCINT,
+                .end    = IRQ_VENCINT,
+                .flags  = IORESOURCE_IRQ,
+        },
+        /* venc registers io space */
+        {
+                .start  = DM355_VENC_BASE,
+                .end    = DM355_VENC_BASE + 0x17f,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static int dm355_vpbe_setup_pinmux(enum v4l2_mbus_pixelcode if_type,
+                            int field)
+{
+        switch (if_type) {
+        case V4L2_MBUS_FMT_SGRBG8_1X8:
+                davinci_cfg_reg(DM355_VOUT_FIELD_G70);
+                break;
+        case V4L2_MBUS_FMT_YUYV10_1X20:
+                if (field)
+                        davinci_cfg_reg(DM355_VOUT_FIELD);
+                else
+                        davinci_cfg_reg(DM355_VOUT_FIELD_G70);
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        davinci_cfg_reg(DM355_VOUT_COUTL_EN);
+        davinci_cfg_reg(DM355_VOUT_COUTH_EN);
+
+        return 0;
+}
+
+static int dm355_venc_setup_clock(enum vpbe_enc_timings_type type,
+                                   unsigned int pclock)
 {
-        vpfe_capture_dev.dev.platform_data = cfg;
+        void __iomem *vpss_clk_ctrl_reg;
+
+        vpss_clk_ctrl_reg = DAVINCI_SYSMOD_VIRT(SYSMOD_VPSS_CLKCTL);
+
+        switch (type) {
+        case VPBE_ENC_STD:
+                writel(VPSS_DACCLKEN_ENABLE | VPSS_VENCCLKEN_ENABLE,
+                       vpss_clk_ctrl_reg);
+                break;
+        case VPBE_ENC_DV_TIMINGS:
+                if (pclock > 27000000)
+                        /*
+                         * For HD, use external clock source since we cannot
+                         * support HD mode with internal clocks.
+                         */
+                        writel(VPSS_MUXSEL_EXTCLK_ENABLE, vpss_clk_ctrl_reg);
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        return 0;
 }
 
+static struct platform_device dm355_vpbe_display = {
+        .name           = "vpbe-v4l2",
+        .id             = -1,
+        .num_resources  = ARRAY_SIZE(dm355_v4l2_disp_resources),
+        .resource       = dm355_v4l2_disp_resources,
+        .dev            = {
+                .dma_mask               = &vpfe_capture_dma_mask,
+                .coherent_dma_mask      = DMA_BIT_MASK(32),
+        },
+};
+
+struct venc_platform_data dm355_venc_pdata = {
+        .setup_pinmux   = dm355_vpbe_setup_pinmux,
+        .setup_clock    = dm355_venc_setup_clock,
+};
+
+static struct platform_device dm355_venc_dev = {
+        .name           = DM355_VPBE_VENC_SUBDEV_NAME,
+        .id             = -1,
+        .num_resources  = ARRAY_SIZE(dm355_venc_resources),
+        .resource       = dm355_venc_resources,
+        .dev            = {
+                .dma_mask               = &vpfe_capture_dma_mask,
+                .coherent_dma_mask      = DMA_BIT_MASK(32),
+                .platform_data          = (void *)&dm355_venc_pdata,
+        },
+};
+
+static struct platform_device dm355_vpbe_dev = {
+        .name           = "vpbe_controller",
+        .id             = -1,
+        .dev            = {
+                .dma_mask               = &vpfe_capture_dma_mask,
+                .coherent_dma_mask      = DMA_BIT_MASK(32),
+        },
+};
+
 /*----------------------------------------------------------------------*/
 
 static struct map_desc dm355_io_desc[] = {
@@ -868,19 +1005,36 @@ void __init dm355_init(void)
         davinci_map_sysmod();
 }
 
+int __init dm355_init_video(struct vpfe_config *vpfe_cfg,
+                                struct vpbe_config *vpbe_cfg)
+{
+        if (vpfe_cfg || vpbe_cfg)
+                platform_device_register(&dm355_vpss_device);
+
+        if (vpfe_cfg) {
+                vpfe_capture_dev.dev.platform_data = vpfe_cfg;
+                platform_device_register(&dm355_ccdc_dev);
+                platform_device_register(&vpfe_capture_dev);
+        }
+
+        if (vpbe_cfg) {
+                dm355_vpbe_dev.dev.platform_data = vpbe_cfg;
+                platform_device_register(&dm355_osd_dev);
+                platform_device_register(&dm355_venc_dev);
+                platform_device_register(&dm355_vpbe_dev);
+                platform_device_register(&dm355_vpbe_display);
+        }
+
+        return 0;
+}
+
 static int __init dm355_init_devices(void)
 {
         if (!cpu_is_davinci_dm355())
                 return 0;
 
-        /* Add ccdc clock aliases */
-        clk_add_alias("master", dm355_ccdc_dev.name, "vpss_master", NULL);
-        clk_add_alias("slave", dm355_ccdc_dev.name, "vpss_master", NULL);
         davinci_cfg_reg(DM355_INT_EDMA_CC);
         platform_device_register(&dm355_edma_device);
-        platform_device_register(&dm355_vpss_device);
-        platform_device_register(&dm355_ccdc_dev);
-        platform_device_register(&vpfe_capture_dev);
 
         return 0;
 }
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 6c3980540be0..ff771ceac3f1 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -39,16 +39,13 @@
 #include "asp.h"
 
 #define DM365_REF_FREQ          24000000        /* 24 MHz on the DM365 EVM */
-
-/* Base of key scan register bank */
-#define DM365_KEYSCAN_BASE              0x01c69400
-
 #define DM365_RTC_BASE                  0x01c69000
-
+#define DM365_KEYSCAN_BASE              0x01c69400
+#define DM365_OSD_BASE                  0x01c71c00
+#define DM365_VENC_BASE                 0x01c71e00
 #define DAVINCI_DM365_VC_BASE           0x01d0c000
 #define DAVINCI_DMA_VC_TX               2
 #define DAVINCI_DMA_VC_RX               3
-
 #define DM365_EMAC_BASE                 0x01d07000
 #define DM365_EMAC_MDIO_BASE            (DM365_EMAC_BASE + 0x4000)
 #define DM365_EMAC_CNTRL_OFFSET         0x0000
@@ -257,6 +254,12 @@ static struct clk vpss_master_clk = {
         .flags          = CLK_PSC,
 };
 
+static struct clk vpss_slave_clk = {
+        .name           = "vpss_slave",
+        .parent         = &pll1_sysclk5,
+        .lpsc           = DAVINCI_LPSC_VPSSSLV,
+};
+
 static struct clk arm_clk = {
         .name           = "arm_clk",
         .parent         = &pll2_sysclk2,
@@ -449,7 +452,8 @@ static struct clk_lookup dm365_clks[] = {
         CLK(NULL, "pll2_sysclk8", &pll2_sysclk8),
         CLK(NULL, "pll2_sysclk9", &pll2_sysclk9),
         CLK(NULL, "vpss_dac", &vpss_dac_clk),
-        CLK(NULL, "vpss_master", &vpss_master_clk),
+        CLK("vpss", "master", &vpss_master_clk),
+        CLK("vpss", "slave", &vpss_slave_clk),
         CLK(NULL, "arm", &arm_clk),
         CLK(NULL, "uart0", &uart0_clk),
         CLK(NULL, "uart1", &uart1_clk),
@@ -1226,6 +1230,173 @@ static struct platform_device dm365_isif_dev = {
         },
 };
 
+static struct resource dm365_osd_resources[] = {
+        {
+                .start = DM365_OSD_BASE,
+                .end   = DM365_OSD_BASE + 0xff,
+                .flags = IORESOURCE_MEM,
+        },
+};
+
+static u64 dm365_video_dma_mask = DMA_BIT_MASK(32);
+
+static struct platform_device dm365_osd_dev = {
+        .name           = DM365_VPBE_OSD_SUBDEV_NAME,
+        .id             = -1,
+        .num_resources  = ARRAY_SIZE(dm365_osd_resources),
+        .resource       = dm365_osd_resources,
+        .dev            = {
+                .dma_mask               = &dm365_video_dma_mask,
+                .coherent_dma_mask      = DMA_BIT_MASK(32),
+        },
+};
+
+static struct resource dm365_venc_resources[] = {
+        {
+                .start = IRQ_VENCINT,
+                .end   = IRQ_VENCINT,
+                .flags = IORESOURCE_IRQ,
+        },
+        /* venc registers io space */
+        {
+                .start = DM365_VENC_BASE,
+                .end   = DM365_VENC_BASE + 0x177,
+                .flags = IORESOURCE_MEM,
+        },
+        /* vdaccfg registers io space */
+        {
+                .start = DAVINCI_SYSTEM_MODULE_BASE + SYSMOD_VDAC_CONFIG,
+                .end   = DAVINCI_SYSTEM_MODULE_BASE + SYSMOD_VDAC_CONFIG + 3,
+                .flags = IORESOURCE_MEM,
+        },
+};
+
+static struct resource dm365_v4l2_disp_resources[] = {
+        {
+                .start = IRQ_VENCINT,
+                .end   = IRQ_VENCINT,
+                .flags = IORESOURCE_IRQ,
+        },
+        /* venc registers io space */
+        {
+                .start = DM365_VENC_BASE,
+                .end   = DM365_VENC_BASE + 0x177,
+                .flags = IORESOURCE_MEM,
+        },
+};
+
+static int dm365_vpbe_setup_pinmux(enum v4l2_mbus_pixelcode if_type,
+                            int field)
+{
+        switch (if_type) {
+        case V4L2_MBUS_FMT_SGRBG8_1X8:
+                davinci_cfg_reg(DM365_VOUT_FIELD_G81);
+                davinci_cfg_reg(DM365_VOUT_COUTL_EN);
+                davinci_cfg_reg(DM365_VOUT_COUTH_EN);
+                break;
+        case V4L2_MBUS_FMT_YUYV10_1X20:
+                if (field)
+                        davinci_cfg_reg(DM365_VOUT_FIELD);
+                else
+                        davinci_cfg_reg(DM365_VOUT_FIELD_G81);
+                davinci_cfg_reg(DM365_VOUT_COUTL_EN);
+                davinci_cfg_reg(DM365_VOUT_COUTH_EN);
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        return 0;
+}
+
+static int dm365_venc_setup_clock(enum vpbe_enc_timings_type type,
+                                  unsigned int pclock)
+{
+        void __iomem *vpss_clkctl_reg;
+        u32 val;
+
+        vpss_clkctl_reg = DAVINCI_SYSMOD_VIRT(SYSMOD_VPSS_CLKCTL);
+
+        switch (type) {
+        case VPBE_ENC_STD:
+                val = VPSS_VENCCLKEN_ENABLE | VPSS_DACCLKEN_ENABLE;
+                break;
+        case VPBE_ENC_DV_TIMINGS:
+                if (pclock <= 27000000) {
+                        val = VPSS_VENCCLKEN_ENABLE | VPSS_DACCLKEN_ENABLE;
+                } else {
+                        /* set sysclk4 to output 74.25 MHz from pll1 */
+                        val = VPSS_PLLC2SYSCLK5_ENABLE | VPSS_DACCLKEN_ENABLE |
+                              VPSS_VENCCLKEN_ENABLE;
+                }
+                break;
+        default:
+                return -EINVAL;
+        }
+        writel(val, vpss_clkctl_reg);
+
+        return 0;
+}
+
+static struct platform_device dm365_vpbe_display = {
+        .name           = "vpbe-v4l2",
+        .id             = -1,
+        .num_resources  = ARRAY_SIZE(dm365_v4l2_disp_resources),
+        .resource       = dm365_v4l2_disp_resources,
+        .dev            = {
+                .dma_mask               = &dm365_video_dma_mask,
+                .coherent_dma_mask      = DMA_BIT_MASK(32),
+        },
+};
+
+struct venc_platform_data dm365_venc_pdata = {
+        .setup_pinmux   = dm365_vpbe_setup_pinmux,
+        .setup_clock    = dm365_venc_setup_clock,
+};
+
+static struct platform_device dm365_venc_dev = {
+        .name           = DM365_VPBE_VENC_SUBDEV_NAME,
+        .id             = -1,
+        .num_resources  = ARRAY_SIZE(dm365_venc_resources),
+        .resource       = dm365_venc_resources,
+        .dev            = {
+                .dma_mask               = &dm365_video_dma_mask,
+                .coherent_dma_mask      = DMA_BIT_MASK(32),
+                .platform_data          = (void *)&dm365_venc_pdata,
+        },
+};
+
+static struct platform_device dm365_vpbe_dev = {
+        .name           = "vpbe_controller",
+        .id             = -1,
+        .dev            = {
+                .dma_mask               = &dm365_video_dma_mask,
+                .coherent_dma_mask      = DMA_BIT_MASK(32),
+        },
+};
+
+int __init dm365_init_video(struct vpfe_config *vpfe_cfg,
+                                struct vpbe_config *vpbe_cfg)
+{
+        if (vpfe_cfg || vpbe_cfg)
+                platform_device_register(&dm365_vpss_device);
+
+        if (vpfe_cfg) {
+                vpfe_capture_dev.dev.platform_data = vpfe_cfg;
+                platform_device_register(&dm365_isif_dev);
+                platform_device_register(&vpfe_capture_dev);
+        }
+        if (vpbe_cfg) {
+                dm365_vpbe_dev.dev.platform_data = vpbe_cfg;
+                platform_device_register(&dm365_osd_dev);
+                platform_device_register(&dm365_venc_dev);
+                platform_device_register(&dm365_vpbe_dev);
+                platform_device_register(&dm365_vpbe_display);
+        }
+
+        return 0;
+}
+
 static int __init dm365_init_devices(void)
 {
         if (!cpu_is_davinci_dm365())
@@ -1239,16 +1410,6 @@ static int __init dm365_init_devices(void)
         clk_add_alias(NULL, dev_name(&dm365_mdio_device.dev),
                       NULL, &dm365_emac_device.dev);
 
-        /* Add isif clock alias */
-        clk_add_alias("master", dm365_isif_dev.name, "vpss_master", NULL);
-        platform_device_register(&dm365_vpss_device);
-        platform_device_register(&dm365_isif_dev);
-        platform_device_register(&vpfe_capture_dev);
         return 0;
 }
 postcore_initcall(dm365_init_devices);
-
-void dm365_set_vpfe_config(struct vpfe_config *cfg)
-{
-       vpfe_capture_dev.dev.platform_data = cfg;
-}
diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c
index db1dd92e00af..c2a9273330bf 100644
--- a/arch/arm/mach-davinci/dm644x.c
+++ b/arch/arm/mach-davinci/dm644x.c
@@ -300,8 +300,8 @@ static struct clk_lookup dm644x_clks[] = {
         CLK(NULL, "dsp", &dsp_clk),
         CLK(NULL, "arm", &arm_clk),
         CLK(NULL, "vicp", &vicp_clk),
-        CLK(NULL, "vpss_master", &vpss_master_clk),
-        CLK(NULL, "vpss_slave", &vpss_slave_clk),
+        CLK("vpss", "master", &vpss_master_clk),
+        CLK("vpss", "slave", &vpss_slave_clk),
         CLK(NULL, "arm", &arm_clk),
         CLK(NULL, "uart0", &uart0_clk),
         CLK(NULL, "uart1", &uart1_clk),
@@ -706,7 +706,7 @@ static int dm644x_venc_setup_clock(enum vpbe_enc_timings_type type,
                 v |= DM644X_VPSS_DACCLKEN;
                 writel(v, DAVINCI_SYSMOD_VIRT(SYSMOD_VPSS_CLKCTL));
                 break;
-        case VPBE_ENC_CUSTOM_TIMINGS:
+        case VPBE_ENC_DV_TIMINGS:
                 if (pclock <= 27000000) {
                         v |= DM644X_VPSS_DACCLKEN;
                         writel(v, DAVINCI_SYSMOD_VIRT(SYSMOD_VPSS_CLKCTL));
@@ -901,11 +901,6 @@ int __init dm644x_init_video(struct vpfe_config *vpfe_cfg,
                 dm644x_vpfe_dev.dev.platform_data = vpfe_cfg;
                 platform_device_register(&dm644x_ccdc_dev);
                 platform_device_register(&dm644x_vpfe_dev);
-                /* Add ccdc clock aliases */
-                clk_add_alias("master", dm644x_ccdc_dev.name,
-                              "vpss_master", NULL);
-                clk_add_alias("slave", dm644x_ccdc_dev.name,
-                              "vpss_slave", NULL);
         }
 
         if (vpbe_cfg) {
diff --git a/arch/arm/mach-davinci/dma.c b/arch/arm/mach-davinci/dma.c
index a685e9706b7b..45b7c71d9cc1 100644
--- a/arch/arm/mach-davinci/dma.c
+++ b/arch/arm/mach-davinci/dma.c
@@ -743,6 +743,9 @@ EXPORT_SYMBOL(edma_free_channel);
  */
 int edma_alloc_slot(unsigned ctlr, int slot)
 {
+        if (!edma_cc[ctlr])
+                return -EINVAL;
+
         if (slot >= 0)
                 slot = EDMA_CHAN_SLOT(slot);
 
diff --git a/arch/arm/mach-davinci/pm_domain.c b/arch/arm/mach-davinci/pm_domain.c
index c90250e3bef8..6b98413cebd6 100644
--- a/arch/arm/mach-davinci/pm_domain.c
+++ b/arch/arm/mach-davinci/pm_domain.c
@@ -53,7 +53,7 @@ static struct dev_pm_domain davinci_pm_domain = {
 
 static struct pm_clk_notifier_block platform_bus_notifier = {
         .pm_domain = &davinci_pm_domain,
-        .con_ids = { "fck", NULL, },
+        .con_ids = { "fck", "master", "slave", NULL },
 };
 
 static int __init davinci_pm_runtime_init(void)
diff --git a/arch/arm/mach-ep93xx/include/mach/uncompress.h b/arch/arm/mach-ep93xx/include/mach/uncompress.h
index d2afb4dd82ab..b5cc77d2380b 100644
--- a/arch/arm/mach-ep93xx/include/mach/uncompress.h
+++ b/arch/arm/mach-ep93xx/include/mach/uncompress.h
@@ -47,9 +47,13 @@ static void __raw_writel(unsigned int value, unsigned int ptr)
 
 static inline void putc(int c)
 {
-        /* Transmit fifo not full?  */
-        while (__raw_readb(PHYS_UART_FLAG) & UART_FLAG_TXFF)
-                ;
+        int i;
+
+        for (i = 0; i < 10000; i++) {
+                /* Transmit fifo not full? */
+                if (!(__raw_readb(PHYS_UART_FLAG) & UART_FLAG_TXFF))
+                        break;
+        }
 
         __raw_writeb(c, PHYS_UART_DATA);
 }
diff --git a/arch/arm/mach-exynos/mach-universal_c210.c b/arch/arm/mach-exynos/mach-universal_c210.c
index 497fcb793dc1..d28c7fbaba2d 100644
--- a/arch/arm/mach-exynos/mach-universal_c210.c
+++ b/arch/arm/mach-exynos/mach-universal_c210.c
@@ -97,6 +97,19 @@ static struct s3c2410_uartcfg universal_uartcfgs[] __initdata = {
 static struct regulator_consumer_supply max8952_consumer =
         REGULATOR_SUPPLY("vdd_arm", NULL);
 
+static struct regulator_init_data universal_max8952_reg_data = {
+        .constraints    = {
+                .name           = "VARM_1.2V",
+                .min_uV         = 770000,
+                .max_uV         = 1400000,
+                .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE,
+                .always_on      = 1,
+                .boot_on        = 1,
+        },
+        .num_consumer_supplies  = 1,
+        .consumer_supplies      = &max8952_consumer,
+};
+
 static struct max8952_platform_data universal_max8952_pdata __initdata = {
         .gpio_vid0      = EXYNOS4_GPX0(3),
         .gpio_vid1      = EXYNOS4_GPX0(4),
@@ -105,19 +118,7 @@ static struct max8952_platform_data universal_max8952_pdata __initdata = {
         .dvs_mode       = { 48, 32, 28, 18 }, /* 1.25, 1.20, 1.05, 0.95V */
         .sync_freq      = 0, /* default: fastest */
         .ramp_speed     = 0, /* default: fastest */
-
-        .reg_data       = {
-                .constraints    = {
-                        .name           = "VARM_1.2V",
-                        .min_uV         = 770000,
-                        .max_uV         = 1400000,
-                        .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE,
-                        .always_on      = 1,
-                        .boot_on        = 1,
-                },
-                .num_consumer_supplies  = 1,
-                .consumer_supplies      = &max8952_consumer,
-        },
+        .reg_data       = &universal_max8952_reg_data,
 };
 
 static struct regulator_consumer_supply lp3974_buck1_consumer =
diff --git a/arch/arm/mach-exynos/setup-usb-phy.c b/arch/arm/mach-exynos/setup-usb-phy.c
index b81cc569a8dd..6af40662a449 100644
--- a/arch/arm/mach-exynos/setup-usb-phy.c
+++ b/arch/arm/mach-exynos/setup-usb-phy.c
@@ -204,9 +204,9 @@ static int exynos4210_usb_phy1_exit(struct platform_device *pdev)
 
 int s5p_usb_phy_init(struct platform_device *pdev, int type)
 {
-        if (type == S5P_USB_PHY_DEVICE)
+        if (type == USB_PHY_TYPE_DEVICE)
                 return exynos4210_usb_phy0_init(pdev);
-        else if (type == S5P_USB_PHY_HOST)
+        else if (type == USB_PHY_TYPE_HOST)
                 return exynos4210_usb_phy1_init(pdev);
 
         return -EINVAL;
@@ -214,9 +214,9 @@ int s5p_usb_phy_init(struct platform_device *pdev, int type)
 
 int s5p_usb_phy_exit(struct platform_device *pdev, int type)
 {
-        if (type == S5P_USB_PHY_DEVICE)
+        if (type == USB_PHY_TYPE_DEVICE)
                 return exynos4210_usb_phy0_exit(pdev);
-        else if (type == S5P_USB_PHY_HOST)
+        else if (type == USB_PHY_TYPE_HOST)
                 return exynos4210_usb_phy1_exit(pdev);
 
         return -EINVAL;
diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig
index abda5a18a664..0f2111a11315 100644
--- a/arch/arm/mach-footbridge/Kconfig
+++ b/arch/arm/mach-footbridge/Kconfig
@@ -67,6 +67,7 @@ config ARCH_NETWINDER
         select ISA
         select ISA_DMA
         select PCI
+        select VIRT_TO_BUS
         help
           Say Y here if you intend to run this kernel on the Rebel.COM
           NetWinder.  Information about this machine can be found at:
diff --git a/arch/arm/mach-gemini/idle.c b/arch/arm/mach-gemini/idle.c
index 92bbd6bb600a..87dff4f5059e 100644
--- a/arch/arm/mach-gemini/idle.c
+++ b/arch/arm/mach-gemini/idle.c
@@ -13,9 +13,11 @@ static void gemini_idle(void)
          * will never wakeup... Acctualy it is not very good to enable
          * interrupts first since scheduler can miss a tick, but there is
          * no other way around this. Platforms that needs it for power saving
-         * should call enable_hlt() in init code, since by default it is
+         * should enable it in init code, since by default it is
          * disabled.
          */
+
+        /* FIXME: Enabling interrupts here is racy! */
         local_irq_enable();
         cpu_do_idle();
 }
diff --git a/arch/arm/mach-gemini/irq.c b/arch/arm/mach-gemini/irq.c
index 020852d3bdd8..6d8f6d1669ff 100644
--- a/arch/arm/mach-gemini/irq.c
+++ b/arch/arm/mach-gemini/irq.c
@@ -15,6 +15,8 @@
 #include <linux/stddef.h>
 #include <linux/list.h>
 #include <linux/sched.h>
+#include <linux/cpu.h>
+
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
 #include <asm/system_misc.h>
@@ -77,7 +79,7 @@ void __init gemini_init_irq(void)
          * Disable the idle handler by default since it is buggy
          * For more info see arch/arm/mach-gemini/idle.c
          */
-        disable_hlt();
+        cpu_idle_poll_ctrl(true);
 
         request_resource(&iomem_resource, &irq_resource);
 
diff --git a/arch/arm/mach-highbank/hotplug.c b/arch/arm/mach-highbank/hotplug.c
index f30c52843396..890cae23c12a 100644
--- a/arch/arm/mach-highbank/hotplug.c
+++ b/arch/arm/mach-highbank/hotplug.c
@@ -28,13 +28,11 @@ extern void secondary_startup(void);
  */
 void __ref highbank_cpu_die(unsigned int cpu)
 {
-        flush_cache_all();
-
         highbank_set_cpu_jump(cpu, phys_to_virt(0));
-        highbank_set_core_pwr();
 
-        cpu_do_idle();
+        flush_cache_louis();
+        highbank_set_core_pwr();
 
-        /* We should never return from idle */
-        panic("highbank: cpu %d unexpectedly exit from shutdown\n", cpu);
+        while (1)
+                cpu_do_idle();
 }
diff --git a/arch/arm/mach-imx/clk-busy.c b/arch/arm/mach-imx/clk-busy.c
index 1ab91b5209e6..85b728cc27ab 100644
--- a/arch/arm/mach-imx/clk-busy.c
+++ b/arch/arm/mach-imx/clk-busy.c
@@ -169,7 +169,7 @@ struct clk *imx_clk_busy_mux(const char *name, void __iomem *reg, u8 shift,
 
         busy->mux.reg = reg;
         busy->mux.shift = shift;
-        busy->mux.width = width;
+        busy->mux.mask = BIT(width) - 1;
         busy->mux.lock = &imx_ccm_lock;
         busy->mux_ops = &clk_mux_ops;
 
diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c
index 74e3a34d78b8..2193c834f55c 100644
--- a/arch/arm/mach-imx/clk-imx35.c
+++ b/arch/arm/mach-imx/clk-imx35.c
@@ -257,6 +257,7 @@ int __init mx35_clocks_init(void)
         clk_register_clkdev(clk[wdog_gate], NULL, "imx2-wdt.0");
         clk_register_clkdev(clk[nfc_div], NULL, "imx25-nand.0");
         clk_register_clkdev(clk[csi_gate], NULL, "mx3-camera.0");
+        clk_register_clkdev(clk[admux_gate], "audmux", NULL);
 
         clk_prepare_enable(clk[spba_gate]);
         clk_prepare_enable(clk[gpio1_gate]);
@@ -264,6 +265,8 @@ int __init mx35_clocks_init(void)
         clk_prepare_enable(clk[gpio3_gate]);
         clk_prepare_enable(clk[iim_gate]);
         clk_prepare_enable(clk[emi_gate]);
+        clk_prepare_enable(clk[max_gate]);
+        clk_prepare_enable(clk[iomuxc_gate]);
 
         /*
          * SCC is needed to boot via mmc after a watchdog reset. The clock code
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 7b025ee528a5..d38e54f5b6d7 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -115,7 +115,7 @@ static const char *gpu2d_core_sels[]	= { "axi", "pll3_usb_otg", "pll2_pfd0_352m"
 static const char *gpu3d_core_sels[]    = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd2_396m", };
 static const char *gpu3d_shader_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd9_720m", };
 static const char *ipu_sels[]           = { "mmdc_ch0_axi", "pll2_pfd2_396m", "pll3_120m", "pll3_pfd1_540m", };
-static const char *ldb_di_sels[]        = { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_pfd1_540m", };
+static const char *ldb_di_sels[]        = { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_usb_otg", };
 static const char *ipu_di_pre_sels[]    = { "mmdc_ch0_axi", "pll3_usb_otg", "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "pll3_pfd1_540m", };
 static const char *ipu1_di0_sels[]      = { "ipu1_di0_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", };
 static const char *ipu1_di1_sels[]      = { "ipu1_di1_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", };
@@ -172,7 +172,7 @@ static struct clk *clk[clk_max];
 static struct clk_onecell_data clk_data;
 
 static enum mx6q_clks const clks_init_on[] __initconst = {
-        mmdc_ch0_axi, rom,
+        mmdc_ch0_axi, rom, pll1_sys,
 };
 
 static struct clk_div_table clk_enet_ref_table[] = {
@@ -443,7 +443,6 @@ int __init mx6q_clocks_init(void)
 
         clk_register_clkdev(clk[gpt_ipg], "ipg", "imx-gpt.0");
         clk_register_clkdev(clk[gpt_ipg_per], "per", "imx-gpt.0");
-        clk_register_clkdev(clk[twd], NULL, "smp_twd");
         clk_register_clkdev(clk[cko1_sel], "cko1_sel", NULL);
         clk_register_clkdev(clk[ahb], "ahb", NULL);
         clk_register_clkdev(clk[cko1], "cko1", NULL);
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index 5a800bfcec5b..5bf4a97ab241 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -110,6 +110,8 @@ void tzic_handle_irq(struct pt_regs *);
 
 extern void imx_enable_cpu(int cpu, bool enable);
 extern void imx_set_cpu_jump(int cpu, void *jump_addr);
+extern u32 imx_get_cpu_arg(int cpu);
+extern void imx_set_cpu_arg(int cpu, u32 arg);
 extern void v7_cpu_resume(void);
 extern u32 *pl310_get_save_ptr(void);
 #ifdef CONFIG_SMP
diff --git a/arch/arm/mach-imx/headsmp.S b/arch/arm/mach-imx/headsmp.S
index 921fc1555854..a58c8b0527cc 100644
--- a/arch/arm/mach-imx/headsmp.S
+++ b/arch/arm/mach-imx/headsmp.S
@@ -26,16 +26,16 @@ ENDPROC(v7_secondary_startup)
 
 #ifdef CONFIG_PM
 /*
- * The following code is located into the .data section.  This is to
- * allow phys_l2x0_saved_regs to be accessed with a relative load
- * as we are running on physical address here.
+ * The following code must assume it is running from physical address
+ * where absolute virtual addresses to the data section have to be
+ * turned into relative ones.
  */
-        .data
-        .align
 
 #ifdef CONFIG_CACHE_L2X0
         .macro  pl310_resume
-        ldr     r2, phys_l2x0_saved_regs
+        adr     r0, l2x0_saved_regs_offset
+        ldr     r2, [r0]
+        add     r2, r2, r0
         ldr     r0, [r2, #L2X0_R_PHY_BASE]      @ get physical base of l2x0
         ldr     r1, [r2, #L2X0_R_AUX_CTRL]      @ get aux_ctrl value
         str     r1, [r0, #L2X0_AUX_CTRL]        @ restore aux_ctrl
@@ -43,9 +43,9 @@ ENDPROC(v7_secondary_startup)
         str     r1, [r0, #L2X0_CTRL]            @ re-enable L2
         .endm
 
-        .globl  phys_l2x0_saved_regs
-phys_l2x0_saved_regs:
-        .long   0
+l2x0_saved_regs_offset:
+        .word   l2x0_saved_regs - .
+
 #else
         .macro  pl310_resume
         .endm
diff --git a/arch/arm/mach-imx/hotplug.c b/arch/arm/mach-imx/hotplug.c
index 7bc5fe15dda2..361a253e2b63 100644
--- a/arch/arm/mach-imx/hotplug.c
+++ b/arch/arm/mach-imx/hotplug.c
@@ -46,11 +46,23 @@ static inline void cpu_enter_lowpower(void)
 void imx_cpu_die(unsigned int cpu)
 {
         cpu_enter_lowpower();
+        /*
+         * We use the cpu jumping argument register to sync with
+         * imx_cpu_kill() which is running on cpu0 and waiting for
+         * the register being cleared to kill the cpu.
+         */
+        imx_set_cpu_arg(cpu, ~0);
         cpu_do_idle();
 }
 
 int imx_cpu_kill(unsigned int cpu)
 {
+        unsigned long timeout = jiffies + msecs_to_jiffies(50);
+
+        while (imx_get_cpu_arg(cpu) == 0)
+                if (time_after(jiffies, timeout))
+                        return 0;
         imx_enable_cpu(cpu, false);
+        imx_set_cpu_arg(cpu, 0);
         return 1;
 }
diff --git a/arch/arm/mach-imx/imx25-dt.c b/arch/arm/mach-imx/imx25-dt.c
index 03b65e5ea541..82348391582a 100644
--- a/arch/arm/mach-imx/imx25-dt.c
+++ b/arch/arm/mach-imx/imx25-dt.c
@@ -27,6 +27,11 @@ static const char * const imx25_dt_board_compat[] __initconst = {
         NULL
 };
 
+static void __init imx25_timer_init(void)
+{
+        mx25_clocks_init_dt();
+}
+
 DT_MACHINE_START(IMX25_DT, "Freescale i.MX25 (Device Tree Support)")
         .map_io         = mx25_map_io,
         .init_early     = imx25_init_early,
diff --git a/arch/arm/mach-imx/pm-imx6q.c b/arch/arm/mach-imx/pm-imx6q.c
index ee42d20cba19..5faba7a3c95f 100644
--- a/arch/arm/mach-imx/pm-imx6q.c
+++ b/arch/arm/mach-imx/pm-imx6q.c
@@ -22,8 +22,6 @@
 #include "common.h"
 #include "hardware.h"
 
-extern unsigned long phys_l2x0_saved_regs;
-
 static int imx6q_suspend_finish(unsigned long val)
 {
         cpu_do_idle();
@@ -57,18 +55,5 @@ static const struct platform_suspend_ops imx6q_pm_ops = {
 
 void __init imx6q_pm_init(void)
 {
-        /*
-         * The l2x0 core code provides an infrastucture to save and restore
-         * l2x0 registers across suspend/resume cycle.  But because imx6q
-         * retains L2 content during suspend and needs to resume L2 before
-         * MMU is enabled, it can only utilize register saving support and
-         * have to take care of restoring on its own.  So we save physical
-         * address of the data structure used by l2x0 core to save registers,
-         * and later restore the necessary ones in imx6q resume entry.
-         */
-#ifdef CONFIG_CACHE_L2X0
-        phys_l2x0_saved_regs = __pa(&l2x0_saved_regs);
-#endif
-
         suspend_set_ops(&imx6q_pm_ops);
 }
diff --git a/arch/arm/mach-imx/src.c b/arch/arm/mach-imx/src.c
index e15f1555c59b..09a742f8c7ab 100644
--- a/arch/arm/mach-imx/src.c
+++ b/arch/arm/mach-imx/src.c
@@ -43,6 +43,18 @@ void imx_set_cpu_jump(int cpu, void *jump_addr)
                        src_base + SRC_GPR1 + cpu * 8);
 }
 
+u32 imx_get_cpu_arg(int cpu)
+{
+        cpu = cpu_logical_map(cpu);
+        return readl_relaxed(src_base + SRC_GPR1 + cpu * 8 + 4);
+}
+
+void imx_set_cpu_arg(int cpu, u32 arg)
+{
+        cpu = cpu_logical_map(cpu);
+        writel_relaxed(arg, src_base + SRC_GPR1 + cpu * 8 + 4);
+}
+
 void imx_src_prepare_restart(void)
 {
         u32 val;
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 1dbeb7c99d58..6600cff6bd92 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -29,6 +29,7 @@
 #include <linux/io.h>
 #include <linux/export.h>
 #include <linux/gpio.h>
+#include <linux/cpu.h>
 
 #include <mach/udc.h>
 #include <mach/hardware.h>
@@ -239,7 +240,7 @@ void __init ixp4xx_init_irq(void)
          * ixp4xx does not implement the XScale PWRMODE register
          * so it must not call cpu_do_idle().
          */
-        disable_hlt();
+        cpu_idle_poll_ctrl(true);
 
         /* Route all sources to IRQ instead of FIQ */
         *IXP4XX_ICLR = 0x0;
diff --git a/arch/arm/mach-ixp4xx/vulcan-setup.c b/arch/arm/mach-ixp4xx/vulcan-setup.c
index d42730a1d4ab..d599e354ca57 100644
--- a/arch/arm/mach-ixp4xx/vulcan-setup.c
+++ b/arch/arm/mach-ixp4xx/vulcan-setup.c
@@ -163,6 +163,7 @@ static struct platform_device vulcan_max6369 = {
 
 static struct w1_gpio_platform_data vulcan_w1_gpio_pdata = {
         .pin                    = 14,
+        .ext_pullup_enable_pin  = -EINVAL,
 };
 
 static struct platform_device vulcan_w1_gpio = {
diff --git a/arch/arm/mach-kirkwood/board-dt.c b/arch/arm/mach-kirkwood/board-dt.c
index 2e73e9d53f70..d367aa6b47bb 100644
--- a/arch/arm/mach-kirkwood/board-dt.c
+++ b/arch/arm/mach-kirkwood/board-dt.c
@@ -41,16 +41,12 @@ static void __init kirkwood_legacy_clk_init(void)
 
         struct device_node *np = of_find_compatible_node(
                 NULL, NULL, "marvell,kirkwood-gating-clock");
-
         struct of_phandle_args clkspec;
+        struct clk *clk;
 
         clkspec.np = np;
         clkspec.args_count = 1;
 
-        clkspec.args[0] = CGC_BIT_GE0;
-        orion_clkdev_add(NULL, "mv643xx_eth_port.0",
-                         of_clk_get_from_provider(&clkspec));
-
         clkspec.args[0] = CGC_BIT_PEX0;
         orion_clkdev_add("0", "pcie",
                          of_clk_get_from_provider(&clkspec));
@@ -59,9 +55,24 @@ static void __init kirkwood_legacy_clk_init(void)
         orion_clkdev_add("1", "pcie",
                          of_clk_get_from_provider(&clkspec));
 
-        clkspec.args[0] = CGC_BIT_GE1;
-        orion_clkdev_add(NULL, "mv643xx_eth_port.1",
+        clkspec.args[0] = CGC_BIT_SDIO;
+        orion_clkdev_add(NULL, "mvsdio",
                          of_clk_get_from_provider(&clkspec));
+
+        /*
+         * The ethernet interfaces forget the MAC address assigned by
+         * u-boot if the clocks are turned off. Until proper DT support
+         * is available we always enable them for now.
+         */
+        clkspec.args[0] = CGC_BIT_GE0;
+        clk = of_clk_get_from_provider(&clkspec);
+        orion_clkdev_add(NULL, "mv643xx_eth_port.0", clk);
+        clk_prepare_enable(clk);
+
+        clkspec.args[0] = CGC_BIT_GE1;
+        clk = of_clk_get_from_provider(&clkspec);
+        orion_clkdev_add(NULL, "mv643xx_eth_port.1", clk);
+        clk_prepare_enable(clk);
 }
 
 static void __init kirkwood_of_clk_init(void)
diff --git a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c b/arch/arm/mach-kirkwood/board-iomega_ix2_200.c
index f655b2637b0e..e5f70415905a 100644
--- a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c
+++ b/arch/arm/mach-kirkwood/board-iomega_ix2_200.c
@@ -20,10 +20,15 @@ static struct mv643xx_eth_platform_data iomega_ix2_200_ge00_data = {
         .duplex         = DUPLEX_FULL,
 };
 
+static struct mv643xx_eth_platform_data iomega_ix2_200_ge01_data = {
+        .phy_addr       = MV643XX_ETH_PHY_ADDR(11),
+};
+
 void __init iomega_ix2_200_init(void)
 {
         /*
          * Basic setup. Needs to be called early.
          */
-        kirkwood_ge01_init(&iomega_ix2_200_ge00_data);
+        kirkwood_ge00_init(&iomega_ix2_200_ge00_data);
+        kirkwood_ge01_init(&iomega_ix2_200_ge01_data);
 }
diff --git a/arch/arm/mach-kirkwood/guruplug-setup.c b/arch/arm/mach-kirkwood/guruplug-setup.c
index 1c6e736cbbf8..08dd739aa709 100644
--- a/arch/arm/mach-kirkwood/guruplug-setup.c
+++ b/arch/arm/mach-kirkwood/guruplug-setup.c
@@ -53,6 +53,8 @@ static struct mv_sata_platform_data guruplug_sata_data = {
 
 static struct mvsdio_platform_data guruplug_mvsdio_data = {
         /* unfortunately the CD signal has not been connected */
+        .gpio_card_detect = -1,
+        .gpio_write_protect = -1,
 };
 
 static struct gpio_led guruplug_led_pins[] = {
diff --git a/arch/arm/mach-kirkwood/openrd-setup.c b/arch/arm/mach-kirkwood/openrd-setup.c
index 8ddd69fdc937..6a6eb548307d 100644
--- a/arch/arm/mach-kirkwood/openrd-setup.c
+++ b/arch/arm/mach-kirkwood/openrd-setup.c
@@ -55,6 +55,7 @@ static struct mv_sata_platform_data openrd_sata_data = {
 
 static struct mvsdio_platform_data openrd_mvsdio_data = {
         .gpio_card_detect = 29, /* MPP29 used as SD card detect */
+        .gpio_write_protect = -1,
 };
 
 static unsigned int openrd_mpp_config[] __initdata = {
diff --git a/arch/arm/mach-kirkwood/rd88f6281-setup.c b/arch/arm/mach-kirkwood/rd88f6281-setup.c
index c7d93b48926b..d24223166e06 100644
--- a/arch/arm/mach-kirkwood/rd88f6281-setup.c
+++ b/arch/arm/mach-kirkwood/rd88f6281-setup.c
@@ -69,6 +69,7 @@ static struct mv_sata_platform_data rd88f6281_sata_data = {
 
 static struct mvsdio_platform_data rd88f6281_mvsdio_data = {
         .gpio_card_detect = 28,
+        .gpio_write_protect = -1,
 };
 
 static unsigned int rd88f6281_mpp_config[] __initdata = {
diff --git a/arch/arm/mach-mmp/aspenite.c b/arch/arm/mach-mmp/aspenite.c
index 9f64d5632e07..76901f4ce611 100644
--- a/arch/arm/mach-mmp/aspenite.c
+++ b/arch/arm/mach-mmp/aspenite.c
@@ -223,13 +223,7 @@ static struct pxa27x_keypad_platform_data aspenite_keypad_info __initdata = {
 };
 
 #if defined(CONFIG_USB_EHCI_MV)
-static char *pxa168_sph_clock_name[] = {
-        [0] = "PXA168-USBCLK",
-};
-
 static struct mv_usb_platform_data pxa168_sph_pdata = {
-        .clknum         = 1,
-        .clkname        = pxa168_sph_clock_name,
         .mode           = MV_USB_MODE_HOST,
         .phy_init       = pxa_usb_phy_init,
         .phy_deinit     = pxa_usb_phy_deinit,
diff --git a/arch/arm/mach-mmp/gplugd.c b/arch/arm/mach-mmp/gplugd.c
index d1e2d595e79c..f62b68d926f4 100644
--- a/arch/arm/mach-mmp/gplugd.c
+++ b/arch/arm/mach-mmp/gplugd.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/platform_device.h>
 #include <linux/gpio.h>
 
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-mmp/ttc_dkb.c b/arch/arm/mach-mmp/ttc_dkb.c
index 22a9058f9f4d..6528a5fa6a26 100644
--- a/arch/arm/mach-mmp/ttc_dkb.c
+++ b/arch/arm/mach-mmp/ttc_dkb.c
@@ -162,13 +162,7 @@ static struct i2c_board_info ttc_dkb_i2c_info[] = {
 #ifdef CONFIG_USB_SUPPORT
 #if defined(CONFIG_USB_MV_UDC) || defined(CONFIG_USB_EHCI_MV_U2O)
 
-static char *pxa910_usb_clock_name[] = {
-        [0] = "U2OCLK",
-};
-
 static struct mv_usb_platform_data ttc_usb_pdata = {
-        .clknum         = 1,
-        .clkname        = pxa910_usb_clock_name,
         .vbus           = NULL,
         .mode           = MV_USB_MODE_OTG,
         .otg_force_a_bus_req = 1,
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 2969027f02fa..f9fd77e8f1f5 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -62,7 +62,10 @@ static int msm_timer_set_next_event(unsigned long cycles,
 {
         u32 ctrl = readl_relaxed(event_base + TIMER_ENABLE);
 
-        writel_relaxed(0, event_base + TIMER_CLEAR);
+        ctrl &= ~TIMER_ENABLE_EN;
+        writel_relaxed(ctrl, event_base + TIMER_ENABLE);
+
+        writel_relaxed(ctrl, event_base + TIMER_CLEAR);
         writel_relaxed(cycles, event_base + TIMER_MATCH_VAL);
         writel_relaxed(ctrl | TIMER_ENABLE_EN, event_base + TIMER_ENABLE);
         return 0;
diff --git a/arch/arm/mach-mvebu/irq-armada-370-xp.c b/arch/arm/mach-mvebu/irq-armada-370-xp.c
index 274ff58271de..830139a3e2ba 100644
--- a/arch/arm/mach-mvebu/irq-armada-370-xp.c
+++ b/arch/arm/mach-mvebu/irq-armada-370-xp.c
@@ -44,6 +44,8 @@
 
 #define ARMADA_370_XP_MAX_PER_CPU_IRQS          (28)
 
+#define ARMADA_370_XP_TIMER0_PER_CPU_IRQ        (5)
+
 #define ACTIVE_DOORBELLS                        (8)
 
 static DEFINE_RAW_SPINLOCK(irq_controller_lock);
@@ -55,40 +57,30 @@ static struct irq_domain *armada_370_xp_mpic_domain;
 /*
  * In SMP mode:
  * For shared global interrupts, mask/unmask global enable bit
- * For CPU interrtups, mask/unmask the calling CPU's bit
+ * For CPU interrupts, mask/unmask the calling CPU's bit
  */
 static void armada_370_xp_irq_mask(struct irq_data *d)
 {
-#ifdef CONFIG_SMP
         irq_hw_number_t hwirq = irqd_to_hwirq(d);
 
-        if (hwirq > ARMADA_370_XP_MAX_PER_CPU_IRQS)
+        if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ)
                 writel(hwirq, main_int_base +
                                 ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS);
         else
                 writel(hwirq, per_cpu_int_base +
                                 ARMADA_370_XP_INT_SET_MASK_OFFS);
-#else
-        writel(irqd_to_hwirq(d),
-               per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS);
-#endif
 }
 
 static void armada_370_xp_irq_unmask(struct irq_data *d)
 {
-#ifdef CONFIG_SMP
         irq_hw_number_t hwirq = irqd_to_hwirq(d);
 
-        if (hwirq > ARMADA_370_XP_MAX_PER_CPU_IRQS)
+        if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ)
                 writel(hwirq, main_int_base +
                                 ARMADA_370_XP_INT_SET_ENABLE_OFFS);
         else
                 writel(hwirq, per_cpu_int_base +
                                 ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
-#else
-        writel(irqd_to_hwirq(d),
-               per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
-#endif
 }
 
 #ifdef CONFIG_SMP
@@ -144,10 +136,14 @@ static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
                                       unsigned int virq, irq_hw_number_t hw)
 {
         armada_370_xp_irq_mask(irq_get_irq_data(virq));
-        writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS);
+        if (hw != ARMADA_370_XP_TIMER0_PER_CPU_IRQ)
+                writel(hw, per_cpu_int_base +
+                        ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+        else
+                writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS);
         irq_set_status_flags(virq, IRQ_LEVEL);
 
-        if (hw < ARMADA_370_XP_MAX_PER_CPU_IRQS) {
+        if (hw == ARMADA_370_XP_TIMER0_PER_CPU_IRQ) {
                 irq_set_percpu_devid(virq);
                 irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
                                         handle_percpu_devid_irq);
diff --git a/arch/arm/mach-mxs/icoll.c b/arch/arm/mach-mxs/icoll.c
index 8fb23af154b3..e26eeba46598 100644
--- a/arch/arm/mach-mxs/icoll.c
+++ b/arch/arm/mach-mxs/icoll.c
@@ -100,7 +100,7 @@ static struct irq_domain_ops icoll_irq_domain_ops = {
         .xlate = irq_domain_xlate_onecell,
 };
 
-void __init icoll_of_init(struct device_node *np,
+static void __init icoll_of_init(struct device_node *np,
                           struct device_node *interrupt_parent)
 {
         /*
diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c
index 052186713347..e7b781d3788f 100644
--- a/arch/arm/mach-mxs/mach-mxs.c
+++ b/arch/arm/mach-mxs/mach-mxs.c
@@ -41,8 +41,6 @@ static struct fb_videomode mx23evk_video_modes[] = {
                 .lower_margin   = 4,
                 .hsync_len      = 1,
                 .vsync_len      = 1,
-                .sync           = FB_SYNC_DATA_ENABLE_HIGH_ACT |
-                                  FB_SYNC_DOTCLK_FAILING_ACT,
         },
 };
 
@@ -59,8 +57,6 @@ static struct fb_videomode mx28evk_video_modes[] = {
                 .lower_margin   = 10,
                 .hsync_len      = 10,
                 .vsync_len      = 10,
-                .sync           = FB_SYNC_DATA_ENABLE_HIGH_ACT |
-                                  FB_SYNC_DOTCLK_FAILING_ACT,
         },
 };
 
@@ -77,7 +73,6 @@ static struct fb_videomode m28evk_video_modes[] = {
                 .lower_margin   = 45,
                 .hsync_len      = 1,
                 .vsync_len      = 1,
-                .sync           = FB_SYNC_DATA_ENABLE_HIGH_ACT,
         },
 };
 
@@ -94,9 +89,7 @@ static struct fb_videomode apx4devkit_video_modes[] = {
                 .lower_margin   = 13,
                 .hsync_len      = 48,
                 .vsync_len      = 3,
-                .sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT |
-                                  FB_SYNC_DATA_ENABLE_HIGH_ACT |
-                                  FB_SYNC_DOTCLK_FAILING_ACT,
+                .sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
         },
 };
 
@@ -113,9 +106,7 @@ static struct fb_videomode apf28dev_video_modes[] = {
                 .lower_margin = 0x15,
                 .hsync_len = 64,
                 .vsync_len = 4,
-                .sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT |
-                                FB_SYNC_DATA_ENABLE_HIGH_ACT |
-                                FB_SYNC_DOTCLK_FAILING_ACT,
+                .sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
         },
 };
 
@@ -132,7 +123,6 @@ static struct fb_videomode cfa10049_video_modes[] = {
                 .lower_margin   = 2,
                 .hsync_len      = 15,
                 .vsync_len      = 15,
-                .sync           = FB_SYNC_DATA_ENABLE_HIGH_ACT
         },
 };
 
@@ -259,6 +249,8 @@ static void __init imx23_evk_init(void)
         mxsfb_pdata.mode_count = ARRAY_SIZE(mx23evk_video_modes);
         mxsfb_pdata.default_bpp = 32;
         mxsfb_pdata.ld_intf_width = STMLCDIF_24BIT;
+        mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT |
+                                MXSFB_SYNC_DOTCLK_FAILING_ACT;
 }
 
 static inline void enable_clk_enet_out(void)
@@ -278,6 +270,8 @@ static void __init imx28_evk_init(void)
         mxsfb_pdata.mode_count = ARRAY_SIZE(mx28evk_video_modes);
         mxsfb_pdata.default_bpp = 32;
         mxsfb_pdata.ld_intf_width = STMLCDIF_24BIT;
+        mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT |
+                                MXSFB_SYNC_DOTCLK_FAILING_ACT;
 
         mxs_saif_clkmux_select(MXS_DIGCTL_SAIF_CLKMUX_EXTMSTR0);
 }
@@ -297,6 +291,7 @@ static void __init m28evk_init(void)
         mxsfb_pdata.mode_count = ARRAY_SIZE(m28evk_video_modes);
         mxsfb_pdata.default_bpp = 16;
         mxsfb_pdata.ld_intf_width = STMLCDIF_18BIT;
+        mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT;
 }
 
 static void __init sc_sps1_init(void)
@@ -322,6 +317,8 @@ static void __init apx4devkit_init(void)
         mxsfb_pdata.mode_count = ARRAY_SIZE(apx4devkit_video_modes);
         mxsfb_pdata.default_bpp = 32;
         mxsfb_pdata.ld_intf_width = STMLCDIF_24BIT;
+        mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT |
+                                MXSFB_SYNC_DOTCLK_FAILING_ACT;
 }
 
 #define ENET0_MDC__GPIO_4_0     MXS_GPIO_NR(4, 0)
@@ -402,17 +399,18 @@ static void __init cfa10049_init(void)
 {
         enable_clk_enet_out();
         update_fec_mac_prop(OUI_CRYSTALFONTZ);
+
+        mxsfb_pdata.mode_list = cfa10049_video_modes;
+        mxsfb_pdata.mode_count = ARRAY_SIZE(cfa10049_video_modes);
+        mxsfb_pdata.default_bpp = 32;
+        mxsfb_pdata.ld_intf_width = STMLCDIF_18BIT;
+        mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT;
 }
 
 static void __init cfa10037_init(void)
 {
         enable_clk_enet_out();
         update_fec_mac_prop(OUI_CRYSTALFONTZ);
-
-        mxsfb_pdata.mode_list = cfa10049_video_modes;
-        mxsfb_pdata.mode_count = ARRAY_SIZE(cfa10049_video_modes);
-        mxsfb_pdata.default_bpp = 32;
-        mxsfb_pdata.ld_intf_width = STMLCDIF_18BIT;
 }
 
 static void __init apf28_init(void)
@@ -423,6 +421,8 @@ static void __init apf28_init(void)
         mxsfb_pdata.mode_count = ARRAY_SIZE(apf28dev_video_modes);
         mxsfb_pdata.default_bpp = 16;
         mxsfb_pdata.ld_intf_width = STMLCDIF_16BIT;
+        mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT |
+                                MXSFB_SYNC_DOTCLK_FAILING_ACT;
 }
 
 static void __init mxs_machine_init(void)
diff --git a/arch/arm/mach-mxs/mm.c b/arch/arm/mach-mxs/mm.c
index a4294aa9f301..e63b7d87acbd 100644
--- a/arch/arm/mach-mxs/mm.c
+++ b/arch/arm/mach-mxs/mm.c
@@ -18,6 +18,7 @@
 
 #include <mach/mx23.h>
 #include <mach/mx28.h>
+#include <mach/common.h>
 
 /*
  * Define the MX23 memory map.
diff --git a/arch/arm/mach-mxs/ocotp.c b/arch/arm/mach-mxs/ocotp.c
index 54add60f94c9..1dff46703753 100644
--- a/arch/arm/mach-mxs/ocotp.c
+++ b/arch/arm/mach-mxs/ocotp.c
@@ -19,6 +19,7 @@
 #include <asm/processor.h>      /* for cpu_relax() */
 
 #include <mach/mxs.h>
+#include <mach/common.h>
 
 #define OCOTP_WORD_OFFSET               0x20
 #define OCOTP_WORD_COUNT                0x20
diff --git a/arch/arm/mach-omap1/clock_data.c b/arch/arm/mach-omap1/clock_data.c
index cb7c6ae2e3fc..6c4f766365a2 100644
--- a/arch/arm/mach-omap1/clock_data.c
+++ b/arch/arm/mach-omap1/clock_data.c
@@ -543,15 +543,6 @@ static struct clk usb_dc_ck = {
         /* Direct from ULPD, no parent */
         .rate           = 48000000,
         .enable_reg     = OMAP1_IO_ADDRESS(SOFT_REQ_REG),
-        .enable_bit     = USB_REQ_EN_SHIFT,
-};
-
-static struct clk usb_dc_ck7xx = {
-        .name           = "usb_dc_ck",
-        .ops            = &clkops_generic,
-        /* Direct from ULPD, no parent */
-        .rate           = 48000000,
-        .enable_reg     = OMAP1_IO_ADDRESS(SOFT_REQ_REG),
         .enable_bit     = SOFT_USB_OTG_DPLL_REQ_SHIFT,
 };
 
@@ -727,8 +718,7 @@ static struct omap_clk omap_clks[] = {
         CLK(NULL,       "usb_clko",     &usb_clko,      CK_16XX | CK_1510 | CK_310),
         CLK(NULL,       "usb_hhc_ck",   &usb_hhc_ck1510, CK_1510 | CK_310),
         CLK(NULL,       "usb_hhc_ck",   &usb_hhc_ck16xx, CK_16XX),
-        CLK(NULL,       "usb_dc_ck",    &usb_dc_ck,     CK_16XX),
-        CLK(NULL,       "usb_dc_ck",    &usb_dc_ck7xx,  CK_7XX),
+        CLK(NULL,       "usb_dc_ck",    &usb_dc_ck,     CK_16XX | CK_7XX),
         CLK(NULL,       "mclk",         &mclk_1510,     CK_1510 | CK_310),
         CLK(NULL,       "mclk",         &mclk_16xx,     CK_16XX),
         CLK(NULL,       "bclk",         &bclk_1510,     CK_1510 | CK_310),
diff --git a/arch/arm/mach-omap1/common.h b/arch/arm/mach-omap1/common.h
index fb18831e88aa..14f7e9920479 100644
--- a/arch/arm/mach-omap1/common.h
+++ b/arch/arm/mach-omap1/common.h
@@ -31,6 +31,8 @@
 
 #include <plat/i2c.h>
 
+#include <mach/irqs.h>
+
 #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850)
 void omap7xx_map_io(void);
 #else
diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c
index 7a7690ab6cb8..db37f49da5ac 100644
--- a/arch/arm/mach-omap1/pm.c
+++ b/arch/arm/mach-omap1/pm.c
@@ -43,6 +43,7 @@
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/atomic.h>
+#include <linux/cpu.h>
 
 #include <asm/fncpy.h>
 #include <asm/system_misc.h>
@@ -584,8 +585,7 @@ static void omap_pm_init_proc(void)
 static int omap_pm_prepare(void)
 {
         /* We cannot sleep in idle until we have resumed */
-        disable_hlt();
-
+        cpu_idle_poll_ctrl(true);
         return 0;
 }
 
@@ -621,7 +621,7 @@ static int omap_pm_enter(suspend_state_t state)
 
 static void omap_pm_finish(void)
 {
-        enable_hlt();
+        cpu_idle_poll_ctrl(false);
 }
 
 
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 49ac3dfebef9..8111cd9ff3e5 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -311,9 +311,6 @@ config MACH_OMAP_ZOOM2
         default y
         select OMAP_PACKAGE_CBB
         select REGULATOR_FIXED_VOLTAGE if REGULATOR
-        select SERIAL_8250
-        select SERIAL_8250_CONSOLE
-        select SERIAL_CORE_CONSOLE
 
 config MACH_OMAP_ZOOM3
         bool "OMAP3630 Zoom3 board"
@@ -321,9 +318,6 @@ config MACH_OMAP_ZOOM3
         default y
         select OMAP_PACKAGE_CBP
         select REGULATOR_FIXED_VOLTAGE if REGULATOR
-        select SERIAL_8250
-        select SERIAL_8250_CONSOLE
-        select SERIAL_CORE_CONSOLE
 
 config MACH_CM_T35
         bool "CompuLab CM-T35/CM-T3730 modules"
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 0274ff7a2a2b..e54a48060198 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -102,6 +102,7 @@ DT_MACHINE_START(OMAP3_DT, "Generic OMAP3 (Flattened Device Tree)")
         .init_irq       = omap_intc_of_init,
         .handle_irq     = omap3_intc_handle_irq,
         .init_machine   = omap_generic_init,
+        .init_late      = omap3_init_late,
         .init_time      = omap3_sync32k_timer_init,
         .dt_compat      = omap3_boards_compat,
         .restart        = omap3xxx_restart,
@@ -119,6 +120,7 @@ DT_MACHINE_START(OMAP3_GP_DT, "Generic OMAP3-GP (Flattened Device Tree)")
         .init_irq       = omap_intc_of_init,
         .handle_irq     = omap3_intc_handle_irq,
         .init_machine   = omap_generic_init,
+        .init_late      = omap3_init_late,
         .init_time      = omap3_secure_sync32k_timer_init,
         .dt_compat      = omap3_gp_boards_compat,
         .restart        = omap3xxx_restart,
diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c
index f7c4616cbb60..d2ea68ea678a 100644
--- a/arch/arm/mach-omap2/board-rx51.c
+++ b/arch/arm/mach-omap2/board-rx51.c
@@ -17,6 +17,7 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
 #include <linux/leds.h>
+#include <linux/usb/phy.h>
 #include <linux/usb/musb.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 
@@ -98,6 +99,7 @@ static void __init rx51_init(void)
         sdrc_params = nokia_get_sdram_timings();
         omap_sdrc_init(sdrc_params, sdrc_params);
 
+        usb_bind_phy("musb-hdrc.0.auto", 0, "twl4030_usb");
         usb_musb_init(&musb_board_data);
         rx51_peripherals_init();
 
diff --git a/arch/arm/mach-omap2/cclock44xx_data.c b/arch/arm/mach-omap2/cclock44xx_data.c
index 3d58f335f173..0c6834ae1fc4 100644
--- a/arch/arm/mach-omap2/cclock44xx_data.c
+++ b/arch/arm/mach-omap2/cclock44xx_data.c
@@ -52,6 +52,13 @@
  */
 #define OMAP4_DPLL_ABE_DEFFREQ                          98304000
 
+/*
+ * OMAP4 USB DPLL default frequency. In OMAP4430 TRM version V, section
+ * "3.6.3.9.5 DPLL_USB Preferred Settings" shows that the preferred
+ * locked frequency for the USB DPLL is 960MHz.
+ */
+#define OMAP4_DPLL_USB_DEFFREQ                          960000000
+
 /* Root clocks */
 
 DEFINE_CLK_FIXED_RATE(extalt_clkin_ck, CLK_IS_ROOT, 59000000, 0x0);
@@ -1011,6 +1018,10 @@ DEFINE_CLK_OMAP_MUX(hsmmc2_fclk, "l3_init_clkdm", hsmmc1_fclk_sel,
                     OMAP4430_CM_L3INIT_MMC2_CLKCTRL, OMAP4430_CLKSEL_MASK,
                     hsmmc1_fclk_parents, func_dmic_abe_gfclk_ops);
 
+DEFINE_CLK_GATE(ocp2scp_usb_phy_phy_48m, "func_48m_fclk", &func_48m_fclk, 0x0,
+                OMAP4430_CM_L3INIT_USBPHYOCP2SCP_CLKCTRL,
+                OMAP4430_OPTFCLKEN_PHY_48M_SHIFT, 0x0, NULL);
+
 DEFINE_CLK_GATE(sha2md5_fck, "l3_div_ck", &l3_div_ck, 0x0,
                 OMAP4430_CM_L4SEC_SHA2MD51_CLKCTRL,
                 OMAP4430_MODULEMODE_SWCTRL_SHIFT, 0x0, NULL);
@@ -1538,6 +1549,7 @@ static struct omap_clk omap44xx_clks[] = {
         CLK(NULL,       "per_mcbsp4_gfclk",                     &per_mcbsp4_gfclk,      CK_443X),
         CLK(NULL,       "hsmmc1_fclk",                  &hsmmc1_fclk,   CK_443X),
         CLK(NULL,       "hsmmc2_fclk",                  &hsmmc2_fclk,   CK_443X),
+        CLK(NULL,       "ocp2scp_usb_phy_phy_48m",      &ocp2scp_usb_phy_phy_48m,       CK_443X),
         CLK(NULL,       "sha2md5_fck",                  &sha2md5_fck,   CK_443X),
         CLK(NULL,       "slimbus1_fclk_1",              &slimbus1_fclk_1,       CK_443X),
         CLK(NULL,       "slimbus1_fclk_0",              &slimbus1_fclk_0,       CK_443X),
@@ -1705,5 +1717,13 @@ int __init omap4xxx_clk_init(void)
         if (rc)
                 pr_err("%s: failed to configure ABE DPLL!\n", __func__);
 
+        /*
+         * Lock USB DPLL on OMAP4 devices so that the L3INIT power
+         * domain can transition to retention state when not in use.
+         */
+        rc = clk_set_rate(&dpll_usb_ck, OMAP4_DPLL_USB_DEFFREQ);
+        if (rc)
+                pr_err("%s: failed to configure USB DPLL!\n", __func__);
+
         return 0;
 }
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index 0a6b9c7a63da..d6ba13e1c540 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -108,7 +108,6 @@ void omap35xx_init_late(void);
 void omap3630_init_late(void);
 void am35xx_init_late(void);
 void ti81xx_init_late(void);
-void omap4430_init_late(void);
 int omap2_common_pm_late_init(void);
 
 #if defined(CONFIG_SOC_OMAP2420) || defined(CONFIG_SOC_OMAP2430)
@@ -294,5 +293,8 @@ extern void omap_reserve(void);
 struct omap_hwmod;
 extern int omap_dss_reset(struct omap_hwmod *);
 
+/* SoC specific clock initializer */
+extern int (*omap_clk_init)(void);
+
 #endif /* __ASSEMBLER__ */
 #endif /* __ARCH_ARM_MACH_OMAP2PLUS_COMMON_H */
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index e4b16c8efe8b..410e1bac7815 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -1122,9 +1122,6 @@ int gpmc_calc_timings(struct gpmc_timings *gpmc_t,
         /* TODO: remove, see function definition */
         gpmc_convert_ps_to_ns(gpmc_t);
 
-        /* Now the GPMC is initialised, unreserve the chip-selects */
-        gpmc_cs_map = 0;
-
         return 0;
 }
 
@@ -1383,6 +1380,9 @@ static int gpmc_probe(struct platform_device *pdev)
         if (IS_ERR_VALUE(gpmc_setup_irq()))
                 dev_warn(gpmc_dev, "gpmc_setup_irq failed\n");
 
+        /* Now the GPMC is initialised, unreserve the chip-selects */
+        gpmc_cs_map = 0;
+
         rc = gpmc_probe_dt(pdev);
         if (rc < 0) {
                 clk_disable_unprepare(gpmc_l3_clk);
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 2c3fdd65387b..5c445ca1e271 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -55,6 +55,12 @@
 #include "prm44xx.h"
 
 /*
+ * omap_clk_init: points to a function that does the SoC-specific
+ * clock initializations
+ */
+int (*omap_clk_init)(void);
+
+/*
  * The machine specific code may provide the extra mapping besides the
  * default mapping provided here.
  */
@@ -397,7 +403,7 @@ void __init omap2420_init_early(void)
         omap242x_clockdomains_init();
         omap2420_hwmod_init();
         omap_hwmod_init_postsetup();
-        omap2420_clk_init();
+        omap_clk_init = omap2420_clk_init;
 }
 
 void __init omap2420_init_late(void)
@@ -427,7 +433,7 @@ void __init omap2430_init_early(void)
         omap243x_clockdomains_init();
         omap2430_hwmod_init();
         omap_hwmod_init_postsetup();
-        omap2430_clk_init();
+        omap_clk_init = omap2430_clk_init;
 }
 
 void __init omap2430_init_late(void)
@@ -462,7 +468,7 @@ void __init omap3_init_early(void)
         omap3xxx_clockdomains_init();
         omap3xxx_hwmod_init();
         omap_hwmod_init_postsetup();
-        omap3xxx_clk_init();
+        omap_clk_init = omap3xxx_clk_init;
 }
 
 void __init omap3430_init_early(void)
@@ -500,7 +506,7 @@ void __init ti81xx_init_early(void)
         omap3xxx_clockdomains_init();
         omap3xxx_hwmod_init();
         omap_hwmod_init_postsetup();
-        omap3xxx_clk_init();
+        omap_clk_init = omap3xxx_clk_init;
 }
 
 void __init omap3_init_late(void)
@@ -568,7 +574,7 @@ void __init am33xx_init_early(void)
         am33xx_clockdomains_init();
         am33xx_hwmod_init();
         omap_hwmod_init_postsetup();
-        am33xx_clk_init();
+        omap_clk_init = am33xx_clk_init;
 }
 #endif
 
@@ -593,7 +599,7 @@ void __init omap4430_init_early(void)
         omap44xx_clockdomains_init();
         omap44xx_hwmod_init();
         omap_hwmod_init_postsetup();
-        omap4xxx_clk_init();
+        omap_clk_init = omap4xxx_clk_init;
 }
 
 void __init omap4430_init_late(void)
diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c
index 6a217c98db54..f82cf878d6af 100644
--- a/arch/arm/mach-omap2/mux.c
+++ b/arch/arm/mach-omap2/mux.c
@@ -211,8 +211,6 @@ static int __init _omap_mux_get_by_name(struct omap_mux_partition *partition,
                 return -EINVAL;
         }
 
-        pr_err("%s: Could not find signal %s\n", __func__, muxname);
-
         return -ENODEV;
 }
 
@@ -234,6 +232,8 @@ int __init omap_mux_get_by_name(const char *muxname,
                 return mux_mode;
         }
 
+        pr_err("%s: Could not find signal %s\n", __func__, muxname);
+
         return -ENODEV;
 }
 
@@ -739,8 +739,9 @@ static void __init omap_mux_dbg_create_entry(
         list_for_each_entry(e, &partition->muxmodes, node) {
                 struct omap_mux *m = &e->mux;
 
-                (void)debugfs_create_file(m->muxnames[0], S_IWUSR, mux_dbg_dir,
-                                          m, &omap_mux_dbg_signal_fops);
+                (void)debugfs_create_file(m->muxnames[0], S_IWUSR | S_IRUGO,
+                                          mux_dbg_dir, m,
+                                          &omap_mux_dbg_signal_fops);
         }
 }
 
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index c2c798c08c2b..e512253601c8 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -138,6 +138,7 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/bootmem.h>
+#include <linux/cpu.h>
 
 #include <asm/system_misc.h>
 
@@ -1368,7 +1369,9 @@ static void _enable_sysc(struct omap_hwmod *oh)
         }
 
         if (sf & SYSC_HAS_MIDLEMODE) {
-                if (oh->flags & HWMOD_SWSUP_MSTANDBY) {
+                if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+                        idlemode = HWMOD_IDLEMODE_FORCE;
+                } else if (oh->flags & HWMOD_SWSUP_MSTANDBY) {
                         idlemode = HWMOD_IDLEMODE_NO;
                 } else {
                         if (sf & SYSC_HAS_ENAWAKEUP)
@@ -1440,7 +1443,8 @@ static void _idle_sysc(struct omap_hwmod *oh)
         }
 
         if (sf & SYSC_HAS_MIDLEMODE) {
-                if (oh->flags & HWMOD_SWSUP_MSTANDBY) {
+                if ((oh->flags & HWMOD_SWSUP_MSTANDBY) ||
+                    (oh->flags & HWMOD_FORCE_MSTANDBY)) {
                         idlemode = HWMOD_IDLEMODE_FORCE;
                 } else {
                         if (sf & SYSC_HAS_ENAWAKEUP)
@@ -2154,7 +2158,7 @@ static int _enable(struct omap_hwmod *oh)
         if (soc_ops.enable_module)
                 soc_ops.enable_module(oh);
         if (oh->flags & HWMOD_BLOCK_WFI)
-                disable_hlt();
+                cpu_idle_poll_ctrl(true);
 
         if (soc_ops.update_context_lost)
                 soc_ops.update_context_lost(oh);
@@ -2218,7 +2222,7 @@ static int _idle(struct omap_hwmod *oh)
         _del_initiator_dep(oh, mpu_oh);
 
         if (oh->flags & HWMOD_BLOCK_WFI)
-                enable_hlt();
+                cpu_idle_poll_ctrl(false);
         if (soc_ops.disable_module)
                 soc_ops.disable_module(oh);
 
@@ -2328,7 +2332,7 @@ static int _shutdown(struct omap_hwmod *oh)
                 _del_initiator_dep(oh, mpu_oh);
                 /* XXX what about the other system initiators here? dma, dsp */
                 if (oh->flags & HWMOD_BLOCK_WFI)
-                        enable_hlt();
+                        cpu_idle_poll_ctrl(false);
                 if (soc_ops.disable_module)
                         soc_ops.disable_module(oh);
                 _disable_clocks(oh);
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index d43d9b608eda..d5dc935f6060 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -427,8 +427,8 @@ struct omap_hwmod_omap4_prcm {
  *
  * HWMOD_SWSUP_SIDLE: omap_hwmod code should manually bring module in and out
  *     of idle, rather than relying on module smart-idle
- * HWMOD_SWSUP_MSTDBY: omap_hwmod code should manually bring module in and out
- *     of standby, rather than relying on module smart-standby
+ * HWMOD_SWSUP_MSTANDBY: omap_hwmod code should manually bring module in and
+ *     out of standby, rather than relying on module smart-standby
  * HWMOD_INIT_NO_RESET: don't reset this module at boot - important for
  *     SDRAM controller, etc. XXX probably belongs outside the main hwmod file
  *     XXX Should be HWMOD_SETUP_NO_RESET
@@ -459,6 +459,10 @@ struct omap_hwmod_omap4_prcm {
  *     correctly, or this is being abused to deal with some PM latency
  *     issues -- but we're currently suffering from a shortage of
  *     folks who are able to track these issues down properly.
+ * HWMOD_FORCE_MSTANDBY: Always keep MIDLEMODE bits cleared so that device
+ *     is kept in force-standby mode. Failing to do so causes PM problems
+ *     with musb on OMAP3630 at least. Note that musb has a dedicated register
+ *     to control MSTANDBY signal when MIDLEMODE is set to force-standby.
  */
 #define HWMOD_SWSUP_SIDLE                       (1 << 0)
 #define HWMOD_SWSUP_MSTANDBY                    (1 << 1)
@@ -471,6 +475,7 @@ struct omap_hwmod_omap4_prcm {
 #define HWMOD_16BIT_REG                         (1 << 8)
 #define HWMOD_EXT_OPT_MAIN_CLK                  (1 << 9)
 #define HWMOD_BLOCK_WFI                         (1 << 10)
+#define HWMOD_FORCE_MSTANDBY                    (1 << 11)
 
 /*
  * omap_hwmod._int_flags definitions
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index ac7e03ec952f..5112d04e7b79 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -1707,9 +1707,14 @@ static struct omap_hwmod omap3xxx_usbhsotg_hwmod = {
          * Erratum ID: i479  idle_req / idle_ack mechanism potentially
          * broken when autoidle is enabled
          * workaround is to disable the autoidle bit at module level.
+         *
+         * Enabling the device in any other MIDLEMODE setting but force-idle
+         * causes core_pwrdm not enter idle states at least on OMAP3630.
+         * Note that musb has OTG_FORCESTDBY register that controls MSTANDBY
+         * signal when MIDLEMODE is set to force-idle.
          */
         .flags          = HWMOD_NO_OCP_AUTOIDLE | HWMOD_SWSUP_SIDLE
-                                | HWMOD_SWSUP_MSTANDBY,
+                                | HWMOD_FORCE_MSTANDBY,
 };
 
 /* usb_otg_hs */
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 0e47d2e1687c..eaba9dc91a0d 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -2719,7 +2719,17 @@ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = {
         .name           = "ocp2scp_usb_phy",
         .class          = &omap44xx_ocp2scp_hwmod_class,
         .clkdm_name     = "l3_init_clkdm",
-        .main_clk       = "func_48m_fclk",
+        /*
+         * ocp2scp_usb_phy_phy_48m is provided by the OMAP4 PRCM IP
+         * block as an "optional clock," and normally should never be
+         * specified as the main_clk for an OMAP IP block.  However it
+         * turns out that this clock is actually the main clock for
+         * the ocp2scp_usb_phy IP block:
+         * http://lists.infradead.org/pipermail/linux-arm-kernel/2012-September/119943.html
+         * So listing ocp2scp_usb_phy_phy_48m as a main_clk here seems
+         * to be the best workaround.
+         */
+        .main_clk       = "ocp2scp_usb_phy_phy_48m",
         .prcm = {
                 .omap4 = {
                         .clkctrl_offs = OMAP4_CM_L3INIT_USBPHYOCP2SCP_CLKCTRL_OFFSET,
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 673a4c1d1d76..dec553349ae2 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -218,7 +218,7 @@ static int omap_pm_enter(suspend_state_t suspend_state)
 
 static int omap_pm_begin(suspend_state_t state)
 {
-        disable_hlt();
+        cpu_idle_poll_ctrl(true);
         if (cpu_is_omap34xx())
                 omap_prcm_irq_prepare();
         return 0;
@@ -226,8 +226,7 @@ static int omap_pm_begin(suspend_state_t state)
 
 static void omap_pm_end(void)
 {
-        enable_hlt();
-        return;
+        cpu_idle_poll_ctrl(false);
 }
 
 static void omap_pm_finish(void)
diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c
index ea62e75ef21d..152a10cf4f1d 100644
--- a/arch/arm/mach-omap2/pm44xx.c
+++ b/arch/arm/mach-omap2/pm44xx.c
@@ -126,8 +126,8 @@ static int __init pwrdms_setup(struct powerdomain *pwrdm, void *unused)
  * omap_default_idle - OMAP4 default ilde routine.'
  *
  * Implements OMAP4 memory, IO ordering requirements which can't be addressed
- * with default cpu_do_idle() hook. Used by all CPUs with !CONFIG_CPUIDLE and
- * by secondary CPU with CONFIG_CPUIDLE.
+ * with default cpu_do_idle() hook. Used by all CPUs with !CONFIG_CPU_IDLE and
+ * by secondary CPU with CONFIG_CPU_IDLE.
  */
 static void omap_default_idle(void)
 {
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 2bdd4cf17a8f..f62b509ed08d 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -547,6 +547,8 @@ static inline void __init realtime_counter_init(void)
                                clksrc_nr, clksrc_src)                   \
 void __init omap##name##_gptimer_timer_init(void)                       \
 {                                                                       \
+        if (omap_clk_init)                                              \
+                omap_clk_init();                                        \
         omap_dmtimer_init();                                            \
         omap2_gp_clockevent_init((clkev_nr), clkev_src, clkev_prop);    \
         omap2_gptimer_clocksource_init((clksrc_nr), clksrc_src);        \
@@ -556,6 +558,8 @@ void __init omap##name##_gptimer_timer_init(void)			\
                                 clksrc_nr, clksrc_src)                  \
 void __init omap##name##_sync32k_timer_init(void)               \
 {                                                                       \
+        if (omap_clk_init)                                              \
+                omap_clk_init();                                        \
         omap_dmtimer_init();                                            \
         omap2_gp_clockevent_init((clkev_nr), clkev_src, clkev_prop);    \
         /* Enable the use of clocksource="gp_timer" kernel parameter */ \
diff --git a/arch/arm/mach-orion5x/board-dt.c b/arch/arm/mach-orion5x/board-dt.c
index 35a8014529ca..94fbb815680c 100644
--- a/arch/arm/mach-orion5x/board-dt.c
+++ b/arch/arm/mach-orion5x/board-dt.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/cpu.h>
 #include <asm/system_misc.h>
 #include <asm/mach/arch.h>
 #include <mach/orion5x.h>
@@ -52,7 +53,7 @@ static void __init orion5x_dt_init(void)
          */
         if (dev == MV88F5281_DEV_ID && rev == MV88F5281_REV_D0) {
                 printk(KERN_INFO "Orion: Applying 5281 D0 WFI workaround.\n");
-                disable_hlt();
+                cpu_idle_poll_ctrl(true);
         }
 
         if (of_machine_is_compatible("lacie,ethernet-disk-mini-v2"))
diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c
index d068f1431c40..ad71c8a03ffd 100644
--- a/arch/arm/mach-orion5x/common.c
+++ b/arch/arm/mach-orion5x/common.c
@@ -293,7 +293,7 @@ void __init orion5x_init(void)
          */
         if (dev == MV88F5281_DEV_ID && rev == MV88F5281_REV_D0) {
                 printk(KERN_INFO "Orion: Applying 5281 D0 WFI workaround.\n");
-                disable_hlt();
+                cpu_idle_poll_ctrl(true);
         }
 
         /*
diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c
index af41888acbd6..969b0ba7fa70 100644
--- a/arch/arm/mach-pxa/raumfeld.c
+++ b/arch/arm/mach-pxa/raumfeld.c
@@ -505,6 +505,7 @@ static struct w1_gpio_platform_data w1_gpio_platform_data = {
         .pin                    = GPIO_ONE_WIRE,
         .is_open_drain          = 0,
         .enable_external_pullup = w1_enable_external_pullup,
+        .ext_pullup_enable_pin  = -EINVAL,
 };
 
 struct platform_device raumfeld_w1_gpio_device = {
diff --git a/arch/arm/mach-s3c24xx/clock-s3c2440.c b/arch/arm/mach-s3c24xx/clock-s3c2440.c
index 04b87ec92537..1069b5680826 100644
--- a/arch/arm/mach-s3c24xx/clock-s3c2440.c
+++ b/arch/arm/mach-s3c24xx/clock-s3c2440.c
@@ -123,6 +123,11 @@ static struct clk s3c2440_clk_ac97 = {
         .ctrlbit        = S3C2440_CLKCON_AC97,
 };
 
+#define S3C24XX_VA_UART0      (S3C_VA_UART)
+#define S3C24XX_VA_UART1      (S3C_VA_UART + 0x4000 )
+#define S3C24XX_VA_UART2      (S3C_VA_UART + 0x8000 )
+#define S3C24XX_VA_UART3      (S3C_VA_UART + 0xC000 )
+
 static unsigned long  s3c2440_fclk_n_getrate(struct clk *clk)
 {
         unsigned long ucon0, ucon1, ucon2, divisor;
diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c
index 6bcf87f65f9e..92e609440c57 100644
--- a/arch/arm/mach-s3c24xx/common.c
+++ b/arch/arm/mach-s3c24xx/common.c
@@ -239,6 +239,11 @@ void __init s3c24xx_init_io(struct map_desc *mach_desc, int size)
 
 /* Serial port registrations */
 
+#define S3C2410_PA_UART0      (S3C24XX_PA_UART)
+#define S3C2410_PA_UART1      (S3C24XX_PA_UART + 0x4000 )
+#define S3C2410_PA_UART2      (S3C24XX_PA_UART + 0x8000 )
+#define S3C2443_PA_UART3      (S3C24XX_PA_UART + 0xC000 )
+
 static struct resource s3c2410_uart0_resource[] = {
         [0] = DEFINE_RES_MEM(S3C2410_PA_UART0, SZ_16K),
         [1] = DEFINE_RES_NAMED(IRQ_S3CUART_RX0, \
diff --git a/arch/arm/mach-s3c24xx/include/mach/irqs.h b/arch/arm/mach-s3c24xx/include/mach/irqs.h
index b7a9f4d469e8..1e73f5fa8659 100644
--- a/arch/arm/mach-s3c24xx/include/mach/irqs.h
+++ b/arch/arm/mach-s3c24xx/include/mach/irqs.h
@@ -188,10 +188,8 @@
 
 #if defined(CONFIG_CPU_S3C2416)
 #define NR_IRQS (IRQ_S3C2416_I2S1 + 1)
-#elif defined(CONFIG_CPU_S3C2443)
-#define NR_IRQS (IRQ_S3C2443_AC97+1)
 #else
-#define NR_IRQS (IRQ_S3C2440_AC97+1)
+#define NR_IRQS (IRQ_S3C2443_AC97 + 1)
 #endif
 
 /* compatibility define. */
diff --git a/arch/arm/mach-s3c24xx/irq.c b/arch/arm/mach-s3c24xx/irq.c
index cb9f5e011e73..d8ba9bee4c7e 100644
--- a/arch/arm/mach-s3c24xx/irq.c
+++ b/arch/arm/mach-s3c24xx/irq.c
@@ -500,7 +500,7 @@ struct s3c_irq_intc *s3c24xx_init_intc(struct device_node *np,
                 base = (void *)0xfd000000;
 
                 intc->reg_mask = base + 0xa4;
-                intc->reg_pending = base + 0x08;
+                intc->reg_pending = base + 0xa8;
                 irq_num = 20;
                 irq_start = S3C2410_IRQ(32);
                 irq_offset = 4;
diff --git a/arch/arm/mach-s3c64xx/setup-usb-phy.c b/arch/arm/mach-s3c64xx/setup-usb-phy.c
index c8174d95339b..ca960bda02fd 100644
--- a/arch/arm/mach-s3c64xx/setup-usb-phy.c
+++ b/arch/arm/mach-s3c64xx/setup-usb-phy.c
@@ -76,7 +76,7 @@ static int s3c_usb_otgphy_exit(struct platform_device *pdev)
 
 int s5p_usb_phy_init(struct platform_device *pdev, int type)
 {
-        if (type == S5P_USB_PHY_DEVICE)
+        if (type == USB_PHY_TYPE_DEVICE)
                 return s3c_usb_otgphy_init(pdev);
 
         return -EINVAL;
@@ -84,7 +84,7 @@ int s5p_usb_phy_init(struct platform_device *pdev, int type)
 
 int s5p_usb_phy_exit(struct platform_device *pdev, int type)
 {
-        if (type == S5P_USB_PHY_DEVICE)
+        if (type == USB_PHY_TYPE_DEVICE)
                 return s3c_usb_otgphy_exit(pdev);
 
         return -EINVAL;
diff --git a/arch/arm/mach-s5pv210/clock.c b/arch/arm/mach-s5pv210/clock.c
index fcdf52dbcc49..f051f53e35b7 100644
--- a/arch/arm/mach-s5pv210/clock.c
+++ b/arch/arm/mach-s5pv210/clock.c
@@ -214,11 +214,6 @@ static struct clk clk_pcmcdclk2 = {
         .name           = "pcmcdclk",
 };
 
-static struct clk dummy_apb_pclk = {
-        .name           = "apb_pclk",
-        .id             = -1,
-};
-
 static struct clk *clkset_vpllsrc_list[] = {
         [0] = &clk_fin_vpll,
         [1] = &clk_sclk_hdmi27m,
@@ -305,18 +300,6 @@ static struct clk_ops clk_fout_apll_ops = {
 
 static struct clk init_clocks_off[] = {
         {
-                .name           = "dma",
-                .devname        = "dma-pl330.0",
-                .parent         = &clk_hclk_psys.clk,
-                .enable         = s5pv210_clk_ip0_ctrl,
-                .ctrlbit        = (1 << 3),
-        }, {
-                .name           = "dma",
-                .devname        = "dma-pl330.1",
-                .parent         = &clk_hclk_psys.clk,
-                .enable         = s5pv210_clk_ip0_ctrl,
-                .ctrlbit        = (1 << 4),
-        }, {
                 .name           = "rot",
                 .parent         = &clk_hclk_dsys.clk,
                 .enable         = s5pv210_clk_ip0_ctrl,
@@ -573,6 +556,20 @@ static struct clk clk_hsmmc3 = {
         .ctrlbit        = (1<<19),
 };
 
+static struct clk clk_pdma0 = {
+        .name           = "pdma0",
+        .parent         = &clk_hclk_psys.clk,
+        .enable         = s5pv210_clk_ip0_ctrl,
+        .ctrlbit        = (1 << 3),
+};
+
+static struct clk clk_pdma1 = {
+        .name           = "pdma1",
+        .parent         = &clk_hclk_psys.clk,
+        .enable         = s5pv210_clk_ip0_ctrl,
+        .ctrlbit        = (1 << 4),
+};
+
 static struct clk *clkset_uart_list[] = {
         [6] = &clk_mout_mpll.clk,
         [7] = &clk_mout_epll.clk,
@@ -1075,6 +1072,8 @@ static struct clk *clk_cdev[] = {
         &clk_hsmmc1,
         &clk_hsmmc2,
         &clk_hsmmc3,
+        &clk_pdma0,
+        &clk_pdma1,
 };
 
 /* Clock initialisation code */
@@ -1333,6 +1332,8 @@ static struct clk_lookup s5pv210_clk_lookup[] = {
         CLKDEV_INIT(NULL, "spi_busclk0", &clk_p),
         CLKDEV_INIT("s5pv210-spi.0", "spi_busclk1", &clk_sclk_spi0.clk),
         CLKDEV_INIT("s5pv210-spi.1", "spi_busclk1", &clk_sclk_spi1.clk),
+        CLKDEV_INIT("dma-pl330.0", "apb_pclk", &clk_pdma0),
+        CLKDEV_INIT("dma-pl330.1", "apb_pclk", &clk_pdma1),
 };
 
 void __init s5pv210_register_clocks(void)
@@ -1361,6 +1362,5 @@ void __init s5pv210_register_clocks(void)
         for (ptr = 0; ptr < ARRAY_SIZE(clk_cdev); ptr++)
                 s3c_disable_clocks(clk_cdev[ptr], 1);
 
-        s3c24xx_register_clock(&dummy_apb_pclk);
         s3c_pwmclk_init();
 }
diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c
index 3a38f7b34b94..e373de44a8b6 100644
--- a/arch/arm/mach-s5pv210/mach-goni.c
+++ b/arch/arm/mach-s5pv210/mach-goni.c
@@ -845,7 +845,7 @@ static struct fimc_source_info goni_camera_sensors[] = {
                 .mux_id         = 0,
                 .flags          = V4L2_MBUS_PCLK_SAMPLE_FALLING |
                                   V4L2_MBUS_VSYNC_ACTIVE_LOW,
-                .bus_type       = FIMC_BUS_TYPE_ITU_601,
+                .fimc_bus_type  = FIMC_BUS_TYPE_ITU_601,
                 .board_info     = &noon010pc30_board_info,
                 .i2c_bus_num    = 0,
                 .clk_frequency  = 16000000UL,
diff --git a/arch/arm/mach-s5pv210/setup-usb-phy.c b/arch/arm/mach-s5pv210/setup-usb-phy.c
index 356a0900af03..b2ee5333f89c 100644
--- a/arch/arm/mach-s5pv210/setup-usb-phy.c
+++ b/arch/arm/mach-s5pv210/setup-usb-phy.c
@@ -80,7 +80,7 @@ static int s5pv210_usb_otgphy_exit(struct platform_device *pdev)
 
 int s5p_usb_phy_init(struct platform_device *pdev, int type)
 {
-        if (type == S5P_USB_PHY_DEVICE)
+        if (type == USB_PHY_TYPE_DEVICE)
                 return s5pv210_usb_otgphy_init(pdev);
 
         return -EINVAL;
@@ -88,7 +88,7 @@ int s5p_usb_phy_init(struct platform_device *pdev, int type)
 
 int s5p_usb_phy_exit(struct platform_device *pdev, int type)
 {
-        if (type == S5P_USB_PHY_DEVICE)
+        if (type == USB_PHY_TYPE_DEVICE)
                 return s5pv210_usb_otgphy_exit(pdev);
 
         return -EINVAL;
diff --git a/arch/arm/mach-shark/core.c b/arch/arm/mach-shark/core.c
index b63dec848195..153555724988 100644
--- a/arch/arm/mach-shark/core.c
+++ b/arch/arm/mach-shark/core.c
@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <linux/serial_8250.h>
 #include <linux/io.h>
+#include <linux/cpu.h>
 
 #include <asm/setup.h>
 #include <asm/mach-types.h>
@@ -130,7 +131,7 @@ static void __init shark_timer_init(void)
 
 static void shark_init_early(void)
 {
-        disable_hlt();
+        cpu_idle_poll_ctrl(true);
 }
 
 MACHINE_START(SHARK, "Shark")
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index f2ec0777cfbe..ff8b7ba9b93c 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -169,7 +169,7 @@ static int usbhsf_get_id(struct platform_device *pdev)
         return USBHS_GADGET;
 }
 
-static void usbhsf_power_ctrl(struct platform_device *pdev,
+static int usbhsf_power_ctrl(struct platform_device *pdev,
                               void __iomem *base, int enable)
 {
         struct usbhsf_private *priv = usbhsf_get_priv(pdev);
@@ -223,6 +223,8 @@ static void usbhsf_power_ctrl(struct platform_device *pdev,
                 clk_disable(priv->pci);         /* usb work around */
                 clk_disable(priv->usb24);       /* usb work around */
         }
+
+        return 0;
 }
 
 static int usbhsf_get_vbus(struct platform_device *pdev)
@@ -239,7 +241,7 @@ static irqreturn_t usbhsf_interrupt(int irq, void *data)
         return IRQ_HANDLED;
 }
 
-static void usbhsf_hardware_exit(struct platform_device *pdev)
+static int usbhsf_hardware_exit(struct platform_device *pdev)
 {
         struct usbhsf_private *priv = usbhsf_get_priv(pdev);
 
@@ -264,6 +266,8 @@ static void usbhsf_hardware_exit(struct platform_device *pdev)
         priv->usbh_base = NULL;
 
         free_irq(IRQ7, pdev);
+
+        return 0;
 }
 
 static int usbhsf_hardware_init(struct platform_device *pdev)
diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c
index 7f3a6b7e7b7c..a385f570bbfc 100644
--- a/arch/arm/mach-shmobile/board-kzm9g.c
+++ b/arch/arm/mach-shmobile/board-kzm9g.c
@@ -155,12 +155,14 @@ static int usbhs_get_vbus(struct platform_device *pdev)
         return !((1 << 7) & __raw_readw(priv->cr2));
 }
 
-static void usbhs_phy_reset(struct platform_device *pdev)
+static int usbhs_phy_reset(struct platform_device *pdev)
 {
         struct usbhs_private *priv = usbhs_get_priv(pdev);
 
         /* init phy */
         __raw_writew(0x8a0a, priv->cr2);
+
+        return 0;
 }
 
 static int usbhs_get_id(struct platform_device *pdev)
@@ -202,7 +204,7 @@ static int usbhs_hardware_init(struct platform_device *pdev)
         return 0;
 }
 
-static void usbhs_hardware_exit(struct platform_device *pdev)
+static int usbhs_hardware_exit(struct platform_device *pdev)
 {
         struct usbhs_private *priv = usbhs_get_priv(pdev);
 
@@ -210,6 +212,8 @@ static void usbhs_hardware_exit(struct platform_device *pdev)
         __raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->phy);
 
         free_irq(IRQ15, pdev);
+
+        return 0;
 }
 
 static u32 usbhs_pipe_cfg[] = {
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index db968a585ff0..979237c18dad 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -596,12 +596,14 @@ static int usbhs_get_vbus(struct platform_device *pdev)
         return usbhs_is_connected(usbhs_get_priv(pdev));
 }
 
-static void usbhs_phy_reset(struct platform_device *pdev)
+static int usbhs_phy_reset(struct platform_device *pdev)
 {
         struct usbhs_private *priv = usbhs_get_priv(pdev);
 
         /* init phy */
         __raw_writew(0x8a0a, priv->usbcrcaddr);
+
+        return 0;
 }
 
 static int usbhs0_get_id(struct platform_device *pdev)
@@ -628,11 +630,13 @@ static int usbhs0_hardware_init(struct platform_device *pdev)
         return 0;
 }
 
-static void usbhs0_hardware_exit(struct platform_device *pdev)
+static int usbhs0_hardware_exit(struct platform_device *pdev)
 {
         struct usbhs_private *priv = usbhs_get_priv(pdev);
 
         cancel_delayed_work_sync(&priv->work);
+
+        return 0;
 }
 
 static struct usbhs_private usbhs0_private = {
@@ -735,7 +739,7 @@ static int usbhs1_hardware_init(struct platform_device *pdev)
         return 0;
 }
 
-static void usbhs1_hardware_exit(struct platform_device *pdev)
+static int usbhs1_hardware_exit(struct platform_device *pdev)
 {
         struct usbhs_private *priv = usbhs_get_priv(pdev);
 
@@ -743,6 +747,8 @@ static void usbhs1_hardware_exit(struct platform_device *pdev)
         __raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->usbphyaddr);
 
         free_irq(IRQ8, pdev);
+
+        return 0;
 }
 
 static int usbhs1_get_id(struct platform_device *pdev)
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index cdcb799e802f..fec49ebc359a 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -32,6 +32,7 @@
 #include <linux/smsc911x.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/sh_hspi.h>
+#include <linux/mmc/host.h>
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <linux/mfd/tmio.h>
 #include <linux/usb/otg.h>
diff --git a/arch/arm/mach-shmobile/suspend.c b/arch/arm/mach-shmobile/suspend.c
index 47d83f7a70b6..5d92b5dd486b 100644
--- a/arch/arm/mach-shmobile/suspend.c
+++ b/arch/arm/mach-shmobile/suspend.c
@@ -12,6 +12,8 @@
 #include <linux/suspend.h>
 #include <linux/module.h>
 #include <linux/err.h>
+#include <linux/cpu.h>
+
 #include <asm/io.h>
 #include <asm/system_misc.h>
 
@@ -23,13 +25,13 @@ static int shmobile_suspend_default_enter(suspend_state_t suspend_state)
 
 static int shmobile_suspend_begin(suspend_state_t state)
 {
-        disable_hlt();
+        cpu_idle_poll_ctrl(true);
         return 0;
 }
 
 static void shmobile_suspend_end(void)
 {
-        enable_hlt();
+        cpu_idle_poll_ctrl(false);
 }
 
 struct platform_suspend_ops shmobile_suspend_ops = {
diff --git a/arch/arm/mach-spear3xx/spear3xx.c b/arch/arm/mach-spear3xx/spear3xx.c
index f9d754f90c59..d2b3937c4014 100644
--- a/arch/arm/mach-spear3xx/spear3xx.c
+++ b/arch/arm/mach-spear3xx/spear3xx.c
@@ -14,7 +14,7 @@
 #define pr_fmt(fmt) "SPEAr3xx: " fmt
 
 #include <linux/amba/pl022.h>
-#include <linux/amba/pl08x.h>
+#include <linux/amba/pl080.h>
 #include <linux/io.h>
 #include <plat/pl080.h>
 #include <mach/generic.h>
diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index d1c4893894ce..dbc653ea851c 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -18,8 +18,8 @@ config ARCH_TEGRA_2x_SOC
         select PL310_ERRATA_727915 if CACHE_L2X0
         select PL310_ERRATA_769419 if CACHE_L2X0
         select USB_ARCH_HAS_EHCI if USB_SUPPORT
-        select USB_ULPI if USB
-        select USB_ULPI_VIEWPORT if USB_SUPPORT
+        select USB_ULPI if USB_PHY
+        select USB_ULPI_VIEWPORT if USB_PHY
         help
           Support for NVIDIA Tegra AP20 and T20 processors, based on the
           ARM CortexA9MP CPU and the ARM PL310 L2 cache controller
@@ -37,8 +37,8 @@ config ARCH_TEGRA_3x_SOC
         select PINCTRL_TEGRA30
         select PL310_ERRATA_769419 if CACHE_L2X0
         select USB_ARCH_HAS_EHCI if USB_SUPPORT
-        select USB_ULPI if USB
-        select USB_ULPI_VIEWPORT if USB_SUPPORT
+        select USB_ULPI if USB_PHY
+        select USB_ULPI_VIEWPORT if USB_PHY
         help
           Support for NVIDIA Tegra T30 processor family, based on the
           ARM CortexA9MP CPU and the ARM PL310 L2 cache controller
diff --git a/arch/arm/mach-ux500/board-mop500-regulators.c b/arch/arm/mach-ux500/board-mop500-regulators.c
index 2a17bc506cff..ff3c9f016591 100644
--- a/arch/arm/mach-ux500/board-mop500-regulators.c
+++ b/arch/arm/mach-ux500/board-mop500-regulators.c
@@ -5,6 +5,7 @@
  *
  * Authors: Sundar Iyer <sundar.iyer@stericsson.com>
  *          Bengt Jonsson <bengt.g.jonsson@stericsson.com>
+ *          Daniel Willerud <daniel.willerud@stericsson.com>
  *
  * MOP500 board specific initialization for regulators
  */
@@ -12,6 +13,7 @@
 #include <linux/regulator/machine.h>
 #include <linux/regulator/ab8500.h>
 #include "board-mop500-regulators.h"
+#include "id.h"
 
 static struct regulator_consumer_supply gpio_en_3v3_consumers[] = {
        REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
@@ -53,21 +55,37 @@ struct regulator_init_data tps61052_regulator = {
 };
 
 static struct regulator_consumer_supply ab8500_vaux1_consumers[] = {
-        /* External displays, connector on board 2v5 power supply */
-        REGULATOR_SUPPLY("vaux12v5", "mcde.0"),
+        /* Main display, u8500 R3 uib */
+        REGULATOR_SUPPLY("vddi", "mcde_disp_sony_acx424akp.0"),
+        /* Main display, u8500 uib and ST uib */
+        REGULATOR_SUPPLY("vdd1", "samsung_s6d16d0.0"),
+        /* Secondary display, ST uib */
+        REGULATOR_SUPPLY("vdd1", "samsung_s6d16d0.1"),
         /* SFH7741 proximity sensor */
         REGULATOR_SUPPLY("vcc", "gpio-keys.0"),
         /* BH1780GLS ambient light sensor */
         REGULATOR_SUPPLY("vcc", "2-0029"),
         /* lsm303dlh accelerometer */
-        REGULATOR_SUPPLY("vdd", "3-0018"),
+        REGULATOR_SUPPLY("vdd", "2-0018"),
+        /* lsm303dlhc accelerometer */
+        REGULATOR_SUPPLY("vdd", "2-0019"),
         /* lsm303dlh magnetometer */
-        REGULATOR_SUPPLY("vdd", "3-001e"),
+        REGULATOR_SUPPLY("vdd", "2-001e"),
         /* Rohm BU21013 Touchscreen devices */
         REGULATOR_SUPPLY("avdd", "3-005c"),
         REGULATOR_SUPPLY("avdd", "3-005d"),
         /* Synaptics RMI4 Touchscreen device */
         REGULATOR_SUPPLY("vdd", "3-004b"),
+        /* L3G4200D Gyroscope device */
+        REGULATOR_SUPPLY("vdd", "2-0068"),
+        /* Ambient light sensor device */
+        REGULATOR_SUPPLY("vdd", "3-0029"),
+        /* Pressure sensor device */
+        REGULATOR_SUPPLY("vdd", "2-005c"),
+        /* Cypress TrueTouch Touchscreen device */
+        REGULATOR_SUPPLY("vcpin", "spi8.0"),
+        /* Camera device */
+        REGULATOR_SUPPLY("vaux12v5", "mmio_camera"),
 };
 
 static struct regulator_consumer_supply ab8500_vaux2_consumers[] = {
@@ -75,18 +93,50 @@ static struct regulator_consumer_supply ab8500_vaux2_consumers[] = {
         REGULATOR_SUPPLY("vmmc", "sdi4"),
         /* AB8500 audio codec */
         REGULATOR_SUPPLY("vcc-N2158", "ab8500-codec.0"),
+        /* AB8500 accessory detect 1 */
+        REGULATOR_SUPPLY("vcc-N2158", "ab8500-acc-det.0"),
+        /* AB8500 Tv-out device */
+        REGULATOR_SUPPLY("vcc-N2158", "mcde_tv_ab8500.4"),
+        /* AV8100 HDMI device */
+        REGULATOR_SUPPLY("vcc-N2158", "av8100_hdmi.3"),
 };
 
 static struct regulator_consumer_supply ab8500_vaux3_consumers[] = {
+        REGULATOR_SUPPLY("v-SD-STM", "stm"),
         /* External MMC slot power */
         REGULATOR_SUPPLY("vmmc", "sdi0"),
 };
 
+static struct regulator_consumer_supply ab8505_vaux4_consumers[] = {
+};
+
+static struct regulator_consumer_supply ab8505_vaux5_consumers[] = {
+};
+
+static struct regulator_consumer_supply ab8505_vaux6_consumers[] = {
+};
+
+static struct regulator_consumer_supply ab8505_vaux8_consumers[] = {
+        /* AB8500 audio codec device */
+        REGULATOR_SUPPLY("v-aux8", NULL),
+};
+
+static struct regulator_consumer_supply ab8505_vadc_consumers[] = {
+        /* Internal general-purpose ADC */
+        REGULATOR_SUPPLY("vddadc", "ab8500-gpadc.0"),
+        /* ADC for charger */
+        REGULATOR_SUPPLY("vddadc", "ab8500-charger.0"),
+};
+
 static struct regulator_consumer_supply ab8500_vtvout_consumers[] = {
         /* TV-out DENC supply */
         REGULATOR_SUPPLY("vtvout", "ab8500-denc.0"),
         /* Internal general-purpose ADC */
         REGULATOR_SUPPLY("vddadc", "ab8500-gpadc.0"),
+        /* ADC for charger */
+        REGULATOR_SUPPLY("vddadc", "ab8500-charger.0"),
+        /* AB8500 Tv-out device */
+        REGULATOR_SUPPLY("vtvout", "mcde_tv_ab8500.4"),
 };
 
 static struct regulator_consumer_supply ab8500_vaud_consumers[] = {
@@ -114,77 +164,90 @@ static struct regulator_consumer_supply ab8500_vintcore_consumers[] = {
         REGULATOR_SUPPLY("v-intcore", NULL),
         /* USB Transceiver */
         REGULATOR_SUPPLY("vddulpivio18", "ab8500-usb.0"),
+        /* Handled by abx500 clk driver */
+        REGULATOR_SUPPLY("v-intcore", "abx500-clk.0"),
+};
+
+static struct regulator_consumer_supply ab8505_usb_consumers[] = {
+        /* HS USB OTG physical interface */
+        REGULATOR_SUPPLY("v-ape", NULL),
 };
 
 static struct regulator_consumer_supply ab8500_vana_consumers[] = {
-        /* External displays, connector on board, 1v8 power supply */
-        REGULATOR_SUPPLY("vsmps2", "mcde.0"),
+        /* DB8500 DSI */
+        REGULATOR_SUPPLY("vdddsi1v2", "mcde"),
+        REGULATOR_SUPPLY("vdddsi1v2", "b2r2_core"),
+        REGULATOR_SUPPLY("vdddsi1v2", "b2r2_1_core"),
+        REGULATOR_SUPPLY("vdddsi1v2", "dsilink.0"),
+        REGULATOR_SUPPLY("vdddsi1v2", "dsilink.1"),
+        REGULATOR_SUPPLY("vdddsi1v2", "dsilink.2"),
+        /* DB8500 CSI */
+        REGULATOR_SUPPLY("vddcsi1v2", "mmio_camera"),
 };
 
 /* ab8500 regulator register initialization */
-struct ab8500_regulator_reg_init
-ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = {
+static struct ab8500_regulator_reg_init ab8500_reg_init[] = {
         /*
          * VanaRequestCtrl          = HP/LP depending on VxRequest
          * VextSupply1RequestCtrl   = HP/LP depending on VxRequest
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL2, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL2,       0xf0, 0x00),
         /*
          * VextSupply2RequestCtrl   = HP/LP depending on VxRequest
          * VextSupply3RequestCtrl   = HP/LP depending on VxRequest
          * Vaux1RequestCtrl         = HP/LP depending on VxRequest
          * Vaux2RequestCtrl         = HP/LP depending on VxRequest
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL3, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL3,       0xff, 0x00),
         /*
          * Vaux3RequestCtrl         = HP/LP depending on VxRequest
          * SwHPReq                  = Control through SWValid disabled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL4, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL4,       0x07, 0x00),
         /*
          * VanaSysClkReq1HPValid    = disabled
          * Vaux1SysClkReq1HPValid   = disabled
          * Vaux2SysClkReq1HPValid   = disabled
          * Vaux3SysClkReq1HPValid   = disabled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID1, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID1, 0xe8, 0x00),
         /*
          * VextSupply1SysClkReq1HPValid = disabled
          * VextSupply2SysClkReq1HPValid = disabled
          * VextSupply3SysClkReq1HPValid = SysClkReq1 controlled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID2, 0x40),
+        INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID2, 0x70, 0x40),
         /*
          * VanaHwHPReq1Valid        = disabled
          * Vaux1HwHPreq1Valid       = disabled
          * Vaux2HwHPReq1Valid       = disabled
          * Vaux3HwHPReqValid        = disabled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID1, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID1,     0xe8, 0x00),
         /*
          * VextSupply1HwHPReq1Valid = disabled
          * VextSupply2HwHPReq1Valid = disabled
          * VextSupply3HwHPReq1Valid = disabled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID2, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID2,     0x07, 0x00),
         /*
          * VanaHwHPReq2Valid        = disabled
          * Vaux1HwHPReq2Valid       = disabled
          * Vaux2HwHPReq2Valid       = disabled
          * Vaux3HwHPReq2Valid       = disabled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID1, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID1,     0xe8, 0x00),
         /*
          * VextSupply1HwHPReq2Valid = disabled
          * VextSupply2HwHPReq2Valid = disabled
          * VextSupply3HwHPReq2Valid = HWReq2 controlled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID2, 0x04),
+        INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID2,     0x07, 0x04),
         /*
          * VanaSwHPReqValid         = disabled
          * Vaux1SwHPReqValid        = disabled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID1, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID1,      0xa0, 0x00),
         /*
          * Vaux2SwHPReqValid        = disabled
          * Vaux3SwHPReqValid        = disabled
@@ -192,7 +255,7 @@ ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = {
          * VextSupply2SwHPReqValid  = disabled
          * VextSupply3SwHPReqValid  = disabled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID2, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID2,      0x1f, 0x00),
         /*
          * SysClkReq2Valid1         = SysClkReq2 controlled
          * SysClkReq3Valid1         = disabled
@@ -202,7 +265,7 @@ ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = {
          * SysClkReq7Valid1         = disabled
          * SysClkReq8Valid1         = disabled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID1, 0x2a),
+        INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID1,    0xfe, 0x2a),
         /*
          * SysClkReq2Valid2         = disabled
          * SysClkReq3Valid2         = disabled
@@ -212,7 +275,7 @@ ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = {
          * SysClkReq7Valid2         = disabled
          * SysClkReq8Valid2         = disabled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID2, 0x20),
+        INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID2,    0xfe, 0x20),
         /*
          * VTVoutEna                = disabled
          * Vintcore12Ena            = disabled
@@ -220,66 +283,62 @@ ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = {
          * Vintcore12LP             = inactive (HP)
          * VTVoutLP                 = inactive (HP)
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUMISC1, 0x10),
+        INIT_REGULATOR_REGISTER(AB8500_REGUMISC1,              0xfe, 0x10),
         /*
          * VaudioEna                = disabled
          * VdmicEna                 = disabled
          * Vamic1Ena                = disabled
          * Vamic2Ena                = disabled
          */
-        INIT_REGULATOR_REGISTER(AB8500_VAUDIOSUPPLY, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_VAUDIOSUPPLY,           0x1e, 0x00),
         /*
          * Vamic1_dzout             = high-Z when Vamic1 is disabled
          * Vamic2_dzout             = high-Z when Vamic2 is disabled
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUCTRL1VAMIC, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUCTRL1VAMIC,         0x03, 0x00),
         /*
-         * VPll                     = Hw controlled
+         * VPll                     = Hw controlled (NOTE! PRCMU bits)
          * VanaRegu                 = force off
          */
-        INIT_REGULATOR_REGISTER(AB8500_VPLLVANAREGU, 0x02),
+        INIT_REGULATOR_REGISTER(AB8500_VPLLVANAREGU,           0x0f, 0x02),
         /*
          * VrefDDREna               = disabled
          * VrefDDRSleepMode         = inactive (no pulldown)
          */
-        INIT_REGULATOR_REGISTER(AB8500_VREFDDR, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_VREFDDR,                0x03, 0x00),
         /*
-         * VextSupply1Regu          = HW control
-         * VextSupply2Regu          = HW control
-         * VextSupply3Regu          = HW control
+         * VextSupply1Regu          = force LP
+         * VextSupply2Regu          = force OFF
+         * VextSupply3Regu          = force HP (-> STBB2=LP and TPS=LP)
          * ExtSupply2Bypass         = ExtSupply12LPn ball is 0 when Ena is 0
          * ExtSupply3Bypass         = ExtSupply3LPn ball is 0 when Ena is 0
          */
-        INIT_REGULATOR_REGISTER(AB8500_EXTSUPPLYREGU, 0x2a),
+        INIT_REGULATOR_REGISTER(AB8500_EXTSUPPLYREGU,          0xff, 0x13),
         /*
          * Vaux1Regu                = force HP
          * Vaux2Regu                = force off
          */
-        INIT_REGULATOR_REGISTER(AB8500_VAUX12REGU, 0x01),
+        INIT_REGULATOR_REGISTER(AB8500_VAUX12REGU,             0x0f, 0x01),
         /*
-         * Vaux3regu                = force off
+         * Vaux3Regu                = force off
          */
-        INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3REGU, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3REGU,          0x03, 0x00),
         /*
-         * Vsmps1                   = 1.15V
+         * Vaux1Sel                 = 2.8 V
          */
-        INIT_REGULATOR_REGISTER(AB8500_VSMPS1SEL1, 0x24),
-        /*
-         * Vaux1Sel                 = 2.5 V
-         */
-        INIT_REGULATOR_REGISTER(AB8500_VAUX1SEL, 0x08),
+        INIT_REGULATOR_REGISTER(AB8500_VAUX1SEL,               0x0f, 0x0C),
         /*
          * Vaux2Sel                 = 2.9 V
          */
-        INIT_REGULATOR_REGISTER(AB8500_VAUX2SEL, 0x0d),
+        INIT_REGULATOR_REGISTER(AB8500_VAUX2SEL,               0x0f, 0x0d),
         /*
          * Vaux3Sel                 = 2.91 V
          */
-        INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3SEL, 0x07),
+        INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3SEL,           0x07, 0x07),
         /*
          * VextSupply12LP           = disabled (no LP)
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUCTRL2SPARE, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUCTRL2SPARE,         0x01, 0x00),
         /*
          * Vaux1Disch               = short discharge time
          * Vaux2Disch               = short discharge time
@@ -288,33 +347,26 @@ ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = {
          * VTVoutDisch              = short discharge time
          * VaudioDisch              = short discharge time
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH,          0xfc, 0x00),
         /*
          * VanaDisch                = short discharge time
          * VdmicPullDownEna         = pulldown disabled when Vdmic is disabled
          * VdmicDisch               = short discharge time
          */
-        INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH2, 0x00),
+        INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH2,         0x16, 0x00),
 };
 
 /* AB8500 regulators */
-struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = {
+static struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = {
         /* supplies to the display/camera */
         [AB8500_LDO_AUX1] = {
                 .constraints = {
                         .name = "V-DISPLAY",
-                        .min_uV = 2500000,
-                        .max_uV = 2900000,
+                        .min_uV = 2800000,
+                        .max_uV = 3300000,
                         .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
                                           REGULATOR_CHANGE_STATUS,
                         .boot_on = 1, /* display is on at boot */
-                        /*
-                         * This voltage cannot be disabled right now because
-                         * it is somehow affecting the external MMC
-                         * functionality, though that typically will use
-                         * AUX3.
-                         */
-                        .always_on = 1,
                 },
                 .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux1_consumers),
                 .consumer_supplies = ab8500_vaux1_consumers,
@@ -326,7 +378,10 @@ struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = {
                         .min_uV = 1100000,
                         .max_uV = 3300000,
                         .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-                                          REGULATOR_CHANGE_STATUS,
+                                          REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
                 },
                 .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux2_consumers),
                 .consumer_supplies = ab8500_vaux2_consumers,
@@ -338,7 +393,10 @@ struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = {
                         .min_uV = 1100000,
                         .max_uV = 3300000,
                         .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-                                          REGULATOR_CHANGE_STATUS,
+                                          REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
                 },
                 .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux3_consumers),
                 .consumer_supplies = ab8500_vaux3_consumers,
@@ -392,18 +450,614 @@ struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = {
         [AB8500_LDO_INTCORE] = {
                 .constraints = {
                         .name = "V-INTCORE",
-                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                        .min_uV = 1250000,
+                        .max_uV = 1350000,
+                        .input_uV = 1800000,
+                        .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+                                          REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE |
+                                          REGULATOR_CHANGE_DRMS,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
                 },
                 .num_consumer_supplies = ARRAY_SIZE(ab8500_vintcore_consumers),
                 .consumer_supplies = ab8500_vintcore_consumers,
         },
-        /* supply for U8500 CSI/DSI, VANA LDO */
+        /* supply for U8500 CSI-DSI, VANA LDO */
         [AB8500_LDO_ANA] = {
                 .constraints = {
-                        .name = "V-CSI/DSI",
+                        .name = "V-CSI-DSI",
                         .valid_ops_mask = REGULATOR_CHANGE_STATUS,
                 },
                 .num_consumer_supplies = ARRAY_SIZE(ab8500_vana_consumers),
                 .consumer_supplies = ab8500_vana_consumers,
         },
 };
+
+/* supply for VextSupply3 */
+static struct regulator_consumer_supply ab8500_ext_supply3_consumers[] = {
+        /* SIM supply for 3 V SIM cards */
+        REGULATOR_SUPPLY("vinvsim", "sim-detect.0"),
+};
+
+/* extended configuration for VextSupply2, only used for HREFP_V20 boards */
+static struct ab8500_ext_regulator_cfg ab8500_ext_supply2 = {
+        .hwreq = true,
+};
+
+/*
+ * AB8500 external regulators
+ */
+static struct regulator_init_data ab8500_ext_regulators[] = {
+        /* fixed Vbat supplies VSMPS1_EXT_1V8 */
+        [AB8500_EXT_SUPPLY1] = {
+                .constraints = {
+                        .name = "ab8500-ext-supply1",
+                        .min_uV = 1800000,
+                        .max_uV = 1800000,
+                        .initial_mode = REGULATOR_MODE_IDLE,
+                        .boot_on = 1,
+                        .always_on = 1,
+                },
+        },
+        /* fixed Vbat supplies VSMPS2_EXT_1V36 and VSMPS5_EXT_1V15 */
+        [AB8500_EXT_SUPPLY2] = {
+                .constraints = {
+                        .name = "ab8500-ext-supply2",
+                        .min_uV = 1360000,
+                        .max_uV = 1360000,
+                },
+        },
+        /* fixed Vbat supplies VSMPS3_EXT_3V4 and VSMPS4_EXT_3V4 */
+        [AB8500_EXT_SUPPLY3] = {
+                .constraints = {
+                        .name = "ab8500-ext-supply3",
+                        .min_uV = 3400000,
+                        .max_uV = 3400000,
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                        .boot_on = 1,
+                },
+                .num_consumer_supplies =
+                        ARRAY_SIZE(ab8500_ext_supply3_consumers),
+                .consumer_supplies = ab8500_ext_supply3_consumers,
+        },
+};
+
+/* ab8505 regulator register initialization */
+static struct ab8500_regulator_reg_init ab8505_reg_init[] = {
+        /*
+         * VarmRequestCtrl
+         * VsmpsCRequestCtrl
+         * VsmpsARequestCtrl
+         * VsmpsBRequestCtrl
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL1,       0x00, 0x00),
+        /*
+         * VsafeRequestCtrl
+         * VpllRequestCtrl
+         * VanaRequestCtrl          = HP/LP depending on VxRequest
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL2,       0x30, 0x00),
+        /*
+         * Vaux1RequestCtrl         = HP/LP depending on VxRequest
+         * Vaux2RequestCtrl         = HP/LP depending on VxRequest
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL3,       0xf0, 0x00),
+        /*
+         * Vaux3RequestCtrl         = HP/LP depending on VxRequest
+         * SwHPReq                  = Control through SWValid disabled
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL4,       0x07, 0x00),
+        /*
+         * VsmpsASysClkReq1HPValid
+         * VsmpsBSysClkReq1HPValid
+         * VsafeSysClkReq1HPValid
+         * VanaSysClkReq1HPValid    = disabled
+         * VpllSysClkReq1HPValid
+         * Vaux1SysClkReq1HPValid   = disabled
+         * Vaux2SysClkReq1HPValid   = disabled
+         * Vaux3SysClkReq1HPValid   = disabled
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQ1HPVALID1, 0xe8, 0x00),
+        /*
+         * VsmpsCSysClkReq1HPValid
+         * VarmSysClkReq1HPValid
+         * VbbSysClkReq1HPValid
+         * VsmpsMSysClkReq1HPValid
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQ1HPVALID2, 0x00, 0x00),
+        /*
+         * VsmpsAHwHPReq1Valid
+         * VsmpsBHwHPReq1Valid
+         * VsafeHwHPReq1Valid
+         * VanaHwHPReq1Valid        = disabled
+         * VpllHwHPReq1Valid
+         * Vaux1HwHPreq1Valid       = disabled
+         * Vaux2HwHPReq1Valid       = disabled
+         * Vaux3HwHPReqValid        = disabled
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ1VALID1,     0xe8, 0x00),
+        /*
+         * VsmpsMHwHPReq1Valid
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ1VALID2,     0x00, 0x00),
+        /*
+         * VsmpsAHwHPReq2Valid
+         * VsmpsBHwHPReq2Valid
+         * VsafeHwHPReq2Valid
+         * VanaHwHPReq2Valid        = disabled
+         * VpllHwHPReq2Valid
+         * Vaux1HwHPReq2Valid       = disabled
+         * Vaux2HwHPReq2Valid       = disabled
+         * Vaux3HwHPReq2Valid       = disabled
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ2VALID1,     0xe8, 0x00),
+        /*
+         * VsmpsMHwHPReq2Valid
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ2VALID2,     0x00, 0x00),
+        /**
+         * VsmpsCSwHPReqValid
+         * VarmSwHPReqValid
+         * VsmpsASwHPReqValid
+         * VsmpsBSwHPReqValid
+         * VsafeSwHPReqValid
+         * VanaSwHPReqValid
+         * VanaSwHPReqValid         = disabled
+         * VpllSwHPReqValid
+         * Vaux1SwHPReqValid        = disabled
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUSWHPREQVALID1,      0xa0, 0x00),
+        /*
+         * Vaux2SwHPReqValid        = disabled
+         * Vaux3SwHPReqValid        = disabled
+         * VsmpsMSwHPReqValid
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUSWHPREQVALID2,      0x03, 0x00),
+        /*
+         * SysClkReq2Valid1         = SysClkReq2 controlled
+         * SysClkReq3Valid1         = disabled
+         * SysClkReq4Valid1         = SysClkReq4 controlled
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQVALID1,    0x0e, 0x0a),
+        /*
+         * SysClkReq2Valid2         = disabled
+         * SysClkReq3Valid2         = disabled
+         * SysClkReq4Valid2         = disabled
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQVALID2,    0x0e, 0x00),
+        /*
+         * Vaux4SwHPReqValid
+         * Vaux4HwHPReq2Valid
+         * Vaux4HwHPReq1Valid
+         * Vaux4SysClkReq1HPValid
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUVAUX4REQVALID,    0x00, 0x00),
+        /*
+         * VadcEna                  = disabled
+         * VintCore12Ena            = disabled
+         * VintCore12Sel            = 1.25 V
+         * VintCore12LP             = inactive (HP)
+         * VadcLP                   = inactive (HP)
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUMISC1,              0xfe, 0x10),
+        /*
+         * VaudioEna                = disabled
+         * Vaux8Ena                 = disabled
+         * Vamic1Ena                = disabled
+         * Vamic2Ena                = disabled
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VAUDIOSUPPLY,           0x1e, 0x00),
+        /*
+         * Vamic1_dzout             = high-Z when Vamic1 is disabled
+         * Vamic2_dzout             = high-Z when Vamic2 is disabled
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUCTRL1VAMIC,         0x03, 0x00),
+        /*
+         * VsmpsARegu
+         * VsmpsASelCtrl
+         * VsmpsAAutoMode
+         * VsmpsAPWMMode
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSMPSAREGU,    0x00, 0x00),
+        /*
+         * VsmpsBRegu
+         * VsmpsBSelCtrl
+         * VsmpsBAutoMode
+         * VsmpsBPWMMode
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSMPSBREGU,    0x00, 0x00),
+        /*
+         * VsafeRegu
+         * VsafeSelCtrl
+         * VsafeAutoMode
+         * VsafePWMMode
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSAFEREGU,    0x00, 0x00),
+        /*
+         * VPll                     = Hw controlled (NOTE! PRCMU bits)
+         * VanaRegu                 = force off
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VPLLVANAREGU,           0x0f, 0x02),
+        /*
+         * VextSupply1Regu          = force OFF (OTP_ExtSupply12LPnPolarity 1)
+         * VextSupply2Regu          = force OFF (OTP_ExtSupply12LPnPolarity 1)
+         * VextSupply3Regu          = force OFF (OTP_ExtSupply3LPnPolarity 0)
+         * ExtSupply2Bypass         = ExtSupply12LPn ball is 0 when Ena is 0
+         * ExtSupply3Bypass         = ExtSupply3LPn ball is 0 when Ena is 0
+         */
+        INIT_REGULATOR_REGISTER(AB8505_EXTSUPPLYREGU,          0xff, 0x30),
+        /*
+         * Vaux1Regu                = force HP
+         * Vaux2Regu                = force off
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VAUX12REGU,             0x0f, 0x01),
+        /*
+         * Vaux3Regu                = force off
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VRF1VAUX3REGU,          0x03, 0x00),
+        /*
+         * VsmpsASel1
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSMPSASEL1,    0x00, 0x00),
+        /*
+         * VsmpsASel2
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSMPSASEL2,    0x00, 0x00),
+        /*
+         * VsmpsASel3
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSMPSASEL3,    0x00, 0x00),
+        /*
+         * VsmpsBSel1
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSMPSBSEL1,    0x00, 0x00),
+        /*
+         * VsmpsBSel2
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSMPSBSEL2,    0x00, 0x00),
+        /*
+         * VsmpsBSel3
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSMPSBSEL3,    0x00, 0x00),
+        /*
+         * VsafeSel1
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSAFESEL1,    0x00, 0x00),
+        /*
+         * VsafeSel2
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSAFESEL2,    0x00, 0x00),
+        /*
+         * VsafeSel3
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VSAFESEL3,    0x00, 0x00),
+        /*
+         * Vaux1Sel                 = 2.8 V
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VAUX1SEL,               0x0f, 0x0C),
+        /*
+         * Vaux2Sel                 = 2.9 V
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VAUX2SEL,               0x0f, 0x0d),
+        /*
+         * Vaux3Sel                 = 2.91 V
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VRF1VAUX3SEL,           0x07, 0x07),
+        /*
+         * Vaux4RequestCtrl
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VAUX4REQCTRL,    0x00, 0x00),
+        /*
+         * Vaux4Regu
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VAUX4REGU,    0x00, 0x00),
+        /*
+         * Vaux4Sel
+         */
+        INIT_REGULATOR_REGISTER(AB8505_VAUX4SEL,    0x00, 0x00),
+        /*
+         * Vaux1Disch               = short discharge time
+         * Vaux2Disch               = short discharge time
+         * Vaux3Disch               = short discharge time
+         * Vintcore12Disch          = short discharge time
+         * VTVoutDisch              = short discharge time
+         * VaudioDisch              = short discharge time
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUCTRLDISCH,          0xfc, 0x00),
+        /*
+         * VanaDisch                = short discharge time
+         * Vaux8PullDownEna         = pulldown disabled when Vaux8 is disabled
+         * Vaux8Disch               = short discharge time
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUCTRLDISCH2,         0x16, 0x00),
+        /*
+         * Vaux4Disch               = short discharge time
+         */
+        INIT_REGULATOR_REGISTER(AB8505_REGUCTRLDISCH3,         0x01, 0x00),
+        /*
+         * Vaux5Sel
+         * Vaux5LP
+         * Vaux5Ena
+         * Vaux5Disch
+         * Vaux5DisSfst
+         * Vaux5DisPulld
+         */
+        INIT_REGULATOR_REGISTER(AB8505_CTRLVAUX5,              0x00, 0x00),
+        /*
+         * Vaux6Sel
+         * Vaux6LP
+         * Vaux6Ena
+         * Vaux6DisPulld
+         */
+        INIT_REGULATOR_REGISTER(AB8505_CTRLVAUX6,              0x00, 0x00),
+};
+
+struct regulator_init_data ab8505_regulators[AB8505_NUM_REGULATORS] = {
+        /* supplies to the display/camera */
+        [AB8505_LDO_AUX1] = {
+                .constraints = {
+                        .name = "V-DISPLAY",
+                        .min_uV = 2800000,
+                        .max_uV = 3300000,
+                        .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+                                          REGULATOR_CHANGE_STATUS,
+                        .boot_on = 1, /* display is on at boot */
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux1_consumers),
+                .consumer_supplies = ab8500_vaux1_consumers,
+        },
+        /* supplies to the on-board eMMC */
+        [AB8505_LDO_AUX2] = {
+                .constraints = {
+                        .name = "V-eMMC1",
+                        .min_uV = 1100000,
+                        .max_uV = 3300000,
+                        .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+                                          REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux2_consumers),
+                .consumer_supplies = ab8500_vaux2_consumers,
+        },
+        /* supply for VAUX3, supplies to SDcard slots */
+        [AB8505_LDO_AUX3] = {
+                .constraints = {
+                        .name = "V-MMC-SD",
+                        .min_uV = 1100000,
+                        .max_uV = 3300000,
+                        .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+                                          REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux3_consumers),
+                .consumer_supplies = ab8500_vaux3_consumers,
+        },
+        /* supply for VAUX4, supplies to NFC and standalone secure element */
+        [AB8505_LDO_AUX4] = {
+                .constraints = {
+                        .name = "V-NFC-SE",
+                        .min_uV = 1100000,
+                        .max_uV = 3300000,
+                        .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+                                          REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8505_vaux4_consumers),
+                .consumer_supplies = ab8505_vaux4_consumers,
+        },
+        /* supply for VAUX5, supplies to TBD */
+        [AB8505_LDO_AUX5] = {
+                .constraints = {
+                        .name = "V-AUX5",
+                        .min_uV = 1050000,
+                        .max_uV = 2790000,
+                        .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+                                          REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8505_vaux5_consumers),
+                .consumer_supplies = ab8505_vaux5_consumers,
+        },
+        /* supply for VAUX6, supplies to TBD */
+        [AB8505_LDO_AUX6] = {
+                .constraints = {
+                        .name = "V-AUX6",
+                        .min_uV = 1050000,
+                        .max_uV = 2790000,
+                        .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+                                          REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8505_vaux6_consumers),
+                .consumer_supplies = ab8505_vaux6_consumers,
+        },
+        /* supply for gpadc, ADC LDO */
+        [AB8505_LDO_ADC] = {
+                .constraints = {
+                        .name = "V-ADC",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8505_vadc_consumers),
+                .consumer_supplies = ab8505_vadc_consumers,
+        },
+        /* supply for ab8500-vaudio, VAUDIO LDO */
+        [AB8505_LDO_AUDIO] = {
+                .constraints = {
+                        .name = "V-AUD",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8500_vaud_consumers),
+                .consumer_supplies = ab8500_vaud_consumers,
+        },
+        /* supply for v-anamic1 VAMic1-LDO */
+        [AB8505_LDO_ANAMIC1] = {
+                .constraints = {
+                        .name = "V-AMIC1",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8500_vamic1_consumers),
+                .consumer_supplies = ab8500_vamic1_consumers,
+        },
+        /* supply for v-amic2, VAMIC2 LDO, reuse constants for AMIC1 */
+        [AB8505_LDO_ANAMIC2] = {
+                .constraints = {
+                        .name = "V-AMIC2",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8500_vamic2_consumers),
+                .consumer_supplies = ab8500_vamic2_consumers,
+        },
+        /* supply for v-aux8, VAUX8 LDO */
+        [AB8505_LDO_AUX8] = {
+                .constraints = {
+                        .name = "V-AUX8",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8505_vaux8_consumers),
+                .consumer_supplies = ab8505_vaux8_consumers,
+        },
+        /* supply for v-intcore12, VINTCORE12 LDO */
+        [AB8505_LDO_INTCORE] = {
+                .constraints = {
+                        .name = "V-INTCORE",
+                        .min_uV = 1250000,
+                        .max_uV = 1350000,
+                        .input_uV = 1800000,
+                        .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+                                          REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE |
+                                          REGULATOR_CHANGE_DRMS,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8500_vintcore_consumers),
+                .consumer_supplies = ab8500_vintcore_consumers,
+        },
+        /* supply for LDO USB */
+        [AB8505_LDO_USB] = {
+                .constraints = {
+                        .name = "V-USB",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS |
+                                          REGULATOR_CHANGE_MODE,
+                        .valid_modes_mask = REGULATOR_MODE_NORMAL |
+                                            REGULATOR_MODE_IDLE,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8505_usb_consumers),
+                .consumer_supplies = ab8505_usb_consumers,
+        },
+        /* supply for U8500 CSI-DSI, VANA LDO */
+        [AB8505_LDO_ANA] = {
+                .constraints = {
+                        .name = "V-CSI-DSI",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+                .num_consumer_supplies = ARRAY_SIZE(ab8500_vana_consumers),
+                .consumer_supplies = ab8500_vana_consumers,
+        },
+};
+
+struct ab8500_regulator_platform_data ab8500_regulator_plat_data = {
+        .reg_init               = ab8500_reg_init,
+        .num_reg_init           = ARRAY_SIZE(ab8500_reg_init),
+        .regulator              = ab8500_regulators,
+        .num_regulator          = ARRAY_SIZE(ab8500_regulators),
+        .ext_regulator          = ab8500_ext_regulators,
+        .num_ext_regulator      = ARRAY_SIZE(ab8500_ext_regulators),
+};
+
+/* Use the AB8500 init settings for AB8505 as they are the same right now */
+struct ab8500_regulator_platform_data ab8505_regulator_plat_data = {
+        .reg_init               = ab8505_reg_init,
+        .num_reg_init           = ARRAY_SIZE(ab8505_reg_init),
+        .regulator              = ab8505_regulators,
+        .num_regulator          = ARRAY_SIZE(ab8505_regulators),
+};
+
+static void ab8500_modify_reg_init(int id, u8 mask, u8 value)
+{
+        int i;
+
+        if (cpu_is_u8520()) {
+                for (i = ARRAY_SIZE(ab8505_reg_init) - 1; i >= 0; i--) {
+                        if (ab8505_reg_init[i].id == id) {
+                                u8 initval = ab8505_reg_init[i].value;
+                                initval = (initval & ~mask) | (value & mask);
+                                ab8505_reg_init[i].value = initval;
+
+                                BUG_ON(mask & ~ab8505_reg_init[i].mask);
+                                return;
+                        }
+                }
+        } else {
+                for (i = ARRAY_SIZE(ab8500_reg_init) - 1; i >= 0; i--) {
+                        if (ab8500_reg_init[i].id == id) {
+                                u8 initval = ab8500_reg_init[i].value;
+                                initval = (initval & ~mask) | (value & mask);
+                                ab8500_reg_init[i].value = initval;
+
+                                BUG_ON(mask & ~ab8500_reg_init[i].mask);
+                                return;
+                        }
+                }
+        }
+
+        BUG_ON(1);
+}
+
+void mop500_regulator_init(void)
+{
+        struct regulator_init_data *regulator;
+
+        /*
+         * Temporarily turn on Vaux2 on 8520 machine
+         */
+        if (cpu_is_u8520()) {
+                /* Vaux2 initialized to be on */
+                ab8500_modify_reg_init(AB8505_VAUX12REGU, 0x0f, 0x05);
+        }
+
+        /*
+         * Handle AB8500_EXT_SUPPLY2 on HREFP_V20_V50 boards (do it for
+         * all HREFP_V20 boards)
+         */
+        if (cpu_is_u8500v20()) {
+                /* VextSupply2RequestCtrl =  HP/OFF depending on VxRequest */
+                ab8500_modify_reg_init(AB8500_REGUREQUESTCTRL3, 0x01, 0x01);
+
+                /* VextSupply2SysClkReq1HPValid = SysClkReq1 controlled */
+                ab8500_modify_reg_init(AB8500_REGUSYSCLKREQ1HPVALID2,
+                        0x20, 0x20);
+
+                /* VextSupply2 = force HP at initialization */
+                ab8500_modify_reg_init(AB8500_EXTSUPPLYREGU, 0x0c, 0x04);
+
+                /* enable VextSupply2 during platform active */
+                regulator = &ab8500_ext_regulators[AB8500_EXT_SUPPLY2];
+                regulator->constraints.always_on = 1;
+
+                /* disable VextSupply2 in suspend */
+                regulator = &ab8500_ext_regulators[AB8500_EXT_SUPPLY2];
+                regulator->constraints.state_mem.disabled = 1;
+                regulator->constraints.state_standby.disabled = 1;
+
+                /* enable VextSupply2 HW control (used in suspend) */
+                regulator->driver_data = (void *)&ab8500_ext_supply2;
+        }
+}
diff --git a/arch/arm/mach-ux500/board-mop500-regulators.h b/arch/arm/mach-ux500/board-mop500-regulators.h
index 78a0642a2206..9bece38fe933 100644
--- a/arch/arm/mach-ux500/board-mop500-regulators.h
+++ b/arch/arm/mach-ux500/board-mop500-regulators.h
@@ -14,10 +14,11 @@
 #include <linux/regulator/machine.h>
 #include <linux/regulator/ab8500.h>
 
-extern struct ab8500_regulator_reg_init
-ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS];
-extern struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS];
+extern struct ab8500_regulator_platform_data ab8500_regulator_plat_data;
+extern struct ab8500_regulator_platform_data ab8505_regulator_plat_data;
 extern struct regulator_init_data tps61052_regulator;
 extern struct regulator_init_data gpio_en_3v3_regulator;
 
+void mop500_regulator_init(void);
+
 #endif
diff --git a/arch/arm/mach-ux500/board-mop500-sdi.c b/arch/arm/mach-ux500/board-mop500-sdi.c
index 051b62c27102..7f2cb6c5e2c1 100644
--- a/arch/arm/mach-ux500/board-mop500-sdi.c
+++ b/arch/arm/mach-ux500/board-mop500-sdi.c
@@ -81,7 +81,6 @@ static struct stedma40_chan_cfg mop500_sdi0_dma_cfg_tx = {
 #endif
 
 struct mmci_platform_data mop500_sdi0_data = {
-        .ios_handler    = mop500_sdi0_ios_handler,
         .ocr_mask       = MMC_VDD_29_30,
         .f_max          = 50000000,
         .capabilities   = MMC_CAP_4_BIT_DATA |
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index b03457881c4b..ce672378a830 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/i2c.h>
 #include <linux/platform_data/i2c-nomadik.h>
@@ -198,10 +199,7 @@ static struct platform_device snowball_sbnet_dev = {
 
 struct ab8500_platform_data ab8500_platdata = {
         .irq_base       = MOP500_AB8500_IRQ_BASE,
-        .regulator_reg_init = ab8500_regulator_reg_init,
-        .num_regulator_reg_init = ARRAY_SIZE(ab8500_regulator_reg_init),
-        .regulator      = ab8500_regulators,
-        .num_regulator  = ARRAY_SIZE(ab8500_regulators),
+        .regulator      = &ab8500_regulator_plat_data,
         .gpio           = &ab8500_gpio_pdata,
         .codec          = &ab8500_codec_pdata,
 };
@@ -439,6 +437,15 @@ static void mop500_prox_deactivate(struct device *dev)
         regulator_put(prox_regulator);
 }
 
+void mop500_snowball_ethernet_clock_enable(void)
+{
+        struct clk *clk;
+
+        clk = clk_get_sys("fsmc", NULL);
+        if (!IS_ERR(clk))
+                clk_prepare_enable(clk);
+}
+
 static struct cryp_platform_data u8500_cryp1_platform_data = {
                 .mem_to_engine = {
                                 .dir = STEDMA40_MEM_TO_PERIPH,
@@ -683,6 +690,8 @@ static void __init snowball_init_machine(void)
         mop500_audio_init(parent);
         mop500_uart_init(parent);
 
+        mop500_snowball_ethernet_clock_enable();
+
         /* This board has full regulator constraints */
         regulator_has_full_constraints();
 }
diff --git a/arch/arm/mach-ux500/board-mop500.h b/arch/arm/mach-ux500/board-mop500.h
index eaa605f5d90d..d38951be70df 100644
--- a/arch/arm/mach-ux500/board-mop500.h
+++ b/arch/arm/mach-ux500/board-mop500.h
@@ -104,6 +104,7 @@ void __init mop500_pinmaps_init(void);
 void __init snowball_pinmaps_init(void);
 void __init hrefv60_pinmaps_init(void);
 void mop500_audio_init(struct device *parent);
+void mop500_snowball_ethernet_clock_enable(void);
 
 int __init mop500_uib_init(void);
 void mop500_uib_i2c_add(int busnum, struct i2c_board_info *info,
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 19235cf7bbe3..f1a581844372 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -312,9 +312,10 @@ static void __init u8500_init_machine(void)
         /* Pinmaps must be in place before devices register */
         if (of_machine_is_compatible("st-ericsson,mop500"))
                 mop500_pinmaps_init();
-        else if (of_machine_is_compatible("calaosystems,snowball-a9500"))
+        else if (of_machine_is_compatible("calaosystems,snowball-a9500")) {
                 snowball_pinmaps_init();
-        else if (of_machine_is_compatible("st-ericsson,hrefv60+"))
+                mop500_snowball_ethernet_clock_enable();
+        } else if (of_machine_is_compatible("st-ericsson,hrefv60+"))
                 hrefv60_pinmaps_init();
         else if (of_machine_is_compatible("st-ericsson,ccu9540")) {}
                 /* TODO: Add pinmaps for ccu9540 board. */
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 915683cb67d6..c5e20b52e3b7 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -21,6 +21,8 @@
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 #include <linux/vexpress.h>
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
 
 #include <asm/arch_timer.h>
 #include <asm/mach-types.h>
@@ -433,7 +435,7 @@ static void __init v2m_dt_timer_init(void)
 {
         struct device_node *node = NULL;
 
-        vexpress_clk_of_init();
+        of_clk_init(NULL);
 
         do {
                 node = of_find_compatible_node(node, NULL, "arm,sp804");
@@ -441,6 +443,10 @@ static void __init v2m_dt_timer_init(void)
         if (node) {
                 pr_info("Using SP804 '%s' as a clock & events source\n",
                                 node->full_name);
+                WARN_ON(clk_register_clkdev(of_clk_get_by_name(node,
+                                "timclken1"), "v2m-timer0", "sp804"));
+                WARN_ON(clk_register_clkdev(of_clk_get_by_name(node,
+                                "timclken2"), "v2m-timer1", "sp804"));
                 v2m_sp804_init(of_iomap(node, 0),
                                 irq_of_parse_and_map(node, 0));
         }
diff --git a/arch/arm/mach-w90x900/dev.c b/arch/arm/mach-w90x900/dev.c
index 7abdb9645c5b..e65a80a1ac75 100644
--- a/arch/arm/mach-w90x900/dev.c
+++ b/arch/arm/mach-w90x900/dev.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
 
 #include <linux/mtd/physmap.h>
 #include <linux/mtd/mtd.h>
@@ -531,7 +532,7 @@ static struct platform_device *nuc900_public_dev[] __initdata = {
 
 void __init nuc900_board_init(struct platform_device **device, int size)
 {
-        disable_hlt();
+        cpu_idle_poll_ctrl(true);
         platform_add_devices(device, size);
         platform_add_devices(nuc900_public_dev, ARRAY_SIZE(nuc900_public_dev));
         spi_register_board_info(nuc900_spi_board_info,
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 025d17328730..4045c4931a30 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -43,7 +43,7 @@ config CPU_ARM740T
         depends on !MMU
         select CPU_32v4T
         select CPU_ABRT_LV4T
-        select CPU_CACHE_V3     # although the core is v4t
+        select CPU_CACHE_V4
         select CPU_CP15_MPU
         select CPU_PABRT_LEGACY
         help
@@ -469,9 +469,6 @@ config CPU_PABRT_V7
         bool
 
 # The cache model
-config CPU_CACHE_V3
-        bool
-
 config CPU_CACHE_V4
         bool
 
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 4e333fa2756f..9e51be96f635 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -33,7 +33,6 @@ obj-$(CONFIG_CPU_PABRT_LEGACY)	+= pabort-legacy.o
 obj-$(CONFIG_CPU_PABRT_V6)      += pabort-v6.o
 obj-$(CONFIG_CPU_PABRT_V7)      += pabort-v7.o
 
-obj-$(CONFIG_CPU_CACHE_V3)      += cache-v3.o
 obj-$(CONFIG_CPU_CACHE_V4)      += cache-v4.o
 obj-$(CONFIG_CPU_CACHE_V4WT)    += cache-v4wt.o
 obj-$(CONFIG_CPU_CACHE_V4WB)    += cache-v4wb.o
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index dd3d59122cc3..48bc3c0a87ce 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override)
         outer_cache.inv_range = feroceon_l2_inv_range;
         outer_cache.clean_range = feroceon_l2_clean_range;
         outer_cache.flush_range = feroceon_l2_flush_range;
+        outer_cache.inv_all = l2_inv_all;
 
         enable_l2();
 
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index c2f37390308a..c465faca51b0 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -299,7 +299,7 @@ static void l2x0_unlock(u32 cache_id)
         int lockregs;
         int i;
 
-        switch (cache_id) {
+        switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
         case L2X0_CACHE_ID_PART_L310:
                 lockregs = 8;
                 break;
@@ -333,15 +333,14 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
         if (cache_id_part_number_from_dt)
                 cache_id = cache_id_part_number_from_dt;
         else
-                cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID)
-                        & L2X0_CACHE_ID_PART_MASK;
+                cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
         aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
 
         aux &= aux_mask;
         aux |= aux_val;
 
         /* Determine the number of ways */
-        switch (cache_id) {
+        switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
         case L2X0_CACHE_ID_PART_L310:
                 if (aux & (1 << 16))
                         ways = 16;
@@ -725,7 +724,6 @@ static const struct l2x0_of_data pl310_data = {
                 .flush_all   = l2x0_flush_all,
                 .inv_all     = l2x0_inv_all,
                 .disable     = l2x0_disable,
-                .set_debug   = pl310_set_debug,
         },
 };
 
@@ -814,9 +812,8 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
                 data->save();
 
         of_init = true;
-        l2x0_init(l2x0_base, aux_val, aux_mask);
-
         memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache));
+        l2x0_init(l2x0_base, aux_val, aux_mask);
 
         return 0;
 }
diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S
deleted file mode 100644
index 8a3fadece8d3..000000000000
--- a/arch/arm/mm/cache-v3.S
+++ /dev/null
@@ -1,137 +0,0 @@
-/*
- *  linux/arch/arm/mm/cache-v3.S
- *
- *  Copyright (C) 1997-2002 Russell king
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/page.h>
-#include "proc-macros.S"
-
-/*
- *      flush_icache_all()
- *
- *      Unconditionally clean and invalidate the entire icache.
- */
-ENTRY(v3_flush_icache_all)
-        mov     pc, lr
-ENDPROC(v3_flush_icache_all)
-
-/*
- *      flush_user_cache_all()
- *
- *      Invalidate all cache entries in a particular address
- *      space.
- *
- *      - mm    - mm_struct describing address space
- */
-ENTRY(v3_flush_user_cache_all)
-        /* FALLTHROUGH */
-/*
- *      flush_kern_cache_all()
- *
- *      Clean and invalidate the entire cache.
- */
-ENTRY(v3_flush_kern_cache_all)
-        /* FALLTHROUGH */
-
-/*
- *      flush_user_cache_range(start, end, flags)
- *
- *      Invalidate a range of cache entries in the specified
- *      address space.
- *
- *      - start - start address (may not be aligned)
- *      - end   - end address (exclusive, may not be aligned)
- *      - flags - vma_area_struct flags describing address space
- */
-ENTRY(v3_flush_user_cache_range)
-        mov     ip, #0
-        mcreq   p15, 0, ip, c7, c0, 0           @ flush ID cache
-        mov     pc, lr
-
-/*
- *      coherent_kern_range(start, end)
- *
- *      Ensure coherency between the Icache and the Dcache in the
- *      region described by start.  If you have non-snooping
- *      Harvard caches, you need to implement this function.
- *
- *      - start  - virtual start address
- *      - end    - virtual end address
- */
-ENTRY(v3_coherent_kern_range)
-        /* FALLTHROUGH */
-
-/*
- *      coherent_user_range(start, end)
- *
- *      Ensure coherency between the Icache and the Dcache in the
- *      region described by start.  If you have non-snooping
- *      Harvard caches, you need to implement this function.
- *
- *      - start  - virtual start address
- *      - end    - virtual end address
- */
-ENTRY(v3_coherent_user_range)
-        mov     r0, #0
-        mov     pc, lr
-
-/*
- *      flush_kern_dcache_area(void *page, size_t size)
- *
- *      Ensure no D cache aliasing occurs, either with itself or
- *      the I cache
- *
- *      - addr  - kernel address
- *      - size  - region size
- */
-ENTRY(v3_flush_kern_dcache_area)
-        /* FALLTHROUGH */
-
-/*
- *      dma_flush_range(start, end)
- *
- *      Clean and invalidate the specified virtual address range.
- *
- *      - start  - virtual start address
- *      - end    - virtual end address
- */
-ENTRY(v3_dma_flush_range)
-        mov     r0, #0
-        mcr     p15, 0, r0, c7, c0, 0           @ flush ID cache
-        mov     pc, lr
-
-/*
- *      dma_unmap_area(start, size, dir)
- *      - start - kernel virtual start address
- *      - size  - size of region
- *      - dir   - DMA direction
- */
-ENTRY(v3_dma_unmap_area)
-        teq     r2, #DMA_TO_DEVICE
-        bne     v3_dma_flush_range
-        /* FALLTHROUGH */
-
-/*
- *      dma_map_area(start, size, dir)
- *      - start - kernel virtual start address
- *      - size  - size of region
- *      - dir   - DMA direction
- */
-ENTRY(v3_dma_map_area)
-        mov     pc, lr
-ENDPROC(v3_dma_unmap_area)
-ENDPROC(v3_dma_map_area)
-
-        .globl  v3_flush_kern_cache_louis
-        .equ    v3_flush_kern_cache_louis, v3_flush_kern_cache_all
-
-        __INITDATA
-
-        @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
-        define_cache_functions v3
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index 43e5d77be677..a7ba68f59f0c 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -58,7 +58,7 @@ ENTRY(v4_flush_kern_cache_all)
 ENTRY(v4_flush_user_cache_range)
 #ifdef CONFIG_CPU_CP15
         mov     ip, #0
-        mcreq   p15, 0, ip, c7, c7, 0           @ flush ID cache
+        mcr     p15, 0, ip, c7, c7, 0           @ flush ID cache
         mov     pc, lr
 #else
         /* FALLTHROUGH */
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index a5a4b2bc42ba..2ac37372ef52 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -48,7 +48,7 @@ static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
 static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION);
 static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS);
 
-static DEFINE_PER_CPU(atomic64_t, active_asids);
+DEFINE_PER_CPU(atomic64_t, active_asids);
 static DEFINE_PER_CPU(u64, reserved_asids);
 static cpumask_t tlb_flush_pending;
 
@@ -215,6 +215,7 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
         if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) {
                 local_flush_bp_all();
                 local_flush_tlb_all();
+                dummy_flush_tlb_a15_erratum();
         }
 
         atomic64_set(&per_cpu(active_asids, cpu), asid);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index c7e3759f16d3..e9db6b4bf65a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -342,6 +342,7 @@ static int __init atomic_pool_init(void)
 {
         struct dma_pool *pool = &atomic_pool;
         pgprot_t prot = pgprot_dmacoherent(pgprot_kernel);
+        gfp_t gfp = GFP_KERNEL | GFP_DMA;
         unsigned long nr_pages = pool->size >> PAGE_SHIFT;
         unsigned long *bitmap;
         struct page *page;
@@ -361,8 +362,8 @@ static int __init atomic_pool_init(void)
                 ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
                                               atomic_pool_init);
         else
-                ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot,
-                                           &page, atomic_pool_init);
+                ptr = __alloc_remap_buffer(NULL, pool->size, gfp, prot, &page,
+                                           atomic_pool_init);
         if (ptr) {
                 int i;
 
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index ad722f1208a5..9a5cdc01fcdf 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -99,6 +99,9 @@ void show_mem(unsigned int filter)
         printk("Mem-info:\n");
         show_free_areas(filter);
 
+        if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+                return;
+
         for_each_bank (i, mi) {
                 struct membank *bank = &mi->bank[i];
                 unsigned int pfn1, pfn2;
@@ -424,24 +427,6 @@ void __init bootmem_init(void)
         max_pfn = max_high - PHYS_PFN_OFFSET;
 }
 
-static inline int free_area(unsigned long pfn, unsigned long end, char *s)
-{
-        unsigned int pages = 0, size = (end - pfn) << (PAGE_SHIFT - 10);
-
-        for (; pfn < end; pfn++) {
-                struct page *page = pfn_to_page(pfn);
-                ClearPageReserved(page);
-                init_page_count(page);
-                __free_page(page);
-                pages++;
-        }
-
-        if (size && s)
-                printk(KERN_INFO "Freeing %s memory: %dK\n", s, size);
-
-        return pages;
-}
-
 /*
  * Poison init memory with an undefined instruction (ARM) or a branch to an
  * undefined instruction (Thumb).
@@ -534,6 +519,14 @@ static void __init free_unused_memmap(struct meminfo *mi)
 #endif
 }
 
+#ifdef CONFIG_HIGHMEM
+static inline void free_area_high(unsigned long pfn, unsigned long end)
+{
+        for (; pfn < end; pfn++)
+                free_highmem_page(pfn_to_page(pfn));
+}
+#endif
+
 static void __init free_highpages(void)
 {
 #ifdef CONFIG_HIGHMEM
@@ -569,8 +562,7 @@ static void __init free_highpages(void)
                         if (res_end > end)
                                 res_end = end;
                         if (res_start != start)
-                                totalhigh_pages += free_area(start, res_start,
-                                                             NULL);
+                                free_area_high(start, res_start);
                         start = res_end;
                         if (start == end)
                                 break;
@@ -578,9 +570,8 @@ static void __init free_highpages(void)
 
                 /* And now free anything which remains */
                 if (start < end)
-                        totalhigh_pages += free_area(start, end, NULL);
+                        free_area_high(start, end);
         }
-        totalram_pages += totalhigh_pages;
 #endif
 }
 
@@ -609,8 +600,7 @@ void __init mem_init(void)
 
 #ifdef CONFIG_SA1111
         /* now that our DMA memory is actually so designated, we can free it */
-        totalram_pages += free_area(PHYS_PFN_OFFSET,
-                                    __phys_to_pfn(__pa(swapper_pg_dir)), NULL);
+        free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL);
 #endif
 
         free_highpages();
@@ -738,16 +728,12 @@ void free_initmem(void)
         extern char __tcm_start, __tcm_end;
 
         poison_init_mem(&__tcm_start, &__tcm_end - &__tcm_start);
-        totalram_pages += free_area(__phys_to_pfn(__pa(&__tcm_start)),
-                                    __phys_to_pfn(__pa(&__tcm_end)),
-                                    "TCM link");
+        free_reserved_area(&__tcm_start, &__tcm_end, 0, "TCM link");
 #endif
 
         poison_init_mem(__init_begin, __init_end - __init_begin);
         if (!machine_is_integrator() && !machine_is_cintegrator())
-                totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)),
-                                            __phys_to_pfn(__pa(__init_end)),
-                                            "init");
+                free_initmem_default(0);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -758,9 +744,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 {
         if (!keep_initrd) {
                 poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
-                totalram_pages += free_area(__phys_to_pfn(__pa(start)),
-                                            __phys_to_pfn(__pa(end)),
-                                            "initrd");
+                free_reserved_area(start, end, 0, "initrd");
         }
 }
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index e95a996ab78f..a84ff763ac39 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -34,6 +34,7 @@
 #include <asm/mach/pci.h>
 
 #include "mm.h"
+#include "tcm.h"
 
 /*
  * empty_zero_page is a special page that is used for
@@ -598,39 +599,60 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
         } while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static void __init alloc_init_section(pud_t *pud, unsigned long addr,
-                                      unsigned long end, phys_addr_t phys,
-                                      const struct mem_type *type)
+static void __init map_init_section(pmd_t *pmd, unsigned long addr,
+                        unsigned long end, phys_addr_t phys,
+                        const struct mem_type *type)
 {
-        pmd_t *pmd = pmd_offset(pud, addr);
-
+#ifndef CONFIG_ARM_LPAE
         /*
-         * Try a section mapping - end, addr and phys must all be aligned
-         * to a section boundary.  Note that PMDs refer to the individual
-         * L1 entries, whereas PGDs refer to a group of L1 entries making
-         * up one logical pointer to an L2 table.
+         * In classic MMU format, puds and pmds are folded in to
+         * the pgds. pmd_offset gives the PGD entry. PGDs refer to a
+         * group of L1 entries making up one logical pointer to
+         * an L2 table (2MB), where as PMDs refer to the individual
+         * L1 entries (1MB). Hence increment to get the correct
+         * offset for odd 1MB sections.
+         * (See arch/arm/include/asm/pgtable-2level.h)
          */
-        if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0) {
-                pmd_t *p = pmd;
-
-#ifndef CONFIG_ARM_LPAE
-                if (addr & SECTION_SIZE)
-                        pmd++;
+        if (addr & SECTION_SIZE)
+                pmd++;
 #endif
+        do {
+                *pmd = __pmd(phys | type->prot_sect);
+                phys += SECTION_SIZE;
+        } while (pmd++, addr += SECTION_SIZE, addr != end);
 
-                do {
-                        *pmd = __pmd(phys | type->prot_sect);
-                        phys += SECTION_SIZE;
-                } while (pmd++, addr += SECTION_SIZE, addr != end);
+        flush_pmd_entry(pmd);
+}
 
-                flush_pmd_entry(p);
-        } else {
+static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
+                                      unsigned long end, phys_addr_t phys,
+                                      const struct mem_type *type)
+{
+        pmd_t *pmd = pmd_offset(pud, addr);
+        unsigned long next;
+
+        do {
                 /*
-                 * No need to loop; pte's aren't interested in the
-                 * individual L1 entries.
+                 * With LPAE, we must loop over to map
+                 * all the pmds for the given range.
                  */
-                alloc_init_pte(pmd, addr, end, __phys_to_pfn(phys), type);
-        }
+                next = pmd_addr_end(addr, end);
+
+                /*
+                 * Try a section mapping - addr, next and phys must all be
+                 * aligned to a section boundary.
+                 */
+                if (type->prot_sect &&
+                                ((addr | next | phys) & ~SECTION_MASK) == 0) {
+                        map_init_section(pmd, addr, next, phys, type);
+                } else {
+                        alloc_init_pte(pmd, addr, next,
+                                                __phys_to_pfn(phys), type);
+                }
+
+                phys += next - addr;
+
+        } while (pmd++, addr = next, addr != end);
 }
 
 static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
@@ -641,7 +663,7 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
 
         do {
                 next = pud_addr_end(addr, end);
-                alloc_init_section(pud, addr, next, phys, type);
+                alloc_init_pmd(pud, addr, next, phys, type);
                 phys += next - addr;
         } while (pud++, addr = next, addr != end);
 }
@@ -1256,6 +1278,7 @@ void __init paging_init(struct machine_desc *mdesc)
         dma_contiguous_remap();
         devicemaps_init(mdesc);
         kmap_init();
+        tcm_init();
 
         top_pmd = pmd_off_k(0xffff0000);
 
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index dc5de5d53f20..fde2d2a794cf 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -77,24 +77,27 @@ __arm740_setup:
         mcr     p15, 0, r0, c6, c0              @ set area 0, default
 
         ldr     r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM
-        ldr     r1, =(CONFIG_DRAM_SIZE >> 12)   @ size of RAM (must be >= 4KB)
-        mov     r2, #10                         @ 11 is the minimum (4KB)
-1:      add     r2, r2, #1                      @ area size *= 2
-        mov     r1, r1, lsr #1
+        ldr     r3, =(CONFIG_DRAM_SIZE >> 12)   @ size of RAM (must be >= 4KB)
+        mov     r4, #10                         @ 11 is the minimum (4KB)
+1:      add     r4, r4, #1                      @ area size *= 2
+        movs    r3, r3, lsr #1
         bne     1b                              @ count not zero r-shift
-        orr     r0, r0, r2, lsl #1              @ the area register value
+        orr     r0, r0, r4, lsl #1              @ the area register value
         orr     r0, r0, #1                      @ set enable bit
         mcr     p15, 0, r0, c6, c1              @ set area 1, RAM
 
         ldr     r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH
-        ldr     r1, =(CONFIG_FLASH_SIZE >> 12)  @ size of FLASH (must be >= 4KB)
-        mov     r2, #10                         @ 11 is the minimum (4KB)
-1:      add     r2, r2, #1                      @ area size *= 2
-        mov     r1, r1, lsr #1
+        ldr     r3, =(CONFIG_FLASH_SIZE >> 12)  @ size of FLASH (must be >= 4KB)
+        cmp     r3, #0
+        moveq   r0, #0
+        beq     2f
+        mov     r4, #10                         @ 11 is the minimum (4KB)
+1:      add     r4, r4, #1                      @ area size *= 2
+        movs    r3, r3, lsr #1
         bne     1b                              @ count not zero r-shift
-        orr     r0, r0, r2, lsl #1              @ the area register value
+        orr     r0, r0, r4, lsl #1              @ the area register value
         orr     r0, r0, #1                      @ set enable bit
-        mcr     p15, 0, r0, c6, c2              @ set area 2, ROM/FLASH
+2:      mcr     p15, 0, r0, c6, c2              @ set area 2, ROM/FLASH
 
         mov     r0, #0x06
         mcr     p15, 0, r0, c2, c0              @ Region 1&2 cacheable
@@ -137,13 +140,14 @@ __arm740_proc_info:
         .long   0x41807400
         .long   0xfffffff0
         .long   0
+        .long   0
         b       __arm740_setup
         .long   cpu_arch_name
         .long   cpu_elf_name
-        .long   HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT
+        .long   HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT
         .long   cpu_arm740_name
         .long   arm740_processor_functions
         .long   0
         .long   0
-        .long   v3_cache_fns                    @ cache model
+        .long   v4_cache_fns                    @ cache model
         .size   __arm740_proc_info, . - __arm740_proc_info
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 2c3b9421ab5e..2556cf1c2da1 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -387,7 +387,7 @@ ENTRY(cpu_arm920_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl  cpu_arm920_suspend_size
 .equ    cpu_arm920_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_arm920_do_suspend)
         stmfd   sp!, {r4 - r6, lr}
         mrc     p15, 0, r4, c13, c0, 0  @ PID
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index f1803f7e2972..344c8a548cc0 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -402,7 +402,7 @@ ENTRY(cpu_arm926_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl  cpu_arm926_suspend_size
 .equ    cpu_arm926_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_arm926_do_suspend)
         stmfd   sp!, {r4 - r6, lr}
         mrc     p15, 0, r4, c13, c0, 0  @ PID
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index 82f9cdc751d6..0b60dd3d742a 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -350,7 +350,7 @@ ENTRY(cpu_mohawk_set_pte_ext)
 
 .globl  cpu_mohawk_suspend_size
 .equ    cpu_mohawk_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_mohawk_do_suspend)
         stmfd   sp!, {r4 - r9, lr}
         mrc     p14, 0, r4, c6, c0, 0   @ clock configuration, for turbo mode
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 3aa0da11fd84..d92dfd081429 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -172,7 +172,7 @@ ENTRY(cpu_sa1100_set_pte_ext)
 
 .globl  cpu_sa1100_suspend_size
 .equ    cpu_sa1100_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_sa1100_do_suspend)
         stmfd   sp!, {r4 - r6, lr}
         mrc     p15, 0, r4, c3, c0, 0           @ domain ID
diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c
index 3e6210b4d6d4..054b491ff764 100644
--- a/arch/arm/mm/proc-syms.c
+++ b/arch/arm/mm/proc-syms.c
@@ -17,7 +17,9 @@
 
 #ifndef MULTI_CPU
 EXPORT_SYMBOL(cpu_dcache_clean_area);
+#ifdef CONFIG_MMU
 EXPORT_SYMBOL(cpu_set_pte_ext);
+#endif
 #else
 EXPORT_SYMBOL(processor);
 #endif
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index bcaaa8de9325..5c07ee4fe3eb 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -138,7 +138,7 @@ ENTRY(cpu_v6_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */
 .globl  cpu_v6_suspend_size
 .equ    cpu_v6_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v6_do_suspend)
         stmfd   sp!, {r4 - r9, lr}
         mrc     p15, 0, r4, c13, c0, 0  @ FCSE/PID
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 3a3c015f8d5c..f584d3f5b37c 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -420,7 +420,7 @@ __v7_pj4b_proc_info:
 __v7_ca7mp_proc_info:
         .long   0x410fc070
         .long   0xff0ffff0
-        __v7_proc __v7_ca7mp_setup, hwcaps = HWCAP_IDIV
+        __v7_proc __v7_ca7mp_setup
         .size   __v7_ca7mp_proc_info, . - __v7_ca7mp_proc_info
 
         /*
@@ -430,10 +430,25 @@ __v7_ca7mp_proc_info:
 __v7_ca15mp_proc_info:
         .long   0x410fc0f0
         .long   0xff0ffff0
-        __v7_proc __v7_ca15mp_setup, hwcaps = HWCAP_IDIV
+        __v7_proc __v7_ca15mp_setup
         .size   __v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info
 
         /*
+         * Qualcomm Inc. Krait processors.
+         */
+        .type   __krait_proc_info, #object
+__krait_proc_info:
+        .long   0x510f0400              @ Required ID value
+        .long   0xff0ffc00              @ Mask for ID
+        /*
+         * Some Krait processors don't indicate support for SDIV and UDIV
+         * instructions in the ARM instruction set, even though they actually
+         * do support them.
+         */
+        __v7_proc __v7_setup, hwcaps = HWCAP_IDIV
+        .size   __krait_proc_info, . - __krait_proc_info
+
+        /*
          * Match any ARMv7 processor core.
          */
         .type   __v7_proc_info, #object
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index eb93d6487f35..e8efd83b6f25 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -413,7 +413,7 @@ ENTRY(cpu_xsc3_set_pte_ext)
 
 .globl  cpu_xsc3_suspend_size
 .equ    cpu_xsc3_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_xsc3_do_suspend)
         stmfd   sp!, {r4 - r9, lr}
         mrc     p14, 0, r4, c6, c0, 0   @ clock configuration, for turbo mode
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 25510361aa18..e766f889bfd6 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -528,7 +528,7 @@ ENTRY(cpu_xscale_set_pte_ext)
 
 .globl  cpu_xscale_suspend_size
 .equ    cpu_xscale_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_xscale_do_suspend)
         stmfd   sp!, {r4 - r9, lr}
         mrc     p14, 0, r4, c6, c0, 0   @ clock configuration, for turbo mode
diff --git a/arch/arm/kernel/tcm.h b/arch/arm/mm/tcm.h
index 8015ad434a40..8015ad434a40 100644
--- a/arch/arm/kernel/tcm.h
+++ b/arch/arm/mm/tcm.h
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 6828ef6ce80e..a0bd8a755bdf 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -576,7 +576,7 @@ load_ind:
                         /* x = ((*(frame + k)) & 0xf) << 2; */
                         ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL;
                         /* the interpreter should deal with the negative K */
-                        if (k < 0)
+                        if ((int)k < 0)
                                 return -1;
                         /* offset in r1: we might have to take the slow path */
                         emit_mov_i(r_off, k, ctx);
diff --git a/arch/arm/plat-orion/addr-map.c b/arch/arm/plat-orion/addr-map.c
index febe3862873c..807ac8e5cbc0 100644
--- a/arch/arm/plat-orion/addr-map.c
+++ b/arch/arm/plat-orion/addr-map.c
@@ -157,9 +157,12 @@ void __init orion_setup_cpu_mbus_target(const struct orion_addr_map_cfg *cfg,
                 u32 size = readl(ddr_window_cpu_base + DDR_SIZE_CS_OFF(i));
 
                 /*
-                 * Chip select enabled?
+                 * We only take care of entries for which the chip
+                 * select is enabled, and that don't have high base
+                 * address bits set (devices can only access the first
+                 * 32 bits of the memory).
                  */
-                if (size & 1) {
+                if ((size & 1) && !(base & 0xF)) {
                         struct mbus_dram_window *w;
 
                         w = &orion_mbus_dram_info.cs[cs++];
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 51afedda9ab6..03db14d8ace9 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -10,6 +10,7 @@
  * published by the Free Software Foundation.
 */
 
+#include <linux/amba/pl330.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
@@ -1552,6 +1553,9 @@ void __init s3c64xx_spi0_set_platdata(int (*cfg_gpio)(void), int src_clk_nr,
         pd.num_cs = num_cs;
         pd.src_clk_nr = src_clk_nr;
         pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi0_cfg_gpio;
+#ifdef CONFIG_PL330_DMA
+        pd.filter = pl330_filter;
+#endif
 
         s3c_set_platdata(&pd, sizeof(pd), &s3c64xx_device_spi0);
 }
@@ -1590,6 +1594,9 @@ void __init s3c64xx_spi1_set_platdata(int (*cfg_gpio)(void), int src_clk_nr,
         pd.num_cs = num_cs;
         pd.src_clk_nr = src_clk_nr;
         pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi1_cfg_gpio;
+#ifdef CONFIG_PL330_DMA
+        pd.filter = pl330_filter;
+#endif
 
         s3c_set_platdata(&pd, sizeof(pd), &s3c64xx_device_spi1);
 }
@@ -1628,6 +1635,9 @@ void __init s3c64xx_spi2_set_platdata(int (*cfg_gpio)(void), int src_clk_nr,
         pd.num_cs = num_cs;
         pd.src_clk_nr = src_clk_nr;
         pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi2_cfg_gpio;
+#ifdef CONFIG_PL330_DMA
+        pd.filter = pl330_filter;
+#endif
 
         s3c_set_platdata(&pd, sizeof(pd), &s3c64xx_device_spi2);
 }
diff --git a/arch/arm/plat-samsung/include/plat/fb.h b/arch/arm/plat-samsung/include/plat/fb.h
index b885322717a1..9ae507270785 100644
--- a/arch/arm/plat-samsung/include/plat/fb.h
+++ b/arch/arm/plat-samsung/include/plat/fb.h
@@ -15,55 +15,7 @@
 #ifndef __PLAT_S3C_FB_H
 #define __PLAT_S3C_FB_H __FILE__
 
-/* S3C_FB_MAX_WIN
- * Set to the maximum number of windows that any of the supported hardware
- * can use. Since the platform data uses this for an array size, having it
- * set to the maximum of any version of the hardware can do is safe.
- */
-#define S3C_FB_MAX_WIN  (5)
-
-/**
- * struct s3c_fb_pd_win - per window setup data
- * @xres     : The window X size.
- * @yres     : The window Y size.
- * @virtual_x: The virtual X size.
- * @virtual_y: The virtual Y size.
- */
-struct s3c_fb_pd_win {
-        unsigned short          default_bpp;
-        unsigned short          max_bpp;
-        unsigned short          xres;
-        unsigned short          yres;
-        unsigned short          virtual_x;
-        unsigned short          virtual_y;
-};
-
-/**
- * struct s3c_fb_platdata -  S3C driver platform specific information
- * @setup_gpio: Setup the external GPIO pins to the right state to transfer
- *              the data from the display system to the connected display
- *              device.
- * @vidcon0: The base vidcon0 values to control the panel data format.
- * @vidcon1: The base vidcon1 values to control the panel data output.
- * @vtiming: Video timing when connected to a RGB type panel.
- * @win: The setup data for each hardware window, or NULL for unused.
- * @display_mode: The LCD output display mode.
- *
- * The platform data supplies the video driver with all the information
- * it requires to work with the display(s) attached to the machine. It
- * controls the initial mode, the number of display windows (0 is always
- * the base framebuffer) that are initialised etc.
- *
- */
-struct s3c_fb_platdata {
-        void    (*setup_gpio)(void);
-
-        struct s3c_fb_pd_win    *win[S3C_FB_MAX_WIN];
-        struct fb_videomode     *vtiming;
-
-        u32                      vidcon0;
-        u32                      vidcon1;
-};
+#include <linux/platform_data/video_s3c.h>
 
 /**
  * s3c_fb_set_platdata() - Setup the FB device with platform data.
diff --git a/arch/arm/plat-samsung/include/plat/regs-serial.h b/arch/arm/plat-samsung/include/plat/regs-serial.h
index 29c26a818842..f05f2afa440d 100644
--- a/arch/arm/plat-samsung/include/plat/regs-serial.h
+++ b/arch/arm/plat-samsung/include/plat/regs-serial.h
@@ -1,281 +1 @@
-/* arch/arm/plat-samsung/include/plat/regs-serial.h
- *
- *  From linux/include/asm-arm/hardware/serial_s3c2410.h
- *
- *  Internal header file for Samsung S3C2410 serial ports (UART0-2)
- *
- *  Copyright (C) 2002 Shane Nay (shane@minirl.com)
- *
- *  Additional defines, Copyright 2003 Simtec Electronics (linux@simtec.co.uk)
- *
- *  Adapted from:
- *
- *  Internal header file for MX1ADS serial ports (UART1 & 2)
- *
- *  Copyright (C) 2002 Shane Nay (shane@minirl.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-*/
-
-#ifndef __ASM_ARM_REGS_SERIAL_H
-#define __ASM_ARM_REGS_SERIAL_H
-
-#define S3C24XX_VA_UART0      (S3C_VA_UART)
-#define S3C24XX_VA_UART1      (S3C_VA_UART + 0x4000 )
-#define S3C24XX_VA_UART2      (S3C_VA_UART + 0x8000 )
-#define S3C24XX_VA_UART3      (S3C_VA_UART + 0xC000 )
-
-#define S3C2410_PA_UART0      (S3C24XX_PA_UART)
-#define S3C2410_PA_UART1      (S3C24XX_PA_UART + 0x4000 )
-#define S3C2410_PA_UART2      (S3C24XX_PA_UART + 0x8000 )
-#define S3C2443_PA_UART3      (S3C24XX_PA_UART + 0xC000 )
-
-#define S3C2410_URXH      (0x24)
-#define S3C2410_UTXH      (0x20)
-#define S3C2410_ULCON     (0x00)
-#define S3C2410_UCON      (0x04)
-#define S3C2410_UFCON     (0x08)
-#define S3C2410_UMCON     (0x0C)
-#define S3C2410_UBRDIV    (0x28)
-#define S3C2410_UTRSTAT   (0x10)
-#define S3C2410_UERSTAT   (0x14)
-#define S3C2410_UFSTAT    (0x18)
-#define S3C2410_UMSTAT    (0x1C)
-
-#define S3C2410_LCON_CFGMASK      ((0xF<<3)|(0x3))
-
-#define S3C2410_LCON_CS5          (0x0)
-#define S3C2410_LCON_CS6          (0x1)
-#define S3C2410_LCON_CS7          (0x2)
-#define S3C2410_LCON_CS8          (0x3)
-#define S3C2410_LCON_CSMASK       (0x3)
-
-#define S3C2410_LCON_PNONE        (0x0)
-#define S3C2410_LCON_PEVEN        (0x5 << 3)
-#define S3C2410_LCON_PODD         (0x4 << 3)
-#define S3C2410_LCON_PMASK        (0x7 << 3)
-
-#define S3C2410_LCON_STOPB        (1<<2)
-#define S3C2410_LCON_IRM          (1<<6)
-
-#define S3C2440_UCON_CLKMASK      (3<<10)
-#define S3C2440_UCON_CLKSHIFT     (10)
-#define S3C2440_UCON_PCLK         (0<<10)
-#define S3C2440_UCON_UCLK         (1<<10)
-#define S3C2440_UCON_PCLK2        (2<<10)
-#define S3C2440_UCON_FCLK         (3<<10)
-#define S3C2443_UCON_EPLL         (3<<10)
-
-#define S3C6400_UCON_CLKMASK    (3<<10)
-#define S3C6400_UCON_CLKSHIFT   (10)
-#define S3C6400_UCON_PCLK       (0<<10)
-#define S3C6400_UCON_PCLK2      (2<<10)
-#define S3C6400_UCON_UCLK0      (1<<10)
-#define S3C6400_UCON_UCLK1      (3<<10)
-
-#define S3C2440_UCON2_FCLK_EN     (1<<15)
-#define S3C2440_UCON0_DIVMASK     (15 << 12)
-#define S3C2440_UCON1_DIVMASK     (15 << 12)
-#define S3C2440_UCON2_DIVMASK     (7 << 12)
-#define S3C2440_UCON_DIVSHIFT     (12)
-
-#define S3C2412_UCON_CLKMASK    (3<<10)
-#define S3C2412_UCON_CLKSHIFT   (10)
-#define S3C2412_UCON_UCLK       (1<<10)
-#define S3C2412_UCON_USYSCLK    (3<<10)
-#define S3C2412_UCON_PCLK       (0<<10)
-#define S3C2412_UCON_PCLK2      (2<<10)
-
-#define S3C2410_UCON_CLKMASK    (1 << 10)
-#define S3C2410_UCON_CLKSHIFT   (10)
-#define S3C2410_UCON_UCLK         (1<<10)
-#define S3C2410_UCON_SBREAK       (1<<4)
-
-#define S3C2410_UCON_TXILEVEL     (1<<9)
-#define S3C2410_UCON_RXILEVEL     (1<<8)
-#define S3C2410_UCON_TXIRQMODE    (1<<2)
-#define S3C2410_UCON_RXIRQMODE    (1<<0)
-#define S3C2410_UCON_RXFIFO_TOI   (1<<7)
-#define S3C2443_UCON_RXERR_IRQEN  (1<<6)
-#define S3C2443_UCON_LOOPBACK     (1<<5)
-
-#define S3C2410_UCON_DEFAULT      (S3C2410_UCON_TXILEVEL  | \
-                                   S3C2410_UCON_RXILEVEL  | \
-                                   S3C2410_UCON_TXIRQMODE | \
-                                   S3C2410_UCON_RXIRQMODE | \
-                                   S3C2410_UCON_RXFIFO_TOI)
-
-#define S3C2410_UFCON_FIFOMODE    (1<<0)
-#define S3C2410_UFCON_TXTRIG0     (0<<6)
-#define S3C2410_UFCON_RXTRIG8     (1<<4)
-#define S3C2410_UFCON_RXTRIG12    (2<<4)
-
-/* S3C2440 FIFO trigger levels */
-#define S3C2440_UFCON_RXTRIG1     (0<<4)
-#define S3C2440_UFCON_RXTRIG8     (1<<4)
-#define S3C2440_UFCON_RXTRIG16    (2<<4)
-#define S3C2440_UFCON_RXTRIG32    (3<<4)
-
-#define S3C2440_UFCON_TXTRIG0     (0<<6)
-#define S3C2440_UFCON_TXTRIG16    (1<<6)
-#define S3C2440_UFCON_TXTRIG32    (2<<6)
-#define S3C2440_UFCON_TXTRIG48    (3<<6)
-
-#define S3C2410_UFCON_RESETBOTH   (3<<1)
-#define S3C2410_UFCON_RESETTX     (1<<2)
-#define S3C2410_UFCON_RESETRX     (1<<1)
-
-#define S3C2410_UFCON_DEFAULT     (S3C2410_UFCON_FIFOMODE | \
-                                   S3C2410_UFCON_TXTRIG0  | \
-                                   S3C2410_UFCON_RXTRIG8 )
-
-#define S3C2410_UMCOM_AFC         (1<<4)
-#define S3C2410_UMCOM_RTS_LOW     (1<<0)
-
-#define S3C2412_UMCON_AFC_63    (0<<5)          /* same as s3c2443 */
-#define S3C2412_UMCON_AFC_56    (1<<5)
-#define S3C2412_UMCON_AFC_48    (2<<5)
-#define S3C2412_UMCON_AFC_40    (3<<5)
-#define S3C2412_UMCON_AFC_32    (4<<5)
-#define S3C2412_UMCON_AFC_24    (5<<5)
-#define S3C2412_UMCON_AFC_16    (6<<5)
-#define S3C2412_UMCON_AFC_8     (7<<5)
-
-#define S3C2410_UFSTAT_TXFULL     (1<<9)
-#define S3C2410_UFSTAT_RXFULL     (1<<8)
-#define S3C2410_UFSTAT_TXMASK     (15<<4)
-#define S3C2410_UFSTAT_TXSHIFT    (4)
-#define S3C2410_UFSTAT_RXMASK     (15<<0)
-#define S3C2410_UFSTAT_RXSHIFT    (0)
-
-/* UFSTAT S3C2443 same as S3C2440 */
-#define S3C2440_UFSTAT_TXFULL     (1<<14)
-#define S3C2440_UFSTAT_RXFULL     (1<<6)
-#define S3C2440_UFSTAT_TXSHIFT    (8)
-#define S3C2440_UFSTAT_RXSHIFT    (0)
-#define S3C2440_UFSTAT_TXMASK     (63<<8)
-#define S3C2440_UFSTAT_RXMASK     (63)
-
-#define S3C2410_UTRSTAT_TXE       (1<<2)
-#define S3C2410_UTRSTAT_TXFE      (1<<1)
-#define S3C2410_UTRSTAT_RXDR      (1<<0)
-
-#define S3C2410_UERSTAT_OVERRUN   (1<<0)
-#define S3C2410_UERSTAT_FRAME     (1<<2)
-#define S3C2410_UERSTAT_BREAK     (1<<3)
-#define S3C2443_UERSTAT_PARITY    (1<<1)
-
-#define S3C2410_UERSTAT_ANY       (S3C2410_UERSTAT_OVERRUN | \
-                                   S3C2410_UERSTAT_FRAME | \
-                                   S3C2410_UERSTAT_BREAK)
-
-#define S3C2410_UMSTAT_CTS        (1<<0)
-#define S3C2410_UMSTAT_DeltaCTS   (1<<2)
-
-#define S3C2443_DIVSLOT           (0x2C)
-
-/* S3C64XX interrupt registers. */
-#define S3C64XX_UINTP           0x30
-#define S3C64XX_UINTSP          0x34
-#define S3C64XX_UINTM           0x38
-
-#define S3C64XX_UINTM_RXD       (0)
-#define S3C64XX_UINTM_TXD       (2)
-#define S3C64XX_UINTM_RXD_MSK   (1 << S3C64XX_UINTM_RXD)
-#define S3C64XX_UINTM_TXD_MSK   (1 << S3C64XX_UINTM_TXD)
-
-/* Following are specific to S5PV210 */
-#define S5PV210_UCON_CLKMASK    (1<<10)
-#define S5PV210_UCON_CLKSHIFT   (10)
-#define S5PV210_UCON_PCLK       (0<<10)
-#define S5PV210_UCON_UCLK       (1<<10)
-
-#define S5PV210_UFCON_TXTRIG0   (0<<8)
-#define S5PV210_UFCON_TXTRIG4   (1<<8)
-#define S5PV210_UFCON_TXTRIG8   (2<<8)
-#define S5PV210_UFCON_TXTRIG16  (3<<8)
-#define S5PV210_UFCON_TXTRIG32  (4<<8)
-#define S5PV210_UFCON_TXTRIG64  (5<<8)
-#define S5PV210_UFCON_TXTRIG128 (6<<8)
-#define S5PV210_UFCON_TXTRIG256 (7<<8)
-
-#define S5PV210_UFCON_RXTRIG1   (0<<4)
-#define S5PV210_UFCON_RXTRIG4   (1<<4)
-#define S5PV210_UFCON_RXTRIG8   (2<<4)
-#define S5PV210_UFCON_RXTRIG16  (3<<4)
-#define S5PV210_UFCON_RXTRIG32  (4<<4)
-#define S5PV210_UFCON_RXTRIG64  (5<<4)
-#define S5PV210_UFCON_RXTRIG128 (6<<4)
-#define S5PV210_UFCON_RXTRIG256 (7<<4)
-
-#define S5PV210_UFSTAT_TXFULL   (1<<24)
-#define S5PV210_UFSTAT_RXFULL   (1<<8)
-#define S5PV210_UFSTAT_TXMASK   (255<<16)
-#define S5PV210_UFSTAT_TXSHIFT  (16)
-#define S5PV210_UFSTAT_RXMASK   (255<<0)
-#define S5PV210_UFSTAT_RXSHIFT  (0)
-
-#define S3C2410_UCON_CLKSEL0    (1 << 0)
-#define S3C2410_UCON_CLKSEL1    (1 << 1)
-#define S3C2410_UCON_CLKSEL2    (1 << 2)
-#define S3C2410_UCON_CLKSEL3    (1 << 3)
-
-/* Default values for s5pv210 UCON and UFCON uart registers */
-#define S5PV210_UCON_DEFAULT    (S3C2410_UCON_TXILEVEL |        \
-                                 S3C2410_UCON_RXILEVEL |        \
-                                 S3C2410_UCON_TXIRQMODE |       \
-                                 S3C2410_UCON_RXIRQMODE |       \
-                                 S3C2410_UCON_RXFIFO_TOI |      \
-                                 S3C2443_UCON_RXERR_IRQEN)
-
-#define S5PV210_UFCON_DEFAULT   (S3C2410_UFCON_FIFOMODE |       \
-                                 S5PV210_UFCON_TXTRIG4 |        \
-                                 S5PV210_UFCON_RXTRIG4)
-
-#ifndef __ASSEMBLY__
-
-/* configuration structure for per-machine configurations for the
- * serial port
- *
- * the pointer is setup by the machine specific initialisation from the
- * arch/arm/mach-s3c2410/ directory.
-*/
-
-struct s3c2410_uartcfg {
-        unsigned char      hwport;       /* hardware port number */
-        unsigned char      unused;
-        unsigned short     flags;
-        upf_t              uart_flags;   /* default uart flags */
-        unsigned int       clk_sel;
-
-        unsigned int       has_fracval;
-
-        unsigned long      ucon;         /* value of ucon for port */
-        unsigned long      ulcon;        /* value of ulcon for port */
-        unsigned long      ufcon;        /* value of ufcon for port */
-};
-
-/* s3c24xx_uart_devs
- *
- * this is exported from the core as we cannot use driver_register(),
- * or platform_add_device() before the console_initcall()
-*/
-
-extern struct platform_device *s3c24xx_uart_devs[4];
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* __ASM_ARM_REGS_SERIAL_H */
-
+#include <linux/serial_s3c.h>
diff --git a/arch/arm/plat-samsung/include/plat/usb-phy.h b/arch/arm/plat-samsung/include/plat/usb-phy.h
index 959bcdb03a25..ab34dfadb7f9 100644
--- a/arch/arm/plat-samsung/include/plat/usb-phy.h
+++ b/arch/arm/plat-samsung/include/plat/usb-phy.h
@@ -11,10 +11,7 @@
 #ifndef __PLAT_SAMSUNG_USB_PHY_H
 #define __PLAT_SAMSUNG_USB_PHY_H __FILE__
 
-enum s5p_usb_phy_type {
-        S5P_USB_PHY_DEVICE,
-        S5P_USB_PHY_HOST,
-};
+#include <linux/usb/samsung_usb_phy.h>
 
 extern int s5p_usb_phy_init(struct platform_device *pdev, int type);
 extern int s5p_usb_phy_exit(struct platform_device *pdev, int type);
diff --git a/arch/arm/plat-spear/Kconfig b/arch/arm/plat-spear/Kconfig
index 739d016eb273..8a08c31b5e20 100644
--- a/arch/arm/plat-spear/Kconfig
+++ b/arch/arm/plat-spear/Kconfig
@@ -10,7 +10,7 @@ choice
 
 config ARCH_SPEAR13XX
         bool "ST SPEAr13xx with Device Tree"
-        select ARCH_HAVE_CPUFREQ
+        select ARCH_HAS_CPUFREQ
         select ARM_GIC
         select CPU_V7
         select GPIO_SPEAR_SPICS
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fd70a68387eb..9b6d19f74078 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -9,7 +9,6 @@ config ARM64
         select CLONE_BACKWARDS
         select COMMON_CLK
         select GENERIC_CLOCKEVENTS
-        select GENERIC_HARDIRQS_NO_DEPRECATED
         select GENERIC_IOMAP
         select GENERIC_IRQ_PROBE
         select GENERIC_IRQ_SHOW
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 51493430f142..1a6bfe954d49 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -6,17 +6,6 @@ config FRAME_POINTER
         bool
         default y
 
-config DEBUG_ERRORS
-        bool "Verbose kernel error messages"
-        depends on DEBUG_KERNEL
-        help
-          This option controls verbose debugging information which can be
-          printed when the kernel detects an internal error. This debugging
-          information is useful to kernel hackers when tracking down problems,
-          but mostly meaningless to other people. It's safe to say Y unless
-          you are concerned with the code size or don't want to see these
-          messages.
-
 config DEBUG_STACK_USAGE
         bool "Enable stack utilization instrumentation"
         depends on DEBUG_KERNEL
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 9212c7880da7..09bef29f3a09 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -82,4 +82,3 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO=y
 # CONFIG_FTRACE is not set
 CONFIG_ATOMIC64_SELFTEST=y
-CONFIG_DEBUG_ERRORS=y
diff --git a/arch/arm64/include/asm/ucontext.h b/arch/arm64/include/asm/ucontext.h
index bde960720892..42e04c877428 100644
--- a/arch/arm64/include/asm/ucontext.h
+++ b/arch/arm64/include/asm/ucontext.h
@@ -22,7 +22,7 @@ struct ucontext {
         stack_t           uc_stack;
         sigset_t          uc_sigmask;
         /* glibc uses a 1024-bit sigset_t */
-        __u8              __unused[(1024 - sizeof(sigset_t)) / 8];
+        __u8              __unused[1024 / 8 - sizeof(sigset_t)];
         /* last for future expansion */
         struct sigcontext uc_mcontext;
 };
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index cef3925eaf60..aa3e948f7885 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -40,7 +40,9 @@ EXPORT_SYMBOL(__copy_to_user);
 EXPORT_SYMBOL(__clear_user);
 
         /* bitops */
+#ifdef CONFIG_SMP
 EXPORT_SYMBOL(__atomic_hash);
+#endif
 
         /* physical memory */
 EXPORT_SYMBOL(memstart_addr);
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 0337cdb0667b..83a0ad5936a5 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -84,11 +84,15 @@ EXPORT_SYMBOL_GPL(pm_power_off);
 void (*pm_restart)(const char *cmd);
 EXPORT_SYMBOL_GPL(pm_restart);
 
+void arch_cpu_idle_prepare(void)
+{
+        local_fiq_enable();
+}
 
 /*
  * This is our default idle handler.
  */
-static void default_idle(void)
+void arch_cpu_idle(void)
 {
         /*
          * This should do all the clock switching and wait for interrupt
@@ -98,43 +102,6 @@ static void default_idle(void)
         local_irq_enable();
 }
 
-/*
- * The idle thread.
- * We always respect 'hlt_counter' to prevent low power idle.
- */
-void cpu_idle(void)
-{
-        local_fiq_enable();
-
-        /* endless idle loop with no priority at all */
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                while (!need_resched()) {
-                        /*
-                         * We need to disable interrupts here to ensure
-                         * we don't miss a wakeup call.
-                         */
-                        local_irq_disable();
-                        if (!need_resched()) {
-                                stop_critical_timings();
-                                default_idle();
-                                start_critical_timings();
-                                /*
-                                 * default_idle functions should always return
-                                 * with IRQs enabled.
-                                 */
-                                WARN_ON(irqs_disabled());
-                        } else {
-                                local_irq_enable();
-                        }
-                }
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                schedule_preempt_disabled();
-        }
-}
-
 void machine_shutdown(void)
 {
 #ifdef CONFIG_SMP
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 7f4f3673f2bc..e393174fe859 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -549,7 +549,6 @@ int compat_setup_rt_frame(int usig, struct k_sigaction *ka, siginfo_t *info,
                           sigset_t *set, struct pt_regs *regs)
 {
         struct compat_rt_sigframe __user *frame;
-        compat_stack_t stack;
         int err = 0;
 
         frame = compat_get_sigframe(ka, regs, sizeof(*frame));
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index bdd34597254b..261445c4666f 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -216,7 +216,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
         /*
          * OK, it's off to the idle thread for us
          */
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 800aac306a08..f497ca77925a 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -197,24 +197,6 @@ void __init bootmem_init(void)
         max_pfn = max_low_pfn = max;
 }
 
-static inline int free_area(unsigned long pfn, unsigned long end, char *s)
-{
-        unsigned int pages = 0, size = (end - pfn) << (PAGE_SHIFT - 10);
-
-        for (; pfn < end; pfn++) {
-                struct page *page = pfn_to_page(pfn);
-                ClearPageReserved(page);
-                init_page_count(page);
-                __free_page(page);
-                pages++;
-        }
-
-        if (size && s)
-                pr_info("Freeing %s memory: %dK\n", s, size);
-
-        return pages;
-}
-
 /*
  * Poison init memory with an undefined instruction (0x0).
  */
@@ -405,9 +387,7 @@ void __init mem_init(void)
 void free_initmem(void)
 {
         poison_init_mem(__init_begin, __init_end - __init_begin);
-        totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)),
-                                    __phys_to_pfn(__pa(__init_end)),
-                                    "init");
+        free_initmem_default(0);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -418,9 +398,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 {
         if (!keep_initrd) {
                 poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
-                totalram_pages += free_area(__phys_to_pfn(__pa(start)),
-                                            __phys_to_pfn(__pa(end)),
-                                            "initrd");
+                free_reserved_area(start, end, 0, "initrd");
         }
 }
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 224b44ab534e..eeecc9c8ed68 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -261,7 +261,7 @@ static void __init create_mapping(phys_addr_t phys, unsigned long virt,
 void __iomem * __init early_io_map(phys_addr_t phys, unsigned long virt)
 {
         unsigned long size, mask;
-        bool page64k = IS_ENABLED(ARM64_64K_PAGES);
+        bool page64k = IS_ENABLED(CONFIG_ARM64_64K_PAGES);
         pgd_t *pgd;
         pud_t *pud;
         pmd_t *pmd;
@@ -391,17 +391,14 @@ int kern_addr_valid(unsigned long addr)
 }
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 #ifdef CONFIG_ARM64_64K_PAGES
-int __meminit vmemmap_populate(struct page *start_page,
-                               unsigned long size, int node)
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 {
-        return vmemmap_populate_basepages(start_page, size, node);
+        return vmemmap_populate_basepages(start, end, node);
 }
 #else   /* !CONFIG_ARM64_64K_PAGES */
-int __meminit vmemmap_populate(struct page *start_page,
-                               unsigned long size, int node)
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 {
-        unsigned long addr = (unsigned long)start_page;
-        unsigned long end = (unsigned long)(start_page + size);
+        unsigned long addr = start;
         unsigned long next;
         pgd_t *pgd;
         pud_t *pud;
@@ -434,7 +431,7 @@ int __meminit vmemmap_populate(struct page *start_page,
         return 0;
 }
 #endif  /* CONFIG_ARM64_64K_PAGES */
-void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+void vmemmap_free(unsigned long start, unsigned long end)
 {
 }
 #endif  /* CONFIG_SPARSEMEM_VMEMMAP */
diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index 9b89257b2cfd..c1a868d398bd 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -7,7 +7,7 @@ config AVR32
         select HAVE_OPROFILE
         select HAVE_KPROBES
         select HAVE_GENERIC_HARDIRQS
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select GENERIC_IRQ_PROBE
         select GENERIC_ATOMIC64
         select HARDIRQS_SW_RESEND
diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h
index cf60d0a9f176..fc6483f83ccc 100644
--- a/arch/avr32/include/asm/io.h
+++ b/arch/avr32/include/asm/io.h
@@ -165,6 +165,10 @@ BUILDIO_IOPORT(l, u32)
 #define readw_be                        __raw_readw
 #define readl_be                        __raw_readl
 
+#define writeb_relaxed                  writeb
+#define writew_relaxed                  writew
+#define writel_relaxed                  writel
+
 #define writeb_be                       __raw_writeb
 #define writew_be                       __raw_writew
 #define writel_be                       __raw_writel
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index fd78f58ea79a..073c3c2fa521 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -30,18 +30,9 @@ EXPORT_SYMBOL(pm_power_off);
  * This file handles the architecture-dependent parts of process handling..
  */
 
-void cpu_idle(void)
+void arch_cpu_idle(void)
 {
-        /* endless idle loop with no priority at all */
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                while (!need_resched())
-                        cpu_idle_sleep();
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                schedule_preempt_disabled();
-        }
+        cpu_enter_idle();
 }
 
 void machine_halt(void)
diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c
index 05ad29112ff4..869a1c6ffeee 100644
--- a/arch/avr32/kernel/time.c
+++ b/arch/avr32/kernel/time.c
@@ -12,6 +12,7 @@
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/time.h>
+#include <linux/cpu.h>
 
 #include <asm/sysreg.h>
 
@@ -87,13 +88,17 @@ static void comparator_mode(enum clock_event_mode mode,
                 pr_debug("%s: start\n", evdev->name);
                 /* FALLTHROUGH */
         case CLOCK_EVT_MODE_RESUME:
-                cpu_disable_idle_sleep();
+                /*
+                 * If we're using the COUNT and COMPARE registers we
+                 * need to force idle poll.
+                 */
+                cpu_idle_poll_ctrl(true);
                 break;
         case CLOCK_EVT_MODE_UNUSED:
         case CLOCK_EVT_MODE_SHUTDOWN:
                 sysreg_write(COMPARE, 0);
                 pr_debug("%s: stop\n", evdev->name);
-                cpu_enable_idle_sleep();
+                cpu_idle_poll_ctrl(false);
                 break;
         default:
                 BUG();
diff --git a/arch/avr32/mach-at32ap/include/mach/pm.h b/arch/avr32/mach-at32ap/include/mach/pm.h
index 979b355b77b6..f29ff2cd23d3 100644
--- a/arch/avr32/mach-at32ap/include/mach/pm.h
+++ b/arch/avr32/mach-at32ap/include/mach/pm.h
@@ -21,30 +21,6 @@
 extern void cpu_enter_idle(void);
 extern void cpu_enter_standby(unsigned long sdramc_base);
 
-extern bool disable_idle_sleep;
-
-static inline void cpu_disable_idle_sleep(void)
-{
-        disable_idle_sleep = true;
-}
-
-static inline void cpu_enable_idle_sleep(void)
-{
-        disable_idle_sleep = false;
-}
-
-static inline void cpu_idle_sleep(void)
-{
-        /*
-         * If we're using the COUNT and COMPARE registers for
-         * timekeeping, we can't use the IDLE state.
-         */
-        if (disable_idle_sleep)
-                cpu_relax();
-        else
-                cpu_enter_idle();
-}
-
 void intc_set_suspend_handler(unsigned long offset);
 #endif
 
diff --git a/arch/avr32/mach-at32ap/pm-at32ap700x.S b/arch/avr32/mach-at32ap/pm-at32ap700x.S
index f868f4ce761b..1c8e4e6bff03 100644
--- a/arch/avr32/mach-at32ap/pm-at32ap700x.S
+++ b/arch/avr32/mach-at32ap/pm-at32ap700x.S
@@ -18,13 +18,6 @@
 /* Same as 0xfff00000 but fits in a 21 bit signed immediate */
 #define PM_BASE -0x100000
 
-        .section .bss, "wa", @nobits
-        .global disable_idle_sleep
-        .type   disable_idle_sleep, @object
-disable_idle_sleep:
-        .int    4
-        .size   disable_idle_sleep, . - disable_idle_sleep
-
         /* Keep this close to the irq handlers */
         .section .irq.text, "ax", @progbits
 
diff --git a/arch/avr32/mm/init.c b/arch/avr32/mm/init.c
index 2798c2d4a1cf..e66e8406f992 100644
--- a/arch/avr32/mm/init.c
+++ b/arch/avr32/mm/init.c
@@ -146,34 +146,14 @@ void __init mem_init(void)
                 initsize >> 10);
 }
 
-static inline void free_area(unsigned long addr, unsigned long end, char *s)
-{
-        unsigned int size = (end - addr) >> 10;
-
-        for (; addr < end; addr += PAGE_SIZE) {
-                struct page *page = virt_to_page(addr);
-                ClearPageReserved(page);
-                init_page_count(page);
-                free_page(addr);
-                totalram_pages++;
-        }
-
-        if (size && s)
-                printk(KERN_INFO "Freeing %s memory: %dK (%lx - %lx)\n",
-                       s, size, end - (size << 10), end);
-}
-
 void free_initmem(void)
 {
-        free_area((unsigned long)__init_begin, (unsigned long)__init_end,
-                  "init");
+        free_initmem_default(0);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        free_area(start, end, "initrd");
+        free_reserved_area(start, end, 0, "initrd");
 }
-
 #endif
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index 600494c70e96..c3f2e0bc644a 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -33,7 +33,7 @@ config BLACKFIN
         select ARCH_HAVE_CUSTOM_GPIO_H
         select ARCH_WANT_OPTIONAL_GPIOLIB
         select HAVE_UID16
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select ARCH_WANT_IPC_PARSE_VERSION
         select HAVE_GENERIC_HARDIRQS
         select GENERIC_ATOMIC64
diff --git a/arch/blackfin/include/asm/bfin_sport3.h b/arch/blackfin/include/asm/bfin_sport3.h
index 03c00220d69b..d82f5fa0ad9f 100644
--- a/arch/blackfin/include/asm/bfin_sport3.h
+++ b/arch/blackfin/include/asm/bfin_sport3.h
@@ -41,7 +41,7 @@
 #define SPORT_CTL_LAFS                0x00020000    /* Late Transmit frame select */
 #define SPORT_CTL_RJUST               0x00040000    /* Right Justified mode select */
 #define SPORT_CTL_FSED                0x00080000    /* External frame sync edge select */
-#define SPORT_CTL_TFIEN               0x00100000    /* Transmit finish interrrupt enable select */
+#define SPORT_CTL_TFIEN               0x00100000    /* Transmit finish interrupt enable select */
 #define SPORT_CTL_GCLKEN              0x00200000    /* Gated clock mode select */
 #define SPORT_CTL_SPENSEC             0x01000000    /* Enable secondary channel */
 #define SPORT_CTL_SPTRAN              0x02000000    /* Data direction control */
diff --git a/arch/blackfin/kernel/early_printk.c b/arch/blackfin/kernel/early_printk.c
index 84ed8375113c..61fbd2de993d 100644
--- a/arch/blackfin/kernel/early_printk.c
+++ b/arch/blackfin/kernel/early_printk.c
@@ -25,8 +25,6 @@ extern struct console *bfin_earlyserial_init(unsigned int port,
 extern struct console *bfin_jc_early_init(void);
 #endif
 
-static struct console *early_console;
-
 /* Default console */
 #define DEFAULT_PORT 0
 #define DEFAULT_CFLAG CS8|B57600
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 9782c0329c14..4aa5545c4fde 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -46,15 +46,14 @@ EXPORT_SYMBOL(pm_power_off);
  * The idle loop on BFIN
  */
 #ifdef CONFIG_IDLE_L1
-static void default_idle(void)__attribute__((l1_text));
-void cpu_idle(void)__attribute__((l1_text));
+void arch_cpu_idle(void)__attribute__((l1_text));
 #endif
 
 /*
  * This is our default idle handler.  We need to disable
  * interrupts here to ensure we don't miss a wakeup call.
  */
-static void default_idle(void)
+void arch_cpu_idle(void)
 {
 #ifdef CONFIG_IPIPE
         ipipe_suspend_domain();
@@ -66,31 +65,12 @@ static void default_idle(void)
         hard_local_irq_enable();
 }
 
-/*
- * The idle thread.  We try to conserve power, while trying to keep
- * overall latency low.  The architecture specific idle is passed
- * a value to indicate the level of "idleness" of the system.
- */
-void cpu_idle(void)
-{
-        /* endless idle loop with no priority at all */
-        while (1) {
-
 #ifdef CONFIG_HOTPLUG_CPU
-                if (cpu_is_offline(smp_processor_id()))
-                        cpu_die();
-#endif
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                while (!need_resched())
-                        default_idle();
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                preempt_enable_no_resched();
-                schedule();
-                preempt_disable();
-        }
+void arch_cpu_idle_dead(void)
+{
+        cpu_die();
 }
+#endif
 
 /*
  * Do necessary setup to start up a newly executed thread.
diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c
index 61c1f47a4bf2..97d701639585 100644
--- a/arch/blackfin/mach-bf609/boards/ezkit.c
+++ b/arch/blackfin/mach-bf609/boards/ezkit.c
@@ -936,19 +936,19 @@ static struct v4l2_input adv7842_inputs[] = {
                 .index = 2,
                 .name = "Component",
                 .type = V4L2_INPUT_TYPE_CAMERA,
-                .capabilities = V4L2_IN_CAP_CUSTOM_TIMINGS,
+                .capabilities = V4L2_IN_CAP_DV_TIMINGS,
         },
         {
                 .index = 3,
                 .name = "VGA",
                 .type = V4L2_INPUT_TYPE_CAMERA,
-                .capabilities = V4L2_IN_CAP_CUSTOM_TIMINGS,
+                .capabilities = V4L2_IN_CAP_DV_TIMINGS,
         },
         {
                 .index = 4,
                 .name = "HDMI",
                 .type = V4L2_INPUT_TYPE_CAMERA,
-                .capabilities = V4L2_IN_CAP_CUSTOM_TIMINGS,
+                .capabilities = V4L2_IN_CAP_DV_TIMINGS,
         },
 };
 
@@ -1074,7 +1074,7 @@ static struct v4l2_output adv7511_outputs[] = {
                 .index = 0,
                 .name = "HDMI",
                 .type = V4L2_INPUT_TYPE_CAMERA,
-                .capabilities = V4L2_OUT_CAP_CUSTOM_TIMINGS,
+                .capabilities = V4L2_OUT_CAP_DV_TIMINGS,
         },
 };
 
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index bb61ae4986e4..1bc2ce6f3c94 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -335,7 +335,7 @@ void __cpuinit secondary_start_kernel(void)
          */
         calibrate_delay();
 
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 void __init smp_prepare_boot_cpu(void)
diff --git a/arch/blackfin/mm/init.c b/arch/blackfin/mm/init.c
index 9cb85537bd2b..82d01a71207f 100644
--- a/arch/blackfin/mm/init.c
+++ b/arch/blackfin/mm/init.c
@@ -103,7 +103,7 @@ void __init mem_init(void)
         max_mapnr = num_physpages = MAP_NR(high_memory);
         printk(KERN_DEBUG "Kernel managed physical pages: %lu\n", num_physpages);
 
-        /* This will put all memory onto the freelists. */
+        /* This will put all low memory onto the freelists. */
         totalram_pages = free_all_bootmem();
 
         reservedpages = 0;
@@ -129,24 +129,11 @@ void __init mem_init(void)
                 initk, codek, datak, DMA_UNCACHED_REGION >> 10, (reservedpages << (PAGE_SHIFT-10)));
 }
 
-static void __init free_init_pages(const char *what, unsigned long begin, unsigned long end)
-{
-        unsigned long addr;
-        /* next to check that the page we free is not a partial page */
-        for (addr = begin; addr + PAGE_SIZE <= end; addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-        printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
-}
-
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
 #ifndef CONFIG_MPU
-        free_init_pages("initrd memory", start, end);
+        free_reserved_area(start, end, 0, "initrd");
 #endif
 }
 #endif
@@ -154,10 +141,7 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 void __init_refok free_initmem(void)
 {
 #if defined CONFIG_RAMKERNEL && !defined CONFIG_MPU
-        free_init_pages("unused kernel memory",
-                        (unsigned long)(&__init_begin),
-                        (unsigned long)(&__init_end));
-
+        free_initmem_default(0);
         if (memory_start == (unsigned long)(&__init_end))
                 memory_start = (unsigned long)(&__init_begin);
 #endif
diff --git a/arch/c6x/include/asm/irqflags.h b/arch/c6x/include/asm/irqflags.h
index cf78e09e18c3..2c71d5634ec2 100644
--- a/arch/c6x/include/asm/irqflags.h
+++ b/arch/c6x/include/asm/irqflags.h
@@ -27,7 +27,7 @@ static inline unsigned long arch_local_save_flags(void)
 /* set interrupt enabled status */
 static inline void arch_local_irq_restore(unsigned long flags)
 {
-        asm volatile (" mvc .s2 %0,CSR\n" : : "b"(flags));
+        asm volatile (" mvc .s2 %0,CSR\n" : : "b"(flags) : "memory");
 }
 
 /* unconditionally enable interrupts */
diff --git a/arch/c6x/kernel/process.c b/arch/c6x/kernel/process.c
index 6434df476f77..57d2ea8d1977 100644
--- a/arch/c6x/kernel/process.c
+++ b/arch/c6x/kernel/process.c
@@ -33,7 +33,7 @@ extern asmlinkage void ret_from_kernel_thread(void);
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
 
-static void c6x_idle(void)
+void arch_cpu_idle(void)
 {
         unsigned long tmp;
 
@@ -49,32 +49,6 @@ static void c6x_idle(void)
                       : "=b"(tmp));
 }
 
-/*
- * The idle loop for C64x
- */
-void cpu_idle(void)
-{
-        /* endless idle loop with no priority at all */
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                while (1) {
-                        local_irq_disable();
-                        if (need_resched()) {
-                                local_irq_enable();
-                                break;
-                        }
-                        c6x_idle(); /* enables local irqs */
-                }
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-
-                preempt_enable_no_resched();
-                schedule();
-                preempt_disable();
-        }
-}
-
 static void halt_loop(void)
 {
         printk(KERN_EMERG "System Halted, OK to turn off power\n");
diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c
index 89395f09648a..a9fcd89b251b 100644
--- a/arch/c6x/mm/init.c
+++ b/arch/c6x/mm/init.c
@@ -77,37 +77,11 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-        int pages = 0;
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page(start);
-                totalram_pages++;
-                pages++;
-        }
-        printk(KERN_INFO "Freeing initrd memory: %luk freed\n",
-               (pages * PAGE_SIZE) >> 10);
+        free_reserved_area(start, end, 0, "initrd");
 }
 #endif
 
 void __init free_initmem(void)
 {
-        unsigned long addr;
-
-        /*
-         * The following code should be cool even if these sections
-         * are not page aligned.
-         */
-        addr = PAGE_ALIGN((unsigned long)(__init_begin));
-
-        /* next to check that the page we free is not a partial page */
-        for (; addr + PAGE_SIZE < (unsigned long)(__init_end);
-             addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-        printk(KERN_INFO "Freeing unused kernel memory: %dK freed\n",
-               (int) ((addr - PAGE_ALIGN((long) &__init_begin)) >> 10));
+        free_initmem_default(0);
 }
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index bb0ac66cf533..06dd026533e3 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -43,7 +43,7 @@ config CRIS
         select GENERIC_ATOMIC64
         select HAVE_GENERIC_HARDIRQS
         select HAVE_UID16
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select ARCH_WANT_IPC_PARSE_VERSION
         select GENERIC_IRQ_SHOW
         select GENERIC_IOMAP
diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c
index b1018750cffb..2ba23c13df68 100644
--- a/arch/cris/arch-v10/kernel/process.c
+++ b/arch/cris/arch-v10/kernel/process.c
@@ -30,8 +30,9 @@ void etrax_gpio_wake_up_check(void); /* drivers/gpio.c */
 void default_idle(void)
 {
 #ifdef CONFIG_ETRAX_GPIO
-  etrax_gpio_wake_up_check();
+        etrax_gpio_wake_up_check();
 #endif
+        local_irq_enable();
 }
 
 /*
diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c
index 2b23ef0e4452..57451faa9b20 100644
--- a/arch/cris/arch-v32/kernel/process.c
+++ b/arch/cris/arch-v32/kernel/process.c
@@ -20,18 +20,12 @@
 
 extern void stop_watchdog(void);
 
-extern int cris_hlt_counter;
-
 /* We use this if we don't have any better idle routine. */
 void default_idle(void)
 {
-        local_irq_disable();
-        if (!need_resched() && !cris_hlt_counter) {
-                /* Halt until exception. */
-                __asm__ volatile("ei    \n\t"
-                                 "halt      ");
-        }
-        local_irq_enable();
+        /* Halt until exception. */
+        __asm__ volatile("ei    \n\t"
+                         "halt      ");
 }
 
 /*
diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c
index 04a16edd5401..cdd12028de0c 100644
--- a/arch/cris/arch-v32/kernel/smp.c
+++ b/arch/cris/arch-v32/kernel/smp.c
@@ -145,8 +145,6 @@ smp_boot_one_cpu(int cpuid, struct task_struct idle)
  * specific stuff such as the local timer and the MMU. */
 void __init smp_callin(void)
 {
-        extern void cpu_idle(void);
-
         int cpu = cpu_now_booting;
         reg_intr_vect_rw_mask vect_mask = {0};
 
@@ -170,7 +168,7 @@ void __init smp_callin(void)
         local_irq_enable();
 
         set_cpu_online(cpu, true);
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 /* Stop execution on this CPU.*/
diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h
index 675823f70c0f..c0a29b96b92b 100644
--- a/arch/cris/include/asm/processor.h
+++ b/arch/cris/include/asm/processor.h
@@ -65,13 +65,6 @@ static inline void release_thread(struct task_struct *dead_task)
 
 #define cpu_relax()     barrier()
 
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-void disable_hlt(void);
-void enable_hlt(void);
-
 void default_idle(void);
 
 #endif /* __ASM_CRIS_PROCESSOR_H */
diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c
index 104ff4dd9b98..b78498eb079b 100644
--- a/arch/cris/kernel/process.c
+++ b/arch/cris/kernel/process.c
@@ -29,59 +29,14 @@
 
 //#define DEBUG
 
-/*
- * The hlt_counter, disable_hlt and enable_hlt is just here as a hook if
- * there would ever be a halt sequence (for power save when idle) with
- * some largish delay when halting or resuming *and* a driver that can't
- * afford that delay.  The hlt_counter would then be checked before
- * executing the halt sequence, and the driver marks the unhaltable
- * region by enable_hlt/disable_hlt.
- */
-
-int cris_hlt_counter=0;
-
-void disable_hlt(void)
-{
-        cris_hlt_counter++;
-}
-
-EXPORT_SYMBOL(disable_hlt);
-
-void enable_hlt(void)
-{
-        cris_hlt_counter--;
-}
-
-EXPORT_SYMBOL(enable_hlt);
- 
 extern void default_idle(void);
 
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
 
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-
-void cpu_idle (void)
+void arch_cpu_idle(void)
 {
-        /* endless idle loop with no priority at all */
-        while (1) {
-                rcu_idle_enter();
-                while (!need_resched()) {
-                        /*
-                         * Mark this as an RCU critical section so that
-                         * synchronize_kernel() in the unload path waits
-                         * for our completion.
-                         */
-                        default_idle();
-                }
-                rcu_idle_exit();
-                schedule_preempt_disabled();
-        }
+        default_idle();
 }
 
 void hard_reset_now (void);
diff --git a/arch/cris/mm/init.c b/arch/cris/mm/init.c
index d72ab58fd83e..9ac80946dada 100644
--- a/arch/cris/mm/init.c
+++ b/arch/cris/mm/init.c
@@ -12,12 +12,10 @@
 #include <linux/init.h>
 #include <linux/bootmem.h>
 #include <asm/tlb.h>
+#include <asm/sections.h>
 
 unsigned long empty_zero_page;
 
-extern char _stext, _edata, _etext; /* From linkerscript */
-extern char __init_begin, __init_end;
-
 void __init
 mem_init(void)
 {
@@ -67,15 +65,5 @@ mem_init(void)
 void 
 free_initmem(void)
 {
-        unsigned long addr;
-
-        addr = (unsigned long)(&__init_begin);
-        for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-        printk (KERN_INFO "Freeing unused kernel memory: %luk freed\n",
-                (unsigned long)((&__init_end - &__init_begin) >> 10));
+        free_initmem_default(0);
 }
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index 12369b194c7b..2ce731f9aa4d 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -6,7 +6,7 @@ config FRV
         select HAVE_PERF_EVENTS
         select HAVE_UID16
         select HAVE_GENERIC_HARDIRQS
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select GENERIC_IRQ_SHOW
         select HAVE_DEBUG_BUGVERBOSE
         select ARCH_HAVE_NMI_SAFE_CMPXCHG
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index 23916b2a12a2..5d40aeb7712e 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -59,29 +59,12 @@ static void core_sleep_idle(void)
         mb();
 }
 
-void (*idle)(void) = core_sleep_idle;
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
+void arch_cpu_idle(void)
 {
-        /* endless idle loop with no priority at all */
-        while (1) {
-                rcu_idle_enter();
-                while (!need_resched()) {
-                        check_pgt_cache();
-
-                        if (!frv_dma_inprogress && idle)
-                                idle();
-                }
-                rcu_idle_exit();
-
-                schedule_preempt_disabled();
-        }
+        if (!frv_dma_inprogress)
+                core_sleep_idle();
+        else
+                local_irq_enable();
 }
 
 void machine_restart(char * __unused)
diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c
index 92e97b0894a6..dee354fa6b64 100644
--- a/arch/frv/mm/init.c
+++ b/arch/frv/mm/init.c
@@ -122,7 +122,7 @@ void __init mem_init(void)
 #endif
         int codek = 0, datak = 0;
 
-        /* this will put all memory onto the freelists */
+        /* this will put all low memory onto the freelists */
         totalram_pages = free_all_bootmem();
 
 #ifdef CONFIG_MMU
@@ -131,14 +131,8 @@ void __init mem_init(void)
                         datapages++;
 
 #ifdef CONFIG_HIGHMEM
-        for (pfn = num_physpages - 1; pfn >= num_mappedpages; pfn--) {
-                struct page *page = &mem_map[pfn];
-
-                ClearPageReserved(page);
-                init_page_count(page);
-                __free_page(page);
-                totalram_pages++;
-        }
+        for (pfn = num_physpages - 1; pfn >= num_mappedpages; pfn--)
+                free_highmem_page(&mem_map[pfn]);
 #endif
 
         codek = ((unsigned long) &_etext - (unsigned long) &_stext) >> 10;
@@ -168,21 +162,7 @@ void __init mem_init(void)
 void free_initmem(void)
 {
 #if defined(CONFIG_RAMKERNEL) && !defined(CONFIG_PROTECT_KERNEL)
-        unsigned long start, end, addr;
-
-        start = PAGE_ALIGN((unsigned long) &__init_begin);      /* round up */
-        end   = ((unsigned long) &__init_end) & PAGE_MASK;      /* round down */
-
-        /* next to check that the page we free is not a partial page */
-        for (addr = start; addr < end; addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-
-        printk("Freeing unused kernel memory: %ldKiB freed (0x%lx - 0x%lx)\n",
-               (end - start) >> 10, start, end);
+        free_initmem_default(0);
 #endif
 } /* end free_initmem() */
 
@@ -193,14 +173,6 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-        int pages = 0;
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page(start);
-                totalram_pages++;
-                pages++;
-        }
-        printk("Freeing initrd memory: %dKiB freed\n", (pages * PAGE_SIZE) >> 10);
+        free_reserved_area(start, end, 0, "initrd");
 } /* end free_initrd_mem() */
 #endif
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index ae8551eb3736..79250de1b12a 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -5,7 +5,7 @@ config H8300
         select HAVE_GENERIC_HARDIRQS
         select GENERIC_ATOMIC64
         select HAVE_UID16
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select ARCH_WANT_IPC_PARSE_VERSION
         select GENERIC_IRQ_SHOW
         select GENERIC_CPU_DEVICES
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index b609f63f1590..a17d2cd463d2 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -53,40 +53,13 @@ asmlinkage void ret_from_kernel_thread(void);
  * The idle loop on an H8/300..
  */
 #if !defined(CONFIG_H8300H_SIM) && !defined(CONFIG_H8S_SIM)
-static void default_idle(void)
+void arch_cpu_idle(void)
 {
-        local_irq_disable();
-        if (!need_resched()) {
-                local_irq_enable();
-                /* XXX: race here! What if need_resched() gets set now? */
-                __asm__("sleep");
-        } else
-                local_irq_enable();
-}
-#else
-static void default_idle(void)
-{
-        cpu_relax();
+        local_irq_enable();
+        /* XXX: race here! What if need_resched() gets set now? */
+        __asm__("sleep");
 }
 #endif
-void (*idle)(void) = default_idle;
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
-{
-        while (1) {
-                rcu_idle_enter();
-                while (!need_resched())
-                        idle();
-                rcu_idle_exit();
-                schedule_preempt_disabled();
-        }
-}
 
 void machine_restart(char * __unused)
 {
diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c
index 981e25094b1a..ff349d70a29b 100644
--- a/arch/h8300/mm/init.c
+++ b/arch/h8300/mm/init.c
@@ -139,7 +139,7 @@ void __init mem_init(void)
         start_mem = PAGE_ALIGN(start_mem);
         max_mapnr = num_physpages = MAP_NR(high_memory);
 
-        /* this will put all memory onto the freelists */
+        /* this will put all low memory onto the freelists */
         totalram_pages = free_all_bootmem();
 
         codek = (_etext - _stext) >> 10;
@@ -161,15 +161,7 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        int pages = 0;
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page(start);
-                totalram_pages++;
-                pages++;
-        }
-        printk ("Freeing initrd memory: %dk freed\n", pages);
+        free_reserved_area(start, end, 0, "initrd");
 }
 #endif
 
@@ -177,23 +169,7 @@ void
 free_initmem(void)
 {
 #ifdef CONFIG_RAMKERNEL
-        unsigned long addr;
-/*
- *      the following code should be cool even if these sections
- *      are not page aligned.
- */
-        addr = PAGE_ALIGN((unsigned long)(__init_begin));
-        /* next to check that the page we free is not a partial page */
-        for (; addr + PAGE_SIZE < (unsigned long)__init_end; addr +=PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-        printk(KERN_INFO "Freeing unused kernel memory: %ldk freed (0x%x - 0x%x)\n",
-                        (addr - PAGE_ALIGN((long) __init_begin)) >> 10,
-                        (int)(PAGE_ALIGN((unsigned long)__init_begin)),
-                        (int)(addr - PAGE_SIZE));
+        free_initmem_default(0);
 #endif
 }
 
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index 06ae9ffcabd5..9b948c619a03 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -51,28 +51,11 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
  *  If hardware or VM offer wait termination even though interrupts
  *  are disabled.
  */
-static void default_idle(void)
+void arch_cpu_idle(void)
 {
         __vmwait();
-}
-
-void (*idle_sleep)(void) = default_idle;
-
-void cpu_idle(void)
-{
-        while (1) {
-                tick_nohz_idle_enter();
-                local_irq_disable();
-                while (!need_resched()) {
-                        idle_sleep();
-                        /*  interrupts wake us up, but aren't serviced  */
-                        local_irq_enable();     /* service interrupt   */
-                        local_irq_disable();
-                }
-                local_irq_enable();
-                tick_nohz_idle_exit();
-                schedule();
-        }
+        /*  interrupts wake us up, but irqs are still disabled */
+        local_irq_enable();
 }
 
 /*
diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c
index 8e095dffd070..0e364ca43198 100644
--- a/arch/hexagon/kernel/smp.c
+++ b/arch/hexagon/kernel/smp.c
@@ -184,7 +184,7 @@ void __cpuinit start_secondary(void)
 
         local_irq_enable();
 
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 33f3fdc0b214..e7e55a00f94f 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -26,7 +26,7 @@ config IA64
         select HAVE_MEMBLOCK
         select HAVE_MEMBLOCK_NODE_MAP
         select HAVE_VIRT_CPU_ACCOUNTING
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select ARCH_DISCARD_MEMBLOCK
         select GENERIC_IRQ_PROBE
         select GENERIC_PENDING_IRQ if SMP
@@ -187,7 +187,7 @@ config IA64_DIG
 
 config IA64_DIG_VTD
         bool "DIG+Intel+IOMMU"
-        select DMAR
+        select INTEL_IOMMU
         select PCI_MSI
 
 config IA64_HP_ZX1
diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c
index da2f319fb71d..e70cadec7ce6 100644
--- a/arch/ia64/hp/sim/simserial.c
+++ b/arch/ia64/hp/sim/simserial.c
@@ -142,8 +142,7 @@ static void transmit_chars(struct tty_struct *tty, struct serial_state *info,
                 goto out;
         }
 
-        if (info->xmit.head == info->xmit.tail || tty->stopped ||
-                        tty->hw_stopped) {
+        if (info->xmit.head == info->xmit.tail || tty->stopped) {
 #ifdef SIMSERIAL_DEBUG
                 printk("transmit_chars: head=%d, tail=%d, stopped=%d\n",
                        info->xmit.head, info->xmit.tail, tty->stopped);
@@ -181,7 +180,7 @@ static void rs_flush_chars(struct tty_struct *tty)
         struct serial_state *info = tty->driver_data;
 
         if (info->xmit.head == info->xmit.tail || tty->stopped ||
-                        tty->hw_stopped || !info->xmit.buf)
+                        !info->xmit.buf)
                 return;
 
         transmit_chars(tty, info, NULL);
@@ -217,7 +216,7 @@ static int rs_write(struct tty_struct * tty,
          * Hey, we transmit directly from here in our case
          */
         if (CIRC_CNT(info->xmit.head, info->xmit.tail, SERIAL_XMIT_SIZE) &&
-                        !tty->stopped && !tty->hw_stopped)
+                        !tty->stopped)
                 transmit_chars(tty, info, NULL);
 
         return ret;
@@ -325,14 +324,6 @@ static int rs_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg)
 
 #define RELEVANT_IFLAG(iflag) (iflag & (IGNBRK|BRKINT|IGNPAR|PARMRK|INPCK))
 
-static void rs_set_termios(struct tty_struct *tty, struct ktermios *old_termios)
-{
-        /* Handle turning off CRTSCTS */
-        if ((old_termios->c_cflag & CRTSCTS) &&
-            !(tty->termios.c_cflag & CRTSCTS)) {
-                tty->hw_stopped = 0;
-        }
-}
 /*
  * This routine will shutdown a serial port; interrupts are disabled, and
  * DTR is dropped if the hangup on close termio flag is on.
@@ -481,7 +472,6 @@ static const struct tty_operations hp_ops = {
         .throttle = rs_throttle,
         .unthrottle = rs_unthrottle,
         .send_xchar = rs_send_xchar,
-        .set_termios = rs_set_termios,
         .hangup = rs_hangup,
         .proc_fops = &rs_proc_fops,
 };
diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h
index d2bf1fd5e44f..76acbcd5c060 100644
--- a/arch/ia64/include/asm/futex.h
+++ b/arch/ia64/include/asm/futex.h
@@ -106,16 +106,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
                 return -EFAULT;
 
         {
-                register unsigned long r8 __asm ("r8");
+                register unsigned long r8 __asm ("r8") = 0;
                 unsigned long prev;
                 __asm__ __volatile__(
                         "       mf;;                                    \n"
-                        "       mov %0=r0                               \n"
                         "       mov ar.ccv=%4;;                         \n"
                         "[1:]   cmpxchg4.acq %1=[%2],%3,ar.ccv          \n"
                         "       .xdata4 \"__ex_table\", 1b-., 2f-.      \n"
                         "[2:]"
-                        : "=r" (r8), "=r" (prev)
+                        : "+r" (r8), "=&r" (prev)
                         : "r" (uaddr), "r" (newval),
                           "rO" ((long) (unsigned) oldval)
                         : "memory");
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index 94eaa5bd5d0c..aa910054b8e7 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -2,6 +2,7 @@
 #define _ASM_IA64_HUGETLB_H
 
 #include <asm/page.h>
+#include <asm-generic/hugetlb.h>
 
 
 void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
diff --git a/arch/ia64/include/asm/irqflags.h b/arch/ia64/include/asm/irqflags.h
index 2b68d856dc78..1bf2cf2f4ab4 100644
--- a/arch/ia64/include/asm/irqflags.h
+++ b/arch/ia64/include/asm/irqflags.h
@@ -89,6 +89,7 @@ static inline bool arch_irqs_disabled(void)
 
 static inline void arch_safe_halt(void)
 {
+        arch_local_irq_enable();
         ia64_pal_halt_light();  /* PAL_HALT_LIGHT */
 }
 
diff --git a/arch/ia64/include/asm/mca.h b/arch/ia64/include/asm/mca.h
index 43f96ab18fa0..8c7096168716 100644
--- a/arch/ia64/include/asm/mca.h
+++ b/arch/ia64/include/asm/mca.h
@@ -143,6 +143,7 @@ extern unsigned long __per_cpu_mca[NR_CPUS];
 extern int cpe_vector;
 extern int ia64_cpe_irq;
 extern void ia64_mca_init(void);
+extern void ia64_mca_irq_init(void);
 extern void ia64_mca_cpu_init(void *);
 extern void ia64_os_mca_dispatch(void);
 extern void ia64_os_mca_dispatch_end(void);
diff --git a/arch/ia64/include/asm/numa.h b/arch/ia64/include/asm/numa.h
index 2e27ef175652..2db0a6c6daa5 100644
--- a/arch/ia64/include/asm/numa.h
+++ b/arch/ia64/include/asm/numa.h
@@ -67,14 +67,13 @@ extern int paddr_to_nid(unsigned long paddr);
 
 extern void map_cpu_to_node(int cpu, int nid);
 extern void unmap_cpu_from_node(int cpu, int nid);
-
+extern void numa_clear_node(int cpu);
 
 #else /* !CONFIG_NUMA */
 #define map_cpu_to_node(cpu, nid)       do{}while(0)
 #define unmap_cpu_from_node(cpu, nid)   do{}while(0)
-
 #define paddr_to_nid(addr)      0
-
+#define numa_clear_node(cpu)    do { } while (0)
 #endif /* CONFIG_NUMA */
 
 #endif /* _ASM_IA64_NUMA_H */
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index 020d655ed082..cade13dd0299 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -131,8 +131,6 @@ struct thread_info {
 #define TS_POLLING              1       /* true if in idle loop and not sleeping */
 #define TS_RESTORE_SIGMASK      2       /* restore signal mask in do_signal() */
 
-#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
-
 #ifndef __ASSEMBLY__
 #define HAVE_SET_RESTORE_SIGMASK        1
 static inline void set_restore_sigmask(void)
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index c4cd45d97749..abc6dee3799c 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -90,53 +90,6 @@ ENTRY(fsys_getpid)
         FSYS_RETURN
 END(fsys_getpid)
 
-ENTRY(fsys_getppid)
-        .prologue
-        .altrp b6
-        .body
-        add r17=IA64_TASK_GROUP_LEADER_OFFSET,r16
-        ;;
-        ld8 r17=[r17]                           // r17 = current->group_leader
-        add r9=TI_FLAGS+IA64_TASK_SIZE,r16
-        ;;
-
-        ld4 r9=[r9]
-        add r17=IA64_TASK_REAL_PARENT_OFFSET,r17 // r17 = &current->group_leader->real_parent
-        ;;
-        and r9=TIF_ALLWORK_MASK,r9
-
-1:      ld8 r18=[r17]                           // r18 = current->group_leader->real_parent
-        ;;
-        cmp.ne p8,p0=0,r9
-        add r8=IA64_TASK_TGID_OFFSET,r18        // r8 = &current->group_leader->real_parent->tgid
-        ;;
-
-        /*
-         * The .acq is needed to ensure that the read of tgid has returned its data before
-         * we re-check "real_parent".
-         */
-        ld4.acq r8=[r8]                         // r8 = current->group_leader->real_parent->tgid
-#ifdef CONFIG_SMP
-        /*
-         * Re-read current->group_leader->real_parent.
-         */
-        ld8 r19=[r17]                           // r19 = current->group_leader->real_parent
-(p8)    br.spnt.many fsys_fallback_syscall
-        ;;
-        cmp.ne p6,p0=r18,r19                    // did real_parent change?
-        mov r19=0                       // i must not leak kernel bits...
-(p6)    br.cond.spnt.few 1b                     // yes -> redo the read of tgid and the check
-        ;;
-        mov r17=0                       // i must not leak kernel bits...
-        mov r18=0                       // i must not leak kernel bits...
-#else
-        mov r17=0                       // i must not leak kernel bits...
-        mov r18=0                       // i must not leak kernel bits...
-        mov r19=0                       // i must not leak kernel bits...
-#endif
-        FSYS_RETURN
-END(fsys_getppid)
-
 ENTRY(fsys_set_tid_address)
         .prologue
         .altrp b6
@@ -614,7 +567,7 @@ paravirt_fsyscall_table:
         data8 0                         // chown
         data8 0                         // lseek                // 1040
         data8 fsys_getpid               // getpid
-        data8 fsys_getppid              // getppid
+        data8 0                         // getppid
         data8 0                         // mount
         data8 0                         // umount
         data8 0                         // setuid               // 1045
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index ee33c3aaa2fc..19f107be734e 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -76,7 +76,7 @@
  *      PCI pin -> global system interrupt (GSI) -> IA-64 vector <-> IRQ
  *
  * Note: The term "IRQ" is loosely used everywhere in Linux kernel to
- * describeinterrupts.  Now we use "IRQ" only for Linux IRQ's.  ISA IRQ
+ * describe interrupts.  Now we use "IRQ" only for Linux IRQ's.  ISA IRQ
  * (isa_irq) is the only exception in this source code.
  */
 
@@ -1010,6 +1010,26 @@ iosapic_check_gsi_range (unsigned int gsi_base, unsigned int ver)
         return 0;
 }
 
+static int
+iosapic_delete_rte(unsigned int irq, unsigned int gsi)
+{
+        struct iosapic_rte_info *rte, *temp;
+
+        list_for_each_entry_safe(rte, temp, &iosapic_intr_info[irq].rtes,
+                                                                rte_list) {
+                if (rte->iosapic->gsi_base + rte->rte_index == gsi) {
+                        if (rte->refcnt)
+                                return -EBUSY;
+
+                        list_del(&rte->rte_list);
+                        kfree(rte);
+                        return 0;
+                }
+        }
+
+        return -EINVAL;
+}
+
 int iosapic_init(unsigned long phys_addr, unsigned int gsi_base)
 {
         int num_rte, err, index;
@@ -1069,7 +1089,7 @@ int iosapic_init(unsigned long phys_addr, unsigned int gsi_base)
 
 int iosapic_remove(unsigned int gsi_base)
 {
-        int index, err = 0;
+        int i, irq, index, err = 0;
         unsigned long flags;
 
         spin_lock_irqsave(&iosapic_lock, flags);
@@ -1087,6 +1107,16 @@ int iosapic_remove(unsigned int gsi_base)
                 goto out;
         }
 
+        for (i = gsi_base; i < gsi_base + iosapic_lists[index].num_rte; i++) {
+                irq = __gsi_to_irq(i);
+                if (irq < 0)
+                        continue;
+
+                err = iosapic_delete_rte(irq, i);
+                if (err)
+                        goto out;
+        }
+
         iounmap(iosapic_lists[index].addr);
         iosapic_free(index);
  out:
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index ad69606613eb..f2c418281130 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -23,6 +23,8 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 
+#include <asm/mca.h>
+
 /*
  * 'what should we do if we get a hw irq event on an illegal vector'.
  * each architecture has to answer this themselves.
@@ -83,6 +85,12 @@ bool is_affinity_mask_valid(const struct cpumask *cpumask)
 
 #endif /* CONFIG_SMP */
 
+int __init arch_early_irq_init(void)
+{
+        ia64_mca_irq_init();
+        return 0;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 unsigned int vectors_in_migration[NR_IRQS];
 
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 65bf9cd39044..d7396dbb07bb 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -2074,22 +2074,16 @@ ia64_mca_init(void)
         printk(KERN_INFO "MCA related initialization done\n");
 }
 
+
 /*
- * ia64_mca_late_init
- *
- *      Opportunity to setup things that require initialization later
- *      than ia64_mca_init.  Setup a timer to poll for CPEs if the
- *      platform doesn't support an interrupt driven mechanism.
- *
- *  Inputs  :   None
- *  Outputs :   Status
+ * These pieces cannot be done in ia64_mca_init() because it is called before
+ * early_irq_init() which would wipe out our percpu irq registrations. But we
+ * cannot leave them until ia64_mca_late_init() because by then all the other
+ * processors have been brought online and have set their own CMC vectors to
+ * point at a non-existant action. Called from arch_early_irq_init().
  */
-static int __init
-ia64_mca_late_init(void)
+void __init ia64_mca_irq_init(void)
 {
-        if (!mca_init)
-                return 0;
-
         /*
          *  Configure the CMCI/P vector and handler. Interrupts for CMC are
          *  per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c).
@@ -2108,6 +2102,23 @@ ia64_mca_late_init(void)
         /* Setup the CPEI/P handler */
         register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction);
 #endif
+}
+
+/*
+ * ia64_mca_late_init
+ *
+ *      Opportunity to setup things that require initialization later
+ *      than ia64_mca_init.  Setup a timer to poll for CPEs if the
+ *      platform doesn't support an interrupt driven mechanism.
+ *
+ *  Inputs  :   None
+ *  Outputs :   Status
+ */
+static int __init
+ia64_mca_late_init(void)
+{
+        if (!mca_init)
+                return 0;
 
         register_hotcpu_notifier(&mca_cpu_notifier);
 
diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c
index 9392e021c93b..94f8bf777afa 100644
--- a/arch/ia64/kernel/mca_drv.c
+++ b/arch/ia64/kernel/mca_drv.c
@@ -349,7 +349,7 @@ init_record_index_pools(void)
 
         /* - 3 - */
         slidx_pool.max_idx = (rec_max_size/sect_min_size) * 2 + 1;
-        slidx_pool.buffer = (slidx_list_t *)
+        slidx_pool.buffer =
                 kmalloc(slidx_pool.max_idx * sizeof(slidx_list_t), GFP_KERNEL);
 
         return slidx_pool.buffer ? 0 : -ENOMEM;
diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c
index 77597e5ea60a..79521d5499f9 100644
--- a/arch/ia64/kernel/palinfo.c
+++ b/arch/ia64/kernel/palinfo.c
@@ -849,17 +849,6 @@ static palinfo_entry_t palinfo_entries[]={
 
 #define NR_PALINFO_ENTRIES      (int) ARRAY_SIZE(palinfo_entries)
 
-/*
- * this array is used to keep track of the proc entries we create. This is
- * required in the module mode when we need to remove all entries. The procfs code
- * does not do recursion of deletion
- *
- * Notes:
- *      - +1 accounts for the cpuN directory entry in /proc/pal
- */
-#define NR_PALINFO_PROC_ENTRIES (NR_CPUS*(NR_PALINFO_ENTRIES+1))
-
-static struct proc_dir_entry *palinfo_proc_entries[NR_PALINFO_PROC_ENTRIES];
 static struct proc_dir_entry *palinfo_dir;
 
 /*
@@ -971,60 +960,32 @@ palinfo_read_entry(char *page, char **start, off_t off, int count, int *eof, voi
 static void __cpuinit
 create_palinfo_proc_entries(unsigned int cpu)
 {
-#       define CPUSTR   "cpu%d"
-
         pal_func_cpu_u_t f;
-        struct proc_dir_entry **pdir;
         struct proc_dir_entry *cpu_dir;
         int j;
-        char cpustr[sizeof(CPUSTR)];
-
-
-        /*
-         * we keep track of created entries in a depth-first order for
-         * cleanup purposes. Each entry is stored into palinfo_proc_entries
-         */
-        sprintf(cpustr,CPUSTR, cpu);
+        char cpustr[3+4+1];     /* cpu numbers are up to 4095 on itanic */
+        sprintf(cpustr, "cpu%d", cpu);
 
         cpu_dir = proc_mkdir(cpustr, palinfo_dir);
+        if (!cpu_dir)
+                return;
 
         f.req_cpu = cpu;
 
-        /*
-         * Compute the location to store per cpu entries
-         * We dont store the top level entry in this list, but
-         * remove it finally after removing all cpu entries.
-         */
-        pdir = &palinfo_proc_entries[cpu*(NR_PALINFO_ENTRIES+1)];
-        *pdir++ = cpu_dir;
         for (j=0; j < NR_PALINFO_ENTRIES; j++) {
                 f.func_id = j;
-                *pdir = create_proc_read_entry(
-                                palinfo_entries[j].name, 0, cpu_dir,
-                                palinfo_read_entry, (void *)f.value);
-                pdir++;
+                create_proc_read_entry(
+                        palinfo_entries[j].name, 0, cpu_dir,
+                        palinfo_read_entry, (void *)f.value);
         }
 }
 
 static void
 remove_palinfo_proc_entries(unsigned int hcpu)
 {
-        int j;
-        struct proc_dir_entry *cpu_dir, **pdir;
-
-        pdir = &palinfo_proc_entries[hcpu*(NR_PALINFO_ENTRIES+1)];
-        cpu_dir = *pdir;
-        *pdir++=NULL;
-        for (j=0; j < (NR_PALINFO_ENTRIES); j++) {
-                if ((*pdir)) {
-                        remove_proc_entry ((*pdir)->name, cpu_dir);
-                        *pdir ++= NULL;
-                }
-        }
-
-        if (cpu_dir) {
-                remove_proc_entry(cpu_dir->name, palinfo_dir);
-        }
+        char cpustr[3+4+1];     /* cpu numbers are up to 4095 on itanic */
+        sprintf(cpustr, "cpu%d", hcpu);
+        remove_proc_subtree(cpustr, palinfo_dir);
 }
 
 static int __cpuinit palinfo_cpu_callback(struct notifier_block *nfb,
@@ -1058,6 +1019,8 @@ palinfo_init(void)
 
         printk(KERN_INFO "PAL Information Facility v%s\n", PALINFO_VERSION);
         palinfo_dir = proc_mkdir("pal", NULL);
+        if (!palinfo_dir)
+                return -ENOMEM;
 
         /* Create palinfo dirs in /proc for all online cpus */
         for_each_online_cpu(i) {
@@ -1073,22 +1036,8 @@ palinfo_init(void)
 static void __exit
 palinfo_exit(void)
 {
-        int i = 0;
-
-        /* remove all nodes: depth first pass. Could optimize this  */
-        for_each_online_cpu(i) {
-                remove_palinfo_proc_entries(i);
-        }
-
-        /*
-         * Remove the top level entry finally
-         */
-        remove_proc_entry(palinfo_dir->name, NULL);
-
-        /*
-         * Unregister from cpu notifier callbacks
-         */
         unregister_hotcpu_notifier(&palinfo_cpu_notifier);
+        remove_proc_subtree("pal", NULL);
 }
 
 module_init(palinfo_init);
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 2eda28414abb..9ea25fce06d5 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -42,6 +42,7 @@
 #include <linux/completion.h>
 #include <linux/tracehook.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
 
 #include <asm/errno.h>
 #include <asm/intrinsics.h>
@@ -1322,8 +1323,6 @@ out:
 }
 EXPORT_SYMBOL(pfm_unregister_buffer_fmt);
 
-extern void update_pal_halt_status(int);
-
 static int
 pfm_reserve_session(struct task_struct *task, int is_syswide, unsigned int cpu)
 {
@@ -1371,9 +1370,9 @@ pfm_reserve_session(struct task_struct *task, int is_syswide, unsigned int cpu)
                 cpu));
 
         /*
-         * disable default_idle() to go to PAL_HALT
+         * Force idle() into poll mode
          */
-        update_pal_halt_status(0);
+        cpu_idle_poll_ctrl(true);
 
         UNLOCK_PFS(flags);
 
@@ -1430,11 +1429,8 @@ pfm_unreserve_session(pfm_context_t *ctx, int is_syswide, unsigned int cpu)
                 is_syswide,
                 cpu));
 
-        /*
-         * if possible, enable default_idle() to go into PAL_HALT
-         */
-        if (pfm_sessions.pfs_task_sessions == 0 && pfm_sessions.pfs_sys_sessions == 0)
-                update_pal_halt_status(1);
+        /* Undo forced polling. Last session reenables pal_halt */
+        cpu_idle_poll_ctrl(false);
 
         UNLOCK_PFS(flags);
 
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index e34f565f595a..a26fc640e4ce 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -209,41 +209,13 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall)
         local_irq_disable();    /* force interrupt disable */
 }
 
-static int pal_halt        = 1;
-static int can_do_pal_halt = 1;
-
 static int __init nohalt_setup(char * str)
 {
-        pal_halt = can_do_pal_halt = 0;
+        cpu_idle_poll_ctrl(true);
         return 1;
 }
 __setup("nohalt", nohalt_setup);
 
-void
-update_pal_halt_status(int status)
-{
-        can_do_pal_halt = pal_halt && status;
-}
-
-/*
- * We use this if we don't have any better idle routine..
- */
-void
-default_idle (void)
-{
-        local_irq_enable();
-        while (!need_resched()) {
-                if (can_do_pal_halt) {
-                        local_irq_disable();
-                        if (!need_resched()) {
-                                safe_halt();
-                        }
-                        local_irq_enable();
-                } else
-                        cpu_relax();
-        }
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 /* We don't actually take CPU down, just spin without interrupts. */
 static inline void play_dead(void)
@@ -270,50 +242,29 @@ static inline void play_dead(void)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-void __attribute__((noreturn))
-cpu_idle (void)
+void arch_cpu_idle_dead(void)
+{
+        play_dead();
+}
+
+void arch_cpu_idle(void)
 {
         void (*mark_idle)(int) = ia64_mark_idle;
-        int cpu = smp_processor_id();
-
-        /* endless idle loop with no priority at all */
-        while (1) {
-                rcu_idle_enter();
-                if (can_do_pal_halt) {
-                        current_thread_info()->status &= ~TS_POLLING;
-                        /*
-                         * TS_POLLING-cleared state must be visible before we
-                         * test NEED_RESCHED:
-                         */
-                        smp_mb();
-                } else {
-                        current_thread_info()->status |= TS_POLLING;
-                }
 
-                if (!need_resched()) {
-                        void (*idle)(void);
 #ifdef CONFIG_SMP
-                        min_xtp();
+        min_xtp();
 #endif
-                        rmb();
-                        if (mark_idle)
-                                (*mark_idle)(1);
-
-                        if (!idle)
-                                idle = default_idle;
-                        (*idle)();
-                        if (mark_idle)
-                                (*mark_idle)(0);
+        rmb();
+        if (mark_idle)
+                (*mark_idle)(1);
+
+        safe_halt();
+
+        if (mark_idle)
+                (*mark_idle)(0);
 #ifdef CONFIG_SMP
-                        normal_xtp();
+        normal_xtp();
 #endif
-                }
-                rcu_idle_exit();
-                schedule_preempt_disabled();
-                check_pgt_cache();
-                if (cpu_is_offline(cpu))
-                        play_dead();
-        }
 }
 
 void
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 500f1e4d9f9d..8d87168d218d 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -455,7 +455,7 @@ start_secondary (void *unused)
         preempt_disable();
         smp_callin();
 
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
         return 0;
 }
 
diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c
index 4332f7ee5203..a7869f8f49a6 100644
--- a/arch/ia64/kvm/vtlb.c
+++ b/arch/ia64/kvm/vtlb.c
@@ -256,7 +256,7 @@ u64 guest_vhpt_lookup(u64 iha, u64 *pte)
                         "srlz.d;;"
                         "ssm psr.i;;"
                         "srlz.d;;"
-                        : "=r"(ret) : "r"(iha), "r"(pte):"memory");
+                        : "=&r"(ret) : "r"(iha), "r"(pte) : "memory");
 
         return ret;
 }
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 80dab509dfb0..67c59ebec899 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -47,6 +47,8 @@ void show_mem(unsigned int filter)
         printk(KERN_INFO "Mem-info:\n");
         show_free_areas(filter);
         printk(KERN_INFO "Node memory in pages:\n");
+        if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+                return;
         for_each_online_pgdat(pgdat) {
                 unsigned long present;
                 unsigned long flags;
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index c2e955ee79a8..ae4db4bd6d97 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -623,6 +623,8 @@ void show_mem(unsigned int filter)
 
         printk(KERN_INFO "Mem-info:\n");
         show_free_areas(filter);
+        if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+                return;
         printk(KERN_INFO "Node memory in pages:\n");
         for_each_online_pgdat(pgdat) {
                 unsigned long present;
@@ -817,13 +819,12 @@ void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat)
 #endif
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-int __meminit vmemmap_populate(struct page *start_page,
-                                                unsigned long size, int node)
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 {
-        return vmemmap_populate_basepages(start_page, size, node);
+        return vmemmap_populate_basepages(start, end, node);
 }
 
-void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+void vmemmap_free(unsigned long start, unsigned long end)
 {
 }
 #endif
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 20bc967c7209..d1fe4b402601 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -154,25 +154,14 @@ ia64_init_addr_space (void)
 void
 free_initmem (void)
 {
-        unsigned long addr, eaddr;
-
-        addr = (unsigned long) ia64_imva(__init_begin);
-        eaddr = (unsigned long) ia64_imva(__init_end);
-        while (addr < eaddr) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                ++totalram_pages;
-                addr += PAGE_SIZE;
-        }
-        printk(KERN_INFO "Freeing unused kernel memory: %ldkB freed\n",
-               (__init_end - __init_begin) >> 10);
+        free_reserved_area((unsigned long)ia64_imva(__init_begin),
+                           (unsigned long)ia64_imva(__init_end),
+                           0, "unused kernel");
 }
 
 void __init
 free_initrd_mem (unsigned long start, unsigned long end)
 {
-        struct page *page;
         /*
          * EFI uses 4KB pages while the kernel can use 4KB or bigger.
          * Thus EFI and the kernel may have different page sizes. It is
@@ -213,11 +202,7 @@ free_initrd_mem (unsigned long start, unsigned long end)
         for (; start < end; start += PAGE_SIZE) {
                 if (!virt_addr_valid(start))
                         continue;
-                page = virt_to_page(start);
-                ClearPageReserved(page);
-                init_page_count(page);
-                free_page(start);
-                ++totalram_pages;
+                free_reserved_page(virt_to_page(start));
         }
 }
 
diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c
index 3dccdd8eb275..43964cde6214 100644
--- a/arch/ia64/mm/ioremap.c
+++ b/arch/ia64/mm/ioremap.c
@@ -16,7 +16,7 @@
 #include <asm/meminit.h>
 
 static inline void __iomem *
-__ioremap (unsigned long phys_addr)
+__ioremap_uc(unsigned long phys_addr)
 {
         return (void __iomem *) (__IA64_UNCACHED_OFFSET | phys_addr);
 }
@@ -24,7 +24,11 @@ __ioremap (unsigned long phys_addr)
 void __iomem *
 early_ioremap (unsigned long phys_addr, unsigned long size)
 {
-        return __ioremap(phys_addr);
+        u64 attr;
+        attr = kern_mem_attribute(phys_addr, size);
+        if (attr & EFI_MEMORY_WB)
+                return (void __iomem *) phys_to_virt(phys_addr);
+        return __ioremap_uc(phys_addr);
 }
 
 void __iomem *
@@ -47,7 +51,7 @@ ioremap (unsigned long phys_addr, unsigned long size)
         if (attr & EFI_MEMORY_WB)
                 return (void __iomem *) phys_to_virt(phys_addr);
         else if (attr & EFI_MEMORY_UC)
-                return __ioremap(phys_addr);
+                return __ioremap_uc(phys_addr);
 
         /*
          * Some chipsets don't support UC access to memory.  If
@@ -93,7 +97,7 @@ ioremap (unsigned long phys_addr, unsigned long size)
                 return (void __iomem *) (offset + (char __iomem *)addr);
         }
 
-        return __ioremap(phys_addr);
+        return __ioremap_uc(phys_addr);
 }
 EXPORT_SYMBOL(ioremap);
 
@@ -103,7 +107,7 @@ ioremap_nocache (unsigned long phys_addr, unsigned long size)
         if (kern_mem_attribute(phys_addr, size) & EFI_MEMORY_WB)
                 return NULL;
 
-        return __ioremap(phys_addr);
+        return __ioremap_uc(phys_addr);
 }
 EXPORT_SYMBOL(ioremap_nocache);
 
diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c
index 3efea7d0a351..4248492b9321 100644
--- a/arch/ia64/mm/numa.c
+++ b/arch/ia64/mm/numa.c
@@ -61,18 +61,36 @@ paddr_to_nid(unsigned long paddr)
 int __meminit __early_pfn_to_nid(unsigned long pfn)
 {
         int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec;
+        /*
+         * NOTE: The following SMP-unsafe globals are only used early in boot
+         * when the kernel is running single-threaded.
+         */
+        static int __meminitdata last_ssec, last_esec;
+        static int __meminitdata last_nid;
+
+        if (section >= last_ssec && section < last_esec)
+                return last_nid;
 
         for (i = 0; i < num_node_memblks; i++) {
                 ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT;
                 esec = (node_memblk[i].start_paddr + node_memblk[i].size +
                         ((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT;
-                if (section >= ssec && section < esec)
+                if (section >= ssec && section < esec) {
+                        last_ssec = ssec;
+                        last_esec = esec;
+                        last_nid = node_memblk[i].nid;
                         return node_memblk[i].nid;
+                }
         }
 
         return -1;
 }
 
+void __cpuinit numa_clear_node(int cpu)
+{
+        unmap_cpu_from_node(cpu, NUMA_NO_NODE);
+}
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
  *  SRAT information is stored in node_memblk[], then we can use SRAT
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 60532ab27346..de1474ff0bc5 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -15,6 +15,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
+#include <linux/pci-acpi.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/slab.h>
@@ -458,6 +459,16 @@ void pcibios_fixup_bus(struct pci_bus *b)
         platform_pci_fixup_bus(b);
 }
 
+void pcibios_add_bus(struct pci_bus *bus)
+{
+        acpi_pci_add_bus(bus);
+}
+
+void pcibios_remove_bus(struct pci_bus *bus)
+{
+        acpi_pci_remove_bus(bus);
+}
+
 void pcibios_set_master (struct pci_dev *dev)
 {
         /* No special bus mastering setup handling */
diff --git a/arch/ia64/sn/kernel/tiocx.c b/arch/ia64/sn/kernel/tiocx.c
index 14c1711238c0..e35f6485c1fd 100644
--- a/arch/ia64/sn/kernel/tiocx.c
+++ b/arch/ia64/sn/kernel/tiocx.c
@@ -490,11 +490,14 @@ static int __init tiocx_init(void)
 {
         cnodeid_t cnodeid;
         int found_tiocx_device = 0;
+        int err;
 
         if (!ia64_platform_is("sn2"))
                 return 0;
 
-        bus_register(&tiocx_bus_type);
+        err = bus_register(&tiocx_bus_type);
+        if (err)
+                return err;
 
         for (cnodeid = 0; cnodeid < num_cnodes; cnodeid++) {
                 nasid_t nasid;
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 92623818a1fe..bcd17b206571 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -10,7 +10,7 @@ config M32R
         select ARCH_WANT_IPC_PARSE_VERSION
         select HAVE_DEBUG_BUGVERBOSE
         select HAVE_GENERIC_HARDIRQS
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select GENERIC_IRQ_PROBE
         select GENERIC_IRQ_SHOW
         select GENERIC_ATOMIC64
diff --git a/arch/m32r/include/uapi/asm/stat.h b/arch/m32r/include/uapi/asm/stat.h
index da4518f82d6d..98470fe483b6 100644
--- a/arch/m32r/include/uapi/asm/stat.h
+++ b/arch/m32r/include/uapi/asm/stat.h
@@ -63,10 +63,10 @@ struct stat64 {
         long long       st_size;
         unsigned long   st_blksize;
 
-#if defined(__BIG_ENDIAN)
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
         unsigned long   __pad4;         /* future possible st_blocks high bits */
         unsigned long   st_blocks;      /* Number 512-byte blocks allocated. */
-#elif defined(__LITTLE_ENDIAN)
+#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
         unsigned long   st_blocks;      /* Number 512-byte blocks allocated. */
         unsigned long   __pad4;         /* future possible st_blocks high bits */
 #else
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index bde899e155d3..e2d049018c3b 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -47,24 +47,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 void (*pm_power_off)(void) = NULL;
 EXPORT_SYMBOL(pm_power_off);
 
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle (void)
-{
-        /* endless idle loop with no priority at all */
-        while (1) {
-                rcu_idle_enter();
-                while (!need_resched())
-                        cpu_relax();
-                rcu_idle_exit();
-                schedule_preempt_disabled();
-        }
-}
-
 void machine_restart(char *__unused)
 {
 #if defined(CONFIG_PLAT_MAPPI3)
diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c
index 13168a769f8f..0ac558adc605 100644
--- a/arch/m32r/kernel/smpboot.c
+++ b/arch/m32r/kernel/smpboot.c
@@ -432,7 +432,7 @@ int __init start_secondary(void *unused)
          */
         local_flush_tlb_all();
 
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
         return 0;
 }
 
diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c
index 3bcb207e5b6d..9fe3467a5133 100644
--- a/arch/m32r/kernel/traps.c
+++ b/arch/m32r/kernel/traps.c
@@ -132,10 +132,8 @@ static void show_trace(struct task_struct *task, unsigned long *stack)
         printk("Call Trace: ");
         while (!kstack_end(stack)) {
                 addr = *stack++;
-                if (__kernel_text_address(addr)) {
-                        printk("[<%08lx>] ", addr);
-                        print_symbol("%s\n", addr);
-                }
+                if (__kernel_text_address(addr))
+                        printk("[<%08lx>] %pSR\n", addr, (void *)addr);
         }
         printk("\n");
 }
diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c
index 78b660e903da..ab4cbce91a9b 100644
--- a/arch/m32r/mm/init.c
+++ b/arch/m32r/mm/init.c
@@ -28,10 +28,7 @@
 #include <asm/mmu_context.h>
 #include <asm/setup.h>
 #include <asm/tlb.h>
-
-/* References to section boundaries */
-extern char _text, _etext, _edata;
-extern char __init_begin, __init_end;
+#include <asm/sections.h>
 
 pgd_t swapper_pg_dir[1024];
 
@@ -184,17 +181,7 @@ void __init mem_init(void)
  *======================================================================*/
 void free_initmem(void)
 {
-        unsigned long addr;
-
-        addr = (unsigned long)(&__init_begin);
-        for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-        printk (KERN_INFO "Freeing unused kernel memory: %dk freed\n", \
-          (int)(&__init_end - &__init_begin) >> 10);
+        free_initmem_default(0);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -204,13 +191,6 @@ void free_initmem(void)
  *======================================================================*/
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        unsigned long p;
-        for (p = start; p < end; p += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(p));
-                init_page_count(virt_to_page(p));
-                free_page(p);
-                totalram_pages++;
-        }
-        printk (KERN_INFO "Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
+        free_reserved_area(start, end, 0, "initrd");
 }
 #endif
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 0e708c78e01c..6de813370b8c 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -8,7 +8,7 @@ config M68K
         select GENERIC_IRQ_SHOW
         select GENERIC_ATOMIC64
         select HAVE_UID16
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS
         select GENERIC_CPU_DEVICES
         select GENERIC_STRNCPY_FROM_USER if MMU
diff --git a/arch/m68k/Kconfig.bus b/arch/m68k/Kconfig.bus
index 93ef0346b209..675b087198f6 100644
--- a/arch/m68k/Kconfig.bus
+++ b/arch/m68k/Kconfig.bus
@@ -45,6 +45,16 @@ config ISA
           (MCA) or VESA.  ISA is an older system, now being displaced by PCI;
           newer boards don't support it.  If you have ISA, say Y, otherwise N.
 
+config ATARI_ROM_ISA
+        bool "Atari ROM port ISA adapter support"
+        depends on ATARI
+        help
+          This option enables support for the ROM port ISA adapter used to
+          operate ISA cards on Atari. Only 8  bit cards are supported, and
+          no interrupt lines are connected.
+          The only driver currently using this adapter is the EtherNEC
+          driver for RTL8019AS based NE2000 compatible network cards.
+
 config GENERIC_ISA_DMA
         def_bool ISA
 
diff --git a/arch/m68k/Kconfig.devices b/arch/m68k/Kconfig.devices
index 4bc945dfe467..d163991c5717 100644
--- a/arch/m68k/Kconfig.devices
+++ b/arch/m68k/Kconfig.devices
@@ -55,6 +55,30 @@ config NFETH
           which will emulate a regular ethernet device while presenting an
           ethertap device to the host system.
 
+config ATARI_ETHERNAT
+        bool "Atari EtherNAT Ethernet support"
+        depends on ATARI
+        ---help---
+          Say Y to include support for the EtherNAT network adapter for the
+          CT/60 extension port.
+
+          To compile the actual ethernet driver, choose Y or M for the SMC91X
+          option in the network device section; the module will be called smc91x.
+
+config ATARI_ETHERNEC
+        bool "Atari EtherNEC Ethernet support"
+        depends on ATARI_ROM_ISA
+        ---help---
+          Say Y to include support for the EtherNEC network adapter for the
+          ROM port. The driver works by polling instead of interrupts, so it
+          is quite slow.
+
+          This driver also suppports the ethernet part of the NetUSBee ROM
+          port combined Ethernet/USB adapter.
+
+          To compile the actual ethernet driver, choose Y or M in for the NE2000
+          option in the network device section; the module will be called ne.
+
 endmenu
 
 menu "Character devices"
diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine
index 7cdf6b010381..7240584d3439 100644
--- a/arch/m68k/Kconfig.machine
+++ b/arch/m68k/Kconfig.machine
@@ -310,7 +310,6 @@ config COBRA5282
 config SOM5282EM
         bool "EMAC.Inc SOM5282EM board support"
         depends on M528x
-        select EMAC_INC
         help
           Support for the EMAC.Inc SOM5282EM module.
 
diff --git a/arch/m68k/atari/ataints.c b/arch/m68k/atari/ataints.c
index 3f41092d1b70..20cde4e9fc77 100644
--- a/arch/m68k/atari/ataints.c
+++ b/arch/m68k/atari/ataints.c
@@ -49,6 +49,7 @@
 #include <asm/atari_stdma.h>
 #include <asm/irq.h>
 #include <asm/entry.h>
+#include <asm/io.h>
 
 
 /*
@@ -122,6 +123,136 @@ static struct irq_chip atari_irq_chip = {
 };
 
 /*
+ * ST-MFP timer D chained interrupts - each driver gets its own timer
+ * interrupt instance.
+ */
+
+struct mfptimerbase {
+        volatile struct MFP *mfp;
+        unsigned char mfp_mask, mfp_data;
+        unsigned short int_mask;
+        int handler_irq, mfptimer_irq, server_irq;
+        char *name;
+} stmfp_base = {
+        .mfp            = &st_mfp,
+        .int_mask       = 0x0,
+        .handler_irq    = IRQ_MFP_TIMD,
+        .mfptimer_irq   = IRQ_MFP_TIMER1,
+        .name           = "MFP Timer D"
+};
+
+static irqreturn_t mfptimer_handler(int irq, void *dev_id)
+{
+        struct mfptimerbase *base = dev_id;
+        int mach_irq;
+        unsigned char ints;
+
+        mach_irq = base->mfptimer_irq;
+        ints = base->int_mask;
+        for (; ints; mach_irq++, ints >>= 1) {
+                if (ints & 1)
+                        generic_handle_irq(mach_irq);
+        }
+        return IRQ_HANDLED;
+}
+
+
+static void atari_mfptimer_enable(struct irq_data *data)
+{
+        int mfp_num = data->irq - IRQ_MFP_TIMER1;
+        stmfp_base.int_mask |= 1 << mfp_num;
+        atari_enable_irq(IRQ_MFP_TIMD);
+}
+
+static void atari_mfptimer_disable(struct irq_data *data)
+{
+        int mfp_num = data->irq - IRQ_MFP_TIMER1;
+        stmfp_base.int_mask &= ~(1 << mfp_num);
+        if (!stmfp_base.int_mask)
+                atari_disable_irq(IRQ_MFP_TIMD);
+}
+
+static struct irq_chip atari_mfptimer_chip = {
+        .name           = "timer_d",
+        .irq_enable     = atari_mfptimer_enable,
+        .irq_disable    = atari_mfptimer_disable,
+};
+
+
+/*
+ * EtherNAT CPLD interrupt handling
+ * CPLD interrupt register is at phys. 0x80000023
+ * Need this mapped in at interrupt startup time
+ * Possibly need this mapped on demand anyway -
+ * EtherNAT USB driver needs to disable IRQ before
+ * startup!
+ */
+
+static unsigned char *enat_cpld;
+
+static unsigned int atari_ethernat_startup(struct irq_data *data)
+{
+        int enat_num = 140 - data->irq + 1;
+
+        m68k_irq_startup(data);
+        /*
+        * map CPLD interrupt register
+        */
+        if (!enat_cpld)
+                enat_cpld = (unsigned char *)ioremap((ATARI_ETHERNAT_PHYS_ADDR+0x23), 0x2);
+        /*
+         * do _not_ enable the USB chip interrupt here - causes interrupt storm
+         * and triggers dead interrupt watchdog
+         * Need to reset the USB chip to a sane state in early startup before
+         * removing this hack
+         */
+        if (enat_num == 1)
+                *enat_cpld |= 1 << enat_num;
+
+        return 0;
+}
+
+static void atari_ethernat_enable(struct irq_data *data)
+{
+        int enat_num = 140 - data->irq + 1;
+        /*
+        * map CPLD interrupt register
+        */
+        if (!enat_cpld)
+                enat_cpld = (unsigned char *)ioremap((ATARI_ETHERNAT_PHYS_ADDR+0x23), 0x2);
+        *enat_cpld |= 1 << enat_num;
+}
+
+static void atari_ethernat_disable(struct irq_data *data)
+{
+        int enat_num = 140 - data->irq + 1;
+        /*
+        * map CPLD interrupt register
+        */
+        if (!enat_cpld)
+                enat_cpld = (unsigned char *)ioremap((ATARI_ETHERNAT_PHYS_ADDR+0x23), 0x2);
+        *enat_cpld &= ~(1 << enat_num);
+}
+
+static void atari_ethernat_shutdown(struct irq_data *data)
+{
+        int enat_num = 140 - data->irq + 1;
+        if (enat_cpld) {
+                *enat_cpld &= ~(1 << enat_num);
+                iounmap(enat_cpld);
+                enat_cpld = NULL;
+        }
+}
+
+static struct irq_chip atari_ethernat_chip = {
+        .name           = "ethernat",
+        .irq_startup    = atari_ethernat_startup,
+        .irq_shutdown   = atari_ethernat_shutdown,
+        .irq_enable     = atari_ethernat_enable,
+        .irq_disable    = atari_ethernat_disable,
+};
+
+/*
  * void atari_init_IRQ (void)
  *
  * Parameters:  None
@@ -198,6 +329,27 @@ void __init atari_init_IRQ(void)
         /* Initialize the PSG: all sounds off, both ports output */
         sound_ym.rd_data_reg_sel = 7;
         sound_ym.wd_data = 0xff;
+
+        m68k_setup_irq_controller(&atari_mfptimer_chip, handle_simple_irq,
+                                  IRQ_MFP_TIMER1, 8);
+
+        /* prepare timer D data for use as poll interrupt */
+        /* set Timer D data Register - needs to be > 0 */
+        st_mfp.tim_dt_d = 254;  /* < 100 Hz */
+        /* start timer D, div = 1:100 */
+        st_mfp.tim_ct_cd = (st_mfp.tim_ct_cd & 0xf0) | 0x6;
+
+        /* request timer D dispatch handler */
+        if (request_irq(IRQ_MFP_TIMD, mfptimer_handler, IRQF_SHARED,
+                        stmfp_base.name, &stmfp_base))
+                pr_err("Couldn't register %s interrupt\n", stmfp_base.name);
+
+        /*
+         * EtherNAT ethernet / USB interrupt handlers
+         */
+
+        m68k_setup_irq_controller(&atari_ethernat_chip, handle_simple_irq,
+                                  139, 2);
 }
 
 
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index 037c11c99331..fb2d0bd9b3ad 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -31,6 +31,8 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/ioport.h>
+#include <linux/platform_device.h>
+#include <linux/usb/isp116x.h>
 #include <linux/vt_kern.h>
 #include <linux/module.h>
 
@@ -655,3 +657,240 @@ static void atari_get_hardware_list(struct seq_file *m)
         ATARIHW_ANNOUNCE(VME, "VME Bus");
         ATARIHW_ANNOUNCE(DSP56K, "DSP56001 processor");
 }
+
+/*
+ * MSch: initial platform device support for Atari,
+ * required for EtherNAT/EtherNEC/NetUSBee drivers
+ */
+
+#if defined(CONFIG_ATARI_ETHERNAT) || defined(CONFIG_ATARI_ETHERNEC)
+static void isp1160_delay(struct device *dev, int delay)
+{
+        ndelay(delay);
+}
+#endif
+
+#ifdef CONFIG_ATARI_ETHERNAT
+/*
+ * EtherNAT: SMC91C111 Ethernet chipset, handled by smc91x driver
+ */
+
+#define ATARI_ETHERNAT_IRQ              140
+
+static struct resource smc91x_resources[] = {
+        [0] = {
+                .name   = "smc91x-regs",
+                .start  = ATARI_ETHERNAT_PHYS_ADDR,
+                .end    = ATARI_ETHERNAT_PHYS_ADDR + 0xfffff,
+                .flags  = IORESOURCE_MEM,
+        },
+        [1] = {
+                .name   = "smc91x-irq",
+                .start  = ATARI_ETHERNAT_IRQ,
+                .end    = ATARI_ETHERNAT_IRQ,
+                .flags  = IORESOURCE_IRQ,
+        },
+};
+
+static struct platform_device smc91x_device = {
+        .name           = "smc91x",
+        .id             = -1,
+        .num_resources  = ARRAY_SIZE(smc91x_resources),
+        .resource       = smc91x_resources,
+};
+
+/*
+ * ISP 1160 - using the isp116x-hcd module
+ */
+
+#define ATARI_USB_PHYS_ADDR     0x80000012
+#define ATARI_USB_IRQ           139
+
+static struct resource isp1160_resources[] = {
+        [0] = {
+                .name   = "isp1160-data",
+                .start  = ATARI_USB_PHYS_ADDR,
+                .end    = ATARI_USB_PHYS_ADDR + 0x1,
+                .flags  = IORESOURCE_MEM,
+        },
+        [1] = {
+                .name   = "isp1160-regs",
+                .start  = ATARI_USB_PHYS_ADDR + 0x4,
+                .end    = ATARI_USB_PHYS_ADDR + 0x5,
+                .flags  = IORESOURCE_MEM,
+        },
+        [2] = {
+                .name   = "isp1160-irq",
+                .start  = ATARI_USB_IRQ,
+                .end    = ATARI_USB_IRQ,
+                .flags  = IORESOURCE_IRQ,
+        },
+};
+
+/* (DataBusWidth16|AnalogOCEnable|DREQOutputPolarity|DownstreamPort15KRSel ) */
+static struct isp116x_platform_data isp1160_platform_data = {
+        /* Enable internal resistors on downstream ports */
+        .sel15Kres              = 1,
+        /* On-chip overcurrent protection */
+        .oc_enable              = 1,
+        /* INT output polarity */
+        .int_act_high           = 1,
+        /* INT edge or level triggered */
+        .int_edge_triggered     = 0,
+
+        /* WAKEUP pin connected - NOT SUPPORTED  */
+        /* .remote_wakeup_connected = 0, */
+        /* Wakeup by devices on usb bus enabled */
+        .remote_wakeup_enable   = 0,
+        .delay                  = isp1160_delay,
+};
+
+static struct platform_device isp1160_device = {
+        .name           = "isp116x-hcd",
+        .id             = 0,
+        .num_resources  = ARRAY_SIZE(isp1160_resources),
+        .resource       = isp1160_resources,
+        .dev                    = {
+                .platform_data  = &isp1160_platform_data,
+        },
+};
+
+static struct platform_device *atari_ethernat_devices[] __initdata = {
+        &smc91x_device,
+        &isp1160_device
+};
+#endif /* CONFIG_ATARI_ETHERNAT */
+
+#ifdef CONFIG_ATARI_ETHERNEC
+/*
+ * EtherNEC: RTL8019 (NE2000 compatible) Ethernet chipset,
+ * handled by ne.c driver
+ */
+
+#define ATARI_ETHERNEC_PHYS_ADDR        0xfffa0000
+#define ATARI_ETHERNEC_BASE             0x300
+#define ATARI_ETHERNEC_IRQ              IRQ_MFP_TIMER1
+
+static struct resource rtl8019_resources[] = {
+        [0] = {
+                .name   = "rtl8019-regs",
+                .start  = ATARI_ETHERNEC_BASE,
+                .end    = ATARI_ETHERNEC_BASE + 0x20 - 1,
+                .flags  = IORESOURCE_IO,
+        },
+        [1] = {
+                .name   = "rtl8019-irq",
+                .start  = ATARI_ETHERNEC_IRQ,
+                .end    = ATARI_ETHERNEC_IRQ,
+                .flags  = IORESOURCE_IRQ,
+        },
+};
+
+static struct platform_device rtl8019_device = {
+        .name           = "ne",
+        .id             = -1,
+        .num_resources  = ARRAY_SIZE(rtl8019_resources),
+        .resource       = rtl8019_resources,
+};
+
+/*
+ * NetUSBee: ISP1160 USB host adapter via ROM-port adapter
+ */
+
+#define ATARI_NETUSBEE_PHYS_ADDR        0xfffa8000
+#define ATARI_NETUSBEE_BASE             0x340
+#define ATARI_NETUSBEE_IRQ              IRQ_MFP_TIMER2
+
+static struct resource netusbee_resources[] = {
+        [0] = {
+                .name   = "isp1160-data",
+                .start  = ATARI_NETUSBEE_BASE,
+                .end    = ATARI_NETUSBEE_BASE + 0x1,
+                .flags  = IORESOURCE_MEM,
+        },
+        [1] = {
+                .name   = "isp1160-regs",
+                .start  = ATARI_NETUSBEE_BASE + 0x20,
+                .end    = ATARI_NETUSBEE_BASE + 0x21,
+                .flags  = IORESOURCE_MEM,
+        },
+        [2] = {
+                .name   = "isp1160-irq",
+                .start  = ATARI_NETUSBEE_IRQ,
+                .end    = ATARI_NETUSBEE_IRQ,
+                .flags  = IORESOURCE_IRQ,
+        },
+};
+
+/* (DataBusWidth16|AnalogOCEnable|DREQOutputPolarity|DownstreamPort15KRSel ) */
+static struct isp116x_platform_data netusbee_platform_data = {
+        /* Enable internal resistors on downstream ports */
+        .sel15Kres              = 1,
+        /* On-chip overcurrent protection */
+        .oc_enable              = 1,
+        /* INT output polarity */
+        .int_act_high           = 1,
+        /* INT edge or level triggered */
+        .int_edge_triggered     = 0,
+
+        /* WAKEUP pin connected - NOT SUPPORTED  */
+        /* .remote_wakeup_connected = 0, */
+        /* Wakeup by devices on usb bus enabled */
+        .remote_wakeup_enable   = 0,
+        .delay                  = isp1160_delay,
+};
+
+static struct platform_device netusbee_device = {
+        .name           = "isp116x-hcd",
+        .id             = 1,
+        .num_resources  = ARRAY_SIZE(netusbee_resources),
+        .resource       = netusbee_resources,
+        .dev                    = {
+                .platform_data  = &netusbee_platform_data,
+        },
+};
+
+static struct platform_device *atari_netusbee_devices[] __initdata = {
+        &rtl8019_device,
+        &netusbee_device
+};
+#endif /* CONFIG_ATARI_ETHERNEC */
+
+int __init atari_platform_init(void)
+{
+        int rv = 0;
+
+        if (!MACH_IS_ATARI)
+                return -ENODEV;
+
+#ifdef CONFIG_ATARI_ETHERNAT
+        {
+                unsigned char *enatc_virt;
+                enatc_virt = (unsigned char *)ioremap((ATARI_ETHERNAT_PHYS_ADDR+0x23), 0xf);
+                if (hwreg_present(enatc_virt)) {
+                        rv = platform_add_devices(atari_ethernat_devices,
+                                                ARRAY_SIZE(atari_ethernat_devices));
+                }
+                iounmap(enatc_virt);
+        }
+#endif
+
+#ifdef CONFIG_ATARI_ETHERNEC
+        {
+                int error;
+                unsigned char *enec_virt;
+                enec_virt = (unsigned char *)ioremap((ATARI_ETHERNEC_PHYS_ADDR), 0xf);
+                if (hwreg_present(enec_virt)) {
+                        error = platform_add_devices(atari_netusbee_devices,
+                                                ARRAY_SIZE(atari_netusbee_devices));
+                        if (error && !rv)
+                                rv = error;
+                }
+                iounmap(enec_virt);
+        }
+#endif
+
+        return rv;
+}
+
+arch_initcall(atari_platform_init);
diff --git a/arch/m68k/include/asm/MC68328.h b/arch/m68k/include/asm/MC68328.h
index a337e56d09bf..4ebf098b8a1f 100644
--- a/arch/m68k/include/asm/MC68328.h
+++ b/arch/m68k/include/asm/MC68328.h
@@ -293,7 +293,7 @@
 /*
  * Here go the bitmasks themselves
  */
-#define IMR_MSPIM       (1 << SPIM _IRQ_NUM)    /* Mask SPI Master interrupt */
+#define IMR_MSPIM       (1 << SPIM_IRQ_NUM)     /* Mask SPI Master interrupt */
 #define IMR_MTMR2       (1 << TMR2_IRQ_NUM)     /* Mask Timer 2 interrupt */
 #define IMR_MUART       (1 << UART_IRQ_NUM)     /* Mask UART interrupt */       
 #define IMR_MWDT        (1 << WDT_IRQ_NUM)      /* Mask Watchdog Timer interrupt */
@@ -327,7 +327,7 @@
 #define IWR_ADDR        0xfffff308
 #define IWR             LONG_REF(IWR_ADDR)
 
-#define IWR_SPIM        (1 << SPIM _IRQ_NUM)    /* SPI Master interrupt */
+#define IWR_SPIM        (1 << SPIM_IRQ_NUM)     /* SPI Master interrupt */
 #define IWR_TMR2        (1 << TMR2_IRQ_NUM)     /* Timer 2 interrupt */
 #define IWR_UART        (1 << UART_IRQ_NUM)     /* UART interrupt */    
 #define IWR_WDT         (1 << WDT_IRQ_NUM)      /* Watchdog Timer interrupt */
@@ -357,7 +357,7 @@
 #define ISR_ADDR        0xfffff30c
 #define ISR             LONG_REF(ISR_ADDR)
 
-#define ISR_SPIM        (1 << SPIM _IRQ_NUM)    /* SPI Master interrupt */
+#define ISR_SPIM        (1 << SPIM_IRQ_NUM)     /* SPI Master interrupt */
 #define ISR_TMR2        (1 << TMR2_IRQ_NUM)     /* Timer 2 interrupt */
 #define ISR_UART        (1 << UART_IRQ_NUM)     /* UART interrupt */    
 #define ISR_WDT         (1 << WDT_IRQ_NUM)      /* Watchdog Timer interrupt */
@@ -391,7 +391,7 @@
 #define IPR_ADDR        0xfffff310
 #define IPR             LONG_REF(IPR_ADDR)
 
-#define IPR_SPIM        (1 << SPIM _IRQ_NUM)    /* SPI Master interrupt */
+#define IPR_SPIM        (1 << SPIM_IRQ_NUM)     /* SPI Master interrupt */
 #define IPR_TMR2        (1 << TMR2_IRQ_NUM)     /* Timer 2 interrupt */
 #define IPR_UART        (1 << UART_IRQ_NUM)     /* UART interrupt */    
 #define IPR_WDT         (1 << WDT_IRQ_NUM)      /* Watchdog Timer interrupt */
@@ -757,7 +757,7 @@
 
 /* 'EZ328-compatible definitions */
 #define TCN_ADDR        TCN1_ADDR
-#define TCN             TCN
+#define TCN             TCN1
 
 /*
  * Timer Unit 1 and 2 Status Registers
diff --git a/arch/m68k/include/asm/atarihw.h b/arch/m68k/include/asm/atarihw.h
index c0cb36350775..d887050e6da6 100644
--- a/arch/m68k/include/asm/atarihw.h
+++ b/arch/m68k/include/asm/atarihw.h
@@ -805,5 +805,11 @@ struct MSTE_RTC {
 
 #define mste_rtc ((*(volatile struct MSTE_RTC *)MSTE_RTC_BAS))
 
+/*
+** EtherNAT add-on card for Falcon - combined ethernet and USB adapter
+*/
+
+#define ATARI_ETHERNAT_PHYS_ADDR        0x80000000
+
 #endif /* linux/atarihw.h */
 
diff --git a/arch/m68k/include/asm/atariints.h b/arch/m68k/include/asm/atariints.h
index 5fc13bdf9044..953e0ac6855e 100644
--- a/arch/m68k/include/asm/atariints.h
+++ b/arch/m68k/include/asm/atariints.h
@@ -32,7 +32,7 @@
 #define VME_SOURCE_BASE    56
 #define VME_MAX_SOURCES    16
 
-#define NUM_ATARI_SOURCES   (VME_SOURCE_BASE+VME_MAX_SOURCES-STMFP_SOURCE_BASE)
+#define NUM_ATARI_SOURCES  141
 
 /* convert vector number to int source number */
 #define IRQ_VECTOR_TO_SOURCE(v) ((v) - ((v) < 0x20 ? 0x18 : (0x40-8)))
@@ -94,6 +94,15 @@
 #define IRQ_SCCA_RX          (52)
 #define IRQ_SCCA_SPCOND      (54)
 
+/* shared MFP timer D interrupts - hires timer for EtherNEC et al. */
+#define IRQ_MFP_TIMER1       (64)
+#define IRQ_MFP_TIMER2       (65)
+#define IRQ_MFP_TIMER3       (66)
+#define IRQ_MFP_TIMER4       (67)
+#define IRQ_MFP_TIMER5       (68)
+#define IRQ_MFP_TIMER6       (69)
+#define IRQ_MFP_TIMER7       (70)
+#define IRQ_MFP_TIMER8       (71)
 
 #define INT_CLK   24576     /* CLK while int_clk =2.456MHz and divide = 100 */
 #define INT_TICKS 246       /* to make sched_time = 99.902... HZ */
diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h
index 5c81d0eae5cf..bc755bc620ad 100644
--- a/arch/m68k/include/asm/cmpxchg.h
+++ b/arch/m68k/include/asm/cmpxchg.h
@@ -124,6 +124,9 @@ static inline unsigned long __cmpxchg(volatile void *p, unsigned long old,
 #define cmpxchg_local(ptr, o, n)                                            \
         ((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),           \
                         (unsigned long)(n), sizeof(*(ptr))))
+
+#define cmpxchg64(ptr, o, n)    cmpxchg64_local((ptr), (o), (n))
+
 #else
 
 /*
diff --git a/arch/m68k/include/asm/delay.h b/arch/m68k/include/asm/delay.h
index 12d8fe4f1d30..d28fa8fe26fe 100644
--- a/arch/m68k/include/asm/delay.h
+++ b/arch/m68k/include/asm/delay.h
@@ -92,5 +92,28 @@ static inline void __udelay(unsigned long usecs)
 #define udelay(n) (__builtin_constant_p(n) ? \
         ((n) > 20000 ? __bad_udelay() : __const_udelay(n)) : __udelay(n))
 
+/*
+ * nanosecond delay:
+ *
+ * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6) is the number of loops
+ * per microsecond
+ *
+ * 1000 / ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6) is the number of
+ * nanoseconds per loop
+ *
+ * So n / ( 1000 / ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6) ) would
+ * be the number of loops for n nanoseconds
+ */
+
+/*
+ * The simpler m68k and ColdFire processors do not have a 32*32->64
+ * multiply instruction. So we need to handle them a little differently.
+ * We use a bit of shifting and a single 32*32->32 multiply to get close.
+ * This is a macro so that the const version can factor out the first
+ * multiply and shift.
+ */
+#define HZSCALE         (268435456 / (1000000 / HZ))
+
+#define ndelay(n) __delay(DIV_ROUND_UP((n) * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6), 1000));
 
 #endif /* defined(_M68K_DELAY_H) */
diff --git a/arch/m68k/include/asm/gpio.h b/arch/m68k/include/asm/gpio.h
index 4395ffc51fdb..8cc83431805b 100644
--- a/arch/m68k/include/asm/gpio.h
+++ b/arch/m68k/include/asm/gpio.h
@@ -86,4 +86,24 @@ static inline int gpio_cansleep(unsigned gpio)
         return gpio < MCFGPIO_PIN_MAX ? 0 : __gpio_cansleep(gpio);
 }
 
+static inline int gpio_request_one(unsigned gpio, unsigned long flags, const char *label)
+{
+        int err;
+
+        err = gpio_request(gpio, label);
+        if (err)
+                return err;
+
+        if (flags & GPIOF_DIR_IN)
+                err = gpio_direction_input(gpio);
+        else
+                err = gpio_direction_output(gpio,
+                        (flags & GPIOF_INIT_HIGH) ? 1 : 0);
+
+        if (err)
+                gpio_free(gpio);
+
+        return err;
+}
+
 #endif
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index a6686d26fe17..ffdf54f44bc6 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -63,6 +63,23 @@
 #endif
 #endif /* AMIGA_PCMCIA */
 
+#ifdef CONFIG_ATARI_ROM_ISA
+
+#define enec_isa_read_base  0xfffa0000
+#define enec_isa_write_base 0xfffb0000
+
+#define ENEC_ISA_IO_B(ioaddr)   (enec_isa_read_base+((((unsigned long)(ioaddr))&0x7F)<<9))
+#define ENEC_ISA_IO_W(ioaddr)   (enec_isa_read_base+((((unsigned long)(ioaddr))&0x7F)<<9))
+#define ENEC_ISA_MEM_B(madr)    (enec_isa_read_base+((((unsigned long)(madr))&0x7F)<<9))
+#define ENEC_ISA_MEM_W(madr)    (enec_isa_read_base+((((unsigned long)(madr))&0x7F)<<9))
+
+#ifndef MULTI_ISA
+#define MULTI_ISA 0
+#else
+#undef MULTI_ISA
+#define MULTI_ISA 1
+#endif
+#endif /* ATARI_ROM_ISA */
 
 
 #if defined(CONFIG_PCI) && defined(CONFIG_COLDFIRE)
@@ -111,14 +128,15 @@ void mcf_pci_outsl(u32 addr, const u32 *buf, u32 len);
 #define readw(addr)     in_le16(addr)
 #define writew(v, addr) out_le16((addr), (v))
 
-#elif defined(CONFIG_ISA)
+#elif defined(CONFIG_ISA) || defined(CONFIG_ATARI_ROM_ISA)
 
 #if MULTI_ISA == 0
 #undef MULTI_ISA
 #endif
 
-#define ISA_TYPE_Q40 (1)
-#define ISA_TYPE_AG  (2)
+#define ISA_TYPE_Q40  (1)
+#define ISA_TYPE_AG   (2)
+#define ISA_TYPE_ENEC (3)
 
 #if defined(CONFIG_Q40) && !defined(MULTI_ISA)
 #define ISA_TYPE ISA_TYPE_Q40
@@ -128,6 +146,10 @@ void mcf_pci_outsl(u32 addr, const u32 *buf, u32 len);
 #define ISA_TYPE ISA_TYPE_AG
 #define ISA_SEX  1
 #endif
+#if defined(CONFIG_ATARI_ROM_ISA) && !defined(MULTI_ISA)
+#define ISA_TYPE ISA_TYPE_ENEC
+#define ISA_SEX  0
+#endif
 
 #ifdef MULTI_ISA
 extern int isa_type;
@@ -152,6 +174,9 @@ static inline u8 __iomem *isa_itb(unsigned long addr)
 #ifdef CONFIG_AMIGA_PCMCIA
     case ISA_TYPE_AG: return (u8 __iomem *)AG_ISA_IO_B(addr);
 #endif
+#ifdef CONFIG_ATARI_ROM_ISA
+    case ISA_TYPE_ENEC: return (u8 __iomem *)ENEC_ISA_IO_B(addr);
+#endif
     default: return NULL; /* avoid warnings, just in case */
     }
 }
@@ -165,6 +190,9 @@ static inline u16 __iomem *isa_itw(unsigned long addr)
 #ifdef CONFIG_AMIGA_PCMCIA
     case ISA_TYPE_AG: return (u16 __iomem *)AG_ISA_IO_W(addr);
 #endif
+#ifdef CONFIG_ATARI_ROM_ISA
+    case ISA_TYPE_ENEC: return (u16 __iomem *)ENEC_ISA_IO_W(addr);
+#endif
     default: return NULL; /* avoid warnings, just in case */
     }
 }
@@ -188,6 +216,9 @@ static inline u8 __iomem *isa_mtb(unsigned long addr)
 #ifdef CONFIG_AMIGA_PCMCIA
     case ISA_TYPE_AG: return (u8 __iomem *)addr;
 #endif
+#ifdef CONFIG_ATARI_ROM_ISA
+    case ISA_TYPE_ENEC: return (u8 __iomem *)ENEC_ISA_MEM_B(addr);
+#endif
     default: return NULL; /* avoid warnings, just in case */
     }
 }
@@ -201,6 +232,9 @@ static inline u16 __iomem *isa_mtw(unsigned long addr)
 #ifdef CONFIG_AMIGA_PCMCIA
     case ISA_TYPE_AG: return (u16 __iomem *)addr;
 #endif
+#ifdef CONFIG_ATARI_ROM_ISA
+    case ISA_TYPE_ENEC: return (u16 __iomem *)ENEC_ISA_MEM_W(addr);
+#endif
     default: return NULL; /* avoid warnings, just in case */
     }
 }
@@ -222,6 +256,36 @@ static inline u16 __iomem *isa_mtw(unsigned long addr)
         (ISA_SEX ? out_be16(isa_mtw((unsigned long)(p)),(val))  \
                  : out_le16(isa_mtw((unsigned long)(p)),(val)))
 
+#ifdef CONFIG_ATARI_ROM_ISA
+#define isa_rom_inb(port)      rom_in_8(isa_itb(port))
+#define isa_rom_inw(port)       \
+        (ISA_SEX ? rom_in_be16(isa_itw(port))   \
+                 : rom_in_le16(isa_itw(port)))
+
+#define isa_rom_outb(val, port) rom_out_8(isa_itb(port), (val))
+#define isa_rom_outw(val, port) \
+        (ISA_SEX ? rom_out_be16(isa_itw(port), (val))   \
+                 : rom_out_le16(isa_itw(port), (val)))
+
+#define isa_rom_readb(p)       rom_in_8(isa_mtb((unsigned long)(p)))
+#define isa_rom_readw(p)       \
+        (ISA_SEX ? rom_in_be16(isa_mtw((unsigned long)(p)))     \
+                 : rom_in_le16(isa_mtw((unsigned long)(p))))
+#define isa_rom_readw_swap(p)       \
+        (ISA_SEX ? rom_in_le16(isa_mtw((unsigned long)(p)))     \
+                 : rom_in_be16(isa_mtw((unsigned long)(p))))
+#define isa_rom_readw_raw(p)   rom_in_be16(isa_mtw((unsigned long)(p)))
+
+#define isa_rom_writeb(val, p)  rom_out_8(isa_mtb((unsigned long)(p)), (val))
+#define isa_rom_writew(val, p)  \
+        (ISA_SEX ? rom_out_be16(isa_mtw((unsigned long)(p)), (val))     \
+                 : rom_out_le16(isa_mtw((unsigned long)(p)), (val)))
+#define isa_rom_writew_swap(val, p)  \
+        (ISA_SEX ? rom_out_le16(isa_mtw((unsigned long)(p)), (val))     \
+                 : rom_out_be16(isa_mtw((unsigned long)(p)), (val)))
+#define isa_rom_writew_raw(val, p)  rom_out_be16(isa_mtw((unsigned long)(p)), (val))
+#endif /* CONFIG_ATARI_ROM_ISA */
+
 static inline void isa_delay(void)
 {
   switch(ISA_TYPE)
@@ -232,6 +296,9 @@ static inline void isa_delay(void)
 #ifdef CONFIG_AMIGA_PCMCIA
     case ISA_TYPE_AG: break;
 #endif
+#ifdef CONFIG_ATARI_ROM_ISA
+    case ISA_TYPE_ENEC: break;
+#endif
     default: break; /* avoid warnings */
     }
 }
@@ -263,6 +330,29 @@ static inline void isa_delay(void)
                   raw_outsw_swapw(isa_itw(port), (u16 *)(buf), (nr)<<1))
 
 
+#ifdef CONFIG_ATARI_ROM_ISA
+#define isa_rom_inb_p(p)        ({ u8 _v = isa_rom_inb(p); isa_delay(); _v; })
+#define isa_rom_inw_p(p)        ({ u16 _v = isa_rom_inw(p); isa_delay(); _v; })
+#define isa_rom_outb_p(v, p)    ({ isa_rom_outb((v), (p)); isa_delay(); })
+#define isa_rom_outw_p(v, p)    ({ isa_rom_outw((v), (p)); isa_delay(); })
+
+#define isa_rom_insb(port, buf, nr) raw_rom_insb(isa_itb(port), (u8 *)(buf), (nr))
+
+#define isa_rom_insw(port, buf, nr)     \
+       (ISA_SEX ? raw_rom_insw(isa_itw(port), (u16 *)(buf), (nr)) :    \
+                  raw_rom_insw_swapw(isa_itw(port), (u16 *)(buf), (nr)))
+
+#define isa_rom_outsb(port, buf, nr) raw_rom_outsb(isa_itb(port), (u8 *)(buf), (nr))
+
+#define isa_rom_outsw(port, buf, nr)    \
+       (ISA_SEX ? raw_rom_outsw(isa_itw(port), (u16 *)(buf), (nr)) :  \
+                  raw_rom_outsw_swapw(isa_itw(port), (u16 *)(buf), (nr)))
+#endif /* CONFIG_ATARI_ROM_ISA */
+
+#endif  /* CONFIG_ISA || CONFIG_ATARI_ROM_ISA */
+
+
+#if defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA)
 #define inb     isa_inb
 #define inb_p   isa_inb_p
 #define outb    isa_outb
@@ -285,9 +375,43 @@ static inline void isa_delay(void)
 #define readw   isa_readw
 #define writeb  isa_writeb
 #define writew  isa_writew
+#endif  /* CONFIG_ISA && !CONFIG_ATARI_ROM_ISA */
 
-#else  /* CONFIG_ISA */
-
+#ifdef CONFIG_ATARI_ROM_ISA
+/*
+ * kernel with both ROM port ISA and IDE compiled in, those have
+ * conflicting defs for in/out. Simply consider port < 1024
+ * ROM port ISA and everything else regular ISA for IDE. read,write defined
+ * below.
+ */
+#define inb(port)       ((port) < 1024 ? isa_rom_inb(port) : in_8(port))
+#define inb_p(port)     ((port) < 1024 ? isa_rom_inb_p(port) : in_8(port))
+#define inw(port)       ((port) < 1024 ? isa_rom_inw(port) : in_le16(port))
+#define inw_p(port)     ((port) < 1024 ? isa_rom_inw_p(port) : in_le16(port))
+#define inl             isa_inl
+#define inl_p           isa_inl_p
+
+#define outb(val, port) ((port) < 1024 ? isa_rom_outb((val), (port)) : out_8((port), (val)))
+#define outb_p(val, port) ((port) < 1024 ? isa_rom_outb_p((val), (port)) : out_8((port), (val)))
+#define outw(val, port) ((port) < 1024 ? isa_rom_outw((val), (port)) : out_le16((port), (val)))
+#define outw_p(val, port) ((port) < 1024 ? isa_rom_outw_p((val), (port)) : out_le16((port), (val)))
+#define outl            isa_outl
+#define outl_p          isa_outl_p
+
+#define insb(port, buf, nr)     ((port) < 1024 ? isa_rom_insb((port), (buf), (nr)) : isa_insb((port), (buf), (nr)))
+#define insw(port, buf, nr)     ((port) < 1024 ? isa_rom_insw((port), (buf), (nr)) : isa_insw((port), (buf), (nr)))
+#define insl                    isa_insl
+#define outsb(port, buf, nr)    ((port) < 1024 ? isa_rom_outsb((port), (buf), (nr)) : isa_outsb((port), (buf), (nr)))
+#define outsw(port, buf, nr)    ((port) < 1024 ? isa_rom_outsw((port), (buf), (nr)) : isa_outsw((port), (buf), (nr)))
+#define outsl                   isa_outsl
+
+#define readb(addr)             in_8(addr)
+#define writeb(val, addr)       out_8((addr), (val))
+#define readw(addr)             in_le16(addr)
+#define writew(val, addr)       out_le16((addr), (val))
+#endif /* CONFIG_ATARI_ROM_ISA */
+
+#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA)
 /*
  * We need to define dummy functions for GENERIC_IOMAP support.
  */
@@ -319,7 +443,7 @@ static inline void isa_delay(void)
 #define readw(addr)      in_le16(addr)
 #define writew(val,addr) out_le16((addr),(val))
 
-#endif /* CONFIG_ISA */
+#endif /* !CONFIG_ISA && !CONFIG_ATARI_ROM_ISA */
 
 #define readl(addr)      in_le32(addr)
 #define writel(val,addr) out_le32((addr),(val))
diff --git a/arch/m68k/include/asm/irq.h b/arch/m68k/include/asm/irq.h
index c1155f0e22cc..81ca118d58af 100644
--- a/arch/m68k/include/asm/irq.h
+++ b/arch/m68k/include/asm/irq.h
@@ -6,12 +6,16 @@
  * different m68k hosts compiled into the kernel.
  * Currently the Atari has 72 and the Amiga 24, but if both are
  * supported in the kernel it is better to make room for 72.
+ * With EtherNAT add-on card on Atari, the highest interrupt
+ * number is 140 so NR_IRQS needs to be 141.
  */
 #if defined(CONFIG_COLDFIRE)
 #define NR_IRQS 256
 #elif defined(CONFIG_VME) || defined(CONFIG_SUN3) || defined(CONFIG_SUN3X)
 #define NR_IRQS 200
-#elif defined(CONFIG_ATARI) || defined(CONFIG_MAC)
+#elif defined(CONFIG_ATARI)
+#define NR_IRQS 141
+#elif defined(CONFIG_MAC)
 #define NR_IRQS 72
 #elif defined(CONFIG_Q40)
 #define NR_IRQS 43
diff --git a/arch/m68k/include/asm/raw_io.h b/arch/m68k/include/asm/raw_io.h
index d9eb9834ccc8..932faa35655b 100644
--- a/arch/m68k/include/asm/raw_io.h
+++ b/arch/m68k/include/asm/raw_io.h
@@ -10,7 +10,7 @@
 
 #ifdef __KERNEL__
 
-#include <asm/types.h>
+#include <asm/byteorder.h>
 
 
 /* Values for nocacheflag and cmode */
@@ -60,6 +60,57 @@ extern void __iounmap(void *addr, unsigned long size);
 #define __raw_writew(val,addr) out_be16((addr),(val))
 #define __raw_writel(val,addr) out_be32((addr),(val))
 
+/*
+ * Atari ROM port (cartridge port) ISA adapter, used for the EtherNEC NE2000
+ * network card driver.
+ * The ISA adapter connects address lines A9-A13 to ISA address lines A0-A4,
+ * and hardwires the rest of the ISA addresses for a base address of 0x300.
+ *
+ * Data lines D8-D15 are connected to ISA data lines D0-D7 for reading.
+ * For writes, address lines A1-A8 are latched to ISA data lines D0-D7
+ * (meaning the bit pattern on A1-A8 can be read back as byte).
+ *
+ * Read and write operations are distinguished by the base address used:
+ * reads are from the ROM A side range, writes are through the B side range
+ * addresses (A side base + 0x10000).
+ *
+ * Reads and writes are byte only.
+ *
+ * 16 bit reads and writes are necessary for the NetUSBee adapter's USB
+ * chipset - 16 bit words are read straight off the ROM port while 16 bit
+ * reads are split into two byte writes. The low byte is latched to the
+ * NetUSBee buffer by a read from the _read_ window (with the data pattern
+ * asserted as A1-A8 address pattern). The high byte is then written to the
+ * write range as usual, completing the write cycle.
+ */
+
+#if defined(CONFIG_ATARI_ROM_ISA)
+#define rom_in_8(addr) \
+        ({ u16 __v = (*(__force volatile u16 *) (addr)); __v >>= 8; __v; })
+#define rom_in_be16(addr) \
+        ({ u16 __v = (*(__force volatile u16 *) (addr)); __v; })
+#define rom_in_le16(addr) \
+        ({ u16 __v = le16_to_cpu(*(__force volatile u16 *) (addr)); __v; })
+
+#define rom_out_8(addr, b)      \
+        ({u8 __w, __v = (b);  u32 _addr = ((u32) (addr)); \
+        __w = ((*(__force volatile u8 *)  ((_addr | 0x10000) + (__v<<1)))); })
+#define rom_out_be16(addr, w)   \
+        ({u16 __w, __v = (w); u32 _addr = ((u32) (addr)); \
+        __w = ((*(__force volatile u16 *) ((_addr & 0xFFFF0000UL) + ((__v & 0xFF)<<1)))); \
+        __w = ((*(__force volatile u16 *) ((_addr | 0x10000) + ((__v >> 8)<<1)))); })
+#define rom_out_le16(addr, w)   \
+        ({u16 __w, __v = (w); u32 _addr = ((u32) (addr)); \
+        __w = ((*(__force volatile u16 *) ((_addr & 0xFFFF0000UL) + ((__v >> 8)<<1)))); \
+        __w = ((*(__force volatile u16 *) ((_addr | 0x10000) + ((__v & 0xFF)<<1)))); })
+
+#define raw_rom_inb rom_in_8
+#define raw_rom_inw rom_in_be16
+
+#define raw_rom_outb(val, port) rom_out_8((port), (val))
+#define raw_rom_outw(val, port) rom_out_be16((port), (val))
+#endif /* CONFIG_ATARI_ROM_ISA */
+
 static inline void raw_insb(volatile u8 __iomem *port, u8 *buf, unsigned int len)
 {
         unsigned int i;
@@ -342,6 +393,62 @@ static inline void raw_outsw_swapw(volatile u16 __iomem *port, const u16 *buf,
                 : "d0", "a0", "a1", "d6");
 }
 
+
+#if defined(CONFIG_ATARI_ROM_ISA)
+static inline void raw_rom_insb(volatile u8 __iomem *port, u8 *buf, unsigned int len)
+{
+        unsigned int i;
+
+        for (i = 0; i < len; i++)
+                *buf++ = rom_in_8(port);
+}
+
+static inline void raw_rom_outsb(volatile u8 __iomem *port, const u8 *buf,
+                             unsigned int len)
+{
+        unsigned int i;
+
+        for (i = 0; i < len; i++)
+                rom_out_8(port, *buf++);
+}
+
+static inline void raw_rom_insw(volatile u16 __iomem *port, u16 *buf,
+                                   unsigned int nr)
+{
+        unsigned int i;
+
+        for (i = 0; i < nr; i++)
+                *buf++ = rom_in_be16(port);
+}
+
+static inline void raw_rom_outsw(volatile u16 __iomem *port, const u16 *buf,
+                                   unsigned int nr)
+{
+        unsigned int i;
+
+        for (i = 0; i < nr; i++)
+                rom_out_be16(port, *buf++);
+}
+
+static inline void raw_rom_insw_swapw(volatile u16 __iomem *port, u16 *buf,
+                                   unsigned int nr)
+{
+        unsigned int i;
+
+        for (i = 0; i < nr; i++)
+                *buf++ = rom_in_le16(port);
+}
+
+static inline void raw_rom_outsw_swapw(volatile u16 __iomem *port, const u16 *buf,
+                                   unsigned int nr)
+{
+        unsigned int i;
+
+        for (i = 0; i < nr; i++)
+                rom_out_le16(port, *buf++);
+}
+#endif /* CONFIG_ATARI_ROM_ISA */
+
 #endif /* __KERNEL__ */
 
 #endif /* _RAW_IO_H */
diff --git a/arch/m68k/include/asm/string.h b/arch/m68k/include/asm/string.h
index 32198454da70..9aea9f11fa25 100644
--- a/arch/m68k/include/asm/string.h
+++ b/arch/m68k/include/asm/string.h
@@ -4,15 +4,6 @@
 #include <linux/types.h>
 #include <linux/compiler.h>
 
-static inline size_t __kernel_strlen(const char *s)
-{
-        const char *sc;
-
-        for (sc = s; *sc++; )
-                ;
-        return sc - s - 1;
-}
-
 static inline char *__kernel_strcpy(char *dest, const char *src)
 {
         char *xdest = dest;
@@ -27,11 +18,6 @@ static inline char *__kernel_strcpy(char *dest, const char *src)
 
 #ifndef __IN_STRING_C
 
-#define __HAVE_ARCH_STRLEN
-#define strlen(s)       (__builtin_constant_p(s) ?      \
-                         __builtin_strlen(s) :          \
-                         __kernel_strlen(s))
-
 #define __HAVE_ARCH_STRNLEN
 static inline size_t strnlen(const char *s, size_t count)
 {
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index d538694ad208..c55ff719fa72 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -51,40 +51,16 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
                 return sw->retpc;
 }
 
-/*
- * The idle loop on an m68k..
- */
-static void default_idle(void)
+void arch_cpu_idle(void)
 {
-        if (!need_resched())
 #if defined(MACH_ATARI_ONLY)
-                /* block out HSYNC on the atari (falcon) */
-                __asm__("stop #0x2200" : : : "cc");
+        /* block out HSYNC on the atari (falcon) */
+        __asm__("stop #0x2200" : : : "cc");
 #else
-                __asm__("stop #0x2000" : : : "cc");
+        __asm__("stop #0x2000" : : : "cc");
 #endif
 }
 
-void (*idle)(void) = default_idle;
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
-{
-        /* endless idle loop with no priority at all */
-        while (1) {
-                rcu_idle_enter();
-                while (!need_resched())
-                        idle();
-                rcu_idle_exit();
-                schedule_preempt_disabled();
-        }
-}
-
 void machine_restart(char * __unused)
 {
         if (mach_reset)
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index 80cfbe56ea32..e67e53159573 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -381,6 +381,12 @@ void __init setup_arch(char **cmdline_p)
                 isa_sex = 1;
         }
 #endif
+#ifdef CONFIG_ATARI_ROM_ISA
+        if (MACH_IS_ATARI) {
+                isa_type = ISA_TYPE_ENEC;
+                isa_sex = 0;
+        }
+#endif
 #endif
 }
 
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index 71fb29938dba..911ba472e6c4 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -57,6 +57,9 @@ void (*mach_reset)(void);
 void (*mach_halt)(void);
 void (*mach_power_off)(void);
 
+#ifdef CONFIG_M68000
+#define CPU_NAME        "MC68000"
+#endif
 #ifdef CONFIG_M68328
 #define CPU_NAME        "MC68328"
 #endif
diff --git a/arch/m68k/lib/string.c b/arch/m68k/lib/string.c
index b9a57abfad08..4d61fa8a112c 100644
--- a/arch/m68k/lib/string.c
+++ b/arch/m68k/lib/string.c
@@ -17,6 +17,6 @@ EXPORT_SYMBOL(strcpy);
 
 char *strcat(char *dest, const char *src)
 {
-        return __kernel_strcpy(dest + __kernel_strlen(dest), src);
+        return __kernel_strcpy(dest + strlen(dest), src);
 }
 EXPORT_SYMBOL(strcat);
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index afd8106fd83b..1af2ca3411f6 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -110,18 +110,7 @@ void __init paging_init(void)
 void free_initmem(void)
 {
 #ifndef CONFIG_MMU_SUN3
-        unsigned long addr;
-
-        addr = (unsigned long) __init_begin;
-        for (; addr < ((unsigned long) __init_end); addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-        pr_notice("Freeing unused kernel memory: %luk freed (0x%x - 0x%x)\n",
-                (addr - (unsigned long) __init_begin) >> 10,
-                (unsigned int) __init_begin, (unsigned int) __init_end);
+        free_initmem_default(0);
 #endif /* CONFIG_MMU_SUN3 */
 }
 
@@ -188,7 +177,7 @@ void __init mem_init(void)
                 }
         }
 
-#if !defined(CONFIG_SUN3) && !defined(CONFIG_COLDFIRE)
+#if defined(CONFIG_MMU) && !defined(CONFIG_SUN3) && !defined(CONFIG_COLDFIRE)
         /* insert pointer tables allocated so far into the tablelist */
         init_pointer_table((unsigned long)kernel_pg_dir);
         for (i = 0; i < PTRS_PER_PGD; i++) {
@@ -213,15 +202,6 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        int pages = 0;
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page(start);
-                totalram_pages++;
-                pages++;
-        }
-        pr_notice("Freeing initrd memory: %dk freed\n",
-                pages << (PAGE_SHIFT - 10));
+        free_reserved_area(start, end, 0, "initrd");
 }
 #endif
diff --git a/arch/m68k/platform/coldfire/m528x.c b/arch/m68k/platform/coldfire/m528x.c
index 83b7dad7a84e..b03a9d271837 100644
--- a/arch/m68k/platform/coldfire/m528x.c
+++ b/arch/m68k/platform/coldfire/m528x.c
@@ -69,7 +69,7 @@ static void __init m528x_uarts_init(void)
         u8 port;
 
         /* make sure PUAPAR is set for UART0 and UART1 */
-        port = readb(MCF5282_GPIO_PUAPAR);
+        port = readb(MCFGPIO_PUAPAR);
         port |= 0x03 | (0x03 << 2);
         writeb(port, MCFGPIO_PUAPAR);
 }
diff --git a/arch/metag/include/asm/thread_info.h b/arch/metag/include/asm/thread_info.h
index 0ecd34d8b5f6..7c4a33006142 100644
--- a/arch/metag/include/asm/thread_info.h
+++ b/arch/metag/include/asm/thread_info.h
@@ -150,6 +150,4 @@ static inline int kstack_end(void *addr)
 #define _TIF_WORK_MASK          (_TIF_ALLWORK_MASK & ~(_TIF_SYSCALL_TRACE | \
                                  _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP))
 
-#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
-
 #endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/metag/kernel/process.c b/arch/metag/kernel/process.c
index c6efe62e5b76..dc5923544560 100644
--- a/arch/metag/kernel/process.c
+++ b/arch/metag/kernel/process.c
@@ -22,6 +22,7 @@
 #include <linux/pm.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/smp.h>
 #include <asm/core_reg.h>
 #include <asm/user_gateway.h>
 #include <asm/tcm.h>
@@ -31,7 +32,7 @@
 /*
  * Wait for the next interrupt and enable local interrupts
  */
-static inline void arch_idle(void)
+void arch_cpu_idle(void)
 {
         int tmp;
 
@@ -59,36 +60,12 @@ static inline void arch_idle(void)
                       : "r" (get_trigger_mask()));
 }
 
-void cpu_idle(void)
-{
-        set_thread_flag(TIF_POLLING_NRFLAG);
-
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-
-                while (!need_resched()) {
-                        /*
-                         * We need to disable interrupts here to ensure we don't
-                         * miss a wakeup call.
-                         */
-                        local_irq_disable();
-                        if (!need_resched()) {
 #ifdef CONFIG_HOTPLUG_CPU
-                                if (cpu_is_offline(smp_processor_id()))
-                                        cpu_die();
-#endif
-                                arch_idle();
-                        } else {
-                                local_irq_enable();
-                        }
-                }
-
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                schedule_preempt_disabled();
-         }
+void arch_cpu_idle_dead(void)
+{
+        cpu_die();
 }
+#endif
 
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c
index 4e7751ac75d2..f443ec9a7cbe 100644
--- a/arch/metag/kernel/smp.c
+++ b/arch/metag/kernel/smp.c
@@ -412,7 +412,7 @@ asmlinkage void secondary_start_kernel(void)
         /*
          * OK, it's off to the idle thread for us
          */
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
index 504a398d5f8b..d05b8455c44c 100644
--- a/arch/metag/mm/init.c
+++ b/arch/metag/mm/init.c
@@ -380,14 +380,8 @@ void __init mem_init(void)
 
 #ifdef CONFIG_HIGHMEM
         unsigned long tmp;
-        for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) {
-                struct page *page = pfn_to_page(tmp);
-                ClearPageReserved(page);
-                init_page_count(page);
-                __free_page(page);
-                totalhigh_pages++;
-        }
-        totalram_pages += totalhigh_pages;
+        for (tmp = highstart_pfn; tmp < highend_pfn; tmp++)
+                free_highmem_page(pfn_to_page(tmp));
         num_physpages += totalhigh_pages;
 #endif /* CONFIG_HIGHMEM */
 
@@ -412,32 +406,15 @@ void __init mem_init(void)
         return;
 }
 
-static void free_init_pages(char *what, unsigned long begin, unsigned long end)
-{
-        unsigned long addr;
-
-        for (addr = begin; addr < end; addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-                free_page(addr);
-                totalram_pages++;
-        }
-        pr_info("Freeing %s: %luk freed\n", what, (end - begin) >> 10);
-}
-
 void free_initmem(void)
 {
-        free_init_pages("unused kernel memory",
-                        (unsigned long)(&__init_begin),
-                        (unsigned long)(&__init_end));
+        free_initmem_default(POISON_FREE_INITMEM);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        end = end & PAGE_MASK;
-        free_init_pages("initrd memory", start, end);
+        free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd");
 }
 #endif
 
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 9dbb2448a9b2..54237af0b07c 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -19,13 +19,14 @@ config MICROBLAZE
         select HAVE_DEBUG_KMEMLEAK
         select IRQ_DOMAIN
         select HAVE_GENERIC_HARDIRQS
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select GENERIC_IRQ_PROBE
         select GENERIC_IRQ_SHOW
         select GENERIC_PCI_IOMAP
         select GENERIC_CPU_DEVICES
         select GENERIC_ATOMIC64
         select GENERIC_CLOCKEVENTS
+        select GENERIC_IDLE_POLL_SETUP
         select MODULES_USE_ELF_RELA
         select CLONE_BACKWARDS
 
diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index 0759153e8117..d6e0ffea28b6 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/arch/microblaze/include/asm/processor.h
@@ -22,7 +22,6 @@
 extern const struct seq_operations cpuinfo_op;
 
 # define cpu_relax()            barrier()
-# define cpu_sleep()            do {} while (0)
 
 #define task_pt_regs(tsk) \
                 (((struct pt_regs *)(THREAD_SIZE + task_stack_page(tsk))) - 1)
@@ -160,10 +159,6 @@ unsigned long get_wchan(struct task_struct *p);
 #  define STACK_TOP     TASK_SIZE
 #  define STACK_TOP_MAX STACK_TOP
 
-void disable_hlt(void);
-void enable_hlt(void);
-void default_idle(void);
-
 #ifdef CONFIG_DEBUG_FS
 extern struct dentry *of_debugfs_root;
 #endif
diff --git a/arch/microblaze/include/asm/setup.h b/arch/microblaze/include/asm/setup.h
index 0e0b0a5ec756..f05df5630c84 100644
--- a/arch/microblaze/include/asm/setup.h
+++ b/arch/microblaze/include/asm/setup.h
@@ -46,7 +46,6 @@ void machine_shutdown(void);
 void machine_halt(void);
 void machine_power_off(void);
 
-void free_init_pages(char *what, unsigned long begin, unsigned long end);
 extern void *alloc_maybe_bootmem(size_t size, gfp_t mask);
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 
diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h
index 008f30433d22..de26ea6373de 100644
--- a/arch/microblaze/include/asm/thread_info.h
+++ b/arch/microblaze/include/asm/thread_info.h
@@ -182,7 +182,6 @@ static inline bool test_and_clear_restore_sigmask(void)
         ti->status &= ~TS_RESTORE_SIGMASK;
         return true;
 }
-#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/arch/microblaze/kernel/early_printk.c b/arch/microblaze/kernel/early_printk.c
index 60dcacc68038..365f2d53f1b2 100644
--- a/arch/microblaze/kernel/early_printk.c
+++ b/arch/microblaze/kernel/early_printk.c
@@ -21,7 +21,6 @@
 #include <asm/setup.h>
 #include <asm/prom.h>
 
-static u32 early_console_initialized;
 static u32 base_addr;
 
 #ifdef CONFIG_SERIAL_UARTLITE_CONSOLE
@@ -109,27 +108,11 @@ static struct console early_serial_uart16550_console = {
 };
 #endif /* CONFIG_SERIAL_8250_CONSOLE */
 
-static struct console *early_console;
-
-void early_printk(const char *fmt, ...)
-{
-        char buf[512];
-        int n;
-        va_list ap;
-
-        if (early_console_initialized) {
-                va_start(ap, fmt);
-                n = vscnprintf(buf, 512, fmt, ap);
-                early_console->write(early_console, buf, n);
-                va_end(ap);
-        }
-}
-
 int __init setup_early_printk(char *opt)
 {
         int version = 0;
 
-        if (early_console_initialized)
+        if (early_console)
                 return 1;
 
         base_addr = of_early_console(&version);
@@ -159,7 +142,6 @@ int __init setup_early_printk(char *opt)
                 }
 
                 register_console(early_console);
-                early_console_initialized = 1;
                 return 0;
         }
         return 1;
@@ -169,7 +151,7 @@ int __init setup_early_printk(char *opt)
  * only for early console because of performance degression */
 void __init remap_early_printk(void)
 {
-        if (!early_console_initialized || !early_console)
+        if (!early_console)
                 return;
         pr_info("early_printk_console remapping from 0x%x to ", base_addr);
         base_addr = (u32) ioremap(base_addr, PAGE_SIZE);
@@ -194,9 +176,9 @@ void __init remap_early_printk(void)
 
 void __init disable_early_printk(void)
 {
-        if (!early_console_initialized || !early_console)
+        if (!early_console)
                 return;
         pr_warn("disabling early console\n");
         unregister_console(early_console);
-        early_console_initialized = 0;
+        early_console = NULL;
 }
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index fa0ea609137c..7cce2e9c1719 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -44,71 +44,6 @@ void show_regs(struct pt_regs *regs)
 void (*pm_power_off)(void) = NULL;
 EXPORT_SYMBOL(pm_power_off);
 
-static int hlt_counter = 1;
-
-void disable_hlt(void)
-{
-        hlt_counter++;
-}
-EXPORT_SYMBOL(disable_hlt);
-
-void enable_hlt(void)
-{
-        hlt_counter--;
-}
-EXPORT_SYMBOL(enable_hlt);
-
-static int __init nohlt_setup(char *__unused)
-{
-        hlt_counter = 1;
-        return 1;
-}
-__setup("nohlt", nohlt_setup);
-
-static int __init hlt_setup(char *__unused)
-{
-        hlt_counter = 0;
-        return 1;
-}
-__setup("hlt", hlt_setup);
-
-void default_idle(void)
-{
-        if (likely(hlt_counter)) {
-                local_irq_disable();
-                stop_critical_timings();
-                cpu_relax();
-                start_critical_timings();
-                local_irq_enable();
-        } else {
-                clear_thread_flag(TIF_POLLING_NRFLAG);
-                smp_mb__after_clear_bit();
-                local_irq_disable();
-                while (!need_resched())
-                        cpu_sleep();
-                local_irq_enable();
-                set_thread_flag(TIF_POLLING_NRFLAG);
-        }
-}
-
-void cpu_idle(void)
-{
-        set_thread_flag(TIF_POLLING_NRFLAG);
-
-        /* endless idle loop with no priority at all */
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                while (!need_resched())
-                        default_idle();
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-
-                schedule_preempt_disabled();
-                check_pgt_cache();
-        }
-}
-
 void flush_thread(void)
 {
 }
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 8f8b367c079e..4ec137d13ad7 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -82,13 +82,9 @@ static unsigned long highmem_setup(void)
                 /* FIXME not sure about */
                 if (memblock_is_reserved(pfn << PAGE_SHIFT))
                         continue;
-                ClearPageReserved(page);
-                init_page_count(page);
-                __free_page(page);
-                totalhigh_pages++;
+                free_highmem_page(page);
                 reservedpages++;
         }
-        totalram_pages += totalhigh_pages;
         pr_info("High memory: %luk\n",
                                         totalhigh_pages << (PAGE_SHIFT-10));
 
@@ -236,40 +232,16 @@ void __init setup_memory(void)
         paging_init();
 }
 
-void free_init_pages(char *what, unsigned long begin, unsigned long end)
-{
-        unsigned long addr;
-
-        for (addr = begin; addr < end; addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-        pr_info("Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
-}
-
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        int pages = 0;
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page(start);
-                totalram_pages++;
-                pages++;
-        }
-        pr_notice("Freeing initrd memory: %dk freed\n",
-                                        (int)(pages * (PAGE_SIZE / 1024)));
+        free_reserved_area(start, end, 0, "initrd");
 }
 #endif
 
 void free_initmem(void)
 {
-        free_init_pages("unused kernel memory",
-                        (unsigned long)(&__init_begin),
-                        (unsigned long)(&__init_end));
+        free_initmem_default(0);
 }
 
 void __init mem_init(void)
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index ae9c716c46bb..3a7b3954ce1b 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -18,7 +18,7 @@ config MIPS
         select HAVE_KRETPROBES
         select HAVE_DEBUG_KMEMLEAK
         select ARCH_BINFMT_ELF_RANDOMIZE_PIE
-        select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+        select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT
         select RTC_LIB if !MACH_LOONGSON
         select GENERIC_ATOMIC64 if !64BIT
         select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
@@ -38,7 +38,7 @@ config MIPS
         select GENERIC_CLOCKEVENTS
         select GENERIC_CMOS_UPDATE
         select HAVE_MOD_ARCH_SPECIFIC
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select MODULES_USE_ELF_REL if MODULES
         select MODULES_USE_ELF_RELA if MODULES && 64BIT
         select CLONE_BACKWARDS
@@ -404,6 +404,8 @@ config PMC_MSP
         select IRQ_CPU
         select SERIAL_8250
         select SERIAL_8250_CONSOLE
+        select USB_EHCI_BIG_ENDIAN_MMIO
+        select USB_EHCI_BIG_ENDIAN_DESC
         help
           This adds support for the PMC-Sierra family of Multi-Service
           Processor System-On-A-Chips.  These parts include a number
@@ -657,7 +659,7 @@ config SNI_RM
         bool "SNI RM200/300/400"
         select FW_ARC if CPU_LITTLE_ENDIAN
         select FW_ARC32 if CPU_LITTLE_ENDIAN
-        select SNIPROM if CPU_BIG_ENDIAN
+        select FW_SNIPROM if CPU_BIG_ENDIAN
         select ARCH_MAY_HAVE_PC_FDC
         select BOOT_ELF32
         select CEVT_R4K
@@ -1144,7 +1146,7 @@ config DEFAULT_SGI_PARTITION
 config FW_ARC32
         bool
 
-config SNIPROM
+config FW_SNIPROM
         bool
 
 config BOOT_ELF32
@@ -1433,6 +1435,7 @@ config CPU_CAVIUM_OCTEON
         select CPU_SUPPORTS_HUGEPAGES
         select LIBFDT
         select USE_OF
+        select USB_EHCI_BIG_ENDIAN_MMIO
         help
           The Cavium Octeon processor is a highly integrated chip containing
           many ethernet hardware widgets for networking tasks. The processor
@@ -1493,7 +1496,6 @@ config CPU_XLP
         select CPU_SUPPORTS_32BIT_KERNEL
         select CPU_SUPPORTS_64BIT_KERNEL
         select CPU_SUPPORTS_HIGHMEM
-        select CPU_HAS_LLSC
         select WEAK_ORDERING
         select WEAK_REORDERING_BEYOND_LLSC
         select CPU_HAS_PREFETCH
diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c
index ed1949c29508..9aa7d44898ed 100644
--- a/arch/mips/bcm63xx/boards/board_bcm963xx.c
+++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c
@@ -745,10 +745,7 @@ void __init board_prom_init(void)
                 strcpy(cfe_version, "unknown");
         printk(KERN_INFO PFX "CFE version: %s\n", cfe_version);
 
-        if (bcm63xx_nvram_init(boot_addr + BCM963XX_NVRAM_OFFSET)) {
-                printk(KERN_ERR PFX "invalid nvram checksum\n");
-                return;
-        }
+        bcm63xx_nvram_init(boot_addr + BCM963XX_NVRAM_OFFSET);
 
         board_name = bcm63xx_nvram_get_name();
         /* find board by name */
diff --git a/arch/mips/bcm63xx/dev-spi.c b/arch/mips/bcm63xx/dev-spi.c
index f1c9c3e2f678..e97fd60e92ef 100644
--- a/arch/mips/bcm63xx/dev-spi.c
+++ b/arch/mips/bcm63xx/dev-spi.c
@@ -85,20 +85,9 @@ static struct platform_device bcm63xx_spi_device = {
 
 int __init bcm63xx_spi_register(void)
 {
-        struct clk *periph_clk;
-
         if (BCMCPU_IS_6328() || BCMCPU_IS_6345())
                 return -ENODEV;
 
-        periph_clk = clk_get(NULL, "periph");
-        if (IS_ERR(periph_clk)) {
-                pr_err("unable to get periph clock\n");
-                return -ENODEV;
-        }
-
-        /* Set bus frequency */
-        spi_pdata.speed_hz = clk_get_rate(periph_clk);
-
         spi_resources[0].start = bcm63xx_regset_address(RSET_SPI);
         spi_resources[0].end = spi_resources[0].start;
         spi_resources[1].start = bcm63xx_get_irq_number(IRQ_SPI);
diff --git a/arch/mips/bcm63xx/nvram.c b/arch/mips/bcm63xx/nvram.c
index 620611680839..a4b8864f9307 100644
--- a/arch/mips/bcm63xx/nvram.c
+++ b/arch/mips/bcm63xx/nvram.c
@@ -38,7 +38,7 @@ struct bcm963xx_nvram {
 static struct bcm963xx_nvram nvram;
 static int mac_addr_used;
 
-int __init bcm63xx_nvram_init(void *addr)
+void __init bcm63xx_nvram_init(void *addr)
 {
         unsigned int check_len;
         u32 crc, expected_crc;
@@ -60,9 +60,8 @@ int __init bcm63xx_nvram_init(void *addr)
         crc = crc32_le(~0, (u8 *)&nvram, check_len);
 
         if (crc != expected_crc)
-                return -EINVAL;
-
-        return 0;
+                pr_warn("nvram checksum failed, contents may be invalid (expected %08x, got %08x)\n",
+                        expected_crc, crc);
 }
 
 u8 *bcm63xx_nvram_get_name(void)
diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c
index 314231be788c..35e18e98beb9 100644
--- a/arch/mips/bcm63xx/setup.c
+++ b/arch/mips/bcm63xx/setup.c
@@ -157,4 +157,4 @@ int __init bcm63xx_register_devices(void)
         return board_register_devices();
 }
 
-device_initcall(bcm63xx_register_devices);
+arch_initcall(bcm63xx_register_devices);
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index c594a3d4f743..b0baa299f899 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -174,7 +174,10 @@ static int octeon_kexec_prepare(struct kimage *image)
 
 static void octeon_generic_shutdown(void)
 {
-        int cpu, i;
+        int i;
+#ifdef CONFIG_SMP
+        int cpu;
+#endif
         struct cvmx_bootmem_desc *bootmem_desc;
         void *named_block_array_ptr;
 
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index ef99db994c2f..fe0d15d32660 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -10,6 +10,7 @@
 #define __ASM_HUGETLB_H
 
 #include <asm/page.h>
+#include <asm-generic/hugetlb.h>
 
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h
index c9bae1362606..b0184cf02575 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h
@@ -13,7 +13,6 @@ struct bcm63xx_spi_pdata {
         unsigned int    msg_ctl_width;
         int             bus_num;
         int             num_chipselect;
-        u32             speed_hz;
 };
 
 enum bcm63xx_regs_spi {
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
index 62d6a3b4d3b7..4e0b6bc1165e 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
@@ -9,10 +9,8 @@
  *
  * Initialized the local nvram copy from the target address and checks
  * its checksum.
- *
- * Returns 0 on success.
  */
-int __init bcm63xx_nvram_init(void *nvram);
+void bcm63xx_nvram_init(void *nvram);
 
 /**
  * bcm63xx_nvram_get_name() - returns the board name according to nvram
diff --git a/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h b/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h
index d9c828419037..193c0912d38e 100644
--- a/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h
@@ -28,11 +28,7 @@
 /* #define cpu_has_prefetch     ? */
 #define cpu_has_mcheck          1
 /* #define cpu_has_ejtag        ? */
-#ifdef CONFIG_CPU_HAS_LLSC
 #define cpu_has_llsc            1
-#else
-#define cpu_has_llsc            0
-#endif
 /* #define cpu_has_vtag_icache  ? */
 /* #define cpu_has_dc_aliases   ? */
 /* #define cpu_has_ic_fills_f_dc ? */
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 12b70c25906a..0da44d422f5b 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1166,7 +1166,10 @@ do {									\
         unsigned int __dspctl;                                          \
                                                                         \
         __asm__ __volatile__(                                           \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
         "       rddsp   %0, %x1                                 \n"     \
+        "       .set pop                                        \n"     \
         : "=r" (__dspctl)                                               \
         : "i" (mask));                                                  \
         __dspctl;                                                       \
@@ -1175,30 +1178,198 @@ do {									\
 #define wrdsp(val, mask)                                                \
 do {                                                                    \
         __asm__ __volatile__(                                           \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
         "       wrdsp   %0, %x1                                 \n"     \
+        "       .set pop                                        \n"     \
         :                                                               \
         : "r" (val), "i" (mask));                                       \
 } while (0)
 
-#define mflo0() ({ long mflo0; __asm__("mflo %0, $ac0" : "=r" (mflo0)); mflo0;})
-#define mflo1() ({ long mflo1; __asm__("mflo %0, $ac1" : "=r" (mflo1)); mflo1;})
-#define mflo2() ({ long mflo2; __asm__("mflo %0, $ac2" : "=r" (mflo2)); mflo2;})
-#define mflo3() ({ long mflo3; __asm__("mflo %0, $ac3" : "=r" (mflo3)); mflo3;})
-
-#define mfhi0() ({ long mfhi0; __asm__("mfhi %0, $ac0" : "=r" (mfhi0)); mfhi0;})
-#define mfhi1() ({ long mfhi1; __asm__("mfhi %0, $ac1" : "=r" (mfhi1)); mfhi1;})
-#define mfhi2() ({ long mfhi2; __asm__("mfhi %0, $ac2" : "=r" (mfhi2)); mfhi2;})
-#define mfhi3() ({ long mfhi3; __asm__("mfhi %0, $ac3" : "=r" (mfhi3)); mfhi3;})
-
-#define mtlo0(x) __asm__("mtlo %0, $ac0" ::"r" (x))
-#define mtlo1(x) __asm__("mtlo %0, $ac1" ::"r" (x))
-#define mtlo2(x) __asm__("mtlo %0, $ac2" ::"r" (x))
-#define mtlo3(x) __asm__("mtlo %0, $ac3" ::"r" (x))
-
-#define mthi0(x) __asm__("mthi %0, $ac0" ::"r" (x))
-#define mthi1(x) __asm__("mthi %0, $ac1" ::"r" (x))
-#define mthi2(x) __asm__("mthi %0, $ac2" ::"r" (x))
-#define mthi3(x) __asm__("mthi %0, $ac3" ::"r" (x))
+#define mflo0()                                                         \
+({                                                                      \
+        long mflo0;                                                     \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mflo %0, $ac0                                   \n"     \
+        "       .set pop                                        \n"     \
+        : "=r" (mflo0));                                                \
+        mflo0;                                                          \
+})
+
+#define mflo1()                                                         \
+({                                                                      \
+        long mflo1;                                                     \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mflo %0, $ac1                                   \n"     \
+        "       .set pop                                        \n"     \
+        : "=r" (mflo1));                                                \
+        mflo1;                                                          \
+})
+
+#define mflo2()                                                         \
+({                                                                      \
+        long mflo2;                                                     \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mflo %0, $ac2                                   \n"     \
+        "       .set pop                                        \n"     \
+        : "=r" (mflo2));                                                \
+        mflo2;                                                          \
+})
+
+#define mflo3()                                                         \
+({                                                                      \
+        long mflo3;                                                     \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mflo %0, $ac3                                   \n"     \
+        "       .set pop                                        \n"     \
+        : "=r" (mflo3));                                                \
+        mflo3;                                                          \
+})
+
+#define mfhi0()                                                         \
+({                                                                      \
+        long mfhi0;                                                     \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mfhi %0, $ac0                                   \n"     \
+        "       .set pop                                        \n"     \
+        : "=r" (mfhi0));                                                \
+        mfhi0;                                                          \
+})
+
+#define mfhi1()                                                         \
+({                                                                      \
+        long mfhi1;                                                     \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mfhi %0, $ac1                                   \n"     \
+        "       .set pop                                        \n"     \
+        : "=r" (mfhi1));                                                \
+        mfhi1;                                                          \
+})
+
+#define mfhi2()                                                         \
+({                                                                      \
+        long mfhi2;                                                     \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mfhi %0, $ac2                                   \n"     \
+        "       .set pop                                        \n"     \
+        : "=r" (mfhi2));                                                \
+        mfhi2;                                                          \
+})
+
+#define mfhi3()                                                         \
+({                                                                      \
+        long mfhi3;                                                     \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mfhi %0, $ac3                                   \n"     \
+        "       .set pop                                        \n"     \
+        : "=r" (mfhi3));                                                \
+        mfhi3;                                                          \
+})
+
+
+#define mtlo0(x)                                                        \
+({                                                                      \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mtlo %0, $ac0                                   \n"     \
+        "       .set pop                                        \n"     \
+        :                                                               \
+        : "r" (x));                                                     \
+})
+
+#define mtlo1(x)                                                        \
+({                                                                      \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mtlo %0, $ac1                                   \n"     \
+        "       .set pop                                        \n"     \
+        :                                                               \
+        : "r" (x));                                                     \
+})
+
+#define mtlo2(x)                                                        \
+({                                                                      \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mtlo %0, $ac2                                   \n"     \
+        "       .set pop                                        \n"     \
+        :                                                               \
+        : "r" (x));                                                     \
+})
+
+#define mtlo3(x)                                                        \
+({                                                                      \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mtlo %0, $ac3                                   \n"     \
+        "       .set pop                                        \n"     \
+        :                                                               \
+        : "r" (x));                                                     \
+})
+
+#define mthi0(x)                                                        \
+({                                                                      \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mthi %0, $ac0                                   \n"     \
+        "       .set pop                                        \n"     \
+        :                                                               \
+        : "r" (x));                                                     \
+})
+
+#define mthi1(x)                                                        \
+({                                                                      \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mthi %0, $ac1                                   \n"     \
+        "       .set pop                                        \n"     \
+        :                                                               \
+        : "r" (x));                                                     \
+})
+
+#define mthi2(x)                                                        \
+({                                                                      \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mthi %0, $ac2                                   \n"     \
+        "       .set pop                                        \n"     \
+        :                                                               \
+        : "r" (x));                                                     \
+})
+
+#define mthi3(x)                                                        \
+({                                                                      \
+        __asm__(                                                        \
+        "       .set push                                       \n"     \
+        "       .set dsp                                        \n"     \
+        "       mthi %0, $ac3                                   \n"     \
+        "       .set pop                                        \n"     \
+        :                                                               \
+        : "r" (x));                                                     \
+})
 
 #else
 
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index 99fc547af9d3..eab99e536b5c 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -31,7 +31,7 @@
 #define PAGE_SHIFT      16
 #endif
 #define PAGE_SIZE       (_AC(1,UL) << PAGE_SHIFT)
-#define PAGE_MASK       (~(PAGE_SIZE - 1))
+#define PAGE_MASK       (~((1 << PAGE_SHIFT) - 1))
 
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 #define HPAGE_SHIFT     (PAGE_SHIFT + PAGE_SHIFT - 3)
diff --git a/arch/mips/include/asm/signal.h b/arch/mips/include/asm/signal.h
index 197f6367c201..8efe5a9e2c3e 100644
--- a/arch/mips/include/asm/signal.h
+++ b/arch/mips/include/asm/signal.h
@@ -21,6 +21,6 @@
 #include <asm/sigcontext.h>
 #include <asm/siginfo.h>
 
-#define __ARCH_HAS_ODD_SIGACTION
+#define __ARCH_HAS_IRIX_SIGACTION
 
 #endif /* _ASM_SIGNAL_H */
diff --git a/arch/mips/include/uapi/asm/signal.h b/arch/mips/include/uapi/asm/signal.h
index d6b18b4d0f3a..addb9f556b71 100644
--- a/arch/mips/include/uapi/asm/signal.h
+++ b/arch/mips/include/uapi/asm/signal.h
@@ -72,6 +72,12 @@ typedef unsigned long old_sigset_t;		/* at least 32 bits */
  *
  * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
  * Unix names RESETHAND and NODEFER respectively.
+ *
+ * SA_RESTORER used to be defined as 0x04000000 but only the O32 ABI ever
+ * supported its use and no libc was using it, so the entire sa-restorer
+ * functionality was removed with lmo commit 39bffc12c3580ab for 2.5.48
+ * retaining only the SA_RESTORER definition as a reminder to avoid
+ * accidental reuse of the mask bit.
  */
 #define SA_ONSTACK      0x08000000
 #define SA_RESETHAND    0x80000000
@@ -84,8 +90,6 @@ typedef unsigned long old_sigset_t;		/* at least 32 bits */
 #define SA_NOMASK       SA_NODEFER
 #define SA_ONESHOT      SA_RESETHAND
 
-#define SA_RESTORER     0x04000000      /* Only for o32 */
-
 #define MINSIGSTKSZ    2048
 #define SIGSTKSZ       8192
 
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index f81d98f6184c..de75fb50562b 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -100,29 +100,16 @@ obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event_mipsxx.o
 obj-$(CONFIG_JUMP_LABEL)        += jump_label.o
 
 #
-# DSP ASE supported for MIPS32 or MIPS64 Release 2 cores only. It is safe
-# to enable DSP assembler support here even if the MIPS Release 2 CPU we
-# are targetting does not support DSP because all code-paths making use of
-# it properly check that the running CPU *actually does* support these
-# instructions.
+# DSP ASE supported for MIPS32 or MIPS64 Release 2 cores only. It is not
+# safe to unconditionnaly use the assembler -mdsp / -mdspr2 switches
+# here because the compiler may use DSP ASE instructions (such as lwx) in
+# code paths where we cannot check that the CPU we are running on supports it.
+# Proper abstraction using HAVE_AS_DSP and macros is done in
+# arch/mips/include/asm/mipsregs.h.
 #
 ifeq ($(CONFIG_CPU_MIPSR2), y)
 CFLAGS_DSP                      = -DHAVE_AS_DSP
 
-#
-# Check if assembler supports DSP ASE
-#
-ifeq ($(call cc-option-yn,-mdsp), y)
-CFLAGS_DSP                      += -mdsp
-endif
-
-#
-# Check if assembler supports DSP ASE Rev2
-#
-ifeq ($(call cc-option-yn,-mdspr2), y)
-CFLAGS_DSP                      += -mdspr2
-endif
-
 CFLAGS_signal.o                 = $(CFLAGS_DSP)
 CFLAGS_signal32.o               = $(CFLAGS_DSP)
 CFLAGS_process.o                = $(CFLAGS_DSP)
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 6bfccc227a95..5fe66a0c3224 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -580,6 +580,9 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
                 c->tlbsize = 48;
                 break;
         case PRID_IMP_VR41XX:
+                set_isa(c, MIPS_CPU_ISA_III);
+                c->options = R4K_OPTS;
+                c->tlbsize = 32;
                 switch (c->processor_id & 0xf0) {
                 case PRID_REV_VR4111:
                         c->cputype = CPU_VR4111;
@@ -604,6 +607,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
                                 __cpu_name[cpu] = "NEC VR4131";
                         } else {
                                 c->cputype = CPU_VR4133;
+                                c->options |= MIPS_CPU_LLSC;
                                 __cpu_name[cpu] = "NEC VR4133";
                         }
                         break;
@@ -613,9 +617,6 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
                         __cpu_name[cpu] = "NEC Vr41xx";
                         break;
                 }
-                set_isa(c, MIPS_CPU_ISA_III);
-                c->options = R4K_OPTS;
-                c->tlbsize = 32;
                 break;
         case PRID_IMP_R4300:
                 c->cputype = CPU_R4300;
@@ -1226,10 +1227,8 @@ __cpuinit void cpu_probe(void)
         if (c->options & MIPS_CPU_FPU) {
                 c->fpu_id = cpu_get_fpu_id();
 
-                if (c->isa_level == MIPS_CPU_ISA_M32R1 ||
-                    c->isa_level == MIPS_CPU_ISA_M32R2 ||
-                    c->isa_level == MIPS_CPU_ISA_M64R1 ||
-                    c->isa_level == MIPS_CPU_ISA_M64R2) {
+                if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 |
+                                    MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)) {
                         if (c->fpu_id & MIPS_FPIR_3D)
                                 c->ases |= MIPS_ASE_MIPS3D;
                 }
diff --git a/arch/mips/kernel/early_printk.c b/arch/mips/kernel/early_printk.c
index 9e6440eaa455..505cb77d1280 100644
--- a/arch/mips/kernel/early_printk.c
+++ b/arch/mips/kernel/early_printk.c
@@ -7,7 +7,9 @@
  * Copyright (C) 2007 MIPS Technologies, Inc.
  *   written by Ralf Baechle (ralf@linux-mips.org)
  */
+#include <linux/kernel.h>
 #include <linux/console.h>
+#include <linux/printk.h>
 #include <linux/init.h>
 
 #include <asm/setup.h>
@@ -24,20 +26,18 @@ static void early_console_write(struct console *con, const char *s, unsigned n)
         }
 }
 
-static struct console early_console = {
+static struct console early_console_prom = {
         .name   = "early",
         .write  = early_console_write,
         .flags  = CON_PRINTBUFFER | CON_BOOT,
         .index  = -1
 };
 
-static int early_console_initialized __initdata;
-
 void __init setup_early_printk(void)
 {
-        if (early_console_initialized)
+        if (early_console)
                 return;
-        early_console_initialized = 1;
+        early_console = &early_console_prom;
 
-        register_console(&early_console);
+        register_console(&early_console_prom);
 }
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 8eeee1c860c0..db9655f08892 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -171,7 +171,7 @@ SYSCALL_DEFINE6(32_ipc, u32, call, long, first, long, second, long, third,
                 err = compat_sys_shmctl(first, second, compat_ptr(ptr));
                 break;
         default:
-                err = -EINVAL;
+                err = -ENOSYS;
                 break;
         }
 
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 165867673357..33d067148e61 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -46,10 +46,9 @@
         PTR_L   a5, PT_R9(sp)
         PTR_L   a6, PT_R10(sp)
         PTR_L   a7, PT_R11(sp)
-#else
-        PTR_ADDIU       sp, PT_SIZE
 #endif
-.endm
+        PTR_ADDIU       sp, PT_SIZE
+        .endm
 
         .macro RETURN_BACK
         jr ra
@@ -68,7 +67,11 @@ NESTED(ftrace_caller, PT_SIZE, ra)
         .globl _mcount
 _mcount:
         b       ftrace_stub
-        addiu sp,sp,8
+#ifdef CONFIG_32BIT
+         addiu sp,sp,8
+#else
+         nop
+#endif
 
         /* When tracing is activated, it calls ftrace_caller+8 (aka here) */
         lw      t1, function_trace_stop
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index 135c4aadccbe..7a54f74b7818 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -67,7 +67,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
         if (cpu_has_mips_r) {
                 seq_printf(m, "isa\t\t\t:");
                 if (cpu_has_mips_1)
-                        seq_printf(m, "%s", "mips1");
+                        seq_printf(m, "%s", " mips1");
                 if (cpu_has_mips_2)
                         seq_printf(m, "%s", " mips2");
                 if (cpu_has_mips_3)
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 3be4405c2d14..cfc742d75b7f 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -41,44 +41,26 @@
 #include <asm/inst.h>
 #include <asm/stacktrace.h>
 
-/*
- * The idle thread. There's no useful work to be done, so just try to conserve
- * power and have a low exit latency (ie sit in a loop waiting for somebody to
- * say that they'd like to reschedule)
- */
-void __noreturn cpu_idle(void)
+#ifdef CONFIG_HOTPLUG_CPU
+void arch_cpu_idle_dead(void)
 {
-        int cpu;
-
-        /* CPU is going idle. */
-        cpu = smp_processor_id();
+        /* What the heck is this check doing ? */
+        if (!cpu_isset(smp_processor_id(), cpu_callin_map))
+                play_dead();
+}
+#endif
 
-        /* endless idle loop with no priority at all */
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                while (!need_resched() && cpu_online(cpu)) {
+void arch_cpu_idle(void)
+{
 #ifdef CONFIG_MIPS_MT_SMTC
-                        extern void smtc_idle_loop_hook(void);
+        extern void smtc_idle_loop_hook(void);
 
-                        smtc_idle_loop_hook();
+        smtc_idle_loop_hook();
 #endif
-
-                        if (cpu_wait) {
-                                /* Don't trace irqs off for idle */
-                                stop_critical_timings();
-                                (*cpu_wait)();
-                                start_critical_timings();
-                        }
-                }
-#ifdef CONFIG_HOTPLUG_CPU
-                if (!cpu_online(cpu) && !cpu_isset(cpu, cpu_callin_map))
-                        play_dead();
-#endif
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                schedule_preempt_disabled();
-        }
+        if (cpu_wait)
+                (*cpu_wait)();
+        else
+                local_irq_enable();
 }
 
 asmlinkage void ret_from_fork(void);
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 66bf4e22d9b9..aee04af213c5 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -139,7 +139,7 @@ asmlinkage __cpuinit void start_secondary(void)
         WARN_ON_ONCE(!irqs_disabled());
         mp_ops->smp_finish();
 
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 /*
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index a200b5bdbb87..c3abb88170fc 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1571,7 +1571,7 @@ void __cpuinit per_cpu_trap_init(bool is_boot_cpu)
 #ifdef CONFIG_64BIT
         status_set |= ST0_FR|ST0_KX|ST0_SX|ST0_UX;
 #endif
-        if (current_cpu_data.isa_level == MIPS_CPU_ISA_IV)
+        if (current_cpu_data.isa_level & MIPS_CPU_ISA_IV)
                 status_set |= ST0_XX;
         if (cpu_has_dsp)
                 status_set |= ST0_MX;
diff --git a/arch/mips/lib/bitops.c b/arch/mips/lib/bitops.c
index 81f1dcfdcab8..a64daee740ee 100644
--- a/arch/mips/lib/bitops.c
+++ b/arch/mips/lib/bitops.c
@@ -90,12 +90,12 @@ int __mips_test_and_set_bit(unsigned long nr,
         unsigned bit = nr & SZLONG_MASK;
         unsigned long mask;
         unsigned long flags;
-        unsigned long res;
+        int res;
 
         a += nr >> SZLONG_LOG;
         mask = 1UL << bit;
         raw_local_irq_save(flags);
-        res = (mask & *a);
+        res = (mask & *a) != 0;
         *a |= mask;
         raw_local_irq_restore(flags);
         return res;
@@ -116,12 +116,12 @@ int __mips_test_and_set_bit_lock(unsigned long nr,
         unsigned bit = nr & SZLONG_MASK;
         unsigned long mask;
         unsigned long flags;
-        unsigned long res;
+        int res;
 
         a += nr >> SZLONG_LOG;
         mask = 1UL << bit;
         raw_local_irq_save(flags);
-        res = (mask & *a);
+        res = (mask & *a) != 0;
         *a |= mask;
         raw_local_irq_restore(flags);
         return res;
@@ -141,12 +141,12 @@ int __mips_test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
         unsigned bit = nr & SZLONG_MASK;
         unsigned long mask;
         unsigned long flags;
-        unsigned long res;
+        int res;
 
         a += nr >> SZLONG_LOG;
         mask = 1UL << bit;
         raw_local_irq_save(flags);
-        res = (mask & *a);
+        res = (mask & *a) != 0;
         *a &= ~mask;
         raw_local_irq_restore(flags);
         return res;
@@ -166,12 +166,12 @@ int __mips_test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
         unsigned bit = nr & SZLONG_MASK;
         unsigned long mask;
         unsigned long flags;
-        unsigned long res;
+        int res;
 
         a += nr >> SZLONG_LOG;
         mask = 1UL << bit;
         raw_local_irq_save(flags);
-        res = (mask & *a);
+        res = (mask & *a) != 0;
         *a ^= mask;
         raw_local_irq_restore(flags);
         return res;
diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index 507147aebd41..a6adffbb4e5f 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -270,7 +270,7 @@ LEAF(csum_partial)
 #endif
 
         /* odd buffer alignment? */
-#ifdef CPU_MIPSR2
+#ifdef CONFIG_CPU_MIPSR2
         wsbh    v1, sum
         movn    sum, v1, t7
 #else
@@ -670,7 +670,7 @@ EXC(	sb	t0, NBYTES-2(dst), .Ls_exc)
         addu    sum, v1
 #endif
 
-#ifdef CPU_MIPSR2
+#ifdef CONFIG_CPU_MIPSR2
         wsbh    v1, sum
         movn    sum, v1, odd
 #else
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index ecca559b8d7b..2078915eacb9 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1247,10 +1247,8 @@ static void __cpuinit setup_scache(void)
                 return;
 
         default:
-                if (c->isa_level == MIPS_CPU_ISA_M32R1 ||
-                    c->isa_level == MIPS_CPU_ISA_M32R2 ||
-                    c->isa_level == MIPS_CPU_ISA_M64R1 ||
-                    c->isa_level == MIPS_CPU_ISA_M64R2) {
+                if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 |
+                                    MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)) {
 #ifdef CONFIG_MIPS_CPU_SCACHE
                         if (mips_sc_init ()) {
                                 scache_size = c->scache.ways * c->scache.sets * c->scache.linesz;
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 67929251286c..3d0346dbccf4 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -77,10 +77,9 @@ EXPORT_SYMBOL_GPL(empty_zero_page);
 /*
  * Not static inline because used by IP27 special magic initialization code
  */
-unsigned long setup_zero_pages(void)
+void setup_zero_pages(void)
 {
-        unsigned int order;
-        unsigned long size;
+        unsigned int order, i;
         struct page *page;
 
         if (cpu_has_vce)
@@ -94,15 +93,10 @@ unsigned long setup_zero_pages(void)
 
         page = virt_to_page((void *)empty_zero_page);
         split_page(page, order);
-        while (page < virt_to_page((void *)(empty_zero_page + (PAGE_SIZE << order)))) {
-                SetPageReserved(page);
-                page++;
-        }
-
-        size = PAGE_SIZE << order;
-        zero_page_mask = (size - 1) & PAGE_MASK;
+        for (i = 0; i < (1 << order); i++, page++)
+                mark_page_reserved(page);
 
-        return 1UL << order;
+        zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK;
 }
 
 #ifdef CONFIG_MIPS_MT_SMTC
@@ -380,7 +374,7 @@ void __init mem_init(void)
         high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
 
         totalram_pages += free_all_bootmem();
-        totalram_pages -= setup_zero_pages();   /* Setup zeroed pages.  */
+        setup_zero_pages();     /* Setup zeroed pages.  */
 
         reservedpages = ram = 0;
         for (tmp = 0; tmp < max_low_pfn; tmp++)
@@ -399,12 +393,8 @@ void __init mem_init(void)
                         SetPageReserved(page);
                         continue;
                 }
-                ClearPageReserved(page);
-                init_page_count(page);
-                __free_page(page);
-                totalhigh_pages++;
+                free_highmem_page(page);
         }
-        totalram_pages += totalhigh_pages;
         num_physpages += totalhigh_pages;
 #endif
 
@@ -440,11 +430,8 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end)
                 struct page *page = pfn_to_page(pfn);
                 void *addr = phys_to_virt(PFN_PHYS(pfn));
 
-                ClearPageReserved(page);
-                init_page_count(page);
                 memset(addr, POISON_FREE_INITMEM, PAGE_SIZE);
-                __free_page(page);
-                totalram_pages++;
+                free_reserved_page(page);
         }
         printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
 }
@@ -452,18 +439,14 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        free_init_pages("initrd memory",
-                        virt_to_phys((void *)start),
-                        virt_to_phys((void *)end));
+        free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd");
 }
 #endif
 
 void __init_refok free_initmem(void)
 {
         prom_free_prom_memory();
-        free_init_pages("unused kernel memory",
-                        __pa_symbol(&__init_begin),
-                        __pa_symbol(&__init_end));
+        free_initmem_default(POISON_FREE_INITMEM);
 }
 
 #ifndef CONFIG_MIPS_PGD_C0_CONTEXT
diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c
index 93d937b4b1ba..df96da7e939b 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -98,10 +98,8 @@ static inline int __init mips_sc_probe(void)
         c->scache.flags |= MIPS_CACHE_NOT_PRESENT;
 
         /* Ignore anything but MIPSxx processors */
-        if (c->isa_level != MIPS_CPU_ISA_M32R1 &&
-            c->isa_level != MIPS_CPU_ISA_M32R2 &&
-            c->isa_level != MIPS_CPU_ISA_M64R1 &&
-            c->isa_level != MIPS_CPU_ISA_M64R2)
+        if (!(c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 |
+                              MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)))
                 return 0;
 
         /* Does this MIPS32/MIPS64 CPU have a config2 register? */
diff --git a/arch/mips/pci/pci-alchemy.c b/arch/mips/pci/pci-alchemy.c
index 38a80c83fd67..d1faece21b6a 100644
--- a/arch/mips/pci/pci-alchemy.c
+++ b/arch/mips/pci/pci-alchemy.c
@@ -19,7 +19,7 @@
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/tlbmisc.h>
 
-#ifdef CONFIG_DEBUG_PCI
+#ifdef CONFIG_PCI_DEBUG
 #define DBG(x...) printk(KERN_DEBUG x)
 #else
 #define DBG(x...) do {} while (0)
@@ -162,7 +162,7 @@ static int config_access(unsigned char access_type, struct pci_bus *bus,
         if (status & (1 << 29)) {
                 *data = 0xffffffff;
                 error = -1;
-                DBG("alchemy-pci: master abort on cfg access %d bus %d dev %d",
+                DBG("alchemy-pci: master abort on cfg access %d bus %d dev %d\n",
                     access_type, bus->number, device);
         } else if ((status >> 28) & 0xf) {
                 DBG("alchemy-pci: PCI ERR detected: dev %d, status %lx\n",
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index 0872f12f268d..594e60d6a43b 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -115,7 +115,6 @@ static void pcibios_scanbus(struct pci_controller *hose)
                         pci_bus_assign_resources(bus);
                         pci_enable_bridges(bus);
                 }
-                bus->dev.of_node = hose->of_node;
         }
 }
 
@@ -169,6 +168,13 @@ void pci_load_of_ranges(struct pci_controller *hose, struct device_node *node)
                 }
         }
 }
+
+struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
+{
+        struct pci_controller *hose = bus->sysdata;
+
+        return of_node_get(hose->of_node);
+}
 #endif
 
 static DEFINE_MUTEX(pci_scan_mutex);
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index 3505d08ff2fd..5f2bddb1860e 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -457,7 +457,7 @@ void __init prom_free_prom_memory(void)
         /* We got nothing to free here ...  */
 }
 
-extern unsigned long setup_zero_pages(void);
+extern void setup_zero_pages(void);
 
 void __init paging_init(void)
 {
@@ -492,7 +492,7 @@ void __init mem_init(void)
                 totalram_pages += free_all_bootmem_node(NODE_DATA(node));
         }
 
-        totalram_pages -= setup_zero_pages();   /* This comes from node 0 */
+        setup_zero_pages();     /* This comes from node 0 */
 
         codesize =  (unsigned long) &_etext - (unsigned long) &_text;
         datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index b06c7360b1c6..428da175d073 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -8,7 +8,7 @@ config MN10300
         select HAVE_ARCH_KGDB
         select GENERIC_ATOMIC64
         select HAVE_NMI_WATCHDOG if MN10300_WD_TIMER
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select GENERIC_CLOCKEVENTS
         select MODULES_USE_ELF_RELA
         select OLD_SIGSUSPEND3
diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h
index f90062b0622d..224b4262486d 100644
--- a/arch/mn10300/include/asm/thread_info.h
+++ b/arch/mn10300/include/asm/thread_info.h
@@ -165,8 +165,6 @@ void arch_release_thread_info(struct thread_info *ti);
 #define _TIF_WORK_MASK          0x0000FFFE      /* work to do on interrupt/exception return */
 #define _TIF_ALLWORK_MASK       0x0000FFFF      /* work to do on any return to u-space */
 
-#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index 84f4e97e3074..2da39fb8b3b2 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -50,77 +50,19 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
 
-#if !defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
-/*
- * we use this if we don't have any better idle routine
- */
-static void default_idle(void)
-{
-        local_irq_disable();
-        if (!need_resched())
-                safe_halt();
-        else
-                local_irq_enable();
-}
-
-#else /* !CONFIG_SMP || CONFIG_HOTPLUG_CPU  */
 /*
  * On SMP it's slightly faster (but much more power-consuming!)
  * to poll the ->work.need_resched flag instead of waiting for the
  * cross-CPU IPI to arrive. Use this option with caution.
+ *
+ * tglx: No idea why this depends on HOTPLUG_CPU !?!
  */
-static inline void poll_idle(void)
-{
-        int oldval;
-
-        local_irq_enable();
-
-        /*
-         * Deal with another CPU just having chosen a thread to
-         * run here:
-         */
-        oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
-
-        if (!oldval) {
-                set_thread_flag(TIF_POLLING_NRFLAG);
-                while (!need_resched())
-                        cpu_relax();
-                clear_thread_flag(TIF_POLLING_NRFLAG);
-        } else {
-                set_need_resched();
-        }
-}
-#endif /* !CONFIG_SMP || CONFIG_HOTPLUG_CPU */
-
-/*
- * the idle thread
- * - there's no useful work to be done, so just try to conserve power and have
- *   a low exit latency (ie sit in a loop waiting for somebody to say that
- *   they'd like to reschedule)
- */
-void cpu_idle(void)
+#if !defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
+void arch_cpu_idle(void)
 {
-        /* endless idle loop with no priority at all */
-        for (;;) {
-                rcu_idle_enter();
-                while (!need_resched()) {
-                        void (*idle)(void);
-
-                        smp_rmb();
-                        if (!idle) {
-#if defined(CONFIG_SMP) && !defined(CONFIG_HOTPLUG_CPU)
-                                idle = poll_idle;
-#else  /* CONFIG_SMP && !CONFIG_HOTPLUG_CPU */
-                                idle = default_idle;
-#endif /* CONFIG_SMP && !CONFIG_HOTPLUG_CPU */
-                        }
-                        idle();
-                }
-                rcu_idle_exit();
-
-                schedule_preempt_disabled();
-        }
+        safe_halt();
 }
+#endif
 
 void release_segments(struct mm_struct *mm)
 {
diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c
index 5d7e152a23b7..a17f9c9c14c9 100644
--- a/arch/mn10300/kernel/smp.c
+++ b/arch/mn10300/kernel/smp.c
@@ -675,7 +675,7 @@ int __init start_secondary(void *unused)
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
         init_clockevents();
 #endif
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
         return 0;
 }
 
@@ -935,8 +935,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
         int timeout;
 
 #ifdef CONFIG_HOTPLUG_CPU
-        if (num_online_cpus() == 1)
-                disable_hlt();
         if (sleep_mode[cpu])
                 run_wakeup_cpu(cpu);
 #endif /* CONFIG_HOTPLUG_CPU */
@@ -1003,9 +1001,6 @@ int __cpu_disable(void)
 void __cpu_die(unsigned int cpu)
 {
         run_sleep_cpu(cpu);
-
-        if (num_online_cpus() == 1)
-                enable_hlt();
 }
 
 #ifdef CONFIG_MN10300_CACHE_ENABLED
diff --git a/arch/mn10300/mm/init.c b/arch/mn10300/mm/init.c
index e57e5bc23562..5a8ace63a6b4 100644
--- a/arch/mn10300/mm/init.c
+++ b/arch/mn10300/mm/init.c
@@ -139,30 +139,11 @@ void __init mem_init(void)
 }
 
 /*
- *
- */
-void free_init_pages(char *what, unsigned long begin, unsigned long end)
-{
-        unsigned long addr;
-
-        for (addr = begin; addr < end; addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                memset((void *) addr, 0xcc, PAGE_SIZE);
-                free_page(addr);
-                totalram_pages++;
-        }
-        printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
-}
-
-/*
  * recycle memory containing stuff only required for initialisation
  */
 void free_initmem(void)
 {
-        free_init_pages("unused kernel memory",
-                        (unsigned long) &__init_begin,
-                        (unsigned long) &__init_end);
+        free_initmem_default(POISON_FREE_INITMEM);
 }
 
 /*
@@ -171,6 +152,6 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        free_init_pages("initrd memory", start, end);
+        free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd");
 }
 #endif
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 014a6482ed4c..9ab3bf2eca8d 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -9,10 +9,9 @@ config OPENRISC
         select OF_EARLY_FLATTREE
         select IRQ_DOMAIN
         select HAVE_MEMBLOCK
-        select ARCH_WANT_OPTIONAL_GPIOLIB
+        select ARCH_REQUIRE_GPIOLIB
         select HAVE_ARCH_TRACEHOOK
         select HAVE_GENERIC_HARDIRQS
-        select HAVE_VIRT_TO_BUS
         select GENERIC_IRQ_CHIP
         select GENERIC_IRQ_PROBE
         select GENERIC_IRQ_SHOW
diff --git a/arch/openrisc/include/asm/thread_info.h b/arch/openrisc/include/asm/thread_info.h
index 07f3212422ad..d797acc901e4 100644
--- a/arch/openrisc/include/asm/thread_info.h
+++ b/arch/openrisc/include/asm/thread_info.h
@@ -128,8 +128,6 @@ register struct thread_info *current_thread_info_reg asm("r10");
 /* For OpenRISC, this is anything in the LSW other than syscall trace */
 #define _TIF_WORK_MASK (0xff & ~(_TIF_SYSCALL_TRACE|_TIF_SINGLESTEP))
 
-#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile
index 35f92ce51c24..ec6d9d37cefd 100644
--- a/arch/openrisc/kernel/Makefile
+++ b/arch/openrisc/kernel/Makefile
@@ -4,7 +4,7 @@
 
 extra-y := head.o vmlinux.lds
 
-obj-y   := setup.o idle.o or32_ksyms.o process.o dma.o \
+obj-y   := setup.o or32_ksyms.o process.o dma.o \
            traps.o time.o irq.o entry.o ptrace.o signal.o \
            sys_call_table.o
 
diff --git a/arch/openrisc/kernel/idle.c b/arch/openrisc/kernel/idle.c
deleted file mode 100644
index 5e8a3b6d6bc6..000000000000
--- a/arch/openrisc/kernel/idle.c
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- * OpenRISC idle.c
- *
- * Linux architectural port borrowing liberally from similar works of
- * others.  All original copyrights apply as per the original source
- * declaration.
- *
- * Modifications for the OpenRISC architecture:
- * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
- * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
- *
- *      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.
- *
- * Idle daemon for or32.  Idle daemon will handle any action
- * that needs to be taken when the system becomes idle.
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/tick.h>
-
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
-#include <asm/io.h>
-#include <asm/processor.h>
-#include <asm/mmu.h>
-#include <asm/cache.h>
-#include <asm/pgalloc.h>
-
-void (*powersave) (void) = NULL;
-
-void cpu_idle(void)
-{
-        set_thread_flag(TIF_POLLING_NRFLAG);
-
-        /* endless idle loop with no priority at all */
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-
-                while (!need_resched()) {
-                        check_pgt_cache();
-                        rmb();
-
-                        clear_thread_flag(TIF_POLLING_NRFLAG);
-
-                        local_irq_disable();
-                        /* Don't trace irqs off for idle */
-                        stop_critical_timings();
-                        if (!need_resched() && powersave != NULL)
-                                powersave();
-                        start_critical_timings();
-                        local_irq_enable();
-                        set_thread_flag(TIF_POLLING_NRFLAG);
-                }
-
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                preempt_enable_no_resched();
-                schedule();
-                preempt_disable();
-        }
-}
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index e7fdc50c4bf0..b3cbc6703837 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -43,6 +43,7 @@
 #include <asm/kmap_types.h>
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
+#include <asm/sections.h>
 
 int mem_init_done;
 
@@ -201,9 +202,6 @@ void __init paging_init(void)
 
 /* References to section boundaries */
 
-extern char _stext, _etext, _edata, __bss_start, _end;
-extern char __init_begin, __init_end;
-
 static int __init free_pages_init(void)
 {
         int reservedpages, pfn;
@@ -263,30 +261,11 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        printk(KERN_INFO "Freeing initrd memory: %ldk freed\n",
-               (end - start) >> 10);
-
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page(start);
-                totalram_pages++;
-        }
+        free_reserved_area(start, end, 0, "initrd");
 }
 #endif
 
 void free_initmem(void)
 {
-        unsigned long addr;
-
-        addr = (unsigned long)(&__init_begin);
-        for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-        printk(KERN_INFO "Freeing unused kernel memory: %luk freed\n",
-               ((unsigned long)&__init_end -
-                (unsigned long)&__init_begin) >> 10);
+        free_initmem_default(0);
 }
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index a9ff712a2864..0339181bf3ac 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -21,7 +21,7 @@ config PARISC
         select GENERIC_STRNCPY_FROM_USER
         select SYSCTL_ARCH_UNALIGN_ALLOW
         select HAVE_MOD_ARCH_SPECIFIC
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select MODULES_USE_ELF_RELA
         select CLONE_BACKWARDS
         select TTY # Needed for pdc_cons.c
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 01d95e2f0581..113e28206503 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -65,8 +65,10 @@ ifndef CONFIG_FUNCTION_TRACER
 endif
 
 # Use long jumps instead of long branches (needed if your linker fails to
-# link a too big vmlinux executable)
-cflags-$(CONFIG_MLONGCALLS)     += -mlong-calls
+# link a too big vmlinux executable). Not enabled for building modules.
+ifdef CONFIG_MLONGCALLS
+KBUILD_CFLAGS_KERNEL += -mlong-calls
+endif
 
 # select which processor to optimise for
 cflags-$(CONFIG_PA7100)         += -march=1.1 -mschedule=7100
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 79f694f3ad9b..f0e2784e7cca 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -140,7 +140,10 @@ static inline void *kmap(struct page *page)
         return page_address(page);
 }
 
-#define kunmap(page)                    kunmap_parisc(page_address(page))
+static inline void kunmap(struct page *page)
+{
+        kunmap_parisc(page_address(page));
+}
 
 static inline void *kmap_atomic(struct page *page)
 {
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 7df49fad29f9..1e40d7f86be3 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -16,6 +16,8 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 
+extern spinlock_t pa_dbit_lock;
+
 /*
  * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
  * memory.  For the return value to be meaningful, ADDR must be >=
@@ -44,8 +46,11 @@ extern void purge_tlb_entries(struct mm_struct *, unsigned long);
 
 #define set_pte_at(mm, addr, ptep, pteval)                      \
         do {                                                    \
+                unsigned long flags;                            \
+                spin_lock_irqsave(&pa_dbit_lock, flags);        \
                 set_pte(ptep, pteval);                          \
                 purge_tlb_entries(mm, addr);                    \
+                spin_unlock_irqrestore(&pa_dbit_lock, flags);   \
         } while (0)
 
 #endif /* !__ASSEMBLY__ */
@@ -435,48 +440,46 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
 
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
-#ifdef CONFIG_SMP
+        pte_t pte;
+        unsigned long flags;
+
         if (!pte_young(*ptep))
                 return 0;
-        return test_and_clear_bit(xlate_pabit(_PAGE_ACCESSED_BIT), &pte_val(*ptep));
-#else
-        pte_t pte = *ptep;
-        if (!pte_young(pte))
+
+        spin_lock_irqsave(&pa_dbit_lock, flags);
+        pte = *ptep;
+        if (!pte_young(pte)) {
+                spin_unlock_irqrestore(&pa_dbit_lock, flags);
                 return 0;
-        set_pte_at(vma->vm_mm, addr, ptep, pte_mkold(pte));
+        }
+        set_pte(ptep, pte_mkold(pte));
+        purge_tlb_entries(vma->vm_mm, addr);
+        spin_unlock_irqrestore(&pa_dbit_lock, flags);
         return 1;
-#endif
 }
 
-extern spinlock_t pa_dbit_lock;
-
 struct mm_struct;
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
         pte_t old_pte;
+        unsigned long flags;
 
-        spin_lock(&pa_dbit_lock);
+        spin_lock_irqsave(&pa_dbit_lock, flags);
         old_pte = *ptep;
         pte_clear(mm,addr,ptep);
-        spin_unlock(&pa_dbit_lock);
+        purge_tlb_entries(mm, addr);
+        spin_unlock_irqrestore(&pa_dbit_lock, flags);
 
         return old_pte;
 }
 
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-#ifdef CONFIG_SMP
-        unsigned long new, old;
-
-        do {
-                old = pte_val(*ptep);
-                new = pte_val(pte_wrprotect(__pte (old)));
-        } while (cmpxchg((unsigned long *) ptep, old, new) != old);
+        unsigned long flags;
+        spin_lock_irqsave(&pa_dbit_lock, flags);
+        set_pte(ptep, pte_wrprotect(*ptep));
         purge_tlb_entries(mm, addr);
-#else
-        pte_t old_pte = *ptep;
-        set_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
-#endif
+        spin_unlock_irqrestore(&pa_dbit_lock, flags);
 }
 
 #define pte_same(A,B)   (pte_val(A) == pte_val(B))
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index d1fb79a36f3d..6182832e5b6c 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -77,8 +77,6 @@ struct thread_info {
 #define _TIF_SYSCALL_TRACE_MASK (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | \
                                  _TIF_BLOCKSTEP)
 
-#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_PARISC_THREAD_INFO_H */
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 4ba2c93770f1..e0a82358517e 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -181,30 +181,24 @@ struct exception_data {
 #if !defined(CONFIG_64BIT)
 
 #define __put_kernel_asm64(__val,ptr) do {                  \
-        u64 __val64 = (u64)(__val);                         \
-        u32 hi = (__val64) >> 32;                           \
-        u32 lo = (__val64) & 0xffffffff;                    \
         __asm__ __volatile__ (                              \
                 "\n1:\tstw %2,0(%1)"                        \
-                "\n2:\tstw %3,4(%1)\n\t"                    \
+                "\n2:\tstw %R2,4(%1)\n\t"                   \
                 ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\
                 ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\
                 : "=r"(__pu_err)                            \
-                : "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \
+                : "r"(ptr), "r"(__val), "0"(__pu_err) \
                 : "r1");                                    \
 } while (0)
 
 #define __put_user_asm64(__val,ptr) do {                    \
-        u64 __val64 = (u64)(__val);                         \
-        u32 hi = (__val64) >> 32;                           \
-        u32 lo = (__val64) & 0xffffffff;                    \
         __asm__ __volatile__ (                              \
                 "\n1:\tstw %2,0(%%sr3,%1)"                  \
-                "\n2:\tstw %3,4(%%sr3,%1)\n\t"              \
+                "\n2:\tstw %R2,4(%%sr3,%1)\n\t"             \
                 ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\
                 ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\
                 : "=r"(__pu_err)                            \
-                : "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \
+                : "r"(ptr), "r"(__val), "0"(__pu_err) \
                 : "r1");                                    \
 } while (0)
 
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 4b12890642eb..83ded26cad06 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -421,14 +421,11 @@ void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
         /* Note: purge_tlb_entries can be called at startup with
            no context.  */
 
-        /* Disable preemption while we play with %sr1.  */
-        preempt_disable();
-        mtsp(mm->context, 1);
         purge_tlb_start(flags);
+        mtsp(mm->context, 1);
         pdtlb(addr);
         pitlb(addr);
         purge_tlb_end(flags);
-        preempt_enable();
 }
 EXPORT_SYMBOL(purge_tlb_entries);
 
diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index 6795dc6c995f..568b2c61ea02 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -120,11 +120,13 @@ extern void __ashrdi3(void);
 extern void __ashldi3(void);
 extern void __lshrdi3(void);
 extern void __muldi3(void);
+extern void __ucmpdi2(void);
 
 EXPORT_SYMBOL(__ashrdi3);
 EXPORT_SYMBOL(__ashldi3);
 EXPORT_SYMBOL(__lshrdi3);
 EXPORT_SYMBOL(__muldi3);
+EXPORT_SYMBOL(__ucmpdi2);
 
 asmlinkage void * __canonicalize_funcptr_for_compare(void *);
 EXPORT_SYMBOL(__canonicalize_funcptr_for_compare);
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index d13507246c5d..55f92b614182 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -59,28 +59,6 @@
 #include <asm/unwind.h>
 #include <asm/sections.h>
 
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
-{
-        set_thread_flag(TIF_POLLING_NRFLAG);
-
-        /* endless idle loop with no priority at all */
-        while (1) {
-                rcu_idle_enter();
-                while (!need_resched())
-                        barrier();
-                rcu_idle_exit();
-                schedule_preempt_disabled();
-                check_pgt_cache();
-        }
-}
-
-
 #define COMMAND_GLOBAL  F_EXTEND(0xfffe0030)
 #define CMD_RESET       5       /* reset any module */
 
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 6266730efd61..fd1bb1519c2b 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -329,7 +329,7 @@ void __init smp_callin(void)
 
         local_irq_enable();  /* Interrupts have been off until now */
 
-        cpu_idle();      /* Wait for timer to schedule some work */
+        cpu_startup_entry(CPUHP_ONLINE);
 
         /* NOTREACHED */
         panic("smp_callin() AAAAaaaaahhhh....\n");
diff --git a/arch/parisc/lib/Makefile b/arch/parisc/lib/Makefile
index 5f2e6904d14a..5651536ac733 100644
--- a/arch/parisc/lib/Makefile
+++ b/arch/parisc/lib/Makefile
@@ -2,6 +2,7 @@
 # Makefile for parisc-specific library files
 #
 
-lib-y   := lusercopy.o bitops.o checksum.o io.o memset.o fixup.o memcpy.o
+lib-y   := lusercopy.o bitops.o checksum.o io.o memset.o fixup.o memcpy.o \
+           ucmpdi2.o
 
 obj-y   := iomap.o
diff --git a/arch/parisc/lib/ucmpdi2.c b/arch/parisc/lib/ucmpdi2.c
new file mode 100644
index 000000000000..149c016f32c5
--- /dev/null
+++ b/arch/parisc/lib/ucmpdi2.c
@@ -0,0 +1,25 @@
+#include <linux/module.h>
+
+union ull_union {
+        unsigned long long ull;
+        struct {
+                unsigned int high;
+                unsigned int low;
+        } ui;
+};
+
+int __ucmpdi2(unsigned long long a, unsigned long long b)
+{
+        union ull_union au = {.ull = a};
+        union ull_union bu = {.ull = b};
+
+        if (au.ui.high < bu.ui.high)
+                return 0;
+        else if (au.ui.high > bu.ui.high)
+                return 2;
+        if (au.ui.low < bu.ui.low)
+                return 0;
+        else if (au.ui.low > bu.ui.low)
+                return 2;
+        return 1;
+}
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 3ac462de53a4..157b931e7b09 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -505,7 +505,6 @@ static void __init map_pages(unsigned long start_vaddr,
 
 void free_initmem(void)
 {
-        unsigned long addr;
         unsigned long init_begin = (unsigned long)__init_begin;
         unsigned long init_end = (unsigned long)__init_end;
 
@@ -533,19 +532,10 @@ void free_initmem(void)
          * pages are no-longer executable */
         flush_icache_range(init_begin, init_end);
         
-        for (addr = init_begin; addr < init_end; addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                num_physpages++;
-                totalram_pages++;
-        }
+        num_physpages += free_initmem_default(0);
 
         /* set up a new led state on systems shipped LED State panel */
         pdc_chassis_send_status(PDC_CHASSIS_DIRECT_BCOMPLETE);
-        
-        printk(KERN_INFO "Freeing unused kernel memory: %luk freed\n",
-                (init_end - init_begin) >> 10);
 }
 
 
@@ -697,6 +687,8 @@ void show_mem(unsigned int filter)
 
         printk(KERN_INFO "Mem-info:\n");
         show_free_areas(filter);
+        if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+                return;
 #ifndef CONFIG_DISCONTIGMEM
         i = max_mapnr;
         while (i-- > 0) {
@@ -1107,15 +1099,6 @@ void flush_tlb_all(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        if (start >= end)
-                return;
-        printk(KERN_INFO "Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page(start);
-                num_physpages++;
-                totalram_pages++;
-        }
+        num_physpages += free_reserved_area(start, end, 0, "initrd");
 }
 #endif
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b89d7eb730a2..ea5bb045983a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -90,6 +90,7 @@ config GENERIC_GPIO
 config PPC
         bool
         default y
+        select BINFMT_ELF
         select OF
         select OF_EARLY_FLATTREE
         select HAVE_FTRACE_MCOUNT_RECORD
@@ -98,7 +99,7 @@ config PPC
         select HAVE_FUNCTION_GRAPH_TRACER
         select SYSCTL_EXCEPTION_TRACE
         select ARCH_WANT_OPTIONAL_GPIOLIB
-        select HAVE_VIRT_TO_BUS if !PPC64
+        select VIRT_TO_BUS if !PPC64
         select HAVE_IDE
         select HAVE_IOREMAP_PROT
         select HAVE_EFFICIENT_UNALIGNED_ACCESS
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 62e11a32c4c2..4fcbd6b14a3a 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -3,6 +3,7 @@
 
 #ifdef CONFIG_HUGETLB_PAGE
 #include <asm/page.h>
+#include <asm-generic/hugetlb.h>
 
 extern struct kmem_cache *hugepte_cache;
 
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 2fdb47a19efd..b59e06f507ea 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -343,17 +343,16 @@ extern void slb_set_size(u16 size);
 /*
  * VSID allocation (256MB segment)
  *
- * We first generate a 38-bit "proto-VSID".  For kernel addresses this
- * is equal to the ESID | 1 << 37, for user addresses it is:
- *      (context << USER_ESID_BITS) | (esid & ((1U << USER_ESID_BITS) - 1)
+ * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated
+ * from mmu context id and effective segment id of the address.
  *
- * This splits the proto-VSID into the below range
- *  0 - (2^(CONTEXT_BITS + USER_ESID_BITS) - 1) : User proto-VSID range
- *  2^(CONTEXT_BITS + USER_ESID_BITS) - 2^(VSID_BITS) : Kernel proto-VSID range
- *
- * We also have CONTEXT_BITS + USER_ESID_BITS = VSID_BITS - 1
- * That is, we assign half of the space to user processes and half
- * to the kernel.
+ * For user processes max context id is limited to ((1ul << 19) - 5)
+ * for kernel space, we use the top 4 context ids to map address as below
+ * NOTE: each context only support 64TB now.
+ * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
+ * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
+ * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
+ * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
  *
  * The proto-VSIDs are then scrambled into real VSIDs with the
  * multiplicative hash:
@@ -363,41 +362,49 @@ extern void slb_set_size(u16 size);
  * VSID_MULTIPLIER is prime, so in particular it is
  * co-prime to VSID_MODULUS, making this a 1:1 scrambling function.
  * Because the modulus is 2^n-1 we can compute it efficiently without
- * a divide or extra multiply (see below).
- *
- * This scheme has several advantages over older methods:
- *
- *      - We have VSIDs allocated for every kernel address
- * (i.e. everything above 0xC000000000000000), except the very top
- * segment, which simplifies several things.
+ * a divide or extra multiply (see below). The scramble function gives
+ * robust scattering in the hash table (at least based on some initial
+ * results).
  *
- *      - We allow for USER_ESID_BITS significant bits of ESID and
- * CONTEXT_BITS  bits of context for user addresses.
- *  i.e. 64T (46 bits) of address space for up to half a million contexts.
+ * We also consider VSID 0 special. We use VSID 0 for slb entries mapping
+ * bad address. This enables us to consolidate bad address handling in
+ * hash_page.
  *
- *      - The scramble function gives robust scattering in the hash
- * table (at least based on some initial results).  The previous
- * method was more susceptible to pathological cases giving excessive
- * hash collisions.
+ * We also need to avoid the last segment of the last context, because that
+ * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
+ * because of the modulo operation in vsid scramble. But the vmemmap
+ * (which is what uses region 0xf) will never be close to 64TB in size
+ * (it's 56 bytes per page of system memory).
  */
 
+#define CONTEXT_BITS            19
+#define ESID_BITS               18
+#define ESID_BITS_1T            6
+
+/*
+ * 256MB segment
+ * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments
+ * available for user + kernel mapping. The top 4 contexts are used for
+ * kernel mapping. Each segment contains 2^28 bytes. Each
+ * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts
+ * (19 == 37 + 28 - 46).
+ */
+#define MAX_USER_CONTEXT        ((ASM_CONST(1) << CONTEXT_BITS) - 5)
+
 /*
  * This should be computed such that protovosid * vsid_mulitplier
  * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus
  */
 #define VSID_MULTIPLIER_256M    ASM_CONST(12538073)     /* 24-bit prime */
-#define VSID_BITS_256M          38
+#define VSID_BITS_256M          (CONTEXT_BITS + ESID_BITS)
 #define VSID_MODULUS_256M       ((1UL<<VSID_BITS_256M)-1)
 
 #define VSID_MULTIPLIER_1T      ASM_CONST(12538073)     /* 24-bit prime */
-#define VSID_BITS_1T            26
+#define VSID_BITS_1T            (CONTEXT_BITS + ESID_BITS_1T)
 #define VSID_MODULUS_1T         ((1UL<<VSID_BITS_1T)-1)
 
-#define CONTEXT_BITS            19
-#define USER_ESID_BITS          18
-#define USER_ESID_BITS_1T       6
 
-#define USER_VSID_RANGE (1UL << (USER_ESID_BITS + SID_SHIFT))
+#define USER_VSID_RANGE (1UL << (ESID_BITS + SID_SHIFT))
 
 /*
  * This macro generates asm code to compute the VSID scramble
@@ -421,7 +428,8 @@ extern void slb_set_size(u16 size);
         srdi    rx,rt,VSID_BITS_##size;                                 \
         clrldi  rt,rt,(64-VSID_BITS_##size);                            \
         add     rt,rt,rx;               /* add high and low bits */     \
-        /* Now, r3 == VSID (mod 2^36-1), and lies between 0 and         \
+        /* NOTE: explanation based on VSID_BITS_##size = 36             \
+         * Now, r3 == VSID (mod 2^36-1), and lies between 0 and         \
          * 2^36-1+2^28-1.  That in particular means that if r3 >=       \
          * 2^36-1, then r3+1 has the 2^36 bit set.  So, if r3+1 has     \
          * the bit clear, r3 already has the answer we want, if it      \
@@ -513,34 +521,6 @@ typedef struct {
         })
 #endif /* 1 */
 
-/*
- * This is only valid for addresses >= PAGE_OFFSET
- * The proto-VSID space is divided into two class
- * User:   0 to 2^(CONTEXT_BITS + USER_ESID_BITS) -1
- * kernel: 2^(CONTEXT_BITS + USER_ESID_BITS) to 2^(VSID_BITS) - 1
- *
- * With KERNEL_START at 0xc000000000000000, the proto vsid for
- * the kernel ends up with 0xc00000000 (36 bits). With 64TB
- * support we need to have kernel proto-VSID in the
- * [2^37 to 2^38 - 1] range due to the increased USER_ESID_BITS.
- */
-static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
-{
-        unsigned long proto_vsid;
-        /*
-         * We need to make sure proto_vsid for the kernel is
-         * >= 2^(CONTEXT_BITS + USER_ESID_BITS[_1T])
-         */
-        if (ssize == MMU_SEGSIZE_256M) {
-                proto_vsid = ea >> SID_SHIFT;
-                proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS));
-                return vsid_scramble(proto_vsid, 256M);
-        }
-        proto_vsid = ea >> SID_SHIFT_1T;
-        proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS_1T));
-        return vsid_scramble(proto_vsid, 1T);
-}
-
 /* Returns the segment size indicator for a user address */
 static inline int user_segment_size(unsigned long addr)
 {
@@ -550,17 +530,41 @@ static inline int user_segment_size(unsigned long addr)
         return MMU_SEGSIZE_256M;
 }
 
-/* This is only valid for user addresses (which are below 2^44) */
 static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
                                      int ssize)
 {
+        /*
+         * Bad address. We return VSID 0 for that
+         */
+        if ((ea & ~REGION_MASK) >= PGTABLE_RANGE)
+                return 0;
+
         if (ssize == MMU_SEGSIZE_256M)
-                return vsid_scramble((context << USER_ESID_BITS)
+                return vsid_scramble((context << ESID_BITS)
                                      | (ea >> SID_SHIFT), 256M);
-        return vsid_scramble((context << USER_ESID_BITS_1T)
+        return vsid_scramble((context << ESID_BITS_1T)
                              | (ea >> SID_SHIFT_1T), 1T);
 }
 
+/*
+ * This is only valid for addresses >= PAGE_OFFSET
+ *
+ * For kernel space, we use the top 4 context ids to map address as below
+ * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
+ * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
+ * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
+ * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
+ */
+static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
+{
+        unsigned long context;
+
+        /*
+         * kernel take the top 4 context from the available range
+         */
+        context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1;
+        return get_vsid(context, ea, ssize);
+}
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_MMU_HASH64_H_ */
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 406b7b9a1341..8ceea14d6fe4 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -182,8 +182,6 @@ static inline bool test_thread_local_flags(unsigned int flags)
 #define is_32bit_task() (1)
 #endif
 
-#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
-
 #endif  /* !__ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h
index b532060d0916..23016020915e 100644
--- a/arch/powerpc/include/asm/uprobes.h
+++ b/arch/powerpc/include/asm/uprobes.h
@@ -51,4 +51,5 @@ extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
 extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
 extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
 extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
 #endif  /* _ASM_UPROBES_H */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 75a3d71b895d..19599ef352bc 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -275,7 +275,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_PPC970,
                 .cpu_user_features      = COMMON_USER_POWER4 |
                         PPC_FEATURE_HAS_ALTIVEC_COMP,
-                .mmu_features           = MMU_FTR_HPTE_TABLE,
+                .mmu_features           = MMU_FTRS_PPC970,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index b3ba5163eae2..9ec3fe174cba 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -150,10 +150,7 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
                 if (addr <= rtas_end && ((addr + PAGE_SIZE) > rtas_start))
                         continue;
 
-                ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
-                init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
-                free_page((unsigned long)__va(addr));
-                totalram_pages++;
+                free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
         }
 }
 #endif
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 256c5bf0adb7..04d69c4a5ac2 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -304,7 +304,7 @@ syscall_exit_work:
         subi    r12,r12,TI_FLAGS
 
 4:      /* Anything else left to do? */
-        SET_DEFAULT_THREAD_PPR(r3, r9)          /* Set thread.ppr = 3 */
+        SET_DEFAULT_THREAD_PPR(r3, r10)         /* Set thread.ppr = 3 */
         andi.   r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
         beq     .ret_from_except_lite
 
@@ -657,7 +657,7 @@ resume_kernel:
         /* Clear _TIF_EMULATE_STACK_STORE flag */
         lis     r11,_TIF_EMULATE_STACK_STORE@h
         addi    r5,r9,TI_FLAGS
-        ldarx   r4,0,r5
+0:      ldarx   r4,0,r5
         andc    r4,r4,r11
         stdcx.  r4,0,r5
         bne-    0b
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
index f3eab8594d9f..d44a571e45a7 100644
--- a/arch/powerpc/kernel/epapr_paravirt.c
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -23,8 +23,10 @@
 #include <asm/code-patching.h>
 #include <asm/machdep.h>
 
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
 extern void epapr_ev_idle(void);
 extern u32 epapr_ev_idle_start[];
+#endif
 
 bool epapr_paravirt_enabled;
 
@@ -47,11 +49,15 @@ static int __init epapr_paravirt_init(void)
 
         for (i = 0; i < (len / 4); i++) {
                 patch_instruction(epapr_hypercall_start + i, insts[i]);
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
                 patch_instruction(epapr_ev_idle_start + i, insts[i]);
+#endif
         }
 
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
         if (of_get_property(hyper_node, "has-idle", NULL))
                 ppc_md.power_save = epapr_ev_idle;
+#endif
 
         epapr_paravirt_enabled = true;
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 87ef8f5ee5bc..56bd92362ce1 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1066,78 +1066,6 @@ unrecov_user_slb:
 #endif /* __DISABLED__ */
 
 
-/*
- * r13 points to the PACA, r9 contains the saved CR,
- * r12 contain the saved SRR1, SRR0 is still ready for return
- * r3 has the faulting address
- * r9 - r13 are saved in paca->exslb.
- * r3 is saved in paca->slb_r3
- * We assume we aren't going to take any exceptions during this procedure.
- */
-_GLOBAL(slb_miss_realmode)
-        mflr    r10
-#ifdef CONFIG_RELOCATABLE
-        mtctr   r11
-#endif
-
-        stw     r9,PACA_EXSLB+EX_CCR(r13)       /* save CR in exc. frame */
-        std     r10,PACA_EXSLB+EX_LR(r13)       /* save LR */
-
-        bl      .slb_allocate_realmode
-
-        /* All done -- return from exception. */
-
-        ld      r10,PACA_EXSLB+EX_LR(r13)
-        ld      r3,PACA_EXSLB+EX_R3(r13)
-        lwz     r9,PACA_EXSLB+EX_CCR(r13)       /* get saved CR */
-
-        mtlr    r10
-
-        andi.   r10,r12,MSR_RI  /* check for unrecoverable exception */
-        beq-    2f
-
-.machine        push
-.machine        "power4"
-        mtcrf   0x80,r9
-        mtcrf   0x01,r9         /* slb_allocate uses cr0 and cr7 */
-.machine        pop
-
-        RESTORE_PPR_PACA(PACA_EXSLB, r9)
-        ld      r9,PACA_EXSLB+EX_R9(r13)
-        ld      r10,PACA_EXSLB+EX_R10(r13)
-        ld      r11,PACA_EXSLB+EX_R11(r13)
-        ld      r12,PACA_EXSLB+EX_R12(r13)
-        ld      r13,PACA_EXSLB+EX_R13(r13)
-        rfid
-        b       .       /* prevent speculative execution */
-
-2:      mfspr   r11,SPRN_SRR0
-        ld      r10,PACAKBASE(r13)
-        LOAD_HANDLER(r10,unrecov_slb)
-        mtspr   SPRN_SRR0,r10
-        ld      r10,PACAKMSR(r13)
-        mtspr   SPRN_SRR1,r10
-        rfid
-        b       .
-
-unrecov_slb:
-        EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB)
-        DISABLE_INTS
-        bl      .save_nvgprs
-1:      addi    r3,r1,STACK_FRAME_OVERHEAD
-        bl      .unrecoverable_exception
-        b       1b
-
-
-#ifdef CONFIG_PPC_970_NAP
-power4_fixup_nap:
-        andc    r9,r9,r10
-        std     r9,TI_LOCAL_FLAGS(r11)
-        ld      r10,_LINK(r1)           /* make idle task do the */
-        std     r10,_NIP(r1)            /* equivalent of a blr */
-        blr
-#endif
-
         .align  7
         .globl alignment_common
 alignment_common:
@@ -1336,6 +1264,78 @@ _GLOBAL(opal_mc_secondary_handler)
 
 
 /*
+ * r13 points to the PACA, r9 contains the saved CR,
+ * r12 contain the saved SRR1, SRR0 is still ready for return
+ * r3 has the faulting address
+ * r9 - r13 are saved in paca->exslb.
+ * r3 is saved in paca->slb_r3
+ * We assume we aren't going to take any exceptions during this procedure.
+ */
+_GLOBAL(slb_miss_realmode)
+        mflr    r10
+#ifdef CONFIG_RELOCATABLE
+        mtctr   r11
+#endif
+
+        stw     r9,PACA_EXSLB+EX_CCR(r13)       /* save CR in exc. frame */
+        std     r10,PACA_EXSLB+EX_LR(r13)       /* save LR */
+
+        bl      .slb_allocate_realmode
+
+        /* All done -- return from exception. */
+
+        ld      r10,PACA_EXSLB+EX_LR(r13)
+        ld      r3,PACA_EXSLB+EX_R3(r13)
+        lwz     r9,PACA_EXSLB+EX_CCR(r13)       /* get saved CR */
+
+        mtlr    r10
+
+        andi.   r10,r12,MSR_RI  /* check for unrecoverable exception */
+        beq-    2f
+
+.machine        push
+.machine        "power4"
+        mtcrf   0x80,r9
+        mtcrf   0x01,r9         /* slb_allocate uses cr0 and cr7 */
+.machine        pop
+
+        RESTORE_PPR_PACA(PACA_EXSLB, r9)
+        ld      r9,PACA_EXSLB+EX_R9(r13)
+        ld      r10,PACA_EXSLB+EX_R10(r13)
+        ld      r11,PACA_EXSLB+EX_R11(r13)
+        ld      r12,PACA_EXSLB+EX_R12(r13)
+        ld      r13,PACA_EXSLB+EX_R13(r13)
+        rfid
+        b       .       /* prevent speculative execution */
+
+2:      mfspr   r11,SPRN_SRR0
+        ld      r10,PACAKBASE(r13)
+        LOAD_HANDLER(r10,unrecov_slb)
+        mtspr   SPRN_SRR0,r10
+        ld      r10,PACAKMSR(r13)
+        mtspr   SPRN_SRR1,r10
+        rfid
+        b       .
+
+unrecov_slb:
+        EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB)
+        DISABLE_INTS
+        bl      .save_nvgprs
+1:      addi    r3,r1,STACK_FRAME_OVERHEAD
+        bl      .unrecoverable_exception
+        b       1b
+
+
+#ifdef CONFIG_PPC_970_NAP
+power4_fixup_nap:
+        andc    r9,r9,r10
+        std     r9,TI_LOCAL_FLAGS(r11)
+        ld      r10,_LINK(r1)           /* make idle task do the */
+        std     r10,_NIP(r1)            /* equivalent of a blr */
+        blr
+#endif
+
+/*
  * Hash table stuff
  */
         .align  7
@@ -1452,20 +1452,36 @@ do_ste_alloc:
 _GLOBAL(do_stab_bolted)
         stw     r9,PACA_EXSLB+EX_CCR(r13)       /* save CR in exc. frame */
         std     r11,PACA_EXSLB+EX_SRR0(r13)     /* save SRR0 in exc. frame */
+        mfspr   r11,SPRN_DAR                    /* ea */
 
+        /*
+         * check for bad kernel/user address
+         * (ea & ~REGION_MASK) >= PGTABLE_RANGE
+         */
+        rldicr. r9,r11,4,(63 - 46 - 4)
+        li      r9,0    /* VSID = 0 for bad address */
+        bne-    0f
+
+        /*
+         * Calculate VSID:
+         * This is the kernel vsid, we take the top for context from
+         * the range. context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
+         * Here we know that (ea >> 60) == 0xc
+         */
+        lis     r9,(MAX_USER_CONTEXT + 1)@ha
+        addi    r9,r9,(MAX_USER_CONTEXT + 1)@l
+
+        srdi    r10,r11,SID_SHIFT
+        rldimi  r10,r9,ESID_BITS,0 /* proto vsid */
+        ASM_VSID_SCRAMBLE(r10, r9, 256M)
+        rldic   r9,r10,12,16    /* r9 = vsid << 12 */
+
+0:
         /* Hash to the primary group */
         ld      r10,PACASTABVIRT(r13)
-        mfspr   r11,SPRN_DAR
-        srdi    r11,r11,28
+        srdi    r11,r11,SID_SHIFT
         rldimi  r10,r11,7,52    /* r10 = first ste of the group */
 
-        /* Calculate VSID */
-        /* This is a kernel address, so protovsid = ESID | 1 << 37 */
-        li      r9,0x1
-        rldimi  r11,r9,(CONTEXT_BITS + USER_ESID_BITS),0
-        ASM_VSID_SCRAMBLE(r11, r9, 256M)
-        rldic   r9,r11,12,16    /* r9 = vsid << 12 */
-
         /* Search the primary group for a free entry */
 1:      ld      r11,0(r10)      /* Test valid bit of the current ste    */
         andi.   r11,r11,0x80
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 06c8202a69cf..2230fd0ca3e4 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -1045,10 +1045,7 @@ static void fadump_release_memory(unsigned long begin, unsigned long end)
                 if (addr <= ra_end && ((addr + PAGE_SIZE) > ra_start))
                         continue;
 
-                ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
-                init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
-                free_page((unsigned long)__va(addr));
-                totalram_pages++;
+                free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
         }
 }
 
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index ea78761aa169..939ea7ef0dc8 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -33,11 +33,6 @@
 #include <asm/runlatch.h>
 #include <asm/smp.h>
 
-#ifdef CONFIG_HOTPLUG_CPU
-#define cpu_should_die()        cpu_is_offline(smp_processor_id())
-#else
-#define cpu_should_die()        0
-#endif
 
 unsigned long cpuidle_disable = IDLE_NO_OVERRIDE;
 EXPORT_SYMBOL(cpuidle_disable);
@@ -50,64 +45,38 @@ static int __init powersave_off(char *arg)
 }
 __setup("powersave=off", powersave_off);
 
-/*
- * The body of the idle task.
- */
-void cpu_idle(void)
+#ifdef CONFIG_HOTPLUG_CPU
+void arch_cpu_idle_dead(void)
 {
-        set_thread_flag(TIF_POLLING_NRFLAG);
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-
-                while (!need_resched() && !cpu_should_die()) {
-                        ppc64_runlatch_off();
-
-                        if (ppc_md.power_save) {
-                                clear_thread_flag(TIF_POLLING_NRFLAG);
-                                /*
-                                 * smp_mb is so clearing of TIF_POLLING_NRFLAG
-                                 * is ordered w.r.t. need_resched() test.
-                                 */
-                                smp_mb();
-                                local_irq_disable();
-
-                                /* Don't trace irqs off for idle */
-                                stop_critical_timings();
-
-                                /* check again after disabling irqs */
-                                if (!need_resched() && !cpu_should_die())
-                                        ppc_md.power_save();
-
-                                start_critical_timings();
-
-                                /* Some power_save functions return with
-                                 * interrupts enabled, some don't.
-                                 */
-                                if (irqs_disabled())
-                                        local_irq_enable();
-                                set_thread_flag(TIF_POLLING_NRFLAG);
-
-                        } else {
-                                /*
-                                 * Go into low thread priority and possibly
-                                 * low power mode.
-                                 */
-                                HMT_low();
-                                HMT_very_low();
-                        }
-                }
+        sched_preempt_enable_no_resched();
+        cpu_die();
+}
+#endif
 
-                HMT_medium();
-                ppc64_runlatch_on();
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                if (cpu_should_die()) {
-                        sched_preempt_enable_no_resched();
-                        cpu_die();
-                }
-                schedule_preempt_disabled();
+void arch_cpu_idle(void)
+{
+        ppc64_runlatch_off();
+
+        if (ppc_md.power_save) {
+                ppc_md.power_save();
+                /*
+                 * Some power_save functions return with
+                 * interrupts enabled, some don't.
+                 */
+                if (irqs_disabled())
+                        local_irq_enable();
+        } else {
+                local_irq_enable();
+                /*
+                 * Go into low thread priority and possibly
+                 * low power mode.
+                 */
+                HMT_low();
+                HMT_very_low();
         }
+
+        HMT_medium();
+        ppc64_runlatch_on();
 }
 
 int powersave_nap;
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index a61b133c4f99..6782221d49bd 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -756,12 +756,7 @@ static __init void kvm_free_tmp(void)
         end = (ulong)&kvm_tmp[ARRAY_SIZE(kvm_tmp)] & PAGE_MASK;
 
         /* Free the tmp space we don't need */
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page(start);
-                totalram_pages++;
-        }
+        free_reserved_area(start, end, 0, NULL);
 }
 
 static int __init kvm_guest_init(void)
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index bec1e930ed73..48fbc2b97e95 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -511,8 +511,7 @@ int __init nvram_scan_partitions(void)
                                "detected: 0-length partition\n");
                         goto out;
                 }
-                tmp_part = (struct nvram_partition *)
-                        kmalloc(sizeof(struct nvram_partition), GFP_KERNEL);
+                tmp_part = kmalloc(sizeof(struct nvram_partition), GFP_KERNEL);
                 err = -ENOMEM;
                 if (!tmp_part) {
                         printk(KERN_ERR "nvram_scan_partitions: kmalloc failed\n");
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 59dd545fdde1..16e77a81ab4f 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -555,10 +555,12 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new)
                 new->thread.regs->msr |=
                         (MSR_FP | new->thread.fpexc_mode);
         }
+#ifdef CONFIG_ALTIVEC
         if (msr & MSR_VEC) {
                 do_load_up_transact_altivec(&new->thread);
                 new->thread.regs->msr |= MSR_VEC;
         }
+#endif
         /* We may as well turn on VSX too since all the state is restored now */
         if (msr & MSR_VSX)
                 new->thread.regs->msr |= MSR_VSX;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 7f7fb7fd991b..13f8d168b3f1 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2832,11 +2832,13 @@ static void unreloc_toc(void)
 {
 }
 #else
-static void __reloc_toc(void *tocstart, unsigned long offset,
-                        unsigned long nr_entries)
+static void __reloc_toc(unsigned long offset, unsigned long nr_entries)
 {
         unsigned long i;
-        unsigned long *toc_entry = (unsigned long *)tocstart;
+        unsigned long *toc_entry;
+
+        /* Get the start of the TOC by using r2 directly. */
+        asm volatile("addi %0,2,-0x8000" : "=b" (toc_entry));
 
         for (i = 0; i < nr_entries; i++) {
                 *toc_entry = *toc_entry + offset;
@@ -2850,8 +2852,7 @@ static void reloc_toc(void)
         unsigned long nr_entries =
                 (__prom_init_toc_end - __prom_init_toc_start) / sizeof(long);
 
-        /* Need to add offset to get at __prom_init_toc_start */
-        __reloc_toc(__prom_init_toc_start + offset, offset, nr_entries);
+        __reloc_toc(offset, nr_entries);
 
         mb();
 }
@@ -2864,8 +2865,7 @@ static void unreloc_toc(void)
 
         mb();
 
-        /* __prom_init_toc_start has been relocated, no need to add offset */
-        __reloc_toc(__prom_init_toc_start, -offset, nr_entries);
+        __reloc_toc(-offset, nr_entries);
 }
 #endif
 #endif
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 245c1b6a0858..f9b30c68ba47 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1428,6 +1428,7 @@ static long ppc_set_hwdebug(struct task_struct *child,
 
         brk.address = bp_info->addr & ~7UL;
         brk.type = HW_BRK_TYPE_TRANSLATE;
+        brk.len = 8;
         if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
                 brk.type |= HW_BRK_TYPE_READ;
         if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 3acb28e245b4..95068bf569ad 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -866,10 +866,12 @@ static long restore_tm_user_regs(struct pt_regs *regs,
                 do_load_up_transact_fpu(&current->thread);
                 regs->msr |= (MSR_FP | current->thread.fpexc_mode);
         }
+#ifdef CONFIG_ALTIVEC
         if (msr & MSR_VEC) {
                 do_load_up_transact_altivec(&current->thread);
                 regs->msr |= MSR_VEC;
         }
+#endif
 
         return 0;
 }
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 995f8543cb57..c1794286098c 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -522,10 +522,12 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
                 do_load_up_transact_fpu(&current->thread);
                 regs->msr |= (MSR_FP | current->thread.fpexc_mode);
         }
+#ifdef CONFIG_ALTIVEC
         if (msr & MSR_VEC) {
                 do_load_up_transact_altivec(&current->thread);
                 regs->msr |= MSR_VEC;
         }
+#endif
 
         return err;
 }
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 76bd9da8cb71..ee7ac5e6e28a 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -669,7 +669,7 @@ __cpuinit void start_secondary(void *unused)
 
         local_irq_enable();
 
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 
         BUG();
 }
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 84dbace657ce..2da67e7a16d5 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -309,6 +309,7 @@ _GLOBAL(tm_recheckpoint)
         or      r5, r6, r5                      /* Set MSR.FP+.VSX/.VEC */
         mtmsr   r5
 
+#ifdef CONFIG_ALTIVEC
         /* FP and VEC registers:  These are recheckpointed from thread.fpr[]
          * and thread.vr[] respectively.  The thread.transact_fpr[] version
          * is more modern, and will be loaded subsequently by any FPUnavailable
@@ -323,6 +324,7 @@ _GLOBAL(tm_recheckpoint)
         REST_32VRS(0, r5, r3)                   /* r5 scratch, r3 THREAD ptr */
         ld      r5, THREAD_VRSAVE(r3)
         mtspr   SPRN_VRSAVE, r5
+#endif
 
 dont_restore_vec:
         andi.   r0, r4, MSR_FP
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index f9748498fe58..13b867093499 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -156,15 +156,13 @@ static struct console udbg_console = {
         .index  = 0,
 };
 
-static int early_console_initialized;
-
 /*
  * Called by setup_system after ppc_md->probe and ppc_md->early_init.
  * Call it again after setting udbg_putc in ppc_md->setup_arch.
  */
 void __init register_early_udbg_console(void)
 {
-        if (early_console_initialized)
+        if (early_console)
                 return;
 
         if (!udbg_putc)
@@ -174,7 +172,7 @@ void __init register_early_udbg_console(void)
                 printk(KERN_INFO "early console immortal !\n");
                 udbg_console.flags &= ~CON_BOOT;
         }
-        early_console_initialized = 1;
+        early_console = &udbg_console;
         register_console(&udbg_console);
 }
 
diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c
index bc77834dbf43..59f419b935f2 100644
--- a/arch/powerpc/kernel/uprobes.c
+++ b/arch/powerpc/kernel/uprobes.c
@@ -31,6 +31,16 @@
 #define UPROBE_TRAP_NR  UINT_MAX
 
 /**
+ * is_trap_insn - check if the instruction is a trap variant
+ * @insn: instruction to be checked.
+ * Returns true if @insn is a trap variant.
+ */
+bool is_trap_insn(uprobe_opcode_t *insn)
+{
+        return (is_trap(*insn));
+}
+
+/**
  * arch_uprobe_analyze_insn
  * @mm: the probed address space.
  * @arch_uprobe: the probepoint information.
@@ -43,12 +53,6 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe,
         if (addr & 0x03)
                 return -EINVAL;
 
-        /*
-         * We currently don't support a uprobe on an already
-         * existing breakpoint instruction underneath
-         */
-        if (is_trap(auprobe->ainsn))
-                return -ENOTSUPP;
         return 0;
 }
 
@@ -188,3 +192,16 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
         return false;
 }
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
+{
+        unsigned long orig_ret_vaddr;
+
+        orig_ret_vaddr = regs->link;
+
+        /* Replace the return addr with trampoline addr */
+        regs->link = trampoline_vaddr;
+
+        return orig_ret_vaddr;
+}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index ead58e317294..5d7d29a313eb 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -326,8 +326,8 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
         vcpu3s->context_id[0] = err;
 
         vcpu3s->proto_vsid_max = ((vcpu3s->context_id[0] + 1)
-                                  << USER_ESID_BITS) - 1;
-        vcpu3s->proto_vsid_first = vcpu3s->context_id[0] << USER_ESID_BITS;
+                                  << ESID_BITS) - 1;
+        vcpu3s->proto_vsid_first = vcpu3s->context_id[0] << ESID_BITS;
         vcpu3s->proto_vsid_next = vcpu3s->proto_vsid_first;
 
         kvmppc_mmu_hpte_init(vcpu);
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 5e93438afb06..dbdc15aa8127 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1039,7 +1039,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
         if (!vcpu_book3s)
                 goto out;
 
-        vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *)
+        vcpu_book3s->shadow_vcpu =
                 kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL);
         if (!vcpu_book3s->shadow_vcpu)
                 goto free_vcpu;
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index 41cefd43655f..33db48a8ce24 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -26,17 +26,20 @@
 #define E500_PID_NUM   3
 #define E500_TLB_NUM   2
 
-#define E500_TLB_VALID 1
-#define E500_TLB_BITMAP 2
+/* entry is mapped somewhere in host TLB */
+#define E500_TLB_VALID          (1 << 0)
+/* TLB1 entry is mapped by host TLB1, tracked by bitmaps */
+#define E500_TLB_BITMAP         (1 << 1)
+/* TLB1 entry is mapped by host TLB0 */
 #define E500_TLB_TLB0           (1 << 2)
 
 struct tlbe_ref {
-        pfn_t pfn;
-        unsigned int flags; /* E500_TLB_* */
+        pfn_t pfn;              /* valid only for TLB0, except briefly */
+        unsigned int flags;     /* E500_TLB_* */
 };
 
 struct tlbe_priv {
-        struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */
+        struct tlbe_ref ref;
 };
 
 #ifdef CONFIG_KVM_E500V2
@@ -63,17 +66,6 @@ struct kvmppc_vcpu_e500 {
 
         unsigned int gtlb_nv[E500_TLB_NUM];
 
-        /*
-         * information associated with each host TLB entry --
-         * TLB1 only for now.  If/when guest TLB1 entries can be
-         * mapped with host TLB0, this will be used for that too.
-         *
-         * We don't want to use this for guest TLB0 because then we'd
-         * have the overhead of doing the translation again even if
-         * the entry is still in the guest TLB (e.g. we swapped out
-         * and back, and our host TLB entries got evicted).
-         */
-        struct tlbe_ref *tlb_refs[E500_TLB_NUM];
         unsigned int host_tlb1_nv;
 
         u32 svr;
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index a222edfb9a9b..1c6a9d729df4 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -193,8 +193,11 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
         struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref;
 
         /* Don't bother with unmapped entries */
-        if (!(ref->flags & E500_TLB_VALID))
-                return;
+        if (!(ref->flags & E500_TLB_VALID)) {
+                WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0),
+                     "%s: flags %x\n", __func__, ref->flags);
+                WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]);
+        }
 
         if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) {
                 u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
@@ -248,7 +251,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
                                          pfn_t pfn)
 {
         ref->pfn = pfn;
-        ref->flags = E500_TLB_VALID;
+        ref->flags |= E500_TLB_VALID;
 
         if (tlbe_is_writable(gtlbe))
                 kvm_set_pfn_dirty(pfn);
@@ -257,6 +260,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
 static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
 {
         if (ref->flags & E500_TLB_VALID) {
+                /* FIXME: don't log bogus pfn for TLB1 */
                 trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
                 ref->flags = 0;
         }
@@ -274,36 +278,23 @@ static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500)
 
 static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
-        int tlbsel = 0;
-        int i;
-
-        for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
-                struct tlbe_ref *ref =
-                        &vcpu_e500->gtlb_priv[tlbsel][i].ref;
-                kvmppc_e500_ref_release(ref);
-        }
-}
-
-static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-        int stlbsel = 1;
+        int tlbsel;
         int i;
 
-        kvmppc_e500_tlbil_all(vcpu_e500);
-
-        for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
-                struct tlbe_ref *ref =
-                        &vcpu_e500->tlb_refs[stlbsel][i];
-                kvmppc_e500_ref_release(ref);
+        for (tlbsel = 0; tlbsel <= 1; tlbsel++) {
+                for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
+                        struct tlbe_ref *ref =
+                                &vcpu_e500->gtlb_priv[tlbsel][i].ref;
+                        kvmppc_e500_ref_release(ref);
+                }
         }
-
-        clear_tlb_privs(vcpu_e500);
 }
 
 void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
 {
         struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-        clear_tlb_refs(vcpu_e500);
+        kvmppc_e500_tlbil_all(vcpu_e500);
+        clear_tlb_privs(vcpu_e500);
         clear_tlb1_bitmap(vcpu_e500);
 }
 
@@ -458,8 +449,6 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
                 gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
         }
 
-        /* Drop old ref and setup new one. */
-        kvmppc_e500_ref_release(ref);
         kvmppc_e500_ref_setup(ref, gtlbe, pfn);
 
         kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
@@ -507,14 +496,15 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500,
         if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
                 vcpu_e500->host_tlb1_nv = 0;
 
-        vcpu_e500->tlb_refs[1][sesel] = *ref;
-        vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
-        vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
         if (vcpu_e500->h2g_tlb1_rmap[sesel]) {
-                unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel];
+                unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel] - 1;
                 vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel);
         }
-        vcpu_e500->h2g_tlb1_rmap[sesel] = esel;
+
+        vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
+        vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
+        vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1;
+        WARN_ON(!(ref->flags & E500_TLB_VALID));
 
         return sesel;
 }
@@ -526,13 +516,12 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
                 u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
                 struct kvm_book3e_206_tlb_entry *stlbe, int esel)
 {
-        struct tlbe_ref ref;
+        struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref;
         int sesel;
         int r;
 
-        ref.flags = 0;
         r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe,
-                                   &ref);
+                                   ref);
         if (r)
                 return r;
 
@@ -544,7 +533,7 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
         }
 
         /* Otherwise map into TLB1 */
-        sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel);
+        sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel);
         write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel);
 
         return 0;
@@ -565,7 +554,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
         case 0:
                 priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
-                /* Triggers after clear_tlb_refs or on initial mapping */
+                /* Triggers after clear_tlb_privs or on initial mapping */
                 if (!(priv->ref.flags & E500_TLB_VALID)) {
                         kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
                 } else {
@@ -665,35 +654,16 @@ int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500)
                 host_tlb_params[0].entries / host_tlb_params[0].ways;
         host_tlb_params[1].sets = 1;
 
-        vcpu_e500->tlb_refs[0] =
-                kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries,
-                        GFP_KERNEL);
-        if (!vcpu_e500->tlb_refs[0])
-                goto err;
-
-        vcpu_e500->tlb_refs[1] =
-                kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries,
-                        GFP_KERNEL);
-        if (!vcpu_e500->tlb_refs[1])
-                goto err;
-
         vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) *
                                            host_tlb_params[1].entries,
                                            GFP_KERNEL);
         if (!vcpu_e500->h2g_tlb1_rmap)
-                goto err;
+                return -EINVAL;
 
         return 0;
-
-err:
-        kfree(vcpu_e500->tlb_refs[0]);
-        kfree(vcpu_e500->tlb_refs[1]);
-        return -EINVAL;
 }
 
 void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
         kfree(vcpu_e500->h2g_tlb1_rmap);
-        kfree(vcpu_e500->tlb_refs[0]);
-        kfree(vcpu_e500->tlb_refs[1]);
 }
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index 1f89d26e65fb..2f4baa074b2e 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -108,6 +108,8 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
 {
 }
 
+static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu);
+
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
         struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -136,8 +138,11 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
         mtspr(SPRN_GDEAR, vcpu->arch.shared->dar);
         mtspr(SPRN_GESR, vcpu->arch.shared->esr);
 
-        if (vcpu->arch.oldpir != mfspr(SPRN_PIR))
+        if (vcpu->arch.oldpir != mfspr(SPRN_PIR) ||
+            __get_cpu_var(last_vcpu_on_cpu) != vcpu) {
                 kvmppc_e500_tlbil_all(vcpu_e500);
+                __get_cpu_var(last_vcpu_on_cpu) = vcpu;
+        }
 
         kvmppc_load_guest_fp(vcpu);
 }
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 1b6e1271719f..f410c3e12c1e 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -195,6 +195,11 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
                 unsigned long vpn  = hpt_vpn(vaddr, vsid, ssize);
                 unsigned long tprot = prot;
 
+                /*
+                 * If we hit a bad address return error.
+                 */
+                if (!vsid)
+                        return -1;
                 /* Make kernel text executable */
                 if (overlaps_kernel_text(vaddr, vaddr + step))
                         tprot &= ~HPTE_R_N;
@@ -759,6 +764,8 @@ void __init early_init_mmu(void)
         /* Initialize stab / SLB management */
         if (mmu_has_feature(MMU_FTR_SLB))
                 slb_initialize();
+        else
+                stab_initialize(get_paca()->stab_real);
 }
 
 #ifdef CONFIG_SMP
@@ -922,11 +929,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
         DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n",
                 ea, access, trap);
 
-        if ((ea & ~REGION_MASK) >= PGTABLE_RANGE) {
-                DBG_LOW(" out of pgtable range !\n");
-                return 1;
-        }
-
         /* Get region & vsid */
         switch (REGION_ID(ea)) {
         case USER_REGION_ID:
@@ -957,6 +959,11 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
         }
         DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid);
 
+        /* Bad address. */
+        if (!vsid) {
+                DBG_LOW("Bad address!\n");
+                return 1;
+        }
         /* Get pgdir */
         pgdir = mm->pgd;
         if (pgdir == NULL)
@@ -1126,6 +1133,8 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
         /* Get VSID */
         ssize = user_segment_size(ea);
         vsid = get_vsid(mm->context.id, ea, ssize);
+        if (!vsid)
+                return;
 
         /* Hash doesn't like irqs */
         local_irq_save(flags);
@@ -1233,6 +1242,9 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
         hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
         hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 
+        /* Don't create HPTE entries for bad address */
+        if (!vsid)
+                return;
         ret = ppc_md.hpte_insert(hpteg, vpn, __pa(vaddr),
                                  mode, HPTE_V_BOLTED,
                                  mmu_linear_psize, mmu_kernel_ssize);
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 7e2246fb2f31..5a535b73ea18 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -263,19 +263,14 @@ static __meminit void vmemmap_list_populate(unsigned long phys,
         vmemmap_list = vmem_back;
 }
 
-int __meminit vmemmap_populate(struct page *start_page,
-                               unsigned long nr_pages, int node)
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 {
-        unsigned long start = (unsigned long)start_page;
-        unsigned long end = (unsigned long)(start_page + nr_pages);
         unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
 
         /* Align to the page size of the linear mapping. */
         start = _ALIGN_DOWN(start, page_size);
 
-        pr_debug("vmemmap_populate page %p, %ld pages, node %d\n",
-                 start_page, nr_pages, node);
-        pr_debug(" -> map %lx..%lx\n", start, end);
+        pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node);
 
         for (; start < end; start += page_size) {
                 void *p;
@@ -298,7 +293,7 @@ int __meminit vmemmap_populate(struct page *start_page,
         return 0;
 }
 
-void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+void vmemmap_free(unsigned long start, unsigned long end)
 {
 }
 
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index f1f7409a4183..cd76c454942f 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -352,13 +352,9 @@ void __init mem_init(void)
                         struct page *page = pfn_to_page(pfn);
                         if (memblock_is_reserved(paddr))
                                 continue;
-                        ClearPageReserved(page);
-                        init_page_count(page);
-                        __free_page(page);
-                        totalhigh_pages++;
+                        free_highmem_page(page);
                         reservedpages--;
                 }
-                totalram_pages += totalhigh_pages;
                 printk(KERN_DEBUG "High memory: %luk\n",
                        totalhigh_pages << (PAGE_SHIFT-10));
         }
@@ -405,39 +401,14 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
-        unsigned long addr;
-
         ppc_md.progress = ppc_printk_progress;
-
-        addr = (unsigned long)__init_begin;
-        for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) {
-                memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-        pr_info("Freeing unused kernel memory: %luk freed\n",
-                ((unsigned long)__init_end -
-                (unsigned long)__init_begin) >> 10);
+        free_initmem_default(POISON_FREE_INITMEM);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-        if (start >= end)
-                return;
-
-        start = _ALIGN_DOWN(start, PAGE_SIZE);
-        end = _ALIGN_UP(end, PAGE_SIZE);
-        pr_info("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page(start);
-                totalram_pages++;
-        }
+        free_reserved_area(start, end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 40bc5b0ace54..d1d1b92c5b99 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -29,15 +29,6 @@
 static DEFINE_SPINLOCK(mmu_context_lock);
 static DEFINE_IDA(mmu_context_ida);
 
-/*
- * 256MB segment
- * The proto-VSID space has 2^(CONTEX_BITS + USER_ESID_BITS) - 1 segments
- * available for user mappings. Each segment contains 2^28 bytes. Each
- * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts
- * (19 == 37 + 28 - 46).
- */
-#define MAX_CONTEXT     ((1UL << CONTEXT_BITS) - 1)
-
 int __init_new_context(void)
 {
         int index;
@@ -56,7 +47,7 @@ again:
         else if (err)
                 return err;
 
-        if (index > MAX_CONTEXT) {
+        if (index > MAX_USER_CONTEXT) {
                 spin_lock(&mmu_context_lock);
                 ida_remove(&mmu_context_ida, index);
                 spin_unlock(&mmu_context_lock);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index bba87ca2b4d7..fa33c546e778 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -22,6 +22,7 @@
 #include <linux/pfn.h>
 #include <linux/cpuset.h>
 #include <linux/node.h>
+#include <linux/slab.h>
 #include <asm/sparsemem.h>
 #include <asm/prom.h>
 #include <asm/smp.h>
@@ -62,14 +63,11 @@ static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS];
  */
 static void __init setup_node_to_cpumask_map(void)
 {
-        unsigned int node, num = 0;
+        unsigned int node;
 
         /* setup nr_node_ids if not done yet */
-        if (nr_node_ids == MAX_NUMNODES) {
-                for_each_node_mask(node, node_possible_map)
-                        num = node;
-                nr_node_ids = num + 1;
-        }
+        if (nr_node_ids == MAX_NUMNODES)
+                setup_nr_node_ids();
 
         /* allocate the map */
         for (node = 0; node < nr_node_ids; node++)
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index e212a271c7a4..654258f165ae 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -61,7 +61,7 @@
 #endif
 
 #ifdef CONFIG_PPC_STD_MMU_64
-#if TASK_SIZE_USER64 > (1UL << (USER_ESID_BITS + SID_SHIFT))
+#if TASK_SIZE_USER64 > (1UL << (ESID_BITS + SID_SHIFT))
 #error TASK_SIZE_USER64 exceeds user VSID range
 #endif
 #endif
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 1a16ca227757..17aa6dfceb34 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -31,10 +31,15 @@
  * No other registers are examined or changed.
  */
 _GLOBAL(slb_allocate_realmode)
-        /* r3 = faulting address */
+        /*
+         * check for bad kernel/user address
+         * (ea & ~REGION_MASK) >= PGTABLE_RANGE
+         */
+        rldicr. r9,r3,4,(63 - 46 - 4)
+        bne-    8f
 
         srdi    r9,r3,60                /* get region */
-        srdi    r10,r3,28               /* get esid */
+        srdi    r10,r3,SID_SHIFT        /* get esid */
         cmpldi  cr7,r9,0xc              /* cmp PAGE_OFFSET for later use */
 
         /* r3 = address, r10 = esid, cr7 = <> PAGE_OFFSET */
@@ -56,12 +61,14 @@ _GLOBAL(slb_allocate_realmode)
          */
 _GLOBAL(slb_miss_kernel_load_linear)
         li      r11,0
-        li      r9,0x1
         /*
-         * for 1T we shift 12 bits more.  slb_finish_load_1T will do
-         * the necessary adjustment
+         * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
+         * r9 = region id.
          */
-        rldimi  r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0
+        addis   r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha
+        addi    r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l
+
+
 BEGIN_FTR_SECTION
         b       slb_finish_load
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
@@ -91,24 +98,19 @@ _GLOBAL(slb_miss_kernel_load_vmemmap)
         _GLOBAL(slb_miss_kernel_load_io)
         li      r11,0
 6:
-        li      r9,0x1
         /*
-         * for 1T we shift 12 bits more.  slb_finish_load_1T will do
-         * the necessary adjustment
+         * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
+         * r9 = region id.
          */
-        rldimi  r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0
+        addis   r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha
+        addi    r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l
+
 BEGIN_FTR_SECTION
         b       slb_finish_load
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
         b       slb_finish_load_1T
 
-0:      /* user address: proto-VSID = context << 15 | ESID. First check
-         * if the address is within the boundaries of the user region
-         */
-        srdi.   r9,r10,USER_ESID_BITS
-        bne-    8f                      /* invalid ea bits set */
-
-
+0:
         /* when using slices, we extract the psize off the slice bitmaps
          * and then we need to get the sllp encoding off the mmu_psize_defs
          * array.
@@ -164,15 +166,13 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
         ld      r9,PACACONTEXTID(r13)
 BEGIN_FTR_SECTION
         cmpldi  r10,0x1000
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
-        rldimi  r10,r9,USER_ESID_BITS,0
-BEGIN_FTR_SECTION
         bge     slb_finish_load_1T
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
         b       slb_finish_load
 
 8:      /* invalid EA */
         li      r10,0                   /* BAD_VSID */
+        li      r9,0                    /* BAD_VSID */
         li      r11,SLB_VSID_USER       /* flags don't much matter */
         b       slb_finish_load
 
@@ -221,8 +221,6 @@ _GLOBAL(slb_allocate_user)
 
         /* get context to calculate proto-VSID */
         ld      r9,PACACONTEXTID(r13)
-        rldimi  r10,r9,USER_ESID_BITS,0
-
         /* fall through slb_finish_load */
 
 #endif /* __DISABLED__ */
@@ -231,9 +229,10 @@ _GLOBAL(slb_allocate_user)
 /*
  * Finish loading of an SLB entry and return
  *
- * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET
+ * r3 = EA, r9 = context, r10 = ESID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET
  */
 slb_finish_load:
+        rldimi  r10,r9,ESID_BITS,0
         ASM_VSID_SCRAMBLE(r10,r9,256M)
         /*
          * bits above VSID_BITS_256M need to be ignored from r10
@@ -298,10 +297,11 @@ _GLOBAL(slb_compare_rr_to_size)
 /*
  * Finish loading of a 1T SLB entry (for the kernel linear mapping) and return.
  *
- * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9
+ * r3 = EA, r9 = context, r10 = ESID(256MB), r11 = flags, clobbers r9
  */
 slb_finish_load_1T:
-        srdi    r10,r10,40-28           /* get 1T ESID */
+        srdi    r10,r10,(SID_SHIFT_1T - SID_SHIFT)      /* get 1T ESID */
+        rldimi  r10,r9,ESID_BITS_1T,0
         ASM_VSID_SCRAMBLE(r10,r9,1T)
         /*
          * bits above VSID_BITS_1T need to be ignored from r10
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 0d82ef50dc3f..023ec8a13f38 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -82,11 +82,11 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
         if (!is_kernel_addr(addr)) {
                 ssize = user_segment_size(addr);
                 vsid = get_vsid(mm->context.id, addr, ssize);
-                WARN_ON(vsid == 0);
         } else {
                 vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
                 ssize = mmu_kernel_ssize;
         }
+        WARN_ON(vsid == 0);
         vpn = hpt_vpn(addr, vsid, ssize);
         rpte = __real_pte(__pte(pte), ptep);
 
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index b554879bd31e..3c475d6267c7 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -420,7 +420,20 @@ static struct attribute_group power7_pmu_events_group = {
         .attrs = power7_events_attr,
 };
 
+PMU_FORMAT_ATTR(event, "config:0-19");
+
+static struct attribute *power7_pmu_format_attr[] = {
+        &format_attr_event.attr,
+        NULL,
+};
+
+struct attribute_group power7_pmu_format_group = {
+        .name = "format",
+        .attrs = power7_pmu_format_attr,
+};
+
 static const struct attribute_group *power7_pmu_attr_groups[] = {
+        &power7_pmu_format_group,
         &power7_pmu_events_group,
         NULL,
 };
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index 0effe9f5a1ea..7be93367d92f 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -274,6 +274,8 @@ config 440EPX
         select IBM_EMAC_EMAC4
         select IBM_EMAC_RGMII
         select IBM_EMAC_ZMII
+        select USB_EHCI_BIG_ENDIAN_MMIO
+        select USB_EHCI_BIG_ENDIAN_DESC
 
 config 440GRX
         bool
diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig
index c16999802ecf..381a592826a2 100644
--- a/arch/powerpc/platforms/512x/Kconfig
+++ b/arch/powerpc/platforms/512x/Kconfig
@@ -7,6 +7,8 @@ config PPC_MPC512x
         select PPC_PCI_CHOICE
         select FSL_PCI if PCI
         select ARCH_WANT_OPTIONAL_GPIOLIB
+        select USB_EHCI_BIG_ENDIAN_MMIO
+        select USB_EHCI_BIG_ENDIAN_DESC
 
 config MPC5121_ADS
         bool "Freescale MPC5121E ADS"
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index d30235b7e3f7..db6ac389ef8c 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -172,12 +172,9 @@ static struct fsl_diu_shared_fb __attribute__ ((__aligned__(8))) diu_shared_fb;
 
 static inline void mpc512x_free_bootmem(struct page *page)
 {
-        __ClearPageReserved(page);
         BUG_ON(PageTail(page));
         BUG_ON(atomic_read(&page->_count) > 1);
-        atomic_set(&page->_count, 1);
-        __free_page(page);
-        totalram_pages++;
+        free_reserved_page(page);
 }
 
 void mpc512x_release_bootmem(void)
diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c
index 611e92f291c4..7179726ba5c5 100644
--- a/arch/powerpc/platforms/85xx/sgy_cts1000.c
+++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c
@@ -69,7 +69,7 @@ static irqreturn_t gpio_halt_irq(int irq, void *__data)
         return IRQ_HANDLED;
 };
 
-static int __devinit gpio_halt_probe(struct platform_device *pdev)
+static int gpio_halt_probe(struct platform_device *pdev)
 {
         enum of_gpio_flags flags;
         struct device_node *node = pdev->dev.of_node;
@@ -128,7 +128,7 @@ static int __devinit gpio_halt_probe(struct platform_device *pdev)
         return 0;
 }
 
-static int __devexit gpio_halt_remove(struct platform_device *pdev)
+static int gpio_halt_remove(struct platform_device *pdev)
 {
         if (halt_node) {
                 int gpio = of_get_gpio(halt_node, 0);
@@ -165,7 +165,7 @@ static struct platform_driver gpio_halt_driver = {
                 .of_match_table = gpio_halt_match,
         },
         .probe          = gpio_halt_probe,
-        .remove         = __devexit_p(gpio_halt_remove),
+        .remove         = gpio_halt_remove,
 };
 
 module_platform_driver(gpio_halt_driver);
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index cea2f09c4241..18e3b76c78d7 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -124,9 +124,8 @@ config 6xx
         select PPC_HAVE_PMU_SUPPORT
 
 config POWER3
-        bool
         depends on PPC64 && PPC_BOOK3S
-        default y if !POWER4_ONLY
+        def_bool y
 
 config POWER4
         depends on PPC64 && PPC_BOOK3S
@@ -145,8 +144,7 @@ config TUNE_CELL
           but somewhat slower on other machines. This option only changes
           the scheduling of instructions, not the selection of instructions
           itself, so the resulting kernel will keep running on all other
-          machines. When building a kernel that is supposed to run only
-          on Cell, you should also select the POWER4_ONLY option.
+          machines.
 
 # this is temp to handle compat with arch=ppc
 config 8xx
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 2372c609fa2b..9a432de363b8 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -72,6 +72,7 @@ unsigned long memory_block_size_bytes(void)
         return get_memblock_size();
 }
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
 static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size)
 {
         unsigned long start, start_pfn;
@@ -153,6 +154,17 @@ static int pseries_remove_memory(struct device_node *np)
         ret = pseries_remove_memblock(base, lmb_size);
         return ret;
 }
+#else
+static inline int pseries_remove_memblock(unsigned long base,
+                                          unsigned int memblock_size)
+{
+        return -EOPNOTSUPP;
+}
+static inline int pseries_remove_memory(struct device_node *np)
+{
+        return -EOPNOTSUPP;
+}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
 
 static int pseries_add_memory(struct device_node *np)
 {
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 0da39fed355a..299731e9036b 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -186,7 +186,13 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group)
                                            (0x1UL << 4), &dummy1, &dummy2);
                 if (lpar_rc == H_SUCCESS)
                         return i;
-                BUG_ON(lpar_rc != H_NOT_FOUND);
+
+                /*
+                 * The test for adjunct partition is performed before the
+                 * ANDCOND test.  H_RESOURCE may be returned, so we need to
+                 * check for that as well.
+                 */
+                BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE);
 
                 slot_offset++;
                 slot_offset &= 0x7;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 4b505370a1d5..bda6ba6f3cf5 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -134,7 +134,7 @@ config S390
         select HAVE_SYSCALL_WRAPPERS
         select HAVE_UID16 if 32BIT
         select HAVE_VIRT_CPU_ACCOUNTING
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select INIT_ALL_POSSIBLE
         select KTIME_SCALAR if 32BIT
         select MODULES_USE_ELF_RELA
@@ -375,19 +375,6 @@ config PACK_STACK
 
           Say Y if you are unsure.
 
-config SMALL_STACK
-        def_bool n
-        prompt "Use 8kb for kernel stack instead of 16kb"
-        depends on PACK_STACK && 64BIT && !LOCKDEP
-        help
-          If you say Y here and the compiler supports the -mkernel-backchain
-          option the kernel will use a smaller kernel stack size. The reduced
-          size is 8kb instead of 16kb. This allows to run more threads on a
-          system and reduces the pressure on the memory management for higher
-          order page allocations.
-
-          Say N if you are unsure.
-
 config CHECK_STACK
         def_bool y
         prompt "Detect kernel stack overflow"
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 7e3ce78d4290..a7d68a467ce8 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -55,22 +55,12 @@ cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls
 ifeq ($(call cc-option-yn,-mkernel-backchain),y)
 cflags-$(CONFIG_PACK_STACK)  += -mkernel-backchain -D__PACK_STACK
 aflags-$(CONFIG_PACK_STACK)  += -D__PACK_STACK
-cflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK
-aflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK
-ifdef CONFIG_SMALL_STACK
-STACK_SIZE := $(shell echo $$(($(STACK_SIZE)/2)) )
-endif
 endif
 
 # new style option for packed stacks
 ifeq ($(call cc-option-yn,-mpacked-stack),y)
 cflags-$(CONFIG_PACK_STACK)  += -mpacked-stack -D__PACK_STACK
 aflags-$(CONFIG_PACK_STACK)  += -D__PACK_STACK
-cflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK
-aflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK
-ifdef CONFIG_SMALL_STACK
-STACK_SIZE := $(shell echo $$(($(STACK_SIZE)/2)) )
-endif
 endif
 
 ifeq ($(call cc-option-yn,-mstack-size=8192 -mstack-guard=128),y)
diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c
index 9fd4a40c6752..bb5dd496614f 100644
--- a/arch/s390/hypfs/hypfs_dbfs.c
+++ b/arch/s390/hypfs/hypfs_dbfs.c
@@ -105,9 +105,7 @@ void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df)
 int hypfs_dbfs_init(void)
 {
         dbfs_dir = debugfs_create_dir("s390_hypfs", NULL);
-        if (IS_ERR(dbfs_dir))
-                return PTR_ERR(dbfs_dir);
-        return 0;
+        return PTR_RET(dbfs_dir);
 }
 
 void hypfs_dbfs_exit(void)
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 15422933c60b..4d8604e311f3 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -61,8 +61,6 @@ extern const char _sb_findmap[];
 
 #ifndef CONFIG_64BIT
 
-#define __BITOPS_ALIGN          3
-#define __BITOPS_WORDSIZE       32
 #define __BITOPS_OR             "or"
 #define __BITOPS_AND            "nr"
 #define __BITOPS_XOR            "xr"
@@ -81,8 +79,6 @@ extern const char _sb_findmap[];
 
 #else /* CONFIG_64BIT */
 
-#define __BITOPS_ALIGN          7
-#define __BITOPS_WORDSIZE       64
 #define __BITOPS_OR             "ogr"
 #define __BITOPS_AND            "ngr"
 #define __BITOPS_XOR            "xgr"
@@ -101,8 +97,7 @@ extern const char _sb_findmap[];
 
 #endif /* CONFIG_64BIT */
 
-#define __BITOPS_WORDS(bits) (((bits)+__BITOPS_WORDSIZE-1)/__BITOPS_WORDSIZE)
-#define __BITOPS_BARRIER() asm volatile("" : : : "memory")
+#define __BITOPS_WORDS(bits) (((bits) + BITS_PER_LONG - 1) / BITS_PER_LONG)
 
 #ifdef CONFIG_SMP
 /*
@@ -114,9 +109,9 @@ static inline void set_bit_cs(unsigned long nr, volatile unsigned long *ptr)
 
         addr = (unsigned long) ptr;
         /* calculate address for CS */
-        addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3;
+        addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3;
         /* make OR mask */
-        mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1));
+        mask = 1UL << (nr & (BITS_PER_LONG - 1));
         /* Do the atomic update. */
         __BITOPS_LOOP(old, new, addr, mask, __BITOPS_OR);
 }
@@ -130,9 +125,9 @@ static inline void clear_bit_cs(unsigned long nr, volatile unsigned long *ptr)
 
         addr = (unsigned long) ptr;
         /* calculate address for CS */
-        addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3;
+        addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3;
         /* make AND mask */
-        mask = ~(1UL << (nr & (__BITOPS_WORDSIZE - 1)));
+        mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
         /* Do the atomic update. */
         __BITOPS_LOOP(old, new, addr, mask, __BITOPS_AND);
 }
@@ -146,9 +141,9 @@ static inline void change_bit_cs(unsigned long nr, volatile unsigned long *ptr)
 
         addr = (unsigned long) ptr;
         /* calculate address for CS */
-        addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3;
+        addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3;
         /* make XOR mask */
-        mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1));
+        mask = 1UL << (nr & (BITS_PER_LONG - 1));
         /* Do the atomic update. */
         __BITOPS_LOOP(old, new, addr, mask, __BITOPS_XOR);
 }
@@ -163,12 +158,12 @@ test_and_set_bit_cs(unsigned long nr, volatile unsigned long *ptr)
 
         addr = (unsigned long) ptr;
         /* calculate address for CS */
-        addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3;
+        addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3;
         /* make OR/test mask */
-        mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1));
+        mask = 1UL << (nr & (BITS_PER_LONG - 1));
         /* Do the atomic update. */
         __BITOPS_LOOP(old, new, addr, mask, __BITOPS_OR);
-        __BITOPS_BARRIER();
+        barrier();
         return (old & mask) != 0;
 }
 
@@ -182,12 +177,12 @@ test_and_clear_bit_cs(unsigned long nr, volatile unsigned long *ptr)
 
         addr = (unsigned long) ptr;
         /* calculate address for CS */
-        addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3;
+        addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3;
         /* make AND/test mask */
-        mask = ~(1UL << (nr & (__BITOPS_WORDSIZE - 1)));
+        mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
         /* Do the atomic update. */
         __BITOPS_LOOP(old, new, addr, mask, __BITOPS_AND);
-        __BITOPS_BARRIER();
+        barrier();
         return (old ^ new) != 0;
 }
 
@@ -201,12 +196,12 @@ test_and_change_bit_cs(unsigned long nr, volatile unsigned long *ptr)
 
         addr = (unsigned long) ptr;
         /* calculate address for CS */
-        addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3;
+        addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3;
         /* make XOR/test mask */
-        mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1));
+        mask = 1UL << (nr & (BITS_PER_LONG - 1));
         /* Do the atomic update. */
         __BITOPS_LOOP(old, new, addr, mask, __BITOPS_XOR);
-        __BITOPS_BARRIER();
+        barrier();
         return (old & mask) != 0;
 }
 #endif /* CONFIG_SMP */
@@ -218,7 +213,7 @@ static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr)
 {
         unsigned long addr;
 
-        addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
+        addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         asm volatile(
                 "       oc      %O0(1,%R0),%1"
                 : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" );
@@ -229,7 +224,7 @@ __constant_set_bit(const unsigned long nr, volatile unsigned long *ptr)
 {
         unsigned long addr;
 
-        addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
+        addr = ((unsigned long) ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         *(unsigned char *) addr |= 1 << (nr & 7);
 }
 
@@ -246,7 +241,7 @@ __clear_bit(unsigned long nr, volatile unsigned long *ptr)
 {
         unsigned long addr;
 
-        addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
+        addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         asm volatile(
                 "       nc      %O0(1,%R0),%1"
                 : "=Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc" );
@@ -257,7 +252,7 @@ __constant_clear_bit(const unsigned long nr, volatile unsigned long *ptr)
 {
         unsigned long addr;
 
-        addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
+        addr = ((unsigned long) ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         *(unsigned char *) addr &= ~(1 << (nr & 7));
 }
 
@@ -273,7 +268,7 @@ static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr)
 {
         unsigned long addr;
 
-        addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
+        addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         asm volatile(
                 "       xc      %O0(1,%R0),%1"
                 : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" );
@@ -284,7 +279,7 @@ __constant_change_bit(const unsigned long nr, volatile unsigned long *ptr)
 {
         unsigned long addr;
 
-        addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
+        addr = ((unsigned long) ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         *(unsigned char *) addr ^= 1 << (nr & 7);
 }
 
@@ -302,7 +297,7 @@ test_and_set_bit_simple(unsigned long nr, volatile unsigned long *ptr)
         unsigned long addr;
         unsigned char ch;
 
-        addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
+        addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         ch = *(unsigned char *) addr;
         asm volatile(
                 "       oc      %O0(1,%R0),%1"
@@ -321,7 +316,7 @@ test_and_clear_bit_simple(unsigned long nr, volatile unsigned long *ptr)
         unsigned long addr;
         unsigned char ch;
 
-        addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
+        addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         ch = *(unsigned char *) addr;
         asm volatile(
                 "       nc      %O0(1,%R0),%1"
@@ -340,7 +335,7 @@ test_and_change_bit_simple(unsigned long nr, volatile unsigned long *ptr)
         unsigned long addr;
         unsigned char ch;
 
-        addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
+        addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         ch = *(unsigned char *) addr;
         asm volatile(
                 "       xc      %O0(1,%R0),%1"
@@ -376,7 +371,7 @@ static inline int __test_bit(unsigned long nr, const volatile unsigned long *ptr
         unsigned long addr;
         unsigned char ch;
 
-        addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
+        addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
         ch = *(volatile unsigned char *) addr;
         return (ch >> (nr & 7)) & 1;
 }
@@ -384,7 +379,7 @@ static inline int __test_bit(unsigned long nr, const volatile unsigned long *ptr
 static inline int 
 __constant_test_bit(unsigned long nr, const volatile unsigned long *addr) {
     return (((volatile char *) addr)
-            [(nr^(__BITOPS_WORDSIZE-8))>>3] & (1<<(nr&7))) != 0;
+            [(nr^(BITS_PER_LONG-8))>>3] & (1<<(nr&7))) != 0;
 }
 
 #define test_bit(nr,addr) \
@@ -693,18 +688,18 @@ static inline int find_next_bit_left(const unsigned long *addr,
 
         if (offset >= size)
                 return size;
-        bit = offset & (__BITOPS_WORDSIZE - 1);
+        bit = offset & (BITS_PER_LONG - 1);
         offset -= bit;
         size -= offset;
-        p = addr + offset / __BITOPS_WORDSIZE;
+        p = addr + offset / BITS_PER_LONG;
         if (bit) {
                 set = __flo_word(0, *p & (~0UL << bit));
                 if (set >= size)
                         return size + offset;
-                if (set < __BITOPS_WORDSIZE)
+                if (set < BITS_PER_LONG)
                         return set + offset;
-                offset += __BITOPS_WORDSIZE;
-                size -= __BITOPS_WORDSIZE;
+                offset += BITS_PER_LONG;
+                size -= BITS_PER_LONG;
                 p++;
         }
         return offset + find_first_bit_left(p, size);
@@ -736,22 +731,22 @@ static inline int find_next_zero_bit (const unsigned long * addr,
 
         if (offset >= size)
                 return size;
-        bit = offset & (__BITOPS_WORDSIZE - 1);
+        bit = offset & (BITS_PER_LONG - 1);
         offset -= bit;
         size -= offset;
-        p = addr + offset / __BITOPS_WORDSIZE;
+        p = addr + offset / BITS_PER_LONG;
         if (bit) {
                 /*
-                 * __ffz_word returns __BITOPS_WORDSIZE
+                 * __ffz_word returns BITS_PER_LONG
                  * if no zero bit is present in the word.
                  */
                 set = __ffz_word(bit, *p >> bit);
                 if (set >= size)
                         return size + offset;
-                if (set < __BITOPS_WORDSIZE)
+                if (set < BITS_PER_LONG)
                         return set + offset;
-                offset += __BITOPS_WORDSIZE;
-                size -= __BITOPS_WORDSIZE;
+                offset += BITS_PER_LONG;
+                size -= BITS_PER_LONG;
                 p++;
         }
         return offset + find_first_zero_bit(p, size);
@@ -773,22 +768,22 @@ static inline int find_next_bit (const unsigned long * addr,
 
         if (offset >= size)
                 return size;
-        bit = offset & (__BITOPS_WORDSIZE - 1);
+        bit = offset & (BITS_PER_LONG - 1);
         offset -= bit;
         size -= offset;
-        p = addr + offset / __BITOPS_WORDSIZE;
+        p = addr + offset / BITS_PER_LONG;
         if (bit) {
                 /*
-                 * __ffs_word returns __BITOPS_WORDSIZE
+                 * __ffs_word returns BITS_PER_LONG
                  * if no one bit is present in the word.
                  */
                 set = __ffs_word(0, *p & (~0UL << bit));
                 if (set >= size)
                         return size + offset;
-                if (set < __BITOPS_WORDSIZE)
+                if (set < BITS_PER_LONG)
                         return set + offset;
-                offset += __BITOPS_WORDSIZE;
-                size -= __BITOPS_WORDSIZE;
+                offset += BITS_PER_LONG;
+                size -= BITS_PER_LONG;
                 p++;
         }
         return offset + find_first_bit(p, size);
@@ -843,22 +838,22 @@ static inline int find_next_zero_bit_le(void *vaddr, unsigned long size,
 
         if (offset >= size)
                 return size;
-        bit = offset & (__BITOPS_WORDSIZE - 1);
+        bit = offset & (BITS_PER_LONG - 1);
         offset -= bit;
         size -= offset;
-        p = addr + offset / __BITOPS_WORDSIZE;
+        p = addr + offset / BITS_PER_LONG;
         if (bit) {
                 /*
-                 * s390 version of ffz returns __BITOPS_WORDSIZE
+                 * s390 version of ffz returns BITS_PER_LONG
                  * if no zero bit is present in the word.
                  */
                 set = __ffz_word(bit, __load_ulong_le(p, 0) >> bit);
                 if (set >= size)
                         return size + offset;
-                if (set < __BITOPS_WORDSIZE)
+                if (set < BITS_PER_LONG)
                         return set + offset;
-                offset += __BITOPS_WORDSIZE;
-                size -= __BITOPS_WORDSIZE;
+                offset += BITS_PER_LONG;
+                size -= BITS_PER_LONG;
                 p++;
         }
         return offset + find_first_zero_bit_le(p, size);
@@ -885,22 +880,22 @@ static inline int find_next_bit_le(void *vaddr, unsigned long size,
 
         if (offset >= size)
                 return size;
-        bit = offset & (__BITOPS_WORDSIZE - 1);
+        bit = offset & (BITS_PER_LONG - 1);
         offset -= bit;
         size -= offset;
-        p = addr + offset / __BITOPS_WORDSIZE;
+        p = addr + offset / BITS_PER_LONG;
         if (bit) {
                 /*
-                 * s390 version of ffz returns __BITOPS_WORDSIZE
+                 * s390 version of ffz returns BITS_PER_LONG
                  * if no zero bit is present in the word.
                  */
                 set = __ffs_word(0, __load_ulong_le(p, 0) & (~0UL << bit));
                 if (set >= size)
                         return size + offset;
-                if (set < __BITOPS_WORDSIZE)
+                if (set < BITS_PER_LONG)
                         return set + offset;
-                offset += __BITOPS_WORDSIZE;
-                size -= __BITOPS_WORDSIZE;
+                offset += BITS_PER_LONG;
+                size -= BITS_PER_LONG;
                 p++;
         }
         return offset + find_first_bit_le(p, size);
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index e6061617a50b..f201af8be580 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -220,7 +220,8 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *);
 #define to_ccwdrv(n) container_of(n, struct ccw_driver, driver)
 
 extern struct ccw_device *ccw_device_probe_console(void);
-extern int ccw_device_force_console(void);
+extern void ccw_device_wait_idle(struct ccw_device *);
+extern int ccw_device_force_console(struct ccw_device *);
 
 int ccw_device_siosl(struct ccw_device *);
 
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index ad2b924167d7..ffb898961c8d 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -296,8 +296,6 @@ static inline int ccw_dev_id_is_equal(struct ccw_dev_id *dev_id1,
         return 0;
 }
 
-extern void wait_cons_dev(void);
-
 extern void css_schedule_reprobe(void);
 
 extern void reipl_ccw_dev(struct ccw_dev_id *id);
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index f8c6df6cd1f0..c1e7c646727c 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -70,6 +70,22 @@ typedef u32		compat_ulong_t;
 typedef u64             compat_u64;
 typedef u32             compat_uptr_t;
 
+typedef struct {
+        u32 mask;
+        u32 addr;
+} __aligned(8) psw_compat_t;
+
+typedef struct {
+        psw_compat_t psw;
+        u32 gprs[NUM_GPRS];
+        u32 acrs[NUM_ACRS];
+        u32 orig_gpr2;
+} s390_compat_regs;
+
+typedef struct {
+        u32 gprs_high[NUM_GPRS];
+} s390_compat_regs_high;
+
 struct compat_timespec {
         compat_time_t   tv_sec;
         s32             tv_nsec;
@@ -124,18 +140,33 @@ struct compat_flock64 {
 };
 
 struct compat_statfs {
-        s32             f_type;
-        s32             f_bsize;
-        s32             f_blocks;
-        s32             f_bfree;
-        s32             f_bavail;
-        s32             f_files;
-        s32             f_ffree;
+        u32             f_type;
+        u32             f_bsize;
+        u32             f_blocks;
+        u32             f_bfree;
+        u32             f_bavail;
+        u32             f_files;
+        u32             f_ffree;
+        compat_fsid_t   f_fsid;
+        u32             f_namelen;
+        u32             f_frsize;
+        u32             f_flags;
+        u32             f_spare[4];
+};
+
+struct compat_statfs64 {
+        u32             f_type;
+        u32             f_bsize;
+        u64             f_blocks;
+        u64             f_bfree;
+        u64             f_bavail;
+        u64             f_files;
+        u64             f_ffree;
         compat_fsid_t   f_fsid;
-        s32             f_namelen;
-        s32             f_frsize;
-        s32             f_flags;
-        s32             f_spare[5];
+        u32             f_namelen;
+        u32             f_frsize;
+        u32             f_flags;
+        u32             f_spare[4];
 };
 
 #define COMPAT_RLIM_OLD_INFINITY        0x7fffffff
@@ -248,8 +279,6 @@ static inline int is_compat_task(void)
         return is_32bit_task();
 }
 
-#endif
-
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
         unsigned long stack;
@@ -260,6 +289,8 @@ static inline void __user *arch_compat_alloc_user_space(long len)
         return (void __user *) (stack - len);
 }
 
+#endif
+
 struct compat_ipc64_perm {
         compat_key_t key;
         __compat_uid32_t uid;
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index f1eddd150dd7..c879fad404c8 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -12,6 +12,7 @@
 #ifndef _ASM_S390_CPU_MF_H
 #define _ASM_S390_CPU_MF_H
 
+#include <linux/errno.h>
 #include <asm/facility.h>
 
 #define CPU_MF_INT_SF_IAE       (1 << 31)       /* invalid entry address */
diff --git a/arch/s390/include/asm/eadm.h b/arch/s390/include/asm/eadm.h
index 8d4847191ecc..dc9200ca32ed 100644
--- a/arch/s390/include/asm/eadm.h
+++ b/arch/s390/include/asm/eadm.h
@@ -34,6 +34,8 @@ struct arsb {
         u32 reserved[4];
 } __packed;
 
+#define EQC_WR_PROHIBIT 22
+
 struct msb {
         u8 fmt:4;
         u8 oc:4;
@@ -96,11 +98,13 @@ struct scm_device {
 #define OP_STATE_TEMP_ERR       2
 #define OP_STATE_PERM_ERR       3
 
+enum scm_event {SCM_CHANGE, SCM_AVAIL};
+
 struct scm_driver {
         struct device_driver drv;
         int (*probe) (struct scm_device *scmdev);
         int (*remove) (struct scm_device *scmdev);
-        void (*notify) (struct scm_device *scmdev);
+        void (*notify) (struct scm_device *scmdev, enum scm_event event);
         void (*handler) (struct scm_device *scmdev, void *data, int error);
 };
 
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 1bfdf24b85a2..78f4f8711d58 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -119,6 +119,8 @@
  */
 
 #include <asm/ptrace.h>
+#include <asm/compat.h>
+#include <asm/syscall.h>
 #include <asm/user.h>
 
 typedef s390_fp_regs elf_fpregset_t;
@@ -180,18 +182,31 @@ extern unsigned long elf_hwcap;
 extern char elf_platform[];
 #define ELF_PLATFORM (elf_platform)
 
-#ifdef CONFIG_64BIT
+#ifndef CONFIG_COMPAT
+#define SET_PERSONALITY(ex) \
+do {                                                            \
+        set_personality(PER_LINUX |                             \
+                (current->personality & (~PER_MASK)));          \
+        current_thread_info()->sys_call_table =                 \
+                (unsigned long) &sys_call_table;                \
+} while (0)
+#else /* CONFIG_COMPAT */
 #define SET_PERSONALITY(ex)                                     \
 do {                                                            \
         if (personality(current->personality) != PER_LINUX32)   \
                 set_personality(PER_LINUX |                     \
                         (current->personality & ~PER_MASK));    \
-        if ((ex).e_ident[EI_CLASS] == ELFCLASS32)               \
+        if ((ex).e_ident[EI_CLASS] == ELFCLASS32) {             \
                 set_thread_flag(TIF_31BIT);                     \
-        else                                                    \
+                current_thread_info()->sys_call_table =         \
+                        (unsigned long) &sys_call_table_emu;    \
+        } else {                                                \
                 clear_thread_flag(TIF_31BIT);                   \
+                current_thread_info()->sys_call_table =         \
+                        (unsigned long) &sys_call_table;        \
+        }                                                       \
 } while (0)
-#endif /* CONFIG_64BIT */
+#endif /* CONFIG_COMPAT */
 
 #define STACK_RND_MASK  0x7ffUL
 
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 593753ee07f3..bd90359d6d22 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -114,7 +114,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 #define huge_ptep_set_wrprotect(__mm, __addr, __ptep)                   \
 ({                                                                      \
         pte_t __pte = huge_ptep_get(__ptep);                            \
-        if (pte_write(__pte)) {                                         \
+        if (huge_pte_write(__pte)) {                                    \
                 huge_ptep_invalidate(__mm, __addr, __ptep);             \
                 set_huge_pte_at(__mm, __addr, __ptep,                   \
                                 huge_pte_wrprotect(__pte));             \
@@ -127,4 +127,58 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
         huge_ptep_invalidate(vma->vm_mm, address, ptep);
 }
 
+static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
+{
+        pte_t pte;
+        pmd_t pmd;
+
+        pmd = mk_pmd_phys(page_to_phys(page), pgprot);
+        pte_val(pte) = pmd_val(pmd);
+        return pte;
+}
+
+static inline int huge_pte_write(pte_t pte)
+{
+        pmd_t pmd;
+
+        pmd_val(pmd) = pte_val(pte);
+        return pmd_write(pmd);
+}
+
+static inline int huge_pte_dirty(pte_t pte)
+{
+        /* No dirty bit in the segment table entry. */
+        return 0;
+}
+
+static inline pte_t huge_pte_mkwrite(pte_t pte)
+{
+        pmd_t pmd;
+
+        pmd_val(pmd) = pte_val(pte);
+        pte_val(pte) = pmd_val(pmd_mkwrite(pmd));
+        return pte;
+}
+
+static inline pte_t huge_pte_mkdirty(pte_t pte)
+{
+        /* No dirty bit in the segment table entry. */
+        return pte;
+}
+
+static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
+{
+        pmd_t pmd;
+
+        pmd_val(pmd) = pte_val(pte);
+        pte_val(pte) = pmd_val(pmd_modify(pmd, newprot));
+        return pte;
+}
+
+static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+                                  pte_t *ptep)
+{
+        pmd_clear((pmd_t *) ptep);
+}
+
 #endif /* _ASM_S390_HUGETLB_H */
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index 27cb32185ce1..379d96e2105e 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -50,10 +50,6 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
 #define ioremap_nocache(addr, size)     ioremap(addr, size)
 #define ioremap_wc                      ioremap_nocache
 
-/* TODO: s390 cannot support io_remap_pfn_range... */
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)                \
-        remap_pfn_range(vma, vaddr, pfn, size, prot)
-
 static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 {
         return (void __iomem *) offset;
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 05333b7f0469..6c1801235db9 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -140,6 +140,7 @@ static inline bool zdev_enabled(struct zpci_dev *zdev)
 struct zpci_dev *zpci_alloc_device(void);
 int zpci_create_device(struct zpci_dev *);
 int zpci_enable_device(struct zpci_dev *);
+int zpci_disable_device(struct zpci_dev *);
 void zpci_stop_device(struct zpci_dev *);
 void zpci_free_device(struct zpci_dev *);
 int zpci_scan_device(struct zpci_dev *);
diff --git a/arch/s390/include/asm/pci_debug.h b/arch/s390/include/asm/pci_debug.h
index 6bbec4265b6e..1ca5d1047c71 100644
--- a/arch/s390/include/asm/pci_debug.h
+++ b/arch/s390/include/asm/pci_debug.h
@@ -7,14 +7,11 @@ extern debug_info_t *pci_debug_msg_id;
 extern debug_info_t *pci_debug_err_id;
 
 #ifdef CONFIG_PCI_DEBUG
-#define zpci_dbg(fmt, args...)                                                  \
-        do {                                                                    \
-                if (pci_debug_msg_id->level >= 2)                               \
-                        debug_sprintf_event(pci_debug_msg_id, 2, fmt , ## args);\
-        } while (0)
+#define zpci_dbg(imp, fmt, args...)                             \
+        debug_sprintf_event(pci_debug_msg_id, imp, fmt, ##args)
 
 #else /* !CONFIG_PCI_DEBUG */
-#define zpci_dbg(fmt, args...) do { } while (0)
+#define zpci_dbg(imp, fmt, args...) do { } while (0)
 #endif
 
 #define zpci_err(text...)                                                       \
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
index 1486a98d5dad..e6a2bdd4d705 100644
--- a/arch/s390/include/asm/pci_insn.h
+++ b/arch/s390/include/asm/pci_insn.h
@@ -1,10 +1,6 @@
 #ifndef _ASM_S390_PCI_INSN_H
 #define _ASM_S390_PCI_INSN_H
 
-#include <linux/delay.h>
-
-#define ZPCI_INSN_BUSY_DELAY    1       /* 1 microsecond */
-
 /* Load/Store status codes */
 #define ZPCI_PCI_ST_FUNC_NOT_ENABLED            4
 #define ZPCI_PCI_ST_FUNC_IN_ERR                 8
@@ -82,199 +78,12 @@ struct zpci_fib {
         u64 reserved7;
 } __packed;
 
-/* Modify PCI Function Controls */
-static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status)
-{
-        u8 cc;
-
-        asm volatile (
-                "       .insn   rxy,0xe300000000d0,%[req],%[fib]\n"
-                "       ipm     %[cc]\n"
-                "       srl     %[cc],28\n"
-                : [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib)
-                : : "cc");
-        *status = req >> 24 & 0xff;
-        return cc;
-}
-
-static inline int mpcifc_instr(u64 req, struct zpci_fib *fib)
-{
-        u8 cc, status;
-
-        do {
-                cc = __mpcifc(req, fib, &status);
-                if (cc == 2)
-                        msleep(ZPCI_INSN_BUSY_DELAY);
-        } while (cc == 2);
-
-        if (cc)
-                printk_once(KERN_ERR "%s: error cc: %d  status: %d\n",
-                             __func__, cc, status);
-        return (cc) ? -EIO : 0;
-}
-
-/* Refresh PCI Translations */
-static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status)
-{
-        register u64 __addr asm("2") = addr;
-        register u64 __range asm("3") = range;
-        u8 cc;
-
-        asm volatile (
-                "       .insn   rre,0xb9d30000,%[fn],%[addr]\n"
-                "       ipm     %[cc]\n"
-                "       srl     %[cc],28\n"
-                : [cc] "=d" (cc), [fn] "+d" (fn)
-                : [addr] "d" (__addr), "d" (__range)
-                : "cc");
-        *status = fn >> 24 & 0xff;
-        return cc;
-}
-
-static inline int rpcit_instr(u64 fn, u64 addr, u64 range)
-{
-        u8 cc, status;
-
-        do {
-                cc = __rpcit(fn, addr, range, &status);
-                if (cc == 2)
-                        udelay(ZPCI_INSN_BUSY_DELAY);
-        } while (cc == 2);
-
-        if (cc)
-                printk_once(KERN_ERR "%s: error cc: %d  status: %d  dma_addr: %Lx  size: %Lx\n",
-                            __func__, cc, status, addr, range);
-        return (cc) ? -EIO : 0;
-}
-
-/* Store PCI function controls */
-static inline u8 __stpcifc(u32 handle, u8 space, struct zpci_fib *fib, u8 *status)
-{
-        u64 fn = (u64) handle << 32 | space << 16;
-        u8 cc;
-
-        asm volatile (
-                "       .insn   rxy,0xe300000000d4,%[fn],%[fib]\n"
-                "       ipm     %[cc]\n"
-                "       srl     %[cc],28\n"
-                : [cc] "=d" (cc), [fn] "+d" (fn), [fib] "=m" (*fib)
-                : : "cc");
-        *status = fn >> 24 & 0xff;
-        return cc;
-}
-
-/* Set Interruption Controls */
-static inline void sic_instr(u16 ctl, char *unused, u8 isc)
-{
-        asm volatile (
-                "       .insn   rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n"
-                : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused));
-}
-
-/* PCI Load */
-static inline u8 __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
-{
-        register u64 __req asm("2") = req;
-        register u64 __offset asm("3") = offset;
-        u64 __data;
-        u8 cc;
-
-        asm volatile (
-                "       .insn   rre,0xb9d20000,%[data],%[req]\n"
-                "       ipm     %[cc]\n"
-                "       srl     %[cc],28\n"
-                : [cc] "=d" (cc), [data] "=d" (__data), [req] "+d" (__req)
-                :  "d" (__offset)
-                : "cc");
-        *status = __req >> 24 & 0xff;
-        *data = __data;
-        return cc;
-}
-
-static inline int pcilg_instr(u64 *data, u64 req, u64 offset)
-{
-        u8 cc, status;
-
-        do {
-                cc = __pcilg(data, req, offset, &status);
-                if (cc == 2)
-                        udelay(ZPCI_INSN_BUSY_DELAY);
-        } while (cc == 2);
-
-        if (cc) {
-                printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
-                            __func__, cc, status, req, offset);
-                /* TODO: on IO errors set data to 0xff...
-                 * here or in users of pcilg (le conversion)?
-                 */
-        }
-        return (cc) ? -EIO : 0;
-}
-
-/* PCI Store */
-static inline u8 __pcistg(u64 data, u64 req, u64 offset, u8 *status)
-{
-        register u64 __req asm("2") = req;
-        register u64 __offset asm("3") = offset;
-        u8 cc;
-
-        asm volatile (
-                "       .insn   rre,0xb9d00000,%[data],%[req]\n"
-                "       ipm     %[cc]\n"
-                "       srl     %[cc],28\n"
-                : [cc] "=d" (cc), [req] "+d" (__req)
-                : "d" (__offset), [data] "d" (data)
-                : "cc");
-        *status = __req >> 24 & 0xff;
-        return cc;
-}
-
-static inline int pcistg_instr(u64 data, u64 req, u64 offset)
-{
-        u8 cc, status;
-
-        do {
-                cc = __pcistg(data, req, offset, &status);
-                if (cc == 2)
-                        udelay(ZPCI_INSN_BUSY_DELAY);
-        } while (cc == 2);
-
-        if (cc)
-                printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
-                        __func__, cc, status, req, offset);
-        return (cc) ? -EIO : 0;
-}
-
-/* PCI Store Block */
-static inline u8 __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
-{
-        u8 cc;
-
-        asm volatile (
-                "       .insn   rsy,0xeb00000000d0,%[req],%[offset],%[data]\n"
-                "       ipm     %[cc]\n"
-                "       srl     %[cc],28\n"
-                : [cc] "=d" (cc), [req] "+d" (req)
-                : [offset] "d" (offset), [data] "Q" (*data)
-                : "cc");
-        *status = req >> 24 & 0xff;
-        return cc;
-}
-
-static inline int pcistb_instr(const u64 *data, u64 req, u64 offset)
-{
-        u8 cc, status;
-
-        do {
-                cc = __pcistb(data, req, offset, &status);
-                if (cc == 2)
-                        udelay(ZPCI_INSN_BUSY_DELAY);
-        } while (cc == 2);
 
-        if (cc)
-                printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
-                            __func__, cc, status, req, offset);
-        return (cc) ? -EIO : 0;
-}
+int s390pci_mod_fc(u64 req, struct zpci_fib *fib);
+int s390pci_refresh_trans(u64 fn, u64 addr, u64 range);
+int s390pci_load(u64 *data, u64 req, u64 offset);
+int s390pci_store(u64 data, u64 req, u64 offset);
+int s390pci_store_block(const u64 *data, u64 req, u64 offset);
+void set_irq_ctrl(u16 ctl, char *unused, u8 isc);
 
 #endif
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index 5fd81f31d6c7..83a9caa6ae53 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -36,7 +36,7 @@ static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr)	\
         u64 data;                                                               \
         int rc;                                                                 \
                                                                                 \
-        rc = pcilg_instr(&data, req, ZPCI_OFFSET(addr));                        \
+        rc = s390pci_load(&data, req, ZPCI_OFFSET(addr));                       \
         if (rc)                                                                 \
                 data = -1ULL;                                                   \
         return (RETTYPE) data;                                                  \
@@ -50,7 +50,7 @@ static inline void zpci_write_##VALTYPE(VALTYPE val,				\
         u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH);               \
         u64 data = (VALTYPE) val;                                               \
                                                                                 \
-        pcistg_instr(data, req, ZPCI_OFFSET(addr));                             \
+        s390pci_store(data, req, ZPCI_OFFSET(addr));                            \
 }
 
 zpci_read(8, u64)
@@ -83,15 +83,18 @@ static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len
                 val = 0;                /* let FW report error */
                 break;
         }
-        return pcistg_instr(val, req, offset);
+        return s390pci_store(val, req, offset);
 }
 
 static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len)
 {
         u64 data;
-        u8 cc;
+        int cc;
+
+        cc = s390pci_load(&data, req, offset);
+        if (cc)
+                goto out;
 
-        cc = pcilg_instr(&data,  req, offset);
         switch (len) {
         case 1:
                 *((u8 *) dst) = (u8) data;
@@ -106,12 +109,13 @@ static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len)
                 *((u64 *) dst) = (u64) data;
                 break;
         }
+out:
         return cc;
 }
 
 static inline int zpci_write_block(u64 req, const u64 *data, u64 offset)
 {
-        return pcistb_instr(data, req, offset);
+        return s390pci_store_block(data, req, offset);
 }
 
 static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 4a2930844d43..b4622915bd15 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -57,6 +57,10 @@ extern unsigned long zero_page_mask;
          (((unsigned long)(vaddr)) &zero_page_mask))))
 #define __HAVE_COLOR_ZERO_PAGE
 
+/* TODO: s390 cannot support io_remap_pfn_range... */
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)                \
+        remap_pfn_range(vma, vaddr, pfn, size, prot)
+
 #endif /* !__ASSEMBLY__ */
 
 /*
@@ -344,6 +348,7 @@ extern unsigned long MODULES_END;
 #define _REGION3_ENTRY_CO       0x100   /* change-recording override        */
 
 /* Bits in the segment table entry */
+#define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address        */
 #define _SEGMENT_ENTRY_ORIGIN   ~0x7ffUL/* segment table origin             */
 #define _SEGMENT_ENTRY_RO       0x200   /* page protection bit              */
 #define _SEGMENT_ENTRY_INV      0x20    /* invalid segment table entry      */
@@ -419,6 +424,13 @@ extern unsigned long MODULES_END;
 #define __S110  PAGE_RW
 #define __S111  PAGE_RW
 
+/*
+ * Segment entry (large page) protection definitions.
+ */
+#define SEGMENT_NONE    __pgprot(_HPAGE_TYPE_NONE)
+#define SEGMENT_RO      __pgprot(_HPAGE_TYPE_RO)
+#define SEGMENT_RW      __pgprot(_HPAGE_TYPE_RW)
+
 static inline int mm_exclusive(struct mm_struct *mm)
 {
         return likely(mm == current->active_mm &&
@@ -759,6 +771,8 @@ void gmap_disable(struct gmap *gmap);
 int gmap_map_segment(struct gmap *gmap, unsigned long from,
                      unsigned long to, unsigned long length);
 int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
+unsigned long __gmap_translate(unsigned long address, struct gmap *);
+unsigned long gmap_translate(unsigned long address, struct gmap *);
 unsigned long __gmap_fault(unsigned long address, struct gmap *);
 unsigned long gmap_fault(unsigned long address, struct gmap *);
 void gmap_discard(unsigned long from, unsigned long to, struct gmap *);
@@ -907,26 +921,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
 #ifdef CONFIG_HUGETLB_PAGE
 static inline pte_t pte_mkhuge(pte_t pte)
 {
-        /*
-         * PROT_NONE needs to be remapped from the pte type to the ste type.
-         * The HW invalid bit is also different for pte and ste. The pte
-         * invalid bit happens to be the same as the ste _SEGMENT_ENTRY_LARGE
-         * bit, so we don't have to clear it.
-         */
-        if (pte_val(pte) & _PAGE_INVALID) {
-                if (pte_val(pte) & _PAGE_SWT)
-                        pte_val(pte) |= _HPAGE_TYPE_NONE;
-                pte_val(pte) |= _SEGMENT_ENTRY_INV;
-        }
-        /*
-         * Clear SW pte bits, there are no SW bits in a segment table entry.
-         */
-        pte_val(pte) &= ~(_PAGE_SWT | _PAGE_SWX | _PAGE_SWC |
-                          _PAGE_SWR | _PAGE_SWW);
-        /*
-         * Also set the change-override bit because we don't need dirty bit
-         * tracking for hugetlbfs pages.
-         */
         pte_val(pte) |= (_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO);
         return pte;
 }
@@ -1271,31 +1265,7 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
         }
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-
-#define SEGMENT_NONE    __pgprot(_HPAGE_TYPE_NONE)
-#define SEGMENT_RO      __pgprot(_HPAGE_TYPE_RO)
-#define SEGMENT_RW      __pgprot(_HPAGE_TYPE_RW)
-
-#define __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
-
-#define __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
-
-static inline int pmd_trans_splitting(pmd_t pmd)
-{
-        return pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT;
-}
-
-static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
-                              pmd_t *pmdp, pmd_t entry)
-{
-        if (!(pmd_val(entry) & _SEGMENT_ENTRY_INV) && MACHINE_HAS_EDAT1)
-                pmd_val(entry) |= _SEGMENT_ENTRY_CO;
-        *pmdp = entry;
-}
-
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
 static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
 {
         /*
@@ -1316,10 +1286,11 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
         return pmd;
 }
 
-static inline pmd_t pmd_mkhuge(pmd_t pmd)
+static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot)
 {
-        pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE;
-        return pmd;
+        pmd_t __pmd;
+        pmd_val(__pmd) = physpage + massage_pgprot_pmd(pgprot);
+        return __pmd;
 }
 
 static inline pmd_t pmd_mkwrite(pmd_t pmd)
@@ -1329,6 +1300,34 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
                 pmd_val(pmd) &= ~_SEGMENT_ENTRY_RO;
         return pmd;
 }
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+#define __HAVE_ARCH_PGTABLE_DEPOSIT
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+
+#define __HAVE_ARCH_PGTABLE_WITHDRAW
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+
+static inline int pmd_trans_splitting(pmd_t pmd)
+{
+        return pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT;
+}
+
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+                              pmd_t *pmdp, pmd_t entry)
+{
+        if (!(pmd_val(entry) & _SEGMENT_ENTRY_INV) && MACHINE_HAS_EDAT1)
+                pmd_val(entry) |= _SEGMENT_ENTRY_CO;
+        *pmdp = entry;
+}
+
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+        pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE;
+        return pmd;
+}
 
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
@@ -1425,13 +1424,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
         }
 }
 
-static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot)
-{
-        pmd_t __pmd;
-        pmd_val(__pmd) = physpage + massage_pgprot_pmd(pgprot);
-        return __pmd;
-}
-
 #define pfn_pmd(pfn, pgprot)    mk_pmd_phys(__pa((pfn) << PAGE_SHIFT), (pgprot))
 #define mk_pmd(page, pgprot)    pfn_pmd(page_to_pfn(page), (pgprot))
 
@@ -1531,7 +1523,8 @@ extern int s390_enable_sie(void);
 /*
  * No page table caches to initialise
  */
-#define pgtable_cache_init()    do { } while (0)
+static inline void pgtable_cache_init(void) { }
+static inline void check_pgt_cache(void) { }
 
 #include <asm-generic/pgtable.h>
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 94e749c90230..6b499870662f 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -161,7 +161,8 @@ extern unsigned long thread_saved_pc(struct task_struct *t);
 
 extern void show_code(struct pt_regs *regs);
 extern void print_fn_code(unsigned char *code, unsigned long len);
-extern int insn_to_mnemonic(unsigned char *instruction, char buf[8]);
+extern int insn_to_mnemonic(unsigned char *instruction, char *buf,
+                            unsigned int len);
 
 unsigned long get_wchan(struct task_struct *p);
 #define task_pt_regs(tsk) ((struct pt_regs *) \
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 3ee5da3bc10c..559512a455da 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -9,9 +9,7 @@
 #include <uapi/asm/ptrace.h>
 
 #ifndef __ASSEMBLY__
-#ifndef __s390x__
-#else /* __s390x__ */
-#endif /* __s390x__ */
+
 extern long psw_kernel_bits;
 extern long psw_user_bits;
 
@@ -77,8 +75,6 @@ struct per_struct_kernel {
 #define PER_CONTROL_SUSPENSION          0x00400000UL
 #define PER_CONTROL_ALTERATION          0x00200000UL
 
-#ifdef __s390x__
-#endif /* __s390x__ */
 /*
  * These are defined as per linux/ptrace.h, which see.
  */
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index fe7b99759e12..cd29d2f4e4f3 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -23,6 +23,7 @@
  * type here is what we want [need] for both 32 bit and 64 bit systems.
  */
 extern const unsigned int sys_call_table[];
+extern const unsigned int sys_call_table_emu[];
 
 static inline long syscall_get_nr(struct task_struct *task,
                                   struct pt_regs *regs)
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 9e2cfe0349c3..eb5f64d26d06 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -14,13 +14,8 @@
 #define THREAD_ORDER 1
 #define ASYNC_ORDER  1
 #else /* CONFIG_64BIT */
-#ifndef __SMALL_STACK
 #define THREAD_ORDER 2
 #define ASYNC_ORDER  2
-#else
-#define THREAD_ORDER 1
-#define ASYNC_ORDER  1
-#endif
 #endif /* CONFIG_64BIT */
 
 #define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER)
@@ -41,6 +36,7 @@ struct thread_info {
         struct task_struct      *task;          /* main task structure */
         struct exec_domain      *exec_domain;   /* execution domain */
         unsigned long           flags;          /* low level flags */
+        unsigned long           sys_call_table; /* System call table address */
         unsigned int            cpu;            /* current CPU */
         int                     preempt_count;  /* 0 => preemptable, <0 => BUG */
         struct restart_block    restart_block;
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index 1d8fe2b17ef6..6b32af30878c 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -74,8 +74,6 @@ static inline void __tlb_flush_idte(unsigned long asce)
 
 static inline void __tlb_flush_mm(struct mm_struct * mm)
 {
-        if (unlikely(cpumask_empty(mm_cpumask(mm))))
-                return;
         /*
          * If the machine has IDTE we prefer to do a per mm flush
          * on all cpus instead of doing a local flush if the mm
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index a5ca214b34fd..3aa9f1ec5b29 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -215,12 +215,6 @@ typedef struct
         unsigned long addr;
 } __attribute__ ((aligned(8))) psw_t;
 
-typedef struct
-{
-        __u32   mask;
-        __u32   addr;
-} __attribute__ ((aligned(8))) psw_compat_t;
-
 #ifndef __s390x__
 
 #define PSW_MASK_PER            0x40000000UL
@@ -295,20 +289,6 @@ typedef struct
         unsigned long orig_gpr2;
 } s390_regs;
 
-typedef struct
-{
-        psw_compat_t    psw;
-        __u32           gprs[NUM_GPRS];
-        __u32           acrs[NUM_ACRS];
-        __u32           orig_gpr2;
-} s390_compat_regs;
-
-typedef struct
-{
-        __u32           gprs_high[NUM_GPRS];
-} s390_compat_regs_high;
-
-
 /*
  * Now for the user space program event recording (trace) definitions.
  * The following structures are used only for the ptrace interface, don't
diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h
index 5acca0a34c20..a61d538756f2 100644
--- a/arch/s390/include/uapi/asm/statfs.h
+++ b/arch/s390/include/uapi/asm/statfs.h
@@ -7,9 +7,6 @@
 #ifndef _S390_STATFS_H
 #define _S390_STATFS_H
 
-#ifndef __s390x__
-#include <asm-generic/statfs.h>
-#else
 /*
  * We can't use <asm-generic/statfs.h> because in 64-bit mode
  * we mix ints of different sizes in our struct statfs.
@@ -21,49 +18,33 @@ typedef __kernel_fsid_t	fsid_t;
 #endif
 
 struct statfs {
-        int  f_type;
-        int  f_bsize;
-        long f_blocks;
-        long f_bfree;
-        long f_bavail;
-        long f_files;
-        long f_ffree;
+        unsigned int    f_type;
+        unsigned int    f_bsize;
+        unsigned long   f_blocks;
+        unsigned long   f_bfree;
+        unsigned long   f_bavail;
+        unsigned long   f_files;
+        unsigned long   f_ffree;
         __kernel_fsid_t f_fsid;
-        int  f_namelen;
-        int  f_frsize;
-        int  f_flags;
-        int  f_spare[4];
+        unsigned int    f_namelen;
+        unsigned int    f_frsize;
+        unsigned int    f_flags;
+        unsigned int    f_spare[4];
 };
 
 struct statfs64 {
-        int  f_type;
-        int  f_bsize;
-        long f_blocks;
-        long f_bfree;
-        long f_bavail;
-        long f_files;
-        long f_ffree;
+        unsigned int    f_type;
+        unsigned int    f_bsize;
+        unsigned long   f_blocks;
+        unsigned long   f_bfree;
+        unsigned long   f_bavail;
+        unsigned long   f_files;
+        unsigned long   f_ffree;
         __kernel_fsid_t f_fsid;
-        int  f_namelen;
-        int  f_frsize;
-        int  f_flags;
-        int  f_spare[4];
+        unsigned int    f_namelen;
+        unsigned int    f_frsize;
+        unsigned int    f_flags;
+        unsigned int    f_spare[4];
 };
 
-struct compat_statfs64 {
-        __u32 f_type;
-        __u32 f_bsize;
-        __u64 f_blocks;
-        __u64 f_bfree;
-        __u64 f_bavail;
-        __u64 f_files;
-        __u64 f_ffree;
-        __kernel_fsid_t f_fsid;
-        __u32 f_namelen;
-        __u32 f_frsize;
-        __u32 f_flags;
-        __u32 f_spare[4];
-};
-
-#endif /* __s390x__ */
 #endif
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 2ac311ef5c9b..1386fcaf4ef6 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -14,16 +14,25 @@ endif
 CFLAGS_smp.o    := -Wno-nonnull
 
 #
+# Disable tailcall optimizations for stack / callchain walking functions
+# since this might generate broken code when accessing register 15 and
+# passing its content to other functions.
+#
+CFLAGS_stacktrace.o     += -fno-optimize-sibling-calls
+CFLAGS_dumpstack.o      += -fno-optimize-sibling-calls
+
+#
 # Pass UTS_MACHINE for user_regset definition
 #
 CFLAGS_ptrace.o         += -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w
 
-obj-y   :=  bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o \
-            processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o \
-            debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o \
-            sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
+obj-y   := bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o
+obj-y   += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
+obj-y   += debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o
+obj-y   += sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
+obj-y   += dumpstack.o
 
 obj-y   += $(if $(CONFIG_64BIT),entry64.o,entry.o)
 obj-y   += $(if $(CONFIG_64BIT),reipl64.o,reipl.o)
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index fface87056eb..7a82f9f70100 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -35,6 +35,7 @@ int main(void)
         DEFINE(__TI_task, offsetof(struct thread_info, task));
         DEFINE(__TI_domain, offsetof(struct thread_info, exec_domain));
         DEFINE(__TI_flags, offsetof(struct thread_info, flags));
+        DEFINE(__TI_sysc_table, offsetof(struct thread_info, sys_call_table));
         DEFINE(__TI_cpu, offsetof(struct thread_info, cpu));
         DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count));
         DEFINE(__TI_user_timer, offsetof(struct thread_info, user_timer));
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 6de049fbe62d..c439ac9ced09 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -362,6 +362,7 @@ static int setup_frame32(int sig, struct k_sigaction *ka,
                 /* set extra registers only for synchronous signals */
                 regs->gprs[4] = regs->int_code & 127;
                 regs->gprs[5] = regs->int_parm_long;
+                regs->gprs[6] = task_thread_info(current)->last_break;
         }
 
         /* Place signal number on stack to allow backtrace from handler.  */
@@ -421,6 +422,7 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info,
         regs->gprs[2] = map_signal(sig);
         regs->gprs[3] = (__force __u64) &frame->info;
         regs->gprs[4] = (__force __u64) &frame->uc;
+        regs->gprs[5] = task_thread_info(current)->last_break;
         return 0;
 
 give_sigsegv:
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 3ad5e9540160..7f4a4a8c847c 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1696,14 +1696,15 @@ static struct insn *find_insn(unsigned char *code)
  * insn_to_mnemonic - decode an s390 instruction
  * @instruction: instruction to decode
  * @buf: buffer to fill with mnemonic
+ * @len: length of buffer
  *
  * Decode the instruction at @instruction and store the corresponding
- * mnemonic into @buf.
+ * mnemonic into @buf of length @len.
  * @buf is left unchanged if the instruction could not be decoded.
  * Returns:
  *  %0 on success, %-ENOENT if the instruction was not found.
  */
-int insn_to_mnemonic(unsigned char *instruction, char buf[8])
+int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len)
 {
         struct insn *insn;
 
@@ -1711,10 +1712,10 @@ int insn_to_mnemonic(unsigned char *instruction, char buf[8])
         if (!insn)
                 return -ENOENT;
         if (insn->name[0] == '\0')
-                snprintf(buf, 8, "%s",
+                snprintf(buf, len, "%s",
                          long_insn_name[(int) insn->name[1]]);
         else
-                snprintf(buf, 8, "%.5s", insn->name);
+                snprintf(buf, len, "%.5s", insn->name);
         return 0;
 }
 EXPORT_SYMBOL_GPL(insn_to_mnemonic);
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
new file mode 100644
index 000000000000..03dce39d01ee
--- /dev/null
+++ b/arch/s390/kernel/dumpstack.c
@@ -0,0 +1,236 @@
+/*
+ * Stack dumping functions
+ *
+ *  Copyright IBM Corp. 1999, 2013
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/hardirq.h>
+#include <linux/kprobes.h>
+#include <linux/utsname.h>
+#include <linux/export.h>
+#include <linux/kdebug.h>
+#include <linux/ptrace.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <asm/processor.h>
+#include <asm/debug.h>
+#include <asm/ipl.h>
+
+#ifndef CONFIG_64BIT
+#define LONG "%08lx "
+#define FOURLONG "%08lx %08lx %08lx %08lx\n"
+static int kstack_depth_to_print = 12;
+#else /* CONFIG_64BIT */
+#define LONG "%016lx "
+#define FOURLONG "%016lx %016lx %016lx %016lx\n"
+static int kstack_depth_to_print = 20;
+#endif /* CONFIG_64BIT */
+
+/*
+ * For show_trace we have tree different stack to consider:
+ *   - the panic stack which is used if the kernel stack has overflown
+ *   - the asynchronous interrupt stack (cpu related)
+ *   - the synchronous kernel stack (process related)
+ * The stack trace can start at any of the three stack and can potentially
+ * touch all of them. The order is: panic stack, async stack, sync stack.
+ */
+static unsigned long
+__show_trace(unsigned long sp, unsigned long low, unsigned long high)
+{
+        struct stack_frame *sf;
+        struct pt_regs *regs;
+
+        while (1) {
+                sp = sp & PSW_ADDR_INSN;
+                if (sp < low || sp > high - sizeof(*sf))
+                        return sp;
+                sf = (struct stack_frame *) sp;
+                printk("([<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN);
+                print_symbol("%s)\n", sf->gprs[8] & PSW_ADDR_INSN);
+                /* Follow the backchain. */
+                while (1) {
+                        low = sp;
+                        sp = sf->back_chain & PSW_ADDR_INSN;
+                        if (!sp)
+                                break;
+                        if (sp <= low || sp > high - sizeof(*sf))
+                                return sp;
+                        sf = (struct stack_frame *) sp;
+                        printk(" [<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN);
+                        print_symbol("%s\n", sf->gprs[8] & PSW_ADDR_INSN);
+                }
+                /* Zero backchain detected, check for interrupt frame. */
+                sp = (unsigned long) (sf + 1);
+                if (sp <= low || sp > high - sizeof(*regs))
+                        return sp;
+                regs = (struct pt_regs *) sp;
+                printk(" [<%016lx>] ", regs->psw.addr & PSW_ADDR_INSN);
+                print_symbol("%s\n", regs->psw.addr & PSW_ADDR_INSN);
+                low = sp;
+                sp = regs->gprs[15];
+        }
+}
+
+static void show_trace(struct task_struct *task, unsigned long *stack)
+{
+        register unsigned long __r15 asm ("15");
+        unsigned long sp;
+
+        sp = (unsigned long) stack;
+        if (!sp)
+                sp = task ? task->thread.ksp : __r15;
+        printk("Call Trace:\n");
+#ifdef CONFIG_CHECK_STACK
+        sp = __show_trace(sp, S390_lowcore.panic_stack - 4096,
+                          S390_lowcore.panic_stack);
+#endif
+        sp = __show_trace(sp, S390_lowcore.async_stack - ASYNC_SIZE,
+                          S390_lowcore.async_stack);
+        if (task)
+                __show_trace(sp, (unsigned long) task_stack_page(task),
+                             (unsigned long) task_stack_page(task) + THREAD_SIZE);
+        else
+                __show_trace(sp, S390_lowcore.thread_info,
+                             S390_lowcore.thread_info + THREAD_SIZE);
+        if (!task)
+                task = current;
+        debug_show_held_locks(task);
+}
+
+void show_stack(struct task_struct *task, unsigned long *sp)
+{
+        register unsigned long *__r15 asm ("15");
+        unsigned long *stack;
+        int i;
+
+        if (!sp)
+                stack = task ? (unsigned long *) task->thread.ksp : __r15;
+        else
+                stack = sp;
+
+        for (i = 0; i < kstack_depth_to_print; i++) {
+                if (((addr_t) stack & (THREAD_SIZE-1)) == 0)
+                        break;
+                if ((i * sizeof(long) % 32) == 0)
+                        printk("%s       ", i == 0 ? "" : "\n");
+                printk(LONG, *stack++);
+        }
+        printk("\n");
+        show_trace(task, sp);
+}
+
+static void show_last_breaking_event(struct pt_regs *regs)
+{
+#ifdef CONFIG_64BIT
+        printk("Last Breaking-Event-Address:\n");
+        printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN);
+        print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN);
+#endif
+}
+
+/*
+ * The architecture-independent dump_stack generator
+ */
+void dump_stack(void)
+{
+        printk("CPU: %d %s %s %.*s\n",
+               task_thread_info(current)->cpu, print_tainted(),
+               init_utsname()->release,
+               (int)strcspn(init_utsname()->version, " "),
+               init_utsname()->version);
+        printk("Process %s (pid: %d, task: %p, ksp: %p)\n",
+               current->comm, current->pid, current,
+               (void *) current->thread.ksp);
+        show_stack(NULL, NULL);
+}
+EXPORT_SYMBOL(dump_stack);
+
+static inline int mask_bits(struct pt_regs *regs, unsigned long bits)
+{
+        return (regs->psw.mask & bits) / ((~bits + 1) & bits);
+}
+
+void show_registers(struct pt_regs *regs)
+{
+        char *mode;
+
+        mode = user_mode(regs) ? "User" : "Krnl";
+        printk("%s PSW : %p %p",
+               mode, (void *) regs->psw.mask,
+               (void *) regs->psw.addr);
+        print_symbol(" (%s)\n", regs->psw.addr & PSW_ADDR_INSN);
+        printk("           R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
+               "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER),
+               mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO),
+               mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY),
+               mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT),
+               mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC),
+               mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM));
+#ifdef CONFIG_64BIT
+        printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA));
+#endif
+        printk("\n%s GPRS: " FOURLONG, mode,
+               regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]);
+        printk("           " FOURLONG,
+               regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]);
+        printk("           " FOURLONG,
+               regs->gprs[8], regs->gprs[9], regs->gprs[10], regs->gprs[11]);
+        printk("           " FOURLONG,
+               regs->gprs[12], regs->gprs[13], regs->gprs[14], regs->gprs[15]);
+        show_code(regs);
+}
+
+void show_regs(struct pt_regs *regs)
+{
+        printk("CPU: %d %s %s %.*s\n",
+               task_thread_info(current)->cpu, print_tainted(),
+               init_utsname()->release,
+               (int)strcspn(init_utsname()->version, " "),
+               init_utsname()->version);
+        printk("Process %s (pid: %d, task: %p, ksp: %p)\n",
+               current->comm, current->pid, current,
+               (void *) current->thread.ksp);
+        show_registers(regs);
+        /* Show stack backtrace if pt_regs is from kernel mode */
+        if (!user_mode(regs))
+                show_trace(NULL, (unsigned long *) regs->gprs[15]);
+        show_last_breaking_event(regs);
+}
+
+static DEFINE_SPINLOCK(die_lock);
+
+void die(struct pt_regs *regs, const char *str)
+{
+        static int die_counter;
+
+        oops_enter();
+        lgr_info_log();
+        debug_stop_all();
+        console_verbose();
+        spin_lock_irq(&die_lock);
+        bust_spinlocks(1);
+        printk("%s: %04x [#%d] ", str, regs->int_code & 0xffff, ++die_counter);
+#ifdef CONFIG_PREEMPT
+        printk("PREEMPT ");
+#endif
+#ifdef CONFIG_SMP
+        printk("SMP ");
+#endif
+#ifdef CONFIG_DEBUG_PAGEALLOC
+        printk("DEBUG_PAGEALLOC");
+#endif
+        printk("\n");
+        notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV);
+        print_modules();
+        show_regs(regs);
+        bust_spinlocks(0);
+        add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
+        spin_unlock_irq(&die_lock);
+        if (in_interrupt())
+                panic("Fatal exception in interrupt");
+        if (panic_on_oops)
+                panic("Fatal exception: panic_on_oops");
+        oops_exit();
+        do_exit(SIGSEGV);
+}
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 550228523267..4d5e6f8a7978 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -45,6 +45,7 @@ _TIF_TRACE    = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 
 STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
 STACK_SIZE  = 1 << STACK_SHIFT
+STACK_INIT  = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
 
 #define BASED(name) name-system_call(%r13)
 
@@ -97,10 +98,10 @@ STACK_SIZE  = 1 << STACK_SHIFT
         sra     %r14,\shift
         jnz     1f
         CHECK_STACK 1<<\shift,\savearea
+        ahi     %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
         j       2f
 1:      l       %r15,\stack             # load target stack
-2:      ahi     %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-        la      %r11,STACK_FRAME_OVERHEAD(%r15)
+2:      la      %r11,STACK_FRAME_OVERHEAD(%r15)
         .endm
 
         .macro  ADD64 high,low,timer
@@ -150,7 +151,7 @@ ENTRY(__switch_to)
         l       %r4,__THREAD_info(%r2)          # get thread_info of prev
         l       %r5,__THREAD_info(%r3)          # get thread_info of next
         lr      %r15,%r5
-        ahi     %r15,STACK_SIZE                 # end of kernel stack of next
+        ahi     %r15,STACK_INIT                 # end of kernel stack of next
         st      %r3,__LC_CURRENT                # store task struct of next
         st      %r5,__LC_THREAD_INFO            # store thread info of next
         st      %r15,__LC_KERNEL_STACK          # store end of kernel stack
@@ -178,7 +179,6 @@ sysc_stm:
         l       %r13,__LC_SVC_NEW_PSW+4
 sysc_per:
         l       %r15,__LC_KERNEL_STACK
-        ahi     %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
         la      %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs
 sysc_vtime:
         UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER
@@ -188,6 +188,7 @@ sysc_vtime:
         mvc     __PT_INT_CODE(4,%r11),__LC_SVC_ILC
 sysc_do_svc:
         oi      __TI_flags+3(%r12),_TIF_SYSCALL
+        l       %r10,__TI_sysc_table(%r12)      # 31 bit system call table
         lh      %r8,__PT_INT_CODE+2(%r11)
         sla     %r8,2                           # shift and test for svc0
         jnz     sysc_nr_ok
@@ -198,7 +199,6 @@ sysc_do_svc:
         lr      %r8,%r1
         sla     %r8,2
 sysc_nr_ok:
-        l       %r10,BASED(.Lsys_call_table)    # 31 bit system call table
         xc      __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
         st      %r2,__PT_ORIG_GPR2(%r11)
         st      %r7,STACK_FRAME_OVERHEAD(%r15)
@@ -359,11 +359,11 @@ ENTRY(pgm_check_handler)
         tm      __LC_PGM_ILC+3,0x80     # check for per exception
         jnz     pgm_svcper              # -> single stepped svc
 0:      CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
+        ahi     %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
         j       2f
 1:      UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
         l       %r15,__LC_KERNEL_STACK
-2:      ahi     %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-        la      %r11,STACK_FRAME_OVERHEAD(%r15)
+2:      la      %r11,STACK_FRAME_OVERHEAD(%r15)
         stm     %r0,%r7,__PT_R0(%r11)
         mvc     __PT_R8(32,%r11),__LC_SAVE_AREA_SYNC
         stm     %r8,%r9,__PT_PSW(%r11)
@@ -485,7 +485,6 @@ io_work:
 #
 io_work_user:
         l       %r1,__LC_KERNEL_STACK
-        ahi     %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
         mvc     STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
         xc      __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1)
         la      %r11,STACK_FRAME_OVERHEAD(%r1)
@@ -636,7 +635,8 @@ ENTRY(mcck_int_handler)
         UPDATE_VTIME %r14,%r15,__LC_MCCK_ENTER_TIMER
 mcck_skip:
         SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+32,__LC_PANIC_STACK,PAGE_SHIFT
-        mvc     __PT_R0(64,%r11),__LC_GPREGS_SAVE_AREA
+        stm     %r0,%r7,__PT_R0(%r11)
+        mvc     __PT_R8(32,%r11),__LC_GPREGS_SAVE_AREA+32
         stm     %r8,%r9,__PT_PSW(%r11)
         xc      __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
         l       %r1,BASED(.Ldo_machine_check)
@@ -645,7 +645,6 @@ mcck_skip:
         tm      __PT_PSW+1(%r11),0x01   # returning to user ?
         jno     mcck_return
         l       %r1,__LC_KERNEL_STACK   # switch to kernel stack
-        ahi     %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
         mvc     STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
         xc      __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1)
         la      %r11,STACK_FRAME_OVERHEAD(%r15)
@@ -673,6 +672,7 @@ mcck_panic:
         sra     %r14,PAGE_SHIFT
         jz      0f
         l       %r15,__LC_PANIC_STACK
+        j       mcck_skip
 0:      ahi     %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
         j       mcck_skip
 
@@ -713,12 +713,10 @@ ENTRY(restart_int_handler)
  */
 stack_overflow:
         l       %r15,__LC_PANIC_STACK   # change to panic stack
-        ahi     %r15,-__PT_SIZE         # create pt_regs
-        stm     %r0,%r7,__PT_R0(%r15)
-        stm     %r8,%r9,__PT_PSW(%r15)
+        la      %r11,STACK_FRAME_OVERHEAD(%r15)
+        stm     %r0,%r7,__PT_R0(%r11)
+        stm     %r8,%r9,__PT_PSW(%r11)
         mvc     __PT_R8(32,%r11),0(%r14)
-        lr      %r15,%r11
-        ahi     %r15,-STACK_FRAME_OVERHEAD
         l       %r1,BASED(1f)
         xc      __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
         lr      %r2,%r11                # pass pointer to pt_regs
@@ -798,15 +796,14 @@ cleanup_system_call:
         mvc     __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
         # set up saved register 11
         l       %r15,__LC_KERNEL_STACK
-        ahi     %r15,-__PT_SIZE
-        st      %r15,12(%r11)           # r11 pt_regs pointer
+        la      %r9,STACK_FRAME_OVERHEAD(%r15)
+        st      %r9,12(%r11)            # r11 pt_regs pointer
         # fill pt_regs
-        mvc     __PT_R8(32,%r15),__LC_SAVE_AREA_SYNC
-        stm     %r0,%r7,__PT_R0(%r15)
-        mvc     __PT_PSW(8,%r15),__LC_SVC_OLD_PSW
-        mvc     __PT_INT_CODE(4,%r15),__LC_SVC_ILC
+        mvc     __PT_R8(32,%r9),__LC_SAVE_AREA_SYNC
+        stm     %r0,%r7,__PT_R0(%r9)
+        mvc     __PT_PSW(8,%r9),__LC_SVC_OLD_PSW
+        mvc     __PT_INT_CODE(4,%r9),__LC_SVC_ILC
         # setup saved register 15
-        ahi     %r15,-STACK_FRAME_OVERHEAD
         st      %r15,28(%r11)           # r15 stack pointer
         # set new psw address and exit
         l       %r9,BASED(cleanup_table+4)      # sysc_do_svc + 0x80000000
@@ -909,7 +906,6 @@ cleanup_idle_wait:
 .Ltrace_enter:          .long   do_syscall_trace_enter
 .Ltrace_exit:           .long   do_syscall_trace_exit
 .Lschedule_tail:        .long   schedule_tail
-.Lsys_call_table:       .long   sys_call_table
 .Lsysc_per:             .long   sysc_per + 0x80000000
 #ifdef CONFIG_TRACE_IRQFLAGS
 .Lhardirqs_on:          .long   trace_hardirqs_on_caller
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index c3a736a3ed44..aa0ab02e9595 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -7,6 +7,7 @@
 #include <asm/cputime.h>
 
 extern void *restart_stack;
+extern unsigned long suspend_zero_pages;
 
 void system_call(void);
 void pgm_check_handler(void);
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 9c837c101297..4c17eece707e 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -39,6 +39,7 @@ __PT_R15     =	__PT_GPRS + 120
 
 STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
 STACK_SIZE  = 1 << STACK_SHIFT
+STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
 
 _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
                  _TIF_MCCK_PENDING | _TIF_PER_TRAP )
@@ -124,10 +125,10 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
         srag    %r14,%r14,\shift
         jnz     1f
         CHECK_STACK 1<<\shift,\savearea
+        aghi    %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
         j       2f
 1:      lg      %r15,\stack             # load target stack
-2:      aghi    %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-        la      %r11,STACK_FRAME_OVERHEAD(%r15)
+2:      la      %r11,STACK_FRAME_OVERHEAD(%r15)
         .endm
 
         .macro UPDATE_VTIME scratch,enter_timer
@@ -177,7 +178,7 @@ ENTRY(__switch_to)
         lg      %r4,__THREAD_info(%r2)          # get thread_info of prev
         lg      %r5,__THREAD_info(%r3)          # get thread_info of next
         lgr     %r15,%r5
-        aghi    %r15,STACK_SIZE                 # end of kernel stack of next
+        aghi    %r15,STACK_INIT                 # end of kernel stack of next
         stg     %r3,__LC_CURRENT                # store task struct of next
         stg     %r5,__LC_THREAD_INFO            # store thread info of next
         stg     %r15,__LC_KERNEL_STACK          # store end of kernel stack
@@ -203,10 +204,8 @@ sysc_stmg:
         stmg    %r8,%r15,__LC_SAVE_AREA_SYNC
         lg      %r10,__LC_LAST_BREAK
         lg      %r12,__LC_THREAD_INFO
-        larl    %r13,system_call
 sysc_per:
         lg      %r15,__LC_KERNEL_STACK
-        aghi    %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
         la      %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs
 sysc_vtime:
         UPDATE_VTIME %r13,__LC_SYNC_ENTER_TIMER
@@ -217,6 +216,7 @@ sysc_vtime:
         mvc     __PT_INT_CODE(4,%r11),__LC_SVC_ILC
 sysc_do_svc:
         oi      __TI_flags+7(%r12),_TIF_SYSCALL
+        lg      %r10,__TI_sysc_table(%r12)      # address of system call table
         llgh    %r8,__PT_INT_CODE+2(%r11)
         slag    %r8,%r8,2                       # shift and test for svc 0
         jnz     sysc_nr_ok
@@ -227,13 +227,6 @@ sysc_do_svc:
         sth     %r1,__PT_INT_CODE+2(%r11)
         slag    %r8,%r1,2
 sysc_nr_ok:
-        larl    %r10,sys_call_table             # 64 bit system call table
-#ifdef CONFIG_COMPAT
-        tm      __TI_flags+5(%r12),(_TIF_31BIT>>16)
-        jno     sysc_noemu
-        larl    %r10,sys_call_table_emu         # 31 bit system call table
-sysc_noemu:
-#endif
         xc      __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
         stg     %r2,__PT_ORIG_GPR2(%r11)
         stg     %r7,STACK_FRAME_OVERHEAD(%r15)
@@ -389,6 +382,7 @@ ENTRY(pgm_check_handler)
         tm      __LC_PGM_ILC+3,0x80     # check for per exception
         jnz     pgm_svcper              # -> single stepped svc
 0:      CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
+        aghi    %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
         j       2f
 1:      UPDATE_VTIME %r14,__LC_SYNC_ENTER_TIMER
         LAST_BREAK %r14
@@ -398,8 +392,7 @@ ENTRY(pgm_check_handler)
         tm      __LC_PGM_ILC+2,0x02     # check for transaction abort
         jz      2f
         mvc     __THREAD_trap_tdb(256,%r14),0(%r13)
-2:      aghi    %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-        la      %r11,STACK_FRAME_OVERHEAD(%r15)
+2:      la      %r11,STACK_FRAME_OVERHEAD(%r15)
         stmg    %r0,%r7,__PT_R0(%r11)
         mvc     __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
         stmg    %r8,%r9,__PT_PSW(%r11)
@@ -526,7 +519,6 @@ io_work:
 #
 io_work_user:
         lg      %r1,__LC_KERNEL_STACK
-        aghi    %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
         mvc     STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
         xc      __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1)
         la      %r11,STACK_FRAME_OVERHEAD(%r1)
@@ -678,8 +670,9 @@ ENTRY(mcck_int_handler)
         UPDATE_VTIME %r14,__LC_MCCK_ENTER_TIMER
         LAST_BREAK %r14
 mcck_skip:
-        lghi    %r14,__LC_GPREGS_SAVE_AREA
-        mvc     __PT_R0(128,%r11),0(%r14)
+        lghi    %r14,__LC_GPREGS_SAVE_AREA+64
+        stmg    %r0,%r7,__PT_R0(%r11)
+        mvc     __PT_R8(64,%r11),0(%r14)
         stmg    %r8,%r9,__PT_PSW(%r11)
         xc      __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
         lgr     %r2,%r11                # pass pointer to pt_regs
@@ -687,7 +680,6 @@ mcck_skip:
         tm      __PT_PSW+1(%r11),0x01   # returning to user ?
         jno     mcck_return
         lg      %r1,__LC_KERNEL_STACK   # switch to kernel stack
-        aghi    %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
         mvc     STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
         xc      __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1)
         la      %r11,STACK_FRAME_OVERHEAD(%r1)
@@ -754,14 +746,12 @@ ENTRY(restart_int_handler)
  * Setup a pt_regs so that show_trace can provide a good call trace.
  */
 stack_overflow:
-        lg      %r11,__LC_PANIC_STACK   # change to panic stack
-        aghi    %r11,-__PT_SIZE         # create pt_regs
+        lg      %r15,__LC_PANIC_STACK   # change to panic stack
+        la      %r11,STACK_FRAME_OVERHEAD(%r15)
         stmg    %r0,%r7,__PT_R0(%r11)
         stmg    %r8,%r9,__PT_PSW(%r11)
         mvc     __PT_R8(64,%r11),0(%r14)
         stg     %r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2
-        lgr     %r15,%r11
-        aghi    %r15,-STACK_FRAME_OVERHEAD
         xc      __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
         lgr     %r2,%r11                # pass pointer to pt_regs
         jg      kernel_stack_overflow
@@ -845,15 +835,14 @@ cleanup_system_call:
         mvc     __TI_last_break(8,%r12),16(%r11)
 0:      # set up saved register r11
         lg      %r15,__LC_KERNEL_STACK
-        aghi    %r15,-__PT_SIZE
-        stg     %r15,24(%r11)           # r11 pt_regs pointer
+        la      %r9,STACK_FRAME_OVERHEAD(%r15)
+        stg     %r9,24(%r11)            # r11 pt_regs pointer
         # fill pt_regs
-        mvc     __PT_R8(64,%r15),__LC_SAVE_AREA_SYNC
-        stmg    %r0,%r7,__PT_R0(%r15)
-        mvc     __PT_PSW(16,%r15),__LC_SVC_OLD_PSW
-        mvc     __PT_INT_CODE(4,%r15),__LC_SVC_ILC
+        mvc     __PT_R8(64,%r9),__LC_SAVE_AREA_SYNC
+        stmg    %r0,%r7,__PT_R0(%r9)
+        mvc     __PT_PSW(16,%r9),__LC_SVC_OLD_PSW
+        mvc     __PT_INT_CODE(4,%r9),__LC_SVC_ILC
         # setup saved register r15
-        aghi    %r15,-STACK_FRAME_OVERHEAD
         stg     %r15,56(%r11)           # r15 stack pointer
         # set new psw address and exit
         larl    %r9,sysc_do_svc
@@ -1010,6 +999,7 @@ sys_call_table:
 #ifdef CONFIG_COMPAT
 
 #define SYSCALL(esa,esame,emu)  .long emu
+        .globl  sys_call_table_emu
 sys_call_table_emu:
 #include "syscalls.S"
 #undef SYSCALL
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 1630f439cd2a..4f5ef62934a4 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -33,7 +33,7 @@ struct irq_class {
 };
 
 /*
- * The list of "main" irq classes on s390. This is the list of interrrupts
+ * The list of "main" irq classes on s390. This is the list of interrupts
  * that appear both in /proc/stat ("intr" line) and /proc/interrupts.
  * Historically only external and I/O interrupts have been part of /proc/stat.
  * We can't add the split external and I/O sub classes since the first field
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index b3de27700016..ac2178161ec3 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -13,6 +13,7 @@
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
 #include <linux/debug_locks.h>
+#include <linux/suspend.h>
 #include <asm/cio.h>
 #include <asm/setup.h>
 #include <asm/pgtable.h>
@@ -67,6 +68,35 @@ void setup_regs(void)
         memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area));
 }
 
+/*
+ * PM notifier callback for kdump
+ */
+static int machine_kdump_pm_cb(struct notifier_block *nb, unsigned long action,
+                               void *ptr)
+{
+        switch (action) {
+        case PM_SUSPEND_PREPARE:
+        case PM_HIBERNATION_PREPARE:
+                if (crashk_res.start)
+                        crash_map_reserved_pages();
+                break;
+        case PM_POST_SUSPEND:
+        case PM_POST_HIBERNATION:
+                if (crashk_res.start)
+                        crash_unmap_reserved_pages();
+                break;
+        default:
+                return NOTIFY_DONE;
+        }
+        return NOTIFY_OK;
+}
+
+static int __init machine_kdump_pm_init(void)
+{
+        pm_notifier(machine_kdump_pm_cb, 0);
+        return 0;
+}
+arch_initcall(machine_kdump_pm_init);
 #endif
 
 /*
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 536d64579d9a..2bc3eddae34a 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -61,18 +61,8 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
         return sf->gprs[8];
 }
 
-/*
- * The idle loop on a S390...
- */
-static void default_idle(void)
+void arch_cpu_idle(void)
 {
-        if (cpu_is_offline(smp_processor_id()))
-                cpu_die();
-        local_irq_disable();
-        if (need_resched()) {
-                local_irq_enable();
-                return;
-        }
         local_mcck_disable();
         if (test_thread_flag(TIF_MCCK_PENDING)) {
                 local_mcck_enable();
@@ -83,19 +73,15 @@ static void default_idle(void)
         vtime_stop_cpu();
 }
 
-void cpu_idle(void)
+void arch_cpu_idle_exit(void)
 {
-        for (;;) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                while (!need_resched() && !test_thread_flag(TIF_MCCK_PENDING))
-                        default_idle();
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                if (test_thread_flag(TIF_MCCK_PENDING))
-                        s390_handle_mcck();
-                schedule_preempt_disabled();
-        }
+        if (test_thread_flag(TIF_MCCK_PENDING))
+                s390_handle_mcck();
+}
+
+void arch_cpu_idle_dead(void)
+{
+        cpu_die();
 }
 
 extern void __kprobes kernel_thread_starter(void);
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index a5360de85ec7..0f419c5765c8 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -377,11 +377,14 @@ static void __init setup_lowcore(void)
                 PSW_MASK_DAT | PSW_MASK_MCHECK;
         lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler;
         lc->clock_comparator = -1ULL;
-        lc->kernel_stack = ((unsigned long) &init_thread_union) + THREAD_SIZE;
+        lc->kernel_stack = ((unsigned long) &init_thread_union)
+                + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
         lc->async_stack = (unsigned long)
-                __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0) + ASYNC_SIZE;
+                __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0)
+                + ASYNC_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
         lc->panic_stack = (unsigned long)
-                __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + PAGE_SIZE;
+                __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0)
+                + PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
         lc->current_task = (unsigned long) init_thread_union.thread_info.task;
         lc->thread_info = (unsigned long) &init_thread_union;
         lc->machine_flags = S390_lowcore.machine_flags;
@@ -571,6 +574,8 @@ static void __init setup_memory_end(void)
 
         /* Split remaining virtual space between 1:1 mapping & vmemmap array */
         tmp = VMALLOC_START / (PAGE_SIZE + sizeof(struct page));
+        /* vmemmap contains a multiple of PAGES_PER_SECTION struct pages */
+        tmp = SECTION_ALIGN_UP(tmp);
         tmp = VMALLOC_START - tmp * sizeof(struct page);
         tmp &= ~((vmax >> 11) - 1);     /* align to page table level */
         tmp = min(tmp, 1UL << MAX_PHYSMEM_BITS);
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 549c9d173c0f..8074cb4b7cbf 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -181,8 +181,10 @@ static int __cpuinit pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
         lc = pcpu->lowcore;
         memcpy(lc, &S390_lowcore, 512);
         memset((char *) lc + 512, 0, sizeof(*lc) - 512);
-        lc->async_stack = pcpu->async_stack + ASYNC_SIZE;
-        lc->panic_stack = pcpu->panic_stack + PAGE_SIZE;
+        lc->async_stack = pcpu->async_stack + ASYNC_SIZE
+                - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
+        lc->panic_stack = pcpu->panic_stack + PAGE_SIZE
+                - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
         lc->cpu_nr = cpu;
 #ifndef CONFIG_64BIT
         if (MACHINE_HAS_IEEE) {
@@ -253,7 +255,8 @@ static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk)
         struct _lowcore *lc = pcpu->lowcore;
         struct thread_info *ti = task_thread_info(tsk);
 
-        lc->kernel_stack = (unsigned long) task_stack_page(tsk) + THREAD_SIZE;
+        lc->kernel_stack = (unsigned long) task_stack_page(tsk)
+                + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
         lc->thread_info = (unsigned long) task_thread_info(tsk);
         lc->current_task = (unsigned long) tsk;
         lc->user_timer = ti->user_timer;
@@ -711,8 +714,7 @@ static void __cpuinit smp_start_secondary(void *cpuvoid)
         set_cpu_online(smp_processor_id(), true);
         inc_irq_stat(CPU_RST);
         local_irq_enable();
-        /* cpu_idle will call schedule for us */
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 /* Upping and downing of CPUs */
@@ -810,8 +812,10 @@ void __init smp_prepare_boot_cpu(void)
         pcpu->state = CPU_STATE_CONFIGURED;
         pcpu->address = boot_cpu_address;
         pcpu->lowcore = (struct _lowcore *)(unsigned long) store_prefix();
-        pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE;
-        pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE;
+        pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE
+                + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+        pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE
+                + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
         S390_lowcore.percpu_offset = __per_cpu_offset[0];
         smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN);
         set_cpu_present(0, true);
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index aa1494d0e380..c479d2f9605b 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -41,6 +41,7 @@ struct page_key_data {
 static struct page_key_data *page_key_data;
 static struct page_key_data *page_key_rp, *page_key_wp;
 static unsigned long page_key_rx, page_key_wx;
+unsigned long suspend_zero_pages;
 
 /*
  * For each page in the hibernation image one additional byte is
@@ -149,6 +150,36 @@ int pfn_is_nosave(unsigned long pfn)
         return 0;
 }
 
+/*
+ * PM notifier callback for suspend
+ */
+static int suspend_pm_cb(struct notifier_block *nb, unsigned long action,
+                         void *ptr)
+{
+        switch (action) {
+        case PM_SUSPEND_PREPARE:
+        case PM_HIBERNATION_PREPARE:
+                suspend_zero_pages = __get_free_pages(GFP_KERNEL, LC_ORDER);
+                if (!suspend_zero_pages)
+                        return NOTIFY_BAD;
+                break;
+        case PM_POST_SUSPEND:
+        case PM_POST_HIBERNATION:
+                free_pages(suspend_zero_pages, LC_ORDER);
+                break;
+        default:
+                return NOTIFY_DONE;
+        }
+        return NOTIFY_OK;
+}
+
+static int __init suspend_pm_init(void)
+{
+        pm_notifier(suspend_pm_cb, 0);
+        return 0;
+}
+arch_initcall(suspend_pm_init);
+
 void save_processor_state(void)
 {
         /* swsusp_arch_suspend() actually saves all cpu register contents.
diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S
index d4ca4e0617b5..c487be4cfc81 100644
--- a/arch/s390/kernel/swsusp_asm64.S
+++ b/arch/s390/kernel/swsusp_asm64.S
@@ -36,8 +36,8 @@ ENTRY(swsusp_arch_suspend)
         /* Store prefix register on stack */
         stpx    __SF_EMPTY(%r15)
 
-        /* Save prefix register contents for lowcore */
-        llgf    %r4,__SF_EMPTY(%r15)
+        /* Save prefix register contents for lowcore copy */
+        llgf    %r10,__SF_EMPTY(%r15)
 
         /* Get pointer to save area */
         lghi    %r1,0x1000
@@ -91,7 +91,18 @@ ENTRY(swsusp_arch_suspend)
         xc      __SF_EMPTY(4,%r15),__SF_EMPTY(%r15)
         spx     __SF_EMPTY(%r15)
 
+        /* Save absolute zero pages */
+        larl    %r2,suspend_zero_pages
+        lg      %r2,0(%r2)
+        lghi    %r4,0
+        lghi    %r3,2*PAGE_SIZE
+        lghi    %r5,2*PAGE_SIZE
+1:      mvcle   %r2,%r4,0
+        jo      1b
+
+        /* Copy lowcore to absolute zero lowcore */
         lghi    %r2,0
+        lgr     %r4,%r10
         lghi    %r3,2*PAGE_SIZE
         lghi    %r5,2*PAGE_SIZE
 1:      mvcle   %r2,%r4,0
@@ -248,8 +259,20 @@ restore_registers:
         /* Load old stack */
         lg      %r15,0x2f8(%r13)
 
+        /* Save prefix register */
+        mvc __SF_EMPTY(4,%r15),0x318(%r13)
+
+        /* Restore absolute zero pages */
+        lghi    %r2,0
+        larl    %r4,suspend_zero_pages
+        lg      %r4,0(%r4)
+        lghi    %r3,2*PAGE_SIZE
+        lghi    %r5,2*PAGE_SIZE
+1:      mvcle   %r2,%r4,0
+        jo      1b
+
         /* Restore prefix register */
-        spx     0x318(%r13)
+        spx     __SF_EMPTY(%r15)
 
         /* Activate DAT */
         stosm   __SF_EMPTY(%r15),0x04
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 13dd63fba367..c5762324d9ee 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -12,49 +12,16 @@
  * 'Traps.c' handles hardware traps and faults after we have saved some
  * state in 'asm.s'.
  */
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/module.h>
 #include <linux/ptrace.h>
-#include <linux/timer.h>
+#include <linux/sched.h>
 #include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/seq_file.h>
-#include <linux/delay.h>
-#include <linux/module.h>
-#include <linux/kdebug.h>
-#include <linux/kallsyms.h>
-#include <linux/reboot.h>
-#include <linux/kprobes.h>
-#include <linux/bug.h>
-#include <linux/utsname.h>
-#include <asm/uaccess.h>
-#include <asm/io.h>
-#include <linux/atomic.h>
-#include <asm/mathemu.h>
-#include <asm/cpcmd.h>
-#include <asm/lowcore.h>
-#include <asm/debug.h>
-#include <asm/ipl.h>
 #include "entry.h"
 
 int show_unhandled_signals = 1;
 
-#define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; })
-
-#ifndef CONFIG_64BIT
-#define LONG "%08lx "
-#define FOURLONG "%08lx %08lx %08lx %08lx\n"
-static int kstack_depth_to_print = 12;
-#else /* CONFIG_64BIT */
-#define LONG "%016lx "
-#define FOURLONG "%016lx %016lx %016lx %016lx\n"
-static int kstack_depth_to_print = 20;
-#endif /* CONFIG_64BIT */
-
 static inline void __user *get_trap_ip(struct pt_regs *regs)
 {
 #ifdef CONFIG_64BIT
@@ -72,215 +39,6 @@ static inline void __user *get_trap_ip(struct pt_regs *regs)
 #endif
 }
 
-/*
- * For show_trace we have tree different stack to consider:
- *   - the panic stack which is used if the kernel stack has overflown
- *   - the asynchronous interrupt stack (cpu related)
- *   - the synchronous kernel stack (process related)
- * The stack trace can start at any of the three stack and can potentially
- * touch all of them. The order is: panic stack, async stack, sync stack.
- */
-static unsigned long
-__show_trace(unsigned long sp, unsigned long low, unsigned long high)
-{
-        struct stack_frame *sf;
-        struct pt_regs *regs;
-
-        while (1) {
-                sp = sp & PSW_ADDR_INSN;
-                if (sp < low || sp > high - sizeof(*sf))
-                        return sp;
-                sf = (struct stack_frame *) sp;
-                printk("([<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN);
-                print_symbol("%s)\n", sf->gprs[8] & PSW_ADDR_INSN);
-                /* Follow the backchain. */
-                while (1) {
-                        low = sp;
-                        sp = sf->back_chain & PSW_ADDR_INSN;
-                        if (!sp)
-                                break;
-                        if (sp <= low || sp > high - sizeof(*sf))
-                                return sp;
-                        sf = (struct stack_frame *) sp;
-                        printk(" [<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN);
-                        print_symbol("%s\n", sf->gprs[8] & PSW_ADDR_INSN);
-                }
-                /* Zero backchain detected, check for interrupt frame. */
-                sp = (unsigned long) (sf + 1);
-                if (sp <= low || sp > high - sizeof(*regs))
-                        return sp;
-                regs = (struct pt_regs *) sp;
-                printk(" [<%016lx>] ", regs->psw.addr & PSW_ADDR_INSN);
-                print_symbol("%s\n", regs->psw.addr & PSW_ADDR_INSN);
-                low = sp;
-                sp = regs->gprs[15];
-        }
-}
-
-static void show_trace(struct task_struct *task, unsigned long *stack)
-{
-        register unsigned long __r15 asm ("15");
-        unsigned long sp;
-
-        sp = (unsigned long) stack;
-        if (!sp)
-                sp = task ? task->thread.ksp : __r15;
-        printk("Call Trace:\n");
-#ifdef CONFIG_CHECK_STACK
-        sp = __show_trace(sp, S390_lowcore.panic_stack - 4096,
-                          S390_lowcore.panic_stack);
-#endif
-        sp = __show_trace(sp, S390_lowcore.async_stack - ASYNC_SIZE,
-                          S390_lowcore.async_stack);
-        if (task)
-                __show_trace(sp, (unsigned long) task_stack_page(task),
-                             (unsigned long) task_stack_page(task) + THREAD_SIZE);
-        else
-                __show_trace(sp, S390_lowcore.thread_info,
-                             S390_lowcore.thread_info + THREAD_SIZE);
-        if (!task)
-                task = current;
-        debug_show_held_locks(task);
-}
-
-void show_stack(struct task_struct *task, unsigned long *sp)
-{
-        register unsigned long * __r15 asm ("15");
-        unsigned long *stack;
-        int i;
-
-        if (!sp)
-                stack = task ? (unsigned long *) task->thread.ksp : __r15;
-        else
-                stack = sp;
-
-        for (i = 0; i < kstack_depth_to_print; i++) {
-                if (((addr_t) stack & (THREAD_SIZE-1)) == 0)
-                        break;
-                if ((i * sizeof(long) % 32) == 0)
-                        printk("%s       ", i == 0 ? "" : "\n");
-                printk(LONG, *stack++);
-        }
-        printk("\n");
-        show_trace(task, sp);
-}
-
-static void show_last_breaking_event(struct pt_regs *regs)
-{
-#ifdef CONFIG_64BIT
-        printk("Last Breaking-Event-Address:\n");
-        printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN);
-        print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN);
-#endif
-}
-
-/*
- * The architecture-independent dump_stack generator
- */
-void dump_stack(void)
-{
-        printk("CPU: %d %s %s %.*s\n",
-               task_thread_info(current)->cpu, print_tainted(),
-               init_utsname()->release,
-               (int)strcspn(init_utsname()->version, " "),
-               init_utsname()->version);
-        printk("Process %s (pid: %d, task: %p, ksp: %p)\n",
-               current->comm, current->pid, current,
-               (void *) current->thread.ksp);
-        show_stack(NULL, NULL);
-}
-EXPORT_SYMBOL(dump_stack);
-
-static inline int mask_bits(struct pt_regs *regs, unsigned long bits)
-{
-        return (regs->psw.mask & bits) / ((~bits + 1) & bits);
-}
-
-void show_registers(struct pt_regs *regs)
-{
-        char *mode;
-
-        mode = user_mode(regs) ? "User" : "Krnl";
-        printk("%s PSW : %p %p",
-               mode, (void *) regs->psw.mask,
-               (void *) regs->psw.addr);
-        print_symbol(" (%s)\n", regs->psw.addr & PSW_ADDR_INSN);
-        printk("           R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
-               "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER),
-               mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO),
-               mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY),
-               mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT),
-               mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC),
-               mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM));
-#ifdef CONFIG_64BIT
-        printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA));
-#endif
-        printk("\n%s GPRS: " FOURLONG, mode,
-               regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]);
-        printk("           " FOURLONG,
-               regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]);
-        printk("           " FOURLONG,
-               regs->gprs[8], regs->gprs[9], regs->gprs[10], regs->gprs[11]);
-        printk("           " FOURLONG,
-               regs->gprs[12], regs->gprs[13], regs->gprs[14], regs->gprs[15]);
-
-        show_code(regs);
-}       
-
-void show_regs(struct pt_regs *regs)
-{
-        printk("CPU: %d %s %s %.*s\n",
-               task_thread_info(current)->cpu, print_tainted(),
-               init_utsname()->release,
-               (int)strcspn(init_utsname()->version, " "),
-               init_utsname()->version);
-        printk("Process %s (pid: %d, task: %p, ksp: %p)\n",
-               current->comm, current->pid, current,
-               (void *) current->thread.ksp);
-        show_registers(regs);
-        /* Show stack backtrace if pt_regs is from kernel mode */
-        if (!user_mode(regs))
-                show_trace(NULL, (unsigned long *) regs->gprs[15]);
-        show_last_breaking_event(regs);
-}
-
-static DEFINE_SPINLOCK(die_lock);
-
-void die(struct pt_regs *regs, const char *str)
-{
-        static int die_counter;
-
-        oops_enter();
-        lgr_info_log();
-        debug_stop_all();
-        console_verbose();
-        spin_lock_irq(&die_lock);
-        bust_spinlocks(1);
-        printk("%s: %04x [#%d] ", str, regs->int_code & 0xffff, ++die_counter);
-#ifdef CONFIG_PREEMPT
-        printk("PREEMPT ");
-#endif
-#ifdef CONFIG_SMP
-        printk("SMP ");
-#endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-        printk("DEBUG_PAGEALLOC");
-#endif
-        printk("\n");
-        notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV);
-        print_modules();
-        show_regs(regs);
-        bust_spinlocks(0);
-        add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
-        spin_unlock_irq(&die_lock);
-        if (in_interrupt())
-                panic("Fatal exception in interrupt");
-        if (panic_on_oops)
-                panic("Fatal exception: panic_on_oops");
-        oops_exit();
-        do_exit(SIGSEGV);
-}
-
 static inline void report_user_fault(struct pt_regs *regs, int signr)
 {
         if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index a0042acbd989..3fb09359eda6 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -158,8 +158,6 @@ void __kprobes vtime_stop_cpu(void)
         unsigned long psw_mask;
 
         trace_hardirqs_on();
-        /* Don't trace preempt off for idle. */
-        stop_critical_timings();
 
         /* Wait for external, I/O or machine check interrupt. */
         psw_mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_DAT |
@@ -169,9 +167,6 @@ void __kprobes vtime_stop_cpu(void)
         /* Call the assembler magic in entry.S */
         psw_idle(idle, psw_mask);
 
-        /* Reenable preemption tracer. */
-        start_critical_timings();
-
         /* Account time spent with enabled wait psw loaded as idle time. */
         idle->sequence++;
         smp_wmb();
diff --git a/arch/s390/kvm/trace.h b/arch/s390/kvm/trace.h
index 2b29e62351d3..c2f582bb1cb2 100644
--- a/arch/s390/kvm/trace.h
+++ b/arch/s390/kvm/trace.h
@@ -67,7 +67,7 @@ TRACE_EVENT(kvm_s390_sie_fault,
 #define sie_intercept_code                              \
         {0x04, "Instruction"},                          \
         {0x08, "Program interruption"},                 \
-        {0x0C, "Instruction and program interuption"},  \
+        {0x0C, "Instruction and program interruption"}, \
         {0x10, "External request"},                     \
         {0x14, "External interruption"},                \
         {0x18, "I/O request"},                          \
@@ -117,7 +117,7 @@ TRACE_EVENT(kvm_s390_intercept_instruction,
                            __entry->instruction,
                            insn_to_mnemonic((unsigned char *)
                                             &__entry->instruction,
-                                         __entry->insn) ?
+                                         __entry->insn, sizeof(__entry->insn)) ?
                            "unknown" : __entry->insn)
         );
 
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index dff631d34b45..466fb3383960 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -77,42 +77,69 @@ static size_t copy_in_kernel(size_t count, void __user *to,
  * >= -4095 (IS_ERR_VALUE(x) returns true), a fault has occured and the address
  * contains the (negative) exception code.
  */
-static __always_inline unsigned long follow_table(struct mm_struct *mm,
-                                                  unsigned long addr, int write)
+#ifdef CONFIG_64BIT
+static unsigned long follow_table(struct mm_struct *mm,
+                                  unsigned long address, int write)
 {
-        pgd_t *pgd;
-        pud_t *pud;
-        pmd_t *pmd;
-        pte_t *ptep;
+        unsigned long *table = (unsigned long *)__pa(mm->pgd);
+
+        switch (mm->context.asce_bits & _ASCE_TYPE_MASK) {
+        case _ASCE_TYPE_REGION1:
+                table = table + ((address >> 53) & 0x7ff);
+                if (unlikely(*table & _REGION_ENTRY_INV))
+                        return -0x39UL;
+                table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+        case _ASCE_TYPE_REGION2:
+                table = table + ((address >> 42) & 0x7ff);
+                if (unlikely(*table & _REGION_ENTRY_INV))
+                        return -0x3aUL;
+                table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+        case _ASCE_TYPE_REGION3:
+                table = table + ((address >> 31) & 0x7ff);
+                if (unlikely(*table & _REGION_ENTRY_INV))
+                        return -0x3bUL;
+                table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+        case _ASCE_TYPE_SEGMENT:
+                table = table + ((address >> 20) & 0x7ff);
+                if (unlikely(*table & _SEGMENT_ENTRY_INV))
+                        return -0x10UL;
+                if (unlikely(*table & _SEGMENT_ENTRY_LARGE)) {
+                        if (write && (*table & _SEGMENT_ENTRY_RO))
+                                return -0x04UL;
+                        return (*table & _SEGMENT_ENTRY_ORIGIN_LARGE) +
+                                (address & ~_SEGMENT_ENTRY_ORIGIN_LARGE);
+                }
+                table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
+        }
+        table = table + ((address >> 12) & 0xff);
+        if (unlikely(*table & _PAGE_INVALID))
+                return -0x11UL;
+        if (write && (*table & _PAGE_RO))
+                return -0x04UL;
+        return (*table & PAGE_MASK) + (address & ~PAGE_MASK);
+}
 
-        pgd = pgd_offset(mm, addr);
-        if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
-                return -0x3aUL;
+#else /* CONFIG_64BIT */
 
-        pud = pud_offset(pgd, addr);
-        if (pud_none(*pud) || unlikely(pud_bad(*pud)))
-                return -0x3bUL;
+static unsigned long follow_table(struct mm_struct *mm,
+                                  unsigned long address, int write)
+{
+        unsigned long *table = (unsigned long *)__pa(mm->pgd);
 
-        pmd = pmd_offset(pud, addr);
-        if (pmd_none(*pmd))
+        table = table + ((address >> 20) & 0x7ff);
+        if (unlikely(*table & _SEGMENT_ENTRY_INV))
                 return -0x10UL;
-        if (pmd_large(*pmd)) {
-                if (write && (pmd_val(*pmd) & _SEGMENT_ENTRY_RO))
-                        return -0x04UL;
-                return (pmd_val(*pmd) & HPAGE_MASK) + (addr & ~HPAGE_MASK);
-        }
-        if (unlikely(pmd_bad(*pmd)))
-                return -0x10UL;
-
-        ptep = pte_offset_map(pmd, addr);
-        if (!pte_present(*ptep))
+        table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
+        table = table + ((address >> 12) & 0xff);
+        if (unlikely(*table & _PAGE_INVALID))
                 return -0x11UL;
-        if (write && (!pte_write(*ptep) || !pte_dirty(*ptep)))
+        if (write && (*table & _PAGE_RO))
                 return -0x04UL;
-
-        return (pte_val(*ptep) & PAGE_MASK) + (addr & ~PAGE_MASK);
+        return (*table & PAGE_MASK) + (address & ~PAGE_MASK);
 }
 
+#endif /* CONFIG_64BIT */
+
 static __always_inline size_t __user_copy_pt(unsigned long uaddr, void *kptr,
                                              size_t n, int write_user)
 {
@@ -197,7 +224,7 @@ size_t copy_to_user_pt(size_t n, void __user *to, const void *from)
 
 static size_t clear_user_pt(size_t n, void __user *to)
 {
-        void *zpage = &empty_zero_page;
+        void *zpage = (void *) empty_zero_page;
         long done, size, ret;
 
         done = 0;
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 479e94282910..9d84a1feefef 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -458,12 +458,10 @@ static int __init cmm_init(void)
         if (rc)
                 goto out_pm;
         cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread");
-        rc = IS_ERR(cmm_thread_ptr) ? PTR_ERR(cmm_thread_ptr) : 0;
-        if (rc)
-                goto out_kthread;
-        return 0;
+        if (!IS_ERR(cmm_thread_ptr))
+                return 0;
 
-out_kthread:
+        rc = PTR_ERR(cmm_thread_ptr);
         unregister_pm_notifier(&cmm_power_notifier);
 out_pm:
         unregister_oom_notifier(&cmm_oom_nb);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 2fb9e63b8fc4..047c3e4c59a2 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -395,8 +395,13 @@ void __kprobes do_protection_exception(struct pt_regs *regs)
         int fault;
 
         trans_exc_code = regs->int_parm_long;
-        /* Protection exception is suppressing, decrement psw address. */
-        regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16);
+        /*
+         * Protection exceptions are suppressing, decrement psw address.
+         * The exception to this rule are aborted transactions, for these
+         * the PSW already points to the correct location.
+         */
+        if (!(regs->int_code & 0x200))
+                regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16);
         /*
          * Check for low-address protection.  This needs to be treated
          * as a special case because the translation exception code
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 532525ec88c1..121089d57802 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -39,7 +39,7 @@ int arch_prepare_hugepage(struct page *page)
         if (!ptep)
                 return -ENOMEM;
 
-        pte = mk_pte(page, PAGE_RW);
+        pte_val(pte) = addr;
         for (i = 0; i < PTRS_PER_PTE; i++) {
                 set_pte_at(&init_mm, addr + i * PAGE_SIZE, ptep + i, pte);
                 pte_val(pte) += PAGE_SIZE;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 49ce6bb2c641..0b09b2342302 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -42,11 +42,10 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE)));
 unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL(empty_zero_page);
 
-static unsigned long __init setup_zero_pages(void)
+static void __init setup_zero_pages(void)
 {
         struct cpuid cpu_id;
         unsigned int order;
-        unsigned long size;
         struct page *page;
         int i;
 
@@ -63,10 +62,18 @@ static unsigned long __init setup_zero_pages(void)
                 break;
         case 0x2097:    /* z10 */
         case 0x2098:    /* z10 */
-        default:
+        case 0x2817:    /* z196 */
+        case 0x2818:    /* z196 */
                 order = 2;
                 break;
+        case 0x2827:    /* zEC12 */
+        default:
+                order = 5;
+                break;
         }
+        /* Limit number of empty zero pages for small memory sizes */
+        if (order > 2 && totalram_pages <= 16384)
+                order = 2;
 
         empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
         if (!empty_zero_page)
@@ -75,14 +82,11 @@ static unsigned long __init setup_zero_pages(void)
         page = virt_to_page((void *) empty_zero_page);
         split_page(page, order);
         for (i = 1 << order; i > 0; i--) {
-                SetPageReserved(page);
+                mark_page_reserved(page);
                 page++;
         }
 
-        size = PAGE_SIZE << order;
-        zero_page_mask = (size - 1) & PAGE_MASK;
-
-        return 1UL << order;
+        zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK;
 }
 
 /*
@@ -139,7 +143,7 @@ void __init mem_init(void)
 
         /* this will put all low memory onto the freelists */
         totalram_pages += free_all_bootmem();
-        totalram_pages -= setup_zero_pages();   /* Setup zeroed pages. */
+        setup_zero_pages();     /* Setup zeroed pages. */
 
         reservedpages = 0;
 
@@ -158,34 +162,15 @@ void __init mem_init(void)
                PFN_ALIGN((unsigned long)&_eshared) - 1);
 }
 
-void free_init_pages(char *what, unsigned long begin, unsigned long end)
-{
-        unsigned long addr = begin;
-
-        if (begin >= end)
-                return;
-        for (; addr < end; addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                memset((void *)(addr & PAGE_MASK), POISON_FREE_INITMEM,
-                       PAGE_SIZE);
-                free_page(addr);
-                totalram_pages++;
-        }
-        printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
-}
-
 void free_initmem(void)
 {
-        free_init_pages("unused kernel memory",
-                        (unsigned long)&__init_begin,
-                        (unsigned long)&__init_end);
+        free_initmem_default(0);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-        free_init_pages("initrd memory", start, end);
+        free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd");
 }
 #endif
 
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index d21040ed5e59..80adfbf75065 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -9,31 +9,25 @@
 #include <asm/pgtable.h>
 #include <asm/page.h>
 
+static inline unsigned long sske_frame(unsigned long addr, unsigned char skey)
+{
+        asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],9,0"
+                     : [addr] "+a" (addr) : [skey] "d" (skey));
+        return addr;
+}
+
 void storage_key_init_range(unsigned long start, unsigned long end)
 {
-        unsigned long boundary, function, size;
+        unsigned long boundary, size;
 
         while (start < end) {
-                if (MACHINE_HAS_EDAT2) {
-                        /* set storage keys for a 2GB frame */
-                        function = 0x22000 | PAGE_DEFAULT_KEY;
-                        size = 1UL << 31;
-                        boundary = (start + size) & ~(size - 1);
-                        if (boundary <= end) {
-                                do {
-                                        start = pfmf(function, start);
-                                } while (start < boundary);
-                                continue;
-                        }
-                }
                 if (MACHINE_HAS_EDAT1) {
                         /* set storage keys for a 1MB frame */
-                        function = 0x21000 | PAGE_DEFAULT_KEY;
                         size = 1UL << 20;
                         boundary = (start + size) & ~(size - 1);
                         if (boundary <= end) {
                                 do {
-                                        start = pfmf(function, start);
+                                        start = sske_frame(start, PAGE_DEFAULT_KEY);
                                 } while (start < boundary);
                                 continue;
                         }
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index ae44d2a34313..bd954e96f51c 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -379,75 +379,183 @@ out_unmap:
 }
 EXPORT_SYMBOL_GPL(gmap_map_segment);
 
-/*
- * this function is assumed to be called with mmap_sem held
- */
-unsigned long __gmap_fault(unsigned long address, struct gmap *gmap)
+static unsigned long *gmap_table_walk(unsigned long address, struct gmap *gmap)
 {
-        unsigned long *table, vmaddr, segment;
-        struct mm_struct *mm;
-        struct gmap_pgtable *mp;
-        struct gmap_rmap *rmap;
-        struct vm_area_struct *vma;
-        struct page *page;
-        pgd_t *pgd;
-        pud_t *pud;
-        pmd_t *pmd;
+        unsigned long *table;
 
-        current->thread.gmap_addr = address;
-        mm = gmap->mm;
-        /* Walk the gmap address space page table */
         table = gmap->table + ((address >> 53) & 0x7ff);
         if (unlikely(*table & _REGION_ENTRY_INV))
-                return -EFAULT;
+                return ERR_PTR(-EFAULT);
         table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
         table = table + ((address >> 42) & 0x7ff);
         if (unlikely(*table & _REGION_ENTRY_INV))
-                return -EFAULT;
+                return ERR_PTR(-EFAULT);
         table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
         table = table + ((address >> 31) & 0x7ff);
         if (unlikely(*table & _REGION_ENTRY_INV))
-                return -EFAULT;
+                return ERR_PTR(-EFAULT);
         table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
         table = table + ((address >> 20) & 0x7ff);
+        return table;
+}
+
+/**
+ * __gmap_translate - translate a guest address to a user space address
+ * @address: guest address
+ * @gmap: pointer to guest mapping meta data structure
+ *
+ * Returns user space address which corresponds to the guest address or
+ * -EFAULT if no such mapping exists.
+ * This function does not establish potentially missing page table entries.
+ * The mmap_sem of the mm that belongs to the address space must be held
+ * when this function gets called.
+ */
+unsigned long __gmap_translate(unsigned long address, struct gmap *gmap)
+{
+        unsigned long *segment_ptr, vmaddr, segment;
+        struct gmap_pgtable *mp;
+        struct page *page;
 
+        current->thread.gmap_addr = address;
+        segment_ptr = gmap_table_walk(address, gmap);
+        if (IS_ERR(segment_ptr))
+                return PTR_ERR(segment_ptr);
         /* Convert the gmap address to an mm address. */
-        segment = *table;
-        if (likely(!(segment & _SEGMENT_ENTRY_INV))) {
+        segment = *segment_ptr;
+        if (!(segment & _SEGMENT_ENTRY_INV)) {
                 page = pfn_to_page(segment >> PAGE_SHIFT);
                 mp = (struct gmap_pgtable *) page->index;
                 return mp->vmaddr | (address & ~PMD_MASK);
         } else if (segment & _SEGMENT_ENTRY_RO) {
                 vmaddr = segment & _SEGMENT_ENTRY_ORIGIN;
-                vma = find_vma(mm, vmaddr);
-                if (!vma || vma->vm_start > vmaddr)
-                        return -EFAULT;
-
-                /* Walk the parent mm page table */
-                pgd = pgd_offset(mm, vmaddr);
-                pud = pud_alloc(mm, pgd, vmaddr);
-                if (!pud)
-                        return -ENOMEM;
-                pmd = pmd_alloc(mm, pud, vmaddr);
-                if (!pmd)
-                        return -ENOMEM;
-                if (!pmd_present(*pmd) &&
-                    __pte_alloc(mm, vma, pmd, vmaddr))
-                        return -ENOMEM;
-                /* pmd now points to a valid segment table entry. */
-                rmap = kmalloc(sizeof(*rmap), GFP_KERNEL|__GFP_REPEAT);
-                if (!rmap)
-                        return -ENOMEM;
-                /* Link gmap segment table entry location to page table. */
-                page = pmd_page(*pmd);
-                mp = (struct gmap_pgtable *) page->index;
-                rmap->entry = table;
-                spin_lock(&mm->page_table_lock);
+                return vmaddr | (address & ~PMD_MASK);
+        }
+        return -EFAULT;
+}
+EXPORT_SYMBOL_GPL(__gmap_translate);
+
+/**
+ * gmap_translate - translate a guest address to a user space address
+ * @address: guest address
+ * @gmap: pointer to guest mapping meta data structure
+ *
+ * Returns user space address which corresponds to the guest address or
+ * -EFAULT if no such mapping exists.
+ * This function does not establish potentially missing page table entries.
+ */
+unsigned long gmap_translate(unsigned long address, struct gmap *gmap)
+{
+        unsigned long rc;
+
+        down_read(&gmap->mm->mmap_sem);
+        rc = __gmap_translate(address, gmap);
+        up_read(&gmap->mm->mmap_sem);
+        return rc;
+}
+EXPORT_SYMBOL_GPL(gmap_translate);
+
+static int gmap_connect_pgtable(unsigned long segment,
+                                unsigned long *segment_ptr,
+                                struct gmap *gmap)
+{
+        unsigned long vmaddr;
+        struct vm_area_struct *vma;
+        struct gmap_pgtable *mp;
+        struct gmap_rmap *rmap;
+        struct mm_struct *mm;
+        struct page *page;
+        pgd_t *pgd;
+        pud_t *pud;
+        pmd_t *pmd;
+
+        mm = gmap->mm;
+        vmaddr = segment & _SEGMENT_ENTRY_ORIGIN;
+        vma = find_vma(mm, vmaddr);
+        if (!vma || vma->vm_start > vmaddr)
+                return -EFAULT;
+        /* Walk the parent mm page table */
+        pgd = pgd_offset(mm, vmaddr);
+        pud = pud_alloc(mm, pgd, vmaddr);
+        if (!pud)
+                return -ENOMEM;
+        pmd = pmd_alloc(mm, pud, vmaddr);
+        if (!pmd)
+                return -ENOMEM;
+        if (!pmd_present(*pmd) &&
+            __pte_alloc(mm, vma, pmd, vmaddr))
+                return -ENOMEM;
+        /* pmd now points to a valid segment table entry. */
+        rmap = kmalloc(sizeof(*rmap), GFP_KERNEL|__GFP_REPEAT);
+        if (!rmap)
+                return -ENOMEM;
+        /* Link gmap segment table entry location to page table. */
+        page = pmd_page(*pmd);
+        mp = (struct gmap_pgtable *) page->index;
+        rmap->entry = segment_ptr;
+        spin_lock(&mm->page_table_lock);
+        if (*segment_ptr == segment) {
                 list_add(&rmap->list, &mp->mapper);
-                spin_unlock(&mm->page_table_lock);
                 /* Set gmap segment table entry to page table. */
-                *table = pmd_val(*pmd) & PAGE_MASK;
-                return vmaddr | (address & ~PMD_MASK);
+                *segment_ptr = pmd_val(*pmd) & PAGE_MASK;
+                rmap = NULL;
+        }
+        spin_unlock(&mm->page_table_lock);
+        kfree(rmap);
+        return 0;
+}
+
+static void gmap_disconnect_pgtable(struct mm_struct *mm, unsigned long *table)
+{
+        struct gmap_rmap *rmap, *next;
+        struct gmap_pgtable *mp;
+        struct page *page;
+        int flush;
+
+        flush = 0;
+        spin_lock(&mm->page_table_lock);
+        page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+        mp = (struct gmap_pgtable *) page->index;
+        list_for_each_entry_safe(rmap, next, &mp->mapper, list) {
+                *rmap->entry =
+                        _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr;
+                list_del(&rmap->list);
+                kfree(rmap);
+                flush = 1;
+        }
+        spin_unlock(&mm->page_table_lock);
+        if (flush)
+                __tlb_flush_global();
+}
+
+/*
+ * this function is assumed to be called with mmap_sem held
+ */
+unsigned long __gmap_fault(unsigned long address, struct gmap *gmap)
+{
+        unsigned long *segment_ptr, segment;
+        struct gmap_pgtable *mp;
+        struct page *page;
+        int rc;
+
+        current->thread.gmap_addr = address;
+        segment_ptr = gmap_table_walk(address, gmap);
+        if (IS_ERR(segment_ptr))
+                return -EFAULT;
+        /* Convert the gmap address to an mm address. */
+        while (1) {
+                segment = *segment_ptr;
+                if (!(segment & _SEGMENT_ENTRY_INV)) {
+                        /* Page table is present */
+                        page = pfn_to_page(segment >> PAGE_SHIFT);
+                        mp = (struct gmap_pgtable *) page->index;
+                        return mp->vmaddr | (address & ~PMD_MASK);
+                }
+                if (!(segment & _SEGMENT_ENTRY_RO))
+                        /* Nothing mapped in the gmap address space. */
+                        break;
+                rc = gmap_connect_pgtable(segment, segment_ptr, gmap);
+                if (rc)
+                        return rc;
         }
         return -EFAULT;
 }
@@ -511,29 +619,6 @@ void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap)
 }
 EXPORT_SYMBOL_GPL(gmap_discard);
 
-void gmap_unmap_notifier(struct mm_struct *mm, unsigned long *table)
-{
-        struct gmap_rmap *rmap, *next;
-        struct gmap_pgtable *mp;
-        struct page *page;
-        int flush;
-
-        flush = 0;
-        spin_lock(&mm->page_table_lock);
-        page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-        mp = (struct gmap_pgtable *) page->index;
-        list_for_each_entry_safe(rmap, next, &mp->mapper, list) {
-                *rmap->entry =
-                        _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr;
-                list_del(&rmap->list);
-                kfree(rmap);
-                flush = 1;
-        }
-        spin_unlock(&mm->page_table_lock);
-        if (flush)
-                __tlb_flush_global();
-}
-
 static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm,
                                                     unsigned long vmaddr)
 {
@@ -586,8 +671,8 @@ static inline void page_table_free_pgste(unsigned long *table)
 {
 }
 
-static inline void gmap_unmap_notifier(struct mm_struct *mm,
-                                          unsigned long *table)
+static inline void gmap_disconnect_pgtable(struct mm_struct *mm,
+                                           unsigned long *table)
 {
 }
 
@@ -653,7 +738,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
         unsigned int bit, mask;
 
         if (mm_has_pgste(mm)) {
-                gmap_unmap_notifier(mm, table);
+                gmap_disconnect_pgtable(mm, table);
                 return page_table_free_pgste(table);
         }
         /* Free 1K/2K page table fragment of a 4K page */
@@ -696,7 +781,7 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table)
 
         mm = tlb->mm;
         if (mm_has_pgste(mm)) {
-                gmap_unmap_notifier(mm, table);
+                gmap_disconnect_pgtable(mm, table);
                 table = (unsigned long *) (__pa(table) | FRAG_MASK);
                 tlb_remove_table(tlb, table);
                 return;
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index ffab84db6907..35837054f734 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -191,19 +191,16 @@ static void vmem_remove_range(unsigned long start, unsigned long size)
 /*
  * Add a backed mem_map array to the virtual mem_map array.
  */
-int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 {
-        unsigned long address, start_addr, end_addr;
+        unsigned long address = start;
         pgd_t *pg_dir;
         pud_t *pu_dir;
         pmd_t *pm_dir;
         pte_t *pt_dir;
         int ret = -ENOMEM;
 
-        start_addr = (unsigned long) start;
-        end_addr = (unsigned long) (start + nr);
-
-        for (address = start_addr; address < end_addr;) {
+        for (address = start; address < end;) {
                 pg_dir = pgd_offset_k(address);
                 if (pgd_none(*pg_dir)) {
                         pu_dir = vmem_pud_alloc();
@@ -262,14 +259,14 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
                 }
                 address += PAGE_SIZE;
         }
-        memset(start, 0, nr * sizeof(struct page));
+        memset((void *)start, 0, end - start);
         ret = 0;
 out:
-        flush_tlb_kernel_range(start_addr, end_addr);
+        flush_tlb_kernel_range(start, end);
         return ret;
 }
 
-void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+void vmemmap_free(unsigned long start, unsigned long end)
 {
 }
 
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 0972e91cced2..82f165f8078c 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -747,10 +747,9 @@ void bpf_jit_compile(struct sk_filter *fp)
 
         if (!bpf_jit_enable)
                 return;
-        addrs = kmalloc(fp->len * sizeof(*addrs), GFP_KERNEL);
+        addrs = kcalloc(fp->len, sizeof(*addrs), GFP_KERNEL);
         if (addrs == NULL)
                 return;
-        memset(addrs, 0, fp->len * sizeof(*addrs));
         memset(&jit, 0, sizeof(cjit));
         memset(&cjit, 0, sizeof(cjit));
 
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 584b93674ea4..ffeb17ce7f31 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -440,6 +440,7 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops)
                 switch (id.machine) {
                 case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
                 case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
+                case 0x2827:              ops->cpu_type = "s390/zEC12"; break;
                 default: return -ENODEV;
                 }
         }
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index f0f426a113ce..086a2e37935d 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -2,5 +2,5 @@
 # Makefile for the s390 PCI subsystem.
 #
 
-obj-$(CONFIG_PCI)       += pci.o pci_dma.o pci_clp.o pci_msi.o \
-                           pci_sysfs.o pci_event.o pci_debug.o
+obj-$(CONFIG_PCI)       += pci.o pci_dma.o pci_clp.o pci_msi.o pci_sysfs.o \
+                           pci_event.o pci_debug.o pci_insn.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 27b4c17855b9..e6f15b5d8b7d 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -99,9 +99,6 @@ static int __read_mostly aisb_max;
 static struct kmem_cache *zdev_irq_cache;
 static struct kmem_cache *zdev_fmb_cache;
 
-debug_info_t *pci_debug_msg_id;
-debug_info_t *pci_debug_err_id;
-
 static inline int irq_to_msi_nr(unsigned int irq)
 {
         return irq & ZPCI_MSI_MASK;
@@ -179,7 +176,7 @@ static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb,
         fib->aisb = (u64) bucket->aisb + aisb / 8;
         fib->aisbo = aisb & ZPCI_MSI_MASK;
 
-        rc = mpcifc_instr(req, fib);
+        rc = s390pci_mod_fc(req, fib);
         pr_debug("%s mpcifc returned noi: %d\n", __func__, fib->noi);
 
         free_page((unsigned long) fib);
@@ -209,7 +206,7 @@ static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args
         fib->iota = args->iota;
         fib->fmb_addr = args->fmb_addr;
 
-        rc = mpcifc_instr(req, fib);
+        rc = s390pci_mod_fc(req, fib);
         free_page((unsigned long) fib);
         return rc;
 }
@@ -249,10 +246,9 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev)
         if (zdev->fmb)
                 return -EINVAL;
 
-        zdev->fmb = kmem_cache_alloc(zdev_fmb_cache, GFP_KERNEL);
+        zdev->fmb = kmem_cache_zalloc(zdev_fmb_cache, GFP_KERNEL);
         if (!zdev->fmb)
                 return -ENOMEM;
-        memset(zdev->fmb, 0, sizeof(*zdev->fmb));
         WARN_ON((u64) zdev->fmb & 0xf);
 
         args.fmb_addr = virt_to_phys(zdev->fmb);
@@ -284,12 +280,12 @@ static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
         u64 data;
         int rc;
 
-        rc = pcilg_instr(&data, req, offset);
-        data = data << ((8 - len) * 8);
-        data = le64_to_cpu(data);
-        if (!rc)
+        rc = s390pci_load(&data, req, offset);
+        if (!rc) {
+                data = data << ((8 - len) * 8);
+                data = le64_to_cpu(data);
                 *val = (u32) data;
-        else
+        } else
                 *val = 0xffffffff;
         return rc;
 }
@@ -302,7 +298,7 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
 
         data = cpu_to_le64(data);
         data = data >> ((8 - len) * 8);
-        rc = pcistg_instr(data, req, offset);
+        rc = s390pci_store(data, req, offset);
         return rc;
 }
 
@@ -409,20 +405,28 @@ static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
                     int size, u32 *val)
 {
         struct zpci_dev *zdev = get_zdev_by_bus(bus);
+        int ret;
 
         if (!zdev || devfn != ZPCI_DEVFN)
-                return 0;
-        return zpci_cfg_load(zdev, where, val, size);
+                ret = -ENODEV;
+        else
+                ret = zpci_cfg_load(zdev, where, val, size);
+
+        return ret;
 }
 
 static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
                      int size, u32 val)
 {
         struct zpci_dev *zdev = get_zdev_by_bus(bus);
+        int ret;
 
         if (!zdev || devfn != ZPCI_DEVFN)
-                return 0;
-        return zpci_cfg_store(zdev, where, val, size);
+                ret = -ENODEV;
+        else
+                ret = zpci_cfg_store(zdev, where, val, size);
+
+        return ret;
 }
 
 static struct pci_ops pci_root_ops = {
@@ -474,7 +478,7 @@ scan:
         }
 
         /* enable interrupts again */
-        sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+        set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
 
         /* check again to not lose initiative */
         rmb();
@@ -596,19 +600,6 @@ static void zpci_map_resources(struct zpci_dev *zdev)
         }
 };
 
-static void zpci_unmap_resources(struct pci_dev *pdev)
-{
-        resource_size_t len;
-        int i;
-
-        for (i = 0; i < PCI_BAR_COUNT; i++) {
-                len = pci_resource_len(pdev, i);
-                if (!len)
-                        continue;
-                pci_iounmap(pdev, (void *) pdev->resource[i].start);
-        }
-};
-
 struct zpci_dev *zpci_alloc_device(void)
 {
         struct zpci_dev *zdev;
@@ -636,32 +627,6 @@ void zpci_free_device(struct zpci_dev *zdev)
         kfree(zdev);
 }
 
-/* Called on removal of pci_dev, leaves zpci and bus device */
-static void zpci_remove_device(struct pci_dev *pdev)
-{
-        struct zpci_dev *zdev = get_zdev(pdev);
-
-        dev_info(&pdev->dev, "Removing device %u\n", zdev->domain);
-        zdev->state = ZPCI_FN_STATE_CONFIGURED;
-        zpci_dma_exit_device(zdev);
-        zpci_fmb_disable_device(zdev);
-        zpci_sysfs_remove_device(&pdev->dev);
-        zpci_unmap_resources(pdev);
-        list_del(&zdev->entry);         /* can be called from init */
-        zdev->pdev = NULL;
-}
-
-static void zpci_scan_devices(void)
-{
-        struct zpci_dev *zdev;
-
-        mutex_lock(&zpci_list_lock);
-        list_for_each_entry(zdev, &zpci_list, entry)
-                if (zdev->state == ZPCI_FN_STATE_CONFIGURED)
-                        zpci_scan_device(zdev);
-        mutex_unlock(&zpci_list_lock);
-}
-
 /*
  * Too late for any s390 specific setup, since interrupts must be set up
  * already which requires DMA setup too and the pci scan will access the
@@ -688,12 +653,6 @@ int pcibios_enable_device(struct pci_dev *pdev, int mask)
         return 0;
 }
 
-void pcibios_disable_device(struct pci_dev *pdev)
-{
-        zpci_remove_device(pdev);
-        pdev->sysdata = NULL;
-}
-
 int pcibios_add_platform_entries(struct pci_dev *pdev)
 {
         return zpci_sysfs_add_device(&pdev->dev);
@@ -789,7 +748,7 @@ static int __init zpci_irq_init(void)
         spin_lock_init(&bucket->lock);
         /* set summary to 1 to be called every time for the ISC */
         *zpci_irq_si = 1;
-        sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+        set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
         return 0;
 
 out_ai:
@@ -872,7 +831,19 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry)
         spin_unlock(&zpci_iomap_lock);
 }
 
-static int zpci_create_device_bus(struct zpci_dev *zdev)
+int pcibios_add_device(struct pci_dev *pdev)
+{
+        struct zpci_dev *zdev = get_zdev(pdev);
+
+        zdev->pdev = pdev;
+        zpci_debug_init_device(zdev);
+        zpci_fmb_enable_device(zdev);
+        zpci_map_resources(zdev);
+
+        return 0;
+}
+
+static int zpci_scan_bus(struct zpci_dev *zdev)
 {
         struct resource *res;
         LIST_HEAD(resources);
@@ -909,8 +880,8 @@ static int zpci_create_device_bus(struct zpci_dev *zdev)
                 pci_add_resource(&resources, res);
         }
 
-        zdev->bus = pci_create_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops,
-                                        zdev, &resources);
+        zdev->bus = pci_scan_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops,
+                                      zdev, &resources);
         if (!zdev->bus)
                 return -EIO;
 
@@ -959,6 +930,13 @@ out:
 }
 EXPORT_SYMBOL_GPL(zpci_enable_device);
 
+int zpci_disable_device(struct zpci_dev *zdev)
+{
+        zpci_dma_exit_device(zdev);
+        return clp_disable_fh(zdev);
+}
+EXPORT_SYMBOL_GPL(zpci_disable_device);
+
 int zpci_create_device(struct zpci_dev *zdev)
 {
         int rc;
@@ -967,9 +945,16 @@ int zpci_create_device(struct zpci_dev *zdev)
         if (rc)
                 goto out;
 
-        rc = zpci_create_device_bus(zdev);
+        if (zdev->state == ZPCI_FN_STATE_CONFIGURED) {
+                rc = zpci_enable_device(zdev);
+                if (rc)
+                        goto out_free;
+
+                zdev->state = ZPCI_FN_STATE_ONLINE;
+        }
+        rc = zpci_scan_bus(zdev);
         if (rc)
-                goto out_bus;
+                goto out_disable;
 
         mutex_lock(&zpci_list_lock);
         list_add_tail(&zdev->entry, &zpci_list);
@@ -977,21 +962,12 @@ int zpci_create_device(struct zpci_dev *zdev)
                 hotplug_ops->create_slot(zdev);
         mutex_unlock(&zpci_list_lock);
 
-        if (zdev->state == ZPCI_FN_STATE_STANDBY)
-                return 0;
-
-        rc = zpci_enable_device(zdev);
-        if (rc)
-                goto out_start;
         return 0;
 
-out_start:
-        mutex_lock(&zpci_list_lock);
-        list_del(&zdev->entry);
-        if (hotplug_ops)
-                hotplug_ops->remove_slot(zdev);
-        mutex_unlock(&zpci_list_lock);
-out_bus:
+out_disable:
+        if (zdev->state == ZPCI_FN_STATE_ONLINE)
+                zpci_disable_device(zdev);
+out_free:
         zpci_free_domain(zdev);
 out:
         return rc;
@@ -1016,15 +992,9 @@ int zpci_scan_device(struct zpci_dev *zdev)
                 goto out;
         }
 
-        zpci_debug_init_device(zdev);
-        zpci_fmb_enable_device(zdev);
-        zpci_map_resources(zdev);
         pci_bus_add_devices(zdev->bus);
 
-        /* now that pdev was added to the bus mark it as used */
-        zdev->state = ZPCI_FN_STATE_ONLINE;
         return 0;
-
 out:
         zpci_dma_exit_device(zdev);
         clp_disable_fh(zdev);
@@ -1087,13 +1057,13 @@ void zpci_deregister_hp_ops(void)
 }
 EXPORT_SYMBOL_GPL(zpci_deregister_hp_ops);
 
-unsigned int s390_pci_probe = 1;
+unsigned int s390_pci_probe;
 EXPORT_SYMBOL_GPL(s390_pci_probe);
 
 char * __init pcibios_setup(char *str)
 {
-        if (!strcmp(str, "off")) {
-                s390_pci_probe = 0;
+        if (!strcmp(str, "on")) {
+                s390_pci_probe = 1;
                 return NULL;
         }
         return str;
@@ -1138,7 +1108,6 @@ static int __init pci_base_init(void)
         if (rc)
                 goto out_find;
 
-        zpci_scan_devices();
         return 0;
 
 out_find:
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index f339fe2feb15..bd34359d1546 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -13,6 +13,7 @@
 #include <linux/err.h>
 #include <linux/delay.h>
 #include <linux/pci.h>
+#include <asm/pci_debug.h>
 #include <asm/pci_clp.h>
 
 /*
@@ -144,6 +145,7 @@ int clp_add_pci_device(u32 fid, u32 fh, int configured)
         struct zpci_dev *zdev;
         int rc;
 
+        zpci_dbg(3, "add fid:%x, fh:%x, c:%d\n", fid, fh, configured);
         zdev = zpci_alloc_device();
         if (IS_ERR(zdev))
                 return PTR_ERR(zdev);
@@ -204,8 +206,8 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
         if (!rc && rrb->response.hdr.rsp == CLP_RC_OK)
                 *fh = rrb->response.fh;
         else {
-                pr_err("Set PCI FN failed with response: %x  cc: %d\n",
-                        rrb->response.hdr.rsp, rc);
+                zpci_dbg(0, "SPF fh:%x, cc:%d, resp:%x\n", *fh, rc,
+                         rrb->response.hdr.rsp);
                 rc = -EIO;
         }
         clp_free_block(rrb);
@@ -221,6 +223,8 @@ int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as)
         if (!rc)
                 /* Success -> store enabled handle in zdev */
                 zdev->fh = fh;
+
+        zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
         return rc;
 }
 
@@ -237,9 +241,8 @@ int clp_disable_fh(struct zpci_dev *zdev)
         if (!rc)
                 /* Success -> store disabled handle in zdev */
                 zdev->fh = fh;
-        else
-                dev_err(&zdev->pdev->dev,
-                        "Failed to disable fn handle: 0x%x\n", fh);
+
+        zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
         return rc;
 }
 
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index a5d07bc2a547..771b82359af4 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -11,12 +11,17 @@
 #include <linux/kernel.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <linux/export.h>
 #include <linux/pci.h>
 #include <asm/debug.h>
 
 #include <asm/pci_dma.h>
 
 static struct dentry *debugfs_root;
+debug_info_t *pci_debug_msg_id;
+EXPORT_SYMBOL_GPL(pci_debug_msg_id);
+debug_info_t *pci_debug_err_id;
+EXPORT_SYMBOL_GPL(pci_debug_err_id);
 
 static char *pci_perf_names[] = {
         /* hardware counters */
@@ -168,7 +173,6 @@ int __init zpci_debug_init(void)
                 return -EINVAL;
         debug_register_view(pci_debug_msg_id, &debug_sprintf_view);
         debug_set_level(pci_debug_msg_id, 3);
-        zpci_dbg("Debug view initialized\n");
 
         /* error log */
         pci_debug_err_id = debug_register("pci_error", 2, 1, 16);
@@ -176,7 +180,6 @@ int __init zpci_debug_init(void)
                 return -EINVAL;
         debug_register_view(pci_debug_err_id, &debug_hex_ascii_view);
         debug_set_level(pci_debug_err_id, 6);
-        zpci_err("Debug view initialized\n");
 
         debugfs_root = debugfs_create_dir("pci", NULL);
         return 0;
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index a547419907c3..f8e69d5bc0a9 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -169,8 +169,9 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
                  * needs to be redone!
                  */
                 goto no_refresh;
-        rc = rpcit_instr((u64) zdev->fh << 32, start_dma_addr,
-                          nr_pages * PAGE_SIZE);
+
+        rc = s390pci_refresh_trans((u64) zdev->fh << 32, start_dma_addr,
+                                   nr_pages * PAGE_SIZE);
 
 no_refresh:
         spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags);
@@ -268,8 +269,6 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
         int flags = ZPCI_PTE_VALID;
         dma_addr_t dma_addr;
 
-        WARN_ON_ONCE(offset > PAGE_SIZE);
-
         /* This rounds up number of pages based on size and offset */
         nr_pages = iommu_num_pages(pa, size, PAGE_SIZE);
         iommu_page_index = dma_alloc_iommu(zdev, nr_pages);
@@ -291,7 +290,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
 
         if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) {
                 atomic64_add(nr_pages, (atomic64_t *) &zdev->fmb->mapped_pages);
-                return dma_addr + offset;
+                return dma_addr + (offset & ~PAGE_MASK);
         }
 
 out_free:
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
new file mode 100644
index 000000000000..22eeb9d7ffeb
--- /dev/null
+++ b/arch/s390/pci/pci_insn.c
@@ -0,0 +1,202 @@
+/*
+ * s390 specific pci instructions
+ *
+ * Copyright IBM Corp. 2013
+ */
+
+#include <linux/export.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <asm/pci_insn.h>
+#include <asm/processor.h>
+
+#define ZPCI_INSN_BUSY_DELAY    1       /* 1 microsecond */
+
+/* Modify PCI Function Controls */
+static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status)
+{
+        u8 cc;
+
+        asm volatile (
+                "       .insn   rxy,0xe300000000d0,%[req],%[fib]\n"
+                "       ipm     %[cc]\n"
+                "       srl     %[cc],28\n"
+                : [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib)
+                : : "cc");
+        *status = req >> 24 & 0xff;
+        return cc;
+}
+
+int s390pci_mod_fc(u64 req, struct zpci_fib *fib)
+{
+        u8 cc, status;
+
+        do {
+                cc = __mpcifc(req, fib, &status);
+                if (cc == 2)
+                        msleep(ZPCI_INSN_BUSY_DELAY);
+        } while (cc == 2);
+
+        if (cc)
+                printk_once(KERN_ERR "%s: error cc: %d  status: %d\n",
+                             __func__, cc, status);
+        return (cc) ? -EIO : 0;
+}
+
+/* Refresh PCI Translations */
+static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status)
+{
+        register u64 __addr asm("2") = addr;
+        register u64 __range asm("3") = range;
+        u8 cc;
+
+        asm volatile (
+                "       .insn   rre,0xb9d30000,%[fn],%[addr]\n"
+                "       ipm     %[cc]\n"
+                "       srl     %[cc],28\n"
+                : [cc] "=d" (cc), [fn] "+d" (fn)
+                : [addr] "d" (__addr), "d" (__range)
+                : "cc");
+        *status = fn >> 24 & 0xff;
+        return cc;
+}
+
+int s390pci_refresh_trans(u64 fn, u64 addr, u64 range)
+{
+        u8 cc, status;
+
+        do {
+                cc = __rpcit(fn, addr, range, &status);
+                if (cc == 2)
+                        udelay(ZPCI_INSN_BUSY_DELAY);
+        } while (cc == 2);
+
+        if (cc)
+                printk_once(KERN_ERR "%s: error cc: %d  status: %d  dma_addr: %Lx  size: %Lx\n",
+                            __func__, cc, status, addr, range);
+        return (cc) ? -EIO : 0;
+}
+
+/* Set Interruption Controls */
+void set_irq_ctrl(u16 ctl, char *unused, u8 isc)
+{
+        asm volatile (
+                "       .insn   rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n"
+                : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused));
+}
+
+/* PCI Load */
+static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
+{
+        register u64 __req asm("2") = req;
+        register u64 __offset asm("3") = offset;
+        int cc = -ENXIO;
+        u64 __data;
+
+        asm volatile (
+                "       .insn   rre,0xb9d20000,%[data],%[req]\n"
+                "0:     ipm     %[cc]\n"
+                "       srl     %[cc],28\n"
+                "1:\n"
+                EX_TABLE(0b, 1b)
+                : [cc] "+d" (cc), [data] "=d" (__data), [req] "+d" (__req)
+                :  "d" (__offset)
+                : "cc");
+        *status = __req >> 24 & 0xff;
+        if (!cc)
+                *data = __data;
+
+        return cc;
+}
+
+int s390pci_load(u64 *data, u64 req, u64 offset)
+{
+        u8 status;
+        int cc;
+
+        do {
+                cc = __pcilg(data, req, offset, &status);
+                if (cc == 2)
+                        udelay(ZPCI_INSN_BUSY_DELAY);
+        } while (cc == 2);
+
+        if (cc)
+                printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+                            __func__, cc, status, req, offset);
+        return (cc > 0) ? -EIO : cc;
+}
+EXPORT_SYMBOL_GPL(s390pci_load);
+
+/* PCI Store */
+static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status)
+{
+        register u64 __req asm("2") = req;
+        register u64 __offset asm("3") = offset;
+        int cc = -ENXIO;
+
+        asm volatile (
+                "       .insn   rre,0xb9d00000,%[data],%[req]\n"
+                "0:     ipm     %[cc]\n"
+                "       srl     %[cc],28\n"
+                "1:\n"
+                EX_TABLE(0b, 1b)
+                : [cc] "+d" (cc), [req] "+d" (__req)
+                : "d" (__offset), [data] "d" (data)
+                : "cc");
+        *status = __req >> 24 & 0xff;
+        return cc;
+}
+
+int s390pci_store(u64 data, u64 req, u64 offset)
+{
+        u8 status;
+        int cc;
+
+        do {
+                cc = __pcistg(data, req, offset, &status);
+                if (cc == 2)
+                        udelay(ZPCI_INSN_BUSY_DELAY);
+        } while (cc == 2);
+
+        if (cc)
+                printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+                        __func__, cc, status, req, offset);
+        return (cc > 0) ? -EIO : cc;
+}
+EXPORT_SYMBOL_GPL(s390pci_store);
+
+/* PCI Store Block */
+static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
+{
+        int cc = -ENXIO;
+
+        asm volatile (
+                "       .insn   rsy,0xeb00000000d0,%[req],%[offset],%[data]\n"
+                "0:     ipm     %[cc]\n"
+                "       srl     %[cc],28\n"
+                "1:\n"
+                EX_TABLE(0b, 1b)
+                : [cc] "+d" (cc), [req] "+d" (req)
+                : [offset] "d" (offset), [data] "Q" (*data)
+                : "cc");
+        *status = req >> 24 & 0xff;
+        return cc;
+}
+
+int s390pci_store_block(const u64 *data, u64 req, u64 offset)
+{
+        u8 status;
+        int cc;
+
+        do {
+                cc = __pcistb(data, req, offset, &status);
+                if (cc == 2)
+                        udelay(ZPCI_INSN_BUSY_DELAY);
+        } while (cc == 2);
+
+        if (cc)
+                printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+                            __func__, cc, status, req, offset);
+        return (cc > 0) ? -EIO : cc;
+}
+EXPORT_SYMBOL_GPL(s390pci_store_block);
diff --git a/arch/s390/pci/pci_msi.c b/arch/s390/pci/pci_msi.c
index 0297931335e1..b097aed05a9b 100644
--- a/arch/s390/pci/pci_msi.c
+++ b/arch/s390/pci/pci_msi.c
@@ -18,8 +18,9 @@
 
 /* mapping of irq numbers to msi_desc */
 static struct hlist_head *msi_hash;
-static unsigned int msihash_shift = 6;
-#define msi_hashfn(nr)  hash_long(nr, msihash_shift)
+static const unsigned int msi_hash_bits = 8;
+#define MSI_HASH_BUCKETS (1U << msi_hash_bits)
+#define msi_hashfn(nr)  hash_long(nr, msi_hash_bits)
 
 static DEFINE_SPINLOCK(msi_map_lock);
 
@@ -74,6 +75,7 @@ int zpci_setup_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi,
         map->irq = nr;
         map->msi = msi;
         zdev->msi_map[nr & ZPCI_MSI_MASK] = map;
+        INIT_HLIST_NODE(&map->msi_chain);
 
         pr_debug("%s hashing irq: %u  to bucket nr: %llu\n",
                 __func__, nr, msi_hashfn(nr));
@@ -125,11 +127,11 @@ int __init zpci_msihash_init(void)
 {
         unsigned int i;
 
-        msi_hash = kmalloc(256 * sizeof(*msi_hash), GFP_KERNEL);
+        msi_hash = kmalloc(MSI_HASH_BUCKETS * sizeof(*msi_hash), GFP_KERNEL);
         if (!msi_hash)
                 return -ENOMEM;
 
-        for (i = 0; i < (1U << msihash_shift); i++)
+        for (i = 0; i < MSI_HASH_BUCKETS; i++)
                 INIT_HLIST_HEAD(&msi_hash[i]);
         return 0;
 }
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index e569aa1fd2ba..c8def8bc9020 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -12,7 +12,7 @@ config SCORE
        select GENERIC_CPU_DEVICES
        select GENERIC_CLOCKEVENTS
        select HAVE_MOD_ARCH_SPECIFIC
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select MODULES_USE_ELF_REL
         select CLONE_BACKWARDS
 
diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c
index 79568466b578..f4c6d02421d3 100644
--- a/arch/score/kernel/process.c
+++ b/arch/score/kernel/process.c
@@ -41,24 +41,6 @@ void machine_halt(void) {}
 /* If or when software machine-power-off is implemented, add code here. */
 void machine_power_off(void) {}
 
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void __noreturn cpu_idle(void)
-{
-        /* endless idle loop with no priority at all */
-        while (1) {
-                rcu_idle_enter();
-                while (!need_resched())
-                        barrier();
-                rcu_idle_exit();
-                schedule_preempt_disabled();
-        }
-}
-
 void ret_from_fork(void);
 void ret_from_kernel_thread(void);
 
diff --git a/arch/score/mm/init.c b/arch/score/mm/init.c
index cee6bce1e30c..1592aad7dbc4 100644
--- a/arch/score/mm/init.c
+++ b/arch/score/mm/init.c
@@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(empty_zero_page);
 
 static struct kcore_list kcore_mem, kcore_vmalloc;
 
-static unsigned long setup_zero_page(void)
+static void setup_zero_page(void)
 {
         struct page *page;
 
@@ -52,9 +52,7 @@ static unsigned long setup_zero_page(void)
                 panic("Oh boy, that early out of memory?");
 
         page = virt_to_page((void *) empty_zero_page);
-        SetPageReserved(page);
-
-        return 1UL;
+        mark_page_reserved(page);
 }
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -84,7 +82,7 @@ void __init mem_init(void)
 
         high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
         totalram_pages += free_all_bootmem();
-        totalram_pages -= setup_zero_page();    /* Setup zeroed pages. */
+        setup_zero_page();      /* Setup zeroed pages. */
         reservedpages = 0;
 
         for (tmp = 0; tmp < max_low_pfn; tmp++)
@@ -109,37 +107,16 @@ void __init mem_init(void)
 }
 #endif /* !CONFIG_NEED_MULTIPLE_NODES */
 
-static void free_init_pages(const char *what, unsigned long begin, unsigned long end)
-{
-        unsigned long pfn;
-
-        for (pfn = PFN_UP(begin); pfn < PFN_DOWN(end); pfn++) {
-                struct page *page = pfn_to_page(pfn);
-                void *addr = phys_to_virt(PFN_PHYS(pfn));
-
-                ClearPageReserved(page);
-                init_page_count(page);
-                memset(addr, POISON_FREE_INITMEM, PAGE_SIZE);
-                __free_page(page);
-                totalram_pages++;
-        }
-        printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
-}
-
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        free_init_pages("initrd memory",
-                virt_to_phys((void *) start),
-                virt_to_phys((void *) end));
+        free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd");
 }
 #endif
 
 void __init_refok free_initmem(void)
 {
-        free_init_pages("unused kernel memory",
-        __pa(&__init_begin),
-        __pa(&__init_end));
+        free_initmem_default(POISON_FREE_INITMEM);
 }
 
 unsigned long pgd_current;
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 5e859633ce69..1ea597c6497a 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -33,6 +33,7 @@ config SUPERH
         select GENERIC_ATOMIC64
         select GENERIC_IRQ_SHOW
         select GENERIC_SMP_IDLE_THREAD
+        select GENERIC_IDLE_POLL_SETUP
         select GENERIC_CLOCKEVENTS
         select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST
         select GENERIC_STRNCPY_FROM_USER
@@ -148,9 +149,6 @@ config ARCH_HAS_ILOG2_U32
 config ARCH_HAS_ILOG2_U64
         def_bool n
 
-config ARCH_HAS_DEFAULT_IDLE
-        def_bool y
-
 config NO_IOPORT
         def_bool !PCI
         depends on !SH_CAYMAN && !SH_SH4202_MICRODEV && !SH_SHMIN && \
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index aaff7671101b..764530c85aa9 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -254,11 +254,13 @@ static int usbhs_get_id(struct platform_device *pdev)
         return gpio_get_value(GPIO_PTB3);
 }
 
-static void usbhs_phy_reset(struct platform_device *pdev)
+static int usbhs_phy_reset(struct platform_device *pdev)
 {
         /* enable vbus if HOST */
         if (!gpio_get_value(GPIO_PTB3))
                 gpio_set_value(GPIO_PTB5, 1);
+
+        return 0;
 }
 
 static struct renesas_usbhs_platform_info usbhs_info = {
diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c
index c2c85f6cd738..a162a7f86b2e 100644
--- a/arch/sh/drivers/pci/pcie-sh7786.c
+++ b/arch/sh/drivers/pci/pcie-sh7786.c
@@ -35,7 +35,7 @@ static unsigned int nr_ports;
 
 static struct sh7786_pcie_hwops {
         int (*core_init)(void);
-        async_func_ptr *port_init_hw;
+        async_func_t port_init_hw;
 } *sh7786_pcie_hwops;
 
 static struct resource sh7786_pci0_resources[] = {
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index b3808c7d67b2..699255d6d1c6 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -3,6 +3,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/page.h>
+#include <asm-generic/hugetlb.h>
 
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h
index 7d5ac4e48485..45a93669289d 100644
--- a/arch/sh/include/asm/thread_info.h
+++ b/arch/sh/include/asm/thread_info.h
@@ -207,8 +207,6 @@ static inline bool test_and_clear_restore_sigmask(void)
         return true;
 }
 
-#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
-
 #endif  /* !__ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index 3d5a1b387cc0..2ea4483fd722 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -24,98 +24,24 @@
 
 static void (*sh_idle)(void);
 
-static int hlt_counter;
-
-static int __init nohlt_setup(char *__unused)
-{
-        hlt_counter = 1;
-        return 1;
-}
-__setup("nohlt", nohlt_setup);
-
-static int __init hlt_setup(char *__unused)
-{
-        hlt_counter = 0;
-        return 1;
-}
-__setup("hlt", hlt_setup);
-
-static inline int hlt_works(void)
-{
-        return !hlt_counter;
-}
-
-/*
- * On SMP it's slightly faster (but much more power-consuming!)
- * to poll the ->work.need_resched flag instead of waiting for the
- * cross-CPU IPI to arrive. Use this option with caution.
- */
-static void poll_idle(void)
+void default_idle(void)
 {
+        set_bl_bit();
         local_irq_enable();
-        while (!need_resched())
-                cpu_relax();
+        /* Isn't this racy ? */
+        cpu_sleep();
+        clear_bl_bit();
 }
 
-void default_idle(void)
+void arch_cpu_idle_dead(void)
 {
-        if (hlt_works()) {
-                clear_thread_flag(TIF_POLLING_NRFLAG);
-                smp_mb__after_clear_bit();
-
-                set_bl_bit();
-                if (!need_resched()) {
-                        local_irq_enable();
-                        cpu_sleep();
-                } else
-                        local_irq_enable();
-
-                set_thread_flag(TIF_POLLING_NRFLAG);
-                clear_bl_bit();
-        } else
-                poll_idle();
+        play_dead();
 }
 
-/*
- * The idle thread. There's no useful work to be done, so just try to conserve
- * power and have a low exit latency (ie sit in a loop waiting for somebody to
- * say that they'd like to reschedule)
- */
-void cpu_idle(void)
+void arch_cpu_idle(void)
 {
-        unsigned int cpu = smp_processor_id();
-
-        set_thread_flag(TIF_POLLING_NRFLAG);
-
-        /* endless idle loop with no priority at all */
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-
-                while (!need_resched()) {
-                        check_pgt_cache();
-                        rmb();
-
-                        if (cpu_is_offline(cpu))
-                                play_dead();
-
-                        local_irq_disable();
-                        /* Don't trace irqs off for idle */
-                        stop_critical_timings();
-                        if (cpuidle_idle_call())
-                                sh_idle();
-                        /*
-                         * Sanity check to ensure that sh_idle() returns
-                         * with IRQs enabled
-                         */
-                        WARN_ON(irqs_disabled());
-                        start_critical_timings();
-                }
-
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                schedule_preempt_disabled();
-        }
+        if (cpuidle_idle_call())
+                sh_idle();
 }
 
 void __init select_idle_routine(void)
@@ -123,13 +49,8 @@ void __init select_idle_routine(void)
         /*
          * If a platform has set its own idle routine, leave it alone.
          */
-        if (sh_idle)
-                return;
-
-        if (hlt_works())
+        if (!sh_idle)
                 sh_idle = default_idle;
-        else
-                sh_idle = poll_idle;
 }
 
 void stop_this_cpu(void *unused)
diff --git a/arch/sh/kernel/sh_bios.c b/arch/sh/kernel/sh_bios.c
index 47475cca068a..fe584e516964 100644
--- a/arch/sh/kernel/sh_bios.c
+++ b/arch/sh/kernel/sh_bios.c
@@ -104,6 +104,7 @@ void sh_bios_vbr_reload(void)
                 );
 }
 
+#ifdef CONFIG_EARLY_PRINTK
 /*
  *      Print a string through the BIOS
  */
@@ -144,8 +145,6 @@ static struct console bios_console = {
         .index          = -1,
 };
 
-static struct console *early_console;
-
 static int __init setup_early_printk(char *buf)
 {
         int keep_early = 0;
@@ -170,3 +169,4 @@ static int __init setup_early_printk(char *buf)
         return 0;
 }
 early_param("earlyprintk", setup_early_printk);
+#endif
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index 2062aa88af41..45696451f0ea 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -203,7 +203,7 @@ asmlinkage void __cpuinit start_secondary(void)
         set_cpu_online(cpu, true);
         per_cpu(cpu_state, cpu) = CPU_ONLINE;
 
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 extern struct {
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 105794037143..20f9ead650d3 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -417,15 +417,13 @@ void __init mem_init(void)
 
         for_each_online_node(nid) {
                 pg_data_t *pgdat = NODE_DATA(nid);
-                unsigned long node_pages = 0;
                 void *node_high_memory;
 
                 num_physpages += pgdat->node_present_pages;
 
                 if (pgdat->node_spanned_pages)
-                        node_pages = free_all_bootmem_node(pgdat);
+                        totalram_pages += free_all_bootmem_node(pgdat);
 
-                totalram_pages += node_pages;
 
                 node_high_memory = (void *)__va((pgdat->node_start_pfn +
                                                  pgdat->node_spanned_pages) <<
@@ -501,31 +499,13 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
-        unsigned long addr;
-
-        addr = (unsigned long)(&__init_begin);
-        for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
-                free_page(addr);
-                totalram_pages++;
-        }
-        printk("Freeing unused kernel memory: %ldk freed\n",
-               ((unsigned long)&__init_end -
-                (unsigned long)&__init_begin) >> 10);
+        free_initmem_default(0);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        unsigned long p;
-        for (p = start; p < end; p += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(p));
-                init_page_count(virt_to_page(p));
-                free_page(p);
-                totalram_pages++;
-        }
-        printk("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
+        free_reserved_area(start, end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 289127d5241c..66dc562950ae 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -84,12 +84,6 @@ config ARCH_DEFCONFIG
         default "arch/sparc/configs/sparc32_defconfig" if SPARC32
         default "arch/sparc/configs/sparc64_defconfig" if SPARC64
 
-# CONFIG_BITS can be used at source level to get 32/64 bits
-config BITS
-        int
-        default 32 if SPARC32
-        default 64 if SPARC64
-
 config IOMMU_HELPER
         bool
         default y if SPARC64
@@ -197,7 +191,7 @@ config RWSEM_XCHGADD_ALGORITHM
 
 config GENERIC_HWEIGHT
         bool
-        default y if !ULTRA_HAS_POPULATION_COUNT
+        default y
 
 config GENERIC_CALIBRATE_DELAY
         bool
@@ -413,6 +407,8 @@ config SERIAL_CONSOLE
 config SPARC_LEON
         bool "Sparc Leon processor family"
         depends on SPARC32
+        select USB_EHCI_BIG_ENDIAN_MMIO
+        select USB_EHCI_BIG_ENDIAN_DESC
         ---help---
           If you say Y here if you are running on a SPARC-LEON processor.
           The LEON processor is a synthesizable VHDL model of the
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index e26d430ce2fd..ff18e3cfb6b1 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -2,11 +2,16 @@
 
 
 generic-y += clkdev.h
+generic-y += cputime.h
 generic-y += div64.h
+generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += local64.h
+generic-y += mutex.h
 generic-y += irq_regs.h
 generic-y += local.h
 generic-y += module.h
+generic-y += serial.h
 generic-y += trace_clock.h
+generic-y += types.h
 generic-y += word-at-a-time.h
diff --git a/arch/sparc/include/asm/cputime.h b/arch/sparc/include/asm/cputime.h
deleted file mode 100644
index 1a642b81e019..000000000000
--- a/arch/sparc/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __SPARC_CPUTIME_H
-#define __SPARC_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __SPARC_CPUTIME_H */
diff --git a/arch/sparc/include/asm/emergency-restart.h b/arch/sparc/include/asm/emergency-restart.h
deleted file mode 100644
index 108d8c48e42e..000000000000
--- a/arch/sparc/include/asm/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 7eb57d245044..e4cab465b81f 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -2,6 +2,7 @@
 #define _ASM_SPARC64_HUGETLB_H
 
 #include <asm/page.h>
+#include <asm-generic/hugetlb.h>
 
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/sparc/include/asm/mutex.h b/arch/sparc/include/asm/mutex.h
deleted file mode 100644
index 458c1f7fbc18..000000000000
--- a/arch/sparc/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 08fcce90316b..7619f2f792af 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -915,6 +915,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
         return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
 }
 
+#include <asm/tlbflush.h>
 #include <asm-generic/pgtable.h>
 
 /* We provide our own get_unmapped_area to cope with VA holes and
diff --git a/arch/sparc/include/asm/serial.h b/arch/sparc/include/asm/serial.h
deleted file mode 100644
index f90d61c28059..000000000000
--- a/arch/sparc/include/asm/serial.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __SPARC_SERIAL_H
-#define __SPARC_SERIAL_H
-
-#define BASE_BAUD ( 1843200 / 16 )
-
-#endif /* __SPARC_SERIAL_H */
diff --git a/arch/sparc/include/asm/smp_32.h b/arch/sparc/include/asm/smp_32.h
index b73da3c5f10a..3c8917f054de 100644
--- a/arch/sparc/include/asm/smp_32.h
+++ b/arch/sparc/include/asm/smp_32.h
@@ -36,7 +36,6 @@ typedef void (*smpfunc_t)(unsigned long, unsigned long, unsigned long,
                        unsigned long, unsigned long);
 
 void cpu_panic(void);
-extern void smp4m_irq_rotate(int cpu);
 
 /*
  *      General functions that each host system must provide.
@@ -46,7 +45,6 @@ void sun4m_init_smp(void);
 void sun4d_init_smp(void);
 
 void smp_callin(void);
-void smp_boot_cpus(void);
 void smp_store_cpu_info(int);
 
 void smp_resched_interrupt(void);
@@ -107,9 +105,6 @@ extern int hard_smp_processor_id(void);
 
 #define raw_smp_processor_id()          (current_thread_info()->cpu)
 
-#define prof_multiplier(__cpu)          cpu_data(__cpu).multiplier
-#define prof_counter(__cpu)             cpu_data(__cpu).counter
-
 void smp_setup_cpu_possible_map(void);
 
 #endif /* !(__ASSEMBLY__) */
diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h
index d06a26601753..6b67e50fb9b4 100644
--- a/arch/sparc/include/asm/spitfire.h
+++ b/arch/sparc/include/asm/spitfire.h
@@ -45,6 +45,7 @@
 #define SUN4V_CHIP_NIAGARA3     0x03
 #define SUN4V_CHIP_NIAGARA4     0x04
 #define SUN4V_CHIP_NIAGARA5     0x05
+#define SUN4V_CHIP_SPARC64X     0x8a
 #define SUN4V_CHIP_UNKNOWN      0xff
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h
index cad36f56fa03..c7de3323819c 100644
--- a/arch/sparc/include/asm/switch_to_64.h
+++ b/arch/sparc/include/asm/switch_to_64.h
@@ -18,8 +18,7 @@ do {						\
          * and 2 stores in this critical code path.  -DaveM
          */
 #define switch_to(prev, next, last)                                     \
-do {    flush_tlb_pending();                                            \
-        save_and_clear_fpu();                                           \
+do {    save_and_clear_fpu();                                           \
         /* If you are tempted to conditionalize the following */        \
         /* so that ASI is only written if it changes, think again. */   \
         __asm__ __volatile__("wr %%g0, %0, %%asi"                       \
diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h
index 25849ae3e900..dd3807599bb9 100644
--- a/arch/sparc/include/asm/thread_info_32.h
+++ b/arch/sparc/include/asm/thread_info_32.h
@@ -132,8 +132,6 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define _TIF_DO_NOTIFY_RESUME_MASK      (_TIF_NOTIFY_RESUME | \
                                          _TIF_SIGPENDING)
 
-#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 269bd92313df..d5e504251079 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -256,8 +256,6 @@ static inline bool test_and_clear_restore_sigmask(void)
         return true;
 }
 
-#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
-
 #define thread32_stack_is_64bit(__SP) (((__SP) & 0x1) != 0)
 #define test_thread_64bit_stack(__SP) \
         ((test_thread_flag(TIF_32BIT) && !thread32_stack_is_64bit(__SP)) ? \
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index 2ef463494153..f0d6a9700f4c 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -11,24 +11,40 @@
 struct tlb_batch {
         struct mm_struct *mm;
         unsigned long tlb_nr;
+        unsigned long active;
         unsigned long vaddrs[TLB_BATCH_NR];
 };
 
 extern void flush_tsb_kernel_range(unsigned long start, unsigned long end);
 extern void flush_tsb_user(struct tlb_batch *tb);
+extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
 
 /* TLB flush operations. */
 
-extern void flush_tlb_pending(void);
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+                                  unsigned long vmaddr)
+{
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+                                   unsigned long start, unsigned long end)
+{
+}
+
+#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 
-#define flush_tlb_range(vma,start,end)  \
-        do { (void)(start); flush_tlb_pending(); } while (0)
-#define flush_tlb_page(vma,addr)        flush_tlb_pending()
-#define flush_tlb_mm(mm)                flush_tlb_pending()
+extern void flush_tlb_pending(void);
+extern void arch_enter_lazy_mmu_mode(void);
+extern void arch_leave_lazy_mmu_mode(void);
+#define arch_flush_lazy_mmu_mode()      do {} while (0)
 
 /* Local cpu only.  */
 extern void __flush_tlb_all(void);
-
+extern void __flush_tlb_page(unsigned long context, unsigned long vaddr);
 extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #ifndef CONFIG_SMP
@@ -38,15 +54,24 @@ do {	flush_tsb_kernel_range(start,end); \
         __flush_tlb_kernel_range(start,end); \
 } while (0)
 
+static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+        __flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
+}
+
 #else /* CONFIG_SMP */
 
 extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
 
 #define flush_tlb_kernel_range(start, end) \
 do {    flush_tsb_kernel_range(start,end); \
         smp_flush_tlb_kernel_range(start, end); \
 } while (0)
 
+#define global_flush_tlb_page(mm, vaddr) \
+        smp_flush_tlb_page(mm, vaddr)
+
 #endif /* ! CONFIG_SMP */
 
 #endif /* _SPARC64_TLBFLUSH_H */
diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild
index ce175aff71b7..b5843ee09fb5 100644
--- a/arch/sparc/include/uapi/asm/Kbuild
+++ b/arch/sparc/include/uapi/asm/Kbuild
@@ -44,7 +44,6 @@ header-y += swab.h
 header-y += termbits.h
 header-y += termios.h
 header-y += traps.h
-header-y += types.h
 header-y += uctx.h
 header-y += unistd.h
 header-y += utrap.h
diff --git a/arch/sparc/include/uapi/asm/types.h b/arch/sparc/include/uapi/asm/types.h
deleted file mode 100644
index 383d156cde9c..000000000000
--- a/arch/sparc/include/uapi/asm/types.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef _SPARC_TYPES_H
-#define _SPARC_TYPES_H
-/*
- * This file is never included by application software unless
- * explicitly requested (e.g., via linux/types.h) in which case the
- * application is Linux specific so (user-) name space pollution is
- * not a major issue.  However, for interoperability, libraries still
- * need to be careful to avoid a name clashes.
- */
-
-#if defined(__sparc__)
-
-#include <asm-generic/int-ll64.h>
-
-#endif /* defined(__sparc__) */
-
-#endif /* defined(_SPARC_TYPES_H) */
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index a6c94a2bf9d4..5c5125895db8 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -493,6 +493,12 @@ static void __init sun4v_cpu_probe(void)
                 sparc_pmu_type = "niagara5";
                 break;
 
+        case SUN4V_CHIP_SPARC64X:
+                sparc_cpu_type = "SPARC64-X";
+                sparc_fpu_type = "SPARC64-X integrated FPU";
+                sparc_pmu_type = "sparc64-x";
+                break;
+
         default:
                 printk(KERN_WARNING "CPU: Unknown sun4v cpu type [%s]\n",
                        prom_cpu_compatible);
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 2feb15c35d9e..26b706a1867d 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -134,6 +134,8 @@ prom_niagara_prefix:
         .asciz  "SUNW,UltraSPARC-T"
 prom_sparc_prefix:
         .asciz  "SPARC-"
+prom_sparc64x_prefix:
+        .asciz  "SPARC64-X"
         .align  4
 prom_root_compatible:
         .skip   64
@@ -412,7 +414,7 @@ sun4v_chip_type:
         cmp     %g2, 'T'
         be,pt   %xcc, 70f
          cmp    %g2, 'M'
-        bne,pn  %xcc, 4f
+        bne,pn  %xcc, 49f
          nop
 
 70:     ldub    [%g1 + 7], %g2
@@ -425,7 +427,7 @@ sun4v_chip_type:
         cmp     %g2, '5'
         be,pt   %xcc, 5f
          mov    SUN4V_CHIP_NIAGARA5, %g4
-        ba,pt   %xcc, 4f
+        ba,pt   %xcc, 49f
          nop
 
 91:     sethi   %hi(prom_cpu_compatible), %g1
@@ -439,6 +441,25 @@ sun4v_chip_type:
          mov    SUN4V_CHIP_NIAGARA2, %g4
         
 4:
+        /* Athena */
+        sethi   %hi(prom_cpu_compatible), %g1
+        or      %g1, %lo(prom_cpu_compatible), %g1
+        sethi   %hi(prom_sparc64x_prefix), %g7
+        or      %g7, %lo(prom_sparc64x_prefix), %g7
+        mov     9, %g3
+41:     ldub    [%g7], %g2
+        ldub    [%g1], %g4
+        cmp     %g2, %g4
+        bne,pn  %icc, 49f
+        add     %g7, 1, %g7
+        subcc   %g3, 1, %g3
+        bne,pt  %xcc, 41b
+        add     %g1, 1, %g1
+        mov     SUN4V_CHIP_SPARC64X, %g4
+        ba,pt   %xcc, 5f
+        nop
+
+49:
         mov     SUN4V_CHIP_UNKNOWN, %g4
 5:      sethi   %hi(sun4v_chip_type), %g2
         or      %g2, %lo(sun4v_chip_type), %g2
diff --git a/arch/sparc/kernel/hvtramp.S b/arch/sparc/kernel/hvtramp.S
index 9365432904d6..605c960b2fa6 100644
--- a/arch/sparc/kernel/hvtramp.S
+++ b/arch/sparc/kernel/hvtramp.S
@@ -128,8 +128,7 @@ hv_cpu_startup:
 
         call            smp_callin
          nop
-        call            cpu_idle
-         mov            0, %o0
+
         call            cpu_panic
          nop
 
diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c
index fc4320886a3a..4d1487138d26 100644
--- a/arch/sparc/kernel/leon_pci_grpci2.c
+++ b/arch/sparc/kernel/leon_pci_grpci2.c
@@ -186,6 +186,8 @@ struct grpci2_cap_first {
 #define CAP9_IOMAP_OFS 0x20
 #define CAP9_BARSIZE_OFS 0x24
 
+#define TGT 256
+
 struct grpci2_priv {
         struct leon_pci_info    info; /* must be on top of this structure */
         struct grpci2_regs      *regs;
@@ -237,8 +239,12 @@ static int grpci2_cfg_r32(struct grpci2_priv *priv, unsigned int bus,
         if (where & 0x3)
                 return -EINVAL;
 
-        if (bus == 0 && PCI_SLOT(devfn) != 0)
-                devfn += (0x8 * 6);
+        if (bus == 0) {
+                devfn += (0x8 * 6); /* start at AD16=Device0 */
+        } else if (bus == TGT) {
+                bus = 0;
+                devfn = 0; /* special case: bridge controller itself */
+        }
 
         /* Select bus */
         spin_lock_irqsave(&grpci2_dev_lock, flags);
@@ -303,8 +309,12 @@ static int grpci2_cfg_w32(struct grpci2_priv *priv, unsigned int bus,
         if (where & 0x3)
                 return -EINVAL;
 
-        if (bus == 0 && PCI_SLOT(devfn) != 0)
-                devfn += (0x8 * 6);
+        if (bus == 0) {
+                devfn += (0x8 * 6); /* start at AD16=Device0 */
+        } else if (bus == TGT) {
+                bus = 0;
+                devfn = 0; /* special case: bridge controller itself */
+        }
 
         /* Select bus */
         spin_lock_irqsave(&grpci2_dev_lock, flags);
@@ -368,7 +378,7 @@ static int grpci2_read_config(struct pci_bus *bus, unsigned int devfn,
         unsigned int busno = bus->number;
         int ret;
 
-        if (PCI_SLOT(devfn) > 15 || (PCI_SLOT(devfn) == 0 && busno == 0)) {
+        if (PCI_SLOT(devfn) > 15 || busno > 255) {
                 *val = ~0;
                 return 0;
         }
@@ -406,7 +416,7 @@ static int grpci2_write_config(struct pci_bus *bus, unsigned int devfn,
         struct grpci2_priv *priv = grpci2priv;
         unsigned int busno = bus->number;
 
-        if (PCI_SLOT(devfn) > 15 || (PCI_SLOT(devfn) == 0 && busno == 0))
+        if (PCI_SLOT(devfn) > 15 || busno > 255)
                 return 0;
 
 #ifdef GRPCI2_DEBUG_CFGACCESS
@@ -578,15 +588,15 @@ void grpci2_hw_init(struct grpci2_priv *priv)
                 REGSTORE(regs->ahbmst_map[i], priv->pci_area);
 
         /* Get the GRPCI2 Host PCI ID */
-        grpci2_cfg_r32(priv, 0, 0, PCI_VENDOR_ID, &priv->pciid);
+        grpci2_cfg_r32(priv, TGT, 0, PCI_VENDOR_ID, &priv->pciid);
 
         /* Get address to first (always defined) capability structure */
-        grpci2_cfg_r8(priv, 0, 0, PCI_CAPABILITY_LIST, &capptr);
+        grpci2_cfg_r8(priv, TGT, 0, PCI_CAPABILITY_LIST, &capptr);
 
         /* Enable/Disable Byte twisting */
-        grpci2_cfg_r32(priv, 0, 0, capptr+CAP9_IOMAP_OFS, &io_map);
+        grpci2_cfg_r32(priv, TGT, 0, capptr+CAP9_IOMAP_OFS, &io_map);
         io_map = (io_map & ~0x1) | (priv->bt_enabled ? 1 : 0);
-        grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_IOMAP_OFS, io_map);
+        grpci2_cfg_w32(priv, TGT, 0, capptr+CAP9_IOMAP_OFS, io_map);
 
         /* Setup the Host's PCI Target BARs for other peripherals to access,
          * and do DMA to the host's memory. The target BARs can be sized and
@@ -617,17 +627,18 @@ void grpci2_hw_init(struct grpci2_priv *priv)
                                 pciadr = 0;
                         }
                 }
-                grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_BARSIZE_OFS+i*4, bar_sz);
-                grpci2_cfg_w32(priv, 0, 0, PCI_BASE_ADDRESS_0+i*4, pciadr);
-                grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_BAR_OFS+i*4, ahbadr);
+                grpci2_cfg_w32(priv, TGT, 0, capptr+CAP9_BARSIZE_OFS+i*4,
+                                bar_sz);
+                grpci2_cfg_w32(priv, TGT, 0, PCI_BASE_ADDRESS_0+i*4, pciadr);
+                grpci2_cfg_w32(priv, TGT, 0, capptr+CAP9_BAR_OFS+i*4, ahbadr);
                 printk(KERN_INFO "        TGT BAR[%d]: 0x%08x (PCI)-> 0x%08x\n",
                         i, pciadr, ahbadr);
         }
 
         /* set as bus master and enable pci memory responses */
-        grpci2_cfg_r32(priv, 0, 0, PCI_COMMAND, &data);
+        grpci2_cfg_r32(priv, TGT, 0, PCI_COMMAND, &data);
         data |= (PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
-        grpci2_cfg_w32(priv, 0, 0, PCI_COMMAND, data);
+        grpci2_cfg_w32(priv, TGT, 0, PCI_COMMAND, data);
 
         /* Enable Error respone (CPU-TRAP) on illegal memory access. */
         REGSTORE(regs->ctrl, CTRL_ER | CTRL_PE);
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 62eede13831a..c85241006e32 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -64,23 +64,12 @@ extern void fpsave(unsigned long *, unsigned long *, void *, unsigned long *);
 struct task_struct *last_task_used_math = NULL;
 struct thread_info *current_set[NR_CPUS];
 
-/*
- * the idle loop on a Sparc... ;)
- */
-void cpu_idle(void)
+/* Idle loop support. */
+void arch_cpu_idle(void)
 {
-        set_thread_flag(TIF_POLLING_NRFLAG);
-
-        /* endless idle loop with no priority at all */
-        for (;;) {
-                while (!need_resched()) {
-                        if (sparc_idle)
-                                (*sparc_idle)();
-                        else
-                                cpu_relax();
-                }
-                schedule_preempt_disabled();
-        }
+        if (sparc_idle)
+                (*sparc_idle)();
+        local_irq_enable();
 }
 
 /* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index cdb80b2adbe0..9fbf0d14a361 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -52,20 +52,17 @@
 
 #include "kstack.h"
 
-static void sparc64_yield(int cpu)
+/* Idle loop support on sparc64. */
+void arch_cpu_idle(void)
 {
         if (tlb_type != hypervisor) {
                 touch_nmi_watchdog();
-                return;
-        }
-
-        clear_thread_flag(TIF_POLLING_NRFLAG);
-        smp_mb__after_clear_bit();
-
-        while (!need_resched() && !cpu_is_offline(cpu)) {
+        } else {
                 unsigned long pstate;
 
-                /* Disable interrupts. */
+                /* The sun4v sleeping code requires that we have PSTATE.IE cleared over
+                 * the cpu sleep hypervisor call.
+                 */
                 __asm__ __volatile__(
                         "rdpr %%pstate, %0\n\t"
                         "andn %0, %1, %0\n\t"
@@ -73,7 +70,7 @@ static void sparc64_yield(int cpu)
                         : "=&r" (pstate)
                         : "i" (PSTATE_IE));
 
-                if (!need_resched() && !cpu_is_offline(cpu))
+                if (!need_resched() && !cpu_is_offline(smp_processor_id()))
                         sun4v_cpu_yield();
 
                 /* Re-enable interrupts. */
@@ -84,36 +81,16 @@ static void sparc64_yield(int cpu)
                         : "=&r" (pstate)
                         : "i" (PSTATE_IE));
         }
-
-        set_thread_flag(TIF_POLLING_NRFLAG);
+        local_irq_enable();
 }
 
-/* The idle loop on sparc64. */
-void cpu_idle(void)
-{
-        int cpu = smp_processor_id();
-
-        set_thread_flag(TIF_POLLING_NRFLAG);
-
-        while(1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-
-                while (!need_resched() && !cpu_is_offline(cpu))
-                        sparc64_yield(cpu);
-
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-
 #ifdef CONFIG_HOTPLUG_CPU
-                if (cpu_is_offline(cpu)) {
-                        sched_preempt_enable_no_resched();
-                        cpu_play_dead();
-                }
-#endif
-                schedule_preempt_disabled();
-        }
+void arch_cpu_idle_dead()
+{
+        sched_preempt_enable_no_resched();
+        cpu_play_dead();
 }
+#endif
 
 #ifdef CONFIG_COMPAT
 static void show_regwindow32(struct pt_regs *regs)
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c
index 9e7e6d718367..e3f2b81c23f1 100644
--- a/arch/sparc/kernel/smp_32.c
+++ b/arch/sparc/kernel/smp_32.c
@@ -369,7 +369,7 @@ void __cpuinit sparc_start_secondary(void *arg)
         local_irq_enable();
 
         wmb();
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 
         /* We should never reach here! */
         BUG();
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 537eb66abd06..77539eda928c 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -127,6 +127,8 @@ void __cpuinit smp_callin(void)
 
         /* idle thread is expected to have preempt disabled */
         preempt_disable();
+
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 void cpu_panic(void)
@@ -849,7 +851,7 @@ void smp_tsb_sync(struct mm_struct *mm)
 }
 
 extern unsigned long xcall_flush_tlb_mm;
-extern unsigned long xcall_flush_tlb_pending;
+extern unsigned long xcall_flush_tlb_page;
 extern unsigned long xcall_flush_tlb_kernel_range;
 extern unsigned long xcall_fetch_glob_regs;
 extern unsigned long xcall_fetch_glob_pmu;
@@ -1074,23 +1076,56 @@ local_flush_and_out:
         put_cpu();
 }
 
+struct tlb_pending_info {
+        unsigned long ctx;
+        unsigned long nr;
+        unsigned long *vaddrs;
+};
+
+static void tlb_pending_func(void *info)
+{
+        struct tlb_pending_info *t = info;
+
+        __flush_tlb_pending(t->ctx, t->nr, t->vaddrs);
+}
+
 void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs)
 {
         u32 ctx = CTX_HWBITS(mm->context);
+        struct tlb_pending_info info;
         int cpu = get_cpu();
 
+        info.ctx = ctx;
+        info.nr = nr;
+        info.vaddrs = vaddrs;
+
         if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
                 cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
         else
-                smp_cross_call_masked(&xcall_flush_tlb_pending,
-                                      ctx, nr, (unsigned long) vaddrs,
-                                      mm_cpumask(mm));
+                smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
+                                       &info, 1);
 
         __flush_tlb_pending(ctx, nr, vaddrs);
 
         put_cpu();
 }
 
+void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+        unsigned long context = CTX_HWBITS(mm->context);
+        int cpu = get_cpu();
+
+        if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
+                cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
+        else
+                smp_cross_call_masked(&xcall_flush_tlb_page,
+                                      context, vaddr, 0,
+                                      mm_cpumask(mm));
+        __flush_tlb_page(context, vaddr);
+
+        put_cpu();
+}
+
 void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
         start &= PAGE_MASK;
diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S
index da1b781b5e65..2e973a26fbda 100644
--- a/arch/sparc/kernel/trampoline_64.S
+++ b/arch/sparc/kernel/trampoline_64.S
@@ -407,8 +407,7 @@ after_lock_tlb:
 
         call            smp_callin
          nop
-        call            cpu_idle
-         mov            0, %o0
+
         call            cpu_panic
          nop
 1:      b,a,pt          %xcc, 1b
diff --git a/arch/sparc/lib/bitext.c b/arch/sparc/lib/bitext.c
index 48d00e72ce15..8ec4e9c0251a 100644
--- a/arch/sparc/lib/bitext.c
+++ b/arch/sparc/lib/bitext.c
@@ -119,11 +119,7 @@ void bit_map_clear(struct bit_map *t, int offset, int len)
 
 void bit_map_init(struct bit_map *t, unsigned long *map, int size)
 {
-
-        if ((size & 07) != 0)
-                BUG();
-        memset(map, 0, size>>3);
-
+        bitmap_zero(map, size);
         memset(t, 0, sizeof *t);
         spin_lock_init(&t->lock);
         t->map = map;
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index 48e0c030e8f5..4490c397bb5b 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -282,14 +282,8 @@ static void map_high_region(unsigned long start_pfn, unsigned long end_pfn)
         printk("mapping high region %08lx - %08lx\n", start_pfn, end_pfn);
 #endif
 
-        for (tmp = start_pfn; tmp < end_pfn; tmp++) {
-                struct page *page = pfn_to_page(tmp);
-
-                ClearPageReserved(page);
-                init_page_count(page);
-                __free_page(page);
-                totalhigh_pages++;
-        }
+        for (tmp = start_pfn; tmp < end_pfn; tmp++)
+                free_highmem_page(pfn_to_page(tmp));
 }
 
 void __init mem_init(void)
@@ -347,8 +341,6 @@ void __init mem_init(void)
                 map_high_region(start_pfn, end_pfn);
         }
         
-        totalram_pages += totalhigh_pages;
-
         codepages = (((unsigned long) &_etext) - ((unsigned long)&_start));
         codepages = PAGE_ALIGN(codepages) >> PAGE_SHIFT;
         datapages = (((unsigned long) &_edata) - ((unsigned long)&_etext));
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 1588d33d5492..6ac99d64a13c 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2181,10 +2181,9 @@ unsigned long vmemmap_table[VMEMMAP_SIZE];
 static long __meminitdata addr_start, addr_end;
 static int __meminitdata node_start;
 
-int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
+int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
+                               int node)
 {
-        unsigned long vstart = (unsigned long) start;
-        unsigned long vend = (unsigned long) (start + nr);
         unsigned long phys_start = (vstart - VMEMMAP_BASE);
         unsigned long phys_end = (vend - VMEMMAP_BASE);
         unsigned long addr = phys_start & VMEMMAP_CHUNK_MASK;
@@ -2236,7 +2235,7 @@ void __meminit vmemmap_populate_print_last(void)
         }
 }
 
-void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+void vmemmap_free(unsigned long start, unsigned long end)
 {
 }
 
diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c
index 0f4f7191fbba..28f96f27c768 100644
--- a/arch/sparc/mm/iommu.c
+++ b/arch/sparc/mm/iommu.c
@@ -34,7 +34,7 @@
 #define IOMMU_RNGE      IOMMU_RNGE_256MB
 #define IOMMU_START     0xF0000000
 #define IOMMU_WINSIZE   (256*1024*1024U)
-#define IOMMU_NPTES     (IOMMU_WINSIZE/PAGE_SIZE)       /* 64K PTEs, 265KB */
+#define IOMMU_NPTES     (IOMMU_WINSIZE/PAGE_SIZE)       /* 64K PTEs, 256KB */
 #define IOMMU_ORDER     6                               /* 4096 * (1<<6) */
 
 /* srmmu.c */
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index c38bb72e3e80..036c2797dece 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -280,7 +280,9 @@ static void __init srmmu_nocache_init(void)
                 SRMMU_NOCACHE_ALIGN_MAX, 0UL);
         memset(srmmu_nocache_pool, 0, srmmu_nocache_size);
 
-        srmmu_nocache_bitmap = __alloc_bootmem(bitmap_bits >> 3, SMP_CACHE_BYTES, 0UL);
+        srmmu_nocache_bitmap =
+                __alloc_bootmem(BITS_TO_LONGS(bitmap_bits) * sizeof(long),
+                                SMP_CACHE_BYTES, 0UL);
         bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits);
 
         srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE);
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index ba6ae7ffdc2c..83d89bcb44af 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, tlb_batch);
 void flush_tlb_pending(void)
 {
         struct tlb_batch *tb = &get_cpu_var(tlb_batch);
+        struct mm_struct *mm = tb->mm;
 
-        if (tb->tlb_nr) {
-                flush_tsb_user(tb);
+        if (!tb->tlb_nr)
+                goto out;
 
-                if (CTX_VALID(tb->mm->context)) {
+        flush_tsb_user(tb);
+
+        if (CTX_VALID(mm->context)) {
+                if (tb->tlb_nr == 1) {
+                        global_flush_tlb_page(mm, tb->vaddrs[0]);
+                } else {
 #ifdef CONFIG_SMP
                         smp_flush_tlb_pending(tb->mm, tb->tlb_nr,
                                               &tb->vaddrs[0]);
@@ -37,12 +43,30 @@ void flush_tlb_pending(void)
                                             tb->tlb_nr, &tb->vaddrs[0]);
 #endif
                 }
-                tb->tlb_nr = 0;
         }
 
+        tb->tlb_nr = 0;
+
+out:
         put_cpu_var(tlb_batch);
 }
 
+void arch_enter_lazy_mmu_mode(void)
+{
+        struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+        tb->active = 1;
+}
+
+void arch_leave_lazy_mmu_mode(void)
+{
+        struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+        if (tb->tlb_nr)
+                flush_tlb_pending();
+        tb->active = 0;
+}
+
 static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
                               bool exec)
 {
@@ -60,6 +84,12 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
                 nr = 0;
         }
 
+        if (!tb->active) {
+                global_flush_tlb_page(mm, vaddr);
+                flush_tsb_user_page(mm, vaddr);
+                goto out;
+        }
+
         if (nr == 0)
                 tb->mm = mm;
 
@@ -68,6 +98,7 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
         if (nr >= TLB_BATCH_NR)
                 flush_tlb_pending();
 
+out:
         put_cpu_var(tlb_batch);
 }
 
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 428982b9becf..2cc3bce5ee91 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -7,11 +7,10 @@
 #include <linux/preempt.h>
 #include <linux/slab.h>
 #include <asm/page.h>
-#include <asm/tlbflush.h>
-#include <asm/tlb.h>
-#include <asm/mmu_context.h>
 #include <asm/pgtable.h>
+#include <asm/mmu_context.h>
 #include <asm/tsb.h>
+#include <asm/tlb.h>
 #include <asm/oplib.h>
 
 extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
@@ -46,23 +45,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
         }
 }
 
-static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
-                            unsigned long tsb, unsigned long nentries)
+static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v,
+                                  unsigned long hash_shift,
+                                  unsigned long nentries)
 {
-        unsigned long i;
+        unsigned long tag, ent, hash;
 
-        for (i = 0; i < tb->tlb_nr; i++) {
-                unsigned long v = tb->vaddrs[i];
-                unsigned long tag, ent, hash;
+        v &= ~0x1UL;
+        hash = tsb_hash(v, hash_shift, nentries);
+        ent = tsb + (hash * sizeof(struct tsb));
+        tag = (v >> 22UL);
 
-                v &= ~0x1UL;
+        tsb_flush(ent, tag);
+}
 
-                hash = tsb_hash(v, hash_shift, nentries);
-                ent = tsb + (hash * sizeof(struct tsb));
-                tag = (v >> 22UL);
+static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
+                            unsigned long tsb, unsigned long nentries)
+{
+        unsigned long i;
 
-                tsb_flush(ent, tag);
-        }
+        for (i = 0; i < tb->tlb_nr; i++)
+                __flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries);
 }
 
 void flush_tsb_user(struct tlb_batch *tb)
@@ -90,6 +93,30 @@ void flush_tsb_user(struct tlb_batch *tb)
         spin_unlock_irqrestore(&mm->context.lock, flags);
 }
 
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr)
+{
+        unsigned long nentries, base, flags;
+
+        spin_lock_irqsave(&mm->context.lock, flags);
+
+        base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+        nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+        if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+                base = __pa(base);
+        __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
+
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+        if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+                base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
+                nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
+                if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+                        base = __pa(base);
+                __flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries);
+        }
+#endif
+        spin_unlock_irqrestore(&mm->context.lock, flags);
+}
+
 #define HV_PGSZ_IDX_BASE        HV_PGSZ_IDX_8K
 #define HV_PGSZ_MASK_BASE       HV_PGSZ_MASK_8K
 
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index f8e13d421fcb..432aa0cb1b38 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -53,6 +53,33 @@ __flush_tlb_mm:		/* 18 insns */
         nop
 
         .align          32
+        .globl          __flush_tlb_page
+__flush_tlb_page:       /* 22 insns */
+        /* %o0 = context, %o1 = vaddr */
+        rdpr            %pstate, %g7
+        andn            %g7, PSTATE_IE, %g2
+        wrpr            %g2, %pstate
+        mov             SECONDARY_CONTEXT, %o4
+        ldxa            [%o4] ASI_DMMU, %g2
+        stxa            %o0, [%o4] ASI_DMMU
+        andcc           %o1, 1, %g0
+        andn            %o1, 1, %o3
+        be,pn           %icc, 1f
+         or             %o3, 0x10, %o3
+        stxa            %g0, [%o3] ASI_IMMU_DEMAP
+1:      stxa            %g0, [%o3] ASI_DMMU_DEMAP
+        membar          #Sync
+        stxa            %g2, [%o4] ASI_DMMU
+        sethi           %hi(KERNBASE), %o4
+        flush           %o4
+        retl
+         wrpr           %g7, 0x0, %pstate
+        nop
+        nop
+        nop
+        nop
+
+        .align          32
         .globl          __flush_tlb_pending
 __flush_tlb_pending:    /* 26 insns */
         /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
@@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */
         retl
          wrpr           %g7, 0x0, %pstate
 
+__cheetah_flush_tlb_page:       /* 22 insns */
+        /* %o0 = context, %o1 = vaddr */
+        rdpr            %pstate, %g7
+        andn            %g7, PSTATE_IE, %g2
+        wrpr            %g2, 0x0, %pstate
+        wrpr            %g0, 1, %tl
+        mov             PRIMARY_CONTEXT, %o4
+        ldxa            [%o4] ASI_DMMU, %g2
+        srlx            %g2, CTX_PGSZ1_NUC_SHIFT, %o3
+        sllx            %o3, CTX_PGSZ1_NUC_SHIFT, %o3
+        or              %o0, %o3, %o0   /* Preserve nucleus page size fields */
+        stxa            %o0, [%o4] ASI_DMMU
+        andcc           %o1, 1, %g0
+        be,pn           %icc, 1f
+         andn           %o1, 1, %o3
+        stxa            %g0, [%o3] ASI_IMMU_DEMAP
+1:      stxa            %g0, [%o3] ASI_DMMU_DEMAP       
+        membar          #Sync
+        stxa            %g2, [%o4] ASI_DMMU
+        sethi           %hi(KERNBASE), %o4
+        flush           %o4
+        wrpr            %g0, 0, %tl
+        retl
+         wrpr           %g7, 0x0, %pstate
+
 __cheetah_flush_tlb_pending:    /* 27 insns */
         /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
         rdpr            %pstate, %g7
@@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns */
         retl
          nop
 
+__hypervisor_flush_tlb_page: /* 11 insns */
+        /* %o0 = context, %o1 = vaddr */
+        mov             %o0, %g2
+        mov             %o1, %o0              /* ARG0: vaddr + IMMU-bit */
+        mov             %g2, %o1              /* ARG1: mmu context */
+        mov             HV_MMU_ALL, %o2       /* ARG2: flags */
+        srlx            %o0, PAGE_SHIFT, %o0
+        sllx            %o0, PAGE_SHIFT, %o0
+        ta              HV_MMU_UNMAP_ADDR_TRAP
+        brnz,pn         %o0, __hypervisor_tlb_tl0_error
+         mov            HV_MMU_UNMAP_ADDR_TRAP, %o1
+        retl
+         nop
+
 __hypervisor_flush_tlb_pending: /* 16 insns */
         /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
         sllx            %o1, 3, %g1
@@ -339,6 +405,13 @@ cheetah_patch_cachetlbops:
         call            tlb_patch_one
          mov            19, %o2
 
+        sethi           %hi(__flush_tlb_page), %o0
+        or              %o0, %lo(__flush_tlb_page), %o0
+        sethi           %hi(__cheetah_flush_tlb_page), %o1
+        or              %o1, %lo(__cheetah_flush_tlb_page), %o1
+        call            tlb_patch_one
+         mov            22, %o2
+
         sethi           %hi(__flush_tlb_pending), %o0
         or              %o0, %lo(__flush_tlb_pending), %o0
         sethi           %hi(__cheetah_flush_tlb_pending), %o1
@@ -397,10 +470,9 @@ xcall_flush_tlb_mm:	/* 21 insns */
         nop
         nop
 
-        .globl          xcall_flush_tlb_pending
-xcall_flush_tlb_pending:        /* 21 insns */
-        /* %g5=context, %g1=nr, %g7=vaddrs[] */
-        sllx            %g1, 3, %g1
+        .globl          xcall_flush_tlb_page
+xcall_flush_tlb_page:   /* 17 insns */
+        /* %g5=context, %g1=vaddr */
         mov             PRIMARY_CONTEXT, %g4
         ldxa            [%g4] ASI_DMMU, %g2
         srlx            %g2, CTX_PGSZ1_NUC_SHIFT, %g4
@@ -408,20 +480,16 @@ xcall_flush_tlb_pending:	/* 21 insns */
         or              %g5, %g4, %g5
         mov             PRIMARY_CONTEXT, %g4
         stxa            %g5, [%g4] ASI_DMMU
-1:      sub             %g1, (1 << 3), %g1
-        ldx             [%g7 + %g1], %g5
-        andcc           %g5, 0x1, %g0
+        andcc           %g1, 0x1, %g0
         be,pn           %icc, 2f
-
-         andn           %g5, 0x1, %g5
+         andn           %g1, 0x1, %g5
         stxa            %g0, [%g5] ASI_IMMU_DEMAP
 2:      stxa            %g0, [%g5] ASI_DMMU_DEMAP
         membar          #Sync
-        brnz,pt         %g1, 1b
-         nop
         stxa            %g2, [%g4] ASI_DMMU
         retry
         nop
+        nop
 
         .globl          xcall_flush_tlb_kernel_range
 xcall_flush_tlb_kernel_range:   /* 25 insns */
@@ -656,15 +724,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
         membar          #Sync
         retry
 
-        .globl          __hypervisor_xcall_flush_tlb_pending
-__hypervisor_xcall_flush_tlb_pending: /* 21 insns */
-        /* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */
-        sllx            %g1, 3, %g1
+        .globl          __hypervisor_xcall_flush_tlb_page
+__hypervisor_xcall_flush_tlb_page: /* 17 insns */
+        /* %g5=ctx, %g1=vaddr */
         mov             %o0, %g2
         mov             %o1, %g3
         mov             %o2, %g4
-1:      sub             %g1, (1 << 3), %g1
-        ldx             [%g7 + %g1], %o0        /* ARG0: virtual address */
+        mov             %g1, %o0                /* ARG0: virtual address */
         mov             %g5, %o1                /* ARG1: mmu context */
         mov             HV_MMU_ALL, %o2         /* ARG2: flags */
         srlx            %o0, PAGE_SHIFT, %o0
@@ -673,8 +739,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */
         mov             HV_MMU_UNMAP_ADDR_TRAP, %g6
         brnz,a,pn       %o0, __hypervisor_tlb_xcall_error
          mov            %o0, %g5
-        brnz,pt         %g1, 1b
-         nop
         mov             %g2, %o0
         mov             %g3, %o1
         mov             %g4, %o2
@@ -757,6 +821,13 @@ hypervisor_patch_cachetlbops:
         call            tlb_patch_one
          mov            10, %o2
 
+        sethi           %hi(__flush_tlb_page), %o0
+        or              %o0, %lo(__flush_tlb_page), %o0
+        sethi           %hi(__hypervisor_flush_tlb_page), %o1
+        or              %o1, %lo(__hypervisor_flush_tlb_page), %o1
+        call            tlb_patch_one
+         mov            11, %o2
+
         sethi           %hi(__flush_tlb_pending), %o0
         or              %o0, %lo(__flush_tlb_pending), %o0
         sethi           %hi(__hypervisor_flush_tlb_pending), %o1
@@ -788,12 +859,12 @@ hypervisor_patch_cachetlbops:
         call            tlb_patch_one
          mov            21, %o2
 
-        sethi           %hi(xcall_flush_tlb_pending), %o0
-        or              %o0, %lo(xcall_flush_tlb_pending), %o0
-        sethi           %hi(__hypervisor_xcall_flush_tlb_pending), %o1
-        or              %o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1
+        sethi           %hi(xcall_flush_tlb_page), %o0
+        or              %o0, %lo(xcall_flush_tlb_page), %o0
+        sethi           %hi(__hypervisor_xcall_flush_tlb_page), %o1
+        or              %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1
         call            tlb_patch_one
-         mov            21, %o2
+         mov            17, %o2
 
         sethi           %hi(xcall_flush_tlb_kernel_range), %o0
         or              %o0, %lo(xcall_flush_tlb_kernel_range), %o0
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index ff496ab1e794..25877aebc685 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -17,7 +17,7 @@ config TILE
         select GENERIC_IRQ_SHOW
         select HAVE_DEBUG_BUGVERBOSE
         select HAVE_SYSCALL_WRAPPERS if TILEGX
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select SYS_HYPERVISOR
         select ARCH_HAVE_NMI_SAFE_CMPXCHG
         select GENERIC_CLOCKEVENTS
diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig
index 8c5eff6d6df5..47684815e5c8 100644
--- a/arch/tile/configs/tilegx_defconfig
+++ b/arch/tile/configs/tilegx_defconfig
@@ -330,7 +330,6 @@ CONFIG_MD_RAID0=m
 CONFIG_MD_RAID1=m
 CONFIG_MD_RAID10=m
 CONFIG_MD_RAID456=m
-CONFIG_MULTICORE_RAID456=y
 CONFIG_MD_FAULTY=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_DEBUG=y
diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig
index e7a3dfcbcda7..dd2b8f0c631f 100644
--- a/arch/tile/configs/tilepro_defconfig
+++ b/arch/tile/configs/tilepro_defconfig
@@ -324,7 +324,6 @@ CONFIG_MD_RAID0=m
 CONFIG_MD_RAID1=m
 CONFIG_MD_RAID10=m
 CONFIG_MD_RAID456=m
-CONFIG_MULTICORE_RAID456=y
 CONFIG_MD_FAULTY=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_DEBUG=y
diff --git a/arch/tile/include/asm/hugetlb.h b/arch/tile/include/asm/hugetlb.h
index 0f885af2b621..3257733003f8 100644
--- a/arch/tile/include/asm/hugetlb.h
+++ b/arch/tile/include/asm/hugetlb.h
@@ -16,6 +16,7 @@
 #define _ASM_TILE_HUGETLB_H
 
 #include <asm/page.h>
+#include <asm-generic/hugetlb.h>
 
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h
index 241c0bb60b12..c96f9bbb760d 100644
--- a/arch/tile/include/asm/irqflags.h
+++ b/arch/tile/include/asm/irqflags.h
@@ -40,7 +40,15 @@
 #include <asm/percpu.h>
 #include <arch/spr_def.h>
 
-/* Set and clear kernel interrupt masks. */
+/*
+ * Set and clear kernel interrupt masks.
+ *
+ * NOTE: __insn_mtspr() is a compiler builtin marked as a memory
+ * clobber.  We rely on it being equivalent to a compiler barrier in
+ * this code since arch_local_irq_save() and friends must act as
+ * compiler barriers.  This compiler semantic is baked into enough
+ * places that the compiler will maintain it going forward.
+ */
 #if CHIP_HAS_SPLIT_INTR_MASK()
 #if INT_PERF_COUNT < 32 || INT_AUX_PERF_COUNT < 32 || INT_MEM_ERROR >= 32
 # error Fix assumptions about which word various interrupts are in
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index e9c670d7a7fe..ccc8ef37235c 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -153,8 +153,6 @@ extern void _cpu_idle(void);
 #define TS_POLLING              0x0004  /* in idle loop but not sleeping */
 #define TS_RESTORE_SIGMASK      0x0008  /* restore signal mask in do_signal */
 
-#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
-
 #ifndef __ASSEMBLY__
 #define HAVE_SET_RESTORE_SIGMASK        1
 static inline void set_restore_sigmask(void)
diff --git a/arch/tile/kernel/early_printk.c b/arch/tile/kernel/early_printk.c
index afb9c9a0d887..34d72a151bf3 100644
--- a/arch/tile/kernel/early_printk.c
+++ b/arch/tile/kernel/early_printk.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/irqflags.h>
+#include <linux/printk.h>
 #include <asm/setup.h>
 #include <hv/hypervisor.h>
 
@@ -33,25 +34,8 @@ static struct console early_hv_console = {
 };
 
 /* Direct interface for emergencies */
-static struct console *early_console = &early_hv_console;
-static int early_console_initialized;
 static int early_console_complete;
 
-static void early_vprintk(const char *fmt, va_list ap)
-{
-        char buf[512];
-        int n = vscnprintf(buf, sizeof(buf), fmt, ap);
-        early_console->write(early_console, buf, n);
-}
-
-void early_printk(const char *fmt, ...)
-{
-        va_list ap;
-        va_start(ap, fmt);
-        early_vprintk(fmt, ap);
-        va_end(ap);
-}
-
 void early_panic(const char *fmt, ...)
 {
         va_list ap;
@@ -69,14 +53,13 @@ static int __initdata keep_early;
 
 static int __init setup_early_printk(char *str)
 {
-        if (early_console_initialized)
+        if (early_console)
                 return 1;
 
         if (str != NULL && strncmp(str, "keep", 4) == 0)
                 keep_early = 1;
 
         early_console = &early_hv_console;
-        early_console_initialized = 1;
         register_console(early_console);
 
         return 0;
@@ -85,12 +68,12 @@ static int __init setup_early_printk(char *str)
 void __init disable_early_printk(void)
 {
         early_console_complete = 1;
-        if (!early_console_initialized || !early_console)
+        if (!early_console)
                 return;
         if (!keep_early) {
                 early_printk("disabling early console\n");
                 unregister_console(early_console);
-                early_console_initialized = 0;
+                early_console = NULL;
         } else {
                 early_printk("keeping early console\n");
         }
@@ -98,7 +81,7 @@ void __init disable_early_printk(void)
 
 void warn_early_printk(void)
 {
-        if (early_console_complete || early_console_initialized)
+        if (early_console_complete || early_console)
                 return;
         early_printk("\
 Machine shutting down before console output is fully initialized.\n\
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index caf93ae11793..80b2a18deb87 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -40,13 +40,11 @@
 #include <arch/abi.h>
 #include <arch/sim_def.h>
 
-
 /*
  * Use the (x86) "idle=poll" option to prefer low latency when leaving the
  * idle loop over low power while in the idle loop, e.g. if we have
  * one thread per core and we want to get threads out of futex waits fast.
  */
-static int no_idle_nap;
 static int __init idle_setup(char *str)
 {
         if (!str)
@@ -54,64 +52,19 @@ static int __init idle_setup(char *str)
 
         if (!strcmp(str, "poll")) {
                 pr_info("using polling idle threads.\n");
-                no_idle_nap = 1;
-        } else if (!strcmp(str, "halt"))
-                no_idle_nap = 0;
-        else
-                return -1;
-
-        return 0;
+                cpu_idle_poll_ctrl(true);
+                return 0;
+        } else if (!strcmp(str, "halt")) {
+                return 0;
+        }
+        return -1;
 }
 early_param("idle", idle_setup);
 
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
+void arch_cpu_idle(void)
 {
-        int cpu = smp_processor_id();
-
-
-        current_thread_info()->status |= TS_POLLING;
-
-        if (no_idle_nap) {
-                while (1) {
-                        while (!need_resched())
-                                cpu_relax();
-                        schedule();
-                }
-        }
-
-        /* endless idle loop with no priority at all */
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                while (!need_resched()) {
-                        if (cpu_is_offline(cpu))
-                                BUG();  /* no HOTPLUG_CPU */
-
-                        local_irq_disable();
-                        __get_cpu_var(irq_stat).idle_timestamp = jiffies;
-                        current_thread_info()->status &= ~TS_POLLING;
-                        /*
-                         * TS_POLLING-cleared state must be visible before we
-                         * test NEED_RESCHED:
-                         */
-                        smp_mb();
-
-                        if (!need_resched())
-                                _cpu_idle();
-                        else
-                                local_irq_enable();
-                        current_thread_info()->status |= TS_POLLING;
-                }
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                schedule_preempt_disabled();
-        }
+        __get_cpu_var(irq_stat).idle_timestamp = jiffies;
+        _cpu_idle();
 }
 
 /*
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index d1e15f7b59c6..7a5aa1a7864e 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -1004,15 +1004,8 @@ void __cpuinit setup_cpu(int boot)
 
 #ifdef CONFIG_BLK_DEV_INITRD
 
-/*
- * Note that the kernel can potentially support other compression
- * techniques than gz, though we don't do so by default.  If we ever
- * decide to do so we can either look for other filename extensions,
- * or just allow a file with this name to be compressed with an
- * arbitrary compressor (somewhat counterintuitively).
- */
 static int __initdata set_initramfs_file;
-static char __initdata initramfs_file[128] = "initramfs.cpio.gz";
+static char __initdata initramfs_file[128] = "initramfs";
 
 static int __init setup_initramfs_file(char *str)
 {
@@ -1026,9 +1019,9 @@ static int __init setup_initramfs_file(char *str)
 early_param("initramfs_file", setup_initramfs_file);
 
 /*
- * We look for an "initramfs.cpio.gz" file in the hvfs.
- * If there is one, we allocate some memory for it and it will be
- * unpacked to the initramfs.
+ * We look for a file called "initramfs" in the hvfs.  If there is one, we
+ * allocate some memory for it and it will be unpacked to the initramfs.
+ * If it's compressed, the initd code will uncompress it first.
  */
 static void __init load_hv_initrd(void)
 {
@@ -1038,10 +1031,16 @@ static void __init load_hv_initrd(void)
 
         fd = hv_fs_findfile((HV_VirtAddr) initramfs_file);
         if (fd == HV_ENOENT) {
-                if (set_initramfs_file)
+                if (set_initramfs_file) {
                         pr_warning("No such hvfs initramfs file '%s'\n",
                                    initramfs_file);
-                return;
+                        return;
+                } else {
+                        /* Try old backwards-compatible name. */
+                        fd = hv_fs_findfile((HV_VirtAddr)"initramfs.cpio.gz");
+                        if (fd == HV_ENOENT)
+                                return;
+                }
         }
         BUG_ON(fd < 0);
         stat = hv_fs_fstat(fd);
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index e686c5ac90be..44bab29bf2f3 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -207,9 +207,7 @@ void __cpuinit online_secondary(void)
         /* Set up tile-timer clock-event device on this cpu */
         setup_tile_timer();
 
-        preempt_enable();
-
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle)
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index b3b4972c2451..dfd63ce87327 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -592,12 +592,7 @@ void iounmap(volatile void __iomem *addr_in)
            in parallel. Reuse of the virtual address is prevented by
            leaving it in the global lists until we're done with it.
            cpa takes care of the direct mappings. */
-        read_lock(&vmlist_lock);
-        for (p = vmlist; p; p = p->next) {
-                if (p->addr == addr)
-                        break;
-        }
-        read_unlock(&vmlist_lock);
+        p = find_vm_area((void *)addr);
 
         if (!p) {
                 pr_err("iounmap: bad address %p\n", addr);
diff --git a/arch/um/drivers/chan.h b/arch/um/drivers/chan.h
index 78f1b8999964..c512b0306dd4 100644
--- a/arch/um/drivers/chan.h
+++ b/arch/um/drivers/chan.h
@@ -37,7 +37,7 @@ extern int console_write_chan(struct chan *chan, const char *buf,
 extern int console_open_chan(struct line *line, struct console *co);
 extern void deactivate_chan(struct chan *chan, int irq);
 extern void reactivate_chan(struct chan *chan, int irq);
-extern void chan_enable_winch(struct chan *chan, struct tty_struct *tty);
+extern void chan_enable_winch(struct chan *chan, struct tty_port *port);
 extern int enable_chan(struct line *line);
 extern void close_chan(struct line *line);
 extern int chan_window_size(struct line *line, 
diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c
index 15c553c239a1..acbe6c67afba 100644
--- a/arch/um/drivers/chan_kern.c
+++ b/arch/um/drivers/chan_kern.c
@@ -122,10 +122,10 @@ static int open_chan(struct list_head *chans)
         return err;
 }
 
-void chan_enable_winch(struct chan *chan, struct tty_struct *tty)
+void chan_enable_winch(struct chan *chan, struct tty_port *port)
 {
         if (chan && chan->primary && chan->ops->winch)
-                register_winch(chan->fd, tty);
+                register_winch(chan->fd, port);
 }
 
 static void line_timer_cb(struct work_struct *work)
@@ -568,11 +568,7 @@ void chan_interrupt(struct line *line, int irq)
                 reactivate_fd(chan->fd, irq);
         if (err == -EIO) {
                 if (chan->primary) {
-                        struct tty_struct *tty = tty_port_tty_get(&line->port);
-                        if (tty != NULL) {
-                                tty_hangup(tty);
-                                tty_kref_put(tty);
-                        }
+                        tty_port_tty_hangup(&line->port, false);
                         if (line->chan_out != chan)
                                 close_one_chan(line->chan_out, 1);
                 }
diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c
index 9be670ad23b5..3fd7c3efdb18 100644
--- a/arch/um/drivers/chan_user.c
+++ b/arch/um/drivers/chan_user.c
@@ -216,7 +216,7 @@ static int winch_thread(void *arg)
         }
 }
 
-static int winch_tramp(int fd, struct tty_struct *tty, int *fd_out,
+static int winch_tramp(int fd, struct tty_port *port, int *fd_out,
                        unsigned long *stack_out)
 {
         struct winch_data data;
@@ -271,7 +271,7 @@ static int winch_tramp(int fd, struct tty_struct *tty, int *fd_out,
         return err;
 }
 
-void register_winch(int fd, struct tty_struct *tty)
+void register_winch(int fd, struct tty_port *port)
 {
         unsigned long stack;
         int pid, thread, count, thread_fd = -1;
@@ -281,17 +281,17 @@ void register_winch(int fd, struct tty_struct *tty)
                 return;
 
         pid = tcgetpgrp(fd);
-        if (is_skas_winch(pid, fd, tty)) {
-                register_winch_irq(-1, fd, -1, tty, 0);
+        if (is_skas_winch(pid, fd, port)) {
+                register_winch_irq(-1, fd, -1, port, 0);
                 return;
         }
 
         if (pid == -1) {
-                thread = winch_tramp(fd, tty, &thread_fd, &stack);
+                thread = winch_tramp(fd, port, &thread_fd, &stack);
                 if (thread < 0)
                         return;
 
-                register_winch_irq(thread_fd, fd, thread, tty, stack);
+                register_winch_irq(thread_fd, fd, thread, port, stack);
 
                 count = write(thread_fd, &c, sizeof(c));
                 if (count != sizeof(c))
diff --git a/arch/um/drivers/chan_user.h b/arch/um/drivers/chan_user.h
index dc693298eb8f..03f1b565c5f9 100644
--- a/arch/um/drivers/chan_user.h
+++ b/arch/um/drivers/chan_user.h
@@ -38,10 +38,10 @@ extern int generic_window_size(int fd, void *unused, unsigned short *rows_out,
                                unsigned short *cols_out);
 extern void generic_free(void *data);
 
-struct tty_struct;
-extern void register_winch(int fd,  struct tty_struct *tty);
+struct tty_port;
+extern void register_winch(int fd,  struct tty_port *port);
 extern void register_winch_irq(int fd, int tty_fd, int pid,
-                               struct tty_struct *tty, unsigned long stack);
+                               struct tty_port *port, unsigned long stack);
 
 #define __channel_help(fn, prefix) \
 __uml_help(fn, prefix "[0-9]*=<channel description>\n" \
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index f1b38571f94e..8035145f043b 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -248,7 +248,6 @@ static irqreturn_t line_write_interrupt(int irq, void *data)
 {
         struct chan *chan = data;
         struct line *line = chan->line;
-        struct tty_struct *tty;
         int err;
 
         /*
@@ -267,12 +266,7 @@ static irqreturn_t line_write_interrupt(int irq, void *data)
         }
         spin_unlock(&line->lock);
 
-        tty = tty_port_tty_get(&line->port);
-        if (tty == NULL)
-                return IRQ_NONE;
-
-        tty_wakeup(tty);
-        tty_kref_put(tty);
+        tty_port_tty_wakeup(&line->port);
 
         return IRQ_HANDLED;
 }
@@ -305,7 +299,7 @@ static int line_activate(struct tty_port *port, struct tty_struct *tty)
                 return ret;
 
         if (!line->sigio) {
-                chan_enable_winch(line->chan_out, tty);
+                chan_enable_winch(line->chan_out, port);
                 line->sigio = 1;
         }
 
@@ -315,8 +309,22 @@ static int line_activate(struct tty_port *port, struct tty_struct *tty)
         return 0;
 }
 
+static void unregister_winch(struct tty_struct *tty);
+
+static void line_destruct(struct tty_port *port)
+{
+        struct tty_struct *tty = tty_port_tty_get(port);
+        struct line *line = tty->driver_data;
+
+        if (line->sigio) {
+                unregister_winch(tty);
+                line->sigio = 0;
+        }
+}
+
 static const struct tty_port_operations line_port_ops = {
         .activate = line_activate,
+        .destruct = line_destruct,
 };
 
 int line_open(struct tty_struct *tty, struct file *filp)
@@ -340,18 +348,6 @@ int line_install(struct tty_driver *driver, struct tty_struct *tty,
         return 0;
 }
 
-static void unregister_winch(struct tty_struct *tty);
-
-void line_cleanup(struct tty_struct *tty)
-{
-        struct line *line = tty->driver_data;
-
-        if (line->sigio) {
-                unregister_winch(tty);
-                line->sigio = 0;
-        }
-}
-
 void line_close(struct tty_struct *tty, struct file * filp)
 {
         struct line *line = tty->driver_data;
@@ -601,7 +597,7 @@ struct winch {
         int fd;
         int tty_fd;
         int pid;
-        struct tty_struct *tty;
+        struct tty_port *port;
         unsigned long stack;
         struct work_struct work;
 };
@@ -655,7 +651,7 @@ static irqreturn_t winch_interrupt(int irq, void *data)
                         goto out;
                 }
         }
-        tty = winch->tty;
+        tty = tty_port_tty_get(winch->port);
         if (tty != NULL) {
                 line = tty->driver_data;
                 if (line != NULL) {
@@ -663,6 +659,7 @@ static irqreturn_t winch_interrupt(int irq, void *data)
                                          &tty->winsize.ws_col);
                         kill_pgrp(tty->pgrp, SIGWINCH, 1);
                 }
+                tty_kref_put(tty);
         }
  out:
         if (winch->fd != -1)
@@ -670,7 +667,7 @@ static irqreturn_t winch_interrupt(int irq, void *data)
         return IRQ_HANDLED;
 }
 
-void register_winch_irq(int fd, int tty_fd, int pid, struct tty_struct *tty,
+void register_winch_irq(int fd, int tty_fd, int pid, struct tty_port *port,
                         unsigned long stack)
 {
         struct winch *winch;
@@ -685,7 +682,7 @@ void register_winch_irq(int fd, int tty_fd, int pid, struct tty_struct *tty,
                                    .fd          = fd,
                                    .tty_fd      = tty_fd,
                                    .pid         = pid,
-                                   .tty         = tty,
+                                   .port        = port,
                                    .stack       = stack });
 
         if (um_request_irq(WINCH_IRQ, fd, IRQ_READ, winch_interrupt,
@@ -714,15 +711,18 @@ static void unregister_winch(struct tty_struct *tty)
 {
         struct list_head *ele, *next;
         struct winch *winch;
+        struct tty_struct *wtty;
 
         spin_lock(&winch_handler_lock);
 
         list_for_each_safe(ele, next, &winch_handlers) {
                 winch = list_entry(ele, struct winch, list);
-                if (winch->tty == tty) {
+                wtty = tty_port_tty_get(winch->port);
+                if (wtty == tty) {
                         free_winch(winch);
                         break;
                 }
+                tty_kref_put(wtty);
         }
         spin_unlock(&winch_handler_lock);
 }
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index d8926c303629..39f186252e02 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -218,6 +218,7 @@ static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
         spin_lock_irqsave(&lp->lock, flags);
 
         len = (*lp->write)(lp->fd, skb, lp);
+        skb_tx_timestamp(skb);
 
         if (len == skb->len) {
                 dev->stats.tx_packets++;
@@ -281,6 +282,7 @@ static void uml_net_get_drvinfo(struct net_device *dev,
 static const struct ethtool_ops uml_net_ethtool_ops = {
         .get_drvinfo    = uml_net_get_drvinfo,
         .get_link       = ethtool_op_get_link,
+        .get_ts_info    = ethtool_op_get_ts_info,
 };
 
 static void uml_net_user_timer_expire(unsigned long _conn)
diff --git a/arch/um/drivers/ssl.c b/arch/um/drivers/ssl.c
index 16fdd0a0f9d6..b8d14fa52059 100644
--- a/arch/um/drivers/ssl.c
+++ b/arch/um/drivers/ssl.c
@@ -105,7 +105,6 @@ static const struct tty_operations ssl_ops = {
         .throttle               = line_throttle,
         .unthrottle             = line_unthrottle,
         .install                = ssl_install,
-        .cleanup                = line_cleanup,
         .hangup                 = line_hangup,
 };
 
diff --git a/arch/um/drivers/stdio_console.c b/arch/um/drivers/stdio_console.c
index 827777af3f6d..7b361f36ca96 100644
--- a/arch/um/drivers/stdio_console.c
+++ b/arch/um/drivers/stdio_console.c
@@ -110,7 +110,6 @@ static const struct tty_operations console_ops = {
         .set_termios            = line_set_termios,
         .throttle               = line_throttle,
         .unthrottle             = line_unthrottle,
-        .cleanup                = line_cleanup,
         .hangup                 = line_hangup,
 };
 
diff --git a/arch/um/kernel/early_printk.c b/arch/um/kernel/early_printk.c
index 49480f092456..4a0800bc37b2 100644
--- a/arch/um/kernel/early_printk.c
+++ b/arch/um/kernel/early_printk.c
@@ -16,7 +16,7 @@ static void early_console_write(struct console *con, const char *s, unsigned int
         um_early_printk(s, n);
 }
 
-static struct console early_console = {
+static struct console early_console_dev = {
         .name = "earlycon",
         .write = early_console_write,
         .flags = CON_BOOT,
@@ -25,8 +25,10 @@ static struct console early_console = {
 
 static int __init setup_early_printk(char *buf)
 {
-        register_console(&early_console);
-
+        if (!early_console) {
+                early_console = &early_console_dev;
+                register_console(&early_console_dev);
+        }
         return 0;
 }
 
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index 5abcbfbe7e25..9df292b270a8 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -42,17 +42,12 @@ static unsigned long brk_end;
 static void setup_highmem(unsigned long highmem_start,
                           unsigned long highmem_len)
 {
-        struct page *page;
         unsigned long highmem_pfn;
         int i;
 
         highmem_pfn = __pa(highmem_start) >> PAGE_SHIFT;
-        for (i = 0; i < highmem_len >> PAGE_SHIFT; i++) {
-                page = &mem_map[highmem_pfn + i];
-                ClearPageReserved(page);
-                init_page_count(page);
-                __free_page(page);
-        }
+        for (i = 0; i < highmem_len >> PAGE_SHIFT; i++)
+                free_highmem_page(&mem_map[highmem_pfn + i]);
 }
 #endif
 
@@ -73,18 +68,13 @@ void __init mem_init(void)
         totalram_pages = free_all_bootmem();
         max_low_pfn = totalram_pages;
 #ifdef CONFIG_HIGHMEM
-        totalhigh_pages = highmem >> PAGE_SHIFT;
-        totalram_pages += totalhigh_pages;
+        setup_highmem(end_iomem, highmem);
 #endif
         num_physpages = totalram_pages;
         max_pfn = totalram_pages;
         printk(KERN_INFO "Memory: %luk available\n",
                nr_free_pages() << (PAGE_SHIFT-10));
         kmalloc_ok = 1;
-
-#ifdef CONFIG_HIGHMEM
-        setup_highmem(end_iomem, highmem);
-#endif
 }
 
 /*
@@ -254,15 +244,7 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        if (start < end)
-                printk(KERN_INFO "Freeing initrd memory: %ldk freed\n",
-                       (end - start) >> 10);
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page(start);
-                totalram_pages++;
-        }
+        free_reserved_area(start, end, 0, "initrd");
 }
 #endif
 
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index b462b13c5bae..bbcef522bcb1 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -210,33 +210,14 @@ void initial_thread_cb(void (*proc)(void *), void *arg)
         kmalloc_ok = save_kmalloc_ok;
 }
 
-void default_idle(void)
+void arch_cpu_idle(void)
 {
         unsigned long long nsecs;
 
-        while (1) {
-                /* endless idle loop with no priority at all */
-
-                /*
-                 * although we are an idle CPU, we do not want to
-                 * get into the scheduler unnecessarily.
-                 */
-                if (need_resched())
-                        schedule();
-
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                nsecs = disable_timer();
-                idle_sleep(nsecs);
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-        }
-}
-
-void cpu_idle(void)
-{
         cpu_tasks[current_thread_info()->cpu].pid = os_getpid();
-        default_idle();
+        nsecs = disable_timer();
+        idle_sleep(nsecs);
+        local_irq_enable();
 }
 
 int __cant_sleep(void) {
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index b1469fe93295..9d9f1b4bf826 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -15,7 +15,7 @@
 #include <sysdep/mcontext.h>
 #include "internal.h"
 
-void (*sig_info[NSIG])(int, siginfo_t *, struct uml_pt_regs *) = {
+void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = {
         [SIGTRAP]       = relay_signal,
         [SIGFPE]        = relay_signal,
         [SIGILL]        = relay_signal,
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index da4b9e9999fd..337518c5042a 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -15,6 +15,8 @@
 #include <sys/mman.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include <asm/unistd.h>
 #include <init.h>
 #include <os.h>
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index dc50b157fc83..2943e3acdf0c 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -9,7 +9,7 @@ config UNICORE32
         select GENERIC_ATOMIC64
         select HAVE_KERNEL_LZO
         select HAVE_KERNEL_LZMA
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select ARCH_HAVE_CUSTOM_GPIO_H
         select GENERIC_FIND_FIRST_BIT
         select GENERIC_IRQ_PROBE
diff --git a/arch/unicore32/kernel/early_printk.c b/arch/unicore32/kernel/early_printk.c
index 3922255f1fa8..9be0d5d02a9a 100644
--- a/arch/unicore32/kernel/early_printk.c
+++ b/arch/unicore32/kernel/early_printk.c
@@ -33,21 +33,17 @@ static struct console early_ocd_console = {
         .index =        -1,
 };
 
-/* Direct interface for emergencies */
-static struct console *early_console = &early_ocd_console;
-
-static int __initdata keep_early;
-
 static int __init setup_early_printk(char *buf)
 {
-        if (!buf)
+        int keep_early;
+
+        if (!buf || early_console)
                 return 0;
 
         if (strstr(buf, "keep"))
                 keep_early = 1;
 
-        if (!strncmp(buf, "ocd", 3))
-                early_console = &early_ocd_console;
+        early_console = &early_ocd_console;
 
         if (keep_early)
                 early_console->flags &= ~CON_BOOT;
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index 872d7e22d847..7fab86d7c5d4 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -45,25 +45,10 @@ static const char * const processor_modes[] = {
         "UK18", "UK19", "UK1A", "EXTN", "UK1C", "UK1D", "UK1E", "SUSR"
 };
 
-void cpu_idle(void)
+void arch_cpu_idle(void)
 {
-        /* endless idle loop with no priority at all */
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                while (!need_resched()) {
-                        local_irq_disable();
-                        stop_critical_timings();
-                        cpu_do_idle();
-                        local_irq_enable();
-                        start_critical_timings();
-                }
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                preempt_enable_no_resched();
-                schedule();
-                preempt_disable();
-        }
+        cpu_do_idle();
+        local_irq_enable();
 }
 
 static char reboot_mode = 'h';
diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c
index de186bde8975..63df12d71ce3 100644
--- a/arch/unicore32/mm/init.c
+++ b/arch/unicore32/mm/init.c
@@ -66,6 +66,9 @@ void show_mem(unsigned int filter)
         printk(KERN_DEFAULT "Mem-info:\n");
         show_free_areas(filter);
 
+        if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+                return;
+
         for_each_bank(i, mi) {
                 struct membank *bank = &mi->bank[i];
                 unsigned int pfn1, pfn2;
@@ -313,24 +316,6 @@ void __init bootmem_init(void)
         max_pfn = max_high - PHYS_PFN_OFFSET;
 }
 
-static inline int free_area(unsigned long pfn, unsigned long end, char *s)
-{
-        unsigned int pages = 0, size = (end - pfn) << (PAGE_SHIFT - 10);
-
-        for (; pfn < end; pfn++) {
-                struct page *page = pfn_to_page(pfn);
-                ClearPageReserved(page);
-                init_page_count(page);
-                __free_page(page);
-                pages++;
-        }
-
-        if (size && s)
-                printk(KERN_INFO "Freeing %s memory: %dK\n", s, size);
-
-        return pages;
-}
-
 static inline void
 free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -404,9 +389,9 @@ void __init mem_init(void)
 
         max_mapnr   = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;
 
-        /* this will put all unused low memory onto the freelists */
         free_unused_memmap(&meminfo);
 
+        /* this will put all unused low memory onto the freelists */
         totalram_pages += free_all_bootmem();
 
         reserved_pages = free_pages = 0;
@@ -491,9 +476,7 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
-        totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)),
-                                    __phys_to_pfn(__pa(__init_end)),
-                                    "init");
+        free_initmem_default(0);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -503,9 +486,7 @@ static int keep_initrd;
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
         if (!keep_initrd)
-                totalram_pages += free_area(__phys_to_pfn(__pa(start)),
-                                            __phys_to_pfn(__pa(end)),
-                                            "initrd");
+                free_reserved_area(start, end, 0, "initrd");
 }
 
 static int __init keepinitrd_setup(char *__unused)
diff --git a/arch/unicore32/mm/ioremap.c b/arch/unicore32/mm/ioremap.c
index b7a605597b08..13068ee22f33 100644
--- a/arch/unicore32/mm/ioremap.c
+++ b/arch/unicore32/mm/ioremap.c
@@ -235,7 +235,7 @@ EXPORT_SYMBOL(__uc32_ioremap_cached);
 void __uc32_iounmap(volatile void __iomem *io_addr)
 {
         void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
-        struct vm_struct **p, *tmp;
+        struct vm_struct *vm;
 
         /*
          * If this is a section based mapping we need to handle it
@@ -244,17 +244,10 @@ void __uc32_iounmap(volatile void __iomem *io_addr)
          * all the mappings before the area can be reclaimed
          * by someone else.
          */
-        write_lock(&vmlist_lock);
-        for (p = &vmlist ; (tmp = *p) ; p = &tmp->next) {
-                if ((tmp->flags & VM_IOREMAP) && (tmp->addr == addr)) {
-                        if (tmp->flags & VM_UNICORE_SECTION_MAPPING) {
-                                unmap_area_sections((unsigned long)tmp->addr,
-                                                    tmp->size);
-                        }
-                        break;
-                }
-        }
-        write_unlock(&vmlist_lock);
+        vm = find_vm_area(addr);
+        if (vm && (vm->flags & VM_IOREMAP) &&
+                (vm->flags & VM_UNICORE_SECTION_MAPPING))
+                unmap_area_sections((unsigned long)vm->addr, vm->size);
 
         vunmap(addr);
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a4f24f5b1218..05b057dca4a7 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -112,7 +112,7 @@ config X86
         select GENERIC_STRNLEN_USER
         select HAVE_CONTEXT_TRACKING if X86_64
         select HAVE_IRQ_TIME_ACCOUNTING
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select MODULES_USE_ELF_REL if X86_32
         select MODULES_USE_ELF_RELA if X86_64
         select CLONE_BACKWARDS if X86_32
@@ -120,6 +120,7 @@ config X86
         select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
         select OLD_SIGACTION if X86_32
         select COMPAT_OLD_SIGACTION if IA32_EMULATION
+        select RTC_LIB
 
 config INSTRUCTION_DECODER
         def_bool y
@@ -188,9 +189,6 @@ config GENERIC_CALIBRATE_DELAY
 config ARCH_HAS_CPU_RELAX
         def_bool y
 
-config ARCH_HAS_DEFAULT_IDLE
-        def_bool y
-
 config ARCH_HAS_CACHE_LINE_SIZE
         def_bool y
 
@@ -389,7 +387,7 @@ config X86_NUMACHIP
 
 config X86_VSMP
         bool "ScaleMP vSMP"
-        select PARAVIRT_GUEST
+        select HYPERVISOR_GUEST
         select PARAVIRT
         depends on X86_64 && PCI
         depends on X86_EXTENDED_PLATFORM
@@ -596,44 +594,17 @@ config SCHED_OMIT_FRAME_POINTER
 
           If in doubt, say "Y".
 
-menuconfig PARAVIRT_GUEST
-        bool "Paravirtualized guest support"
-        ---help---
-          Say Y here to get to see options related to running Linux under
-          various hypervisors.  This option alone does not add any kernel code.
-
-          If you say N, all options in this submenu will be skipped and disabled.
-
-if PARAVIRT_GUEST
-
-config PARAVIRT_TIME_ACCOUNTING
-        bool "Paravirtual steal time accounting"
-        select PARAVIRT
-        default n
+menuconfig HYPERVISOR_GUEST
+        bool "Linux guest support"
         ---help---
-          Select this option to enable fine granularity task steal time
-          accounting. Time spent executing other tasks in parallel with
-          the current vCPU is discounted from the vCPU power. To account for
-          that, there can be a small performance impact.
-
-          If in doubt, say N here.
-
-source "arch/x86/xen/Kconfig"
+          Say Y here to enable options for running Linux under various hyper-
+          visors. This option enables basic hypervisor detection and platform
+          setup.
 
-config KVM_GUEST
-        bool "KVM Guest support (including kvmclock)"
-        select PARAVIRT
-        select PARAVIRT
-        select PARAVIRT_CLOCK
-        default y if PARAVIRT_GUEST
-        ---help---
-          This option enables various optimizations for running under the KVM
-          hypervisor. It includes a paravirtualized clock, so that instead
-          of relying on a PIT (or probably other) emulation by the
-          underlying device model, the host provides the guest with
-          timing infrastructure such as time of day, and system time
+          If you say N, all options in this submenu will be skipped and
+          disabled, and Linux guest support won't be built in.
 
-source "arch/x86/lguest/Kconfig"
+if HYPERVISOR_GUEST
 
 config PARAVIRT
         bool "Enable paravirtualization code"
@@ -643,6 +614,13 @@ config PARAVIRT
           over full virtualization.  However, when run without a hypervisor
           the kernel is theoretically slower and slightly larger.
 
+config PARAVIRT_DEBUG
+        bool "paravirt-ops debugging"
+        depends on PARAVIRT && DEBUG_KERNEL
+        ---help---
+          Enable to debug paravirt_ops internals.  Specifically, BUG if
+          a paravirt_op is missing when it is called.
+
 config PARAVIRT_SPINLOCKS
         bool "Paravirtualization layer for spinlocks"
         depends on PARAVIRT && SMP
@@ -656,17 +634,38 @@ config PARAVIRT_SPINLOCKS
 
           If you are unsure how to answer this question, answer N.
 
-config PARAVIRT_CLOCK
-        bool
+source "arch/x86/xen/Kconfig"
 
-endif
+config KVM_GUEST
+        bool "KVM Guest support (including kvmclock)"
+        depends on PARAVIRT
+        select PARAVIRT_CLOCK
+        default y
+        ---help---
+          This option enables various optimizations for running under the KVM
+          hypervisor. It includes a paravirtualized clock, so that instead
+          of relying on a PIT (or probably other) emulation by the
+          underlying device model, the host provides the guest with
+          timing infrastructure such as time of day, and system time
 
-config PARAVIRT_DEBUG
-        bool "paravirt-ops debugging"
-        depends on PARAVIRT && DEBUG_KERNEL
+source "arch/x86/lguest/Kconfig"
+
+config PARAVIRT_TIME_ACCOUNTING
+        bool "Paravirtual steal time accounting"
+        depends on PARAVIRT
+        default n
         ---help---
-          Enable to debug paravirt_ops internals.  Specifically, BUG if
-          a paravirt_op is missing when it is called.
+          Select this option to enable fine granularity task steal time
+          accounting. Time spent executing other tasks in parallel with
+          the current vCPU is discounted from the vCPU power. To account for
+          that, there can be a small performance impact.
+
+          If in doubt, say N here.
+
+config PARAVIRT_CLOCK
+        bool
+
+endif #HYPERVISOR_GUEST
 
 config NO_BOOTMEM
         def_bool y
@@ -1549,6 +1548,7 @@ config X86_SMAP
 config EFI
         bool "EFI runtime service support"
         depends on ACPI
+        select UCS2_STRING
         ---help---
           This enables the kernel to use EFI runtime services that are
           available (such as the EFI variable services).
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index b322f124ee3c..16f738385dcb 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -131,7 +131,7 @@ config DOUBLEFAULT
 
 config DEBUG_TLBFLUSH
         bool "Set upper limit of TLB entries to flush one-by-one"
-        depends on DEBUG_KERNEL && (X86_64 || X86_INVLPG)
+        depends on DEBUG_KERNEL
         ---help---
 
         X86-only for now.
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 8a84501acb1b..5ef205c5f37b 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -4,7 +4,7 @@
 # create a compressed vmlinux image from the original vmlinux
 #
 
-targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o
+targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
@@ -29,7 +29,6 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
         $(obj)/piggy.o
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
-$(obj)/efi_stub_$(BITS).o: KBUILD_CLFAGS += -fshort-wchar -mno-red-zone
 
 ifeq ($(CONFIG_EFI_STUB), y)
         VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
@@ -43,7 +42,7 @@ OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
 $(obj)/vmlinux.bin: vmlinux FORCE
         $(call if_changed,objcopy)
 
-targets += vmlinux.bin.all vmlinux.relocs
+targets += $(patsubst $(obj)/%,%,$(VMLINUX_OBJS)) vmlinux.bin.all vmlinux.relocs
 
 CMD_RELOCS = arch/x86/tools/relocs
 quiet_cmd_relocs = RELOCS  $@
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index c205035a6b96..35ee62fccf98 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -251,6 +251,51 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size)
         *size = len;
 }
 
+static efi_status_t setup_efi_vars(struct boot_params *params)
+{
+        struct setup_data *data;
+        struct efi_var_bootdata *efidata;
+        u64 store_size, remaining_size, var_size;
+        efi_status_t status;
+
+        if (sys_table->runtime->hdr.revision < EFI_2_00_SYSTEM_TABLE_REVISION)
+                return EFI_UNSUPPORTED;
+
+        data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+        while (data && data->next)
+                data = (struct setup_data *)(unsigned long)data->next;
+
+        status = efi_call_phys4((void *)sys_table->runtime->query_variable_info,
+                                EFI_VARIABLE_NON_VOLATILE |
+                                EFI_VARIABLE_BOOTSERVICE_ACCESS |
+                                EFI_VARIABLE_RUNTIME_ACCESS, &store_size,
+                                &remaining_size, &var_size);
+
+        if (status != EFI_SUCCESS)
+                return status;
+
+        status = efi_call_phys3(sys_table->boottime->allocate_pool,
+                                EFI_LOADER_DATA, sizeof(*efidata), &efidata);
+
+        if (status != EFI_SUCCESS)
+                return status;
+
+        efidata->data.type = SETUP_EFI_VARS;
+        efidata->data.len = sizeof(struct efi_var_bootdata) -
+                sizeof(struct setup_data);
+        efidata->data.next = 0;
+        efidata->store_size = store_size;
+        efidata->remaining_size = remaining_size;
+        efidata->max_var_size = var_size;
+
+        if (data)
+                data->next = (unsigned long)efidata;
+        else
+                params->hdr.setup_data = (unsigned long)efidata;
+
+}
+
 static efi_status_t setup_efi_pci(struct boot_params *params)
 {
         efi_pci_io_protocol *pci;
@@ -1157,6 +1202,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
 
         setup_graphics(boot_params);
 
+        setup_efi_vars(boot_params);
+
         setup_efi_pci(boot_params);
 
         status = efi_call_phys3(sys_table->boottime->allocate_pool,
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index c1d383d1fb7e..16f24e6dad79 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -52,7 +52,7 @@ ENTRY(startup_32)
         jnz 1f
 
         cli
-        movl    $(__KERNEL_DS), %eax
+        movl    $(__BOOT_DS), %eax
         movl    %eax, %ds
         movl    %eax, %es
         movl    %eax, %ss
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 8d871eaddb66..d47786acb016 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -35,7 +35,7 @@ extern void __add_wrong_size(void)
 
 /* 
  * An exchange-type operation, which takes a value and a pointer, and
- * returns a the old value.
+ * returns the old value.
  */
 #define __xchg_op(ptr, arg, op, lock)                                   \
         ({                                                              \
diff --git a/arch/x86/include/asm/context_tracking.h b/arch/x86/include/asm/context_tracking.h
index 1616562683e9..1fe49704b146 100644
--- a/arch/x86/include/asm/context_tracking.h
+++ b/arch/x86/include/asm/context_tracking.h
@@ -1,31 +1,10 @@
 #ifndef _ASM_X86_CONTEXT_TRACKING_H
 #define _ASM_X86_CONTEXT_TRACKING_H
 
-#ifndef __ASSEMBLY__
-#include <linux/context_tracking.h>
-#include <asm/ptrace.h>
-
-static inline void exception_enter(struct pt_regs *regs)
-{
-        user_exit();
-}
-
-static inline void exception_exit(struct pt_regs *regs)
-{
-#ifdef CONFIG_CONTEXT_TRACKING
-        if (user_mode(regs))
-                user_enter();
-#endif
-}
-
-#else /* __ASSEMBLY__ */
-
 #ifdef CONFIG_CONTEXT_TRACKING
 # define SCHEDULE_USER call schedule_user
 #else
 # define SCHEDULE_USER call schedule
 #endif
 
-#endif /* !__ASSEMBLY__ */
-
 #endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 93fe929d1cee..398f7cb1353d 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -9,6 +9,7 @@
 #endif
 
 #define NCAPINTS        10      /* N 32-bit words worth of info */
+#define NBUGINTS        1       /* N 32-bit bug flags */
 
 /*
  * Note: If the comment begins with a quoted string, that string is used
@@ -100,6 +101,7 @@
 #define X86_FEATURE_AMD_DCM     (3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF  (3*32+28) /* APERFMPERF */
 #define X86_FEATURE_EAGER_FPU   (3*32+29) /* "eagerfpu" Non lazy FPU restore */
+#define X86_FEATURE_NONSTOP_TSC_S3 (3*32+30) /* TSC doesn't stop in S3 state */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3        (4*32+ 0) /* "pni" SSE-3 */
@@ -168,6 +170,7 @@
 #define X86_FEATURE_TOPOEXT     (6*32+22) /* topology extensions CPUID leafs */
 #define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
 #define X86_FEATURE_PERFCTR_NB  (6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_PERFCTR_L2  (6*32+28) /* L2 performance counter extensions */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -216,6 +219,17 @@
 #define X86_FEATURE_ADX         (9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP        (9*32+20) /* Supervisor Mode Access Prevention */
 
+/*
+ * BUG word(s)
+ */
+#define X86_BUG(x)              (NCAPINTS*32 + (x))
+
+#define X86_BUG_F00F            X86_BUG(0) /* Intel F00F */
+#define X86_BUG_FDIV            X86_BUG(1) /* FPU FDIV */
+#define X86_BUG_COMA            X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_AMD_TLB_MMATCH  X86_BUG(3) /* AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E    X86_BUG(4) /* AMD Erratum 400 */
+
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
 #include <asm/asm.h>
@@ -311,6 +325,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_pclmulqdq       boot_cpu_has(X86_FEATURE_PCLMULQDQ)
 #define cpu_has_perfctr_core    boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
 #define cpu_has_perfctr_nb      boot_cpu_has(X86_FEATURE_PERFCTR_NB)
+#define cpu_has_perfctr_l2      boot_cpu_has(X86_FEATURE_PERFCTR_L2)
 #define cpu_has_cx8             boot_cpu_has(X86_FEATURE_CX8)
 #define cpu_has_cx16            boot_cpu_has(X86_FEATURE_CX16)
 #define cpu_has_eager_fpu       boot_cpu_has(X86_FEATURE_EAGER_FPU)
@@ -401,6 +416,13 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 #define static_cpu_has(bit) boot_cpu_has(bit)
 #endif
 
+#define cpu_has_bug(c, bit)     cpu_has(c, (bit))
+#define set_cpu_bug(c, bit)     set_cpu_cap(c, (bit))
+#define clear_cpu_bug(c, bit)   clear_cpu_cap(c, (bit));
+
+#define static_cpu_has_bug(bit) static_cpu_has((bit))
+#define boot_cpu_has_bug(bit)   cpu_has_bug(&boot_cpu_data, (bit))
+
 #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
 
 #endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 60c89f30c727..2fb5d5884e23 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -102,6 +102,13 @@ extern void efi_call_phys_epilog(void);
 extern void efi_unmap_memmap(void);
 extern void efi_memory_uc(u64 addr, unsigned long size);
 
+struct efi_var_bootdata {
+        struct setup_data data;
+        u64 store_size;
+        u64 remaining_size;
+        u64 max_var_size;
+};
+
 #ifdef CONFIG_EFI
 
 static inline bool efi_is_native(void)
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index a09c28571064..0dc7d9e21c34 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -104,12 +104,7 @@ enum fixed_addresses {
         FIX_LI_PCIA,    /* Lithium PCI Bridge A */
         FIX_LI_PCIB,    /* Lithium PCI Bridge B */
 #endif
-#ifdef CONFIG_X86_F00F_BUG
-        FIX_F00F_IDT,   /* Virtual mapping for IDT */
-#endif
-#ifdef CONFIG_X86_CYCLONE_TIMER
-        FIX_CYCLONE_TIMER, /*cyclone timer register*/
-#endif
+        FIX_RO_IDT,     /* Virtual mapping for read-only IDT */
 #ifdef CONFIG_X86_32
         FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
         FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index bdd35dbd0605..a8091216963b 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_HUGETLB_H
 
 #include <asm/page.h>
+#include <asm-generic/hugetlb.h>
 
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 86095ed14135..2d4b5e6107cd 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -20,13 +20,11 @@
 #ifndef _ASM_X86_HYPERVISOR_H
 #define _ASM_X86_HYPERVISOR_H
 
+#ifdef CONFIG_HYPERVISOR_GUEST
+
 #include <asm/kvm_para.h>
 #include <asm/xen/hypervisor.h>
 
-extern void init_hypervisor(struct cpuinfo_x86 *c);
-extern void init_hypervisor_platform(void);
-extern bool hypervisor_x2apic_available(void);
-
 /*
  * x86 hypervisor information
  */
@@ -55,4 +53,12 @@ extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
 extern const struct hypervisor_x86 x86_hyper_xen_hvm;
 extern const struct hypervisor_x86 x86_hyper_kvm;
 
-#endif
+extern void init_hypervisor(struct cpuinfo_x86 *c);
+extern void init_hypervisor_platform(void);
+extern bool hypervisor_x2apic_available(void);
+#else
+static inline void init_hypervisor(struct cpuinfo_x86 *c) { }
+static inline void init_hypervisor_platform(void) { }
+static inline bool hypervisor_x2apic_available(void) { return false; }
+#endif /* CONFIG_HYPERVISOR_GUEST */
+#endif /* _ASM_X86_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index d3ddd17405d0..5a6d2873f80e 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -77,6 +77,7 @@ struct arch_specific_insn {
          * a post_handler or break_handler).
          */
         int boostable;
+        bool if_modifier;
 };
 
 struct arch_optimized_insn {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 635a74d22409..4979778cc7fb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -414,8 +414,8 @@ struct kvm_vcpu_arch {
         gpa_t time;
         struct pvclock_vcpu_time_info hv_clock;
         unsigned int hw_tsc_khz;
-        unsigned int time_offset;
-        struct page *time_page;
+        struct gfn_to_hva_cache pv_time;
+        bool pv_time_enabled;
         /* set guest stopped flag in pvclock flags field */
         bool pvclock_set_guest_stopped_request;
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index f4076af1f4ed..fa5f71e021d5 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -146,13 +146,13 @@ DECLARE_PER_CPU(struct device *, mce_device);
 void mce_intel_feature_init(struct cpuinfo_x86 *c);
 void cmci_clear(void);
 void cmci_reenable(void);
-void cmci_rediscover(int dying);
+void cmci_rediscover(void);
 void cmci_recheck(void);
 #else
 static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
 static inline void cmci_clear(void) {}
 static inline void cmci_reenable(void) {}
-static inline void cmci_rediscover(int dying) {}
+static inline void cmci_rediscover(void) {}
 static inline void cmci_recheck(void) {}
 #endif
 
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 9264802e2824..cb7502852acb 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -137,11 +137,11 @@ static inline unsigned long long native_read_pmc(int counter)
  * pointer indirection), this allows gcc to optimize better
  */
 
-#define rdmsr(msr, val1, val2)                                  \
+#define rdmsr(msr, low, high)                                   \
 do {                                                            \
         u64 __val = native_read_msr((msr));                     \
-        (void)((val1) = (u32)__val);                            \
-        (void)((val2) = (u32)(__val >> 32));                    \
+        (void)((low) = (u32)__val);                             \
+        (void)((high) = (u32)(__val >> 32));                    \
 } while (0)
 
 static inline void wrmsr(unsigned msr, unsigned low, unsigned high)
@@ -162,12 +162,12 @@ static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high)
 }
 
 /* rdmsr with exception handling */
-#define rdmsr_safe(msr, p1, p2)                                 \
+#define rdmsr_safe(msr, low, high)                              \
 ({                                                              \
         int __err;                                              \
         u64 __val = native_read_msr_safe((msr), &__err);        \
-        (*p1) = (u32)__val;                                     \
-        (*p2) = (u32)(__val >> 32);                             \
+        (*low) = (u32)__val;                                    \
+        (*high) = (u32)(__val >> 32);                           \
         __err;                                                  \
 })
 
@@ -208,7 +208,7 @@ do {                                                            \
 #define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val),             \
                                              (u32)((val) >> 32))
 
-#define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2))
+#define write_tsc(low, high) wrmsr(MSR_IA32_TSC, (low), (high))
 
 #define write_rdtscp_aux(val) wrmsr(MSR_TSC_AUX, (val), 0)
 
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 8b491e66eaa8..6c896fbe21db 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -48,6 +48,5 @@
  * arch/x86/kernel/head_64.S), and it is mapped here:
  */
 #define KERNEL_IMAGE_SIZE       (512 * 1024 * 1024)
-#define KERNEL_IMAGE_START      _AC(0xffffffff80000000, UL)
 
 #endif /* _ASM_X86_PAGE_64_DEFS_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 5edd1742cfd0..cfdc9ee4c900 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -262,10 +262,6 @@ static inline void set_ldt(const void *addr, unsigned entries)
 {
         PVOP_VCALL2(pv_cpu_ops.set_ldt, addr, entries);
 }
-static inline void store_gdt(struct desc_ptr *dtr)
-{
-        PVOP_VCALL1(pv_cpu_ops.store_gdt, dtr);
-}
 static inline void store_idt(struct desc_ptr *dtr)
 {
         PVOP_VCALL1(pv_cpu_ops.store_idt, dtr);
@@ -703,7 +699,10 @@ static inline void arch_leave_lazy_mmu_mode(void)
         PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
 }
 
-void arch_flush_lazy_mmu_mode(void);
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+        PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush);
+}
 
 static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
                                 phys_addr_t phys, pgprot_t flags)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 142236ed83af..0db1fcac668c 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -91,6 +91,7 @@ struct pv_lazy_ops {
         /* Set deferred update mode, used for batching operations. */
         void (*enter)(void);
         void (*leave)(void);
+        void (*flush)(void);
 };
 
 struct pv_time_ops {
@@ -122,7 +123,7 @@ struct pv_cpu_ops {
         void (*load_tr_desc)(void);
         void (*load_gdt)(const struct desc_ptr *);
         void (*load_idt)(const struct desc_ptr *);
-        void (*store_gdt)(struct desc_ptr *);
+        /* store_gdt has been removed. */
         void (*store_idt)(struct desc_ptr *);
         void (*set_ldt)(const void *desc, unsigned entries);
         unsigned long (*store_tr)(void);
@@ -679,6 +680,7 @@ void paravirt_end_context_switch(struct task_struct *next);
 
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);
+void paravirt_flush_lazy_mmu(void);
 
 void _paravirt_nop(void);
 u32 _paravirt_ident_32(u32);
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 4f7e67e2345e..85e13ccf15c4 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -24,45 +24,45 @@
 #define ARCH_P4_CNTRVAL_MASK    ((1ULL << ARCH_P4_CNTRVAL_BITS) - 1)
 #define ARCH_P4_UNFLAGGED_BIT   ((1ULL) << (ARCH_P4_CNTRVAL_BITS - 1))
 
-#define P4_ESCR_EVENT_MASK      0x7e000000U
+#define P4_ESCR_EVENT_MASK      0x7e000000ULL
 #define P4_ESCR_EVENT_SHIFT     25
-#define P4_ESCR_EVENTMASK_MASK  0x01fffe00U
+#define P4_ESCR_EVENTMASK_MASK  0x01fffe00ULL
 #define P4_ESCR_EVENTMASK_SHIFT 9
-#define P4_ESCR_TAG_MASK        0x000001e0U
+#define P4_ESCR_TAG_MASK        0x000001e0ULL
 #define P4_ESCR_TAG_SHIFT       5
-#define P4_ESCR_TAG_ENABLE      0x00000010U
-#define P4_ESCR_T0_OS           0x00000008U
-#define P4_ESCR_T0_USR          0x00000004U
-#define P4_ESCR_T1_OS           0x00000002U
-#define P4_ESCR_T1_USR          0x00000001U
+#define P4_ESCR_TAG_ENABLE      0x00000010ULL
+#define P4_ESCR_T0_OS           0x00000008ULL
+#define P4_ESCR_T0_USR          0x00000004ULL
+#define P4_ESCR_T1_OS           0x00000002ULL
+#define P4_ESCR_T1_USR          0x00000001ULL
 
 #define P4_ESCR_EVENT(v)        ((v) << P4_ESCR_EVENT_SHIFT)
 #define P4_ESCR_EMASK(v)        ((v) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_TAG(v)          ((v) << P4_ESCR_TAG_SHIFT)
 
-#define P4_CCCR_OVF                     0x80000000U
-#define P4_CCCR_CASCADE                 0x40000000U
-#define P4_CCCR_OVF_PMI_T0              0x04000000U
-#define P4_CCCR_OVF_PMI_T1              0x08000000U
-#define P4_CCCR_FORCE_OVF               0x02000000U
-#define P4_CCCR_EDGE                    0x01000000U
-#define P4_CCCR_THRESHOLD_MASK          0x00f00000U
+#define P4_CCCR_OVF                     0x80000000ULL
+#define P4_CCCR_CASCADE                 0x40000000ULL
+#define P4_CCCR_OVF_PMI_T0              0x04000000ULL
+#define P4_CCCR_OVF_PMI_T1              0x08000000ULL
+#define P4_CCCR_FORCE_OVF               0x02000000ULL
+#define P4_CCCR_EDGE                    0x01000000ULL
+#define P4_CCCR_THRESHOLD_MASK          0x00f00000ULL
 #define P4_CCCR_THRESHOLD_SHIFT         20
-#define P4_CCCR_COMPLEMENT              0x00080000U
-#define P4_CCCR_COMPARE                 0x00040000U
-#define P4_CCCR_ESCR_SELECT_MASK        0x0000e000U
+#define P4_CCCR_COMPLEMENT              0x00080000ULL
+#define P4_CCCR_COMPARE                 0x00040000ULL
+#define P4_CCCR_ESCR_SELECT_MASK        0x0000e000ULL
 #define P4_CCCR_ESCR_SELECT_SHIFT       13
-#define P4_CCCR_ENABLE                  0x00001000U
-#define P4_CCCR_THREAD_SINGLE           0x00010000U
-#define P4_CCCR_THREAD_BOTH             0x00020000U
-#define P4_CCCR_THREAD_ANY              0x00030000U
-#define P4_CCCR_RESERVED                0x00000fffU
+#define P4_CCCR_ENABLE                  0x00001000ULL
+#define P4_CCCR_THREAD_SINGLE           0x00010000ULL
+#define P4_CCCR_THREAD_BOTH             0x00020000ULL
+#define P4_CCCR_THREAD_ANY              0x00030000ULL
+#define P4_CCCR_RESERVED                0x00000fffULL
 
 #define P4_CCCR_THRESHOLD(v)            ((v) << P4_CCCR_THRESHOLD_SHIFT)
 #define P4_CCCR_ESEL(v)                 ((v) << P4_CCCR_ESCR_SELECT_SHIFT)
 
 #define P4_GEN_ESCR_EMASK(class, name, bit)     \
-        class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)
+        class##__##name = ((1ULL << bit) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_EMASK_BIT(class, name)          class##__##name
 
 /*
@@ -107,7 +107,7 @@
  * P4_PEBS_CONFIG_MASK and related bits on
  * modification.)
  */
-#define P4_CONFIG_ALIASABLE             (1 << 9)
+#define P4_CONFIG_ALIASABLE             (1ULL << 9)
 
 /*
  * The bits we allow to pass for RAW events
@@ -784,17 +784,17 @@ enum P4_ESCR_EMASKS {
  * Note we have UOP and PEBS bits reserved for now
  * just in case if we will need them once
  */
-#define P4_PEBS_CONFIG_ENABLE           (1 << 7)
-#define P4_PEBS_CONFIG_UOP_TAG          (1 << 8)
-#define P4_PEBS_CONFIG_METRIC_MASK      0x3f
-#define P4_PEBS_CONFIG_MASK             0xff
+#define P4_PEBS_CONFIG_ENABLE           (1ULL << 7)
+#define P4_PEBS_CONFIG_UOP_TAG          (1ULL << 8)
+#define P4_PEBS_CONFIG_METRIC_MASK      0x3FLL
+#define P4_PEBS_CONFIG_MASK             0xFFLL
 
 /*
  * mem: Only counters MSR_IQ_COUNTER4 (16) and
  * MSR_IQ_COUNTER5 (17) are allowed for PEBS sampling
  */
-#define P4_PEBS_ENABLE                  0x02000000U
-#define P4_PEBS_ENABLE_UOP_TAG          0x01000000U
+#define P4_PEBS_ENABLE                  0x02000000ULL
+#define P4_PEBS_ENABLE_UOP_TAG          0x01000000ULL
 
 #define p4_config_unpack_metric(v)      (((u64)(v)) & P4_PEBS_CONFIG_METRIC_MASK)
 #define p4_config_unpack_pebs(v)        (((u64)(v)) & P4_PEBS_CONFIG_MASK)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 567b5d0632b2..e6423002c10b 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -351,7 +351,6 @@ static inline void update_page_count(int level, unsigned long pages) { }
  * as a pte too.
  */
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
-extern int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 
 #endif  /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3270116b1488..22224b3b43bb 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -91,9 +91,6 @@ struct cpuinfo_x86 {
         /* Problems on some 486Dx4's and old 386's: */
         char                    hard_math;
         char                    rfu;
-        char                    fdiv_bug;
-        char                    f00f_bug;
-        char                    coma_bug;
         char                    pad0;
 #else
         /* Number of 4K pages in DTLB/ITLB combined(in pages): */
@@ -107,7 +104,7 @@ struct cpuinfo_x86 {
         __u32                   extended_cpuid_level;
         /* Maximum supported CPUID level, -1=no CPUID: */
         int                     cpuid_level;
-        __u32                   x86_capability[NCAPINTS];
+        __u32                   x86_capability[NCAPINTS + NBUGINTS];
         char                    x86_vendor_id[16];
         char                    x86_model_id[64];
         /* in KB - valid for CPUS which support this call: */
@@ -973,26 +970,6 @@ unsigned long calc_aperfmperf_ratio(struct aperfmperf *old,
         return ratio;
 }
 
-/*
- * AMD errata checking
- */
-#ifdef CONFIG_CPU_SUP_AMD
-extern const int amd_erratum_383[];
-extern const int amd_erratum_400[];
-extern bool cpu_has_amd_erratum(const int *);
-
-#define AMD_LEGACY_ERRATUM(...)         { -1, __VA_ARGS__, 0 }
-#define AMD_OSVW_ERRATUM(osvw_id, ...)  { osvw_id, __VA_ARGS__, 0 }
-#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \
-        ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end))
-#define AMD_MODEL_RANGE_FAMILY(range)   (((range) >> 24) & 0xff)
-#define AMD_MODEL_RANGE_START(range)    (((range) >> 12) & 0xfff)
-#define AMD_MODEL_RANGE_END(range)      ((range) & 0xfff)
-
-#else
-#define cpu_has_amd_erratum(x)  (false)
-#endif /* CONFIG_CPU_SUP_AMD */
-
 extern unsigned long arch_align_stack(unsigned long sp);
 extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
 
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 487055c8c1aa..f6064b7385b0 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -15,7 +15,6 @@ struct saved_context {
         unsigned long cr0, cr2, cr3, cr4;
         u64 misc_enable;
         bool misc_enable_saved;
-        struct desc_ptr gdt;
         struct desc_ptr idt;
         u16 ldt;
         u16 tss;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 09b0bf104156..97b84e08a211 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -25,9 +25,6 @@ struct saved_context {
         u64 misc_enable;
         bool misc_enable_saved;
         unsigned long efer;
-        u16 gdt_pad;
-        u16 gdt_limit;
-        unsigned long gdt_base;
         u16 idt_pad;
         u16 idt_limit;
         unsigned long idt_base;
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 1ace47b62592..2e188d68397c 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -29,13 +29,13 @@ extern const unsigned long sys_call_table[];
  */
 static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 {
-        return regs->orig_ax & __SYSCALL_MASK;
+        return regs->orig_ax;
 }
 
 static inline void syscall_rollback(struct task_struct *task,
                                     struct pt_regs *regs)
 {
-        regs->ax = regs->orig_ax & __SYSCALL_MASK;
+        regs->ax = regs->orig_ax;
 }
 
 static inline long syscall_get_error(struct task_struct *task,
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 2cd056e3ada3..a1df6e84691f 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -241,8 +241,6 @@ static inline struct thread_info *current_thread_info(void)
                                            skip sending interrupt */
 #define TS_RESTORE_SIGMASK      0x0008  /* restore signal mask in do_signal() */
 
-#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
-
 #ifndef __ASSEMBLY__
 #define HAVE_SET_RESTORE_SIGMASK        1
 static inline void set_restore_sigmask(void)
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 4fef20773b8f..c7797307fc2b 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -7,7 +7,7 @@
 
 #define tlb_flush(tlb)                                                  \
 {                                                                       \
-        if (tlb->fullmm == 0)                                           \
+        if (!tlb->fullmm && !tlb->need_flush_all)                       \
                 flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL); \
         else                                                            \
                 flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL);   \
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 8ff8be7835ab..6e5197910fd8 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -55,4 +55,5 @@ extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
 extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
 extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
 extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
 #endif  /* _ASM_UPROBES_H */
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index c20d1ce62dc6..e709884d0ef9 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -382,14 +382,14 @@ HYPERVISOR_console_io(int cmd, int count, char *str)
         return _hypercall3(int, console_io, cmd, count, str);
 }
 
-extern int __must_check HYPERVISOR_physdev_op_compat(int, void *);
+extern int __must_check xen_physdev_op_compat(int, void *);
 
 static inline int
 HYPERVISOR_physdev_op(int cmd, void *arg)
 {
         int rc = _hypercall2(int, physdev_op, cmd, arg);
         if (unlikely(rc == -ENOSYS))
-                rc = HYPERVISOR_physdev_op_compat(cmd, arg);
+                rc = xen_physdev_op_compat(cmd, arg);
         return rc;
 }
 
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index c15ddaf90710..08744242b8d2 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -6,6 +6,7 @@
 #define SETUP_E820_EXT                  1
 #define SETUP_DTB                       2
 #define SETUP_PCI                       3
+#define SETUP_EFI_VARS                  4
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK        0x07FF
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 892ce40a7470..b5757885d7a4 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -44,6 +44,7 @@
 #define SNB_C1_AUTO_UNDEMOTE            (1UL << 27)
 #define SNB_C3_AUTO_UNDEMOTE            (1UL << 28)
 
+#define MSR_PLATFORM_INFO               0x000000ce
 #define MSR_MTRRcap                     0x000000fe
 #define MSR_IA32_BBL_CR_CTL             0x00000119
 #define MSR_IA32_BBL_CR_CTL3            0x0000011e
@@ -71,6 +72,7 @@
 #define MSR_IA32_PEBS_ENABLE            0x000003f1
 #define MSR_IA32_DS_AREA                0x00000600
 #define MSR_IA32_PERF_CAPABILITIES      0x00000345
+#define MSR_PEBS_LD_LAT_THRESHOLD       0x000003f6
 
 #define MSR_MTRRfix64K_00000            0x00000250
 #define MSR_MTRRfix16K_80000            0x00000258
@@ -194,6 +196,10 @@
 #define MSR_AMD64_IBSBRTARGET           0xc001103b
 #define MSR_AMD64_IBS_REG_COUNT_MAX     8 /* includes MSR_AMD64_IBSBRTARGET */
 
+/* Fam 16h MSRs */
+#define MSR_F16H_L2I_PERF_CTL           0xc0010230
+#define MSR_F16H_L2I_PERF_CTR           0xc0010231
+
 /* Fam 15h MSRs */
 #define MSR_F15H_PERF_CTL               0xc0010200
 #define MSR_F15H_PERF_CTR               0xc0010201
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 0532f5d6e4ef..b44577bc9744 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -46,7 +46,7 @@ int acpi_suspend_lowlevel(void)
         header->pmode_behavior = 0;
 
 #ifndef CONFIG_64BIT
-        store_gdt((struct desc_ptr *)&header->pmode_gdt);
+        native_store_gdt((struct desc_ptr *)&header->pmode_gdt);
 
         if (!rdmsr_safe(MSR_EFER,
                         &header->pmode_efer_low,
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 13ab720573e3..d1daa66ab162 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -1,4 +1,4 @@
-        .section .text..page_aligned
+        .text
 #include <linux/linkage.h>
 #include <asm/segment.h>
 #include <asm/page_types.h>
@@ -18,7 +18,6 @@ wakeup_pmode_return:
         movw    %ax, %gs
 
         # reload the gdt, as we need the full 32 bit address
-        lgdt    saved_gdt
         lidt    saved_idt
         lldt    saved_ldt
         ljmp    $(__KERNEL_CS), $1f
@@ -44,7 +43,6 @@ bogus_magic:
 
 
 save_registers:
-        sgdt    saved_gdt
         sidt    saved_idt
         sldt    saved_ldt
         str     saved_tss
@@ -93,7 +91,6 @@ ENTRY(saved_magic)	.long	0
 ENTRY(saved_eip)        .long   0
 
 # saved registers
-saved_gdt:      .long   0,0
 saved_idt:      .long   0,0
 saved_ldt:      .long   0
 saved_tss:      .long   0
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ef5ccca79a6c..c15cf9a25e27 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -271,7 +271,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
                 replacement = (u8 *)&a->repl_offset + a->repl_offset;
                 BUG_ON(a->replacementlen > a->instrlen);
                 BUG_ON(a->instrlen > sizeof(insnbuf));
-                BUG_ON(a->cpuid >= NCAPINTS*32);
+                BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
                 if (!boot_cpu_has(a->cpuid))
                         continue;
 
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index aadf3359e2a7..3048ded1b598 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -20,12 +20,14 @@ const struct pci_device_id amd_nb_misc_ids[] = {
         { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
         { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
         { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
+        { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
         {}
 };
 EXPORT_SYMBOL(amd_nb_misc_ids);
 
-static struct pci_device_id amd_nb_link_ids[] = {
+static const struct pci_device_id amd_nb_link_ids[] = {
         { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
+        { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
         {}
 };
 
@@ -81,7 +83,6 @@ int amd_cache_northbridges(void)
                         next_northbridge(link, amd_nb_link_ids);
         }
 
-        /* some CPU families (e.g. family 0x11) do not support GART */
         if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
             boot_cpu_data.x86 == 0x15)
                 amd_northbridges.flags |= AMD_NB_GART;
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index d5fd66f0d4cd..fd972a3e4cbb 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -87,7 +87,7 @@ static u32 __init allocate_aperture(void)
          */
         addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR,
                                       aper_size, aper_size);
-        if (!addr || addr + aper_size > GART_MAX_ADDR) {
+        if (!addr) {
                 printk(KERN_ERR
                         "Cannot allocate aperture memory hole (%lx,%uK)\n",
                                 addr, aper_size>>10);
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index a0e067d3d96c..b0684e4a73aa 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -14,7 +14,6 @@ CFLAGS_common.o		:= $(nostackp)
 
 obj-y                   := intel_cacheinfo.o scattered.o topology.o
 obj-y                   += proc.o capflags.o powerflags.o common.o
-obj-y                   += vmware.o hypervisor.o mshyperv.o
 obj-y                   += rdrand.o
 obj-y                   += match.o
 
@@ -31,7 +30,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 obj-$(CONFIG_PERF_EVENTS)               += perf_event.o
 
 ifdef CONFIG_PERF_EVENTS
-obj-$(CONFIG_CPU_SUP_AMD)               += perf_event_amd.o
+obj-$(CONFIG_CPU_SUP_AMD)               += perf_event_amd.o perf_event_amd_uncore.o
 obj-$(CONFIG_CPU_SUP_INTEL)             += perf_event_p6.o perf_event_knc.o perf_event_p4.o
 obj-$(CONFIG_CPU_SUP_INTEL)             += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
 obj-$(CONFIG_CPU_SUP_INTEL)             += perf_event_intel_uncore.o
@@ -42,11 +41,13 @@ obj-$(CONFIG_MTRR)			+= mtrr/
 
 obj-$(CONFIG_X86_LOCAL_APIC)            += perfctr-watchdog.o perf_event_amd_ibs.o
 
+obj-$(CONFIG_HYPERVISOR_GUEST)          += vmware.o hypervisor.o mshyperv.o
+
 quiet_cmd_mkcapflags = MKCAP   $@
-      cmd_mkcapflags = $(PERL) $(srctree)/$(src)/mkcapflags.pl $< $@
+      cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $< $@
 
 cpufeature = $(src)/../../include/asm/cpufeature.h
 
 targets += capflags.c
-$(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.pl FORCE
+$(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE
         $(call if_changed,mkcapflags)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index fa96eb0d02fb..5013a48d1aff 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -20,11 +20,11 @@
 
 static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 {
-        struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
         u32 gprs[8] = { 0 };
         int err;
 
-        WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__);
+        WARN_ONCE((boot_cpu_data.x86 != 0xf),
+                  "%s should only be used on K8!\n", __func__);
 
         gprs[1] = msr;
         gprs[7] = 0x9c5a203a;
@@ -38,10 +38,10 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 
 static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
 {
-        struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
         u32 gprs[8] = { 0 };
 
-        WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__);
+        WARN_ONCE((boot_cpu_data.x86 != 0xf),
+                  "%s should only be used on K8!\n", __func__);
 
         gprs[0] = (u32)val;
         gprs[1] = msr;
@@ -192,11 +192,11 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
         /* Athlon 660/661 is valid. */
         if ((c->x86_model == 6) && ((c->x86_mask == 0) ||
             (c->x86_mask == 1)))
-                goto valid_k7;
+                return;
 
         /* Duron 670 is valid */
         if ((c->x86_model == 7) && (c->x86_mask == 0))
-                goto valid_k7;
+                return;
 
         /*
          * Athlon 662, Duron 671, and Athlon >model 7 have capability
@@ -209,7 +209,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
             ((c->x86_model == 7) && (c->x86_mask >= 1)) ||
              (c->x86_model > 7))
                 if (cpu_has_mp)
-                        goto valid_k7;
+                        return;
 
         /* If we get here, not a certified SMP capable AMD system. */
 
@@ -220,9 +220,6 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
         WARN_ONCE(1, "WARNING: This combination of AMD"
                 " processors is not suitable for SMP.\n");
         add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE);
-
-valid_k7:
-        ;
 }
 
 static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
@@ -513,6 +510,10 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 #endif
 }
 
+static const int amd_erratum_383[];
+static const int amd_erratum_400[];
+static bool cpu_has_amd_erratum(const int *erratum);
+
 static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 {
         u32 dummy;
@@ -727,8 +728,14 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
                 rdmsrl_safe(MSR_AMD64_BU_CFG2, &value);
                 value &= ~(1ULL << 24);
                 wrmsrl_safe(MSR_AMD64_BU_CFG2, value);
+
+                if (cpu_has_amd_erratum(amd_erratum_383))
+                        set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
         }
 
+        if (cpu_has_amd_erratum(amd_erratum_400))
+                set_cpu_bug(c, X86_BUG_AMD_APIC_C1E);
+
         rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
 }
 
@@ -847,8 +854,7 @@ cpu_dev_register(amd_cpu_dev);
  * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that
  * have an OSVW id assigned, which it takes as first argument. Both take a
  * variable number of family-specific model-stepping ranges created by
- * AMD_MODEL_RANGE(). Each erratum also has to be declared as extern const
- * int[] in arch/x86/include/asm/processor.h.
+ * AMD_MODEL_RANGE().
  *
  * Example:
  *
@@ -858,16 +864,22 @@ cpu_dev_register(amd_cpu_dev);
  *                         AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0));
  */
 
-const int amd_erratum_400[] =
+#define AMD_LEGACY_ERRATUM(...)         { -1, __VA_ARGS__, 0 }
+#define AMD_OSVW_ERRATUM(osvw_id, ...)  { osvw_id, __VA_ARGS__, 0 }
+#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \
+        ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end))
+#define AMD_MODEL_RANGE_FAMILY(range)   (((range) >> 24) & 0xff)
+#define AMD_MODEL_RANGE_START(range)    (((range) >> 12) & 0xfff)
+#define AMD_MODEL_RANGE_END(range)      ((range) & 0xfff)
+
+static const int amd_erratum_400[] =
         AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
                             AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
-EXPORT_SYMBOL_GPL(amd_erratum_400);
 
-const int amd_erratum_383[] =
+static const int amd_erratum_383[] =
         AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
-EXPORT_SYMBOL_GPL(amd_erratum_383);
 
-bool cpu_has_amd_erratum(const int *erratum)
+static bool cpu_has_amd_erratum(const int *erratum)
 {
         struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info);
         int osvw_id = *erratum++;
@@ -908,5 +920,3 @@ bool cpu_has_amd_erratum(const int *erratum)
 
         return false;
 }
-
-EXPORT_SYMBOL_GPL(cpu_has_amd_erratum);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index af6455e3fcc9..4112be9a4659 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -59,7 +59,7 @@ static void __init check_fpu(void)
          * trap_init() enabled FXSR and company _before_ testing for FP
          * problems here.
          *
-         * Test for the divl bug..
+         * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
          */
         __asm__("fninit\n\t"
                 "fldl %1\n\t"
@@ -75,26 +75,12 @@ static void __init check_fpu(void)
 
         kernel_fpu_end();
 
-        boot_cpu_data.fdiv_bug = fdiv_bug;
-        if (boot_cpu_data.fdiv_bug)
+        if (fdiv_bug) {
+                set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
                 pr_warn("Hmm, FPU with FDIV bug\n");
+        }
 }
 
-/*
- * Check whether we are able to run this kernel safely on SMP.
- *
- * - i386 is no longer supported.
- * - In order to run on anything without a TSC, we need to be
- *   compiled for a i486.
- */
-
-static void __init check_config(void)
-{
-        if (boot_cpu_data.x86 < 4)
-                panic("Kernel requires i486+ for 'invlpg' and other features");
-}
-
-
 void __init check_bugs(void)
 {
         identify_boot_cpu();
@@ -102,7 +88,17 @@ void __init check_bugs(void)
         pr_info("CPU: ");
         print_cpu_info(&boot_cpu_data);
 #endif
-        check_config();
+
+        /*
+         * Check whether we are able to run this kernel safely on SMP.
+         *
+         * - i386 is no longer supported.
+         * - In order to run on anything without a TSC, we need to be
+         *   compiled for a i486.
+         */
+        if (boot_cpu_data.x86 < 4)
+                panic("Kernel requires i486+ for 'invlpg' and other features");
+
         init_utsname()->machine[1] =
                 '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
         alternative_instructions();
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d814772c5bed..22018f70a671 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -920,6 +920,10 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
                 /* AND the already accumulated flags with these */
                 for (i = 0; i < NCAPINTS; i++)
                         boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
+
+                /* OR, i.e. replicate the bug flags */
+                for (i = NCAPINTS; i < NCAPINTS + NBUGINTS; i++)
+                        c->x86_capability[i] |= boot_cpu_data.x86_capability[i];
         }
 
         /* Init Machine Check Exception if available. */
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 4fbd384fb645..d048d5ca43c1 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -249,7 +249,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
                 /* Emulate MTRRs using Cyrix's ARRs. */
                 set_cpu_cap(c, X86_FEATURE_CYRIX_ARR);
                 /* 6x86's contain this bug */
-                c->coma_bug = 1;
+                set_cpu_bug(c, X86_BUG_COMA);
                 break;
 
         case 4: /* MediaGX/GXm or Geode GXM/GXLV/GX1 */
@@ -317,7 +317,8 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
                         /* Enable MMX extensions (App note 108) */
                         setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1);
                 } else {
-                        c->coma_bug = 1;      /* 6x86MX, it has the bug. */
+                        /* A 6x86MX - it has the bug. */
+                        set_cpu_bug(c, X86_BUG_COMA);
                 }
                 tmp = (!(dir0_lsn & 7) || dir0_lsn & 1) ? 2 : 0;
                 Cx86_cb[tmp] = cyrix_model_mult2[dir0_lsn & 7];
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 1905ce98bee0..9b0c441c03f5 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -96,6 +96,18 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
                         sched_clock_stable = 1;
         }
 
+        /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
+        if (c->x86 == 6) {
+                switch (c->x86_model) {
+                case 0x27:      /* Penwell */
+                case 0x35:      /* Cloverview */
+                        set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3);
+                        break;
+                default:
+                        break;
+                }
+        }
+
         /*
          * There is a known erratum on Pentium III and Core Solo
          * and Core Duo CPUs.
@@ -164,20 +176,6 @@ int __cpuinit ppro_with_ram_bug(void)
         return 0;
 }
 
-#ifdef CONFIG_X86_F00F_BUG
-static void __cpuinit trap_init_f00f_bug(void)
-{
-        __set_fixmap(FIX_F00F_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO);
-
-        /*
-         * Update the IDT descriptor and reload the IDT so that
-         * it uses the read-only mapped virtual address.
-         */
-        idt_descr.address = fix_to_virt(FIX_F00F_IDT);
-        load_idt(&idt_descr);
-}
-#endif
-
 static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c)
 {
         /* calling is from identify_secondary_cpu() ? */
@@ -206,16 +204,14 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
         /*
          * All current models of Pentium and Pentium with MMX technology CPUs
          * have the F0 0F bug, which lets nonprivileged users lock up the
-         * system.
-         * Note that the workaround only should be initialized once...
+         * system. Announce that the fault handler will be checking for it.
          */
-        c->f00f_bug = 0;
+        clear_cpu_bug(c, X86_BUG_F00F);
         if (!paravirt_enabled() && c->x86 == 5) {
                 static int f00f_workaround_enabled;
 
-                c->f00f_bug = 1;
+                set_cpu_bug(c, X86_BUG_F00F);
                 if (!f00f_workaround_enabled) {
-                        trap_init_f00f_bug();
                         printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n");
                         f00f_workaround_enabled = 1;
                 }
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7bc126346ace..9239504b41cb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2358,7 +2358,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
         if (action == CPU_POST_DEAD) {
                 /* intentionally ignoring frozen here */
-                cmci_rediscover(cpu);
+                cmci_rediscover();
         }
 
         return NOTIFY_OK;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 1ac581f38dfa..9cb52767999a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -33,7 +33,6 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 
-#define NR_BANKS          6
 #define NR_BLOCKS         9
 #define THRESHOLD_MAX     0xFFF
 #define INT_TYPE_APIC     0x00020000
@@ -57,12 +56,7 @@ static const char * const th_names[] = {
         "execution_unit",
 };
 
-static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
-
-static unsigned char shared_bank[NR_BANKS] = {
-        0, 0, 0, 0, 1
-};
-
+static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
 static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */
 
 static void amd_threshold_interrupt(void);
@@ -79,6 +73,12 @@ struct thresh_restart {
         u16                     old_limit;
 };
 
+static inline bool is_shared_bank(int bank)
+{
+        /* Bank 4 is for northbridge reporting and is thus shared */
+        return (bank == 4);
+}
+
 static const char * const bank4_names(struct threshold_block *b)
 {
         switch (b->address) {
@@ -214,7 +214,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
         unsigned int bank, block;
         int offset = -1;
 
-        for (bank = 0; bank < NR_BANKS; ++bank) {
+        for (bank = 0; bank < mca_cfg.banks; ++bank) {
                 for (block = 0; block < NR_BLOCKS; ++block) {
                         if (block == 0)
                                 address = MSR_IA32_MC0_MISC + bank * 4;
@@ -276,7 +276,7 @@ static void amd_threshold_interrupt(void)
         mce_setup(&m);
 
         /* assume first bank caused it */
-        for (bank = 0; bank < NR_BANKS; ++bank) {
+        for (bank = 0; bank < mca_cfg.banks; ++bank) {
                 if (!(per_cpu(bank_map, m.cpu) & (1 << bank)))
                         continue;
                 for (block = 0; block < NR_BLOCKS; ++block) {
@@ -467,7 +467,7 @@ static __cpuinit int allocate_threshold_blocks(unsigned int cpu,
         u32 low, high;
         int err;
 
-        if ((bank >= NR_BANKS) || (block >= NR_BLOCKS))
+        if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
                 return 0;
 
         if (rdmsr_safe_on_cpu(cpu, address, &low, &high))
@@ -575,7 +575,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
         const char *name = th_names[bank];
         int err = 0;
 
-        if (shared_bank[bank]) {
+        if (is_shared_bank(bank)) {
                 nb = node_to_amd_nb(amd_get_nb_id(cpu));
 
                 /* threshold descriptor already initialized on this node? */
@@ -609,7 +609,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
         per_cpu(threshold_banks, cpu)[bank] = b;
 
-        if (shared_bank[bank]) {
+        if (is_shared_bank(bank)) {
                 atomic_set(&b->cpus, 1);
 
                 /* nb is already initialized, see above */
@@ -635,9 +635,17 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 static __cpuinit int threshold_create_device(unsigned int cpu)
 {
         unsigned int bank;
+        struct threshold_bank **bp;
         int err = 0;
 
-        for (bank = 0; bank < NR_BANKS; ++bank) {
+        bp = kzalloc(sizeof(struct threshold_bank *) * mca_cfg.banks,
+                     GFP_KERNEL);
+        if (!bp)
+                return -ENOMEM;
+
+        per_cpu(threshold_banks, cpu) = bp;
+
+        for (bank = 0; bank < mca_cfg.banks; ++bank) {
                 if (!(per_cpu(bank_map, cpu) & (1 << bank)))
                         continue;
                 err = threshold_create_bank(cpu, bank);
@@ -691,7 +699,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank)
         if (!b->blocks)
                 goto free_out;
 
-        if (shared_bank[bank]) {
+        if (is_shared_bank(bank)) {
                 if (!atomic_dec_and_test(&b->cpus)) {
                         __threshold_remove_blocks(b);
                         per_cpu(threshold_banks, cpu)[bank] = NULL;
@@ -719,11 +727,12 @@ static void threshold_remove_device(unsigned int cpu)
 {
         unsigned int bank;
 
-        for (bank = 0; bank < NR_BANKS; ++bank) {
+        for (bank = 0; bank < mca_cfg.banks; ++bank) {
                 if (!(per_cpu(bank_map, cpu) & (1 << bank)))
                         continue;
                 threshold_remove_bank(cpu, bank);
         }
+        kfree(per_cpu(threshold_banks, cpu));
 }
 
 /* get notified when a cpu comes on/off */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 402c454fbff0..ae1697c2afe3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -285,39 +285,24 @@ void cmci_clear(void)
         raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
-static long cmci_rediscover_work_func(void *arg)
+static void cmci_rediscover_work_func(void *arg)
 {
         int banks;
 
         /* Recheck banks in case CPUs don't all have the same */
         if (cmci_supported(&banks))
                 cmci_discover(banks);
-
-        return 0;
 }
 
-/*
- * After a CPU went down cycle through all the others and rediscover
- * Must run in process context.
- */
-void cmci_rediscover(int dying)
+/* After a CPU went down cycle through all the others and rediscover */
+void cmci_rediscover(void)
 {
-        int cpu, banks;
+        int banks;
 
         if (!cmci_supported(&banks))
                 return;
 
-        for_each_online_cpu(cpu) {
-                if (cpu == dying)
-                        continue;
-
-                if (cpu == smp_processor_id()) {
-                        cmci_rediscover_work_func(NULL);
-                        continue;
-                }
-
-                work_on_cpu(cpu, cmci_rediscover_work_func, NULL);
-        }
+        on_each_cpu(cmci_rediscover_work_func, NULL, 1);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mkcapflags.pl b/arch/x86/kernel/cpu/mkcapflags.pl
deleted file mode 100644
index 091972ef49de..000000000000
--- a/arch/x86/kernel/cpu/mkcapflags.pl
+++ /dev/null
@@ -1,48 +0,0 @@
-#!/usr/bin/perl -w
-#
-# Generate the x86_cap_flags[] array from include/asm-x86/cpufeature.h
-#
-
-($in, $out) = @ARGV;
-
-open(IN, "< $in\0")   or die "$0: cannot open: $in: $!\n";
-open(OUT, "> $out\0") or die "$0: cannot create: $out: $!\n";
-
-print OUT "#ifndef _ASM_X86_CPUFEATURE_H\n";
-print OUT "#include <asm/cpufeature.h>\n";
-print OUT "#endif\n";
-print OUT "\n";
-print OUT "const char * const x86_cap_flags[NCAPINTS*32] = {\n";
-
-%features = ();
-$err = 0;
-
-while (defined($line = <IN>)) {
-        if ($line =~ /^\s*\#\s*define\s+(X86_FEATURE_(\S+))\s+(.*)$/) {
-                $macro = $1;
-                $feature = "\L$2";
-                $tail = $3;
-                if ($tail =~ /\/\*\s*\"([^"]*)\".*\*\//) {
-                        $feature = "\L$1";
-                }
-
-                next if ($feature eq '');
-
-                if ($features{$feature}++) {
-                        print STDERR "$in: duplicate feature name: $feature\n";
-                        $err++;
-                }
-                printf OUT "\t%-32s = \"%s\",\n", "[$macro]", $feature;
-        }
-}
-print OUT "};\n";
-
-close(IN);
-close(OUT);
-
-if ($err) {
-        unlink($out);
-        exit(1);
-}
-
-exit(0);
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
new file mode 100644
index 000000000000..2bf616505499
--- /dev/null
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -0,0 +1,41 @@
+#!/bin/sh
+#
+# Generate the x86_cap_flags[] array from include/asm/cpufeature.h
+#
+
+IN=$1
+OUT=$2
+
+TABS="$(printf '\t\t\t\t\t')"
+trap 'rm "$OUT"' EXIT
+
+(
+        echo "#ifndef _ASM_X86_CPUFEATURE_H"
+        echo "#include <asm/cpufeature.h>"
+        echo "#endif"
+        echo ""
+        echo "const char * const x86_cap_flags[NCAPINTS*32] = {"
+
+        # Iterate through any input lines starting with #define X86_FEATURE_
+        sed -n -e 's/\t/ /g' -e 's/^ *# *define *X86_FEATURE_//p' $IN |
+        while read i
+        do
+                # Name is everything up to the first whitespace
+                NAME="$(echo "$i" | sed 's/ .*//')"
+
+                # If the /* comment */ starts with a quote string, grab that.
+                VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')"
+                [ -z "$VALUE" ] && VALUE="\"$NAME\""
+                [ "$VALUE" == '""' ] && continue
+
+                # Name is uppercase, VALUE is all lowercase
+                VALUE="$(echo "$VALUE" | tr A-Z a-z)"
+
+                TABCOUNT=$(( ( 5*8 - 14 - $(echo "$NAME" | wc -c) ) / 8 ))
+                printf "\t[%s]%.*s = %s,\n" \
+                        "X86_FEATURE_$NAME" "$TABCOUNT" "$TABS" "$VALUE"
+        done
+        echo "};"
+) > $OUT
+
+trap - EXIT
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index a7d26d83fb70..8f4be53ea04b 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -35,13 +35,6 @@ static bool __init ms_hyperv_platform(void)
         if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
                 return false;
 
-        /*
-         * Xen emulates Hyper-V to support enlightened Windows.
-         * Check to see first if we are on a Xen Hypervisor.
-         */
-        if (xen_cpuid_base())
-                return false;
-
         cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
               &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
 
@@ -82,12 +75,6 @@ static void __init ms_hyperv_init_platform(void)
 
         if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
                 clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
-#if IS_ENABLED(CONFIG_HYPERV)
-        /*
-         * Setup the IDT for hypervisor callback.
-         */
-        alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
-#endif
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
@@ -103,6 +90,11 @@ static irq_handler_t vmbus_isr;
 
 void hv_register_vmbus_handler(int irq, irq_handler_t handler)
 {
+        /*
+         * Setup the IDT for hypervisor callback.
+         */
+        alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
+
         vmbus_irq = irq;
         vmbus_isr = handler;
 }
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index bf0f01aea994..1025f3c99d20 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -180,8 +180,9 @@ static void release_pmc_hardware(void) {}
 
 static bool check_hw_exists(void)
 {
-        u64 val, val_new = ~0;
-        int i, reg, ret = 0;
+        u64 val, val_fail, val_new= ~0;
+        int i, reg, reg_fail, ret = 0;
+        int bios_fail = 0;
 
         /*
          * Check to see if the BIOS enabled any of the counters, if so
@@ -192,8 +193,11 @@ static bool check_hw_exists(void)
                 ret = rdmsrl_safe(reg, &val);
                 if (ret)
                         goto msr_fail;
-                if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
-                        goto bios_fail;
+                if (val & ARCH_PERFMON_EVENTSEL_ENABLE) {
+                        bios_fail = 1;
+                        val_fail = val;
+                        reg_fail = reg;
+                }
         }
 
         if (x86_pmu.num_counters_fixed) {
@@ -202,8 +206,11 @@ static bool check_hw_exists(void)
                 if (ret)
                         goto msr_fail;
                 for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
-                        if (val & (0x03 << i*4))
-                                goto bios_fail;
+                        if (val & (0x03 << i*4)) {
+                                bios_fail = 1;
+                                val_fail = val;
+                                reg_fail = reg;
+                        }
                 }
         }
 
@@ -221,14 +228,13 @@ static bool check_hw_exists(void)
         if (ret || val != val_new)
                 goto msr_fail;
 
-        return true;
-
-bios_fail:
         /*
          * We still allow the PMU driver to operate:
          */
-        printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n");
-        printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val);
+        if (bios_fail) {
+                printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n");
+                printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg_fail, val_fail);
+        }
 
         return true;
 
@@ -1316,9 +1322,16 @@ static struct attribute_group x86_pmu_format_group = {
  */
 static void __init filter_events(struct attribute **attrs)
 {
+        struct device_attribute *d;
+        struct perf_pmu_events_attr *pmu_attr;
         int i, j;
 
         for (i = 0; attrs[i]; i++) {
+                d = (struct device_attribute *)attrs[i];
+                pmu_attr = container_of(d, struct perf_pmu_events_attr, attr);
+                /* str trumps id */
+                if (pmu_attr->event_str)
+                        continue;
                 if (x86_pmu.event_map(i))
                         continue;
 
@@ -1330,22 +1343,45 @@ static void __init filter_events(struct attribute **attrs)
         }
 }
 
-static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+/* Merge two pointer arrays */
+static __init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
+{
+        struct attribute **new;
+        int j, i;
+
+        for (j = 0; a[j]; j++)
+                ;
+        for (i = 0; b[i]; i++)
+                j++;
+        j++;
+
+        new = kmalloc(sizeof(struct attribute *) * j, GFP_KERNEL);
+        if (!new)
+                return NULL;
+
+        j = 0;
+        for (i = 0; a[i]; i++)
+                new[j++] = a[i];
+        for (i = 0; b[i]; i++)
+                new[j++] = b[i];
+        new[j] = NULL;
+
+        return new;
+}
+
+ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
                           char *page)
 {
         struct perf_pmu_events_attr *pmu_attr = \
                 container_of(attr, struct perf_pmu_events_attr, attr);
-
         u64 config = x86_pmu.event_map(pmu_attr->id);
-        return x86_pmu.events_sysfs_show(page, config);
-}
 
-#define EVENT_VAR(_id)  event_attr_##_id
-#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
+        /* string trumps id */
+        if (pmu_attr->event_str)
+                return sprintf(page, "%s", pmu_attr->event_str);
 
-#define EVENT_ATTR(_name, _id)                                          \
-        PMU_EVENT_ATTR(_name, EVENT_VAR(_id), PERF_COUNT_HW_##_id,      \
-                        events_sysfs_show)
+        return x86_pmu.events_sysfs_show(page, config);
+}
 
 EVENT_ATTR(cpu-cycles,                  CPU_CYCLES              );
 EVENT_ATTR(instructions,                INSTRUCTIONS            );
@@ -1459,16 +1495,27 @@ static int __init init_hw_perf_events(void)
 
         unconstrained = (struct event_constraint)
                 __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
-                                   0, x86_pmu.num_counters, 0);
+                                   0, x86_pmu.num_counters, 0, 0);
 
         x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
         x86_pmu_format_group.attrs = x86_pmu.format_attrs;
 
+        if (x86_pmu.event_attrs)
+                x86_pmu_events_group.attrs = x86_pmu.event_attrs;
+
         if (!x86_pmu.events_sysfs_show)
                 x86_pmu_events_group.attrs = &empty_attrs;
         else
                 filter_events(x86_pmu_events_group.attrs);
 
+        if (x86_pmu.cpu_events) {
+                struct attribute **tmp;
+
+                tmp = merge_attr(x86_pmu_events_group.attrs, x86_pmu.cpu_events);
+                if (!WARN_ON(!tmp))
+                        x86_pmu_events_group.attrs = tmp;
+        }
+
         pr_info("... version:                %d\n",     x86_pmu.version);
         pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
         pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 7f5c75c2afdd..ba9aadfa683b 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -46,6 +46,7 @@ enum extra_reg_type {
         EXTRA_REG_RSP_0 = 0,    /* offcore_response_0 */
         EXTRA_REG_RSP_1 = 1,    /* offcore_response_1 */
         EXTRA_REG_LBR   = 2,    /* lbr_select */
+        EXTRA_REG_LDLAT = 3,    /* ld_lat_threshold */
 
         EXTRA_REG_MAX           /* number of entries needed */
 };
@@ -59,7 +60,13 @@ struct event_constraint {
         u64     cmask;
         int     weight;
         int     overlap;
+        int     flags;
 };
+/*
+ * struct event_constraint flags
+ */
+#define PERF_X86_EVENT_PEBS_LDLAT       0x1 /* ld+ldlat data address sampling */
+#define PERF_X86_EVENT_PEBS_ST          0x2 /* st data address sampling */
 
 struct amd_nb {
         int nb_id;  /* NorthBridge id */
@@ -170,16 +177,17 @@ struct cpu_hw_events {
         void                            *kfree_on_online;
 };
 
-#define __EVENT_CONSTRAINT(c, n, m, w, o) {\
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
         { .idxmsk64 = (n) },            \
         .code = (c),                    \
         .cmask = (m),                   \
         .weight = (w),                  \
         .overlap = (o),                 \
+        .flags = f,                     \
 }
 
 #define EVENT_CONSTRAINT(c, n, m)       \
-        __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0)
+        __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
 
 /*
  * The overlap flag marks event constraints with overlapping counter
@@ -203,7 +211,7 @@ struct cpu_hw_events {
  * and its counter masks must be kept at a minimum.
  */
 #define EVENT_CONSTRAINT_OVERLAP(c, n, m)       \
-        __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1)
+        __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1, 0)
 
 /*
  * Constraint on the Event code.
@@ -231,6 +239,14 @@ struct cpu_hw_events {
 #define INTEL_UEVENT_CONSTRAINT(c, n)   \
         EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
 
+#define INTEL_PLD_CONSTRAINT(c, n)      \
+        __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+                           HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
+
+#define INTEL_PST_CONSTRAINT(c, n)      \
+        __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+                          HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
+
 #define EVENT_CONSTRAINT_END            \
         EVENT_CONSTRAINT(0, 0, 0)
 
@@ -260,12 +276,22 @@ struct extra_reg {
         .msr = (ms),            \
         .config_mask = (m),     \
         .valid_mask = (vm),     \
-        .idx = EXTRA_REG_##i    \
+        .idx = EXTRA_REG_##i,   \
         }
 
 #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx)      \
         EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx)
 
+#define INTEL_UEVENT_EXTRA_REG(event, msr, vm, idx) \
+        EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT | \
+                        ARCH_PERFMON_EVENTSEL_UMASK, vm, idx)
+
+#define INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(c) \
+        INTEL_UEVENT_EXTRA_REG(c, \
+                               MSR_PEBS_LD_LAT_THRESHOLD, \
+                               0xffff, \
+                               LDLAT)
+
 #define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0)
 
 union perf_capabilities {
@@ -355,8 +381,10 @@ struct x86_pmu {
          */
         int             attr_rdpmc;
         struct attribute **format_attrs;
+        struct attribute **event_attrs;
 
         ssize_t         (*events_sysfs_show)(char *page, u64 config);
+        struct attribute **cpu_events;
 
         /*
          * CPU Hotplug hooks
@@ -421,6 +449,23 @@ do {									\
 #define ERF_NO_HT_SHARING       1
 #define ERF_HAS_RSP_1           2
 
+#define EVENT_VAR(_id)  event_attr_##_id
+#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
+
+#define EVENT_ATTR(_name, _id)                                          \
+static struct perf_pmu_events_attr EVENT_VAR(_id) = {                   \
+        .attr           = __ATTR(_name, 0444, events_sysfs_show, NULL), \
+        .id             = PERF_COUNT_HW_##_id,                          \
+        .event_str      = NULL,                                         \
+};
+
+#define EVENT_ATTR_STR(_name, v, str)                                   \
+static struct perf_pmu_events_attr event_attr_##v = {                   \
+        .attr           = __ATTR(_name, 0444, events_sysfs_show, NULL), \
+        .id             = 0,                                            \
+        .event_str      = str,                                          \
+};
+
 extern struct x86_pmu x86_pmu __read_mostly;
 
 DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
@@ -628,6 +673,9 @@ int p6_pmu_init(void);
 
 int knc_pmu_init(void);
 
+ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+                          char *page);
+
 #else /* CONFIG_CPU_SUP_INTEL */
 
 static inline void reserve_ds_buffers(void)
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index dfdab42aed27..7e28d9467bb4 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -132,14 +132,11 @@ static u64 amd_pmu_event_map(int hw_event)
         return amd_perfmon_event_map[hw_event];
 }
 
-static struct event_constraint *amd_nb_event_constraint;
-
 /*
  * Previously calculated offsets
  */
 static unsigned int event_offsets[X86_PMC_IDX_MAX] __read_mostly;
 static unsigned int count_offsets[X86_PMC_IDX_MAX] __read_mostly;
-static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly;
 
 /*
  * Legacy CPUs:
@@ -147,14 +144,10 @@ static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly;
  *
  * CPUs with core performance counter extensions:
  *   6 counters starting at 0xc0010200 each offset by 2
- *
- * CPUs with north bridge performance counter extensions:
- *   4 additional counters starting at 0xc0010240 each offset by 2
- *   (indexed right above either one of the above core counters)
  */
 static inline int amd_pmu_addr_offset(int index, bool eventsel)
 {
-        int offset, first, base;
+        int offset;
 
         if (!index)
                 return index;
@@ -167,23 +160,7 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel)
         if (offset)
                 return offset;
 
-        if (amd_nb_event_constraint &&
-            test_bit(index, amd_nb_event_constraint->idxmsk)) {
-                /*
-                 * calculate the offset of NB counters with respect to
-                 * base eventsel or perfctr
-                 */
-
-                first = find_first_bit(amd_nb_event_constraint->idxmsk,
-                                       X86_PMC_IDX_MAX);
-
-                if (eventsel)
-                        base = MSR_F15H_NB_PERF_CTL - x86_pmu.eventsel;
-                else
-                        base = MSR_F15H_NB_PERF_CTR - x86_pmu.perfctr;
-
-                offset = base + ((index - first) << 1);
-        } else if (!cpu_has_perfctr_core)
+        if (!cpu_has_perfctr_core)
                 offset = index;
         else
                 offset = index << 1;
@@ -196,36 +173,6 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel)
         return offset;
 }
 
-static inline int amd_pmu_rdpmc_index(int index)
-{
-        int ret, first;
-
-        if (!index)
-                return index;
-
-        ret = rdpmc_indexes[index];
-
-        if (ret)
-                return ret;
-
-        if (amd_nb_event_constraint &&
-            test_bit(index, amd_nb_event_constraint->idxmsk)) {
-                /*
-                 * according to the mnual, ECX value of the NB counters is
-                 * the index of the NB counter (0, 1, 2 or 3) plus 6
-                 */
-
-                first = find_first_bit(amd_nb_event_constraint->idxmsk,
-                                       X86_PMC_IDX_MAX);
-                ret = index - first + 6;
-        } else
-                ret = index;
-
-        rdpmc_indexes[index] = ret;
-
-        return ret;
-}
-
 static int amd_core_hw_config(struct perf_event *event)
 {
         if (event->attr.exclude_host && event->attr.exclude_guest)
@@ -245,34 +192,6 @@ static int amd_core_hw_config(struct perf_event *event)
 }
 
 /*
- * NB counters do not support the following event select bits:
- *   Host/Guest only
- *   Counter mask
- *   Invert counter mask
- *   Edge detect
- *   OS/User mode
- */
-static int amd_nb_hw_config(struct perf_event *event)
-{
-        /* for NB, we only allow system wide counting mode */
-        if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
-                return -EINVAL;
-
-        if (event->attr.exclude_user || event->attr.exclude_kernel ||
-            event->attr.exclude_host || event->attr.exclude_guest)
-                return -EINVAL;
-
-        event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR |
-                              ARCH_PERFMON_EVENTSEL_OS);
-
-        if (event->hw.config & ~(AMD64_RAW_EVENT_MASK_NB |
-                                 ARCH_PERFMON_EVENTSEL_INT))
-                return -EINVAL;
-
-        return 0;
-}
-
-/*
  * AMD64 events are detected based on their event codes.
  */
 static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc)
@@ -285,11 +204,6 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc)
         return (hwc->config & 0xe0) == 0xe0;
 }
 
-static inline int amd_is_perfctr_nb_event(struct hw_perf_event *hwc)
-{
-        return amd_nb_event_constraint && amd_is_nb_event(hwc);
-}
-
 static inline int amd_has_nb(struct cpu_hw_events *cpuc)
 {
         struct amd_nb *nb = cpuc->amd_nb;
@@ -315,9 +229,6 @@ static int amd_pmu_hw_config(struct perf_event *event)
         if (event->attr.type == PERF_TYPE_RAW)
                 event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK;
 
-        if (amd_is_perfctr_nb_event(&event->hw))
-                return amd_nb_hw_config(event);
-
         return amd_core_hw_config(event);
 }
 
@@ -341,19 +252,6 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc,
         }
 }
 
-static void amd_nb_interrupt_hw_config(struct hw_perf_event *hwc)
-{
-        int core_id = cpu_data(smp_processor_id()).cpu_core_id;
-
-        /* deliver interrupts only to this core */
-        if (hwc->config & ARCH_PERFMON_EVENTSEL_INT) {
-                hwc->config |= AMD64_EVENTSEL_INT_CORE_ENABLE;
-                hwc->config &= ~AMD64_EVENTSEL_INT_CORE_SEL_MASK;
-                hwc->config |= (u64)(core_id) <<
-                        AMD64_EVENTSEL_INT_CORE_SEL_SHIFT;
-        }
-}
-
  /*
   * AMD64 NorthBridge events need special treatment because
   * counter access needs to be synchronized across all cores
@@ -441,9 +339,6 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev
         if (new == -1)
                 return &emptyconstraint;
 
-        if (amd_is_perfctr_nb_event(hwc))
-                amd_nb_interrupt_hw_config(hwc);
-
         return &nb->event_constraints[new];
 }
 
@@ -543,8 +438,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
         if (!(amd_has_nb(cpuc) && amd_is_nb_event(&event->hw)))
                 return &unconstrained;
 
-        return __amd_get_nb_event_constraints(cpuc, event,
-                                              amd_nb_event_constraint);
+        return __amd_get_nb_event_constraints(cpuc, event, NULL);
 }
 
 static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
@@ -643,9 +537,6 @@ static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT_OVERLAP(0, 0x09,
 static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0);
 static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
 
-static struct event_constraint amd_NBPMC96 = EVENT_CONSTRAINT(0, 0x3C0, 0);
-static struct event_constraint amd_NBPMC74 = EVENT_CONSTRAINT(0, 0xF0, 0);
-
 static struct event_constraint *
 amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
 {
@@ -711,8 +602,8 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev
                         return &amd_f15_PMC20;
                 }
         case AMD_EVENT_NB:
-                return __amd_get_nb_event_constraints(cpuc, event,
-                                                      amd_nb_event_constraint);
+                /* moved to perf_event_amd_uncore.c */
+                return &emptyconstraint;
         default:
                 return &emptyconstraint;
         }
@@ -738,7 +629,6 @@ static __initconst const struct x86_pmu amd_pmu = {
         .eventsel               = MSR_K7_EVNTSEL0,
         .perfctr                = MSR_K7_PERFCTR0,
         .addr_offset            = amd_pmu_addr_offset,
-        .rdpmc_index            = amd_pmu_rdpmc_index,
         .event_map              = amd_pmu_event_map,
         .max_events             = ARRAY_SIZE(amd_perfmon_event_map),
         .num_counters           = AMD64_NUM_COUNTERS,
@@ -790,23 +680,6 @@ static int setup_perfctr_core(void)
         return 0;
 }
 
-static int setup_perfctr_nb(void)
-{
-        if (!cpu_has_perfctr_nb)
-                return -ENODEV;
-
-        x86_pmu.num_counters += AMD64_NUM_COUNTERS_NB;
-
-        if (cpu_has_perfctr_core)
-                amd_nb_event_constraint = &amd_NBPMC96;
-        else
-                amd_nb_event_constraint = &amd_NBPMC74;
-
-        printk(KERN_INFO "perf: AMD northbridge performance counters detected\n");
-
-        return 0;
-}
-
 __init int amd_pmu_init(void)
 {
         /* Performance-monitoring supported from K7 and later: */
@@ -817,7 +690,6 @@ __init int amd_pmu_init(void)
 
         setup_event_constraints();
         setup_perfctr_core();
-        setup_perfctr_nb();
 
         /* Events are common for all AMDs */
         memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
new file mode 100644
index 000000000000..c0c661adf03e
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -0,0 +1,547 @@
+/*
+ * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ *
+ * Author: Jacob Shin <jacob.shin@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+
+#include <asm/cpufeature.h>
+#include <asm/perf_event.h>
+#include <asm/msr.h>
+
+#define NUM_COUNTERS_NB         4
+#define NUM_COUNTERS_L2         4
+#define MAX_COUNTERS            NUM_COUNTERS_NB
+
+#define RDPMC_BASE_NB           6
+#define RDPMC_BASE_L2           10
+
+#define COUNTER_SHIFT           16
+
+struct amd_uncore {
+        int id;
+        int refcnt;
+        int cpu;
+        int num_counters;
+        int rdpmc_base;
+        u32 msr_base;
+        cpumask_t *active_mask;
+        struct pmu *pmu;
+        struct perf_event *events[MAX_COUNTERS];
+        struct amd_uncore *free_when_cpu_online;
+};
+
+static struct amd_uncore * __percpu *amd_uncore_nb;
+static struct amd_uncore * __percpu *amd_uncore_l2;
+
+static struct pmu amd_nb_pmu;
+static struct pmu amd_l2_pmu;
+
+static cpumask_t amd_nb_active_mask;
+static cpumask_t amd_l2_active_mask;
+
+static bool is_nb_event(struct perf_event *event)
+{
+        return event->pmu->type == amd_nb_pmu.type;
+}
+
+static bool is_l2_event(struct perf_event *event)
+{
+        return event->pmu->type == amd_l2_pmu.type;
+}
+
+static struct amd_uncore *event_to_amd_uncore(struct perf_event *event)
+{
+        if (is_nb_event(event) && amd_uncore_nb)
+                return *per_cpu_ptr(amd_uncore_nb, event->cpu);
+        else if (is_l2_event(event) && amd_uncore_l2)
+                return *per_cpu_ptr(amd_uncore_l2, event->cpu);
+
+        return NULL;
+}
+
+static void amd_uncore_read(struct perf_event *event)
+{
+        struct hw_perf_event *hwc = &event->hw;
+        u64 prev, new;
+        s64 delta;
+
+        /*
+         * since we do not enable counter overflow interrupts,
+         * we do not have to worry about prev_count changing on us
+         */
+
+        prev = local64_read(&hwc->prev_count);
+        rdpmcl(hwc->event_base_rdpmc, new);
+        local64_set(&hwc->prev_count, new);
+        delta = (new << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
+        delta >>= COUNTER_SHIFT;
+        local64_add(delta, &event->count);
+}
+
+static void amd_uncore_start(struct perf_event *event, int flags)
+{
+        struct hw_perf_event *hwc = &event->hw;
+
+        if (flags & PERF_EF_RELOAD)
+                wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
+
+        hwc->state = 0;
+        wrmsrl(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE));
+        perf_event_update_userpage(event);
+}
+
+static void amd_uncore_stop(struct perf_event *event, int flags)
+{
+        struct hw_perf_event *hwc = &event->hw;
+
+        wrmsrl(hwc->config_base, hwc->config);
+        hwc->state |= PERF_HES_STOPPED;
+
+        if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+                amd_uncore_read(event);
+                hwc->state |= PERF_HES_UPTODATE;
+        }
+}
+
+static int amd_uncore_add(struct perf_event *event, int flags)
+{
+        int i;
+        struct amd_uncore *uncore = event_to_amd_uncore(event);
+        struct hw_perf_event *hwc = &event->hw;
+
+        /* are we already assigned? */
+        if (hwc->idx != -1 && uncore->events[hwc->idx] == event)
+                goto out;
+
+        for (i = 0; i < uncore->num_counters; i++) {
+                if (uncore->events[i] == event) {
+                        hwc->idx = i;
+                        goto out;
+                }
+        }
+
+        /* if not, take the first available counter */
+        hwc->idx = -1;
+        for (i = 0; i < uncore->num_counters; i++) {
+                if (cmpxchg(&uncore->events[i], NULL, event) == NULL) {
+                        hwc->idx = i;
+                        break;
+                }
+        }
+
+out:
+        if (hwc->idx == -1)
+                return -EBUSY;
+
+        hwc->config_base = uncore->msr_base + (2 * hwc->idx);
+        hwc->event_base = uncore->msr_base + 1 + (2 * hwc->idx);
+        hwc->event_base_rdpmc = uncore->rdpmc_base + hwc->idx;
+        hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+        if (flags & PERF_EF_START)
+                amd_uncore_start(event, PERF_EF_RELOAD);
+
+        return 0;
+}
+
+static void amd_uncore_del(struct perf_event *event, int flags)
+{
+        int i;
+        struct amd_uncore *uncore = event_to_amd_uncore(event);
+        struct hw_perf_event *hwc = &event->hw;
+
+        amd_uncore_stop(event, PERF_EF_UPDATE);
+
+        for (i = 0; i < uncore->num_counters; i++) {
+                if (cmpxchg(&uncore->events[i], event, NULL) == event)
+                        break;
+        }
+
+        hwc->idx = -1;
+}
+
+static int amd_uncore_event_init(struct perf_event *event)
+{
+        struct amd_uncore *uncore;
+        struct hw_perf_event *hwc = &event->hw;
+
+        if (event->attr.type != event->pmu->type)
+                return -ENOENT;
+
+        /*
+         * NB and L2 counters (MSRs) are shared across all cores that share the
+         * same NB / L2 cache. Interrupts can be directed to a single target
+         * core, however, event counts generated by processes running on other
+         * cores cannot be masked out. So we do not support sampling and
+         * per-thread events.
+         */
+        if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
+                return -EINVAL;
+
+        /* NB and L2 counters do not have usr/os/guest/host bits */
+        if (event->attr.exclude_user || event->attr.exclude_kernel ||
+            event->attr.exclude_host || event->attr.exclude_guest)
+                return -EINVAL;
+
+        /* and we do not enable counter overflow interrupts */
+        hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
+        hwc->idx = -1;
+
+        if (event->cpu < 0)
+                return -EINVAL;
+
+        uncore = event_to_amd_uncore(event);
+        if (!uncore)
+                return -ENODEV;
+
+        /*
+         * since request can come in to any of the shared cores, we will remap
+         * to a single common cpu.
+         */
+        event->cpu = uncore->cpu;
+
+        return 0;
+}
+
+static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
+                                            struct device_attribute *attr,
+                                            char *buf)
+{
+        int n;
+        cpumask_t *active_mask;
+        struct pmu *pmu = dev_get_drvdata(dev);
+
+        if (pmu->type == amd_nb_pmu.type)
+                active_mask = &amd_nb_active_mask;
+        else if (pmu->type == amd_l2_pmu.type)
+                active_mask = &amd_l2_active_mask;
+        else
+                return 0;
+
+        n = cpulist_scnprintf(buf, PAGE_SIZE - 2, active_mask);
+        buf[n++] = '\n';
+        buf[n] = '\0';
+        return n;
+}
+static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL);
+
+static struct attribute *amd_uncore_attrs[] = {
+        &dev_attr_cpumask.attr,
+        NULL,
+};
+
+static struct attribute_group amd_uncore_attr_group = {
+        .attrs = amd_uncore_attrs,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-7,32-35");
+PMU_FORMAT_ATTR(umask, "config:8-15");
+
+static struct attribute *amd_uncore_format_attr[] = {
+        &format_attr_event.attr,
+        &format_attr_umask.attr,
+        NULL,
+};
+
+static struct attribute_group amd_uncore_format_group = {
+        .name = "format",
+        .attrs = amd_uncore_format_attr,
+};
+
+static const struct attribute_group *amd_uncore_attr_groups[] = {
+        &amd_uncore_attr_group,
+        &amd_uncore_format_group,
+        NULL,
+};
+
+static struct pmu amd_nb_pmu = {
+        .attr_groups    = amd_uncore_attr_groups,
+        .name           = "amd_nb",
+        .event_init     = amd_uncore_event_init,
+        .add            = amd_uncore_add,
+        .del            = amd_uncore_del,
+        .start          = amd_uncore_start,
+        .stop           = amd_uncore_stop,
+        .read           = amd_uncore_read,
+};
+
+static struct pmu amd_l2_pmu = {
+        .attr_groups    = amd_uncore_attr_groups,
+        .name           = "amd_l2",
+        .event_init     = amd_uncore_event_init,
+        .add            = amd_uncore_add,
+        .del            = amd_uncore_del,
+        .start          = amd_uncore_start,
+        .stop           = amd_uncore_stop,
+        .read           = amd_uncore_read,
+};
+
+static struct amd_uncore * __cpuinit amd_uncore_alloc(unsigned int cpu)
+{
+        return kzalloc_node(sizeof(struct amd_uncore), GFP_KERNEL,
+                        cpu_to_node(cpu));
+}
+
+static void __cpuinit amd_uncore_cpu_up_prepare(unsigned int cpu)
+{
+        struct amd_uncore *uncore;
+
+        if (amd_uncore_nb) {
+                uncore = amd_uncore_alloc(cpu);
+                uncore->cpu = cpu;
+                uncore->num_counters = NUM_COUNTERS_NB;
+                uncore->rdpmc_base = RDPMC_BASE_NB;
+                uncore->msr_base = MSR_F15H_NB_PERF_CTL;
+                uncore->active_mask = &amd_nb_active_mask;
+                uncore->pmu = &amd_nb_pmu;
+                *per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
+        }
+
+        if (amd_uncore_l2) {
+                uncore = amd_uncore_alloc(cpu);
+                uncore->cpu = cpu;
+                uncore->num_counters = NUM_COUNTERS_L2;
+                uncore->rdpmc_base = RDPMC_BASE_L2;
+                uncore->msr_base = MSR_F16H_L2I_PERF_CTL;
+                uncore->active_mask = &amd_l2_active_mask;
+                uncore->pmu = &amd_l2_pmu;
+                *per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
+        }
+}
+
+static struct amd_uncore *
+__cpuinit amd_uncore_find_online_sibling(struct amd_uncore *this,
+                                         struct amd_uncore * __percpu *uncores)
+{
+        unsigned int cpu;
+        struct amd_uncore *that;
+
+        for_each_online_cpu(cpu) {
+                that = *per_cpu_ptr(uncores, cpu);
+
+                if (!that)
+                        continue;
+
+                if (this == that)
+                        continue;
+
+                if (this->id == that->id) {
+                        that->free_when_cpu_online = this;
+                        this = that;
+                        break;
+                }
+        }
+
+        this->refcnt++;
+        return this;
+}
+
+static void __cpuinit amd_uncore_cpu_starting(unsigned int cpu)
+{
+        unsigned int eax, ebx, ecx, edx;
+        struct amd_uncore *uncore;
+
+        if (amd_uncore_nb) {
+                uncore = *per_cpu_ptr(amd_uncore_nb, cpu);
+                cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+                uncore->id = ecx & 0xff;
+
+                uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_nb);
+                *per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
+        }
+
+        if (amd_uncore_l2) {
+                unsigned int apicid = cpu_data(cpu).apicid;
+                unsigned int nshared;
+
+                uncore = *per_cpu_ptr(amd_uncore_l2, cpu);
+                cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx);
+                nshared = ((eax >> 14) & 0xfff) + 1;
+                uncore->id = apicid - (apicid % nshared);
+
+                uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2);
+                *per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
+        }
+}
+
+static void __cpuinit uncore_online(unsigned int cpu,
+                                    struct amd_uncore * __percpu *uncores)
+{
+        struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
+
+        kfree(uncore->free_when_cpu_online);
+        uncore->free_when_cpu_online = NULL;
+
+        if (cpu == uncore->cpu)
+                cpumask_set_cpu(cpu, uncore->active_mask);
+}
+
+static void __cpuinit amd_uncore_cpu_online(unsigned int cpu)
+{
+        if (amd_uncore_nb)
+                uncore_online(cpu, amd_uncore_nb);
+
+        if (amd_uncore_l2)
+                uncore_online(cpu, amd_uncore_l2);
+}
+
+static void __cpuinit uncore_down_prepare(unsigned int cpu,
+                                          struct amd_uncore * __percpu *uncores)
+{
+        unsigned int i;
+        struct amd_uncore *this = *per_cpu_ptr(uncores, cpu);
+
+        if (this->cpu != cpu)
+                return;
+
+        /* this cpu is going down, migrate to a shared sibling if possible */
+        for_each_online_cpu(i) {
+                struct amd_uncore *that = *per_cpu_ptr(uncores, i);
+
+                if (cpu == i)
+                        continue;
+
+                if (this == that) {
+                        perf_pmu_migrate_context(this->pmu, cpu, i);
+                        cpumask_clear_cpu(cpu, that->active_mask);
+                        cpumask_set_cpu(i, that->active_mask);
+                        that->cpu = i;
+                        break;
+                }
+        }
+}
+
+static void __cpuinit amd_uncore_cpu_down_prepare(unsigned int cpu)
+{
+        if (amd_uncore_nb)
+                uncore_down_prepare(cpu, amd_uncore_nb);
+
+        if (amd_uncore_l2)
+                uncore_down_prepare(cpu, amd_uncore_l2);
+}
+
+static void __cpuinit uncore_dead(unsigned int cpu,
+                                  struct amd_uncore * __percpu *uncores)
+{
+        struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
+
+        if (cpu == uncore->cpu)
+                cpumask_clear_cpu(cpu, uncore->active_mask);
+
+        if (!--uncore->refcnt)
+                kfree(uncore);
+        *per_cpu_ptr(amd_uncore_nb, cpu) = NULL;
+}
+
+static void __cpuinit amd_uncore_cpu_dead(unsigned int cpu)
+{
+        if (amd_uncore_nb)
+                uncore_dead(cpu, amd_uncore_nb);
+
+        if (amd_uncore_l2)
+                uncore_dead(cpu, amd_uncore_l2);
+}
+
+static int __cpuinit
+amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action,
+                        void *hcpu)
+{
+        unsigned int cpu = (long)hcpu;
+
+        switch (action & ~CPU_TASKS_FROZEN) {
+        case CPU_UP_PREPARE:
+                amd_uncore_cpu_up_prepare(cpu);
+                break;
+
+        case CPU_STARTING:
+                amd_uncore_cpu_starting(cpu);
+                break;
+
+        case CPU_ONLINE:
+                amd_uncore_cpu_online(cpu);
+                break;
+
+        case CPU_DOWN_PREPARE:
+                amd_uncore_cpu_down_prepare(cpu);
+                break;
+
+        case CPU_UP_CANCELED:
+        case CPU_DEAD:
+                amd_uncore_cpu_dead(cpu);
+                break;
+
+        default:
+                break;
+        }
+
+        return NOTIFY_OK;
+}
+
+static struct notifier_block amd_uncore_cpu_notifier_block __cpuinitdata = {
+        .notifier_call  = amd_uncore_cpu_notifier,
+        .priority       = CPU_PRI_PERF + 1,
+};
+
+static void __init init_cpu_already_online(void *dummy)
+{
+        unsigned int cpu = smp_processor_id();
+
+        amd_uncore_cpu_starting(cpu);
+        amd_uncore_cpu_online(cpu);
+}
+
+static int __init amd_uncore_init(void)
+{
+        unsigned int cpu;
+        int ret = -ENODEV;
+
+        if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+                return -ENODEV;
+
+        if (!cpu_has_topoext)
+                return -ENODEV;
+
+        if (cpu_has_perfctr_nb) {
+                amd_uncore_nb = alloc_percpu(struct amd_uncore *);
+                perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1);
+
+                printk(KERN_INFO "perf: AMD NB counters detected\n");
+                ret = 0;
+        }
+
+        if (cpu_has_perfctr_l2) {
+                amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
+                perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+
+                printk(KERN_INFO "perf: AMD L2I counters detected\n");
+                ret = 0;
+        }
+
+        if (ret)
+                return -ENODEV;
+
+        get_online_cpus();
+        /* init cpus already online before registering for hotplug notifier */
+        for_each_online_cpu(cpu) {
+                amd_uncore_cpu_up_prepare(cpu);
+                smp_call_function_single(cpu, init_cpu_already_online, NULL, 1);
+        }
+
+        register_cpu_notifier(&amd_uncore_cpu_notifier_block);
+        put_online_cpus();
+
+        return 0;
+}
+device_initcall(amd_uncore_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 529c8931fc02..ffd6050a1de4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -81,6 +81,7 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly =
 static struct extra_reg intel_nehalem_extra_regs[] __read_mostly =
 {
         INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
+        INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
         EVENT_EXTRA_END
 };
 
@@ -101,9 +102,15 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
         FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
         FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
         FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+        INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
+        INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
+        INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
+        INTEL_UEVENT_CONSTRAINT(0x06a3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
         INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
         INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
         INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+        INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
+        INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
         EVENT_CONSTRAINT_END
 };
 
@@ -132,6 +139,7 @@ static struct extra_reg intel_westmere_extra_regs[] __read_mostly =
 {
         INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
         INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1),
+        INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
         EVENT_EXTRA_END
 };
 
@@ -149,11 +157,34 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 };
 
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
-        INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
-        INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+        INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
+        INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
+        INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+        INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
         EVENT_EXTRA_END
 };
 
+static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
+        INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
+        INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
+        EVENT_EXTRA_END
+};
+
+EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
+EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
+EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
+
+struct attribute *nhm_events_attrs[] = {
+        EVENT_PTR(mem_ld_nhm),
+        NULL,
+};
+
+struct attribute *snb_events_attrs[] = {
+        EVENT_PTR(mem_ld_snb),
+        EVENT_PTR(mem_st_snb),
+        NULL,
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
         return intel_perfmon_event_map[hw_event];
@@ -1388,8 +1419,11 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 
         if (x86_pmu.event_constraints) {
                 for_each_event_constraint(c, x86_pmu.event_constraints) {
-                        if ((event->hw.config & c->cmask) == c->code)
+                        if ((event->hw.config & c->cmask) == c->code) {
+                                /* hw.flags zeroed at initialization */
+                                event->hw.flags |= c->flags;
                                 return c;
+                        }
                 }
         }
 
@@ -1434,6 +1468,7 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc,
 static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
                                         struct perf_event *event)
 {
+        event->hw.flags = 0;
         intel_put_shared_regs_event_constraints(cpuc, event);
 }
 
@@ -1757,6 +1792,8 @@ static void intel_pmu_flush_branch_stack(void)
 
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
+PMU_FORMAT_ATTR(ldlat, "config1:0-15");
+
 static struct attribute *intel_arch3_formats_attr[] = {
         &format_attr_event.attr,
         &format_attr_umask.attr,
@@ -1767,6 +1804,7 @@ static struct attribute *intel_arch3_formats_attr[] = {
         &format_attr_cmask.attr,
 
         &format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */
+        &format_attr_ldlat.attr, /* PEBS load latency */
         NULL,
 };
 
@@ -2027,6 +2065,8 @@ __init int intel_pmu_init(void)
                 x86_pmu.enable_all = intel_pmu_nhm_enable_all;
                 x86_pmu.extra_regs = intel_nehalem_extra_regs;
 
+                x86_pmu.cpu_events = nhm_events_attrs;
+
                 /* UOPS_ISSUED.STALLED_CYCLES */
                 intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
                         X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
@@ -2070,6 +2110,8 @@ __init int intel_pmu_init(void)
                 x86_pmu.extra_regs = intel_westmere_extra_regs;
                 x86_pmu.er_flags |= ERF_HAS_RSP_1;
 
+                x86_pmu.cpu_events = nhm_events_attrs;
+
                 /* UOPS_ISSUED.STALLED_CYCLES */
                 intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
                         X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
@@ -2093,11 +2135,16 @@ __init int intel_pmu_init(void)
                 x86_pmu.event_constraints = intel_snb_event_constraints;
                 x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
                 x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-                x86_pmu.extra_regs = intel_snb_extra_regs;
+                if (boot_cpu_data.x86_model == 45)
+                        x86_pmu.extra_regs = intel_snbep_extra_regs;
+                else
+                        x86_pmu.extra_regs = intel_snb_extra_regs;
                 /* all extra regs are per-cpu when HT is on */
                 x86_pmu.er_flags |= ERF_HAS_RSP_1;
                 x86_pmu.er_flags |= ERF_NO_HT_SHARING;
 
+                x86_pmu.cpu_events = snb_events_attrs;
+
                 /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
                 intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
                         X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
@@ -2119,11 +2166,16 @@ __init int intel_pmu_init(void)
                 x86_pmu.event_constraints = intel_ivb_event_constraints;
                 x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
                 x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-                x86_pmu.extra_regs = intel_snb_extra_regs;
+                if (boot_cpu_data.x86_model == 62)
+                        x86_pmu.extra_regs = intel_snbep_extra_regs;
+                else
+                        x86_pmu.extra_regs = intel_snb_extra_regs;
                 /* all extra regs are per-cpu when HT is on */
                 x86_pmu.er_flags |= ERF_HAS_RSP_1;
                 x86_pmu.er_flags |= ERF_NO_HT_SHARING;
 
+                x86_pmu.cpu_events = snb_events_attrs;
+
                 /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
                 intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
                         X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 826054a4f2ee..60250f687052 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -24,6 +24,130 @@ struct pebs_record_32 {
 
  */
 
+union intel_x86_pebs_dse {
+        u64 val;
+        struct {
+                unsigned int ld_dse:4;
+                unsigned int ld_stlb_miss:1;
+                unsigned int ld_locked:1;
+                unsigned int ld_reserved:26;
+        };
+        struct {
+                unsigned int st_l1d_hit:1;
+                unsigned int st_reserved1:3;
+                unsigned int st_stlb_miss:1;
+                unsigned int st_locked:1;
+                unsigned int st_reserved2:26;
+        };
+};
+
+
+/*
+ * Map PEBS Load Latency Data Source encodings to generic
+ * memory data source information
+ */
+#define P(a, b) PERF_MEM_S(a, b)
+#define OP_LH (P(OP, LOAD) | P(LVL, HIT))
+#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
+
+static const u64 pebs_data_source[] = {
+        P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
+        OP_LH | P(LVL, L1)  | P(SNOOP, NONE),   /* 0x01: L1 local */
+        OP_LH | P(LVL, LFB) | P(SNOOP, NONE),   /* 0x02: LFB hit */
+        OP_LH | P(LVL, L2)  | P(SNOOP, NONE),   /* 0x03: L2 hit */
+        OP_LH | P(LVL, L3)  | P(SNOOP, NONE),   /* 0x04: L3 hit */
+        OP_LH | P(LVL, L3)  | P(SNOOP, MISS),   /* 0x05: L3 hit, snoop miss */
+        OP_LH | P(LVL, L3)  | P(SNOOP, HIT),    /* 0x06: L3 hit, snoop hit */
+        OP_LH | P(LVL, L3)  | P(SNOOP, HITM),   /* 0x07: L3 hit, snoop hitm */
+        OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HIT),  /* 0x08: L3 miss snoop hit */
+        OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/
+        OP_LH | P(LVL, LOC_RAM)  | P(SNOOP, HIT),  /* 0x0a: L3 miss, shared */
+        OP_LH | P(LVL, REM_RAM1) | P(SNOOP, HIT),  /* 0x0b: L3 miss, shared */
+        OP_LH | P(LVL, LOC_RAM)  | SNOOP_NONE_MISS,/* 0x0c: L3 miss, excl */
+        OP_LH | P(LVL, REM_RAM1) | SNOOP_NONE_MISS,/* 0x0d: L3 miss, excl */
+        OP_LH | P(LVL, IO)  | P(SNOOP, NONE), /* 0x0e: I/O */
+        OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
+};
+
+static u64 precise_store_data(u64 status)
+{
+        union intel_x86_pebs_dse dse;
+        u64 val = P(OP, STORE) | P(SNOOP, NA) | P(LVL, L1) | P(TLB, L2);
+
+        dse.val = status;
+
+        /*
+         * bit 4: TLB access
+         * 1 = stored missed 2nd level TLB
+         *
+         * so it either hit the walker or the OS
+         * otherwise hit 2nd level TLB
+         */
+        if (dse.st_stlb_miss)
+                val |= P(TLB, MISS);
+        else
+                val |= P(TLB, HIT);
+
+        /*
+         * bit 0: hit L1 data cache
+         * if not set, then all we know is that
+         * it missed L1D
+         */
+        if (dse.st_l1d_hit)
+                val |= P(LVL, HIT);
+        else
+                val |= P(LVL, MISS);
+
+        /*
+         * bit 5: Locked prefix
+         */
+        if (dse.st_locked)
+                val |= P(LOCK, LOCKED);
+
+        return val;
+}
+
+static u64 load_latency_data(u64 status)
+{
+        union intel_x86_pebs_dse dse;
+        u64 val;
+        int model = boot_cpu_data.x86_model;
+        int fam = boot_cpu_data.x86;
+
+        dse.val = status;
+
+        /*
+         * use the mapping table for bit 0-3
+         */
+        val = pebs_data_source[dse.ld_dse];
+
+        /*
+         * Nehalem models do not support TLB, Lock infos
+         */
+        if (fam == 0x6 && (model == 26 || model == 30
+            || model == 31 || model == 46)) {
+                val |= P(TLB, NA) | P(LOCK, NA);
+                return val;
+        }
+        /*
+         * bit 4: TLB access
+         * 0 = did not miss 2nd level TLB
+         * 1 = missed 2nd level TLB
+         */
+        if (dse.ld_stlb_miss)
+                val |= P(TLB, MISS) | P(TLB, L2);
+        else
+                val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+        /*
+         * bit 5: locked prefix
+         */
+        if (dse.ld_locked)
+                val |= P(LOCK, LOCKED);
+
+        return val;
+}
+
 struct pebs_record_core {
         u64 flags, ip;
         u64 ax, bx, cx, dx;
@@ -314,10 +438,11 @@ int intel_pmu_drain_bts_buffer(void)
         if (top <= at)
                 return 0;
 
+        memset(&regs, 0, sizeof(regs));
+
         ds->bts_index = ds->bts_buffer_base;
 
         perf_sample_data_init(&data, 0, event->hw.last_period);
-        regs.ip     = 0;
 
         /*
          * Prepare a generic sample, i.e. fill in the invariant fields.
@@ -364,7 +489,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
-        INTEL_EVENT_CONSTRAINT(0x0b, 0xf),    /* MEM_INST_RETIRED.* */
+        INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
         INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
         INTEL_EVENT_CONSTRAINT(0xc0, 0xf),    /* INST_RETIRED.ANY */
@@ -379,7 +504,7 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_westmere_pebs_event_constraints[] = {
-        INTEL_EVENT_CONSTRAINT(0x0b, 0xf),    /* MEM_INST_RETIRED.* */
+        INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
         INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
         INTEL_EVENT_CONSTRAINT(0xc0, 0xf),    /* INSTR_RETIRED.* */
@@ -399,7 +524,8 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
         INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
         INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
+        INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
+        INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
         INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -413,7 +539,8 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
         INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
         INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
+        INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
+        INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
         INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -430,8 +557,10 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 
         if (x86_pmu.pebs_constraints) {
                 for_each_event_constraint(c, x86_pmu.pebs_constraints) {
-                        if ((event->hw.config & c->cmask) == c->code)
+                        if ((event->hw.config & c->cmask) == c->code) {
+                                event->hw.flags |= c->flags;
                                 return c;
+                        }
                 }
         }
 
@@ -446,6 +575,11 @@ void intel_pmu_pebs_enable(struct perf_event *event)
         hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
         cpuc->pebs_enabled |= 1ULL << hwc->idx;
+
+        if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+                cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
+        else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
+                cpuc->pebs_enabled |= 1ULL << 63;
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
@@ -558,20 +692,51 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
                                    struct pt_regs *iregs, void *__pebs)
 {
         /*
-         * We cast to pebs_record_core since that is a subset of
-         * both formats and we don't use the other fields in this
-         * routine.
+         * We cast to pebs_record_nhm to get the load latency data
+         * if extra_reg MSR_PEBS_LD_LAT_THRESHOLD used
          */
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-        struct pebs_record_core *pebs = __pebs;
+        struct pebs_record_nhm *pebs = __pebs;
         struct perf_sample_data data;
         struct pt_regs regs;
+        u64 sample_type;
+        int fll, fst;
 
         if (!intel_pmu_save_and_restart(event))
                 return;
 
+        fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
+        fst = event->hw.flags & PERF_X86_EVENT_PEBS_ST;
+
         perf_sample_data_init(&data, 0, event->hw.last_period);
 
+        data.period = event->hw.last_period;
+        sample_type = event->attr.sample_type;
+
+        /*
+         * if PEBS-LL or PreciseStore
+         */
+        if (fll || fst) {
+                if (sample_type & PERF_SAMPLE_ADDR)
+                        data.addr = pebs->dla;
+
+                /*
+                 * Use latency for weight (only avail with PEBS-LL)
+                 */
+                if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
+                        data.weight = pebs->lat;
+
+                /*
+                 * data.data_src encodes the data source
+                 */
+                if (sample_type & PERF_SAMPLE_DATA_SRC) {
+                        if (fll)
+                                data.data_src.val = load_latency_data(pebs->dse);
+                        else
+                                data.data_src.val = precise_store_data(pebs->dse);
+                }
+        }
+
         /*
          * We use the interrupt regs as a base because the PEBS record
          * does not contain a full regs set, specifically it seems to
@@ -729,3 +894,13 @@ void intel_ds_init(void)
                 }
         }
 }
+
+void perf_restore_debug_store(void)
+{
+        struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
+
+        if (!x86_pmu.bts && !x86_pmu.pebs)
+                return;
+
+        wrmsrl(MSR_IA32_DS_AREA, (unsigned long)ds);
+}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index b43200dbfe7e..d0f9e5aa2151 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -17,6 +17,9 @@ static struct event_constraint constraint_fixed =
 static struct event_constraint constraint_empty =
         EVENT_CONSTRAINT(0, 0, 0);
 
+#define __BITS_VALUE(x, i, n)  ((typeof(x))(((x) >> ((i) * (n))) & \
+                                ((1ULL << (n)) - 1)))
+
 DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
 DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
 DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
@@ -31,9 +34,13 @@ DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
 DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
 DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
 DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
+DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
 DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
 DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
 DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
 DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
@@ -110,6 +117,21 @@ static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_even
         reg1->alloc = 0;
 }
 
+static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
+{
+        struct intel_uncore_extra_reg *er;
+        unsigned long flags;
+        u64 config;
+
+        er = &box->shared_regs[idx];
+
+        raw_spin_lock_irqsave(&er->lock, flags);
+        config = er->config;
+        raw_spin_unlock_irqrestore(&er->lock, flags);
+
+        return config;
+}
+
 /* Sandy Bridge-EP uncore support */
 static struct intel_uncore_type snbep_uncore_cbox;
 static struct intel_uncore_type snbep_uncore_pcu;
@@ -205,7 +227,7 @@ static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct p
         struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 
         if (reg1->idx != EXTRA_REG_NONE)
-                wrmsrl(reg1->reg, reg1->config);
+                wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0));
 
         wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
 }
@@ -226,29 +248,6 @@ static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
                 wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
 }
 
-static int snbep_uncore_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-        struct hw_perf_event *hwc = &event->hw;
-        struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-
-        if (box->pmu->type == &snbep_uncore_cbox) {
-                reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
-                        SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
-                reg1->config = event->attr.config1 &
-                        SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK;
-        } else {
-                if (box->pmu->type == &snbep_uncore_pcu) {
-                        reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
-                        reg1->config = event->attr.config1 & SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK;
-                } else {
-                        return 0;
-                }
-        }
-        reg1->idx = 0;
-
-        return 0;
-}
-
 static struct attribute *snbep_uncore_formats_attr[] = {
         &format_attr_event.attr,
         &format_attr_umask.attr,
@@ -345,16 +344,16 @@ static struct attribute_group snbep_uncore_qpi_format_group = {
         .attrs = snbep_uncore_qpi_formats_attr,
 };
 
+#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()                      \
+        .init_box       = snbep_uncore_msr_init_box,            \
+        .disable_box    = snbep_uncore_msr_disable_box,         \
+        .enable_box     = snbep_uncore_msr_enable_box,          \
+        .disable_event  = snbep_uncore_msr_disable_event,       \
+        .enable_event   = snbep_uncore_msr_enable_event,        \
+        .read_counter   = uncore_msr_read_counter
+
 static struct intel_uncore_ops snbep_uncore_msr_ops = {
-        .init_box       = snbep_uncore_msr_init_box,
-        .disable_box    = snbep_uncore_msr_disable_box,
-        .enable_box     = snbep_uncore_msr_enable_box,
-        .disable_event  = snbep_uncore_msr_disable_event,
-        .enable_event   = snbep_uncore_msr_enable_event,
-        .read_counter   = uncore_msr_read_counter,
-        .get_constraint = uncore_get_constraint,
-        .put_constraint = uncore_put_constraint,
-        .hw_config      = snbep_uncore_hw_config,
+        SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
 };
 
 static struct intel_uncore_ops snbep_uncore_pci_ops = {
@@ -372,6 +371,7 @@ static struct event_constraint snbep_uncore_cbox_constraints[] = {
         UNCORE_EVENT_CONSTRAINT(0x04, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x05, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x07, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x09, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
         UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x13, 0x3),
@@ -421,6 +421,14 @@ static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
         UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x2a, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x2b, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x30, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
@@ -428,6 +436,8 @@ static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
         UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
         UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+        UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
         EVENT_CONSTRAINT_END
 };
 
@@ -446,6 +456,145 @@ static struct intel_uncore_type snbep_uncore_ubox = {
         .format_group   = &snbep_uncore_ubox_format_group,
 };
 
+static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
+        SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+                                  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xc),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xc),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xc),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xc),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2),
+        EVENT_EXTRA_END
+};
+
+static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+        struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+        int i;
+
+        if (uncore_box_is_fake(box))
+                return;
+
+        for (i = 0; i < 5; i++) {
+                if (reg1->alloc & (0x1 << i))
+                        atomic_sub(1 << (i * 6), &er->ref);
+        }
+        reg1->alloc = 0;
+}
+
+static struct event_constraint *
+__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event,
+                            u64 (*cbox_filter_mask)(int fields))
+{
+        struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+        struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+        int i, alloc = 0;
+        unsigned long flags;
+        u64 mask;
+
+        if (reg1->idx == EXTRA_REG_NONE)
+                return NULL;
+
+        raw_spin_lock_irqsave(&er->lock, flags);
+        for (i = 0; i < 5; i++) {
+                if (!(reg1->idx & (0x1 << i)))
+                        continue;
+                if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
+                        continue;
+
+                mask = cbox_filter_mask(0x1 << i);
+                if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) ||
+                    !((reg1->config ^ er->config) & mask)) {
+                        atomic_add(1 << (i * 6), &er->ref);
+                        er->config &= ~mask;
+                        er->config |= reg1->config & mask;
+                        alloc |= (0x1 << i);
+                } else {
+                        break;
+                }
+        }
+        raw_spin_unlock_irqrestore(&er->lock, flags);
+        if (i < 5)
+                goto fail;
+
+        if (!uncore_box_is_fake(box))
+                reg1->alloc |= alloc;
+
+        return 0;
+fail:
+        for (; i >= 0; i--) {
+                if (alloc & (0x1 << i))
+                        atomic_sub(1 << (i * 6), &er->ref);
+        }
+        return &constraint_empty;
+}
+
+static u64 snbep_cbox_filter_mask(int fields)
+{
+        u64 mask = 0;
+
+        if (fields & 0x1)
+                mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID;
+        if (fields & 0x2)
+                mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID;
+        if (fields & 0x4)
+                mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE;
+        if (fields & 0x8)
+                mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC;
+
+        return mask;
+}
+
+static struct event_constraint *
+snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+        return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask);
+}
+
+static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+        struct extra_reg *er;
+        int idx = 0;
+
+        for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) {
+                if (er->event != (event->hw.config & er->config_mask))
+                        continue;
+                idx |= er->idx;
+        }
+
+        if (idx) {
+                reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+                        SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+                reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx);
+                reg1->idx = idx;
+        }
+        return 0;
+}
+
+static struct intel_uncore_ops snbep_uncore_cbox_ops = {
+        SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+        .hw_config              = snbep_cbox_hw_config,
+        .get_constraint         = snbep_cbox_get_constraint,
+        .put_constraint         = snbep_cbox_put_constraint,
+};
+
 static struct intel_uncore_type snbep_uncore_cbox = {
         .name                   = "cbox",
         .num_counters           = 4,
@@ -458,10 +607,104 @@ static struct intel_uncore_type snbep_uncore_cbox = {
         .msr_offset             = SNBEP_CBO_MSR_OFFSET,
         .num_shared_regs        = 1,
         .constraints            = snbep_uncore_cbox_constraints,
-        .ops                    = &snbep_uncore_msr_ops,
+        .ops                    = &snbep_uncore_cbox_ops,
         .format_group           = &snbep_uncore_cbox_format_group,
 };
 
+static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify)
+{
+        struct hw_perf_event *hwc = &event->hw;
+        struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+        u64 config = reg1->config;
+
+        if (new_idx > reg1->idx)
+                config <<= 8 * (new_idx - reg1->idx);
+        else
+                config >>= 8 * (reg1->idx - new_idx);
+
+        if (modify) {
+                hwc->config += new_idx - reg1->idx;
+                reg1->config = config;
+                reg1->idx = new_idx;
+        }
+        return config;
+}
+
+static struct event_constraint *
+snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+        struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+        unsigned long flags;
+        int idx = reg1->idx;
+        u64 mask, config1 = reg1->config;
+        bool ok = false;
+
+        if (reg1->idx == EXTRA_REG_NONE ||
+            (!uncore_box_is_fake(box) && reg1->alloc))
+                return NULL;
+again:
+        mask = 0xff << (idx * 8);
+        raw_spin_lock_irqsave(&er->lock, flags);
+        if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) ||
+            !((config1 ^ er->config) & mask)) {
+                atomic_add(1 << (idx * 8), &er->ref);
+                er->config &= ~mask;
+                er->config |= config1 & mask;
+                ok = true;
+        }
+        raw_spin_unlock_irqrestore(&er->lock, flags);
+
+        if (!ok) {
+                idx = (idx + 1) % 4;
+                if (idx != reg1->idx) {
+                        config1 = snbep_pcu_alter_er(event, idx, false);
+                        goto again;
+                }
+                return &constraint_empty;
+        }
+
+        if (!uncore_box_is_fake(box)) {
+                if (idx != reg1->idx)
+                        snbep_pcu_alter_er(event, idx, true);
+                reg1->alloc = 1;
+        }
+        return NULL;
+}
+
+static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+        struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+
+        if (uncore_box_is_fake(box) || !reg1->alloc)
+                return;
+
+        atomic_sub(1 << (reg1->idx * 8), &er->ref);
+        reg1->alloc = 0;
+}
+
+static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct hw_perf_event *hwc = &event->hw;
+        struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+        int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
+
+        if (ev_sel >= 0xb && ev_sel <= 0xe) {
+                reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
+                reg1->idx = ev_sel - 0xb;
+                reg1->config = event->attr.config1 & (0xff << reg1->idx);
+        }
+        return 0;
+}
+
+static struct intel_uncore_ops snbep_uncore_pcu_ops = {
+        SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+        .hw_config              = snbep_pcu_hw_config,
+        .get_constraint         = snbep_pcu_get_constraint,
+        .put_constraint         = snbep_pcu_put_constraint,
+};
+
 static struct intel_uncore_type snbep_uncore_pcu = {
         .name                   = "pcu",
         .num_counters           = 4,
@@ -472,7 +715,7 @@ static struct intel_uncore_type snbep_uncore_pcu = {
         .event_mask             = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
         .box_ctl                = SNBEP_PCU_MSR_PMON_BOX_CTL,
         .num_shared_regs        = 1,
-        .ops                    = &snbep_uncore_msr_ops,
+        .ops                    = &snbep_uncore_pcu_ops,
         .format_group           = &snbep_uncore_pcu_format_group,
 };
 
@@ -544,55 +787,63 @@ static struct intel_uncore_type snbep_uncore_r3qpi = {
         SNBEP_UNCORE_PCI_COMMON_INIT(),
 };
 
+enum {
+        SNBEP_PCI_UNCORE_HA,
+        SNBEP_PCI_UNCORE_IMC,
+        SNBEP_PCI_UNCORE_QPI,
+        SNBEP_PCI_UNCORE_R2PCIE,
+        SNBEP_PCI_UNCORE_R3QPI,
+};
+
 static struct intel_uncore_type *snbep_pci_uncores[] = {
-        &snbep_uncore_ha,
-        &snbep_uncore_imc,
-        &snbep_uncore_qpi,
-        &snbep_uncore_r2pcie,
-        &snbep_uncore_r3qpi,
+        [SNBEP_PCI_UNCORE_HA]           = &snbep_uncore_ha,
+        [SNBEP_PCI_UNCORE_IMC]          = &snbep_uncore_imc,
+        [SNBEP_PCI_UNCORE_QPI]          = &snbep_uncore_qpi,
+        [SNBEP_PCI_UNCORE_R2PCIE]       = &snbep_uncore_r2pcie,
+        [SNBEP_PCI_UNCORE_R3QPI]        = &snbep_uncore_r3qpi,
         NULL,
 };
 
 static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = {
         { /* Home Agent */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
-                .driver_data = (unsigned long)&snbep_uncore_ha,
+                .driver_data = SNBEP_PCI_UNCORE_HA,
         },
         { /* MC Channel 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
-                .driver_data = (unsigned long)&snbep_uncore_imc,
+                .driver_data = SNBEP_PCI_UNCORE_IMC,
         },
         { /* MC Channel 1 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
-                .driver_data = (unsigned long)&snbep_uncore_imc,
+                .driver_data = SNBEP_PCI_UNCORE_IMC,
         },
         { /* MC Channel 2 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
-                .driver_data = (unsigned long)&snbep_uncore_imc,
+                .driver_data = SNBEP_PCI_UNCORE_IMC,
         },
         { /* MC Channel 3 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
-                .driver_data = (unsigned long)&snbep_uncore_imc,
+                .driver_data = SNBEP_PCI_UNCORE_IMC,
         },
         { /* QPI Port 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
-                .driver_data = (unsigned long)&snbep_uncore_qpi,
+                .driver_data = SNBEP_PCI_UNCORE_QPI,
         },
         { /* QPI Port 1 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
-                .driver_data = (unsigned long)&snbep_uncore_qpi,
+                .driver_data = SNBEP_PCI_UNCORE_QPI,
         },
-        { /* P2PCIe */
+        { /* R2PCIe */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
-                .driver_data = (unsigned long)&snbep_uncore_r2pcie,
+                .driver_data = SNBEP_PCI_UNCORE_R2PCIE,
         },
         { /* R3QPI Link 0 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
-                .driver_data = (unsigned long)&snbep_uncore_r3qpi,
+                .driver_data = SNBEP_PCI_UNCORE_R3QPI,
         },
         { /* R3QPI Link 1 */
                 PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
-                .driver_data = (unsigned long)&snbep_uncore_r3qpi,
+                .driver_data = SNBEP_PCI_UNCORE_R3QPI,
         },
         { /* end: all zeroes */ }
 };
@@ -605,7 +856,7 @@ static struct pci_driver snbep_uncore_pci_driver = {
 /*
  * build pci bus to socket mapping
  */
-static int snbep_pci2phy_map_init(void)
+static int snbep_pci2phy_map_init(int devid)
 {
         struct pci_dev *ubox_dev = NULL;
         int i, bus, nodeid;
@@ -614,9 +865,7 @@ static int snbep_pci2phy_map_init(void)
 
         while (1) {
                 /* find the UBOX device */
-                ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL,
-                                        PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX,
-                                        ubox_dev);
+                ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev);
                 if (!ubox_dev)
                         break;
                 bus = ubox_dev->bus->number;
@@ -639,7 +888,7 @@ static int snbep_pci2phy_map_init(void)
                                 break;
                         }
                 }
-        };
+        }
 
         if (ubox_dev)
                 pci_dev_put(ubox_dev);
@@ -648,6 +897,440 @@ static int snbep_pci2phy_map_init(void)
 }
 /* end of Sandy Bridge-EP uncore support */
 
+/* IvyTown uncore support */
+static void ivt_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+        unsigned msr = uncore_msr_box_ctl(box);
+        if (msr)
+                wrmsrl(msr, IVT_PMON_BOX_CTL_INT);
+}
+
+static void ivt_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+        struct pci_dev *pdev = box->pci_dev;
+
+        pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVT_PMON_BOX_CTL_INT);
+}
+
+#define IVT_UNCORE_MSR_OPS_COMMON_INIT()                        \
+        .init_box       = ivt_uncore_msr_init_box,              \
+        .disable_box    = snbep_uncore_msr_disable_box,         \
+        .enable_box     = snbep_uncore_msr_enable_box,          \
+        .disable_event  = snbep_uncore_msr_disable_event,       \
+        .enable_event   = snbep_uncore_msr_enable_event,        \
+        .read_counter   = uncore_msr_read_counter
+
+static struct intel_uncore_ops ivt_uncore_msr_ops = {
+        IVT_UNCORE_MSR_OPS_COMMON_INIT(),
+};
+
+static struct intel_uncore_ops ivt_uncore_pci_ops = {
+        .init_box       = ivt_uncore_pci_init_box,
+        .disable_box    = snbep_uncore_pci_disable_box,
+        .enable_box     = snbep_uncore_pci_enable_box,
+        .disable_event  = snbep_uncore_pci_disable_event,
+        .enable_event   = snbep_uncore_pci_enable_event,
+        .read_counter   = snbep_uncore_pci_read_counter,
+};
+
+#define IVT_UNCORE_PCI_COMMON_INIT()                            \
+        .perf_ctr       = SNBEP_PCI_PMON_CTR0,                  \
+        .event_ctl      = SNBEP_PCI_PMON_CTL0,                  \
+        .event_mask     = IVT_PMON_RAW_EVENT_MASK,              \
+        .box_ctl        = SNBEP_PCI_PMON_BOX_CTL,               \
+        .ops            = &ivt_uncore_pci_ops,                  \
+        .format_group   = &ivt_uncore_format_group
+
+static struct attribute *ivt_uncore_formats_attr[] = {
+        &format_attr_event.attr,
+        &format_attr_umask.attr,
+        &format_attr_edge.attr,
+        &format_attr_inv.attr,
+        &format_attr_thresh8.attr,
+        NULL,
+};
+
+static struct attribute *ivt_uncore_ubox_formats_attr[] = {
+        &format_attr_event.attr,
+        &format_attr_umask.attr,
+        &format_attr_edge.attr,
+        &format_attr_inv.attr,
+        &format_attr_thresh5.attr,
+        NULL,
+};
+
+static struct attribute *ivt_uncore_cbox_formats_attr[] = {
+        &format_attr_event.attr,
+        &format_attr_umask.attr,
+        &format_attr_edge.attr,
+        &format_attr_tid_en.attr,
+        &format_attr_thresh8.attr,
+        &format_attr_filter_tid.attr,
+        &format_attr_filter_link.attr,
+        &format_attr_filter_state2.attr,
+        &format_attr_filter_nid2.attr,
+        &format_attr_filter_opc2.attr,
+        NULL,
+};
+
+static struct attribute *ivt_uncore_pcu_formats_attr[] = {
+        &format_attr_event_ext.attr,
+        &format_attr_occ_sel.attr,
+        &format_attr_edge.attr,
+        &format_attr_thresh5.attr,
+        &format_attr_occ_invert.attr,
+        &format_attr_occ_edge.attr,
+        &format_attr_filter_band0.attr,
+        &format_attr_filter_band1.attr,
+        &format_attr_filter_band2.attr,
+        &format_attr_filter_band3.attr,
+        NULL,
+};
+
+static struct attribute *ivt_uncore_qpi_formats_attr[] = {
+        &format_attr_event_ext.attr,
+        &format_attr_umask.attr,
+        &format_attr_edge.attr,
+        &format_attr_thresh8.attr,
+        NULL,
+};
+
+static struct attribute_group ivt_uncore_format_group = {
+        .name = "format",
+        .attrs = ivt_uncore_formats_attr,
+};
+
+static struct attribute_group ivt_uncore_ubox_format_group = {
+        .name = "format",
+        .attrs = ivt_uncore_ubox_formats_attr,
+};
+
+static struct attribute_group ivt_uncore_cbox_format_group = {
+        .name = "format",
+        .attrs = ivt_uncore_cbox_formats_attr,
+};
+
+static struct attribute_group ivt_uncore_pcu_format_group = {
+        .name = "format",
+        .attrs = ivt_uncore_pcu_formats_attr,
+};
+
+static struct attribute_group ivt_uncore_qpi_format_group = {
+        .name = "format",
+        .attrs = ivt_uncore_qpi_formats_attr,
+};
+
+static struct intel_uncore_type ivt_uncore_ubox = {
+        .name           = "ubox",
+        .num_counters   = 2,
+        .num_boxes      = 1,
+        .perf_ctr_bits  = 44,
+        .fixed_ctr_bits = 48,
+        .perf_ctr       = SNBEP_U_MSR_PMON_CTR0,
+        .event_ctl      = SNBEP_U_MSR_PMON_CTL0,
+        .event_mask     = IVT_U_MSR_PMON_RAW_EVENT_MASK,
+        .fixed_ctr      = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
+        .fixed_ctl      = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
+        .ops            = &ivt_uncore_msr_ops,
+        .format_group   = &ivt_uncore_ubox_format_group,
+};
+
+static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
+        SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+                                  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8),
+        EVENT_EXTRA_END
+};
+
+static u64 ivt_cbox_filter_mask(int fields)
+{
+        u64 mask = 0;
+
+        if (fields & 0x1)
+                mask |= IVT_CB0_MSR_PMON_BOX_FILTER_TID;
+        if (fields & 0x2)
+                mask |= IVT_CB0_MSR_PMON_BOX_FILTER_LINK;
+        if (fields & 0x4)
+                mask |= IVT_CB0_MSR_PMON_BOX_FILTER_STATE;
+        if (fields & 0x8)
+                mask |= IVT_CB0_MSR_PMON_BOX_FILTER_NID;
+        if (fields & 0x10)
+                mask |= IVT_CB0_MSR_PMON_BOX_FILTER_OPC;
+
+        return mask;
+}
+
+static struct event_constraint *
+ivt_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+        return __snbep_cbox_get_constraint(box, event, ivt_cbox_filter_mask);
+}
+
+static int ivt_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+        struct extra_reg *er;
+        int idx = 0;
+
+        for (er = ivt_uncore_cbox_extra_regs; er->msr; er++) {
+                if (er->event != (event->hw.config & er->config_mask))
+                        continue;
+                idx |= er->idx;
+        }
+
+        if (idx) {
+                reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+                        SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+                reg1->config = event->attr.config1 & ivt_cbox_filter_mask(idx);
+                reg1->idx = idx;
+        }
+        return 0;
+}
+
+static void ivt_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct hw_perf_event *hwc = &event->hw;
+        struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+        if (reg1->idx != EXTRA_REG_NONE) {
+                u64 filter = uncore_shared_reg_config(box, 0);
+                wrmsrl(reg1->reg, filter & 0xffffffff);
+                wrmsrl(reg1->reg + 6, filter >> 32);
+        }
+
+        wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops ivt_uncore_cbox_ops = {
+        .init_box               = ivt_uncore_msr_init_box,
+        .disable_box            = snbep_uncore_msr_disable_box,
+        .enable_box             = snbep_uncore_msr_enable_box,
+        .disable_event          = snbep_uncore_msr_disable_event,
+        .enable_event           = ivt_cbox_enable_event,
+        .read_counter           = uncore_msr_read_counter,
+        .hw_config              = ivt_cbox_hw_config,
+        .get_constraint         = ivt_cbox_get_constraint,
+        .put_constraint         = snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type ivt_uncore_cbox = {
+        .name                   = "cbox",
+        .num_counters           = 4,
+        .num_boxes              = 15,
+        .perf_ctr_bits          = 44,
+        .event_ctl              = SNBEP_C0_MSR_PMON_CTL0,
+        .perf_ctr               = SNBEP_C0_MSR_PMON_CTR0,
+        .event_mask             = IVT_CBO_MSR_PMON_RAW_EVENT_MASK,
+        .box_ctl                = SNBEP_C0_MSR_PMON_BOX_CTL,
+        .msr_offset             = SNBEP_CBO_MSR_OFFSET,
+        .num_shared_regs        = 1,
+        .constraints            = snbep_uncore_cbox_constraints,
+        .ops                    = &ivt_uncore_cbox_ops,
+        .format_group           = &ivt_uncore_cbox_format_group,
+};
+
+static struct intel_uncore_ops ivt_uncore_pcu_ops = {
+        IVT_UNCORE_MSR_OPS_COMMON_INIT(),
+        .hw_config              = snbep_pcu_hw_config,
+        .get_constraint         = snbep_pcu_get_constraint,
+        .put_constraint         = snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type ivt_uncore_pcu = {
+        .name                   = "pcu",
+        .num_counters           = 4,
+        .num_boxes              = 1,
+        .perf_ctr_bits          = 48,
+        .perf_ctr               = SNBEP_PCU_MSR_PMON_CTR0,
+        .event_ctl              = SNBEP_PCU_MSR_PMON_CTL0,
+        .event_mask             = IVT_PCU_MSR_PMON_RAW_EVENT_MASK,
+        .box_ctl                = SNBEP_PCU_MSR_PMON_BOX_CTL,
+        .num_shared_regs        = 1,
+        .ops                    = &ivt_uncore_pcu_ops,
+        .format_group           = &ivt_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *ivt_msr_uncores[] = {
+        &ivt_uncore_ubox,
+        &ivt_uncore_cbox,
+        &ivt_uncore_pcu,
+        NULL,
+};
+
+static struct intel_uncore_type ivt_uncore_ha = {
+        .name           = "ha",
+        .num_counters   = 4,
+        .num_boxes      = 2,
+        .perf_ctr_bits  = 48,
+        IVT_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivt_uncore_imc = {
+        .name           = "imc",
+        .num_counters   = 4,
+        .num_boxes      = 8,
+        .perf_ctr_bits  = 48,
+        .fixed_ctr_bits = 48,
+        .fixed_ctr      = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+        .fixed_ctl      = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+        IVT_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivt_uncore_qpi = {
+        .name           = "qpi",
+        .num_counters   = 4,
+        .num_boxes      = 3,
+        .perf_ctr_bits  = 48,
+        .perf_ctr       = SNBEP_PCI_PMON_CTR0,
+        .event_ctl      = SNBEP_PCI_PMON_CTL0,
+        .event_mask     = IVT_QPI_PCI_PMON_RAW_EVENT_MASK,
+        .box_ctl        = SNBEP_PCI_PMON_BOX_CTL,
+        .ops            = &ivt_uncore_pci_ops,
+        .format_group   = &ivt_uncore_qpi_format_group,
+};
+
+static struct intel_uncore_type ivt_uncore_r2pcie = {
+        .name           = "r2pcie",
+        .num_counters   = 4,
+        .num_boxes      = 1,
+        .perf_ctr_bits  = 44,
+        .constraints    = snbep_uncore_r2pcie_constraints,
+        IVT_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivt_uncore_r3qpi = {
+        .name           = "r3qpi",
+        .num_counters   = 3,
+        .num_boxes      = 2,
+        .perf_ctr_bits  = 44,
+        .constraints    = snbep_uncore_r3qpi_constraints,
+        IVT_UNCORE_PCI_COMMON_INIT(),
+};
+
+enum {
+        IVT_PCI_UNCORE_HA,
+        IVT_PCI_UNCORE_IMC,
+        IVT_PCI_UNCORE_QPI,
+        IVT_PCI_UNCORE_R2PCIE,
+        IVT_PCI_UNCORE_R3QPI,
+};
+
+static struct intel_uncore_type *ivt_pci_uncores[] = {
+        [IVT_PCI_UNCORE_HA]     = &ivt_uncore_ha,
+        [IVT_PCI_UNCORE_IMC]    = &ivt_uncore_imc,
+        [IVT_PCI_UNCORE_QPI]    = &ivt_uncore_qpi,
+        [IVT_PCI_UNCORE_R2PCIE] = &ivt_uncore_r2pcie,
+        [IVT_PCI_UNCORE_R3QPI]  = &ivt_uncore_r3qpi,
+        NULL,
+};
+
+static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = {
+        { /* Home Agent 0 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
+                .driver_data = IVT_PCI_UNCORE_HA,
+        },
+        { /* Home Agent 1 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
+                .driver_data = IVT_PCI_UNCORE_HA,
+        },
+        { /* MC0 Channel 0 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
+                .driver_data = IVT_PCI_UNCORE_IMC,
+        },
+        { /* MC0 Channel 1 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
+                .driver_data = IVT_PCI_UNCORE_IMC,
+        },
+        { /* MC0 Channel 3 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
+                .driver_data = IVT_PCI_UNCORE_IMC,
+        },
+        { /* MC0 Channel 4 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
+                .driver_data = IVT_PCI_UNCORE_IMC,
+        },
+        { /* MC1 Channel 0 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
+                .driver_data = IVT_PCI_UNCORE_IMC,
+        },
+        { /* MC1 Channel 1 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
+                .driver_data = IVT_PCI_UNCORE_IMC,
+        },
+        { /* MC1 Channel 3 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
+                .driver_data = IVT_PCI_UNCORE_IMC,
+        },
+        { /* MC1 Channel 4 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
+                .driver_data = IVT_PCI_UNCORE_IMC,
+        },
+        { /* QPI0 Port 0 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
+                .driver_data = IVT_PCI_UNCORE_QPI,
+        },
+        { /* QPI0 Port 1 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
+                .driver_data = IVT_PCI_UNCORE_QPI,
+        },
+        { /* QPI1 Port 2 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
+                .driver_data = IVT_PCI_UNCORE_QPI,
+        },
+        { /* R2PCIe */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
+                .driver_data = IVT_PCI_UNCORE_R2PCIE,
+        },
+        { /* R3QPI0 Link 0 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
+                .driver_data = IVT_PCI_UNCORE_R3QPI,
+        },
+        { /* R3QPI0 Link 1 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
+                .driver_data = IVT_PCI_UNCORE_R3QPI,
+        },
+        { /* R3QPI1 Link 2 */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
+                .driver_data = IVT_PCI_UNCORE_R3QPI,
+        },
+        { /* end: all zeroes */ }
+};
+
+static struct pci_driver ivt_uncore_pci_driver = {
+        .name           = "ivt_uncore",
+        .id_table       = ivt_uncore_pci_ids,
+};
+/* end of IvyTown uncore support */
+
 /* Sandy Bridge uncore support */
 static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
@@ -808,9 +1491,6 @@ static struct intel_uncore_type *nhm_msr_uncores[] = {
 /* end of Nehalem uncore support */
 
 /* Nehalem-EX uncore support */
-#define __BITS_VALUE(x, i, n)  ((typeof(x))(((x) >> ((i) * (n))) & \
-                                ((1ULL << (n)) - 1)))
-
 DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
 DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
 DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
@@ -1161,7 +1841,7 @@ static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
 };
 
 /* Nehalem-EX or Westmere-EX ? */
-bool uncore_nhmex;
+static bool uncore_nhmex;
 
 static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
 {
@@ -1239,7 +1919,7 @@ static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx)
         atomic_sub(1 << (idx * 8), &er->ref);
 }
 
-u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
+static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
 {
         struct hw_perf_event *hwc = &event->hw;
         struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
@@ -1554,7 +2234,7 @@ static struct intel_uncore_type nhmex_uncore_mbox = {
         .format_group           = &nhmex_uncore_mbox_format_group,
 };
 
-void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
+static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
 {
         struct hw_perf_event *hwc = &event->hw;
         struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
@@ -1724,21 +2404,6 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event
         return 0;
 }
 
-static u64 nhmex_rbox_shared_reg_config(struct intel_uncore_box *box, int idx)
-{
-        struct intel_uncore_extra_reg *er;
-        unsigned long flags;
-        u64 config;
-
-        er = &box->shared_regs[idx];
-
-        raw_spin_lock_irqsave(&er->lock, flags);
-        config = er->config;
-        raw_spin_unlock_irqrestore(&er->lock, flags);
-
-        return config;
-}
-
 static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
         struct hw_perf_event *hwc = &event->hw;
@@ -1759,7 +2424,7 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per
         case 2:
         case 3:
                 wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
-                        nhmex_rbox_shared_reg_config(box, 2 + (idx / 6) * 5));
+                        uncore_shared_reg_config(box, 2 + (idx / 6) * 5));
                 break;
         case 4:
                 wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
@@ -2285,7 +2950,7 @@ out:
         return ret;
 }
 
-int uncore_pmu_event_init(struct perf_event *event)
+static int uncore_pmu_event_init(struct perf_event *event)
 {
         struct intel_uncore_pmu *pmu;
         struct intel_uncore_box *box;
@@ -2438,7 +3103,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
 
         type->unconstrainted = (struct event_constraint)
                 __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
-                                0, type->num_counters, 0);
+                                0, type->num_counters, 0, 0);
 
         for (i = 0; i < type->num_boxes; i++) {
                 pmus[i].func_id = -1;
@@ -2556,6 +3221,8 @@ static void uncore_pci_remove(struct pci_dev *pdev)
         if (WARN_ON_ONCE(phys_id != box->phys_id))
                 return;
 
+        pci_set_drvdata(pdev, NULL);
+
         raw_spin_lock(&uncore_box_lock);
         list_del(&box->list);
         raw_spin_unlock(&uncore_box_lock);
@@ -2574,11 +3241,7 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 static int uncore_pci_probe(struct pci_dev *pdev,
                             const struct pci_device_id *id)
 {
-        struct intel_uncore_type *type;
-
-        type = (struct intel_uncore_type *)id->driver_data;
-
-        return uncore_pci_add(type, pdev);
+        return uncore_pci_add(pci_uncores[id->driver_data], pdev);
 }
 
 static int __init uncore_pci_init(void)
@@ -2587,12 +3250,19 @@ static int __init uncore_pci_init(void)
 
         switch (boot_cpu_data.x86_model) {
         case 45: /* Sandy Bridge-EP */
-                ret = snbep_pci2phy_map_init();
+                ret = snbep_pci2phy_map_init(0x3ce0);
                 if (ret)
                         return ret;
                 pci_uncores = snbep_pci_uncores;
                 uncore_pci_driver = &snbep_uncore_pci_driver;
                 break;
+        case 62: /* IvyTown */
+                ret = snbep_pci2phy_map_init(0x0e1e);
+                if (ret)
+                        return ret;
+                pci_uncores = ivt_pci_uncores;
+                uncore_pci_driver = &ivt_uncore_pci_driver;
+                break;
         default:
                 return 0;
         }
@@ -2622,6 +3292,21 @@ static void __init uncore_pci_exit(void)
         }
 }
 
+/* CPU hot plug/unplug are serialized by cpu_add_remove_lock mutex */
+static LIST_HEAD(boxes_to_free);
+
+static void __cpuinit uncore_kfree_boxes(void)
+{
+        struct intel_uncore_box *box;
+
+        while (!list_empty(&boxes_to_free)) {
+                box = list_entry(boxes_to_free.next,
+                                 struct intel_uncore_box, list);
+                list_del(&box->list);
+                kfree(box);
+        }
+}
+
 static void __cpuinit uncore_cpu_dying(int cpu)
 {
         struct intel_uncore_type *type;
@@ -2636,7 +3321,7 @@ static void __cpuinit uncore_cpu_dying(int cpu)
                         box = *per_cpu_ptr(pmu->box, cpu);
                         *per_cpu_ptr(pmu->box, cpu) = NULL;
                         if (box && atomic_dec_and_test(&box->refcnt))
-                                kfree(box);
+                                list_add(&box->list, &boxes_to_free);
                 }
         }
 }
@@ -2666,8 +3351,11 @@ static int __cpuinit uncore_cpu_starting(int cpu)
                                 if (exist && exist->phys_id == phys_id) {
                                         atomic_inc(&exist->refcnt);
                                         *per_cpu_ptr(pmu->box, cpu) = exist;
-                                        kfree(box);
-                                        box = NULL;
+                                        if (box) {
+                                                list_add(&box->list,
+                                                         &boxes_to_free);
+                                                box = NULL;
+                                        }
                                         break;
                                 }
                         }
@@ -2806,6 +3494,10 @@ static int
         case CPU_DYING:
                 uncore_cpu_dying(cpu);
                 break;
+        case CPU_ONLINE:
+        case CPU_DEAD:
+                uncore_kfree_boxes();
+                break;
         default:
                 break;
         }
@@ -2871,6 +3563,12 @@ static int __init uncore_cpu_init(void)
                         nhmex_uncore_cbox.num_boxes = max_cores;
                 msr_uncores = nhmex_msr_uncores;
                 break;
+        case 62: /* IvyTown */
+                if (ivt_uncore_cbox.num_boxes > max_cores)
+                        ivt_uncore_cbox.num_boxes = max_cores;
+                msr_uncores = ivt_msr_uncores;
+                break;
+
         default:
                 return 0;
         }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index e68a4550e952..f9528917f6e8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -76,7 +76,7 @@
 #define SNBEP_PMON_CTL_UMASK_MASK       0x0000ff00
 #define SNBEP_PMON_CTL_RST              (1 << 17)
 #define SNBEP_PMON_CTL_EDGE_DET         (1 << 18)
-#define SNBEP_PMON_CTL_EV_SEL_EXT       (1 << 21)       /* only for QPI */
+#define SNBEP_PMON_CTL_EV_SEL_EXT       (1 << 21)
 #define SNBEP_PMON_CTL_EN               (1 << 22)
 #define SNBEP_PMON_CTL_INVERT           (1 << 23)
 #define SNBEP_PMON_CTL_TRESH_MASK       0xff000000
@@ -148,9 +148,20 @@
 #define SNBEP_C0_MSR_PMON_CTL0                  0xd10
 #define SNBEP_C0_MSR_PMON_BOX_CTL               0xd04
 #define SNBEP_C0_MSR_PMON_BOX_FILTER            0xd14
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK      0xfffffc1f
 #define SNBEP_CBO_MSR_OFFSET                    0x20
 
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID       0x1f
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID       0x3fc00
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE     0x7c0000
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC       0xff800000
+
+#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) {    \
+        .event = (e),                           \
+        .msr = SNBEP_C0_MSR_PMON_BOX_FILTER,    \
+        .config_mask = (m),                     \
+        .idx = (i)                              \
+}
+
 /* SNB-EP PCU register */
 #define SNBEP_PCU_MSR_PMON_CTR0                 0xc36
 #define SNBEP_PCU_MSR_PMON_CTL0                 0xc30
@@ -160,6 +171,55 @@
 #define SNBEP_PCU_MSR_CORE_C3_CTR               0x3fc
 #define SNBEP_PCU_MSR_CORE_C6_CTR               0x3fd
 
+/* IVT event control */
+#define IVT_PMON_BOX_CTL_INT            (SNBEP_PMON_BOX_CTL_RST_CTRL | \
+                                         SNBEP_PMON_BOX_CTL_RST_CTRS)
+#define IVT_PMON_RAW_EVENT_MASK         (SNBEP_PMON_CTL_EV_SEL_MASK | \
+                                         SNBEP_PMON_CTL_UMASK_MASK | \
+                                         SNBEP_PMON_CTL_EDGE_DET | \
+                                         SNBEP_PMON_CTL_TRESH_MASK)
+/* IVT Ubox */
+#define IVT_U_MSR_PMON_GLOBAL_CTL               0xc00
+#define IVT_U_PMON_GLOBAL_FRZ_ALL               (1 << 31)
+#define IVT_U_PMON_GLOBAL_UNFRZ_ALL             (1 << 29)
+
+#define IVT_U_MSR_PMON_RAW_EVENT_MASK   \
+                                (SNBEP_PMON_CTL_EV_SEL_MASK | \
+                                 SNBEP_PMON_CTL_UMASK_MASK | \
+                                 SNBEP_PMON_CTL_EDGE_DET | \
+                                 SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
+/* IVT Cbo */
+#define IVT_CBO_MSR_PMON_RAW_EVENT_MASK         (IVT_PMON_RAW_EVENT_MASK | \
+                                                 SNBEP_CBO_PMON_CTL_TID_EN)
+
+#define IVT_CB0_MSR_PMON_BOX_FILTER_TID         (0x1fULL << 0)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_LINK        (0xfULL << 5)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_STATE       (0x3fULL << 17)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_NID         (0xffffULL << 32)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_OPC         (0x1ffULL << 52)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_C6          (0x1ULL << 61)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_NC          (0x1ULL << 62)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_IOSC        (0x1ULL << 63)
+
+/* IVT home agent */
+#define IVT_HA_PCI_PMON_CTL_Q_OCC_RST           (1 << 16)
+#define IVT_HA_PCI_PMON_RAW_EVENT_MASK          \
+                                (IVT_PMON_RAW_EVENT_MASK | \
+                                 IVT_HA_PCI_PMON_CTL_Q_OCC_RST)
+/* IVT PCU */
+#define IVT_PCU_MSR_PMON_RAW_EVENT_MASK \
+                                (SNBEP_PMON_CTL_EV_SEL_MASK | \
+                                 SNBEP_PMON_CTL_EV_SEL_EXT | \
+                                 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+                                 SNBEP_PMON_CTL_EDGE_DET | \
+                                 SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
+                                 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+                                 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
+/* IVT QPI */
+#define IVT_QPI_PCI_PMON_RAW_EVENT_MASK \
+                                (IVT_PMON_RAW_EVENT_MASK | \
+                                 SNBEP_PMON_CTL_EV_SEL_EXT)
+
 /* NHM-EX event control */
 #define NHMEX_PMON_CTL_EV_SEL_MASK      0x000000ff
 #define NHMEX_PMON_CTL_UMASK_MASK       0x0000ff00
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
index 4b7731bf23a8..838fa8772c62 100644
--- a/arch/x86/kernel/cpu/perf_event_knc.c
+++ b/arch/x86/kernel/cpu/perf_event_knc.c
@@ -17,7 +17,7 @@ static const u64 knc_perfmon_event_map[] =
   [PERF_COUNT_HW_BRANCH_MISSES]         = 0x002b,
 };
 
-static __initconst u64 knc_hw_cache_event_ids
+static const u64 __initconst knc_hw_cache_event_ids
                                 [PERF_COUNT_HW_CACHE_MAX]
                                 [PERF_COUNT_HW_CACHE_OP_MAX]
                                 [PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -284,7 +284,7 @@ static struct attribute *intel_knc_formats_attr[] = {
         NULL,
 };
 
-static __initconst struct x86_pmu knc_pmu = {
+static const struct x86_pmu knc_pmu __initconst = {
         .name                   = "knc",
         .handle_irq             = knc_pmu_handle_irq,
         .disable_all            = knc_pmu_disable_all,
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 92c7e39a079f..3486e6660357 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -895,8 +895,8 @@ static void p4_pmu_disable_pebs(void)
          * So at moment let leave metrics turned on forever -- it's
          * ok for now but need to be revisited!
          *
-         * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)0);
-         * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)0);
+         * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, 0);
+         * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, 0);
          */
 }
 
@@ -910,8 +910,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
          * asserted again and again
          */
         (void)wrmsrl_safe(hwc->config_base,
-                (u64)(p4_config_unpack_cccr(hwc->config)) &
-                        ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
+                p4_config_unpack_cccr(hwc->config) & ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
 }
 
 static void p4_pmu_disable_all(void)
@@ -957,7 +956,7 @@ static void p4_pmu_enable_event(struct perf_event *event)
         u64 escr_addr, cccr;
 
         bind = &p4_event_bind_map[idx];
-        escr_addr = (u64)bind->escr_msr[thread];
+        escr_addr = bind->escr_msr[thread];
 
         /*
          * - we dont support cascaded counters yet
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index 4820c232a0b9..b1e2fe115323 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -19,7 +19,7 @@ static const u64 p6_perfmon_event_map[] =
 
 };
 
-static u64 p6_hw_cache_event_ids
+static const u64 __initconst p6_hw_cache_event_ids
                                 [PERF_COUNT_HW_CACHE_MAX]
                                 [PERF_COUNT_HW_CACHE_OP_MAX]
                                 [PERF_COUNT_HW_CACHE_RESULT_MAX] =
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index e280253f6f94..37a198bd48c8 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -34,9 +34,9 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
                    "fpu_exception\t: %s\n"
                    "cpuid level\t: %d\n"
                    "wp\t\t: %s\n",
-                   c->fdiv_bug ? "yes" : "no",
-                   c->f00f_bug ? "yes" : "no",
-                   c->coma_bug ? "yes" : "no",
+                   static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
+                   static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
+                   static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
                    c->hard_math ? "yes" : "no",
                    c->hard_math ? "yes" : "no",
                    c->cpuid_level,
diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault_32.c
index 37250fe490b1..155a13f33ed8 100644
--- a/arch/x86/kernel/doublefault_32.c
+++ b/arch/x86/kernel/doublefault_32.c
@@ -20,7 +20,7 @@ static void doublefault_fn(void)
         struct desc_ptr gdt_desc = {0, 0};
         unsigned long gdt, tss;
 
-        store_gdt(&gdt_desc);
+        native_store_gdt(&gdt_desc);
         gdt = gdt_desc.address;
 
         printk(KERN_EMERG "PANIC: double fault, gdt at %08lx [%d bytes]\n", gdt, gdt_desc.size);
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 9b9f18b49918..d15f575a861b 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -169,25 +169,9 @@ static struct console early_serial_console = {
         .index =        -1,
 };
 
-/* Direct interface for emergencies */
-static struct console *early_console = &early_vga_console;
-static int __initdata early_console_initialized;
-
-asmlinkage void early_printk(const char *fmt, ...)
-{
-        char buf[512];
-        int n;
-        va_list ap;
-
-        va_start(ap, fmt);
-        n = vscnprintf(buf, sizeof(buf), fmt, ap);
-        early_console->write(early_console, buf, n);
-        va_end(ap);
-}
-
 static inline void early_console_register(struct console *con, int keep_early)
 {
-        if (early_console->index != -1) {
+        if (con->index != -1) {
                 printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n",
                        con->name);
                 return;
@@ -207,9 +191,8 @@ static int __init setup_early_printk(char *buf)
         if (!buf)
                 return 0;
 
-        if (early_console_initialized)
+        if (early_console)
                 return 0;
-        early_console_initialized = 1;
 
         keep = (strstr(buf, "keep") != NULL);
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index c5e403f6d869..101ac1a9263e 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -144,10 +144,10 @@ void __init x86_64_start_kernel(char * real_mode_data)
          * Build-time sanity checks on the kernel image and module
          * area mappings. (these are purely build-time and produce no code)
          */
-        BUILD_BUG_ON(MODULES_VADDR < KERNEL_IMAGE_START);
-        BUILD_BUG_ON(MODULES_VADDR-KERNEL_IMAGE_START < KERNEL_IMAGE_SIZE);
+        BUILD_BUG_ON(MODULES_VADDR < __START_KERNEL_map);
+        BUILD_BUG_ON(MODULES_VADDR - __START_KERNEL_map < KERNEL_IMAGE_SIZE);
         BUILD_BUG_ON(MODULES_LEN + KERNEL_IMAGE_SIZE > 2*PUD_SIZE);
-        BUILD_BUG_ON((KERNEL_IMAGE_START & ~PMD_MASK) != 0);
+        BUILD_BUG_ON((__START_KERNEL_map & ~PMD_MASK) != 0);
         BUILD_BUG_ON((MODULES_VADDR & ~PMD_MASK) != 0);
         BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
         BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) ==
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 3f06e6149981..9895a9a41380 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -353,7 +353,11 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src)
                  * have given.
                  */
                 newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest;
-                BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check.  */
+                if ((s64) (s32) newdisp != newdisp) {
+                        pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
+                        pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", src, dest, insn.displacement.value);
+                        return 0;
+                }
                 disp = (u8 *) dest + insn_offset_displacement(&insn);
                 *(s32 *) disp = (s32) newdisp;
         }
@@ -375,6 +379,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
         else
                 p->ainsn.boostable = -1;
 
+        /* Check whether the instruction modifies Interrupt Flag or not */
+        p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn);
+
         /* Also, displacement change doesn't affect the first byte */
         p->opcode = p->ainsn.insn[0];
 }
@@ -434,7 +441,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
         __this_cpu_write(current_kprobe, p);
         kcb->kprobe_saved_flags = kcb->kprobe_old_flags
                 = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
-        if (is_IF_modifier(p->ainsn.insn))
+        if (p->ainsn.if_modifier)
                 kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
 }
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b686a904d7c3..cd6d9a5a42f6 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -20,6 +20,7 @@
  *   Authors: Anthony Liguori <aliguori@us.ibm.com>
  */
 
+#include <linux/context_tracking.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/kvm_para.h>
@@ -43,7 +44,6 @@
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
 #include <asm/kvm_guest.h>
-#include <asm/context_tracking.h>
 
 static int kvmapf = 1;
 
@@ -254,16 +254,18 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason);
 dotraplinkage void __kprobes
 do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+        enum ctx_state prev_state;
+
         switch (kvm_read_and_reset_pf_reason()) {
         default:
                 do_page_fault(regs, error_code);
                 break;
         case KVM_PV_REASON_PAGE_NOT_PRESENT:
                 /* page is swapped out by the host. */
-                exception_enter(regs);
+                prev_state = exception_enter();
                 exit_idle();
                 kvm_async_pf_task_wait((u32)read_cr2());
-                exception_exit(regs);
+                exception_exit(prev_state);
                 break;
         case KVM_PV_REASON_PAGE_READY:
                 rcu_irq_enter();
diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c
index 577db8417d15..833d51d6ee06 100644
--- a/arch/x86/kernel/microcode_core_early.c
+++ b/arch/x86/kernel/microcode_core_early.c
@@ -45,9 +45,6 @@ static int __cpuinit x86_vendor(void)
         u32 eax = 0x00000000;
         u32 ebx, ecx = 0, edx;
 
-        if (!have_cpuid_p())
-                return X86_VENDOR_UNKNOWN;
-
         native_cpuid(&eax, &ebx, &ecx, &edx);
 
         if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx))
@@ -59,18 +56,45 @@ static int __cpuinit x86_vendor(void)
         return X86_VENDOR_UNKNOWN;
 }
 
+static int __cpuinit x86_family(void)
+{
+        u32 eax = 0x00000001;
+        u32 ebx, ecx = 0, edx;
+        int x86;
+
+        native_cpuid(&eax, &ebx, &ecx, &edx);
+
+        x86 = (eax >> 8) & 0xf;
+        if (x86 == 15)
+                x86 += (eax >> 20) & 0xff;
+
+        return x86;
+}
+
 void __init load_ucode_bsp(void)
 {
-        int vendor = x86_vendor();
+        int vendor, x86;
+
+        if (!have_cpuid_p())
+                return;
 
-        if (vendor == X86_VENDOR_INTEL)
+        vendor = x86_vendor();
+        x86 = x86_family();
+
+        if (vendor == X86_VENDOR_INTEL && x86 >= 6)
                 load_ucode_intel_bsp();
 }
 
 void __cpuinit load_ucode_ap(void)
 {
-        int vendor = x86_vendor();
+        int vendor, x86;
+
+        if (!have_cpuid_p())
+                return;
+
+        vendor = x86_vendor();
+        x86 = x86_family();
 
-        if (vendor == X86_VENDOR_INTEL)
+        if (vendor == X86_VENDOR_INTEL && x86 >= 6)
                 load_ucode_intel_ap();
 }
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
index 7890bc838952..d893e8ed8ac9 100644
--- a/arch/x86/kernel/microcode_intel_early.c
+++ b/arch/x86/kernel/microcode_intel_early.c
@@ -90,13 +90,13 @@ microcode_phys(struct microcode_intel **mc_saved_tmp,
         struct microcode_intel ***mc_saved;
 
         mc_saved = (struct microcode_intel ***)
-                   __pa_symbol(&mc_saved_data->mc_saved);
+                   __pa_nodebug(&mc_saved_data->mc_saved);
         for (i = 0; i < mc_saved_data->mc_saved_count; i++) {
                 struct microcode_intel *p;
 
                 p = *(struct microcode_intel **)
-                        __pa(mc_saved_data->mc_saved + i);
-                mc_saved_tmp[i] = (struct microcode_intel *)__pa(p);
+                        __pa_nodebug(mc_saved_data->mc_saved + i);
+                mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p);
         }
 }
 #endif
@@ -562,7 +562,7 @@ scan_microcode(unsigned long start, unsigned long end,
         struct cpio_data cd;
         long offset = 0;
 #ifdef CONFIG_X86_32
-        char *p = (char *)__pa_symbol(ucode_name);
+        char *p = (char *)__pa_nodebug(ucode_name);
 #else
         char *p = ucode_name;
 #endif
@@ -630,8 +630,8 @@ static void __cpuinit print_ucode(struct ucode_cpu_info *uci)
         if (mc_intel == NULL)
                 return;
 
-        delay_ucode_info_p = (int *)__pa_symbol(&delay_ucode_info);
-        current_mc_date_p = (int *)__pa_symbol(&current_mc_date);
+        delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info);
+        current_mc_date_p = (int *)__pa_nodebug(&current_mc_date);
 
         *delay_ucode_info_p = 1;
         *current_mc_date_p = mc_intel->hdr.date;
@@ -659,8 +659,8 @@ static inline void __cpuinit print_ucode(struct ucode_cpu_info *uci)
 }
 #endif
 
-static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
-                                 struct ucode_cpu_info *uci)
+static int __cpuinit apply_microcode_early(struct mc_saved_data *mc_saved_data,
+                                           struct ucode_cpu_info *uci)
 {
         struct microcode_intel *mc_intel;
         unsigned int val[2];
@@ -741,15 +741,15 @@ load_ucode_intel_bsp(void)
 #ifdef CONFIG_X86_32
         struct boot_params *boot_params_p;
 
-        boot_params_p = (struct boot_params *)__pa_symbol(&boot_params);
+        boot_params_p = (struct boot_params *)__pa_nodebug(&boot_params);
         ramdisk_image = boot_params_p->hdr.ramdisk_image;
         ramdisk_size  = boot_params_p->hdr.ramdisk_size;
         initrd_start_early = ramdisk_image;
         initrd_end_early = initrd_start_early + ramdisk_size;
 
         _load_ucode_intel_bsp(
-                (struct mc_saved_data *)__pa_symbol(&mc_saved_data),
-                (unsigned long *)__pa_symbol(&mc_saved_in_initrd),
+                (struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
+                (unsigned long *)__pa_nodebug(&mc_saved_in_initrd),
                 initrd_start_early, initrd_end_early, &uci);
 #else
         ramdisk_image = boot_params.hdr.ramdisk_image;
@@ -772,10 +772,10 @@ void __cpuinit load_ucode_intel_ap(void)
         unsigned long *initrd_start_p;
 
         mc_saved_in_initrd_p =
-                (unsigned long *)__pa_symbol(mc_saved_in_initrd);
-        mc_saved_data_p = (struct mc_saved_data *)__pa_symbol(&mc_saved_data);
-        initrd_start_p = (unsigned long *)__pa_symbol(&initrd_start);
-        initrd_start_addr = (unsigned long)__pa_symbol(*initrd_start_p);
+                (unsigned long *)__pa_nodebug(mc_saved_in_initrd);
+        mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
+        initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
+        initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p);
 #else
         mc_saved_data_p = &mc_saved_data;
         mc_saved_in_initrd_p = mc_saved_in_initrd;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 17fff18a1031..cd6de64cc480 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -263,6 +263,18 @@ void paravirt_leave_lazy_mmu(void)
         leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
+void paravirt_flush_lazy_mmu(void)
+{
+        preempt_disable();
+
+        if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+                arch_leave_lazy_mmu_mode();
+                arch_enter_lazy_mmu_mode();
+        }
+
+        preempt_enable();
+}
+
 void paravirt_start_context_switch(struct task_struct *prev)
 {
         BUG_ON(preemptible());
@@ -292,18 +304,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
         return this_cpu_read(paravirt_lazy_mode);
 }
 
-void arch_flush_lazy_mmu_mode(void)
-{
-        preempt_disable();
-
-        if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-                arch_leave_lazy_mmu_mode();
-                arch_enter_lazy_mmu_mode();
-        }
-
-        preempt_enable();
-}
-
 struct pv_info pv_info = {
         .name = "bare hardware",
         .paravirt_enabled = 0,
@@ -360,7 +360,6 @@ struct pv_cpu_ops pv_cpu_ops = {
         .set_ldt = native_set_ldt,
         .load_gdt = native_load_gdt,
         .load_idt = native_load_idt,
-        .store_gdt = native_store_gdt,
         .store_idt = native_store_idt,
         .store_tr = native_store_tr,
         .load_tls = native_load_tls,
@@ -475,6 +474,7 @@ struct pv_mmu_ops pv_mmu_ops = {
         .lazy_mode = {
                 .enter = paravirt_nop,
                 .leave = paravirt_nop,
+                .flush = paravirt_nop,
         },
 
         .set_fixmap = native_set_fixmap,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 14ae10031ff0..14fcf55a5c5b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -301,13 +301,7 @@ void exit_idle(void)
 }
 #endif
 
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
+void arch_cpu_idle_prepare(void)
 {
         /*
          * If we're the non-boot CPU, nothing set the stack canary up
@@ -317,71 +311,40 @@ void cpu_idle(void)
          * canaries already on the stack wont ever trigger).
          */
         boot_init_stack_canary();
-        current_thread_info()->status |= TS_POLLING;
-
-        while (1) {
-                tick_nohz_idle_enter();
-
-                while (!need_resched()) {
-                        rmb();
-
-                        if (cpu_is_offline(smp_processor_id()))
-                                play_dead();
-
-                        /*
-                         * Idle routines should keep interrupts disabled
-                         * from here on, until they go to idle.
-                         * Otherwise, idle callbacks can misfire.
-                         */
-                        local_touch_nmi();
-                        local_irq_disable();
-
-                        enter_idle();
-
-                        /* Don't trace irqs off for idle */
-                        stop_critical_timings();
-
-                        /* enter_idle() needs rcu for notifiers */
-                        rcu_idle_enter();
+}
 
-                        if (cpuidle_idle_call())
-                                x86_idle();
+void arch_cpu_idle_enter(void)
+{
+        local_touch_nmi();
+        enter_idle();
+}
 
-                        rcu_idle_exit();
-                        start_critical_timings();
+void arch_cpu_idle_exit(void)
+{
+        __exit_idle();
+}
 
-                        /* In many cases the interrupt that ended idle
-                           has already called exit_idle. But some idle
-                           loops can be woken up without interrupt. */
-                        __exit_idle();
-                }
+void arch_cpu_idle_dead(void)
+{
+        play_dead();
+}
 
-                tick_nohz_idle_exit();
-                preempt_enable_no_resched();
-                schedule();
-                preempt_disable();
-        }
+/*
+ * Called from the generic idle code.
+ */
+void arch_cpu_idle(void)
+{
+        if (cpuidle_idle_call())
+                x86_idle();
 }
 
 /*
- * We use this if we don't have any better
- * idle routine..
+ * We use this if we don't have any better idle routine..
  */
 void default_idle(void)
 {
         trace_cpu_idle_rcuidle(1, smp_processor_id());
-        current_thread_info()->status &= ~TS_POLLING;
-        /*
-         * TS_POLLING-cleared state must be visible before we
-         * test NEED_RESCHED:
-         */
-        smp_mb();
-
-        if (!need_resched())
-                safe_halt();    /* enables interrupts racelessly */
-        else
-                local_irq_enable();
-        current_thread_info()->status |= TS_POLLING;
+        safe_halt();
         trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 #ifdef CONFIG_APM_MODULE
@@ -411,20 +374,6 @@ void stop_this_cpu(void *dummy)
                 halt();
 }
 
-/*
- * On SMP it's slightly faster (but much more power-consuming!)
- * to poll the ->work.need_resched flag instead of waiting for the
- * cross-CPU IPI to arrive. Use this option with caution.
- */
-static void poll_idle(void)
-{
-        trace_cpu_idle_rcuidle(0, smp_processor_id());
-        local_irq_enable();
-        while (!need_resched())
-                cpu_relax();
-        trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
-}
-
 bool amd_e400_c1e_detected;
 EXPORT_SYMBOL(amd_e400_c1e_detected);
 
@@ -489,13 +438,13 @@ static void amd_e400_idle(void)
 void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
-        if (x86_idle == poll_idle && smp_num_siblings > 1)
+        if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1)
                 pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n");
 #endif
-        if (x86_idle)
+        if (x86_idle || boot_option_idle_override == IDLE_POLL)
                 return;
 
-        if (cpu_has_amd_erratum(amd_erratum_400)) {
+        if (cpu_has_bug(c, X86_BUG_AMD_APIC_C1E)) {
                 /* E400: APIC timer interrupt does not wake up CPU from C1e */
                 pr_info("using AMD E400 aware idle routine\n");
                 x86_idle = amd_e400_idle;
@@ -517,8 +466,8 @@ static int __init idle_setup(char *str)
 
         if (!strcmp(str, "poll")) {
                 pr_info("using polling idle threads\n");
-                x86_idle = poll_idle;
                 boot_option_idle_override = IDLE_POLL;
+                cpu_idle_poll_ctrl(true);
         } else if (!strcmp(str, "halt")) {
                 /*
                  * When the boot option of idle=halt is added, halt is
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 26ee48a33dc4..04ee1e2e4c02 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -354,18 +354,22 @@ static void ati_force_hpet_resume(void)
 
 static u32 ati_ixp4x0_rev(struct pci_dev *dev)
 {
-        u32 d;
-        u8  b;
+        int err = 0;
+        u32 d = 0;
+        u8  b = 0;
 
-        pci_read_config_byte(dev, 0xac, &b);
+        err = pci_read_config_byte(dev, 0xac, &b);
         b &= ~(1<<5);
-        pci_write_config_byte(dev, 0xac, b);
-        pci_read_config_dword(dev, 0x70, &d);
+        err |= pci_write_config_byte(dev, 0xac, b);
+        err |= pci_read_config_dword(dev, 0x70, &d);
         d |= 1<<8;
-        pci_write_config_dword(dev, 0x70, d);
-        pci_read_config_dword(dev, 0x8, &d);
+        err |= pci_write_config_dword(dev, 0x70, d);
+        err |= pci_read_config_dword(dev, 0x8, &d);
         d &= 0xff;
         dev_printk(KERN_DEBUG, &dev->dev, "SB4X0 revision 0x%x\n", d);
+
+        WARN_ON_ONCE(err);
+
         return d;
 }
 
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 2e8f3d3b5641..198eb201ed3b 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -13,6 +13,7 @@
 #include <asm/x86_init.h>
 #include <asm/time.h>
 #include <asm/mrst.h>
+#include <asm/rtc.h>
 
 #ifdef CONFIG_X86_32
 /*
@@ -36,70 +37,24 @@ EXPORT_SYMBOL(rtc_lock);
  * nowtime is written into the registers of the CMOS clock, it will
  * jump to the next second precisely 500 ms later. Check the Motorola
  * MC146818A or Dallas DS12887 data sheet for details.
- *
- * BUG: This routine does not handle hour overflow properly; it just
- *      sets the minutes. Usually you'll only notice that after reboot!
  */
 int mach_set_rtc_mmss(unsigned long nowtime)
 {
-        int real_seconds, real_minutes, cmos_minutes;
-        unsigned char save_control, save_freq_select;
-        unsigned long flags;
+        struct rtc_time tm;
         int retval = 0;
 
-        spin_lock_irqsave(&rtc_lock, flags);
-
-         /* tell the clock it's being set */
-        save_control = CMOS_READ(RTC_CONTROL);
-        CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
-
-        /* stop and reset prescaler */
-        save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
-        CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
-
-        cmos_minutes = CMOS_READ(RTC_MINUTES);
-        if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
-                cmos_minutes = bcd2bin(cmos_minutes);
-
-        /*
-         * since we're only adjusting minutes and seconds,
-         * don't interfere with hour overflow. This avoids
-         * messing with unknown time zones but requires your
-         * RTC not to be off by more than 15 minutes
-         */
-        real_seconds = nowtime % 60;
-        real_minutes = nowtime / 60;
-        /* correct for half hour time zone */
-        if (((abs(real_minutes - cmos_minutes) + 15)/30) & 1)
-                real_minutes += 30;
-        real_minutes %= 60;
-
-        if (abs(real_minutes - cmos_minutes) < 30) {
-                if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-                        real_seconds = bin2bcd(real_seconds);
-                        real_minutes = bin2bcd(real_minutes);
-                }
-                CMOS_WRITE(real_seconds, RTC_SECONDS);
-                CMOS_WRITE(real_minutes, RTC_MINUTES);
+        rtc_time_to_tm(nowtime, &tm);
+        if (!rtc_valid_tm(&tm)) {
+                retval = set_rtc_time(&tm);
+                if (retval)
+                        printk(KERN_ERR "%s: RTC write failed with error %d\n",
+                               __FUNCTION__, retval);
         } else {
-                printk_once(KERN_NOTICE
-                       "set_rtc_mmss: can't update from %d to %d\n",
-                       cmos_minutes, real_minutes);
-                retval = -1;
+                printk(KERN_ERR
+                       "%s: Invalid RTC value: write of %lx to RTC failed\n",
+                        __FUNCTION__, nowtime);
+                retval = -EINVAL;
         }
-
-        /* The following flags have to be released exactly in this order,
-         * otherwise the DS12887 (popular MC146818A clone with integrated
-         * battery and quartz) will not reset the oscillator and will not
-         * update precisely 500 ms later. You won't find this mentioned in
-         * the Dallas Semiconductor data sheets, but who believes data
-         * sheets anyway ...                           -- Markus Kuhn
-         */
-        CMOS_WRITE(save_control, RTC_CONTROL);
-        CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
-
-        spin_unlock_irqrestore(&rtc_lock, flags);
-
         return retval;
 }
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 90d8cc930f5e..4689855c2f8a 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -82,7 +82,6 @@
 #include <asm/timer.h>
 #include <asm/i8259.h>
 #include <asm/sections.h>
-#include <asm/dmi.h>
 #include <asm/io_apic.h>
 #include <asm/ist.h>
 #include <asm/setup_arch.h>
@@ -173,12 +172,10 @@ static struct resource bss_resource = {
 /* cpu data as detected by the assembly code in head.S */
 struct cpuinfo_x86 new_cpu_data __cpuinitdata = {
         .wp_works_ok = -1,
-        .fdiv_bug = -1,
 };
 /* common cpu data for all cpus */
 struct cpuinfo_x86 boot_cpu_data __read_mostly = {
         .wp_works_ok = -1,
-        .fdiv_bug = -1,
 };
 EXPORT_SYMBOL(boot_cpu_data);
 
@@ -507,11 +504,14 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
  * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * On 64bit, old kexec-tools need to under 896MiB.
  */
 #ifdef CONFIG_X86_32
-# define CRASH_KERNEL_ADDR_MAX  (512 << 20)
+# define CRASH_KERNEL_ADDR_LOW_MAX      (512 << 20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX     (512 << 20)
 #else
-# define CRASH_KERNEL_ADDR_MAX  MAXMEM
+# define CRASH_KERNEL_ADDR_LOW_MAX      (896UL<<20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX     MAXMEM
 #endif
 
 static void __init reserve_crashkernel_low(void)
@@ -521,19 +521,35 @@ static void __init reserve_crashkernel_low(void)
         unsigned long long low_base = 0, low_size = 0;
         unsigned long total_low_mem;
         unsigned long long base;
+        bool auto_set = false;
         int ret;
 
         total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT));
+        /* crashkernel=Y,low */
         ret = parse_crashkernel_low(boot_command_line, total_low_mem,
                                                 &low_size, &base);
-        if (ret != 0 || low_size <= 0)
-                return;
+        if (ret != 0) {
+                /*
+                 * two parts from lib/swiotlb.c:
+                 *      swiotlb size: user specified with swiotlb= or default.
+                 *      swiotlb overflow buffer: now is hardcoded to 32k.
+                 *              We round it to 8M for other buffers that
+                 *              may need to stay low too.
+                 */
+                low_size = swiotlb_size_or_default() + (8UL<<20);
+                auto_set = true;
+        } else {
+                /* passed with crashkernel=0,low ? */
+                if (!low_size)
+                        return;
+        }
 
         low_base = memblock_find_in_range(low_size, (1ULL<<32),
                                         low_size, alignment);
 
         if (!low_base) {
-                pr_info("crashkernel low reservation failed - No suitable area found.\n");
+                if (!auto_set)
+                        pr_info("crashkernel low reservation failed - No suitable area found.\n");
 
                 return;
         }
@@ -554,14 +570,22 @@ static void __init reserve_crashkernel(void)
         const unsigned long long alignment = 16<<20;    /* 16M */
         unsigned long long total_mem;
         unsigned long long crash_size, crash_base;
+        bool high = false;
         int ret;
 
         total_mem = memblock_phys_mem_size();
 
+        /* crashkernel=XM */
         ret = parse_crashkernel(boot_command_line, total_mem,
                         &crash_size, &crash_base);
-        if (ret != 0 || crash_size <= 0)
-                return;
+        if (ret != 0 || crash_size <= 0) {
+                /* crashkernel=X,high */
+                ret = parse_crashkernel_high(boot_command_line, total_mem,
+                                &crash_size, &crash_base);
+                if (ret != 0 || crash_size <= 0)
+                        return;
+                high = true;
+        }
 
         /* 0 means: find the address automatically */
         if (crash_base <= 0) {
@@ -569,7 +593,9 @@ static void __init reserve_crashkernel(void)
                  *  kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
                  */
                 crash_base = memblock_find_in_range(alignment,
-                               CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
+                                        high ? CRASH_KERNEL_ADDR_HIGH_MAX :
+                                               CRASH_KERNEL_ADDR_LOW_MAX,
+                                        crash_size, alignment);
 
                 if (!crash_base) {
                         pr_info("crashkernel reservation failed - No suitable area found.\n");
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 9f190a2a00e9..9c73b51817e4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -284,7 +284,7 @@ notrace static void __cpuinit start_secondary(void *unused)
         x86_cpuinit.setup_percpu_clockev();
 
         wmb();
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 void __init smp_store_boot_cpu_info(void)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 68bda7a84159..772e2a846dec 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -12,6 +12,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/context_tracking.h>
 #include <linux/interrupt.h>
 #include <linux/kallsyms.h>
 #include <linux/spinlock.h>
@@ -55,8 +56,7 @@
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/mce.h>
-#include <asm/context_tracking.h>
-
+#include <asm/fixmap.h>
 #include <asm/mach_traps.h>
 
 #ifdef CONFIG_X86_64
@@ -176,34 +176,38 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 #define DO_ERROR(trapnr, signr, str, name)                              \
 dotraplinkage void do_##name(struct pt_regs *regs, long error_code)     \
 {                                                                       \
-        exception_enter(regs);                                          \
+        enum ctx_state prev_state;                                      \
+                                                                        \
+        prev_state = exception_enter();                                 \
         if (notify_die(DIE_TRAP, str, regs, error_code,                 \
                         trapnr, signr) == NOTIFY_STOP) {                \
-                exception_exit(regs);                                   \
+                exception_exit(prev_state);                             \
                 return;                                                 \
         }                                                               \
         conditional_sti(regs);                                          \
         do_trap(trapnr, signr, str, regs, error_code, NULL);            \
-        exception_exit(regs);                                           \
+        exception_exit(prev_state);                                     \
 }
 
 #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr)         \
 dotraplinkage void do_##name(struct pt_regs *regs, long error_code)     \
 {                                                                       \
         siginfo_t info;                                                 \
+        enum ctx_state prev_state;                                      \
+                                                                        \
         info.si_signo = signr;                                          \
         info.si_errno = 0;                                              \
         info.si_code = sicode;                                          \
         info.si_addr = (void __user *)siaddr;                           \
-        exception_enter(regs);                                          \
+        prev_state = exception_enter();                                 \
         if (notify_die(DIE_TRAP, str, regs, error_code,                 \
                         trapnr, signr) == NOTIFY_STOP) {                \
-                exception_exit(regs);                                   \
+                exception_exit(prev_state);                             \
                 return;                                                 \
         }                                                               \
         conditional_sti(regs);                                          \
         do_trap(trapnr, signr, str, regs, error_code, &info);           \
-        exception_exit(regs);                                           \
+        exception_exit(prev_state);                                     \
 }
 
 DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
@@ -226,14 +230,16 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
 /* Runs on IST stack */
 dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
 {
-        exception_enter(regs);
+        enum ctx_state prev_state;
+
+        prev_state = exception_enter();
         if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
                        X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
                 preempt_conditional_sti(regs);
                 do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
                 preempt_conditional_cli(regs);
         }
-        exception_exit(regs);
+        exception_exit(prev_state);
 }
 
 dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
@@ -241,7 +247,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
         static const char str[] = "double fault";
         struct task_struct *tsk = current;
 
-        exception_enter(regs);
+        exception_enter();
         /* Return not checked because double check cannot be ignored */
         notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
@@ -261,8 +267,9 @@ dotraplinkage void __kprobes
 do_general_protection(struct pt_regs *regs, long error_code)
 {
         struct task_struct *tsk;
+        enum ctx_state prev_state;
 
-        exception_enter(regs);
+        prev_state = exception_enter();
         conditional_sti(regs);
 
 #ifdef CONFIG_X86_32
@@ -300,12 +307,14 @@ do_general_protection(struct pt_regs *regs, long error_code)
 
         force_sig(SIGSEGV, tsk);
 exit:
-        exception_exit(regs);
+        exception_exit(prev_state);
 }
 
 /* May run on IST stack. */
 dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code)
 {
+        enum ctx_state prev_state;
+
 #ifdef CONFIG_DYNAMIC_FTRACE
         /*
          * ftrace must be first, everything else may cause a recursive crash.
@@ -315,7 +324,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
             ftrace_int3_handler(regs))
                 return;
 #endif
-        exception_enter(regs);
+        prev_state = exception_enter();
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
         if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
                                 SIGTRAP) == NOTIFY_STOP)
@@ -336,7 +345,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
         preempt_conditional_cli(regs);
         debug_stack_usage_dec();
 exit:
-        exception_exit(regs);
+        exception_exit(prev_state);
 }
 
 #ifdef CONFIG_X86_64
@@ -393,11 +402,12 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 {
         struct task_struct *tsk = current;
+        enum ctx_state prev_state;
         int user_icebp = 0;
         unsigned long dr6;
         int si_code;
 
-        exception_enter(regs);
+        prev_state = exception_enter();
 
         get_debugreg(dr6, 6);
 
@@ -467,7 +477,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
         debug_stack_usage_dec();
 
 exit:
-        exception_exit(regs);
+        exception_exit(prev_state);
 }
 
 /*
@@ -561,17 +571,21 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
 
 dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
 {
-        exception_enter(regs);
+        enum ctx_state prev_state;
+
+        prev_state = exception_enter();
         math_error(regs, error_code, X86_TRAP_MF);
-        exception_exit(regs);
+        exception_exit(prev_state);
 }
 
 dotraplinkage void
 do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 {
-        exception_enter(regs);
+        enum ctx_state prev_state;
+
+        prev_state = exception_enter();
         math_error(regs, error_code, X86_TRAP_XF);
-        exception_exit(regs);
+        exception_exit(prev_state);
 }
 
 dotraplinkage void
@@ -639,7 +653,9 @@ EXPORT_SYMBOL_GPL(math_state_restore);
 dotraplinkage void __kprobes
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
-        exception_enter(regs);
+        enum ctx_state prev_state;
+
+        prev_state = exception_enter();
         BUG_ON(use_eager_fpu());
 
 #ifdef CONFIG_MATH_EMULATION
@@ -650,7 +666,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 
                 info.regs = regs;
                 math_emulate(&info);
-                exception_exit(regs);
+                exception_exit(prev_state);
                 return;
         }
 #endif
@@ -658,15 +674,16 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 #ifdef CONFIG_X86_32
         conditional_sti(regs);
 #endif
-        exception_exit(regs);
+        exception_exit(prev_state);
 }
 
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 {
         siginfo_t info;
+        enum ctx_state prev_state;
 
-        exception_enter(regs);
+        prev_state = exception_enter();
         local_irq_enable();
 
         info.si_signo = SIGILL;
@@ -678,7 +695,7 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
                 do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
                         &info);
         }
-        exception_exit(regs);
+        exception_exit(prev_state);
 }
 #endif
 
@@ -753,6 +770,14 @@ void __init trap_init(void)
 #endif
 
         /*
+         * Set the IDT descriptor to a fixed read-only location, so that the
+         * "sidt" instruction will not leak the location of the kernel, and
+         * to defend the IDT against arbitrary memory write vulnerabilities.
+         * It will be reloaded in cpu_init() */
+        __set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO);
+        idt_descr.address = fix_to_virt(FIX_RO_IDT);
+
+        /*
          * Should be a barrier for any external CPU state:
          */
         cpu_init();
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 4b9ea101fe3b..098b3cfda72e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -768,7 +768,8 @@ static cycle_t read_tsc(struct clocksource *cs)
 
 static void resume_tsc(struct clocksource *cs)
 {
-        clocksource_tsc.cycle_last = 0;
+        if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
+                clocksource_tsc.cycle_last = 0;
 }
 
 static struct clocksource clocksource_tsc = {
@@ -939,6 +940,9 @@ static int __init init_tsc_clocksource(void)
                 clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
         }
 
+        if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
+                clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
+
         /*
          * Trust the results of the earlier calibration on systems
          * exporting a reliable TSC.
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 0ba4cfb4f412..2ed845928b5f 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -697,3 +697,32 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
                 send_sig(SIGTRAP, current, 0);
         return ret;
 }
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
+{
+        int rasize, ncopied;
+        unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */
+
+        rasize = is_ia32_task() ? 4 : 8;
+        ncopied = copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize);
+        if (unlikely(ncopied))
+                return -1;
+
+        /* check whether address has been already hijacked */
+        if (orig_ret_vaddr == trampoline_vaddr)
+                return orig_ret_vaddr;
+
+        ncopied = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize);
+        if (likely(!ncopied))
+                return orig_ret_vaddr;
+
+        if (ncopied != rasize) {
+                pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, "
+                        "%%ip=%#lx\n", current->pid, regs->sp, regs->ip);
+
+                force_sig_info(SIGSEGV, SEND_SIG_FORCED, current);
+        }
+
+        return -1;
+}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 22a1530146a8..10c4f3006afd 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -94,10 +94,6 @@ SECTIONS
                 _text = .;
                 /* bootstrapping code */
                 HEAD_TEXT
-#ifdef CONFIG_X86_32
-                . = ALIGN(PAGE_SIZE);
-                *(.text..page_aligned)
-#endif
                 . = ALIGN(8);
                 _stext = .;
                 TEXT_TEXT
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 02b51dd4e4ad..f77df1c5de6e 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1857,7 +1857,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
         if (!pv_eoi_enabled(vcpu))
                 return 0;
         return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
-                                         addr);
+                                         addr, sizeof(u8));
 }
 
 void kvm_lapic_init(void)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e1b1ce21bc00..7d39d70647e3 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -555,7 +555,7 @@ static void svm_init_erratum_383(void)
         int err;
         u64 val;
 
-        if (!cpu_has_amd_erratum(amd_erratum_383))
+        if (!static_cpu_has_bug(X86_BUG_AMD_TLB_MMATCH))
                 return;
 
         /* Use _safe variants to not break nested virtualization */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6667042714cc..867b81037f96 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2459,7 +2459,7 @@ static int hardware_enable(void *garbage)
                 ept_sync_global();
         }
 
-        store_gdt(&__get_cpu_var(host_gdt));
+        native_store_gdt(&__get_cpu_var(host_gdt));
 
         return 0;
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f71500af1f81..e1721324c271 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1406,25 +1406,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
         unsigned long flags, this_tsc_khz;
         struct kvm_vcpu_arch *vcpu = &v->arch;
         struct kvm_arch *ka = &v->kvm->arch;
-        void *shared_kaddr;
         s64 kernel_ns, max_kernel_ns;
         u64 tsc_timestamp, host_tsc;
-        struct pvclock_vcpu_time_info *guest_hv_clock;
+        struct pvclock_vcpu_time_info guest_hv_clock;
         u8 pvclock_flags;
         bool use_master_clock;
 
         kernel_ns = 0;
         host_tsc = 0;
 
-        /* Keep irq disabled to prevent changes to the clock */
-        local_irq_save(flags);
-        this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
-        if (unlikely(this_tsc_khz == 0)) {
-                local_irq_restore(flags);
-                kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
-                return 1;
-        }
-
         /*
          * If the host uses TSC clock, then passthrough TSC as stable
          * to the guest.
@@ -1436,6 +1426,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
                 kernel_ns = ka->master_kernel_ns;
         }
         spin_unlock(&ka->pvclock_gtod_sync_lock);
+
+        /* Keep irq disabled to prevent changes to the clock */
+        local_irq_save(flags);
+        this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+        if (unlikely(this_tsc_khz == 0)) {
+                local_irq_restore(flags);
+                kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
+                return 1;
+        }
         if (!use_master_clock) {
                 host_tsc = native_read_tsc();
                 kernel_ns = get_kernel_ns();
@@ -1463,7 +1462,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
         local_irq_restore(flags);
 
-        if (!vcpu->time_page)
+        if (!vcpu->pv_time_enabled)
                 return 0;
 
         /*
@@ -1525,12 +1524,12 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
          */
         vcpu->hv_clock.version += 2;
 
-        shared_kaddr = kmap_atomic(vcpu->time_page);
-
-        guest_hv_clock = shared_kaddr + vcpu->time_offset;
+        if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
+                &guest_hv_clock, sizeof(guest_hv_clock))))
+                return 0;
 
         /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
-        pvclock_flags = (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED);
+        pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
 
         if (vcpu->pvclock_set_guest_stopped_request) {
                 pvclock_flags |= PVCLOCK_GUEST_STOPPED;
@@ -1543,12 +1542,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
         vcpu->hv_clock.flags = pvclock_flags;
 
-        memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
-               sizeof(vcpu->hv_clock));
-
-        kunmap_atomic(shared_kaddr);
-
-        mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
+        kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+                                &vcpu->hv_clock,
+                                sizeof(vcpu->hv_clock));
         return 0;
 }
 
@@ -1827,7 +1823,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
                 return 0;
         }
 
-        if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa))
+        if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa,
+                                        sizeof(u32)))
                 return 1;
 
         vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
@@ -1837,10 +1834,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
-        if (vcpu->arch.time_page) {
-                kvm_release_page_dirty(vcpu->arch.time_page);
-                vcpu->arch.time_page = NULL;
-        }
+        vcpu->arch.pv_time_enabled = false;
 }
 
 static void accumulate_steal_time(struct kvm_vcpu *vcpu)
@@ -1947,6 +1941,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
                 break;
         case MSR_KVM_SYSTEM_TIME_NEW:
         case MSR_KVM_SYSTEM_TIME: {
+                u64 gpa_offset;
                 kvmclock_reset(vcpu);
 
                 vcpu->arch.time = data;
@@ -1956,14 +1951,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
                 if (!(data & 1))
                         break;
 
-                /* ...but clean it before doing the actual write */
-                vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
-
-                vcpu->arch.time_page =
-                                gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
+                gpa_offset = data & ~(PAGE_MASK | 1);
 
-                if (is_error_page(vcpu->arch.time_page))
-                        vcpu->arch.time_page = NULL;
+                if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+                     &vcpu->arch.pv_time, data & ~1ULL,
+                     sizeof(struct pvclock_vcpu_time_info)))
+                        vcpu->arch.pv_time_enabled = false;
+                else
+                        vcpu->arch.pv_time_enabled = true;
 
                 break;
         }
@@ -1980,7 +1975,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
                         return 1;
 
                 if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
-                                                        data & KVM_STEAL_VALID_BITS))
+                                                data & KVM_STEAL_VALID_BITS,
+                                                sizeof(struct kvm_steal_time)))
                         return 1;
 
                 vcpu->arch.st.msr_val = data;
@@ -2967,7 +2963,7 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
  */
 static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
 {
-        if (!vcpu->arch.time_page)
+        if (!vcpu->arch.pv_time_enabled)
                 return -EINVAL;
         vcpu->arch.pvclock_set_guest_stopped_request = true;
         kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -6718,6 +6714,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
                 goto fail_free_wbinvd_dirty_mask;
 
         vcpu->arch.ia32_tsc_adjust_msr = 0x0;
+        vcpu->arch.pv_time_enabled = false;
         kvm_async_pf_hash_reset(vcpu);
         kvm_pmu_init(vcpu);
 
diff --git a/arch/x86/lguest/Kconfig b/arch/x86/lguest/Kconfig
index 29043d2048a0..4a0890f815c4 100644
--- a/arch/x86/lguest/Kconfig
+++ b/arch/x86/lguest/Kconfig
@@ -1,7 +1,6 @@
 config LGUEST_GUEST
         bool "Lguest guest support"
-        select PARAVIRT
-        depends on X86_32
+        depends on X86_32 && PARAVIRT
         select TTY
         select VIRTUALIZATION
         select VIRTIO
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 1cbd89ca5569..7114c63f047d 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1334,6 +1334,7 @@ __init void lguest_init(void)
         pv_mmu_ops.read_cr3 = lguest_read_cr3;
         pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
         pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
+        pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu;
         pv_mmu_ops.pte_update = lguest_pte_update;
         pv_mmu_ops.pte_update_defer = lguest_pte_update;
 
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 2af5df3ade7c..e78b8eee6615 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -61,7 +61,7 @@ ENTRY(csum_partial)
         testl $3, %esi          # Check alignment.
         jz 2f                   # Jump if alignment is ok.
         testl $1, %esi          # Check alignment.
-        jz 10f                  # Jump if alignment is boundary of 2bytes.
+        jz 10f                  # Jump if alignment is boundary of 2 bytes.
 
         # buf is odd
         dec %ecx
diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
index b908a59eccf5..e78761d6b7f8 100644
--- a/arch/x86/lib/memcpy_32.c
+++ b/arch/x86/lib/memcpy_32.c
@@ -26,7 +26,7 @@ void *memmove(void *dest, const void *src, size_t n)
         char *ret = dest;
 
         __asm__ __volatile__(
-                /* Handle more 16bytes in loop */
+                /* Handle more 16 bytes in loop */
                 "cmp $0x10, %0\n\t"
                 "jb     1f\n\t"
 
@@ -51,7 +51,7 @@ void *memmove(void *dest, const void *src, size_t n)
                 "sub $0x10, %0\n\t"
 
                 /*
-                 * We gobble 16byts forward in each loop.
+                 * We gobble 16 bytes forward in each loop.
                  */
                 "3:\n\t"
                 "sub $0x10, %0\n\t"
@@ -117,7 +117,7 @@ void *memmove(void *dest, const void *src, size_t n)
                 "sub $0x10, %0\n\t"
 
                 /*
-                 * We gobble 16byts backward in each loop.
+                 * We gobble 16 bytes backward in each loop.
                  */
                 "7:\n\t"
                 "sub $0x10, %0\n\t"
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 1c273be7c97e..56313a326188 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -98,7 +98,7 @@ ENTRY(memcpy)
         subq $0x20,     %rdx
         /*
          * At most 3 ALU operations in one cycle,
-         * so append NOPS in the same 16bytes trunk.
+         * so append NOPS in the same 16 bytes trunk.
          */
         .p2align 4
 .Lcopy_backward_loop:
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index ee164610ec46..65268a6104f4 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -27,7 +27,7 @@
 ENTRY(memmove)
         CFI_STARTPROC
 
-        /* Handle more 32bytes in loop */
+        /* Handle more 32 bytes in loop */
         mov %rdi, %rax
         cmp $0x20, %rdx
         jb      1f
@@ -56,7 +56,7 @@ ENTRY(memmove)
 3:
         sub $0x20, %rdx
         /*
-         * We gobble 32byts forward in each loop.
+         * We gobble 32 bytes forward in each loop.
          */
 5:
         sub $0x20, %rdx
@@ -122,7 +122,7 @@ ENTRY(memmove)
         addq %rdx, %rdi
         subq $0x20, %rdx
         /*
-         * We gobble 32byts backward in each loop.
+         * We gobble 32 bytes backward in each loop.
          */
 8:
         subq $0x20, %rdx
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 05928aae911e..906fea315791 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -74,10 +74,10 @@ copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest)
         char c;
         unsigned zero_len;
 
-        for (; len; --len) {
+        for (; len; --len, to++) {
                 if (__get_user_nocheck(c, from++, sizeof(char)))
                         break;
-                if (__put_user_nocheck(c, to++, sizeof(char)))
+                if (__put_user_nocheck(c, to, sizeof(char)))
                         break;
         }
 
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
index 5247d01329ca..2ca15b59fb3f 100644
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@@ -130,9 +130,8 @@ int __init amd_numa_init(void)
                 }
 
                 limit >>= 16;
-                limit <<= 24;
-                limit |= (1<<24)-1;
                 limit++;
+                limit <<= 24;
 
                 if (limit > end)
                         limit = end;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2b97525246d4..654be4ae3047 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -13,12 +13,12 @@
 #include <linux/perf_event.h>           /* perf_sw_event                */
 #include <linux/hugetlb.h>              /* hstate_index_to_shift        */
 #include <linux/prefetch.h>             /* prefetchw                    */
+#include <linux/context_tracking.h>     /* exception_enter(), ...       */
 
 #include <asm/traps.h>                  /* dotraplinkage, ...           */
 #include <asm/pgalloc.h>                /* pgd_*(), ...                 */
 #include <asm/kmemcheck.h>              /* kmemcheck_*(), ...           */
 #include <asm/fixmap.h>                 /* VSYSCALL_START               */
-#include <asm/context_tracking.h>       /* exception_enter(), ...       */
 
 /*
  * Page fault error code bits:
@@ -378,10 +378,12 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
         if (pgd_none(*pgd_ref))
                 return -1;
 
-        if (pgd_none(*pgd))
+        if (pgd_none(*pgd)) {
                 set_pgd(pgd, *pgd_ref);
-        else
+                arch_flush_lazy_mmu_mode();
+        } else {
                 BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+        }
 
         /*
          * Below here mismatches are bugs because these lower tables
@@ -555,7 +557,7 @@ static int is_f00f_bug(struct pt_regs *regs, unsigned long address)
         /*
          * Pentium F0 0F C7 C8 bug workaround:
          */
-        if (boot_cpu_data.f00f_bug) {
+        if (boot_cpu_has_bug(X86_BUG_F00F)) {
                 nr = (address - idt_descr.address) >> 3;
 
                 if (nr == 6) {
@@ -1222,7 +1224,9 @@ good_area:
 dotraplinkage void __kprobes
 do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
-        exception_enter(regs);
+        enum ctx_state prev_state;
+
+        prev_state = exception_enter();
         __do_page_fault(regs, error_code);
-        exception_exit(regs);
+        exception_exit(prev_state);
 }
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 6f31ee56c008..252b8f5489ba 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -137,5 +137,4 @@ void __init set_highmem_pages_init(void)
                 add_highpages_with_active_regions(nid, zone_start_pfn,
                                  zone_end_pfn);
         }
-        totalram_pages += totalhigh_pages;
 }
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 59b7fc453277..fdc5dca14fb3 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -515,11 +515,8 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
         printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
 
         for (; addr < end; addr += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(addr));
-                init_page_count(virt_to_page(addr));
                 memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-                free_page(addr);
-                totalram_pages++;
+                free_reserved_page(virt_to_page(addr));
         }
 #endif
 }
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 2d19001151d5..3ac7e319918d 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -427,14 +427,6 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base)
         pkmap_page_table = pte;
 }
 
-static void __init add_one_highpage_init(struct page *page)
-{
-        ClearPageReserved(page);
-        init_page_count(page);
-        __free_page(page);
-        totalhigh_pages++;
-}
-
 void __init add_highpages_with_active_regions(int nid,
                          unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -448,7 +440,7 @@ void __init add_highpages_with_active_regions(int nid,
                                               start_pfn, end_pfn);
                 for ( ; pfn < e_pfn; pfn++)
                         if (pfn_valid(pfn))
-                                add_one_highpage_init(pfn_to_page(pfn));
+                                free_highmem_page(pfn_to_page(pfn));
         }
 }
 #else
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 474e28f10815..caad9a0ee19f 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1011,14 +1011,12 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct)
         flush_tlb_all();
 }
 
-void __ref vmemmap_free(struct page *memmap, unsigned long nr_pages)
+void __ref vmemmap_free(unsigned long start, unsigned long end)
 {
-        unsigned long start = (unsigned long)memmap;
-        unsigned long end = (unsigned long)(memmap + nr_pages);
-
         remove_pagetable(start, end, false);
 }
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
 static void __meminit
 kernel_physical_mapping_remove(unsigned long start, unsigned long end)
 {
@@ -1028,7 +1026,6 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end)
         remove_pagetable(start, end, true);
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 int __ref arch_remove_memory(u64 start, u64 size)
 {
         unsigned long start_pfn = start >> PAGE_SHIFT;
@@ -1067,10 +1064,9 @@ void __init mem_init(void)
 
         /* clear_bss() already clear the empty_zero_page */
 
-        reservedpages = 0;
-
-        /* this will put all low memory onto the freelists */
         register_page_bootmem_info();
+
+        /* this will put all memory onto the freelists */
         totalram_pages = free_all_bootmem();
 
         absent_pages = absent_pages_in_range(0, max_pfn);
@@ -1285,18 +1281,17 @@ static long __meminitdata addr_start, addr_end;
 static void __meminitdata *p_start, *p_end;
 static int __meminitdata node_start;
 
-int __meminit
-vmemmap_populate(struct page *start_page, unsigned long size, int node)
+static int __meminit vmemmap_populate_hugepages(unsigned long start,
+                                                unsigned long end, int node)
 {
-        unsigned long addr = (unsigned long)start_page;
-        unsigned long end = (unsigned long)(start_page + size);
+        unsigned long addr;
         unsigned long next;
         pgd_t *pgd;
         pud_t *pud;
         pmd_t *pmd;
 
-        for (; addr < end; addr = next) {
-                void *p = NULL;
+        for (addr = start; addr < end; addr = next) {
+                next = pmd_addr_end(addr, end);
 
                 pgd = vmemmap_pgd_populate(addr, node);
                 if (!pgd)
@@ -1306,31 +1301,14 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
                 if (!pud)
                         return -ENOMEM;
 
-                if (!cpu_has_pse) {
-                        next = (addr + PAGE_SIZE) & PAGE_MASK;
-                        pmd = vmemmap_pmd_populate(pud, addr, node);
-
-                        if (!pmd)
-                                return -ENOMEM;
-
-                        p = vmemmap_pte_populate(pmd, addr, node);
+                pmd = pmd_offset(pud, addr);
+                if (pmd_none(*pmd)) {
+                        void *p;
 
-                        if (!p)
-                                return -ENOMEM;
-
-                        addr_end = addr + PAGE_SIZE;
-                        p_end = p + PAGE_SIZE;
-                } else {
-                        next = pmd_addr_end(addr, end);
-
-                        pmd = pmd_offset(pud, addr);
-                        if (pmd_none(*pmd)) {
+                        p = vmemmap_alloc_block_buf(PMD_SIZE, node);
+                        if (p) {
                                 pte_t entry;
 
-                                p = vmemmap_alloc_block_buf(PMD_SIZE, node);
-                                if (!p)
-                                        return -ENOMEM;
-
                                 entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
                                                 PAGE_KERNEL_LARGE);
                                 set_pmd(pmd, __pmd(pte_val(entry)));
@@ -1347,15 +1325,32 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 
                                 addr_end = addr + PMD_SIZE;
                                 p_end = p + PMD_SIZE;
-                        } else
-                                vmemmap_verify((pte_t *)pmd, node, addr, next);
+                                continue;
+                        }
+                } else if (pmd_large(*pmd)) {
+                        vmemmap_verify((pte_t *)pmd, node, addr, next);
+                        continue;
                 }
-
+                pr_warn_once("vmemmap: falling back to regular page backing\n");
+                if (vmemmap_populate_basepages(addr, next, node))
+                        return -ENOMEM;
         }
-        sync_global_pgds((unsigned long)start_page, end - 1);
         return 0;
 }
 
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
+{
+        int err;
+
+        if (cpu_has_pse)
+                err = vmemmap_populate_hugepages(start, end, node);
+        else
+                err = vmemmap_populate_basepages(start, end, node);
+        if (!err)
+                sync_global_pgds(start, end - 1);
+        return err;
+}
+
 #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE)
 void register_page_bootmem_memmap(unsigned long section_nr,
                                   struct page *start_page, unsigned long size)
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 78fe3f1ac49f..9a1e6583910c 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -282,12 +282,7 @@ void iounmap(volatile void __iomem *addr)
            in parallel. Reuse of the virtual address is prevented by
            leaving it in the global lists until we're done with it.
            cpa takes care of the direct mappings. */
-        read_lock(&vmlist_lock);
-        for (p = vmlist; p; p = p->next) {
-                if (p->addr == (void __force *)addr)
-                        break;
-        }
-        read_unlock(&vmlist_lock);
+        p = find_vm_area((void __force *)addr);
 
         if (!p) {
                 printk(KERN_ERR "iounmap: bad address %p\n", addr);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 72fe01e9e414..a71c4e207679 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -114,14 +114,11 @@ void numa_clear_node(int cpu)
  */
 void __init setup_node_to_cpumask_map(void)
 {
-        unsigned int node, num = 0;
+        unsigned int node;
 
         /* setup nr_node_ids if not done yet */
-        if (nr_node_ids == MAX_NUMNODES) {
-                for_each_node_mask(node, node_possible_map)
-                        num = node;
-                nr_node_ids = num + 1;
-        }
+        if (nr_node_ids == MAX_NUMNODES)
+                setup_nr_node_ids();
 
         /* allocate the map */
         for (node = 0; node < nr_node_ids; node++)
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index b0086567271c..d0b1773d9d2e 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -68,7 +68,7 @@ static int print_split(struct split_state *s)
                         s->gpg++;
                         i += GPS/PAGE_SIZE;
                 } else if (level == PG_LEVEL_2M) {
-                        if (!(pte_val(*pte) & _PAGE_PSE)) {
+                        if ((pte_val(*pte) & _PAGE_PRESENT) && !(pte_val(*pte) & _PAGE_PSE)) {
                                 printk(KERN_ERR
                                         "%lx level %d but not PSE %Lx\n",
                                         addr, level, (u64)pte_val(*pte));
@@ -130,13 +130,12 @@ static int pageattr_test(void)
         }
 
         failed += print_split(&sa);
-        srandom32(100);
 
         for (i = 0; i < NTEST; i++) {
-                unsigned long pfn = random32() % max_pfn_mapped;
+                unsigned long pfn = prandom_u32() % max_pfn_mapped;
 
                 addr[i] = (unsigned long)__va(pfn << PAGE_SHIFT);
-                len[i] = random32() % 100;
+                len[i] = prandom_u32() % 100;
                 len[i] = min_t(unsigned long, len[i], max_pfn_mapped - pfn - 1);
 
                 if (len[i] == 0)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 091934e1d0d9..bb32480c2d71 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -467,7 +467,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
          * We are safe now. Check whether the new pgprot is the same:
          */
         old_pte = *kpte;
-        old_prot = new_prot = req_prot = pte_pgprot(old_pte);
+        old_prot = req_prot = pte_pgprot(old_pte);
 
         pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr);
         pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
@@ -478,12 +478,12 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
          * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL
          * for the ancient hardware that doesn't support it.
          */
-        if (pgprot_val(new_prot) & _PAGE_PRESENT)
-                pgprot_val(new_prot) |= _PAGE_PSE | _PAGE_GLOBAL;
+        if (pgprot_val(req_prot) & _PAGE_PRESENT)
+                pgprot_val(req_prot) |= _PAGE_PSE | _PAGE_GLOBAL;
         else
-                pgprot_val(new_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL);
+                pgprot_val(req_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL);
 
-        new_prot = canon_pgprot(new_prot);
+        req_prot = canon_pgprot(req_prot);
 
         /*
          * old_pte points to the large page base address. So we need
@@ -542,13 +542,14 @@ out_unlock:
         return do_split;
 }
 
-int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase)
+static int
+__split_large_page(pte_t *kpte, unsigned long address, struct page *base)
 {
+        pte_t *pbase = (pte_t *)page_address(base);
         unsigned long pfn, pfninc = 1;
         unsigned int i, level;
         pte_t *tmp;
         pgprot_t ref_prot;
-        struct page *base = virt_to_page(pbase);
 
         spin_lock(&pgd_lock);
         /*
@@ -633,7 +634,6 @@ int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase)
 
 static int split_large_page(pte_t *kpte, unsigned long address)
 {
-        pte_t *pbase;
         struct page *base;
 
         if (!debug_pagealloc)
@@ -644,8 +644,7 @@ static int split_large_page(pte_t *kpte, unsigned long address)
         if (!base)
                 return -ENOMEM;
 
-        pbase = (pte_t *)page_address(base);
-        if (__split_large_page(kpte, address, pbase))
+        if (__split_large_page(kpte, address, base))
                 __free_page(base);
 
         return 0;
@@ -1413,6 +1412,8 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
          * but that can deadlock->flush only current cpu:
          */
         __flush_tlb_all();
+
+        arch_flush_lazy_mmu_mode();
 }
 
 #ifdef CONFIG_HIBERNATION
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 193350b51f90..17fda6a8b3c2 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -58,6 +58,13 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 {
         paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
+        /*
+         * NOTE! For PAE, any changes to the top page-directory-pointer-table
+         * entries need a full cr3 reload to flush.
+         */
+#ifdef CONFIG_X86_PAE
+        tlb->need_flush_all = 1;
+#endif
         tlb_remove_page(tlb, virt_to_page(pmd));
 }
 
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 901177d75ff5..305c68b8d538 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -6,6 +6,7 @@
 
 #include <linux/sched.h>
 #include <linux/pci.h>
+#include <linux/pci-acpi.h>
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/dmi.h>
@@ -170,6 +171,16 @@ void pcibios_fixup_bus(struct pci_bus *b)
                 pcibios_fixup_device_resources(dev);
 }
 
+void pcibios_add_bus(struct pci_bus *bus)
+{
+        acpi_pci_add_bus(bus);
+}
+
+void pcibios_remove_bus(struct pci_bus *bus)
+{
+        acpi_pci_remove_bus(bus);
+}
+
 /*
  * Only use DMI information to set this if nothing was passed
  * on the kernel command line (which was parsed earlier).
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 94e76620460f..4a9be6ddf054 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -177,7 +177,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
                 goto error;
         i = 0;
         list_for_each_entry(msidesc, &dev->msi_list, list) {
-                irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0,
+                irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i],
                                                (type == PCI_CAP_ID_MSIX) ?
                                                "pcifront-msi-x" :
                                                "pcifront-msi",
@@ -244,7 +244,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
                         dev_dbg(&dev->dev,
                                 "xen: msi already bound to pirq=%d\n", pirq);
                 }
-                irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0,
+                irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
                                                (type == PCI_CAP_ID_MSIX) ?
                                                "msi-x" : "msi",
                                                DOMID_SELF);
@@ -326,7 +326,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
                 }
 
                 ret = xen_bind_pirq_msi_to_irq(dev, msidesc,
-                                               map_irq.pirq, map_irq.index,
+                                               map_irq.pirq,
                                                (type == PCI_CAP_ID_MSIX) ?
                                                "msi-x" : "msi",
                                                 domid);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 5f2ecaf3f9d8..b55d174e5034 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -41,6 +41,7 @@
 #include <linux/io.h>
 #include <linux/reboot.h>
 #include <linux/bcd.h>
+#include <linux/ucs2_string.h>
 
 #include <asm/setup.h>
 #include <asm/efi.h>
@@ -48,9 +49,17 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/x86_init.h>
+#include <asm/rtc.h>
 
 #define EFI_DEBUG       1
 
+/*
+ * There's some additional metadata associated with each
+ * variable. Intel's reference implementation is 60 bytes - bump that
+ * to account for potential alignment constraints
+ */
+#define VAR_METADATA_SIZE 64
+
 struct efi __read_mostly efi = {
         .mps        = EFI_INVALID_TABLE_ADDR,
         .acpi       = EFI_INVALID_TABLE_ADDR,
@@ -69,6 +78,13 @@ struct efi_memory_map memmap;
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
+static u64 efi_var_store_size;
+static u64 efi_var_remaining_size;
+static u64 efi_var_max_var_size;
+static u64 boot_used_size;
+static u64 boot_var_size;
+static u64 active_size;
+
 unsigned long x86_efi_facility;
 
 /*
@@ -98,6 +114,15 @@ static int __init setup_add_efi_memmap(char *arg)
 }
 early_param("add_efi_memmap", setup_add_efi_memmap);
 
+static bool efi_no_storage_paranoia;
+
+static int __init setup_storage_paranoia(char *arg)
+{
+        efi_no_storage_paranoia = true;
+        return 0;
+}
+early_param("efi_no_storage_paranoia", setup_storage_paranoia);
+
 
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
@@ -162,8 +187,53 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
                                                efi_char16_t *name,
                                                efi_guid_t *vendor)
 {
-        return efi_call_virt3(get_next_variable,
-                              name_size, name, vendor);
+        efi_status_t status;
+        static bool finished = false;
+        static u64 var_size;
+
+        status = efi_call_virt3(get_next_variable,
+                                name_size, name, vendor);
+
+        if (status == EFI_NOT_FOUND) {
+                finished = true;
+                if (var_size < boot_used_size) {
+                        boot_var_size = boot_used_size - var_size;
+                        active_size += boot_var_size;
+                } else {
+                        printk(KERN_WARNING FW_BUG  "efi: Inconsistent initial sizes\n");
+                }
+        }
+
+        if (boot_used_size && !finished) {
+                unsigned long size;
+                u32 attr;
+                efi_status_t s;
+                void *tmp;
+
+                s = virt_efi_get_variable(name, vendor, &attr, &size, NULL);
+
+                if (s != EFI_BUFFER_TOO_SMALL || !size)
+                        return status;
+
+                tmp = kmalloc(size, GFP_ATOMIC);
+
+                if (!tmp)
+                        return status;
+
+                s = virt_efi_get_variable(name, vendor, &attr, &size, tmp);
+
+                if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) {
+                        var_size += size;
+                        var_size += ucs2_strsize(name, 1024);
+                        active_size += size;
+                        active_size += VAR_METADATA_SIZE;
+                        active_size += ucs2_strsize(name, 1024);
+                }
+
+                kfree(tmp);
+        }
+
+        return status;
 }
 
 static efi_status_t virt_efi_set_variable(efi_char16_t *name,
@@ -172,9 +242,34 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
                                           unsigned long data_size,
                                           void *data)
 {
-        return efi_call_virt5(set_variable,
-                              name, vendor, attr,
-                              data_size, data);
+        efi_status_t status;
+        u32 orig_attr = 0;
+        unsigned long orig_size = 0;
+
+        status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size,
+                                       NULL);
+
+        if (status != EFI_BUFFER_TOO_SMALL)
+                orig_size = 0;
+
+        status = efi_call_virt5(set_variable,
+                                name, vendor, attr,
+                                data_size, data);
+
+        if (status == EFI_SUCCESS) {
+                if (orig_size) {
+                        active_size -= orig_size;
+                        active_size -= ucs2_strsize(name, 1024);
+                        active_size -= VAR_METADATA_SIZE;
+                }
+                if (data_size) {
+                        active_size += data_size;
+                        active_size += ucs2_strsize(name, 1024);
+                        active_size += VAR_METADATA_SIZE;
+                }
+        }
+
+        return status;
 }
 
 static efi_status_t virt_efi_query_variable_info(u32 attr,
@@ -258,10 +353,10 @@ static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
 
 int efi_set_rtc_mmss(unsigned long nowtime)
 {
-        int real_seconds, real_minutes;
         efi_status_t    status;
         efi_time_t      eft;
         efi_time_cap_t  cap;
+        struct rtc_time tm;
 
         status = efi.get_time(&eft, &cap);
         if (status != EFI_SUCCESS) {
@@ -269,13 +364,20 @@ int efi_set_rtc_mmss(unsigned long nowtime)
                 return -1;
         }
 
-        real_seconds = nowtime % 60;
-        real_minutes = nowtime / 60;
-        if (((abs(real_minutes - eft.minute) + 15)/30) & 1)
-                real_minutes += 30;
-        real_minutes %= 60;
-        eft.minute = real_minutes;
-        eft.second = real_seconds;
+        rtc_time_to_tm(nowtime, &tm);
+        if (!rtc_valid_tm(&tm)) {
+                eft.year = tm.tm_year + 1900;
+                eft.month = tm.tm_mon + 1;
+                eft.day = tm.tm_mday;
+                eft.minute = tm.tm_min;
+                eft.second = tm.tm_sec;
+                eft.nanosecond = 0;
+        } else {
+                printk(KERN_ERR
+                       "%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n",
+                       __FUNCTION__, nowtime);
+                return -1;
+        }
 
         status = efi.set_time(&eft);
         if (status != EFI_SUCCESS) {
@@ -682,6 +784,9 @@ void __init efi_init(void)
         char vendor[100] = "unknown";
         int i = 0;
         void *tmp;
+        struct setup_data *data;
+        struct efi_var_bootdata *efi_var_data;
+        u64 pa_data;
 
 #ifdef CONFIG_X86_32
         if (boot_params.efi_info.efi_systab_hi ||
@@ -699,6 +804,22 @@ void __init efi_init(void)
         if (efi_systab_init(efi_phys.systab))
                 return;
 
+        pa_data = boot_params.hdr.setup_data;
+        while (pa_data) {
+                data = early_ioremap(pa_data, sizeof(*efi_var_data));
+                if (data->type == SETUP_EFI_VARS) {
+                        efi_var_data = (struct efi_var_bootdata *)data;
+
+                        efi_var_store_size = efi_var_data->store_size;
+                        efi_var_remaining_size = efi_var_data->remaining_size;
+                        efi_var_max_var_size = efi_var_data->max_var_size;
+                }
+                pa_data = data->next;
+                early_iounmap(data, sizeof(*efi_var_data));
+        }
+
+        boot_used_size = efi_var_store_size - efi_var_remaining_size;
+
         set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
 
         /*
@@ -999,3 +1120,48 @@ u64 efi_mem_attributes(unsigned long phys_addr)
         }
         return 0;
 }
+
+/*
+ * Some firmware has serious problems when using more than 50% of the EFI
+ * variable store, i.e. it triggers bugs that can brick machines. Ensure that
+ * we never use more than this safe limit.
+ *
+ * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
+ * store.
+ */
+efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
+{
+        efi_status_t status;
+        u64 storage_size, remaining_size, max_size;
+
+        status = efi.query_variable_info(attributes, &storage_size,
+                                         &remaining_size, &max_size);
+        if (status != EFI_SUCCESS)
+                return status;
+
+        if (!max_size && remaining_size > size)
+                printk_once(KERN_ERR FW_BUG "Broken EFI implementation"
+                            " is returning MaxVariableSize=0\n");
+        /*
+         * Some firmware implementations refuse to boot if there's insufficient
+         * space in the variable store. We account for that by refusing the
+         * write if permitting it would reduce the available space to under
+         * 50%. However, some firmware won't reclaim variable space until
+         * after the used (not merely the actively used) space drops below
+         * a threshold. We can approximate that case with the value calculated
+         * above. If both the firmware and our calculations indicate that the
+         * available space would drop below 50%, refuse the write.
+         */
+
+        if (!storage_size || size > remaining_size ||
+            (max_size && size > max_size))
+                return EFI_OUT_OF_RESOURCES;
+
+        if (!efi_no_storage_paranoia &&
+            ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) &&
+             (remaining_size - size < storage_size / 2)))
+                return EFI_OUT_OF_RESOURCES;
+
+        return EFI_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(efi_query_variable_store);
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index e31bcd8f2eee..a0a0a4389bbd 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -356,8 +356,7 @@ static int __init sfi_parse_gpio(struct sfi_table_header *table)
         num = SFI_GET_NUM_ENTRIES(sb, struct sfi_gpio_table_entry);
         pentry = (struct sfi_gpio_table_entry *)sb->pentry;
 
-        gpio_table = (struct sfi_gpio_table_entry *)
-                                kmalloc(num * sizeof(*pentry), GFP_KERNEL);
+        gpio_table = kmalloc(num * sizeof(*pentry), GFP_KERNEL);
         if (!gpio_table)
                 return -1;
         memcpy(gpio_table, pentry, num * sizeof(*pentry));
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index 225bd0f0f675..d62b0a3b5c14 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -85,27 +85,35 @@ unsigned long vrtc_get_time(void)
         return mktime(year, mon, mday, hour, min, sec);
 }
 
-/* Only care about the minutes and seconds */
 int vrtc_set_mmss(unsigned long nowtime)
 {
-        int real_sec, real_min;
         unsigned long flags;
-        int vrtc_min;
-
-        spin_lock_irqsave(&rtc_lock, flags);
-        vrtc_min = vrtc_cmos_read(RTC_MINUTES);
-
-        real_sec = nowtime % 60;
-        real_min = nowtime / 60;
-        if (((abs(real_min - vrtc_min) + 15)/30) & 1)
-                real_min += 30;
-        real_min %= 60;
-
-        vrtc_cmos_write(real_sec, RTC_SECONDS);
-        vrtc_cmos_write(real_min, RTC_MINUTES);
-        spin_unlock_irqrestore(&rtc_lock, flags);
-
-        return 0;
+        struct rtc_time tm;
+        int year;
+        int retval = 0;
+
+        rtc_time_to_tm(nowtime, &tm);
+        if (!rtc_valid_tm(&tm) && tm.tm_year >= 72) {
+                /*
+                 * tm.year is the number of years since 1900, and the
+                 * vrtc need the years since 1972.
+                 */
+                year = tm.tm_year - 72;
+                spin_lock_irqsave(&rtc_lock, flags);
+                vrtc_cmos_write(year, RTC_YEAR);
+                vrtc_cmos_write(tm.tm_mon, RTC_MONTH);
+                vrtc_cmos_write(tm.tm_mday, RTC_DAY_OF_MONTH);
+                vrtc_cmos_write(tm.tm_hour, RTC_HOURS);
+                vrtc_cmos_write(tm.tm_min, RTC_MINUTES);
+                vrtc_cmos_write(tm.tm_sec, RTC_SECONDS);
+                spin_unlock_irqrestore(&rtc_lock, flags);
+        } else {
+                printk(KERN_ERR
+                       "%s: Invalid vRTC value: write of %lx to vRTC failed\n",
+                        __FUNCTION__, nowtime);
+                retval = -EINVAL;
+        }
+        return retval;
 }
 
 void __init mrst_rtc_init(void)
diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c
index 74704be7b1fe..9a2e590dd202 100644
--- a/arch/x86/platform/olpc/olpc-xo1-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo1-sci.c
@@ -460,7 +460,6 @@ static int setup_power_button(struct platform_device *pdev)
 static void free_power_button(void)
 {
         input_unregister_device(power_button_idev);
-        input_free_device(power_button_idev);
 }
 
 static int setup_ebook_switch(struct platform_device *pdev)
@@ -491,7 +490,6 @@ static int setup_ebook_switch(struct platform_device *pdev)
 static void free_ebook_switch(void)
 {
         input_unregister_device(ebook_switch_idev);
-        input_free_device(ebook_switch_idev);
 }
 
 static int setup_lid_switch(struct platform_device *pdev)
@@ -526,6 +524,7 @@ static int setup_lid_switch(struct platform_device *pdev)
 
 err_create_attr:
         input_unregister_device(lid_switch_idev);
+        lid_switch_idev = NULL;
 err_register:
         input_free_device(lid_switch_idev);
         return r;
@@ -535,7 +534,6 @@ static void free_lid_switch(void)
 {
         device_remove_file(&lid_switch_idev->dev, &dev_attr_lid_wake_mode);
         input_unregister_device(lid_switch_idev);
-        input_free_device(lid_switch_idev);
 }
 
 static int xo1_sci_probe(struct platform_device *pdev)
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 98718f604eb6..5c86786bbfd2 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -159,10 +159,9 @@ static __init int uv_rtc_allocate_timers(void)
 {
         int cpu;
 
-        blade_info = kmalloc(uv_possible_blades * sizeof(void *), GFP_KERNEL);
+        blade_info = kzalloc(uv_possible_blades * sizeof(void *), GFP_KERNEL);
         if (!blade_info)
                 return -ENOMEM;
-        memset(blade_info, 0, uv_possible_blades * sizeof(void *));
 
         for_each_present_cpu(cpu) {
                 int nid = cpu_to_node(cpu);
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 120cee1c3f8d..6d6e907cee46 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -11,6 +11,7 @@
 #include <linux/suspend.h>
 #include <linux/export.h>
 #include <linux/smp.h>
+#include <linux/perf_event.h>
 
 #include <asm/pgtable.h>
 #include <asm/proto.h>
@@ -61,11 +62,9 @@ static void __save_processor_state(struct saved_context *ctxt)
          * descriptor tables
          */
 #ifdef CONFIG_X86_32
-        store_gdt(&ctxt->gdt);
         store_idt(&ctxt->idt);
 #else
 /* CONFIG_X86_64 */
-        store_gdt((struct desc_ptr *)&ctxt->gdt_limit);
         store_idt((struct desc_ptr *)&ctxt->idt_limit);
 #endif
         store_tr(ctxt->tr);
@@ -134,7 +133,10 @@ static void fix_processor_context(void)
 {
         int cpu = smp_processor_id();
         struct tss_struct *t = &per_cpu(init_tss, cpu);
-
+#ifdef CONFIG_X86_64
+        struct desc_struct *desc = get_cpu_gdt_table(cpu);
+        tss_desc tss;
+#endif
         set_tss_desc(cpu, t);   /*
                                  * This just modifies memory; should not be
                                  * necessary. But... This is necessary, because
@@ -143,7 +145,9 @@ static void fix_processor_context(void)
                                  */
 
 #ifdef CONFIG_X86_64
-        get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS].type = 9;
+        memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc));
+        tss.type = 0x9; /* The available 64-bit TSS (see AMD vol 2, pg 91 */
+        write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS);
 
         syscall_init();                         /* This sets MSR_*STAR and related */
 #endif
@@ -182,11 +186,9 @@ static void __restore_processor_state(struct saved_context *ctxt)
          * ltr is done i fix_processor_context().
          */
 #ifdef CONFIG_X86_32
-        load_gdt(&ctxt->gdt);
         load_idt(&ctxt->idt);
 #else
 /* CONFIG_X86_64 */
-        load_gdt((const struct desc_ptr *)&ctxt->gdt_limit);
         load_idt((const struct desc_ptr *)&ctxt->idt_limit);
 #endif
 
@@ -228,6 +230,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
         do_fpu_end();
         x86_platform.restore_sched_clock_state();
         mtrr_bp_restore();
+        perf_restore_debug_store();
 }
 
 /* Needed by apm.c */
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index bae601f900ef..e8120346903b 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -39,4 +39,5 @@ $(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/ina
 
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 hostprogs-y     += relocs
+relocs-objs     := relocs_32.o relocs_64.o relocs_common.o
 relocs: $(obj)/relocs
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 79d67bd507fa..590be1090892 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -1,43 +1,36 @@
-#include <stdio.h>
-#include <stdarg.h>
-#include <stdlib.h>
-#include <stdint.h>
-#include <string.h>
-#include <errno.h>
-#include <unistd.h>
-#include <elf.h>
-#include <byteswap.h>
-#define USE_BSD
-#include <endian.h>
-#include <regex.h>
-#include <tools/le_byteshift.h>
-
-static void die(char *fmt, ...);
-
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-static Elf32_Ehdr ehdr;
-static unsigned long reloc_count, reloc_idx;
-static unsigned long *relocs;
-static unsigned long reloc16_count, reloc16_idx;
-static unsigned long *relocs16;
+/* This is included from relocs_32/64.c */
+
+#define ElfW(type)              _ElfW(ELF_BITS, type)
+#define _ElfW(bits, type)       __ElfW(bits, type)
+#define __ElfW(bits, type)      Elf##bits##_##type
+
+#define Elf_Addr                ElfW(Addr)
+#define Elf_Ehdr                ElfW(Ehdr)
+#define Elf_Phdr                ElfW(Phdr)
+#define Elf_Shdr                ElfW(Shdr)
+#define Elf_Sym                 ElfW(Sym)
+
+static Elf_Ehdr ehdr;
+
+struct relocs {
+        uint32_t        *offset;
+        unsigned long   count;
+        unsigned long   size;
+};
+
+static struct relocs relocs16;
+static struct relocs relocs32;
+static struct relocs relocs64;
 
 struct section {
-        Elf32_Shdr     shdr;
+        Elf_Shdr       shdr;
         struct section *link;
-        Elf32_Sym      *symtab;
-        Elf32_Rel      *reltab;
+        Elf_Sym        *symtab;
+        Elf_Rel        *reltab;
         char           *strtab;
 };
 static struct section *secs;
 
-enum symtype {
-        S_ABS,
-        S_REL,
-        S_SEG,
-        S_LIN,
-        S_NSYMTYPES
-};
-
 static const char * const sym_regex_kernel[S_NSYMTYPES] = {
 /*
  * Following symbols have been audited. There values are constant and do
@@ -49,6 +42,9 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
         "^(xen_irq_disable_direct_reloc$|"
         "xen_save_fl_direct_reloc$|"
         "VDSO|"
+#if ELF_BITS == 64
+        "__vvar_page|"
+#endif
         "__crc_)",
 
 /*
@@ -72,6 +68,11 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
         "__end_rodata|"
         "__initramfs_start|"
         "(jiffies|jiffies_64)|"
+#if ELF_BITS == 64
+        "__per_cpu_load|"
+        "init_per_cpu__.*|"
+        "__end_rodata_hpage_align|"
+#endif
         "_end)$"
 };
 
@@ -132,15 +133,6 @@ static void regex_init(int use_real_mode)
         }
 }
 
-static void die(char *fmt, ...)
-{
-        va_list ap;
-        va_start(ap, fmt);
-        vfprintf(stderr, fmt, ap);
-        va_end(ap);
-        exit(1);
-}
-
 static const char *sym_type(unsigned type)
 {
         static const char *type_name[] = {
@@ -198,6 +190,24 @@ static const char *rel_type(unsigned type)
 {
         static const char *type_name[] = {
 #define REL_TYPE(X) [X] = #X
+#if ELF_BITS == 64
+                REL_TYPE(R_X86_64_NONE),
+                REL_TYPE(R_X86_64_64),
+                REL_TYPE(R_X86_64_PC32),
+                REL_TYPE(R_X86_64_GOT32),
+                REL_TYPE(R_X86_64_PLT32),
+                REL_TYPE(R_X86_64_COPY),
+                REL_TYPE(R_X86_64_GLOB_DAT),
+                REL_TYPE(R_X86_64_JUMP_SLOT),
+                REL_TYPE(R_X86_64_RELATIVE),
+                REL_TYPE(R_X86_64_GOTPCREL),
+                REL_TYPE(R_X86_64_32),
+                REL_TYPE(R_X86_64_32S),
+                REL_TYPE(R_X86_64_16),
+                REL_TYPE(R_X86_64_PC16),
+                REL_TYPE(R_X86_64_8),
+                REL_TYPE(R_X86_64_PC8),
+#else
                 REL_TYPE(R_386_NONE),
                 REL_TYPE(R_386_32),
                 REL_TYPE(R_386_PC32),
@@ -213,6 +223,7 @@ static const char *rel_type(unsigned type)
                 REL_TYPE(R_386_PC8),
                 REL_TYPE(R_386_16),
                 REL_TYPE(R_386_PC16),
+#endif
 #undef REL_TYPE
         };
         const char *name = "unknown type rel type name";
@@ -240,7 +251,7 @@ static const char *sec_name(unsigned shndx)
         return name;
 }
 
-static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym)
+static const char *sym_name(const char *sym_strtab, Elf_Sym *sym)
 {
         const char *name;
         name = "<noname>";
@@ -253,15 +264,42 @@ static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym)
         return name;
 }
 
+static Elf_Sym *sym_lookup(const char *symname)
+{
+        int i;
+        for (i = 0; i < ehdr.e_shnum; i++) {
+                struct section *sec = &secs[i];
+                long nsyms;
+                char *strtab;
+                Elf_Sym *symtab;
+                Elf_Sym *sym;
+
+                if (sec->shdr.sh_type != SHT_SYMTAB)
+                        continue;
 
+                nsyms = sec->shdr.sh_size/sizeof(Elf_Sym);
+                symtab = sec->symtab;
+                strtab = sec->link->strtab;
+
+                for (sym = symtab; --nsyms >= 0; sym++) {
+                        if (!sym->st_name)
+                                continue;
+                        if (strcmp(symname, strtab + sym->st_name) == 0)
+                                return sym;
+                }
+        }
+        return 0;
+}
 
 #if BYTE_ORDER == LITTLE_ENDIAN
 #define le16_to_cpu(val) (val)
 #define le32_to_cpu(val) (val)
+#define le64_to_cpu(val) (val)
 #endif
 #if BYTE_ORDER == BIG_ENDIAN
 #define le16_to_cpu(val) bswap_16(val)
 #define le32_to_cpu(val) bswap_32(val)
+#define le64_to_cpu(val) bswap_64(val)
 #endif
 
 static uint16_t elf16_to_cpu(uint16_t val)
@@ -274,6 +312,23 @@ static uint32_t elf32_to_cpu(uint32_t val)
         return le32_to_cpu(val);
 }
 
+#define elf_half_to_cpu(x)      elf16_to_cpu(x)
+#define elf_word_to_cpu(x)      elf32_to_cpu(x)
+
+#if ELF_BITS == 64
+static uint64_t elf64_to_cpu(uint64_t val)
+{
+        return le64_to_cpu(val);
+}
+#define elf_addr_to_cpu(x)      elf64_to_cpu(x)
+#define elf_off_to_cpu(x)       elf64_to_cpu(x)
+#define elf_xword_to_cpu(x)     elf64_to_cpu(x)
+#else
+#define elf_addr_to_cpu(x)      elf32_to_cpu(x)
+#define elf_off_to_cpu(x)       elf32_to_cpu(x)
+#define elf_xword_to_cpu(x)     elf32_to_cpu(x)
+#endif
+
 static void read_ehdr(FILE *fp)
 {
         if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) {
@@ -283,8 +338,8 @@ static void read_ehdr(FILE *fp)
         if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0) {
                 die("No ELF magic\n");
         }
-        if (ehdr.e_ident[EI_CLASS] != ELFCLASS32) {
-                die("Not a 32 bit executable\n");
+        if (ehdr.e_ident[EI_CLASS] != ELF_CLASS) {
+                die("Not a %d bit executable\n", ELF_BITS);
         }
         if (ehdr.e_ident[EI_DATA] != ELFDATA2LSB) {
                 die("Not a LSB ELF executable\n");
@@ -293,36 +348,36 @@ static void read_ehdr(FILE *fp)
                 die("Unknown ELF version\n");
         }
         /* Convert the fields to native endian */
-        ehdr.e_type      = elf16_to_cpu(ehdr.e_type);
-        ehdr.e_machine   = elf16_to_cpu(ehdr.e_machine);
-        ehdr.e_version   = elf32_to_cpu(ehdr.e_version);
-        ehdr.e_entry     = elf32_to_cpu(ehdr.e_entry);
-        ehdr.e_phoff     = elf32_to_cpu(ehdr.e_phoff);
-        ehdr.e_shoff     = elf32_to_cpu(ehdr.e_shoff);
-        ehdr.e_flags     = elf32_to_cpu(ehdr.e_flags);
-        ehdr.e_ehsize    = elf16_to_cpu(ehdr.e_ehsize);
-        ehdr.e_phentsize = elf16_to_cpu(ehdr.e_phentsize);
-        ehdr.e_phnum     = elf16_to_cpu(ehdr.e_phnum);
-        ehdr.e_shentsize = elf16_to_cpu(ehdr.e_shentsize);
-        ehdr.e_shnum     = elf16_to_cpu(ehdr.e_shnum);
-        ehdr.e_shstrndx  = elf16_to_cpu(ehdr.e_shstrndx);
+        ehdr.e_type      = elf_half_to_cpu(ehdr.e_type);
+        ehdr.e_machine   = elf_half_to_cpu(ehdr.e_machine);
+        ehdr.e_version   = elf_word_to_cpu(ehdr.e_version);
+        ehdr.e_entry     = elf_addr_to_cpu(ehdr.e_entry);
+        ehdr.e_phoff     = elf_off_to_cpu(ehdr.e_phoff);
+        ehdr.e_shoff     = elf_off_to_cpu(ehdr.e_shoff);
+        ehdr.e_flags     = elf_word_to_cpu(ehdr.e_flags);
+        ehdr.e_ehsize    = elf_half_to_cpu(ehdr.e_ehsize);
+        ehdr.e_phentsize = elf_half_to_cpu(ehdr.e_phentsize);
+        ehdr.e_phnum     = elf_half_to_cpu(ehdr.e_phnum);
+        ehdr.e_shentsize = elf_half_to_cpu(ehdr.e_shentsize);
+        ehdr.e_shnum     = elf_half_to_cpu(ehdr.e_shnum);
+        ehdr.e_shstrndx  = elf_half_to_cpu(ehdr.e_shstrndx);
 
         if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN)) {
                 die("Unsupported ELF header type\n");
         }
-        if (ehdr.e_machine != EM_386) {
-                die("Not for x86\n");
+        if (ehdr.e_machine != ELF_MACHINE) {
+                die("Not for %s\n", ELF_MACHINE_NAME);
         }
         if (ehdr.e_version != EV_CURRENT) {
                 die("Unknown ELF version\n");
         }
-        if (ehdr.e_ehsize != sizeof(Elf32_Ehdr)) {
+        if (ehdr.e_ehsize != sizeof(Elf_Ehdr)) {
                 die("Bad Elf header size\n");
         }
-        if (ehdr.e_phentsize != sizeof(Elf32_Phdr)) {
+        if (ehdr.e_phentsize != sizeof(Elf_Phdr)) {
                 die("Bad program header entry\n");
         }
-        if (ehdr.e_shentsize != sizeof(Elf32_Shdr)) {
+        if (ehdr.e_shentsize != sizeof(Elf_Shdr)) {
                 die("Bad section header entry\n");
         }
         if (ehdr.e_shstrndx >= ehdr.e_shnum) {
@@ -333,7 +388,7 @@ static void read_ehdr(FILE *fp)
 static void read_shdrs(FILE *fp)
 {
         int i;
-        Elf32_Shdr shdr;
+        Elf_Shdr shdr;
 
         secs = calloc(ehdr.e_shnum, sizeof(struct section));
         if (!secs) {
@@ -349,16 +404,16 @@ static void read_shdrs(FILE *fp)
                 if (fread(&shdr, sizeof shdr, 1, fp) != 1)
                         die("Cannot read ELF section headers %d/%d: %s\n",
                             i, ehdr.e_shnum, strerror(errno));
-                sec->shdr.sh_name      = elf32_to_cpu(shdr.sh_name);
-                sec->shdr.sh_type      = elf32_to_cpu(shdr.sh_type);
-                sec->shdr.sh_flags     = elf32_to_cpu(shdr.sh_flags);
-                sec->shdr.sh_addr      = elf32_to_cpu(shdr.sh_addr);
-                sec->shdr.sh_offset    = elf32_to_cpu(shdr.sh_offset);
-                sec->shdr.sh_size      = elf32_to_cpu(shdr.sh_size);
-                sec->shdr.sh_link      = elf32_to_cpu(shdr.sh_link);
-                sec->shdr.sh_info      = elf32_to_cpu(shdr.sh_info);
-                sec->shdr.sh_addralign = elf32_to_cpu(shdr.sh_addralign);
-                sec->shdr.sh_entsize   = elf32_to_cpu(shdr.sh_entsize);
+                sec->shdr.sh_name      = elf_word_to_cpu(shdr.sh_name);
+                sec->shdr.sh_type      = elf_word_to_cpu(shdr.sh_type);
+                sec->shdr.sh_flags     = elf_xword_to_cpu(shdr.sh_flags);
+                sec->shdr.sh_addr      = elf_addr_to_cpu(shdr.sh_addr);
+                sec->shdr.sh_offset    = elf_off_to_cpu(shdr.sh_offset);
+                sec->shdr.sh_size      = elf_xword_to_cpu(shdr.sh_size);
+                sec->shdr.sh_link      = elf_word_to_cpu(shdr.sh_link);
+                sec->shdr.sh_info      = elf_word_to_cpu(shdr.sh_info);
+                sec->shdr.sh_addralign = elf_xword_to_cpu(shdr.sh_addralign);
+                sec->shdr.sh_entsize   = elf_xword_to_cpu(shdr.sh_entsize);
                 if (sec->shdr.sh_link < ehdr.e_shnum)
                         sec->link = &secs[sec->shdr.sh_link];
         }
@@ -412,12 +467,12 @@ static void read_symtabs(FILE *fp)
                         die("Cannot read symbol table: %s\n",
                                 strerror(errno));
                 }
-                for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) {
-                        Elf32_Sym *sym = &sec->symtab[j];
-                        sym->st_name  = elf32_to_cpu(sym->st_name);
-                        sym->st_value = elf32_to_cpu(sym->st_value);
-                        sym->st_size  = elf32_to_cpu(sym->st_size);
-                        sym->st_shndx = elf16_to_cpu(sym->st_shndx);
+                for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Sym); j++) {
+                        Elf_Sym *sym = &sec->symtab[j];
+                        sym->st_name  = elf_word_to_cpu(sym->st_name);
+                        sym->st_value = elf_addr_to_cpu(sym->st_value);
+                        sym->st_size  = elf_xword_to_cpu(sym->st_size);
+                        sym->st_shndx = elf_half_to_cpu(sym->st_shndx);
                 }
         }
 }
@@ -428,7 +483,7 @@ static void read_relocs(FILE *fp)
         int i,j;
         for (i = 0; i < ehdr.e_shnum; i++) {
                 struct section *sec = &secs[i];
-                if (sec->shdr.sh_type != SHT_REL) {
+                if (sec->shdr.sh_type != SHT_REL_TYPE) {
                         continue;
                 }
                 sec->reltab = malloc(sec->shdr.sh_size);
@@ -445,10 +500,13 @@ static void read_relocs(FILE *fp)
                         die("Cannot read symbol table: %s\n",
                                 strerror(errno));
                 }
-                for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) {
-                        Elf32_Rel *rel = &sec->reltab[j];
-                        rel->r_offset = elf32_to_cpu(rel->r_offset);
-                        rel->r_info   = elf32_to_cpu(rel->r_info);
+                for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) {
+                        Elf_Rel *rel = &sec->reltab[j];
+                        rel->r_offset = elf_addr_to_cpu(rel->r_offset);
+                        rel->r_info   = elf_xword_to_cpu(rel->r_info);
+#if (SHT_REL_TYPE == SHT_RELA)
+                        rel->r_addend = elf_xword_to_cpu(rel->r_addend);
+#endif
                 }
         }
 }
@@ -457,6 +515,13 @@ static void read_relocs(FILE *fp)
 static void print_absolute_symbols(void)
 {
         int i;
+        const char *format;
+
+        if (ELF_BITS == 64)
+                format = "%5d %016"PRIx64" %5"PRId64" %10s %10s %12s %s\n";
+        else
+                format = "%5d %08"PRIx32"  %5"PRId32" %10s %10s %12s %s\n";
+
         printf("Absolute symbols\n");
         printf(" Num:    Value Size  Type       Bind        Visibility  Name\n");
         for (i = 0; i < ehdr.e_shnum; i++) {
@@ -468,19 +533,19 @@ static void print_absolute_symbols(void)
                         continue;
                 }
                 sym_strtab = sec->link->strtab;
-                for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) {
-                        Elf32_Sym *sym;
+                for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Sym); j++) {
+                        Elf_Sym *sym;
                         const char *name;
                         sym = &sec->symtab[j];
                         name = sym_name(sym_strtab, sym);
                         if (sym->st_shndx != SHN_ABS) {
                                 continue;
                         }
-                        printf("%5d %08x %5d %10s %10s %12s %s\n",
+                        printf(format,
                                 j, sym->st_value, sym->st_size,
-                                sym_type(ELF32_ST_TYPE(sym->st_info)),
-                                sym_bind(ELF32_ST_BIND(sym->st_info)),
-                                sym_visibility(ELF32_ST_VISIBILITY(sym->st_other)),
+                                sym_type(ELF_ST_TYPE(sym->st_info)),
+                                sym_bind(ELF_ST_BIND(sym->st_info)),
+                                sym_visibility(ELF_ST_VISIBILITY(sym->st_other)),
                                 name);
                 }
         }
@@ -490,14 +555,20 @@ static void print_absolute_symbols(void)
 static void print_absolute_relocs(void)
 {
         int i, printed = 0;
+        const char *format;
+
+        if (ELF_BITS == 64)
+                format = "%016"PRIx64" %016"PRIx64" %10s %016"PRIx64"  %s\n";
+        else
+                format = "%08"PRIx32" %08"PRIx32" %10s %08"PRIx32"  %s\n";
 
         for (i = 0; i < ehdr.e_shnum; i++) {
                 struct section *sec = &secs[i];
                 struct section *sec_applies, *sec_symtab;
                 char *sym_strtab;
-                Elf32_Sym *sh_symtab;
+                Elf_Sym *sh_symtab;
                 int j;
-                if (sec->shdr.sh_type != SHT_REL) {
+                if (sec->shdr.sh_type != SHT_REL_TYPE) {
                         continue;
                 }
                 sec_symtab  = sec->link;
@@ -507,12 +578,12 @@ static void print_absolute_relocs(void)
                 }
                 sh_symtab  = sec_symtab->symtab;
                 sym_strtab = sec_symtab->link->strtab;
-                for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) {
-                        Elf32_Rel *rel;
-                        Elf32_Sym *sym;
+                for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) {
+                        Elf_Rel *rel;
+                        Elf_Sym *sym;
                         const char *name;
                         rel = &sec->reltab[j];
-                        sym = &sh_symtab[ELF32_R_SYM(rel->r_info)];
+                        sym = &sh_symtab[ELF_R_SYM(rel->r_info)];
                         name = sym_name(sym_strtab, sym);
                         if (sym->st_shndx != SHN_ABS) {
                                 continue;
@@ -542,10 +613,10 @@ static void print_absolute_relocs(void)
                                 printed = 1;
                         }
 
-                        printf("%08x %08x %10s %08x  %s\n",
+                        printf(format,
                                 rel->r_offset,
                                 rel->r_info,
-                                rel_type(ELF32_R_TYPE(rel->r_info)),
+                                rel_type(ELF_R_TYPE(rel->r_info)),
                                 sym->st_value,
                                 name);
                 }
@@ -555,19 +626,34 @@ static void print_absolute_relocs(void)
                 printf("\n");
 }
 
-static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym),
-                        int use_real_mode)
+static void add_reloc(struct relocs *r, uint32_t offset)
+{
+        if (r->count == r->size) {
+                unsigned long newsize = r->size + 50000;
+                void *mem = realloc(r->offset, newsize * sizeof(r->offset[0]));
+
+                if (!mem)
+                        die("realloc of %ld entries for relocs failed\n",
+                                newsize);
+                r->offset = mem;
+                r->size = newsize;
+        }
+        r->offset[r->count++] = offset;
+}
+
+static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
+                        Elf_Sym *sym, const char *symname))
 {
         int i;
         /* Walk through the relocations */
         for (i = 0; i < ehdr.e_shnum; i++) {
                 char *sym_strtab;
-                Elf32_Sym *sh_symtab;
+                Elf_Sym *sh_symtab;
                 struct section *sec_applies, *sec_symtab;
                 int j;
                 struct section *sec = &secs[i];
 
-                if (sec->shdr.sh_type != SHT_REL) {
+                if (sec->shdr.sh_type != SHT_REL_TYPE) {
                         continue;
                 }
                 sec_symtab  = sec->link;
@@ -577,101 +663,281 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym),
                 }
                 sh_symtab = sec_symtab->symtab;
                 sym_strtab = sec_symtab->link->strtab;
-                for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) {
-                        Elf32_Rel *rel;
-                        Elf32_Sym *sym;
-                        unsigned r_type;
-                        const char *symname;
-                        int shn_abs;
+                for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) {
+                        Elf_Rel *rel = &sec->reltab[j];
+                        Elf_Sym *sym = &sh_symtab[ELF_R_SYM(rel->r_info)];
+                        const char *symname = sym_name(sym_strtab, sym);
 
-                        rel = &sec->reltab[j];
-                        sym = &sh_symtab[ELF32_R_SYM(rel->r_info)];
-                        r_type = ELF32_R_TYPE(rel->r_info);
-
-                        shn_abs = sym->st_shndx == SHN_ABS;
-
-                        switch (r_type) {
-                        case R_386_NONE:
-                        case R_386_PC32:
-                        case R_386_PC16:
-                        case R_386_PC8:
-                                /*
-                                 * NONE can be ignored and and PC relative
-                                 * relocations don't need to be adjusted.
-                                 */
-                                break;
+                        process(sec, rel, sym, symname);
+                }
+        }
+}
 
-                        case R_386_16:
-                                symname = sym_name(sym_strtab, sym);
-                                if (!use_real_mode)
-                                        goto bad;
-                                if (shn_abs) {
-                                        if (is_reloc(S_ABS, symname))
-                                                break;
-                                        else if (!is_reloc(S_SEG, symname))
-                                                goto bad;
-                                } else {
-                                        if (is_reloc(S_LIN, symname))
-                                                goto bad;
-                                        else
-                                                break;
-                                }
-                                visit(rel, sym);
-                                break;
+/*
+ * The .data..percpu section is a special case for x86_64 SMP kernels.
+ * It is used to initialize the actual per_cpu areas and to provide
+ * definitions for the per_cpu variables that correspond to their offsets
+ * within the percpu area. Since the values of all of the symbols need
+ * to be offsets from the start of the per_cpu area the virtual address
+ * (sh_addr) of .data..percpu is 0 in SMP kernels.
+ *
+ * This means that:
+ *
+ *      Relocations that reference symbols in the per_cpu area do not
+ *      need further relocation (since the value is an offset relative
+ *      to the start of the per_cpu area that does not change).
+ *
+ *      Relocations that apply to the per_cpu area need to have their
+ *      offset adjusted by by the value of __per_cpu_load to make them
+ *      point to the correct place in the loaded image (because the
+ *      virtual address of .data..percpu is 0).
+ *
+ * For non SMP kernels .data..percpu is linked as part of the normal
+ * kernel data and does not require special treatment.
+ *
+ */
+static int per_cpu_shndx        = -1;
+Elf_Addr per_cpu_load_addr;
 
-                        case R_386_32:
-                                symname = sym_name(sym_strtab, sym);
-                                if (shn_abs) {
-                                        if (is_reloc(S_ABS, symname))
-                                                break;
-                                        else if (!is_reloc(S_REL, symname))
-                                                goto bad;
-                                } else {
-                                        if (use_real_mode &&
-                                            !is_reloc(S_LIN, symname))
-                                                break;
-                                }
-                                visit(rel, sym);
-                                break;
-                        default:
-                                die("Unsupported relocation type: %s (%d)\n",
-                                    rel_type(r_type), r_type);
+static void percpu_init(void)
+{
+        int i;
+        for (i = 0; i < ehdr.e_shnum; i++) {
+                ElfW(Sym) *sym;
+                if (strcmp(sec_name(i), ".data..percpu"))
+                        continue;
+
+                if (secs[i].shdr.sh_addr != 0)  /* non SMP kernel */
+                        return;
+
+                sym = sym_lookup("__per_cpu_load");
+                if (!sym)
+                        die("can't find __per_cpu_load\n");
+
+                per_cpu_shndx = i;
+                per_cpu_load_addr = sym->st_value;
+                return;
+        }
+}
+
+#if ELF_BITS == 64
+
+/*
+ * Check to see if a symbol lies in the .data..percpu section.
+ * For some as yet not understood reason the "__init_begin"
+ * symbol which immediately preceeds the .data..percpu section
+ * also shows up as it it were part of it so we do an explict
+ * check for that symbol name and ignore it.
+ */
+static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
+{
+        return (sym->st_shndx == per_cpu_shndx) &&
+                strcmp(symname, "__init_begin");
+}
+
+
+static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
+                      const char *symname)
+{
+        unsigned r_type = ELF64_R_TYPE(rel->r_info);
+        ElfW(Addr) offset = rel->r_offset;
+        int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname);
+
+        if (sym->st_shndx == SHN_UNDEF)
+                return 0;
+
+        /*
+         * Adjust the offset if this reloc applies to the percpu section.
+         */
+        if (sec->shdr.sh_info == per_cpu_shndx)
+                offset += per_cpu_load_addr;
+
+        switch (r_type) {
+        case R_X86_64_NONE:
+        case R_X86_64_PC32:
+                /*
+                 * NONE can be ignored and PC relative relocations don't
+                 * need to be adjusted.
+                 */
+                break;
+
+        case R_X86_64_32:
+        case R_X86_64_32S:
+        case R_X86_64_64:
+                /*
+                 * References to the percpu area don't need to be adjusted.
+                 */
+                if (is_percpu_sym(sym, symname))
+                        break;
+
+                if (shn_abs) {
+                        /*
+                         * Whitelisted absolute symbols do not require
+                         * relocation.
+                         */
+                        if (is_reloc(S_ABS, symname))
                                 break;
-                        bad:
-                                symname = sym_name(sym_strtab, sym);
-                                die("Invalid %s %s relocation: %s\n",
-                                    shn_abs ? "absolute" : "relative",
-                                    rel_type(r_type), symname);
-                        }
+
+                        die("Invalid absolute %s relocation: %s\n",
+                            rel_type(r_type), symname);
+                        break;
                 }
+
+                /*
+                 * Relocation offsets for 64 bit kernels are output
+                 * as 32 bits and sign extended back to 64 bits when
+                 * the relocations are processed.
+                 * Make sure that the offset will fit.
+                 */
+                if ((int32_t)offset != (int64_t)offset)
+                        die("Relocation offset doesn't fit in 32 bits\n");
+
+                if (r_type == R_X86_64_64)
+                        add_reloc(&relocs64, offset);
+                else
+                        add_reloc(&relocs32, offset);
+                break;
+
+        default:
+                die("Unsupported relocation type: %s (%d)\n",
+                    rel_type(r_type), r_type);
+                break;
         }
+
+        return 0;
 }
 
-static void count_reloc(Elf32_Rel *rel, Elf32_Sym *sym)
+#else
+
+static int do_reloc32(struct section *sec, Elf_Rel *rel, Elf_Sym *sym,
+                      const char *symname)
 {
-        if (ELF32_R_TYPE(rel->r_info) == R_386_16)
-                reloc16_count++;
-        else
-                reloc_count++;
+        unsigned r_type = ELF32_R_TYPE(rel->r_info);
+        int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname);
+
+        switch (r_type) {
+        case R_386_NONE:
+        case R_386_PC32:
+        case R_386_PC16:
+        case R_386_PC8:
+                /*
+                 * NONE can be ignored and PC relative relocations don't
+                 * need to be adjusted.
+                 */
+                break;
+
+        case R_386_32:
+                if (shn_abs) {
+                        /*
+                         * Whitelisted absolute symbols do not require
+                         * relocation.
+                         */
+                        if (is_reloc(S_ABS, symname))
+                                break;
+
+                        die("Invalid absolute %s relocation: %s\n",
+                            rel_type(r_type), symname);
+                        break;
+                }
+
+                add_reloc(&relocs32, rel->r_offset);
+                break;
+
+        default:
+                die("Unsupported relocation type: %s (%d)\n",
+                    rel_type(r_type), r_type);
+                break;
+        }
+
+        return 0;
 }
 
-static void collect_reloc(Elf32_Rel *rel, Elf32_Sym *sym)
+static int do_reloc_real(struct section *sec, Elf_Rel *rel, Elf_Sym *sym,
+                         const char *symname)
 {
-        /* Remember the address that needs to be adjusted. */
-        if (ELF32_R_TYPE(rel->r_info) == R_386_16)
-                relocs16[reloc16_idx++] = rel->r_offset;
-        else
-                relocs[reloc_idx++] = rel->r_offset;
+        unsigned r_type = ELF32_R_TYPE(rel->r_info);
+        int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname);
+
+        switch (r_type) {
+        case R_386_NONE:
+        case R_386_PC32:
+        case R_386_PC16:
+        case R_386_PC8:
+                /*
+                 * NONE can be ignored and PC relative relocations don't
+                 * need to be adjusted.
+                 */
+                break;
+
+        case R_386_16:
+                if (shn_abs) {
+                        /*
+                         * Whitelisted absolute symbols do not require
+                         * relocation.
+                         */
+                        if (is_reloc(S_ABS, symname))
+                                break;
+
+                        if (is_reloc(S_SEG, symname)) {
+                                add_reloc(&relocs16, rel->r_offset);
+                                break;
+                        }
+                } else {
+                        if (!is_reloc(S_LIN, symname))
+                                break;
+                }
+                die("Invalid %s %s relocation: %s\n",
+                    shn_abs ? "absolute" : "relative",
+                    rel_type(r_type), symname);
+                break;
+
+        case R_386_32:
+                if (shn_abs) {
+                        /*
+                         * Whitelisted absolute symbols do not require
+                         * relocation.
+                         */
+                        if (is_reloc(S_ABS, symname))
+                                break;
+
+                        if (is_reloc(S_REL, symname)) {
+                                add_reloc(&relocs32, rel->r_offset);
+                                break;
+                        }
+                } else {
+                        if (is_reloc(S_LIN, symname))
+                                add_reloc(&relocs32, rel->r_offset);
+                        break;
+                }
+                die("Invalid %s %s relocation: %s\n",
+                    shn_abs ? "absolute" : "relative",
+                    rel_type(r_type), symname);
+                break;
+
+        default:
+                die("Unsupported relocation type: %s (%d)\n",
+                    rel_type(r_type), r_type);
+                break;
+        }
+
+        return 0;
 }
 
+#endif
+
 static int cmp_relocs(const void *va, const void *vb)
 {
-        const unsigned long *a, *b;
+        const uint32_t *a, *b;
         a = va; b = vb;
         return (*a == *b)? 0 : (*a > *b)? 1 : -1;
 }
 
-static int write32(unsigned int v, FILE *f)
+static void sort_relocs(struct relocs *r)
+{
+        qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
+}
+
+static int write32(uint32_t v, FILE *f)
 {
         unsigned char buf[4];
 
@@ -679,33 +945,40 @@ static int write32(unsigned int v, FILE *f)
         return fwrite(buf, 1, 4, f) == 4 ? 0 : -1;
 }
 
+static int write32_as_text(uint32_t v, FILE *f)
+{
+        return fprintf(f, "\t.long 0x%08"PRIx32"\n", v) > 0 ? 0 : -1;
+}
+
 static void emit_relocs(int as_text, int use_real_mode)
 {
         int i;
-        /* Count how many relocations I have and allocate space for them. */
-        reloc_count = 0;
-        walk_relocs(count_reloc, use_real_mode);
-        relocs = malloc(reloc_count * sizeof(relocs[0]));
-        if (!relocs) {
-                die("malloc of %d entries for relocs failed\n",
-                        reloc_count);
-        }
+        int (*write_reloc)(uint32_t, FILE *) = write32;
+        int (*do_reloc)(struct section *sec, Elf_Rel *rel, Elf_Sym *sym,
+                        const char *symname);
+
+#if ELF_BITS == 64
+        if (!use_real_mode)
+                do_reloc = do_reloc64;
+        else
+                die("--realmode not valid for a 64-bit ELF file");
+#else
+        if (!use_real_mode)
+                do_reloc = do_reloc32;
+        else
+                do_reloc = do_reloc_real;
+#endif
 
-        relocs16 = malloc(reloc16_count * sizeof(relocs[0]));
-        if (!relocs16) {
-                die("malloc of %d entries for relocs16 failed\n",
-                        reloc16_count);
-        }
         /* Collect up the relocations */
-        reloc_idx = 0;
-        walk_relocs(collect_reloc, use_real_mode);
+        walk_relocs(do_reloc);
 
-        if (reloc16_count && !use_real_mode)
+        if (relocs16.count && !use_real_mode)
                 die("Segment relocations found but --realmode not specified\n");
 
         /* Order the relocations for more efficient processing */
-        qsort(relocs, reloc_count, sizeof(relocs[0]), cmp_relocs);
-        qsort(relocs16, reloc16_count, sizeof(relocs16[0]), cmp_relocs);
+        sort_relocs(&relocs16);
+        sort_relocs(&relocs32);
+        sort_relocs(&relocs64);
 
         /* Print the relocations */
         if (as_text) {
@@ -714,114 +987,60 @@ static void emit_relocs(int as_text, int use_real_mode)
                  */
                 printf(".section \".data.reloc\",\"a\"\n");
                 printf(".balign 4\n");
-                if (use_real_mode) {
-                        printf("\t.long %lu\n", reloc16_count);
-                        for (i = 0; i < reloc16_count; i++)
-                                printf("\t.long 0x%08lx\n", relocs16[i]);
-                        printf("\t.long %lu\n", reloc_count);
-                        for (i = 0; i < reloc_count; i++) {
-                                printf("\t.long 0x%08lx\n", relocs[i]);
-                        }
-                } else {
-                        /* Print a stop */
-                        printf("\t.long 0x%08lx\n", (unsigned long)0);
-                        for (i = 0; i < reloc_count; i++) {
-                                printf("\t.long 0x%08lx\n", relocs[i]);
-                        }
-                }
-
-                printf("\n");
+                write_reloc = write32_as_text;
         }
-        else {
-                if (use_real_mode) {
-                        write32(reloc16_count, stdout);
-                        for (i = 0; i < reloc16_count; i++)
-                                write32(relocs16[i], stdout);
-                        write32(reloc_count, stdout);
 
-                        /* Now print each relocation */
-                        for (i = 0; i < reloc_count; i++)
-                                write32(relocs[i], stdout);
-                } else {
+        if (use_real_mode) {
+                write_reloc(relocs16.count, stdout);
+                for (i = 0; i < relocs16.count; i++)
+                        write_reloc(relocs16.offset[i], stdout);
+
+                write_reloc(relocs32.count, stdout);
+                for (i = 0; i < relocs32.count; i++)
+                        write_reloc(relocs32.offset[i], stdout);
+        } else {
+                if (ELF_BITS == 64) {
                         /* Print a stop */
-                        write32(0, stdout);
+                        write_reloc(0, stdout);
 
                         /* Now print each relocation */
-                        for (i = 0; i < reloc_count; i++) {
-                                write32(relocs[i], stdout);
-                        }
+                        for (i = 0; i < relocs64.count; i++)
+                                write_reloc(relocs64.offset[i], stdout);
                 }
+
+                /* Print a stop */
+                write_reloc(0, stdout);
+
+                /* Now print each relocation */
+                for (i = 0; i < relocs32.count; i++)
+                        write_reloc(relocs32.offset[i], stdout);
         }
 }
 
-static void usage(void)
-{
-        die("relocs [--abs-syms|--abs-relocs|--text|--realmode] vmlinux\n");
-}
+#if ELF_BITS == 64
+# define process process_64
+#else
+# define process process_32
+#endif
 
-int main(int argc, char **argv)
+void process(FILE *fp, int use_real_mode, int as_text,
+             int show_absolute_syms, int show_absolute_relocs)
 {
-        int show_absolute_syms, show_absolute_relocs;
-        int as_text, use_real_mode;
-        const char *fname;
-        FILE *fp;
-        int i;
-
-        show_absolute_syms = 0;
-        show_absolute_relocs = 0;
-        as_text = 0;
-        use_real_mode = 0;
-        fname = NULL;
-        for (i = 1; i < argc; i++) {
-                char *arg = argv[i];
-                if (*arg == '-') {
-                        if (strcmp(arg, "--abs-syms") == 0) {
-                                show_absolute_syms = 1;
-                                continue;
-                        }
-                        if (strcmp(arg, "--abs-relocs") == 0) {
-                                show_absolute_relocs = 1;
-                                continue;
-                        }
-                        if (strcmp(arg, "--text") == 0) {
-                                as_text = 1;
-                                continue;
-                        }
-                        if (strcmp(arg, "--realmode") == 0) {
-                                use_real_mode = 1;
-                                continue;
-                        }
-                }
-                else if (!fname) {
-                        fname = arg;
-                        continue;
-                }
-                usage();
-        }
-        if (!fname) {
-                usage();
-        }
         regex_init(use_real_mode);
-        fp = fopen(fname, "r");
-        if (!fp) {
-                die("Cannot open %s: %s\n",
-                        fname, strerror(errno));
-        }
         read_ehdr(fp);
         read_shdrs(fp);
         read_strtabs(fp);
         read_symtabs(fp);
         read_relocs(fp);
+        if (ELF_BITS == 64)
+                percpu_init();
         if (show_absolute_syms) {
                 print_absolute_symbols();
-                goto out;
+                return;
         }
         if (show_absolute_relocs) {
                 print_absolute_relocs();
-                goto out;
+                return;
         }
         emit_relocs(as_text, use_real_mode);
-out:
-        fclose(fp);
-        return 0;
 }
diff --git a/arch/x86/tools/relocs.h b/arch/x86/tools/relocs.h
new file mode 100644
index 000000000000..07cdb1eca4fa
--- /dev/null
+++ b/arch/x86/tools/relocs.h
@@ -0,0 +1,36 @@
+#ifndef RELOCS_H
+#define RELOCS_H
+
+#include <stdio.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <inttypes.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <elf.h>
+#include <byteswap.h>
+#define USE_BSD
+#include <endian.h>
+#include <regex.h>
+#include <tools/le_byteshift.h>
+
+void die(char *fmt, ...);
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+enum symtype {
+        S_ABS,
+        S_REL,
+        S_SEG,
+        S_LIN,
+        S_NSYMTYPES
+};
+
+void process_32(FILE *fp, int use_real_mode, int as_text,
+                int show_absolute_syms, int show_absolute_relocs);
+void process_64(FILE *fp, int use_real_mode, int as_text,
+                int show_absolute_syms, int show_absolute_relocs);
+
+#endif /* RELOCS_H */
diff --git a/arch/x86/tools/relocs_32.c b/arch/x86/tools/relocs_32.c
new file mode 100644
index 000000000000..b2ade2bb4162
--- /dev/null
+++ b/arch/x86/tools/relocs_32.c
@@ -0,0 +1,17 @@
+#include "relocs.h"
+
+#define ELF_BITS 32
+
+#define ELF_MACHINE             EM_386
+#define ELF_MACHINE_NAME        "i386"
+#define SHT_REL_TYPE            SHT_REL
+#define Elf_Rel                 ElfW(Rel)
+
+#define ELF_CLASS               ELFCLASS32
+#define ELF_R_SYM(val)          ELF32_R_SYM(val)
+#define ELF_R_TYPE(val)         ELF32_R_TYPE(val)
+#define ELF_ST_TYPE(o)          ELF32_ST_TYPE(o)
+#define ELF_ST_BIND(o)          ELF32_ST_BIND(o)
+#define ELF_ST_VISIBILITY(o)    ELF32_ST_VISIBILITY(o)
+
+#include "relocs.c"
diff --git a/arch/x86/tools/relocs_64.c b/arch/x86/tools/relocs_64.c
new file mode 100644
index 000000000000..56b61b743c4c
--- /dev/null
+++ b/arch/x86/tools/relocs_64.c
@@ -0,0 +1,17 @@
+#include "relocs.h"
+
+#define ELF_BITS 64
+
+#define ELF_MACHINE             EM_X86_64
+#define ELF_MACHINE_NAME        "x86_64"
+#define SHT_REL_TYPE            SHT_RELA
+#define Elf_Rel                 Elf64_Rela
+
+#define ELF_CLASS               ELFCLASS64
+#define ELF_R_SYM(val)          ELF64_R_SYM(val)
+#define ELF_R_TYPE(val)         ELF64_R_TYPE(val)
+#define ELF_ST_TYPE(o)          ELF64_ST_TYPE(o)
+#define ELF_ST_BIND(o)          ELF64_ST_BIND(o)
+#define ELF_ST_VISIBILITY(o)    ELF64_ST_VISIBILITY(o)
+
+#include "relocs.c"
diff --git a/arch/x86/tools/relocs_common.c b/arch/x86/tools/relocs_common.c
new file mode 100644
index 000000000000..44d396823a53
--- /dev/null
+++ b/arch/x86/tools/relocs_common.c
@@ -0,0 +1,76 @@
+#include "relocs.h"
+
+void die(char *fmt, ...)
+{
+        va_list ap;
+        va_start(ap, fmt);
+        vfprintf(stderr, fmt, ap);
+        va_end(ap);
+        exit(1);
+}
+
+static void usage(void)
+{
+        die("relocs [--abs-syms|--abs-relocs|--text|--realmode] vmlinux\n");
+}
+
+int main(int argc, char **argv)
+{
+        int show_absolute_syms, show_absolute_relocs;
+        int as_text, use_real_mode;
+        const char *fname;
+        FILE *fp;
+        int i;
+        unsigned char e_ident[EI_NIDENT];
+
+        show_absolute_syms = 0;
+        show_absolute_relocs = 0;
+        as_text = 0;
+        use_real_mode = 0;
+        fname = NULL;
+        for (i = 1; i < argc; i++) {
+                char *arg = argv[i];
+                if (*arg == '-') {
+                        if (strcmp(arg, "--abs-syms") == 0) {
+                                show_absolute_syms = 1;
+                                continue;
+                        }
+                        if (strcmp(arg, "--abs-relocs") == 0) {
+                                show_absolute_relocs = 1;
+                                continue;
+                        }
+                        if (strcmp(arg, "--text") == 0) {
+                                as_text = 1;
+                                continue;
+                        }
+                        if (strcmp(arg, "--realmode") == 0) {
+                                use_real_mode = 1;
+                                continue;
+                        }
+                }
+                else if (!fname) {
+                        fname = arg;
+                        continue;
+                }
+                usage();
+        }
+        if (!fname) {
+                usage();
+        }
+        fp = fopen(fname, "r");
+        if (!fp) {
+                die("Cannot open %s: %s\n", fname, strerror(errno));
+        }
+        if (fread(&e_ident, 1, EI_NIDENT, fp) != EI_NIDENT) {
+                die("Cannot read %s: %s", fname, strerror(errno));
+        }
+        rewind(fp);
+        if (e_ident[EI_CLASS] == ELFCLASS64)
+                process_64(fp, use_real_mode, as_text,
+                           show_absolute_syms, show_absolute_relocs);
+        else
+                process_32(fp, use_real_mode, as_text,
+                           show_absolute_syms, show_absolute_relocs);
+        fclose(fp);
+        return 0;
+}
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 131dacd2748a..1a3c76505649 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -4,7 +4,7 @@
 
 config XEN
         bool "Xen guest support"
-        select PARAVIRT
+        depends on PARAVIRT
         select PARAVIRT_CLOCK
         select XEN_HAVE_PVMMU
         depends on X86_64 || (X86_32 && X86_PAE && !X86_VISWS)
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c8e1c7b95c3b..53d4f680c9b5 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -31,6 +31,7 @@
 #include <linux/pci.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
+#include <linux/edd.h>
 
 #include <xen/xen.h>
 #include <xen/events.h>
@@ -1220,7 +1221,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
         .alloc_ldt = xen_alloc_ldt,
         .free_ldt = xen_free_ldt,
 
-        .store_gdt = native_store_gdt,
         .store_idt = native_store_idt,
         .store_tr = xen_store_tr,
 
@@ -1306,6 +1306,55 @@ static const struct machine_ops xen_machine_ops __initconst = {
         .emergency_restart = xen_emergency_restart,
 };
 
+static void __init xen_boot_params_init_edd(void)
+{
+#if IS_ENABLED(CONFIG_EDD)
+        struct xen_platform_op op;
+        struct edd_info *edd_info;
+        u32 *mbr_signature;
+        unsigned nr;
+        int ret;
+
+        edd_info = boot_params.eddbuf;
+        mbr_signature = boot_params.edd_mbr_sig_buffer;
+
+        op.cmd = XENPF_firmware_info;
+
+        op.u.firmware_info.type = XEN_FW_DISK_INFO;
+        for (nr = 0; nr < EDDMAXNR; nr++) {
+                struct edd_info *info = edd_info + nr;
+
+                op.u.firmware_info.index = nr;
+                info->params.length = sizeof(info->params);
+                set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params,
+                                     &info->params);
+                ret = HYPERVISOR_dom0_op(&op);
+                if (ret)
+                        break;
+
+#define C(x) info->x = op.u.firmware_info.u.disk_info.x
+                C(device);
+                C(version);
+                C(interface_support);
+                C(legacy_max_cylinder);
+                C(legacy_max_head);
+                C(legacy_sectors_per_track);
+#undef C
+        }
+        boot_params.eddbuf_entries = nr;
+
+        op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE;
+        for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) {
+                op.u.firmware_info.index = nr;
+                ret = HYPERVISOR_dom0_op(&op);
+                if (ret)
+                        break;
+                mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature;
+        }
+        boot_params.edd_mbr_sig_buf_entries = nr;
+#endif
+}
+
 /*
  * Set up the GDT and segment registers for -fstack-protector.  Until
  * we do this, we have to be careful not to call any stack-protected
@@ -1508,6 +1557,8 @@ asmlinkage void __init xen_start_kernel(void)
                 /* Avoid searching for BIOS MP tables */
                 x86_init.mpparse.find_smp_config = x86_init_noop;
                 x86_init.mpparse.get_smp_config = x86_init_uint_noop;
+
+                xen_boot_params_init_edd();
         }
 #ifdef CONFIG_PCI
         /* PCI BIOS service won't work from a PV guest. */
@@ -1589,8 +1640,11 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
         switch (action) {
         case CPU_UP_PREPARE:
                 xen_vcpu_setup(cpu);
-                if (xen_have_vector_callback)
+                if (xen_have_vector_callback) {
                         xen_init_lock_cpu(cpu);
+                        if (xen_feature(XENFEAT_hvm_safe_pvclock))
+                                xen_setup_timer(cpu);
+                }
                 break;
         default:
                 break;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index e8e34938c57d..fdc3ba28ca38 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1467,8 +1467,6 @@ static void __init xen_write_cr3_init(unsigned long cr3)
         __xen_write_cr3(true, cr3);
 
         xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
-
-        pv_mmu_ops.write_cr3 = &xen_write_cr3;
 }
 #endif
 
@@ -1750,14 +1748,18 @@ static void *m2v(phys_addr_t maddr)
 }
 
 /* Set the page permissions on an identity-mapped pages */
-static void set_page_prot(void *addr, pgprot_t prot)
+static void set_page_prot_flags(void *addr, pgprot_t prot, unsigned long flags)
 {
         unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
         pte_t pte = pfn_pte(pfn, prot);
 
-        if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
+        if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags))
                 BUG();
 }
+static void set_page_prot(void *addr, pgprot_t prot)
+{
+        return set_page_prot_flags(addr, prot, UVMF_NONE);
+}
 #ifdef CONFIG_X86_32
 static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 {
@@ -1841,12 +1843,12 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
                                  unsigned long addr)
 {
         if (*pt_base == PFN_DOWN(__pa(addr))) {
-                set_page_prot((void *)addr, PAGE_KERNEL);
+                set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG);
                 clear_page((void *)addr);
                 (*pt_base)++;
         }
         if (*pt_end == PFN_DOWN(__pa(addr))) {
-                set_page_prot((void *)addr, PAGE_KERNEL);
+                set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG);
                 clear_page((void *)addr);
                 (*pt_end)--;
         }
@@ -2041,9 +2043,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 
         switch (idx) {
         case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
-#ifdef CONFIG_X86_F00F_BUG
-        case FIX_F00F_IDT:
-#endif
+        case FIX_RO_IDT:
 #ifdef CONFIG_X86_32
         case FIX_WP_TEST:
         case FIX_VDSO:
@@ -2122,6 +2122,7 @@ static void __init xen_post_allocator_init(void)
 #endif
 
 #ifdef CONFIG_X86_64
+        pv_mmu_ops.write_cr3 = &xen_write_cr3;
         SetPagePinned(virt_to_page(level3_user_vsyscall));
 #endif
         xen_mark_init_mm_pinned();
@@ -2197,6 +2198,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
         .lazy_mode = {
                 .enter = paravirt_enter_lazy_mmu,
                 .leave = xen_leave_lazy_mmu,
+                .flush = paravirt_flush_lazy_mmu,
         },
 
         .set_fixmap = xen_set_fixmap,
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 09ea61d2e02f..8ff37995d54e 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -95,7 +95,7 @@ static void __cpuinit cpu_bringup(void)
 static void __cpuinit cpu_bringup_and_idle(void)
 {
         cpu_bringup();
-        cpu_idle();
+        cpu_startup_entry(CPUHP_ONLINE);
 }
 
 static int xen_smp_intr_init(unsigned int cpu)
@@ -144,6 +144,13 @@ static int xen_smp_intr_init(unsigned int cpu)
                 goto fail;
         per_cpu(xen_callfuncsingle_irq, cpu) = rc;
 
+        /*
+         * The IRQ worker on PVHVM goes through the native path and uses the
+         * IPI mechanism.
+         */
+        if (xen_hvm_domain())
+                return 0;
+
         callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
         rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
                                     cpu,
@@ -167,6 +174,9 @@ static int xen_smp_intr_init(unsigned int cpu)
         if (per_cpu(xen_callfuncsingle_irq, cpu) >= 0)
                 unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu),
                                        NULL);
+        if (xen_hvm_domain())
+                return rc;
+
         if (per_cpu(xen_irq_work, cpu) >= 0)
                 unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
 
@@ -418,7 +428,7 @@ static int xen_cpu_disable(void)
 
 static void xen_cpu_die(unsigned int cpu)
 {
-        while (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) {
+        while (xen_pv_domain() && HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) {
                 current->state = TASK_UNINTERRUPTIBLE;
                 schedule_timeout(HZ/10);
         }
@@ -426,7 +436,8 @@ static void xen_cpu_die(unsigned int cpu)
         unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
         unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
         unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
-        unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
+        if (!xen_hvm_domain())
+                unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
         xen_uninit_lock_cpu(cpu);
         xen_teardown_timer(cpu);
 }
@@ -657,11 +668,7 @@ static int __cpuinit xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
 
 static void xen_hvm_cpu_die(unsigned int cpu)
 {
-        unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
-        unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
-        unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
-        unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
-        unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
+        xen_cpu_die(cpu);
         native_cpu_die(cpu);
 }
 
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index f7a080ef0354..8b54603ce816 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -364,6 +364,16 @@ void __cpuinit xen_init_lock_cpu(int cpu)
         int irq;
         const char *name;
 
+        WARN(per_cpu(lock_kicker_irq, cpu) > 0, "spinlock on CPU%d exists on IRQ%d!\n",
+             cpu, per_cpu(lock_kicker_irq, cpu));
+
+        /*
+         * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
+         * (xen: disable PV spinlocks on HVM)
+         */
+        if (xen_hvm_domain())
+                return;
+
         name = kasprintf(GFP_KERNEL, "spinlock%d", cpu);
         irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR,
                                      cpu,
@@ -382,11 +392,26 @@ void __cpuinit xen_init_lock_cpu(int cpu)
 
 void xen_uninit_lock_cpu(int cpu)
 {
+        /*
+         * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
+         * (xen: disable PV spinlocks on HVM)
+         */
+        if (xen_hvm_domain())
+                return;
+
         unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL);
+        per_cpu(lock_kicker_irq, cpu) = -1;
 }
 
 void __init xen_init_spinlocks(void)
 {
+        /*
+         * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
+         * (xen: disable PV spinlocks on HVM)
+         */
+        if (xen_hvm_domain())
+                return;
+
         BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t));
 
         pv_lock_ops.spin_is_locked = xen_spin_is_locked;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 0296a9522501..3d88bfdf9e1c 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -377,7 +377,7 @@ static const struct clock_event_device xen_vcpuop_clockevent = {
 
 static const struct clock_event_device *xen_clockevent =
         &xen_timerop_clockevent;
-static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events);
+static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events) = { .irq = -1 };
 
 static irqreturn_t xen_timer_interrupt(int irq, void *dev_id)
 {
@@ -401,6 +401,9 @@ void xen_setup_timer(int cpu)
         struct clock_event_device *evt;
         int irq;
 
+        evt = &per_cpu(xen_clock_events, cpu);
+        WARN(evt->irq >= 0, "IRQ%d for CPU%d is already allocated\n", evt->irq, cpu);
+
         printk(KERN_INFO "installing Xen timer for CPU %d\n", cpu);
 
         name = kasprintf(GFP_KERNEL, "timer%d", cpu);
@@ -413,7 +416,6 @@ void xen_setup_timer(int cpu)
                                       IRQF_FORCE_RESUME,
                                       name, NULL);
 
-        evt = &per_cpu(xen_clock_events, cpu);
         memcpy(evt, xen_clockevent, sizeof(*evt));
 
         evt->cpumask = cpumask_of(cpu);
@@ -426,6 +428,7 @@ void xen_teardown_timer(int cpu)
         BUG_ON(cpu == 0);
         evt = &per_cpu(xen_clock_events, cpu);
         unbind_from_irqhandler(evt->irq, NULL);
+        evt->irq = -1;
 }
 
 void xen_setup_cpu_clockevents(void)
@@ -497,7 +500,11 @@ static void xen_hvm_setup_cpu_clockevents(void)
 {
         int cpu = smp_processor_id();
         xen_setup_runstate_info(cpu);
-        xen_setup_timer(cpu);
+        /*
+         * xen_setup_timer(cpu) - snprintf is bad in atomic context. Hence
+         * doing it xen_hvm_cpu_notify (which gets called by smp_init during
+         * early bootup and also during CPU hotplug events).
+         */
         xen_setup_cpu_clockevents();
 }
 
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 35876ffac11d..b09de49dbec5 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -9,7 +9,7 @@ config XTENSA
         select HAVE_IDE
         select GENERIC_ATOMIC64
         select HAVE_GENERIC_HARDIRQS
-        select HAVE_VIRT_TO_BUS
+        select VIRT_TO_BUS
         select GENERIC_IRQ_SHOW
         select GENERIC_CPU_DEVICES
         select MODULES_USE_ELF_RELA
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 5cd82e9f601c..1c85323f01d7 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -105,19 +105,9 @@ void coprocessor_flush_all(struct thread_info *ti)
 /*
  * Powermanagement idle function, if any is provided by the platform.
  */
-
-void cpu_idle(void)
+void arch_cpu_idle(void)
 {
-        local_irq_enable();
-
-        /* endless idle loop with no priority at all */
-        while (1) {
-                rcu_idle_enter();
-                while (!need_resched())
-                        platform_idle();
-                rcu_idle_exit();
-                schedule_preempt_disabled();
-        }
+        platform_idle();
 }
 
 /*
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 7a5156ffebb6..bba125b4bb06 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -208,32 +208,17 @@ void __init mem_init(void)
                highmemsize >> 10);
 }
 
-void
-free_reserved_mem(void *start, void *end)
-{
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page((unsigned long)start);
-                totalram_pages++;
-        }
-}
-
 #ifdef CONFIG_BLK_DEV_INITRD
 extern int initrd_is_mapped;
 
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        if (initrd_is_mapped) {
-                free_reserved_mem((void*)start, (void*)end);
-                printk ("Freeing initrd memory: %ldk freed\n",(end-start)>>10);
-        }
+        if (initrd_is_mapped)
+                free_reserved_area(start, end, 0, "initrd");
 }
 #endif
 
 void free_initmem(void)
 {
-        free_reserved_mem(__init_begin, __init_end);
-        printk("Freeing unused kernel memory: %zuk freed\n",
-               (__init_end - __init_begin) >> 10);
+        free_initmem_default(0);
 }